explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-12 10:16:27 +03:00
Code Issues Packages Projects Releases Wiki Activity
0c1be7effe
spaCy/spacy/lexeme.cpp

3125 lines
129 KiB
C++
Raw Normal View History

* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* Generated by Cython 0.20.1 on Mon Jul 7 04:19:15 2014 */
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
#define PY_SSIZE_T_CLEAN
#ifndef CYTHON_USE_PYLONG_INTERNALS
#ifdef PYLONG_BITS_IN_DIGIT
#define CYTHON_USE_PYLONG_INTERNALS 0
#else
#include "pyconfig.h"
#ifdef PYLONG_BITS_IN_DIGIT
#define CYTHON_USE_PYLONG_INTERNALS 1
#else
#define CYTHON_USE_PYLONG_INTERNALS 0
#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 < 0x02040000
#error Cython requires Python 2.4+.
#else
#define CYTHON_ABI "0_20_1"
#include <stddef.h> /* For offsetof */
#ifndef offsetof
#define offsetof(type, member) ( (size_t) & ((type*)0) -> member )
#endif
#if !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
#ifndef PY_LONG_LONG
#define PY_LONG_LONG LONG_LONG
#endif
#ifndef Py_HUGE_VAL
#define Py_HUGE_VAL HUGE_VAL
#endif
#ifdef PYPY_VERSION
#define CYTHON_COMPILING_IN_PYPY 1
#define CYTHON_COMPILING_IN_CPYTHON 0
#else
#define CYTHON_COMPILING_IN_PYPY 0
#define CYTHON_COMPILING_IN_CPYTHON 1
#endif
#if CYTHON_COMPILING_IN_PYPY
#define Py_OptimizeFlag 0
#endif
#if PY_VERSION_HEX < 0x02050000
typedef int Py_ssize_t;
#define PY_SSIZE_T_MAX INT_MAX
#define PY_SSIZE_T_MIN INT_MIN
#define PY_FORMAT_SIZE_T ""
#define CYTHON_FORMAT_SSIZE_T ""
#define PyInt_FromSsize_t(z) PyInt_FromLong(z)
#define PyInt_AsSsize_t(o) __Pyx_PyInt_As_int(o)
#define PyNumber_Index(o) ((PyNumber_Check(o) && !PyFloat_Check(o)) ? PyNumber_Int(o) : \
(PyErr_Format(PyExc_TypeError, \
"expected index value, got %.200s", Py_TYPE(o)->tp_name), \
(PyObject*)0))
#define __Pyx_PyIndex_Check(o) (PyNumber_Check(o) && !PyFloat_Check(o) && \
!PyComplex_Check(o))
#define PyIndex_Check __Pyx_PyIndex_Check
#define PyErr_WarnEx(category, message, stacklevel) PyErr_Warn(category, message)
#define __PYX_BUILD_PY_SSIZE_T "i"
#else
#define __PYX_BUILD_PY_SSIZE_T "n"
#define CYTHON_FORMAT_SSIZE_T "z"
#define __Pyx_PyIndex_Check PyIndex_Check
#endif
#if PY_VERSION_HEX < 0x02060000
#define Py_REFCNT(ob) (((PyObject*)(ob))->ob_refcnt)
#define Py_TYPE(ob) (((PyObject*)(ob))->ob_type)
#define Py_SIZE(ob) (((PyVarObject*)(ob))->ob_size)
#define PyVarObject_HEAD_INIT(type, size) \
PyObject_HEAD_INIT(type) size,
#define PyType_Modified(t)
typedef struct {
void *buf;
PyObject *obj;
Py_ssize_t len;
Py_ssize_t itemsize;
int readonly;
int ndim;
char *format;
Py_ssize_t *shape;
Py_ssize_t *strides;
Py_ssize_t *suboffsets;
void *internal;
} Py_buffer;
#define PyBUF_SIMPLE 0
#define PyBUF_WRITABLE 0x0001
#define PyBUF_FORMAT 0x0004
#define PyBUF_ND 0x0008
#define PyBUF_STRIDES (0x0010 | PyBUF_ND)
#define PyBUF_C_CONTIGUOUS (0x0020 | PyBUF_STRIDES)
#define PyBUF_F_CONTIGUOUS (0x0040 | PyBUF_STRIDES)
#define PyBUF_ANY_CONTIGUOUS (0x0080 | PyBUF_STRIDES)
#define PyBUF_INDIRECT (0x0100 | PyBUF_STRIDES)
#define PyBUF_RECORDS (PyBUF_STRIDES | PyBUF_FORMAT | PyBUF_WRITABLE)
#define PyBUF_FULL (PyBUF_INDIRECT | PyBUF_FORMAT | PyBUF_WRITABLE)
typedef int (*getbufferproc)(PyObject *, Py_buffer *, int);
typedef void (*releasebufferproc)(PyObject *, Py_buffer *);
#endif
#if PY_MAJOR_VERSION < 3
#define __Pyx_BUILTIN_MODULE_NAME "__builtin__"
#define __Pyx_PyCode_New(a, 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)
#define __Pyx_DefaultClassType PyClass_Type
#else
#define __Pyx_BUILTIN_MODULE_NAME "builtins"
#define __Pyx_PyCode_New(a, 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)
#define __Pyx_DefaultClassType PyType_Type
#endif
#if PY_VERSION_HEX < 0x02060000
#define PyUnicode_FromString(s) PyUnicode_Decode(s, strlen(s), "UTF-8", "strict")
#endif
#if PY_MAJOR_VERSION >= 3
#define Py_TPFLAGS_CHECKTYPES 0
#define Py_TPFLAGS_HAVE_INDEX 0
#endif
#if (PY_VERSION_HEX < 0x02060000) || (PY_MAJOR_VERSION >= 3)
#define Py_TPFLAGS_HAVE_NEWBUFFER 0
#endif
#if PY_VERSION_HEX < 0x02060000
#define Py_TPFLAGS_HAVE_VERSION_TAG 0
#endif
#if PY_VERSION_HEX < 0x02060000 && !defined(Py_TPFLAGS_IS_ABSTRACT)
#define Py_TPFLAGS_IS_ABSTRACT 0
#endif
#if PY_VERSION_HEX < 0x030400a1 && !defined(Py_TPFLAGS_HAVE_FINALIZE)
#define Py_TPFLAGS_HAVE_FINALIZE 0
#endif
#if PY_VERSION_HEX > 0x03030000 && defined(PyUnicode_KIND)
#define CYTHON_PEP393_ENABLED 1
#define __Pyx_PyUnicode_READY(op) (likely(PyUnicode_IS_READY(op)) ? \
0 : _PyUnicode_Ready((PyObject *)(op)))
#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_KIND(u) PyUnicode_KIND(u)
#define __Pyx_PyUnicode_DATA(u) PyUnicode_DATA(u)
#define __Pyx_PyUnicode_READ(k, d, i) PyUnicode_READ(k, d, i)
#else
#define CYTHON_PEP393_ENABLED 0
#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_KIND(u) (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]))
#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
#define __Pyx_PyString_FormatSafe(a, b) ((unlikely((a) == Py_None)) ? PyNumber_Remainder(a, b) : __Pyx_PyString_Format(a, b))
#define __Pyx_PyUnicode_FormatSafe(a, b) ((unlikely((a) == Py_None)) ? 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
#define PyBaseString_Type PyUnicode_Type
#define PyStringObject PyUnicodeObject
#define PyString_Type PyUnicode_Type
#define PyString_Check PyUnicode_Check
#define PyString_CheckExact PyUnicode_CheckExact
#endif
#if PY_VERSION_HEX < 0x02060000
#define PyBytesObject PyStringObject
#define PyBytes_Type PyString_Type
#define PyBytes_Check PyString_Check
#define PyBytes_CheckExact PyString_CheckExact
#define PyBytes_FromString PyString_FromString
#define PyBytes_FromStringAndSize PyString_FromStringAndSize
#define PyBytes_FromFormat PyString_FromFormat
#define PyBytes_DecodeEscape PyString_DecodeEscape
#define PyBytes_AsString PyString_AsString
#define PyBytes_AsStringAndSize PyString_AsStringAndSize
#define PyBytes_Size PyString_Size
#define PyBytes_AS_STRING PyString_AS_STRING
#define PyBytes_GET_SIZE PyString_GET_SIZE
#define PyBytes_Repr PyString_Repr
#define PyBytes_Concat PyString_Concat
#define PyBytes_ConcatAndDel PyString_ConcatAndDel
#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_CheckExact(obj) || PyUnicode_CheckExact(obj) || \
PyString_Check(obj) || PyUnicode_Check(obj))
#define __Pyx_PyBaseString_CheckExact(obj) (PyString_CheckExact(obj) || PyUnicode_CheckExact(obj))
#endif
#if PY_VERSION_HEX < 0x02060000
#define PySet_Check(obj) PyObject_TypeCheck(obj, &PySet_Type)
#define PyFrozenSet_Check(obj) PyObject_TypeCheck(obj, &PyFrozenSet_Type)
#endif
#ifndef PySet_CheckExact
#define PySet_CheckExact(obj) (Py_TYPE(obj) == &PySet_Type)
#endif
#define __Pyx_TypeCheck(obj, type) PyObject_TypeCheck(obj, (PyTypeObject *)type)
#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 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
#endif
#if PY_MAJOR_VERSION >= 3
#define PyBoolObject PyLongObject
#endif
#if PY_VERSION_HEX < 0x030200A4
typedef long Py_hash_t;
#define __Pyx_PyInt_FromHash_t PyInt_FromLong
#define __Pyx_PyInt_AsHash_t PyInt_AsLong
#else
#define __Pyx_PyInt_FromHash_t PyInt_FromSsize_t
#define __Pyx_PyInt_AsHash_t PyInt_AsSsize_t
#endif
#if (PY_MAJOR_VERSION < 3) || (PY_VERSION_HEX >= 0x03010300)
#define __Pyx_PySequence_GetSlice(obj, a, b) PySequence_GetSlice(obj, a, b)
#define __Pyx_PySequence_SetSlice(obj, a, b, value) PySequence_SetSlice(obj, a, b, value)
#define __Pyx_PySequence_DelSlice(obj, a, b) PySequence_DelSlice(obj, a, b)
#else
#define __Pyx_PySequence_GetSlice(obj, a, b) (unlikely(!(obj)) ? \
(PyErr_SetString(PyExc_SystemError, "null argument to internal routine"), (PyObject*)0) : \
(likely((obj)->ob_type->tp_as_mapping) ? (PySequence_GetSlice(obj, a, b)) : \
(PyErr_Format(PyExc_TypeError, "'%.200s' object is unsliceable", (obj)->ob_type->tp_name), (PyObject*)0)))
#define __Pyx_PySequence_SetSlice(obj, a, b, value) (unlikely(!(obj)) ? \
(PyErr_SetString(PyExc_SystemError, "null argument to internal routine"), -1) : \
(likely((obj)->ob_type->tp_as_mapping) ? (PySequence_SetSlice(obj, a, b, value)) : \
(PyErr_Format(PyExc_TypeError, "'%.200s' object doesn't support slice assignment", (obj)->ob_type->tp_name), -1)))
#define __Pyx_PySequence_DelSlice(obj, a, b) (unlikely(!(obj)) ? \
(PyErr_SetString(PyExc_SystemError, "null argument to internal routine"), -1) : \
(likely((obj)->ob_type->tp_as_mapping) ? (PySequence_DelSlice(obj, a, b)) : \
(PyErr_Format(PyExc_TypeError, "'%.200s' object doesn't support slice deletion", (obj)->ob_type->tp_name), -1)))
#endif
#if PY_MAJOR_VERSION >= 3
#define PyMethod_New(func, self, klass) ((self) ? PyMethod_New(func, self) : PyInstanceMethod_New(func))
#endif
#if PY_VERSION_HEX < 0x02050000
#define __Pyx_GetAttrString(o,n) PyObject_GetAttrString((o),((char *)(n)))
#define __Pyx_SetAttrString(o,n,a) PyObject_SetAttrString((o),((char *)(n)),(a))
#define __Pyx_DelAttrString(o,n) PyObject_DelAttrString((o),((char *)(n)))
#else
#define __Pyx_GetAttrString(o,n) PyObject_GetAttrString((o),(n))
#define __Pyx_SetAttrString(o,n,a) PyObject_SetAttrString((o),(n),(a))
#define __Pyx_DelAttrString(o,n) PyObject_DelAttrString((o),(n))
#endif
#if PY_VERSION_HEX < 0x02050000
#define __Pyx_NAMESTR(n) ((char *)(n))
#define __Pyx_DOCSTR(n) ((char *)(n))
#else
#define __Pyx_NAMESTR(n) (n)
#define __Pyx_DOCSTR(n) (n)
#endif
#ifndef CYTHON_INLINE
#if defined(__GNUC__)
#define CYTHON_INLINE __inline__
#elif defined(_MSC_VER)
#define CYTHON_INLINE __inline
#elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
#define CYTHON_INLINE inline
#else
#define CYTHON_INLINE
#endif
#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
#ifdef NAN
#define __PYX_NAN() ((float) NAN)
#else
static CYTHON_INLINE float __PYX_NAN() {
/* Initialize NaN. The sign is irrelevant, an exponent with all bits 1 and
a nonzero mantissa means NaN. If the first bit in the mantissa is 1, it is
a quiet NaN. */
float value;
memset(&value, 0xFF, sizeof(value));
return value;
}
#endif
#if PY_MAJOR_VERSION >= 3
#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
#ifndef __PYX_EXTERN_C
#ifdef __cplusplus
#define __PYX_EXTERN_C extern "C"
#else
#define __PYX_EXTERN_C extern
#endif
#endif
#if defined(WIN32) || defined(MS_WINDOWS)
#define _USE_MATH_DEFINES
#endif
#include <math.h>
#define __PYX_HAVE__spacy__lexeme
#define __PYX_HAVE_API__spacy__lexeme
#include "stdint.h"
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
#include <vector>
#include "ios"
#include "new"
#include "stdexcept"
#include "typeinfo"
#include <utility>
#include "sparsehash/dense_hash_map"
#include "string.h"
#include "stdlib.h"
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
#ifdef _OPENMP
#include <omp.h>
#endif /* _OPENMP */
#ifdef PYREX_WITHOUT_ASSERTIONS
#define CYTHON_WITHOUT_ASSERTIONS
#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
typedef struct {PyObject **p; char *s; const Py_ssize_t n; const char* encoding;
const char is_unicode; const char is_str; const char intern; } __Pyx_StringTabEntry; /*proto*/
#define __PYX_DEFAULT_STRING_ENCODING_IS_ASCII 0
#define __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT 0
#define __PYX_DEFAULT_STRING_ENCODING ""
#define __Pyx_PyObject_FromString __Pyx_PyBytes_FromString
#define __Pyx_PyObject_FromStringAndSize __Pyx_PyBytes_FromStringAndSize
#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 char* __Pyx_PyObject_AsString(PyObject*);
static CYTHON_INLINE char* __Pyx_PyObject_AsStringAndSize(PyObject*, Py_ssize_t* length);
#define __Pyx_PyByteArray_FromString(s) PyByteArray_FromStringAndSize((const char*)s, strlen((const char*)s))
#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(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_PyObject_AsSString(s) ((signed char*) __Pyx_PyObject_AsString(s))
#define __Pyx_PyObject_AsUString(s) ((unsigned char*) __Pyx_PyObject_AsString(s))
#define __Pyx_PyObject_FromUString(s) __Pyx_PyObject_FromString((char*)s)
#define __Pyx_PyBytes_FromUString(s) __Pyx_PyBytes_FromString((char*)s)
#define __Pyx_PyByteArray_FromUString(s) __Pyx_PyByteArray_FromString((char*)s)
#define __Pyx_PyStr_FromUString(s) __Pyx_PyStr_FromString((char*)s)
#define __Pyx_PyUnicode_FromUString(s) __Pyx_PyUnicode_FromString((char*)s)
#if PY_MAJOR_VERSION < 3
static CYTHON_INLINE size_t __Pyx_Py_UNICODE_strlen(const Py_UNICODE *u)
{
const Py_UNICODE *u_end = u;
while (*u_end++) ;
return u_end - u - 1;
}
#else
#define __Pyx_Py_UNICODE_strlen Py_UNICODE_strlen
#endif
#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_Owned_Py_None(b) (Py_INCREF(Py_None), Py_None)
#define __Pyx_PyBool_FromLong(b) ((b) ? (Py_INCREF(Py_True), Py_True) : (Py_INCREF(Py_False), Py_False))
static CYTHON_INLINE int __Pyx_PyObject_IsTrue(PyObject*);
static CYTHON_INLINE PyObject* __Pyx_PyNumber_Int(PyObject* x);
static CYTHON_INLINE Py_ssize_t __Pyx_PyIndex_AsSsize_t(PyObject*);
