PageRenderTime 59ms CodeModel.GetById 18ms RepoModel.GetById 0ms app.codeStats 0ms

/old/txt2tags-1.3.py

http://txt2tags.googlecode.com/
Python | 2091 lines | 2067 code | 5 blank | 19 comment | 7 complexity | 2c9b95472f5ce6f552936d3a17e22220 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 = '1.3'
    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. regex = {}
    35. 

  35. TAGS = {}
    36. 

  36. rules = {}
    37. 

  37. CMDLINE = ''
    38. 

  38. 

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

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

  41. doctype = outfile = ''
    42. 

  42. pipefileid = '-'
    43. 

  43. 

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

  45. 

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

  47. quotedepth = []
    48. 

  48. listindent = []
    49. 

  49. listids = []
    50. 

  50. subarea = None
    51. 

  51. tableborder = 0
    52. 

  52. 

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

  54. usage = """
    55. 

  55. %s
    56. 

  56. 

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

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

  59. 

  60.   -t, --type       target document type. actually supported:
    61. 

  61.                    %s
    62. 

  62. 

  63.       --stdout     by default, the output is written to file.<type>
    64. 

  64.                    with this option, STDOUT is used (no files written)
    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 to <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.       --gui        invoke Graphical Tk Interface
    72. 

  72. 

  73.   -h, --help       print this help information and exit
    74. 

  74.   -V, --version    print program version and exit
    75. 

  75. 

  76. extra options for HTML target (needs sgml-tools):
    77. 

  77.       --split      split documents. values: 0, 1, 2 (default 0)
    78. 

  78.       --lang       document language (default english)
    79. 

  79. """%(versionstr, re.sub(r"[]'[]",'',repr(targets)))
    80. 

    81. 

  81. 

  82. # here is all the target's templates
    83. 

  83. # you may edit them to fit your needs
    84. 

  84. #  - the %(HEADERn)s strings represent the Header lines
    85. 

  85. #  - use %% to represent a literal %
    86. 

  86. #
    87. 

  87. HEADER_TEMPLATE = {
    88. 

  88.   'txt': """\
    89. 

  89. %(HEADER1)s
    90. 

  90. %(HEADER2)s
    91. 

  91. %(HEADER3)s
    92. 

  92. """,
    93. 

    94. 

  94.   'sgml': """\
    95. 

  95. <!doctype linuxdoc system>
    96. 

  96. <article>
    97. 

  97. <title>%(HEADER1)s
    98. 

  98. <author>%(HEADER2)s
    99. 

  99. <date>%(HEADER3)s
    100. 

  100. """,
    101. 

    102. 

  102.   'html': """\
    103. 

  103. <HTML>
    104. 

  104. <HEAD>
    105. 

  105. <META NAME="GENERATOR" CONTENT="http://txt2tags.sf.net">
    106. 

  106. <META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=%(ENCODING)s">
    107. 

  107. <TITLE>%(HEADER1)s</TITLE></HEAD>
    108. 

  108. <BODY BGCOLOR="white" TEXT="black">
    109. 

  109. <P ALIGN="center"><CENTER><H1>%(HEADER1)s</H1>
    110. 

  110. <FONT SIZE=4>
    111. 

  111. <I>%(HEADER2)s</I><BR>
    112. 

  112. %(HEADER3)s
    113. 

  113. </FONT></CENTER>
    114. 

  114. """,
    115. 

    116. 

  116. 

  117. # TODO man section 1 is hardcoded...
    118. 

  118.   'man': """\
    119. 

  119. .TH "%(HEADER1)s" 1 %(HEADER3)s "%(HEADER2)s"
    120. 

  120. """,
    121. 

    122. 

  122. # TODO style to <HR>
    123. 

  123.   'pm6': """\
    124. 

  124. <PMTags1.0 win><C-COLORTABLE ("Preto" 1 0 0 0)
    125. 

  125. ><@Normal=
    126. 

  126.   <FONT "Times New Roman"><CCOLOR "Preto"><SIZE 11>
    127. 

  127.   <HORIZONTAL 100><LETTERSPACE 0><CTRACK 127><CSSIZE 70><C+SIZE 58.3>
    128. 

  128.   <C-POSITION 33.3><C+POSITION 33.3><P><CBASELINE 0><CNOBREAK 0><CLEADING -0.05>
    129. 

  129.   <GGRID 0><GLEFT 7.2><GRIGHT 0><GFIRST 0><G+BEFORE 7.2><G+AFTER 0>
    130. 

  130.   <GALIGNMENT "justify"><GMETHOD "proportional"><G& "ENGLISH">
    131. 

  131.   <GPAIRS 12><G%% 120><GKNEXT 0><GKWIDOW 0><GKORPHAN 0><GTABS $>
    132. 

  132.   <GHYPHENATION 2 34 0><GWORDSPACE 75 100 150><GSPACE -5 0 25>
    133. 

  133. ><@Bullet=<@-PARENT "Normal"><FONT "Abadi MT Condensed Light">
    134. 

  134.   <GLEFT 14.4><G+BEFORE 2.15><G%% 110><GTABS(25.2 l "")>
    135. 

  135. ><@PreFormat=<@-PARENT "Normal"><FONT "Lucida Console"><SIZE 8><CTRACK 0>
    136. 

  136.   <GLEFT 0><G+BEFORE 0><GALIGNMENT "left"><GWORDSPACE 100 100 100><GSPACE 0 0 0>
    137. 

  137. ><@Title1=<@-PARENT "Normal"><FONT "Arial"><SIZE 14><B>
    138. 

  138.   <GCONTENTS><GLEFT 0><G+BEFORE 0><GALIGNMENT "left">
    139. 

  139. ><@Title2=<@-PARENT "Title1"><SIZE 12><G+BEFORE 3.6>
    140. 

  140. ><@Title3=<@-PARENT "Title1"><SIZE 10><GLEFT 7.2><G+BEFORE 7.2>
    141. 

  141. ><@Title4=<@-PARENT "Title3">
    142. 

  142. ><@Title5=<@-PARENT "Title3">
    143. 

  143. ><@Quote=<@-PARENT "Normal"><SIZE 10><I>>
    144. 

  144. 

  145. %(HEADER1)s
    146. 

  146. %(HEADER2)s
    147. 

  147. %(HEADER3)s
    148. 

  148. """,
    149. 

    150. 

  150.   'mgp': """\
    151. 

  151. #!/usr/X11R6/bin/mgp -t 90
    152. 

  152. %%deffont "normal"    xfont  "utopia-medium-r", charset "iso8859-1"
    153. 

  153. %%deffont "normal-i"  xfont  "utopia-medium-i", charset "iso8859-1"
    154. 

  154. %%deffont "normal-b"  xfont  "utopia-bold-r"  , charset "iso8859-1"
    155. 

  155. %%deffont "normal-bi" xfont  "utopia-bold-i"  , charset "iso8859-1"
    156. 

  156. %%deffont "mono"      xfont "courier-medium-r", charset "iso8859-1"
    157. 

  157. %%default 1 size 5
    158. 

  158. %%default 2 size 8, fore "yellow", font "normal-b", center
    159. 

  159. %%default 3 size 5, fore "white",  font "normal", left, prefix "  "
    160. 

  160. %%tab 1 size 4, vgap 30, prefix "     ", icon arc "red" 40, leftfill
    161. 

  161. %%tab 2 prefix "            ", icon arc "orange" 40, leftfill
    162. 

  162. %%tab 3 prefix "                   ", icon arc "brown" 40, leftfill
    163. 

  163. %%tab 4 prefix "                          ", icon arc "darkmagenta" 40, leftfill
    164. 

  164. %%tab 5 prefix "                                ", icon arc "magenta" 40, leftfill
    165. 

  165. %%%%------------------------- end of headers -----------------------------
    166. 

  166. %%page
    167. 

  167. 

  168. 

  169. 

  170. 

  171. 

  172. %%size 10, center, fore "yellow"
    173. 

  173. %(HEADER1)s
    174. 

  174. 

  175. %%font "normal-i", size 6, fore "white", center
    176. 

  176. %(HEADER2)s
    177. 

  177. 

  178. %%font "mono", size 7, center
    179. 

  179. %(HEADER3)s
    180. 

  180. """,
    181. 

    182. 

  182. # TODO please, improve me!
    183. 

  183.   'moin': """\
    184. 

  184. %(HEADER1)s
    185. 

  185. %(HEADER2)s
    186. 

  186. %(HEADER3)s
    187. 

  187. """,
    188. 

    189. 

  189.   'tex': \
    190. 

  190. r"""\documentclass[11pt,a4paper]{article}
    191. 

  191. \usepackage{amsfonts,amssymb,graphicx,url}
    192. 

  192. \usepackage[%(ENCODING)s]{inputenc}  %% char encoding
    193. 

  193. \pagestyle{plain}   %% do page numbering ('empty' turns off)
    194. 

  194. \frenchspacing      %% no aditional spaces after periods
    195. 

  195. \setlength{\parskip}{8pt}\parindent=0pt  %% no paragraph indentation
    196. 

  196. %% uncomment next line for fancy PDF output on Adobe Acrobat Reader
    197. 

  197. %%\usepackage[pdfstartview=FitV,colorlinks=true,bookmarks=true]{hyperref}
    198. 

  198. 

  199. \title{%(HEADER1)s}
    200. 

  200. \author{%(HEADER2)s}
    201. 

  201. \begin{document}
    202. 

  202. \date{%(HEADER3)s}
    203. 

  203. \maketitle
    204. 

  204. """
    205. 

  205. }
    206. 

  206. 

  207. #-----------------------------------------------------------------------
    208. 

  208. 

  209. def Quit(msg, exitcode=0): print msg ; sys.exit(exitcode)
    210. 

  210. def Error(msg): print "ERROR: %s"%msg ; sys.exit()
    211. 

  211. def Debug(msg,i=0,linenr=None):
    212. 

  212. 	if i > DEBUG: return
    213. 

  213. 	if linenr is not None:
    214. 

  214. 		print "(%d) %04d:%s"%(i,linenr,msg)
    215. 

  215. 	else:
    216. 

  216. 		print "(%d) %s"%(i,msg)
    217. 

  217. def Readfile(file):
    218. 

  218. 	if file == '-':
    219. 

  219. 		try: data = sys.stdin.readlines()
    220. 

  220. 		except: Error('You must feed me with data on STDIN!')
    221. 

  221. 	else:
    222. 

  222. 		try: f = open(file); data = f.readlines() ; f.close()
    223. 

  223. 		except: Error("Cannot read file:\n    %s"%file)
    224. 

  224. 	return data
    225. 

  225. def Savefile(file, contents):
    226. 

  226. 	try: f = open(file, 'w')
    227. 

  227. 	except: Error("Cannot open file for writing:\n    %s"%file)
    228. 

  228. 	if type(contents) == type([]): doit = f.writelines
    229. 

  229. 	else: doit = f.write
    230. 

  230. 	doit(contents) ; f.close()
    231. 

  231. 

  232. def NewArea(new, linenr):
    233. 

  233. 	if new not in ['head', 'conf', 'body']:
    234. 

  234. 		Error("Invalid new AREA '%s' on line '%s'"%(new,linenr))
    235. 

  235. 	Debug('NEW AREA: %s'%new, 1, linenr)
    236. 

  236. 	return new
    237. 

  237. 

  238. def reset_flags():
    239. 

  239. 	global FLAGS
    240. 

  240. 	for flag in FLAGS.keys(): FLAGS[flag] = 0
    241. 

  241. 

  242. def set_outfile_name(infile, doctype):
    243. 

  243. 	"dirname is the same for {in,out}file"
    244. 

  244. 	if not infile: return
    245. 

