PageRenderTime 60ms CodeModel.GetById 20ms RepoModel.GetById 0ms app.codeStats 0ms

/old/txt2tags-1.5.1.py

http://txt2tags.googlecode.com/
Python | 2341 lines | 2296 code | 17 blank | 28 comment | 10 complexity | 8eae18bda32683fe34ab503ab5290fef 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 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 better, even readable now, but needs more improvements
    21. 

  21. 

  22. # TODO what if %!cmdline with syn error or wrong opts? and if on include?
    23. 

  23. # TODO headers. what is valid: date, !image, !link, !beautifiers, !structs
    24. 

  24. # TODO mgp: any line (header or not) can't begin with % (add a space before)
    25. 

    26. 

  26. import re, string, os, sys, getopt, traceback
    27. 

  27. from time import strftime,time,localtime
    28. 

  28. 

  29. my_url = 'http://txt2tags.sf.net'
    30. 

  30. my_email = 'verde@aurelio.net'
    31. 

  31. my_version = '1.5.1'
    32. 

  32. 

  33. DEBUG = 0   # do not edit here, please use --debug
    34. 

  34. targets = ['txt', 'sgml', 'html', 'pm6', 'mgp', 'moin', 'man', 'tex']
    35. 

  35. FLAGS   = {'noheaders':0,'enumtitle':0 ,'maskemail':0 ,'stdout'  :0,
    36. 

  36.            'toconly'  :0,'toc'      :0 ,'gui'      :0 ,'included':0}
    37. 

  37. OPTIONS = {'toclevel' :3,'style'    :'','type'     :'','outfile' :'',
    38. 

  38.            'split':0, 'lang':''}
    39. 

  39. CONFIG_KEYWORDS = ['encoding', 'style', 'cmdline']
    40. 

  40. CONF = {}
    41. 

  41. regex = {}
    42. 

  42. TAGS = {}
    43. 

  43. rules = {}
    44. 

  44. 

  45. currdate = strftime('%Y%m%d',localtime(time()))    # ISO current date
    46. 

  46. lang = 'english'
    47. 

  47. doctype = outfile = ''
    48. 

  48. STDIN = STDOUT = '-'
    49. 

  49. 

  50. ESCCHAR = '\x00'
    51. 

  51. 

  52. #my_version = my_version + '-beta0505'            # beta!
    53. 

  53. #my_version = my_version + '-dev' + currdate[4:]  # devel!
    54. 

  54. 

  55. # global vars for doClose*()
    56. 

  56. quotedepth = []
    57. 

  57. listindent = []
    58. 

  58. listids = []
    59. 

  59. subarea = None
    60. 

  60. tableborder = 0
    61. 

  61. 

  62. versionstr = "txt2tags version %s <%s>"%(my_version,my_url)
    63. 

  63. usage = """
    64. 

  64. %s
    65. 

  65. 

  66. Usage: txt2tags -t <type> [OPTIONS] file.t2t
    67. 

  67. 

  68.   -t, --type         set target document type. actually supported:
    69. 

  69.                      %s
    70. 

  70. 

  71.   -o, --outfile=FILE set FILE as the output filename ('-' for STDOUT)   	  
    72. 

  72.       --stdout       same as '-o -' or '--outfile -' (deprecated option)
    73. 

  73.   -H, --noheaders    suppress header, title and footer information
    74. 

  74.   -n, --enumtitle    enumerate all title lines as 1, 1.1, 1.1.1, etc
    75. 

  75.       --maskemail    hide email from spam robots. x@y.z turns <x (a) y z>
    76. 

  76. 

  77.       --toc          add TOC (Table of Contents) to target document
    78. 

  78.       --toconly      print document TOC and exit
    79. 

  79.       --toclevel=N   set maximum TOC level (deepness) to N
    80. 

  80. 

  81.       --gui          invoke Graphical Tk Interface
    82. 

  82.       --style=FILE   use FILE as the document style (like Html CSS)
    83. 

  83. 

  84.   -h, --help         print this help information and exit
    85. 

  85.   -V, --version      print program version and exit
    86. 

  86. 

  87. Extra options for HTML target (needs sgml-tools):
    88. 

  88.       --split        split documents. values: 0, 1, 2 (default 0)
    89. 

  89.       --lang         document language (default english)
    90. 

  90. 

  91. By default, converted output is saved to 'file.<type>'.
    92. 

  92. Use --outfile to force an output filename.
    93. 

  93. If input file is '-', reads from STDIN.
    94. 

  94. If outfile is '-', dumps output to STDOUT.\
    95. 

  95. """%(versionstr, re.sub(r"[]'[]",'',repr(targets)))
    96. 

    97. 

  97. 

  98. # here is all the target's templates
    99. 

  99. # you may edit them to fit your needs
    100. 

  100. #  - the %(HEADERn)s strings represent the Header lines
    101. 

  101. #  - use %% to represent a literal %
    102. 

  102. #
    103. 

  103. HEADER_TEMPLATE = {
    104. 

  104.   'txt': """\
    105. 

  105. %(HEADER1)s
    106. 

  106. %(HEADER2)s
    107. 

  107. %(HEADER3)s
    108. 

  108. """,
    109. 

    110. 

  110.   'sgml': """\
    111. 

  111. <!doctype linuxdoc system>
    112. 

  112. <article>
    113. 

  113. <title>%(HEADER1)s
    114. 

  114. <author>%(HEADER2)s
    115. 

  115. <date>%(HEADER3)s
    116. 

  116. """,
    117. 

    118. 

  118.   'html': """\
    119. 

  119. <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
    120. 

  120. <HTML>
    121. 

  121. <HEAD>
    122. 

  122. <META NAME="generator" CONTENT="http://txt2tags.sf.net">
    123. 

  123. <META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=%(ENCODING)s">
    124. 

  124. <LINK REL="stylesheet" TYPE="text/css" HREF="%(STYLE)s">
    125. 

  125. <TITLE>%(HEADER1)s</TITLE>
    126. 

  126. </HEAD><BODY BGCOLOR="white" TEXT="black">
    127. 

  127. <P ALIGN="center"><CENTER><H1>%(HEADER1)s</H1>
    128. 

  128. <FONT SIZE=4>
    129. 

  129. <I>%(HEADER2)s</I><BR>
    130. 

  130. %(HEADER3)s
    131. 

  131. </FONT></CENTER>
    132. 

  132. """,
    133. 

    134. 

  134. 

  135. # TODO man section 1 is hardcoded...
    136. 

  136.   'man': """\
    137. 

  137. .TH "%(HEADER1)s" 1 %(HEADER3)s "%(HEADER2)s"
    138. 

  138. """,
    139. 

    140. 

  140. # TODO style to <HR>
    141. 

  141.   'pm6': """\
    142. 

  142. <PMTags1.0 win><C-COLORTABLE ("Preto" 1 0 0 0)
    143. 

  143. ><@Normal=
    144. 

  144.   <FONT "Times New Roman"><CCOLOR "Preto"><SIZE 11>
    145. 

  145.   <HORIZONTAL 100><LETTERSPACE 0><CTRACK 127><CSSIZE 70><C+SIZE 58.3>
    146. 

  146.   <C-POSITION 33.3><C+POSITION 33.3><P><CBASELINE 0><CNOBREAK 0><CLEADING -0.05>
    147. 

  147.   <GGRID 0><GLEFT 7.2><GRIGHT 0><GFIRST 0><G+BEFORE 7.2><G+AFTER 0>
    148. 

  148.   <GALIGNMENT "justify"><GMETHOD "proportional"><G& "ENGLISH">
    149. 

  149.   <GPAIRS 12><G%% 120><GKNEXT 0><GKWIDOW 0><GKORPHAN 0><GTABS $>
    150. 

  150.   <GHYPHENATION 2 34 0><GWORDSPACE 75 100 150><GSPACE -5 0 25>
    151. 

  151. ><@Bullet=<@-PARENT "Normal"><FONT "Abadi MT Condensed Light">
    152. 

  152.   <GLEFT 14.4><G+BEFORE 2.15><G%% 110><GTABS(25.2 l "")>
    153. 

  153. ><@PreFormat=<@-PARENT "Normal"><FONT "Lucida Console"><SIZE 8><CTRACK 0>
    154. 

  154.   <GLEFT 0><G+BEFORE 0><GALIGNMENT "left"><GWORDSPACE 100 100 100><GSPACE 0 0 0>
    155. 

  155. ><@Title1=<@-PARENT "Normal"><FONT "Arial"><SIZE 14><B>
    156. 

  156.   <GCONTENTS><GLEFT 0><G+BEFORE 0><GALIGNMENT "left">
    157. 

  157. ><@Title2=<@-PARENT "Title1"><SIZE 12><G+BEFORE 3.6>
    158. 

  158. ><@Title3=<@-PARENT "Title1"><SIZE 10><GLEFT 7.2><G+BEFORE 7.2>
    159. 

  159. ><@Title4=<@-PARENT "Title3">
    160. 

  160. ><@Title5=<@-PARENT "Title3">
    161. 

  161. ><@Quote=<@-PARENT "Normal"><SIZE 10><I>>
    162. 

  162. 

  163. %(HEADER1)s
    164. 

  164. %(HEADER2)s
    165. 

  165. %(HEADER3)s
    166. 

  166. """,
    167. 

    168. 

  168.   'mgp': """\
    169. 

  169. #!/usr/X11R6/bin/mgp -t 90
    170. 

  170. %%deffont "normal"    xfont  "utopia-medium-r", charset "iso8859-1"
    171. 

  171. %%deffont "normal-i"  xfont  "utopia-medium-i", charset "iso8859-1"
    172. 

  172. %%deffont "normal-b"  xfont  "utopia-bold-r"  , charset "iso8859-1"
    173. 

  173. %%deffont "normal-bi" xfont  "utopia-bold-i"  , charset "iso8859-1"
    174. 

  174. %%deffont "mono"      xfont "courier-medium-r", charset "iso8859-1"
    175. 

  175. %%default 1 size 5
    176. 

  176. %%default 2 size 8, fore "yellow", font "normal-b", center
    177. 

  177. %%default 3 size 5, fore "white",  font "normal", left, prefix "  "
    178. 

  178. %%tab 1 size 4, vgap 30, prefix "     ", icon arc "red" 40, leftfill
    179. 

  179. %%tab 2 prefix "            ", icon arc "orange" 40, leftfill
    180. 

  180. %%tab 3 prefix "                   ", icon arc "brown" 40, leftfill
    181. 

  181. %%tab 4 prefix "                          ", icon arc "darkmagenta" 40, leftfill
    182. 

  182. %%tab 5 prefix "                                ", icon arc "magenta" 40, leftfill
    183. 

  183. %%%%------------------------- end of headers -----------------------------
    184. 

  184. %%page
    185. 

  185. 

  186. 

  187. 

  188. 

  189. 

  190. %%size 10, center, fore "yellow"
    191. 

  191. %(HEADER1)s
    192. 

  192. 

  193. %%font "normal-i", size 6, fore "white", center
    194. 

  194. %(HEADER2)s
    195. 

  195. 

  196. %%font "mono", size 7, center
    197. 

  197. %(HEADER3)s
    198. 

  198. """,
    199. 

    200. 

  200. # TODO please, improve me!
    201. 

  201.   'moin': """\
    202. 

  202. %(HEADER1)s
    203. 

  203. %(HEADER2)s
    204. 

  204. %(HEADER3)s
    205. 

  205. """,
    206. 

    207. 

  207.   'tex': \
    208. 

