/* Generated by Cython 3.0.8 */ /* BEGIN: Cython Metadata { "distutils": { "depends": [ "curated_tokenizers\\merges.hh" ], "include_dirs": [ "curated_tokenizers" ], "language": "c++", "name": "curated_tokenizers._bbpe", "sources": [ "curated_tokenizers/_bbpe.pyx", "curated_tokenizers/merges.cc" ] }, "module_name": "curated_tokenizers._bbpe" } END: Cython Metadata */ #ifndef PY_SSIZE_T_CLEAN #define PY_SSIZE_T_CLEAN #endif /* PY_SSIZE_T_CLEAN */ #if defined(CYTHON_LIMITED_API) && 0 #ifndef Py_LIMITED_API #if CYTHON_LIMITED_API+0 > 0x03030000 #define Py_LIMITED_API CYTHON_LIMITED_API #else #define Py_LIMITED_API 0x03030000 #endif #endif #endif #include "Python.h" #ifndef Py_PYTHON_H #error Python headers needed to compile C extensions, please install development version of Python. #elif PY_VERSION_HEX < 0x02070000 || (0x03000000 <= PY_VERSION_HEX && PY_VERSION_HEX < 0x03030000) #error Cython requires Python 2.7+ or Python 3.3+. #else #if defined(CYTHON_LIMITED_API) && CYTHON_LIMITED_API #define __PYX_EXTRA_ABI_MODULE_NAME "limited" #else #define __PYX_EXTRA_ABI_MODULE_NAME "" #endif #define CYTHON_ABI "3_0_8" __PYX_EXTRA_ABI_MODULE_NAME #define __PYX_ABI_MODULE_NAME "_cython_" CYTHON_ABI #define __PYX_TYPE_MODULE_PREFIX __PYX_ABI_MODULE_NAME "." #define CYTHON_HEX_VERSION 0x030008F0 #define CYTHON_FUTURE_DIVISION 0 #include #ifndef offsetof #define offsetof(type, member) ( (size_t) & ((type*)0) -> member ) #endif #if !defined(_WIN32) && !defined(WIN32) && !defined(MS_WINDOWS) #ifndef __stdcall #define __stdcall #endif #ifndef __cdecl #define __cdecl #endif #ifndef __fastcall #define __fastcall #endif #endif #ifndef DL_IMPORT #define DL_IMPORT(t) t #endif #ifndef DL_EXPORT #define DL_EXPORT(t) t #endif #define __PYX_COMMA , #ifndef HAVE_LONG_LONG #define HAVE_LONG_LONG #endif #ifndef PY_LONG_LONG #define PY_LONG_LONG LONG_LONG #endif #ifndef Py_HUGE_VAL #define Py_HUGE_VAL HUGE_VAL #endif #define __PYX_LIMITED_VERSION_HEX PY_VERSION_HEX #if defined(GRAALVM_PYTHON) /* For very preliminary testing purposes. Most variables are set the same as PyPy. The existence of this section does not imply that anything works or is even tested */ #define CYTHON_COMPILING_IN_PYPY 0 #define CYTHON_COMPILING_IN_CPYTHON 0 #define CYTHON_COMPILING_IN_LIMITED_API 0 #define CYTHON_COMPILING_IN_GRAAL 1 #define CYTHON_COMPILING_IN_NOGIL 0 #undef CYTHON_USE_TYPE_SLOTS #define CYTHON_USE_TYPE_SLOTS 0 #undef CYTHON_USE_TYPE_SPECS #define CYTHON_USE_TYPE_SPECS 0 #undef CYTHON_USE_PYTYPE_LOOKUP #define CYTHON_USE_PYTYPE_LOOKUP 0 #if PY_VERSION_HEX < 0x03050000 #undef CYTHON_USE_ASYNC_SLOTS #define CYTHON_USE_ASYNC_SLOTS 0 #elif !defined(CYTHON_USE_ASYNC_SLOTS) #define CYTHON_USE_ASYNC_SLOTS 1 #endif #undef CYTHON_USE_PYLIST_INTERNALS #define CYTHON_USE_PYLIST_INTERNALS 0 #undef CYTHON_USE_UNICODE_INTERNALS #define CYTHON_USE_UNICODE_INTERNALS 0 #undef CYTHON_USE_UNICODE_WRITER #define CYTHON_USE_UNICODE_WRITER 0 #undef CYTHON_USE_PYLONG_INTERNALS #define CYTHON_USE_PYLONG_INTERNALS 0 #undef CYTHON_AVOID_BORROWED_REFS #define CYTHON_AVOID_BORROWED_REFS 1 #undef CYTHON_ASSUME_SAFE_MACROS #define CYTHON_ASSUME_SAFE_MACROS 0 #undef CYTHON_UNPACK_METHODS #define CYTHON_UNPACK_METHODS 0 #undef CYTHON_FAST_THREAD_STATE #define CYTHON_FAST_THREAD_STATE 0 #undef CYTHON_FAST_GIL #define CYTHON_FAST_GIL 0 #undef CYTHON_METH_FASTCALL #define CYTHON_METH_FASTCALL 0 #undef CYTHON_FAST_PYCALL #define CYTHON_FAST_PYCALL 0 #ifndef CYTHON_PEP487_INIT_SUBCLASS #define CYTHON_PEP487_INIT_SUBCLASS (PY_MAJOR_VERSION >= 3) #endif #undef CYTHON_PEP489_MULTI_PHASE_INIT #define CYTHON_PEP489_MULTI_PHASE_INIT 1 #undef CYTHON_USE_MODULE_STATE #define CYTHON_USE_MODULE_STATE 0 #undef CYTHON_USE_TP_FINALIZE #define CYTHON_USE_TP_FINALIZE 0 #undef CYTHON_USE_DICT_VERSIONS #define CYTHON_USE_DICT_VERSIONS 0 #undef CYTHON_USE_EXC_INFO_STACK #define CYTHON_USE_EXC_INFO_STACK 0 #ifndef CYTHON_UPDATE_DESCRIPTOR_DOC #define CYTHON_UPDATE_DESCRIPTOR_DOC 0 #endif #elif defined(PYPY_VERSION) #define CYTHON_COMPILING_IN_PYPY 1 #define CYTHON_COMPILING_IN_CPYTHON 0 #define CYTHON_COMPILING_IN_LIMITED_API 0 #define CYTHON_COMPILING_IN_GRAAL 0 #define CYTHON_COMPILING_IN_NOGIL 0 #undef CYTHON_USE_TYPE_SLOTS #define CYTHON_USE_TYPE_SLOTS 0 #ifndef CYTHON_USE_TYPE_SPECS #define CYTHON_USE_TYPE_SPECS 0 #endif #undef CYTHON_USE_PYTYPE_LOOKUP #define CYTHON_USE_PYTYPE_LOOKUP 0 #if PY_VERSION_HEX < 0x03050000 #undef CYTHON_USE_ASYNC_SLOTS #define CYTHON_USE_ASYNC_SLOTS 0 #elif !defined(CYTHON_USE_ASYNC_SLOTS) #define CYTHON_USE_ASYNC_SLOTS 1 #endif #undef CYTHON_USE_PYLIST_INTERNALS #define CYTHON_USE_PYLIST_INTERNALS 0 #undef CYTHON_USE_UNICODE_INTERNALS #define CYTHON_USE_UNICODE_INTERNALS 0 #undef CYTHON_USE_UNICODE_WRITER #define CYTHON_USE_UNICODE_WRITER 0 #undef CYTHON_USE_PYLONG_INTERNALS #define CYTHON_USE_PYLONG_INTERNALS 0 #undef CYTHON_AVOID_BORROWED_REFS #define CYTHON_AVOID_BORROWED_REFS 1 #undef CYTHON_ASSUME_SAFE_MACROS #define CYTHON_ASSUME_SAFE_MACROS 0 #undef CYTHON_UNPACK_METHODS #define CYTHON_UNPACK_METHODS 0 #undef CYTHON_FAST_THREAD_STATE #define CYTHON_FAST_THREAD_STATE 0 #undef CYTHON_FAST_GIL #define CYTHON_FAST_GIL 0 #undef CYTHON_METH_FASTCALL #define CYTHON_METH_FASTCALL 0 #undef CYTHON_FAST_PYCALL #define CYTHON_FAST_PYCALL 0 #ifndef CYTHON_PEP487_INIT_SUBCLASS #define CYTHON_PEP487_INIT_SUBCLASS (PY_MAJOR_VERSION >= 3) #endif #if PY_VERSION_HEX < 0x03090000 #undef CYTHON_PEP489_MULTI_PHASE_INIT #define CYTHON_PEP489_MULTI_PHASE_INIT 0 #elif !defined(CYTHON_PEP489_MULTI_PHASE_INIT) #define CYTHON_PEP489_MULTI_PHASE_INIT 1 #endif #undef CYTHON_USE_MODULE_STATE #define CYTHON_USE_MODULE_STATE 0 #undef CYTHON_USE_TP_FINALIZE #define CYTHON_USE_TP_FINALIZE (PY_VERSION_HEX >= 0x030400a1 && PYPY_VERSION_NUM >= 0x07030C00) #undef CYTHON_USE_DICT_VERSIONS #define CYTHON_USE_DICT_VERSIONS 0 #undef CYTHON_USE_EXC_INFO_STACK #define CYTHON_USE_EXC_INFO_STACK 0 #ifndef CYTHON_UPDATE_DESCRIPTOR_DOC #define CYTHON_UPDATE_DESCRIPTOR_DOC 0 #endif #elif defined(CYTHON_LIMITED_API) #ifdef Py_LIMITED_API #undef __PYX_LIMITED_VERSION_HEX #define __PYX_LIMITED_VERSION_HEX Py_LIMITED_API #endif #define CYTHON_COMPILING_IN_PYPY 0 #define CYTHON_COMPILING_IN_CPYTHON 0 #define CYTHON_COMPILING_IN_LIMITED_API 1 #define CYTHON_COMPILING_IN_GRAAL 0 #define CYTHON_COMPILING_IN_NOGIL 0 #undef CYTHON_CLINE_IN_TRACEBACK #define CYTHON_CLINE_IN_TRACEBACK 0 #undef CYTHON_USE_TYPE_SLOTS #define CYTHON_USE_TYPE_SLOTS 0 #undef CYTHON_USE_TYPE_SPECS #define CYTHON_USE_TYPE_SPECS 1 #undef CYTHON_USE_PYTYPE_LOOKUP #define CYTHON_USE_PYTYPE_LOOKUP 0 #undef CYTHON_USE_ASYNC_SLOTS #define CYTHON_USE_ASYNC_SLOTS 0 #undef CYTHON_USE_PYLIST_INTERNALS #define CYTHON_USE_PYLIST_INTERNALS 0 #undef CYTHON_USE_UNICODE_INTERNALS #define CYTHON_USE_UNICODE_INTERNALS 0 #ifndef CYTHON_USE_UNICODE_WRITER #define CYTHON_USE_UNICODE_WRITER 0 #endif #undef CYTHON_USE_PYLONG_INTERNALS #define CYTHON_USE_PYLONG_INTERNALS 0 #ifndef CYTHON_AVOID_BORROWED_REFS #define CYTHON_AVOID_BORROWED_REFS 0 #endif #undef CYTHON_ASSUME_SAFE_MACROS #define CYTHON_ASSUME_SAFE_MACROS 0 #undef CYTHON_UNPACK_METHODS #define CYTHON_UNPACK_METHODS 0 #undef CYTHON_FAST_THREAD_STATE #define CYTHON_FAST_THREAD_STATE 0 #undef CYTHON_FAST_GIL #define CYTHON_FAST_GIL 0 #undef CYTHON_METH_FASTCALL #define CYTHON_METH_FASTCALL 0 #undef CYTHON_FAST_PYCALL #define CYTHON_FAST_PYCALL 0 #ifndef CYTHON_PEP487_INIT_SUBCLASS #define CYTHON_PEP487_INIT_SUBCLASS 1 #endif #undef CYTHON_PEP489_MULTI_PHASE_INIT #define CYTHON_PEP489_MULTI_PHASE_INIT 0 #undef CYTHON_USE_MODULE_STATE #define CYTHON_USE_MODULE_STATE 1 #ifndef CYTHON_USE_TP_FINALIZE #define CYTHON_USE_TP_FINALIZE 0 #endif #undef CYTHON_USE_DICT_VERSIONS #define CYTHON_USE_DICT_VERSIONS 0 #undef CYTHON_USE_EXC_INFO_STACK #define CYTHON_USE_EXC_INFO_STACK 0 #ifndef CYTHON_UPDATE_DESCRIPTOR_DOC #define CYTHON_UPDATE_DESCRIPTOR_DOC 0 #endif #elif defined(Py_GIL_DISABLED) || defined(Py_NOGIL) #define CYTHON_COMPILING_IN_PYPY 0 #define CYTHON_COMPILING_IN_CPYTHON 0 #define CYTHON_COMPILING_IN_LIMITED_API 0 #define CYTHON_COMPILING_IN_GRAAL 0 #define CYTHON_COMPILING_IN_NOGIL 1 #ifndef CYTHON_USE_TYPE_SLOTS #define CYTHON_USE_TYPE_SLOTS 1 #endif #undef CYTHON_USE_PYTYPE_LOOKUP #define CYTHON_USE_PYTYPE_LOOKUP 0 #ifndef CYTHON_USE_ASYNC_SLOTS #define CYTHON_USE_ASYNC_SLOTS 1 #endif #undef CYTHON_USE_PYLIST_INTERNALS #define CYTHON_USE_PYLIST_INTERNALS 0 #ifndef CYTHON_USE_UNICODE_INTERNALS #define CYTHON_USE_UNICODE_INTERNALS 1 #endif #undef CYTHON_USE_UNICODE_WRITER #define CYTHON_USE_UNICODE_WRITER 0 #undef CYTHON_USE_PYLONG_INTERNALS #define CYTHON_USE_PYLONG_INTERNALS 0 #ifndef CYTHON_AVOID_BORROWED_REFS #define CYTHON_AVOID_BORROWED_REFS 0 #endif #ifndef CYTHON_ASSUME_SAFE_MACROS #define CYTHON_ASSUME_SAFE_MACROS 1 #endif #ifndef CYTHON_UNPACK_METHODS #define CYTHON_UNPACK_METHODS 1 #endif #undef CYTHON_FAST_THREAD_STATE #define CYTHON_FAST_THREAD_STATE 0 #undef CYTHON_FAST_PYCALL #define CYTHON_FAST_PYCALL 0 #ifndef CYTHON_PEP489_MULTI_PHASE_INIT #define CYTHON_PEP489_MULTI_PHASE_INIT 1 #endif #ifndef CYTHON_USE_TP_FINALIZE #define CYTHON_USE_TP_FINALIZE 1 #endif #undef CYTHON_USE_DICT_VERSIONS #define CYTHON_USE_DICT_VERSIONS 0 #undef CYTHON_USE_EXC_INFO_STACK #define CYTHON_USE_EXC_INFO_STACK 0 #else #define CYTHON_COMPILING_IN_PYPY 0 #define CYTHON_COMPILING_IN_CPYTHON 1 #define CYTHON_COMPILING_IN_LIMITED_API 0 #define CYTHON_COMPILING_IN_GRAAL 0 #define CYTHON_COMPILING_IN_NOGIL 0 #ifndef CYTHON_USE_TYPE_SLOTS #define CYTHON_USE_TYPE_SLOTS 1 #endif #ifndef CYTHON_USE_TYPE_SPECS #define CYTHON_USE_TYPE_SPECS 0 #endif #ifndef CYTHON_USE_PYTYPE_LOOKUP #define CYTHON_USE_PYTYPE_LOOKUP 1 #endif #if PY_MAJOR_VERSION < 3 #undef CYTHON_USE_ASYNC_SLOTS #define CYTHON_USE_ASYNC_SLOTS 0 #elif !defined(CYTHON_USE_ASYNC_SLOTS) #define CYTHON_USE_ASYNC_SLOTS 1 #endif #ifndef CYTHON_USE_PYLONG_INTERNALS #define CYTHON_USE_PYLONG_INTERNALS 1 #endif #ifndef CYTHON_USE_PYLIST_INTERNALS #define CYTHON_USE_PYLIST_INTERNALS 1 #endif #ifndef CYTHON_USE_UNICODE_INTERNALS #define CYTHON_USE_UNICODE_INTERNALS 1 #endif #if PY_VERSION_HEX < 0x030300F0 || PY_VERSION_HEX >= 0x030B00A2 #undef CYTHON_USE_UNICODE_WRITER #define CYTHON_USE_UNICODE_WRITER 0 #elif !defined(CYTHON_USE_UNICODE_WRITER) #define CYTHON_USE_UNICODE_WRITER 1 #endif #ifndef CYTHON_AVOID_BORROWED_REFS #define CYTHON_AVOID_BORROWED_REFS 0 #endif #ifndef CYTHON_ASSUME_SAFE_MACROS #define CYTHON_ASSUME_SAFE_MACROS 1 #endif #ifndef CYTHON_UNPACK_METHODS #define CYTHON_UNPACK_METHODS 1 #endif #ifndef CYTHON_FAST_THREAD_STATE #define CYTHON_FAST_THREAD_STATE 1 #endif #ifndef CYTHON_FAST_GIL #define CYTHON_FAST_GIL (PY_MAJOR_VERSION < 3 || PY_VERSION_HEX >= 0x03060000 && PY_VERSION_HEX < 0x030C00A6) #endif #ifndef CYTHON_METH_FASTCALL #define CYTHON_METH_FASTCALL (PY_VERSION_HEX >= 0x030700A1) #endif #ifndef CYTHON_FAST_PYCALL #define CYTHON_FAST_PYCALL 1 #endif #ifndef CYTHON_PEP487_INIT_SUBCLASS #define CYTHON_PEP487_INIT_SUBCLASS 1 #endif #if PY_VERSION_HEX < 0x03050000 #undef CYTHON_PEP489_MULTI_PHASE_INIT #define CYTHON_PEP489_MULTI_PHASE_INIT 0 #elif !defined(CYTHON_PEP489_MULTI_PHASE_INIT) #define CYTHON_PEP489_MULTI_PHASE_INIT 1 #endif #ifndef CYTHON_USE_MODULE_STATE #define CYTHON_USE_MODULE_STATE 0 #endif #if PY_VERSION_HEX < 0x030400a1 #undef CYTHON_USE_TP_FINALIZE #define CYTHON_USE_TP_FINALIZE 0 #elif !defined(CYTHON_USE_TP_FINALIZE) #define CYTHON_USE_TP_FINALIZE 1 #endif #if PY_VERSION_HEX < 0x030600B1 #undef CYTHON_USE_DICT_VERSIONS #define CYTHON_USE_DICT_VERSIONS 0 #elif !defined(CYTHON_USE_DICT_VERSIONS) #define CYTHON_USE_DICT_VERSIONS (PY_VERSION_HEX < 0x030C00A5) #endif #if PY_VERSION_HEX < 0x030700A3 #undef CYTHON_USE_EXC_INFO_STACK #define CYTHON_USE_EXC_INFO_STACK 0 #elif !defined(CYTHON_USE_EXC_INFO_STACK) #define CYTHON_USE_EXC_INFO_STACK 1 #endif #ifndef CYTHON_UPDATE_DESCRIPTOR_DOC #define CYTHON_UPDATE_DESCRIPTOR_DOC 1 #endif #endif #if !defined(CYTHON_FAST_PYCCALL) #define CYTHON_FAST_PYCCALL (CYTHON_FAST_PYCALL && PY_VERSION_HEX >= 0x030600B1) #endif #if !defined(CYTHON_VECTORCALL) #define CYTHON_VECTORCALL (CYTHON_FAST_PYCCALL && PY_VERSION_HEX >= 0x030800B1) #endif #define CYTHON_BACKPORT_VECTORCALL (CYTHON_METH_FASTCALL && PY_VERSION_HEX < 0x030800B1) #if CYTHON_USE_PYLONG_INTERNALS #if PY_MAJOR_VERSION < 3 #include "longintrepr.h" #endif #undef SHIFT #undef BASE #undef MASK #ifdef SIZEOF_VOID_P enum { __pyx_check_sizeof_voidp = 1 / (int)(SIZEOF_VOID_P == sizeof(void*)) }; #endif #endif #ifndef __has_attribute #define __has_attribute(x) 0 #endif #ifndef __has_cpp_attribute #define __has_cpp_attribute(x) 0 #endif #ifndef CYTHON_RESTRICT #if defined(__GNUC__) #define CYTHON_RESTRICT __restrict__ #elif defined(_MSC_VER) && _MSC_VER >= 1400 #define CYTHON_RESTRICT __restrict #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L #define CYTHON_RESTRICT restrict #else #define CYTHON_RESTRICT #endif #endif #ifndef CYTHON_UNUSED #if defined(__cplusplus) /* for clang __has_cpp_attribute(maybe_unused) is true even before C++17 * but leads to warnings with -pedantic, since it is a C++17 feature */ #if ((defined(_MSVC_LANG) && _MSVC_LANG >= 201703L) || __cplusplus >= 201703L) #if __has_cpp_attribute(maybe_unused) #define CYTHON_UNUSED [[maybe_unused]] #endif #endif #endif #endif #ifndef CYTHON_UNUSED # if defined(__GNUC__) # if !(defined(__cplusplus)) || (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 4)) # define CYTHON_UNUSED __attribute__ ((__unused__)) # else # define CYTHON_UNUSED # endif # elif defined(__ICC) || (defined(__INTEL_COMPILER) && !defined(_MSC_VER)) # define CYTHON_UNUSED __attribute__ ((__unused__)) # else # define CYTHON_UNUSED # endif #endif #ifndef CYTHON_UNUSED_VAR # if defined(__cplusplus) template void CYTHON_UNUSED_VAR( const T& ) { } # else # define CYTHON_UNUSED_VAR(x) (void)(x) # endif #endif #ifndef CYTHON_MAYBE_UNUSED_VAR #define CYTHON_MAYBE_UNUSED_VAR(x) CYTHON_UNUSED_VAR(x) #endif #ifndef CYTHON_NCP_UNUSED # if CYTHON_COMPILING_IN_CPYTHON # define CYTHON_NCP_UNUSED # else # define CYTHON_NCP_UNUSED CYTHON_UNUSED # endif #endif #ifndef CYTHON_USE_CPP_STD_MOVE #if defined(__cplusplus) && (\ __cplusplus >= 201103L || (defined(_MSC_VER) && _MSC_VER >= 1600)) #define CYTHON_USE_CPP_STD_MOVE 1 #else #define CYTHON_USE_CPP_STD_MOVE 0 #endif #endif #define __Pyx_void_to_None(void_result) ((void)(void_result), Py_INCREF(Py_None), Py_None) #ifdef _MSC_VER #ifndef _MSC_STDINT_H_ #if _MSC_VER < 1300 typedef unsigned char uint8_t; typedef unsigned short uint16_t; typedef unsigned int uint32_t; #else typedef unsigned __int8 uint8_t; typedef unsigned __int16 uint16_t; typedef unsigned __int32 uint32_t; #endif #endif #if _MSC_VER < 1300 #ifdef _WIN64 typedef unsigned long long __pyx_uintptr_t; #else typedef unsigned int __pyx_uintptr_t; #endif #else #ifdef _WIN64 typedef unsigned __int64 __pyx_uintptr_t; #else typedef unsigned __int32 __pyx_uintptr_t; #endif #endif #else #include typedef uintptr_t __pyx_uintptr_t; #endif #ifndef CYTHON_FALLTHROUGH #if defined(__cplusplus) /* for clang __has_cpp_attribute(fallthrough) is true even before C++17 * but leads to warnings with -pedantic, since it is a C++17 feature */ #if ((defined(_MSVC_LANG) && _MSVC_LANG >= 201703L) || __cplusplus >= 201703L) #if __has_cpp_attribute(fallthrough) #define CYTHON_FALLTHROUGH [[fallthrough]] #endif #endif #ifndef CYTHON_FALLTHROUGH #if __has_cpp_attribute(clang::fallthrough) #define CYTHON_FALLTHROUGH [[clang::fallthrough]] #elif __has_cpp_attribute(gnu::fallthrough) #define CYTHON_FALLTHROUGH [[gnu::fallthrough]] #endif #endif #endif #ifndef CYTHON_FALLTHROUGH #if __has_attribute(fallthrough) #define CYTHON_FALLTHROUGH __attribute__((fallthrough)) #else #define CYTHON_FALLTHROUGH #endif #endif #if defined(__clang__) && defined(__apple_build_version__) #if __apple_build_version__ < 7000000 #undef CYTHON_FALLTHROUGH #define CYTHON_FALLTHROUGH #endif #endif #endif #ifdef __cplusplus template struct __PYX_IS_UNSIGNED_IMPL {static const bool value = T(0) < T(-1);}; #define __PYX_IS_UNSIGNED(type) (__PYX_IS_UNSIGNED_IMPL::value) #else #define __PYX_IS_UNSIGNED(type) (((type)-1) > 0) #endif #if CYTHON_COMPILING_IN_PYPY == 1 #define __PYX_NEED_TP_PRINT_SLOT (PY_VERSION_HEX >= 0x030800b4 && PY_VERSION_HEX < 0x030A0000) #else #define __PYX_NEED_TP_PRINT_SLOT (PY_VERSION_HEX >= 0x030800b4 && PY_VERSION_HEX < 0x03090000) #endif #define __PYX_REINTERPRET_FUNCION(func_pointer, other_pointer) ((func_pointer)(void(*)(void))(other_pointer)) #ifndef __cplusplus #error "Cython files generated with the C++ option must be compiled with a C++ compiler." #endif #ifndef CYTHON_INLINE #if defined(__clang__) #define CYTHON_INLINE __inline__ __attribute__ ((__unused__)) #else #define CYTHON_INLINE inline #endif #endif template void __Pyx_call_destructor(T& x) { x.~T(); } template class __Pyx_FakeReference { public: __Pyx_FakeReference() : ptr(NULL) { } __Pyx_FakeReference(const T& ref) : ptr(const_cast(&ref)) { } T *operator->() { return ptr; } T *operator&() { return ptr; } operator T&() { return *ptr; } template bool operator ==(const U& other) const { return *ptr == other; } template bool operator !=(const U& other) const { return *ptr != other; } template bool operator==(const __Pyx_FakeReference& other) const { return *ptr == *other.ptr; } template bool operator!=(const __Pyx_FakeReference& other) const { return *ptr != *other.ptr; } private: T *ptr; }; #define __PYX_BUILD_PY_SSIZE_T "n" #define CYTHON_FORMAT_SSIZE_T "z" #if PY_MAJOR_VERSION < 3 #define __Pyx_BUILTIN_MODULE_NAME "__builtin__" #define __Pyx_DefaultClassType PyClass_Type #define __Pyx_PyCode_New(a, p, k, l, s, f, code, c, n, v, fv, cell, fn, name, fline, lnos)\ PyCode_New(a+k, l, s, f, code, c, n, v, fv, cell, fn, name, fline, lnos) #else #define __Pyx_BUILTIN_MODULE_NAME "builtins" #define __Pyx_DefaultClassType PyType_Type #if CYTHON_COMPILING_IN_LIMITED_API static CYTHON_INLINE PyObject* __Pyx_PyCode_New(int a, int p, int k, int l, int s, int f, PyObject *code, PyObject *c, PyObject* n, PyObject *v, PyObject *fv, PyObject *cell, PyObject* fn, PyObject *name, int fline, PyObject *lnos) { PyObject *exception_table = NULL; PyObject *types_module=NULL, *code_type=NULL, *result=NULL; #if __PYX_LIMITED_VERSION_HEX < 0x030B0000 PyObject *version_info; PyObject *py_minor_version = NULL; #endif long minor_version = 0; PyObject *type, *value, *traceback; PyErr_Fetch(&type, &value, &traceback); #if __PYX_LIMITED_VERSION_HEX >= 0x030B0000 minor_version = 11; #else if (!(version_info = PySys_GetObject("version_info"))) goto end; if (!(py_minor_version = PySequence_GetItem(version_info, 1))) goto end; minor_version = PyLong_AsLong(py_minor_version); Py_DECREF(py_minor_version); if (minor_version == -1 && PyErr_Occurred()) goto end; #endif if (!(types_module = PyImport_ImportModule("types"))) goto end; if (!(code_type = PyObject_GetAttrString(types_module, "CodeType"))) goto end; if (minor_version <= 7) { (void)p; result = PyObject_CallFunction(code_type, "iiiiiOOOOOOiOO", a, k, l, s, f, code, c, n, v, fn, name, fline, lnos, fv, cell); } else if (minor_version <= 10) { result = PyObject_CallFunction(code_type, "iiiiiiOOOOOOiOO", a,p, k, l, s, f, code, c, n, v, fn, name, fline, lnos, fv, cell); } else { if (!(exception_table = PyBytes_FromStringAndSize(NULL, 0))) goto end; result = PyObject_CallFunction(code_type, "iiiiiiOOOOOOOiOO", a,p, k, l, s, f, code, c, n, v, fn, name, name, fline, lnos, exception_table, fv, cell); } end: Py_XDECREF(code_type); Py_XDECREF(exception_table); Py_XDECREF(types_module); if (type) { PyErr_Restore(type, value, traceback); } return result; } #ifndef CO_OPTIMIZED #define CO_OPTIMIZED 0x0001 #endif #ifndef CO_NEWLOCALS #define CO_NEWLOCALS 0x0002 #endif #ifndef CO_VARARGS #define CO_VARARGS 0x0004 #endif #ifndef CO_VARKEYWORDS #define CO_VARKEYWORDS 0x0008 #endif #ifndef CO_ASYNC_GENERATOR #define CO_ASYNC_GENERATOR 0x0200 #endif #ifndef CO_GENERATOR #define CO_GENERATOR 0x0020 #endif #ifndef CO_COROUTINE #define CO_COROUTINE 0x0080 #endif #elif PY_VERSION_HEX >= 0x030B0000 static CYTHON_INLINE PyCodeObject* __Pyx_PyCode_New(int a, int p, int k, int l, int s, int f, PyObject *code, PyObject *c, PyObject* n, PyObject *v, PyObject *fv, PyObject *cell, PyObject* fn, PyObject *name, int fline, PyObject *lnos) { PyCodeObject *result; PyObject *empty_bytes = PyBytes_FromStringAndSize("", 0); if (!empty_bytes) return NULL; result = #if PY_VERSION_HEX >= 0x030C0000 PyUnstable_Code_NewWithPosOnlyArgs #else PyCode_NewWithPosOnlyArgs #endif (a, p, k, l, s, f, code, c, n, v, fv, cell, fn, name, name, fline, lnos, empty_bytes); Py_DECREF(empty_bytes); return result; } #elif PY_VERSION_HEX >= 0x030800B2 && !CYTHON_COMPILING_IN_PYPY #define __Pyx_PyCode_New(a, p, k, l, s, f, code, c, n, v, fv, cell, fn, name, fline, lnos)\ PyCode_NewWithPosOnlyArgs(a, p, k, l, s, f, code, c, n, v, fv, cell, fn, name, fline, lnos) #else #define __Pyx_PyCode_New(a, p, k, l, s, f, code, c, n, v, fv, cell, fn, name, fline, lnos)\ PyCode_New(a, k, l, s, f, code, c, n, v, fv, cell, fn, name, fline, lnos) #endif #endif #if PY_VERSION_HEX >= 0x030900A4 || defined(Py_IS_TYPE) #define __Pyx_IS_TYPE(ob, type) Py_IS_TYPE(ob, type) #else #define __Pyx_IS_TYPE(ob, type) (((const PyObject*)ob)->ob_type == (type)) #endif #if PY_VERSION_HEX >= 0x030A00B1 || defined(Py_Is) #define __Pyx_Py_Is(x, y) Py_Is(x, y) #else #define __Pyx_Py_Is(x, y) ((x) == (y)) #endif #if PY_VERSION_HEX >= 0x030A00B1 || defined(Py_IsNone) #define __Pyx_Py_IsNone(ob) Py_IsNone(ob) #else #define __Pyx_Py_IsNone(ob) __Pyx_Py_Is((ob), Py_None) #endif #if PY_VERSION_HEX >= 0x030A00B1 || defined(Py_IsTrue) #define __Pyx_Py_IsTrue(ob) Py_IsTrue(ob) #else #define __Pyx_Py_IsTrue(ob) __Pyx_Py_Is((ob), Py_True) #endif #if PY_VERSION_HEX >= 0x030A00B1 || defined(Py_IsFalse) #define __Pyx_Py_IsFalse(ob) Py_IsFalse(ob) #else #define __Pyx_Py_IsFalse(ob) __Pyx_Py_Is((ob), Py_False) #endif #define __Pyx_NoneAsNull(obj) (__Pyx_Py_IsNone(obj) ? NULL : (obj)) #if PY_VERSION_HEX >= 0x030900F0 && !CYTHON_COMPILING_IN_PYPY #define __Pyx_PyObject_GC_IsFinalized(o) PyObject_GC_IsFinalized(o) #else #define __Pyx_PyObject_GC_IsFinalized(o) _PyGC_FINALIZED(o) #endif #ifndef CO_COROUTINE #define CO_COROUTINE 0x80 #endif #ifndef CO_ASYNC_GENERATOR #define CO_ASYNC_GENERATOR 0x200 #endif #ifndef Py_TPFLAGS_CHECKTYPES #define Py_TPFLAGS_CHECKTYPES 0 #endif #ifndef Py_TPFLAGS_HAVE_INDEX #define Py_TPFLAGS_HAVE_INDEX 0 #endif #ifndef Py_TPFLAGS_HAVE_NEWBUFFER #define Py_TPFLAGS_HAVE_NEWBUFFER 0 #endif #ifndef Py_TPFLAGS_HAVE_FINALIZE #define Py_TPFLAGS_HAVE_FINALIZE 0 #endif #ifndef Py_TPFLAGS_SEQUENCE #define Py_TPFLAGS_SEQUENCE 0 #endif #ifndef Py_TPFLAGS_MAPPING #define Py_TPFLAGS_MAPPING 0 #endif #ifndef METH_STACKLESS #define METH_STACKLESS 0 #endif #if PY_VERSION_HEX <= 0x030700A3 || !defined(METH_FASTCALL) #ifndef METH_FASTCALL #define METH_FASTCALL 0x80 #endif typedef PyObject *(*__Pyx_PyCFunctionFast) (PyObject *self, PyObject *const *args, Py_ssize_t nargs); typedef PyObject *(*__Pyx_PyCFunctionFastWithKeywords) (PyObject *self, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames); #else #define __Pyx_PyCFunctionFast _PyCFunctionFast #define __Pyx_PyCFunctionFastWithKeywords _PyCFunctionFastWithKeywords #endif #if CYTHON_METH_FASTCALL #define __Pyx_METH_FASTCALL METH_FASTCALL #define __Pyx_PyCFunction_FastCall __Pyx_PyCFunctionFast #define __Pyx_PyCFunction_FastCallWithKeywords __Pyx_PyCFunctionFastWithKeywords #else #define __Pyx_METH_FASTCALL METH_VARARGS #define __Pyx_PyCFunction_FastCall PyCFunction #define __Pyx_PyCFunction_FastCallWithKeywords PyCFunctionWithKeywords #endif #if CYTHON_VECTORCALL #define __pyx_vectorcallfunc vectorcallfunc #define __Pyx_PY_VECTORCALL_ARGUMENTS_OFFSET PY_VECTORCALL_ARGUMENTS_OFFSET #define __Pyx_PyVectorcall_NARGS(n) PyVectorcall_NARGS((size_t)(n)) #elif CYTHON_BACKPORT_VECTORCALL typedef PyObject *(*__pyx_vectorcallfunc)(PyObject *callable, PyObject *const *args, size_t nargsf, PyObject *kwnames); #define __Pyx_PY_VECTORCALL_ARGUMENTS_OFFSET ((size_t)1 << (8 * sizeof(size_t) - 1)) #define __Pyx_PyVectorcall_NARGS(n) ((Py_ssize_t)(((size_t)(n)) & ~__Pyx_PY_VECTORCALL_ARGUMENTS_OFFSET)) #else #define __Pyx_PY_VECTORCALL_ARGUMENTS_OFFSET 0 #define __Pyx_PyVectorcall_NARGS(n) ((Py_ssize_t)(n)) #endif #if PY_MAJOR_VERSION >= 0x030900B1 #define __Pyx_PyCFunction_CheckExact(func) PyCFunction_CheckExact(func) #else #define __Pyx_PyCFunction_CheckExact(func) PyCFunction_Check(func) #endif #define __Pyx_CyOrPyCFunction_Check(func) PyCFunction_Check(func) #if CYTHON_COMPILING_IN_CPYTHON #define __Pyx_CyOrPyCFunction_GET_FUNCTION(func) (((PyCFunctionObject*)(func))->m_ml->ml_meth) #elif !CYTHON_COMPILING_IN_LIMITED_API #define __Pyx_CyOrPyCFunction_GET_FUNCTION(func) PyCFunction_GET_FUNCTION(func) #endif #if CYTHON_COMPILING_IN_CPYTHON #define __Pyx_CyOrPyCFunction_GET_FLAGS(func) (((PyCFunctionObject*)(func))->m_ml->ml_flags) static CYTHON_INLINE PyObject* __Pyx_CyOrPyCFunction_GET_SELF(PyObject *func) { return (__Pyx_CyOrPyCFunction_GET_FLAGS(func) & METH_STATIC) ? NULL : ((PyCFunctionObject*)func)->m_self; } #endif static CYTHON_INLINE int __Pyx__IsSameCFunction(PyObject *func, void *cfunc) { #if CYTHON_COMPILING_IN_LIMITED_API return PyCFunction_Check(func) && PyCFunction_GetFunction(func) == (PyCFunction) cfunc; #else return PyCFunction_Check(func) && PyCFunction_GET_FUNCTION(func) == (PyCFunction) cfunc; #endif } #define __Pyx_IsSameCFunction(func, cfunc) __Pyx__IsSameCFunction(func, cfunc) #if __PYX_LIMITED_VERSION_HEX < 0x030900B1 #define __Pyx_PyType_FromModuleAndSpec(m, s, b) ((void)m, PyType_FromSpecWithBases(s, b)) typedef PyObject *(*__Pyx_PyCMethod)(PyObject *, PyTypeObject *, PyObject *const *, size_t, PyObject *); #else #define __Pyx_PyType_FromModuleAndSpec(m, s, b) PyType_FromModuleAndSpec(m, s, b) #define __Pyx_PyCMethod PyCMethod #endif #ifndef METH_METHOD #define METH_METHOD 0x200 #endif #if CYTHON_COMPILING_IN_PYPY && !defined(PyObject_Malloc) #define PyObject_Malloc(s) PyMem_Malloc(s) #define PyObject_Free(p) PyMem_Free(p) #define PyObject_Realloc(p) PyMem_Realloc(p) #endif #if CYTHON_COMPILING_IN_LIMITED_API #define __Pyx_PyCode_HasFreeVars(co) (PyCode_GetNumFree(co) > 0) #define __Pyx_PyFrame_SetLineNumber(frame, lineno) #else #define __Pyx_PyCode_HasFreeVars(co) (PyCode_GetNumFree(co) > 0) #define __Pyx_PyFrame_SetLineNumber(frame, lineno) (frame)->f_lineno = (lineno) #endif #if CYTHON_COMPILING_IN_LIMITED_API #define __Pyx_PyThreadState_Current PyThreadState_Get() #elif !CYTHON_FAST_THREAD_STATE #define __Pyx_PyThreadState_Current PyThreadState_GET() #elif PY_VERSION_HEX >= 0x030d00A1 #define __Pyx_PyThreadState_Current PyThreadState_GetUnchecked() #elif PY_VERSION_HEX >= 0x03060000 #define __Pyx_PyThreadState_Current _PyThreadState_UncheckedGet() #elif PY_VERSION_HEX >= 0x03000000 #define __Pyx_PyThreadState_Current PyThreadState_GET() #else #define __Pyx_PyThreadState_Current _PyThreadState_Current #endif #if CYTHON_COMPILING_IN_LIMITED_API static CYTHON_INLINE void *__Pyx_PyModule_GetState(PyObject *op) { void *result; result = PyModule_GetState(op); if (!result) Py_FatalError("Couldn't find the module state"); return result; } #endif #define __Pyx_PyObject_GetSlot(obj, name, func_ctype) __Pyx_PyType_GetSlot(Py_TYPE(obj), name, func_ctype) #if CYTHON_COMPILING_IN_LIMITED_API #define __Pyx_PyType_GetSlot(type, name, func_ctype) ((func_ctype) PyType_GetSlot((type), Py_##name)) #else #define __Pyx_PyType_GetSlot(type, name, func_ctype) ((type)->name) #endif #if PY_VERSION_HEX < 0x030700A2 && !defined(PyThread_tss_create) && !defined(Py_tss_NEEDS_INIT) #include "pythread.h" #define Py_tss_NEEDS_INIT 0 typedef int Py_tss_t; static CYTHON_INLINE int PyThread_tss_create(Py_tss_t *key) { *key = PyThread_create_key(); return 0; } static CYTHON_INLINE Py_tss_t * PyThread_tss_alloc(void) { Py_tss_t *key = (Py_tss_t *)PyObject_Malloc(sizeof(Py_tss_t)); *key = Py_tss_NEEDS_INIT; return key; } static CYTHON_INLINE void PyThread_tss_free(Py_tss_t *key) { PyObject_Free(key); } static CYTHON_INLINE int PyThread_tss_is_created(Py_tss_t *key) { return *key != Py_tss_NEEDS_INIT; } static CYTHON_INLINE void PyThread_tss_delete(Py_tss_t *key) { PyThread_delete_key(*key); *key = Py_tss_NEEDS_INIT; } static CYTHON_INLINE int PyThread_tss_set(Py_tss_t *key, void *value) { return PyThread_set_key_value(*key, value); } static CYTHON_INLINE void * PyThread_tss_get(Py_tss_t *key) { return PyThread_get_key_value(*key); } #endif #if PY_MAJOR_VERSION < 3 #if CYTHON_COMPILING_IN_PYPY #if PYPY_VERSION_NUM < 0x07030600 #if defined(__cplusplus) && __cplusplus >= 201402L [[deprecated("`with nogil:` inside a nogil function will not release the GIL in PyPy2 < 7.3.6")]] #elif defined(__GNUC__) || defined(__clang__) __attribute__ ((__deprecated__("`with nogil:` inside a nogil function will not release the GIL in PyPy2 < 7.3.6"))) #elif defined(_MSC_VER) __declspec(deprecated("`with nogil:` inside a nogil function will not release the GIL in PyPy2 < 7.3.6")) #endif static CYTHON_INLINE int PyGILState_Check(void) { return 0; } #else // PYPY_VERSION_NUM < 0x07030600 #endif // PYPY_VERSION_NUM < 0x07030600 #else static CYTHON_INLINE int PyGILState_Check(void) { PyThreadState * tstate = _PyThreadState_Current; return tstate && (tstate == PyGILState_GetThisThreadState()); } #endif #endif #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX < 0x030d0000 || defined(_PyDict_NewPresized) #define __Pyx_PyDict_NewPresized(n) ((n <= 8) ? PyDict_New() : _PyDict_NewPresized(n)) #else #define __Pyx_PyDict_NewPresized(n) PyDict_New() #endif #if PY_MAJOR_VERSION >= 3 || CYTHON_FUTURE_DIVISION #define __Pyx_PyNumber_Divide(x,y) PyNumber_TrueDivide(x,y) #define __Pyx_PyNumber_InPlaceDivide(x,y) PyNumber_InPlaceTrueDivide(x,y) #else #define __Pyx_PyNumber_Divide(x,y) PyNumber_Divide(x,y) #define __Pyx_PyNumber_InPlaceDivide(x,y) PyNumber_InPlaceDivide(x,y) #endif #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX > 0x030600B4 && PY_VERSION_HEX < 0x030d0000 && CYTHON_USE_UNICODE_INTERNALS #define __Pyx_PyDict_GetItemStrWithError(dict, name) _PyDict_GetItem_KnownHash(dict, name, ((PyASCIIObject *) name)->hash) static CYTHON_INLINE PyObject * __Pyx_PyDict_GetItemStr(PyObject *dict, PyObject *name) { PyObject *res = __Pyx_PyDict_GetItemStrWithError(dict, name); if (res == NULL) PyErr_Clear(); return res; } #elif PY_MAJOR_VERSION >= 3 && (!CYTHON_COMPILING_IN_PYPY || PYPY_VERSION_NUM >= 0x07020000) #define __Pyx_PyDict_GetItemStrWithError PyDict_GetItemWithError #define __Pyx_PyDict_GetItemStr PyDict_GetItem #else static CYTHON_INLINE PyObject * __Pyx_PyDict_GetItemStrWithError(PyObject *dict, PyObject *name) { #if CYTHON_COMPILING_IN_PYPY return PyDict_GetItem(dict, name); #else PyDictEntry *ep; PyDictObject *mp = (PyDictObject*) dict; long hash = ((PyStringObject *) name)->ob_shash; assert(hash != -1); ep = (mp->ma_lookup)(mp, name, hash); if (ep == NULL) { return NULL; } return ep->me_value; #endif } #define __Pyx_PyDict_GetItemStr PyDict_GetItem #endif #if CYTHON_USE_TYPE_SLOTS #define __Pyx_PyType_GetFlags(tp) (((PyTypeObject *)tp)->tp_flags) #define __Pyx_PyType_HasFeature(type, feature) ((__Pyx_PyType_GetFlags(type) & (feature)) != 0) #define __Pyx_PyObject_GetIterNextFunc(obj) (Py_TYPE(obj)->tp_iternext) #else #define __Pyx_PyType_GetFlags(tp) (PyType_GetFlags((PyTypeObject *)tp)) #define __Pyx_PyType_HasFeature(type, feature) PyType_HasFeature(type, feature) #define __Pyx_PyObject_GetIterNextFunc(obj) PyIter_Next #endif #if CYTHON_COMPILING_IN_LIMITED_API #define __Pyx_SetItemOnTypeDict(tp, k, v) PyObject_GenericSetAttr((PyObject*)tp, k, v) #else #define __Pyx_SetItemOnTypeDict(tp, k, v) PyDict_SetItem(tp->tp_dict, k, v) #endif #if CYTHON_USE_TYPE_SPECS && PY_VERSION_HEX >= 0x03080000 #define __Pyx_PyHeapTypeObject_GC_Del(obj) {\ PyTypeObject *type = Py_TYPE((PyObject*)obj);\ assert(__Pyx_PyType_HasFeature(type, Py_TPFLAGS_HEAPTYPE));\ PyObject_GC_Del(obj);\ Py_DECREF(type);\ } #else #define __Pyx_PyHeapTypeObject_GC_Del(obj) PyObject_GC_Del(obj) #endif #if CYTHON_COMPILING_IN_LIMITED_API #define CYTHON_PEP393_ENABLED 1 #define __Pyx_PyUnicode_READY(op) (0) #define __Pyx_PyUnicode_GET_LENGTH(u) PyUnicode_GetLength(u) #define __Pyx_PyUnicode_READ_CHAR(u, i) PyUnicode_ReadChar(u, i) #define __Pyx_PyUnicode_MAX_CHAR_VALUE(u) ((void)u, 1114111U) #define __Pyx_PyUnicode_KIND(u) ((void)u, (0)) #define __Pyx_PyUnicode_DATA(u) ((void*)u) #define __Pyx_PyUnicode_READ(k, d, i) ((void)k, PyUnicode_ReadChar((PyObject*)(d), i)) #define __Pyx_PyUnicode_IS_TRUE(u) (0 != PyUnicode_GetLength(u)) #elif PY_VERSION_HEX > 0x03030000 && defined(PyUnicode_KIND) #define CYTHON_PEP393_ENABLED 1 #if PY_VERSION_HEX >= 0x030C0000 #define __Pyx_PyUnicode_READY(op) (0) #else #define __Pyx_PyUnicode_READY(op) (likely(PyUnicode_IS_READY(op)) ?\ 0 : _PyUnicode_Ready((PyObject *)(op))) #endif #define __Pyx_PyUnicode_GET_LENGTH(u) PyUnicode_GET_LENGTH(u) #define __Pyx_PyUnicode_READ_CHAR(u, i) PyUnicode_READ_CHAR(u, i) #define __Pyx_PyUnicode_MAX_CHAR_VALUE(u) PyUnicode_MAX_CHAR_VALUE(u) #define __Pyx_PyUnicode_KIND(u) ((int)PyUnicode_KIND(u)) #define __Pyx_PyUnicode_DATA(u) PyUnicode_DATA(u) #define __Pyx_PyUnicode_READ(k, d, i) PyUnicode_READ(k, d, i) #define __Pyx_PyUnicode_WRITE(k, d, i, ch) PyUnicode_WRITE(k, d, i, (Py_UCS4) ch) #if PY_VERSION_HEX >= 0x030C0000 #define __Pyx_PyUnicode_IS_TRUE(u) (0 != PyUnicode_GET_LENGTH(u)) #else #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x03090000 #define __Pyx_PyUnicode_IS_TRUE(u) (0 != (likely(PyUnicode_IS_READY(u)) ? PyUnicode_GET_LENGTH(u) : ((PyCompactUnicodeObject *)(u))->wstr_length)) #else #define __Pyx_PyUnicode_IS_TRUE(u) (0 != (likely(PyUnicode_IS_READY(u)) ? PyUnicode_GET_LENGTH(u) : PyUnicode_GET_SIZE(u))) #endif #endif #else #define CYTHON_PEP393_ENABLED 0 #define PyUnicode_1BYTE_KIND 1 #define PyUnicode_2BYTE_KIND 2 #define PyUnicode_4BYTE_KIND 4 #define __Pyx_PyUnicode_READY(op) (0) #define __Pyx_PyUnicode_GET_LENGTH(u) PyUnicode_GET_SIZE(u) #define __Pyx_PyUnicode_READ_CHAR(u, i) ((Py_UCS4)(PyUnicode_AS_UNICODE(u)[i])) #define __Pyx_PyUnicode_MAX_CHAR_VALUE(u) ((sizeof(Py_UNICODE) == 2) ? 65535U : 1114111U) #define __Pyx_PyUnicode_KIND(u) ((int)sizeof(Py_UNICODE)) #define __Pyx_PyUnicode_DATA(u) ((void*)PyUnicode_AS_UNICODE(u)) #define __Pyx_PyUnicode_READ(k, d, i) ((void)(k), (Py_UCS4)(((Py_UNICODE*)d)[i])) #define __Pyx_PyUnicode_WRITE(k, d, i, ch) (((void)(k)), ((Py_UNICODE*)d)[i] = (Py_UNICODE) ch) #define __Pyx_PyUnicode_IS_TRUE(u) (0 != PyUnicode_GET_SIZE(u)) #endif #if CYTHON_COMPILING_IN_PYPY #define __Pyx_PyUnicode_Concat(a, b) PyNumber_Add(a, b) #define __Pyx_PyUnicode_ConcatSafe(a, b) PyNumber_Add(a, b) #else #define __Pyx_PyUnicode_Concat(a, b) PyUnicode_Concat(a, b) #define __Pyx_PyUnicode_ConcatSafe(a, b) ((unlikely((a) == Py_None) || unlikely((b) == Py_None)) ?\ PyNumber_Add(a, b) : __Pyx_PyUnicode_Concat(a, b)) #endif #if CYTHON_COMPILING_IN_PYPY #if !defined(PyUnicode_DecodeUnicodeEscape) #define PyUnicode_DecodeUnicodeEscape(s, size, errors) PyUnicode_Decode(s, size, "unicode_escape", errors) #endif #if !defined(PyUnicode_Contains) || (PY_MAJOR_VERSION == 2 && PYPY_VERSION_NUM < 0x07030500) #undef PyUnicode_Contains #define PyUnicode_Contains(u, s) PySequence_Contains(u, s) #endif #if !defined(PyByteArray_Check) #define PyByteArray_Check(obj) PyObject_TypeCheck(obj, &PyByteArray_Type) #endif #if !defined(PyObject_Format) #define PyObject_Format(obj, fmt) PyObject_CallMethod(obj, "__format__", "O", fmt) #endif #endif #define __Pyx_PyString_FormatSafe(a, b) ((unlikely((a) == Py_None || (PyString_Check(b) && !PyString_CheckExact(b)))) ? PyNumber_Remainder(a, b) : __Pyx_PyString_Format(a, b)) #define __Pyx_PyUnicode_FormatSafe(a, b) ((unlikely((a) == Py_None || (PyUnicode_Check(b) && !PyUnicode_CheckExact(b)))) ? PyNumber_Remainder(a, b) : PyUnicode_Format(a, b)) #if PY_MAJOR_VERSION >= 3 #define __Pyx_PyString_Format(a, b) PyUnicode_Format(a, b) #else #define __Pyx_PyString_Format(a, b) PyString_Format(a, b) #endif #if PY_MAJOR_VERSION < 3 && !defined(PyObject_ASCII) #define PyObject_ASCII(o) PyObject_Repr(o) #endif #if PY_MAJOR_VERSION >= 3 #define PyBaseString_Type PyUnicode_Type #define PyStringObject PyUnicodeObject #define PyString_Type PyUnicode_Type #define PyString_Check PyUnicode_Check #define PyString_CheckExact PyUnicode_CheckExact #ifndef PyObject_Unicode #define PyObject_Unicode PyObject_Str #endif #endif #if PY_MAJOR_VERSION >= 3 #define __Pyx_PyBaseString_Check(obj) PyUnicode_Check(obj) #define __Pyx_PyBaseString_CheckExact(obj) PyUnicode_CheckExact(obj) #else #define __Pyx_PyBaseString_Check(obj) (PyString_Check(obj) || PyUnicode_Check(obj)) #define __Pyx_PyBaseString_CheckExact(obj) (PyString_CheckExact(obj) || PyUnicode_CheckExact(obj)) #endif #if CYTHON_COMPILING_IN_CPYTHON #define __Pyx_PySequence_ListKeepNew(obj)\ (likely(PyList_CheckExact(obj) && Py_REFCNT(obj) == 1) ? __Pyx_NewRef(obj) : PySequence_List(obj)) #else #define __Pyx_PySequence_ListKeepNew(obj) PySequence_List(obj) #endif #ifndef PySet_CheckExact #define PySet_CheckExact(obj) __Pyx_IS_TYPE(obj, &PySet_Type) #endif #if PY_VERSION_HEX >= 0x030900A4 #define __Pyx_SET_REFCNT(obj, refcnt) Py_SET_REFCNT(obj, refcnt) #define __Pyx_SET_SIZE(obj, size) Py_SET_SIZE(obj, size) #else #define __Pyx_SET_REFCNT(obj, refcnt) Py_REFCNT(obj) = (refcnt) #define __Pyx_SET_SIZE(obj, size) Py_SIZE(obj) = (size) #endif #if CYTHON_ASSUME_SAFE_MACROS #define __Pyx_PySequence_ITEM(o, i) PySequence_ITEM(o, i) #define __Pyx_PySequence_SIZE(seq) Py_SIZE(seq) #define __Pyx_PyTuple_SET_ITEM(o, i, v) (PyTuple_SET_ITEM(o, i, v), (0)) #define __Pyx_PyList_SET_ITEM(o, i, v) (PyList_SET_ITEM(o, i, v), (0)) #define __Pyx_PyTuple_GET_SIZE(o) PyTuple_GET_SIZE(o) #define __Pyx_PyList_GET_SIZE(o) PyList_GET_SIZE(o) #define __Pyx_PySet_GET_SIZE(o) PySet_GET_SIZE(o) #define __Pyx_PyBytes_GET_SIZE(o) PyBytes_GET_SIZE(o) #define __Pyx_PyByteArray_GET_SIZE(o) PyByteArray_GET_SIZE(o) #else #define __Pyx_PySequence_ITEM(o, i) PySequence_GetItem(o, i) #define __Pyx_PySequence_SIZE(seq) PySequence_Size(seq) #define __Pyx_PyTuple_SET_ITEM(o, i, v) PyTuple_SetItem(o, i, v) #define __Pyx_PyList_SET_ITEM(o, i, v) PyList_SetItem(o, i, v) #define __Pyx_PyTuple_GET_SIZE(o) PyTuple_Size(o) #define __Pyx_PyList_GET_SIZE(o) PyList_Size(o) #define __Pyx_PySet_GET_SIZE(o) PySet_Size(o) #define __Pyx_PyBytes_GET_SIZE(o) PyBytes_Size(o) #define __Pyx_PyByteArray_GET_SIZE(o) PyByteArray_Size(o) #endif #if PY_VERSION_HEX >= 0x030d00A1 #define __Pyx_PyImport_AddModuleRef(name) PyImport_AddModuleRef(name) #else static CYTHON_INLINE PyObject *__Pyx_PyImport_AddModuleRef(const char *name) { PyObject *module = PyImport_AddModule(name); Py_XINCREF(module); return module; } #endif #if PY_MAJOR_VERSION >= 3 #define PyIntObject PyLongObject #define PyInt_Type PyLong_Type #define PyInt_Check(op) PyLong_Check(op) #define PyInt_CheckExact(op) PyLong_CheckExact(op) #define __Pyx_Py3Int_Check(op) PyLong_Check(op) #define __Pyx_Py3Int_CheckExact(op) PyLong_CheckExact(op) #define PyInt_FromString PyLong_FromString #define PyInt_FromUnicode PyLong_FromUnicode #define PyInt_FromLong PyLong_FromLong #define PyInt_FromSize_t PyLong_FromSize_t #define PyInt_FromSsize_t PyLong_FromSsize_t #define PyInt_AsLong PyLong_AsLong #define PyInt_AS_LONG PyLong_AS_LONG #define PyInt_AsSsize_t PyLong_AsSsize_t #define PyInt_AsUnsignedLongMask PyLong_AsUnsignedLongMask #define PyInt_AsUnsignedLongLongMask PyLong_AsUnsignedLongLongMask #define PyNumber_Int PyNumber_Long #else #define __Pyx_Py3Int_Check(op) (PyLong_Check(op) || PyInt_Check(op)) #define __Pyx_Py3Int_CheckExact(op) (PyLong_CheckExact(op) || PyInt_CheckExact(op)) #endif #if PY_MAJOR_VERSION >= 3 #define PyBoolObject PyLongObject #endif #if PY_MAJOR_VERSION >= 3 && CYTHON_COMPILING_IN_PYPY #ifndef PyUnicode_InternFromString #define PyUnicode_InternFromString(s) PyUnicode_FromString(s) #endif #endif #if PY_VERSION_HEX < 0x030200A4 typedef long Py_hash_t; #define __Pyx_PyInt_FromHash_t PyInt_FromLong #define __Pyx_PyInt_AsHash_t __Pyx_PyIndex_AsHash_t #else #define __Pyx_PyInt_FromHash_t PyInt_FromSsize_t #define __Pyx_PyInt_AsHash_t __Pyx_PyIndex_AsSsize_t #endif #if CYTHON_USE_ASYNC_SLOTS #if PY_VERSION_HEX >= 0x030500B1 #define __Pyx_PyAsyncMethodsStruct PyAsyncMethods #define __Pyx_PyType_AsAsync(obj) (Py_TYPE(obj)->tp_as_async) #else #define __Pyx_PyType_AsAsync(obj) ((__Pyx_PyAsyncMethodsStruct*) (Py_TYPE(obj)->tp_reserved)) #endif #else #define __Pyx_PyType_AsAsync(obj) NULL #endif #ifndef __Pyx_PyAsyncMethodsStruct typedef struct { unaryfunc am_await; unaryfunc am_aiter; unaryfunc am_anext; } __Pyx_PyAsyncMethodsStruct; #endif #if defined(_WIN32) || defined(WIN32) || defined(MS_WINDOWS) #if !defined(_USE_MATH_DEFINES) #define _USE_MATH_DEFINES #endif #endif #include #ifdef NAN #define __PYX_NAN() ((float) NAN) #else static CYTHON_INLINE float __PYX_NAN() { float value; memset(&value, 0xFF, sizeof(value)); return value; } #endif #if defined(__CYGWIN__) && defined(_LDBL_EQ_DBL) #define __Pyx_truncl trunc #else #define __Pyx_truncl truncl #endif #define __PYX_MARK_ERR_POS(f_index, lineno) \ { __pyx_filename = __pyx_f[f_index]; (void)__pyx_filename; __pyx_lineno = lineno; (void)__pyx_lineno; __pyx_clineno = __LINE__; (void)__pyx_clineno; } #define __PYX_ERR(f_index, lineno, Ln_error) \ { __PYX_MARK_ERR_POS(f_index, lineno) goto Ln_error; } #ifdef CYTHON_EXTERN_C #undef __PYX_EXTERN_C #define __PYX_EXTERN_C CYTHON_EXTERN_C #elif defined(__PYX_EXTERN_C) #ifdef _MSC_VER #pragma message ("Please do not define the '__PYX_EXTERN_C' macro externally. Use 'CYTHON_EXTERN_C' instead.") #else #warning Please do not define the '__PYX_EXTERN_C' macro externally. Use 'CYTHON_EXTERN_C' instead. #endif #else #define __PYX_EXTERN_C extern "C++" #endif #define __PYX_HAVE__curated_tokenizers___bbpe #define __PYX_HAVE_API__curated_tokenizers___bbpe /* Early includes */ #include #include #include "ios" #include "new" #include "stdexcept" #include "typeinfo" #include #include #if __cplusplus >= 201103L || (defined(_MSC_VER) && _MSC_VER >= 1600) // move should be defined for these versions of MSVC, but __cplusplus isn't set usefully #include namespace cython_std { template typename std::remove_reference::type&& move(T& t) noexcept { return std::move(t); } template typename std::remove_reference::type&& move(T&& t) noexcept { return std::move(t); } } #endif #include "merges.hh" #include #ifdef _OPENMP #include #endif /* _OPENMP */ #if defined(PYREX_WITHOUT_ASSERTIONS) && !defined(CYTHON_WITHOUT_ASSERTIONS) #define CYTHON_WITHOUT_ASSERTIONS #endif typedef struct {PyObject **p; const char *s; const Py_ssize_t n; const char* encoding; const char is_unicode; const char is_str; const char intern; } __Pyx_StringTabEntry; #define __PYX_DEFAULT_STRING_ENCODING_IS_ASCII 0 #define __PYX_DEFAULT_STRING_ENCODING_IS_UTF8 0 #define __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT (PY_MAJOR_VERSION >= 3 && __PYX_DEFAULT_STRING_ENCODING_IS_UTF8) #define __PYX_DEFAULT_STRING_ENCODING "" #define __Pyx_PyObject_FromString __Pyx_PyBytes_FromString #define __Pyx_PyObject_FromStringAndSize __Pyx_PyBytes_FromStringAndSize #define __Pyx_uchar_cast(c) ((unsigned char)c) #define __Pyx_long_cast(x) ((long)x) #define __Pyx_fits_Py_ssize_t(v, type, is_signed) (\ (sizeof(type) < sizeof(Py_ssize_t)) ||\ (sizeof(type) > sizeof(Py_ssize_t) &&\ likely(v < (type)PY_SSIZE_T_MAX ||\ v == (type)PY_SSIZE_T_MAX) &&\ (!is_signed || likely(v > (type)PY_SSIZE_T_MIN ||\ v == (type)PY_SSIZE_T_MIN))) ||\ (sizeof(type) == sizeof(Py_ssize_t) &&\ (is_signed || likely(v < (type)PY_SSIZE_T_MAX ||\ v == (type)PY_SSIZE_T_MAX))) ) static CYTHON_INLINE int __Pyx_is_valid_index(Py_ssize_t i, Py_ssize_t limit) { return (size_t) i < (size_t) limit; } #if defined (__cplusplus) && __cplusplus >= 201103L #include #define __Pyx_sst_abs(value) std::abs(value) #elif SIZEOF_INT >= SIZEOF_SIZE_T #define __Pyx_sst_abs(value) abs(value) #elif SIZEOF_LONG >= SIZEOF_SIZE_T #define __Pyx_sst_abs(value) labs(value) #elif defined (_MSC_VER) #define __Pyx_sst_abs(value) ((Py_ssize_t)_abs64(value)) #elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L #define __Pyx_sst_abs(value) llabs(value) #elif defined (__GNUC__) #define __Pyx_sst_abs(value) __builtin_llabs(value) #else #define __Pyx_sst_abs(value) ((value<0) ? -value : value) #endif static CYTHON_INLINE Py_ssize_t __Pyx_ssize_strlen(const char *s); static CYTHON_INLINE const char* __Pyx_PyObject_AsString(PyObject*); static CYTHON_INLINE const char* __Pyx_PyObject_AsStringAndSize(PyObject*, Py_ssize_t* length); static CYTHON_INLINE PyObject* __Pyx_PyByteArray_FromString(const char*); #define __Pyx_PyByteArray_FromStringAndSize(s, l) PyByteArray_FromStringAndSize((const char*)s, l) #define __Pyx_PyBytes_FromString PyBytes_FromString #define __Pyx_PyBytes_FromStringAndSize PyBytes_FromStringAndSize static CYTHON_INLINE PyObject* __Pyx_PyUnicode_FromString(const char*); #if PY_MAJOR_VERSION < 3 #define __Pyx_PyStr_FromString __Pyx_PyBytes_FromString #define __Pyx_PyStr_FromStringAndSize __Pyx_PyBytes_FromStringAndSize #else #define __Pyx_PyStr_FromString __Pyx_PyUnicode_FromString #define __Pyx_PyStr_FromStringAndSize __Pyx_PyUnicode_FromStringAndSize #endif #define __Pyx_PyBytes_AsWritableString(s) ((char*) PyBytes_AS_STRING(s)) #define __Pyx_PyBytes_AsWritableSString(s) ((signed char*) PyBytes_AS_STRING(s)) #define __Pyx_PyBytes_AsWritableUString(s) ((unsigned char*) PyBytes_AS_STRING(s)) #define __Pyx_PyBytes_AsString(s) ((const char*) PyBytes_AS_STRING(s)) #define __Pyx_PyBytes_AsSString(s) ((const signed char*) PyBytes_AS_STRING(s)) #define __Pyx_PyBytes_AsUString(s) ((const unsigned char*) PyBytes_AS_STRING(s)) #define __Pyx_PyObject_AsWritableString(s) ((char*)(__pyx_uintptr_t) __Pyx_PyObject_AsString(s)) #define __Pyx_PyObject_AsWritableSString(s) ((signed char*)(__pyx_uintptr_t) __Pyx_PyObject_AsString(s)) #define __Pyx_PyObject_AsWritableUString(s) ((unsigned char*)(__pyx_uintptr_t) __Pyx_PyObject_AsString(s)) #define __Pyx_PyObject_AsSString(s) ((const signed char*) __Pyx_PyObject_AsString(s)) #define __Pyx_PyObject_AsUString(s) ((const unsigned char*) __Pyx_PyObject_AsString(s)) #define __Pyx_PyObject_FromCString(s) __Pyx_PyObject_FromString((const char*)s) #define __Pyx_PyBytes_FromCString(s) __Pyx_PyBytes_FromString((const char*)s) #define __Pyx_PyByteArray_FromCString(s) __Pyx_PyByteArray_FromString((const char*)s) #define __Pyx_PyStr_FromCString(s) __Pyx_PyStr_FromString((const char*)s) #define __Pyx_PyUnicode_FromCString(s) __Pyx_PyUnicode_FromString((const char*)s) #if CYTHON_COMPILING_IN_LIMITED_API static CYTHON_INLINE size_t __Pyx_Py_UNICODE_strlen(const wchar_t *u) { const wchar_t *u_end = u; while (*u_end++) ; return (size_t)(u_end - u - 1); } #else static CYTHON_INLINE size_t __Pyx_Py_UNICODE_strlen(const Py_UNICODE *u) { const Py_UNICODE *u_end = u; while (*u_end++) ; return (size_t)(u_end - u - 1); } #endif #define __Pyx_PyUnicode_FromOrdinal(o) PyUnicode_FromOrdinal((int)o) #define __Pyx_PyUnicode_FromUnicode(u) PyUnicode_FromUnicode(u, __Pyx_Py_UNICODE_strlen(u)) #define __Pyx_PyUnicode_FromUnicodeAndLength PyUnicode_FromUnicode #define __Pyx_PyUnicode_AsUnicode PyUnicode_AsUnicode #define __Pyx_NewRef(obj) (Py_INCREF(obj), obj) #define __Pyx_Owned_Py_None(b) __Pyx_NewRef(Py_None) static CYTHON_INLINE PyObject * __Pyx_PyBool_FromLong(long b); static CYTHON_INLINE int __Pyx_PyObject_IsTrue(PyObject*); static CYTHON_INLINE int __Pyx_PyObject_IsTrueAndDecref(PyObject*); static CYTHON_INLINE PyObject* __Pyx_PyNumber_IntOrLong(PyObject* x); #define __Pyx_PySequence_Tuple(obj)\ (likely(PyTuple_CheckExact(obj)) ? __Pyx_NewRef(obj) : PySequence_Tuple(obj)) static CYTHON_INLINE Py_ssize_t __Pyx_PyIndex_AsSsize_t(PyObject*); static CYTHON_INLINE PyObject * __Pyx_PyInt_FromSize_t(size_t); static CYTHON_INLINE Py_hash_t __Pyx_PyIndex_AsHash_t(PyObject*); #if CYTHON_ASSUME_SAFE_MACROS #define __pyx_PyFloat_AsDouble(x) (PyFloat_CheckExact(x) ? PyFloat_AS_DOUBLE(x) : PyFloat_AsDouble(x)) #else #define __pyx_PyFloat_AsDouble(x) PyFloat_AsDouble(x) #endif #define __pyx_PyFloat_AsFloat(x) ((float) __pyx_PyFloat_AsDouble(x)) #if PY_MAJOR_VERSION >= 3 #define __Pyx_PyNumber_Int(x) (PyLong_CheckExact(x) ? __Pyx_NewRef(x) : PyNumber_Long(x)) #else #define __Pyx_PyNumber_Int(x) (PyInt_CheckExact(x) ? __Pyx_NewRef(x) : PyNumber_Int(x)) #endif #if CYTHON_USE_PYLONG_INTERNALS #if PY_VERSION_HEX >= 0x030C00A7 #ifndef _PyLong_SIGN_MASK #define _PyLong_SIGN_MASK 3 #endif #ifndef _PyLong_NON_SIZE_BITS #define _PyLong_NON_SIZE_BITS 3 #endif #define __Pyx_PyLong_Sign(x) (((PyLongObject*)x)->long_value.lv_tag & _PyLong_SIGN_MASK) #define __Pyx_PyLong_IsNeg(x) ((__Pyx_PyLong_Sign(x) & 2) != 0) #define __Pyx_PyLong_IsNonNeg(x) (!__Pyx_PyLong_IsNeg(x)) #define __Pyx_PyLong_IsZero(x) (__Pyx_PyLong_Sign(x) & 1) #define __Pyx_PyLong_IsPos(x) (__Pyx_PyLong_Sign(x) == 0) #define __Pyx_PyLong_CompactValueUnsigned(x) (__Pyx_PyLong_Digits(x)[0]) #define __Pyx_PyLong_DigitCount(x) ((Py_ssize_t) (((PyLongObject*)x)->long_value.lv_tag >> _PyLong_NON_SIZE_BITS)) #define __Pyx_PyLong_SignedDigitCount(x)\ ((1 - (Py_ssize_t) __Pyx_PyLong_Sign(x)) * __Pyx_PyLong_DigitCount(x)) #if defined(PyUnstable_Long_IsCompact) && defined(PyUnstable_Long_CompactValue) #define __Pyx_PyLong_IsCompact(x) PyUnstable_Long_IsCompact((PyLongObject*) x) #define __Pyx_PyLong_CompactValue(x) PyUnstable_Long_CompactValue((PyLongObject*) x) #else #define __Pyx_PyLong_IsCompact(x) (((PyLongObject*)x)->long_value.lv_tag < (2 << _PyLong_NON_SIZE_BITS)) #define __Pyx_PyLong_CompactValue(x) ((1 - (Py_ssize_t) __Pyx_PyLong_Sign(x)) * (Py_ssize_t) __Pyx_PyLong_Digits(x)[0]) #endif typedef Py_ssize_t __Pyx_compact_pylong; typedef size_t __Pyx_compact_upylong; #else #define __Pyx_PyLong_IsNeg(x) (Py_SIZE(x) < 0) #define __Pyx_PyLong_IsNonNeg(x) (Py_SIZE(x) >= 0) #define __Pyx_PyLong_IsZero(x) (Py_SIZE(x) == 0) #define __Pyx_PyLong_IsPos(x) (Py_SIZE(x) > 0) #define __Pyx_PyLong_CompactValueUnsigned(x) ((Py_SIZE(x) == 0) ? 0 : __Pyx_PyLong_Digits(x)[0]) #define __Pyx_PyLong_DigitCount(x) __Pyx_sst_abs(Py_SIZE(x)) #define __Pyx_PyLong_SignedDigitCount(x) Py_SIZE(x) #define __Pyx_PyLong_IsCompact(x) (Py_SIZE(x) == 0 || Py_SIZE(x) == 1 || Py_SIZE(x) == -1) #define __Pyx_PyLong_CompactValue(x)\ ((Py_SIZE(x) == 0) ? (sdigit) 0 : ((Py_SIZE(x) < 0) ? -(sdigit)__Pyx_PyLong_Digits(x)[0] : (sdigit)__Pyx_PyLong_Digits(x)[0])) typedef sdigit __Pyx_compact_pylong; typedef digit __Pyx_compact_upylong; #endif #if PY_VERSION_HEX >= 0x030C00A5 #define __Pyx_PyLong_Digits(x) (((PyLongObject*)x)->long_value.ob_digit) #else #define __Pyx_PyLong_Digits(x) (((PyLongObject*)x)->ob_digit) #endif #endif #if PY_MAJOR_VERSION < 3 && __PYX_DEFAULT_STRING_ENCODING_IS_ASCII #include static int __Pyx_sys_getdefaultencoding_not_ascii; static int __Pyx_init_sys_getdefaultencoding_params(void) { PyObject* sys; PyObject* default_encoding = NULL; PyObject* ascii_chars_u = NULL; PyObject* ascii_chars_b = NULL; const char* default_encoding_c; sys = PyImport_ImportModule("sys"); if (!sys) goto bad; default_encoding = PyObject_CallMethod(sys, (char*) "getdefaultencoding", NULL); Py_DECREF(sys); if (!default_encoding) goto bad; default_encoding_c = PyBytes_AsString(default_encoding); if (!default_encoding_c) goto bad; if (strcmp(default_encoding_c, "ascii") == 0) { __Pyx_sys_getdefaultencoding_not_ascii = 0; } else { char ascii_chars[128]; int c; for (c = 0; c < 128; c++) { ascii_chars[c] = (char) c; } __Pyx_sys_getdefaultencoding_not_ascii = 1; ascii_chars_u = PyUnicode_DecodeASCII(ascii_chars, 128, NULL); if (!ascii_chars_u) goto bad; ascii_chars_b = PyUnicode_AsEncodedString(ascii_chars_u, default_encoding_c, NULL); if (!ascii_chars_b || !PyBytes_Check(ascii_chars_b) || memcmp(ascii_chars, PyBytes_AS_STRING(ascii_chars_b), 128) != 0) { PyErr_Format( PyExc_ValueError, "This module compiled with c_string_encoding=ascii, but default encoding '%.200s' is not a superset of ascii.", default_encoding_c); goto bad; } Py_DECREF(ascii_chars_u); Py_DECREF(ascii_chars_b); } Py_DECREF(default_encoding); return 0; bad: Py_XDECREF(default_encoding); Py_XDECREF(ascii_chars_u); Py_XDECREF(ascii_chars_b); return -1; } #endif #if __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT && PY_MAJOR_VERSION >= 3 #define __Pyx_PyUnicode_FromStringAndSize(c_str, size) PyUnicode_DecodeUTF8(c_str, size, NULL) #else #define __Pyx_PyUnicode_FromStringAndSize(c_str, size) PyUnicode_Decode(c_str, size, __PYX_DEFAULT_STRING_ENCODING, NULL) #if __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT #include static char* __PYX_DEFAULT_STRING_ENCODING; static int __Pyx_init_sys_getdefaultencoding_params(void) { PyObject* sys; PyObject* default_encoding = NULL; char* default_encoding_c; sys = PyImport_ImportModule("sys"); if (!sys) goto bad; default_encoding = PyObject_CallMethod(sys, (char*) (const char*) "getdefaultencoding", NULL); Py_DECREF(sys); if (!default_encoding) goto bad; default_encoding_c = PyBytes_AsString(default_encoding); if (!default_encoding_c) goto bad; __PYX_DEFAULT_STRING_ENCODING = (char*) malloc(strlen(default_encoding_c) + 1); if (!__PYX_DEFAULT_STRING_ENCODING) goto bad; strcpy(__PYX_DEFAULT_STRING_ENCODING, default_encoding_c); Py_DECREF(default_encoding); return 0; bad: Py_XDECREF(default_encoding); return -1; } #endif #endif /* Test for GCC > 2.95 */ #if defined(__GNUC__) && (__GNUC__ > 2 || (__GNUC__ == 2 && (__GNUC_MINOR__ > 95))) #define likely(x) __builtin_expect(!!(x), 1) #define unlikely(x) __builtin_expect(!!(x), 0) #else /* !__GNUC__ or GCC < 2.95 */ #define likely(x) (x) #define unlikely(x) (x) #endif /* __GNUC__ */ static CYTHON_INLINE void __Pyx_pretend_to_initialize(void* ptr) { (void)ptr; } #if !CYTHON_USE_MODULE_STATE static PyObject *__pyx_m = NULL; #endif static int __pyx_lineno; static int __pyx_clineno = 0; static const char * __pyx_cfilenm = __FILE__; static const char *__pyx_filename; /* #### Code section: filename_table ### */ static const char *__pyx_f[] = { "curated_tokenizers\\\\_bbpe.pyx", "", }; /* #### Code section: utility_code_proto_before_types ### */ /* ForceInitThreads.proto */ #ifndef __PYX_FORCE_INIT_THREADS #define __PYX_FORCE_INIT_THREADS 0 #endif /* #### Code section: numeric_typedefs ### */ /* #### Code section: complex_type_declarations ### */ /* #### Code section: type_declarations ### */ /*--- Type declarations ---*/ struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor; struct __pyx_obj_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr; /* "curated_tokenizers/_bbpe.pyx":50 * return dict(zip(bs, cs)) * * cdef class ByteBPEProcessor: # <<<<<<<<<<<<<< * cdef shared_ptr[Merges] _merges * cdef dict _byte_decoder */ struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor { PyObject_HEAD std::shared_ptr _merges; PyObject *_byte_decoder; PyObject *_byte_encoder; PyObject *_split_pattern; PyObject *_piece_to_id; PyObject *_id_to_piece; }; /* "curated_tokenizers/_bbpe.pyx":141 * token_bytes = [self._byte_encoder[b] for b in token.encode("utf-8")] * merged = deref(self._merges).apply_merges(token_bytes) * pieces.extend(merge.decode("utf-8") for merge in merged) # <<<<<<<<<<<<<< * return pieces * */ struct __pyx_obj_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr { PyObject_HEAD std::vector __pyx_genexpr_arg_0; std::string __pyx_v_merge; std::vector ::iterator __pyx_t_0; }; /* #### Code section: utility_code_proto ### */ /* --- Runtime support code (head) --- */ /* Refnanny.proto */ #ifndef CYTHON_REFNANNY #define CYTHON_REFNANNY 0 #endif #if CYTHON_REFNANNY typedef struct { void (*INCREF)(void*, PyObject*, Py_ssize_t); void (*DECREF)(void*, PyObject*, Py_ssize_t); void (*GOTREF)(void*, PyObject*, Py_ssize_t); void (*GIVEREF)(void*, PyObject*, Py_ssize_t); void* (*SetupContext)(const char*, Py_ssize_t, const char*); void (*FinishContext)(void**); } __Pyx_RefNannyAPIStruct; static __Pyx_RefNannyAPIStruct *__Pyx_RefNanny = NULL; static __Pyx_RefNannyAPIStruct *__Pyx_RefNannyImportAPI(const char *modname); #define __Pyx_RefNannyDeclarations void *__pyx_refnanny = NULL; #ifdef WITH_THREAD #define __Pyx_RefNannySetupContext(name, acquire_gil)\ if (acquire_gil) {\ PyGILState_STATE __pyx_gilstate_save = PyGILState_Ensure();\ __pyx_refnanny = __Pyx_RefNanny->SetupContext((name), (__LINE__), (__FILE__));\ PyGILState_Release(__pyx_gilstate_save);\ } else {\ __pyx_refnanny = __Pyx_RefNanny->SetupContext((name), (__LINE__), (__FILE__));\ } #define __Pyx_RefNannyFinishContextNogil() {\ PyGILState_STATE __pyx_gilstate_save = PyGILState_Ensure();\ __Pyx_RefNannyFinishContext();\ PyGILState_Release(__pyx_gilstate_save);\ } #else #define __Pyx_RefNannySetupContext(name, acquire_gil)\ __pyx_refnanny = __Pyx_RefNanny->SetupContext((name), (__LINE__), (__FILE__)) #define __Pyx_RefNannyFinishContextNogil() __Pyx_RefNannyFinishContext() #endif #define __Pyx_RefNannyFinishContextNogil() {\ PyGILState_STATE __pyx_gilstate_save = PyGILState_Ensure();\ __Pyx_RefNannyFinishContext();\ PyGILState_Release(__pyx_gilstate_save);\ } #define __Pyx_RefNannyFinishContext()\ __Pyx_RefNanny->FinishContext(&__pyx_refnanny) #define __Pyx_INCREF(r) __Pyx_RefNanny->INCREF(__pyx_refnanny, (PyObject *)(r), (__LINE__)) #define __Pyx_DECREF(r) __Pyx_RefNanny->DECREF(__pyx_refnanny, (PyObject *)(r), (__LINE__)) #define __Pyx_GOTREF(r) __Pyx_RefNanny->GOTREF(__pyx_refnanny, (PyObject *)(r), (__LINE__)) #define __Pyx_GIVEREF(r) __Pyx_RefNanny->GIVEREF(__pyx_refnanny, (PyObject *)(r), (__LINE__)) #define __Pyx_XINCREF(r) do { if((r) == NULL); else {__Pyx_INCREF(r); }} while(0) #define __Pyx_XDECREF(r) do { if((r) == NULL); else {__Pyx_DECREF(r); }} while(0) #define __Pyx_XGOTREF(r) do { if((r) == NULL); else {__Pyx_GOTREF(r); }} while(0) #define __Pyx_XGIVEREF(r) do { if((r) == NULL); else {__Pyx_GIVEREF(r);}} while(0) #else #define __Pyx_RefNannyDeclarations #define __Pyx_RefNannySetupContext(name, acquire_gil) #define __Pyx_RefNannyFinishContextNogil() #define __Pyx_RefNannyFinishContext() #define __Pyx_INCREF(r) Py_INCREF(r) #define __Pyx_DECREF(r) Py_DECREF(r) #define __Pyx_GOTREF(r) #define __Pyx_GIVEREF(r) #define __Pyx_XINCREF(r) Py_XINCREF(r) #define __Pyx_XDECREF(r) Py_XDECREF(r) #define __Pyx_XGOTREF(r) #define __Pyx_XGIVEREF(r) #endif #define __Pyx_Py_XDECREF_SET(r, v) do {\ PyObject *tmp = (PyObject *) r;\ r = v; Py_XDECREF(tmp);\ } while (0) #define __Pyx_XDECREF_SET(r, v) do {\ PyObject *tmp = (PyObject *) r;\ r = v; __Pyx_XDECREF(tmp);\ } while (0) #define __Pyx_DECREF_SET(r, v) do {\ PyObject *tmp = (PyObject *) r;\ r = v; __Pyx_DECREF(tmp);\ } while (0) #define __Pyx_CLEAR(r) do { PyObject* tmp = ((PyObject*)(r)); r = NULL; __Pyx_DECREF(tmp);} while(0) #define __Pyx_XCLEAR(r) do { if((r) != NULL) {PyObject* tmp = ((PyObject*)(r)); r = NULL; __Pyx_DECREF(tmp);}} while(0) /* PyErrExceptionMatches.proto */ #if CYTHON_FAST_THREAD_STATE #define __Pyx_PyErr_ExceptionMatches(err) __Pyx_PyErr_ExceptionMatchesInState(__pyx_tstate, err) static CYTHON_INLINE int __Pyx_PyErr_ExceptionMatchesInState(PyThreadState* tstate, PyObject* err); #else #define __Pyx_PyErr_ExceptionMatches(err) PyErr_ExceptionMatches(err) #endif /* PyThreadStateGet.proto */ #if CYTHON_FAST_THREAD_STATE #define __Pyx_PyThreadState_declare PyThreadState *__pyx_tstate; #define __Pyx_PyThreadState_assign __pyx_tstate = __Pyx_PyThreadState_Current; #if PY_VERSION_HEX >= 0x030C00A6 #define __Pyx_PyErr_Occurred() (__pyx_tstate->current_exception != NULL) #define __Pyx_PyErr_CurrentExceptionType() (__pyx_tstate->current_exception ? (PyObject*) Py_TYPE(__pyx_tstate->current_exception) : (PyObject*) NULL) #else #define __Pyx_PyErr_Occurred() (__pyx_tstate->curexc_type != NULL) #define __Pyx_PyErr_CurrentExceptionType() (__pyx_tstate->curexc_type) #endif #else #define __Pyx_PyThreadState_declare #define __Pyx_PyThreadState_assign #define __Pyx_PyErr_Occurred() (PyErr_Occurred() != NULL) #define __Pyx_PyErr_CurrentExceptionType() PyErr_Occurred() #endif /* PyErrFetchRestore.proto */ #if CYTHON_FAST_THREAD_STATE #define __Pyx_PyErr_Clear() __Pyx_ErrRestore(NULL, NULL, NULL) #define __Pyx_ErrRestoreWithState(type, value, tb) __Pyx_ErrRestoreInState(PyThreadState_GET(), type, value, tb) #define __Pyx_ErrFetchWithState(type, value, tb) __Pyx_ErrFetchInState(PyThreadState_GET(), type, value, tb) #define __Pyx_ErrRestore(type, value, tb) __Pyx_ErrRestoreInState(__pyx_tstate, type, value, tb) #define __Pyx_ErrFetch(type, value, tb) __Pyx_ErrFetchInState(__pyx_tstate, type, value, tb) static CYTHON_INLINE void __Pyx_ErrRestoreInState(PyThreadState *tstate, PyObject *type, PyObject *value, PyObject *tb); static CYTHON_INLINE void __Pyx_ErrFetchInState(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb); #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX < 0x030C00A6 #define __Pyx_PyErr_SetNone(exc) (Py_INCREF(exc), __Pyx_ErrRestore((exc), NULL, NULL)) #else #define __Pyx_PyErr_SetNone(exc) PyErr_SetNone(exc) #endif #else #define __Pyx_PyErr_Clear() PyErr_Clear() #define __Pyx_PyErr_SetNone(exc) PyErr_SetNone(exc) #define __Pyx_ErrRestoreWithState(type, value, tb) PyErr_Restore(type, value, tb) #define __Pyx_ErrFetchWithState(type, value, tb) PyErr_Fetch(type, value, tb) #define __Pyx_ErrRestoreInState(tstate, type, value, tb) PyErr_Restore(type, value, tb) #define __Pyx_ErrFetchInState(tstate, type, value, tb) PyErr_Fetch(type, value, tb) #define __Pyx_ErrRestore(type, value, tb) PyErr_Restore(type, value, tb) #define __Pyx_ErrFetch(type, value, tb) PyErr_Fetch(type, value, tb) #endif /* PyObjectGetAttrStr.proto */ #if CYTHON_USE_TYPE_SLOTS static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name); #else #define __Pyx_PyObject_GetAttrStr(o,n) PyObject_GetAttr(o,n) #endif /* PyObjectGetAttrStrNoError.proto */ static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStrNoError(PyObject* obj, PyObject* attr_name); /* GetBuiltinName.proto */ static PyObject *__Pyx_GetBuiltinName(PyObject *name); /* TupleAndListFromArray.proto */ #if CYTHON_COMPILING_IN_CPYTHON static CYTHON_INLINE PyObject* __Pyx_PyList_FromArray(PyObject *const *src, Py_ssize_t n); static CYTHON_INLINE PyObject* __Pyx_PyTuple_FromArray(PyObject *const *src, Py_ssize_t n); #endif /* IncludeStringH.proto */ #include /* BytesEquals.proto */ static CYTHON_INLINE int __Pyx_PyBytes_Equals(PyObject* s1, PyObject* s2, int equals); /* UnicodeEquals.proto */ static CYTHON_INLINE int __Pyx_PyUnicode_Equals(PyObject* s1, PyObject* s2, int equals); /* fastcall.proto */ #if CYTHON_AVOID_BORROWED_REFS #define __Pyx_Arg_VARARGS(args, i) PySequence_GetItem(args, i) #elif CYTHON_ASSUME_SAFE_MACROS #define __Pyx_Arg_VARARGS(args, i) PyTuple_GET_ITEM(args, i) #else #define __Pyx_Arg_VARARGS(args, i) PyTuple_GetItem(args, i) #endif #if CYTHON_AVOID_BORROWED_REFS #define __Pyx_Arg_NewRef_VARARGS(arg) __Pyx_NewRef(arg) #define __Pyx_Arg_XDECREF_VARARGS(arg) Py_XDECREF(arg) #else #define __Pyx_Arg_NewRef_VARARGS(arg) arg #define __Pyx_Arg_XDECREF_VARARGS(arg) #endif #define __Pyx_NumKwargs_VARARGS(kwds) PyDict_Size(kwds) #define __Pyx_KwValues_VARARGS(args, nargs) NULL #define __Pyx_GetKwValue_VARARGS(kw, kwvalues, s) __Pyx_PyDict_GetItemStrWithError(kw, s) #define __Pyx_KwargsAsDict_VARARGS(kw, kwvalues) PyDict_Copy(kw) #if CYTHON_METH_FASTCALL #define __Pyx_Arg_FASTCALL(args, i) args[i] #define __Pyx_NumKwargs_FASTCALL(kwds) PyTuple_GET_SIZE(kwds) #define __Pyx_KwValues_FASTCALL(args, nargs) ((args) + (nargs)) static CYTHON_INLINE PyObject * __Pyx_GetKwValue_FASTCALL(PyObject *kwnames, PyObject *const *kwvalues, PyObject *s); #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030d0000 CYTHON_UNUSED static PyObject *__Pyx_KwargsAsDict_FASTCALL(PyObject *kwnames, PyObject *const *kwvalues); #else #define __Pyx_KwargsAsDict_FASTCALL(kw, kwvalues) _PyStack_AsDict(kwvalues, kw) #endif #define __Pyx_Arg_NewRef_FASTCALL(arg) arg /* no-op, __Pyx_Arg_FASTCALL is direct and this needs to have the same reference counting */ #define __Pyx_Arg_XDECREF_FASTCALL(arg) #else #define __Pyx_Arg_FASTCALL __Pyx_Arg_VARARGS #define __Pyx_NumKwargs_FASTCALL __Pyx_NumKwargs_VARARGS #define __Pyx_KwValues_FASTCALL __Pyx_KwValues_VARARGS #define __Pyx_GetKwValue_FASTCALL __Pyx_GetKwValue_VARARGS #define __Pyx_KwargsAsDict_FASTCALL __Pyx_KwargsAsDict_VARARGS #define __Pyx_Arg_NewRef_FASTCALL(arg) __Pyx_Arg_NewRef_VARARGS(arg) #define __Pyx_Arg_XDECREF_FASTCALL(arg) __Pyx_Arg_XDECREF_VARARGS(arg) #endif #if CYTHON_COMPILING_IN_CPYTHON && CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS #define __Pyx_ArgsSlice_VARARGS(args, start, stop) __Pyx_PyTuple_FromArray(&__Pyx_Arg_VARARGS(args, start), stop - start) #define __Pyx_ArgsSlice_FASTCALL(args, start, stop) __Pyx_PyTuple_FromArray(&__Pyx_Arg_FASTCALL(args, start), stop - start) #else #define __Pyx_ArgsSlice_VARARGS(args, start, stop) PyTuple_GetSlice(args, start, stop) #define __Pyx_ArgsSlice_FASTCALL(args, start, stop) PyTuple_GetSlice(args, start, stop) #endif /* PyObjectCall.proto */ #if CYTHON_COMPILING_IN_CPYTHON static CYTHON_INLINE PyObject* __Pyx_PyObject_Call(PyObject *func, PyObject *arg, PyObject *kw); #else #define __Pyx_PyObject_Call(func, arg, kw) PyObject_Call(func, arg, kw) #endif /* SliceTupleAndList.proto */ #if CYTHON_COMPILING_IN_CPYTHON static CYTHON_INLINE PyObject* __Pyx_PyList_GetSlice(PyObject* src, Py_ssize_t start, Py_ssize_t stop); static CYTHON_INLINE PyObject* __Pyx_PyTuple_GetSlice(PyObject* src, Py_ssize_t start, Py_ssize_t stop); #else #define __Pyx_PyList_GetSlice(seq, start, stop) PySequence_GetSlice(seq, start, stop) #define __Pyx_PyTuple_GetSlice(seq, start, stop) PySequence_GetSlice(seq, start, stop) #endif /* PySequenceContains.proto */ static CYTHON_INLINE int __Pyx_PySequence_ContainsTF(PyObject* item, PyObject* seq, int eq) { int result = PySequence_Contains(seq, item); return unlikely(result < 0) ? result : (result == (eq == Py_EQ)); } /* ListAppend.proto */ #if CYTHON_USE_PYLIST_INTERNALS && CYTHON_ASSUME_SAFE_MACROS static CYTHON_INLINE int __Pyx_PyList_Append(PyObject* list, PyObject* x) { PyListObject* L = (PyListObject*) list; Py_ssize_t len = Py_SIZE(list); if (likely(L->allocated > len) & likely(len > (L->allocated >> 1))) { Py_INCREF(x); #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030d0000 L->ob_item[len] = x; #else PyList_SET_ITEM(list, len, x); #endif __Pyx_SET_SIZE(list, len + 1); return 0; } return PyList_Append(list, x); } #else #define __Pyx_PyList_Append(L,x) PyList_Append(L,x) #endif /* PyIntBinop.proto */ #if !CYTHON_COMPILING_IN_PYPY static PyObject* __Pyx_PyInt_AddCObj(PyObject *op1, PyObject *op2, long intval, int inplace, int zerodivision_check); #else #define __Pyx_PyInt_AddCObj(op1, op2, intval, inplace, zerodivision_check)\ (inplace ? PyNumber_InPlaceAdd(op1, op2) : PyNumber_Add(op1, op2)) #endif /* PyIntBinop.proto */ #if !CYTHON_COMPILING_IN_PYPY static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, long intval, int inplace, int zerodivision_check); #else #define __Pyx_PyInt_AddObjC(op1, op2, intval, inplace, zerodivision_check)\ (inplace ? PyNumber_InPlaceAdd(op1, op2) : PyNumber_Add(op1, op2)) #endif /* ListCompAppend.proto */ #if CYTHON_USE_PYLIST_INTERNALS && CYTHON_ASSUME_SAFE_MACROS static CYTHON_INLINE int __Pyx_ListComp_Append(PyObject* list, PyObject* x) { PyListObject* L = (PyListObject*) list; Py_ssize_t len = Py_SIZE(list); if (likely(L->allocated > len)) { Py_INCREF(x); #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030d0000 L->ob_item[len] = x; #else PyList_SET_ITEM(list, len, x); #endif __Pyx_SET_SIZE(list, len + 1); return 0; } return PyList_Append(list, x); } #else #define __Pyx_ListComp_Append(L,x) PyList_Append(L,x) #endif /* PyFunctionFastCall.proto */ #if CYTHON_FAST_PYCALL #if !CYTHON_VECTORCALL #define __Pyx_PyFunction_FastCall(func, args, nargs)\ __Pyx_PyFunction_FastCallDict((func), (args), (nargs), NULL) static PyObject *__Pyx_PyFunction_FastCallDict(PyObject *func, PyObject **args, Py_ssize_t nargs, PyObject *kwargs); #endif #define __Pyx_BUILD_ASSERT_EXPR(cond)\ (sizeof(char [1 - 2*!(cond)]) - 1) #ifndef Py_MEMBER_SIZE #define Py_MEMBER_SIZE(type, member) sizeof(((type *)0)->member) #endif #if !CYTHON_VECTORCALL #if PY_VERSION_HEX >= 0x03080000 #include "frameobject.h" #if PY_VERSION_HEX >= 0x030b00a6 && !CYTHON_COMPILING_IN_LIMITED_API #ifndef Py_BUILD_CORE #define Py_BUILD_CORE 1 #endif #include "internal/pycore_frame.h" #endif #define __Pxy_PyFrame_Initialize_Offsets() #define __Pyx_PyFrame_GetLocalsplus(frame) ((frame)->f_localsplus) #else static size_t __pyx_pyframe_localsplus_offset = 0; #include "frameobject.h" #define __Pxy_PyFrame_Initialize_Offsets()\ ((void)__Pyx_BUILD_ASSERT_EXPR(sizeof(PyFrameObject) == offsetof(PyFrameObject, f_localsplus) + Py_MEMBER_SIZE(PyFrameObject, f_localsplus)),\ (void)(__pyx_pyframe_localsplus_offset = ((size_t)PyFrame_Type.tp_basicsize) - Py_MEMBER_SIZE(PyFrameObject, f_localsplus))) #define __Pyx_PyFrame_GetLocalsplus(frame)\ (assert(__pyx_pyframe_localsplus_offset), (PyObject **)(((char *)(frame)) + __pyx_pyframe_localsplus_offset)) #endif #endif #endif /* PyObjectCallMethO.proto */ #if CYTHON_COMPILING_IN_CPYTHON static CYTHON_INLINE PyObject* __Pyx_PyObject_CallMethO(PyObject *func, PyObject *arg); #endif /* PyObjectFastCall.proto */ #define __Pyx_PyObject_FastCall(func, args, nargs) __Pyx_PyObject_FastCallDict(func, args, (size_t)(nargs), NULL) static CYTHON_INLINE PyObject* __Pyx_PyObject_FastCallDict(PyObject *func, PyObject **args, size_t nargs, PyObject *kwargs); /* PyObjectCallOneArg.proto */ static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObject *arg); /* RaiseArgTupleInvalid.proto */ static void __Pyx_RaiseArgtupleInvalid(const char* func_name, int exact, Py_ssize_t num_min, Py_ssize_t num_max, Py_ssize_t num_found); /* RaiseDoubleKeywords.proto */ static void __Pyx_RaiseDoubleKeywordsError(const char* func_name, PyObject* kw_name); /* ParseKeywords.proto */ static int __Pyx_ParseOptionalKeywords(PyObject *kwds, PyObject *const *kwvalues, PyObject **argnames[], PyObject *kwds2, PyObject *values[], Py_ssize_t num_pos_args, const char* function_name); /* PyDictVersioning.proto */ #if CYTHON_USE_DICT_VERSIONS && CYTHON_USE_TYPE_SLOTS #define __PYX_DICT_VERSION_INIT ((PY_UINT64_T) -1) #define __PYX_GET_DICT_VERSION(dict) (((PyDictObject*)(dict))->ma_version_tag) #define __PYX_UPDATE_DICT_CACHE(dict, value, cache_var, version_var)\ (version_var) = __PYX_GET_DICT_VERSION(dict);\ (cache_var) = (value); #define __PYX_PY_DICT_LOOKUP_IF_MODIFIED(VAR, DICT, LOOKUP) {\ static PY_UINT64_T __pyx_dict_version = 0;\ static PyObject *__pyx_dict_cached_value = NULL;\ if (likely(__PYX_GET_DICT_VERSION(DICT) == __pyx_dict_version)) {\ (VAR) = __pyx_dict_cached_value;\ } else {\ (VAR) = __pyx_dict_cached_value = (LOOKUP);\ __pyx_dict_version = __PYX_GET_DICT_VERSION(DICT);\ }\ } static CYTHON_INLINE PY_UINT64_T __Pyx_get_tp_dict_version(PyObject *obj); static CYTHON_INLINE PY_UINT64_T __Pyx_get_object_dict_version(PyObject *obj); static CYTHON_INLINE int __Pyx_object_dict_version_matches(PyObject* obj, PY_UINT64_T tp_dict_version, PY_UINT64_T obj_dict_version); #else #define __PYX_GET_DICT_VERSION(dict) (0) #define __PYX_UPDATE_DICT_CACHE(dict, value, cache_var, version_var) #define __PYX_PY_DICT_LOOKUP_IF_MODIFIED(VAR, DICT, LOOKUP) (VAR) = (LOOKUP); #endif /* GetModuleGlobalName.proto */ #if CYTHON_USE_DICT_VERSIONS #define __Pyx_GetModuleGlobalName(var, name) do {\ static PY_UINT64_T __pyx_dict_version = 0;\ static PyObject *__pyx_dict_cached_value = NULL;\ (var) = (likely(__pyx_dict_version == __PYX_GET_DICT_VERSION(__pyx_d))) ?\ (likely(__pyx_dict_cached_value) ? __Pyx_NewRef(__pyx_dict_cached_value) : __Pyx_GetBuiltinName(name)) :\ __Pyx__GetModuleGlobalName(name, &__pyx_dict_version, &__pyx_dict_cached_value);\ } while(0) #define __Pyx_GetModuleGlobalNameUncached(var, name) do {\ PY_UINT64_T __pyx_dict_version;\ PyObject *__pyx_dict_cached_value;\ (var) = __Pyx__GetModuleGlobalName(name, &__pyx_dict_version, &__pyx_dict_cached_value);\ } while(0) static PyObject *__Pyx__GetModuleGlobalName(PyObject *name, PY_UINT64_T *dict_version, PyObject **dict_cached_value); #else #define __Pyx_GetModuleGlobalName(var, name) (var) = __Pyx__GetModuleGlobalName(name) #define __Pyx_GetModuleGlobalNameUncached(var, name) (var) = __Pyx__GetModuleGlobalName(name) static CYTHON_INLINE PyObject *__Pyx__GetModuleGlobalName(PyObject *name); #endif /* RaiseUnexpectedTypeError.proto */ static int __Pyx_RaiseUnexpectedTypeError(const char *expected, PyObject *obj); /* py_dict_items.proto */ static CYTHON_INLINE PyObject* __Pyx_PyDict_Items(PyObject* d); /* UnpackUnboundCMethod.proto */ typedef struct { PyObject *type; PyObject **method_name; PyCFunction func; PyObject *method; int flag; } __Pyx_CachedCFunction; /* CallUnboundCMethod0.proto */ static PyObject* __Pyx__CallUnboundCMethod0(__Pyx_CachedCFunction* cfunc, PyObject* self); #if CYTHON_COMPILING_IN_CPYTHON #define __Pyx_CallUnboundCMethod0(cfunc, self)\ (likely((cfunc)->func) ?\ (likely((cfunc)->flag == METH_NOARGS) ? (*((cfunc)->func))(self, NULL) :\ (PY_VERSION_HEX >= 0x030600B1 && likely((cfunc)->flag == METH_FASTCALL) ?\ (PY_VERSION_HEX >= 0x030700A0 ?\ (*(__Pyx_PyCFunctionFast)(void*)(PyCFunction)(cfunc)->func)(self, &__pyx_empty_tuple, 0) :\ (*(__Pyx_PyCFunctionFastWithKeywords)(void*)(PyCFunction)(cfunc)->func)(self, &__pyx_empty_tuple, 0, NULL)) :\ (PY_VERSION_HEX >= 0x030700A0 && (cfunc)->flag == (METH_FASTCALL | METH_KEYWORDS) ?