1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481
|
/* ------------------------------------------------------------------------
unicodedata -- Provides access to the Unicode 3.0 data base.
Data was extracted from the Unicode 3.0 UnicodeData.txt file.
Written by Marc-Andre Lemburg (mal@lemburg.com).
Modified for Python 2.0 by Fredrik Lundh (fredrik@pythonware.com)
Copyright (c) Corporation for National Research Initiatives.
------------------------------------------------------------------------ */
#include "Python.h"
#include "ucnhash.h"
/* character properties */
typedef struct {
const unsigned char category; /* index into
_PyUnicode_CategoryNames */
const unsigned char combining; /* combining class value 0 - 255 */
const unsigned char bidirectional; /* index into
_PyUnicode_BidirectionalNames */
const unsigned char mirrored; /* true if mirrored in bidir mode */
} _PyUnicode_DatabaseRecord;
/* data file generated by Tools/unicode/makeunicodedata.py */
#include "unicodedata_db.h"
static const _PyUnicode_DatabaseRecord*
_getrecord(PyUnicodeObject* v)
{
int code;
int index;
code = (int) *PyUnicode_AS_UNICODE(v);
if (code < 0 || code >= 65536)
index = 0;
else {
index = index1[(code>>SHIFT)];
index = index2[(index<<SHIFT)+(code&((1<<SHIFT)-1))];
}
return &_PyUnicode_Database_Records[index];
}
/* --- Module API --------------------------------------------------------- */
static PyObject *
unicodedata_decimal(PyObject *self, PyObject *args)
{
PyUnicodeObject *v;
PyObject *defobj = NULL;
long rc;
if (!PyArg_ParseTuple(args, "O!|O:decimal", &PyUnicode_Type, &v, &defobj))
return NULL;
if (PyUnicode_GET_SIZE(v) != 1) {
PyErr_SetString(PyExc_TypeError,
"need a single Unicode character as parameter");
return NULL;
}
rc = Py_UNICODE_TODECIMAL(*PyUnicode_AS_UNICODE(v));
if (rc < 0) {
if (defobj == NULL) {
PyErr_SetString(PyExc_ValueError,
"not a decimal");
return NULL;
}
else {
Py_INCREF(defobj);
return defobj;
}
}
return PyInt_FromLong(rc);
}
static PyObject *
unicodedata_digit(PyObject *self, PyObject *args)
{
PyUnicodeObject *v;
PyObject *defobj = NULL;
long rc;
if (!PyArg_ParseTuple(args, "O!|O:digit", &PyUnicode_Type, &v, &defobj))
return NULL;
if (PyUnicode_GET_SIZE(v) != 1) {
PyErr_SetString(PyExc_TypeError,
"need a single Unicode character as parameter");
return NULL;
}
rc = Py_UNICODE_TODIGIT(*PyUnicode_AS_UNICODE(v));
if (rc < 0) {
if (defobj == NULL) {
PyErr_SetString(PyExc_ValueError, "not a digit");
return NULL;
}
else {
Py_INCREF(defobj);
return defobj;
}
}
return PyInt_FromLong(rc);
}
static PyObject *
unicodedata_numeric(PyObject *self, PyObject *args)
{
PyUnicodeObject *v;
PyObject *defobj = NULL;
double rc;
if (!PyArg_ParseTuple(args, "O!|O:numeric", &PyUnicode_Type, &v, &defobj))
return NULL;
if (PyUnicode_GET_SIZE(v) != 1) {
PyErr_SetString(PyExc_TypeError,
"need a single Unicode character as parameter");
return NULL;
}
rc = Py_UNICODE_TONUMERIC(*PyUnicode_AS_UNICODE(v));
if (rc < 0) {
if (defobj == NULL) {
PyErr_SetString(PyExc_ValueError, "not a numeric character");
return NULL;
}
else {
Py_INCREF(defobj);
return defobj;
}
}
return PyFloat_FromDouble(rc);
}
static PyObject *
unicodedata_category(PyObject *self, PyObject *args)
{
PyUnicodeObject *v;
int index;
if (!PyArg_ParseTuple(args, "O!:category",
&PyUnicode_Type, &v))
return NULL;
if (PyUnicode_GET_SIZE(v) != 1) {
PyErr_SetString(PyExc_TypeError,
"need a single Unicode character as parameter");
return NULL;
}
index = (int) _getrecord(v)->category;
return PyString_FromString(_PyUnicode_CategoryNames[index]);
