summaryrefslogtreecommitdiffstats
path: root/Lib/gettext.py
blob: e43f044cc71419aaa95dfa2555aee2389a13e9ce (plain)
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
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
"""Internationalization and localization support.

This module provides internationalization (I18N) and localization (L10N)
support for your Python programs by providing an interface to the GNU gettext
message catalog library.

I18N refers to the operation by which a program is made aware of multiple
languages.  L10N refers to the adaptation of your program, once
internationalized, to the local language and cultural habits.

"""

# This module represents the integration of work, contributions, feedback, and
# suggestions from the following people:
#
# Martin von Loewis, who wrote the initial implementation of the underlying
# C-based libintlmodule (later renamed _gettext), along with a skeletal
# gettext.py implementation.
#
# Peter Funk, who wrote fintl.py, a fairly complete wrapper around intlmodule,
# which also included a pure-Python implementation to read .mo files if
# intlmodule wasn't available.
#
# James Henstridge, who also wrote a gettext.py module, which has some
# interesting, but currently unsupported experimental features: the notion of
# a Catalog class and instances, and the ability to add to a catalog file via
# a Python API.
#
# Barry Warsaw integrated these modules, wrote the .install() API and code,
# and conformed all C and Python code to Python's coding standards.
#
# Francois Pinard and Marc-Andre Lemburg also contributed valuably to this
# module.
#
# J. David Ibanez implemented plural forms. Bruno Haible fixed some bugs.
#
# TODO:
# - Lazy loading of .mo files.  Currently the entire catalog is loaded into
#   memory, but that's probably bad for large translated programs.  Instead,
#   the lexical sort of original strings in GNU .mo files should be exploited
#   to do binary searches and lazy initializations.  Or you might want to use
#   the undocumented double-hash algorithm for .mo files with hash tables, but
#   you'll need to study the GNU gettext code to do this.
#
# - Support Solaris .mo file formats.  Unfortunately, we've been unable to
#   find this format documented anywhere.


import locale, copy, io, os, re, struct, sys
from errno import ENOENT


__all__ = ['NullTranslations', 'GNUTranslations', 'Catalog',
           'find', 'translation', 'install', 'textdomain', 'bindtextdomain',
           'dgettext', 'dngettext', 'gettext', 'ngettext',
           ]

_default_localedir = os.path.join(sys.base_prefix, 'share', 'locale')


def c2py(plural):
    """Gets a C expression as used in PO files for plural forms and returns a
    Python lambda function that implements an equivalent expression.
    """
    # Security check, allow only the "n" identifier
    import token, tokenize
    tokens = tokenize.generate_tokens(io.StringIO(plural).readline)
    try:
        danger = [x for x in tokens if x[0] == token.NAME and x[1] != 'n']
    except tokenize.TokenError:
        raise ValueError('plural forms expression error, maybe unbalanced parenthesis')
    else:
        if danger:
            raise ValueError('plural forms expression could be dangerous')

    # Replace some C operators by their Python equivalents
    plural = plural.replace('&&', ' and ')
    plural = plural.replace('||', ' or ')

    expr = re.compile(r'\!([^=])')
    plural = expr.sub(' not \\1', plural)

    # Regular expression and replacement function used to transform
    # "a?b:c" to "b if a else c".
    expr = re.compile(r'(.*?)\?(.*?):(.*)')
    def repl(x):
        return "(%s if %s else %s)" % (x.group(2), x.group(1),
                                       expr.sub(repl, x.group(3)))