\ (*(__Pyx_PyCFunctionFastWithKeywords)(void*)(PyCFunction)(cfunc)->func)(self, &__pyx_empty_tuple, 0, NULL) :\ (likely((cfunc)->flag == (METH_VARARGS | METH_KEYWORDS)) ? ((*(PyCFunctionWithKeywords)(void*)(PyCFunction)(cfunc)->func)(self, __pyx_empty_tuple, NULL)) :\ ((cfunc)->flag == METH_VARARGS ? (*((cfunc)->func))(self, __pyx_empty_tuple) :\ __Pyx__CallUnboundCMethod0(cfunc, self)))))) :\ __Pyx__CallUnboundCMethod0(cfunc, self)) #else #define __Pyx_CallUnboundCMethod0(cfunc, self) __Pyx__CallUnboundCMethod0(cfunc, self) #endif /* RaiseTooManyValuesToUnpack.proto */ static CYTHON_INLINE void __Pyx_RaiseTooManyValuesError(Py_ssize_t expected); /* RaiseNeedMoreValuesToUnpack.proto */ static CYTHON_INLINE void __Pyx_RaiseNeedMoreValuesError(Py_ssize_t index); /* IterFinish.proto */ static CYTHON_INLINE int __Pyx_IterFinish(void); /* UnpackItemEndCheck.proto */ static int __Pyx_IternextUnpackEndCheck(PyObject *retval, Py_ssize_t expected); /* MoveIfSupported.proto */ #if CYTHON_USE_CPP_STD_MOVE #include #define __PYX_STD_MOVE_IF_SUPPORTED(x) std::move(x) #else #define __PYX_STD_MOVE_IF_SUPPORTED(x) x #endif /* KeywordStringCheck.proto */ static int __Pyx_CheckKeywordStrings(PyObject *kw, const char* function_name, int kw_allowed); /* RaiseKeywordRequired.proto */ static void __Pyx_RaiseKeywordRequired(const char* func_name, PyObject* kw_name); /* PyObjectLookupSpecial.proto */ #if CYTHON_USE_PYTYPE_LOOKUP && CYTHON_USE_TYPE_SLOTS #define __Pyx_PyObject_LookupSpecialNoError(obj, attr_name) __Pyx__PyObject_LookupSpecial(obj, attr_name, 0) #define __Pyx_PyObject_LookupSpecial(obj, attr_name) __Pyx__PyObject_LookupSpecial(obj, attr_name, 1) static CYTHON_INLINE PyObject* __Pyx__PyObject_LookupSpecial(PyObject* obj, PyObject* attr_name, int with_error); #else #define __Pyx_PyObject_LookupSpecialNoError(o,n) __Pyx_PyObject_GetAttrStrNoError(o,n) #define __Pyx_PyObject_LookupSpecial(o,n) __Pyx_PyObject_GetAttrStr(o,n) #endif /* GetTopmostException.proto */ #if CYTHON_USE_EXC_INFO_STACK && CYTHON_FAST_THREAD_STATE static _PyErr_StackItem * __Pyx_PyErr_GetTopmostException(PyThreadState *tstate); #endif /* SaveResetException.proto */ #if CYTHON_FAST_THREAD_STATE #define __Pyx_ExceptionSave(type, value, tb) __Pyx__ExceptionSave(__pyx_tstate, type, value, tb) static CYTHON_INLINE void __Pyx__ExceptionSave(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb); #define __Pyx_ExceptionReset(type, value, tb) __Pyx__ExceptionReset(__pyx_tstate, type, value, tb) static CYTHON_INLINE void __Pyx__ExceptionReset(PyThreadState *tstate, PyObject *type, PyObject *value, PyObject *tb); #else #define __Pyx_ExceptionSave(type, value, tb) PyErr_GetExcInfo(type, value, tb) #define __Pyx_ExceptionReset(type, value, tb) PyErr_SetExcInfo(type, value, tb) #endif /* GetException.proto */ #if CYTHON_FAST_THREAD_STATE #define __Pyx_GetException(type, value, tb) __Pyx__GetException(__pyx_tstate, type, value, tb) static int __Pyx__GetException(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb); #else static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb); #endif /* PyObjectFormatSimple.proto */ #if CYTHON_COMPILING_IN_PYPY #define __Pyx_PyObject_FormatSimple(s, f) (\ likely(PyUnicode_CheckExact(s)) ? (Py_INCREF(s), s) :\ PyObject_Format(s, f)) #elif PY_MAJOR_VERSION < 3 #define __Pyx_PyObject_FormatSimple(s, f) (\ likely(PyUnicode_CheckExact(s)) ? (Py_INCREF(s), s) :\ likely(PyString_CheckExact(s)) ? PyUnicode_FromEncodedObject(s, NULL, "strict") :\ PyObject_Format(s, f)) #elif CYTHON_USE_TYPE_SLOTS #define __Pyx_PyObject_FormatSimple(s, f) (\ likely(PyUnicode_CheckExact(s)) ? (Py_INCREF(s), s) :\ likely(PyLong_CheckExact(s)) ? PyLong_Type.tp_repr(s) :\ likely(PyFloat_CheckExact(s)) ? PyFloat_Type.tp_repr(s) :\ PyObject_Format(s, f)) #else #define __Pyx_PyObject_FormatSimple(s, f) (\ likely(PyUnicode_CheckExact(s)) ? (Py_INCREF(s), s) :\ PyObject_Format(s, f)) #endif /* RaiseException.proto */ static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, PyObject *cause); /* GCCDiagnostics.proto */ #if !defined(__INTEL_COMPILER) && defined(__GNUC__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 6)) #define __Pyx_HAS_GCC_DIAGNOSTIC #endif /* BuildPyUnicode.proto */ static PyObject* __Pyx_PyUnicode_BuildFromAscii(Py_ssize_t ulength, char* chars, int clength, int prepend_sign, char padding_char); /* CIntToPyUnicode.proto */ static CYTHON_INLINE PyObject* __Pyx_PyUnicode_From_Py_ssize_t(Py_ssize_t value, Py_ssize_t width, char padding_char, char format_char); /* JoinPyUnicode.proto */ static PyObject* __Pyx_PyUnicode_Join(PyObject* value_tuple, Py_ssize_t value_count, Py_ssize_t result_ulength, Py_UCS4 max_char); /* PyObjectCall2Args.proto */ static CYTHON_INLINE PyObject* __Pyx_PyObject_Call2Args(PyObject* function, PyObject* arg1, PyObject* arg2); /* PyObjectGetMethod.proto */ static int __Pyx_PyObject_GetMethod(PyObject *obj, PyObject *name, PyObject **method); /* PyObjectCallMethod1.proto */ static PyObject* __Pyx_PyObject_CallMethod1(PyObject* obj, PyObject* method_name, PyObject* arg); /* append.proto */ static CYTHON_INLINE int __Pyx_PyObject_Append(PyObject* L, PyObject* x); /* dict_getitem_default.proto */ static PyObject* __Pyx_PyDict_GetItemDefault(PyObject* d, PyObject* key, PyObject* default_value); /* CallUnboundCMethod1.proto */ static PyObject* __Pyx__CallUnboundCMethod1(__Pyx_CachedCFunction* cfunc, PyObject* self, PyObject* arg); #if CYTHON_COMPILING_IN_CPYTHON static CYTHON_INLINE PyObject* __Pyx_CallUnboundCMethod1(__Pyx_CachedCFunction* cfunc, PyObject* self, PyObject* arg); #else #define __Pyx_CallUnboundCMethod1(cfunc, self, arg) __Pyx__CallUnboundCMethod1(cfunc, self, arg) #endif /* CallUnboundCMethod2.proto */ static PyObject* __Pyx__CallUnboundCMethod2(__Pyx_CachedCFunction* cfunc, PyObject* self, PyObject* arg1, PyObject* arg2); #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030600B1 static CYTHON_INLINE PyObject *__Pyx_CallUnboundCMethod2(__Pyx_CachedCFunction *cfunc, PyObject *self, PyObject *arg1, PyObject *arg2); #else #define __Pyx_CallUnboundCMethod2(cfunc, self, arg1, arg2) __Pyx__CallUnboundCMethod2(cfunc, self, arg1, arg2) #endif /* DictGetItem.proto */ #if PY_MAJOR_VERSION >= 3 && !CYTHON_COMPILING_IN_PYPY static PyObject *__Pyx_PyDict_GetItem(PyObject *d, PyObject* key); #define __Pyx_PyObject_Dict_GetItem(obj, name)\ (likely(PyDict_CheckExact(obj)) ?\ __Pyx_PyDict_GetItem(obj, name) : PyObject_GetItem(obj, name)) #else #define __Pyx_PyDict_GetItem(d, key) PyObject_GetItem(d, key) #define __Pyx_PyObject_Dict_GetItem(obj, name) PyObject_GetItem(obj, name) #endif /* IncludeCppStringH.proto */ #include /* decode_c_string_utf16.proto */ static CYTHON_INLINE PyObject *__Pyx_PyUnicode_DecodeUTF16(const char *s, Py_ssize_t size, const char *errors) { int byteorder = 0; return PyUnicode_DecodeUTF16(s, size, errors, &byteorder); } static CYTHON_INLINE PyObject *__Pyx_PyUnicode_DecodeUTF16LE(const char *s, Py_ssize_t size, const char *errors) { int byteorder = -1; return PyUnicode_DecodeUTF16(s, size, errors, &byteorder); } static CYTHON_INLINE PyObject *__Pyx_PyUnicode_DecodeUTF16BE(const char *s, Py_ssize_t size, const char *errors) { int byteorder = 1; return PyUnicode_DecodeUTF16(s, size, errors, &byteorder); } /* decode_c_bytes.proto */ static CYTHON_INLINE PyObject* __Pyx_decode_c_bytes( const char* cstring, Py_ssize_t length, Py_ssize_t start, Py_ssize_t stop, const char* encoding, const char* errors, PyObject* (*decode_func)(const char *s, Py_ssize_t size, const char *errors)); /* decode_cpp_string.proto */ static CYTHON_INLINE PyObject* __Pyx_decode_cpp_string( std::string cppstring, Py_ssize_t start, Py_ssize_t stop, const char* encoding, const char* errors, PyObject* (*decode_func)(const char *s, Py_ssize_t size, const char *errors)) { return __Pyx_decode_c_bytes( cppstring.data(), cppstring.size(), start, stop, encoding, errors, decode_func); } /* ListExtend.proto */ static CYTHON_INLINE int __Pyx_PyList_Extend(PyObject* L, PyObject* v) { #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX < 0x030d0000 PyObject* none = _PyList_Extend((PyListObject*)L, v); if (unlikely(!none)) return -1; Py_DECREF(none); return 0; #else return PyList_SetSlice(L, PY_SSIZE_T_MAX, PY_SSIZE_T_MAX, v); #endif } /* IncludeStructmemberH.proto */ #include /* FixUpExtensionType.proto */ #if CYTHON_USE_TYPE_SPECS static int __Pyx_fix_up_extension_type_from_spec(PyType_Spec *spec, PyTypeObject *type); #endif /* PyObjectCallNoArg.proto */ static CYTHON_INLINE PyObject* __Pyx_PyObject_CallNoArg(PyObject *func); /* PyObjectCallMethod0.proto */ static PyObject* __Pyx_PyObject_CallMethod0(PyObject* obj, PyObject* method_name); /* ValidateBasesTuple.proto */ #if CYTHON_COMPILING_IN_CPYTHON || CYTHON_COMPILING_IN_LIMITED_API || CYTHON_USE_TYPE_SPECS static int __Pyx_validate_bases_tuple(const char *type_name, Py_ssize_t dictoffset, PyObject *bases); #endif /* PyType_Ready.proto */ CYTHON_UNUSED static int __Pyx_PyType_Ready(PyTypeObject *t); /* PyObject_GenericGetAttrNoDict.proto */ #if CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP && PY_VERSION_HEX < 0x03070000 static CYTHON_INLINE PyObject* __Pyx_PyObject_GenericGetAttrNoDict(PyObject* obj, PyObject* attr_name); #else #define __Pyx_PyObject_GenericGetAttrNoDict PyObject_GenericGetAttr #endif /* PyObject_GenericGetAttr.proto */ #if CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP && PY_VERSION_HEX < 0x03070000 static PyObject* __Pyx_PyObject_GenericGetAttr(PyObject* obj, PyObject* attr_name); #else #define __Pyx_PyObject_GenericGetAttr PyObject_GenericGetAttr #endif /* Import.proto */ static PyObject *__Pyx_Import(PyObject *name, PyObject *from_list, int level); /* ImportFrom.proto */ static PyObject* __Pyx_ImportFrom(PyObject* module, PyObject* name); /* ImportDottedModule.proto */ static PyObject *__Pyx_ImportDottedModule(PyObject *name, PyObject *parts_tuple); #if PY_MAJOR_VERSION >= 3 static PyObject *__Pyx_ImportDottedModule_WalkParts(PyObject *module, PyObject *name, PyObject *parts_tuple); #endif /* ImportDottedModuleRelFirst.proto */ static PyObject *__Pyx_ImportDottedModuleRelFirst(PyObject *name, PyObject *parts_tuple); /* FetchSharedCythonModule.proto */ static PyObject *__Pyx_FetchSharedCythonABIModule(void); /* FetchCommonType.proto */ #if !CYTHON_USE_TYPE_SPECS static PyTypeObject* __Pyx_FetchCommonType(PyTypeObject* type); #else static PyTypeObject* __Pyx_FetchCommonTypeFromSpec(PyObject *module, PyType_Spec *spec, PyObject *bases); #endif /* PyMethodNew.proto */ #if CYTHON_COMPILING_IN_LIMITED_API static PyObject *__Pyx_PyMethod_New(PyObject *func, PyObject *self, PyObject *typ) { PyObject *typesModule=NULL, *methodType=NULL, *result=NULL; CYTHON_UNUSED_VAR(typ); if (!self) return __Pyx_NewRef(func); typesModule = PyImport_ImportModule("types"); if (!typesModule) return NULL; methodType = PyObject_GetAttrString(typesModule, "MethodType"); Py_DECREF(typesModule); if (!methodType) return NULL; result = PyObject_CallFunctionObjArgs(methodType, func, self, NULL); Py_DECREF(methodType); return result; } #elif PY_MAJOR_VERSION >= 3 static PyObject *__Pyx_PyMethod_New(PyObject *func, PyObject *self, PyObject *typ) { CYTHON_UNUSED_VAR(typ); if (!self) return __Pyx_NewRef(func); return PyMethod_New(func, self); } #else #define __Pyx_PyMethod_New PyMethod_New #endif /* PyVectorcallFastCallDict.proto */ #if CYTHON_METH_FASTCALL static CYTHON_INLINE PyObject *__Pyx_PyVectorcall_FastCallDict(PyObject *func, __pyx_vectorcallfunc vc, PyObject *const *args, size_t nargs, PyObject *kw); #endif /* CythonFunctionShared.proto */ #define __Pyx_CyFunction_USED #define __Pyx_CYFUNCTION_STATICMETHOD 0x01 #define __Pyx_CYFUNCTION_CLASSMETHOD 0x02 #define __Pyx_CYFUNCTION_CCLASS 0x04 #define __Pyx_CYFUNCTION_COROUTINE 0x08 #define __Pyx_CyFunction_GetClosure(f)\ (((__pyx_CyFunctionObject *) (f))->func_closure) #if PY_VERSION_HEX < 0x030900B1 || CYTHON_COMPILING_IN_LIMITED_API #define __Pyx_CyFunction_GetClassObj(f)\ (((__pyx_CyFunctionObject *) (f))->func_classobj) #else #define __Pyx_CyFunction_GetClassObj(f)\ ((PyObject*) ((PyCMethodObject *) (f))->mm_class) #endif #define __Pyx_CyFunction_SetClassObj(f, classobj)\ __Pyx__CyFunction_SetClassObj((__pyx_CyFunctionObject *) (f), (classobj)) #define __Pyx_CyFunction_Defaults(type, f)\ ((type *)(((__pyx_CyFunctionObject *) (f))->defaults)) #define __Pyx_CyFunction_SetDefaultsGetter(f, g)\ ((__pyx_CyFunctionObject *) (f))->defaults_getter = (g) typedef struct { #if CYTHON_COMPILING_IN_LIMITED_API PyObject_HEAD PyObject *func; #elif PY_VERSION_HEX < 0x030900B1 PyCFunctionObject func; #else PyCMethodObject func; #endif #if CYTHON_BACKPORT_VECTORCALL __pyx_vectorcallfunc func_vectorcall; #endif #if PY_VERSION_HEX < 0x030500A0 || CYTHON_COMPILING_IN_LIMITED_API PyObject *func_weakreflist; #endif PyObject *func_dict; PyObject *func_name; PyObject *func_qualname; PyObject *func_doc; PyObject *func_globals; PyObject *func_code; PyObject *func_closure; #if PY_VERSION_HEX < 0x030900B1 || CYTHON_COMPILING_IN_LIMITED_API PyObject *func_classobj; #endif void *defaults; int defaults_pyobjects; size_t defaults_size; int flags; PyObject *defaults_tuple; PyObject *defaults_kwdict; PyObject *(*defaults_getter)(PyObject *); PyObject *func_annotations; PyObject *func_is_coroutine; } __pyx_CyFunctionObject; #undef __Pyx_CyOrPyCFunction_Check #define __Pyx_CyFunction_Check(obj) __Pyx_TypeCheck(obj, __pyx_CyFunctionType) #define __Pyx_CyOrPyCFunction_Check(obj) __Pyx_TypeCheck2(obj, __pyx_CyFunctionType, &PyCFunction_Type) #define __Pyx_CyFunction_CheckExact(obj) __Pyx_IS_TYPE(obj, __pyx_CyFunctionType) static CYTHON_INLINE int __Pyx__IsSameCyOrCFunction(PyObject *func, void *cfunc); #undef __Pyx_IsSameCFunction #define __Pyx_IsSameCFunction(func, cfunc) __Pyx__IsSameCyOrCFunction(func, cfunc) static PyObject *__Pyx_CyFunction_Init(__pyx_CyFunctionObject* op, PyMethodDef *ml, int flags, PyObject* qualname, PyObject *closure, PyObject *module, PyObject *globals, PyObject* code); static CYTHON_INLINE void __Pyx__CyFunction_SetClassObj(__pyx_CyFunctionObject* f, PyObject* classobj); static CYTHON_INLINE void *__Pyx_CyFunction_InitDefaults(PyObject *m, size_t size, int pyobjects); static CYTHON_INLINE void __Pyx_CyFunction_SetDefaultsTuple(PyObject *m, PyObject *tuple); static CYTHON_INLINE void __Pyx_CyFunction_SetDefaultsKwDict(PyObject *m, PyObject *dict); static CYTHON_INLINE void __Pyx_CyFunction_SetAnnotationsDict(PyObject *m, PyObject *dict); static int __pyx_CyFunction_init(PyObject *module); #if CYTHON_METH_FASTCALL static PyObject * __Pyx_CyFunction_Vectorcall_NOARGS(PyObject *func, PyObject *const *args, size_t nargsf, PyObject *kwnames); static PyObject * __Pyx_CyFunction_Vectorcall_O(PyObject *func, PyObject *const *args, size_t nargsf, PyObject *kwnames); static PyObject * __Pyx_CyFunction_Vectorcall_FASTCALL_KEYWORDS(PyObject *func, PyObject *const *args, size_t nargsf, PyObject *kwnames); static PyObject * __Pyx_CyFunction_Vectorcall_FASTCALL_KEYWORDS_METHOD(PyObject *func, PyObject *const *args, size_t nargsf, PyObject *kwnames); #if CYTHON_BACKPORT_VECTORCALL #define __Pyx_CyFunction_func_vectorcall(f) (((__pyx_CyFunctionObject*)f)->func_vectorcall) #else #define __Pyx_CyFunction_func_vectorcall(f) (((PyCFunctionObject*)f)->vectorcall) #endif #endif /* CythonFunction.proto */ static PyObject *__Pyx_CyFunction_New(PyMethodDef *ml, int flags, PyObject* qualname, PyObject *closure, PyObject *module, PyObject *globals, PyObject* code); /* GetNameInClass.proto */ #define __Pyx_GetNameInClass(var, nmspace, name) (var) = __Pyx__GetNameInClass(nmspace, name) static PyObject *__Pyx__GetNameInClass(PyObject *nmspace, PyObject *name); /* CLineInTraceback.proto */ #ifdef CYTHON_CLINE_IN_TRACEBACK #define __Pyx_CLineForTraceback(tstate, c_line) (((CYTHON_CLINE_IN_TRACEBACK)) ? c_line : 0) #else static int __Pyx_CLineForTraceback(PyThreadState *tstate, int c_line); #endif /* CodeObjectCache.proto */ #if !CYTHON_COMPILING_IN_LIMITED_API typedef struct { PyCodeObject* code_object; int code_line; } __Pyx_CodeObjectCacheEntry; struct __Pyx_CodeObjectCache { int count; int max_count; __Pyx_CodeObjectCacheEntry* entries; }; static struct __Pyx_CodeObjectCache __pyx_code_cache = {0,0,NULL}; static int __pyx_bisect_code_objects(__Pyx_CodeObjectCacheEntry* entries, int count, int code_line); static PyCodeObject *__pyx_find_code_object(int code_line); static void __pyx_insert_code_object(int code_line, PyCodeObject* code_object); #endif /* AddTraceback.proto */ static void __Pyx_AddTraceback(const char *funcname, int c_line, int py_line, const char *filename); /* None.proto */ #include /* CppExceptionConversion.proto */ #ifndef __Pyx_CppExn2PyErr #include #include #include #include static void __Pyx_CppExn2PyErr() { try { if (PyErr_Occurred()) ; // let the latest Python exn pass through and ignore the current one else throw; } catch (const std::bad_alloc& exn) { PyErr_SetString(PyExc_MemoryError, exn.what()); } catch (const std::bad_cast& exn) { PyErr_SetString(PyExc_TypeError, exn.what()); } catch (const std::bad_typeid& exn) { PyErr_SetString(PyExc_TypeError, exn.what()); } catch (const std::domain_error& exn) { PyErr_SetString(PyExc_ValueError, exn.what()); } catch (const std::invalid_argument& exn) { PyErr_SetString(PyExc_ValueError, exn.what()); } catch (const std::ios_base::failure& exn) { PyErr_SetString(PyExc_IOError, exn.what()); } catch (const std::out_of_range& exn) { PyErr_SetString(PyExc_IndexError, exn.what()); } catch (const std::overflow_error& exn) { PyErr_SetString(PyExc_OverflowError, exn.what()); } catch (const std::range_error& exn) { PyErr_SetString(PyExc_ArithmeticError, exn.what()); } catch (const std::underflow_error& exn) { PyErr_SetString(PyExc_ArithmeticError, exn.what()); } catch (const std::exception& exn) { PyErr_SetString(PyExc_RuntimeError, exn.what()); } catch (...) { PyErr_SetString(PyExc_RuntimeError, "Unknown exception"); } } #endif /* CIntToPy.proto */ static CYTHON_INLINE PyObject* __Pyx_PyInt_From_long(long value); /* CIntFromPy.proto */ static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *); /* FormatTypeName.proto */ #if CYTHON_COMPILING_IN_LIMITED_API typedef PyObject *__Pyx_TypeName; #define __Pyx_FMT_TYPENAME "%U" static __Pyx_TypeName __Pyx_PyType_GetName(PyTypeObject* tp); #define __Pyx_DECREF_TypeName(obj) Py_XDECREF(obj) #else typedef const char *__Pyx_TypeName; #define __Pyx_FMT_TYPENAME "%.200s" #define __Pyx_PyType_GetName(tp) ((tp)->tp_name) #define __Pyx_DECREF_TypeName(obj) #endif /* CIntFromPy.proto */ static CYTHON_INLINE int __Pyx_PyInt_As_int(PyObject *); /* FastTypeChecks.proto */ #if CYTHON_COMPILING_IN_CPYTHON #define __Pyx_TypeCheck(obj, type) __Pyx_IsSubtype(Py_TYPE(obj), (PyTypeObject *)type) #define __Pyx_TypeCheck2(obj, type1, type2) __Pyx_IsAnySubtype2(Py_TYPE(obj), (PyTypeObject *)type1, (PyTypeObject *)type2) static CYTHON_INLINE int __Pyx_IsSubtype(PyTypeObject *a, PyTypeObject *b); static CYTHON_INLINE int __Pyx_IsAnySubtype2(PyTypeObject *cls, PyTypeObject *a, PyTypeObject *b); static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches(PyObject *err, PyObject *type); static CYTHON_INLINE int __Pyx_PyErr_GivenExceptionMatches2(PyObject *err, PyObject *type1, PyObject *type2); #else #define __Pyx_TypeCheck(obj, type) PyObject_TypeCheck(obj, (PyTypeObject *)type) #define __Pyx_TypeCheck2(obj, type1, type2) (PyObject_TypeCheck(obj, (PyTypeObject *)type1) || PyObject_TypeCheck(obj, (PyTypeObject *)type2)) #define __Pyx_PyErr_GivenExceptionMatches(err, type) PyErr_GivenExceptionMatches(err, type) #define __Pyx_PyErr_GivenExceptionMatches2(err, type1, type2) (PyErr_GivenExceptionMatches(err, type1) || PyErr_GivenExceptionMatches(err, type2)) #endif #define __Pyx_PyErr_ExceptionMatches2(err1, err2) __Pyx_PyErr_GivenExceptionMatches2(__Pyx_PyErr_CurrentExceptionType(), err1, err2) #define __Pyx_PyException_Check(obj) __Pyx_TypeCheck(obj, PyExc_Exception) /* SwapException.proto */ #if CYTHON_FAST_THREAD_STATE #define __Pyx_ExceptionSwap(type, value, tb) __Pyx__ExceptionSwap(__pyx_tstate, type, value, tb) static CYTHON_INLINE void __Pyx__ExceptionSwap(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb); #else static CYTHON_INLINE void __Pyx_ExceptionSwap(PyObject **type, PyObject **value, PyObject **tb); #endif /* CoroutineBase.proto */ struct __pyx_CoroutineObject; typedef PyObject *(*__pyx_coroutine_body_t)(struct __pyx_CoroutineObject *, PyThreadState *, PyObject *); #if CYTHON_USE_EXC_INFO_STACK #define __Pyx_ExcInfoStruct _PyErr_StackItem #else typedef struct { PyObject *exc_type; PyObject *exc_value; PyObject *exc_traceback; } __Pyx_ExcInfoStruct; #endif typedef struct __pyx_CoroutineObject { PyObject_HEAD __pyx_coroutine_body_t body; PyObject *closure; __Pyx_ExcInfoStruct gi_exc_state; PyObject *gi_weakreflist; PyObject *classobj; PyObject *yieldfrom; PyObject *gi_name; PyObject *gi_qualname; PyObject *gi_modulename; PyObject *gi_code; PyObject *gi_frame; int resume_label; char is_running; } __pyx_CoroutineObject; static __pyx_CoroutineObject *__Pyx__Coroutine_New( PyTypeObject *type, __pyx_coroutine_body_t body, PyObject *code, PyObject *closure, PyObject *name, PyObject *qualname, PyObject *module_name); static __pyx_CoroutineObject *__Pyx__Coroutine_NewInit( __pyx_CoroutineObject *gen, __pyx_coroutine_body_t body, PyObject *code, PyObject *closure, PyObject *name, PyObject *qualname, PyObject *module_name); static CYTHON_INLINE void __Pyx_Coroutine_ExceptionClear(__Pyx_ExcInfoStruct *self); static int __Pyx_Coroutine_clear(PyObject *self); static PyObject *__Pyx_Coroutine_Send(PyObject *self, PyObject *value); static PyObject *__Pyx_Coroutine_Close(PyObject *self); static PyObject *__Pyx_Coroutine_Throw(PyObject *gen, PyObject *args); #if CYTHON_USE_EXC_INFO_STACK #define __Pyx_Coroutine_SwapException(self) #define __Pyx_Coroutine_ResetAndClearException(self) __Pyx_Coroutine_ExceptionClear(&(self)->gi_exc_state) #else #define __Pyx_Coroutine_SwapException(self) {\ __Pyx_ExceptionSwap(&(self)->gi_exc_state.exc_type, &(self)->gi_exc_state.exc_value, &(self)->gi_exc_state.exc_traceback);\ __Pyx_Coroutine_ResetFrameBackpointer(&(self)->gi_exc_state);\ } #define __Pyx_Coroutine_ResetAndClearException(self) {\ __Pyx_ExceptionReset((self)->gi_exc_state.exc_type, (self)->gi_exc_state.exc_value, (self)->gi_exc_state.exc_traceback);\ (self)->gi_exc_state.exc_type = (self)->gi_exc_state.exc_value = (self)->gi_exc_state.exc_traceback = NULL;\ } #endif #if CYTHON_FAST_THREAD_STATE #define __Pyx_PyGen_FetchStopIterationValue(pvalue)\ __Pyx_PyGen__FetchStopIterationValue(__pyx_tstate, pvalue) #else #define __Pyx_PyGen_FetchStopIterationValue(pvalue)\ __Pyx_PyGen__FetchStopIterationValue(__Pyx_PyThreadState_Current, pvalue) #endif static int __Pyx_PyGen__FetchStopIterationValue(PyThreadState *tstate, PyObject **pvalue); static CYTHON_INLINE void __Pyx_Coroutine_ResetFrameBackpointer(__Pyx_ExcInfoStruct *exc_state); /* PatchModuleWithCoroutine.proto */ static PyObject* __Pyx_Coroutine_patch_module(PyObject* module, const char* py_code); /* PatchGeneratorABC.proto */ static int __Pyx_patch_abc(void); /* Generator.proto */ #define __Pyx_Generator_USED #define __Pyx_Generator_CheckExact(obj) __Pyx_IS_TYPE(obj, __pyx_GeneratorType) #define __Pyx_Generator_New(body, code, closure, name, qualname, module_name)\ __Pyx__Coroutine_New(__pyx_GeneratorType, body, code, closure, name, qualname, module_name) static PyObject *__Pyx_Generator_Next(PyObject *self); static int __pyx_Generator_init(PyObject *module); /* CheckBinaryVersion.proto */ static unsigned long __Pyx_get_runtime_version(void); static int __Pyx_check_binary_version(unsigned long ct_version, unsigned long rt_version, int allow_newer); /* InitStrings.proto */ static int __Pyx_InitStrings(__Pyx_StringTabEntry *t); /* #### Code section: module_declarations ### */ /* Module declarations from "libc.string" */ /* Module declarations from "libcpp.string" */ /* Module declarations from "libcpp.vector" */ /* Module declarations from "libcpp.utility" */ /* Module declarations from "libcpp" */ /* Module declarations from "libcpp.memory" */ /* Module declarations from "curated_tokenizers._bbpe" */ static std::string __pyx_convert_string_from_py_std__in_string(PyObject *); /*proto*/ static std::vector __pyx_convert_vector_from_py_std_3a__3a_string(PyObject *); /*proto*/ static CYTHON_INLINE PyObject *__pyx_convert_PyObject_string_to_py_std__in_string(std::string const &); /*proto*/ static CYTHON_INLINE PyObject *__pyx_convert_PyUnicode_string_to_py_std__in_string(std::string const &); /*proto*/ static CYTHON_INLINE PyObject *__pyx_convert_PyStr_string_to_py_std__in_string(std::string const &); /*proto*/ static CYTHON_INLINE PyObject *__pyx_convert_PyBytes_string_to_py_std__in_string(std::string const &); /*proto*/ static CYTHON_INLINE PyObject *__pyx_convert_PyByteArray_string_to_py_std__in_string(std::string const &); /*proto*/ static PyObject *__pyx_convert_pair_to_py_std_3a__3a_string____std_3a__3a_string(std::pair const &); /*proto*/ /* #### Code section: typeinfo ### */ /* #### Code section: before_global_var ### */ #define __Pyx_MODULE_NAME "curated_tokenizers._bbpe" extern int __pyx_module_is_main_curated_tokenizers___bbpe; int __pyx_module_is_main_curated_tokenizers___bbpe = 0; /* Implementation of "curated_tokenizers._bbpe" */ /* #### Code section: global_var ### */ static PyObject *__pyx_builtin_staticmethod; static PyObject *__pyx_builtin_range; static PyObject *__pyx_builtin_chr; static PyObject *__pyx_builtin_zip; static PyObject *__pyx_builtin_open; static PyObject *__pyx_builtin_ValueError; /* #### Code section: string_decls ### */ static const char __pyx_k_b[] = "b"; static const char __pyx_k_f[] = "f"; static const char __pyx_k_n[] = "n"; static const char __pyx_k__2[] = " "; static const char __pyx_k__3[] = ": "; static const char __pyx_k__4[] = "."; static const char __pyx_k__5[] = "*"; static const char __pyx_k_bs[] = "bs"; static const char __pyx_k_cp[] = "cp"; static const char __pyx_k_cs[] = "cs"; static const char __pyx_k_gc[] = "gc"; static const char __pyx_k_io[] = "io"; static const char __pyx_k__28[] = "?"; static const char __pyx_k_chr[] = "chr"; static const char __pyx_k_get[] = "get"; static const char __pyx_k_ids[] = "ids"; static const char __pyx_k_str[] = "str"; static const char __pyx_k_zip[] = "zip"; static const char __pyx_k_Dict[] = "Dict"; static const char __pyx_k_List[] = "List"; static const char __pyx_k_Path[] = "Path"; static const char __pyx_k_args[] = "args"; static const char __pyx_k_copy[] = "__copy__"; static const char __pyx_k_dict[] = "__dict__"; static const char __pyx_k_exit[] = "__exit__"; static const char __pyx_k_json[] = "json"; static const char __pyx_k_line[] = "line"; static const char __pyx_k_load[] = "load"; static const char __pyx_k_main[] = "__main__"; static const char __pyx_k_memo[] = "memo"; static const char __pyx_k_name[] = "__name__"; static const char __pyx_k_open[] = "open"; static const char __pyx_k_self[] = "self"; static const char __pyx_k_send[] = "send"; static const char __pyx_k_spec[] = "__spec__"; static const char __pyx_k_test[] = "__test__"; static const char __pyx_k_text[] = "text"; static const char __pyx_k_Tuple[] = "Tuple"; static const char __pyx_k_close[] = "close"; static const char __pyx_k_enter[] = "__enter__"; static const char __pyx_k_items[] = "items"; static const char __pyx_k_merge[] = "merge"; static const char __pyx_k_piece[] = "piece"; static const char __pyx_k_range[] = "range"; static const char __pyx_k_regex[] = "regex"; static const char __pyx_k_split[] = "split"; static const char __pyx_k_strip[] = "strip"; static const char __pyx_k_throw[] = "throw"; static const char __pyx_k_token[] = "token"; static const char __pyx_k_utf_8[] = "utf-8"; static const char __pyx_k_vocab[] = "vocab"; static const char __pyx_k_write[] = "write"; static const char __pyx_k_append[] = "append"; static const char __pyx_k_decode[] = "decode"; static const char __pyx_k_enable[] = "enable"; static const char __pyx_k_encode[] = "encode"; static const char __pyx_k_import[] = "__import__"; static const char __pyx_k_merged[] = "merged"; static const char __pyx_k_merges[] = "merges"; static const char __pyx_k_pieces[] = "pieces"; static const char __pyx_k_reduce[] = "__reduce__"; static const char __pyx_k_return[] = "return"; static const char __pyx_k_typing[] = "typing"; static const char __pyx_k_BytesIO[] = "BytesIO"; static const char __pyx_k_compile[] = "compile"; static const char __pyx_k_decoded[] = "decoded"; static const char __pyx_k_disable[] = "disable"; static const char __pyx_k_findall[] = "findall"; static const char __pyx_k_genexpr[] = "genexpr"; static const char __pyx_k_pathlib[] = "pathlib"; static const char __pyx_k_version[] = "version"; static const char __pyx_k_Iterable[] = "Iterable"; static const char __pyx_k_List_int[] = "List[int]"; static const char __pyx_k_List_str[] = "List[str]"; static const char __pyx_k_Optional[] = "Optional"; static const char __pyx_k_deepcopy[] = "__deepcopy__"; static const char __pyx_k_encoding[] = "encoding"; static const char __pyx_k_getvalue[] = "getvalue"; static const char __pyx_k_piece_id[] = "piece_id"; static const char __pyx_k_readline[] = "readline"; static const char __pyx_k_functools[] = "functools"; static const char __pyx_k_isenabled[] = "isenabled"; static const char __pyx_k_lru_cache[] = "lru_cache"; static const char __pyx_k_piece_ids[] = "piece_ids"; static const char __pyx_k_ValueError[] = "ValueError"; static const char __pyx_k_startswith[] = "startswith"; static const char __pyx_k_token_bytes[] = "token_bytes"; static const char __pyx_k_version_0_2[] = "#version: 0.2"; static const char __pyx_k_Dict_str_int[] = "Dict[str, int]"; static const char __pyx_k_Iterable_int[] = "Iterable[int]"; static const char __pyx_k_Optional_int[] = "Optional[int]"; static const char __pyx_k_initializing[] = "_initializing"; static const char __pyx_k_is_coroutine[] = "_is_coroutine"; static const char __pyx_k_staticmethod[] = "staticmethod"; static const char __pyx_k_SPLIT_PATTERN[] = "SPLIT_PATTERN"; static const char __pyx_k_encode_as_ids[] = "encode_as_ids"; static const char __pyx_k_pieces_to_ids[] = "_pieces_to_ids"; static const char __pyx_k_Dict_int_bytes[] = "Dict[int, bytes]"; static const char __pyx_k_decode_from_ids[] = "decode_from_ids"; static const char __pyx_k_load_from_files[] = "load_from_files"; static const char __pyx_k_ByteBPEProcessor[] = "ByteBPEProcessor"; static const char __pyx_k_bytes_to_unicode[] = "bytes_to_unicode"; static const char __pyx_k_encode_as_pieces[] = "encode_as_pieces"; static const char __pyx_k_List_Tuple_str_str[] = "List[Tuple[str, str]]"; static const char __pyx_k_asyncio_coroutines[] = "asyncio.coroutines"; static const char __pyx_k_cline_in_traceback[] = "cline_in_traceback"; static const char __pyx_k_ByteBPEProcessor___copy[] = "ByteBPEProcessor.__copy__"; static const char __pyx_k_ByteBPEProcessor_encode[] = "ByteBPEProcessor.encode"; static const char __pyx_k_Tuple_List_int_List_str[] = "Tuple[List[int], List[str]]"; static const char __pyx_k_Unknown_piece_identifier[] = "Unknown piece identifier: "; static const char __pyx_k_curated_tokenizers__bbpe[] = "curated_tokenizers._bbpe"; static const char __pyx_k_ByteBPEProcessor___reduce[] = "ByteBPEProcessor.__reduce__"; static const char __pyx_k_ByteBPEProcessor_piece_id[] = "ByteBPEProcessor.piece_id"; static const char __pyx_k_Piece_is_not_in_vocabulary[] = "Piece is not in vocabulary: "; static const char __pyx_k_ByteBPEProcessor___deepcopy[] = "ByteBPEProcessor.__deepcopy__"; static const char __pyx_k_unpickle_byte_bpe_processor[] = "unpickle_byte_bpe_processor"; static const char __pyx_k_curated_tokenizers__bbpe_pyx[] = "curated_tokenizers\\_bbpe.pyx"; static const char __pyx_k_ByteBPEProcessor_encode_as_ids[] = "ByteBPEProcessor.encode_as_ids"; static const char __pyx_k_s_t_re_ve_m_ll_d_p_L_p_N_s_p_L[] = "'s|'t|'re|'ve|'m|'ll|'d| ?\\p{L}+| ?\\p{N}+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)|\\s+"; static const char __pyx_k_ByteBPEProcessor__pieces_to_ids[] = "ByteBPEProcessor._pieces_to_ids"; static const char __pyx_k_encode_as_pieces_locals_genexpr[] = "encode_as_pieces..genexpr"; static const char __pyx_k_ByteBPEProcessor_decode_from_ids[] = "ByteBPEProcessor.decode_from_ids"; static const char __pyx_k_ByteBPEProcessor_encode_as_piece[] = "ByteBPEProcessor.encode_as_pieces"; static const char __pyx_k_ByteBPEProcessor_load_from_files[] = "ByteBPEProcessor.load_from_files"; static const char __pyx_k_Merge_must_consist_of_2_items_wa[] = "Merge must consist of 2 items, was "; static const char __pyx_k_Only_version_0_2_of_the_merges_f[] = "Only version 0.2 of the merges format is supported, was: "; /* #### Code section: decls ### */ static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_bytes_to_unicode(CYTHON_UNUSED PyObject *__pyx_self); /* proto */ static int __pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor___init__(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self, PyObject *__pyx_v_vocab, PyObject *__pyx_v_merges); /* proto */ static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_2__copy__(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self); /* proto */ static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_4__deepcopy__(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self, CYTHON_UNUSED PyObject *__pyx_v_memo); /* proto */ static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_6load_from_files(PyObject *__pyx_v_vocab, PyObject *__pyx_v_merges); /* proto */ static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_8decode_from_ids(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self, PyObject *__pyx_v_ids); /* proto */ static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_10encode(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self, PyObject *__pyx_v_text); /* proto */ static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_12encode_as_ids(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self, PyObject *__pyx_v_text); /* proto */ static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_16encode_as_pieces_genexpr(CYTHON_UNUSED PyObject *__pyx_self, std::vector __pyx_genexpr_arg_0); /* proto */ static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_14encode_as_pieces(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self, PyObject *__pyx_v_text); /* proto */ static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_6merges___get__(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self); /* proto */ static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_16piece_id(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self, PyObject *__pyx_v_piece); /* proto */ static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_5vocab___get__(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self); /* proto */ static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_18_pieces_to_ids(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self, PyObject *__pyx_v_pieces); /* proto */ static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_20__reduce__(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self); /* proto */ static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_2unpickle_byte_bpe_processor(CYTHON_UNUSED PyObject *__pyx_self, PyObject *__pyx_v_vocab, PyObject *__pyx_v_merges); /* proto */ static PyObject *__pyx_tp_new_18curated_tokenizers_5_bbpe_ByteBPEProcessor(PyTypeObject *t, PyObject *a, PyObject *k); /*proto*/ static PyObject *__pyx_tp_new_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr(PyTypeObject *t, PyObject *a, PyObject *k); /*proto*/ static __Pyx_CachedCFunction __pyx_umethod_PyDict_Type_get = {0, 0, 0, 0, 0}; static __Pyx_CachedCFunction __pyx_umethod_PyDict_Type_items = {0, 0, 0, 0, 0}; /* #### Code section: late_includes ### */ /* #### Code section: module_state ### */ typedef struct { PyObject *__pyx_d; PyObject *__pyx_b; PyObject *__pyx_cython_runtime; PyObject *__pyx_empty_tuple; PyObject *__pyx_empty_bytes; PyObject *__pyx_empty_unicode; #ifdef __Pyx_CyFunction_USED PyTypeObject *__pyx_CyFunctionType; #endif #ifdef __Pyx_FusedFunction_USED PyTypeObject *__pyx_FusedFunctionType; #endif #ifdef __Pyx_Generator_USED PyTypeObject *__pyx_GeneratorType; #endif #ifdef __Pyx_IterableCoroutine_USED PyTypeObject *__pyx_IterableCoroutineType; #endif #ifdef __Pyx_Coroutine_USED PyTypeObject *__pyx_CoroutineAwaitType; #endif #ifdef __Pyx_Coroutine_USED PyTypeObject *__pyx_CoroutineType; #endif #if CYTHON_USE_MODULE_STATE #endif #if CYTHON_USE_MODULE_STATE #endif #if CYTHON_USE_MODULE_STATE #endif #if CYTHON_USE_MODULE_STATE #endif #if CYTHON_USE_MODULE_STATE #endif #if CYTHON_USE_MODULE_STATE #endif #if CYTHON_USE_MODULE_STATE PyObject *__pyx_type_18curated_tokenizers_5_bbpe_ByteBPEProcessor; PyObject *__pyx_type_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr; #endif PyTypeObject *__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor; PyTypeObject *__pyx_ptype_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr; PyObject *__pyx_n_s_ByteBPEProcessor; PyObject *__pyx_n_s_ByteBPEProcessor___copy; PyObject *__pyx_n_s_ByteBPEProcessor___deepcopy; PyObject *__pyx_n_s_ByteBPEProcessor___reduce; PyObject *__pyx_n_s_ByteBPEProcessor__pieces_to_ids; PyObject *__pyx_n_s_ByteBPEProcessor_decode_from_ids; PyObject *__pyx_n_s_ByteBPEProcessor_encode; PyObject *__pyx_n_s_ByteBPEProcessor_encode_as_ids; PyObject *__pyx_n_s_ByteBPEProcessor_encode_as_piece; PyObject *__pyx_n_s_ByteBPEProcessor_load_from_files; PyObject *__pyx_n_s_ByteBPEProcessor_piece_id; PyObject *__pyx_n_s_BytesIO; PyObject *__pyx_n_s_Dict; PyObject *__pyx_kp_s_Dict_int_bytes; PyObject *__pyx_kp_s_Dict_str_int; PyObject *__pyx_n_s_Iterable; PyObject *__pyx_kp_s_Iterable_int; PyObject *__pyx_n_s_List; PyObject *__pyx_kp_s_List_Tuple_str_str; PyObject *__pyx_kp_s_List_int; PyObject *__pyx_kp_s_List_str; PyObject *__pyx_kp_u_Merge_must_consist_of_2_items_wa; PyObject *__pyx_kp_u_Only_version_0_2_of_the_merges_f; PyObject *__pyx_n_s_Optional; PyObject *__pyx_kp_s_Optional_int; PyObject *__pyx_n_s_Path; PyObject *__pyx_kp_u_Piece_is_not_in_vocabulary; PyObject *__pyx_n_s_SPLIT_PATTERN; PyObject *__pyx_n_s_Tuple; PyObject *__pyx_kp_s_Tuple_List_int_List_str; PyObject *__pyx_kp_u_Unknown_piece_identifier; PyObject *__pyx_n_s_ValueError; PyObject *__pyx_kp_s__2; PyObject *__pyx_n_s__28; PyObject *__pyx_kp_u__3; PyObject *__pyx_kp_u__4; PyObject *__pyx_n_s__5; PyObject *__pyx_n_s_append; PyObject *__pyx_n_s_args; PyObject *__pyx_n_s_asyncio_coroutines; PyObject *__pyx_n_s_b; PyObject *__pyx_n_s_bs; PyObject *__pyx_n_s_bytes_to_unicode; PyObject *__pyx_n_s_chr; PyObject *__pyx_n_s_cline_in_traceback; PyObject *__pyx_n_s_close; PyObject *__pyx_n_s_compile; PyObject *__pyx_n_s_copy; PyObject *__pyx_n_s_cp; PyObject *__pyx_n_s_cs; PyObject *__pyx_n_s_curated_tokenizers__bbpe; PyObject *__pyx_kp_s_curated_tokenizers__bbpe_pyx; PyObject *__pyx_n_s_decode; PyObject *__pyx_n_s_decode_from_ids; PyObject *__pyx_n_s_decoded; PyObject *__pyx_n_s_deepcopy; PyObject *__pyx_n_s_dict; PyObject *__pyx_kp_u_disable; PyObject *__pyx_kp_u_enable; PyObject *__pyx_n_s_encode; PyObject *__pyx_n_s_encode_as_ids; PyObject *__pyx_n_s_encode_as_pieces; PyObject *__pyx_n_s_encode_as_pieces_locals_genexpr; PyObject *__pyx_n_s_encoding; PyObject *__pyx_n_s_enter; PyObject *__pyx_n_s_exit; PyObject *__pyx_n_s_f; PyObject *__pyx_n_s_findall; PyObject *__pyx_n_s_functools; PyObject *__pyx_kp_u_gc; PyObject *__pyx_n_s_genexpr; PyObject *__pyx_n_s_get; PyObject *__pyx_n_s_getvalue; PyObject *__pyx_n_s_ids; PyObject *__pyx_n_s_import; PyObject *__pyx_n_s_initializing; PyObject *__pyx_n_s_io; PyObject *__pyx_n_s_is_coroutine; PyObject *__pyx_kp_u_isenabled; PyObject *__pyx_n_s_items; PyObject *__pyx_n_s_json; PyObject *__pyx_n_s_line; PyObject *__pyx_n_s_load; PyObject *__pyx_n_s_load_from_files; PyObject *__pyx_n_s_lru_cache; PyObject *__pyx_n_s_main; PyObject *__pyx_n_s_memo; PyObject *__pyx_n_s_merge; PyObject *__pyx_n_s_merged; PyObject *__pyx_n_s_merges; PyObject *__pyx_n_s_n; PyObject *__pyx_n_s_name; PyObject *__pyx_n_s_open; PyObject *__pyx_n_s_pathlib; PyObject *__pyx_n_s_piece; PyObject *__pyx_n_s_piece_id; PyObject *__pyx_n_s_piece_ids; PyObject *__pyx_n_s_pieces; PyObject *__pyx_n_s_pieces_to_ids; PyObject *__pyx_n_s_range; PyObject *__pyx_n_s_readline; PyObject *__pyx_n_s_reduce; PyObject *__pyx_n_s_regex; PyObject *__pyx_n_s_return; PyObject *__pyx_kp_s_s_t_re_ve_m_ll_d_p_L_p_N_s_p_L; PyObject *__pyx_n_s_self; PyObject *__pyx_n_s_send; PyObject *__pyx_n_s_spec; PyObject *__pyx_n_s_split; PyObject *__pyx_n_s_startswith; PyObject *__pyx_n_s_staticmethod; PyObject *__pyx_n_s_str; PyObject *__pyx_n_s_strip; PyObject *__pyx_n_s_test; PyObject *__pyx_n_s_text; PyObject *__pyx_n_s_throw; PyObject *__pyx_n_s_token; PyObject *__pyx_n_s_token_bytes; PyObject *__pyx_n_s_typing; PyObject *__pyx_n_s_unpickle_byte_bpe_processor; PyObject *__pyx_kp_s_utf_8; PyObject *__pyx_n_s_version; PyObject *__pyx_kp_s_version_0_2; PyObject *__pyx_n_s_vocab; PyObject *__pyx_n_s_write; PyObject *__pyx_n_s_zip; PyObject *__pyx_int_0; PyObject *__pyx_int_1; PyObject *__pyx_int_33; PyObject *__pyx_int_161; PyObject *__pyx_int_174; PyObject *__pyx_int_256; PyObject *__pyx_tuple_; PyObject *__pyx_tuple__6; PyObject *__pyx_tuple__8; PyObject *__pyx_tuple__10; PyObject *__pyx_tuple__12; PyObject *__pyx_tuple__14; PyObject *__pyx_tuple__16; PyObject *__pyx_tuple__19; PyObject *__pyx_tuple__21; PyObject *__pyx_tuple__23; PyObject *__pyx_tuple__26; PyObject *__pyx_codeobj__7; PyObject *__pyx_codeobj__9; PyObject *__pyx_codeobj__11; PyObject *__pyx_codeobj__13; PyObject *__pyx_codeobj__15; PyObject *__pyx_codeobj__17; PyObject *__pyx_codeobj__18; PyObject *__pyx_codeobj__20; PyObject *__pyx_codeobj__22; PyObject *__pyx_codeobj__24; PyObject *__pyx_codeobj__25; PyObject *__pyx_codeobj__27; } __pyx_mstate; #if CYTHON_USE_MODULE_STATE #ifdef __cplusplus namespace { extern struct PyModuleDef __pyx_moduledef; } /* anonymous namespace */ #else static struct PyModuleDef __pyx_moduledef; #endif #define __pyx_mstate(o) ((__pyx_mstate *)__Pyx_PyModule_GetState(o)) #define __pyx_mstate_global (__pyx_mstate(PyState_FindModule(&__pyx_moduledef))) #define __pyx_m (PyState_FindModule(&__pyx_moduledef)) #else static __pyx_mstate __pyx_mstate_global_static = #ifdef __cplusplus {}; #else {0}; #endif static __pyx_mstate *__pyx_mstate_global = &__pyx_mstate_global_static; #endif /* #### Code section: module_state_clear ### */ #if CYTHON_USE_MODULE_STATE static int __pyx_m_clear(PyObject *m) { __pyx_mstate *clear_module_state = __pyx_mstate(m); if (!clear_module_state) return 0; Py_CLEAR(clear_module_state->__pyx_d); Py_CLEAR(clear_module_state->__pyx_b); Py_CLEAR(clear_module_state->__pyx_cython_runtime); Py_CLEAR(clear_module_state->__pyx_empty_tuple); Py_CLEAR(clear_module_state->__pyx_empty_bytes); Py_CLEAR(clear_module_state->__pyx_empty_unicode); #ifdef __Pyx_CyFunction_USED Py_CLEAR(clear_module_state->__pyx_CyFunctionType); #endif #ifdef __Pyx_FusedFunction_USED Py_CLEAR(clear_module_state->__pyx_FusedFunctionType); #endif Py_CLEAR(clear_module_state->__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor); Py_CLEAR(clear_module_state->__pyx_type_18curated_tokenizers_5_bbpe_ByteBPEProcessor); Py_CLEAR(clear_module_state->__pyx_ptype_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr); Py_CLEAR(clear_module_state->__pyx_type_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr); Py_CLEAR(clear_module_state->__pyx_n_s_ByteBPEProcessor); Py_CLEAR(clear_module_state->__pyx_n_s_ByteBPEProcessor___copy); Py_CLEAR(clear_module_state->__pyx_n_s_ByteBPEProcessor___deepcopy); Py_CLEAR(clear_module_state->__pyx_n_s_ByteBPEProcessor___reduce); Py_CLEAR(clear_module_state->__pyx_n_s_ByteBPEProcessor__pieces_to_ids); Py_CLEAR(clear_module_state->__pyx_n_s_ByteBPEProcessor_decode_from_ids); Py_CLEAR(clear_module_state->__pyx_n_s_ByteBPEProcessor_encode); Py_CLEAR(clear_module_state->__pyx_n_s_ByteBPEProcessor_encode_as_ids); Py_CLEAR(clear_module_state->__pyx_n_s_ByteBPEProcessor_encode_as_piece); Py_CLEAR(clear_module_state->__pyx_n_s_ByteBPEProcessor_load_from_files); Py_CLEAR(clear_module_state->__pyx_n_s_ByteBPEProcessor_piece_id); Py_CLEAR(clear_module_state->__pyx_n_s_BytesIO); Py_CLEAR(clear_module_state->__pyx_n_s_Dict); Py_CLEAR(clear_module_state->__pyx_kp_s_Dict_int_bytes); Py_CLEAR(clear_module_state->__pyx_kp_s_Dict_str_int); Py_CLEAR(clear_module_state->__pyx_n_s_Iterable); Py_CLEAR(clear_module_state->__pyx_kp_s_Iterable_int); Py_CLEAR(clear_module_state->__pyx_n_s_List); Py_CLEAR(clear_module_state->__pyx_kp_s_List_Tuple_str_str); Py_CLEAR(clear_module_state->__pyx_kp_s_List_int); Py_CLEAR(clear_module_state->__pyx_kp_s_List_str); Py_CLEAR(clear_module_state->__pyx_kp_u_Merge_must_consist_of_2_items_wa); Py_CLEAR(clear_module_state->__pyx_kp_u_Only_version_0_2_of_the_merges_f); Py_CLEAR(clear_module_state->__pyx_n_s_Optional); Py_CLEAR(clear_module_state->__pyx_kp_s_Optional_int); Py_CLEAR(clear_module_state->__pyx_n_s_Path); Py_CLEAR(clear_module_state->__pyx_kp_u_Piece_is_not_in_vocabulary); Py_CLEAR(clear_module_state->__pyx_n_s_SPLIT_PATTERN); Py_CLEAR(clear_module_state->__pyx_n_s_Tuple); Py_CLEAR(clear_module_state->__pyx_kp_s_Tuple_List_int_List_str); Py_CLEAR(clear_module_state->__pyx_kp_u_Unknown_piece_identifier); Py_CLEAR(clear_module_state->__pyx_n_s_ValueError); Py_CLEAR(clear_module_state->__pyx_kp_s__2); Py_CLEAR(clear_module_state->__pyx_n_s__28); Py_CLEAR(clear_module_state->__pyx_kp_u__3); Py_CLEAR(clear_module_state->__pyx_kp_u__4); Py_CLEAR(clear_module_state->__pyx_n_s__5); Py_CLEAR(clear_module_state->__pyx_n_s_append); Py_CLEAR(clear_module_state->__pyx_n_s_args); Py_CLEAR(clear_module_state->__pyx_n_s_asyncio_coroutines); Py_CLEAR(clear_module_state->__pyx_n_s_b); Py_CLEAR(clear_module_state->__pyx_n_s_bs); Py_CLEAR(clear_module_state->__pyx_n_s_bytes_to_unicode); Py_CLEAR(clear_module_state->__pyx_n_s_chr); Py_CLEAR(clear_module_state->__pyx_n_s_cline_in_traceback); Py_CLEAR(clear_module_state->__pyx_n_s_close); Py_CLEAR(clear_module_state->__pyx_n_s_compile); Py_CLEAR(clear_module_state->__pyx_n_s_copy); Py_CLEAR(clear_module_state->__pyx_n_s_cp); Py_CLEAR(clear_module_state->__pyx_n_s_cs); Py_CLEAR(clear_module_state->__pyx_n_s_curated_tokenizers__bbpe); Py_CLEAR(clear_module_state->__pyx_kp_s_curated_tokenizers__bbpe_pyx); Py_CLEAR(clear_module_state->__pyx_n_s_decode); Py_CLEAR(clear_module_state->__pyx_n_s_decode_from_ids); Py_CLEAR(clear_module_state->__pyx_n_s_decoded); Py_CLEAR(clear_module_state->__pyx_n_s_deepcopy); Py_CLEAR(clear_module_state->__pyx_n_s_dict); Py_CLEAR(clear_module_state->__pyx_kp_u_disable); Py_CLEAR(clear_module_state->__pyx_kp_u_enable); Py_CLEAR(clear_module_state->__pyx_n_s_encode); Py_CLEAR(clear_module_state->__pyx_n_s_encode_as_ids); Py_CLEAR(clear_module_state->__pyx_n_s_encode_as_pieces); Py_CLEAR(clear_module_state->__pyx_n_s_encode_as_pieces_locals_genexpr); Py_CLEAR(clear_module_state->__pyx_n_s_encoding); Py_CLEAR(clear_module_state->__pyx_n_s_enter); Py_CLEAR(clear_module_state->__pyx_n_s_exit); Py_CLEAR(clear_module_state->__pyx_n_s_f); Py_CLEAR(clear_module_state->__pyx_n_s_findall); Py_CLEAR(clear_module_state->__pyx_n_s_functools); Py_CLEAR(clear_module_state->__pyx_kp_u_gc); Py_CLEAR(clear_module_state->__pyx_n_s_genexpr); Py_CLEAR(clear_module_state->__pyx_n_s_get); Py_CLEAR(clear_module_state->__pyx_n_s_getvalue); Py_CLEAR(clear_module_state->__pyx_n_s_ids); Py_CLEAR(clear_module_state->__pyx_n_s_import); Py_CLEAR(clear_module_state->__pyx_n_s_initializing); Py_CLEAR(clear_module_state->__pyx_n_s_io); Py_CLEAR(clear_module_state->__pyx_n_s_is_coroutine); Py_CLEAR(clear_module_state->__pyx_kp_u_isenabled); Py_CLEAR(clear_module_state->__pyx_n_s_items); Py_CLEAR(clear_module_state->__pyx_n_s_json); Py_CLEAR(clear_module_state->__pyx_n_s_line); Py_CLEAR(clear_module_state->__pyx_n_s_load); Py_CLEAR(clear_module_state->__pyx_n_s_load_from_files); Py_CLEAR(clear_module_state->__pyx_n_s_lru_cache); Py_CLEAR(clear_module_state->__pyx_n_s_main); Py_CLEAR(clear_module_state->__pyx_n_s_memo); Py_CLEAR(clear_module_state->__pyx_n_s_merge); Py_CLEAR(clear_module_state->__pyx_n_s_merged); Py_CLEAR(clear_module_state->__pyx_n_s_merges); Py_CLEAR(clear_module_state->__pyx_n_s_n); Py_CLEAR(clear_module_state->__pyx_n_s_name); Py_CLEAR(clear_module_state->__pyx_n_s_open); Py_CLEAR(clear_module_state->__pyx_n_s_pathlib); Py_CLEAR(clear_module_state->__pyx_n_s_piece); Py_CLEAR(clear_module_state->__pyx_n_s_piece_id); Py_CLEAR(clear_module_state->__pyx_n_s_piece_ids); Py_CLEAR(clear_module_state->__pyx_n_s_pieces); Py_CLEAR(clear_module_state->__pyx_n_s_pieces_to_ids); Py_CLEAR(clear_module_state->__pyx_n_s_range); Py_CLEAR(clear_module_state->__pyx_n_s_readline); Py_CLEAR(clear_module_state->__pyx_n_s_reduce); Py_CLEAR(clear_module_state->__pyx_n_s_regex); Py_CLEAR(clear_module_state->__pyx_n_s_return); Py_CLEAR(clear_module_state->__pyx_kp_s_s_t_re_ve_m_ll_d_p_L_p_N_s_p_L); Py_CLEAR(clear_module_state->__pyx_n_s_self); Py_CLEAR(clear_module_state->__pyx_n_s_send); Py_CLEAR(clear_module_state->__pyx_n_s_spec); Py_CLEAR(clear_module_state->__pyx_n_s_split); Py_CLEAR(clear_module_state->__pyx_n_s_startswith); Py_CLEAR(clear_module_state->__pyx_n_s_staticmethod); Py_CLEAR(clear_module_state->__pyx_n_s_str); Py_CLEAR(clear_module_state->__pyx_n_s_strip); Py_CLEAR(clear_module_state->__pyx_n_s_test); Py_CLEAR(clear_module_state->__pyx_n_s_text); Py_CLEAR(clear_module_state->__pyx_n_s_throw); Py_CLEAR(clear_module_state->__pyx_n_s_token); Py_CLEAR(clear_module_state->__pyx_n_s_token_bytes); Py_CLEAR(clear_module_state->__pyx_n_s_typing); Py_CLEAR(clear_module_state->__pyx_n_s_unpickle_byte_bpe_processor); Py_CLEAR(clear_module_state->__pyx_kp_s_utf_8); Py_CLEAR(clear_module_state->__pyx_n_s_version); Py_CLEAR(clear_module_state->__pyx_kp_s_version_0_2); Py_CLEAR(clear_module_state->__pyx_n_s_vocab); Py_CLEAR(clear_module_state->__pyx_n_s_write); Py_CLEAR(clear_module_state->__pyx_n_s_zip); Py_CLEAR(clear_module_state->__pyx_int_0); Py_CLEAR(clear_module_state->__pyx_int_1); Py_CLEAR(clear_module_state->__pyx_int_33); Py_CLEAR(clear_module_state->__pyx_int_161); Py_CLEAR(clear_module_state->__pyx_int_174); Py_CLEAR(clear_module_state->__pyx_int_256); Py_CLEAR(clear_module_state->__pyx_tuple_); Py_CLEAR(clear_module_state->__pyx_tuple__6); Py_CLEAR(clear_module_state->__pyx_tuple__8); Py_CLEAR(clear_module_state->__pyx_tuple__10); Py_CLEAR(clear_module_state->__pyx_tuple__12); Py_CLEAR(clear_module_state->__pyx_tuple__14); Py_CLEAR(clear_module_state->__pyx_tuple__16); Py_CLEAR(clear_module_state->__pyx_tuple__19); Py_CLEAR(clear_module_state->__pyx_tuple__21); Py_CLEAR(clear_module_state->__pyx_tuple__23); Py_CLEAR(clear_module_state->__pyx_tuple__26); Py_CLEAR(clear_module_state->__pyx_codeobj__7); Py_CLEAR(clear_module_state->__pyx_codeobj__9); Py_CLEAR(clear_module_state->__pyx_codeobj__11); Py_CLEAR(clear_module_state->__pyx_codeobj__13); Py_CLEAR(clear_module_state->__pyx_codeobj__15); Py_CLEAR(clear_module_state->__pyx_codeobj__17); Py_CLEAR(clear_module_state->__pyx_codeobj__18); Py_CLEAR(clear_module_state->__pyx_codeobj__20); Py_CLEAR(clear_module_state->__pyx_codeobj__22); Py_CLEAR(clear_module_state->__pyx_codeobj__24); Py_CLEAR(clear_module_state->__pyx_codeobj__25); Py_CLEAR(clear_module_state->__pyx_codeobj__27); return 0; } #endif /* #### Code section: module_state_traverse ### */ #if CYTHON_USE_MODULE_STATE static int __pyx_m_traverse(PyObject *m, visitproc visit, void *arg) { __pyx_mstate *traverse_module_state = __pyx_mstate(m); if (!traverse_module_state) return 0; Py_VISIT(traverse_module_state->__pyx_d); Py_VISIT(traverse_module_state->__pyx_b); Py_VISIT(traverse_module_state->__pyx_cython_runtime); Py_VISIT(traverse_module_state->__pyx_empty_tuple); Py_VISIT(traverse_module_state->__pyx_empty_bytes); Py_VISIT(traverse_module_state->__pyx_empty_unicode); #ifdef __Pyx_CyFunction_USED Py_VISIT(traverse_module_state->__pyx_CyFunctionType); #endif #ifdef __Pyx_FusedFunction_USED Py_VISIT(traverse_module_state->__pyx_FusedFunctionType); #endif Py_VISIT(traverse_module_state->__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor); Py_VISIT(traverse_module_state->__pyx_type_18curated_tokenizers_5_bbpe_ByteBPEProcessor); Py_VISIT(traverse_module_state->__pyx_ptype_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr); Py_VISIT(traverse_module_state->__pyx_type_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr); Py_VISIT(traverse_module_state->__pyx_n_s_ByteBPEProcessor); Py_VISIT(traverse_module_state->__pyx_n_s_ByteBPEProcessor___copy); Py_VISIT(traverse_module_state->__pyx_n_s_ByteBPEProcessor___deepcopy); Py_VISIT(traverse_module_state->__pyx_n_s_ByteBPEProcessor___reduce); Py_VISIT(traverse_module_state->__pyx_n_s_ByteBPEProcessor__pieces_to_ids); Py_VISIT(traverse_module_state->__pyx_n_s_ByteBPEProcessor_decode_from_ids); Py_VISIT(traverse_module_state->__pyx_n_s_ByteBPEProcessor_encode); Py_VISIT(traverse_module_state->__pyx_n_s_ByteBPEProcessor_encode_as_ids); Py_VISIT(traverse_module_state->__pyx_n_s_ByteBPEProcessor_encode_as_piece); Py_VISIT(traverse_module_state->__pyx_n_s_ByteBPEProcessor_load_from_files); Py_VISIT(traverse_module_state->__pyx_n_s_ByteBPEProcessor_piece_id); Py_VISIT(traverse_module_state->__pyx_n_s_BytesIO); Py_VISIT(traverse_module_state->__pyx_n_s_Dict); Py_VISIT(traverse_module_state->__pyx_kp_s_Dict_int_bytes); Py_VISIT(traverse_module_state->__pyx_kp_s_Dict_str_int); Py_VISIT(traverse_module_state->__pyx_n_s_Iterable); Py_VISIT(traverse_module_state->__pyx_kp_s_Iterable_int); Py_VISIT(traverse_module_state->__pyx_n_s_List); Py_VISIT(traverse_module_state->__pyx_kp_s_List_Tuple_str_str); Py_VISIT(traverse_module_state->__pyx_kp_s_List_int); Py_VISIT(traverse_module_state->__pyx_kp_s_List_str); Py_VISIT(traverse_module_state->__pyx_kp_u_Merge_must_consist_of_2_items_wa); Py_VISIT(traverse_module_state->__pyx_kp_u_Only_version_0_2_of_the_merges_f); Py_VISIT(traverse_module_state->__pyx_n_s_Optional); Py_VISIT(traverse_module_state->__pyx_kp_s_Optional_int); Py_VISIT(traverse_module_state->__pyx_n_s_Path); Py_VISIT(traverse_module_state->__pyx_kp_u_Piece_is_not_in_vocabulary); Py_VISIT(traverse_module_state->__pyx_n_s_SPLIT_PATTERN); Py_VISIT(traverse_module_state->__pyx_n_s_Tuple); Py_VISIT(traverse_module_state->__pyx_kp_s_Tuple_List_int_List_str); Py_VISIT(traverse_module_state->__pyx_kp_u_Unknown_piece_identifier); Py_VISIT(traverse_module_state->__pyx_n_s_ValueError); Py_VISIT(traverse_module_state->__pyx_kp_s__2); Py_VISIT(traverse_module_state->__pyx_n_s__28); Py_VISIT(traverse_module_state->__pyx_kp_u__3); Py_VISIT(traverse_module_state->__pyx_kp_u__4); Py_VISIT(traverse_module_state->__pyx_n_s__5); Py_VISIT(traverse_module_state->__pyx_n_s_append); Py_VISIT(traverse_module_state->__pyx_n_s_args); Py_VISIT(traverse_module_state->__pyx_n_s_asyncio_coroutines); Py_VISIT(traverse_module_state->__pyx_n_s_b); Py_VISIT(traverse_module_state->__pyx_n_s_bs); Py_VISIT(traverse_module_state->__pyx_n_s_bytes_to_unicode); Py_VISIT(traverse_module_state->__pyx_n_s_chr); Py_VISIT(traverse_module_state->__pyx_n_s_cline_in_traceback); Py_VISIT(traverse_module_state->__pyx_n_s_close); Py_VISIT(traverse_module_state->__pyx_n_s_compile); Py_VISIT(traverse_module_state->__pyx_n_s_copy); Py_VISIT(traverse_module_state->__pyx_n_s_cp); Py_VISIT(traverse_module_state->__pyx_n_s_cs); Py_VISIT(traverse_module_state->__pyx_n_s_curated_tokenizers__bbpe); Py_VISIT(traverse_module_state->__pyx_kp_s_curated_tokenizers__bbpe_pyx); Py_VISIT(traverse_module_state->__pyx_n_s_decode); Py_VISIT(traverse_module_state->__pyx_n_s_decode_from_ids); Py_VISIT(traverse_module_state->__pyx_n_s_decoded); Py_VISIT(traverse_module_state->__pyx_n_s_deepcopy); Py_VISIT(traverse_module_state->__pyx_n_s_dict); Py_VISIT(traverse_module_state->__pyx_kp_u_disable); Py_VISIT(traverse_module_state->__pyx_kp_u_enable); Py_VISIT(traverse_module_state->__pyx_n_s_encode); Py_VISIT(traverse_module_state->__pyx_n_s_encode_as_ids); Py_VISIT(traverse_module_state->__pyx_n_s_encode_as_pieces); Py_VISIT(traverse_module_state->__pyx_n_s_encode_as_pieces_locals_genexpr); Py_VISIT(traverse_module_state->__pyx_n_s_encoding); Py_VISIT(traverse_module_state->__pyx_n_s_enter); Py_VISIT(traverse_module_state->__pyx_n_s_exit); Py_VISIT(traverse_module_state->__pyx_n_s_f); Py_VISIT(traverse_module_state->__pyx_n_s_findall); Py_VISIT(traverse_module_state->__pyx_n_s_functools); Py_VISIT(traverse_module_state->__pyx_kp_u_gc); Py_VISIT(traverse_module_state->__pyx_n_s_genexpr); Py_VISIT(traverse_module_state->__pyx_n_s_get); Py_VISIT(traverse_module_state->__pyx_n_s_getvalue); Py_VISIT(traverse_module_state->__pyx_n_s_ids); Py_VISIT(traverse_module_state->__pyx_n_s_import); Py_VISIT(traverse_module_state->__pyx_n_s_initializing); Py_VISIT(traverse_module_state->__pyx_n_s_io); Py_VISIT(traverse_module_state->__pyx_n_s_is_coroutine); Py_VISIT(traverse_module_state->__pyx_kp_u_isenabled); Py_VISIT(traverse_module_state->__pyx_n_s_items); Py_VISIT(traverse_module_state->__pyx_n_s_json); Py_VISIT(traverse_module_state->__pyx_n_s_line); Py_VISIT(traverse_module_state->__pyx_n_s_load); Py_VISIT(traverse_module_state->__pyx_n_s_load_from_files); Py_VISIT(traverse_module_state->__pyx_n_s_lru_cache); Py_VISIT(traverse_module_state->__pyx_n_s_main); Py_VISIT(traverse_module_state->__pyx_n_s_memo); Py_VISIT(traverse_module_state->__pyx_n_s_merge); Py_VISIT(traverse_module_state->__pyx_n_s_merged); Py_VISIT(traverse_module_state->__pyx_n_s_merges); Py_VISIT(traverse_module_state->__pyx_n_s_n); Py_VISIT(traverse_module_state->__pyx_n_s_name); Py_VISIT(traverse_module_state->__pyx_n_s_open); Py_VISIT(traverse_module_state->__pyx_n_s_pathlib); Py_VISIT(traverse_module_state->__pyx_n_s_piece); Py_VISIT(traverse_module_state->__pyx_n_s_piece_id); Py_VISIT(traverse_module_state->__pyx_n_s_piece_ids); Py_VISIT(traverse_module_state->__pyx_n_s_pieces); Py_VISIT(traverse_module_state->__pyx_n_s_pieces_to_ids); Py_VISIT(traverse_module_state->__pyx_n_s_range); Py_VISIT(traverse_module_state->__pyx_n_s_readline); Py_VISIT(traverse_module_state->__pyx_n_s_reduce); Py_VISIT(traverse_module_state->__pyx_n_s_regex); Py_VISIT(traverse_module_state->__pyx_n_s_return); Py_VISIT(traverse_module_state->__pyx_kp_s_s_t_re_ve_m_ll_d_p_L_p_N_s_p_L); Py_VISIT(traverse_module_state->__pyx_n_s_self); Py_VISIT(traverse_module_state->__pyx_n_s_send); Py_VISIT(traverse_module_state->__pyx_n_s_spec); Py_VISIT(traverse_module_state->__pyx_n_s_split); Py_VISIT(traverse_module_state->__pyx_n_s_startswith); Py_VISIT(traverse_module_state->__pyx_n_s_staticmethod); Py_VISIT(traverse_module_state->__pyx_n_s_str); Py_VISIT(traverse_module_state->__pyx_n_s_strip); Py_VISIT(traverse_module_state->__pyx_n_s_test); Py_VISIT(traverse_module_state->__pyx_n_s_text); Py_VISIT(traverse_module_state->__pyx_n_s_throw); Py_VISIT(traverse_module_state->__pyx_n_s_token); Py_VISIT(traverse_module_state->__pyx_n_s_token_bytes); Py_VISIT(traverse_module_state->__pyx_n_s_typing); Py_VISIT(traverse_module_state->__pyx_n_s_unpickle_byte_bpe_processor); Py_VISIT(traverse_module_state->__pyx_kp_s_utf_8); Py_VISIT(traverse_module_state->__pyx_n_s_version); Py_VISIT(traverse_module_state->__pyx_kp_s_version_0_2); Py_VISIT(traverse_module_state->__pyx_n_s_vocab); Py_VISIT(traverse_module_state->__pyx_n_s_write); Py_VISIT(traverse_module_state->__pyx_n_s_zip); Py_VISIT(traverse_module_state->__pyx_int_0); Py_VISIT(traverse_module_state->__pyx_int_1); Py_VISIT(traverse_module_state->__pyx_int_33); Py_VISIT(traverse_module_state->__pyx_int_161); Py_VISIT(traverse_module_state->__pyx_int_174); Py_VISIT(traverse_module_state->__pyx_int_256); Py_VISIT(traverse_module_state->__pyx_tuple_); Py_VISIT(traverse_module_state->__pyx_tuple__6); Py_VISIT(traverse_module_state->__pyx_tuple__8); Py_VISIT(traverse_module_state->__pyx_tuple__10); Py_VISIT(traverse_module_state->__pyx_tuple__12); Py_VISIT(traverse_module_state->__pyx_tuple__14); Py_VISIT(traverse_module_state->__pyx_tuple__16); Py_VISIT(traverse_module_state->__pyx_tuple__19); Py_VISIT(traverse_module_state->__pyx_tuple__21); Py_VISIT(traverse_module_state->__pyx_tuple__23); Py_VISIT(traverse_module_state->__pyx_tuple__26); Py_VISIT(traverse_module_state->__pyx_codeobj__7); Py_VISIT(traverse_module_state->__pyx_codeobj__9); Py_VISIT(traverse_module_state->__pyx_codeobj__11); Py_VISIT(traverse_module_state->__pyx_codeobj__13); Py_VISIT(traverse_module_state->__pyx_codeobj__15); Py_VISIT(traverse_module_state->__pyx_codeobj__17); Py_VISIT(traverse_module_state->__pyx_codeobj__18); Py_VISIT(traverse_module_state->__pyx_codeobj__20); Py_VISIT(traverse_module_state->__pyx_codeobj__22); Py_VISIT(traverse_module_state->__pyx_codeobj__24); Py_VISIT(traverse_module_state->__pyx_codeobj__25); Py_VISIT(traverse_module_state->__pyx_codeobj__27); return 0; } #endif /* #### Code section: module_state_defines ### */ #define __pyx_d __pyx_mstate_global->__pyx_d #define __pyx_b __pyx_mstate_global->__pyx_b #define __pyx_cython_runtime __pyx_mstate_global->__pyx_cython_runtime #define __pyx_empty_tuple __pyx_mstate_global->__pyx_empty_tuple #define __pyx_empty_bytes __pyx_mstate_global->__pyx_empty_bytes #define __pyx_empty_unicode __pyx_mstate_global->__pyx_empty_unicode #ifdef __Pyx_CyFunction_USED #define __pyx_CyFunctionType __pyx_mstate_global->__pyx_CyFunctionType #endif #ifdef __Pyx_FusedFunction_USED #define __pyx_FusedFunctionType __pyx_mstate_global->__pyx_FusedFunctionType #endif #ifdef __Pyx_Generator_USED #define __pyx_GeneratorType __pyx_mstate_global->__pyx_GeneratorType #endif #ifdef __Pyx_IterableCoroutine_USED #define __pyx_IterableCoroutineType __pyx_mstate_global->__pyx_IterableCoroutineType #endif #ifdef __Pyx_Coroutine_USED #define __pyx_CoroutineAwaitType __pyx_mstate_global->__pyx_CoroutineAwaitType #endif #ifdef __Pyx_Coroutine_USED #define __pyx_CoroutineType __pyx_mstate_global->__pyx_CoroutineType #endif #if CYTHON_USE_MODULE_STATE #endif #if CYTHON_USE_MODULE_STATE #endif #if CYTHON_USE_MODULE_STATE #endif #if CYTHON_USE_MODULE_STATE #endif #if CYTHON_USE_MODULE_STATE #endif #if CYTHON_USE_MODULE_STATE #endif #if CYTHON_USE_MODULE_STATE #define __pyx_type_18curated_tokenizers_5_bbpe_ByteBPEProcessor __pyx_mstate_global->__pyx_type_18curated_tokenizers_5_bbpe_ByteBPEProcessor #define __pyx_type_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr __pyx_mstate_global->__pyx_type_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr #endif #define __pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor __pyx_mstate_global->__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor #define __pyx_ptype_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr __pyx_mstate_global->__pyx_ptype_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr #define __pyx_n_s_ByteBPEProcessor __pyx_mstate_global->__pyx_n_s_ByteBPEProcessor #define __pyx_n_s_ByteBPEProcessor___copy __pyx_mstate_global->__pyx_n_s_ByteBPEProcessor___copy #define __pyx_n_s_ByteBPEProcessor___deepcopy __pyx_mstate_global->__pyx_n_s_ByteBPEProcessor___deepcopy #define __pyx_n_s_ByteBPEProcessor___reduce __pyx_mstate_global->__pyx_n_s_ByteBPEProcessor___reduce #define __pyx_n_s_ByteBPEProcessor__pieces_to_ids __pyx_mstate_global->__pyx_n_s_ByteBPEProcessor__pieces_to_ids #define __pyx_n_s_ByteBPEProcessor_decode_from_ids __pyx_mstate_global->__pyx_n_s_ByteBPEProcessor_decode_from_ids #define __pyx_n_s_ByteBPEProcessor_encode __pyx_mstate_global->__pyx_n_s_ByteBPEProcessor_encode #define __pyx_n_s_ByteBPEProcessor_encode_as_ids __pyx_mstate_global->__pyx_n_s_ByteBPEProcessor_encode_as_ids #define __pyx_n_s_ByteBPEProcessor_encode_as_piece __pyx_mstate_global->__pyx_n_s_ByteBPEProcessor_encode_as_piece #define __pyx_n_s_ByteBPEProcessor_load_from_files __pyx_mstate_global->__pyx_n_s_ByteBPEProcessor_load_from_files #define __pyx_n_s_ByteBPEProcessor_piece_id __pyx_mstate_global->__pyx_n_s_ByteBPEProcessor_piece_id #define __pyx_n_s_BytesIO __pyx_mstate_global->__pyx_n_s_BytesIO #define __pyx_n_s_Dict __pyx_mstate_global->__pyx_n_s_Dict #define __pyx_kp_s_Dict_int_bytes __pyx_mstate_global->__pyx_kp_s_Dict_int_bytes #define __pyx_kp_s_Dict_str_int __pyx_mstate_global->__pyx_kp_s_Dict_str_int #define __pyx_n_s_Iterable __pyx_mstate_global->__pyx_n_s_Iterable #define __pyx_kp_s_Iterable_int __pyx_mstate_global->__pyx_kp_s_Iterable_int #define __pyx_n_s_List __pyx_mstate_global->__pyx_n_s_List #define __pyx_kp_s_List_Tuple_str_str __pyx_mstate_global->__pyx_kp_s_List_Tuple_str_str #define __pyx_kp_s_List_int __pyx_mstate_global->__pyx_kp_s_List_int #define __pyx_kp_s_List_str __pyx_mstate_global->__pyx_kp_s_List_str #define __pyx_kp_u_Merge_must_consist_of_2_items_wa __pyx_mstate_global->__pyx_kp_u_Merge_must_consist_of_2_items_wa #define __pyx_kp_u_Only_version_0_2_of_the_merges_f __pyx_mstate_global->__pyx_kp_u_Only_version_0_2_of_the_merges_f #define __pyx_n_s_Optional __pyx_mstate_global->__pyx_n_s_Optional #define __pyx_kp_s_Optional_int __pyx_mstate_global->__pyx_kp_s_Optional_int #define __pyx_n_s_Path __pyx_mstate_global->__pyx_n_s_Path #define __pyx_kp_u_Piece_is_not_in_vocabulary __pyx_mstate_global->__pyx_kp_u_Piece_is_not_in_vocabulary #define __pyx_n_s_SPLIT_PATTERN __pyx_mstate_global->__pyx_n_s_SPLIT_PATTERN #define __pyx_n_s_Tuple __pyx_mstate_global->__pyx_n_s_Tuple #define __pyx_kp_s_Tuple_List_int_List_str __pyx_mstate_global->__pyx_kp_s_Tuple_List_int_List_str #define __pyx_kp_u_Unknown_piece_identifier __pyx_mstate_global->__pyx_kp_u_Unknown_piece_identifier #define __pyx_n_s_ValueError __pyx_mstate_global->__pyx_n_s_ValueError #define __pyx_kp_s__2 __pyx_mstate_global->__pyx_kp_s__2 #define __pyx_n_s__28 __pyx_mstate_global->__pyx_n_s__28 #define __pyx_kp_u__3 __pyx_mstate_global->__pyx_kp_u__3 #define __pyx_kp_u__4 __pyx_mstate_global->__pyx_kp_u__4 #define __pyx_n_s__5 __pyx_mstate_global->__pyx_n_s__5 #define __pyx_n_s_append __pyx_mstate_global->__pyx_n_s_append #define __pyx_n_s_args __pyx_mstate_global->__pyx_n_s_args #define __pyx_n_s_asyncio_coroutines __pyx_mstate_global->__pyx_n_s_asyncio_coroutines #define __pyx_n_s_b __pyx_mstate_global->__pyx_n_s_b #define __pyx_n_s_bs __pyx_mstate_global->__pyx_n_s_bs #define __pyx_n_s_bytes_to_unicode __pyx_mstate_global->__pyx_n_s_bytes_to_unicode #define __pyx_n_s_chr __pyx_mstate_global->__pyx_n_s_chr #define __pyx_n_s_cline_in_traceback __pyx_mstate_global->__pyx_n_s_cline_in_traceback #define __pyx_n_s_close __pyx_mstate_global->__pyx_n_s_close #define __pyx_n_s_compile __pyx_mstate_global->__pyx_n_s_compile #define __pyx_n_s_copy __pyx_mstate_global->__pyx_n_s_copy #define __pyx_n_s_cp __pyx_mstate_global->__pyx_n_s_cp #define __pyx_n_s_cs __pyx_mstate_global->__pyx_n_s_cs #define __pyx_n_s_curated_tokenizers__bbpe __pyx_mstate_global->__pyx_n_s_curated_tokenizers__bbpe #define __pyx_kp_s_curated_tokenizers__bbpe_pyx __pyx_mstate_global->__pyx_kp_s_curated_tokenizers__bbpe_pyx #define __pyx_n_s_decode __pyx_mstate_global->__pyx_n_s_decode #define __pyx_n_s_decode_from_ids __pyx_mstate_global->__pyx_n_s_decode_from_ids #define __pyx_n_s_decoded __pyx_mstate_global->__pyx_n_s_decoded #define __pyx_n_s_deepcopy __pyx_mstate_global->__pyx_n_s_deepcopy #define __pyx_n_s_dict __pyx_mstate_global->__pyx_n_s_dict #define __pyx_kp_u_disable __pyx_mstate_global->__pyx_kp_u_disable #define __pyx_kp_u_enable __pyx_mstate_global->__pyx_kp_u_enable #define __pyx_n_s_encode __pyx_mstate_global->__pyx_n_s_encode #define __pyx_n_s_encode_as_ids __pyx_mstate_global->__pyx_n_s_encode_as_ids #define __pyx_n_s_encode_as_pieces __pyx_mstate_global->__pyx_n_s_encode_as_pieces #define __pyx_n_s_encode_as_pieces_locals_genexpr __pyx_mstate_global->__pyx_n_s_encode_as_pieces_locals_genexpr #define __pyx_n_s_encoding __pyx_mstate_global->__pyx_n_s_encoding #define __pyx_n_s_enter __pyx_mstate_global->__pyx_n_s_enter #define __pyx_n_s_exit __pyx_mstate_global->__pyx_n_s_exit #define __pyx_n_s_f __pyx_mstate_global->__pyx_n_s_f #define __pyx_n_s_findall __pyx_mstate_global->__pyx_n_s_findall #define __pyx_n_s_functools __pyx_mstate_global->__pyx_n_s_functools #define __pyx_kp_u_gc __pyx_mstate_global->__pyx_kp_u_gc #define __pyx_n_s_genexpr __pyx_mstate_global->__pyx_n_s_genexpr #define __pyx_n_s_get __pyx_mstate_global->__pyx_n_s_get #define __pyx_n_s_getvalue __pyx_mstate_global->__pyx_n_s_getvalue #define __pyx_n_s_ids __pyx_mstate_global->__pyx_n_s_ids #define __pyx_n_s_import __pyx_mstate_global->__pyx_n_s_import #define __pyx_n_s_initializing __pyx_mstate_global->__pyx_n_s_initializing #define __pyx_n_s_io __pyx_mstate_global->__pyx_n_s_io #define __pyx_n_s_is_coroutine __pyx_mstate_global->__pyx_n_s_is_coroutine #define __pyx_kp_u_isenabled __pyx_mstate_global->__pyx_kp_u_isenabled #define __pyx_n_s_items __pyx_mstate_global->__pyx_n_s_items #define __pyx_n_s_json __pyx_mstate_global->__pyx_n_s_json #define __pyx_n_s_line __pyx_mstate_global->__pyx_n_s_line #define __pyx_n_s_load __pyx_mstate_global->__pyx_n_s_load #define __pyx_n_s_load_from_files __pyx_mstate_global->__pyx_n_s_load_from_files #define __pyx_n_s_lru_cache __pyx_mstate_global->__pyx_n_s_lru_cache #define __pyx_n_s_main __pyx_mstate_global->__pyx_n_s_main #define __pyx_n_s_memo __pyx_mstate_global->__pyx_n_s_memo #define __pyx_n_s_merge __pyx_mstate_global->__pyx_n_s_merge #define __pyx_n_s_merged __pyx_mstate_global->__pyx_n_s_merged #define __pyx_n_s_merges __pyx_mstate_global->__pyx_n_s_merges #define __pyx_n_s_n __pyx_mstate_global->__pyx_n_s_n #define __pyx_n_s_name __pyx_mstate_global->__pyx_n_s_name #define __pyx_n_s_open __pyx_mstate_global->__pyx_n_s_open #define __pyx_n_s_pathlib __pyx_mstate_global->__pyx_n_s_pathlib #define __pyx_n_s_piece __pyx_mstate_global->__pyx_n_s_piece #define __pyx_n_s_piece_id __pyx_mstate_global->__pyx_n_s_piece_id #define __pyx_n_s_piece_ids __pyx_mstate_global->__pyx_n_s_piece_ids #define __pyx_n_s_pieces __pyx_mstate_global->__pyx_n_s_pieces #define __pyx_n_s_pieces_to_ids __pyx_mstate_global->__pyx_n_s_pieces_to_ids #define __pyx_n_s_range __pyx_mstate_global->__pyx_n_s_range #define __pyx_n_s_readline __pyx_mstate_global->__pyx_n_s_readline #define __pyx_n_s_reduce __pyx_mstate_global->__pyx_n_s_reduce #define __pyx_n_s_regex __pyx_mstate_global->__pyx_n_s_regex #define __pyx_n_s_return __pyx_mstate_global->__pyx_n_s_return #define __pyx_kp_s_s_t_re_ve_m_ll_d_p_L_p_N_s_p_L __pyx_mstate_global->__pyx_kp_s_s_t_re_ve_m_ll_d_p_L_p_N_s_p_L #define __pyx_n_s_self __pyx_mstate_global->__pyx_n_s_self #define __pyx_n_s_send __pyx_mstate_global->__pyx_n_s_send #define __pyx_n_s_spec __pyx_mstate_global->__pyx_n_s_spec #define __pyx_n_s_split __pyx_mstate_global->__pyx_n_s_split #define __pyx_n_s_startswith __pyx_mstate_global->__pyx_n_s_startswith #define __pyx_n_s_staticmethod __pyx_mstate_global->__pyx_n_s_staticmethod #define __pyx_n_s_str __pyx_mstate_global->__pyx_n_s_str #define __pyx_n_s_strip __pyx_mstate_global->__pyx_n_s_strip #define __pyx_n_s_test __pyx_mstate_global->__pyx_n_s_test #define __pyx_n_s_text __pyx_mstate_global->__pyx_n_s_text #define __pyx_n_s_throw __pyx_mstate_global->__pyx_n_s_throw #define __pyx_n_s_token __pyx_mstate_global->__pyx_n_s_token #define __pyx_n_s_token_bytes __pyx_mstate_global->__pyx_n_s_token_bytes #define __pyx_n_s_typing __pyx_mstate_global->__pyx_n_s_typing #define __pyx_n_s_unpickle_byte_bpe_processor __pyx_mstate_global->__pyx_n_s_unpickle_byte_bpe_processor #define __pyx_kp_s_utf_8 __pyx_mstate_global->__pyx_kp_s_utf_8 #define __pyx_n_s_version __pyx_mstate_global->__pyx_n_s_version #define __pyx_kp_s_version_0_2 __pyx_mstate_global->__pyx_kp_s_version_0_2 #define __pyx_n_s_vocab __pyx_mstate_global->__pyx_n_s_vocab #define __pyx_n_s_write __pyx_mstate_global->__pyx_n_s_write #define __pyx_n_s_zip __pyx_mstate_global->__pyx_n_s_zip #define __pyx_int_0 __pyx_mstate_global->__pyx_int_0 #define __pyx_int_1 __pyx_mstate_global->__pyx_int_1 #define __pyx_int_33 __pyx_mstate_global->__pyx_int_33 #define __pyx_int_161 __pyx_mstate_global->__pyx_int_161 #define __pyx_int_174 __pyx_mstate_global->__pyx_int_174 #define __pyx_int_256 __pyx_mstate_global->__pyx_int_256 #define __pyx_tuple_ __pyx_mstate_global->__pyx_tuple_ #define __pyx_tuple__6 __pyx_mstate_global->__pyx_tuple__6 #define __pyx_tuple__8 __pyx_mstate_global->__pyx_tuple__8 #define __pyx_tuple__10 __pyx_mstate_global->__pyx_tuple__10 #define __pyx_tuple__12 __pyx_mstate_global->__pyx_tuple__12 #define __pyx_tuple__14 __pyx_mstate_global->__pyx_tuple__14 #define __pyx_tuple__16 __pyx_mstate_global->__pyx_tuple__16 #define __pyx_tuple__19 __pyx_mstate_global->__pyx_tuple__19 #define __pyx_tuple__21 __pyx_mstate_global->__pyx_tuple__21 #define __pyx_tuple__23 __pyx_mstate_global->__pyx_tuple__23 #define __pyx_tuple__26 __pyx_mstate_global->__pyx_tuple__26 #define __pyx_codeobj__7 __pyx_mstate_global->__pyx_codeobj__7 #define __pyx_codeobj__9 __pyx_mstate_global->__pyx_codeobj__9 #define __pyx_codeobj__11 __pyx_mstate_global->__pyx_codeobj__11 #define __pyx_codeobj__13 __pyx_mstate_global->__pyx_codeobj__13 #define __pyx_codeobj__15 __pyx_mstate_global->__pyx_codeobj__15 #define __pyx_codeobj__17 __pyx_mstate_global->__pyx_codeobj__17 #define __pyx_codeobj__18 __pyx_mstate_global->__pyx_codeobj__18 #define __pyx_codeobj__20 __pyx_mstate_global->__pyx_codeobj__20 #define __pyx_codeobj__22 __pyx_mstate_global->__pyx_codeobj__22 #define __pyx_codeobj__24 __pyx_mstate_global->__pyx_codeobj__24 #define __pyx_codeobj__25 __pyx_mstate_global->__pyx_codeobj__25 #define __pyx_codeobj__27 __pyx_mstate_global->__pyx_codeobj__27 /* #### Code section: module_code ### */ /* "string.from_py":13 * * @cname("__pyx_convert_string_from_py_std__in_string") * cdef string __pyx_convert_string_from_py_std__in_string(object o) except *: # <<<<<<<<<<<<<< * cdef Py_ssize_t length = 0 * cdef const char* data = __Pyx_PyObject_AsStringAndSize(o, &length) */ static std::string __pyx_convert_string_from_py_std__in_string(PyObject *__pyx_v_o) { Py_ssize_t __pyx_v_length; char const *__pyx_v_data; std::string __pyx_r; char const *__pyx_t_1; std::string __pyx_t_2; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; /* "string.from_py":14 * @cname("__pyx_convert_string_from_py_std__in_string") * cdef string __pyx_convert_string_from_py_std__in_string(object o) except *: * cdef Py_ssize_t length = 0 # <<<<<<<<<<<<<< * cdef const char* data = __Pyx_PyObject_AsStringAndSize(o, &length) * return string(data, length) */ __pyx_v_length = 0; /* "string.from_py":15 * cdef string __pyx_convert_string_from_py_std__in_string(object o) except *: * cdef Py_ssize_t length = 0 * cdef const char* data = __Pyx_PyObject_AsStringAndSize(o, &length) # <<<<<<<<<<<<<< * return string(data, length) * */ __pyx_t_1 = __Pyx_PyObject_AsStringAndSize(__pyx_v_o, (&__pyx_v_length)); if (unlikely(__pyx_t_1 == ((char const *)NULL))) __PYX_ERR(1, 15, __pyx_L1_error) __pyx_v_data = __pyx_t_1; /* "string.from_py":16 * cdef Py_ssize_t length = 0 * cdef const char* data = __Pyx_PyObject_AsStringAndSize(o, &length) * return string(data, length) # <<<<<<<<<<<<<< * * */ try { __pyx_t_2 = std::string(__pyx_v_data, __pyx_v_length); } catch(...) { __Pyx_CppExn2PyErr(); __PYX_ERR(1, 16, __pyx_L1_error) } __pyx_r = __pyx_t_2; goto __pyx_L0; /* "string.from_py":13 * * @cname("__pyx_convert_string_from_py_std__in_string") * cdef string __pyx_convert_string_from_py_std__in_string(object o) except *: # <<<<<<<<<<<<<< * cdef Py_ssize_t length = 0 * cdef const char* data = __Pyx_PyObject_AsStringAndSize(o, &length) */ /* function exit code */ __pyx_L1_error:; __Pyx_AddTraceback("string.from_py.