PageRenderTime 35ms CodeModel.GetById 12ms RepoModel.GetById 0ms app.codeStats 1ms

/old/txt2tags-1.7.py

http://txt2tags.googlecode.com/
Python | 2628 lines | 2582 code | 16 blank | 30 comment | 9 complexity | f705939eba7a6267cceef0ee2a39b8ff MD5 | raw file
Possible License(s): GPL-2.0, GPL-3.0, WTFPL 
    

  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 = '1.7'                               #-betaN
    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 ,'dump-source':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. currently supported:
    74. 

  74.                      %s
    75. 

  75. 

  76.   -o, --outfile=FILE set FILE as the output file name ('-' 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 (depth) 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 file name.
    98. 

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

  99. If output file 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, remove_linebreaks=0):
    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. 	if remove_linebreaks:
    249. 

  249. 		data = map(lambda x:re.sub('[\n\r]+$','',x), data)
    250. 

  250. 	return data
    251. 

  251. def Savefile(file, contents):
    252. 

  252. 	try: f = open(file, 'wb')
    253. 

  253. 	except: Error("Cannot open file for writing:\n    %s"%file)
    254. 

  254. 	if type(contents) == type([]): doit = f.writelines
    255. 

  255. 	else: doit = f.write
    256. 

  256. 	doit(contents) ; f.close()
    257. 

  257. 

  258. 

  259. def get_include_contents(file, path=''):
    260. 

  260. 	"Parses %!include: value and extract file contents"
    261. 

  261. 	# set include type
    262. 

  262. 	id = 'T2T'
    263. 

  263. 	if file[0] == file[-1] == '`':
    264. 

  264. 		id = 'VERB'
    265. 

  265. 		file = file[1:-1]  # remove ``
    266. 

  266. 	elif file[0] == file[-1] == "'":
    267. 

  267. 		id = 'PASS'
    268. 

  268. 		file = file[1:-1]  # remove ''
    269. 

  269. 	# handle remote dir execution
    270. 

  270. 	filepath = os.path.join(path, file)
    271. 

  271. 	# pass-thru
    272. 

  272. 	if id == 'PASS':
    273. 

  273. 		return id, Readfile(filepath, remove_linebreaks=1)
    274. 

  274. 	# VERB text
    275. 

  275. 	if id == 'VERB':
    276. 

  276. 		lines = Readfile(filepath, remove_linebreaks=1)
    277. 

  277. 		# escape inner '---' that would end VERB block
    278. 

  278. 		lines = map(lambda x: re.sub('^---$','--- ',x), lines)
    279. 

  279. 		# add VERB block identifiers
    280. 

  280. 		lines = ['---'] + lines + ['---']
    281. 

  281. 	# default txt2tags marked text
    282. 

  282. 	else:
    283. 

  283. 		id = 'T2T'
    284. 

  284. 		lines = get_file_body(filepath)
    285. 

  285. 	# add delimiter comments
    286. 

  286. 	lines.insert(0, '%%INCLUDED_%s starts here: %s'%(id,file))
    287. 

  287. 	lines.append('%%INCLUDED_%s ends here: %s'%(id,file))
    288. 

  288. 	return id, lines
    289. 

  289. 

  290. 

  291. def ParseConfig(text='',name='', target=''):
    292. 

  292. 	ret = {}
    293. 

  293. 	if not text: return ret
    294. 

  294. 	re_name = name or '[a-z]+'
    295. 

  295. 	re_target = target or '[a-z]*'
    296. 

  296. 	cfgregex = re.compile("""
    297. 

  297. 	  ^%%!\s*               # leading id with opt spaces
    298. 

  298. 	  (?P<name>%s)\s*       # config name 
    299. 

  299. 	  (\((?P<target>%s)\))? # optional target spec inside ()
    300. 

  300. 	  \s*:\s*               # key:value delimiter with opt spaces
    301. 

  301. 	  (?P<value>\S.+?)      # config value
    302. 

  302. 	  \s*$                  # rstrip() spaces and hit EOL
    303. 

  303. 	  """%(re_name,re_target), re.I+re.VERBOSE)
    304. 

  304. 	prepostregex = re.compile("""
    305. 

  305. 	                        # ---[ PATTERN ]---
    306. 

  306. 	  ^( "([^"]*)"            # "double quoted" or
    307. 

  307. 	   | '([^']*)'            # 'single quoted' or
    308. 

  308. 	   | ([^\s]+)             # single_word
    309. 

  309. 	   )
    310. 

  310. 	    \s+                 # separated by spaces
    311. 

  311. 	   
    312. 

  312. 		                    # ---[ REPLACE ]---
    313. 

  313. 	       ( "([^"]*)"        # "double quoted" or
    314. 

  314. 	       | '([^']*)'        # 'single quoted' or
    315. 

  315. 	       | (.*)             # anything
    316. 

  316. 		   )
    317. 

  317. 		    \s*$
    318. 

  318. 	  """, re.VERBOSE)
    319. 

  319. 	match = cfgregex.match(text)
    320. 

  320. 	if match:
    321. 

  321. 		ret = {'name'  :string.lower(match.group('name') or ''),
    322. 

  322. 		       'target':string.lower(match.group('target') or 'all'),
    323. 

  323. 		       'value' :match.group('value') }
    324. 

  324. 		
    325. 

  325. 		# Special config with two quoted values (%!preproc: "foo" 'bar')
    326. 

  326. 		if ret['name'] in ['preproc','postproc']:
    327. 

  327. 			valmatch = prepostregex.search(ret['value'])
    328. 

  328. 			if not valmatch: return None
    329. 

  329. 			getval = valmatch.group
    330. 

  330. 			patt = getval(2) or getval(3) or getval(4) or ''
    331. 

  331. 			repl = getval(6) or getval(7) or getval(8) or ''
    332. 

  332. 			ret['value'] = (patt, repl)
    333. 

  333. 	
    334. 

  334. 	return ret
    335. 

  335. 

  336. 

  337. class Cmdline:
    338. 

  338. 	def __init__(self, cmdline=[], nocheck=0):
    339. 

  339. 		self.conf = {}
    340. 

  340. 		self.cmdline = cmdline
    341. 

  341. 		self.cmdline_conf = {}
    342. 

  342. 		self.dft_options = OPTIONS.copy()
    343. 

  343. 		self.dft_flags   = FLAGS.copy()
    344. 

  344. 		self.all_options = self.dft_options.keys()
    345. 

  345. 		self.all_flags   = self.dft_flags.keys()
    346. 

  346. 		self.defaults = self._get_empty_conf()
    347. 

  347. 		self.nocheck = nocheck
    348. 

  348. 		if cmdline: self.parse()
    349. 

  349. 	
    350. 

  350. 	#TODO protect quotes contents
    351. 

  351. 	def _tokenize(self, cmd_string):
    352. 

  352. 		return string.split(cmd_string)
    353. 

  353. 	
    354. 

  354. 	def parse(self):
    355. 

  355. 		"return a dic with all options:value found"
    356. 

  356. 		if not self.cmdline: return {}
    357. 

  357. 		Debug("cmdline: %s"%self.cmdline, 1)
    358. 

  358. 		options = {'infile': '', 'infiles':''}
    359. 

  359. 		# compose valid options list
    360. 

  360. 		longopts = ['help','version'] + self.all_flags + \
    361. 

  361. 		           map(lambda x:x+'=', self.all_options) # add =
    362. 

  362. 		cmdline = self.cmdline[1:]           # del prog name  
    363. 

  363. 		# get cmdline options
    364. 

  364. 		try: (opt, args) = getopt.getopt(cmdline, 'hVnHt:o:', longopts)
    365. 

  365. 		except getopt.error, errmsg:
    366. 

  366. 			Error("%s (try --help)"%errmsg)
    367. 

  367. 		# get infile, if any
    368. 

  368. 		if args:
    369. 

  369. 			options['infile'] = args[0]
    370. 

  370. 			options['infiles'] = args  # multi
    371. 

  371. 		# parse all options
    372. 

  372. 		for name,val in opt:
    373. 

  373. 			if   name in ['-h','--help'   ]: Quit(usage)
    374. 

  374. 			elif name in ['-V','--version']: Quit(versionstr)
    375. 

  375. 			elif name in ['-t','--type'     ]: options['type'] = val
    376. 

  376. 			elif name in ['-o','--outfile'  ]: options['outfile'] = val
    377. 

  377. 			elif name in ['-n','--enumtitle']: options['enumtitle'] = 1
    378. 

  378. 			elif name in ['-H','--noheaders']: options['noheaders'] = 1
    379. 

  379. 			elif name in ['--stdout']: options['outfile'] = STDOUT
    380. 

  380. 			else: options[name[2:]] = val or 1 # del --
    381. 

  381. 		# save results
    382. 

  382. 		Debug("cmdline arguments: %s"%options, 1)
    383. 

  383. 		self.cmdline_conf = options
    384. 

  384. 	
    385. 

  385. 	def compose(self, conf={}):
    386. 

  386. 		"compose full command line from CONF dict"
    387. 

  387. 		if not conf: return ''
    388. 

  388. 		args = []
    389. 

  389. 		cfg = conf.copy()
    390. 

  390. 		valid_opts = self.all_options + self.all_flags
    391. 

  391. 		use_short = {'noheaders':'H', 'enumtitle':'n'}
    392. 

  392. 		# remove useless options
    393. 

  393. 		if cfg.get('toconly'):
    394. 

  394. 			del cfg['noheaders']
    395. 

  395. 			del cfg['outfile']        # defaults to STDOUT
    396. 

  396. 			if cfg.get('type') == 'txt':
    397. 

  397. 				del cfg['type']       # already default
    398. 

  398. 			args.append('--toconly')  # must be the first
    399. 

  399. 			del cfg['toconly']
    400. 

  400. 		# add target type
    401. 

  401. 		if cfg.has_key('type'):
    402. 

  402. 			args.append('-t '+cfg['type'])
    403. 

  403. 			del cfg['type']
    404. 

  404. 		# add other options
    405. 

  405. 		for key in cfg.keys():
    406. 

  406. 			if key not in valid_opts: continue  # must be a %!setting
    407. 

  407. 			if key == 'outfile': continue       # later
    408. 

  408. 			val = cfg[key]
    409. 

  409. 			if not val: continue
    410. 

  410. 			# default values are useless on cmdline
    411. 

  411. 			if val == self.dft_options.get(key): continue
    412. 

  412. 			# -short format
    413. 

  413. 			if key in use_short.keys():
    414. 

  414. 				args.append('-'+use_short[key])
    415. 

  415. 				continue
    416. 

  416. 			# --long format
    417. 

  417. 			if key in self.all_flags: # add --option
    418. 

  418. 				args.append('--'+key)
    419. 

  419. 			else:                     # add --option=value
    420. 

  420. 				args.append('--%s=%s'%(key,val))
    421. 

  421. 		# the outfile using -o
    422. 

  422. 		if cfg.has_key('outfile') and \
    423. 

  423. 		   cfg['outfile'] != self.dft_options.get('outfile'):
    424. 

  424. 			args.append('-o '+cfg['outfile'])
    425. 

  425. 		# the input file is always at the end
    426. 

  426. 		if cfg.has_key('infile'):
    427. 

  427. 			args.append(cfg['infile'])
    428. 

  428. 		# return as a single string
    429. 

  429. 		ret = string.join(args,' ')
    430. 

  430. 		Debug("Diet command line: %s"%ret, 1)
    431. 

  431. 		return ret
    432. 

  432. 	
    433. 

  433. 	def merge(self, extraopts=''):
    434. 

  434. 		"insert cmdline portion BEFORE current cmdline"
    435. 

  435. 		if not extraopts: return
    436. 

  436. 		if type(extraopts) == type(''):
    437. 

  437. 			extraopts = self._tokenize(extraopts)
    438. 

  438. 		if not self.cmdline: self.cmdline = extraopts
    439. 

  439. 		else: self.cmdline = ['t2t-merged'] +extraopts +self.cmdline[1:]
    440. 

  440. 		self.parse()
    441. 

  441. 	
    442. 

  442. 	def _get_outfile_name(self, conf):
    443. 

  443. 		"dirname is the same for {in,out}file"
    444. 

  444. 		infile = conf['infile']
    445. 

  445. 		if not infile: return ''
    446. 

  446. 		if infile == STDIN or conf['outfile'] == STDOUT:
    447. 

  447. 			outfile = STDOUT
    448. 

  448. 		else:
    449. 

  449. 			basename = re.sub('\.(txt|t2t)$','',infile)
    450. 

  450. 			outfile = "%s.%s"%(basename, conf['type'])
    451. 

  451. 		self.dft_options['outfile'] = outfile # save for self.compose()
    452. 

  452. 		Debug(" infile: '%s'"%infile , 1)
    453. 

  453. 		Debug("outfile: '%s'"%outfile, 1)
    454. 

  454. 		return outfile
    455. 

  455. 	
    456. 

  456. 	def _sanity(self, dic):
    457. 

  457. 		"basic cmdline syntax checkings"
    458. 

  458. 		if not dic: return {}
    459. 

  459. 		if not dic['infile'] or not dic['type']:
    460. 

  460. 			Quit(usage, 1)                  # no filename/doctype
    461. 

  461. 		if not targets.count(dic['type']):      # check target
    462. 

  462. 			Error("Invalid document type '%s' (try --help)"%(
    463. 

  463. 			       dic['type']))
    464. 

  464. 		#DISABLED: conflicting with %!cmdline: -o foo	   
    465. 

  465. 		#if len(dic['infiles']) > 1 and dic['outfile']: # -o FILE *.t2t
    466. 

  466. 		#	Error("--outfile can't be used with multiple files")
    467. 

  467. 		for opt in self.all_options:            # check numeric options
    468. 

  468. 			opttype = type(self.dft_options[opt])
    469. 

  469. 			if dic.get(opt) and opttype == type(9):
    470. 

  470. 				try: dic[opt] = int(dic.get(opt)) # save
    471. 

  471. 				except: Error('--%s value must be a number'%opt)
    472. 

  472. 		if dic['split'] not in [0,1,2]:         # check split level
    473. 

  473. 			Error('Option --split must be 0, 1 or 2')
    474. 

  474. 		return dic
    475. 

  475. 	
    476. 

  476. 	def merge_conf(self, newconfs={}, override=0):
    477. 

  477. 		"include Config Area settings into self.conf"
    478. 

  478. 		if not self.conf: self.get_conf()
    479. 

  479. 		if not newconfs: return self.conf
    480. 

  480. 		for key in newconfs.keys():
    481. 

  481. 			if key == 'cmdline': continue   # already done
    482. 

  482. 			# filters are always accumulative
    483. 

  483. 			if key in ['preproc','postproc']:
    484. 

  484. 				if not self.conf.has_key(key):
    485. 

  485. 					self.conf[key] = []
    486. 

  486. 				self.conf[key].extend(newconfs[key])
    487. 

  487. 				continue
    488. 

  488. 			# add anyway
    489. 

  489. 			if override:
    490. 

  490. 				self.conf[key] = newconfs[key]
    491. 

  491. 				continue
    492. 

  492. 			# just update if still 'virgin'
    493. 

  493. 			if self.conf.has_key(key) and \
    494. 

  494. 			   self.conf[key] == self.defaults.get(key):
    495. 

  495. 				self.conf[key] = newconfs[key]
    496. 

  496. 			# add new
    497. 

  497. 			if not self.conf.has_key(key):
    498. 

  498. 				self.conf[key] = newconfs[key]
    499. 

  499. 		
    500. 

  500. 		Debug("Merged CONF (override=%s): %s"%(override,self.conf), 1)
    501. 

  501. 		return self.conf
    502. 

  502. 	
    503. 

  503. 	def _get_empty_conf(self):
    504. 

  504. 		econf = self.dft_options.copy()
    505. 

  505. 		for k in self.dft_flags.keys(): econf[k] = self.dft_flags[k]
    506. 

  506. 		return econf
    507. 

  507. 	
    508. 

  508. 	def get_conf(self):
    509. 

  509. 		"set vars and flags according to options dic"
    510. 

  510. 		if not self.cmdline_conf:
    511. 

  511. 			if not self.cmdline: return {}
    512. 

  512. 			self.parse()
    513. 

  513. 		dic = self.cmdline_conf
    514. 

  514. 		conf = self.defaults.copy()
    515. 

  515. 		
    516. 

  516. 		## store flags & options
    517. 

  517. 		for flag in self.all_flags:
    518. 

  518. 			if dic.has_key(flag): conf[flag] = 1
    519. 

  519. 		for opt in self.all_options + ['infile', 'infiles']:
    520. 

  520. 			if dic.has_key(opt): conf[opt] = dic.get(opt)
    521. 

  521. 		
    522. 

  522. 		if not conf['type'] and conf['toconly']: conf['type'] = 'txt'
    523. 

  523. 		if not conf['type'] and conf['dump-source']: conf['type'] = 'txt'
    524. 

  524. 		if not self.nocheck: conf = self._sanity(conf)
    525. 

  525. 		
    526. 

  526. 		## some gotchas for specific issues
    527. 

  527. 		doctype = conf['type']
    528. 

  528. 		infile = conf['infile']
    529. 

  529. 		
    530. 

  530. 		# toconly is stronger than others
    531. 

  531. 		if conf['toconly']:
    532. 

  532. 			conf['noheaders'] = 1
    533. 

  533. 			conf['toc'] = 0
    534. 

  534. 			conf['split'] = 0
    535. 

  535. 			conf['gui'] = 0
    536. 

  536. 			conf['outfile'] = STDOUT
    537. 

  537. 			conf['toclevel'] = conf['toclevel'] or \
    538. 

  538. 			                   self.dft_options['toclevel']
    539. 

  539. 		
    540. 

  540. 		# dump-source is stronger than others (including toconly)
    541. 

  541. 		if conf['dump-source']:
    542. 

  542. 			conf['toconly'] = 0
    543. 

  543. 			conf['noheaders'] = 0
    544. 

  544. 			conf['toc'] = 0
    545. 

  545. 			conf['split'] = 0
    546. 

  546. 			conf['gui'] = 0
    547. 

  547. 			conf['outfile'] = STDOUT
    548. 

  548. 		
    549. 

  549. 		# split: just HTML, no stdout, 1st do a sgml, then sgml2html
    550. 

  550. 		if conf['split']:
    551. 

  551. 			if doctype != 'html':
    552. 

  552. 				conf['split'] = 0
    553. 

  553. 			else:
    554. 

  554. 				conf['type'] = 'sgml' 
    555. 

  555. 				if conf['outfile'] == STDOUT:
    556. 

  556. 					conf['outfile'] = ''
    557. 

  557. 		
    558. 

