PageRenderTime 93ms CodeModel.GetById 15ms RepoModel.GetById 0ms app.codeStats 1ms

/old/txt2tags-2.2.py

http://txt2tags.googlecode.com/
Python | 4517 lines | 4086 code | 160 blank | 271 comment | 157 complexity | 28f3e926696e9b98da7c6234906e4f9f 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, 2004 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. 

  20. #
    21. 

  21. #   +-------------------------------------------------------------+
    22. 

  22. #   |               IMPORTANT MESSAGES, PLEASE READ               |
    23. 

  23. #   +-------------------------------------------------------------+
    24. 

  24. #   |                                                             |
    25. 

  25. #   |                                                             |
    26. 

  26. #   |                     v1.x COMPATIBILITY                      |
    27. 

  27. #   |                     ------------------                      |
    28. 

  28. #   |                                                             |
    29. 

  29. #   |      Due the major syntax changes, the new 2.x series       |
    30. 

  30. #   |      BREAKS backwards compatibility.                        |
    31. 

  31. #   |                                                             |
    32. 

  32. #   |      Use the 't2tconv' script to upgrade your existing      |
    33. 

  33. #   |      v1.x files to conform the new v2.x syntax.             |
    34. 

  34. #   |                                                             |
    35. 

  35. #   |      Do a visual inspection on the new converted file.      |
    36. 

  36. #   |      Specially Pre & Post proc filters can break.           |
    37. 

  37. #   |      Check them!                                            |
    38. 

  38. #   |                                                             |
    39. 

  39. #   |                                                             |
    40. 

  40. #   +-------------------------------------------------------------+
    41. 

  41. #
    42. 

  42. #
    43. 

  43. ########################################################################
    44. 

  44. #
    45. 

  45. #   BORING CODE EXPLANATION AHEAD
    46. 

  46. #
    47. 

  47. # Just read if you wish to understand how the txt2tags code works
    48. 

  48. #
    49. 

  49. ########################################################################
    50. 

  50. #
    51. 

  51. # Version 2.0 was a complete rewrite for the program 'core'.
    52. 

  52. #
    53. 

  53. # Now the code that [1] parses the marked text is separated from the
    54. 

  54. # code that [2] insert the target tags.
    55. 

  55. #
    56. 

  56. #   [1] made by: def convert()
    57. 

  57. #   [2] made by: class BlockMaster
    58. 

  58. #
    59. 

  59. # The structures of the marked text are identifyed and its contents are
    60. 

  60. # extracted into a data holder (Python lists and dictionaries).
    61. 

  61. #
    62. 

  62. # When parsing the source file, the blocks (para, lists, quote, table)
    63. 

  63. # are opened with BlockMaster, right when found. Then its contents,
    64. 

  64. # which spans on several lines, are feeded into a special holder on the
    65. 

  65. # BlockMaster instance. Just when the block is closed, the target tags
    66. 

  66. # are inserted for the full block as a whole, in one pass. This way, we
    67. 

  67. # have a better control on blocks. Much better than the previous line by
    68. 

  68. # line approach.
    69. 

  69. #
    70. 

  70. # In other words, whenever inside a block, the parser *holds* the tag
    71. 

  71. # insertion process, waiting until the full block is readed. That was
    72. 

  72. # needed primary to close paragraphs for the new XHTML target, but
    73. 

  73. # proved to be a very good adding, improving many other processings.
    74. 

  74. #
    75. 

  75. # -------------------------------------------------------------------
    76. 

  76. #
    77. 

  77. # There is also a brand new code for the Configuration schema, 100%
    78. 

  78. # rewritten. There are new classes, all self documented: CommandLine,
    79. 

  79. # SourceDocument, ConfigMaster and ConfigLines. In short, a new RAW
    80. 

  80. # Config format was created, and all kind of configuration is first
    81. 

  81. # converted to this format, and then a generic method parses it.
    82. 

  82. #
    83. 

  83. # The init processing was changed also, and now the functions which
    84. 

  84. # gets informations about the input files are: get_infiles_config(),
    85. 

  85. #  process_source_file() and convert_this_files()
    86. 

  86. #
    87. 

  87. # Other parts are untouched, and remains the same as in v1.7, as the
    88. 

  88. # marks regexes, target Headers and target Tags&Rules.
    89. 

  89. #
    90. 

  90. ########################################################################
    91. 

  91. 

  92. # Now I think the code is nice, easier to read and understand
    93. 

  93. 

  94. #XXX Python coding warning
    95. 

  95. # Avoid common mistakes:
    96. 

  96. # - do NOT use newlist=list instead newlist=list[:]
    97. 

  97. # - do NOT use newdic=dic   instead newdic=dic.copy()
    98. 

  98. # - do NOT use dic[key]     instead dic.get(key)
    99. 

  99. # - do NOT use del dic[key] without has_key() before
    100. 

  100. 

  101. #XXX Smart Image Align don't work if the image is a link
    102. 

  102. # Can't fix that because the image is expanded together with the
    103. 

  103. # link, at the linkbank filling moment. Only the image is passed
    104. 

  104. # to parse_images(), not the full line, so it is always 'middle'.
    105. 

  105. 

  106. #XXX Paragraph separation not valid inside Quote
    107. 

  107. # Quote will not have <p></p> inside, instead will close and open
    108. 

  108. # again the <blockquote>. This really sux in CSS, when defining a
    109. 

  109. # diferent background color. Still don't know how to fix it.
    110. 

    111. 

  111. #XXX TODO (maybe)
    112. 

  112. # New mark or macro which expands to an anchor full title.
    113. 

  113. # It is necessary to parse the full document in this order:
    114. 

  114. #  DONE  1st scan: HEAD: get all settings, including %!includeconf
    115. 

  115. #  DONE  2nd scan: BODY: expand includes & apply %!preproc
    116. 

  116. #        3rd scan: BODY: read titles and compose TOC info
    117. 

  117. #        4th scan: BODY: full parsing, expanding [#anchor] 1st
    118. 

  118. # Steps 2 and 3 can be made together, with no tag adding.
    119. 

  119. # Two complete body scans will be *slow*, don't know if it worths.
    120. 

  120. # One solution may be add the titles as postproc rules
    121. 

  121. 

  122. 

  123. ##############################################################################
    124. 

  124. 

  125. # User config (1=ON, 0=OFF)
    126. 

  126. 

  127. USE_I18N    = 1   # use gettext for i18ned messages?        (default is 1)
    128. 

  128. COLOR_DEBUG = 1   # show debug messages in colors?          (default is 1)
    129. 

  129. BG_LIGHT    = 0   # your terminal background color is light (default is 0)
    130. 

  130. HTML_LOWER  = 0   # use lowercased HTML tags instead upper? (default is 0)
    131. 

  131. 

  132. ##############################################################################
    133. 

  133. 

  134. 

  135. # these are all the core Python modules used by txt2tags (KISS!)
    136. 

  136. import re, string, os, sys, time, getopt
    137. 

  137. 

  138. # program information
    139. 

  139. my_url = 'http://txt2tags.sf.net'
    140. 

  140. my_name = 'txt2tags'
    141. 

  141. my_email = 'verde@aurelio.net'
    142. 

  142. my_version = '2.2'
    143. 

  143. 

  144. # i18n - just use if available
    145. 

  145. if USE_I18N:
    146. 

  146. 	try:
    147. 

  147. 		import gettext
    148. 

  148. 		# if your locale dir is different, change it here
    149. 

  149. 		cat = gettext.Catalog('txt2tags',localedir='/usr/share/locale/')
    150. 

  150. 		_ = cat.gettext
    151. 

  151. 	except:
    152. 

  152. 		_ = lambda x:x
    153. 

  153. else:
    154. 

  154. 	_ = lambda x:x
    155. 

  155. 

  156. # FLAGS   : the conversion related flags  , may be used in %!options
    157. 

  157. # OPTIONS : the conversion related options, may be used in %!options
    158. 

  158. # ACTIONS : the other behaviour modifiers, valid on command line only
    159. 

  159. # MACROS  : the valid macros with their default values for formatting
    160. 

  160. # SETTINGS: global miscelaneous settings, valid on RC file only
    161. 

  161. # CONFIG_KEYWORDS: the valid %!key:val keywords
    162. 

  162. #
    163. 

  163. # FLAGS and OPTIONS are configs that affect the converted document.
    164. 

  164. # They usually have also a --no-<option> to turn them OFF.
    165. 

  165. # ACTIONS are needed because when doing multiple input files, strange
    166. 

  166. # behaviour would be found, as use command line interface for the
    167. 

  167. # first file and gui for the second. There is no --no-<action>.
    168. 

  168. # --version and --help inside %!options are also odd
    169. 

  169. #
    170. 

  170. TARGETS  = ['html', 'xhtml', 'sgml', 'tex', 'lout', 'man', 'mgp',
    171. 

  171.             'moin', 'pm6'  , 'txt']
    172. 

  172. FLAGS    = {'headers'    :1 , 'enum-title' :0 , 'mask-email' :0 ,
    173. 

  173.             'toc-only'   :0 , 'toc'        :0 , 'rc'         :1 ,
    174. 

  174.             'css-sugar'  :0 , 'css-suggar' :0 , 'css-inside' :0 ,
    175. 

  175.             'quiet'      :0 }
    176. 

  176. OPTIONS  = {'target'     :'', 'toc-level'  :3 , 'style'      :'',
    177. 

  177.             'infile'     :'', 'outfile'    :'', 'encoding'   :'',
    178. 

  178.             'split'      :0 , 'lang'       :''}
    179. 

  179. ACTIONS  = {'help'       :0 , 'version'    :0 , 'gui'        :0 ,
    180. 

  180.             'verbose'    :0 , 'debug'      :0 , 'dump-config':0 }
    181. 

  181. MACROS   = {'date' : '%Y%m%d',  'infile': '%f',
    182. 

  182.             'mtime': '%Y%m%d', 'outfile': '%f'}
    183. 

  183. SETTINGS = {}         # for future use
    184. 

  184. CONFIG_KEYWORDS = [
    185. 

  185.             'target', 'encoding', 'style', 'options', 'preproc','postproc',
    186. 

  186.             'guicolors']
    187. 

  187. TARGET_NAMES = {
    188. 

  188.   'html' : _('HTML page'),
    189. 

  189.   'xhtml': _('XHTML page'),
    190. 

  190.   'sgml' : _('SGML document'),
    191. 

  191.   'tex'  : _('LaTeX document'),
    192. 

  192.   'lout' : _('Lout document'),
    193. 

  193.   'man'  : _('UNIX Manual page'),
    194. 

  194.   'mgp'  : _('Magic Point presentation'),
    195. 

  195.   'moin' : _('MoinMoin page'),
    196. 

  196.   'pm6'  : _('PageMaker 6.0 document'),
    197. 

  197.   'txt'  : _('Plain Text'),
    198. 

  198. }
    199. 

  199. 

  200. DEBUG = 0     # do not edit here, please use --debug
    201. 

  201. VERBOSE = 0   # do not edit here, please use -v, -vv or -vvv
    202. 

  202. QUIET = 0     # do not edit here, please use --quiet
    203. 

  203. GUI = 0       # do not edit here, please use --gui
    204. 

  204. AUTOTOC = 1   # do not edit here, please use --no-toc or %%toc
    205. 

  205. 

  206. RC_RAW = []
    207. 

  207. CMDLINE_RAW = []
    208. 

  208. CONF = {}
    209. 

  209. BLOCK = None
    210. 

  210. regex = {}
    211. 

  211. TAGS = {}
    212. 

  212. rules = {}
    213. 

  213. 

  214. lang = 'english'
    215. 

  215. TARGET = ''
    216. 

  216. 

  217. STDIN = STDOUT = '-'
    218. 

  218. ESCCHAR   = '\x00'
    219. 

  219. SEPARATOR = '\x01'
    220. 

  220. LISTNAMES = {'-':'list', '+':'numlist', ':':'deflist'}
    221. 

  221. LINEBREAK = {'default':'\n', 'win':'\r\n', 'mac':'\r'}
    222. 

  222. 

  223. # plataform specific settings
    224. 

  224. LB = LINEBREAK.get(sys.platform[:3]) or LINEBREAK['default']
    225. 

  225. 

  226. # identify a development version
    227. 

  227. #dev_suffix = '-dev'+time.strftime('%m%d',time.localtime(time.time()))
    228. 

  228. #my_version = my_version + dev_suffix
    229. 

  229. 

  230. VERSIONSTR = _("%s version %s <%s>")%(my_name,my_version,my_url)
    231. 

  231. 

  232. USAGE = string.join([
    233. 

  233. '',
    234. 

  234. _("Usage: %s [OPTIONS] [infile.t2t ...]") % my_name,
    235. 

  235. '',
    236. 

  236. _("  -t, --target=TYPE   set target document type. currently supported:"),
    237. 

  237. '                      %s' % re.sub(r"[]'[]",'',repr(TARGETS)),
    238. 

  238. _("  -i, --infile=FILE   set FILE as the input file name ('-' for STDIN)"),
    239. 

  239. _("  -o, --outfile=FILE  set FILE as the output file name ('-' for STDOUT)"),
    240. 

  240. _("  -n, --enum-title    enumerate all title lines as 1, 1.1, 1.1.1, etc"),
    241. 

  241. _("  -H, --no-headers    suppress header, title and footer contents"),
    242. 

  242. _("      --headers       show header, title and footer contents (default ON)"),
    243. 

  243. _("      --encoding=ENC  set target file encoding (utf-8, iso-8859-1, etc)"),
    244. 

  244. _("      --style=FILE    use FILE as the document style (like HTML CSS)"),
    245. 

  245. _("      --css-sugar     insert CSS-friendly tags for HTML and XHTML targets"),
    246. 

  246. _("      --css-inside    insert CSS file contents inside HTML/XHTML headers"),
    247. 

  247. _("      --mask-email    hide email from spam robots. x@y.z turns <x (a) y z>"),
    248. 

  248. _("      --toc           add TOC (Table of Contents) to target document"),
    249. 

  249. _("      --toc-only      print document TOC and exit"),
    250. 

  250. _("      --toc-level=N   set maximum TOC level (depth) to N"),
    251. 

  251. _("      --rc            read user config file ~/.txt2tagsrc (default ON)"),
    252. 

  252. _("      --gui           invoke Graphical Tk Interface"),
    253. 

  253. _("  -q, --quiet         quiet mode, suppress all output (except errors)"),
    254. 

  254. _("  -v, --verbose       print informative messages during conversion"),
    255. 

  255. _("  -h, --help          print this help information and exit"),
    256. 

  256. _("  -V, --version       print program version and exit"),
    257. 

  257. _("      --dump-config   print all the config found and exit"),
    258. 

  258. '',
    259. 

  259. _("Turn OFF options:"),
    260. 

  260. "     --no-outfile, --no-infile, --no-style, --no-encoding, --no-headers",
    261. 

  261. "     --no-toc, --no-toc-only, --no-mask-email, --no-enum-title, --no-rc",
    262. 

  262. "     --no-css-sugar, --no-css-inside, --no-quiet",
    263. 

  263. '',
    264. 

  264. _("Example:\n     %s -t html --toc myfile.t2t") % my_name,
    265. 

  265. '',
    266. 

  266. _("By default, converted output is saved to 'infile.<target>'."),
    267. 

  267. _("Use --outfile to force an output file name."),
    268. 

  268. _("If  input file is '-', reads from STDIN."),
    269. 

  269. _("If output file is '-', dumps output to STDOUT."),
    270. 

  270. ''
    271. 

  271. ], '\n')
    272. 

  272. 

  273. 

  274. ##############################################################################
    275. 

  275. 

  276. 

  277. # here is all the target's templates
    278. 

  278. # you may edit them to fit your needs
    279. 

  279. #  - the %(HEADERn)s strings represent the Header lines
    280. 

  280. #  - the %(STYLE)s string is changed by --style contents
    281. 

  281. #  - the %(ENCODING)s string is changed by --encoding contents
    282. 

  282. #  - if any of the above is empty, the full line is removed
    283. 

  283. #  - use %% to represent a literal %
    284. 

  284. #
    285. 

  285. HEADER_TEMPLATE = {
    286. 

  286.   'txt': """\
    287. 

  287. %(HEADER1)s
    288. 

  288. %(HEADER2)s
    289. 

  289. %(HEADER3)s
    290. 

  290. """,
    291. 

    292. 

  292.   'sgml': """\
    293. 

  293. <!doctype linuxdoc system>
    294. 

  294. <article>
    295. 

  295. <title>%(HEADER1)s
    296. 

  296. <author>%(HEADER2)s
    297. 

  297. <date>%(HEADER3)s
    298. 

  298. """,
    299. 

    300. 

  300.   'html': """\
    301. 

  301. <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
    302. 

  302. <HTML>
    303. 

  303. <HEAD>
    304. 

  304. <META NAME="generator" CONTENT="http://txt2tags.sf.net">
    305. 

  305. <META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=%(ENCODING)s">
    306. 

  306. <LINK REL="stylesheet" TYPE="text/css" HREF="%(STYLE)s">
    307. 

  307. <TITLE>%(HEADER1)s</TITLE>
    308. 

  308. </HEAD><BODY BGCOLOR="white" TEXT="black">
    309. 

  309. <P ALIGN="center"><CENTER><H1>%(HEADER1)s</H1>
    310. 

  310. <FONT SIZE="4">
    311. 

  311. <I>%(HEADER2)s</I><BR>
    312. 

  312. %(HEADER3)s
    313. 

  313. </FONT></CENTER>
    314. 

  314. """,
    315. 

    316. 

  316.   'htmlcss': """\
    317. 

  317. <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
    318. 

  318. <HTML>
    319. 

  319. <HEAD>
    320. 

  320. <META NAME="generator" CONTENT="http://txt2tags.sf.net">
    321. 

  321. <META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=%(ENCODING)s">
    322. 

  322. <LINK REL="stylesheet" TYPE="text/css" HREF="%(STYLE)s">
    323. 

  323. <TITLE>%(HEADER1)s</TITLE>
    324. 

  324. </HEAD>
    325. 

  325. <BODY>
    326. 

  326. 

  327. <DIV CLASS="header" ID="header">
    328. 

  328. <H1>%(HEADER1)s</H1>
    329. 

  329. <H2>%(HEADER2)s</H2>
    330. 

  330. <H3>%(HEADER3)s</H3>
    331. 

  331. </DIV>
    332. 

  332. """,
    333. 

    334. 

  334.   'xhtml': """\
    335. 

  335. <?xml version="1.0"
    336. 

  336.       encoding="%(ENCODING)s"
    337. 

  337. ?>
    338. 

  338. <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"\
    339. 

  339.  "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
    340. 

  340. <html xmlns="http://www.w3.org/1999/xhtml">
    341. 

  341. <head>
    342. 

  342. <title>%(HEADER1)s</title>
    343. 

  343. <meta name="generator" content="http://txt2tags.sf.net" />
    344. 

  344. <link rel="stylesheet" type="text/css" href="%(STYLE)s" />
    345. 

  345. </head>
    346. 

  346. <body bgcolor="white" text="black">
    347. 

  347. <div align="center">
    348. 

  348. <h1>%(HEADER1)s</h1>
    349. 

  349. <h2>%(HEADER2)s</h2>
    350. 

  350. <h3>%(HEADER3)s</h3>
    351. 

  351. </div>
    352. 

  352. """,
    353. 

    354. 

  354.   'xhtmlcss': """\
    355. 

  355. <?xml version="1.0"?>
    356. 

  356. <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"\
    357. 

  357.  "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
    358. 

  358. <html xmlns="http://www.w3.org/1999/xhtml">
    359. 

  359. <head>
    360. 

  360. <title>%(HEADER1)s</title>
    361. 

  361. <meta name="generator" content="http://txt2tags.sf.net" />
    362. 

  362. <meta http-equiv="Content-Type" content="text/html; charset=%(ENCODING)s" />
    363. 

  363. <link rel="stylesheet" type="text/css" href="%(STYLE)s" />
    364. 

  364. </head>
    365. 

  365. <body>
    366. 

  366. 

  367. <div class="header" id="header">
    368. 

  368. <h1>%(HEADER1)s</h1>
    369. 

  369. <h2>%(HEADER2)s</h2>
    370. 

  370. <h3>%(HEADER3)s</h3>
    371. 

  371. </div>
    372. 

  372. """,
    373. 

    374. 

  374.   'man': """\
    375. 

  375. .TH "%(HEADER1)s" 1 "%(HEADER3)s" "%(HEADER2)s"
    376. 

  376. """,
    377. 

    378. 

  378. # TODO style to <HR>
    379. 

  379.   'pm6': """\
    380. 

  380. <PMTags1.0 win><C-COLORTABLE ("Preto" 1 0 0 0)
    381. 

  381. ><@Normal=
    382. 

  382.   <FONT "Times New Roman"><CCOLOR "Preto"><SIZE 11>
    383. 