__pyx_convert_string_from_py_std__in_string", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_pretend_to_initialize(&__pyx_r); __pyx_L0:; return __pyx_r; } /* "vector.from_py":45 * * @cname("__pyx_convert_vector_from_py_std_3a__3a_string") * cdef vector[X] __pyx_convert_vector_from_py_std_3a__3a_string(object o) except *: # <<<<<<<<<<<<<< * cdef vector[X] v * for item in o: */ static std::vector __pyx_convert_vector_from_py_std_3a__3a_string(PyObject *__pyx_v_o) { std::vector __pyx_v_v; PyObject *__pyx_v_item = NULL; std::vector __pyx_r; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; Py_ssize_t __pyx_t_2; PyObject *(*__pyx_t_3)(PyObject *); PyObject *__pyx_t_4 = NULL; std::string __pyx_t_5; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("__pyx_convert_vector_from_py_std_3a__3a_string", 1); /* "vector.from_py":47 * cdef vector[X] __pyx_convert_vector_from_py_std_3a__3a_string(object o) except *: * cdef vector[X] v * for item in o: # <<<<<<<<<<<<<< * v.push_back(item) * return v */ if (likely(PyList_CheckExact(__pyx_v_o)) || PyTuple_CheckExact(__pyx_v_o)) { __pyx_t_1 = __pyx_v_o; __Pyx_INCREF(__pyx_t_1); __pyx_t_2 = 0; __pyx_t_3 = NULL; } else { __pyx_t_2 = -1; __pyx_t_1 = PyObject_GetIter(__pyx_v_o); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 47, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_3 = __Pyx_PyObject_GetIterNextFunc(__pyx_t_1); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 47, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_3)) { if (likely(PyList_CheckExact(__pyx_t_1))) { { Py_ssize_t __pyx_temp = __Pyx_PyList_GET_SIZE(__pyx_t_1); #if !CYTHON_ASSUME_SAFE_MACROS if (unlikely((__pyx_temp < 0))) __PYX_ERR(1, 47, __pyx_L1_error) #endif if (__pyx_t_2 >= __pyx_temp) break; } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_4 = PyList_GET_ITEM(__pyx_t_1, __pyx_t_2); __Pyx_INCREF(__pyx_t_4); __pyx_t_2++; if (unlikely((0 < 0))) __PYX_ERR(1, 47, __pyx_L1_error) #else __pyx_t_4 = __Pyx_PySequence_ITEM(__pyx_t_1, __pyx_t_2); __pyx_t_2++; if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 47, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); #endif } else { { Py_ssize_t __pyx_temp = __Pyx_PyTuple_GET_SIZE(__pyx_t_1); #if !CYTHON_ASSUME_SAFE_MACROS if (unlikely((__pyx_temp < 0))) __PYX_ERR(1, 47, __pyx_L1_error) #endif if (__pyx_t_2 >= __pyx_temp) break; } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_4 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_2); __Pyx_INCREF(__pyx_t_4); __pyx_t_2++; if (unlikely((0 < 0))) __PYX_ERR(1, 47, __pyx_L1_error) #else __pyx_t_4 = __Pyx_PySequence_ITEM(__pyx_t_1, __pyx_t_2); __pyx_t_2++; if (unlikely(!__pyx_t_4)) __PYX_ERR(1, 47, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); #endif } } else { __pyx_t_4 = __pyx_t_3(__pyx_t_1); if (unlikely(!__pyx_t_4)) { PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); else __PYX_ERR(1, 47, __pyx_L1_error) } break; } __Pyx_GOTREF(__pyx_t_4); } __Pyx_XDECREF_SET(__pyx_v_item, __pyx_t_4); __pyx_t_4 = 0; /* "vector.from_py":48 * cdef vector[X] v * for item in o: * v.push_back(item) # <<<<<<<<<<<<<< * return v * */ __pyx_t_5 = __pyx_convert_string_from_py_std__in_string(__pyx_v_item); if (unlikely(PyErr_Occurred())) __PYX_ERR(1, 48, __pyx_L1_error) try { __pyx_v_v.push_back(((std::string)__pyx_t_5)); } catch(...) { __Pyx_CppExn2PyErr(); __PYX_ERR(1, 48, __pyx_L1_error) } /* "vector.from_py":47 * cdef vector[X] __pyx_convert_vector_from_py_std_3a__3a_string(object o) except *: * cdef vector[X] v * for item in o: # <<<<<<<<<<<<<< * v.push_back(item) * return v */ } __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; /* "vector.from_py":49 * for item in o: * v.push_back(item) * return v # <<<<<<<<<<<<<< * * */ __pyx_r = __pyx_v_v; goto __pyx_L0; /* "vector.from_py":45 * * @cname("__pyx_convert_vector_from_py_std_3a__3a_string") * cdef vector[X] __pyx_convert_vector_from_py_std_3a__3a_string(object o) except *: # <<<<<<<<<<<<<< * cdef vector[X] v * for item in o: */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_XDECREF(__pyx_t_4); __Pyx_AddTraceback("vector.from_py.__pyx_convert_vector_from_py_std_3a__3a_string", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_pretend_to_initialize(&__pyx_r); __pyx_L0:; __Pyx_XDECREF(__pyx_v_item); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "string.to_py":31 * * @cname("__pyx_convert_PyObject_string_to_py_std__in_string") * cdef inline object __pyx_convert_PyObject_string_to_py_std__in_string(const string& s): # <<<<<<<<<<<<<< * return __Pyx_PyObject_FromStringAndSize(s.data(), s.size()) * cdef extern from *: */ static CYTHON_INLINE PyObject *__pyx_convert_PyObject_string_to_py_std__in_string(std::string const &__pyx_v_s) { PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("__pyx_convert_PyObject_string_to_py_std__in_string", 1); /* "string.to_py":32 * @cname("__pyx_convert_PyObject_string_to_py_std__in_string") * cdef inline object __pyx_convert_PyObject_string_to_py_std__in_string(const string& s): * return __Pyx_PyObject_FromStringAndSize(s.data(), s.size()) # <<<<<<<<<<<<<< * cdef extern from *: * cdef object __Pyx_PyUnicode_FromStringAndSize(const char*, size_t) */ __Pyx_XDECREF(__pyx_r); __pyx_t_1 = __Pyx_PyObject_FromStringAndSize(__pyx_v_s.data(), __pyx_v_s.size()); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 32, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; /* "string.to_py":31 * * @cname("__pyx_convert_PyObject_string_to_py_std__in_string") * cdef inline object __pyx_convert_PyObject_string_to_py_std__in_string(const string& s): # <<<<<<<<<<<<<< * return __Pyx_PyObject_FromStringAndSize(s.data(), s.size()) * cdef extern from *: */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_AddTraceback("string.to_py.__pyx_convert_PyObject_string_to_py_std__in_string", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = 0; __pyx_L0:; __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "string.to_py":37 * * @cname("__pyx_convert_PyUnicode_string_to_py_std__in_string") * cdef inline object __pyx_convert_PyUnicode_string_to_py_std__in_string(const string& s): # <<<<<<<<<<<<<< * return __Pyx_PyUnicode_FromStringAndSize(s.data(), s.size()) * cdef extern from *: */ static CYTHON_INLINE PyObject *__pyx_convert_PyUnicode_string_to_py_std__in_string(std::string const &__pyx_v_s) { PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("__pyx_convert_PyUnicode_string_to_py_std__in_string", 1); /* "string.to_py":38 * @cname("__pyx_convert_PyUnicode_string_to_py_std__in_string") * cdef inline object __pyx_convert_PyUnicode_string_to_py_std__in_string(const string& s): * return __Pyx_PyUnicode_FromStringAndSize(s.data(), s.size()) # <<<<<<<<<<<<<< * cdef extern from *: * cdef object __Pyx_PyStr_FromStringAndSize(const char*, size_t) */ __Pyx_XDECREF(__pyx_r); __pyx_t_1 = __Pyx_PyUnicode_FromStringAndSize(__pyx_v_s.data(), __pyx_v_s.size()); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 38, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; /* "string.to_py":37 * * @cname("__pyx_convert_PyUnicode_string_to_py_std__in_string") * cdef inline object __pyx_convert_PyUnicode_string_to_py_std__in_string(const string& s): # <<<<<<<<<<<<<< * return __Pyx_PyUnicode_FromStringAndSize(s.data(), s.size()) * cdef extern from *: */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_AddTraceback("string.to_py.__pyx_convert_PyUnicode_string_to_py_std__in_string", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = 0; __pyx_L0:; __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "string.to_py":43 * * @cname("__pyx_convert_PyStr_string_to_py_std__in_string") * cdef inline object __pyx_convert_PyStr_string_to_py_std__in_string(const string& s): # <<<<<<<<<<<<<< * return __Pyx_PyStr_FromStringAndSize(s.data(), s.size()) * cdef extern from *: */ static CYTHON_INLINE PyObject *__pyx_convert_PyStr_string_to_py_std__in_string(std::string const &__pyx_v_s) { PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("__pyx_convert_PyStr_string_to_py_std__in_string", 1); /* "string.to_py":44 * @cname("__pyx_convert_PyStr_string_to_py_std__in_string") * cdef inline object __pyx_convert_PyStr_string_to_py_std__in_string(const string& s): * return __Pyx_PyStr_FromStringAndSize(s.data(), s.size()) # <<<<<<<<<<<<<< * cdef extern from *: * cdef object __Pyx_PyBytes_FromStringAndSize(const char*, size_t) */ __Pyx_XDECREF(__pyx_r); __pyx_t_1 = __Pyx_PyStr_FromStringAndSize(__pyx_v_s.data(), __pyx_v_s.size()); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 44, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; /* "string.to_py":43 * * @cname("__pyx_convert_PyStr_string_to_py_std__in_string") * cdef inline object __pyx_convert_PyStr_string_to_py_std__in_string(const string& s): # <<<<<<<<<<<<<< * return __Pyx_PyStr_FromStringAndSize(s.data(), s.size()) * cdef extern from *: */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_AddTraceback("string.to_py.__pyx_convert_PyStr_string_to_py_std__in_string", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = 0; __pyx_L0:; __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "string.to_py":49 * * @cname("__pyx_convert_PyBytes_string_to_py_std__in_string") * cdef inline object __pyx_convert_PyBytes_string_to_py_std__in_string(const string& s): # <<<<<<<<<<<<<< * return __Pyx_PyBytes_FromStringAndSize(s.data(), s.size()) * cdef extern from *: */ static CYTHON_INLINE PyObject *__pyx_convert_PyBytes_string_to_py_std__in_string(std::string const &__pyx_v_s) { PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("__pyx_convert_PyBytes_string_to_py_std__in_string", 1); /* "string.to_py":50 * @cname("__pyx_convert_PyBytes_string_to_py_std__in_string") * cdef inline object __pyx_convert_PyBytes_string_to_py_std__in_string(const string& s): * return __Pyx_PyBytes_FromStringAndSize(s.data(), s.size()) # <<<<<<<<<<<<<< * cdef extern from *: * cdef object __Pyx_PyByteArray_FromStringAndSize(const char*, size_t) */ __Pyx_XDECREF(__pyx_r); __pyx_t_1 = __Pyx_PyBytes_FromStringAndSize(__pyx_v_s.data(), __pyx_v_s.size()); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 50, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; /* "string.to_py":49 * * @cname("__pyx_convert_PyBytes_string_to_py_std__in_string") * cdef inline object __pyx_convert_PyBytes_string_to_py_std__in_string(const string& s): # <<<<<<<<<<<<<< * return __Pyx_PyBytes_FromStringAndSize(s.data(), s.size()) * cdef extern from *: */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_AddTraceback("string.to_py.__pyx_convert_PyBytes_string_to_py_std__in_string", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = 0; __pyx_L0:; __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "string.to_py":55 * * @cname("__pyx_convert_PyByteArray_string_to_py_std__in_string") * cdef inline object __pyx_convert_PyByteArray_string_to_py_std__in_string(const string& s): # <<<<<<<<<<<<<< * return __Pyx_PyByteArray_FromStringAndSize(s.data(), s.size()) * */ static CYTHON_INLINE PyObject *__pyx_convert_PyByteArray_string_to_py_std__in_string(std::string const &__pyx_v_s) { PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("__pyx_convert_PyByteArray_string_to_py_std__in_string", 1); /* "string.to_py":56 * @cname("__pyx_convert_PyByteArray_string_to_py_std__in_string") * cdef inline object __pyx_convert_PyByteArray_string_to_py_std__in_string(const string& s): * return __Pyx_PyByteArray_FromStringAndSize(s.data(), s.size()) # <<<<<<<<<<<<<< * */ __Pyx_XDECREF(__pyx_r); __pyx_t_1 = __Pyx_PyByteArray_FromStringAndSize(__pyx_v_s.data(), __pyx_v_s.size()); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 56, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; /* "string.to_py":55 * * @cname("__pyx_convert_PyByteArray_string_to_py_std__in_string") * cdef inline object __pyx_convert_PyByteArray_string_to_py_std__in_string(const string& s): # <<<<<<<<<<<<<< * return __Pyx_PyByteArray_FromStringAndSize(s.data(), s.size()) * */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_AddTraceback("string.to_py.__pyx_convert_PyByteArray_string_to_py_std__in_string", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = 0; __pyx_L0:; __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "pair.to_py":190 * * @cname("__pyx_convert_pair_to_py_std_3a__3a_string____std_3a__3a_string") * cdef object __pyx_convert_pair_to_py_std_3a__3a_string____std_3a__3a_string(const pair[X,Y]& p): # <<<<<<<<<<<<<< * return p.first, p.second * */ static PyObject *__pyx_convert_pair_to_py_std_3a__3a_string____std_3a__3a_string(std::pair const &__pyx_v_p) { PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; PyObject *__pyx_t_2 = NULL; PyObject *__pyx_t_3 = NULL; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("__pyx_convert_pair_to_py_std_3a__3a_string____std_3a__3a_string", 1); /* "pair.to_py":191 * @cname("__pyx_convert_pair_to_py_std_3a__3a_string____std_3a__3a_string") * cdef object __pyx_convert_pair_to_py_std_3a__3a_string____std_3a__3a_string(const pair[X,Y]& p): * return p.first, p.second # <<<<<<<<<<<<<< * * */ __Pyx_XDECREF(__pyx_r); __pyx_t_1 = __pyx_convert_PyBytes_string_to_py_std__in_string(__pyx_v_p.first); if (unlikely(!__pyx_t_1)) __PYX_ERR(1, 191, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_2 = __pyx_convert_PyBytes_string_to_py_std__in_string(__pyx_v_p.second); if (unlikely(!__pyx_t_2)) __PYX_ERR(1, 191, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __pyx_t_3 = PyTuple_New(2); if (unlikely(!__pyx_t_3)) __PYX_ERR(1, 191, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_GIVEREF(__pyx_t_1); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_3, 0, __pyx_t_1)) __PYX_ERR(1, 191, __pyx_L1_error); __Pyx_GIVEREF(__pyx_t_2); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_3, 1, __pyx_t_2)) __PYX_ERR(1, 191, __pyx_L1_error); __pyx_t_1 = 0; __pyx_t_2 = 0; __pyx_r = __pyx_t_3; __pyx_t_3 = 0; goto __pyx_L0; /* "pair.to_py":190 * * @cname("__pyx_convert_pair_to_py_std_3a__3a_string____std_3a__3a_string") * cdef object __pyx_convert_pair_to_py_std_3a__3a_string____std_3a__3a_string(const pair[X,Y]& p): # <<<<<<<<<<<<<< * return p.first, p.second * */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_XDECREF(__pyx_t_2); __Pyx_XDECREF(__pyx_t_3); __Pyx_AddTraceback("pair.to_py.__pyx_convert_pair_to_py_std_3a__3a_string____std_3a__3a_string", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = 0; __pyx_L0:; __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "curated_tokenizers/_bbpe.pyx":24 * * * @lru_cache() # <<<<<<<<<<<<<< * def bytes_to_unicode() -> Dict[int, bytes]: * """ */ /* Python wrapper */ static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_1bytes_to_unicode(PyObject *__pyx_self, CYTHON_UNUSED PyObject *unused); /*proto*/ PyDoc_STRVAR(__pyx_doc_18curated_tokenizers_5_bbpe_bytes_to_unicode, "bytes_to_unicode() -> Dict[int, bytes]\n\n Returns list of utf-8 byte and a corresponding list of unicode strings.\n The reversible bpe codes work on unicode strings.\n This means you need a large # of unicode characters in your vocab if you want to avoid UNKs.\n When you're at something like a 10B token dataset you end up needing around 5K for decent coverage.\n This is a signficant percentage of your normal, say, 32K bpe vocab.\n To avoid that, we want lookup tables between utf-8 bytes and unicode strings.\n And avoids mapping to whitespace/control characters the bpe code barfs on.\n "); static PyMethodDef __pyx_mdef_18curated_tokenizers_5_bbpe_1bytes_to_unicode = {"bytes_to_unicode", (PyCFunction)__pyx_pw_18curated_tokenizers_5_bbpe_1bytes_to_unicode, METH_NOARGS, __pyx_doc_18curated_tokenizers_5_bbpe_bytes_to_unicode}; static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_1bytes_to_unicode(PyObject *__pyx_self, CYTHON_UNUSED PyObject *unused) { CYTHON_UNUSED PyObject *const *__pyx_kwvalues; PyObject *__pyx_r = 0; __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("bytes_to_unicode (wrapper)", 0); __pyx_kwvalues = __Pyx_KwValues_VARARGS(__pyx_args, __pyx_nargs); __pyx_r = __pyx_pf_18curated_tokenizers_5_bbpe_bytes_to_unicode(__pyx_self); /* function exit code */ __Pyx_RefNannyFinishContext(); return __pyx_r; } static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_bytes_to_unicode(CYTHON_UNUSED PyObject *__pyx_self) { PyObject *__pyx_v_bs = NULL; PyObject *__pyx_v_cs = NULL; PyObject *__pyx_v_n = NULL; long __pyx_v_b; PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; PyObject *__pyx_t_2 = NULL; PyObject *__pyx_t_3 = NULL; long __pyx_t_4; int __pyx_t_5; int __pyx_t_6; Py_ssize_t __pyx_t_7; PyObject *__pyx_t_8 = NULL; PyObject *__pyx_t_9 = NULL; int __pyx_t_10; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("bytes_to_unicode", 1); /* "curated_tokenizers/_bbpe.pyx":36 * """ * bs = ( * list(range(ord("!"), ord("~") + 1)) # <<<<<<<<<<<<<< * + list(range(ord(""), ord("") + 1)) * + list(range(ord(""), ord("") + 1)) */ __pyx_t_1 = __Pyx_PyInt_From_long((0x7E + 1)); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 36, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_2 = PyTuple_New(2); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 36, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_INCREF(__pyx_int_33); __Pyx_GIVEREF(__pyx_int_33); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_2, 0, __pyx_int_33)) __PYX_ERR(0, 36, __pyx_L1_error); __Pyx_GIVEREF(__pyx_t_1); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_2, 1, __pyx_t_1)) __PYX_ERR(0, 36, __pyx_L1_error); __pyx_t_1 = 0; __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_range, __pyx_t_2, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 36, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = __Pyx_PySequence_ListKeepNew(__pyx_t_1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 36, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":37 * bs = ( * list(range(ord("!"), ord("~") + 1)) * + list(range(ord(""), ord("") + 1)) # <<<<<<<<<<<<<< * + list(range(ord(""), ord("") + 1)) * ) */ __pyx_t_1 = __Pyx_PyInt_From_long((0xAC + 1)); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 37, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_3 = PyTuple_New(2); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 37, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_INCREF(__pyx_int_161); __Pyx_GIVEREF(__pyx_int_161); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_3, 0, __pyx_int_161)) __PYX_ERR(0, 37, __pyx_L1_error); __Pyx_GIVEREF(__pyx_t_1); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_3, 1, __pyx_t_1)) __PYX_ERR(0, 37, __pyx_L1_error); __pyx_t_1 = 0; __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_range, __pyx_t_3, NULL); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 37, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_t_3 = __Pyx_PySequence_ListKeepNew(__pyx_t_1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 37, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_t_1 = PyNumber_Add(__pyx_t_2, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 37, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; /* "curated_tokenizers/_bbpe.pyx":38 * list(range(ord("!"), ord("~") + 1)) * + list(range(ord(""), ord("") + 1)) * + list(range(ord(""), ord("") + 1)) # <<<<<<<<<<<<<< * ) * cs = bs[:] */ __pyx_t_3 = __Pyx_PyInt_From_long((0xFF + 1)); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 38, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_2 = PyTuple_New(2); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 38, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_INCREF(__pyx_int_174); __Pyx_GIVEREF(__pyx_int_174); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_2, 0, __pyx_int_174)) __PYX_ERR(0, 38, __pyx_L1_error); __Pyx_GIVEREF(__pyx_t_3); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_2, 1, __pyx_t_3)) __PYX_ERR(0, 38, __pyx_L1_error); __pyx_t_3 = 0; __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_range, __pyx_t_2, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 38, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = __Pyx_PySequence_ListKeepNew(__pyx_t_3); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 38, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_t_3 = PyNumber_Add(__pyx_t_1, __pyx_t_2); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 38, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_v_bs = ((PyObject*)__pyx_t_3); __pyx_t_3 = 0; /* "curated_tokenizers/_bbpe.pyx":40 * + list(range(ord(""), ord("") + 1)) * ) * cs = bs[:] # <<<<<<<<<<<<<< * n = 0 * for b in range(2**8): */ __pyx_t_3 = __Pyx_PyList_GetSlice(__pyx_v_bs, 0, PY_SSIZE_T_MAX); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 40, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_v_cs = ((PyObject*)__pyx_t_3); __pyx_t_3 = 0; /* "curated_tokenizers/_bbpe.pyx":41 * ) * cs = bs[:] * n = 0 # <<<<<<<<<<<<<< * for b in range(2**8): * if b not in bs: */ __Pyx_INCREF(__pyx_int_0); __pyx_v_n = __pyx_int_0; /* "curated_tokenizers/_bbpe.pyx":42 * cs = bs[:] * n = 0 * for b in range(2**8): # <<<<<<<<<<<<<< * if b not in bs: * bs.append(b) */ for (__pyx_t_4 = 0; __pyx_t_4 < 0x100; __pyx_t_4+=1) { __pyx_v_b = __pyx_t_4; /* "curated_tokenizers/_bbpe.pyx":43 * n = 0 * for b in range(2**8): * if b not in bs: # <<<<<<<<<<<<<< * bs.append(b) * cs.append(2**8 + n) */ __pyx_t_3 = __Pyx_PyInt_From_long(__pyx_v_b); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 43, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_5 = (__Pyx_PySequence_ContainsTF(__pyx_t_3, __pyx_v_bs, Py_NE)); if (unlikely((__pyx_t_5 < 0))) __PYX_ERR(0, 43, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (__pyx_t_5) { /* "curated_tokenizers/_bbpe.pyx":44 * for b in range(2**8): * if b not in bs: * bs.append(b) # <<<<<<<<<<<<<< * cs.append(2**8 + n) * n += 1 */ __pyx_t_3 = __Pyx_PyInt_From_long(__pyx_v_b); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 44, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_6 = __Pyx_PyList_Append(__pyx_v_bs, __pyx_t_3); if (unlikely(__pyx_t_6 == ((int)-1))) __PYX_ERR(0, 44, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; /* "curated_tokenizers/_bbpe.pyx":45 * if b not in bs: * bs.append(b) * cs.append(2**8 + n) # <<<<<<<<<<<<<< * n += 1 * cs = [chr(n).encode("utf-8") for n in cs] */ __pyx_t_3 = __Pyx_PyInt_AddCObj(__pyx_int_256, __pyx_v_n, 0x100, 0, 0); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 45, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_6 = __Pyx_PyList_Append(__pyx_v_cs, __pyx_t_3); if (unlikely(__pyx_t_6 == ((int)-1))) __PYX_ERR(0, 45, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; /* "curated_tokenizers/_bbpe.pyx":46 * bs.append(b) * cs.append(2**8 + n) * n += 1 # <<<<<<<<<<<<<< * cs = [chr(n).encode("utf-8") for n in cs] * return dict(zip(bs, cs)) */ __pyx_t_3 = __Pyx_PyInt_AddObjC(__pyx_v_n, __pyx_int_1, 1, 1, 0); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 46, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF_SET(__pyx_v_n, __pyx_t_3); __pyx_t_3 = 0; /* "curated_tokenizers/_bbpe.pyx":43 * n = 0 * for b in range(2**8): * if b not in bs: # <<<<<<<<<<<<<< * bs.append(b) * cs.append(2**8 + n) */ } } /* "curated_tokenizers/_bbpe.pyx":47 * cs.append(2**8 + n) * n += 1 * cs = [chr(n).encode("utf-8") for n in cs] # <<<<<<<<<<<<<< * return dict(zip(bs, cs)) * */ __pyx_t_3 = PyList_New(0); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 47, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_2 = __pyx_v_cs; __Pyx_INCREF(__pyx_t_2); __pyx_t_7 = 0; for (;;) { { Py_ssize_t __pyx_temp = __Pyx_PyList_GET_SIZE(__pyx_t_2); #if !CYTHON_ASSUME_SAFE_MACROS if (unlikely((__pyx_temp < 0))) __PYX_ERR(0, 47, __pyx_L1_error) #endif if (__pyx_t_7 >= __pyx_temp) break; } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_1 = PyList_GET_ITEM(__pyx_t_2, __pyx_t_7); __Pyx_INCREF(__pyx_t_1); __pyx_t_7++; if (unlikely((0 < 0))) __PYX_ERR(0, 47, __pyx_L1_error) #else __pyx_t_1 = __Pyx_PySequence_ITEM(__pyx_t_2, __pyx_t_7); __pyx_t_7++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 47, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); #endif __Pyx_DECREF_SET(__pyx_v_n, __pyx_t_1); __pyx_t_1 = 0; __pyx_t_8 = __Pyx_PyObject_CallOneArg(__pyx_builtin_chr, __pyx_v_n); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 47, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); __pyx_t_9 = __Pyx_PyObject_GetAttrStr(__pyx_t_8, __pyx_n_s_encode); if (unlikely(!__pyx_t_9)) __PYX_ERR(0, 47, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_9); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __pyx_t_8 = NULL; __pyx_t_10 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_9))) { __pyx_t_8 = PyMethod_GET_SELF(__pyx_t_9); if (likely(__pyx_t_8)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_9); __Pyx_INCREF(__pyx_t_8); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_9, function); __pyx_t_10 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_8, __pyx_kp_s_utf_8}; __pyx_t_1 = __Pyx_PyObject_FastCall(__pyx_t_9, __pyx_callargs+1-__pyx_t_10, 1+__pyx_t_10); __Pyx_XDECREF(__pyx_t_8); __pyx_t_8 = 0; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 47, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; } if (unlikely(__Pyx_ListComp_Append(__pyx_t_3, (PyObject*)__pyx_t_1))) __PYX_ERR(0, 47, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; } __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_DECREF_SET(__pyx_v_cs, ((PyObject*)__pyx_t_3)); __pyx_t_3 = 0; /* "curated_tokenizers/_bbpe.pyx":48 * n += 1 * cs = [chr(n).encode("utf-8") for n in cs] * return dict(zip(bs, cs)) # <<<<<<<<<<<<<< * * cdef class ByteBPEProcessor: */ __Pyx_XDECREF(__pyx_r); __pyx_t_3 = PyTuple_New(2); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 48, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_INCREF(__pyx_v_bs); __Pyx_GIVEREF(__pyx_v_bs); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_3, 0, __pyx_v_bs)) __PYX_ERR(0, 48, __pyx_L1_error); __Pyx_INCREF(__pyx_v_cs); __Pyx_GIVEREF(__pyx_v_cs); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_3, 1, __pyx_v_cs)) __PYX_ERR(0, 48, __pyx_L1_error); __pyx_t_2 = __Pyx_PyObject_Call(__pyx_builtin_zip, __pyx_t_3, NULL); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 48, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_t_3 = __Pyx_PyObject_CallOneArg(((PyObject *)(&PyDict_Type)), __pyx_t_2); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 48, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_r = __pyx_t_3; __pyx_t_3 = 0; goto __pyx_L0; /* "curated_tokenizers/_bbpe.pyx":24 * * * @lru_cache() # <<<<<<<<<<<<<< * def bytes_to_unicode() -> Dict[int, bytes]: * """ */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_XDECREF(__pyx_t_2); __Pyx_XDECREF(__pyx_t_3); __Pyx_XDECREF(__pyx_t_8); __Pyx_XDECREF(__pyx_t_9); __Pyx_AddTraceback("curated_tokenizers._bbpe.bytes_to_unicode", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = NULL; __pyx_L0:; __Pyx_XDECREF(__pyx_v_bs); __Pyx_XDECREF(__pyx_v_cs); __Pyx_XDECREF(__pyx_v_n); __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "curated_tokenizers/_bbpe.pyx":58 * cdef dict _id_to_piece * * def __init__(self, vocab: Dict[str, int], merges: List[Tuple[str, str]]): # <<<<<<<<<<<<<< * self._byte_encoder = bytes_to_unicode() * self._byte_decoder = {v.decode("utf-8"): k for k, v in self._byte_encoder.items()} */ /* Python wrapper */ static int __pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_1__init__(PyObject *__pyx_v_self, PyObject *__pyx_args, PyObject *__pyx_kwds); /*proto*/ static int __pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_1__init__(PyObject *__pyx_v_self, PyObject *__pyx_args, PyObject *__pyx_kwds) { PyObject *__pyx_v_vocab = 0; PyObject *__pyx_v_merges = 0; CYTHON_UNUSED Py_ssize_t __pyx_nargs; CYTHON_UNUSED PyObject *const *__pyx_kwvalues; PyObject* values[2] = {0,0}; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; int __pyx_r; __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__init__ (wrapper)", 0); #if CYTHON_ASSUME_SAFE_MACROS __pyx_nargs = PyTuple_GET_SIZE(__pyx_args); #else __pyx_nargs = PyTuple_Size(__pyx_args); if (unlikely(__pyx_nargs < 0)) return -1; #endif __pyx_kwvalues = __Pyx_KwValues_VARARGS(__pyx_args, __pyx_nargs); { PyObject **__pyx_pyargnames[] = {&__pyx_n_s_vocab,&__pyx_n_s_merges,0}; if (__pyx_kwds) { Py_ssize_t kw_args; switch (__pyx_nargs) { case 2: values[1] = __Pyx_Arg_VARARGS(__pyx_args, 1); CYTHON_FALLTHROUGH; case 1: values[0] = __Pyx_Arg_VARARGS(__pyx_args, 0); CYTHON_FALLTHROUGH; case 0: break; default: goto __pyx_L5_argtuple_error; } kw_args = __Pyx_NumKwargs_VARARGS(__pyx_kwds); switch (__pyx_nargs) { case 0: if (likely((values[0] = __Pyx_GetKwValue_VARARGS(__pyx_kwds, __pyx_kwvalues, __pyx_n_s_vocab)) != 0)) { (void)__Pyx_Arg_NewRef_VARARGS(values[0]); kw_args--; } else if (unlikely(PyErr_Occurred())) __PYX_ERR(0, 58, __pyx_L3_error) else goto __pyx_L5_argtuple_error; CYTHON_FALLTHROUGH; case 1: if (likely((values[1] = __Pyx_GetKwValue_VARARGS(__pyx_kwds, __pyx_kwvalues, __pyx_n_s_merges)) != 0)) { (void)__Pyx_Arg_NewRef_VARARGS(values[1]); kw_args--; } else if (unlikely(PyErr_Occurred())) __PYX_ERR(0, 58, __pyx_L3_error) else { __Pyx_RaiseArgtupleInvalid("__init__", 1, 2, 2, 1); __PYX_ERR(0, 58, __pyx_L3_error) } } if (unlikely(kw_args > 0)) { const Py_ssize_t kwd_pos_args = __pyx_nargs; if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_kwvalues, __pyx_pyargnames, 0, values + 0, kwd_pos_args, "__init__") < 0)) __PYX_ERR(0, 58, __pyx_L3_error) } } else if (unlikely(__pyx_nargs != 2)) { goto __pyx_L5_argtuple_error; } else { values[0] = __Pyx_Arg_VARARGS(__pyx_args, 0); values[1] = __Pyx_Arg_VARARGS(__pyx_args, 1); } __pyx_v_vocab = values[0]; __pyx_v_merges = values[1]; } goto __pyx_L6_skip; __pyx_L5_argtuple_error:; __Pyx_RaiseArgtupleInvalid("__init__", 1, 2, 2, __pyx_nargs); __PYX_ERR(0, 58, __pyx_L3_error) __pyx_L6_skip:; goto __pyx_L4_argument_unpacking_done; __pyx_L3_error:; { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < (Py_ssize_t)(sizeof(values)/sizeof(values[0])); ++__pyx_temp) { __Pyx_Arg_XDECREF_VARARGS(values[__pyx_temp]); } } __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.__init__", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); return -1; __pyx_L4_argument_unpacking_done:; __pyx_r = __pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor___init__(((struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *)__pyx_v_self), __pyx_v_vocab, __pyx_v_merges); /* function exit code */ { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < (Py_ssize_t)(sizeof(values)/sizeof(values[0])); ++__pyx_temp) { __Pyx_Arg_XDECREF_VARARGS(values[__pyx_temp]); } } __Pyx_RefNannyFinishContext(); return __pyx_r; } static int __pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor___init__(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self, PyObject *__pyx_v_vocab, PyObject *__pyx_v_merges) { std::vector > __pyx_v_c_merges; PyObject *__pyx_v_p1 = NULL; PyObject *__pyx_v_p2 = NULL; PyObject *__pyx_7genexpr__pyx_v_k = NULL; PyObject *__pyx_7genexpr__pyx_v_v = NULL; PyObject *__pyx_8genexpr1__pyx_v_k = NULL; PyObject *__pyx_8genexpr1__pyx_v_v = NULL; int __pyx_r; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; PyObject *__pyx_t_2 = NULL; PyObject *__pyx_t_3 = NULL; int __pyx_t_4; Py_ssize_t __pyx_t_5; PyObject *(*__pyx_t_6)(PyObject *); PyObject *__pyx_t_7 = NULL; PyObject *__pyx_t_8 = NULL; PyObject *__pyx_t_9 = NULL; PyObject *(*__pyx_t_10)(PyObject *); std::string __pyx_t_11; std::string __pyx_t_12; std::pair __pyx_t_13; std::shared_ptr __pyx_t_14; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("__init__", 1); /* "curated_tokenizers/_bbpe.pyx":59 * * def __init__(self, vocab: Dict[str, int], merges: List[Tuple[str, str]]): * self._byte_encoder = bytes_to_unicode() # <<<<<<<<<<<<<< * self._byte_decoder = {v.decode("utf-8"): k for k, v in self._byte_encoder.items()} * self._split_pattern = regex.compile(SPLIT_PATTERN) */ __Pyx_GetModuleGlobalName(__pyx_t_2, __pyx_n_s_bytes_to_unicode); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 59, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __pyx_t_3 = NULL; __pyx_t_4 = 0; #if CYTHON_UNPACK_METHODS if (unlikely(PyMethod_Check(__pyx_t_2))) { __pyx_t_3 = PyMethod_GET_SELF(__pyx_t_2); if (likely(__pyx_t_3)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_2); __Pyx_INCREF(__pyx_t_3); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_2, function); __pyx_t_4 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_3, NULL}; __pyx_t_1 = __Pyx_PyObject_FastCall(__pyx_t_2, __pyx_callargs+1-__pyx_t_4, 0+__pyx_t_4); __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 59, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } if (!(likely(PyDict_CheckExact(__pyx_t_1))||((__pyx_t_1) == Py_None) || __Pyx_RaiseUnexpectedTypeError("dict", __pyx_t_1))) __PYX_ERR(0, 59, __pyx_L1_error) __Pyx_GIVEREF(__pyx_t_1); __Pyx_GOTREF(__pyx_v_self->_byte_encoder); __Pyx_DECREF(__pyx_v_self->_byte_encoder); __pyx_v_self->_byte_encoder = ((PyObject*)__pyx_t_1); __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":60 * def __init__(self, vocab: Dict[str, int], merges: List[Tuple[str, str]]): * self._byte_encoder = bytes_to_unicode() * self._byte_decoder = {v.decode("utf-8"): k for k, v in self._byte_encoder.items()} # <<<<<<<<<<<<<< * self._split_pattern = regex.compile(SPLIT_PATTERN) * self._piece_to_id = vocab */ { /* enter inner scope */ __pyx_t_1 = PyDict_New(); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 60, __pyx_L5_error) __Pyx_GOTREF(__pyx_t_1); if (unlikely(__pyx_v_self->_byte_encoder == Py_None)) { PyErr_Format(PyExc_AttributeError, "'NoneType' object has no attribute '%.30s'", "items"); __PYX_ERR(0, 60, __pyx_L5_error) } __pyx_t_2 = __Pyx_PyDict_Items(__pyx_v_self->_byte_encoder); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 60, __pyx_L5_error) __Pyx_GOTREF(__pyx_t_2); if (likely(PyList_CheckExact(__pyx_t_2)) || PyTuple_CheckExact(__pyx_t_2)) { __pyx_t_3 = __pyx_t_2; __Pyx_INCREF(__pyx_t_3); __pyx_t_5 = 0; __pyx_t_6 = NULL; } else { __pyx_t_5 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_t_2); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 60, __pyx_L5_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_6 = __Pyx_PyObject_GetIterNextFunc(__pyx_t_3); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 60, __pyx_L5_error) } __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; for (;;) { if (likely(!__pyx_t_6)) { if (likely(PyList_CheckExact(__pyx_t_3))) { { Py_ssize_t __pyx_temp = __Pyx_PyList_GET_SIZE(__pyx_t_3); #if !CYTHON_ASSUME_SAFE_MACROS if (unlikely((__pyx_temp < 0))) __PYX_ERR(0, 60, __pyx_L5_error) #endif if (__pyx_t_5 >= __pyx_temp) break; } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_2 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_5); __Pyx_INCREF(__pyx_t_2); __pyx_t_5++; if (unlikely((0 < 0))) __PYX_ERR(0, 60, __pyx_L5_error) #else __pyx_t_2 = __Pyx_PySequence_ITEM(__pyx_t_3, __pyx_t_5); __pyx_t_5++; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 60, __pyx_L5_error) __Pyx_GOTREF(__pyx_t_2); #endif } else { { Py_ssize_t __pyx_temp = __Pyx_PyTuple_GET_SIZE(__pyx_t_3); #if !CYTHON_ASSUME_SAFE_MACROS if (unlikely((__pyx_temp < 0))) __PYX_ERR(0, 60, __pyx_L5_error) #endif if (__pyx_t_5 >= __pyx_temp) break; } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_2 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_5); __Pyx_INCREF(__pyx_t_2); __pyx_t_5++; if (unlikely((0 < 0))) __PYX_ERR(0, 60, __pyx_L5_error) #else __pyx_t_2 = __Pyx_PySequence_ITEM(__pyx_t_3, __pyx_t_5); __pyx_t_5++; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 60, __pyx_L5_error) __Pyx_GOTREF(__pyx_t_2); #endif } } else { __pyx_t_2 = __pyx_t_6(__pyx_t_3); if (unlikely(!__pyx_t_2)) { PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); else __PYX_ERR(0, 60, __pyx_L5_error) } break; } __Pyx_GOTREF(__pyx_t_2); } if ((likely(PyTuple_CheckExact(__pyx_t_2))) || (PyList_CheckExact(__pyx_t_2))) { PyObject* sequence = __pyx_t_2; Py_ssize_t size = __Pyx_PySequence_SIZE(sequence); if (unlikely(size != 2)) { if (size > 2) __Pyx_RaiseTooManyValuesError(2); else if (size >= 0) __Pyx_RaiseNeedMoreValuesError(size); __PYX_ERR(0, 60, __pyx_L5_error) } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS if (likely(PyTuple_CheckExact(sequence))) { __pyx_t_7 = PyTuple_GET_ITEM(sequence, 0); __pyx_t_8 = PyTuple_GET_ITEM(sequence, 1); } else { __pyx_t_7 = PyList_GET_ITEM(sequence, 0); __pyx_t_8 = PyList_GET_ITEM(sequence, 1); } __Pyx_INCREF(__pyx_t_7); __Pyx_INCREF(__pyx_t_8); #else __pyx_t_7 = PySequence_ITEM(sequence, 0); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 60, __pyx_L5_error) __Pyx_GOTREF(__pyx_t_7); __pyx_t_8 = PySequence_ITEM(sequence, 1); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 60, __pyx_L5_error) __Pyx_GOTREF(__pyx_t_8); #endif __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } else { Py_ssize_t index = -1; __pyx_t_9 = PyObject_GetIter(__pyx_t_2); if (unlikely(!__pyx_t_9)) __PYX_ERR(0, 60, __pyx_L5_error) __Pyx_GOTREF(__pyx_t_9); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_10 = __Pyx_PyObject_GetIterNextFunc(__pyx_t_9); index = 0; __pyx_t_7 = __pyx_t_10(__pyx_t_9); if (unlikely(!__pyx_t_7)) goto __pyx_L8_unpacking_failed; __Pyx_GOTREF(__pyx_t_7); index = 1; __pyx_t_8 = __pyx_t_10(__pyx_t_9); if (unlikely(!__pyx_t_8)) goto __pyx_L8_unpacking_failed; __Pyx_GOTREF(__pyx_t_8); if (__Pyx_IternextUnpackEndCheck(__pyx_t_10(__pyx_t_9), 2) < 0) __PYX_ERR(0, 60, __pyx_L5_error) __pyx_t_10 = NULL; __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; goto __pyx_L9_unpacking_done; __pyx_L8_unpacking_failed:; __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; __pyx_t_10 = NULL; if (__Pyx_IterFinish() == 0) __Pyx_RaiseNeedMoreValuesError(index); __PYX_ERR(0, 60, __pyx_L5_error) __pyx_L9_unpacking_done:; } __Pyx_XDECREF_SET(__pyx_7genexpr__pyx_v_k, __pyx_t_7); __pyx_t_7 = 0; __Pyx_XDECREF_SET(__pyx_7genexpr__pyx_v_v, __pyx_t_8); __pyx_t_8 = 0; __pyx_t_8 = __Pyx_PyObject_GetAttrStr(__pyx_7genexpr__pyx_v_v, __pyx_n_s_decode); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 60, __pyx_L5_error) __Pyx_GOTREF(__pyx_t_8); __pyx_t_7 = NULL; __pyx_t_4 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_8))) { __pyx_t_7 = PyMethod_GET_SELF(__pyx_t_8); if (likely(__pyx_t_7)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_8); __Pyx_INCREF(__pyx_t_7); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_8, function); __pyx_t_4 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_7, __pyx_kp_s_utf_8}; __pyx_t_2 = __Pyx_PyObject_FastCall(__pyx_t_8, __pyx_callargs+1-__pyx_t_4, 1+__pyx_t_4); __Pyx_XDECREF(__pyx_t_7); __pyx_t_7 = 0; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 60, __pyx_L5_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; } if (unlikely(PyDict_SetItem(__pyx_t_1, (PyObject*)__pyx_t_2, (PyObject*)__pyx_7genexpr__pyx_v_k))) __PYX_ERR(0, 60, __pyx_L5_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_XDECREF(__pyx_7genexpr__pyx_v_k); __pyx_7genexpr__pyx_v_k = 0; __Pyx_XDECREF(__pyx_7genexpr__pyx_v_v); __pyx_7genexpr__pyx_v_v = 0; goto __pyx_L11_exit_scope; __pyx_L5_error:; __Pyx_XDECREF(__pyx_7genexpr__pyx_v_k); __pyx_7genexpr__pyx_v_k = 0; __Pyx_XDECREF(__pyx_7genexpr__pyx_v_v); __pyx_7genexpr__pyx_v_v = 0; goto __pyx_L1_error; __pyx_L11_exit_scope:; } /* exit inner scope */ __Pyx_GIVEREF(__pyx_t_1); __Pyx_GOTREF(__pyx_v_self->_byte_decoder); __Pyx_DECREF(__pyx_v_self->_byte_decoder); __pyx_v_self->_byte_decoder = ((PyObject*)__pyx_t_1); __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":61 * self._byte_encoder = bytes_to_unicode() * self._byte_decoder = {v.decode("utf-8"): k for k, v in self._byte_encoder.items()} * self._split_pattern = regex.compile(SPLIT_PATTERN) # <<<<<<<<<<<<<< * self._piece_to_id = vocab * self._id_to_piece = {v: k for k, v in vocab.items()} */ __Pyx_GetModuleGlobalName(__pyx_t_3, __pyx_n_s_regex); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 61, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_compile); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 61, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_GetModuleGlobalName(__pyx_t_3, __pyx_n_s_SPLIT_PATTERN); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 61, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_8 = NULL; __pyx_t_4 = 0; #if CYTHON_UNPACK_METHODS if (unlikely(PyMethod_Check(__pyx_t_2))) { __pyx_t_8 = PyMethod_GET_SELF(__pyx_t_2); if (likely(__pyx_t_8)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_2); __Pyx_INCREF(__pyx_t_8); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_2, function); __pyx_t_4 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_8, __pyx_t_3}; __pyx_t_1 = __Pyx_PyObject_FastCall(__pyx_t_2, __pyx_callargs+1-__pyx_t_4, 1+__pyx_t_4); __Pyx_XDECREF(__pyx_t_8); __pyx_t_8 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 61, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } __Pyx_GIVEREF(__pyx_t_1); __Pyx_GOTREF(__pyx_v_self->_split_pattern); __Pyx_DECREF(__pyx_v_self->_split_pattern); __pyx_v_self->_split_pattern = __pyx_t_1; __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":62 * self._byte_decoder = {v.decode("utf-8"): k for k, v in self._byte_encoder.items()} * self._split_pattern = regex.compile(SPLIT_PATTERN) * self._piece_to_id = vocab # <<<<<<<<<<<<<< * self._id_to_piece = {v: k for k, v in vocab.items()} * cdef vector[pair[string, string]] c_merges */ if (!(likely(PyDict_CheckExact(__pyx_v_vocab))||((__pyx_v_vocab) == Py_None) || __Pyx_RaiseUnexpectedTypeError("dict", __pyx_v_vocab))) __PYX_ERR(0, 62, __pyx_L1_error) __pyx_t_1 = __pyx_v_vocab; __Pyx_INCREF(__pyx_t_1); __Pyx_GIVEREF(__pyx_t_1); __Pyx_GOTREF(__pyx_v_self->_piece_to_id); __Pyx_DECREF(__pyx_v_self->_piece_to_id); __pyx_v_self->_piece_to_id = ((PyObject*)__pyx_t_1); __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":63 * self._split_pattern = regex.compile(SPLIT_PATTERN) * self._piece_to_id = vocab * self._id_to_piece = {v: k for k, v in vocab.items()} # <<<<<<<<<<<<<< * cdef vector[pair[string, string]] c_merges * for p1, p2 in merges: */ { /* enter inner scope */ __pyx_t_1 = PyDict_New(); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 63, __pyx_L14_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_vocab, __pyx_n_s_items); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 63, __pyx_L14_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_8 = NULL; __pyx_t_4 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_3))) { __pyx_t_8 = PyMethod_GET_SELF(__pyx_t_3); if (likely(__pyx_t_8)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_3); __Pyx_INCREF(__pyx_t_8); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_3, function); __pyx_t_4 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_8, NULL}; __pyx_t_2 = __Pyx_PyObject_FastCall(__pyx_t_3, __pyx_callargs+1-__pyx_t_4, 0+__pyx_t_4); __Pyx_XDECREF(__pyx_t_8); __pyx_t_8 = 0; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 63, __pyx_L14_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; } if (likely(PyList_CheckExact(__pyx_t_2)) || PyTuple_CheckExact(__pyx_t_2)) { __pyx_t_3 = __pyx_t_2; __Pyx_INCREF(__pyx_t_3); __pyx_t_5 = 0; __pyx_t_6 = NULL; } else { __pyx_t_5 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_t_2); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 63, __pyx_L14_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_6 = __Pyx_PyObject_GetIterNextFunc(__pyx_t_3); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 63, __pyx_L14_error) } __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; for (;;) { if (likely(!__pyx_t_6)) { if (likely(PyList_CheckExact(__pyx_t_3))) { { Py_ssize_t __pyx_temp = __Pyx_PyList_GET_SIZE(__pyx_t_3); #if !CYTHON_ASSUME_SAFE_MACROS if (unlikely((__pyx_temp < 0))) __PYX_ERR(0, 63, __pyx_L14_error) #endif if (__pyx_t_5 >= __pyx_temp) break; } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_2 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_5); __Pyx_INCREF(__pyx_t_2); __pyx_t_5++; if (unlikely((0 < 0))) __PYX_ERR(0, 63, __pyx_L14_error) #else __pyx_t_2 = __Pyx_PySequence_ITEM(__pyx_t_3, __pyx_t_5); __pyx_t_5++; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 63, __pyx_L14_error) __Pyx_GOTREF(__pyx_t_2); #endif } else { { Py_ssize_t __pyx_temp = __Pyx_PyTuple_GET_SIZE(__pyx_t_3); #if !CYTHON_ASSUME_SAFE_MACROS if (unlikely((__pyx_temp < 0))) __PYX_ERR(0, 63, __pyx_L14_error) #endif if (__pyx_t_5 >= __pyx_temp) break; } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_2 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_5); __Pyx_INCREF(__pyx_t_2); __pyx_t_5++; if (unlikely((0 < 0))) __PYX_ERR(0, 63, __pyx_L14_error) #else __pyx_t_2 = __Pyx_PySequence_ITEM(__pyx_t_3, __pyx_t_5); __pyx_t_5++; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 63, __pyx_L14_error) __Pyx_GOTREF(__pyx_t_2); #endif } } else { __pyx_t_2 = __pyx_t_6(__pyx_t_3); if (unlikely(!__pyx_t_2)) { PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); else __PYX_ERR(0, 63, __pyx_L14_error) } break; } __Pyx_GOTREF(__pyx_t_2); } if ((likely(PyTuple_CheckExact(__pyx_t_2))) || (PyList_CheckExact(__pyx_t_2))) { PyObject* sequence = __pyx_t_2; Py_ssize_t size = __Pyx_PySequence_SIZE(sequence); if (unlikely(size != 2)) { if (size > 2) __Pyx_RaiseTooManyValuesError(2); else if (size >= 0) __Pyx_RaiseNeedMoreValuesError(size); __PYX_ERR(0, 63, __pyx_L14_error) } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS if (likely(PyTuple_CheckExact(sequence))) { __pyx_t_8 = PyTuple_GET_ITEM(sequence, 0); __pyx_t_7 = PyTuple_GET_ITEM(sequence, 1); } else { __pyx_t_8 = PyList_GET_ITEM(sequence, 0); __pyx_t_7 = PyList_GET_ITEM(sequence, 1); } __Pyx_INCREF(__pyx_t_8); __Pyx_INCREF(__pyx_t_7); #else __pyx_t_8 = PySequence_ITEM(sequence, 0); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 63, __pyx_L14_error) __Pyx_GOTREF(__pyx_t_8); __pyx_t_7 = PySequence_ITEM(sequence, 1); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 63, __pyx_L14_error) __Pyx_GOTREF(__pyx_t_7); #endif __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } else { Py_ssize_t index = -1; __pyx_t_9 = PyObject_GetIter(__pyx_t_2); if (unlikely(!__pyx_t_9)) __PYX_ERR(0, 63, __pyx_L14_error) __Pyx_GOTREF(__pyx_t_9); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_10 = __Pyx_PyObject_GetIterNextFunc(__pyx_t_9); index = 0; __pyx_t_8 = __pyx_t_10(__pyx_t_9); if (unlikely(!__pyx_t_8)) goto __pyx_L17_unpacking_failed; __Pyx_GOTREF(__pyx_t_8); index = 1; __pyx_t_7 = __pyx_t_10(__pyx_t_9); if (unlikely(!__pyx_t_7)) goto __pyx_L17_unpacking_failed; __Pyx_GOTREF(__pyx_t_7); if (__Pyx_IternextUnpackEndCheck(__pyx_t_10(__pyx_t_9), 2) < 0) __PYX_ERR(0, 63, __pyx_L14_error) __pyx_t_10 = NULL; __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; goto __pyx_L18_unpacking_done; __pyx_L17_unpacking_failed:; __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; __pyx_t_10 = NULL; if (__Pyx_IterFinish() == 0) __Pyx_RaiseNeedMoreValuesError(index); __PYX_ERR(0, 63, __pyx_L14_error) __pyx_L18_unpacking_done:; } __Pyx_XDECREF_SET(__pyx_8genexpr1__pyx_v_k, __pyx_t_8); __pyx_t_8 = 0; __Pyx_XDECREF_SET(__pyx_8genexpr1__pyx_v_v, __pyx_t_7); __pyx_t_7 = 0; if (unlikely(PyDict_SetItem(__pyx_t_1, (PyObject*)__pyx_8genexpr1__pyx_v_v, (PyObject*)__pyx_8genexpr1__pyx_v_k))) __PYX_ERR(0, 63, __pyx_L14_error) } __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_XDECREF(__pyx_8genexpr1__pyx_v_k); __pyx_8genexpr1__pyx_v_k = 0; __Pyx_XDECREF(__pyx_8genexpr1__pyx_v_v); __pyx_8genexpr1__pyx_v_v = 0; goto __pyx_L20_exit_scope; __pyx_L14_error:; __Pyx_XDECREF(__pyx_8genexpr1__pyx_v_k); __pyx_8genexpr1__pyx_v_k = 0; __Pyx_XDECREF(__pyx_8genexpr1__pyx_v_v); __pyx_8genexpr1__pyx_v_v = 0; goto __pyx_L1_error; __pyx_L20_exit_scope:; } /* exit inner scope */ __Pyx_GIVEREF(__pyx_t_1); __Pyx_GOTREF(__pyx_v_self->_id_to_piece); __Pyx_DECREF(__pyx_v_self->_id_to_piece); __pyx_v_self->_id_to_piece = ((PyObject*)__pyx_t_1); __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":65 * self._id_to_piece = {v: k for k, v in vocab.items()} * cdef vector[pair[string, string]] c_merges * for p1, p2 in merges: # <<<<<<<<<<<<<< * c_merges.push_back(pair[string, string](p1.encode('utf-8'), p2.encode('utf-8'))) * self._merges = make_shared[Merges](c_merges) */ if (likely(PyList_CheckExact(__pyx_v_merges)) || PyTuple_CheckExact(__pyx_v_merges)) { __pyx_t_1 = __pyx_v_merges; __Pyx_INCREF(__pyx_t_1); __pyx_t_5 = 0; __pyx_t_6 = NULL; } else { __pyx_t_5 = -1; __pyx_t_1 = PyObject_GetIter(__pyx_v_merges); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 65, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_6 = __Pyx_PyObject_GetIterNextFunc(__pyx_t_1); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 65, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_6)) { if (likely(PyList_CheckExact(__pyx_t_1))) { { Py_ssize_t __pyx_temp = __Pyx_PyList_GET_SIZE(__pyx_t_1); #if !CYTHON_ASSUME_SAFE_MACROS if (unlikely((__pyx_temp < 0))) __PYX_ERR(0, 65, __pyx_L1_error) #endif if (__pyx_t_5 >= __pyx_temp) break; } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_3 = PyList_GET_ITEM(__pyx_t_1, __pyx_t_5); __Pyx_INCREF(__pyx_t_3); __pyx_t_5++; if (unlikely((0 < 0))) __PYX_ERR(0, 65, __pyx_L1_error) #else __pyx_t_3 = __Pyx_PySequence_ITEM(__pyx_t_1, __pyx_t_5); __pyx_t_5++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 65, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); #endif } else { { Py_ssize_t __pyx_temp = __Pyx_PyTuple_GET_SIZE(__pyx_t_1); #if !CYTHON_ASSUME_SAFE_MACROS if (unlikely((__pyx_temp < 0))) __PYX_ERR(0, 65, __pyx_L1_error) #endif if (__pyx_t_5 >= __pyx_temp) break; } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_5); __Pyx_INCREF(__pyx_t_3); __pyx_t_5++; if (unlikely((0 < 0))) __PYX_ERR(0, 65, __pyx_L1_error) #else __pyx_t_3 = __Pyx_PySequence_ITEM(__pyx_t_1, __pyx_t_5); __pyx_t_5++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 65, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); #endif } } else { __pyx_t_3 = __pyx_t_6(__pyx_t_1); if (unlikely(!__pyx_t_3)) { PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); else __PYX_ERR(0, 65, __pyx_L1_error) } break; } __Pyx_GOTREF(__pyx_t_3); } if ((likely(PyTuple_CheckExact(__pyx_t_3))) || (PyList_CheckExact(__pyx_t_3))) { PyObject* sequence = __pyx_t_3; Py_ssize_t size = __Pyx_PySequence_SIZE(sequence); if (unlikely(size != 2)) { if (size > 2) __Pyx_RaiseTooManyValuesError(2); else if (size >= 0) __Pyx_RaiseNeedMoreValuesError(size); __PYX_ERR(0, 65, __pyx_L1_error) } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS if (likely(PyTuple_CheckExact(sequence))) { __pyx_t_2 = PyTuple_GET_ITEM(sequence, 0); __pyx_t_7 = PyTuple_GET_ITEM(sequence, 1); } else { __pyx_t_2 = PyList_GET_ITEM(sequence, 0); __pyx_t_7 = PyList_GET_ITEM(sequence, 1); } __Pyx_INCREF(__pyx_t_2); __Pyx_INCREF(__pyx_t_7); #else __pyx_t_2 = PySequence_ITEM(sequence, 0); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 65, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __pyx_t_7 = PySequence_ITEM(sequence, 1); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 65, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); #endif __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; } else { Py_ssize_t index = -1; __pyx_t_8 = PyObject_GetIter(__pyx_t_3); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 65, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_t_10 = __Pyx_PyObject_GetIterNextFunc(__pyx_t_8); index = 0; __pyx_t_2 = __pyx_t_10(__pyx_t_8); if (unlikely(!__pyx_t_2)) goto __pyx_L23_unpacking_failed; __Pyx_GOTREF(__pyx_t_2); index = 1; __pyx_t_7 = __pyx_t_10(__pyx_t_8); if (unlikely(!__pyx_t_7)) goto __pyx_L23_unpacking_failed; __Pyx_GOTREF(__pyx_t_7); if (__Pyx_IternextUnpackEndCheck(__pyx_t_10(__pyx_t_8), 2) < 0) __PYX_ERR(0, 65, __pyx_L1_error) __pyx_t_10 = NULL; __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; goto __pyx_L24_unpacking_done; __pyx_L23_unpacking_failed:; __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __pyx_t_10 = NULL; if (__Pyx_IterFinish() == 0) __Pyx_RaiseNeedMoreValuesError(index); __PYX_ERR(0, 65, __pyx_L1_error) __pyx_L24_unpacking_done:; } __Pyx_XDECREF_SET(__pyx_v_p1, __pyx_t_2); __pyx_t_2 = 0; __Pyx_XDECREF_SET(__pyx_v_p2, __pyx_t_7); __pyx_t_7 = 0; /* "curated_tokenizers/_bbpe.pyx":66 * cdef vector[pair[string, string]] c_merges * for p1, p2 in merges: * c_merges.push_back(pair[string, string](p1.encode('utf-8'), p2.encode('utf-8'))) # <<<<<<<<<<<<<< * self._merges = make_shared[Merges](c_merges) * */ __pyx_t_7 = __Pyx_PyObject_GetAttrStr(__pyx_v_p1, __pyx_n_s_encode); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 66, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); __pyx_t_2 = NULL; __pyx_t_4 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_7))) { __pyx_t_2 = PyMethod_GET_SELF(__pyx_t_7); if (likely(__pyx_t_2)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_7); __Pyx_INCREF(__pyx_t_2); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_7, function); __pyx_t_4 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_2, __pyx_kp_s_utf_8}; __pyx_t_3 = __Pyx_PyObject_FastCall(__pyx_t_7, __pyx_callargs+1-__pyx_t_4, 1+__pyx_t_4); __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 66, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; } __pyx_t_11 = __pyx_convert_string_from_py_std__in_string(__pyx_t_3); if (unlikely(PyErr_Occurred())) __PYX_ERR(0, 66, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_t_7 = __Pyx_PyObject_GetAttrStr(__pyx_v_p2, __pyx_n_s_encode); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 66, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); __pyx_t_2 = NULL; __pyx_t_4 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_7))) { __pyx_t_2 = PyMethod_GET_SELF(__pyx_t_7); if (likely(__pyx_t_2)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_7); __Pyx_INCREF(__pyx_t_2); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_7, function); __pyx_t_4 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_2, __pyx_kp_s_utf_8}; __pyx_t_3 = __Pyx_PyObject_FastCall(__pyx_t_7, __pyx_callargs+1-__pyx_t_4, 1+__pyx_t_4); __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 66, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; } __pyx_t_12 = __pyx_convert_string_from_py_std__in_string(__pyx_t_3); if (unlikely(PyErr_Occurred())) __PYX_ERR(0, 66, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; try { __pyx_t_13 = std::pair (__pyx_t_11, __pyx_t_12); } catch(...) { __Pyx_CppExn2PyErr(); __PYX_ERR(0, 66, __pyx_L1_error) } try { __pyx_v_c_merges.push_back(__pyx_t_13); } catch(...) { __Pyx_CppExn2PyErr(); __PYX_ERR(0, 66, __pyx_L1_error) } /* "curated_tokenizers/_bbpe.pyx":65 * self._id_to_piece = {v: k for k, v in vocab.items()} * cdef vector[pair[string, string]] c_merges * for p1, p2 in merges: # <<<<<<<<<<<<<< * c_merges.push_back(pair[string, string](p1.encode('utf-8'), p2.encode('utf-8'))) * self._merges = make_shared[Merges](c_merges) */ } __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":67 * for p1, p2 in merges: * c_merges.push_back(pair[string, string](p1.encode('utf-8'), p2.encode('utf-8'))) * self._merges = make_shared[Merges](c_merges) # <<<<<<<<<<<<<< * * def __copy__(self): */ try { __pyx_t_14 = std::make_shared(__pyx_v_c_merges); } catch(...) { __Pyx_CppExn2PyErr(); __PYX_ERR(0, 67, __pyx_L1_error) } __pyx_v_self->_merges = __PYX_STD_MOVE_IF_SUPPORTED(__pyx_t_14); /* "curated_tokenizers/_bbpe.pyx":58 * cdef dict _id_to_piece * * def __init__(self, vocab: Dict[str, int], merges: List[Tuple[str, str]]): # <<<<<<<<<<<<<< * self._byte_encoder = bytes_to_unicode() * self._byte_decoder = {v.decode("utf-8"): k for k, v in self._byte_encoder.items()} */ /* function exit code */ __pyx_r = 0; goto __pyx_L0; __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_XDECREF(__pyx_t_2); __Pyx_XDECREF(__pyx_t_3); __Pyx_XDECREF(__pyx_t_7); __Pyx_XDECREF(__pyx_t_8); __Pyx_XDECREF(__pyx_t_9); __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.__init__", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = -1; __pyx_L0:; __Pyx_XDECREF(__pyx_v_p1); __Pyx_XDECREF(__pyx_v_p2); __Pyx_XDECREF(__pyx_7genexpr__pyx_v_k); __Pyx_XDECREF(__pyx_7genexpr__pyx_v_v); __Pyx_XDECREF(__pyx_8genexpr1__pyx_v_k); __Pyx_XDECREF(__pyx_8genexpr1__pyx_v_v); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "curated_tokenizers/_bbpe.pyx":69 * self._merges = make_shared[Merges](c_merges) * * def __copy__(self): # <<<<<<<<<<<<<< * return ByteBPEProcessor(vocab=self.vocab, merges=self.merges) * */ /* Python wrapper */ static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_3__copy__(PyObject *__pyx_v_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ); /*proto*/ PyDoc_STRVAR(__pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_2__copy__, "ByteBPEProcessor.__copy__(self)"); static PyMethodDef __pyx_mdef_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_3__copy__ = {"__copy__", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_3__copy__, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_2__copy__}; static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_3__copy__(PyObject *__pyx_v_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ) { #if !CYTHON_METH_FASTCALL CYTHON_UNUSED Py_ssize_t __pyx_nargs; #endif CYTHON_UNUSED PyObject *const *__pyx_kwvalues; PyObject *__pyx_r = 0; __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__copy__ (wrapper)", 0); #if !CYTHON_METH_FASTCALL #if CYTHON_ASSUME_SAFE_MACROS __pyx_nargs = PyTuple_GET_SIZE(__pyx_args); #else __pyx_nargs = PyTuple_Size(__pyx_args); if (unlikely(__pyx_nargs < 0)) return NULL; #endif #endif __pyx_kwvalues = __Pyx_KwValues_FASTCALL(__pyx_args, __pyx_nargs); if (unlikely(__pyx_nargs > 0)) { __Pyx_RaiseArgtupleInvalid("__copy__", 1, 0, 0, __pyx_nargs); return NULL;} if (unlikely(__pyx_kwds) && __Pyx_NumKwargs_FASTCALL(__pyx_kwds) && unlikely(!__Pyx_CheckKeywordStrings(__pyx_kwds, "__copy__", 0))) return NULL; __pyx_r = __pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_2__copy__(((struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *)__pyx_v_self)); /* function exit code */ __Pyx_RefNannyFinishContext(); return __pyx_r; } static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_2__copy__(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self) { PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; PyObject *__pyx_t_2 = NULL; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("__copy__", 1); /* "curated_tokenizers/_bbpe.pyx":70 * * def __copy__(self): * return ByteBPEProcessor(vocab=self.vocab, merges=self.merges) # <<<<<<<<<<<<<< * * def __deepcopy__(self, memo): */ __Pyx_XDECREF(__pyx_r); __pyx_t_1 = __Pyx_PyDict_NewPresized(2); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 70, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_2 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_vocab); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 70, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (PyDict_SetItem(__pyx_t_1, __pyx_n_s_vocab, __pyx_t_2) < 0) __PYX_ERR(0, 70, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_merges); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 70, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (PyDict_SetItem(__pyx_t_1, __pyx_n_s_merges, __pyx_t_2) < 0) __PYX_ERR(0, 70, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = __Pyx_PyObject_Call(((PyObject *)__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor), __pyx_empty_tuple, __pyx_t_1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 70, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_r = __pyx_t_2; __pyx_t_2 = 0; goto __pyx_L0; /* "curated_tokenizers/_bbpe.pyx":69 * self._merges = make_shared[Merges](c_merges) * * def __copy__(self): # <<<<<<<<<<<<<< * return ByteBPEProcessor(vocab=self.vocab, merges=self.merges) * */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_XDECREF(__pyx_t_2); __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.__copy__", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = NULL; __pyx_L0:; __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "curated_tokenizers/_bbpe.pyx":72 * return ByteBPEProcessor(vocab=self.vocab, merges=self.merges) * * def __deepcopy__(self, memo): # <<<<<<<<<<<<<< * # We don't need a deepcopy of the vocab and merges dicts as their * # contents will be copied into a backing store in the c'tor. */ /* Python wrapper */ static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_5__deepcopy__(PyObject *__pyx_v_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ); /*proto*/ PyDoc_STRVAR(__pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_4__deepcopy__, "ByteBPEProcessor.__deepcopy__(self, memo)"); static PyMethodDef __pyx_mdef_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_5__deepcopy__ = {"__deepcopy__", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_5__deepcopy__, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_4__deepcopy__}; static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_5__deepcopy__(PyObject *__pyx_v_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ) { CYTHON_UNUSED PyObject *__pyx_v_memo = 0; #if !CYTHON_METH_FASTCALL CYTHON_UNUSED Py_ssize_t __pyx_nargs; #endif CYTHON_UNUSED PyObject *const *__pyx_kwvalues; PyObject* values[1] = {0}; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; PyObject *__pyx_r = 0; __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__deepcopy__ (wrapper)", 0); #if !CYTHON_METH_FASTCALL #if CYTHON_ASSUME_SAFE_MACROS __pyx_nargs = PyTuple_GET_SIZE(__pyx_args); #else __pyx_nargs = PyTuple_Size(__pyx_args); if (unlikely(__pyx_nargs < 0)) return NULL; #endif #endif __pyx_kwvalues = __Pyx_KwValues_FASTCALL(__pyx_args, __pyx_nargs); { PyObject **__pyx_pyargnames[] = {&__pyx_n_s_memo,0}; if (__pyx_kwds) { Py_ssize_t kw_args; switch (__pyx_nargs) { case 1: values[0] = __Pyx_Arg_FASTCALL(__pyx_args, 0); CYTHON_FALLTHROUGH; case 0: break; default: goto __pyx_L5_argtuple_error; } kw_args = __Pyx_NumKwargs_FASTCALL(__pyx_kwds); switch (__pyx_nargs) { case 0: if (likely((values[0] = __Pyx_GetKwValue_FASTCALL(__pyx_kwds, __pyx_kwvalues, __pyx_n_s_memo)) != 0)) { (void)__Pyx_Arg_NewRef_FASTCALL(values[0]); kw_args--; } else if (unlikely(PyErr_Occurred())) __PYX_ERR(0, 72, __pyx_L3_error) else goto __pyx_L5_argtuple_error; } if (unlikely(kw_args > 0)) { const Py_ssize_t kwd_pos_args = __pyx_nargs; if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_kwvalues, __pyx_pyargnames, 0, values + 0, kwd_pos_args, "__deepcopy__") < 0)) __PYX_ERR(0, 72, __pyx_L3_error) } } else if (unlikely(__pyx_nargs != 1)) { goto __pyx_L5_argtuple_error; } else { values[0] = __Pyx_Arg_FASTCALL(__pyx_args, 0); } __pyx_v_memo = values[0]; } goto __pyx_L6_skip; __pyx_L5_argtuple_error:; __Pyx_RaiseArgtupleInvalid("__deepcopy__", 1, 1, 1, __pyx_nargs); __PYX_ERR(0, 72, __pyx_L3_error) __pyx_L6_skip:; goto __pyx_L4_argument_unpacking_done; __pyx_L3_error:; { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < (Py_ssize_t)(sizeof(values)/sizeof(values[0])); ++__pyx_temp) { __Pyx_Arg_XDECREF_FASTCALL(values[__pyx_temp]); } } __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.__deepcopy__", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); return NULL; __pyx_L4_argument_unpacking_done:; __pyx_r = __pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_4__deepcopy__(((struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *)__pyx_v_self), __pyx_v_memo); /* function exit code */ { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < (Py_ssize_t)(sizeof(values)/sizeof(values[0])); ++__pyx_temp) { __Pyx_Arg_XDECREF_FASTCALL(values[__pyx_temp]); } } __Pyx_RefNannyFinishContext(); return __pyx_r; } static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_4__deepcopy__(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self, CYTHON_UNUSED PyObject *__pyx_v_memo) { PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; PyObject *__pyx_t_2 = NULL; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("__deepcopy__", 1); /* "curated_tokenizers/_bbpe.pyx":75 * # We don't need a deepcopy of the vocab and merges dicts as their * # contents will be copied into a backing store in the c'tor. * return ByteBPEProcessor(vocab=self.vocab, merges=self.merges) # <<<<<<<<<<<<<< * * @staticmethod */ __Pyx_XDECREF(__pyx_r); __pyx_t_1 = __Pyx_PyDict_NewPresized(2); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 75, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_2 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_vocab); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 75, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (PyDict_SetItem(__pyx_t_1, __pyx_n_s_vocab, __pyx_t_2) < 0) __PYX_ERR(0, 75, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_merges); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 75, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (PyDict_SetItem(__pyx_t_1, __pyx_n_s_merges, __pyx_t_2) < 0) __PYX_ERR(0, 75, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = __Pyx_PyObject_Call(((PyObject *)__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor), __pyx_empty_tuple, __pyx_t_1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 75, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_r = __pyx_t_2; __pyx_t_2 = 0; goto __pyx_L0; /* "curated_tokenizers/_bbpe.pyx":72 * return ByteBPEProcessor(vocab=self.vocab, merges=self.merges) * * def __deepcopy__(self, memo): # <<<<<<<<<<<<<< * # We don't need a deepcopy of the vocab and merges dicts as their * # contents will be copied into a backing store in the c'tor. */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_XDECREF(__pyx_t_2); __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.__deepcopy__", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = NULL; __pyx_L0:; __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "curated_tokenizers/_bbpe.pyx":77 * return ByteBPEProcessor(vocab=self.vocab, merges=self.merges) * * @staticmethod # <<<<<<<<<<<<<< * def load_from_files(*, vocab: Path, merges: Path) -> ByteBPEProcessor: * """Construct a processor from the given vocabulary and merges files.""" */ /* Python wrapper */ static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_7load_from_files(CYTHON_UNUSED PyObject *__pyx_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ); /*proto*/ PyDoc_STRVAR(__pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_6load_from_files, "ByteBPEProcessor.load_from_files(*, vocab: Path, merges: Path) -> ByteBPEProcessor\nConstruct a processor from the given vocabulary and merges files."); static PyMethodDef __pyx_mdef_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_7load_from_files = {"load_from_files", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_7load_from_files, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_6load_from_files}; static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_7load_from_files(CYTHON_UNUSED PyObject *__pyx_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ) { PyObject *__pyx_v_vocab = 0; PyObject *__pyx_v_merges = 0; #if !CYTHON_METH_FASTCALL CYTHON_UNUSED Py_ssize_t __pyx_nargs; #endif CYTHON_UNUSED PyObject *const *__pyx_kwvalues; PyObject* values[2] = {0,0}; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; PyObject *__pyx_r = 0; __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("load_from_files (wrapper)", 0); #if !CYTHON_METH_FASTCALL #if CYTHON_ASSUME_SAFE_MACROS __pyx_nargs = PyTuple_GET_SIZE(__pyx_args); #else __pyx_nargs = PyTuple_Size(__pyx_args); if (unlikely(__pyx_nargs < 0)) return NULL; #endif #endif __pyx_kwvalues = __Pyx_KwValues_FASTCALL(__pyx_args, __pyx_nargs); { PyObject **__pyx_pyargnames[] = {&__pyx_n_s_vocab,&__pyx_n_s_merges,0}; if (likely(__pyx_kwds)) { Py_ssize_t kw_args; switch (__pyx_nargs) { case 0: break; default: goto __pyx_L5_argtuple_error; } kw_args = __Pyx_NumKwargs_FASTCALL(__pyx_kwds); if (likely((values[0] = __Pyx_GetKwValue_FASTCALL(__pyx_kwds, __pyx_kwvalues, __pyx_n_s_vocab)) != 0)) { (void)__Pyx_Arg_NewRef_FASTCALL(values[0]); kw_args--; } else if (unlikely(PyErr_Occurred())) __PYX_ERR(0, 77, __pyx_L3_error) else { __Pyx_RaiseKeywordRequired("load_from_files", __pyx_n_s_vocab); __PYX_ERR(0, 77, __pyx_L3_error) } if (likely((values[1] = __Pyx_GetKwValue_FASTCALL(__pyx_kwds, __pyx_kwvalues, __pyx_n_s_merges)) != 0)) { (void)__Pyx_Arg_NewRef_FASTCALL(values[1]); kw_args--; } else if (unlikely(PyErr_Occurred())) __PYX_ERR(0, 77, __pyx_L3_error) else { __Pyx_RaiseKeywordRequired("load_from_files", __pyx_n_s_merges); __PYX_ERR(0, 77, __pyx_L3_error) } if (unlikely(kw_args > 0)) { if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_kwvalues, __pyx_pyargnames, 0, values + 0, 0, "load_from_files") < 0)) __PYX_ERR(0, 77, __pyx_L3_error) } } else if (unlikely(__pyx_nargs != 0)) { goto __pyx_L5_argtuple_error; } else { __Pyx_RaiseKeywordRequired("load_from_files", __pyx_n_s_vocab); __PYX_ERR(0, 77, __pyx_L3_error) } __pyx_v_vocab = values[0]; __pyx_v_merges = values[1]; } goto __pyx_L6_skip; __pyx_L5_argtuple_error:; __Pyx_RaiseArgtupleInvalid("load_from_files", 1, 0, 0, __pyx_nargs); __PYX_ERR(0, 77, __pyx_L3_error) __pyx_L6_skip:; goto __pyx_L4_argument_unpacking_done; __pyx_L3_error:; { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < (Py_ssize_t)(sizeof(values)/sizeof(values[0])); ++__pyx_temp) { __Pyx_Arg_XDECREF_FASTCALL(values[__pyx_temp]); } } __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.load_from_files", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); return NULL; __pyx_L4_argument_unpacking_done:; __pyx_r = __pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_6load_from_files(__pyx_v_vocab, __pyx_v_merges); /* function exit code */ { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < (Py_ssize_t)(sizeof(values)/sizeof(values[0])); ++__pyx_temp) { __Pyx_Arg_XDECREF_FASTCALL(values[__pyx_temp]); } } __Pyx_RefNannyFinishContext(); return __pyx_r; } static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_6load_from_files(PyObject *__pyx_v_vocab, PyObject *__pyx_v_merges) { PyObject *__pyx_v_f = NULL; PyObject *__pyx_v_version = NULL; PyObject *__pyx_v_line = NULL; PyObject *__pyx_v_merge = NULL; PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; PyObject *__pyx_t_2 = NULL; PyObject *__pyx_t_3 = NULL; PyObject *__pyx_t_4 = NULL; PyObject *__pyx_t_5 = NULL; int __pyx_t_6; PyObject *__pyx_t_7 = NULL; PyObject *__pyx_t_8 = NULL; PyObject *__pyx_t_9 = NULL; PyObject *__pyx_t_10 = NULL; int __pyx_t_11; int __pyx_t_12; Py_ssize_t __pyx_t_13; PyObject *(*__pyx_t_14)(PyObject *); PyObject *__pyx_t_15 = NULL; Py_ssize_t __pyx_t_16; Py_UCS4 __pyx_t_17; Py_ssize_t __pyx_t_18; int __pyx_t_19; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("load_from_files", 0); __Pyx_INCREF(__pyx_v_vocab); __Pyx_INCREF(__pyx_v_merges); /* "curated_tokenizers/_bbpe.pyx":80 * def load_from_files(*, vocab: Path, merges: Path) -> ByteBPEProcessor: * """Construct a processor from the given vocabulary and merges files.""" * with open(vocab, encoding="utf-8") as f: # <<<<<<<<<<<<<< * vocab = json.load(f) * with open(merges, encoding="utf-8") as f: */ /*with:*/ { __pyx_t_1 = PyTuple_New(1); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 80, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_INCREF(__pyx_v_vocab); __Pyx_GIVEREF(__pyx_v_vocab); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_1, 0, __pyx_v_vocab)) __PYX_ERR(0, 80, __pyx_L1_error); __pyx_t_2 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 80, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (PyDict_SetItem(__pyx_t_2, __pyx_n_s_encoding, __pyx_kp_s_utf_8) < 0) __PYX_ERR(0, 80, __pyx_L1_error) __pyx_t_3 = __Pyx_PyObject_Call(__pyx_builtin_open, __pyx_t_1, __pyx_t_2); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 80, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_4 = __Pyx_PyObject_LookupSpecial(__pyx_t_3, __pyx_n_s_exit); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 80, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __pyx_t_1 = __Pyx_PyObject_LookupSpecial(__pyx_t_3, __pyx_n_s_enter); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 80, __pyx_L3_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_5 = NULL; __pyx_t_6 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_1))) { __pyx_t_5 = PyMethod_GET_SELF(__pyx_t_1); if (likely(__pyx_t_5)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_1); __Pyx_INCREF(__pyx_t_5); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_1, function); __pyx_t_6 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_5, NULL}; __pyx_t_2 = __Pyx_PyObject_FastCall(__pyx_t_1, __pyx_callargs+1-__pyx_t_6, 0+__pyx_t_6); __Pyx_XDECREF(__pyx_t_5); __pyx_t_5 = 0; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 80, __pyx_L3_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; } __pyx_t_1 = __pyx_t_2; __pyx_t_2 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; /*try:*/ { { __Pyx_PyThreadState_declare __Pyx_PyThreadState_assign __Pyx_ExceptionSave(&__pyx_t_7, &__pyx_t_8, &__pyx_t_9); __Pyx_XGOTREF(__pyx_t_7); __Pyx_XGOTREF(__pyx_t_8); __Pyx_XGOTREF(__pyx_t_9); /*try:*/ { __pyx_v_f = __pyx_t_1; __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":81 * """Construct a processor from the given vocabulary and merges files.""" * with open(vocab, encoding="utf-8") as f: * vocab = json.load(f) # <<<<<<<<<<<<<< * with open(merges, encoding="utf-8") as f: * version = f.readline() */ __Pyx_GetModuleGlobalName(__pyx_t_3, __pyx_n_s_json); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 81, __pyx_L7_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_t_3, __pyx_n_s_load); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 81, __pyx_L7_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_t_3 = NULL; __pyx_t_6 = 0; #if CYTHON_UNPACK_METHODS if (unlikely(PyMethod_Check(__pyx_t_2))) { __pyx_t_3 = PyMethod_GET_SELF(__pyx_t_2); if (likely(__pyx_t_3)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_2); __Pyx_INCREF(__pyx_t_3); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_2, function); __pyx_t_6 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_3, __pyx_v_f}; __pyx_t_1 = __Pyx_PyObject_FastCall(__pyx_t_2, __pyx_callargs+1-__pyx_t_6, 1+__pyx_t_6); __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 81, __pyx_L7_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } __Pyx_DECREF_SET(__pyx_v_vocab, __pyx_t_1); __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":80 * def load_from_files(*, vocab: Path, merges: Path) -> ByteBPEProcessor: * """Construct a processor from the given vocabulary and merges files.""" * with open(vocab, encoding="utf-8") as f: # <<<<<<<<<<<<<< * vocab = json.load(f) * with open(merges, encoding="utf-8") as f: */ } __Pyx_XDECREF(__pyx_t_7); __pyx_t_7 = 0; __Pyx_XDECREF(__pyx_t_8); __pyx_t_8 = 0; __Pyx_XDECREF(__pyx_t_9); __pyx_t_9 = 0; goto __pyx_L12_try_end; __pyx_L7_error:; __Pyx_XDECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_XDECREF(__pyx_t_5); __pyx_t_5 = 0; /*except:*/ { __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.load_from_files", __pyx_clineno, __pyx_lineno, __pyx_filename); if (__Pyx_GetException(&__pyx_t_1, &__pyx_t_2, &__pyx_t_3) < 0) __PYX_ERR(0, 80, __pyx_L9_except_error) __Pyx_XGOTREF(__pyx_t_1); __Pyx_XGOTREF(__pyx_t_2); __Pyx_XGOTREF(__pyx_t_3); __pyx_t_5 = PyTuple_Pack(3, __pyx_t_1, __pyx_t_2, __pyx_t_3); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 80, __pyx_L9_except_error) __Pyx_GOTREF(__pyx_t_5); __pyx_t_10 = __Pyx_PyObject_Call(__pyx_t_4, __pyx_t_5, NULL); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 80, __pyx_L9_except_error) __Pyx_GOTREF(__pyx_t_10); __pyx_t_11 = __Pyx_PyObject_IsTrue(__pyx_t_10); __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; if (__pyx_t_11 < 0) __PYX_ERR(0, 80, __pyx_L9_except_error) __pyx_t_12 = (!