PageRenderTime 54ms CodeModel.GetById 13ms RepoModel.GetById 0ms app.codeStats 1ms

/old/txt2tags-1.6.py

http://txt2tags.googlecode.com/
Python | 2542 lines | 2502 code | 10 blank | 30 comment | 9 complexity | 04ccb57d7ce5ada49fd8c0233f13047c 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, 2003 Aurelio 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 better, even readable now, but needs more improvements
    21. 

  21. # please wait for the upcoming 2.0 series for a cleaner one
    22. 

  22. 

  23. #XXX Python coding warning
    24. 

  24. # Avoid common mistakes:
    25. 

  25. # - do NOT use newlist=list instead newlist=list[:]
    26. 

  26. # - do NOT use newdic=dic   instead newdic=dic.copy()
    27. 

  27. # - do NOT use dic[key]     instead dic.get(key)
    28. 

  28. 

  29. import re, string, os, sys, getopt, traceback
    30. 

  30. from time import strftime,time,localtime
    31. 

  31. 

  32. my_url = 'http://txt2tags.sf.net'
    33. 

  33. my_email = 'verde@aurelio.net'
    34. 

  34. my_version = '1.6'                               #-betaMMDD
    35. 

  35. 

  36. DEBUG = 0   # do not edit here, please use --debug
    37. 

  37. targets = ['txt', 'sgml', 'html', 'pm6', 'mgp', 'moin', 'man', 'tex']
    38. 

  38. FLAGS   = {'noheaders':0,'enumtitle':0 ,'maskemail':0 ,'stdout'  :0,
    39. 

  39.            'toconly'  :0,'toc'      :0 ,'gui'      :0 ,'included':0}
    40. 

  40. OPTIONS = {'toclevel' :3,'style'    :'','type'     :'','outfile' :'',
    41. 

  41.            'split':0, 'lang':''}
    42. 

  42. CONFIG_KEYWORDS = ['encoding', 'style', 'cmdline','preproc','postproc']
    43. 

  43. CONF = {}
    44. 

  44. regex = {}
    45. 

  45. TAGS = {}
    46. 

  46. rules = {}
    47. 

  47. 

  48. currdate = strftime('%Y%m%d',localtime(time()))    # ISO current date
    49. 

  49. lang = 'english'
    50. 

  50. doctype = outfile = ''
    51. 

  51. STDIN = STDOUT = '-'
    52. 

  52. 

  53. ESCCHAR = '\x00'
    54. 

  54. LINEBREAK = {'default':'\n', 'win':'\r\n', 'mac':'\r'}
    55. 

  55. 

  56. #my_version = my_version + '-dev' + currdate[4:]  # devel!
    57. 

  57. 

  58. # global vars for doClose*()
    59. 

  59. quotedepth = []
    60. 

  60. listindent = []
    61. 

  61. listids = []
    62. 

  62. subarea = None
    63. 

  63. tableborder = 0
    64. 

  64. # set the Line Break across platforms
    65. 

  65. LB = LINEBREAK.get(sys.platform[:3]) or LINEBREAK['default']
    66. 

  66. 

  67. versionstr = "txt2tags version %s <%s>"%(my_version,my_url)
    68. 

  68. usage = """
    69. 

  69. %s
    70. 

  70. 

  71. Usage: txt2tags -t <type> [OPTIONS] file.t2t
    72. 

  72. 

  73.   -t, --type         set target document type. actually supported:
    74. 

  74.                      %s
    75. 

  75. 

  76.   -o, --outfile=FILE set FILE as the output filename ('-' for STDOUT)   	  
    77. 

  77.       --stdout       same as '-o -' or '--outfile -' (deprecated option)
    78. 

  78.   -H, --noheaders    suppress header, title and footer information
    79. 

  79.   -n, --enumtitle    enumerate all title lines as 1, 1.1, 1.1.1, etc
    80. 

  80.       --maskemail    hide email from spam robots. x@y.z turns <x (a) y z>
    81. 

  81. 

  82.       --toc          add TOC (Table of Contents) to target document
    83. 

  83.       --toconly      print document TOC and exit
    84. 

  84.       --toclevel=N   set maximum TOC level (deepness) to N
    85. 

  85. 

  86.       --gui          invoke Graphical Tk Interface
    87. 

  87.       --style=FILE   use FILE as the document style (like Html CSS)
    88. 

  88. 

  89.   -h, --help         print this help information and exit
    90. 

  90.   -V, --version      print program version and exit
    91. 

  91. 

  92. Extra options for HTML target (needs sgml-tools):
    93. 

  93.       --split        split documents. values: 0, 1, 2 (default 0)
    94. 

  94.       --lang         document language (default english)
    95. 

  95. 

  96. By default, converted output is saved to 'file.<type>'.
    97. 

  97. Use --outfile to force an output filename.
    98. 

  98. If input file is '-', reads from STDIN.
    99. 

  99. If outfile is '-', dumps output to STDOUT.\
    100. 

  100. """%(versionstr, re.sub(r"[]'[]",'',repr(targets)))
    101. 

    102. 

  102. 

  103. # here is all the target's templates
    104. 

  104. # you may edit them to fit your needs
    105. 

  105. #  - the %(HEADERn)s strings represent the Header lines
    106. 

  106. #  - use %% to represent a literal %
    107. 

  107. #
    108. 

  108. HEADER_TEMPLATE = {
    109. 

  109.   'txt': """\
    110. 

  110. %(HEADER1)s
    111. 

  111. %(HEADER2)s
    112. 

  112. %(HEADER3)s
    113. 

  113. """,
    114. 

    115. 

  115.   'sgml': """\
    116. 

  116. <!doctype linuxdoc system>
    117. 

  117. <article>
    118. 

  118. <title>%(HEADER1)s
    119. 

  119. <author>%(HEADER2)s
    120. 

  120. <date>%(HEADER3)s
    121. 

  121. """,
    122. 

    123. 

  123.   'html': """\
    124. 

  124. <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
    125. 

  125. <HTML>
    126. 

  126. <HEAD>
    127. 

  127. <META NAME="generator" CONTENT="http://txt2tags.sf.net">
    128. 

  128. <META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=%(ENCODING)s">
    129. 

  129. <LINK REL="stylesheet" TYPE="text/css" HREF="%(STYLE)s">
    130. 

  130. <TITLE>%(HEADER1)s</TITLE>
    131. 

  131. </HEAD><BODY BGCOLOR="white" TEXT="black">
    132. 

  132. <P ALIGN="center"><CENTER><H1>%(HEADER1)s</H1>
    133. 

  133. <FONT SIZE=4>
    134. 

  134. <I>%(HEADER2)s</I><BR>
    135. 

  135. %(HEADER3)s
    136. 

  136. </FONT></CENTER>
    137. 

  137. """,
    138. 

    139. 

  139. 

  140. # TODO man section 1 is hardcoded...
    141. 

  141.   'man': """\
    142. 

  142. .TH "%(HEADER1)s" 1 %(HEADER3)s "%(HEADER2)s"
    143. 

  143. """,
    144. 

    145. 

  145. # TODO style to <HR>
    146. 

  146.   'pm6': """\
    147. 

  147. <PMTags1.0 win><C-COLORTABLE ("Preto" 1 0 0 0)
    148. 

  148. ><@Normal=
    149. 

  149.   <FONT "Times New Roman"><CCOLOR "Preto"><SIZE 11>
    150. 

  150.   <HORIZONTAL 100><LETTERSPACE 0><CTRACK 127><CSSIZE 70><C+SIZE 58.3>
    151. 

  151.   <C-POSITION 33.3><C+POSITION 33.3><P><CBASELINE 0><CNOBREAK 0><CLEADING -0.05>
    152. 

  152.   <GGRID 0><GLEFT 7.2><GRIGHT 0><GFIRST 0><G+BEFORE 7.2><G+AFTER 0>
    153. 

  153.   <GALIGNMENT "justify"><GMETHOD "proportional"><G& "ENGLISH">
    154. 

  154.   <GPAIRS 12><G%% 120><GKNEXT 0><GKWIDOW 0><GKORPHAN 0><GTABS $>
    155. 

  155.   <GHYPHENATION 2 34 0><GWORDSPACE 75 100 150><GSPACE -5 0 25>
    156. 

  156. ><@Bullet=<@-PARENT "Normal"><FONT "Abadi MT Condensed Light">
    157. 

  157.   <GLEFT 14.4><G+BEFORE 2.15><G%% 110><GTABS(25.2 l "")>
    158. 

  158. ><@PreFormat=<@-PARENT "Normal"><FONT "Lucida Console"><SIZE 8><CTRACK 0>
    159. 

  159.   <GLEFT 0><G+BEFORE 0><GALIGNMENT "left"><GWORDSPACE 100 100 100><GSPACE 0 0 0>
    160. 

  160. ><@Title1=<@-PARENT "Normal"><FONT "Arial"><SIZE 14><B>
    161. 

  161.   <GCONTENTS><GLEFT 0><G+BEFORE 0><GALIGNMENT "left">
    162. 

  162. ><@Title2=<@-PARENT "Title1"><SIZE 12><G+BEFORE 3.6>
    163. 

  163. ><@Title3=<@-PARENT "Title1"><SIZE 10><GLEFT 7.2><G+BEFORE 7.2>
    164. 

  164. ><@Title4=<@-PARENT "Title3">
    165. 

  165. ><@Title5=<@-PARENT "Title3">
    166. 

  166. ><@Quote=<@-PARENT "Normal"><SIZE 10><I>>
    167. 

  167. 

  168. %(HEADER1)s
    169. 

  169. %(HEADER2)s
    170. 

  170. %(HEADER3)s
    171. 

  171. """,
    172. 

    173. 

  173.   'mgp': """\
    174. 

  174. #!/usr/X11R6/bin/mgp -t 90
    175. 

  175. %%deffont "normal"    xfont  "utopia-medium-r", charset "iso8859-1"
    176. 

  176. %%deffont "normal-i"  xfont  "utopia-medium-i", charset "iso8859-1"
    177. 

  177. %%deffont "normal-b"  xfont  "utopia-bold-r"  , charset "iso8859-1"
    178. 

  178. %%deffont "normal-bi" xfont  "utopia-bold-i"  , charset "iso8859-1"
    179. 

  179. %%deffont "mono"      xfont "courier-medium-r", charset "iso8859-1"
    180. 

  180. %%default 1 size 5
    181. 

  181. %%default 2 size 8, fore "yellow", font "normal-b", center
    182. 

  182. %%default 3 size 5, fore "white",  font "normal", left, prefix "  "
    183. 

  183. %%tab 1 size 4, vgap 30, prefix "     ", icon arc "red" 40, leftfill
    184. 

  184. %%tab 2 prefix "            ", icon arc "orange" 40, leftfill
    185. 

  185. %%tab 3 prefix "                   ", icon arc "brown" 40, leftfill
    186. 

  186. %%tab 4 prefix "                          ", icon arc "darkmagenta" 40, leftfill
    187. 

  187. %%tab 5 prefix "                                ", icon arc "magenta" 40, leftfill
    188. 

  188. %%%%------------------------- end of headers -----------------------------
    189. 

  189. %%page
    190. 

  190. 

  191. 

  192. 

  193. 

  194. 

  195. %%size 10, center, fore "yellow"
    196. 

  196. %(HEADER1)s
    197. 

  197. 

  198. %%font "normal-i", size 6, fore "white", center
    199. 