  245. 	if infile == pipefileid or FLAGS['toconly'] or FLAGS['stdout']:
    246. 

  246. 		outfile = pipefileid
    247. 

  247. 	else:
    248. 

  248. 		outfile = "%s.%s"%(re.sub('\.(txt|t2t)$','',infile), doctype)
    249. 

  249. 	Debug(" infile: '%s'"% infile, 1)
    250. 

  250. 	Debug("outfile: '%s'"%outfile, 1)
    251. 

  251. 	return outfile
    252. 

  252. 

  253. def finish_him(outlist, outfile):
    254. 

  254. 	"writing output to screen or file"
    255. 

  255. 	if outfile == pipefileid:
    256. 

  256. 		for line in outlist: print line
    257. 

  257. 	else:
    258. 

  258. 		Savefile(outfile, addLineBreaks(outlist))
    259. 

  259. 		if not FLAGS['gui']: print 'wrote %s'%(outfile)
    260. 

  260. 	
    261. 

  261. 	if splitlevel:
    262. 

  262. 		print "--- html..."
    263. 

  263. 		os.system('sgml2html --language=%s --split=%s %s'%(
    264. 

  264. 		           lang,splitlevel,outfile))
    265. 

  265. 

  266. def ParseCmdline(cmdline=sys.argv):
    267. 

  267. 	"return a dic with all options:value found"
    268. 

  268. 	global CMDLINE ; CMDLINE = cmdline  # save for dofooter()
    269. 

  269. 	Debug("cmdline: %s"%cmdline, 1)
    270. 

  270. 	options = {'infile': '', 'infiles':''}
    271. 

  271. 	
    272. 

  272. 	# get cmdline options
    273. 

  273. 	longopt = ['help', 'version', 'type=', 'split=', 'lang=']+FLAGS.keys()
    274. 

  274. 	try: (opt, args) = getopt.getopt(cmdline[1:], 'hVt:', longopt)
    275. 

  275. 	except getopt.GetoptError:
    276. 

  276. 		Error('Bad option or missing argument (try --help)')
    277. 

  277. 	
    278. 

  278. 	# get infile, if any
    279. 

  279. 	if args:
    280. 

  280. 		options['infile'] = args[0]
    281. 

  281. 		options['infiles'] = args  # multi
    282. 

  282. 	
    283. 

  283. 	for name,val in opt:
    284. 

  284. 		# parse information options
    285. 

  285. 		if   name in ['-h','--help'   ]: Quit(usage)
    286. 

  286. 		elif name in ['-V','--version']: Quit(versionstr)
    287. 

  287. 		# parse short/long options
    288. 

  288. 		elif name in ['-t','--type']:
    289. 

  289. 			options['doctype'] = val
    290. 

  290. 			continue
    291. 

  291. 		# just long options
    292. 

  292. 		options[name[2:]] = val  # del --
    293. 

  293. 	
    294. 

  294. 	Debug("cmdline options: %s"%options, 1)
    295. 

  295. 	return options
    296. 

  296. 

  297. 

  298. def ParseCmdlineOptions(optdic):
    299. 

  299. 	"set vars and flags according to options dic"
    300. 

  300. 	global FLAGS, splitlevel, lang
    301. 

  301. 	
    302. 

  302. 	# store flags and vars 
    303. 

  303. 	myflags = [] # for debug msg
    304. 

  304. 	for flag in FLAGS.keys():
    305. 

  305. 		if optdic.has_key(flag):
    306. 

  306. 			FLAGS[flag] = 1
    307. 

  307. 			myflags.append(flag)
    308. 

  308. 	doctype    = optdic.get('doctype')
    309. 

  309. 	infile     = optdic.get('infile')
    310. 

  310. 	splitlevel = optdic.get('split')
    311. 

  311. 	lang       = optdic.get('lang')
    312. 

  312. 	Debug("cmdline flags: %s"%string.join(myflags,', '), 1)
    313. 

  313. 	
    314. 

  314. 	if not doctype and FLAGS['toconly']: doctype = 'txt' # toconly dft type
    315. 

  315. 	if not infile or not doctype: Quit(usage, 1)    # no filename/doctype
    316. 

  316. 	
    317. 

  317. 	# sanity check: validate target type
    318. 

  318. 	if not targets.count(doctype):
    319. 

  319. 		Error("Invalid document type '%s' (try --help)"%(doctype))
    320. 

  320. 	
    321. 

  321. 	outfile = set_outfile_name(infile, doctype)
    322. 

  322. 	
    323. 

  323. 	# sanity check: validate split level
    324. 

  324. 	if doctype != 'html': splitlevel = '' # only valid for HTML target
    325. 

  325. 	if splitlevel:
    326. 

  326. 		# checkings
    327. 

  327. 		if outfile == pipefileid:
    328. 

  328. 			Error('You need to provide a FILE (not STDIN) '
    329. 

  329. 			      'when using --split')
    330. 

  330. 		if splitlevel[0] not in '012':
    331. 

  331. 			Error('Option --split must be 0, 1 or 2')
    332. 

  332. 		# check for sgml-tools	
    333. 

  333. 		#TODO how to test (in a clever way) if an executable is in path?
    334. 

  334. 		#TODO os.system() return code? sgml2html w/out --help exit 0?
    335. 

  335. 		#TODO bah! implement sgml2html split natively and we're done
    336. 

  336. 		# Error("Sorry, you must have 'sgml2html' to use --split")
    337. 

  337. 		
    338. 

  338. 		# set things
    339. 

  339. 		FLAGS['stdout'] = 0  # no --stdout
    340. 

  340. 		doctype = 'sgml'     # 1st do a sgml, then sgml2html
    341. 

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

  342. 	
    343. 

  343. 	# sanity check: source loss!
    344. 

  344. 	if infile != pipefileid and infile == outfile:
    345. 

  345. 		Error("SUICIDE WARNING!!!   (try --stdout)\n  source"+\
    346. 

  346. 		      " and target files has the same name: %s"%outfile)
    347. 

  347. 	### yes, i've got my sample.t2t file deleted before add this test... :/
    348. 

  348. 	
    349. 

  349. 	return infile,outfile,doctype
    350. 

  350. 	#TODO splitlevel, lang
    351. 

  351. 

  352. #---End of ParseCmdlineOptions
    353. 

  353. 

  354. def toc_master(doctype, header, doc, toc):
    355. 

  355. 	"decide to include TOC or not on the outlist"
    356. 

  356. 	
    357. 

  357. 	# deal with the TOC options
    358. 

  358. 	if FLAGS['toc'] or FLAGS['toconly']:
    359. 

  359. 		# format TOC lines
    360. 

  360. 		### here we do toc as a valid t2t marked text (list type)
    361. 

  361. 		FLAGS['noheaders'] = 1
    362. 

  362. 		x,y,toc = convert(['']+toc+['',''], doctype)
    363. 

  363. 		
    364. 

  364. 		# TOC between bars (not for --toconly)
    365. 

  365. 		if FLAGS['toc']:
    366. 

  366. 			para = TAGS['paragraph']
    367. 

  367. 			tocbar = [para, regex['x'].sub('-'*72,TAGS['bar1']), para]
    368. 

  368. 			toc = tocbar + toc + tocbar
    369. 

  369. 		
    370. 

  370. 		if FLAGS['toconly']: header = doc = []
    371. 

  371. 	else:
    372. 

  372. 		toc = []
    373. 

  373. 	
    374. 

  374. 	# TOC is a tag
    375. 

  375. 	if TAGS['TOC'] and not FLAGS['toconly']:
    376. 

  376. 		toc = []
    377. 

  377. 	
    378. 

  378. 	return header + toc + doc
    379. 

  379. 

  380. 

  381. def doitall(cmdlinedic):
    382. 

  382. 	global outfile
    383. 

  383. 	infile,outfile,doctype = ParseCmdlineOptions(cmdlinedic)
    384. 

  384. 	header,toc,doc = convert(Readfile(infile), doctype)
    385. 

  385. 	outlist = toc_master(doctype,header,doc,toc)
    386. 

  386. 	return doctype, outfile, outlist
    387. 

  387. 

  388. 

  389. # set the Line Break across platforms
    390. 

  390. LB = '\n'                                   # default
    391. 

  391. if   sys.platform[:3] == 'win': LB = '\r\n'
    392. 

  392. #elif sys.platform[:3] == 'cyg': LB = '\r\n' # not sure if it's best :(
    393. 

  393. elif sys.platform[:3] == 'mac': LB = '\r'
    394. 

  394. 

  395. 

  396. def escapePythonSpecials(txt):
    397. 

  397. 	# drawback of using re.sub() - double escape some specials like \n
    398. 

  398. 	# see also: 'force_re' marks on the code
    399. 

  399. 	if sys.version[0] == '1':
    400. 

  400. 		return re.sub(r'(\\[ntsrfvul])',r'\\\1',txt)
    401. 

  401. 	else:
    402. 

  402. 		return re.sub(r'(\\[ntsrfv])'  ,r'\\\1',txt)
    403. 

  403. 

  404. def getTags(doctype):
    405. 

  405. 	keys = [
    406. 

  406. 	'paragraph','title1','title2','title3','title4','title5',
    407. 

  407. 	'areaPreOpen','areaPreClose',
    408. 

  408. 	'areaQuoteOpen','areaQuoteClose',
    409. 

  409. 	'fontMonoOpen','fontMonoClose',
    410. 

  410. 	'fontBoldOpen','fontBoldClose',
    411. 

  411. 	'fontItalicOpen','fontItalicClose',
    412. 

  412. 	'fontBolditalicOpen','fontBolditalicClose',
    413. 

  413. 	'fontUnderlineOpen','fontUnderlineClose',
    414. 

  414. 	'listOpen','listClose','listItem',
    415. 

  415. 	'numlistOpen','numlistClose','numlistItem',
    416. 

  416. 	'deflistOpen','deflistClose','deflistItem1','deflistItem2',
    417. 

  417. 	'bar1','bar2',
    418. 

  418. 	'url','urlMark','email','emailMark',
    419. 

  419. 	'img','imgsolo',
    420. 

  420. 	'tableOpen','tableClose','tableLineOpen','tableLineClose',
    421. 

  421. 	'tableCellOpen','tableCellClose',
    422. 

  422. 	'tableTitleCellOpen','tableTitleCellClose',
    423. 

  423. 	'anchor','comment','TOC',
    424. 

  424. 	'EOD'
    425. 

  425. 	]
    426. 

  426. 	
    427. 

  427. 	if doctype == "txt":
    428. 

  428. 		tags = {
    429. 

  429. 		'title1'             : '  \a'      , 
    430. 

  430. 		'title2'             : '\t\a'      ,
    431. 

  431. 		'title3'             : '\t\t\a'    ,
    432. 

  432. 		'title4'             : '\t\t\t\a'  ,
    433. 

  433. 		'title5'             : '\t\t\t\t\a',
    434. 

  434. 		'areaQuoteOpen'      : '    '      ,
    435. 

  435. 		'listItem'           : '- '        ,
    436. 

  436. 		'numlistItem'        : '\a. '      ,
    437. 

  437. 		'bar1'               : '\a'        ,
    438. 

  438. 		'bar2'               : '\a'        ,
    439. 

  439. 		'url'                : '\a'        ,
    440. 

  440. 		'urlMark'            : '\a (\a)'   ,
    441. 

  441. 		'email'              : '\a'        ,
    442. 

  442. 		'emailMark'          : '\a (\a)'   ,
    443. 

  443. 		'img'                : '[\a]'      ,
    444. 

  444. 		}
    445. 

  445. 	
    446. 

  446. 	elif doctype == "html":
    447. 

  447. 		tags = {
    448. 

