-
Notifications
You must be signed in to change notification settings - Fork 0
/
txt2tags-0.9.py
executable file
·883 lines (756 loc) · 31.4 KB
/
txt2tags-0.9.py
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
#!/usr/bin/python
import re, string, os, sys, getopt
from time import strftime,time,localtime
my_url = 'http://txt2tags.sourceforge.net'
my_email = '[email protected]'
my_version = '0.9'
tags = ['txt', 'sgml', 'html', 'pm6', 'mgp', 'moin', 'man']
f_noheaders = f_enumtitle = f_maskemail = f_toconly = f_toc = 0
splitlevel = '' ; lang = 'english'
doctype = outfile = ''
pipefileid = '-'
versionstr = "txt2tags version %s <%s>"%(my_version,my_url)
usage = """
%s
usage: txt2tags -t <type> [OPTIONS] file.t2t
txt2tags -t html -s <split level> -l <lang> file.t2t
-t, --type target document type. actually supported:
%s
--stdout by default, the output is written to file.<type>
with this option, STDOUT is used (no files written)
--noheaders suppress header, title and footer information
--enumtitle enumerate all title lines as 1, 1.1, 1.1.1, etc
--maskemail hide email from spam robots. [email protected] turns to <x (a) y z>
--toc add TOC (Table of Contents) to target document
--toconly print document TOC and exit
-h, --help print this help information and exit
-V, --version print program version and exit
extra options for HTML target (needs sgml-tools):
-s, --split split documents. values: 0, 1, 2 (default 0)
-l, --lang document language (default english)
"""%(versionstr, re.sub(r"[]'[]",'',repr(tags)))
def Quit(msg, exitcode=0): print msg ; sys.exit(exitcode)
# get cmdline options
errormsg = 'ERROR: bad option or missing argument (try --help)'
try: (opt, args) = getopt.getopt(sys.argv[1:], 'hVt:',
['help', 'version', 'stdout', 'type=', 'split=', 'lang=',
'noheaders', 'enumtitle', 'maskemail', 'toc', 'toconly'])
except getopt.GetoptError: Quit(errormsg, 1)
for o in opt:
if o[0] == '--noheaders': f_noheaders = 1
elif o[0] == '--enumtitle': f_enumtitle = 1
elif o[0] == '--maskemail': f_maskemail = 1
elif o[0] == '--split' : splitlevel = o[1]
elif o[0] == '--lang' : lang = o[1]
elif o[0] == '--toc' : f_toc = 1
elif o[0] == '--toconly' : outfile = pipefileid ; f_toconly = 1
elif o[0] == '--stdout' : outfile = pipefileid
elif o[0] in ['-t','--type']: doctype = o[1]
elif o[0] in ['-h','--help']: Quit(usage)
elif o[0] in ['-V','--version']: Quit(versionstr)
if not doctype and f_toconly: doctype = 'txt' # toconly defaults to txt
if not args or not doctype: Quit(usage, 1) # no filename/doctype
infile = args[0] # set source txt file name
# sanity check: validate target type
try: T = tags.index(doctype)
except ValueError:
Quit("ERROR: invalid document type '%s' (try --help)"%(doctype),1)
# sanity check: file exists?
if infile != pipefileid and not os.path.isfile(infile):
Quit('ERROR: file not found: %s'%infile, 1)
# sanity check: validate split level
if doctype != 'html': splitlevel = '' # only valid for HTML target
if splitlevel:
doctype = 'sgml' # 1st do a sgml, then sgml2html
outfile = '' # --stdout is forbidden
# check splitlevel value
if splitlevel[0] not in '012':
Quit('ERROR: option --split must be 0, 1 or 2')
# check for sgml-tools
#TODO how to test (in a clever way) if an executable is in path?
# Quit("Sorry, you must have 'sgml2html' program to use --split")
# set outfile name
if not outfile:
outfile = re.sub('\.(txt|t2t)$','',os.path.basename(infile))
outfile = "%s.%s"%(outfile,doctype)
