summaryrefslogtreecommitdiffstats
path: root/libxml2/doc/apibuild.py
blob: 7a364663b14b3f9c63a8a401ef6633d9dd564043 (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
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
#!/usr/bin/python -u
#
# This is the API builder, it parses the C sources and build the
# API formal description in XML.
#
# See Copyright for the status of this software.
#
# daniel@veillard.com
#
import os, sys
import string
import glob

debug=0
#debugsym='ignorableWhitespaceSAXFunc'
debugsym=None

#
# C parser analysis code
#
ignored_files = {
  "trio": "too many non standard macros",
  "trio.c": "too many non standard macros",
  "trionan.c": "too many non standard macros",
  "triostr.c": "too many non standard macros",
  "acconfig.h": "generated portability layer",
  "config.h": "generated portability layer",
  "libxml.h": "internal only",
  "testOOM.c": "out of memory tester",
  "testOOMlib.h": "out of memory tester",
  "testOOMlib.c": "out of memory tester",
  "rngparser.c": "not yet integrated",
  "rngparser.h": "not yet integrated",
  "elfgcchack.h": "not a normal header",
  "testHTML.c": "test tool",
  "testReader.c": "test tool",
  "testSchemas.c": "test tool",
  "testXPath.c": "test tool",
  "testAutomata.c": "test tool",
  "testModule.c": "test tool",
  "testRegexp.c": "test tool",
  "testThreads.c": "test tool",
  "testC14N.c": "test tool",
  "testRelax.c": "test tool",
  "testThreadsWin32.c": "test tool",
  "testSAX.c": "test tool",
  "testURI.c": "test tool",
  "testapi.c": "generated regression tests",
  "runtest.c": "regression tests program",
  "runsuite.c": "regression tests program",
  "tst.c": "not part of the library",
  "test.c": "not part of the library",
  "testdso.c": "test for dynamid shared libraries",
  "testrecurse.c": "test for entities recursions",
  "xzlib.h": "Internal API only 2.8.0",
  "buf.h": "Internal API only 2.9.0",
  "enc.h": "Internal API only 2.9.0",
  "/save.h": "Internal API only 2.9.0",
  "timsort.h": "Internal header only for xpath.c 2.9.0",
}

ignored_words = {
  "WINAPI": (0, "Windows keyword"),
  "LIBXML_DLL_IMPORT": (0, "Special macro to flag external keywords"),
  "XMLPUBVAR": (0, "Special macro for extern vars for win32"),
  "XSLTPUBVAR": (0, "Special macro for extern vars for win32"),
  "EXSLTPUBVAR": (0, "Special macro for extern vars for win32"),
  "XMLPUBFUN": (0, "Special macro for extern funcs for win32"),
  "XSLTPUBFUN": (0, "Special macro for extern funcs for win32"),
  "EXSLTPUBFUN": (0, "Special macro for extern funcs for win32"),
  "XMLCALL": (0, "Special macro for win32 calls"),
  "XSLTCALL": (0, "Special macro for win32 calls"),
  "XMLCDECL": (0, "Special macro for win32 calls"),
  "EXSLTCALL": (0, "Special macro for win32 calls"),
  "__declspec": (3, "Windows keyword"),
  "__stdcall": (0, "Windows keyword"),
  "ATTRIBUTE_UNUSED": (0, "macro keyword"),
  "LIBEXSLT_PUBLIC": (0, "macro keyword"),
  "X_IN_Y": (5, "macro function builder"),
  "ATTRIBUTE_ALLOC_SIZE": (3, "macro for gcc checking extension"),
  "ATTRIBUTE_PRINTF": (5, "macro for gcc printf args checking extension"),
  "LIBXML_ATTR_FORMAT": (5, "macro for gcc printf args checking extension"),
  "LIBXML_ATTR_ALLOC_SIZE": (3, "macro for gcc checking extension"),
  "__XML_EXTERNC": (0, "Special macro added for os400"),
}

def escape(raw):
    raw = raw.replace('&', '&')
    raw = raw.replace('<', '&lt;')
    raw = raw.replace('>', '&gt;')
    raw = raw.replace("'", '&apos;')
    raw = raw.replace('"', '&quot;')
    return raw

def uniq(items):
    d = {}
    for item in items:
        d[item]=1
    return list(d.keys())

class identifier:
    def __init__(self, name, header=None, module=None, type=None, lineno = 0,
                 info=None, extra=None, conditionals = None):
        self.name = name
        self.header = header
        self.module = module
        self.type = type
        self.info = info
        self.extra = extra
        self.lineno = lineno
        self.static = 0
        if conditionals == None or len(conditionals) == 0:
            self.conditionals = None
        else:
            self.conditionals = conditionals[:]
        if self.name == debugsym:
            print("=> define %s : %s" % (debugsym, (module, type, info,
                                         extra, conditionals)))

    def __repr__(self):
        r = "%s %s:" % (self.type, self.name)
        if self.static:
            r = r + " static"
        if self.module != None:
            r = r + " from %s" % (self.module)
        if self.info != None:
            r = r + " " +  repr(self.info)
        if self.extra != None:
            r = r + " " + repr(self.extra)
        if self.conditionals != None:
            r = r + " " + repr(self.conditionals)
        return r


    def set_header(self, header):
        self.header = header
    def set_module(self, module):
        self.module = module
    def set_type(self, type):
        self.type = type
    def set_info(self, info):
        self.info = info
    def set_extra(self, extra):
        self.extra = extra
    def set_lineno(self, lineno):
        self.lineno = lineno
    def set_static(self, static):
        self.static = static
    def set_conditionals(self, conditionals):
        if conditionals == None or len(conditionals) == 0:
            self.conditionals = None
        else:
            self.conditionals = conditionals[:]

    def get_name(self):
        return self.name
    def get_header(self):
        return self.module
    def get_module(self):
        return self.module
    def get_type(self):
        return self.type
    def get_info(self):
        return self.info
    def get_lineno(self):
        return self.lineno
    def get_extra(self):
        return self.extra
    def get_static(self):
        return self.static
    def get_conditionals(self):
        return self.conditionals

    def update(self, header, module, type = None, info = None, extra=None,
               conditionals=None):
        if self.name == debugsym:
            print("=> update %s : %s" % (debugsym, (module, type, info,
                                         extra, conditionals)))
        if header != None and self.header == None:
            self.set_header(module)
        if module != None and (self.module == None or self.header == self.module):
            self.set_module(module)
        if type != None and self.type == None:
            self.set_type(type)
        if info != None:
            self.set_info(info)
        if extra != None:
            self.set_extra(extra)
        if conditionals != None:
            self.set_conditionals(conditionals)

class index:
    def __init__(self, name = "noname"):
        self.name = name
        self.identifiers = {}
        self.functions = {}
        self.variables = {}
        self.includes = {}
        self.structs = {}
        self.enums = {}
        self.typedefs = {}
        self.macros = {}
        self.references = {}
        self.info = {}

    def add_ref(self, name, header, module, static, type, lineno, info=None, extra=None, conditionals = None):
        if name[0:2] == '__':
            return None
        d = None
        try:
           d = self.identifiers[name]
           d.update(header, module, type, lineno, info, extra, conditionals)
        except:
           d = identifier(name, header, module, type, lineno, info, extra, conditionals)
           self.identifiers[name] = d

        if d != None and static == 1:
            d.set_static(1)

        if d != None and name != None and type != None:
            self.references[name] = d

        if name == debugsym:
            print("New ref: %s" % (d))

        return d

    def add(self, name, header, module, static, type, lineno, info=None, extra=None, conditionals = None):
        if name[0:2] == '__':
            return None
        d = None
        try:
           d = self.identifiers[name]
           d.update(header, module, type, lineno, info, extra, conditionals)
        except:
           d = identifier(name, header, module, type, lineno, info, extra, conditionals)
           self.identifiers[name] = d

        if d != None and static == 1:
            d.set_static(1)