static CYTHON_INLINE PyObject * __Pyx_PyInt_FromSize_t(size_t);
#if CYTHON_COMPILING_IN_CPYTHON
#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 && __PYX_DEFAULT_STRING_ENCODING_IS_ASCII
static int __Pyx_sys_getdefaultencoding_not_ascii;
static int __Pyx_init_sys_getdefaultencoding_params(void) {
PyObject* sys = NULL;
PyObject* default_encoding = NULL;
PyObject* ascii_chars_u = NULL;
PyObject* ascii_chars_b = NULL;
sys = PyImport_ImportModule("sys");
if (sys == NULL) goto bad;
default_encoding = PyObject_CallMethod(sys, (char*) (const char*) "getdefaultencoding", NULL);
if (default_encoding == NULL) goto bad;
if (strcmp(PyBytes_AsString(default_encoding), "ascii") == 0) {
__Pyx_sys_getdefaultencoding_not_ascii = 0;
} else {
const char* default_encoding_c = PyBytes_AS_STRING(default_encoding);
char ascii_chars[128];
int c;
for (c = 0; c < 128; c++) {
ascii_chars[c] = c;
}
__Pyx_sys_getdefaultencoding_not_ascii = 1;
ascii_chars_u = PyUnicode_DecodeASCII(ascii_chars, 128, NULL);
if (ascii_chars_u == NULL) goto bad;
ascii_chars_b = PyUnicode_AsEncodedString(ascii_chars_u, default_encoding_c, NULL);
if (ascii_chars_b == NULL || strncmp(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_XDECREF(sys);
Py_XDECREF(default_encoding);
Py_XDECREF(ascii_chars_u);
Py_XDECREF(ascii_chars_b);
return 0;
bad:
Py_XDECREF(sys);
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
static char* __PYX_DEFAULT_STRING_ENCODING;
static int __Pyx_init_sys_getdefaultencoding_params(void) {
PyObject* sys = NULL;
PyObject* default_encoding = NULL;
char* default_encoding_c;
sys = PyImport_ImportModule("sys");
if (sys == NULL) goto bad;
default_encoding = PyObject_CallMethod(sys, (char*) (const char*) "getdefaultencoding", NULL);
if (default_encoding == NULL) goto bad;
default_encoding_c = PyBytes_AS_STRING(default_encoding);
__PYX_DEFAULT_STRING_ENCODING = (char*) malloc(strlen(default_encoding_c));
strcpy(__PYX_DEFAULT_STRING_ENCODING, default_encoding_c);
Py_DECREF(sys);
Py_DECREF(default_encoding);
return 0;
bad:
Py_XDECREF(sys);
Py_XDECREF(default_encoding);
return -1;
}
#endif
#endif
#ifdef __GNUC__
/* Test for GCC > 2.95 */
#if __GNUC__ > 2 || (__GNUC__ == 2 && (__GNUC_MINOR__ > 95))
#define likely(x) __builtin_expect(!!(x), 1)
#define unlikely(x) __builtin_expect(!!(x), 0)
#else /* __GNUC__ > 2 ... */
#define likely(x) (x)
#define unlikely(x) (x)
#endif /* __GNUC__ > 2 ... */
#else /* __GNUC__ */
#define likely(x) (x)
#define unlikely(x) (x)
#endif /* __GNUC__ */
static PyObject *__pyx_m;
static PyObject *__pyx_d;
static PyObject *__pyx_b;
static PyObject *__pyx_empty_tuple;
static PyObject *__pyx_empty_bytes;
static int __pyx_lineno;
static int __pyx_clineno = 0;
static const char * __pyx_cfilenm= __FILE__;
static const char *__pyx_filename;
static const char *__pyx_f[] = {
"lexeme.pyx",
};
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/spacy.pxd":7
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
* # Circular import problems here
* ctypedef size_t Lexeme_addr # <<<<<<<<<<<<<<
* ctypedef uint64_t StringHash
* ctypedef dense_hash_map[StringHash, Lexeme_addr] Vocab
*/
typedef size_t __pyx_t_5spacy_5spacy_Lexeme_addr;
/* "spacy/spacy.pxd":8
* # Circular import problems here
* ctypedef size_t Lexeme_addr
* ctypedef uint64_t StringHash # <<<<<<<<<<<<<<
* ctypedef dense_hash_map[StringHash, Lexeme_addr] Vocab
* ctypedef int (*Splitter)(unicode word, size_t length)
*/
typedef uint64_t __pyx_t_5spacy_5spacy_StringHash;
/* "spacy/lexeme.pxd":4
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
* # Put these above import to avoid circular import problem
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* ctypedef int ClusterID # <<<<<<<<<<<<<<
* ctypedef uint64_t StringHash
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
* ctypedef size_t Lexeme_addr
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*/
typedef int __pyx_t_5spacy_6lexeme_ClusterID;
/* "spacy/lexeme.pxd":5
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
* # Put these above import to avoid circular import problem
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* ctypedef int ClusterID
* ctypedef uint64_t StringHash # <<<<<<<<<<<<<<
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
* ctypedef size_t Lexeme_addr
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*/
typedef uint64_t __pyx_t_5spacy_6lexeme_StringHash;
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pxd":6
* ctypedef int ClusterID
* ctypedef uint64_t StringHash
* ctypedef size_t Lexeme_addr # <<<<<<<<<<<<<<
*
* from spacy.spacy cimport Vocab
*/
typedef size_t __pyx_t_5spacy_6lexeme_Lexeme_addr;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
/*--- Type declarations ---*/
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/spacy.pxd":9
* ctypedef size_t Lexeme_addr
* ctypedef uint64_t StringHash
* ctypedef dense_hash_map[StringHash, Lexeme_addr] Vocab # <<<<<<<<<<<<<<
* ctypedef int (*Splitter)(unicode word, size_t length)
*
*/
typedef google::dense_hash_map<__pyx_t_5spacy_5spacy_StringHash,__pyx_t_5spacy_5spacy_Lexeme_addr> __pyx_t_5spacy_5spacy_Vocab;
/* "spacy/spacy.pxd":10
* ctypedef uint64_t StringHash
* ctypedef dense_hash_map[StringHash, Lexeme_addr] Vocab
* ctypedef int (*Splitter)(unicode word, size_t length) # <<<<<<<<<<<<<<
*
*
*/
typedef int (*__pyx_t_5spacy_5spacy_Splitter)(PyObject *, size_t);
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
struct __pyx_t_5spacy_6lexeme_Lexeme;
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pxd":36
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* # over the Lexeme, via:
* # for field in range(LexAttr.n): get_attr(Lexeme*, field)
* cdef enum HashFields: # <<<<<<<<<<<<<<
* sic
* lex
*/
enum __pyx_t_5spacy_6lexeme_HashFields {
__pyx_e_5spacy_6lexeme_sic,
__pyx_e_5spacy_6lexeme_lex,
__pyx_e_5spacy_6lexeme_normed,
__pyx_e_5spacy_6lexeme_cluster,
__pyx_e_5spacy_6lexeme_n
};
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pxd":11
* from spacy.spacy cimport Splitter
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
* cdef struct Lexeme: # <<<<<<<<<<<<<<
* StringHash sic # Hash of the original string
* StringHash lex # Hash of the word, with punctuation and clitics split off
*/
struct __pyx_t_5spacy_6lexeme_Lexeme {
__pyx_t_5spacy_6lexeme_StringHash sic;
__pyx_t_5spacy_6lexeme_StringHash lex;
__pyx_t_5spacy_6lexeme_StringHash normed;
__pyx_t_5spacy_6lexeme_StringHash last3;
Py_UNICODE first;
double prob;
__pyx_t_5spacy_6lexeme_ClusterID cluster;
int oft_upper;
int oft_title;
struct __pyx_t_5spacy_6lexeme_Lexeme *tail;
};
#ifndef CYTHON_REFNANNY
#define CYTHON_REFNANNY 0
#endif
#if CYTHON_REFNANNY
typedef struct {
void (*INCREF)(void*, PyObject*, int);
void (*DECREF)(void*, PyObject*, int);
void (*GOTREF)(void*, PyObject*, int);
void (*GIVEREF)(void*, PyObject*, int);
void* (*SetupContext)(const char*, int, const char*);
void (*FinishContext)(void**);
} __Pyx_RefNannyAPIStruct;
static __Pyx_RefNannyAPIStruct *__Pyx_RefNanny = NULL;
static __Pyx_RefNannyAPIStruct *__Pyx_RefNannyImportAPI(const char *modname); /*proto*/
#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__); \
}
#else
#define __Pyx_RefNannySetupContext(name, acquire_gil) \
__pyx_refnanny = __Pyx_RefNanny->SetupContext((name), __LINE__, __FILE__)
#endif
#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) {__Pyx_INCREF(r); }} while(0)
#define __Pyx_XDECREF(r) do { if((r) != NULL) {__Pyx_DECREF(r); }} while(0)
#define __Pyx_XGOTREF(r) do { if((r) != NULL) {__Pyx_GOTREF(r); }} while(0)
#define __Pyx_XGIVEREF(r) do { if((r) != NULL) {__Pyx_GIVEREF(r);}} while(0)
#else
#define __Pyx_RefNannyDeclarations
#define __Pyx_RefNannySetupContext(name, acquire_gil)
#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 /* CYTHON_REFNANNY */
#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)
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
#define __Pyx_GetItemInt_Unicode(o, i, type, is_signed, to_py_func, is_list, wraparound, boundscheck) \
(__Pyx_fits_Py_ssize_t(i, type, is_signed) ? \
__Pyx_GetItemInt_Unicode_Fast(o, (Py_ssize_t)i, wraparound, boundscheck) : \
(PyErr_SetString(PyExc_IndexError, "string index out of range"), (Py_UCS4)-1))
static CYTHON_INLINE Py_UCS4 __Pyx_GetItemInt_Unicode_Fast(PyObject* ustring, Py_ssize_t i,
int wraparound, int boundscheck);
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static CYTHON_INLINE size_t __Pyx_PyInt_As_size_t(PyObject *);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
static CYTHON_INLINE PyObject* __Pyx_PyInt_From_long(long value);
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static CYTHON_INLINE PyObject* __Pyx_PyInt_From_uint64_t(uint64_t value);
static CYTHON_INLINE PyObject* __Pyx_PyInt_From_int(int value);
static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *);
static CYTHON_INLINE int __Pyx_PyInt_As_int(PyObject *);
static int __Pyx_check_binary_version(void);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
#if CYTHON_COMPILING_IN_CPYTHON
#define __Pyx_PyObject_DelAttrStr(o,n) __Pyx_PyObject_SetAttrStr(o,n,NULL)
static CYTHON_INLINE int __Pyx_PyObject_SetAttrStr(PyObject* obj, PyObject* attr_name, PyObject* value) {
PyTypeObject* tp = Py_TYPE(obj);
if (likely(tp->tp_setattro))
return tp->tp_setattro(obj, attr_name, value);
#if PY_MAJOR_VERSION < 3
if (likely(tp->tp_setattr))
return tp->tp_setattr(obj, PyString_AS_STRING(attr_name), value);
#endif
return PyObject_SetAttr(obj, attr_name, value);
}
#else
#define __Pyx_PyObject_DelAttrStr(o,n) PyObject_DelAttr(o,n)
#define __Pyx_PyObject_SetAttrStr(o,n,v) PyObject_SetAttr(o,n,v)
#endif
static int __Pyx_ExportVoidPtr(PyObject *name, void *p, const char *sig); /*proto*/
static int __Pyx_ExportFunction(const char *name, void (*f)(void), const char *sig); /*proto*/
#if !defined(__Pyx_PyIdentifier_FromString)
#if PY_MAJOR_VERSION < 3
#define __Pyx_PyIdentifier_FromString(s) PyString_FromString(s)
#else
#define __Pyx_PyIdentifier_FromString(s) PyUnicode_FromString(s)
#endif
#endif
static PyObject *__Pyx_ImportModule(const char *name); /*proto*/
static int __Pyx_ImportFunction(PyObject *module, const char *funcname, void (**f)(void), const char *sig); /*proto*/
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
typedef struct {
int code_line;
PyCodeObject* code_object;
} __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);
static void __Pyx_AddTraceback(const char *funcname, int c_line,
int py_line, const char *filename); /*proto*/
static int __Pyx_InitStrings(__Pyx_StringTabEntry *t); /*proto*/
/* Module declarations from 'libc.stdint' */
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* Module declarations from 'libcpp.vector' */
/* Module declarations from 'libcpp.utility' */
/* Module declarations from 'ext.sparsehash' */
/* Module declarations from 'spacy.spacy' */
static __pyx_t_5spacy_5spacy_Lexeme_addr (*__pyx_f_5spacy_5spacy_lookup)(__pyx_t_5spacy_5spacy_Vocab &, PyObject *, __pyx_t_5spacy_5spacy_Splitter, int, PyObject *); /*proto*/
static __pyx_t_5spacy_5spacy_StringHash (*__pyx_f_5spacy_5spacy_hash_string)(PyObject *, size_t); /*proto*/
/* Module declarations from 'spacy.string_tools' */
static PyObject *(*__pyx_f_5spacy_12string_tools_substr)(PyObject *, int, int, size_t, int __pyx_skip_dispatch); /*proto*/
/* Module declarations from 'libc.string' */
/* Module declarations from 'libc.stdlib' */
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
/* Module declarations from 'spacy.lexeme' */
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
static struct __pyx_t_5spacy_6lexeme_Lexeme __pyx_v_5spacy_6lexeme_BLANK_WORD;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static __pyx_t_5spacy_6lexeme_StringHash __pyx_f_5spacy_6lexeme_sic_of(size_t, int __pyx_skip_dispatch); /*proto*/
static __pyx_t_5spacy_6lexeme_StringHash __pyx_f_5spacy_6lexeme_lex_of(size_t, int __pyx_skip_dispatch); /*proto*/
static __pyx_t_5spacy_6lexeme_ClusterID __pyx_f_5spacy_6lexeme_cluster_of(size_t, int __pyx_skip_dispatch); /*proto*/
static Py_UNICODE __pyx_f_5spacy_6lexeme_first_of(size_t, int __pyx_skip_dispatch); /*proto*/
static double __pyx_f_5spacy_6lexeme_prob_of(size_t, int __pyx_skip_dispatch); /*proto*/
static __pyx_t_5spacy_6lexeme_StringHash __pyx_f_5spacy_6lexeme_last3_of(size_t, int __pyx_skip_dispatch); /*proto*/
static int __pyx_f_5spacy_6lexeme_is_oft_upper(size_t, int __pyx_skip_dispatch); /*proto*/
static int __pyx_f_5spacy_6lexeme_is_oft_title(size_t, int __pyx_skip_dispatch); /*proto*/
#define __Pyx_MODULE_NAME "spacy.lexeme"
int __pyx_module_is_main_spacy__lexeme = 0;
/* Implementation of 'spacy.lexeme' */
static PyObject *__pyx_pf_5spacy_6lexeme_sic_of(CYTHON_UNUSED PyObject *__pyx_self, size_t __pyx_v_lex_id); /* proto */
static PyObject *__pyx_pf_5spacy_6lexeme_2lex_of(CYTHON_UNUSED PyObject *__pyx_self, size_t __pyx_v_lex_id); /* proto */
