File: | Modules/unicodedata.c |
Location: | line 521, column 13 |
Description: | Assigned value is garbage or undefined |
1 | /* ------------------------------------------------------------------------ | ||
2 | |||
3 | unicodedata -- Provides access to the Unicode 5.2 data base. | ||
4 | |||
5 | Data was extracted from the Unicode 5.2 UnicodeData.txt file. | ||
6 | |||
7 | Written by Marc-Andre Lemburg (mal@lemburg.com). | ||
8 | Modified for Python 2.0 by Fredrik Lundh (fredrik@pythonware.com) | ||
9 | Modified by Martin v. Löwis (martin@v.loewis.de) | ||
10 | |||
11 | Copyright (c) Corporation for National Research Initiatives. | ||
12 | |||
13 | ------------------------------------------------------------------------ */ | ||
14 | |||
15 | #include "Python.h" | ||
16 | #include "ucnhash.h" | ||
17 | #include "structmember.h" | ||
18 | |||
19 | /* character properties */ | ||
20 | |||
21 | typedef struct { | ||
22 | const unsigned char category; /* index into | ||
23 | _PyUnicode_CategoryNames */ | ||
24 | const unsigned char combining; /* combining class value 0 - 255 */ | ||
25 | const unsigned char bidirectional; /* index into | ||
26 | _PyUnicode_BidirectionalNames */ | ||
27 | const unsigned char mirrored; /* true if mirrored in bidir mode */ | ||
28 | const unsigned char east_asian_width; /* index into | ||
29 | _PyUnicode_EastAsianWidth */ | ||
30 | const unsigned char normalization_quick_check; /* see is_normalized() */ | ||
31 | } _PyUnicode_DatabaseRecord; | ||
32 | |||
33 | typedef struct change_record { | ||
34 | /* sequence of fields should be the same as in merge_old_version */ | ||
35 | const unsigned char bidir_changed; | ||
36 | const unsigned char category_changed; | ||
37 | const unsigned char decimal_changed; | ||
38 | const unsigned char mirrored_changed; | ||
39 | const double numeric_changed; | ||
40 | } change_record; | ||
41 | |||
42 | /* data file generated by Tools/unicode/makeunicodedata.py */ | ||
43 | #include "unicodedata_db.h" | ||
44 | |||
45 | static const _PyUnicode_DatabaseRecord* | ||
46 | _getrecord_ex(Py_UCS4 code) | ||
47 | { | ||
48 | int index; | ||
49 | if (code >= 0x110000) | ||
50 | index = 0; | ||
51 | else { | ||
52 | index = index1[(code>>SHIFT7)]; | ||
53 | index = index2[(index<<SHIFT7)+(code&((1<<SHIFT7)-1))]; | ||
54 | } | ||
55 | |||
56 | return &_PyUnicode_Database_Records[index]; | ||
57 | } | ||
58 | |||
59 | /* ------------- Previous-version API ------------------------------------- */ | ||
60 | typedef struct previous_version { | ||
61 | PyObject_HEADPyObject ob_base; | ||
62 | const char *name; | ||
63 | const change_record* (*getrecord)(Py_UCS4); | ||
64 | Py_UCS4 (*normalization)(Py_UCS4); | ||
65 | } PreviousDBVersion; | ||
66 | |||
67 | #define get_old_record(self, v)((((PreviousDBVersion*)self)->getrecord)(v)) ((((PreviousDBVersion*)self)->getrecord)(v)) | ||
68 | |||
69 | static PyMemberDef DB_members[] = { | ||
70 | {"unidata_version", T_STRING5, offsetof(PreviousDBVersion, name)__builtin_offsetof(PreviousDBVersion, name), READONLY1}, | ||
71 | {NULL((void*)0)} | ||
72 | }; | ||
73 | |||
74 | /* forward declaration */ | ||
75 | static PyTypeObject UCD_Type; | ||
76 | #define UCD_Check(o)((((PyObject*)(o))->ob_type)==&UCD_Type) (Py_TYPE(o)(((PyObject*)(o))->ob_type)==&UCD_Type) | ||
77 | |||
78 | static PyObject* | ||
79 | new_previous_version(const char*name, const change_record* (*getrecord)(Py_UCS4), | ||
80 | Py_UCS4 (*normalization)(Py_UCS4)) | ||
81 | { | ||
82 | PreviousDBVersion *self; | ||
83 | self = PyObject_New(PreviousDBVersion, &UCD_Type)( (PreviousDBVersion *) _PyObject_New(&UCD_Type) ); | ||
84 | if (self == NULL((void*)0)) | ||
85 | return NULL((void*)0); | ||
86 | self->name = name; | ||
87 | self->getrecord = getrecord; | ||
88 | self->normalization = normalization; | ||
89 | return (PyObject*)self; | ||
90 | } | ||
91 | |||
92 | |||
93 | static Py_UCS4 getuchar(PyUnicodeObject *obj) | ||
94 | { | ||
95 | Py_UNICODE *v = PyUnicode_AS_UNICODE(obj)((__builtin_expect(!(((((((PyObject*)(obj))->ob_type))-> tp_flags & ((1L<<28))) != 0)), 0) ? __assert_rtn(__func__ , "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c", 95 , "PyUnicode_Check(obj)") : (void)0),(((PyUnicodeObject *)(obj ))->str)); | ||
96 | |||
97 | if (PyUnicode_GET_SIZE(obj)((__builtin_expect(!(((((((PyObject*)(obj))->ob_type))-> tp_flags & ((1L<<28))) != 0)), 0) ? __assert_rtn(__func__ , "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c", 97 , "PyUnicode_Check(obj)") : (void)0),(((PyUnicodeObject *)(obj ))->length)) == 1) | ||
98 | return *v; | ||
99 | #ifndef Py_UNICODE_WIDE | ||
100 | else if ((PyUnicode_GET_SIZE(obj)((__builtin_expect(!(((((((PyObject*)(obj))->ob_type))-> tp_flags & ((1L<<28))) != 0)), 0) ? __assert_rtn(__func__ , "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c", 100 , "PyUnicode_Check(obj)") : (void)0),(((PyUnicodeObject *)(obj ))->length)) == 2) && | ||
101 | (0xD800 <= v[0] && v[0] <= 0xDBFF) && | ||
102 | (0xDC00 <= v[1] && v[1] <= 0xDFFF)) | ||
103 | return (((v[0] & 0x3FF)<<10) | (v[1] & 0x3FF)) + 0x10000; | ||
104 | #endif | ||
105 | PyErr_SetString(PyExc_TypeError, | ||
106 | "need a single Unicode character as parameter"); | ||
107 | return (Py_UCS4)-1; | ||
108 | } | ||
109 | |||
110 | /* --- Module API --------------------------------------------------------- */ | ||
111 | |||
112 | PyDoc_STRVAR(unicodedata_decimal__doc__,static char unicodedata_decimal__doc__[] = "decimal(unichr[, default])\n\nReturns the decimal value assigned to the Unicode character unichr\nas integer. If no such value is defined, default is returned, or, if\nnot given, ValueError is raised." | ||
113 | "decimal(unichr[, default])\n\static char unicodedata_decimal__doc__[] = "decimal(unichr[, default])\n\nReturns the decimal value assigned to the Unicode character unichr\nas integer. If no such value is defined, default is returned, or, if\nnot given, ValueError is raised." | ||
114 | \n\static char unicodedata_decimal__doc__[] = "decimal(unichr[, default])\n\nReturns the decimal value assigned to the Unicode character unichr\nas integer. If no such value is defined, default is returned, or, if\nnot given, ValueError is raised." | ||
115 | Returns the decimal value assigned to the Unicode character unichr\n\static char unicodedata_decimal__doc__[] = "decimal(unichr[, default])\n\nReturns the decimal value assigned to the Unicode character unichr\nas integer. If no such value is defined, default is returned, or, if\nnot given, ValueError is raised." | ||
116 | as integer. If no such value is defined, default is returned, or, if\n\static char unicodedata_decimal__doc__[] = "decimal(unichr[, default])\n\nReturns the decimal value assigned to the Unicode character unichr\nas integer. If no such value is defined, default is returned, or, if\nnot given, ValueError is raised." | ||
117 | not given, ValueError is raised.")static char unicodedata_decimal__doc__[] = "decimal(unichr[, default])\n\nReturns the decimal value assigned to the Unicode character unichr\nas integer. If no such value is defined, default is returned, or, if\nnot given, ValueError is raised."; | ||
118 | |||
119 | static PyObject * | ||
120 | unicodedata_decimal(PyObject *self, PyObject *args) | ||
121 | { | ||
122 | PyUnicodeObject *v; | ||
123 | PyObject *defobj = NULL((void*)0); | ||
124 | int have_old = 0; | ||
125 | long rc; | ||
126 | Py_UCS4 c; | ||
127 | |||
128 | if (!PyArg_ParseTuple(args, "O!|O:decimal", &PyUnicode_Type, &v, &defobj)) | ||
129 | return NULL((void*)0); | ||
130 | c = getuchar(v); | ||
131 | if (c == (Py_UCS4)-1) | ||
132 | return NULL((void*)0); | ||
133 | |||
134 | if (self && UCD_Check(self)((((PyObject*)(self))->ob_type)==&UCD_Type)) { | ||
135 | const change_record *old = get_old_record(self, c)((((PreviousDBVersion*)self)->getrecord)(c)); | ||
136 | if (old->category_changed == 0) { | ||
137 | /* unassigned */ | ||
138 | have_old = 1; | ||
139 | rc = -1; | ||
140 | } | ||
141 | else if (old->decimal_changed != 0xFF) { | ||
142 | have_old = 1; | ||
143 | rc = old->decimal_changed; | ||
144 | } | ||
145 | } | ||
146 | |||
147 | if (!have_old) | ||
148 | rc = Py_UNICODE_TODECIMAL(c)_PyUnicode_ToDecimalDigit(c); | ||
149 | if (rc < 0) { | ||
150 | if (defobj == NULL((void*)0)) { | ||
151 | PyErr_SetString(PyExc_ValueError, | ||
152 | "not a decimal"); | ||
153 | return NULL((void*)0); | ||
154 | } | ||
155 | else { | ||
156 | Py_INCREF(defobj)( _Py_RefTotal++ , ((PyObject*)(defobj))->ob_refcnt++); | ||
157 | return defobj; | ||
158 | } | ||
159 | } | ||
160 | return PyLong_FromLong(rc); | ||
161 | } | ||
162 | |||
163 | PyDoc_STRVAR(unicodedata_digit__doc__,static char unicodedata_digit__doc__[] = "digit(unichr[, default])\n\nReturns the digit value assigned to the Unicode character unichr as\ninteger. If no such value is defined, default is returned, or, if\nnot given, ValueError is raised." | ||
164 | "digit(unichr[, default])\n\static char unicodedata_digit__doc__[] = "digit(unichr[, default])\n\nReturns the digit value assigned to the Unicode character unichr as\ninteger. If no such value is defined, default is returned, or, if\nnot given, ValueError is raised." | ||