  199. %(HEADER2)s
    200. 

  200. 

  201. %%font "mono", size 7, center
    202. 

  202. %(HEADER3)s
    203. 

  203. """,
    204. 

    205. 

  205. # TODO please, improve me!
    206. 

  206.   'moin': """\
    207. 

  207. %(HEADER1)s
    208. 

  208. %(HEADER2)s
    209. 

  209. %(HEADER3)s
    210. 

  210. """,
    211. 

    212. 

  212.   'tex': \
    213. 

  213. r"""\documentclass[11pt,a4paper]{article}
    214. 

  214. \usepackage{amsfonts,amssymb,graphicx,url}
    215. 

  215. \usepackage[%(ENCODING)s]{inputenc}  %% char encoding
    216. 

  216. \pagestyle{plain}   %% do page numbering ('empty' turns off)
    217. 

  217. \frenchspacing      %% no aditional spaces after periods
    218. 

  218. \setlength{\parskip}{8pt}\parindent=0pt  %% no paragraph indentation
    219. 

  219. %% uncomment next line for fancy PDF output on Adobe Acrobat Reader
    220. 

  220. %%\usepackage[pdfstartview=FitV,colorlinks=true,bookmarks=true]{hyperref}
    221. 

  221. 

  222. \title{%(HEADER1)s}
    223. 

  223. \author{%(HEADER2)s}
    224. 

  224. \begin{document}
    225. 

  225. \date{%(HEADER3)s}
    226. 

  226. \maketitle
    227. 

  227. """
    228. 

  228. }
    229. 

  229. 

  230. #-----------------------------------------------------------------------
    231. 

  231. 

  232. def Quit(msg, exitcode=0): print msg ; sys.exit(exitcode)
    233. 

  233. def Error(msg): print "ERROR: %s"%msg ; sys.exit()
    234. 

  234. def echo(msg): print '\033[32;1m%s\033[m'%msg # quick debug
    235. 

  235. def Debug(msg,i=0,linenr=None):
    236. 

  236. 	if i > DEBUG: return
    237. 

  237. 	if linenr is not None:
    238. 

  238. 		print "(%d) %04d:%s"%(i,linenr,msg)
    239. 

  239. 	else:
    240. 

  240. 		print "(%d) %s"%(i,msg)
    241. 

  241. def Readfile(file):
    242. 

  242. 	if file == '-':
    243. 

  243. 		try: data = sys.stdin.readlines()
    244. 

  244. 		except: Error('You must feed me with data on STDIN!')
    245. 

  245. 	else:
    246. 

  246. 		try: f = open(file); data = f.readlines() ; f.close()
    247. 

  247. 		except: Error("Cannot read file:\n    %s"%file)
    248. 

  248. 	return data
    249. 

  249. def Savefile(file, contents):
    250. 

  250. 	try: f = open(file, 'wb')
    251. 

  251. 	except: Error("Cannot open file for writing:\n    %s"%file)
    252. 

  252. 	if type(contents) == type([]): doit = f.writelines
    253. 

  253. 	else: doit = f.write
    254. 

  254. 	doit(contents) ; f.close()
    255. 

  255. 

  256. def ParseConfig(text='',name='', target=''):
    257. 

  257. 	ret = {}
    258. 

  258. 	if not text: return ret
    259. 

  259. 	re_name = name or '[a-z]+'
    260. 

  260. 	re_target = target or '[a-z]*'
    261. 

  261. 	cfgregex = re.compile("""
    262. 

  262. 	  ^%%!\s*               # leading id with opt spaces
    263. 

  263. 	  (?P<name>%s)\s*       # config name 
    264. 

  264. 	  (\((?P<target>%s)\))? # optional target spec inside ()
    265. 

  265. 	  \s*:\s*               # key:value delimiter with opt spaces
    266. 

  266. 	  (?P<value>\S.+?)      # config value
    267. 

  267. 	  \s*$                  # rstrip() spaces and hit EOL
    268. 

  268. 	  """%(re_name,re_target), re.I+re.VERBOSE)
    269. 

  269. 	prepostregex = re.compile("""
    270. 

  270. 	                        # ---[ PATTERN ]---
    271. 

  271. 	  ^( "([^"]*)"            # "double quoted" or
    272. 

  272. 	   | '([^']*)'            # 'single quoted' or
    273. 

  273. 	   | ([^\s]+)             # single_word
    274. 

  274. 	   )
    275. 

  275. 	    \s+                 # separated by spaces
    276. 

  276. 	   
    277. 

  277. 		                    # ---[ REPLACE ]---
    278. 

  278. 	       ( "([^"]*)"        # "double quoted" or
    279. 

  279. 	       | '([^']*)'        # 'single quoted' or
    280. 

  280. 	       | (.*)             # anything
    281. 

  281. 		   )
    282. 

  282. 		    \s*$
    283. 

  283. 	  """, re.VERBOSE)
    284. 

  284. 	match = cfgregex.match(text)
    285. 

  285. 	if match:
    286. 

  286. 		ret = {'name'  :string.lower(match.group('name') or ''),
    287. 

  287. 		       'target':string.lower(match.group('target') or 'all'),
    288. 

  288. 		       'value' :match.group('value') }
    289. 

  289. 		
    290. 

  290. 		# Special config with two quoted values (%!preproc: "foo" 'bar')
    291. 

  291. 		if ret['name'] in ['preproc','postproc']:
    292. 

  292. 			valmatch = prepostregex.search(ret['value'])
    293. 

  293. 			if not valmatch: return None
    294. 

  294. 			getval = valmatch.group
    295. 

  295. 			patt = getval(2) or getval(3) or getval(4) or ''
    296. 

  296. 			repl = getval(6) or getval(7) or getval(8) or ''
    297. 

  297. 			ret['value'] = (patt, repl)
    298. 

  298. 	
    299. 

  299. 	return ret
    300. 

  300. 

  301. 

  302. class Cmdline:
    303. 

  303. 	def __init__(self, cmdline=[], nocheck=0):
    304. 

  304. 		self.conf = {}
    305. 

  305. 		self.cmdline = cmdline
    306. 

  306. 		self.cmdline_conf = {}
    307. 

  307. 		self.dft_options = OPTIONS.copy()
    308. 

  308. 		self.dft_flags   = FLAGS.copy()
    309. 

  309. 		self.all_options = self.dft_options.keys()
    310. 

  310. 		self.all_flags   = self.dft_flags.keys()
    311. 

  311. 		self.defaults = self._get_empty_conf()
    312. 

  312. 		self.nocheck = nocheck
    313. 

  313. 		if cmdline: self.parse()
    314. 

  314. 	
    315. 

  315. 	#TODO protect quotes contents
    316. 

  316. 	def _tokenize(self, cmd_string):
    317. 

  317. 		return string.split(cmd_string)
    318. 

  318. 	
    319. 

  319. 	def parse(self):
    320. 

  320. 		"return a dic with all options:value found"
    321. 

  321. 		if not self.cmdline: return {}
    322. 

  322. 		Debug("cmdline: %s"%self.cmdline, 1)
    323. 

  323. 		options = {'infile': '', 'infiles':''}
    324. 

  324. 		# compose valid options list
    325. 

  325. 		longopts = ['help','version'] + self.all_flags + \
    326. 

  326. 		           map(lambda x:x+'=', self.all_options) # add =
    327. 

  327. 		cmdline = self.cmdline[1:]           # del prog name  
    328. 

  328. 		# get cmdline options
    329. 

  329. 		try: (opt, args) = getopt.getopt(cmdline, 'hVnHt:o:', longopts)
    330. 

  330. 		except getopt.GetoptError:
    331. 

  331. 			Error('Bad option or missing argument (try --help)')
    332. 

  332. 		# get infile, if any
    333. 

  333. 		if args:
    334. 

  334. 			options['infile'] = args[0]
    335. 

  335. 			options['infiles'] = args  # multi
    336. 

  336. 		# parse all options
    337. 

  337. 		for name,val in opt:
    338. 

  338. 			if   name in ['-h','--help'   ]: Quit(usage)
    339. 

  339. 			elif name in ['-V','--version']: Quit(versionstr)
    340. 

  340. 			elif name in ['-t','--type'     ]: options['type'] = val
    341. 

  341. 			elif name in ['-o','--outfile'  ]: options['outfile'] = val
    342. 

  342. 			elif name in ['-n','--enumtitle']: options['enumtitle'] = 1
    343. 

  343. 			elif name in ['-H','--noheaders']: options['noheaders'] = 1
    344. 

  344. 			elif name in ['--stdout']: options['outfile'] = STDOUT
    345. 

  345. 			else: options[name[2:]] = val or 1 # del --
    346. 

  346. 		# save results
    347. 

  347. 		Debug("cmdline arguments: %s"%options, 1)
    348. 

  348. 		self.cmdline_conf = options
    349. 

  349. 	
    350. 

  350. 	def compose(self, conf={}):
    351. 

  351. 		"compose full command line from CONF dict"
    352. 

  352. 		if not conf: return ''
    353. 

  353. 		args = []
    354. 

  354. 		cfg = conf.copy()
    355. 

  355. 		valid_opts = self.all_options + self.all_flags
    356. 

  356. 		use_short = {'noheaders':'H', 'enumtitle':'n'}
    357. 

  357. 		# remove useless options
    358. 

  358. 		if cfg.get('toconly'):
    359. 

  359. 			del cfg['noheaders']
    360. 

  360. 			del cfg['outfile']        # defaults to STDOUT
    361. 

  361. 			if cfg.get('type') == 'txt':
    362. 

  362. 				del cfg['type']       # already default
    363. 

  363. 			args.append('--toconly')  # must be the first
    364. 

  364. 			del cfg['toconly']
    365. 

  365. 		# add target type
    366. 

  366. 		if cfg.has_key('type'):
    367. 

  367. 			args.append('-t '+cfg['type'])
    368. 

  368. 			del cfg['type']
    369. 

  369. 		# add other options
    370. 

  370. 		for key in cfg.keys():
    371. 

  371. 			if key not in valid_opts: continue  # must be a %!setting
    372. 

  372. 			if key == 'outfile': continue       # later
    373. 

  373. 			val = cfg[key]
    374. 

  374. 			if not val: continue
    375. 

  375. 			# default values are useless on cmdline
    376. 

  376. 			if val == self.dft_options.get(key): continue
    377. 

  377. 			# -short format
    378. 

  378. 			if key in use_short.keys():
    379. 

  379. 				args.append('-'+use_short[key])
    380. 

  380. 				continue
    381. 

  381. 			# --long format
    382. 

  382. 			if key in self.all_flags: # add --option
    383. 

  383. 				args.append('--'+key)
    384. 

  384. 			else:                     # add --option=value
    385. 

  385. 				args.append('--%s=%s'%(key,val))
    386. 

  386. 		# the outfile using -o
    387. 

  387. 		if cfg.has_key('outfile') and \
    388. 

  388. 		   cfg['outfile'] != self.dft_options.get('outfile'):
    389. 

  389. 			args.append('-o '+cfg['outfile'])
    390. 

  390. 		# the input file is always at the end
    391. 

  391. 		if cfg.has_key('infile'):
    392. 

  392. 			args.append(cfg['infile'])
    393. 

  393. 		# return as a single string
    394. 

  394. 		ret = string.join(args,' ')
    395. 

  395. 		Debug("Diet command line: %s"%ret, 1)
    396. 

  396. 		return ret
    397. 

  397. 	
    398. 