  208. r"""\documentclass[11pt,a4paper]{article}
    209. 

  209. \usepackage{amsfonts,amssymb,graphicx,url}
    210. 

  210. \usepackage[%(ENCODING)s]{inputenc}  %% char encoding
    211. 

  211. \pagestyle{plain}   %% do page numbering ('empty' turns off)
    212. 

  212. \frenchspacing      %% no aditional spaces after periods
    213. 

  213. \setlength{\parskip}{8pt}\parindent=0pt  %% no paragraph indentation
    214. 

  214. %% uncomment next line for fancy PDF output on Adobe Acrobat Reader
    215. 

  215. %%\usepackage[pdfstartview=FitV,colorlinks=true,bookmarks=true]{hyperref}
    216. 

  216. 

  217. \title{%(HEADER1)s}
    218. 

  218. \author{%(HEADER2)s}
    219. 

  219. \begin{document}
    220. 

  220. \date{%(HEADER3)s}
    221. 

  221. \maketitle
    222. 

  222. """
    223. 

  223. }
    224. 

  224. 

  225. #-----------------------------------------------------------------------
    226. 

  226. 

  227. def Quit(msg, exitcode=0): print msg ; sys.exit(exitcode)
    228. 

  228. def Error(msg): print "ERROR: %s"%msg ; sys.exit()
    229. 

  229. def Debug(msg,i=0,linenr=None):
    230. 

  230. 	if i > DEBUG: return
    231. 

  231. 	if linenr is not None:
    232. 

  232. 		print "(%d) %04d:%s"%(i,linenr,msg)
    233. 

  233. 	else:
    234. 

  234. 		print "(%d) %s"%(i,msg)
    235. 

  235. def Readfile(file):
    236. 

  236. 	if file == '-':
    237. 

  237. 		try: data = sys.stdin.readlines()
    238. 

  238. 		except: Error('You must feed me with data on STDIN!')
    239. 

  239. 	else:
    240. 

  240. 		try: f = open(file); data = f.readlines() ; f.close()
    241. 

  241. 		except: Error("Cannot read file:\n    %s"%file)
    242. 

  242. 	return data
    243. 

  243. def Savefile(file, contents):
    244. 

  244. 	try: f = open(file, 'w')
    245. 

  245. 	except: Error("Cannot open file for writing:\n    %s"%file)
    246. 

  246. 	if type(contents) == type([]): doit = f.writelines
    247. 

  247. 	else: doit = f.write
    248. 

  248. 	doit(contents) ; f.close()
    249. 

  249. 

  250. def ParseConfig(text='',name='',kind=''):
    251. 

  251. 	ret = {}
    252. 

  252. 	if not text: return ret
    253. 

  253. 	re_name = name or '[a-z]+'
    254. 

  254. 	re_kind = kind or '[a-z]*'
    255. 

  255. 	regex = re.compile("""
    256. 

  256. 	  ^%%!\s*               # leading id with opt spaces
    257. 

  257. 	  (?P<name>%s)          # config name 
    258. 

  258. 	  (\((?P<kind>%s)\))?   # optional config kind inside ()
    259. 

  259. 	  \s*:\s*               # key:value delimiter with opt spaces
    260. 

  260. 	  (?P<value>.+?)        # config value
    261. 

  261. 	  \s*$                  # rstrip() spaces and hit EOL
    262. 

  262. 	  """%(re_name,re_kind), re.I+re.VERBOSE)
    263. 

  263. 	match = regex.match(text)
    264. 

  264. 	if match: ret = {
    265. 

  265. 	  'name' :string.lower(match.group('name') or ''),
    266. 

  266. 	  'kind' :string.lower(match.group('kind') or ''),
    267. 

  267. 	  'value':match.group('value') }
    268. 

  268. 	return ret
    269. 

  269. 

  270. 

  271. class Cmdline:
    272. 

  272. 	def __init__(self, cmdline=[]):
    273. 

  273. 		self.conf = {}
    274. 

  274. 		self.cmdline = cmdline
    275. 

  275. 		self.cmdline_conf = {}
    276. 

  276. 		self.dft_options = OPTIONS
    277. 

  277. 		self.dft_flags   = FLAGS
    278. 

  278. 		self.all_options = self.dft_options.keys()
    279. 

  279. 		self.all_flags   = self.dft_flags.keys()
    280. 

  280. 		self.defaults = self._get_empty_conf()
    281. 

  281. 		if cmdline: self.parse()
    282. 

  282. 	
    283. 

  283. 	#TODO protect quotes contents
    284. 

  284. 	def _tokenize(self, cmd_string):
    285. 

  285. 		return string.split(cmd_string)
    286. 

  286. 	
    287. 

  287. 	def parse(self):
    288. 

  288. 		"return a dic with all options:value found"
    289. 

  289. 		if not self.cmdline: return {}
    290. 

  290. 		Debug("cmdline: %s"%self.cmdline, 1)
    291. 

  291. 		options = {'infile': '', 'infiles':''}
    292. 

  292. 		# compose valid options list
    293. 

  293. 		longopts = ['help','version'] + self.all_flags + \
    294. 

  294. 		           map(lambda x:x+'=', self.all_options) # add =
    295. 

  295. 		cmdline = self.cmdline[1:]           # del prog name  
    296. 

  296. 		# get cmdline options
    297. 

  297. 		try: (opt, args) = getopt.getopt(cmdline, 'hVnHt:o:', longopts)
    298. 

  298. 		except getopt.GetoptError:
    299. 

  299. 			Error('Bad option or missing argument (try --help)')
    300. 

  300. 		# get infile, if any
    301. 

  301. 		if args:
    302. 

  302. 			options['infile'] = args[0]
    303. 

  303. 			options['infiles'] = args  # multi
    304. 

  304. 		# parse all options
    305. 

  305. 		for name,val in opt:
    306. 

  306. 			if   name in ['-h','--help'   ]: Quit(usage)
    307. 

  307. 			elif name in ['-V','--version']: Quit(versionstr)
    308. 

  308. 			elif name in ['-t','--type'     ]: options['type'] = val
    309. 

  309. 			elif name in ['-o','--outfile'  ]: options['outfile'] = val
    310. 

  310. 			elif name in ['-n','--enumtitle']: options['enumtitle'] = 1
    311. 

  311. 			elif name in ['-H','--noheaders']: options['noheaders'] = 1
    312. 

  312. 			else: options[name[2:]] = val  # del --
    313. 

  313. 		# save results
    314. 

  314. 		Debug("cmdline arguments: %s"%options, 1)
    315. 

  315. 		self.cmdline_conf = options
    316. 

  316. 	
    317. 

  317. 	def compose(self, conf):
    318. 

  318. 		"compose cmdline from CONF dict"
    319. 

  319. 		#TODO if toconly, del noheaders, del toc, del toclevel
    320. 

  320. 		args = []
    321. 

  321. 		if conf.has_key('type'):     # the first
    322. 

  322. 			args.extend(['-t', conf['type']]) ; 
    323. 

  323. 			del conf[type]
    324. 

  324. 		for key in conf.keys():
    325. 

  325. 			if key in ['infile','infiles']: continue
    326. 

  326. 			args.extend(['--'+key, conf[key]])
    327. 

  327. 		if conf.has_key('infiles'):  # the last
    328. 

  328. 			args.extend(conf['infiles'])
    329. 

  329. 		return string.join(args, ' ')
    330. 

  330. 	
    331. 

  331. 	def merge(self, extraopts=''):
    332. 

  332. 		"insert cmdline portion BEFORE current cmdline"
    333. 

  333. 		if not extraopts: return
    334. 

  334. 		if type(extraopts) == type(''):
    335. 

  335. 			extraopts = self._tokenize(extraopts)
    336. 

  336. 		if not self.cmdline: self.cmdline = extraopts
    337. 

  337. 		else: self.cmdline = ['t2t-merged'] +extraopts +self.cmdline[1:]
    338. 

  338. 		self.parse()
    339. 

  339. 	
    340. 

  340. 	def _get_outfile_name(self, conf):
    341. 

  341. 		"dirname is the same for {in,out}file"
    342. 

  342. 		infile = conf['infile']
    343. 

  343. 		if not infile: return ''
    344. 

  344. 		if infile == STDIN or conf['stdout']:
    345. 

  345. 			outfile = STDOUT
    346. 

  346. 		else:
    347. 

  347. 			basename = re.sub('\.(txt|t2t)$','',infile)
    348. 

  348. 			outfile = "%s.%s"%(basename, conf['type'])
    349. 

  349. 		Debug(" infile: '%s'"%infile , 1)
    350. 

  350. 		Debug("outfile: '%s'"%outfile, 1)
    351. 

  351. 		return outfile
    352. 

  352. 	
    353. 

  353. 	def _sanity(self, dic):
    354. 

  354. 		"basic cmdline syntax checkings"
    355. 

  355. 		if not dic: return {}
    356. 

  356. 		if not dic['infile'] or not dic['type']:
    357. 

  357. 			Quit(usage, 1)                  # no filename/doctype
    358. 

  358. 		if not targets.count(dic['type']):      # check target
    359. 

  359. 			Error("Invalid document type '%s' (try --help)"%(
    360. 

  360. 			       dic['type']))
    361. 

  361. 		if len(dic['infiles']) > 1 and dic['outfile']: # -o FILE *.t2t
    362. 

  362. 			Error("--outfile can't be used with multiple files")
    363. 

  363. 		for opt in self.all_options:            # check numeric options
    364. 

  364. 			opttype = type(self.dft_options[opt])
    365. 

  365. 			if dic.get(opt) and opttype == type(9):
    366. 

  366. 				try: dic[opt] = int(dic.get(opt)) # save
    367. 

  367. 				except: Error('--%s value must be a number'%opt)
    368. 

  368. 		if dic['split'] not in [0,1,2]:         # check split level
    369. 

  369. 			Error('Option --split must be 0, 1 or 2')
    370. 

  370. 		return dic
    371. 

  371. 	
    372. 

  372. 	def merge_conf(self, newconfs={}):
    373. 

  373. 		"include Config Area settings into self.conf"
    374. 

  374. 		if not self.conf: self.get_conf()
    375. 

  375. 		if not newconfs: return self.conf
    376. 

  376. 		for key in newconfs.keys():
    377. 

  377. 			if key == 'cmdline': continue   # already done
    378. 

  378. 			# just update if still 'virgin'
    379. 

  379. 			if self.conf.has_key(key) and \
    380. 

  380. 			   self.conf[key] == self.defaults[key]:
    381. 

  381. 				self.conf[key] = newconfs[key]
    382. 

  382. 			# add new
    383. 

  383. 			if not self.conf.has_key(key):
    384. 

  384. 				self.conf[key] = newconfs[key]
    385. 

  385. 		
    386. 

  386. 		Debug("Merged CONF: %s"%self.conf, 1)
    387. 

  387. 		return self.conf
    388. 

  388. 	
    389. 

  389. 	def _get_empty_conf(self):
    390. 

  390. 		econf = self.dft_options.copy()
    391. 

  391. 		for k in self.dft_flags.keys(): econf[k] = self.dft_flags[k]
    392. 

  392. 		return econf
    393. 

  393. 	
    394. 

  394. 	def get_conf(self):
    395. 

  395. 		"set vars and flags according to options dic"
    396. 

  396. 		if not self.cmdline_conf:
    397. 

  397. 			if not self.cmdline: return {}
    398. 

  398. 			self.parse()
    399. 

  399. 		dic = self.cmdline_conf
    400. 

  400. 		conf = self.defaults.copy()
    401. 