  558. 		outfile = conf['outfile'] or self._get_outfile_name(conf)
    559. 

  559. 		
    560. 

  560. 		# final checkings
    561. 

  561. 		if conf['split'] and outfile == STDOUT:
    562. 

  562. 			Error('--split: You must provide a FILE (not STDIN)')
    563. 

  563. 		if infile == outfile and outfile != STDOUT:
    564. 

  564. 			Error("SUICIDE WARNING!!!  (see --outfile)\n  source"+\
    565. 

  565. 			      " and target files has the same name: "+outfile)
    566. 

  566. 		### author's note: "yes, i've got my sample.t2t file deleted
    567. 

  567. 		### before add this test... :/"
    568. 

  568. 		
    569. 

  569. 		conf['outfile'] = outfile
    570. 

  570. 		conf['cmdline'] = self.cmdline
    571. 

  571. 		Debug("CONF data: %s\n"%conf, 1)
    572. 

  572. 		self.conf = conf
    573. 

  573. 		return self.conf
    574. 

  574. #
    575. 

  575. ### End of Cmdline class
    576. 

  576. 

  577. 

  578. 

  579. 

  580. class Proprierties:
    581. 

  581. 	def __init__(self, filename=''):
    582. 

  582. 		self.buffer = ['']   # text start at pos 1
    583. 

  583. 		self.areas = ['head','conf','body']
    584. 

  584. 		self.arearef = []
    585. 

  585. 		self.headers = ['','','']
    586. 

  586. 		self.config = self.get_empty_config()
    587. 

  587. 		self.lastline = 0
    588. 

  588. 		self.filename = filename
    589. 

  589. 		self.conflines = []
    590. 

  590. 		self.bodylines = []
    591. 

  591. 		if filename:
    592. 

  592. 			self.read_file(filename)
    593. 

  593. 			self.find_areas()
    594. 

  594. 			self.set_headers()
    595. 

  595. 			self.set_config()
    596. 

  596. 	
    597. 

  597. 	def read_file(self, file):
    598. 

  598. 		lines = Readfile(file)
    599. 

  599. 		if not lines: Error('Empty file! %s'%file)
    600. 

  600. 		self.buffer.extend(lines)
    601. 

  601. 	
    602. 

  602. 	def get_empty_config(self):
    603. 

  603. 		empty = {}
    604. 

  604. 		for targ in targets+['all']: empty[targ] = {}
    605. 

  605. 		return empty
    606. 

  606. 	
    607. 

  607. 	def find_areas(self):
    608. 

  608. 		"Run through buffer and identify head/conf/body areas"
    609. 

  609. 		buf = self.buffer ; ref = [1,4,0]       # defaults
    610. 

  610. 		if not string.strip(buf[1]):            # no header
    611. 

  611. 			ref[0] = 0 ; ref[1] = 2
    612. 

  612. 		for i in range(ref[1],len(buf)):        # find body init
    613. 

  613. 			if string.strip(buf[i]) and buf[i][0] != '%':
    614. 

  614. 				ref[2] = i ; break      # !blank, !comment
    615. 

  615. 			if ParseConfig(buf[i], 'include'):
    616. 

  616. 				ref[2] = i ; break      # %!include command
    617. 

  617. 		if ref[1] == ref[2]: ref[1] = 0         # no conf area
    618. 

  618. 		for i in 0,1,2:                         # del !existent
    619. 

  619. 			if not ref[i]: self.areas[i] = ''
    620. 

  620. 		self.arearef = ref                      # save results
    621. 

  621. 		self.lastline = len(self.buffer)-1
    622. 

  622. 		Debug('Head,Conf,Body start line: %s'%ref, 1)
    623. 

  623. 		# store CONF and BODY lines found
    624. 

  624. 		cfgend = ref[2] or len(buf)
    625. 

  625. 		self.conflines = buf[ref[1]:cfgend]
    626. 

  626. 		if ref[2]: self.bodylines = buf[ref[2]:]
    627. 

  627. 	
    628. 

  628. 	
    629. 

  629. 	def set_headers(self):
    630. 

  630. 		"Extract and save headers contents"
    631. 

  631. 		if not self.arearef: self.find_areas()
    632. 

  632. 		if not self.areas.count('head'): return
    633. 

  633. 		if self.lastline < 3:
    634. 

  634. 			#TODO on gui this checking is !working
    635. 

  635. 			Error(
    636. 

  636. 			"Premature end of Headers on '%s'."%self.filename +\
    637. 

  637. 			'\n\nFile has %s line(s), but '%self.lastline     +\
    638. 

  638. 			'Headers should be composed by 3 lines. '         +\
    639. 

  639. 			'\nMaybe you should left the first line blank? '  +\
    640. 

  640. 			'(for no headers)')
    641. 

  641. 		for i in 0,1,2:
    642. 

  642. 			self.headers[i] = string.strip(self.buffer[i+1])
    643. 

  643. 		Debug("Headers found: %s"%self.headers, 1, i+1)
    644. 

  644. 	
    645. 

  645. 	def set_config(self):
    646. 

  646. 		"Extract and save config contents (including includes)"
    647. 

  647. 		if not self.arearef: self.find_areas()
    648. 

  648. 		if not self.areas.count('conf'): return
    649. 

  649. 		keywords = string.join(CONFIG_KEYWORDS, '|')
    650. 

  650. 		linenr = self.arearef[1]-1  # for debug messages
    651. 

  651. 		for line in self.conflines:
    652. 

  652. 			linenr = linenr + 1
    653. 

  653. 			if len(line) < 3: continue
    654. 

  654. 			if line[:2] != '%!': continue
    655. 

  655. 			cfg = ParseConfig(line, keywords)
    656. 

  656. 			# any _valid_ config found?
    657. 

  657. 			if not cfg:
    658. 

  658. 				Debug('Bogus Config Line',1,linenr)
    659. 

  659. 				continue
    660. 

  660. 			# get data	
    661. 

  661. 			targ, key, val = cfg['target'],cfg['name'], cfg['value']
    662. 

  662. 			# check config target specification
    663. 

  663. 			if targ not in targets+['all']:
    664. 

  664. 				Debug("Config Error: Invalid target '%s', ignoring"%targ,
    665. 

  665. 				      1,linenr)
    666. 

  666. 				continue
    667. 

  667. 			# filters are multiple config
    668. 

  668. 			if key in ['preproc','postproc']:
    669. 

  669. 				if not self.config['all'].has_key(key):  # 1st one
    670. 

  670. 					self.config['all'][key] = []
    671. 

  671. 				# all filters are saved to target 'all'
    672. 

  672. 				# finish_him will decide what to consider
    673. 

  673. 				self.config['all'][key].append((targ,)+val)
    674. 

  674. 			else:
    675. 

  675. 				self.config[targ][key] = val
    676. 

  676. 			Debug("Found config for target '%s': '%s', value '%s'"%(
    677. 

  677. 			       targ,key,val),1,linenr)
    678. 

  678. 		Debug("All %%!CONFIG: %s"%self.config, 1)
    679. 

  679. 

  680. 

  681. def get_file_body(file):
    682. 

  682. 	"Returns all the document BODY lines (including includes)"
    683. 

  683. 	prop = Proprierties()
    684. 

  684. 	prop.read_file(file)
    685. 

  685. 	prop.find_areas()
    686. 

  686. 	return prop.bodylines
    687. 

  687. 

  688. 

  689. def finish_him(outlist, CONF):
    690. 

  690. 	"Writing output to screen or file"
    691. 

  691. 	outfile = CONF['outfile']
    692. 

  692. 	outlist = unmaskEscapeChar(outlist)
    693. 

  693. 	
    694. 

  694. 	# do PostProc
    695. 

  695. 	if CONF['postproc']:
    696. 

  696. 		postoutlist = []
    697. 

  697. 		for line in outlist:
    698. 

  698. 			for targ,patt,repl in CONF['postproc']:
    699. 

  699. 				if targ not in [CONF['type'], 'all']: continue
    700. 

  700. 				try   : line = re.sub(patt, repl, line)
    701. 

  701. 				except: Error("Invalid PostProc filter regex: '%s'"%patt)
    702. 

  702. 			postoutlist.append(line)
    703. 

  703. 		outlist = postoutlist[:]
    704. 

  704. 	
    705. 

  705. 	if outfile == STDOUT:
    706. 

  706. 		if CONF['gui']:
    707. 

  707. 			return outlist
    708. 

  708. 		else:
    709. 

  709. 			for line in outlist: print line
    710. 

  710. 	else:
    711. 

  711. 		Savefile(outfile, addLineBreaks(outlist))
    712. 

  712. 		if not CONF['gui']: print 'wrote %s'%(outfile)
    713. 

  713. 	
    714. 

  714. 	if CONF['split']:
    715. 

  715. 		print "--- html..."
    716. 

  716. 		sgml2html = 'sgml2html -s %s -l %s %s'%(
    717. 

  717. 		            CONF['split'],CONF['lang'] or lang,outfile)
    718. 

  718. 		print "Running system command:", sgml2html
    719. 

  719. 		os.system(sgml2html)
    720. 

  720. 

  721. 

  722. def toc_maker(toc, conf):
    723. 

  723. 	"Compose TOC list 'by hand'"
    724. 

  724. 	# TOC is a tag, so there's nothing to do here
    725. 

  725. 	if TAGS['TOC']: return []
    726. 

  726. 	# toc is a valid t2t marked text (list type), that is converted
    727. 

  727. 	if conf['toc'] or conf['toconly']:
    728. 

  728. 		fakeconf = conf.copy()
    729. 

  729. 		fakeconf['noheaders'] = 1
    730. 

  730. 		fakeconf['toconly']   = 0
    731. 

  731. 		fakeconf['maskemail'] = 0
    732. 

  732. 		fakeconf['dump-source'] = 0
    733. 

  733. 		fakeconf['preproc'] = []
    734. 

  734. 		fakeconf['postproc'] = []
    735. 

  735. 		toc,foo = convert(toc, fakeconf)
    736. 

  736. 	# TOC between bars (not for --toconly)
    737. 

  737. 	if conf['toc']:
    738. 

  738. 		para = TAGS['paragraph']
    739. 

  739. 		tocbar = [para, regex['x'].sub('-'*72,TAGS['bar1']), para]
    740. 

  740. 		toc = tocbar + toc + tocbar
    741. 

  741. 	return toc
    742. 

  742. 

  743. 

  744. def getTags(doctype):
    745. 

  745. 	keys = [
    746. 

  746. 	'paragraph','title1','title2','title3','title4','title5',
    747. 

  747. 	'numtitle1','numtitle2','numtitle3','numtitle4','numtitle5',
    748. 

  748. 	'areaPreOpen','areaPreClose',
    749. 

  749. 	'areaQuoteOpen','areaQuoteClose',
    750. 

  750. 	'fontMonoOpen','fontMonoClose',
    751. 

  751. 	'fontBoldOpen','fontBoldClose',
    752. 

  752. 	'fontItalicOpen','fontItalicClose',
    753. 

  753. 	'fontBolditalicOpen','fontBolditalicClose',
    754. 

  754. 	'fontUnderlineOpen','fontUnderlineClose',
    755. 

  755. 	'listOpen','listClose','listItem',
    756. 

  756. 	'numlistOpen','numlistClose','numlistItem',
    757. 

  757. 	'deflistOpen','deflistClose','deflistItem1','deflistItem2',
    758. 

  758. 	'bar1','bar2',
    759. 

  759. 	'url','urlMark','email','emailMark',
    760. 

  760. 	'img','imgsolo',
    761. 

  761. 	'tableOpen','tableClose','tableLineOpen','tableLineClose',
    762. 

  762. 	'tableCellOpen','tableCellClose',
    763. 

  763. 	'tableTitleCellOpen','tableTitleCellClose',
    764. 

  764. 	'anchor','comment','TOC',
    765. 

  765. 	'EOD'
    766. 

  766. 	]
    767. 

  767. 	
    768. 

  768. 	alltags = {
    769. 

  769. 	
    770. 

  770. 	'txt': {
    771. 

  771. 	   'title1'              : '  \a'      ,
    772. 

  772. 	   'title2'              : '\t\a'      ,
    773. 

  773. 	   'title3'              : '\t\t\a'    ,
    774. 

  774. 	   'title4'              : '\t\t\t\a'  ,
    775. 

  775. 	   'title5'              : '\t\t\t\t\a',
    776. 

  776. 	   'areaQuoteOpen'       : '    '      ,
    777. 

  777. 	   'listItem'            : '- '        ,
    778. 

  778. 	   'numlistItem'         : '\a. '      ,
    779. 

  779. 	   'bar1'                : '\a'        ,
    780. 

  780. 	   'bar2'                : '\a'        ,
    781. 

  781. 	   'url'                 : '\a'        ,
    782. 

  782. 	   'urlMark'             : '\a (\a)'   ,
    783. 

  783. 	   'email'               : '\a'        ,
    784. 

  784. 	   'emailMark'           : '\a (\a)'   ,
    785. 

  785. 	   'img'                 : '[\a]'      ,
    786. 

  786. 	},
    787. 

  787. 	
    788. 

  788. 	'html': {
    789. 

  789. 	   'paragraph'           : '<P>'            ,
    790. 

  790. 	   'title1'              : '<H1>\a</H1>'    ,
    791. 

  791. 	   'title2'              : '<H2>\a</H2>'    ,
    792. 

  792. 	   'title3'              : '<H3>\a</H3>'    ,
    793. 

  793. 	   'title4'              : '<H4>\a</H4>'    ,
    794. 

  794. 	   'title5'              : '<H5>\a</H5>'    ,
    795. 

  795. 	   'areaPreOpen'         : '<PRE>'          ,
    796. 

  796. 	   'areaPreClose'        : '</PRE>'         ,
    797. 

  797. 	   'areaQuoteOpen'       : '<BLOCKQUOTE>'   ,
    798. 

  798. 	   'areaQuoteClose'      : '</BLOCKQUOTE>'  ,
    799. 

  799. 	   'fontMonoOpen'        : '<CODE>'         ,
    800. 

  800. 	   'fontMonoClose'       : '</CODE>'        ,
    801. 

  801. 	   'fontBoldOpen'        : '<B>'            ,
    802. 

  802. 	   'fontBoldClose'       : '</B>'           ,
    803. 

  803. 	   'fontItalicOpen'      : '<I>'            ,
    804. 

  804. 	   'fontItalicClose'     : '</I>'           ,
    805. 

  805. 	   'fontBolditalicOpen'  : '<B><I>'         ,
    806. 

  806. 	   'fontBolditalicClose' : '</I></B>'       ,
    807. 

  807. 	   'fontUnderlineOpen'   : '<U>'            ,
    808. 

  808. 	   'fontUnderlineClose'  : '</U>'           ,
    809. 

  809. 	   'listOpen'            : '<UL>'           ,
    810. 

  810. 	   'listClose'           : '</UL>'          ,
    811. 

  811. 	   'listItem'            : '<LI>'           ,
    812. 

  812. 	   'numlistOpen'         : '<OL>'           ,
    813. 

  813. 	   'numlistClose'        : '</OL>'          ,
    814. 

  814. 	   'numlistItem'         : '<LI>'           ,
    815. 

  815. 	   'deflistOpen'         : '<DL>'           ,
    816. 

  816. 	   'deflistClose'        : '</DL>'          ,
    817. 

  817. 	   'deflistItem1'        : '<DT>\a</DT>'    ,
    818. 

  818. 	   'deflistItem2'        : '<DD>'           ,
    819. 

  819. 	   'bar1'                : '<HR NOSHADE SIZE=1>'        ,
    820. 

  820. 	   'bar2'                : '<HR NOSHADE SIZE=5>'        ,
    821. 

  821. 	   'url'                 : '<A HREF="\a">\a</A>'        ,
    822. 

  822. 	   'urlMark'             : '<A HREF="\a">\a</A>'        ,
    823. 

  823. 	   'email'               : '<A HREF="mailto:\a">\a</A>' ,
    824. 

  824. 	   'emailMark'           : '<A HREF="mailto:\a">\a</A>' ,
    825. 

  825. 	   'img'                 : '<IMG ALIGN="\a" SRC="\a" BORDER="0">',
    826. 

  826. 	   'imgsolo'             : '<P ALIGN="center">\a</P>'   ,
    827. 

  827. 	   'tableOpen'           : '<table\a cellpadding=4 border=\a>',
    828. 

  828. 	   'tableClose'          : '</table>'       ,
    829. 

  829. 	   'tableLineOpen'       : '<tr>'           ,
    830. 

  830. 	   'tableLineClose'      : '</tr>'          ,
    831. 

  831. 	   'tableCellOpen'       : '<td\a>'         ,
    832. 

  832. 	   'tableCellClose'      : '</td>'          ,
    833. 

  833. 	   'tableTitleCellOpen'  : '<th>'           ,
    834. 

  834. 	   'tableTitleCellClose' : '</th>'          ,
    835. 

  835. 	   'tableAlignLeft'      : ''               ,
    836. 

  836. 	   'tableAlignCenter'    : ' align="center"',
    837. 

  837. 	   'tableCellAlignLeft'  : ''               ,
    838. 

  838. 	   'tableCellAlignRight' : ' align="right"' ,
    839. 

  839. 	   'tableCellAlignCenter': ' align="center"',
    840. 

  840. 	   'anchor'              : '<a name="\a"></a>',
    841. 

  841. 	   'comment'             : '<!-- \a -->'    ,
    842. 

  842. 	   'EOD'                 : '</BODY></HTML>'
    843. 

  843. 	},
    844. 

  844. 	
    845. 

  845. 	'sgml': {
    846. 

  846. 	   'paragraph'           : '<p>'                ,
    847. 

  847. 	   'title1'              : '<sect>\a<p>'        ,
    848. 

  848. 	   'title2'              : '<sect1>\a<p>'       ,
    849. 

  849. 	   'title3'              : '<sect2>\a<p>'       ,
    850. 

  850. 	   'title4'              : '<sect3>\a<p>'       ,
    851. 

  851. 	   'title5'              : '<sect4>\a<p>'       ,
    852. 

  852. 	   'areaPreOpen'         : '<tscreen><verb>'    ,
    853. 

  853. 	   'areaPreClose'        : '</verb></tscreen>'  ,
    854. 

  854. 	   'areaQuoteOpen'       : '<quote>'            ,
    855. 

  855. 	   'areaQuoteClose'      : '</quote>'           ,
    856. 

  856. 	   'fontMonoOpen'        : '<tt>'               ,
    857. 

  857. 	   'fontMonoClose'       : '</tt>'              ,
    858. 

  858. 	   'fontBoldOpen'        : '<bf>'               ,
    859. 

  859. 	   'fontBoldClose'       : '</bf>'              ,
    860. 

