summaryrefslogtreecommitdiff
path: root/solenv/bin/polib.py
blob: 092e7dfdb8b3f11d59adf71966f19b8084d86266 (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
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
# -* coding: utf-8 -*-
#
# License: MIT (see LICENSE file provided)
# vim: set expandtab tabstop=4 shiftwidth=4 softtabstop=4:
8
"""
**polib** allows you to manipulate, create, modify gettext files (pot, po and
mo files).  You can load existing files, iterate through it's entries, add,
modify entries, comments or metadata, etc. or create new po files from scratch.

**polib** provides a simple and pythonic API via the :func:`~polib.pofile` and
:func:`~polib.mofile` convenience functions.
"""

__author__ = 'David Jean Louis <izimobil@gmail.com>'
__version__ = '1.0.8'
__all__ = ['pofile', 'POFile', 'POEntry', 'mofile', 'MOFile', 'MOEntry',
           'default_encoding', 'escape', 'unescape', 'detect_encoding', ]

import array
import codecs
import os
import re
import struct
import sys
import textwrap
import binascii

try:
    import io
except ImportError:
    # replacement of io.open() for python < 2.6
    # we use codecs instead
    class io(object):
        @staticmethod
        def open(fpath, mode='r', encoding=None):
            return codecs.open(fpath, mode, encoding)


# the default encoding to use when encoding cannot be detected
default_encoding = 'utf-8'

# python 2/3 compatibility helpers {{{


if sys.version_info[:2] < (3, 0):
    PY3 = False
    text_type = unicode

    def b(s):
        return s

    def u(s):
        return unicode(s, "unicode_escape")

else:
    PY3 = True
    text_type = str

    def b(s):
        return s.encode("latin-1")

    def u(s):
        return s
# }}}
# _pofile_or_mofile {{{


def _pofile_or_mofile(f, type, **kwargs):
    """
    Internal function used by :func:`polib.pofile` and :func:`polib.mofile` to
    honor the DRY concept.
    """
    # get the file encoding
    enc = kwargs.get('encoding')
    if enc is None:
        enc = detect_encoding(f, type == 'mofile')

    # parse the file
    kls = type == 'pofile' and _POFileParser or _MOFileParser
    parser = kls(
        f,
        encoding=enc,
        check_for_duplicates=kwargs.get('check_for_duplicates', False),
        klass=kwargs.get('klass')
    )
    instance = parser.parse()
    instance.wrapwidth = kwargs.get('wrapwidth', 78)
    return instance
# }}}
# _is_file {{{


def _is_file(filename_or_contents):
    """
    Safely returns the value of os.path.exists(filename_or_contents).

    Arguments:

    ``filename_or_contents``
        either a filename, or a string holding the contents of some file.
        In the latter case, this function will always return False.
    """
    try:
        return os.path.exists(filename_or_contents)
    except (ValueError, UnicodeEncodeError):
        return False
# }}}
# function pofile() {{{


def pofile(pofile, **kwargs):
    """
    Convenience function that parses the po or pot file ``pofile`` and returns
    a :class:`~polib.POFile` instance.

    Arguments:

    ``pofile``
        string, full or relative path to the po/pot file or its content (data).

    ``wrapwidth``
        integer, the wrap width, only useful when the ``-w`` option was passed
        to xgettext (optional, default: ``78``).

    ``encoding``
        string, the encoding to use (e.g. "utf-8") (default: ``None``, the
        encoding will be auto-detected).

    ``check_for_duplicates``
        whether to check for duplicate entries when adding entries to the
        file (optional, default: ``False``).

    ``klass``
        class which is used to instantiate the return value (optional,
        default: ``None``, the return value with be a :class:`~polib.POFile`
        instance).
    """
    return _pofile_or_mofile(pofile, 'pofile', **kwargs)
# }}}
# function mofile() {{{


def mofile(mofile, **kwargs):
    """
    Convenience function that parses the mo file ``mofile`` and returns a
    :class:`~polib.MOFile` instance.

    Arguments:

    ``mofile``
        string, full or relative path to the mo file or its content (data).

    ``wrapwidth``
        integer, the wrap width, only useful when the ``-w`` option was passed
        to xgettext to generate the po file that was used to format the mo file
        (optional, default: ``78``).

    ``encoding``
        string, the encoding to use (e.g. "utf-8") (default: ``None``, the
        encoding will be auto-detected).

    ``check_for_duplicates``
        whether to check for duplicate entries when adding entries to the
        file (optional, default: ``False``).

    ``klass``
        class which is used to instantiate the return value (optional,
        default: ``None``, the return value with be a :class:`~polib.POFile`
        instance).
    """
    return _pofile_or_mofile(mofile, 'mofile', **kwargs)
# }}}
# function detect_encoding() {{{


def detect_encoding(file, binary_mode=False):
    """
    Try to detect the encoding used by the ``file``. The ``file`` argument can
    be a PO or MO file path or a string containing the contents of the file.
    If the encoding cannot be detected, the function will return the value of
    ``default_encoding``.

    Arguments:

    ``file``
        string, full or relative path to the po/mo file or its content.

    ``binary_mode``
        boolean, set this to True if ``file`` is a mo file.
    """
    PATTERN = r'"?Content-Type:.+? charset=([\w_\-:\.]+)'
    rxt = re.compile(u(PATTERN))
    rxb = re.compile(b(PATTERN))

    def charset_exists(charset):
        """Check whether ``charset`` is valid or not."""
        try:
            codecs.lookup(charset)
        except LookupError:
            return False
        return True

    if not _is_file(file):
        match = rxt.search(file)
        if match:
            enc = match.group(1).strip()
            if charset_exists(enc):
                return enc
    else:
        # For PY3, always treat as binary
        if binary_mode or PY3:
            mode = 'rb'
            rx = rxb
        else:
            mode = 'r'
            rx = rxt
        f = open(file, mode)
        for l in f.readlines():
            match = rx.search(l)
            if match:
                f.close()
                enc = match.group(1).strip()
                if not isinstance(enc, text_type):
                    enc = enc.decode('utf-8')
                if charset_exists(enc):
                    return enc
        f.close()
    return default_encoding
# }}}
# function escape() {{{


def escape(st):
    """
    Escapes the characters ``\\\\``, ``\\t``, ``\\n``, ``\\r`` and ``"`` in
    the given string ``st`` and returns it.
    """
    return st.replace('\\', r'\\')\
             .replace('\t', r'\t')\
             .replace('\r', r'\r')\
             .replace('\n', r'\n')\
             .replace('\"', r'\"')
# }}}
# function unescape() {{{


def unescape(st):
    """
    Unescapes the characters ``\\\\``, ``\\t``, ``\\n``, ``\\r`` and ``"`` in
    the given string ``st`` and returns it.
    """
    def unescape_repl(m):
        m = m.group(1)
        if m == 'n':
            return '\n'
        if m == 't':
            return '\t'
        if m == 'r':
            return '\r'
        if m == '\\':
            return '\\'
        return m  # handles escaped double quote
    return re.sub(r'\\(\\|n|t|r|")', unescape_repl, st)
# }}}
# function natural_sort() {{{


def natural_sort(lst):
    """
    Sort naturally the given list.
    Credits: http://stackoverflow.com/a/4836734
    """
    convert = lambda text: int(text) if text.isdigit() else text.lower() 
    alphanum_key = lambda key: [ convert(c) for c in re.split('([0-9]+)', key) ] 
    return sorted(lst, key = alphanum_key)
# }}}
# class _BaseFile {{{


class _BaseFile(list):
    """
    Common base class for the :class:`~polib.POFile` and :class:`~polib.MOFile`
    classes. This class should **not** be instantiated directly.
    """

    def __init__(self, *args, **kwargs):
        """
        Constructor, accepts the following keyword arguments:

        ``pofile``
            string, the path to the po or mo file, or its content as a string.