  401. 		
    402. 

  402. 		## store flags & options
    403. 

  403. 		for flag in self.all_flags:
    404. 

  404. 			if dic.has_key(flag): conf[flag] = 1
    405. 

  405. 		for opt in self.all_options + ['infile', 'infiles']:
    406. 

  406. 			if dic.has_key(opt): conf[opt] = dic.get(opt)
    407. 

  407. 		
    408. 

  408. 		if not conf['type'] and conf['toconly']: conf['type'] = 'txt'
    409. 

  409. 		conf = self._sanity(conf)
    410. 

  410. 		
    411. 

  411. 		## some gotchas for specific issues
    412. 

  412. 		doctype = conf['type']
    413. 

  413. 		infile = conf['infile']
    414. 

  414. 		
    415. 

  415. 		# toconly is stronger than others
    416. 

  416. 		if conf['toconly']:
    417. 

  417. 			conf['noheaders'] = 1
    418. 

  418. 			conf['stdout'] = 1
    419. 

  419. 			conf['toc'] = 0
    420. 

  420. 			conf['split'] = 0
    421. 

  421. 			conf['toclevel'] = self.dft_options['toclevel']
    422. 

  422. 		
    423. 

  423. 		# split: just HTML, no stdout, 1st do a sgml, then sgml2html
    424. 

  424. 		if conf['split']:
    425. 

  425. 			if doctype != 'html': conf['split'] = 0
    426. 

  426. 			else: conf['stdout'] = 0 ; conf['type'] = 'sgml' 
    427. 

  427. 		
    428. 

  428. 		outfile = conf['outfile'] or self._get_outfile_name(conf)
    429. 

  429. 		
    430. 

  430. 		# final checkings
    431. 

  431. 		if conf['split'] and outfile == STDOUT:
    432. 

  432. 			Error('--split: You must provide a FILE (not STDIN)')
    433. 

  433. 		if infile == outfile and outfile != STDOUT:
    434. 

  434. 			Error("SUICIDE WARNING!!!  (see --outfile)\n  source"+\
    435. 

  435. 			      " and target files has the same name: "+outfile)
    436. 

  436. 		### author's note: "yes, i've got my sample.t2t file deleted
    437. 

  437. 		### before add this test... :/"
    438. 

  438. 		
    439. 

  439. 		conf['outfile'] = outfile
    440. 

  440. 		conf['cmdline'] = self.cmdline
    441. 

  441. 		Debug("CONF data: %s\n"%conf, 1)
    442. 

  442. 		self.conf = conf
    443. 

  443. 		return self.conf
    444. 

  444. #		
    445. 

  445. ### End of Cmdline class
    446. 

  446. 

  447. 

  448. 

  449. 

  450. class Proprierties:
    451. 

  451. 	def __init__(self, filename=''):
    452. 

  452. 		self.buffer = ['']   # text start at pos 1
    453. 

  453. 		self.areas = ['head','conf','body']
    454. 

  454. 		self.arearef = []
    455. 

  455. 		self.headers = ['','','']
    456. 

  456. 		self.config = self.get_empty_config()
    457. 

  457. 		self.lastline = 0
    458. 

  458. 		self.filename = filename
    459. 

  459. 		self.conflines = []
    460. 

  460. 		self.bodylines = []
    461. 

  461. 		if filename:
    462. 

  462. 			self.read_file(filename)
    463. 

  463. 			self.find_areas()
    464. 

  464. 			self.set_headers()
    465. 

  465. 			self.set_config()
    466. 

  466. 	
    467. 

  467. 	def read_file(self, file):
    468. 

  468. 		lines = Readfile(file)
    469. 

  469. 		if not lines: Error('Empty file! %s'%file)
    470. 

  470. 		self.buffer.extend(lines)
    471. 

  471. 	
    472. 

  472. 	def get_empty_config(self):
    473. 

  473. 		empty = {}
    474. 

  474. 		for key in CONFIG_KEYWORDS: empty[key] = ''
    475. 

  475. 		return empty
    476. 

  476. 	
    477. 

  477. 	def find_areas(self):
    478. 

  478. 		"Run through buffer and identify head/conf/body areas"
    479. 

  479. 		buf = self.buffer ; ref = [1,4,0]       # defaults
    480. 

  480. 		if not string.strip(buf[1]):            # no header
    481. 

  481. 			ref[0] = 0 ; ref[1] = 2
    482. 

  482. 		for i in range(ref[1],len(buf)):        # find body init
    483. 

  483. 			if string.strip(buf[i]) and buf[i][0] != '%':
    484. 

  484. 				ref[2] = i ; break      # !blank, !comment
    485. 

  485. 			if ParseConfig(buf[i], 'include', 'verb|body|'):
    486. 

  486. 				ref[2] = i ; break      # %!include
    487. 

  487. 		if ref[1] == ref[2]: ref[1] = 0         # no conf area
    488. 

  488. 		for i in 0,1,2:                         # del !existent
    489. 

  489. 			if not ref[i]: self.areas[i] = ''
    490. 

  490. 		self.arearef = ref                      # save results
    491. 

  491. 		self.lastline = len(self.buffer)-1
    492. 

  492. 		Debug('Head,Conf,Body start line: %s'%ref, 1)
    493. 

  493. 		# store CONF and BODY lines found
    494. 

  494. 		cfgend = ref[2] or len(buf)
    495. 

  495. 		self.conflines = buf[ref[1]:cfgend]
    496. 

  496. 		if ref[2]: self.bodylines = buf[ref[2]:]
    497. 

  497. 	
    498. 

  498. 	
    499. 

  499. 	def set_headers(self):
    500. 

  500. 		"Extract and save headers contents"
    501. 

  501. 		if not self.arearef: self.find_areas()
    502. 

  502. 		if not self.areas.count('head'): return
    503. 

  503. 		if self.lastline < 3:
    504. 

  504. 			#TODO on gui this checking is !working
    505. 

  505. 			Error(
    506. 

  506. 			"Premature end of Headers on '%s'."%self.filename +\
    507. 

  507. 			'\n\nFile has %s line(s), but '%self.lastline     +\
    508. 

  508. 			'Headers should be composed by 3 lines. '         +\
    509. 

  509. 			'\nMaybe you should left the first line blank? '  +\
    510. 

  510. 			'(for no headers)')
    511. 

  511. 		for i in 0,1,2:
    512. 

  512. 			self.headers[i] = string.strip(self.buffer[i+1])
    513. 

  513. 		Debug("Headers found: %s"%self.headers, 1, i+1)
    514. 

  514. 	
    515. 

  515. 	def set_config(self):
    516. 

  516. 		"Extract and save config contents (including includes)"
    517. 

  517. 		if not self.arearef: self.find_areas()
    518. 

  518. 		if not self.areas.count('conf'): return
    519. 

  519. 		keywords = string.join(CONFIG_KEYWORDS, '|')
    520. 

  520. 		linenr = self.arearef[1]  # for debug messages
    521. 

  521. 		for line in self.conflines:
    522. 

  522. 			linenr = linenr + 1
    523. 

  523. 			if len(line) < 3: continue
    524. 

  524. 			if line[:2] != '%!': continue
    525. 

  525. 			cfg = ParseConfig(line, name=keywords)
    526. 

  526. 			if not cfg:
    527. 

  527. 				Debug('Bogus Config Line',1,linenr)
    528. 

  528. 				continue
    529. 

  529. 			key, val = cfg['name'], cfg['value']
    530. 

  530. 			self.config[key] = val
    531. 

  531. 			Debug("Found config '%s', value '%s'"%(
    532. 

  532. 			       key,val),1,linenr)
    533. 

  533. 

  534. 

  535. def get_file_body(file):
    536. 

  536. 	"Returns all the document BODY lines (including includes)"
    537. 

  537. 	prop = Proprierties()
    538. 

  538. 	prop.read_file(file)
    539. 

  539. 	prop.find_areas()
    540. 

  540. 	return prop.bodylines
    541. 

  541. 

  542. 

  543. def finish_him(outlist, CONF):
    544. 

  544. 	"Writing output to screen or file"
    545. 

  545. 	outfile = CONF['outfile']
    546. 

  546. 	outlist = unmaskEscapeChar(outlist)
    547. 

  547. 	if outfile == STDOUT:
    548. 

  548. 		for line in outlist: print line
    549. 

  549. 	else:
    550. 

  550. 		Savefile(outfile, addLineBreaks(outlist))
    551. 

  551. 		if not CONF['gui']: print 'wrote %s'%(outfile)
    552. 

  552. 	
    553. 

  553. 	if CONF['split']:
    554. 

  554. 		print "--- html..."
    555. 

  555. 		sgml2html = 'sgml2html -s %s -l %s %s'%(
    556. 

  556. 		            CONF['split'],CONF['lang'] or lang,outfile)
    557. 

  557. 		print "Running system command:", sgml2html
    558. 

  558. 		os.system(sgml2html)
    559. 

  559. 

  560. 

  561. def toc_maker(toc, conf):
    562. 

  562. 	"Compose TOC list 'by hand'"
    563. 

  563. 	# TOC is a tag, so there's nothing to do here
    564. 

  564. 	if TAGS['TOC']: return []
    565. 

  565. 	# toc is a valid t2t marked text (list type), that is converted
    566. 

  566. 	if conf['toc'] or conf['toconly']:
    567. 

  567. 		fakeconf = conf.copy()
    568. 

  568. 		fakeconf['noheaders'] = 1
    569. 

  569. 		fakeconf['toconly']   = 0
    570. 

  570. 		fakeconf['maskemail'] = 0
    571. 

  571. 		toc,foo = convert(toc, fakeconf)
    572. 

  572. 	# TOC between bars (not for --toconly)
    573. 

  573. 	if conf['toc']:
    574. 

  574. 		para = TAGS['paragraph']
    575. 

  575. 		tocbar = [para, regex['x'].sub('-'*72,TAGS['bar1']), para]
    576. 

  576. 		toc = tocbar + toc + tocbar
    577. 

  577. 	return toc
    578. 

  578. 

  579. 

  580. # set the Line Break across platforms
    581. 

  581. LB = '\n'                                   # default
    582. 

  582. if   sys.platform[:3] == 'win': LB = '\r\n'
    583. 

  583. #elif sys.platform[:3] == 'cyg': LB = '\r\n' # not sure if it's best :(
    584. 

  584. elif sys.platform[:3] == 'mac': LB = '\r'
    585. 

  585. 

  586. 

  587. def getTags(doctype):
    588. 

  588. 	keys = [
    589. 

  589. 	'paragraph','title1','title2','title3','title4','title5',
    590. 

  590. 	'areaPreOpen','areaPreClose',
    591. 

  591. 	'areaQuoteOpen','areaQuoteClose',
    592. 

  592. 	'fontMonoOpen','fontMonoClose',
    593. 

  593. 	'fontBoldOpen','fontBoldClose',
    594. 

  594. 	'fontItalicOpen','fontItalicClose',
    595. 

  595. 	'fontBolditalicOpen','fontBolditalicClose',
    596. 

  596. 	'fontUnderlineOpen','fontUnderlineClose',
    597. 

  597. 	'listOpen','listClose','listItem',
    598. 

  598. 	'numlistOpen','numlistClose','numlistItem',
    599. 

  599. 	'deflistOpen','deflistClose','deflistItem1','deflistItem2',
    600. 

  600. 	'bar1','bar2',
    601. 

  601. 	'url','urlMark','email','emailMark',
    602. 

  602. 	'img','imgsolo',
    603. 