  860. 	   'fontItalicOpen'      : '<em>'               ,
    861. 

  861. 	   'fontItalicClose'     : '</em>'              ,
    862. 

  862. 	   'fontBolditalicOpen'  : '<bf><em>'           ,
    863. 

  863. 	   'fontBolditalicClose' : '</em></bf>'         ,
    864. 

  864. 	   'fontUnderlineOpen'   : '<bf><em>'           ,
    865. 

  865. 	   'fontUnderlineClose'  : '</em></bf>'         ,
    866. 

  866. 	   'listOpen'            : '<itemize>'          ,
    867. 

  867. 	   'listClose'           : '</itemize>'         ,
    868. 

  868. 	   'listItem'            : '<item>'             ,
    869. 

  869. 	   'numlistOpen'         : '<enum>'             ,
    870. 

  870. 	   'numlistClose'        : '</enum>'            ,
    871. 

  871. 	   'numlistItem'         : '<item>'             ,
    872. 

  872. 	   'deflistOpen'         : '<descrip>'          ,
    873. 

  873. 	   'deflistClose'        : '</descrip>'         ,
    874. 

  874. 	   'deflistItem1'        : '<tag>\a</tag>'      ,
    875. 

  875. 	   'bar1'                : '<!-- \a -->'        ,
    876. 

  876. 	   'bar2'                : '<!-- \a -->'        ,
    877. 

  877. 	   'url'                 : '<htmlurl url="\a" name="\a">'        ,
    878. 

  878. 	   'urlMark'             : '<htmlurl url="\a" name="\a">'        ,
    879. 

  879. 	   'email'               : '<htmlurl url="mailto:\a" name="\a">' ,
    880. 

  880. 	   'emailMark'           : '<htmlurl url="mailto:\a" name="\a">' ,
    881. 

  881. 	   'img'                 : '<figure><ph vspace=""><img src="\a">'+\
    882. 

  882. 	                           '</figure>'                           ,
    883. 

  883. 	   'tableOpen'           : '<table><tabular ca="\a">'            ,
    884. 

  884. 	   'tableClose'          : '</tabular></table>' ,
    885. 

  885. 	   'tableLineClose'      : '<rowsep>'           ,
    886. 

  886. 	   'tableCellClose'      : '<colsep>'           ,
    887. 

  887. 	   'tableTitleCellClose' : '<colsep>'           ,
    888. 

  888. 	   'tableColAlignLeft'   : 'l'                  ,
    889. 

  889. 	   'tableColAlignRight'  : 'r'                  ,
    890. 

  890. 	   'tableColAlignCenter' : 'c'                  ,
    891. 

  891. 	   'comment'             : '<!-- \a -->'        ,
    892. 

  892. 	   'TOC'                 : '<toc>'              ,
    893. 

  893. 	   'EOD'                 : '</article>'
    894. 

  894. 	},
    895. 

  895. 	   
    896. 

  896. 	'tex': {
    897. 

  897. 	   'title1'              : '\n\\newpage\section*{\a}',
    898. 

  898. 	   'title2'              : '\\subsection*{\a}'       ,
    899. 

  899. 	   'title3'              : '\\subsubsection*{\a}'    ,
    900. 

  900. 	   # title 4/5: DIRTY: para+BF+\\+\n
    901. 

  901. 	   'title4'              : '\\paragraph{}\\textbf{\a}\\\\\n',
    902. 

  902. 	   'title5'              : '\\paragraph{}\\textbf{\a}\\\\\n',
    903. 

  903. 	   'numtitle1'           : '\n\\newpage\section{\a}',
    904. 

  904. 	   'numtitle2'           : '\\subsection{\a}'       ,
    905. 

  905. 	   'numtitle3'           : '\\subsubsection{\a}'    ,
    906. 

  906. 	   'areaPreOpen'         : '\\begin{verbatim}'   ,
    907. 

  907. 	   'areaPreClose'        : '\\end{verbatim}'     ,
    908. 

  908. 	   'areaQuoteOpen'       : '\\begin{quotation}'  ,
    909. 

  909. 	   'areaQuoteClose'      : '\\end{quotation}'    ,
    910. 

  910. 	   'fontMonoOpen'        : '\\texttt{'           ,
    911. 

  911. 	   'fontMonoClose'       : '}'                   ,
    912. 

  912. 	   'fontBoldOpen'        : '\\textbf{'           ,
    913. 

  913. 	   'fontBoldClose'       : '}'                   ,
    914. 

  914. 	   'fontItalicOpen'      : '\\textit{'           ,
    915. 

  915. 	   'fontItalicClose'     : '}'                   ,
    916. 

  916. 	   'fontBolditalicOpen'  : '\\textbf{\\textit{'  ,
    917. 

  917. 	   'fontBolditalicClose' : '}}'                  ,
    918. 

  918. 	   'fontUnderlineOpen'   : '\\underline{'        ,
    919. 

  919. 	   'fontUnderlineClose'  : '}'                   ,
    920. 

  920. 	   'listOpen'            : '\\begin{itemize}'    ,
    921. 

  921. 	   'listClose'           : '\\end{itemize}'      ,
    922. 

  922. 	   'listItem'            : '\\item '             ,
    923. 

  923. 	   'numlistOpen'         : '\\begin{enumerate}'  ,
    924. 

  924. 	   'numlistClose'        : '\\end{enumerate}'    ,
    925. 

  925. 	   'numlistItem'         : '\\item '             ,
    926. 

  926. 	   'deflistOpen'         : '\\begin{description}',
    927. 

  927. 	   'deflistClose'        : '\\end{description}'  ,
    928. 

  928. 	   'deflistItem1'        : '\\item[\a]'          ,
    929. 

  929. 	   'bar1'                : '\n\\hrulefill{}\n'   ,
    930. 

  930. 	   'bar2'                : '\n\\rule{\linewidth}{1mm}\n',
    931. 

  931. 	   'url'                 : '\\url{\a}'                  ,
    932. 

  932. 	   'urlMark'             : '\\textit{\a} (\\url{\a})'   ,
    933. 

  933. 	   'email'               : '\\url{\a}'                  ,
    934. 

  934. 	   'emailMark'           : '\\textit{\a} (\\url{\a})'   ,
    935. 

  935. 	   'img'                 : '\\begin{figure}\\includegraphics{\a}'+\
    936. 

  936. 	                           '\\end{figure}',
    937. 

  937. 	   'tableOpen'           : '\\begin{center}\\begin{tabular}{\a|}',
    938. 

  938. 	   'tableClose'          : '\\end{tabular}\\end{center}',
    939. 

  939. 	   'tableLineOpen'       : '\\hline ' ,
    940. 

  940. 	   'tableLineClose'      : ' \\\\'    ,
    941. 

  941. 	   'tableCellClose'      : ' & '      ,
    942. 

  942. 	   'tableTitleCellOpen'  : '\\textbf{',
    943. 

  943. 	   'tableTitleCellClose' : '} & '     ,
    944. 

  944. 	   'tableColAlignLeft'   : '|l'       ,
    945. 

  945. 	   'tableColAlignRight'  : '|r'       ,
    946. 

  946. 	   'tableColAlignCenter' : '|c'       ,
    947. 

  947. 	   'comment'             : '% \a'     ,
    948. 

  948. 	   'TOC'                 : '\\newpage\\tableofcontents',
    949. 

  949. 	   'EOD'                 : '\\end{document}'
    950. 

  950. 	},
    951. 

  951. 	
    952. 

  952. 	'moin': {
    953. 

  953. 	   'title1'              : '= \a ='        ,
    954. 

  954. 	   'title2'              : '== \a =='      ,
    955. 

  955. 	   'title3'              : '=== \a ==='    ,
    956. 

  956. 	   'title4'              : '==== \a ===='  ,
    957. 

  957. 	   'title5'              : '===== \a =====',
    958. 

  958. 	   'areaPreOpen'         : '{{{'           ,
    959. 

  959. 	   'areaPreClose'        : '}}}'           ,
    960. 

  960. 	   'areaQuoteOpen'       : ' '             ,
    961. 

  961. 	   'fontMonoOpen'        : '{{{'           ,
    962. 

  962. 	   'fontMonoClose'       : '}}}'           ,
    963. 

  963. 	   'fontBoldOpen'        : "'''"           ,
    964. 

  964. 	   'fontBoldClose'       : "'''"           ,
    965. 

  965. 	   'fontItalicOpen'      : "''"            ,
    966. 

  966. 	   'fontItalicClose'     : "''"            ,
    967. 

  967. 	   'fontBolditalicOpen'  : "'''''"         ,
    968. 

  968. 	   'fontBolditalicClose' : "'''''"         ,
    969. 

  969. 	   'fontUnderlineOpen'   : "'''''"         ,
    970. 

  970. 	   'fontUnderlineClose'  : "'''''"         ,
    971. 

  971. 	   'listItem'            : ' * '           ,
    972. 

  972. 	   'numlistItem'         : ' \a. '         ,
    973. 

  973. 	   'bar1'                : '----'          ,
    974. 

  974. 	   'bar2'                : '----'          ,
    975. 

  975. 	   'url'                 : '[\a]'          ,
    976. 

  976. 	   'urlMark'             : '[\a \a]'       ,
    977. 

  977. 	   'email'               : '[\a]'          ,
    978. 

  978. 	   'emailMark'           : '[\a \a]'       ,
    979. 

  979. 	   'img'                 : '[\a]'          ,
    980. 

  980. 	   'tableLineOpen'       : '||'            ,
    981. 

  981. 	   'tableCellClose'      : '||'            ,
    982. 

  982. 	   'tableTitleCellClose' : '||'
    983. 

  983. 	},
    984. 

  984. 	
    985. 

  985. 	'mgp': {
    986. 

  986. 	   'paragraph'           : '%font "normal", size 5\n'   ,
    987. 

  987. 	   'title1'              : '%page\n\n\a'                ,
    988. 

  988. 	   'title2'              : '%page\n\n\a'                ,
    989. 

  989. 	   'title3'              : '%page\n\n\a'                ,
    990. 

  990. 	   'title4'              : '%page\n\n\a'                ,
    991. 

  991. 	   'title5'              : '%page\n\n\a'                ,
    992. 

  992. 	   'areaPreOpen'         : '\n%font "mono"'             ,
    993. 

  993. 	   'areaPreClose'        : '%font "normal"'             ,
    994. 

  994. 	   'areaQuoteOpen'       : '%prefix "       "'          ,
    995. 

  995. 	   'areaQuoteClose'      : '%prefix "  "'               ,
    996. 

  996. 	   'fontMonoOpen'        : '\n%cont, font "mono"\n'     ,
    997. 

  997. 	   'fontMonoClose'       : '\n%cont, font "normal"\n'   ,
    998. 

  998. 	   'fontBoldOpen'        : '\n%cont, font "normal-b"\n' ,
    999. 

  999. 	   'fontBoldClose'       : '\n%cont, font "normal"\n'   ,
    1000. 

  1000. 	   'fontItalicOpen'      : '\n%cont, font "normal-i"\n' ,
    1001. 

  1001. 	   'fontItalicClose'     : '\n%cont, font "normal"\n'   ,
    1002. 

  1002. 	   'fontBolditalicOpen'  : '\n%cont, font "normal-bi"\n',
    1003. 

  1003. 	   'fontBolditalicClose' : '\n%cont, font "normal"\n'   ,
    1004. 

  1004. 	   'fontUnderlineOpen'   : '\n%cont, fore "cyan"\n'     ,
    1005. 

  1005. 	   'fontUnderlineClose'  : '\n%cont, fore "white"\n'    ,
    1006. 

  1006. 	   'numlistItem'         : '\a. '                       ,
    1007. 

  1007. 	   'bar1'                : '%bar "white" 5'             ,
    1008. 

  1008. 	   'bar2'                : '%pause'                     ,
    1009. 

  1009. 	   'url'                 : '\n%cont, fore "cyan"\n\a'   +\
    1010. 

  1010. 	                           '\n%cont, fore "white"\n'    ,
    1011. 

  1011. 	   'urlMark'             : '\a \n%cont, fore "cyan"\n\a'+\
    1012. 

  1012. 	                           '\n%cont, fore "white"\n'    ,
    1013. 

  1013. 	   'email'               : '\n%cont, fore "cyan"\n\a'   +\
    1014. 

  1014. 	                           '\n%cont, fore "white"\n'    ,
    1015. 

  1015. 	   'emailMark'           : '\a \n%cont, fore "cyan"\n\a'+\
    1016. 

  1016. 	                           '\n%cont, fore "white"\n'    ,
    1017. 

  1017. 	   'img'                 : '\n%center\n%newimage "\a", left\n',
    1018. 

  1018. 	   'comment'             : '%% \a'                      ,
    1019. 

  1019. 	   'EOD'                 : '%%EOD'
    1020. 

  1020. 	},
    1021. 

  1021. 	
    1022. 

  1022. 	'man': {
    1023. 

  1023. 	   'paragraph'           : '.P'     ,
    1024. 

  1024. 	   'title1'              : '.SH \a' ,
    1025. 

  1025. 	   'title2'              : '.SS \a' ,
    1026. 

  1026. 	   'title3'              : '.SS \a' ,
    1027. 

  1027. 	   'title4'              : '.SS \a' ,
    1028. 

  1028. 	   'title5'              : '.SS \a' ,
    1029. 

  1029. 	   'areaPreOpen'         : '.nf'    ,
    1030. 

  1030. 	   'areaPreClose'        : '.fi\n'  ,
    1031. 

  1031. 	   'areaQuoteOpen'       : '\n'     ,
    1032. 

  1032. 	   'areaQuoteClose'      : '\n'     ,
    1033. 

  1033. 	   'fontBoldOpen'        : '\\fB'   ,
    1034. 

  1034. 	   'fontBoldClose'       : '\\fP'   ,
    1035. 

  1035. 	   'fontItalicOpen'      : '\\fI'   ,
    1036. 

  1036. 	   'fontItalicClose'     : '\\fP'   ,
    1037. 

  1037. 	   'fontBolditalicOpen'  : '\\fI'   ,
    1038. 

  1038. 	   'fontBolditalicClose' : '\\fP'   ,
    1039. 

  1039. 	   'listOpen'            : '\n.nf'  ,  # pre
    1040. 

  1040. 	   'listClose'           : '.fi\n'  ,
    1041. 

  1041. 	   'listItem'            : '* '     ,
    1042. 

  1042. 	   'numlistOpen'         : '\n.nf'  ,  # pre
    1043. 

  1043. 	   'numlistClose'        : '.fi\n'  ,
    1044. 

  1044. 	   'numlistItem'         : '\a. '   ,
    1045. 

  1045. 	   'bar1'                : '\n\n'   ,
    1046. 

  1046. 	   'bar2'                : '\n\n'   ,
    1047. 

  1047. 	   'url'                 : '\a'     ,
    1048. 

  1048. 	   'urlMark'             : '\a (\a)',
    1049. 

  1049. 	   'email'               : '\a'     ,
    1050. 

  1050. 	   'emailMark'           : '\a (\a)',
    1051. 

  1051. 	   'img'                 : '\a'     ,
    1052. 

  1052. 	   'comment'             : '.\\" \a'
    1053. 

  1053. 	},
    1054. 

  1054. 	
    1055. 

  1055. 	'pm6': {
    1056. 

  1056. 	   'paragraph'           : '<@Normal:>'    ,
    1057. 

  1057. 	   'title1'              : '\n<@Title1:>\a',
    1058. 

  1058. 	   'title2'              : '\n<@Title2:>\a',
    1059. 

  1059. 	   'title3'              : '\n<@Title3:>\a',
    1060. 

  1060. 	   'title4'              : '\n<@Title4:>\a',
    1061. 

  1061. 	   'title5'              : '\n<@Title5:>\a',
    1062. 

  1062. 	   'areaPreOpen'         : '<@PreFormat:>' ,
    1063. 

  1063. 	   'areaQuoteOpen'       : '<@Quote:>'     ,
    1064. 

  1064. 	   'fontMonoOpen'        : '<FONT "Lucida Console"><SIZE 9>' ,
    1065. 

  1065. 	   'fontMonoClose'       : '<SIZE$><FONT$>',
    1066. 

  1066. 	   'fontBoldOpen'        : '<B>'           ,
    1067. 

  1067. 	   'fontBoldClose'       : '<P>'           ,
    1068. 

  1068. 	   'fontItalicOpen'      : '<I>'           ,
    1069. 

  1069. 	   'fontItalicClose'     : '<P>'           ,
    1070. 

  1070. 	   'fontBolditalicOpen'  : '<B><I>'        ,
    1071. 

  1071. 	   'fontBolditalicClose' : '<P>'           ,
    1072. 

  1072. 	   'fontUnderlineOpen'   : '<U>'           ,
    1073. 

  1073. 	   'fontUnderlineClose'  : '<P>'           ,
    1074. 

  1074. 	   'listOpen'            : '<@Bullet:>'    ,
    1075. 

  1075. 	   'listItem'            : '\x95	'       ,  # \x95 == ~U
    1076. 

  1076. 	   'numlistOpen'         : '<@Bullet:>'    ,
    1077. 

  1077. 	   'numlistItem'         : '\x95    '      ,
    1078. 

  1078. 	   'bar1'                : '\a'            ,
    1079. 

  1079. 	   'bar2'                : '\a'            ,
    1080. 

  1080. 	   'url'                 : '<U>\a<P>'      ,  # underline
    1081. 

  1081. 	   'urlMark'             : '\a <U>\a<P>'   ,
    1082. 

  1082. 	   'email'               : '\a'            ,
    1083. 

  1083. 	   'emailMark'           : '\a \a'         ,
    1084. 

  1084. 	   'img'                 : '\a'
    1085. 

  1085. 	}
    1086. 

  1086. 	}
    1087. 

  1087. 	
    1088. 

  1088. 	# compose the target tags dictionary
    1089. 

  1089. 	tags = {}
    1090. 

  1090. 	target_tags = alltags[doctype]
    1091. 

  1091. 	for key in keys: tags[key] = ''     # create empty keys
    1092. 

  1092. 	for key in target_tags.keys():
    1093. 

  1093. 		tags[key] = maskEscapeChar(target_tags[key]) # populate
    1094. 

  1094. 	
    1095. 

  1095. 	return tags
    1096. 

  1096. 

  1097. 

  1098. def getRules(doctype):
    1099. 

  1099. 	ret = {}
    1100. 

  1100. 	allrules = [
    1101. 

  1101. 	
    1102. 

  1102. 	 # target rules (ON/OFF)
    1103. 

  1103. 	  'linkable',           # target supports external links
    1104. 

  1104. 	  'tableable',          # target supports tables
    1105. 