  383.   <HORIZONTAL 100><LETTERSPACE 0><CTRACK 127><CSSIZE 70><C+SIZE 58.3>
    384. 

  384.   <C-POSITION 33.3><C+POSITION 33.3><P><CBASELINE 0><CNOBREAK 0><CLEADING -0.05>
    385. 

  385.   <GGRID 0><GLEFT 7.2><GRIGHT 0><GFIRST 0><G+BEFORE 7.2><G+AFTER 0>
    386. 

  386.   <GALIGNMENT "justify"><GMETHOD "proportional"><G& "ENGLISH">
    387. 

  387.   <GPAIRS 12><G%% 120><GKNEXT 0><GKWIDOW 0><GKORPHAN 0><GTABS $>
    388. 

  388.   <GHYPHENATION 2 34 0><GWORDSPACE 75 100 150><GSPACE -5 0 25>
    389. 

  389. ><@Bullet=<@-PARENT "Normal"><FONT "Abadi MT Condensed Light">
    390. 

  390.   <GLEFT 14.4><G+BEFORE 2.15><G%% 110><GTABS(25.2 l "")>
    391. 

  391. ><@PreFormat=<@-PARENT "Normal"><FONT "Lucida Console"><SIZE 8><CTRACK 0>
    392. 

  392.   <GLEFT 0><G+BEFORE 0><GALIGNMENT "left"><GWORDSPACE 100 100 100><GSPACE 0 0 0>
    393. 

  393. ><@Title1=<@-PARENT "Normal"><FONT "Arial"><SIZE 14><B>
    394. 

  394.   <GCONTENTS><GLEFT 0><G+BEFORE 0><GALIGNMENT "left">
    395. 

  395. ><@Title2=<@-PARENT "Title1"><SIZE 12><G+BEFORE 3.6>
    396. 

  396. ><@Title3=<@-PARENT "Title1"><SIZE 10><GLEFT 7.2><G+BEFORE 7.2>
    397. 

  397. ><@Title4=<@-PARENT "Title3">
    398. 

  398. ><@Title5=<@-PARENT "Title3">
    399. 

  399. ><@Quote=<@-PARENT "Normal"><SIZE 10><I>>
    400. 

  400. 

  401. %(HEADER1)s
    402. 

  402. %(HEADER2)s
    403. 

  403. %(HEADER3)s
    404. 

  404. """,
    405. 

    406. 

  406.   'mgp': """\
    407. 

  407. #!/usr/X11R6/bin/mgp -t 90
    408. 

  408. %%deffont "normal"    xfont  "utopia-medium-r", charset "iso8859-1"
    409. 

  409. %%deffont "normal-i"  xfont  "utopia-medium-i", charset "iso8859-1"
    410. 

  410. %%deffont "normal-b"  xfont  "utopia-bold-r"  , charset "iso8859-1"
    411. 

  411. %%deffont "normal-bi" xfont  "utopia-bold-i"  , charset "iso8859-1"
    412. 

  412. %%deffont "mono"      xfont "courier-medium-r", charset "iso8859-1"
    413. 

  413. %%default 1 size 5
    414. 

  414. %%default 2 size 8, fore "yellow", font "normal-b", center
    415. 

  415. %%default 3 size 5, fore "white",  font "normal", left, prefix "  "
    416. 

  416. %%tab 1 size 4, vgap 30, prefix "     ", icon arc "red" 40, leftfill
    417. 

  417. %%tab 2 prefix "            ", icon arc "orange" 40, leftfill
    418. 

  418. %%tab 3 prefix "                   ", icon arc "brown" 40, leftfill
    419. 

  419. %%tab 4 prefix "                          ", icon arc "darkmagenta" 40, leftfill
    420. 

  420. %%tab 5 prefix "                                ", icon arc "magenta" 40, leftfill
    421. 

  421. %%%%------------------------- end of headers -----------------------------
    422. 

  422. %%page
    423. 

  423. 

  424. 

  425. 

  426. 

  427. 

  428. %%size 10, center, fore "yellow"
    429. 

  429. %(HEADER1)s
    430. 

  430. 

  431. %%font "normal-i", size 6, fore "white", center
    432. 

  432. %(HEADER2)s
    433. 

  433. 

  434. %%font "mono", size 7, center
    435. 

  435. %(HEADER3)s
    436. 

  436. """,
    437. 

    438. 

  438.   'moin': """\
    439. 

  439. '''%(HEADER1)s'''
    440. 

  440. 

  441. ''%(HEADER2)s''
    442. 

  442. 

  443. %(HEADER3)s
    444. 

  444. """,
    445. 

    446. 

  446.   'tex': \
    447. 

  447. r"""\documentclass[11pt,a4paper]{article}
    448. 

  448. \usepackage{amsfonts,graphicx}
    449. 

  449. \usepackage[pdfstartview=FitV,urlcolor=blue,colorlinks=true,bookmarks=true]{hyperref}
    450. 

  450. \usepackage[%(ENCODING)s]{inputenc}  %% char encoding
    451. 

  451. \usepackage{%(STYLE)s}  %% user defined package
    452. 

  452. \pagestyle{plain}   %% do page numbering ('empty' turns off)
    453. 

  453. \frenchspacing      %% no aditional spaces after periods
    454. 

  454. \setlength{\parskip}{8pt}\parindent=0pt  %% no paragraph indentation
    455. 

  455. 

  456. \title{%(HEADER1)s}
    457. 

  457. \author{%(HEADER2)s}
    458. 

  458. \begin{document}
    459. 

  459. \date{%(HEADER3)s}
    460. 

  460. \maketitle
    461. 

  461. \clearpage
    462. 

  462. """,
    463. 

    464. 

  464.   'lout': """\
    465. 

  465. @SysInclude { doc }
    466. 

  466. @Document
    467. 

  467.   @InitialFont { Times Base 12p }	# Times, Courier, Helvetica, ...
    468. 

  468.   @PageOrientation { Portrait }		# Portrait, Landscape
    469. 

  469.   @ColumnNumber { 1 }			# Number of columns (2, 3, ...)
    470. 

  470.   @PageHeaders { Simple }		# None, Simple, Titles, NoTitles
    471. 

  471.   @InitialLanguage { English }		# German, French, Portuguese, ...
    472. 

  472.   @OptimizePages { Yes }                # Yes/No smart page break feature
    473. 

  473. //
    474. 

  474. @Text @Begin
    475. 

  475. @Display @Heading { %(HEADER1)s }
    476. 

  476. @Display @I { %(HEADER2)s }
    477. 

  477. @Display { %(HEADER3)s }
    478. 

  478. #@NP                                    # Break page after Headers
    479. 

  479. """
    480. 

  480. # @SysInclude { tbl }			# Tables support
    481. 

  481. # setup: @MakeContents { Yes }          # show TOC
    482. 

  482. # setup: @SectionGap                    # break page at each section
    483. 

  483. }
    484. 

  484. 

  485. 

  486. ##############################################################################
    487. 

  487. 

  488. 

  489. def getTags(config):
    490. 

  490. 	"Returns all the known tags for the specified target"
    491. 

  491. 	
    492. 

  492. 	keys = [
    493. 

  493. 	'paragraphOpen','paragraphClose',
    494. 

  494. 	'title1','title2','title3','title4','title5',
    495. 

  495. 	'title1Open','title1Close','title2Open','title2Close',
    496. 

  496. 	'blocktitle1Open','title1Close','title2Open','title2Close',
    497. 

  497. 	'title3Open','title3Close','title4Open','title4Close',
    498. 

  498. 	'title5Open','title5Close',
    499. 

  499. 	'numtitle1','numtitle2','numtitle3','numtitle4','numtitle5',
    500. 

  500. 	'blockVerbOpen','blockVerbClose',
    501. 

  501. 	'blockQuoteOpen','blockQuoteClose','blockQuoteLine',
    502. 

  502. 	'fontMonoOpen','fontMonoClose',
    503. 

  503. 	'fontBoldOpen','fontBoldClose',
    504. 

  504. 	'fontItalicOpen','fontItalicClose',
    505. 

  505. 	'fontUnderlineOpen','fontUnderlineClose',
    506. 

  506. 	'listOpen','listClose',
    507. 

  507. 	'listItemOpen','listItemClose','listItemLine',
    508. 

  508. 	'numlistOpen','numlistClose',
    509. 

  509. 	'numlistItemOpen','numlistItemClose','numlistItemLine',
    510. 

  510. 	'deflistOpen','deflistClose',
    511. 

  511. 	'deflistItem1Open','deflistItem1Close',
    512. 

  512. 	'deflistItem2Open','deflistItem2Close',
    513. 

  513. 	'bar1','bar2',
    514. 

  514. 	'url','urlMark','email','emailMark',
    515. 

  515. 	'img','imgAlignLeft','imgAlignRight','imgAlignCenter',
    516. 

  516. 	'tableOpen','tableClose',
    517. 

  517. 	'tableRowOpen','tableRowClose','tableRowSep',
    518. 

  518. 	'tableCellOpen','tableCellClose','tableCellSep',
    519. 

  519. 	'tableTitleCellOpen','tableTitleCellClose','tableTitleCellSep',
    520. 

  520. 	'tableTitleRowOpen','tableTitleRowClose',
    521. 

  521. 	'tableBorder', 'tableAlignLeft', 'tableAlignCenter',
    522. 

  522. 	'tableCellAlignLeft','tableCellAlignRight','tableCellAlignCenter',
    523. 

  523. 	'tableColAlignLeft','tableColAlignRight','tableColAlignCenter',
    524. 

  524. 	'tableColAlignSep',
    525. 

  525. 	'anchor','comment','pageBreak',
    526. 

  526. 	'TOC','tocOpen','tocClose',
    527. 

  527. 	'cssOpen', 'cssClose',
    528. 

  528. 	'bodyOpen','bodyClose',
    529. 

  529. 	'EOD'
    530. 

  530. 	]
    531. 

  531. 	
    532. 

  532. 	# TIP: \a represents the current text on the mark
    533. 

  533. 	# TIP: ~A~, ~B~ and ~C~ are expanded to other tags parts
    534. 

  534. 	
    535. 

  535. 	alltags = {
    536. 

  536. 	
    537. 

  537. 	'txt': {
    538. 

  538. 	   'title1'              : '  \a'      ,
    539. 

  539. 	   'title2'              : '\t\a'      ,
    540. 

  540. 	   'title3'              : '\t\t\a'    ,
    541. 

  541. 	   'title4'              : '\t\t\t\a'  ,
    542. 

  542. 	   'title5'              : '\t\t\t\t\a',
    543. 

  543. 	   'blockQuoteLine'      : '\t'        ,
    544. 

  544. 	   'listItemOpen'        : '- '        ,
    545. 

  545. 	   'numlistItemOpen'     : '\a. '      ,
    546. 

  546. 	   'bar1'                : '\a'        ,
    547. 

  547. 	   'url'                 : '\a'        ,
    548. 

  548. 	   'urlMark'             : '\a (\a)'   ,
    549. 

  549. 	   'email'               : '\a'        ,
    550. 

  550. 	   'emailMark'           : '\a (\a)'   ,
    551. 

  551. 	   'img'                 : '[\a]'      ,
    552. 

  552. 	},
    553. 

  553. 	
    554. 

  554. 	'html': {
    555. 

  555. 	   'paragraphOpen'       : '<P>'            ,
    556. 

  556. 	   'paragraphClose'      : '</P>'           ,
    557. 

  557. 	   'title1'              : '~A~<H1>\a</H1>' ,
    558. 

  558. 	   'title2'              : '~A~<H2>\a</H2>' ,
    559. 

  559. 	   'title3'              : '~A~<H3>\a</H3>' ,
    560. 

  560. 	   'title4'              : '~A~<H4>\a</H4>' ,
    561. 

  561. 	   'title5'              : '~A~<H5>\a</H5>' ,
    562. 

  562. 	   'blockVerbOpen'       : '<PRE>'          ,
    563. 

  563. 	   'blockVerbClose'      : '</PRE>'         ,
    564. 

  564. 	   'blockQuoteOpen'      : '<BLOCKQUOTE>'   ,
    565. 

  565. 	   'blockQuoteClose'     : '</BLOCKQUOTE>'  ,
    566. 

  566. 	   'fontMonoOpen'        : '<CODE>'         ,
    567. 

  567. 	   'fontMonoClose'       : '</CODE>'        ,
    568. 

  568. 	   'fontBoldOpen'        : '<B>'            ,
    569. 

  569. 	   'fontBoldClose'       : '</B>'           ,
    570. 

  570. 	   'fontItalicOpen'      : '<I>'            ,
    571. 

  571. 	   'fontItalicClose'     : '</I>'           ,
    572. 

  572. 	   'fontUnderlineOpen'   : '<U>'            ,
    573. 

  573. 	   'fontUnderlineClose'  : '</U>'           ,
    574. 

  574. 	   'listOpen'            : '<UL>'           ,
    575. 

  575. 	   'listClose'           : '</UL>'          ,
    576. 

  576. 	   'listItemOpen'        : '<LI>'           ,
    577. 

  577. 	   'numlistOpen'         : '<OL>'           ,
    578. 

  578. 	   'numlistClose'        : '</OL>'          ,
    579. 

  579. 	   'numlistItemOpen'     : '<LI>'           ,
    580. 

  580. 	   'deflistOpen'         : '<DL>'           ,
    581. 

  581. 	   'deflistClose'        : '</DL>'          ,
    582. 

  582. 	   'deflistItem1Open'    : '<DT>'           ,
    583. 

  583. 	   'deflistItem1Close'   : '</DT>'          ,
    584. 

  584. 	   'deflistItem2Open'    : '<DD>'           ,
    585. 

  585. 	   'bar1'                : '<HR NOSHADE SIZE=1>'        ,
    586. 

  586. 	   'bar2'                : '<HR NOSHADE SIZE=5>'        ,
    587. 

  587. 	   'url'                 : '<A HREF="\a">\a</A>'        ,
    588. 

  588. 	   'urlMark'             : '<A HREF="\a">\a</A>'        ,
    589. 

  589. 	   'email'               : '<A HREF="mailto:\a">\a</A>' ,
    590. 

  590. 	   'emailMark'           : '<A HREF="mailto:\a">\a</A>' ,
    591. 

  591. 	   'img'                 : '<IMG~A~ SRC="\a" BORDER="0" ALT="">',
    592. 

  592. 	   'imgAlignLeft'        : ' ALIGN="left"'  ,
    593. 

  593. 	   'imgAlignCenter'      : ' ALIGN="middle"',
    594. 

  594. 	   'imgAlignRight'       : ' ALIGN="right"' ,
    595. 

  595. 	   'tableOpen'           : '<TABLE~A~ CELLPADDING="4"~B~>',
    596. 

  596. 	   'tableClose'          : '</TABLE>'       ,
    597. 

  597. 	   'tableRowOpen'        : '<TR>'           ,
    598. 

  598. 	   'tableRowClose'       : '</TR>'          ,
    599. 

  599. 	   'tableCellOpen'       : '<TD\a>'         ,
    600. 

  600. 	   'tableCellClose'      : '</TD>'          ,
    601. 

  601. 	   'tableTitleCellOpen'  : '<TH>'           ,
    602. 

  602. 	   'tableTitleCellClose' : '</TH>'          ,
    603. 

  603. 	   'tableBorder'         : ' BORDER="1"'    ,
    604. 

  604. 	   'tableAlignCenter'    : ' ALIGN="center"',
    605. 

  605. 	   'tableCellAlignRight' : ' ALIGN="right"' ,
    606. 

  606. 	   'tableCellAlignCenter': ' ALIGN="center"',
    607. 

  607. 	   'anchor'              : '<A NAME="\a"></A>\n',
    608. 

  608. 	   'cssOpen'             : '<STYLE TYPE="text/css">',
    609. 

  609. 	   'cssClose'            : '</STYLE>'       ,
    610. 

  610. 	   'comment'             : '<!-- \a -->'    ,
    611. 

  611. 	   'EOD'                 : '</BODY></HTML>'
    612. 

  612. 	},
    613. 

  613. 	
    614. 

  614. 	#TIP xhtml inherits all HTML definitions (lowercased)
    615. 

  615. 	#TIP http://www.w3.org/TR/xhtml1/#guidelines
    616. 

  616. 	#TIP http://www.htmlref.com/samples/Chapt17/17_08.htm
    617. 

  617. 	'xhtml': {
    618. 

  618. 	   'listItemClose'       : '</li>'          ,
    619. 

  619. 	   'numlistItemClose'    : '</li>'          ,
    620. 

  620. 	   'deflistItem2Close'   : '</dd>'          ,
    621. 

  621. 	   'bar1'                : '<hr class="light" />',
    622. 

  622. 	   'bar2'                : '<hr class="heavy" />',
    623. 

  623. 	   'anchor'              : '<a id="\a" name="\a"></a>\n',
    624. 

  624. 	   'img'                 : '<img~A~ src="\a" border="0" alt=""/>',
    625. 

  625. 	},
    626. 

  626. 	
    627. 

  627. 	'sgml': {
    628. 

  628. 	   'paragraphOpen'       : '<p>'                ,
    629. 

  629. 	   'title1'              : '<sect>\a~A~<p>'     ,
    630. 

  630. 	   'title2'              : '<sect1>\a~A~<p>'    ,
    631. 

  631. 	   'title3'              : '<sect2>\a~A~<p>'    ,
    632. 

  632. 	   'title4'              : '<sect3>\a~A~<p>'    ,
    633. 

  633. 	   'title5'              : '<sect4>\a~A~<p>'    ,
    634. 

  634. 	   'blockVerbOpen'       : '<tscreen><verb>'    ,
    635. 

  635. 	   'blockVerbClose'      : '</verb></tscreen>'  ,
    636. 

  636. 	   'blockQuoteOpen'      : '<quote>'            ,
    637. 

  637. 	   'blockQuoteClose'     : '</quote>'           ,
    638. 

  638. 	   'fontMonoOpen'        : '<tt>'               ,
    639. 

  639. 	   'fontMonoClose'       : '</tt>'              ,
    640. 

  640. 	   'fontBoldOpen'        : '<bf>'               ,
    641. 

  641. 	   'fontBoldClose'       : '</bf>'              ,
    642. 

  642. 	   'fontItalicOpen'      : '<em>'               ,
    643. 

  643. 	   'fontItalicClose'     : '</em>'              ,
    644. 

  644. 	   'fontUnderlineOpen'   : '<bf><em>'           ,
    645. 

  645. 	   'fontUnderlineClose'  : '</em></bf>'         ,
    646. 

  646. 	   'listOpen'            : '<itemize>'          ,
    647. 

  647. 	   'listClose'           : '</itemize>'         ,
    648. 

  648. 	   'listItemOpen'        : '<item>'             ,
    649. 

  649. 	   'numlistOpen'         : '<enum>'             ,
    650. 

  650. 	   'numlistClose'        : '</enum>'            ,
    651. 

  651. 	   'numlistItemOpen'     : '<item>'             ,
    652. 

  652. 	   'deflistOpen'         : '<descrip>'          ,
    653. 

  653. 	   'deflistClose'        : '</descrip>'         ,
    654. 

  654. 	   'deflistItem1Open'    : '<tag>'              ,
    655. 

  655. 	   'deflistItem1Close'   : '</tag>'             ,
    656. 

  656. 	   'bar1'                : '<!-- \a -->'        ,
    657. 

  657. 	   'url'                 : '<htmlurl url="\a" name="\a">'        ,
    658. 

  658. 	   'urlMark'             : '<htmlurl url="\a" name="\a">'        ,
    659. 

  659. 	   'email'               : '<htmlurl url="mailto:\a" name="\a">' ,
    660. 

  660. 	   'emailMark'           : '<htmlurl url="mailto:\a" name="\a">' ,
    661. 

  661. 	   'img'                 : '<figure><ph vspace=""><img src="\a">'+\
    662. 

  662. 	                           '</figure>'                           ,
    663. 

  663. 	   'tableOpen'           : '<table><tabular ca="~C~">'           ,
    664. 

  664. 	   'tableClose'          : '</tabular></table>' ,
    665. 

  665. 	   'tableRowSep'         : '<rowsep>'           ,
    666. 

  666. 	   'tableCellSep'        : '<colsep>'           ,
    667. 

  667. 	   'tableColAlignLeft'   : 'l'                  ,
    668. 

  668. 	   'tableColAlignRight'  : 'r'                  ,
    669. 

  669. 	   'tableColAlignCenter' : 'c'                  ,
    670. 

  670. 	   'comment'             : '<!-- \a -->'        ,
    671. 

  671. 	   'anchor'              : '<label id="\a">'    ,
    672. 

  672. 	   'TOC'                 : '<toc>'              ,
    673. 

  673. 	   'EOD'                 : '</article>'
    674. 

  674. 	},
    675. 

  675. 	
    676. 

  676. 	'tex': {
    677. 

  677. 	   'title1'              : '\n\section*{\a}'     ,
    678. 

