summaryrefslogtreecommitdiffstats
path: root/msgfmt.py
blob: 31d117d9cc5ef101128a8584c205faf88086c88a (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
# -*- coding: iso-8859-1 -*-
# Written by Martin v. Lwis <loewis@informatik.hu-berlin.de>
# Plural forms support added by alexander smishlajev <alex@tycobka.lv>
"""
Generate binary message catalog from textual translation description.

This program converts a textual Uniforum-style message catalog (.po file) into
a binary GNU catalog (.mo file).  This is essentially the same function as the
GNU msgfmt program, however, it is a simpler implementation.

Usage: msgfmt.py [OPTIONS] filename.po

Options:
    -o file
    --output-file=file
        Specify the output file to write to.  If omitted, output will go to a
        file named filename.mo (based off the input file name).

    -h
    --help
        Print this message and exit.

    -V
    --version
        Display version information and exit.
"""

import sys
import os
import getopt
import struct
import array

__version__ = "1.1"

MESSAGES = {}


def usage (ecode, msg=''):
    """
    Print usage and msg and exit with given code.
    """
    print >> sys.stderr, __doc__
    if msg:
        print >> sys.stderr, msg
    sys.exit(ecode)


def add (msgid, transtr, fuzzy):
    """
    Add a non-fuzzy translation to the dictionary.
    """
    global MESSAGES
    if not fuzzy and transtr and not transtr.startswith('\0'):
        MESSAGES[msgid] = transtr


def generate ():
    """
    Return the generated output.
    """
    global MESSAGES
    keys = MESSAGES.keys()
    # the keys are sorted in the .mo file
    keys.sort()
    offsets = []
    ids = strs = ''
    for _id in keys:
        # For each string, we need size and file offset.  Each string is NUL
        # terminated; the NUL does not count into the size.
        offsets.append((len(ids), len(_id), len(strs), len(MESSAGES[_id])))
        ids += _id + '\0'
        strs += MESSAGES[_id] + '\0'
    output = ''
    # The header is 7 32-bit unsigned integers.  We don't use hash tables, so
    # the keys start right after the index tables.
    # translated string.
    keystart = 7*4+16*len(keys)
    # and the values start after the keys
    valuestart = keystart + len(ids)
    koffsets = []
    voffsets = []
    # The string table first has the list of keys, then the list of values.
    # Each entry has first the size of the string, then the file offset.
    for o1, l1, o2, l2 in offsets:
        koffsets += [l1, o1+keystart]
        voffsets += [l2, o2+valuestart]
    offsets = koffsets + voffsets
    output = struct.pack("Iiiiiii",
                         0x950412deL,       # Magic
                         0,                 # Version
                         len(keys),         # # of entries
                         7*4,               # start of key index
                         7*4+len(keys)*8,   # start of value index
                         0, 0)              # size and offset of hash table
    output += array.array("i", offsets).tostring()
    output += ids
    output += strs
    return output


def make (filename, outfile):
    ID = 1
    STR = 2
    global MESSAGES
    MESSAGES = {}

    # Compute .mo name from .po name and arguments
    if filename.endswith('.po'):
        infile = filename
    else:
        infile = filename + '.po'
    if outfile is None:
        outfile = os.path.splitext(infile)[0] + '.mo'

    try:
        lines = open(infile).readlines()
    except IOError, msg:
        print >> sys.stderr, msg
        sys.exit(1)