  1105. 	  'imglinkable',        # target supports images as links
    1106. 

  1106. 	  'imgalignable',       # target supports image alignment
    1107. 

  1107. 	  'imgasdefterm',       # target supports image as definition term
    1108. 

  1108. 	  'tablealignable',     # target supports table alignment
    1109. 

  1109. 	  'autonumberlist',     # target supports numbered lists natively
    1110. 

  1110. 	  'autonumbertitle',    # target supports numbered titles natively
    1111. 

  1111. 	  'tablecellsplit',     # place delimiters only *between* cells
    1112. 

  1112. 	  'listnotnested',      # lists cannot be nested
    1113. 

  1113. 	  'quotenotnested',     # quotes cannot be nested
    1114. 

  1114. 	  'preareanotescaped',  # don't escape specials in PRE area
    1115. 

  1115. 	  'escapeurl',          # escape special in link URL
    1116. 

  1116. 	  
    1117. 

  1117. 	# target code beautify (ON/OFF)
    1118. 

  1118. 	  'indentprearea',      # add leading spaces to PRE area lines
    1119. 

  1119. 	  'breaktablecell',     # break lines after any table cell
    1120. 

  1120. 	  'breaktablelineopen', # break line after opening table line
    1121. 

  1121. 	  'keepquoteindent',    # don't remove the leading TABs on quotes
    1122. 

  1122. 	
    1123. 

  1123. 	# value settings
    1124. 

  1124. 	  'listmaxdepth',       # maximum depth for lists
    1125. 

  1125. 	  'tablecellaligntype'  # type of table cell align: cell, column
    1126. 

  1126. 	]
    1127. 

  1127. 	
    1128. 

  1128. 	rules = {
    1129. 

  1129. 	  'txt' : {
    1130. 

  1130. 	    'indentprearea':1
    1131. 

  1131. 	    },
    1132. 

  1132. 	  'html': {
    1133. 

  1133. 	    'indentprearea':1,
    1134. 

  1134. 	    'linkable':1,
    1135. 

  1135. 	    'imglinkable':1,
    1136. 

  1136. 	    'imgalignable':1,
    1137. 

  1137. 	    'imgasdefterm':1,
    1138. 

  1138. 	    'autonumberlist':1,
    1139. 

  1139. 	    'tableable':1,
    1140. 

  1140. 	    'breaktablecell':1,
    1141. 

  1141. 	    'breaktablelineopen':1,
    1142. 

  1142. 	    'keepquoteindent':1,
    1143. 

  1143. 	    'tablealignable':1,
    1144. 

  1144. 	    'tablecellaligntype':'cell'
    1145. 

  1145. 	    },
    1146. 

  1146. 	  'sgml': {
    1147. 

  1147. 	    'linkable':1,
    1148. 

  1148. 	    'escapeurl':1,
    1149. 

  1149. 	    'autonumberlist':1,
    1150. 

  1150. 	    'tableable':1,
    1151. 

  1151. 	    'tablecellsplit':1,
    1152. 

  1152. 	    'quotenotnested':1,
    1153. 

  1153. 	    'keepquoteindent':1,
    1154. 

  1154. 	    'tablecellaligntype':'column'
    1155. 

  1155. 	    },
    1156. 

  1156. 	  'mgp' : {
    1157. 

  1157. 	    },
    1158. 

  1158. 	  'tex' : {
    1159. 

  1159. 	    'autonumberlist':1,
    1160. 

  1160. 	    'autonumbertitle':1,
    1161. 

  1161. 	    'tableable':1,
    1162. 

  1162. 	    'tablecellsplit':1,
    1163. 

  1163. 	    'preareanotescaped':1,
    1164. 

  1164. 	    'listmaxdepth':4,
    1165. 

  1165. 	    'tablecellaligntype':'column'
    1166. 

  1166. 	    },
    1167. 

  1167. 	  'moin': {
    1168. 

  1168. 	    'linkable':1,
    1169. 

  1169. 	    'tableable':1
    1170. 

  1170. 	    },
    1171. 

  1171. 	  'man' : {
    1172. 

  1172. 	    'indentprearea':1,
    1173. 

  1173. 	    'listnotnested':1
    1174. 

  1174. 	    },
    1175. 

  1175. 	  'pm6' : {
    1176. 

  1176. 	    }
    1177. 

  1177. 	}
    1178. 

  1178. 	
    1179. 

  1179. 	
    1180. 

  1180. 	# populate return dictionary
    1181. 

  1181. 	myrules = rules[doctype]
    1182. 

  1182. 	for key in allrules      : ret[key] = 0            # reset all
    1183. 

  1183. 	for key in myrules.keys(): ret[key] = myrules[key] # turn ON
    1184. 

  1184. 	return ret
    1185. 

  1185. 

  1186. 

  1187. def getRegexes():
    1188. 

  1188. 	regex = {
    1189. 

  1189. 	# extra at end: (\[(?P<label>\w+)\])?
    1190. 

  1190. 	'title':
    1191. 

  1191. 		re.compile(r'^\s*(?P<id>={1,5})(?P<txt>[^=].*[^=])\1\s*$'),
    1192. 

  1192. 	'numtitle':
    1193. 

  1193. 		re.compile(r'^\s*(?P<id>\+{1,5})(?P<txt>[^+].*[^+])\1\s*$'),
    1194. 

  1194. 	'areaPreOpen':
    1195. 

  1195. 		re.compile(r'^---$'),
    1196. 

  1196. 	'areaPreClose':
    1197. 

  1197. 		re.compile(r'^---$'),
    1198. 

  1198. 	'quote':
    1199. 

  1199. 		re.compile(r'^\t+'),
    1200. 

  1200. 	'1linePre':
    1201. 

  1201. 		re.compile(r'^--- (?=.)'),
    1202. 

  1202. 	'fontMono':
    1203. 

  1203. 		re.compile(r'`([^`]+)`'),
    1204. 

  1204. 	'fontBold':
    1205. 

  1205. 		re.compile(r'\*\*([^\s*].*?)\*\*'),
    1206. 

  1206. 	'fontItalic':
    1207. 

  1207. 		re.compile(r'(^|[^:])//([^ /].*?)//'),
    1208. 

  1208. 	'fontUnderline':
    1209. 

  1209. 		re.compile(r'__([^_].*?)__'), # underline lead/trailing blank
    1210. 

  1210. 	'fontBolditalic':
    1211. 

  1211. 		re.compile(r'\*/([^/].*?)/\*'),
    1212. 

  1212. 	'list':
    1213. 

  1213. 		re.compile(r'^( *)([+-]) ([^ ])'),
    1214. 

  1214. 	'deflist':
    1215. 

  1215. 		re.compile(r'^( *)(=) ([^:]+):'),
    1216. 

  1216. 	'bar':
    1217. 

  1217. 		re.compile(r'^\s*([_=-]{20,})\s*$'),
    1218. 

  1218. 	'table':
    1219. 

  1219. 		re.compile(r'^ *\|\|? '),
    1220. 

  1220. 	'blankline':
    1221. 

  1221. 		re.compile(r'^\s*$'),
    1222. 

  1222. 	'comment':
    1223. 

  1223. 		re.compile(r'^%'),
    1224. 

  1224. 	'raw':
    1225. 

  1225. 		re.compile(r'``(.+?)``')
    1226. 

  1226. 	}
    1227. 

  1227. 	
    1228. 

  1228. 	# special char to place data on TAGs contents  (\a == bell)
    1229. 

  1229. 	regex['x'] = re.compile('\a')
    1230. 

  1230. 	
    1231. 

  1231. 	# %%date [ (formatting) ]
    1232. 

  1232. 	regex['date'] = re.compile(r'%%date\b(\((?P<fmt>.*?)\))?', re.I)
    1233. 

  1233. 	
    1234. 

  1234. 	
    1235. 

  1235. 	### complicated regexes begin here ;)
    1236. 

  1236. 	#
    1237. 

  1237. 	# textual descriptions on --help's style: [...] is optional, | is OR
    1238. 

  1238. 	
    1239. 

  1239. 	
    1240. 

  1240. 	### first, some auxiliar variables
    1241. 

  1241. 	#
    1242. 

  1242. 	
    1243. 

  1243. 	# [image.EXT]
    1244. 

  1244. 	patt_img = r'\[([\w_,.+%$#@!?+~/-]+\.(png|jpe?g|gif|eps|bmp))\]'
    1245. 

  1245. 	
    1246. 

  1246. 	# link things
    1247. 

  1247. 	urlskel = {
    1248. 

  1248. 	  'proto' : r'(https?|ftp|news|telnet|gopher|wais)://',
    1249. 

  1249. 	  'guess' : r'(www[23]?|ftp)\.',    # w/out proto, try to guess
    1250. 

  1250. 	  'login' : r'A-Za-z0-9_.-',        # for ftp://login@domain.com
    1251. 

  1251. 	  'pass'  : r'[^ @]*',              # for ftp://login:password@dom.com
    1252. 

  1252. 	  'chars' : r'A-Za-z0-9%._/~:,=$@-',# %20(space), :80(port)
    1253. 

  1253. 	  'anchor': r'A-Za-z0-9%._-',       # %nn(encoded)
    1254. 

  1254. 	  'form'  : r'A-Za-z0-9/%&=+.,@*_-',# .,@*_-(as is)
    1255. 

  1255. 	  'punct' : r'.,;:!?'
    1256. 

  1256. 	}
    1257. 

  1257. 	
    1258. 

  1258. 	# username [ :password ] @
    1259. 

  1259. 	patt_url_login = r'([%s]+(:%s)?@)?'%(urlskel['login'],urlskel['pass'])
    1260. 

  1260. 	
    1261. 

  1261. 	# [ http:// ] [ username:password@ ] domain.com [ / ]
    1262. 

  1262. 	#     [ #anchor | ?form=data ]
    1263. 

  1263. 	retxt_url = r'\b(%s%s|%s)[%s]+\b/*(\?[%s]+)?(#[%s]+)?'%(
    1264. 

  1264. 	             urlskel['proto'],patt_url_login, urlskel['guess'],
    1265. 

  1265. 	             urlskel['chars'],urlskel['form'],urlskel['anchor'])
    1266. 

  1266. 	
    1267. 

  1267. 	# filename | [ filename ] #anchor
    1268. 

  1268. 	retxt_url_local = r'[%s]+|[%s]*(#[%s]+)'%(
    1269. 

  1269. 	             urlskel['chars'],urlskel['chars'],urlskel['anchor'])
    1270. 

  1270. 	
    1271. 

  1271. 	# user@domain [ ?form=data ]
    1272. 

  1272. 	patt_email = r'\b[%s]+@([A-Za-z0-9_-]+\.)+[A-Za-z]{2,4}\b(\?[%s]+)?'%(
    1273. 

  1273. 	             urlskel['login'],urlskel['form'])
    1274. 

  1274. 	
    1275. 

  1275. 	
    1276. 

  1276. 	# saving for future use
    1277. 

  1277. 	regex['_urlskel'] = urlskel
    1278. 

  1278. 	
    1279. 

  1279. 	### and now the real regexes
    1280. 

  1280. 	#
    1281. 

  1281. 	
    1282. 

  1282. 	regex['email'] = re.compile(patt_email,re.I)
    1283. 

  1283. 	
    1284. 

  1284. 	# email | url
    1285. 

  1285. 	regex['link'] = \
    1286. 

  1286. 		re.compile(r'%s|%s'%(retxt_url,patt_email), re.I)
    1287. 

  1287. 	
    1288. 

  1288. 	# \[ label | imagetag    url | email | filename \]
    1289. 

  1289. 	regex['linkmark'] = \
    1290. 

  1290. 		re.compile(r'\[(?P<label>%s|[^]]+) (?P<link>%s|%s|%s)\]'%(
    1291. 

  1291. 		   patt_img, retxt_url, patt_email, retxt_url_local),
    1292. 

  1292. 		   re.L+re.I)
    1293. 

  1293. 	
    1294. 

  1294. 	# image
    1295. 

  1295. 	regex['img'] = re.compile(patt_img, re.L+re.I)
    1296. 

  1296. 	
    1297. 

  1297. 	# all macros
    1298. 

  1298. 	regex['macro'] = regex['date']
    1299. 

  1299. 	
    1300. 

  1300. 	# special things
    1301. 

  1301. 	regex['special'] = re.compile(r'^%!\s*')
    1302. 

  1302. 	regex['command'] = re.compile(r'(Include)\s*:\s*(.+)\s*$',re.I)
    1303. 

  1303. 	return regex
    1304. 

  1304. ### END OF regex nightmares
    1305. 

  1305. 

  1306. 

  1307. class SubareaMaster:
    1308. 

  1308. 	def __init__(self) : self.x = []
    1309. 

  1309. 	def __call__(self) :
    1310. 

  1310. 		if not self.x: return ''
    1311. 

  1311. 		return self.x[-1]
    1312. 

  1312. 	def add(self, area):
    1313. 

  1313. 		if not self.x or (self.x and self.x[-1] != area):
    1314. 

  1314. 			self.x.append(area)
    1315. 

  1315. 		Debug('subarea ++ (%s): %s' % (area,self.x), 1)
    1316. 

  1316. 	def pop(self, area=None):
    1317. 

  1317. 		if area and self.x[-1] == area: self.x.pop()
    1318. 

  1318. 		Debug('subarea -- (%s): %s' % (area,self.x), 1)
    1319. 

  1319. 

  1320. def doHeader(headers, CONF):
    1321. 

  1321. 	if CONF['noheaders']: return []
    1322. 

  1322. 	doctype = CONF['type']
    1323. 

  1323. 	if not HEADER_TEMPLATE.has_key(doctype):
    1324. 

  1324. 		Error("doheader: Unknow doctype '%s'"%doctype)
    1325. 

  1325. 	
    1326. 

  1326. 	template = string.split(HEADER_TEMPLATE[doctype], '\n')
    1327. 

  1327. 	
    1328. 

  1328. 	head_data = {'STYLE':'', 'ENCODING':''}
    1329. 

  1329. 	for key in head_data.keys():
    1330. 

  1330. 		val = CONF.get(string.lower(key))
    1331. 

  1331. 		if key == 'ENCODING': val = get_encoding_string(val, doctype)
    1332. 

  1332. 		head_data[key] = val
    1333. 

  1333. 	# parse header contents
    1334. 

  1334. 	for i in 0,1,2:
    1335. 

  1335. 		contents = doDateMacro(headers[i])  # expand %%date
    1336. 

  1336. 		# Escapes - on tex, just do it if any \tag{} present
    1337. 

  1337. 		if doctype != 'tex' or \
    1338. 

  1338. 		  (doctype == 'tex' and re.search(r'\\\w+{', contents)):
    1339. 

  1339. 			contents = doEscape(doctype, contents)
    1340. 

  1340. 		
    1341. 

  1341. 		head_data['HEADER%d'%(i+1)] = contents
    1342. 

  1342. 	Debug("Header Data: %s"%head_data, 1)
    1343. 

  1343. 	# scan for empty dictionary keys
    1344. 

  1344. 	# if found, scan template lines for that key reference
    1345. 

  1345. 	# if found, remove the reference
    1346. 

  1346. 	# if there isn't any other key reference on the same line, remove it
    1347. 

  1347. 	for key in head_data.keys():
    1348. 

  1348. 		if head_data.get(key): continue
    1349. 

  1349. 		for line in template:
    1350. 

  1350. 			if string.count(line, '%%(%s)s'%key):
    1351. 

  1351. 				sline = string.replace(line, '%%(%s)s'%key, '')
    1352. 

  1352. 				if not re.search(r'%\([A-Z0-9]+\)s', sline):
    1353. 

  1353. 					template.remove(line)
    1354. 

  1354. 	# populate template with data
    1355. 

  1355. 	template = string.join(template, '\n') % head_data
    1356. 

  1356. 	### post processing
    1357. 

  1357. 	#
    1358. 

  1358. 	# let tex format today
    1359. 

  1359. 	if doctype == 'tex' and head_data['HEADER3'] == currdate:
    1360. 

  1360. 		template = re.sub(r'\\date\{.*?}', r'\date', template)
    1361. 

  1361. 	
    1362. 

  1362. 	return string.split(template, '\n')
    1363. 

  1363. 

  1364. def doDateMacro(line):
    1365. 

  1365. 	re_date = getRegexes()['date']
    1366. 

  1366. 	while re_date.search(line):
    1367. 

  1367. 		m = re_date.search(line)
    1368. 

  1368. 		fmt = m.group('fmt') or ''
    1369. 

  1369. 		dateme = currdate
    1370. 

  1370. 		if fmt: dateme = strftime(fmt,localtime(time()))
    1371. 

  1371. 		line = re_date.sub(dateme,line,1)
    1372. 

  1372. 	return line
    1373. 

  1373. 

  1374. def doCommentLine(txt):
    1375. 

  1375. 	# the -- string ends a sgml/html comment :(
    1376. 

  1376. 	txt = maskEscapeChar(txt)
    1377. 

  1377. 	if string.count(TAGS['comment'], '--') and \
    1378. 

  1378. 		string.count(txt, '--'):
    1379. 

  1379. 		txt = re.sub('-(?=-)', r'-\\', txt)
    1380. 

  1380. 	
    1381. 

  1381. 	if TAGS['comment']:
    1382. 

  1382. 		return regex['x'].sub(txt, TAGS['comment'])
    1383. 

  1383. 	return ''
    1384. 

  1384. 

  1385. def doFooter(CONF):
    1386. 

  1386. 	ret = []
    1387. 

  1387. 	doctype = CONF['type']
    1388. 

  1388. 	cmdline = CONF['cmdline']
    1389. 

  1389. 	typename = doctype
    1390. 

  1390. 	if doctype == 'tex': typename = 'LaTeX2e'
    1391. 

  1391. 	ppgd = '%s code generated by txt2tags %s (%s)'%(
    1392. 

  1392. 	        typename,my_version,my_url)
    1393. 

  1393. 	cmdline = 'cmdline: txt2tags %s'%string.join(cmdline[1:], ' ')
    1394. 

  1394. 	ret.append('\n'+doCommentLine(ppgd))
    1395. 

  1395. 	ret.append(doCommentLine(cmdline))
    1396. 

  1396. 	ret.append(TAGS['EOD'])
    1397. 

  1397. 	return ret
    1398. 

  1398. 

  1399. # TODO mgp: any line (header or not) can't begin with % (add a space before)
    1400. 

  1400. def doEscape(doctype,txt):
    1401. 

  1401. 	if doctype in ['html','sgml']:
    1402. 

  1402. 		txt = re.sub('&','&amp;',txt)
    1403. 

  1403. 		txt = re.sub('<','&lt;',txt)
    1404. 