        ``wrapwidth``
            integer, the wrap width, only useful when the ``-w`` option was
            passed to xgettext (optional, default: ``78``).

        ``encoding``
            string, the encoding to use, defaults to ``default_encoding``
            global variable (optional).

        ``check_for_duplicates``
            whether to check for duplicate entries when adding entries to the
            file, (optional, default: ``False``).
        """
        list.__init__(self)
        # the opened file handle
        pofile = kwargs.get('pofile', None)
        if pofile and _is_file(pofile):
            self.fpath = pofile
        else:
            self.fpath = kwargs.get('fpath')
        # the width at which lines should be wrapped
        self.wrapwidth = kwargs.get('wrapwidth', 78)
        # the file encoding
        self.encoding = kwargs.get('encoding', default_encoding)
        # whether to check for duplicate entries or not
        self.check_for_duplicates = kwargs.get('check_for_duplicates', False)
        # header
        self.header = ''
        # both po and mo files have metadata
        self.metadata = {}
        self.metadata_is_fuzzy = 0

    def __unicode__(self):
        """
        Returns the unicode representation of the file.
        """
        ret = []
        entries = [self.metadata_as_entry()] + \
                  [e for e in self if not e.obsolete]
        for entry in entries:
            ret.append(entry.__unicode__(self.wrapwidth))
        for entry in self.obsolete_entries():
            ret.append(entry.__unicode__(self.wrapwidth))
        ret = u('\n').join(ret)

        assert isinstance(ret, text_type)
        #if type(ret) != text_type:
        #    return unicode(ret, self.encoding)
        return ret

    if PY3:
        def __str__(self):
            return self.__unicode__()
    else:
        def __str__(self):
            """
            Returns the string representation of the file.
            """
            return unicode(self).encode(self.encoding)

    def __contains__(self, entry):
        """
        Overridden ``list`` method to implement the membership test (in and
        not in).
        The method considers that an entry is in the file if it finds an entry
        that has the same msgid (the test is **case sensitive**) and the same
        msgctxt (or none for both entries).

        Argument:

        ``entry``
            an instance of :class:`~polib._BaseEntry`.
        """
        return self.find(entry.msgid, by='msgid', msgctxt=entry.msgctxt) \
            is not None

    def __eq__(self, other):
        return str(self) == str(other)

    def append(self, entry):
        """
        Overridden method to check for duplicates entries, if a user tries to
        add an entry that is already in the file, the method will raise a
        ``ValueError`` exception.

        Argument:

        ``entry``
            an instance of :class:`~polib._BaseEntry`.
        """
        # check_for_duplicates may not be defined (yet) when unpickling.
        # But if pickling, we never want to check for duplicates anyway.
        if getattr(self, 'check_for_duplicates', False) and entry in self:
            raise ValueError('Entry "%s" already exists' % entry.msgid)
        super(_BaseFile, self).append(entry)

    def insert(self, index, entry):
        """
        Overridden method to check for duplicates entries, if a user tries to
        add an entry that is already in the file, the method will raise a
        ``ValueError`` exception.

        Arguments:

        ``index``
            index at which the entry should be inserted.

        ``entry``
            an instance of :class:`~polib._BaseEntry`.
        """
        if self.check_for_duplicates and entry in self:
            raise ValueError('Entry "%s" already exists' % entry.msgid)
        super(_BaseFile, self).insert(index, entry)

    def metadata_as_entry(self):
        """
        Returns the file metadata as a :class:`~polib.POFile` instance.
        """
        e = POEntry(msgid='')
        mdata = self.ordered_metadata()
        if mdata:
            strs = []
            for name, value in mdata:
                # Strip whitespace off each line in a multi-line entry
                strs.append('%s: %s' % (name, value))
            e.msgstr = '\n'.join(strs) + '\n'
        if self.metadata_is_fuzzy:
            e.flags.append('fuzzy')
        return e

    def save(self, fpath=None, repr_method='__unicode__'):
        """
        Saves the po file to ``fpath``.
        If it is an existing file and no ``fpath`` is provided, then the
        existing file is rewritten with the modified data.

        Keyword arguments:

        ``fpath``
            string, full or relative path to the file.

        ``repr_method``
            string, the method to use for output.
        """
        if self.fpath is None and fpath is None:
            raise IOError('You must provide a file path to save() method')
        contents = getattr(self, repr_method)()
        if fpath is None:
            fpath = self.fpath
        if repr_method == 'to_binary':
            fhandle = open(fpath, 'wb')
        else:
            fhandle = io.open(fpath, 'w', encoding=self.encoding)
            if not isinstance(contents, text_type):
                contents = contents.decode(self.encoding)
        fhandle.write(contents)
        fhandle.close()
        # set the file path if not set
        if self.fpath is None and fpath:
            self.fpath = fpath

    def find(self, st, by='msgid', include_obsolete_entries=False,
             msgctxt=False):
        """
        Find the entry which msgid (or property identified by the ``by``
        argument) matches the string ``st``.

        Keyword arguments:

        ``st``
            string, the string to search for.

        ``by``
            string, the property to use for comparison (default: ``msgid``).

        ``include_obsolete_entries``
            boolean, whether to also search in entries that are obsolete.