  678. 	   'title2'              : '\\subsection*{\a}'   ,
    679. 

  679. 	   'title3'              : '\\subsubsection*{\a}',
    680. 

  680. 	   # title 4/5: DIRTY: para+BF+\\+\n
    681. 

  681. 	   'title4'              : '\\paragraph{}\\textbf{\a}\\\\\n',
    682. 

  682. 	   'title5'              : '\\paragraph{}\\textbf{\a}\\\\\n',
    683. 

  683. 	   'numtitle1'           : '\n\section{\a}'      ,
    684. 

  684. 	   'numtitle2'           : '\\subsection{\a}'    ,
    685. 

  685. 	   'numtitle3'           : '\\subsubsection{\a}' ,
    686. 

  686. 	   'blockVerbOpen'       : '\\begin{verbatim}'   ,
    687. 

  687. 	   'blockVerbClose'      : '\\end{verbatim}'     ,
    688. 

  688. 	   'blockQuoteOpen'      : '\\begin{quotation}'  ,
    689. 

  689. 	   'blockQuoteClose'     : '\\end{quotation}'    ,
    690. 

  690. 	   'fontMonoOpen'        : '\\texttt{'           ,
    691. 

  691. 	   'fontMonoClose'       : '}'                   ,
    692. 

  692. 	   'fontBoldOpen'        : '\\textbf{'           ,
    693. 

  693. 	   'fontBoldClose'       : '}'                   ,
    694. 

  694. 	   'fontItalicOpen'      : '\\textit{'           ,
    695. 

  695. 	   'fontItalicClose'     : '}'                   ,
    696. 

  696. 	   'fontUnderlineOpen'   : '\\underline{'        ,
    697. 

  697. 	   'fontUnderlineClose'  : '}'                   ,
    698. 

  698. 	   'listOpen'            : '\\begin{itemize}'    ,
    699. 

  699. 	   'listClose'           : '\\end{itemize}'      ,
    700. 

  700. 	   'listItemOpen'        : '\\item '             ,
    701. 

  701. 	   'numlistOpen'         : '\\begin{enumerate}'  ,
    702. 

  702. 	   'numlistClose'        : '\\end{enumerate}'    ,
    703. 

  703. 	   'numlistItemOpen'     : '\\item '             ,
    704. 

  704. 	   'deflistOpen'         : '\\begin{description}',
    705. 

  705. 	   'deflistClose'        : '\\end{description}'  ,
    706. 

  706. 	   'deflistItem1Open'    : '\\item['             ,
    707. 

  707. 	   'deflistItem1Close'   : ']'                   ,
    708. 

  708. 	   'bar1'                : '\n\\hrulefill{}\n'   ,
    709. 

  709. 	   'bar2'                : '\n\\rule{\linewidth}{1mm}\n',
    710. 

  710. 	   'url'                 : '\\htmladdnormallink{\a}{\a}',
    711. 

  711. 	   'urlMark'             : '\\htmladdnormallink{\a}{\a}',
    712. 

  712. 	   'email'               : '\\htmladdnormallink{\a}{mailto:\a}',
    713. 

  713. 	   'emailMark'           : '\\htmladdnormallink{\a}{mailto:\a}',
    714. 

  714. 	   'img'                 : '\\includegraphics{\a}',
    715. 

  715. 	   'tableOpen'           : '\\begin{center}\\begin{tabular}{|~C~|}',
    716. 

  716. 	   'tableClose'          : '\\end{tabular}\\end{center}',
    717. 

  717. 	   'tableRowOpen'        : '\\hline ' ,
    718. 

  718. 	   'tableRowClose'       : ' \\\\'    ,
    719. 

  719. 	   'tableCellSep'        : ' & '      ,
    720. 

  720. 	   'tableColAlignLeft'   : 'l'        ,
    721. 

  721. 	   'tableColAlignRight'  : 'r'        ,
    722. 

  722. 	   'tableColAlignCenter' : 'c'        ,
    723. 

  723. 	   'tableColAlignSep'    : '|'        ,
    724. 

  724. 	   'comment'             : '% \a'     ,
    725. 

  725. 	   'TOC'                 : '\\tableofcontents',
    726. 

  726. 	   'pageBreak'           : '\\clearpage',
    727. 

  727. 	   'EOD'                 : '\\end{document}'
    728. 

  728. 	},
    729. 

  729. 	
    730. 

  730. 	'lout': {
    731. 

  731. 	   'paragraphOpen'       : '@LP'                     ,
    732. 

  732. 	   'blockTitle1Open'     : '@BeginSections'          ,
    733. 

  733. 	   'blockTitle1Close'    : '@EndSections'            ,
    734. 

  734. 	   'blockTitle2Open'     : ' @BeginSubSections'      ,
    735. 

  735. 	   'blockTitle2Close'    : ' @EndSubSections'        ,
    736. 

  736. 	   'blockTitle3Open'     : '  @BeginSubSubSections'  ,
    737. 

  737. 	   'blockTitle3Close'    : '  @EndSubSubSections'    ,
    738. 

  738. 	   'title1Open'          : '\n@Section @Title { \a } @Begin',
    739. 

  739. 	   'title1Close'         : '@End @Section'           ,
    740. 

  740. 	   'title2Open'          : '\n @SubSection @Title { \a } @Begin',
    741. 

  741. 	   'title2Close'         : ' @End @SubSection'       ,
    742. 

  742. 	   'title3Open'          : '\n  @SubSubSection @Title { \a } @Begin',
    743. 

  743. 	   'title3Close'         : '  @End @SubSubSection'   ,
    744. 

  744. 	   'title4Open'          : '\n@LP @LeftDisplay @B { \a }',
    745. 

  745. 	   'title5Open'          : '\n@LP @LeftDisplay @B { \a }',
    746. 

  746. 	   'anchor'              : '@Tag { \a }'             ,
    747. 

  747. 	   'blockVerbOpen'       : '@LP @ID @F @RawVerbatim @Begin',
    748. 

  748. 	   'blockVerbClose'      : '@End @RawVerbatim'   ,
    749. 

  749. 	   'blockQuoteOpen'      : '@QD {'               ,
    750. 

  750. 	   'blockQuoteClose'     : '}'                   ,
    751. 

  751. 	   # enclosed inside {} to deal with joined**words**
    752. 

  752. 	   'fontMonoOpen'        : '{@F {'               ,
    753. 

  753. 	   'fontMonoClose'       : '}}'                  ,
    754. 

  754. 	   'fontBoldOpen'        : '{@B {'               ,
    755. 

  755. 	   'fontBoldClose'       : '}}'                  ,
    756. 

  756. 	   'fontItalicOpen'      : '{@II {'              ,
    757. 

  757. 	   'fontItalicClose'     : '}}'                  ,
    758. 

  758. 	   'fontUnderlineOpen'   : '{@Underline{'        ,
    759. 

  759. 	   'fontUnderlineClose'  : '}}'                  ,
    760. 

  760. 	   # the full form is more readable, but could be BL EL LI NL TL DTI
    761. 

  761. 	   'listOpen'            : '@BulletList'         ,
    762. 

  762. 	   'listClose'           : '@EndList'            ,
    763. 

  763. 	   'listItemOpen'        : '@ListItem{'          ,
    764. 

  764. 	   'listItemClose'       : '}'                   ,
    765. 

  765. 	   'numlistOpen'         : '@NumberedList'       ,
    766. 

  766. 	   'numlistClose'        : '@EndList'            ,
    767. 

  767. 	   'numlistItemOpen'     : '@ListItem{'          ,
    768. 

  768. 	   'numlistItemClose'    : '}'                   ,
    769. 

  769. 	   'deflistOpen'         : '@TaggedList'         ,
    770. 

  770. 	   'deflistClose'        : '@EndList'            ,
    771. 

  771. 	   'deflistItem1Open'    : '@DropTagItem {'      ,
    772. 

  772. 	   'deflistItem1Close'   : '}'                   ,
    773. 

  773. 	   'deflistItem2Open'    : '{'                   ,
    774. 

  774. 	   'deflistItem2Close'   : '}'                   ,
    775. 

  775. 	   'bar1'                : '\n@DP @FullWidthRule\n'     ,
    776. 

  776. 	   'url'                 : '{blue @Colour { \a }}'      ,
    777. 

  777. 	   'urlMark'             : '\a ({blue @Colour { \a }})' ,
    778. 

  778. 	   'email'               : '{blue @Colour { \a }}'      ,
    779. 

  779. 	   'emailMark'           : '\a ({blue Colour{ \a }})'   ,
    780. 

  780. 	   'img'                 : '~A~@IncludeGraphic { \a }'  ,  # eps only!
    781. 

  781. 	   'imgAlignLeft'        : '@LeftDisplay '              ,
    782. 

  782. 	   'imgAlignRight'       : '@RightDisplay '             ,
    783. 

  783. 	   'imgAlignCenter'      : '@CentredDisplay '           ,
    784. 

  784. 	   # lout tables are *way* complicated, no support for now
    785. 

  785. 	   #'tableOpen'          : '~A~@Tbl~B~\naformat{ @Cell A | @Cell B } {',
    786. 

  786. 	   #'tableClose'         : '}'     ,
    787. 

  787. 	   #'tableRowOpen'       : '@Rowa\n'       ,
    788. 

  788. 	   #'tableTitleRowOpen'  : '@HeaderRowa'       ,
    789. 

  789. 	   #'tableCenterAlign'   : '@CentredDisplay '         ,
    790. 

  790. 	   #'tableCellOpen'      : '\a {'                     ,  # A, B, ...
    791. 

  791. 	   #'tableCellClose'     : '}'                        ,
    792. 

  792. 	   #'tableBorder'        : '\nrule {yes}'             ,
    793. 

  793. 	   'comment'             : '# \a'                     ,
    794. 

  794. 	   # @MakeContents must be on the config file
    795. 

  795. 	   'TOC'                 : '@DP @ContentsGoesHere @DP',
    796. 

  796. 	   'pageBreak'           : '\n@NP\n'                  ,
    797. 

  797. 	   'EOD'                 : '@End @Text'
    798. 

  798. 	},
    799. 

  799. 	
    800. 

  800. 	'moin': {
    801. 

  801. 	   'title1'              : '= \a ='        ,
    802. 

  802. 	   'title2'              : '== \a =='      ,
    803. 

  803. 	   'title3'              : '=== \a ==='    ,
    804. 

  804. 	   'title4'              : '==== \a ===='  ,
    805. 

  805. 	   'title5'              : '===== \a =====',
    806. 

  806. 	   'blockVerbOpen'       : '{{{'           ,
    807. 

  807. 	   'blockVerbClose'      : '}}}'           ,
    808. 

  808. 	   'blockQuoteLine'      : '  '            ,
    809. 

  809. 	   'fontMonoOpen'        : '{{{'           ,
    810. 

  810. 	   'fontMonoClose'       : '}}}'           ,
    811. 

  811. 	   'fontBoldOpen'        : "'''"           ,
    812. 

  812. 	   'fontBoldClose'       : "'''"           ,
    813. 

  813. 	   'fontItalicOpen'      : "''"            ,
    814. 

  814. 	   'fontItalicClose'     : "''"            ,
    815. 

  815. 	   'fontUnderlineOpen'   : "__"            ,
    816. 

  816. 	   'fontUnderlineClose'  : "__"            ,
    817. 

  817. 	   'listItemOpen'        : ' * '           ,
    818. 

  818. 	   'numlistItemOpen'     : ' \a. '         ,
    819. 

  819. 	   'bar1'                : '----'          ,
    820. 

  820. 	   'url'                 : '[\a]'          ,
    821. 

  821. 	   'urlMark'             : '[\a \a]'       ,
    822. 

  822. 	   'email'               : '[\a]'          ,
    823. 

  823. 	   'emailMark'           : '[\a \a]'       ,
    824. 

  824. 	   'img'                 : '[\a]'          ,
    825. 

  825. 	   'tableRowOpen'        : '||'            ,
    826. 

  826. 	   'tableCellOpen'       : '\a'            ,
    827. 

  827. 	   'tableCellClose'      : '||'            ,
    828. 

  828. 	   'tableTitleCellClose' : '||'            ,
    829. 

  829. 	   'tableCellAlignRight' : '<)>'           ,
    830. 

  830. 	   'tableCellAlignCenter': '<:>'           ,
    831. 

  831. 	   'comment'             : '## \a'         ,
    832. 

  832. 	   'TOC'                 : '[[TableOfContents]]'
    833. 

  833. 	},
    834. 

  834. 	
    835. 

  835. 	'mgp': {
    836. 

  836. 	   'paragraphOpen'       : '%font "normal", size 5'     ,
    837. 

  837. 	   'title1'              : '%page\n\n\a\n'              ,
    838. 

  838. 	   'title2'              : '%page\n\n\a\n'              ,
    839. 

  839. 	   'title3'              : '%page\n\n\a\n'              ,
    840. 

  840. 	   'title4'              : '%page\n\n\a\n'              ,
    841. 

  841. 	   'title5'              : '%page\n\n\a\n'              ,
    842. 

  842. 	   'blockVerbOpen'       : '%font "mono"'               ,
    843. 

  843. 	   'blockVerbClose'      : '%font "normal"'             ,
    844. 

  844. 	   'blockQuoteOpen'      : '%prefix "       "'          ,
    845. 

  845. 	   'blockQuoteClose'     : '%prefix "  "'               ,
    846. 

  846. 	   'fontMonoOpen'        : '\n%cont, font "mono"\n'     ,
    847. 

  847. 	   'fontMonoClose'       : '\n%cont, font "normal"\n'   ,
    848. 

  848. 	   'fontBoldOpen'        : '\n%cont, font "normal-b"\n' ,
    849. 

  849. 	   'fontBoldClose'       : '\n%cont, font "normal"\n'   ,
    850. 

  850. 	   'fontItalicOpen'      : '\n%cont, font "normal-i"\n' ,
    851. 

  851. 	   'fontItalicClose'     : '\n%cont, font "normal"\n'   ,
    852. 

  852. 	   'fontUnderlineOpen'   : '\n%cont, fore "cyan"\n'     ,
    853. 

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

  854. 	   'listItemLine'        : '\t'                         ,
    855. 

  855. 	   'numlistItemLine'     : '\t'                         ,
    856. 

  856. 	   'deflistItem1Open'    : '\t\n%cont, font "normal-b"\n',
    857. 

  857. 	   'deflistItem1Close'   : '\n%cont, font "normal"\n'   ,
    858. 

  858. 	   'bar1'                : '%bar "white" 5'             ,
    859. 

  859. 	   'bar2'                : '%pause'                     ,
    860. 

  860. 	   'url'                 : '\n%cont, fore "cyan"\n\a'   +\
    861. 

  861. 	                           '\n%cont, fore "white"\n'    ,
    862. 

  862. 	   'urlMark'             : '\a \n%cont, fore "cyan"\n\a'+\
    863. 

  863. 	                           '\n%cont, fore "white"\n'    ,
    864. 

  864. 	   'email'               : '\n%cont, fore "cyan"\n\a'   +\
    865. 

  865. 	                           '\n%cont, fore "white"\n'    ,
    866. 

  866. 	   'emailMark'           : '\a \n%cont, fore "cyan"\n\a'+\
    867. 

  867. 	                           '\n%cont, fore "white"\n'    ,
    868. 

  868. 	   'img'                 : '~A~\n%newimage "\a"\n%left\n',
    869. 

  869. 	   'imgAlignLeft'        : '\n%left'                    ,
    870. 

  870. 	   'imgAlignRight'       : '\n%right'                   ,
    871. 

  871. 	   'imgAlignCenter'      : '\n%center'                  ,
    872. 

  872. 	   'comment'             : '%% \a'                      ,
    873. 

  873. 	   'pageBreak'           : '%page\n\n\n'                ,
    874. 

  874. 	   'EOD'                 : '%%EOD'
    875. 

  875. 	},
    876. 

  876. 	
    877. 

  877. 	# man groff_man ; man 7 groff
    878. 

  878. 	'man': {
    879. 

  879. 	   'paragraphOpen'       : '.P'     ,
    880. 

  880. 	   'title1'              : '.SH \a' ,
    881. 

  881. 	   'title2'              : '.SS \a' ,
    882. 

  882. 	   'title3'              : '.SS \a' ,
    883. 

  883. 	   'title4'              : '.SS \a' ,
    884. 

  884. 	   'title5'              : '.SS \a' ,
    885. 

  885. 	   'blockVerbOpen'       : '.nf'    ,
    886. 

  886. 	   'blockVerbClose'      : '.fi\n'  ,
    887. 

  887. 	   'blockQuoteOpen'      : '.RS'    ,
    888. 

  888. 	   'blockQuoteClose'     : '.RE'    ,
    889. 

  889. 	   'fontBoldOpen'        : '\\fB'   ,
    890. 

  890. 	   'fontBoldClose'       : '\\fR'   ,
    891. 

  891. 	   'fontItalicOpen'      : '\\fI'   ,
    892. 

  892. 	   'fontItalicClose'     : '\\fR'   ,
    893. 

  893. 	   'listOpen'            : '.RS'    ,
    894. 

  894. 	   'listItemOpen'        : '.IP \(bu 3\n',
    895. 

  895. 	   'listClose'           : '.RE'    ,
    896. 

  896. 	   'numlistOpen'         : '.RS'    ,
    897. 

  897. 	   'numlistItemOpen'     : '.IP \a. 3\n',
    898. 

  898. 	   'numlistClose'        : '.RE'    ,
    899. 

  899. 	   'deflistItem1Open'    : '.TP\n'  ,
    900. 

  900. 	   'bar1'                : '\n\n'   ,
    901. 

  901. 	   'url'                 : '\a'     ,
    902. 

  902. 	   'urlMark'             : '\a (\a)',
    903. 

  903. 	   'email'               : '\a'     ,
    904. 

  904. 	   'emailMark'           : '\a (\a)',
    905. 

  905. 	   'img'                 : '\a'     ,
    906. 

  906. 	   'tableOpen'           : '.TS\n~A~~B~tab(^); ~C~.',
    907. 

  907. 	   'tableClose'          : '.TE'     ,
    908. 

  908. 	   'tableRowOpen'        : ' '       ,
    909. 

  909. 	   'tableCellSep'        : '^'       ,
    910. 

  910. 	   'tableAlignCenter'    : 'center, ',
    911. 

  911. 	   'tableBorder'         : 'allbox, ',
    912. 

  912. 	   'tableColAlignLeft'   : 'l'       ,
    913. 

  913. 	   'tableColAlignRight'  : 'r'       ,
    914. 

  914. 	   'tableColAlignCenter' : 'c'       ,
    915. 

  915. 	   'comment'             : '.\\" \a'
    916. 

  916. 	},
    917. 

  917. 	
    918. 

  918. 	'pm6': {
    919. 

  919. 	   'paragraphOpen'       : '<@Normal:>'    ,
    920. 

  920. 	   'title1'              : '\n<@Title1:>\a',
    921. 

  921. 	   'title2'              : '\n<@Title2:>\a',
    922. 

  922. 	   'title3'              : '\n<@Title3:>\a',
    923. 

  923. 	   'title4'              : '\n<@Title4:>\a',
    924. 

  924. 	   'title5'              : '\n<@Title5:>\a',
    925. 

  925. 	   'blockVerbOpen'       : '<@PreFormat:>' ,
    926. 

  926. 	   'blockQuoteLine'      : '<@Quote:>'     ,
    927. 

  927. 	   'fontMonoOpen'        : '<FONT "Lucida Console"><SIZE 9>' ,
    928. 

  928. 	   'fontMonoClose'       : '<SIZE$><FONT$>',
    929. 

  929. 	   'fontBoldOpen'        : '<B>'           ,
    930. 

  930. 	   'fontBoldClose'       : '<P>'           ,
    931. 

  931. 	   'fontItalicOpen'      : '<I>'           ,
    932. 

  932. 	   'fontItalicClose'     : '<P>'           ,
    933. 

  933. 	   'fontUnderlineOpen'   : '<U>'           ,
    934. 

  934. 	   'fontUnderlineClose'  : '<P>'           ,
    935. 

  935. 	   'listOpen'            : '<@Bullet:>'    ,
    936. 

  936. 	   'listItemOpen'        : '\x95\t'        ,  # \x95 == ~U
    937. 

  937. 	   'numlistOpen'         : '<@Bullet:>'    ,
    938. 

  938. 	   'numlistItemOpen'     : '\x95\t'        ,
    939. 

  939. 	   'bar1'                : '\a'            ,
    940. 

  940. 	   'url'                 : '<U>\a<P>'      ,  # underline
    941. 

  941. 	   'urlMark'             : '\a <U>\a<P>'   ,
    942. 

  942. 	   'email'               : '\a'            ,
    943. 

  943. 	   'emailMark'           : '\a \a'         ,
    944. 

  944. 	   'img'                 : '\a'
    945. 

  945. 	}
    946. 

  946. 	}
    947. 

  947. 	
    948. 

  948. 	# exceptions for --css-sugar
    949. 