  1404. 		txt = re.sub('>','&gt;',txt)
    1405. 

  1405. 		if doctype == 'sgml':
    1406. 

  1406. 			txt = re.sub('\xff','&yuml;',txt)  # "+y
    1407. 

  1407. 	elif doctype == 'pm6':
    1408. 

  1408. 		txt = re.sub('<','<\#60>',txt)
    1409. 

  1409. 	elif doctype == 'mgp':
    1410. 

  1410. 		txt = re.sub('^%',' %',txt)  # add leading blank to avoid parse
    1411. 

  1411. 	elif doctype == 'man':
    1412. 

  1412. 		txt = re.sub("^([.'])", '\\&\\1',txt)           # command ID
    1413. 

  1413. 		txt = string.replace(txt,ESCCHAR, ESCCHAR+'e')  # \e
    1414. 

  1414. 	elif doctype == 'tex':
    1415. 

  1415. 		txt = string.replace(txt, ESCCHAR, '@@LaTeX-escaping-SUX@@')
    1416. 

  1416. 		txt = re.sub('([#$&%{}])', r'\\\1', txt)
    1417. 

  1417. 		txt = string.replace(txt, '~', maskEscapeChar(r'\~{}'))
    1418. 

  1418. 		txt = string.replace(txt, '^', maskEscapeChar(r'\^{}'))
    1419. 

  1419. 		txt = string.replace(txt, '@@LaTeX-escaping-SUX@@',
    1420. 

  1420. 		                     maskEscapeChar(r'$\backslash$'))
    1421. 

  1421. 		# TIP the _ is escaped at the end
    1422. 

  1422. 	return txt
    1423. 

  1423. 

  1424. def doFinalEscape(doctype, txt):
    1425. 

  1425. 	"Last escapes of each line"
    1426. 

  1426. 	if   doctype == 'pm6' : txt = string.replace(txt,ESCCHAR+'<',r'<\#92><')
    1427. 

  1427. 	elif doctype == 'man' : txt = string.replace(txt, '-', r'\-')
    1428. 

  1428. 	elif doctype == 'tex' : txt = string.replace(txt, '_', r'\_')
    1429. 

  1429. 	elif doctype == 'sgml': txt = string.replace(txt, '[', '&lsqb;')
    1430. 

  1430. 	return txt
    1431. 

  1431. 

  1432. def EscapeCharHandler(action, data):
    1433. 

  1433. 	"Mask/Unmask the Escape Char on the given string"
    1434. 

  1434. 	if not string.strip(data): return data
    1435. 

  1435. 	if action not in ['mask','unmask']:
    1436. 

  1436. 		Error("EscapeCharHandler: Invalid action '%s'"%action)
    1437. 

  1437. 	if action == 'mask': return string.replace(data,'\\',ESCCHAR)
    1438. 

  1438. 	else:                return string.replace(data,ESCCHAR,'\\')
    1439. 

  1439. 

  1440. def maskEscapeChar(data):
    1441. 

  1441. 	"Replace any Escape Char \ with a text mask (Input: str or list)"
    1442. 

  1442. 	if type(data) == type([]):
    1443. 

  1443. 		return map(lambda x: EscapeCharHandler('mask', x), data)
    1444. 

  1444. 	return EscapeCharHandler('mask',data)
    1445. 

  1445. 

  1446. def unmaskEscapeChar(data):
    1447. 

  1447. 	"Undo the Escape char \ masking (Input: str or list)"
    1448. 

  1448. 	if type(data) == type([]):
    1449. 

  1449. 		return map(lambda x: EscapeCharHandler('unmask', x), data)
    1450. 

  1450. 	return EscapeCharHandler('unmask',data)
    1451. 

  1451. 

  1452. def addLineBreaks(list):
    1453. 

  1453. 	"use LB to respect sys.platform"
    1454. 

  1454. 	ret = []
    1455. 

  1455. 	for line in list:
    1456. 

  1456. 		line = string.replace(line,'\n',LB)  # embedded \n's
    1457. 

  1457. 		ret.append(line+LB)                  # add final line break
    1458. 

  1458. 	return ret
    1459. 

  1459. 

  1460. def doPreLine(doctype,line):
    1461. 

  1461. 	"Parsing procedures for preformatted (verbatim) lines"
    1462. 

  1462. 	if not rules['preareanotescaped']: line = doEscape(doctype,line)
    1463. 

  1463. 	if rules['indentprearea']: line = '  '+line
    1464. 

  1464. 	if doctype == 'pm6': line = doFinalEscape(doctype, line)
    1465. 

  1465. 	return line
    1466. 

  1466. 

  1467. def doCloseTable(doctype):
    1468. 

  1468. 	global subarea, tableborder
    1469. 

  1469. 	ret = ''
    1470. 

  1470. 	if rules['tableable']:
    1471. 

  1471. 		if doctype == 'tex' and tableborder:
    1472. 

  1472. 			ret = TAGS['tableLineOpen']+TAGS['tableClose']+'\n'
    1473. 

  1473. 		else:
    1474. 

  1474. 			ret = TAGS['tableClose']+'\n'
    1475. 

  1475. 	else:
    1476. 

  1476. 		ret = TAGS['areaPreClose']
    1477. 

  1477. 	tableborder = 0
    1478. 

  1478. 	subarea.pop('table')
    1479. 

  1479. 	return ret
    1480. 

  1480. 

  1481. def doCloseQuote(howmany=None):
    1482. 

  1482. 	global quotedepth
    1483. 

  1483. 	ret = []
    1484. 

  1484. 	if not howmany: howmany = len(quotedepth)
    1485. 

  1485. 	for i in range(howmany):
    1486. 

  1486. 		quotedepth.pop()
    1487. 

  1487. 		#TODO align open/close tag -> FREE_ALING_TAG = 1 (man not)
    1488. 

  1488. 		ret.append(TAGS['areaQuoteClose'])
    1489. 

  1489. 	
    1490. 

  1490. 	if not quotedepth: subarea.pop('quote')
    1491. 

  1491. 	return string.join(ret,'\n')
    1492. 

  1492. 

  1493. def doCloseList(howmany=None):
    1494. 

  1494. 	global listindent, listids
    1495. 

  1495. 	ret = []
    1496. 

  1496. 	if not howmany: howmany = len(listindent)
    1497. 

  1497. 	for i in range(howmany):
    1498. 

  1498. 		if   listids[-1] == '-': tag = TAGS['listClose']
    1499. 

  1499. 		elif listids[-1] == '+': tag = TAGS['numlistClose']
    1500. 

  1500. 		elif listids[-1] == '=': tag = TAGS['deflistClose']
    1501. 

  1501. 		if not tag: tag = TAGS['listClose'] # default
    1502. 

  1502. 		if tag:
    1503. 

  1503. 			# unnested lists are only closed at mother-list
    1504. 

  1504. 			if rules['listnotnested']:
    1505. 

  1505. 				if len(listindent) == 1:
    1506. 

  1506. 					ret.append(tag)
    1507. 

  1507. 			else:
    1508. 

  1508. 				ret.append(listindent[-1]+tag)
    1509. 

  1509. 		del listindent[-1]
    1510. 

  1510. 		del listids[-1]
    1511. 

  1511. 	
    1512. 

  1512. 	if not listindent: subarea.pop('list')
    1513. 

  1513. 	return string.join(ret,'\n')
    1514. 

  1514. 

  1515. 

  1516. def beautify_me(name, line):
    1517. 

  1517. 	"where name is: bold, italic, underline or bolditalic"
    1518. 

  1518. 	name  = 'font%s' % string.capitalize(name)
    1519. 

  1519. 	open  = TAGS['%sOpen'%name]
    1520. 

  1520. 	close = TAGS['%sClose'%name]
    1521. 

  1521. 	txt = r'%s\1%s'%(open, close)
    1522. 

  1522. 	if name == 'fontItalic':
    1523. 

  1523. 		txt = r'\1%s\2%s'%(open, close)
    1524. 

  1524. 	line = regex[name].sub(txt,line)
    1525. 

  1525. 	return line
    1526. 

  1526. 

  1527. 

  1528. def get_tagged_link(label, url, CONF):
    1529. 

  1529. 	ret = ''
    1530. 

  1530. 	doctype = CONF['type']
    1531. 

  1531. 	
    1532. 

  1532. 	# set link type
    1533. 

  1533. 	if regex['email'].match(url):
    1534. 

  1534. 		linktype = 'email'
    1535. 

  1535. 	else:
    1536. 

  1536. 		linktype = 'url';
    1537. 

  1537. 	
    1538. 

  1538. 	# escape specials from TEXT parts
    1539. 

  1539. 	label = doEscape(doctype,label)
    1540. 

  1540. 	
    1541. 

  1541. 	# escape specials from link URL
    1542. 

  1542. 	if rules['linkable'] and rules['escapeurl']:
    1543. 

  1543. 		url = doEscape(doctype, url)
    1544. 

  1544. 	
    1545. 

  1545. 	# if not linkable, the URL is plain text, that needs escape
    1546. 

  1546. 	if not rules['linkable']:
    1547. 

  1547. 		if doctype == 'tex':
    1548. 

  1548. 			url = re.sub('^#', '\#', url) # ugly, but compile
    1549. 

  1549. 		else:
    1550. 

  1550. 			url = doEscape(doctype,url)
    1551. 

  1551. 	
    1552. 

  1552. 	# adding protocol to guessed link
    1553. 

  1553. 	guessurl = ''
    1554. 

  1554. 	if linktype == 'url' and \
    1555. 

  1555. 	   re.match(regex['_urlskel']['guess'], url):
    1556. 

  1556. 		if url[0] == 'w': guessurl = 'http://' +url
    1557. 

  1557. 		else            : guessurl =  'ftp://' +url
    1558. 

  1558. 		
    1559. 

  1559. 		# not link aware targets -> protocol is useless
    1560. 

  1560. 		if not rules['linkable']: guessurl = ''
    1561. 

  1561. 	
    1562. 

  1562. 	# simple link (not guessed)
    1563. 

  1563. 	if not label and not guessurl:
    1564. 

  1564. 		if CONF['maskemail'] and linktype == 'email':
    1565. 

  1565. 			# do the email mask feature (no TAGs, just text)
    1566. 

  1566. 			url = string.replace(url,'@',' (a) ')
    1567. 

  1567. 			url = string.replace(url,'.',' ')
    1568. 

  1568. 			url = "<%s>" % url
    1569. 

  1569. 			if rules['linkable']: url = doEscape(doctype, url)
    1570. 

  1570. 			ret = url
    1571. 

  1571. 		else:
    1572. 

  1572. 			# just add link data to tag
    1573. 

  1573. 			tag = TAGS[linktype]
    1574. 

  1574. 			ret = regex['x'].sub(url,tag)
    1575. 

  1575. 	
    1576. 

  1576. 	# named link or guessed simple link
    1577. 

  1577. 	else:
    1578. 

  1578. 		# adjusts for guessed link
    1579. 

  1579. 		if not label: label = url       # no   protocol
    1580. 

  1580. 		if guessurl : url   = guessurl  # with protocol
    1581. 

  1581. 		
    1582. 

  1582. 		# change image tag for !supported img+link targets
    1583. 

  1583. 		if regex['img'].match(label) and not rules['imglinkable']:
    1584. 

  1584. 			label = "(%s)"%regex['img'].match(label).group(1)
    1585. 

  1585. 		
    1586. 

  1586. 		# putting data on the right appearance order
    1587. 

  1587. 		if rules['linkable']:
    1588. 

  1588. 			urlorder = [url, label]   # link before label
    1589. 

  1589. 		else:
    1590. 

  1590. 			urlorder = [label, url]   # label before link
    1591. 

  1591. 		
    1592. 

  1592. 		# add link data to tag (replace \a's)
    1593. 

  1593. 		ret = TAGS["%sMark"%linktype]
    1594. 

  1594. 		for data in urlorder:
    1595. 

  1595. 			ret = regex['x'].sub(data,ret,1)
    1596. 

  1596. 	
    1597. 

  1597. 	return ret
    1598. 

  1598. 

  1599. 

  1600. def get_image_align(line):
    1601. 

  1601. 	align = ''
    1602. 

  1602. 	line = string.strip(line)
    1603. 

  1603. 	m = regex['img'].search(line)
    1604. 

  1604. 	ini = m.start() ; head = 0
    1605. 

  1605. 	end = m.end()   ; tail = len(line)
    1606. 

  1606. 	
    1607. 

  1607. 	align = 'middle'  # default align              # ^text +img +text$
    1608. 

  1608. 	if ini == head and end == tail: align = 'para' # ^img$
    1609. 

  1609. 	elif ini == head: align = 'left'               # ^img + text$
    1610. 

  1610. 	elif end == tail: align = 'right'              # ^text + img$
    1611. 

  1611. 	
    1612. 

  1612. 	return align
    1613. 

  1613. 

  1614. 

  1615. def get_tablecell_align(cells):
    1616. 

  1616. 	ret = []
    1617. 

  1617. 	for cell in cells:
    1618. 

  1618. 		align = 'Left'
    1619. 

  1619. 		if string.strip(cell): 
    1620. 

  1620. 			if cell[0] == ' ' and cell[-1] == ' ': align = 'Center'
    1621. 

  1621. 			elif cell[0] == ' ': align = 'Right'
    1622. 

  1622. 		ret.append(align)
    1623. 

  1623. 	return ret
    1624. 

  1624. 

  1625. 

  1626. def get_table_prop(line):
    1627. 

  1627. 	# default table proprierties
    1628. 

  1628. 	ret = {'border':0,'header':0,'align':'Left','cells':[],'cellalign':[]}
    1629. 

  1629. 	# detect table align (and remove spaces mark)
    1630. 

  1630. 	if line[0] == ' ': ret['align'] = 'Center'
    1631. 

  1631. 	line = string.lstrip(line)
    1632. 

  1632. 	# detect header (title) mark
    1633. 

  1633. 	if line[1] == '|':
    1634. 

  1634. 		ret['header'] = 1
    1635. 

  1635. 	# delete trailing spaces after last cell border
    1636. 

  1636. 	line = re.sub('\|\s*$','|', line)
    1637. 

  1637. 	# detect (and delete) border mark (and leading space)
    1638. 

  1638. 	if line[-1] == '|':
    1639. 

  1639. 		ret['border'] = 1 ; line = line[:-2]
    1640. 

  1640. 	# delete table mark
    1641. 

  1641. 	line = regex['table'].sub('', line)
    1642. 

  1642. 	# split cells
    1643. 

  1643. 	ret['cells'] = string.split(line, ' | ')
    1644. 

  1644. 	# find cells align
    1645. 

  1645. 	ret['cellalign'] = get_tablecell_align(ret['cells'])
    1646. 

  1646. 	
    1647. 

  1647. 	Debug('Table Prop: %s' % ret, 1)
    1648. 

  1648. 	return ret
    1649. 

  1649. 

  1650. 

  1651. def tag_table_cells(table, doctype):
    1652. 

  1652. 	ret = ''
    1653. 

  1653. 	open, close = TAGS['tableCellOpen'], TAGS['tableCellClose']
    1654. 

  1654. 	# title cell
    1655. 

  1655. 	if table['header']:
    1656. 

  1656. 		open = TAGS['tableTitleCellOpen']
    1657. 

  1657. 		close = TAGS['tableTitleCellClose']
    1658. 

  1658. 	# should we break the line?
    1659. 

  1659. 	if rules['breaktablecell']: close = close+'\n'
    1660. 

  1660. 	# here we go
    1661. 

  1661. 	while table['cells']:
    1662. 

  1662. 		openalign = open
    1663. 

  1663. 		cel = table['cells'].pop(0)
    1664. 

  1664. 		# set each cell align
    1665. 

  1665. 		if rules['tablecellaligntype'] == 'cell':
    1666. 

  1666. 			align = table['cellalign'].pop(0)
    1667. 

  1667. 			align = TAGS['tableCellAlign%s'%align]
    1668. 

  1668. 			openalign = string.replace(open,'\a',align)
    1669. 

  1669. 		# show empty cell on HTML
    1670. 

  1670. 		if not cel and doctype == 'html': cel = '&nbsp;'
    1671. 

  1671. 		# last cell gotchas
    1672. 

  1672. 		if not table['cells']:
    1673. 

  1673. 			# don't need cell separator
    1674. 

  1674. 			if rules['tablecellsplit']: close = ''
    1675. 

  1675. 			# close beautifier for last title cell
    1676. 

  1676. 			if doctype == 'tex' and table['header']: close = '}'
    1677. 

  1677. 		# join it all
    1678. 

  1678. 		newcell = openalign + string.strip(cel) + close
    1679. 

  1679. 		ret = ret + newcell
    1680. 

  1680. 	return ret
    1681. 

  1681. 

  1682. 

  1683. def get_tableopen_tag(table_prop, doctype):
    1684. 

  1684. 	global tableborder
    1685. 

  1685. 	open = TAGS['tableOpen'] # the default one
    1686. 

  1686. 	# the first line defines if table has border or not
    1687. 

  1687. 	tableborder = table_prop['border']
    1688. 

  1688. 	# align full table
    1689. 

  1689. 	if rules['tablealignable']:
    1690. 

  1690. 		talign = TAGS['tableAlign'+table_prop['align']]
    1691. 

  1691. 		open = regex['x'].sub(talign, open, 1)
    1692. 

  1692. 	# set the columns alignment
    1693. 

  1693. 	if rules['tablecellaligntype'] == 'column':
    1694. 

  1694. 		calign = map(lambda x: TAGS['tableColAlign%s'%x],
    1695. 

  1695. 		             table_prop['cellalign'])
    1696. 

  1696. 		calign = string.join(calign,'')
    1697. 

  1697. 		open = regex['x'].sub(calign, open, 1)
    1698. 

  1698. 	# tex table spec, border or not: {|l|c|r|} , {lcr}
    1699. 

  1699. 	if doctype == 'tex' and not tableborder:
    1700. 

  1700. 		open = string.replace(open,'|','')
    1701. 

  1701. 	# we're almost done, just border left
    1702. 

  1702. 	tag = regex['x'].sub(`tableborder`, open)
    1703. 

  1703. 	return tag
    1704. 

  1704. 

  1705. 

  1706. # reference: http://www.iana.org/assignments/character-sets
    1707. 

  1707. # http://www.drclue.net/F1.cgi/HTML/META/META.html
    1708. 

  1708. def get_encoding_string(enc, doctype):
    1709. 

  1709. 	if not enc: return ''
    1710. 

  1710. 	# target specific translation table
    1711. 

  1711. 	translate = {
    1712. 

  1712. 	'tex': {
    1713. 

  1713. 	  # missing: ansinew , applemac , cp437 , cp437de , cp865
    1714. 