  398. 	def merge(self, extraopts=''):
    399. 

  399. 		"insert cmdline portion BEFORE current cmdline"
    400. 

  400. 		if not extraopts: return
    401. 

  401. 		if type(extraopts) == type(''):
    402. 

  402. 			extraopts = self._tokenize(extraopts)
    403. 

  403. 		if not self.cmdline: self.cmdline = extraopts
    404. 

  404. 		else: self.cmdline = ['t2t-merged'] +extraopts +self.cmdline[1:]
    405. 

  405. 		self.parse()
    406. 

  406. 	
    407. 

  407. 	def _get_outfile_name(self, conf):
    408. 

  408. 		"dirname is the same for {in,out}file"
    409. 

  409. 		infile = conf['infile']
    410. 

  410. 		if not infile: return ''
    411. 

  411. 		if infile == STDIN or conf['outfile'] == STDOUT:
    412. 

  412. 			outfile = STDOUT
    413. 

  413. 		else:
    414. 

  414. 			basename = re.sub('\.(txt|t2t)$','',infile)
    415. 

  415. 			outfile = "%s.%s"%(basename, conf['type'])
    416. 

  416. 		self.dft_options['outfile'] = outfile # save for self.compose()
    417. 

  417. 		Debug(" infile: '%s'"%infile , 1)
    418. 

  418. 		Debug("outfile: '%s'"%outfile, 1)
    419. 

  419. 		return outfile
    420. 

  420. 	
    421. 

  421. 	def _sanity(self, dic):
    422. 

  422. 		"basic cmdline syntax checkings"
    423. 

  423. 		if not dic: return {}
    424. 

  424. 		if not dic['infile'] or not dic['type']:
    425. 

  425. 			Quit(usage, 1)                  # no filename/doctype
    426. 

  426. 		if not targets.count(dic['type']):      # check target
    427. 

  427. 			Error("Invalid document type '%s' (try --help)"%(
    428. 

  428. 			       dic['type']))
    429. 

  429. 		#DISABLED: conflicting with %!cmdline: -o foo	   
    430. 

  430. 		#if len(dic['infiles']) > 1 and dic['outfile']: # -o FILE *.t2t
    431. 

  431. 		#	Error("--outfile can't be used with multiple files")
    432. 

  432. 		for opt in self.all_options:            # check numeric options
    433. 

  433. 			opttype = type(self.dft_options[opt])
    434. 

  434. 			if dic.get(opt) and opttype == type(9):
    435. 

  435. 				try: dic[opt] = int(dic.get(opt)) # save
    436. 

  436. 				except: Error('--%s value must be a number'%opt)
    437. 

  437. 		if dic['split'] not in [0,1,2]:         # check split level
    438. 

  438. 			Error('Option --split must be 0, 1 or 2')
    439. 

  439. 		return dic
    440. 

  440. 	
    441. 

  441. 	def merge_conf(self, newconfs={}, override=0):
    442. 

  442. 		"include Config Area settings into self.conf"
    443. 

  443. 		if not self.conf: self.get_conf()
    444. 

  444. 		if not newconfs: return self.conf
    445. 

  445. 		for key in newconfs.keys():
    446. 

  446. 			if key == 'cmdline': continue   # already done
    447. 

  447. 			# filters are always accumulative
    448. 

  448. 			if key in ['preproc','postproc']:
    449. 

  449. 				if not self.conf.has_key(key):
    450. 

  450. 					self.conf[key] = []
    451. 

  451. 				self.conf[key].extend(newconfs[key])
    452. 

  452. 				continue
    453. 

  453. 			# add anyway
    454. 

  454. 			if override:
    455. 

  455. 				self.conf[key] = newconfs[key]
    456. 

  456. 				continue
    457. 

  457. 			# just update if still 'virgin'
    458. 

  458. 			if self.conf.has_key(key) and \
    459. 

  459. 			   self.conf[key] == self.defaults.get(key):
    460. 

  460. 				self.conf[key] = newconfs[key]
    461. 

  461. 			# add new
    462. 

  462. 			if not self.conf.has_key(key):
    463. 

  463. 				self.conf[key] = newconfs[key]
    464. 

  464. 		
    465. 

  465. 		Debug("Merged CONF (override=%s): %s"%(override,self.conf), 1)
    466. 

  466. 		return self.conf
    467. 

  467. 	
    468. 

  468. 	def _get_empty_conf(self):
    469. 

  469. 		econf = self.dft_options.copy()
    470. 

  470. 		for k in self.dft_flags.keys(): econf[k] = self.dft_flags[k]
    471. 

  471. 		return econf
    472. 

  472. 	
    473. 

  473. 	def get_conf(self):
    474. 

  474. 		"set vars and flags according to options dic"
    475. 

  475. 		if not self.cmdline_conf:
    476. 

  476. 			if not self.cmdline: return {}
    477. 

  477. 			self.parse()
    478. 

  478. 		dic = self.cmdline_conf
    479. 

  479. 		conf = self.defaults.copy()
    480. 

  480. 		
    481. 

  481. 		## store flags & options
    482. 

  482. 		for flag in self.all_flags:
    483. 

  483. 			if dic.has_key(flag): conf[flag] = 1
    484. 

  484. 		for opt in self.all_options + ['infile', 'infiles']:
    485. 

  485. 			if dic.has_key(opt): conf[opt] = dic.get(opt)
    486. 

  486. 		
    487. 

  487. 		if not conf['type'] and conf['toconly']: conf['type'] = 'txt'
    488. 

  488. 		if not self.nocheck: conf = self._sanity(conf)
    489. 

  489. 		
    490. 

  490. 		## some gotchas for specific issues
    491. 

  491. 		doctype = conf['type']
    492. 

  492. 		infile = conf['infile']
    493. 

  493. 		
    494. 

  494. 		# toconly is stronger than others
    495. 

  495. 		if conf['toconly']:
    496. 

  496. 			conf['noheaders'] = 1
    497. 

  497. 			conf['toc'] = 0
    498. 

  498. 			conf['split'] = 0
    499. 

  499. 			conf['gui'] = 0
    500. 

  500. 			conf['outfile'] = STDOUT
    501. 

  501. 			conf['toclevel'] = conf['toclevel'] or \
    502. 

  502. 			                   self.dft_options['toclevel']
    503. 

  503. 		
    504. 

  504. 		# split: just HTML, no stdout, 1st do a sgml, then sgml2html
    505. 

  505. 		if conf['split']:
    506. 

  506. 			if doctype != 'html':
    507. 

  507. 				conf['split'] = 0
    508. 

  508. 			else:
    509. 

  509. 				conf['type'] = 'sgml' 
    510. 

  510. 				if conf['outfile'] == STDOUT:
    511. 

  511. 					conf['outfile'] = ''
    512. 

  512. 		
    513. 

  513. 		outfile = conf['outfile'] or self._get_outfile_name(conf)
    514. 

  514. 		
    515. 

  515. 		# final checkings
    516. 

  516. 		if conf['split'] and outfile == STDOUT:
    517. 

  517. 			Error('--split: You must provide a FILE (not STDIN)')
    518. 

  518. 		if infile == outfile and outfile != STDOUT:
    519. 

  519. 			Error("SUICIDE WARNING!!!  (see --outfile)\n  source"+\
    520. 

  520. 			      " and target files has the same name: "+outfile)
    521. 

  521. 		### author's note: "yes, i've got my sample.t2t file deleted
    522. 

  522. 		### before add this test... :/"
    523. 

  523. 		
    524. 

  524. 		conf['outfile'] = outfile
    525. 

  525. 		conf['cmdline'] = self.cmdline
    526. 

  526. 		Debug("CONF data: %s\n"%conf, 1)
    527. 

  527. 		self.conf = conf
    528. 

  528. 		return self.conf
    529. 

  529. #
    530. 

  530. ### End of Cmdline class
    531. 

  531. 

  532. 

  533. 

  534. 

  535. class Proprierties:
    536. 

  536. 	def __init__(self, filename=''):
    537. 

  537. 		self.buffer = ['']   # text start at pos 1
    538. 

  538. 		self.areas = ['head','conf','body']
    539. 

  539. 		self.arearef = []
    540. 

  540. 		self.headers = ['','','']
    541. 

  541. 		self.config = self.get_empty_config()
    542. 

  542. 		self.lastline = 0
    543. 

  543. 		self.filename = filename
    544. 

  544. 		self.conflines = []
    545. 

  545. 		self.bodylines = []
    546. 

  546. 		if filename:
    547. 

  547. 			self.read_file(filename)
    548. 

  548. 			self.find_areas()
    549. 

  549. 			self.set_headers()
    550. 

  550. 			self.set_config()
    551. 

  551. 	
    552. 

  552. 	def read_file(self, file):
    553. 

  553. 		lines = Readfile(file)
    554. 

  554. 		if not lines: Error('Empty file! %s'%file)
    555. 

  555. 		self.buffer.extend(lines)
    556. 

  556. 	
    557. 

  557. 	def get_empty_config(self):
    558. 

  558. 		empty = {}
    559. 

  559. 		for targ in targets+['all']: empty[targ] = {}
    560. 

  560. 		return empty
    561. 

  561. 	
    562. 

  562. 	def find_areas(self):
    563. 

  563. 		"Run through buffer and identify head/conf/body areas"
    564. 

  564. 		buf = self.buffer ; ref = [1,4,0]       # defaults
    565. 

  565. 		if not string.strip(buf[1]):            # no header
    566. 

  566. 			ref[0] = 0 ; ref[1] = 2
    567. 

  567. 		for i in range(ref[1],len(buf)):        # find body init
    568. 

  568. 			if string.strip(buf[i]) and buf[i][0] != '%':
    569. 

  569. 				ref[2] = i ; break      # !blank, !comment
    570. 

  570. 		if ref[1] == ref[2]: ref[1] = 0         # no conf area
    571. 

  571. 		for i in 0,1,2:                         # del !existent
    572. 

  572. 			if not ref[i]: self.areas[i] = ''
    573. 

  573. 		self.arearef = ref                      # save results
    574. 

  574. 		self.lastline = len(self.buffer)-1
    575. 

  575. 		Debug('Head,Conf,Body start line: %s'%ref, 1)
    576. 

  576. 		# store CONF and BODY lines found
    577. 

  577. 		cfgend = ref[2] or len(buf)
    578. 

  578. 		self.conflines = buf[ref[1]:cfgend]
    579. 

  579. 		if ref[2]: self.bodylines = buf[ref[2]:]
    580. 

  580. 	
    581. 

  581. 	
    582. 

  582. 	def set_headers(self):
    583. 

  583. 		"Extract and save headers contents"
    584. 

  584. 		if not self.arearef: self.find_areas()
    585. 

  585. 		if not self.areas.count('head'): return
    586. 

  586. 		if self.lastline < 3:
    587. 

  587. 			#TODO on gui this checking is !working
    588. 

  588. 			Error(
    589. 

  589. 			"Premature end of Headers on '%s'."%self.filename +\
    590. 

  590. 			'\n\nFile has %s line(s), but '%self.lastline     +\
    591. 

  591. 			'Headers should be composed by 3 lines. '         +\
    592. 

  592. 			'\nMaybe you should left the first line blank? '  +\
    593. 

  593. 			'(for no headers)')
    594. 

  594. 		for i in 0,1,2:
    595. 

  595. 			self.headers[i] = string.strip(self.buffer[i+1])
    596. 