        ``msgctxt``
            string, allows specifying a specific message context for the
            search.
        """
        if include_obsolete_entries:
            entries = self[:]
        else:
            entries = [e for e in self if not e.obsolete]
        for e in entries:
            if getattr(e, by) == st:
                if msgctxt is not False and e.msgctxt != msgctxt:
                    continue
                return e
        return None

    def ordered_metadata(self):
        """
        Convenience method that returns an ordered version of the metadata
        dictionary. The return value is list of tuples (metadata name,
        metadata_value).
        """
        # copy the dict first
        metadata = self.metadata.copy()
        data_order = [
            'Project-Id-Version',
            'Report-Msgid-Bugs-To',
            'POT-Creation-Date',
            'PO-Revision-Date',
            'Last-Translator',
            'Language-Team',
            'Language',
            'MIME-Version',
            'Content-Type',
            'Content-Transfer-Encoding',
            'Plural-Forms'
        ]
        ordered_data = []
        for data in data_order:
            try:
                value = metadata.pop(data)
                ordered_data.append((data, value))
            except KeyError:
                pass
        # the rest of the metadata will be alphabetically ordered since there
        # are no specs for this AFAIK
        for data in natural_sort(metadata.keys()):
            value = metadata[data]
            ordered_data.append((data, value))
        return ordered_data

    def to_binary(self):
        """
        Return the binary representation of the file.
        """
        offsets = []
        entries = self.translated_entries()

        # the keys are sorted in the .mo file
        def cmp(_self, other):
            # msgfmt compares entries with msgctxt if it exists
            self_msgid = _self.msgctxt and _self.msgctxt or _self.msgid
            other_msgid = other.msgctxt and other.msgctxt or other.msgid
            if self_msgid > other_msgid:
                return 1
            elif self_msgid < other_msgid:
                return -1
            else:
                return 0
        # add metadata entry
        entries.sort(key=lambda o: o.msgctxt or o.msgid)
        mentry = self.metadata_as_entry()
        #mentry.msgstr = mentry.msgstr.replace('\\n', '').lstrip()
        entries = [mentry] + entries
        entries_len = len(entries)
        ids, strs = b(''), b('')
        for e in entries:
            # For each string, we need size and file offset.  Each string is
            # NUL terminated; the NUL does not count into the size.
            msgid = b('')
            if e.msgctxt:
                # Contexts are stored by storing the concatenation of the
                # context, a <EOT> byte, and the original string
                msgid = self._encode(e.msgctxt + '\4')
            if e.msgid_plural:
                msgstr = []
                for index in sorted(e.msgstr_plural.keys()):
                    msgstr.append(e.msgstr_plural[index])
                msgid += self._encode(e.msgid + '\0' + e.msgid_plural)
                msgstr = self._encode('\0'.join(msgstr))
            else:
                msgid += self._encode(e.msgid)
                msgstr = self._encode(e.msgstr)
            offsets.append((len(ids), len(msgid), len(strs), len(msgstr)))
            ids += msgid + b('\0')
            strs += msgstr + b('\0')

        # The header is 7 32-bit unsigned integers.
        keystart = 7 * 4 + 16 * entries_len
        # 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",
            # Magic number
            MOFile.MAGIC,
            # Version
            0,
            # number of entries
            entries_len,
            # start of key index
            7 * 4,
            # start of value index
            7 * 4 + entries_len * 8,
            # size and offset of hash table, we don't use hash tables
            0, keystart

        )
        if PY3 and sys.version_info.minor > 1:  # python 3.2 or superior
            output += array.array("i", offsets).tobytes()
        else:
            output += array.array("i", offsets).tostring()
        output += ids
        output += strs
        return output

    def _encode(self, mixed):
        """
        Encodes the given ``mixed`` argument with the file encoding if and
        only if it's a unicode string and returns the encoded string.
        """
        if isinstance(mixed, text_type):
            mixed = mixed.encode(self.encoding)
        return mixed
# }}}
# class POFile {{{


class POFile(_BaseFile):
    """
    Po (or Pot) file reader/writer.
    This class inherits the :class:`~polib._BaseFile` class and, by extension,
    the python ``list`` type.
    """

    def __unicode__(self):
        """
        Returns the unicode representation of the po file.
        """
        ret, headers = '', self.header.split('\n')
        for header in headers:
            if not len(header):
                ret += "#\n"
            elif header[:1] in [',', ':']:
                ret += '#%s\n' % header
            else:
                ret += '# %s\n' % header

        if not isinstance(ret, text_type):
            ret = ret.decode(self.encoding)

        return ret + _BaseFile.__unicode__(self)

    def save_as_mofile(self, fpath):
        """
        Saves the binary representation of the file to given ``fpath``.

        Keyword argument:

        ``fpath``
            string, full or relative path to the mo file.
        """
        _BaseFile.save(self, fpath, 'to_binary')

    def percent_translated(self):
        """
        Convenience method that returns the percentage of translated
        messages.
        """
        total = len([e for e in self if not e.obsolete])
        if total == 0:
            return 100
        translated = len(self.translated_entries())
        return int(translated * 100 / float(total))

    def translated_entries(self):
        """
        Convenience method that returns the list of translated entries.
        """
        return [e for e in self if e.translated()]

    def untranslated_entries(self):
        """
        Convenience method that returns the list of untranslated entries.
        """
        return [e for e in self if not e.translated() and not e.obsolete
                and not 'fuzzy' in e.flags]

    def fuzzy_entries(self):
        """
        Convenience method that returns the list of fuzzy entries.
        """
        return [e for e in self if 'fuzzy' in e.flags]

    def obsolete_entries(self):
        """
        Convenience method that returns the list of obsolete entries.
        """
        return [e for e in self if e.obsolete]

    def merge(self, refpot):
        """
        Convenience method that merges the current pofile with the pot file
        provided. It behaves exactly as the gettext msgmerge utility:

        * comments of this file will be preserved, but extracted comments and
          occurrences will be discarded;
        * any translations or comments in the file will be discarded, however,
          dot comments and file positions will be preserved;
        * the fuzzy flags are preserved.

        Keyword argument:

        ``refpot``
            object POFile, the reference catalog.
        """
        # Store entries in dict/set for faster access
        self_entries = dict((entry.msgid, entry) for entry in self)
        refpot_msgids = set(entry.msgid for entry in refpot)
        # Merge entries that are in the refpot
        for entry in refpot:
            e = self_entries.get(entry.msgid)
            if e is None:
                e = POEntry()
                self.append(e)
            e.merge(entry)
        # ok, now we must "obsolete" entries that are not in the refpot anymore
        for entry in self:
            if entry.msgid not in refpot_msgids:
                entry.obsolete = True
# }}}
# class MOFile {{{


class MOFile(_BaseFile):
    """
    Mo file reader/writer.
    This class inherits the :class:`~polib._BaseFile` class and, by
    extension, the python ``list`` type.
    """
    MAGIC = 0x950412de
    MAGIC_SWAPPED = 0xde120495

    def __init__(self, *args, **kwargs):
        """
        Constructor, accepts all keywords arguments accepted by
        :class:`~polib._BaseFile` class.
        """
        _BaseFile.__init__(self, *args, **kwargs)
        self.magic_number = None
        self.version = 0

    def save_as_pofile(self, fpath):
        """
        Saves the mofile as a pofile to ``fpath``.

        Keyword argument:

        ``fpath``
            string, full or relative path to the file.
        """
        _BaseFile.save(self, fpath)

    def save(self, fpath=None):
        """
        Saves the mofile to ``fpath``.

        Keyword argument:

        ``fpath``
            string, full or relative path to the file.
        """
        _BaseFile.save(self, fpath, 'to_binary')

    def percent_translated(self):
        """
        Convenience method to keep the same interface with POFile instances.
        """
        return 100

    def translated_entries(self):
        """
        Convenience method to keep the same interface with POFile instances.
        """
        return self

    def untranslated_entries(self):
        """
        Convenience method to keep the same interface with POFile instances.
        """
        return []

    def fuzzy_entries(self):
        """
        Convenience method to keep the same interface with POFile instances.
        """
        return []

    def obsolete_entries(self):
        """
        Convenience method to keep the same interface with POFile instances.
        """
        return []
# }}}
# class _BaseEntry {{{


class _BaseEntry(object):
    """
    Base class for :class:`~polib.POEntry` and :class:`~polib.MOEntry` classes.
    This class should **not** be instantiated directly.
    """

    def __init__(self, *args, **kwargs):
        """
        Constructor, accepts the following keyword arguments:

        ``msgid``
            string, the entry msgid.

        ``msgstr``
            string, the entry msgstr.

        ``msgid_plural``
            string, the entry msgid_plural.

        ``msgstr_plural``
            list, the entry msgstr_plural lines.

        ``msgctxt``
            string, the entry context (msgctxt).

        ``obsolete``
            bool, whether the entry is "obsolete" or not.

        ``encoding``
            string, the encoding to use, defaults to ``default_encoding``
            global variable (optional).
        """
        self.msgid = kwargs.get('msgid', '')
        self.msgstr = kwargs.get('msgstr', '')
        self.msgid_plural = kwargs.get('msgid_plural', '')
        self.msgstr_plural = kwargs.get('msgstr_plural', {})
        self.msgctxt = kwargs.get('msgctxt', None)
        self.obsolete = kwargs.get('obsolete', False)
        self.encoding = kwargs.get('encoding', default_encoding)

    def __unicode__(self, wrapwidth=78):
        """
        Returns the unicode representation of the entry.
        """
        if self.obsolete:
            delflag = '#~ '
        else:
            delflag = ''
        ret = []
        # write the msgctxt if any
        if self.msgctxt is not None:
            ret += self._str_field("msgctxt", delflag, "", self.msgctxt,
                                   wrapwidth)
        # write the msgid
        ret += self._str_field("msgid", delflag, "", self.msgid, wrapwidth)
        # write the msgid_plural if any
        if self.msgid_plural:
            ret += self._str_field("msgid_plural", delflag, "",
                                   self.msgid_plural, wrapwidth)
        if self.msgstr_plural:
            # write the msgstr_plural if any
            msgstrs = self.msgstr_plural
            keys = list(msgstrs)
            keys.sort()
            for index in keys:
                msgstr = msgstrs[index]
                plural_index = '[%s]' % index
                ret += self._str_field("msgstr", delflag, plural_index, msgstr,
                                       wrapwidth)
        else:
            # otherwise write the msgstr
            ret += self._str_field("msgstr", delflag, "", self.msgstr,
                                   wrapwidth)
        ret.append('')
        usedirect = True
        if not PY3 and type(ret[0] != unicode):
            try:
                usedirect = False
                ret = u('\n').join(x.decode('utf-8') for x in ret)
            except:
                usedirect = True
        if usedirect:
            ret = u('\n').join(ret)
        return ret

    if PY3:
        def __str__(self):
            return self.__unicode__()
    else:
        def __str__(self):
            """
            Returns the string representation of the entry.
            """
            return unicode(self).encode(self.encoding)

    def __eq__(self, other):
        return str(self) == str(other)

    def _str_field(self, fieldname, delflag, plural_index, field,
                   wrapwidth=78):
        lines = field.splitlines(True)
        if len(lines) > 1:
            lines = [''] + lines  # start with initial empty line
        else:
            escaped_field = escape(field)
            specialchars_count = 0
            for c in ['\\', '\n', '\r', '\t', '"']:
                specialchars_count += field.count(c)
            # comparison must take into account fieldname length + one space
            # + 2 quotes (eg. msgid "<string>")
            flength = len(fieldname) + 3
            if plural_index:
                flength += len(plural_index)
            real_wrapwidth = wrapwidth - flength + specialchars_count
            if wrapwidth > 0 and len(field) > real_wrapwidth:
                # Wrap the line but take field name into account
                lines = [''] + [unescape(item) for item in wrap(
                    escaped_field,
                    wrapwidth - 2,  # 2 for quotes ""
                    drop_whitespace=False,
                    break_long_words=False
                )]
            else:
                lines = [field]
        if fieldname.startswith('previous_'):
            # quick and dirty trick to get the real field name
            fieldname = fieldname[9:]

        ret = ['%s%s%s "%s"' % (delflag, fieldname, plural_index,
                                escape(lines.pop(0)))]
        for line in lines:
            ret.append('%s"%s"' % (delflag, escape(line)))
        return ret
# }}}
# class POEntry {{{


class POEntry(_BaseEntry):
    """
    Represents a po file entry.
    """

    def __init__(self, *args, **kwargs):
        """
        Constructor, accepts the following keyword arguments:

        ``comment``
            string, the entry comment.

        ``tcomment``
            string, the entry translator comment.

        ``occurrences``
            list, the entry occurrences.

        ``flags``
            list, the entry flags.

        ``previous_msgctxt``
            string, the entry previous context.

        ``previous_msgid``
            string, the entry previous msgid.

        ``previous_msgid_plural``
            string, the entry previous msgid_plural.

        ``linenum``
            integer, the line number of the entry
        """
        _BaseEntry.__init__(self, *args, **kwargs)
        self.comment = kwargs.get('comment', '')
        self.tcomment = kwargs.get('tcomment', '')
        self.occurrences = kwargs.get('occurrences', [])
        self.flags = kwargs.get('flags', [])
        self.previous_msgctxt = kwargs.get('previous_msgctxt', None)
        self.previous_msgid = kwargs.get('previous_msgid', None)
        self.previous_msgid_plural = kwargs.get('previous_msgid_plural', None)
        self.linenum = kwargs.get('linenum', None)

    def __unicode__(self, wrapwidth=0):
        """
        Returns the unicode representation of the entry.
        """
        ret = []
        # comments first, if any (with text wrapping as xgettext does)
        if self.obsolete:
            comments = [('tcomment', '# ')]
        else:
            comments = [('comment', '#. '), ('tcomment', '# ')]
        for c in comments:
            val = getattr(self, c[0])
            if val:
                for comment in val.split('\n'):
                    if wrapwidth > 0 and len(comment) + len(c[1]) > wrapwidth:
                        ret += wrap(
                            comment,
                            wrapwidth,
                            initial_indent=c[1],
                            subsequent_indent=c[1],
                            break_long_words=False
                        )
                    else:
                        ret.append('%s%s' % (c[1], comment))

        # occurrences (with text wrapping as xgettext does)
        if not self.obsolete and self.occurrences:
            filelist = []
            for fpath, lineno in self.occurrences:
                if lineno:
                    filelist.append('%s:%s' % (fpath, lineno))
                else:
                    filelist.append(fpath)
            filestr = ' '.join(filelist)
            if wrapwidth > 0 and len(filestr) + 3 > wrapwidth:
                # textwrap split words that contain hyphen, this is not
                # what we want for filenames, so the dirty hack is to
                # temporally replace hyphens with a char that a file cannot
                # contain, like "*"
                ret += [l.replace('*', '-') for l in wrap(
                    filestr.replace('-', '*'),
                    wrapwidth,
                    initial_indent='#: ',
                    subsequent_indent='#: ',
                    break_long_words=False
                )]
            else:
                ret.append('#: ' + filestr)

        # flags (TODO: wrapping ?)
        if self.flags:
            ret.append('#, %s' % ', '.join(self.flags))

        # previous context and previous msgid/msgid_plural
        fields = ['previous_msgctxt', 'previous_msgid',
                  'previous_msgid_plural']
        if self.obsolete:
            prefix = "#~| "
        else:
            prefix = "#| "
        for f in fields:
            val = getattr(self, f)
            if val:
                ret += self._str_field(f, prefix, "", val, wrapwidth)

        ret.append(_BaseEntry.__unicode__(self, wrapwidth))
        ret = u('\n').join(ret)
        return ret

    def __cmp__(self, other):
        """
        Called by comparison operations if rich comparison is not defined.
        """

        # First: Obsolete test
        if self.obsolete != other.obsolete:
            if self.obsolete:
                return -1
            else:
                return 1
        # Work on a copy to protect original
        occ1 = sorted(self.occurrences[:])
        occ2 = sorted(other.occurrences[:])
        pos = 0
        for entry1 in occ1:
            try:
                entry2 = occ2[pos]
            except IndexError:
                return 1
            pos = pos + 1
            if entry1[0] != entry2[0]:
                if entry1[0] > entry2[0]:
                    return 1
                else:
                    return -1
            if entry1[1] != entry2[1]:
                if entry1[1] > entry2[1]:
                    return 1
                else:
                    return -1
        # Compare msgid_plural if set
        if self.msgid_plural:
            if not other.msgid_plural:
                return 1
            for pos in self.msgid_plural:
                if pos not in other.msgid_plural:
                    return 1
                if self.msgid_plural[pos] > other.msgid_plural[pos]:
                    return 1
                if self.msgid_plural[pos] < other.msgid_plural[pos]:
                    return -1
        # Finally: Compare message ID
        if self.msgid > other.msgid:
            return 1
        elif self.msgid < other.msgid:
            return -1
        return 0

    def __gt__(self, other):
        return self.__cmp__(other) > 0

    def __lt__(self, other):
        return self.__cmp__(other) < 0

    def __ge__(self, other):
        return self.__cmp__(other) >= 0

    def __le__(self, other):
        return self.__cmp__(other) <= 0

    def __eq__(self, other):
        return self.__cmp__(other) == 0

    def __ne__(self, other):
        return self.__cmp__(other) != 0

    def translated(self):
        """
        Returns ``True`` if the entry has been translated or ``False``
        otherwise.
        """
        if self.obsolete or 'fuzzy' in self.flags:
            return False
        if self.msgstr != '':
            return True
        if self.msgstr_plural:
            for pos in self.msgstr_plural:
                if self.msgstr_plural[pos] == '':
                    return False
            return True
        return False

    def merge(self, other):
        """
        Merge the current entry with the given pot entry.
        """
        self.msgid = other.msgid
        self.msgctxt = other.msgctxt
        self.occurrences = other.occurrences
        self.comment = other.comment
        fuzzy = 'fuzzy' in self.flags
        self.flags = other.flags[:]  # clone flags
        if fuzzy:
            self.flags.append('fuzzy')
        self.msgid_plural = other.msgid_plural
        self.obsolete = other.obsolete
        self.previous_msgctxt = other.previous_msgctxt
        self.previous_msgid = other.previous_msgid
        self.previous_msgid_plural = other.previous_msgid_plural
        if other.msgstr_plural:
            for pos in other.msgstr_plural:
                try:
                    # keep existing translation at pos if any
                    self.msgstr_plural[pos]
                except KeyError:
                    self.msgstr_plural[pos] = ''

    def __hash__(self):
        return hash((self.msgid, self.msgstr))
# }}}
# class MOEntry {{{


class MOEntry(_BaseEntry):
    """
    Represents a mo file entry.
    """
    def __init__(self, *args, **kwargs):
        """
        Constructor, accepts the following keyword arguments,
        for consistency with :class:`~polib.POEntry`:

        ``comment``
        ``tcomment``
        ``occurrences``
        ``flags``
        ``previous_msgctxt``
        ``previous_msgid``
        ``previous_msgid_plural``

        Note: even though these keyword arguments are accepted,
        they hold no real meaning in the context of MO files
        and are simply ignored.
        """
        _BaseEntry.__init__(self, *args, **kwargs)
        self.comment = ''
        self.tcomment = ''
        self.occurrences = []
        self.flags = []
        self.previous_msgctxt = None
        self.previous_msgid = None
        self.previous_msgid_plural = None

    def __hash__(self):
        return hash((self.msgid, self.msgstr))

# }}}
# class _POFileParser {{{


class _POFileParser(object):
    """
    A finite state machine to parse efficiently and correctly po
    file format.
    """

    def __init__(self, pofile, *args, **kwargs):
        """
        Constructor.

        Keyword arguments:

        ``pofile``
            string, path to the po file or its content

        ``encoding``
            string, the encoding to use, defaults to ``default_encoding``
            global variable (optional).

        ``check_for_duplicates``
            whether to check for duplicate entries when adding entries to the
            file (optional, default: ``False``).
        """
        enc = kwargs.get('encoding', default_encoding)
        if _is_file(pofile):
            try:
                self.fhandle = io.open(pofile, 'rt', encoding=enc)
            except LookupError:
                enc = default_encoding
                self.fhandle = io.open(pofile, 'rt', encoding=enc)
        else:
            self.fhandle = pofile.splitlines()

        klass = kwargs.get('klass')
        if klass is None:
            klass = POFile
        self.instance = klass(
            pofile=pofile,
            encoding=enc,
            check_for_duplicates=kwargs.get('check_for_duplicates', False)
        )
        self.transitions = {}
        self.current_line = 0
        self.current_entry = POEntry(linenum=self.current_line)
        self.current_state = 'st'
        self.current_token = None
        # two memo flags used in handlers
        self.msgstr_index = 0
        self.entry_obsolete = 0
        # Configure the state machine, by adding transitions.
        # Signification of symbols:
        #     * ST: Beginning of the file (start)
        #     * HE: Header
        #     * TC: a translation comment
        #     * GC: a generated comment
        #     * OC: a file/line occurrence
        #     * FL: a flags line
        #     * CT: a message context
        #     * PC: a previous msgctxt
        #     * PM: a previous msgid
        #     * PP: a previous msgid_plural
        #     * MI: a msgid
        #     * MP: a msgid plural
        #     * MS: a msgstr
        #     * MX: a msgstr plural
        #     * MC: a msgid or msgstr continuation line
        all = ['st', 'he', 'gc', 'oc', 'fl', 'ct', 'pc', 'pm', 'pp', 'tc',
               'ms', 'mp', 'mx', 'mi']

        self.add('tc', ['st', 'he'],                                     'he')
        self.add('tc', ['gc', 'oc', 'fl', 'tc', 'pc', 'pm', 'pp', 'ms',
                        'mp', 'mx', 'mi'],                               'tc')
        self.add('gc', all,                                              'gc')
        self.add('oc', all,                                              'oc')
        self.add('fl', all,                                              'fl')
        self.add('pc', all,                                              'pc')
        self.add('pm', all,                                              'pm')
        self.add('pp', all,                                              'pp')
        self.add('ct', ['st', 'he', 'gc', 'oc', 'fl', 'tc', 'pc', 'pm',
                        'pp', 'ms', 'mx'],                               'ct')
        self.add('mi', ['st', 'he', 'gc', 'oc', 'fl', 'ct', 'tc', 'pc',
                 'pm', 'pp', 'ms', 'mx'],                                'mi')
        self.add('mp', ['tc', 'gc', 'pc', 'pm', 'pp', 'mi'],             'mp')
        self.add('ms', ['mi', 'mp', 'tc'],                               'ms')
        self.add('mx', ['mi', 'mx', 'mp', 'tc'],                         'mx')
        self.add('mc', ['ct', 'mi', 'mp', 'ms', 'mx', 'pm', 'pp', 'pc'], 'mc')

    def parse(self):
        """
        Run the state machine, parse the file line by line and call process()
        with the current matched symbol.
        """

        keywords = {
            'msgctxt': 'ct',
            'msgid': 'mi',
            'msgstr': 'ms',
            'msgid_plural': 'mp',
        }
        prev_keywords = {
            'msgid_plural': 'pp',
            'msgid': 'pm',
            'msgctxt': 'pc',
        }
        tokens = []
        for line in self.fhandle:
            self.current_line += 1
            line = line.strip()
            if line == '':
                continue

            tokens = line.split(None, 2)
            nb_tokens = len(tokens)

            if tokens[0] == '#~|':
                continue

            if tokens[0] == '#~' and nb_tokens > 1:
                line = line[3:].strip()
                tokens = tokens[1:]
                nb_tokens -= 1
                self.entry_obsolete = 1
            else:
                self.entry_obsolete = 0

            # Take care of keywords like
            # msgid, msgid_plural, msgctxt & msgstr.
            if tokens[0] in keywords and nb_tokens > 1:
                line = line[len(tokens[0]):].lstrip()
                if re.search(r'([^\\]|^)"', line[1:-1]):
                    raise IOError('Syntax error in po file %s (line %s): '
                                  'unescaped double quote found' %
                                  (self.instance.fpath, self.current_line))
                self.current_token = line
                self.process(keywords[tokens[0]])
                continue

            self.current_token = line

            if tokens[0] == '#:':
                if nb_tokens <= 1:
                    continue
                # we are on an occurrences line
                self.process('oc')

            elif line[:1] == '"':
                # we are on a continuation line
                if re.search(r'([^\\]|^)"', line[1:-1]):
                    raise IOError('Syntax error in po file %s (line %s): '
                                  'unescaped double quote found' %
                                  (self.instance.fpath, self.current_line))
                self.process('mc')

            elif line[:7] == 'msgstr[':
                # we are on a msgstr plural
                self.process('mx')

            elif tokens[0] == '#,':
                if nb_tokens <= 1:
                    continue
                # we are on a flags line
                self.process('fl')

            elif tokens[0] == '#' or tokens[0].startswith('##'):
                if line == '#':
                    line += ' '
                # we are on a translator comment line
                self.process('tc')

            elif tokens[0] == '#.':
                if nb_tokens <= 1:
                    continue
                # we are on a generated comment line
                self.process('gc')

            elif tokens[0] == '#|':
                if nb_tokens <= 1:
                    raise IOError('Syntax error in po file %s (line %s)' %
                                  (self.instance.fpath, self.current_line))

                # Remove the marker and any whitespace right after that.
                line = line[2:].lstrip()
                self.current_token = line

                if tokens[1].startswith('"'):
                    # Continuation of previous metadata.
                    self.process('mc')
                    continue

                if nb_tokens == 2:
                    # Invalid continuation line.
                    raise IOError('Syntax error in po file %s (line %s): '
                                  'invalid continuation line' %
                                  (self.instance.fpath, self.current_line))

                # we are on a "previous translation" comment line,
                if tokens[1] not in prev_keywords:
                    # Unknown keyword in previous translation comment.
                    raise IOError('Syntax error in po file %s (line %s): '
                                  'unknown keyword %s' %
                                  (self.instance.fpath, self.current_line,
                                   tokens[1]))

                # Remove the keyword and any whitespace
                # between it and the starting quote.
                line = line[len(tokens[1]):].lstrip()
                self.current_token = line
                self.process(prev_keywords[tokens[1]])

            else:
                raise IOError('Syntax error in po file %s (line %s)' %
                              (self.instance.fpath, self.current_line))

        if self.current_entry and len(tokens) > 0 and \
           not tokens[0].startswith('#'):
            # since entries are added when another entry is found, we must add
            # the last entry here (only if there are lines). Trailing comments
            # are ignored
            self.instance.append(self.current_entry)

        # before returning the instance, check if there's metadata and if
        # so extract it in a dict
        metadataentry = self.instance.find('')
        if metadataentry:  # metadata found
            # remove the entry
            self.instance.remove(metadataentry)
            self.instance.metadata_is_fuzzy = metadataentry.flags
            key = None
            for msg in metadataentry.msgstr.splitlines():
                try:
                    key, val = msg.split(':', 1)
                    self.instance.metadata[key] = val.strip()
                except (ValueError, KeyError):
                    if key is not None:
                        self.instance.metadata[key] += '\n' + msg.strip()
        # close opened file
        if not isinstance(self.fhandle, list):  # must be file
            self.fhandle.close()
        return self.instance

    def add(self, symbol, states, next_state):
        """
        Add a transition to the state machine.

        Keywords arguments:

        ``symbol``
            string, the matched token (two chars symbol).

        ``states``
            list, a list of states (two chars symbols).

        ``next_state``
            the next state the fsm will have after the action.
        """
        for state in states:
            action = getattr(self, 'handle_%s' % next_state)
            self.transitions[(symbol, state)] = (action, next_state)

    def process(self, symbol):
        """
        Process the transition corresponding to the current state and the
        symbol provided.