__pyx_t_11); if (unlikely(__pyx_t_12)) { __Pyx_GIVEREF(__pyx_t_1); __Pyx_GIVEREF(__pyx_t_2); __Pyx_XGIVEREF(__pyx_t_3); __Pyx_ErrRestoreWithState(__pyx_t_1, __pyx_t_2, __pyx_t_3); __pyx_t_1 = 0; __pyx_t_2 = 0; __pyx_t_3 = 0; __PYX_ERR(0, 80, __pyx_L9_except_error) } __Pyx_XDECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; goto __pyx_L8_exception_handled; } __pyx_L9_except_error:; __Pyx_XGIVEREF(__pyx_t_7); __Pyx_XGIVEREF(__pyx_t_8); __Pyx_XGIVEREF(__pyx_t_9); __Pyx_ExceptionReset(__pyx_t_7, __pyx_t_8, __pyx_t_9); goto __pyx_L1_error; __pyx_L8_exception_handled:; __Pyx_XGIVEREF(__pyx_t_7); __Pyx_XGIVEREF(__pyx_t_8); __Pyx_XGIVEREF(__pyx_t_9); __Pyx_ExceptionReset(__pyx_t_7, __pyx_t_8, __pyx_t_9); __pyx_L12_try_end:; } } /*finally:*/ { /*normal exit:*/{ if (__pyx_t_4) { __pyx_t_9 = __Pyx_PyObject_Call(__pyx_t_4, __pyx_tuple_, NULL); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (unlikely(!__pyx_t_9)) __PYX_ERR(0, 80, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_9); __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; } goto __pyx_L6; } __pyx_L6:; } goto __pyx_L16; __pyx_L3_error:; __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; goto __pyx_L1_error; __pyx_L16:; } /* "curated_tokenizers/_bbpe.pyx":82 * with open(vocab, encoding="utf-8") as f: * vocab = json.load(f) * with open(merges, encoding="utf-8") as f: # <<<<<<<<<<<<<< * version = f.readline() * if not version.startswith("#version: 0.2"): */ /*with:*/ { __pyx_t_3 = PyTuple_New(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 82, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_INCREF(__pyx_v_merges); __Pyx_GIVEREF(__pyx_v_merges); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_3, 0, __pyx_v_merges)) __PYX_ERR(0, 82, __pyx_L1_error); __pyx_t_2 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 82, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (PyDict_SetItem(__pyx_t_2, __pyx_n_s_encoding, __pyx_kp_s_utf_8) < 0) __PYX_ERR(0, 82, __pyx_L1_error) __pyx_t_1 = __Pyx_PyObject_Call(__pyx_builtin_open, __pyx_t_3, __pyx_t_2); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 82, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_4 = __Pyx_PyObject_LookupSpecial(__pyx_t_1, __pyx_n_s_exit); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 82, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __pyx_t_3 = __Pyx_PyObject_LookupSpecial(__pyx_t_1, __pyx_n_s_enter); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 82, __pyx_L17_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_5 = NULL; __pyx_t_6 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_3))) { __pyx_t_5 = PyMethod_GET_SELF(__pyx_t_3); if (likely(__pyx_t_5)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_3); __Pyx_INCREF(__pyx_t_5); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_3, function); __pyx_t_6 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_5, NULL}; __pyx_t_2 = __Pyx_PyObject_FastCall(__pyx_t_3, __pyx_callargs+1-__pyx_t_6, 0+__pyx_t_6); __Pyx_XDECREF(__pyx_t_5); __pyx_t_5 = 0; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 82, __pyx_L17_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; } __pyx_t_3 = __pyx_t_2; __pyx_t_2 = 0; __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; /*try:*/ { { __Pyx_PyThreadState_declare __Pyx_PyThreadState_assign __Pyx_ExceptionSave(&__pyx_t_9, &__pyx_t_8, &__pyx_t_7); __Pyx_XGOTREF(__pyx_t_9); __Pyx_XGOTREF(__pyx_t_8); __Pyx_XGOTREF(__pyx_t_7); /*try:*/ { __Pyx_XDECREF_SET(__pyx_v_f, __pyx_t_3); __pyx_t_3 = 0; /* "curated_tokenizers/_bbpe.pyx":83 * vocab = json.load(f) * with open(merges, encoding="utf-8") as f: * version = f.readline() # <<<<<<<<<<<<<< * if not version.startswith("#version: 0.2"): * raise ValueError(f"Only version 0.2 of the merges format is supported, was: {version.strip()}") */ __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_f, __pyx_n_s_readline); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 83, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_2 = NULL; __pyx_t_6 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_1))) { __pyx_t_2 = PyMethod_GET_SELF(__pyx_t_1); if (likely(__pyx_t_2)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_1); __Pyx_INCREF(__pyx_t_2); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_1, function); __pyx_t_6 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_2, NULL}; __pyx_t_3 = __Pyx_PyObject_FastCall(__pyx_t_1, __pyx_callargs+1-__pyx_t_6, 0+__pyx_t_6); __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 83, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; } __pyx_v_version = __pyx_t_3; __pyx_t_3 = 0; /* "curated_tokenizers/_bbpe.pyx":84 * with open(merges, encoding="utf-8") as f: * version = f.readline() * if not version.startswith("#version: 0.2"): # <<<<<<<<<<<<<< * raise ValueError(f"Only version 0.2 of the merges format is supported, was: {version.strip()}") * merges = [] */ __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_version, __pyx_n_s_startswith); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 84, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_2 = NULL; __pyx_t_6 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_1))) { __pyx_t_2 = PyMethod_GET_SELF(__pyx_t_1); if (likely(__pyx_t_2)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_1); __Pyx_INCREF(__pyx_t_2); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_1, function); __pyx_t_6 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_2, __pyx_kp_s_version_0_2}; __pyx_t_3 = __Pyx_PyObject_FastCall(__pyx_t_1, __pyx_callargs+1-__pyx_t_6, 1+__pyx_t_6); __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 84, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; } __pyx_t_12 = __Pyx_PyObject_IsTrue(__pyx_t_3); if (unlikely((__pyx_t_12 < 0))) __PYX_ERR(0, 84, __pyx_L21_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_t_11 = (!__pyx_t_12); if (unlikely(__pyx_t_11)) { /* "curated_tokenizers/_bbpe.pyx":85 * version = f.readline() * if not version.startswith("#version: 0.2"): * raise ValueError(f"Only version 0.2 of the merges format is supported, was: {version.strip()}") # <<<<<<<<<<<<<< * merges = [] * for line in f: */ __pyx_t_1 = __Pyx_PyObject_GetAttrStr(__pyx_v_version, __pyx_n_s_strip); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 85, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_2 = NULL; __pyx_t_6 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_1))) { __pyx_t_2 = PyMethod_GET_SELF(__pyx_t_1); if (likely(__pyx_t_2)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_1); __Pyx_INCREF(__pyx_t_2); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_1, function); __pyx_t_6 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_2, NULL}; __pyx_t_3 = __Pyx_PyObject_FastCall(__pyx_t_1, __pyx_callargs+1-__pyx_t_6, 0+__pyx_t_6); __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 85, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; } __pyx_t_1 = __Pyx_PyObject_FormatSimple(__pyx_t_3, __pyx_empty_unicode); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 85, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_t_3 = __Pyx_PyUnicode_Concat(__pyx_kp_u_Only_version_0_2_of_the_merges_f, __pyx_t_1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 85, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_t_1 = __Pyx_PyObject_CallOneArg(__pyx_builtin_ValueError, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 85, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_Raise(__pyx_t_1, 0, 0, 0); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __PYX_ERR(0, 85, __pyx_L21_error) /* "curated_tokenizers/_bbpe.pyx":84 * with open(merges, encoding="utf-8") as f: * version = f.readline() * if not version.startswith("#version: 0.2"): # <<<<<<<<<<<<<< * raise ValueError(f"Only version 0.2 of the merges format is supported, was: {version.strip()}") * merges = [] */ } /* "curated_tokenizers/_bbpe.pyx":86 * if not version.startswith("#version: 0.2"): * raise ValueError(f"Only version 0.2 of the merges format is supported, was: {version.strip()}") * merges = [] # <<<<<<<<<<<<<< * for line in f: * merge = line.strip().split(" ") */ __pyx_t_1 = PyList_New(0); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 86, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF_SET(__pyx_v_merges, __pyx_t_1); __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":87 * raise ValueError(f"Only version 0.2 of the merges format is supported, was: {version.strip()}") * merges = [] * for line in f: # <<<<<<<<<<<<<< * merge = line.strip().split(" ") * if len(merge) != 2: */ if (likely(PyList_CheckExact(__pyx_v_f)) || PyTuple_CheckExact(__pyx_v_f)) { __pyx_t_1 = __pyx_v_f; __Pyx_INCREF(__pyx_t_1); __pyx_t_13 = 0; __pyx_t_14 = NULL; } else { __pyx_t_13 = -1; __pyx_t_1 = PyObject_GetIter(__pyx_v_f); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 87, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_14 = __Pyx_PyObject_GetIterNextFunc(__pyx_t_1); if (unlikely(!__pyx_t_14)) __PYX_ERR(0, 87, __pyx_L21_error) } for (;;) { if (likely(!__pyx_t_14)) { if (likely(PyList_CheckExact(__pyx_t_1))) { { Py_ssize_t __pyx_temp = __Pyx_PyList_GET_SIZE(__pyx_t_1); #if !CYTHON_ASSUME_SAFE_MACROS if (unlikely((__pyx_temp < 0))) __PYX_ERR(0, 87, __pyx_L21_error) #endif if (__pyx_t_13 >= __pyx_temp) break; } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_3 = PyList_GET_ITEM(__pyx_t_1, __pyx_t_13); __Pyx_INCREF(__pyx_t_3); __pyx_t_13++; if (unlikely((0 < 0))) __PYX_ERR(0, 87, __pyx_L21_error) #else __pyx_t_3 = __Pyx_PySequence_ITEM(__pyx_t_1, __pyx_t_13); __pyx_t_13++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 87, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_3); #endif } else { { Py_ssize_t __pyx_temp = __Pyx_PyTuple_GET_SIZE(__pyx_t_1); #if !CYTHON_ASSUME_SAFE_MACROS if (unlikely((__pyx_temp < 0))) __PYX_ERR(0, 87, __pyx_L21_error) #endif if (__pyx_t_13 >= __pyx_temp) break; } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_3 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_13); __Pyx_INCREF(__pyx_t_3); __pyx_t_13++; if (unlikely((0 < 0))) __PYX_ERR(0, 87, __pyx_L21_error) #else __pyx_t_3 = __Pyx_PySequence_ITEM(__pyx_t_1, __pyx_t_13); __pyx_t_13++; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 87, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_3); #endif } } else { __pyx_t_3 = __pyx_t_14(__pyx_t_1); if (unlikely(!__pyx_t_3)) { PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); else __PYX_ERR(0, 87, __pyx_L21_error) } break; } __Pyx_GOTREF(__pyx_t_3); } __Pyx_XDECREF_SET(__pyx_v_line, __pyx_t_3); __pyx_t_3 = 0; /* "curated_tokenizers/_bbpe.pyx":88 * merges = [] * for line in f: * merge = line.strip().split(" ") # <<<<<<<<<<<<<< * if len(merge) != 2: * raise ValueError(f"Merge must consist of 2 items, was {len(merge)}: {line.strip()}") */ __pyx_t_5 = __Pyx_PyObject_GetAttrStr(__pyx_v_line, __pyx_n_s_strip); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 88, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_5); __pyx_t_15 = NULL; __pyx_t_6 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_5))) { __pyx_t_15 = PyMethod_GET_SELF(__pyx_t_5); if (likely(__pyx_t_15)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_5); __Pyx_INCREF(__pyx_t_15); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_5, function); __pyx_t_6 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_15, NULL}; __pyx_t_2 = __Pyx_PyObject_FastCall(__pyx_t_5, __pyx_callargs+1-__pyx_t_6, 0+__pyx_t_6); __Pyx_XDECREF(__pyx_t_15); __pyx_t_15 = 0; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 88, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; } __pyx_t_5 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_split); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 88, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = NULL; __pyx_t_6 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_5))) { __pyx_t_2 = PyMethod_GET_SELF(__pyx_t_5); if (likely(__pyx_t_2)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_5); __Pyx_INCREF(__pyx_t_2); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_5, function); __pyx_t_6 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_2, __pyx_kp_s__2}; __pyx_t_3 = __Pyx_PyObject_FastCall(__pyx_t_5, __pyx_callargs+1-__pyx_t_6, 1+__pyx_t_6); __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 88, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; } __Pyx_XDECREF_SET(__pyx_v_merge, __pyx_t_3); __pyx_t_3 = 0; /* "curated_tokenizers/_bbpe.pyx":89 * for line in f: * merge = line.strip().split(" ") * if len(merge) != 2: # <<<<<<<<<<<<<< * raise ValueError(f"Merge must consist of 2 items, was {len(merge)}: {line.strip()}") * merges.append(merge) */ __pyx_t_16 = PyObject_Length(__pyx_v_merge); if (unlikely(__pyx_t_16 == ((Py_ssize_t)-1))) __PYX_ERR(0, 89, __pyx_L21_error) __pyx_t_11 = (__pyx_t_16 != 2); if (unlikely(__pyx_t_11)) { /* "curated_tokenizers/_bbpe.pyx":90 * merge = line.strip().split(" ") * if len(merge) != 2: * raise ValueError(f"Merge must consist of 2 items, was {len(merge)}: {line.strip()}") # <<<<<<<<<<<<<< * merges.append(merge) * return ByteBPEProcessor(vocab, merges) */ __pyx_t_3 = PyTuple_New(4); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 90, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_16 = 0; __pyx_t_17 = 127; __Pyx_INCREF(__pyx_kp_u_Merge_must_consist_of_2_items_wa); __pyx_t_16 += 35; __Pyx_GIVEREF(__pyx_kp_u_Merge_must_consist_of_2_items_wa); PyTuple_SET_ITEM(__pyx_t_3, 0, __pyx_kp_u_Merge_must_consist_of_2_items_wa); __pyx_t_18 = PyObject_Length(__pyx_v_merge); if (unlikely(__pyx_t_18 == ((Py_ssize_t)-1))) __PYX_ERR(0, 90, __pyx_L21_error) __pyx_t_5 = __Pyx_PyUnicode_From_Py_ssize_t(__pyx_t_18, 0, ' ', 'd'); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 90, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_5); __pyx_t_16 += __Pyx_PyUnicode_GET_LENGTH(__pyx_t_5); __Pyx_GIVEREF(__pyx_t_5); PyTuple_SET_ITEM(__pyx_t_3, 1, __pyx_t_5); __pyx_t_5 = 0; __Pyx_INCREF(__pyx_kp_u__3); __pyx_t_16 += 2; __Pyx_GIVEREF(__pyx_kp_u__3); PyTuple_SET_ITEM(__pyx_t_3, 2, __pyx_kp_u__3); __pyx_t_2 = __Pyx_PyObject_GetAttrStr(__pyx_v_line, __pyx_n_s_strip); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 90, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_2); __pyx_t_15 = NULL; __pyx_t_6 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_2))) { __pyx_t_15 = PyMethod_GET_SELF(__pyx_t_2); if (likely(__pyx_t_15)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_2); __Pyx_INCREF(__pyx_t_15); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_2, function); __pyx_t_6 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_15, NULL}; __pyx_t_5 = __Pyx_PyObject_FastCall(__pyx_t_2, __pyx_callargs+1-__pyx_t_6, 0+__pyx_t_6); __Pyx_XDECREF(__pyx_t_15); __pyx_t_15 = 0; if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 90, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } __pyx_t_2 = __Pyx_PyObject_FormatSimple(__pyx_t_5, __pyx_empty_unicode); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 90, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; __pyx_t_17 = (__Pyx_PyUnicode_MAX_CHAR_VALUE(__pyx_t_2) > __pyx_t_17) ? __Pyx_PyUnicode_MAX_CHAR_VALUE(__pyx_t_2) : __pyx_t_17; __pyx_t_16 += __Pyx_PyUnicode_GET_LENGTH(__pyx_t_2); __Pyx_GIVEREF(__pyx_t_2); PyTuple_SET_ITEM(__pyx_t_3, 3, __pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = __Pyx_PyUnicode_Join(__pyx_t_3, 4, __pyx_t_16, __pyx_t_17); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 90, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_t_3 = __Pyx_PyObject_CallOneArg(__pyx_builtin_ValueError, __pyx_t_2); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 90, __pyx_L21_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_Raise(__pyx_t_3, 0, 0, 0); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __PYX_ERR(0, 90, __pyx_L21_error) /* "curated_tokenizers/_bbpe.pyx":89 * for line in f: * merge = line.strip().split(" ") * if len(merge) != 2: # <<<<<<<<<<<<<< * raise ValueError(f"Merge must consist of 2 items, was {len(merge)}: {line.strip()}") * merges.append(merge) */ } /* "curated_tokenizers/_bbpe.pyx":91 * if len(merge) != 2: * raise ValueError(f"Merge must consist of 2 items, was {len(merge)}: {line.strip()}") * merges.append(merge) # <<<<<<<<<<<<<< * return ByteBPEProcessor(vocab, merges) * */ __pyx_t_19 = __Pyx_PyObject_Append(__pyx_v_merges, __pyx_v_merge); if (unlikely(__pyx_t_19 == ((int)-1))) __PYX_ERR(0, 91, __pyx_L21_error) /* "curated_tokenizers/_bbpe.pyx":87 * raise ValueError(f"Only version 0.2 of the merges format is supported, was: {version.strip()}") * merges = [] * for line in f: # <<<<<<<<<<<<<< * merge = line.strip().split(" ") * if len(merge) != 2: */ } __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":82 * with open(vocab, encoding="utf-8") as f: * vocab = json.load(f) * with open(merges, encoding="utf-8") as f: # <<<<<<<<<<<<<< * version = f.readline() * if not version.startswith("#version: 0.2"): */ } __Pyx_XDECREF(__pyx_t_9); __pyx_t_9 = 0; __Pyx_XDECREF(__pyx_t_8); __pyx_t_8 = 0; __Pyx_XDECREF(__pyx_t_7); __pyx_t_7 = 0; goto __pyx_L26_try_end; __pyx_L21_error:; __Pyx_XDECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_XDECREF(__pyx_t_15); __pyx_t_15 = 0; __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_XDECREF(__pyx_t_5); __pyx_t_5 = 0; /*except:*/ { __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.load_from_files", __pyx_clineno, __pyx_lineno, __pyx_filename); if (__Pyx_GetException(&__pyx_t_1, &__pyx_t_3, &__pyx_t_2) < 0) __PYX_ERR(0, 82, __pyx_L23_except_error) __Pyx_XGOTREF(__pyx_t_1); __Pyx_XGOTREF(__pyx_t_3); __Pyx_XGOTREF(__pyx_t_2); __pyx_t_5 = PyTuple_Pack(3, __pyx_t_1, __pyx_t_3, __pyx_t_2); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 82, __pyx_L23_except_error) __Pyx_GOTREF(__pyx_t_5); __pyx_t_10 = __Pyx_PyObject_Call(__pyx_t_4, __pyx_t_5, NULL); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 82, __pyx_L23_except_error) __Pyx_GOTREF(__pyx_t_10); __pyx_t_11 = __Pyx_PyObject_IsTrue(__pyx_t_10); __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; if (__pyx_t_11 < 0) __PYX_ERR(0, 82, __pyx_L23_except_error) __pyx_t_12 = (!__pyx_t_11); if (unlikely(__pyx_t_12)) { __Pyx_GIVEREF(__pyx_t_1); __Pyx_GIVEREF(__pyx_t_3); __Pyx_XGIVEREF(__pyx_t_2); __Pyx_ErrRestoreWithState(__pyx_t_1, __pyx_t_3, __pyx_t_2); __pyx_t_1 = 0; __pyx_t_3 = 0; __pyx_t_2 = 0; __PYX_ERR(0, 82, __pyx_L23_except_error) } __Pyx_XDECREF(__pyx_t_1); __pyx_t_1 = 0; __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; goto __pyx_L22_exception_handled; } __pyx_L23_except_error:; __Pyx_XGIVEREF(__pyx_t_9); __Pyx_XGIVEREF(__pyx_t_8); __Pyx_XGIVEREF(__pyx_t_7); __Pyx_ExceptionReset(__pyx_t_9, __pyx_t_8, __pyx_t_7); goto __pyx_L1_error; __pyx_L22_exception_handled:; __Pyx_XGIVEREF(__pyx_t_9); __Pyx_XGIVEREF(__pyx_t_8); __Pyx_XGIVEREF(__pyx_t_7); __Pyx_ExceptionReset(__pyx_t_9, __pyx_t_8, __pyx_t_7); __pyx_L26_try_end:; } } /*finally:*/ { /*normal exit:*/{ if (__pyx_t_4) { __pyx_t_7 = __Pyx_PyObject_Call(__pyx_t_4, __pyx_tuple_, NULL); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 82, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; } goto __pyx_L20; } __pyx_L20:; } goto __pyx_L35; __pyx_L17_error:; __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; goto __pyx_L1_error; __pyx_L35:; } /* "curated_tokenizers/_bbpe.pyx":92 * raise ValueError(f"Merge must consist of 2 items, was {len(merge)}: {line.strip()}") * merges.append(merge) * return ByteBPEProcessor(vocab, merges) # <<<<<<<<<<<<<< * * def decode_from_ids(self, ids: Iterable[int]) -> str: */ __Pyx_XDECREF(__pyx_r); __pyx_t_2 = PyTuple_New(2); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 92, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_INCREF(__pyx_v_vocab); __Pyx_GIVEREF(__pyx_v_vocab); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_2, 0, __pyx_v_vocab)) __PYX_ERR(0, 92, __pyx_L1_error); __Pyx_INCREF(__pyx_v_merges); __Pyx_GIVEREF(__pyx_v_merges); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_2, 1, __pyx_v_merges)) __PYX_ERR(0, 92, __pyx_L1_error); __pyx_t_3 = __Pyx_PyObject_Call(((PyObject *)__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor), __pyx_t_2, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 92, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_r = __pyx_t_3; __pyx_t_3 = 0; goto __pyx_L0; /* "curated_tokenizers/_bbpe.pyx":77 * return ByteBPEProcessor(vocab=self.vocab, merges=self.merges) * * @staticmethod # <<<<<<<<<<<<<< * def load_from_files(*, vocab: Path, merges: Path) -> ByteBPEProcessor: * """Construct a processor from the given vocabulary and merges files.""" */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_XDECREF(__pyx_t_2); __Pyx_XDECREF(__pyx_t_3); __Pyx_XDECREF(__pyx_t_5); __Pyx_XDECREF(__pyx_t_15); __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.load_from_files", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = NULL; __pyx_L0:; __Pyx_XDECREF(__pyx_v_f); __Pyx_XDECREF(__pyx_v_version); __Pyx_XDECREF(__pyx_v_line); __Pyx_XDECREF(__pyx_v_merge); __Pyx_XDECREF(__pyx_v_vocab); __Pyx_XDECREF(__pyx_v_merges); __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "curated_tokenizers/_bbpe.pyx":94 * return ByteBPEProcessor(vocab, merges) * * def decode_from_ids(self, ids: Iterable[int]) -> str: # <<<<<<<<<<<<<< * """ * Decode piece identifiers into string. */ /* Python wrapper */ static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_9decode_from_ids(PyObject *__pyx_v_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ); /*proto*/ PyDoc_STRVAR(__pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_8decode_from_ids, "ByteBPEProcessor.decode_from_ids(self, ids: Iterable[int]) -> str\n\n Decode piece identifiers into string.\n\n ids (Iterable[int]): piece identifiers.\n RETURNS (str): decoded string.\n "); static PyMethodDef __pyx_mdef_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_9decode_from_ids = {"decode_from_ids", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_9decode_from_ids, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_8decode_from_ids}; static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_9decode_from_ids(PyObject *__pyx_v_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ) { PyObject *__pyx_v_ids = 0; #if !CYTHON_METH_FASTCALL CYTHON_UNUSED Py_ssize_t __pyx_nargs; #endif CYTHON_UNUSED PyObject *const *__pyx_kwvalues; PyObject* values[1] = {0}; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; PyObject *__pyx_r = 0; __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("decode_from_ids (wrapper)", 0); #if !CYTHON_METH_FASTCALL #if CYTHON_ASSUME_SAFE_MACROS __pyx_nargs = PyTuple_GET_SIZE(__pyx_args); #else __pyx_nargs = PyTuple_Size(__pyx_args); if (unlikely(__pyx_nargs < 0)) return NULL; #endif #endif __pyx_kwvalues = __Pyx_KwValues_FASTCALL(__pyx_args, __pyx_nargs); { PyObject **__pyx_pyargnames[] = {&__pyx_n_s_ids,0}; if (__pyx_kwds) { Py_ssize_t kw_args; switch (__pyx_nargs) { case 1: values[0] = __Pyx_Arg_FASTCALL(__pyx_args, 0); CYTHON_FALLTHROUGH; case 0: break; default: goto __pyx_L5_argtuple_error; } kw_args = __Pyx_NumKwargs_FASTCALL(__pyx_kwds); switch (__pyx_nargs) { case 0: if (likely((values[0] = __Pyx_GetKwValue_FASTCALL(__pyx_kwds, __pyx_kwvalues, __pyx_n_s_ids)) != 0)) { (void)__Pyx_Arg_NewRef_FASTCALL(values[0]); kw_args--; } else if (unlikely(PyErr_Occurred())) __PYX_ERR(0, 94, __pyx_L3_error) else goto __pyx_L5_argtuple_error; } if (unlikely(kw_args > 0)) { const Py_ssize_t kwd_pos_args = __pyx_nargs; if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_kwvalues, __pyx_pyargnames, 0, values + 0, kwd_pos_args, "decode_from_ids") < 0)) __PYX_ERR(0, 94, __pyx_L3_error) } } else if (unlikely(__pyx_nargs != 1)) { goto __pyx_L5_argtuple_error; } else { values[0] = __Pyx_Arg_FASTCALL(__pyx_args, 0); } __pyx_v_ids = values[0]; } goto __pyx_L6_skip; __pyx_L5_argtuple_error:; __Pyx_RaiseArgtupleInvalid("decode_from_ids", 1, 1, 1, __pyx_nargs); __PYX_ERR(0, 94, __pyx_L3_error) __pyx_L6_skip:; goto __pyx_L4_argument_unpacking_done; __pyx_L3_error:; { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < (Py_ssize_t)(sizeof(values)/sizeof(values[0])); ++__pyx_temp) { __Pyx_Arg_XDECREF_FASTCALL(values[__pyx_temp]); } } __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.decode_from_ids", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); return NULL; __pyx_L4_argument_unpacking_done:; __pyx_r = __pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_8decode_from_ids(((struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *)__pyx_v_self), __pyx_v_ids); /* function exit code */ { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < (Py_ssize_t)(sizeof(values)/sizeof(values[0])); ++__pyx_temp) { __Pyx_Arg_XDECREF_FASTCALL(values[__pyx_temp]); } } __Pyx_RefNannyFinishContext(); return __pyx_r; } static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_8decode_from_ids(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self, PyObject *__pyx_v_ids) { PyObject *__pyx_v_decoded = NULL; PyObject *__pyx_v_piece_id = NULL; PyObject *__pyx_v_piece = NULL; PyObject *__pyx_v_cp = NULL; PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; PyObject *__pyx_t_2 = NULL; PyObject *__pyx_t_3 = NULL; int __pyx_t_4; Py_ssize_t __pyx_t_5; PyObject *(*__pyx_t_6)(PyObject *); int __pyx_t_7; PyObject *__pyx_t_8 = NULL; PyObject *__pyx_t_9 = NULL; PyObject *__pyx_t_10 = NULL; Py_ssize_t __pyx_t_11; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("decode_from_ids", 1); /* "curated_tokenizers/_bbpe.pyx":101 * RETURNS (str): decoded string. * """ * decoded = BytesIO() # <<<<<<<<<<<<<< * for piece_id in ids: * piece = self._id_to_piece.get(piece_id, None) */ __Pyx_GetModuleGlobalName(__pyx_t_2, __pyx_n_s_BytesIO); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 101, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __pyx_t_3 = NULL; __pyx_t_4 = 0; #if CYTHON_UNPACK_METHODS if (unlikely(PyMethod_Check(__pyx_t_2))) { __pyx_t_3 = PyMethod_GET_SELF(__pyx_t_2); if (likely(__pyx_t_3)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_2); __Pyx_INCREF(__pyx_t_3); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_2, function); __pyx_t_4 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_3, NULL}; __pyx_t_1 = __Pyx_PyObject_FastCall(__pyx_t_2, __pyx_callargs+1-__pyx_t_4, 0+__pyx_t_4); __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 101, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } __pyx_v_decoded = __pyx_t_1; __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":102 * """ * decoded = BytesIO() * for piece_id in ids: # <<<<<<<<<<<<<< * piece = self._id_to_piece.get(piece_id, None) * if piece is None: */ if (likely(PyList_CheckExact(__pyx_v_ids)) || PyTuple_CheckExact(__pyx_v_ids)) { __pyx_t_1 = __pyx_v_ids; __Pyx_INCREF(__pyx_t_1); __pyx_t_5 = 0; __pyx_t_6 = NULL; } else { __pyx_t_5 = -1; __pyx_t_1 = PyObject_GetIter(__pyx_v_ids); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 102, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_6 = __Pyx_PyObject_GetIterNextFunc(__pyx_t_1); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 102, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_6)) { if (likely(PyList_CheckExact(__pyx_t_1))) { { Py_ssize_t __pyx_temp = __Pyx_PyList_GET_SIZE(__pyx_t_1); #if !CYTHON_ASSUME_SAFE_MACROS if (unlikely((__pyx_temp < 0))) __PYX_ERR(0, 102, __pyx_L1_error) #endif if (__pyx_t_5 >= __pyx_temp) break; } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_2 = PyList_GET_ITEM(__pyx_t_1, __pyx_t_5); __Pyx_INCREF(__pyx_t_2); __pyx_t_5++; if (unlikely((0 < 0))) __PYX_ERR(0, 102, __pyx_L1_error) #else __pyx_t_2 = __Pyx_PySequence_ITEM(__pyx_t_1, __pyx_t_5); __pyx_t_5++; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 102, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); #endif } else { { Py_ssize_t __pyx_temp = __Pyx_PyTuple_GET_SIZE(__pyx_t_1); #if !CYTHON_ASSUME_SAFE_MACROS if (unlikely((__pyx_temp < 0))) __PYX_ERR(0, 102, __pyx_L1_error) #endif if (__pyx_t_5 >= __pyx_temp) break; } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_2 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_5); __Pyx_INCREF(__pyx_t_2); __pyx_t_5++; if (unlikely((0 < 0))) __PYX_ERR(0, 102, __pyx_L1_error) #else __pyx_t_2 = __Pyx_PySequence_ITEM(__pyx_t_1, __pyx_t_5); __pyx_t_5++; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 102, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); #endif } } else { __pyx_t_2 = __pyx_t_6(__pyx_t_1); if (unlikely(!__pyx_t_2)) { PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); else __PYX_ERR(0, 102, __pyx_L1_error) } break; } __Pyx_GOTREF(__pyx_t_2); } __Pyx_XDECREF_SET(__pyx_v_piece_id, __pyx_t_2); __pyx_t_2 = 0; /* "curated_tokenizers/_bbpe.pyx":103 * decoded = BytesIO() * for piece_id in ids: * piece = self._id_to_piece.get(piece_id, None) # <<<<<<<<<<<<<< * if piece is None: * raise ValueError(f"Unknown piece identifier: {piece_id}") */ if (unlikely(__pyx_v_self->_id_to_piece == Py_None)) { PyErr_Format(PyExc_AttributeError, "'NoneType' object has no attribute '%.30s'", "get"); __PYX_ERR(0, 103, __pyx_L1_error) } __pyx_t_2 = __Pyx_PyDict_GetItemDefault(__pyx_v_self->_id_to_piece, __pyx_v_piece_id, Py_None); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 103, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_XDECREF_SET(__pyx_v_piece, __pyx_t_2); __pyx_t_2 = 0; /* "curated_tokenizers/_bbpe.pyx":104 * for piece_id in ids: * piece = self._id_to_piece.get(piece_id, None) * if piece is None: # <<<<<<<<<<<<<< * raise ValueError(f"Unknown piece identifier: {piece_id}") * decoded.write(bytes([self._byte_decoder[cp] for cp in list(piece)])) */ __pyx_t_7 = (__pyx_v_piece == Py_None); if (unlikely(__pyx_t_7)) { /* "curated_tokenizers/_bbpe.pyx":105 * piece = self._id_to_piece.get(piece_id, None) * if piece is None: * raise ValueError(f"Unknown piece identifier: {piece_id}") # <<<<<<<<<<<<<< * decoded.write(bytes([self._byte_decoder[cp] for cp in list(piece)])) * */ __pyx_t_2 = __Pyx_PyObject_FormatSimple(__pyx_v_piece_id, __pyx_empty_unicode); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 105, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __pyx_t_3 = __Pyx_PyUnicode_Concat(__pyx_kp_u_Unknown_piece_identifier, __pyx_t_2); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 105, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = __Pyx_PyObject_CallOneArg(__pyx_builtin_ValueError, __pyx_t_3); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 105, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_Raise(__pyx_t_2, 0, 0, 0); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __PYX_ERR(0, 105, __pyx_L1_error) /* "curated_tokenizers/_bbpe.pyx":104 * for piece_id in ids: * piece = self._id_to_piece.get(piece_id, None) * if piece is None: # <<<<<<<<<<<<<< * raise ValueError(f"Unknown piece identifier: {piece_id}") * decoded.write(bytes([self._byte_decoder[cp] for cp in list(piece)])) */ } /* "curated_tokenizers/_bbpe.pyx":106 * if piece is None: * raise ValueError(f"Unknown piece identifier: {piece_id}") * decoded.write(bytes([self._byte_decoder[cp] for cp in list(piece)])) # <<<<<<<<<<<<<< * * return decoded.getvalue().decode("utf-8") */ __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_decoded, __pyx_n_s_write); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 106, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_8 = PyList_New(0); if (unlikely(!__pyx_t_8)) __PYX_ERR(0, 106, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_8); __pyx_t_9 = PySequence_List(__pyx_v_piece); if (unlikely(!__pyx_t_9)) __PYX_ERR(0, 106, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_9); __pyx_t_10 = __pyx_t_9; __Pyx_INCREF(__pyx_t_10); __pyx_t_11 = 0; __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; for (;;) { { Py_ssize_t __pyx_temp = __Pyx_PyList_GET_SIZE(__pyx_t_10); #if !CYTHON_ASSUME_SAFE_MACROS if (unlikely((__pyx_temp < 0))) __PYX_ERR(0, 106, __pyx_L1_error) #endif if (__pyx_t_11 >= __pyx_temp) break; } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_9 = PyList_GET_ITEM(__pyx_t_10, __pyx_t_11); __Pyx_INCREF(__pyx_t_9); __pyx_t_11++; if (unlikely((0 < 0))) __PYX_ERR(0, 106, __pyx_L1_error) #else __pyx_t_9 = __Pyx_PySequence_ITEM(__pyx_t_10, __pyx_t_11); __pyx_t_11++; if (unlikely(!__pyx_t_9)) __PYX_ERR(0, 106, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_9); #endif __Pyx_XDECREF_SET(__pyx_v_cp, __pyx_t_9); __pyx_t_9 = 0; if (unlikely(__pyx_v_self->_byte_decoder == Py_None)) { PyErr_SetString(PyExc_TypeError, "'NoneType' object is not subscriptable"); __PYX_ERR(0, 106, __pyx_L1_error) } __pyx_t_9 = __Pyx_PyDict_GetItem(__pyx_v_self->_byte_decoder, __pyx_v_cp); if (unlikely(!__pyx_t_9)) __PYX_ERR(0, 106, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_9); if (unlikely(__Pyx_ListComp_Append(__pyx_t_8, (PyObject*)__pyx_t_9))) __PYX_ERR(0, 106, __pyx_L1_error) __Pyx_DECREF(__pyx_t_9); __pyx_t_9 = 0; } __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; __pyx_t_10 = __Pyx_PyObject_CallOneArg(((PyObject *)(&PyBytes_Type)), __pyx_t_8); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 106, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_10); __Pyx_DECREF(__pyx_t_8); __pyx_t_8 = 0; __pyx_t_8 = NULL; __pyx_t_4 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_3))) { __pyx_t_8 = PyMethod_GET_SELF(__pyx_t_3); if (likely(__pyx_t_8)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_3); __Pyx_INCREF(__pyx_t_8); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_3, function); __pyx_t_4 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_8, __pyx_t_10}; __pyx_t_2 = __Pyx_PyObject_FastCall(__pyx_t_3, __pyx_callargs+1-__pyx_t_4, 1+__pyx_t_4); __Pyx_XDECREF(__pyx_t_8); __pyx_t_8 = 0; __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 106, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; } __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; /* "curated_tokenizers/_bbpe.pyx":102 * """ * decoded = BytesIO() * for piece_id in ids: # <<<<<<<<<<<<<< * piece = self._id_to_piece.get(piece_id, None) * if piece is None: */ } __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":108 * decoded.write(bytes([self._byte_decoder[cp] for cp in list(piece)])) * * return decoded.getvalue().decode("utf-8") # <<<<<<<<<<<<<< * * def encode(self, text: str) -> Tuple[List[int], List[str]]: */ __Pyx_XDECREF(__pyx_r); __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_v_decoded, __pyx_n_s_getvalue); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 108, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_10 = NULL; __pyx_t_4 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_3))) { __pyx_t_10 = PyMethod_GET_SELF(__pyx_t_3); if (likely(__pyx_t_10)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_3); __Pyx_INCREF(__pyx_t_10); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_3, function); __pyx_t_4 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_10, NULL}; __pyx_t_2 = __Pyx_PyObject_FastCall(__pyx_t_3, __pyx_callargs+1-__pyx_t_4, 0+__pyx_t_4); __Pyx_XDECREF(__pyx_t_10); __pyx_t_10 = 0; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 108, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; } __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_decode); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 108, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = NULL; __pyx_t_4 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_3))) { __pyx_t_2 = PyMethod_GET_SELF(__pyx_t_3); if (likely(__pyx_t_2)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_3); __Pyx_INCREF(__pyx_t_2); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_3, function); __pyx_t_4 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_2, __pyx_kp_s_utf_8}; __pyx_t_1 = __Pyx_PyObject_FastCall(__pyx_t_3, __pyx_callargs+1-__pyx_t_4, 1+__pyx_t_4); __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 108, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; } __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; /* "curated_tokenizers/_bbpe.pyx":94 * return ByteBPEProcessor(vocab, merges) * * def decode_from_ids(self, ids: Iterable[int]) -> str: # <<<<<<<<<<<<<< * """ * Decode piece identifiers into string. */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_XDECREF(__pyx_t_2); __Pyx_XDECREF(__pyx_t_3); __Pyx_XDECREF(__pyx_t_8); __Pyx_XDECREF(__pyx_t_9); __Pyx_XDECREF(__pyx_t_10); __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.decode_from_ids", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = NULL; __pyx_L0:; __Pyx_XDECREF(__pyx_v_decoded); __Pyx_XDECREF(__pyx_v_piece_id); __Pyx_XDECREF(__pyx_v_piece); __Pyx_XDECREF(__pyx_v_cp); __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "curated_tokenizers/_bbpe.pyx":110 * return decoded.getvalue().decode("utf-8") * * def encode(self, text: str) -> Tuple[List[int], List[str]]: # <<<<<<<<<<<<<< * """ * Split a text into pieces. */ /* Python wrapper */ static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_11encode(PyObject *__pyx_v_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ); /*proto*/ PyDoc_STRVAR(__pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_10encode, "ByteBPEProcessor.encode(self, text: str) -> Tuple[List[int], List[str]]\n\n Split a text into pieces.\n\n text: The text to split.\n RETURNS: A pair of pieces and piece identifiers.\n "); static PyMethodDef __pyx_mdef_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_11encode = {"encode", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_11encode, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_10encode}; static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_11encode(PyObject *__pyx_v_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ) { PyObject *__pyx_v_text = 0; #if !CYTHON_METH_FASTCALL CYTHON_UNUSED Py_ssize_t __pyx_nargs; #endif CYTHON_UNUSED PyObject *const *__pyx_kwvalues; PyObject* values[1] = {0}; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; PyObject *__pyx_r = 0; __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("encode (wrapper)", 0); #if !CYTHON_METH_FASTCALL #if CYTHON_ASSUME_SAFE_MACROS __pyx_nargs = PyTuple_GET_SIZE(__pyx_args); #else __pyx_nargs = PyTuple_Size(__pyx_args); if (unlikely(__pyx_nargs < 0)) return NULL; #endif #endif __pyx_kwvalues = __Pyx_KwValues_FASTCALL(__pyx_args, __pyx_nargs); { PyObject **__pyx_pyargnames[] = {&__pyx_n_s_text,0}; if (__pyx_kwds) { Py_ssize_t kw_args; switch (__pyx_nargs) { case 1: values[0] = __Pyx_Arg_FASTCALL(__pyx_args, 0); CYTHON_FALLTHROUGH; case 0: break; default: goto __pyx_L5_argtuple_error; } kw_args = __Pyx_NumKwargs_FASTCALL(__pyx_kwds); switch (__pyx_nargs) { case 0: if (likely((values[0] = __Pyx_GetKwValue_FASTCALL(__pyx_kwds, __pyx_kwvalues, __pyx_n_s_text)) != 0)) { (void)__Pyx_Arg_NewRef_FASTCALL(values[0]); kw_args--; } else if (unlikely(PyErr_Occurred())) __PYX_ERR(0, 110, __pyx_L3_error) else goto __pyx_L5_argtuple_error; } if (unlikely(kw_args > 0)) { const Py_ssize_t kwd_pos_args = __pyx_nargs; if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_kwvalues, __pyx_pyargnames, 0, values + 0, kwd_pos_args, "encode") < 0)) __PYX_ERR(0, 110, __pyx_L3_error) } } else if (unlikely(__pyx_nargs != 1)) { goto __pyx_L5_argtuple_error; } else { values[0] = __Pyx_Arg_FASTCALL(__pyx_args, 0); } __pyx_v_text = values[0]; } goto __pyx_L6_skip; __pyx_L5_argtuple_error:; __Pyx_RaiseArgtupleInvalid("encode", 1, 1, 1, __pyx_nargs); __PYX_ERR(0, 110, __pyx_L3_error) __pyx_L6_skip:; goto __pyx_L4_argument_unpacking_done; __pyx_L3_error:; { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < (Py_ssize_t)(sizeof(values)/sizeof(values[0])); ++__pyx_temp) { __Pyx_Arg_XDECREF_FASTCALL(values[__pyx_temp]); } } __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.encode", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); return NULL; __pyx_L4_argument_unpacking_done:; __pyx_r = __pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_10encode(((struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *)__pyx_v_self), __pyx_v_text); /* function exit code */ { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < (Py_ssize_t)(sizeof(values)/sizeof(values[0])); ++__pyx_temp) { __Pyx_Arg_XDECREF_FASTCALL(values[__pyx_temp]); } } __Pyx_RefNannyFinishContext(); return __pyx_r; } static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_10encode(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self, PyObject *__pyx_v_text) { PyObject *__pyx_v_pieces = NULL; PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; PyObject *__pyx_t_2 = NULL; PyObject *__pyx_t_3 = NULL; int __pyx_t_4; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("encode", 1); /* "curated_tokenizers/_bbpe.pyx":117 * RETURNS: A pair of pieces and piece identifiers. * """ * pieces = self.encode_as_pieces(text) # <<<<<<<<<<<<<< * return self._pieces_to_ids(pieces), pieces * */ __pyx_t_2 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_encode_as_pieces); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 117, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __pyx_t_3 = NULL; __pyx_t_4 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_2))) { __pyx_t_3 = PyMethod_GET_SELF(__pyx_t_2); if (likely(__pyx_t_3)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_2); __Pyx_INCREF(__pyx_t_3); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_2, function); __pyx_t_4 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_3, __pyx_v_text}; __pyx_t_1 = __Pyx_PyObject_FastCall(__pyx_t_2, __pyx_callargs+1-__pyx_t_4, 1+__pyx_t_4); __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 117, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } __pyx_v_pieces = __pyx_t_1; __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":118 * """ * pieces = self.encode_as_pieces(text) * return self._pieces_to_ids(pieces), pieces # <<<<<<<<<<<<<< * * def encode_as_ids(self, text: str) -> List[int]: */ __Pyx_XDECREF(__pyx_r); __pyx_t_2 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_pieces_to_ids); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 118, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __pyx_t_3 = NULL; __pyx_t_4 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_2))) { __pyx_t_3 = PyMethod_GET_SELF(__pyx_t_2); if (likely(__pyx_t_3)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_2); __Pyx_INCREF(__pyx_t_3); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_2, function); __pyx_t_4 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_3, __pyx_v_pieces}; __pyx_t_1 = __Pyx_PyObject_FastCall(__pyx_t_2, __pyx_callargs+1-__pyx_t_4, 1+__pyx_t_4); __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 118, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } __pyx_t_2 = PyTuple_New(2); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 118, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_GIVEREF(__pyx_t_1); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_2, 0, __pyx_t_1)) __PYX_ERR(0, 118, __pyx_L1_error); __Pyx_INCREF(__pyx_v_pieces); __Pyx_GIVEREF(__pyx_v_pieces); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_2, 1, __pyx_v_pieces)) __PYX_ERR(0, 118, __pyx_L1_error); __pyx_t_1 = 0; __pyx_r = __pyx_t_2; __pyx_t_2 = 0; goto __pyx_L0; /* "curated_tokenizers/_bbpe.pyx":110 * return decoded.getvalue().decode("utf-8") * * def encode(self, text: str) -> Tuple[List[int], List[str]]: # <<<<<<<<<<<<<< * """ * Split a text into pieces. */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_XDECREF(__pyx_t_2); __Pyx_XDECREF(__pyx_t_3); __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.encode", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = NULL; __pyx_L0:; __Pyx_XDECREF(__pyx_v_pieces); __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "curated_tokenizers/_bbpe.pyx":120 * return self._pieces_to_ids(pieces), pieces * * def encode_as_ids(self, text: str) -> List[int]: # <<<<<<<<<<<<<< * """ * Split a text into pieces, returning piece identifiers. */ /* Python wrapper */ static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_13encode_as_ids(PyObject *__pyx_v_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ); /*proto*/ PyDoc_STRVAR(__pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_12encode_as_ids, "ByteBPEProcessor.encode_as_ids(self, text: str) -> List[int]\n\n Split a text into pieces, returning piece identifiers.\n\n text: The text to split.\n RETURNS: Piece identifiers.\n "); static PyMethodDef __pyx_mdef_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_13encode_as_ids = {"encode_as_ids", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_13encode_as_ids, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_12encode_as_ids}; static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_13encode_as_ids(PyObject *__pyx_v_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ) { PyObject *__pyx_v_text = 0; #if !CYTHON_METH_FASTCALL CYTHON_UNUSED Py_ssize_t __pyx_nargs; #endif CYTHON_UNUSED PyObject *const *__pyx_kwvalues; PyObject* values[1] = {0}; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; PyObject *__pyx_r = 0; __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("encode_as_ids (wrapper)", 0); #if !CYTHON_METH_FASTCALL #if CYTHON_ASSUME_SAFE_MACROS __pyx_nargs = PyTuple_GET_SIZE(__pyx_args); #else __pyx_nargs = PyTuple_Size(__pyx_args); if (unlikely(__pyx_nargs < 0)) return NULL; #endif #endif __pyx_kwvalues = __Pyx_KwValues_FASTCALL(__pyx_args, __pyx_nargs); { PyObject **__pyx_pyargnames[] = {&__pyx_n_s_text,0}; if (__pyx_kwds) { Py_ssize_t kw_args; switch (__pyx_nargs) { case 1: values[0] = __Pyx_Arg_FASTCALL(__pyx_args, 0); CYTHON_FALLTHROUGH; case 0: break; default: goto __pyx_L5_argtuple_error; } kw_args = __Pyx_NumKwargs_FASTCALL(__pyx_kwds); switch (__pyx_nargs) { case 0: if (likely((values[0] = __Pyx_GetKwValue_FASTCALL(__pyx_kwds, __pyx_kwvalues, __pyx_n_s_text)) != 0)) { (void)__Pyx_Arg_NewRef_FASTCALL(values[0]); kw_args--; } else if (unlikely(PyErr_Occurred())) __PYX_ERR(0, 120, __pyx_L3_error) else goto __pyx_L5_argtuple_error; } if (unlikely(kw_args > 0)) { const Py_ssize_t kwd_pos_args = __pyx_nargs; if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_kwvalues, __pyx_pyargnames, 0, values + 0, kwd_pos_args, "encode_as_ids") < 0)) __PYX_ERR(0, 120, __pyx_L3_error) } } else if (unlikely(__pyx_nargs != 1)) { goto __pyx_L5_argtuple_error; } else { values[0] = __Pyx_Arg_FASTCALL(__pyx_args, 0); } __pyx_v_text = values[0]; } goto __pyx_L6_skip; __pyx_L5_argtuple_error:; __Pyx_RaiseArgtupleInvalid("encode_as_ids", 1, 1, 1, __pyx_nargs); __PYX_ERR(0, 120, __pyx_L3_error) __pyx_L6_skip:; goto __pyx_L4_argument_unpacking_done; __pyx_L3_error:; { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < (Py_ssize_t)(sizeof(values)/sizeof(values[0])); ++__pyx_temp) { __Pyx_Arg_XDECREF_FASTCALL(values[__pyx_temp]); } } __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.encode_as_ids", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); return NULL; __pyx_L4_argument_unpacking_done:; __pyx_r = __pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_12encode_as_ids(((struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *)__pyx_v_self), __pyx_v_text); /* function exit code */ { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < (Py_ssize_t)(sizeof(values)/sizeof(values[0])); ++__pyx_temp) { __Pyx_Arg_XDECREF_FASTCALL(values[__pyx_temp]); } } __Pyx_RefNannyFinishContext(); return __pyx_r; } static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_12encode_as_ids(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self, PyObject *__pyx_v_text) { PyObject *__pyx_v_pieces = NULL; PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; PyObject *__pyx_t_2 = NULL; PyObject *__pyx_t_3 = NULL; int __pyx_t_4; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("encode_as_ids", 1); /* "curated_tokenizers/_bbpe.pyx":127 * RETURNS: Piece identifiers. * """ * pieces = self.encode_as_pieces(text) # <<<<<<<<<<<<<< * return self._pieces_to_ids(pieces) * */ __pyx_t_2 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_encode_as_pieces); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 127, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __pyx_t_3 = NULL; __pyx_t_4 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_2))) { __pyx_t_3 = PyMethod_GET_SELF(__pyx_t_2); if (likely(__pyx_t_3)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_2); __Pyx_INCREF(__pyx_t_3); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_2, function); __pyx_t_4 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_3, __pyx_v_text}; __pyx_t_1 = __Pyx_PyObject_FastCall(__pyx_t_2, __pyx_callargs+1-__pyx_t_4, 1+__pyx_t_4); __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 127, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } __pyx_v_pieces = __pyx_t_1; __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":128 * """ * pieces = self.encode_as_pieces(text) * return self._pieces_to_ids(pieces) # <<<<<<<<<<<<<< * * def encode_as_pieces(self, text: str) -> List[str]: */ __Pyx_XDECREF(__pyx_r); __pyx_t_2 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_pieces_to_ids); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 128, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __pyx_t_3 = NULL; __pyx_t_4 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_2))) { __pyx_t_3 = PyMethod_GET_SELF(__pyx_t_2); if (likely(__pyx_t_3)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_2); __Pyx_INCREF(__pyx_t_3); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_2, function); __pyx_t_4 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_3, __pyx_v_pieces}; __pyx_t_1 = __Pyx_PyObject_FastCall(__pyx_t_2, __pyx_callargs+1-__pyx_t_4, 1+__pyx_t_4); __Pyx_XDECREF(__pyx_t_3); __pyx_t_3 = 0; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 128, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; /* "curated_tokenizers/_bbpe.pyx":120 * return self._pieces_to_ids(pieces), pieces * * def encode_as_ids(self, text: str) -> List[int]: # <<<<<<<<<<<<<< * """ * Split a text into pieces, returning piece identifiers. */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_XDECREF(__pyx_t_2); __Pyx_XDECREF(__pyx_t_3); __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.encode_as_ids", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = NULL; __pyx_L0:; __Pyx_XDECREF(__pyx_v_pieces); __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "curated_tokenizers/_bbpe.pyx":130 * return self._pieces_to_ids(pieces) * * def encode_as_pieces(self, text: str) -> List[str]: # <<<<<<<<<<<<<< * """ * Split a text into pieces, returning piece pieces. */ /* Python wrapper */ static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_15encode_as_pieces(PyObject *__pyx_v_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ); /*proto*/ PyDoc_STRVAR(__pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_14encode_as_pieces, "ByteBPEProcessor.encode_as_pieces(self, text: str) -> List[str]\n\n Split a text into pieces, returning piece pieces.\n\n text: The text to split.\n RETURNS: Piece pieces.\n "); static PyMethodDef __pyx_mdef_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_15encode_as_pieces = {"encode_as_pieces", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_15encode_as_pieces, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_14encode_as_pieces}; static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_15encode_as_pieces(PyObject *__pyx_v_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ) { PyObject *__pyx_v_text = 0; #if !CYTHON_METH_FASTCALL CYTHON_UNUSED Py_ssize_t __pyx_nargs; #endif CYTHON_UNUSED PyObject *const *__pyx_kwvalues; PyObject* values[1] = {0}; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; PyObject *__pyx_r = 0; __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("encode_as_pieces (wrapper)", 0); #if !CYTHON_METH_FASTCALL #if CYTHON_ASSUME_SAFE_MACROS __pyx_nargs = PyTuple_GET_SIZE(__pyx_args); #else __pyx_nargs = PyTuple_Size(__pyx_args); if (unlikely(__pyx_nargs < 0)) return NULL; #endif #endif __pyx_kwvalues = __Pyx_KwValues_FASTCALL(__pyx_args, __pyx_nargs); { PyObject **__pyx_pyargnames[] = {&__pyx_n_s_text,0}; if (__pyx_kwds) { Py_ssize_t kw_args; switch (__pyx_nargs) { case 1: values[0] = __Pyx_Arg_FASTCALL(__pyx_args, 0); CYTHON_FALLTHROUGH; case 0: break; default: goto __pyx_L5_argtuple_error; } kw_args = __Pyx_NumKwargs_FASTCALL(__pyx_kwds); switch (__pyx_nargs) { case 0: if (likely((values[0] = __Pyx_GetKwValue_FASTCALL(__pyx_kwds, __pyx_kwvalues, __pyx_n_s_text)) != 0)) { (void)__Pyx_Arg_NewRef_FASTCALL(values[0]); kw_args--; } else if (unlikely(PyErr_Occurred())) __PYX_ERR(0, 130, __pyx_L3_error) else goto __pyx_L5_argtuple_error; } if (unlikely(kw_args > 0)) { const Py_ssize_t kwd_pos_args = __pyx_nargs; if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_kwvalues, __pyx_pyargnames, 0, values + 0, kwd_pos_args, "encode_as_pieces") < 0)) __PYX_ERR(0, 130, __pyx_L3_error) } } else if (unlikely(__pyx_nargs != 1)) { goto __pyx_L5_argtuple_error; } else { values[0] = __Pyx_Arg_FASTCALL(__pyx_args, 0); } __pyx_v_text = values[0]; } goto __pyx_L6_skip; __pyx_L5_argtuple_error:; __Pyx_RaiseArgtupleInvalid("encode_as_pieces", 1, 1, 1, __pyx_nargs); __PYX_ERR(0, 130, __pyx_L3_error) __pyx_L6_skip:; goto __pyx_L4_argument_unpacking_done; __pyx_L3_error:; { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < (Py_ssize_t)(sizeof(values)/sizeof(values[0])); ++__pyx_temp) { __Pyx_Arg_XDECREF_FASTCALL(values[__pyx_temp]); } } __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.encode_as_pieces", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); return NULL; __pyx_L4_argument_unpacking_done:; __pyx_r = __pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_14encode_as_pieces(((struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *)__pyx_v_self), __pyx_v_text); /* function exit code */ { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < (Py_ssize_t)(sizeof(values)/sizeof(values[0])); ++__pyx_temp) { __Pyx_Arg_XDECREF_FASTCALL(values[__pyx_temp]); } } __Pyx_RefNannyFinishContext(); return __pyx_r; } static PyObject *__pyx_gb_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_16encode_as_pieces_2generator(__pyx_CoroutineObject *__pyx_generator, CYTHON_UNUSED PyThreadState *__pyx_tstate, PyObject *__pyx_sent_value); /* proto */ /* "curated_tokenizers/_bbpe.pyx":141 * token_bytes = [self._byte_encoder[b] for b in token.encode("utf-8")] * merged = deref(self._merges).apply_merges(token_bytes) * pieces.extend(merge.decode("utf-8") for merge in merged) # <<<<<<<<<<<<<< * return pieces * */ static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_16encode_as_pieces_genexpr(CYTHON_UNUSED PyObject *__pyx_self, std::vector __pyx_genexpr_arg_0) { struct __pyx_obj_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr *__pyx_cur_scope; PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("genexpr", 0); __pyx_cur_scope = (struct __pyx_obj_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr *)__pyx_tp_new_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr(__pyx_ptype_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr, __pyx_empty_tuple, NULL); if (unlikely(!__pyx_cur_scope)) { __pyx_cur_scope = ((struct __pyx_obj_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr *)Py_None); __Pyx_INCREF(Py_None); __PYX_ERR(0, 141, __pyx_L1_error) } else { __Pyx_GOTREF((PyObject *)__pyx_cur_scope); } __pyx_cur_scope->__pyx_genexpr_arg_0 = __pyx_genexpr_arg_0; { __pyx_CoroutineObject *gen = __Pyx_Generator_New((__pyx_coroutine_body_t) __pyx_gb_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_16encode_as_pieces_2generator, NULL, (PyObject *) __pyx_cur_scope, __pyx_n_s_genexpr, __pyx_n_s_encode_as_pieces_locals_genexpr, __pyx_n_s_curated_tokenizers__bbpe); if (unlikely(!gen)) __PYX_ERR(0, 141, __pyx_L1_error) __Pyx_DECREF(__pyx_cur_scope); __Pyx_RefNannyFinishContext(); return (PyObject *) gen; } /* function exit code */ __pyx_L1_error:; __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.encode_as_pieces.genexpr", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = NULL; __Pyx_DECREF((PyObject *)__pyx_cur_scope); __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } static PyObject *__pyx_gb_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_16encode_as_pieces_2generator(__pyx_CoroutineObject *__pyx_generator, CYTHON_UNUSED PyThreadState *__pyx_tstate, PyObject *__pyx_sent_value) /* generator body */ { struct __pyx_obj_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr *__pyx_cur_scope = ((struct __pyx_obj_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr *)__pyx_generator->closure); PyObject *__pyx_r = NULL; std::vector ::iterator __pyx_t_1; std::string __pyx_t_2; PyObject *__pyx_t_3 = NULL; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("genexpr", 0); switch (__pyx_generator->resume_label) { case 0: goto __pyx_L3_first_run; case 1: goto __pyx_L6_resume_from_yield; default: /* CPython raises the right error here */ __Pyx_RefNannyFinishContext(); return NULL; } __pyx_L3_first_run:; if (unlikely(!__pyx_sent_value)) __PYX_ERR(0, 141, __pyx_L1_error) __pyx_t_1 = __pyx_cur_scope->__pyx_genexpr_arg_0.begin(); for (;;) { if (!(__pyx_t_1 != __pyx_cur_scope->__pyx_genexpr_arg_0.end())) break; __pyx_t_2 = *__pyx_t_1; ++__pyx_t_1; __pyx_cur_scope->__pyx_v_merge = __PYX_STD_MOVE_IF_SUPPORTED(__pyx_t_2); __pyx_t_3 = __Pyx_decode_cpp_string(__pyx_cur_scope->__pyx_v_merge, 0, PY_SSIZE_T_MAX, NULL, NULL, PyUnicode_DecodeUTF8); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 141, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_r = __pyx_t_3; __pyx_t_3 = 0; __pyx_cur_scope->__pyx_t_0 = __PYX_STD_MOVE_IF_SUPPORTED(__pyx_t_1); __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); __Pyx_Coroutine_ResetAndClearException(__pyx_generator); /* return from generator, yielding value */ __pyx_generator->resume_label = 1; return __pyx_r; __pyx_L6_resume_from_yield:; __pyx_t_1 = __PYX_STD_MOVE_IF_SUPPORTED(__pyx_cur_scope->__pyx_t_0); if (unlikely(!__pyx_sent_value)) __PYX_ERR(0, 141, __pyx_L1_error) } CYTHON_MAYBE_UNUSED_VAR(__pyx_cur_scope); /* function exit code */ PyErr_SetNone(PyExc_StopIteration); goto __pyx_L0; __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_3); __Pyx_AddTraceback("genexpr", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_L0:; __Pyx_XDECREF(__pyx_r); __pyx_r = 0; #if !CYTHON_USE_EXC_INFO_STACK __Pyx_Coroutine_ResetAndClearException(__pyx_generator); #endif __pyx_generator->resume_label = -1; __Pyx_Coroutine_clear((PyObject*)__pyx_generator); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "curated_tokenizers/_bbpe.pyx":130 * return self._pieces_to_ids(pieces) * * def encode_as_pieces(self, text: str) -> List[str]: # <<<<<<<<<<<<<< * """ * Split a text into pieces, returning piece pieces. */ static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_14encode_as_pieces(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self, PyObject *__pyx_v_text) { PyObject *__pyx_v_pieces = NULL; PyObject *__pyx_v_token = NULL; PyObject *__pyx_v_token_bytes = NULL; std::vector __pyx_v_merged; PyObject *__pyx_v_b = NULL; PyObject *__pyx_gb_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_16encode_as_pieces_2generator = 0; PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; PyObject *__pyx_t_2 = NULL; PyObject *__pyx_t_3 = NULL; int __pyx_t_4; Py_ssize_t __pyx_t_5; PyObject *(*__pyx_t_6)(PyObject *); PyObject *__pyx_t_7 = NULL; PyObject *__pyx_t_8 = NULL; Py_ssize_t __pyx_t_9; PyObject *(*__pyx_t_10)(PyObject *); std::vector __pyx_t_11; int __pyx_t_12; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("encode_as_pieces", 1); /* "curated_tokenizers/_bbpe.pyx":137 * RETURNS: Piece pieces. * """ * pieces = [] # <<<<<<<<<<<<<< * for token in regex.findall(self._split_pattern, text): * token_bytes = [self._byte_encoder[b] for b in token.encode("utf-8")] */ __pyx_t_1 = PyList_New(0); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 137, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_v_pieces = ((PyObject*)__pyx_t_1); __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":138 * """ * pieces = [] * for token in regex.findall(self._split_pattern, text): # <<<<<<<<<<<<<< * token_bytes = [self._byte_encoder[b] for b in token.encode("utf-8")] * merged = deref(self._merges).apply_merges(token_bytes) */ __Pyx_GetModuleGlobalName(__pyx_t_2, __pyx_n_s_regex); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 138, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __pyx_t_3 = __Pyx_PyObject_GetAttrStr(__pyx_t_2, __pyx_n_s_findall); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 138, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = NULL; __pyx_t_4 = 0; #if CYTHON_UNPACK_METHODS if (unlikely(PyMethod_Check(__pyx_t_3))) { __pyx_t_2 = PyMethod_GET_SELF(__pyx_t_3); if (likely(__pyx_t_2)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_3); __Pyx_INCREF(__pyx_t_2); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_3, function); __pyx_t_4 = 1; } } #endif { PyObject *__pyx_callargs[3] = {__pyx_t_2, __pyx_v_self->_split_pattern, __pyx_v_text}; __pyx_t_1 = __Pyx_PyObject_FastCall(__pyx_t_3, __pyx_callargs+1-__pyx_t_4, 2+__pyx_t_4); __Pyx_XDECREF(__pyx_t_2); __pyx_t_2 = 0; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 138, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; } if (likely(PyList_CheckExact(__pyx_t_1)) || PyTuple_CheckExact(__pyx_t_1)) { __pyx_t_3 = __pyx_t_1; __Pyx_INCREF(__pyx_t_3); __pyx_t_5 = 0; __pyx_t_6 = NULL; } else { __pyx_t_5 = -1; __pyx_t_3 = PyObject_GetIter(__pyx_t_1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 138, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_6 = __Pyx_PyObject_GetIterNextFunc(__pyx_t_3); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 138, __pyx_L1_error) } __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; for (;;) { if (likely(!__pyx_t_6)) { if (likely(PyList_CheckExact(__pyx_t_3))) { { Py_ssize_t __pyx_temp = __Pyx_PyList_GET_SIZE(__pyx_t_3); #if !CYTHON_ASSUME_SAFE_MACROS if (unlikely((__pyx_temp < 0))) __PYX_ERR(0, 138, __pyx_L1_error) #endif if (__pyx_t_5 >= __pyx_temp) break; } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_1 = PyList_GET_ITEM(__pyx_t_3, __pyx_t_5); __Pyx_INCREF(__pyx_t_1); __pyx_t_5++; if (unlikely((0 < 0))) __PYX_ERR(0, 138, __pyx_L1_error) #else __pyx_t_1 = __Pyx_PySequence_ITEM(__pyx_t_3, __pyx_t_5); __pyx_t_5++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 138, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); #endif } else { { Py_ssize_t __pyx_temp = __Pyx_PyTuple_GET_SIZE(__pyx_t_3); #if !CYTHON_ASSUME_SAFE_MACROS if (unlikely((__pyx_temp < 0))) __PYX_ERR(0, 138, __pyx_L1_error) #endif if (__pyx_t_5 >= __pyx_temp) break; } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_1 = PyTuple_GET_ITEM(__pyx_t_3, __pyx_t_5); __Pyx_INCREF(__pyx_t_1); __pyx_t_5++; if (unlikely((0 < 0))) __PYX_ERR(0, 138, __pyx_L1_error) #else __pyx_t_1 = __Pyx_PySequence_ITEM(__pyx_t_3, __pyx_t_5); __pyx_t_5++; if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 138, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); #endif } } else { __pyx_t_1 = __pyx_t_6(__pyx_t_3); if (unlikely(!__pyx_t_1)) { PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); else __PYX_ERR(0, 138, __pyx_L1_error) } break; } __Pyx_GOTREF(__pyx_t_1); } __Pyx_XDECREF_SET(__pyx_v_token, __pyx_t_1); __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":139 * pieces = [] * for token in regex.findall(self._split_pattern, text): * token_bytes = [self._byte_encoder[b] for b in token.encode("utf-8")] # <<<<<<<<<<<<<< * merged = deref(self._merges).apply_merges(token_bytes) * pieces.extend(merge.decode("utf-8") for merge in merged) */ __pyx_t_1 = PyList_New(0); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 139, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_7 = __Pyx_PyObject_GetAttrStr(__pyx_v_token, __pyx_n_s_encode); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 139, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); __pyx_t_8 = NULL; __pyx_t_4 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_7))) { __pyx_t_8 = PyMethod_GET_SELF(__pyx_t_7); if (likely(__pyx_t_8)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_7); __Pyx_INCREF(__pyx_t_8); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_7, function); __pyx_t_4 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_8, __pyx_kp_s_utf_8}; __pyx_t_2 = __Pyx_PyObject_FastCall(__pyx_t_7, __pyx_callargs+1-__pyx_t_4, 1+__pyx_t_4); __Pyx_XDECREF(__pyx_t_8); __pyx_t_8 = 0; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 139, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; } if (likely(PyList_CheckExact(__pyx_t_2)) || PyTuple_CheckExact(__pyx_t_2)) { __pyx_t_7 = __pyx_t_2; __Pyx_INCREF(__pyx_t_7); __pyx_t_9 = 0; __pyx_t_10 = NULL; } else { __pyx_t_9 = -1; __pyx_t_7 = PyObject_GetIter(__pyx_t_2); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 139, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); __pyx_t_10 = __Pyx_PyObject_GetIterNextFunc(__pyx_t_7); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 139, __pyx_L1_error) } __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; for (;;) { if (likely(!__pyx_t_10)) { if (likely(PyList_CheckExact(__pyx_t_7))) { { Py_ssize_t __pyx_temp = __Pyx_PyList_GET_SIZE(__pyx_t_7); #if !CYTHON_ASSUME_SAFE_MACROS if (unlikely((__pyx_temp < 0))) __PYX_ERR(0, 139, __pyx_L1_error) #endif if (__pyx_t_9 >= __pyx_temp) break; } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_2 = PyList_GET_ITEM(__pyx_t_7, __pyx_t_9); __Pyx_INCREF(__pyx_t_2); __pyx_t_9++; if (unlikely((0 < 0))) __PYX_ERR(0, 139, __pyx_L1_error) #else __pyx_t_2 = __Pyx_PySequence_ITEM(__pyx_t_7, __pyx_t_9); __pyx_t_9++; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 139, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); #endif } else { { Py_ssize_t __pyx_temp = __Pyx_PyTuple_GET_SIZE(__pyx_t_7); #if !CYTHON_ASSUME_SAFE_MACROS if (unlikely((__pyx_temp < 0))) __PYX_ERR(0, 139, __pyx_L1_error) #endif if (__pyx_t_9 >= __pyx_temp) break; } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_2 = PyTuple_GET_ITEM(__pyx_t_7, __pyx_t_9); __Pyx_INCREF(__pyx_t_2); __pyx_t_9++; if (unlikely((0 < 0))) __PYX_ERR(0, 139, __pyx_L1_error) #else __pyx_t_2 = __Pyx_PySequence_ITEM(__pyx_t_7, __pyx_t_9); __pyx_t_9++; if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 139, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); #endif } } else { __pyx_t_2 = __pyx_t_10(__pyx_t_7); if (unlikely(!__pyx_t_2)) { PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); else __PYX_ERR(0, 139, __pyx_L1_error) } break; } __Pyx_GOTREF(__pyx_t_2); } __Pyx_XDECREF_SET(__pyx_v_b, __pyx_t_2); __pyx_t_2 = 0; if (unlikely(__pyx_v_self->_byte_encoder == Py_None)) { PyErr_SetString(PyExc_TypeError, "'NoneType' object is not subscriptable"); __PYX_ERR(0, 139, __pyx_L1_error) } __pyx_t_2 = __Pyx_PyDict_GetItem(__pyx_v_self->_byte_encoder, __pyx_v_b); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 139, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (unlikely(__Pyx_ListComp_Append(__pyx_t_1, (PyObject*)__pyx_t_2))) __PYX_ERR(0, 139, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; } __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; __Pyx_XDECREF_SET(__pyx_v_token_bytes, ((PyObject*)__pyx_t_1)); __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":140 * for token in regex.findall(self._split_pattern, text): * token_bytes = [self._byte_encoder[b] for b in token.encode("utf-8")] * merged = deref(self._merges).apply_merges(token_bytes) # <<<<<<<<<<<<<< * pieces.extend(merge.decode("utf-8") for merge in merged) * return pieces */ __pyx_t_11 = __pyx_convert_vector_from_py_std_3a__3a_string(__pyx_v_token_bytes); if (unlikely(PyErr_Occurred())) __PYX_ERR(0, 140, __pyx_L1_error) __pyx_v_merged = (*__pyx_v_self->_merges).apply_merges(__PYX_STD_MOVE_IF_SUPPORTED(__pyx_t_11)); /* "curated_tokenizers/_bbpe.pyx":141 * token_bytes = [self._byte_encoder[b] for b in token.encode("utf-8")] * merged = deref(self._merges).apply_merges(token_bytes) * pieces.extend(merge.decode("utf-8") for merge in merged) # <<<<<<<<<<<<<< * return pieces * */ __pyx_t_1 = __pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_16encode_as_pieces_genexpr(NULL, __pyx_v_merged); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 141, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_12 = __Pyx_PyList_Extend(__pyx_v_pieces, __pyx_t_1); if (unlikely(__pyx_t_12 == ((int)-1))) __PYX_ERR(0, 141, __pyx_L1_error) __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":138 * """ * pieces = [] * for token in regex.findall(self._split_pattern, text): # <<<<<<<<<<<<<< * token_bytes = [self._byte_encoder[b] for b in token.encode("utf-8")] * merged = deref(self._merges).apply_merges(token_bytes) */ } __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; /* "curated_tokenizers/_bbpe.pyx":142 * merged = deref(self._merges).apply_merges(token_bytes) * pieces.extend(merge.decode("utf-8") for merge in merged) * return pieces # <<<<<<<<<<<<<< * * @property */ __Pyx_XDECREF(__pyx_r); __Pyx_INCREF(__pyx_v_pieces); __pyx_r = __pyx_v_pieces; goto __pyx_L0; /* "curated_tokenizers/_bbpe.pyx":130 * return self._pieces_to_ids(pieces) * * def encode_as_pieces(self, text: str) -> List[str]: # <<<<<<<<<<<<<< * """ * Split a text into pieces, returning piece pieces. */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_XDECREF(__pyx_t_2); __Pyx_XDECREF(__pyx_t_3); __Pyx_XDECREF(__pyx_t_7); __Pyx_XDECREF(__pyx_t_8); __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.encode_as_pieces", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = NULL; __pyx_L0:; __Pyx_XDECREF(__pyx_v_pieces); __Pyx_XDECREF(__pyx_v_token); __Pyx_XDECREF(__pyx_v_token_bytes); __Pyx_XDECREF(__pyx_v_b); __Pyx_XDECREF(__pyx_gb_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_16encode_as_pieces_2generator); __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "curated_tokenizers/_bbpe.pyx":144 * return pieces * * @property # <<<<<<<<<<<<<< * def merges(self) -> List[Tuple[str, str]]: * """Get all merges.""" */ /* Python wrapper */ static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_6merges_1__get__(PyObject *__pyx_v_self); /*proto*/ static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_6merges_1__get__(PyObject *__pyx_v_self) { CYTHON_UNUSED PyObject *const *__pyx_kwvalues; PyObject *__pyx_r = 0; __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__get__ (wrapper)", 0); __pyx_kwvalues = __Pyx_KwValues_VARARGS(__pyx_args, __pyx_nargs); __pyx_r = __pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_6merges___get__(((struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *)__pyx_v_self)); /* function exit code */ __Pyx_RefNannyFinishContext(); return __pyx_r; } static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_6merges___get__(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self) { std::vector > __pyx_v_merges_bytes; PyObject *__pyx_v_m1 = NULL; PyObject *__pyx_v_m2 = NULL; PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; std::vector > ::iterator __pyx_t_2; std::pair __pyx_t_3; PyObject *__pyx_t_4 = NULL; PyObject *__pyx_t_5 = NULL; PyObject *__pyx_t_6 = NULL; PyObject *__pyx_t_7 = NULL; PyObject *(*__pyx_t_8)(PyObject *); int __pyx_t_9; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("__get__", 1); /* "curated_tokenizers/_bbpe.pyx":147 * def merges(self) -> List[Tuple[str, str]]: * """Get all merges.""" * merges_bytes = deref(self._merges).merges() # <<<<<<<<<<<<<< * return [(m1.decode('utf-8'), m2.decode('utf-8')) for m1, m2 in merges_bytes] * */ __pyx_v_merges_bytes = (*__pyx_v_self->_merges).merges(); /* "curated_tokenizers/_bbpe.pyx":148 * """Get all merges.""" * merges_bytes = deref(self._merges).merges() * return [(m1.decode('utf-8'), m2.decode('utf-8')) for m1, m2 in merges_bytes] # <<<<<<<<<<<<<< * * def piece_id(self, piece: str) -> Optional[int]: */ __Pyx_XDECREF(__pyx_r); __pyx_t_1 = PyList_New(0); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 148, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_2 = __pyx_v_merges_bytes.begin(); for (;;) { if (!(__pyx_t_2 != __pyx_v_merges_bytes.end())) break; __pyx_t_3 = *__pyx_t_2; ++__pyx_t_2; __pyx_t_4 = __pyx_convert_pair_to_py_std_3a__3a_string____std_3a__3a_string(__pyx_t_3); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 148, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); if ((likely(PyTuple_CheckExact(__pyx_t_4))) || (PyList_CheckExact(__pyx_t_4))) { PyObject* sequence = __pyx_t_4; Py_ssize_t size = __Pyx_PySequence_SIZE(sequence); if (unlikely(size != 2)) { if (size > 2) __Pyx_RaiseTooManyValuesError(2); else if (size >= 0) __Pyx_RaiseNeedMoreValuesError(size); __PYX_ERR(0, 148, __pyx_L1_error) } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS if (likely(PyTuple_CheckExact(sequence))) { __pyx_t_5 = PyTuple_GET_ITEM(sequence, 0); __pyx_t_6 = PyTuple_GET_ITEM(sequence, 1); } else { __pyx_t_5 = PyList_GET_ITEM(sequence, 0); __pyx_t_6 = PyList_GET_ITEM(sequence, 1); } __Pyx_INCREF(__pyx_t_5); __Pyx_INCREF(__pyx_t_6); #else __pyx_t_5 = PySequence_ITEM(sequence, 0); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 148, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); __pyx_t_6 = PySequence_ITEM(sequence, 1); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 148, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_6); #endif __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; } else { Py_ssize_t index = -1; __pyx_t_7 = PyObject_GetIter(__pyx_t_4); if (unlikely(!