  596. 		Debug("Headers found: %s"%self.headers, 1, i+1)
    597. 

  597. 	
    598. 

  598. 	def set_config(self):
    599. 

  599. 		"Extract and save config contents (including includes)"
    600. 

  600. 		if not self.arearef: self.find_areas()
    601. 

  601. 		if not self.areas.count('conf'): return
    602. 

  602. 		keywords = string.join(CONFIG_KEYWORDS, '|')
    603. 

  603. 		linenr = self.arearef[1]-1  # for debug messages
    604. 

  604. 		for line in self.conflines:
    605. 

  605. 			linenr = linenr + 1
    606. 

  606. 			if len(line) < 3: continue
    607. 

  607. 			if line[:2] != '%!': continue
    608. 

  608. 			cfg = ParseConfig(line, keywords)
    609. 

  609. 			# any _valid_ config found?
    610. 

  610. 			if not cfg:
    611. 

  611. 				Debug('Bogus Config Line',1,linenr)
    612. 

  612. 				continue
    613. 

  613. 			# get data	
    614. 

  614. 			targ, key, val = cfg['target'],cfg['name'], cfg['value']
    615. 

  615. 			# check config target specification
    616. 

  616. 			if targ not in targets+['all']:
    617. 

  617. 				Debug("Config Error: Invalid target '%s', ignoring"%targ,
    618. 

  618. 				      1,linenr)
    619. 

  619. 				continue
    620. 

  620. 			# filters are multiple config
    621. 

  621. 			if key in ['preproc','postproc']:
    622. 

  622. 				if not self.config['all'].has_key(key):  # 1st one
    623. 

  623. 					self.config['all'][key] = []
    624. 

  624. 				# all filters are saved to target 'all'
    625. 

  625. 				# finish_him will decide what to consider
    626. 

  626. 				self.config['all'][key].append((targ,)+val)
    627. 

  627. 			else:
    628. 

  628. 				self.config[targ][key] = val
    629. 

  629. 			Debug("Found config for target '%s': '%s', value '%s'"%(
    630. 

  630. 			       targ,key,val),1,linenr)
    631. 

  631. 		Debug("All %%!CONFIG: %s"%self.config, 1)
    632. 

  632. 

  633. 

  634. def get_file_body(file):
    635. 

  635. 	"Returns all the document BODY lines (including includes)"
    636. 

  636. 	prop = Proprierties()
    637. 

  637. 	prop.read_file(file)
    638. 

  638. 	prop.find_areas()
    639. 

  639. 	return prop.bodylines
    640. 

  640. 

  641. 

  642. def finish_him(outlist, CONF):
    643. 

  643. 	"Writing output to screen or file"
    644. 

  644. 	outfile = CONF['outfile']
    645. 

  645. 	outlist = unmaskEscapeChar(outlist)
    646. 

  646. 	
    647. 

  647. 	# do PostProc
    648. 

  648. 	if CONF['postproc']:
    649. 

  649. 		postoutlist = []
    650. 

  650. 		for line in outlist:
    651. 

  651. 			for targ,patt,repl in CONF['postproc']:
    652. 

  652. 				if targ not in [CONF['type'], 'all']: continue
    653. 

  653. 				line = re.sub(patt, repl, line)
    654. 

  654. 			postoutlist.append(line)
    655. 

  655. 		outlist = postoutlist[:]
    656. 

  656. 	
    657. 

  657. 	if outfile == STDOUT:
    658. 

  658. 		for line in outlist: print line
    659. 

  659. 	else:
    660. 

  660. 		Savefile(outfile, addLineBreaks(outlist))
    661. 

  661. 		if not CONF['gui']: print 'wrote %s'%(outfile)
    662. 

  662. 	
    663. 

  663. 	if CONF['split']:
    664. 

  664. 		print "--- html..."
    665. 

  665. 		sgml2html = 'sgml2html -s %s -l %s %s'%(
    666. 

  666. 		            CONF['split'],CONF['lang'] or lang,outfile)
    667. 

  667. 		print "Running system command:", sgml2html
    668. 

  668. 		os.system(sgml2html)
    669. 

  669. 

  670. 

  671. def toc_maker(toc, conf):
    672. 

  672. 	"Compose TOC list 'by hand'"
    673. 

  673. 	# TOC is a tag, so there's nothing to do here
    674. 

  674. 	if TAGS['TOC']: return []
    675. 

  675. 	# toc is a valid t2t marked text (list type), that is converted
    676. 

  676. 	if conf['toc'] or conf['toconly']:
    677. 

  677. 		fakeconf = conf.copy()
    678. 

  678. 		fakeconf['noheaders'] = 1
    679. 

  679. 		fakeconf['toconly']   = 0
    680. 

  680. 		fakeconf['maskemail'] = 0
    681. 

  681. 		fakeconf['preproc'] = []
    682. 

  682. 		fakeconf['postproc'] = []
    683. 

  683. 		toc,foo = convert(toc, fakeconf)
    684. 

  684. 	# TOC between bars (not for --toconly)
    685. 

  685. 	if conf['toc']:
    686. 

  686. 		para = TAGS['paragraph']
    687. 

  687. 		tocbar = [para, regex['x'].sub('-'*72,TAGS['bar1']), para]
    688. 

  688. 		toc = tocbar + toc + tocbar
    689. 

  689. 	return toc
    690. 

  690. 

  691. 

  692. def getTags(doctype):
    693. 

  693. 	keys = [
    694. 

  694. 	'paragraph','title1','title2','title3','title4','title5',
    695. 

  695. 	'numtitle1','numtitle2','numtitle3','numtitle4','numtitle5',
    696. 

  696. 	'areaPreOpen','areaPreClose',
    697. 

  697. 	'areaQuoteOpen','areaQuoteClose',
    698. 

  698. 	'fontMonoOpen','fontMonoClose',
    699. 

  699. 	'fontBoldOpen','fontBoldClose',
    700. 

  700. 	'fontItalicOpen','fontItalicClose',
    701. 

  701. 	'fontBolditalicOpen','fontBolditalicClose',
    702. 

  702. 	'fontUnderlineOpen','fontUnderlineClose',
    703. 

  703. 	'listOpen','listClose','listItem',
    704. 

  704. 	'numlistOpen','numlistClose','numlistItem',
    705. 

  705. 	'deflistOpen','deflistClose','deflistItem1','deflistItem2',
    706. 

  706. 	'bar1','bar2',
    707. 

  707. 	'url','urlMark','email','emailMark',
    708. 

  708. 	'img','imgsolo',
    709. 

  709. 	'tableOpen','tableClose','tableLineOpen','tableLineClose',
    710. 

  710. 	'tableCellOpen','tableCellClose',
    711. 

  711. 	'tableTitleCellOpen','tableTitleCellClose',
    712. 

  712. 	'anchor','comment','TOC',
    713. 

  713. 	'EOD'
    714. 

  714. 	]
    715. 

  715. 	
    716. 

  716. 	alltags = {
    717. 

  717. 	
    718. 

  718. 	'txt': {
    719. 

  719. 	   'title1'              : '  \a'      ,
    720. 

  720. 	   'title2'              : '\t\a'      ,
    721. 

  721. 	   'title3'              : '\t\t\a'    ,
    722. 

  722. 	   'title4'              : '\t\t\t\a'  ,
    723. 

  723. 	   'title5'              : '\t\t\t\t\a',
    724. 

  724. 	   'areaQuoteOpen'       : '    '      ,
    725. 

  725. 	   'listItem'            : '- '        ,
    726. 

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

  727. 	   'bar1'                : '\a'        ,
    728. 

  728. 	   'bar2'                : '\a'        ,
    729. 

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

  730. 	   'urlMark'             : '\a (\a)'   ,
    731. 

  731. 	   'email'               : '\a'        ,
    732. 

  732. 	   'emailMark'           : '\a (\a)'   ,
    733. 

  733. 	   'img'                 : '[\a]'      ,
    734. 

  734. 	},
    735. 

  735. 	
    736. 

  736. 	'html': {
    737. 

  737. 	   'paragraph'           : '<P>'            ,
    738. 

  738. 	   'title1'              : '<H1>\a</H1>'    ,
    739. 

  739. 	   'title2'              : '<H2>\a</H2>'    ,
    740. 

  740. 	   'title3'              : '<H3>\a</H3>'    ,
    741. 

  741. 	   'title4'              : '<H4>\a</H4>'    ,
    742. 

  742. 	   'title5'              : '<H5>\a</H5>'    ,
    743. 

  743. 	   'areaPreOpen'         : '<PRE>'          ,
    744. 

  744. 	   'areaPreClose'        : '</PRE>'         ,
    745. 

  745. 	   'areaQuoteOpen'       : '<BLOCKQUOTE>'   ,
    746. 

  746. 	   'areaQuoteClose'      : '</BLOCKQUOTE>'  ,
    747. 

  747. 	   'fontMonoOpen'        : '<CODE>'         ,
    748. 

  748. 	   'fontMonoClose'       : '</CODE>'        ,
    749. 

  749. 	   'fontBoldOpen'        : '<B>'            ,
    750. 

  750. 	   'fontBoldClose'       : '</B>'           ,
    751. 

  751. 	   'fontItalicOpen'      : '<I>'            ,
    752. 

  752. 	   'fontItalicClose'     : '</I>'           ,
    753. 

  753. 	   'fontBolditalicOpen'  : '<B><I>'         ,
    754. 

  754. 	   'fontBolditalicClose' : '</I></B>'       ,
    755. 

  755. 	   'fontUnderlineOpen'   : '<U>'            ,
    756. 

  756. 	   'fontUnderlineClose'  : '</U>'           ,
    757. 

  757. 	   'listOpen'            : '<UL>'           ,
    758. 

  758. 	   'listClose'           : '</UL>'          ,
    759. 

  759. 	   'listItem'            : '<LI>'           ,
    760. 

  760. 	   'numlistOpen'         : '<OL>'           ,
    761. 

  761. 	   'numlistClose'        : '</OL>'          ,
    762. 

  762. 	   'numlistItem'         : '<LI>'           ,
    763. 

  763. 	   'deflistOpen'         : '<DL>'           ,
    764. 

  764. 	   'deflistClose'        : '</DL>'          ,
    765. 

  765. 	   'deflistItem1'        : '<DT>\a</DT>'    ,
    766. 

  766. 	   'deflistItem2'        : '<DD>'           ,
    767. 

  767. 	   'bar1'                : '<HR NOSHADE SIZE=1>'        ,
    768. 

  768. 	   'bar2'                : '<HR NOSHADE SIZE=5>'        ,
    769. 

  769. 	   'url'                 : '<A HREF="\a">\a</A>'        ,
    770. 

  770. 	   'urlMark'             : '<A HREF="\a">\a</A>'        ,
    771. 

  771. 	   'email'               : '<A HREF="mailto:\a">\a</A>' ,
    772. 

  772. 	   'emailMark'           : '<A HREF="mailto:\a">\a</A>' ,
    773. 

  773. 	   'img'                 : '<IMG ALIGN="\a" SRC="\a" BORDER="0">',
    774. 

  774. 	   'imgsolo'             : '<P ALIGN="center">\a</P>'   ,
    775. 

  775. 	   'tableOpen'           : '<table\a cellpadding=4 border=\a>',
    776. 

  776. 	   'tableClose'          : '</table>'       ,
    777. 

  777. 	   'tableLineOpen'       : '<tr>'           ,
    778. 

