summaryrefslogtreecommitdiff
path: root/helpcontent2/to-wiki/wikiconv2.py
blob: 837ffebf2ec39ac3b50ce8190640612567ef045b (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
#!/usr/bin/env python

import os, sys, thread, threading, time
import xml.parsers.expat
import codecs
from threading import Thread

root="source/"
max_threads = 25

titles = []

# map of id -> localized text
localization_data = {}

# to collect a list of pages that will be redirections to the pages with nice
# names
redirects = []

# to collect images that we will up-load later
images = set()

# various types of paragraphs
replace_paragraph_role = \
    {'start':{'code': '<code>',
              'codeintip': '<code>',
              'emph' : '', # must be empty to be able to strip empty <emph/>
              'example': '<code>',
              'heading1': '= ',
              'heading2': '== ',
              'heading3': '=== ',
              'heading4': '==== ',
              'heading5': '===== ',
              'heading6': '====== ',
              'head1': '= ', # used only in one file, probably in error?
              'head2': '== ', # used only in one file, probably in error?
              'listitem': '',
              'note': '{{Note|',
              'null': '', # special paragraph for Variable, CaseInline, etc.
              'paragraph': '',
              'related': '', # used only in one file, probably in error?
              'relatedtopics': '', # used only in one file, probably in error?
              'tablecontent': '| ',
              'tablecontentcode': '| <code>',
              'tablehead': '! scope="col" | ',
              'tablenextpara': '\n',
              'tablenextparacode': '\n<code>',
              'tip': '{{Tip|',
              'variable': '',
              'warning': '{{Warning|',
             },
     'end':{'code': '</code>\n\n',
            'codeintip': '</code>\n\n',
            'emph' : '',
            'example': '</code>\n\n',
            'heading1': ' =\n\n',
            'heading2': ' ==\n\n',
            'heading3': ' ===\n\n',
            'heading4': ' ====\n\n',
            'heading5': ' =====\n\n',
            'heading6': ' ======\n\n',
            'head1': ' =\n\n', # used only in one file, probably in error?
            'head2': ' ==\n\n', # used only in one file, probably in error?
            'listitem': '',
            'note': '}}\n\n',
            'null': '', # special paragraph for Variable, CaseInline, etc.
            'paragraph': '\n\n',
            'related': '\n\n', # used only in one file, probably in error?
            'relatedtopics': '\n\n', # used only in one file, probably in error?
            'tablecontent': '\n',
            'tablecontentcode': '</code>\n',
            'tablehead': '\n',
            'tablenextpara': '\n',
            'tablenextparacode': '</code>\n',
            'tip': '}}\n\n',
            'variable': '',
            'warning': '}}\n\n',
           },
     'templ':{'code': False,
              'codeintip': False,
              'emph' : False,
              'example': False,
              'heading1': False,
              'heading2': False,
              'heading3': False,
              'heading4': False,
              'heading5': False,
              'heading6': False,
              'head1': False,
              'head2': False,
              'listitem': False,
              'note': True,
              'null': False,
              'paragraph': False,
              'related': False,
              'relatedtopics': False,
              'tablecontent': False,
              'tablecontentcode': False,
              'tablehead': False,
              'tablenextpara': False,
              'tablenextparacode': False,
              'tip': True,
              'variable': False,
              'warning': True,
           }
    }

section_id_mapping = \
    {'relatedtopics': 'RelatedTopics'}

# text snippets that we need to convert
replace_text_list = \
    [["$[officename]", "{{ProductName}}"],
     ["%PRODUCTNAME", "{{ProductName}}"],
     ["$PRODUCTNAME", "{{ProductName}}"]
    ]

def get_link_filename(link, name):
    text = link.strip()
    fragment = ''
    if text.find('http') == 0:
        text = name
    else:
        f = text.find('#')
        if f >= 0:
            fragment = text[f:]
            text = text[0:f]

    for title in titles:
        try:
            if title[0].find(text) >= 0:
                return (title[1].strip(), fragment)
        except:
            pass
    return (link, '')

def replace_text(text):
    for i in replace_text_list:
        if text.find(i[0]) >= 0:
            text = text.replace(i[0],i[1])
    return text

# modify the text so that in templates like {{Name|something}}, the 'something'
# does not look like template params
def escape_equals_sign(text):
    depth = 0
    t = ''
    for i in text:
        if i == '=':
            if depth == 0:
                t = t + '&#61;'
            else:
                t = t + '='
        else:
            t = t + i
            if i == '{' or i == '[' or i == '<':
                depth = depth + 1
            elif i == '}' or i == ']' or i == '>':
                depth = depth - 1
                if depth < 0:
                    depth = 0

    return t

def load_localization_data(sdf_file):
    global localization_data
    localization_data = {}
    try:
        file = codecs.open(sdf_file, "r", "utf-8")
    except:
        sys.stderr.write('Error: Cannot open .sdf file "%s"\n'% sdf_file)
        return False

    for line in file:
        line = line.strip()
        if line[0] == '#':
            continue
        spl = line.split("\t")