  603. 	'tableOpen','tableClose','tableLineOpen','tableLineClose',
    604. 

  604. 	'tableCellOpen','tableCellClose',
    605. 

  605. 	'tableTitleCellOpen','tableTitleCellClose',
    606. 

  606. 	'anchor','comment','TOC',
    607. 

  607. 	'EOD'
    608. 

  608. 	]
    609. 

  609. 	
    610. 

  610. 	alltags = {
    611. 

  611. 	
    612. 

  612. 	'txt': {
    613. 

  613. 	   'title1'              : '  \a'      ,
    614. 

  614. 	   'title2'              : '\t\a'      ,
    615. 

  615. 	   'title3'              : '\t\t\a'    ,
    616. 

  616. 	   'title4'              : '\t\t\t\a'  ,
    617. 

  617. 	   'title5'              : '\t\t\t\t\a',
    618. 

  618. 	   'areaQuoteOpen'       : '    '      ,
    619. 

  619. 	   'listItem'            : '- '        ,
    620. 

  620. 	   'numlistItem'         : '\a. '      ,
    621. 

  621. 	   'bar1'                : '\a'        ,
    622. 

  622. 	   'bar2'                : '\a'        ,
    623. 

  623. 	   'url'                 : '\a'        ,
    624. 

  624. 	   'urlMark'             : '\a (\a)'   ,
    625. 

  625. 	   'email'               : '\a'        ,
    626. 

  626. 	   'emailMark'           : '\a (\a)'   ,
    627. 

  627. 	   'img'                 : '[\a]'      ,
    628. 

  628. 	},
    629. 

  629. 	
    630. 

  630. 	'html': {
    631. 

  631. 	   'paragraph'           : '<P>'            ,
    632. 

  632. 	   'title1'              : '<H1>\a</H1>'    ,
    633. 

  633. 	   'title2'              : '<H2>\a</H2>'    ,
    634. 

  634. 	   'title3'              : '<H3>\a</H3>'    ,
    635. 

  635. 	   'title4'              : '<H4>\a</H4>'    ,
    636. 

  636. 	   'title5'              : '<H5>\a</H5>'    ,
    637. 

  637. 	   'areaPreOpen'         : '<PRE>'          ,
    638. 

  638. 	   'areaPreClose'        : '</PRE>'         ,
    639. 

  639. 	   'areaQuoteOpen'       : '<BLOCKQUOTE>'   ,
    640. 

  640. 	   'areaQuoteClose'      : '</BLOCKQUOTE>'  ,
    641. 

  641. 	   'fontMonoOpen'        : '<CODE>'         ,
    642. 

  642. 	   'fontMonoClose'       : '</CODE>'        ,
    643. 

  643. 	   'fontBoldOpen'        : '<B>'            ,
    644. 

  644. 	   'fontBoldClose'       : '</B>'           ,
    645. 

  645. 	   'fontItalicOpen'      : '<I>'            ,
    646. 

  646. 	   'fontItalicClose'     : '</I>'           ,
    647. 

  647. 	   'fontBolditalicOpen'  : '<B><I>'         ,
    648. 

  648. 	   'fontBolditalicClose' : '</I></B>'       ,
    649. 

  649. 	   'fontUnderlineOpen'   : '<U>'            ,
    650. 

  650. 	   'fontUnderlineClose'  : '</U>'           ,
    651. 

  651. 	   'listOpen'            : '<UL>'           ,
    652. 

  652. 	   'listClose'           : '</UL>'          ,
    653. 

  653. 	   'listItem'            : '<LI>'           ,
    654. 

  654. 	   'numlistOpen'         : '<OL>'           ,
    655. 

  655. 	   'numlistClose'        : '</OL>'          ,
    656. 

  656. 	   'numlistItem'         : '<LI>'           ,
    657. 

  657. 	   'deflistOpen'         : '<DL>'           ,
    658. 

  658. 	   'deflistClose'        : '</DL>'          ,
    659. 

  659. 	   'deflistItem1'        : '<DT>\a</DT>'    ,
    660. 

  660. 	   'deflistItem2'        : '<DD>'           ,
    661. 

  661. 	   'bar1'                : '<HR NOSHADE SIZE=1>'        ,
    662. 

  662. 	   'bar2'                : '<HR NOSHADE SIZE=5>'        ,
    663. 

  663. 	   'url'                 : '<A HREF="\a">\a</A>'        ,
    664. 

  664. 	   'urlMark'             : '<A HREF="\a">\a</A>'        ,
    665. 

  665. 	   'email'               : '<A HREF="mailto:\a">\a</A>' ,
    666. 

  666. 	   'emailMark'           : '<A HREF="mailto:\a">\a</A>' ,
    667. 

  667. 	   'img'                 : '<IMG ALIGN="\a" SRC="\a" BORDER="0">',
    668. 

  668. 	   'imgsolo'             : '<P ALIGN="center">\a</P>'   ,
    669. 

  669. 	   'tableOpen'           : '<table\a cellpadding=4 border=\a>',
    670. 

  670. 	   'tableClose'          : '</table>'       ,
    671. 

  671. 	   'tableLineOpen'       : '<tr>'           ,
    672. 

  672. 	   'tableLineClose'      : '</tr>'          ,
    673. 

  673. 	   'tableCellOpen'       : '<td\a>'         ,
    674. 

  674. 	   'tableCellClose'      : '</td>'          ,
    675. 

  675. 	   'tableTitleCellOpen'  : '<th>'           ,
    676. 

  676. 	   'tableTitleCellClose' : '</th>'          ,
    677. 

  677. 	   'tableAlignLeft'      : ''               ,
    678. 

  678. 	   'tableAlignCenter'    : ' align="center"',
    679. 

  679. 	   'tableCellAlignLeft'  : ''               ,
    680. 

  680. 	   'tableCellAlignRight' : ' align="right"' ,
    681. 

  681. 	   'tableCellAlignCenter': ' align="center"',
    682. 

  682. 	   'anchor'              : '<a name="\a">'  ,
    683. 

  683. 	   'comment'             : '<!-- \a -->'    ,
    684. 

  684. 	   'EOD'                 : '</BODY></HTML>'
    685. 

  685. 	},
    686. 

  686. 	
    687. 

  687. 	'sgml': {
    688. 

  688. 	   'paragraph'           : '<p>'                ,
    689. 

  689. 	   'title1'              : '<sect>\a<p>'        ,
    690. 

  690. 	   'title2'              : '<sect1>\a<p>'       ,
    691. 

  691. 	   'title3'              : '<sect2>\a<p>'       ,
    692. 

  692. 	   'title4'              : '<sect3>\a<p>'       ,
    693. 

  693. 	   'title5'              : '<sect4>\a<p>'       ,
    694. 

  694. 	   'areaPreOpen'         : '<tscreen><verb>'    ,
    695. 

  695. 	   'areaPreClose'        : '</verb></tscreen>'  ,
    696. 

  696. 	   'areaQuoteOpen'       : '<quote>'            ,
    697. 

  697. 	   'areaQuoteClose'      : '</quote>'           ,
    698. 

  698. 	   'fontMonoOpen'        : '<tt>'               ,
    699. 

  699. 	   'fontMonoClose'       : '</tt>'              ,
    700. 

  700. 	   'fontBoldOpen'        : '<bf>'               ,
    701. 

  701. 	   'fontBoldClose'       : '</bf>'              ,
    702. 

  702. 	   'fontItalicOpen'      : '<em>'               ,
    703. 

  703. 	   'fontItalicClose'     : '</em>'              ,
    704. 

  704. 	   'fontBolditalicOpen'  : '<bf><em>'           ,
    705. 

  705. 	   'fontBolditalicClose' : '</em></bf>'         ,
    706. 

  706. 	   'fontUnderlineOpen'   : '<bf><em>'           ,
    707. 

  707. 	   'fontUnderlineClose'  : '</em></bf>'         ,
    708. 

  708. 	   'listOpen'            : '<itemize>'          ,
    709. 

  709. 	   'listClose'           : '</itemize>'         ,
    710. 

  710. 	   'listItem'            : '<item>'             ,
    711. 

  711. 	   'numlistOpen'         : '<enum>'             ,
    712. 

  712. 	   'numlistClose'        : '</enum>'            ,
    713. 

  713. 	   'numlistItem'         : '<item>'             ,
    714. 

  714. 	   'deflistOpen'         : '<descrip>'          ,
    715. 

  715. 	   'deflistClose'        : '</descrip>'         ,
    716. 

  716. 	   'deflistItem1'        : '<tag>\a</tag>'      ,
    717. 

  717. 	   'bar1'                : '<!-- \a -->'        ,
    718. 

  718. 	   'bar2'                : '<!-- \a -->'        ,
    719. 

  719. 	   'url'                 : '<htmlurl url="\a" name="\a">'        ,
    720. 

  720. 	   'urlMark'             : '<htmlurl url="\a" name="\a">'        ,
    721. 

  721. 	   'email'               : '<htmlurl url="mailto:\a" name="\a">' ,
    722. 

  722. 	   'emailMark'           : '<htmlurl url="mailto:\a" name="\a">' ,
    723. 

  723. 	   'img'                 : '<figure><ph vspace=""><img src="\a">'+\
    724. 

  724. 	                           '</figure>'                           ,
    725. 

  725. 	   'tableOpen'           : '<table><tabular ca="\a">'            ,
    726. 

  726. 	   'tableClose'          : '</tabular></table>' ,
    727. 

  727. 	   'tableLineClose'      : '<rowsep>'           ,
    728. 

  728. 	   'tableCellClose'      : '<colsep>'           ,
    729. 

  729. 	   'tableTitleCellClose' : '<colsep>'           ,
    730. 

  730. 	   'tableColAlignLeft'   : 'l'                  ,
    731. 

  731. 	   'tableColAlignRight'  : 'r'                  ,
    732. 

  732. 	   'tableColAlignCenter' : 'c'                  ,
    733. 

  733. 	   'comment'             : '<!-- \a -->'        ,
    734. 

  734. 	   'TOC'                 : '<toc>'              ,
    735. 

  735. 	   'EOD'                 : '</article>'
    736. 

  736. 	},
    737. 

  737. 	   
    738. 

  738. 	'tex': {
    739. 

  739. 	   'title1'              : '\n\\newpage\section{\a}',
    740. 

  740. 	   'title2'              : '\\subsection{\a}'       ,
    741. 

  741. 	   'title3'              : '\\subsubsection{\a}'    ,
    742. 

  742. 	   # title 4/5: DIRTY: para+BF+\\+\n
    743. 

  743. 	   'title4'              : '\\paragraph{}\\textbf{\a}\\\\\n',
    744. 

  744. 	   'title5'              : '\\paragraph{}\\textbf{\a}\\\\\n',
    745. 

  745. 	   'areaPreOpen'         : '\\begin{verbatim}'   ,
    746. 

  746. 	   'areaPreClose'        : '\\end{verbatim}'     ,
    747. 

  747. 	   'areaQuoteOpen'       : '\\begin{quotation}'  ,
    748. 

  748. 	   'areaQuoteClose'      : '\\end{quotation}'    ,
    749. 

  749. 	   'fontMonoOpen'        : '\\texttt{'           ,
    750. 

  750. 	   'fontMonoClose'       : '}'                   ,
    751. 

  751. 	   'fontBoldOpen'        : '\\textbf{'           ,
    752. 

  752. 	   'fontBoldClose'       : '}'                   ,
    753. 

  753. 	   'fontItalicOpen'      : '\\textit{'           ,
    754. 