  778. 	   'tableLineClose'      : '</tr>'          ,
    779. 

  779. 	   'tableCellOpen'       : '<td\a>'         ,
    780. 

  780. 	   'tableCellClose'      : '</td>'          ,
    781. 

  781. 	   'tableTitleCellOpen'  : '<th>'           ,
    782. 

  782. 	   'tableTitleCellClose' : '</th>'          ,
    783. 

  783. 	   'tableAlignLeft'      : ''               ,
    784. 

  784. 	   'tableAlignCenter'    : ' align="center"',
    785. 

  785. 	   'tableCellAlignLeft'  : ''               ,
    786. 

  786. 	   'tableCellAlignRight' : ' align="right"' ,
    787. 

  787. 	   'tableCellAlignCenter': ' align="center"',
    788. 

  788. 	   'anchor'              : '<a name="\a"></a>',
    789. 

  789. 	   'comment'             : '<!-- \a -->'    ,
    790. 

  790. 	   'EOD'                 : '</BODY></HTML>'
    791. 

  791. 	},
    792. 

  792. 	
    793. 

  793. 	'sgml': {
    794. 

  794. 	   'paragraph'           : '<p>'                ,
    795. 

  795. 	   'title1'              : '<sect>\a<p>'        ,
    796. 

  796. 	   'title2'              : '<sect1>\a<p>'       ,
    797. 

  797. 	   'title3'              : '<sect2>\a<p>'       ,
    798. 

  798. 	   'title4'              : '<sect3>\a<p>'       ,
    799. 

  799. 	   'title5'              : '<sect4>\a<p>'       ,
    800. 

  800. 	   'areaPreOpen'         : '<tscreen><verb>'    ,
    801. 

  801. 	   'areaPreClose'        : '</verb></tscreen>'  ,
    802. 

  802. 	   'areaQuoteOpen'       : '<quote>'            ,
    803. 

  803. 	   'areaQuoteClose'      : '</quote>'           ,
    804. 

  804. 	   'fontMonoOpen'        : '<tt>'               ,
    805. 

  805. 	   'fontMonoClose'       : '</tt>'              ,
    806. 

  806. 	   'fontBoldOpen'        : '<bf>'               ,
    807. 

  807. 	   'fontBoldClose'       : '</bf>'              ,
    808. 

  808. 	   'fontItalicOpen'      : '<em>'               ,
    809. 

  809. 	   'fontItalicClose'     : '</em>'              ,
    810. 

  810. 	   'fontBolditalicOpen'  : '<bf><em>'           ,
    811. 

  811. 	   'fontBolditalicClose' : '</em></bf>'         ,
    812. 

  812. 	   'fontUnderlineOpen'   : '<bf><em>'           ,
    813. 

  813. 	   'fontUnderlineClose'  : '</em></bf>'         ,
    814. 

  814. 	   'listOpen'            : '<itemize>'          ,
    815. 

  815. 	   'listClose'           : '</itemize>'         ,
    816. 

  816. 	   'listItem'            : '<item>'             ,
    817. 

  817. 	   'numlistOpen'         : '<enum>'             ,
    818. 

  818. 	   'numlistClose'        : '</enum>'            ,
    819. 

  819. 	   'numlistItem'         : '<item>'             ,
    820. 

  820. 	   'deflistOpen'         : '<descrip>'          ,
    821. 

  821. 	   'deflistClose'        : '</descrip>'         ,
    822. 

  822. 	   'deflistItem1'        : '<tag>\a</tag>'      ,
    823. 

  823. 	   'bar1'                : '<!-- \a -->'        ,
    824. 

  824. 	   'bar2'                : '<!-- \a -->'        ,
    825. 

  825. 	   'url'                 : '<htmlurl url="\a" name="\a">'        ,
    826. 

  826. 	   'urlMark'             : '<htmlurl url="\a" name="\a">'        ,
    827. 

  827. 	   'email'               : '<htmlurl url="mailto:\a" name="\a">' ,
    828. 

  828. 	   'emailMark'           : '<htmlurl url="mailto:\a" name="\a">' ,
    829. 

  829. 	   'img'                 : '<figure><ph vspace=""><img src="\a">'+\
    830. 

  830. 	                           '</figure>'                           ,
    831. 

  831. 	   'tableOpen'           : '<table><tabular ca="\a">'            ,
    832. 

  832. 	   'tableClose'          : '</tabular></table>' ,
    833. 

  833. 	   'tableLineClose'      : '<rowsep>'           ,
    834. 

  834. 	   'tableCellClose'      : '<colsep>'           ,
    835. 

  835. 	   'tableTitleCellClose' : '<colsep>'           ,
    836. 

  836. 	   'tableColAlignLeft'   : 'l'                  ,
    837. 

  837. 	   'tableColAlignRight'  : 'r'                  ,
    838. 

  838. 	   'tableColAlignCenter' : 'c'                  ,
    839. 

  839. 	   'comment'             : '<!-- \a -->'        ,
    840. 

  840. 	   'TOC'                 : '<toc>'              ,
    841. 

  841. 	   'EOD'                 : '</article>'
    842. 

  842. 	},
    843. 

  843. 	   
    844. 

  844. 	'tex': {
    845. 

  845. 	   'title1'              : '\n\\newpage\section*{\a}',
    846. 

  846. 	   'title2'              : '\\subsection*{\a}'       ,
    847. 

  847. 	   'title3'              : '\\subsubsection*{\a}'    ,
    848. 

  848. 	   # title 4/5: DIRTY: para+BF+\\+\n
    849. 

  849. 	   'title4'              : '\\paragraph{}\\textbf{\a}\\\\\n',
    850. 

  850. 	   'title5'              : '\\paragraph{}\\textbf{\a}\\\\\n',
    851. 

  851. 	   'numtitle1'           : '\n\\newpage\section{\a}',
    852. 

  852. 	   'numtitle2'           : '\\subsection{\a}'       ,
    853. 

  853. 	   'numtitle3'           : '\\subsubsection{\a}'    ,
    854. 

  854. 	   'areaPreOpen'         : '\\begin{verbatim}'   ,
    855. 

  855. 	   'areaPreClose'        : '\\end{verbatim}'     ,
    856. 

  856. 	   'areaQuoteOpen'       : '\\begin{quotation}'  ,
    857. 

  857. 	   'areaQuoteClose'      : '\\end{quotation}'    ,
    858. 

  858. 	   'fontMonoOpen'        : '\\texttt{'           ,
    859. 

  859. 	   'fontMonoClose'       : '}'                   ,
    860. 

  860. 	   'fontBoldOpen'        : '\\textbf{'           ,
    861. 

  861. 	   'fontBoldClose'       : '}'                   ,
    862. 

  862. 	   'fontItalicOpen'      : '\\textit{'           ,
    863. 

  863. 	   'fontItalicClose'     : '}'                   ,
    864. 

  864. 	   'fontBolditalicOpen'  : '\\textbf{\\textit{'  ,
    865. 

  865. 	   'fontBolditalicClose' : '}}'                  ,
    866. 

  866. 	   'fontUnderlineOpen'   : '\\underline{'        ,
    867. 

  867. 	   'fontUnderlineClose'  : '}'                   ,
    868. 

  868. 	   'listOpen'            : '\\begin{itemize}'    ,
    869. 

  869. 	   'listClose'           : '\\end{itemize}'      ,
    870. 

  870. 	   'listItem'            : '\\item '             ,
    871. 

  871. 	   'numlistOpen'         : '\\begin{enumerate}'  ,
    872. 

  872. 	   'numlistClose'        : '\\end{enumerate}'    ,
    873. 

  873. 	   'numlistItem'         : '\\item '             ,
    874. 

  874. 	   'deflistOpen'         : '\\begin{description}',
    875. 

  875. 	   'deflistClose'        : '\\end{description}'  ,
    876. 

  876. 	   'deflistItem1'        : '\\item[\a]'          ,
    877. 

  877. 	   'bar1'                : '\n\\hrulefill{}\n'   ,
    878. 

  878. 	   'bar2'                : '\n\\rule{\linewidth}{1mm}\n',
    879. 

  879. 	   'url'                 : '\\url{\a}'                  ,
    880. 

  880. 	   'urlMark'             : '\\textit{\a} (\\url{\a})'   ,
    881. 

  881. 	   'email'               : '\\url{\a}'                  ,
    882. 

  882. 	   'emailMark'           : '\\textit{\a} (\\url{\a})'   ,
    883. 

  883. 	   'img'                 : '\\begin{figure}\\includegraphics{\a}'+\
    884. 

  884. 	                           '\\end{figure}',
    885. 

  885. 	   'tableOpen'           : '\\begin{center}\\begin{tabular}{\a|}',
    886. 

  886. 	   'tableClose'          : '\\end{tabular}\\end{center}',
    887. 

  887. 	   'tableLineOpen'       : '\\hline ' ,
    888. 

  888. 	   'tableLineClose'      : ' \\\\'    ,
    889. 

  889. 	   'tableCellClose'      : ' & '      ,
    890. 

  890. 	   'tableTitleCellOpen'  : '\\textbf{',
    891. 

  891. 	   'tableTitleCellClose' : '} & '     ,
    892. 

  892. 	   'tableColAlignLeft'   : '|l'       ,
    893. 

  893. 	   'tableColAlignRight'  : '|r'       ,
    894. 

  894. 	   'tableColAlignCenter' : '|c'       ,
    895. 

  895. 	   'comment'             : '% \a'     ,
    896. 

  896. 	   'TOC'                 : '\\newpage\\tableofcontents',
    897. 

  897. 	   'EOD'                 : '\\end{document}'
    898. 

  898. 	},
    899. 

  899. 	
    900. 

  900. 	'moin': {
    901. 

  901. 	   'title1'              : '= \a ='        ,
    902. 

  902. 	   'title2'              : '== \a =='      ,
    903. 

  903. 	   'title3'              : '=== \a ==='    ,
    904. 

  904. 	   'title4'              : '==== \a ===='  ,
    905. 

  905. 	   'title5'              : '===== \a =====',
    906. 

  906. 	   'areaPreOpen'         : '{{{'           ,
    907. 

  907. 	   'areaPreClose'        : '}}}'           ,
    908. 

  908. 	   'areaQuoteOpen'       : ' '             ,
    909. 

  909. 	   'fontMonoOpen'        : '{{{'           ,
    910. 

  910. 	   'fontMonoClose'       : '}}}'           ,
    911. 

  911. 	   'fontBoldOpen'        : "'''"           ,
    912. 

  912. 	   'fontBoldClose'       : "'''"           ,
    913. 

  913. 	   'fontItalicOpen'      : "''"            ,
    914. 

  914. 	   'fontItalicClose'     : "''"            ,
    915. 

  915. 	   'fontBolditalicOpen'  : "'''''"         ,
    916. 

  916. 	   'fontBolditalicClose' : "'''''"         ,
    917. 

  917. 	   'fontUnderlineOpen'   : "'''''"         ,
    918. 

  918. 	   'fontUnderlineClose'  : "'''''"         ,
    919. 

  919. 	   'listItem'            : '* '            ,
    920. 

  920. 	   'numlistItem'         : '\a. '          ,
    921. 

  921. 	   'bar1'                : '----'          ,
    922. 

  922. 	   'bar2'                : '----'          ,
    923. 

  923. 	   'url'                 : '[\a]'          ,
    924. 

  924. 	   'urlMark'             : '[\a \a]'       ,
    925. 