        # the form of the key is like
        # source/text/shared/explorer/database/02010100.xhp#hd_id3149233
        # otherwise we are getting duplicates
        key = '%s#%s'% (spl[1].replace('\\', '/'), spl[4])
        try:
            localization_data[key] = spl[10]
        except:
            sys.stderr.write('Warning: Ignored line "%s"\n'% line.encode('utf-8'))

    file.close()
    return True

def unescape(str):
    unescape_map = {'<': {True:'<', False:'&lt;'},
                    '>': {True:'>', False:'&gt;'},
                    '&': {True:'&', False:'&amp;'},
                    '"': {True:'"', False:'"'}}
    result = ''
    escape = False
    for c in str:
        if c == '\\':
            if escape:
                result = result + '\\'
                escape = False
            else:
                escape = True
        else:
            try:
                replace = unescape_map[c]
                result = result + replace[escape]
            except:
                result = result + c
            escape = False

    return result

def get_localized_text(filename, id):
    try:
        str = localization_data['%s#%s'% (filename, id)]
    except:
        return ''

    return unescape(str)

def href_to_fname_id(href):
    link = href.replace('"', '')
    fname = link
    id = ''
    if link.find("#") >= 0:
        fname = link[:link.find("#")]
        id = link[link.find("#")+1:]
    else:
        sys.stderr.write('Reference without a "#" in "%s".'% link)

    return [fname, id]

# Base class for all the elements
#
# self.name - name of the element, to drop the self.child_parsing flag
# self.objects - collects the child objects that are constructed during
#                parsing of the child elements
# self.child_parsing - flag whether we are parsing a child, or the object
#                      itself
# self.parent - parent object
class ElementBase:
    def __init__(self, name, parent):
        self.name = name
        self.objects = []
        self.child_parsing = False
        self.parent = parent

    def start_element(self, parser, name, attrs):
        pass

    def end_element(self, parser, name):
        if name == self.name:
            self.parent.child_parsing = False

    def char_data(self, parser, data):
        pass

    def get_curobj(self):
        if self.child_parsing:
            return self.objects[len(self.objects)-1].get_curobj()
        return self

    # start parsing a child element
    def parse_child(self, child):
        self.child_parsing = True
        self.objects.append(child)

    # construct the wiki representation of this object, including the objects
    # held in self.objects (here only the text of the objects)
    def get_all(self):
        text = u''
        for i in self.objects:
            text = text + i.get_all()
        return text

    # for handling variables, and embedding in general
    # id - the variable name we want to get
    def get_variable(self, id):
        for i in self.objects:
            if i != None:
                var = i.get_variable(id)
                if var != None:
                    return var
        return None

    # embed part of another file into current structure
    def embed_href(self, parent_parser, fname, id):
        # parse another xhp
        parser = XhpParser('source/' + fname, False, \
                parent_parser.current_app, parent_parser.wiki_page_name, \
                parent_parser.lang)
        var = parser.get_variable(id)

        if var != None:
            try:
                if var.role == 'variable':
                    var.role = 'paragraph'
            except:
                pass
            self.objects.append(var)
        elif parser.follow_embed:
            sys.stderr.write('Cannot find reference "#%s" in "%s".\n'% \
                    (id, fname))

    def unhandled_element(self, parser, name):
        sys.stderr.write('Warning: Unhandled element "%s" in "%s" (%s)\n'% \
                        (name, self.name, parser.filename))

# Base class for trivial elements that operate on char_data
#
# Like <comment>, or <title>
class TextElementBase(ElementBase):
    def __init__(self, attrs, parent, element_name, start, end, templ):
        ElementBase.__init__(self, element_name, parent)
        self.text = u''
        self.start = start
        self.end = end
        self.templ = templ

    def char_data(self, parser, data):
        self.text = self.text + data

    def get_all(self):
        if self.templ:
            return self.start + escape_equals_sign(replace_text(self.text)) + self.end
        else:
            return self.start + replace_text(self.text) + self.end

class XhpFile(ElementBase):
    def __init__(self):
        ElementBase.__init__(self, None, None)

    def start_element(self, parser, name, attrs):
        if name == 'body':
            # ignored, we flatten the structure
            pass
        elif name == 'bookmark':
            self.parse_child(Bookmark(attrs, self, 'div', parser))
        elif name == 'comment':
            self.parse_child(Comment(attrs, self))
        elif name == 'embed' or name == 'embedvar':
            if parser.follow_embed:
                (fname, id) = href_to_fname_id(attrs['href'])
                self.embed_href(parser, fname, id)
        elif name == 'helpdocument':
            # ignored, we flatten the structure
            pass
        elif name == 'list':
            self.parse_child(List(attrs, self))
        elif name == 'meta':
            self.parse_child(Meta(attrs, self))
        elif name == 'paragraph':
            parser.parse_paragraph(attrs, self)
        elif name == 'section':
            self.parse_child(Section(attrs, self))
        elif name == 'sort':
            self.parse_child(Sort(attrs, self))
        elif name == 'switch':
            self.parse_child(Switch(attrs, self, parser.embedding_app))
        elif name == 'table':
            self.parse_child(Table(attrs, self))
        else:
            self.unhandled_element(parser, name)

class Bookmark(ElementBase):
    def __init__(self, attrs, parent, type, parser):
        ElementBase.__init__(self, 'bookmark', parent)

        self.type = type

        self.id = attrs['id']
        self.app = ''
        self.redirect = ''
        self.target = ''
        self.authoritative = False

