summaryrefslogtreecommitdiff
path: root/giscanner/annotationparser.py
blob: c9ff5c2b818e294716fcf39ca374db47fb74e2ae (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
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
# -*- coding: utf-8 -*-
# -*- Mode: Python -*-

# GObject-Introspection - a framework for introspecting GObject libraries
# Copyright (C) 2008-2010 Johan Dahlin
# Copyright (C) 2012-2013 Dieter Verfaillie <dieterv@optionexplicit.be>
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; either version 2
# of the License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
# 02110-1301, USA.
#


'''
GTK-Doc comment block format
----------------------------

A GTK-Doc comment block is built out of multiple parts. Each part can be further
divided into fields which are separated by a colon ("``:``") delimiter.

Known parts and the fields they are constructed from look like the following
(optional fields are enclosed in square brackets)::

    ┌───────────────────────────────────────────────────────────┐
    │ /**                                                       │ ─▷ start token
    ├────────────────────┬──────────────────────────────────────┤
    │  * identifier_name │ [: annotations]                      │ ─▷ identifier part
    ├────────────────────┼─────────────────┬────────────────────┤
    │  * @parameter_name │ [: annotations] │ : description      │ ─▷ parameter part
    ├────────────────────┴─────────────────┴────────────────────┤
    │  *                                                        │ ─▷ comment block description
    │  * comment_block_description                              │
    ├─────────────┬─────────────────┬───────────┬───────────────┤
    │  * tag_name │ [: annotations] │ [: value] │ : description │ ─▷ tag part
    ├─────────────┴─────────────────┴───────────┴───────────────┤
    │  */                                                       │ ─▷ end token
    └───────────────────────────────────────────────────────────┘

There are two conditions that must be met before a comment block is recognized
as a GTK-Doc comment block:

#. The comment block is opened with a GTK-Doc start token ("``/**``")
#. The first line following the start token contains a valid identifier part

Once a GTK-Doc comment block has been identified as such and has been stripped
from its start and end tokens the remaining parts have to be written in a
specific order:

#. There must be exactly 1 `identifier` part on the first line of the
   comment block which consists of:

   * a required `identifier_name` field
   * an optional `annotations` field, optionally spanning multiple lines

#. Zero or more `parameter` parts, each consisting of:

   * a required `parameter_name` field
   * an optional `annotations` field, optionally spanning multiple lines
   * a required `description` field (can be the empty string)

#. One optional `comment block description` part which must begin with at
   least 1 empty line signaling the start of this part.

#. Zero or more `tag` parts, each consisting of:

   * a required `tag_name` field
   * an optional `annotations` field, optionally spanning multiple lines
   * an optional `value` field
   * a required `description` field (can be the empty string)

Additionally, the following restrictions are in effect:

#. Separating parts with an empty line:

   * `identifier` and `parameter` parts cannot be separated from each other by
     an empty line as this would signal the start of the
     `comment block description` part (see above).
   * it is required to separate the `comment block description` part from the
     `identifier` or `parameter` parts with an empty line (see above)
   * `comment block description` and `tag` parts can optionally be separated
     by an empty line

#. Parts and fields cannot span multiple lines, except for:

   * the `comment_block_description` part
   * `parameter description` and `tag description` fields
   * `identifier`, `parameter` and `tag` part `annotations` fields

#. Taking the above restrictions into account, spanning multiple paragraphs is
   limited to the `comment block description` part and `tag description` fields.

Refer to the `GTK-Doc manual`_ for more detailed usage information.

.. _GTK-Doc manual:
        http://developer.gnome.org/gtk-doc-manual/1.18/documenting.html.en
'''

import os
import re
import operator

from operator import ne, gt, lt
from collections import namedtuple, Counter, OrderedDict

from .message import Position, warn, error


# GTK-Doc comment block parts
PART_IDENTIFIER = 0
PART_PARAMETERS = 1
PART_DESCRIPTION = 2
PART_TAGS = 3

# GTK-Doc comment block tags
#   1) Basic GTK-Doc tags.
#      Note: This list cannot be extended unless the GTK-Doc project defines new tags.
TAG_DEPRECATED = 'deprecated'
TAG_RETURNS = 'returns'
TAG_SINCE = 'since'
TAG_STABILITY = 'stability'

GTKDOC_TAGS = [TAG_DEPRECATED,
               TAG_RETURNS,
               TAG_SINCE,
               TAG_STABILITY]

#   2) Deprecated basic GTK-Doc tags.
#      Note: This list cannot be extended unless the GTK-Doc project defines new deprecated tags.
TAG_DESCRIPTION = 'description'
TAG_RETURN_VALUE = 'return value'

DEPRECATED_GTKDOC_TAGS = [TAG_DESCRIPTION,
                          TAG_RETURN_VALUE]

#   3) Deprecated GObject-Introspection tags.
#      Unfortunately, these where accepted by old versions of this module.
TAG_RETURN = 'return'
TAG_RETURNS_VALUE = 'returns value'

DEPRECATED_GI_TAGS = [TAG_RETURN,
                      TAG_RETURNS_VALUE]

#   4) Deprecated GObject-Introspection annotation tags.
#      Accepted by old versions of this module while they should have been
#      annotations on the identifier part instead.
#      Note: This list can not be extended ever again. The GObject-Introspection project is not
#            allowed to invent GTK-Doc tags. Please create new annotations instead.
TAG_ATTRIBUTES = 'attributes'
TAG_GET_VALUE_FUNC = 'get value func'
TAG_REF_FUNC = 'ref func'
TAG_RENAME_TO = 'rename to'
TAG_SET_VALUE_FUNC = 'set value func'
TAG_TRANSFER = 'transfer'
TAG_TYPE = 'type'
TAG_UNREF_FUNC = 'unref func'
TAG_VALUE = 'value'
TAG_VFUNC = 'virtual'

DEPRECATED_GI_ANN_TAGS = [TAG_ATTRIBUTES,
                          TAG_GET_VALUE_FUNC,
                          TAG_REF_FUNC,
                          TAG_RENAME_TO,
                          TAG_SET_VALUE_FUNC,
                          TAG_TRANSFER,
                          TAG_TYPE,
                          TAG_UNREF_FUNC,
                          TAG_VALUE,
                          TAG_VFUNC]

ALL_TAGS = GTKDOC_TAGS + DEPRECATED_GTKDOC_TAGS + DEPRECATED_GI_TAGS + DEPRECATED_GI_ANN_TAGS

# GObject-Introspection annotation start/end tokens
ANN_LPAR = '('
ANN_RPAR = ')'

# GObject-Introspection annotations
#   1) Supported annotations
#      Note: when adding new annotations, GTK-Doc project's gtkdoc-mkdb needs to be modified too!
ANN_ALLOW_NONE = 'allow-none'
ANN_ARRAY = 'array'
ANN_ATTRIBUTES = 'attributes'
ANN_CLOSURE = 'closure'
ANN_CONSTRUCTOR = 'constructor'
ANN_DESTROY = 'destroy'
ANN_ELEMENT_TYPE = 'element-type'
ANN_FOREIGN = 'foreign'
ANN_GET_VALUE_FUNC = 'get-value-func'
ANN_IN = 'in'
ANN_INOUT = 'inout'
ANN_METHOD = 'method'
ANN_NULLABLE = 'nullable'
ANN_OPTIONAL = 'optional'
ANN_NOT = 'not'
ANN_OUT = 'out'
ANN_REF_FUNC = 'ref-func'
ANN_RENAME_TO = 'rename-to'
ANN_SCOPE = 'scope'
ANN_SET_VALUE_FUNC = 'set-value-func'
ANN_SKIP = 'skip'
ANN_TRANSFER = 'transfer'
ANN_TYPE = 'type'
ANN_UNREF_FUNC = 'unref-func'
ANN_VFUNC = 'virtual'
ANN_VALUE = 'value'

GI_ANNS = [ANN_ALLOW_NONE,
           ANN_NULLABLE,
           ANN_OPTIONAL,
           ANN_NOT,
           ANN_ARRAY,
           ANN_ATTRIBUTES,
           ANN_CLOSURE,
           ANN_CONSTRUCTOR,
           ANN_DESTROY,
           ANN_ELEMENT_TYPE,
           ANN_FOREIGN,
           ANN_GET_VALUE_FUNC,
           ANN_IN,
           ANN_INOUT,
           ANN_METHOD,
           ANN_OUT,
           ANN_REF_FUNC,
           ANN_RENAME_TO,
           ANN_SCOPE,
           ANN_SET_VALUE_FUNC,
           ANN_SKIP,
           ANN_TRANSFER,
           ANN_TYPE,
           ANN_UNREF_FUNC,
           ANN_VFUNC,
           ANN_VALUE]

#   2) Deprecated GObject-Introspection annotations
ANN_ATTRIBUTE = 'attribute'
ANN_INOUT_ALT = 'in-out'

DEPRECATED_GI_ANNS = [ANN_ATTRIBUTE,
                      ANN_INOUT_ALT]