        if d != None and name != None and type != None:
            if type == "function":
                self.functions[name] = d
            elif type == "functype":
                self.functions[name] = d
            elif type == "variable":
                self.variables[name] = d
            elif type == "include":
                self.includes[name] = d
            elif type == "struct":
                self.structs[name] = d
            elif type == "enum":
                self.enums[name] = d
            elif type == "typedef":
                self.typedefs[name] = d
            elif type == "macro":
                self.macros[name] = d
            else:
                print("Unable to register type ", type)

        if name == debugsym:
            print("New symbol: %s" % (d))

        return d

    def merge(self, idx):
        for id in list(idx.functions.keys()):
              #
              # macro might be used to override functions or variables
              # definitions
              #
             if id in self.macros:
                 del self.macros[id]
             if id in self.functions:
                 print("function %s from %s redeclared in %s" % (
                    id, self.functions[id].header, idx.functions[id].header))
             else:
                 self.functions[id] = idx.functions[id]
                 self.identifiers[id] = idx.functions[id]
        for id in list(idx.variables.keys()):
              #
              # macro might be used to override functions or variables
              # definitions
              #
             if id in self.macros:
                 del self.macros[id]
             if id in self.variables:
                 print("variable %s from %s redeclared in %s" % (
                    id, self.variables[id].header, idx.variables[id].header))
             else:
                 self.variables[id] = idx.variables[id]
                 self.identifiers[id] = idx.variables[id]
        for id in list(idx.structs.keys()):
             if id in self.structs:
                 print("struct %s from %s redeclared in %s" % (
                    id, self.structs[id].header, idx.structs[id].header))
             else:
                 self.structs[id] = idx.structs[id]
                 self.identifiers[id] = idx.structs[id]
        for id in list(idx.typedefs.keys()):
             if id in self.typedefs:
                 print("typedef %s from %s redeclared in %s" % (
                    id, self.typedefs[id].header, idx.typedefs[id].header))
             else:
                 self.typedefs[id] = idx.typedefs[id]
                 self.identifiers[id] = idx.typedefs[id]
        for id in list(idx.macros.keys()):
              #
              # macro might be used to override functions or variables
              # definitions
              #
             if id in self.variables:
                 continue
             if id in self.functions:
                 continue
             if id in self.enums:
                 continue
             if id in self.macros:
                 print("macro %s from %s redeclared in %s" % (
                    id, self.macros[id].header, idx.macros[id].header))
             else:
                 self.macros[id] = idx.macros[id]
                 self.identifiers[id] = idx.macros[id]
        for id in list(idx.enums.keys()):
             if id in self.enums:
                 print("enum %s from %s redeclared in %s" % (
                    id, self.enums[id].header, idx.enums[id].header))
             else:
                 self.enums[id] = idx.enums[id]
                 self.identifiers[id] = idx.enums[id]

    def merge_public(self, idx):
        for id in list(idx.functions.keys()):
             if id in self.functions:
                 # check that function condition agrees with header
                 if idx.functions[id].conditionals != \
                    self.functions[id].conditionals:
                     print("Header condition differs from Function for %s:" \
                        % id)
                     print("  H: %s" % self.functions[id].conditionals)
                     print("  C: %s" % idx.functions[id].conditionals)
                 up = idx.functions[id]
                 self.functions[id].update(None, up.module, up.type, up.info, up.extra)
         #     else:
         #         print "Function %s from %s is not declared in headers" % (
         #                id, idx.functions[id].module)
         # TODO: do the same for variables.

    def analyze_dict(self, type, dict):
        count = 0
        public = 0
        for name in list(dict.keys()):
            id = dict[name]
            count = count + 1
            if id.static == 0:
                public = public + 1
        if count != public:
            print("  %d %s , %d public" % (count, type, public))
        elif count != 0:
            print("  %d public %s" % (count, type))


    def analyze(self):
        self.analyze_dict("functions", self.functions)
        self.analyze_dict("variables", self.variables)
        self.analyze_dict("structs", self.structs)
        self.analyze_dict("typedefs", self.typedefs)
        self.analyze_dict("macros", self.macros)

class CLexer:
    """A lexer for the C language, tokenize the input by reading and
       analyzing it line by line"""
    def __init__(self, input):
        self.input = input
        self.tokens = []
        self.line = ""
        self.lineno = 0

    def getline(self):
        line = ''
        while line == '':
            line = self.input.readline()
            if not line:
                return None
            self.lineno = self.lineno + 1
            line = line.lstrip()
            line = line.rstrip()
            if line == '':
                continue
            while line[-1] == '\\':
                line = line[:-1]
                n = self.input.readline()
                self.lineno = self.lineno + 1
                n = n.lstrip()
                n = n.rstrip()
                if not n:
                    break
                else:
                    line = line + n
        return line

    def getlineno(self):
        return self.lineno

    def push(self, token):
        self.tokens.insert(0, token);

    def debug(self):
        print("Last token: ", self.last)
        print("Token queue: ", self.tokens)
        print("Line %d end: " % (self.lineno), self.line)

    def token(self):
        while self.tokens == []:
            if self.line == "":
                line = self.getline()
            else:
                line = self.line
                self.line = ""
            if line == None:
                return None

            if line[0] == '#':
                self.tokens = list(map((lambda x: ('preproc', x)),
                                  line.split()))
                break;
            l = len(line)
            if line[0] == '"' or line[0] == "'":
                end = line[0]
                line = line[1:]
                found = 0
                tok = ""
                while found == 0:
                    i = 0
                    l = len(line)
                    while i < l:
                        if line[i] == end:
                            self.line = line[i+1:]
                            line = line[:i]
                            l = i
                            found = 1
                            break
                        if line[i] == '\\':
                            i = i + 1
                        i = i + 1
                    tok = tok + line
                    if found == 0:
                        line = self.getline()
                        if line == None:
                            return None
                self.last = ('string', tok)
                return self.last

            if l >= 2 and line[0] == '/' and line[1] == '*':
                line = line[2:]
                found = 0
                tok = ""
                while found == 0:
                    i = 0
                    l = len(line)
                    while i < l:
                        if line[i] == '*' and i+1 < l and line[i+1] == '/':
                            self.line = line[i+2:]
                            line = line[:i-1]
                            l = i
                            found = 1
                            break
                        i = i + 1
                    if tok != "":
                        tok = tok + "\n"
                    tok = tok + line
                    if found == 0:
                        line = self.getline()
                        if line == None:
                            return None
                self.last = ('comment', tok)
                return self.last
            if l >= 2 and line[0] == '/' and line[1] == '/':
                line = line[2:]
                self.last = ('comment', line)
                return self.last
            i = 0
            while i < l:
                if line[i] == '/' and i+1 < l and line[i+1] == '/':
                    self.line = line[i:]
                    line = line[:i]
                    break
                if line[i] == '/' and i+1 < l and line[i+1] == '*':
                    self.line = line[i:]
                    line = line[:i]
                    break
                if line[i] == '"' or line[i] == "'":
                    self.line = line[i:]
                    line = line[:i]
                    break
                i = i + 1
            l = len(line)
            i = 0
            while i < l:
                if line[i] == ' ' or line[i] == '\t':
                    i = i + 1
                    continue
                o = ord(line[i])
                if (o >= 97 and o <= 122) or (o >= 65 and o <= 90) or \
                   (o >= 48 and o <= 57):
                    s = i
                    while i < l:
                        o = ord(line[i])
                        if (o >= 97 and o <= 122) or (o >= 65 and o <= 90) or \
                           (o >= 48 and o <= 57) or \
			   (" \t(){}:;,+-*/%&!|[]=><".find(line[i])) == -1:
                            i = i + 1
                        else:
                            break
                    self.tokens.append(('name', line[s:i]))
                    continue
                if "(){}:;,[]".find(line[i]) != -1:
#                 if line[i] == '(' or line[i] == ')' or line[i] == '{' or \
#                    line[i] == '}' or line[i] == ':' or line[i] == ';' or \
#                    line[i] == ',' or line[i] == '[' or line[i] == ']':
                    self.tokens.append(('sep', line[i]))
                    i = i + 1
                    continue
                if "+-*><=/%&!|.".find(line[i]) != -1:
#                 if line[i] == '+' or line[i] == '-' or line[i] == '*' or \
#                    line[i] == '>' or line[i] == '<' or line[i] == '=' or \
#                    line[i] == '/' or line[i] == '%' or line[i] == '&' or \
#                    line[i] == '!' or line[i] == '|' or line[i] == '.':
                    if line[i] == '.' and  i + 2 < l and \
                       line[i+1] == '.' and line[i+2] == '.':
                        self.tokens.append(('name', '...'))
                        i = i + 3
                        continue