        Keywords arguments:

        ``symbol``
            string, the matched token (two chars symbol).

        ``linenum``
            integer, the current line number of the parsed file.
        """
        try:
            (action, state) = self.transitions[(symbol, self.current_state)]
            if action():
                self.current_state = state
        except Exception:
            raise IOError('Syntax error in po file (line %s)' %
                          self.current_line)

    # state handlers

    def handle_he(self):
        """Handle a header comment."""
        if self.instance.header != '':
            self.instance.header += '\n'
        self.instance.header += self.current_token[2:]
        return 1

    def handle_tc(self):
        """Handle a translator comment."""
        if self.current_state in ['mc', 'ms', 'mx']:
            self.instance.append(self.current_entry)
            self.current_entry = POEntry(linenum=self.current_line)
        if self.current_entry.tcomment != '':
            self.current_entry.tcomment += '\n'
        tcomment = self.current_token.lstrip('#')
        if tcomment.startswith(' '):
            tcomment = tcomment[1:]
        self.current_entry.tcomment += tcomment
        return True

    def handle_gc(self):
        """Handle a generated comment."""
        if self.current_state in ['mc', 'ms', 'mx']:
            self.instance.append(self.current_entry)
            self.current_entry = POEntry(linenum=self.current_line)
        if self.current_entry.comment != '':
            self.current_entry.comment += '\n'
        self.current_entry.comment += self.current_token[3:]
        return True

    def handle_oc(self):
        """Handle a file:num occurrence."""
        if self.current_state in ['mc', 'ms', 'mx']:
            self.instance.append(self.current_entry)
            self.current_entry = POEntry(linenum=self.current_line)
        occurrences = self.current_token[3:].split()
        for occurrence in occurrences:
            if occurrence != '':
                try:
                    fil, line = occurrence.rsplit(':', 1)
                    if not line.isdigit():
                        fil = fil + line
                        line = ''
                    self.current_entry.occurrences.append((fil, line))
                except (ValueError, AttributeError):
                    self.current_entry.occurrences.append((occurrence, ''))
        return True

    def handle_fl(self):
        """Handle a flags line."""
        if self.current_state in ['mc', 'ms', 'mx']:
            self.instance.append(self.current_entry)
            self.current_entry = POEntry(linenum=self.current_line)
        self.current_entry.flags += [c.strip() for c in
                                     self.current_token[3:].split(',')]
        return True

    def handle_pp(self):
        """Handle a previous msgid_plural line."""
        if self.current_state in ['mc', 'ms', 'mx']:
            self.instance.append(self.current_entry)
            self.current_entry = POEntry(linenum=self.current_line)
        self.current_entry.previous_msgid_plural = \
            unescape(self.current_token[1:-1])
        return True

    def handle_pm(self):
        """Handle a previous msgid line."""
        if self.current_state in ['mc', 'ms', 'mx']:
            self.instance.append(self.current_entry)
            self.current_entry = POEntry(linenum=self.current_line)
        self.current_entry.previous_msgid = \
            unescape(self.current_token[1:-1])
        return True

    def handle_pc(self):
        """Handle a previous msgctxt line."""
        if self.current_state in ['mc', 'ms', 'mx']:
            self.instance.append(self.current_entry)
            self.current_entry = POEntry(linenum=self.current_line)
        self.current_entry.previous_msgctxt = \
            unescape(self.current_token[1:-1])
        return True

    def handle_ct(self):
        """Handle a msgctxt."""
        if self.current_state in ['mc', 'ms', 'mx']:
            self.instance.append(self.current_entry)
            self.current_entry = POEntry(linenum=self.current_line)
        self.current_entry.msgctxt = unescape(self.current_token[1:-1])
        return True

    def handle_mi(self):
        """Handle a msgid."""
        if self.current_state in ['mc', 'ms', 'mx']:
            self.instance.append(self.current_entry)
            self.current_entry = POEntry(linenum=self.current_line)
        self.current_entry.obsolete = self.entry_obsolete
        self.current_entry.msgid = unescape(self.current_token[1:-1])
        return True

    def handle_mp(self):
        """Handle a msgid plural."""
        self.current_entry.msgid_plural = unescape(self.current_token[1:-1])
        return True

    def handle_ms(self):
        """Handle a msgstr."""
        self.current_entry.msgstr = unescape(self.current_token[1:-1])
        return True

    def handle_mx(self):
        """Handle a msgstr plural."""
        index = self.current_token[7]
        value = self.current_token[self.current_token.find('"') + 1:-1]
        self.current_entry.msgstr_plural[int(index)] = unescape(value)
        self.msgstr_index = int(index)
        return True

    def handle_mc(self):
        """Handle a msgid or msgstr continuation line."""
        token = unescape(self.current_token[1:-1])
        if self.current_state == 'ct':
            self.current_entry.msgctxt += token
        elif self.current_state == 'mi':
            self.current_entry.msgid += token
        elif self.current_state == 'mp':
            self.current_entry.msgid_plural += token
        elif self.current_state == 'ms':
            self.current_entry.msgstr += token
        elif self.current_state == 'mx':
            self.current_entry.msgstr_plural[self.msgstr_index] += token
        elif self.current_state == 'pp':
            self.current_entry.previous_msgid_plural += token
        elif self.current_state == 'pm':
            self.current_entry.previous_msgid += token
        elif self.current_state == 'pc':
            self.current_entry.previous_msgctxt += token
        # don't change the current state
        return False
# }}}
# class _MOFileParser {{{


class _MOFileParser(object):
    """
    A class to parse binary mo files.
    """

    def __init__(self, mofile, *args, **kwargs):
        """
        Constructor.

        Keyword arguments:

        ``mofile``
            string, path to the mo file or its content

        ``encoding``
            string, the encoding to use, defaults to ``default_encoding``
            global variable (optional).

        ``check_for_duplicates``
            whether to check for duplicate entries when adding entries to the
            file (optional, default: ``False``).
        """
        self.fhandle = open(mofile, 'rb')

        klass = kwargs.get('klass')
        if klass is None:
            klass = MOFile
        self.instance = klass(
            fpath=mofile,
            encoding=kwargs.get('encoding', default_encoding),
            check_for_duplicates=kwargs.get('check_for_duplicates', False)
        )

    def __del__(self):
        """
        Make sure the file is closed, this prevents warnings on unclosed file
        when running tests with python >= 3.2.
        """
        if self.fhandle:
            self.fhandle.close()