  754. 	   'fontItalicClose'     : '}'                   ,
    755. 

  755. 	   'fontBolditalicOpen'  : '\\textbf{\\textit{'  ,
    756. 

  756. 	   'fontBolditalicClose' : '}}'                  ,
    757. 

  757. 	   'fontUnderlineOpen'   : '\\underline{'        ,
    758. 

  758. 	   'fontUnderlineClose'  : '}'                   ,
    759. 

  759. 	   'listOpen'            : '\\begin{itemize}'    ,
    760. 

  760. 	   'listClose'           : '\\end{itemize}'      ,
    761. 

  761. 	   'listItem'            : '\\item '             ,
    762. 

  762. 	   'numlistOpen'         : '\\begin{enumerate}'  ,
    763. 

  763. 	   'numlistClose'        : '\\end{enumerate}'    ,
    764. 

  764. 	   'numlistItem'         : '\\item '             ,
    765. 

  765. 	   'deflistOpen'         : '\\begin{description}',
    766. 

  766. 	   'deflistClose'        : '\\end{description}'  ,
    767. 

  767. 	   'deflistItem1'        : '\\item[\a]'          ,
    768. 

  768. 	   'bar1'                : '\n\\hrulefill{}\n'   ,
    769. 

  769. 	   'bar2'                : '\n\\rule{\linewidth}{1mm}\n',
    770. 

  770. 	   'url'                 : '\\url{\a}'                  ,
    771. 

  771. 	   'urlMark'             : '\\textit{\a} (\\url{\a})'   ,
    772. 

  772. 	   'email'               : '\\url{\a}'                  ,
    773. 

  773. 	   'emailMark'           : '\\textit{\a} (\\url{\a})'   ,
    774. 

  774. 	   'img'                 : '\\begin{figure}\\includegraphics{\a}'+\
    775. 

  775. 	                           '\\end{figure}',
    776. 

  776. 	   'tableOpen'           : '\\begin{center}\\begin{tabular}{\a|}',
    777. 

  777. 	   'tableClose'          : '\\end{tabular}\\end{center}',
    778. 

  778. 	   'tableLineOpen'       : '\\hline ' ,
    779. 

  779. 	   'tableLineClose'      : ' \\\\'    ,
    780. 

  780. 	   'tableCellClose'      : ' & '      ,
    781. 

  781. 	   'tableTitleCellOpen'  : '\\textbf{',
    782. 

  782. 	   'tableTitleCellClose' : '} & '     ,
    783. 

  783. 	   'tableColAlignLeft'   : '|l'       ,
    784. 

  784. 	   'tableColAlignRight'  : '|r'       ,
    785. 

  785. 	   'tableColAlignCenter' : '|c'       ,
    786. 

  786. 	   'comment'             : '% \a'     ,
    787. 

  787. 	   'TOC'                 : '\\newpage\\tableofcontents',
    788. 

  788. 	   'EOD'                 : '\\end{document}'
    789. 

  789. 	},
    790. 

  790. 	
    791. 

  791. 	'moin': {
    792. 

  792. 	   'title1'              : '= \a ='        ,
    793. 

  793. 	   'title2'              : '== \a =='      ,
    794. 

  794. 	   'title3'              : '=== \a ==='    ,
    795. 

  795. 	   'title4'              : '==== \a ===='  ,
    796. 

  796. 	   'title5'              : '===== \a =====',
    797. 

  797. 	   'areaPreOpen'         : '{{{'           ,
    798. 

  798. 	   'areaPreClose'        : '}}}'           ,
    799. 

  799. 	   'areaQuoteOpen'       : ' '             ,
    800. 

  800. 	   'fontMonoOpen'        : '{{{'           ,
    801. 

  801. 	   'fontMonoClose'       : '}}}'           ,
    802. 

  802. 	   'fontBoldOpen'        : "'''"           ,
    803. 

  803. 	   'fontBoldClose'       : "'''"           ,
    804. 

  804. 	   'fontItalicOpen'      : "''"            ,
    805. 

  805. 	   'fontItalicClose'     : "''"            ,
    806. 

  806. 	   'fontBolditalicOpen'  : "'''''"         ,
    807. 

  807. 	   'fontBolditalicClose' : "'''''"         ,
    808. 

  808. 	   'fontUnderlineOpen'   : "'''''"         ,
    809. 

  809. 	   'fontUnderlineClose'  : "'''''"         ,
    810. 

  810. 	   'listItem'            : '* '            ,
    811. 

  811. 	   'numlistItem'         : '\a. '          ,
    812. 

  812. 	   'bar1'                : '----'          ,
    813. 

  813. 	   'bar2'                : '----'          ,
    814. 

  814. 	   'url'                 : '[\a]'          ,
    815. 

  815. 	   'urlMark'             : '[\a \a]'       ,
    816. 

  816. 	   'email'               : '[\a]'          ,
    817. 

  817. 	   'emailMark'           : '[\a \a]'       ,
    818. 

  818. 	   'img'                 : '[\a]'          ,
    819. 

  819. 	   'tableLineOpen'       : '||'            ,
    820. 

  820. 	   'tableCellClose'      : '||'            ,
    821. 

  821. 	   'tableTitleCellClose' : '||'
    822. 

  822. 	},
    823. 

  823. 	
    824. 

  824. 	'mgp': {
    825. 

  825. 	   'paragraph'           : '%font "normal", size 5\n'   ,
    826. 

  826. 	   'title1'              : '%page\n\n\a'                ,
    827. 

  827. 	   'title2'              : '%page\n\n\a'                ,
    828. 

  828. 	   'title3'              : '%page\n\n\a'                ,
    829. 

  829. 	   'title4'              : '%page\n\n\a'                ,
    830. 

  830. 	   'title5'              : '%page\n\n\a'                ,
    831. 

  831. 	   'areaPreOpen'         : '\n%font "mono"'             ,
    832. 

  832. 	   'areaPreClose'        : '%font "normal"'             ,
    833. 

  833. 	   'areaQuoteOpen'       : '%prefix "       "'          ,
    834. 

  834. 	   'areaQuoteClose'      : '%prefix "  "'               ,
    835. 

  835. 	   'fontMonoOpen'        : '\n%cont, font "mono"\n'     ,
    836. 

  836. 	   'fontMonoClose'       : '\n%cont, font "normal"\n'   ,
    837. 

  837. 	   'fontBoldOpen'        : '\n%cont, font "normal-b"\n' ,
    838. 

  838. 	   'fontBoldClose'       : '\n%cont, font "normal"\n'   ,
    839. 

  839. 	   'fontItalicOpen'      : '\n%cont, font "normal-i"\n' ,
    840. 

  840. 	   'fontItalicClose'     : '\n%cont, font "normal"\n'   ,
    841. 

  841. 	   'fontBolditalicOpen'  : '\n%cont, font "normal-bi"\n',
    842. 

  842. 	   'fontBolditalicClose' : '\n%cont, font "normal"\n'   ,
    843. 

  843. 	   'fontUnderlineOpen'   : '\n%cont, fore "cyan"\n'     ,
    844. 

  844. 	   'fontUnderlineClose'  : '\n%cont, fore "white"\n'    ,
    845. 

  845. 	   'numlistItem'         : '\a. '                       ,
    846. 

  846. 	   'bar1'                : '%bar "white" 5'             ,
    847. 

  847. 	   'bar2'                : '%pause'                     ,
    848. 

  848. 	   'url'                 : '\n%cont, fore "cyan"\n\a'   +\
    849. 

  849. 	                           '\n%cont, fore "white"\n'    ,
    850. 

  850. 	   'urlMark'             : '\a \n%cont, fore "cyan"\n\a'+\
    851. 

  851. 	                           '\n%cont, fore "white"\n'    ,
    852. 

  852. 	   'email'               : '\n%cont, fore "cyan"\n\a'   +\
    853. 

  853. 	                           '\n%cont, fore "white"\n'    ,
    854. 

  854. 	   'emailMark'           : '\a \n%cont, fore "cyan"\n\a'+\
    855. 

  855. 	                           '\n%cont, fore "white"\n'    ,
    856. 

  856. 	   'img'                 : '\n%center\n%newimage "\a", left\n',
    857. 

  857. 	   'comment'             : '%% \a'                      ,
    858. 

  858. 	   'EOD'                 : '%%EOD'
    859. 

  859. 	},
    860. 

  860. 	
    861. 

  861. 	'man': {
    862. 

  862. 	   'paragraph'           : '.P'     ,
    863. 

  863. 	   'title1'              : '.SH \a' ,
    864. 

  864. 	   'title2'              : '.SS \a' ,
    865. 

  865. 	   'title3'              : '.SS \a' ,
    866. 

  866. 	   'title4'              : '.SS \a' ,
    867. 

  867. 	   'title5'              : '.SS \a' ,
    868. 

  868. 	   'areaPreOpen'         : '.nf'    ,
    869. 

  869. 	   'areaPreClose'        : '.fi\n'  ,
    870. 

  870. 	   'areaQuoteOpen'       : '\n'     ,
    871. 

  871. 	   'areaQuoteClose'      : '\n'     ,
    872. 

  872. 	   'fontBoldOpen'        : '\\fB'   ,
    873. 

  873. 	   'fontBoldClose'       : '\\fP'   ,
    874. 

  874. 	   'fontItalicOpen'      : '\\fI'   ,
    875. 

  875. 	   'fontItalicClose'     : '\\fP'   ,
    876. 

  876. 	   'fontBolditalicOpen'  : '\n.BI ' ,
    877. 

  877. 	   'fontBolditalicClose' : '\n\\&'  ,
    878. 

  878. 	   'listOpen'            : '\n.nf'  ,  # pre
    879. 

  879. 	   'listClose'           : '.fi\n'  ,
    880. 

  880. 	   'listItem'            : '* '     ,
    881. 

  881. 	   'numlistOpen'         : '\n.nf'  ,  # pre
    882. 

  882. 	   'numlistClose'        : '.fi\n'  ,
    883. 

  883. 	   'numlistItem'         : '\a. '   ,
    884. 

  884. 	   'bar1'                : '\n\n'   ,
    885. 

  885. 	   'bar2'                : '\n\n'   ,
    886. 

  886. 	   'url'                 : '\a'     ,
    887. 

  887. 	   'urlMark'             : '\a (\a)',
    888. 

  888. 	   'email'               : '\a'     ,
    889. 

  889. 	   'emailMark'           : '\a (\a)',
    890. 

  890. 	   'img'                 : '\a'     ,
    891. 

  891. 	   'comment'             : '.\\" \a'
    892. 

  892. 	},
    893. 

  893. 	
    894. 

  894. 	'pm6': {
    895. 

  895. 	   'paragraph'           : '<@Normal:>'    ,
    896. 

  896. 	   'title1'              : '\n<@Title1:>\a',
    897. 

  897. 	   'title2'              : '\n<@Title2:>\a',
    898. 

  898. 	   'title3'              : '\n<@Title3:>\a',
    899. 

  899. 	   'title4'              : '\n<@Title4:>\a',
    900. 

  900. 	   'title5'              : '\n<@Title5:>\a',
    901. 

  901. 	   'areaPreOpen'         : '<@PreFormat:>' ,
    902. 

  902. 	   'areaQuoteOpen'       : '<@Quote:>'     ,
    903. 

  903. 	   'fontMonoOpen'        : '<FONT "Lucida Console"><SIZE 9>' ,
    904. 

  904. 	   'fontMonoClose'       : '<SIZE$><FONT$>',
    905. 

  905. 	   'fontBoldOpen'        : '<B>'           ,
    906. 