  448. 		'paragraph'          : '<P>'            ,
    449. 

  449. 		'title1'             : '<H1>\a</H1>'    ,
    450. 

  450. 		'title2'             : '<H2>\a</H2>'    ,
    451. 

  451. 		'title3'             : '<H3>\a</H3>'    ,
    452. 

  452. 		'title4'             : '<H4>\a</H4>'    ,
    453. 

  453. 		'title5'             : '<H5>\a</H5>'    ,
    454. 

  454. 		'areaPreOpen'        : '<PRE>'          ,
    455. 

  455. 		'areaPreClose'       : '</PRE>'         ,
    456. 

  456. 		'areaQuoteOpen'      : '<BLOCKQUOTE>'   ,
    457. 

  457. 		'areaQuoteClose'     : '</BLOCKQUOTE>'  ,
    458. 

  458. 		'fontMonoOpen'       : '<CODE>'         ,
    459. 

  459. 		'fontMonoClose'      : '</CODE>'        ,
    460. 

  460. 		'fontBoldOpen'       : '<B>'            ,
    461. 

  461. 		'fontBoldClose'      : '</B>'           ,
    462. 

  462. 		'fontItalicOpen'     : '<I>'            ,
    463. 

  463. 		'fontItalicClose'    : '</I>'           ,
    464. 

  464. 		'fontBolditalicOpen' : '<B><I>'         ,
    465. 

  465. 		'fontBolditalicClose': '</I></B>'       ,
    466. 

  466. 		'fontUnderlineOpen'  : '<U>'            ,
    467. 

  467. 		'fontUnderlineClose' : '</U>'           ,
    468. 

  468. 		'listOpen'           : '<UL>'           ,
    469. 

  469. 		'listClose'          : '</UL>'          ,
    470. 

  470. 		'listItem'           : '<LI>'           ,
    471. 

  471. 		'numlistOpen'        : '<OL>'           ,
    472. 

  472. 		'numlistClose'       : '</OL>'          ,
    473. 

  473. 		'numlistItem'        : '<LI>'           ,
    474. 

  474. 		'deflistOpen'        : '<DL>'           ,
    475. 

  475. 		'deflistClose'       : '</DL>'          ,
    476. 

  476. 		'deflistItem1'       : '<DT>\a</DT>'    ,
    477. 

  477. 		'deflistItem2'       : '<DD>'           ,
    478. 

  478. 		'bar1'               : '<HR NOSHADE SIZE=1>'        ,
    479. 

  479. 		'bar2'               : '<HR NOSHADE SIZE=5>'        ,
    480. 

  480. 		'url'                : '<A HREF="\a">\a</A>'        ,
    481. 

  481. 		'urlMark'            : '<A HREF="\a">\a</A>'        ,
    482. 

  482. 		'email'              : '<A HREF="mailto:\a">\a</A>' ,
    483. 

  483. 		'emailMark'          : '<A HREF="mailto:\a">\a</A>' ,
    484. 

  484. 		'img'                : '<IMG ALIGN="\a" SRC="\a" BORDER="0">',
    485. 

  485. 		'imgsolo'            : '<P ALIGN="center">\a</P>'   ,
    486. 

  486. 		'tableOpen'          : '<table align=center cellpadding=4 border=\a>',
    487. 

  487. 		'tableClose'         : '</table>'       ,
    488. 

  488. 		'tableLineOpen'      : '<tr>'           ,
    489. 

  489. 		'tableLineClose'     : '</tr>'          ,
    490. 

  490. 		'tableCellOpen'      : '<td>'           ,
    491. 

  491. 		'tableCellClose'     : '</td>'          ,
    492. 

  492. 		'tableTitleCellOpen' : '<th>'           ,
    493. 

  493. 		'tableTitleCellClose': '</th>'          ,
    494. 

  494. 		'anchor'             : '<a name="\a">'  ,
    495. 

  495. 		'comment'            : '<!-- \a -->'    ,
    496. 

  496. 		'EOD'                : '</BODY></HTML>'
    497. 

  497. 		}
    498. 

  498. 	
    499. 

  499. 	elif doctype == "sgml":
    500. 

  500. 		tags = {
    501. 

  501. 		'paragraph'          : '<p>'                ,
    502. 

  502. 		'title1'             : '<sect>\a<p>'        ,
    503. 

  503. 		'title2'             : '<sect1>\a<p>'       ,
    504. 

  504. 		'title3'             : '<sect2>\a<p>'       ,
    505. 

  505. 		'title4'             : '<sect3>\a<p>'       ,
    506. 

  506. 		'title5'             : '<sect4>\a<p>'       ,
    507. 

  507. 		'areaPreOpen'        : '<tscreen><verb>'    ,
    508. 

  508. 		'areaPreClose'       : '</verb></tscreen>'  ,
    509. 

  509. 		'areaQuoteOpen'      : '<quote>'            ,
    510. 

  510. 		'areaQuoteClose'     : '</quote>'           ,
    511. 

  511. 		'fontMonoOpen'       : '<tt>'               ,
    512. 

  512. 		'fontMonoClose'      : '</tt>'              ,
    513. 

  513. 		'fontBoldOpen'       : '<bf>'               ,
    514. 

  514. 		'fontBoldClose'      : '</bf>'              ,
    515. 

  515. 		'fontItalicOpen'     : '<em>'               ,
    516. 

  516. 		'fontItalicClose'    : '</em>'              ,
    517. 

  517. 		'fontBolditalicOpen' : '<bf><em>'           ,
    518. 

  518. 		'fontBolditalicClose': '</em></bf>'         ,
    519. 

  519. 		'fontUnderlineOpen'  : '<bf><em>'           ,
    520. 

  520. 		'fontUnderlineClose' : '</em></bf>'         ,
    521. 

  521. 		'listOpen'           : '<itemize>'          ,
    522. 

  522. 		'listClose'          : '</itemize>'         ,
    523. 

  523. 		'listItem'           : '<item>'             ,
    524. 

  524. 		'numlistOpen'        : '<enum>'             ,
    525. 

  525. 		'numlistClose'       : '</enum>'            ,
    526. 

  526. 		'numlistItem'        : '<item>'             ,
    527. 

  527. 		'deflistOpen'        : '<descrip>'          ,
    528. 

  528. 		'deflistClose'       : '</descrip>'         ,
    529. 

  529. 		'deflistItem1'       : '<tag>\a</tag>'      ,
    530. 

  530. 		'bar1'               : '<!-- \a -->'        ,
    531. 

  531. 		'bar2'               : '<!-- \a -->'        ,
    532. 

  532. 		'url'                : '<htmlurl url="\a" name="\a">'        ,
    533. 

  533. 		'urlMark'            : '<htmlurl url="\a" name="\a">'        ,
    534. 

  534. 		'email'              : '<htmlurl url="mailto:\a" name="\a">' ,
    535. 

  535. 		'emailMark'          : '<htmlurl url="mailto:\a" name="\a">' ,
    536. 

  536. 		'img'                : '<figure><ph vspace=""><img src="\a"></figure>',
    537. 

  537. 		'tableOpen'          : '<table><tabular ca="c">'             ,
    538. 

  538. 		'tableClose'         : '</tabular></table>' ,
    539. 

  539. 		'tableLineClose'     : '<rowsep>'           ,
    540. 

  540. 		'tableCellClose'     : '<colsep>'           ,
    541. 

  541. 		'tableTitleCellClose': '<colsep>'           ,
    542. 

  542. 		'comment'            : '<!-- \a -->'        ,
    543. 

  543. 		'TOC'                : '<toc>',
    544. 

  544. 		'EOD'                : '</article>'
    545. 

  545. 		}
    546. 

  546. 	
    547. 

  547. 	elif doctype == "tex":
    548. 

  548. 		tags = {
    549. 

  549. 		'title1'             : '\n\\newpage\section{\a}',
    550. 

  550. 		'title2'             : '\\subsection{\a}'       ,
    551. 

  551. 		'title3'             : '\\subsubsection{\a}'    ,
    552. 

  552. 		# title 4/5: DIRTY: para+BF+\\+\n
    553. 

  553. 		'title4'             : '\\paragraph{}\\textbf{\a}\\\\\\\n' ,
    554. 

  554. 		'title5'             : '\\paragraph{}\\textbf{\a}\\\\\\\n' ,
    555. 

  555. 		'areaPreOpen'        : '\\begin{verbatim}'    ,
    556. 

  556. 		'areaPreClose'       : '\\end{verbatim}'      ,
    557. 

  557. 		'areaQuoteOpen'      : '\\begin{quotation}'   ,
    558. 

  558. 		'areaQuoteClose'     : '\\end{quotation}'     ,
    559. 

  559. 		'fontMonoOpen'       : '\\texttt{'            ,
    560. 

  560. 		'fontMonoClose'      : '}'                    ,
    561. 

  561. 		'fontBoldOpen'       : '\\textbf{'            ,
    562. 

  562. 		'fontBoldClose'      : '}'                    ,
    563. 

  563. 		'fontItalicOpen'     : '\\textit{'            ,
    564. 

  564. 		'fontItalicClose'    : '}'                    ,
    565. 

  565. 		'fontBolditalicOpen' : '\\textbf{\\textit{'   ,
    566. 

  566. 		'fontBolditalicClose': '}}'                   ,
    567. 

  567. 		'fontUnderlineOpen'  : '\\underline{'         ,  
    568. 

  568. 		'fontUnderlineClose' : '}'                    ,
    569. 

  569. 		'listOpen'           : '\\begin{itemize}'     ,
    570. 

  570. 		'listClose'          : '\\end{itemize}'       ,
    571. 

  571. 		'listItem'           : '\\item '              ,
    572. 

  572. 		'numlistOpen'        : '\\begin{enumerate}'   ,
    573. 

  573. 		'numlistClose'       : '\\end{enumerate}'     ,
    574. 

  574. 		'numlistItem'        : '\\item '              ,
    575. 

  575. 		'deflistOpen'        : '\\begin{description}' ,
    576. 

  576. 		'deflistClose'       : '\\end{description}'   ,
    577. 

  577. 		'deflistItem1'       : '\\item[\a]'           ,
    578. 

  578. 		'bar1'               : '\n\\hrulefill{}\n'    ,
    579. 

  579. 		'bar2'               : '\n\\rule{\linewidth}{1mm}\n'    ,
    580. 

  580. 		'url'                : '\\url{\a}'                      ,
    581. 

  581. 		'urlMark'            : '\\textit{\a} (\\url{\a})'       ,
    582. 

  582. 		'email'              : '\\url{\a}'                      ,
    583. 

  583. 		'emailMark'          : '\\textit{\a} (\\url{\a})'       ,
    584. 

  584. 		'img'                : '(\a)'                           ,
    585. 

  585. 		'tableOpen'          : '\\begin{center}\\begin{tabular}',
    586. 

  586. 		'tableClose'         : '\\end{tabular}\\end{center}'    ,
    587. 

  587. 		'tableLineOpen'      : '\\hline '             ,
    588. 

  588. 		'tableLineClose'     : ' \\\\'                ,
    589. 

  589. 		'tableCellClose'     : ' & '                  ,
    590. 

  590. 		'tableTitleCellOpen' : '\\textbf{'            ,
    591. 

  591. 		'tableTitleCellClose': '} & '                 ,
    592. 

  592. 		'comment'            : '% \a'                 ,
    593. 

  593. 		'TOC'                : '\\newpage\\tableofcontents',
    594. 

  594. 		'EOD'                : '\\end{document}'
    595. 

  595. 		}
    596. 

  596. 	
    597. 

  597. 	elif doctype == "moin":
    598. 

  598. 		tags = {
    599. 

