Commit | Line | Data |
---|---|---|
920dae64 AT |
1 | """ Locale support. |
2 | ||
3 | The module provides low-level access to the C lib's locale APIs | |
4 | and adds high level number formatting APIs as well as a locale | |
5 | aliasing engine to complement these. | |
6 | ||
7 | The aliasing engine includes support for many commonly used locale | |
8 | names and maps them to values suitable for passing to the C lib's | |
9 | setlocale() function. It also includes default encodings for all | |
10 | supported locale names. | |
11 | ||
12 | """ | |
13 | ||
14 | import sys | |
15 | ||
16 | # Try importing the _locale module. | |
17 | # | |
18 | # If this fails, fall back on a basic 'C' locale emulation. | |
19 | ||
20 | # Yuck: LC_MESSAGES is non-standard: can't tell whether it exists before | |
21 | # trying the import. So __all__ is also fiddled at the end of the file. | |
22 | __all__ = ["setlocale","Error","localeconv","strcoll","strxfrm", | |
23 | "format","str","atof","atoi","LC_CTYPE","LC_COLLATE", | |
24 | "LC_TIME","LC_MONETARY","LC_NUMERIC", "LC_ALL","CHAR_MAX"] | |
25 | ||
26 | try: | |
27 | ||
28 | from _locale import * | |
29 | ||
30 | except ImportError: | |
31 | ||
32 | # Locale emulation | |
33 | ||
34 | CHAR_MAX = 127 | |
35 | LC_ALL = 6 | |
36 | LC_COLLATE = 3 | |
37 | LC_CTYPE = 0 | |
38 | LC_MESSAGES = 5 | |
39 | LC_MONETARY = 4 | |
40 | LC_NUMERIC = 1 | |
41 | LC_TIME = 2 | |
42 | Error = ValueError | |
43 | ||
44 | def localeconv(): | |
45 | """ localeconv() -> dict. | |
46 | Returns numeric and monetary locale-specific parameters. | |
47 | """ | |
48 | # 'C' locale default values | |
49 | return {'grouping': [127], | |
50 | 'currency_symbol': '', | |
51 | 'n_sign_posn': 127, | |
52 | 'p_cs_precedes': 127, | |
53 | 'n_cs_precedes': 127, | |
54 | 'mon_grouping': [], | |
55 | 'n_sep_by_space': 127, | |
56 | 'decimal_point': '.', | |
57 | 'negative_sign': '', | |
58 | 'positive_sign': '', | |
59 | 'p_sep_by_space': 127, | |
60 | 'int_curr_symbol': '', | |
61 | 'p_sign_posn': 127, | |
62 | 'thousands_sep': '', | |
63 | 'mon_thousands_sep': '', | |
64 | 'frac_digits': 127, | |
65 | 'mon_decimal_point': '', | |
66 | 'int_frac_digits': 127} | |
67 | ||
68 | def setlocale(category, value=None): | |
69 | """ setlocale(integer,string=None) -> string. | |
70 | Activates/queries locale processing. | |
71 | """ | |
72 | if value not in (None, '', 'C'): | |
73 | raise Error, '_locale emulation only supports "C" locale' | |
74 | return 'C' | |
75 | ||
76 | def strcoll(a,b): | |
77 | """ strcoll(string,string) -> int. | |
78 | Compares two strings according to the locale. | |
79 | """ | |
80 | return cmp(a,b) | |
81 | ||
82 | def strxfrm(s): | |
83 | """ strxfrm(string) -> string. | |
84 | Returns a string that behaves for cmp locale-aware. | |
85 | """ | |
86 | return s | |
87 | ||
88 | ### Number formatting APIs | |
89 | ||
90 | # Author: Martin von Loewis | |
91 | ||
92 | #perform the grouping from right to left | |
93 | def _group(s): | |
94 | conv=localeconv() | |
95 | grouping=conv['grouping'] | |
96 | if not grouping:return (s, 0) | |
97 | result="" | |
98 | seps = 0 | |
99 | spaces = "" | |
100 | if s[-1] == ' ': | |
101 | sp = s.find(' ') | |
102 | spaces = s[sp:] | |
103 | s = s[:sp] | |
104 | while s and grouping: | |
105 | # if grouping is -1, we are done | |
106 | if grouping[0]==CHAR_MAX: | |
107 | break | |
108 | # 0: re-use last group ad infinitum | |
109 | elif grouping[0]!=0: | |
110 | #process last group | |
111 | group=grouping[0] | |
112 | grouping=grouping[1:] | |
113 | if result: | |
114 | result=s[-group:]+conv['thousands_sep']+result | |
115 | seps += 1 | |
116 | else: | |
117 | result=s[-group:] | |
118 | s=s[:-group] | |
119 | if s and s[-1] not in "0123456789": | |
120 | # the leading string is only spaces and signs | |
121 | return s+result+spaces,seps | |
122 | if not result: | |
123 | return s+spaces,seps | |
124 | if s: | |
125 | result=s+conv['thousands_sep']+result | |
126 | seps += 1 | |
127 | return result+spaces,seps | |
128 | ||
129 | def format(f,val,grouping=0): | |
130 | """Formats a value in the same way that the % formatting would use, | |
131 | but takes the current locale into account. | |
132 | Grouping is applied if the third parameter is true.""" | |
133 | result = f % val | |
134 | fields = result.split(".") | |
135 | seps = 0 | |
136 | if grouping: | |
137 | fields[0],seps=_group(fields[0]) | |
138 | if len(fields)==2: | |
139 | result = fields[0]+localeconv()['decimal_point']+fields[1] | |
140 | elif len(fields)==1: | |
141 | result = fields[0] | |
142 | else: | |
143 | raise Error, "Too many decimal points in result string" | |
144 | ||
145 | while seps: | |
146 | # If the number was formatted for a specific width, then it | |
147 | # might have been filled with spaces to the left or right. If | |
148 | # so, kill as much spaces as there where separators. | |
149 | # Leading zeroes as fillers are not yet dealt with, as it is | |
150 | # not clear how they should interact with grouping. | |
151 | sp = result.find(" ") | |
152 | if sp==-1:break | |
153 | result = result[:sp]+result[sp+1:] | |
154 | seps -= 1 | |
155 | ||
156 | return result | |
157 | ||
158 | def str(val): | |
159 | """Convert float to integer, taking the locale into account.""" | |
160 | return format("%.12g",val) | |
161 | ||
162 | def atof(string,func=float): | |
163 | "Parses a string as a float according to the locale settings." | |
164 | #First, get rid of the grouping | |
165 | ts = localeconv()['thousands_sep'] | |
166 | if ts: | |
167 | string = string.replace(ts, '') | |
168 | #next, replace the decimal point with a dot | |
169 | dd = localeconv()['decimal_point'] | |
170 | if dd: | |
171 | string = string.replace(dd, '.') | |
172 | #finally, parse the string | |
173 | return func(string) | |
174 | ||
175 | def atoi(str): | |
176 | "Converts a string to an integer according to the locale settings." | |
177 | return atof(str, int) | |
178 | ||
179 | def _test(): | |
180 | setlocale(LC_ALL, "") | |
181 | #do grouping | |
182 | s1=format("%d", 123456789,1) | |
183 | print s1, "is", atoi(s1) | |
184 | #standard formatting | |
185 | s1=str(3.14) | |
186 | print s1, "is", atof(s1) | |
187 | ||
188 | ### Locale name aliasing engine | |
189 | ||
190 | # Author: Marc-Andre Lemburg, mal@lemburg.com | |
191 | # Various tweaks by Fredrik Lundh <fredrik@pythonware.com> | |
192 | ||
193 | # store away the low-level version of setlocale (it's | |
194 | # overridden below) | |
195 | _setlocale = setlocale | |
196 | ||
197 | def normalize(localename): | |
198 | ||
199 | """ Returns a normalized locale code for the given locale | |
200 | name. | |
201 | ||
202 | The returned locale code is formatted for use with | |
203 | setlocale(). | |
204 | ||
205 | If normalization fails, the original name is returned | |
206 | unchanged. | |
207 | ||
208 | If the given encoding is not known, the function defaults to | |
209 | the default encoding for the locale code just like setlocale() | |
210 | does. | |
211 | ||
212 | """ | |
213 | # Normalize the locale name and extract the encoding | |
214 | fullname = localename.lower() | |
215 | if ':' in fullname: | |
216 | # ':' is sometimes used as encoding delimiter. | |
217 | fullname = fullname.replace(':', '.') | |
218 | if '.' in fullname: | |
219 | langname, encoding = fullname.split('.')[:2] | |
220 | fullname = langname + '.' + encoding | |
221 | else: | |
222 | langname = fullname | |
223 | encoding = '' | |
224 | ||
225 | # First lookup: fullname (possibly with encoding) | |
226 | code = locale_alias.get(fullname, None) | |
227 | if code is not None: | |
228 | return code | |
229 | ||
230 | # Second try: langname (without encoding) | |
231 | code = locale_alias.get(langname, None) | |
232 | if code is not None: | |
233 | if '.' in code: | |
234 | langname, defenc = code.split('.') | |
235 | else: | |
236 | langname = code | |
237 | defenc = '' | |
238 | if encoding: | |
239 | encoding = encoding_alias.get(encoding, encoding) | |
240 | else: | |
241 | encoding = defenc | |
242 | if encoding: | |
243 | return langname + '.' + encoding | |
244 | else: | |
245 | return langname | |
246 | ||
247 | else: | |
248 | return localename | |
249 | ||
250 | def _parse_localename(localename): | |
251 | ||
252 | """ Parses the locale code for localename and returns the | |
253 | result as tuple (language code, encoding). | |
254 | ||
255 | The localename is normalized and passed through the locale | |
256 | alias engine. A ValueError is raised in case the locale name | |
257 | cannot be parsed. | |
258 | ||
259 | The language code corresponds to RFC 1766. code and encoding | |
260 | can be None in case the values cannot be determined or are | |
261 | unknown to this implementation. | |
262 | ||
263 | """ | |
264 | code = normalize(localename) | |
265 | if '@' in localename: | |
266 | # Deal with locale modifiers | |
267 | code, modifier = code.split('@') | |
268 | if modifier == 'euro' and '.' not in code: | |
269 | # Assume Latin-9 for @euro locales. This is bogus, | |
270 | # since some systems may use other encodings for these | |
271 | # locales. Also, we ignore other modifiers. | |
272 | return code, 'iso-8859-15' | |
273 | ||
274 | if '.' in code: | |
275 | return tuple(code.split('.')[:2]) | |
276 | elif code == 'C': | |
277 | return None, None | |
278 | raise ValueError, 'unknown locale: %s' % localename | |
279 | ||
280 | def _build_localename(localetuple): | |
281 | ||
282 | """ Builds a locale code from the given tuple (language code, | |
283 | encoding). | |
284 | ||
285 | No aliasing or normalizing takes place. | |
286 | ||
287 | """ | |
288 | language, encoding = localetuple | |
289 | if language is None: | |
290 | language = 'C' | |
291 | if encoding is None: | |
292 | return language | |
293 | else: | |
294 | return language + '.' + encoding | |
295 | ||
296 | def getdefaultlocale(envvars=('LC_ALL', 'LC_CTYPE', 'LANG', 'LANGUAGE')): | |
297 | ||
298 | """ Tries to determine the default locale settings and returns | |
299 | them as tuple (language code, encoding). | |
300 | ||
301 | According to POSIX, a program which has not called | |
302 | setlocale(LC_ALL, "") runs using the portable 'C' locale. | |
303 | Calling setlocale(LC_ALL, "") lets it use the default locale as | |
304 | defined by the LANG variable. Since we don't want to interfere | |
305 | with the current locale setting we thus emulate the behavior | |
306 | in the way described above. | |
307 | ||
308 | To maintain compatibility with other platforms, not only the | |
309 | LANG variable is tested, but a list of variables given as | |
310 | envvars parameter. The first found to be defined will be | |
311 | used. envvars defaults to the search path used in GNU gettext; | |
312 | it must always contain the variable name 'LANG'. | |
313 | ||
314 | Except for the code 'C', the language code corresponds to RFC | |
315 | 1766. code and encoding can be None in case the values cannot | |
316 | be determined. | |
317 | ||
318 | """ | |
319 | ||
320 | try: | |
321 | # check if it's supported by the _locale module | |
322 | import _locale | |
323 | code, encoding = _locale._getdefaultlocale() | |
324 | except (ImportError, AttributeError): | |
325 | pass | |
326 | else: | |
327 | # make sure the code/encoding values are valid | |
328 | if sys.platform == "win32" and code and code[:2] == "0x": | |
329 | # map windows language identifier to language name | |
330 | code = windows_locale.get(int(code, 0)) | |
331 | # ...add other platform-specific processing here, if | |
332 | # necessary... | |
333 | return code, encoding | |
334 | ||
335 | # fall back on POSIX behaviour | |
336 | import os | |
337 | lookup = os.environ.get | |
338 | for variable in envvars: | |
339 | localename = lookup(variable,None) | |
340 | if localename: | |
341 | if variable == 'LANGUAGE': | |
342 | localename = localename.split(':')[0] | |
343 | break | |
344 | else: | |
345 | localename = 'C' | |
346 | return _parse_localename(localename) | |
347 | ||
348 | ||
349 | def getlocale(category=LC_CTYPE): | |
350 | ||
351 | """ Returns the current setting for the given locale category as | |
352 | tuple (language code, encoding). | |
353 | ||
354 | category may be one of the LC_* value except LC_ALL. It | |
355 | defaults to LC_CTYPE. | |
356 | ||
357 | Except for the code 'C', the language code corresponds to RFC | |
358 | 1766. code and encoding can be None in case the values cannot | |
359 | be determined. | |
360 | ||
361 | """ | |
362 | localename = _setlocale(category) | |
363 | if category == LC_ALL and ';' in localename: | |
364 | raise TypeError, 'category LC_ALL is not supported' | |
365 | return _parse_localename(localename) | |
366 | ||
367 | def setlocale(category, locale=None): | |
368 | ||
369 | """ Set the locale for the given category. The locale can be | |
370 | a string, a locale tuple (language code, encoding), or None. | |
371 | ||
372 | Locale tuples are converted to strings the locale aliasing | |
373 | engine. Locale strings are passed directly to the C lib. | |
374 | ||
375 | category may be given as one of the LC_* values. | |
376 | ||
377 | """ | |
378 | if locale and type(locale) is not type(""): | |
379 | # convert to string | |
380 | locale = normalize(_build_localename(locale)) | |
381 | return _setlocale(category, locale) | |
382 | ||
383 | def resetlocale(category=LC_ALL): | |
384 | ||
385 | """ Sets the locale for category to the default setting. | |
386 | ||
387 | The default setting is determined by calling | |
388 | getdefaultlocale(). category defaults to LC_ALL. | |
389 | ||
390 | """ | |
391 | _setlocale(category, _build_localename(getdefaultlocale())) | |
392 | ||
393 | if sys.platform in ('win32', 'darwin', 'mac'): | |
394 | # On Win32, this will return the ANSI code page | |
395 | # On the Mac, it should return the system encoding; | |
396 | # it might return "ascii" instead | |
397 | def getpreferredencoding(do_setlocale = True): | |
398 | """Return the charset that the user is likely using.""" | |
399 | import _locale | |
400 | return _locale._getdefaultlocale()[1] | |
401 | else: | |
402 | # On Unix, if CODESET is available, use that. | |
403 | try: | |
404 | CODESET | |
405 | except NameError: | |
406 | # Fall back to parsing environment variables :-( | |
407 | def getpreferredencoding(do_setlocale = True): | |
408 | """Return the charset that the user is likely using, | |
409 | by looking at environment variables.""" | |
410 | return getdefaultlocale()[1] | |
411 | else: | |
412 | def getpreferredencoding(do_setlocale = True): | |
413 | """Return the charset that the user is likely using, | |
414 | according to the system configuration.""" | |
415 | if do_setlocale: | |
416 | oldloc = setlocale(LC_CTYPE) | |
417 | setlocale(LC_CTYPE, "") | |
418 | result = nl_langinfo(CODESET) | |
419 | setlocale(LC_CTYPE, oldloc) | |
420 | return result | |
421 | else: | |
422 | return nl_langinfo(CODESET) | |
423 | ||
424 | ||
425 | ### Database | |
426 | # | |
427 | # The following data was extracted from the locale.alias file which | |
428 | # comes with X11 and then hand edited removing the explicit encoding | |
429 | # definitions and adding some more aliases. The file is usually | |
430 | # available as /usr/lib/X11/locale/locale.alias. | |
431 | # | |
432 | ||
433 | # | |
434 | # The encoding_alias table maps lowercase encoding alias names to C | |
435 | # locale encoding names (case-sensitive). | |
436 | # | |
437 | encoding_alias = { | |
438 | '437': 'C', | |
439 | 'c': 'C', | |
440 | 'iso8859': 'ISO8859-1', | |
441 | '8859': 'ISO8859-1', | |
442 | '88591': 'ISO8859-1', | |
443 | 'ascii': 'ISO8859-1', | |
444 | 'en': 'ISO8859-1', | |
445 | 'iso88591': 'ISO8859-1', | |
446 | 'iso_8859-1': 'ISO8859-1', | |
447 | '885915': 'ISO8859-15', | |
448 | 'iso885915': 'ISO8859-15', | |
449 | 'iso_8859-15': 'ISO8859-15', | |
450 | 'iso8859-2': 'ISO8859-2', | |
451 | 'iso88592': 'ISO8859-2', | |
452 | 'iso_8859-2': 'ISO8859-2', | |
453 | 'iso88595': 'ISO8859-5', | |
454 | 'iso88596': 'ISO8859-6', | |
455 | 'iso88597': 'ISO8859-7', | |
456 | 'iso88598': 'ISO8859-8', | |
457 | 'iso88599': 'ISO8859-9', | |
458 | 'iso-2022-jp': 'JIS7', | |
459 | 'jis': 'JIS7', | |
460 | 'jis7': 'JIS7', | |
461 | 'sjis': 'SJIS', | |
462 | 'tis620': 'TACTIS', | |
463 | 'ajec': 'eucJP', | |
464 | 'eucjp': 'eucJP', | |
465 | 'ujis': 'eucJP', | |
466 | 'utf-8': 'utf', | |
467 | 'utf8': 'utf', | |
468 | 'utf8@ucs4': 'utf', | |
469 | } | |
470 | ||
471 | # | |
472 | # The locale_alias table maps lowercase alias names to C locale names | |
473 | # (case-sensitive). Encodings are always separated from the locale | |
474 | # name using a dot ('.'); they should only be given in case the | |
475 | # language name is needed to interpret the given encoding alias | |
476 | # correctly (CJK codes often have this need). | |
477 | # | |
478 | locale_alias = { | |
479 | 'american': 'en_US.ISO8859-1', | |
480 | 'ar': 'ar_AA.ISO8859-6', | |
481 | 'ar_aa': 'ar_AA.ISO8859-6', | |
482 | 'ar_sa': 'ar_SA.ISO8859-6', | |
483 | 'arabic': 'ar_AA.ISO8859-6', | |
484 | 'bg': 'bg_BG.ISO8859-5', | |
485 | 'bg_bg': 'bg_BG.ISO8859-5', | |
486 | 'bulgarian': 'bg_BG.ISO8859-5', | |
487 | 'c-french': 'fr_CA.ISO8859-1', | |
488 | 'c': 'C', | |
489 | 'c_c': 'C', | |
490 | 'cextend': 'en_US.ISO8859-1', | |
491 | 'chinese-s': 'zh_CN.eucCN', | |
492 | 'chinese-t': 'zh_TW.eucTW', | |
493 | 'croatian': 'hr_HR.ISO8859-2', | |
494 | 'cs': 'cs_CZ.ISO8859-2', | |
495 | 'cs_cs': 'cs_CZ.ISO8859-2', | |
496 | 'cs_cz': 'cs_CZ.ISO8859-2', | |
497 | 'cz': 'cz_CZ.ISO8859-2', | |
498 | 'cz_cz': 'cz_CZ.ISO8859-2', | |
499 | 'czech': 'cs_CS.ISO8859-2', | |
500 | 'da': 'da_DK.ISO8859-1', | |
501 | 'da_dk': 'da_DK.ISO8859-1', | |
502 | 'danish': 'da_DK.ISO8859-1', | |
503 | 'de': 'de_DE.ISO8859-1', | |
504 | 'de_at': 'de_AT.ISO8859-1', | |
505 | 'de_ch': 'de_CH.ISO8859-1', | |
506 | 'de_de': 'de_DE.ISO8859-1', | |
507 | 'dutch': 'nl_BE.ISO8859-1', | |
508 | 'ee': 'ee_EE.ISO8859-4', | |
509 | 'el': 'el_GR.ISO8859-7', | |
510 | 'el_gr': 'el_GR.ISO8859-7', | |
511 | 'en': 'en_US.ISO8859-1', | |
512 | 'en_au': 'en_AU.ISO8859-1', | |
513 | 'en_ca': 'en_CA.ISO8859-1', | |
514 | 'en_gb': 'en_GB.ISO8859-1', | |
515 | 'en_ie': 'en_IE.ISO8859-1', | |
516 | 'en_nz': 'en_NZ.ISO8859-1', | |
517 | 'en_uk': 'en_GB.ISO8859-1', | |
518 | 'en_us': 'en_US.ISO8859-1', | |
519 | 'eng_gb': 'en_GB.ISO8859-1', | |
520 | 'english': 'en_EN.ISO8859-1', | |
521 | 'english_uk': 'en_GB.ISO8859-1', | |
522 | 'english_united-states': 'en_US.ISO8859-1', | |
523 | 'english_us': 'en_US.ISO8859-1', | |
524 | 'es': 'es_ES.ISO8859-1', | |
525 | 'es_ar': 'es_AR.ISO8859-1', | |
526 | 'es_bo': 'es_BO.ISO8859-1', | |
527 | 'es_cl': 'es_CL.ISO8859-1', | |
528 | 'es_co': 'es_CO.ISO8859-1', | |
529 | 'es_cr': 'es_CR.ISO8859-1', | |
530 | 'es_ec': 'es_EC.ISO8859-1', | |
531 | 'es_es': 'es_ES.ISO8859-1', | |
532 | 'es_gt': 'es_GT.ISO8859-1', | |
533 | 'es_mx': 'es_MX.ISO8859-1', | |
534 | 'es_ni': 'es_NI.ISO8859-1', | |
535 | 'es_pa': 'es_PA.ISO8859-1', | |
536 | 'es_pe': 'es_PE.ISO8859-1', | |
537 | 'es_py': 'es_PY.ISO8859-1', | |
538 | 'es_sv': 'es_SV.ISO8859-1', | |
539 | 'es_uy': 'es_UY.ISO8859-1', | |
540 | 'es_ve': 'es_VE.ISO8859-1', | |
541 | 'et': 'et_EE.ISO8859-4', | |
542 | 'et_ee': 'et_EE.ISO8859-4', | |
543 | 'fi': 'fi_FI.ISO8859-1', | |
544 | 'fi_fi': 'fi_FI.ISO8859-1', | |
545 | 'finnish': 'fi_FI.ISO8859-1', | |
546 | 'fr': 'fr_FR.ISO8859-1', | |
547 | 'fr_be': 'fr_BE.ISO8859-1', | |
548 | 'fr_ca': 'fr_CA.ISO8859-1', | |
549 | 'fr_ch': 'fr_CH.ISO8859-1', | |
550 | 'fr_fr': 'fr_FR.ISO8859-1', | |
551 | 'fre_fr': 'fr_FR.ISO8859-1', | |
552 | 'french': 'fr_FR.ISO8859-1', | |
553 | 'french_france': 'fr_FR.ISO8859-1', | |
554 | 'ger_de': 'de_DE.ISO8859-1', | |
555 | 'german': 'de_DE.ISO8859-1', | |
556 | 'german_germany': 'de_DE.ISO8859-1', | |
557 | 'greek': 'el_GR.ISO8859-7', | |
558 | 'hebrew': 'iw_IL.ISO8859-8', | |
559 | 'hr': 'hr_HR.ISO8859-2', | |
560 | 'hr_hr': 'hr_HR.ISO8859-2', | |
561 | 'hu': 'hu_HU.ISO8859-2', | |
562 | 'hu_hu': 'hu_HU.ISO8859-2', | |
563 | 'hungarian': 'hu_HU.ISO8859-2', | |
564 | 'icelandic': 'is_IS.ISO8859-1', | |
565 | 'id': 'id_ID.ISO8859-1', | |
566 | 'id_id': 'id_ID.ISO8859-1', | |
567 | 'is': 'is_IS.ISO8859-1', | |
568 | 'is_is': 'is_IS.ISO8859-1', | |
569 | 'iso-8859-1': 'en_US.ISO8859-1', | |
570 | 'iso-8859-15': 'en_US.ISO8859-15', | |
571 | 'iso8859-1': 'en_US.ISO8859-1', | |
572 | 'iso8859-15': 'en_US.ISO8859-15', | |
573 | 'iso_8859_1': 'en_US.ISO8859-1', | |
574 | 'iso_8859_15': 'en_US.ISO8859-15', | |
575 | 'it': 'it_IT.ISO8859-1', | |
576 | 'it_ch': 'it_CH.ISO8859-1', | |
577 | 'it_it': 'it_IT.ISO8859-1', | |
578 | 'italian': 'it_IT.ISO8859-1', | |
579 | 'iw': 'iw_IL.ISO8859-8', | |
580 | 'iw_il': 'iw_IL.ISO8859-8', | |
581 | 'ja': 'ja_JP.eucJP', | |
582 | 'ja.jis': 'ja_JP.JIS7', | |
583 | 'ja.sjis': 'ja_JP.SJIS', | |
584 | 'ja_jp': 'ja_JP.eucJP', | |
585 | 'ja_jp.ajec': 'ja_JP.eucJP', | |
586 | 'ja_jp.euc': 'ja_JP.eucJP', | |
587 | 'ja_jp.eucjp': 'ja_JP.eucJP', | |
588 | 'ja_jp.iso-2022-jp': 'ja_JP.JIS7', | |
589 | 'ja_jp.jis': 'ja_JP.JIS7', | |
590 | 'ja_jp.jis7': 'ja_JP.JIS7', | |
591 | 'ja_jp.mscode': 'ja_JP.SJIS', | |
592 | 'ja_jp.sjis': 'ja_JP.SJIS', | |
593 | 'ja_jp.ujis': 'ja_JP.eucJP', | |
594 | 'japan': 'ja_JP.eucJP', | |
595 | 'japanese': 'ja_JP.SJIS', | |
596 | 'japanese-euc': 'ja_JP.eucJP', | |
597 | 'japanese.euc': 'ja_JP.eucJP', | |
598 | 'jp_jp': 'ja_JP.eucJP', | |
599 | 'ko': 'ko_KR.eucKR', | |
600 | 'ko_kr': 'ko_KR.eucKR', | |
601 | 'ko_kr.euc': 'ko_KR.eucKR', | |
602 | 'korean': 'ko_KR.eucKR', | |
603 | 'lt': 'lt_LT.ISO8859-4', | |
604 | 'lv': 'lv_LV.ISO8859-4', | |
605 | 'mk': 'mk_MK.ISO8859-5', | |
606 | 'mk_mk': 'mk_MK.ISO8859-5', | |
607 | 'nl': 'nl_NL.ISO8859-1', | |
608 | 'nl_be': 'nl_BE.ISO8859-1', | |
609 | 'nl_nl': 'nl_NL.ISO8859-1', | |
610 | 'no': 'no_NO.ISO8859-1', | |
611 | 'no_no': 'no_NO.ISO8859-1', | |
612 | 'norwegian': 'no_NO.ISO8859-1', | |
613 | 'pl': 'pl_PL.ISO8859-2', | |
614 | 'pl_pl': 'pl_PL.ISO8859-2', | |
615 | 'polish': 'pl_PL.ISO8859-2', | |
616 | 'portuguese': 'pt_PT.ISO8859-1', | |
617 | 'portuguese_brazil': 'pt_BR.ISO8859-1', | |
618 | 'posix': 'C', | |
619 | 'posix-utf2': 'C', | |
620 | 'pt': 'pt_PT.ISO8859-1', | |
621 | 'pt_br': 'pt_BR.ISO8859-1', | |
622 | 'pt_pt': 'pt_PT.ISO8859-1', | |
623 | 'ro': 'ro_RO.ISO8859-2', | |
624 | 'ro_ro': 'ro_RO.ISO8859-2', | |
625 | 'ru': 'ru_RU.ISO8859-5', | |
626 | 'ru_ru': 'ru_RU.ISO8859-5', | |
627 | 'rumanian': 'ro_RO.ISO8859-2', | |
628 | 'russian': 'ru_RU.ISO8859-5', | |
629 | 'serbocroatian': 'sh_YU.ISO8859-2', | |
630 | 'sh': 'sh_YU.ISO8859-2', | |
631 | 'sh_hr': 'sh_HR.ISO8859-2', | |
632 | 'sh_sp': 'sh_YU.ISO8859-2', | |
633 | 'sh_yu': 'sh_YU.ISO8859-2', | |
634 | 'sk': 'sk_SK.ISO8859-2', | |
635 | 'sk_sk': 'sk_SK.ISO8859-2', | |
636 | 'sl': 'sl_CS.ISO8859-2', | |
637 | 'sl_cs': 'sl_CS.ISO8859-2', | |
638 | 'sl_si': 'sl_SI.ISO8859-2', | |
639 | 'slovak': 'sk_SK.ISO8859-2', | |
640 | 'slovene': 'sl_CS.ISO8859-2', | |
641 | 'sp': 'sp_YU.ISO8859-5', | |
642 | 'sp_yu': 'sp_YU.ISO8859-5', | |
643 | 'spanish': 'es_ES.ISO8859-1', | |
644 | 'spanish_spain': 'es_ES.ISO8859-1', | |
645 | 'sr_sp': 'sr_SP.ISO8859-2', | |
646 | 'sv': 'sv_SE.ISO8859-1', | |
647 | 'sv_se': 'sv_SE.ISO8859-1', | |
648 | 'swedish': 'sv_SE.ISO8859-1', | |
649 | 'th_th': 'th_TH.TACTIS', | |
650 | 'tr': 'tr_TR.ISO8859-9', | |
651 | 'tr_tr': 'tr_TR.ISO8859-9', | |
652 | 'turkish': 'tr_TR.ISO8859-9', | |
653 | 'univ': 'en_US.utf', | |
654 | 'universal': 'en_US.utf', | |
655 | 'zh': 'zh_CN.eucCN', | |
656 | 'zh_cn': 'zh_CN.eucCN', | |
657 | 'zh_cn.big5': 'zh_TW.eucTW', | |
658 | 'zh_cn.euc': 'zh_CN.eucCN', | |
659 | 'zh_tw': 'zh_TW.eucTW', | |
660 | 'zh_tw.euc': 'zh_TW.eucTW', | |
661 | } | |
662 | ||
663 | # | |
664 | # this maps windows language identifiers (as used on Windows 95 and | |
665 | # earlier) to locale strings. | |
666 | # | |
667 | # NOTE: this mapping is incomplete. If your language is missing, please | |
668 | # submit a bug report to Python bug manager, which you can find via: | |
669 | # http://www.python.org/dev/ | |
670 | # Make sure you include the missing language identifier and the suggested | |
671 | # locale code. | |
672 | # | |
673 | ||
674 | windows_locale = { | |
675 | 0x0404: "zh_TW", # Chinese (Taiwan) | |
676 | 0x0804: "zh_CN", # Chinese (PRC) | |
677 | 0x0406: "da_DK", # Danish | |
678 | 0x0413: "nl_NL", # Dutch (Netherlands) | |
679 | 0x0409: "en_US", # English (United States) | |
680 | 0x0809: "en_UK", # English (United Kingdom) | |
681 | 0x0c09: "en_AU", # English (Australian) | |
682 | 0x1009: "en_CA", # English (Canadian) | |
683 | 0x1409: "en_NZ", # English (New Zealand) | |
684 | 0x1809: "en_IE", # English (Ireland) | |
685 | 0x1c09: "en_ZA", # English (South Africa) | |
686 | 0x040b: "fi_FI", # Finnish | |
687 | 0x040c: "fr_FR", # French (Standard) | |
688 | 0x080c: "fr_BE", # French (Belgian) | |
689 | 0x0c0c: "fr_CA", # French (Canadian) | |
690 | 0x100c: "fr_CH", # French (Switzerland) | |
691 | 0x0407: "de_DE", # German (Standard) | |
692 | 0x0408: "el_GR", # Greek | |
693 | 0x040d: "iw_IL", # Hebrew | |
694 | 0x040f: "is_IS", # Icelandic | |
695 | 0x0410: "it_IT", # Italian (Standard) | |
696 | 0x0411: "ja_JA", # Japanese | |
697 | 0x0414: "no_NO", # Norwegian (Bokmal) | |
698 | 0x0816: "pt_PT", # Portuguese (Standard) | |
699 | 0x0c0a: "es_ES", # Spanish (Modern Sort) | |
700 | 0x0441: "sw_KE", # Swahili (Kenya) | |
701 | 0x041d: "sv_SE", # Swedish | |
702 | 0x081d: "sv_FI", # Swedish (Finland) | |
703 | 0x041f: "tr_TR", # Turkish | |
704 | } | |
705 | ||
706 | def _print_locale(): | |
707 | ||
708 | """ Test function. | |
709 | """ | |
710 | categories = {} | |
711 | def _init_categories(categories=categories): | |
712 | for k,v in globals().items(): | |
713 | if k[:3] == 'LC_': | |
714 | categories[k] = v | |
715 | _init_categories() | |
716 | del categories['LC_ALL'] | |
717 | ||
718 | print 'Locale defaults as determined by getdefaultlocale():' | |
719 | print '-'*72 | |
720 | lang, enc = getdefaultlocale() | |
721 | print 'Language: ', lang or '(undefined)' | |
722 | print 'Encoding: ', enc or '(undefined)' | |
723 | ||
724 | ||
725 | print 'Locale settings on startup:' | |
726 | print '-'*72 | |
727 | for name,category in categories.items(): | |
728 | print name, '...' | |
729 | lang, enc = getlocale(category) | |
730 | print ' Language: ', lang or '(undefined)' | |
731 | print ' Encoding: ', enc or '(undefined)' | |
732 | ||
733 | ||
734 | ||
735 | print 'Locale settings after calling resetlocale():' | |
736 | print '-'*72 | |
737 | resetlocale() | |
738 | for name,category in categories.items(): | |
739 | print name, '...' | |
740 | lang, enc = getlocale(category) | |
741 | print ' Language: ', lang or '(undefined)' | |
742 | print ' Encoding: ', enc or '(undefined)' | |
743 | ||
744 | ||
745 | try: | |
746 | setlocale(LC_ALL, "") | |
747 | except: | |
748 | print 'NOTE:' | |
749 | print 'setlocale(LC_ALL, "") does not support the default locale' | |
750 | print 'given in the OS environment variables.' | |
751 | else: | |
752 | ||
753 | print 'Locale settings after calling setlocale(LC_ALL, ""):' | |
754 | print '-'*72 | |
755 | for name,category in categories.items(): | |
756 | print name, '...' | |
757 | lang, enc = getlocale(category) | |
758 | print ' Language: ', lang or '(undefined)' | |
759 | print ' Encoding: ', enc or '(undefined)' | |
760 | ||
761 | ||
762 | ### | |
763 | ||
764 | try: | |
765 | LC_MESSAGES | |
766 | except NameError: | |
767 | pass | |
768 | else: | |
769 | __all__.append("LC_MESSAGES") | |
770 | ||
771 | if __name__=='__main__': | |
772 | print 'Locale aliasing:' | |
773 | ||
774 | _print_locale() | |
775 | ||
776 | print 'Number formatting:' | |
777 | ||
778 | _test() |