                    j = i + 1
                    if j < l and (
                       "+-*><=/%&!|".find(line[j]) != -1):
#                        line[j] == '+' or line[j] == '-' or line[j] == '*' or \
#                        line[j] == '>' or line[j] == '<' or line[j] == '=' or \
#                        line[j] == '/' or line[j] == '%' or line[j] == '&' or \
#                        line[j] == '!' or line[j] == '|'):
                        self.tokens.append(('op', line[i:j+1]))
                        i = j + 1
                    else:
                        self.tokens.append(('op', line[i]))
                        i = i + 1
                    continue
                s = i
                while i < l:
                    o = ord(line[i])
                    if (o >= 97 and o <= 122) or (o >= 65 and o <= 90) or \
                       (o >= 48 and o <= 57) or (
                        " \t(){}:;,+-*/%&!|[]=><".find(line[i]) == -1):
#                         line[i] != ' ' and line[i] != '\t' and
#                         line[i] != '(' and line[i] != ')' and
#                         line[i] != '{'  and line[i] != '}' and
#                         line[i] != ':' and line[i] != ';' and
#                         line[i] != ',' and line[i] != '+' and
#                         line[i] != '-' and line[i] != '*' and
#                         line[i] != '/' and line[i] != '%' and
#                         line[i] != '&' and line[i] != '!' and
#                         line[i] != '|' and line[i] != '[' and
#                         line[i] != ']' and line[i] != '=' and
#                         line[i] != '*' and line[i] != '>' and
#                         line[i] != '<'):
                        i = i + 1
                    else:
                        break
                self.tokens.append(('name', line[s:i]))

        tok = self.tokens[0]
        self.tokens = self.tokens[1:]
        self.last = tok
        return tok

class CParser:
    """The C module parser"""
    def __init__(self, filename, idx = None):
        self.filename = filename
        if len(filename) > 2 and filename[-2:] == '.h':
            self.is_header = 1
        else:
            self.is_header = 0
        self.input = open(filename)
        self.lexer = CLexer(self.input)
        if idx == None:
            self.index = index()
        else:
            self.index = idx
        self.top_comment = ""
        self.last_comment = ""
        self.comment = None
        self.collect_ref = 0
        self.no_error = 0
        self.conditionals = []
        self.defines = []

    def collect_references(self):
        self.collect_ref = 1

    def stop_error(self):
        self.no_error = 1

    def start_error(self):
        self.no_error = 0

    def lineno(self):
        return self.lexer.getlineno()

    def index_add(self, name, module, static, type, info=None, extra = None):
        if self.is_header == 1:
            self.index.add(name, module, module, static, type, self.lineno(),
                           info, extra, self.conditionals)
        else:
            self.index.add(name, None, module, static, type, self.lineno(),
                           info, extra, self.conditionals)

    def index_add_ref(self, name, module, static, type, info=None,
                      extra = None):
        if self.is_header == 1:
            self.index.add_ref(name, module, module, static, type,
                               self.lineno(), info, extra, self.conditionals)
        else:
            self.index.add_ref(name, None, module, static, type, self.lineno(),
                               info, extra, self.conditionals)

    def warning(self, msg):
        if self.no_error:
            return
        print(msg)

    def error(self, msg, token=-1):
        if self.no_error:
            return

        print("Parse Error: " + msg)
        if token != -1:
            print("Got token ", token)
        self.lexer.debug()
        sys.exit(1)

    def debug(self, msg, token=-1):
        print("Debug: " + msg)
        if token != -1:
            print("Got token ", token)
        self.lexer.debug()

    def parseTopComment(self, comment):
        res = {}
        lines = comment.split("\n")
        item = None
        for line in lines:
            while line != "" and (line[0] == ' ' or line[0] == '\t'):
                line = line[1:]
            while line != "" and line[0] == '*':
                line = line[1:]
            while line != "" and (line[0] == ' ' or line[0] == '\t'):
                line = line[1:]
            try:
                (it, line) = line.split(":", 1)
                item = it
                while line != "" and (line[0] == ' ' or line[0] == '\t'):
                    line = line[1:]
                if item in res:
                    res[item] = res[item] + " " + line
                else:
                    res[item] = line
            except:
                if item != None:
                    if item in res:
                        res[item] = res[item] + " " + line
                    else:
                        res[item] = line
        self.index.info = res

    def parseComment(self, token):
        if self.top_comment == "":
            self.top_comment = token[1]
        if self.comment == None or token[1][0] == '*':
            self.comment = token[1];
        else:
            self.comment = self.comment + token[1]
        token = self.lexer.token()

        if self.comment.find("DOC_DISABLE") != -1:
            self.stop_error()

        if self.comment.find("DOC_ENABLE") != -1:
            self.start_error()

        return token

    #
    # Parse a comment block associate to a typedef
    #
    def parseTypeComment(self, name, quiet = 0):
        if name[0:2] == '__':
            quiet = 1

        args = []
        desc = ""

        if self.comment == None:
            if not quiet:
                self.warning("Missing comment for type %s" % (name))
            return((args, desc))
        if self.comment[0] != '*':
            if not quiet:
                self.warning("Missing * in type comment for %s" % (name))
            return((args, desc))
        lines = self.comment.split('\n')
        if lines[0] == '*':
            del lines[0]
        if lines[0] != "* %s:" % (name):
            if not quiet:
                self.warning("Misformatted type comment for %s" % (name))
                self.warning("  Expecting '* %s:' got '%s'" % (name, lines[0]))
            return((args, desc))
        del lines[0]
        while len(lines) > 0 and lines[0] == '*':
            del lines[0]
        desc = ""
        while len(lines) > 0:
            l = lines[0]
            while len(l) > 0 and l[0] == '*':
                l = l[1:]
            l = l.strip()
            desc = desc + " " + l
            del lines[0]

        desc = desc.strip()

        if quiet == 0:
            if desc == "":
                self.warning("Type comment for %s lack description of the macro" % (name))

        return(desc)
    #
    # Parse a comment block associate to a macro
    #
    def parseMacroComment(self, name, quiet = 0):
        if name[0:2] == '__':
            quiet = 1

        args = []
        desc = ""

        if self.comment == None:
            if not quiet:
                self.warning("Missing comment for macro %s" % (name))
            return((args, desc))
        if self.comment[0] != '*':
            if not quiet:
                self.warning("Missing * in macro comment for %s" % (name))
            return((args, desc))
        lines = self.comment.split('\n')
        if lines[0] == '*':
            del lines[0]
        if lines[0] != "* %s:" % (name):
            if not quiet:
                self.warning("Misformatted macro comment for %s" % (name))
                self.warning("  Expecting '* %s:' got '%s'" % (name, lines[0]))
            return((args, desc))
        del lines[0]
        while lines[0] == '*':
            del lines[0]
        while len(lines) > 0 and lines[0][0:3] == '* @':
            l = lines[0][3:]
            try:
                (arg, desc) = l.split(':', 1)
                desc=desc.strip()
                arg=arg.strip()
            except:
                if not quiet:
                    self.warning("Misformatted macro comment for %s" % (name))
                    self.warning("  problem with '%s'" % (lines[0]))
                del lines[0]
                continue
            del lines[0]
            l = lines[0].strip()
            while len(l) > 2 and l[0:3] != '* @':
                while l[0] == '*':
                    l = l[1:]
                desc = desc + ' ' + l.strip()
                del lines[0]
                if len(lines) == 0:
                    break
                l = lines[0]
            args.append((arg, desc))
        while len(lines) > 0 and lines[0] == '*':
            del lines[0]
        desc = ""
        while len(lines) > 0:
            l = lines[0]
            while len(l) > 0 and l[0] == '*':
                l = l[1:]
            l = l.strip()
            desc = desc + " " + l
            del lines[0]

        desc = desc.strip()

        if quiet == 0:
            if desc == "":
                self.warning("Macro comment for %s lack description of the macro" % (name))

        return((args, desc))