  949. 	if config['css-sugar'] and config['target'] in ('html','xhtml'):
    950. 

  950. 		# change just HTML because XHTML inherits it
    951. 

  951. 		htmltags = alltags['html']
    952. 

  952. 		# table with no cellpadding
    953. 

  953. 		htmltags['tableOpen'] = string.replace(
    954. 

  954. 			htmltags['tableOpen'], ' CELLPADDING="4"', '')
    955. 

  955. 		# DIVs
    956. 

  956. 		htmltags['tocOpen' ] = '<DIV CLASS="toc" ID="toc">'
    957. 

  957. 		htmltags['tocClose'] = '</DIV>'
    958. 

  958. 		htmltags['bodyOpen'] = '<DIV CLASS="body" ID="body">'
    959. 

  959. 		htmltags['bodyClose']= '</DIV>'
    960. 

  960. 	
    961. 

  961. 	# make the HTML -> XHTML inheritance
    962. 

  962. 	xhtml = alltags['html'].copy()
    963. 

  963. 	for key in xhtml.keys(): xhtml[key] = string.lower(xhtml[key])
    964. 

  964. 	# some like HTML tags as lowercase, some don't... (headers out)
    965. 

  965. 	if HTML_LOWER: alltags['html'] = xhtml.copy()
    966. 

  966. 	xhtml.update(alltags['xhtml'])
    967. 

  967. 	alltags['xhtml'] = xhtml.copy()
    968. 

  968. 	
    969. 

  969. 	# compose the target tags dictionary
    970. 

  970. 	tags = {}
    971. 

  971. 	target_tags = alltags[config['target']].copy()
    972. 

  972. 	
    973. 

  973. 	for key in keys: tags[key] = ''     # create empty keys
    974. 

  974. 	for key in target_tags.keys():
    975. 

  975. 		tags[key] = maskEscapeChar(target_tags[key]) # populate
    976. 

  976. 	
    977. 

  977. 	# map strong line to separator if not defined
    978. 

  978. 	if not tags['bar2'] and tags['bar1']:
    979. 

  979. 		tags['bar2'] = tags['bar1']
    980. 

  980. 	
    981. 

  981. 	return tags
    982. 

  982. 

  983. 

  984. ##############################################################################
    985. 

  985. 

  986. 

  987. def getRules(config):
    988. 

  988. 	"Returns all the target-specific syntax rules"
    989. 

  989. 	
    990. 

  990. 	ret = {}
    991. 

  991. 	allrules = [
    992. 

  992. 	
    993. 

  993. 	 # target rules (ON/OFF)
    994. 

  994. 	  'linkable',             # target supports external links
    995. 

  995. 	  'tableable',            # target supports tables
    996. 

  996. 	  'imglinkable',          # target supports images as links
    997. 

  997. 	  'imgalignable',         # target supports image alignment
    998. 

  998. 	  'imgasdefterm',         # target supports image as definition term
    999. 

  999. 	  'autonumberlist',       # target supports numbered lists natively
    1000. 

  1000. 	  'autonumbertitle',      # target supports numbered titles natively
    1001. 

  1001. 	  'parainsidelist',       # lists items supports paragraph
    1002. 

  1002. 	  'spacedlistitem',       # lists support blank lines between items
    1003. 

  1003. 	  'listnotnested',        # lists cannot be nested
    1004. 

  1004. 	  'quotenotnested',       # quotes cannot be nested
    1005. 

  1005. 	  'verbblocknotescaped',  # don't escape specials in verb block
    1006. 

  1006. 	  'verbblockfinalescape', # do final escapes in verb block
    1007. 

  1007. 	  'escapeurl',            # escape special in link URL
    1008. 

  1008. 	  'onelinepara',          # dump paragraph as a single long line
    1009. 

  1009. 	  'tabletitlerowinbold',  # manually bold any cell on table titles
    1010. 

  1010. 	  'tablecellstrip',       # strip extra spaces from each table cell
    1011. 

  1011. 	  'barinsidequote',       # bars are allowed inside quote blocks
    1012. 

  1012. 	  'finalescapetitle',     # perform final escapes on title lines
    1013. 

  1013. 	  'autotocnewpagebefore', # break page before automatic TOC
    1014. 

  1014. 	  'autotocnewpageafter',  # break page after automatic TOC
    1015. 

  1015. 	  'autotocwithbars',      # automatic TOC surrounded by bars
    1016. 

  1016. 	  'mapbar2pagebreak',     # map the strong bar to a page break
    1017. 

  1017. 	  'titleblocks',          # titles must be on open/close section blocks
    1018. 

  1018. 	
    1019. 

  1019. 	# target code beautify (ON/OFF)
    1020. 

  1020. 	  'indentverbblock',      # add leading spaces to verb block lines
    1021. 

  1021. 	  'breaktablecell',       # break lines after any table cell
    1022. 

  1022. 	  'breaktablelineopen',   # break line after opening table line
    1023. 

  1023. 	  'notbreaklistopen',     # don't break line after opening a new list
    1024. 

  1024. 	  'notbreakparaopen',     # don't break line after opening a new para
    1025. 

  1025. 	  'keepquoteindent',      # don't remove the leading TABs on quotes
    1026. 

  1026. 	  'keeplistindent',       # don't remove the leading spaces on lists
    1027. 

  1027. 	  'blankendmotherlist',   # append a blank line at the mother list end
    1028. 

  1028. 	  'blankendtable',        # append a blank line at the table end
    1029. 

  1029. 	  'blankendautotoc',      # append a blank line at the auto TOC end
    1030. 

  1030. 	  'tagnotindentable',     # tags must be placed at the line begining
    1031. 

  1031. 	
    1032. 

  1032. 	# value settings
    1033. 

  1033. 	  'listmaxdepth',         # maximum depth for lists
    1034. 

  1034. 	  'tablecellaligntype'    # type of table cell align: cell, column
    1035. 

  1035. 	]
    1036. 

  1036. 	
    1037. 

  1037. 	rules_bank = {
    1038. 

  1038. 	  'txt' : {
    1039. 

  1039. 	    'indentverbblock':1,
    1040. 

  1040. 	    'spacedlistitem':1,
    1041. 

  1041. 	    'parainsidelist':1,
    1042. 

  1042. 	    'keeplistindent':1,
    1043. 

  1043. 	    'barinsidequote':1,
    1044. 

  1044. 	    'autotocwithbars':1,
    1045. 

  1045. 	    'blankendmotherlist':1
    1046. 

  1046. 	    },
    1047. 

  1047. 	  'html': {
    1048. 

  1048. 	    'indentverbblock':1,
    1049. 

  1049. 	    'linkable':1,
    1050. 

  1050. 	    'escapeurl':1,
    1051. 

  1051. 	    'imglinkable':1,
    1052. 

  1052. 	    'imgalignable':1,
    1053. 

  1053. 	    'imgasdefterm':1,
    1054. 

  1054. 	    'autonumberlist':1,
    1055. 

  1055. 	    'spacedlistitem':1,
    1056. 

  1056. 	    'parainsidelist':1,
    1057. 

  1057. 	    'blankendmotherlist':1,
    1058. 

  1058. 	    'tableable':1,
    1059. 

  1059. 	    'tablecellstrip':1,
    1060. 

  1060. 	    'blankendtable':1,
    1061. 

  1061. 	    'breaktablecell':1,
    1062. 

  1062. 	    'breaktablelineopen':1,
    1063. 

  1063. 	    'keeplistindent':1,
    1064. 

  1064. 	    'keepquoteindent':1,
    1065. 

  1065. 	    'barinsidequote':1,
    1066. 

  1066. 	    'autotocwithbars':1,
    1067. 

  1067. 	    'tablecellaligntype':'cell'
    1068. 

  1068. 	    },
    1069. 

  1069. 	  #TIP xhtml inherits all HTML rules
    1070. 

  1070. 	  'xhtml': {
    1071. 

  1071. 	    },
    1072. 

  1072. 	  'sgml': {
    1073. 

  1073. 	    'linkable':1,
    1074. 

  1074. 	    'escapeurl':1,
    1075. 

  1075. 	    'autonumberlist':1,
    1076. 

  1076. 	    'spacedlistitem':1,
    1077. 

  1077. 	    'blankendmotherlist':1,
    1078. 

  1078. 	    'tableable':1,
    1079. 

  1079. 	    'tablecellstrip':1,
    1080. 

  1080. 	    'blankendtable':1,
    1081. 

  1081. 	    'blankendautotoc':1,
    1082. 

  1082. 	    'quotenotnested':1,
    1083. 

  1083. 	    'keeplistindent':1,
    1084. 

  1084. 	    'keepquoteindent':1,
    1085. 

  1085. 	    'barinsidequote':1,
    1086. 

  1086. 	    'finalescapetitle':1,
    1087. 

  1087. 	    'tablecellaligntype':'column'
    1088. 

  1088. 	    },
    1089. 

  1089. 	  'mgp' : {
    1090. 

  1090. 	    'blankendmotherlist':1,
    1091. 

  1091. 	    'tagnotindentable':1,
    1092. 

  1092. 	    'spacedlistitem':1,
    1093. 

  1093. 	    'imgalignable':1,
    1094. 

  1094. 	    'autotocnewpagebefore':1,
    1095. 

  1095. 	    },
    1096. 

  1096. 	  'tex' : {
    1097. 

  1097. 	    'autonumberlist':1,
    1098. 

  1098. 	    'autonumbertitle':1,
    1099. 

  1099. 	    'spacedlistitem':1,
    1100. 

  1100. 	    'blankendmotherlist':1,
    1101. 

  1101. 	    'tableable':1,
    1102. 

  1102. 	    'tablecellstrip':1,
    1103. 

  1103. 	    'tabletitlerowinbold':1,
    1104. 

  1104. 	    'blankendtable':1,
    1105. 

  1105. 	    'verbblocknotescaped':1,
    1106. 

  1106. 	    'keeplistindent':1,
    1107. 

  1107. 	    'listmaxdepth':4,
    1108. 

  1108. 	    'barinsidequote':1,
    1109. 

  1109. 	    'finalescapetitle':1,
    1110. 

  1110. 	    'autotocnewpageafter':1,
    1111. 

  1111. 	    'mapbar2pagebreak':1,
    1112. 

  1112. 	    'tablecellaligntype':'column'
    1113. 

  1113. 	    },
    1114. 

  1114. 	  'lout': {
    1115. 

  1115. 	    'keepquoteindent':1,
    1116. 

  1116. 	    'escapeurl':1,
    1117. 

  1117. 	    'verbblocknotescaped':1,
    1118. 

  1118. 	    'tableable':0,
    1119. 

  1119. 	    'imgalignable':1,
    1120. 

  1120. 	    'mapbar2pagebreak':1,
    1121. 

  1121. 	    'titleblocks':1,
    1122. 

  1122. 	    'notbreakparaopen':1
    1123. 

  1123. 	    },
    1124. 

  1124. 	  'moin': {
    1125. 

  1125. 	    'spacedlistitem':1,
    1126. 

  1126. 	    'linkable':1,
    1127. 

  1127. 	    'blankendmotherlist':1,
    1128. 

  1128. 	    'keeplistindent':1,
    1129. 

  1129. 	    'tableable':1,
    1130. 

  1130. 	    'barinsidequote':1,
    1131. 

  1131. 	    'blankendtable':1,
    1132. 

  1132. 	    'tabletitlerowinbold':1,
    1133. 

  1133. 	    'tablecellstrip':1,
    1134. 

  1134. 	    'autotocwithbars':1,
    1135. 

  1135. 	    'tablecellaligntype':'cell'
    1136. 

  1136. 	    },
    1137. 

  1137. 	  'man' : {
    1138. 

  1138. 	    'spacedlistitem':1,
    1139. 

  1139. 	    'indentverbblock':1,
    1140. 

  1140. 	    'blankendmotherlist':1,
    1141. 

  1141. 	    'tagnotindentable':1,
    1142. 

  1142. 	    'tableable':1,
    1143. 

  1143. 	    'tablecellaligntype':'column',
    1144. 

  1144. 	    'tabletitlerowinbold':1,
    1145. 

  1145. 	    'tablecellstrip':1,
    1146. 

  1146. 	    'blankendtable':1,
    1147. 

  1147. 	    'keeplistindent':0,
    1148. 

  1148. 	    'barinsidequote':1,
    1149. 

  1149. 	    'parainsidelist':0,
    1150. 

  1150. 	    },
    1151. 

  1151. 	  'pm6' : {
    1152. 

  1152. 	    'keeplistindent':1,
    1153. 

  1153. 	    'verbblockfinalescape':1,
    1154. 

  1154. 	    #TODO add support for these - maybe set a JOINNEXT char and
    1155. 

  1155. 	    #     do it on addLineBreaks()
    1156. 

  1156. 	    'notbreaklistopen':1,
    1157. 

  1157. 	    'notbreakparaopen':1,
    1158. 

  1158. 	    'barinsidequote':1,
    1159. 

  1159. 	    'autotocwithbars':1,
    1160. 

  1160. 	    'onelinepara':1,
    1161. 

  1161. 	    }
    1162. 

  1162. 	}
    1163. 

  1163. 	
    1164. 

  1164. 	# exceptions for --css-sugar
    1165. 

  1165. 	if config['css-sugar'] and config['target'] in ('html','xhtml'):
    1166. 

  1166. 		rules_bank['html']['indentverbblock'] = 0
    1167. 

  1167. 		rules_bank['html']['autotocwithbars'] = 0
    1168. 

  1168. 	
    1169. 

  1169. 	# get the target specific rules
    1170. 

  1170. 	if config['target'] == 'xhtml':
    1171. 

  1171. 		myrules = rules_bank['html'].copy()   # inheritance
    1172. 

  1172. 		myrules.update(rules_bank['xhtml'])   # get XHTML specific
    1173. 

  1173. 	else:
    1174. 

  1174. 		myrules = rules_bank[config['target']].copy()
    1175. 

  1175. 	
    1176. 

  1176. 	# populate return dictionary
    1177. 

  1177. 	for key in allrules: ret[key] = 0        # reset all
    1178. 

  1178. 	ret.update(myrules)                      # get rules
    1179. 

  1179. 	
    1180. 

  1180. 	return ret
    1181. 

  1181. 

  1182. 

  1183. ##############################################################################
    1184. 

  1184. 

  1185. 

  1186. def getRegexes():
    1187. 

  1187. 	"Returns all the regexes used to find the t2t marks"
    1188. 

  1188. 	
    1189. 

  1189. 	bank = {
    1190. 

  1190. 	'blockVerbOpen':
    1191. 

  1191. 		re.compile(r'^```\s*$'),
    1192. 

  1192. 	'blockVerbClose':
    1193. 

  1193. 		re.compile(r'^```\s*$'),
    1194. 

  1194. 	'blockRawOpen':
    1195. 

  1195. 		re.compile(r'^"""\s*$'),
    1196. 

  1196. 	'blockRawClose':
    1197. 

  1197. 		re.compile(r'^"""\s*$'),
    1198. 

  1198. 	'quote':
    1199. 

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

  1200. 	'1lineVerb':
    1201. 

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

  1202. 	'1lineRaw':
    1203. 

  1203. 		re.compile(r'^""" (?=.)'),
    1204. 

  1204. 	# mono, raw, bold, italic, underline:
    1205. 

  1205. 	# - marks must be glued with the contents, no boundary spaces
    1206. 

  1206. 	# - they are greedy, so in ****bold****, turns to <b>**bold**</b>
    1207. 

  1207. 	'fontMono':
    1208. 

  1208. 		re.compile(  r'``([^\s](|.*?[^\s])`*)``'),
    1209. 

  1209. 	'raw':
    1210. 

  1210. 		re.compile(  r'""([^\s](|.*?[^\s])"*)""'),
    1211. 

  1211. 	'fontBold':
    1212. 

  1212. 		re.compile(r'\*\*([^\s](|.*?[^\s])\**)\*\*'),
    1213. 

  1213. 	'fontItalic':
    1214. 

  1214. 		re.compile(  r'//([^\s](|.*?[^\s])/*)//'),
    1215. 

  1215. 	'fontUnderline':
    1216. 

  1216. 		re.compile(  r'__([^\s](|.*?[^\s])_*)__'),
    1217. 

  1217. 	'list':
    1218. 

  1218. 		re.compile(r'^( *)(-) (?=[^ ])'),
    1219. 

  1219. 	'numlist':
    1220. 

  1220. 		re.compile(r'^( *)(\+) (?=[^ ])'),
    1221. 

  1221. 	'deflist':
    1222. 

  1222. 		re.compile(r'^( *)(:) (.*)$'),
    1223. 

  1223. 	'listclose':
    1224. 

  1224. 		re.compile(r'^( *)([-+:])\s*$'),
    1225. 

  1225. 	'bar':
    1226. 

  1226. 		re.compile(r'^(\s*)([_=-]{20,})\s*$'),
    1227. 

  1227. 	'table':
    1228. 

  1228. 		re.compile(r'^ *\|\|? '),
    1229. 

  1229. 	'blankline':
    1230. 

  1230. 		re.compile(r'^\s*$'),
    1231. 

  1231. 	'comment':
    1232. 

  1232. 		re.compile(r'^%'),
    1233. 

  1233. 	
    1234. 

  1234. 	# auxiliar tag regexes
    1235. 

  1235. 	'_imgAlign'     : re.compile(r'~A~',re.I),
    1236. 

  1236. 	'_tableAlign'   : re.compile(r'~A~',re.I),
    1237. 

  1237. 	'_anchor'       : re.compile(r'~A~',re.I),
    1238. 

  1238. 	'_tableBorder'  : re.compile(r'~B~',re.I),
    1239. 

  1239. 	'_tableColAlign': re.compile(r'~C~',re.I),
    1240. 

  1240. 	}
    1241. 

  1241. 	
    1242. 

  1242. 	# special char to place data on TAGs contents  (\a == bell)
    1243. 

  1243. 	bank['x'] = re.compile('\a')
    1244. 

  1244. 	
    1245. 

  1245. 	# %%macroname [ (formatting) ]
    1246. 

  1246. 	bank['macros'] = re.compile(r'%%%%(?P<name>%s)\b(\((?P<fmt>.*?)\))?'%(
    1247. 

  1247. 	                            string.join(MACROS.keys(), '|')), re.I)
    1248. 

  1248. 	
    1249. 

  1249. 	# %%TOC special macro for TOC positioning
    1250. 

  1250. 	bank['toc'] = re.compile(r'^ *%%toc\s*$', re.I)
    1251. 

  1251. 	
    1252. 

  1252. 	# almost complicated title regexes ;)
    1253. 

  1253. 	titskel = r'^ *(?P<id>%s)(?P<txt>%s)\1(\[(?P<label>[\w-]*)\])?\s*$'
    1254. 

  1254. 	bank[   'title'] = re.compile(titskel%('[=]{1,5}','[^=](|.*[^=])'))
    1255. 

  1255. 	bank['numtitle'] = re.compile(titskel%('[+]{1,5}','[^+](|.*[^+])'))
    1256. 

  1256. 	
    1257. 

  1257. 	### complicated regexes begin here ;)
    1258. 

  1258. 	#
    1259. 

  1259. 	# textual descriptions on --help's style: [...] is optional, | is OR
    1260. 

  1260. 	
    1261. 

  1261. 	
    1262. 

  1262. 	### first, some auxiliar variables
    1263. 

  1263. 	#
    1264. 

  1264. 	
    1265. 

  1265. 	# [image.EXT]
    1266. 

  1266. 	patt_img = r'\[([\w_,.+%$#@!?+~/-]+\.(png|jpe?g|gif|eps|bmp))\]'
    1267. 

  1267. 	
    1268. 

  1268. 	# link things
    1269. 

  1269. 	urlskel = {
    1270. 

  1270. 	  'proto' : r'(https?|ftp|news|telnet|gopher|wais)://',
    1271. 

  1271. 	  'guess' : r'(www[23]?|ftp)\.',         # w/out proto, try to guess
    1272. 

  1272. 	  'login' : r'A-Za-z0-9_.-',             # for ftp://login@domain.com
    1273. 

  1273. 	  'pass'  : r'[^ @]*',                   # for ftp://login:pass@dom.com
    1274. 

  1274. 	  'chars' : r'A-Za-z0-9%._/~:,=$@&+-',   # %20(space), :80(port), D&D
    1275. 

  1275. 	  'anchor': r'A-Za-z0-9%._-',            # %nn(encoded)
    1276. 

  1276. 	  'form'  : r'A-Za-z0-9/%&=+;.,$@*_-',   # .,@*_-(as is)
    1277. 

  1277. 	  'punct' : r'.,;:!?'
    1278. 

  1278. 	}
    1279. 

  1279. 	
    1280. 

  1280. 	# username [ :password ] @
    1281. 

  1281. 	patt_url_login = r'([%s]+(:%s)?@)?'%(urlskel['login'],urlskel['pass'])
    1282. 

  1282. 	
    1283. 