__pyx_t_7)) __PYX_ERR(0, 148, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_7); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; __pyx_t_8 = __Pyx_PyObject_GetIterNextFunc(__pyx_t_7); index = 0; __pyx_t_5 = __pyx_t_8(__pyx_t_7); if (unlikely(!__pyx_t_5)) goto __pyx_L5_unpacking_failed; __Pyx_GOTREF(__pyx_t_5); index = 1; __pyx_t_6 = __pyx_t_8(__pyx_t_7); if (unlikely(!__pyx_t_6)) goto __pyx_L5_unpacking_failed; __Pyx_GOTREF(__pyx_t_6); if (__Pyx_IternextUnpackEndCheck(__pyx_t_8(__pyx_t_7), 2) < 0) __PYX_ERR(0, 148, __pyx_L1_error) __pyx_t_8 = NULL; __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; goto __pyx_L6_unpacking_done; __pyx_L5_unpacking_failed:; __Pyx_DECREF(__pyx_t_7); __pyx_t_7 = 0; __pyx_t_8 = NULL; if (__Pyx_IterFinish() == 0) __Pyx_RaiseNeedMoreValuesError(index); __PYX_ERR(0, 148, __pyx_L1_error) __pyx_L6_unpacking_done:; } __Pyx_XDECREF_SET(__pyx_v_m1, __pyx_t_5); __pyx_t_5 = 0; __Pyx_XDECREF_SET(__pyx_v_m2, __pyx_t_6); __pyx_t_6 = 0; __pyx_t_6 = __Pyx_PyObject_GetAttrStr(__pyx_v_m1, __pyx_n_s_decode); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 148, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_6); __pyx_t_5 = NULL; __pyx_t_9 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_6))) { __pyx_t_5 = PyMethod_GET_SELF(__pyx_t_6); if (likely(__pyx_t_5)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_6); __Pyx_INCREF(__pyx_t_5); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_6, function); __pyx_t_9 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_5, __pyx_kp_s_utf_8}; __pyx_t_4 = __Pyx_PyObject_FastCall(__pyx_t_6, __pyx_callargs+1-__pyx_t_9, 1+__pyx_t_9); __Pyx_XDECREF(__pyx_t_5); __pyx_t_5 = 0; if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 148, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; } __pyx_t_5 = __Pyx_PyObject_GetAttrStr(__pyx_v_m2, __pyx_n_s_decode); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 148, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); __pyx_t_7 = NULL; __pyx_t_9 = 0; #if CYTHON_UNPACK_METHODS if (likely(PyMethod_Check(__pyx_t_5))) { __pyx_t_7 = PyMethod_GET_SELF(__pyx_t_5); if (likely(__pyx_t_7)) { PyObject* function = PyMethod_GET_FUNCTION(__pyx_t_5); __Pyx_INCREF(__pyx_t_7); __Pyx_INCREF(function); __Pyx_DECREF_SET(__pyx_t_5, function); __pyx_t_9 = 1; } } #endif { PyObject *__pyx_callargs[2] = {__pyx_t_7, __pyx_kp_s_utf_8}; __pyx_t_6 = __Pyx_PyObject_FastCall(__pyx_t_5, __pyx_callargs+1-__pyx_t_9, 1+__pyx_t_9); __Pyx_XDECREF(__pyx_t_7); __pyx_t_7 = 0; if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 148, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_6); __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; } __pyx_t_5 = PyTuple_New(2); if (unlikely(!__pyx_t_5)) __PYX_ERR(0, 148, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_5); __Pyx_GIVEREF(__pyx_t_4); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_5, 0, __pyx_t_4)) __PYX_ERR(0, 148, __pyx_L1_error); __Pyx_GIVEREF(__pyx_t_6); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_5, 1, __pyx_t_6)) __PYX_ERR(0, 148, __pyx_L1_error); __pyx_t_4 = 0; __pyx_t_6 = 0; if (unlikely(__Pyx_ListComp_Append(__pyx_t_1, (PyObject*)__pyx_t_5))) __PYX_ERR(0, 148, __pyx_L1_error) __Pyx_DECREF(__pyx_t_5); __pyx_t_5 = 0; } __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; /* "curated_tokenizers/_bbpe.pyx":144 * return pieces * * @property # <<<<<<<<<<<<<< * def merges(self) -> List[Tuple[str, str]]: * """Get all merges.""" */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_XDECREF(__pyx_t_4); __Pyx_XDECREF(__pyx_t_5); __Pyx_XDECREF(__pyx_t_6); __Pyx_XDECREF(__pyx_t_7); __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.merges.__get__", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = NULL; __pyx_L0:; __Pyx_XDECREF(__pyx_v_m1); __Pyx_XDECREF(__pyx_v_m2); __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "curated_tokenizers/_bbpe.pyx":150 * return [(m1.decode('utf-8'), m2.decode('utf-8')) for m1, m2 in merges_bytes] * * def piece_id(self, piece: str) -> Optional[int]: # <<<<<<<<<<<<<< * """Get the identifier for a piece.""" * return self._piece_to_id.get(piece) */ /* Python wrapper */ static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_17piece_id(PyObject *__pyx_v_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ); /*proto*/ PyDoc_STRVAR(__pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_16piece_id, "ByteBPEProcessor.piece_id(self, piece: str) -> Optional[int]\nGet the identifier for a piece."); static PyMethodDef __pyx_mdef_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_17piece_id = {"piece_id", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_17piece_id, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_16piece_id}; static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_17piece_id(PyObject *__pyx_v_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ) { PyObject *__pyx_v_piece = 0; #if !CYTHON_METH_FASTCALL CYTHON_UNUSED Py_ssize_t __pyx_nargs; #endif CYTHON_UNUSED PyObject *const *__pyx_kwvalues; PyObject* values[1] = {0}; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; PyObject *__pyx_r = 0; __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("piece_id (wrapper)", 0); #if !CYTHON_METH_FASTCALL #if CYTHON_ASSUME_SAFE_MACROS __pyx_nargs = PyTuple_GET_SIZE(__pyx_args); #else __pyx_nargs = PyTuple_Size(__pyx_args); if (unlikely(__pyx_nargs < 0)) return NULL; #endif #endif __pyx_kwvalues = __Pyx_KwValues_FASTCALL(__pyx_args, __pyx_nargs); { PyObject **__pyx_pyargnames[] = {&__pyx_n_s_piece,0}; if (__pyx_kwds) { Py_ssize_t kw_args; switch (__pyx_nargs) { case 1: values[0] = __Pyx_Arg_FASTCALL(__pyx_args, 0); CYTHON_FALLTHROUGH; case 0: break; default: goto __pyx_L5_argtuple_error; } kw_args = __Pyx_NumKwargs_FASTCALL(__pyx_kwds); switch (__pyx_nargs) { case 0: if (likely((values[0] = __Pyx_GetKwValue_FASTCALL(__pyx_kwds, __pyx_kwvalues, __pyx_n_s_piece)) != 0)) { (void)__Pyx_Arg_NewRef_FASTCALL(values[0]); kw_args--; } else if (unlikely(PyErr_Occurred())) __PYX_ERR(0, 150, __pyx_L3_error) else goto __pyx_L5_argtuple_error; } if (unlikely(kw_args > 0)) { const Py_ssize_t kwd_pos_args = __pyx_nargs; if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_kwvalues, __pyx_pyargnames, 0, values + 0, kwd_pos_args, "piece_id") < 0)) __PYX_ERR(0, 150, __pyx_L3_error) } } else if (unlikely(__pyx_nargs != 1)) { goto __pyx_L5_argtuple_error; } else { values[0] = __Pyx_Arg_FASTCALL(__pyx_args, 0); } __pyx_v_piece = values[0]; } goto __pyx_L6_skip; __pyx_L5_argtuple_error:; __Pyx_RaiseArgtupleInvalid("piece_id", 1, 1, 1, __pyx_nargs); __PYX_ERR(0, 150, __pyx_L3_error) __pyx_L6_skip:; goto __pyx_L4_argument_unpacking_done; __pyx_L3_error:; { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < (Py_ssize_t)(sizeof(values)/sizeof(values[0])); ++__pyx_temp) { __Pyx_Arg_XDECREF_FASTCALL(values[__pyx_temp]); } } __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.piece_id", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); return NULL; __pyx_L4_argument_unpacking_done:; __pyx_r = __pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_16piece_id(((struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *)__pyx_v_self), __pyx_v_piece); /* function exit code */ { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < (Py_ssize_t)(sizeof(values)/sizeof(values[0])); ++__pyx_temp) { __Pyx_Arg_XDECREF_FASTCALL(values[__pyx_temp]); } } __Pyx_RefNannyFinishContext(); return __pyx_r; } static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_16piece_id(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self, PyObject *__pyx_v_piece) { PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("piece_id", 1); /* "curated_tokenizers/_bbpe.pyx":152 * def piece_id(self, piece: str) -> Optional[int]: * """Get the identifier for a piece.""" * return self._piece_to_id.get(piece) # <<<<<<<<<<<<<< * * @property */ __Pyx_XDECREF(__pyx_r); if (unlikely(__pyx_v_self->_piece_to_id == Py_None)) { PyErr_Format(PyExc_AttributeError, "'NoneType' object has no attribute '%.30s'", "get"); __PYX_ERR(0, 152, __pyx_L1_error) } __pyx_t_1 = __Pyx_PyDict_GetItemDefault(__pyx_v_self->_piece_to_id, __pyx_v_piece, Py_None); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 152, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; /* "curated_tokenizers/_bbpe.pyx":150 * return [(m1.decode('utf-8'), m2.decode('utf-8')) for m1, m2 in merges_bytes] * * def piece_id(self, piece: str) -> Optional[int]: # <<<<<<<<<<<<<< * """Get the identifier for a piece.""" * return self._piece_to_id.get(piece) */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.piece_id", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = NULL; __pyx_L0:; __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "curated_tokenizers/_bbpe.pyx":154 * return self._piece_to_id.get(piece) * * @property # <<<<<<<<<<<<<< * def vocab(self) -> Dict[str, int]: * """Get a copy of the vocabulary.""" */ /* Python wrapper */ static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_5vocab_1__get__(PyObject *__pyx_v_self); /*proto*/ static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_5vocab_1__get__(PyObject *__pyx_v_self) { CYTHON_UNUSED PyObject *const *__pyx_kwvalues; PyObject *__pyx_r = 0; __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__get__ (wrapper)", 0); __pyx_kwvalues = __Pyx_KwValues_VARARGS(__pyx_args, __pyx_nargs); __pyx_r = __pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_5vocab___get__(((struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *)__pyx_v_self)); /* function exit code */ __Pyx_RefNannyFinishContext(); return __pyx_r; } static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_5vocab___get__(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self) { PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("__get__", 1); /* "curated_tokenizers/_bbpe.pyx":157 * def vocab(self) -> Dict[str, int]: * """Get a copy of the vocabulary.""" * return dict(self._piece_to_id) # <<<<<<<<<<<<<< * * def _pieces_to_ids(self, pieces): */ __Pyx_XDECREF(__pyx_r); if (unlikely(__pyx_v_self->_piece_to_id == Py_None)) { PyErr_SetString(PyExc_TypeError, "'NoneType' is not iterable"); __PYX_ERR(0, 157, __pyx_L1_error) } __pyx_t_1 = PyDict_Copy(__pyx_v_self->_piece_to_id); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 157, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_r = __pyx_t_1; __pyx_t_1 = 0; goto __pyx_L0; /* "curated_tokenizers/_bbpe.pyx":154 * return self._piece_to_id.get(piece) * * @property # <<<<<<<<<<<<<< * def vocab(self) -> Dict[str, int]: * """Get a copy of the vocabulary.""" */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.vocab.__get__", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = NULL; __pyx_L0:; __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "curated_tokenizers/_bbpe.pyx":159 * return dict(self._piece_to_id) * * def _pieces_to_ids(self, pieces): # <<<<<<<<<<<<<< * piece_ids = [] * for piece in pieces: */ /* Python wrapper */ static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_19_pieces_to_ids(PyObject *__pyx_v_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ); /*proto*/ PyDoc_STRVAR(__pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_18_pieces_to_ids, "ByteBPEProcessor._pieces_to_ids(self, pieces)"); static PyMethodDef __pyx_mdef_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_19_pieces_to_ids = {"_pieces_to_ids", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_19_pieces_to_ids, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_18_pieces_to_ids}; static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_19_pieces_to_ids(PyObject *__pyx_v_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ) { PyObject *__pyx_v_pieces = 0; #if !CYTHON_METH_FASTCALL CYTHON_UNUSED Py_ssize_t __pyx_nargs; #endif CYTHON_UNUSED PyObject *const *__pyx_kwvalues; PyObject* values[1] = {0}; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; PyObject *__pyx_r = 0; __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("_pieces_to_ids (wrapper)", 0); #if !CYTHON_METH_FASTCALL #if CYTHON_ASSUME_SAFE_MACROS __pyx_nargs = PyTuple_GET_SIZE(__pyx_args); #else __pyx_nargs = PyTuple_Size(__pyx_args); if (unlikely(__pyx_nargs < 0)) return NULL; #endif #endif __pyx_kwvalues = __Pyx_KwValues_FASTCALL(__pyx_args, __pyx_nargs); { PyObject **__pyx_pyargnames[] = {&__pyx_n_s_pieces,0}; if (__pyx_kwds) { Py_ssize_t kw_args; switch (__pyx_nargs) { case 1: values[0] = __Pyx_Arg_FASTCALL(__pyx_args, 0); CYTHON_FALLTHROUGH; case 0: break; default: goto __pyx_L5_argtuple_error; } kw_args = __Pyx_NumKwargs_FASTCALL(__pyx_kwds); switch (__pyx_nargs) { case 0: if (likely((values[0] = __Pyx_GetKwValue_FASTCALL(__pyx_kwds, __pyx_kwvalues, __pyx_n_s_pieces)) != 0)) { (void)__Pyx_Arg_NewRef_FASTCALL(values[0]); kw_args--; } else if (unlikely(PyErr_Occurred())) __PYX_ERR(0, 159, __pyx_L3_error) else goto __pyx_L5_argtuple_error; } if (unlikely(kw_args > 0)) { const Py_ssize_t kwd_pos_args = __pyx_nargs; if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_kwvalues, __pyx_pyargnames, 0, values + 0, kwd_pos_args, "_pieces_to_ids") < 0)) __PYX_ERR(0, 159, __pyx_L3_error) } } else if (unlikely(__pyx_nargs != 1)) { goto __pyx_L5_argtuple_error; } else { values[0] = __Pyx_Arg_FASTCALL(__pyx_args, 0); } __pyx_v_pieces = values[0]; } goto __pyx_L6_skip; __pyx_L5_argtuple_error:; __Pyx_RaiseArgtupleInvalid("_pieces_to_ids", 1, 1, 1, __pyx_nargs); __PYX_ERR(0, 159, __pyx_L3_error) __pyx_L6_skip:; goto __pyx_L4_argument_unpacking_done; __pyx_L3_error:; { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < (Py_ssize_t)(sizeof(values)/sizeof(values[0])); ++__pyx_temp) { __Pyx_Arg_XDECREF_FASTCALL(values[__pyx_temp]); } } __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor._pieces_to_ids", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); return NULL; __pyx_L4_argument_unpacking_done:; __pyx_r = __pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_18_pieces_to_ids(((struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *)__pyx_v_self), __pyx_v_pieces); /* function exit code */ { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < (Py_ssize_t)(sizeof(values)/sizeof(values[0])); ++__pyx_temp) { __Pyx_Arg_XDECREF_FASTCALL(values[__pyx_temp]); } } __Pyx_RefNannyFinishContext(); return __pyx_r; } static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_18_pieces_to_ids(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self, PyObject *__pyx_v_pieces) { PyObject *__pyx_v_piece_ids = NULL; PyObject *__pyx_v_piece = NULL; PyObject *__pyx_v_piece_id = NULL; PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; Py_ssize_t __pyx_t_2; PyObject *(*__pyx_t_3)(PyObject *); PyObject *__pyx_t_4 = NULL; int __pyx_t_5; PyObject *__pyx_t_6 = NULL; int __pyx_t_7; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("_pieces_to_ids", 1); /* "curated_tokenizers/_bbpe.pyx":160 * * def _pieces_to_ids(self, pieces): * piece_ids = [] # <<<<<<<<<<<<<< * for piece in pieces: * piece_id = self._piece_to_id.get(piece) */ __pyx_t_1 = PyList_New(0); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 160, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_v_piece_ids = ((PyObject*)__pyx_t_1); __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":161 * def _pieces_to_ids(self, pieces): * piece_ids = [] * for piece in pieces: # <<<<<<<<<<<<<< * piece_id = self._piece_to_id.get(piece) * if piece_id is None: */ if (likely(PyList_CheckExact(__pyx_v_pieces)) || PyTuple_CheckExact(__pyx_v_pieces)) { __pyx_t_1 = __pyx_v_pieces; __Pyx_INCREF(__pyx_t_1); __pyx_t_2 = 0; __pyx_t_3 = NULL; } else { __pyx_t_2 = -1; __pyx_t_1 = PyObject_GetIter(__pyx_v_pieces); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 161, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_3 = __Pyx_PyObject_GetIterNextFunc(__pyx_t_1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 161, __pyx_L1_error) } for (;;) { if (likely(!__pyx_t_3)) { if (likely(PyList_CheckExact(__pyx_t_1))) { { Py_ssize_t __pyx_temp = __Pyx_PyList_GET_SIZE(__pyx_t_1); #if !CYTHON_ASSUME_SAFE_MACROS if (unlikely((__pyx_temp < 0))) __PYX_ERR(0, 161, __pyx_L1_error) #endif if (__pyx_t_2 >= __pyx_temp) break; } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_4 = PyList_GET_ITEM(__pyx_t_1, __pyx_t_2); __Pyx_INCREF(__pyx_t_4); __pyx_t_2++; if (unlikely((0 < 0))) __PYX_ERR(0, 161, __pyx_L1_error) #else __pyx_t_4 = __Pyx_PySequence_ITEM(__pyx_t_1, __pyx_t_2); __pyx_t_2++; if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 161, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); #endif } else { { Py_ssize_t __pyx_temp = __Pyx_PyTuple_GET_SIZE(__pyx_t_1); #if !CYTHON_ASSUME_SAFE_MACROS if (unlikely((__pyx_temp < 0))) __PYX_ERR(0, 161, __pyx_L1_error) #endif if (__pyx_t_2 >= __pyx_temp) break; } #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS __pyx_t_4 = PyTuple_GET_ITEM(__pyx_t_1, __pyx_t_2); __Pyx_INCREF(__pyx_t_4); __pyx_t_2++; if (unlikely((0 < 0))) __PYX_ERR(0, 161, __pyx_L1_error) #else __pyx_t_4 = __Pyx_PySequence_ITEM(__pyx_t_1, __pyx_t_2); __pyx_t_2++; if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 161, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); #endif } } else { __pyx_t_4 = __pyx_t_3(__pyx_t_1); if (unlikely(!__pyx_t_4)) { PyObject* exc_type = PyErr_Occurred(); if (exc_type) { if (likely(__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) PyErr_Clear(); else __PYX_ERR(0, 161, __pyx_L1_error) } break; } __Pyx_GOTREF(__pyx_t_4); } __Pyx_XDECREF_SET(__pyx_v_piece, __pyx_t_4); __pyx_t_4 = 0; /* "curated_tokenizers/_bbpe.pyx":162 * piece_ids = [] * for piece in pieces: * piece_id = self._piece_to_id.get(piece) # <<<<<<<<<<<<<< * if piece_id is None: * raise ValueError(f"Piece is not in vocabulary: {piece}") */ if (unlikely(__pyx_v_self->_piece_to_id == Py_None)) { PyErr_Format(PyExc_AttributeError, "'NoneType' object has no attribute '%.30s'", "get"); __PYX_ERR(0, 162, __pyx_L1_error) } __pyx_t_4 = __Pyx_PyDict_GetItemDefault(__pyx_v_self->_piece_to_id, __pyx_v_piece, Py_None); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 162, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_XDECREF_SET(__pyx_v_piece_id, __pyx_t_4); __pyx_t_4 = 0; /* "curated_tokenizers/_bbpe.pyx":163 * for piece in pieces: * piece_id = self._piece_to_id.get(piece) * if piece_id is None: # <<<<<<<<<<<<<< * raise ValueError(f"Piece is not in vocabulary: {piece}") * piece_ids.append(piece_id) */ __pyx_t_5 = (__pyx_v_piece_id == Py_None); if (unlikely(__pyx_t_5)) { /* "curated_tokenizers/_bbpe.pyx":164 * piece_id = self._piece_to_id.get(piece) * if piece_id is None: * raise ValueError(f"Piece is not in vocabulary: {piece}") # <<<<<<<<<<<<<< * piece_ids.append(piece_id) * */ __pyx_t_4 = __Pyx_PyObject_FormatSimple(__pyx_v_piece, __pyx_empty_unicode); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 164, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __pyx_t_6 = __Pyx_PyUnicode_Concat(__pyx_kp_u_Piece_is_not_in_vocabulary, __pyx_t_4); if (unlikely(!__pyx_t_6)) __PYX_ERR(0, 164, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_6); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; __pyx_t_4 = __Pyx_PyObject_CallOneArg(__pyx_builtin_ValueError, __pyx_t_6); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 164, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0; __Pyx_Raise(__pyx_t_4, 0, 0, 0); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; __PYX_ERR(0, 164, __pyx_L1_error) /* "curated_tokenizers/_bbpe.pyx":163 * for piece in pieces: * piece_id = self._piece_to_id.get(piece) * if piece_id is None: # <<<<<<<<<<<<<< * raise ValueError(f"Piece is not in vocabulary: {piece}") * piece_ids.append(piece_id) */ } /* "curated_tokenizers/_bbpe.pyx":165 * if piece_id is None: * raise ValueError(f"Piece is not in vocabulary: {piece}") * piece_ids.append(piece_id) # <<<<<<<<<<<<<< * * return piece_ids */ __pyx_t_7 = __Pyx_PyList_Append(__pyx_v_piece_ids, __pyx_v_piece_id); if (unlikely(__pyx_t_7 == ((int)-1))) __PYX_ERR(0, 165, __pyx_L1_error) /* "curated_tokenizers/_bbpe.pyx":161 * def _pieces_to_ids(self, pieces): * piece_ids = [] * for piece in pieces: # <<<<<<<<<<<<<< * piece_id = self._piece_to_id.get(piece) * if piece_id is None: */ } __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; /* "curated_tokenizers/_bbpe.pyx":167 * piece_ids.append(piece_id) * * return piece_ids # <<<<<<<<<<<<<< * * def __reduce__(self): */ __Pyx_XDECREF(__pyx_r); __Pyx_INCREF(__pyx_v_piece_ids); __pyx_r = __pyx_v_piece_ids; goto __pyx_L0; /* "curated_tokenizers/_bbpe.pyx":159 * return dict(self._piece_to_id) * * def _pieces_to_ids(self, pieces): # <<<<<<<<<<<<<< * piece_ids = [] * for piece in pieces: */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_XDECREF(__pyx_t_4); __Pyx_XDECREF(__pyx_t_6); __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor._pieces_to_ids", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = NULL; __pyx_L0:; __Pyx_XDECREF(__pyx_v_piece_ids); __Pyx_XDECREF(__pyx_v_piece); __Pyx_XDECREF(__pyx_v_piece_id); __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "curated_tokenizers/_bbpe.pyx":169 * return piece_ids * * def __reduce__(self): # <<<<<<<<<<<<<< * return (unpickle_byte_bpe_processor, (self.vocab, self.merges,)) * */ /* Python wrapper */ static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_21__reduce__(PyObject *__pyx_v_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ); /*proto*/ PyDoc_STRVAR(__pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_20__reduce__, "ByteBPEProcessor.__reduce__(self)"); static PyMethodDef __pyx_mdef_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_21__reduce__ = {"__reduce__", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_21__reduce__, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_20__reduce__}; static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_21__reduce__(PyObject *__pyx_v_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ) { #if !CYTHON_METH_FASTCALL CYTHON_UNUSED Py_ssize_t __pyx_nargs; #endif CYTHON_UNUSED PyObject *const *__pyx_kwvalues; PyObject *__pyx_r = 0; __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__reduce__ (wrapper)", 0); #if !CYTHON_METH_FASTCALL #if CYTHON_ASSUME_SAFE_MACROS __pyx_nargs = PyTuple_GET_SIZE(__pyx_args); #else __pyx_nargs = PyTuple_Size(__pyx_args); if (unlikely(__pyx_nargs < 0)) return NULL; #endif #endif __pyx_kwvalues = __Pyx_KwValues_FASTCALL(__pyx_args, __pyx_nargs); if (unlikely(__pyx_nargs > 0)) { __Pyx_RaiseArgtupleInvalid("__reduce__", 1, 0, 0, __pyx_nargs); return NULL;} if (unlikely(__pyx_kwds) && __Pyx_NumKwargs_FASTCALL(__pyx_kwds) && unlikely(!__Pyx_CheckKeywordStrings(__pyx_kwds, "__reduce__", 0))) return NULL; __pyx_r = __pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_20__reduce__(((struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *)__pyx_v_self)); /* function exit code */ __Pyx_RefNannyFinishContext(); return __pyx_r; } static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_20__reduce__(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *__pyx_v_self) { PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; PyObject *__pyx_t_2 = NULL; PyObject *__pyx_t_3 = NULL; PyObject *__pyx_t_4 = NULL; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("__reduce__", 1); /* "curated_tokenizers/_bbpe.pyx":170 * * def __reduce__(self): * return (unpickle_byte_bpe_processor, (self.vocab, self.merges,)) # <<<<<<<<<<<<<< * * def unpickle_byte_bpe_processor(vocab: Dict[str, int], */ __Pyx_XDECREF(__pyx_r); __Pyx_GetModuleGlobalName(__pyx_t_1, __pyx_n_s_unpickle_byte_bpe_processor); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 170, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __pyx_t_2 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_vocab); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 170, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __pyx_t_3 = __Pyx_PyObject_GetAttrStr(((PyObject *)__pyx_v_self), __pyx_n_s_merges); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 170, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __pyx_t_4 = PyTuple_New(2); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 170, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_GIVEREF(__pyx_t_2); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_4, 0, __pyx_t_2)) __PYX_ERR(0, 170, __pyx_L1_error); __Pyx_GIVEREF(__pyx_t_3); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_4, 1, __pyx_t_3)) __PYX_ERR(0, 170, __pyx_L1_error); __pyx_t_2 = 0; __pyx_t_3 = 0; __pyx_t_3 = PyTuple_New(2); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 170, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_GIVEREF(__pyx_t_1); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_3, 0, __pyx_t_1)) __PYX_ERR(0, 170, __pyx_L1_error); __Pyx_GIVEREF(__pyx_t_4); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_3, 1, __pyx_t_4)) __PYX_ERR(0, 170, __pyx_L1_error); __pyx_t_1 = 0; __pyx_t_4 = 0; __pyx_r = __pyx_t_3; __pyx_t_3 = 0; goto __pyx_L0; /* "curated_tokenizers/_bbpe.pyx":169 * return piece_ids * * def __reduce__(self): # <<<<<<<<<<<<<< * return (unpickle_byte_bpe_processor, (self.vocab, self.merges,)) * */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_XDECREF(__pyx_t_2); __Pyx_XDECREF(__pyx_t_3); __Pyx_XDECREF(__pyx_t_4); __Pyx_AddTraceback("curated_tokenizers._bbpe.ByteBPEProcessor.__reduce__", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = NULL; __pyx_L0:; __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } /* "curated_tokenizers/_bbpe.pyx":172 * return (unpickle_byte_bpe_processor, (self.vocab, self.merges,)) * * def unpickle_byte_bpe_processor(vocab: Dict[str, int], # <<<<<<<<<<<<<< * merges: List[Tuple[str, str]]) -> ByteBPEProcessor: * return ByteBPEProcessor(vocab, merges) */ /* Python wrapper */ static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_3unpickle_byte_bpe_processor(PyObject *__pyx_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ); /*proto*/ PyDoc_STRVAR(__pyx_doc_18curated_tokenizers_5_bbpe_2unpickle_byte_bpe_processor, "unpickle_byte_bpe_processor(vocab: Dict[str, int], merges: List[Tuple[str, str]]) -> ByteBPEProcessor"); static PyMethodDef __pyx_mdef_18curated_tokenizers_5_bbpe_3unpickle_byte_bpe_processor = {"unpickle_byte_bpe_processor", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_3unpickle_byte_bpe_processor, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_2unpickle_byte_bpe_processor}; static PyObject *__pyx_pw_18curated_tokenizers_5_bbpe_3unpickle_byte_bpe_processor(PyObject *__pyx_self, #if CYTHON_METH_FASTCALL PyObject *const *__pyx_args, Py_ssize_t __pyx_nargs, PyObject *__pyx_kwds #else PyObject *__pyx_args, PyObject *__pyx_kwds #endif ) { PyObject *__pyx_v_vocab = 0; PyObject *__pyx_v_merges = 0; #if !CYTHON_METH_FASTCALL CYTHON_UNUSED Py_ssize_t __pyx_nargs; #endif CYTHON_UNUSED PyObject *const *__pyx_kwvalues; PyObject* values[2] = {0,0}; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; PyObject *__pyx_r = 0; __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("unpickle_byte_bpe_processor (wrapper)", 0); #if !CYTHON_METH_FASTCALL #if CYTHON_ASSUME_SAFE_MACROS __pyx_nargs = PyTuple_GET_SIZE(__pyx_args); #else __pyx_nargs = PyTuple_Size(__pyx_args); if (unlikely(__pyx_nargs < 0)) return NULL; #endif #endif __pyx_kwvalues = __Pyx_KwValues_FASTCALL(__pyx_args, __pyx_nargs); { PyObject **__pyx_pyargnames[] = {&__pyx_n_s_vocab,&__pyx_n_s_merges,0}; if (__pyx_kwds) { Py_ssize_t kw_args; switch (__pyx_nargs) { case 2: values[1] = __Pyx_Arg_FASTCALL(__pyx_args, 1); CYTHON_FALLTHROUGH; case 1: values[0] = __Pyx_Arg_FASTCALL(__pyx_args, 0); CYTHON_FALLTHROUGH; case 0: break; default: goto __pyx_L5_argtuple_error; } kw_args = __Pyx_NumKwargs_FASTCALL(__pyx_kwds); switch (__pyx_nargs) { case 0: if (likely((values[0] = __Pyx_GetKwValue_FASTCALL(__pyx_kwds, __pyx_kwvalues, __pyx_n_s_vocab)) != 0)) { (void)__Pyx_Arg_NewRef_FASTCALL(values[0]); kw_args--; } else if (unlikely(PyErr_Occurred())) __PYX_ERR(0, 172, __pyx_L3_error) else goto __pyx_L5_argtuple_error; CYTHON_FALLTHROUGH; case 1: if (likely((values[1] = __Pyx_GetKwValue_FASTCALL(__pyx_kwds, __pyx_kwvalues, __pyx_n_s_merges)) != 0)) { (void)__Pyx_Arg_NewRef_FASTCALL(values[1]); kw_args--; } else if (unlikely(PyErr_Occurred())) __PYX_ERR(0, 172, __pyx_L3_error) else { __Pyx_RaiseArgtupleInvalid("unpickle_byte_bpe_processor", 1, 2, 2, 1); __PYX_ERR(0, 172, __pyx_L3_error) } } if (unlikely(kw_args > 0)) { const Py_ssize_t kwd_pos_args = __pyx_nargs; if (unlikely(__Pyx_ParseOptionalKeywords(__pyx_kwds, __pyx_kwvalues, __pyx_pyargnames, 0, values + 0, kwd_pos_args, "unpickle_byte_bpe_processor") < 0)) __PYX_ERR(0, 172, __pyx_L3_error) } } else if (unlikely(__pyx_nargs != 2)) { goto __pyx_L5_argtuple_error; } else { values[0] = __Pyx_Arg_FASTCALL(__pyx_args, 0); values[1] = __Pyx_Arg_FASTCALL(__pyx_args, 1); } __pyx_v_vocab = values[0]; __pyx_v_merges = values[1]; } goto __pyx_L6_skip; __pyx_L5_argtuple_error:; __Pyx_RaiseArgtupleInvalid("unpickle_byte_bpe_processor", 1, 2, 2, __pyx_nargs); __PYX_ERR(0, 172, __pyx_L3_error) __pyx_L6_skip:; goto __pyx_L4_argument_unpacking_done; __pyx_L3_error:; { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < (Py_ssize_t)(sizeof(values)/sizeof(values[0])); ++__pyx_temp) { __Pyx_Arg_XDECREF_FASTCALL(values[__pyx_temp]); } } __Pyx_AddTraceback("curated_tokenizers._bbpe.unpickle_byte_bpe_processor", __pyx_clineno, __pyx_lineno, __pyx_filename); __Pyx_RefNannyFinishContext(); return NULL; __pyx_L4_argument_unpacking_done:; __pyx_r = __pyx_pf_18curated_tokenizers_5_bbpe_2unpickle_byte_bpe_processor(__pyx_self, __pyx_v_vocab, __pyx_v_merges); /* function exit code */ { Py_ssize_t __pyx_temp; for (__pyx_temp=0; __pyx_temp < (Py_ssize_t)(sizeof(values)/sizeof(values[0])); ++__pyx_temp) { __Pyx_Arg_XDECREF_FASTCALL(values[__pyx_temp]); } } __Pyx_RefNannyFinishContext(); return __pyx_r; } static PyObject *__pyx_pf_18curated_tokenizers_5_bbpe_2unpickle_byte_bpe_processor(CYTHON_UNUSED PyObject *__pyx_self, PyObject *__pyx_v_vocab, PyObject *__pyx_v_merges) { PyObject *__pyx_r = NULL; __Pyx_RefNannyDeclarations PyObject *__pyx_t_1 = NULL; PyObject *__pyx_t_2 = NULL; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("unpickle_byte_bpe_processor", 1); /* "curated_tokenizers/_bbpe.pyx":174 * def unpickle_byte_bpe_processor(vocab: Dict[str, int], * merges: List[Tuple[str, str]]) -> ByteBPEProcessor: * return ByteBPEProcessor(vocab, merges) # <<<<<<<<<<<<<< */ __Pyx_XDECREF(__pyx_r); __pyx_t_1 = PyTuple_New(2); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 174, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_1); __Pyx_INCREF(__pyx_v_vocab); __Pyx_GIVEREF(__pyx_v_vocab); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_1, 0, __pyx_v_vocab)) __PYX_ERR(0, 174, __pyx_L1_error); __Pyx_INCREF(__pyx_v_merges); __Pyx_GIVEREF(__pyx_v_merges); if (__Pyx_PyTuple_SET_ITEM(__pyx_t_1, 1, __pyx_v_merges)) __PYX_ERR(0, 174, __pyx_L1_error); __pyx_t_2 = __Pyx_PyObject_Call(((PyObject *)__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor), __pyx_t_1, NULL); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 174, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0; __pyx_r = __pyx_t_2; __pyx_t_2 = 0; goto __pyx_L0; /* "curated_tokenizers/_bbpe.pyx":172 * return (unpickle_byte_bpe_processor, (self.vocab, self.merges,)) * * def unpickle_byte_bpe_processor(vocab: Dict[str, int], # <<<<<<<<<<<<<< * merges: List[Tuple[str, str]]) -> ByteBPEProcessor: * return ByteBPEProcessor(vocab, merges) */ /* function exit code */ __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_1); __Pyx_XDECREF(__pyx_t_2); __Pyx_AddTraceback("curated_tokenizers._bbpe.unpickle_byte_bpe_processor", __pyx_clineno, __pyx_lineno, __pyx_filename); __pyx_r = NULL; __pyx_L0:; __Pyx_XGIVEREF(__pyx_r); __Pyx_RefNannyFinishContext(); return __pyx_r; } static PyObject *__pyx_tp_new_18curated_tokenizers_5_bbpe_ByteBPEProcessor(PyTypeObject *t, CYTHON_UNUSED PyObject *a, CYTHON_UNUSED PyObject *k) { struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *p; PyObject *o; #if CYTHON_COMPILING_IN_LIMITED_API allocfunc alloc_func = (allocfunc)PyType_GetSlot(t, Py_tp_alloc); o = alloc_func(t, 0); #else if (likely(!__Pyx_PyType_HasFeature(t, Py_TPFLAGS_IS_ABSTRACT))) { o = (*t->tp_alloc)(t, 0); } else { o = (PyObject *) PyBaseObject_Type.tp_new(t, __pyx_empty_tuple, 0); } if (unlikely(!o)) return 0; #endif p = ((struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *)o); new((void*)&(p->_merges)) std::shared_ptr (); p->_byte_decoder = ((PyObject*)Py_None); Py_INCREF(Py_None); p->_byte_encoder = ((PyObject*)Py_None); Py_INCREF(Py_None); p->_split_pattern = Py_None; Py_INCREF(Py_None); p->_piece_to_id = ((PyObject*)Py_None); Py_INCREF(Py_None); p->_id_to_piece = ((PyObject*)Py_None); Py_INCREF(Py_None); return o; } static void __pyx_tp_dealloc_18curated_tokenizers_5_bbpe_ByteBPEProcessor(PyObject *o) { struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *p = (struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *)o; #if CYTHON_USE_TP_FINALIZE if (unlikely((PY_VERSION_HEX >= 0x03080000 || __Pyx_PyType_HasFeature(Py_TYPE(o), Py_TPFLAGS_HAVE_FINALIZE)) && __Pyx_PyObject_GetSlot(o, tp_finalize, destructor)) && !__Pyx_PyObject_GC_IsFinalized(o)) { if (__Pyx_PyObject_GetSlot(o, tp_dealloc, destructor) == __pyx_tp_dealloc_18curated_tokenizers_5_bbpe_ByteBPEProcessor) { if (PyObject_CallFinalizerFromDealloc(o)) return; } } #endif PyObject_GC_UnTrack(o); __Pyx_call_destructor(p->_merges); Py_CLEAR(p->_byte_decoder); Py_CLEAR(p->_byte_encoder); Py_CLEAR(p->_split_pattern); Py_CLEAR(p->_piece_to_id); Py_CLEAR(p->_id_to_piece); #if CYTHON_USE_TYPE_SLOTS || CYTHON_COMPILING_IN_PYPY (*Py_TYPE(o)->tp_free)(o); #else { freefunc tp_free = (freefunc)PyType_GetSlot(Py_TYPE(o), Py_tp_free); if (tp_free) tp_free(o); } #endif } static int __pyx_tp_traverse_18curated_tokenizers_5_bbpe_ByteBPEProcessor(PyObject *o, visitproc v, void *a) { int e; struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *p = (struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *)o; if (p->_byte_decoder) { e = (*v)(p->_byte_decoder, a); if (e) return e; } if (p->_byte_encoder) { e = (*v)(p->_byte_encoder, a); if (e) return e; } if (p->_split_pattern) { e = (*v)(p->_split_pattern, a); if (e) return e; } if (p->_piece_to_id) { e = (*v)(p->_piece_to_id, a); if (e) return e; } if (p->_id_to_piece) { e = (*v)(p->_id_to_piece, a); if (e) return e; } return 0; } static int __pyx_tp_clear_18curated_tokenizers_5_bbpe_ByteBPEProcessor(PyObject *o) { PyObject* tmp; struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *p = (struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor *)o; tmp = ((PyObject*)p->_byte_decoder); p->_byte_decoder = ((PyObject*)Py_None); Py_INCREF(Py_None); Py_XDECREF(tmp); tmp = ((PyObject*)p->_byte_encoder); p->_byte_encoder = ((PyObject*)Py_None); Py_INCREF(Py_None); Py_XDECREF(tmp); tmp = ((PyObject*)p->_split_pattern); p->_split_pattern = Py_None; Py_INCREF(Py_None); Py_XDECREF(tmp); tmp = ((PyObject*)p->_piece_to_id); p->_piece_to_id = ((PyObject*)Py_None); Py_INCREF(Py_None); Py_XDECREF(tmp); tmp = ((PyObject*)p->_id_to_piece); p->_id_to_piece = ((PyObject*)Py_None); Py_INCREF(Py_None); Py_XDECREF(tmp); return 0; } static PyObject *__pyx_getprop_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_merges(PyObject *o, CYTHON_UNUSED void *x) { return __pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_6merges_1__get__(o); } static PyObject *__pyx_getprop_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_vocab(PyObject *o, CYTHON_UNUSED void *x) { return __pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_5vocab_1__get__(o); } static PyMethodDef __pyx_methods_18curated_tokenizers_5_bbpe_ByteBPEProcessor[] = { {"__copy__", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_3__copy__, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_2__copy__}, {"__deepcopy__", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_5__deepcopy__, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_4__deepcopy__}, {"load_from_files", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_7load_from_files, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_6load_from_files}, {"decode_from_ids", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_9decode_from_ids, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_8decode_from_ids}, {"encode", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_11encode, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_10encode}, {"encode_as_ids", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_13encode_as_ids, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_12encode_as_ids}, {"encode_as_pieces", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_15encode_as_pieces, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_14encode_as_pieces}, {"piece_id", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_17piece_id, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_16piece_id}, {"_pieces_to_ids", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_19_pieces_to_ids, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_18_pieces_to_ids}, {"__reduce__", (PyCFunction)(void*)(__Pyx_PyCFunction_FastCallWithKeywords)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_21__reduce__, __Pyx_METH_FASTCALL|METH_KEYWORDS, __pyx_doc_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_20__reduce__}, {0, 0, 0, 0} }; static struct PyGetSetDef __pyx_getsets_18curated_tokenizers_5_bbpe_ByteBPEProcessor[] = { {(char *)"merges", __pyx_getprop_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_merges, 0, (char *)PyDoc_STR("ByteBPEProcessor.merges: List[Tuple[str, str]]\nGet all merges."), 0}, {(char *)"vocab", __pyx_getprop_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_vocab, 0, (char *)PyDoc_STR("ByteBPEProcessor.vocab: Dict[str, int]\nGet a copy of the vocabulary."), 0}, {0, 0, 0, 0, 0} }; #if CYTHON_USE_TYPE_SPECS static PyType_Slot __pyx_type_18curated_tokenizers_5_bbpe_ByteBPEProcessor_slots[] = { {Py_tp_dealloc, (void *)__pyx_tp_dealloc_18curated_tokenizers_5_bbpe_ByteBPEProcessor}, {Py_tp_doc, (void *)PyDoc_STR("ByteBPEProcessor(vocab: Dict[str, int], merges: List[Tuple[str, str]])")}, {Py_tp_traverse, (void *)__pyx_tp_traverse_18curated_tokenizers_5_bbpe_ByteBPEProcessor}, {Py_tp_clear, (void *)__pyx_tp_clear_18curated_tokenizers_5_bbpe_ByteBPEProcessor}, {Py_tp_methods, (void *)__pyx_methods_18curated_tokenizers_5_bbpe_ByteBPEProcessor}, {Py_tp_getset, (void *)__pyx_getsets_18curated_tokenizers_5_bbpe_ByteBPEProcessor}, {Py_tp_init, (void *)__pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_1__init__}, {Py_tp_new, (void *)__pyx_tp_new_18curated_tokenizers_5_bbpe_ByteBPEProcessor}, {0, 0}, }; static PyType_Spec __pyx_type_18curated_tokenizers_5_bbpe_ByteBPEProcessor_spec = { "curated_tokenizers._bbpe.ByteBPEProcessor", sizeof(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor), 0, Py_TPFLAGS_DEFAULT|Py_TPFLAGS_HAVE_VERSION_TAG|Py_TPFLAGS_CHECKTYPES|Py_TPFLAGS_HAVE_NEWBUFFER|Py_TPFLAGS_BASETYPE|Py_TPFLAGS_HAVE_GC, __pyx_type_18curated_tokenizers_5_bbpe_ByteBPEProcessor_slots, }; #else static PyTypeObject __pyx_type_18curated_tokenizers_5_bbpe_ByteBPEProcessor = { PyVarObject_HEAD_INIT(0, 0) "curated_tokenizers._bbpe.""ByteBPEProcessor", /*tp_name*/ sizeof(struct __pyx_obj_18curated_tokenizers_5_bbpe_ByteBPEProcessor), /*tp_basicsize*/ 0, /*tp_itemsize*/ __pyx_tp_dealloc_18curated_tokenizers_5_bbpe_ByteBPEProcessor, /*tp_dealloc*/ #if PY_VERSION_HEX < 0x030800b4 0, /*tp_print*/ #endif #if PY_VERSION_HEX >= 0x030800b4 0, /*tp_vectorcall_offset*/ #endif 0, /*tp_getattr*/ 0, /*tp_setattr*/ #if PY_MAJOR_VERSION < 3 0, /*tp_compare*/ #endif #if PY_MAJOR_VERSION >= 3 0, /*tp_as_async*/ #endif 0, /*tp_repr*/ 0, /*tp_as_number*/ 0, /*tp_as_sequence*/ 0, /*tp_as_mapping*/ 0, /*tp_hash*/ 0, /*tp_call*/ 0, /*tp_str*/ 0, /*tp_getattro*/ 0, /*tp_setattro*/ 0, /*tp_as_buffer*/ Py_TPFLAGS_DEFAULT|Py_TPFLAGS_HAVE_VERSION_TAG|Py_TPFLAGS_CHECKTYPES|Py_TPFLAGS_HAVE_NEWBUFFER|Py_TPFLAGS_BASETYPE|Py_TPFLAGS_HAVE_GC, /*tp_flags*/ PyDoc_STR("ByteBPEProcessor(vocab: Dict[str, int], merges: List[Tuple[str, str]])"), /*tp_doc*/ __pyx_tp_traverse_18curated_tokenizers_5_bbpe_ByteBPEProcessor, /*tp_traverse*/ __pyx_tp_clear_18curated_tokenizers_5_bbpe_ByteBPEProcessor, /*tp_clear*/ 0, /*tp_richcompare*/ 0, /*tp_weaklistoffset*/ 0, /*tp_iter*/ 0, /*tp_iternext*/ __pyx_methods_18curated_tokenizers_5_bbpe_ByteBPEProcessor, /*tp_methods*/ 0, /*tp_members*/ __pyx_getsets_18curated_tokenizers_5_bbpe_ByteBPEProcessor, /*tp_getset*/ 0, /*tp_base*/ 0, /*tp_dict*/ 0, /*tp_descr_get*/ 0, /*tp_descr_set*/ #if !CYTHON_USE_TYPE_SPECS 0, /*tp_dictoffset*/ #endif __pyx_pw_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_1__init__, /*tp_init*/ 0, /*tp_alloc*/ __pyx_tp_new_18curated_tokenizers_5_bbpe_ByteBPEProcessor, /*tp_new*/ 0, /*tp_free*/ 0, /*tp_is_gc*/ 0, /*tp_bases*/ 0, /*tp_mro*/ 0, /*tp_cache*/ 0, /*tp_subclasses*/ 0, /*tp_weaklist*/ 0, /*tp_del*/ 0, /*tp_version_tag*/ #if PY_VERSION_HEX >= 0x030400a1 #if CYTHON_USE_TP_FINALIZE 0, /*tp_finalize*/ #else NULL, /*tp_finalize*/ #endif #endif #if PY_VERSION_HEX >= 0x030800b1 && (!CYTHON_COMPILING_IN_PYPY || PYPY_VERSION_NUM >= 0x07030800) 0, /*tp_vectorcall*/ #endif #if __PYX_NEED_TP_PRINT_SLOT == 1 0, /*tp_print*/ #endif #if PY_VERSION_HEX >= 0x030C0000 0, /*tp_watched*/ #endif #if CYTHON_COMPILING_IN_PYPY && PY_VERSION_HEX >= 0x03090000 && PY_VERSION_HEX < 0x030a0000 0, /*tp_pypy_flags*/ #endif }; #endif static struct __pyx_obj_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr *__pyx_freelist_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr[8]; static int __pyx_freecount_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr = 0; static PyObject *__pyx_tp_new_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr(PyTypeObject *t, CYTHON_UNUSED PyObject *a, CYTHON_UNUSED PyObject *k) { struct __pyx_obj_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr *p; PyObject *o; #if CYTHON_COMPILING_IN_LIMITED_API allocfunc alloc_func = (allocfunc)PyType_GetSlot(t, Py_tp_alloc); o = alloc_func(t, 0); #else #if CYTHON_COMPILING_IN_CPYTHON if (likely((int)(__pyx_freecount_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr > 0) & (int)(t->tp_basicsize == sizeof(struct __pyx_obj_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr)))) { o = (PyObject*)__pyx_freelist_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr[--__pyx_freecount_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr]; memset(o, 0, sizeof(struct __pyx_obj_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr)); (void) PyObject_INIT(o, t); } else #endif { o = (*t->tp_alloc)(t, 0); if (unlikely(!o)) return 0; } #endif p = ((struct __pyx_obj_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr *)o); new((void*)&(p->__pyx_genexpr_arg_0)) std::vector (); new((void*)&(p->__pyx_v_merge)) std::string(); new((void*)&(p->__pyx_t_0)) std::vector ::iterator(); return o; } static void __pyx_tp_dealloc_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr(PyObject *o) { struct __pyx_obj_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr *p = (struct __pyx_obj_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr *)o; #if CYTHON_USE_TP_FINALIZE if (unlikely((PY_VERSION_HEX >= 0x03080000 || __Pyx_PyType_HasFeature(Py_TYPE(o), Py_TPFLAGS_HAVE_FINALIZE)) && __Pyx_PyObject_GetSlot(o, tp_finalize, destructor)) && (!PyType_IS_GC(Py_TYPE(o)) || !__Pyx_PyObject_GC_IsFinalized(o))) { if (__Pyx_PyObject_GetSlot(o, tp_dealloc, destructor) == __pyx_tp_dealloc_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr) { if (PyObject_CallFinalizerFromDealloc(o)) return; } } #endif __Pyx_call_destructor(p->__pyx_genexpr_arg_0); __Pyx_call_destructor(p->__pyx_v_merge); __Pyx_call_destructor(p->__pyx_t_0); #if CYTHON_COMPILING_IN_CPYTHON if (((int)(__pyx_freecount_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr < 8) & (int)(Py_TYPE(o)->tp_basicsize == sizeof(struct __pyx_obj_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr)))) { __pyx_freelist_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr[__pyx_freecount_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr++] = ((struct __pyx_obj_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr *)o); } else #endif { #if CYTHON_USE_TYPE_SLOTS || CYTHON_COMPILING_IN_PYPY (*Py_TYPE(o)->tp_free)(o); #else { freefunc tp_free = (freefunc)PyType_GetSlot(Py_TYPE(o), Py_tp_free); if (tp_free) tp_free(o); } #endif } } #if CYTHON_USE_TYPE_SPECS static PyType_Slot __pyx_type_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr_slots[] = { {Py_tp_dealloc, (void *)__pyx_tp_dealloc_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr}, {Py_tp_new, (void *)__pyx_tp_new_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr}, {0, 0}, }; static PyType_Spec __pyx_type_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr_spec = { "curated_tokenizers._bbpe.__pyx_scope_struct__genexpr", sizeof(struct __pyx_obj_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr), 0, Py_TPFLAGS_DEFAULT|Py_TPFLAGS_HAVE_VERSION_TAG|Py_TPFLAGS_CHECKTYPES|Py_TPFLAGS_HAVE_NEWBUFFER|Py_TPFLAGS_HAVE_FINALIZE, __pyx_type_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr_slots, }; #else static PyTypeObject __pyx_type_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr = { PyVarObject_HEAD_INIT(0, 0) "curated_tokenizers._bbpe.""__pyx_scope_struct__genexpr", /*tp_name*/ sizeof(struct __pyx_obj_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr), /*tp_basicsize*/ 0, /*tp_itemsize*/ __pyx_tp_dealloc_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr, /*tp_dealloc*/ #if PY_VERSION_HEX < 0x030800b4 0, /*tp_print*/ #endif #if PY_VERSION_HEX >= 0x030800b4 0, /*tp_vectorcall_offset*/ #endif 0, /*tp_getattr*/ 0, /*tp_setattr*/ #if PY_MAJOR_VERSION < 3 0, /*tp_compare*/ #endif #if PY_MAJOR_VERSION >= 3 0, /*tp_as_async*/ #endif 0, /*tp_repr*/ 0, /*tp_as_number*/ 0, /*tp_as_sequence*/ 0, /*tp_as_mapping*/ 0, /*tp_hash*/ 0, /*tp_call*/ 0, /*tp_str*/ 0, /*tp_getattro*/ 0, /*tp_setattro*/ 0, /*tp_as_buffer*/ Py_TPFLAGS_DEFAULT|Py_TPFLAGS_HAVE_VERSION_TAG|Py_TPFLAGS_CHECKTYPES|Py_TPFLAGS_HAVE_NEWBUFFER|Py_TPFLAGS_HAVE_FINALIZE, /*tp_flags*/ 0, /*tp_doc*/ 0, /*tp_traverse*/ 0, /*tp_clear*/ 0, /*tp_richcompare*/ 0, /*tp_weaklistoffset*/ 0, /*tp_iter*/ 0, /*tp_iternext*/ 0, /*tp_methods*/ 0, /*tp_members*/ 0, /*tp_getset*/ 0, /*tp_base*/ 0, /*tp_dict*/ 0, /*tp_descr_get*/ 0, /*tp_descr_set*/ #if !CYTHON_USE_TYPE_SPECS 0, /*tp_dictoffset*/ #endif 0, /*tp_init*/ 0, /*tp_alloc*/ __pyx_tp_new_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr, /*tp_new*/ 0, /*tp_free*/ 0, /*tp_is_gc*/ 0, /*tp_bases*/ 0, /*tp_mro*/ 0, /*tp_cache*/ 0, /*tp_subclasses*/ 0, /*tp_weaklist*/ 0, /*tp_del*/ 0, /*tp_version_tag*/ #if PY_VERSION_HEX >= 0x030400a1 #if CYTHON_USE_TP_FINALIZE 0, /*tp_finalize*/ #else NULL, /*tp_finalize*/ #endif #endif #if PY_VERSION_HEX >= 0x030800b1 && (!CYTHON_COMPILING_IN_PYPY || PYPY_VERSION_NUM >= 0x07030800) 0, /*tp_vectorcall*/ #endif #if __PYX_NEED_TP_PRINT_SLOT == 1 0, /*tp_print*/ #endif #if PY_VERSION_HEX >= 0x030C0000 0, /*tp_watched*/ #endif #if CYTHON_COMPILING_IN_PYPY && PY_VERSION_HEX >= 0x03090000 && PY_VERSION_HEX < 0x030a0000 0, /*tp_pypy_flags*/ #endif }; #endif static PyMethodDef __pyx_methods[] = { {0, 0, 0, 0} }; #ifndef CYTHON_SMALL_CODE #if defined(__clang__) #define CYTHON_SMALL_CODE #elif defined(__GNUC__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 3)) #define CYTHON_SMALL_CODE __attribute__((cold)) #else #define CYTHON_SMALL_CODE #endif #endif /* #### Code section: pystring_table ### */ static int __Pyx_CreateStringTabAndInitStrings(void) { __Pyx_StringTabEntry __pyx_string_tab[] = { {&__pyx_n_s_ByteBPEProcessor, __pyx_k_ByteBPEProcessor, sizeof(__pyx_k_ByteBPEProcessor), 0, 0, 1, 1}, {&__pyx_n_s_ByteBPEProcessor___copy, __pyx_k_ByteBPEProcessor___copy, sizeof(__pyx_k_ByteBPEProcessor___copy), 0, 0, 1, 1}, {&__pyx_n_s_ByteBPEProcessor___deepcopy, __pyx_k_ByteBPEProcessor___deepcopy, sizeof(__pyx_k_ByteBPEProcessor___deepcopy), 0, 0, 1, 1}, {&__pyx_n_s_ByteBPEProcessor___reduce, __pyx_k_ByteBPEProcessor___reduce, sizeof(__pyx_k_ByteBPEProcessor___reduce), 0, 0, 1, 1}, {&__pyx_n_s_ByteBPEProcessor__pieces_to_ids, __pyx_k_ByteBPEProcessor__pieces_to_ids, sizeof(__pyx_k_ByteBPEProcessor__pieces_to_ids), 0, 0, 1, 1}, {&__pyx_n_s_ByteBPEProcessor_decode_from_ids, __pyx_k_ByteBPEProcessor_decode_from_ids, sizeof(__pyx_k_ByteBPEProcessor_decode_from_ids), 0, 0, 1, 1}, {&__pyx_n_s_ByteBPEProcessor_encode, __pyx_k_ByteBPEProcessor_encode, sizeof(__pyx_k_ByteBPEProcessor_encode), 0, 0, 1, 1}, {&__pyx_n_s_ByteBPEProcessor_encode_as_ids, __pyx_k_ByteBPEProcessor_encode_as_ids, sizeof(__pyx_k_ByteBPEProcessor_encode_as_ids), 0, 0, 1, 1}, {&__pyx_n_s_ByteBPEProcessor_encode_as_piece, __pyx_k_ByteBPEProcessor_encode_as_piece, sizeof(__pyx_k_ByteBPEProcessor_encode_as_piece), 0, 0, 1, 1}, {&__pyx_n_s_ByteBPEProcessor_load_from_files, __pyx_k_ByteBPEProcessor_load_from_files, sizeof(__pyx_k_ByteBPEProcessor_load_from_files), 0, 0, 1, 1}, {&__pyx_n_s_ByteBPEProcessor_piece_id, __pyx_k_ByteBPEProcessor_piece_id, sizeof(__pyx_k_ByteBPEProcessor_piece_id), 0, 0, 1, 1}, {&__pyx_n_s_BytesIO, __pyx_k_BytesIO, sizeof(__pyx_k_BytesIO), 0, 0, 1, 1}, {&__pyx_n_s_Dict, __pyx_k_Dict, sizeof(__pyx_k_Dict), 0, 0, 1, 1}, {&__pyx_kp_s_Dict_int_bytes, __pyx_k_Dict_int_bytes, sizeof(__pyx_k_Dict_int_bytes), 0, 0, 1, 0}, {&__pyx_kp_s_Dict_str_int, __pyx_k_Dict_str_int, sizeof(__pyx_k_Dict_str_int), 0, 0, 1, 0}, {&__pyx_n_s_Iterable, __pyx_k_Iterable, sizeof(__pyx_k_Iterable), 0, 0, 1, 1}, {&__pyx_kp_s_Iterable_int, __pyx_k_Iterable_int, sizeof(__pyx_k_Iterable_int), 0, 0, 1, 0}, {&__pyx_n_s_List, __pyx_k_List, sizeof(__pyx_k_List), 0, 0, 1, 1}, {&__pyx_kp_s_List_Tuple_str_str, __pyx_k_List_Tuple_str_str, sizeof(__pyx_k_List_Tuple_str_str), 0, 0, 1, 0}, {&__pyx_kp_s_List_int, __pyx_k_List_int, sizeof(__pyx_k_List_int), 0, 0, 1, 0}, {&__pyx_kp_s_List_str, __pyx_k_List_str, sizeof(__pyx_k_List_str), 0, 0, 1, 0}, {&__pyx_kp_u_Merge_must_consist_of_2_items_wa, __pyx_k_Merge_must_consist_of_2_items_wa, sizeof(__pyx_k_Merge_must_consist_of_2_items_wa), 0, 1, 0, 0}, {&__pyx_kp_u_Only_version_0_2_of_the_merges_f, __pyx_k_Only_version_0_2_of_the_merges_f, sizeof(__pyx_k_Only_version_0_2_of_the_merges_f), 0, 1, 0, 0}, {&__pyx_n_s_Optional, __pyx_k_Optional, sizeof(__pyx_k_Optional), 0, 0, 1, 1}, {&__pyx_kp_s_Optional_int, __pyx_k_Optional_int, sizeof(__pyx_k_Optional_int), 0, 0, 1, 0}, {&__pyx_n_s_Path, __pyx_k_Path, sizeof(__pyx_k_Path), 0, 0, 1, 1}, {&__pyx_kp_u_Piece_is_not_in_vocabulary, __pyx_k_Piece_is_not_in_vocabulary, sizeof(__pyx_k_Piece_is_not_in_vocabulary), 0, 1, 0, 0}, {&__pyx_n_s_SPLIT_PATTERN, __pyx_k_SPLIT_PATTERN, sizeof(__pyx_k_SPLIT_PATTERN), 0, 0, 1, 1}, {&__pyx_n_s_Tuple, __pyx_k_Tuple, sizeof(__pyx_k_Tuple), 0, 0, 1, 1}, {&__pyx_kp_s_Tuple_List_int_List_str, __pyx_k_Tuple_List_int_List_str, sizeof(__pyx_k_Tuple_List_int_List_str), 0, 0, 1, 0}, {&__pyx_kp_u_Unknown_piece_identifier, __pyx_k_Unknown_piece_identifier, sizeof(__pyx_k_Unknown_piece_identifier), 0, 1, 0, 0}, {&__pyx_n_s_ValueError, __pyx_k_ValueError, sizeof(__pyx_k_ValueError), 0, 0, 1, 1}, {&__pyx_kp_s__2, __pyx_k__2, sizeof(__pyx_k__2), 0, 0, 1, 0}, {&__pyx_n_s__28, __pyx_k__28, sizeof(__pyx_k__28), 0, 0, 1, 1}, {&__pyx_kp_u__3, __pyx_k__3, sizeof(__pyx_k__3), 0, 1, 0, 0}, {&__pyx_kp_u__4, __pyx_k__4, sizeof(__pyx_k__4), 0, 1, 0, 0}, {&__pyx_n_s__5, __pyx_k__5, sizeof(__pyx_k__5), 0, 0, 1, 1}, {&__pyx_n_s_append, __pyx_k_append, sizeof(__pyx_k_append), 0, 0, 1, 1}, {&__pyx_n_s_args, __pyx_k_args, sizeof(__pyx_k_args), 0, 0, 1, 1}, {&__pyx_n_s_asyncio_coroutines, __pyx_k_asyncio_coroutines, sizeof(__pyx_k_asyncio_coroutines), 0, 0, 1, 1}, {&__pyx_n_s_b, __pyx_k_b, sizeof(__pyx_k_b), 0, 0, 1, 1}, {&__pyx_n_s_bs, __pyx_k_bs, sizeof(__pyx_k_bs), 0, 0, 1, 1}, {&__pyx_n_s_bytes_to_unicode, __pyx_k_bytes_to_unicode, sizeof(__pyx_k_bytes_to_unicode), 0, 0, 1, 1}, {&__pyx_n_s_chr, __pyx_k_chr, sizeof(__pyx_k_chr), 0, 0, 1, 1}, {&__pyx_n_s_cline_in_traceback, __pyx_k_cline_in_traceback, sizeof(__pyx_k_cline_in_traceback), 0, 0, 1, 1}, {&__pyx_n_s_close, __pyx_k_close, sizeof(__pyx_k_close), 0, 0, 1, 1}, {&__pyx_n_s_compile, __pyx_k_compile, sizeof(__pyx_k_compile), 0, 0, 1, 1}, {&__pyx_n_s_copy, __pyx_k_copy, sizeof(__pyx_k_copy), 0, 0, 1, 1}, {&__pyx_n_s_cp, __pyx_k_cp, sizeof(__pyx_k_cp), 0, 0, 1, 1}, {&__pyx_n_s_cs, __pyx_k_cs, sizeof(__pyx_k_cs), 0, 0, 1, 1}, {&__pyx_n_s_curated_tokenizers__bbpe, __pyx_k_curated_tokenizers__bbpe, sizeof(__pyx_k_curated_tokenizers__bbpe), 0, 0, 1, 1}, {&__pyx_kp_s_curated_tokenizers__bbpe_pyx, __pyx_k_curated_tokenizers__bbpe_pyx, sizeof(__pyx_k_curated_tokenizers__bbpe_pyx), 0, 0, 1, 0}, {&__pyx_n_s_decode, __pyx_k_decode, sizeof(__pyx_k_decode), 0, 0, 1, 1}, {&__pyx_n_s_decode_from_ids, __pyx_k_decode_from_ids, sizeof(__pyx_k_decode_from_ids), 0, 0, 1, 1}, {&__pyx_n_s_decoded, __pyx_k_decoded, sizeof(__pyx_k_decoded), 0, 0, 1, 1}, {&__pyx_n_s_deepcopy, __pyx_k_deepcopy, sizeof(__pyx_k_deepcopy), 0, 0, 1, 1}, {&__pyx_n_s_dict, __pyx_k_dict, sizeof(__pyx_k_dict), 0, 0, 1, 1}, {&__pyx_kp_u_disable, __pyx_k_disable, sizeof(__pyx_k_disable), 0, 1, 0, 0}, {&__pyx_kp_u_enable, __pyx_k_enable, sizeof(__pyx_k_enable), 0, 1, 0, 0}, {&__pyx_n_s_encode, __pyx_k_encode, sizeof(__pyx_k_encode), 0, 0, 1, 1}, {&__pyx_n_s_encode_as_ids, __pyx_k_encode_as_ids, sizeof(__pyx_k_encode_as_ids), 0, 0, 1, 1}, {&__pyx_n_s_encode_as_pieces, __pyx_k_encode_as_pieces, sizeof(__pyx_k_encode_as_pieces), 0, 0, 1, 1}, {&__pyx_n_s_encode_as_pieces_locals_genexpr, __pyx_k_encode_as_pieces_locals_genexpr, sizeof(__pyx_k_encode_as_pieces_locals_genexpr), 0, 0, 1, 1}, {&__pyx_n_s_encoding, __pyx_k_encoding, sizeof(__pyx_k_encoding), 0, 0, 1, 1}, {&__pyx_n_s_enter, __pyx_k_enter, sizeof(__pyx_k_enter), 0, 0, 1, 1}, {&__pyx_n_s_exit, __pyx_k_exit, sizeof(__pyx_k_exit), 0, 0, 1, 1}, {&__pyx_n_s_f, __pyx_k_f, sizeof(__pyx_k_f), 0, 0, 1, 1}, {&__pyx_n_s_findall, __pyx_k_findall, sizeof(__pyx_k_findall), 0, 0, 1, 1}, {&__pyx_n_s_functools, __pyx_k_functools, sizeof(__pyx_k_functools), 0, 0, 1, 1}, {&__pyx_kp_u_gc, __pyx_k_gc, sizeof(__pyx_k_gc), 0, 1, 0, 0}, {&__pyx_n_s_genexpr, __pyx_k_genexpr, sizeof(__pyx_k_genexpr), 0, 0, 1, 1}, {&__pyx_n_s_get, __pyx_k_get, sizeof(__pyx_k_get), 0, 0, 1, 1}, {&__pyx_n_s_getvalue, __pyx_k_getvalue, sizeof(__pyx_k_getvalue), 0, 0, 1, 1}, {&__pyx_n_s_ids, __pyx_k_ids, sizeof(__pyx_k_ids), 0, 0, 1, 1}, {&__pyx_n_s_import, __pyx_k_import, sizeof(__pyx_k_import), 0, 0, 1, 1}, {&__pyx_n_s_initializing, __pyx_k_initializing, sizeof(__pyx_k_initializing), 0, 0, 1, 1}, {&__pyx_n_s_io, __pyx_k_io, sizeof(__pyx_k_io), 0, 0, 1, 1}, {&__pyx_n_s_is_coroutine, __pyx_k_is_coroutine, sizeof(__pyx_k_is_coroutine), 0, 0, 1, 1}, {&__pyx_kp_u_isenabled, __pyx_k_isenabled, sizeof(__pyx_k_isenabled), 0, 1, 0, 0}, {&__pyx_n_s_items, __pyx_k_items, sizeof(__pyx_k_items), 0, 0, 1, 1}, {&__pyx_n_s_json, __pyx_k_json, sizeof(__pyx_k_json), 0, 0, 1, 1}, {&__pyx_n_s_line, __pyx_k_line, sizeof(__pyx_k_line), 0, 0, 1, 1}, {&__pyx_n_s_load, __pyx_k_load, sizeof(__pyx_k_load), 0, 0, 1, 1}, {&__pyx_n_s_load_from_files, __pyx_k_load_from_files, sizeof(__pyx_k_load_from_files), 0, 0, 1, 1}, {&__pyx_n_s_lru_cache, __pyx_k_lru_cache, sizeof(__pyx_k_lru_cache), 0, 0, 1, 1}, {&__pyx_n_s_main, __pyx_k_main, sizeof(__pyx_k_main), 0, 0, 1, 1}, {&__pyx_n_s_memo, __pyx_k_memo, sizeof(__pyx_k_memo), 0, 0, 1, 1}, {&__pyx_n_s_merge, __pyx_k_merge, sizeof(__pyx_k_merge), 0, 0, 1, 1}, {&__pyx_n_s_merged, __pyx_k_merged, sizeof(__pyx_k_merged), 0, 0, 1, 1}, {&__pyx_n_s_merges, __pyx_k_merges, sizeof(__pyx_k_merges), 0, 0, 1, 1}, {&__pyx_n_s_n, __pyx_k_n, sizeof(__pyx_k_n), 0, 0, 1, 1}, {&__pyx_n_s_name, __pyx_k_name, sizeof(__pyx_k_name), 0, 0, 1, 1}, {&__pyx_n_s_open, __pyx_k_open, sizeof(__pyx_k_open), 0, 0, 1, 1}, {&__pyx_n_s_pathlib, __pyx_k_pathlib, sizeof(__pyx_k_pathlib), 0, 0, 1, 1}, {&__pyx_n_s_piece, __pyx_k_piece, sizeof(__pyx_k_piece), 0, 0, 1, 1}, {&__pyx_n_s_piece_id, __pyx_k_piece_id, sizeof(__pyx_k_piece_id), 0, 0, 1, 1}, {&__pyx_n_s_piece_ids, __pyx_k_piece_ids, sizeof(__pyx_k_piece_ids), 0, 0, 1, 1}, {&__pyx_n_s_pieces, __pyx_k_pieces, sizeof(__pyx_k_pieces), 0, 0, 1, 1}, {&__pyx_n_s_pieces_to_ids, __pyx_k_pieces_to_ids, sizeof(__pyx_k_pieces_to_ids), 0, 0, 1, 1}, {&__pyx_n_s_range, __pyx_k_range, sizeof(__pyx_k_range), 0, 0, 1, 1}, {&__pyx_n_s_readline, __pyx_k_readline, sizeof(__pyx_k_readline), 0, 0, 1, 1}, {&__pyx_n_s_reduce, __pyx_k_reduce, sizeof(__pyx_k_reduce), 0, 0, 1, 1}, {&__pyx_n_s_regex, __pyx_k_regex, sizeof(__pyx_k_regex), 0, 0, 1, 1}, {&__pyx_n_s_return, __pyx_k_return, sizeof(__pyx_k_return), 0, 0, 1, 1}, {&__pyx_kp_s_s_t_re_ve_m_ll_d_p_L_p_N_s_p_L, __pyx_k_s_t_re_ve_m_ll_d_p_L_p_N_s_p_L, sizeof(__pyx_k_s_t_re_ve_m_ll_d_p_L_p_N_s_p_L), 0, 0, 1, 0}, {&__pyx_n_s_self, __pyx_k_self, sizeof(__pyx_k_self), 0, 0, 1, 1}, {&__pyx_n_s_send, __pyx_k_send, sizeof(__pyx_k_send), 0, 0, 1, 1}, {&__pyx_n_s_spec, __pyx_k_spec, sizeof(__pyx_k_spec), 0, 0, 1, 1}, {&__pyx_n_s_split, __pyx_k_split, sizeof(__pyx_k_split), 0, 0, 1, 1}, {&__pyx_n_s_startswith, __pyx_k_startswith, sizeof(__pyx_k_startswith), 0, 0, 1, 1}, {&__pyx_n_s_staticmethod, __pyx_k_staticmethod, sizeof(__pyx_k_staticmethod), 0, 0, 1, 1}, {&__pyx_n_s_str, __pyx_k_str, sizeof(__pyx_k_str), 0, 0, 1, 1}, {&__pyx_n_s_strip, __pyx_k_strip, sizeof(__pyx_k_strip), 0, 0, 1, 1}, {&__pyx_n_s_test, __pyx_k_test, sizeof(__pyx_k_test), 0, 0, 1, 1}, {&__pyx_n_s_text, __pyx_k_text, sizeof(__pyx_k_text), 0, 0, 1, 1}, {&__pyx_n_s_throw, __pyx_k_throw, sizeof(__pyx_k_throw), 0, 0, 1, 1}, {&__pyx_n_s_token, __pyx_k_token, sizeof(__pyx_k_token), 0, 0, 1, 1}, {&__pyx_n_s_token_bytes, __pyx_k_token_bytes, sizeof(__pyx_k_token_bytes), 0, 0, 1, 1}, {&__pyx_n_s_typing, __pyx_k_typing, sizeof(__pyx_k_typing), 0, 0, 1, 1}, {&__pyx_n_s_unpickle_byte_bpe_processor, __pyx_k_unpickle_byte_bpe_processor, sizeof(__pyx_k_unpickle_byte_bpe_processor), 0, 0, 1, 1}, {&__pyx_kp_s_utf_8, __pyx_k_utf_8, sizeof(__pyx_k_utf_8), 0, 0, 1, 0}, {&__pyx_n_s_version, __pyx_k_version, sizeof(__pyx_k_version), 0, 0, 1, 1}, {&__pyx_kp_s_version_0_2, __pyx_k_version_0_2, sizeof(__pyx_k_version_0_2), 0, 0, 1, 0}, {&__pyx_n_s_vocab, __pyx_k_vocab, sizeof(__pyx_k_vocab), 0, 0, 1, 1}, {&__pyx_n_s_write, __pyx_k_write, sizeof(__pyx_k_write), 0, 0, 1, 1}, {&__pyx_n_s_zip, __pyx_k_zip, sizeof(__pyx_k_zip), 0, 0, 1, 1}, {0, 0, 0, 0, 0, 0, 0} }; return __Pyx_InitStrings(__pyx_string_tab); } /* #### Code section: cached_builtins ### */ static CYTHON_SMALL_CODE int __Pyx_InitCachedBuiltins(void) { __pyx_builtin_staticmethod = __Pyx_GetBuiltinName(__pyx_n_s_staticmethod); if (!__pyx_builtin_staticmethod) __PYX_ERR(0, 77, __pyx_L1_error) __pyx_builtin_range = __Pyx_GetBuiltinName(__pyx_n_s_range); if (!__pyx_builtin_range) __PYX_ERR(0, 36, __pyx_L1_error) __pyx_builtin_chr = __Pyx_GetBuiltinName(__pyx_n_s_chr); if (!__pyx_builtin_chr) __PYX_ERR(0, 47, __pyx_L1_error) __pyx_builtin_zip = __Pyx_GetBuiltinName(__pyx_n_s_zip); if (!__pyx_builtin_zip) __PYX_ERR(0, 48, __pyx_L1_error) __pyx_builtin_open = __Pyx_GetBuiltinName(__pyx_n_s_open); if (!__pyx_builtin_open) __PYX_ERR(0, 80, __pyx_L1_error) __pyx_builtin_ValueError = __Pyx_GetBuiltinName(__pyx_n_s_ValueError); if (!__pyx_builtin_ValueError) __PYX_ERR(0, 85, __pyx_L1_error) return 0; __pyx_L1_error:; return -1; } /* #### Code section: cached_constants ### */ static CYTHON_SMALL_CODE int __Pyx_InitCachedConstants(void) { __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__Pyx_InitCachedConstants", 0); /* "curated_tokenizers/_bbpe.pyx":80 * def load_from_files(*, vocab: Path, merges: Path) -> ByteBPEProcessor: * """Construct a processor from the given vocabulary and merges files.""" * with open(vocab, encoding="utf-8") as f: # <<<<<<<<<<<<<< * vocab = json.load(f) * with open(merges, encoding="utf-8") as f: */ __pyx_tuple_ = PyTuple_Pack(3, Py_None, Py_None, Py_None); if (unlikely(!__pyx_tuple_)) __PYX_ERR(0, 80, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple_); __Pyx_GIVEREF(__pyx_tuple_); /* "curated_tokenizers/_bbpe.pyx":24 * * * @lru_cache() # <<<<<<<<<<<<<< * def bytes_to_unicode() -> Dict[int, bytes]: * """ */ __pyx_tuple__6 = PyTuple_Pack(4, __pyx_n_s_bs, __pyx_n_s_cs, __pyx_n_s_n, __pyx_n_s_b); if (unlikely(!__pyx_tuple__6)) __PYX_ERR(0, 24, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__6); __Pyx_GIVEREF(__pyx_tuple__6); __pyx_codeobj__7 = (PyObject*)__Pyx_PyCode_New(0, 0, 0, 4, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__6, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_curated_tokenizers__bbpe_pyx, __pyx_n_s_bytes_to_unicode, 24, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__7)) __PYX_ERR(0, 24, __pyx_L1_error) /* "curated_tokenizers/_bbpe.pyx":69 * self._merges = make_shared[Merges](c_merges) * * def __copy__(self): # <<<<<<<<<<<<<< * return ByteBPEProcessor(vocab=self.vocab, merges=self.merges) * */ __pyx_tuple__8 = PyTuple_Pack(1, __pyx_n_s_self); if (unlikely(!__pyx_tuple__8)) __PYX_ERR(0, 69, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__8); __Pyx_GIVEREF(__pyx_tuple__8); __pyx_codeobj__9 = (PyObject*)__Pyx_PyCode_New(1, 0, 0, 1, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__8, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_curated_tokenizers__bbpe_pyx, __pyx_n_s_copy, 69, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__9)) __PYX_ERR(0, 69, __pyx_L1_error) /* "curated_tokenizers/_bbpe.pyx":72 * return ByteBPEProcessor(vocab=self.vocab, merges=self.merges) * * def __deepcopy__(self, memo): # <<<<<<<<<<<<<< * # We don't need a deepcopy of the vocab and merges dicts as their * # contents will be copied into a backing store in the c'tor. */ __pyx_tuple__10 = PyTuple_Pack(2, __pyx_n_s_self, __pyx_n_s_memo); if (unlikely(!__pyx_tuple__10)) __PYX_ERR(0, 72, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__10); __Pyx_GIVEREF(__pyx_tuple__10); __pyx_codeobj__11 = (PyObject*)__Pyx_PyCode_New(2, 0, 0, 2, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__10, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_curated_tokenizers__bbpe_pyx, __pyx_n_s_deepcopy, 72, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__11)) __PYX_ERR(0, 72, __pyx_L1_error) /* "curated_tokenizers/_bbpe.pyx":77 * return ByteBPEProcessor(vocab=self.vocab, merges=self.merges) * * @staticmethod # <<<<<<<<<<<<<< * def load_from_files(*, vocab: Path, merges: Path) -> ByteBPEProcessor: * """Construct a processor from the given vocabulary and merges files.""" */ __pyx_tuple__12 = PyTuple_Pack(6, __pyx_n_s_vocab, __pyx_n_s_merges, __pyx_n_s_f, __pyx_n_s_version, __pyx_n_s_line, __pyx_n_s_merge); if (unlikely(!__pyx_tuple__12)) __PYX_ERR(0, 77, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__12); __Pyx_GIVEREF(__pyx_tuple__12); __pyx_codeobj__13 = (PyObject*)__Pyx_PyCode_New(0, 0, 2, 6, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__12, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_curated_tokenizers__bbpe_pyx, __pyx_n_s_load_from_files, 77, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__13)) __PYX_ERR(0, 77, __pyx_L1_error) /* "curated_tokenizers/_bbpe.pyx":94 * return ByteBPEProcessor(vocab, merges) * * def decode_from_ids(self, ids: Iterable[int]) -> str: # <<<<<<<<<<<<<< * """ * Decode piece identifiers into string. */ __pyx_tuple__14 = PyTuple_Pack(6, __pyx_n_s_self, __pyx_n_s_ids, __pyx_n_s_decoded, __pyx_n_s_piece_id, __pyx_n_s_piece, __pyx_n_s_cp); if (unlikely(!__pyx_tuple__14)) __PYX_ERR(0, 94, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__14); __Pyx_GIVEREF(__pyx_tuple__14); __pyx_codeobj__15 = (PyObject*)__Pyx_PyCode_New(2, 0, 0, 6, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__14, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_curated_tokenizers__bbpe_pyx, __pyx_n_s_decode_from_ids, 94, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__15)) __PYX_ERR(0, 94, __pyx_L1_error) /* "curated_tokenizers/_bbpe.pyx":110 * return decoded.getvalue().decode("utf-8") * * def encode(self, text: str) -> Tuple[List[int], List[str]]: # <<<<<<<<<<<<<< * """ * Split a text into pieces. */ __pyx_tuple__16 = PyTuple_Pack(3, __pyx_n_s_self, __pyx_n_s_text, __pyx_n_s_pieces); if (unlikely(!__pyx_tuple__16)) __PYX_ERR(0, 110, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__16); __Pyx_GIVEREF(__pyx_tuple__16); __pyx_codeobj__17 = (PyObject*)__Pyx_PyCode_New(2, 0, 0, 3, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__16, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_curated_tokenizers__bbpe_pyx, __pyx_n_s_encode, 110, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__17)) __PYX_ERR(0, 110, __pyx_L1_error) /* "curated_tokenizers/_bbpe.pyx":120 * return self._pieces_to_ids(pieces), pieces * * def encode_as_ids(self, text: str) -> List[int]: # <<<<<<<<<<<<<< * """ * Split a text into pieces, returning piece identifiers. */ __pyx_codeobj__18 = (PyObject*)__Pyx_PyCode_New(2, 0, 0, 3, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__16, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_curated_tokenizers__bbpe_pyx, __pyx_n_s_encode_as_ids, 120, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__18)) __PYX_ERR(0, 120, __pyx_L1_error) /* "curated_tokenizers/_bbpe.pyx":130 * return self._pieces_to_ids(pieces) * * def encode_as_pieces(self, text: str) -> List[str]: # <<<<<<<<<<<<<< * """ * Split a text into pieces, returning piece pieces. */ __pyx_tuple__19 = PyTuple_Pack(9, __pyx_n_s_self, __pyx_n_s_text, __pyx_n_s_pieces, __pyx_n_s_token, __pyx_n_s_token_bytes, __pyx_n_s_merged, __pyx_n_s_b, __pyx_n_s_genexpr, __pyx_n_s_genexpr); if (unlikely(!__pyx_tuple__19)) __PYX_ERR(0, 130, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__19); __Pyx_GIVEREF(__pyx_tuple__19); __pyx_codeobj__20 = (PyObject*)__Pyx_PyCode_New(2, 0, 0, 9, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__19, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_curated_tokenizers__bbpe_pyx, __pyx_n_s_encode_as_pieces, 130, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__20)) __PYX_ERR(0, 130, __pyx_L1_error) /* "curated_tokenizers/_bbpe.pyx":150 * return [(m1.decode('utf-8'), m2.decode('utf-8')) for m1, m2 in merges_bytes] * * def piece_id(self, piece: str) -> Optional[int]: # <<<<<<<<<<<<<< * """Get the identifier for a piece.""" * return self._piece_to_id.get(piece) */ __pyx_tuple__21 = PyTuple_Pack(2, __pyx_n_s_self, __pyx_n_s_piece); if (unlikely(!__pyx_tuple__21)) __PYX_ERR(0, 150, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__21); __Pyx_GIVEREF(__pyx_tuple__21); __pyx_codeobj__22 = (PyObject*)__Pyx_PyCode_New(2, 0, 0, 2, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__21, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_curated_tokenizers__bbpe_pyx, __pyx_n_s_piece_id, 150, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__22)) __PYX_ERR(0, 150, __pyx_L1_error) /* "curated_tokenizers/_bbpe.pyx":159 * return dict(self._piece_to_id) * * def _pieces_to_ids(self, pieces): # <<<<<<<<<<<<<< * piece_ids = [] * for piece in pieces: */ __pyx_tuple__23 = PyTuple_Pack(5, __pyx_n_s_self, __pyx_n_s_pieces, __pyx_n_s_piece_ids, __pyx_n_s_piece, __pyx_n_s_piece_id); if (unlikely(!__pyx_tuple__23)) __PYX_ERR(0, 159, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__23); __Pyx_GIVEREF(__pyx_tuple__23); __pyx_codeobj__24 = (PyObject*)__Pyx_PyCode_New(2, 0, 0, 5, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__23, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_curated_tokenizers__bbpe_pyx, __pyx_n_s_pieces_to_ids, 159, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__24)) __PYX_ERR(0, 159, __pyx_L1_error) /* "curated_tokenizers/_bbpe.pyx":169 * return piece_ids * * def __reduce__(self): # <<<<<<<<<<<<<< * return (unpickle_byte_bpe_processor, (self.vocab, self.merges,)) * */ __pyx_codeobj__25 = (PyObject*)__Pyx_PyCode_New(1, 0, 0, 1, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__8, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_curated_tokenizers__bbpe_pyx, __pyx_n_s_reduce, 169, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__25)) __PYX_ERR(0, 169, __pyx_L1_error) /* "curated_tokenizers/_bbpe.pyx":172 * return (unpickle_byte_bpe_processor, (self.vocab, self.merges,)) * * def unpickle_byte_bpe_processor(vocab: Dict[str, int], # <<<<<<<<<<<<<< * merges: List[Tuple[str, str]]) -> ByteBPEProcessor: * return ByteBPEProcessor(vocab, merges) */ __pyx_tuple__26 = PyTuple_Pack(2, __pyx_n_s_vocab, __pyx_n_s_merges); if (unlikely(!__pyx_tuple__26)) __PYX_ERR(0, 172, __pyx_L1_error) __Pyx_GOTREF(__pyx_tuple__26); __Pyx_GIVEREF(__pyx_tuple__26); __pyx_codeobj__27 = (PyObject*)__Pyx_PyCode_New(2, 0, 0, 2, 0, CO_OPTIMIZED|CO_NEWLOCALS, __pyx_empty_bytes, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_tuple__26, __pyx_empty_tuple, __pyx_empty_tuple, __pyx_kp_s_curated_tokenizers__bbpe_pyx, __pyx_n_s_unpickle_byte_bpe_processor, 172, __pyx_empty_bytes); if (unlikely(!__pyx_codeobj__27)) __PYX_ERR(0, 172, __pyx_L1_error) __Pyx_RefNannyFinishContext(); return 0; __pyx_L1_error:; __Pyx_RefNannyFinishContext(); return -1; } /* #### Code section: init_constants ### */ static CYTHON_SMALL_CODE int __Pyx_InitConstants(void) { __pyx_umethod_PyDict_Type_get.type = (PyObject*)&PyDict_Type; __pyx_umethod_PyDict_Type_get.method_name = &__pyx_n_s_get; __pyx_umethod_PyDict_Type_items.type = (PyObject*)&PyDict_Type; __pyx_umethod_PyDict_Type_items.method_name = &__pyx_n_s_items; if (__Pyx_CreateStringTabAndInitStrings() < 0) __PYX_ERR(0, 1, __pyx_L1_error); __pyx_int_0 = PyInt_FromLong(0); if (unlikely(!__pyx_int_0)) __PYX_ERR(0, 1, __pyx_L1_error) __pyx_int_1 = PyInt_FromLong(1); if (unlikely(!__pyx_int_1)) __PYX_ERR(0, 1, __pyx_L1_error) __pyx_int_33 = PyInt_FromLong(33); if (unlikely(!__pyx_int_33)) __PYX_ERR(0, 1, __pyx_L1_error) __pyx_int_161 = PyInt_FromLong(161); if (unlikely(!__pyx_int_161)) __PYX_ERR(0, 1, __pyx_L1_error) __pyx_int_174 = PyInt_FromLong(174); if (unlikely(!__pyx_int_174)) __PYX_ERR(0, 1, __pyx_L1_error) __pyx_int_256 = PyInt_FromLong(256); if (unlikely(!__pyx_int_256)) __PYX_ERR(0, 1, __pyx_L1_error) return 0; __pyx_L1_error:; return -1; } /* #### Code section: init_globals ### */ static CYTHON_SMALL_CODE int __Pyx_InitGlobals(void) { return 0; } /* #### Code section: init_module ### */ static CYTHON_SMALL_CODE int __Pyx_modinit_global_init_code(void); /*proto*/ static CYTHON_SMALL_CODE int __Pyx_modinit_variable_export_code(void); /*proto*/ static CYTHON_SMALL_CODE int __Pyx_modinit_function_export_code(void); /*proto*/ static CYTHON_SMALL_CODE int __Pyx_modinit_type_init_code(void); /*proto*/ static CYTHON_SMALL_CODE int __Pyx_modinit_type_import_code(void); /*proto*/ static CYTHON_SMALL_CODE int __Pyx_modinit_variable_import_code(void); /*proto*/ static CYTHON_SMALL_CODE int __Pyx_modinit_function_import_code(void); /*proto*/ static int __Pyx_modinit_global_init_code(void) { __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__Pyx_modinit_global_init_code", 0); /*--- Global init code ---*/ __Pyx_RefNannyFinishContext(); return 0; } static int __Pyx_modinit_variable_export_code(void) { __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__Pyx_modinit_variable_export_code", 0); /*--- Variable export code ---*/ __Pyx_RefNannyFinishContext(); return 0; } static int __Pyx_modinit_function_export_code(void) { __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__Pyx_modinit_function_export_code", 0); /*--- Function export code ---*/ __Pyx_RefNannyFinishContext(); return 0; } static int __Pyx_modinit_type_init_code(void) { __Pyx_RefNannyDeclarations int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannySetupContext("__Pyx_modinit_type_init_code", 0); /*--- Type init code ---*/ #if CYTHON_USE_TYPE_SPECS __pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor = (PyTypeObject *) __Pyx_PyType_FromModuleAndSpec(__pyx_m, &__pyx_type_18curated_tokenizers_5_bbpe_ByteBPEProcessor_spec, NULL); if (unlikely(!__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor)) __PYX_ERR(0, 50, __pyx_L1_error) if (__Pyx_fix_up_extension_type_from_spec(&__pyx_type_18curated_tokenizers_5_bbpe_ByteBPEProcessor_spec, __pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor) < 0) __PYX_ERR(0, 50, __pyx_L1_error) #else __pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor = &__pyx_type_18curated_tokenizers_5_bbpe_ByteBPEProcessor; #endif #if !CYTHON_COMPILING_IN_LIMITED_API #endif #if !CYTHON_USE_TYPE_SPECS if (__Pyx_PyType_Ready(__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor) < 0) __PYX_ERR(0, 50, __pyx_L1_error) #endif #if PY_MAJOR_VERSION < 3 __pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor->tp_print = 0; #endif #if !CYTHON_COMPILING_IN_LIMITED_API if ((CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP) && likely(!__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor->tp_dictoffset && __pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor->tp_getattro == PyObject_GenericGetAttr)) { __pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor->tp_getattro = __Pyx_PyObject_GenericGetAttr; } #endif if (PyObject_SetAttr(__pyx_m, __pyx_n_s_ByteBPEProcessor, (PyObject *) __pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor) < 0) __PYX_ERR(0, 50, __pyx_L1_error) #if CYTHON_USE_TYPE_SPECS __pyx_ptype_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr = (PyTypeObject *) __Pyx_PyType_FromModuleAndSpec(__pyx_m, &__pyx_type_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr_spec, NULL); if (unlikely(!__pyx_ptype_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr)) __PYX_ERR(0, 141, __pyx_L1_error) if (__Pyx_fix_up_extension_type_from_spec(&__pyx_type_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr_spec, __pyx_ptype_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr) < 0) __PYX_ERR(0, 141, __pyx_L1_error) #else __pyx_ptype_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr = &__pyx_type_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr; #endif #if !CYTHON_COMPILING_IN_LIMITED_API #endif #if !CYTHON_USE_TYPE_SPECS if (__Pyx_PyType_Ready(__pyx_ptype_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr) < 0) __PYX_ERR(0, 141, __pyx_L1_error) #endif #if PY_MAJOR_VERSION < 3 __pyx_ptype_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr->tp_print = 0; #endif #if !CYTHON_COMPILING_IN_LIMITED_API if ((CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP) && likely(!