  906. 	   'fontBoldClose'       : '<P>'           ,
    907. 

  907. 	   'fontItalicOpen'      : '<I>'           ,
    908. 

  908. 	   'fontItalicClose'     : '<P>'           ,
    909. 

  909. 	   'fontBolditalicOpen'  : '<B><I>'        ,
    910. 

  910. 	   'fontBolditalicClose' : '<P>'           ,
    911. 

  911. 	   'fontUnderlineOpen'   : '<U>'           ,
    912. 

  912. 	   'fontUnderlineClose'  : '<P>'           ,
    913. 

  913. 	   'listOpen'            : '<@Bullet:>'    ,
    914. 

  914. 	   'listItem'            : '\x95	'       ,  # \x95 == ~U
    915. 

  915. 	   'numlistOpen'         : '<@Bullet:>'    ,
    916. 

  916. 	   'numlistItem'         : '\x95    '      ,
    917. 

  917. 	   'bar1'                : '\a'            ,
    918. 

  918. 	   'bar2'                : '\a'            ,
    919. 

  919. 	   'url'                 : '<U>\a<P>'      ,  # underline
    920. 

  920. 	   'urlMark'             : '\a <U>\a<P>'   ,
    921. 

  921. 	   'email'               : '\a'            ,
    922. 

  922. 	   'emailMark'           : '\a \a'         ,
    923. 

  923. 	   'img'                 : '\a'
    924. 

  924. 	}
    925. 

  925. 	}
    926. 

  926. 	
    927. 

  927. 	# compose the target tags dictionary
    928. 

  928. 	tags = {}
    929. 

  929. 	target_tags = alltags[doctype]
    930. 

  930. 	for key in keys: tags[key] = ''     # create empty keys
    931. 

  931. 	for key in target_tags.keys():
    932. 

  932. 		tags[key] = maskEscapeChar(target_tags[key]) # populate
    933. 

  933. 	
    934. 

  934. 	return tags
    935. 

  935. 

  936. 

  937. def getRules(doctype):
    938. 

  938. 	ret = {}
    939. 

  939. 	allrules = [
    940. 

  940. 	
    941. 

  941. 	 # target rules (ON/OFF)
    942. 

  942. 	  'linkable',           # target supports external links
    943. 

  943. 	  'tableable',          # target supports tables
    944. 

  944. 	  'imglinkable',        # target supports images as links
    945. 

  945. 	  'imgalignable',       # target supports image alignment
    946. 

  946. 	  'imgasdefterm',       # target supports image as definition term
    947. 

  947. 	  'tablealignable',     # target supports table alignment
    948. 

  948. 	  'listcountable',      # target supports numbered lists natively
    949. 

  949. 	  'tablecellsplit',     # place delimiters only *between* cells
    950. 

  950. 	  'listnotnested',      # lists cannot be nested
    951. 

  951. 	  'quotenotnested',     # quotes cannot be nested
    952. 

  952. 	  'preareanotescaped',  # don't escape specials in PRE area
    953. 

  953. 	  'escapeurl',          # escape special in link URL
    954. 

  954. 	  
    955. 

  955. 	# target code beautify (ON/OFF)
    956. 

  956. 	  'indentprearea',      # add leading spaces to PRE area lines
    957. 

  957. 	  'breaktablecell',     # break lines after any table cell
    958. 

  958. 	  'breaktablelineopen', # break line after opening table line
    959. 

  959. 	  'keepquoteindent',    # don't remove the leading TABs on quotes
    960. 

  960. 	
    961. 

  961. 	# value settings
    962. 

  962. 	  'listmaxdepth',       # maximum depth for lists
    963. 

  963. 	  'tablecellaligntype'  # type of table cell align: cell, column
    964. 

  964. 	]
    965. 

  965. 	
    966. 

  966. 	rules = {
    967. 

  967. 	  'txt' : {
    968. 

  968. 	    'indentprearea':1
    969. 

  969. 	    },
    970. 

  970. 	  'html': {
    971. 

  971. 	    'indentprearea':1,
    972. 

  972. 	    'linkable':1,
    973. 

  973. 	    'imglinkable':1,
    974. 

  974. 	    'imgalignable':1,
    975. 

  975. 	    'imgasdefterm':1,
    976. 

  976. 	    'listcountable':1,
    977. 

  977. 	    'tableable':1,
    978. 

  978. 	    'breaktablecell':1,
    979. 

  979. 	    'breaktablelineopen':1,
    980. 

  980. 	    'keepquoteindent':1,
    981. 

  981. 	    'tablealignable':1,
    982. 

  982. 	    'tablecellaligntype':'cell'
    983. 

  983. 	    },
    984. 

  984. 	  'sgml': {
    985. 

  985. 	    'linkable':1,
    986. 

  986. 	    'escapeurl':1,
    987. 

  987. 	    'listcountable':1,
    988. 

  988. 	    'tableable':1,
    989. 

  989. 	    'tablecellsplit':1,
    990. 

  990. 	    'quotenotnested':1,
    991. 

  991. 	    'keepquoteindent':1,
    992. 

  992. 	    'tablecellaligntype':'column'
    993. 

  993. 	    },
    994. 

  994. 	  'mgp' : {
    995. 

  995. 	    },
    996. 

  996. 	  'tex' : {
    997. 

  997. 	    'listcountable':1,
    998. 

  998. 	    'tableable':1,
    999. 

  999. 	    'tablecellsplit':1,
    1000. 

  1000. 	    'preareanotescaped':1,
    1001. 

  1001. 	    'listmaxdepth':4,
    1002. 

  1002. 	    'tablecellaligntype':'column'
    1003. 

  1003. 	    },
    1004. 

  1004. 	  'moin': {
    1005. 

  1005. 	    'linkable':1,
    1006. 

  1006. 	    'tableable':1
    1007. 

  1007. 	    },
    1008. 

  1008. 	  'man' : {
    1009. 

  1009. 	    'indentprearea':1,
    1010. 

  1010. 	    'listnotnested':1
    1011. 

  1011. 	    },
    1012. 

  1012. 	  'pm6' : {
    1013. 

  1013. 	    }
    1014. 

  1014. 	}
    1015. 

  1015. 	
    1016. 

  1016. 	
    1017. 

  1017. 	# populate return dictionary
    1018. 

  1018. 	myrules = rules[doctype]
    1019. 

  1019. 	for key in allrules      : ret[key] = 0            # reset all
    1020. 

  1020. 	for key in myrules.keys(): ret[key] = myrules[key] # turn ON
    1021. 

  1021. 	return ret
    1022. 

  1022. 

  1023. 

  1024. def getRegexes():
    1025. 

  1025. 	regex = {
    1026. 

  1026. 	# extra at end: (\[(?P<label>\w+)\])?
    1027. 

  1027. 	'title':
    1028. 

  1028. 		re.compile(r'^\s*(?P<tag>={1,5})(?P<txt>[^=].*[^=])\1\s*$'),
    1029. 

  1029. 	'areaPreOpen':
    1030. 

  1030. 		re.compile(r'^---$'),
    1031. 

  1031. 	'areaPreClose':
    1032. 

  1032. 		re.compile(r'^---$'),
    1033. 

  1033. 	'quote':
    1034. 

  1034. 		re.compile(r'^\t+'),
    1035. 

  1035. 	'1linePre':
    1036. 

  1036. #		re.compile(r'^--- '),
    1037. 

  1037. 		re.compile(r'^--- (?=.)'),
    1038. 

  1038. 	'fontMono':
    1039. 

  1039. 		re.compile(r'`([^`]+)`'),
    1040. 

  1040. 	'fontBold':
    1041. 

  1041. 		re.compile(r'\*\*([^\s*].*?)\*\*'),
    1042. 

  1042. 	'fontItalic':
    1043. 

  1043. 		re.compile(r'(^|[^:])//([^ /].*?)//'),
    1044. 

  1044. 	'fontUnderline':
    1045. 

  1045. 		re.compile(r'__([^_].*?)__'), # underline lead/trailing blank
    1046. 

  1046. 	'fontBolditalic':
    1047. 

  1047. 		re.compile(r'\*/([^/].*?)/\*'),
    1048. 

  1048. 	'list':
    1049. 

  1049. 		re.compile(r'^( *)([+-]) ([^ ])'),
    1050. 

  1050. 	'deflist':
    1051. 

  1051. 		re.compile(r'^( *)(=) ([^:]+):'),
    1052. 

  1052. 	'bar':
    1053. 

  1053. 		re.compile(r'^\s*([_=-]{20,})\s*$'),
    1054. 

  1054. 	'table':
    1055. 

  1055. 		re.compile(r'^ *\|\|? '),
    1056. 

  1056. 	'blankline':
    1057. 

  1057. 		re.compile(r'^\s*$'),
    1058. 

  1058. 	'comment':
    1059. 

  1059. 		re.compile(r'^%'),
    1060. 

  1060. 	'raw':
    1061. 

  1061. 		re.compile(r'``(.+?)``')
    1062. 

  1062. 	}
    1063. 

  1063. 	
    1064. 

  1064. 	# special char to place data on TAGs contents  (\a == bell)
    1065. 

  1065. 	regex['x'] = re.compile('\a')
    1066. 

  1066. 	
    1067. 

  1067. 	# %%date [ (formatting) ]
    1068. 

  1068. 	regex['date'] = re.compile(r'%%date\b(\((?P<fmt>.*?)\))?', re.I)
    1069. 

  1069. 	
    1070. 

  1070. 	
    1071. 

  1071. 	### complicated regexes begin here ;)
    1072. 

  1072. 	#
    1073. 

  1073. 	# textual descriptions on --help's style: [...] is optional, | is OR
    1074. 

  1074. 	
    1075. 

  1075. 	
    1076. 

  1076. 	### first, some auxiliar variables
    1077. 

  1077. 	#
    1078. 

  1078. 	
    1079. 

  1079. 	# [image.EXT]
    1080. 

  1080. 	patt_img = r'\[([\w_,.+%$#@!?+~/-]+\.(png|jpe?g|gif|eps|bmp))\]'
    1081. 

  1081. 	
    1082. 

  1082. 	# link things
    1083. 

  1083. 	urlskel = {
    1084. 

  1084. 	  'proto' : r'(https?|ftp|news|telnet|gopher|wais)://',
    1085. 

  1085. 	  'guess' : r'(www[23]?|ftp)\.',    # w/out proto, try to guess
    1086. 

  1086. 	  'login' : r'A-Za-z0-9_.-',        # for ftp://login@domain.com
    1087. 

  1087. 	  'pass'  : r'[^ @]*',              # for ftp://login:password@dom.com
    1088. 

  1088. 	  'chars' : r'A-Za-z0-9%._/~:,=$@-',# %20(space), :80(port)
    1089. 

  1089. 	  'anchor': r'A-Za-z0-9%._-',       # %nn(encoded)
    1090. 

  1090. 	  'form'  : r'A-Za-z0-9/%&=+.,@*_-',# .,@*_-(as is)
    1091. 

  1091. 	  'punct' : r'.,;:!?'
    1092. 

  1092. 	}
    1093. 

  1093. 	
    1094. 

  1094. 	# username [ :password ] @
    1095. 

  1095. 	patt_url_login = r'([%s]+(:%s)?@)?'%(urlskel['login'],urlskel['pass'])
    1096. 

  1096. 	
    1097. 

  1097. 	# [ http:// ] [ username:password@ ] domain.com [ / ]
    1098. 

  1098. 	#     [ #anchor | ?form=data ]
    1099. 