  925. 	   'email'               : '[\a]'          ,
    926. 

  926. 	   'emailMark'           : '[\a \a]'       ,
    927. 

  927. 	   'img'                 : '[\a]'          ,
    928. 

  928. 	   'tableLineOpen'       : '||'            ,
    929. 

  929. 	   'tableCellClose'      : '||'            ,
    930. 

  930. 	   'tableTitleCellClose' : '||'
    931. 

  931. 	},
    932. 

  932. 	
    933. 

  933. 	'mgp': {
    934. 

  934. 	   'paragraph'           : '%font "normal", size 5\n'   ,
    935. 

  935. 	   'title1'              : '%page\n\n\a'                ,
    936. 

  936. 	   'title2'              : '%page\n\n\a'                ,
    937. 

  937. 	   'title3'              : '%page\n\n\a'                ,
    938. 

  938. 	   'title4'              : '%page\n\n\a'                ,
    939. 

  939. 	   'title5'              : '%page\n\n\a'                ,
    940. 

  940. 	   'areaPreOpen'         : '\n%font "mono"'             ,
    941. 

  941. 	   'areaPreClose'        : '%font "normal"'             ,
    942. 

  942. 	   'areaQuoteOpen'       : '%prefix "       "'          ,
    943. 

  943. 	   'areaQuoteClose'      : '%prefix "  "'               ,
    944. 

  944. 	   'fontMonoOpen'        : '\n%cont, font "mono"\n'     ,
    945. 

  945. 	   'fontMonoClose'       : '\n%cont, font "normal"\n'   ,
    946. 

  946. 	   'fontBoldOpen'        : '\n%cont, font "normal-b"\n' ,
    947. 

  947. 	   'fontBoldClose'       : '\n%cont, font "normal"\n'   ,
    948. 

  948. 	   'fontItalicOpen'      : '\n%cont, font "normal-i"\n' ,
    949. 

  949. 	   'fontItalicClose'     : '\n%cont, font "normal"\n'   ,
    950. 

  950. 	   'fontBolditalicOpen'  : '\n%cont, font "normal-bi"\n',
    951. 

  951. 	   'fontBolditalicClose' : '\n%cont, font "normal"\n'   ,
    952. 

  952. 	   'fontUnderlineOpen'   : '\n%cont, fore "cyan"\n'     ,
    953. 

  953. 	   'fontUnderlineClose'  : '\n%cont, fore "white"\n'    ,
    954. 

  954. 	   'numlistItem'         : '\a. '                       ,
    955. 

  955. 	   'bar1'                : '%bar "white" 5'             ,
    956. 

  956. 	   'bar2'                : '%pause'                     ,
    957. 

  957. 	   'url'                 : '\n%cont, fore "cyan"\n\a'   +\
    958. 

  958. 	                           '\n%cont, fore "white"\n'    ,
    959. 

  959. 	   'urlMark'             : '\a \n%cont, fore "cyan"\n\a'+\
    960. 

  960. 	                           '\n%cont, fore "white"\n'    ,
    961. 

  961. 	   'email'               : '\n%cont, fore "cyan"\n\a'   +\
    962. 

  962. 	                           '\n%cont, fore "white"\n'    ,
    963. 

  963. 	   'emailMark'           : '\a \n%cont, fore "cyan"\n\a'+\
    964. 

  964. 	                           '\n%cont, fore "white"\n'    ,
    965. 

  965. 	   'img'                 : '\n%center\n%newimage "\a", left\n',
    966. 

  966. 	   'comment'             : '%% \a'                      ,
    967. 

  967. 	   'EOD'                 : '%%EOD'
    968. 

  968. 	},
    969. 

  969. 	
    970. 

  970. 	'man': {
    971. 

  971. 	   'paragraph'           : '.P'     ,
    972. 

  972. 	   'title1'              : '.SH \a' ,
    973. 

  973. 	   'title2'              : '.SS \a' ,
    974. 

  974. 	   'title3'              : '.SS \a' ,
    975. 

  975. 	   'title4'              : '.SS \a' ,
    976. 

  976. 	   'title5'              : '.SS \a' ,
    977. 

  977. 	   'areaPreOpen'         : '.nf'    ,
    978. 

  978. 	   'areaPreClose'        : '.fi\n'  ,
    979. 

  979. 	   'areaQuoteOpen'       : '\n'     ,
    980. 

  980. 	   'areaQuoteClose'      : '\n'     ,
    981. 

  981. 	   'fontBoldOpen'        : '\\fB'   ,
    982. 

  982. 	   'fontBoldClose'       : '\\fP'   ,
    983. 

  983. 	   'fontItalicOpen'      : '\\fI'   ,
    984. 

  984. 	   'fontItalicClose'     : '\\fP'   ,
    985. 

  985. 	   'fontBolditalicOpen'  : '\\fI'   ,
    986. 

  986. 	   'fontBolditalicClose' : '\\fP'   ,
    987. 

  987. 	   'listOpen'            : '\n.nf'  ,  # pre
    988. 

  988. 	   'listClose'           : '.fi\n'  ,
    989. 

  989. 	   'listItem'            : '* '     ,
    990. 

  990. 	   'numlistOpen'         : '\n.nf'  ,  # pre
    991. 

  991. 	   'numlistClose'        : '.fi\n'  ,
    992. 

  992. 	   'numlistItem'         : '\a. '   ,
    993. 

  993. 	   'bar1'                : '\n\n'   ,
    994. 

  994. 	   'bar2'                : '\n\n'   ,
    995. 

  995. 	   'url'                 : '\a'     ,
    996. 

  996. 	   'urlMark'             : '\a (\a)',
    997. 

  997. 	   'email'               : '\a'     ,
    998. 

  998. 	   'emailMark'           : '\a (\a)',
    999. 

  999. 	   'img'                 : '\a'     ,
    1000. 

  1000. 	   'comment'             : '.\\" \a'
    1001. 

  1001. 	},
    1002. 

  1002. 	
    1003. 

  1003. 	'pm6': {
    1004. 

  1004. 	   'paragraph'           : '<@Normal:>'    ,
    1005. 

  1005. 	   'title1'              : '\n<@Title1:>\a',
    1006. 

  1006. 	   'title2'              : '\n<@Title2:>\a',
    1007. 

  1007. 	   'title3'              : '\n<@Title3:>\a',
    1008. 

  1008. 	   'title4'              : '\n<@Title4:>\a',
    1009. 

  1009. 	   'title5'              : '\n<@Title5:>\a',
    1010. 

  1010. 	   'areaPreOpen'         : '<@PreFormat:>' ,
    1011. 

  1011. 	   'areaQuoteOpen'       : '<@Quote:>'     ,
    1012. 

  1012. 	   'fontMonoOpen'        : '<FONT "Lucida Console"><SIZE 9>' ,
    1013. 

  1013. 	   'fontMonoClose'       : '<SIZE$><FONT$>',
    1014. 

  1014. 	   'fontBoldOpen'        : '<B>'           ,
    1015. 

  1015. 	   'fontBoldClose'       : '<P>'           ,
    1016. 

  1016. 	   'fontItalicOpen'      : '<I>'           ,
    1017. 

  1017. 	   'fontItalicClose'     : '<P>'           ,
    1018. 

  1018. 	   'fontBolditalicOpen'  : '<B><I>'        ,
    1019. 

  1019. 	   'fontBolditalicClose' : '<P>'           ,
    1020. 

  1020. 	   'fontUnderlineOpen'   : '<U>'           ,
    1021. 

  1021. 	   'fontUnderlineClose'  : '<P>'           ,
    1022. 

  1022. 	   'listOpen'            : '<@Bullet:>'    ,
    1023. 

  1023. 	   'listItem'            : '\x95	'       ,  # \x95 == ~U
    1024. 

  1024. 	   'numlistOpen'         : '<@Bullet:>'    ,
    1025. 

  1025. 	   'numlistItem'         : '\x95    '      ,
    1026. 

  1026. 	   'bar1'                : '\a'            ,
    1027. 

  1027. 	   'bar2'                : '\a'            ,
    1028. 

  1028. 	   'url'                 : '<U>\a<P>'      ,  # underline
    1029. 

  1029. 	   'urlMark'             : '\a <U>\a<P>'   ,
    1030. 

  1030. 	   'email'               : '\a'            ,
    1031. 

  1031. 	   'emailMark'           : '\a \a'         ,
    1032. 

  1032. 	   'img'                 : '\a'
    1033. 

  1033. 	}
    1034. 

  1034. 	}
    1035. 

  1035. 	
    1036. 

  1036. 	# compose the target tags dictionary
    1037. 

  1037. 	tags = {}
    1038. 

  1038. 	target_tags = alltags[doctype]
    1039. 

  1039. 	for key in keys: tags[key] = ''     # create empty keys
    1040. 

  1040. 	for key in target_tags.keys():
    1041. 

  1041. 		tags[key] = maskEscapeChar(target_tags[key]) # populate
    1042. 

  1042. 	
    1043. 

  1043. 	return tags
    1044. 

  1044. 

  1045. 

  1046. def getRules(doctype):
    1047. 

  1047. 	ret = {}
    1048. 

  1048. 	allrules = [
    1049. 

  1049. 	
    1050. 

  1050. 	 # target rules (ON/OFF)
    1051. 

  1051. 	  'linkable',           # target supports external links
    1052. 

  1052. 	  'tableable',          # target supports tables
    1053. 

  1053. 	  'imglinkable',        # target supports images as links
    1054. 

  1054. 	  'imgalignable',       # target supports image alignment
    1055. 

  1055. 	  'imgasdefterm',       # target supports image as definition term
    1056. 

  1056. 	  'tablealignable',     # target supports table alignment
    1057. 

  1057. 	  'autonumberlist',     # target supports numbered lists natively
    1058. 

  1058. 	  'autonumbertitle',    # target supports numbered titles natively
    1059. 

  1059. 	  'tablecellsplit',     # place delimiters only *between* cells
    1060. 

  1060. 	  'listnotnested',      # lists cannot be nested
    1061. 

  1061. 	  'quotenotnested',     # quotes cannot be nested
    1062. 

  1062. 	  'preareanotescaped',  # don't escape specials in PRE area
    1063. 

  1063. 	  'escapeurl',          # escape special in link URL
    1064. 

  1064. 	  
    1065. 

  1065. 	# target code beautify (ON/OFF)
    1066. 

  1066. 	  'indentprearea',      # add leading spaces to PRE area lines
    1067. 

  1067. 	  'breaktablecell',     # break lines after any table cell
    1068. 

  1068. 	  'breaktablelineopen', # break line after opening table line
    1069. 

  1069. 	  'keepquoteindent',    # don't remove the leading TABs on quotes
    1070. 

  1070. 	
    1071. 

  1071. 	# value settings
    1072. 

  1072. 	  'listmaxdepth',       # maximum depth for lists
    1073. 

  1073. 	  'tablecellaligntype'  # type of table cell align: cell, column
    1074. 

  1074. 	]
    1075. 

  1075. 	
    1076. 

  1076. 	rules = {
    1077. 

  1077. 	  'txt' : {
    1078. 

  1078. 	    'indentprearea':1
    1079. 

  1079. 	    },
    1080. 

  1080. 	  'html': {
    1081. 

  1081. 	    'indentprearea':1,
    1082. 

  1082. 	    'linkable':1,
    1083. 

  1083. 	    'imglinkable':1,
    1084. 

  1084. 	    'imgalignable':1,
    1085. 