__pyx_ptype_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr->tp_dictoffset && __pyx_ptype_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr->tp_getattro == PyObject_GenericGetAttr)) { __pyx_ptype_18curated_tokenizers_5_bbpe___pyx_scope_struct__genexpr->tp_getattro = __Pyx_PyObject_GenericGetAttrNoDict; } #endif __Pyx_RefNannyFinishContext(); return 0; __pyx_L1_error:; __Pyx_RefNannyFinishContext(); return -1; } static int __Pyx_modinit_type_import_code(void) { __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__Pyx_modinit_type_import_code", 0); /*--- Type import code ---*/ __Pyx_RefNannyFinishContext(); return 0; } static int __Pyx_modinit_variable_import_code(void) { __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__Pyx_modinit_variable_import_code", 0); /*--- Variable import code ---*/ __Pyx_RefNannyFinishContext(); return 0; } static int __Pyx_modinit_function_import_code(void) { __Pyx_RefNannyDeclarations __Pyx_RefNannySetupContext("__Pyx_modinit_function_import_code", 0); /*--- Function import code ---*/ __Pyx_RefNannyFinishContext(); return 0; } #if PY_MAJOR_VERSION >= 3 #if CYTHON_PEP489_MULTI_PHASE_INIT static PyObject* __pyx_pymod_create(PyObject *spec, PyModuleDef *def); /*proto*/ static int __pyx_pymod_exec__bbpe(PyObject* module); /*proto*/ static PyModuleDef_Slot __pyx_moduledef_slots[] = { {Py_mod_create, (void*)__pyx_pymod_create}, {Py_mod_exec, (void*)__pyx_pymod_exec__bbpe}, {0, NULL} }; #endif #ifdef __cplusplus namespace { struct PyModuleDef __pyx_moduledef = #else static struct PyModuleDef __pyx_moduledef = #endif { PyModuleDef_HEAD_INIT, "_bbpe", 0, /* m_doc */ #if CYTHON_PEP489_MULTI_PHASE_INIT 0, /* m_size */ #elif CYTHON_USE_MODULE_STATE sizeof(__pyx_mstate), /* m_size */ #else -1, /* m_size */ #endif __pyx_methods /* m_methods */, #if CYTHON_PEP489_MULTI_PHASE_INIT __pyx_moduledef_slots, /* m_slots */ #else NULL, /* m_reload */ #endif #if CYTHON_USE_MODULE_STATE __pyx_m_traverse, /* m_traverse */ __pyx_m_clear, /* m_clear */ NULL /* m_free */ #else NULL, /* m_traverse */ NULL, /* m_clear */ NULL /* m_free */ #endif }; #ifdef __cplusplus } /* anonymous namespace */ #endif #endif #ifndef CYTHON_NO_PYINIT_EXPORT #define __Pyx_PyMODINIT_FUNC PyMODINIT_FUNC #elif PY_MAJOR_VERSION < 3 #ifdef __cplusplus #define __Pyx_PyMODINIT_FUNC extern "C" void #else #define __Pyx_PyMODINIT_FUNC void #endif #else #ifdef __cplusplus #define __Pyx_PyMODINIT_FUNC extern "C" PyObject * #else #define __Pyx_PyMODINIT_FUNC PyObject * #endif #endif #if PY_MAJOR_VERSION < 3 __Pyx_PyMODINIT_FUNC init_bbpe(void) CYTHON_SMALL_CODE; /*proto*/ __Pyx_PyMODINIT_FUNC init_bbpe(void) #else __Pyx_PyMODINIT_FUNC PyInit__bbpe(void) CYTHON_SMALL_CODE; /*proto*/ __Pyx_PyMODINIT_FUNC PyInit__bbpe(void) #if CYTHON_PEP489_MULTI_PHASE_INIT { return PyModuleDef_Init(&__pyx_moduledef); } static CYTHON_SMALL_CODE int __Pyx_check_single_interpreter(void) { #if PY_VERSION_HEX >= 0x030700A1 static PY_INT64_T main_interpreter_id = -1; PY_INT64_T current_id = PyInterpreterState_GetID(PyThreadState_Get()->interp); if (main_interpreter_id == -1) { main_interpreter_id = current_id; return (unlikely(current_id == -1)) ? -1 : 0; } else if (unlikely(main_interpreter_id != current_id)) #else static PyInterpreterState *main_interpreter = NULL; PyInterpreterState *current_interpreter = PyThreadState_Get()->interp; if (!main_interpreter) { main_interpreter = current_interpreter; } else if (unlikely(main_interpreter != current_interpreter)) #endif { PyErr_SetString( PyExc_ImportError, "Interpreter change detected - this module can only be loaded into one interpreter per process."); return -1; } return 0; } #if CYTHON_COMPILING_IN_LIMITED_API static CYTHON_SMALL_CODE int __Pyx_copy_spec_to_module(PyObject *spec, PyObject *module, const char* from_name, const char* to_name, int allow_none) #else static CYTHON_SMALL_CODE int __Pyx_copy_spec_to_module(PyObject *spec, PyObject *moddict, const char* from_name, const char* to_name, int allow_none) #endif { PyObject *value = PyObject_GetAttrString(spec, from_name); int result = 0; if (likely(value)) { if (allow_none || value != Py_None) { #if CYTHON_COMPILING_IN_LIMITED_API result = PyModule_AddObject(module, to_name, value); #else result = PyDict_SetItemString(moddict, to_name, value); #endif } Py_DECREF(value); } else if (PyErr_ExceptionMatches(PyExc_AttributeError)) { PyErr_Clear(); } else { result = -1; } return result; } static CYTHON_SMALL_CODE PyObject* __pyx_pymod_create(PyObject *spec, PyModuleDef *def) { PyObject *module = NULL, *moddict, *modname; CYTHON_UNUSED_VAR(def); if (__Pyx_check_single_interpreter()) return NULL; if (__pyx_m) return __Pyx_NewRef(__pyx_m); modname = PyObject_GetAttrString(spec, "name"); if (unlikely(!modname)) goto bad; module = PyModule_NewObject(modname); Py_DECREF(modname); if (unlikely(!module)) goto bad; #if CYTHON_COMPILING_IN_LIMITED_API moddict = module; #else moddict = PyModule_GetDict(module); if (unlikely(!moddict)) goto bad; #endif if (unlikely(__Pyx_copy_spec_to_module(spec, moddict, "loader", "__loader__", 1) < 0)) goto bad; if (unlikely(__Pyx_copy_spec_to_module(spec, moddict, "origin", "__file__", 1) < 0)) goto bad; if (unlikely(__Pyx_copy_spec_to_module(spec, moddict, "parent", "__package__", 1) < 0)) goto bad; if (unlikely(__Pyx_copy_spec_to_module(spec, moddict, "submodule_search_locations", "__path__", 0) < 0)) goto bad; return module; bad: Py_XDECREF(module); return NULL; } static CYTHON_SMALL_CODE int __pyx_pymod_exec__bbpe(PyObject *__pyx_pyinit_module) #endif #endif { int stringtab_initialized = 0; #if CYTHON_USE_MODULE_STATE int pystate_addmodule_run = 0; #endif PyObject *__pyx_t_1 = NULL; PyObject *__pyx_t_2 = NULL; PyObject *__pyx_t_3 = NULL; PyObject *__pyx_t_4 = NULL; int __pyx_lineno = 0; const char *__pyx_filename = NULL; int __pyx_clineno = 0; __Pyx_RefNannyDeclarations #if CYTHON_PEP489_MULTI_PHASE_INIT if (__pyx_m) { if (__pyx_m == __pyx_pyinit_module) return 0; PyErr_SetString(PyExc_RuntimeError, "Module '_bbpe' has already been imported. Re-initialisation is not supported."); return -1; } #elif PY_MAJOR_VERSION >= 3 if (__pyx_m) return __Pyx_NewRef(__pyx_m); #endif /*--- Module creation code ---*/ #if CYTHON_PEP489_MULTI_PHASE_INIT __pyx_m = __pyx_pyinit_module; Py_INCREF(__pyx_m); #else #if PY_MAJOR_VERSION < 3 __pyx_m = Py_InitModule4("_bbpe", __pyx_methods, 0, 0, PYTHON_API_VERSION); Py_XINCREF(__pyx_m); if (unlikely(!__pyx_m)) __PYX_ERR(0, 1, __pyx_L1_error) #elif CYTHON_USE_MODULE_STATE __pyx_t_1 = PyModule_Create(&__pyx_moduledef); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 1, __pyx_L1_error) { int add_module_result = PyState_AddModule(__pyx_t_1, &__pyx_moduledef); __pyx_t_1 = 0; /* transfer ownership from __pyx_t_1 to "_bbpe" pseudovariable */ if (unlikely((add_module_result < 0))) __PYX_ERR(0, 1, __pyx_L1_error) pystate_addmodule_run = 1; } #else __pyx_m = PyModule_Create(&__pyx_moduledef); if (unlikely(!__pyx_m)) __PYX_ERR(0, 1, __pyx_L1_error) #endif #endif CYTHON_UNUSED_VAR(__pyx_t_1); __pyx_d = PyModule_GetDict(__pyx_m); if (unlikely(!__pyx_d)) __PYX_ERR(0, 1, __pyx_L1_error) Py_INCREF(__pyx_d); __pyx_b = __Pyx_PyImport_AddModuleRef(__Pyx_BUILTIN_MODULE_NAME); if (unlikely(!__pyx_b)) __PYX_ERR(0, 1, __pyx_L1_error) __pyx_cython_runtime = __Pyx_PyImport_AddModuleRef((const char *) "cython_runtime"); if (unlikely(!__pyx_cython_runtime)) __PYX_ERR(0, 1, __pyx_L1_error) if (PyObject_SetAttrString(__pyx_m, "__builtins__", __pyx_b) < 0) __PYX_ERR(0, 1, __pyx_L1_error) #if CYTHON_REFNANNY __Pyx_RefNanny = __Pyx_RefNannyImportAPI("refnanny"); if (!__Pyx_RefNanny) { PyErr_Clear(); __Pyx_RefNanny = __Pyx_RefNannyImportAPI("Cython.Runtime.refnanny"); if (!__Pyx_RefNanny) Py_FatalError("failed to import 'refnanny' module"); } #endif __Pyx_RefNannySetupContext("__Pyx_PyMODINIT_FUNC PyInit__bbpe(void)", 0); if (__Pyx_check_binary_version(__PYX_LIMITED_VERSION_HEX, __Pyx_get_runtime_version(), CYTHON_COMPILING_IN_LIMITED_API) < 0) __PYX_ERR(0, 1, __pyx_L1_error) #ifdef __Pxy_PyFrame_Initialize_Offsets __Pxy_PyFrame_Initialize_Offsets(); #endif __pyx_empty_tuple = PyTuple_New(0); if (unlikely(!__pyx_empty_tuple)) __PYX_ERR(0, 1, __pyx_L1_error) __pyx_empty_bytes = PyBytes_FromStringAndSize("", 0); if (unlikely(!__pyx_empty_bytes)) __PYX_ERR(0, 1, __pyx_L1_error) __pyx_empty_unicode = PyUnicode_FromStringAndSize("", 0); if (unlikely(!__pyx_empty_unicode)) __PYX_ERR(0, 1, __pyx_L1_error) #ifdef __Pyx_CyFunction_USED if (__pyx_CyFunction_init(__pyx_m) < 0) __PYX_ERR(0, 1, __pyx_L1_error) #endif #ifdef __Pyx_FusedFunction_USED if (__pyx_FusedFunction_init(__pyx_m) < 0) __PYX_ERR(0, 1, __pyx_L1_error) #endif #ifdef __Pyx_Coroutine_USED if (__pyx_Coroutine_init(__pyx_m) < 0) __PYX_ERR(0, 1, __pyx_L1_error) #endif #ifdef __Pyx_Generator_USED if (__pyx_Generator_init(__pyx_m) < 0) __PYX_ERR(0, 1, __pyx_L1_error) #endif #ifdef __Pyx_AsyncGen_USED if (__pyx_AsyncGen_init(__pyx_m) < 0) __PYX_ERR(0, 1, __pyx_L1_error) #endif #ifdef __Pyx_StopAsyncIteration_USED if (__pyx_StopAsyncIteration_init(__pyx_m) < 0) __PYX_ERR(0, 1, __pyx_L1_error) #endif /*--- Library function declarations ---*/ /*--- Threads initialization code ---*/ #if defined(WITH_THREAD) && PY_VERSION_HEX < 0x030700F0 && defined(__PYX_FORCE_INIT_THREADS) && __PYX_FORCE_INIT_THREADS PyEval_InitThreads(); #endif /*--- Initialize various global constants etc. ---*/ if (__Pyx_InitConstants() < 0) __PYX_ERR(0, 1, __pyx_L1_error) stringtab_initialized = 1; if (__Pyx_InitGlobals() < 0) __PYX_ERR(0, 1, __pyx_L1_error) #if PY_MAJOR_VERSION < 3 && (__PYX_DEFAULT_STRING_ENCODING_IS_ASCII || __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT) if (__Pyx_init_sys_getdefaultencoding_params() < 0) __PYX_ERR(0, 1, __pyx_L1_error) #endif if (__pyx_module_is_main_curated_tokenizers___bbpe) { if (PyObject_SetAttr(__pyx_m, __pyx_n_s_name, __pyx_n_s_main) < 0) __PYX_ERR(0, 1, __pyx_L1_error) } #if PY_MAJOR_VERSION >= 3 { PyObject *modules = PyImport_GetModuleDict(); if (unlikely(!modules)) __PYX_ERR(0, 1, __pyx_L1_error) if (!PyDict_GetItemString(modules, "curated_tokenizers._bbpe")) { if (unlikely((PyDict_SetItemString(modules, "curated_tokenizers._bbpe", __pyx_m) < 0))) __PYX_ERR(0, 1, __pyx_L1_error) } } #endif /*--- Builtin init code ---*/ if (__Pyx_InitCachedBuiltins() < 0) __PYX_ERR(0, 1, __pyx_L1_error) /*--- Constants init code ---*/ if (__Pyx_InitCachedConstants() < 0) __PYX_ERR(0, 1, __pyx_L1_error) /*--- Global type/function init code ---*/ (void)__Pyx_modinit_global_init_code(); (void)__Pyx_modinit_variable_export_code(); (void)__Pyx_modinit_function_export_code(); if (unlikely((__Pyx_modinit_type_init_code() < 0))) __PYX_ERR(0, 1, __pyx_L1_error) (void)__Pyx_modinit_type_import_code(); (void)__Pyx_modinit_variable_import_code(); (void)__Pyx_modinit_function_import_code(); /*--- Execution code ---*/ #if defined(__Pyx_Generator_USED) || defined(__Pyx_Coroutine_USED) if (__Pyx_patch_abc() < 0) __PYX_ERR(0, 1, __pyx_L1_error) #endif /* "curated_tokenizers/_bbpe.pyx":3 * # cython: infer_types * * from typing import Dict, Iterable, List, Optional, Tuple # <<<<<<<<<<<<<< * from cython.operator cimport dereference as deref * from functools import lru_cache */ __pyx_t_2 = PyList_New(5); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 3, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_INCREF(__pyx_n_s_Dict); __Pyx_GIVEREF(__pyx_n_s_Dict); if (__Pyx_PyList_SET_ITEM(__pyx_t_2, 0, __pyx_n_s_Dict)) __PYX_ERR(0, 3, __pyx_L1_error); __Pyx_INCREF(__pyx_n_s_Iterable); __Pyx_GIVEREF(__pyx_n_s_Iterable); if (__Pyx_PyList_SET_ITEM(__pyx_t_2, 1, __pyx_n_s_Iterable)) __PYX_ERR(0, 3, __pyx_L1_error); __Pyx_INCREF(__pyx_n_s_List); __Pyx_GIVEREF(__pyx_n_s_List); if (__Pyx_PyList_SET_ITEM(__pyx_t_2, 2, __pyx_n_s_List)) __PYX_ERR(0, 3, __pyx_L1_error); __Pyx_INCREF(__pyx_n_s_Optional); __Pyx_GIVEREF(__pyx_n_s_Optional); if (__Pyx_PyList_SET_ITEM(__pyx_t_2, 3, __pyx_n_s_Optional)) __PYX_ERR(0, 3, __pyx_L1_error); __Pyx_INCREF(__pyx_n_s_Tuple); __Pyx_GIVEREF(__pyx_n_s_Tuple); if (__Pyx_PyList_SET_ITEM(__pyx_t_2, 4, __pyx_n_s_Tuple)) __PYX_ERR(0, 3, __pyx_L1_error); __pyx_t_3 = __Pyx_Import(__pyx_n_s_typing, __pyx_t_2, -1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 3, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = __Pyx_ImportFrom(__pyx_t_3, __pyx_n_s_Dict); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 3, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (PyDict_SetItem(__pyx_d, __pyx_n_s_Dict, __pyx_t_2) < 0) __PYX_ERR(0, 3, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = __Pyx_ImportFrom(__pyx_t_3, __pyx_n_s_Iterable); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 3, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (PyDict_SetItem(__pyx_d, __pyx_n_s_Iterable, __pyx_t_2) < 0) __PYX_ERR(0, 3, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = __Pyx_ImportFrom(__pyx_t_3, __pyx_n_s_List); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 3, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (PyDict_SetItem(__pyx_d, __pyx_n_s_List, __pyx_t_2) < 0) __PYX_ERR(0, 3, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = __Pyx_ImportFrom(__pyx_t_3, __pyx_n_s_Optional); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 3, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (PyDict_SetItem(__pyx_d, __pyx_n_s_Optional, __pyx_t_2) < 0) __PYX_ERR(0, 3, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = __Pyx_ImportFrom(__pyx_t_3, __pyx_n_s_Tuple); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 3, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (PyDict_SetItem(__pyx_d, __pyx_n_s_Tuple, __pyx_t_2) < 0) __PYX_ERR(0, 3, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; /* "curated_tokenizers/_bbpe.pyx":5 * from typing import Dict, Iterable, List, Optional, Tuple * from cython.operator cimport dereference as deref * from functools import lru_cache # <<<<<<<<<<<<<< * from io import BytesIO * import json */ __pyx_t_3 = PyList_New(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 5, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_INCREF(__pyx_n_s_lru_cache); __Pyx_GIVEREF(__pyx_n_s_lru_cache); if (__Pyx_PyList_SET_ITEM(__pyx_t_3, 0, __pyx_n_s_lru_cache)) __PYX_ERR(0, 5, __pyx_L1_error); __pyx_t_2 = __Pyx_Import(__pyx_n_s_functools, __pyx_t_3, -1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 5, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_t_3 = __Pyx_ImportFrom(__pyx_t_2, __pyx_n_s_lru_cache); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 5, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); if (PyDict_SetItem(__pyx_d, __pyx_n_s_lru_cache, __pyx_t_3) < 0) __PYX_ERR(0, 5, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; /* "curated_tokenizers/_bbpe.pyx":6 * from cython.operator cimport dereference as deref * from functools import lru_cache * from io import BytesIO # <<<<<<<<<<<<<< * import json * from libcpp.memory cimport make_shared, shared_ptr */ __pyx_t_2 = PyList_New(1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 6, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_INCREF(__pyx_n_s_BytesIO); __Pyx_GIVEREF(__pyx_n_s_BytesIO); if (__Pyx_PyList_SET_ITEM(__pyx_t_2, 0, __pyx_n_s_BytesIO)) __PYX_ERR(0, 6, __pyx_L1_error); __pyx_t_3 = __Pyx_Import(__pyx_n_s_io, __pyx_t_2, -1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 6, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = __Pyx_ImportFrom(__pyx_t_3, __pyx_n_s_BytesIO); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 6, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (PyDict_SetItem(__pyx_d, __pyx_n_s_BytesIO, __pyx_t_2) < 0) __PYX_ERR(0, 6, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; /* "curated_tokenizers/_bbpe.pyx":7 * from functools import lru_cache * from io import BytesIO * import json # <<<<<<<<<<<<<< * from libcpp.memory cimport make_shared, shared_ptr * from pathlib import Path */ __pyx_t_3 = __Pyx_ImportDottedModuleRelFirst(__pyx_n_s_json, NULL); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 7, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); if (PyDict_SetItem(__pyx_d, __pyx_n_s_json, __pyx_t_3) < 0) __PYX_ERR(0, 7, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; /* "curated_tokenizers/_bbpe.pyx":9 * import json * from libcpp.memory cimport make_shared, shared_ptr * from pathlib import Path # <<<<<<<<<<<<<< * import regex * */ __pyx_t_3 = PyList_New(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 9, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_INCREF(__pyx_n_s_Path); __Pyx_GIVEREF(__pyx_n_s_Path); if (__Pyx_PyList_SET_ITEM(__pyx_t_3, 0, __pyx_n_s_Path)) __PYX_ERR(0, 9, __pyx_L1_error); __pyx_t_2 = __Pyx_Import(__pyx_n_s_pathlib, __pyx_t_3, -1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 9, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __pyx_t_3 = __Pyx_ImportFrom(__pyx_t_2, __pyx_n_s_Path); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 9, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); if (PyDict_SetItem(__pyx_d, __pyx_n_s_Path, __pyx_t_3) < 0) __PYX_ERR(0, 9, __pyx_L1_error) __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; /* "curated_tokenizers/_bbpe.pyx":10 * from libcpp.memory cimport make_shared, shared_ptr * from pathlib import Path * import regex # <<<<<<<<<<<<<< * * */ __pyx_t_2 = __Pyx_ImportDottedModuleRelFirst(__pyx_n_s_regex, NULL); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 10, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (PyDict_SetItem(__pyx_d, __pyx_n_s_regex, __pyx_t_2) < 0) __PYX_ERR(0, 10, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; /* "curated_tokenizers/_bbpe.pyx":21 * * * SPLIT_PATTERN = r"""'s|'t|'re|'ve|'m|'ll|'d| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+""" # <<<<<<<<<<<<<< * * */ if (PyDict_SetItem(__pyx_d, __pyx_n_s_SPLIT_PATTERN, __pyx_kp_s_s_t_re_ve_m_ll_d_p_L_p_N_s_p_L) < 0) __PYX_ERR(0, 21, __pyx_L1_error) /* "curated_tokenizers/_bbpe.pyx":24 * * * @lru_cache() # <<<<<<<<<<<<<< * def bytes_to_unicode() -> Dict[int, bytes]: * """ */ __Pyx_GetModuleGlobalName(__pyx_t_2, __pyx_n_s_lru_cache); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 24, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __pyx_t_3 = __Pyx_PyObject_CallNoArg(__pyx_t_2); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 24, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_3); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 24, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (PyDict_SetItem(__pyx_t_2, __pyx_n_s_return, __pyx_kp_s_Dict_int_bytes) < 0) __PYX_ERR(0, 24, __pyx_L1_error) __pyx_t_4 = __Pyx_CyFunction_New(&__pyx_mdef_18curated_tokenizers_5_bbpe_1bytes_to_unicode, 0, __pyx_n_s_bytes_to_unicode, NULL, __pyx_n_s_curated_tokenizers__bbpe, __pyx_d, ((PyObject *)__pyx_codeobj__7)); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 24, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_CyFunction_SetAnnotationsDict(__pyx_t_4, __pyx_t_2); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; __pyx_t_2 = __Pyx_PyObject_CallOneArg(__pyx_t_3, __pyx_t_4); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 24, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0; __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (PyDict_SetItem(__pyx_d, __pyx_n_s_bytes_to_unicode, __pyx_t_2) < 0) __PYX_ERR(0, 24, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; /* "curated_tokenizers/_bbpe.pyx":69 * self._merges = make_shared[Merges](c_merges) * * def __copy__(self): # <<<<<<<<<<<<<< * return ByteBPEProcessor(vocab=self.vocab, merges=self.merges) * */ __pyx_t_2 = __Pyx_CyFunction_New(&__pyx_mdef_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_3__copy__, __Pyx_CYFUNCTION_CCLASS, __pyx_n_s_ByteBPEProcessor___copy, NULL, __pyx_n_s_curated_tokenizers__bbpe, __pyx_d, ((PyObject *)__pyx_codeobj__9)); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 69, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (__Pyx_SetItemOnTypeDict((PyObject *)__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor, __pyx_n_s_copy, __pyx_t_2) < 0) __PYX_ERR(0, 69, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; PyType_Modified(__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor); /* "curated_tokenizers/_bbpe.pyx":72 * return ByteBPEProcessor(vocab=self.vocab, merges=self.merges) * * def __deepcopy__(self, memo): # <<<<<<<<<<<<<< * # We don't need a deepcopy of the vocab and merges dicts as their * # contents will be copied into a backing store in the c'tor. */ __pyx_t_2 = __Pyx_CyFunction_New(&__pyx_mdef_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_5__deepcopy__, __Pyx_CYFUNCTION_CCLASS, __pyx_n_s_ByteBPEProcessor___deepcopy, NULL, __pyx_n_s_curated_tokenizers__bbpe, __pyx_d, ((PyObject *)__pyx_codeobj__11)); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 72, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (__Pyx_SetItemOnTypeDict((PyObject *)__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor, __pyx_n_s_deepcopy, __pyx_t_2) < 0) __PYX_ERR(0, 72, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; PyType_Modified(__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor); /* "curated_tokenizers/_bbpe.pyx":77 * return ByteBPEProcessor(vocab=self.vocab, merges=self.merges) * * @staticmethod # <<<<<<<<<<<<<< * def load_from_files(*, vocab: Path, merges: Path) -> ByteBPEProcessor: * """Construct a processor from the given vocabulary and merges files.""" */ __pyx_t_2 = __Pyx_PyDict_NewPresized(3); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 77, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (PyDict_SetItem(__pyx_t_2, __pyx_n_s_vocab, __pyx_n_s_Path) < 0) __PYX_ERR(0, 77, __pyx_L1_error) if (PyDict_SetItem(__pyx_t_2, __pyx_n_s_merges, __pyx_n_s_Path) < 0) __PYX_ERR(0, 77, __pyx_L1_error) if (PyDict_SetItem(__pyx_t_2, __pyx_n_s_return, __pyx_n_s_ByteBPEProcessor) < 0) __PYX_ERR(0, 77, __pyx_L1_error) __pyx_t_4 = __Pyx_CyFunction_New(&__pyx_mdef_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_7load_from_files, __Pyx_CYFUNCTION_STATICMETHOD | __Pyx_CYFUNCTION_CCLASS, __pyx_n_s_ByteBPEProcessor_load_from_files, NULL, __pyx_n_s_curated_tokenizers__bbpe, __pyx_d, ((PyObject *)__pyx_codeobj__13)); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 77, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_CyFunction_SetAnnotationsDict(__pyx_t_4, __pyx_t_2); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; if (__Pyx_SetItemOnTypeDict((PyObject *)__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor, __pyx_n_s_load_from_files, __pyx_t_4) < 0) __PYX_ERR(0, 77, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; PyType_Modified(__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor); __Pyx_GetNameInClass(__pyx_t_4, (PyObject *)__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor, __pyx_n_s_load_from_files); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 77, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __pyx_t_2 = __Pyx_PyObject_CallOneArg(__pyx_builtin_staticmethod, __pyx_t_4); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 77, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__Pyx_SetItemOnTypeDict((PyObject *)__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor, __pyx_n_s_load_from_files, __pyx_t_2) < 0) __PYX_ERR(0, 77, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; PyType_Modified(__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor); /* "curated_tokenizers/_bbpe.pyx":94 * return ByteBPEProcessor(vocab, merges) * * def decode_from_ids(self, ids: Iterable[int]) -> str: # <<<<<<<<<<<<<< * """ * Decode piece identifiers into string. */ __pyx_t_2 = __Pyx_PyDict_NewPresized(2); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 94, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (PyDict_SetItem(__pyx_t_2, __pyx_n_s_ids, __pyx_kp_s_Iterable_int) < 0) __PYX_ERR(0, 94, __pyx_L1_error) if (PyDict_SetItem(__pyx_t_2, __pyx_n_s_return, __pyx_n_s_str) < 0) __PYX_ERR(0, 94, __pyx_L1_error) __pyx_t_4 = __Pyx_CyFunction_New(&__pyx_mdef_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_9decode_from_ids, __Pyx_CYFUNCTION_CCLASS, __pyx_n_s_ByteBPEProcessor_decode_from_ids, NULL, __pyx_n_s_curated_tokenizers__bbpe, __pyx_d, ((PyObject *)__pyx_codeobj__15)); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 94, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_CyFunction_SetAnnotationsDict(__pyx_t_4, __pyx_t_2); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; if (__Pyx_SetItemOnTypeDict((PyObject *)__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor, __pyx_n_s_decode_from_ids, __pyx_t_4) < 0) __PYX_ERR(0, 94, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; PyType_Modified(__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor); /* "curated_tokenizers/_bbpe.pyx":110 * return decoded.getvalue().decode("utf-8") * * def encode(self, text: str) -> Tuple[List[int], List[str]]: # <<<<<<<<<<<<<< * """ * Split a text into pieces. */ __pyx_t_4 = __Pyx_PyDict_NewPresized(2); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 110, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); if (PyDict_SetItem(__pyx_t_4, __pyx_n_s_text, __pyx_n_s_str) < 0) __PYX_ERR(0, 110, __pyx_L1_error) if (PyDict_SetItem(__pyx_t_4, __pyx_n_s_return, __pyx_kp_s_Tuple_List_int_List_str) < 0) __PYX_ERR(0, 110, __pyx_L1_error) __pyx_t_2 = __Pyx_CyFunction_New(&__pyx_mdef_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_11encode, __Pyx_CYFUNCTION_CCLASS, __pyx_n_s_ByteBPEProcessor_encode, NULL, __pyx_n_s_curated_tokenizers__bbpe, __pyx_d, ((PyObject *)__pyx_codeobj__17)); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 110, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_CyFunction_SetAnnotationsDict(__pyx_t_2, __pyx_t_4); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__Pyx_SetItemOnTypeDict((PyObject *)__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor, __pyx_n_s_encode, __pyx_t_2) < 0) __PYX_ERR(0, 110, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; PyType_Modified(__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor); /* "curated_tokenizers/_bbpe.pyx":120 * return self._pieces_to_ids(pieces), pieces * * def encode_as_ids(self, text: str) -> List[int]: # <<<<<<<<<<<<<< * """ * Split a text into pieces, returning piece identifiers. */ __pyx_t_2 = __Pyx_PyDict_NewPresized(2); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 120, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (PyDict_SetItem(__pyx_t_2, __pyx_n_s_text, __pyx_n_s_str) < 0) __PYX_ERR(0, 120, __pyx_L1_error) if (PyDict_SetItem(__pyx_t_2, __pyx_n_s_return, __pyx_kp_s_List_int) < 0) __PYX_ERR(0, 120, __pyx_L1_error) __pyx_t_4 = __Pyx_CyFunction_New(&__pyx_mdef_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_13encode_as_ids, __Pyx_CYFUNCTION_CCLASS, __pyx_n_s_ByteBPEProcessor_encode_as_ids, NULL, __pyx_n_s_curated_tokenizers__bbpe, __pyx_d, ((PyObject *)__pyx_codeobj__18)); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 120, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_CyFunction_SetAnnotationsDict(__pyx_t_4, __pyx_t_2); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; if (__Pyx_SetItemOnTypeDict((PyObject *)__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor, __pyx_n_s_encode_as_ids, __pyx_t_4) < 0) __PYX_ERR(0, 120, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; PyType_Modified(__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor); /* "curated_tokenizers/_bbpe.pyx":130 * return self._pieces_to_ids(pieces) * * def encode_as_pieces(self, text: str) -> List[str]: # <<<<<<<<<<<<<< * """ * Split a text into pieces, returning piece pieces. */ __pyx_t_4 = __Pyx_PyDict_NewPresized(2); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 130, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); if (PyDict_SetItem(__pyx_t_4, __pyx_n_s_text, __pyx_n_s_str) < 0) __PYX_ERR(0, 130, __pyx_L1_error) if (PyDict_SetItem(__pyx_t_4, __pyx_n_s_return, __pyx_kp_s_List_str) < 0) __PYX_ERR(0, 130, __pyx_L1_error) __pyx_t_2 = __Pyx_CyFunction_New(&__pyx_mdef_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_15encode_as_pieces, __Pyx_CYFUNCTION_CCLASS, __pyx_n_s_ByteBPEProcessor_encode_as_piece, NULL, __pyx_n_s_curated_tokenizers__bbpe, __pyx_d, ((PyObject *)__pyx_codeobj__20)); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 130, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_CyFunction_SetAnnotationsDict(__pyx_t_2, __pyx_t_4); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (__Pyx_SetItemOnTypeDict((PyObject *)__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor, __pyx_n_s_encode_as_pieces, __pyx_t_2) < 0) __PYX_ERR(0, 130, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; PyType_Modified(__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor); /* "curated_tokenizers/_bbpe.pyx":150 * return [(m1.decode('utf-8'), m2.decode('utf-8')) for m1, m2 in merges_bytes] * * def piece_id(self, piece: str) -> Optional[int]: # <<<<<<<<<<<<<< * """Get the identifier for a piece.""" * return self._piece_to_id.get(piece) */ __pyx_t_2 = __Pyx_PyDict_NewPresized(2); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 150, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (PyDict_SetItem(__pyx_t_2, __pyx_n_s_piece, __pyx_n_s_str) < 0) __PYX_ERR(0, 150, __pyx_L1_error) if (PyDict_SetItem(__pyx_t_2, __pyx_n_s_return, __pyx_kp_s_Optional_int) < 0) __PYX_ERR(0, 150, __pyx_L1_error) __pyx_t_4 = __Pyx_CyFunction_New(&__pyx_mdef_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_17piece_id, __Pyx_CYFUNCTION_CCLASS, __pyx_n_s_ByteBPEProcessor_piece_id, NULL, __pyx_n_s_curated_tokenizers__bbpe, __pyx_d, ((PyObject *)__pyx_codeobj__22)); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 150, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); __Pyx_CyFunction_SetAnnotationsDict(__pyx_t_4, __pyx_t_2); __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; if (__Pyx_SetItemOnTypeDict((PyObject *)__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor, __pyx_n_s_piece_id, __pyx_t_4) < 0) __PYX_ERR(0, 150, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; PyType_Modified(__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor); /* "curated_tokenizers/_bbpe.pyx":159 * return dict(self._piece_to_id) * * def _pieces_to_ids(self, pieces): # <<<<<<<<<<<<<< * piece_ids = [] * for piece in pieces: */ __pyx_t_4 = __Pyx_CyFunction_New(&__pyx_mdef_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_19_pieces_to_ids, __Pyx_CYFUNCTION_CCLASS, __pyx_n_s_ByteBPEProcessor__pieces_to_ids, NULL, __pyx_n_s_curated_tokenizers__bbpe, __pyx_d, ((PyObject *)__pyx_codeobj__24)); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 159, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); if (__Pyx_SetItemOnTypeDict((PyObject *)__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor, __pyx_n_s_pieces_to_ids, __pyx_t_4) < 0) __PYX_ERR(0, 159, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; PyType_Modified(__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor); /* "curated_tokenizers/_bbpe.pyx":169 * return piece_ids * * def __reduce__(self): # <<<<<<<<<<<<<< * return (unpickle_byte_bpe_processor, (self.vocab, self.merges,)) * */ __pyx_t_4 = __Pyx_CyFunction_New(&__pyx_mdef_18curated_tokenizers_5_bbpe_16ByteBPEProcessor_21__reduce__, __Pyx_CYFUNCTION_CCLASS, __pyx_n_s_ByteBPEProcessor___reduce, NULL, __pyx_n_s_curated_tokenizers__bbpe, __pyx_d, ((PyObject *)__pyx_codeobj__25)); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 169, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); if (__Pyx_SetItemOnTypeDict((PyObject *)__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor, __pyx_n_s_reduce, __pyx_t_4) < 0) __PYX_ERR(0, 169, __pyx_L1_error) __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; PyType_Modified(__pyx_ptype_18curated_tokenizers_5_bbpe_ByteBPEProcessor); /* "curated_tokenizers/_bbpe.pyx":172 * return (unpickle_byte_bpe_processor, (self.vocab, self.merges,)) * * def unpickle_byte_bpe_processor(vocab: Dict[str, int], # <<<<<<<<<<<<<< * merges: List[Tuple[str, str]]) -> ByteBPEProcessor: * return ByteBPEProcessor(vocab, merges) */ __pyx_t_4 = __Pyx_PyDict_NewPresized(3); if (unlikely(!__pyx_t_4)) __PYX_ERR(0, 172, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_4); if (PyDict_SetItem(__pyx_t_4, __pyx_n_s_vocab, __pyx_kp_s_Dict_str_int) < 0) __PYX_ERR(0, 172, __pyx_L1_error) if (PyDict_SetItem(__pyx_t_4, __pyx_n_s_merges, __pyx_kp_s_List_Tuple_str_str) < 0) __PYX_ERR(0, 172, __pyx_L1_error) if (PyDict_SetItem(__pyx_t_4, __pyx_n_s_return, __pyx_n_s_ByteBPEProcessor) < 0) __PYX_ERR(0, 172, __pyx_L1_error) __pyx_t_2 = __Pyx_CyFunction_New(&__pyx_mdef_18curated_tokenizers_5_bbpe_3unpickle_byte_bpe_processor, 0, __pyx_n_s_unpickle_byte_bpe_processor, NULL, __pyx_n_s_curated_tokenizers__bbpe, __pyx_d, ((PyObject *)__pyx_codeobj__27)); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 172, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); __Pyx_CyFunction_SetAnnotationsDict(__pyx_t_2, __pyx_t_4); __Pyx_DECREF(__pyx_t_4); __pyx_t_4 = 0; if (PyDict_SetItem(__pyx_d, __pyx_n_s_unpickle_byte_bpe_processor, __pyx_t_2) < 0) __PYX_ERR(0, 172, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; /* "curated_tokenizers/_bbpe.pyx":1 * # cython: infer_types # <<<<<<<<<<<<<< * * from typing import Dict, Iterable, List, Optional, Tuple */ __pyx_t_2 = __Pyx_PyDict_NewPresized(0); if (unlikely(!__pyx_t_2)) __PYX_ERR(0, 1, __pyx_L1_error) __Pyx_GOTREF(__pyx_t_2); if (PyDict_SetItem(__pyx_d, __pyx_n_s_test, __pyx_t_2) < 0) __PYX_ERR(0, 1, __pyx_L1_error) __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0; /*--- Wrapped vars code ---*/ goto __pyx_L0; __pyx_L1_error:; __Pyx_XDECREF(__pyx_t_2); __Pyx_XDECREF(__pyx_t_3); __Pyx_XDECREF(__pyx_t_4); if (__pyx_m) { if (__pyx_d && stringtab_initialized) { __Pyx_AddTraceback("init curated_tokenizers._bbpe", __pyx_clineno, __pyx_lineno, __pyx_filename); } #if !CYTHON_USE_MODULE_STATE Py_CLEAR(__pyx_m); #else Py_DECREF(__pyx_m); if (pystate_addmodule_run) { PyObject *tp, *value, *tb; PyErr_Fetch(&tp, &value, &tb); PyState_RemoveModule(&__pyx_moduledef); PyErr_Restore(tp, value, tb); } #endif } else if (!PyErr_Occurred()) { PyErr_SetString(PyExc_ImportError, "init curated_tokenizers._bbpe"); } __pyx_L0:; __Pyx_RefNannyFinishContext(); #if CYTHON_PEP489_MULTI_PHASE_INIT return (__pyx_m != NULL) ? 0 : -1; #elif PY_MAJOR_VERSION >= 3 return __pyx_m; #else return; #endif } /* #### Code section: cleanup_globals ### */ /* #### Code section: cleanup_module ### */ /* #### Code section: main_method ### */ /* #### Code section: utility_code_pragmas ### */ #ifdef _MSC_VER #pragma warning( push ) /* Warning 4127: conditional expression is constant * Cython uses constant conditional expressions to allow in inline functions to be optimized at * compile-time, so this warning is not useful */ #pragma warning( disable : 4127 ) #endif /* #### Code section: utility_code_def ### */ /* --- Runtime support code --- */ /* Refnanny */ #if CYTHON_REFNANNY static __Pyx_RefNannyAPIStruct *__Pyx_RefNannyImportAPI(const char *modname) { PyObject *m = NULL, *p = NULL; void *r = NULL; m = PyImport_ImportModule(modname); if (!m) goto end; p = PyObject_GetAttrString(m, "RefNannyAPI"); if (!p) goto end; r = PyLong_AsVoidPtr(p); end: Py_XDECREF(p); Py_XDECREF(m); return (__Pyx_RefNannyAPIStruct *)r; } #endif /* PyErrExceptionMatches */ #if CYTHON_FAST_THREAD_STATE static int __Pyx_PyErr_ExceptionMatchesTuple(PyObject *exc_type, PyObject *tuple) { Py_ssize_t i, n; n = PyTuple_GET_SIZE(tuple); #if PY_MAJOR_VERSION >= 3 for (i=0; i= 0x030C00A6 PyObject *current_exception = tstate->current_exception; if (unlikely(!current_exception)) return 0; exc_type = (PyObject*) Py_TYPE(current_exception); if (exc_type == err) return 1; #else exc_type = tstate->curexc_type; if (exc_type == err) return 1; if (unlikely(!exc_type)) return 0; #endif #if CYTHON_AVOID_BORROWED_REFS Py_INCREF(exc_type); #endif if (unlikely(PyTuple_Check(err))) { result = __Pyx_PyErr_ExceptionMatchesTuple(exc_type, err); } else { result = __Pyx_PyErr_GivenExceptionMatches(exc_type, err); } #if CYTHON_AVOID_BORROWED_REFS Py_DECREF(exc_type); #endif return result; } #endif /* PyErrFetchRestore */ #if CYTHON_FAST_THREAD_STATE static CYTHON_INLINE void __Pyx_ErrRestoreInState(PyThreadState *tstate, PyObject *type, PyObject *value, PyObject *tb) { #if PY_VERSION_HEX >= 0x030C00A6 PyObject *tmp_value; assert(type == NULL || (value != NULL && type == (PyObject*) Py_TYPE(value))); if (value) { #if CYTHON_COMPILING_IN_CPYTHON if (unlikely(((PyBaseExceptionObject*) value)->traceback != tb)) #endif PyException_SetTraceback(value, tb); } tmp_value = tstate->current_exception; tstate->current_exception = value; Py_XDECREF(tmp_value); Py_XDECREF(type); Py_XDECREF(tb); #else PyObject *tmp_type, *tmp_value, *tmp_tb; tmp_type = tstate->curexc_type; tmp_value = tstate->curexc_value; tmp_tb = tstate->curexc_traceback; tstate->curexc_type = type; tstate->curexc_value = value; tstate->curexc_traceback = tb; Py_XDECREF(tmp_type); Py_XDECREF(tmp_value); Py_XDECREF(tmp_tb); #endif } static CYTHON_INLINE void __Pyx_ErrFetchInState(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb) { #if PY_VERSION_HEX >= 0x030C00A6 PyObject* exc_value; exc_value = tstate->current_exception; tstate->current_exception = 0; *value = exc_value; *type = NULL; *tb = NULL; if (exc_value) { *type = (PyObject*) Py_TYPE(exc_value); Py_INCREF(*type); #if CYTHON_COMPILING_IN_CPYTHON *tb = ((PyBaseExceptionObject*) exc_value)->traceback; Py_XINCREF(*tb); #else *tb = PyException_GetTraceback(exc_value); #endif } #else *type = tstate->curexc_type; *value = tstate->curexc_value; *tb = tstate->curexc_traceback; tstate->curexc_type = 0; tstate->curexc_value = 0; tstate->curexc_traceback = 0; #endif } #endif /* PyObjectGetAttrStr */ #if CYTHON_USE_TYPE_SLOTS static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStr(PyObject* obj, PyObject* attr_name) { PyTypeObject* tp = Py_TYPE(obj); if (likely(tp->tp_getattro)) return tp->tp_getattro(obj, attr_name); #if PY_MAJOR_VERSION < 3 if (likely(tp->tp_getattr)) return tp->tp_getattr(obj, PyString_AS_STRING(attr_name)); #endif return PyObject_GetAttr(obj, attr_name); } #endif /* PyObjectGetAttrStrNoError */ #if __PYX_LIMITED_VERSION_HEX < 0x030d00A1 static void __Pyx_PyObject_GetAttrStr_ClearAttributeError(void) { __Pyx_PyThreadState_declare __Pyx_PyThreadState_assign if (likely(__Pyx_PyErr_ExceptionMatches(PyExc_AttributeError))) __Pyx_PyErr_Clear(); } #endif static CYTHON_INLINE PyObject* __Pyx_PyObject_GetAttrStrNoError(PyObject* obj, PyObject* attr_name) { PyObject *result; #if __PYX_LIMITED_VERSION_HEX >= 0x030d00A1 (void) PyObject_GetOptionalAttr(obj, attr_name, &result); return result; #else #if CYTHON_COMPILING_IN_CPYTHON && CYTHON_USE_TYPE_SLOTS && PY_VERSION_HEX >= 0x030700B1 PyTypeObject* tp = Py_TYPE(obj); if (likely(tp->tp_getattro == PyObject_GenericGetAttr)) { return _PyObject_GenericGetAttrWithDict(obj, attr_name, NULL, 1); } #endif result = __Pyx_PyObject_GetAttrStr(obj, attr_name); if (unlikely(!result)) { __Pyx_PyObject_GetAttrStr_ClearAttributeError(); } return result; #endif } /* GetBuiltinName */ static PyObject *__Pyx_GetBuiltinName(PyObject *name) { PyObject* result = __Pyx_PyObject_GetAttrStrNoError(__pyx_b, name); if (unlikely(!result) && !PyErr_Occurred()) { PyErr_Format(PyExc_NameError, #if PY_MAJOR_VERSION >= 3 "name '%U' is not defined", name); #else "name '%.200s' is not defined", PyString_AS_STRING(name)); #endif } return result; } /* TupleAndListFromArray */ #if CYTHON_COMPILING_IN_CPYTHON static CYTHON_INLINE void __Pyx_copy_object_array(PyObject *const *CYTHON_RESTRICT src, PyObject** CYTHON_RESTRICT dest, Py_ssize_t length) { PyObject *v; Py_ssize_t i; for (i = 0; i < length; i++) { v = dest[i] = src[i]; Py_INCREF(v); } } static CYTHON_INLINE PyObject * __Pyx_PyTuple_FromArray(PyObject *const *src, Py_ssize_t n) { PyObject *res; if (n <= 0) { Py_INCREF(__pyx_empty_tuple); return __pyx_empty_tuple; } res = PyTuple_New(n); if (unlikely(res == NULL)) return NULL; __Pyx_copy_object_array(src, ((PyTupleObject*)res)->ob_item, n); return res; } static CYTHON_INLINE PyObject * __Pyx_PyList_FromArray(PyObject *const *src, Py_ssize_t n) { PyObject *res; if (n <= 0) { return PyList_New(0); } res = PyList_New(n); if (unlikely(res == NULL)) return NULL; __Pyx_copy_object_array(src, ((PyListObject*)res)->ob_item, n); return res; } #endif /* BytesEquals */ static CYTHON_INLINE int __Pyx_PyBytes_Equals(PyObject* s1, PyObject* s2, int equals) { #if CYTHON_COMPILING_IN_PYPY || CYTHON_COMPILING_IN_LIMITED_API return PyObject_RichCompareBool(s1, s2, equals); #else if (s1 == s2) { return (equals == Py_EQ); } else if (PyBytes_CheckExact(s1) & PyBytes_CheckExact(s2)) { const char *ps1, *ps2; Py_ssize_t length = PyBytes_GET_SIZE(s1); if (length != PyBytes_GET_SIZE(s2)) return (equals == Py_NE); ps1 = PyBytes_AS_STRING(s1); ps2 = PyBytes_AS_STRING(s2); if (ps1[0] != ps2[0]) { return (equals == Py_NE); } else if (length == 1) { return (equals == Py_EQ); } else { int result; #if CYTHON_USE_UNICODE_INTERNALS && (PY_VERSION_HEX < 0x030B0000) Py_hash_t hash1, hash2; hash1 = ((PyBytesObject*)s1)->ob_shash; hash2 = ((PyBytesObject*)s2)->ob_shash; if (hash1 != hash2 && hash1 != -1 && hash2 != -1) { return (equals == Py_NE); } #endif result = memcmp(ps1, ps2, (size_t)length); return (equals == Py_EQ) ? (result == 0) : (result != 0); } } else if ((s1 == Py_None) & PyBytes_CheckExact(s2)) { return (equals == Py_NE); } else if ((s2 == Py_None) & PyBytes_CheckExact(s1)) { return (equals == Py_NE); } else { int result; PyObject* py_result = PyObject_RichCompare(s1, s2, equals); if (!py_result) return -1; result = __Pyx_PyObject_IsTrue(py_result); Py_DECREF(py_result); return result; } #endif } /* UnicodeEquals */ static CYTHON_INLINE int __Pyx_PyUnicode_Equals(PyObject* s1, PyObject* s2, int equals) { #if CYTHON_COMPILING_IN_PYPY || CYTHON_COMPILING_IN_LIMITED_API return PyObject_RichCompareBool(s1, s2, equals); #else #if PY_MAJOR_VERSION < 3 PyObject* owned_ref = NULL; #endif int s1_is_unicode, s2_is_unicode; if (s1 == s2) { goto return_eq; } s1_is_unicode = PyUnicode_CheckExact(s1); s2_is_unicode = PyUnicode_CheckExact(s2); #if PY_MAJOR_VERSION < 3 if ((s1_is_unicode & (!s2_is_unicode)) && PyString_CheckExact(s2)) { owned_ref = PyUnicode_FromObject(s2); if (unlikely(!owned_ref)) return -1; s2 = owned_ref; s2_is_unicode = 1; } else if ((s2_is_unicode & (!s1_is_unicode)) && PyString_CheckExact(s1)) { owned_ref = PyUnicode_FromObject(s1); if (unlikely(!owned_ref)) return -1; s1 = owned_ref; s1_is_unicode = 1; } else if (((!s2_is_unicode) & (!s1_is_unicode))) { return __Pyx_PyBytes_Equals(s1, s2, equals); } #endif if (s1_is_unicode & s2_is_unicode) { Py_ssize_t length; int kind; void *data1, *data2; if (unlikely(__Pyx_PyUnicode_READY(s1) < 0) || unlikely(__Pyx_PyUnicode_READY(s2) < 0)) return -1; length = __Pyx_PyUnicode_GET_LENGTH(s1); if (length != __Pyx_PyUnicode_GET_LENGTH(s2)) { goto return_ne; } #if CYTHON_USE_UNICODE_INTERNALS { Py_hash_t hash1, hash2; #if CYTHON_PEP393_ENABLED hash1 = ((PyASCIIObject*)s1)->hash; hash2 = ((PyASCIIObject*)s2)->hash; #else hash1 = ((PyUnicodeObject*)s1)->hash; hash2 = ((PyUnicodeObject*)s2)->hash; #endif if (hash1 != hash2 && hash1 != -1 && hash2 != -1) { goto return_ne; } } #endif kind = __Pyx_PyUnicode_KIND(s1); if (kind != __Pyx_PyUnicode_KIND(s2)) { goto return_ne; } data1 = __Pyx_PyUnicode_DATA(s1); data2 = __Pyx_PyUnicode_DATA(s2); if (__Pyx_PyUnicode_READ(kind, data1, 0) != __Pyx_PyUnicode_READ(kind, data2, 0)) { goto return_ne; } else if (length == 1) { goto return_eq; } else { int result = memcmp(data1, data2, (size_t)(length * kind)); #if PY_MAJOR_VERSION < 3 Py_XDECREF(owned_ref); #endif return (equals == Py_EQ) ? (result == 0) : (result != 0); } } else if ((s1 == Py_None) & s2_is_unicode) { goto return_ne; } else if ((s2 == Py_None) & s1_is_unicode) { goto return_ne; } else { int result; PyObject* py_result = PyObject_RichCompare(s1, s2, equals); #if PY_MAJOR_VERSION < 3 Py_XDECREF(owned_ref); #endif if (!py_result) return -1; result = __Pyx_PyObject_IsTrue(py_result); Py_DECREF(py_result); return result; } return_eq: #if PY_MAJOR_VERSION < 3 Py_XDECREF(owned_ref); #endif return (equals == Py_EQ); return_ne: #if PY_MAJOR_VERSION < 3 Py_XDECREF(owned_ref); #endif return (equals == Py_NE); #endif } /* fastcall */ #if CYTHON_METH_FASTCALL static CYTHON_INLINE PyObject * __Pyx_GetKwValue_FASTCALL(PyObject *kwnames, PyObject *const *kwvalues, PyObject *s) { Py_ssize_t i, n = PyTuple_GET_SIZE(kwnames); for (i = 0; i < n; i++) { if (s == PyTuple_GET_ITEM(kwnames, i)) return kwvalues[i]; } for (i = 0; i < n; i++) { int eq = __Pyx_PyUnicode_Equals(s, PyTuple_GET_ITEM(kwnames, i), Py_EQ); if (unlikely(eq != 0)) { if (unlikely(eq < 0)) return NULL; return kwvalues[i]; } } return NULL; } #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030d0000 CYTHON_UNUSED static PyObject *__Pyx_KwargsAsDict_FASTCALL(PyObject *kwnames, PyObject *const *kwvalues) { Py_ssize_t i, nkwargs = PyTuple_GET_SIZE(kwnames); PyObject *dict; dict = PyDict_New(); if (unlikely(!dict)) return NULL; for (i=0; itp_call; if (unlikely(!call)) return PyObject_Call(func, arg, kw); #if PY_MAJOR_VERSION < 3 if (unlikely(Py_EnterRecursiveCall((char*)" while calling a Python object"))) return NULL; #else if (unlikely(Py_EnterRecursiveCall(" while calling a Python object"))) return NULL; #endif result = (*call)(func, arg, kw); Py_LeaveRecursiveCall(); if (unlikely(!result) && unlikely(!PyErr_Occurred())) { PyErr_SetString( PyExc_SystemError, "NULL result without error in PyObject_Call"); } return result; } #endif /* SliceTupleAndList */ #if CYTHON_COMPILING_IN_CPYTHON static CYTHON_INLINE void __Pyx_crop_slice(Py_ssize_t* _start, Py_ssize_t* _stop, Py_ssize_t* _length) { Py_ssize_t start = *_start, stop = *_stop, length = *_length; if (start < 0) { start += length; if (start < 0) start = 0; } if (stop < 0) stop += length; else if (stop > length) stop = length; *_length = stop - start; *_start = start; *_stop = stop; } static CYTHON_INLINE PyObject* __Pyx_PyList_GetSlice( PyObject* src, Py_ssize_t start, Py_ssize_t stop) { Py_ssize_t length = PyList_GET_SIZE(src); __Pyx_crop_slice(&start, &stop, &length); if (length <= 0) { return PyList_New(0); } return __Pyx_PyList_FromArray(((PyListObject*)src)->ob_item + start, length); } static CYTHON_INLINE PyObject* __Pyx_PyTuple_GetSlice( PyObject* src, Py_ssize_t start, Py_ssize_t stop) { Py_ssize_t length = PyTuple_GET_SIZE(src); __Pyx_crop_slice(&start, &stop, &length); return __Pyx_PyTuple_FromArray(((PyTupleObject*)src)->ob_item + start, length); } #endif /* PyIntBinop */ #if !CYTHON_COMPILING_IN_PYPY static PyObject* __Pyx_PyInt_AddCObj(PyObject *op1, PyObject *op2, long intval, int inplace, int zerodivision_check) { CYTHON_MAYBE_UNUSED_VAR(intval); CYTHON_MAYBE_UNUSED_VAR(inplace); CYTHON_UNUSED_VAR(zerodivision_check); #if PY_MAJOR_VERSION < 3 if (likely(PyInt_CheckExact(op2))) { const long a = intval; long x; long b = PyInt_AS_LONG(op2); x = (long)((unsigned long)a + (unsigned long)b); if (likely((x^a) >= 0 || (x^b) >= 0)) return PyInt_FromLong(x); return PyLong_Type.tp_as_number->nb_add(op1, op2); } #endif #if CYTHON_USE_PYLONG_INTERNALS if (likely(PyLong_CheckExact(op2))) { const long a = intval; long b, x; #ifdef HAVE_LONG_LONG const PY_LONG_LONG lla = intval; PY_LONG_LONG llb, llx; #endif if (unlikely(__Pyx_PyLong_IsZero(op2))) { return __Pyx_NewRef(op1); } if (likely(__Pyx_PyLong_IsCompact(op2))) { b = __Pyx_PyLong_CompactValue(op2); } else { const digit* digits = __Pyx_PyLong_Digits(op2); const Py_ssize_t size = __Pyx_PyLong_SignedDigitCount(op2); switch (size) { case -2: if (8 * sizeof(long) - 1 > 2 * PyLong_SHIFT) { b = -(long) (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; #ifdef HAVE_LONG_LONG } else if (8 * sizeof(PY_LONG_LONG) - 1 > 2 * PyLong_SHIFT) { llb = -(PY_LONG_LONG) (((((unsigned PY_LONG_LONG)digits[1]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[0])); goto long_long; #endif } CYTHON_FALLTHROUGH; case 2: if (8 * sizeof(long) - 1 > 2 * PyLong_SHIFT) { b = (long) (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; #ifdef HAVE_LONG_LONG } else if (8 * sizeof(PY_LONG_LONG) - 1 > 2 * PyLong_SHIFT) { llb = (PY_LONG_LONG) (((((unsigned PY_LONG_LONG)digits[1]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[0])); goto long_long; #endif } CYTHON_FALLTHROUGH; case -3: if (8 * sizeof(long) - 1 > 3 * PyLong_SHIFT) { b = -(long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; #ifdef HAVE_LONG_LONG } else if (8 * sizeof(PY_LONG_LONG) - 1 > 3 * PyLong_SHIFT) { llb = -(PY_LONG_LONG) (((((((unsigned PY_LONG_LONG)digits[2]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[1]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[0])); goto long_long; #endif } CYTHON_FALLTHROUGH; case 3: if (8 * sizeof(long) - 1 > 3 * PyLong_SHIFT) { b = (long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; #ifdef HAVE_LONG_LONG } else if (8 * sizeof(PY_LONG_LONG) - 1 > 3 * PyLong_SHIFT) { llb = (PY_LONG_LONG) (((((((unsigned PY_LONG_LONG)digits[2]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[1]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[0])); goto long_long; #endif } CYTHON_FALLTHROUGH; case -4: if (8 * sizeof(long) - 1 > 4 * PyLong_SHIFT) { b = -(long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; #ifdef HAVE_LONG_LONG } else if (8 * sizeof(PY_LONG_LONG) - 1 > 4 * PyLong_SHIFT) { llb = -(PY_LONG_LONG) (((((((((unsigned PY_LONG_LONG)digits[3]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[2]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[1]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[0])); goto long_long; #endif } CYTHON_FALLTHROUGH; case 4: if (8 * sizeof(long) - 1 > 4 * PyLong_SHIFT) { b = (long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; #ifdef HAVE_LONG_LONG } else if (8 * sizeof(PY_LONG_LONG) - 1 > 4 * PyLong_SHIFT) { llb = (PY_LONG_LONG) (((((((((unsigned PY_LONG_LONG)digits[3]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[2]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[1]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[0])); goto long_long; #endif } CYTHON_FALLTHROUGH; default: return PyLong_Type.tp_as_number->nb_add(op1, op2); } } x = a + b; return PyLong_FromLong(x); #ifdef HAVE_LONG_LONG long_long: llx = lla + llb; return PyLong_FromLongLong(llx); #endif } #endif if (PyFloat_CheckExact(op2)) { const long a = intval; #if CYTHON_COMPILING_IN_LIMITED_API double b = __pyx_PyFloat_AsDouble(op2); #else double b = PyFloat_AS_DOUBLE(op2); #endif double result; PyFPE_START_PROTECT("add", return NULL) result = ((double)a) + (double)b; PyFPE_END_PROTECT(result) return PyFloat_FromDouble(result); } return (inplace ? PyNumber_InPlaceAdd : PyNumber_Add)(op1, op2); } #endif /* PyIntBinop */ #if !CYTHON_COMPILING_IN_PYPY static PyObject* __Pyx_PyInt_AddObjC(PyObject *op1, PyObject *op2, long intval, int inplace, int zerodivision_check) { CYTHON_MAYBE_UNUSED_VAR(intval); CYTHON_MAYBE_UNUSED_VAR(inplace); CYTHON_UNUSED_VAR(zerodivision_check); #if PY_MAJOR_VERSION < 3 if (likely(PyInt_CheckExact(op1))) { const long b = intval; long x; long a = PyInt_AS_LONG(op1); x = (long)((unsigned long)a + (unsigned long)b); if (likely((x^a) >= 0 || (x^b) >= 0)) return PyInt_FromLong(x); return PyLong_Type.tp_as_number->nb_add(op1, op2); } #endif #if CYTHON_USE_PYLONG_INTERNALS if (likely(PyLong_CheckExact(op1))) { const long b = intval; long a, x; #ifdef HAVE_LONG_LONG const PY_LONG_LONG llb = intval; PY_LONG_LONG lla, llx; #endif if (unlikely(__Pyx_PyLong_IsZero(op1))) { return __Pyx_NewRef(op2); } if (likely(__Pyx_PyLong_IsCompact(op1))) { a = __Pyx_PyLong_CompactValue(op1); } else { const digit* digits = __Pyx_PyLong_Digits(op1); const Py_ssize_t size = __Pyx_PyLong_SignedDigitCount(op1); switch (size) { case -2: if (8 * sizeof(long) - 1 > 2 * PyLong_SHIFT) { a = -(long) (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; #ifdef HAVE_LONG_LONG } else if (8 * sizeof(PY_LONG_LONG) - 1 > 2 * PyLong_SHIFT) { lla = -(PY_LONG_LONG) (((((unsigned PY_LONG_LONG)digits[1]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[0])); goto long_long; #endif } CYTHON_FALLTHROUGH; case 2: if (8 * sizeof(long) - 1 > 2 * PyLong_SHIFT) { a = (long) (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; #ifdef HAVE_LONG_LONG } else if (8 * sizeof(PY_LONG_LONG) - 1 > 2 * PyLong_SHIFT) { lla = (PY_LONG_LONG) (((((unsigned PY_LONG_LONG)digits[1]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[0])); goto long_long; #endif } CYTHON_FALLTHROUGH; case -3: if (8 * sizeof(long) - 1 > 3 * PyLong_SHIFT) { a = -(long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; #ifdef HAVE_LONG_LONG } else if (8 * sizeof(PY_LONG_LONG) - 1 > 3 * PyLong_SHIFT) { lla = -(PY_LONG_LONG) (((((((unsigned PY_LONG_LONG)digits[2]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[1]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[0])); goto long_long; #endif } CYTHON_FALLTHROUGH; case 3: if (8 * sizeof(long) - 1 > 3 * PyLong_SHIFT) { a = (long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; #ifdef HAVE_LONG_LONG } else if (8 * sizeof(PY_LONG_LONG) - 1 > 3 * PyLong_SHIFT) { lla = (PY_LONG_LONG) (((((((unsigned PY_LONG_LONG)digits[2]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[1]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[0])); goto long_long; #endif } CYTHON_FALLTHROUGH; case -4: if (8 * sizeof(long) - 1 > 4 * PyLong_SHIFT) { a = -(long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; #ifdef HAVE_LONG_LONG } else if (8 * sizeof(PY_LONG_LONG) - 1 > 4 * PyLong_SHIFT) { lla = -(PY_LONG_LONG) (((((((((unsigned PY_LONG_LONG)digits[3]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[2]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[1]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[0])); goto long_long; #endif } CYTHON_FALLTHROUGH; case 4: if (8 * sizeof(long) - 1 > 4 * PyLong_SHIFT) { a = (long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0])); break; #ifdef HAVE_LONG_LONG } else if (8 * sizeof(PY_LONG_LONG) - 1 > 4 * PyLong_SHIFT) { lla = (PY_LONG_LONG) (((((((((unsigned PY_LONG_LONG)digits[3]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[2]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[1]) << PyLong_SHIFT) | (unsigned PY_LONG_LONG)digits[0])); goto long_long; #endif } CYTHON_FALLTHROUGH; default: return PyLong_Type.tp_as_number->nb_add(op1, op2); } } x = a + b; return PyLong_FromLong(x); #ifdef HAVE_LONG_LONG long_long: llx = lla + llb; return PyLong_FromLongLong(llx); #endif } #endif if (PyFloat_CheckExact(op1)) { const long b = intval; #if CYTHON_COMPILING_IN_LIMITED_API double a = __pyx_PyFloat_AsDouble(op1); #else double a = PyFloat_AS_DOUBLE(op1); #endif double result; PyFPE_START_PROTECT("add", return NULL) result = ((double)a) + (double)b; PyFPE_END_PROTECT(result) return PyFloat_FromDouble(result); } return (inplace ? PyNumber_InPlaceAdd : PyNumber_Add)(op1, op2); } #endif /* PyFunctionFastCall */ #if CYTHON_FAST_PYCALL && !CYTHON_VECTORCALL static PyObject* __Pyx_PyFunction_FastCallNoKw(PyCodeObject *co, PyObject **args, Py_ssize_t na, PyObject *globals) { PyFrameObject *f; PyThreadState *tstate = __Pyx_PyThreadState_Current; PyObject **fastlocals; Py_ssize_t i; PyObject *result; assert(globals != NULL); /* XXX Perhaps we should create a specialized PyFrame_New() that doesn't take locals, but does take builtins without sanity checking them. */ assert(tstate != NULL); f = PyFrame_New(tstate, co, globals, NULL); if (f == NULL) { return NULL; } fastlocals = __Pyx_PyFrame_GetLocalsplus(f); for (i = 0; i < na; i++) { Py_INCREF(*args); fastlocals[i] = *args++; } result = PyEval_EvalFrameEx(f,0); ++tstate->recursion_depth; Py_DECREF(f); --tstate->recursion_depth; return result; } static PyObject *__Pyx_PyFunction_FastCallDict(PyObject *func, PyObject **args, Py_ssize_t nargs, PyObject *kwargs) { PyCodeObject *co = (PyCodeObject *)PyFunction_GET_CODE(func); PyObject *globals = PyFunction_GET_GLOBALS(func); PyObject *argdefs = PyFunction_GET_DEFAULTS(func); PyObject *closure; #if PY_MAJOR_VERSION >= 3 PyObject *kwdefs; #endif PyObject *kwtuple, **k; PyObject **d; Py_ssize_t nd; Py_ssize_t nk; PyObject *result; assert(kwargs == NULL || PyDict_Check(kwargs)); nk = kwargs ? PyDict_Size(kwargs) : 0; #if PY_MAJOR_VERSION < 3 if (unlikely(Py_EnterRecursiveCall((char*)" while calling a Python object"))) { return NULL; } #else if (unlikely(Py_EnterRecursiveCall(" while calling a Python object"))) { return NULL; } #endif if ( #if PY_MAJOR_VERSION >= 3 co->co_kwonlyargcount == 0 && #endif likely(kwargs == NULL || nk == 0) && co->co_flags == (CO_OPTIMIZED | CO_NEWLOCALS | CO_NOFREE)) { if (argdefs == NULL && co->co_argcount == nargs) { result = __Pyx_PyFunction_FastCallNoKw(co, args, nargs, globals); goto done; } else if (nargs == 0 && argdefs != NULL && co->co_argcount == Py_SIZE(argdefs)) { /* function called with no arguments, but all parameters have a default value: use default values as arguments .*/ args = &PyTuple_GET_ITEM(argdefs, 0); result =__Pyx_PyFunction_FastCallNoKw(co, args, Py_SIZE(argdefs), globals); goto done; } } if (kwargs != NULL) { Py_ssize_t pos, i; kwtuple = PyTuple_New(2 * nk); if (kwtuple == NULL) { result = NULL; goto done; } k = &PyTuple_GET_ITEM(kwtuple, 0); pos = i = 0; while (PyDict_Next(kwargs, &pos, &k[i], &k[i+1])) { Py_INCREF(k[i]); Py_INCREF(k[i+1]); i += 2; } nk = i / 2; } else { kwtuple = NULL; k = NULL; } closure = PyFunction_GET_CLOSURE(func); #if PY_MAJOR_VERSION >= 3 kwdefs = PyFunction_GET_KW_DEFAULTS(func); #endif if (argdefs != NULL) { d = &PyTuple_GET_ITEM(argdefs, 0); nd = Py_SIZE(argdefs); } else { d = NULL; nd = 0; } #if PY_MAJOR_VERSION >= 3 result = PyEval_EvalCodeEx((PyObject*)co, globals, (PyObject *)NULL, args, (int)nargs, k, (int)nk, d, (int)nd, kwdefs, closure); #else result = PyEval_EvalCodeEx(co, globals, (PyObject *)NULL, args, (int)nargs, k, (int)nk, d, (int)nd, closure); #endif Py_XDECREF(kwtuple); done: Py_LeaveRecursiveCall(); return result; } #endif /* PyObjectCallMethO */ #if CYTHON_COMPILING_IN_CPYTHON static CYTHON_INLINE PyObject* __Pyx_PyObject_CallMethO(PyObject *func, PyObject *arg) { PyObject *self, *result; PyCFunction cfunc; cfunc = __Pyx_CyOrPyCFunction_GET_FUNCTION(func); self = __Pyx_CyOrPyCFunction_GET_SELF(func); #if PY_MAJOR_VERSION < 3 if (unlikely(Py_EnterRecursiveCall((char*)" while calling a Python object"))) return NULL; #else if (unlikely(Py_EnterRecursiveCall(" while calling a Python object"))) return NULL; #endif result = cfunc(self, arg); Py_LeaveRecursiveCall(); if (unlikely(!result) && unlikely(!PyErr_Occurred())) { PyErr_SetString( PyExc_SystemError, "NULL result without error in PyObject_Call"); } return result; } #endif /* PyObjectFastCall */ #if PY_VERSION_HEX < 0x03090000 || CYTHON_COMPILING_IN_LIMITED_API static PyObject* __Pyx_PyObject_FastCall_fallback(PyObject *func, PyObject **args, size_t nargs, PyObject *kwargs) { PyObject *argstuple; PyObject *result = 0; size_t i; argstuple = PyTuple_New((Py_ssize_t)nargs); if (unlikely(!argstuple)) return NULL; for (i = 0; i < nargs; i++) { Py_INCREF(args[i]); if (__Pyx_PyTuple_SET_ITEM(argstuple, (Py_ssize_t)i, args[i]) < 0) goto bad; } result = __Pyx_PyObject_Call(func, argstuple, kwargs); bad: Py_DECREF(argstuple); return result; } #endif static CYTHON_INLINE PyObject* __Pyx_PyObject_FastCallDict(PyObject *func, PyObject **args, size_t _nargs, PyObject *kwargs) { Py_ssize_t nargs = __Pyx_PyVectorcall_NARGS(_nargs); #if CYTHON_COMPILING_IN_CPYTHON if (nargs == 0 && kwargs == NULL) { if (__Pyx_CyOrPyCFunction_Check(func) && likely( __Pyx_CyOrPyCFunction_GET_FLAGS(func) & METH_NOARGS)) return __Pyx_PyObject_CallMethO(func, NULL); } else if (nargs == 1 && kwargs == NULL) { if (__Pyx_CyOrPyCFunction_Check(func) && likely( __Pyx_CyOrPyCFunction_GET_FLAGS(func) & METH_O)) return __Pyx_PyObject_CallMethO(func, args[0]); } #endif #if PY_VERSION_HEX < 0x030800B1 #if CYTHON_FAST_PYCCALL if (PyCFunction_Check(func)) { if (kwargs) { return _PyCFunction_FastCallDict(func, args, nargs, kwargs); } else { return _PyCFunction_FastCallKeywords(func, args, nargs, NULL); } } #if PY_VERSION_HEX >= 0x030700A1 if (!kwargs && __Pyx_IS_TYPE(func, &PyMethodDescr_Type)) { return _PyMethodDescr_FastCallKeywords(func, args, nargs, NULL); } #endif #endif #if CYTHON_FAST_PYCALL if (PyFunction_Check(func)) { return __Pyx_PyFunction_FastCallDict(func, args, nargs, kwargs); } #endif #endif if (kwargs == NULL) { #if CYTHON_VECTORCALL #if PY_VERSION_HEX < 0x03090000 vectorcallfunc f = _PyVectorcall_Function(func); #else vectorcallfunc f = PyVectorcall_Function(func); #endif if (f) { return f(func, args, (size_t)nargs, NULL); } #elif defined(__Pyx_CyFunction_USED) && CYTHON_BACKPORT_VECTORCALL if (__Pyx_CyFunction_CheckExact(func)) { __pyx_vectorcallfunc f = __Pyx_CyFunction_func_vectorcall(func); if (f) return f(func, args, (size_t)nargs, NULL); } #endif } if (nargs == 0) { return __Pyx_PyObject_Call(func, __pyx_empty_tuple, kwargs); } #if PY_VERSION_HEX >= 0x03090000 && !CYTHON_COMPILING_IN_LIMITED_API return PyObject_VectorcallDict(func, args, (size_t)nargs, kwargs); #else return __Pyx_PyObject_FastCall_fallback(func, args, (size_t)nargs, kwargs); #endif } /* PyObjectCallOneArg */ static CYTHON_INLINE PyObject* __Pyx_PyObject_CallOneArg(PyObject *func, PyObject *arg) { PyObject *args[2] = {NULL, arg}; return __Pyx_PyObject_FastCall(func, args+1, 1 | __Pyx_PY_VECTORCALL_ARGUMENTS_OFFSET); } /* RaiseArgTupleInvalid */ static void __Pyx_RaiseArgtupleInvalid( const char* func_name, int exact, Py_ssize_t num_min, Py_ssize_t num_max, Py_ssize_t num_found) { Py_ssize_t num_expected; const char *more_or_less; if (num_found < num_min) { num_expected = num_min; more_or_less = "at least"; } else { num_expected = num_max; more_or_less = "at most"; } if (exact) { more_or_less = "exactly"; } PyErr_Format(PyExc_TypeError, "%.200s() takes %.8s %" CYTHON_FORMAT_SSIZE_T "d positional argument%.1s (%" CYTHON_FORMAT_SSIZE_T "d given)", func_name, more_or_less, num_expected, (num_expected == 1) ? "" : "s", num_found); } /* RaiseDoubleKeywords */ static void __Pyx_RaiseDoubleKeywordsError( const char* func_name, PyObject* kw_name) { PyErr_Format(PyExc_TypeError, #if PY_MAJOR_VERSION >= 3 "%s() got multiple values for keyword argument '%U'", func_name, kw_name); #else "%s() got multiple values for keyword argument '%s'", func_name, PyString_AsString(kw_name)); #endif } /* ParseKeywords */ static int __Pyx_ParseOptionalKeywords( PyObject *kwds, PyObject *const *kwvalues, PyObject **argnames[], PyObject *kwds2, PyObject *values[], Py_ssize_t num_pos_args, const char* function_name) { PyObject *key = 0, *value = 0; Py_ssize_t pos = 0; PyObject*** name; PyObject*** first_kw_arg = argnames + num_pos_args; int kwds_is_tuple = CYTHON_METH_FASTCALL && likely(PyTuple_Check(kwds)); while (1) { Py_XDECREF(key); key = NULL; Py_XDECREF(value); value = NULL; if (kwds_is_tuple) { Py_ssize_t size; #if CYTHON_ASSUME_SAFE_MACROS size = PyTuple_GET_SIZE(kwds); #else size = PyTuple_Size(kwds); if (size < 0) goto bad; #endif if (pos >= size) break; #if CYTHON_AVOID_BORROWED_REFS key = __Pyx_PySequence_ITEM(kwds, pos); if (!key) goto bad; #elif CYTHON_ASSUME_SAFE_MACROS key = PyTuple_GET_ITEM(kwds, pos); #else key = PyTuple_GetItem(kwds, pos); if (!key) goto bad; #endif value = kwvalues[pos]; pos++; } else { if (!PyDict_Next(kwds, &pos, &key, &value)) break; #if CYTHON_AVOID_BORROWED_REFS Py_INCREF(key); #endif } name = first_kw_arg; while (*name && (**name != key)) name++; if (*name) { values[name-argnames] = value; #if CYTHON_AVOID_BORROWED_REFS Py_INCREF(value); Py_DECREF(key); #endif key = NULL; value = NULL; continue; } #if !CYTHON_AVOID_BORROWED_REFS Py_INCREF(key); #endif Py_INCREF(value); name = first_kw_arg; #if PY_MAJOR_VERSION < 3 if (likely(PyString_Check(key))) { while (*name) { if ((CYTHON_COMPILING_IN_PYPY || PyString_GET_SIZE(**name) == PyString_GET_SIZE(key)) && _PyString_Eq(**name, key)) { values[name-argnames] = value; #if CYTHON_AVOID_BORROWED_REFS value = NULL; #endif break; } name++; } if (*name) continue; else { PyObject*** argname = argnames; while (argname != first_kw_arg) { if ((**argname == key) || ( (CYTHON_COMPILING_IN_PYPY || PyString_GET_SIZE(**argname) == PyString_GET_SIZE(key)) && _PyString_Eq(**argname, key))) { goto arg_passed_twice; } argname++; } } } else #endif if (likely(PyUnicode_Check(key))) { while (*name) { int cmp = ( #if !CYTHON_COMPILING_IN_PYPY && PY_MAJOR_VERSION >= 3 (__Pyx_PyUnicode_GET_LENGTH(**name) != __Pyx_PyUnicode_GET_LENGTH(key)) ? 1 : #endif PyUnicode_Compare(**name, key) ); if (cmp < 0 && unlikely(PyErr_Occurred())) goto bad; if (cmp == 0) { values[name-argnames] = value; #if CYTHON_AVOID_BORROWED_REFS value = NULL; #endif break; } name++; } if (*name) continue; else { PyObject*** argname = argnames; while (argname != first_kw_arg) { int cmp = (**argname == key) ? 0 : #if !CYTHON_COMPILING_IN_PYPY && PY_MAJOR_VERSION >= 3 (__Pyx_PyUnicode_GET_LENGTH(**argname) != __Pyx_PyUnicode_GET_LENGTH(key)) ? 1 : #endif PyUnicode_Compare(**argname, key); if (cmp < 0 && unlikely(PyErr_Occurred())) goto bad; if (cmp == 0) goto arg_passed_twice; argname++; } } } else goto invalid_keyword_type; if (kwds2) { if (unlikely(PyDict_SetItem(kwds2, key, value))) goto bad; } else { goto invalid_keyword; } } Py_XDECREF(key); Py_XDECREF(value); return 0; arg_passed_twice: __Pyx_RaiseDoubleKeywordsError(function_name, key); goto bad; invalid_keyword_type: PyErr_Format(PyExc_TypeError, "%.200s() keywords must be strings", function_name); goto bad; invalid_keyword: #if PY_MAJOR_VERSION < 3 PyErr_Format(PyExc_TypeError, "%.200s() got an unexpected keyword argument '%.200s'", function_name, PyString_AsString(key)); #else PyErr_Format(PyExc_TypeError, "%s() got an unexpected keyword argument '%U'", function_name, key); #endif bad: Py_XDECREF(key); Py_XDECREF(value); return -1; } /* PyDictVersioning */ #if CYTHON_USE_DICT_VERSIONS && CYTHON_USE_TYPE_SLOTS static CYTHON_INLINE PY_UINT64_T __Pyx_get_tp_dict_version(PyObject *obj) { PyObject *dict = Py_TYPE(obj)->tp_dict; return likely(dict) ? __PYX_GET_DICT_VERSION(dict) : 0; } static CYTHON_INLINE PY_UINT64_T __Pyx_get_object_dict_version(PyObject *obj) { PyObject **dictptr = NULL; Py_ssize_t offset = Py_TYPE(obj)->tp_dictoffset; if (offset) { #if CYTHON_COMPILING_IN_CPYTHON dictptr = (likely(offset > 0)) ? (PyObject **) ((char *)obj + offset) : _PyObject_GetDictPtr(obj); #else dictptr = _PyObject_GetDictPtr(obj); #endif } return (dictptr && *dictptr) ? __PYX_GET_DICT_VERSION(*dictptr) : 0; } static CYTHON_INLINE int __Pyx_object_dict_version_matches(PyObject* obj, PY_UINT64_T tp_dict_version, PY_UINT64_T obj_dict_version) { PyObject *dict = Py_TYPE(obj)->tp_dict; if (unlikely(!dict) || unlikely(tp_dict_version != __PYX_GET_DICT_VERSION(dict))) return 0; return obj_dict_version == __Pyx_get_object_dict_version(obj); } #endif /* GetModuleGlobalName */ #if CYTHON_USE_DICT_VERSIONS static PyObject *__Pyx__GetModuleGlobalName(PyObject *name, PY_UINT64_T *dict_version, PyObject **dict_cached_value) #else static CYTHON_INLINE PyObject *__Pyx__GetModuleGlobalName(PyObject *name) #endif { PyObject *result; #if !CYTHON_AVOID_BORROWED_REFS #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030500A1 && PY_VERSION_HEX < 0x030d0000 result = _PyDict_GetItem_KnownHash(__pyx_d, name, ((PyASCIIObject *) name)->hash); __PYX_UPDATE_DICT_CACHE(__pyx_d, result, *dict_cached_value, *dict_version) if (likely(result)) { return __Pyx_NewRef(result); } else if (unlikely(PyErr_Occurred())) { return NULL; } #elif CYTHON_COMPILING_IN_LIMITED_API if (unlikely(!__pyx_m)) { return NULL; } result = PyObject_GetAttr(__pyx_m, name); if (likely(result)) { return result; } #else result = PyDict_GetItem(__pyx_d, name); __PYX_UPDATE_DICT_CACHE(__pyx_d, result, *dict_cached_value, *dict_version) if (likely(result)) { return __Pyx_NewRef(result); } #endif #else result = PyObject_GetItem(__pyx_d, name); __PYX_UPDATE_DICT_CACHE(__pyx_d, result, *dict_cached_value, *dict_version) if (likely(result)) { return __Pyx_NewRef(result); } PyErr_Clear(); #endif return __Pyx_GetBuiltinName(name); } /* RaiseUnexpectedTypeError */ static int __Pyx_RaiseUnexpectedTypeError(const char *expected, PyObject *obj) { __Pyx_TypeName obj_type_name = __Pyx_PyType_GetName(Py_TYPE(obj)); PyErr_Format(PyExc_TypeError, "Expected %s, got " __Pyx_FMT_TYPENAME, expected, obj_type_name); __Pyx_DECREF_TypeName(obj_type_name); return 0; } /* UnpackUnboundCMethod */ static PyObject *__Pyx_SelflessCall(PyObject *method, PyObject *args, PyObject *kwargs) { PyObject *result; PyObject *selfless_args = PyTuple_GetSlice(args, 1, PyTuple_Size(args)); if (unlikely(!selfless_args)) return NULL; result = PyObject_Call(method, selfless_args, kwargs); Py_DECREF(selfless_args); return result; } static PyMethodDef __Pyx_UnboundCMethod_Def = { "CythonUnboundCMethod", __PYX_REINTERPRET_FUNCION(PyCFunction, __Pyx_SelflessCall), METH_VARARGS | METH_KEYWORDS, NULL }; static int __Pyx_TryUnpackUnboundCMethod(__Pyx_CachedCFunction* target) { PyObject *method; method = __Pyx_PyObject_GetAttrStr(target->type, *target->method_name); if (unlikely(!method)) return -1; target->method = method; #if CYTHON_COMPILING_IN_CPYTHON #if PY_MAJOR_VERSION >= 3 if (likely(__Pyx_TypeCheck(method, &PyMethodDescr_Type))) #else if (likely(!__Pyx_CyOrPyCFunction_Check(method))) #endif { PyMethodDescrObject *descr = (PyMethodDescrObject*) method; target->func = descr->d_method->ml_meth; target->flag = descr->d_method->ml_flags & ~(METH_CLASS | METH_STATIC | METH_COEXIST | METH_STACKLESS); } else #endif #if CYTHON_COMPILING_IN_PYPY #else if (PyCFunction_Check(method)) #endif { PyObject *self; int self_found; #if CYTHON_COMPILING_IN_LIMITED_API || CYTHON_COMPILING_IN_PYPY self = PyObject_GetAttrString(method, "__self__"); if (!self) { PyErr_Clear(); } #else self = PyCFunction_GET_SELF(method); #endif self_found = (self && self != Py_None); #if CYTHON_COMPILING_IN_LIMITED_API || CYTHON_COMPILING_IN_PYPY Py_XDECREF(self); #endif if (self_found) { PyObject *unbound_method = PyCFunction_New(&__Pyx_UnboundCMethod_Def, method); if (unlikely(!unbound_method)) return -1; Py_DECREF(method); target->method = unbound_method; } } return 0; } /* CallUnboundCMethod0 */ static PyObject* __Pyx__CallUnboundCMethod0(__Pyx_CachedCFunction* cfunc, PyObject* self) { PyObject *args, *result = NULL; if (unlikely(!cfunc->method) && unlikely(__Pyx_TryUnpackUnboundCMethod(cfunc) < 0)) return NULL; #if CYTHON_ASSUME_SAFE_MACROS args = PyTuple_New(1); if (unlikely(!args)) goto bad; Py_INCREF(self); PyTuple_SET_ITEM(args, 0, self); #else args = PyTuple_Pack(1, self); if (unlikely(!args)) goto bad; #endif result = __Pyx_PyObject_Call(cfunc->method, args, NULL); Py_DECREF(args); bad: return result; } /* py_dict_items */ static CYTHON_INLINE PyObject* __Pyx_PyDict_Items(PyObject* d) { if (PY_MAJOR_VERSION >= 3) return __Pyx_CallUnboundCMethod0(&__pyx_umethod_PyDict_Type_items, d); else return PyDict_Items(d); } /* RaiseTooManyValuesToUnpack */ static CYTHON_INLINE void __Pyx_RaiseTooManyValuesError(Py_ssize_t expected) { PyErr_Format(PyExc_ValueError, "too many values to unpack (expected %" CYTHON_FORMAT_SSIZE_T "d)", expected); } /* RaiseNeedMoreValuesToUnpack */ static CYTHON_INLINE void __Pyx_RaiseNeedMoreValuesError(Py_ssize_t index) { PyErr_Format(PyExc_ValueError, "need more than %" CYTHON_FORMAT_SSIZE_T "d value%.1s to unpack", index, (index == 1) ? "" : "s"); } /* IterFinish */ static CYTHON_INLINE int __Pyx_IterFinish(void) { PyObject* exc_type; __Pyx_PyThreadState_declare __Pyx_PyThreadState_assign exc_type = __Pyx_PyErr_CurrentExceptionType(); if (unlikely(exc_type)) { if (unlikely(!