  1714. 	  'us-ascii'    : 'ascii',
    1715. 

  1715. 	  'windows-1250': 'cp1250',
    1716. 

  1716. 	  'windows-1252': 'cp1252',
    1717. 

  1717. 	  'ibm850'      : 'cp850',
    1718. 

  1718. 	  'ibm852'      : 'cp852',
    1719. 

  1719. 	  'iso-8859-1'  : 'latin1',
    1720. 

  1720. 	  'iso-8859-2'  : 'latin2',
    1721. 

  1721. 	  'iso-8859-3'  : 'latin3',
    1722. 

  1722. 	  'iso-8859-4'  : 'latin4',
    1723. 

  1723. 	  'iso-8859-5'  : 'latin5',
    1724. 

  1724. 	  'iso-8859-9'  : 'latin9',
    1725. 

  1725. 	  'koi8-r'      : 'koi8-r'
    1726. 

  1726. 	  }
    1727. 

  1727. 	}
    1728. 

  1728. 	# normalization
    1729. 

  1729. 	enc = re.sub('(?i)(us[-_]?)?ascii|us|ibm367','us-ascii'  , enc)
    1730. 

  1730. 	enc = re.sub('(?i)(ibm|cp)?85([02])'        ,'ibm85\\2'  , enc)
    1731. 

  1731. 	enc = re.sub('(?i)(iso[_-]?)?8859[_-]?'     ,'iso-8859-' , enc)
    1732. 

  1732. 	enc = re.sub('iso-8859-($|[^1-9]).*'        ,'iso-8859-1', enc)
    1733. 

  1733. 	# apply translation table
    1734. 

  1734. 	try: enc = translate[doctype][string.lower(enc)]
    1735. 

  1735. 	except: pass
    1736. 

  1736. 	return enc
    1737. 

  1737. 

  1738. 

  1739. ################################################################################
    1740. 

  1740. ###MerryChristmas,IdontwanttofighttonightwithyouImissyourbodyandIneedyourlove###
    1741. 

  1741. ################################################################################
    1742. 

  1742. 

  1743. 

  1744. def getAllConf(cmdlinelist, nocheck=0):
    1745. 

  1745. 	"""
    1746. 

  1746. 	Returns a list of (File Configuration, File Proprierties) tuples
    1747. 

  1747. 	for all the given Input files. The Configuration is the merge of
    1748. 

  1748. 	command line options and %!cmdline settings.
    1749. 

  1749. 	"""
    1750. 

  1750. 	all_confs = []
    1751. 

  1751. 	# parse command line to get input files list
    1752. 

  1752. 	cmdline = Cmdline(cmdlinelist, nocheck)
    1753. 

  1753. 	infiles = cmdline.cmdline_conf.get('infiles')
    1754. 

  1754. 	if not infiles: return []
    1755. 

  1755. 	
    1756. 

  1756. 	for infile in infiles:                 # multifile support
    1757. 

  1757. 		# the first file doesn't need to recall Cmdline()
    1758. 

  1758. 		if all_confs: cmdline = Cmdline(cmdlinelist, nocheck)
    1759. 

  1759. 		# extract file Headers and Config
    1760. 

  1760. 		prop = Proprierties(infile)
    1761. 

  1761. 		# decide to use generic or target specfic (if any) %!cmdline:
    1762. 

  1762. 		cmdline_target = cmdline.cmdline_conf.get('type')
    1763. 

  1763. 		if cmdline_target and cmdline_target in targets and \
    1764. 

  1764. 		   prop.config[cmdline_target].get('cmdline'):
    1765. 

  1765. 			cfgcmdline_target = cmdline_target
    1766. 

  1766. 		else:
    1767. 

  1767. 			cfgcmdline_target = 'all'
    1768. 

  1768. 		# merge %!cmdline contents (if any) into original cmdline
    1769. 

  1769. 		cmdline.merge(prop.config[cfgcmdline_target].get('cmdline'))
    1770. 

  1770. 		# force infile
    1771. 

  1771. 		cmdline.cmdline_conf['infile'] = infile
    1772. 

  1772. 		# get all the configuration (flags/options) for this file
    1773. 

  1773. 		# it saves general AND specific config (not OR as in %!cmdline)
    1774. 

  1774. 		myconf = cmdline.merge_conf(prop.config['all'])
    1775. 

  1775. 		myconf = cmdline.merge_conf(prop.config.get(myconf['type']), override=1)
    1776. 

  1776. 		# adding %!cmdline contents to config (used by GUI)
    1777. 

  1777. 		myconf['%!cmdline'] = prop.config[cfgcmdline_target].get('cmdline')
    1778. 

  1778. 		# ensure the configuration has ALL keys defined
    1779. 

  1779. 		for key in FLAGS.keys() + OPTIONS.keys() + CONFIG_KEYWORDS:
    1780. 

  1780. 			if not myconf.has_key(key): myconf[key] = ''
    1781. 

  1781. 		# append the (configuration, proprierties) tuple
    1782. 

  1782. 		all_confs.append((myconf,prop))
    1783. 

  1783. 		# remove what has left
    1784. 

  1784. 		del cmdline, prop
    1785. 

  1785. 	return all_confs
    1786. 

  1786. 

  1787. def convertAllFiles(confs):
    1788. 

  1788. 	if not confs: Quit(usage, 1)
    1789. 

  1789. 	header = []
    1790. 

  1790. 	for myconf,prop in confs:                 # multifile support
    1791. 

  1791. 		# --dump-source option handler
    1792. 

  1792. 		# hidden option, maybe will be removed on next versions
    1793. 

  1793. 		if myconf['dump-source']:
    1794. 

  1794. 			comment_id = '%--------------------- Area Delimiter:' 
    1795. 

  1795. 			for line in prop.headers: print line
    1796. 

  1796. 			print '%s HEADER --> CONFIG'%comment_id
    1797. 

  1797. 			for line in prop.conflines: print string.rstrip(line)
    1798. 

  1798. 			print '%s CONFIG --> BODY'%comment_id
    1799. 

  1799. 			doc = convert(prop.bodylines, myconf)
    1800. 

  1800. 			for line in doc: print line
    1801. 

  1801. 			print '%s EOD'%comment_id
    1802. 

  1802. 			continue
    1803. 

  1803. 		# compose the target file Headers
    1804. 

  1804. 		#TODO escape line before?
    1805. 

  1805. 		#TODO see exceptions by tex and mgp
    1806. 

  1806. 		header = doHeader(prop.headers, myconf)
    1807. 

  1807. 		# get the marked file BODY that has left
    1808. 

  1808. 		body = prop.bodylines
    1809. 

  1809. 		# parse the full marked body into tagged target
    1810. 

  1810. 		doc,toc = convert(body, myconf, firstlinenr=prop.arearef[-1])
    1811. 

  1811. 		# make TOC (if needed)
    1812. 

  1812. 		toc = toc_maker(toc,myconf)
    1813. 

  1813. 		# finally, we have our document
    1814. 

  1814. 		outlist = header + toc + doc
    1815. 

  1815. 		# break here if Gui - it has some more processing to do
    1816. 

  1816. 		if myconf['gui']: return outlist, myconf
    1817. 

  1817. 		# write results to file or STDOUT
    1818. 

  1818. 		finish_him(outlist, myconf)
    1819. 

  1819. 

  1820. def reallydoitall(cmdlinelist):
    1821. 

  1821. 	confs = getAllConf(cmdlinelist)
    1822. 

  1822. 	return convertAllFiles(confs)
    1823. 

  1823. 

  1824. def convert(bodylines, CONF, firstlinenr=1):
    1825. 

  1825. 	# global vars for doClose*()
    1826. 

  1826. 	global TAGS, regex, rules, quotedepth, listindent, listids
    1827. 

  1827. 	global subarea, tableborder
    1828. 

  1828. 	
    1829. 

  1829. 	doctype = CONF['type']
    1830. 

  1830. 	outfile = CONF['outfile']
    1831. 

  1831. 	TAGS = getTags(doctype)
    1832. 

  1832. 	rules = getRules(doctype)
    1833. 

  1833. 	regex = getRegexes()
    1834. 

  1834. 	
    1835. 

  1835. 	# the defaults
    1836. 

  1836. 	linkmask  = '@@_link_@@'
    1837. 

  1837. 	monomask  = '@@_mono_@@'
    1838. 

  1838. 	macromask = '@@_macro_@@'
    1839. 

  1839. 	rawmask   = '@@_raw_@@'
    1840. 

  1840. 	
    1841. 

  1841. 	subarea = SubareaMaster()
    1842. 

  1842. 	ret = []
    1843. 

  1843. 	incdumpbuf = []
    1844. 

  1844. 	toclist = []
    1845. 

  1845. 	f_tt = 0
    1846. 

  1846. 	listindent = []
    1847. 

  1847. 	listids = []
    1848. 

  1848. 	listcount = []
    1849. 

  1849. 	titlecount = ['',0,0,0,0,0]
    1850. 

  1850. 	f_lastwasblank = 0
    1851. 

  1851. 	holdspace = ''
    1852. 

  1852. 	listholdspace = ''
    1853. 

  1853. 	quotedepth = []
    1854. 

  1854. 	tableborder = 0
    1855. 

  1855. 	
    1856. 

  1856. 	if outfile != STDOUT:
    1857. 

  1857. 		if not CONF['gui']:
    1858. 

  1858. 			print "--- %s..."%doctype
    1859. 

  1859. 	
    1860. 

  1860. 	# if TOC is a header tag
    1861. 

  1861. 	if CONF['toc'] and TAGS['TOC']:
    1862. 

  1862. 		ret.append(TAGS['TOC']+'\n')
    1863. 

  1863. 	
    1864. 

  1864. 	# let's put the opening paragraph
    1865. 

  1865. 	if doctype != 'pm6':
    1866. 

  1866. 		ret.append(TAGS['paragraph'])
    1867. 

  1867. 	
    1868. 

  1868. 	# let's mark it up!
    1869. 

  1869. 	linenr = firstlinenr-1
    1870. 

  1870. 	lineref = -1
    1871. 

  1871. 	while lineref < len(bodylines)-1:
    1872. 

  1872. #	for lineref in range(len(bodylines)):
    1873. 

  1873. 		lineref = lineref + 1
    1874. 

  1874. #		print lineref, len(bodylines)
    1875. 

  1875. 		skip_continue = 0
    1876. 

  1876. 		linkbank = []
    1877. 

  1877. 		monobank = []
    1878. 

  1878. 		macrobank = []
    1879. 

  1879. 		rawbank = []
    1880. 

  1880. 		
    1881. 

  1881. 		untouchedline = bodylines[lineref]
    1882. 

  1882. 		line = re.sub('[\n\r]+$','',untouchedline)   # del line break
    1883. 

  1883. 		incdumpbuf.append(line)                      # for --dump-source
    1884. 

  1884. 		
    1885. 

  1885. 		# apply PreProc rules
    1886. 

  1886. 		if CONF['preproc']:
    1887. 

  1887. 			for targ,patt,repl in CONF['preproc']:
    1888. 

  1888. 				if targ not in [CONF['type'], 'all']: continue
    1889. 

  1889. 				try   : line = re.sub(patt, repl, line)
    1890. 

  1890. 				except: Error("Invalid PreProc filter regex: '%s'"%patt)
    1891. 

  1891. 		
    1892. 

  1892. 		line = maskEscapeChar(line)                  # protect \ char
    1893. 

  1893. 		linenr = linenr +1
    1894. 

  1894. 		
    1895. 

  1895. 		Debug('LINE %04d: %s'%(linenr,repr(line)), 1)  # heavy debug
    1896. 

  1896. 		
    1897. 

  1897. 		# we need (not really) to mark each paragraph
    1898. 

  1898. 		#TODO check if this is really needed
    1899. 

  1899. 		if doctype == 'pm6' and f_lastwasblank:
    1900. 

  1900. 			if f_tt or listindent:
    1901. 

  1901. 				holdspace = ''
    1902. 

  1902. 			else:
    1903. 

  1903. 				holdspace = TAGS['paragraph']+'\n'
    1904. 

  1904. 		
    1905. 

  1905. 		# any NOT table line (or comment), closes an open table
    1906. 

  1906. 		#if subarea() == 'table' and not regex['table'].search(line):
    1907. 

  1907. 		if subarea() == 'table' \
    1908. 

  1908. 		  and not regex['table'].search(line) \
    1909. 

  1909. 		  and not regex['comment'].search(line):
    1910. 

  1910. 			ret.append(doCloseTable(doctype))
    1911. 

  1911. 		
    1912. 

  1912. 		
    1913. 

  1913. 		#---------------------[ PRE formatted ]----------------------
    1914. 

  1914. 		
    1915. 

  1915. 		#TIP we'll never support beautifiers inside pre-formatted
    1916. 

  1916. 		
    1917. 

  1917. 		# we're already on a PRE area
    1918. 

  1918. 		if f_tt:
    1919. 

  1919. 			# closing PRE
    1920. 

  1920. 			if regex['areaPreClose'].search(line):
    1921. 

  1921. 				if doctype != 'pm6':
    1922. 

  1922. 					ret.append(TAGS['areaPreClose'])
    1923. 

  1923. 				f_tt = 0
    1924. 

  1924. 				continue
    1925. 

  1925. 			
    1926. 

  1926. 			# normal PRE-inside line
    1927. 

  1927. 			line = doPreLine(doctype, line)
    1928. 

  1928. 			ret.append(line)
    1929. 

  1929. 			continue
    1930. 

  1930. 		
    1931. 

  1931. 		# detecting PRE area init
    1932. 

  1932. 		if regex['areaPreOpen'].search(line):
    1933. 

  1933. 			ret.append(TAGS['areaPreOpen'])
    1934. 

  1934. 			f_lastwasblank = 0
    1935. 

  1935. 			f_tt = 1
    1936. 

  1936. 			continue
    1937. 

  1937. 		
    1938. 

  1938. 		# one line PRE-formatted text
    1939. 

  1939. 		if regex['1linePre'].search(line):
    1940. 

  1940. 			f_lastwasblank = 0
    1941. 

  1941. 			line = regex['1linePre'].sub('',line)
    1942. 

  1942. 			line = doPreLine(doctype, line)
    1943. 

  1943. 			t1, t2 = TAGS['areaPreOpen'],TAGS['areaPreClose']
    1944. 

  1944. 			ret.append('%s\n%s\n%s'%(t1,line,t2))
    1945. 

  1945. 			continue
    1946. 

  1946. 		
    1947. 

  1947. 		#---------------------[ blank lines ]-----------------------
    1948. 

  1948. 		
    1949. 

  1949. 		#TODO "holdspace" to save <p> to not show in closelist
    1950. 

  1950. 		if regex['blankline'].search(line):
    1951. 

  1951. 			
    1952. 

  1952. 			# closing all open quotes
    1953. 

  1953. 			if quotedepth:
    1954. 

  1954. 				ret.append(doCloseQuote())
    1955. 

  1955. 			
    1956. 

  1956. 			# closing all open lists
    1957. 

  1957. 			if f_lastwasblank:   # 2nd consecutive blank line
    1958. 

  1958. 				if listindent:   # closes list (if any)
    1959. 

  1959. 					ret.append(doCloseList())
    1960. 

  1960. 					holdspace = ''
    1961. 

  1961. 				continue         # consecutive blanks are trash
    1962. 

  1962. 			
    1963. 

  1963. 			# normal blank line
    1964. 

  1964. 			if doctype != 'pm6':
    1965. 

  1965. 				# paragraph (if any) is wanted inside lists also
    1966. 

  1966. 				if listindent:
    1967. 

  1967. 					para = TAGS['paragraph'] + '\n'
    1968. 

  1968. 					holdspace = holdspace + para
    1969. 

  1969. 				elif doctype == 'html':
    1970. 

  1970. 					ret.append(TAGS['paragraph'])
    1971. 

  1971. 				# sgml: quote close tag must not be \n\n</quote>
    1972. 

  1972. 				elif doctype == 'sgml' and quotedepth:
    1973. 

  1973. 					skip_continue = 1
    1974. 

  1974. 				# otherwise we just show a blank line
    1975. 

  1975. 				else:
    1976. 

  1976. 					ret.append('')
    1977. 

  1977. 			
    1978. 

  1978. 			f_lastwasblank = 1
    1979. 

  1979. 			if not skip_continue: continue
    1980. 

  1980. 		
    1981. 

  1981. 		
    1982. 

  1982. 		#---------------------[ special ]------------------------
    1983. 

  1983. 		
    1984. 

  1984. 		if regex['special'].search(line):
    1985. 

  1985. 			
    1986. 

  1986. 			# include command
    1987. 

  1987. 			m = ParseConfig(line, 'include', doctype)
    1988. 

  1988. 			if m:
    1989. 

  1989. 				incpath = os.path.dirname(CONF['infile'])
    1990. 

  1990. 				incfile = m['value']
    1991. 

  1991. 				if CONF['infile'] == incfile:
    1992. 

  1992. 					Error('A file cannot include itself (loop!): %s'%incfile)
    1993. 

  1993. 				inctype, inclines = get_include_contents(incfile, incpath)
    1994. 

  1994. 				
    1995. 

  1995. 				if inctype == 'PASS':
    1996. 

  1996. 					ret.extend(inclines)
    1997. 

  1997. 					continue
    1998. 

  1998. 				
    1999. 

  1999. 				# change %!include command by comment
    2000. 

  2000. 				incdumpbuf[-1] = inclines[0]
    2001. 

  2001. 				
    2002. 

  2002. 				# insert include lines into bodylines list
    2003. 

  2003. 				# removing the %!include command call
    2004. 

  2004. 				bodylines = bodylines[:lineref] +inclines \
    2005. 

  2005. 				           +bodylines[lineref+1:]
    2006. 

  2006. 				continue
    2007. 

  2007. 		
    2008. 

  2008. 		#---------------------[ comments ]-----------------------
    2009. 

  2009. 		
    2010. 

  2010. 		# just skip them (if not macro or config)
    2011. 

  2011. 		if regex['comment'].search(line) and not \
    2012. 

  2012. 		   regex['date'].match(line):
    2013. 

  2013. 			continue
    2014. 

  2014. 		f_lastwasblank = 0       # reset blank status
    2015. 

  2015. 		
    2016. 

  2016. 		#---------------------[ Title ]-----------------------
    2017. 

  2017. 		
    2018. 

  2018. 		#TODO set next blank and set f_lastwasblank or f_lasttitle
    2019. 

  2019. 		if (regex['title'].search(line) or
    2020. 

  2020. 		    regex['numtitle'].search(line)) and not listindent:
    2021. 

  2021. 			
    2022. 

  2022. 			if string.lstrip(line)[0] == '=':
    2023. 