     #
     # Parse a comment block and merge the informations found in the
     # parameters descriptions, finally returns a block as complete
     # as possible
     #
    def mergeFunctionComment(self, name, description, quiet = 0):
        if name == 'main':
            quiet = 1
        if name[0:2] == '__':
            quiet = 1

        (ret, args) = description
        desc = ""
        retdesc = ""

        if self.comment == None:
            if not quiet:
                self.warning("Missing comment for function %s" % (name))
            return(((ret[0], retdesc), args, desc))
        if self.comment[0] != '*':
            if not quiet:
                self.warning("Missing * in function comment for %s" % (name))
            return(((ret[0], retdesc), args, desc))
        lines = self.comment.split('\n')
        if lines[0] == '*':
            del lines[0]
        if lines[0] != "* %s:" % (name):
            if not quiet:
                self.warning("Misformatted function comment for %s" % (name))
                self.warning("  Expecting '* %s:' got '%s'" % (name, lines[0]))
            return(((ret[0], retdesc), args, desc))
        del lines[0]
        while lines[0] == '*':
            del lines[0]
        nbargs = len(args)
        while len(lines) > 0 and lines[0][0:3] == '* @':
            l = lines[0][3:]
            try:
                (arg, desc) = l.split(':', 1)
                desc=desc.strip()
                arg=arg.strip()
            except:
                if not quiet:
                    self.warning("Misformatted function comment for %s" % (name))
                    self.warning("  problem with '%s'" % (lines[0]))
                del lines[0]
                continue
            del lines[0]
            l = lines[0].strip()
            while len(l) > 2 and l[0:3] != '* @':
                while l[0] == '*':
                    l = l[1:]
                desc = desc + ' ' + l.strip()
                del lines[0]
                if len(lines) == 0:
                    break
                l = lines[0]
            i = 0
            while i < nbargs:
                if args[i][1] == arg:
                    args[i] = (args[i][0], arg, desc)
                    break;
                i = i + 1
            if i >= nbargs:
                if not quiet:
                    self.warning("Unable to find arg %s from function comment for %s" % (
                       arg, name))
        while len(lines) > 0 and lines[0] == '*':
            del lines[0]
        desc = ""
        while len(lines) > 0:
            l = lines[0]
            while len(l) > 0 and l[0] == '*':
                l = l[1:]
            l = l.strip()
            if len(l) >= 6 and  l[0:6] == "return" or l[0:6] == "Return":
                try:
                    l = l.split(' ', 1)[1]
                except:
                    l = ""
                retdesc = l.strip()
                del lines[0]
                while len(lines) > 0:
                    l = lines[0]
                    while len(l) > 0 and l[0] == '*':
                        l = l[1:]
                    l = l.strip()
                    retdesc = retdesc + " " + l
                    del lines[0]
            else:
                desc = desc + " " + l
                del lines[0]

        retdesc = retdesc.strip()
        desc = desc.strip()

        if quiet == 0:
             #
             # report missing comments
             #
            i = 0
            while i < nbargs:
                if args[i][2] == None and args[i][0] != "void" and \
                   ((args[i][1] != None) or (args[i][1] == '')):
                    self.warning("Function comment for %s lacks description of arg %s" % (name, args[i][1]))
                i = i + 1
            if retdesc == "" and ret[0] != "void":
                self.warning("Function comment for %s lacks description of return value" % (name))
            if desc == "":
                self.warning("Function comment for %s lacks description of the function" % (name))

        return(((ret[0], retdesc), args, desc))

    def parsePreproc(self, token):
        if debug:
            print("=> preproc ", token, self.lexer.tokens)
        name = token[1]
        if name == "#include":
            token = self.lexer.token()
            if token == None:
                return None
            if token[0] == 'preproc':
                self.index_add(token[1], self.filename, not self.is_header,
                                "include")
                return self.lexer.token()
            return token
        if name == "#define":
            token = self.lexer.token()
            if token == None:
                return None
            if token[0] == 'preproc':
                 # TODO macros with arguments
                name = token[1]
                lst = []
                token = self.lexer.token()
                while token != None and token[0] == 'preproc' and \
                      token[1][0] != '#':
                    lst.append(token[1])
                    token = self.lexer.token()
                try:
                    name = name.split('(') [0]
                except:
                    pass
                info = self.parseMacroComment(name, not self.is_header)
                self.index_add(name, self.filename, not self.is_header,
                                "macro", info)
                return token

        #
        # Processing of conditionals modified by Bill 1/1/05
        #
        # We process conditionals (i.e. tokens from #ifdef, #ifndef,
        # #if, #else and #endif) for headers and mainline code,
        # store the ones from the header in libxml2-api.xml, and later
        # (in the routine merge_public) verify that the two (header and
        # mainline code) agree.
        #
        # There is a small problem with processing the headers. Some of
        # the variables are not concerned with enabling / disabling of
        # library functions (e.g. '__XML_PARSER_H__'), and we don't want
        # them to be included in libxml2-api.xml, or involved in
        # the check between the header and the mainline code.  To
        # accomplish this, we ignore any conditional which doesn't include
        # the string 'ENABLED'
        #
        if name == "#ifdef":
            apstr = self.lexer.tokens[0][1]
            try:
                self.defines.append(apstr)
                if apstr.find('ENABLED') != -1:
                    self.conditionals.append("defined(%s)" % apstr)
            except:
                pass
        elif name == "#ifndef":
            apstr = self.lexer.tokens[0][1]
            try:
                self.defines.append(apstr)
                if apstr.find('ENABLED') != -1:
                    self.conditionals.append("!defined(%s)" % apstr)
            except:
                pass
        elif name == "#if":
            apstr = ""
            for tok in self.lexer.tokens:
                if apstr != "":
                    apstr = apstr + " "
                apstr = apstr + tok[1]
            try:
                self.defines.append(apstr)
                if apstr.find('ENABLED') != -1:
                    self.conditionals.append(apstr)
            except:
                pass
        elif name == "#else":
            if self.conditionals != [] and \
               self.defines[-1].find('ENABLED') != -1:
                self.conditionals[-1] = "!(%s)" % self.conditionals[-1]
        elif name == "#endif":
            if self.conditionals != [] and \
               self.defines[-1].find('ENABLED') != -1:
                self.conditionals = self.conditionals[:-1]
            self.defines = self.defines[:-1]
        token = self.lexer.token()
        while token != None and token[0] == 'preproc' and \
            token[1][0] != '#':
            token = self.lexer.token()
        return token

     #
     # token acquisition on top of the lexer, it handle internally
     # preprocessor and comments since they are logically not part of
     # the program structure.
     #
    def token(self):
        global ignored_words

        token = self.lexer.token()
        while token != None:
            if token[0] == 'comment':
                token = self.parseComment(token)
                continue
            elif token[0] == 'preproc':
                token = self.parsePreproc(token)
                continue
            elif token[0] == "name" and token[1] == "__const":
                token = ("name", "const")
                return token
            elif token[0] == "name" and token[1] == "__attribute":
                token = self.lexer.token()
                while token != None and token[1] != ";":
                    token = self.lexer.token()
                return token
            elif token[0] == "name" and token[1] in ignored_words:
                (n, info) = ignored_words[token[1]]
                i = 0
                while i < n:
                    token = self.lexer.token()
                    i = i + 1
                token = self.lexer.token()
                continue
            else:
                if debug:
                    print("=> ", token)
                return token
        return None