  1085. 	    'imgasdefterm':1,
    1086. 

  1086. 	    'autonumberlist':1,
    1087. 

  1087. 	    'tableable':1,
    1088. 

  1088. 	    'breaktablecell':1,
    1089. 

  1089. 	    'breaktablelineopen':1,
    1090. 

  1090. 	    'keepquoteindent':1,
    1091. 

  1091. 	    'tablealignable':1,
    1092. 

  1092. 	    'tablecellaligntype':'cell'
    1093. 

  1093. 	    },
    1094. 

  1094. 	  'sgml': {
    1095. 

  1095. 	    'linkable':1,
    1096. 

  1096. 	    'escapeurl':1,
    1097. 

  1097. 	    'autonumberlist':1,
    1098. 

  1098. 	    'tableable':1,
    1099. 

  1099. 	    'tablecellsplit':1,
    1100. 

  1100. 	    'quotenotnested':1,
    1101. 

  1101. 	    'keepquoteindent':1,
    1102. 

  1102. 	    'tablecellaligntype':'column'
    1103. 

  1103. 	    },
    1104. 

  1104. 	  'mgp' : {
    1105. 

  1105. 	    },
    1106. 

  1106. 	  'tex' : {
    1107. 

  1107. 	    'autonumberlist':1,
    1108. 

  1108. 	    'autonumbertitle':1,
    1109. 

  1109. 	    'tableable':1,
    1110. 

  1110. 	    'tablecellsplit':1,
    1111. 

  1111. 	    'preareanotescaped':1,
    1112. 

  1112. 	    'listmaxdepth':4,
    1113. 

  1113. 	    'tablecellaligntype':'column'
    1114. 

  1114. 	    },
    1115. 

  1115. 	  'moin': {
    1116. 

  1116. 	    'linkable':1,
    1117. 

  1117. 	    'tableable':1
    1118. 

  1118. 	    },
    1119. 

  1119. 	  'man' : {
    1120. 

  1120. 	    'indentprearea':1,
    1121. 

  1121. 	    'listnotnested':1
    1122. 

  1122. 	    },
    1123. 

  1123. 	  'pm6' : {
    1124. 

  1124. 	    }
    1125. 

  1125. 	}
    1126. 

  1126. 	
    1127. 

  1127. 	
    1128. 

  1128. 	# populate return dictionary
    1129. 

  1129. 	myrules = rules[doctype]
    1130. 

  1130. 	for key in allrules      : ret[key] = 0            # reset all
    1131. 

  1131. 	for key in myrules.keys(): ret[key] = myrules[key] # turn ON
    1132. 

  1132. 	return ret
    1133. 

  1133. 

  1134. 

  1135. def getRegexes():
    1136. 

  1136. 	regex = {
    1137. 

  1137. 	# extra at end: (\[(?P<label>\w+)\])?
    1138. 

  1138. 	'title':
    1139. 

  1139. 		re.compile(r'^\s*(?P<id>={1,5})(?P<txt>[^=].*[^=])\1\s*$'),
    1140. 

  1140. 	'numtitle':
    1141. 

  1141. 		re.compile(r'^\s*(?P<id>\+{1,5})(?P<txt>[^+].*[^+])\1\s*$'),
    1142. 

  1142. 	'areaPreOpen':
    1143. 

  1143. 		re.compile(r'^---$'),
    1144. 

  1144. 	'areaPreClose':
    1145. 

  1145. 		re.compile(r'^---$'),
    1146. 

  1146. 	'quote':
    1147. 

  1147. 		re.compile(r'^\t+'),
    1148. 

  1148. 	'1linePre':
    1149. 

  1149. 		re.compile(r'^--- (?=.)'),
    1150. 

  1150. 	'fontMono':
    1151. 

  1151. 		re.compile(r'`([^`]+)`'),
    1152. 

  1152. 	'fontBold':
    1153. 

  1153. 		re.compile(r'\*\*([^\s*].*?)\*\*'),
    1154. 

  1154. 	'fontItalic':
    1155. 

  1155. 		re.compile(r'(^|[^:])//([^ /].*?)//'),
    1156. 

  1156. 	'fontUnderline':
    1157. 

  1157. 		re.compile(r'__([^_].*?)__'), # underline lead/trailing blank
    1158. 

  1158. 	'fontBolditalic':
    1159. 

  1159. 		re.compile(r'\*/([^/].*?)/\*'),
    1160. 

  1160. 	'list':
    1161. 

  1161. 		re.compile(r'^( *)([+-]) ([^ ])'),
    1162. 

  1162. 	'deflist':
    1163. 

  1163. 		re.compile(r'^( *)(=) ([^:]+):'),
    1164. 

  1164. 	'bar':
    1165. 

  1165. 		re.compile(r'^\s*([_=-]{20,})\s*$'),
    1166. 

  1166. 	'table':
    1167. 

  1167. 		re.compile(r'^ *\|\|? '),
    1168. 

  1168. 	'blankline':
    1169. 

  1169. 		re.compile(r'^\s*$'),
    1170. 

  1170. 	'comment':
    1171. 

  1171. 		re.compile(r'^%'),
    1172. 

  1172. 	'raw':
    1173. 

  1173. 		re.compile(r'``(.+?)``')
    1174. 

  1174. 	}
    1175. 

  1175. 	
    1176. 

  1176. 	# special char to place data on TAGs contents  (\a == bell)
    1177. 

  1177. 	regex['x'] = re.compile('\a')
    1178. 

  1178. 	
    1179. 

  1179. 	# %%date [ (formatting) ]
    1180. 

  1180. 	regex['date'] = re.compile(r'%%date\b(\((?P<fmt>.*?)\))?', re.I)
    1181. 

  1181. 	
    1182. 

  1182. 	
    1183. 

  1183. 	### complicated regexes begin here ;)
    1184. 

  1184. 	#
    1185. 

  1185. 	# textual descriptions on --help's style: [...] is optional, | is OR
    1186. 

  1186. 	
    1187. 

  1187. 	
    1188. 

  1188. 	### first, some auxiliar variables
    1189. 

  1189. 	#
    1190. 

  1190. 	
    1191. 

  1191. 	# [image.EXT]
    1192. 

  1192. 	patt_img = r'\[([\w_,.+%$#@!?+~/-]+\.(png|jpe?g|gif|eps|bmp))\]'
    1193. 

  1193. 	
    1194. 

  1194. 	# link things
    1195. 

  1195. 	urlskel = {
    1196. 

  1196. 	  'proto' : r'(https?|ftp|news|telnet|gopher|wais)://',
    1197. 

  1197. 	  'guess' : r'(www[23]?|ftp)\.',    # w/out proto, try to guess
    1198. 

  1198. 	  'login' : r'A-Za-z0-9_.-',        # for ftp://login@domain.com
    1199. 

  1199. 	  'pass'  : r'[^ @]*',              # for ftp://login:password@dom.com
    1200. 

  1200. 	  'chars' : r'A-Za-z0-9%._/~:,=$@-',# %20(space), :80(port)
    1201. 

  1201. 	  'anchor': r'A-Za-z0-9%._-',       # %nn(encoded)
    1202. 

  1202. 	  'form'  : r'A-Za-z0-9/%&=+.,@*_-',# .,@*_-(as is)
    1203. 

  1203. 	  'punct' : r'.,;:!?'
    1204. 

  1204. 	}
    1205. 

  1205. 	
    1206. 

  1206. 	# username [ :password ] @
    1207. 

  1207. 	patt_url_login = r'([%s]+(:%s)?@)?'%(urlskel['login'],urlskel['pass'])
    1208. 

  1208. 	
    1209. 

  1209. 	# [ http:// ] [ username:password@ ] domain.com [ / ]
    1210. 

  1210. 	#     [ #anchor | ?form=data ]
    1211. 

  1211. 	retxt_url = r'\b(%s%s|%s)[%s]+\b/*(\?[%s]+)?(#[%s]+)?'%(
    1212. 

  1212. 	             urlskel['proto'],patt_url_login, urlskel['guess'],
    1213. 

  1213. 	             urlskel['chars'],urlskel['form'],urlskel['anchor'])
    1214. 

  1214. 	
    1215. 

  1215. 	# filename | [ filename ] #anchor
    1216. 

  1216. 	retxt_url_local = r'[%s]+|[%s]*(#[%s]+)'%(
    1217. 

  1217. 	             urlskel['chars'],urlskel['chars'],urlskel['anchor'])
    1218. 

  1218. 	
    1219. 

  1219. 	# user@domain [ ?form=data ]
    1220. 

  1220. 	patt_email = r'\b[%s]+@([A-Za-z0-9_-]+\.)+[A-Za-z]{2,4}\b(\?[%s]+)?'%(
    1221. 

  1221. 	             urlskel['login'],urlskel['form'])
    1222. 

  1222. 	
    1223. 

  1223. 	
    1224. 

  1224. 	# saving for future use
    1225. 

  1225. 	regex['_urlskel'] = urlskel
    1226. 

  1226. 	
    1227. 

  1227. 	### and now the real regexes
    1228. 

  1228. 	#
    1229. 

  1229. 	
    1230. 

  1230. 	regex['email'] = re.compile(patt_email,re.I)
    1231. 

  1231. 	
    1232. 

  1232. 	# email | url
    1233. 

  1233. 	regex['link'] = \
    1234. 

  1234. 		re.compile(r'%s|%s'%(retxt_url,patt_email), re.I)
    1235. 

  1235. 	
    1236. 

  1236. 	# \[ label | imagetag    url | email | filename \]
    1237. 

  1237. 	regex['linkmark'] = \
    1238. 

  1238. 		re.compile(r'\[(?P<label>%s|[^]]+) (?P<link>%s|%s|%s)\]'%(
    1239. 

  1239. 		   patt_img, retxt_url, patt_email, retxt_url_local),
    1240. 

  1240. 		   re.L+re.I)
    1241. 

  1241. 	
    1242. 

  1242. 	# image
    1243. 

  1243. 	regex['img'] = re.compile(patt_img, re.L+re.I)
    1244. 

  1244. 	
    1245. 

  1245. 	# all macros
    1246. 

  1246. 	regex['macro'] = regex['date']
    1247. 

  1247. 	
    1248. 

  1248. 	# special things
    1249. 

  1249. 	regex['special'] = re.compile(r'^%!\s*')
    1250. 

  1250. 	regex['command'] = re.compile(r'(Include)\s*:\s*(.+)\s*$',re.I)
    1251. 

  1251. 	return regex
    1252. 

  1252. ### END OF regex nightmares
    1253. 

  1253. 

  1254. 

  1255. class SubareaMaster:
    1256. 

  1256. 	def __init__(self) : self.x = []
    1257. 

  1257. 	def __call__(self) :
    1258. 

  1258. 		if not self.x: return ''
    1259. 

  1259. 		return self.x[-1]
    1260. 

  1260. 	def add(self, area):
    1261. 

  1261. 		if not self.x or (self.x and self.x[-1] != area):
    1262. 

  1262. 			self.x.append(area)
    1263. 

  1263. 		Debug('subarea ++ (%s): %s' % (area,self.x), 1)
    1264. 

  1264. 	def pop(self, area=None):
    1265. 

  1265. 		if area and self.x[-1] == area: self.x.pop()
    1266. 

  1266. 		Debug('subarea -- (%s): %s' % (area,self.x), 1)
    1267. 

  1267. 

  1268. def doHeader(headers, CONF):
    1269. 