__Pyx_PyErr_GivenExceptionMatches(exc_type, PyExc_StopIteration))) return -1; __Pyx_PyErr_Clear(); return 0; } return 0; } /* UnpackItemEndCheck */ static int __Pyx_IternextUnpackEndCheck(PyObject *retval, Py_ssize_t expected) { if (unlikely(retval)) { Py_DECREF(retval); __Pyx_RaiseTooManyValuesError(expected); return -1; } return __Pyx_IterFinish(); } /* KeywordStringCheck */ static int __Pyx_CheckKeywordStrings( PyObject *kw, const char* function_name, int kw_allowed) { PyObject* key = 0; Py_ssize_t pos = 0; #if CYTHON_COMPILING_IN_PYPY if (!kw_allowed && PyDict_Next(kw, &pos, &key, 0)) goto invalid_keyword; return 1; #else if (CYTHON_METH_FASTCALL && likely(PyTuple_Check(kw))) { Py_ssize_t kwsize; #if CYTHON_ASSUME_SAFE_MACROS kwsize = PyTuple_GET_SIZE(kw); #else kwsize = PyTuple_Size(kw); if (kwsize < 0) return 0; #endif if (unlikely(kwsize == 0)) return 1; if (!kw_allowed) { #if CYTHON_ASSUME_SAFE_MACROS key = PyTuple_GET_ITEM(kw, 0); #else key = PyTuple_GetItem(kw, pos); if (!key) return 0; #endif goto invalid_keyword; } #if PY_VERSION_HEX < 0x03090000 for (pos = 0; pos < kwsize; pos++) { #if CYTHON_ASSUME_SAFE_MACROS key = PyTuple_GET_ITEM(kw, pos); #else key = PyTuple_GetItem(kw, pos); if (!key) return 0; #endif if (unlikely(!PyUnicode_Check(key))) goto invalid_keyword_type; } #endif return 1; } while (PyDict_Next(kw, &pos, &key, 0)) { #if PY_MAJOR_VERSION < 3 if (unlikely(!PyString_Check(key))) #endif if (unlikely(!PyUnicode_Check(key))) goto invalid_keyword_type; } if (!kw_allowed && unlikely(key)) goto invalid_keyword; return 1; invalid_keyword_type: PyErr_Format(PyExc_TypeError, "%.200s() keywords must be strings", function_name); return 0; #endif invalid_keyword: #if PY_MAJOR_VERSION < 3 PyErr_Format(PyExc_TypeError, "%.200s() got an unexpected keyword argument '%.200s'", function_name, PyString_AsString(key)); #else PyErr_Format(PyExc_TypeError, "%s() got an unexpected keyword argument '%U'", function_name, key); #endif return 0; } /* RaiseKeywordRequired */ static void __Pyx_RaiseKeywordRequired(const char* func_name, PyObject* kw_name) { PyErr_Format(PyExc_TypeError, #if PY_MAJOR_VERSION >= 3 "%s() needs keyword-only argument %U", func_name, kw_name); #else "%s() needs keyword-only argument %s", func_name, PyString_AS_STRING(kw_name)); #endif } /* PyObjectLookupSpecial */ #if CYTHON_USE_PYTYPE_LOOKUP && CYTHON_USE_TYPE_SLOTS static CYTHON_INLINE PyObject* __Pyx__PyObject_LookupSpecial(PyObject* obj, PyObject* attr_name, int with_error) { PyObject *res; PyTypeObject *tp = Py_TYPE(obj); #if PY_MAJOR_VERSION < 3 if (unlikely(PyInstance_Check(obj))) return with_error ? __Pyx_PyObject_GetAttrStr(obj, attr_name) : __Pyx_PyObject_GetAttrStrNoError(obj, attr_name); #endif res = _PyType_Lookup(tp, attr_name); if (likely(res)) { descrgetfunc f = Py_TYPE(res)->tp_descr_get; if (!f) { Py_INCREF(res); } else { res = f(res, obj, (PyObject *)tp); } } else if (with_error) { PyErr_SetObject(PyExc_AttributeError, attr_name); } return res; } #endif /* GetTopmostException */ #if CYTHON_USE_EXC_INFO_STACK && CYTHON_FAST_THREAD_STATE static _PyErr_StackItem * __Pyx_PyErr_GetTopmostException(PyThreadState *tstate) { _PyErr_StackItem *exc_info = tstate->exc_info; while ((exc_info->exc_value == NULL || exc_info->exc_value == Py_None) && exc_info->previous_item != NULL) { exc_info = exc_info->previous_item; } return exc_info; } #endif /* SaveResetException */ #if CYTHON_FAST_THREAD_STATE static CYTHON_INLINE void __Pyx__ExceptionSave(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb) { #if CYTHON_USE_EXC_INFO_STACK && PY_VERSION_HEX >= 0x030B00a4 _PyErr_StackItem *exc_info = __Pyx_PyErr_GetTopmostException(tstate); PyObject *exc_value = exc_info->exc_value; if (exc_value == NULL || exc_value == Py_None) { *value = NULL; *type = NULL; *tb = NULL; } else { *value = exc_value; Py_INCREF(*value); *type = (PyObject*) Py_TYPE(exc_value); Py_INCREF(*type); *tb = PyException_GetTraceback(exc_value); } #elif CYTHON_USE_EXC_INFO_STACK _PyErr_StackItem *exc_info = __Pyx_PyErr_GetTopmostException(tstate); *type = exc_info->exc_type; *value = exc_info->exc_value; *tb = exc_info->exc_traceback; Py_XINCREF(*type); Py_XINCREF(*value); Py_XINCREF(*tb); #else *type = tstate->exc_type; *value = tstate->exc_value; *tb = tstate->exc_traceback; Py_XINCREF(*type); Py_XINCREF(*value); Py_XINCREF(*tb); #endif } static CYTHON_INLINE void __Pyx__ExceptionReset(PyThreadState *tstate, PyObject *type, PyObject *value, PyObject *tb) { #if CYTHON_USE_EXC_INFO_STACK && PY_VERSION_HEX >= 0x030B00a4 _PyErr_StackItem *exc_info = tstate->exc_info; PyObject *tmp_value = exc_info->exc_value; exc_info->exc_value = value; Py_XDECREF(tmp_value); Py_XDECREF(type); Py_XDECREF(tb); #else PyObject *tmp_type, *tmp_value, *tmp_tb; #if CYTHON_USE_EXC_INFO_STACK _PyErr_StackItem *exc_info = tstate->exc_info; tmp_type = exc_info->exc_type; tmp_value = exc_info->exc_value; tmp_tb = exc_info->exc_traceback; exc_info->exc_type = type; exc_info->exc_value = value; exc_info->exc_traceback = tb; #else tmp_type = tstate->exc_type; tmp_value = tstate->exc_value; tmp_tb = tstate->exc_traceback; tstate->exc_type = type; tstate->exc_value = value; tstate->exc_traceback = tb; #endif Py_XDECREF(tmp_type); Py_XDECREF(tmp_value); Py_XDECREF(tmp_tb); #endif } #endif /* GetException */ #if CYTHON_FAST_THREAD_STATE static int __Pyx__GetException(PyThreadState *tstate, PyObject **type, PyObject **value, PyObject **tb) #else static int __Pyx_GetException(PyObject **type, PyObject **value, PyObject **tb) #endif { PyObject *local_type = NULL, *local_value, *local_tb = NULL; #if CYTHON_FAST_THREAD_STATE PyObject *tmp_type, *tmp_value, *tmp_tb; #if PY_VERSION_HEX >= 0x030C00A6 local_value = tstate->current_exception; tstate->current_exception = 0; if (likely(local_value)) { local_type = (PyObject*) Py_TYPE(local_value); Py_INCREF(local_type); local_tb = PyException_GetTraceback(local_value); } #else local_type = tstate->curexc_type; local_value = tstate->curexc_value; local_tb = tstate->curexc_traceback; tstate->curexc_type = 0; tstate->curexc_value = 0; tstate->curexc_traceback = 0; #endif #else PyErr_Fetch(&local_type, &local_value, &local_tb); #endif PyErr_NormalizeException(&local_type, &local_value, &local_tb); #if CYTHON_FAST_THREAD_STATE && PY_VERSION_HEX >= 0x030C00A6 if (unlikely(tstate->current_exception)) #elif CYTHON_FAST_THREAD_STATE if (unlikely(tstate->curexc_type)) #else if (unlikely(PyErr_Occurred())) #endif goto bad; #if PY_MAJOR_VERSION >= 3 if (local_tb) { if (unlikely(PyException_SetTraceback(local_value, local_tb) < 0)) goto bad; } #endif Py_XINCREF(local_tb); Py_XINCREF(local_type); Py_XINCREF(local_value); *type = local_type; *value = local_value; *tb = local_tb; #if CYTHON_FAST_THREAD_STATE #if CYTHON_USE_EXC_INFO_STACK { _PyErr_StackItem *exc_info = tstate->exc_info; #if PY_VERSION_HEX >= 0x030B00a4 tmp_value = exc_info->exc_value; exc_info->exc_value = local_value; tmp_type = NULL; tmp_tb = NULL; Py_XDECREF(local_type); Py_XDECREF(local_tb); #else tmp_type = exc_info->exc_type; tmp_value = exc_info->exc_value; tmp_tb = exc_info->exc_traceback; exc_info->exc_type = local_type; exc_info->exc_value = local_value; exc_info->exc_traceback = local_tb; #endif } #else tmp_type = tstate->exc_type; tmp_value = tstate->exc_value; tmp_tb = tstate->exc_traceback; tstate->exc_type = local_type; tstate->exc_value = local_value; tstate->exc_traceback = local_tb; #endif Py_XDECREF(tmp_type); Py_XDECREF(tmp_value); Py_XDECREF(tmp_tb); #else PyErr_SetExcInfo(local_type, local_value, local_tb); #endif return 0; bad: *type = 0; *value = 0; *tb = 0; Py_XDECREF(local_type); Py_XDECREF(local_value); Py_XDECREF(local_tb); return -1; } /* RaiseException */ #if PY_MAJOR_VERSION < 3 static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, PyObject *cause) { __Pyx_PyThreadState_declare CYTHON_UNUSED_VAR(cause); Py_XINCREF(type); if (!value || value == Py_None) value = NULL; else Py_INCREF(value); if (!tb || tb == Py_None) tb = NULL; else { Py_INCREF(tb); if (!PyTraceBack_Check(tb)) { PyErr_SetString(PyExc_TypeError, "raise: arg 3 must be a traceback or None"); goto raise_error; } } if (PyType_Check(type)) { #if CYTHON_COMPILING_IN_PYPY if (!value) { Py_INCREF(Py_None); value = Py_None; } #endif PyErr_NormalizeException(&type, &value, &tb); } else { if (value) { PyErr_SetString(PyExc_TypeError, "instance exception may not have a separate value"); goto raise_error; } value = type; type = (PyObject*) Py_TYPE(type); Py_INCREF(type); if (!PyType_IsSubtype((PyTypeObject *)type, (PyTypeObject *)PyExc_BaseException)) { PyErr_SetString(PyExc_TypeError, "raise: exception class must be a subclass of BaseException"); goto raise_error; } } __Pyx_PyThreadState_assign __Pyx_ErrRestore(type, value, tb); return; raise_error: Py_XDECREF(value); Py_XDECREF(type); Py_XDECREF(tb); return; } #else static void __Pyx_Raise(PyObject *type, PyObject *value, PyObject *tb, PyObject *cause) { PyObject* owned_instance = NULL; if (tb == Py_None) { tb = 0; } else if (tb && !PyTraceBack_Check(tb)) { PyErr_SetString(PyExc_TypeError, "raise: arg 3 must be a traceback or None"); goto bad; } if (value == Py_None) value = 0; if (PyExceptionInstance_Check(type)) { if (value) { PyErr_SetString(PyExc_TypeError, "instance exception may not have a separate value"); goto bad; } value = type; type = (PyObject*) Py_TYPE(value); } else if (PyExceptionClass_Check(type)) { PyObject *instance_class = NULL; if (value && PyExceptionInstance_Check(value)) { instance_class = (PyObject*) Py_TYPE(value); if (instance_class != type) { int is_subclass = PyObject_IsSubclass(instance_class, type); if (!is_subclass) { instance_class = NULL; } else if (unlikely(is_subclass == -1)) { goto bad; } else { type = instance_class; } } } if (!instance_class) { PyObject *args; if (!value) args = PyTuple_New(0); else if (PyTuple_Check(value)) { Py_INCREF(value); args = value; } else args = PyTuple_Pack(1, value); if (!args) goto bad; owned_instance = PyObject_Call(type, args, NULL); Py_DECREF(args); if (!owned_instance) goto bad; value = owned_instance; if (!PyExceptionInstance_Check(value)) { PyErr_Format(PyExc_TypeError, "calling %R should have returned an instance of " "BaseException, not %R", type, Py_TYPE(value)); goto bad; } } } else { PyErr_SetString(PyExc_TypeError, "raise: exception class must be a subclass of BaseException"); goto bad; } if (cause) { PyObject *fixed_cause; if (cause == Py_None) { fixed_cause = NULL; } else if (PyExceptionClass_Check(cause)) { fixed_cause = PyObject_CallObject(cause, NULL); if (fixed_cause == NULL) goto bad; } else if (PyExceptionInstance_Check(cause)) { fixed_cause = cause; Py_INCREF(fixed_cause); } else { PyErr_SetString(PyExc_TypeError, "exception causes must derive from " "BaseException"); goto bad; } PyException_SetCause(value, fixed_cause); } PyErr_SetObject(type, value); if (tb) { #if PY_VERSION_HEX >= 0x030C00A6 PyException_SetTraceback(value, tb); #elif CYTHON_FAST_THREAD_STATE PyThreadState *tstate = __Pyx_PyThreadState_Current; PyObject* tmp_tb = tstate->curexc_traceback; if (tb != tmp_tb) { Py_INCREF(tb); tstate->curexc_traceback = tb; Py_XDECREF(tmp_tb); } #else PyObject *tmp_type, *tmp_value, *tmp_tb; PyErr_Fetch(&tmp_type, &tmp_value, &tmp_tb); Py_INCREF(tb); PyErr_Restore(tmp_type, tmp_value, tb); Py_XDECREF(tmp_tb); #endif } bad: Py_XDECREF(owned_instance); return; } #endif /* CIntToDigits */ static const char DIGIT_PAIRS_10[2*10*10+1] = { "00010203040506070809" "10111213141516171819" "20212223242526272829" "30313233343536373839" "40414243444546474849" "50515253545556575859" "60616263646566676869" "70717273747576777879" "80818283848586878889" "90919293949596979899" }; static const char DIGIT_PAIRS_8[2*8*8+1] = { "0001020304050607" "1011121314151617" "2021222324252627" "3031323334353637" "4041424344454647" "5051525354555657" "6061626364656667" "7071727374757677" }; static const char DIGITS_HEX[2*16+1] = { "0123456789abcdef" "0123456789ABCDEF" }; /* BuildPyUnicode */ static PyObject* __Pyx_PyUnicode_BuildFromAscii(Py_ssize_t ulength, char* chars, int clength, int prepend_sign, char padding_char) { PyObject *uval; Py_ssize_t uoffset = ulength - clength; #if CYTHON_USE_UNICODE_INTERNALS Py_ssize_t i; #if CYTHON_PEP393_ENABLED void *udata; uval = PyUnicode_New(ulength, 127); if (unlikely(!uval)) return NULL; udata = PyUnicode_DATA(uval); #else Py_UNICODE *udata; uval = PyUnicode_FromUnicode(NULL, ulength); if (unlikely(!uval)) return NULL; udata = PyUnicode_AS_UNICODE(uval); #endif if (uoffset > 0) { i = 0; if (prepend_sign) { __Pyx_PyUnicode_WRITE(PyUnicode_1BYTE_KIND, udata, 0, '-'); i++; } for (; i < uoffset; i++) { __Pyx_PyUnicode_WRITE(PyUnicode_1BYTE_KIND, udata, i, padding_char); } } for (i=0; i < clength; i++) { __Pyx_PyUnicode_WRITE(PyUnicode_1BYTE_KIND, udata, uoffset+i, chars[i]); } #else { PyObject *sign = NULL, *padding = NULL; uval = NULL; if (uoffset > 0) { prepend_sign = !!prepend_sign; if (uoffset > prepend_sign) { padding = PyUnicode_FromOrdinal(padding_char); if (likely(padding) && uoffset > prepend_sign + 1) { PyObject *tmp; PyObject *repeat = PyInt_FromSsize_t(uoffset - prepend_sign); if (unlikely(!repeat)) goto done_or_error; tmp = PyNumber_Multiply(padding, repeat); Py_DECREF(repeat); Py_DECREF(padding); padding = tmp; } if (unlikely(!padding)) goto done_or_error; } if (prepend_sign) { sign = PyUnicode_FromOrdinal('-'); if (unlikely(!sign)) goto done_or_error; } } uval = PyUnicode_DecodeASCII(chars, clength, NULL); if (likely(uval) && padding) { PyObject *tmp = PyNumber_Add(padding, uval); Py_DECREF(uval); uval = tmp; } if (likely(uval) && sign) { PyObject *tmp = PyNumber_Add(sign, uval); Py_DECREF(uval); uval = tmp; } done_or_error: Py_XDECREF(padding); Py_XDECREF(sign); } #endif return uval; } /* CIntToPyUnicode */ static CYTHON_INLINE PyObject* __Pyx_PyUnicode_From_Py_ssize_t(Py_ssize_t value, Py_ssize_t width, char padding_char, char format_char) { char digits[sizeof(Py_ssize_t)*3+2]; char *dpos, *end = digits + sizeof(Py_ssize_t)*3+2; const char *hex_digits = DIGITS_HEX; Py_ssize_t length, ulength; int prepend_sign, last_one_off; Py_ssize_t remaining; #ifdef __Pyx_HAS_GCC_DIAGNOSTIC #pragma GCC diagnostic push #pragma GCC diagnostic ignored "-Wconversion" #endif const Py_ssize_t neg_one = (Py_ssize_t) -1, const_zero = (Py_ssize_t) 0; #ifdef __Pyx_HAS_GCC_DIAGNOSTIC #pragma GCC diagnostic pop #endif const int is_unsigned = neg_one > const_zero; if (format_char == 'X') { hex_digits += 16; format_char = 'x'; } remaining = value; last_one_off = 0; dpos = end; do { int digit_pos; switch (format_char) { case 'o': digit_pos = abs((int)(remaining % (8*8))); remaining = (Py_ssize_t) (remaining / (8*8)); dpos -= 2; memcpy(dpos, DIGIT_PAIRS_8 + digit_pos * 2, 2); last_one_off = (digit_pos < 8); break; case 'd': digit_pos = abs((int)(remaining % (10*10))); remaining = (Py_ssize_t) (remaining / (10*10)); dpos -= 2; memcpy(dpos, DIGIT_PAIRS_10 + digit_pos * 2, 2); last_one_off = (digit_pos < 10); break; case 'x': *(--dpos) = hex_digits[abs((int)(remaining % 16))]; remaining = (Py_ssize_t) (remaining / 16); break; default: assert(0); break; } } while (unlikely(remaining != 0)); assert(!last_one_off || *dpos == '0'); dpos += last_one_off; length = end - dpos; ulength = length; prepend_sign = 0; if (!is_unsigned && value <= neg_one) { if (padding_char == ' ' || width <= length + 1) { *(--dpos) = '-'; ++length; } else { prepend_sign = 1; } ++ulength; } if (width > ulength) { ulength = width; } if (ulength == 1) { return PyUnicode_FromOrdinal(*dpos); } return __Pyx_PyUnicode_BuildFromAscii(ulength, dpos, (int) length, prepend_sign, padding_char); } /* JoinPyUnicode */ static PyObject* __Pyx_PyUnicode_Join(PyObject* value_tuple, Py_ssize_t value_count, Py_ssize_t result_ulength, Py_UCS4 max_char) { #if CYTHON_USE_UNICODE_INTERNALS && CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS PyObject *result_uval; int result_ukind, kind_shift; Py_ssize_t i, char_pos; void *result_udata; CYTHON_MAYBE_UNUSED_VAR(max_char); #if CYTHON_PEP393_ENABLED result_uval = PyUnicode_New(result_ulength, max_char); if (unlikely(!result_uval)) return NULL; result_ukind = (max_char <= 255) ? PyUnicode_1BYTE_KIND : (max_char <= 65535) ? PyUnicode_2BYTE_KIND : PyUnicode_4BYTE_KIND; kind_shift = (result_ukind == PyUnicode_4BYTE_KIND) ? 2 : result_ukind - 1; result_udata = PyUnicode_DATA(result_uval); #else result_uval = PyUnicode_FromUnicode(NULL, result_ulength); if (unlikely(!result_uval)) return NULL; result_ukind = sizeof(Py_UNICODE); kind_shift = (result_ukind == 4) ? 2 : result_ukind - 1; result_udata = PyUnicode_AS_UNICODE(result_uval); #endif assert(kind_shift == 2 || kind_shift == 1 || kind_shift == 0); char_pos = 0; for (i=0; i < value_count; i++) { int ukind; Py_ssize_t ulength; void *udata; PyObject *uval = PyTuple_GET_ITEM(value_tuple, i); if (unlikely(__Pyx_PyUnicode_READY(uval))) goto bad; ulength = __Pyx_PyUnicode_GET_LENGTH(uval); if (unlikely(!ulength)) continue; if (unlikely((PY_SSIZE_T_MAX >> kind_shift) - ulength < char_pos)) goto overflow; ukind = __Pyx_PyUnicode_KIND(uval); udata = __Pyx_PyUnicode_DATA(uval); if (!CYTHON_PEP393_ENABLED || ukind == result_ukind) { memcpy((char *)result_udata + (char_pos << kind_shift), udata, (size_t) (ulength << kind_shift)); } else { #if PY_VERSION_HEX >= 0x030d0000 if (unlikely(PyUnicode_CopyCharacters(result_uval, char_pos, uval, 0, ulength) < 0)) goto bad; #elif CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030300F0 || defined(_PyUnicode_FastCopyCharacters) _PyUnicode_FastCopyCharacters(result_uval, char_pos, uval, 0, ulength); #else Py_ssize_t j; for (j=0; j < ulength; j++) { Py_UCS4 uchar = __Pyx_PyUnicode_READ(ukind, udata, j); __Pyx_PyUnicode_WRITE(result_ukind, result_udata, char_pos+j, uchar); } #endif } char_pos += ulength; } return result_uval; overflow: PyErr_SetString(PyExc_OverflowError, "join() result is too long for a Python string"); bad: Py_DECREF(result_uval); return NULL; #else CYTHON_UNUSED_VAR(max_char); CYTHON_UNUSED_VAR(result_ulength); CYTHON_UNUSED_VAR(value_count); return PyUnicode_Join(__pyx_empty_unicode, value_tuple); #endif } /* PyObjectCall2Args */ static CYTHON_INLINE PyObject* __Pyx_PyObject_Call2Args(PyObject* function, PyObject* arg1, PyObject* arg2) { PyObject *args[3] = {NULL, arg1, arg2}; return __Pyx_PyObject_FastCall(function, args+1, 2 | __Pyx_PY_VECTORCALL_ARGUMENTS_OFFSET); } /* PyObjectGetMethod */ static int __Pyx_PyObject_GetMethod(PyObject *obj, PyObject *name, PyObject **method) { PyObject *attr; #if CYTHON_UNPACK_METHODS && CYTHON_COMPILING_IN_CPYTHON && CYTHON_USE_PYTYPE_LOOKUP __Pyx_TypeName type_name; PyTypeObject *tp = Py_TYPE(obj); PyObject *descr; descrgetfunc f = NULL; PyObject **dictptr, *dict; int meth_found = 0; assert (*method == NULL); if (unlikely(tp->tp_getattro != PyObject_GenericGetAttr)) { attr = __Pyx_PyObject_GetAttrStr(obj, name); goto try_unpack; } if (unlikely(tp->tp_dict == NULL) && unlikely(PyType_Ready(tp) < 0)) { return 0; } descr = _PyType_Lookup(tp, name); if (likely(descr != NULL)) { Py_INCREF(descr); #if defined(Py_TPFLAGS_METHOD_DESCRIPTOR) && Py_TPFLAGS_METHOD_DESCRIPTOR if (__Pyx_PyType_HasFeature(Py_TYPE(descr), Py_TPFLAGS_METHOD_DESCRIPTOR)) #elif PY_MAJOR_VERSION >= 3 #ifdef __Pyx_CyFunction_USED if (likely(PyFunction_Check(descr) || __Pyx_IS_TYPE(descr, &PyMethodDescr_Type) || __Pyx_CyFunction_Check(descr))) #else if (likely(PyFunction_Check(descr) || __Pyx_IS_TYPE(descr, &PyMethodDescr_Type))) #endif #else #ifdef __Pyx_CyFunction_USED if (likely(PyFunction_Check(descr) || __Pyx_CyFunction_Check(descr))) #else if (likely(PyFunction_Check(descr))) #endif #endif { meth_found = 1; } else { f = Py_TYPE(descr)->tp_descr_get; if (f != NULL && PyDescr_IsData(descr)) { attr = f(descr, obj, (PyObject *)Py_TYPE(obj)); Py_DECREF(descr); goto try_unpack; } } } dictptr = _PyObject_GetDictPtr(obj); if (dictptr != NULL && (dict = *dictptr) != NULL) { Py_INCREF(dict); attr = __Pyx_PyDict_GetItemStr(dict, name); if (attr != NULL) { Py_INCREF(attr); Py_DECREF(dict); Py_XDECREF(descr); goto try_unpack; } Py_DECREF(dict); } if (meth_found) { *method = descr; return 1; } if (f != NULL) { attr = f(descr, obj, (PyObject *)Py_TYPE(obj)); Py_DECREF(descr); goto try_unpack; } if (likely(descr != NULL)) { *method = descr; return 0; } type_name = __Pyx_PyType_GetName(tp); PyErr_Format(PyExc_AttributeError, #if PY_MAJOR_VERSION >= 3 "'" __Pyx_FMT_TYPENAME "' object has no attribute '%U'", type_name, name); #else "'" __Pyx_FMT_TYPENAME "' object has no attribute '%.400s'", type_name, PyString_AS_STRING(name)); #endif __Pyx_DECREF_TypeName(type_name); return 0; #else attr = __Pyx_PyObject_GetAttrStr(obj, name); goto try_unpack; #endif try_unpack: #if CYTHON_UNPACK_METHODS if (likely(attr) && PyMethod_Check(attr) && likely(PyMethod_GET_SELF(attr) == obj)) { PyObject *function = PyMethod_GET_FUNCTION(attr); Py_INCREF(function); Py_DECREF(attr); *method = function; return 1; } #endif *method = attr; return 0; } /* PyObjectCallMethod1 */ #if !(CYTHON_VECTORCALL && __PYX_LIMITED_VERSION_HEX >= 0x030C00A2) static PyObject* __Pyx__PyObject_CallMethod1(PyObject* method, PyObject* arg) { PyObject *result = __Pyx_PyObject_CallOneArg(method, arg); Py_DECREF(method); return result; } #endif static PyObject* __Pyx_PyObject_CallMethod1(PyObject* obj, PyObject* method_name, PyObject* arg) { #if CYTHON_VECTORCALL && __PYX_LIMITED_VERSION_HEX >= 0x030C00A2 PyObject *args[2] = {obj, arg}; (void) __Pyx_PyObject_GetMethod; (void) __Pyx_PyObject_CallOneArg; (void) __Pyx_PyObject_Call2Args; return PyObject_VectorcallMethod(method_name, args, 2 | PY_VECTORCALL_ARGUMENTS_OFFSET, NULL); #else PyObject *method = NULL, *result; int is_method = __Pyx_PyObject_GetMethod(obj, method_name, &method); if (likely(is_method)) { result = __Pyx_PyObject_Call2Args(method, obj, arg); Py_DECREF(method); return result; } if (unlikely(!method)) return NULL; return __Pyx__PyObject_CallMethod1(method, arg); #endif } /* append */ static CYTHON_INLINE int __Pyx_PyObject_Append(PyObject* L, PyObject* x) { if (likely(PyList_CheckExact(L))) { if (unlikely(__Pyx_PyList_Append(L, x) < 0)) return -1; } else { PyObject* retval = __Pyx_PyObject_CallMethod1(L, __pyx_n_s_append, x); if (unlikely(!retval)) return -1; Py_DECREF(retval); } return 0; } /* CallUnboundCMethod1 */ #if CYTHON_COMPILING_IN_CPYTHON static CYTHON_INLINE PyObject* __Pyx_CallUnboundCMethod1(__Pyx_CachedCFunction* cfunc, PyObject* self, PyObject* arg) { if (likely(cfunc->func)) { int flag = cfunc->flag; if (flag == METH_O) { return (*(cfunc->func))(self, arg); } else if ((PY_VERSION_HEX >= 0x030600B1) && flag == METH_FASTCALL) { #if PY_VERSION_HEX >= 0x030700A0 return (*(__Pyx_PyCFunctionFast)(void*)(PyCFunction)cfunc->func)(self, &arg, 1); #else return (*(__Pyx_PyCFunctionFastWithKeywords)(void*)(PyCFunction)cfunc->func)(self, &arg, 1, NULL); #endif } else if ((PY_VERSION_HEX >= 0x030700A0) && flag == (METH_FASTCALL | METH_KEYWORDS)) { return (*(__Pyx_PyCFunctionFastWithKeywords)(void*)(PyCFunction)cfunc->func)(self, &arg, 1, NULL); } } return __Pyx__CallUnboundCMethod1(cfunc, self, arg); } #endif static PyObject* __Pyx__CallUnboundCMethod1(__Pyx_CachedCFunction* cfunc, PyObject* self, PyObject* arg){ PyObject *args, *result = NULL; if (unlikely(!cfunc->func && !cfunc->method) && unlikely(__Pyx_TryUnpackUnboundCMethod(cfunc) < 0)) return NULL; #if CYTHON_COMPILING_IN_CPYTHON if (cfunc->func && (cfunc->flag & METH_VARARGS)) { args = PyTuple_New(1); if (unlikely(!args)) goto bad; Py_INCREF(arg); PyTuple_SET_ITEM(args, 0, arg); if (cfunc->flag & METH_KEYWORDS) result = (*(PyCFunctionWithKeywords)(void*)(PyCFunction)cfunc->func)(self, args, NULL); else result = (*cfunc->func)(self, args); } else { args = PyTuple_New(2); if (unlikely(!args)) goto bad; Py_INCREF(self); PyTuple_SET_ITEM(args, 0, self); Py_INCREF(arg); PyTuple_SET_ITEM(args, 1, arg); result = __Pyx_PyObject_Call(cfunc->method, args, NULL); } #else args = PyTuple_Pack(2, self, arg); if (unlikely(!args)) goto bad; result = __Pyx_PyObject_Call(cfunc->method, args, NULL); #endif bad: Py_XDECREF(args); return result; } /* CallUnboundCMethod2 */ #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030600B1 static CYTHON_INLINE PyObject *__Pyx_CallUnboundCMethod2(__Pyx_CachedCFunction *cfunc, PyObject *self, PyObject *arg1, PyObject *arg2) { if (likely(cfunc->func)) { PyObject *args[2] = {arg1, arg2}; if (cfunc->flag == METH_FASTCALL) { #if PY_VERSION_HEX >= 0x030700A0 return (*(__Pyx_PyCFunctionFast)(void*)(PyCFunction)cfunc->func)(self, args, 2); #else return (*(__Pyx_PyCFunctionFastWithKeywords)(void*)(PyCFunction)cfunc->func)(self, args, 2, NULL); #endif } #if PY_VERSION_HEX >= 0x030700A0 if (cfunc->flag == (METH_FASTCALL | METH_KEYWORDS)) return (*(__Pyx_PyCFunctionFastWithKeywords)(void*)(PyCFunction)cfunc->func)(self, args, 2, NULL); #endif } return __Pyx__CallUnboundCMethod2(cfunc, self, arg1, arg2); } #endif static PyObject* __Pyx__CallUnboundCMethod2(__Pyx_CachedCFunction* cfunc, PyObject* self, PyObject* arg1, PyObject* arg2){ PyObject *args, *result = NULL; if (unlikely(!cfunc->func && !cfunc->method) && unlikely(__Pyx_TryUnpackUnboundCMethod(cfunc) < 0)) return NULL; #if CYTHON_COMPILING_IN_CPYTHON if (cfunc->func && (cfunc->flag & METH_VARARGS)) { args = PyTuple_New(2); if (unlikely(!args)) goto bad; Py_INCREF(arg1); PyTuple_SET_ITEM(args, 0, arg1); Py_INCREF(arg2); PyTuple_SET_ITEM(args, 1, arg2); if (cfunc->flag & METH_KEYWORDS) result = (*(PyCFunctionWithKeywords)(void*)(PyCFunction)cfunc->func)(self, args, NULL); else result = (*cfunc->func)(self, args); } else { args = PyTuple_New(3); if (unlikely(!args)) goto bad; Py_INCREF(self); PyTuple_SET_ITEM(args, 0, self); Py_INCREF(arg1); PyTuple_SET_ITEM(args, 1, arg1); Py_INCREF(arg2); PyTuple_SET_ITEM(args, 2, arg2); result = __Pyx_PyObject_Call(cfunc->method, args, NULL); } #else args = PyTuple_Pack(3, self, arg1, arg2); if (unlikely(!args)) goto bad; result = __Pyx_PyObject_Call(cfunc->method, args, NULL); #endif bad: Py_XDECREF(args); return result; } /* dict_getitem_default */ static PyObject* __Pyx_PyDict_GetItemDefault(PyObject* d, PyObject* key, PyObject* default_value) { PyObject* value; #if PY_MAJOR_VERSION >= 3 && (!CYTHON_COMPILING_IN_PYPY || PYPY_VERSION_NUM >= 0x07020000) value = PyDict_GetItemWithError(d, key); if (unlikely(!value)) { if (unlikely(PyErr_Occurred())) return NULL; value = default_value; } Py_INCREF(value); if ((1)); #else if (PyString_CheckExact(key) || PyUnicode_CheckExact(key) || PyInt_CheckExact(key)) { value = PyDict_GetItem(d, key); if (unlikely(!value)) { value = default_value; } Py_INCREF(value); } #endif else { if (default_value == Py_None) value = __Pyx_CallUnboundCMethod1(&__pyx_umethod_PyDict_Type_get, d, key); else value = __Pyx_CallUnboundCMethod2(&__pyx_umethod_PyDict_Type_get, d, key, default_value); } return value; } /* DictGetItem */ #if PY_MAJOR_VERSION >= 3 && !CYTHON_COMPILING_IN_PYPY static PyObject *__Pyx_PyDict_GetItem(PyObject *d, PyObject* key) { PyObject *value; value = PyDict_GetItemWithError(d, key); if (unlikely(!value)) { if (!PyErr_Occurred()) { if (unlikely(PyTuple_Check(key))) { PyObject* args = PyTuple_Pack(1, key); if (likely(args)) { PyErr_SetObject(PyExc_KeyError, args); Py_DECREF(args); } } else { PyErr_SetObject(PyExc_KeyError, key); } } return NULL; } Py_INCREF(value); return value; } #endif /* decode_c_bytes */ static CYTHON_INLINE PyObject* __Pyx_decode_c_bytes( const char* cstring, Py_ssize_t length, Py_ssize_t start, Py_ssize_t stop, const char* encoding, const char* errors, PyObject* (*decode_func)(const char *s, Py_ssize_t size, const char *errors)) { if (unlikely((start < 0) | (stop < 0))) { if (start < 0) { start += length; if (start < 0) start = 0; } if (stop < 0) stop += length; } if (stop > length) stop = length; if (unlikely(stop <= start)) return __Pyx_NewRef(__pyx_empty_unicode); length = stop - start; cstring += start; if (decode_func) { return decode_func(cstring, length, errors); } else { return PyUnicode_Decode(cstring, length, encoding, errors); } } /* FixUpExtensionType */ #if CYTHON_USE_TYPE_SPECS static int __Pyx_fix_up_extension_type_from_spec(PyType_Spec *spec, PyTypeObject *type) { #if PY_VERSION_HEX > 0x030900B1 || CYTHON_COMPILING_IN_LIMITED_API CYTHON_UNUSED_VAR(spec); CYTHON_UNUSED_VAR(type); #else const PyType_Slot *slot = spec->slots; while (slot && slot->slot && slot->slot != Py_tp_members) slot++; if (slot && slot->slot == Py_tp_members) { int changed = 0; #if !(PY_VERSION_HEX <= 0x030900b1 && CYTHON_COMPILING_IN_CPYTHON) const #endif PyMemberDef *memb = (PyMemberDef*) slot->pfunc; while (memb && memb->name) { if (memb->name[0] == '_' && memb->name[1] == '_') { #if PY_VERSION_HEX < 0x030900b1 if (strcmp(memb->name, "__weaklistoffset__") == 0) { assert(memb->type == T_PYSSIZET); assert(memb->flags == READONLY); type->tp_weaklistoffset = memb->offset; changed = 1; } else if (strcmp(memb->name, "__dictoffset__") == 0) { assert(memb->type == T_PYSSIZET); assert(memb->flags == READONLY); type->tp_dictoffset = memb->offset; changed = 1; } #if CYTHON_METH_FASTCALL else if (strcmp(memb->name, "__vectorcalloffset__") == 0) { assert(memb->type == T_PYSSIZET); assert(memb->flags == READONLY); #if PY_VERSION_HEX >= 0x030800b4 type->tp_vectorcall_offset = memb->offset; #else type->tp_print = (printfunc) memb->offset; #endif changed = 1; } #endif #else if ((0)); #endif #if PY_VERSION_HEX <= 0x030900b1 && CYTHON_COMPILING_IN_CPYTHON else if (strcmp(memb->name, "__module__") == 0) { PyObject *descr; assert(memb->type == T_OBJECT); assert(memb->flags == 0 || memb->flags == READONLY); descr = PyDescr_NewMember(type, memb); if (unlikely(!descr)) return -1; if (unlikely(PyDict_SetItem(type->tp_dict, PyDescr_NAME(descr), descr) < 0)) { Py_DECREF(descr); return -1; } Py_DECREF(descr); changed = 1; } #endif } memb++; } if (changed) PyType_Modified(type); } #endif return 0; } #endif /* PyObjectCallNoArg */ static CYTHON_INLINE PyObject* __Pyx_PyObject_CallNoArg(PyObject *func) { PyObject *arg[2] = {NULL, NULL}; return __Pyx_PyObject_FastCall(func, arg + 1, 0 | __Pyx_PY_VECTORCALL_ARGUMENTS_OFFSET); } /* PyObjectCallMethod0 */ static PyObject* __Pyx_PyObject_CallMethod0(PyObject* obj, PyObject* method_name) { PyObject *method = NULL, *result = NULL; int is_method = __Pyx_PyObject_GetMethod(obj, method_name, &method); if (likely(is_method)) { result = __Pyx_PyObject_CallOneArg(method, obj); Py_DECREF(method); return result; } if (unlikely(!method)) goto bad; result = __Pyx_PyObject_CallNoArg(method); Py_DECREF(method); bad: return result; } /* ValidateBasesTuple */ #if CYTHON_COMPILING_IN_CPYTHON || CYTHON_COMPILING_IN_LIMITED_API || CYTHON_USE_TYPE_SPECS static int __Pyx_validate_bases_tuple(const char *type_name, Py_ssize_t dictoffset, PyObject *bases) { Py_ssize_t i, n; #if CYTHON_ASSUME_SAFE_MACROS n = PyTuple_GET_SIZE(bases); #else n = PyTuple_Size(bases); if (n < 0) return -1; #endif for (i = 1; i < n; i++) { #if CYTHON_AVOID_BORROWED_REFS PyObject *b0 = PySequence_GetItem(bases, i); if (!b0) return -1; #elif CYTHON_ASSUME_SAFE_MACROS PyObject *b0 = PyTuple_GET_ITEM(bases, i); #else PyObject *b0 = PyTuple_GetItem(bases, i); if (!b0) return -1; #endif PyTypeObject *b; #if PY_MAJOR_VERSION < 3 if (PyClass_Check(b0)) { PyErr_Format(PyExc_TypeError, "base class '%.200s' is an old-style class", PyString_AS_STRING(((PyClassObject*)b0)->cl_name)); #if CYTHON_AVOID_BORROWED_REFS Py_DECREF(b0); #endif return -1; } #endif b = (PyTypeObject*) b0; if (!__Pyx_PyType_HasFeature(b, Py_TPFLAGS_HEAPTYPE)) { __Pyx_TypeName b_name = __Pyx_PyType_GetName(b); PyErr_Format(PyExc_TypeError, "base class '" __Pyx_FMT_TYPENAME "' is not a heap type", b_name); __Pyx_DECREF_TypeName(b_name); #if CYTHON_AVOID_BORROWED_REFS Py_DECREF(b0); #endif return -1; } if (dictoffset == 0) { Py_ssize_t b_dictoffset = 0; #if CYTHON_USE_TYPE_SLOTS || CYTHON_COMPILING_IN_PYPY b_dictoffset = b->tp_dictoffset; #else PyObject *py_b_dictoffset = PyObject_GetAttrString((PyObject*)b, "__dictoffset__"); if (!py_b_dictoffset) goto dictoffset_return; b_dictoffset = PyLong_AsSsize_t(py_b_dictoffset); Py_DECREF(py_b_dictoffset); if (b_dictoffset == -1 && PyErr_Occurred()) goto dictoffset_return; #endif if (b_dictoffset) { { __Pyx_TypeName b_name = __Pyx_PyType_GetName(b); PyErr_Format(PyExc_TypeError, "extension type '%.200s' has no __dict__ slot, " "but base type '" __Pyx_FMT_TYPENAME "' has: " "either add 'cdef dict __dict__' to the extension type " "or add '__slots__ = [...]' to the base type", type_name, b_name); __Pyx_DECREF_TypeName(b_name); } #if !(CYTHON_USE_TYPE_SLOTS || CYTHON_COMPILING_IN_PYPY) dictoffset_return: #endif #if CYTHON_AVOID_BORROWED_REFS Py_DECREF(b0); #endif return -1; } } #if CYTHON_AVOID_BORROWED_REFS Py_DECREF(b0); #endif } return 0; } #endif /* PyType_Ready */ static int __Pyx_PyType_Ready(PyTypeObject *t) { #if CYTHON_USE_TYPE_SPECS || !(CYTHON_COMPILING_IN_CPYTHON || CYTHON_COMPILING_IN_LIMITED_API) || defined(PYSTON_MAJOR_VERSION) (void)__Pyx_PyObject_CallMethod0; #if CYTHON_USE_TYPE_SPECS (void)__Pyx_validate_bases_tuple; #endif return PyType_Ready(t); #else int r; PyObject *bases = __Pyx_PyType_GetSlot(t, tp_bases, PyObject*); if (bases && unlikely(__Pyx_validate_bases_tuple(t->tp_name, t->tp_dictoffset, bases) == -1)) return -1; #if PY_VERSION_HEX >= 0x03050000 && !defined(PYSTON_MAJOR_VERSION) { int gc_was_enabled; #if PY_VERSION_HEX >= 0x030A00b1 gc_was_enabled = PyGC_Disable(); (void)__Pyx_PyObject_CallMethod0; #else PyObject *ret, *py_status; PyObject *gc = NULL; #if PY_VERSION_HEX >= 0x030700a1 && (!CYTHON_COMPILING_IN_PYPY || PYPY_VERSION_NUM+0 >= 0x07030400) gc = PyImport_GetModule(__pyx_kp_u_gc); #endif if (unlikely(!gc)) gc = PyImport_Import(__pyx_kp_u_gc); if (unlikely(!gc)) return -1; py_status = __Pyx_PyObject_CallMethod0(gc, __pyx_kp_u_isenabled); if (unlikely(!py_status)) { Py_DECREF(gc); return -1; } gc_was_enabled = __Pyx_PyObject_IsTrue(py_status); Py_DECREF(py_status); if (gc_was_enabled > 0) { ret = __Pyx_PyObject_CallMethod0(gc, __pyx_kp_u_disable); if (unlikely(!ret)) { Py_DECREF(gc); return -1; } Py_DECREF(ret); } else if (unlikely(gc_was_enabled == -1)) { Py_DECREF(gc); return -1; } #endif t->tp_flags |= Py_TPFLAGS_HEAPTYPE; #if PY_VERSION_HEX >= 0x030A0000 t->tp_flags |= Py_TPFLAGS_IMMUTABLETYPE; #endif #else (void)__Pyx_PyObject_CallMethod0; #endif r = PyType_Ready(t); #if PY_VERSION_HEX >= 0x03050000 && !defined(PYSTON_MAJOR_VERSION) t->tp_flags &= ~Py_TPFLAGS_HEAPTYPE; #if PY_VERSION_HEX >= 0x030A00b1 if (gc_was_enabled) PyGC_Enable(); #else if (gc_was_enabled) { PyObject *tp, *v, *tb; PyErr_Fetch(&tp, &v, &tb); ret = __Pyx_PyObject_CallMethod0(gc, __pyx_kp_u_enable); if (likely(ret || r == -1)) { Py_XDECREF(ret); PyErr_Restore(tp, v, tb); } else { Py_XDECREF(tp); Py_XDECREF(v); Py_XDECREF(tb); r = -1; } } Py_DECREF(gc); #endif } #endif return r; #endif } /* PyObject_GenericGetAttrNoDict */ #if CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP && PY_VERSION_HEX < 0x03070000 static PyObject *__Pyx_RaiseGenericGetAttributeError(PyTypeObject *tp, PyObject *attr_name) { __Pyx_TypeName type_name = __Pyx_PyType_GetName(tp); PyErr_Format(PyExc_AttributeError, #if PY_MAJOR_VERSION >= 3 "'" __Pyx_FMT_TYPENAME "' object has no attribute '%U'", type_name, attr_name); #else "'" __Pyx_FMT_TYPENAME "' object has no attribute '%.400s'", type_name, PyString_AS_STRING(attr_name)); #endif __Pyx_DECREF_TypeName(type_name); return NULL; } static CYTHON_INLINE PyObject* __Pyx_PyObject_GenericGetAttrNoDict(PyObject* obj, PyObject* attr_name) { PyObject *descr; PyTypeObject *tp = Py_TYPE(obj); if (unlikely(!PyString_Check(attr_name))) { return PyObject_GenericGetAttr(obj, attr_name); } assert(!tp->tp_dictoffset); descr = _PyType_Lookup(tp, attr_name); if (unlikely(!descr)) { return __Pyx_RaiseGenericGetAttributeError(tp, attr_name); } Py_INCREF(descr); #if PY_MAJOR_VERSION < 3 if (likely(PyType_HasFeature(Py_TYPE(descr), Py_TPFLAGS_HAVE_CLASS))) #endif { descrgetfunc f = Py_TYPE(descr)->tp_descr_get; if (unlikely(f)) { PyObject *res = f(descr, obj, (PyObject *)tp); Py_DECREF(descr); return res; } } return descr; } #endif /* PyObject_GenericGetAttr */ #if CYTHON_USE_TYPE_SLOTS && CYTHON_USE_PYTYPE_LOOKUP && PY_VERSION_HEX < 0x03070000 static PyObject* __Pyx_PyObject_GenericGetAttr(PyObject* obj, PyObject* attr_name) { if (unlikely(Py_TYPE(obj)->tp_dictoffset)) { return PyObject_GenericGetAttr(obj, attr_name); } return __Pyx_PyObject_GenericGetAttrNoDict(obj, attr_name); } #endif /* Import */ static PyObject *__Pyx_Import(PyObject *name, PyObject *from_list, int level) { PyObject *module = 0; PyObject *empty_dict = 0; PyObject *empty_list = 0; #if PY_MAJOR_VERSION < 3 PyObject *py_import; py_import = __Pyx_PyObject_GetAttrStr(__pyx_b, __pyx_n_s_import); if (unlikely(!py_import)) goto bad; if (!from_list) { empty_list = PyList_New(0); if (unlikely(!empty_list)) goto bad; from_list = empty_list; } #endif empty_dict = PyDict_New(); if (unlikely(!empty_dict)) goto bad; { #if PY_MAJOR_VERSION >= 3 if (level == -1) { if (strchr(__Pyx_MODULE_NAME, '.') != NULL) { module = PyImport_ImportModuleLevelObject( name, __pyx_d, empty_dict, from_list, 1); if (unlikely(!module)) { if (unlikely(!PyErr_ExceptionMatches(PyExc_ImportError))) goto bad; PyErr_Clear(); } } level = 0; } #endif if (!module) { #if PY_MAJOR_VERSION < 3 PyObject *py_level = PyInt_FromLong(level); if (unlikely(!py_level)) goto bad; module = PyObject_CallFunctionObjArgs(py_import, name, __pyx_d, empty_dict, from_list, py_level, (PyObject *)NULL); Py_DECREF(py_level); #else module = PyImport_ImportModuleLevelObject( name, __pyx_d, empty_dict, from_list, level); #endif } } bad: Py_XDECREF(empty_dict); Py_XDECREF(empty_list); #if PY_MAJOR_VERSION < 3 Py_XDECREF(py_import); #endif return module; } /* ImportFrom */ static PyObject* __Pyx_ImportFrom(PyObject* module, PyObject* name) { PyObject* value = __Pyx_PyObject_GetAttrStr(module, name); if (unlikely(!value) && PyErr_ExceptionMatches(PyExc_AttributeError)) { const char* module_name_str = 0; PyObject* module_name = 0; PyObject* module_dot = 0; PyObject* full_name = 0; PyErr_Clear(); module_name_str = PyModule_GetName(module); if (unlikely(!module_name_str)) { goto modbad; } module_name = PyUnicode_FromString(module_name_str); if (unlikely(!module_name)) { goto modbad; } module_dot = PyUnicode_Concat(module_name, __pyx_kp_u__4); if (unlikely(!module_dot)) { goto modbad; } full_name = PyUnicode_Concat(module_dot, name); if (unlikely(!full_name)) { goto modbad; } #if PY_VERSION_HEX < 0x030700A1 || (CYTHON_COMPILING_IN_PYPY && PYPY_VERSION_NUM < 0x07030400) { PyObject *modules = PyImport_GetModuleDict(); if (unlikely(!modules)) goto modbad; value = PyObject_GetItem(modules, full_name); } #else value = PyImport_GetModule(full_name); #endif modbad: Py_XDECREF(full_name); Py_XDECREF(module_dot); Py_XDECREF(module_name); } if (unlikely(!value)) { PyErr_Format(PyExc_ImportError, #if PY_MAJOR_VERSION < 3 "cannot import name %.230s", PyString_AS_STRING(name)); #else "cannot import name %S", name); #endif } return value; } /* ImportDottedModule */ #if PY_MAJOR_VERSION >= 3 static PyObject *__Pyx__ImportDottedModule_Error(PyObject *name, PyObject *parts_tuple, Py_ssize_t count) { PyObject *partial_name = NULL, *slice = NULL, *sep = NULL; if (unlikely(PyErr_Occurred())) { PyErr_Clear(); } if (likely(PyTuple_GET_SIZE(parts_tuple) == count)) { partial_name = name; } else { slice = PySequence_GetSlice(parts_tuple, 0, count); if (unlikely(!slice)) goto bad; sep = PyUnicode_FromStringAndSize(".", 1); if (unlikely(!sep)) goto bad; partial_name = PyUnicode_Join(sep, slice); } PyErr_Format( #if PY_MAJOR_VERSION < 3 PyExc_ImportError, "No module named '%s'", PyString_AS_STRING(partial_name)); #else #if PY_VERSION_HEX >= 0x030600B1 PyExc_ModuleNotFoundError, #else PyExc_ImportError, #endif "No module named '%U'", partial_name); #endif bad: Py_XDECREF(sep); Py_XDECREF(slice); Py_XDECREF(partial_name); return NULL; } #endif #if PY_MAJOR_VERSION >= 3 static PyObject *__Pyx__ImportDottedModule_Lookup(PyObject *name) { PyObject *imported_module; #if PY_VERSION_HEX < 0x030700A1 || (CYTHON_COMPILING_IN_PYPY && PYPY_VERSION_NUM < 0x07030400) PyObject *modules = PyImport_GetModuleDict(); if (unlikely(!modules)) return NULL; imported_module = __Pyx_PyDict_GetItemStr(modules, name); Py_XINCREF(imported_module); #else imported_module = PyImport_GetModule(name); #endif return imported_module; } #endif #if PY_MAJOR_VERSION >= 3 static PyObject *__Pyx_ImportDottedModule_WalkParts(PyObject *module, PyObject *name, PyObject *parts_tuple) { Py_ssize_t i, nparts; nparts = PyTuple_GET_SIZE(parts_tuple); for (i=1; i < nparts && module; i++) { PyObject *part, *submodule; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS part = PyTuple_GET_ITEM(parts_tuple, i); #else part = PySequence_ITEM(parts_tuple, i); #endif submodule = __Pyx_PyObject_GetAttrStrNoError(module, part); #if !(CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS) Py_DECREF(part); #endif Py_DECREF(module); module = submodule; } if (unlikely(!module)) { return __Pyx__ImportDottedModule_Error(name, parts_tuple, i); } return module; } #endif static PyObject *__Pyx__ImportDottedModule(PyObject *name, PyObject *parts_tuple) { #if PY_MAJOR_VERSION < 3 PyObject *module, *from_list, *star = __pyx_n_s__5; CYTHON_UNUSED_VAR(parts_tuple); from_list = PyList_New(1); if (unlikely(!from_list)) return NULL; Py_INCREF(star); PyList_SET_ITEM(from_list, 0, star); module = __Pyx_Import(name, from_list, 0); Py_DECREF(from_list); return module; #else PyObject *imported_module; PyObject *module = __Pyx_Import(name, NULL, 0); if (!parts_tuple || unlikely(!module)) return module; imported_module = __Pyx__ImportDottedModule_Lookup(name); if (likely(imported_module)) { Py_DECREF(module); return imported_module; } PyErr_Clear(); return __Pyx_ImportDottedModule_WalkParts(module, name, parts_tuple); #endif } static PyObject *__Pyx_ImportDottedModule(PyObject *name, PyObject *parts_tuple) { #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x030400B1 PyObject *module = __Pyx__ImportDottedModule_Lookup(name); if (likely(module)) { PyObject *spec = __Pyx_PyObject_GetAttrStrNoError(module, __pyx_n_s_spec); if (likely(spec)) { PyObject *unsafe = __Pyx_PyObject_GetAttrStrNoError(spec, __pyx_n_s_initializing); if (likely(!unsafe || !__Pyx_PyObject_IsTrue(unsafe))) { Py_DECREF(spec); spec = NULL; } Py_XDECREF(unsafe); } if (likely(!spec)) { PyErr_Clear(); return module; } Py_DECREF(spec); Py_DECREF(module); } else if (PyErr_Occurred()) { PyErr_Clear(); } #endif return __Pyx__ImportDottedModule(name, parts_tuple); } /* ImportDottedModuleRelFirst */ static PyObject *__Pyx_ImportDottedModuleRelFirst(PyObject *name, PyObject *parts_tuple) { PyObject *module; PyObject *from_list = NULL; #if PY_MAJOR_VERSION < 3 PyObject *star = __pyx_n_s__5; from_list = PyList_New(1); if (unlikely(!from_list)) return NULL; Py_INCREF(star); PyList_SET_ITEM(from_list, 0, star); #endif module = __Pyx_Import(name, from_list, -1); Py_XDECREF(from_list); if (module) { #if PY_MAJOR_VERSION >= 3 if (parts_tuple) { module = __Pyx_ImportDottedModule_WalkParts(module, name, parts_tuple); } #endif return module; } if (unlikely(!PyErr_ExceptionMatches(PyExc_ImportError))) return NULL; PyErr_Clear(); return __Pyx_ImportDottedModule(name, parts_tuple); } /* FetchSharedCythonModule */ static PyObject *__Pyx_FetchSharedCythonABIModule(void) { return __Pyx_PyImport_AddModuleRef((char*) __PYX_ABI_MODULE_NAME); } /* FetchCommonType */ static int __Pyx_VerifyCachedType(PyObject *cached_type, const char *name, Py_ssize_t basicsize, Py_ssize_t expected_basicsize) { if (!PyType_Check(cached_type)) { PyErr_Format(PyExc_TypeError, "Shared Cython type %.200s is not a type object", name); return -1; } if (basicsize != expected_basicsize) { PyErr_Format(PyExc_TypeError, "Shared Cython type %.200s has the wrong size, try recompiling", name); return -1; } return 0; } #if !CYTHON_USE_TYPE_SPECS static PyTypeObject* __Pyx_FetchCommonType(PyTypeObject* type) { PyObject* abi_module; const char* object_name; PyTypeObject *cached_type = NULL; abi_module = __Pyx_FetchSharedCythonABIModule(); if (!abi_module) return NULL; object_name = strrchr(type->tp_name, '.'); object_name = object_name ? object_name+1 : type->tp_name; cached_type = (PyTypeObject*) PyObject_GetAttrString(abi_module, object_name); if (cached_type) { if (__Pyx_VerifyCachedType( (PyObject *)cached_type, object_name, cached_type->tp_basicsize, type->tp_basicsize) < 0) { goto bad; } goto done; } if (!PyErr_ExceptionMatches(PyExc_AttributeError)) goto bad; PyErr_Clear(); if (PyType_Ready(type) < 0) goto bad; if (PyObject_SetAttrString(abi_module, object_name, (PyObject *)type) < 0) goto bad; Py_INCREF(type); cached_type = type; done: Py_DECREF(abi_module); return cached_type; bad: Py_XDECREF(cached_type); cached_type = NULL; goto done; } #else static PyTypeObject *__Pyx_FetchCommonTypeFromSpec(PyObject *module, PyType_Spec *spec, PyObject *bases) { PyObject *abi_module, *cached_type = NULL; const char* object_name = strrchr(spec->name, '.'); object_name = object_name ? object_name+1 : spec->name; abi_module = __Pyx_FetchSharedCythonABIModule(); if (!abi_module) return NULL; cached_type = PyObject_GetAttrString(abi_module, object_name); if (cached_type) { Py_ssize_t basicsize; #if CYTHON_COMPILING_IN_LIMITED_API PyObject *py_basicsize; py_basicsize = PyObject_GetAttrString(cached_type, "__basicsize__"); if (unlikely(!py_basicsize)) goto bad; basicsize = PyLong_AsSsize_t(py_basicsize); Py_DECREF(py_basicsize); py_basicsize = 0; if (unlikely(basicsize == (Py_ssize_t)-1) && PyErr_Occurred()) goto bad; #else basicsize = likely(PyType_Check(cached_type)) ? ((PyTypeObject*) cached_type)->tp_basicsize : -1; #endif if (__Pyx_VerifyCachedType( cached_type, object_name, basicsize, spec->basicsize) < 0) { goto bad; } goto done; } if (!PyErr_ExceptionMatches(PyExc_AttributeError)) goto bad; PyErr_Clear(); CYTHON_UNUSED_VAR(module); cached_type = __Pyx_PyType_FromModuleAndSpec(abi_module, spec, bases); if (unlikely(!cached_type)) goto bad; if (unlikely(__Pyx_fix_up_extension_type_from_spec(spec, (PyTypeObject *) cached_type) < 0)) goto bad; if (PyObject_SetAttrString(abi_module, object_name, cached_type) < 0) goto bad; done: Py_DECREF(abi_module); assert(cached_type == NULL || PyType_Check(cached_type)); return (PyTypeObject *) cached_type; bad: Py_XDECREF(cached_type); cached_type = NULL; goto done; } #endif /* PyVectorcallFastCallDict */ #if CYTHON_METH_FASTCALL static PyObject *__Pyx_PyVectorcall_FastCallDict_kw(PyObject *func, __pyx_vectorcallfunc vc, PyObject *const *args, size_t nargs, PyObject *kw) { PyObject *res = NULL; PyObject *kwnames; PyObject **newargs; PyObject **kwvalues; Py_ssize_t i, pos; size_t j; PyObject *key, *value; unsigned long keys_are_strings; Py_ssize_t nkw = PyDict_GET_SIZE(kw); newargs = (PyObject **)PyMem_Malloc((nargs + (size_t)nkw) * sizeof(args[0])); if (unlikely(newargs == NULL)) { PyErr_NoMemory(); return NULL; } for (j = 0; j < nargs; j++) newargs[j] = args[j]; kwnames = PyTuple_New(nkw); if (unlikely(kwnames == NULL)) { PyMem_Free(newargs); return NULL; } kwvalues = newargs + nargs; pos = i = 0; keys_are_strings = Py_TPFLAGS_UNICODE_SUBCLASS; while (PyDict_Next(kw, &pos, &key, &value)) { keys_are_strings &= Py_TYPE(key)->tp_flags; Py_INCREF(key); Py_INCREF(value); PyTuple_SET_ITEM(kwnames, i, key); kwvalues[i] = value; i++; } if (unlikely(!keys_are_strings)) { PyErr_SetString(PyExc_TypeError, "keywords must be strings"); goto cleanup; } res = vc(func, newargs, nargs, kwnames); cleanup: Py_DECREF(kwnames); for (i = 0; i < nkw; i++) Py_DECREF(kwvalues[i]); PyMem_Free(newargs); return res; } static CYTHON_INLINE PyObject *__Pyx_PyVectorcall_FastCallDict(PyObject *func, __pyx_vectorcallfunc vc, PyObject *const *args, size_t nargs, PyObject *kw) { if (likely(kw == NULL) || PyDict_GET_SIZE(kw) == 0) { return vc(func, args, nargs, NULL); } return __Pyx_PyVectorcall_FastCallDict_kw(func, vc, args, nargs, kw); } #endif /* CythonFunctionShared */ #if CYTHON_COMPILING_IN_LIMITED_API static CYTHON_INLINE int __Pyx__IsSameCyOrCFunction(PyObject *func, void *cfunc) { if (__Pyx_CyFunction_Check(func)) { return PyCFunction_GetFunction(((__pyx_CyFunctionObject*)func)->func) == (PyCFunction) cfunc; } else if (PyCFunction_Check(func)) { return PyCFunction_GetFunction(func) == (PyCFunction) cfunc; } return 0; } #else static CYTHON_INLINE int __Pyx__IsSameCyOrCFunction(PyObject *func, void *cfunc) { return __Pyx_CyOrPyCFunction_Check(func) && __Pyx_CyOrPyCFunction_GET_FUNCTION(func) == (PyCFunction) cfunc; } #endif static CYTHON_INLINE void __Pyx__CyFunction_SetClassObj(__pyx_CyFunctionObject* f, PyObject* classobj) { #if PY_VERSION_HEX < 0x030900B1 || CYTHON_COMPILING_IN_LIMITED_API __Pyx_Py_XDECREF_SET( __Pyx_CyFunction_GetClassObj(f), ((classobj) ? __Pyx_NewRef(classobj) : NULL)); #else __Pyx_Py_XDECREF_SET( ((PyCMethodObject *) (f))->mm_class, (PyTypeObject*)((classobj) ? __Pyx_NewRef(classobj) : NULL)); #endif } static PyObject * __Pyx_CyFunction_get_doc(__pyx_CyFunctionObject *op, void *closure) { CYTHON_UNUSED_VAR(closure); if (unlikely(op->func_doc == NULL)) { #if CYTHON_COMPILING_IN_LIMITED_API op->func_doc = PyObject_GetAttrString(op->func, "__doc__"); if (unlikely(!op->func_doc)) return NULL; #else if (((PyCFunctionObject*)op)->m_ml->ml_doc) { #if PY_MAJOR_VERSION >= 3 op->func_doc = PyUnicode_FromString(((PyCFunctionObject*)op)->m_ml->ml_doc); #else op->func_doc = PyString_FromString(((PyCFunctionObject*)op)->m_ml->ml_doc); #endif if (unlikely(op->func_doc == NULL)) return NULL; } else { Py_INCREF(Py_None); return Py_None; } #endif } Py_INCREF(op->func_doc); return op->func_doc; } static int __Pyx_CyFunction_set_doc(__pyx_CyFunctionObject *op, PyObject *value, void *context) { CYTHON_UNUSED_VAR(context); if (value == NULL) { value = Py_None; } Py_INCREF(value); __Pyx_Py_XDECREF_SET(op->func_doc, value); return 0; } static PyObject * __Pyx_CyFunction_get_name(__pyx_CyFunctionObject *op, void *context) { CYTHON_UNUSED_VAR(context); if (unlikely(op->func_name == NULL)) { #if CYTHON_COMPILING_IN_LIMITED_API op->func_name = PyObject_GetAttrString(op->func, "__name__"); #elif PY_MAJOR_VERSION >= 3 op->func_name = PyUnicode_InternFromString(((PyCFunctionObject*)op)->m_ml->ml_name); #else op->func_name = PyString_InternFromString(((PyCFunctionObject*)op)->m_ml->ml_name); #endif if (unlikely(op->func_name == NULL)) return NULL; } Py_INCREF(op->func_name); return op->func_name; } static int __Pyx_CyFunction_set_name(__pyx_CyFunctionObject *op, PyObject *value, void *context) { CYTHON_UNUSED_VAR(context); #if PY_MAJOR_VERSION >= 3 if (unlikely(value == NULL || !PyUnicode_Check(value))) #else if (unlikely(value == NULL || !PyString_Check(value))) #endif { PyErr_SetString(PyExc_TypeError, "__name__ must be set to a string object"); return -1; } Py_INCREF(value); __Pyx_Py_XDECREF_SET(op->func_name, value); return 0; } static PyObject * __Pyx_CyFunction_get_qualname(__pyx_CyFunctionObject *op, void *context) { CYTHON_UNUSED_VAR(context); Py_INCREF(op->func_qualname); return op->func_qualname; } static int __Pyx_CyFunction_set_qualname(__pyx_CyFunctionObject *op, PyObject *value, void *context) { CYTHON_UNUSED_VAR(context); #if PY_MAJOR_VERSION >= 3 if (unlikely(value == NULL || !PyUnicode_Check(value))) #else if (unlikely(value == NULL || !PyString_Check(value))) #endif { PyErr_SetString(PyExc_TypeError, "__qualname__ must be set to a string object"); return -1; } Py_INCREF(value); __Pyx_Py_XDECREF_SET(op->func_qualname, value); return 0; } static PyObject * __Pyx_CyFunction_get_dict(__pyx_CyFunctionObject *op, void *context) { CYTHON_UNUSED_VAR(context); if (unlikely(op->func_dict == NULL)) { op->func_dict = PyDict_New(); if (unlikely(op->func_dict == NULL)) return NULL; } Py_INCREF(op->func_dict); return op->func_dict; } static int __Pyx_CyFunction_set_dict(__pyx_CyFunctionObject *op, PyObject *value, void *context) { CYTHON_UNUSED_VAR(context); if (unlikely(value == NULL)) { PyErr_SetString(PyExc_TypeError, "function's dictionary may not be deleted"); return -1; } if (unlikely(!PyDict_Check(value))) { PyErr_SetString(PyExc_TypeError, "setting function's dictionary to a non-dict"); return -1; } Py_INCREF(value); __Pyx_Py_XDECREF_SET(op->func_dict, value); return 0; } static PyObject * __Pyx_CyFunction_get_globals(__pyx_CyFunctionObject *op, void *context) { CYTHON_UNUSED_VAR(context); Py_INCREF(op->func_globals); return op->func_globals; } static PyObject * __Pyx_CyFunction_get_closure(__pyx_CyFunctionObject *op, void *context) { CYTHON_UNUSED_VAR(op); CYTHON_UNUSED_VAR(context); Py_INCREF(Py_None); return Py_None; } static PyObject * __Pyx_CyFunction_get_code(__pyx_CyFunctionObject *op, void *context) { PyObject* result = (op->func_code) ? op->func_code : Py_None; CYTHON_UNUSED_VAR(context); Py_INCREF(result); return result; } static int __Pyx_CyFunction_init_defaults(__pyx_CyFunctionObject *op) { int result = 0; PyObject *res = op->defaults_getter((PyObject *) op); if (unlikely(!res)) return -1; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS op->defaults_tuple = PyTuple_GET_ITEM(res, 0); Py_INCREF(op->defaults_tuple); op->defaults_kwdict = PyTuple_GET_ITEM(res, 1); Py_INCREF(op->defaults_kwdict); #else op->defaults_tuple = __Pyx_PySequence_ITEM(res, 0); if (unlikely(!op->defaults_tuple)) result = -1; else { op->defaults_kwdict = __Pyx_PySequence_ITEM(res, 1); if (unlikely(!op->defaults_kwdict)) result = -1; } #endif Py_DECREF(res); return result; } static int __Pyx_CyFunction_set_defaults(__pyx_CyFunctionObject *op, PyObject* value, void *context) { CYTHON_UNUSED_VAR(context); if (!value) { value = Py_None; } else if (unlikely(value != Py_None && !PyTuple_Check(value))) { PyErr_SetString(PyExc_TypeError, "__defaults__ must be set to a tuple object"); return -1; } PyErr_WarnEx(PyExc_RuntimeWarning, "changes to cyfunction.__defaults__ will not " "currently affect the values used in function calls", 1); Py_INCREF(value); __Pyx_Py_XDECREF_SET(op->defaults_tuple, value); return 0; } static PyObject * __Pyx_CyFunction_get_defaults(__pyx_CyFunctionObject *op, void *context) { PyObject* result = op->defaults_tuple; CYTHON_UNUSED_VAR(context); if (unlikely(!result)) { if (op->defaults_getter) { if (unlikely(__Pyx_CyFunction_init_defaults(op) < 0)) return NULL; result = op->defaults_tuple; } else { result = Py_None; } } Py_INCREF(result); return result; } static int __Pyx_CyFunction_set_kwdefaults(__pyx_CyFunctionObject *op, PyObject* value, void *context) { CYTHON_UNUSED_VAR(context); if (!value) { value = Py_None; } else if (unlikely(value != Py_None && !PyDict_Check(value))) { PyErr_SetString(PyExc_TypeError, "__kwdefaults__ must be set to a dict object"); return -1; } PyErr_WarnEx(PyExc_RuntimeWarning, "changes to cyfunction.__kwdefaults__ will not " "currently affect the values used in function calls", 1); Py_INCREF(value); __Pyx_Py_XDECREF_SET(op->defaults_kwdict, value); return 0; } static PyObject * __Pyx_CyFunction_get_kwdefaults(__pyx_CyFunctionObject *op, void *context) { PyObject* result = op->defaults_kwdict; CYTHON_UNUSED_VAR(context); if (unlikely(!result)) { if (op->defaults_getter) { if (unlikely(__Pyx_CyFunction_init_defaults(op) < 0)) return NULL; result = op->defaults_kwdict; } else { result = Py_None; } } Py_INCREF(result); return result; } static int __Pyx_CyFunction_set_annotations(__pyx_CyFunctionObject *op, PyObject* value, void *context) { CYTHON_UNUSED_VAR(context); if (!value || value == Py_None) { value = NULL; } else if (unlikely(!PyDict_Check(value))) { PyErr_SetString(PyExc_TypeError, "__annotations__ must be set to a dict object"); return -1; } Py_XINCREF(value); __Pyx_Py_XDECREF_SET(op->func_annotations, value); return 0; } static PyObject * __Pyx_CyFunction_get_annotations(__pyx_CyFunctionObject *op, void *context) { PyObject* result = op->func_annotations; CYTHON_UNUSED_VAR(context); if (unlikely(!result)) { result = PyDict_New(); if (unlikely(!result)) return NULL; op->func_annotations = result; } Py_INCREF(result); return result; } static PyObject * __Pyx_CyFunction_get_is_coroutine(__pyx_CyFunctionObject *op, void *context) { int is_coroutine; CYTHON_UNUSED_VAR(context); if (op->func_is_coroutine) { return __Pyx_NewRef(op->func_is_coroutine); } is_coroutine = op->flags & __Pyx_CYFUNCTION_COROUTINE; #if PY_VERSION_HEX >= 0x03050000 if (is_coroutine) { PyObject *module, *fromlist, *marker = __pyx_n_s_is_coroutine; fromlist = PyList_New(1); if (unlikely(!fromlist)) return NULL; Py_INCREF(marker); #if CYTHON_ASSUME_SAFE_MACROS PyList_SET_ITEM(fromlist, 0, marker); #else if (unlikely(PyList_SetItem(fromlist, 0, marker) < 0)) { Py_DECREF(marker); Py_DECREF(fromlist); return NULL; } #endif module = PyImport_ImportModuleLevelObject(__pyx_n_s_asyncio_coroutines, NULL, NULL, fromlist, 0); Py_DECREF(fromlist); if (unlikely(!module)) goto ignore; op->func_is_coroutine = __Pyx_PyObject_GetAttrStr(module, marker); Py_DECREF(module); if (likely(op->func_is_coroutine)) { return __Pyx_NewRef(op->func_is_coroutine); } ignore: PyErr_Clear(); } #endif op->func_is_coroutine = __Pyx_PyBool_FromLong(is_coroutine); return __Pyx_NewRef(op->func_is_coroutine); } #if CYTHON_COMPILING_IN_LIMITED_API static PyObject * __Pyx_CyFunction_get_module(__pyx_CyFunctionObject *op, void *context) { CYTHON_UNUSED_VAR(context); return PyObject_GetAttrString(op->func, "__module__"); } static int __Pyx_CyFunction_set_module(__pyx_CyFunctionObject *op, PyObject* value, void *context) { CYTHON_UNUSED_VAR(context); return PyObject_SetAttrString(op->func, "__module__", value); } #endif static PyGetSetDef __pyx_CyFunction_getsets[] = { {(char *) "func_doc", (getter)__Pyx_CyFunction_get_doc, (setter)__Pyx_CyFunction_set_doc, 0, 0}, {(char *) "__doc__", (getter)__Pyx_CyFunction_get_doc, (setter)__Pyx_CyFunction_set_doc, 0, 0}, {(char *) "func_name", (getter)__Pyx_CyFunction_get_name, (setter)__Pyx_CyFunction_set_name, 0, 0}, {(char *) "__name__", (getter)__Pyx_CyFunction_get_name, (setter)__Pyx_CyFunction_set_name, 0, 0}, {(char *) "__qualname__", (getter)__Pyx_CyFunction_get_qualname, (setter)__Pyx_CyFunction_set_qualname, 0, 0}, {(char *) "func_dict", (getter)__Pyx_CyFunction_get_dict, (setter)__Pyx_CyFunction_set_dict, 0, 0}, {(char *) "__dict__", (getter)__Pyx_CyFunction_get_dict, (setter)__Pyx_CyFunction_set_dict, 0, 0}, {(char *) "func_globals", (getter)__Pyx_CyFunction_get_globals, 0, 0, 0}, {(char *) "__globals__", (getter)__Pyx_CyFunction_get_globals, 0, 0, 0}, {(char *) "func_closure", (getter)__Pyx_CyFunction_get_closure, 0, 0, 0}, {(char *) "__closure__", (getter)__Pyx_CyFunction_get_closure, 0, 0, 0}, {(char *) "func_code", (getter)__Pyx_CyFunction_get_code, 0, 0, 0}, {(char *) "__code__", (getter)__Pyx_CyFunction_get_code, 0, 0, 0}, {(char *) "func_defaults", (getter)__Pyx_CyFunction_get_defaults, (setter)__Pyx_CyFunction_set_defaults, 0, 0}, {(char *) "__defaults__", (getter)__Pyx_CyFunction_get_defaults, (setter)__Pyx_CyFunction_set_defaults, 0, 0}, {(char *) "__kwdefaults__", (getter)__Pyx_CyFunction_get_kwdefaults, (setter)__Pyx_CyFunction_set_kwdefaults, 0, 0}, {(char *) "__annotations__", (getter)__Pyx_CyFunction_get_annotations, (setter)__Pyx_CyFunction_set_annotations, 0, 0}, {(char *) "_is_coroutine", (getter)__Pyx_CyFunction_get_is_coroutine, 0, 0, 0}, #if CYTHON_COMPILING_IN_LIMITED_API {"__module__", (getter)__Pyx_CyFunction_get_module, (setter)__Pyx_CyFunction_set_module, 0, 0}, #endif {0, 0, 0, 0, 0} }; static PyMemberDef __pyx_CyFunction_members[] = { #if !CYTHON_COMPILING_IN_LIMITED_API {(char *) "__module__", T_OBJECT, offsetof(PyCFunctionObject, m_module), 0, 0}, #endif #if CYTHON_USE_TYPE_SPECS {(char *) "__dictoffset__", T_PYSSIZET, offsetof(__pyx_CyFunctionObject, func_dict), READONLY, 0}, #if CYTHON_METH_FASTCALL #if CYTHON_BACKPORT_VECTORCALL {(char *) "__vectorcalloffset__", T_PYSSIZET, offsetof(__pyx_CyFunctionObject, func_vectorcall), READONLY, 0}, #else #if !CYTHON_COMPILING_IN_LIMITED_API {(char *) "__vectorcalloffset__", T_PYSSIZET, offsetof(PyCFunctionObject, vectorcall), READONLY, 0}, #endif #endif #endif #if PY_VERSION_HEX < 0x030500A0 || CYTHON_COMPILING_IN_LIMITED_API {(char *) "__weaklistoffset__", T_PYSSIZET, offsetof(__pyx_CyFunctionObject, func_weakreflist), READONLY, 0}, #else {(char *) "__weaklistoffset__", T_PYSSIZET, offsetof(PyCFunctionObject, m_weakreflist), READONLY, 0}, #endif #endif {0, 0, 0, 0, 0} }; static PyObject * __Pyx_CyFunction_reduce(__pyx_CyFunctionObject *m, PyObject *args) { CYTHON_UNUSED_VAR(args); #if PY_MAJOR_VERSION >= 3 Py_INCREF(m->func_qualname); return m->func_qualname; #else return PyString_FromString(((PyCFunctionObject*)m)->m_ml->ml_name); #endif } static PyMethodDef __pyx_CyFunction_methods[] = { {"__reduce__", (PyCFunction)__Pyx_CyFunction_reduce, METH_VARARGS, 0}, {0, 0, 0, 0} }; #if PY_VERSION_HEX < 0x030500A0 || CYTHON_COMPILING_IN_LIMITED_API #define __Pyx_CyFunction_weakreflist(cyfunc) ((cyfunc)->func_weakreflist) #else #define __Pyx_CyFunction_weakreflist(cyfunc) (((PyCFunctionObject*)cyfunc)->m_weakreflist) #endif static PyObject *__Pyx_CyFunction_Init(__pyx_CyFunctionObject *op, PyMethodDef *ml, int flags, PyObject* qualname, PyObject *closure, PyObject *module, PyObject* globals, PyObject* code) { #if !CYTHON_COMPILING_IN_LIMITED_API PyCFunctionObject *cf = (PyCFunctionObject*) op; #endif if (unlikely(op == NULL)) return NULL; #if CYTHON_COMPILING_IN_LIMITED_API op->func = PyCFunction_NewEx(ml, (PyObject*)op, module); if (unlikely(!op->func)) return NULL; #endif op->flags = flags; __Pyx_CyFunction_weakreflist(op) = NULL; #if !CYTHON_COMPILING_IN_LIMITED_API cf->m_ml = ml; cf->m_self = (PyObject *) op; #endif Py_XINCREF(closure); op->func_closure = closure; #if !CYTHON_COMPILING_IN_LIMITED_API Py_XINCREF(module); cf->m_module = module; #endif op->func_dict = NULL; op->func_name = NULL; Py_INCREF(qualname); op->func_qualname = qualname; op->func_doc = NULL; #if PY_VERSION_HEX < 0x030900B1 || CYTHON_COMPILING_IN_LIMITED_API op->func_classobj = NULL; #else ((PyCMethodObject*)op)->mm_class = NULL; #endif op->func_globals = globals; Py_INCREF(op->func_globals); Py_XINCREF(code); op->func_code = code; op->defaults_pyobjects = 0; op->defaults_size = 0; op->defaults = NULL; op->defaults_tuple = NULL; op->defaults_kwdict = NULL; op->defaults_getter = NULL; op->func_annotations = NULL; op->func_is_coroutine = NULL; #if CYTHON_METH_FASTCALL switch (ml->ml_flags & (METH_VARARGS | METH_FASTCALL | METH_NOARGS | METH_O | METH_KEYWORDS | METH_METHOD)) { case METH_NOARGS: __Pyx_CyFunction_func_vectorcall(op) = __Pyx_CyFunction_Vectorcall_NOARGS; break; case METH_O: __Pyx_CyFunction_func_vectorcall(op) = __Pyx_CyFunction_Vectorcall_O; break; case METH_METHOD | METH_FASTCALL | METH_KEYWORDS: __Pyx_CyFunction_func_vectorcall(op) = __Pyx_CyFunction_Vectorcall_FASTCALL_KEYWORDS_METHOD; break; case METH_FASTCALL | METH_KEYWORDS: __Pyx_CyFunction_func_vectorcall(op) = __Pyx_CyFunction_Vectorcall_FASTCALL_KEYWORDS; break; case METH_VARARGS | METH_KEYWORDS: __Pyx_CyFunction_func_vectorcall(op) = NULL; break; default: PyErr_SetString(PyExc_SystemError, "Bad call flags for CyFunction"); Py_DECREF(op); return NULL; } #endif return (PyObject *) op; } static int __Pyx_CyFunction_clear(__pyx_CyFunctionObject *m) { Py_CLEAR(m->func_closure); #if CYTHON_COMPILING_IN_LIMITED_API Py_CLEAR(m->func); #else Py_CLEAR(((PyCFunctionObject*)m)->m_module); #endif Py_CLEAR(m->func_dict); Py_CLEAR(m->func_name); Py_CLEAR(m->func_qualname); Py_CLEAR(m->func_doc); Py_CLEAR(m->func_globals); Py_CLEAR(m->func_code); #if !CYTHON_COMPILING_IN_LIMITED_API #if PY_VERSION_HEX < 0x030900B1 Py_CLEAR(__Pyx_CyFunction_GetClassObj(m)); #else { PyObject *cls = (PyObject*) ((PyCMethodObject *) (m))->mm_class; ((PyCMethodObject *) (m))->mm_class = NULL; Py_XDECREF(cls); } #endif #endif Py_CLEAR(m->defaults_tuple); Py_CLEAR(m->defaults_kwdict); Py_CLEAR(m->func_annotations); Py_CLEAR(m->func_is_coroutine); if (m->defaults) { PyObject **pydefaults = __Pyx_CyFunction_Defaults(PyObject *, m); int i; for (i = 0; i < m->defaults_pyobjects; i++) Py_XDECREF(pydefaults[i]); PyObject_Free(m->defaults); m->defaults = NULL; } return 0; } static void __Pyx__CyFunction_dealloc(__pyx_CyFunctionObject *m) { if (__Pyx_CyFunction_weakreflist(m) != NULL) PyObject_ClearWeakRefs((PyObject *) m); __Pyx_CyFunction_clear(m); __Pyx_PyHeapTypeObject_GC_Del(m); } static void __Pyx_CyFunction_dealloc(__pyx_CyFunctionObject *m) { PyObject_GC_UnTrack(m); __Pyx__CyFunction_dealloc(m); } static int __Pyx_CyFunction_traverse(__pyx_CyFunctionObject *m, visitproc visit, void *arg) { Py_VISIT(m->func_closure); #if CYTHON_COMPILING_IN_LIMITED_API Py_VISIT(m->func); #else Py_VISIT(((PyCFunctionObject*)m)->m_module); #endif Py_VISIT(m->func_dict); Py_VISIT(m->func_name); Py_VISIT(m->func_qualname); Py_VISIT(m->func_doc); Py_VISIT(m->func_globals); Py_VISIT(m->func_code); #if !CYTHON_COMPILING_IN_LIMITED_API Py_VISIT(__Pyx_CyFunction_GetClassObj(m)); #endif Py_VISIT(m->defaults_tuple); Py_VISIT(m->defaults_kwdict); Py_VISIT(m->func_is_coroutine); if (m->defaults) { PyObject **pydefaults = __Pyx_CyFunction_Defaults(PyObject *, m); int i; for (i = 0; i < m->defaults_pyobjects; i++) Py_VISIT(pydefaults[i]); } return 0; } static PyObject* __Pyx_CyFunction_repr(__pyx_CyFunctionObject *op) { #if PY_MAJOR_VERSION >= 3 return PyUnicode_FromFormat("", op->func_qualname, (void *)op); #else return PyString_FromFormat("", PyString_AsString(op->func_qualname), (void *)op); #endif } static PyObject * __Pyx_CyFunction_CallMethod(PyObject *func, PyObject *self, PyObject *arg, PyObject *kw) { #if CYTHON_COMPILING_IN_LIMITED_API PyObject *f = ((__pyx_CyFunctionObject*)func)->func; PyObject *py_name = NULL; PyCFunction meth; int flags; meth = PyCFunction_GetFunction(f); if (unlikely(!meth)) return NULL; flags = PyCFunction_GetFlags(f); if (unlikely(flags < 0)) return NULL; #else PyCFunctionObject* f = (PyCFunctionObject*)func; PyCFunction meth = f->m_ml->ml_meth; int flags = f->m_ml->ml_flags; #endif Py_ssize_t size; switch (flags & (METH_VARARGS | METH_KEYWORDS | METH_NOARGS | METH_O)) { case METH_VARARGS: if (likely(kw == NULL || PyDict_Size(kw) == 0)) return (*meth)(self, arg); break; case METH_VARARGS | METH_KEYWORDS: return (*(PyCFunctionWithKeywords)(void*)meth)(self, arg, kw); case METH_NOARGS: if (likely(kw == NULL || PyDict_Size(kw) == 0)) { #if CYTHON_ASSUME_SAFE_MACROS size = PyTuple_GET_SIZE(arg); #else size = PyTuple_Size(arg); if (unlikely(size < 0)) return NULL; #endif if (likely(size == 0)) return (*meth)(self, NULL); #if CYTHON_COMPILING_IN_LIMITED_API py_name = __Pyx_CyFunction_get_name((__pyx_CyFunctionObject*)func, NULL); if (!py_name) return NULL; PyErr_Format(PyExc_TypeError, "%.200S() takes no arguments (%" CYTHON_FORMAT_SSIZE_T "d given)", py_name, size); Py_DECREF(py_name); #else PyErr_Format(PyExc_TypeError, "%.200s() takes no arguments (%" CYTHON_FORMAT_SSIZE_T "d given)", f->m_ml->ml_name, size); #endif return NULL; } break; case METH_O: if (likely(kw == NULL || PyDict_Size(kw) == 0)) { #if CYTHON_ASSUME_SAFE_MACROS size = PyTuple_GET_SIZE(arg); #else size = PyTuple_Size(arg); if (unlikely(size < 0)) return NULL; #endif if (likely(size == 1)) { PyObject *result, *arg0; #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS arg0 = PyTuple_GET_ITEM(arg, 0); #else arg0 = __Pyx_PySequence_ITEM(arg, 0); if (unlikely(!arg0)) return NULL; #endif result = (*meth)(self, arg0); #if !(CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS) Py_DECREF(arg0); #endif return result; } #if CYTHON_COMPILING_IN_LIMITED_API py_name = __Pyx_CyFunction_get_name((__pyx_CyFunctionObject*)func, NULL); if (!py_name) return NULL; PyErr_Format(PyExc_TypeError, "%.200S() takes exactly one argument (%" CYTHON_FORMAT_SSIZE_T "d given)", py_name, size); Py_DECREF(py_name); #else PyErr_Format(PyExc_TypeError, "%.200s() takes exactly one argument (%" CYTHON_FORMAT_SSIZE_T "d given)", f->m_ml->ml_name, size); #endif return NULL; } break; default: PyErr_SetString(PyExc_SystemError, "Bad call flags for CyFunction"); return NULL; } #if CYTHON_COMPILING_IN_LIMITED_API py_name = __Pyx_CyFunction_get_name((__pyx_CyFunctionObject*)func, NULL); if (!py_name) return NULL; PyErr_Format(PyExc_TypeError, "%.200S() takes no keyword arguments", py_name); Py_DECREF(py_name); #else PyErr_Format(PyExc_TypeError, "%.200s() takes no keyword arguments", f->m_ml->ml_name); #endif return NULL; } static CYTHON_INLINE PyObject *__Pyx_CyFunction_Call(PyObject *func, PyObject *arg, PyObject *kw) { PyObject *self, *result; #if CYTHON_COMPILING_IN_LIMITED_API self = PyCFunction_GetSelf(((__pyx_CyFunctionObject*)func)->func); if (unlikely(!self) && PyErr_Occurred()) return NULL; #else self = ((PyCFunctionObject*)func)->m_self; #endif result = __Pyx_CyFunction_CallMethod(func, self, arg, kw); return result; } static PyObject *__Pyx_CyFunction_CallAsMethod(PyObject *func, PyObject *args, PyObject *kw) { PyObject *result; __pyx_CyFunctionObject *cyfunc = (__pyx_CyFunctionObject *) func; #if CYTHON_METH_FASTCALL __pyx_vectorcallfunc vc = __Pyx_CyFunction_func_vectorcall(cyfunc); if (vc) { #if CYTHON_ASSUME_SAFE_MACROS return __Pyx_PyVectorcall_FastCallDict(func, vc, &PyTuple_GET_ITEM(args, 0), (size_t)PyTuple_GET_SIZE(args), kw); #else (void) &__Pyx_PyVectorcall_FastCallDict; return PyVectorcall_Call(func, args, kw); #endif } #endif if ((cyfunc->flags & __Pyx_CYFUNCTION_CCLASS) && !(cyfunc->flags & __Pyx_CYFUNCTION_STATICMETHOD)) { Py_ssize_t argc; PyObject *new_args; PyObject *self; #if CYTHON_ASSUME_SAFE_MACROS argc = PyTuple_GET_SIZE(args); #else argc = PyTuple_Size(args); if (unlikely(!argc) < 0) return NULL; #endif new_args = PyTuple_GetSlice(args, 1, argc); if (unlikely(!new_args)) return NULL; self = PyTuple_GetItem(args, 0); if (unlikely(!self)) { Py_DECREF(new_args); #if PY_MAJOR_VERSION > 2 PyErr_Format(PyExc_TypeError, "unbound method %.200S() needs an argument", cyfunc->func_qualname); #else PyErr_SetString(PyExc_TypeError, "unbound method needs an argument"); #endif return NULL; } result = __Pyx_CyFunction_CallMethod(func, self, new_args, kw); Py_DECREF(new_args); } else { result = __Pyx_CyFunction_Call(func, args, kw); } return result; } #if CYTHON_METH_FASTCALL static CYTHON_INLINE int __Pyx_CyFunction_Vectorcall_CheckArgs(__pyx_CyFunctionObject *cyfunc, Py_ssize_t nargs, PyObject *kwnames) { int ret = 0; if ((cyfunc->flags & __Pyx_CYFUNCTION_CCLASS) && !(cyfunc->flags & __Pyx_CYFUNCTION_STATICMETHOD)) { if (unlikely(nargs < 1)) { PyErr_Format(PyExc_TypeError, "%.200s() needs an argument", ((PyCFunctionObject*)cyfunc)->m_ml->ml_name); return -1; } ret = 1; } if (unlikely(kwnames) && unlikely(PyTuple_GET_SIZE(kwnames))) { PyErr_Format(PyExc_TypeError, "%.200s() takes no keyword arguments", ((PyCFunctionObject*)cyfunc)->m_ml->ml_name); return -1; } return ret; } static PyObject * __Pyx_CyFunction_Vectorcall_NOARGS(PyObject *func, PyObject *const *args, size_t nargsf, PyObject *kwnames) { __pyx_CyFunctionObject *cyfunc = (__pyx_CyFunctionObject *)func; PyMethodDef* def = ((PyCFunctionObject*)cyfunc)->m_ml; #if CYTHON_BACKPORT_VECTORCALL Py_ssize_t nargs = (Py_ssize_t)nargsf; #else Py_ssize_t nargs = PyVectorcall_NARGS(nargsf); #endif PyObject *self; switch (__Pyx_CyFunction_Vectorcall_CheckArgs(cyfunc, nargs, kwnames)) { case 1: self = args[0]; args += 1; nargs -= 1; break; case 0: self = ((PyCFunctionObject*)cyfunc)->m_self; break; default: return NULL; } if (unlikely(nargs != 0)) { PyErr_Format(PyExc_TypeError, "%.200s() takes no arguments (%" CYTHON_FORMAT_SSIZE_T "d given)", def->ml_name, nargs); return NULL; } return def->ml_meth(self, NULL); } static PyObject * __Pyx_CyFunction_Vectorcall_O(PyObject *func, PyObject *const *args, size_t nargsf, PyObject *kwnames) { __pyx_CyFunctionObject *cyfunc = (__pyx_CyFunctionObject *)func; PyMethodDef* def = ((PyCFunctionObject*)cyfunc)->m_ml; #if CYTHON_BACKPORT_VECTORCALL Py_ssize_t nargs = (Py_ssize_t)nargsf; #else Py_ssize_t nargs = PyVectorcall_NARGS(nargsf); #endif PyObject *self; switch (__Pyx_CyFunction_Vectorcall_CheckArgs(cyfunc, nargs, kwnames)) { case 1: self = args[0]; args += 1; nargs -= 1; break; case 0: self = ((PyCFunctionObject*)cyfunc)->m_self; break; default: return NULL; } if (unlikely(nargs != 1)) { PyErr_Format(PyExc_TypeError, "%.200s() takes exactly one argument (%" CYTHON_FORMAT_SSIZE_T "d given)", def->ml_name, nargs); return NULL; } return def->ml_meth(self, args[0]); } static PyObject * __Pyx_CyFunction_Vectorcall_FASTCALL_KEYWORDS(PyObject *func, PyObject *const *args, size_t nargsf, PyObject *kwnames) { __pyx_CyFunctionObject *cyfunc = (__pyx_CyFunctionObject *)func; PyMethodDef* def = ((PyCFunctionObject*)cyfunc)->m_ml; #if CYTHON_BACKPORT_VECTORCALL Py_ssize_t nargs = (Py_ssize_t)nargsf; #else Py_ssize_t nargs = PyVectorcall_NARGS(nargsf); #endif PyObject *self; switch (__Pyx_CyFunction_Vectorcall_CheckArgs(cyfunc, nargs, NULL)) { case 1: self = args[0]; args += 1; nargs -= 1; break; case 0: self = ((PyCFunctionObject*)cyfunc)->m_self; break; default: return NULL; } return ((_PyCFunctionFastWithKeywords)(void(*)(void))def->ml_meth)(self, args, nargs, kwnames); } static PyObject * __Pyx_CyFunction_Vectorcall_FASTCALL_KEYWORDS_METHOD(PyObject *func, PyObject *const *args, size_t nargsf, PyObject *kwnames) { __pyx_CyFunctionObject *cyfunc = (__pyx_CyFunctionObject *)func; PyMethodDef* def = ((PyCFunctionObject*)cyfunc)->m_ml; PyTypeObject *cls = (PyTypeObject *) __Pyx_CyFunction_GetClassObj(cyfunc); #if CYTHON_BACKPORT_VECTORCALL Py_ssize_t nargs = (Py_ssize_t)nargsf; #else Py_ssize_t nargs = PyVectorcall_NARGS(nargsf); #endif PyObject *self; switch (__Pyx_CyFunction_Vectorcall_CheckArgs(cyfunc, nargs, NULL)) { case 1: self = args[0]; args += 1; nargs -= 1; break; case 0: self = ((PyCFunctionObject*)cyfunc)->m_self; break; default: return NULL; } return ((__Pyx_PyCMethod)(void(*)(void))def->ml_meth)(self, cls, args, (size_t)nargs, kwnames); } #endif #if CYTHON_USE_TYPE_SPECS static PyType_Slot __pyx_CyFunctionType_slots[] = { {Py_tp_dealloc, (void *)__Pyx_CyFunction_dealloc}, {Py_tp_repr, (void *)__Pyx_CyFunction_repr}, {Py_tp_call, (void *)__Pyx_CyFunction_CallAsMethod}, {Py_tp_traverse, (void *)__Pyx_CyFunction_traverse}, {Py_tp_clear, (void *)__Pyx_CyFunction_clear}, {Py_tp_methods, (void *)__pyx_CyFunction_methods}, {Py_tp_members, (void *)__pyx_CyFunction_members}, {Py_tp_getset, (void *)__pyx_CyFunction_getsets}, {Py_tp_descr_get, (void *)__Pyx_PyMethod_New}, {0, 0}, }; static PyType_Spec __pyx_CyFunctionType_spec = { __PYX_TYPE_MODULE_PREFIX "cython_function_or_method", sizeof(__pyx_CyFunctionObject), 0, #ifdef Py_TPFLAGS_METHOD_DESCRIPTOR Py_TPFLAGS_METHOD_DESCRIPTOR | #endif #if (defined(_Py_TPFLAGS_HAVE_VECTORCALL) && CYTHON_METH_FASTCALL) _Py_TPFLAGS_HAVE_VECTORCALL | #endif Py_TPFLAGS_DEFAULT | Py_TPFLAGS_HAVE_GC | Py_TPFLAGS_BASETYPE, __pyx_CyFunctionType_slots }; #else static PyTypeObject __pyx_CyFunctionType_type = { PyVarObject_HEAD_INIT(0, 0) __PYX_TYPE_MODULE_PREFIX "cython_function_or_method", sizeof(__pyx_CyFunctionObject), 0, (destructor) __Pyx_CyFunction_dealloc, #if !CYTHON_METH_FASTCALL 0, #elif CYTHON_BACKPORT_VECTORCALL (printfunc)offsetof(__pyx_CyFunctionObject, func_vectorcall), #else offsetof(PyCFunctionObject, vectorcall), #endif 0, 0, #if PY_MAJOR_VERSION < 3 0, #else 0, #endif (reprfunc) __Pyx_CyFunction_repr, 0, 0, 0, 0, __Pyx_CyFunction_CallAsMethod, 0, 0, 0, 0, #ifdef Py_TPFLAGS_METHOD_DESCRIPTOR Py_TPFLAGS_METHOD_DESCRIPTOR | #endif #if defined(_Py_TPFLAGS_HAVE_VECTORCALL) && CYTHON_METH_FASTCALL _Py_TPFLAGS_HAVE_VECTORCALL | #endif Py_TPFLAGS_DEFAULT | Py_TPFLAGS_HAVE_GC | Py_TPFLAGS_BASETYPE, 0, (traverseproc) __Pyx_CyFunction_traverse, (inquiry) __Pyx_CyFunction_clear, 0, #if PY_VERSION_HEX < 0x030500A0 offsetof(__pyx_CyFunctionObject, func_weakreflist), #else offsetof(PyCFunctionObject, m_weakreflist), #endif 0, 0, __pyx_CyFunction_methods, __pyx_CyFunction_members, __pyx_CyFunction_getsets, 0, 0, __Pyx_PyMethod_New, 0, offsetof(__pyx_CyFunctionObject, func_dict), 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, #if PY_VERSION_HEX >= 0x030400a1 0, #endif #if PY_VERSION_HEX >= 0x030800b1 && (!CYTHON_COMPILING_IN_PYPY || PYPY_VERSION_NUM >= 0x07030800) 0, #endif #if __PYX_NEED_TP_PRINT_SLOT 0, #endif #if PY_VERSION_HEX >= 0x030C0000 0, #endif #if CYTHON_COMPILING_IN_PYPY && PY_VERSION_HEX >= 0x03090000 && PY_VERSION_HEX < 0x030a0000 0, #endif }; #endif static int __pyx_CyFunction_init(PyObject *module) { #if CYTHON_USE_TYPE_SPECS __pyx_CyFunctionType = __Pyx_FetchCommonTypeFromSpec(module, &__pyx_CyFunctionType_spec, NULL); #else CYTHON_UNUSED_VAR(module); __pyx_CyFunctionType = __Pyx_FetchCommonType(&__pyx_CyFunctionType_type); #endif if (unlikely(__pyx_CyFunctionType == NULL)) { return -1; } return 0; } static CYTHON_INLINE void *__Pyx_CyFunction_InitDefaults(PyObject *func, size_t size, int pyobjects) { __pyx_CyFunctionObject *m = (__pyx_CyFunctionObject *) func; m->defaults = PyObject_Malloc(size); if (unlikely(!m->defaults)) return PyErr_NoMemory(); memset(m->defaults, 0, size); m->defaults_pyobjects = pyobjects; m->defaults_size = size; return m->defaults; } static CYTHON_INLINE void __Pyx_CyFunction_SetDefaultsTuple(PyObject *func, PyObject *tuple) { __pyx_CyFunctionObject *m = (__pyx_CyFunctionObject *) func; m->defaults_tuple = tuple; Py_INCREF(tuple); } static CYTHON_INLINE void __Pyx_CyFunction_SetDefaultsKwDict(PyObject *func, PyObject *dict) { __pyx_CyFunctionObject *m = (__pyx_CyFunctionObject *) func; m->defaults_kwdict = dict; Py_INCREF(dict); } static CYTHON_INLINE void __Pyx_CyFunction_SetAnnotationsDict(PyObject *func, PyObject *dict) { __pyx_CyFunctionObject *m = (__pyx_CyFunctionObject *) func; m->func_annotations = dict; Py_INCREF(dict); } /* CythonFunction */ static PyObject *__Pyx_CyFunction_New(PyMethodDef *ml, int flags, PyObject* qualname, PyObject *closure, PyObject *module, PyObject* globals, PyObject* code) { PyObject *op = __Pyx_CyFunction_Init( PyObject_GC_New(__pyx_CyFunctionObject, __pyx_CyFunctionType), ml, flags, qualname, closure, module, globals, code ); if (likely(op)) { PyObject_GC_Track(op); } return op; } /* GetNameInClass */ static PyObject *__Pyx__GetNameInClass(PyObject *nmspace, PyObject *name) { PyObject *result; PyObject *dict; assert(PyType_Check(nmspace)); #if CYTHON_USE_TYPE_SLOTS dict = ((PyTypeObject*)nmspace)->tp_dict; Py_XINCREF(dict); #else dict = PyObject_GetAttr(nmspace, __pyx_n_s_dict); #endif if (likely(dict)) { result = PyObject_GetItem(dict, name); Py_DECREF(dict); if (result) { return result; } } PyErr_Clear(); __Pyx_GetModuleGlobalNameUncached(result, name); return result; } /* CLineInTraceback */ #ifndef CYTHON_CLINE_IN_TRACEBACK static int __Pyx_CLineForTraceback(PyThreadState *tstate, int c_line) { PyObject *use_cline; PyObject *ptype, *pvalue, *ptraceback; #if CYTHON_COMPILING_IN_CPYTHON PyObject **cython_runtime_dict; #endif CYTHON_MAYBE_UNUSED_VAR(tstate); if (unlikely(!