  599. 		'title1'             : '= \a ='         ,
    600. 

  600. 		'title2'             : '== \a =='       ,
    601. 

  601. 		'title3'             : '=== \a ==='     ,
    602. 

  602. 		'title4'             : '==== \a ===='   ,
    603. 

  603. 		'title5'             : '===== \a =====' ,
    604. 

  604. 		'areaPreOpen'        : '{{{'            ,
    605. 

  605. 		'areaPreClose'       : '}}}'            ,
    606. 

  606. 		'areaQuoteOpen'      : ' '              ,
    607. 

  607. 		'fontMonoOpen'       : '{{{'            ,
    608. 

  608. 		'fontMonoClose'      : '}}}'            ,
    609. 

  609. 		'fontBoldOpen'       : "'''"            ,
    610. 

  610. 		'fontBoldClose'      : "'''"            ,
    611. 

  611. 		'fontItalicOpen'     : "''"             ,
    612. 

  612. 		'fontItalicClose'    : "''"             ,
    613. 

  613. 		'fontBolditalicOpen' : "'''''"          ,
    614. 

  614. 		'fontBolditalicClose': "'''''"          ,
    615. 

  615. 		'fontUnderlineOpen'  : "'''''"          ,
    616. 

  616. 		'fontUnderlineClose' : "'''''"          , 
    617. 

  617. 		'listItem'           : '* '             ,
    618. 

  618. 		'numlistItem'        : '\a. '           ,
    619. 

  619. 		'bar1'               : '----'           ,
    620. 

  620. 		'bar2'               : '----'           ,
    621. 

  621. 		'url'                : '[\a]'           ,
    622. 

  622. 		'urlMark'            : '[\a \a]'        ,
    623. 

  623. 		'email'              : '[\a]'           ,
    624. 

  624. 		'emailMark'          : '[\a \a]'        ,
    625. 

  625. 		'img'                : '[\a]'           ,
    626. 

  626. 		'tableLineOpen'      : '||'             ,
    627. 

  627. 		'tableCellClose'     : '||'             ,
    628. 

  628. 		'tableTitleCellClose': '||'             ,
    629. 

  629. 		}
    630. 

  630. 	
    631. 

  631. 	elif doctype == "mgp":
    632. 

  632. 		tags = {
    633. 

  633. 		'paragraph'          : '%font "normal", size 5\n'    , 
    634. 

  634. 		'title1'             : '%page\n\n\a'                 ,
    635. 

  635. 		'title2'             : '%page\n\n\a'                 ,
    636. 

  636. 		'title3'             : '%page\n\n\a'                 ,
    637. 

  637. 		'title4'             : '%page\n\n\a'                 ,
    638. 

  638. 		'title5'             : '%page\n\n\a'                 ,
    639. 

  639. 		'areaPreOpen'        : '\n%font "mono"'              ,
    640. 

  640. 		'areaPreClose'       : '%font "normal"'              ,
    641. 

  641. 		'areaQuoteOpen'      : '%prefix "       "'           ,
    642. 

  642. 		'areaQuoteClose'     : '%prefix "  "'                ,
    643. 

  643. 		'fontMonoOpen'       : '\n%cont, font "mono"\n'      ,
    644. 

  644. 		'fontMonoClose'      : '\n%cont, font "normal"\n'    ,
    645. 

  645. 		'fontBoldOpen'       : '\n%cont, font "normal-b"\n'  ,
    646. 

  646. 		'fontBoldClose'      : '\n%cont, font "normal"\n'    ,
    647. 

  647. 		'fontItalicOpen'     : '\n%cont, font "normal-i"\n'  ,
    648. 

  648. 		'fontItalicClose'    : '\n%cont, font "normal"\n'    ,
    649. 

  649. 		'fontBolditalicOpen' : '\n%cont, font "normal-bi"\n' ,
    650. 

  650. 		'fontBolditalicClose': '\n%cont, font "normal"\n'    ,
    651. 

  651. 		'fontUnderlineOpen'  : '\n%cont, fore "cyan"\n'      ,
    652. 

  652. 		'fontUnderlineClose' : '\n%cont, fore "white"\n'     ,
    653. 

  653. 		'numlistItem'        : '\a. '                        ,
    654. 

  654. 		'bar1'               : '%bar "white" 5'              ,
    655. 

  655. 		'bar2'               : '%pause'                      ,
    656. 

  656. 		'url'                : '\n%cont, fore "cyan"\n\a\n%cont, fore "white"\n',
    657. 

  657. 		'urlMark'            : '\a \n%cont, fore "cyan"\n\a\n%cont, fore "white"\n',
    658. 

  658. 		'email'              : '\n%cont, fore "cyan"\n\a\n%cont, fore "white"\n',
    659. 

  659. 		'emailMark'          : '\a \n%cont, fore "cyan"\n\a\n%cont, fore "white"\n',
    660. 

  660. 		'img'                : '\n%center\n%newimage "\a", left\n',
    661. 

  661. 		'comment'            : '%% \a'                       ,
    662. 

  662. 		'EOD'                : '%%EOD'
    663. 

  663. 		}
    664. 

  664. 	
    665. 

  665. 	elif doctype == "man":
    666. 

  666. 		tags = {
    667. 

  667. 		'paragraph'          : '.P'      ,
    668. 

  668. 		'title1'             : '.SH \a'  ,
    669. 

  669. 		'title2'             : '.SS \a'  ,
    670. 

  670. 		'title3'             : '.SS \a'  ,
    671. 

  671. 		'title4'             : '.SS \a'  ,
    672. 

  672. 		'title5'             : '.SS \a'  ,
    673. 

  673. 		'areaPreOpen'        : '.nf'     ,
    674. 

  674. 		'areaPreClose'       : '.fi\n'   ,
    675. 

  675. 		'areaQuoteOpen'      : '\n'      ,
    676. 

  676. 		'areaQuoteClose'     : '\n'      ,
    677. 

  677. 		'fontBoldOpen'       : '\\fB'   ,
    678. 

  678. 		'fontBoldClose'      : '\\fP'   ,
    679. 

  679. 		'fontItalicOpen'     : '\\fI'   ,
    680. 

  680. 		'fontItalicClose'    : '\\fP'   ,
    681. 

  681. 		'fontBolditalicOpen' : '\n.BI '  ,
    682. 

  682. 		'fontBolditalicClose': '\n\\&'   ,
    683. 

  683. 		'listOpen'           : '\n.nf'   ,  # pre
    684. 

  684. 		'listClose'          : '.fi\n'   ,
    685. 

  685. 		'listItem'           : '* '      ,
    686. 

  686. 		'numlistOpen'        : '\n.nf'   ,  # pre
    687. 

  687. 		'numlistClose'       : '.fi\n'   ,
    688. 

  688. 		'numlistItem'        : '\a. '    ,
    689. 

  689. 		'bar1'               : '\n\n'    ,
    690. 

  690. 		'bar2'               : '\n\n'    ,
    691. 

  691. 		'url'                : '\a'      ,
    692. 

  692. 		'urlMark'            : '\a (\a)' ,
    693. 

  693. 		'email'              : '\a'      ,
    694. 

  694. 		'emailMark'          : '\a (\a)' ,
    695. 

  695. 		'img'                : '\a'      ,
    696. 

  696. 		'comment'            : '.\\" \a'
    697. 

  697. 		}
    698. 

  698. 	
    699. 

  699. 	elif doctype == "pm6":
    700. 

  700. 		tags = {
    701. 

  701. 		'paragraph'          : '<@Normal:>'     ,
    702. 

  702. 		'title1'             : '\n<@Title1:>\a' ,
    703. 

  703. 		'title2'             : '\n<@Title2:>\a' ,
    704. 

  704. 		'title3'             : '\n<@Title3:>\a' ,
    705. 

  705. 		'title4'             : '\n<@Title4:>\a' ,
    706. 

  706. 		'title5'             : '\n<@Title5:>\a' ,
    707. 

  707. 		'areaPreOpen'        : '<@PreFormat:>'  ,
    708. 

  708. 		'areaQuoteOpen'      : '<@Quote:>'      ,
    709. 

  709. 		'fontMonoOpen'       : '<FONT "Lucida Console"><SIZE 9>' ,
    710. 

  710. 		'fontMonoClose'      : '<SIZE$><FONT$>' ,
    711. 

  711. 		'fontBoldOpen'       : '<B>'            ,
    712. 

  712. 		'fontBoldClose'      : '<P>'            ,
    713. 

  713. 		'fontItalicOpen'     : '<I>'            ,
    714. 

  714. 		'fontItalicClose'    : '<P>'            , 
    715. 

  715. 		'fontBolditalicOpen' : '<B><I>'         ,
    716. 

  716. 		'fontBolditalicClose': '<P>'            ,
    717. 

  717. 		'fontUnderlineOpen'  : '<U>'            ,
    718. 

  718. 		'fontUnderlineClose' : '<P>'            ,
    719. 

  719. 		'listOpen'           : '<@Bullet:>'     ,
    720. 

  720. 		'listItem'           : '\x95	'       ,   # \x95 == ~U
    721. 

  721. 		'numlistOpen'        : '<@Bullet:>'     ,
    722. 

  722. 		'numlistItem'        : '\x95    '       ,
    723. 

  723. 		'bar1'               : '\a'             ,
    724. 

  724. 		'bar2'               : '\a'             ,
    725. 

  725. 		'url'                : '<U>\a<P>'       ,   # underline
    726. 

  726. 		'urlMark'            : '\a <U>\a<P>'    ,
    727. 

  727. 		'email'              : '\a'             ,
    728. 

  728. 		'emailMark'          : '\a \a'          ,
    729. 

  729. 		'img'                : '\a'             ,
    730. 

  730. 		}
    731. 

  731. 	
    732. 

  732. 	# create empty tags keys
    733. 

  733. 	for key in keys:
    734. 

  734. 		if not tags.has_key(key):
    735. 

  735. 			tags[key] = ''
    736. 

  736. 		else:
    737. 

  737. 			tags[key] = escapePythonSpecials(tags[key])
    738. 

  738. 	
    739. 

  739. 	return tags
    740. 

  740. 

  741. 

  742. def getRules(doctype):
    743. 

  743. 	ret = {}
    744. 

  744. 	allrules = [
    745. 

  745. 	
    746. 

  746. 	 # target rules (ON/OFF)
    747. 

  747. 	  'linkable',           # target supports external links
    748. 

  748. 	  'tableable',          # target supports tables
    749. 

  749. 	  'imgalignable',       # target supports image alignment
    750. 

  750. 	  'listcountable',      # target supports numbered lists natively
    751. 

  751. 	  'tablecellsplit',     # place delimiters only *between* cells
    752. 

  752. 	  'listnotnested',      # lists cannot be nested
    753. 

  753. 	  'quotenotnested',     # quotes cannot be nested 
    754. 

  754. 	  'preareanotescaped',  # don't escape specials in PRE area
    755. 

  755. 	  
    756. 

  756. 	# target code beautify (ON/OFF)
    757. 

  757. 	  'indentprearea',      # add leading spaces to PRE area lines
    758. 

  758. 	  'breaktablecell',     # break lines after any table cell
    759. 

  759. 	  'breaktablelineopen', # break line after opening table line
    760. 

  760. 	  'keepquoteindent',    # don't remove the leading TABs on quotes
    761. 

  761. 	
    762. 

  762. 	# value settings
    763. 

  763. 	  'listmaxdepth',       # maximum depth for lists
    764. 

  764. 	]
    765. 

  765. 	
    766. 

  766. 	rules = {
    767. 

  767. 	  'txt' : {
    768. 

  768. 	    'indentprearea':1
    769. 

  769. 	    },
    770. 