  2023. 				titletype = 'title'
    2024. 

  2024. 			else:
    2025. 

  2025. 				titletype = 'numtitle'
    2026. 

  2026. 			
    2027. 

  2027. 			m = regex[titletype].search(line)
    2028. 

  2028. 			level = len(m.group('id'))
    2029. 

  2029. 			tag = TAGS['title%s'%level]
    2030. 

  2030. 			txt = string.strip(m.group('txt'))
    2031. 

  2031. 			
    2032. 

  2032. 			### numbered title
    2033. 

  2033. 			if CONF['enumtitle'] or titletype == 'numtitle':
    2034. 

  2034. 				if rules['autonumbertitle']:
    2035. 

  2035. 					tag = TAGS['numtitle%s'%level] or tag
    2036. 

  2036. 					idtxt = txt
    2037. 

  2037. 				else:
    2038. 

  2038. 					# add count manually
    2039. 

  2039. 					id = '' ; n = level
    2040. 

  2040. 					titlecount[n] = titlecount[n] +1
    2041. 

  2041. 					if n < len(titlecount)-1: # reset sublevels count
    2042. 

  2042. 						for i in range(n+1, len(titlecount)):
    2043. 

  2043. 							titlecount[i] = 0
    2044. 

  2044. 					for i in range(n):        # compose id from hierarchy
    2045. 

  2045. 						id = "%s%d."%(id,titlecount[i+1])
    2046. 

  2046. 					idtxt = "%s %s"%(id, txt) # add id to title
    2047. 

  2047. 			else:
    2048. 

  2048. 				idtxt = txt
    2049. 

  2049. 			
    2050. 

  2050. 			anchorid = 'toc%d'%(len(toclist)+1)
    2051. 

  2051. 			if TAGS['anchor'] and CONF['toc'] \
    2052. 

  2052. 			  and level <= CONF['toclevel']:
    2053. 

  2053. 				ret.append(regex['x'].sub(anchorid,TAGS['anchor']))
    2054. 

  2054. 			
    2055. 

  2055. 			# place title tag overriding line
    2056. 

  2056. 			line = regex[titletype].sub(tag,line)
    2057. 

  2057. 			
    2058. 

  2058. 			### escape title text (unescaped text is used for TOC)
    2059. 

  2059. 			#
    2060. 

  2060. 			esctxt = doEscape(doctype,idtxt)
    2061. 

  2061. 			# sgml: [ is special on title (and lists) - here bcos 'continue'
    2062. 

  2062. 			if doctype in ['sgml','tex']:
    2063. 

  2063. 				esctxt = doFinalEscape(doctype, esctxt)
    2064. 

  2064. 			# txt: blank before
    2065. 

  2065. 			if doctype == 'txt': ret.append('')
    2066. 

  2066. 			# finish title line
    2067. 

  2067. 			ret.append(regex['x'].sub(esctxt,line))
    2068. 

  2068. 			
    2069. 

  2069. 			# add "underline" to text titles
    2070. 

  2070. 			if doctype == 'txt':
    2071. 

  2071. 				ret.append(regex['x'].sub('='*len(idtxt),tag))
    2072. 

  2072. 				ret.append('') # blank line after
    2073. 

  2073. 			
    2074. 

  2074. 			# let's do some TOC!
    2075. 

  2075. 			if not CONF['toc'] and not CONF['toconly']: continue
    2076. 

  2076. 			if level > CONF['toclevel']: continue    # max level
    2077. 

  2077. 			if TAGS['TOC']: continue                 # TOC is a tag
    2078. 

  2078. 			if TAGS['anchor']:
    2079. 

  2079. 				# tocitemid = '#toc%d'%(len(toclist)+1)
    2080. 

  2080. 				# TOC more readable with master topics not
    2081. 

  2081. 				# linked at number stoled idea from windows .CHM
    2082. 

  2082. 				# files (help system)
    2083. 

  2083. 				if CONF['enumtitle'] and level == 1:
    2084. 

  2084. 					tocitem = '%s+ [``%s`` #%s]'%(' '*level,txt,anchorid)
    2085. 

  2085. 				else:
    2086. 

  2086. 					tocitem = '%s- [``%s`` #%s]'%(' '*level,idtxt,anchorid)
    2087. 

  2087. 			else:
    2088. 

  2088. 				tocitem = '%s- ``%s``'%(' '*level,idtxt)
    2089. 

  2089. 				if doctype in ['txt', 'man']:
    2090. 

  2090. 					tocitem = '%s``%s``' %('  '*level,idtxt)
    2091. 

  2091. 			toclist.append(tocitem)
    2092. 

  2092. 			
    2093. 

  2093. 			continue
    2094. 

  2094. 		
    2095. 

  2095. 		#TODO!	labeltxt = ''
    2096. 

  2096. 		#		label = m.group('label')
    2097. 

  2097. 		#		if label: labeltxt = '<label id="%s">' %label
    2098. 

  2098. 		
    2099. 

  2099. 		
    2100. 

  2100. 		#---------------------[ apply masks ]-----------------------
    2101. 

  2101. 		
    2102. 

  2102. 		### protect important structures from escaping and formatting
    2103. 

  2103. 		while regex['raw'].search(line):
    2104. 

  2104. 			txt = regex['raw'].search(line).group(1)
    2105. 

  2105. 			txt = doEscape(doctype,txt)
    2106. 

  2106. 			rawbank.append(txt)
    2107. 

  2107. 			line = regex['raw'].sub(rawmask,line,1)
    2108. 

  2108. 		
    2109. 

  2109. 		# protect pre-formatted font text
    2110. 

  2110. 		while regex['fontMono'].search(line):
    2111. 

  2111. 			txt = regex['fontMono'].search(line).group(1)
    2112. 

  2112. 			txt = doEscape(doctype,txt)
    2113. 

  2113. 			monobank.append(txt)
    2114. 

  2114. 			line = regex['fontMono'].sub(monomask,line,1)
    2115. 

  2115. 		
    2116. 

  2116. 		# protect macros
    2117. 

  2117. 		while regex['macro'].search(line):
    2118. 

  2118. 			txt = regex['macro'].search(line).group()
    2119. 

  2119. 			macrobank.append(txt)
    2120. 

  2120. 			line = regex['macro'].sub(macromask,line,1)
    2121. 

  2121. 		
    2122. 

  2122. 		# protect URLs and emails
    2123. 

  2123. 		while regex['linkmark'].search(line) or regex['link'].search(line):
    2124. 

  2124. 			
    2125. 

  2125. 			# try to match plain or named links
    2126. 

  2126. 			match_link  = regex['link'].search(line)
    2127. 

  2127. 			match_named = regex['linkmark'].search(line)
    2128. 

  2128. 			
    2129. 

  2129. 			# define the current match
    2130. 

  2130. 			if match_link and match_named:
    2131. 

  2131. 				# both types found, which is the first?
    2132. 

  2132. 				m = match_link
    2133. 

  2133. 				if match_named.start() < match_link.start():
    2134. 

  2134. 					m = match_named
    2135. 

  2135. 			else:
    2136. 

  2136. 				# just one type found, we're fine
    2137. 

  2137. 				m = match_link or match_named
    2138. 

  2138. 			
    2139. 

  2139. 			# extract link data and apply mask
    2140. 

  2140. 			if m == match_link:              # plain link
    2141. 

  2141. 				label = ''
    2142. 

  2142. 				link  = m.group()
    2143. 

  2143. 				line  = regex['link'].sub(linkmask,line,1)
    2144. 

  2144. 			else:                            # named link
    2145. 

  2145. 				label = string.rstrip(m.group('label'))
    2146. 

  2146. 				link  = m.group('link')
    2147. 

  2147. 				line = regex['linkmark'].sub(linkmask,line,1)
    2148. 

  2148. 			
    2149. 

  2149. 			# save link data to the link bank
    2150. 

  2150. 			linkbank.append((label, link))
    2151. 

  2151. 		
    2152. 

  2152. 		#---------------------[ do Escapes ]-----------------------
    2153. 

  2153. 		
    2154. 

  2154. 		# the target-specific special char escapes for body lines
    2155. 

  2155. 		line = doEscape(doctype,line)
    2156. 

  2156. 		
    2157. 

  2157. 		#---------------------[ Horizontal Bar ]--------------------
    2158. 

  2158. 		
    2159. 

  2159. 		if regex['bar'].search(line):
    2160. 

  2160. 			txt = regex['bar'].search(line).group(1)
    2161. 

  2161. 			if txt[0] == '=': bar = TAGS['bar2']
    2162. 

  2162. 			else            : bar = TAGS['bar1']
    2163. 

  2163. 			
    2164. 

  2164. 			# to avoid comment tag confusion
    2165. 

  2165. 			if doctype == 'sgml':
    2166. 

  2166. 				txt = string.replace(txt,'--','__')
    2167. 

  2167. 			
    2168. 

  2168. 			line = regex['bar'].sub(bar,line)
    2169. 

  2169. 			ret.append(regex['x'].sub(txt,line))
    2170. 

  2170. 			continue
    2171. 

  2171. 		
    2172. 

  2172. 		#---------------------[ Quote ]-----------------------
    2173. 

  2173. 		
    2174. 

  2174. 		if regex['quote'].search(line):
    2175. 

  2175. 			subarea.add('quote')
    2176. 

  2176. 			
    2177. 

  2177. 			# store number of leading TABS
    2178. 

  2178. 			currquotedepth = len(regex['quote'].search(line).group(0))
    2179. 

  2179. 			
    2180. 

  2180. 			# SGML doesn't support nested quotes
    2181. 

  2181. 			if rules['quotenotnested']:
    2182. 

  2182. 				if quotedepth and currquotedepth > quotedepth[-1]:
    2183. 

  2183. 					currquotedepth = quotedepth[-1]
    2184. 

  2184. 			
    2185. 

  2185. 			# for don't-close-me quote tags
    2186. 

  2186. 			if not TAGS['areaQuoteClose']:
    2187. 

  2187. 				line = regex['quote'].sub(TAGS['areaQuoteOpen']*currquotedepth, line)
    2188. 

  2188. 			else:
    2189. 

  2189. 				# new (sub)quote
    2190. 

  2190. 				if not quotedepth or currquotedepth > quotedepth[-1]:
    2191. 

  2191. 					quotedepth.append(currquotedepth)
    2192. 

  2192. 					ret.append(TAGS['areaQuoteOpen'])
    2193. 

  2193. 				
    2194. 

  2194. 				# remove leading TABs
    2195. 

  2195. 				if not rules['keepquoteindent']:
    2196. 

  2196. 					line = regex['quote'].sub('', line)
    2197. 

  2197. 				
    2198. 

  2198. 				# closing quotes
    2199. 

  2199. 				while currquotedepth < quotedepth[-1]:
    2200. 

  2200. 					ret.append(doCloseQuote(1))
    2201. 

  2201. 		else:
    2202. 

  2202. 			# closing all quotes (not quote line)
    2203. 

  2203. 			if quotedepth: ret.append(doCloseQuote())
    2204. 

  2204. 		
    2205. 

  2205. 		
    2206. 

  2206. 		#---------------------[ Lists ]-----------------------
    2207. 

  2207. 		
    2208. 

  2208. 		if (regex['list'].search(line) or regex['deflist'].search(line)):
    2209. 

  2209. 			subarea.add('list')
    2210. 

  2210. 			
    2211. 

  2211. 			if regex['list'].search(line): rgx = regex['list']
    2212. 

  2212. 			else: rgx = regex['deflist']
    2213. 

  2213. 			
    2214. 

  2214. 			m = rgx.search(line)
    2215. 

  2215. 			listitemindent = m.group(1)
    2216. 

  2216. 			listtype = m.group(2)
    2217. 

  2217. 			extra = m.group(3)        # regex anchor char
    2218. 

  2218. 			
    2219. 

  2219. 			if listtype == '=':
    2220. 

  2220. 				listdefterm = m.group(3)
    2221. 

  2221. 				extra = ''
    2222. 

  2222. 				if doctype == 'tex':
    2223. 

  2223. 					# on tex, brackets are term delimiters
    2224. 

  2224. 					# TODO escape ] at list definition
    2225. 

  2225. 					# \], \rbrack{} and \verb!]!  don't work :(
    2226. 

  2226. 					#listdefterm = string.replace(listdefterm, ']', '???')
    2227. 

  2227. 					pass
    2228. 

  2228. 				if not rules['imgasdefterm'] and \
    2229. 

  2229. 				   regex['img'].search(listdefterm):
    2230. 

  2230. 					while regex['img'].search(listdefterm):
    2231. 

  2231. 						img = regex['img'].search(listdefterm).group(1)
    2232. 

  2232. 						masked = '(%s)'%img
    2233. 

  2233. 						listdefterm = regex['img'].sub(masked,listdefterm,1)
    2234. 

  2234. 			
    2235. 

  2235. 			# don't cross depth limit
    2236. 

  2236. 			maxdepth =  rules['listmaxdepth']
    2237. 

  2237. 			if maxdepth and len(listindent) == maxdepth:
    2238. 

  2238. 				if len(listitemindent) > len(listindent[-1]):
    2239. 

  2239. 					listitemindent = listindent[-1]
    2240. 

  2240. 			
    2241. 

  2241. 			# new sublist
    2242. 

  2242. 			if not listindent or len(listitemindent) > len(listindent[-1]):
    2243. 

  2243. 				listindent.append(listitemindent)
    2244. 

  2244. 				listids.append(listtype)
    2245. 

  2245. 				if   listids[-1] == '-': tag = TAGS['listOpen']
    2246. 

  2246. 				elif listids[-1] == '+': tag = TAGS['numlistOpen']
    2247. 

  2247. 				elif listids[-1] == '=': tag = TAGS['deflistOpen']
    2248. 

  2248. 				if not tag: tag = TAGS['listOpen'] # default
    2249. 

  2249. 				# no need to reopen <pre> tag on man sublists
    2250. 

  2250. 				if rules['listnotnested'] and len(listindent) != 1:
    2251. 

  2251. 					tag = ''
    2252. 

  2252. 				openlist = listindent[-1]+tag
    2253. 

  2253. 				if doctype == 'pm6':
    2254. 

  2254. 					listholdspace = openlist
    2255. 

  2255. 				else:
    2256. 

  2256. 					if string.strip(openlist): ret.append(openlist)
    2257. 

  2257. 				# reset item manual count
    2258. 

  2258. 				listcount.append(0)
    2259. 

  2259. 			
    2260. 

  2260. 			# closing sublists
    2261. 

  2261. 			while len(listitemindent) < len(listindent[-1]):
    2262. 

  2262. 				close = doCloseList(1)
    2263. 

  2263. 				if close: ret.append(close)
    2264. 

  2264. 				if listcount: del listcount[-1]
    2265. 

  2265. 			
    2266. 

  2266. 			# normal item
    2267. 

  2267. 			listid = listindent[-1]
    2268. 

  2268. 			if listids[-1] == '-':
    2269. 

  2269. 				tag = TAGS['listItem']
    2270. 

  2270. 			elif listids[-1] == '+':
    2271. 

  2271. 				tag = TAGS['numlistItem']
    2272. 

  2272. 				listcount[-1] = listcount[-1] +1
    2273. 

  2273. 				if not rules['autonumberlist']:
    2274. 

  2274. 					tag = regex['x'].sub(str(listcount[-1]), tag)
    2275. 

  2275. 			elif listids[-1] == '=':
    2276. 

  2276. 				if not TAGS['deflistItem1']:
    2277. 

  2277. 					# emulate def list, with <li><b>def</b>:
    2278. 

  2278. 					tag = TAGS['listItem'] +TAGS['fontBoldOpen'] +listdefterm
    2279. 

  2279. 					tag = tag +TAGS['fontBoldClose'] +':'
    2280. 

  2280. 				else:
    2281. 

  2281. 					tag = regex['x'].sub(listdefterm, TAGS['deflistItem1'])
    2282. 

  2282. 				tag = tag + TAGS['deflistItem2']  # open <DD>
    2283. 

  2283. 			if doctype == 'mgp': listid = len(listindent)*'\t'
    2284. 

  2284. 			line = rgx.sub(listid+tag+extra,line)
    2285. 

  2285. 			if listholdspace:
    2286. 

  2286. 				line = listholdspace+line
    2287. 

  2287. 				listholdspace = ''
    2288. 

  2288. 		
    2289. 

  2289. 		
    2290. 

  2290. 		#---------------------[ Table ]-----------------------
    2291. 

  2291. 		
    2292. 

  2292. 		#TODO escape undesired format inside table
    2293. 

  2293. 		#TODO add man, pm6 targets
    2294. 

  2294. 		if regex['table'].search(line):
    2295. 

  2295. 			
    2296. 

  2296. 			table = get_table_prop(line)
    2297. 

  2297. 			
    2298. 

  2298. 			if subarea() != 'table':
    2299. 

  2299. 				subarea.add('table')        # first table line!
    2300. 

  2300. 				if rules['tableable']:      # table-aware target
    2301. 

  2301. 					ret.append(get_tableopen_tag(table,doctype))
    2302. 

  2302. 				else:                       # if not, use verb
    2303. 

  2303. 					ret.append(TAGS['areaPreOpen'])
    2304. 

  2304. 			
    2305. 

  2305. 			if rules['tableable']:
    2306. 

  2306. 				# setting line tags
    2307. 

  2307. 				tl1 = TAGS['tableLineOpen']
    2308. 

  2308. 				tl2 = TAGS['tableLineClose']
    2309. 

  2309. 				# little table gotchas
    2310. 

  2310. 				if rules['breaktablelineopen']:
    2311. 

  2311. 					tl1 = tl1+'\n'
    2312. 

  2312. 				if doctype == 'tex' and not tableborder:
    2313. 

  2313. 					tl1 = ''
    2314. 

  2314. 				# do cells and finish
    2315. 

  2315. 				cells = tag_table_cells(table, doctype)
    2316. 

  2316. 				line = tl1 + cells + tl2
    2317. 

  2317. 		
    2318. 

  2318. 		
    2319. 

  2319. 		### BEGIN of at-any-part-of-the-line/various-per-line TAGs.
    2320. 

  2320. 		
    2321. 

  2321. 		for beauti in ['Bold', 'Italic', 'Bolditalic', 'Underline']:
    2322. 

  2322. 			if regex['font%s'%beauti].search(line):
    2323. 

  2323. 				line = beautify_me(beauti, line)
    2324. 

  2324. 		
    2325. 

  2325. 		#---------------------[ URL & E-mail ]-----------------------
    2326. 

  2326. 		
    2327. 

  2327. 		for label,url in linkbank:
    2328. 

  2328. 			link = get_tagged_link(label, url, CONF)
    2329. 