  1283. 	# [ http:// ] [ username:password@ ] domain.com [ / ]
    1284. 

  1284. 	#     [ #anchor | ?form=data ]
    1285. 

  1285. 	retxt_url = r'\b(%s%s|%s)[%s]+\b/*(\?[%s]+)?(#[%s]+)?'%(
    1286. 

  1286. 	             urlskel['proto'],patt_url_login, urlskel['guess'],
    1287. 

  1287. 	             urlskel['chars'],urlskel['form'],urlskel['anchor'])
    1288. 

  1288. 	
    1289. 

  1289. 	# filename | [ filename ] #anchor
    1290. 

  1290. 	retxt_url_local = r'[%s]+|[%s]*(#[%s]+)'%(
    1291. 

  1291. 	             urlskel['chars'],urlskel['chars'],urlskel['anchor'])
    1292. 

  1292. 	
    1293. 

  1293. 	# user@domain [ ?form=data ]
    1294. 

  1294. 	patt_email = r'\b[%s]+@([A-Za-z0-9_-]+\.)+[A-Za-z]{2,4}\b(\?[%s]+)?'%(
    1295. 

  1295. 	             urlskel['login'],urlskel['form'])
    1296. 

  1296. 	
    1297. 

  1297. 	# saving for future use
    1298. 

  1298. 	bank['_urlskel'] = urlskel
    1299. 

  1299. 	
    1300. 

  1300. 	### and now the real regexes
    1301. 

  1301. 	#
    1302. 

  1302. 	
    1303. 

  1303. 	bank['email'] = re.compile(patt_email,re.I)
    1304. 

  1304. 	
    1305. 

  1305. 	# email | url
    1306. 

  1306. 	bank['link'] = re.compile(r'%s|%s'%(retxt_url,patt_email), re.I)
    1307. 

  1307. 	
    1308. 

  1308. 	# \[ label | imagetag    url | email | filename \]
    1309. 

  1309. 	bank['linkmark'] = re.compile(
    1310. 

  1310. 		r'\[(?P<label>%s|[^]]+) (?P<link>%s|%s|%s)\]'%(
    1311. 

  1311. 		  patt_img, retxt_url, patt_email, retxt_url_local),
    1312. 

  1312. 		re.L+re.I)
    1313. 

  1313. 	
    1314. 

  1314. 	# image
    1315. 

  1315. 	bank['img'] = re.compile(patt_img, re.L+re.I)
    1316. 

  1316. 	
    1317. 

  1317. 	# special things
    1318. 

  1318. 	bank['special'] = re.compile(r'^%!\s*')
    1319. 

  1319. 	return bank
    1320. 

  1320. ### END OF regex nightmares
    1321. 

  1321. 

  1322. 

  1323. ##############################################################################
    1324. 

  1324. 

  1325. class error(Exception):
    1326. 

  1326. 	pass
    1327. 

  1327. def echo(msg):   # for quick debug
    1328. 

  1328. 	print '\033[32;1m%s\033[m'%msg
    1329. 

  1329. def Quit(msg=''):
    1330. 

  1330. 	if msg: print msg
    1331. 

  1331. 	sys.exit(0)
    1332. 

  1332. def Error(msg):
    1333. 

  1333. 	msg = _("%s: Error: ")%my_name + msg
    1334. 

  1334. 	raise error, msg
    1335. 

  1335. def getTraceback():
    1336. 

  1336. 	try:
    1337. 

  1337. 		from traceback import format_exception
    1338. 

  1338. 		etype, value, tb = sys.exc_info()
    1339. 

  1339. 		return string.join(format_exception(etype, value, tb), '')
    1340. 

  1340. 	except: pass
    1341. 

  1341. def getUnknownErrorMessage():
    1342. 

  1342. 	msg = '%s\n%s (%s):\n\n%s'%(
    1343. 

  1343. 	  _('Sorry! Txt2tags aborted by an unknow error.'),
    1344. 

  1344. 	  _('Please send the following Error Traceback to the author'),
    1345. 

  1345. 	  my_email, getTraceback())
    1346. 

  1346. 	return msg
    1347. 

  1347. def Message(msg,level):
    1348. 

  1348. 	if level <= VERBOSE and not QUIET:
    1349. 

  1349. 		prefix = '-'*5
    1350. 

  1350. 		print "%s %s"%(prefix*level, msg)
    1351. 

  1351. def Debug(msg,id=0,linenr=None):
    1352. 

  1352. 	"Show debug messages, categorized (colored or not)"
    1353. 

  1353. 	if QUIET or not DEBUG: return
    1354. 

  1354. 	if int(id) not in range(8): id = 0
    1355. 

  1355. 	# 0:black 1:red 2:green 3:yellow 4:blue 5:pink 6:cyan 7:white ;1:light
    1356. 

  1356. 	ids            = ['INI','CFG','SRC','BLK','HLD','GUI','OUT','DET']
    1357. 

  1357. 	colors_bgdark  = ['7;1','1;1','3;1','6;1','4;1','5;1','2;1','7;1']
    1358. 

  1358. 	colors_bglight = ['0'  ,'1'  ,'3'  ,'6'  ,'4'  ,'5'  ,'2'  ,'0'  ]
    1359. 

  1359. 	if linenr is not None: msg = "LINE %04d: %s"%(linenr,msg)
    1360. 

  1360. 	if COLOR_DEBUG:
    1361. 

  1361. 		if BG_LIGHT: color = colors_bglight[id]
    1362. 

  1362. 		else       : color = colors_bgdark[id]
    1363. 

  1363. 		msg = '\033[3%sm%s\033[m'%(color,msg)
    1364. 

  1364. 	print "++ %s: %s"%(ids[id],msg)
    1365. 

  1365. def Readfile(file, remove_linebreaks=0, ignore_error=0):
    1366. 

  1366. 	data = []
    1367. 

  1367. 	if file == '-':
    1368. 

  1368. 		try: data = sys.stdin.readlines()
    1369. 

  1369. 		except:
    1370. 

  1370. 			if not ignore_error:
    1371. 

  1371. 				Error(_('You must feed me with data on STDIN!'))
    1372. 

  1372. 	else:
    1373. 

  1373. 		try: f = open(file); data = f.readlines() ; f.close()
    1374. 

  1374. 		except:
    1375. 

  1375. 			if not ignore_error:
    1376. 

  1376. 				Error(_("Cannot read file:")+" %s"%file)
    1377. 

  1377. 	if remove_linebreaks:
    1378. 

  1378. 		data = map(lambda x:re.sub('[\n\r]+$','',x), data)
    1379. 

  1379. 	Message(_("Readed file (%d lines): %s")%(len(data),file),2)
    1380. 

  1380. 	return data
    1381. 

  1381. def Savefile(file, contents):
    1382. 

  1382. 	try: f = open(file, 'wb')
    1383. 

  1383. 	except: Error(_("Cannot open file for writing:")+" %s"%file)
    1384. 

  1384. 	if type(contents) == type([]): doit = f.writelines
    1385. 

  1385. 	else: doit = f.write
    1386. 

  1386. 	doit(contents) ; f.close()
    1387. 

  1387. 

  1388. def showdic(dic):
    1389. 

  1389. 	for k in dic.keys(): print "%15s : %s" % (k,dic[k])
    1390. 

  1390. def dotted_spaces(txt=''):
    1391. 

  1391. 	return string.replace(txt,' ','.')
    1392. 

  1392. 

  1393. # TIP: win env vars http://www.winnetmag.com/Article/ArticleID/23873/23873.html
    1394. 

  1394. def get_rc_path():
    1395. 

  1395. 	"Return the full path for the users' RC file"
    1396. 

  1396. 	# try to get the path from an env var. if yes, we're done
    1397. 

  1397. 	user_defined = os.environ.get('T2TCONFIG')
    1398. 

  1398. 	if user_defined: return user_defined
    1399. 

  1399. 	# env var not found, so perform automatic path composing
    1400. 

  1400. 	# set default filename according system platform
    1401. 

  1401. 	rc_names = {'default':'.txt2tagsrc', 'win':'_t2trc'}
    1402. 

  1402. 	rc_file = rc_names.get(sys.platform[:3]) or rc_names['default']
    1403. 

  1403. 	# the file must be on the user directory, but where is this dir?
    1404. 

  1404. 	rc_dir_search = ['HOME', 'HOMEPATH']
    1405. 

  1405. 	for var in rc_dir_search:
    1406. 

  1406. 		rc_dir = os.environ.get(var)
    1407. 

  1407. 		if rc_dir: break
    1408. 

  1408. 	# rc dir found, now we must join dir+file to compose the full path
    1409. 

  1409. 	if rc_dir:
    1410. 

  1410. 		# compose path and return it if the file exists
    1411. 

  1411. 		rc_path = os.path.join(rc_dir, rc_file)
    1412. 

  1412. 		# on windows, prefix with the drive (%homedrive%: 2k/XP/NT)
    1413. 

  1413. 		if sys.platform[:3] == 'win':
    1414. 

  1414. 			rc_drive = os.environ.get('HOMEDRIVE')
    1415. 

  1415. 			rc_path = os.path.join(rc_drive,rc_path)
    1416. 

  1416. 		return rc_path
    1417. 

  1417. 	# sorry, not found
    1418. 

  1418. 	return ''
    1419. 

  1419. 

  1420. 

  1421. 

  1422. ##############################################################################
    1423. 

  1423. 

  1424. class CommandLine:
    1425. 

  1425. 	"""
    1426. 

  1426. 	Command Line class - Masters command line
    1427. 

  1427. 

  1428. 	This class checks and extract data from the provided command line.
    1429. 

  1429. 	The --long options and flags are taken from the global OPTIONS,
    1430. 

  1430. 	FLAGS and ACTIONS dictionaries. The short options are registered
    1431. 

  1431. 	here, and also their equivalence to the long ones.
    1432. 

  1432. 

  1433. 	METHODS:
    1434. 

  1434. 	  _compose_short_opts() -> str
    1435. 

  1435. 	  _compose_long_opts() -> list
    1436. 

  1436. 	      Compose the valid short and long options list, on the
    1437. 

  1437. 	      'getopt' format.
    1438. 

  1438. 	  
    1439. 

  1439. 	  parse() -> (opts, args)
    1440. 

  1440. 	      Call getopt to check and parse the command line.
    1441. 

  1441. 	      It expects to receive the command line as a list, and
    1442. 

  1442. 	      without the program name (sys.argv[1:]).
    1443. 

  1443. 	  
    1444. 

  1444. 	  get_raw_config() -> [RAW config]
    1445. 

  1445. 	      Scans command line and convert the data to the RAW config
    1446. 

  1446. 	      format. See ConfigMaster class to the RAW format description.
    1447. 

  1447. 	      Optional 'ignore' and 'filter' arguments are used to filter
    1448. 

  1448. 	      in or out specified keys.
    1449. 

  1449. 	  
    1450. 

  1450. 	  compose_cmdline(dict) -> [Command line]
    1451. 

  1451. 	      Compose a command line list from an already parsed config
    1452. 

  1452. 	      dictionary, generated from RAW by ConfigMaster(). Use
    1453. 

  1453. 	      this to compose an optimal command line for a group of
    1454. 

  1454. 	      options.
    1455. 

  1455. 	
    1456. 

  1456. 	The get_raw_config() calls parse(), so the tipical use of this
    1457. 

  1457. 	class is:
    1458. 

  1458. 	
    1459. 

  1459.             raw = CommandLine().get_raw_config(sys.argv[1:])
    1460. 

  1460. 	"""
    1461. 

  1461. 	def __init__(self):
    1462. 

  1462. 		self.all_options = OPTIONS.keys()
    1463. 

  1463. 		self.all_flags   = FLAGS.keys()
    1464. 

  1464. 		self.all_actions = ACTIONS.keys()
    1465. 

  1465. 		
    1466. 

  1466. 		# short:long options equivalence
    1467. 

  1467. 		self.short_long = {
    1468. 

  1468. 		  'h':'help'     ,   'V':'version',
    1469. 

  1469. 		  'n':'enum-title',  'i':'infile' ,
    1470. 

  1470. 		  'H':'no-headers',  'o':'outfile',
    1471. 

  1471. 		  'v':'verbose'   ,  't':'target' ,
    1472. 

  1472. 		  'q':'quiet'
    1473. 

  1473. 		}
    1474. 

  1474. 		
    1475. 

  1475. 		# compose valid short and long options data for getopt
    1476. 

  1476. 		self.short_opts = self._compose_short_opts()
    1477. 

  1477. 		self.long_opts  = self._compose_long_opts()
    1478. 

  1478. 	
    1479. 

  1479. 	def _compose_short_opts(self):
    1480. 

  1480. 		"Returns a string like 'hVt:o' with all short options/flags"
    1481. 

  1481. 		ret = []
    1482. 

  1482. 		for opt in self.short_long.keys():
    1483. 

  1483. 			long = self.short_long[opt]
    1484. 

  1484. 			if long in self.all_options: # is flag or option?
    1485. 

  1485. 				opt = opt+':'        # option: have param
    1486. 

  1486. 			ret.append(opt)
    1487. 

  1487. 		#Debug('Valid SHORT options: %s'%ret)
    1488. 

  1488. 		return string.join(ret, '')
    1489. 

  1489. 	
    1490. 

  1490. 	def _compose_long_opts(self):
    1491. 

  1491. 		"Returns a list with all the valid long options/flags"
    1492. 

  1492. 		ret = map(lambda x:x+'=', self.all_options)          # add =
    1493. 

  1493. 		ret.extend(self.all_flags)                           # flag ON
    1494. 

  1494. 		ret.extend(self.all_actions)                         # acts
    1495. 

  1495. 		ret.extend(map(lambda x:'no-'+x, self.all_flags))    # add no-*
    1496. 

  1496. 		ret.extend(['no-style','no-encoding','no-outfile'])  # turn OFF
    1497. 

  1497. 		#Debug('Valid LONG options: %s'%ret)
    1498. 

  1498. 		return ret
    1499. 

  1499. 	
    1500. 

  1500. 	def _tokenize(self, cmd_string=''):
    1501. 

  1501. 		"Convert a command line string to a list"
    1502. 

  1502. 		#TODO protect quotes contents
    1503. 

  1503. 		return string.split(cmd_string)
    1504. 

  1504. 	
    1505. 

  1505. 	def parse(self, cmdline=[]):
    1506. 

  1506. 		"Check/Parse a command line list     TIP: no program name!"
    1507. 

  1507. 		# get the valid options
    1508. 

  1508. 		short, long = self.short_opts, self.long_opts
    1509. 

  1509. 		# parse it!
    1510. 

  1510. 		try:
    1511. 

  1511. 			opts, args = getopt.getopt(cmdline, short, long)
    1512. 

  1512. 		except getopt.error, errmsg:
    1513. 

  1513. 			Error(_("%s (try --help)")%errmsg)
    1514. 

  1514. 		return (opts, args)
    1515. 

  1515. 	
    1516. 

  1516. 	def get_raw_config(self, cmdline=[], ignore=[], filter=[], relative=0):
    1517. 

  1517. 		"Returns the options/arguments found as RAW config"
    1518. 

  1518. 		if not cmdline: return []
    1519. 

  1519. 		ret = []
    1520. 

  1520. 		# we need lists, not strings
    1521. 

  1521. 		if type(cmdline) == type(''): cmdline = self._tokenize(cmdline)
    1522. 

  1522. 		opts, args = self.parse(cmdline[:])
    1523. 

  1523. 		# get infile, if any
    1524. 

  1524. 		while args:
    1525. 

  1525. 			infile = args.pop(0)
    1526. 

  1526. 			ret.append(['infile', infile])
    1527. 

  1527. 		# parse all options
    1528. 

  1528. 		for name,value in opts:
    1529. 

  1529. 			# remove leading - and --
    1530. 

  1530. 			name = re.sub('^--?', '', name)
    1531. 

  1531. 			# alias to old mispelled 'suGGar'
    1532. 

  1532. 			if   name ==    'css-suggar': name =    'css-sugar'
    1533. 

  1533. 			elif name == 'no-css-suggar': name = 'no-css-sugar'
    1534. 

  1534. 			# translate short opt to long
    1535. 

  1535. 			if len(name) == 1: name = self.short_long.get(name)
    1536. 

  1536. 			# outfile exception: path relative to PWD
    1537. 

  1537. 			if name == 'outfile' and value != STDOUT and relative:
    1538. 

  1538. 				value = os.path.abspath(value)
    1539. 

  1539. 			# save it
    1540. 

  1540. 			ret.append([name, value])
    1541. 

  1541. 		# apply 'ignore' and 'filter' rules (filter is stronger)
    1542. 

  1542. 		temp = ret[:] ; ret = []
    1543. 

  1543. 		for name,value in temp:
    1544. 

  1544. 			if (not filter and not ignore) or \
    1545. 

  1545. 			   (filter and name in filter) or \
    1546. 

  1546. 			   (ignore and name not in ignore):
    1547. 

  1547. 				ret.append( ['all', name, value] )
    1548. 

  1548. 		# add the original command line string as 'realcmdline'
    1549. 

  1549. 		ret.append( ['all', 'realcmdline', cmdline] )
    1550. 

  1550. 		return ret
    1551. 

  1551. 	
    1552. 

  1552. 	def compose_cmdline(self, conf={}, no_check=0):
    1553. 

  1553. 		"compose a full (and diet) command line from CONF dict"
    1554. 

  1554. 		if not conf: return []
    1555. 

  1555. 		args = []
    1556. 

  1556. 		dft_options = OPTIONS.copy()
    1557. 

  1557. 		cfg = conf.copy()
    1558. 

  1558. 		valid_opts = self.all_options + self.all_flags
    1559. 

  1559. 		use_short = {'no-headers':'H', 'enum-title':'n'}
    1560. 

  1560. 		# remove useless options
    1561. 

  1561. 		if not no_check and cfg.get('toc-only'):
    1562. 

  1562. 			if cfg.has_key('no-headers'):
    1563. 

  1563. 				del cfg['no-headers']
    1564. 

  1564. 			if cfg.has_key('outfile'):
    1565. 

  1565. 				del cfg['outfile']      # defaults to STDOUT
    1566. 

  1566. 			if cfg.get('target') == 'txt':
    1567. 

  1567. 				del cfg['target']       # already default
    1568. 

  1568. 			args.append('--toc-only')  # must be the first
    1569. 

  1569. 			del cfg['toc-only']
    1570. 

  1570. 		# add target type
    1571. 

  1571. 		if cfg.has_key('target'):
    1572. 

  1572. 			args.append('-t '+cfg['target'])
    1573. 

  1573. 			del cfg['target']
    1574. 

  1574. 		# add other options
    1575. 

  1575. 		for key in cfg.keys():
    1576. 

  1576. 			if key not in valid_opts: continue  # may be a %!setting
    1577. 

  1577. 			if key in ['outfile','infile']: continue   # later
    1578. 

  1578. 			val = cfg[key]
    1579. 

  1579. 			if not val: continue
    1580. 

  1580. 			# default values are useless on cmdline
    1581. 

  1581. 			if val == dft_options.get(key): continue
    1582. 

  1582. 			# -short format
    1583. 

  1583. 			if key in use_short.keys():
    1584. 

  1584. 				args.append('-'+use_short[key])
    1585. 

  1585. 				continue
    1586. 

  1586. 			# --long format
    1587. 

  1587. 			if key in self.all_flags: # add --option
    1588. 

  1588. 				args.append('--'+key)
    1589. 

  1589. 			else:                     # add --option=value
    1590. 

  1590. 				args.append('--%s=%s'%(key,val))
    1591. 

  1591. 		# the outfile using -o
    1592. 

  1592. 		if cfg.has_key('outfile') and \
    1593. 

  1593. 		   cfg['outfile'] != dft_options.get('outfile'):
    1594. 

  1594. 			args.append('-o '+cfg['outfile'])
    1595. 

  1595. 		# place input file(s) always at the end
    1596. 

  1596. 		if cfg.has_key('infile'):
    1597. 

  1597. 			args.append(string.join(cfg['infile'],' '))
    1598. 

  1598. 		# return as a nice list
    1599. 

  1599. 		Debug("Diet command line: %s"%string.join(args,' '), 1)
    1600. 

  1600. 		return args
    1601. 

  1601. 

  1602. ##############################################################################
    1603. 

  1603. 

  1604. class SourceDocument:
    1605. 

  1605. 	"""
    1606. 

  1606. 	SourceDocument class - scan document structure, extract data
    1607. 

  1607. 	
    1608. 

  1608. 	It knows about full files. It reads a file and identify all
    1609. 

  1609. 	the areas begining (Head,Conf,Body). With this info it can
    1610. 

  1610. 	extract each area contents.
    1611. 

  1611. 	Note: the original line break is removed.
    1612. 

  1612. 	
    1613. 

  1613. 	DATA:
    1614. 

  1614. 	  self.arearef - Save Head, Conf, Body init line number
    1615. 