  770. 	  'html': {
    771. 

  771. 	    'indentprearea':1,
    772. 

  772. 	    'linkable':1,
    773. 

  773. 	    'imgalignable':1,
    774. 

  774. 	    'listcountable':1,
    775. 

  775. 	    'tableable':1,
    776. 

  776. 	    'breaktablecell':1,
    777. 

  777. 	    'breaktablelineopen':1,
    778. 

  778. 	    'keepquoteindent':1
    779. 

  779. 	    },
    780. 

  780. 	  'sgml': {
    781. 

  781. 	    'linkable':1,
    782. 

  782. 	    'listcountable':1,
    783. 

  783. 	    'tableable':1,
    784. 

  784. 	    'tablecellsplit':1,
    785. 

  785. 	    'quotenotnested':1,
    786. 

  786. 	    'keepquoteindent':1
    787. 

  787. 	    },
    788. 

  788. 	  'mgp' : {
    789. 

  789. 	    },
    790. 

  790. 	  'tex' : {
    791. 

  791. 	    'listcountable':1,
    792. 

  792. 	    'tableable':1,
    793. 

  793. 	    'tablecellsplit':1,
    794. 

  794. 	    'preareanotescaped':1,
    795. 

  795. 	    'listmaxdepth':4
    796. 

  796. 	    },
    797. 

  797. 	  'moin': {
    798. 

  798. 	    'linkable':1,
    799. 

  799. 	    'tableable':1
    800. 

  800. 	    },
    801. 

  801. 	  'man' : {
    802. 

  802. 	    'indentprearea':1,
    803. 

  803. 	    'listnotnested':1
    804. 

  804. 	    },
    805. 

  805. 	  'pm6' : {
    806. 

  806. 	    }
    807. 

  807. 	}
    808. 

  808. 	
    809. 

  809. 	
    810. 

  810. 	# populate return dictionary
    811. 

  811. 	myrules = rules[doctype]
    812. 

  812. 	for key in allrules      : ret[key] = 0            # reset all
    813. 

  813. 	for key in myrules.keys(): ret[key] = myrules[key] # turn ON
    814. 

  814. 	return ret
    815. 

  815. 

  816. 

  817. def getRegexes():
    818. 

  818. 	regex = {
    819. 

  819. 	# extra at end: (\[(?P<label>\w+)\])? 
    820. 

  820. 	'title':
    821. 

  821. 		re.compile(r'^\s*(?P<tag>={1,5})(?P<txt>[^=].*[^=])\1$'), 
    822. 

  822. 	'areaPreOpen':
    823. 

  823. 		re.compile(r'^---$'), 
    824. 

  824. 	'areaPreClose':
    825. 

  825. 		re.compile(r'^---$'), 
    826. 

  826. 	'quote':
    827. 

  827. 		re.compile(r'^\t+'), 
    828. 

  828. 	'1linePreOld':
    829. 

  829. 		re.compile(r'^ {4}([^\s-])'), 
    830. 

  830. 	'1linePre':
    831. 

  831. 		re.compile(r'^--- '), 
    832. 

  832. 	'fontMono':
    833. 

  833. 		re.compile(r'`([^`]+)`'), 
    834. 

  834. 	'fontBold':
    835. 

  835. 		re.compile(r'\*\*([^\s*].*?)\*\*'), 
    836. 

  836. 	'fontItalic':
    837. 

  837. 		re.compile(r'(^|[^:])//([^ /].*?)//'), 
    838. 

  838. 	'fontUnderline':
    839. 

  839. 		re.compile(r'__([^_].*?)__'), # underline lead/trailing blank
    840. 

  840. 	'fontBolditalic':
    841. 

  841. 		re.compile(r'\*/([^/].*?)/\*'), 
    842. 

  842. 	'list':
    843. 

  843. 		re.compile(r'^( *)([+-]) ([^ ])'), 
    844. 

  844. 	'deflist':
    845. 

  845. 		re.compile(r'^( *)(=) ([^:]+):'), 
    846. 

  846. 	'bar':
    847. 

  847. 		re.compile(r'^\s*([_=-]{20,})\s*$'), 
    848. 

  848. 	'table':
    849. 

  849. 		re.compile(r'^ *\|\|? '), 
    850. 

  850. 	'blankline':
    851. 

  851. 		re.compile(r'^\s*$'), 
    852. 

  852. 	'comment':
    853. 

  853. 		re.compile(r'^%'),
    854. 

  854. 	'raw':
    855. 

  855. 		re.compile(r'``(.+?)``')
    856. 

  856. 	}
    857. 

  857. 	
    858. 

  858. 	# special char to place data on TAGs contents  (\a == bell)
    859. 

  859. 	regex['x'] = re.compile('\a')
    860. 

  860. 	
    861. 

  861. 	# %%date [ (formatting) ]
    862. 

  862. 	regex['date'] = re.compile(r'%%date\b(\((?P<fmt>.*?)\))?', re.I)
    863. 

  863. 	
    864. 

  864. 	
    865. 

  865. 	### complicated regexes begin here ;)
    866. 

  866. 	#
    867. 

  867. 	# textual descriptions on --help's style: [...] is optional, | is OR
    868. 

  868. 	
    869. 

  869. 	
    870. 

  870. 	### first, some auxiliar variables
    871. 

  871. 	#
    872. 

  872. 	
    873. 

  873. 	# [image.EXT]
    874. 

  874. 	patt_img = r'\[([\w_,.+%$#@!?+~/-]+\.(png|jpe?g|gif|eps|bmp))\]'
    875. 

  875. 	
    876. 

  876. 	# link things
    877. 

  877. 	urlskel = {
    878. 

  878. 	  'proto' : r'(https?|ftp|news|telnet|gopher|wais)://',
    879. 

  879. 	  'guess' : r'(www[23]?|ftp)\.',    # w/out proto, try to guess
    880. 

  880. 	  'login' : r'A-Za-z0-9_.-',        # for ftp://login@domain.com
    881. 

  881. 	  'pass'  : r'[^ @]*',              # for ftp://login:password@domain.com
    882. 

  882. 	  'chars' : r'A-Za-z0-9%._/~:,=$@-',# %20(space), :80(port)
    883. 

  883. 	  'anchor': r'A-Za-z0-9%._-',       # %nn(encoded)
    884. 

  884. 	  'form'  : r'A-Za-z0-9/%&=+.@*_-', # .@*_-(as is)
    885. 

  885. 	  'punct' : r'.,;:!?'
    886. 

  886. 	}
    887. 

  887. 	
    888. 

  888. 	# username [ :password ] @
    889. 

  889. 	patt_url_login = r'([%s]+(:%s)?@)?'%(urlskel['login'],urlskel['pass'])
    890. 

  890. 	
    891. 

  891. 	# [ http:// ] [ username:password@ ] domain.com [ / ] [ #anchor | ?form=data ]
    892. 

  892. 	retxt_url = r'\b(%s%s|%s)[%s]+\b/*(\?[%s]+)?(#[%s]+)?'%(
    893. 

  893. 	             urlskel['proto'],patt_url_login, urlskel['guess'],
    894. 

  894. 	             urlskel['chars'],urlskel['form'],urlskel['anchor'])
    895. 

  895. 	
    896. 

  896. 	# filename | [ filename ] #anchor
    897. 

  897. 	retxt_url_local = r'[%s]+|[%s]*(#[%s]+)'%(
    898. 

  898. 	             urlskel['chars'],urlskel['chars'],urlskel['anchor'])
    899. 

  899. 	
    900. 

  900. 	# user@domain [ ?form=data ]
    901. 

  901. 	patt_email = r'\b[%s]+@([A-Za-z0-9_-]+\.)+[A-Za-z]{2,4}\b(\?[%s]+)?'%(
    902. 

  902. 	             urlskel['login'],urlskel['form'])
    903. 

  903. 	
    904. 

  904. 	
    905. 

  905. 	# saving for future use
    906. 

  906. 	regex['_urlskel'] = urlskel
    907. 

  907. 	
    908. 

  908. 	### and now the real regexes
    909. 

  909. 	#
    910. 

  910. 	
    911. 

  911. 	regex['email'] = re.compile(patt_email,re.I)
    912. 

  912. 	
    913. 

  913. 	# email | url
    914. 

  914. 	regex['link'] = \
    915. 

  915. 		re.compile(r'%s|%s'%(retxt_url,patt_email), re.I)
    916. 

  916. 	
    917. 

  917. 	# \[ label | imagetag    url | email | filename \]
    918. 

  918. 	regex['linkmark'] = \
    919. 

  919. 		re.compile(r'\[(?P<label>%s|[^]]+) (?P<link>%s|%s|%s)\]'%(
    920. 

  920. 		   patt_img, retxt_url, patt_email, retxt_url_local),
    921. 

  921. 		   re.L+re.I)
    922. 

  922. 	
    923. 

  923. 	# image
    924. 

  924. 	regex['img'] = re.compile(patt_img, re.L+re.I)
    925. 

  925. 	
    926. 

  926. 	# all macros
    927. 

  927. 	regex['macro'] = regex['date']
    928. 

  928. 	
    929. 

  929. 	# special things
    930. 

  930. 	regex['special'] = re.compile(r'^%!\s*')
    931. 

  931. 	regex['setting'] = re.compile(r'(Encoding)\s*:\s*(.+)\s*$',re.I)
    932. 

  932. 	
    933. 

  933. 	return regex
    934. 

  934. ### END OF regex nightmares
    935. 

  935. 

  936. 

  937. class SubareaMaster:
    938. 

  938. 	def __init__(self) : self.x = []
    939. 

  939. 	def __call__(self) :
    940. 

  940. 		if not self.x: return ''
    941. 

  941. 		return self.x[-1]
    942. 

  942. 	def add(self, area):
    943. 

  943. 		if not self.x or (self.x and self.x[-1] != area):
    944. 

  944. 			self.x.append(area)
    945. 

  945. 		Debug('subarea ++ (%s): %s' % (area,self.x), 1)
    946. 

  946. 	def pop(self, area=None):
    947. 

  947. 		if area and self.x[-1] == area: self.x.pop()
    948. 

  948. 		Debug('subarea -- (%s): %s' % (area,self.x), 1)
    949. 

  949. 

  950. def doHeader(doctype, headdic):
    951. 

  951. 	if not HEADER_TEMPLATE.has_key(doctype):
    952. 

  952. 		Error("doheader: Unknow doctype '%s'"%doctype)
    953. 

  953. 	Debug('HEADER data: %s'%headdic, 1)
    954. 

  954. 	template = string.split(HEADER_TEMPLATE[doctype], '\n')
    955. 

  955. 	
    956. 

  956. 	# scan for empty dictionary keys
    957. 

  957. 	# if found, scan template lines for that key reference
    958. 

  958. 	# if found, remove the reference
    959. 

  959. 	# if there aren't any other key reference on the same line, remove it
    960. 

  960. 	for key in headdic.keys():
    961. 

  961. 		if not headdic[key]:
    962. 

  962. 			for line in template:
    963. 

  963. 				if string.count(line, key):
    964. 

  964. 					sline = string.replace(
    965. 

  965. 					          line, '%%(%s)s'%key, '')
    966. 

  966. 					if not string.count(sline, '%(HEADER'):
    967. 

  967. 						template.remove(line)
    968. 

  968. 	# populate template with data
    969. 

  969. 	template = string.join(template, '\n') % headdic
    970. 

  970. 	
    971. 

  971. 	### post processing
    972. 

  972. 	#
    973. 

  973. 	# TOC is a header tag
    974. 

  974. 	if FLAGS['toc'] and TAGS['TOC']:
    975. 

  975. 		toctag = re.sub('.*', TAGS['TOC'], '') #force_re
    976. 