    # Code to transform the plural expression, taking care of parentheses
    stack = ['']
    for c in plural:
        if c == '(':
            stack.append('')
        elif c == ')':
            if len(stack) == 1:
                # Actually, we never reach this code, because unbalanced
                # parentheses get caught in the security check at the
                # beginning.
                raise ValueError('unbalanced parenthesis in plural form')
            s = expr.sub(repl, stack.pop())
            stack[-1] += '(%s)' % s
        else:
            stack[-1] += c
    plural = expr.sub(repl, stack.pop())

    return eval('lambda n: int(%s)' % plural)



def _expand_lang(loc):
    loc = locale.normalize(loc)
    COMPONENT_CODESET   = 1 << 0
    COMPONENT_TERRITORY = 1 << 1
    COMPONENT_MODIFIER  = 1 << 2
    # split up the locale into its base components
    mask = 0
    pos = loc.find('@')
    if pos >= 0:
        modifier = loc[pos:]
        loc = loc[:pos]
        mask |= COMPONENT_MODIFIER
    else:
        modifier = ''
    pos = loc.find('.')
    if pos >= 0:
        codeset = loc[pos:]
        loc = loc[:pos]
        mask |= COMPONENT_CODESET
    else:
        codeset = ''
    pos = loc.find('_')
    if pos >= 0:
        territory = loc[pos:]
        loc = loc[:pos]
        mask |= COMPONENT_TERRITORY
    else:
        territory = ''
    language = loc
    ret = []
    for i in range(mask+1):
        if not (i & ~mask):  # if all components for this combo exist ...
            val = language
            if i & COMPONENT_TERRITORY: val += territory
            if i & COMPONENT_CODESET:   val += codeset
            if i & COMPONENT_MODIFIER:  val += modifier
            ret.append(val)
    ret.reverse()
    return ret



class NullTranslations:
    def __init__(self, fp=None):
        self._info = {}
        self._charset = None
        self._output_charset = None
        self._fallback = None
        if fp is not None:
            self._parse(fp)

    def _parse(self, fp):
        pass

    def add_fallback(self, fallback):
        if self._fallback:
            self._fallback.add_fallback(fallback)
        else:
            self._fallback = fallback

    def gettext(self, message):
        if self._fallback:
            return self._fallback.gettext(message)
        return message

    def lgettext(self, message):
        if self._fallback:
            return self._fallback.lgettext(message)
        return message

    def ngettext(self, msgid1, msgid2, n):
        if self._fallback:
            return self._fallback.ngettext(msgid1, msgid2, n)
        if n == 1:
            return msgid1
        else:
            return msgid2

    def lngettext(self, msgid1, msgid2, n):
        if self._fallback:
            return self._fallback.lngettext(msgid1, msgid2, n)
        if n == 1:
            return msgid1
        else:
            return msgid2

    def info(self):
        return self._info

    def charset(self):
        return self._charset

    def output_charset(self):
        return self._output_charset

    def set_output_charset(self, charset):
        self._output_charset = charset

    def install(self, names=None):
        import builtins
        builtins.__dict__['_'] = self.gettext
        if hasattr(names, "__contains__"):
            if "gettext" in names:
                builtins.__dict__['gettext'] = builtins.__dict__['_']
            if "ngettext" in names:
                builtins.__dict__['ngettext'] = self.ngettext
            if "lgettext" in names:
                builtins.__dict__['lgettext'] = self.lgettext
            if "lngettext" in names:
                builtins.__dict__['lngettext'] = self.lngettext


class GNUTranslations(NullTranslations):
    # Magic number of .mo files
    LE_MAGIC = 0x950412de
    BE_MAGIC = 0xde120495