  1615. 	  self.areas   - Store the area names which are not empty
    1616. 

  1616. 	  self.buffer  - The full file contents (with NO \\r, \\n)
    1617. 

  1617. 

  1618. 	METHODS:
    1619. 

  1619. 	  get()   - Access the contents of an Area. Example:
    1620. 

  1620. 	            config = SourceDocument(file).get('conf')
    1621. 

  1621. 	
    1622. 

  1622. 	  split() - Get all the document Areas at once. Example:
    1623. 

  1623. 	            head, conf, body = SourceDocument(file).split()
    1624. 

  1624. 	
    1625. 

  1625. 	RULES:
    1626. 

  1626. 	    * The document parts are sequential: Head, Conf and Body.
    1627. 

  1627. 	    * One ends when the next begins.
    1628. 

  1628. 	    * The Conf Area is optional, so a document can have just
    1629. 

  1629. 	      Head and Body Areas.
    1630. 

  1630. 	
    1631. 

  1631. 	    These are the Areas limits:
    1632. 

  1632. 	      - Head Area: the first three lines
    1633. 

  1633. 	      - Body Area: from the first valid text line to the end
    1634. 

  1634. 	      - Conf Area: the comments between Head and Body Areas
    1635. 

  1635. 

  1636. 	    Exception: If the first line is blank, this means no
    1637. 

  1637. 	    header info, so the Head Area is just the first line.
    1638. 

  1638. 	"""
    1639. 

  1639. 	def __init__(self, filename='', contents=[]):
    1640. 

  1640. 		self.areas = ['head','conf','body']
    1641. 

  1641. 		self.arearef = []
    1642. 

  1642. 		self.areas_fancy = ''
    1643. 

  1643. 		self.filename = filename
    1644. 

  1644. 		self.buffer = []
    1645. 

  1645. 		if filename:
    1646. 

  1646. 			self.scan_file(filename)
    1647. 

  1647. 		elif contents:
    1648. 

  1648. 			self.scan(contents)
    1649. 

  1649. 	
    1650. 

  1650. 	def split(self):
    1651. 

  1651. 		"Returns all document parts, splitted into lists."
    1652. 

  1652. 		return self.get('head'), self.get('conf'), self.get('body')
    1653. 

  1653. 	
    1654. 

  1654. 	def get(self, areaname):
    1655. 

  1655. 		"Returns head|conf|body contents from self.buffer"
    1656. 

  1656. 		# sanity
    1657. 

  1657. 		if areaname not in self.areas: return []
    1658. 

  1658. 		if not self.buffer           : return []
    1659. 

  1659. 		# go get it
    1660. 

  1660. 		bufini = 1
    1661. 

  1661. 		bufend = len(self.buffer)
    1662. 

  1662. 		if   areaname == 'head':
    1663. 

  1663. 			ini = bufini
    1664. 

  1664. 			end = self.arearef[1] or self.arearef[2] or bufend
    1665. 

  1665. 		elif areaname == 'conf':
    1666. 

  1666. 			ini = self.arearef[1]
    1667. 

  1667. 			end = self.arearef[2] or bufend
    1668. 

  1668. 		elif areaname == 'body':
    1669. 

  1669. 			ini = self.arearef[2]
    1670. 

  1670. 			end = bufend
    1671. 

  1671. 		else:
    1672. 

  1672. 			Error("Unknown Area name '%s'"%areaname)
    1673. 

  1673. 		lines = self.buffer[ini:end]
    1674. 

  1674. 		# make sure head will always have 3 lines
    1675. 

  1675. 		while areaname == 'head' and len(lines) < 3:
    1676. 

  1676. 			lines.append('')
    1677. 

  1677. 		return lines
    1678. 

  1678. 	
    1679. 

  1679. 	def scan_file(self, filename):
    1680. 

  1680. 		Debug("source file: %s"%filename)
    1681. 

  1681. 		Message(_("Loading source document"),1)
    1682. 

  1682. 		buf = Readfile(filename, remove_linebreaks=1)
    1683. 

  1683. 		self.scan(buf)
    1684. 

  1684. 	
    1685. 

  1685. 	def scan(self, lines):
    1686. 

  1686. 		"Run through source file and identify head/conf/body areas"
    1687. 

  1687. 		buf = lines
    1688. 

  1688. 		if len(buf) == 0:
    1689. 

  1689. 			Error(_('The input file is empty: %s')%filename)
    1690. 

  1690. 		cfg_parser = ConfigLines().parse_line
    1691. 

  1691. 		buf.insert(0, '')                         # text start at pos 1
    1692. 

  1692. 		ref = [1,4,0]
    1693. 

  1693. 		if not string.strip(buf[1]):              # no header
    1694. 

  1694. 			ref[0] = 0 ; ref[1] = 2
    1695. 

  1695. 		rgx = getRegexes()
    1696. 

  1696. 		for i in range(ref[1],len(buf)):          # find body init:
    1697. 

  1697. 			if string.strip(buf[i]) and (     # ... not blank and
    1698. 

  1698. 			   buf[i][0] != '%' or            # ... not comment or
    1699. 

  1699. 			   rgx['macros'].match(buf[i]) or # ... %%macro
    1700. 

  1700. 			   rgx['toc'].match(buf[i])    or # ... %%toc
    1701. 

  1701. 			   cfg_parser(buf[i],'include')[1]): # ... %!include
    1702. 

  1702. 				ref[2] = i ; break
    1703. 

  1703. 		if ref[1] == ref[2]: ref[1] = 0           # no conf area
    1704. 

  1704. 		for i in 0,1,2:                           # del !existent
    1705. 

  1705. 			if ref[i] >= len(buf): ref[i] = 0 # title-only
    1706. 

  1706. 			if not ref[i]: self.areas[i] = ''
    1707. 

  1707. 		Debug('Head,Conf,Body start line: %s'%ref)
    1708. 

  1708. 		self.arearef = ref                        # save results
    1709. 

  1709. 		self.buffer  = buf
    1710. 

  1710. 		# fancyness sample: head conf body (1 4 8)
    1711. 

  1711. 		self.areas_fancy = "%s (%s)"%(
    1712. 

  1712. 		     string.join(self.areas),
    1713. 

  1713. 		     string.join(map(str, map(lambda x:x or '', ref))))
    1714. 

  1714. 		Message(_("Areas found: %s")%self.areas_fancy, 2)
    1715. 

  1715. 	
    1716. 

  1716. 	def get_raw_config(self):
    1717. 

  1717. 		"Handy method to get the CONF area RAW config (if any)"
    1718. 

  1718. 		if not self.areas.count('conf'): return []
    1719. 

  1719. 		Message(_("Scanning source document CONF area"),1)
    1720. 

  1720. 		raw = ConfigLines(
    1721. 

  1721. 		      file=self.filename, lines=self.get('conf'),
    1722. 

  1722. 		      first_line=self.arearef[1]).get_raw_config()
    1723. 

  1723. 		Debug("document raw config: %s"%raw, 1)
    1724. 

  1724. 		return raw
    1725. 

  1725. 

  1726. ##############################################################################
    1727. 

  1727. 

  1728. class ConfigMaster:
    1729. 

  1729. 	"""
    1730. 

  1730. 	ConfigMaster class - the configuration wizard
    1731. 

  1731. 	
    1732. 

  1732. 	This class is the configuration master. It knows how to handle
    1733. 

  1733. 	the RAW and PARSED config format. It also performs the sanity
    1734. 

  1734. 	checkings for a given configuration.
    1735. 

  1735. 	
    1736. 

  1736. 	DATA:
    1737. 

  1737. 	  self.raw         - Stores the config on the RAW format
    1738. 

  1738. 	  self.parsed      - Stores the config on the PARSED format
    1739. 

  1739. 	  self.defaults    - Stores the default values for all keys
    1740. 

  1740. 	  self.off         - Stores the OFF values for all keys
    1741. 

  1741. 	  self.multi       - List of keys which can have multiple values
    1742. 

  1742. 	  self.numeric     - List of keys which value must be a number
    1743. 

  1743. 	  self.incremental - List of keys which are incremental
    1744. 

  1744. 	
    1745. 

  1745.         RAW FORMAT:
    1746. 

  1746. 	  The RAW format is a list of lists, being each mother list item
    1747. 

  1747. 	  a full configuration entry. Any entry is a 3 item list, on
    1748. 

  1748. 	  the following format: [ TARGET, KEY, VALUE ]
    1749. 

  1749. 	  Being a list, the order is preserved, so it's easy to use
    1750. 

  1750. 	  different kinds of configs, as CONF area and command line,
    1751. 

  1751. 	  respecting the precedence.
    1752. 

  1752. 	  The special target 'all' is used when no specific target was
    1753. 

  1753. 	  defined on the original config.
    1754. 

  1754. 	
    1755. 

  1755. 	PARSED FORMAT:
    1756. 

  1756. 	  The PARSED format is a dictionary, with all the 'key : value'
    1757. 

  1757. 	  found by reading the RAW config. The self.target contents
    1758. 

  1758. 	  matters, so this dictionary only contains the target's
    1759. 

  1759. 	  config. The configs of other targets are ignored.
    1760. 

  1760. 	
    1761. 

  1761. 	The CommandLine and ConfigLines classes have the get_raw_config()
    1762. 

  1762. 	method which convert the configuration found to the RAW format.
    1763. 

  1763. 	Just feed it to parse() and get a brand-new ready-to-use config
    1764. 

  1764. 	dictionary. Example:
    1765. 

  1765. 	
    1766. 

  1766. 	    >>> raw = CommandLine().get_raw_config(['-n', '-H'])
    1767. 

  1767. 	    >>> print raw
    1768. 

  1768. 	    [['all', 'enum-title', ''], ['all', 'no-headers', '']]
    1769. 

  1769. 	    >>> parsed = ConfigMaster(raw).parse()
    1770. 

  1770. 	    >>> print parsed
    1771. 

  1771. 	    {'enum-title': 1, 'headers': 0}
    1772. 

  1772. 	"""
    1773. 

  1773. 	def __init__(self, raw=[], target=''):
    1774. 

  1774. 		self.raw          = raw
    1775. 

  1775. 		self.target       = target
    1776. 

  1776. 		self.parsed       = {}
    1777. 

  1777. 		self.dft_options  = OPTIONS.copy()
    1778. 

  1778. 		self.dft_flags    = FLAGS.copy()
    1779. 

  1779. 		self.dft_actions  = ACTIONS.copy()
    1780. 

  1780. 		self.dft_settings = SETTINGS.copy()
    1781. 

  1781. 		self.defaults     = self._get_defaults()
    1782. 

  1782. 		self.off          = self._get_off()
    1783. 

  1783. 		self.multi        = ['infile', 'options','preproc','postproc']
    1784. 

  1784. 		self.incremental  = ['verbose']
    1785. 

  1785. 		self.numeric      = ['toc-level','split']
    1786. 

  1786. 	
    1787. 

  1787. 	def _get_defaults(self):
    1788. 

  1788. 		"Get the default values for all config/options/flags"
    1789. 

  1789. 		empty = {}
    1790. 

  1790. 		for kw in CONFIG_KEYWORDS: empty[kw] = ''
    1791. 

  1791. 		empty.update(self.dft_options)
    1792. 

  1792. 		empty.update(self.dft_flags)
    1793. 

  1793. 		empty.update(self.dft_actions)
    1794. 

  1794. 		empty.update(self.dft_settings)
    1795. 

  1795. 		empty['realcmdline'] = ''  # internal use only
    1796. 

  1796. 		empty['sourcefile']  = ''  # internal use only
    1797. 

  1797. 		return empty
    1798. 

  1798. 	
    1799. 

  1799. 	def _get_off(self):
    1800. 

  1800. 		"Turns OFF all the config/options/flags"
    1801. 

  1801. 		off = {}
    1802. 

  1802. 		for key in self.defaults.keys():
    1803. 

  1803. 			kind = type(self.defaults[key])
    1804. 

  1804. 			if kind == type(9):
    1805. 

  1805. 				off[key] = 0
    1806. 

  1806. 			elif kind == type(''):
    1807. 

  1807. 				off[key] = ''
    1808. 

  1808. 			elif kind == type([]):
    1809. 

  1809. 				off[key] = []
    1810. 

  1810. 			else:
    1811. 

  1811. 				Error('ConfigMaster: %s: Unknown type'+key)
    1812. 

  1812. 		return off
    1813. 

  1813. 	
    1814. 

  1814. 	def _check_target(self):
    1815. 

  1815. 		"Checks if the target is already defined. If not, do it"
    1816. 

  1816. 		if not self.target:
    1817. 

  1817. 			self.target = self.find_value('target')
    1818. 

  1818. 	
    1819. 

  1819. 	def get_target_raw(self):
    1820. 

  1820. 		"Returns the raw config for self.target or 'all'"
    1821. 

  1821. 		ret = []
    1822. 

  1822. 		self._check_target()
    1823. 

  1823. 		for entry in self.raw:
    1824. 

  1824. 			if entry[0] in [self.target, 'all']:
    1825. 

  1825. 				ret.append(entry)
    1826. 

  1826. 		return ret
    1827. 

  1827. 	
    1828. 

  1828. 	def add(self, key, val):
    1829. 

  1829. 		"Adds the key:value pair to the config dictionary (if needed)"
    1830. 

  1830. 		# %!options
    1831. 

  1831. 		if key == 'options':
    1832. 

  1832. 			ignoreme = self.dft_actions.keys() + ['target']
    1833. 

  1833. 			raw_opts = CommandLine().get_raw_config(
    1834. 

  1834. 			             val, ignore=ignoreme)
    1835. 

  1835. 			for target, key, val in raw_opts:
    1836. 

  1836. 				self.add(key, val)
    1837. 

  1837. 			return
    1838. 

  1838. 		# the no- prefix turns OFF this key
    1839. 

  1839. 		if key[:3] == 'no-':
    1840. 

  1840. 			key = key[3:]              # remove prefix
    1841. 

  1841. 			val = self.off.get(key)    # turn key OFF
    1842. 

  1842. 		# is this key valid?
    1843. 

  1843. 		if key not in self.defaults.keys():
    1844. 

  1844. 			Debug('Bogus Config %s:%s'%(key,val),1)
    1845. 

  1845. 			return
    1846. 

  1846. 		# is this value the default one?
    1847. 

  1847. 		if val == self.defaults.get(key):
    1848. 

  1848. 			# if default value, remove previous key:val
    1849. 

  1849. 			if self.parsed.has_key(key):
    1850. 

  1850. 				del self.parsed[key]
    1851. 

  1851. 			# nothing more to do
    1852. 

  1852. 			return
    1853. 

  1853. 		# flags ON comes empty. we'll add the 1 value now
    1854. 

  1854. 		if val == '' and \
    1855. 

  1855. 		   key in self.dft_flags.keys()+self.dft_actions.keys():
    1856. 

  1856. 			val = 1
    1857. 

  1857. 		# multi value or single?
    1858. 

  1858. 		if key in self.multi:
    1859. 

  1859. 			# first one? start new list
    1860. 

  1860. 			if not self.parsed.has_key(key):
    1861. 

  1861. 				self.parsed[key] = []
    1862. 

  1862. 			self.parsed[key].append(val)
    1863. 

  1863. 		# incremental value? so let's add it
    1864. 

  1864. 		elif key in self.incremental:
    1865. 

  1865. 			self.parsed[key] = (self.parsed.get(key) or 0) + val
    1866. 

  1866. 		else:
    1867. 

  1867. 			self.parsed[key] = val
    1868. 

  1868. 		fancykey = dotted_spaces("%12s"%key)
    1869. 

  1869. 		Message(_("Added config %s : %s")%(fancykey,val),3)
    1870. 

  1870. 	
    1871. 

  1871. 	def get_outfile_name(self, config={}):
    1872. 

  1872. 		"Dirname is the same for {in,out}file"
    1873. 

  1873. 		infile, outfile = config['sourcefile'], config['outfile']
    1874. 

  1874. 		if outfile and outfile != STDOUT and not os.path.isabs(outfile):
    1875. 

  1875. 			outfile = os.path.join(os.path.dirname(infile), outfile)
    1876. 

  1876. 		if infile == STDIN and not outfile: outfile = STDOUT
    1877. 

  1877. 		if not outfile and (infile and config.get('target')):
    1878. 

  1878. 			basename = re.sub('\.(txt|t2t)$','',infile)
    1879. 

  1879. 			outfile = "%s.%s"%(basename, config['target'])
    1880. 

  1880. 		Debug(" infile: '%s'"%infile , 1)
    1881. 

  1881. 		Debug("outfile: '%s'"%outfile, 1)
    1882. 

  1882. 		return outfile
    1883. 

  1883. 	
    1884. 

  1884. 	def sanity(self, config, gui=0):
    1885. 

  1885. 		"Basic config sanity checkings"
    1886. 

  1886. 		if not config: return {}
    1887. 

  1887. 		target = config.get('target')
    1888. 

  1888. 		# --toc-only doesn't require target specification
    1889. 

  1889. 		if not target and config.get('toc-only'):
    1890. 

  1890. 			target = 'txt'
    1891. 

  1891. 		# on GUI, some checkings are skipped
    1892. 

  1892. 		if not gui:
    1893. 

  1893. 			# we *need* a target
    1894. 

  1894. 			if not target:
    1895. 

  1895. 				Error(_('No target specified (try --help)')+\
    1896. 

  1896. 				'\n\n'+\
    1897. 

  1897. 				_('Maybe trying to convert an old v1.x file?'))
    1898. 

  1898. 			# and of course, an infile also
    1899. 

  1899. 			if not config.get('infile'):
    1900. 

  1900. 				Error(_('Missing input file (try --help)'))
    1901. 

  1901. 			# is the target valid?
    1902. 

  1902. 			if not TARGETS.count(target):
    1903. 

  1903. 				Error(_("Invalid target '%s' (try --help)")%\
    1904. 

  1904. 				     target)
    1905. 

  1905. 		# ensure all keys are present
    1906. 

  1906. 		empty = self.defaults.copy() ; empty.update(config)
    1907. 

  1907. 		config = empty.copy()
    1908. 

  1908. 		# check integers options
    1909. 

  1909. 		for key in config.keys():
    1910. 

  1910. 			if key in self.numeric:
    1911. 

  1911. 				try: config[key] = int(config[key])
    1912. 

  1912. 				except: Error(_('--%s value must be a number'
    1913. 

  1913. 				                )%key)
    1914. 

  1914. 		# check split level value
    1915. 

  1915. 		if config['split'] not in [0,1,2]:
    1916. 

  1916. 			Error(_('Option --split must be 0, 1 or 2'))
    1917. 

  1917. 		# --toc-only is stronger than others
    1918. 

  1918. 		if config['toc-only']:
    1919. 

  1919. 			config['headers'] = 0
    1920. 

  1920. 			config['toc']     = 0
    1921. 

  1921. 			config['split']   = 0
    1922. 

  1922. 			config['gui']     = 0
    1923. 

  1923. 			config['outfile'] = config['outfile'] or STDOUT
    1924. 

  1924. 		# splitting is disable for now (future: HTML only, no STDOUT)
    1925. 

  1925. 		config['split'] = 0
    1926. 

  1926. 		# restore target
    1927. 

  1927. 		config['target'] = target
    1928. 

  1928. 		# set output file name
    1929. 

  1929. 		config['outfile'] = self.get_outfile_name(config)
    1930. 

  1930. 		# checking suicide
    1931. 

  1931. 		if config['sourcefile'] == config['outfile'] and \
    1932. 

  1932. 		   config['outfile'] != STDOUT and not gui:
    1933. 

  1933. 			Error(_("Input and Output files are the same: %s")%(
    1934. 

  1934. 			config['outfile']))
    1935. 

  1935. 		return config
    1936. 

  1936. 	
    1937. 

  1937. 	def parse(self):
    1938. 

  1938. 		"Returns the parsed config for the current target"
    1939. 

  1939. 		raw = self.get_target_raw()
    1940. 

  1940. 		for target, key, value in raw:
    1941. 

  1941. 			self.add(key, value)
    1942. 

  1942. 		Message(_("Added the following keys: %s")%string.join(
    1943. 

  1943. 		         self.parsed.keys(),', '),2)
    1944. 

  1944. 		return self.parsed.copy()
    1945. 

  1945. 	
    1946. 

  1946. 	def find_value(self, key='', target=''):
    1947. 

  1947. 		"Scans ALL raw config to find the desired key"
    1948. 

  1948. 		ret = []
    1949. 

  1949. 		# scan and save all values found
    1950. 

  1950. 		for targ, k, val in self.raw:
    1951. 

  1951. 			if targ in [target, 'all'] and k == key:
    1952. 

  1952. 				ret.append(val)
    1953. 

  1953. 		if not ret: return ''
    1954. 

  1954. 		# if not multi value, return only the last found
    1955. 

  1955. 		if key in self.multi: return ret
    1956. 

  1956. 		else                : return ret[-1]
    1957. 

  1957. 