    section = None
    fuzzy = 0

    # Parse the catalog
    msgid = msgstr = ''
    lno = 0
    for l in lines:
        lno += 1
        # If we get a comment line after a msgstr, this is a new entry
        if l[0] == '#' and section == STR:
            add(msgid, msgstr, fuzzy)
            section = None
            fuzzy = 0
        # Record a fuzzy mark
        if l[:2] == '#,' and (l.find('fuzzy') >= 0):
            fuzzy = 1
        # Skip comments
        if l[0] == '#':
            continue
        # Start of msgid_plural section, separate from singular form with \0
        if l.startswith('msgid_plural'):
            msgid += '\0'
            l = l[12:]
        # Now we are in a msgid section, output previous section
        elif l.startswith('msgid'):
            if section == STR:
                add(msgid, msgstr, fuzzy)
            section = ID
            l = l[5:]
            msgid = msgstr = ''
        # Now we are in a msgstr section
        elif l.startswith('msgstr'):
            section = STR
            l = l[6:]
            # Check for plural forms
            if l.startswith('['):
                # Separate plural forms with \0
                if not l.startswith('[0]'):
                    msgstr += '\0'
                # Ignore the index - must come in sequence
                l = l[l.index(']') + 1:]
        # Skip empty lines
        l = l.strip()
        if not l:
            continue
        # XXX: Does this always follow Python escape semantics?
        l = eval(l)
        if section == ID:
            msgid += l
        elif section == STR:
            msgstr += l
        else:
            print >> sys.stderr, 'Syntax error on %s:%d' % (infile, lno), \
                  'before:'
            print >> sys.stderr, l
            sys.exit(1)
    # Add last entry
    if section == STR:
        add(msgid, msgstr, fuzzy)

    # Compute output
    output = generate()

    try:
        open(outfile,"wb").write(output)
    except IOError,msg:
        print >> sys.stderr, msg


def main ():
    try:
        opts, args = getopt.getopt(sys.argv[1:], 'hVo:',
                                   ['help', 'version', 'output-file='])
    except getopt.error, msg:
        usage(1, msg)

    outfile = None
    # parse options
    for opt, arg in opts:
        if opt in ('-h', '--help'):
            usage(0)
        elif opt in ('-V', '--version'):
            print >> sys.stderr, "msgfmt.py", __version__
            sys.exit(0)
        elif opt in ('-o', '--output-file'):
            outfile = arg
    # do it
    if not args:
        print >> sys.stderr, 'No input file given'
        print >> sys.stderr, "Try `msgfmt --help' for more information."
        return

    for filename in args:
        make(filename, outfile)


if __name__ == '__main__':
    main()
# -*- coding: iso-8859-1 -*-
# Written by Martin v. Lwis <loewis@informatik.hu-berlin.de>
# Plural forms support added by alexander smishlajev <alex@tycobka.lv>
"""
Generate binary message catalog from textual translation description.

This program converts a textual Uniforum-style message catalog (.po file) into
a binary GNU catalog (.mo file).  This is essentially the same function as the
GNU msgfmt program, however, it is a simpler implementation.

Usage: msgfmt.py [OPTIONS] filename.po

Options:
    -o file
    --output-file=file
        Specify the output file to write to.  If omitted, output will go to a
        file named filename.mo (based off the input file name).

    -h
    --help
        Print this message and exit.

    -V
    --version
        Display version information and exit.
"""

import sys
import os
import getopt
import struct
import array

__version__ = "1.1"

MESSAGES = {}


def usage (ecode, msg=''):
    """
    Print usage and msg and exit with given code.
    """
    print >> sys.stderr, __doc__
    if msg:
        print >> sys.stderr, msg
    sys.exit(ecode)


def add (msgid, transtr, fuzzy):
    """
    Add a non-fuzzy translation to the dictionary.
    """
    global MESSAGES
    if not fuzzy and transtr and not transtr.startswith('\0'):
        MESSAGES[msgid] = transtr