  976. 		template = template + toctag
    977. 

  977. 	#
    978. 

  978. 	# let tex format today
    979. 

  979. 	if doctype == 'tex' and headdic['HEADER3'] == currdate:
    980. 

  980. 		template = re.sub(r'\\date\{.*?}', r'\date', template)
    981. 

  981. 	
    982. 

  982. 	return string.split(template, '\n')
    983. 

  983. 

  984. def doCommentLine(doctype,txt):
    985. 

  985. 	# the -- string ends a sgml comment :(
    986. 

  986. 	if doctype == 'sgml':
    987. 

  987. 		txt = string.replace(txt, '--', '\\-\\-')
    988. 

  988. 	
    989. 

  989. 	if TAGS['comment']:
    990. 

  990. 		return regex['x'].sub(txt, TAGS['comment'])
    991. 

  991. 	return ''
    992. 

  992. 

  993. def doFooter(doctype):
    994. 

  994. 	ret = []
    995. 

  995. 	typename = doctype
    996. 

  996. 	if doctype == 'tex': typename = 'LaTeX2e'
    997. 

  997. 	ppgd = '%s code generated by txt2tags %s (%s)'%(
    998. 

  998. 	        typename,my_version,my_url)
    999. 

  999. 	cmdline = 'cmdline: txt2tags %s'%string.join(CMDLINE[1:], ' ')
    1000. 

  1000. 	ret.append('\n'+doCommentLine(doctype,ppgd))
    1001. 

  1001. 	ret.append(doCommentLine(doctype,cmdline))
    1002. 

  1002. 	ret.append(TAGS['EOD'])
    1003. 

  1003. 	return ret
    1004. 

  1004. 

  1005. def doEscape(doctype,txt):
    1006. 

  1006. 	if doctype == 'html' or doctype == 'sgml':
    1007. 

  1007. 		txt = re.sub('&','&amp;',txt)
    1008. 

  1008. 		txt = re.sub('<','&lt;',txt)
    1009. 

  1009. 		txt = re.sub('>','&gt;',txt)
    1010. 

  1010. 		if doctype == 'sgml':
    1011. 

  1011. 			txt = re.sub('\xff','&yuml;',txt)  # "+y
    1012. 

  1012. 	elif doctype == 'pm6':
    1013. 

  1013. 		txt = re.sub('<','<\#60>',txt)
    1014. 

  1014. 	elif doctype == 'mgp':
    1015. 

  1015. 		txt = re.sub('^%',' %',txt)  # add leading blank to avoid parse
    1016. 

  1016. 		#txt = re.sub('^%([^%])','%prefix ""\n  %\n%cont, prefix "  "\n\\1',txt)
    1017. 

  1017. 	elif doctype == 'man':
    1018. 

  1018. 		txt = re.sub('^\.', ' .',txt) # command ID
    1019. 

  1019. 		txt = doEscapeEscapechar(txt)
    1020. 

  1020. 	elif doctype == 'tex':
    1021. 

  1021. 		txt = string.replace(txt, '\\', r'\verb!\!')
    1022. 

  1022. 		txt = string.replace(txt, '~', r'\verb!~!')
    1023. 

  1023. 		txt = string.replace(txt, '^', r'\verb!^!')
    1024. 

  1024. 		txt = re.sub('([#$&%{}])', r'\\\1', txt)
    1025. 

  1025. 		# TIP the _ is escaped at end
    1026. 

  1026. 	return txt
    1027. 

  1027. 

  1028. def doFinalEscape(doctype, txt):
    1029. 

  1029. 	if   doctype == 'pm6' : txt = string.replace(txt, r'\<',r'<\#92><')
    1030. 

  1030. 	elif doctype == 'man' : txt = string.replace(txt, '-', r'\-')
    1031. 

  1031. 	elif doctype == 'tex' : txt = string.replace(txt, '_', r'\_')
    1032. 

  1032. 	elif doctype == 'sgml': txt = string.replace(txt, '[', '&lsqb;')
    1033. 

  1033. 	return txt
    1034. 

  1034. 

  1035. def doEscapeEscapechar(txt):
    1036. 

  1036. 	return string.replace(txt, '\\', '\\\\')
    1037. 

  1037. 

  1038. def addLineBreaks(list):
    1039. 

  1039. 	"use LB to respect sys.platform"
    1040. 

  1040. 	ret = []
    1041. 

  1041. 	for line in list:
    1042. 

  1042. 		line = string.replace(line,'\n',LB)  # embedded \n's
    1043. 

  1043. 		ret.append(line+LB)                  # add final line break
    1044. 

  1044. 	return ret
    1045. 

  1045. 

  1046. def doPreLine(doctype,line):
    1047. 

  1047. 	"Parsing procedures for preformatted (verbatim) lines"
    1048. 

  1048. 	if not rules['preareanotescaped']: line = doEscape(doctype,line)
    1049. 

  1049. 	if rules['indentprearea']: line = '  '+line
    1050. 

  1050. 	if doctype == 'pm6': line = doFinalEscape(doctype, line)
    1051. 

  1051. 	return line
    1052. 

  1052. 

  1053. def doCloseTable(doctype):
    1054. 

  1054. 	global subarea, tableborder
    1055. 

  1055. 	ret = ''
    1056. 

  1056. 	if rules['tableable']:
    1057. 

  1057. 		if doctype == 'tex' and tableborder:
    1058. 

  1058. 			ret = TAGS['tableLineOpen']+TAGS['tableClose']+'\n'
    1059. 

  1059. 		else:
    1060. 

  1060. 			ret = TAGS['tableClose']+'\n'
    1061. 

  1061. 	else:
    1062. 

  1062. 		ret = TAGS['areaPreClose']
    1063. 

  1063. 	tableborder = 0
    1064. 

  1064. 	subarea.pop('table')
    1065. 

  1065. 	return ret
    1066. 

  1066. 

  1067. def doCloseQuote(howmany=None):
    1068. 

  1068. 	global quotedepth
    1069. 

  1069. 	ret = []
    1070. 

  1070. 	if not howmany: howmany = len(quotedepth)
    1071. 

  1071. 	for i in range(howmany):
    1072. 

  1072. 		quotedepth.pop()
    1073. 

  1073. 		#TODO align open/close tag -> FREE_ALING_TAG = 1 (man not)
    1074. 

  1074. 		ret.append(TAGS['areaQuoteClose'])
    1075. 

  1075. 	
    1076. 

  1076. 	if not quotedepth: subarea.pop('quote')
    1077. 

  1077. 	return string.join(ret,'\n')
    1078. 

  1078. 

  1079. def doCloseList(howmany=None):
    1080. 

  1080. 	global listindent, listids
    1081. 

  1081. 	ret = []
    1082. 

  1082. 	if not howmany: howmany = len(listindent)
    1083. 

  1083. 	for i in range(howmany):
    1084. 

  1084. 		if   listids[-1] == '-': tag = TAGS['listClose']
    1085. 

  1085. 		elif listids[-1] == '+': tag = TAGS['numlistClose']
    1086. 

  1086. 		elif listids[-1] == '=': tag = TAGS['deflistClose']
    1087. 

  1087. 		if not tag: tag = TAGS['listClose'] # default
    1088. 

  1088. 		if tag:
    1089. 

  1089. 			# unnested lists are only closed at mother-list
    1090. 

  1090. 			if rules['listnotnested']:
    1091. 

  1091. 				if len(listindent) == 1:
    1092. 

  1092. 					ret.append(tag)
    1093. 

  1093. 			else:
    1094. 

  1094. 				ret.append(listindent[-1]+tag)
    1095. 

  1095. 		del listindent[-1]
    1096. 

  1096. 		del listids[-1]
    1097. 

  1097. 	
    1098. 

  1098. 	if not listindent: subarea.pop('list')
    1099. 

  1099. 	return string.join(ret,'\n')
    1100. 

  1100. 

  1101. 

  1102. def beautify_me(name, doctype, line):
    1103. 

  1103. 	"where name is: bold, italic, underline or bolditalic"
    1104. 

  1104. 	name  = 'font%s' % string.capitalize(name)
    1105. 

  1105. 	open  = TAGS['%sOpen'%name]
    1106. 

  1106. 	close = TAGS['%sClose'%name]
    1107. 

  1107. 	txt = r'%s\1%s'%(open, close)
    1108. 

  1108. 	if name == 'fontItalic':
    1109. 

  1109. 		txt = r'\1%s\2%s'%(open, close)
    1110. 

  1110. 	line = regex[name].sub(txt,line)
    1111. 

  1111. 	return line
    1112. 

  1112. 

  1113. 

  1114. def get_tagged_link(doctype, label, url):
    1115. 

  1115. 	ret = ''
    1116. 

  1116. 	
    1117. 

  1117. 	# set link type
    1118. 

  1118. 	if regex['email'].match(url):
    1119. 

  1119. 		linktype = 'email'
    1120. 

  1120. 	else:
    1121. 

  1121. 		linktype = 'url';
    1122. 

  1122. 	
    1123. 

  1123. 	# adding protocol to guessed link
    1124. 

  1124. 	guessurl = ''
    1125. 

  1125. 	if linktype == 'url' and \
    1126. 

  1126. 	   re.match(regex['_urlskel']['guess'], url):
    1127. 

  1127. 		if url[0] == 'w': guessurl = 'http://' +url
    1128. 

  1128. 		else            : guessurl =  'ftp://' +url
    1129. 

  1129. 		
    1130. 

  1130. 		# not link aware targets -> protocol is useless 
    1131. 

  1131. 		if not rules['linkable']: guessurl = ''
    1132. 

  1132. 	
    1133. 

  1133. 	# escape specials from TEXT parts
    1134. 

  1134. 	label = doEscape(doctype,label)
    1135. 

  1135. 	if not rules['linkable']:
    1136. 

  1136. 		if doctype == 'tex':
    1137. 

  1137. 			url = re.sub('^#', '\#', url) # ugly, but compile
    1138. 

  1138. 		else:
    1139. 

  1139. 			url = doEscape(doctype,url)
    1140. 

  1140. 	
    1141. 

  1141. 	# simple link (not guessed)
    1142. 

  1142. 	if not label and not guessurl:
    1143. 

  1143. 		if FLAGS['maskemail'] and linktype == 'email':
    1144. 

  1144. 			# do the email mask feature (no TAGs, just text)
    1145. 

  1145. 			url = string.replace(url,'@',' (a) ')
    1146. 

  1146. 			url = string.replace(url,'.',' ')
    1147. 

  1147. 			url = "<%s>" % url
    1148. 

  1148. 			if rules['linkable']: url = doEscape(url)
    1149. 

  1149. 			ret = url
    1150. 

  1150. 		else:
    1151. 

  1151. 			# just add link data to tag
    1152. 

  1152. 			tag = re.sub('.*', TAGS[linktype], '')  #force_re
    1153. 

  1153. 			ret = regex['x'].sub(url,tag)
    1154. 

  1154. 	
    1155. 

  1155. 	# named link or guessed simple link
    1156. 

  1156. 	else:
    1157. 

  1157. 		# adjusts for guessed link
    1158. 

  1158. 		if not label: label = url       # no   protocol
    1159. 

  1159. 		if guessurl : url   = guessurl  # with protocol
    1160. 

  1160. 		
    1161. 

  1161. 		# handle \ on link label
    1162. 

  1162. 		label = doEscapeEscapechar(label)
    1163. 

  1163. 		
    1164. 

  1164. 		# putting data on the right appearance order
    1165. 

  1165. 		if rules['linkable']:
    1166. 

  1166. 			urlorder = [url, label]   # link before label
    1167. 

  1167. 		else:
    1168. 