ALL_ANNOTATIONS = GI_ANNS + DEPRECATED_GI_ANNS
DICT_ANNOTATIONS = [ANN_ARRAY, ANN_ATTRIBUTES]
LIST_ANNOTATIONS = [ann for ann in ALL_ANNOTATIONS if ann not in DICT_ANNOTATIONS]

# (array) annotation options
OPT_ARRAY_FIXED_SIZE = 'fixed-size'
OPT_ARRAY_LENGTH = 'length'
OPT_ARRAY_ZERO_TERMINATED = 'zero-terminated'

ARRAY_OPTIONS = [OPT_ARRAY_FIXED_SIZE,
                 OPT_ARRAY_LENGTH,
                 OPT_ARRAY_ZERO_TERMINATED]

# (out) annotation options
OPT_OUT_CALLEE_ALLOCATES = 'callee-allocates'
OPT_OUT_CALLER_ALLOCATES = 'caller-allocates'

OUT_OPTIONS = [OPT_OUT_CALLEE_ALLOCATES,
               OPT_OUT_CALLER_ALLOCATES]

# (not) annotation options
OPT_NOT_NULLABLE = 'nullable'

NOT_OPTIONS = [OPT_NOT_NULLABLE]

# (scope) annotation options
OPT_SCOPE_ASYNC = 'async'
OPT_SCOPE_CALL = 'call'
OPT_SCOPE_NOTIFIED = 'notified'

SCOPE_OPTIONS = [OPT_SCOPE_ASYNC,
                 OPT_SCOPE_CALL,
                 OPT_SCOPE_NOTIFIED]

# (transfer) annotation options
OPT_TRANSFER_CONTAINER = 'container'
OPT_TRANSFER_FLOATING = 'floating'
OPT_TRANSFER_FULL = 'full'
OPT_TRANSFER_NONE = 'none'

TRANSFER_OPTIONS = [OPT_TRANSFER_CONTAINER,
                    OPT_TRANSFER_FLOATING,
                    OPT_TRANSFER_FULL,
                    OPT_TRANSFER_NONE]


# Pattern used to normalize different types of line endings
LINE_BREAK_RE = re.compile(r'\r\n|\r|\n', re.UNICODE)

# Pattern matching the start token of a comment block.
COMMENT_BLOCK_START_RE = re.compile(
    r'''
    ^                                                    # start
    (?P<code>.*?)                                        # whitespace, code, ...
    \s*                                                  # 0 or more whitespace characters
    (?P<token>/\*{2}(?![\*/]))                           # 1 forward slash character followed
                                                         #   by exactly 2 asterisk characters
                                                         #   and not followed by a slash character
    \s*                                                  # 0 or more whitespace characters
    (?P<comment>.*?)                                     # GTK-Doc comment text
    \s*                                                  # 0 or more whitespace characters
    $                                                    # end
    ''',
    re.UNICODE | re.VERBOSE)

# Pattern matching the end token of a comment block.
COMMENT_BLOCK_END_RE = re.compile(
    r'''
    ^                                                    # start
    \s*                                                  # 0 or more whitespace characters
    (?P<comment>.*?)                                     # GTK-Doc comment text
    \s*                                                  # 0 or more whitespace characters
    (?P<token>\*+/)                                      # 1 or more asterisk characters followed
                                                         #   by exactly 1 forward slash character
    (?P<code>.*?)                                        # whitespace, code, ...
    \s*                                                  # 0 or more whitespace characters
    $                                                    # end
    ''',
    re.UNICODE | re.VERBOSE)

# Pattern matching the ' * ' at the beginning of every
# line inside a comment block.
COMMENT_ASTERISK_RE = re.compile(
    r'''
    ^                                                    # start
    \s*                                                  # 0 or more whitespace characters
    (?P<comment>.*?)                                     # invalid comment text
    \s*                                                  # 0 or more whitespace characters
    \*                                                   # 1 asterisk character
    \s?                                                  # 0 or 1 whitespace characters
                                                         #   WARNING: removing more than 1
                                                         #   whitespace character breaks
                                                         #   embedded example program indentation
    ''',
    re.UNICODE | re.VERBOSE)

# Pattern matching the indentation level of a line (used
# to get the indentation before and after the ' * ').
INDENTATION_RE = re.compile(
    r'''
    ^
    (?P<indentation>\s*)                                 # 0 or more whitespace characters
    .*
    $
    ''',
    re.UNICODE | re.VERBOSE)

# Pattern matching an empty line.
EMPTY_LINE_RE = re.compile(
    r'''
    ^                                                    # start
    \s*                                                  # 0 or more whitespace characters
    $                                                    # end
    ''',
    re.UNICODE | re.VERBOSE)

# Pattern matching SECTION identifiers.
SECTION_RE = re.compile(
    r'''
    ^                                                    # start
    \s*                                                  # 0 or more whitespace characters
    SECTION                                              # SECTION
    \s*                                                  # 0 or more whitespace characters
    (?P<delimiter>:?)                                    # delimiter
    \s*                                                  # 0 or more whitespace characters
    (?P<section_name>\w\S+?)                             # section name
    \s*                                                  # 0 or more whitespace characters
    :?                                                   # invalid delimiter
    \s*                                                  # 0 or more whitespace characters
    $
    ''',
    re.UNICODE | re.VERBOSE)

# Pattern matching symbol (function, constant, struct and enum) identifiers.
SYMBOL_RE = re.compile(
    r'''
    ^                                                    # start
    \s*                                                  # 0 or more whitespace characters
    (?P<symbol_name>[\w-]*\w)                            # symbol name
    \s*                                                  # 0 or more whitespace characters
    (?P<delimiter>:?)                                    # delimiter
    \s*                                                  # 0 or more whitespace characters
    (?P<fields>.*?)                                      # annotations + description
    \s*                                                  # 0 or more whitespace characters
    :?                                                   # invalid delimiter
    \s*                                                  # 0 or more whitespace characters
    $                                                    # end
    ''',
    re.UNICODE | re.VERBOSE)

# Pattern matching property identifiers.
PROPERTY_RE = re.compile(
    r'''
    ^                                                    # start
    \s*                                                  # 0 or more whitespace characters
    (?P<class_name>[\w]+)                                # class name
    \s*                                                  # 0 or more whitespace characters
    :{1}                                                 # 1 required colon
    \s*                                                  # 0 or more whitespace characters
    (?P<property_name>[\w-]*\w)                          # property name
    \s*                                                  # 0 or more whitespace characters
    (?P<delimiter>:?)                                    # delimiter
    \s*                                                  # 0 or more whitespace characters
    (?P<fields>.*?)                                      # annotations + description
    \s*                                                  # 0 or more whitespace characters
    :?                                                   # invalid delimiter
    \s*                                                  # 0 or more whitespace characters
    $                                                    # end
    ''',
    re.UNICODE | re.VERBOSE)

# Pattern matching signal identifiers.
SIGNAL_RE = re.compile(
    r'''
    ^                                                    # start
    \s*                                                  # 0 or more whitespace characters
    (?P<class_name>[\w]+)                                # class name
    \s*                                                  # 0 or more whitespace characters
    :{2}                                                 # 2 required colons
    \s*                                                  # 0 or more whitespace characters
    (?P<signal_name>[\w-]*\w)                            # signal name
    \s*                                                  # 0 or more whitespace characters
    (?P<delimiter>:?)                                    # delimiter
    \s*                                                  # 0 or more whitespace characters
    (?P<fields>.*?)                                      # annotations + description
    \s*                                                  # 0 or more whitespace characters
    :?                                                   # invalid delimiter
    \s*                                                  # 0 or more whitespace characters
    $                                                    # end
    ''',
    re.UNICODE | re.VERBOSE)

# Pattern matching action identifiers.
ACTION_RE = re.compile(
    r'''
    ^                                                    # start
    \s*                                                  # 0 or more whitespace characters
    (?P<class_name>[\w]+)                                # class name
    \s*                                                  # 0 or more whitespace characters
    \|{1}                                                # 1 required vertical bar
    \s*                                                  # 0 or more whitespace characters
    (?P<action_name>[\w-]+\.[\w-]+)                      # action name
    \s*                                                  # 0 or more whitespace characters
    (?P<delimiter>:?)                                    # delimiter
    \s*                                                  # 0 or more whitespace characters
    (?P<fields>.*?)                                      # annotations + description
    \s*                                                  # 0 or more whitespace characters
    :?                                                   # invalid delimiter
    \s*                                                  # 0 or more whitespace characters
    $                                                    # end
    ''',
    re.UNICODE | re.VERBOSE)