     #
     # Parse a typedef, it records the type and its name.
     #
    def parseTypedef(self, token):
        if token == None:
            return None
        token = self.parseType(token)
        if token == None:
            self.error("parsing typedef")
            return None
        base_type = self.type
        type = base_type
         #self.debug("end typedef type", token)
        while token != None:
            if token[0] == "name":
                name = token[1]
                signature = self.signature
                if signature != None:
                    type = type.split('(')[0]
                    d = self.mergeFunctionComment(name,
                            ((type, None), signature), 1)
                    self.index_add(name, self.filename, not self.is_header,
                                    "functype", d)
                else:
                    if base_type == "struct":
                        self.index_add(name, self.filename, not self.is_header,
                                        "struct", type)
                        base_type = "struct " + name
                    else:
                        # TODO report missing or misformatted comments
                        info = self.parseTypeComment(name, 1)
                        self.index_add(name, self.filename, not self.is_header,
                                    "typedef", type, info)
                token = self.token()
            else:
                self.error("parsing typedef: expecting a name")
                return token
             #self.debug("end typedef", token)
            if token != None and token[0] == 'sep' and token[1] == ',':
                type = base_type
                token = self.token()
                while token != None and token[0] == "op":
                    type = type + token[1]
                    token = self.token()
            elif token != None and token[0] == 'sep' and token[1] == ';':
                break;
            elif token != None and token[0] == 'name':
                type = base_type
                continue;
            else:
                self.error("parsing typedef: expecting ';'", token)
                return token
        token = self.token()
        return token

     #
     # Parse a C code block, used for functions it parse till
     # the balancing } included
     #
    def parseBlock(self, token):
        while token != None:
            if token[0] == "sep" and token[1] == "{":
                token = self.token()
                token = self.parseBlock(token)
            elif token[0] == "sep" and token[1] == "}":
                self.comment = None
                token = self.token()
                return token
            else:
                if self.collect_ref == 1:
                    oldtok = token
                    token = self.token()
                    if oldtok[0] == "name" and oldtok[1][0:3] == "xml":
                        if token[0] == "sep" and token[1] == "(":
                            self.index_add_ref(oldtok[1], self.filename,
                                                0, "function")
                            token = self.token()
                        elif token[0] == "name":
                            token = self.token()
                            if token[0] == "sep" and (token[1] == ";" or
                               token[1] == "," or token[1] == "="):
                                self.index_add_ref(oldtok[1], self.filename,
                                                    0, "type")
                    elif oldtok[0] == "name" and oldtok[1][0:4] == "XML_":
                        self.index_add_ref(oldtok[1], self.filename,
                                            0, "typedef")
                    elif oldtok[0] == "name" and oldtok[1][0:7] == "LIBXML_":
                        self.index_add_ref(oldtok[1], self.filename,
                                            0, "typedef")

                else:
                    token = self.token()
        return token

     #
     # Parse a C struct definition till the balancing }
     #
    def parseStruct(self, token):
        fields = []
         #self.debug("start parseStruct", token)
        while token != None:
            if token[0] == "sep" and token[1] == "{":
                token = self.token()
                token = self.parseTypeBlock(token)
            elif token[0] == "sep" and token[1] == "}":
                self.struct_fields = fields
                 #self.debug("end parseStruct", token)
                 #print fields
                token = self.token()
                return token
            else:
                base_type = self.type
                 #self.debug("before parseType", token)
                token = self.parseType(token)
                 #self.debug("after parseType", token)
                if token != None and token[0] == "name":
                    fname = token[1]
                    token = self.token()
                    if token[0] == "sep" and token[1] == ";":
                        self.comment = None
                        token = self.token()
                        fields.append((self.type, fname, self.comment))
                        self.comment = None
                    else:
                        self.error("parseStruct: expecting ;", token)
                elif token != None and token[0] == "sep" and token[1] == "{":
                    token = self.token()
                    token = self.parseTypeBlock(token)
                    if token != None and token[0] == "name":
                        token = self.token()
                    if token != None and token[0] == "sep" and token[1] == ";":
                        token = self.token()
                    else:
                        self.error("parseStruct: expecting ;", token)
                else:
                    self.error("parseStruct: name", token)
                    token = self.token()
                self.type = base_type;
        self.struct_fields = fields
         #self.debug("end parseStruct", token)
         #print fields
        return token

     #
     # Parse a C enum block, parse till the balancing }
     #
    def parseEnumBlock(self, token):
        self.enums = []
        name = None
        self.comment = None
        comment = ""
        value = "0"
        while token != None:
            if token[0] == "sep" and token[1] == "{":
                token = self.token()
                token = self.parseTypeBlock(token)
            elif token[0] == "sep" and token[1] == "}":
                if name != None:
                    if self.comment != None:
                        comment = self.comment
                        self.comment = None
                    self.enums.append((name, value, comment))
                token = self.token()
                return token
            elif token[0] == "name":
                    if name != None:
                        if self.comment != None:
                            comment = self.comment.strip()
                            self.comment = None
                        self.enums.append((name, value, comment))
                    name = token[1]
                    comment = ""
                    token = self.token()
                    if token[0] == "op" and token[1][0] == "=":
                        value = ""
                        if len(token[1]) > 1:
                            value = token[1][1:]
                        token = self.token()
                        while token[0] != "sep" or (token[1] != ',' and
                              token[1] != '}'):
                            value = value + token[1]
                            token = self.token()
                    else:
                        try:
                            value = "%d" % (int(value) + 1)
                        except:
                            self.warning("Failed to compute value of enum %s" % (name))
                            value=""
                    if token[0] == "sep" and token[1] == ",":
                        token = self.token()
            else:
                token = self.token()
        return token

     #
     # Parse a C definition block, used for structs it parse till
     # the balancing }
     #
    def parseTypeBlock(self, token):
        while token != None:
            if token[0] == "sep" and token[1] == "{":
                token = self.token()
                token = self.parseTypeBlock(token)
            elif token[0] == "sep" and token[1] == "}":
                token = self.token()
                return token
            else:
                token = self.token()
        return token

     #
     # Parse a type: the fact that the type name can either occur after
     #    the definition or within the definition makes it a little harder
     #    if inside, the name token is pushed back before returning
     #
    def parseType(self, token):
        self.type = ""
        self.struct_fields = []
        self.signature = None
        if token == None:
            return token

        while token[0] == "name" and (
              token[1] == "const" or \
              token[1] == "unsigned" or \
              token[1] == "signed"):
            if self.type == "":
                self.type = token[1]
            else:
                self.type = self.type + " " + token[1]
            token = self.token()

        if token[0] == "name" and (token[1] == "long" or token[1] == "short"):
            if self.type == "":
                self.type = token[1]
            else:
                self.type = self.type + " " + token[1]
            if token[0] == "name" and token[1] == "int":
                if self.type == "":
                    self.type = tmp[1]
                else:
                    self.type = self.type + " " + tmp[1]

        elif token[0] == "name" and token[1] == "struct":
            if self.type == "":
                self.type = token[1]
            else:
                self.type = self.type + " " + token[1]
            token = self.token()
            nametok = None
            if token[0] == "name":
                nametok = token
                token = self.token()
            if token != None and token[0] == "sep" and token[1] == "{":
                token = self.token()
                token = self.parseStruct(token)
            elif token != None and token[0] == "op" and token[1] == "*":
                self.type = self.type + " " + nametok[1] + " *"
                token = self.token()
                while token != None and token[0] == "op" and token[1] == "*":
                    self.type = self.type + " *"
                    token = self.token()
                if token[0] == "name":
                    nametok = token
                    token = self.token()
                else:
                    self.error("struct : expecting name", token)
                    return token
            elif token != None and token[0] == "name" and nametok != None:
                self.type = self.type + " " + nametok[1]
                return token

            if nametok != None:
                self.lexer.push(token)
                token = nametok
            return token

        elif token[0] == "name" and token[1] == "enum":
            if self.type == "":
                self.type = token[1]
            else:
                self.type = self.type + " " + token[1]
            self.enums = []
            token = self.token()
            if token != None and token[0] == "sep" and token[1] == "{":
                token = self.token()
                token = self.parseEnumBlock(token)
            else:
                self.error("parsing enum: expecting '{'", token)
            enum_type = None
            if token != None and token[0] != "name":
                self.lexer.push(token)
                token = ("name", "enum")
            else:
                enum_type = token[1]
            for enum in self.enums:
                self.index_add(enum[0], self.filename,
                               not self.is_header, "enum",
                               (enum[1], enum[2], enum_type))
            return token

        elif token[0] == "name":
            if self.type == "":
                self.type = token[1]
            else:
                self.type = self.type + " " + token[1]
        else:
            self.error("parsing type %s: expecting a name" % (self.type),
                       token)
            return token
        token = self.token()
        while token != None and (token[0] == "op" or
              token[0] == "name" and token[1] == "const"):
            self.type = self.type + " " + token[1]
            token = self.token()

