summaryrefslogtreecommitdiffstats
path: root/doc/translator.py
blob: 32c70d5b0a121967862fe4e52aa8392123508ead (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
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
"""Script to generate reports on translator classes from Doxygen sources.

  The main purpose of the script is to extract the information from sources
  related to internationalization (the translator classes). It uses the
  information to generate documentation (language.doc,
  translator_report.txt) from templates (language.tpl, maintainers.txt).
  
  Simply run the script without parameters to get the reports and
  documentation for all supported languages. If you want to generate the
  translator report only for some languages, pass their codes as arguments
  to the script. In that case, the language.doc will not be generated.
  Example:
  
    python translator.py en nl cz
  
  Originally, the script was written in Perl and was known as translator.pl.
  The last Perl version was dated 2002/05/21 (plus some later corrections)

  $Id$
  
                                         Petr Prikryl (prikrylp@skil.cz)
                               
  History:
  --------
  2002/05/21 - This was the last Perl version. 
  2003/05/16 - List of language marks can be passed as arguments.
  2004/01/24 - Total reimplementation started: classes TrManager, and Transl.
  2004/02/05 - First version that produces translator report. No language.doc yet.
  2004/02/10 - First fully functional version that generates both the translator
               report and the documentation. It is a bit slower than the
               Perl version, but is much less tricky and much more flexible.
               It also solves some problems that were not solved by the Perl
               version. The translator report content should be more useful
               for developers.
  2004/02/11 - Some tuning-up to provide more useful information.
  2004/04/16 - Added new tokens to the tokenizer (to remove some warnings).
  2004/05/25 - Added from __future__ import generators not to force Python 2.3.
  2004/06/03 - Removed dependency on textwrap module.
  2004/07/07 - Fixed the bug in the fill() function.
  2004/07/21 - Better e-mail mangling for HTML part of language.doc.
             - Plural not used for reporting a single missing method.
             - Removal of not used translator adapters is suggested only
               when the report is not restricted to selected languages
               explicitly via script arguments.
  2004/07/26 - Better reporting of not-needed adapters.
  2004/10/04 - Reporting of not called translator methods added.
  2004/10/05 - Modified to check only doxygen/src sources for the previous report.
  2005/02/28 - Slight modification to generate "mailto.txt" auxiliary file.
  2005/08/15 - Doxygen's root directory determined primarily from DOXYGEN 
               environment variable. When not found, then relatively to the script.
  2007/03/20 - The "translate me!" searched in comments and reported if found.
  2008/06/09 - Warning when the MAX_DOT_GRAPH_HEIGHT is still part of trLegendDocs().
  2009/05/09 - Changed HTML output to fit it with XHTML DTD
  2009/09/02 - Added percentage info to the report (implemented / to be implemented).
  2010/02/09 - Added checking/suggestion 'Reimplementation using UTF-8 suggested.
  2010/03/03 - Added [unreachable] prefix used in maintainers.txt.
  2010/05/28 - BOM skipped; minor code cleaning.
  2010/05/31 - e-mail mangled already in maintainers.txt
  2010/08/20 - maintainers.txt to UTF-8, related processin of unicode strings
             - [any mark] introduced instead of [unreachable] only
             - marks hihglighted in HTML
  2010/09/30 - Highlighting in what will be the table in langhowto.html modified.
  """                               

from __future__ import generators
import codecs
import os
import re
import sys


def fill(s):
    """Returns string formated to the wrapped paragraph multiline string.
    
    Replaces whitespaces by one space and then uses he textwrap.fill()."""
    
    # Replace all whitespace by spaces, remove whitespaces that are not
    # necessary, strip the left and right whitespaces, and break the string 
    # to list of words.
    rexWS = re.compile(r'\s+')
    lst = rexWS.sub(' ', s).strip().split()
    
    # If the list is not empty, put the words together and form the lines 
    # of maximum 70 characters. Build the list of lines.
    lines = []
    if lst:
        line = lst.pop(0)   # no separation space in front of the first word
        for word in lst:
            if len(line) + len(word) < 70:
                line += ' ' + word
            else:
                lines.append(line)  # another full line formed
                line = word         # next line started
        lines.append(line)          # the last line
    return '\n'.join(lines)

    
# The following function dedent() is the verbatim copy from the textwrap.py
# module. The textwrap.py was introduced in Python 2.3. To make this script
# working also in older Python versions, I have decided to copy it. 
# Notice that the textwrap.py is copyrighted:
#
# Copyright (C) 1999-2001 Gregory P. Ward.
# Copyright (C) 2002, 2003 Python Software Foundation.
# Written by Greg Ward <gward@python.net>
#
# The explicit permission to use the code here was sent by Guido van Rossum 
# (4th June, 2004).
#
def dedent(text):
    """dedent(text : string) -> string

    Remove any whitespace than can be uniformly removed from the left
    of every line in `text`.

    This can be used e.g. to make triple-quoted strings line up with
    the left edge of screen/whatever, while still presenting it in the
    source code in indented form.

    For example:

        def test():
            # end first line with \ to avoid the empty line!
            s = '''\
            hello
              world
            '''
            print repr(s)          # prints '    hello\n      world\n    '
            print repr(dedent(s))  # prints 'hello\n  world\n'
    """
    lines = text.expandtabs().split('\n')
    margin = None
    for line in lines:
        content = line.lstrip()
        if not content:
            continue
        indent = len(line) - len(content)
        if margin is None:
            margin = indent
        else:
            margin = min(margin, indent)

    if margin is not None and margin > 0:
        for i in range(len(lines)):
            lines[i] = lines[i][margin:]

    return '\n'.join(lines)
    

class Transl:
    """One instance is build for each translator.
    
    The abbreviation of the source file--part after 'translator_'--is used as
    the identification of the object. The empty string is used for the
    abstract Translator class from translator.h. The other information is
    extracted from inside the source file."""
    
    def __init__(self, fname, manager):
        """Bind to the manager and initialize."""
        
        # Store the filename and the reference to the manager object.
        self.fname = fname
        self.manager = manager
        
        # The instance is responsible for loading the source file, so it checks
        # for its existence and quits if something goes wrong.
        if not os.path.isfile(fname):
            sys.stderr.write("\a\nFile '%s' not found!\n" % fname)
            sys.exit(1)
            
        # Initialize the other collected information.
        self.classId = None
        self.baseClassId = None
        self.readableStatus = None   # 'up-to-date', '1.2.3', '1.3', etc.
        self.status = None           # '', '1.2.03', '1.3.00', etc.
        self.lang = None             # like 'Brasilian'
        self.langReadable = None     # like 'Brasilian Portuguese'
        self.note = None             # like 'should be cleaned up'
        self.prototypeDic = {}       # uniPrototype -> prototype
        self.translateMeText = 'translate me!'
        self.translateMeFlag = False # comments with "translate me!" found
        self.txtMAX_DOT_GRAPH_HEIGHT_flag = False # found in string in trLegendDocs()
        self.obsoleteMethods = None  # list of prototypes to be removed
        self.missingMethods = None   # list of prototypes to be implemented
        self.implementedMethods = None  # list of implemented required methods
        self.adaptMinClass = None    # The newest adapter class that can be used
        self.isDecodedTranslator = None  # Flag related to internal usage of UTF-8    
        
    def __tokenGenerator(self):
        """Generator that reads the file and yields tokens as 4-tuples.
        
        The tokens have the form (tokenId, tokenString, lineNo). The
        last returned token has the form ('eof', None, None). When trying
        to access next token afer that, the exception would be raised."""