}
static PyObject *
unicodedata_bidirectional(PyObject *self, PyObject *args)
{
PyUnicodeObject *v;
int index;
if (!PyArg_ParseTuple(args, "O!:bidirectional",
&PyUnicode_Type, &v))
return NULL;
if (PyUnicode_GET_SIZE(v) != 1) {
PyErr_SetString(PyExc_TypeError,
"need a single Unicode character as parameter");
return NULL;
}
index = (int) _getrecord(v)->bidirectional;
return PyString_FromString(_PyUnicode_BidirectionalNames[index]);
}
static PyObject *
unicodedata_combining(PyObject *self, PyObject *args)
{
PyUnicodeObject *v;
if (!PyArg_ParseTuple(args, "O!:combining",
&PyUnicode_Type, &v))
return NULL;
if (PyUnicode_GET_SIZE(v) != 1) {
PyErr_SetString(PyExc_TypeError,
"need a single Unicode character as parameter");
return NULL;
}
return PyInt_FromLong((int) _getrecord(v)->combining);
}
static PyObject *
unicodedata_mirrored(PyObject *self, PyObject *args)
{
PyUnicodeObject *v;
if (!PyArg_ParseTuple(args, "O!:mirrored",
&PyUnicode_Type, &v))
return NULL;
if (PyUnicode_GET_SIZE(v) != 1) {
PyErr_SetString(PyExc_TypeError,
"need a single Unicode character as parameter");
return NULL;
}
return PyInt_FromLong((int) _getrecord(v)->mirrored);
}
static PyObject *
unicodedata_decomposition(PyObject *self, PyObject *args)
{
PyUnicodeObject *v;
char decomp[256];
int code, index, count, i;
if (!PyArg_ParseTuple(args, "O!:decomposition",
&PyUnicode_Type, &v))
return NULL;
if (PyUnicode_GET_SIZE(v) != 1) {
PyErr_SetString(PyExc_TypeError,
"need a single Unicode character as parameter");
return NULL;
}
code = (int) *PyUnicode_AS_UNICODE(v);
if (code < 0 || code >= 65536)
index = 0;
else {
index = decomp_index1[(code>>DECOMP_SHIFT)];
index = decomp_index2[(index<<DECOMP_SHIFT)+
(code&((1<<DECOMP_SHIFT)-1))];
}
/* high byte is of hex bytes (usually one or two), low byte
is prefix code (from*/
count = decomp_data[index] >> 8;
/* XXX: could allocate the PyString up front instead
(strlen(prefix) + 5 * count + 1 bytes) */
/* copy prefix */
i = strlen(decomp_prefix[decomp_data[index] & 255]);
memcpy(decomp, decomp_prefix[decomp_data[index] & 255], i);
while (count-- > 0) {
if (i)
decomp[i++] = ' ';
sprintf(decomp + i, "%04X", decomp_data[++index]);
i += strlen(decomp + i);
}
decomp[i] = '\0';
return PyString_FromString(decomp);
}
/* -------------------------------------------------------------------- */
/* unicode character name tables */
/* data file generated by Tools/unicode/makeunicodedata.py */
#include "unicodename_db.h"
/* -------------------------------------------------------------------- */
/* database code (cut and pasted from the unidb package) */
static unsigned long
_gethash(const char *s, int len, int scale)
{
int i;
unsigned long h = 0;
unsigned long ix;
for (i = 0; i < len; i++) {
h = (h * scale) + (unsigned char) toupper(s[i]);
ix = h & 0xff000000;
if (ix)
h = (h ^ ((ix>>24) & 0xff)) & 0x00ffffff;
}
return h;
}
static int
_getname(Py_UCS4 code, char* buffer, int buflen)
{
int offset;
int i;
int word;
unsigned char* w;
if (code < 0 || code >= 65536)
return 0;
/* get offset into phrasebook */
offset = phrasebook_offset1[(code>>phrasebook_shift)];
offset = phrasebook_offset2[(offset<<phrasebook_shift) +
(code&((1<<phrasebook_shift)-1))];
if (!offset)
return 0;
i = 0;
for (;;) {
/* get word index */
word = phrasebook[offset] - phrasebook_short;
if (word >= 0) {
word = (word << 8) + phrasebook[offset+1];
offset += 2;
} else
word = phrasebook[offset++];
if (i) {
if (i > buflen)
return 0; /* buffer overflow */
buffer[i++] = ' ';
}
/* copy word string from lexicon. the last character in the