  1958. ########################################################################
    1959. 

  1959. 

  1960. class ConfigLines:
    1961. 

  1961. 	"""
    1962. 

  1962. 	ConfigLines class - the config file data extractor
    1963. 

  1963. 	
    1964. 

  1964. 	This class reads and parse the config lines on the %!key:val
    1965. 

  1965. 	format, converting it to RAW config. It deals with user
    1966. 

  1966. 	config file (RC file), source document CONF area and
    1967. 

  1967. 	%!includeconf directives.
    1968. 

  1968. 

  1969. 	Call it passing a file name or feed the desired config lines.
    1970. 

  1970. 	Then just call the get_raw_config() method and wait to
    1971. 

  1971. 	receive the full config data on the RAW format. This method
    1972. 

  1972. 	also follows the possible %!includeconf directives found on
    1973. 

  1973. 	the config lines. Example:
    1974. 

  1974. 

  1975. 	    raw = ConfigLines(file=".txt2tagsrc").get_raw_config()
    1976. 

  1976. 

  1977. 	The parse_line() method is also useful to be used alone,
    1978. 

  1978. 	to identify and tokenize a single config line. For example,
    1979. 

  1979. 	to get the %!include command components, on the source
    1980. 

  1980. 	document BODY:
    1981. 

  1981. 	
    1982. 

  1982. 	    target, key, value = ConfigLines().parse_line(body_line)
    1983. 

  1983. 	"""
    1984. 

  1984. 	def __init__(self, file='', lines=[], first_line=1):
    1985. 

  1985. 		self.file = file or 'NOFILE'
    1986. 

  1986. 		self.lines = lines
    1987. 

  1987. 		self.first_line = first_line
    1988. 

  1988. 	
    1989. 

  1989. 	def load_lines(self):
    1990. 

  1990. 		"Make sure we've loaded the file contents into buffer"
    1991. 

  1991. 		if not self.lines and not self.file:
    1992. 

  1992. 			Error("ConfigLines: No file or lines provided")
    1993. 

  1993. 		if not self.lines:
    1994. 

  1994. 			self.lines = self.read_config_file(self.file)
    1995. 

  1995. 	
    1996. 

  1996. 	def read_config_file(self, filename=''):
    1997. 

  1997. 		"Read a Config File contents, aborting on invalid line"
    1998. 

  1998. 		if not filename: return []
    1999. 

  1999. 		errormsg = _("Invalid CONFIG line on %s")+"\n%03d:%s"
    2000. 

  2000. 		lines = Readfile(filename, remove_linebreaks=1)
    2001. 

  2001. 		# sanity: try to find invalid config lines
    2002. 

  2002. 		for i in range(len(lines)):
    2003. 

  2003. 			line = string.rstrip(lines[i])
    2004. 

  2004. 			if not line: continue  # empty
    2005. 

  2005. 			if line[0] != '%': Error(errormsg%(filename,i+1,line))
    2006. 

  2006. 		return lines
    2007. 

  2007. 	
    2008. 

  2008. 	def include_config_file(self, file=''):
    2009. 

  2009. 		"Perform the %!includeconf action, returning RAW config"
    2010. 

  2010. 		if not file: return []
    2011. 

  2011. 		# current dir relative to the current file (self.file)
    2012. 

  2012. 		current_dir = os.path.dirname(self.file)
    2013. 

  2013. 		file = os.path.join(current_dir, file)
    2014. 

  2014. 		# read and parse included config file contents
    2015. 

  2015. 		lines = self.read_config_file(file)
    2016. 

  2016. 		return ConfigLines(file=file, lines=lines).get_raw_config()
    2017. 

  2017. 	
    2018. 

  2018. 	def get_raw_config(self):
    2019. 

  2019. 		"Scan buffer and extract all config as RAW (including includes)"
    2020. 

  2020. 		ret = []
    2021. 

  2021. 		self.load_lines()
    2022. 

  2022. 		first = self.first_line
    2023. 

  2023. 		for i in range(len(self.lines)):
    2024. 

  2024. 			line = self.lines[i]
    2025. 

  2025. 			Message(_("Processing line %03d: %s")%(first+i,line),2)
    2026. 

  2026. 			target, key, val = self.parse_line(line)
    2027. 

  2027. 			if not key: continue    # no config on this line
    2028. 

  2028. 			if key == 'includeconf':
    2029. 

  2029. 				more_raw = self.include_config_file(val)
    2030. 

  2030. 				ret.extend(more_raw)
    2031. 

  2031. 				Message(_("Finished Config file inclusion: %s"
    2032. 

  2032. 				          )%(val),2)
    2033. 

  2033. 			else:
    2034. 

  2034. 				ret.append([target, key, val])
    2035. 

  2035. 				Message(_("Added %s")%key,3)
    2036. 

  2036. 		return ret
    2037. 

  2037. 	
    2038. 

  2038. 	def parse_line(self, line='', keyname='', target=''):
    2039. 

  2039. 		"Detects %!key:val config lines and extract data from it"
    2040. 

  2040. 		empty = ['', '', '']
    2041. 

  2041. 		if not line: return empty
    2042. 

  2042. 		no_target = ['target', 'includeconf']
    2043. 

  2043. 		re_name   = keyname or '[a-z]+'
    2044. 

  2044. 		re_target = target  or '[a-z]*'
    2045. 

  2045. 		cfgregex  = re.compile("""
    2046. 

  2046. 		  ^%%!\s*               # leading id with opt spaces
    2047. 

  2047. 		  (?P<name>%s)\s*       # config name
    2048. 

  2048. 		  (\((?P<target>%s)\))? # optional target spec inside ()
    2049. 

  2049. 		  \s*:\s*               # key:value delimiter with opt spaces
    2050. 

  2050. 		  (?P<value>\S.+?)      # config value
    2051. 

  2051. 		  \s*$                  # rstrip() spaces and hit EOL
    2052. 

  2052. 		  """%(re_name,re_target), re.I+re.VERBOSE)
    2053. 

  2053. 		prepostregex = re.compile("""
    2054. 

  2054. 		                        # ---[ PATTERN ]---
    2055. 

  2055. 		  ^( "([^"]*)"          # "double quoted" or
    2056. 

  2056. 		   | '([^']*)'          # 'single quoted' or
    2057. 

  2057. 		   | ([^\s]+)           # single_word
    2058. 

  2058. 		   )
    2059. 

  2059. 		    \s+                 # separated by spaces
    2060. 

  2060. 		
    2061. 

  2061. 		                        # ---[ REPLACE ]---
    2062. 

  2062. 		       ( "([^"]*)"      # "double quoted" or
    2063. 

  2063. 		       | '([^']*)'      # 'single quoted' or
    2064. 

  2064. 		       | (.*)           # anything
    2065. 

  2065. 		           )
    2066. 

  2066. 		            \s*$
    2067. 

  2067. 		  """, re.VERBOSE)
    2068. 

  2068. 		guicolors = re.compile("^([^\s]+\s+){3}[^\s]+") # 4 tokens
    2069. 

  2069. 		match = cfgregex.match(line)
    2070. 

  2070. 		if not match: return empty
    2071. 

  2071. 		
    2072. 

  2072. 		name   = string.lower(match.group('name') or '')
    2073. 

  2073. 		target = string.lower(match.group('target') or 'all')
    2074. 

  2074. 		value  = match.group('value')
    2075. 

  2075. 		
    2076. 

  2076. 		# NO target keywords: force all targets
    2077. 

  2077. 		if name in no_target: target = 'all'
    2078. 

  2078. 		
    2079. 

  2079. 		# special config for GUI colors
    2080. 

  2080. 		if name == 'guicolors':
    2081. 

  2081. 			valmatch = guicolors.search(value)
    2082. 

  2082. 			if not valmatch: return empty
    2083. 

  2083. 			value = re.split('\s+', value)
    2084. 

  2084. 		
    2085. 

  2085. 		# Special config with two quoted values (%!preproc: "foo" 'bar')
    2086. 

  2086. 		if name in ['preproc','postproc']:
    2087. 

  2087. 			valmatch = prepostregex.search(value)
    2088. 

  2088. 			if not valmatch: return empty
    2089. 

  2089. 			getval = valmatch.group
    2090. 

  2090. 			patt   = getval(2) or getval(3) or getval(4) or ''
    2091. 

  2091. 			repl   = getval(6) or getval(7) or getval(8) or ''
    2092. 

  2092. 			value  = (patt, repl)
    2093. 

  2093. 		return [target, name, value]
    2094. 

  2094. 

  2095. ##############################################################################
    2096. 

  2096. 

  2097. class MaskMaster:
    2098. 

  2098. 	"(Un)Protect important structures from escaping and formatting"
    2099. 

  2099. 	def __init__(self):
    2100. 

  2100. 		self.linkmask  = 'vvvLINKvvv'
    2101. 

  2101. 		self.monomask  = 'vvvMONOvvv'
    2102. 

  2102. 		self.macromask = 'vvvMACROvvv'
    2103. 

  2103. 		self.rawmask   = 'vvvRAWvvv'
    2104. 

  2104. 		self.tocmask   = 'vvvTOCvvv'
    2105. 

  2105. 		self.macroman  = MacroMaster()
    2106. 

  2106. 		self.reset()
    2107. 

  2107. 	
    2108. 

  2108. 	def reset(self):
    2109. 

  2109. 		self.linkbank = []
    2110. 

  2110. 		self.monobank = []
    2111. 

  2111. 		self.macrobank = []
    2112. 

  2112. 		self.rawbank = []
    2113. 

  2113. 	
    2114. 

  2114. 	def mask(self, line=''):
    2115. 

  2115. 		global AUTOTOC
    2116. 

  2116. 		
    2117. 

  2117. 		# protect raw text
    2118. 

  2118. 		while regex['raw'].search(line):
    2119. 

  2119. 			txt = regex['raw'].search(line).group(1)
    2120. 

  2120. 			txt = doEscape(TARGET,txt)
    2121. 

  2121. 			self.rawbank.append(txt)
    2122. 

  2122. 			line = regex['raw'].sub(self.rawmask,line,1)
    2123. 

  2123. 		
    2124. 

  2124. 		# protect pre-formatted font text
    2125. 

  2125. 		while regex['fontMono'].search(line):
    2126. 

  2126. 			txt = regex['fontMono'].search(line).group(1)
    2127. 

  2127. 			txt = doEscape(TARGET,txt)
    2128. 

  2128. 			self.monobank.append(txt)
    2129. 

  2129. 			line = regex['fontMono'].sub(self.monomask,line,1)
    2130. 

  2130. 		
    2131. 

  2131. 		# protect macros
    2132. 

  2132. 		while regex['macros'].search(line):
    2133. 

  2133. 			txt = regex['macros'].search(line).group()
    2134. 

  2134. 			self.macrobank.append(txt)
    2135. 

  2135. 			line = regex['macros'].sub(self.macromask,line,1)
    2136. 

  2136. 		
    2137. 

  2137. 		# protect TOC location
    2138. 

  2138. 		while regex['toc'].search(line):
    2139. 

  2139. 			line = regex['toc'].sub(self.tocmask,line)
    2140. 

  2140. 			AUTOTOC = 0
    2141. 

  2141. 		
    2142. 

  2142. 		# protect URLs and emails
    2143. 

  2143. 		while regex['linkmark'].search(line) or \
    2144. 

  2144. 		      regex['link'    ].search(line):
    2145. 

  2145. 			
    2146. 

  2146. 			# try to match plain or named links
    2147. 

  2147. 			match_link  = regex['link'].search(line)
    2148. 

  2148. 			match_named = regex['linkmark'].search(line)
    2149. 

  2149. 			
    2150. 

  2150. 			# define the current match
    2151. 

  2151. 			if match_link and match_named:
    2152. 

  2152. 				# both types found, which is the first?
    2153. 

  2153. 				m = match_link
    2154. 

  2154. 				if match_named.start() < match_link.start():
    2155. 

  2155. 					m = match_named
    2156. 

  2156. 			else:
    2157. 

  2157. 				# just one type found, we're fine
    2158. 

  2158. 				m = match_link or match_named
    2159. 

  2159. 			
    2160. 

  2160. 			# extract link data and apply mask
    2161. 

  2161. 			if m == match_link:              # plain link
    2162. 

  2162. 				link = m.group()
    2163. 

  2163. 				label = ''
    2164. 

  2164. 				link_re = regex['link']
    2165. 

  2165. 			else:                            # named link
    2166. 

  2166. 				link = m.group('link')
    2167. 

  2167. 				label = string.rstrip(m.group('label'))
    2168. 

  2168. 				link_re = regex['linkmark']
    2169. 

  2169. 			line = link_re.sub(self.linkmask,line,1)
    2170. 

  2170. 			
    2171. 

  2171. 			# save link data to the link bank
    2172. 

  2172. 			self.linkbank.append((label, link))
    2173. 

  2173. 		return line
    2174. 

  2174. 	
    2175. 

  2175. 	def undo(self, line):
    2176. 

  2176. 		
    2177. 

  2177. 		# url & email
    2178. 

  2178. 		for label,url in self.linkbank:
    2179. 

  2179. 			link = get_tagged_link(label, url)
    2180. 

  2180. 			line = string.replace(line, self.linkmask, link, 1)
    2181. 

  2181. 		
    2182. 

  2182. 		# expand macros
    2183. 

  2183. 		for macro in self.macrobank:
    2184. 

  2184. 			macro = self.macroman.expand(macro)
    2185. 

  2185. 			line = string.replace(line, self.macromask, macro,1)
    2186. 

  2186. 		
    2187. 

  2187. 		# expand verb
    2188. 

  2188. 		for mono in self.monobank:
    2189. 

  2189. 			open,close = TAGS['fontMonoOpen'],TAGS['fontMonoClose']
    2190. 

  2190. 			tagged = open+mono+close
    2191. 

  2191. 			line = string.replace(line,self.monomask,tagged,1)
    2192. 

  2192. 		
    2193. 

  2193. 		# expand raw
    2194. 

  2194. 		for raw in self.rawbank:
    2195. 

  2195. 			line = string.replace(line,self.rawmask,raw,1)
    2196. 

  2196. 		
    2197. 

  2197. 		return line
    2198. 

  2198. 

  2199. 

  2200. ##############################################################################
    2201. 

  2201. 

  2202. 

  2203. class TitleMaster:
    2204. 

  2204. 	"Title things"
    2205. 

  2205. 	def __init__(self):
    2206. 

  2206. 		self.count = ['',0,0,0,0,0]
    2207. 

  2207. 		self.toc   = []
    2208. 

  2208. 		self.level = 0
    2209. 

  2209. 		self.kind  = ''
    2210. 

  2210. 		self.txt   = ''
    2211. 

  2211. 		self.label = ''
    2212. 

  2212. 		self.tag   = ''
    2213. 

  2213. 		self.tag_hold = []
    2214. 

  2214. 		self.last_level = 0
    2215. 

  2215. 		self.count_id = ''
    2216. 

  2216. 		self.user_labels = {}
    2217. 

  2217. 		self.anchor_count = 0
    2218. 

  2218. 		self.anchor_prefix = 'toc'
    2219. 

  2219. 	
    2220. 

  2220. 	def _open_close_blocks(self):
    2221. 

  2221. 		"Open new title blocks, closing the previous (if any)"
    2222. 

  2222. 		if not rules['titleblocks']: return
    2223. 

  2223. 		tag = ''
    2224. 

  2224. 		last = self.last_level
    2225. 

  2225. 		curr = self.level
    2226. 

  2226. 		
    2227. 

  2227. 		# same level, just close the previous
    2228. 

  2228. 		if curr == last:
    2229. 

  2229. 			tag = TAGS.get('title%dClose'%last)
    2230. 

  2230. 			if tag: self.tag_hold.append(tag)
    2231. 

  2231. 		
    2232. 

  2232. 		# section -> subsection, more depth
    2233. 

  2233. 		while curr > last:
    2234. 

  2234. 			last = last + 1
    2235. 

  2235. 			
    2236. 

  2236. 			# open the new block of subsections
    2237. 

  2237. 			tag = TAGS.get('blockTitle%dOpen'%last)
    2238. 

  2238. 			if tag: self.tag_hold.append(tag)
    2239. 

  2239. 			
    2240. 

  2240. 			# jump from title1 to title3 or more
    2241. 

  2241. 			# fill the gap with an empty section
    2242. 

  2242. 			if curr - last > 0:
    2243. 

  2243. 				tag = TAGS.get('title%dOpen'%last)
    2244. 

  2244. 				tag = regex['x'].sub('', tag)      # del \a
    2245. 

  2245. 				if tag: self.tag_hold.append(tag)
    2246. 

  2246. 		
    2247. 

  2247. 		# section <- subsection, less depth
    2248. 

  2248. 		while curr < last:
    2249. 

  2249. 			# close the current opened subsection
    2250. 

  2250. 			tag = TAGS.get('title%dClose'%last)
    2251. 

  2251. 			if tag: self.tag_hold.append(tag)
    2252. 

  2252. 			
    2253. 

  2253. 			# close the current opened block of subsections
    2254. 

  2254. 			tag = TAGS.get('blockTitle%dClose'%last)
    2255. 

  2255. 			if tag: self.tag_hold.append(tag)
    2256. 

  2256. 			
    2257. 

  2257. 			last = last - 1
    2258. 

  2258. 			
    2259. 

  2259. 			# close the previous section of the same level
    2260. 

  2260. 			# the subsections were under it
    2261. 

  2261. 			if curr == last:
    2262. 

  2262. 				tag = TAGS.get('title%dClose'%last)
    2263. 

  2263. 				if tag: self.tag_hold.append(tag)
    2264. 

  2264. 	
    2265. 

  2265. 	def add(self, line):
    2266. 

  2266. 		"Parses a new title line."
    2267. 

  2267. 		if not line: return
    2268. 

  2268. 		self._set_prop(line)
    2269. 

  2269. 		self._open_close_blocks()
    2270. 

  2270. 		self._set_count_id()
    2271. 

  2271. 		self._set_label()
    2272. 

  2272. 		self._save_toc_info()
    2273. 

  2273. 	
    2274. 

  2274. 	def close_all(self):
    2275. 

  2275. 		"Closes all opened title blocks"
    2276. 

  2276. 		ret = []
    2277. 

  2277. 		ret.extend(self.tag_hold)
    2278. 

  2278. 		while self.level:
    2279. 

  2279. 			tag = TAGS.get('title%dClose'%self.level)
    2280. 

  2280. 			if tag: ret.append(tag)
    2281. 

  2281. 			tag = TAGS.get('blockTitle%dClose'%self.level)
    2282. 

  2282. 			if tag: ret.append(tag)
    2283. 

  2283. 			self.level = self.level - 1
    2284. 

  2284. 		return ret
    2285. 

  2285. 	
    2286. 

  2286. 	def _save_toc_info(self):
    2287. 

  2287. 		"Save TOC info, used by self.dump_marked_toc()"
    2288. 

  2288. 		self.toc.append((self.level, self.count_id,
    2289. 

  2289. 		                 self.txt  , self.label   ))
    2290. 

  2290. 	
    2291. 

  2291. 	def _set_prop(self, line=''):
    2292. 

  2292. 		"Extract info from original line and set data holders."
    2293. 

  2293. 		# detect title type (numbered or not)
    2294. 

  2294. 		id = string.lstrip(line)[0]
    2295. 

  2295. 		if   id == '=': kind = 'title'
    2296. 

  2296. 		elif id == '+': kind = 'numtitle'
    2297. 

  2297. 		else: Error("Unknown Title ID '%s'"%id)
    2298. 

  2298. 		# extract line info
    2299. 

  2299. 		match = regex[kind].search(line)
    2300. 

  2300. 		level = len(match.group('id'))
    2301. 

  2301. 		txt   = string.strip(match.group('txt'))
    2302. 

  2302. 		label = match.group('label')
    2303. 

  2303. 		# parse info & save
    2304. 

  2304. 		if CONF['enum-title']: kind = 'numtitle'  # force
    2305. 

  2305. 		if rules['titleblocks']:
    2306. 

  2306. 			self.tag = TAGS.get('%s%dOpen'%(kind,level)) or \
    2307. 

  2307. 			           TAGS.get('title%dOpen'%level)
    2308. 

  2308. 		else:
    2309. 

  2309. 			self.tag = TAGS.get(kind+`level`) or \
    2310. 

  2310. 			           TAGS.get('title'+`level`)
    2311. 

  2311. 		self.last_level = self.level
    2312. 

  2312. 		self.kind  = kind
    2313. 

  2313. 		self.level = level
    2314. 

  2314. 		self.txt   = txt
    2315. 

  2315. 		self.label = label
    2316. 

  2316. 	
    2317. 

  2317. 	def _set_count_id(self):
    2318. 

  2318. 		"Compose and save the title count identifier (if needed)."
    2319. 

  2319. 		count_id = ''
    2320. 

  2320. 		if self.kind == 'numtitle' and not rules['autonumbertitle']:
    2321. 