        # Set the dictionary for recognizing tokenId for keywords, separators
        # and the similar categories. The key is the string to be recognized,
        # the value says its token identification.
        tokenDic = { 'class':     'class',
                     'const':     'const',
                     'public':    'public',
                     'protected': 'protected',
                     'private':   'private',
                     'static':    'static',
                     'virtual':   'virtual',
                     ':':         'colon',    
                     ';':         'semic',
                     ',':         'comma',
                     '[':         'lsqbra',   
                     ']':         'rsqbra',
                     '(':         'lpar',    
                     ')':         'rpar',
                     '{':         'lcurly',    
                     '}':         'rcurly',
                     '=':         'assign',
                     '*':         'star',
                     '&':         'amp',
                     '+':         'plus',
                     '-':         'minus',
                     '!':         'excl',
                     '?':         'qmark',
                     '<':         'lt',
                     '>':         'gt',
                     "'":         'quot',
                     '"':         'dquot',
                     '.':         'dot',
                     '%':         'perc',
                     '~':         'tilde',
                     '^':         'caret',
                   }
        
        # Regular expression for recognizing identifiers.
        rexId = re.compile(r'^[a-zA-Z]\w*$')

        # Open the file for reading and extracting tokens until the eof.
        # Initialize the finite automaton.
        f = open(self.fname)
        lineNo = 0
        line = ''         # init -- see the pos initialization below
        linelen = 0       # init
        pos = 100         # init -- pos after the end of line
        status = 0     
        
        tokenId = None    # init
        tokenStr = ''     # init -- the characters will be appended.
        tokenLineNo = 0

        while status != 777:
            
            # Get the next character. Read next line first, if necessary.
            if pos < linelen:
                c = line[pos]
            else:
                lineNo += 1
                line = f.readline()
                if line.startswith('\xef\xbb\xbf'):
                    line = line[3:]    # skip the BOM
                linelen = len(line)
                pos = 0
                if line == '':         # eof
                    status = 777
                else:
                    c = line[pos]
                
            # Consume the character based on the status

            if status == 0:     # basic status
                
                # This is the initial status. If tokenId is set, yield the
                # token here and only here (except when eof is found).
                # Initialize the token variables after the yield.
                if tokenId:
                    # If it is an unknown item, it can still be recognized
                    # here. Keywords and separators are the example.
                    if tokenId == 'unknown': 
                        if tokenDic.has_key(tokenStr):
                            tokenId = tokenDic[tokenStr]
                        elif tokenStr.isdigit():
                            tokenId = 'num'
                        elif rexId.match(tokenStr):
                            tokenId = 'id'
                        else:
                            msg = '\aWarning: unknown token "' + tokenStr + '"'
                            msg += '\tfound on line %d' % tokenLineNo 
                            msg += ' in "' + self.fname + '".\n'
                            sys.stderr.write(msg)
                    
                    yield (tokenId, tokenStr, tokenLineNo)

                    # If it is a comment that contains the self.translateMeText 
                    # string, set the flag -- the situation will be reported.
                    if tokenId == 'comment' and tokenStr.find(self.translateMeText) >= 0:
                        self.translateMeFlag = True
            
                    tokenId = None
                    tokenStr = ''
                    tokenLineNo = 0 
                
                # Now process the character. When we just skip it (spaces),
                # stay in this status. All characters that will be part of
                # some token cause moving to the specific status. And only
                # when moving to the status == 0 (or the final state 777), 
                # the token is yielded. With respect to that the automaton
                # behaves as Moore's one (output bound to status). When 
                # collecting tokens, the automaton is the Mealy's one 
                # (actions bound to transitions).
                if c.isspace():
                    pass                 # just skip whitespace characters
                elif c == '/':           # Possibly comment starts here, but
                    tokenId = 'unknown'  # it could be only a slash in code.
                    tokenStr = c
                    tokenLineNo = lineNo
                    status = 1
                elif c == '#':
                    tokenId = 'preproc'  # preprocessor directive
                    tokenStr = c
                    tokenLineNo = lineNo
                    status = 5
                elif c == '"':           # string starts here
                    tokenId = 'string'
                    tokenStr = c
                    tokenLineNo = lineNo
                    status = 6
                elif c == "'":           # char literal starts here
                    tokenId = 'charlit'
                    tokenStr = c
                    tokenLineNo = lineNo
                    status = 8
                elif tokenDic.has_key(c):  # known one-char token 
                    tokenId = tokenDic[c]
                    tokenStr = c
                    tokenLineNo = lineNo
                    # stay in this state to yield token immediately
                else:
                    tokenId = 'unknown'  # totally unknown
                    tokenStr = c
                    tokenLineNo = lineNo
                    status = 333
                
                pos += 1                 # move position in any case
                    
            elif status == 1:            # possibly a comment
                if c == '/':             # ... definitely the C++ comment
                    tokenId = 'comment'
                    tokenStr += c
                    pos += 1            
                    status = 2
                elif c == '*':           # ... definitely the C comment
                    tokenId = 'comment'
                    tokenStr += c
                    pos += 1            
                    status = 3
                else:
                    status = 0           # unrecognized, don't move pos
                    
            elif status == 2:            # inside the C++ comment
                if c == '\n':            # the end of C++ comment
                    status = 0           # yield the token
                else:
                    tokenStr += c        # collect the C++ comment
                pos += 1
                
            elif status == 3:            # inside the C comment
                if c == '*':             # possibly the end of the C comment
                    tokenStr += c
                    status = 4
                else:
                    tokenStr += c        # collect the C comment
                pos += 1

            elif status == 4:            # possibly the end of the C comment
                if c == '/':             # definitely the end of the C comment
                    tokenStr += c
                    status = 0           # yield the token
                elif c == '*':           # more stars inside the comment
                    tokenStr += c
                else:
                    tokenStr += c        # this cannot be the end of comment
                    status = 3
                pos += 1

            elif status == 5:            # inside the preprocessor directive
                if c == '\n':            # the end of the preproc. command
                    status = 0           # yield the token
                else:
                    tokenStr += c        # collect the preproc
                pos += 1
                
            elif status == 6:            # inside the string
                if c == '\\':            # escaped char inside the string
                    tokenStr += c
                    status = 7
                elif c == '"':           # end of the string
                    tokenStr += c
                    status = 0
                else:
                    tokenStr += c        # collect the chars of the string
                pos += 1
                
            elif status == 7:            # escaped char inside the string
                tokenStr += c            # collect the char of the string
                status = 6
                pos += 1
                
            elif status == 8:            # inside the char literal
                tokenStr += c            # collect the char of the literal
                status = 9
                pos += 1
                
            elif status == 9:            # end of char literal expected
                if c == "'":             # ... and found
                    tokenStr += c
                    status = 0
                    pos += 1
                else:
                    tokenId = 'error'    # end of literal was expected
                    tokenStr += c
                    status = 0

            elif status == 333:          # start of the unknown token
                if c.isspace():
                    pos += 1
                    status = 0           # tokenId may be determined later
                elif tokenDic.has_key(c):  # separator, don't move pos
                    status = 0
                else:
                    tokenStr += c        # collect
                    pos += 1
                    
        # We should have finished in the final status. If some token 
        # have been extracted, yield it first.
        assert(status == 777)
        if tokenId:
            yield (tokenId, tokenStr, tokenLineNo)
            tokenId = None
            tokenStr = ''
            tokenLineNo = 0 

        # The file content is processed. Close the file. Then always yield 
        # the eof token.
        f.close()
        yield ('eof', None, None)
            
        
    def __collectClassInfo(self, tokenIterator):
        """Collect the information about the class and base class.
        
        The tokens including the opening left curly brace of the class are
        consumed."""
        
        status = 0  # initial state
        
        while status != 777:   # final state
            
            # Always assume that the previous tokens were processed. Get
            # the next one.
            tokenId, tokenStr, tokenLineNo = tokenIterator.next()

            # Process the token and never return back.
            if status == 0:    # waiting for the 'class' keyword.
                if tokenId == 'class':
                    status = 1
                    
            elif status == 1:  # expecting the class identification
                if tokenId == 'id':
                    self.classId = tokenStr
                    status = 2
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                
            elif status == 2:  # expecting the curly brace or base class info
                if tokenId == 'lcurly':
                    status = 777        # correctly finished
                elif tokenId == 'colon':
                    status = 3
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                    
            elif status == 3:  # expecting the 'public' in front of base class id
                if tokenId == 'public':
                    status = 4
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                
            elif status == 4:  # expecting the base class id
                if tokenId == 'id':
                    self.baseClassId = tokenStr
                    status = 5
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                
            elif status == 5:  # expecting the curly brace and quitting
                if tokenId == 'lcurly':
                    status = 777        # correctly finished
                elif tokenId == 'comment':
                    pass
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                
        # Extract the status of the TranslatorXxxx class. The readable form
        # will be used in reports the status form is a string that can be
        # compared lexically (unified length, padding with zeros, etc.).
        if self.baseClassId:
            lst = self.baseClassId.split('_')
            if lst[0] == 'Translator':
                self.readableStatus = 'up-to-date'
                self.status = ''
            elif lst[0] == 'TranslatorAdapter':
                self.status = lst[1] + '.' + lst[2]
                self.readableStatus = self.status
                if len(lst) > 3:        # add the last part of the number
                    self.status += '.' + ('%02d' % int(lst[3]))
                    self.readableStatus += '.' + lst[3]
                else:
                    self.status += '.00'
            elif lst[0] == 'TranslatorEnglish':
                # Obsolete or Based on English.
                if self.classId[-2:] == 'En':
                    self.readableStatus = 'English based'
                    self.status = 'En'
                else:
                    self.readableStatus = 'obsolete'
                    self.status = '0.0.00'
                    
            # Check whether status was set, or set 'strange'.
            if self.status == None: 
                self.status = 'strange'
            if not self.readableStatus: 
                self.readableStatus = 'strange'
                
            # Extract the name of the language and the readable form.
            self.lang = self.classId[10:]  # without 'Translator'
            if self.lang == 'Brazilian':
                self.langReadable = 'Brazilian Portuguese'
            elif self.lang == 'Chinesetraditional':
                self.langReadable = 'Chinese Traditional'
            else:
                self.langReadable = self.lang
                

    def __unexpectedToken(self, status, tokenId, tokenLineNo):
        """Reports unexpected token and quits with exit code 1."""
    
        import inspect
        calledFrom = inspect.stack()[1][3]
        msg = "\a\nUnexpected token '%s' on the line %d in '%s'.\n"
        msg = msg % (tokenId, tokenLineNo, self.fname)
        msg += 'status = %d in %s()\n' % (status, calledFrom)
        sys.stderr.write(msg)
        sys.exit(1)
        
                
    def collectPureVirtualPrototypes(self):
        """Returns dictionary 'unified prototype' -> 'full prototype'.

        The method is expected to be called only for the translator.h. It
        extracts only the pure virtual method and build the dictionary where
        key is the unified prototype without argument identifiers."""
        
        # Prepare empty dictionary that will be returned.
        resultDic = {}
        
        # Start the token generator which parses the class source file.
        tokenIterator = self.__tokenGenerator()

        # Collect the class and the base class identifiers.
        self.__collectClassInfo(tokenIterator)
        assert(self.classId == 'Translator')
        
        # Let's collect readable form of the public virtual pure method
        # prototypes in the readable form -- as defined in translator.h.
        # Let's collect also unified form of the same prototype that omits
        # everything that can be omitted, namely 'virtual' and argument
        # identifiers.
        prototype = ''    # readable prototype (with everything)
        uniPrototype = '' # unified prototype (without arg. identifiers)
        
        # Collect the pure virtual method prototypes. Stop on the closing
        # curly brace followed by the semicolon (end of class).
        status = 0
        curlyCnt = 0      # counter for the level of curly braces

        # Loop until the final state 777 is reached. The errors are processed
        # immediately. In this implementation, it always quits the application.
        while status != 777:     
            
            # Get the next token.
            tokenId, tokenStr, tokenLineNo = tokenIterator.next()
            
            if status == 0:      # waiting for 'public:'
                if tokenId == 'public':
                    status = 1
                
            elif status == 1:    # colon after the 'public'
                if tokenId == 'colon':
                    status = 2
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                
            elif status == 2:    # waiting for 'virtual'
                if tokenId == 'virtual':
                    prototype = tokenStr  # but not to unified prototype
                    status = 3
                elif tokenId == 'comment':
                    pass
                elif tokenId == 'rcurly':
                    status = 11         # expected end of class
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                    
            elif status == 3:    # return type of the method expected
                if tokenId == 'id':
                    prototype += ' ' + tokenStr
                    uniPrototype = tokenStr  # start collecting the unified prototype
                    status = 4
		elif tokenId == 'tilde':
                    status = 4
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                    
            elif status == 4:    # method identifier expected
                if tokenId == 'id':
                    prototype += ' ' + tokenStr
                    uniPrototype += ' ' + tokenStr
                    status = 5
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                    
            elif status == 5:    # left bracket of the argument list expected
                if tokenId == 'lpar':
                    prototype += tokenStr
                    uniPrototype += tokenStr
                    status = 6
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                    
            elif status == 6:    # collecting arguments of the method
                if tokenId == 'rpar':
                    prototype += tokenStr
                    uniPrototype += tokenStr
                    status = 7
                elif tokenId == 'const':
                    prototype += tokenStr
                    uniPrototype += tokenStr
                    status = 12
                elif tokenId == 'id':           # type identifier
                    prototype += tokenStr
                    uniPrototype += tokenStr
                    status = 13
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                    
            elif status == 7:    # assignment expected or left curly brace
                if tokenId == 'assign':
                    status = 8
                elif tokenId == 'lcurly':
                    curlyCnt = 1      # method body entered 
                    status = 10
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                    
            elif status == 8:    # zero expected
                if tokenId == 'num' and tokenStr == '0':
                    status = 9
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                    
            elif status == 9:    # after semicolon, produce the dic item
                if tokenId == 'semic':
                    assert(not resultDic.has_key(uniPrototype))
                    resultDic[uniPrototype] = prototype
                    status = 2
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                    
            elif status == 10:   # consuming the body of the method
                if tokenId == 'rcurly':
                    curlyCnt -= 1
                    if curlyCnt == 0:
                        status = 2     # body consumed
                elif tokenId == 'lcurly':
                    curlyCnt += 1
                        
            elif status == 11:   # probably the end of class
                if tokenId == 'semic':
                    status = 777
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                   
            elif status == 12:   # type id for argument expected
                if tokenId == 'id':
                    prototype += ' ' + tokenStr
                    uniPrototype += ' ' + tokenStr
                    status = 13
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                   
            elif status == 13:   # namespace qualification or * or & expected
                if tokenId == 'colon':        # was namespace id
                    prototype += tokenStr
                    uniPrototype += tokenStr
                    status = 14
                elif tokenId == 'star' or tokenId == 'amp':  # pointer or reference
                    prototype += ' ' + tokenStr
                    uniPrototype += ' ' + tokenStr
                    status = 16
                elif tokenId == 'id':         # argument identifier
                    prototype += ' ' + tokenStr
                    # don't put this into unified prototype
                    status = 17
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                   
            elif status == 14:   # second colon for namespace:: expected
                if tokenId == 'colon':        
                    prototype += tokenStr
                    uniPrototype += tokenStr
                    status = 15
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                   
            elif status == 15:   # type after namespace:: expected
                if tokenId == 'id':        
                    prototype += tokenStr
                    uniPrototype += tokenStr
                    status = 13
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                   
            elif status == 16:   # argument identifier expected
                if tokenId == 'id':        
                    prototype += ' ' + tokenStr
                    # don't put this into unified prototype
                    status = 17
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                   
            elif status == 17:   # comma or ')' after argument identifier expected
                if tokenId == 'comma':        
                    prototype += ', '
                    uniPrototype += ', '
                    status = 6
                elif tokenId == 'rpar':
                    prototype += tokenStr
                    uniPrototype += tokenStr
                    status = 7
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
 
        # Eat the rest of the source to cause closing the file.
        while tokenId != 'eof':
            tokenId, tokenStr, tokenLineNo = tokenIterator.next()
            
        # Return the resulting dictionary with 'uniPrototype -> prototype'.
        return resultDic
            
        
    def __collectPublicMethodPrototypes(self, tokenIterator):    
        """Collects prototypes of public methods and fills self.prototypeDic.
        
        The dictionary is filled by items: uniPrototype -> prototype. 
        The method is expected to be called only for TranslatorXxxx classes,
        i.e. for the classes that implement translation to some language.
        It assumes that the openning curly brace of the class was already
        consumed. The source is consumed until the end of the class. 
        The caller should consume the source until the eof to cause closing 
        the source file."""
        
        assert(self.classId != 'Translator')
        assert(self.baseClassId != None)

        # The following finite automaton slightly differs from the one
        # inside self.collectPureVirtualPrototypes(). It produces the
        # dictionary item just after consuming the body of the method
        # (transition from from state 10 to state 2). It also does not allow
        # definitions of public pure virtual methods, except for
        # TranslatorAdapterBase (states 8 and 9). Argument identifier inside
        # method argument lists can be omitted or commented.
        #
        # Let's collect readable form of all public method prototypes in 
        # the readable form -- as defined in the source file.
        # Let's collect also unified form of the same prototype that omits
        # everything that can be omitted, namely 'virtual' and argument
        # identifiers.
        prototype = ''    # readable prototype (with everything)
        uniPrototype = '' # unified prototype (without arg. identifiers)
        warning = ''      # warning message -- if something special detected
        methodId = None   # processed method id
        
        # Collect the method prototypes. Stop on the closing
        # curly brace followed by the semicolon (end of class).
        status = 0
        curlyCnt = 0      # counter for the level of curly braces

        # Loop until the final state 777 is reached. The errors are processed
        # immediately. In this implementation, it always quits the application.
        while status != 777:     
            
            # Get the next token.
            tokenId, tokenStr, tokenLineNo = tokenIterator.next()
            
            if status == 0:      # waiting for 'public:'
                if tokenId == 'public':
                    status = 1
                elif tokenId == 'eof':  # non-public things until the eof
                    status = 777
                
            elif status == 1:    # colon after the 'public'
                if tokenId == 'colon':
                    status = 2
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                
            elif status == 2:    # waiting for 'virtual' (can be omitted)
                if tokenId == 'virtual':
                    prototype = tokenStr  # but not to unified prototype
                    status = 3
                elif tokenId == 'id':     # 'virtual' was omitted
                    prototype = tokenStr
                    uniPrototype = tokenStr  # start collecting the unified prototype
                    status = 4
                elif tokenId == 'comment':
                    pass
                elif tokenId == 'protected' or tokenId == 'private':
                    status = 0
                elif tokenId == 'rcurly':
                    status = 11         # expected end of class
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                    
            elif status == 3:    # return type of the method expected
                if tokenId == 'id':
                    prototype += ' ' + tokenStr
                    uniPrototype = tokenStr  # start collecting the unified prototype
                    status = 4
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                    
            elif status == 4:    # method identifier expected
                if tokenId == 'id':
                    prototype += ' ' + tokenStr
                    uniPrototype += ' ' + tokenStr
                    methodId = tokenStr    # for reporting
                    status = 5
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                    
            elif status == 5:    # left bracket of the argument list expected
                if tokenId == 'lpar':
                    prototype += tokenStr
                    uniPrototype += tokenStr
                    status = 6
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                    
            elif status == 6:    # collecting arguments of the method
                if tokenId == 'rpar':
                    prototype += tokenStr
                    uniPrototype += tokenStr
                    status = 7
                elif tokenId == 'const':
                    prototype += tokenStr
                    uniPrototype += tokenStr
                    status = 12
                elif tokenId == 'id':           # type identifier
                    prototype += tokenStr
                    uniPrototype += tokenStr
                    status = 13
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                    
            elif status == 7:    # left curly brace expected 
                if tokenId == 'lcurly':
                    curlyCnt = 1      # method body entered 
                    status = 10
                elif tokenId == 'comment':
                    pass
                elif tokenId == 'assign': # allowed only for TranslatorAdapterBase
                    assert(self.classId == 'TranslatorAdapterBase')
                    status = 8
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                    
            elif status == 8:    # zero expected (TranslatorAdapterBase)
                assert(self.classId == 'TranslatorAdapterBase')
                if tokenId == 'num' and tokenStr == '0':
                    status = 9
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                    
            elif status == 9:    # after semicolon (TranslatorAdapterBase)
                assert(self.classId == 'TranslatorAdapterBase')
                if tokenId == 'semic':
                    status = 2
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)

            elif status == 10:   # consuming the body of the method, then dic item
                if tokenId == 'rcurly':
                    curlyCnt -= 1
                    if curlyCnt == 0:
                        # Insert new dictionary item.
                        assert(not self.prototypeDic.has_key(uniPrototype))
                        self.prototypeDic[uniPrototype] = prototype
                        status = 2      # body consumed
                        methodId = None # outside of any method
                elif tokenId == 'lcurly':
                    curlyCnt += 1
                    
                # Warn in special case.     
                elif methodId == 'trLegendDocs' and tokenId == 'string' \
                    and tokenStr.find('MAX_DOT_GRAPH_HEIGHT') >= 0:
                        self.txtMAX_DOT_GRAPH_HEIGHT_flag = True  
  
                    
            elif status == 11:   # probably the end of class
                if tokenId == 'semic':
                    status = 777
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                   
            elif status == 12:   # type id for argument expected
                if tokenId == 'id':
                    prototype += ' ' + tokenStr
                    uniPrototype += ' ' + tokenStr
                    status = 13
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                   
            elif status == 13:   # :: or * or & or id or ) expected
                if tokenId == 'colon':        # was namespace id
                    prototype += tokenStr
                    uniPrototype += tokenStr
                    status = 14
                elif tokenId == 'star' or tokenId == 'amp':  # pointer or reference
                    prototype += ' ' + tokenStr
                    uniPrototype += ' ' + tokenStr
                    status = 16
                elif tokenId == 'id':         # argument identifier
                    prototype += ' ' + tokenStr
                    # don't put this into unified prototype
                    status = 17
                elif tokenId == 'comment':    # probably commented-out identifier
                    prototype += tokenStr
                elif tokenId == 'rpar':
                    prototype += tokenStr
                    uniPrototype += tokenStr
                    status = 7
                elif tokenId == 'comma':        
                    prototype += ', '
                    uniPrototype += ', '
                    status = 6
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                   
            elif status == 14:   # second colon for namespace:: expected
                if tokenId == 'colon':        
                    prototype += tokenStr
                    uniPrototype += tokenStr
                    status = 15
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                   
            elif status == 15:   # type after namespace:: expected
                if tokenId == 'id':        
                    prototype += tokenStr
                    uniPrototype += tokenStr
                    status = 13
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                   
            elif status == 16:   # argument identifier or ) expected
                if tokenId == 'id':        
                    prototype += ' ' + tokenStr
                    # don't put this into unified prototype
                    status = 17
                elif tokenId == 'rpar':
                    prototype += tokenStr
                    uniPrototype += tokenStr
                    status = 7
                elif tokenId == 'comment':
                    prototype += tokenStr
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                   
            elif status == 17:   # comma or ')' after argument identifier expected
                if tokenId == 'comma':        
                    prototype += ', '
                    uniPrototype += ', '
                    status = 6
                elif tokenId == 'rpar':
                    prototype += tokenStr
                    uniPrototype += tokenStr
                    status = 7
                else:
                    self.__unexpectedToken(status, tokenId, tokenLineNo)
                   
        

    def collectAdapterPrototypes(self):
        """Returns the dictionary of prototypes implemented by adapters.
        
        It is created to process the translator_adapter.h. The returned 
        dictionary has the form: unifiedPrototype -> (version, classId)
        thus by looking for the prototype, we get the information what is 
        the newest (least adapting) adapter that is sufficient for 
        implementing the method."""            

        # Start the token generator which parses the class source file.
        assert(os.path.split(self.fname)[1] == 'translator_adapter.h')
        tokenIterator = self.__tokenGenerator()

        # Get the references to the involved dictionaries.
        reqDic = self.manager.requiredMethodsDic

        # Create the empty dictionary that will be returned.
        adaptDic = {}
        
        
        # Loop through the source of the adapter file until no other adapter
        # class is found.
        while True:
            try:
                # Collect the class and the base class identifiers.
                self.__collectClassInfo(tokenIterator)

                # Extract the comparable version of the adapter class.
                # Note: The self.status as set by self.__collectClassInfo()
                # contains similar version, but is related to the base class,
                # not to the class itself.
                lst = self.classId.split('_')
                version = ''
                if lst[0] == 'TranslatorAdapter': # TranslatorAdapterBase otherwise
                    version = lst[1] + '.' + lst[2]
                    if len(lst) > 3:        # add the last part of the number
                        version += '.' + ('%02d' % int(lst[3]))
                    else:
                        version += '.00'
                
                # Collect the prototypes of implemented public methods.
                self.__collectPublicMethodPrototypes(tokenIterator)
        
                # For the required methods, update the dictionary of methods 
                # implemented by the adapter.
                for protoUni in self.prototypeDic:
                    if reqDic.has_key(protoUni):
                        # This required method will be marked as implemented
                        # by this adapter class. This implementation assumes 
                        # that newer adapters do not reimplement any required
                        # methods already implemented by older adapters.
                        assert(not adaptDic.has_key(protoUni))
                        adaptDic[protoUni] = (version, self.classId)

                # Clear the dictionary object and the information related
                # to the class as the next adapter class is to be processed.
                self.prototypeDic.clear()
                self.classId = None
                self.baseClassId = None
                
            except StopIteration:
                break

        # Return the result dictionary.
        return adaptDic    

        
    def processing(self):
        """Processing of the source file -- only for TranslatorXxxx classes."""            

        # Start the token generator which parses the class source file.
        tokenIterator = self.__tokenGenerator()

        # Collect the class and the base class identifiers.
        self.__collectClassInfo(tokenIterator)
        assert(self.classId != 'Translator')
        assert(self.classId[:17] != 'TranslatorAdapter')
        
        # Collect the prototypes of implemented public methods.
        self.__collectPublicMethodPrototypes(tokenIterator)
        
        # Eat the rest of the source to cause closing the file.
        while True:
            try:
                t = tokenIterator.next()
            except StopIteration:
                break

        # Shorthands for the used dictionaries.
        reqDic = self.manager.requiredMethodsDic
        adaptDic = self.manager.adaptMethodsDic
        myDic = self.prototypeDic
        
        # Build the list of obsolete methods.
        self.obsoleteMethods = []
        for p in myDic:
            if not reqDic.has_key(p):
                self.obsoleteMethods.append(p)
        
        # Build the list of missing methods and the list of implemented
        # required methods.
        self.missingMethods = []
        self.implementedMethods = []
        for p in reqDic:
            if myDic.has_key(p):
                self.implementedMethods.append(p)
            else:
                self.missingMethods.append(p)

        # Set the least important note first if the translator is decoded.
        # If yes, then it means that the implementation should be switched
        # to UTF-8 later (suggestion).
        self.isDecodedTranslator = self.classId in self.manager.decodedTranslators
        if self.isDecodedTranslator:
            self.note = 'Reimplementation using UTF-8 suggested.'
            
        # Check whether adapter must be used or suggest the newest one.
        # Change the status and set the note accordingly.
        if self.baseClassId != 'Translator':
            if not self.missingMethods: 
                self.note = 'Change the base class to Translator.'
                self.status = ''
                self.readableStatus = 'up-to-date'
            elif self.baseClassId != 'TranslatorEnglish':
                # The translator uses some of the adapters.
                # Look at the missing methods and check what adapter 
                # implements them. Remember the one with the lowest version.
                adaptMinVersion = '9.9.99'
                adaptMinClass = 'TranslatorAdapter_9_9_99'
                for uniProto in self.missingMethods:
                    if adaptDic.has_key(uniProto):
                        version, cls = adaptDic[uniProto]
                        if version < adaptMinVersion:
                            adaptMinVersion = version
                            adaptMinClass = cls
                
                # Test against the current status -- preserve the self.status.
                # Possibly, the translator implements enough methods to 
                # use some newer adapter.
                status = self.status
                    
                # If the version of the used adapter is smaller than
                # the required, set the note and update the status as if
                # the newer adapter was used.
                if adaptMinVersion > status:
                    self.note = 'Change the base class to %s.' % adaptMinClass
                    self.status = adaptMinVersion
                    self.adaptMinClass = adaptMinClass
                    self.readableStatus = adaptMinVersion # simplified
        
        # If everything seems OK, some explicit warning flags still could 
        # be set. 
        if not self.note and self.status == '' and \
           (self.translateMeFlag or self.txtMAX_DOT_GRAPH_HEIGHT_flag):
           self.note = '' 
           if self.translateMeFlag:
               self.note += 'The "%s" found in a comment.' % self.translateMeText
           if self.note != '':
               self.note += '\n\t\t'          
           if self.txtMAX_DOT_GRAPH_HEIGHT_flag:
                self.note += 'The MAX_DOT_GRAPH_HEIGHT found in trLegendDocs()'
        
        # If everything seems OK, but there are obsolete methods, set 
        # the note to clean-up source. This note will be used only when
        # the previous code did not set another note (priority).
        if not self.note and self.status == '' and self.obsoleteMethods:
            self.note = 'Remove the obsolete methods (never used).'
            
                
    def report(self, fout):
        """Returns the report part for the source as a multiline string.
        
        No output for up-to-date translators without problem."""
        
        # If there is nothing to report, return immediately.
        if self.status == '' and not self.note:
            return
            
        # Report the number of not implemented methods.
        fout.write('\n\n\n')
        fout.write(self.classId + '   (' + self.baseClassId + ')')
        percentImplemented = 100    # init
        allNum = len(self.manager.requiredMethodsDic) 
        if self.missingMethods:
            num = len(self.missingMethods)
            percentImplemented = 100 * (allNum - num) / allNum
            fout.write('  %d' % num)
            fout.write(' method')
            if num > 1:
                fout.write('s')
            fout.write(' to implement (%d %%)' % (100 * num / allNum))
        fout.write('\n' + '-' * len(self.classId))
        
        # Write the info about the implemented required methods.
        fout.write('\n\n  Implements %d' % len(self.implementedMethods))
        fout.write(' of the required methods (%d %%).' % percentImplemented)
        
        # Report the missing method, but only when it is not English-based
        # translator.
        if self.missingMethods and self.status != 'En':
            fout.write('\n\n  Missing methods (should be implemented):\n')
            reqDic = self.manager.requiredMethodsDic
            for p in self.missingMethods:
                fout.write('\n    ' + reqDic[p])

        # Always report obsolete methods.
        if self.obsoleteMethods:
            fout.write('\n\n  Obsolete methods (should be removed, never used):\n')
            myDic = self.prototypeDic
            for p in self.obsoleteMethods:
                fout.write('\n    ' + myDic[p])

        # For English-based translator, report the implemented methods.
        if self.status == 'En' and self.implementedMethods:
            fout.write('\n\n  This English-based translator implements ')
            fout.write('the following methods:\n')
            reqDic = self.manager.requiredMethodsDic
            for p in self.implementedMethods:
                fout.write('\n    ' + reqDic[p])

                
    def getmtime(self):
        """Returns the last modification time of the source file."""
        assert(os.path.isfile(self.fname))
        return os.path.getmtime(self.fname)
        
                
class TrManager:
    """Collects basic info and builds subordinate Transl objects."""
    
    def __init__(self):
        """Determines paths, creates and initializes structures.
        
        The arguments of the script may explicitly say what languages should 
        be processed. Write the two letter identifications that are used
        for composing the source filenames, so...
            
            python translator.py cz
            
        this will process only translator_cz.h source.
        """
        
        # Determine the path to the script and its name.
        self.script = os.path.abspath(sys.argv[0]) 
        self.script_path, self.script_name = os.path.split(self.script) 
        self.script_path = os.path.abspath(self.script_path)
        
        # Determine the absolute path to the Doxygen's root subdirectory.
        # If DOXYGEN environment variable is not found, the directory is
        # determined from the path of the script.
        doxy_default = os.path.join(self.script_path, '..')    
        self.doxy_path = os.path.abspath(os.getenv('DOXYGEN', doxy_default))
        
        # Get the explicit arguments of the script.
        self.script_argLst = sys.argv[1:]
        
        # Build the path names based on the Doxygen's root knowledge.
        self.doc_path = os.path.join(self.doxy_path, 'doc')
        self.src_path = os.path.join(self.doxy_path, 'src')
        
        # Create the empty dictionary for Transl object identitied by the
        # class identifier of the translator. 
        self.__translDic = {}

        # Create the None dictionary of required methods. The key is the
        # unified prototype, the value is the full prototype. Set inside
        # the self.__build().
        self.requiredMethodsDic = None
        
        # Create the empty dictionary that says what method is implemented
        # by what adapter.
        self.adaptMethodsDic = {}
        
        # The last modification time will capture the modification of this
        # script, of the translator.h, of the translator_adapter.h (see the 
        # self.__build() for the last two) of all the translator_xx.h files
        # and of the template for generating the documentation. So, this
        # time can be compared with modification time of the generated 
        # documentation to decide, whether the doc should be re-generated.
        self.lastModificationTime = os.path.getmtime(self.script)
        
        # Set the names of the translator report text file, of the template
        # for generating "Internationalization" document, for the generated
        # file itself, and for the maintainers list.
        self.translatorReportFileName = 'translator_report.txt'
        self.maintainersFileName = 'maintainers.txt'
        self.languageTplFileName = 'language.tpl'
        self.languageDocFileName = 'language.doc'
        
        # The information about the maintainers will be stored 
        # in the dictionary with the following name.
        self.__maintainersDic = None
        
        # Define the other used structures and variables for information.
        self.langLst = None                   # including English based
        self.supportedLangReadableStr = None  # coupled En-based as a note
        self.numLang = None                   # excluding coupled En-based
        self.doxVersion = None                # Doxygen version
        
        # Capture the knowledge about translators that are not implemented
        # to use UTF-8 internally.
        self.decodedTranslators = self.getDecodedTranslators()
        
        # Build objects where each one is responsible for one translator.
        self.__build()
        
        
    def getDecodedTranslators(self):
        """Parses language.cpp to find what translators do not use UTF-8 yet"""
        decodedTranslators = []
        
        # Regular expression to detect the lines like
        #     theTranslator=new TranslatorDecoder(new TranslatorSwedish);
        rex = re.compile(r'^\s*theTranslator\s*=\s*new\s+.*$')
        
        # Regular expression to get the (optional) TranslatorDecoder and TranslatorXXX
        rex2 = re.compile(r'\bTranslator\w+')
        
        # Parse the lines in the specific source code.
        f = open(os.path.join(self.src_path, 'language.cpp'), 'rU')
        for line in f:
            if rex.match(line):
                lst = rex2.findall(line)
                if lst[0] == 'TranslatorDecoder':
                    decodedTranslators.append(lst[1])
        f.close()
        
        # Display warning when all translator implementations were converted 
        # to UTF-8.
        if len(decodedTranslators) == 0:
            print 'This script should be updated. All translators do use UTF-8'
            print 'internally.  The TranslatorDecoder adapter should be removed'
            print 'from the code and its usage should not be checked any more.'
            
        return decodedTranslators
    
        
    def __build(self):
        """Find the translator files and build the objects for translators."""
        
        # The translator.h must exist (the Transl object will check it),
        # create the object for it and let it build the dictionary of
        # required methods.
        tr = Transl(os.path.join(self.src_path, 'translator.h'), self)
        self.requiredMethodsDic = tr.collectPureVirtualPrototypes()
        tim = tr.getmtime()
        if tim > self.lastModificationTime:
            self.lastModificationTime = tim
        
        # The translator_adapter.h must exist (the Transl object will check it),
        # create the object for it and store the reference in the dictionary.
        tr = Transl(os.path.join(self.src_path, 'translator_adapter.h'), self)
        self.adaptMethodsDic = tr.collectAdapterPrototypes()
        tim = tr.getmtime()
        if tim > self.lastModificationTime:
            self.lastModificationTime = tim
            
        # Create the list of the filenames with language translator sources.
        # If the explicit arguments of the script were typed, process only
        # those files.
        if self.script_argLst:
            lst = ['translator_' + x + '.h' for x in self.script_argLst]
            for fname in lst:
                if not os.path.isfile(os.path.join(self.src_path, fname)):
                    sys.stderr.write("\a\nFile '%s' not found!\n" % fname)
                    sys.exit(1)
        else:                    
            lst = os.listdir(self.src_path)
            lst = filter(lambda x: x[:11] == 'translator_'
                                   and x[-2:] == '.h'
                                   and x != 'translator_adapter.h', lst)
    
        # Build the object for the translator_xx.h files, and process the 
        # content of the file. Then insert the object to the dictionary
        # accessed via classId.
        for fname in lst:
            fullname = os.path.join(self.src_path, fname)
            tr = Transl(fullname, self)
            tr.processing()
            assert(tr.classId != 'Translator')
            self.__translDic[tr.classId] = tr

        # Extract the global information of the processed info. 
        self.__extractProcessedInfo()
        
    
    def __extractProcessedInfo(self):
        """Build lists and strings of the processed info."""        

        # Build the auxiliary list with strings compound of the status,
        # readable form of the language, and classId.
        statLst = []
        for obj in self.__translDic.values():
            assert(obj.classId != 'Translator')
            s = obj.status + '|' + obj.langReadable + '|' + obj.classId
            statLst.append(s)
        
        # Sort the list and extract the object identifiers (classId's) for
        # the up-to-date translators and English-based translators.
        statLst.sort()
        self.upToDateIdLst = [x.split('|')[2] for x in statLst if x[0] == '|']
        self.EnBasedIdLst = [x.split('|')[2] for x in statLst if x[:2] == 'En']

        # Reverse the list and extract the TranslatorAdapter based translators.
        statLst.reverse()
        self.adaptIdLst = [x.split('|')[2] for x in statLst if x[0].isdigit()]

        # Build the list of tuples that contain (langReadable, obj). 
        # Sort it by readable name.
        self.langLst = []
        for obj in self.__translDic.values():
            self.langLst.append((obj.langReadable, obj))
        self.langLst.sort(lambda a, b: cmp(a[0], b[0]))
            
        # Create the list with readable language names. If the language has
        # also the English-based version, modify the item by appending
        # the note. Number of the supported languages is equal to the length
        # of the list.
        langReadableLst = []
        for name, obj in self.langLst:
            if obj.status == 'En': continue
            
            # Append the 'En' to the classId to possibly obtain the classId
            # of the English-based object. If the object exists, modify the
            # name for the readable list of supported languages.
            classIdEn = obj.classId + 'En'
            if self.__translDic.has_key(classIdEn):
                name += ' (+En)'
            
            # Append the result name of the language, possibly with note.
            langReadableLst.append(name)

        # Create the multiline string of readable language names, 
        # with punctuation, wrapped to paragraph.
        if len(langReadableLst) == 1:
            s = langReadableLst[0]
        elif len(langReadableLst) == 2:
            s = ' and '.join(langReadableLst) 
        else:    
            s = ', '.join(langReadableLst[:-1]) + ', and ' 
            s += langReadableLst[-1]
        
        self.supportedLangReadableStr = fill(s + '.') 

        # Find the number of the supported languages. The English based
        # languages are not counted if the non-English based also exists.
        self.numLang = len(self.langLst)
        for name, obj in self.langLst:
            if obj.status == 'En':
                classId = obj.classId[:-2]
                if self.__translDic.has_key(classId):
                    self.numLang -= 1    # the couple will be counted as one
        
        # Extract the version of Doxygen.
        f = open(os.path.join(self.doxy_path, 'VERSION'))
        self.doxVersion = f.readline().strip()
        f.close()
        
        # Update the last modification time.
        for tr in self.__translDic.values():
            tim = tr.getmtime()
            if tim > self.lastModificationTime:
                self.lastModificationTime = tim
        
        
    def __getNoTrSourceFilesLst(self):
        """Returns the list of sources to be checked.
        
        All .cpp files and also .h files that do not declare or define
        the translator methods are included in the list. The file names 
        are searched in doxygen/src directory.
        """ 
        files = []
        for item in os.listdir(self.src_path):
            # Split the bare name to get the extension.
            name, ext = os.path.splitext(item)
            ext = ext.lower()
            
            # Include only .cpp and .h files (case independent) and exclude
            # the files where the checked identifiers are defined.
            if ext == '.cpp' or (ext == '.h' and name.find('translator') == -1):
                fname = os.path.join(self.src_path, item)
                assert os.path.isfile(fname) # assumes no directory with the ext
                files.append(fname)          # full name
        return files
        
    
    def __removeUsedInFiles(self, fname, dic):
        """Removes items for method identifiers that are found in fname.
        
        The method reads the content of the file as one string and searches
        for all identifiers from dic. The identifiers that were found in
        the file are removed from the dictionary.
        
        Note: If more files is to be checked, the files where most items are
        probably used should be checked first and the resulting reduced 
        dictionary should be used for checking the next files (speed up).
        """
        lst_in = dic.keys()   # identifiers to be searched for
        
        # Read content of the file as one string.
        assert os.path.isfile(fname)
        f = open(fname)
        cont = f.read()
        f.close()
        
        # Remove the items for identifiers that were found in the file.
        while lst_in:
            item = lst_in.pop(0)
            if cont.find(item) != -1:
                del dic[item]

    
    def __checkForNotUsedTrMethods(self):
        """Returns the dictionary of not used translator methods.
        
        The method can be called only after self.requiredMethodsDic has been
        built. The stripped prototypes are the values, the method identifiers
        are the keys.
        """
        # Build the dictionary of the required method prototypes with
        # method identifiers used as keys.
        trdic = {}
        for prototype in self.requiredMethodsDic.keys():
            ri = prototype.split('(')[0]
            identifier = ri.split()[1].strip()
            trdic[identifier] = prototype
        
        # Build the list of source files where translator method identifiers
        # can be used.
        files = self.__getNoTrSourceFilesLst()
        
        # Loop through the files and reduce the dictionary of id -> proto.
        for fname in files:
            self.__removeUsedInFiles(fname, trdic)
        
        # Return the dictionary of not used translator methods.
        return trdic
        
        
    def __emails(self, classId):
        """Returns the list of maintainer emails.
        