        # let's construct the name of the redirect, so that we can point
        # to the wikihelp directly from the LO code; wiki then takes care of
        # the correct redirect
        branch = attrs['branch']
        if branch.find('hid/') == 0 and (parser.current_app_raw != '' or parser.follow_embed):
            name = branch[branch.find('/') + 1:]

            self.app = parser.current_app_raw
            self.target = parser.wiki_page_name
            self.authoritative = parser.follow_embed
            self.redirect = name

    def get_all(self):
        global redirects
        # first of all, we need to create a redirect page for this one
        if self.redirect != '' and self.target != '':
            redirects.append([self.app, self.redirect, \
                '%s#%s'% (self.target, self.id), \
                self.authoritative])

        # then we also have to setup ID inside the page
        if self.type == 'div':
            return '<div id="%s"></div>\n'% self.id
        elif self.type == 'span':
            return '<span id="%s"></span>'% self.id
        else:
            sys.stderr.write('Unknown bookmark type "%s"'% self.type)

        return ''

class Image(ElementBase):
    def __init__(self, attrs, parent):
        ElementBase.__init__(self, 'image', parent)
        self.src     = attrs['src']
        try:
            self.width   = attrs['width']
            self.height  = attrs['height']
        except:
            self.width = self.height = ""
        self.align   = 'left'
        self.alt     = False
        self.alttext = ""

    def start_element(self, parser, name, attrs):
        if name == 'alt':
            self.alt = True
        else:
            self.unhandled_element(parser, name)

    def end_element(self, parser, name):
        ElementBase.end_element(self, parser, name)

        if name == 'alt':
            self.alt = False

    def char_data(self, parser, data):
        if self.alt:
            self.alttext = self.alttext + data

    def get_all(self):
        global images
        images.add(self.src)

        name = self.src[self.src.rfind('/') + 1:]
        wikitext = "[[Image:"+name+"|border|"+self.align+"|"
        if len(self.width):
            wikitext = wikitext + self.width+"x"+self.height+"|"
        wikitext = wikitext + self.alttext+"]]"
        return wikitext

    def get_curobj(self):
        return self

class Br(TextElementBase):
    def __init__(self, attrs, parent):
        TextElementBase.__init__(self, attrs, parent, 'br', '<br/>', '', False)

class Comment(TextElementBase):
    def __init__(self, attrs, parent):
        TextElementBase.__init__(self, attrs, parent, 'comment', '<!-- ', ' -->', False)

class HelpIdMissing(TextElementBase):
    def __init__(self, attrs, parent):
        TextElementBase.__init__(self, attrs, parent, 'help-id-missing', '{{MissingHelpId}}', '', False)

class Text:
    def __init__(self, text):
        self.wikitext = replace_text(text)

    def get_all(self):
        return self.wikitext

    def get_variable(self, id):
        return None

class TableCell(ElementBase):
    def __init__(self, attrs, parent):
        ElementBase.__init__(self, 'tablecell', parent)
        self.cellHasChildElement = False

    def start_element(self, parser, name, attrs):
        self.cellHasChildElement = True
        if name == 'bookmark':
            self.parse_child(Bookmark(attrs, self, 'div', parser))
        elif name == 'comment':
            self.parse_child(Comment(attrs, self))
        elif name == 'embed' or name == 'embedvar':
            (fname, id) = href_to_fname_id(attrs['href'])
            if parser.follow_embed:
                self.embed_href(parser, fname, id)
        elif name == 'paragraph':
            parser.parse_localized_paragraph(TableContentParagraph(attrs, self), attrs, self)
        elif name == 'section':
            self.parse_child(Section(attrs, self))
        else:
            self.unhandled_element(parser, name)

    def get_all(self):
        text = ''
        if not self.cellHasChildElement: # an empty element
            if self.parent.isTableHeader: # get from TableRow Element
                role = 'tablehead'
            else:
                role = 'tablecontent'
            text = text + replace_paragraph_role['start'][role]
            text = text + replace_paragraph_role['end'][role]
        text = text + ElementBase.get_all(self)
        return text

class TableRow(ElementBase):
    def __init__(self, attrs, parent):
        ElementBase.__init__(self, 'tablerow', parent)

    def start_element(self, parser, name, attrs):
        if name == 'tablecell':
            self.parse_child(TableCell(attrs, self))
        else:
            self.unhandled_element(parser, name)