word has bit 7 set. the last word in a string ends with
0x80 */
w = lexicon + lexicon_offset[word];
while (*w < 128) {
if (i >= buflen)
return 0; /* buffer overflow */
buffer[i++] = *w++;
}
if (i >= buflen)
return 0; /* buffer overflow */
buffer[i++] = *w & 127;
if (*w == 128)
break; /* end of word */
}
return 1;
}
static int
_cmpname(int code, const char* name, int namelen)
{
/* check if code corresponds to the given name */
int i;
char buffer[NAME_MAXLEN];
if (!_getname(code, buffer, sizeof(buffer)))
return 0;
for (i = 0; i < namelen; i++) {
if (toupper(name[i]) != buffer[i])
return 0;
}
return buffer[namelen] == '\0';
}
static int
_getcode(const char* name, int namelen, Py_UCS4* code)
{
unsigned int h, v;
unsigned int mask = code_size-1;
unsigned int i, incr;
/* the following is the same as python's dictionary lookup, with
only minor changes. see the makeunicodedata script for more
details */
h = (unsigned int) _gethash(name, namelen, code_magic);
i = (~h) & mask;
v = code_hash[i];
if (!v)
return 0;
if (_cmpname(v, name, namelen)) {
*code = v;
return 1;
}
incr = (h ^ (h >> 3)) & mask;
if (!incr)
incr = mask;
for (;;) {
i = (i + incr) & mask;
v = code_hash[i];
if (!v)
return 0;
if (_cmpname(v, name, namelen)) {
*code = v;
return 1;
}
incr = incr << 1;
if (incr > mask)
incr = incr ^ code_poly;
}
}
static const _PyUnicode_Name_CAPI hashAPI =
{
sizeof(_PyUnicode_Name_CAPI),
_getname,
_getcode
};
/* -------------------------------------------------------------------- */
/* Python bindings */
static PyObject *
unicodedata_name(PyObject* self, PyObject* args)
{
char name[NAME_MAXLEN];
PyUnicodeObject* v;
PyObject* defobj = NULL;
if (!PyArg_ParseTuple(args, "O!|O:name", &PyUnicode_Type, &v, &defobj))
return NULL;
if (PyUnicode_GET_SIZE(v) != 1) {
PyErr_SetString(PyExc_TypeError,
"need a single Unicode character as parameter");
return NULL;
}
if (!_getname((Py_UCS4) *PyUnicode_AS_UNICODE(v),
name, sizeof(name))) {
if (defobj == NULL) {
PyErr_SetString(PyExc_ValueError, "no such name");
return NULL;
}
else {
Py_INCREF(defobj);
return defobj;
}
}
return Py_BuildValue("s", name);
}
static PyObject *
unicodedata_lookup(PyObject* self, PyObject* args)
{
Py_UCS4 code;
Py_UNICODE str[1];
char* name;
int namelen;
if (!PyArg_ParseTuple(args, "s#:lookup", &name, &namelen))
return NULL;
if (!_getcode(name, namelen, &code)) {
PyErr_SetString(PyExc_KeyError, "undefined character name");
return NULL;
}
str[0] = (Py_UNICODE) code;
return PyUnicode_FromUnicode(str, 1);
}
/* XXX Add doc strings. */
static PyMethodDef unicodedata_functions[] = {
{"decimal", unicodedata_decimal, METH_VARARGS},
{"digit", unicodedata_digit, METH_VARARGS},
{"numeric", unicodedata_numeric, METH_VARARGS},
{"category", unicodedata_category, METH_VARARGS},
{"bidirectional", unicodedata_bidirectional, METH_VARARGS},
{"combining", unicodedata_combining, METH_VARARGS},
{"mirrored", unicodedata_mirrored, METH_VARARGS},
{"decomposition",unicodedata_decomposition, METH_VARARGS},
{"name", unicodedata_name, METH_VARARGS},
{"lookup", unicodedata_lookup, METH_VARARGS},
{NULL, NULL} /* sentinel */
};
static char *unicodedata_docstring = "unicode character database";
DL_EXPORT(void)
initunicodedata(void)
{
PyObject *m, *d, *v;
m = Py_InitModule3(
"unicodedata", unicodedata_functions, unicodedata_docstring);
if (!m)
return;
d = PyModule_GetDict(m);
if (!d)
return;
/* Export C API */
v = PyCObject_FromVoidPtr((void *) &hashAPI, NULL);
if (v != NULL) {
PyDict_SetItemString(d, "ucnhash_CAPI", v);
Py_DECREF(v);
}
}
|