static PyObject *__pyx_pf_5spacy_6lexeme_4cluster_of(CYTHON_UNUSED PyObject *__pyx_self, size_t __pyx_v_lex_id); /* proto */
static PyObject *__pyx_pf_5spacy_6lexeme_6first_of(CYTHON_UNUSED PyObject *__pyx_self, size_t __pyx_v_lex_id); /* proto */
static PyObject *__pyx_pf_5spacy_6lexeme_8prob_of(CYTHON_UNUSED PyObject *__pyx_self, size_t __pyx_v_lex_id); /* proto */
static PyObject *__pyx_pf_5spacy_6lexeme_10last3_of(CYTHON_UNUSED PyObject *__pyx_self, size_t __pyx_v_lex_id); /* proto */
static PyObject *__pyx_pf_5spacy_6lexeme_12is_oft_upper(CYTHON_UNUSED PyObject *__pyx_self, size_t __pyx_v_lex_id); /* proto */
static PyObject *__pyx_pf_5spacy_6lexeme_14is_oft_title(CYTHON_UNUSED PyObject *__pyx_self, size_t __pyx_v_lex_id); /* proto */
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
static char __pyx_k_[] = "";
static char __pyx_k__2[] = "?";
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static char __pyx_k_main[] = "__main__";
static char __pyx_k_test[] = "__test__";
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
static char __pyx_k_pyx_capi[] = "__pyx_capi__";
static char __pyx_k_BLANK_WORD[] = "BLANK_WORD";
static char __pyx_k_lex_of_line_73[] = "lex_of (line 73)";
static char __pyx_k_sic_of_line_61[] = "sic_of (line 61)";
static char __pyx_k_prob_of_line_117[] = "prob_of (line 117)";
static char __pyx_k_first_of_line_106[] = "first_of (line 106)";
static char __pyx_k_last3_of_line_130[] = "last3_of (line 130)";
static char __pyx_k_cluster_of_line_87[] = "cluster_of (line 87)";
static char __pyx_k_is_oft_title_line_156[] = "is_oft_title (line 156)";
static char __pyx_k_is_oft_upper_line_141[] = "is_oft_upper (line 141)";
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static char __pyx_k_Access_the_cluster_field_of_the[] = "Access the `cluster' field of the Lexeme pointed to by lex_id, which\n gives an integer representation of the cluster ID of the word, \n which should be understood as a binary address:\n\n >>> strings = (u'pineapple', u'apple', u'dapple', u'scalable')\n >>> token_ids = [lookup(s) for s in strings]\n >>> clusters = [cluster_of(t) for t in token_ids]\n >>> print [\"{0:b\"} % cluster_of(t) for t in token_ids]\n [\"100111110110\", \"100111100100\", \"01010111011001\", \"100111110110\"]\n\n The clusterings are unideal, but often slightly useful.\n \"pineapple\" and \"apple\" share a long prefix, indicating a similar meaning,\n while \"dapple\" is totally different. On the other hand, \"scalable\" receives\n the same cluster ID as \"pineapple\", which is not what we'd like.\n ";
static char __pyx_k_Accessors_for_Lexeme_properties[] = "Accessors for Lexeme properties, given a lex_id, which is cast to a Lexeme*.\nMostly useful from Python-space. From Cython-space, you can just cast to\nLexeme* yourself.\n";
static char __pyx_k_Access_the_first_field_of_the_Le[] = "Access the `first' field of the Lexeme pointed to by lex_id, which\n stores the first character of the lex string of the word.\n\n >>> lex_id = lookup(u'Hello')\n >>> unhash(first_of(lex_id))\n u'H'\n ";
static char __pyx_k_Access_the_last3_field_of_the_Le[] = "Access the `last3' field of the Lexeme pointed to by lex_id, which stores\n the hash of the last three characters of the word:\n\n >>> lex_ids = [lookup(w) for w in (u'Hello', u'!')]\n >>> [unhash(last3_of(lex_id)) for lex_id in lex_ids]\n [u'llo', u'!']\n ";
static char __pyx_k_Access_the_lex_field_of_the_Lexe[] = "Access the `lex' field of the Lexeme pointed to by lex_id.\n\n The lex field is the hash of the string you would expect to get back from\n a standard tokenizer, i.e. the word with punctuation and other non-whitespace\n delimited tokens split off. The other fields refer to properties of the\n string that the lex field stores a hash of, except sic and tail.\n\n >>> [unhash(lex_of(lex_id) for lex_id in from_string(u'Hi! world')]\n [u'Hi', u'!', u'world']\n ";
static char __pyx_k_Access_the_oft_upper_field_of_th[] = "Access the `oft_upper' field of the Lexeme pointed to by lex_id, which\n stores whether the lowered version of the string hashed by `lex' is found\n in all-upper case frequently in a large sample of text. Users are free\n to load different data, by default we use a sample from Wikipedia, with\n a threshold of 0.95, picked to maximize mutual information for POS tagging.\n\n >>> is_oft_upper(lookup(u'abc'))\n True\n >>> is_oft_upper(lookup(u'aBc')) # This must get the same answer\n True\n ";
static char __pyx_k_Access_the_prob_field_of_the_Lex[] = "Access the `prob' field of the Lexeme pointed to by lex_id, which stores\n the smoothed unigram log probability of the word, as estimated from a large\n text corpus. By default, probabilities are based on counts from Gigaword,\n smoothed using Knesser-Ney; but any probabilities file can be supplied to\n load_probs.\n \n >>> prob_of(lookup(u'world'))\n -20.10340371976182\n ";
static char __pyx_k_Access_the_sic_field_of_the_Lexe[] = "Access the `sic' field of the Lexeme pointed to by lex_id.\n \n The sic field stores the hash of the whitespace-delimited string-chunk used to\n construct the Lexeme.\n \n >>> [unhash(sic_of(lex_id)) for lex_id in from_string(u'Hi! world')]\n [u'Hi!', u'', u'world]\n ";
static char __pyx_k_Access_the_oft_upper_field_of_th_2[] = "Access the `oft_upper' field of the Lexeme pointed to by lex_id, which\n stores whether the lowered version of the string hashed by `lex' is found\n title-cased frequently in a large sample of text. Users are free\n to load different data, by default we use a sample from Wikipedia, with\n a threshold of 0.3, picked to maximize mutual information for POS tagging.\n\n >>> is_oft_title(lookup(u'marcus'))\n True\n >>> is_oft_title(lookup(u'MARCUS')) # This must get the same value\n True\n ";
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
static PyObject *__pyx_kp_u_;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static PyObject *__pyx_kp_u_Access_the_cluster_field_of_the;
static PyObject *__pyx_kp_u_Access_the_first_field_of_the_Le;
static PyObject *__pyx_kp_u_Access_the_last3_field_of_the_Le;
static PyObject *__pyx_kp_u_Access_the_lex_field_of_the_Lexe;
static PyObject *__pyx_kp_u_Access_the_oft_upper_field_of_th;
static PyObject *__pyx_kp_u_Access_the_oft_upper_field_of_th_2;
static PyObject *__pyx_kp_u_Access_the_prob_field_of_the_Lex;
static PyObject *__pyx_kp_u_Access_the_sic_field_of_the_Lexe;
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
static PyObject *__pyx_n_s_BLANK_WORD;
static PyObject *__pyx_kp_u__2;
static PyObject *__pyx_kp_u_cluster_of_line_87;
static PyObject *__pyx_kp_u_first_of_line_106;
static PyObject *__pyx_kp_u_is_oft_title_line_156;
static PyObject *__pyx_kp_u_is_oft_upper_line_141;
static PyObject *__pyx_kp_u_last3_of_line_130;
static PyObject *__pyx_kp_u_lex_of_line_73;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static PyObject *__pyx_n_s_main;
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
static PyObject *__pyx_kp_u_prob_of_line_117;
static PyObject *__pyx_n_s_pyx_capi;
static PyObject *__pyx_kp_u_sic_of_line_61;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
static PyObject *__pyx_n_s_test;
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":16
*
*
* cdef Lexeme* init_lexeme(Vocab vocab, dict bacov, Splitter find_split, # <<<<<<<<<<<<<<
* unicode string, StringHash hashed,
* int split, size_t length) except NULL:
*/
static struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_f_5spacy_6lexeme_init_lexeme(__pyx_t_5spacy_5spacy_Vocab __pyx_v_vocab, PyObject *__pyx_v_bacov, __pyx_t_5spacy_5spacy_Splitter __pyx_v_find_split, PyObject *__pyx_v_string, __pyx_t_5spacy_6lexeme_StringHash __pyx_v_hashed, int __pyx_v_split, size_t __pyx_v_length) {
struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_v_word;
PyObject *__pyx_v_tail_string = 0;
PyObject *__pyx_v_lex = 0;
PyObject *__pyx_v_normed = 0;
PyObject *__pyx_v_last3 = 0;
struct __pyx_t_5spacy_6lexeme_Lexeme *__pyx_r;
__Pyx_RefNannyDeclarations
long __pyx_t_1;
int __pyx_t_2;
Py_UCS4 __pyx_t_3;
int __pyx_t_4;
int __pyx_t_5;
PyObject *__pyx_t_6 = NULL;
Py_ssize_t __pyx_t_7;
__pyx_t_5spacy_5spacy_StringHash __pyx_t_8;
__pyx_t_5spacy_5spacy_Lexeme_addr __pyx_t_9;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("init_lexeme", 0);
/* "spacy/lexeme.pyx":19
* unicode string, StringHash hashed,
* int split, size_t length) except NULL:
* assert split <= length # <<<<<<<<<<<<<<
* cdef Lexeme* word = <Lexeme*>calloc(1, sizeof(Lexeme))
*
*/
#ifndef CYTHON_WITHOUT_ASSERTIONS
if (unlikely(!Py_OptimizeFlag)) {
if (unlikely(!((__pyx_v_split <= __pyx_v_length) != 0))) {
PyErr_SetNone(PyExc_AssertionError);
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 19; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
}
}
#endif
/* "spacy/lexeme.pyx":20
* int split, size_t length) except NULL:
* assert split <= length
* cdef Lexeme* word = <Lexeme*>calloc(1, sizeof(Lexeme)) # <<<<<<<<<<<<<<
*
* word.first = <Py_UNICODE>(string[0] if string else 0)
*/
__pyx_v_word = ((struct __pyx_t_5spacy_6lexeme_Lexeme *)calloc(1, (sizeof(struct __pyx_t_5spacy_6lexeme_Lexeme))));
/* "spacy/lexeme.pyx":22
* cdef Lexeme* word = <Lexeme*>calloc(1, sizeof(Lexeme))
*
* word.first = <Py_UNICODE>(string[0] if string else 0) # <<<<<<<<<<<<<<
* word.sic = hashed
*
*/
__pyx_t_2 = (__pyx_v_string != Py_None) && (PyUnicode_GET_SIZE(__pyx_v_string) != 0);
if (__pyx_t_2) {
__pyx_t_3 = __Pyx_GetItemInt_Unicode(__pyx_v_string, 0, long, 1, __Pyx_PyInt_From_long, 0, 0, 1); if (unlikely(__pyx_t_3 == (Py_UCS4)-1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 22; __pyx_clineno = __LINE__; goto __pyx_L1_error;};
__pyx_t_1 = __pyx_t_3;
} else {
__pyx_t_1 = 0;
}
__pyx_v_word->first = ((Py_UNICODE)__pyx_t_1);
/* "spacy/lexeme.pyx":23
*
* word.first = <Py_UNICODE>(string[0] if string else 0)
* word.sic = hashed # <<<<<<<<<<<<<<
*
* cdef unicode tail_string
*/
__pyx_v_word->sic = __pyx_v_hashed;
/* "spacy/lexeme.pyx":27
* cdef unicode tail_string
* cdef unicode lex
* if split != 0 and split < length: # <<<<<<<<<<<<<<
* lex = substr(string, 0, split, length)
* tail_string = substr(string, split, length, length)
*/
__pyx_t_2 = ((__pyx_v_split != 0) != 0);
if (__pyx_t_2) {
__pyx_t_4 = ((__pyx_v_split < __pyx_v_length) != 0);
__pyx_t_5 = __pyx_t_4;
} else {
__pyx_t_5 = __pyx_t_2;
}
if (__pyx_t_5) {
/* "spacy/lexeme.pyx":28
* cdef unicode lex
* if split != 0 and split < length:
* lex = substr(string, 0, split, length) # <<<<<<<<<<<<<<
* tail_string = substr(string, split, length, length)
* else:
*/
__pyx_t_6 = __pyx_f_5spacy_12string_tools_substr(__pyx_v_string, 0, __pyx_v_split, __pyx_v_length, 0); if (unlikely(!__pyx_t_6)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 28; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__Pyx_GOTREF(__pyx_t_6);
__pyx_v_lex = ((PyObject*)__pyx_t_6);
__pyx_t_6 = 0;
/* "spacy/lexeme.pyx":29
* if split != 0 and split < length:
* lex = substr(string, 0, split, length)
* tail_string = substr(string, split, length, length) # <<<<<<<<<<<<<<
* else:
* lex = string
*/
__pyx_t_6 = __pyx_f_5spacy_12string_tools_substr(__pyx_v_string, __pyx_v_split, __pyx_v_length, __pyx_v_length, 0); if (unlikely(!__pyx_t_6)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 29; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__Pyx_GOTREF(__pyx_t_6);
__pyx_v_tail_string = ((PyObject*)__pyx_t_6);
__pyx_t_6 = 0;
goto __pyx_L3;
}
/*else*/ {
/* "spacy/lexeme.pyx":31
* tail_string = substr(string, split, length, length)
* else:
* lex = string # <<<<<<<<<<<<<<
* tail_string = ''
* assert lex
*/
__Pyx_INCREF(__pyx_v_string);
__pyx_v_lex = __pyx_v_string;
/* "spacy/lexeme.pyx":32
* else:
* lex = string
* tail_string = '' # <<<<<<<<<<<<<<
* assert lex
* #cdef unicode normed = normalize_word_string(lex)
*/
__Pyx_INCREF(__pyx_kp_u_);
__pyx_v_tail_string = __pyx_kp_u_;
}
__pyx_L3:;
/* "spacy/lexeme.pyx":33
* lex = string
* tail_string = ''
* assert lex # <<<<<<<<<<<<<<
* #cdef unicode normed = normalize_word_string(lex)
* cdef unicode normed = '?'
*/
#ifndef CYTHON_WITHOUT_ASSERTIONS
if (unlikely(!Py_OptimizeFlag)) {
__pyx_t_5 = (__pyx_v_lex != Py_None) && (PyUnicode_GET_SIZE(__pyx_v_lex) != 0);
if (unlikely(!__pyx_t_5)) {
PyErr_SetNone(PyExc_AssertionError);
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 33; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
}
}
#endif
/* "spacy/lexeme.pyx":35
* assert lex
* #cdef unicode normed = normalize_word_string(lex)
* cdef unicode normed = '?' # <<<<<<<<<<<<<<
* cdef unicode last3 = substr(string, length - 3, length, length)
*
*/
__Pyx_INCREF(__pyx_kp_u__2);
__pyx_v_normed = __pyx_kp_u__2;
/* "spacy/lexeme.pyx":36
* #cdef unicode normed = normalize_word_string(lex)
* cdef unicode normed = '?'