    def get_all(self):
        text = '|-\n' + ElementBase.get_all(self)
        return text

class Table(ElementBase):
    def __init__(self, attrs, parent):
        ElementBase.__init__(self, 'table', parent)

    def start_element(self, parser, name, attrs):
        if name == 'comment':
            self.parse_child(Comment(attrs, self))
        elif name == 'tablerow':
            self.parse_child(TableRow(attrs, self))
        else:
            self.unhandled_element(parser, name)

    def get_all(self):
        # + ' align="left"' etc.?
        text = '{| class="wikitable"\n' + \
            ElementBase.get_all(self) + \
            '|}\n\n'
        return text

class ListItem(ElementBase):
    def __init__(self, attrs, parent):
        ElementBase.__init__(self, 'listitem', parent)

    def start_element(self, parser, name, attrs):
        if name == 'bookmark':
            self.parse_child(Bookmark(attrs, self, 'span', parser))
        elif name == 'embed' or name == 'embedvar':
            (fname, id) = href_to_fname_id(attrs['href'])
            if parser.follow_embed:
                self.embed_href(parser, fname, id)
        elif name == 'paragraph':
            parser.parse_localized_paragraph(ListItemParagraph(attrs, self), attrs, self)
        else:
            self.unhandled_element(parser, name)

    def get_all(self):
        text = '*'
        postfix = '\n'
        if self.parent.startwith > 0:
            text = '<li>'
            postfix = '</li>'
        elif self.parent.type == 'ordered':
            text = '#'

        # add the text itself
        linebreak = False
        for i in self.objects:
            if linebreak:
                text = text + '<br/>'
            text = text + i.get_all()
            linebreak = True

        return text + postfix

class List(ElementBase):
    def __init__(self, attrs, parent):
        ElementBase.__init__(self, 'list', parent)

        self.type = attrs['type']
        try:
            self.startwith = int(attrs['startwith'])
        except:
            self.startwith = 0

    def start_element(self, parser, name, attrs):
        if name == 'listitem':
            self.parse_child(ListItem(attrs, self))
        else:
            self.unhandled_element(parser, name)

    def get_all(self):
        text = ""
        if self.startwith > 0:
            text = text + '<ol start="%d">\n'% self.startwith

        text = text + ElementBase.get_all(self)

        if self.startwith > 0:
            text = text + '\n</ol>\n'
        else:
            text = text + '\n'
        return text

# To handle elements that should be completely ignored
class Ignore(ElementBase):
    def __init__(self, attrs, parent, element_name):
        ElementBase.__init__(self, element_name, parent)

class OrigTitle(TextElementBase):
    def __init__(self, attrs, parent):
        TextElementBase.__init__(self, attrs, parent, 'title', '{{OrigLang|', '}}\n', True)

class Title(TextElementBase):
    def __init__(self, attrs, parent, localized_title):
        TextElementBase.__init__(self, attrs, parent, 'title', '{{Lang|', '}}\n', True)
        self.localized_title = localized_title

    def get_all(self):
        if self.localized_title != '':
            self.text = self.localized_title
        return TextElementBase.get_all(self)

class Topic(ElementBase):
    def __init__(self, attrs, parent):
        ElementBase.__init__(self, 'topic', parent)

    def start_element(self, parser, name, attrs):
        if name == 'title':
            if parser.lang == '':
                self.parse_child(OrigTitle(attrs, self))
            else:
                self.parse_child(Title(attrs, self, get_localized_text(parser.filename, 'tit')))
        elif name == 'filename':
            self.parse_child(Ignore(attrs, self, name))
        else:
            self.unhandled_element(parser, name)

class Meta(ElementBase):
    def __init__(self, attrs, parent):
        ElementBase.__init__(self, 'meta', parent)

    def start_element(self, parser, name, attrs):
        if name == 'topic':
            self.parse_child(Topic(attrs, self))
        elif name == 'history' or name == 'lastedited':
            self.parse_child(Ignore(attrs, self, name))
        else:
            self.unhandled_element(parser, name)

class Section(ElementBase):
    def __init__(self, attrs, parent):
        ElementBase.__init__(self, 'section', parent)
        self.id = attrs['id']

    def start_element(self, parser, name, attrs):
        if name == 'bookmark':
            self.parse_child(Bookmark(attrs, self, 'div', parser))
        elif name == 'comment':
            self.parse_child(Comment(attrs, self))
        elif name == 'embed' or name == 'embedvar':
            (fname, id) = href_to_fname_id(attrs['href'])
            if parser.follow_embed:
                self.embed_href(parser, fname, id)
        elif name == 'list':
            self.parse_child(List(attrs, self))
        elif name == 'paragraph':
            parser.parse_paragraph(attrs, self)
        elif name == 'section':
            # sections can be nested
            self.parse_child(Section(attrs, self))
        elif name == 'switch':
            self.parse_child(Switch(attrs, self, parser.embedding_app))
        elif name == 'table':
            self.parse_child(Table(attrs, self))
        else:
            self.unhandled_element(parser, name)

    def get_all(self):
        mapping = ''
        try:
            mapping = section_id_mapping[self.id]
        except:
            pass