         #
         # if there is a parenthesis here, this means a function type
         #
        if token != None and token[0] == "sep" and token[1] == '(':
            self.type = self.type + token[1]
            token = self.token()
            while token != None and token[0] == "op" and token[1] == '*':
                self.type = self.type + token[1]
                token = self.token()
            if token == None or token[0] != "name" :
                self.error("parsing function type, name expected", token);
                return token
            self.type = self.type + token[1]
            nametok = token
            token = self.token()
            if token != None and token[0] == "sep" and token[1] == ')':
                self.type = self.type + token[1]
                token = self.token()
                if token != None and token[0] == "sep" and token[1] == '(':
                    token = self.token()
                    type = self.type;
                    token = self.parseSignature(token);
                    self.type = type;
                else:
                    self.error("parsing function type, '(' expected", token);
                    return token
            else:
                self.error("parsing function type, ')' expected", token);
                return token
            self.lexer.push(token)
            token = nametok
            return token

         #
         # do some lookahead for arrays
         #
        if token != None and token[0] == "name":
            nametok = token
            token = self.token()
            if token != None and token[0] == "sep" and token[1] == '[':
                self.type = self.type + nametok[1]
                while token != None and token[0] == "sep" and token[1] == '[':
                    self.type = self.type + token[1]
                    token = self.token()
                    while token != None and token[0] != 'sep' and \
                          token[1] != ']' and token[1] != ';':
                        self.type = self.type + token[1]
                        token = self.token()
                if token != None and token[0] == 'sep' and token[1] == ']':
                    self.type = self.type + token[1]
                    token = self.token()
                else:
                    self.error("parsing array type, ']' expected", token);
                    return token
            elif token != None and token[0] == "sep" and token[1] == ':':
                 # remove :12 in case it's a limited int size
                token = self.token()
                token = self.token()
            self.lexer.push(token)
            token = nametok

        return token

     #
     # Parse a signature: '(' has been parsed and we scan the type definition
     #    up to the ')' included
    def parseSignature(self, token):
        signature = []
        if token != None and token[0] == "sep" and token[1] == ')':
            self.signature = []
            token = self.token()
            return token
        while token != None:
            token = self.parseType(token)
            if token != None and token[0] == "name":
                signature.append((self.type, token[1], None))
                token = self.token()
            elif token != None and token[0] == "sep" and token[1] == ',':
                token = self.token()
                continue
            elif token != None and token[0] == "sep" and token[1] == ')':
                 # only the type was provided
                if self.type == "...":
                    signature.append((self.type, "...", None))
                else:
                    signature.append((self.type, None, None))
            if token != None and token[0] == "sep":
                if token[1] == ',':
                    token = self.token()
                    continue
                elif token[1] == ')':
                    token = self.token()
                    break
        self.signature = signature
        return token

     #
     # Parse a global definition, be it a type, variable or function
     # the extern "C" blocks are a bit nasty and require it to recurse.
     #
    def parseGlobal(self, token):
        static = 0
        if token[1] == 'extern':
            token = self.token()
            if token == None:
                return token
            if token[0] == 'string':
                if token[1] == 'C':
                    token = self.token()
                    if token == None:
                        return token
                    if token[0] == 'sep' and token[1] == "{":
                        token = self.token()
#                         print 'Entering extern "C line ', self.lineno()
                        while token != None and (token[0] != 'sep' or
                              token[1] != "}"):
                            if token[0] == 'name':
                                token = self.parseGlobal(token)
                            else:
                                self.error(
                                 "token %s %s unexpected at the top level" % (
                                        token[0], token[1]))
                                token = self.parseGlobal(token)
#                         print 'Exiting extern "C" line', self.lineno()
                        token = self.token()
                        return token
                else:
                    return token
        elif token[1] == 'static':
            static = 1
            token = self.token()
            if token == None or  token[0] != 'name':
                return token

        if token[1] == 'typedef':
            token = self.token()
            return self.parseTypedef(token)
        else:
            token = self.parseType(token)
            type_orig = self.type
        if token == None or token[0] != "name":
            return token
        type = type_orig
        self.name = token[1]
        token = self.token()
        while token != None and (token[0] == "sep" or token[0] == "op"):
            if token[0] == "sep":
                if token[1] == "[":
                    type = type + token[1]
                    token = self.token()
                    while token != None and (token[0] != "sep" or \
                          token[1] != ";"):
                        type = type + token[1]
                        token = self.token()

            if token != None and token[0] == "op" and token[1] == "=":
                 #
                 # Skip the initialization of the variable
                 #
                token = self.token()
                if token[0] == 'sep' and token[1] == '{':
                    token = self.token()
                    token = self.parseBlock(token)
                else:
                    self.comment = None
                    while token != None and (token[0] != "sep" or \
                          (token[1] != ';' and token[1] != ',')):
                            token = self.token()
                self.comment = None
                if token == None or token[0] != "sep" or (token[1] != ';' and
                   token[1] != ','):
                    self.error("missing ';' or ',' after value")

            if token != None and token[0] == "sep":
                if token[1] == ";":
                    self.comment = None
                    token = self.token()
                    if type == "struct":
                        self.index_add(self.name, self.filename,
                             not self.is_header, "struct", self.struct_fields)
                    else:
                        self.index_add(self.name, self.filename,
                             not self.is_header, "variable", type)
                    break
                elif token[1] == "(":
                    token = self.token()
                    token = self.parseSignature(token)
                    if token == None:
                        return None
                    if token[0] == "sep" and token[1] == ";":
                        d = self.mergeFunctionComment(self.name,
                                ((type, None), self.signature), 1)
                        self.index_add(self.name, self.filename, static,
                                        "function", d)
                        token = self.token()
                    elif token[0] == "sep" and token[1] == "{":
                        d = self.mergeFunctionComment(self.name,
                                ((type, None), self.signature), static)
                        self.index_add(self.name, self.filename, static,
                                        "function", d)
                        token = self.token()
                        token = self.parseBlock(token);
                elif token[1] == ',':
                    self.comment = None
                    self.index_add(self.name, self.filename, static,
                                    "variable", type)
                    type = type_orig
                    token = self.token()
                    while token != None and token[0] == "sep":
                        type = type + token[1]
                        token = self.token()
                    if token != None and token[0] == "name":
                        self.name = token[1]
                        token = self.token()
                else:
                    break

        return token

    def parse(self):
        self.warning("Parsing %s" % (self.filename))
        token = self.token()
        while token != None:
            if token[0] == 'name':
                token = self.parseGlobal(token)
            else:
                self.error("token %s %s unexpected at the top level" % (
                       token[0], token[1]))
                token = self.parseGlobal(token)
                return
        self.parseTopComment(self.top_comment)
        return self.index


class docBuilder:
    """A documentation builder"""
    def __init__(self, name, directories=['.'], excludes=[]):
        self.name = name
        self.directories = directories
        self.excludes = excludes + list(ignored_files.keys())
        self.modules = {}
        self.headers = {}
        self.idx = index()
        self.xref = {}
        self.index = {}
        if name == 'libxml2':
            self.basename = 'libxml'
        else:
            self.basename = name

    def indexString(self, id, str):
        if str == None:
            return
        str = str.replace("'", ' ')
        str = str.replace('"', ' ')
        str = str.replace("/", ' ')
        str = str.replace('*', ' ')
        str = str.replace("[", ' ')
        str = str.replace("]", ' ')
        str = str.replace("(", ' ')
        str = str.replace(")", ' ')
        str = str.replace("<", ' ')
        str = str.replace('>', ' ')
        str = str.replace("&", ' ')
        str = str.replace('#', ' ')
        str = str.replace(",", ' ')
        str = str.replace('.', ' ')
        str = str.replace(';', ' ')
        tokens = str.split()
        for token in tokens:
            try:
                c = token[0]
                if string.ascii_letters.find(c) < 0:
                    pass
                elif len(token) < 3:
                    pass
                else:
                    lower = token.lower()
                    # TODO: generalize this a bit
                    if lower == 'and' or lower == 'the':
                        pass
                    elif token in self.xref:
                        self.xref[token].append(id)
                    else:
                        self.xref[token] = [id]
            except:
                pass