    def parse(self):
        """
        Build the instance with the file handle provided in the
        constructor.
        """
        # parse magic number
        magic_number = self._readbinary('<I', 4)
        if magic_number == MOFile.MAGIC:
            ii = '<II'
        elif magic_number == MOFile.MAGIC_SWAPPED:
            ii = '>II'
        else:
            raise IOError('Invalid mo file, magic number is incorrect !')
        self.instance.magic_number = magic_number
        # parse the version number and the number of strings
        version, numofstrings = self._readbinary(ii, 8)
        # from MO file format specs: "A program seeing an unexpected major
        # revision number should stop reading the MO file entirely"
        if version not in (0, 1):
            raise IOError('Invalid mo file, unexpected major revision number')
        self.instance.version = version
        # original strings and translation strings hash table offset
        msgids_hash_offset, msgstrs_hash_offset = self._readbinary(ii, 8)
        # move to msgid hash table and read length and offset of msgids
        self.fhandle.seek(msgids_hash_offset)
        msgids_index = []
        for i in range(numofstrings):
            msgids_index.append(self._readbinary(ii, 8))
        # move to msgstr hash table and read length and offset of msgstrs
        self.fhandle.seek(msgstrs_hash_offset)
        msgstrs_index = []
        for i in range(numofstrings):
            msgstrs_index.append(self._readbinary(ii, 8))
        # build entries
        encoding = self.instance.encoding
        for i in range(numofstrings):
            self.fhandle.seek(msgids_index[i][1])
            msgid = self.fhandle.read(msgids_index[i][0])

            self.fhandle.seek(msgstrs_index[i][1])
            msgstr = self.fhandle.read(msgstrs_index[i][0])
            if i == 0 and not msgid:  # metadata
                raw_metadata, metadata = msgstr.split(b('\n')), {}
                for line in raw_metadata:
                    tokens = line.split(b(':'), 1)
                    if tokens[0] != b(''):
                        try:
                            k = tokens[0].decode(encoding)
                            v = tokens[1].decode(encoding)
                            metadata[k] = v.strip()
                        except IndexError:
                            metadata[k] = u('')
                self.instance.metadata = metadata
                continue
            # test if we have a plural entry
            msgid_tokens = msgid.split(b('\0'))
            if len(msgid_tokens) > 1:
                entry = self._build_entry(
                    msgid=msgid_tokens[0],
                    msgid_plural=msgid_tokens[1],
                    msgstr_plural=dict((k, v) for k, v in
                                       enumerate(msgstr.split(b('\0'))))
                )
            else:
                entry = self._build_entry(msgid=msgid, msgstr=msgstr)
            self.instance.append(entry)
        # close opened file
        self.fhandle.close()
        return self.instance

    def _build_entry(self, msgid, msgstr=None, msgid_plural=None,
                     msgstr_plural=None):
        msgctxt_msgid = msgid.split(b('\x04'))
        encoding = self.instance.encoding
        if len(msgctxt_msgid) > 1:
            kwargs = {
                'msgctxt': msgctxt_msgid[0].decode(encoding),
                'msgid': msgctxt_msgid[1].decode(encoding),
            }
        else:
            kwargs = {'msgid': msgid.decode(encoding)}
        if msgstr:
            kwargs['msgstr'] = msgstr.decode(encoding)
        if msgid_plural:
            kwargs['msgid_plural'] = msgid_plural.decode(encoding)
        if msgstr_plural:
            for k in msgstr_plural:
                msgstr_plural[k] = msgstr_plural[k].decode(encoding)
            kwargs['msgstr_plural'] = msgstr_plural
        return MOEntry(**kwargs)

    def _readbinary(self, fmt, numbytes):
        """
        Private method that unpack n bytes of data using format <fmt>.
        It returns a tuple or a mixed value if the tuple length is 1.
        """
        bytes = self.fhandle.read(numbytes)
        tup = struct.unpack(fmt, bytes)
        if len(tup) == 1:
            return tup[0]
        return tup
# }}}
# class TextWrapper {{{


class TextWrapper(textwrap.TextWrapper):
    """
    Subclass of textwrap.TextWrapper that backport the
    drop_whitespace option.
    """
    def __init__(self, *args, **kwargs):
        drop_whitespace = kwargs.pop('drop_whitespace', True)
        textwrap.TextWrapper.__init__(self, *args, **kwargs)
        self.drop_whitespace = drop_whitespace

    def _wrap_chunks(self, chunks):
        """_wrap_chunks(chunks : [string]) -> [string]

        Wrap a sequence of text chunks and return a list of lines of
        length 'self.width' or less.  (If 'break_long_words' is false,
        some lines may be longer than this.)  Chunks correspond roughly
        to words and the whitespace between them: each chunk is
        indivisible (modulo 'break_long_words'), but a line break can
        come between any two chunks.  Chunks should not have internal
        whitespace; ie. a chunk is either all whitespace or a "word".
        Whitespace chunks will be removed from the beginning and end of
        lines, but apart from that whitespace is preserved.
        """
        lines = []
        if self.width <= 0:
            raise ValueError("invalid width %r (must be > 0)" % self.width)

        # Arrange in reverse order so items can be efficiently popped
        # from a stack of chucks.
        chunks.reverse()

        while chunks:

            # Start the list of chunks that will make up the current line.
            # cur_len is just the length of all the chunks in cur_line.
            cur_line = []
            cur_len = 0

            # Figure out which static string will prefix this line.
            if lines:
                indent = self.subsequent_indent
            else:
                indent = self.initial_indent

            # Maximum width for this line.
            width = self.width - len(indent)

            # First chunk on line is whitespace -- drop it, unless this
            # is the very beginning of the text (ie. no lines started yet).
            if self.drop_whitespace and chunks[-1].strip() == '' and lines:
                del chunks[-1]

            while chunks:
                l = len(chunks[-1])

                # Can at least squeeze this chunk onto the current line.
                if cur_len + l <= width:
                    cur_line.append(chunks.pop())
                    cur_len += l

                # Nope, this line is full.
                else:
                    break

            # The current line is full, and the next chunk is too big to
            # fit on *any* line (not just this one).
            if chunks and len(chunks[-1]) > width:
                self._handle_long_word(chunks, cur_line, cur_len, width)

            # If the last chunk on this line is all whitespace, drop it.
            if self.drop_whitespace and cur_line and not cur_line[-1].strip():
                del cur_line[-1]

            # Convert current line back to a string and store it in list
            # of all lines (return value).
            if cur_line:
                lines.append(indent + ''.join(cur_line))

        return lines
# }}}
# function wrap() {{{


def wrap(text, width=70, **kwargs):
    """
    Wrap a single paragraph of text, returning a list of wrapped lines.
    """
    if sys.version_info < (2, 6):
        return TextWrapper(width=width, **kwargs).wrap(text)
    return textwrap.wrap(text, width=width, **kwargs)

# }}}

def genKeyId(inkey):
    crc = binascii.crc32(bytes(inkey, encoding="UTF-8")) & 0xffffffff
    # Use simple ASCII characters, exclude I, l, 1 and O, 0 to avoid confusing IDs
    symbols = "ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz23456789";
    outkey = ""
    for keyind in range(0, 5):
        outkey += symbols[(crc & 63) % len(symbols)];
        crc >>= 6;
    return outkey