  1099. 	retxt_url = r'\b(%s%s|%s)[%s]+\b/*(\?[%s]+)?(#[%s]+)?'%(
    1100. 

  1100. 	             urlskel['proto'],patt_url_login, urlskel['guess'],
    1101. 

  1101. 	             urlskel['chars'],urlskel['form'],urlskel['anchor'])
    1102. 

  1102. 	
    1103. 

  1103. 	# filename | [ filename ] #anchor
    1104. 

  1104. 	retxt_url_local = r'[%s]+|[%s]*(#[%s]+)'%(
    1105. 

  1105. 	             urlskel['chars'],urlskel['chars'],urlskel['anchor'])
    1106. 

  1106. 	
    1107. 

  1107. 	# user@domain [ ?form=data ]
    1108. 

  1108. 	patt_email = r'\b[%s]+@([A-Za-z0-9_-]+\.)+[A-Za-z]{2,4}\b(\?[%s]+)?'%(
    1109. 

  1109. 	             urlskel['login'],urlskel['form'])
    1110. 

  1110. 	
    1111. 

  1111. 	
    1112. 

  1112. 	# saving for future use
    1113. 

  1113. 	regex['_urlskel'] = urlskel
    1114. 

  1114. 	
    1115. 

  1115. 	### and now the real regexes
    1116. 

  1116. 	#
    1117. 

  1117. 	
    1118. 

  1118. 	regex['email'] = re.compile(patt_email,re.I)
    1119. 

  1119. 	
    1120. 

  1120. 	# email | url
    1121. 

  1121. 	regex['link'] = \
    1122. 

  1122. 		re.compile(r'%s|%s'%(retxt_url,patt_email), re.I)
    1123. 

  1123. 	
    1124. 

  1124. 	# \[ label | imagetag    url | email | filename \]
    1125. 

  1125. 	regex['linkmark'] = \
    1126. 

  1126. 		re.compile(r'\[(?P<label>%s|[^]]+) (?P<link>%s|%s|%s)\]'%(
    1127. 

  1127. 		   patt_img, retxt_url, patt_email, retxt_url_local),
    1128. 

  1128. 		   re.L+re.I)
    1129. 

  1129. 	
    1130. 

  1130. 	# image
    1131. 

  1131. 	regex['img'] = re.compile(patt_img, re.L+re.I)
    1132. 

  1132. 	
    1133. 

  1133. 	# all macros
    1134. 

  1134. 	regex['macro'] = regex['date']
    1135. 

  1135. 	
    1136. 

  1136. 	# special things
    1137. 

  1137. 	regex['special'] = re.compile(r'^%!\s*')
    1138. 

  1138. 	regex['command'] = re.compile(r'(Include)\s*:\s*(.+)\s*$',re.I)
    1139. 

  1139. 	return regex
    1140. 

  1140. ### END OF regex nightmares
    1141. 

  1141. 

  1142. 

  1143. class SubareaMaster:
    1144. 

  1144. 	def __init__(self) : self.x = []
    1145. 

  1145. 	def __call__(self) :
    1146. 

  1146. 		if not self.x: return ''
    1147. 

  1147. 		return self.x[-1]
    1148. 

  1148. 	def add(self, area):
    1149. 

  1149. 		if not self.x or (self.x and self.x[-1] != area):
    1150. 

  1150. 			self.x.append(area)
    1151. 

  1151. 		Debug('subarea ++ (%s): %s' % (area,self.x), 1)
    1152. 

  1152. 	def pop(self, area=None):
    1153. 

  1153. 		if area and self.x[-1] == area: self.x.pop()
    1154. 

  1154. 		Debug('subarea -- (%s): %s' % (area,self.x), 1)
    1155. 

  1155. 

  1156. def doHeader(headers, CONF):
    1157. 

  1157. 	if CONF['noheaders']: return []
    1158. 

  1158. 	doctype = CONF['type']
    1159. 

  1159. 	if not HEADER_TEMPLATE.has_key(doctype):
    1160. 

  1160. 		Error("doheader: Unknow doctype '%s'"%doctype)
    1161. 

  1161. 	
    1162. 

  1162. 	template = string.split(HEADER_TEMPLATE[doctype], '\n')
    1163. 

  1163. 	
    1164. 

  1164. 	head_data = {'STYLE':'', 'ENCODING':''}
    1165. 

  1165. 	for key in head_data.keys():
    1166. 

  1166. 		val = CONF.get(string.lower(key))
    1167. 

  1167. 		if key == 'ENCODING': val = get_encoding_string(val, doctype)
    1168. 

  1168. 		head_data[key] = val
    1169. 

  1169. 	# parse header contents
    1170. 

  1170. 	for i in 0,1,2:
    1171. 

  1171. 		contents = doDateMacro(headers[i])  # expand %%date
    1172. 

  1172. 		# Escapes - on tex, just do it if any \tag{} present
    1173. 

  1173. 		if doctype != 'tex' or \
    1174. 

  1174. 		  (doctype == 'tex' and re.search(r'\\\w+{', contents)):
    1175. 

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

  1176. 		
    1177. 

  1177. 		head_data['HEADER%d'%(i+1)] = contents
    1178. 

  1178. 	Debug("Header Data: %s"%head_data, 1)
    1179. 

  1179. 	# scan for empty dictionary keys
    1180. 

  1180. 	# if found, scan template lines for that key reference
    1181. 

  1181. 	# if found, remove the reference
    1182. 

  1182. 	# if there isn't any other key reference on the same line, remove it
    1183. 

  1183. 	for key in head_data.keys():
    1184. 

  1184. 		if head_data.get(key): continue
    1185. 

  1185. 		for line in template:
    1186. 

  1186. 			if string.count(line, '%%(%s)s'%key):
    1187. 

  1187. 				sline = string.replace(line, '%%(%s)s'%key, '')
    1188. 

  1188. 				if not re.search(r'%\([A-Z0-9]+\)s', sline):
    1189. 

  1189. 					template.remove(line)
    1190. 

  1190. 	# populate template with data
    1191. 

  1191. 	template = string.join(template, '\n') % head_data
    1192. 

  1192. 	### post processing
    1193. 

  1193. 	#
    1194. 

  1194. 	# let tex format today
    1195. 

  1195. 	if doctype == 'tex' and head_data['HEADER3'] == currdate:
    1196. 

  1196. 		template = re.sub(r'\\date\{.*?}', r'\date', template)
    1197. 

  1197. 	
    1198. 

  1198. 	return string.split(template, '\n')
    1199. 

  1199. 

  1200. def doDateMacro(line):
    1201. 

  1201. 	re_date = getRegexes()['date']
    1202. 

  1202. 	while re_date.search(line):
    1203. 

  1203. 		m = re_date.search(line)
    1204. 

  1204. 		fmt = m.group('fmt') or ''
    1205. 

  1205. 		dateme = currdate
    1206. 

  1206. 		if fmt: dateme = strftime(fmt,localtime(time()))
    1207. 

  1207. 		line = re_date.sub(dateme,line,1)
    1208. 

  1208. 	return line
    1209. 

  1209. 

  1210. def doCommentLine(doctype,txt):
    1211. 

  1211. 	# the -- string ends a sgml comment :(
    1212. 

  1212. 	if doctype == 'sgml':
    1213. 

  1213. 		txt = string.replace(txt, '--', '\\-\\-')
    1214. 

  1214. 	
    1215. 

  1215. 	if TAGS['comment']:
    1216. 

  1216. 		return regex['x'].sub(txt, TAGS['comment'])
    1217. 

  1217. 	return ''
    1218. 

  1218. 

  1219. def doFooter(CONF):
    1220. 

  1220. 	ret = []
    1221. 

  1221. 	doctype = CONF['type']
    1222. 

  1222. 	cmdline = CONF['cmdline']
    1223. 

  1223. 	typename = doctype
    1224. 

  1224. 	if doctype == 'tex': typename = 'LaTeX2e'
    1225. 

  1225. 	ppgd = '%s code generated by txt2tags %s (%s)'%(
    1226. 

  1226. 	        typename,my_version,my_url)
    1227. 

  1227. 	cmdline = 'cmdline: txt2tags %s'%string.join(cmdline[1:], ' ')
    1228. 

  1228. 	ret.append('\n'+doCommentLine(doctype,ppgd))
    1229. 

  1229. 	ret.append(doCommentLine(doctype,cmdline))
    1230. 

  1230. 	ret.append(TAGS['EOD'])
    1231. 

  1231. 	return ret
    1232. 

  1232. 

  1233. def doEscape(doctype,txt):
    1234. 

  1234. 	if doctype in ['html','sgml']:
    1235. 

  1235. 		txt = re.sub('&','&amp;',txt)
    1236. 

  1236. 		txt = re.sub('<','&lt;',txt)
    1237. 

  1237. 		txt = re.sub('>','&gt;',txt)
    1238. 

  1238. 		if doctype == 'sgml':
    1239. 

  1239. 			txt = re.sub('\xff','&yuml;',txt)  # "+y
    1240. 

  1240. 	elif doctype == 'pm6':
    1241. 

  1241. 		txt = re.sub('<','<\#60>',txt)
    1242. 

  1242. 	elif doctype == 'mgp':
    1243. 

  1243. 		txt = re.sub('^%',' %',txt)  # add leading blank to avoid parse
    1244. 

  1244. 	elif doctype == 'man':
    1245. 

  1245. 		txt = re.sub('^\.', ' .',txt) # command ID
    1246. 

  1246. 		txt = doEscapeEscapechar(txt)
    1247. 

  1247. 	elif doctype == 'tex':
    1248. 

  1248. 		txt = string.replace(txt, ESCCHAR, maskEscapeChar(r'\verb!\!'))
    1249. 

  1249. 		txt = string.replace(txt, '~', maskEscapeChar(r'\verb!~!'))
    1250. 

  1250. 		txt = string.replace(txt, '^', maskEscapeChar(r'\verb!^!'))
    1251. 

  1251. 		txt = re.sub('([#$&%{}])', r'\\\1', txt)
    1252. 

  1252. 		# TIP the _ is escaped at the end
    1253. 

  1253. 	return txt
    1254. 

  1254. 

  1255. def doFinalEscape(doctype, txt):
    1256. 

  1256. 	"Last escapes of each line"
    1257. 

  1257. 	if   doctype == 'pm6' : txt = string.replace(txt,ESCCHAR+'<',r'<\#92><')
    1258. 

  1258. 	elif doctype == 'man' : txt = string.replace(txt, '-', r'\-')
    1259. 

  1259. 	elif doctype == 'tex' : txt = string.replace(txt, '_', r'\_')
    1260. 

  1260. 	elif doctype == 'sgml': txt = string.replace(txt, '[', '&lsqb;')
    1261. 

  1261. 	return txt
    1262. 

  1262. 

  1263. def doEscapeEscapechar(txt):
    1264. 

  1264. 	"Double all Escape Chars"
    1265. 

  1265. 	return string.replace(txt, ESCCHAR, ESCCHAR*2)
    1266. 

  1266. 

  1267. def EscapeCharHandler(action, data):
    1268. 

  1268. 	"Mask/Unmask the Escape Char on the given string"
    1269. 

  1269. 	if not string.strip(data): return data
    1270. 

  1270. 	if action not in ['mask','unmask']:
    1271. 

  1271. 		Error("EscapeCharHandler: Invalid action '%s'"%action)
    1272. 

  1272. 	if action == 'mask': return string.replace(data,'\\',ESCCHAR)
    1273. 