__pyx_cython_runtime)) { return c_line; } __Pyx_ErrFetchInState(tstate, &ptype, &pvalue, &ptraceback); #if CYTHON_COMPILING_IN_CPYTHON cython_runtime_dict = _PyObject_GetDictPtr(__pyx_cython_runtime); if (likely(cython_runtime_dict)) { __PYX_PY_DICT_LOOKUP_IF_MODIFIED( use_cline, *cython_runtime_dict, __Pyx_PyDict_GetItemStr(*cython_runtime_dict, __pyx_n_s_cline_in_traceback)) } else #endif { PyObject *use_cline_obj = __Pyx_PyObject_GetAttrStrNoError(__pyx_cython_runtime, __pyx_n_s_cline_in_traceback); if (use_cline_obj) { use_cline = PyObject_Not(use_cline_obj) ? Py_False : Py_True; Py_DECREF(use_cline_obj); } else { PyErr_Clear(); use_cline = NULL; } } if (!use_cline) { c_line = 0; (void) PyObject_SetAttr(__pyx_cython_runtime, __pyx_n_s_cline_in_traceback, Py_False); } else if (use_cline == Py_False || (use_cline != Py_True && PyObject_Not(use_cline) != 0)) { c_line = 0; } __Pyx_ErrRestoreInState(tstate, ptype, pvalue, ptraceback); return c_line; } #endif /* CodeObjectCache */ #if !CYTHON_COMPILING_IN_LIMITED_API static int __pyx_bisect_code_objects(__Pyx_CodeObjectCacheEntry* entries, int count, int code_line) { int start = 0, mid = 0, end = count - 1; if (end >= 0 && code_line > entries[end].code_line) { return count; } while (start < end) { mid = start + (end - start) / 2; if (code_line < entries[mid].code_line) { end = mid; } else if (code_line > entries[mid].code_line) { start = mid + 1; } else { return mid; } } if (code_line <= entries[mid].code_line) { return mid; } else { return mid + 1; } } static PyCodeObject *__pyx_find_code_object(int code_line) { PyCodeObject* code_object; int pos; if (unlikely(!code_line) || unlikely(!__pyx_code_cache.entries)) { return NULL; } pos = __pyx_bisect_code_objects(__pyx_code_cache.entries, __pyx_code_cache.count, code_line); if (unlikely(pos >= __pyx_code_cache.count) || unlikely(__pyx_code_cache.entries[pos].code_line != code_line)) { return NULL; } code_object = __pyx_code_cache.entries[pos].code_object; Py_INCREF(code_object); return code_object; } static void __pyx_insert_code_object(int code_line, PyCodeObject* code_object) { int pos, i; __Pyx_CodeObjectCacheEntry* entries = __pyx_code_cache.entries; if (unlikely(!code_line)) { return; } if (unlikely(!entries)) { entries = (__Pyx_CodeObjectCacheEntry*)PyMem_Malloc(64*sizeof(__Pyx_CodeObjectCacheEntry)); if (likely(entries)) { __pyx_code_cache.entries = entries; __pyx_code_cache.max_count = 64; __pyx_code_cache.count = 1; entries[0].code_line = code_line; entries[0].code_object = code_object; Py_INCREF(code_object); } return; } pos = __pyx_bisect_code_objects(__pyx_code_cache.entries, __pyx_code_cache.count, code_line); if ((pos < __pyx_code_cache.count) && unlikely(__pyx_code_cache.entries[pos].code_line == code_line)) { PyCodeObject* tmp = entries[pos].code_object; entries[pos].code_object = code_object; Py_DECREF(tmp); return; } if (__pyx_code_cache.count == __pyx_code_cache.max_count) { int new_max = __pyx_code_cache.max_count + 64; entries = (__Pyx_CodeObjectCacheEntry*)PyMem_Realloc( __pyx_code_cache.entries, ((size_t)new_max) * sizeof(__Pyx_CodeObjectCacheEntry)); if (unlikely(!entries)) { return; } __pyx_code_cache.entries = entries; __pyx_code_cache.max_count = new_max; } for (i=__pyx_code_cache.count; i>pos; i--) { entries[i] = entries[i-1]; } entries[pos].code_line = code_line; entries[pos].code_object = code_object; __pyx_code_cache.count++; Py_INCREF(code_object); } #endif /* AddTraceback */ #include "compile.h" #include "frameobject.h" #include "traceback.h" #if PY_VERSION_HEX >= 0x030b00a6 && !CYTHON_COMPILING_IN_LIMITED_API #ifndef Py_BUILD_CORE #define Py_BUILD_CORE 1 #endif #include "internal/pycore_frame.h" #endif #if CYTHON_COMPILING_IN_LIMITED_API static PyObject *__Pyx_PyCode_Replace_For_AddTraceback(PyObject *code, PyObject *scratch_dict, PyObject *firstlineno, PyObject *name) { PyObject *replace = NULL; if (unlikely(PyDict_SetItemString(scratch_dict, "co_firstlineno", firstlineno))) return NULL; if (unlikely(PyDict_SetItemString(scratch_dict, "co_name", name))) return NULL; replace = PyObject_GetAttrString(code, "replace"); if (likely(replace)) { PyObject *result; result = PyObject_Call(replace, __pyx_empty_tuple, scratch_dict); Py_DECREF(replace); return result; } PyErr_Clear(); #if __PYX_LIMITED_VERSION_HEX < 0x030780000 { PyObject *compiled = NULL, *result = NULL; if (unlikely(PyDict_SetItemString(scratch_dict, "code", code))) return NULL; if (unlikely(PyDict_SetItemString(scratch_dict, "type", (PyObject*)(&PyType_Type)))) return NULL; compiled = Py_CompileString( "out = type(code)(\n" " code.co_argcount, code.co_kwonlyargcount, code.co_nlocals, code.co_stacksize,\n" " code.co_flags, code.co_code, code.co_consts, code.co_names,\n" " code.co_varnames, code.co_filename, co_name, co_firstlineno,\n" " code.co_lnotab)\n", "", Py_file_input); if (!compiled) return NULL; result = PyEval_EvalCode(compiled, scratch_dict, scratch_dict); Py_DECREF(compiled); if (!result) PyErr_Print(); Py_DECREF(result); result = PyDict_GetItemString(scratch_dict, "out"); if (result) Py_INCREF(result); return result; } #else return NULL; #endif } static void __Pyx_AddTraceback(const char *funcname, int c_line, int py_line, const char *filename) { PyObject *code_object = NULL, *py_py_line = NULL, *py_funcname = NULL, *dict = NULL; PyObject *replace = NULL, *getframe = NULL, *frame = NULL; PyObject *exc_type, *exc_value, *exc_traceback; int success = 0; if (c_line) { (void) __pyx_cfilenm; (void) __Pyx_CLineForTraceback(__Pyx_PyThreadState_Current, c_line); } PyErr_Fetch(&exc_type, &exc_value, &exc_traceback); code_object = Py_CompileString("_getframe()", filename, Py_eval_input); if (unlikely(!code_object)) goto bad; py_py_line = PyLong_FromLong(py_line); if (unlikely(!py_py_line)) goto bad; py_funcname = PyUnicode_FromString(funcname); if (unlikely(!py_funcname)) goto bad; dict = PyDict_New(); if (unlikely(!dict)) goto bad; { PyObject *old_code_object = code_object; code_object = __Pyx_PyCode_Replace_For_AddTraceback(code_object, dict, py_py_line, py_funcname); Py_DECREF(old_code_object); } if (unlikely(!code_object)) goto bad; getframe = PySys_GetObject("_getframe"); if (unlikely(!getframe)) goto bad; if (unlikely(PyDict_SetItemString(dict, "_getframe", getframe))) goto bad; frame = PyEval_EvalCode(code_object, dict, dict); if (unlikely(!frame) || frame == Py_None) goto bad; success = 1; bad: PyErr_Restore(exc_type, exc_value, exc_traceback); Py_XDECREF(code_object); Py_XDECREF(py_py_line); Py_XDECREF(py_funcname); Py_XDECREF(dict); Py_XDECREF(replace); if (success) { PyTraceBack_Here( (struct _frame*)frame); } Py_XDECREF(frame); } #else static PyCodeObject* __Pyx_CreateCodeObjectForTraceback( const char *funcname, int c_line, int py_line, const char *filename) { PyCodeObject *py_code = NULL; PyObject *py_funcname = NULL; #if PY_MAJOR_VERSION < 3 PyObject *py_srcfile = NULL; py_srcfile = PyString_FromString(filename); if (!py_srcfile) goto bad; #endif if (c_line) { #if PY_MAJOR_VERSION < 3 py_funcname = PyString_FromFormat( "%s (%s:%d)", funcname, __pyx_cfilenm, c_line); if (!py_funcname) goto bad; #else py_funcname = PyUnicode_FromFormat( "%s (%s:%d)", funcname, __pyx_cfilenm, c_line); if (!py_funcname) goto bad; funcname = PyUnicode_AsUTF8(py_funcname); if (!funcname) goto bad; #endif } else { #if PY_MAJOR_VERSION < 3 py_funcname = PyString_FromString(funcname); if (!py_funcname) goto bad; #endif } #if PY_MAJOR_VERSION < 3 py_code = __Pyx_PyCode_New( 0, 0, 0, 0, 0, 0, __pyx_empty_bytes, /*PyObject *code,*/ __pyx_empty_tuple, /*PyObject *consts,*/ __pyx_empty_tuple, /*PyObject *names,*/ __pyx_empty_tuple, /*PyObject *varnames,*/ __pyx_empty_tuple, /*PyObject *freevars,*/ __pyx_empty_tuple, /*PyObject *cellvars,*/ py_srcfile, /*PyObject *filename,*/ py_funcname, /*PyObject *name,*/ py_line, __pyx_empty_bytes /*PyObject *lnotab*/ ); Py_DECREF(py_srcfile); #else py_code = PyCode_NewEmpty(filename, funcname, py_line); #endif Py_XDECREF(py_funcname); return py_code; bad: Py_XDECREF(py_funcname); #if PY_MAJOR_VERSION < 3 Py_XDECREF(py_srcfile); #endif return NULL; } static void __Pyx_AddTraceback(const char *funcname, int c_line, int py_line, const char *filename) { PyCodeObject *py_code = 0; PyFrameObject *py_frame = 0; PyThreadState *tstate = __Pyx_PyThreadState_Current; PyObject *ptype, *pvalue, *ptraceback; if (c_line) { c_line = __Pyx_CLineForTraceback(tstate, c_line); } py_code = __pyx_find_code_object(c_line ? -c_line : py_line); if (!py_code) { __Pyx_ErrFetchInState(tstate, &ptype, &pvalue, &ptraceback); py_code = __Pyx_CreateCodeObjectForTraceback( funcname, c_line, py_line, filename); if (!py_code) { /* If the code object creation fails, then we should clear the fetched exception references and propagate the new exception */ Py_XDECREF(ptype); Py_XDECREF(pvalue); Py_XDECREF(ptraceback); goto bad; } __Pyx_ErrRestoreInState(tstate, ptype, pvalue, ptraceback); __pyx_insert_code_object(c_line ? -c_line : py_line, py_code); } py_frame = PyFrame_New( tstate, /*PyThreadState *tstate,*/ py_code, /*PyCodeObject *code,*/ __pyx_d, /*PyObject *globals,*/ 0 /*PyObject *locals*/ ); if (!py_frame) goto bad; __Pyx_PyFrame_SetLineNumber(py_frame, py_line); PyTraceBack_Here(py_frame); bad: Py_XDECREF(py_code); Py_XDECREF(py_frame); } #endif /* CIntFromPyVerify */ #define __PYX_VERIFY_RETURN_INT(target_type, func_type, func_value)\ __PYX__VERIFY_RETURN_INT(target_type, func_type, func_value, 0) #define __PYX_VERIFY_RETURN_INT_EXC(target_type, func_type, func_value)\ __PYX__VERIFY_RETURN_INT(target_type, func_type, func_value, 1) #define __PYX__VERIFY_RETURN_INT(target_type, func_type, func_value, exc)\ {\ func_type value = func_value;\ if (sizeof(target_type) < sizeof(func_type)) {\ if (unlikely(value != (func_type) (target_type) value)) {\ func_type zero = 0;\ if (exc && unlikely(value == (func_type)-1 && PyErr_Occurred()))\ return (target_type) -1;\ if (is_unsigned && unlikely(value < zero))\ goto raise_neg_overflow;\ else\ goto raise_overflow;\ }\ }\ return (target_type) value;\ } /* CIntToPy */ static CYTHON_INLINE PyObject* __Pyx_PyInt_From_long(long value) { #ifdef __Pyx_HAS_GCC_DIAGNOSTIC #pragma GCC diagnostic push #pragma GCC diagnostic ignored "-Wconversion" #endif const long neg_one = (long) -1, const_zero = (long) 0; #ifdef __Pyx_HAS_GCC_DIAGNOSTIC #pragma GCC diagnostic pop #endif const int is_unsigned = neg_one > const_zero; if (is_unsigned) { if (sizeof(long) < sizeof(long)) { return PyInt_FromLong((long) value); } else if (sizeof(long) <= sizeof(unsigned long)) { return PyLong_FromUnsignedLong((unsigned long) value); #ifdef HAVE_LONG_LONG } else if (sizeof(long) <= sizeof(unsigned PY_LONG_LONG)) { return PyLong_FromUnsignedLongLong((unsigned PY_LONG_LONG) value); #endif } } else { if (sizeof(long) <= sizeof(long)) { return PyInt_FromLong((long) value); #ifdef HAVE_LONG_LONG } else if (sizeof(long) <= sizeof(PY_LONG_LONG)) { return PyLong_FromLongLong((PY_LONG_LONG) value); #endif } } { int one = 1; int little = (int)*(unsigned char *)&one; unsigned char *bytes = (unsigned char *)&value; #if !CYTHON_COMPILING_IN_LIMITED_API && PY_VERSION_HEX < 0x030d0000 return _PyLong_FromByteArray(bytes, sizeof(long), little, !is_unsigned); #else PyObject *from_bytes, *result = NULL; PyObject *py_bytes = NULL, *arg_tuple = NULL, *kwds = NULL, *order_str = NULL; from_bytes = PyObject_GetAttrString((PyObject*)&PyLong_Type, "from_bytes"); if (!from_bytes) return NULL; py_bytes = PyBytes_FromStringAndSize((char*)bytes, sizeof(long)); if (!py_bytes) goto limited_bad; order_str = PyUnicode_FromString(little ? "little" : "big"); if (!order_str) goto limited_bad; arg_tuple = PyTuple_Pack(2, py_bytes, order_str); if (!arg_tuple) goto limited_bad; if (!is_unsigned) { kwds = PyDict_New(); if (!kwds) goto limited_bad; if (PyDict_SetItemString(kwds, "signed", __Pyx_NewRef(Py_True))) goto limited_bad; } result = PyObject_Call(from_bytes, arg_tuple, kwds); limited_bad: Py_XDECREF(kwds); Py_XDECREF(arg_tuple); Py_XDECREF(order_str); Py_XDECREF(py_bytes); Py_XDECREF(from_bytes); return result; #endif } } /* CIntFromPy */ static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *x) { #ifdef __Pyx_HAS_GCC_DIAGNOSTIC #pragma GCC diagnostic push #pragma GCC diagnostic ignored "-Wconversion" #endif const long neg_one = (long) -1, const_zero = (long) 0; #ifdef __Pyx_HAS_GCC_DIAGNOSTIC #pragma GCC diagnostic pop #endif const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 if (likely(PyInt_Check(x))) { if ((sizeof(long) < sizeof(long))) { __PYX_VERIFY_RETURN_INT(long, long, PyInt_AS_LONG(x)) } else { long val = PyInt_AS_LONG(x); if (is_unsigned && unlikely(val < 0)) { goto raise_neg_overflow; } return (long) val; } } else #endif if (likely(PyLong_Check(x))) { if (is_unsigned) { #if CYTHON_USE_PYLONG_INTERNALS if (unlikely(__Pyx_PyLong_IsNeg(x))) { goto raise_neg_overflow; } else if (__Pyx_PyLong_IsCompact(x)) { __PYX_VERIFY_RETURN_INT(long, __Pyx_compact_upylong, __Pyx_PyLong_CompactValueUnsigned(x)) } else { const digit* digits = __Pyx_PyLong_Digits(x); assert(__Pyx_PyLong_DigitCount(x) > 1); switch (__Pyx_PyLong_DigitCount(x)) { case 2: if ((8 * sizeof(long) > 1 * PyLong_SHIFT)) { if ((8 * sizeof(unsigned long) > 2 * PyLong_SHIFT)) { __PYX_VERIFY_RETURN_INT(long, unsigned long, (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) } else if ((8 * sizeof(long) >= 2 * PyLong_SHIFT)) { return (long) (((((long)digits[1]) << PyLong_SHIFT) | (long)digits[0])); } } break; case 3: if ((8 * sizeof(long) > 2 * PyLong_SHIFT)) { if ((8 * sizeof(unsigned long) > 3 * PyLong_SHIFT)) { __PYX_VERIFY_RETURN_INT(long, unsigned long, (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) } else if ((8 * sizeof(long) >= 3 * PyLong_SHIFT)) { return (long) (((((((long)digits[2]) << PyLong_SHIFT) | (long)digits[1]) << PyLong_SHIFT) | (long)digits[0])); } } break; case 4: if ((8 * sizeof(long) > 3 * PyLong_SHIFT)) { if ((8 * sizeof(unsigned long) > 4 * PyLong_SHIFT)) { __PYX_VERIFY_RETURN_INT(long, unsigned long, (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) } else if ((8 * sizeof(long) >= 4 * PyLong_SHIFT)) { return (long) (((((((((long)digits[3]) << PyLong_SHIFT) | (long)digits[2]) << PyLong_SHIFT) | (long)digits[1]) << PyLong_SHIFT) | (long)digits[0])); } } break; } } #endif #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX < 0x030C00A7 if (unlikely(Py_SIZE(x) < 0)) { goto raise_neg_overflow; } #else { int result = PyObject_RichCompareBool(x, Py_False, Py_LT); if (unlikely(result < 0)) return (long) -1; if (unlikely(result == 1)) goto raise_neg_overflow; } #endif if ((sizeof(long) <= sizeof(unsigned long))) { __PYX_VERIFY_RETURN_INT_EXC(long, unsigned long, PyLong_AsUnsignedLong(x)) #ifdef HAVE_LONG_LONG } else if ((sizeof(long) <= sizeof(unsigned PY_LONG_LONG))) { __PYX_VERIFY_RETURN_INT_EXC(long, unsigned PY_LONG_LONG, PyLong_AsUnsignedLongLong(x)) #endif } } else { #if CYTHON_USE_PYLONG_INTERNALS if (__Pyx_PyLong_IsCompact(x)) { __PYX_VERIFY_RETURN_INT(long, __Pyx_compact_pylong, __Pyx_PyLong_CompactValue(x)) } else { const digit* digits = __Pyx_PyLong_Digits(x); assert(__Pyx_PyLong_DigitCount(x) > 1); switch (__Pyx_PyLong_SignedDigitCount(x)) { case -2: if ((8 * sizeof(long) - 1 > 1 * PyLong_SHIFT)) { if ((8 * sizeof(unsigned long) > 2 * PyLong_SHIFT)) { __PYX_VERIFY_RETURN_INT(long, long, -(long) (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) } else if ((8 * sizeof(long) - 1 > 2 * PyLong_SHIFT)) { return (long) (((long)-1)*(((((long)digits[1]) << PyLong_SHIFT) | (long)digits[0]))); } } break; case 2: if ((8 * sizeof(long) > 1 * PyLong_SHIFT)) { if ((8 * sizeof(unsigned long) > 2 * PyLong_SHIFT)) { __PYX_VERIFY_RETURN_INT(long, unsigned long, (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) } else if ((8 * sizeof(long) - 1 > 2 * PyLong_SHIFT)) { return (long) ((((((long)digits[1]) << PyLong_SHIFT) | (long)digits[0]))); } } break; case -3: if ((8 * sizeof(long) - 1 > 2 * PyLong_SHIFT)) { if ((8 * sizeof(unsigned long) > 3 * PyLong_SHIFT)) { __PYX_VERIFY_RETURN_INT(long, long, -(long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) } else if ((8 * sizeof(long) - 1 > 3 * PyLong_SHIFT)) { return (long) (((long)-1)*(((((((long)digits[2]) << PyLong_SHIFT) | (long)digits[1]) << PyLong_SHIFT) | (long)digits[0]))); } } break; case 3: if ((8 * sizeof(long) > 2 * PyLong_SHIFT)) { if ((8 * sizeof(unsigned long) > 3 * PyLong_SHIFT)) { __PYX_VERIFY_RETURN_INT(long, unsigned long, (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) } else if ((8 * sizeof(long) - 1 > 3 * PyLong_SHIFT)) { return (long) ((((((((long)digits[2]) << PyLong_SHIFT) | (long)digits[1]) << PyLong_SHIFT) | (long)digits[0]))); } } break; case -4: if ((8 * sizeof(long) - 1 > 3 * PyLong_SHIFT)) { if ((8 * sizeof(unsigned long) > 4 * PyLong_SHIFT)) { __PYX_VERIFY_RETURN_INT(long, long, -(long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) } else if ((8 * sizeof(long) - 1 > 4 * PyLong_SHIFT)) { return (long) (((long)-1)*(((((((((long)digits[3]) << PyLong_SHIFT) | (long)digits[2]) << PyLong_SHIFT) | (long)digits[1]) << PyLong_SHIFT) | (long)digits[0]))); } } break; case 4: if ((8 * sizeof(long) > 3 * PyLong_SHIFT)) { if ((8 * sizeof(unsigned long) > 4 * PyLong_SHIFT)) { __PYX_VERIFY_RETURN_INT(long, unsigned long, (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) } else if ((8 * sizeof(long) - 1 > 4 * PyLong_SHIFT)) { return (long) ((((((((((long)digits[3]) << PyLong_SHIFT) | (long)digits[2]) << PyLong_SHIFT) | (long)digits[1]) << PyLong_SHIFT) | (long)digits[0]))); } } break; } } #endif if ((sizeof(long) <= sizeof(long))) { __PYX_VERIFY_RETURN_INT_EXC(long, long, PyLong_AsLong(x)) #ifdef HAVE_LONG_LONG } else if ((sizeof(long) <= sizeof(PY_LONG_LONG))) { __PYX_VERIFY_RETURN_INT_EXC(long, PY_LONG_LONG, PyLong_AsLongLong(x)) #endif } } { long val; PyObject *v = __Pyx_PyNumber_IntOrLong(x); #if PY_MAJOR_VERSION < 3 if (likely(v) && !PyLong_Check(v)) { PyObject *tmp = v; v = PyNumber_Long(tmp); Py_DECREF(tmp); } #endif if (likely(v)) { int ret = -1; #if PY_VERSION_HEX < 0x030d0000 && !(CYTHON_COMPILING_IN_PYPY || CYTHON_COMPILING_IN_LIMITED_API) || defined(_PyLong_AsByteArray) int one = 1; int is_little = (int)*(unsigned char *)&one; unsigned char *bytes = (unsigned char *)&val; ret = _PyLong_AsByteArray((PyLongObject *)v, bytes, sizeof(val), is_little, !is_unsigned); #else PyObject *stepval = NULL, *mask = NULL, *shift = NULL; int bits, remaining_bits, is_negative = 0; long idigit; int chunk_size = (sizeof(long) < 8) ? 30 : 62; if (unlikely(!PyLong_CheckExact(v))) { PyObject *tmp = v; v = PyNumber_Long(v); assert(PyLong_CheckExact(v)); Py_DECREF(tmp); if (unlikely(!v)) return (long) -1; } #if CYTHON_COMPILING_IN_LIMITED_API && PY_VERSION_HEX < 0x030B0000 if (Py_SIZE(x) == 0) return (long) 0; is_negative = Py_SIZE(x) < 0; #else { int result = PyObject_RichCompareBool(x, Py_False, Py_LT); if (unlikely(result < 0)) return (long) -1; is_negative = result == 1; } #endif if (is_unsigned && unlikely(is_negative)) { goto raise_neg_overflow; } else if (is_negative) { stepval = PyNumber_Invert(v); if (unlikely(!stepval)) return (long) -1; } else { stepval = __Pyx_NewRef(v); } val = (long) 0; mask = PyLong_FromLong((1L << chunk_size) - 1); if (unlikely(!mask)) goto done; shift = PyLong_FromLong(chunk_size); if (unlikely(!shift)) goto done; for (bits = 0; bits < (int) sizeof(long) * 8 - chunk_size; bits += chunk_size) { PyObject *tmp, *digit; digit = PyNumber_And(stepval, mask); if (unlikely(!digit)) goto done; idigit = PyLong_AsLong(digit); Py_DECREF(digit); if (unlikely(idigit < 0)) goto done; tmp = PyNumber_Rshift(stepval, shift); if (unlikely(!tmp)) goto done; Py_DECREF(stepval); stepval = tmp; val |= ((long) idigit) << bits; #if CYTHON_COMPILING_IN_LIMITED_API && PY_VERSION_HEX < 0x030B0000 if (Py_SIZE(stepval) == 0) goto unpacking_done; #endif } idigit = PyLong_AsLong(stepval); if (unlikely(idigit < 0)) goto done; remaining_bits = ((int) sizeof(long) * 8) - bits - (is_unsigned ? 0 : 1); if (unlikely(idigit >= (1L << remaining_bits))) goto raise_overflow; val |= ((long) idigit) << bits; #if CYTHON_COMPILING_IN_LIMITED_API && PY_VERSION_HEX < 0x030B0000 unpacking_done: #endif if (!is_unsigned) { if (unlikely(val & (((long) 1) << (sizeof(long) * 8 - 1)))) goto raise_overflow; if (is_negative) val = ~val; } ret = 0; done: Py_XDECREF(shift); Py_XDECREF(mask); Py_XDECREF(stepval); #endif Py_DECREF(v); if (likely(!ret)) return val; } return (long) -1; } } else { long val; PyObject *tmp = __Pyx_PyNumber_IntOrLong(x); if (!tmp) return (long) -1; val = __Pyx_PyInt_As_long(tmp); Py_DECREF(tmp); return val; } raise_overflow: PyErr_SetString(PyExc_OverflowError, "value too large to convert to long"); return (long) -1; raise_neg_overflow: PyErr_SetString(PyExc_OverflowError, "can't convert negative value to long"); return (long) -1; } /* FormatTypeName */ #if CYTHON_COMPILING_IN_LIMITED_API static __Pyx_TypeName __Pyx_PyType_GetName(PyTypeObject* tp) { PyObject *name = __Pyx_PyObject_GetAttrStr((PyObject *)tp, __pyx_n_s_name); if (unlikely(name == NULL) || unlikely(!PyUnicode_Check(name))) { PyErr_Clear(); Py_XDECREF(name); name = __Pyx_NewRef(__pyx_n_s__28); } return name; } #endif /* CIntFromPy */ static CYTHON_INLINE int __Pyx_PyInt_As_int(PyObject *x) { #ifdef __Pyx_HAS_GCC_DIAGNOSTIC #pragma GCC diagnostic push #pragma GCC diagnostic ignored "-Wconversion" #endif const int neg_one = (int) -1, const_zero = (int) 0; #ifdef __Pyx_HAS_GCC_DIAGNOSTIC #pragma GCC diagnostic pop #endif const int is_unsigned = neg_one > const_zero; #if PY_MAJOR_VERSION < 3 if (likely(PyInt_Check(x))) { if ((sizeof(int) < sizeof(long))) { __PYX_VERIFY_RETURN_INT(int, long, PyInt_AS_LONG(x)) } else { long val = PyInt_AS_LONG(x); if (is_unsigned && unlikely(val < 0)) { goto raise_neg_overflow; } return (int) val; } } else #endif if (likely(PyLong_Check(x))) { if (is_unsigned) { #if CYTHON_USE_PYLONG_INTERNALS if (unlikely(__Pyx_PyLong_IsNeg(x))) { goto raise_neg_overflow; } else if (__Pyx_PyLong_IsCompact(x)) { __PYX_VERIFY_RETURN_INT(int, __Pyx_compact_upylong, __Pyx_PyLong_CompactValueUnsigned(x)) } else { const digit* digits = __Pyx_PyLong_Digits(x); assert(__Pyx_PyLong_DigitCount(x) > 1); switch (__Pyx_PyLong_DigitCount(x)) { case 2: if ((8 * sizeof(int) > 1 * PyLong_SHIFT)) { if ((8 * sizeof(unsigned long) > 2 * PyLong_SHIFT)) { __PYX_VERIFY_RETURN_INT(int, unsigned long, (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) } else if ((8 * sizeof(int) >= 2 * PyLong_SHIFT)) { return (int) (((((int)digits[1]) << PyLong_SHIFT) | (int)digits[0])); } } break; case 3: if ((8 * sizeof(int) > 2 * PyLong_SHIFT)) { if ((8 * sizeof(unsigned long) > 3 * PyLong_SHIFT)) { __PYX_VERIFY_RETURN_INT(int, unsigned long, (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) } else if ((8 * sizeof(int) >= 3 * PyLong_SHIFT)) { return (int) (((((((int)digits[2]) << PyLong_SHIFT) | (int)digits[1]) << PyLong_SHIFT) | (int)digits[0])); } } break; case 4: if ((8 * sizeof(int) > 3 * PyLong_SHIFT)) { if ((8 * sizeof(unsigned long) > 4 * PyLong_SHIFT)) { __PYX_VERIFY_RETURN_INT(int, unsigned long, (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) } else if ((8 * sizeof(int) >= 4 * PyLong_SHIFT)) { return (int) (((((((((int)digits[3]) << PyLong_SHIFT) | (int)digits[2]) << PyLong_SHIFT) | (int)digits[1]) << PyLong_SHIFT) | (int)digits[0])); } } break; } } #endif #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX < 0x030C00A7 if (unlikely(Py_SIZE(x) < 0)) { goto raise_neg_overflow; } #else { int result = PyObject_RichCompareBool(x, Py_False, Py_LT); if (unlikely(result < 0)) return (int) -1; if (unlikely(result == 1)) goto raise_neg_overflow; } #endif if ((sizeof(int) <= sizeof(unsigned long))) { __PYX_VERIFY_RETURN_INT_EXC(int, unsigned long, PyLong_AsUnsignedLong(x)) #ifdef HAVE_LONG_LONG } else if ((sizeof(int) <= sizeof(unsigned PY_LONG_LONG))) { __PYX_VERIFY_RETURN_INT_EXC(int, unsigned PY_LONG_LONG, PyLong_AsUnsignedLongLong(x)) #endif } } else { #if CYTHON_USE_PYLONG_INTERNALS if (__Pyx_PyLong_IsCompact(x)) { __PYX_VERIFY_RETURN_INT(int, __Pyx_compact_pylong, __Pyx_PyLong_CompactValue(x)) } else { const digit* digits = __Pyx_PyLong_Digits(x); assert(__Pyx_PyLong_DigitCount(x) > 1); switch (__Pyx_PyLong_SignedDigitCount(x)) { case -2: if ((8 * sizeof(int) - 1 > 1 * PyLong_SHIFT)) { if ((8 * sizeof(unsigned long) > 2 * PyLong_SHIFT)) { __PYX_VERIFY_RETURN_INT(int, long, -(long) (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) } else if ((8 * sizeof(int) - 1 > 2 * PyLong_SHIFT)) { return (int) (((int)-1)*(((((int)digits[1]) << PyLong_SHIFT) | (int)digits[0]))); } } break; case 2: if ((8 * sizeof(int) > 1 * PyLong_SHIFT)) { if ((8 * sizeof(unsigned long) > 2 * PyLong_SHIFT)) { __PYX_VERIFY_RETURN_INT(int, unsigned long, (((((unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) } else if ((8 * sizeof(int) - 1 > 2 * PyLong_SHIFT)) { return (int) ((((((int)digits[1]) << PyLong_SHIFT) | (int)digits[0]))); } } break; case -3: if ((8 * sizeof(int) - 1 > 2 * PyLong_SHIFT)) { if ((8 * sizeof(unsigned long) > 3 * PyLong_SHIFT)) { __PYX_VERIFY_RETURN_INT(int, long, -(long) (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) } else if ((8 * sizeof(int) - 1 > 3 * PyLong_SHIFT)) { return (int) (((int)-1)*(((((((int)digits[2]) << PyLong_SHIFT) | (int)digits[1]) << PyLong_SHIFT) | (int)digits[0]))); } } break; case 3: if ((8 * sizeof(int) > 2 * PyLong_SHIFT)) { if ((8 * sizeof(unsigned long) > 3 * PyLong_SHIFT)) { __PYX_VERIFY_RETURN_INT(int, unsigned long, (((((((unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) } else if ((8 * sizeof(int) - 1 > 3 * PyLong_SHIFT)) { return (int) ((((((((int)digits[2]) << PyLong_SHIFT) | (int)digits[1]) << PyLong_SHIFT) | (int)digits[0]))); } } break; case -4: if ((8 * sizeof(int) - 1 > 3 * PyLong_SHIFT)) { if ((8 * sizeof(unsigned long) > 4 * PyLong_SHIFT)) { __PYX_VERIFY_RETURN_INT(int, long, -(long) (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) } else if ((8 * sizeof(int) - 1 > 4 * PyLong_SHIFT)) { return (int) (((int)-1)*(((((((((int)digits[3]) << PyLong_SHIFT) | (int)digits[2]) << PyLong_SHIFT) | (int)digits[1]) << PyLong_SHIFT) | (int)digits[0]))); } } break; case 4: if ((8 * sizeof(int) > 3 * PyLong_SHIFT)) { if ((8 * sizeof(unsigned long) > 4 * PyLong_SHIFT)) { __PYX_VERIFY_RETURN_INT(int, unsigned long, (((((((((unsigned long)digits[3]) << PyLong_SHIFT) | (unsigned long)digits[2]) << PyLong_SHIFT) | (unsigned long)digits[1]) << PyLong_SHIFT) | (unsigned long)digits[0]))) } else if ((8 * sizeof(int) - 1 > 4 * PyLong_SHIFT)) { return (int) ((((((((((int)digits[3]) << PyLong_SHIFT) | (int)digits[2]) << PyLong_SHIFT) | (int)digits[1]) << PyLong_SHIFT) | (int)digits[0]))); } } break; } } #endif if ((sizeof(int) <= sizeof(long))) { __PYX_VERIFY_RETURN_INT_EXC(int, long, PyLong_AsLong(x)) #ifdef HAVE_LONG_LONG } else if ((sizeof(int) <= sizeof(PY_LONG_LONG))) { __PYX_VERIFY_RETURN_INT_EXC(int, PY_LONG_LONG, PyLong_AsLongLong(x)) #endif } } { int val; PyObject *v = __Pyx_PyNumber_IntOrLong(x); #if PY_MAJOR_VERSION < 3 if (likely(v) && !PyLong_Check(v)) { PyObject *tmp = v; v = PyNumber_Long(tmp); Py_DECREF(tmp); } #endif if (likely(v)) { int ret = -1; #if PY_VERSION_HEX < 0x030d0000 && !(CYTHON_COMPILING_IN_PYPY || CYTHON_COMPILING_IN_LIMITED_API) || defined(_PyLong_AsByteArray) int one = 1; int is_little = (int)*(unsigned char *)&one; unsigned char *bytes = (unsigned char *)&val; ret = _PyLong_AsByteArray((PyLongObject *)v, bytes, sizeof(val), is_little, !is_unsigned); #else PyObject *stepval = NULL, *mask = NULL, *shift = NULL; int bits, remaining_bits, is_negative = 0; long idigit; int chunk_size = (sizeof(long) < 8) ? 30 : 62; if (unlikely(!PyLong_CheckExact(v))) { PyObject *tmp = v; v = PyNumber_Long(v); assert(PyLong_CheckExact(v)); Py_DECREF(tmp); if (unlikely(!v)) return (int) -1; } #if CYTHON_COMPILING_IN_LIMITED_API && PY_VERSION_HEX < 0x030B0000 if (Py_SIZE(x) == 0) return (int) 0; is_negative = Py_SIZE(x) < 0; #else { int result = PyObject_RichCompareBool(x, Py_False, Py_LT); if (unlikely(result < 0)) return (int) -1; is_negative = result == 1; } #endif if (is_unsigned && unlikely(is_negative)) { goto raise_neg_overflow; } else if (is_negative) { stepval = PyNumber_Invert(v); if (unlikely(!stepval)) return (int) -1; } else { stepval = __Pyx_NewRef(v); } val = (int) 0; mask = PyLong_FromLong((1L << chunk_size) - 1); if (unlikely(!mask)) goto done; shift = PyLong_FromLong(chunk_size); if (unlikely(!shift)) goto done; for (bits = 0; bits < (int) sizeof(int) * 8 - chunk_size; bits += chunk_size) { PyObject *tmp, *digit; digit = PyNumber_And(stepval, mask); if (unlikely(!digit)) goto done; idigit = PyLong_AsLong(digit); Py_DECREF(digit); if (unlikely(idigit < 0)) goto done; tmp = PyNumber_Rshift(stepval, shift); if (unlikely(!tmp)) goto done; Py_DECREF(stepval); stepval = tmp; val |= ((int) idigit) << bits; #if CYTHON_COMPILING_IN_LIMITED_API && PY_VERSION_HEX < 0x030B0000 if (Py_SIZE(stepval) == 0) goto unpacking_done; #endif } idigit = PyLong_AsLong(stepval); if (unlikely(idigit < 0)) goto done; remaining_bits = ((int) sizeof(int) * 8) - bits - (is_unsigned ? 0 : 1); if (unlikely(idigit >= (1L << remaining_bits))) goto raise_overflow; val |= ((int) idigit) << bits; #if CYTHON_COMPILING_IN_LIMITED_API && PY_VERSION_HEX < 0x030B0000 unpacking_done: #endif if (!is_unsigned) { if (unlikely(val & (((int) 1) << (sizeof(int) * 8 - 1)))) goto raise_overflow; if (is_negative) val = ~val; } ret = 0; done: Py_XDECREF(shift); Py_XDECREF(mask); Py_XDECREF(stepval); #endif Py_DECREF(v); if (likely(!ret)) return val; } return (int) -1; } } else { int val; PyObject *tmp = __Pyx_PyNumber_IntOrLong(x); if (!tmp) return (int) -1; val = __Pyx_PyInt_As_int(tmp); Py_DECREF(tmp); return val; } raise_overflow: PyErr_SetString(PyExc_OverflowError, "value too large to convert to int"); return (int) -1; raise_neg_overflow: PyErr_SetString(PyExc_OverflowError, "can't convert negative value to int"); return (int) -1; } /* FastTypeChecks */ #if CYTHON_COMPILING_IN_CPYTHON static int __Pyx_InBases(PyTypeObject *a, PyTypeObject *b) { while (a) { a = __Pyx_PyType_GetSlot(a, tp_base, PyTypeObject*); if (a == b) return 1; } return b == &PyBaseObject_Type; } static CYTHON_INLINE int __Pyx_IsSubtype(PyTypeObject *a, PyTypeObject *b) { PyObject *mro; if (a == b) return 1; mro = a->tp_mro; if (likely(mro)) { Py_ssize_t i, n; n = PyTuple_GET_SIZE(mro); for (i = 0; i < n; i++) { if (PyTuple_GET_ITEM(mro, i) == (PyObject *)b) return 1; } return 0; } return __Pyx_InBases(a, b); } static CYTHON_INLINE int __Pyx_IsAnySubtype2(PyTypeObject *cls, PyTypeObject *a, PyTypeObject *b) { PyObject *mro; if (cls == a || cls == b) return 1; mro = cls->tp_mro; if (likely(mro)) { Py_ssize_t i, n; n = PyTuple_GET_SIZE(mro); for (i = 0; i < n; i++) { PyObject *base = PyTuple_GET_ITEM(mro, i); if (base == (PyObject *)a || base == (PyObject *)b) return 1; } return 0; } return __Pyx_InBases(cls, a) || __Pyx_InBases(cls, b); } #if PY_MAJOR_VERSION == 2 static int __Pyx_inner_PyErr_GivenExceptionMatches2(PyObject *err, PyObject* exc_type1, PyObject* exc_type2) { PyObject *exception, *value, *tb; int res; __Pyx_PyThreadState_declare __Pyx_PyThreadState_assign __Pyx_ErrFetch(&exception, &value, &tb); res = exc_type1 ? PyObject_IsSubclass(err, exc_type1) : 0; if (unlikely(res == -1)) { PyErr_WriteUnraisable(err); res = 0; } if (!res) { res = PyObject_IsSubclass(err, exc_type2); if (unlikely(res == -1)) { PyErr_WriteUnraisable(err); res = 0; } } __Pyx_ErrRestore(exception, value, tb); return res; } #else static CYTHON_INLINE int __Pyx_inner_PyErr_GivenExceptionMatches2(PyObject *err, PyObject* exc_type1, PyObject *exc_type2) { if (exc_type1) { return __Pyx_IsAnySubtype2((PyTypeObject*)err, (PyTypeObject*)exc_type1, (PyTypeObject*)exc_type2); } else { return __Pyx_IsSubtype((PyTypeObject*)err, (PyTypeObject*)exc_type2); } } #endif static int __Pyx_PyErr_GivenExceptionMatchesTuple(PyObject *exc_type, PyObject *tuple) { Py_ssize_t i, n; assert(PyExceptionClass_Check(exc_type)); n = PyTuple_GET_SIZE(tuple); #if PY_MAJOR_VERSION >= 3 for (i=0; i= 0x030B00a4 _PyErr_StackItem *exc_info = tstate->exc_info; tmp_value = exc_info->exc_value; exc_info->exc_value = *value; if (tmp_value == NULL || tmp_value == Py_None) { Py_XDECREF(tmp_value); tmp_value = NULL; tmp_type = NULL; tmp_tb = NULL; } else { tmp_type = (PyObject*) Py_TYPE(tmp_value); Py_INCREF(tmp_type); #if CYTHON_COMPILING_IN_CPYTHON tmp_tb = ((PyBaseExceptionObject*) tmp_value)->traceback; Py_XINCREF(tmp_tb); #else tmp_tb = PyException_GetTraceback(tmp_value); #endif } #elif CYTHON_USE_EXC_INFO_STACK _PyErr_StackItem *exc_info = tstate->exc_info; tmp_type = exc_info->exc_type; tmp_value = exc_info->exc_value; tmp_tb = exc_info->exc_traceback; exc_info->exc_type = *type; exc_info->exc_value = *value; exc_info->exc_traceback = *tb; #else tmp_type = tstate->exc_type; tmp_value = tstate->exc_value; tmp_tb = tstate->exc_traceback; tstate->exc_type = *type; tstate->exc_value = *value; tstate->exc_traceback = *tb; #endif *type = tmp_type; *value = tmp_value; *tb = tmp_tb; } #else static CYTHON_INLINE void __Pyx_ExceptionSwap(PyObject **type, PyObject **value, PyObject **tb) { PyObject *tmp_type, *tmp_value, *tmp_tb; PyErr_GetExcInfo(&tmp_type, &tmp_value, &tmp_tb); PyErr_SetExcInfo(*type, *value, *tb); *type = tmp_type; *value = tmp_value; *tb = tmp_tb; } #endif /* CoroutineBase */ #include #if PY_VERSION_HEX >= 0x030b00a6 #ifndef Py_BUILD_CORE #define Py_BUILD_CORE 1 #endif #include "internal/pycore_frame.h" #endif #define __Pyx_Coroutine_Undelegate(gen) Py_CLEAR((gen)->yieldfrom) static int __Pyx_PyGen__FetchStopIterationValue(PyThreadState *__pyx_tstate, PyObject **pvalue) { PyObject *et, *ev, *tb; PyObject *value = NULL; CYTHON_UNUSED_VAR(__pyx_tstate); __Pyx_ErrFetch(&et, &ev, &tb); if (!et) { Py_XDECREF(tb); Py_XDECREF(ev); Py_INCREF(Py_None); *pvalue = Py_None; return 0; } if (likely(et == PyExc_StopIteration)) { if (!ev) { Py_INCREF(Py_None); value = Py_None; } #if PY_VERSION_HEX >= 0x030300A0 else if (likely(__Pyx_IS_TYPE(ev, (PyTypeObject*)PyExc_StopIteration))) { value = ((PyStopIterationObject *)ev)->value; Py_INCREF(value); Py_DECREF(ev); } #endif else if (unlikely(PyTuple_Check(ev))) { if (PyTuple_GET_SIZE(ev) >= 1) { #if CYTHON_ASSUME_SAFE_MACROS && !CYTHON_AVOID_BORROWED_REFS value = PyTuple_GET_ITEM(ev, 0); Py_INCREF(value); #else value = PySequence_ITEM(ev, 0); #endif } else { Py_INCREF(Py_None); value = Py_None; } Py_DECREF(ev); } else if (!__Pyx_TypeCheck(ev, (PyTypeObject*)PyExc_StopIteration)) { value = ev; } if (likely(value)) { Py_XDECREF(tb); Py_DECREF(et); *pvalue = value; return 0; } } else if (!__Pyx_PyErr_GivenExceptionMatches(et, PyExc_StopIteration)) { __Pyx_ErrRestore(et, ev, tb); return -1; } PyErr_NormalizeException(&et, &ev, &tb); if (unlikely(!PyObject_TypeCheck(ev, (PyTypeObject*)PyExc_StopIteration))) { __Pyx_ErrRestore(et, ev, tb); return -1; } Py_XDECREF(tb); Py_DECREF(et); #if PY_VERSION_HEX >= 0x030300A0 value = ((PyStopIterationObject *)ev)->value; Py_INCREF(value); Py_DECREF(ev); #else { PyObject* args = __Pyx_PyObject_GetAttrStr(ev, __pyx_n_s_args); Py_DECREF(ev); if (likely(args)) { value = PySequence_GetItem(args, 0); Py_DECREF(args); } if (unlikely(!value)) { __Pyx_ErrRestore(NULL, NULL, NULL); Py_INCREF(Py_None); value = Py_None; } } #endif *pvalue = value; return 0; } static CYTHON_INLINE void __Pyx_Coroutine_ExceptionClear(__Pyx_ExcInfoStruct *exc_state) { #if PY_VERSION_HEX >= 0x030B00a4 Py_CLEAR(exc_state->exc_value); #else PyObject *t, *v, *tb; t = exc_state->exc_type; v = exc_state->exc_value; tb = exc_state->exc_traceback; exc_state->exc_type = NULL; exc_state->exc_value = NULL; exc_state->exc_traceback = NULL; Py_XDECREF(t); Py_XDECREF(v); Py_XDECREF(tb); #endif } #define __Pyx_Coroutine_AlreadyRunningError(gen) (__Pyx__Coroutine_AlreadyRunningError(gen), (PyObject*)NULL) static void __Pyx__Coroutine_AlreadyRunningError(__pyx_CoroutineObject *gen) { const char *msg; CYTHON_MAYBE_UNUSED_VAR(gen); if ((0)) { #ifdef __Pyx_Coroutine_USED } else if (__Pyx_Coroutine_Check((PyObject*)gen)) { msg = "coroutine already executing"; #endif #ifdef __Pyx_AsyncGen_USED } else if (__Pyx_AsyncGen_CheckExact((PyObject*)gen)) { msg = "async generator already executing"; #endif } else { msg = "generator already executing"; } PyErr_SetString(PyExc_ValueError, msg); } #define __Pyx_Coroutine_NotStartedError(gen) (__Pyx__Coroutine_NotStartedError(gen), (PyObject*)NULL) static void __Pyx__Coroutine_NotStartedError(PyObject *gen) { const char *msg; CYTHON_MAYBE_UNUSED_VAR(gen); if ((0)) { #ifdef __Pyx_Coroutine_USED } else if (__Pyx_Coroutine_Check(gen)) { msg = "can't send non-None value to a just-started coroutine"; #endif #ifdef __Pyx_AsyncGen_USED } else if (__Pyx_AsyncGen_CheckExact(gen)) { msg = "can't send non-None value to a just-started async generator"; #endif } else { msg = "can't send non-None value to a just-started generator"; } PyErr_SetString(PyExc_TypeError, msg); } #define __Pyx_Coroutine_AlreadyTerminatedError(gen, value, closing) (__Pyx__Coroutine_AlreadyTerminatedError(gen, value, closing), (PyObject*)NULL) static void __Pyx__Coroutine_AlreadyTerminatedError(PyObject *gen, PyObject *value, int closing) { CYTHON_MAYBE_UNUSED_VAR(gen); CYTHON_MAYBE_UNUSED_VAR(closing); #ifdef __Pyx_Coroutine_USED if (!closing && __Pyx_Coroutine_Check(gen)) { PyErr_SetString(PyExc_RuntimeError, "cannot reuse already awaited coroutine"); } else #endif if (value) { #ifdef __Pyx_AsyncGen_USED if (__Pyx_AsyncGen_CheckExact(gen)) PyErr_SetNone(__Pyx_PyExc_StopAsyncIteration); else #endif PyErr_SetNone(PyExc_StopIteration); } } static PyObject *__Pyx_Coroutine_SendEx(__pyx_CoroutineObject *self, PyObject *value, int closing) { __Pyx_PyThreadState_declare PyThreadState *tstate; __Pyx_ExcInfoStruct *exc_state; PyObject *retval; assert(!self->is_running); if (unlikely(self->resume_label == 0)) { if (unlikely(value && value != Py_None)) { return __Pyx_Coroutine_NotStartedError((PyObject*)self); } } if (unlikely(self->resume_label == -1)) { return __Pyx_Coroutine_AlreadyTerminatedError((PyObject*)self, value, closing); } #if CYTHON_FAST_THREAD_STATE __Pyx_PyThreadState_assign tstate = __pyx_tstate; #else tstate = __Pyx_PyThreadState_Current; #endif exc_state = &self->gi_exc_state; if (exc_state->exc_value) { #if CYTHON_COMPILING_IN_PYPY #else PyObject *exc_tb; #if PY_VERSION_HEX >= 0x030B00a4 && !CYTHON_COMPILING_IN_CPYTHON exc_tb = PyException_GetTraceback(exc_state->exc_value); #elif PY_VERSION_HEX >= 0x030B00a4 exc_tb = ((PyBaseExceptionObject*) exc_state->exc_value)->traceback; #else exc_tb = exc_state->exc_traceback; #endif if (exc_tb) { PyTracebackObject *tb = (PyTracebackObject *) exc_tb; PyFrameObject *f = tb->tb_frame; assert(f->f_back == NULL); #if PY_VERSION_HEX >= 0x030B00A1 f->f_back = PyThreadState_GetFrame(tstate); #else Py_XINCREF(tstate->frame); f->f_back = tstate->frame; #endif #if PY_VERSION_HEX >= 0x030B00a4 && !CYTHON_COMPILING_IN_CPYTHON Py_DECREF(exc_tb); #endif } #endif } #if CYTHON_USE_EXC_INFO_STACK exc_state->previous_item = tstate->exc_info; tstate->exc_info = exc_state; #else if (exc_state->exc_type) { __Pyx_ExceptionSwap(&exc_state->exc_type, &exc_state->exc_value, &exc_state->exc_traceback); } else { __Pyx_Coroutine_ExceptionClear(exc_state); __Pyx_ExceptionSave(&exc_state->exc_type, &exc_state->exc_value, &exc_state->exc_traceback); } #endif self->is_running = 1; retval = self->body(self, tstate, value); self->is_running = 0; #if CYTHON_USE_EXC_INFO_STACK exc_state = &self->gi_exc_state; tstate->exc_info = exc_state->previous_item; exc_state->previous_item = NULL; __Pyx_Coroutine_ResetFrameBackpointer(exc_state); #endif return retval; } static CYTHON_INLINE void __Pyx_Coroutine_ResetFrameBackpointer(__Pyx_ExcInfoStruct *exc_state) { #if CYTHON_COMPILING_IN_PYPY CYTHON_UNUSED_VAR(exc_state); #else PyObject *exc_tb; #if PY_VERSION_HEX >= 0x030B00a4 if (!exc_state->exc_value) return; exc_tb = PyException_GetTraceback(exc_state->exc_value); #else exc_tb = exc_state->exc_traceback; #endif if (likely(exc_tb)) { PyTracebackObject *tb = (PyTracebackObject *) exc_tb; PyFrameObject *f = tb->tb_frame; Py_CLEAR(f->f_back); #if PY_VERSION_HEX >= 0x030B00a4 Py_DECREF(exc_tb); #endif } #endif } static CYTHON_INLINE PyObject *__Pyx_Coroutine_MethodReturn(PyObject* gen, PyObject *retval) { CYTHON_MAYBE_UNUSED_VAR(gen); if (unlikely(!retval)) { __Pyx_PyThreadState_declare __Pyx_PyThreadState_assign if (!__Pyx_PyErr_Occurred()) { PyObject *exc = PyExc_StopIteration; #ifdef __Pyx_AsyncGen_USED if (__Pyx_AsyncGen_CheckExact(gen)) exc = __Pyx_PyExc_StopAsyncIteration; #endif __Pyx_PyErr_SetNone(exc); } } return retval; } #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x03030000 && (defined(__linux__) || PY_VERSION_HEX >= 0x030600B3) static CYTHON_INLINE PyObject *__Pyx_PyGen_Send(PyGenObject *gen, PyObject *arg) { #if PY_VERSION_HEX <= 0x030A00A1 return _PyGen_Send(gen, arg); #else PyObject *result; if (PyIter_Send((PyObject*)gen, arg ? arg : Py_None, &result) == PYGEN_RETURN) { if (PyAsyncGen_CheckExact(gen)) { assert(result == Py_None); PyErr_SetNone(PyExc_StopAsyncIteration); } else if (result == Py_None) { PyErr_SetNone(PyExc_StopIteration); } else { #if PY_VERSION_HEX < 0x030d00A1 _PyGen_SetStopIterationValue(result); #else if (!PyTuple_Check(result) && !PyExceptionInstance_Check(result)) { PyErr_SetObject(PyExc_StopIteration, result); } else { PyObject *exc = __Pyx_PyObject_CallOneArg(PyExc_StopIteration, result); if (likely(exc != NULL)) { PyErr_SetObject(PyExc_StopIteration, exc); Py_DECREF(exc); } } #endif } Py_DECREF(result); result = NULL; } return result; #endif } #endif static CYTHON_INLINE PyObject *__Pyx_Coroutine_FinishDelegation(__pyx_CoroutineObject *gen) { PyObject *ret; PyObject *val = NULL; __Pyx_Coroutine_Undelegate(gen); __Pyx_PyGen__FetchStopIterationValue(__Pyx_PyThreadState_Current, &val); ret = __Pyx_Coroutine_SendEx(gen, val, 0); Py_XDECREF(val); return ret; } static PyObject *__Pyx_Coroutine_Send(PyObject *self, PyObject *value) { PyObject *retval; __pyx_CoroutineObject *gen = (__pyx_CoroutineObject*) self; PyObject *yf = gen->yieldfrom; if (unlikely(gen->is_running)) return __Pyx_Coroutine_AlreadyRunningError(gen); if (yf) { PyObject *ret; gen->is_running = 1; #ifdef __Pyx_Generator_USED if (__Pyx_Generator_CheckExact(yf)) { ret = __Pyx_Coroutine_Send(yf, value); } else #endif #ifdef __Pyx_Coroutine_USED if (__Pyx_Coroutine_Check(yf)) { ret = __Pyx_Coroutine_Send(yf, value); } else #endif #ifdef __Pyx_AsyncGen_USED if (__pyx_PyAsyncGenASend_CheckExact(yf)) { ret = __Pyx_async_gen_asend_send(yf, value); } else #endif #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x03030000 && (defined(__linux__) || PY_VERSION_HEX >= 0x030600B3) if (PyGen_CheckExact(yf)) { ret = __Pyx_PyGen_Send((PyGenObject*)yf, value == Py_None ? NULL : value); } else #endif #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x03050000 && defined(PyCoro_CheckExact) && (defined(__linux__) || PY_VERSION_HEX >= 0x030600B3) if (PyCoro_CheckExact(yf)) { ret = __Pyx_PyGen_Send((PyGenObject*)yf, value == Py_None ? NULL : value); } else #endif { if (value == Py_None) ret = __Pyx_PyObject_GetIterNextFunc(yf)(yf); else ret = __Pyx_PyObject_CallMethod1(yf, __pyx_n_s_send, value); } gen->is_running = 0; if (likely(ret)) { return ret; } retval = __Pyx_Coroutine_FinishDelegation(gen); } else { retval = __Pyx_Coroutine_SendEx(gen, value, 0); } return __Pyx_Coroutine_MethodReturn(self, retval); } static int __Pyx_Coroutine_CloseIter(__pyx_CoroutineObject *gen, PyObject *yf) { PyObject *retval = NULL; int err = 0; #ifdef __Pyx_Generator_USED if (__Pyx_Generator_CheckExact(yf)) { retval = __Pyx_Coroutine_Close(yf); if (!retval) return -1; } else #endif #ifdef __Pyx_Coroutine_USED if (__Pyx_Coroutine_Check(yf)) { retval = __Pyx_Coroutine_Close(yf); if (!retval) return -1; } else if (__Pyx_CoroutineAwait_CheckExact(yf)) { retval = __Pyx_CoroutineAwait_Close((__pyx_CoroutineAwaitObject*)yf, NULL); if (!retval) return -1; } else #endif #ifdef __Pyx_AsyncGen_USED if (__pyx_PyAsyncGenASend_CheckExact(yf)) { retval = __Pyx_async_gen_asend_close(yf, NULL); } else if (__pyx_PyAsyncGenAThrow_CheckExact(yf)) { retval = __Pyx_async_gen_athrow_close(yf, NULL); } else #endif { PyObject *meth; gen->is_running = 1; meth = __Pyx_PyObject_GetAttrStrNoError(yf, __pyx_n_s_close); if (unlikely(!meth)) { if (unlikely(PyErr_Occurred())) { PyErr_WriteUnraisable(yf); } } else { retval = __Pyx_PyObject_CallNoArg(meth); Py_DECREF(meth); if (unlikely(!retval)) err = -1; } gen->is_running = 0; } Py_XDECREF(retval); return err; } static PyObject *__Pyx_Generator_Next(PyObject *self) { __pyx_CoroutineObject *gen = (__pyx_CoroutineObject*) self; PyObject *yf = gen->yieldfrom; if (unlikely(gen->is_running)) return __Pyx_Coroutine_AlreadyRunningError(gen); if (yf) { PyObject *ret; gen->is_running = 1; #ifdef __Pyx_Generator_USED if (__Pyx_Generator_CheckExact(yf)) { ret = __Pyx_Generator_Next(yf); } else #endif #if CYTHON_COMPILING_IN_CPYTHON && PY_VERSION_HEX >= 0x03030000 && (defined(__linux__) || PY_VERSION_HEX >= 0x030600B3) if (PyGen_CheckExact(yf)) { ret = __Pyx_PyGen_Send((PyGenObject*)yf, NULL); } else #endif #ifdef __Pyx_Coroutine_USED if (__Pyx_Coroutine_Check(yf)) { ret = __Pyx_Coroutine_Send(yf, Py_None); } else #endif ret = __Pyx_PyObject_GetIterNextFunc(yf)(yf); gen->is_running = 0; if (likely(ret)) { return ret; } return __Pyx_Coroutine_FinishDelegation(gen); } return __Pyx_Coroutine_SendEx(gen, Py_None, 0); } static PyObject *__Pyx_Coroutine_Close_Method(PyObject *self, PyObject *arg) { CYTHON_UNUSED_VAR(arg); return __Pyx_Coroutine_Close(self); } static PyObject *__Pyx_Coroutine_Close(PyObject *self) { __pyx_CoroutineObject *gen = (__pyx_CoroutineObject *) self; PyObject *retval, *raised_exception; PyObject *yf = gen->yieldfrom; int err = 0; if (unlikely(gen->is_running)) return __Pyx_Coroutine_AlreadyRunningError(gen); if (yf) { Py_INCREF(yf); err = __Pyx_Coroutine_CloseIter(gen, yf); __Pyx_Coroutine_Undelegate(gen); Py_DECREF(yf); } if (err == 0) PyErr_SetNone(PyExc_GeneratorExit); retval = __Pyx_Coroutine_SendEx(gen, NULL, 1); if (unlikely(retval)) { const char *msg; Py_DECREF(retval); if ((0)) { #ifdef __Pyx_Coroutine_USED } else if (__Pyx_Coroutine_Check(self)) { msg = "coroutine ignored GeneratorExit"; #endif #ifdef __Pyx_AsyncGen_USED } else if (__Pyx_AsyncGen_CheckExact(self)) { #if PY_VERSION_HEX < 0x03060000 msg = "async generator ignored GeneratorExit - might require Python 3.6+ finalisation (PEP 525)"; #else msg = "async generator ignored GeneratorExit"; #endif #endif } else { msg = "generator ignored GeneratorExit"; } PyErr_SetString(PyExc_RuntimeError, msg); return NULL; } raised_exception = PyErr_Occurred(); if (likely(!raised_exception || __Pyx_PyErr_GivenExceptionMatches2(raised_exception, PyExc_GeneratorExit, PyExc_StopIteration))) { if (raised_exception) PyErr_Clear(); Py_INCREF(Py_None); return Py_None; } return NULL; } static PyObject *__Pyx__Coroutine_Throw(PyObject *self, PyObject *typ, PyObject *val, PyObject *tb, PyObject *args, int close_on_genexit) { __pyx_CoroutineObject *gen = (__pyx_CoroutineObject *) self; PyObject *yf = gen->yieldfrom; if (unlikely(gen->is_running)) return __Pyx_Coroutine_AlreadyRunningError(gen); if (yf) { PyObject *ret; Py_INCREF(yf); if (__Pyx_PyErr_GivenExceptionMatches(typ, PyExc_GeneratorExit) && close_on_genexit) { int err = __Pyx_Coroutine_CloseIter(gen, yf); Py_DECREF(yf); __Pyx_Coroutine_Undelegate(gen); if (err < 0) return __Pyx_Coroutine_MethodReturn(self, __Pyx_Coroutine_SendEx(gen, NULL, 0)); goto throw_here; } gen->is_running = 1; if (0 #ifdef __Pyx_Generator_USED || __Pyx_Generator_CheckExact(yf) #endif #ifdef __Pyx_Coroutine_USED || __Pyx_Coroutine_Check(yf) #endif ) { ret = __Pyx__Coroutine_Throw(yf, typ, val, tb, args, close_on_genexit); #ifdef __Pyx_Coroutine_USED } else if (__Pyx_CoroutineAwait_CheckExact(yf)) { ret = __Pyx__Coroutine_Throw(((__pyx_CoroutineAwaitObject*)yf)->coroutine, typ, val, tb, args, close_on_genexit); #endif } else { PyObject *meth = __Pyx_PyObject_GetAttrStrNoError(yf, __pyx_n_s_throw); if (unlikely(!meth)) { Py_DECREF(yf); if (unlikely(PyErr_Occurred())) { gen->is_running = 0; return NULL; } __Pyx_Coroutine_Undelegate(gen); gen->is_running = 0; goto throw_here; } if (likely(args)) { ret = __Pyx_PyObject_Call(meth, args, NULL); } else { PyObject *cargs[4] = {NULL, typ, val, tb}; ret = __Pyx_PyObject_FastCall(meth, cargs+1, 3 | __Pyx_PY_VECTORCALL_ARGUMENTS_OFFSET); } Py_DECREF(meth); } gen->is_running = 0; Py_DECREF(yf); if (!ret) { ret = __Pyx_Coroutine_FinishDelegation(gen); } return __Pyx_Coroutine_MethodReturn(self, ret); } throw_here: __Pyx_Raise(typ, val, tb, NULL); return __Pyx_Coroutine_MethodReturn(self, __Pyx_Coroutine_SendEx(gen, NULL, 0)); } static PyObject *__Pyx_Coroutine_Throw(PyObject *self, PyObject *args) { PyObject *typ; PyObject *val = NULL; PyObject *tb = NULL; if (unlikely(!PyArg_UnpackTuple(args, (char *)"throw", 1, 3, &typ, &val, &tb))) return NULL; return __Pyx__Coroutine_Throw(self, typ, val, tb, args, 1); } static CYTHON_INLINE int __Pyx_Coroutine_traverse_excstate(__Pyx_ExcInfoStruct *exc_state, visitproc visit, void *arg) { #if PY_VERSION_HEX >= 0x030B00a4 Py_VISIT(exc_state->exc_value); #else Py_VISIT(exc_state->exc_type); Py_VISIT(exc_state->exc_value); Py_VISIT(exc_state->exc_traceback); #endif return 0; } static int __Pyx_Coroutine_traverse(__pyx_CoroutineObject *gen, visitproc visit, void *arg) { Py_VISIT(gen->closure); Py_VISIT(gen->classobj); Py_VISIT(gen->yieldfrom); return __Pyx_Coroutine_traverse_excstate(&gen->gi_exc_state, visit, arg); } static int __Pyx_Coroutine_clear(PyObject *self) { __pyx_CoroutineObject *gen = (__pyx_CoroutineObject *) self; Py_CLEAR(gen->closure); Py_CLEAR(gen->classobj); Py_CLEAR(gen->yieldfrom); __Pyx_Coroutine_ExceptionClear(&gen->gi_exc_state); #ifdef __Pyx_AsyncGen_USED if (__Pyx_AsyncGen_CheckExact(self)) { Py_CLEAR(((__pyx_PyAsyncGenObject*)gen)->ag_finalizer); } #endif Py_CLEAR(gen->gi_code); Py_CLEAR(gen->gi_frame); Py_CLEAR(gen->gi_name); Py_CLEAR(gen->gi_qualname); Py_CLEAR(gen->gi_modulename); return 0; } static void __Pyx_Coroutine_dealloc(PyObject *self) { __pyx_CoroutineObject *gen = (__pyx_CoroutineObject *) self; PyObject_GC_UnTrack(gen); if (gen->gi_weakreflist != NULL) PyObject_ClearWeakRefs(self); if (gen->resume_label >= 0) { PyObject_GC_Track(self); #if PY_VERSION_HEX >= 0x030400a1 && CYTHON_USE_TP_FINALIZE if (unlikely(PyObject_CallFinalizerFromDealloc(self))) #else Py_TYPE(gen)->tp_del(self); if (unlikely(Py_REFCNT(self) > 0)) #endif { return; } PyObject_GC_UnTrack(self); } #ifdef __Pyx_AsyncGen_USED if (__Pyx_AsyncGen_CheckExact(self)) { /* We have to handle this case for asynchronous generators right here, because this code has to be between UNTRACK and GC_Del. */ Py_CLEAR(((__pyx_PyAsyncGenObject*)self)->ag_finalizer); } #endif __Pyx_Coroutine_clear(self); __Pyx_PyHeapTypeObject_GC_Del(gen); } static void __Pyx_Coroutine_del(PyObject *self) { PyObject *error_type, *error_value, *error_traceback; __pyx_CoroutineObject *gen = (__pyx_CoroutineObject *) self; __Pyx_PyThreadState_declare if (gen->resume_label < 0) { return; } #if !CYTHON_USE_TP_FINALIZE assert(self->ob_refcnt == 0); __Pyx_SET_REFCNT(self, 1); #endif __Pyx_PyThreadState_assign __Pyx_ErrFetch(&error_type, &error_value, &error_traceback); #ifdef __Pyx_AsyncGen_USED if (__Pyx_AsyncGen_CheckExact(self)) { __pyx_PyAsyncGenObject *agen = (__pyx_PyAsyncGenObject*)self; PyObject *finalizer = agen->ag_finalizer; if (finalizer && !agen->ag_closed) { PyObject *res = __Pyx_PyObject_CallOneArg(finalizer, self); if (unlikely(!res)) { PyErr_WriteUnraisable(self); } else { Py_DECREF(res); } __Pyx_ErrRestore(error_type, error_value, error_traceback); return; } } #endif if (unlikely(gen->resume_label == 0 && !error_value)) { #ifdef __Pyx_Coroutine_USED #ifdef __Pyx_Generator_USED if (!__Pyx_Generator_CheckExact(self)) #endif { PyObject_GC_UnTrack(self); #if PY_MAJOR_VERSION >= 3 || defined(PyErr_WarnFormat) if (unlikely(PyErr_WarnFormat(PyExc_RuntimeWarning, 1, "coroutine '%.50S' was never awaited", gen->gi_qualname) < 0)) PyErr_WriteUnraisable(self); #else {PyObject *msg; char *cmsg; #if CYTHON_COMPILING_IN_PYPY msg = NULL; cmsg = (char*) "coroutine was never awaited"; #else char *cname; PyObject *qualname; qualname = gen->gi_qualname; cname = PyString_AS_STRING(qualname); msg = PyString_FromFormat("coroutine '%.50s' was never awaited", cname); if (unlikely(!msg)) { PyErr_Clear(); cmsg = (char*) "coroutine was never awaited"; } else { cmsg = PyString_AS_STRING(msg); } #endif if (unlikely(PyErr_WarnEx(PyExc_RuntimeWarning, cmsg, 1) < 0)) PyErr_WriteUnraisable(self); Py_XDECREF(msg);} #endif PyObject_GC_Track(self); } #endif } else { PyObject *res = __Pyx_Coroutine_Close(self); if (unlikely(!res)) { if (PyErr_Occurred()) PyErr_WriteUnraisable(self); } else { Py_DECREF(res); } } __Pyx_ErrRestore(error_type, error_value, error_traceback); #if !CYTHON_USE_TP_FINALIZE assert(Py_REFCNT(self) > 0); if (likely(--self->ob_refcnt == 0)) { return; } { Py_ssize_t refcnt = Py_REFCNT(self); _Py_NewReference(self); __Pyx_SET_REFCNT(self, refcnt); } #if CYTHON_COMPILING_IN_CPYTHON assert(PyType_IS_GC(Py_TYPE(self)) && _Py_AS_GC(self)->gc.gc_refs != _PyGC_REFS_UNTRACKED); _Py_DEC_REFTOTAL; #endif #ifdef COUNT_ALLOCS --Py_TYPE(self)->tp_frees; --Py_TYPE(self)->tp_allocs; #endif #endif } static PyObject * __Pyx_Coroutine_get_name(__pyx_CoroutineObject *self, void *context) { PyObject *name = self->gi_name; CYTHON_UNUSED_VAR(context); if (unlikely(!name)) name = Py_None; Py_INCREF(name); return name; } static int __Pyx_Coroutine_set_name(__pyx_CoroutineObject *self, PyObject *value, void *context) { CYTHON_UNUSED_VAR(context); #if PY_MAJOR_VERSION >= 3 if (unlikely(value == NULL || !PyUnicode_Check(value))) #else if (unlikely(value == NULL || !PyString_Check(value))) #endif { PyErr_SetString(PyExc_TypeError, "__name__ must be set to a string object"); return -1; } Py_INCREF(value); __Pyx_Py_XDECREF_SET(self->gi_name, value); return 0; } static PyObject * __Pyx_Coroutine_get_qualname(__pyx_CoroutineObject *self, void *context) { PyObject *name = self->gi_qualname; CYTHON_UNUSED_VAR(context); if (unlikely(!name)) name = Py_None; Py_INCREF(name); return name; } static int __Pyx_Coroutine_set_qualname(__pyx_CoroutineObject *self, PyObject *value, void *context) { CYTHON_UNUSED_VAR(context); #if PY_MAJOR_VERSION >= 3 if (unlikely(value == NULL || !PyUnicode_Check(value))) #else if (unlikely(value == NULL || !PyString_Check(value))) #endif { PyErr_SetString(PyExc_TypeError, "__qualname__ must be set to a string object"); return -1; } Py_INCREF(value); __Pyx_Py_XDECREF_SET(self->gi_qualname, value); return 0; } static PyObject * __Pyx_Coroutine_get_frame(__pyx_CoroutineObject *self, void *context) { PyObject *frame = self->gi_frame; CYTHON_UNUSED_VAR(context); if (!frame) { if (unlikely(!self->gi_code)) { Py_RETURN_NONE; } frame = (PyObject *) PyFrame_New( PyThreadState_Get(), /*PyThreadState *tstate,*/ (PyCodeObject*) self->gi_code, /*PyCodeObject *code,*/ __pyx_d, /*PyObject *globals,*/ 0 /*PyObject *locals*/ ); if (unlikely(!frame)) return NULL; self->gi_frame = frame; } Py_INCREF(frame); return frame; } static __pyx_CoroutineObject *__Pyx__Coroutine_New( PyTypeObject* type, __pyx_coroutine_body_t body, PyObject *code, PyObject *closure, PyObject *name, PyObject *qualname, PyObject *module_name) { __pyx_CoroutineObject *gen = PyObject_GC_New(__pyx_CoroutineObject, type); if (unlikely(!gen)) return NULL; return __Pyx__Coroutine_NewInit(gen, body, code, closure, name, qualname, module_name); } static __pyx_CoroutineObject *__Pyx__Coroutine_NewInit( __pyx_CoroutineObject *gen, __pyx_coroutine_body_t body, PyObject *code, PyObject *closure, PyObject *name, PyObject *qualname, PyObject *module_name) { gen->body = body; gen->closure = closure; Py_XINCREF(closure); gen->is_running = 0; gen->resume_label = 0; gen->classobj = NULL; gen->yieldfrom = NULL; #if PY_VERSION_HEX >= 0x030B00a4 gen->gi_exc_state.exc_value = NULL; #else gen->gi_exc_state.exc_type = NULL; gen->gi_exc_state.exc_value = NULL; gen->gi_exc_state.exc_traceback = NULL; #endif #if CYTHON_USE_EXC_INFO_STACK gen->gi_exc_state.previous_item = NULL; #endif gen->gi_weakreflist = NULL; Py_XINCREF(qualname); gen->gi_qualname = qualname; Py_XINCREF(name); gen->gi_name = name; Py_XINCREF(module_name); gen->gi_modulename = module_name; Py_XINCREF(code); gen->gi_code = code; gen->gi_frame = NULL; PyObject_GC_Track(gen); return gen; } /* PatchModuleWithCoroutine */ static PyObject* __Pyx_Coroutine_patch_module(PyObject* module, const char* py_code) { #if defined(__Pyx_Generator_USED) || defined(__Pyx_Coroutine_USED) int result; PyObject *globals, *result_obj; globals = PyDict_New(); if (unlikely(!globals)) goto ignore; result = PyDict_SetItemString(globals, "_cython_coroutine_type", #ifdef __Pyx_Coroutine_USED (PyObject*)__pyx_CoroutineType); #else Py_None); #endif if (unlikely(result < 0)) goto ignore; result = PyDict_SetItemString(globals, "_cython_generator_type", #ifdef __Pyx_Generator_USED (PyObject*)__pyx_GeneratorType); #else Py_None); #endif if (unlikely(result < 0)) goto ignore; if (unlikely(PyDict_SetItemString(globals, "_module", module) < 0)) goto ignore; if (unlikely(PyDict_SetItemString(globals, "__builtins__", __pyx_b) < 0)) goto ignore; result_obj = PyRun_String(py_code, Py_file_input, globals, globals); if (unlikely(!result_obj)) goto ignore; Py_DECREF(result_obj); Py_DECREF(globals); return module; ignore: Py_XDECREF(globals); PyErr_WriteUnraisable(module); if (unlikely(PyErr_WarnEx(PyExc_RuntimeWarning, "Cython module failed to patch module with custom type", 1) < 0)) { Py_DECREF(module); module = NULL; } #else py_code++; #endif return module; } /* PatchGeneratorABC */ #ifndef CYTHON_REGISTER_ABCS #define CYTHON_REGISTER_ABCS 1 #endif #if defined(__Pyx_Generator_USED) || defined(__Pyx_Coroutine_USED) static PyObject* __Pyx_patch_abc_module(PyObject *module); static PyObject* __Pyx_patch_abc_module(PyObject *module) { module = __Pyx_Coroutine_patch_module( module, "" "if _cython_generator_type is not None:\n" " try: Generator = _module.Generator\n" " except AttributeError: pass\n" " else: Generator.register(_cython_generator_type)\n" "if _cython_coroutine_type is not None:\n" " try: Coroutine = _module.Coroutine\n" " except AttributeError: pass\n" " else: Coroutine.register(_cython_coroutine_type)\n" ); return module; } #endif static int __Pyx_patch_abc(void) { #if defined(__Pyx_Generator_USED) || defined(__Pyx_Coroutine_USED) static int abc_patched = 0; if (CYTHON_REGISTER_ABCS && !abc_patched) { PyObject *module; module = PyImport_ImportModule((PY_MAJOR_VERSION >= 3) ? "collections.abc" : "collections"); if (unlikely(!module)) { PyErr_WriteUnraisable(NULL); if (unlikely(PyErr_WarnEx(PyExc_RuntimeWarning, ((PY_MAJOR_VERSION >= 3) ? "Cython module failed to register with collections.abc module" : "Cython module failed to register with collections module"), 1) < 0)) { return -1; } } else { module = __Pyx_patch_abc_module(module); abc_patched = 1; if (unlikely(!module)) return -1; Py_DECREF(module); } module = PyImport_ImportModule("backports_abc"); if (module) { module = __Pyx_patch_abc_module(module); Py_XDECREF(module); } if (!module) { PyErr_Clear(); } } #else if ((0)) __Pyx_Coroutine_patch_module(NULL, NULL); #endif return 0; } /* Generator */ static PyMethodDef __pyx_Generator_methods[] = { {"send", (PyCFunction) __Pyx_Coroutine_Send, METH_O, (char*) PyDoc_STR("send(arg) -> send 'arg' into generator,\nreturn next yielded value or raise StopIteration.")}, {"throw", (PyCFunction) __Pyx_Coroutine_Throw, METH_VARARGS, (char*) PyDoc_STR("throw(typ[,val[,tb]]) -> raise exception in generator,\nreturn next yielded value or raise StopIteration.")}, {"close", (PyCFunction) __Pyx_Coroutine_Close_Method, METH_NOARGS, (char*) PyDoc_STR("close() -> raise GeneratorExit inside generator.")}, {0, 0, 0, 0} }; static PyMemberDef __pyx_Generator_memberlist[] = { {(char *) "gi_running", T_BOOL, offsetof(__pyx_CoroutineObject, is_running), READONLY, NULL}, {(char*) "gi_yieldfrom", T_OBJECT, offsetof(__pyx_CoroutineObject, yieldfrom), READONLY, (char*) PyDoc_STR("object being iterated by 'yield from', or None")}, {(char*) "gi_code", T_OBJECT, offsetof(__pyx_CoroutineObject, gi_code), READONLY, NULL}, {(char *) "__module__", T_OBJECT, offsetof(__pyx_CoroutineObject, gi_modulename), 0, 0}, #if CYTHON_USE_TYPE_SPECS {(char *) "__weaklistoffset__", T_PYSSIZET, offsetof(__pyx_CoroutineObject, gi_weakreflist), READONLY, 0}, #endif {0, 0, 0, 0, 0} }; static PyGetSetDef __pyx_Generator_getsets[] = { {(char *) "__name__", (getter)__Pyx_Coroutine_get_name, (setter)__Pyx_Coroutine_set_name, (char*) PyDoc_STR("name of the generator"), 0}, {(char *) "__qualname__", (getter)__Pyx_Coroutine_get_qualname, (setter)__Pyx_Coroutine_set_qualname, (char*) PyDoc_STR("qualified name of the generator"), 0}, {(char *) "gi_frame", (getter)__Pyx_Coroutine_get_frame, NULL, (char*) PyDoc_STR("Frame of the generator"), 0}, {0, 0, 0, 0, 0} }; #if CYTHON_USE_TYPE_SPECS static PyType_Slot __pyx_GeneratorType_slots[] = { {Py_tp_dealloc, (void *)__Pyx_Coroutine_dealloc}, {Py_tp_traverse, (void *)__Pyx_Coroutine_traverse}, {Py_tp_iter, (void *)PyObject_SelfIter}, {Py_tp_iternext, (void *)__Pyx_Generator_Next}, {Py_tp_methods, (void *)__pyx_Generator_methods}, {Py_tp_members, (void *)__pyx_Generator_memberlist}, {Py_tp_getset, (void *)__pyx_Generator_getsets}, {Py_tp_getattro, (void *) __Pyx_PyObject_GenericGetAttrNoDict}, #if CYTHON_USE_TP_FINALIZE {Py_tp_finalize, (void *)__Pyx_Coroutine_del}, #endif {0, 0}, }; static PyType_Spec __pyx_GeneratorType_spec = { __PYX_TYPE_MODULE_PREFIX "generator", sizeof(__pyx_CoroutineObject), 0, Py_TPFLAGS_DEFAULT | Py_TPFLAGS_HAVE_GC | Py_TPFLAGS_HAVE_FINALIZE, __pyx_GeneratorType_slots }; #else static PyTypeObject __pyx_GeneratorType_type = { PyVarObject_HEAD_INIT(0, 0) __PYX_TYPE_MODULE_PREFIX "generator", sizeof(__pyx_CoroutineObject), 0, (destructor) __Pyx_Coroutine_dealloc, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, Py_TPFLAGS_DEFAULT | Py_TPFLAGS_HAVE_GC | Py_TPFLAGS_HAVE_FINALIZE, 0, (traverseproc) __Pyx_Coroutine_traverse, 0, 0, offsetof(__pyx_CoroutineObject, gi_weakreflist), 0, (iternextfunc) __Pyx_Generator_Next, __pyx_Generator_methods, __pyx_Generator_memberlist, __pyx_Generator_getsets, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, #if CYTHON_USE_TP_FINALIZE 0, #else __Pyx_Coroutine_del, #endif 0, #if CYTHON_USE_TP_FINALIZE __Pyx_Coroutine_del, #elif PY_VERSION_HEX >= 0x030400a1 0, #endif #if PY_VERSION_HEX >= 0x030800b1 && (!CYTHON_COMPILING_IN_PYPY || PYPY_VERSION_NUM >= 0x07030800) 0, #endif #if __PYX_NEED_TP_PRINT_SLOT 0, #endif #if PY_VERSION_HEX >= 0x030C0000 0, #endif #if CYTHON_COMPILING_IN_PYPY && PY_VERSION_HEX >= 0x03090000 && PY_VERSION_HEX < 0x030a0000 0, #endif }; #endif static int __pyx_Generator_init(PyObject *module) { #if CYTHON_USE_TYPE_SPECS __pyx_GeneratorType = __Pyx_FetchCommonTypeFromSpec(module, &__pyx_GeneratorType_spec, NULL); #else CYTHON_UNUSED_VAR(module); __pyx_GeneratorType_type.tp_getattro = __Pyx_PyObject_GenericGetAttrNoDict; __pyx_GeneratorType_type.tp_iter = PyObject_SelfIter; __pyx_GeneratorType = __Pyx_FetchCommonType(&__pyx_GeneratorType_type); #endif if (unlikely(!__pyx_GeneratorType)) { return -1; } return 0; } /* CheckBinaryVersion */ static unsigned long __Pyx_get_runtime_version(void) { #if __PYX_LIMITED_VERSION_HEX >= 0x030B00A4 return Py_Version & ~0xFFUL; #else const char* rt_version = Py_GetVersion(); unsigned long version = 0; unsigned long factor = 0x01000000UL; unsigned int digit = 0; int i = 0; while (factor) { while ('0' <= rt_version[i] && rt_version[i] <= '9') { digit = digit * 10 + (unsigned int) (rt_version[i] - '0'); ++i; } version += factor * digit; if (rt_version[i] != '.') break; digit = 0; factor >>= 8; ++i; } return version; #endif } static int __Pyx_check_binary_version(unsigned long ct_version, unsigned long rt_version, int allow_newer) { const unsigned long MAJOR_MINOR = 0xFFFF0000UL; if ((rt_version & MAJOR_MINOR) == (ct_version & MAJOR_MINOR)) return 0; if (likely(allow_newer && (rt_version & MAJOR_MINOR) > (ct_version & MAJOR_MINOR))) return 1; { char message[200]; PyOS_snprintf(message, sizeof(message), "compile time Python version %d.%d " "of module '%.100s' " "%s " "runtime version %d.%d", (int) (ct_version >> 24), (int) ((ct_version >> 16) & 0xFF), __Pyx_MODULE_NAME, (allow_newer) ? "was newer than" : "does not match", (int) (rt_version >> 24), (int) ((rt_version >> 16) & 0xFF) ); return PyErr_WarnEx(NULL, message, 1); } } /* InitStrings */ #if PY_MAJOR_VERSION >= 3 static int __Pyx_InitString(__Pyx_StringTabEntry t, PyObject **str) { if (t.is_unicode | t.is_str) { if (t.intern) { *str = PyUnicode_InternFromString(t.s); } else if (t.encoding) { *str = PyUnicode_Decode(t.s, t.n - 1, t.encoding, NULL); } else { *str = PyUnicode_FromStringAndSize(t.s, t.n - 1); } } else { *str = PyBytes_FromStringAndSize(t.s, t.n - 1); } if (!*str) return -1; if (PyObject_Hash(*str) == -1) return -1; return 0; } #endif static int __Pyx_InitStrings(__Pyx_StringTabEntry *t) { while (t->p) { #if PY_MAJOR_VERSION >= 3 __Pyx_InitString(*t, t->p); #else if (t->is_unicode) { *t->p = PyUnicode_DecodeUTF8(t->s, t->n - 1, NULL); } else if (t->intern) { *t->p = PyString_InternFromString(t->s); } else { *t->p = PyString_FromStringAndSize(t->s, t->n - 1); } if (!*t->p) return -1; if (PyObject_Hash(*t->p) == -1) return -1; #endif ++t; } return 0; } #include static CYTHON_INLINE Py_ssize_t __Pyx_ssize_strlen(const char *s) { size_t len = strlen(s); if (unlikely(len > (size_t) PY_SSIZE_T_MAX)) { PyErr_SetString(PyExc_OverflowError, "byte string is too long"); return -1; } return (Py_ssize_t) len; } static CYTHON_INLINE PyObject* __Pyx_PyUnicode_FromString(const char* c_str) { Py_ssize_t len = __Pyx_ssize_strlen(c_str); if (unlikely(len < 0)) return NULL; return __Pyx_PyUnicode_FromStringAndSize(c_str, len); } static CYTHON_INLINE PyObject* __Pyx_PyByteArray_FromString(const char* c_str) { Py_ssize_t len = __Pyx_ssize_strlen(c_str); if (unlikely(len < 0)) return NULL; return PyByteArray_FromStringAndSize(c_str, len); } static CYTHON_INLINE const char* __Pyx_PyObject_AsString(PyObject* o) { Py_ssize_t ignore; return __Pyx_PyObject_AsStringAndSize(o, &ignore); } #if __PYX_DEFAULT_STRING_ENCODING_IS_ASCII || __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT #if !CYTHON_PEP393_ENABLED static const char* __Pyx_PyUnicode_AsStringAndSize(PyObject* o, Py_ssize_t *length) { char* defenc_c; PyObject* defenc = _PyUnicode_AsDefaultEncodedString(o, NULL); if (!defenc) return NULL; defenc_c = PyBytes_AS_STRING(defenc); #if __PYX_DEFAULT_STRING_ENCODING_IS_ASCII { char* end = defenc_c + PyBytes_GET_SIZE(defenc); char* c; for (c = defenc_c; c < end; c++) { if ((unsigned char) (*c) >= 128) { PyUnicode_AsASCIIString(o); return NULL; } } } #endif *length = PyBytes_GET_SIZE(defenc); return defenc_c; } #else static CYTHON_INLINE const char* __Pyx_PyUnicode_AsStringAndSize(PyObject* o, Py_ssize_t *length) { if (unlikely(__Pyx_PyUnicode_READY(o) == -1)) return NULL; #if __PYX_DEFAULT_STRING_ENCODING_IS_ASCII if (likely(PyUnicode_IS_ASCII(o))) { *length = PyUnicode_GET_LENGTH(o); return PyUnicode_AsUTF8(o); } else { PyUnicode_AsASCIIString(o); return NULL; } #else return PyUnicode_AsUTF8AndSize(o, length); #endif } #endif #endif static CYTHON_INLINE const char* __Pyx_PyObject_AsStringAndSize(PyObject* o, Py_ssize_t *length) { #if __PYX_DEFAULT_STRING_ENCODING_IS_ASCII || __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT if ( #if PY_MAJOR_VERSION < 3 && __PYX_DEFAULT_STRING_ENCODING_IS_ASCII __Pyx_sys_getdefaultencoding_not_ascii && #endif PyUnicode_Check(o)) { return __Pyx_PyUnicode_AsStringAndSize(o, length); } else #endif #if (!CYTHON_COMPILING_IN_PYPY && !CYTHON_COMPILING_IN_LIMITED_API) || (defined(PyByteArray_AS_STRING) && defined(PyByteArray_GET_SIZE)) if (PyByteArray_Check(o)) { *length = PyByteArray_GET_SIZE(o); return PyByteArray_AS_STRING(o); } else #endif { char* result; int r = PyBytes_AsStringAndSize(o, &result, length); if (unlikely(r < 0)) { return NULL; } else { return result; } } } static CYTHON_INLINE int __Pyx_PyObject_IsTrue(PyObject* x) { int is_true = x == Py_True; if (is_true | (x == Py_False) | (x == Py_None)) return is_true; else return PyObject_IsTrue(x); } static CYTHON_INLINE int __Pyx_PyObject_IsTrueAndDecref(PyObject* x) { int retval; if (unlikely(!x)) return -1; retval = __Pyx_PyObject_IsTrue(x); Py_DECREF(x); return retval; } static PyObject* __Pyx_PyNumber_IntOrLongWrongResultType(PyObject* result, const char* type_name) { __Pyx_TypeName result_type_name = __Pyx_PyType_GetName(Py_TYPE(result)); #if PY_MAJOR_VERSION >= 3 if (PyLong_Check(result)) { if (PyErr_WarnFormat(PyExc_DeprecationWarning, 1, "__int__ returned non-int (type " __Pyx_FMT_TYPENAME "). " "The ability to return an instance of a strict subclass of int is deprecated, " "and may be removed in a future version of Python.", result_type_name)) { __Pyx_DECREF_TypeName(result_type_name); Py_DECREF(result); return NULL; } __Pyx_DECREF_TypeName(result_type_name); return result; } #endif PyErr_Format(PyExc_TypeError, "__%.4s__ returned non-%.4s (type " __Pyx_FMT_TYPENAME ")", type_name, type_name, result_type_name); __Pyx_DECREF_TypeName(result_type_name); Py_DECREF(result); return NULL; } static CYTHON_INLINE PyObject* __Pyx_PyNumber_IntOrLong(PyObject* x) { #if CYTHON_USE_TYPE_SLOTS PyNumberMethods *m; #endif const char *name = NULL; PyObject *res = NULL; #if PY_MAJOR_VERSION < 3 if (likely(PyInt_Check(x) || PyLong_Check(x))) #else if (likely(PyLong_Check(x))) #endif return __Pyx_NewRef(x); #if CYTHON_USE_TYPE_SLOTS m = Py_TYPE(x)->tp_as_number; #if PY_MAJOR_VERSION < 3 if (m && m->nb_int) { name = "int"; res = m->nb_int(x); } else if (m && m->nb_long) { name = "long"; res = m->nb_long(x); } #else if (likely(m && m->nb_int)) { name = "int"; res = m->nb_int(x); } #endif #else if (!PyBytes_CheckExact(x) && !PyUnicode_CheckExact(x)) { res = PyNumber_Int(x); } #endif if (likely(res)) { #if PY_MAJOR_VERSION < 3 if (unlikely(!PyInt_Check(res) && !PyLong_Check(res))) { #else if (unlikely(!PyLong_CheckExact(res))) { #endif return __Pyx_PyNumber_IntOrLongWrongResultType(res, name); } } else if (!PyErr_Occurred()) { PyErr_SetString(PyExc_TypeError, "an integer is required"); } return res; } static CYTHON_INLINE Py_ssize_t __Pyx_PyIndex_AsSsize_t(PyObject* b) { Py_ssize_t ival; PyObject *x; #if PY_MAJOR_VERSION < 3 if (likely(PyInt_CheckExact(b))) { if (sizeof(Py_ssize_t) >= sizeof(long)) return PyInt_AS_LONG(b); else return PyInt_AsSsize_t(b); } #endif if (likely(PyLong_CheckExact(b))) { #if CYTHON_USE_PYLONG_INTERNALS if (likely(__Pyx_PyLong_IsCompact(b))) { return __Pyx_PyLong_CompactValue(b); } else { const digit* digits = __Pyx_PyLong_Digits(b); const Py_ssize_t size = __Pyx_PyLong_SignedDigitCount(b); switch (size) { case 2: if (8 * sizeof(Py_ssize_t) > 2 * PyLong_SHIFT) { return (Py_ssize_t) (((((size_t)digits[1]) << PyLong_SHIFT) | (size_t)digits[0])); } break; case -2: if (8 * sizeof(Py_ssize_t) > 2 * PyLong_SHIFT) { return -(Py_ssize_t) (((((size_t)digits[1]) << PyLong_SHIFT) | (size_t)digits[0])); } break; case 3: if (8 * sizeof(Py_ssize_t) > 3 * PyLong_SHIFT) { return (Py_ssize_t) (((((((size_t)digits[2]) << PyLong_SHIFT) | (size_t)digits[1]) << PyLong_SHIFT) | (size_t)digits[0])); } break; case -3: if (8 * sizeof(Py_ssize_t) > 3 * PyLong_SHIFT) { return -(Py_ssize_t) (((((((size_t)digits[2]) << PyLong_SHIFT) | (size_t)digits[1]) << PyLong_SHIFT) | (size_t)digits[0])); } break; case 4: if (8 * sizeof(Py_ssize_t) > 4 * PyLong_SHIFT) { return (Py_ssize_t) (((((((((size_t)digits[3]) << PyLong_SHIFT) | (size_t)digits[2]) << PyLong_SHIFT) | (size_t)digits[1]) << PyLong_SHIFT) | (size_t)digits[0])); } break; case -4: if (8 * sizeof(Py_ssize_t) > 4 * PyLong_SHIFT) { return -(Py_ssize_t) (((((((((size_t)digits[3]) << PyLong_SHIFT) | (size_t)digits[2]) << PyLong_SHIFT) | (size_t)digits[1]) << PyLong_SHIFT) | (size_t)digits[0])); } break; } } #endif return PyLong_AsSsize_t(b); } x = PyNumber_Index(b); if (!x) return -1; ival = PyInt_AsSsize_t(x); Py_DECREF(x); return ival; } static CYTHON_INLINE Py_hash_t __Pyx_PyIndex_AsHash_t(PyObject* o) { if (sizeof(Py_hash_t) == sizeof(Py_ssize_t)) { return (Py_hash_t) __Pyx_PyIndex_AsSsize_t(o); #if PY_MAJOR_VERSION < 3 } else if (likely(PyInt_CheckExact(o))) { return PyInt_AS_LONG(o); #endif } else { Py_ssize_t ival; PyObject *x; x = PyNumber_Index(o); if (!x) return -1; ival = PyInt_AsLong(x); Py_DECREF(x); return ival; } } static CYTHON_INLINE PyObject * __Pyx_PyBool_FromLong(long b) { return b ? __Pyx_NewRef(Py_True) : __Pyx_NewRef(Py_False); } static CYTHON_INLINE PyObject * __Pyx_PyInt_FromSize_t(size_t ival) { return PyInt_FromSize_t(ival); } /* #### Code section: utility_code_pragmas_end ### */ #ifdef _MSC_VER #pragma warning( pop ) #endif /* #### Code section: end ### */ #endif /* Py_PYTHON_H */