if infile == pipefileid: outfile = pipefileid
# sanity check: source loss!
if infile != pipefileid and infile == outfile:
warn = 'SUICIDE WARNING!!! (try --stdout)\n '
Quit("%ssource and target files has the same name: %s"%(warn,outfile),1)
### yes, i've got my sample.t2t file deleted before add this test... :/
### all the registered tags
TAGparagraph = ['', '<p>', '<P>', '<@Normal:>', '%font "normal", size 5\n', '', '.P']
TAGtitle1 = [' \a' , '<sect>\a<p>' , '<H1>\a</H1>', '\n<@Title1:>\a', '%page\n\n\a', '= \a =', '.SH \a']
TAGtitle2 = ['\t\a' , '<sect1>\a<p>', '<H2>\a</H2>', '\n<@Title2:>\a', '%page\n\n\a', '== \a ==', '.SS \a']
TAGtitle3 = ['\t\t\a' , '<sect2>\a<p>', '<H3>\a</H3>', '\n<@Title3:>\a', '%page\n\n\a', '=== \a ===', '.SS \a']
TAGtitle4 = ['\t\t\t\a' , '<sect3>\a<p>', '<H4>\a</H4>', '\n<@Title4:>\a', '%page\n\n\a', '==== \a ====', '.SS \a']
TAGtitle5 = ['\t\t\t\t\a', '<sect4>\a<p>', '<H5>\a</H5>', '\n<@Title5:>\a', '%page\n\n\a', '===== \a =====', '.SS \a']
TAGareaPreOpen = ['', '<tscreen><verb>', '<PRE>', '<@PreFormat:>', '\n%font "mono"', '{{{', '.nf']
TAGareaPreClose = ['', '</verb></tscreen>', '</PRE>', '', '%font "normal"', '}}}', '.fi\n']
TAGareaQuoteOpen = [' ', '<quote>', '<BLOCKQUOTE>', '<@Quote:>', '%prefix " "', ' ', '\n']
TAGareaQuoteClose = ['', '</quote>', '</BLOCKQUOTE>', '', '%prefix " "', '', '\n']
TAGfontMonoOpen = ['', '<tt>', '<CODE>', '<FONT "Lucida Console"><SIZE 9>', '\n%cont, font "mono"\n', '{{{', '']
TAGfontMonoClose = ['', '</tt>', '</CODE>', '<SIZE$><FONT$>', '\n%cont, font "normal"\n', '}}}', '']
TAGfontBoldOpen = ['', '<bf>', '<B>', '<B>', '\n%cont, font "normal-b"\n', "'''", r'\\fB']
TAGfontBoldClose = ['', '</bf>', '</B>', '<P>', '\n%cont, font "normal"\n', "'''", r'\\fP']
TAGfontItalicOpen = ['', '<em>', '<I>', '<I>', '\n%cont, font "normal-i"\n', "''", r'\\fI']
TAGfontItalicClose = ['', '</em>', '</I>', '<P>', '\n%cont, font "normal"\n', "''", r'\\fP']
TAGfontBoldItalicOpen = ['', '<bf><em>', '<B><I>', '<B><I>', '\n%cont, font "normal-bi"\n', "'''''", '\n.BI ']
TAGfontBoldItalicClose = ['', '</em></bf>', '</I></B>', '<P>', '\n%cont, font "normal"\n', "'''''", '\n\\&']
TAGfontUnderlineOpen = ['', TAGfontBoldItalicOpen[1], '<U>', '<U>', '\n%cont, fore "cyan"\n', TAGfontBoldItalicOpen[5], '']
TAGfontUnderlineClose = ['', TAGfontBoldItalicClose[1], '</U>', '<P>', '\n%cont, fore "white"\n', TAGfontBoldItalicClose[5], '']
TAGlistOpen = ['', '<itemize>', '<UL>', '<@Bullet:>', '', '', '\n'+TAGareaPreOpen[6]]
TAGlistClose = ['', '</itemize>', '</UL>', '', '', '', TAGareaPreClose[6]]
TAGlistItem = ['- ', '<item>', '<LI>', '• ', '', '* ', '* ']
TAGnumlistOpen = ['', '<enum>', '<OL>', '<@Bullet:>', '', '', '\n'+TAGareaPreOpen[6]]
TAGnumlistClose = ['', '</enum>', '</OL>', '', '', '', TAGareaPreClose[6]]
TAGnumlistItem = ['\a. ', '<item>', '<LI>', '~U ', '\a. ', '\a. ', '\a. ']
TAGdeflistOpen = ['', '', '<DL>' , '', '', '', '']
TAGdeflistItem1 = ['', '', '<DT>\a</DT>', '', '', '', '']
TAGdeflistItem2 = ['', '', '<DD>' , '', '', '', ''] #TODO must close?