  1273. 	else:                return string.replace(data,ESCCHAR,'\\')
    1274. 

  1274. 

  1275. def maskEscapeChar(data):
    1276. 

  1276. 	"Replace any Escape Char \ with a text mask (Input: str or list)"
    1277. 

  1277. 	if type(data) == type([]):
    1278. 

  1278. 		return map(lambda x: EscapeCharHandler('mask', x), data)
    1279. 

  1279. 	return EscapeCharHandler('mask',data)
    1280. 

  1280. 

  1281. def unmaskEscapeChar(data):
    1282. 

  1282. 	"Undo the Escape char \ masking (Input: str or list)"
    1283. 

  1283. 	if type(data) == type([]):
    1284. 

  1284. 		return map(lambda x: EscapeCharHandler('unmask', x), data)
    1285. 

  1285. 	return EscapeCharHandler('unmask',data)
    1286. 

  1286. 

  1287. def addLineBreaks(list):
    1288. 

  1288. 	"use LB to respect sys.platform"
    1289. 

  1289. 	ret = []
    1290. 

  1290. 	for line in list:
    1291. 

  1291. 		line = string.replace(line,'\n',LB)  # embedded \n's
    1292. 

  1292. 		ret.append(line+LB)                  # add final line break
    1293. 

  1293. 	return ret
    1294. 

  1294. 

  1295. def doPreLine(doctype,line):
    1296. 

  1296. 	"Parsing procedures for preformatted (verbatim) lines"
    1297. 

  1297. 	if not rules['preareanotescaped']: line = doEscape(doctype,line)
    1298. 

  1298. 	if rules['indentprearea']: line = '  '+line
    1299. 

  1299. 	if doctype == 'pm6': line = doFinalEscape(doctype, line)
    1300. 

  1300. 	return line
    1301. 

  1301. 

  1302. def doCloseTable(doctype):
    1303. 

  1303. 	global subarea, tableborder
    1304. 

  1304. 	ret = ''
    1305. 

  1305. 	if rules['tableable']:
    1306. 

  1306. 		if doctype == 'tex' and tableborder:
    1307. 

  1307. 			ret = TAGS['tableLineOpen']+TAGS['tableClose']+'\n'
    1308. 

  1308. 		else:
    1309. 

  1309. 			ret = TAGS['tableClose']+'\n'
    1310. 

  1310. 	else:
    1311. 

  1311. 		ret = TAGS['areaPreClose']
    1312. 

  1312. 	tableborder = 0
    1313. 

  1313. 	subarea.pop('table')
    1314. 

  1314. 	return ret
    1315. 

  1315. 

  1316. def doCloseQuote(howmany=None):
    1317. 

  1317. 	global quotedepth
    1318. 

  1318. 	ret = []
    1319. 

  1319. 	if not howmany: howmany = len(quotedepth)
    1320. 

  1320. 	for i in range(howmany):
    1321. 

  1321. 		quotedepth.pop()
    1322. 

  1322. 		#TODO align open/close tag -> FREE_ALING_TAG = 1 (man not)
    1323. 

  1323. 		ret.append(TAGS['areaQuoteClose'])
    1324. 

  1324. 	
    1325. 

  1325. 	if not quotedepth: subarea.pop('quote')
    1326. 

  1326. 	return string.join(ret,'\n')
    1327. 

  1327. 

  1328. def doCloseList(howmany=None):
    1329. 

  1329. 	global listindent, listids
    1330. 

  1330. 	ret = []
    1331. 

  1331. 	if not howmany: howmany = len(listindent)
    1332. 

  1332. 	for i in range(howmany):
    1333. 

  1333. 		if   listids[-1] == '-': tag = TAGS['listClose']
    1334. 

  1334. 		elif listids[-1] == '+': tag = TAGS['numlistClose']
    1335. 

  1335. 		elif listids[-1] == '=': tag = TAGS['deflistClose']
    1336. 

  1336. 		if not tag: tag = TAGS['listClose'] # default
    1337. 

  1337. 		if tag:
    1338. 

  1338. 			# unnested lists are only closed at mother-list
    1339. 

  1339. 			if rules['listnotnested']:
    1340. 

  1340. 				if len(listindent) == 1:
    1341. 

  1341. 					ret.append(tag)
    1342. 

  1342. 			else:
    1343. 

  1343. 				ret.append(listindent[-1]+tag)
    1344. 

  1344. 		del listindent[-1]
    1345. 

  1345. 		del listids[-1]
    1346. 

  1346. 	
    1347. 

  1347. 	if not listindent: subarea.pop('list')
    1348. 

  1348. 	return string.join(ret,'\n')
    1349. 

  1349. 

  1350. 

  1351. def beautify_me(name, doctype, line):
    1352. 

  1352. 	"where name is: bold, italic, underline or bolditalic"
    1353. 

  1353. 	name  = 'font%s' % string.capitalize(name)
    1354. 

  1354. 	open  = TAGS['%sOpen'%name]
    1355. 

  1355. 	close = TAGS['%sClose'%name]
    1356. 

  1356. 	txt = r'%s\1%s'%(open, close)
    1357. 

  1357. 	if name == 'fontItalic':
    1358. 

  1358. 		txt = r'\1%s\2%s'%(open, close)
    1359. 

  1359. 	line = regex[name].sub(txt,line)
    1360. 

  1360. 	return line
    1361. 

  1361. 

  1362. 

  1363. def get_tagged_link(label, url, CONF):
    1364. 

  1364. 	ret = ''
    1365. 

  1365. 	doctype = CONF['type']
    1366. 

  1366. 	
    1367. 

  1367. 	# set link type
    1368. 

  1368. 	if regex['email'].match(url):
    1369. 

  1369. 		linktype = 'email'
    1370. 

  1370. 	else:
    1371. 

  1371. 		linktype = 'url';
    1372. 

  1372. 	
    1373. 

  1373. 	# escape specials from TEXT parts
    1374. 

  1374. 	label = doEscape(doctype,label)
    1375. 

  1375. 	
    1376. 

  1376. 	# escape specials from link URL
    1377. 

  1377. 	if rules['linkable'] and rules['escapeurl']:
    1378. 

  1378. 		url = doEscape(doctype, url)
    1379. 

  1379. 	
    1380. 

  1380. 	# if not linkable, the URL is plain text, that needs escape
    1381. 

  1381. 	if not rules['linkable']:
    1382. 

  1382. 		if doctype == 'tex':
    1383. 

  1383. 			url = re.sub('^#', '\#', url) # ugly, but compile
    1384. 

  1384. 		else:
    1385. 

  1385. 			url = doEscape(doctype,url)
    1386. 

  1386. 	
    1387. 

  1387. 	# adding protocol to guessed link
    1388. 

  1388. 	guessurl = ''
    1389. 

  1389. 	if linktype == 'url' and \
    1390. 

  1390. 	   re.match(regex['_urlskel']['guess'], url):
    1391. 

  1391. 		if url[0] == 'w': guessurl = 'http://' +url
    1392. 

  1392. 		else            : guessurl =  'ftp://' +url
    1393. 

  1393. 		
    1394. 

  1394. 		# not link aware targets -> protocol is useless
    1395. 

  1395. 		if not rules['linkable']: guessurl = ''
    1396. 

  1396. 	
    1397. 

  1397. 	# simple link (not guessed)
    1398. 

  1398. 	if not label and not guessurl:
    1399. 

  1399. 		if CONF['maskemail'] and linktype == 'email':
    1400. 

  1400. 			# do the email mask feature (no TAGs, just text)
    1401. 

  1401. 			url = string.replace(url,'@',' (a) ')
    1402. 

  1402. 			url = string.replace(url,'.',' ')
    1403. 

  1403. 			url = "<%s>" % url
    1404. 

  1404. 			if rules['linkable']: url = doEscape(doctype, url)
    1405. 

  1405. 			ret = url
    1406. 

  1406. 		else:
    1407. 

  1407. 			# just add link data to tag
    1408. 

  1408. 			tag = TAGS[linktype]
    1409. 

  1409. 			ret = regex['x'].sub(url,tag)
    1410. 

  1410. 	
    1411. 

  1411. 	# named link or guessed simple link
    1412. 

  1412. 	else:
    1413. 

  1413. 		# adjusts for guessed link
    1414. 

  1414. 		if not label: label = url       # no   protocol
    1415. 

  1415. 		if guessurl : url   = guessurl  # with protocol
    1416. 

  1416. 		
    1417. 

  1417. 		# change image tag for !supported img+link targets
    1418. 

  1418. 		if regex['img'].match(label) and not rules['imglinkable']:
    1419. 

  1419. 			label = "(%s)"%regex['img'].match(label).group(1)
    1420. 

  1420. 		
    1421. 

  1421. 		# putting data on the right appearance order
    1422. 

  1422. 		if rules['linkable']:
    1423. 

  1423. 			urlorder = [url, label]   # link before label
    1424. 

  1424. 		else:
    1425. 

  1425. 			urlorder = [label, url]   # label before link
    1426. 

  1426. 		
    1427. 

  1427. 		# add link data to tag (replace \a's)
    1428. 

  1428. 		ret = TAGS["%sMark"%linktype]
    1429. 

  1429. 		for data in urlorder:
    1430. 

  1430. 			ret = regex['x'].sub(data,ret,1)
    1431. 

  1431. 	
    1432. 

  1432. 	return ret
    1433. 

  1433. 

  1434. 

  1435. def get_image_align(line):
    1436. 

  1436. 	align = ''
    1437. 

  1437. 	line = string.strip(line)
    1438. 

  1438. 	m = regex['img'].search(line)
    1439. 

  1439. 	ini = m.start() ; head = 0
    1440. 

  1440. 	end = m.end()   ; tail = len(line)
    1441. 

  1441. 	
    1442. 

  1442. 	align = 'center'  # default align              # ^text +img +text$
    1443. 

  1443. 	if ini == head and end == tail: align = 'para' # ^img$
    1444. 

  1444. 	elif ini == head: align = 'left'               # ^img + text$
    1445. 

  1445. 	elif end == tail: align = 'right'              # ^text + img$
    1446. 

  1446. 	
    1447. 

  1447. 	return align
    1448. 

  1448. 

  1449. 

  1450. def get_tablecell_align(cells):
    1451. 

  1451. 	ret = []
    1452. 

  1452. 	for cell in cells:
    1453. 

  1453. 		align = 'Left'
    1454. 

  1454. 		if string.strip(cell): 
    1455. 

  1455. 			if cell[0] == ' ' and cell[-1] == ' ': align = 'Center'
    1456. 

  1456. 			elif cell[0] == ' ': align = 'Right'
    1457. 

  1457. 		ret.append(align)
    1458. 

  1458. 	return ret
    1459. 

  1459. 

  1460. 

  1461. def get_table_prop(line):
    1462. 

  1462. 	# default table proprierties
    1463. 

  1463. 	ret = {'border':0,'header':0,'align':'Left','cells':[],'cellalign':[]}
    1464. 

  1464. 	# detect table align (and remove spaces mark)
    1465. 

  1465. 	if line[0] == ' ': ret['align'] = 'Center'
    1466. 

  1466. 	line = string.lstrip(line)
    1467. 

  1467. 	# detect header (title) mark
    1468. 

  1468. 	if line[1] == '|':
    1469. 

  1469. 		ret['header'] = 1
    1470. 

  1470. 	# delete trailing spaces after last cell border
    1471. 

  1471. 	line = re.sub('\|\s*$','|', line)
    1472. 

  1472. 	# detect (and delete) border mark (and leading sp…
    1473.

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