  1269. 	if CONF['noheaders']: return []
    1270. 

  1270. 	doctype = CONF['type']
    1271. 

  1271. 	if not HEADER_TEMPLATE.has_key(doctype):
    1272. 

  1272. 		Error("doheader: Unknow doctype '%s'"%doctype)
    1273. 

  1273. 	
    1274. 

  1274. 	template = string.split(HEADER_TEMPLATE[doctype], '\n')
    1275. 

  1275. 	
    1276. 

  1276. 	head_data = {'STYLE':'', 'ENCODING':''}
    1277. 

  1277. 	for key in head_data.keys():
    1278. 

  1278. 		val = CONF.get(string.lower(key))
    1279. 

  1279. 		if key == 'ENCODING': val = get_encoding_string(val, doctype)
    1280. 

  1280. 		head_data[key] = val
    1281. 

  1281. 	# parse header contents
    1282. 

  1282. 	for i in 0,1,2:
    1283. 

  1283. 		contents = doDateMacro(headers[i])  # expand %%date
    1284. 

  1284. 		# Escapes - on tex, just do it if any \tag{} present
    1285. 

  1285. 		if doctype != 'tex' or \
    1286. 

  1286. 		  (doctype == 'tex' and re.search(r'\\\w+{', contents)):
    1287. 

  1287. 			contents = doEscape(doctype, contents)
    1288. 

  1288. 		
    1289. 

  1289. 		head_data['HEADER%d'%(i+1)] = contents
    1290. 

  1290. 	Debug("Header Data: %s"%head_data, 1)
    1291. 

  1291. 	# scan for empty dictionary keys
    1292. 

  1292. 	# if found, scan template lines for that key reference
    1293. 

  1293. 	# if found, remove the reference
    1294. 

  1294. 	# if there isn't any other key reference on the same line, remove it
    1295. 

  1295. 	for key in head_data.keys():
    1296. 

  1296. 		if head_data.get(key): continue
    1297. 

  1297. 		for line in template:
    1298. 

  1298. 			if string.count(line, '%%(%s)s'%key):
    1299. 

  1299. 				sline = string.replace(line, '%%(%s)s'%key, '')
    1300. 

  1300. 				if not re.search(r'%\([A-Z0-9]+\)s', sline):
    1301. 

  1301. 					template.remove(line)
    1302. 

  1302. 	# populate template with data
    1303. 

  1303. 	template = string.join(template, '\n') % head_data
    1304. 

  1304. 	### post processing
    1305. 

  1305. 	#
    1306. 

  1306. 	# let tex format today
    1307. 

  1307. 	if doctype == 'tex' and head_data['HEADER3'] == currdate:
    1308. 

  1308. 		template = re.sub(r'\\date\{.*?}', r'\date', template)
    1309. 

  1309. 	
    1310. 

  1310. 	return string.split(template, '\n')
    1311. 

  1311. 

  1312. def doDateMacro(line):
    1313. 

  1313. 	re_date = getRegexes()['date']
    1314. 

  1314. 	while re_date.search(line):
    1315. 

  1315. 		m = re_date.search(line)
    1316. 

  1316. 		fmt = m.group('fmt') or ''
    1317. 

  1317. 		dateme = currdate
    1318. 

  1318. 		if fmt: dateme = strftime(fmt,localtime(time()))
    1319. 

  1319. 		line = re_date.sub(dateme,line,1)
    1320. 

  1320. 	return line
    1321. 

  1321. 

  1322. def doCommentLine(txt):
    1323. 

  1323. 	# the -- string ends a sgml/html comment :(
    1324. 

  1324. 	if string.count(TAGS['comment'], '--') and \
    1325. 

  1325. 		string.count(txt, '--'):
    1326. 

  1326. 		txt = re.sub('-(?=-)', r'-\\', txt)
    1327. 

  1327. 	
    1328. 

  1328. 	if TAGS['comment']:
    1329. 

  1329. 		return regex['x'].sub(txt, TAGS['comment'])
    1330. 

  1330. 	return ''
    1331. 

  1331. 

  1332. def doFooter(CONF):
    1333. 

  1333. 	ret = []
    1334. 

  1334. 	doctype = CONF['type']
    1335. 

  1335. 	cmdline = CONF['cmdline']
    1336. 

  1336. 	typename = doctype
    1337. 

  1337. 	if doctype == 'tex': typename = 'LaTeX2e'
    1338. 

  1338. 	ppgd = '%s code generated by txt2tags %s (%s)'%(
    1339. 

  1339. 	        typename,my_version,my_url)
    1340. 

  1340. 	cmdline = 'cmdline: txt2tags %s'%string.join(cmdline[1:], ' ')
    1341. 

  1341. 	ret.append('\n'+doCommentLine(ppgd))
    1342. 

  1342. 	ret.append(doCommentLine(cmdline))
    1343. 

  1343. 	ret.append(TAGS['EOD'])
    1344. 

  1344. 	return ret
    1345. 

  1345. 

  1346. # TODO mgp: any line (header or not) can't begin with % (add a space before)
    1347. 

  1347. def doEscape(doctype,txt):
    1348. 

  1348. 	if doctype in ['html','sgml']:
    1349. 

  1349. 		txt = re.sub('&','&amp;',txt)
    1350. 

  1350. 		txt = re.sub('<','&lt;',txt)
    1351. 

  1351. 		txt = re.sub('>','&gt;',txt)
    1352. 

  1352. 		if doctype == 'sgml':
    1353. 

  1353. 			txt = re.sub('\xff','&yuml;',txt)  # "+y
    1354. 

  1354. 	elif doctype == 'pm6':
    1355. 

  1355. 		txt = re.sub('<','<\#60>',txt)
    1356. 

  1356. 	elif doctype == 'mgp':
    1357. 

  1357. 		txt = re.sub('^%',' %',txt)  # add leading blank to avoid parse
    1358. 

  1358. 	elif doctype == 'man':
    1359. 

  1359. 		txt = re.sub("^([.'])", '\\&\\1',txt)           # command ID
    1360. 

  1360. 		txt = string.replace(txt,ESCCHAR, ESCCHAR+'e')  # \e
    1361. 

  1361. 	elif doctype == 'tex':
    1362. 

  1362. 		txt = string.replace(txt, ESCCHAR, '@@LaTeX-escaping-SUX@@')
    1363. 

  1363. 		txt = re.sub('([#$&%{}])', r'\\\1', txt)
    1364. 

  1364. 		txt = string.replace(txt, '~', maskEscapeChar(r'\~{}'))
    1365. 

  1365. 		txt = string.replace(txt, '^', maskEscapeChar(r'\^{}'))
    1366. 

  1366. 		txt = string.replace(txt, '@@LaTeX-escaping-SUX@@',
    1367. 

  1367. 		                     maskEscapeChar(r'$\backslash$'))
    1368. 

  1368. 		# TIP the _ is escaped at the end
    1369. 

  1369. 	return txt
    1370. 

  1370. 

  1371. def doFinalEscape(doctype, txt):
    1372. 

  1372. 	"Last escapes of each line"
    1373. 

  1373. 	if   doctype == 'pm6' : txt = string.replace(txt,ESCCHAR+'<',r'<\#92><')
    1374. 

  1374. 	elif doctype == 'man' : txt = string.replace(txt, '-', r'\-')
    1375. 

  1375. 	elif doctype == 'tex' : txt = string.replace(txt, '_', r'\_')
    1376. 

  1376. 	elif doctype == 'sgml': txt = string.replace(txt, '[', '&lsqb;')
    1377. 

  1377. 	return txt
    1378. 

  1378. 

  1379. def EscapeCharHandler(action, data):
    1380. 

  1380. 	"Mask/Unmask the Escape Char on the given string"
    1381. 

  1381. 	if not string.strip(data): return data
    1382. 

  1382. 	if action not in ['mask','unmask']:
    1383. 

  1383. 		Error("EscapeCharHandler: Invalid action '%s'"%action)
    1384. 

  1384. 	if action == 'mask': return string.replace(data,'\\',ESCCHAR)
    1385. 

  1385. 	else:                return string.replace(data,ESCCHAR,'\\')
    1386. 

  1386. 

  1387. def maskEscapeChar(data):
    1388. 

  1388. 	"Replace any Escape Char \ with a text mask (Input: str or list)"
    1389. 

  1389. 	if type(data) == type([]):
    1390. 

  1390. 		return map(lambda x: EscapeCharHandler('mask', x), data)
    1391. 

  1391. 	return EscapeCharHandler('mask',data)
    1392. 

  1392. 

  1393. def unmaskEscapeChar(data):
    1394. 

  1394. 	"Undo the Escape char \ masking (Input: str or list)"
    1395. 

  1395. 	if type(data) == type([]):
    1396. 

  1396. 		return map(lambda x: EscapeCharHandler('unmask', x), data)
    1397. 

  1397. 	return EscapeCharHandler('unmask',data)
    1398. 

  1398. 

  1399. def addLineBreaks(list):
    1400. 

  1400. 	"use LB to respect sys.platform"
    1401. 

  1401. 	ret = []
    1402. 

  1402. 	for line in list:
    1403. 

  1403. 		line = string.replace(line,'\n',LB)  # embedded \n's
    1404. 

  1404. 		ret.append(line+LB)                  # add final line break
    1405. 

  1405. 	return ret
    1406. 

  1406. 

  1407. def doPreLine(doctype,line):
    1408. 

  1408. 	"Parsing procedures for preformatted (verbatim) lines"
    1409. 

  1409. 	if not rules['preareanotescaped']: line = doEscape(doctype,line)
    1410. 

  1410. 	if rules['indentprearea']: line = '  '+line
    1411. 

  1411. 	if doctype == 'pm6': line = doFinalEscape(doctype, line)
    1412. 

  1412. 	return line
    1413. 

  1413. 

  1414. def doCloseTable(doctype):
    1415. 

  1415. 	global subarea, tableborder
    1416. 

  1416. 	ret = ''
    1417. 

  1417. 	if rules['tableable']:
    1418. 

  1418. 		if doctype == 'tex' and tableborder:
    1419. 

  1419. 			ret = TAGS['tableLineOpen']+TAGS['tableClose']+'\n'
    1420. 

  1420. 		else:
    1421. 

  1421. 			ret = TAGS['tableClose']+'\n'
    1422. 

  1422. 	else:
    1423. 

  1423. 		ret = TAGS['areaPreClose']
    1424. 

  1424. 	tableborder = 0
    1425. 

  1425. 	subarea.pop('table')
    1426. 

  1426. 	return ret
    1427. 

  1427. 

  1428. def doCloseQuote(howmany=None):
    1429. 

  1429. 	global quotedepth
    1430. 

  1430. 	ret = []
    1431. 

  1431. 	if not howmany: howmany = len(quotedepth)
    1432. 

  1432. 	for i in range(howmany):
    1433. 

  1433. 		quotedepth.pop()
    1434. 

  1434. 		#TODO align open/close tag -> FREE_ALING_TAG = 1 (man not)
    1435. 

  1435. 		ret.append(TAGS['areaQuoteClose'])
    1436. 

  1436. 	
    1437. 

  1437. 	if not quotedepth: subarea.pop('quote')
    1438. 

  1438. 	return string.join(ret,'\n')
    1439. 

  1439. 

  1440. def doCloseList(howmany=None):
    1441. 

  1441. 	global listindent, listids
    1442. 

  1442. 	ret…
    1443.

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