# Pattern matching struct fields.
FIELD_RE = re.compile(
    r'''
    ^                                                    # start
    \s*                                                  # 0 or more whitespace characters
    (?P<class_name>[\w]+)                                # class name
    \s*                                                  # 0 or more whitespace characters
    \.{1}                                                # 1 required dot
    \s*                                                  # 0 or more whitespace characters
    (?P<field_name>[\w-]*\w)                             # field name
    \s*                                                  # 0 or more whitespace characters
    (?P<delimiter>:?)                                    # delimiter
    \s*                                                  # 0 or more whitespace characters
    (?P<fields>.*?)                                      # annotations + description
    \s*                                                  # 0 or more whitespace characters
    :?                                                   # invalid delimiter
    \s*                                                  # 0 or more whitespace characters
    $                                                    # end
    ''',
    re.UNICODE | re.VERBOSE)

# Pattern matching parameters.
PARAMETER_RE = re.compile(
    r'''
    ^                                                    # start
    \s*                                                  # 0 or more whitespace characters
    @                                                    # @ character
    (?P<parameter_name>[\w-]*\w|.*?\.\.\.)               # parameter name
    \s*                                                  # 0 or more whitespace characters
    :{1}                                                 # 1 required delimiter
    \s*                                                  # 0 or more whitespace characters
    (?P<fields>.*?)                                      # annotations + description
    \s*                                                  # 0 or more whitespace characters
    $                                                    # end
    ''',
    re.UNICODE | re.VERBOSE)

# Pattern matching tags.
_all_tags = '|'.join(ALL_TAGS).replace(' ', r'\s')
TAG_RE = re.compile(
    r'''
    ^                                                    # start
    \s*                                                  # 0 or more whitespace characters
    (?P<tag_name>''' + _all_tags + r''')                 # tag name
    \s*                                                  # 0 or more whitespace characters
    :{1}                                                 # 1 required delimiter
    \s*                                                  # 0 or more whitespace characters
    (?P<fields>.*?)                                      # annotations + value + description
    \s*                                                  # 0 or more whitespace characters
    $                                                    # end
    ''',
    re.UNICODE | re.VERBOSE | re.IGNORECASE)

# Pattern matching value and description fields for TAG_DEPRECATED & TAG_SINCE tags.
TAG_VALUE_VERSION_RE = re.compile(
    r'''
    ^                                                    # start
    \s*                                                  # 0 or more whitespace characters
    (?P<value>([0-9\.])*)                                # value
    \s*                                                  # 0 or more whitespace characters
    (?P<delimiter>:?)                                    # delimiter
    \s*                                                  # 0 or more whitespace characters
    (?P<description>.*?)                                 # description
    \s*                                                  # 0 or more whitespace characters
    $                                                    # end
    ''',
    re.UNICODE | re.VERBOSE)

# Pattern matching value and description fields for TAG_STABILITY tags.
TAG_VALUE_STABILITY_RE = re.compile(
    r'''
    ^                                                    # start
    \s*                                                  # 0 or more whitespace characters
    (?P<value>(stable|unstable|private|internal)?)       # value
    \s*                                                  # 0 or more whitespace characters
    (?P<delimiter>:?)                                    # delimiter
    \s*                                                  # 0 or more whitespace characters
    (?P<description>.*?)                                 # description
    \s*                                                  # 0 or more whitespace characters
    $                                                    # end
    ''',
    re.UNICODE | re.VERBOSE | re.IGNORECASE)


class GtkDocAnnotations(OrderedDict):
    '''
    An ordered dictionary mapping annotation names to annotation options (if any). Annotation
    options can be either a :class:`list`, a :class:`giscanner.collections.OrderedDict`
    (depending on the annotation name)or :const:`None`.
    '''

    __slots__ = ('position')

    def __init__(self, *args, **kwargs):
        #: A :class:`giscanner.message.Position` instance specifying the location of the
        #: annotations in the source file or :const:`None`.
        self.position = kwargs.pop('position', None)

        OrderedDict.__init__(self, *args, **kwargs)

    def __copy__(self):
        return GtkDocAnnotations(self, position=self.position)


class GtkDocAnnotatable(object):
    '''
    Base class for GTK-Doc comment block parts that can be annotated.
    '''

    __slots__ = ('position', 'annotations')

    #: A :class:`tuple` of annotation name constants that are valid for this object. Annotation
    #: names not in this :class:`tuple` will be reported as *unknown* by :func:`validate`. The
    #: :attr:`valid_annotations` class attribute should be overridden by subclasses.
    valid_annotations = ()

    def __init__(self, position=None):
        #: A :class:`giscanner.message.Position` instance specifying the location of the
        #: annotatable comment block part in the source file or :const:`None`.
        self.position = position

        #: A :class:`GtkDocAnnotations` instance representing the annotations
        #: applied to this :class:`GtkDocAnnotatable` instance.
        self.annotations = GtkDocAnnotations()

    def __repr__(self):
        return "<GtkDocAnnotatable '%s'>" % (self.annotations, )

    def validate(self):
        '''
        Validate annotations stored by the :class:`GtkDocAnnotatable` instance, if any.
        '''

        if self.annotations:
            position = self.annotations.position

            for ann_name, options in self.annotations.items():
                if ann_name in self.valid_annotations:
                    validate = getattr(self, '_do_validate_' + ann_name.replace('-', '_'))
                    validate(position, ann_name, options)
                elif ann_name in ALL_ANNOTATIONS:
                    # Not error() as ann_name might be valid in some newer
                    # GObject-Instrospection version.
                    warn('unexpected annotation: %s' % (ann_name, ), position)
                else:
                    # Not error() as ann_name might be valid in some newer
                    # GObject-Instrospection version.
                    warn('unknown annotation: %s' % (ann_name, ), position)

                # Validate that (nullable) and (not nullable) are not both
                # present. Same for (allow-none) and (not nullable).
                if ann_name == ANN_NOT and OPT_NOT_NULLABLE in options:
                    if ANN_NULLABLE in self.annotations:
                        warn('cannot have both "%s" and "%s" present' %
                             (ANN_NOT + ' ' + OPT_NOT_NULLABLE, ANN_NULLABLE),
                             position)
                    if ANN_ALLOW_NONE in self.annotations:
                        warn('cannot have both "%s" and "%s" present' %
                             (ANN_NOT + ' ' + OPT_NOT_NULLABLE, ANN_ALLOW_NONE),
                             position)

    def _validate_options(self, position, ann_name, n_options, expected_n_options, operator,
                          message):
        '''
        Validate the number of options held by an annotation according to the test
        ``operator(n_options, expected_n_options)``.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param n_options: number of options held by the annotation
        :param expected_n_options: number of expected options
        :param operator: an operator function from python's :mod:`operator` module, for example
                         :func:`operator.ne` or :func:`operator.lt`
        :param message: warning message used when the test
                        ``operator(n_options, expected_n_options)`` fails.
        '''

        if n_options == 0:
            t = 'none'
        else:
            t = '%d' % (n_options, )

        if expected_n_options == 0:
            s = 'no options'
        elif expected_n_options == 1:
            s = 'one option'
        else:
            s = '%d options' % (expected_n_options, )

        if operator(n_options, expected_n_options):
            warn('"%s" annotation %s %s, %s given' % (ann_name, message, s, t), position)

    def _validate_annotation(self, position, ann_name, options, choices=None,
                             exact_n_options=None, min_n_options=None, max_n_options=None):
        '''
        Validate an annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to be validated
        :param choices: an iterable of allowed option names or :const:`None` to skip this test
        :param exact_n_options: exact number of expected options or :const:`None` to skip this test
        :param min_n_options: minimum number of expected options or :const:`None` to skip this test
        :param max_n_options: maximum number of expected options or :const:`None` to skip this test
        '''

        n_options = len(options)

        if exact_n_options is not None:
            self._validate_options(position,
                                   ann_name, n_options, exact_n_options, ne, 'needs')

        if min_n_options is not None:
            self._validate_options(position,
                                   ann_name, n_options, min_n_options, lt, 'takes at least')

        if max_n_options is not None:
            self._validate_options(position,
                                   ann_name, n_options, max_n_options, gt, 'takes at most')

        if options and choices is not None:
            option = options[0]
            if option not in choices:
                warn('invalid "%s" annotation option: "%s"' % (ann_name, option), position)

    def _do_validate_allow_none(self, position, ann_name, options):
        '''
        Validate the ``(allow-none)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options held by the annotation
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=0)

    def _do_validate_array(self, position, ann_name, options):
        '''
        Validate the ``(array)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options held by the annotation
        '''