  2329. 			line = string.replace(line, linkmask, link, 1)
    2330. 

  2330. 		
    2331. 

  2331. 		#---------------------[ Image ]-----------------------
    2332. 

  2332. 		
    2333. 

  2333. 		#TODO fix smart align when image is a link label
    2334. 

  2334. 		while regex['img'].search(line) and TAGS['img'] != '[\a]':
    2335. 

  2335. 			txt = regex['img'].search(line).group(1)
    2336. 

  2336. 			tag = TAGS['img']
    2337. 

  2337. 			
    2338. 

  2338. 			# HTML is the only align-aware target for now
    2339. 

  2339. 			if rules['imgalignable']:
    2340. 

  2340. 				align = get_image_align(line)
    2341. 

  2341. 				if align == 'para':
    2342. 

  2342. 					align = 'center'
    2343. 

  2343. 					tag= regex['x'].sub(tag,TAGS['imgsolo'])
    2344. 

  2344. 				# add align on tag
    2345. 

  2345. 				tag = regex['x'].sub(align, tag, 1)
    2346. 

  2346. 			
    2347. 

  2347. 			if doctype == 'tex': tag = re.sub(r'\\b',r'\\\\b',tag)
    2348. 

  2348. 			line = regex['img'].sub(tag,line,1)
    2349. 

  2349. 			line = regex['x'].sub(txt,line,1)
    2350. 

  2350. 		
    2351. 

  2351. 		#---------------------[ Expand Macros ]-----------------------
    2352. 

  2352. 		
    2353. 

  2353. 		if macrobank:
    2354. 

  2354. 			for macro in macrobank:
    2355. 

  2355. 				line = string.replace(line, macromask, macro,1)
    2356. 

  2356. 			# now the line is full of macros again
    2357. 

  2357. 			line = doDateMacro(line)
    2358. 

  2358. 		
    2359. 

  2359. 		#---------------------[ Expand PREs ]-----------------------
    2360. 

  2360. 		
    2361. 

  2361. 		for mono in monobank:
    2362. 

  2362. 			open,close = TAGS['fontMonoOpen'],TAGS['fontMonoClose']
    2363. 

  2363. 			tagged = open+mono+close
    2364. 

  2364. 			line = string.replace(line,monomask,tagged,1)
    2365. 

  2365. 		
    2366. 

  2366. 		#---------------------[ Expand raw ]-----------------------
    2367. 

  2367. 		
    2368. 

  2368. 		for raw in rawbank:
    2369. 

  2369. 			line = string.replace(line,rawmask,raw,1)
    2370. 

  2370. 		
    2371. 

  2371. 		#---------------------[ Final Escapes ]-----------------------
    2372. 

  2372. 		
    2373. 

  2373. 		line = doFinalEscape(doctype, line)
    2374. 

  2374. 		ret.append(holdspace+line)
    2375. 

  2375. 		holdspace = ''
    2376. 

  2376. 	
    2377. 

  2377. 	# We just need the included dump
    2378. 

  2378. 	if CONF['dump-source']: return incdumpbuf
    2379. 

  2379. 	
    2380. 

  2380. 	# EOF: close any open lists/tables/quotes
    2381. 

  2381. 	#TODO take table exception out when self.doctype
    2382. 

  2382. 	while subarea():
    2383. 

  2383. 		func = eval("doClose%s" % string.capitalize(subarea()))
    2384. 

  2384. 		parm = None
    2385. 

  2385. 		if subarea() == 'table': parm = doctype
    2386. 

  2386. 		txt = func(parm)
    2387. 

  2387. 		if txt: ret.append(txt)
    2388. 

  2388. 	
    2389. 

  2389. 	# add footer
    2390. 

  2390. 	if not CONF['noheaders']:
    2391. 

  2391. 		ret.extend(doFooter(CONF))
    2392. 

  2392. 	
    2393. 

  2393. 	if CONF['toconly']: ret = []
    2394. 

  2394. 	return ret, toclist
    2395. 

  2395. 

  2396. 

  2397. 

  2398. ################################################################################
    2399. 

  2399. ##################################### GUI ######################################
    2400. 

  2400. ################################################################################
    2401. 

  2401. 

  2402. # tk help: http://python.org/topics/tkinter/
    2403. 

  2403. class Gui:
    2404. 

  2404. 	"Graphical Tk Interface"
    2405. 

  2405. 	def __init__(self, conf={}):
    2406. 

  2406. 		self.bg = 'orange'
    2407. 

  2407. 		self.root = Tkinter.Tk()
    2408. 

  2408. 		self.root.config(bd=15,bg=self.bg)
    2409. 

  2409. 		self.root.title("txt2tags")
    2410. 

  2410. 		self.frame1 = Tkinter.Frame(self.root,bg=self.bg)
    2411. 

  2411. 		self.frame1.pack(fill='x')
    2412. 

  2412. 		self.frame2 = Tkinter.Frame(self.root,bg=self.bg)
    2413. 

  2413. 		self.frame2.pack()
    2414. 

  2414. 		self.frame3 = Tkinter.Frame(self.root,bg=self.bg)
    2415. 

  2415. 		self.frame3.pack(fill='x')
    2416. 

  2416. 		self.frame = self.root
    2417. 

  2417. 		
    2418. 

  2418. 		self.conf    = conf
    2419. 

  2419. 		self.infile  = self.setvar('')
    2420. 

  2420. 		#self.infile = self.setvar('C:/aurelio/a.txt')
    2421. 

  2421. 		self.doctype = self.setvar('')
    2422. 

  2422. 		self.checks  = ['noheaders','enumtitle','toc','toconly','stdout']
    2423. 

  2423. 		
    2424. 

  2424. 		# creating variables
    2425. 

  2425. 		for check in self.checks:
    2426. 

  2426. 			setattr(self, 'f_'+check, self.setvar(''))
    2427. 

  2427. 	
    2428. 

  2428. 	### config as dic for python 1.5 compat (**opts don't work :( )
    2429. 

  2429. 	def entry(self, **opts): return Tkinter.Entry(self.frame, opts)
    2430. 

  2430. 	def label(self, txt='', **opts):
    2431. 

  2431. 		opts.update({'text':txt,'bg':self.bg})
    2432. 

  2432. 		return Tkinter.Label(self.frame, opts)
    2433. 

  2433. 	def button(self,name,cmd,**opts):
    2434. 

  2434. 		opts.update({'text':name,'command':cmd})
    2435. 

  2435. 		return Tkinter.Button(self.frame, opts)
    2436. 

  2436. 	def check(self,name,val,checked=0,**opts):
    2437. 

  2437. 		opts.update( {'text':name, 'onvalue':val, 'offvalue':'',
    2438. 

  2438. 		  'anchor':'w', 'bg':self.bg, 'activebackground':self.bg} )
    2439. 

  2439. 		chk = Tkinter.Checkbutton(self.frame, opts)
    2440. 

  2440. 		if checked: chk.select()
    2441. 

  2441. 		chk.pack(fill='x',padx=10)
    2442. 

  2442. 	
    2443. 

  2443. 	def exit(self): self.root.destroy(); sys.exit()
    2444. 

  2444. 	def setvar(self, val): z = Tkinter.StringVar() ; z.set(val) ; return z
    2445. 

  2445. 	def menu(self,sel,items):
    2446. 

  2446. 		return apply(Tkinter.OptionMenu,(self.frame,sel)+tuple(items))
    2447. 

  2447. 	def askfile(self):
    2448. 

  2448. 		ftypes= [("txt2tags files",("*.t2t","*.txt")),("All files","*")]
    2449. 

  2449. 		newfile = askopenfilename(filetypes=ftypes)
    2450. 

  2450. 		if newfile:
    2451. 

  2451. 			self.infile.set(newfile)
    2452. 

  2452. 			newconf = getAllConf(['foo',newfile], nocheck=1)
    2453. 

  2453. 			if newconf: newconf = newconf[0][0]
    2454. 

  2454. 			# restate all checkboxes after file selection
    2455. 

  2455. 			# TODO how to make a refresh without killing it?
    2456. 

  2456. 			self.root.destroy()
    2457. 

  2457. 			self.__init__(newconf)
    2458. 

  2458. 			self.mainwindow()
    2459. 

  2459. 	
    2460. 

  2460. 	def scrollwindow(self,txt='no text!',title=''):
    2461. 

  2461. 		win = Tkinter.Toplevel() ; win.title(title)
    2462. 

  2462. 		scroll = Tkinter.Scrollbar(win)
    2463. 

  2463. 		text = Tkinter.Text(win,yscrollcommand=scroll.set)
    2464. 

  2464. 		scroll.config(command=text.yview)
    2465. 

  2465. 		text.insert(Tkinter.END, string.join(txt,'\n'))
    2466. 

  2466. 		text.pack(side='left',fill='both')
    2467. 

  2467. 		scroll.pack(side='right',fill='y')
    2468. 

  2468. 	
    2469. 

  2469. 	def runprogram(self):
    2470. 

  2470. 		# prepare
    2471. 

  2471. 		infile, doctype = self.infile.get(), self.doctype.get()
    2472. 

  2472. 		if not infile:
    2473. 

  2473. 			showwarning('txt2tags',\
    2474. 

  2474. 			   "You must provide the source file location!")
    2475. 

  2475. 			return
    2476. 

  2476. 		# compose cmdline
    2477. 

  2477. 		guiflags = []
    2478. 

  2478. 		for flag in self.checks:
    2479. 

  2479. 			flag = getattr(self, 'f_%s'%flag).get()
    2480. 

  2480. 			if flag: guiflags.append(flag)
    2481. 

  2481. 		cmdline = ['txt2tags', '--gui', '-t', doctype] +guiflags +[infile]
    2482. 

  2482. 		Debug('Gui/Tk cmdline: %s'%cmdline,1)
    2483. 

  2483. 		# run!
    2484. 

  2484. 		try:
    2485. 

  2485. 			outlist, CONF = reallydoitall(cmdline)
    2486. 

  2486. 			outfile = CONF['outfile']
    2487. 

  2487. 			infile  = CONF['infile']
    2488. 

  2488. 			outlist = finish_him(outlist,CONF) or ''
    2489. 

  2489. 			
    2490. 

  2490. 			if outfile == STDOUT:
    2491. 

  2491. 				title = 'txt2tags: %s converted to %s'%(
    2492. 

  2492. 				  os.path.basename(infile),
    2493. 

  2493. 				  string.upper(CONF['type']))
    2494. 

  2494. 				self.scrollwindow(outlist, title)
    2495. 

  2495. 			else:
    2496. 

  2496. 				msg = "Conversion done!\n\n" +\
    2497. 

  2497. 				      "FROM:\n\t%s\n"%infile +\
    2498. 

  2498. 				      "TO:\n\t%s"%outfile
    2499. 

  2499. 				showinfo('txt2tags', msg)
    2500. 

  2500. 		except ZeroDivisionError:   # common error, not quit
    2501. 

  2501. 			pass
    2502. 

  2502. 		except:                     # fatal error
    2503. 

  2503. 			traceback.print_exc()
    2504. 

  2504. 			print '\nSorry! txt2tags-Tk Fatal Error.'
    2505. 

  2505. 			errmsg = 'Unknown error occurred.\n\n'+\
    2506. 

  2506. 			         'Please send the Error Traceback '+\
    2507. 

  2507. 			         'dumped to the author:\n    %s'%my_email
    2508. 

  2508. 			showerror('txt2tags FATAL ERROR!',errmsg)
    2509. 

  2509. 			self.exit()
    2510. 

  2510. 	
    2511. 

  2511. 	def mainwindow(self):
    2512. 

  2512. 		#TODO show outfile somewhere
    2513. 

  2513. 		#TODO redraw GUI only using grid() because pack() sux
    2514. 

  2514. 		self.infile.set(self.conf.get('infile') or '')
    2515. 

  2515. 		self.doctype.set(self.conf.get('type') or 'html')
    2516. 

  2516. 		if self.conf.get('outfile') == STDOUT: # map -o-
    2517. 

  2517. 			self.conf['stdout'] = 1
    2518. 

  2518. 		
    2519. 

  2519. 		action1 = "  \nChoose the target document type:"
    2520. 

  2520. 		action2 = "\n\nEnter the tagged source file location:"
    2521. 

  2521. 		action3 = "\n\nSome options you may check:"
    2522. 

  2522. 		checks_txt = {
    2523. 

  2523. 		'noheaders': "Suppress headers from output",
    2524. 

  2524. 		'enumtitle': "Number titles (1, 1.1, 1.1.1, etc)",
    2525. 

  2525. 		'toc'      : "Do TOC also (Table of Contents)",
    2526. 

  2526. 		'toconly'  : "Just do TOC, nothing more",
    2527. 

  2527. 		'stdout'   : "Dump to screen (Don't save target file)"
    2528. 

  2528. 		}
    2529. 

  2529. 		
    2530. 

  2530. 		self.frame = self.frame1
    2531. 

  2531. 		self.label("TXT2TAGS\n%s\nv%s"%(my_url,my_version)).pack()
    2532. 

  2532. 		self.label(action1, anchor='w').pack(fill='x')
    2533. 

  2533. 		self.menu(self.doctype, targets).pack()
    2534. 

  2534. 		self.label(action2, anchor='w').pack(fill='x')
    2535. 

  2535. 		
    2536. 

  2536. 		self.frame = self.frame2
    2537. 

  2537. 		self.entry(textvariable=self.infile).grid(row=0, column=0)
    2538. 

  2538. 		self.button("Browse", self.askfile
    2539. 

  2539. 		     ).grid(row=0, column=1, padx=10)
    2540. 

  2540. 		if self.conf.get('%!cmdline'):
    2541. 

  2541. 			txt = '%%!cmdline: %s' % self.conf['%!cmdline']
    2542. 

  2542. 			self.label(txt,fg='brown'
    2543. 

  2543. 			    ).grid(row=1, column=0, columnspan=2, sticky='w')
    2544. 

  2544. 		
    2545. 

  2545. 		self.frame = self.frame3
    2546. 

  2546. 		self.label(action3, anchor='w').pack(fill='x')
    2547. 

  2547. 		
    2548. 

  2548. 		# compose options check boxes, example:
    2549. 

  2549. 		# self.check(checks_txt['toc'], '--toc', 1, variable=self.f_toc)
    2550. 

  2550. 		for check in self.checks:
    2551. 

  2551. 			txt = checks_txt[check]
    2552. 

  2552. 			opt = '--'+check
    2553. 

  2553. 			var = getattr(self, 'f_'+check)
    2554. 

  2554. 			onoff = self.conf.get(check)
    2555. 

  2555. 			self.check(txt,opt,onoff,variable=var)
    2556. 

  2556. 		
    2557. 

  2557. 		self.label('\n').pack()
    2558. 

  2558. 		self.button("Quit", self.exit).pack(side='left',padx=40)
    2559. 

  2559. 		self.button("Convert!", self.runprogram
    2560. 

  2560. 		     ).pack(side='right',padx=40)
    2561. 

  2561. 		
    2562. 

  2562. 		# as documentation told me
    2563. 

  2563. 		if sys.platform[:3] == 'win':
    2564. 

  2564. 			self.root.iconify()
    2565. 

  2565. 			self.root.update()
    2566. 

  2566. 			self.root.deiconify()
    2567. 

  2567. 		
    2568. 

  2568. 		self.root.mainloop()
    2569. 

  2569. 

  2570. 

  2571. ################################################################################
    2572. 

  2572. ################################################################################
    2573. 

  2573. 

  2574. 

  2575. if __name__ == '__main__':
    2576. 

  2576. 

  2577. 	# set debug and remove option from cmdline
    2578. 

  2578. 	if sys.argv.count('--debug'):
    2579. 

  2579. 		DEBUG = 1
    2580. 

  2580. 		sys.argv.remove('--debug')
    2581. 

  2581. 	
    2582. 

  2582. 	### check if we will enter on GUI mode
    2583. 

  2583. 	CONF['gui'] = 0
    2584. 

  2584. 	# GUI is default on this platforms, when called alone
    2585. 

  2585. 	if len(sys.argv) == 1 and sys.platform[:3] in ['mac','cyg','win']:
    2586. 

  2586. 		CONF['gui'] = 1
    2587. 

  2587. 	# user specified GUI mode	
    2588. 

  2588. 	if sys.argv.count('--gui'): CONF['gui'] = 1
    2589. 

  2589. 	
    2590. 

  2590. 	# check for GUI mode ressorces
    2591. 

  2591. 	if CONF['gui'] == 1:
    2592. 

  2592. 		try:
    2593. 

  2593. 			from tkFileDialog import askopenfilename
    2594. 

  2594. 			from tkMessageBox import showinfo,showwarning,showerror
    2595. 

  2595. 			import Tkinter
    2596. 

  2596. 		except:
    2597. 

  2597. 			# if GUI was forced, show the error message
    2598. 

  2598. 			if len(sys.argv) > 1 and sys.argv[1] == '--gui':
    2599. 

  2599. 				traceback.print_exc()
    2600. 

  2600. 				sys.exit()
    2601. 

  2601. 			# or just abandon GUI mode, and continue
    2602. 

  2602. 			else:
    2603. 

  2603. 				CONF['gui'] = 0
    2604. 

  2604. 	
    2605. 

  2605. 	Debug("system platform: %s"%sys.platform,1)
    2606. 

  2606. 	Debug("line break char: %s"%repr(LB),1)
    2607. 

  2607. 	nocheck = CONF['gui']                  # if GUI, no cmdline checking
    2608. 

  2608. 	CONFS = getAllConf(sys.argv, nocheck)  # get all infiles config (if any)
    2609. 

  2609. 	
    2610. 

  2610. 	if CONF['gui'] == 1:
    2611. 

  2611. 		if len(CONFS) > 1:
    2612. 

  2612. 			Error("GUI doesn't support multiple Input files.")
    2613. 

  2613. 		# remove proprierties, get just config
    2614. 

  2614. 		if CONFS: conf = CONFS[0][0]
    2615. 

  2615. 		else    : conf = {}
    2616. 

  2616. 		
    2617. 

  2617. 		# redefine Error function to raise exception instead sys.exit()
    2618. 

  2618. 		def Error(msg):
    2619. 

  2619. 			showerror('txt2tags ERROR!', msg)
    2620. 

  2620. 			raise ZeroDivisionError
    2621. 

  2621. 		Gui(conf).mainwindow()
    2622. 

  2622. 	else:
    2623. 

  2623. 		# console mode rocks forever!
    2624. 

  2624. 		convertAllFiles(CONFS)
    2625. 

  2625. 	
    2626. 

  2626. 	sys.exit(0)
    2627. 

  2627. 

  2628. # vim: ts=4
    2629. 

  2629.