        # some of the section ids are used as real id's, some of them have
        # function (like relatetopics), and have to be templatized
        text = ''
        if mapping != '':
            text = '{{%s|%s}}\n\n'% (mapping, \
                    escape_equals_sign(ElementBase.get_all(self)))
        else:
            text = ElementBase.get_all(self)

        return text

    def get_variable(self, id):
        var = ElementBase.get_variable(self, id)
        if var != None:
            return var
        if id == self.id:
            return self
        return None

class Sort(ElementBase):
    def __init__(self, attrs, parent):
        ElementBase.__init__(self, 'sort', parent)

        try:
            self.order = attrs['order']
        except:
            self.order = 'asc'

    def start_element(self, parser, name, attrs):
        if name == 'section':
            self.parse_child(Section(attrs, self))
        else:
            self.unhandled_element(parser, name)

    def get_all(self):
        rev = False
        if self.order == 'asc':
            rev = True
        self.objects = sorted(self.objects, key=lambda obj: obj.id, reverse=rev)

        return ElementBase.get_all(self)

class Link(ElementBase):
    def __init__(self, attrs, parent, lang):
        ElementBase.__init__(self, 'link', parent)

        self.link = attrs['href']
        try:
            self.lname = attrs['name']
        except:
            self.lname = self.link[self.link.rfind("/")+1:]
        # Override lname
        self.default_name = self.lname
        (self.lname, self.fragment) = get_link_filename(self.link, self.lname)
        self.wikitext = ""
        self.lang = lang

    def char_data(self, parser, data):
        self.wikitext = self.wikitext + data

    def get_all(self):
        if self.wikitext == "":
            self.wikitext = self.default_name

        self.wikitext = replace_text(self.wikitext)
        if self.link.find("http") == 0:
            text = '[%s %s]'% (self.link, self.wikitext)
        elif self.lang != '':
            text = '[[%s/%s%s|%s]]'% (self.lname, self.lang, self.fragment, self.wikitext)
        else:
            text = '[[%s%s|%s]]'% (self.lname, self.fragment, self.wikitext)
        return text

class SwitchInline(ElementBase):
    def __init__(self, attrs, parent, app):
        ElementBase.__init__(self, 'switchinline', parent)
        self.switch = attrs['select']
        self.embedding_app = app

    def start_element(self, parser, name, attrs):
        if name == 'caseinline':
            self.parse_child(CaseInline(attrs, self, False))
        elif name == 'defaultinline':
            self.parse_child(CaseInline(attrs, self, True))
        else:
            self.unhandled_element(parser, name)

    def get_all(self):
        if len(self.objects) == 0:
            return ''
        elif self.switch == 'sys':
            system = {'MAC':'', 'UNIX':'', 'WIN':'', 'default':''}
            for i in self.objects:
                if i.case == 'MAC' or i.case == 'UNIX' or \
                   i.case == 'WIN' or i.case == 'default':
                    system[i.case] = i.get_all()
                elif i.case == 'OS2':
                    # ignore, there is only one mention of OS2, which is a
                    # 'note to translators', and no meat
                    pass
                elif i.case == 'HIDE_HERE':
                    # do what the name suggest ;-)
                    pass
                else:
                    sys.stderr.write('Unhandled "%s" case in "sys" switchinline.\n'% \
                            i.case )
            text = '{{System'
            for i in [['default', 'default'], ['MAC', 'mac'], \
                      ['UNIX', 'unx'], ['WIN', 'win']]:
                if system[i[0]] != '':
                    text = '%s|%s=%s'% (text, i[1], system[i[0]])
            return text + '}}'
        elif self.switch == 'appl':
            # we want directly use the right text, when inlining something
            # 'shared' into an 'app'
            if self.embedding_app == '':
                text = ''
                default = ''
                for i in self.objects:
                    appls = {'BASIC':'Basic', 'CALC':'Calc', \
                             'CHART':'Chart', 'DRAW':'Draw', \
                             'IMAGE':'Draw', 'IMPRESS': 'Impress', \
                             'MATH':'Math', 'WRITER':'Writer', \
                             'OFFICE':'', 'default':''}
                    try:
                        app = appls[i.case]
                        all = i.get_all()
                        if all == '':
                            pass
                        elif app == '':
                            default = all
                        else:
                            text = text + '{{WhenIn%s|%s}}'% (app, escape_equals_sign(all))
                    except:
                        sys.stderr.write('Unhandled "%s" case in "appl" switchinline.\n'% \
                                i.case)

                if text == '':
                    text = default
                elif default != '':
                    text = text + '{{WhenDefault|%s}}'% escape_equals_sign(default)

                return text
            else:
                for i in self.objects:
                    if i.case == self.embedding_app:
                        return i.get_all()

        return ''