    def _parse(self, fp):
        """Override this method to support alternative .mo formats."""
        unpack = struct.unpack
        filename = getattr(fp, 'name', '')
        # Parse the .mo file header, which consists of 5 little endian 32
        # bit words.
        self._catalog = catalog = {}
        self.plural = lambda n: int(n != 1) # germanic plural by default
        buf = fp.read()
        buflen = len(buf)
        # Are we big endian or little endian?
        magic = unpack('<I', buf[:4])[0]
        if magic == self.LE_MAGIC:
            version, msgcount, masteridx, transidx = unpack('<4I', buf[4:20])
            ii = '<II'
        elif magic == self.BE_MAGIC:
            version, msgcount, masteridx, transidx = unpack('>4I', buf[4:20])
            ii = '>II'
        else:
            raise IOError(0, 'Bad magic number', filename)
        # Now put all messages from the .mo file buffer into the catalog
        # dictionary.
        for i in range(0, msgcount):
            mlen, moff = unpack(ii, buf[masteridx:masteridx+8])
            mend = moff + mlen
            tlen, toff = unpack(ii, buf[transidx:transidx+8])
            tend = toff + tlen
            if mend < buflen and tend < buflen:
                msg = buf[moff:mend]
                tmsg = buf[toff:tend]
            else:
                raise IOError(0, 'File is corrupt', filename)
            # See if we're looking at GNU .mo conventions for metadata
            if mlen == 0:
                # Catalog description
                lastk = k = None
                for b_item in tmsg.split('\n'.encode("ascii")):
                    item = b_item.decode().strip()
                    if not item:
                        continue
                    if ':' in item:
                        k, v = item.split(':', 1)
                        k = k.strip().lower()
                        v = v.strip()
                        self._info[k] = v
                        lastk = k
                    elif lastk:
                        self._info[lastk] += '\n' + item
                    if k == 'content-type':
                        self._charset = v.split('charset=')[1]
                    elif k == 'plural-forms':
                        v = v.split(';')
                        plural = v[1].split('plural=')[1]
                        self.plural = c2py(plural)
            # Note: we unconditionally convert both msgids and msgstrs to
            # Unicode using the character encoding specified in the charset
            # parameter of the Content-Type header.  The gettext documentation
            # strongly encourages msgids to be us-ascii, but some applications
            # require alternative encodings (e.g. Zope's ZCML and ZPT).  For
            # traditional gettext applications, the msgid conversion will
            # cause no problems since us-ascii should always be a subset of
            # the charset encoding.  We may want to fall back to 8-bit msgids
            # if the Unicode conversion fails.
            charset = self._charset or 'ascii'
            if b'\x00' in msg:
                # Plural forms
                msgid1, msgid2 = msg.split(b'\x00')
                tmsg = tmsg.split(b'\x00')
                msgid1 = str(msgid1, charset)
                for i, x in enumerate(tmsg):
                    catalog[(msgid1, i)] = str(x, charset)
            else:
                catalog[str(msg, charset)] = str(tmsg, charset)
            # advance to next entry in the seek tables
            masteridx += 8
            transidx += 8

    def lgettext(self, message):
        missing = object()
        tmsg = self._catalog.get(message, missing)
        if tmsg is missing:
            if self._fallback:
                return self._fallback.lgettext(message)
            return message
        if self._output_charset:
            return tmsg.encode(self._output_charset)
        return tmsg.encode(locale.getpreferredencoding())

    def lngettext(self, msgid1, msgid2, n):
        try:
            tmsg = self._catalog[(msgid1, self.plural(n))]
            if self._output_charset:
                return tmsg.encode(self._output_charset)
            return tmsg.encode(locale.getpreferredencoding())
        except KeyError:
            if self._fallback:
                return self._fallback.lngettext(msgid1, msgid2, n)
            if n == 1:
                return msgid1
            else:
                return msgid2

    def gettext(self, message):
        missing = object()
        tmsg = self._catalog.get(message, missing)
        if tmsg is missing:
            if self._fallback:
                return self._fallback.gettext(message)
            return message
        return tmsg

    def ngettext(self, msgid1, msgid2, n):
        try:
            tmsg = self._catalog[(msgid1, self.plural(n))]
        except KeyError:
            if self._fallback:
                return self._fallback.ngettext(msgid1, msgid2, n)
            if n == 1:
                tmsg = msgid1
            else:
                tmsg = msgid2
        return tmsg


# Locate a .mo file using the gettext strategy
def find(domain, localedir=None, languages=None, all=False):
    # Get some reasonable defaults for arguments that were not supplied
    if localedir is None:
        localedir = _default_localedir
    if languages is None:
        languages = []
        for envar in ('LANGUAGE', 'LC_ALL', 'LC_MESSAGES', 'LANG'):
            val = os.environ.get(envar)
            if val:
                languages = val.split(':')
                break
        if 'C' not in languages:
            languages.append('C')
    # now normalize and expand the languages
    nelangs = []
    for lang in languages:
        for nelang in _expand_lang(lang):
            if nelang not in nelangs:
                nelangs.append(nelang)
    # select a language
    if all:
        result = []
    else:
        result = None
    for lang in nelangs:
        if lang == 'C':
            break
        mofile = os.path.join(localedir, lang, 'LC_MESSAGES', '%s.mo' % domain)
        if os.path.exists(mofile):
            if all:
                result.append(mofile)
            else:
                return mofile
    return result