        The method returns the list of e-mail adresses for the translator
        class, but only the addresses that were not marked as [xxx]."""
        lst = []
        for m in self.__maintainersDic[classId]:
            if not m[1].startswith('['):
                email = m[1]
                email = email.replace(' at ', '@') # Unmangle the mangled e-mail 
                email = email.replace(' dot ', '.')
                lst.append(email)
        return lst
                    
    
    def generateTranslatorReport(self):
        """Generates the translator report."""

        output = os.path.join(self.doc_path, self.translatorReportFileName)
        
        # Open the textual report file for the output.
        f = open(output, 'w')

        # Output the information about the version.
        f.write('(' + self.doxVersion + ')\n\n')
        
        # Output the information about the number of the supported languages
        # and the list of the languages, or only the note about the explicitly
        # given languages to process.
        if self.script_argLst:
            f.write('The report was generated for the following, explicitly')
            f.write(' identified languages:\n\n')
            f.write(self.supportedLangReadableStr + '\n\n')
        else:
            f.write('Doxygen supports the following ')
            f.write(str(self.numLang))
            f.write(' languages (sorted alphabetically):\n\n')
            f.write(self.supportedLangReadableStr + '\n\n')
        
            # Write the summary about the status of language translators (how 
            # many translators) are up-to-date, etc.
            s = 'Of them, %d translators are up-to-date, ' % len(self.upToDateIdLst)
            s += '%d translators are based on some adapter class, ' % len(self.adaptIdLst)  
            s += 'and %d are English based.' % len(self.EnBasedIdLst)
            f.write(fill(s) + '\n\n')
        
        # The e-mail addresses of the maintainers will be collected to 
        # the auxiliary file in the order of translator classes listed
        # in the translator report.
        fmail = open('mailto.txt', 'w')
        
        # Write the list of up-to-date translator classes. 
        if self.upToDateIdLst:
            s = '''The following translator classes are up-to-date (sorted
                alphabetically). This means that they derive from the
                Translator class and they implement all %d of the required
                methods. Anyway, there still may be some details listed even 
                for them:'''
            s = s % len(self.requiredMethodsDic)    
            f.write('-' * 70 + '\n')
            f.write(fill(s) + '\n\n')
            
            mailtoLst = []
            for x in self.upToDateIdLst:
                obj = self.__translDic[x]
                f.write('  ' + obj.classId)
                if obj.note:
                    f.write(' -- ' + obj.note)
                f.write('\n')
                mailtoLst.extend(self.__emails(obj.classId))
                
            fmail.write('up-to-date\n')
            fmail.write('; '.join(mailtoLst))

        # Write the list of the adapter based classes. The very obsolete
        # translators that derive from TranslatorEnglish are included.
        if self.adaptIdLst:
            s = '''The following translator classes need some maintenance 
                (the most obsolete at the end). The other info shows the
                estimation of Doxygen version when the class was last
                updated and number of methods that must be implemented to
                become up-to-date:'''
            f.write('\n' + '-' * 70 + '\n')
            f.write(fill(s) + '\n\n')
    
            # Find also whether some adapter classes may be removed.
            adaptMinVersion = '9.9.99'
            
            mailtoLst = []
            numRequired = len(self.requiredMethodsDic)
            for x in self.adaptIdLst:
                obj = self.__translDic[x]
                f.write('  %-30s' % obj.classId)
                f.write('  %-6s' % obj.readableStatus)
                numimpl = len(obj.missingMethods)
                pluralS = ''
                if numimpl > 1: pluralS = 's'
                percent = 100 * numimpl / numRequired
                f.write('\t%2d method%s to implement (%d %%)' % (
                        numimpl, pluralS, percent))
                if obj.note:
                    f.write('\n\tNote: ' + obj.note + '\n')
                f.write('\n')
                mailtoLst.extend(self.__emails(obj.classId)) # to maintainer
                
                # Check the level of required adapter classes.
                if obj.status != '0.0.00' and obj.status < adaptMinVersion:
                    adaptMinVersion = obj.status

            fmail.write('\n\ntranslator based\n')
            fmail.write('; '.join(mailtoLst))
                
            # Set the note if some old translator adapters are not needed 
            # any more. Do it only when the script is called without arguments,
            # i.e. all languages were checked against the needed translator 
            # adapters. 
            if not self.script_argLst:
                to_remove = {}
                for version, adaptClassId in self.adaptMethodsDic.values():
                    if version < adaptMinVersion:
                        to_remove[adaptClassId] = True
                
                if to_remove:
                    lst = to_remove.keys()
                    lst.sort()
                    plural = len(lst) > 1
                    note = 'Note: The adapter class'
                    if plural: note += 'es'
                    note += ' ' + ', '.join(lst)    
                    if not plural: 
                        note += ' is'
                    else:
                        note += ' are'
                    note += ' not used and can be removed.'
                    f.write('\n' + fill(note) + '\n')
                
        # Write the list of the English-based classes.
        if self.EnBasedIdLst:
            s = '''The following translator classes derive directly from the 
                TranslatorEnglish. The class identifier has the suffix 'En' 
                that says that this is intentional. Usually, there is also 
                a non-English based version of the translator for 
                the language:'''
            f.write('\n' + '-' * 70 + '\n')
            f.write(fill(s) + '\n\n')
    
            for x in self.EnBasedIdLst:
                obj = self.__translDic[x]
                f.write('  ' + obj.classId)
                f.write('\timplements %d methods' % len(obj.implementedMethods))
                if obj.note:
                    f.write(' -- ' + obj.note)
                f.write('\n')
            
        # Check for not used translator methods and generate warning if found.
        # The check is rather time consuming, so it is not done when report
        # is restricted to explicitly given language identifiers.
        if not self.script_argLst:
            dic = self.__checkForNotUsedTrMethods()
            if dic:
                s = '''WARNING: The following translator methods are declared
                    in the Translator class but their identifiers do not appear 
                    in source files. The situation should be checked. The .cpp 
                    files and .h files excluding the '*translator*' files 
                    in doxygen/src directory were simply searched for occurence 
                    of the method identifiers:'''
                f.write('\n' + '=' * 70 + '\n')
                f.write(fill(s) + '\n\n')
                
                keys = dic.keys()
                keys.sort()
                for key in keys:
                    f.write('  ' + dic[key] + '\n')
                f.write('\n')
        
        # Write the details for the translators.
        f.write('\n' + '=' * 70)
        f.write('\nDetails for translators (classes sorted alphabetically):\n')
        
        cls = self.__translDic.keys()
        cls.sort()
        
        for c in cls:
            obj = self.__translDic[c]
            assert(obj.classId != 'Translator') 
            obj.report(f)
                
        # Close the report file and the auxiliary file with e-mails.     
        f.close()
        fmail.close()
        
            
    def __loadMaintainers(self):
        """Load and process the file with the maintainers.
        
        Fills the dictionary classId -> [(name, e-mail), ...]."""
        
        fname = os.path.join(self.doc_path, self.maintainersFileName)

        # Include the maintainers file to the group of files checked with
        # respect to the modification time.
        tim = os.path.getmtime(fname)
        if tim > self.lastModificationTime:
            self.lastModificationTime = tim
        
        # Process the content of the maintainers file.
        f = codecs.open(fname, 'r', 'utf-8')
        inside = False  # inside the record for the language
        lineReady = True
        classId = None
        maintainersLst = None
        self.__maintainersDic = {}
        while lineReady:
            line = f.readline()            # next line
            lineReady = line != ''         # when eof, then line == ''
                
            line = line.strip()            # eof should also behave as separator
            if line != u'' and line[0] == u'%':    # skip the comment line
                continue           
        
            if not inside:                 # if outside of the record
                if line != u'':            # should be language identifier
                    classId = line
                    maintainersLst = []
                    inside = True
                # Otherwise skip empty line that do not act as separator.
                
            else:                          # if inside the record                       
                if line == u'':            # separator found
                    inside = False
                else:
                    # If it is the first maintainer, create the empty list.
                    if not self.__maintainersDic.has_key(classId):
                        self.__maintainersDic[classId] = []
                    