class Case(ElementBase):
    def __init__(self, attrs, parent, is_default):
        ElementBase.__init__(self, 'case', parent)

        if is_default:
            self.name = 'default'
            self.case = 'default'
        else:
            self.case = attrs['select']

    def start_element(self, parser, name, attrs):
        if name == 'bookmark':
            self.parse_child(Bookmark(attrs, self, 'div', parser))
        elif name == 'comment':
            self.parse_child(Comment(attrs, self))
        elif name == 'embed' or name == 'embedvar':
            if parser.follow_embed:
                (fname, id) = href_to_fname_id(attrs['href'])
                self.embed_href(parser, fname, id)
        elif name == 'list':
            self.parse_child(List(attrs, self))
        elif name == 'paragraph':
            parser.parse_paragraph(attrs, self)
        elif name == 'section':
            self.parse_child(Section(attrs, self))
        elif name == 'table':
            self.parse_child(Table(attrs, self))
        else:
            self.unhandled_element(parser, name)

class Switch(SwitchInline):
    def __init__(self, attrs, parent, app):
        SwitchInline.__init__(self, attrs, parent, app)
        self.name = 'switch'

    def start_element(self, parser, name, attrs):
        self.embedding_app = parser.embedding_app
        if name == 'case':
            self.parse_child(Case(attrs, self, False))
        elif name == 'default':
            self.parse_child(Case(attrs, self, True))
        else:
            self.unhandled_element(parser, name)

class Item(ElementBase):
    replace_type = \
            {'start':{'input': '<code>',
                      'keycode': '{{KeyCode|',
                      'tasto': '{{KeyCode|',
                      'litera': '<code>',
                      'literal': '<code>',
                      'menuitem': '{{MenuItem|',
                      'mwnuitem': '{{MenuItem|',
                      'OpenOffice.org': '',
                      'productname': '',
                      'unknown': '<code>'
                     },
             'end':{'input': '</code>',
                    'keycode': '}}',
                    'tasto': '}}',
                    'litera': '</code>',
                    'literal': '</code>',
                    'menuitem': '}}',
                    'mwnuitem': '}}',
                    'OpenOffice.org': '',
                    'productname': '',
                    'unknown': '</code>'
                   },
             'templ':{'input': False,
                      'keycode': True,
                      'tasto': True,
                      'litera': False,
                      'literal': False,
                      'menuitem': True,
                      'mwnuitem': True,
                      'OpenOffice.org': False,
                      'productname': False,
                      'unknown': False
                     }}

    def __init__(self, attrs, parent):
        ElementBase.__init__(self, 'item', parent)

        try:
            self.type = attrs['type']
        except:
            self.type = 'unknown'
        self.text = ''

    def char_data(self, parser, data):
        self.text = self.text + data

    def get_all(self):
        try:
            text = ''
            if self.replace_type['templ'][self.type]:
                text = escape_equals_sign(replace_text(self.text))
            else:
                text = replace_text(self.text)
            return self.replace_type['start'][self.type] + \
                   text + \
                   self.replace_type['end'][self.type]
        except:
            sys.stderr.write('Unhandled item type "%s".\n'% self.type)

        return replace_text(self.text)


class Paragraph(ElementBase):
    def __init__(self, attrs, parent):
        ElementBase.__init__(self, 'paragraph', parent)

        try:
            self.role = attrs['role']
        except:
            self.role = 'paragraph'

        try:
            self.id = attrs['id']
        except:
            self.id = ""

        try:
            self.level = int(attrs['level'])
        except:
            self.level = 0

        self.is_first = (len(self.parent.objects) == 0)

    def start_element(self, parser, name, attrs):
        if name == 'ahelp':
            try:
                if attrs['visibility'] == 'hidden':
                    self.parse_child(Ignore(attrs, self, name))
            except:
                pass
        elif name == 'br':
            self.parse_child(Br(attrs, self))
        elif name == 'comment':
            self.parse_child(Comment(attrs, self))
        elif name == 'emph':
            self.parse_child(Emph(attrs, self))
        elif name == 'embedvar':
            if parser.follow_embed:
                (fname, id) = href_to_fname_id(attrs['href'])
                self.embed_href(parser, fname, id)
        elif name == 'help-id-missing':
            self.parse_child(HelpIdMissing(attrs, self))
        elif name == 'image':
            self.parse_child(Image(attrs, self))
        elif name == 'item':
            self.parse_child(Item(attrs, self))
        elif name == 'link':
            self.parse_child(Link(attrs, self, parser.lang))
        elif name == 'localized':
            # we ignore this tag, it is added arbitrary for the paragraphs
            # that come from .sdf files
            pass
        elif name == 'switchinline':
            self.parse_child(SwitchInline(attrs, self, parser.embedding_app))
        elif name == 'variable':
            self.parse_child(Variable(attrs, self))
        else:
            self.unhandled_element(parser, name)

    def char_data(self, parser, data):
        if self.role == 'paragraph' or self.role == 'heading' or \
                self.role == 'listitem' or self.role == 'variable':
            if data != '' and data[0] == ' ':
                data = ' ' + data.lstrip()
            data = data.replace('\n', ' ')

        if len(data):
            self.objects.append(Text(data))

    def get_all(self):
        role = self.role
        if role == 'heading':
            if self.level <= 0:
                sys.stderr.write('Heading, but the level is %d.\n'% self.level)
            elif self.level < 6:
                role = 'heading%d'% self.level
            else:
                role = 'heading6'