TAGdeflistClose = ['', '', '</DL>' , '', '', '', '']
TAGbar1 = ['\a', '<!-- \a -->', '<HR NOSHADE SIZE=1>', '\a', '%bar "white" 5', '----', '\n\n']
TAGbar2 = ['\a', '<!-- \a -->', '<HR NOSHADE SIZE=5>', '\a', '%pause', '----', '\n\n']
TAGurl = ['\a', '<htmlurl url="\a" name="\a">', '<A HREF="\a">\a</A>', TAGfontUnderlineOpen[3]+'\a'+TAGfontUnderlineClose[3], '\n%cont, fore "cyan"\n\a\n%cont, fore "white"\n', '[\a]', '\a']
TAGurlMark = ['\a (\a)', TAGurl[1], TAGurl[2], '\a '+TAGurl[3], '\a '+TAGurl[4], '[\a \a]', '\a (\a)']
TAGemail = ['\a', '<htmlurl url="mailto:\a" name="\a">', '<A HREF="mailto:\a">\a</A>', '\a', TAGurl[4], '[\a]', '\a']
TAGemailMark = ['\a (\a)', TAGemail[1], TAGemail[2], '\a '+TAGemail[3], '\a '+TAGemail[4], '[\a \a]', '\a (\a)']
TAGemail = ['\a', '<htmlurl url="mailto:\a" name="\a">', '<A HREF="mailto:\a">\a</A>', '\a', TAGurl[4], '[\a]', '\a']
TAGimg = ['[\a]', '<figure><ph vspace=""><img src="\a"></figure>', '<IMG ALIGN="\a" SRC="\a">', '\a', '\n%center\n%newimage "\a", left\n', '[\a]', '\a']
TAGtableOpen = [ '', '<table><tabular ca="c">', '<table align=center cellpadding=4 border=\a>', '', '', '', '']
TAGtableLineOpen = [ '', '', '<tr>', '', '', '||', '']
TAGtableLineClose = [ '', '<rowsep>', '</tr>', '', '', '', '']
TAGtableCellOpen = [ '', '', '<td>', '', '', '', '']
TAGtableCellClose = [ '', '<colsep>', '</td>', '', '', '||', '']
TAGtableTitleCellOpen = [ '', '', '<th>', '', '', '', '']
TAGtableTitleCellClose = [ '', '<colsep>', '</th>', '', '', '||', '']
TAGtableClose = [ '', '</tabular></table>', '</table>', '', '', '', '']
TAGanchor = ['', '', '<a name="\a">', '', '', '', '']
TAGEOD = ['', '</article>', '</BODY></HTML>', '', '%%EOD', '', '']
### the cool regexes
re_title = re.compile(r'^\s*(?P<tag>={1,5})(?P<txt>[^=].*[^=])\1(\[(?P<label>\w+)\])?$')
re_areaPreOpen = re_areaPreClose = re.compile(r'^---$')
re_quote = re.compile(r'^\t+')
re_1linePreOld = re.compile(r'^ {4}([^\s-])')
re_1linePre = re.compile(r'^--- ')
re_mono = re.compile(r'`([^`]+)`')
re_bold = re.compile(r'\*\*([^\s*].*?)\*\*')
re_italic = re.compile(r'(^|[^:])//([^ /].*?)//')
re_underline = re.compile(r'__([^_].*?)__') # underline lead/trailing blank
re_bolditalic = re.compile(r'\*/([^/].*?)/\*')
re_list = re.compile(r'^( *)([+-]) ([^ ])')
re_deflist = re.compile(r'^( *)(=) ([^:]+):')
re_bar =re.compile(r'^\s*([_=-]{20,})\s*$')
re_table = re.compile(r'^ *\|\|?[<:>]*\s')
# link things
urlskel = {
'proto' : r'(https?|ftp|news|telnet|gopher|wais)://',
'guess' : r'(www[23]?|ftp)\.', # w/out proto, try to guess
'login' : r'A-Za-z0-9_.-', # for ftp://[email protected]
'pass' : r'[^ @]*', # for ftp://login:[email protected]
'chars' : r'A-Za-z0-9%._/~:,=-', # %20(space), :80(port)
'anchor': r'A-Za-z0-9%.-', # %nn(encoded)
'form' : r'A-Za-z0-9/%&=+.@*_-',# .@*_-(as is)
'punct' : r'.,;:!?'
}
patt_url_login = r'([%s]+(:%s)?@)?'%(urlskel['login'],urlskel['pass'])
retxt_url = r'\b(%s%s|%s)[%s]+(#[%s]+|\?[%s]+)?(?=[%s]|[^%s]|$)\b'%(
urlskel['proto'],patt_url_login, urlskel['guess'],
urlskel['chars'],urlskel['anchor'],
urlskel['form'] ,urlskel['punct'],urlskel['form'])
retxt_url_local = r'[%s]+|[%s]*(#[%s]+)'%(
urlskel['chars'],urlskel['chars'],urlskel['anchor'])
retxt_email = r'\b[%s]+@([A-Za-z0-9_-]+\.)+[A-Za-z]{2,4}(\?[%s]+)?\b'%(
urlskel['login'],urlskel['form'])
re_link = re.compile(r'%s|%s'%(retxt_url,retxt_email), re.I)
re_linkmark = re.compile(r'\[([^]]*) (%s|%s|%s)\]'%(
retxt_url, retxt_email, retxt_url_local))
re_x = re.compile('\a')
re_blankline = re.compile(r'^\s*$')
re_comment = re.compile(r'^//')
re_date = re.compile(r'%%date\b(\((?P<fmt>.*?)\))?', re.I)
re_img = re.compile(r'\[([\w_,.+%$#@!?+~/-][\w_,.+%$#@!?+~/ -]+\.(png|jpe?g|gif|eps|bmp))\]', re.L+re.I)
def doHeader(title, author, date):
ret = []
title = string.strip(title)
author = string.strip(author)
date = string.strip(date)
if doctype == 'txt':
ret.append("%s\n%s\n%s"%(title,author,date))
elif doctype == 'sgml':
ret.append("<!doctype linuxdoc system>\n<article>")
ret.append("<title>%s\n<author>%s\n<date>%s\n" %(title,author,date))
elif doctype == 'html':
ret.append('<HTML>\n<HEAD><TITLE>%s</TITLE></HEAD>'%title)
ret.append('<BODY BGCOLOR="white" TEXT="black">')
ret.append('<P ALIGN="center"><CENTER><H1>%s</H1>'%title)
ret.append('<FONT SIZE=4><I>%s</I><BR>'%author)
ret.append('%s</FONT></CENTER>\n'%date)
elif doctype == 'man':
# TODO man section 1 is hardcoded...
ret.append('.TH "%s" 1 %s "%s"'%(title,date,author))
elif doctype == 'pm6':
# TODO style to <HR>
# TODO unix2dos before apply
ret.append("""\
<PMTags1.0 win><C-COLORTABLE ("Preto" 1 0 0 0)
><@Normal=
<FONT "Times New Roman"><CCOLOR "Preto"><SIZE 11>
<HORIZONTAL 100><LETTERSPACE 0><CTRACK 127><CSSIZE 70><C+SIZE 58.3>
<C-POSITION 33.3><C+POSITION 33.3><P><CBASELINE 0><CNOBREAK 0><CLEADING -0.05>
<GGRID 0><GLEFT 7.2><GRIGHT 0><GFIRST 0><G+BEFORE 7.2><G+AFTER 0>
<GALIGNMENT "justify"><GMETHOD "proportional"><G& "ENGLISH">
<GPAIRS 12><G% 120><GKNEXT 0><GKWIDOW 0><GKORPHAN 0><GTABS $>
<GHYPHENATION 2 34 0><GWORDSPACE 75 100 150><GSPACE -5 0 25>
><@Bullet=<@-PARENT "Normal"><FONT "Abadi MT Condensed Light">
<GLEFT 14.4><G+BEFORE 2.15><G% 110><GTABS(25.2 l "")>
><@PreFormat=<@-PARENT "Normal"><FONT "Lucida Console"><SIZE 8><CTRACK 0>
<GLEFT 0><G+BEFORE 0><GALIGNMENT "left"><GWORDSPACE 100 100 100><GSPACE 0 0 0>
><@Title1=<@-PARENT "Normal"><FONT "Arial"><SIZE 14><B>
<GCONTENTS><GLEFT 0><G+BEFORE 0><GALIGNMENT "left">
><@Title2=<@-PARENT "Title1"><SIZE 12><G+BEFORE 3.6>
><@Title3=<@-PARENT "Title1"><SIZE 10><GLEFT 7.2><G+BEFORE 7.2>
><@Title4=<@-PARENT "Title3">
><@Title5=<@-PARENT "Title3">
><@Quote=<@-PARENT "Normal"><SIZE 10><I>>
""")
elif doctype == 'mgp':
ret.append("""\
#!/usr/X11R6/bin/mgp -t 90
%deffont "normal" xfont "utopia-medium-r", charset "iso8859-1"
%deffont "normal-i" xfont "utopia-medium-i", charset "iso8859-1"
%deffont "normal-b" xfont "utopia-bold-r", charset "iso8859-1"
%deffont "normal-bi" xfont "utopia-bold-i", charset "iso8859-1"
%deffont "mono" xfont "courier-medium-r", charset "iso8859-1"
%default 1 size 5
%default 2 size 8, fore "yellow", font "normal-b", center
%default 3 size 5, fore "white", font "normal", left, prefix " "
%tab 1 size 4, vgap 30, prefix " ", icon arc "red" 40, leftfill
%tab 2 prefix " ", icon arc "orange" 40, leftfill
%tab 3 prefix " ", icon arc "brown" 40, leftfill
%tab 4 prefix " ", icon arc "darkmagenta" 40, leftfill
%tab 5 prefix " ", icon arc "magenta" 40, leftfill
%%%%%%%%%%%%%%%%%%%%%%%%%% end of headers %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%page
""")
# 1st title page
ret.append('\n\n\n\n%%size 10, center, fore "yellow"\n%s'%title)
ret.append('\n%%font "normal-i", size 6, fore "white", center')
ret.append('%s\n\n%%font "mono", size 7, center\n%s'%(author,date))
return ret
def doCommentLine(txt):
if doctype == 'sgml' or doctype == 'html': ret = "<!-- %s -->"%txt
elif doctype == 'mgp': ret = "%%%% %s"%txt
elif doctype == 'man': ret = '.\\" %s'%txt
else: ret = ''
return ret
def doFooter():
ret = []
ppgd = '%s code generated by txt2tags %s (%s)'%(doctype,my_version,my_url)
cmdline = 'cmdline: txt2tags %s'%string.join(sys.argv[1:], ' ')
ret.append('\n'+doCommentLine(ppgd))
ret.append(doCommentLine(cmdline))
ret.append(TAGEOD[T])
return ret
def doEscape(txt):
if doctype == 'html' or doctype == 'sgml':
txt = re.sub('&','&',txt)
txt = re.sub('<','<',txt)
txt = re.sub('>','>',txt)
if doctype == 'sgml': txt = re.sub('ÿ','ÿ',txt)
elif doctype == 'pm6' : txt = re.sub('<','<\#60>',txt)
elif doctype == 'mgp' : txt = re.sub('^%([^%])','%prefix ""\n %\n%cont, prefix " "\n\\1',txt)
elif doctype == 'man' : txt = re.sub('^\.', ' .',txt) # command ID
return txt
def doEscapeEscape(txt):
while re.search(r'\\<', txt):
txt = re.sub(r'\\<','<\#92><',txt)
return txt
def addLineBreaks(list):
ret = []
for line in list:
ret.append(line+'\n')
return ret
################################################################################
###MerryChristmas,IdontwanttofighttonightwithyouImissyourbodyandIneedyourlove###
################################################################################
def doitall(inlines, doctype):
# the defaults
title = 'document title'
author = 'author name'
currdate = strftime('%Y%m%d',localtime(time())) # ISO current date
date = currdate
linkmask = '@@_@_@@'
monomask = '@@_m_@@'
ret = []
toclist = []
header = []
f_tt = 0
listident = []
listids = []
listcount = []
titlecount = ['',0,0,0,0,0]
f_header = 0
f_lastblank = 0
holdspace = ''
listholdspace = ''
quotedepth = 0
istable = 0
tableborder = 0
tablealign = []
if outfile != pipefileid:
print "--- %s..."%doctype
# let's mark it up!
linenr = 0
for lineref in range(len(inlines)):
skip_continue = 0
urlbank = [] ; emailbank = []
linkbank = []
monobank = []
linenr = lineref +1
line = string.rstrip(inlines[lineref])
# we need (not really) to mark each paragraph
if doctype == 'pm6' and f_lastblank:
if f_tt or f_header or listident: holdspace = ''
else: holdspace = TAGparagraph[T]+'\n'
# PRE-formatted area
# we'll never support beautifiers inside pre-formatted
if f_tt:
f_lastblank = 0
line = doEscape(line)
# closing PRE
if re_areaPreClose.search(line):
if doctype != 'pm6': ret.append(TAGareaPreClose[T])
f_tt = 0
continue
# normal PRE-inside line
if doctype == 'pm6': line = doEscapeEscape(line)
elif doctype in ('txt', 'man', 'html'): line = ' '+line # align
ret.append(line)
continue
# detecting PRE
if re_areaPreOpen.search(line):
line = doEscape(line)
if f_tt:
warn = "WARNING:%d:opening PRE-formatted tag"%linenr
print warn, "without closing previous one"
ret.append(line)
continue
ret.append(TAGareaPreOpen[T])
f_tt = 1
continue
# one line PRE-formatted text
if re_1linePre.search(line):
f_lastblank = 0
line = doEscape(line)
line = re_1linePre.sub('',line)
if doctype == 'pm6': line = doEscapeEscape(line)
if doctype in ('txt', 'man', 'html'): line = ' '+line # align
ret.append('%s\n%s\n%s'%(TAGareaPreOpen[T],line,TAGareaPreClose[T]))
continue
# blank lines
#TODO "holdspace" to save <p> to not show in closelist
if re_blankline.search(line):
if istable:
if istableaware: ret.append(TAGtableClose[T])
else: ret.append(TAGareaPreClose[T])
istable = tableborder = 0
continue
#TODO generic class or function to close quotes/lists/tables
# when entering pre,list,table,etc
# closing quotes
while quotedepth:
quotedepth = quotedepth-1
ret.append(TAGareaQuoteClose[T])
if f_lastblank: # 2nd consecutive blank line
if listident: # closes list (if any)
while len(listident):
if listids[-1] == '-': tag = TAGlistClose[T]
elif listids[-1] == '+': tag = TAGnumlistClose[T]
elif listids[-1] == '=': tag = TAGdeflistClose[T]
if not tag: tag = TAGlistClose[T] # default
if tag: # man tags just for mother-list and at ^
if doctype == 'man':
if len(listident) == 1: ret.append(tag)
else: ret.append(listident[-1]+tag)
del listident[-1]
del listids[-1]
# add visual separator line for the mother list
if not listids and doctype == 'txt': ret.append('\n')
holdspace = ''
continue # consecutive blanks are trash
if f_header or linenr == 1: # 1st blank after header (if any)
if not f_noheaders: header = doHeader(title,author,date)
if doctype != 'pm6': ret.append(TAGparagraph[T])
f_header = 0 # we're done with header
continue
# normal blank line
if doctype != 'pm6':
# paragraph (if any) is wanted inside lists also
if listident:
holdspace = holdspace+TAGparagraph[T]+'\n'
elif doctype == 'html': ret.append(TAGparagraph[T])
# sgml: the quote close tag must not be \n\n</quote>
elif doctype == 'sgml' and quotedepth:
skip_continue = 1
# otherwise we just print a blank line
else: ret.append('')
f_lastblank = 1
if not skip_continue: continue
else:
f_lastblank = 0 # reset blank status
# first line with no header
if f_noheaders and linenr == 1 and doctype != 'pm6':
ret.append(TAGparagraph[T])
# comments
# just skip them
if re_comment.search(line):
f_lastblank = 1
continue
# protect pre-formatted font text from escaping and formatting
if not f_tt:
while re_mono.search(line):
txt = re_mono.search(line).group(1)
monobank.append(doEscape(txt))
line = re_mono.sub(monomask,line,1)
# protect URLs and emails from escaping and formatting
# changing them by a mask
if not f_tt:
while re_linkmark.search(line): # search for named link
m = re_linkmark.search(line)
# remove quotes from old ["" link] tag
label = re.sub('^"|"$','',m.group(1))
link = m.group(2)
linkbank.append([label, link])
line = re_linkmark.sub(linkmask,line,1)
while re_link.search(line): # simple url or email
link = re_link.search(line).group()
linkbank.append(['', link])
line = re_link.sub(linkmask,line,1)
# the target-specific special char escapes
line = doEscape(line)
# HR line
if re_bar.search(line):
txt = re_bar.search(line).group(1)
if txt[0] == '=': bar = TAGbar2[T]
else : bar = TAGbar1[T]
line = re_bar.sub(bar,line)
ret.append(re_x.sub(txt,line))
continue
# quote
if re_quote.search(line):
currquotedepth = len(re_quote.search(line).group(0)) # TABs number
if doctype == 'sgml' and quotedepth and currquotedepth > quotedepth:
currquotedepth = quotedepth
if not TAGareaQuoteClose[T]:
line = re_quote.sub(TAGareaQuoteOpen[T]*currquotedepth, line)
else:
# new (sub)quote
if not quotedepth or currquotedepth > quotedepth:
quotedepth = currquotedepth
ret.append(TAGareaQuoteOpen[T])
if doctype != 'html'and doctype != 'sgml':
line = re_quote.sub('', line)
# closing quotes
while currquotedepth < quotedepth:
quotedepth = quotedepth-1
ret.append(TAGareaQuoteClose[T])
else:
# closing quotes
while quotedepth:
quotedepth = quotedepth-1
ret.append(TAGareaQuoteClose[T])
# title
#TODO set next blank and set f_lastblank or f_lasttitle
if re_title.search(line) and not listident:
m = re_title.search(line)
tag = m.group('tag')
level = len(tag)
tag = eval('TAGtitle%s[T]'%level)
txt = string.strip(m.group('txt'))
# initpos = string.find(line,txt)
if doctype == 'sgml':
txt = re.sub(r'\[', r'[', txt)
txt = re.sub(r'\\', r'\', txt)
if f_enumtitle: ### numbered title
id = '' ; n = level #
titlecount[n] = titlecount[n] +1 # add count
if n < len(titlecount)-1: # reset sublevels count
for i in range(n+1, len(titlecount)): titlecount[i] = 0
for i in range(n): # compose id from hierarchy
id = "%s%d."%(id,titlecount[i+1])
txt = "%s %s"%(id, txt) # add id to title
anchorid = '#toc%d'%(len(toclist)+1)
if TAGanchor[T] and f_toc:
ret.append(re_x.sub(anchorid,TAGanchor[T]))
line = re_title.sub(tag,line)
ret.append(re_x.sub(txt,line))
# let's do some TOC!
if TAGanchor[T]:
tocitemid = '#toc%d'%(len(toclist)+1)
tocitem = '%s- [%s %s]'%(' '*level,txt,anchorid)
else:
tocitem = '%s- %s'%(' '*level,txt)
if doctype in ['txt', 'man']:
tocitem = '%s%s' %(' '*level,txt)
toclist.append(tocitem)
# add "underline" to text titles
if doctype == 'txt': ret.append(re_x.sub('='*len(txt),tag))
continue
#TODO!
# labeltxt = ''
# label = m.group('label')
# if label: labeltxt = '<label id="%s">' %label
# list
if re_list.search(line) or re_deflist.search(line):
if re_list.search(line): rgx = re_list
else : rgx = re_deflist
m = rgx.search(line)
listitemident = m.group(1)
listtype = m.group(2)
extra = m.group(3) # regex anchor char
if listtype == '=':
listdefterm = m.group(3)
extra = ''
# new sublist
if not listident or len(listitemident) > len(listident[-1]):
listident.append(listitemident)
listids.append(listtype)
if listids[-1] == '-': tag = TAGlistOpen[T]
elif listids[-1] == '+': tag = TAGnumlistOpen[T]
elif listids[-1] == '=': tag = TAGdeflistOpen[T]
if not tag: tag = TAGlistOpen[T] # default
# no need to reopen <pre> tag on man sublists
if doctype == 'man' and len(listident) != 1: tag = ''
openlist = listident[-1]+tag
if doctype == 'pm6': listholdspace = openlist
else:
if string.strip(openlist): ret.append(openlist)
# reset item manual count
listcount.append(0)
# closing sublists
while len(listitemident) < len(listident[-1]):
if listids[-1] == '-': tag = TAGlistClose[T]
elif listids[-1] == '+': tag = TAGnumlistClose[T]
elif listids[-1] == '=': tag = TAGdeflistClose[T]
if not tag: tag = TAGlistClose[T] # default
if tag: # man list is just a <pre> text, closed at mother-list
if doctype != 'man': ret.append(listident[-1]+tag)
del listident[-1]
del listids[-1]
if listcount: del listcount[-1]
# normal item
listid = listident[-1]
if listids[-1] == '-':
tag = TAGlistItem[T]
elif listids[-1] == '+':
tag = TAGnumlistItem[T]
listcount[-1] = listcount[-1] +1
if doctype in ['txt', 'man', 'moin', 'mgp']:
tag = re_x.sub(str(listcount[-1]), tag)
elif listids[-1] == '=':
if not TAGdeflistItem1[T]:
# emulate def list, with <li><b>def</b>:
tag = TAGlistItem[T] +TAGfontBoldOpen[T] +listdefterm
tag = tag +TAGfontBoldClose[T] +':'
else:
tag = re_x.sub(listdefterm, TAGdeflistItem1[T])
tag = tag + TAGdeflistItem2[T] # open <DD>
if doctype == 'mgp': listid = len(listident)*'\t'
line = rgx.sub(listid+tag+extra,line)
if listholdspace:
line = listholdspace+line
listholdspace = ''
if doctype == 'sgml': line = re.sub(r'\[', r'[', line)
# table
#TODO escape undesired format inside table
#TODO not rstrip if table line (above)
#TODO add man, pm6 targets
if re_table.search(line): # only HTML for now
closingbar = re.compile(r'\| *$')
tableid = line[re_table.search(line).end()-1]
if not istable: # table header
if doctype in ['sgml', 'html', 'moin']:
istableaware = 1
if tableid == '\t': tableborder = 1
if closingbar.search(line): tableborder = 1
# add border=1
ret.append(re_x.sub(`tableborder`, TAGtableOpen[T]))
else:
istableaware = 0 ; ret.append(TAGareaPreOpen[T])
istable = 1
if istableaware:
line = re.sub(r'^ *' , '', line) # del leading spaces
line = closingbar.sub('', line) # del last bar |
tablefmt, tablecel = re.split(r'\s', line, 1)
tablefmt = tablefmt[1:] # cut mark off
tablecel = re.split(r'\t\|?| \|', tablecel)
line = ''
# setting cell and line tags
tl1, tl2 = TAGtableLineOpen[T], TAGtableLineClose[T]
tc1, tc2 = TAGtableCellOpen[T], TAGtableCellClose[T]
if tablefmt and tablefmt[0] == '|': # title cell
tc1, tc2 = TAGtableTitleCellOpen[T], TAGtableTitleCellClose[T]
if doctype == 'html': tc2 = tc2+'\n' ; tl1 = tl1+'\n'
if tablecel:
while tablecel:
cel = tablecel.pop(0)
if not cel and doctype == 'html':
cel = ' '
else:
# user escaped (not delim!)
cel = string.replace(cel,'\|', '|')
if not tablecel and doctype == 'sgml':
tc2 = '' # last cell
line = '%s%s%s%s'%(line,tc1,string.strip(cel),tc2)
line = '%s%s%s'%(tl1,line,tl2)