  1168. 			urlorder = [label, url]   # label before link
    1169. 

  1169. 		
    1170. 

  1170. 		# get tag
    1171. 

  1171. 		ret = re.sub('.*', TAGS["%sMark"%linktype], '')  #force_re
    1172. 

  1172. 		
    1173. 

  1173. 		# add link data to tag (replace \a's)
    1174. 

  1174. 		for data in urlorder:
    1175. 

  1175. 			ret = regex['x'].sub(data,ret,1)
    1176. 

  1176. 	return ret
    1177. 

  1177. 

  1178. 

  1179. def get_image_align(line):
    1180. 

  1180. 	align = ''
    1181. 

  1181. 	line = string.strip(line)
    1182. 

  1182. 	m = regex['img'].search(line)
    1183. 

  1183. 	ini = m.start() ; head = 0
    1184. 

  1184. 	end = m.end()   ; tail = len(line)
    1185. 

  1185. 	
    1186. 

  1186. 	align = 'center'  # default align              # ^text +img +text$
    1187. 

  1187. 	if ini == head and end == tail: align = 'para' # ^img$
    1188. 

  1188. 	elif ini == head: align = 'left'               # ^img + text$
    1189. 

  1189. 	elif end == tail: align = 'right'              # ^text + img$
    1190. 

  1190. 	
    1191. 

  1191. 	return align
    1192. 

  1192. 

  1193. 

  1194. def get_table_prop(line):
    1195. 

  1195. 	# default table proprierties
    1196. 

  1196. 	ret = {'border': 0, 'header':0, 'cells':[]}
    1197. 

  1197. 	line = string.strip(line)
    1198. 

  1198. 	# detect header (title) mark
    1199. 

  1199. 	if line[1] == '|':
    1200. 

  1200. 		ret['header'] = 1
    1201. 

  1201. 	# detect (and delete) border mark
    1202. 

  1202. 	if line[-1] == '|':
    1203. 

  1203. 		ret['border'] = 1
    1204. 

  1204. 		line = line[:-1]
    1205. 

  1205. 	# delete table mark
    1206. 

  1206. 	line = regex['table'].sub('', line)
    1207. 

  1207. 	# split cells
    1208. 

  1208. 	ret['cells'] = string.split(line, ' | ')
    1209. 

  1209. 	
    1210. 

  1210. 	Debug('Table Prop: %s' % ret, 1)
    1211. 

  1211. 	return ret
    1212. 

  1212. 

  1213. 

  1214. #TODO if ' |   ' table cell is center align
    1215. 

  1215. def tag_table_cells(table, doctype):
    1216. 

  1216. 	ret = ''
    1217. 

  1217. 	# plain cell
    1218. 

  1218. 	open, close = TAGS['tableCellOpen'], TAGS['tableCellClose']
    1219. 

  1219. 	# title cell
    1220. 

  1220. 	if table['header']:
    1221. 

  1221. 		open = TAGS['tableTitleCellOpen']
    1222. 

  1222. 		close = TAGS['tableTitleCellClose']
    1223. 

  1223. 	# should we break the line?
    1224. 

  1224. 	if rules['breaktablecell']: close = close+'\n'
    1225. 

  1225. 	# here we go
    1226. 

  1226. 	while table['cells']:
    1227. 

  1227. 		cel = table['cells'].pop(0)
    1228. 

  1228. 		if not cel and doctype == 'html':
    1229. 

  1229. 			cel = '&nbsp;'
    1230. 

  1230. 		# last cell gotchas
    1231. 

  1231. 		if not table['cells']:
    1232. 

  1232. 			# don't need cell separator
    1233. 

  1233. 			if rules['tablecellsplit']: close = ''
    1234. 

  1234. 			# close beautifier for last title cell
    1235. 

  1235. 			if doctype == 'tex' and table['header']: close = '}'
    1236. 

  1236. 		newcell = open + string.strip(cel) + close
    1237. 

  1237. 		newcell = re.sub('.*', newcell, '') #force_re
    1238. 

  1238. 		ret = ret + newcell
    1239. 

  1239. 	return ret
    1240. 

  1240. 

  1241. # reference: http://www.iana.org/assignments/character-sets
    1242. 

  1242. # http://www.drclue.net/F1.cgi/HTML/META/META.html
    1243. 

  1243. def get_encoding_string(enc, doctype):
    1244. 

  1244. 	if not enc: return ''
    1245. 

  1245. 	# target specific translation table
    1246. 

  1246. 	translate = {
    1247. 

  1247. 	'tex': {
    1248. 

  1248. 	  # missing: ansinew , applemac , cp437 , cp437de , cp865
    1249. 

  1249. 	  'us-ascii'    : 'ascii',
    1250. 

  1250. 	  'windows-1250': 'cp1250',
    1251. 

  1251. 	  'windows-1252': 'cp1252',
    1252. 

  1252. 	  'ibm850'      : 'cp850',
    1253. 

  1253. 	  'ibm852'      : 'cp852',
    1254. 

  1254. 	  'iso-8859-1'  : 'latin1',
    1255. 

  1255. 	  'iso-8859-2'  : 'latin2',
    1256. 

  1256. 	  'iso-8859-3'  : 'latin3',
    1257. 

  1257. 	  'iso-8859-4'  : 'latin4',
    1258. 

  1258. 	  'iso-8859-5'  : 'latin5',
    1259. 

  1259. 	  'iso-8859-9'  : 'latin9',
    1260. 

  1260. 	  'koi8-r'      : 'koi8-r'
    1261. 

  1261. 	  }
    1262. 

  1262. 	}
    1263. 

  1263. 	# normalization
    1264. 

  1264. 	enc = re.sub('(?i)(us[-_]?)?ascii|us|ibm367','us-ascii'  , enc)
    1265. 

  1265. 	enc = re.sub('(?i)(ibm|cp)?85([02])'        ,'ibm85\\2'  , enc)
    1266. 

  1266. 	enc = re.sub('(?i)(iso[_-]?)?8859[_-]?'     ,'iso-8859-' , enc)
    1267. 

  1267. 	enc = re.sub('iso-8859-($|[^1-9]).*'        ,'iso-8859-1', enc)
    1268. 

  1268. 	# apply translation table
    1269. 

  1269. 	try: enc = translate[doctype][string.upper(enc)]
    1270. 

  1270. 	except: pass
    1271. 

  1271. 	return enc
    1272. 

  1272. 

  1273. 

  1274. ################################################################################
    1275. 

  1275. ###MerryChristmas,IdontwanttofighttonightwithyouImissyourbodyandIneedyourlove###
    1276. 

  1276. ################################################################################
    1277. 

  1277. 

  1278. 

  1279. def convert(inlines, doctype):
    1280. 

  1280. 	# global vars for doClose*()
    1281. 

  1281. 	global TAGS, regex, rules, quotedepth, listindent, listids
    1282. 

  1282. 	global subarea, tableborder
    1283. 

  1283. 	
    1284. 

  1284. 	TAGS = getTags(doctype)
    1285. 

  1285. 	rules = getRules(doctype)
    1286. 

  1286. 	regex = getRegexes()
    1287. 

  1287. 	
    1288. 

  1288. 	# the defaults
    1289. 

  1289. 	linkmask  = '@@_link_@@'
    1290. 

  1290. 	monomask  = '@@_mono_@@'
    1291. 

  1291. 	macromask = '@@_macro_@@' 
    1292. 

  1292. 	rawmask   = '@@_raw_@@'
    1293. 

  1293. 	
    1294. 

  1294. 	AREA = NewArea('head',0)   # then conf, then body
    1295. 

  1295. 	subarea = SubareaMaster()
    1296. 

  1296. 	HEADERS = { 'HEADER1': '-NO TITLE-', 'HEADER2':'', 'HEADER3':'',
    1297. 

  1297. 	            'ENCODING': '' }
    1298. 

  1298. 	ret = []
    1299. 

  1299. 	toclist = []
    1300. 

  1300. 	header = []
    1301. 

  1301. 	f_tt = 0
    1302. 

  1302. 	listindent = []
    1303. 

  1303. 	listids = []
    1304. 

  1304. 	listcount = []
    1305. 

  1305. 	titlecount = ['',0,0,0,0,0]
    1306. 

  1306. 	f_lastblank = 0
    1307. 

  1307. 	holdspace = ''
    1308. 

  1308. 	listholdspace = ''
    1309. 

  1309. 	quotedepth = []
    1310. 

  1310. 	tableborder = 0
    1311. 

  1311. 	tablealign = []
    1312. 

  1312. 	
    1313. 

  1313. 	if outfile != pipefileid:
    1314. 

  1314. 		if not FLAGS['gui']:
    1315. 

  1315. 			print "--- %s..."%doctype
    1316. 

  1316. 	
    1317. 

  1317. 	# let's mark it up!
    1318. 

  1318. 	linenr = 0
    1319. 

  1319. 	for lineref in range(len(inlines)):
    1320. 

  1320. 		skip_continue = 0
    1321. 

  1321. 		linkbank = []
    1322. 

  1322. 		monobank = []
    1323. 

  1323. 		macrobank = []
    1324. 

  1324. 		rawbank = []
    1325. 

  1325. 		linenr = lineref +1
    1326. 

  1326. 		untouchedline = inlines[lineref]
    1327. 

  1327. 		line = string.rstrip(untouchedline)
    1328. 

  1328. 		
    1329. 

  1329. 		Debug('LINE %04d: %s' % (linenr,repr(line)), 1)  # for heavy debug
    1330. 

  1330. 		
    1331. 

  1331. 		# detect if head section is over
    1332. 

  1332. 		#TIP 'not line' depends on previous line.rstrip()
    1333. 

  1333. 		if (linenr == 4 and AREA == 'head') or \
    1334. 

  1334. 		   (linenr == 1 and not line):
    1335. 

  1335. 			AREA = NewArea('conf',linenr)
    1336. 

  1336. 		
    1337. 

  1337. 		# we need (not really) to mark each paragraph
    1338. 

  1338. 		#TODO check if this is really needed
    1339. 

  1339. 		if doctype == 'pm6' and f_lastblank:
    1340. 

  1340. 			if f_tt or AREA == 'head' or listindent:
    1341. 

  1341. 				holdspace = ''
    1342. 

  1342. 			else:
    1343. 

  1343. 				holdspace = TAGS['paragraph']+'\n'
    1344. 

  1344. 		
    1345. 

  1345. 		# any NOT table line, closes an open table 
    1346. 

  1346. 		if subarea() == 'table' and not regex['table'].search(line):
    1347. 

  1347. 			ret.append(doCloseTable(doctype))
    1348. 

  1348. 		
    1349. 

  1349. 		
    1350. 

  1350. 		#---------------------[ PRE formatted ]----------------------
    1351. 

  1351. 		
    1352. 

  1352. 		#TIP we'll never support beautifiers inside pre-formatted
    1353. 

  1353. 		
    1354. 

  1354. 		# we're already on a PRE area
    1355. 

  1355. 		if f_tt:
    1356. 

  1356. 			# closing PRE
    1357. 

  1357. 			if regex['areaPreClose'].search(line):
    1358. 

  1358. 				if doctype != 'pm6':
    1359. 

  1359. 					ret.append(TAGS['areaPreClose'])
    1360. 

  1360. 				f_tt = 0
    1361. 

  1361. 				continue
    1362. 

  1362. 			
    1363. 

  1363. 			# normal PRE-inside line
    1364. 

  1364. 			line = doPreLine(doctype, line)
    1365. 

  1365. 			ret.append(line)
    1366. 

  1366. 			continue
    1367. 

  1367. 		
    1368. 

  1368. 		# detecting PRE area init
    1369. 