        if len(options) == 0:
            return

        for option, value in options.items():
            if option == OPT_ARRAY_FIXED_SIZE:
                try:
                    int(value)
                except (TypeError, ValueError):
                    if value is None:
                        warn('"%s" annotation option "%s" needs a value' % (ann_name, option),
                             position)
                    else:
                        warn('invalid "%s" annotation option "%s" value "%s", must be an integer' %
                             (ann_name, option, value),
                             position)
            elif option == OPT_ARRAY_ZERO_TERMINATED:
                if value is not None and value not in ['0', '1']:
                    warn('invalid "%s" annotation option "%s" value "%s", must be 0 or 1' %
                         (ann_name, option, value),
                         position)
            elif option == OPT_ARRAY_LENGTH:
                if value is None:
                    warn('"%s" annotation option "length" needs a value' % (ann_name, ),
                         position)
            else:
                warn('invalid "%s" annotation option: "%s"' % (ann_name, option),
                     position)

    def _do_validate_attributes(self, position, ann_name, options):
        '''
        Validate the ``(attributes)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        # The 'attributes' annotation allows free form annotations.
        pass

    def _do_validate_closure(self, position, ann_name, options):
        '''
        Validate the ``(closure)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        self._validate_annotation(position, ann_name, options, max_n_options=1)

    def _do_validate_constructor(self, position, ann_name, options):
        '''
        Validate the ``(constructor)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=0)

    def _do_validate_destroy(self, position, ann_name, options):
        '''
        Validate the ``(destroy)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=1)

    def _do_validate_element_type(self, position, ann_name, options):
        '''
        Validate the ``(element)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        self._validate_annotation(position, ann_name, options, min_n_options=1, max_n_options=2)

    def _do_validate_foreign(self, position, ann_name, options):
        '''
        Validate the ``(foreign)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=0)

    def _do_validate_get_value_func(self, position, ann_name, options):
        '''
        Validate the ``(value-func)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=1)

    def _do_validate_in(self, position, ann_name, options):
        '''
        Validate the ``(in)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=0)

    def _do_validate_inout(self, position, ann_name, options):
        '''
        Validate the ``(in-out)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=0)

    def _do_validate_method(self, position, ann_name, options):
        '''
        Validate the ``(method)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=0)

    def _do_validate_nullable(self, position, ann_name, options):
        '''
        Validate the ``(nullable)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options held by the annotation
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=0)

    def _do_validate_optional(self, position, ann_name, options):
        '''
        Validate the ``(optional)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options held by the annotation
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=0)

    def _do_validate_not(self, position, ann_name, options):
        '''
        Validate the ``(not)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options held by the annotation
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=1,
                                  choices=NOT_OPTIONS)

    def _do_validate_out(self, position, ann_name, options):
        '''
        Validate the ``(out)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        self._validate_annotation(position, ann_name, options, max_n_options=1,
                                  choices=OUT_OPTIONS)

    def _do_validate_ref_func(self, position, ann_name, options):
        '''
        Validate the ``(ref-func)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=1)

    def _do_validate_rename_to(self, position, ann_name, options):
        '''
        Validate the ``(rename-to)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=1)

    def _do_validate_scope(self, position, ann_name, options):
        '''
        Validate the ``(scope)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=1,
                                  choices=SCOPE_OPTIONS)

    def _do_validate_set_value_func(self, position, ann_name, options):
        '''
        Validate the ``(value-func)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=1)

    def _do_validate_skip(self, position, ann_name, options):
        '''
        Validate the ``(skip)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=0)

    def _do_validate_transfer(self, position, ann_name, options):
        '''
        Validate the ``(transfer)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=1,
                                  choices=TRANSFER_OPTIONS)

    def _do_validate_type(self, position, ann_name, options):
        '''
        Validate the ``(type)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=1)

    def _do_validate_unref_func(self, position, ann_name, options):
        '''
        Validate the ``(unref-func)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=1)

    def _do_validate_value(self, position, ann_name, options):
        '''
        Validate the ``(value)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=1)

    def _do_validate_virtual(self, position, ann_name, options):
        '''
        Validate the ``(virtual)`` annotation.

        :param position: :class:`giscanner.message.Position` of the line in the source file
                         containing the annotation to be validated
        :param ann_name: name of the annotation holding the options to validate
        :param options: annotation options to validate
        '''

        self._validate_annotation(position, ann_name, options, exact_n_options=1)


class GtkDocParameter(GtkDocAnnotatable):
    '''
    Represents a GTK-Doc parameter part.
    '''

    __slots__ = ('name', 'description')

    valid_annotations = (ANN_ALLOW_NONE, ANN_ARRAY, ANN_ATTRIBUTES, ANN_CLOSURE, ANN_DESTROY,
                         ANN_ELEMENT_TYPE, ANN_IN, ANN_INOUT, ANN_OUT, ANN_SCOPE, ANN_SKIP,
                         ANN_TRANSFER, ANN_TYPE, ANN_OPTIONAL, ANN_NULLABLE, ANN_NOT)

    def __init__(self, name, position=None):
        GtkDocAnnotatable.__init__(self, position)

        #: Parameter name.
        self.name = name

        #: Parameter description or :const:`None`.
        self.description = None

    def __repr__(self):
        return "<GtkDocParameter '%s' %r>" % (self.name, self.annotations)


class GtkDocTag(GtkDocAnnotatable):
    '''
    Represents a GTK-Doc tag part.
    '''

    __slots__ = ('name', 'value', 'description')

    valid_annotations = (ANN_ALLOW_NONE, ANN_ARRAY, ANN_ATTRIBUTES, ANN_ELEMENT_TYPE, ANN_SKIP,
                         ANN_TRANSFER, ANN_TYPE, ANN_NULLABLE, ANN_OPTIONAL, ANN_NOT)

    def __init__(self, name, position=None):
        GtkDocAnnotatable.__init__(self, position)

        #: Tag name.
        self.name = name

        #: Tag value or :const:`None`.
        self.value = None

        #: Tag description or :const:`None`.
        self.description = None

    def __repr__(self):
        return "<GtkDocTag '%s' %r>" % (self.name, self.annotations)


class GtkDocCommentBlock(GtkDocAnnotatable):
    '''
    Represents a GTK-Doc comment block.
    '''

    __slots__ = ('code_before', 'code_after', 'indentation',
                 'name', 'params', 'description', 'tags')

    #: Valid annotation names for the GTK-Doc comment block identifier part.
    valid_annotations = (ANN_ATTRIBUTES, ANN_CONSTRUCTOR, ANN_FOREIGN, ANN_GET_VALUE_FUNC,
                         ANN_METHOD, ANN_REF_FUNC, ANN_RENAME_TO, ANN_SET_VALUE_FUNC,
                         ANN_SKIP, ANN_TRANSFER, ANN_TYPE, ANN_UNREF_FUNC, ANN_VALUE, ANN_VFUNC)

    def __init__(self, name, position=None):
        GtkDocAnnotatable.__init__(self, position)

        #: Code preceding the GTK-Doc comment block start token ("``/**``"), if any.
        self.code_before = None

        #: Code following the GTK-Doc comment block end token ("``*/``"), if any.
        self.code_after = None

        #: List of indentation levels (preceding the "``*``") for all lines in the comment
        #: block's source text.
        self.indentation = []

        #: Identifier name.
        self.name = name

        #: Ordered dictionary mapping parameter names to :class:`GtkDocParameter` instances
        #: applied to this :class:`GtkDocCommentBlock`.
        self.params = OrderedDict()

        #: The GTK-Doc comment block description part.
        self.description = None

        #: Ordered dictionary mapping tag names to :class:`GtkDocTag` instances
        #: applied to this :class:`GtkDocCommentBlock`.
        self.tags = OrderedDict()

    def _compare(self, other, op):
        # Note: This is used by g-ir-annotation-tool, which does a ``sorted(blocks.values())``,
        #       meaning that keeping this around makes update-glib-annotations.py patches
        #       easier to review.
        return op(self.name, other.name)

    def __lt__(self, other):
        return self._compare(other, operator.lt)

    def __gt__(self, other):
        return self._compare(other, operator.gt)

    def __ge__(self, other):
        return self._compare(other, operator.ge)

    def __le__(self, other):
        return self._compare(other, operator.le)

    def __eq__(self, other):
        return self._compare(other, operator.eq)

    def __ne__(self, other):
        return self._compare(other, operator.ne)

    def __hash__(self):
        return hash(self.name)

    def __repr__(self):
        return "<GtkDocCommentBlock '%s' %r>" % (self.name, self.annotations)

    def validate(self):
        '''
        Validate annotations applied to the :class:`GtkDocCommentBlock` identifier, parameters
        and tags.
        '''
        GtkDocAnnotatable.validate(self)

        for param in self.params.values():
            param.validate()

        for tag in self.tags.values():
            tag.validate()


#: Result object returned by :class:`GtkDocCommentBlockParser`._parse_annotations()
_ParseAnnotationsResult = namedtuple('Result', ['success', 'annotations', 'annotations_changed',
                                                'start_pos', 'end_pos'])

#: Result object returned by :class:`GtkDocCommentBlockParser`._parse_fields()
_ParseFieldsResult = namedtuple('Result', ['success', 'annotations', 'annotations_changed',
                                           'description'])


class GtkDocCommentBlockParser(object):
    '''
    Parse GTK-Doc comment blocks into a parse tree built out of :class:`GtkDocCommentBlock`,
    :class:`GtkDocParameter`, :class:`GtkDocTag` and :class:`GtkDocAnnotations`
    objects. This parser tries to accept malformed input whenever possible and does
    not cause the process to exit on syntax errors. It does however emit:

        * warning messages at the slightest indication of recoverable malformed input and
        * error messages for unrecoverable malformed input

    whenever possible. Recoverable, in this context, means that we can serialize the
    :class:`GtkDocCommentBlock` instance using a :class:`GtkDocCommentBlockWriter` without
    information being lost. It is usually a good idea to heed these warning and error messages
    as malformed input can result in both:

        * invalid GTK-Doc output (HTML, pdf, ...) when the comment blocks are parsed
          with GTK-Doc's gtkdoc-mkdb
        * unexpected introspection behavior, for example missing parameters in the
          generated .gir and .typelib files

    .. NOTE:: :class:`GtkDocCommentBlockParser` functionality is based on gtkdoc-mkdb's
        `ScanSourceFile()`_ function.