    def analyze(self):
        print("Project %s : %d headers, %d modules" % (self.name, len(list(self.headers.keys())), len(list(self.modules.keys()))))
        self.idx.analyze()

    def scanHeaders(self):
        for header in list(self.headers.keys()):
            parser = CParser(header)
            idx = parser.parse()
            self.headers[header] = idx;
            self.idx.merge(idx)

    def scanModules(self):
        for module in list(self.modules.keys()):
            parser = CParser(module)
            idx = parser.parse()
            # idx.analyze()
            self.modules[module] = idx
            self.idx.merge_public(idx)

    def scan(self):
        for directory in self.directories:
            files = glob.glob(directory + "/*.c")
            for file in files:
                skip = 0
                for excl in self.excludes:
                    if file.find(excl) != -1:
                        print("Skipping %s" % file)
                        skip = 1
                        break
                if skip == 0:
                    self.modules[file] = None;
            files = glob.glob(directory + "/*.h")
            for file in files:
                skip = 0
                for excl in self.excludes:
                    if file.find(excl) != -1:
                        print("Skipping %s" % file)
                        skip = 1
                        break
                if skip == 0:
                    self.headers[file] = None;
        self.scanHeaders()
        self.scanModules()

    def modulename_file(self, file):
        module = os.path.basename(file)
        if module[-2:] == '.h':
            module = module[:-2]
        elif module[-2:] == '.c':
            module = module[:-2]
        return module

    def serialize_enum(self, output, name):
        id = self.idx.enums[name]
        output.write("    <enum name='%s' file='%s'" % (name,
                     self.modulename_file(id.header)))
        if id.info != None:
            info = id.info
            if info[0] != None and info[0] != '':
                try:
                    val = eval(info[0])
                except:
                    val = info[0]
                output.write(" value='%s'" % (val));
            if info[2] != None and info[2] != '':
                output.write(" type='%s'" % info[2]);
            if info[1] != None and info[1] != '':
                output.write(" info='%s'" % escape(info[1]));
        output.write("/>\n")

    def serialize_macro(self, output, name):
        id = self.idx.macros[name]
        output.write("    <macro name='%s' file='%s'>\n" % (name,
                     self.modulename_file(id.header)))
        if id.info != None:
            try:
                (args, desc) = id.info
                if desc != None and desc != "":
                    output.write("      <info>%s</info>\n" % (escape(desc)))
                    self.indexString(name, desc)
                for arg in args:
                    (name, desc) = arg
                    if desc != None and desc != "":
                        output.write("      <arg name='%s' info='%s'/>\n" % (
                                     name, escape(desc)))
                        self.indexString(name, desc)
                    else:
                        output.write("      <arg name='%s'/>\n" % (name))
            except:
                pass
        output.write("    </macro>\n")

    def serialize_typedef(self, output, name):
        id = self.idx.typedefs[name]
        if id.info[0:7] == 'struct ':
            output.write("    <struct name='%s' file='%s' type='%s'" % (
                     name, self.modulename_file(id.header), id.info))
            name = id.info[7:]
            if name in self.idx.structs and ( \
               type(self.idx.structs[name].info) == type(()) or
                type(self.idx.structs[name].info) == type([])):
                output.write(">\n");
                try:
                    for field in self.idx.structs[name].info:
                        desc = field[2]
                        self.indexString(name, desc)
                        if desc == None:
                            desc = ''
                        else:
                            desc = escape(desc)
                        output.write("      <field name='%s' type='%s' info='%s'/>\n" % (field[1] , field[0], desc))
                except:
                    print("Failed to serialize struct %s" % (name))
                output.write("    </struct>\n")
            else:
                output.write("/>\n");
        else :
            output.write("    <typedef name='%s' file='%s' type='%s'" % (
                         name, self.modulename_file(id.header), id.info))
            try:
                desc = id.extra
                if desc != None and desc != "":
                    output.write(">\n      <info>%s</info>\n" % (escape(desc)))
                    output.write("    </typedef>\n")
                else:
                    output.write("/>\n")
            except:
                output.write("/>\n")

    def serialize_variable(self, output, name):
        id = self.idx.variables[name]
        if id.info != None:
            output.write("    <variable name='%s' file='%s' type='%s'/>\n" % (
                    name, self.modulename_file(id.header), id.info))
        else:
            output.write("    <variable name='%s' file='%s'/>\n" % (
                    name, self.modulename_file(id.header)))

    def serialize_function(self, output, name):
        id = self.idx.functions[name]
        if name == debugsym:
            print("=>", id)

        output.write("    <%s name='%s' file='%s' module='%s'>\n" % (id.type,
                     name, self.modulename_file(id.header),
                     self.modulename_file(id.module)))
        #
        # Processing of conditionals modified by Bill 1/1/05
        #
        if id.conditionals != None:
            apstr = ""
            for cond in id.conditionals:
                if apstr != "":
                    apstr = apstr + " &amp;&amp; "
                apstr = apstr + cond
            output.write("      <cond>%s</cond>\n"% (apstr));
        try:
            (ret, params, desc) = id.info
            if (desc == None or desc == '') and \
               name[0:9] != "xmlThrDef" and name != "xmlDllMain":
                print("%s %s from %s has no description" % (id.type, name,
                       self.modulename_file(id.module)))

            output.write("      <info>%s</info>\n" % (escape(desc)))
            self.indexString(name, desc)
            if ret[0] != None:
                if ret[0] == "void":
                    output.write("      <return type='void'/>\n")
                else:
                    output.write("      <return type='%s' info='%s'/>\n" % (
                             ret[0], escape(ret[1])))
                    self.indexString(name, ret[1])
            for param in params:
                if param[0] == 'void':
                    continue
                if param[2] == None:
                    output.write("      <arg name='%s' type='%s' info=''/>\n" % (param[1], param[0]))
                else:
                    output.write("      <arg name='%s' type='%s' info='%s'/>\n" % (param[1], param[0], escape(param[2])))
                    self.indexString(name, param[2])
        except:
            print("Failed to save function %s info: " % name, repr(id.info))
        output.write("    </%s>\n" % (id.type))

    def serialize_exports(self, output, file):
        module = self.modulename_file(file)
        output.write("    <file name='%s'>\n" % (module))
        dict = self.headers[file]
        if dict.info != None:
            for data in ('Summary', 'Description', 'Author'):
                try:
                    output.write("     <%s>%s</%s>\n" % (
                                 data.lower(),
                                 escape(dict.info[data]),
                                 data.lower()))
                except:
                    print("Header %s lacks a %s description" % (module, data))
            if 'Description' in dict.info:
                desc = dict.info['Description']
                if desc.find("DEPRECATED") != -1:
                    output.write("     <deprecated/>\n")

        ids = list(dict.macros.keys())
        ids.sort()
        for id in uniq(ids):
            # Macros are sometime used to masquerade other types.
            if id in dict.functions:
                continue
            if id in dict.variables:
                continue
            if id in dict.typedefs:
                continue
            if id in dict.structs:
                continue
            if id in dict.enums:
                continue
            output.write("     <exports symbol='%s' type='macro'/>\n" % (id))
        ids = list(dict.enums.keys())
        ids.sort()
        for id in uniq(ids):
            output.write("     <exports symbol='%s' type='enum'/>\n" % (id))
        ids = list(dict.typedefs.keys())
        ids.sort()
        for id in uniq(ids):
            output.write("     <exports symbol='%s' type='typedef'/>\n" % (id))
        ids = list(dict.structs.keys())
        ids.sort()
        for id in uniq(ids):
            output.write("     <exports symbol='%s' type='struct'/>\n" % (id))
        ids = list(dict.variables.keys())
        ids.sort()
        for id in uniq(ids):
            output.write("     <exports symbol='%s' type='variable'/>\n" % (id))
        ids = list(dict.functions.keys())
        ids.sort()
        for id in uniq(ids):
            output.write("     <exports symbol='%s' type='function'/>\n" % (id))
        output.write("    </file>\n")