# a mapping between absolute .mo file path and Translation object
_translations = {}

def translation(domain, localedir=None, languages=None,
                class_=None, fallback=False, codeset=None):
    if class_ is None:
        class_ = GNUTranslations
    mofiles = find(domain, localedir, languages, all=True)
    if not mofiles:
        if fallback:
            return NullTranslations()
        raise IOError(ENOENT, 'No translation file found for domain', domain)
    # Avoid opening, reading, and parsing the .mo file after it's been done
    # once.
    result = None
    for mofile in mofiles:
        key = (class_, os.path.abspath(mofile))
        t = _translations.get(key)
        if t is None:
            with open(mofile, 'rb') as fp:
                t = _translations.setdefault(key, class_(fp))
        # Copy the translation object to allow setting fallbacks and
        # output charset. All other instance data is shared with the
        # cached object.
        t = copy.copy(t)
        if codeset:
            t.set_output_charset(codeset)
        if result is None:
            result = t
        else:
            result.add_fallback(t)
    return result


def install(domain, localedir=None, codeset=None, names=None):
    t = translation(domain, localedir, fallback=True, codeset=codeset)
    t.install(names)



# a mapping b/w domains and locale directories
_localedirs = {}
# a mapping b/w domains and codesets
_localecodesets = {}
# current global domain, `messages' used for compatibility w/ GNU gettext
_current_domain = 'messages'


def textdomain(domain=None):
    global _current_domain
    if domain is not None:
        _current_domain = domain
    return _current_domain


def bindtextdomain(domain, localedir=None):
    global _localedirs
    if localedir is not None:
        _localedirs[domain] = localedir
    return _localedirs.get(domain, _default_localedir)


def bind_textdomain_codeset(domain, codeset=None):
    global _localecodesets
    if codeset is not None:
        _localecodesets[domain] = codeset
    return _localecodesets.get(domain)


def dgettext(domain, message):
    try:
        t = translation(domain, _localedirs.get(domain, None),
                        codeset=_localecodesets.get(domain))
    except IOError:
        return message
    return t.gettext(message)

def ldgettext(domain, message):
    try:
        t = translation(domain, _localedirs.get(domain, None),
                        codeset=_localecodesets.get(domain))
    except IOError:
        return message
    return t.lgettext(message)

def dngettext(domain, msgid1, msgid2, n):
    try:
        t = translation(domain, _localedirs.get(domain, None),
                        codeset=_localecodesets.get(domain))
    except IOError:
        if n == 1:
            return msgid1
        else:
            return msgid2
    return t.ngettext(msgid1, msgid2, n)

def ldngettext(domain, msgid1, msgid2, n):
    try:
        t = translation(domain, _localedirs.get(domain, None),
                        codeset=_localecodesets.get(domain))
    except IOError:
        if n == 1:
            return msgid1
        else:
            return msgid2
    return t.lngettext(msgid1, msgid2, n)

def gettext(message):
    return dgettext(_current_domain, message)

def lgettext(message):
    return ldgettext(_current_domain, message)

def ngettext(msgid1, msgid2, n):
    return dngettext(_current_domain, msgid1, msgid2, n)

def lngettext(msgid1, msgid2, n):
    return ldngettext(_current_domain, msgid1, msgid2, n)

# dcgettext() has been deemed unnecessary and is not implemented.

# James Henstridge's Catalog constructor from GNOME gettext.  Documented usage
# was:
#
#    import gettext
#    cat = gettext.Catalog(PACKAGE, localedir=LOCALEDIR)
#    _ = cat.gettext
#    print _('Hello World')

# The resulting catalog object currently don't support access through a
# dictionary API, which was supported (but apparently unused) in GNOME
# gettext.

Catalog = translation