* cdef unicode last3 = substr(string, length - 3, length, length) # <<<<<<<<<<<<<<
*
* assert normed
*/
__pyx_t_6 = __pyx_f_5spacy_12string_tools_substr(__pyx_v_string, (__pyx_v_length - 3), __pyx_v_length, __pyx_v_length, 0); if (unlikely(!__pyx_t_6)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 36; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__Pyx_GOTREF(__pyx_t_6);
__pyx_v_last3 = ((PyObject*)__pyx_t_6);
__pyx_t_6 = 0;
/* "spacy/lexeme.pyx":38
* cdef unicode last3 = substr(string, length - 3, length, length)
*
* assert normed # <<<<<<<<<<<<<<
* assert len(normed)
*
*/
#ifndef CYTHON_WITHOUT_ASSERTIONS
if (unlikely(!Py_OptimizeFlag)) {
__pyx_t_5 = (__pyx_v_normed != Py_None) && (PyUnicode_GET_SIZE(__pyx_v_normed) != 0);
if (unlikely(!__pyx_t_5)) {
PyErr_SetNone(PyExc_AssertionError);
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 38; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
}
}
#endif
/* "spacy/lexeme.pyx":39
*
* assert normed
* assert len(normed) # <<<<<<<<<<<<<<
*
* word.lex = hash_string(lex, len(lex))
*/
#ifndef CYTHON_WITHOUT_ASSERTIONS
if (unlikely(!Py_OptimizeFlag)) {
__pyx_t_7 = __Pyx_PyUnicode_GET_LENGTH(__pyx_v_normed); if (unlikely(__pyx_t_7 == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 39; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
if (unlikely(!(__pyx_t_7 != 0))) {
PyErr_SetNone(PyExc_AssertionError);
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 39; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
}
}
#endif
/* "spacy/lexeme.pyx":41
* assert len(normed)
*
* word.lex = hash_string(lex, len(lex)) # <<<<<<<<<<<<<<
* word.normed = hash_string(normed, len(normed))
* word.last3 = hash_string(last3, len(last3))
*/
if (unlikely(__pyx_v_lex == Py_None)) {
PyErr_SetString(PyExc_TypeError, "object of type 'NoneType' has no len()");
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 41; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
}
__pyx_t_7 = __Pyx_PyUnicode_GET_LENGTH(__pyx_v_lex); if (unlikely(__pyx_t_7 == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 41; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_t_8 = __pyx_f_5spacy_5spacy_hash_string(__pyx_v_lex, __pyx_t_7); if (unlikely(__pyx_t_8 == 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 41; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_v_word->lex = __pyx_t_8;
/* "spacy/lexeme.pyx":42
*
* word.lex = hash_string(lex, len(lex))
* word.normed = hash_string(normed, len(normed)) # <<<<<<<<<<<<<<
* word.last3 = hash_string(last3, len(last3))
*
*/
__pyx_t_7 = __Pyx_PyUnicode_GET_LENGTH(__pyx_v_normed); if (unlikely(__pyx_t_7 == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 42; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_t_8 = __pyx_f_5spacy_5spacy_hash_string(__pyx_v_normed, __pyx_t_7); if (unlikely(__pyx_t_8 == 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 42; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_v_word->normed = __pyx_t_8;
/* "spacy/lexeme.pyx":43
* word.lex = hash_string(lex, len(lex))
* word.normed = hash_string(normed, len(normed))
* word.last3 = hash_string(last3, len(last3)) # <<<<<<<<<<<<<<
*
* bacov[word.lex] = lex
*/
if (unlikely(__pyx_v_last3 == Py_None)) {
PyErr_SetString(PyExc_TypeError, "object of type 'NoneType' has no len()");
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 43; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
}
__pyx_t_7 = __Pyx_PyUnicode_GET_LENGTH(__pyx_v_last3); if (unlikely(__pyx_t_7 == -1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 43; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_t_8 = __pyx_f_5spacy_5spacy_hash_string(__pyx_v_last3, __pyx_t_7); if (unlikely(__pyx_t_8 == 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 43; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_v_word->last3 = __pyx_t_8;
/* "spacy/lexeme.pyx":45
* word.last3 = hash_string(last3, len(last3))
*
* bacov[word.lex] = lex # <<<<<<<<<<<<<<
* bacov[word.normed] = normed
* bacov[word.last3] = last3
*/
if (unlikely(__pyx_v_bacov == Py_None)) {
PyErr_SetString(PyExc_TypeError, "'NoneType' object is not subscriptable");
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 45; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
}
__pyx_t_6 = __Pyx_PyInt_From_uint64_t(__pyx_v_word->lex); if (unlikely(!__pyx_t_6)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 45; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__Pyx_GOTREF(__pyx_t_6);
if (unlikely(PyDict_SetItem(__pyx_v_bacov, __pyx_t_6, __pyx_v_lex) < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 45; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0;
/* "spacy/lexeme.pyx":46
*
* bacov[word.lex] = lex
* bacov[word.normed] = normed # <<<<<<<<<<<<<<
* bacov[word.last3] = last3
*
*/
if (unlikely(__pyx_v_bacov == Py_None)) {
PyErr_SetString(PyExc_TypeError, "'NoneType' object is not subscriptable");
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 46; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
}
__pyx_t_6 = __Pyx_PyInt_From_uint64_t(__pyx_v_word->normed); if (unlikely(!__pyx_t_6)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 46; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__Pyx_GOTREF(__pyx_t_6);
if (unlikely(PyDict_SetItem(__pyx_v_bacov, __pyx_t_6, __pyx_v_normed) < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 46; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0;
/* "spacy/lexeme.pyx":47
* bacov[word.lex] = lex
* bacov[word.normed] = normed
* bacov[word.last3] = last3 # <<<<<<<<<<<<<<
*
* # These are loaded later
*/
if (unlikely(__pyx_v_bacov == Py_None)) {
PyErr_SetString(PyExc_TypeError, "'NoneType' object is not subscriptable");
{__pyx_filename = __pyx_f[0]; __pyx_lineno = 47; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
}
__pyx_t_6 = __Pyx_PyInt_From_uint64_t(__pyx_v_word->last3); if (unlikely(!__pyx_t_6)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 47; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__Pyx_GOTREF(__pyx_t_6);
if (unlikely(PyDict_SetItem(__pyx_v_bacov, __pyx_t_6, __pyx_v_last3) < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 47; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__Pyx_DECREF(__pyx_t_6); __pyx_t_6 = 0;
/* "spacy/lexeme.pyx":50
*
* # These are loaded later
* word.prob = 0 # <<<<<<<<<<<<<<
* word.cluster = 0
* word.oft_upper = False
*/
__pyx_v_word->prob = 0.0;
/* "spacy/lexeme.pyx":51
* # These are loaded later
* word.prob = 0
* word.cluster = 0 # <<<<<<<<<<<<<<
* word.oft_upper = False
* word.oft_title = False
*/
__pyx_v_word->cluster = 0;
/* "spacy/lexeme.pyx":52
* word.prob = 0
* word.cluster = 0
* word.oft_upper = False # <<<<<<<<<<<<<<
* word.oft_title = False
*
*/
__pyx_v_word->oft_upper = 0;
/* "spacy/lexeme.pyx":53
* word.cluster = 0
* word.oft_upper = False
* word.oft_title = False # <<<<<<<<<<<<<<
*
* # Now recurse, and deal with the tail
*/
__pyx_v_word->oft_title = 0;
/* "spacy/lexeme.pyx":56
*
* # Now recurse, and deal with the tail
* if tail_string: # <<<<<<<<<<<<<<
* word.tail = <Lexeme*>lookup(vocab, bacov, find_split, -1, tail_string)
* return word
*/
__pyx_t_5 = (__pyx_v_tail_string != Py_None) && (PyUnicode_GET_SIZE(__pyx_v_tail_string) != 0);
if (__pyx_t_5) {
/* "spacy/lexeme.pyx":57
* # Now recurse, and deal with the tail
* if tail_string:
* word.tail = <Lexeme*>lookup(vocab, bacov, find_split, -1, tail_string) # <<<<<<<<<<<<<<
* return word
*
*/
__pyx_t_9 = __pyx_f_5spacy_5spacy_lookup(__pyx_v_vocab, __pyx_v_bacov, __pyx_v_find_split, -1, __pyx_v_tail_string); if (unlikely(__pyx_t_9 == 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 57; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_v_word->tail = ((struct __pyx_t_5spacy_6lexeme_Lexeme *)__pyx_t_9);
goto __pyx_L4;
}
__pyx_L4:;
/* "spacy/lexeme.pyx":58
* if tail_string:
* word.tail = <Lexeme*>lookup(vocab, bacov, find_split, -1, tail_string)
* return word # <<<<<<<<<<<<<<
*
*
*/
__pyx_r = __pyx_v_word;
goto __pyx_L0;
/* "spacy/lexeme.pyx":16
*
*
* cdef Lexeme* init_lexeme(Vocab vocab, dict bacov, Splitter find_split, # <<<<<<<<<<<<<<
* unicode string, StringHash hashed,
* int split, size_t length) except NULL:
*/
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_6);
__Pyx_AddTraceback("spacy.lexeme.init_lexeme", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = NULL;
__pyx_L0:;
__Pyx_XDECREF(__pyx_v_tail_string);
__Pyx_XDECREF(__pyx_v_lex);
__Pyx_XDECREF(__pyx_v_normed);
__Pyx_XDECREF(__pyx_v_last3);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
/* "spacy/lexeme.pyx":61
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef StringHash sic_of(size_t lex_id) except 0: # <<<<<<<<<<<<<<
* '''Access the `sic' field of the Lexeme pointed to by lex_id.
*
*/
static PyObject *__pyx_pw_5spacy_6lexeme_1sic_of(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id); /*proto*/
static __pyx_t_5spacy_6lexeme_StringHash __pyx_f_5spacy_6lexeme_sic_of(size_t __pyx_v_lex_id, CYTHON_UNUSED int __pyx_skip_dispatch) {
__pyx_t_5spacy_6lexeme_StringHash __pyx_r;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("sic_of", 0);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":70
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* [u'Hi!', u'', u'world]
* '''
* return (<Lexeme*>lex_id).sic # <<<<<<<<<<<<<<
*
*
*/
__pyx_r = ((struct __pyx_t_5spacy_6lexeme_Lexeme *)__pyx_v_lex_id)->sic;
goto __pyx_L0;
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":61
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef StringHash sic_of(size_t lex_id) except 0: # <<<<<<<<<<<<<<
* '''Access the `sic' field of the Lexeme pointed to by lex_id.
*
*/
/* function exit code */
__pyx_L0:;
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
/* Python wrapper */
static PyObject *__pyx_pw_5spacy_6lexeme_1sic_of(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id); /*proto*/
static char __pyx_doc_5spacy_6lexeme_sic_of[] = "Access the `sic' field of the Lexeme pointed to by lex_id.\n \n The sic field stores the hash of the whitespace-delimited string-chunk used to\n construct the Lexeme.\n \n >>> [unhash(sic_of(lex_id)) for lex_id in from_string(u'Hi! world')]\n [u'Hi!', u'', u'world]\n ";
static PyObject *__pyx_pw_5spacy_6lexeme_1sic_of(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id) {
size_t __pyx_v_lex_id;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
PyObject *__pyx_r = 0;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("sic_of (wrapper)", 0);
assert(__pyx_arg_lex_id); {
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
__pyx_v_lex_id = __Pyx_PyInt_As_size_t(__pyx_arg_lex_id); if (unlikely((__pyx_v_lex_id == (size_t)-1) && PyErr_Occurred())) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 61; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
goto __pyx_L4_argument_unpacking_done;
__pyx_L3_error:;
__Pyx_AddTraceback("spacy.lexeme.sic_of", __pyx_clineno, __pyx_lineno, __pyx_filename);
__Pyx_RefNannyFinishContext();
return NULL;
__pyx_L4_argument_unpacking_done:;
__pyx_r = __pyx_pf_5spacy_6lexeme_sic_of(__pyx_self, ((size_t)__pyx_v_lex_id));
/* function exit code */
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
static PyObject *__pyx_pf_5spacy_6lexeme_sic_of(CYTHON_UNUSED PyObject *__pyx_self, size_t __pyx_v_lex_id) {
PyObject *__pyx_r = NULL;
__Pyx_RefNannyDeclarations
__pyx_t_5spacy_6lexeme_StringHash __pyx_t_1;
PyObject *__pyx_t_2 = NULL;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("sic_of", 0);
__Pyx_XDECREF(__pyx_r);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
__pyx_t_1 = __pyx_f_5spacy_6lexeme_sic_of(__pyx_v_lex_id, 0); if (unlikely(__pyx_t_1 == 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 61; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_t_2 = __Pyx_PyInt_From_uint64_t(__pyx_t_1); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 61; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_2);
__pyx_r = __pyx_t_2;
__pyx_t_2 = 0;
goto __pyx_L0;
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_2);
__Pyx_AddTraceback("spacy.lexeme.sic_of", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = NULL;
__pyx_L0:;
__Pyx_XGIVEREF(__pyx_r);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":73
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef StringHash lex_of(size_t lex_id) except 0: # <<<<<<<<<<<<<<
* '''Access the `lex' field of the Lexeme pointed to by lex_id.
*
*/
static PyObject *__pyx_pw_5spacy_6lexeme_3lex_of(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id); /*proto*/
static __pyx_t_5spacy_6lexeme_StringHash __pyx_f_5spacy_6lexeme_lex_of(size_t __pyx_v_lex_id, CYTHON_UNUSED int __pyx_skip_dispatch) {
__pyx_t_5spacy_6lexeme_StringHash __pyx_r;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("lex_of", 0);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":84
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* [u'Hi', u'!', u'world']
* '''
* return (<Lexeme*>lex_id).lex # <<<<<<<<<<<<<<
*
*
*/
__pyx_r = ((struct __pyx_t_5spacy_6lexeme_Lexeme *)__pyx_v_lex_id)->lex;
goto __pyx_L0;
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":73
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef StringHash lex_of(size_t lex_id) except 0: # <<<<<<<<<<<<<<
* '''Access the `lex' field of the Lexeme pointed to by lex_id.
*
*/
/* function exit code */
__pyx_L0:;
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
/* Python wrapper */
static PyObject *__pyx_pw_5spacy_6lexeme_3lex_of(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id); /*proto*/
static char __pyx_doc_5spacy_6lexeme_2lex_of[] = "Access the `lex' field of the Lexeme pointed to by lex_id.\n\n The lex field is the hash of the string you would expect to get back from\n a standard tokenizer, i.e. the word with punctuation and other non-whitespace\n delimited tokens split off. The other fields refer to properties of the\n string that the lex field stores a hash of, except sic and tail.\n\n >>> [unhash(lex_of(lex_id) for lex_id in from_string(u'Hi! world')]\n [u'Hi', u'!', u'world']\n ";
static PyObject *__pyx_pw_5spacy_6lexeme_3lex_of(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id) {
size_t __pyx_v_lex_id;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
PyObject *__pyx_r = 0;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("lex_of (wrapper)", 0);
assert(__pyx_arg_lex_id); {
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
__pyx_v_lex_id = __Pyx_PyInt_As_size_t(__pyx_arg_lex_id); if (unlikely((__pyx_v_lex_id == (size_t)-1) && PyErr_Occurred())) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 73; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
goto __pyx_L4_argument_unpacking_done;
__pyx_L3_error:;
__Pyx_AddTraceback("spacy.lexeme.lex_of", __pyx_clineno, __pyx_lineno, __pyx_filename);
__Pyx_RefNannyFinishContext();
return NULL;
__pyx_L4_argument_unpacking_done:;
__pyx_r = __pyx_pf_5spacy_6lexeme_2lex_of(__pyx_self, ((size_t)__pyx_v_lex_id));
/* function exit code */
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
static PyObject *__pyx_pf_5spacy_6lexeme_2lex_of(CYTHON_UNUSED PyObject *__pyx_self, size_t __pyx_v_lex_id) {
PyObject *__pyx_r = NULL;
__Pyx_RefNannyDeclarations
__pyx_t_5spacy_6lexeme_StringHash __pyx_t_1;
PyObject *__pyx_t_2 = NULL;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannySetupContext("lex_of", 0);
__Pyx_XDECREF(__pyx_r);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
__pyx_t_1 = __pyx_f_5spacy_6lexeme_lex_of(__pyx_v_lex_id, 0); if (unlikely(__pyx_t_1 == 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 73; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_t_2 = __Pyx_PyInt_From_uint64_t(__pyx_t_1); if (unlikely(!__pyx_t_2)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 73; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_2);
__pyx_r = __pyx_t_2;
__pyx_t_2 = 0;
goto __pyx_L0;
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_2);
__Pyx_AddTraceback("spacy.lexeme.lex_of", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = NULL;
__pyx_L0:;
__Pyx_XGIVEREF(__pyx_r);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":87
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef ClusterID cluster_of(size_t lex_id): # <<<<<<<<<<<<<<
* '''Access the `cluster' field of the Lexeme pointed to by lex_id, which
* gives an integer representation of the cluster ID of the word,
*/
static PyObject *__pyx_pw_5spacy_6lexeme_5cluster_of(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id); /*proto*/
static __pyx_t_5spacy_6lexeme_ClusterID __pyx_f_5spacy_6lexeme_cluster_of(size_t __pyx_v_lex_id, CYTHON_UNUSED int __pyx_skip_dispatch) {
__pyx_t_5spacy_6lexeme_ClusterID __pyx_r;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("cluster_of", 0);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":103
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* the same cluster ID as "pineapple", which is not what we'd like.
* '''
* return (<Lexeme*>lex_id).cluster # <<<<<<<<<<<<<<
*
*
*/
__pyx_r = ((struct __pyx_t_5spacy_6lexeme_Lexeme *)__pyx_v_lex_id)->cluster;
goto __pyx_L0;
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":87
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef ClusterID cluster_of(size_t lex_id): # <<<<<<<<<<<<<<
* '''Access the `cluster' field of the Lexeme pointed to by lex_id, which
* gives an integer representation of the cluster ID of the word,
*/
/* function exit code */
__pyx_L0:;
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
/* Python wrapper */
static PyObject *__pyx_pw_5spacy_6lexeme_5cluster_of(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id); /*proto*/
static char __pyx_doc_5spacy_6lexeme_4cluster_of[] = "Access the `cluster' field of the Lexeme pointed to by lex_id, which\n gives an integer representation of the cluster ID of the word, \n which should be understood as a binary address:\n\n >>> strings = (u'pineapple', u'apple', u'dapple', u'scalable')\n >>> token_ids = [lookup(s) for s in strings]\n >>> clusters = [cluster_of(t) for t in token_ids]\n >>> print [\"{0:b\"} % cluster_of(t) for t in token_ids]\n [\"100111110110\", \"100111100100\", \"01010111011001\", \"100111110110\"]\n\n The clusterings are unideal, but often slightly useful.\n \"pineapple\" and \"apple\" share a long prefix, indicating a similar meaning,\n while \"dapple\" is totally different. On the other hand, \"scalable\" receives\n the same cluster ID as \"pineapple\", which is not what we'd like.\n ";
static PyObject *__pyx_pw_5spacy_6lexeme_5cluster_of(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id) {
size_t __pyx_v_lex_id;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
PyObject *__pyx_r = 0;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("cluster_of (wrapper)", 0);
assert(__pyx_arg_lex_id); {
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
__pyx_v_lex_id = __Pyx_PyInt_As_size_t(__pyx_arg_lex_id); if (unlikely((__pyx_v_lex_id == (size_t)-1) && PyErr_Occurred())) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 87; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
goto __pyx_L4_argument_unpacking_done;
__pyx_L3_error:;
__Pyx_AddTraceback("spacy.lexeme.cluster_of", __pyx_clineno, __pyx_lineno, __pyx_filename);
__Pyx_RefNannyFinishContext();
return NULL;
__pyx_L4_argument_unpacking_done:;
__pyx_r = __pyx_pf_5spacy_6lexeme_4cluster_of(__pyx_self, ((size_t)__pyx_v_lex_id));
/* function exit code */
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
static PyObject *__pyx_pf_5spacy_6lexeme_4cluster_of(CYTHON_UNUSED PyObject *__pyx_self, size_t __pyx_v_lex_id) {
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("cluster_of", 0);
__Pyx_XDECREF(__pyx_r);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
__pyx_t_1 = __Pyx_PyInt_From_int(__pyx_f_5spacy_6lexeme_cluster_of(__pyx_v_lex_id, 0)); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 87; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_1);
__pyx_r = __pyx_t_1;
__pyx_t_1 = 0;
goto __pyx_L0;
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_1);
__Pyx_AddTraceback("spacy.lexeme.cluster_of", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = NULL;
__pyx_L0:;
__Pyx_XGIVEREF(__pyx_r);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":106
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef Py_UNICODE first_of(size_t lex_id): # <<<<<<<<<<<<<<
* '''Access the `first' field of the Lexeme pointed to by lex_id, which
* stores the first character of the lex string of the word.
*/
static PyObject *__pyx_pw_5spacy_6lexeme_7first_of(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id); /*proto*/
static Py_UNICODE __pyx_f_5spacy_6lexeme_first_of(size_t __pyx_v_lex_id, CYTHON_UNUSED int __pyx_skip_dispatch) {
Py_UNICODE __pyx_r;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("first_of", 0);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":114
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* u'H'
* '''
* return (<Lexeme*>lex_id).first # <<<<<<<<<<<<<<
*
*
*/
__pyx_r = ((struct __pyx_t_5spacy_6lexeme_Lexeme *)__pyx_v_lex_id)->first;
goto __pyx_L0;
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":106
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef Py_UNICODE first_of(size_t lex_id): # <<<<<<<<<<<<<<
* '''Access the `first' field of the Lexeme pointed to by lex_id, which
* stores the first character of the lex string of the word.
*/
/* function exit code */
__pyx_L0:;
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
/* Python wrapper */
static PyObject *__pyx_pw_5spacy_6lexeme_7first_of(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id); /*proto*/
static char __pyx_doc_5spacy_6lexeme_6first_of[] = "Access the `first' field of the Lexeme pointed to by lex_id, which\n stores the first character of the lex string of the word.\n\n >>> lex_id = lookup(u'Hello')\n >>> unhash(first_of(lex_id))\n u'H'\n ";
static PyObject *__pyx_pw_5spacy_6lexeme_7first_of(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id) {
size_t __pyx_v_lex_id;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
PyObject *__pyx_r = 0;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("first_of (wrapper)", 0);
assert(__pyx_arg_lex_id); {
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
__pyx_v_lex_id = __Pyx_PyInt_As_size_t(__pyx_arg_lex_id); if (unlikely((__pyx_v_lex_id == (size_t)-1) && PyErr_Occurred())) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 106; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
goto __pyx_L4_argument_unpacking_done;
__pyx_L3_error:;
__Pyx_AddTraceback("spacy.lexeme.first_of", __pyx_clineno, __pyx_lineno, __pyx_filename);
__Pyx_RefNannyFinishContext();
return NULL;
__pyx_L4_argument_unpacking_done:;
__pyx_r = __pyx_pf_5spacy_6lexeme_6first_of(__pyx_self, ((size_t)__pyx_v_lex_id));
/* function exit code */
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
static PyObject *__pyx_pf_5spacy_6lexeme_6first_of(CYTHON_UNUSED PyObject *__pyx_self, size_t __pyx_v_lex_id) {
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("first_of", 0);
__Pyx_XDECREF(__pyx_r);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
__pyx_t_1 = PyUnicode_FromOrdinal(__pyx_f_5spacy_6lexeme_first_of(__pyx_v_lex_id, 0)); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 106; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_1);
__pyx_r = __pyx_t_1;
__pyx_t_1 = 0;
goto __pyx_L0;
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_1);
__Pyx_AddTraceback("spacy.lexeme.first_of", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = NULL;
__pyx_L0:;
__Pyx_XGIVEREF(__pyx_r);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":117
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef double prob_of(size_t lex_id): # <<<<<<<<<<<<<<
* '''Access the `prob' field of the Lexeme pointed to by lex_id, which stores
* the smoothed unigram log probability of the word, as estimated from a large
*/
static PyObject *__pyx_pw_5spacy_6lexeme_9prob_of(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id); /*proto*/
static double __pyx_f_5spacy_6lexeme_prob_of(CYTHON_UNUSED size_t __pyx_v_lex_id, CYTHON_UNUSED int __pyx_skip_dispatch) {
double __pyx_r;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("prob_of", 0);
/* function exit code */
__pyx_r = 0;
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
/* Python wrapper */
static PyObject *__pyx_pw_5spacy_6lexeme_9prob_of(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id); /*proto*/
static char __pyx_doc_5spacy_6lexeme_8prob_of[] = "Access the `prob' field of the Lexeme pointed to by lex_id, which stores\n the smoothed unigram log probability of the word, as estimated from a large\n text corpus. By default, probabilities are based on counts from Gigaword,\n smoothed using Knesser-Ney; but any probabilities file can be supplied to\n load_probs.\n \n >>> prob_of(lookup(u'world'))\n -20.10340371976182\n ";
static PyObject *__pyx_pw_5spacy_6lexeme_9prob_of(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id) {
size_t __pyx_v_lex_id;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
PyObject *__pyx_r = 0;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("prob_of (wrapper)", 0);
assert(__pyx_arg_lex_id); {
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
__pyx_v_lex_id = __Pyx_PyInt_As_size_t(__pyx_arg_lex_id); if (unlikely((__pyx_v_lex_id == (size_t)-1) && PyErr_Occurred())) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 117; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
goto __pyx_L4_argument_unpacking_done;
__pyx_L3_error:;
__Pyx_AddTraceback("spacy.lexeme.prob_of", __pyx_clineno, __pyx_lineno, __pyx_filename);
__Pyx_RefNannyFinishContext();
return NULL;
__pyx_L4_argument_unpacking_done:;
__pyx_r = __pyx_pf_5spacy_6lexeme_8prob_of(__pyx_self, ((size_t)__pyx_v_lex_id));
/* function exit code */
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
static PyObject *__pyx_pf_5spacy_6lexeme_8prob_of(CYTHON_UNUSED PyObject *__pyx_self, size_t __pyx_v_lex_id) {
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("prob_of", 0);
__Pyx_XDECREF(__pyx_r);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
__pyx_t_1 = PyFloat_FromDouble(__pyx_f_5spacy_6lexeme_prob_of(__pyx_v_lex_id, 0)); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 117; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_1);
__pyx_r = __pyx_t_1;
__pyx_t_1 = 0;
goto __pyx_L0;
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_1);
__Pyx_AddTraceback("spacy.lexeme.prob_of", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = NULL;
__pyx_L0:;
__Pyx_XGIVEREF(__pyx_r);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":130
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef StringHash last3_of(size_t lex_id): # <<<<<<<<<<<<<<
* '''Access the `last3' field of the Lexeme pointed to by lex_id, which stores
* the hash of the last three characters of the word:
*/
static PyObject *__pyx_pw_5spacy_6lexeme_11last3_of(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id); /*proto*/
static __pyx_t_5spacy_6lexeme_StringHash __pyx_f_5spacy_6lexeme_last3_of(size_t __pyx_v_lex_id, CYTHON_UNUSED int __pyx_skip_dispatch) {
__pyx_t_5spacy_6lexeme_StringHash __pyx_r;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("last3_of", 0);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":138
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* [u'llo', u'!']
* '''
* return (<Lexeme*>lex_id).last3 # <<<<<<<<<<<<<<
*
*
*/
__pyx_r = ((struct __pyx_t_5spacy_6lexeme_Lexeme *)__pyx_v_lex_id)->last3;
goto __pyx_L0;
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":130
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef StringHash last3_of(size_t lex_id): # <<<<<<<<<<<<<<
* '''Access the `last3' field of the Lexeme pointed to by lex_id, which stores
* the hash of the last three characters of the word:
*/
/* function exit code */
__pyx_L0:;
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
/* Python wrapper */
static PyObject *__pyx_pw_5spacy_6lexeme_11last3_of(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id); /*proto*/
static char __pyx_doc_5spacy_6lexeme_10last3_of[] = "Access the `last3' field of the Lexeme pointed to by lex_id, which stores\n the hash of the last three characters of the word:\n\n >>> lex_ids = [lookup(w) for w in (u'Hello', u'!')]\n >>> [unhash(last3_of(lex_id)) for lex_id in lex_ids]\n [u'llo', u'!']\n ";
static PyObject *__pyx_pw_5spacy_6lexeme_11last3_of(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id) {
size_t __pyx_v_lex_id;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
PyObject *__pyx_r = 0;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("last3_of (wrapper)", 0);
assert(__pyx_arg_lex_id); {
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
__pyx_v_lex_id = __Pyx_PyInt_As_size_t(__pyx_arg_lex_id); if (unlikely((__pyx_v_lex_id == (size_t)-1) && PyErr_Occurred())) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 130; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
goto __pyx_L4_argument_unpacking_done;
__pyx_L3_error:;
__Pyx_AddTraceback("spacy.lexeme.last3_of", __pyx_clineno, __pyx_lineno, __pyx_filename);
__Pyx_RefNannyFinishContext();
return NULL;
__pyx_L4_argument_unpacking_done:;
__pyx_r = __pyx_pf_5spacy_6lexeme_10last3_of(__pyx_self, ((size_t)__pyx_v_lex_id));
/* function exit code */
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
static PyObject *__pyx_pf_5spacy_6lexeme_10last3_of(CYTHON_UNUSED PyObject *__pyx_self, size_t __pyx_v_lex_id) {
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("last3_of", 0);
__Pyx_XDECREF(__pyx_r);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
__pyx_t_1 = __Pyx_PyInt_From_uint64_t(__pyx_f_5spacy_6lexeme_last3_of(__pyx_v_lex_id, 0)); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 130; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_1);
__pyx_r = __pyx_t_1;
__pyx_t_1 = 0;
goto __pyx_L0;
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_1);
__Pyx_AddTraceback("spacy.lexeme.last3_of", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = NULL;
__pyx_L0:;
__Pyx_XGIVEREF(__pyx_r);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":141
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef bint is_oft_upper(size_t lex_id): # <<<<<<<<<<<<<<
* '''Access the `oft_upper' field of the Lexeme pointed to by lex_id, which
* stores whether the lowered version of the string hashed by `lex' is found
*/
static PyObject *__pyx_pw_5spacy_6lexeme_13is_oft_upper(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id); /*proto*/
static int __pyx_f_5spacy_6lexeme_is_oft_upper(size_t __pyx_v_lex_id, CYTHON_UNUSED int __pyx_skip_dispatch) {
int __pyx_r;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("is_oft_upper", 0);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":153
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* True
* '''
* return (<Lexeme*>lex_id).oft_upper # <<<<<<<<<<<<<<
*
*
*/
__pyx_r = ((struct __pyx_t_5spacy_6lexeme_Lexeme *)__pyx_v_lex_id)->oft_upper;
goto __pyx_L0;
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":141
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef bint is_oft_upper(size_t lex_id): # <<<<<<<<<<<<<<
* '''Access the `oft_upper' field of the Lexeme pointed to by lex_id, which
* stores whether the lowered version of the string hashed by `lex' is found
*/
/* function exit code */
__pyx_L0:;
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
/* Python wrapper */
static PyObject *__pyx_pw_5spacy_6lexeme_13is_oft_upper(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id); /*proto*/
static char __pyx_doc_5spacy_6lexeme_12is_oft_upper[] = "Access the `oft_upper' field of the Lexeme pointed to by lex_id, which\n stores whether the lowered version of the string hashed by `lex' is found\n in all-upper case frequently in a large sample of text. Users are free\n to load different data, by default we use a sample from Wikipedia, with\n a threshold of 0.95, picked to maximize mutual information for POS tagging.\n\n >>> is_oft_upper(lookup(u'abc'))\n True\n >>> is_oft_upper(lookup(u'aBc')) # This must get the same answer\n True\n ";
static PyObject *__pyx_pw_5spacy_6lexeme_13is_oft_upper(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id) {
size_t __pyx_v_lex_id;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
PyObject *__pyx_r = 0;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("is_oft_upper (wrapper)", 0);
assert(__pyx_arg_lex_id); {
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
__pyx_v_lex_id = __Pyx_PyInt_As_size_t(__pyx_arg_lex_id); if (unlikely((__pyx_v_lex_id == (size_t)-1) && PyErr_Occurred())) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 141; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
goto __pyx_L4_argument_unpacking_done;
__pyx_L3_error:;
__Pyx_AddTraceback("spacy.lexeme.is_oft_upper", __pyx_clineno, __pyx_lineno, __pyx_filename);
__Pyx_RefNannyFinishContext();
return NULL;
__pyx_L4_argument_unpacking_done:;
__pyx_r = __pyx_pf_5spacy_6lexeme_12is_oft_upper(__pyx_self, ((size_t)__pyx_v_lex_id));
/* function exit code */
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
static PyObject *__pyx_pf_5spacy_6lexeme_12is_oft_upper(CYTHON_UNUSED PyObject *__pyx_self, size_t __pyx_v_lex_id) {
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("is_oft_upper", 0);
__Pyx_XDECREF(__pyx_r);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
__pyx_t_1 = __Pyx_PyBool_FromLong(__pyx_f_5spacy_6lexeme_is_oft_upper(__pyx_v_lex_id, 0)); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 141; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_1);
__pyx_r = __pyx_t_1;
__pyx_t_1 = 0;
goto __pyx_L0;
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_1);
__Pyx_AddTraceback("spacy.lexeme.is_oft_upper", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = NULL;
__pyx_L0:;
__Pyx_XGIVEREF(__pyx_r);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":156
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef bint is_oft_title(size_t lex_id): # <<<<<<<<<<<<<<
* '''Access the `oft_upper' field of the Lexeme pointed to by lex_id, which
* stores whether the lowered version of the string hashed by `lex' is found
*/
static PyObject *__pyx_pw_5spacy_6lexeme_15is_oft_title(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id); /*proto*/
static int __pyx_f_5spacy_6lexeme_is_oft_title(size_t __pyx_v_lex_id, CYTHON_UNUSED int __pyx_skip_dispatch) {
int __pyx_r;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("is_oft_title", 0);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":168
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
* True
* '''
* return (<Lexeme*>lex_id).oft_title # <<<<<<<<<<<<<<
*/
__pyx_r = ((struct __pyx_t_5spacy_6lexeme_Lexeme *)__pyx_v_lex_id)->oft_title;
goto __pyx_L0;
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
/* "spacy/lexeme.pyx":156
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
*
*
* cpdef bint is_oft_title(size_t lex_id): # <<<<<<<<<<<<<<
* '''Access the `oft_upper' field of the Lexeme pointed to by lex_id, which
* stores whether the lowered version of the string hashed by `lex' is found
*/
/* function exit code */
__pyx_L0:;
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
/* Python wrapper */
static PyObject *__pyx_pw_5spacy_6lexeme_15is_oft_title(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id); /*proto*/
static char __pyx_doc_5spacy_6lexeme_14is_oft_title[] = "Access the `oft_upper' field of the Lexeme pointed to by lex_id, which\n stores whether the lowered version of the string hashed by `lex' is found\n title-cased frequently in a large sample of text. Users are free\n to load different data, by default we use a sample from Wikipedia, with\n a threshold of 0.3, picked to maximize mutual information for POS tagging.\n\n >>> is_oft_title(lookup(u'marcus'))\n True\n >>> is_oft_title(lookup(u'MARCUS')) # This must get the same value\n True\n ";
static PyObject *__pyx_pw_5spacy_6lexeme_15is_oft_title(PyObject *__pyx_self, PyObject *__pyx_arg_lex_id) {
size_t __pyx_v_lex_id;
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
PyObject *__pyx_r = 0;
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("is_oft_title (wrapper)", 0);
assert(__pyx_arg_lex_id); {
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
__pyx_v_lex_id = __Pyx_PyInt_As_size_t(__pyx_arg_lex_id); if (unlikely((__pyx_v_lex_id == (size_t)-1) && PyErr_Occurred())) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 156; __pyx_clineno = __LINE__; goto __pyx_L3_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
}
goto __pyx_L4_argument_unpacking_done;
__pyx_L3_error:;
__Pyx_AddTraceback("spacy.lexeme.is_oft_title", __pyx_clineno, __pyx_lineno, __pyx_filename);
__Pyx_RefNannyFinishContext();
return NULL;
__pyx_L4_argument_unpacking_done:;
__pyx_r = __pyx_pf_5spacy_6lexeme_14is_oft_title(__pyx_self, ((size_t)__pyx_v_lex_id));
/* function exit code */
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
static PyObject *__pyx_pf_5spacy_6lexeme_14is_oft_title(CYTHON_UNUSED PyObject *__pyx_self, size_t __pyx_v_lex_id) {
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("is_oft_title", 0);
__Pyx_XDECREF(__pyx_r);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
__pyx_t_1 = __Pyx_PyBool_FromLong(__pyx_f_5spacy_6lexeme_is_oft_title(__pyx_v_lex_id, 0)); if (unlikely(!__pyx_t_1)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 156; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
__Pyx_GOTREF(__pyx_t_1);
__pyx_r = __pyx_t_1;
__pyx_t_1 = 0;
goto __pyx_L0;
/* function exit code */
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_1);
__Pyx_AddTraceback("spacy.lexeme.is_oft_title", __pyx_clineno, __pyx_lineno, __pyx_filename);
__pyx_r = NULL;
__pyx_L0:;
__Pyx_XGIVEREF(__pyx_r);
__Pyx_RefNannyFinishContext();
return __pyx_r;
}
static PyMethodDef __pyx_methods[] = {
{__Pyx_NAMESTR("sic_of"), (PyCFunction)__pyx_pw_5spacy_6lexeme_1sic_of, METH_O, __Pyx_DOCSTR(__pyx_doc_5spacy_6lexeme_sic_of)},
{__Pyx_NAMESTR("lex_of"), (PyCFunction)__pyx_pw_5spacy_6lexeme_3lex_of, METH_O, __Pyx_DOCSTR(__pyx_doc_5spacy_6lexeme_2lex_of)},
{__Pyx_NAMESTR("cluster_of"), (PyCFunction)__pyx_pw_5spacy_6lexeme_5cluster_of, METH_O, __Pyx_DOCSTR(__pyx_doc_5spacy_6lexeme_4cluster_of)},
{__Pyx_NAMESTR("first_of"), (PyCFunction)__pyx_pw_5spacy_6lexeme_7first_of, METH_O, __Pyx_DOCSTR(__pyx_doc_5spacy_6lexeme_6first_of)},
{__Pyx_NAMESTR("prob_of"), (PyCFunction)__pyx_pw_5spacy_6lexeme_9prob_of, METH_O, __Pyx_DOCSTR(__pyx_doc_5spacy_6lexeme_8prob_of)},
{__Pyx_NAMESTR("last3_of"), (PyCFunction)__pyx_pw_5spacy_6lexeme_11last3_of, METH_O, __Pyx_DOCSTR(__pyx_doc_5spacy_6lexeme_10last3_of)},
{__Pyx_NAMESTR("is_oft_upper"), (PyCFunction)__pyx_pw_5spacy_6lexeme_13is_oft_upper, METH_O, __Pyx_DOCSTR(__pyx_doc_5spacy_6lexeme_12is_oft_upper)},
{__Pyx_NAMESTR("is_oft_title"), (PyCFunction)__pyx_pw_5spacy_6lexeme_15is_oft_title, METH_O, __Pyx_DOCSTR(__pyx_doc_5spacy_6lexeme_14is_oft_title)},
{0, 0, 0, 0}
};
#if PY_MAJOR_VERSION >= 3
static struct PyModuleDef __pyx_moduledef = {
#if PY_VERSION_HEX < 0x03020000
{ PyObject_HEAD_INIT(NULL) NULL, 0, NULL },
#else
PyModuleDef_HEAD_INIT,
#endif
__Pyx_NAMESTR("lexeme"),
__Pyx_DOCSTR(__pyx_k_Accessors_for_Lexeme_properties), /* m_doc */
-1, /* m_size */
__pyx_methods /* m_methods */,
NULL, /* m_reload */
NULL, /* m_traverse */
NULL, /* m_clear */
NULL /* m_free */
};
#endif
static __Pyx_StringTabEntry __pyx_string_tab[] = {
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
{&__pyx_kp_u_, __pyx_k_, sizeof(__pyx_k_), 0, 1, 0, 0},
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
{&__pyx_kp_u_Access_the_cluster_field_of_the, __pyx_k_Access_the_cluster_field_of_the, sizeof(__pyx_k_Access_the_cluster_field_of_the), 0, 1, 0, 0},
{&__pyx_kp_u_Access_the_first_field_of_the_Le, __pyx_k_Access_the_first_field_of_the_Le, sizeof(__pyx_k_Access_the_first_field_of_the_Le), 0, 1, 0, 0},
{&__pyx_kp_u_Access_the_last3_field_of_the_Le, __pyx_k_Access_the_last3_field_of_the_Le, sizeof(__pyx_k_Access_the_last3_field_of_the_Le), 0, 1, 0, 0},
{&__pyx_kp_u_Access_the_lex_field_of_the_Lexe, __pyx_k_Access_the_lex_field_of_the_Lexe, sizeof(__pyx_k_Access_the_lex_field_of_the_Lexe), 0, 1, 0, 0},
{&__pyx_kp_u_Access_the_oft_upper_field_of_th, __pyx_k_Access_the_oft_upper_field_of_th, sizeof(__pyx_k_Access_the_oft_upper_field_of_th), 0, 1, 0, 0},
{&__pyx_kp_u_Access_the_oft_upper_field_of_th_2, __pyx_k_Access_the_oft_upper_field_of_th_2, sizeof(__pyx_k_Access_the_oft_upper_field_of_th_2), 0, 1, 0, 0},
{&__pyx_kp_u_Access_the_prob_field_of_the_Lex, __pyx_k_Access_the_prob_field_of_the_Lex, sizeof(__pyx_k_Access_the_prob_field_of_the_Lex), 0, 1, 0, 0},
{&__pyx_kp_u_Access_the_sic_field_of_the_Lexe, __pyx_k_Access_the_sic_field_of_the_Lexe, sizeof(__pyx_k_Access_the_sic_field_of_the_Lexe), 0, 1, 0, 0},
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
{&__pyx_n_s_BLANK_WORD, __pyx_k_BLANK_WORD, sizeof(__pyx_k_BLANK_WORD), 0, 0, 1, 1},
{&__pyx_kp_u__2, __pyx_k__2, sizeof(__pyx_k__2), 0, 1, 0, 0},
{&__pyx_kp_u_cluster_of_line_87, __pyx_k_cluster_of_line_87, sizeof(__pyx_k_cluster_of_line_87), 0, 1, 0, 0},
{&__pyx_kp_u_first_of_line_106, __pyx_k_first_of_line_106, sizeof(__pyx_k_first_of_line_106), 0, 1, 0, 0},
{&__pyx_kp_u_is_oft_title_line_156, __pyx_k_is_oft_title_line_156, sizeof(__pyx_k_is_oft_title_line_156), 0, 1, 0, 0},
{&__pyx_kp_u_is_oft_upper_line_141, __pyx_k_is_oft_upper_line_141, sizeof(__pyx_k_is_oft_upper_line_141), 0, 1, 0, 0},
{&__pyx_kp_u_last3_of_line_130, __pyx_k_last3_of_line_130, sizeof(__pyx_k_last3_of_line_130), 0, 1, 0, 0},
{&__pyx_kp_u_lex_of_line_73, __pyx_k_lex_of_line_73, sizeof(__pyx_k_lex_of_line_73), 0, 1, 0, 0},
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
{&__pyx_n_s_main, __pyx_k_main, sizeof(__pyx_k_main), 0, 0, 1, 1},
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
{&__pyx_kp_u_prob_of_line_117, __pyx_k_prob_of_line_117, sizeof(__pyx_k_prob_of_line_117), 0, 1, 0, 0},
{&__pyx_n_s_pyx_capi, __pyx_k_pyx_capi, sizeof(__pyx_k_pyx_capi), 0, 0, 1, 1},
{&__pyx_kp_u_sic_of_line_61, __pyx_k_sic_of_line_61, sizeof(__pyx_k_sic_of_line_61), 0, 1, 0, 0},
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
{&__pyx_n_s_test, __pyx_k_test, sizeof(__pyx_k_test), 0, 0, 1, 1},
{0, 0, 0, 0, 0, 0, 0}
};
static int __Pyx_InitCachedBuiltins(void) {
return 0;
}
static int __Pyx_InitCachedConstants(void) {
__Pyx_RefNannyDeclarations
__Pyx_RefNannySetupContext("__Pyx_InitCachedConstants", 0);
__Pyx_RefNannyFinishContext();
return 0;
}
static int __Pyx_InitGlobals(void) {
if (__Pyx_InitStrings(__pyx_string_tab) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;};
return 0;
__pyx_L1_error:;
return -1;
}
#if PY_MAJOR_VERSION < 3
PyMODINIT_FUNC initlexeme(void); /*proto*/
PyMODINIT_FUNC initlexeme(void)
#else
PyMODINIT_FUNC PyInit_lexeme(void); /*proto*/
PyMODINIT_FUNC PyInit_lexeme(void)
#endif
{
PyObject *__pyx_t_1 = NULL;
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
PyObject *__pyx_t_2 = NULL;
PyObject *__pyx_t_3 = NULL;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
int __pyx_lineno = 0;
const char *__pyx_filename = NULL;
int __pyx_clineno = 0;
__Pyx_RefNannyDeclarations
#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("PyMODINIT_FUNC PyInit_lexeme(void)", 0);
if ( __Pyx_check_binary_version() < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_empty_tuple = PyTuple_New(0); if (unlikely(!__pyx_empty_tuple)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_empty_bytes = PyBytes_FromStringAndSize("", 0); if (unlikely(!__pyx_empty_bytes)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
#ifdef __Pyx_CyFunction_USED
if (__Pyx_CyFunction_init() < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
#endif
#ifdef __Pyx_FusedFunction_USED
if (__pyx_FusedFunction_init() < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
#endif
#ifdef __Pyx_Generator_USED
if (__pyx_Generator_init() < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
#endif
/*--- Library function declarations ---*/
/*--- Threads initialization code ---*/
#if defined(__PYX_FORCE_INIT_THREADS) && __PYX_FORCE_INIT_THREADS
#ifdef WITH_THREAD /* Python build with threading support? */
PyEval_InitThreads();
#endif
#endif
/*--- Module creation code ---*/
#if PY_MAJOR_VERSION < 3
__pyx_m = Py_InitModule4(__Pyx_NAMESTR("lexeme"), __pyx_methods, __Pyx_DOCSTR(__pyx_k_Accessors_for_Lexeme_properties), 0, PYTHON_API_VERSION); Py_XINCREF(__pyx_m);
#else
__pyx_m = PyModule_Create(&__pyx_moduledef);
#endif
if (unlikely(!__pyx_m)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__pyx_d = PyModule_GetDict(__pyx_m); if (unlikely(!__pyx_d)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
Py_INCREF(__pyx_d);
__pyx_b = PyImport_AddModule(__Pyx_NAMESTR(__Pyx_BUILTIN_MODULE_NAME)); if (unlikely(!__pyx_b)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
#if CYTHON_COMPILING_IN_PYPY
Py_INCREF(__pyx_b);
#endif
if (__Pyx_SetAttrString(__pyx_m, "__builtins__", __pyx_b) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;};
/*--- Initialize various global constants etc. ---*/
if (unlikely(__Pyx_InitGlobals() < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __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_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
#endif
if (__pyx_module_is_main_spacy__lexeme) {
if (__Pyx_SetAttrString(__pyx_m, "__name__", __pyx_n_s_main) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;};
}
#if PY_MAJOR_VERSION >= 3
{
PyObject *modules = PyImport_GetModuleDict(); if (unlikely(!modules)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
if (!PyDict_GetItemString(modules, "spacy.lexeme")) {
if (unlikely(PyDict_SetItemString(modules, "spacy.lexeme", __pyx_m) < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
}
}
#endif
/*--- Builtin init code ---*/
if (unlikely(__Pyx_InitCachedBuiltins() < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
/*--- Constants init code ---*/
if (unlikely(__Pyx_InitCachedConstants() < 0)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
/*--- Global init code ---*/
/*--- Variable export code ---*/
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
if (__Pyx_ExportVoidPtr(__pyx_n_s_BLANK_WORD, (void *)&__pyx_v_5spacy_6lexeme_BLANK_WORD, "struct __pyx_t_5spacy_6lexeme_Lexeme") < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
/*--- Function export code ---*/
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
if (__Pyx_ExportFunction("init_lexeme", (void (*)(void))__pyx_f_5spacy_6lexeme_init_lexeme, "struct __pyx_t_5spacy_6lexeme_Lexeme *(__pyx_t_5spacy_5spacy_Vocab, PyObject *, __pyx_t_5spacy_5spacy_Splitter, PyObject *, __pyx_t_5spacy_6lexeme_StringHash, int, size_t)") < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
/*--- Type init code ---*/
/*--- Type import code ---*/
/*--- Variable import code ---*/
/*--- Function import code ---*/
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
__pyx_t_1 = __Pyx_ImportModule("spacy.spacy"); if (!__pyx_t_1) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
if (__Pyx_ImportFunction(__pyx_t_1, "lookup", (void (**)(void))&__pyx_f_5spacy_5spacy_lookup, "__pyx_t_5spacy_5spacy_Lexeme_addr (__pyx_t_5spacy_5spacy_Vocab &, PyObject *, __pyx_t_5spacy_5spacy_Splitter, int, PyObject *)") < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
if (__Pyx_ImportFunction(__pyx_t_1, "hash_string", (void (**)(void))&__pyx_f_5spacy_5spacy_hash_string, "__pyx_t_5spacy_5spacy_StringHash (PyObject *, size_t)") < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
Py_DECREF(__pyx_t_1); __pyx_t_1 = 0;
__pyx_t_2 = __Pyx_ImportModule("spacy.string_tools"); if (!__pyx_t_2) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
if (__Pyx_ImportFunction(__pyx_t_2, "substr", (void (**)(void))&__pyx_f_5spacy_12string_tools_substr, "PyObject *(PyObject *, int, int, size_t, int __pyx_skip_dispatch)") < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
Py_DECREF(__pyx_t_2); __pyx_t_2 = 0;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
/*--- Execution code ---*/
/* "spacy/lexeme.pyx":1
* '''Accessors for Lexeme properties, given a lex_id, which is cast to a Lexeme*. # <<<<<<<<<<<<<<
* Mostly useful from Python-space. From Cython-space, you can just cast to
* Lexeme* yourself.
*/
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
__pyx_t_3 = PyDict_New(); if (unlikely(!__pyx_t_3)) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__Pyx_GOTREF(__pyx_t_3);
if (PyDict_SetItem(__pyx_t_3, __pyx_kp_u_sic_of_line_61, __pyx_kp_u_Access_the_sic_field_of_the_Lexe) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
if (PyDict_SetItem(__pyx_t_3, __pyx_kp_u_lex_of_line_73, __pyx_kp_u_Access_the_lex_field_of_the_Lexe) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
if (PyDict_SetItem(__pyx_t_3, __pyx_kp_u_cluster_of_line_87, __pyx_kp_u_Access_the_cluster_field_of_the) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
if (PyDict_SetItem(__pyx_t_3, __pyx_kp_u_first_of_line_106, __pyx_kp_u_Access_the_first_field_of_the_Le) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
if (PyDict_SetItem(__pyx_t_3, __pyx_kp_u_prob_of_line_117, __pyx_kp_u_Access_the_prob_field_of_the_Lex) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
if (PyDict_SetItem(__pyx_t_3, __pyx_kp_u_last3_of_line_130, __pyx_kp_u_Access_the_last3_field_of_the_Le) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
if (PyDict_SetItem(__pyx_t_3, __pyx_kp_u_is_oft_upper_line_141, __pyx_kp_u_Access_the_oft_upper_field_of_th) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
if (PyDict_SetItem(__pyx_t_3, __pyx_kp_u_is_oft_title_line_156, __pyx_kp_u_Access_the_oft_upper_field_of_th_2) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
if (PyDict_SetItem(__pyx_d, __pyx_n_s_test, __pyx_t_3) < 0) {__pyx_filename = __pyx_f[0]; __pyx_lineno = 1; __pyx_clineno = __LINE__; goto __pyx_L1_error;}
__Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
goto __pyx_L0;
__pyx_L1_error:;
__Pyx_XDECREF(__pyx_t_1);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
__Pyx_XDECREF(__pyx_t_2);
__Pyx_XDECREF(__pyx_t_3);
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
if (__pyx_m) {
__Pyx_AddTraceback("init spacy.lexeme", __pyx_clineno, __pyx_lineno, __pyx_filename);
Py_DECREF(__pyx_m); __pyx_m = 0;
} else if (!PyErr_Occurred()) {
PyErr_SetString(PyExc_ImportError, "init spacy.lexeme");
}
__pyx_L0:;
__Pyx_RefNannyFinishContext();
#if PY_MAJOR_VERSION < 3
return;
#else
return __pyx_m;
#endif
}
/* Runtime support code */
#if CYTHON_REFNANNY
static __Pyx_RefNannyAPIStruct *__Pyx_RefNannyImportAPI(const char *modname) {
PyObject *m = NULL, *p = NULL;
void *r = NULL;
m = PyImport_ImportModule((char *)modname);
if (!m) goto end;
p = PyObject_GetAttrString(m, (char *)"RefNannyAPI");
if (!p) goto end;
r = PyLong_AsVoidPtr(p);
end:
Py_XDECREF(p);
Py_XDECREF(m);
return (__Pyx_RefNannyAPIStruct *)r;
}
#endif /* CYTHON_REFNANNY */
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
static CYTHON_INLINE Py_UCS4 __Pyx_GetItemInt_Unicode_Fast(PyObject* ustring, Py_ssize_t i,
int wraparound, int boundscheck) {
Py_ssize_t length;
#if CYTHON_PEP393_ENABLED
if (unlikely(__Pyx_PyUnicode_READY(ustring) < 0)) return (Py_UCS4)-1;
#endif
if (wraparound | boundscheck) {
length = __Pyx_PyUnicode_GET_LENGTH(ustring);
if (wraparound & unlikely(i < 0)) i += length;
if ((!boundscheck) || likely((0 <= i) & (i < length))) {
return __Pyx_PyUnicode_READ_CHAR(ustring, i);
} else {
PyErr_SetString(PyExc_IndexError, "string index out of range");
return (Py_UCS4)-1;
}
} else {
return __Pyx_PyUnicode_READ_CHAR(ustring, i);
}
}
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
#define __PYX_VERIFY_RETURN_INT(target_type, func_type, func) \
{ \
func_type value = func(x); \
if (sizeof(target_type) < sizeof(func_type)) { \
if (unlikely(value != (func_type) (target_type) value)) { \
func_type zero = 0; \
PyErr_SetString(PyExc_OverflowError, \
(is_unsigned && unlikely(value < zero)) ? \
"can't convert negative value to " #target_type : \
"value too large to convert to " #target_type); \
return (target_type) -1; \
} \
} \
return (target_type) value; \
}
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
#include "longintrepr.h"
#endif
#endif
static CYTHON_INLINE size_t __Pyx_PyInt_As_size_t(PyObject *x) {
const size_t neg_one = (size_t) -1, const_zero = 0;
const int is_unsigned = neg_one > const_zero;
#if PY_MAJOR_VERSION < 3
if (likely(PyInt_Check(x))) {
if (sizeof(size_t) < sizeof(long)) {
__PYX_VERIFY_RETURN_INT(size_t, long, PyInt_AS_LONG)
} else {
long val = PyInt_AS_LONG(x);
if (is_unsigned && unlikely(val < 0)) {
PyErr_SetString(PyExc_OverflowError,
"can't convert negative value to size_t");
return (size_t) -1;
}
return (size_t) val;
}
} else
#endif
if (likely(PyLong_Check(x))) {
if (is_unsigned) {
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
if (sizeof(digit) <= sizeof(size_t)) {
switch (Py_SIZE(x)) {
case 0: return 0;
case 1: return (size_t) ((PyLongObject*)x)->ob_digit[0];
}
}
#endif
#endif
if (unlikely(Py_SIZE(x) < 0)) {
PyErr_SetString(PyExc_OverflowError,
"can't convert negative value to size_t");
return (size_t) -1;
}
if (sizeof(size_t) <= sizeof(unsigned long)) {
__PYX_VERIFY_RETURN_INT(size_t, unsigned long, PyLong_AsUnsignedLong)
} else if (sizeof(size_t) <= sizeof(unsigned long long)) {
__PYX_VERIFY_RETURN_INT(size_t, unsigned long long, PyLong_AsUnsignedLongLong)
}
} else {
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
if (sizeof(digit) <= sizeof(size_t)) {
switch (Py_SIZE(x)) {
case 0: return 0;
case 1: return +(size_t) ((PyLongObject*)x)->ob_digit[0];
case -1: return -(size_t) ((PyLongObject*)x)->ob_digit[0];
}
}
#endif
#endif
if (sizeof(size_t) <= sizeof(long)) {
__PYX_VERIFY_RETURN_INT(size_t, long, PyLong_AsLong)
} else if (sizeof(size_t) <= sizeof(long long)) {
__PYX_VERIFY_RETURN_INT(size_t, long long, PyLong_AsLongLong)
}
}
{
#if CYTHON_COMPILING_IN_PYPY && !defined(_PyLong_AsByteArray)
PyErr_SetString(PyExc_RuntimeError,
"_PyLong_AsByteArray() not available in PyPy, cannot convert large numbers");
#else
size_t val;
PyObject *v = __Pyx_PyNumber_Int(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 one = 1; int is_little = (int)*(unsigned char *)&one;
unsigned char *bytes = (unsigned char *)&val;
int ret = _PyLong_AsByteArray((PyLongObject *)v,
bytes, sizeof(val),
is_little, !is_unsigned);
Py_DECREF(v);
if (likely(!ret))
return val;
}
#endif
return (size_t) -1;
}
} else {
size_t val;
PyObject *tmp = __Pyx_PyNumber_Int(x);
if (!tmp) return (size_t) -1;
val = __Pyx_PyInt_As_size_t(tmp);
Py_DECREF(tmp);
return val;
}
}
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
static CYTHON_INLINE PyObject* __Pyx_PyInt_From_long(long value) {
const long neg_one = (long) -1, const_zero = 0;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
const int is_unsigned = neg_one > const_zero;
if (is_unsigned) {
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
if (sizeof(long) < sizeof(long)) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
return PyInt_FromLong((long) value);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
} else if (sizeof(long) <= sizeof(unsigned long)) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
return PyLong_FromUnsignedLong((unsigned long) value);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
} else if (sizeof(long) <= sizeof(unsigned long long)) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
return PyLong_FromUnsignedLongLong((unsigned long long) value);
}
} else {
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
if (sizeof(long) <= sizeof(long)) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
return PyInt_FromLong((long) value);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
} else if (sizeof(long) <= sizeof(long long)) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
return PyLong_FromLongLong((long long) value);
}
}
{
int one = 1; int little = (int)*(unsigned char *)&one;
unsigned char *bytes = (unsigned char *)&value;
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
return _PyLong_FromByteArray(bytes, sizeof(long),
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
little, !is_unsigned);
}
}
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
static CYTHON_INLINE PyObject* __Pyx_PyInt_From_uint64_t(uint64_t value) {
const uint64_t neg_one = (uint64_t) -1, const_zero = 0;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
const int is_unsigned = neg_one > const_zero;
if (is_unsigned) {
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
if (sizeof(uint64_t) < sizeof(long)) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
return PyInt_FromLong((long) value);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
} else if (sizeof(uint64_t) <= sizeof(unsigned long)) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
return PyLong_FromUnsignedLong((unsigned long) value);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
} else if (sizeof(uint64_t) <= sizeof(unsigned long long)) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
return PyLong_FromUnsignedLongLong((unsigned long long) value);
}
} else {
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
if (sizeof(uint64_t) <= sizeof(long)) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
return PyInt_FromLong((long) value);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
} else if (sizeof(uint64_t) <= sizeof(long long)) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
return PyLong_FromLongLong((long long) value);
}
}
{
int one = 1; int little = (int)*(unsigned char *)&one;
unsigned char *bytes = (unsigned char *)&value;
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
return _PyLong_FromByteArray(bytes, sizeof(uint64_t),
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
little, !is_unsigned);
}
}
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
static CYTHON_INLINE PyObject* __Pyx_PyInt_From_int(int value) {
const int neg_one = (int) -1, const_zero = 0;
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
const int is_unsigned = neg_one > const_zero;
if (is_unsigned) {
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
if (sizeof(int) < sizeof(long)) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
return PyInt_FromLong((long) value);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
} else if (sizeof(int) <= sizeof(unsigned long)) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
return PyLong_FromUnsignedLong((unsigned long) value);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
} else if (sizeof(int) <= sizeof(unsigned long long)) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
return PyLong_FromUnsignedLongLong((unsigned long long) value);
}
} else {
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
if (sizeof(int) <= sizeof(long)) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
return PyInt_FromLong((long) value);
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
} else if (sizeof(int) <= sizeof(long long)) {
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
return PyLong_FromLongLong((long long) value);
}
}
{
int one = 1; int little = (int)*(unsigned char *)&one;
unsigned char *bytes = (unsigned char *)&value;
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
return _PyLong_FromByteArray(bytes, sizeof(int),
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
little, !is_unsigned);
}
}
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
#include "longintrepr.h"
#endif
#endif
static CYTHON_INLINE long __Pyx_PyInt_As_long(PyObject *x) {
const long neg_one = (long) -1, const_zero = 0;
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)
} else {
long val = PyInt_AS_LONG(x);
if (is_unsigned && unlikely(val < 0)) {
PyErr_SetString(PyExc_OverflowError,
"can't convert negative value to long");
return (long) -1;
}
return (long) val;
}
} else
#endif
if (likely(PyLong_Check(x))) {
if (is_unsigned) {
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
if (sizeof(digit) <= sizeof(long)) {
switch (Py_SIZE(x)) {
case 0: return 0;
case 1: return (long) ((PyLongObject*)x)->ob_digit[0];
}
}
#endif
#endif
if (unlikely(Py_SIZE(x) < 0)) {
PyErr_SetString(PyExc_OverflowError,
"can't convert negative value to long");
return (long) -1;
}
if (sizeof(long) <= sizeof(unsigned long)) {
__PYX_VERIFY_RETURN_INT(long, unsigned long, PyLong_AsUnsignedLong)
} else if (sizeof(long) <= sizeof(unsigned long long)) {
__PYX_VERIFY_RETURN_INT(long, unsigned long long, PyLong_AsUnsignedLongLong)
}
} else {
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
if (sizeof(digit) <= sizeof(long)) {
switch (Py_SIZE(x)) {
case 0: return 0;
case 1: return +(long) ((PyLongObject*)x)->ob_digit[0];
case -1: return -(long) ((PyLongObject*)x)->ob_digit[0];
}
}
#endif
#endif
if (sizeof(long) <= sizeof(long)) {
__PYX_VERIFY_RETURN_INT(long, long, PyLong_AsLong)
} else if (sizeof(long) <= sizeof(long long)) {
__PYX_VERIFY_RETURN_INT(long, long long, PyLong_AsLongLong)
}
}
{
#if CYTHON_COMPILING_IN_PYPY && !defined(_PyLong_AsByteArray)
PyErr_SetString(PyExc_RuntimeError,
"_PyLong_AsByteArray() not available in PyPy, cannot convert large numbers");
#else
long val;
PyObject *v = __Pyx_PyNumber_Int(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 one = 1; int is_little = (int)*(unsigned char *)&one;
unsigned char *bytes = (unsigned char *)&val;
int ret = _PyLong_AsByteArray((PyLongObject *)v,
bytes, sizeof(val),
is_little, !is_unsigned);
Py_DECREF(v);
if (likely(!ret))
return val;
}
#endif
return (long) -1;
}
} else {
long val;
PyObject *tmp = __Pyx_PyNumber_Int(x);
if (!tmp) return (long) -1;
val = __Pyx_PyInt_As_long(tmp);
Py_DECREF(tmp);
return val;
}
}
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
#include "longintrepr.h"
#endif
#endif
static CYTHON_INLINE int __Pyx_PyInt_As_int(PyObject *x) {
const int neg_one = (int) -1, const_zero = 0;
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)
} else {
long val = PyInt_AS_LONG(x);
if (is_unsigned && unlikely(val < 0)) {
PyErr_SetString(PyExc_OverflowError,
"can't convert negative value to int");
return (int) -1;
}
return (int) val;
}
} else
#endif
if (likely(PyLong_Check(x))) {
if (is_unsigned) {
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
if (sizeof(digit) <= sizeof(int)) {
switch (Py_SIZE(x)) {
case 0: return 0;
case 1: return (int) ((PyLongObject*)x)->ob_digit[0];
}
}
#endif
#endif
if (unlikely(Py_SIZE(x) < 0)) {
PyErr_SetString(PyExc_OverflowError,
"can't convert negative value to int");
return (int) -1;
}
if (sizeof(int) <= sizeof(unsigned long)) {
__PYX_VERIFY_RETURN_INT(int, unsigned long, PyLong_AsUnsignedLong)
} else if (sizeof(int) <= sizeof(unsigned long long)) {
__PYX_VERIFY_RETURN_INT(int, unsigned long long, PyLong_AsUnsignedLongLong)
}
} else {
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
if (sizeof(digit) <= sizeof(int)) {
switch (Py_SIZE(x)) {
case 0: return 0;
case 1: return +(int) ((PyLongObject*)x)->ob_digit[0];
case -1: return -(int) ((PyLongObject*)x)->ob_digit[0];
}
}
#endif
#endif
if (sizeof(int) <= sizeof(long)) {
__PYX_VERIFY_RETURN_INT(int, long, PyLong_AsLong)
} else if (sizeof(int) <= sizeof(long long)) {
__PYX_VERIFY_RETURN_INT(int, long long, PyLong_AsLongLong)
}
}
{
#if CYTHON_COMPILING_IN_PYPY && !defined(_PyLong_AsByteArray)
PyErr_SetString(PyExc_RuntimeError,
"_PyLong_AsByteArray() not available in PyPy, cannot convert large numbers");
#else
int val;
PyObject *v = __Pyx_PyNumber_Int(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 one = 1; int is_little = (int)*(unsigned char *)&one;
unsigned char *bytes = (unsigned char *)&val;
int ret = _PyLong_AsByteArray((PyLongObject *)v,
bytes, sizeof(val),
is_little, !is_unsigned);
Py_DECREF(v);
if (likely(!ret))
return val;
}
#endif
return (int) -1;
}
} else {
int val;
PyObject *tmp = __Pyx_PyNumber_Int(x);
if (!tmp) return (int) -1;
val = __Pyx_PyInt_As_int(tmp);
Py_DECREF(tmp);
return val;
}
}
static int __Pyx_check_binary_version(void) {
char ctversion[4], rtversion[4];
PyOS_snprintf(ctversion, 4, "%d.%d", PY_MAJOR_VERSION, PY_MINOR_VERSION);
PyOS_snprintf(rtversion, 4, "%s", Py_GetVersion());
if (ctversion[0] != rtversion[0] || ctversion[2] != rtversion[2]) {
char message[200];
PyOS_snprintf(message, sizeof(message),
"compiletime version %s of module '%.100s' "
"does not match runtime version %s",
ctversion, __Pyx_MODULE_NAME, rtversion);
#if PY_VERSION_HEX < 0x02050000
return PyErr_Warn(NULL, message);
#else
return PyErr_WarnEx(NULL, message, 1);
#endif
}
return 0;
}
* Reorganized, moving language-independent stuff to spacy. The functions in spacy ask for the dictionaries and split function on input, but the language-specific modules are curried versions that use the globals
2014-07-07 06:21:06 +04:00
static int __Pyx_ExportVoidPtr(PyObject *name, void *p, const char *sig) {
PyObject *d;
PyObject *cobj = 0;
d = PyDict_GetItem(__pyx_d, __pyx_n_s_pyx_capi);
Py_XINCREF(d);
if (!d) {
d = PyDict_New();
if (!d)
goto bad;
if (__Pyx_PyObject_SetAttrStr(__pyx_m, __pyx_n_s_pyx_capi, d) < 0)
goto bad;
}
#if PY_VERSION_HEX >= 0x02070000 && !(PY_MAJOR_VERSION==3 && PY_MINOR_VERSION==0)
cobj = PyCapsule_New(p, sig, 0);
#else
cobj = PyCObject_FromVoidPtrAndDesc(p, (void *)sig, 0);
#endif
if (!cobj)
goto bad;
if (PyDict_SetItem(d, name, cobj) < 0)
goto bad;
Py_DECREF(cobj);
Py_DECREF(d);
return 0;
bad:
Py_XDECREF(cobj);
Py_XDECREF(d);
return -1;
}
static int __Pyx_ExportFunction(const char *name, void (*f)(void), const char *sig) {
PyObject *d = 0;
PyObject *cobj = 0;
union {
void (*fp)(void);
void *p;
} tmp;
d = PyObject_GetAttrString(__pyx_m, (char *)"__pyx_capi__");
if (!d) {
PyErr_Clear();
d = PyDict_New();
if (!d)
goto bad;
Py_INCREF(d);
if (PyModule_AddObject(__pyx_m, (char *)"__pyx_capi__", d) < 0)
goto bad;
}
tmp.fp = f;
#if PY_VERSION_HEX >= 0x02070000 && !(PY_MAJOR_VERSION==3&&PY_MINOR_VERSION==0)
cobj = PyCapsule_New(tmp.p, sig, 0);
#else
cobj = PyCObject_FromVoidPtrAndDesc(tmp.p, (void *)sig, 0);
#endif
if (!cobj)
goto bad;
if (PyDict_SetItemString(d, name, cobj) < 0)
goto bad;
Py_DECREF(cobj);
Py_DECREF(d);
return 0;
bad:
Py_XDECREF(cobj);
Py_XDECREF(d);
return -1;
}
#ifndef __PYX_HAVE_RT_ImportModule
#define __PYX_HAVE_RT_ImportModule
static PyObject *__Pyx_ImportModule(const char *name) {
PyObject *py_name = 0;
PyObject *py_module = 0;
py_name = __Pyx_PyIdentifier_FromString(name);
if (!py_name)
goto bad;
py_module = PyImport_Import(py_name);
Py_DECREF(py_name);
return py_module;
bad:
Py_XDECREF(py_name);
return 0;
}
#endif
#ifndef __PYX_HAVE_RT_ImportFunction
#define __PYX_HAVE_RT_ImportFunction
static int __Pyx_ImportFunction(PyObject *module, const char *funcname, void (**f)(void), const char *sig) {
PyObject *d = 0;
PyObject *cobj = 0;
union {
void (*fp)(void);
void *p;
} tmp;
d = PyObject_GetAttrString(module, (char *)"__pyx_capi__");
if (!d)
goto bad;
cobj = PyDict_GetItemString(d, funcname);
if (!cobj) {
PyErr_Format(PyExc_ImportError,
"%.200s does not export expected C function %.200s",
PyModule_GetName(module), funcname);
goto bad;
}
#if PY_VERSION_HEX >= 0x02070000 && !(PY_MAJOR_VERSION==3 && PY_MINOR_VERSION==0)
if (!PyCapsule_IsValid(cobj, sig)) {
PyErr_Format(PyExc_TypeError,
"C function %.200s.%.200s has wrong signature (expected %.500s, got %.500s)",
PyModule_GetName(module), funcname, sig, PyCapsule_GetName(cobj));
goto bad;
}
tmp.p = PyCapsule_GetPointer(cobj, sig);
#else
{const char *desc, *s1, *s2;
desc = (const char *)PyCObject_GetDesc(cobj);
if (!desc)
goto bad;
s1 = desc; s2 = sig;
while (*s1 != '\0' && *s1 == *s2) { s1++; s2++; }
if (*s1 != *s2) {
PyErr_Format(PyExc_TypeError,
"C function %.200s.%.200s has wrong signature (expected %.500s, got %.500s)",
PyModule_GetName(module), funcname, sig, desc);
goto bad;
}
tmp.p = PyCObject_AsVoidPtr(cobj);}
#endif
*f = tmp.fp;
if (!(*f))
goto bad;
Py_DECREF(d);
return 0;
bad:
Py_XDECREF(d);
return -1;
}
#endif
* Initial commit. Tests passing for punctuation handling. Need contractions, file transport, tokenize function, etc.
2014-07-05 22:51:42 +04:00
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) / 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, 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);
}
#include "compile.h"
#include "frameobject.h"
#include "traceback.h"
static PyCodeObject* __Pyx_CreateCodeObjectForTraceback(
const char *funcname, int c_line,
int py_line, const char *filename) {
PyCodeObject *py_code = 0;
PyObject *py_srcfile = 0;
PyObject *py_funcname = 0;
#if PY_MAJOR_VERSION < 3
py_srcfile = PyString_FromString(filename);
#else
py_srcfile = PyUnicode_FromString(filename);
#endif
if (!py_srcfile) goto bad;
if (c_line) {
#if PY_MAJOR_VERSION < 3
py_funcname = PyString_FromFormat( "%s (%s:%d)", funcname, __pyx_cfilenm, c_line);
#else
py_funcname = PyUnicode_FromFormat( "%s (%s:%d)", funcname, __pyx_cfilenm, c_line);
#endif
}
else {
#if PY_MAJOR_VERSION < 3
py_funcname = PyString_FromString(funcname);
#else
py_funcname = PyUnicode_FromString(funcname);
#endif
}
if (!py_funcname) goto bad;
py_code = __Pyx_PyCode_New(
0, /*int argcount,*/
0, /*int kwonlyargcount,*/
0, /*int nlocals,*/
0, /*int stacksize,*/
0, /*int flags,*/
__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, /*int firstlineno,*/
__pyx_empty_bytes /*PyObject *lnotab*/
);
Py_DECREF(py_srcfile);
Py_DECREF(py_funcname);
return py_code;
bad:
Py_XDECREF(py_srcfile);
Py_XDECREF(py_funcname);
return NULL;
}
static void __Pyx_AddTraceback(const char *funcname, int c_line,
int py_line, const char *filename) {
PyCodeObject *py_code = 0;
PyObject *py_globals = 0;
PyFrameObject *py_frame = 0;
py_code = __pyx_find_code_object(c_line ? c_line : py_line);
if (!py_code) {
py_code = __Pyx_CreateCodeObjectForTraceback(
funcname, c_line, py_line, filename);
if (!py_code) goto bad;
__pyx_insert_code_object(c_line ? c_line : py_line, py_code);
}
py_globals = PyModule_GetDict(__pyx_m);
if (!py_globals) goto bad;
py_frame = PyFrame_New(
PyThreadState_GET(), /*PyThreadState *tstate,*/
py_code, /*PyCodeObject *code,*/
py_globals, /*PyObject *globals,*/
0 /*PyObject *locals*/
);
if (!py_frame) goto bad;
py_frame->f_lineno = py_line;
PyTraceBack_Here(py_frame);
bad:
Py_XDECREF(py_code);
Py_XDECREF(py_frame);
}
static int __Pyx_InitStrings(__Pyx_StringTabEntry *t) {
while (t->p) {
#if PY_MAJOR_VERSION < 3
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);
}
#else /* Python 3+ has unicode identifiers */
if (t->is_unicode | t->is_str) {
if (t->intern) {
*t->p = PyUnicode_InternFromString(t->s);
} else if (t->encoding) {
*t->p = PyUnicode_Decode(t->s, t->n - 1, t->encoding, NULL);
} else {
*t->p = PyUnicode_FromStringAndSize(t->s, t->n - 1);
}
} else {
*t->p = PyBytes_FromStringAndSize(t->s, t->n - 1);
}
#endif
if (!*t->p)
return -1;
++t;
}
return 0;
}
static CYTHON_INLINE PyObject* __Pyx_PyUnicode_FromString(char* c_str) {
return __Pyx_PyUnicode_FromStringAndSize(c_str, strlen(c_str));
}
static CYTHON_INLINE char* __Pyx_PyObject_AsString(PyObject* o) {
Py_ssize_t ignore;
return __Pyx_PyObject_AsStringAndSize(o, &ignore);
}
static CYTHON_INLINE 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)) {
#if PY_VERSION_HEX < 0x03030000
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 /*__PYX_DEFAULT_STRING_ENCODING_IS_ASCII*/
*length = PyBytes_GET_SIZE(defenc);
return defenc_c;
#else /* PY_VERSION_HEX < 0x03030000 */
if (PyUnicode_READY(o) == -1) return NULL;
#if __PYX_DEFAULT_STRING_ENCODING_IS_ASCII
if (PyUnicode_IS_ASCII(o)) {
*length = PyUnicode_GET_DATA_SIZE(o);
return PyUnicode_AsUTF8(o);
} else {
PyUnicode_AsASCIIString(o);
return NULL;
}
#else /* __PYX_DEFAULT_STRING_ENCODING_IS_ASCII */
return PyUnicode_AsUTF8AndSize(o, length);
#endif /* __PYX_DEFAULT_STRING_ENCODING_IS_ASCII */
#endif /* PY_VERSION_HEX < 0x03030000 */
} else
#endif /* __PYX_DEFAULT_STRING_ENCODING_IS_ASCII || __PYX_DEFAULT_STRING_ENCODING_IS_DEFAULT */
#if !CYTHON_COMPILING_IN_PYPY
#if PY_VERSION_HEX >= 0x02060000
if (PyByteArray_Check(o)) {
*length = PyByteArray_GET_SIZE(o);
return PyByteArray_AS_STRING(o);
} else
#endif
#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 PyObject* __Pyx_PyNumber_Int(PyObject* x) {
PyNumberMethods *m;
const char *name = NULL;
PyObject *res = NULL;
#if PY_MAJOR_VERSION < 3
if (PyInt_Check(x) || PyLong_Check(x))
#else
if (PyLong_Check(x))
#endif
return Py_INCREF(x), x;
m = Py_TYPE(x)->tp_as_number;
#if PY_MAJOR_VERSION < 3
if (m && m->nb_int) {
name = "int";
res = PyNumber_Int(x);
}
else if (m && m->nb_long) {
name = "long";
res = PyNumber_Long(x);
}
#else
if (m && m->nb_int) {
name = "int";
res = PyNumber_Long(x);
}
#endif
if (res) {
#if PY_MAJOR_VERSION < 3
if (!PyInt_Check(res) && !PyLong_Check(res)) {
#else
if (!PyLong_Check(res)) {
#endif
PyErr_Format(PyExc_TypeError,
"__%.4s__ returned non-%.4s (type %.200s)",
name, name, Py_TYPE(res)->tp_name);
Py_DECREF(res);
return NULL;
}
}
else if (!PyErr_Occurred()) {
PyErr_SetString(PyExc_TypeError,
"an integer is required");
}
return res;
}
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
#include "longintrepr.h"
#endif
#endif
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)))
return PyInt_AS_LONG(b);
#endif
if (likely(PyLong_CheckExact(b))) {
#if CYTHON_COMPILING_IN_CPYTHON && PY_MAJOR_VERSION >= 3
#if CYTHON_USE_PYLONG_INTERNALS
switch (Py_SIZE(b)) {
case -1: return -(sdigit)((PyLongObject*)b)->ob_digit[0];
case 0: return 0;
case 1: return ((PyLongObject*)b)->ob_digit[0];
}
#endif
#endif
#if PY_VERSION_HEX < 0x02060000
return PyInt_AsSsize_t(b);
#else
return PyLong_AsSsize_t(b);
#endif
}
x = PyNumber_Index(b);
if (!x) return -1;
ival = PyInt_AsSsize_t(x);
Py_DECREF(x);
return ival;
}
static CYTHON_INLINE PyObject * __Pyx_PyInt_FromSize_t(size_t ival) {
#if PY_VERSION_HEX < 0x02050000
if (ival <= LONG_MAX)
return PyInt_FromLong((long)ival);
else {
unsigned char *bytes = (unsigned char *) &ival;
int one = 1; int little = (int)*(unsigned char*)&one;
return _PyLong_FromByteArray(bytes, sizeof(size_t), little, 0);
}
#else
return PyInt_FromSize_t(ival);
#endif
}
#endif /* Py_PYTHON_H */
Reference in New Issue Copy Permalink