    .. _ScanSourceFile():
           http://git.gnome.org/browse/gtk-doc/tree/gtkdoc-mkdb.in#n3722
    '''

    def parse_comment_blocks(self, comments):
        '''
        Parse multiple GTK-Doc comment blocks.

        :param comments: an iterable of ``(comment, filename, lineno)`` tuples
        :returns: a dictionary mapping identifier names to :class:`GtkDocCommentBlock` objects
        '''

        comment_blocks = {}

        for (comment, filename, lineno) in comments:
            try:
                comment_block = self.parse_comment_block(comment, filename, lineno)
            except Exception as e:
                error('unrecoverable parse error, please file a GObject-Introspection bug'
                      'report including the complete comment block at the indicated location. %s' %
                      str(e),
                      Position(filename, lineno))
                continue

            if comment_block is not None:
                # Note: previous versions of this parser did not check if an identifier was
                #       already stored in comment_blocks, so when different comment blocks where
                #       encountered documenting the same identifier the last comment block seen
                #       "wins". Keep this behavior for backwards compatibility, but emit a warning.
                if comment_block.name in comment_blocks:
                    firstseen = comment_blocks[comment_block.name]
                    path = os.path.dirname(firstseen.position.filename)
                    warn('multiple comment blocks documenting \'%s:\' identifier '
                         '(already seen at %s).' %
                         (comment_block.name, firstseen.position.format(path)),
                         comment_block.position)

                comment_blocks[comment_block.name] = comment_block

        return comment_blocks

    def parse_comment_block(self, comment, filename, lineno):
        '''
        Parse a single GTK-Doc comment block.

        :param comment: string representing the GTK-Doc comment block including it's
                        start ("``/**``") and end ("``*/``") tokens.
        :param filename: source file name where the comment block originated from
        :param lineno: line number in the source file where the comment block starts
        :returns: a :class:`GtkDocCommentBlock` object or ``None``
        '''

        code_before = ''
        code_after = ''
        comment_block_pos = Position(filename, lineno)
        comment_lines = re.sub(LINE_BREAK_RE, '\n', comment).split('\n')
        comment_lines_len = len(comment_lines)

        # Check for the start of the comment block.
        result = COMMENT_BLOCK_START_RE.match(comment_lines[0])
        if result:
            # Skip single line comment blocks
            if comment_lines_len == 1:
                position = Position(filename, lineno)
                error('Skipping invalid GTK-Doc comment block:',
                     position, None, result.end('code'), comment_lines[0])
                return None

            code_before = result.group('code')
            comment = result.group('comment')

            if code_before:
                position = Position(filename, lineno)
                warn('GTK-Doc comment block start token "/**" should not be preceded by code:',
                     position, None, result.end('code'), comment_lines[0])

            if comment:
                position = Position(filename, lineno)
                warn('GTK-Doc comment block start token "/**" should '
                     'not be followed by comment text:',
                     position, None, result.start('comment'), comment_lines[0])

                comment_lines[0] = comment
            else:
                del comment_lines[0]
        else:
            # Not a GTK-Doc comment block.
            return None

        # Check for the end of the comment block.
        result = COMMENT_BLOCK_END_RE.match(comment_lines[-1])
        if result:
            code_after = result.group('code')
            comment = result.group('comment')
            if code_after:
                position = Position(filename, lineno + comment_lines_len - 1)
                warn('GTK-Doc comment block end token "*/" should '
                     'not be followed by code:',
                     position, None, result.end('code'), comment_lines[-1])

            if comment:
                position = Position(filename, lineno + comment_lines_len - 1)
                warn('GTK-Doc comment block end token "*/" should '
                     'not be preceded by comment text:',
                     position, None, result.end('comment'), comment_lines[-1])

                comment_lines[-1] = comment
            else:
                del comment_lines[-1]
        else:
            # Not a GTK-Doc comment block.
            return None

        # If we get this far, we must be inside something
        # that looks like a GTK-Doc comment block.
        comment_block = None
        identifier_warned = False
        block_indent = []
        line_indent = None
        part_indent = None
        in_part = None
        current_part = None
        returns_seen = False

        for line in comment_lines:
            lineno += 1
            position = Position(filename, lineno)

            # Store the original line (without \n) and column offset
            # so we can generate meaningful warnings later on.
            original_line = line
            column_offset = 0

            # Store indentation level of the comment (before the ' * ')
            result = INDENTATION_RE.match(line)
            block_indent.append(result.group('indentation'))

            # Get rid of the ' * ' at the start of the line.
            result = COMMENT_ASTERISK_RE.match(line)
            if result:
                comment = result.group('comment')
                if comment:
                    error('invalid comment text:',
                          position, None, result.start('comment'), original_line)

                column_offset = result.end(0)
                line = line[result.end(0):]

            # Store indentation level of the line (after the ' * ').
            result = INDENTATION_RE.match(line)
            line_indent = len(result.group('indentation').replace('\t', '  '))

            ####################################################################
            # Check for GTK-Doc comment block identifier.
            ####################################################################
            if comment_block is None:
                result = SECTION_RE.match(line)

                if result:
                    # Some projects use kebab-case or CamelCase for section
                    # names. Convert them all to flat case so we can match
                    # them easily later on.
                    identifier_name = 'SECTION:%s' % (result.group('section_name')
                                                            .replace("-", "")
                                                            .lower(), )
                    identifier_delimiter = None
                    identifier_fields = None
                    identifier_fields_start = None
                else:
                    result = PROPERTY_RE.match(line)

                    if result:
                        identifier_name = '%s:%s' % (result.group('class_name'),
                                                     result.group('property_name'))
                        identifier_delimiter = result.group('delimiter')
                        identifier_fields = result.group('fields')
                        identifier_fields_start = result.start('fields')
                    else:
                        result = SIGNAL_RE.match(line)

                        if result:
                            identifier_name = '%s::%s' % (result.group('class_name'),
                                                          result.group('signal_name'))
                            identifier_delimiter = result.group('delimiter')
                            identifier_fields = result.group('fields')
                            identifier_fields_start = result.start('fields')
                        else:
                            result = ACTION_RE.match(line)

                            if result:
                                identifier_name = 'ACTION:%s:%s' % (result.group('class_name'),
                                                                        result.group('action_name'))
                                identifier_delimiter = None
                                identifier_fields = None
                                identifier_fields_start = None
                            else:
                                result = FIELD_RE.match(line)

                                if result:
                                    identifier_name = '%s.%s' % (result.group('class_name'),
                                                                  result.group('field_name'))
                                    identifier_delimiter = result.group('delimiter')
                                    identifier_fields = result.group('fields')
                                    identifier_fields_start = result.start('fields')
                                else:
                                    result = SYMBOL_RE.match(line)

                                    if result:
                                        identifier_name = '%s' % (result.group('symbol_name'), )
                                        identifier_delimiter = result.group('delimiter')
                                        identifier_fields = result.group('fields')
                                        identifier_fields_start = result.start('fields')

                if result:
                    in_part = PART_IDENTIFIER
                    part_indent = line_indent

                    comment_block = GtkDocCommentBlock(identifier_name, comment_block_pos)
                    comment_block.code_before = code_before
                    comment_block.code_after = code_after

                    if identifier_fields:
                        res = self._parse_annotations(position,
                                                      column_offset + identifier_fields_start,
                                                      original_line,
                                                      identifier_fields)

                        if res.success:
                            if identifier_fields[res.end_pos:].strip():
                                # Not an identifier due to invalid trailing description field
                                result = None
                                in_part = None
                                part_indent = None
                                comment_block = None
                            else:
                                comment_block.annotations = res.annotations

                                if not identifier_delimiter and res.annotations:
                                    marker_pos = column_offset + result.start('delimiter')
                                    warn('missing ":" at column %s:' % (marker_pos + 1, ),
                                         position, None, marker_pos, original_line)

                if not result:
                    # Emit a single warning when the identifier is not found on the first line
                    if not identifier_warned:
                        identifier_warned = True
                        error('identifier not found on the first line:',
                              position, None, column_offset, original_line)
                continue

            ####################################################################
            # Check for comment block parameters.
            ####################################################################
            result = PARAMETER_RE.match(line)
            if result:
                part_indent = line_indent
                param_name = result.group('parameter_name')
                param_name_lower = param_name.lower()
                param_fields = result.group('fields')
                param_fields_start = result.start('fields')
                marker_pos = result.start('parameter_name') + column_offset

                if in_part not in [PART_IDENTIFIER, PART_PARAMETERS]:
                    warn('"@%s" parameter unexpected at this location:' % (param_name, ),
                         position, None, marker_pos, original_line)

                in_part = PART_PARAMETERS

                if param_name_lower == TAG_RETURNS:
                    # Deprecated return value as parameter instead of tag
                    param_name = TAG_RETURNS

                    if not returns_seen:
                        returns_seen = True
                    else:
                        error('encountered multiple "Returns" parameters or tags for "%s".' %
                              (comment_block.name, ),
                              position)

                    tag = GtkDocTag(TAG_RETURNS, position)

                    if param_fields:
                        result = self._parse_fields(position,
                                                    column_offset + param_fields_start,
                                                    original_line,
                                                    param_fields)
                        if result.success:
                            tag.annotations = result.annotations
                            tag.description = result.description
                    comment_block.tags[TAG_RETURNS] = tag
                    current_part = tag
                    continue
                elif (param_name == 'Varargs'
                or (param_name.endswith('...') and param_name != '...')):
                    # Deprecated @Varargs notation or named __VA_ARGS__ instead of @...
                    warn('"@%s" parameter is deprecated, please use "@..." instead:' %
                         (param_name, ),
                         position, None, marker_pos, original_line)
                    param_name = '...'

                if param_name in comment_block.params.keys():
                    error('multiple "@%s" parameters for identifier "%s":' %
                          (param_name, comment_block.name),
                          position, None, marker_pos, original_line)

                parameter = GtkDocParameter(param_name, position)

                if param_fields:
                    result = self._parse_fields(position,
                                                column_offset + param_fields_start,
                                                original_line,
                                                param_fields)
                    if result.success:
                        parameter.annotations = result.annotations
                        parameter.description = result.description

                comment_block.params[param_name] = parameter
                current_part = parameter
                continue

            ####################################################################
            # Check for comment block description.
            #
            # When we are parsing parameter parts or the identifier part (when
            # there are no parameters) and encounter an empty line, we must be
            # parsing the comment block description.
            #
            # Note: it is unclear why GTK-Doc does not allow paragraph breaks
            #       at this location as those might be handy describing
            #       parameters from time to time...
            ####################################################################
            if (EMPTY_LINE_RE.match(line) and in_part in [PART_IDENTIFIER, PART_PARAMETERS]):
                in_part = PART_DESCRIPTION
                part_indent = line_indent
                continue

            ####################################################################
            # Check for GTK-Doc comment block tags.
            ####################################################################
            result = TAG_RE.match(line)
            if result and line_indent <= part_indent:
                part_indent = line_indent
                tag_name = result.group('tag_name')
                tag_name_lower = tag_name.lower()
                tag_fields = result.group('fields')
                tag_fields_start = result.start('fields')
                marker_pos = result.start('tag_name') + column_offset

                if tag_name_lower in DEPRECATED_GI_ANN_TAGS:
                    # Deprecated GObject-Introspection specific tags.
                    # Emit a warning and transform these into annotations on the identifier
                    # instead, as agreed upon in http://bugzilla.gnome.org/show_bug.cgi?id=676133
                    warn('GObject-Introspection specific GTK-Doc tag "%s" '
                         'has been deprecated, please use annotations on the identifier '
                         'instead:' % (tag_name, ),
                         position, None, marker_pos, original_line)

                    # Translate deprecated tag name into corresponding annotation name
                    ann_name = tag_name_lower.replace(' ', '-')

                    if tag_name_lower == TAG_ATTRIBUTES:
                        transformed = ''
                        result = self._parse_fields(position,
                                                    result.start('tag_name') + column_offset,
                                                    line,
                                                    tag_fields.strip(),
                                                    None,
                                                    False,
                                                    False)

                        if result.success:
                            for annotation in result.annotations:
                                ann_options = self._parse_annotation_options_list(position,
                                                                                  marker_pos,
                                                                                  line,
                                                                                  annotation)
                                n_options = len(ann_options)
                                if n_options == 1:
                                    transformed = '%s %s' % (transformed, ann_options[0], )
                                elif n_options == 2:
                                    transformed = '%s %s=%s' % (transformed, ann_options[0],
                                                                ann_options[1])
                                else:
                                    # Malformed Attributes: tag
                                    error('malformed "Attributes:" tag will be ignored:',
                                          position, None, marker_pos, original_line)
                                    transformed = None

                            if transformed:
                                transformed = '%s %s' % (ann_name, transformed.strip())
                                ann_name, docannotation = self._parse_annotation(
                                    position,
                                    column_offset + tag_fields_start,
                                    original_line,
                                    transformed)
                                stored_annotation = comment_block.annotations.get('attributes')
                                if stored_annotation:
                                    error('Duplicate "Attributes:" annotation will '
                                          'be ignored:',
                                          position, None, marker_pos, original_line)
                                else:
                                    comment_block.annotations[ann_name] = docannotation
                    else:
                        ann_name, options = self._parse_annotation(position,
                                                               column_offset + tag_fields_start,
                                                               line,
                                                               '%s %s' % (ann_name, tag_fields))
                        comment_block.annotations[ann_name] = options

                    continue
                elif tag_name_lower == TAG_DESCRIPTION:
                    # Deprecated GTK-Doc Description: tag
                    warn('GTK-Doc tag "Description:" has been deprecated:',
                         position, None, marker_pos, original_line)

                    in_part = PART_DESCRIPTION

                    if comment_block.description is None:
                        comment_block.description = tag_fields
                    else:
                        comment_block.description += '\n%s' % (tag_fields, )
                    continue

                # Now that the deprecated stuff is out of the way, continue parsing real tags
                if (in_part == PART_DESCRIPTION
                or (in_part == PART_PARAMETERS and not comment_block.description)
                or (in_part == PART_IDENTIFIER and not comment_block.params and not
                comment_block.description)):
                    in_part = PART_TAGS

                if in_part != PART_TAGS:
                    in_part = PART_TAGS
                    warn('"%s:" tag unexpected at this location:' % (tag_name, ),
                         position, None, marker_pos, original_line)

                if tag_name_lower in [TAG_RETURN, TAG_RETURNS,
                                      TAG_RETURN_VALUE, TAG_RETURNS_VALUE]:
                    if not returns_seen:
                        returns_seen = True
                    else:
                        error('encountered multiple return value parameters or tags for "%s".' %
                              (comment_block.name, ),
                              position)

                    tag = GtkDocTag(TAG_RETURNS, position)

                    if tag_fields:
                        result = self._parse_fields(position,
                                                    column_offset + tag_fields_start,
                                                    original_line,
                                                    tag_fields)
                        if result.success:
                            tag.annotations = result.annotations
                            tag.description = result.description

                    comment_block.tags[TAG_RETURNS] = tag
                    current_part = tag
                    continue
                else:
                    if tag_name_lower in comment_block.tags.keys():
                        error('multiple "%s:" tags for identifier "%s":' %
                              (tag_name, comment_block.name),
                              position, None, marker_pos, original_line)

                    tag = GtkDocTag(tag_name_lower, position)

                    if tag_fields:
                        result = self._parse_fields(position,
                                                    column_offset + tag_fields_start,
                                                    original_line,
                                                    tag_fields)
                        if result.success:
                            if result.annotations:
                                error('annotations not supported for tag "%s:".' % (tag_name, ),
                                      position)

                            if tag_name_lower in [TAG_DEPRECATED, TAG_SINCE]:
                                result = TAG_VALUE_VERSION_RE.match(result.description)
                                tag.value = result.group('value')
                                tag.description = result.group('description')
                            elif tag_name_lower == TAG_STABILITY:
                                result = TAG_VALUE_STABILITY_RE.match(result.description)
                                tag.value = result.group('value').capitalize()
                                tag.description = result.group('description')

                    comment_block.tags[tag_name_lower] = tag
                    current_part = tag
                    continue

            ####################################################################
            # If we get here, we must be in the middle of a multiline
            # comment block, parameter or tag description.
            ####################################################################
            if EMPTY_LINE_RE.match(line) is None:
                line = line.rstrip()

            if in_part in [PART_IDENTIFIER, PART_DESCRIPTION]:
                if not comment_block.description:
                    if in_part == PART_IDENTIFIER:
                        r = self._parse_annotations(position, column_offset, original_line, line,
                                                    comment_block.annotations)

                        if r.success and r.annotations_changed:
                            comment_block.annotations = r.annotations
                            continue
                if comment_block.description is None:
                    comment_block.description = line
                else:
                    comment_block.description += '\n' + line
                continue
            elif in_part in [PART_PARAMETERS, PART_TAGS]:
                if not current_part.description:
                    r = self._parse_fields(position, column_offset, original_line, line,
                                           current_part.annotations)
                    if r.success and r.annotations_changed:
                        current_part.annotations = r.annotations
                        current_part.description = r.description
                        continue
                if current_part.description is None:
                    current_part.description = line
                else:
                    current_part.description += '\n' + line
                continue

        ########################################################################
        # Finished parsing this comment block.
        ########################################################################
        if comment_block:
            # We have picked up a couple of \n characters that where not
            # intended. Strip those.
            if comment_block.description:
                comment_block.description = comment_block.description.strip()

            for tag in comment_block.tags.values():
                self._clean_description_field(tag)

            for param in comment_block.params.values():
                self._clean_description_field(param)

            comment_block.indentation = block_indent
            comment_block.validate()
            return comment_block
        else:
            return None

    def _clean_description_field(self, part):
        '''
        Remove extraneous leading and trailing whitespace from description fields.

        :param part: a GTK-Doc comment block part having a description field
        '''

        if part.description:
            if part.description.strip() == '':
                part.description = None
            else:
                if EMPTY_LINE_RE.match(part.description.split('\n', 1)[0]):
                    part.description = part.description.rstrip()
                else:
                    part.description = part.description.strip()

    def _parse_annotation_options_list(self, position, column, line, options):
        '''
        Parse annotation options into a list. For example::

            ┌──────────────────────────────────────────────────────────────┐
            │ 'option1 option2 option3'                                    │ ─▷ source
            ├──────────────────────────────────────────────────────────────┤
            │ ['option1', 'option2', 'option3']                            │ ◁─ parsed options
            └──────────────────────────────────────────────────────────────┘

        :param position: :class:`giscanner.message.Position` of `line` in the source file
        :param column: start column of the `options` in the source file
        :param line: complete source line
        :param options: annotation options to parse
        :returns: a list of annotation options
        '''

        parsed = []

        if options:
            result = options.find('=')
            if result >= 0:
                warn('invalid annotation options: expected a "list" but '
                     'received "key=value pairs":',
                     position, None, column + result, line)
                parsed = self._parse_annotation_options_unknown(position, column, line, options)
            else:
                parsed = options.split(' ')

        return parsed

    def _parse_annotation_options_dict(self, position, column, line, options):
        '''
        Parse annotation options into a dict. For example::

            ┌──────────────────────────────────────────────────────────────┐
            │ 'option1=value1 option2 option3=value2'                      │ ─▷ source
            ├──────────────────────────────────────────────────────────────┤
            │ {'option1': 'value1', 'option2': None, 'option3': 'value2'}  │ ◁─ parsed options
            └──────────────────────────────────────────────────────────────┘

        :param position: :class:`giscanner.message.Position` of `line` in the source file
        :param column: start column of the `options` in the source file
        :param line: complete source line
        :param options: annotation options to parse
        :returns: an ordered dictionary of annotation options
        '''

        parsed = OrderedDict()

        if options:
            for p in options.split(' '):
                parts = p.split('=', 1)
                key = parts[0]
                value = parts[1] if len(parts) == 2 else None
                parsed[key] = value

        return parsed

    def _parse_annotation_options_unknown(self, position, column, line, options):
        '''
        Parse annotation options into a list holding a single item. This is used when the
        annotation options to parse in not known to be a list nor dict. For example::

            ┌──────────────────────────────────────────────────────────────┐
            │ '   option1 option2   option3=value1   '                     │ ─▷ source
            ├──────────────────────────────────────────────────────────────┤
            │ ['option1 option2   option3=value1']                         │ ◁─ parsed options
            └──────────────────────────────────────────────────────────────┘

        :param position: :class:`giscanner.message.Position` of `line` in the source file
        :param column: start column of the `options` in the source file
        :param line: complete source line
        :param options: annotation options to parse
        :returns: a list of annotation options
        '''

        if options:
            return [options.strip()]

    def _parse_annotation(self, position, column, line, annotation):
        '''
        Parse an annotation into the annotation name and a list or dict (depending on the
        name of the annotation) holding the options. For example::

            ┌──────────────────────────────────────────────────────────────┐
            │ 'name opt1=value1 opt2=value2 opt3'                          │ ─▷ source
            ├──────────────────────────────────────────────────────────────┤
            │ 'name', {'opt1': 'value1', 'opt2':'value2', 'opt3':None}     │ ◁─ parsed annotation
            └──────────────────────────────────────────────────────────────┘

            ┌──────────────────────────────────────────────────────────────┐
            │ 'name   opt1 opt2'                                           │ ─▷ source
            ├──────────────────────────────────────────────────────────────┤
            │ 'name', ['opt1', 'opt2']                                     │ ◁─ parsed annotation
            └──────────────────────────────────────────────────────────────┘

            ┌──────────────────────────────────────────────────────────────┐
            │ 'unkownname   unknown list of options'                       │ ─▷ source
            ├──────────────────────────────────────────────────────────────┤
            │ 'unkownname', ['unknown list of options']                    │ ◁─ parsed annotation
            └──────────────────────────────────────────────────────────────┘

        :param position: :class:`giscanner.message.Position` of `line` in the source file
        :param column: start column of the `annotation` in the source file
        :param line: complete source line
        :param annotation: annotation to parse
        :returns: a tuple containing the annotation name and options
        '''

        # Transform deprecated type syntax "tokens"
        annotation = annotation.replace('<', ANN_LPAR).replace('>', ANN_RPAR)

        parts = annotation.split(' ', 1)
        ann_name = parts[0].lower()
        ann_options = parts[1] if len(parts) == 2 else None

        if ann_name == ANN_INOUT_ALT:
            warn('"%s" annotation has been deprecated, please use "%s" instead:' %
                 (ANN_INOUT_ALT, ANN_INOUT),
                 position, None, column, line)

            ann_name = ANN_INOUT
        elif ann_name == ANN_ATTRIBUTE:
            warn('"%s" annotation has been deprecated, please use "%s" instead:' %
                 (ANN_ATTRIBUTE, ANN_ATTRIBUTES),
                 position, None, column, line)

            ann_name = ANN_ATTRIBUTES
            ann_options = self._parse_annotation_options_list(position, column, line, ann_options)
            n_options = len(ann_options)
            if n_options == 1:
                ann_options = ann_options[0]
            elif n_options == 2:
                ann_options = '%s=%s' % (ann_options[0], ann_options[1])
            else:
                error('malformed "(attribute)" annotation will be ignored:',
                      position, None, column, line)
                return None, None

        column += len(ann_name) + 2

        if ann_name in LIST_ANNOTATIONS:
            ann_options = self._parse_annotation_options_list(position, column, line, ann_options)
        elif ann_name in DICT_ANNOTATIONS:
            ann_options = self._parse_annotation_options_dict(position, column, line, ann_options)
        else:
            ann_options = self._parse_annotation_options_unknown(position, column, line,
                                                                 ann_options)

        return ann_name, ann_options

    def _parse_annotations(self, position, column, line, fields,
                           annotations=None, parse_options=True):
        '''
        Parse annotations into a :class:`GtkDocAnnotations` object.

        :param position: :class:`giscanner.message.Position` of `line` in the source file
        :param column: start column of the `annotations` in the source file
        :param line: complete source line
        :param fields: string containing the fields to parse
        :param annotations: a :class:`GtkDocAnnotations` object
        :param parse_options: whether options will be parsed into a :class:`GtkDocAnnotations`
                              object or into a :class:`list`
        :returns: if `parse_options` evaluates to True a :class:`GtkDocAnnotations` object,
                  a :class:`list` otherwise. If `line` does not contain any annotations,
                  :const:`None`
        '''

        if parse_options:
            if annotations is None:
                parsed_annotations = GtkDocAnnotations(position=position)
            else:
                parsed_annotations = annotations.copy()
        else:
            parsed_annotations = []

        parsed_annotations_changed = False

        i = 0
        parens_level = 0
        prev_char = ''
        char_buffer = []
        start_pos = 0
        end_pos = 0

        for i, cur_char in enumerate(fields):
            cur_char_is_space = cur_char.isspace()

            if cur_char == ANN_LPAR:
                parens_level += 1

                if parens_level == 1:
                    start_pos = i

                if prev_char == ANN_LPAR:
                    error('unexpected parentheses, annotations will be ignored:',
                          position, None, column + i, line)
                    return _ParseAnnotationsResult(False, None, None, None, None)
                elif parens_level > 1:
                    char_buffer.append(cur_char)
            elif cur_char == ANN_RPAR:
                parens_level -= 1

                if prev_char == ANN_LPAR:
                    error('unexpected parentheses, annotations will be ignored:',
                          position, None, column + i, line)
                    return _ParseAnnotationsResult(False, None, None, None, None)
                elif parens_level < 0:
                    error('unbalanced parentheses, annotations will be ignored:',
                          position, None, column + i, line)
                    return _ParseAnnotationsResult(False, None, None, None, None)
                elif parens_level == 0:
                    end_pos = i + 1

                    if parse_options is True:
                        name, options = self._parse_annotation(position,
                                                               column + start_pos,
                                                               line,
                                                               ''.join(char_buffer).strip())
                        if name is not None:
                            if name in parsed_annotations:
                                error('multiple "%s" annotations:' % (name, ),
                                      position, None, column + i, line)
                            parsed_annotations[name] = options
                            parsed_annotations_changed = True
                    else:
                        parsed_annotations.append(''.join(char_buffer).strip())
                        parsed_annotations_changed = True

                    char_buffer = []
                else:
                    char_buffer.append(cur_char)
            elif cur_char_is_space:
                if parens_level > 0:
                    char_buffer.append(cur_char)
            else:
                if parens_level == 0:
                    break
                else:
                    char_buffer.append(cur_char)

            prev_char = cur_char

        if parens_level > 0:
            error('unbalanced parentheses, annotations will be ignored:',
                  position, None, column + i, line)
            return _ParseAnnotationsResult(False, None, None, None, None)
        else:
            return _ParseAnnotationsResult(True, parsed_annotations, parsed_annotations_changed,
                                           start_pos, end_pos)

    def _parse_fields(self, position, column, line, fields, annotations=None,
                      parse_options=True, validate_description_field=True):
        '''
        Parse annotations out of field data. For example::

            ┌──────────────────────────────────────────────────────────────┐
            │ '(skip): description of some parameter'                      │ ─▷ source
            ├──────────────────────────────────────────────────────────────┤
            │ ({'skip': []}, 'description of some parameter')              │ ◁─ annotations and
            └──────────────────────────────────────────────────────────────┘    remaining fields

        :param position: :class:`giscanner.message.Position` of `line` in the source file
        :param column: start column of `fields` in the source file
        :param line: complete source line
        :param fields: string containing the fields to parse
        :param parse_options: whether options will be parsed into a :class:`GtkDocAnnotations`
                              object or into a :class:`list`
        :param validate_description_field: :const:`True` to validate the description field
        :returns: if `parse_options` evaluates to True a :class:`GtkDocAnnotations` object,
                  a :class:`list` otherwise. If `line` does not contain any annotations,
                  :const:`None` and a string holding the remaining fields
        '''
        description_field = ''
        result = self._parse_annotations(position, column, line, fields,
                                         annotations, parse_options)
        if result.success:
            description_field = fields[result.end_pos:].strip()

            if description_field and validate_description_field:
                if description_field.startswith(':'):
                    description_field = description_field[1:]
                else:
                    if result.end_pos > 0:
                        marker_pos = column + result.end_pos
                        warn('missing ":" at column %s:' % (marker_pos + 1, ),
                             position, None, marker_pos, line)

        return _ParseFieldsResult(result.success, result.annotations, result.annotations_changed,
                                  description_field)


class GtkDocCommentBlockWriter(object):
    '''
    Serialized :class:`GtkDocCommentBlock` objects into GTK-Doc comment blocks.
    '''

    def __init__(self, indent=True):
        #: :const:`True` if the original indentation preceding the "``*``" needs to be retained,
        #: :const:`False` otherwise. Default value is :const:`True`.
        self.indent = indent

    def _serialize_annotations(self, annotations):
        '''
        Serialize an annotation field. For example::

            ┌──────────────────────────────────────────────────────────────┐
            │ {'name': {'opt1': 'value1', 'opt2':'value2', 'opt3':None}    │ ◁─ GtkDocAnnotations
            ├──────────────────────────────────────────────────────────────┤
            │ '(name opt1=value1 opt2=value2 opt3)'                        │ ─▷ serialized
            └──────────────────────────────────────────────────────────────┘

            ┌──────────────────────────────────────────────────────────────┐
            │ {'name': ['opt1', 'opt2']}                                   │ ◁─ GtkDocAnnotations
            ├──────────────────────────────────────────────────────────────┤
            │ '(name opt1 opt2)'                                           │ ─▷ serialized
            └──────────────────────────────────────────────────────────────┘

            ┌──────────────────────────────────────────────────────────────┐
            │ {'unkownname': ['unknown list of options']}                  │ ◁─ GtkDocAnnotations
            ├──────────────────────────────────────────────────────────────┤
            │ '(unkownname unknown list of options)'                       │ ─▷ serialized
            └──────────────────────────────────────────────────────────────┘

        :param annotations: :class:`GtkDocAnnotations` to be serialized
        :returns: a string
        '''

        serialized = []

        for ann_name, options in annotations.items():
            if options:
                if isinstance(options, list):
                    serialize_options = ' '.join(options)
                else:
                    serialize_options = ''

                    for key, value in options.items():
                        if value:
                            serialize_options += '%s=%s ' % (key, value)
                        else:
                            serialize_options += '%s ' % (key, )

                    serialize_options = serialize_options.strip()

                serialized.append('(%s %s)' % (ann_name, serialize_options))
            else:
                serialized.append('(%s)' % (ann_name, ))

        return ' '.join(serialized)

    def _serialize_parameter(self, parameter):
        '''
        Serialize a parameter.

        :param parameter: :class:`GtkDocParameter` to be serialized
        :returns: a string
        '''

        # parameter_name field
        serialized = '@%s' % (parameter.name, )

        # annotations field
        if parameter.annotations:
            serialized += ': ' + self._serialize_annotations(parameter.annotations)

        # description field
        if parameter.description:
            if parameter.description.startswith('\n'):
                serialized += ':' + parameter.description
            else:
                serialized += ': ' + parameter.description
        else:
            serialized += ':'

        return serialized.split('\n')

    def _serialize_tag(self, tag):
        '''
        Serialize a tag.

        :param tag: :class:`GtkDocTag` to be serialized
        :returns: a string
        '''

        # tag_name field
        serialized = tag.name.capitalize()

        # annotations field
        if tag.annotations:
            serialized += ': ' + self._serialize_annotations(tag.annotations)

        # value field
        if tag.value:
            serialized += ': ' + tag.value

        # description field
        if tag.description:
            if tag.description.startswith('\n'):
                serialized += ':' + tag.description
            else:
                serialized += ': ' + tag.description

        if not tag.value and not tag.description:
            serialized += ':'

        return serialized.split('\n')

    def write(self, block):
        '''
        Serialize a :class:`GtkDocCommentBlock` object.

        :param block: :class:`GtkDocCommentBlock` to be serialized
        :returns: a string
        '''

        if block is None:
            return ''
        else:
            lines = []

            # Identifier part
            if block.name.startswith('SECTION') or block.name.startswith('ACTION'):
                lines.append(block.name)
            else:
                if block.annotations:
                    annotations = self._serialize_annotations(block.annotations)
                    lines.append('%s: %s' % (block.name, annotations))
                else:
                    # Note: this delimiter serves no purpose other than most people being used
                    #       to reading/writing it. It is completely legal to ommit this.
                    lines.append('%s:' % (block.name, ))

            # Parameter parts
            for param in block.params.values():
                lines.extend(self._serialize_parameter(param))

            # Comment block description part
            if block.description:
                lines.append('')
                for l in block.description.split('\n'):
                    lines.append(l)

            # Tag parts
            if block.tags:
                # Note: this empty line servers no purpose other than most people being used
                #       to reading/writing it. It is completely legal to ommit this.
                lines.append('')
                for tag in block.tags.values():
                    lines.extend(self._serialize_tag(tag))

            # Restore comment block indentation and *
            if self.indent:
                indent = Counter(block.indentation).most_common(1)[0][0] or ' '
                if indent.endswith('\t'):
                    start_indent = indent
                    line_indent = indent + ' '
                else:
                    start_indent = indent[:-1]
                    line_indent = indent
            else:
                start_indent = ''
                line_indent = ' '

            i = 0
            while i < len(lines):
                line = lines[i]
                if line:
                    lines[i] = '%s* %s\n' % (line_indent, line)
                else:
                    lines[i] = '%s*\n' % (line_indent, )
                i += 1

            # Restore comment block start and end tokens
            lines.insert(0, '%s/**\n' % (start_indent, ))
            lines.append('%s*/\n' % (line_indent, ))

            # Restore code before and after comment block start and end tokens
            if block.code_before:
                lines.insert(0, '%s\n' % (block.code_before, ))

            if block.code_after:
                lines.append('%s\n' % (block.code_after, ))

            return ''.join(lines)