        # if we are not the first para in the table, we need special handling
        if not self.is_first and role.find('table') == 0:
            if role == 'tablecontentcode':
                role = 'tablenextparacode'
            else:
                role = 'tablenextpara'

        # the text itself
        children = ElementBase.get_all(self)
        if self.role != 'emph':
            children = children.strip()

        if len(children) == 0:
            return ''

        # prepend the markup according to the role
        text = ''
        try:
            text = text + replace_paragraph_role['start'][role]
        except:
            sys.stderr.write( "Unknown paragraph role start: " + role + "\n" )

        if replace_paragraph_role['templ'][role]:
            text = text + escape_equals_sign(children)
        else:
            text = text + children

        # append the markup according to the role
        try:
            text = text + replace_paragraph_role['end'][role]
        except:
            sys.stderr.write( "Unknown paragraph role end: " + role + "\n" )

        return text

class Variable(Paragraph):
    def __init__(self, attrs, parent):
        Paragraph.__init__(self, attrs, parent)
        self.name = 'variable'
        self.role = 'variable'
        self.id = attrs['id']

    def get_variable(self, id):
        if id == self.id:
            return self
        return None

class CaseInline(Paragraph):
    def __init__(self, attrs, parent, is_default):
        Paragraph.__init__(self, attrs, parent)

        self.role = 'null'
        if is_default:
            self.name = 'defaultinline'
            self.case = 'default'
        else:
            self.name = 'caseinline'
            self.case = attrs['select']

class Emph(Paragraph):
    def __init__(self, attrs, parent):
        Paragraph.__init__(self, attrs, parent)
        self.name = 'emph'
        self.role = 'emph'

    def get_all(self):
        text = Paragraph.get_all(self)
        if len(text):
            return "'''" + text + "'''"
        return ''

class ListItemParagraph(Paragraph):
    def __init__(self, attrs, parent):
        Paragraph.__init__(self, attrs, parent)
        self.role = 'listitem'

class TableContentParagraph(Paragraph):
    def __init__(self, attrs, parent):
        Paragraph.__init__(self, attrs, parent)
        if self.role != 'tablehead' and self.role != 'tablecontent':
            if self.role == 'code':
                self.role = 'tablecontentcode'
            else:
                self.role = 'tablecontent'
        if self.role == 'tablehead':
            self.parent.parent.isTableHeader = True # self.parent.parent is TableRow Element
        else:
            self.parent.parent.isTableHeader = False

class ParserBase:
    def __init__(self, filename, follow_embed, embedding_app, current_app, wiki_page_name, lang, head_object, buffer):
        self.filename = filename
        self.follow_embed = follow_embed
        self.embedding_app = embedding_app
        self.current_app = current_app
        self.wiki_page_name = wiki_page_name
        self.lang = lang
        self.head_obj = head_object

        p = xml.parsers.expat.ParserCreate()
        p.StartElementHandler = self.start_element
        p.EndElementHandler = self.end_element
        p.CharacterDataHandler = self.char_data

        p.Parse(buffer)

    def start_element(self, name, attrs):
        self.head_obj.get_curobj().start_element(self, name, attrs)

    def end_element(self, name):
        self.head_obj.get_curobj().end_element(self, name)

    def char_data(self, data):
        self.head_obj.get_curobj().char_data(self, data)

    def get_all(self):
        return self.head_obj.get_all()

    def get_variable(self, id):
        return self.head_obj.get_variable(id)

    def parse_localized_paragraph(self, paragraph, attrs, obj):
        localized_text = ''
        try:
            localized_text = get_localized_text(self.filename, attrs['id'])
        except:
            pass

        if localized_text != '':
            # parse the localized text
            text = u'<?xml version="1.0" encoding="UTF-8"?><localized>' + localized_text + '</localized>'
            ParserBase(self.filename, self.follow_embed, self.embedding_app, \
                    self.current_app, self.wiki_page_name, self.lang, \
                    paragraph, text.encode('utf-8'))
            # add it to the overall structure
            obj.objects.append(paragraph)
            # and ignore the original text
            obj.parse_child(Ignore(attrs, obj, 'paragraph'))
        else:
            obj.parse_child(paragraph)

    def parse_paragraph(self, attrs, obj):
        ignore_this = False
        try:
            if attrs['role'] == 'heading' and int(attrs['level']) == 1 \
                    and self.ignore_heading and self.follow_embed:
                self.ignore_heading = False
                ignore_this = True
        except:
            pass