    def serialize_xrefs_files(self, output):
        headers = list(self.headers.keys())
        headers.sort()
        for file in headers:
            module = self.modulename_file(file)
            output.write("    <file name='%s'>\n" % (module))
            dict = self.headers[file]
            ids = uniq(list(dict.functions.keys()) + list(dict.variables.keys()) + \
                  list(dict.macros.keys()) + list(dict.typedefs.keys()) + \
                  list(dict.structs.keys()) + list(dict.enums.keys()))
            ids.sort()
            for id in ids:
                output.write("      <ref name='%s'/>\n" % (id))
            output.write("    </file>\n")
        pass

    def serialize_xrefs_functions(self, output):
        funcs = {}
        for name in list(self.idx.functions.keys()):
            id = self.idx.functions[name]
            try:
                (ret, params, desc) = id.info
                for param in params:
                    if param[0] == 'void':
                        continue
                    if param[0] in funcs:
                        funcs[param[0]].append(name)
                    else:
                        funcs[param[0]] = [name]
            except:
                pass
        typ = list(funcs.keys())
        typ.sort()
        for type in typ:
            if type == '' or type == 'void' or type == "int" or \
               type == "char *" or type == "const char *" :
                continue
            output.write("    <type name='%s'>\n" % (type))
            ids = funcs[type]
            ids.sort()
            pid = ''        # not sure why we have dups, but get rid of them!
            for id in ids:
                if id != pid:
                    output.write("      <ref name='%s'/>\n" % (id))
                    pid = id
            output.write("    </type>\n")

    def serialize_xrefs_constructors(self, output):
        funcs = {}
        for name in list(self.idx.functions.keys()):
            id = self.idx.functions[name]
            try:
                (ret, params, desc) = id.info
                if ret[0] == "void":
                    continue
                if ret[0] in funcs:
                    funcs[ret[0]].append(name)
                else:
                    funcs[ret[0]] = [name]
            except:
                pass
        typ = list(funcs.keys())
        typ.sort()
        for type in typ:
            if type == '' or type == 'void' or type == "int" or \
               type == "char *" or type == "const char *" :
                continue
            output.write("    <type name='%s'>\n" % (type))
            ids = funcs[type]
            ids.sort()
            for id in ids:
                output.write("      <ref name='%s'/>\n" % (id))
            output.write("    </type>\n")

    def serialize_xrefs_alpha(self, output):
        letter = None
        ids = list(self.idx.identifiers.keys())
        ids.sort()
        for id in ids:
            if id[0] != letter:
                if letter != None:
                    output.write("    </letter>\n")
                letter = id[0]
                output.write("    <letter name='%s'>\n" % (letter))
            output.write("      <ref name='%s'/>\n" % (id))
        if letter != None:
            output.write("    </letter>\n")

    def serialize_xrefs_references(self, output):
        typ = list(self.idx.identifiers.keys())
        typ.sort()
        for id in typ:
            idf = self.idx.identifiers[id]
            module = idf.header
            output.write("    <reference name='%s' href='%s'/>\n" % (id,
                         'html/' + self.basename + '-' +
                         self.modulename_file(module) + '.html#' +
                         id))

    def serialize_xrefs_index(self, output):
        index = self.xref
        typ = list(index.keys())
        typ.sort()
        letter = None
        count = 0
        chunk = 0
        chunks = []
        for id in typ:
            if len(index[id]) > 30:
                continue
            if id[0] != letter:
                if letter == None or count > 200:
                    if letter != None:
                        output.write("      </letter>\n")
                        output.write("    </chunk>\n")
                        count = 0
                        chunks.append(["chunk%s" % (chunk -1), first_letter, letter])
                    output.write("    <chunk name='chunk%s'>\n" % (chunk))
                    first_letter = id[0]
                    chunk = chunk + 1
                elif letter != None:
                    output.write("      </letter>\n")
                letter = id[0]
                output.write("      <letter name='%s'>\n" % (letter))
            output.write("        <word name='%s'>\n" % (id))
            tokens = index[id];
            tokens.sort()
            tok = None
            for token in tokens:
                if tok == token:
                    continue
                tok = token
                output.write("          <ref name='%s'/>\n" % (token))
                count = count + 1
            output.write("        </word>\n")
        if letter != None:
            output.write("      </letter>\n")
            output.write("    </chunk>\n")
            if count != 0:
                chunks.append(["chunk%s" % (chunk -1), first_letter, letter])
            output.write("    <chunks>\n")
            for ch in chunks:
                output.write("      <chunk name='%s' start='%s' end='%s'/>\n" % (
                             ch[0], ch[1], ch[2]))
            output.write("    </chunks>\n")

    def serialize_xrefs(self, output):
        output.write("  <references>\n")
        self.serialize_xrefs_references(output)
        output.write("  </references>\n")
        output.write("  <alpha>\n")
        self.serialize_xrefs_alpha(output)
        output.write("  </alpha>\n")
        output.write("  <constructors>\n")
        self.serialize_xrefs_constructors(output)
        output.write("  </constructors>\n")
        output.write("  <functions>\n")
        self.serialize_xrefs_functions(output)
        output.write("  </functions>\n")
        output.write("  <files>\n")
        self.serialize_xrefs_files(output)
        output.write("  </files>\n")
        output.write("  <index>\n")
        self.serialize_xrefs_index(output)
        output.write("  </index>\n")

    def serialize(self):
        filename = "%s-api.xml" % self.name
        print("Saving XML description %s" % (filename))
        output = open(filename, "w")
        output.write('<?xml version="1.0" encoding="ISO-8859-1"?>\n')
        output.write("<api name='%s'>\n" % self.name)
        output.write("  <files>\n")
        headers = list(self.headers.keys())
        headers.sort()
        for file in headers:
            self.serialize_exports(output, file)
        output.write("  </files>\n")
        output.write("  <symbols>\n")
        macros = list(self.idx.macros.keys())
        macros.sort()
        for macro in macros:
            self.serialize_macro(output, macro)
        enums = list(self.idx.enums.keys())
        enums.sort()
        for enum in enums:
            self.serialize_enum(output, enum)
        typedefs = list(self.idx.typedefs.keys())
        typedefs.sort()
        for typedef in typedefs:
            self.serialize_typedef(output, typedef)
        variables = list(self.idx.variables.keys())
        variables.sort()
        for variable in variables:
            self.serialize_variable(output, variable)
        functions = list(self.idx.functions.keys())
        functions.sort()
        for function in functions:
            self.serialize_function(output, function)
        output.write("  </symbols>\n")
        output.write("</api>\n")
        output.close()

        filename = "%s-refs.xml" % self.name
        print("Saving XML Cross References %s" % (filename))
        output = open(filename, "w")
        output.write('<?xml version="1.0" encoding="ISO-8859-1"?>\n')
        output.write("<apirefs name='%s'>\n" % self.name)
        self.serialize_xrefs(output)
        output.write("</apirefs>\n")
        output.close()


def rebuild():
    builder = None
    if glob.glob("parser.c") != [] :
        print("Rebuilding API description for libxml2")
        builder = docBuilder("libxml2", [".", "."],
                             ["xmlwin32version.h", "tst.c"])
    elif glob.glob("../parser.c") != [] :
        print("Rebuilding API description for libxml2")
        builder = docBuilder("libxml2", ["..", "../include/libxml"],
                             ["xmlwin32version.h", "tst.c"])
    elif glob.glob("../libxslt/transform.c") != [] :
        print("Rebuilding API description for libxslt")
        builder = docBuilder("libxslt", ["../libxslt"],
                             ["win32config.h", "libxslt.h", "tst.c"])
    else:
        print("rebuild() failed, unable to guess the module")
        return None
    builder.scan()
    builder.analyze()
    builder.serialize()
    if glob.glob("../libexslt/exslt.c") != [] :
        extra = docBuilder("libexslt", ["../libexslt"], ["libexslt.h"])
        extra.scan()
        extra.analyze()
        extra.serialize()
    return builder

#
# for debugging the parser
#
def parse(filename):
    parser = CParser(filename)
    idx = parser.parse()
    return idx

if __name__ == "__main__":
    if len(sys.argv) > 1:
        debug = 1
        parse(sys.argv[1])
    else:
        rebuild()