                    # Split the information about the maintainer and append
                    # the tuple. The address may be prefixed '[unreachable]'
                    # or whatever '[xxx]'. This will be processed later.
                    lst = line.split(u':', 1)
                    assert(len(lst) == 2)
                    t = (lst[0].strip(), lst[1].strip())
                    self.__maintainersDic[classId].append(t)
        f.close()

        
    def generateLanguageDoc(self):
        """Checks the modtime of files and generates language.doc."""
        self.__loadMaintainers()
        
        # Check the last modification time of the template file. It is the
        # last file from the group that decide whether the documentation
        # should or should not be generated.
        fTplName = os.path.join(self.doc_path, self.languageTplFileName)
        tim = os.path.getmtime(fTplName)
        if tim > self.lastModificationTime:
            self.lastModificationTime = tim

        # If the generated documentation exists and is newer than any of 
        # the source files from the group, do not generate it and quit 
        # quietly.
        fDocName = os.path.join(self.doc_path, self.languageDocFileName)
        if os.path.isfile(fDocName): 
            if os.path.getmtime(fDocName) > self.lastModificationTime:
                return
            
        # The document or does not exist or is older than some of the
        # sources. It must be generated again.
        #
        # Read the template of the documentation, and remove the first
        # attention lines.
        f = codecs.open(fTplName, 'r', 'utf-8')
        doctpl = f.read()
        f.close()

        pos = doctpl.find(u'/***')
        assert pos != -1
        doctpl = doctpl[pos:]

        # Fill the tplDic by symbols that will be inserted into the 
        # document template.
        tplDic = {}
        
        s = u'Do not edit this file. It was generated by the %s script.' % self.script_name
        tplDic['editnote'] = s
        
        tplDic['doxVersion'] = self.doxVersion
        tplDic['supportedLangReadableStr'] = self.supportedLangReadableStr 
        tplDic['translatorReportFileName'] = self.translatorReportFileName

        ahref = u'<a href="../doc/' + self.translatorReportFileName
        ahref += u'"\n><code>doxygen/doc/'  + self.translatorReportFileName
        ahref += u'</code></a>'
        tplDic['translatorReportLink'] = ahref
        tplDic['numLangStr'] = str(self.numLang)
        
        # Define templates for HTML table parts of the documentation.
        htmlTableTpl = u'''\
            \\htmlonly
            <table align="center" cellspacing="0" cellpadding="0" border="0">
            <tr bgcolor="#000000">
            <td>
              <table cellspacing="1" cellpadding="2" border="0">
              <tr bgcolor="#4040c0">
              <td ><b><font size="+1" color="#ffffff"> Language </font></b></td>
              <td ><b><font size="+1" color="#ffffff"> Maintainer </font></b></td>
              <td ><b><font size="+1" color="#ffffff"> Contact address </font>
                      <font size="-2" color="#ffffff">(replace the at and dot)</font></b></td>
              <td ><b><font size="+1" color="#ffffff"> Status </font></b></td>
              </tr>
              <!-- table content begin -->
            %s
              <!-- table content end -->
              </table>
            </td>
            </tr>
            </table>
            \\endhtmlonly
            '''
        htmlTableTpl = dedent(htmlTableTpl)    
        htmlTrTpl = u'\n  <tr bgcolor="#ffffff">%s\n  </tr>'
        htmlTdTpl = u'\n    <td>%s</td>'

        # Loop through transl objects in the order of sorted readable names
        # and add generate the content of the HTML table.
        trlst = []
        for name, obj in self.langLst:
            # Fill the table data elements for one row. The first element
            # contains the readable name of the language.
            lst = [ htmlTdTpl % obj.langReadable ]
            
            # The next two elements contain the list of maintainers 
            # and the list of their mangled e-mails. For English-based
            # translators that are coupled with the non-English based, 
            # insert the 'see' note.
            mm = None  # init -- maintainer
            ee = None  # init -- e-mail address
            if obj.status == 'En':
                # Check whether there is the coupled non-English.
                classId = obj.classId[:-2]
                if classId in self.__translDic:
                    lang = self.__translDic[classId].langReadable
                    mm = u'see the %s language' % lang
                    ee = u'&nbsp;'
            
            if not mm and obj.classId in self.__maintainersDic:
                # Build a string of names separated by the HTML break element.
                # Special notes used instead of names are highlighted.
                lm = []  
                for maintainer in self.__maintainersDic[obj.classId]:
                    name = maintainer[0]
                    if name.startswith(u'--'):
                        name = u'<span style="color: red; background-color: yellow">'\
                               + name + u'</span>'
                    lm.append(name)
                mm = u'<br/>'.join(lm)
                
                # The marked adresses (they start with the mark '[unreachable]', 
                # '[resigned]', whatever '[xxx]') will not be displayed at all.
                # Only the mark will be used instead.
                rexMark = re.compile(ur'(?P<mark>\[.*?\])')
                le = []
                for maintainer in self.__maintainersDic[obj.classId]:
                    address = maintainer[1]
                    m = rexMark.search(address)
                    if m is not None:
                        address = u'<span style="color: brown">'\
                                  + m.group(u'mark') + u'</span>'
                    le.append(address)    
                ee = u'<br/>'.join(le)
            
            # Append the maintainer and e-mail elements.
            lst.append(htmlTdTpl % mm)
            lst.append(htmlTdTpl % ee)
            
            # The last element contains the readable form of the status.
            lst.append(htmlTdTpl % obj.readableStatus)
            
            # Join the table data to one table row. 
            trlst.append(htmlTrTpl % (''.join(lst)))
             
        # Join the table rows and insert into the template.
        htmlTable = htmlTableTpl % (''.join(trlst))
        
        # Define templates for LaTeX table parts of the documentation.
        latexTableTpl = ur'''
            \latexonly
            \footnotesize
            \begin{longtable}{|l|l|l|l|}
              \hline 
              {\bf Language} & {\bf Maintainer} & {\bf Contact address} & {\bf Status} \\
              \hline
            %s
              \hline
            \end{longtable}
            \normalsize
            \endlatexonly
            '''
        latexTableTpl = dedent(latexTableTpl)    
        latexLineTpl = u'\n' + r'  %s & %s & {\tt\tiny %s} & %s \\'

        # Loop through transl objects in the order of sorted readable names
        # and add generate the content of the LaTeX table.
        trlst = []
        for name, obj in self.langLst:
            # For LaTeX, more maintainers for the same language are
            # placed on separate rows in the table.  The line separator
            # in the table is placed explicitly above the first
            # maintainer. Prepare the arguments for the LaTeX row template.
            maintainers = []
            if self.__maintainersDic.has_key(obj.classId):
                maintainers = self.__maintainersDic[obj.classId]

            lang = obj.langReadable
            maintainer = None  # init
            email = None       # init
            if obj.status == 'En':
                # Check whether there is the coupled non-English.
                classId = obj.classId[:-2]
                if self.__translDic.has_key(classId):
                    langNE = self.__translDic[classId].langReadable
                    maintainer = u'see the %s language' % langNE
                    email = u'~'
            
            if not maintainer and self.__maintainersDic.has_key(obj.classId):
                lm = [ m[0] for m in self.__maintainersDic[obj.classId] ]  
                maintainer = maintainers[0][0]
                email = maintainers[0][1]

            status = obj.readableStatus

            # Use the template to produce the line of the table and insert
            # the hline plus the constructed line into the table content.
            trlst.append(u'\n  \\hline')
            trlst.append(latexLineTpl % (lang, maintainer, email, status))
                        
            # List the other maintainers for the language. Do not set
            # lang and status for them.
            lang = u'~'
            status = u'~'
            for m in maintainers[1:]:
                maintainer = m[0]
                email = m[1]
                trlst.append(latexLineTpl % (lang, maintainer, email, status))
            
        # Join the table lines and insert into the template.
        latexTable = latexTableTpl % (u''.join(trlst))
            
        # Put the HTML and LaTeX parts together and define the dic item.
        tplDic['informationTable'] = htmlTable + u'\n' + latexTable 

        # Insert the symbols into the document template and write it down.
        f = codecs.open(fDocName, 'w', 'utf-8')
        f.write(doctpl % tplDic)
        f.close()
                    
if __name__ == '__main__':
    
    # Create the manager, build the transl objects, and parse the related
    # sources.
    trMan = TrManager()

    # Generate the language.doc.
    trMan.generateLanguageDoc()
    
    # Generate the translator report.
    trMan.generateTranslatorReport()