        if ignore_this:
            obj.parse_child(Ignore(attrs, obj, 'paragraph'))
        else:
            self.parse_localized_paragraph(Paragraph(attrs, obj), attrs, obj)

class XhpParser(ParserBase):
    def __init__(self, filename, follow_embed, embedding_app, wiki_page_name, lang):
        # we want to ignore the 1st level="1" heading, because in most of the
        # cases, it is the only level="1" heading in the file, and it is the
        # same as the page title
        self.ignore_heading = True

        current_app = ''
        self.current_app_raw = ''
        for i in [['sbasic', 'BASIC'], ['scalc', 'CALC'], \
                  ['sdatabase', 'DATABASE'], ['sdraw', 'DRAW'], \
                  ['schart', 'CHART'], ['simpress', 'IMPRESS'], \
                  ['smath', 'MATH'], ['swriter', 'WRITER']]:
            if filename.find('/%s/'% i[0]) >= 0:
                self.current_app_raw = i[0]
                current_app = i[1]
                break

        if embedding_app == '':
            embedding_app = current_app

        file = codecs.open(filename, "r", "utf-8")
        buf = file.read()
        file.close()

        ParserBase.__init__(self, filename, follow_embed, embedding_app,
                current_app, wiki_page_name, lang, XhpFile(), buf.encode('utf-8'))

def loadallfiles(filename):
    global titles
    titles = []
    file = codecs.open(filename, "r", "utf-8")
    for line in file:
        title = line.split(";", 2)
        titles.append(title)
    file.close()

class WikiConverter(Thread):
    def __init__(self, inputfile, wiki_page_name, lang, outputfile):
        Thread.__init__(self)
        self.inputfile = inputfile
        self.wiki_page_name = wiki_page_name
        self.lang = lang
        self.outputfile = outputfile

    def run(self):
        parser = XhpParser(self.inputfile, True, '', self.wiki_page_name, self.lang)
        file = codecs.open(self.outputfile, "wb", "utf-8")
        file.write(parser.get_all())
        file.close()

def write_link(r, target):
    fname = 'wiki/%s'% r
    try:
        file = open(fname, "w")
        file.write('#REDIRECT [[%s]]\n'% target)
        file.close()
    except:
        sys.stderr.write('Unable to write "%s".\n'%'wiki/%s'% fname)

def write_redirects():
    print 'Generating the redirects...'
    written = {}
    # in the first pass, immediately writte the links that are embedded, so that
    # we can always point to that source versions
    for redir in redirects:
        app = redir[0]
        redirect = redir[1]
        target = redir[2]
        authoritative = redir[3]
    
        if app != '':
            r = '%s/%s'% (app, redirect)
            if authoritative:
                write_link(r, target)
                written[r] = True
            else:
                try:
                    written[r]
                except:
                    written[r] = False
    
    # in the second pass, output the wiki links
    for redir in redirects:
        app = redir[0]
        redirect = redir[1]
        target = redir[2]
    
        if app == '':
            for i in ['swriter', 'scalc', 'simpress', 'sdraw', 'smath', \
                      'schart', 'sbasic', 'sdatabase']:
                write_link('%s/%s'% (i, redirect), target)
        else:
            r = '%s/%s'% (app, redirect)
            if not written[r]:
                write_link(r, target)

# Main Function
def convert(generate_redirects, lang, sdf_file):
    if lang == '':
        print 'Generating the main wiki pages...'
    else:
        print 'Generating the wiki pages for language %s...'% lang

    global redirects
    redirects = []
    global images
    images = set()

    loadallfiles("alltitles.csv")

    if lang != '':
        sys.stderr.write('Using localizations from "%s"\n'% sdf_file)
        if not load_localization_data(sdf_file):
            return

    for title in titles:
        while threading.active_count() > max_threads:
            time.sleep(0.001)
    
        infile = title[0].strip()
        wikiname = title[1].strip()
        articledir = 'wiki/' + wikiname
        try:
            os.mkdir(articledir)
        except:
            pass

        outfile = ''
        if lang != '':
            wikiname = '%s/%s'% (wikiname, lang)
            outfile = '%s/%s'% (articledir, lang)
        else:
            outfile = '%s/MAIN'% articledir

        try:
            file = open(outfile, 'r')
        except:
            try:
                wiki = WikiConverter(infile, wikiname, lang, outfile)
                wiki.start()
                continue
            except:
                print 'Failed to convert "%s" into "%s".\n'% \
                        (infile, outfile)
        sys.stderr.write('Warning: Skipping: %s > %s\n'% (infile, outfile))
        file.close()
    
    # wait for everyone to finish
    while threading.active_count() > 1:
        time.sleep(0.001)

    if lang == '':
        # set of the images used here
        print 'Generating "images.txt", the list of used images...'
        file = open('images.txt', "w")
        for image in images:
            file.write('%s\n'% image)
        file.close()

        # generate the redirects
        if generate_redirects:
            write_redirects()

# vim:set shiftwidth=4 softtabstop=4 expandtab: