PageRenderTime 55ms CodeModel.GetById 13ms RepoModel.GetById 0ms app.codeStats 0ms

/old/txt2tags-1.4.py

http://txt2tags.googlecode.com/
Python | 2157 lines | 2133 code | 5 blank | 19 comment | 7 complexity | cfa33d77fcd57ac3df3a16e2a9743c25 MD5 | raw file
Possible License(s): GPL-2.0, GPL-3.0, WTFPL

Large files files are truncated, but you can click here to view the full file

    

  1. #!/usr/bin/env python
    2. 

  2. # txt2tags - generic text conversion tool
    3. 

  3. # http://txt2tags.sf.net
    4. 

  4. #
    5. 

  5. # Copyright 2001, 2002 Aurélio Marinho Jargas
    6. 

  6. #
    7. 

  7. #   This program is free software; you can redistribute it and/or modify
    8. 

  8. #   it under the terms of the GNU General Public License as published by
    9. 

  9. #   the Free Software Foundation, version 2.
    10. 

  10. #
    11. 

  11. #   This program is distributed in the hope that it will be useful,
    12. 

  12. #   but WITHOUT ANY WARRANTY; without even the implied warranty of
    13. 

  13. #   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    14. 

  14. #   GNU General Public License for more details.
    15. 

  15. #
    16. 

  16. #   You have received a copy of the GNU General Public License along
    17. 

  17. #   with this program, on the COPYING file.
    18. 

  18. #
    19. 

  19. 

  20. # the code is getting better, but is still ugly - stay tunned
    21. 

  21. 

  22. 

  23. import re, string, os, sys, getopt, traceback
    24. 

  24. from time import strftime,time,localtime
    25. 

  25. 

  26. my_url = 'http://txt2tags.sf.net'
    27. 

  27. my_email = 'aurelio@verde666.org'
    28. 

  28. my_version = '1.4'
    29. 

  29. 

  30. DEBUG = 0   # do not edit here, please use --debug
    31. 

  31. targets = ['txt', 'sgml', 'html', 'pm6', 'mgp', 'moin', 'man', 'tex']
    32. 

  32. FLAGS   = {'noheaders':0,'enumtitle':0,'maskemail':0, 'stdout':0,
    33. 

  33.            'toconly'  :0,'toc'      :0,'gui'      :0}
    34. 

  34. OPTIONS = {'toclevel' :3,'style'    :''}
    35. 

  35. regex = {}
    36. 

  36. TAGS = {}
    37. 

  37. rules = {}
    38. 

  38. CMDLINE = ''
    39. 

  39. 

  40. currdate = strftime('%Y%m%d',localtime(time()))    # ISO current date
    41. 

  41. splitlevel = '' ; lang = 'english'
    42. 

  42. doctype = outfile = ''
    43. 

  43. pipefileid = '-'
    44. 

  44. 

  45. #my_version = my_version + '-dev' + currdate[4:]  # devel!
    46. 

  46. 

  47. # global vars for doClose*()
    48. 

  48. quotedepth = []
    49. 

  49. listindent = []
    50. 

  50. listids = []
    51. 

  51. subarea = None
    52. 

  52. tableborder = 0
    53. 

  53. 

  54. versionstr = "txt2tags version %s <%s>"%(my_version,my_url)
    55. 

  55. usage = """
    56. 

  56. %s
    57. 

  57. 

  58. usage: txt2tags -t <type> [OPTIONS] file.t2t
    59. 

  59.        txt2tags -t html -s <split level> -l <lang> file.t2t
    60. 

  60. 

  61.   -t, --type        set target document type. actually supported:
    62. 

  62.                     %s
    63. 

  63. 

  64.       --stdout      send output to STDOUT instead writing to a file
    65. 

  65.       --noheaders   suppress header, title and footer information
    66. 

  66.       --enumtitle   enumerate all title lines as 1, 1.1, 1.1.1, etc
    67. 

  67.       --maskemail   hide email from spam robots. x@y.z turns <x (a) y z>
    68. 

  68. 

  69.       --toc         add TOC (Table of Contents) to target document
    70. 

  70.       --toconly     print document TOC and exit
    71. 

  71.       --toclevel N  set maximum TOC level (deepness) to N
    72. 

  72. 	  
    73. 

  73.       --gui         invoke Graphical Tk Interface
    74. 

  74.       --style FILE  use FILE as the document style (like Html CSS)
    75. 

  75. 

  76.   -h, --help        print this help information and exit
    77. 

  77.   -V, --version     print program version and exit
    78. 

  78. 

  79. extra options for HTML target (needs sgml-tools):
    80. 

  80.       --split       split documents. values: 0, 1, 2 (default 0)
    81. 

  81.       --lang        document language (default english)
    82. 

  82. 

  83. 

  84. If input file is '-', reads from STDIN. Output is saved to
    85. 

  85. 'file.<type>' file, unless --stdout is specified.
    86. 

  86. """%(versionstr, re.sub(r"[]'[]",'',repr(targets)))
    87. 

    88. 

  88. 

  89. # here is all the target's templates
    90. 

  90. # you may edit them to fit your needs
    91. 

  91. #  - the %(HEADERn)s strings represent the Header lines
    92. 

  92. #  - use %% to represent a literal %
    93. 

  93. #
    94. 

  94. HEADER_TEMPLATE = {
    95. 

  95.   'txt': """\
    96. 

  96. %(HEADER1)s
    97. 

  97. %(HEADER2)s
    98. 

  98. %(HEADER3)s
    99. 

  99. """,
    100. 

    101. 

  101.   'sgml': """\
    102. 

  102. <!doctype linuxdoc system>
    103. 

  103. <article>
    104. 

  104. <title>%(HEADER1)s
    105. 

  105. <author>%(HEADER2)s
    106. 

  106. <date>%(HEADER3)s
    107. 

  107. """,
    108. 

    109. 

  109.   'html': """\
    110. 

  110. <HTML>
    111. 

  111. <HEAD>
    112. 

  112. <META NAME="generator" CONTENT="http://txt2tags.sf.net">
    113. 

  113. <META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=%(ENCODING)s">
    114. 

  114. <LINK REL="stylesheet" TYPE="text/css" HREF="%(STYLE)s">
    115. 

  115. <TITLE>%(HEADER1)s</TITLE>
    116. 

  116. </HEAD><BODY BGCOLOR="white" TEXT="black">
    117. 

  117. <P ALIGN="center"><CENTER><H1>%(HEADER1)s</H1>
    118. 

  118. <FONT SIZE=4>
    119. 

  119. <I>%(HEADER2)s</I><BR>
    120. 

  120. %(HEADER3)s
    121. 

  121. </FONT></CENTER>
    122. 

  122. """,
    123. 

    124. 

  124. 

  125. # TODO man section 1 is hardcoded...
    126. 

  126.   'man': """\
    127. 

  127. .TH "%(HEADER1)s" 1 %(HEADER3)s "%(HEADER2)s"
    128. 

  128. """,
    129. 

    130. 

  130. # TODO style to <HR>
    131. 

  131.   'pm6': """\
    132. 

  132. <PMTags1.0 win><C-COLORTABLE ("Preto" 1 0 0 0)
    133. 

  133. ><@Normal=
    134. 

  134.   <FONT "Times New Roman"><CCOLOR "Preto"><SIZE 11>
    135. 

  135.   <HORIZONTAL 100><LETTERSPACE 0><CTRACK 127><CSSIZE 70><C+SIZE 58.3>
    136. 

  136.   <C-POSITION 33.3><C+POSITION 33.3><P><CBASELINE 0><CNOBREAK 0><CLEADING -0.05>
    137. 

  137.   <GGRID 0><GLEFT 7.2><GRIGHT 0><GFIRST 0><G+BEFORE 7.2><G+AFTER 0>
    138. 

  138.   <GALIGNMENT "justify"><GMETHOD "proportional"><G& "ENGLISH">
    139. 

  139.   <GPAIRS 12><G%% 120><GKNEXT 0><GKWIDOW 0><GKORPHAN 0><GTABS $>
    140. 

  140.   <GHYPHENATION 2 34 0><GWORDSPACE 75 100 150><GSPACE -5 0 25>
    141. 

  141. ><@Bullet=<@-PARENT "Normal"><FONT "Abadi MT Condensed Light">
    142. 

  142.   <GLEFT 14.4><G+BEFORE 2.15><G%% 110><GTABS(25.2 l "")>
    143. 

  143. ><@PreFormat=<@-PARENT "Normal"><FONT "Lucida Console"><SIZE 8><CTRACK 0>
    144. 

  144.   <GLEFT 0><G+BEFORE 0><GALIGNMENT "left"><GWORDSPACE 100 100 100><GSPACE 0 0 0>
    145. 

  145. ><@Title1=<@-PARENT "Normal"><FONT "Arial"><SIZE 14><B>
    146. 

  146.   <GCONTENTS><GLEFT 0><G+BEFORE 0><GALIGNMENT "left">
    147. 

  147. ><@Title2=<@-PARENT "Title1"><SIZE 12><G+BEFORE 3.6>
    148. 

  148. ><@Title3=<@-PARENT "Title1"><SIZE 10><GLEFT 7.2><G+BEFORE 7.2>
    149. 

  149. ><@Title4=<@-PARENT "Title3">
    150. 

  150. ><@Title5=<@-PARENT "Title3">
    151. 

  151. ><@Quote=<@-PARENT "Normal"><SIZE 10><I>>
    152. 

  152. 

  153. %(HEADER1)s
    154. 

  154. %(HEADER2)s
    155. 

  155. %(HEADER3)s
    156. 

  156. """,
    157. 

    158. 

  158.   'mgp': """\
    159. 

  159. #!/usr/X11R6/bin/mgp -t 90
    160. 

  160. %%deffont "normal"    xfont  "utopia-medium-r", charset "iso8859-1"
    161. 

  161. %%deffont "normal-i"  xfont  "utopia-medium-i", charset "iso8859-1"
    162. 

  162. %%deffont "normal-b"  xfont  "utopia-bold-r"  , charset "iso8859-1"
    163. 

  163. %%deffont "normal-bi" xfont  "utopia-bold-i"  , charset "iso8859-1"
    164. 

  164. %%deffont "mono"      xfont "courier-medium-r", charset "iso8859-1"
    165. 

  165. %%default 1 size 5
    166. 

  166. %%default 2 size 8, fore "yellow", font "normal-b", center
    167. 

  167. %%default 3 size 5, fore "white",  font "normal", left, prefix "  "
    168. 

  168. %%tab 1 size 4, vgap 30, prefix "     ", icon arc "red" 40, leftfill
    169. 

  169. %%tab 2 prefix "            ", icon arc "orange" 40, leftfill
    170. 

  170. %%tab 3 prefix "                   ", icon arc "brown" 40, leftfill
    171. 

  171. %%tab 4 prefix "                          ", icon arc "darkmagenta" 40, leftfill
    172. 

  172. %%tab 5 prefix "                                ", icon arc "magenta" 40, leftfill
    173. 

  173. %%%%------------------------- end of headers -----------------------------
    174. 

  174. %%page
    175. 

  175. 

  176. 

  177. 

  178. 

  179. 

  180. %%size 10, center, fore "yellow"
    181. 

  181. %(HEADER1)s
    182. 

  182. 

  183. %%font "normal-i", size 6, fore "white", center
    184. 

  184. %(HEADER2)s
    185. 

  185. 

  186. %%font "mono", size 7, center
    187. 

  187. %(HEADER3)s
    188. 

  188. """,
    189. 

    190. 

  190. # TODO please, improve me!
    191. 

  191.   'moin': """\
    192. 

  192. %(HEADER1)s
    193. 

  193. %(HEADER2)s
    194. 

  194. %(HEADER3)s
    195. 

  195. """,
    196. 

    197. 

  197.   'tex': \
    198. 

  198. r"""\documentclass[11pt,a4paper]{article}
    199. 

  199. \usepackage{amsfonts,amssymb,graphicx,url}
    200. 

  200. \usepackage[%(ENCODING)s]{inputenc}  %% char encoding
    201. 

  201. \pagestyle{plain}   %% do page numbering ('empty' turns off)
    202. 

  202. \frenchspacing      %% no aditional spaces after periods
    203. 

  203. \setlength{\parskip}{8pt}\parindent=0pt  %% no paragraph indentation
    204. 

  204. %% uncomment next line for fancy PDF output on Adobe Acrobat Reader
    205. 

  205. %%\usepackage[pdfstartview=FitV,colorlinks=true,bookmarks=true]{hyperref}
    206. 

  206. 

  207. \title{%(HEADER1)s}
    208. 

  208. \author{%(HEADER2)s}
    209. 

  209. \begin{document}
    210. 

  210. \date{%(HEADER3)s}
    211. 

  211. \maketitle
    212. 

  212. """
    213. 

  213. }
    214. 

  214. 

  215. #-----------------------------------------------------------------------
    216. 

  216. 

  217. def Quit(msg, exitcode=0): print msg ; sys.exit(exitcode)
    218. 

  218. def Error(msg): print "ERROR: %s"%msg ; sys.exit()
    219. 

  219. def Debug(msg,i=0,linenr=None):
    220. 

  220. 	if i > DEBUG: return
    221. 

  221. 	if linenr is not None:
    222. 

  222. 		print "(%d) %04d:%s"%(i,linenr,msg)
    223. 

  223. 	else:
    224. 

  224. 		print "(%d) %s"%(i,msg)
    225. 

  225. def Readfile(file):
    226. 

  226. 	if file == '-':
    227. 

  227. 		try: data = sys.stdin.readlines()
    228. 

  228. 		except: Error('You must feed me with data on STDIN!')
    229. 

  229. 	else:
    230. 

  230. 		try: f = open(file); data = f.readlines() ; f.close()
    231. 

  231. 		except: Error("Cannot read file:\n    %s"%file)
    232. 

  232. 	return data
    233. 

  233. def Savefile(file, contents):
    234. 

  234. 	try: f = open(file, 'w')
    235. 

  235. 	except: Error("Cannot open file for writing:\n    %s"%file)
    236. 

  236. 	if type(contents) == type([]): doit = f.writelines
    237. 

  237. 	else: doit = f.write
    238. 

  238. 	doit(contents) ; f.close()
    239. 

  239. 

  240. def NewArea(new, linenr):
    241. 

  241. 	if new not in ['head', 'conf', 'body']:
    242. 

  242. 		Error("Invalid new AREA '%s' on line '%s'"%(new,linenr))
    243. 

  243. 	Debug('NEW AREA: %s'%new, 1, linenr)
    244. 

  244. 	return new
    245. 

  245. 

  246. def reset_flags():
    247. 

  247. 	global FLAGS
    248. 

  248. 	for flag in FLAGS.keys(): FLAGS[flag] = 0
    249. 

  249. 

  250. def set_outfile_name(infile, doctype):
    251. 

  251. 	"dirname is the same for {in,out}file"
    252. 

  252. 	if not infile: return
    253. 

  253. 	if infile == pipefileid or FLAGS['toconly'] or FLAGS['stdout']:
    254. 

  254. 		outfile = pipefileid
    255. 

  255. 	else:
    256. 

  256. 		outfile = "%s.%s"%(re.sub('\.(txt|t2t)$','',infile), doctype)
    257. 

  257. 	Debug(" infile: '%s'"% infile, 1)
    258. 

  258. 	Debug("outfile: '%s'"%outfile, 1)
    259. 

  259. 	return outfile
    260. 

  260. 

  261. def finish_him(outlist, outfile):
    262. 

  262. 	"writing output to screen or file"
    263. 

  263. 	if outfile == pipefileid:
    264. 

  264. 		for line in outlist: print line
    265. 

  265. 	else:
    266. 

  266. 		Savefile(outfile, addLineBreaks(outlist))
    267. 

  267. 		if not FLAGS['gui']: print 'wrote %s'%(outfile)
    268. 

  268. 	
    269. 

  269. 	if splitlevel:
    270. 

  270. 		print "--- html..."
    271. 

  271. 		os.system('sgml2html --language=%s --split=%s %s'%(
    272. 

  272. 		           lang,splitlevel,outfile))
    273. 

  273. 

  274. def ParseCmdline(cmdline=sys.argv):
    275. 

  275. 	"return a dic with all options:value found"
    276. 

  276. 	global CMDLINE ; CMDLINE = cmdline  # save for dofooter()
    277. 

  277. 	Debug("cmdline: %s"%cmdline, 1)
    278. 

  278. 	options = {'infile': '', 'infiles':''}
    279. 

  279. 	
    280. 

  280. 	# get cmdline options
    281. 

  281. 	longopt = ['help','version','type=','split=','lang='] +FLAGS.keys()
    282. 

  282. 	longopt = longopt + map(lambda x:x+'=', OPTIONS.keys()) # add =
    283. 

  283. 	try: (opt, args) = getopt.getopt(cmdline[1:], 'hVt:', longopt)
    284. 

  284. 	except getopt.GetoptError:
    285. 

  285. 		Error('Bad option or missing argument (try --help)')
    286. 

  286. 	
    287. 

  287. 	# get infile, if any
    288. 

  288. 	if args:
    289. 

  289. 		options['infile'] = args[0]
    290. 

  290. 		options['infiles'] = args  # multi
    291. 

  291. 	
    292. 

  292. 	for name,val in opt:
    293. 

  293. 		# parse information options
    294. 

  294. 		if   name in ['-h','--help'   ]: Quit(usage)
    295. 

  295. 		elif name in ['-V','--version']: Quit(versionstr)
    296. 

  296. 		# parse short/long options
    297. 

  297. 		elif name in ['-t','--type']:
    298. 

  298. 			options['doctype'] = val
    299. 

  299. 			continue
    300. 

  300. 		# just long options
    301. 

  301. 		options[name[2:]] = val  # del --
    302. 

  302. 	
    303. 

  303. 	Debug("cmdline arguments: %s"%options, 1)
    304. 

  304. 	return options
    305. 

  305. 

  306. 

  307. def ParseCmdlineOptions(optdic):
    308. 

  308. 	"set vars and flags according to options dic"
    309. 

  309. 	global FLAGS, OPTIONS, splitlevel, lang
    310. 

  310. 	
    311. 

  311. 	# store flags
    312. 

  312. 	myflags = [] # for debug msg
    313. 

  313. 	for flag in FLAGS.keys():
    314. 

  314. 		if optdic.has_key(flag):
    315. 

  315. 			FLAGS[flag] = 1
    316. 

  316. 			myflags.append(flag)
    317. 

  317. 	# and now options
    318. 

  318. 	for opt in OPTIONS.keys():
    319. 

  319. 		opttype = type(OPTIONS[opt])
    320. 

  320. 		val = optdic.get(opt)
    321. 

  321. 		if val:
    322. 

  322. 			if opttype == type(9):
    323. 

  323. 				try: val = int(val)
    324. 

  324. 				except: Error('--%s value must be a number'%opt)
    325. 

  325. 			OPTIONS[opt] = val
    326. 

  326. 	# finally, the most important vars
    327. 

  327. 	doctype    = optdic.get('doctype')
    328. 

  328. 	infile     = optdic.get('infile')
    329. 

  329. 	splitlevel = optdic.get('split')
    330. 

  330. 	lang       = optdic.get('lang')
    331. 

  331. 	Debug("cmdline flags: %s"%string.join(myflags,', '), 1)
    332. 

  332. 	Debug("cmdline options: %s"%OPTIONS, 1)
    333. 

  333. 	
    334. 

  334. 	if not doctype and FLAGS['toconly']: doctype = 'txt' # toconly dft type
    335. 

  335. 	if not infile or not doctype: Quit(usage, 1)    # no filename/doctype
    336. 

  336. 	
    337. 

  337. 	# sanity check: validate target type
    338. 

  338. 	if not targets.count(doctype):
    339. 

  339. 		Error("Invalid document type '%s' (try --help)"%(doctype))
    340. 

  340. 	
    341. 

  341. 	outfile = set_outfile_name(infile, doctype)
    342. 

  342. 	
    343. 

  343. 	# sanity check: validate split level
    344. 

  344. 	if doctype != 'html': splitlevel = '' # only valid for HTML target
    345. 

  345. 	if splitlevel:
    346. 

  346. 		# checkings
    347. 

  347. 		if outfile == pipefileid:
    348. 

  348. 			Error('You need to provide a FILE (not STDIN) '
    349. 

  349. 			      'when using --split')
    350. 

  350. 		if splitlevel[0] not in '012':
    351. 

  351. 			Error('Option --split must be 0, 1 or 2')
    352. 

  352. 		# check for sgml-tools
    353. 

  353. 		#TODO how to test (in a clever way) if an executable is in path?
    354. 

  354. 		#TODO os.system() return code? sgml2html w/out --help exit 0?
    355. 

  355. 		#TODO bah! implement sgml2html split natively and we're done
    356. 

  356. 		# Error("Sorry, you must have 'sgml2html' to use --split")
    357. 

  357. 		
    358. 

  358. 		# set things
    359. 

  359. 		FLAGS['stdout'] = 0  # no --stdout
    360. 

  360. 		doctype = 'sgml'     # 1st do a sgml, then sgml2html
    361. 

  361. 		outfile = set_outfile_name(infile, doctype)
    362. 

  362. 	
    363. 

  363. 	# sanity check: source loss!
    364. 

  364. 	if infile != pipefileid and infile == outfile:
    365. 

  365. 		Error("SUICIDE WARNING!!!   (try --stdout)\n  source"+\
    366. 

  366. 		      " and target files has the same name: %s"%outfile)
    367. 

  367. 	### yes, i've got my sample.t2t file deleted before add this test... :/
    368. 

  368. 	
    369. 

  369. 	return infile,outfile,doctype
    370. 

  370. 	#TODO splitlevel, lang
    371. 

  371. 

  372. #---End of ParseCmdlineOptions
    373. 

  373. 

  374. def toc_master(doctype, header, doc, toc):
    375. 

  375. 	"decide to include TOC or not on the outlist"
    376. 

  376. 	
    377. 

  377. 	# deal with the TOC options
    378. 

  378. 	if FLAGS['toc'] or FLAGS['toconly']:
    379. 

  379. 		# format TOC lines
    380. 

  380. 		### here we do toc as a valid t2t marked text (list type)
    381. 

  381. 		FLAGS['noheaders'] = 1
    382. 

  382. 		x,y,toc = convert(['']+toc+['',''], doctype)
    383. 

  383. 		
    384. 

  384. 		# TOC between bars (not for --toconly)
    385. 

  385. 		if FLAGS['toc']:
    386. 

  386. 			para = TAGS['paragraph']
    387. 

  387. 			tocbar = [para, regex['x'].sub('-'*72,TAGS['bar1']), para]
    388. 

  388. 			toc = tocbar + toc + tocbar
    389. 

  389. 		
    390. 

  390. 		if FLAGS['toconly']: header = doc = []
    391. 

  391. 	else:
    392. 

  392. 		toc = []
    393. 

  393. 	
    394. 

  394. 	# TOC is a tag
    395. 

  395. 	if TAGS['TOC'] and not FLAGS['toconly']:
    396. 

  396. 		toc = []
    397. 

  397. 	
    398. 

  398. 	return header + toc + doc
    399. 

  399. 

  400. 

  401. def doitall(cmdlinedic):
    402. 

  402. 	global outfile
    403. 

  403. 	infile,outfile,doctype = ParseCmdlineOptions(cmdlinedic)
    404. 

  404. 	header,toc,doc = convert(Readfile(infile), doctype)
    405. 

  405. 	outlist = toc_master(doctype,header,doc,toc)
    406. 

  406. 	return doctype, outfile, outlist
    407. 

  407. 

  408. 

  409. # set the Line Break across platforms
    410. 

  410. LB = '\n'                                   # default
    411. 

  411. if   sys.platform[:3] == 'win': LB = '\r\n'
    412. 

  412. #elif sys.platform[:3] == 'cyg': LB = '\r\n' # not sure if it's best :(
    413. 

  413. elif sys.platform[:3] == 'mac': LB = '\r'
    414. 

  414. 

  415. 

  416. def escapePythonSpecials(txt):
    417. 

  417. 	# drawback of using re.sub() - double escape some specials like \n
    418. 

  418. 	# see also: 'force_re' marks on the code
    419. 

  419. 	if sys.version[0] == '1':
    420. 

  420. 		return re.sub(r'(\\[ntsrfvul])',r'\\\1',txt)
    421. 

  421. 	else:
    422. 

  422. 		return re.sub(r'(\\[ntsrfv])'  ,r'\\\1',txt)
    423. 

  423. 

  424. def getTags(doctype):
    425. 

  425. 	keys = [
    426. 

  426. 	'paragraph','title1','title2','title3','title4','title5',
    427. 

  427. 	'areaPreOpen','areaPreClose',
    428. 

  428. 	'areaQuoteOpen','areaQuoteClose',
    429. 

  429. 	'fontMonoOpen','fontMonoClose',
    430. 

  430. 	'fontBoldOpen','fontBoldClose',
    431. 

  431. 	'fontItalicOpen','fontItalicClose',
    432. 

  432. 	'fontBolditalicOpen','fontBolditalicClose',
    433. 

  433. 	'fontUnderlineOpen','fontUnderlineClose',
    434. 

  434. 	'listOpen','listClose','listItem',
    435. 

  435. 	'numlistOpen','numlistClose','numlistItem',
    436. 

  436. 	'deflistOpen','deflistClose','deflistItem1','deflistItem2',
    437. 

  437. 	'bar1','bar2',
    438. 

  438. 	'url','urlMark','email','emailMark',
    439. 

  439. 	'img','imgsolo',
    440. 

  440. 	'tableOpen','tableClose','tableLineOpen','tableLineClose',
    441. 

  441. 	'tableCellOpen','tableCellClose',
    442. 

  442. 	'tableTitleCellOpen','tableTitleCellClose',
    443. 

  443. 	'anchor','comment','TOC',
    444. 

  444. 	'EOD'
    445. 

  445. 	]
    446. 

  446. 	
    447. 

  447. 	if doctype == "txt":
    448. 

  448. 		tags = {
    449. 

  449. 		'title1'              : '  \a'      ,
    450. 

  450. 		'title2'              : '\t\a'      ,
    451. 

  451. 		'title3'              : '\t\t\a'    ,
    452. 

  452. 		'title4'              : '\t\t\t\a'  ,
    453. 

  453. 		'title5'              : '\t\t\t\t\a',
    454. 

  454. 		'areaQuoteOpen'       : '    '      ,
    455. 

  455. 		'listItem'            : '- '        ,
    456. 

  456. 		'numlistItem'         : '\a. '      ,
    457. 

  457. 		'bar1'                : '\a'        ,
    458. 

  458. 		'bar2'                : '\a'        ,
    459. 

  459. 		'url'                 : '\a'        ,
    460. 

  460. 		'urlMark'             : '\a (\a)'   ,
    461. 

  461. 		'email'               : '\a'        ,
    462. 

  462. 		'emailMark'           : '\a (\a)'   ,
    463. 

  463. 		'img'                 : '[\a]'      ,
    464. 

  464. 		}
    465. 

  465. 	
    466. 

  466. 	elif doctype == "html":
    467. 

  467. 		tags = {
    468. 

  468. 		'paragraph'           : '<P>'            ,
    469. 

  469. 		'title1'              : '<H1>\a</H1>'    ,
    470. 

  470. 		'title2'              : '<H2>\a</H2>'    ,
    471. 

  471. 		'title3'              : '<H3>\a</H3>'    ,
    472. 

  472. 		'title4'              : '<H4>\a</H4>'    ,
    473. 

  473. 		'title5'              : '<H5>\a</H5>'    ,
    474. 

  474. 		'areaPreOpen'         : '<PRE>'          ,
    475. 

  475. 		'areaPreClose'        : '</PRE>'         ,
    476. 

  476. 		'areaQuoteOpen'       : '<BLOCKQUOTE>'   ,
    477. 

  477. 		'areaQuoteClose'      : '</BLOCKQUOTE>'  ,
    478. 

  478. 		'fontMonoOpen'        : '<CODE>'         ,
    479. 

  479. 		'fontMonoClose'       : '</CODE>'        ,
    480. 

  480. 		'fontBoldOpen'        : '<B>'            ,
    481. 

  481. 		'fontBoldClose'       : '</B>'           ,
    482. 

  482. 		'fontItalicOpen'      : '<I>'            ,
    483. 

  483. 		'fontItalicClose'     : '</I>'           ,
    484. 

  484. 		'fontBolditalicOpen'  : '<B><I>'         ,
    485. 

  485. 		'fontBolditalicClose' : '</I></B>'       ,
    486. 

  486. 		'fontUnderlineOpen'   : '<U>'            ,
    487. 

  487. 		'fontUnderlineClose'  : '</U>'           ,
    488. 

  488. 		'listOpen'            : '<UL>'           ,
    489. 

  489. 		'listClose'           : '</UL>'          ,
    490. 

  490. 		'listItem'            : '<LI>'           ,
    491. 

  491. 		'numlistOpen'         : '<OL>'           ,
    492. 

  492. 		'numlistClose'        : '</OL>'          ,
    493. 

  493. 		'numlistItem'         : '<LI>'           ,
    494. 

  494. 		'deflistOpen'         : '<DL>'           ,
    495. 

  495. 		'deflistClose'        : '</DL>'          ,
    496. 

  496. 		'deflistItem1'        : '<DT>\a</DT>'    ,
    497. 

  497. 		'deflistItem2'        : '<DD>'           ,
    498. 

  498. 		'bar1'                : '<HR NOSHADE SIZE=1>'        ,
    499. 

  499. 		'bar2'                : '<HR NOSHADE SIZE=5>'        ,
    500. 

  500. 		'url'                 : '<A HREF="\a">\a</A>'        ,
    501. 

  501. 		'urlMark'             : '<A HREF="\a">\a</A>'        ,
    502. 

  502. 		'email'               : '<A HREF="mailto:\a">\a</A>' ,
    503. 

  503. 		'emailMark'           : '<A HREF="mailto:\a">\a</A>' ,
    504. 

  504. 		'img'                 : '<IMG ALIGN="\a" SRC="\a" BORDER="0">',
    505. 

  505. 		'imgsolo'             : '<P ALIGN="center">\a</P>'   ,
    506. 

  506. 		'tableOpen'           : '<table\a cellpadding=4 border=\a>',
    507. 

  507. 		'tableClose'          : '</table>'       ,
    508. 

  508. 		'tableLineOpen'       : '<tr>'           ,
    509. 

  509. 		'tableLineClose'      : '</tr>'          ,
    510. 

  510. 		'tableCellOpen'       : '<td\a>'         ,
    511. 

  511. 		'tableCellClose'      : '</td>'          ,
    512. 

  512. 		'tableTitleCellOpen'  : '<th>'           ,
    513. 

  513. 		'tableTitleCellClose' : '</th>'          ,
    514. 

  514. 		'tableAlignLeft'      : ''               ,
    515. 

  515. 		'tableAlignCenter'    : ' align="center"',
    516. 

  516. 		'tableCellAlignLeft'  : ''               ,
    517. 

  517. 		'tableCellAlignRight' : ' align="right"' ,
    518. 

  518. 		'tableCellAlignCenter': ' align="center"',
    519. 

  519. 		'anchor'              : '<a name="\a">'  ,
    520. 

  520. 		'comment'             : '<!-- \a -->'    ,
    521. 

  521. 		'EOD'                 : '</BODY></HTML>'
    522. 

  522. 		}
    523. 

  523. 	
    524. 

  524. 	elif doctype == "sgml":
    525. 

  525. 		tags = {
    526. 

  526. 		'paragraph'           : '<p>'                ,
    527. 

  527. 		'title1'              : '<sect>\a<p>'        ,
    528. 

  528. 		'title2'              : '<sect1>\a<p>'       ,
    529. 

  529. 		'title3'              : '<sect2>\a<p>'       ,
    530. 

  530. 		'title4'              : '<sect3>\a<p>'       ,
    531. 

  531. 		'title5'              : '<sect4>\a<p>'       ,
    532. 

  532. 		'areaPreOpen'         : '<tscreen><verb>'    ,
    533. 

  533. 		'areaPreClose'        : '</verb></tscreen>'  ,
    534. 

  534. 		'areaQuoteOpen'       : '<quote>'            ,
    535. 

  535. 		'areaQuoteClose'      : '</quote>'           ,
    536. 

  536. 		'fontMonoOpen'        : '<tt>'               ,
    537. 

  537. 		'fontMonoClose'       : '</tt>'              ,
    538. 

  538. 		'fontBoldOpen'        : '<bf>'               ,
    539. 

  539. 		'fontBoldClose'       : '</bf>'              ,
    540. 

  540. 		'fontItalicOpen'      : '<em>'               ,
    541. 

  541. 		'fontItalicClose'     : '</em>'              ,
    542. 

  542. 		'fontBolditalicOpen'  : '<bf><em>'           ,
    543. 

  543. 		'fontBolditalicClose' : '</em></bf>'         ,
    544. 

  544. 		'fontUnderlineOpen'   : '<bf><em>'           ,
    545. 

  545. 		'fontUnderlineClose'  : '</em></bf>'         ,
    546. 

  546. 		'listOpen'            : '<itemize>'          ,
    547. 

  547. 		'listClose'           : '</itemize>'         ,
    548. 

  548. 		'listItem'            : '<item>'             ,
    549. 

  549. 		'numlistOpen'         : '<enum>'             ,
    550. 

  550. 		'numlistClose'        : '</enum>'            ,
    551. 

  551. 		'numlistItem'         : '<item>'             ,
    552. 

  552. 		'deflistOpen'         : '<descrip>'          ,
    553. 

  553. 		'deflistClose'        : '</descrip>'         ,
    554. 

  554. 		'deflistItem1'        : '<tag>\a</tag>'      ,
    555. 

  555. 		'bar1'                : '<!-- \a -->'        ,
    556. 

  556. 		'bar2'                : '<!-- \a -->'        ,
    557. 

  557. 		'url'                 : '<htmlurl url="\a" name="\a">'        ,
    558. 

  558. 		'urlMark'             : '<htmlurl url="\a" name="\a">'        ,
    559. 

  559. 		'email'               : '<htmlurl url="mailto:\a" name="\a">' ,
    560. 

  560. 		'emailMark'           : '<htmlurl url="mailto:\a" name="\a">' ,
    561. 

  561. 		'img'                 : '<figure><ph vspace=""><img src="\a"></figure>',
    562. 

  562. 		'tableOpen'           : '<table><tabular ca="\a">'            ,
    563. 

  563. 		'tableClose'          : '</tabular></table>' ,
    564. 

  564. 		'tableLineClose'      : '<rowsep>'           ,
    565. 

  565. 		'tableCellClose'      : '<colsep>'           ,
    566. 

  566. 		'tableTitleCellClose' : '<colsep>'           ,
    567. 

  567. 		'tableColAlignLeft'   : 'l'                  ,
    568. 

  568. 		'tableColAlignRight'  : 'r'                  ,
    569. 

  569. 		'tableColAlignCenter' : 'c'                  ,
    570. 

  570. 		'comment'             : '<!-- \a -->'        ,
    571. 

  571. 		'TOC'                 : '<toc>'              ,
    572. 

  572. 		'EOD'                 : '</article>'
    573. 

  573. 		}
    574. 

  574. 	
    575. 

  575. 	elif doctype == "tex":
    576. 

  576. 		tags = {
    577. 

  577. 		'title1'              : '\n\\newpage\section{\a}',
    578. 

  578. 		'title2'              : '\\subsection{\a}'       ,
    579. 

  579. 		'title3'              : '\\subsubsection{\a}'    ,
    580. 

  580. 		# title 4/5: DIRTY: para+BF+\\+\n
    581. 

  581. 		'title4'              : '\\paragraph{}\\textbf{\a}\\\\\\\n',
    582. 

  582. 		'title5'              : '\\paragraph{}\\textbf{\a}\\\\\\\n',
    583. 

  583. 		'areaPreOpen'         : '\\begin{verbatim}'   ,
    584. 

  584. 		'areaPreClose'        : '\\end{verbatim}'     ,
    585. 

  585. 		'areaQuoteOpen'       : '\\begin{quotation}'  ,
    586. 

  586. 		'areaQuoteClose'      : '\\end{quotation}'    ,
    587. 

  587. 		'fontMonoOpen'        : '\\texttt{'           ,
    588. 

  588. 		'fontMonoClose'       : '}'                   ,
    589. 

  589. 		'fontBoldOpen'        : '\\textbf{'           ,
    590. 

  590. 		'fontBoldClose'       : '}'                   ,
    591. 

  591. 		'fontItalicOpen'      : '\\textit{'           ,
    592. 

  592. 		'fontItalicClose'     : '}'                   ,
    593. 

  593. 		'fontBolditalicOpen'  : '\\textbf{\\textit{'  ,
    594. 

  594. 		'fontBolditalicClose' : '}}'                  ,
    595. 

  595. 		'fontUnderlineOpen'   : '\\underline{'        ,
    596. 

  596. 		'fontUnderlineClose'  : '}'                   ,
    597. 

  597. 		'listOpen'            : '\\begin{itemize}'    ,
    598. 

  598. 		'listClose'           : '\\end{itemize}'      ,
    599. 

  599. 		'listItem'            : '\\item '             ,
    600. 

  600. 		'numlistOpen'         : '\\begin{enumerate}'  ,
    601. 

  601. 		'numlistClose'        : '\\end{enumerate}'    ,
    602. 

  602. 		'numlistItem'         : '\\item '             ,
    603. 

  603. 		'deflistOpen'         : '\\begin{description}',
    604. 

  604. 		'deflistClose'        : '\\end{description}'  ,
    605. 

  605. 		'deflistItem1'        : '\\item[\a]'          ,
    606. 

  606. 		'bar1'                : '\n\\hrulefill{}\n'   ,
    607. 

  607. 		'bar2'                : '\n\\rule{\linewidth}{1mm}\n',
    608. 

  608. 		'url'                 : '\\url{\a}'                  ,
    609. 

  609. 		'urlMark'             : '\\textit{\a} (\\url{\a})'   ,
    610. 

  610. 		'email'               : '\\url{\a}'                  ,
    611. 

  611. 		'emailMark'           : '\\textit{\a} (\\url{\a})'   ,
    612. 

  612. 		'img'                 : '(\a)'                       ,
    613. 

  613. 		'tableOpen'           : '\\begin{center}\\begin{tabular}{\a|}',
    614. 

  614. 		'tableClose'          : '\\end{tabular}\\end{center}',
    615. 

  615. 		'tableLineOpen'       : '\\hline ' ,
    616. 

  616. 		'tableLineClose'      : ' \\\\'    ,
    617. 

  617. 		'tableCellClose'      : ' & '      ,
    618. 

  618. 		'tableTitleCellOpen'  : '\\textbf{',
    619. 

  619. 		'tableTitleCellClose' : '} & '     ,
    620. 

  620. 		'tableColAlignLeft'   : '|l'       ,
    621. 

  621. 		'tableColAlignRight'  : '|r'       ,
    622. 

  622. 		'tableColAlignCenter' : '|c'       ,
    623. 

  623. 		'comment'             : '% \a'     ,
    624. 

  624. 		'TOC'                 : '\\newpage\\tableofcontents',
    625. 

  625. 		'EOD'                 : '\\end{document}'
    626. 

  626. 		}
    627. 

  627. 	
    628. 

  628. 	elif doctype == "moin":
    629. 

  629. 		tags = {
    630. 

  630. 		'title1'              : '= \a ='        ,
    631. 

  631. 		'title2'              : '== \a =='      ,
    632. 

  632. 		'title3'              : '=== \a ==='    ,
    633. 

  633. 		'title4'              : '==== \a ===='  ,
    634. 

  634. 		'title5'              : '===== \a =====',
    635. 

  635. 		'areaPreOpen'         : '{{{'           ,
    636. 

  636. 		'areaPreClose'        : '}}}'           ,
    637. 

  637. 		'areaQuoteOpen'       : ' '             ,
    638. 

  638. 		'fontMonoOpen'        : '{{{'           ,
    639. 

  639. 		'fontMonoClose'       : '}}}'           ,
    640. 

  640. 		'fontBoldOpen'        : "'''"           ,
    641. 

  641. 		'fontBoldClose'       : "'''"           ,
    642. 

  642. 		'fontItalicOpen'      : "''"            ,
    643. 

  643. 		'fontItalicClose'     : "''"            ,
    644. 

  644. 		'fontBolditalicOpen'  : "'''''"         ,
    645. 

  645. 		'fontBolditalicClose' : "'''''"         ,
    646. 

  646. 		'fontUnderlineOpen'   : "'''''"         ,
    647. 

  647. 		'fontUnderlineClose'  : "'''''"         ,
    648. 

  648. 		'listItem'            : '* '            ,
    649. 

  649. 		'numlistItem'         : '\a. '          ,
    650. 

  650. 		'bar1'                : '----'          ,
    651. 

  651. 		'bar2'                : '----'          ,
    652. 

  652. 		'url'                 : '[\a]'          ,
    653. 

  653. 		'urlMark'             : '[\a \a]'       ,
    654. 

  654. 		'email'               : '[\a]'          ,
    655. 

  655. 		'emailMark'           : '[\a \a]'       ,
    656. 

  656. 		'img'                 : '[\a]'          ,
    657. 

  657. 		'tableLineOpen'       : '||'            ,
    658. 

  658. 		'tableCellClose'      : '||'            ,
    659. 

  659. 		'tableTitleCellClose' : '||'            ,
    660. 

  660. 		}
    661. 

  661. 	
    662. 

  662. 	elif doctype == "mgp":
    663. 

  663. 		tags = {
    664. 

  664. 		'paragraph'           : '%font "normal", size 5\n'   ,
    665. 

  665. 		'title1'              : '%page\n\n\a'                ,
    666. 

  666. 		'title2'              : '%page\n\n\a'                ,
    667. 

  667. 		'title3'              : '%page\n\n\a'                ,
    668. 

  668. 		'title4'              : '%page\n\n\a'                ,
    669. 

  669. 		'title5'              : '%page\n\n\a'                ,
    670. 

  670. 		'areaPreOpen'         : '\n%font "mono"'             ,
    671. 

  671. 		'areaPreClose'        : '%font "normal"'             ,
    672. 

  672. 		'areaQuoteOpen'       : '%prefix "       "'          ,
    673. 

  673. 		'areaQuoteClose'      : '%prefix "  "'               ,
    674. 

  674. 		'fontMonoOpen'        : '\n%cont, font "mono"\n'     ,
    675. 

  675. 		'fontMonoClose'       : '\n%cont, font "normal"\n'   ,
    676. 

  676. 		'fontBoldOpen'        : '\n%cont, font "normal-b"\n' ,
    677. 

  677. 		'fontBoldClose'       : '\n%cont, font "normal"\n'   ,
    678. 

  678. 		'fontItalicOpen'      : '\n%cont, font "normal-i"\n' ,
    679. 

  679. 		'fontItalicClose'     : '\n%cont, font "normal"\n'   ,
    680. 

  680. 		'fontBolditalicOpen'  : '\n%cont, font "normal-bi"\n',
    681. 

  681. 		'fontBolditalicClose' : '\n%cont, font "normal"\n'   ,
    682. 

  682. 		'fontUnderlineOpen'   : '\n%cont, fore "cyan"\n'     ,
    683. 

  683. 		'fontUnderlineClose'  : '\n%cont, fore "white"\n'    ,
    684. 

  684. 		'numlistItem'         : '\a. '                       ,
    685. 

  685. 		'bar1'                : '%bar "white" 5'             ,
    686. 

  686. 		'bar2'                : '%pause'                     ,
    687. 

  687. 		'url'                 : '\n%cont, fore "cyan"\n\a\n%cont, fore "white"\n',
    688. 

  688. 		'urlMark'             : '\a \n%cont, fore "cyan"\n\a\n%cont, fore "white"\n',
    689. 

  689. 		'email'               : '\n%cont, fore "cyan"\n\a\n%cont, fore "white"\n',
    690. 

  690. 		'emailMark'           : '\a \n%cont, fore "cyan"\n\a\n%cont, fore "white"\n',
    691. 

  691. 		'img'                 : '\n%center\n%newimage "\a", left\n',
    692. 

  692. 		'comment'             : '%% \a'                      ,
    693. 

  693. 		'EOD'                 : '%%EOD'
    694. 

  694. 		}
    695. 

  695. 	
    696. 

  696. 	elif doctype == "man":
    697. 

  697. 		tags = {
    698. 

  698. 		'paragraph'           : '.P'     ,
    699. 

  699. 		'title1'              : '.SH \a' ,
    700. 

  700. 		'title2'              : '.SS \a' ,
    701. 

  701. 		'title3'              : '.SS \a' ,
    702. 

  702. 		'title4'              : '.SS \a' ,
    703. 

  703. 		'title5'              : '.SS \a' ,
    704. 

  704. 		'areaPreOpen'         : '.nf'    ,
    705. 

  705. 		'areaPreClose'        : '.fi\n'  ,
    706. 

  706. 		'areaQuoteOpen'       : '\n'     ,
    707. 

  707. 		'areaQuoteClose'      : '\n'     ,
    708. 

  708. 		'fontBoldOpen'        : '\\fB'   ,
    709. 

  709. 		'fontBoldClose'       : '\\fP'   ,
    710. 

  710. 		'fontItalicOpen'      : '\\fI'   ,
    711. 

  711. 		'fontItalicClose'     : '\\fP'   ,
    712. 

  712. 		'fontBolditalicOpen'  : '\n.BI ' ,
    713. 

  713. 		'fontBolditalicClose' : '\n\\&'  ,
    714. 

  714. 		'listOpen'            : '\n.nf'  ,  # pre
    715. 

  715. 		'listClose'           : '.fi\n'  ,
    716. 

  716. 		'listItem'            : '* '     ,
    717. 

  717. 		'numlistOpen'         : '\n.nf'  ,  # pre
    718. 

  718. 		'numlistClose'        : '.fi\n'  ,
    719. 

  719. 		'numlistItem'         : '\a. '   ,
    720. 

  720. 		'bar1'                : '\n\n'   ,
    721. 

  721. 		'bar2'                : '\n\n'   ,
    722. 

  722. 		'url'                 : '\a'     ,
    723. 

  723. 		'urlMark'             : '\a (\a)',
    724. 

  724. 		'email'               : '\a'     ,
    725. 

  725. 		'emailMark'           : '\a (\a)',
    726. 

  726. 		'img'                 : '\a'     ,
    727. 

  727. 		'comment'             : '.\\" \a'
    728. 

  728. 		}
    729. 

  729. 	
    730. 

  730. 	elif doctype == "pm6":
    731. 

  731. 		tags = {
    732. 

  732. 		'paragraph'           : '<@Normal:>'    ,
    733. 

  733. 		'title1'              : '\n<@Title1:>\a',
    734. 

  734. 		'title2'              : '\n<@Title2:>\a',
    735. 

  735. 		'title3'              : '\n<@Title3:>\a',
    736. 

  736. 		'title4'              : '\n<@Title4:>\a',
    737. 

  737. 		'title5'              : '\n<@Title5:>\a',
    738. 

  738. 		'areaPreOpen'         : '<@PreFormat:>' ,
    739. 

  739. 		'areaQuoteOpen'       : '<@Quote:>'     ,
    740. 

  740. 		'fontMonoOpen'        : '<FONT "Lucida Console"><SIZE 9>' ,
    741. 

  741. 		'fontMonoClose'       : '<SIZE$><FONT$>',
    742. 

  742. 		'fontBoldOpen'        : '<B>'           ,
    743. 

  743. 		'fontBoldClose'       : '<P>'           ,
    744. 

  744. 		'fontItalicOpen'      : '<I>'           ,
    745. 

  745. 		'fontItalicClose'     : '<P>'           ,
    746. 

  746. 		'fontBolditalicOpen'  : '<B><I>'        ,
    747. 

  747. 		'fontBolditalicClose' : '<P>'           ,
    748. 

  748. 		'fontUnderlineOpen'   : '<U>'           ,
    749. 

  749. 		'fontUnderlineClose'  : '<P>'           ,
    750. 

  750. 		'listOpen'            : '<@Bullet:>'    ,
    751. 

  751. 		'listItem'            : '\x95	'       ,  # \x95 == ~U
    752. 

  752. 		'numlistOpen'         : '<@Bullet:>'    ,
    753. 

  753. 		'numlistItem'         : '\x95    '      ,
    754. 

  754. 		'bar1'                : '\a'            ,
    755. 

  755. 		'bar2'                : '\a'            ,
    756. 

  756. 		'url'                 : '<U>\a<P>'      ,  # underline
    757. 

  757. 		'urlMark'             : '\a <U>\a<P>'   ,
    758. 

  758. 		'email'               : '\a'            ,
    759. 

  759. 		'emailMark'           : '\a \a'         ,
    760. 

  760. 		'img'                 : '\a'            ,
    761. 

  761. 		}
    762. 

  762. 	
    763. 

  763. 	# create empty tags keys
    764. 

  764. 	for key in keys:
    765. 

  765. 		if not tags.has_key(key):
    766. 

  766. 			tags[key] = ''
    767. 

  767. 		else:
    768. 

  768. 			tags[key] = escapePythonSpecials(tags[key])
    769. 

  769. 	
    770. 

  770. 	return tags
    771. 

  771. 

  772. 

  773. def getRules(doctype):
    774. 

  774. 	ret = {}
    775. 

  775. 	allrules = [
    776. 

  776. 	
    777. 

  777. 	 # target rules (ON/OFF)
    778. 

  778. 	  'linkable',           # target supports external links
    779. 

  779. 	  'tableable',          # target supports tables
    780. 

  780. 	  'imgalignable',       # target supports image alignment
    781. 

  781. 	  'tablealignable',     # target supports table alignment
    782. 

  782. 	  'listcountable',      # target supports numbered lists natively
    783. 

  783. 	  'tablecellsplit',     # place delimiters only *between* cells
    784. 

  784. 	  'listnotnested',      # lists cannot be nested
    785. 

  785. 	  'quotenotnested',     # quotes cannot be nested
    786. 

  786. 	  'preareanotescaped',  # don't escape specials in PRE area
    787. 

  787. 	  
    788. 

  788. 	# target code beautify (ON/OFF)
    789. 

  789. 	  'indentprearea',      # add leading spaces to PRE area lines
    790. 

  790. 	  'breaktablecell',     # break lines after any table cell
    791. 

  791. 	  'breaktablelineopen', # break line after opening table line
    792. 

  792. 	  'keepquoteindent',    # don't remove the leading TABs on quotes
    793. 

  793. 	
    794. 

  794. 	# value settings
    795. 

  795. 	  'listmaxdepth',       # maximum depth for lists
    796. 

  796. 	  'tablecellaligntype'  # type of table cell align: cell, column
    797. 

  797. 	]
    798. 

  798. 	
    799. 

  799. 	rules = {
    800. 

  800. 	  'txt' : {
    801. 

  801. 	    'indentprearea':1
    802. 

  802. 	    },
    803. 

  803. 	  'html': {
    804. 

  804. 	    'indentprearea':1,
    805. 

  805. 	    'linkable':1,
    806. 

  806. 	    'imgalignable':1,
    807. 

  807. 	    'listcountable':1,
    808. 

  808. 	    'tableable':1,
    809. 

  809. 	    'breaktablecell':1,
    810. 

  810. 	    'breaktablelineopen':1,
    811. 

  811. 	    'keepquoteindent':1,
    812. 

  812. 	    'tablealignable':1,
    813. 

  813. 	    'tablecellaligntype':'cell'
    814. 

  814. 	    },
    815. 

  815. 	  'sgml': {
    816. 

  816. 	    'linkable':1,
    817. 

  817. 	    'listcountable':1,
    818. 

  818. 	    'tableable':1,
    819. 

  819. 	    'tablecellsplit':1,
    820. 

  820. 	    'quotenotnested':1,
    821. 

  821. 	    'keepquoteindent':1,
    822. 

  822. 	    'tablecellaligntype':'column'
    823. 

  823. 	    },
    824. 

  824. 	  'mgp' : {
    825. 

  825. 	    },
    826. 

  826. 	  'tex' : {
    827. 

  827. 	    'listcountable':1,
    828. 

  828. 	    'tableable':1,
    829. 

  829. 	    'tablecellsplit':1,
    830. 

  830. 	    'preareanotescaped':1,
    831. 

  831. 	    'listmaxdepth':4,
    832. 

  832. 	    'tablecellaligntype':'column'
    833. 

  833. 	    },
    834. 

  834. 	  'moin': {
    835. 

  835. 	    'linkable':1,
    836. 

  836. 	    'tableable':1
    837. 

  837. 	    },
    838. 

  838. 	  'man' : {
    839. 

  839. 	    'indentprearea':1,
    840. 

  840. 	    'listnotnested':1
    841. 

  841. 	    },
    842. 

  842. 	  'pm6' : {
    843. 

  843. 	    }
    844. 

  844. 	}
    845. 

  845. 	
    846. 

  846. 	
    847. 

  847. 	# populate return dictionary
    848. 

  848. 	myrules = rules[doctype]
    849. 

  849. 	for key in allrules      : ret[key] = 0            # reset all
    850. 

  850. 	for key in myrules.keys(): ret[key] = myrules[key] # turn ON
    851. 

  851. 	return ret
    852. 

  852. 

  853. 

  854. def getRegexes():
    855. 

  855. 	regex = {
    856. 

  856. 	# extra at end: (\[(?P<label>\w+)\])?
    857. 

  857. 	'title':
    858. 

  858. 		re.compile(r'^\s*(?P<tag>={1,5})(?P<txt>[^=].*[^=])\1\s*$'),
    859. 

  859. 	'areaPreOpen':
    860. 

  860. 		re.compile(r'^---$'),
    861. 

  861. 	'areaPreClose':
    862. 

  862. 		re.compile(r'^---$'),
    863. 

  863. 	'quote':
    864. 

  864. 		re.compile(r'^\t+'),
    865. 

  865. 	'1linePreOld':
    866. 

  866. 		re.compile(r'^ {4}([^\s-])'),
    867. 

  867. 	'1linePre':
    868. 

  868. 		re.compile(r'^--- '),
    869. 

  869. 	'fontMono':
    870. 

  870. 		re.compile(r'`([^`]+)`'),
    871. 

  871. 	'fontBold':
    872. 

  872. 		re.compile(r'\*\*([^\s*].*?)\*\*'),
    873. 

  873. 	'fontItalic':
    874. 

  874. 		re.compile(r'(^|[^:])//([^ /].*?)//'),
    875. 

  875. 	'fontUnderline':
    876. 

  876. 		re.compile(r'__([^_].*?)__'), # underline lead/trailing blank
    877. 

  877. 	'fontBolditalic':
    878. 

  878. 		re.compile(r'\*/([^/].*?)/\*'),
    879. 

  879. 	'list':
    880. 

  880. 		re.compile(r'^( *)([+-]) ([^ ])'),
    881. 

  881. 	'deflist':
    882. 

  882. 		re.compile(r'^( *)(=) ([^:]+):'),
    883. 

  883. 	'bar':
    884. 

  884. 		re.compile(r'^\s*([_=-]{20,})\s*$'),
    885. 

  885. 	'table':
    886. 

  886. 		re.compile(r'^ *\|\|? '),
    887. 

  887. 	'blankline':
    888. 

  888. 		re.compile(r'^\s*$'),
    889. 

  889. 	'comment':
    890. 

  890. 		re.compile(r'^%'),
    891. 

  891. 	'raw':
    892. 

  892. 		re.compile(r'``(.+?)``')
    893. 

  893. 	}
    894. 

  894. 	
    895. 

  895. 	# special char to place data on TAGs contents  (\a == bell)
    896. 

  896. 	regex['x'] = re.compile('\a')
    897. 

  897. 	
    898. 

  898. 	# %%date [ (formatting) ]
    899. 

  899. 	regex['date'] = re.compile(r'%%date\b(\((?P<fmt>.*?)\))?', re.I)
    900. 

  900. 	
    901. 

  901. 	
    902. 

  902. 	### complicated regexes begin here ;)
    903. 

  903. 	#
    904. 

  904. 	# textual descriptions on --help's style: [...] is optional, | is OR
    905. 

  905. 	
    906. 

  906. 	
    907. 

  907. 	### first, some auxiliar variables
    908. 

  908. 	#
    909. 

  909. 	
    910. 

  910. 	# [image.EXT]
    911. 

  911. 	patt_img = r'\[([\w_,.+%$#@!?+~/-]+\.(png|jpe?g|gif|eps|bmp))\]'
    912. 

  912. 	
    913. 

  913. 	# link things
    914. 

  914. 	urlskel = {
    915. 

  915. 	  'proto' : r'(https?|ftp|news|telnet|gopher|wais)://',
    916. 

  916. 	  'guess' : r'(www[23]?|ftp)\.',    # w/out proto, try to guess
    917. 

  917. 	  'login' : r'A-Za-z0-9_.-',        # for ftp://login@domain.com
    918. 

  918. 	  'pass'  : r'[^ @]*',              # for ftp://login:password@domain.com
    919. 

  919. 	  'chars' : r'A-Za-z0-9%._/~:,=$@-',# %20(space), :80(port)
    920. 

  920. 	  'anchor': r'A-Za-z0-9%._-',       # %nn(encoded)
    921. 

  921. 	  'form'  : r'A-Za-z0-9/%&=+.@*_-', # .@*_-(as is)
    922. 

  922. 	  'punct' : r'.,;:!?'
    923. 

  923. 	}
    924. 

  924. 	
    925. 

  925. 	# username [ :password ] @
    926. 

  926. 	patt_url_login = r'([%s]+(:%s)?@)?'%(urlskel['login'],urlskel['pass'])
    927. 

  927. 	
    928. 

  928. 	# [ http:// ] [ username:password@ ] domain.com [ / ] [ #anchor | ?form=data ]
    929. 

  929. 	retxt_url = r'\b(%s%s|%s)[%s]+\b/*(\?[%s]+)?(#[%s]+)?'%(
    930. 

  930. 	             urlskel['proto'],patt_url_login, urlskel['guess'],
    931. 

  931. 	             urlskel['chars'],urlskel['form'],urlskel['anchor'])
    932. 

  932. 	
    933. 

  933. 	# filename | [ filename ] #anchor
    934. 

  934. 	retxt_url_local = r'[%s]+|[%s]*(#[%s]+)'%(
    935. 

  935. 	             urlskel['chars'],urlskel['chars'],urlskel['anchor'])
    936. 

  936. 	
    937. 

  937. 	# user@domain [ ?form=data ]
    938. 

  938. 	patt_email = r'\b[%s]+@([A-Za-z0-9_-]+\.)+[A-Za-z]{2,4}\b(\?[%s]+)?'%(
    939. 

  939. 	             urlskel['login'],urlskel['form'])
    940. 

  940. 	
    941. 

  941. 	
    942. 

  942. 	# saving for future use
    943. 

  943. 	regex['_urlskel'] = urlskel
    944. 

  944. 	
    945. 

  945. 	### and now the real regexes
    946. 

  946. 	#
    947. 

  947. 	
    948. 

  948. 	regex['email'] = re.compile(patt_email,re.I)
    949. 

  949. 	
    950. 

  950. 	# email | url
    951. 

  951. 	regex['link'] = \
    952. 

  952. 		re.compile(r'%s|%s'%(retxt_url,patt_email), re.I)
    953. 

  953. 	
    954. 

  954. 	# \[ label | imagetag    url | email | filename \]
    955. 

  955. 	regex['linkmark'] = \
    956. 

  956. 		re.compile(r'\[(?P<label>%s|[^]]+) (?P<link>%s|%s|%s)\]'%(
    957. 

  957. 		   patt_img, retxt_url, patt_email, retxt_url_local),
    958. 

  958. 		   re.L+re.I)
    959. 

  959. 	
    960. 

  960. 	# image
    961. 

  961. 	regex['img'] = re.compile(patt_img, re.L+re.I)
    962. 

  962. 	
    963. 

  963. 	# all macros
    964. 

  964. 	regex['macro'] = regex['date']
    965. 

  965. 	
    966. 

  966. 	# special things
    967. 

  967. 	regex['special'] = re.compile(r'^%!\s*')
    968. 

  968. 	regex['setting'] = re.compile(r'(Encoding|Style)\s*:\s*(.+)\s*$',re.I)
    969. 

  969. 	
    970. 

  970. 	return regex
    971. 

  971. ### END OF regex nightmares
    972. 

  972. 

  973. 

  974. class SubareaMaster:
    975. 

  975. 	def __init__(self) : self.x = []
    976. 

  976. 	def __call__(self) :
    977. 

  977. 		if not self.x: return ''
    978. 

  978. 		return self.x[-1]
    979. 

  979. 	def add(self, area):
    980. 

  980. 		if not self.x or (self.x and self.x[-1] != area):
    981. 

  981. 			self.x.append(area)
    982. 

  982. 		Debug('subarea ++ (%s): %s' % (area,self.x), 1)
    983. 

  983. 	def pop(self, area=None):
    984. 

  984. 		if area and self.x[-1] == area: self.x.pop()
    985. 

  985. 		Debug('subarea -- (%s): %s' % (area,self.x), 1)
    986. 

  986. 

  987. def doHeader(doctype, headdic):
    988. 

  988. 	if not HEADER_TEMPLATE.has_key(doctype):
    989. 

  989. 		Error("doheader: Unknow doctype '%s'"%doctype)
    990. 

  990. 	
    991. 

  991. 	# cmdline options takes precedence on settings
    992. 

  992. 	if OPTIONS['style']: headdic['STYLE'] = OPTIONS['style']
    993. 

  993. 	
    994. 

  994. 	Debug('HEADER data: %s'%headdic, 1)
    995. 

  995. 	template = string.split(HEADER_TEMPLATE[doctype], '\n')
    996. 

  996. 	
    997. 

  997. 	# scan for empty dictionary keys
    998. 

  998. 	# if found, scan template lines for that key reference
    999. 

  999. 	# if found, remove the reference
    1000. 

  1000. 	# if there aren't any other key reference on the same line, remove it
    1001. 

  1001. 	for key in headdic.keys():
    1002. 

  1002. 		if not headdic[key]:
    1003. 

  1003. 			for line in template:
    1004. 

  1004. 				if string.count(line, '%%(%s)s'%key):
    1005. 

  1005. 					sline = string.replace(line, '%%(%s)s'%key, '')
    1006. 

  1006. 					if not re.search(r'%([A-Z0-9]+)s', sline):
    1007. 

  1007. 						template.remove(line)
    1008. 

  1008. 	
    1009. 

  1009. 	# populate template with data
    1010. 

  1010. 	template = string.join(template, '\n') % headdic
    1011. 

  1011. 	
    1012. 

  1012. 	### post processing
    1013. 

  1013. 	#
    1014. 

  1014. 	# TOC is a header tag
    1015. 

  1015. 	if FLAGS['toc'] and TAGS['TOC']:
    1016. 

  1016. 		toctag = re.sub('.*', TAGS['TOC'], '') #force_re
    1017. 

  1017. 		template = template + toctag
    1018. 

  1018. 	#
    1019. 

  1019. 	# let tex format today
    1020. 

  1020. 	if doctype == 'tex' and headdic['HEADER3'] == currdate:
    1021. 

  1021. 		template = re.sub(r'\\date\{.*?}', r'\date', template)
    1022. 

  1022. 	
    1023. 

  1023. 	return string.split(template, '\n')
    1024. 

  1024. 

  1025. def doCommentLine(doctype,txt):
    1026. 

  1026. 	# the -- string ends a sgml comment :(
    1027. 

  1027. 	if doctype == 'sgml':
    1028. 

  1028. 		txt = string.replace(txt, '--', '\\-\\-')
    1029. 

  1029. 	
    1030. 

  1030. 	if TAGS['comment']:
    1031. 

  1031. 		return regex['x'].sub(txt, TAGS['comment'])
    1032. 

  1032. 	return ''
    1033. 

  1033. 

  1034. def doFooter(doctype):
    1035. 

  1035. 	ret = []
    1036. 

  1036. 	typename = doctype
    1037. 

  1037. 	if doctype == 'tex': typename = 'LaTeX2e'
    1038. 

  1038. 	ppgd = '%s code generated by txt2tags %s (%s)'%(
    1039. 

  1039. 	        typename,my_version,my_url)
    1040. 

  1040. 	cmdline = 'cmdline: txt2tags %s'%string.join(CMDLINE[1:], ' ')
    1041. 

  1041. 	ret.append('\n'+doCommentLine(doctype,ppgd))
    1042. 

  1042. 	ret.append(doCommentLine(doctype,cmdline))
    1043. 

  1043. 	ret.append(TAGS['EOD'])
    1044. 

  1044. 	return ret
    1045. 

  1045. 

  1046. def doEscape(doctype,txt):
    1047. 

  1047. 	if doctype == 'html' or doctype == 'sgml':
    1048. 

  1048. 		txt = re.sub('&','&amp;',txt)
    1049. 

  1049. 		txt = re.sub('<','&lt;',txt)
    1050. 

  1050. 		txt = re.sub('>','&gt;',txt)
    1051. 

  1051. 		if doctype == 'sgml':
    1052. 

  1052. 			txt = re.sub('\xff','&yuml;',txt)  # "+y
    1053. 

  1053. 	elif doctype == 'pm6':
    1054. 

  1054. 		txt = re.sub('<','<\#60>',txt)
    1055. 

  1055. 	elif doctype == 'mgp':
    1056. 

  1056. 		txt = re.sub('^%',' %',txt)  # add leading blank to avoid parse
    1057. 

  1057. 		#txt = re.sub('^%([^%])','%prefix ""\n  %\n%cont, prefix "  "\n\\1',txt)
    1058. 

  1058. 	elif doctype == 'man':
    1059. 

  1059. 		txt = re.sub('^\.', ' .',txt) # command ID
    1060. 

  1060. 		txt = doEscapeEscapechar(txt)
    1061. 

  1061. 	elif doctype == 'tex':
    1062. 

  1062. 		txt = string.replace(txt, '\\', r'\verb!\!')
    1063. 

  1063. 		txt = string.replace(txt, '~', r'\verb!~!')
    1064. 

  1064. 		txt = string.replace(txt, '^', r'\verb!^!')
    1065. 

  1065. 		txt = re.sub('([#$&%{}])', r'\\\1', txt)
    1066. 

  1066. 		# TIP the _ is escaped at end
    1067. 

  1067. 	return txt
    1068. 

  1068. 

  1069. def doFinalEscape(doctype, txt):
    1070. 

  1070. 	if   doctype == 'pm6' : txt = string.replace(txt, r'\<',r'<\#92><')
    1071. 

  1071. 	elif doctype == 'man' : txt = string.replace(txt, '-', r'\-')
    1072. 

  1072. 	elif doctype == 'tex' : txt = string.replace(txt, '_', r'\_')
    1073. 

  1073. 	elif doctype == 'sgml': txt = string.replace(txt, '[', '&lsqb;')
    1074. 

  1074. 	return txt
    1075. 

  1075. 

  1076. def doEscapeEscapechar(txt):
    1077. 

  1077. 	return string.replace(txt, '\\', '\\\\')
    1078. 

  1078. 

  1079. def addLineBreaks(list):
    1080. 

  1080. 	"use LB to respect sys.platform"
    1081. 

  1081. 	ret = []
    1082. 

  1082. 	for line in list:
    1083. 

  1083. 		line = string.replace(line,'\n',LB)  # embedded \n's
    1084. 

  1084. 		ret.append(line+LB)                  # add final line break
    1085. 

  1085. 	return ret
    1086. 

  1086. 

  1087. def doPreLine(doctype,line):
    1088. 

  1088. 	"Parsing procedures for preformatted (verbatim) lines"
    1089. 

  1089. 	if not rules['preareanotescaped']: line = doEscape(doctype,line)
    1090. 

  1090. 	if rules['indentprearea']: line = '  '+line
    1091. 

  1091. 	if doctype == 'pm6': line = doFinalEscape(doctype, line)
    1092. 

  1092. 	return line
    1093. 

  1093. 

  1094. def doCloseTable(doctype):
    1095. 

  1095. 	global subarea, tableborder
    1096. 

  1096. 	ret = ''
    1097. 

  1097. 	if rules['tableable']:
    1098. 

  1098. 		if doctype == 'tex' and tableborder:
    1099. 

  1099. 			ret = TAGS['tableLineOpen']+TAGS['tableClose']+'\n'
    1100. 

  1100. 		else:
    1101. 

  1101. 			ret = TAGS['tableClose']+'\n'
    1102. 

  1102. 	else:
    1103. 

  1103. 		ret = TAGS['areaPreClose']
    1104. 

  1104. 	tableborder = 0
    1105. 

  1105. 	subarea.pop('table')
    1106. 

  1106. 	return ret
    1107. 

  1107. 

  1108. def doCloseQuote(howmany=None):
    1109. 

  1109. 	global quotedepth
    1110. 

  1110. 	ret = []
    1111. 

  1111. 	if not howmany: howmany = len(quotedepth)
    1112. 

  1112. 	for i in range(howmany):
    1113. 

  1113. 		quotedepth.pop()
    1114. 

  1114. 		#TODO align open/close tag -> FREE_ALING_TAG = 1 (man not)
    1115. 

  1115. 		ret.append(TAGS['areaQuoteClose'])
    1116. 

  1116. 	
    1117. 

  1117. 	if not quotedepth: subarea.pop('quote')
    1118. 

  1118. 	return string.join(ret,'\n')
    1119. 

  1119. 

  1120. def doCloseList(howmany=None):
    1121. 

  1121. 	global listindent, listids
    1122. 

  1122. 	ret = []
    1123. 

  1123. 	if not howmany: howmany = len(listindent)
    1124. 

  1124. 	for i in range(howmany):
    1125. 

  1125. 		if   listids[-1] == '-': tag = TAGS['listClose']
    1126. 

  1126. 		elif listids[-1] == '+': tag = TAGS['numlistClose']
    1127. 

  1127. 		elif listids[-1] == '=': tag = TAGS['deflistClose']
    1128. 

  1128. 		if not tag: tag = TAGS['listClose'] # default
    1129. 

  1129. 		if tag:
    1130. 

  1130. 			# unnested lists are only closed at mother-list
    1131. 

  1131. 			if rules['listnotnested']:
    1132. 

  1132. 				if len(listindent) == 1:
    1133. 

  1133. 					ret.append(tag)
    1134. 

  1134. 			else:
    1135. 

  1135. 				ret.append(listindent[-1]+tag)
    1136. 

  1136. 		del listindent[-1]
    1137. 

  1137. 		del listids[-1]
    1138. 

  1138. 	
    1139. 

  1139. 	if not listindent: subarea.pop('list')
    1140. 

  1140. 	return string.join(ret,'\n')
    1141. 

  1141. 

  1142. 

  1143. def beautify_me(name, doctype, line):
    1144. 

  1144. 	"where name is: bold, italic, underline or bolditalic"
    1145. 

  1145. 	name  = 'font%s' % string.capitalize(name)
    1146. 

  1146. 	open  = TAGS['%sOpen'%name]
    1147. 

  1147. 	close = TAGS['%sClose'%name]
    1148. 

  1148. 	txt = r'%s\1%s'%(open, close)
    1149. 

  1149. 	if name == 'fontItalic':
    1150. 

  1150. 		txt = r'\1%s\2%s'%(open, close)
    1151. 

  1151. 	line = regex[name].sub(txt,line)
    1152. 

  1152. 	return line
    1153. 

  1153. 

  1154. 

  1155. def get_tagged_link(doctype, label, url):
    1156. 

  1156. 	ret = ''
    1157. 

  1157. 	
    1158. 

  1158. 	# set link type
    1159. 

  1159. 	if regex['email'].match(url):
    1160. 

  1160. 		linktype = 'email'
    1161. 

  1161. 	else:
    1162. 

  1162. 		linktype = 'url';
    1163. 

  1163. 	
    1164. 

  1164. 	# adding protocol to guessed link
    1165. 

  1165. 	guessurl = ''
    1166. 

  1166. 	if linktype == 'url' and \
    1167. 

  1167. 	   re.match(regex['_urlskel']['guess'], url):
    1168. 

  1168. 		if url[0] == 'w': guessurl = 'http://' +url
    1169. 

  1169. 		else            : guessurl =  'ftp://' +url
    1170. 

  1170. 		
    1171. 

  1171. 		# not link aware targets -> protocol is useless
    1172. 

  1172. 		if not rules['linkable']: guessurl = ''
    1173. 

  1173. 	
    1174. 

  1174. 	# escape specials from TEXT parts
    1175. 

  1175. 	label = doEscape(doctype,label)
    1176. 

  1176. 	if not rules['linkable']:
    1177. 

  1177. 		if doctype == 'tex':
    1178. 

  1178. 			url = re.sub('^#', '\#', url) # ugly, but compile
    1179. 

  1179. 		else:
    1180. 

  1180. 			url = doEscape(doctype,url)
    1181. 

  1181. 	
    1182. 

  1182. 	# simple link (not guessed)
    1183. 

  1183. 	if not label and not guessurl:
    1184. 

  1184. 		if FLAGS['maskemail'] and linktype == 'email':
    1185. 

  1185. 			# do the email mask feature (no TAGs, just text)
    1186. 

  1186. 			url = string.replace(url,'@',' (a) ')
    1187. 

  1187. 			url = string.replace(url,'.',' ')
    1188. 

  1188. 			url = "<%s>" % url
    1189. 

  1189. 			if rules['linkable']: url = doEscape(doctype, url)
    1190. 

  1190. 			ret = url
    1191. 

  1191. 		else:
    1192. 

  1192. 			# just add link data to tag
    1193. 

  1193. 			tag = re.sub('.*', TAGS[linktype], '')  #force_re
    1194. 

  1194. 			ret = regex['x'].sub(url,tag)
    1195. 

  1195. 	
    1196. 

  1196. 	# named link or guessed simple link
    1197. 

  1197. 	else:
    1198. 

  1198. 		# adjusts for guessed link
    1199. 

  1199. 		if not label: label = url       # no   protocol
    1200. 

  1200. 		if guessurl : url   = guessurl  # with protocol
    1201. 

  1201. 		
    1202. 

  1202. 		# handle \ on link label
    1203. 

  1203. 		label = doEscapeEscapechar(label)
    1204. 

  1204. 		
    1205. 

  1205. 		# putting data on the right appearance order
    1206. 

  1206. 		if rules['linkable']:
    1207. 

  1207. 			urlorder = [url, label]   # link before label
    1208. 

  1208. 		else:
    1209. 

  1209. 			urlorder = [label, url]   # label before link
    1210. 

  1210. 		
    1211. 

  1211. 		# get tag
    1212. 

  1212. 		ret = re.sub('.*', TAGS["%sMark"%linktype], '')  #force_re
    1213. 

  1213. 		
    1214. 

  1214. 		# add link data to tag (replace \a's)
    1215. 

  1215. 		for data in urlorder:
    1216. 

  1216. 			ret = regex['x'].sub(data,ret,1)
    1217. 

  1217. 	return ret
    1218. 

  1218. 

  1219. 

  1220. def get_image_align(line):
    1221. 

  1221. 	align = ''
    1222. 

  1222. 	line = string.strip(line)
    1223. 

  1223. 	m = regex['img'].search(line)
    1224. 

  1224. 	ini = m.start() ; head = 0
    1225. 

  1225. 	end = m.end()   ; tail = len(line)
    1226. 

  1226. 	
    1227. 

  1227. 	align = 'center'  # default align              # ^text +img +text$
    1228. 

  1228. 	if ini == head and end == tail: align = 'para' # ^img$
    1229. 

  1229. 	elif ini == head: align = 'left'               # ^img + text$
    1230. 

  1230. 	elif end == tail: align = 'right'              # ^text + img$
    1231. 

  1231. 	
    1232. 

  1232. 	return align
    1233. 

  1233. 

  1234. 

  1235. def get_tablecell_align(cells):
    1236. 

  1236. 	ret = []
    1237. 

  1237. 	for cell in cells:
    1238. 

  1238. 		align = 'Left'
    1239. 

  1239. 		if string.strip(cell): 
    1240. 

  1240. 			if   cell[0] == ' ' and cell[-1] == ' ': align = 'Center'
    1241. 

  1241. 			elif cell[0] == ' ': align = 'Right'
    1242. 

  1242. 		ret.append(align)
    1243. 

  1243. 	return ret
    1244. 

  1244. 

  1245. 

  1246. def get_table_prop(line):
    1247. 

  1247. 	# default table proprierties
    1248. 

  1248. 	ret = {'border': 0, 'header':0, 'align':'Left', 'cells':[], 'cellalign':[]}
    1249. 

  1249. 	# detect table align (and remove spaces mark)
    1250. 

  1250. 	if line[0] == ' ': ret['align'] = 'Center'
    1251. 

  1251. 	line = string.lstrip(line)
    1252. 

  1252. 	# detect header (title) mark
    1253. 

  1253. 	if line[1] == '|':
    1254. 

  1254. 		ret['header'] = 1
    1255. 

  1255. 	# delete trailing spaces after last cell border
    1256. 

  1256. 	line = re.sub('\|\s*$','|', line)
    1257. 

  1257. 	# detect (and delete) border mark (and leading space)
    1258. 

  1258. 	if line[-1] == '|':
    1259. 

  1259. 		ret['border'] = 1 ; line = line[:-2]
    1260. 

  1260. 	# delete table mark
    1261. 

  1261. 	line = regex['table'].sub('', line)
    1262. 

  1262. 	# split cells
    1263. 

  1263. 	ret['cells'] = string.split(line, ' | ')
    1264. 

  1264. 	# find cells align
    1265. 

  1265. 	ret['cellalign'] = get_tablecell_align(ret['cells'])
    1266. 

  1266. 	
    1267. 

  1267. 	Debug('Table Prop: %s' % ret, 1)
    1268. 

  1268. 	return ret
    1269. 

  1269. 

  1270. 

  1271. def tag_table_cells(table, doctype):
    1272. 

  1272. 	ret = ''
    1273. 

  1273. 	open, close = TAGS['tableCellOpen'], TAGS['tableCellClose']
    1274. 

  1274. 	# title cell
    1275. 

  1275. 	if table['header']:
    1276. 

  1276. 		open = TAGS['tableTitleCellOpen']
    1277. 

  1277. 		close = TAGS['tableTitleCellClose']
    1278. 

  1278. 		if doctype == 'tex': open = re.sub('.*',open,'')  # force_re
    1279. 

  1279. 	# should we break the line?
    1280. 

  1280. 	if rules['breaktablecell']: close = close+'\n'
    1281. 

  1281. 	# here we go
    1282. 

  1282. 	while table['cells']:
    1283. 

  1283. 		openalign = open
    1284. 

  1284. 		cel = table['cells'].pop(0)
    1285. 

  1285. 		# set each cell align
    1286. 

  1286. 		if rules['tablecellaligntype'] == 'cell':
    1287. 

  1287. 			align = table['cellalign'].pop(0)
    1288. 

  1288. 			align = TAGS['tableCellAlign%s'%align]
    1289. 

  1289. 			openalign = string.replace(open,'\a',align)
    1290. 

  1290. 		# show empty cell on HTML
    1291. 

  1291. 		if not cel and doctype == 'html': cel = '&nbsp;'
    1292. 

  1292. 		# last cell gotchas
    1293. 

  1293. 		if not table['cells']:
    1294. 

  1294. 			# don't need cell separator
    1295. 

  1295. 			if rules['tablecellsplit']: close = ''
    1296. 

  1296. 			# close beautifier for last title cell
    1297. 

  1297. 			if doctype == 'tex' and table['header']: close = '}'
    1298. 

  1298. 		# join it all
    1299. 

  1299. 		newcell = openalign + string.strip(cel) + close
    1300. 

  1300. 		ret = ret + newcell
    1301. 

  1301. 	return ret
    1302. 

  1302. 

  1303. 

  1304. def get_tableopen_tag(table_prop, doctype):
    1305. 

  1305. 	global tableborder
    1306. 

  1306. 	open = TAGS['tableOpen'] # the default one
    1307. 

  1307. 	# the first line defines if table has border or not
    1308. 

  1308. 	tableborder = table_prop['border']
    1309. 

  1309. 	# align full table
    1310. 

  1310. 	if rules['tablealignable']:
    1311. 

  1311. 		talign = TAGS['tableAlign'+table_prop['align']]
    1312. 

  1312. 		open = regex['x'].sub(talign, open, 1)
    1313. 

  1313. 	# set the columns alignment
    1314. 

  1314. 	if rules['tablecellaligntype'] == 'column':
    1315. 

  1315. 		calign = map(lambda x: TAGS['tableColAlign%s'%x],
    1316. 

  1316. 		             table_prop['cellalign'])
    1317. 

  1317. 		calign = string.join(calign,'')
    1318. 

  1318. 		open = regex['x'].sub(calign, open, 1)
    1319. 

  1319. 	# tex table spec, border or not: {|l|c|r|} , {lcr}
    1320. 

  1320. 	if doctype == 'tex' and not tableborder:
    1321. 

  1321. 		open = string.replace(open,'|','')
    1322. 

  1322. 	# we're almost done, just border left
    1323. 

  1323. 	tag = regex['x'].sub(`tableborder`, open)
    1324. 

  1324. 	return tag
    1325. 

  1325. 

  1326. 

  1327. # reference: http://www.iana.org/assignments/character-sets
    1328. 

  1328. # http://www.drclue.net/F1.cgi/HTML/META/META.html
    1329. 

  1329. def get_encoding_string(enc, doctype):
    1330. 

  1330. 	if not enc: return ''
    1331. 

  1331. 	# target specific translation table
    1332. 

  1332. 	translate = {
    1333. 

  1333. 	'tex': {
    1334. 

  1334. 	  # missing: ansinew , applemac , cp437 , cp437de , cp865
    1335. 

  1335. 	  'us-ascii'    : 'ascii',
    1336. 

  1336. 	  'windows-1250': 'cp1250',
    1337. 

  1337. 	  'windows-1252': 'cp1252',
    1338. 

  1338. 	  'ibm850'      : 'cp850',
    1339. 

  1339. 	  'ibm852'      : 'cp852',
    1340. 

  1340. 	  'iso-8859-1'  : 'latin1',
    1341. 

  1341. 	  'iso-8859-2'  : 'latin2',
    1342. 

  1342. 	  'iso-8859-3'  : 'latin3',
    1343. 

  1343. 	  'iso-8859-4'  : 'latin4',
    1344. 

  1344. 	  'iso-8859-5'  : 'latin5',
    1345. 

  1345. 	  'iso-8859-9'  : 'latin9',
    1346. 

  1346. 	  'koi8-r'      : 'koi8-r'
    1347. 

  1347. 	  }
    1348. 

  1348. 	}
    1349. 

  1349. 	# normalization
    1350. 

  1350. 	enc = re.sub('(?i)(us[-_]?)?ascii|us|ibm367','us-ascii'  , enc)
    1351. 

  1351. 	enc = re.sub('(?i)(ibm|cp)?85([02])'        ,'ibm85\\2'  , enc)
    1352. 

  1352. 	enc = re.sub('(?i)(iso[_-]?)?8859[_-]?'     ,'iso-8859-' , enc)
    1353. 

  1353. 	enc = re.sub('iso-8859-($|[^1-9]).*'        ,'iso-8859-1', enc)
    1354. 

  1354. 	# apply translation table
    1355. 

  1355. 	try: enc = translate[doctype][string.upper(enc)]
    1356. 

  1356. 	except: pass
    1357. 

  1357. 	return enc
    1358. 

  1358. 

  1359. 

  1360. ################################################################################
    1361. 

  1361. ###MerryChristmas,IdontwanttofighttonightwithyouImissyourbodyandIneedyourlove###
    1362. 

  1362. ################################################################################
    1363. 

  1363. 

  1364. 

  1365. def convert(inlines, doctype):
    1366. 

  1366. 	# global vars for doClose*()
    1367. 

  1367. 	global TAGS, regex, rules, quotedepth, listindent, listids
    1368. 

  1368. 	global subarea, tableborder
    1369. 

  1369. 	
    1370. 

  1370. 	TAGS = getTags(doctype)
    1371. 

  1371. 	rules = getRules(doctype)
    1372. 

  1372. 	regex = getRegexes()
    1373. 

  1373. 	
    1374. 

  1374. 	# the defaults
    1375. 

  1375. 	linkmask  = '@@_link_@@'
    1376. 

  1376. 	monomask  = '@@_mono_@@'
    1377. 

  1377. 	macromask = '@@_macro_@@'
    1378. 

  1378. 	rawmask   = '@@_raw_@@'
    1379. 

  1379. 	
    1380. 

  1380. 	AREA = NewArea('head',0)   # then conf, then body
    1381. 

  1381. 	subarea = SubareaMaster()
    1382. 

  1382. 	HEADERS = { 'HEADER1': '', 'HEADER2':'', 'HEADER3':'',
    1383. 

  1383. 	            'ENCODING': '', 'STYLE': '' }
    1384. 

  1384. 	ret = []
    1385. 

  1385. 	toclist = []
    1386. 

  1386. 	header = []
    1387. 

  1387. 	f_tt = 0
    1388. 

  1388. 	listindent = []
    1389. 

  1389. 	listids = []
    1390. 

  1390. 	listcount = []
    1391. 

  1391. 	titlecount = ['',0,0,0,0,0]
    1392. 

  1392. 	f_lastwasblank = 0
    1393. 

  1393. 	holdspace = ''
    1394. 

  1394. 	listholdspace = ''
    1395. 

  1395. 	quotedepth = []
    1396. 

  1396. 	tableborder = 0
    1397. 

  1397. 	
    1398. 

  1398. 	if outfile != pipefileid:
    1399. 

  1399. 		if not FLAGS['gui']:
    1400. 

  1400. 			print "--- %s..."%doctype
    1401. 

  1401. 	
    1402. 

  1402. 	# let's mark it up!
    1403. 

  1403. 	linenr = 0
    1404. 

  1404. 	for lineref in range(len(inlines)):
    1405. 

  1405. 		skip_continue = 0
    1406. 

  1406. 		linkbank = []
    1407. 

  1407. 		monobank = []
    1408. 

  1408. 		macrobank = []
    1409. 

  1409. 		rawbank = []
    1410. 

  1410. 		linenr = lineref +1
    1411. 

  1411. 		untouchedline = inlines[lineref]
    1412. 

  1412. 		# TODO take this rstrip() out - think about consequences
    1413. 

  1413. 		#line = string.rstrip(untouchedline)
    1414. 

  1414. 		line = re.sub('[\n\r]+$','',untouchedline)       # del line break
    1415. 

  1415. 		
    1416. 

  1416. 		Debug('LINE %04d: %s' % (linenr,repr(line)), 1)  # for heavy debug
    1417. 

  1417. 		
    1418. 

  1418. 		# detect if head section is over
    1419. 

  1419. 		if (linenr == 4 and AREA == 'head') or \
    1420. 

  1420. 		   (linenr == 1 and not string.rstrip(line)):
    1421. 

  1421. 			AREA = NewArea('conf',linenr)
    1422. 

  1422. 		
    1423. 

  1423. 		# we need (not really) to mark each paragraph
    1424. 

  1424. 		#TODO check if this is really needed
    1425. 

  1425. 		if doctype == 'pm6' and f_lastwasblank:
    1426. 

  1426. 			if f_tt or AREA == 'head' or listindent:
    1427. 

  1427. 				holdspace = ''
    1428. 

  1428. 			else:
    1429. 

  1429. 				holdspace = TAGS['paragraph']+'\n'
    1430. 

  1430. 		
    1431. 

  1431. 		# any NOT table line (or comment), closes an open table
    1432. 

  1432. 		#if subarea() == 'table' and not regex['table'].search(line):
    1433. 

  1433. 		if subarea() == 'table' \
    1434. 

  1434. 		  and not regex['table'].search(line) \
    1435. 

  1435. 		  and not regex['comment'].search(line):
    1436. 

  1436. 			ret.append(doCloseTable(doctype))
    1437. 

  1437. 		
    1438. 

  1438. 		
    1439. 

  1439. 		#---------------------[ PRE formatted ]----------------------
    1440. 

  1440. 		
    1441. 

  1441. 		#TIP we'll never support beautifiers inside pre-formatted
    1442. 

  1442. 		
    1443. 

  1443. 		# we're already on a PRE area
    1444. 

  1444. 		if f_tt:
    1445. 

  1445. 			# closing PRE
    1446. 

  1446. 			if regex['areaPreClose'].search(line):
    1447. 

  1447. 				if doctype != 'pm6':
    1448. 

  1448. 					ret.append(TAGS['areaPreClose'])
    1449. 

  1449. 				f_tt = 0
    1450. 

  1450. 				continue
    1451. 

  1451. 			
    1452. 

  1452. 			# normal PRE-inside line
    1453. 

  1453. 			line = doPreLine(doctype, line)
    1454. 

  1454. 			ret.append(line)
    1455. 

  1455. 			continue
    1456. 

  1456. 		
    1457. 

  1457. 		# detecting PRE area init
    1458. 

  1458. 		if regex['areaPreOpen'].search(line):
    1459. 

  1459. 			ret.append(TAGS['areaPreOpen'])
    1460. 

  1460. 			f_lastwasblank = 0
    1461. 

  1461. 			f_tt = 1
    1462. 

  1462. 			continue
    1463. 

  1463. 		
    1464. 

  1464. 		# one line PRE-formatted text
    1465. 

  1465. 		if regex['1linePre'].search(line):
    1466. 

  1466. 			f_lastwasblank = 0
    1467. 

  1467. 			line = regex['1linePre'].sub('',line)
    1468. 

  1468. 			line = doPreLine(doctype, line)
    1469. 

  1469. 			t1, t2 = TAGS['areaPreOpen'],TAGS['areaPreClose']
    1470. 

  1470. 			ret.append('%s\n%s\n%s'%(t1,line,t2))
    1471. 

  1471. 			continue
    1472. 

  1472. 		
    1473. 

  1473. 		#---------------------[ blank lines ]-----------------------
    1474. 

  1474. 		
    1475. 

  1475. 		#TODO "holdspace" to save <p> to not show in closelist
    1476. 

  1476. 		if regex['blankline'].search(line):
    1477. 

  1477. 			
    1478. 

  1478. 			# closing all open quotes
    1479. 

  1479. 			if quotedepth:
    1480. 

  1480. 				ret.append(doCloseQuote())
    1481. 

  1481. 			
    1482. 

  1482. 			# closing all open lists
    1483. 

  1483. 			if f_lastwasblank:   # 2nd consecutive blank line
    1484. 

  1484. 				if listindent:   # closes list (if any)
    1485. 

  1485. 					ret.append(doCloseList())
    1486. 

  1486. 					holdspace = ''
    1487. 

  1487. 				continue         # consecutive blanks are trash
    1488. 

  1488. 			
    1489. 

  1489. 			# normal blank line
    1490. 

  1490. 			if doctype != 'pm6' and AREA == 'body':
    1491. 

  1491. 				# paragraph (if any) is wanted inside lists also
    1492. 

  1492. 				if listindent:
    1493. 

  1493. 					para = TAGS['paragraph'] + '\n'
    1494. 

  1494. 					holdspace = holdspace + para
    1495. 

  1495. 				elif doctype == 'html':
    1496. 

  1496. 					ret.append(TAGS['paragraph'])
    1497. 

  1497. 				# sgml: quote close tag must not be \n\n</quote>
    1498. 

  1498. 				elif doctype == 'sgml' and quotedepth:
    1499. 

  1499. 					skip_continue = 1
    1500. 

  1500. 				# otherwise we just print a blank line
    1501. 

  1501. 				else:
    1502. 

  1502. 					ret.append('')
    1503. 

  1503. 			
    1504. 

  1504. 			f_lastwasblank = 1
    1505. 

  1505. 			if not skip_continue: continue
    1506. 

  1506. 		
    1507. 

  1507. 		
    1508. 

  1508. 		#---------------------[ special ]------------------------
    1509. 

  1509. 		# just encoding for now
    1510. 

  1510. 		
    1511. 

  1511. 		if regex['special'].search(line):
    1512. 

  1512. 			special = line[2:]
    1513. 

  1513. 			
    1514. 

  1514. 			# try Settings
    1515. 

  1515. 			m = regex['setting'].match(special)
    1516. 

  1516. 			if m:
    1517. 

  1517. 				name = string.upper(m.group(1))
    1518. 

  1518. 				val  = m.group(2)
    1519. 

  1519. 				if AREA == 'conf':
    1520. 

  1520. 					if name == 'ENCODING':
    1521. 

  1521. 						val = get_encoding_string(val,doctype)
    1522. 

  1522. 					HEADERS[name] = val
    1523. 

  1523. 					Debug("Found Setting '%s', value '%s'"%(
    1524. 

  1524. 					       name,val),1,linenr)
    1525. 

  1525. 				else:
    1526. 

  1526. 					Debug('Ignoring Setting outside CONF area:'
    1527. 

  1527. 					      ' %s'%name,1,linenr)
    1528. 

  1528. 			else:
    1529. 

  1529. 				Debug('Bogus Special Line',1,linenr)
    1530. 

  1530. 		
    1531. 

  1531. 		#---------------------[ comments ]-----------------------
    1532. 

  1532. 		
    1533. 

  1533. 		# just skip them (if not macro or setting)
    1534. 

  1534. 		if regex['comment'].search(line) and not regex['date'].match(line):
    1535. 

  1535. 			continue
    1536. 

  1536. 		f_lastwasblank = 0       # reset blank status
    1537. 

  1537. 		
    1538. 

  1538. 		#---------------------[ BODY detect ]-----------------------
    1539. 

  1539. 		
    1540. 

  1540. 		### if got here, its a header or a valid line
    1541. 

  1541. 		if AREA == 'conf':
    1542. 

  1542. 			# oops, not header, so we're now on document BODY
    1543. 

  1543. 			AREA = NewArea('body', linenr)
    1544. 

  1544. 			# do headers!
    1545. 

  1545. 			if not FLAGS['noheaders']:
    1546. 

  1546. 				header = doHeader(doctype,HEADERS)
    1547. 

  1547. 			# so, let's print …
    1548.

Large files files are truncated, but you can click here to view the full file