### BEGIN of at-any-part-of-the-line/various-per-line TAGs.
# date
while re_date.search(line):
m = re_date.search(line)
fmt = m.group('fmt') or ''
dateme = currdate
if fmt: dateme = strftime(fmt,localtime(time()))
line = re_date.sub(dateme,line,1)
# bold
if re_bold.search(line):
txt = r'%s\1%s'%(TAGfontBoldOpen[T],TAGfontBoldClose[T])
line = re_bold.sub(txt,line)
# italic
if re_italic.search(line):
txt = r'\1%s\2%s'%(TAGfontItalicOpen[T],TAGfontItalicClose[T])
line = re_italic.sub(txt,line)
# bolditalic
if re_bolditalic.search(line):
txt = r'%s\1%s'%(TAGfontBoldItalicOpen[T],TAGfontBoldItalicClose[T])
line = re_bolditalic.sub(txt,line)
# underline
if re_underline.search(line):
txt = r'%s\1%s'%(TAGfontUnderlineOpen[T],TAGfontUnderlineClose[T])
line = re_underline.sub(txt,line)
# image
# first store blanks to detect image at ^
try: leadingblanks = re.match(' +',line).end()
except: leadingblanks = 0
# moin and txt tags are the same as the mark
while re_img.search(line) and doctype not in ['moin','txt']:
m = re_img.search(line)
txt = m.group(1)
ini = m.start() ; head = leadingblanks
end = m.end() ; tail = len(line)
tag = TAGimg[T]
if doctype == 'html': # do img align
align = 'center' # default align # text + img + text
if ini == head and end == tail:
tag = '<P ALIGN="center">%s</P>'%tag # ^img$
elif ini == head: align = 'left' # ^img + text$
elif end == tail: align = 'right' # ^text + img$
tag = re_x.sub(align, tag, 1) # add align on tag
line = re_img.sub(tag,line,1)
line = re_x.sub(txt,line,1)
if doctype == 'sgml': line = re.sub(r'\[', r'[', line)
line = '%s%s'%(' '*leadingblanks,line) # put blanks back
# font PRE
for mono in monobank:
line = string.replace(line, monomask, "%s%s%s"%(
TAGfontMonoOpen[T],mono,TAGfontMonoClose[T]),1)
# URL & email
for link in linkbank:
linktype = 'url'; label = link[0]; url = link[1]
if re.match(retxt_email, url): linktype = 'email'
guessurl = '' # adding protocol to guessed link
if linktype == 'url' and re.match(urlskel['guess'], url):
if url[0] == 'w': guessurl = 'http://' +url
else: guessurl = 'ftp://' +url
if not label and not guessurl: # simple link
if f_maskemail and linktype == 'email':
url = string.replace(url,'@',' (a) ')
url = string.replace(url,'.',' ')
url = doEscape("<%s>"%url)
line = string.replace(line, linkmask, url, 1)
else:
line = eval('string.replace(line,linkmask,TAG%s[T],1)'%linktype)
line = re_x.sub(url,line)
else: # named link!
if not label: label = url
if guessurl: url = guessurl
# putting data on the right appearance order
urlorder = [label, url] # label before link
if doctype in ('html', 'sgml', 'moin'): # link before label
urlorder = [url, label]
# replace mask with tag
line = eval('string.replace(line,linkmask,TAG%sMark[T],1)'%linktype)
for data in urlorder: # fill \a from tag with data
line = re_x.sub(data,line,1)
# header
if not f_noheaders:
if linenr == 1:
title = line
f_header = 1
continue
if f_header:
if linenr == 2: author = line ; continue
elif linenr == 3: date = line ; continue
else:
header = doHeader(title,author,date)
f_header = 0
# FINAL scapes. TODO function for it
# convert all \ before <...> to tag
if doctype == 'pm6': line = doEscapeEscape(line)
elif doctype == 'man' : line = re.sub('-',r'\-',line)
ret.append(holdspace+line)
holdspace = ''
if not f_noheaders: ret.extend(doFooter())
return header,toclist,ret
################################################################################
################################################################################
# reading our source file
if infile == pipefileid:
lines = sys.stdin.readlines()
else:
f = open(infile, 'r') ; lines = f.readlines() ; f.close
# let's do it!
header,toc,doc = doitall(lines, doctype)
# deal with the TOC options
if f_toc or f_toconly:
# format TOC lines
#TODO list is piggy, try QUOTE+BR
### here we do toc as a valid t2t marked text (list type)
f_noheaders = 1
x,y,toc = doitall(['']+toc+['',''], doctype)
# TOC between bars (not for --toconly)
if f_toc:
para = TAGparagraph[T]
tocbar = [para, re_x.sub('-'*72,TAGbar1[T]), para]
toc = tocbar + toc + tocbar
doc = toc + doc
outlist = header + doc
if f_toconly: outlist = toc[:] # TOC only!
# writing output to screen or file
if outfile == pipefileid:
for line in outlist: print line
else:
f = open(outfile, 'w') ; f.writelines(addLineBreaks(outlist)) ; f.close()
print 'wrote %s'%(outfile)
if splitlevel:
print "--- html..."
os.system('sgml2html --language=%s --split=%s %s'%(lang,splitlevel,outfile))
sys.exit(0)
### RESOURCES
# html: http://www.w3.org/TR/WD-html-lex
# man: man 7 man
# sgml: www.linuxdoc.org
# moin: http://twistedmatrix.com/users/jh.twistd/moin/moin.cgi/WikiSandBox
# moin: http://moin.sf.net
# pm6: <font$> turn all formatting to the style's default
# pm6: <#comments#> <font #comment# $>
# pagemaker table
# 1 = 0,55
# 2 = 1,10
# 3 = 1,65
# 4 = 2,20
#
# |__1_| | | | | |
# |_______2_| | | | |
# |____________3_| | | |