  1369. 		if regex['areaPreOpen'].search(line):
    1370. 

  1370. 			ret.append(TAGS['areaPreOpen'])
    1371. 

  1371. 			f_lastblank = 0
    1372. 

  1372. 			f_tt = 1
    1373. 

  1373. 			continue
    1374. 

  1374. 		
    1375. 

  1375. 		# one line PRE-formatted text
    1376. 

  1376. 		if regex['1linePre'].search(line):
    1377. 

  1377. 			f_lastblank = 0
    1378. 

  1378. 			line = regex['1linePre'].sub('',line)
    1379. 

  1379. 			line = doPreLine(doctype, line)
    1380. 

  1380. 			t1, t2 = TAGS['areaPreOpen'],TAGS['areaPreClose']
    1381. 

  1381. 			ret.append('%s\n%s\n%s'%(t1,line,t2))
    1382. 

  1382. 			continue
    1383. 

  1383. 		
    1384. 

  1384. 		#---------------------[ blank lines ]-----------------------
    1385. 

  1385. 		
    1386. 

  1386. 		#TODO "holdspace" to save <p> to not show in closelist
    1387. 

  1387. 		if regex['blankline'].search(line):
    1388. 

  1388. 			
    1389. 

  1389. 			# closing all open quotes
    1390. 

  1390. 			if quotedepth:
    1391. 

  1391. 				ret.append(doCloseQuote())
    1392. 

  1392. 			
    1393. 

  1393. 			# closing all open lists
    1394. 

  1394. 			if f_lastblank:      # 2nd consecutive blank line
    1395. 

  1395. 				if listindent:   # closes list (if any)
    1396. 

  1396. 					ret.append(doCloseList())
    1397. 

  1397. 					holdspace = ''
    1398. 

  1398. 				continue         # consecutive blanks are trash
    1399. 

  1399. 			
    1400. 

  1400. 			# normal blank line
    1401. 

  1401. 			if doctype != 'pm6' and AREA == 'body':
    1402. 

  1402. 				# paragraph (if any) is wanted inside lists also
    1403. 

  1403. 				if listindent:
    1404. 

  1404. 					para = TAGS['paragraph'] + '\n'
    1405. 

  1405. 					holdspace = holdspace + para
    1406. 

  1406. 				elif doctype == 'html':
    1407. 

  1407. 					ret.append(TAGS['paragraph'])
    1408. 

  1408. 				# sgml: quote close tag must not be \n\n</quote>
    1409. 

  1409. 				elif doctype == 'sgml' and quotedepth:
    1410. 

  1410. 					skip_continue = 1
    1411. 

  1411. 				# otherwise we just print a blank line
    1412. 

  1412. 				else:
    1413. 

  1413. 					ret.append('')
    1414. 

  1414. 			
    1415. 

  1415. 			f_lastblank = 1
    1416. 

  1416. 			if not skip_continue: continue
    1417. 

  1417. 		else:
    1418. 

  1418. 			f_lastblank = 0      # reset blank status
    1419. 

  1419. 		
    1420. 

  1420. 		
    1421. 

  1421. 		#---------------------[ special ]------------------------
    1422. 

  1422. 		# just encoding for now
    1423. 

  1423. 		
    1424. 

  1424. 		if regex['special'].search(line):
    1425. 

  1425. 			special = line[2:]
    1426. 

  1426. 			
    1427. 

  1427. 			# try Settings
    1428. 

  1428. 			m = regex['setting'].match(special)
    1429. 

  1429. 			if m:
    1430. 

  1430. 				name = string.upper(m.group(1))
    1431. 

  1431. 				val  = m.group(2)
    1432. 

  1432. 				if AREA == 'conf':
    1433. 

  1433. 					if name == 'ENCODING':
    1434. 

  1434. 						val = get_encoding_string(val,doctype)
    1435. 

  1435. 					HEADERS[name] = val
    1436. 

  1436. 					Debug("Found Setting '%s', value '%s'"%(
    1437. 

  1437. 					       name,val),1,linenr)
    1438. 

  1438. 				else:
    1439. 

  1439. 					Debug('Ignoring Setting outside CONF area:'
    1440. 

  1440. 					      ' %s'%name,1,linenr)
    1441. 

  1441. 			else:
    1442. 

  1442. 				Debug('Bogus Special Line',1,linenr)
    1443. 

  1443. 		
    1444. 

  1444. 		#---------------------[ comments ]-----------------------
    1445. 

  1445. 		
    1446. 

  1446. 		# just skip them (if not macro or setting)
    1447. 

  1447. 		if regex['comment'].search(line) and not regex['date'].match(line):
    1448. 

  1448. 			f_lastblank = 1
    1449. 

  1449. 			continue
    1450. 

  1450. 		
    1451. 

  1451. 		#---------------------[ BODY detect ]-----------------------
    1452. 

  1452. 		
    1453. 

  1453. 		### if got here, its a header or a valid line
    1454. 

  1454. 		if AREA == 'conf':
    1455. 

  1455. 			# oops, not header, so we're now on document BODY
    1456. 

  1456. 			AREA = NewArea('body', linenr)
    1457. 

  1457. 			# do headers!
    1458. 

  1458. 			if not FLAGS['noheaders']:
    1459. 

  1459. 				header = doHeader(doctype,HEADERS)
    1460. 

  1460. 			# so, let's print the opening paragraph
    1461. 

  1461. 			if doctype != 'pm6':
    1462. 

  1462. 				ret.append(TAGS['paragraph'])
    1463. 

  1463. 		
    1464. 

  1464. 		
    1465. 

  1465. 		#---------------------[ Title ]-----------------------
    1466. 

  1466. 		
    1467. 

  1467. 		# man: - should not be escaped, \ turns to \\\\
    1468. 

  1468. 		
    1469. 

  1469. 		#TODO set next blank and set f_lastblank or f_lasttitle
    1470. 

  1470. 		if regex['title'].search(line) and not listindent and AREA == 'body':
    1471. 

  1471. 			m = regex['title'].search(line)
    1472. 

  1472. 			tag = m.group('tag')
    1473. 

  1473. 			level = len(tag)
    1474. 

  1474. 			tag = TAGS['title%s'%level]
    1475. 

  1475. 			
    1476. 

  1476. 			txt = string.strip(m.group('txt'))
    1477. 

  1477. 			
    1478. 

  1478. 			if FLAGS['enumtitle']:                ### numbered title
    1479. 

  1479. 				id = '' ; n = level               #
    1480. 

  1480. 				titlecount[n] = titlecount[n] +1  # add count
    1481. 

  1481. 				if n < len(titlecount)-1:         # reset sublevels count
    1482. 

  1482. 					for i in range(n+1, len(titlecount)): titlecount[i] = 0
    1483. 

  1483. 				for i in range(n):                # compose id from hierarchy
    1484. 

  1484. 					id = "%s%d."%(id,titlecount[i+1])
    1485. 

  1485. 				idtxt = "%s %s"%(id, txt)         # add id to title
    1486. 

  1486. 			else:
    1487. 

  1487. 				idtxt = txt
    1488. 

  1488. 			
    1489. 

  1489. 			anchorid = 'toc%d'%(len(toclist)+1)
    1490. 

  1490. 			if TAGS['anchor'] and FLAGS['toc'] and level <= 3:
    1491. 

  1491. 				ret.append(regex['x'].sub(anchorid,TAGS['anchor']))
    1492. 

  1492. 			
    1493. 

  1493. 			# place title tag overriding line
    1494. 

  1494. 			line = regex['title'].sub(tag,line)
    1495. 

  1495. 			
    1496. 

  1496. 			### escape title text (unescaped text is used for TOC)
    1497. 

  1497. 			#
    1498. 

  1498. 			esctxt = doEscape(doctype,idtxt)
    1499. 

  1499. 			# sgml: [ is special on title (and lists) - here bcos 'continue'
    1500. 

  1500. 			if doctype == 'sgml': esctxt = re.sub(r'\[', r'&lsqb;', esctxt)
    1501. 

  1501. 			esctxt = doEscapeEscapechar(esctxt)   # for re.sub()
    1502. 

  1502. 			# man: \ on title becomes \\\\
    1503. 

  1503. 			if doctype == 'man': esctxt = doEscapeEscapechar(esctxt)
    1504. 

  1504. 			# finish title line
    1505. 

  1505. 			ret.append(regex['x'].sub(esctxt,line))
    1506. 

  1506. 			
    1507. 

  1507. 			# let's do some TOC!
    1508. 

  1508. 			if TAGS['anchor']:
    1509. 

  1509. 				# tocitemid = '#toc%d'%(len(toclist)+1)
    1510. 

  1510. 				# TOC more readable with master topics not linked at number
    1511. 

  1511. 				# stoled idea from windows .CHM files (help system)
    1512. 

  1512. 				if FLAGS['enumtitle'] and level == 1:
    1513. 

  1513. 					tocitem = '%s+ [``%s`` #%s]'%(' '*level,txt,anchorid)
    1514. 

  1514. 				else:
    1515. 

  1515. 					tocitem = '%s- [``%s`` #%s]'%(' '*level,idtxt,anchorid)
    1516. 

  1516. 			else:
    1517. 

  1517. 				tocitem = '%s- %s'%(' '*level,idtxt)
    1518. 

  1518. 				if doctype in ['txt', 'man']:
    1519. 

  1519. 					tocitem = '%s%s' %('  '*level,idtxt)
    1520. 

  1520. 			if level <= 3: toclist.append(tocitem) # max toc level: 3
    1521. 

  1521. 			
    1522. 

  1522. 			# add "underline" to text titles
    1523. 

  1523. 			if doctype == 'txt':
    1524. 

  1524. 				ret.append(regex['x'].sub('='*len(idtxt),tag))
    1525. 

  1525. 			
    1526. 

  1526. 			continue
    1527. 

  1527. 		
    1528. 

  1528. 		#TODO!	labeltxt = ''
    1529. 

  1529. 		#		label = m.group('label')
    1530. 

  1530. 		#		if label: labeltxt = '<label id="%s">' %label
    1531. 

  1531. 		
    1532. 

  1532. 		
    1533. 

  1533. 		#---------------------[ apply masks ]-----------------------
    1534. 

  1534. 		
    1535. 

  1535. 		### protect important structures from escaping and formatting
    1536. 

  1536. 		while regex['raw'].search(line):
    1537. 

  1537. 			txt = regex['raw'].search(line).group(1)
    1538. 

  1538. 			rawbank.append(doEscape(doctype,txt))
    1539. 

  1539. 			line = regex['raw'].sub(rawmask,line,1)
    1540. 

  1540. 		
    1541. 

  1541. 		# protect pre-formatted font text 
    1542. 

  1542. 		while regex['fontMono'].search(line):
    1543. 

  1543. 			txt = regex['fontMono'].search(line).group(1)
    1544. 

  1544. 			txt = doEscape(doctype,txt)
    1545. 

  1545. 			txt = escapePythonSpecials(txt)
    1546. 

  1546. 			monobank.append(txt)
    1547. 

  1547. 			line = regex['fontMono'].sub(monomask,line,1)
    1548. 

  1548. 		
    1549. 

  1549. 		# protect macros
    1550. 

  1550. 		while regex['macro'].search(line):
    1551. 

  1551. 			txt = regex['macro'].search(line).group()
    1552. 

  1552. 			macrobank.append(txt)
    1553. 

  1553. 			line = regex['macro'].sub(macromask,line,1)
    1554. 

  1554. 		
    1555. 

  1555. 		# protect URLs and emails
    1556. 

  1556. 		while regex['linkmark'].search(line) or regex['link'].search(line):
    1557. 

  1557. 			
    1558. 

  1558. 			# try to match pl…
    1559.

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