165 | \n\static char unicodedata_digit__doc__[] = "digit(unichr[, default])\n\nReturns the digit value assigned to the Unicode character unichr as\ninteger. If no such value is defined, default is returned, or, if\nnot given, ValueError is raised." | ||
166 | Returns the digit value assigned to the Unicode character unichr as\n\static char unicodedata_digit__doc__[] = "digit(unichr[, default])\n\nReturns the digit value assigned to the Unicode character unichr as\ninteger. If no such value is defined, default is returned, or, if\nnot given, ValueError is raised." | ||
167 | integer. If no such value is defined, default is returned, or, if\n\static char unicodedata_digit__doc__[] = "digit(unichr[, default])\n\nReturns the digit value assigned to the Unicode character unichr as\ninteger. If no such value is defined, default is returned, or, if\nnot given, ValueError is raised." | ||
168 | not given, ValueError is raised.")static char unicodedata_digit__doc__[] = "digit(unichr[, default])\n\nReturns the digit value assigned to the Unicode character unichr as\ninteger. If no such value is defined, default is returned, or, if\nnot given, ValueError is raised."; | ||
169 | |||
170 | static PyObject * | ||
171 | unicodedata_digit(PyObject *self, PyObject *args) | ||
172 | { | ||
173 | PyUnicodeObject *v; | ||
174 | PyObject *defobj = NULL((void*)0); | ||
175 | long rc; | ||
176 | Py_UCS4 c; | ||
177 | |||
178 | if (!PyArg_ParseTuple(args, "O!|O:digit", &PyUnicode_Type, &v, &defobj)) | ||
179 | return NULL((void*)0); | ||
180 | c = getuchar(v); | ||
181 | if (c == (Py_UCS4)-1) | ||
182 | return NULL((void*)0); | ||
183 | rc = Py_UNICODE_TODIGIT(c)_PyUnicode_ToDigit(c); | ||
184 | if (rc < 0) { | ||
185 | if (defobj == NULL((void*)0)) { | ||
186 | PyErr_SetString(PyExc_ValueError, "not a digit"); | ||
187 | return NULL((void*)0); | ||
188 | } | ||
189 | else { | ||
190 | Py_INCREF(defobj)( _Py_RefTotal++ , ((PyObject*)(defobj))->ob_refcnt++); | ||
191 | return defobj; | ||
192 | } | ||
193 | } | ||
194 | return PyLong_FromLong(rc); | ||
195 | } | ||
196 | |||
197 | PyDoc_STRVAR(unicodedata_numeric__doc__,static char unicodedata_numeric__doc__[] = "numeric(unichr[, default])\n\nReturns the numeric value assigned to the Unicode character unichr\nas float. If no such value is defined, default is returned, or, if\nnot given, ValueError is raised." | ||
198 | "numeric(unichr[, default])\n\static char unicodedata_numeric__doc__[] = "numeric(unichr[, default])\n\nReturns the numeric value assigned to the Unicode character unichr\nas float. If no such value is defined, default is returned, or, if\nnot given, ValueError is raised." | ||
199 | \n\static char unicodedata_numeric__doc__[] = "numeric(unichr[, default])\n\nReturns the numeric value assigned to the Unicode character unichr\nas float. If no such value is defined, default is returned, or, if\nnot given, ValueError is raised." | ||
200 | Returns the numeric value assigned to the Unicode character unichr\n\static char unicodedata_numeric__doc__[] = "numeric(unichr[, default])\n\nReturns the numeric value assigned to the Unicode character unichr\nas float. If no such value is defined, default is returned, or, if\nnot given, ValueError is raised." | ||
201 | as float. If no such value is defined, default is returned, or, if\n\static char unicodedata_numeric__doc__[] = "numeric(unichr[, default])\n\nReturns the numeric value assigned to the Unicode character unichr\nas float. If no such value is defined, default is returned, or, if\nnot given, ValueError is raised." | ||
202 | not given, ValueError is raised.")static char unicodedata_numeric__doc__[] = "numeric(unichr[, default])\n\nReturns the numeric value assigned to the Unicode character unichr\nas float. If no such value is defined, default is returned, or, if\nnot given, ValueError is raised."; | ||
203 | |||
204 | static PyObject * | ||
205 | unicodedata_numeric(PyObject *self, PyObject *args) | ||
206 | { | ||
207 | PyUnicodeObject *v; | ||
208 | PyObject *defobj = NULL((void*)0); | ||
209 | int have_old = 0; | ||
210 | double rc; | ||
211 | Py_UCS4 c; | ||
212 | |||
213 | if (!PyArg_ParseTuple(args, "O!|O:numeric", &PyUnicode_Type, &v, &defobj)) | ||
214 | return NULL((void*)0); | ||
215 | c = getuchar(v); | ||
216 | if (c == (Py_UCS4)-1) | ||
217 | return NULL((void*)0); | ||
218 | |||
219 | if (self && UCD_Check(self)((((PyObject*)(self))->ob_type)==&UCD_Type)) { | ||
220 | const change_record *old = get_old_record(self, c)((((PreviousDBVersion*)self)->getrecord)(c)); | ||
221 | if (old->category_changed == 0) { | ||
222 | /* unassigned */ | ||
223 | have_old = 1; | ||
224 | rc = -1.0; | ||
225 | } | ||
226 | else if (old->decimal_changed != 0xFF) { | ||
227 | have_old = 1; | ||
228 | rc = old->decimal_changed; | ||
229 | } | ||
230 | } | ||
231 | |||
232 | if (!have_old) | ||
233 | rc = Py_UNICODE_TONUMERIC(c)_PyUnicode_ToNumeric(c); | ||
234 | if (rc == -1.0) { | ||
235 | if (defobj == NULL((void*)0)) { | ||
236 | PyErr_SetString(PyExc_ValueError, "not a numeric character"); | ||
237 | return NULL((void*)0); | ||
238 | } | ||
239 | else { | ||
240 | Py_INCREF(defobj)( _Py_RefTotal++ , ((PyObject*)(defobj))->ob_refcnt++); | ||
241 | return defobj; | ||
242 | } | ||
243 | } | ||
244 | return PyFloat_FromDouble(rc); | ||
245 | } | ||
246 | |||
247 | PyDoc_STRVAR(unicodedata_category__doc__,static char unicodedata_category__doc__[] = "category(unichr)\n\nReturns the general category assigned to the Unicode character\nunichr as string." | ||
248 | "category(unichr)\n\static char unicodedata_category__doc__[] = "category(unichr)\n\nReturns the general category assigned to the Unicode character\nunichr as string." | ||
249 | \n\static char unicodedata_category__doc__[] = "category(unichr)\n\nReturns the general category assigned to the Unicode character\nunichr as string." | ||
250 | Returns the general category assigned to the Unicode character\n\static char unicodedata_category__doc__[] = "category(unichr)\n\nReturns the general category assigned to the Unicode character\nunichr as string." | ||
251 | unichr as string.")static char unicodedata_category__doc__[] = "category(unichr)\n\nReturns the general category assigned to the Unicode character\nunichr as string."; | ||
252 | |||
253 | static PyObject * | ||
254 | unicodedata_category(PyObject *self, PyObject *args) | ||
255 | { | ||
256 | PyUnicodeObject *v; | ||
257 | int index; | ||
258 | Py_UCS4 c; | ||
259 | |||
260 | if (!PyArg_ParseTuple(args, "O!:category", | ||
261 | &PyUnicode_Type, &v)) | ||
262 | return NULL((void*)0); | ||
263 | c = getuchar(v); | ||
264 | if (c == (Py_UCS4)-1) | ||
265 | return NULL((void*)0); | ||
266 | index = (int) _getrecord_ex(c)->category; | ||
267 | if (self && UCD_Check(self)((((PyObject*)(self))->ob_type)==&UCD_Type)) { | ||
268 | const change_record *old = get_old_record(self, c)((((PreviousDBVersion*)self)->getrecord)(c)); | ||
269 | if (old->category_changed != 0xFF) | ||
270 | index = old->category_changed; | ||
271 | } | ||
272 | return PyUnicode_FromStringPyUnicodeUCS2_FromString(_PyUnicode_CategoryNames[index]); | ||
273 | } | ||
274 | |||
275 | PyDoc_STRVAR(unicodedata_bidirectional__doc__,static char unicodedata_bidirectional__doc__[] = "bidirectional(unichr)\n\nReturns the bidirectional category assigned to the Unicode character\nunichr as string. If no such value is defined, an empty string is\nreturned." | ||
276 | "bidirectional(unichr)\n\static char unicodedata_bidirectional__doc__[] = "bidirectional(unichr)\n\nReturns the bidirectional category assigned to the Unicode character\nunichr as string. If no such value is defined, an empty string is\nreturned." | ||
277 | \n\static char unicodedata_bidirectional__doc__[] = "bidirectional(unichr)\n\nReturns the bidirectional category assigned to the Unicode character\nunichr as string. If no such value is defined, an empty string is\nreturned." | ||
278 | Returns the bidirectional category assigned to the Unicode character\n\static char unicodedata_bidirectional__doc__[] = "bidirectional(unichr)\n\nReturns the bidirectional category assigned to the Unicode character\nunichr as string. If no such value is defined, an empty string is\nreturned." | ||
279 | unichr as string. If no such value is defined, an empty string is\n\static char unicodedata_bidirectional__doc__[] = "bidirectional(unichr)\n\nReturns the bidirectional category assigned to the Unicode character\nunichr as string. If no such value is defined, an empty string is\nreturned." | ||
280 | returned.")static char unicodedata_bidirectional__doc__[] = "bidirectional(unichr)\n\nReturns the bidirectional category assigned to the Unicode character\nunichr as string. If no such value is defined, an empty string is\nreturned."; | ||
281 | |||
282 | static PyObject * | ||
283 | unicodedata_bidirectional(PyObject *self, PyObject *args) | ||
284 | { | ||
285 | PyUnicodeObject *v; | ||
286 | int index; | ||
287 | Py_UCS4 c; | ||
288 | |||
289 | if (!PyArg_ParseTuple(args, "O!:bidirectional", | ||
290 | &PyUnicode_Type, &v)) | ||
291 | return NULL((void*)0); | ||
292 | c = getuchar(v); | ||
293 | if (c == (Py_UCS4)-1) | ||
294 | return NULL((void*)0); | ||
295 | index = (int) _getrecord_ex(c)->bidirectional; | ||
296 | if (self && UCD_Check(self)((((PyObject*)(self))->ob_type)==&UCD_Type)) { | ||
297 | const change_record *old = get_old_record(self, c)((((PreviousDBVersion*)self)->getrecord)(c)); | ||
298 | if (old->category_changed == 0) | ||
299 | index = 0; /* unassigned */ | ||
300 | else if (old->bidir_changed != 0xFF) | ||
301 | index = old->bidir_changed; | ||
302 | } | ||
303 | return PyUnicode_FromStringPyUnicodeUCS2_FromString(_PyUnicode_BidirectionalNames[index]); | ||
304 | } | ||
305 | |||
306 | PyDoc_STRVAR(unicodedata_combining__doc__,static char unicodedata_combining__doc__[] = "combining(unichr)\n\nReturns the canonical combining class assigned to the Unicode\ncharacter unichr as integer. Returns 0 if no combining class is\ndefined." | ||
307 | "combining(unichr)\n\static char unicodedata_combining__doc__[] = "combining(unichr)\n\nReturns the canonical combining class assigned to the Unicode\ncharacter unichr as integer. Returns 0 if no combining class is\ndefined." | ||
308 | \n\static char unicodedata_combining__doc__[] = "combining(unichr)\n\nReturns the canonical combining class assigned to the Unicode\ncharacter unichr as integer. Returns 0 if no combining class is\ndefined." | ||
309 | Returns the canonical combining class assigned to the Unicode\n\static char unicodedata_combining__doc__[] = "combining(unichr)\n\nReturns the canonical combining class assigned to the Unicode\ncharacter unichr as integer. Returns 0 if no combining class is\ndefined." | ||
310 | character unichr as integer. Returns 0 if no combining class is\n\static char unicodedata_combining__doc__[] = "combining(unichr)\n\nReturns the canonical combining class assigned to the Unicode\ncharacter unichr as integer. Returns 0 if no combining class is\ndefined." | ||
311 | defined.")static char unicodedata_combining__doc__[] = "combining(unichr)\n\nReturns the canonical combining class assigned to the Unicode\ncharacter unichr as integer. Returns 0 if no combining class is\ndefined."; | ||
312 | |||
313 | static PyObject * | ||
314 | unicodedata_combining(PyObject *self, PyObject *args) | ||
315 | { | ||
316 | PyUnicodeObject *v; | ||
317 | int index; | ||
318 | Py_UCS4 c; | ||
319 | |||
320 | if (!PyArg_ParseTuple(args, "O!:combining", | ||
321 | &PyUnicode_Type, &v)) | ||
322 | return NULL((void*)0); | ||
323 | c = getuchar(v); | ||
324 | if (c == (Py_UCS4)-1) | ||
325 | return NULL((void*)0); | ||
326 | index = (int) _getrecord_ex(c)->combining; | ||
327 | if (self && UCD_Check(self)((((PyObject*)(self))->ob_type)==&UCD_Type)) { | ||
328 | const change_record *old = get_old_record(self, c)((((PreviousDBVersion*)self)->getrecord)(c)); | ||
329 | if (old->category_changed == 0) | ||
330 | index = 0; /* unassigned */ | ||
331 | } | ||
332 | return PyLong_FromLong(index); | ||
333 | } | ||
334 | |||
335 | PyDoc_STRVAR(unicodedata_mirrored__doc__,static char unicodedata_mirrored__doc__[] = "mirrored(unichr)\n\nReturns the mirrored property assigned to the Unicode character\nunichr as integer. Returns 1 if the character has been identified as\na \"mirrored\" character in bidirectional text, 0 otherwise." | ||
336 | "mirrored(unichr)\n\static char unicodedata_mirrored__doc__[] = "mirrored(unichr)\n\nReturns the mirrored property assigned to the Unicode character\nunichr as integer. Returns 1 if the character has been identified as\na \"mirrored\" character in bidirectional text, 0 otherwise." | ||
337 | \n\static char unicodedata_mirrored__doc__[] = "mirrored(unichr)\n\nReturns the mirrored property assigned to the Unicode character\nunichr as integer. Returns 1 if the character has been identified as\na \"mirrored\" character in bidirectional text, 0 otherwise." | ||
338 | Returns the mirrored property assigned to the Unicode character\n\static char unicodedata_mirrored__doc__[] = "mirrored(unichr)\n\nReturns the mirrored property assigned to the Unicode character\nunichr as integer. Returns 1 if the character has been identified as\na \"mirrored\" character in bidirectional text, 0 otherwise." | ||
339 | unichr as integer. Returns 1 if the character has been identified as\n\static char unicodedata_mirrored__doc__[] = "mirrored(unichr)\n\nReturns the mirrored property assigned to the Unicode character\nunichr as integer. Returns 1 if the character has been identified as\na \"mirrored\" character in bidirectional text, 0 otherwise." | ||
340 | a \"mirrored\" character in bidirectional text, 0 otherwise.")static char unicodedata_mirrored__doc__[] = "mirrored(unichr)\n\nReturns the mirrored property assigned to the Unicode character\nunichr as integer. Returns 1 if the character has been identified as\na \"mirrored\" character in bidirectional text, 0 otherwise."; | ||
341 | |||
342 | static PyObject * | ||
343 | unicodedata_mirrored(PyObject *self, PyObject *args) | ||
344 | { | ||
345 | PyUnicodeObject *v; | ||
346 | int index; | ||
347 | Py_UCS4 c; | ||
348 | |||
349 | if (!PyArg_ParseTuple(args, "O!:mirrored", | ||
350 | &PyUnicode_Type, &v)) | ||
351 | return NULL((void*)0); | ||
352 | c = getuchar(v); | ||
353 | if (c == (Py_UCS4)-1) | ||
354 | return NULL((void*)0); | ||
355 | index = (int) _getrecord_ex(c)->mirrored; | ||
356 | if (self && UCD_Check(self)((((PyObject*)(self))->ob_type)==&UCD_Type)) { | ||
357 | const change_record *old = get_old_record(self, c)((((PreviousDBVersion*)self)->getrecord)(c)); | ||
358 | if (old->category_changed == 0) | ||
359 | index = 0; /* unassigned */ | ||
360 | else if (old->mirrored_changed != 0xFF) | ||
361 | index = old->mirrored_changed; | ||
362 | } | ||
363 | return PyLong_FromLong(index); | ||
364 | } | ||
365 | |||
366 | PyDoc_STRVAR(unicodedata_east_asian_width__doc__,static char unicodedata_east_asian_width__doc__[] = "east_asian_width(unichr)\n\nReturns the east asian width assigned to the Unicode character\nunichr as string." | ||
367 | "east_asian_width(unichr)\n\static char unicodedata_east_asian_width__doc__[] = "east_asian_width(unichr)\n\nReturns the east asian width assigned to the Unicode character\nunichr as string." | ||
368 | \n\static char unicodedata_east_asian_width__doc__[] = "east_asian_width(unichr)\n\nReturns the east asian width assigned to the Unicode character\nunichr as string." | ||
369 | Returns the east asian width assigned to the Unicode character\n\static char unicodedata_east_asian_width__doc__[] = "east_asian_width(unichr)\n\nReturns the east asian width assigned to the Unicode character\nunichr as string." | ||
370 | unichr as string.")static char unicodedata_east_asian_width__doc__[] = "east_asian_width(unichr)\n\nReturns the east asian width assigned to the Unicode character\nunichr as string."; | ||
371 | |||
372 | static PyObject * | ||
373 | unicodedata_east_asian_width(PyObject *self, PyObject *args) | ||
374 | { | ||
375 | PyUnicodeObject *v; | ||
376 | int index; | ||
377 | Py_UCS4 c; | ||
378 | |||
379 | if (!PyArg_ParseTuple(args, "O!:east_asian_width", | ||
380 | &PyUnicode_Type, &v)) | ||
381 | return NULL((void*)0); | ||
382 | c = getuchar(v); | ||
383 | if (c == (Py_UCS4)-1) | ||
384 | return NULL((void*)0); | ||
385 | index = (int) _getrecord_ex(c)->east_asian_width; | ||
386 | if (self && UCD_Check(self)((((PyObject*)(self))->ob_type)==&UCD_Type)) { | ||
387 | const change_record *old = get_old_record(self, c)((((PreviousDBVersion*)self)->getrecord)(c)); | ||
388 | if (old->category_changed == 0) | ||
389 | index = 0; /* unassigned */ | ||
390 | } | ||
391 | return PyUnicode_FromStringPyUnicodeUCS2_FromString(_PyUnicode_EastAsianWidthNames[index]); | ||
392 | } | ||
393 | |||
394 | PyDoc_STRVAR(unicodedata_decomposition__doc__,static char unicodedata_decomposition__doc__[] = "decomposition(unichr)\n\nReturns the character decomposition mapping assigned to the Unicode\ncharacter unichr as string. An empty string is returned in case no\nsuch mapping is defined." | ||
395 | "decomposition(unichr)\n\static char unicodedata_decomposition__doc__[] = "decomposition(unichr)\n\nReturns the character decomposition mapping assigned to the Unicode\ncharacter unichr as string. An empty string is returned in case no\nsuch mapping is defined." | ||
396 | \n\static char unicodedata_decomposition__doc__[] = "decomposition(unichr)\n\nReturns the character decomposition mapping assigned to the Unicode\ncharacter unichr as string. An empty string is returned in case no\nsuch mapping is defined." | ||
397 | Returns the character decomposition mapping assigned to the Unicode\n\static char unicodedata_decomposition__doc__[] = "decomposition(unichr)\n\nReturns the character decomposition mapping assigned to the Unicode\ncharacter unichr as string. An empty string is returned in case no\nsuch mapping is defined." | ||
398 | character unichr as string. An empty string is returned in case no\n\static char unicodedata_decomposition__doc__[] = "decomposition(unichr)\n\nReturns the character decomposition mapping assigned to the Unicode\ncharacter unichr as string. An empty string is returned in case no\nsuch mapping is defined." | ||
399 | such mapping is defined.")static char unicodedata_decomposition__doc__[] = "decomposition(unichr)\n\nReturns the character decomposition mapping assigned to the Unicode\ncharacter unichr as string. An empty string is returned in case no\nsuch mapping is defined."; | ||
400 | |||
401 | static PyObject * | ||
402 | unicodedata_decomposition(PyObject *self, PyObject *args) | ||
403 | { | ||
404 | PyUnicodeObject *v; | ||
405 | char decomp[256]; | ||
406 | int code, index, count; | ||
407 | size_t i; | ||
408 | unsigned int prefix_index; | ||
409 | Py_UCS4 c; | ||
410 | |||
411 | if (!PyArg_ParseTuple(args, "O!:decomposition", | ||
412 | &PyUnicode_Type, &v)) | ||
413 | return NULL((void*)0); | ||
414 | c = getuchar(v); | ||
415 | if (c == (Py_UCS4)-1) | ||
416 | return NULL((void*)0); | ||
417 | |||
418 | code = (int)c; | ||
419 | |||
420 | if (self && UCD_Check(self)((((PyObject*)(self))->ob_type)==&UCD_Type)) { | ||
421 | const change_record *old = get_old_record(self, c)((((PreviousDBVersion*)self)->getrecord)(c)); | ||
422 | if (old->category_changed == 0) | ||
423 | return PyUnicode_FromStringPyUnicodeUCS2_FromString(""); /* unassigned */ | ||
424 | } | ||
425 | |||
426 | if (code < 0 || code >= 0x110000) | ||
427 | index = 0; | ||
428 | else { | ||
429 | index = decomp_index1[(code>>DECOMP_SHIFT8)]; | ||
430 | index = decomp_index2[(index<<DECOMP_SHIFT8)+ | ||
431 | (code&((1<<DECOMP_SHIFT8)-1))]; | ||
432 | } | ||
433 | |||
434 | /* high byte is number of hex bytes (usually one or two), low byte | ||
435 | is prefix code (from*/ | ||
436 | count = decomp_data[index] >> 8; | ||
437 | |||
438 | /* XXX: could allocate the PyString up front instead | ||
439 | (strlen(prefix) + 5 * count + 1 bytes) */ | ||
440 | |||
441 | /* Based on how index is calculated above and decomp_data is generated | ||
442 | from Tools/unicode/makeunicodedata.py, it should not be possible | ||
443 | to overflow decomp_prefix. */ | ||
444 | prefix_index = decomp_data[index] & 255; | ||
445 | assert(prefix_index < (sizeof(decomp_prefix)/sizeof(*decomp_prefix)))(__builtin_expect(!(prefix_index < (sizeof(decomp_prefix)/ sizeof(*decomp_prefix))), 0) ? __assert_rtn(__func__, "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c" , 445, "prefix_index < (sizeof(decomp_prefix)/sizeof(*decomp_prefix))" ) : (void)0); | ||
446 | |||
447 | /* copy prefix */ | ||
448 | i = strlen(decomp_prefix[prefix_index]); | ||
449 | memcpy(decomp, decomp_prefix[prefix_index], i)((__builtin_object_size (decomp, 0) != (size_t) -1) ? __builtin___memcpy_chk (decomp, decomp_prefix[prefix_index], i, __builtin_object_size (decomp, 0)) : __inline_memcpy_chk (decomp, decomp_prefix[prefix_index ], i)); | ||
450 | |||
451 | while (count-- > 0) { | ||
452 | if (i) | ||
453 | decomp[i++] = ' '; | ||
454 | assert(i < sizeof(decomp))(__builtin_expect(!(i < sizeof(decomp)), 0) ? __assert_rtn (__func__, "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c" , 454, "i < sizeof(decomp)") : (void)0); | ||
455 | PyOS_snprintf(decomp + i, sizeof(decomp) - i, "%04X", | ||
456 | decomp_data[++index]); | ||
457 | i += strlen(decomp + i); | ||
458 | } | ||
459 | return PyUnicode_FromStringAndSizePyUnicodeUCS2_FromStringAndSize(decomp, i); | ||
460 | } | ||
461 | |||
462 | static void | ||
463 | get_decomp_record(PyObject *self, Py_UCS4 code, int *index, int *prefix, int *count) | ||
464 | { | ||
465 | if (code >= 0x110000) { | ||
466 | *index = 0; | ||
467 | } else if (self && UCD_Check(self)((((PyObject*)(self))->ob_type)==&UCD_Type) && | ||
468 | get_old_record(self, code)((((PreviousDBVersion*)self)->getrecord)(code))->category_changed==0) { | ||
469 | /* unassigned in old version */ | ||
470 | *index = 0; | ||
471 | } | ||
472 | else { | ||
473 | *index = decomp_index1[(code>>DECOMP_SHIFT8)]; | ||
474 | *index = decomp_index2[(*index<<DECOMP_SHIFT8)+ | ||
475 | (code&((1<<DECOMP_SHIFT8)-1))]; | ||
476 | } | ||
477 | |||
478 | /* high byte is number of hex bytes (usually one or two), low byte | ||
479 | is prefix code (from*/ | ||
480 | *count = decomp_data[*index] >> 8; | ||
481 | *prefix = decomp_data[*index] & 255; | ||
482 | |||
483 | (*index)++; | ||
484 | } | ||
485 | |||
486 | #define SBase0xAC00 0xAC00 | ||
487 | #define LBase0x1100 0x1100 | ||
488 | #define VBase0x1161 0x1161 | ||
489 | #define TBase0x11A7 0x11A7 | ||
490 | #define LCount19 19 | ||
491 | #define VCount21 21 | ||
492 | #define TCount28 28 | ||
493 | #define NCount(21*28) (VCount21*TCount28) | ||
494 | #define SCount(19*(21*28)) (LCount19*NCount(21*28)) | ||
495 | |||
496 | static PyObject* | ||
497 | nfd_nfkd(PyObject *self, PyObject *input, int k) | ||
498 | { | ||
499 | PyObject *result; | ||
500 | Py_UNICODE *i, *end, *o; | ||
501 | /* Longest decomposition in Unicode 3.2: U+FDFA */ | ||
502 | Py_UNICODE stack[20]; | ||
503 | Py_ssize_t space, isize; | ||
504 | int index, prefix, count, stackptr; | ||
505 | unsigned char prev, cur; | ||
506 | |||
507 | stackptr = 0; | ||
508 | isize = PyUnicode_GET_SIZE(input)((__builtin_expect(!(((((((PyObject*)(input))->ob_type))-> tp_flags & ((1L<<28))) != 0)), 0) ? __assert_rtn(__func__ , "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c", 508 , "PyUnicode_Check(input)") : (void)0),(((PyUnicodeObject *)( input))->length)); | ||
509 | /* Overallocate atmost 10 characters. */ | ||
510 | space = (isize > 10 ? 10 : isize) + isize; | ||
| |||
511 | result = PyUnicode_FromUnicodePyUnicodeUCS2_FromUnicode(NULL((void*)0), space); | ||
512 | if (!result) | ||
| |||
513 | return NULL((void*)0); | ||
514 | i = PyUnicode_AS_UNICODE(input)((__builtin_expect(!(((((((PyObject*)(input))->ob_type))-> tp_flags & ((1L<<28))) != 0)), 0) ? __assert_rtn(__func__ , "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c", 514 , "PyUnicode_Check(input)") : (void)0),(((PyUnicodeObject *)( input))->str)); | ||
515 | end = i + isize; | ||
516 | o = PyUnicode_AS_UNICODE(result)((__builtin_expect(!(((((((PyObject*)(result))->ob_type))-> tp_flags & ((1L<<28))) != 0)), 0) ? __assert_rtn(__func__ , "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c", 516 , "PyUnicode_Check(result)") : (void)0),(((PyUnicodeObject *) (result))->str)); | ||
517 | |||
518 | while (i < end) { | ||
| |||
519 | stack[stackptr++] = *i++; | ||
520 | while(stackptr) { | ||
| |||
521 | Py_UNICODE code = stack[--stackptr]; | ||
| |||
522 | /* Hangul Decomposition adds three characters in | ||
523 | a single step, so we need atleast that much room. */ | ||
524 | if (space < 3) { | ||
525 | Py_ssize_t newsize = PyUnicode_GET_SIZE(result)((__builtin_expect(!(((((((PyObject*)(result))->ob_type))-> tp_flags & ((1L<<28))) != 0)), 0) ? __assert_rtn(__func__ , "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c", 525 , "PyUnicode_Check(result)") : (void)0),(((PyUnicodeObject *) (result))->length)) + 10; | ||
526 | space += 10; | ||
527 | if (PyUnicode_ResizePyUnicodeUCS2_Resize(&result, newsize) == -1) | ||
528 | return NULL((void*)0); | ||
529 | o = PyUnicode_AS_UNICODE(result)((__builtin_expect(!(((((((PyObject*)(result))->ob_type))-> tp_flags & ((1L<<28))) != 0)), 0) ? __assert_rtn(__func__ , "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c", 529 , "PyUnicode_Check(result)") : (void)0),(((PyUnicodeObject *) (result))->str)) + newsize - space; | ||
530 | } | ||
531 | /* Hangul Decomposition. */ | ||
532 | if (SBase0xAC00 <= code && code < (SBase0xAC00+SCount(19*(21*28)))) { | ||
533 | int SIndex = code - SBase0xAC00; | ||
534 | int L = LBase0x1100 + SIndex / NCount(21*28); | ||
535 | int V = VBase0x1161 + (SIndex % NCount(21*28)) / TCount28; | ||
536 | int T = TBase0x11A7 + SIndex % TCount28; | ||
537 | *o++ = L; | ||
538 | *o++ = V; | ||
539 | space -= 2; | ||
540 | if (T != TBase0x11A7) { | ||
541 | *o++ = T; | ||
542 | space --; | ||
543 | } | ||
544 | continue; | ||
545 | } | ||
546 | /* normalization changes */ | ||
547 | if (self && UCD_Check(self)((((PyObject*)(self))->ob_type)==&UCD_Type)) { | ||
548 | Py_UCS4 value = ((PreviousDBVersion*)self)->normalization(code); | ||
549 | if (value != 0) { | ||
550 | stack[stackptr++] = value; | ||
551 | continue; | ||
552 | } | ||
553 | } | ||
554 | |||
555 | /* Other decompositions. */ | ||
556 | get_decomp_record(self, code, &index, &prefix, &count); | ||
557 | |||
558 | /* Copy character if it is not decomposable, or has a | ||
559 | compatibility decomposition, but we do NFD. */ | ||
560 | if (!count || (prefix && !k)) { | ||
561 | *o++ = code; | ||
562 | space--; | ||
563 | continue; | ||
564 | } | ||
565 | /* Copy decomposition onto the stack, in reverse | ||
566 | order. */ | ||
567 | while(count) { | ||
568 | code = decomp_data[index + (--count)]; | ||
569 | stack[stackptr++] = code; | ||
570 | } | ||
571 | } | ||
572 | } | ||
573 | |||
574 | /* Drop overallocation. Cannot fail. */ | ||
575 | PyUnicode_ResizePyUnicodeUCS2_Resize(&result, PyUnicode_GET_SIZE(result)((__builtin_expect(!(((((((PyObject*)(result))->ob_type))-> tp_flags & ((1L<<28))) != 0)), 0) ? __assert_rtn(__func__ , "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c", 575 , "PyUnicode_Check(result)") : (void)0),(((PyUnicodeObject *) (result))->length)) - space); | ||
576 | |||
577 | /* Sort canonically. */ | ||
578 | i = PyUnicode_AS_UNICODE(result)((__builtin_expect(!(((((((PyObject*)(result))->ob_type))-> tp_flags & ((1L<<28))) != 0)), 0) ? __assert_rtn(__func__ , "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c", 578 , "PyUnicode_Check(result)") : (void)0),(((PyUnicodeObject *) (result))->str)); | ||
579 | prev = _getrecord_ex(*i)->combining; | ||
580 | end = i + PyUnicode_GET_SIZE(result)((__builtin_expect(!(((((((PyObject*)(result))->ob_type))-> tp_flags & ((1L<<28))) != 0)), 0) ? __assert_rtn(__func__ , "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c", 580 , "PyUnicode_Check(result)") : (void)0),(((PyUnicodeObject *) (result))->length)); | ||
581 | for (i++; i < end; i++) { | ||
582 | cur = _getrecord_ex(*i)->combining; | ||
583 | if (prev == 0 || cur == 0 || prev <= cur) { | ||
584 | prev = cur; | ||
585 | continue; | ||
586 | } | ||
587 | /* Non-canonical order. Need to switch *i with previous. */ | ||
588 | o = i - 1; | ||
589 | while (1) { | ||
590 | Py_UNICODE tmp = o[1]; | ||
591 | o[1] = o[0]; | ||
592 | o[0] = tmp; | ||
593 | o--; | ||
594 | if (o < PyUnicode_AS_UNICODE(result)((__builtin_expect(!(((((((PyObject*)(result))->ob_type))-> tp_flags & ((1L<<28))) != 0)), 0) ? __assert_rtn(__func__ , "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c", 594 , "PyUnicode_Check(result)") : (void)0),(((PyUnicodeObject *) (result))->str))) | ||
595 | break; | ||
596 | prev = _getrecord_ex(*o)->combining; | ||
597 | if (prev == 0 || prev <= cur) | ||
598 | break; | ||
599 | } | ||
600 | prev = _getrecord_ex(*i)->combining; | ||
601 | } | ||
602 | return result; | ||
603 | } | ||
604 | |||
605 | static int | ||
606 | find_nfc_index(PyObject *self, struct reindex* nfc, Py_UNICODE code) | ||
607 | { | ||
608 | int index; | ||
609 | for (index = 0; nfc[index].start; index++) { | ||
610 | int start = nfc[index].start; | ||
611 | if (code < start) | ||
612 | return -1; | ||
613 | if (code <= start + nfc[index].count) { | ||
614 | int delta = code - start; | ||
615 | return nfc[index].index + delta; | ||
616 | } | ||
617 | } | ||
618 | return -1; | ||
619 | } | ||
620 | |||
621 | static PyObject* | ||
622 | nfc_nfkc(PyObject *self, PyObject *input, int k) | ||
623 | { | ||
624 | PyObject *result; | ||
625 | Py_UNICODE *i, *i1, *o, *end; | ||
626 | int f,l,index,index1,comb; | ||
627 | Py_UNICODE code; | ||
628 | Py_UNICODE *skipped[20]; | ||
629 | int cskipped = 0; | ||
630 | |||
631 | result = nfd_nfkd(self, input, k); | ||
632 | if (!result) | ||
633 | return NULL((void*)0); | ||
634 | |||
635 | /* We are going to modify result in-place. | ||
636 | If nfd_nfkd is changed to sometimes return the input, | ||
637 | this code needs to be reviewed. */ | ||
638 | assert(result != input)(__builtin_expect(!(result != input), 0) ? __assert_rtn(__func__ , "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c", 638 , "result != input") : (void)0); | ||
639 | |||
640 | i = PyUnicode_AS_UNICODE(result)((__builtin_expect(!(((((((PyObject*)(result))->ob_type))-> tp_flags & ((1L<<28))) != 0)), 0) ? __assert_rtn(__func__ , "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c", 640 , "PyUnicode_Check(result)") : (void)0),(((PyUnicodeObject *) (result))->str)); | ||
641 | end = i + PyUnicode_GET_SIZE(result)((__builtin_expect(!(((((((PyObject*)(result))->ob_type))-> tp_flags & ((1L<<28))) != 0)), 0) ? __assert_rtn(__func__ , "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c", 641 , "PyUnicode_Check(result)") : (void)0),(((PyUnicodeObject *) (result))->length)); | ||
642 | o = PyUnicode_AS_UNICODE(result)((__builtin_expect(!(((((((PyObject*)(result))->ob_type))-> tp_flags & ((1L<<28))) != 0)), 0) ? __assert_rtn(__func__ , "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c", 642 , "PyUnicode_Check(result)") : (void)0),(((PyUnicodeObject *) (result))->str)); | ||
643 | |||
644 | again: | ||
645 | while (i < end) { | ||
646 | for (index = 0; index < cskipped; index++) { | ||
647 | if (skipped[index] == i) { | ||
648 | /* *i character is skipped. | ||
649 | Remove from list. */ | ||
650 | skipped[index] = skipped[cskipped-1]; | ||
651 | cskipped--; | ||
652 | i++; | ||
653 | goto again; /* continue while */ | ||
654 | } | ||
655 | } | ||
656 | /* Hangul Composition. We don't need to check for <LV,T> | ||
657 | pairs, since we always have decomposed data. */ | ||
658 | if (LBase0x1100 <= *i && *i < (LBase0x1100+LCount19) && | ||
659 | i + 1 < end && | ||
660 | VBase0x1161 <= i[1] && i[1] <= (VBase0x1161+VCount21)) { | ||
661 | int LIndex, VIndex; | ||
662 | LIndex = i[0] - LBase0x1100; | ||
663 | VIndex = i[1] - VBase0x1161; | ||
664 | code = SBase0xAC00 + (LIndex*VCount21+VIndex)*TCount28; | ||
665 | i+=2; | ||
666 | if (i < end && | ||
667 | TBase0x11A7 <= *i && *i <= (TBase0x11A7+TCount28)) { | ||
668 | code += *i-TBase0x11A7; | ||
669 | i++; | ||
670 | } | ||
671 | *o++ = code; | ||
672 | continue; | ||
673 | } | ||
674 | |||
675 | f = find_nfc_index(self, nfc_first, *i); | ||
676 | if (f == -1) { | ||
677 | *o++ = *i++; | ||
678 | continue; | ||
679 | } | ||
680 | /* Find next unblocked character. */ | ||
681 | i1 = i+1; | ||
682 | comb = 0; | ||
683 | while (i1 < end) { | ||
684 | int comb1 = _getrecord_ex(*i1)->combining; | ||
685 | if (comb) { | ||
686 | if (comb1 == 0) | ||
687 | break; | ||
688 | if (comb >= comb1) { | ||
689 | /* Character is blocked. */ | ||
690 | i1++; | ||
691 | continue; | ||
692 | } | ||
693 | } | ||
694 | l = find_nfc_index(self, nfc_last, *i1); | ||
695 | /* *i1 cannot be combined with *i. If *i1 | ||
696 | is a starter, we don't need to look further. | ||
697 | Otherwise, record the combining class. */ | ||
698 | if (l == -1) { | ||
699 | not_combinable: | ||
700 | if (comb1 == 0) | ||
701 | break; | ||
702 | comb = comb1; | ||
703 | i1++; | ||
704 | continue; | ||
705 | } | ||
706 | index = f*TOTAL_LAST55 + l; | ||
707 | index1 = comp_index[index >> COMP_SHIFT2]; | ||
708 | code = comp_data[(index1<<COMP_SHIFT2)+ | ||
709 | (index&((1<<COMP_SHIFT2)-1))]; | ||
710 | if (code == 0) | ||
711 | goto not_combinable; | ||
712 | |||
713 | /* Replace the original character. */ | ||
714 | *i = code; | ||
715 | /* Mark the second character unused. */ | ||
716 | assert(cskipped < 20)(__builtin_expect(!(cskipped < 20), 0) ? __assert_rtn(__func__ , "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c", 716 , "cskipped < 20") : (void)0); | ||
717 | skipped[cskipped++] = i1; | ||
718 | i1++; | ||
719 | f = find_nfc_index(self, nfc_first, *i); | ||
720 | if (f == -1) | ||
721 | break; | ||
722 | } | ||
723 | *o++ = *i++; | ||
724 | } | ||
725 | if (o != end) | ||
726 | PyUnicode_ResizePyUnicodeUCS2_Resize(&result, o - PyUnicode_AS_UNICODE(result)((__builtin_expect(!(((((((PyObject*)(result))->ob_type))-> tp_flags & ((1L<<28))) != 0)), 0) ? __assert_rtn(__func__ , "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c", 726 , "PyUnicode_Check(result)") : (void)0),(((PyUnicodeObject *) (result))->str))); | ||
727 | return result; | ||
728 | } | ||
729 | |||
730 | /* Return 1 if the input is certainly normalized, 0 if it might not be. */ | ||
731 | static int | ||
732 | is_normalized(PyObject *self, PyObject *input, int nfc, int k) | ||
733 | { | ||
734 | Py_UNICODE *i, *end; | ||
735 | unsigned char prev_combining = 0, quickcheck_mask; | ||
736 | |||
737 | /* An older version of the database is requested, quickchecks must be | ||
738 | disabled. */ | ||
739 | if (self && UCD_Check(self)((((PyObject*)(self))->ob_type)==&UCD_Type)) | ||
740 | return 0; | ||
741 | |||
742 | /* The two quickcheck bits at this shift mean 0=Yes, 1=Maybe, 2=No, | ||
743 | as described in http://unicode.org/reports/tr15/#Annex8. */ | ||
744 | quickcheck_mask = 3 << ((nfc ? 4 : 0) + (k ? 2 : 0)); | ||
745 | |||
746 | i = PyUnicode_AS_UNICODE(input)((__builtin_expect(!(((((((PyObject*)(input))->ob_type))-> tp_flags & ((1L<<28))) != 0)), 0) ? __assert_rtn(__func__ , "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c", 746 , "PyUnicode_Check(input)") : (void)0),(((PyUnicodeObject *)( input))->str)); | ||
747 | end = i + PyUnicode_GET_SIZE(input)((__builtin_expect(!(((((((PyObject*)(input))->ob_type))-> tp_flags & ((1L<<28))) != 0)), 0) ? __assert_rtn(__func__ , "/Users/brett/Dev/python/3.x/py3k/Modules/unicodedata.c", 747 , "PyUnicode_Check(input)") : (void)0),(((PyUnicodeObject *)( input))->length)); | ||
748 | while (i < end) { | ||
749 | const _PyUnicode_DatabaseRecord *record = _getrecord_ex(*i++); | ||
750 | unsigned char combining = record->combining; | ||
751 | unsigned char quickcheck = record->normalization_quick_check; | ||
752 | |||
753 | if (quickcheck & quickcheck_mask) | ||
754 | return 0; /* this string might need normalization */ | ||
755 | if (combining && prev_combining > combining) | ||
756 | return 0; /* non-canonical sort order, not normalized */ | ||
757 | prev_combining = combining; | ||
758 | } | ||
759 | return 1; /* certainly normalized */ | ||
760 | } | ||
761 | |||
762 | PyDoc_STRVAR(unicodedata_normalize__doc__,static char unicodedata_normalize__doc__[] = "normalize(form, unistr)\n\nReturn the normal form 'form' for the Unicode string unistr. Valid\nvalues for form are 'NFC', 'NFKC', 'NFD', and 'NFKD'." | ||
763 | "normalize(form, unistr)\n\static char unicodedata_normalize__doc__[] = "normalize(form, unistr)\n\nReturn the normal form 'form' for the Unicode string unistr. Valid\nvalues for form are 'NFC', 'NFKC', 'NFD', and 'NFKD'." | ||
764 | \n\static char unicodedata_normalize__doc__[] = "normalize(form, unistr)\n\nReturn the normal form 'form' for the Unicode string unistr. Valid\nvalues for form are 'NFC', 'NFKC', 'NFD', and 'NFKD'." | ||
765 | Return the normal form 'form' for the Unicode string unistr. Valid\n\static char unicodedata_normalize__doc__[] = "normalize(form, unistr)\n\nReturn the normal form 'form' for the Unicode string unistr. Valid\nvalues for form are 'NFC', 'NFKC', 'NFD', and 'NFKD'." | ||
766 | values for form are 'NFC', 'NFKC', 'NFD', and 'NFKD'.")static char unicodedata_normalize__doc__[] = "normalize(form, unistr)\n\nReturn the normal form 'form' for the Unicode string unistr. Valid\nvalues for form are 'NFC', 'NFKC', 'NFD', and 'NFKD'."; | ||
767 | |||
768 | static PyObject* | ||
769 | unicodedata_normalize(PyObject *self, PyObject *args) | ||
770 | { | ||
771 | char *form; | ||
772 | PyObject *input; | ||
773 | |||
774 | if(!PyArg_ParseTuple(args, "sO!:normalize", | ||
775 | &form, &PyUnicode_Type, &input)) | ||
776 | return NULL((void*)0); | ||
777 | |||
778 | if (PyUnicode_GetSizePyUnicodeUCS2_GetSize(input) == 0) { | ||
779 | /* Special case empty input strings, since resizing | ||
780 | them later would cause internal errors. */ | ||
781 | Py_INCREF(input)( _Py_RefTotal++ , ((PyObject*)(input))->ob_refcnt++); | ||
782 | return input; | ||
783 | } | ||
784 | |||
785 | if (strcmp(form, "NFC") == 0) { | ||
786 | if (is_normalized(self, input, 1, 0)) { | ||
787 | Py_INCREF(input)( _Py_RefTotal++ , ((PyObject*)(input))->ob_refcnt++); | ||
788 | return input; | ||
789 | } | ||
790 | return nfc_nfkc(self, input, 0); | ||
791 | } | ||
792 | if (strcmp(form, "NFKC") == 0) { | ||
793 | if (is_normalized(self, input, 1, 1)) { | ||
794 | Py_INCREF(input)( _Py_RefTotal++ , ((PyObject*)(input))->ob_refcnt++); | ||
795 | return input; | ||
796 | } | ||
797 | return nfc_nfkc(self, input, 1); | ||
798 | } | ||
799 | if (strcmp(form, "NFD") == 0) { | ||
800 | if (is_normalized(self, input, 0, 0)) { | ||
801 | Py_INCREF(input)( _Py_RefTotal++ , ((PyObject*)(input))->ob_refcnt++); | ||
802 | return input; | ||
803 | } | ||
804 | return nfd_nfkd(self, input, 0); | ||
805 | } | ||
806 | if (strcmp(form, "NFKD") == 0) { | ||
807 | if (is_normalized(self, input, 0, 1)) { | ||
808 | Py_INCREF(input)( _Py_RefTotal++ , ((PyObject*)(input))->ob_refcnt++); | ||
809 | return input; | ||
810 | } | ||
811 | return nfd_nfkd(self, input, 1); | ||
812 | } | ||
813 | PyErr_SetString(PyExc_ValueError, "invalid normalization form"); | ||
814 | return NULL((void*)0); | ||
815 | } | ||
816 | |||
817 | /* -------------------------------------------------------------------- */ | ||
818 | /* unicode character name tables */ | ||
819 | |||
820 | /* data file generated by Tools/unicode/makeunicodedata.py */ | ||
821 | #include "unicodename_db.h" | ||
822 | |||
823 | /* -------------------------------------------------------------------- */ | ||
824 | /* database code (cut and pasted from the unidb package) */ | ||
825 | |||
826 | static unsigned long | ||
827 | _gethash(const char *s, int len, int scale) | ||
828 | { | ||
829 | int i; | ||
830 | unsigned long h = 0; | ||
831 | unsigned long ix; | ||
832 | for (i = 0; i < len; i++) { | ||
833 | h = (h * scale) + (unsigned char) toupper(Py_CHARMASK(s[i]))towupper(btowc(((unsigned char)((s[i]) & 0xff)))); | ||
834 | ix = h & 0xff000000; | ||
835 | if (ix) | ||
836 | h = (h ^ ((ix>>24) & 0xff)) & 0x00ffffff; | ||
837 | } | ||
838 | return h; | ||
839 | } | ||
840 | |||
841 | static char *hangul_syllables[][3] = { | ||
842 | { "G", "A", "" }, | ||
843 | { "GG", "AE", "G" }, | ||
844 | { "N", "YA", "GG" }, | ||
845 | { "D", "YAE", "GS" }, | ||
846 | { "DD", "EO", "N", }, | ||
847 | { "R", "E", "NJ" }, | ||
848 | { "M", "YEO", "NH" }, | ||
849 | { "B", "YE", "D" }, | ||
850 | { "BB", "O", "L" }, | ||
851 | { "S", "WA", "LG" }, | ||
852 | { "SS", "WAE", "LM" }, | ||
853 | { "", "OE", "LB" }, | ||
854 | { "J", "YO", "LS" }, | ||
855 | { "JJ", "U", "LT" }, | ||
856 | { "C", "WEO", "LP" }, | ||
857 | { "K", "WE", "LH" }, | ||
858 | { "T", "WI", "M" }, | ||
859 | { "P", "YU", "B" }, | ||
860 | { "H", "EU", "BS" }, | ||
861 | { 0, "YI", "S" }, | ||
862 | { 0, "I", "SS" }, | ||
863 | { 0, 0, "NG" }, | ||
864 | { 0, 0, "J" }, | ||
865 | { 0, 0, "C" }, | ||
866 | { 0, 0, "K" }, | ||
867 | { 0, 0, "T" }, | ||
868 | { 0, 0, "P" }, | ||
869 | { 0, 0, "H" } | ||
870 | }; | ||
871 | |||
872 | /* These ranges need to match makeunicodedata.py:cjk_ranges. */ | ||
873 | static int | ||
874 | is_unified_ideograph(Py_UCS4 code) | ||
875 | { | ||
876 | return | ||
877 | (0x3400 <= code && code <= 0x4DB5) || /* CJK Ideograph Extension A */ | ||
878 | (0x4E00 <= code && code <= 0x9FCB) || /* CJK Ideograph */ | ||
879 | (0x20000 <= code && code <= 0x2A6D6) || /* CJK Ideograph Extension B */ | ||
880 | (0x2A700 <= code && code <= 0x2B734) || /* CJK Ideograph Extension C */ | ||
881 | (0x2B740 <= code && code <= 0x2B81D); /* CJK Ideograph Extension D */ | ||
882 | } | ||
883 | |||
884 | static int | ||
885 | _getucname(PyObject *self, Py_UCS4 code, char* buffer, int buflen) | ||
886 | { | ||
887 | int offset; | ||
888 | int i; | ||
889 | int word; | ||
890 | unsigned char* w; | ||
891 | |||
892 | if (code >= 0x110000) | ||
893 | return 0; | ||
894 | |||
895 | if (self && UCD_Check(self)((((PyObject*)(self))->ob_type)==&UCD_Type)) { | ||
896 | const change_record *old = get_old_record(self, code)((((PreviousDBVersion*)self)->getrecord)(code)); | ||
897 | if (old->category_changed == 0) { | ||
898 | /* unassigned */ | ||
899 | return 0; | ||
900 | } | ||
901 | } | ||
902 | |||
903 | if (SBase0xAC00 <= code && code < SBase0xAC00+SCount(19*(21*28))) { | ||
904 | /* Hangul syllable. */ | ||
905 | int SIndex = code - SBase0xAC00; | ||
906 | int L = SIndex / NCount(21*28); | ||
907 | int V = (SIndex % NCount(21*28)) / TCount28; | ||
908 | int T = SIndex % TCount28; | ||
909 | |||
910 | if (buflen < 27) | ||
911 | /* Worst case: HANGUL SYLLABLE <10chars>. */ | ||
912 | return 0; | ||
913 | strcpy(buffer, "HANGUL SYLLABLE ")((__builtin_object_size (buffer, 0) != (size_t) -1) ? __builtin___strcpy_chk (buffer, "HANGUL SYLLABLE ", __builtin_object_size (buffer, 2 > 1)) : __inline_strcpy_chk (buffer, "HANGUL SYLLABLE ")); | ||
914 | buffer += 16; | ||
915 | strcpy(buffer, hangul_syllables[L][0])((__builtin_object_size (buffer, 0) != (size_t) -1) ? __builtin___strcpy_chk (buffer, hangul_syllables[L][0], __builtin_object_size (buffer , 2 > 1)) : __inline_strcpy_chk (buffer, hangul_syllables[ L][0])); | ||
916 | buffer += strlen(hangul_syllables[L][0]); | ||
917 | strcpy(buffer, hangul_syllables[V][1])((__builtin_object_size (buffer, 0) != (size_t) -1) ? __builtin___strcpy_chk (buffer, hangul_syllables[V][1], __builtin_object_size (buffer , 2 > 1)) : __inline_strcpy_chk (buffer, hangul_syllables[ V][1])); | ||
918 | buffer += strlen(hangul_syllables[V][1]); | ||
919 | strcpy(buffer, hangul_syllables[T][2])((__builtin_object_size (buffer, 0) != (size_t) -1) ? __builtin___strcpy_chk (buffer, hangul_syllables[T][2], __builtin_object_size (buffer , 2 > 1)) : __inline_strcpy_chk (buffer, hangul_syllables[ T][2])); | ||
920 | buffer += strlen(hangul_syllables[T][2]); | ||
921 | *buffer = '\0'; | ||
922 | return 1; | ||
923 | } | ||
924 | |||
925 | if (is_unified_ideograph(code)) { | ||
926 | if (buflen < 28) | ||
927 | /* Worst case: CJK UNIFIED IDEOGRAPH-20000 */ | ||
928 | return 0; | ||
929 | sprintf(buffer, "CJK UNIFIED IDEOGRAPH-%X", code)__builtin___sprintf_chk (buffer, 0, __builtin_object_size (buffer , 2 > 1), "CJK UNIFIED IDEOGRAPH-%X", code); | ||
930 | return 1; | ||
931 | } | ||
932 | |||
933 | /* get offset into phrasebook */ | ||
934 | offset = phrasebook_offset1[(code>>phrasebook_shift7)]; | ||
935 | offset = phrasebook_offset2[(offset<<phrasebook_shift7) + | ||
936 | (code&((1<<phrasebook_shift7)-1))]; | ||
937 | if (!offset) | ||
938 | return 0; | ||
939 | |||
940 | i = 0; | ||
941 | |||
942 | for (;;) { | ||
943 | /* get word index */ | ||
944 | word = phrasebook[offset] - phrasebook_short211; | ||
945 | if (word >= 0) { | ||
946 | word = (word << 8) + phrasebook[offset+1]; | ||
947 | offset += 2; | ||
948 | } else | ||
949 | word = phrasebook[offset++]; | ||
950 | if (i) { | ||
951 | if (i > buflen) | ||
952 | return 0; /* buffer overflow */ | ||
953 | buffer[i++] = ' '; | ||
954 | } | ||
955 | /* copy word string from lexicon. the last character in the | ||
956 | word has bit 7 set. the last word in a string ends with | ||
957 | 0x80 */ | ||
958 | w = lexicon + lexicon_offset[word]; | ||
959 | while (*w < 128) { | ||
960 | if (i >= buflen) | ||
961 | return 0; /* buffer overflow */ | ||
962 | buffer[i++] = *w++; | ||
963 | } | ||
964 | if (i >= buflen) | ||
965 | return 0; /* buffer overflow */ | ||
966 | buffer[i++] = *w & 127; | ||
967 | if (*w == 128) | ||
968 | break; /* end of word */ | ||
969 | } | ||
970 | |||
971 | return 1; | ||
972 | } | ||
973 | |||
974 | static int | ||
975 | _cmpname(PyObject *self, int code, const char* name, int namelen) | ||
976 | { | ||
977 | /* check if code corresponds to the given name */ | ||
978 | int i; | ||
979 | char buffer[NAME_MAXLEN256]; | ||
980 | if (!_getucname(self, code, buffer, sizeof(buffer))) | ||
981 | return 0; | ||
982 | for (i = 0; i < namelen; i++) { | ||
983 | if (toupper(Py_CHARMASK(name[i]))towupper(btowc(((unsigned char)((name[i]) & 0xff)))) != buffer[i]) | ||
984 | return 0; | ||
985 | } | ||
986 | return buffer[namelen] == '\0'; | ||
987 | } | ||
988 | |||
989 | static void | ||
990 | find_syllable(const char *str, int *len, int *pos, int count, int column) | ||
991 | { | ||
992 | int i, len1; | ||
993 | *len = -1; | ||
994 | for (i = 0; i < count; i++) { | ||
995 | char *s = hangul_syllables[i][column]; | ||
996 | len1 = strlen(s); | ||
997 | if (len1 <= *len) | ||
998 | continue; | ||
999 | if (strncmp(str, s, len1) == 0) { | ||
1000 | *len = len1; | ||
1001 | *pos = i; | ||
1002 | } | ||
1003 | } | ||
1004 | if (*len == -1) { | ||
1005 | *len = 0; | ||
1006 | } | ||
1007 | } | ||
1008 | |||
1009 | static int | ||
1010 | _getcode(PyObject* self, const char* name, int namelen, Py_UCS4* code) | ||
1011 | { | ||
1012 | unsigned int h, v; | ||
1013 | unsigned int mask = code_size32768-1; | ||
1014 | unsigned int i, incr; | ||
1015 | |||
1016 | /* Check for hangul syllables. */ | ||
1017 | if (strncmp(name, "HANGUL SYLLABLE ", 16) == 0) { | ||
1018 | int len, L = -1, V = -1, T = -1; | ||
1019 | const char *pos = name + 16; | ||
1020 | find_syllable(pos, &len, &L, LCount19, 0); | ||
1021 | pos += len; | ||
1022 | find_syllable(pos, &len, &V, VCount21, 1); | ||
1023 | pos += len; | ||
1024 | find_syllable(pos, &len, &T, TCount28, 2); | ||
1025 | pos += len; | ||
1026 | if (L != -1 && V != -1 && T != -1 && pos-name == namelen) { | ||
1027 | *code = SBase0xAC00 + (L*VCount21+V)*TCount28 + T; | ||
1028 | return 1; | ||
1029 | } | ||
1030 | /* Otherwise, it's an illegal syllable name. */ | ||
1031 | return 0; | ||
1032 | } | ||
1033 | |||
1034 | /* Check for unified ideographs. */ | ||
1035 | if (strncmp(name, "CJK UNIFIED IDEOGRAPH-", 22) == 0) { | ||
1036 | /* Four or five hexdigits must follow. */ | ||
1037 | v = 0; | ||
1038 | name += 22; | ||
1039 | namelen -= 22; | ||
1040 | if (namelen != 4 && namelen != 5) | ||
1041 | return 0; | ||
1042 | while (namelen--) { | ||
1043 | v *= 16; | ||
1044 | if (*name >= '0' && *name <= '9') | ||
1045 | v += *name - '0'; | ||
1046 | else if (*name >= 'A' && *name <= 'F') | ||
1047 | v += *name - 'A' + 10; | ||
1048 | else | ||
1049 | return 0; | ||
1050 | name++; | ||
1051 | } | ||
1052 | if (!is_unified_ideograph(v)) | ||
1053 | return 0; | ||
1054 | *code = v; | ||
1055 | return 1; | ||
1056 | } | ||
1057 | |||
1058 | /* the following is the same as python's dictionary lookup, with | ||
1059 | only minor changes. see the makeunicodedata script for more | ||
1060 | details */ | ||
1061 | |||
1062 | h = (unsigned int) _gethash(name, namelen, code_magic47); | ||
1063 | i = (~h) & mask; | ||
1064 | v = code_hash[i]; | ||
1065 | if (!v) | ||
1066 | return 0; | ||
1067 | if (_cmpname(self, v, name, namelen)) { | ||
1068 | *code = v; | ||
1069 | return 1; | ||
1070 | } | ||
1071 | incr = (h ^ (h >> 3)) & mask; | ||
1072 | if (!incr) | ||
1073 | incr = mask; | ||
1074 | for (;;) { | ||
1075 | i = (i + incr) & mask; | ||
1076 | v = code_hash[i]; | ||
1077 | if (!v) | ||
1078 | return 0; | ||
1079 | if (_cmpname(self, v, name, namelen)) { | ||
1080 | *code = v; | ||
1081 | return 1; | ||
1082 | } | ||
1083 | incr = incr << 1; | ||
1084 | if (incr > mask) | ||
1085 | incr = incr ^ code_poly32771; | ||
1086 | } | ||
1087 | } | ||
1088 | |||
1089 | static const _PyUnicode_Name_CAPI hashAPI = | ||
1090 | { | ||
1091 | sizeof(_PyUnicode_Name_CAPI), | ||
1092 | _getucname, | ||
1093 | _getcode | ||
1094 | }; | ||
1095 | |||
1096 | /* -------------------------------------------------------------------- */ | ||
1097 | /* Python bindings */ | ||
1098 | |||
1099 | PyDoc_STRVAR(unicodedata_name__doc__,static char unicodedata_name__doc__[] = "name(unichr[, default])\nReturns the name assigned to the Unicode character unichr as a\nstring. If no name is defined, default is returned, or, if not\ngiven, ValueError is raised." | ||
1100 | "name(unichr[, default])\n\static char unicodedata_name__doc__[] = "name(unichr[, default])\nReturns the name assigned to the Unicode character unichr as a\nstring. If no name is defined, default is returned, or, if not\ngiven, ValueError is raised." | ||
1101 | Returns the name assigned to the Unicode character unichr as a\n\static char unicodedata_name__doc__[] = "name(unichr[, default])\nReturns the name assigned to the Unicode character unichr as a\nstring. If no name is defined, default is returned, or, if not\ngiven, ValueError is raised." | ||
1102 | string. If no name is defined, default is returned, or, if not\n\static char unicodedata_name__doc__[] = "name(unichr[, default])\nReturns the name assigned to the Unicode character unichr as a\nstring. If no name is defined, default is returned, or, if not\ngiven, ValueError is raised." | ||
1103 | given, ValueError is raised.")static char unicodedata_name__doc__[] = "name(unichr[, default])\nReturns the name assigned to the Unicode character unichr as a\nstring. If no name is defined, default is returned, or, if not\ngiven, ValueError is raised."; | ||
1104 | |||
1105 | static PyObject * | ||
1106 | unicodedata_name(PyObject* self, PyObject* args) | ||
1107 | { | ||
1108 | char name[NAME_MAXLEN256]; | ||
1109 | Py_UCS4 c; | ||
1110 | |||
1111 | PyUnicodeObject* v; | ||
1112 | PyObject* defobj = NULL((void*)0); | ||
1113 | if (!PyArg_ParseTuple(args, "O!|O:name", &PyUnicode_Type, &v, &defobj)) | ||
1114 | return NULL((void*)0); | ||
1115 | |||
1116 | c = getuchar(v); | ||
1117 | if (c == (Py_UCS4)-1) | ||
1118 | return NULL((void*)0); | ||
1119 | |||
1120 | if (!_getucname(self, c, name, sizeof(name))) { | ||
1121 | if (defobj == NULL((void*)0)) { | ||
1122 | PyErr_SetString(PyExc_ValueError, "no such name"); | ||
1123 | return NULL((void*)0); | ||
1124 | } | ||
1125 | else { | ||
1126 | Py_INCREF(defobj)( _Py_RefTotal++ , ((PyObject*)(defobj))->ob_refcnt++); | ||
1127 | return defobj; | ||
1128 | } | ||
1129 | } | ||
1130 | |||
1131 | return PyUnicode_FromStringPyUnicodeUCS2_FromString(name); | ||
1132 | } | ||
1133 | |||
1134 | PyDoc_STRVAR(unicodedata_lookup__doc__,static char unicodedata_lookup__doc__[] = "lookup(name)\n\nLook up character by name. If a character with the\ngiven name is found, return the corresponding Unicode\ncharacter. If not found, KeyError is raised." | ||
1135 | "lookup(name)\n\static char unicodedata_lookup__doc__[] = "lookup(name)\n\nLook up character by name. If a character with the\ngiven name is found, return the corresponding Unicode\ncharacter. If not found, KeyError is raised." | ||
1136 | \n\static char unicodedata_lookup__doc__[] = "lookup(name)\n\nLook up character by name. If a character with the\ngiven name is found, return the corresponding Unicode\ncharacter. If not found, KeyError is raised." | ||
1137 | Look up character by name. If a character with the\n\static char unicodedata_lookup__doc__[] = "lookup(name)\n\nLook up character by name. If a character with the\ngiven name is found, return the corresponding Unicode\ncharacter. If not found, KeyError is raised." | ||
1138 | given name is found, return the corresponding Unicode\n\static char unicodedata_lookup__doc__[] = "lookup(name)\n\nLook up character by name. If a character with the\ngiven name is found, return the corresponding Unicode\ncharacter. If not found, KeyError is raised." | ||
1139 | character. If not found, KeyError is raised.")static char unicodedata_lookup__doc__[] = "lookup(name)\n\nLook up character by name. If a character with the\ngiven name is found, return the corresponding Unicode\ncharacter. If not found, KeyError is raised."; | ||
1140 | |||
1141 | static PyObject * | ||
1142 | unicodedata_lookup(PyObject* self, PyObject* args) | ||
1143 | { | ||
1144 | Py_UCS4 code; | ||
1145 | Py_UNICODE str[2]; | ||
1146 | |||
1147 | char* name; | ||
1148 | int namelen; | ||
1149 | if (!PyArg_ParseTuple(args, "s#:lookup", &name, &namelen)) | ||
1150 | return NULL((void*)0); | ||
1151 | |||
1152 | if (!_getcode(self, name, namelen, &code)) { | ||
1153 | PyErr_Format(PyExc_KeyError, "undefined character name '%s'", | ||
1154 | name); | ||
1155 | return NULL((void*)0); | ||
1156 | } | ||
1157 | |||
1158 | #ifndef Py_UNICODE_WIDE | ||
1159 | if (code >= 0x10000) { | ||
1160 | str[0] = 0xd800 + ((code - 0x10000) >> 10); | ||
1161 | str[1] = 0xdc00 + ((code - 0x10000) & 0x3ff); | ||
1162 | return PyUnicode_FromUnicodePyUnicodeUCS2_FromUnicode(str, 2); | ||
1163 | } | ||
1164 | #endif | ||
1165 | str[0] = (Py_UNICODE) code; | ||
1166 | return PyUnicode_FromUnicodePyUnicodeUCS2_FromUnicode(str, 1); | ||
1167 | } | ||
1168 | |||
1169 | /* XXX Add doc strings. */ | ||
1170 | |||
1171 | static PyMethodDef unicodedata_functions[] = { | ||
1172 | {"decimal", unicodedata_decimal, METH_VARARGS0x0001, unicodedata_decimal__doc__}, | ||
1173 | {"digit", unicodedata_digit, METH_VARARGS0x0001, unicodedata_digit__doc__}, | ||
1174 | {"numeric", unicodedata_numeric, METH_VARARGS0x0001, unicodedata_numeric__doc__}, | ||
1175 | {"category", unicodedata_category, METH_VARARGS0x0001, | ||
1176 | unicodedata_category__doc__}, | ||
1177 | {"bidirectional", unicodedata_bidirectional, METH_VARARGS0x0001, | ||
1178 | unicodedata_bidirectional__doc__}, | ||
1179 | {"combining", unicodedata_combining, METH_VARARGS0x0001, | ||
1180 | unicodedata_combining__doc__}, | ||
1181 | {"mirrored", unicodedata_mirrored, METH_VARARGS0x0001, | ||
1182 | unicodedata_mirrored__doc__}, | ||
1183 | {"east_asian_width", unicodedata_east_asian_width, METH_VARARGS0x0001, | ||
1184 | unicodedata_east_asian_width__doc__}, | ||
1185 | {"decomposition", unicodedata_decomposition, METH_VARARGS0x0001, | ||
1186 | unicodedata_decomposition__doc__}, | ||
1187 | {"name", unicodedata_name, METH_VARARGS0x0001, unicodedata_name__doc__}, | ||
1188 | {"lookup", unicodedata_lookup, METH_VARARGS0x0001, unicodedata_lookup__doc__}, | ||
1189 | {"normalize", unicodedata_normalize, METH_VARARGS0x0001, | ||
1190 | unicodedata_normalize__doc__}, | ||
1191 | {NULL((void*)0), NULL((void*)0)} /* sentinel */ | ||
1192 | }; | ||
1193 | |||
1194 | static PyTypeObject UCD_Type = { | ||
1195 | /* The ob_type field must be initialized in the module init function | ||
1196 | * to be portable to Windows without using C++. */ | ||
1197 | PyVarObject_HEAD_INIT(NULL, 0){ { 0, 0, 1, ((void*)0) }, 0 }, | ||
1198 | "unicodedata.UCD", /*tp_name*/ | ||
1199 | sizeof(PreviousDBVersion), /*tp_basicsize*/ | ||
1200 | 0, /*tp_itemsize*/ | ||
1201 | /* methods */ | ||
1202 | (destructor)PyObject_Del_PyObject_DebugFree, /*tp_dealloc*/ | ||
1203 | 0, /*tp_print*/ | ||
1204 | 0, /*tp_getattr*/ | ||
1205 | 0, /*tp_setattr*/ | ||
1206 | 0, /*tp_reserved*/ | ||
1207 | 0, /*tp_repr*/ | ||
1208 | 0, /*tp_as_number*/ | ||
1209 | 0, /*tp_as_sequence*/ | ||
1210 | 0, /*tp_as_mapping*/ | ||
1211 | 0, /*tp_hash*/ | ||
1212 | 0, /*tp_call*/ | ||
1213 | 0, /*tp_str*/ | ||
1214 | PyObject_GenericGetAttr,/*tp_getattro*/ | ||
1215 | 0, /*tp_setattro*/ | ||
1216 | 0, /*tp_as_buffer*/ | ||
1217 | Py_TPFLAGS_DEFAULT( 0 | (1L<<18) | 0), /*tp_flags*/ | ||
1218 | 0, /*tp_doc*/ | ||
1219 | 0, /*tp_traverse*/ | ||
1220 | 0, /*tp_clear*/ | ||
1221 | 0, /*tp_richcompare*/ | ||
1222 | 0, /*tp_weaklistoffset*/ | ||
1223 | 0, /*tp_iter*/ | ||
1224 | 0, /*tp_iternext*/ | ||
1225 | unicodedata_functions, /*tp_methods*/ | ||
1226 | DB_members, /*tp_members*/ | ||
1227 | 0, /*tp_getset*/ | ||
1228 | 0, /*tp_base*/ | ||
1229 | 0, /*tp_dict*/ | ||
1230 | 0, /*tp_descr_get*/ | ||
1231 | 0, /*tp_descr_set*/ | ||
1232 | 0, /*tp_dictoffset*/ | ||
1233 | 0, /*tp_init*/ | ||
1234 | 0, /*tp_alloc*/ | ||
1235 | 0, /*tp_new*/ | ||
1236 | 0, /*tp_free*/ | ||
1237 | 0, /*tp_is_gc*/ | ||
1238 | }; | ||
1239 | |||
1240 | PyDoc_STRVAR(unicodedata_docstring,static char unicodedata_docstring[] = "This module provides access to the Unicode Character Database which\ndefines character properties for all Unicode characters. The data in\nthis database is based on the UnicodeData.txt file version\n5.2.0 which is publically available from ftp://ftp.unicode.org/.\n\nThe module uses the same names and symbols as defined by the\nUnicodeData File Format 5.2.0 (see\nhttp://www.unicode.org/reports/tr44/tr44-4.html)." | ||
1241 | "This module provides access to the Unicode Character Database which\n\static char unicodedata_docstring[] = "This module provides access to the Unicode Character Database which\ndefines character properties for all Unicode characters. The data in\nthis database is based on the UnicodeData.txt file version\n5.2.0 which is publically available from ftp://ftp.unicode.org/.\n\nThe module uses the same names and symbols as defined by the\nUnicodeData File Format 5.2.0 (see\nhttp://www.unicode.org/reports/tr44/tr44-4.html)." | ||
1242 | defines character properties for all Unicode characters. The data in\n\static char unicodedata_docstring[] = "This module provides access to the Unicode Character Database which\ndefines character properties for all Unicode characters. The data in\nthis database is based on the UnicodeData.txt file version\n5.2.0 which is publically available from ftp://ftp.unicode.org/.\n\nThe module uses the same names and symbols as defined by the\nUnicodeData File Format 5.2.0 (see\nhttp://www.unicode.org/reports/tr44/tr44-4.html)." | ||
1243 | this database is based on the UnicodeData.txt file version\n\static char unicodedata_docstring[] = "This module provides access to the Unicode Character Database which\ndefines character properties for all Unicode characters. The data in\nthis database is based on the UnicodeData.txt file version\n5.2.0 which is publically available from ftp://ftp.unicode.org/.\n\nThe module uses the same names and symbols as defined by the\nUnicodeData File Format 5.2.0 (see\nhttp://www.unicode.org/reports/tr44/tr44-4.html)." | ||
1244 | 5.2.0 which is publically available from ftp://ftp.unicode.org/.\n\static char unicodedata_docstring[] = "This module provides access to the Unicode Character Database which\ndefines character properties for all Unicode characters. The data in\nthis database is based on the UnicodeData.txt file version\n5.2.0 which is publically available from ftp://ftp.unicode.org/.\n\nThe module uses the same names and symbols as defined by the\nUnicodeData File Format 5.2.0 (see\nhttp://www.unicode.org/reports/tr44/tr44-4.html)." | ||
1245 | \n\static char unicodedata_docstring[] = "This module provides access to the Unicode Character Database which\ndefines character properties for all Unicode characters. The data in\nthis database is based on the UnicodeData.txt file version\n5.2.0 which is publically available from ftp://ftp.unicode.org/.\n\nThe module uses the same names and symbols as defined by the\nUnicodeData File Format 5.2.0 (see\nhttp://www.unicode.org/reports/tr44/tr44-4.html)." | ||
1246 | The module uses the same names and symbols as defined by the\n\static char unicodedata_docstring[] = "This module provides access to the Unicode Character Database which\ndefines character properties for all Unicode characters. The data in\nthis database is based on the UnicodeData.txt file version\n5.2.0 which is publically available from ftp://ftp.unicode.org/.\n\nThe module uses the same names and symbols as defined by the\nUnicodeData File Format 5.2.0 (see\nhttp://www.unicode.org/reports/tr44/tr44-4.html)." | ||
1247 | UnicodeData File Format 5.2.0 (see\n\static char unicodedata_docstring[] = "This module provides access to the Unicode Character Database which\ndefines character properties for all Unicode characters. The data in\nthis database is based on the UnicodeData.txt file version\n5.2.0 which is publically available from ftp://ftp.unicode.org/.\n\nThe module uses the same names and symbols as defined by the\nUnicodeData File Format 5.2.0 (see\nhttp://www.unicode.org/reports/tr44/tr44-4.html)." | ||
1248 | http://www.unicode.org/reports/tr44/tr44-4.html).")static char unicodedata_docstring[] = "This module provides access to the Unicode Character Database which\ndefines character properties for all Unicode characters. The data in\nthis database is based on the UnicodeData.txt file version\n5.2.0 which is publically available from ftp://ftp.unicode.org/.\n\nThe module uses the same names and symbols as defined by the\nUnicodeData File Format 5.2.0 (see\nhttp://www.unicode.org/reports/tr44/tr44-4.html)."; | ||
1249 | |||
1250 | |||
1251 | static struct PyModuleDef unicodedatamodule = { | ||
1252 | PyModuleDef_HEAD_INIT{ { 0, 0, 1, ((void*)0) }, ((void*)0), 0, ((void*)0), }, | ||
1253 | "unicodedata", | ||
1254 | unicodedata_docstring, | ||
1255 | -1, | ||
1256 | unicodedata_functions, | ||
1257 | NULL((void*)0), | ||
1258 | NULL((void*)0), | ||
1259 | NULL((void*)0), | ||
1260 | NULL((void*)0) | ||
1261 | }; | ||
1262 | |||
1263 | PyMODINIT_FUNCPyObject* | ||
1264 | PyInit_unicodedata(void) | ||
1265 | { | ||
1266 | PyObject *m, *v; | ||
1267 | |||
1268 | Py_TYPE(&UCD_Type)(((PyObject*)(&UCD_Type))->ob_type) = &PyType_Type; | ||
1269 | |||
1270 | m = PyModule_Create(&unicodedatamodule)PyModule_Create2TraceRefs(&unicodedatamodule, 1013); | ||
1271 | if (!m) | ||
1272 | return NULL((void*)0); | ||
1273 | |||
1274 | PyModule_AddStringConstant(m, "unidata_version", UNIDATA_VERSION"6.0.0"); | ||
1275 | Py_INCREF(&UCD_Type)( _Py_RefTotal++ , ((PyObject*)(&UCD_Type))->ob_refcnt ++); | ||
1276 | PyModule_AddObject(m, "UCD", (PyObject*)&UCD_Type); | ||
1277 | |||
1278 | /* Previous versions */ | ||
1279 | v = new_previous_version("3.2.0", get_change_3_2_0, normalization_3_2_0); | ||
1280 | if (v != NULL((void*)0)) | ||
1281 | PyModule_AddObject(m, "ucd_3_2_0", v); | ||
1282 | |||
1283 | /* Export C API */ | ||
1284 | v = PyCapsule_New((void *)&hashAPI, PyUnicodeData_CAPSULE_NAME"unicodedata.ucnhash_CAPI", NULL((void*)0)); | ||
1285 | if (v != NULL((void*)0)) | ||
1286 | PyModule_AddObject(m, "ucnhash_CAPI", v); | ||
1287 | return m; | ||
1288 | } | ||
1289 | |||
1290 | /* | ||
1291 | Local variables: | ||
1292 | c-basic-offset: 4 | ||
1293 | indent-tabs-mode: nil | ||
1294 | End: | ||
1295 | */ |