def generate ():
    """
    Return the generated output.
    """
    global MESSAGES
    keys = MESSAGES.keys()
    # the keys are sorted in the .mo file
    keys.sort()
    offsets = []
    ids = strs = ''
    for _id in keys:
        # For each string, we need size and file offset.  Each string is NUL
        # terminated; the NUL does not count into the size.
        offsets.append((len(ids), len(_id), len(strs), len(MESSAGES[_id])))
        ids += _id + '\0'
        strs += MESSAGES[_id] + '\0'
    output = ''
    # The header is 7 32-bit unsigned integers.  We don't use hash tables, so
    # the keys start right after the index tables.
    # translated string.
    keystart = 7*4+16*len(keys)
    # and the values start after the keys
    valuestart = keystart + len(ids)
    koffsets = []
    voffsets = []
    # The string table first has the list of keys, then the list of values.
    # Each entry has first the size of the string, then the file offset.
    for o1, l1, o2, l2 in offsets:
        koffsets += [l1, o1+keystart]
        voffsets += [l2, o2+valuestart]
    offsets = koffsets + voffsets
    output = struct.pack("Iiiiiii",
                         0x950412deL,       # Magic
                         0,                 # Version
                         len(keys),         # # of entries
                         7*4,               # start of key index
                         7*4+len(keys)*8,   # start of value index
                         0, 0)              # size and offset of hash table
    output += array.array("i", offsets).tostring()
    output += ids
    output += strs
    return output


def make (filename, outfile):
    ID = 1
    STR = 2
    global MESSAGES
    MESSAGES = {}

    # Compute .mo name from .po name and arguments
    if filename.endswith('.po'):
        infile = filename
    else:
        infile = filename + '.po'
    if outfile is None:
        outfile = os.path.splitext(infile)[0] + '.mo'

    try:
        lines = open(infile).readlines()
    except IOError, msg:
        print >> sys.stderr, msg
        sys.exit(1)

    section = None
    fuzzy = 0

    # Parse the catalog
    msgid = msgstr = ''
    lno = 0
    for l in lines:
        lno += 1
        # If we get a comment line after a msgstr, this is a new entry
        if l[0] == '#' and section == STR:
            add(msgid, msgstr, fuzzy)
            section = None
            fuzzy = 0
        # Record a fuzzy mark
        if l[:2] == '#,' and (l.find('fuzzy') >= 0):
            fuzzy = 1
        # Skip comments
        if l[0] == '#':
            continue
        # Start of msgid_plural section, separate from singular form with \0
        if l.startswith('msgid_plural'):
            msgid += '\0'
            l = l[12:]
        # Now we are in a msgid section, output previous section
        elif l.startswith('msgid'):
            if section == STR:
                add(msgid, msgstr, fuzzy)
            section = ID
            l = l[5:]
            msgid = msgstr = ''
        # Now we are in a msgstr section
        elif l.startswith('msgstr'):
            section = STR
            l = l[6:]
            # Check for plural forms
            if l.startswith('['):
                # Separate plural forms with \0
                if not l.startswith('[0]'):
                    msgstr += '\0'
                # Ignore the index - must come in sequence
                l = l[l.index(']') + 1:]
        # Skip empty lines
        l = l.strip()
        if not l:
            continue
        # XXX: Does this always follow Python escape semantics?
        l = eval(l)
        if section == ID:
            msgid += l
        elif section == STR:
            msgstr += l
        else:
            print >> sys.stderr, 'Syntax error on %s:%d' % (infile, lno), \
                  'before:'
            print >> sys.stderr, l
            sys.exit(1)
    # Add last entry
    if section == STR:
        add(msgid, msgstr, fuzzy)

    # Compute output
    output = generate()

    try:
        open(outfile,"wb").write(output)
    except IOError,msg:
        print >> sys.stderr, msg


def main ():
    try:
        opts, args = getopt.getopt(sys.argv[1:], 'hVo:',
                                   ['help', 'version', 'output-file='])
    except getopt.error, msg:
        usage(1, msg)

    outfile = None
    # parse options
    for opt, arg in opts:
        if opt in ('-h', '--help'):
            usage(0)
        elif opt in ('-V', '--version'):
            print >> sys.stderr, "msgfmt.py", __version__
            sys.exit(0)
        elif opt in ('-o', '--output-file'):
            outfile = arg
    # do it
    if not args:
        print >> sys.stderr, 'No input file given'
        print >> sys.stderr, "Try `msgfmt --help' for more information."
        return

    for filename in args:
        make(filename, outfile)


if __name__ == '__main__':
    main()