  2321. 			# manually increase title count
    2322. 

  2322. 			self.count[self.level] = self.count[self.level] +1
    2323. 

  2323. 			# reset sublevels count (if any)
    2324. 

  2324. 			max_levels = len(self.count)
    2325. 

  2325. 			if self.level < max_levels-1:
    2326. 

  2326. 				for i in range(self.level+1, max_levels):
    2327. 

  2327. 					self.count[i] = 0
    2328. 

  2328. 			# compose count id from hierarchy
    2329. 

  2329. 			for i in range(self.level):
    2330. 

  2330. 				count_id= "%s%d."%(count_id, self.count[i+1])
    2331. 

  2331. 		self.count_id = count_id
    2332. 

  2332. 	
    2333. 

  2333. 	def _set_label(self):
    2334. 

  2334. 		"Compose and save title label, used by anchors."
    2335. 

  2335. 		# remove invalid chars from label set by user
    2336. 

  2336. 		self.label = re.sub('[^A-Za-z0-9_-]', '', self.label or '')
    2337. 

  2337. 		# generate name as 15 first :alnum: chars
    2338. 

  2338. 		#TODO how to translate safely accented chars to plain?
    2339. 

  2339. 		#self.label = re.sub('[^A-Za-z0-9]', '', self.txt)[:15]
    2340. 

  2340. 		# 'tocN' label - sequential count, ignoring 'toc-level'
    2341. 

  2341. 		#self.label = self.anchor_prefix + str(len(self.toc)+1)
    2342. 

  2342. 	
    2343. 

  2343. 	def _get_tagged_anchor(self):
    2344. 

  2344. 		"Return anchor if user defined a label, or TOC is on."
    2345. 

  2345. 		ret = ''
    2346. 

  2346. 		label = self.label
    2347. 

  2347. 		if CONF['toc'] and self.level <= CONF['toc-level']:
    2348. 

  2348. 			# this count is needed bcos self.toc stores all
    2349. 

  2349. 			# titles, regardless of the 'toc-level' setting,
    2350. 

  2350. 			# so we can't use self.toc lenght to number anchors
    2351. 

  2351. 			self.anchor_count = self.anchor_count + 1
    2352. 

  2352. 			# autonumber label (if needed)
    2353. 

  2353. 			label = label or '%s%s'%(
    2354. 

  2354. 			        self.anchor_prefix, self.anchor_count)
    2355. 

  2355. 		if label and TAGS['anchor']:
    2356. 

  2356. 			ret = regex['x'].sub(label,TAGS['anchor'])
    2357. 

  2357. 		return ret
    2358. 

  2358. 	
    2359. 

  2359. 	def _get_full_title_text(self):
    2360. 

  2360. 		"Returns the full title contents, already escaped."
    2361. 

  2361. 		ret = self.txt
    2362. 

  2362. 		# insert count_id (if any) before text
    2363. 

  2363. 		if self.count_id:
    2364. 

  2364. 			ret = '%s %s'%(self.count_id, ret)
    2365. 

  2365. 		# escape specials
    2366. 

  2366. 		ret = doEscape(TARGET, ret)
    2367. 

  2367. 		# same targets needs final escapes on title lines
    2368. 

  2368. 		# it's here because there is a 'continue' after title
    2369. 

  2369. 		if rules['finalescapetitle']:
    2370. 

  2370. 			ret = doFinalEscape(TARGET, ret)
    2371. 

  2371. 		return ret
    2372. 

  2372. 	
    2373. 

  2373. 	def get(self):
    2374. 

  2374. 		"Returns the tagged title as a list."
    2375. 

  2375. 		ret = []
    2376. 

  2376. 		
    2377. 

  2377. 		# maybe some anchoring before?
    2378. 

  2378. 		anchor = self._get_tagged_anchor()
    2379. 

  2379. 		self.tag = regex['_anchor'].sub(anchor, self.tag)
    2380. 

  2380. 		
    2381. 

  2381. 		### compose & escape title text (TOC uses unescaped)
    2382. 

  2382. 		full_title = self._get_full_title_text()
    2383. 

  2383. 		
    2384. 

  2384. 		# close previous section area
    2385. 

  2385. 		ret.extend(self.tag_hold)
    2386. 

  2386. 		self.tag_hold = []
    2387. 

  2387. 		 
    2388. 

  2388. 		# finish title, adding "underline" on TXT target
    2389. 

  2389. 		tagged = regex['x'].sub(full_title, self.tag)
    2390. 

  2390. 		if TARGET == 'txt':
    2391. 

  2391. 			ret.append('') # blank line before
    2392. 

  2392. 			ret.append(tagged)
    2393. 

  2393. 			ret.append(regex['x'].sub('='*len(full_title),self.tag))
    2394. 

  2394. 			ret.append('') # blank line after
    2395. 

  2395. 		else:
    2396. 

  2396. 			ret.append(tagged)
    2397. 

  2397. 		return ret
    2398. 

  2398. 	
    2399. 

  2399. 	def dump_marked_toc(self, max_level=99):
    2400. 

  2400. 		"Dumps all toc itens as a valid t2t markup list"
    2401. 

  2401. 		#TODO maybe use quote+linebreaks instead lists
    2402. 

  2402. 		ret = []
    2403. 

  2403. 		toc_count = 1
    2404. 

  2404. 		for level, count_id, txt, label in self.toc:
    2405. 

  2405. 			if level > max_level: continue   # ignore
    2406. 

  2406. 			indent = '  '*level
    2407. 

  2407. 			id_txt = string.lstrip('%s %s'%(count_id, txt))
    2408. 

  2408. 			label = label or self.anchor_prefix+`toc_count`
    2409. 

  2409. 			toc_count = toc_count + 1
    2410. 

  2410. 			# TOC will have links
    2411. 

  2411. 			if TAGS['anchor']:
    2412. 

  2412. 				# TOC is more readable with master topics
    2413. 

  2413. 				# not linked at number. This is a stoled
    2414. 

  2414. 				# idea from Windows .CHM help files
    2415. 

  2415. 				if CONF['enum-title'] and level == 1:
    2416. 

  2416. 					tocitem = '%s+ [""%s"" #%s]'%(
    2417. 

  2417. 					          indent, txt, label)
    2418. 

  2418. 				else:
    2419. 

  2419. 					tocitem = '%s- [""%s"" #%s]'%(
    2420. 

  2420. 					          indent, id_txt, label)
    2421. 

  2421. 			# no links on TOC, just text
    2422. 

  2422. 			else:
    2423. 

  2423. 				# man don't reformat TOC lines, cool!
    2424. 

  2424. 				if TARGET in ['txt', 'man']:
    2425. 

  2425. 					tocitem = '%s""%s""' %(
    2426. 

  2426. 					          indent, id_txt)
    2427. 

  2427. 				else:
    2428. 

  2428. 					tocitem = '%s- ""%s""'%(
    2429. 

  2429. 					          indent, id_txt)
    2430. 

  2430. 			ret.append(tocitem)
    2431. 

  2431. 		return ret
    2432. 

  2432. 

  2433. 

  2434. ##############################################################################
    2435. 

  2435. 

  2436. #TODO check all this table mess
    2437. 

  2437. # trata linhas TABLE, com as prop do parse_row
    2438. 

  2438. # o metodo table() do BLOCK xunxa e troca as celulas pelas parseadas
    2439. 

  2439. class TableMaster:
    2440. 

  2440. 	def __init__(self, line=''):
    2441. 

  2441. 		self.rows      = []
    2442. 

  2442. 		self.border    = 0
    2443. 

  2443. 		self.align     = 'Left'
    2444. 

  2444. 		self.cellalign = []
    2445. 

  2445. 		if line:
    2446. 

  2446. 			prop = self.parse_row(line)
    2447. 

  2447. 			self.border    = prop['border']
    2448. 

  2448. 			self.align     = prop['align']
    2449. 

  2449. 			self.cellalign = prop['cellalign']
    2450. 

  2450. 	
    2451. 

  2451. 	def _get_open_tag(self):
    2452. 

  2452. 		topen     = TAGS['tableOpen']
    2453. 

  2453. 		tborder   = TAGS['tableBorder']
    2454. 

  2454. 		talign    = TAGS['tableAlign'+self.align]
    2455. 

  2455. 		calignsep = TAGS['tableColAlignSep']
    2456. 

  2456. 		calign    = ''
    2457. 

  2457. 		
    2458. 

  2458. 		# the first line defines if table has border or not
    2459. 

  2459. 		if not self.border: tborder = ''
    2460. 

  2460. 		# set the columns alignment
    2461. 

  2461. 		if rules['tablecellaligntype'] == 'column':
    2462. 

  2462. 			calign = map(lambda x: TAGS['tableColAlign%s'%x],
    2463. 

  2463. 			             self.cellalign)
    2464. 

  2464. 			calign = string.join(calign, calignsep)
    2465. 

  2465. 		# align full table, set border and Column align (if any)
    2466. 

  2466. 		topen = regex['_tableAlign'   ].sub(talign , topen)
    2467. 

  2467. 		topen = regex['_tableBorder'  ].sub(tborder, topen)
    2468. 

  2468. 		topen = regex['_tableColAlign'].sub(calign , topen)
    2469. 

  2469. 		# tex table spec, border or not: {|l|c|r|} , {lcr}
    2470. 

  2470. 		if calignsep and not self.border:
    2471. 

  2471. 			# remove cell align separator
    2472. 

  2472. 			topen = string.replace(topen, calignsep, '')
    2473. 

  2473. 		return topen
    2474. 

  2474. 	
    2475. 

  2475. 	def _get_cell_align(self, cells):
    2476. 

  2476. 		ret = []
    2477. 

  2477. 		for cell in cells:
    2478. 

  2478. 			align = 'Left'
    2479. 

  2479. 			if string.strip(cell):
    2480. 

  2480. 				if cell[0] == ' ' and cell[-1] == ' ':
    2481. 

  2481. 					align = 'Center'
    2482. 

  2482. 				elif cell[0] == ' ':
    2483. 

  2483. 					align = 'Right'
    2484. 

  2484. 			ret.append(align)
    2485. 

  2485. 		return ret
    2486. 

  2486. 	
    2487. 

  2487. 	def _tag_cells(self, rowdata):
    2488. 

  2488. 		row = []
    2489. 

  2489. 		cells  = rowdata['cells']
    2490. 

  2490. 		open   = TAGS['tableCellOpen']
    2491. 

  2491. 		close  = TAGS['tableCellClose']
    2492. 

  2492. 		sep    = TAGS['tableCellSep']
    2493. 

  2493. 		calign = map(lambda x: TAGS['tableCellAlign'+x],
    2494. 

  2494. 		             rowdata['cellalign'])
    2495. 

  2495. 		
    2496. 

  2496. 		# maybe is it a title row?
    2497. 

  2497. 		if rowdata['title']:
    2498. 

  2498. 			open  = TAGS['tableTitleCellOpen']  or open
    2499. 

  2499. 			close = TAGS['tableTitleCellClose'] or close
    2500. 

  2500. 			sep   = TAGS['tableTitleCellSep']   or sep
    2501. 

  2501. 		
    2502. 

  2502. 		# should we break the line on *each* table cell?
    2503. 

  2503. 		if rules['breaktablecell']: close = close+'\n'
    2504. 

  2504. 		
    2505. 

  2505. 		# cells pre processing
    2506. 

  2506. 		if rules['tablecellstrip']:
    2507. 

  2507. 			cells = map(lambda x: string.strip(x), cells)
    2508. 

  2508. 		if rowdata['title'] and rules['tabletitlerowinbold']:
    2509. 

  2509. 			cells = map(lambda x: enclose_me('fontBold',x), cells)
    2510. 

  2510. 		
    2511. 

  2511. 		# add cell BEGIN/END tags
    2512. 

  2512. 		for cell in cells:
    2513. 

  2513. 			# insert cell align into open tag (if cell is alignable)
    2514. 

  2514. 			if rules['tablecellaligntype'] == 'cell':
    2515. 

  2515. 				copen = string.replace(open,'\a',calign.pop(0))
    2516. 

  2516. 			else:
    2517. 

  2517. 				copen = open
    2518. 

  2518. 			row.append(copen + cell + close)
    2519. 

  2519. 		
    2520. 

  2520. 		# maybe there are cell separators?
    2521. 

  2521. 		return string.join(row, sep)
    2522. 

  2522. 	
    2523. 

  2523. 	def add_row(self, cells):
    2524. 

  2524. 		self.rows.append(cells)
    2525. 

  2525. 	
    2526. 

  2526. 	def parse_row(self, line):
    2527. 

  2527. 		# default table proprierties
    2528. 

  2528. 		ret = {'border':0,'title':0,'align':'Left',
    2529. 

  2529. 		       'cells':[],'cellalign':[]}
    2530. 

  2530. 		# detect table align (and remove spaces mark)
    2531. 

  2531. 		if line[0] == ' ': ret['align'] = 'Center'
    2532. 

  2532. 		line = string.lstrip(line)
    2533. 

  2533. 		# detect title mark
    2534. 

  2534. 		if line[1] == '|': ret['title'] = 1
    2535. 

  2535. 		# delete trailing spaces after last cell border
    2536. 

  2536. 		line = re.sub('\|\s*$','|', line)
    2537. 

  2537. 		# detect (and delete) border mark (and leading space)
    2538. 

  2538. 		if line[-1] == '|': ret['border'] = 1 ; line = line[:-2]
    2539. 

  2539. 		# delete table mark
    2540. 

  2540. 		line = regex['table'].sub('', line)
    2541. 

  2541. 		# split cells
    2542. 

  2542. 		ret['cells'] = string.split(line, ' | ')
    2543. 

  2543. 		# find cells align
    2544. 

  2544. 		ret['cellalign'] = self._get_cell_align(ret['cells'])
    2545. 

  2545. 		
    2546. 

  2546. 		Debug('Table Prop: %s' % ret, 7)
    2547. 

  2547. 		return ret
    2548. 

  2548. 	
    2549. 

  2549. 	def dump(self):
    2550. 

  2550. 		open  = self._get_open_tag()
    2551. 

  2551. 		rows  = self.rows
    2552. 

  2552. 		close = TAGS['tableClose']
    2553. 

  2553. 		
    2554. 

  2554. 		rowopen     = TAGS['tableRowOpen']
    2555. 

  2555. 		rowclose    = TAGS['tableRowClose']
    2556. 

  2556. 		rowsep      = TAGS['tableRowSep']
    2557. 

  2557. 		titrowopen  = TAGS['tableTitleRowOpen']  or rowopen
    2558. 

  2558. 		titrowclose = TAGS['tableTitleRowClose'] or rowclose
    2559. 

  2559. 		
    2560. 

  2560. 		if rules['breaktablelineopen']:
    2561. 

  2561. 			rowopen = rowopen + '\n'
    2562. 

  2562. 			titrowopen = titrowopen + '\n'
    2563. 

  2563. 		
    2564. 

  2564. 		# tex gotchas
    2565. 

  2565. 		if TARGET == 'tex':
    2566. 

  2566. 			if not self.border:
    2567. 

  2567. 				rowopen = titrowopen = ''
    2568. 

  2568. 			else:
    2569. 

  2569. 				close = rowopen + close
    2570. 

  2570. 		
    2571. 

  2571. 		# now we tag all the table cells on each row
    2572. 

  2572. 		#tagged_cells = map(lambda x: self._tag_cells(x), rows) #!py15
    2573. 

  2573. 		tagged_cells = []
    2574. 

  2574. 		for cell in rows: tagged_cells.append(self._tag_cells(cell))
    2575. 

  2575. 		
    2576. 

  2576. 		# add row separator tags between lines
    2577. 

  2577. 		tagged_rows = []
    2578. 

  2578. 		if rowsep:
    2579. 

  2579. 			#!py15
    2580. 

  2580. 			#tagged_rows = map(lambda x:x+rowsep, tagged_cells)
    2581. 

  2581. 			for cell in tagged_cells:
    2582. 

  2582. 				tagged_rows.append(cell+rowsep)
    2583. 

  2583. 			# remove last rowsep, because the table is over
    2584. 

  2584. 			tagged_rows[-1] = string.replace(
    2585. 

  2585. 			                  tagged_rows[-1], rowsep, '')
    2586. 

  2586. 		# add row BEGIN/END tags for each line
    2587. 

  2587. 		else:
    2588. 

  2588. 			for rowdata in rows:
    2589. 

  2589. 				if rowdata['title']:
    2590. 

  2590. 					o,c = titrowopen, titrowclose
    2591. 

  2591. 				else:
    2592. 

  2592. 					o,c = rowopen, rowclose
    2593. 

  2593. 				row = tagged_cells.pop(0)
    2594. 

  2594. 				tagged_rows.append(o + row + c)
    2595. 

  2595. 		
    2596. 

  2596. 		fulltable = [open] + tagged_rows + [close]
    2597. 

  2597. 		
    2598. 

  2598. 		if rules['blankendtable']: fulltable.append('')
    2599. 

  2599. 		return fulltable
    2600. 

  2600. 

  2601. 

  2602. ##############################################################################
    2603. 

  2603. 

  2604. 

  2605. class BlockMaster:
    2606. 

  2606. 	"TIP: use blockin/out to add/del holders"
    2607. 

  2607. 	def __init__(self):
    2608. 

  2608. 		self.BLK = []
    2609. 

  2609. 		self.HLD = []
    2610. 

  2610. 		self.PRP = []
    2611. 

  2611. 		self.depth = 0
    2612. 

  2612. 		self.last = ''
    2613. 

  2613. 		self.tableparser = None
    2614. 

  2614. 		self.contains = {
    2615. 

  2615. 		  'para'    :['passthru','raw'],
    2616. 

  2616. 		  'verb'    :[],
    2617. 

  2617. 		  'table'   :[],
    2618. 

  2618. 		  'raw'     :[],
    2619. 

  2619. 		  'passthru':[],
    2620. 

  2620. 		  'quote'   :['quote','passthru','raw'],
    2621. 

  2621. 		  'list'    :['list' ,'numlist' ,'deflist','para','verb',
    2622. 

  2622. 		              'raw'  ,'passthru'],
    2623. 

  2623. 		  'numlist' :['list' ,'numlist' ,'deflist','para','verb',
    2624. 

  2624. 		              'raw'  ,'passthru'],
    2625. 

  2625. 		  'deflist' :['list' ,'numlist' ,'deflist','para','verb',
    2626. 

  2626. 		              'raw'  ,'passthru']
    2627. 

  2627. 		}
    2628. 

  2628. 		self.allblocks = self.contains.keys()
    2629. 

  2629. 	
    2630. 

  2630. 	def block(self):
    2631. 

  2631. 		if not self.BLK: return ''
    2632. 

  2632. 		return self.BLK[-1]
    2633. 

  2633. 	
    2634. 

  2634. 	def isblock(self, name=''):
    2635. 

  2635. 		return self.block() == name
    2636. 

  2636. 	
    2637. 

  2637. 	def prop(self, key):
    2638. 

  2638. 		if not self.PRP: return ''
    2639. 

  2639. 		return self.PRP[-1].get(key) or ''
    2640. 

  2640. 	
    2641. 

  2641. 	def propset(self, key, val):
    2642. 

  2642. 		self.PRP[-1][key] = val
    2643. 

  2643. 		#Debug('BLOCK prop ++: %s->%s'%(key,repr(val)), 1)
    2644. 

  2644. 		#Debug('BLOCK props: %s'%(repr(self.PRP)), 1)
    2645. 

  2645. 	
    2646. 

  2646. 	def hold(self):
    2647. 

  2647. 		if not self.HLD: return []
    2648. 

  2648. 		return self.HLD[-1]
    2649. 

  2649. 	
    2650. 

  2650. 	def holdadd(self, line):
    2651. 

  2651. 		if self.block()[-4:] == 'list': line = [line]
    2652. 

  2652. 		self.HLD[-1].append(line)
    2653. 

  2653. 		Debug('HOLD add: %s'%repr(line), 4)
    2654. 

  2654. 		Debug('FULL HOLD: %s'%self.HLD, 4)
    2655. 

  2655. 	
    2656. 

  2656. 	def holdaddsub(self, line):
    2657. 

  2657. 		self.HLD[-1][-1].append(line)
    2658. 

  2658. 		Debug('HOLD addsub: %s'%repr(line), 4)
    2659. 

  2659. 		Debug('FULL HOLD: %s'%self.HLD, 4)
    2660. 

  2660. 	
    2661. 

  2661. 	def holdextend(self, lines):
    2662. 

  2662. 		if self.block()[-4:] == 'list': lines = [lines]
    2663. 

  2663. 		self.HLD[-1].extend(lines)
    2664. 

  2664. 		Debug('HOLD extend: %s'%repr(lines), 4)
    2665. 

  2665. 		Debug('FULL HOLD: %s'%self.HLD, 4)
    2666. 

  2666. 	
    2667. 

  2667. 	def blockin(self, block):
    2668. 

  2668. 		ret = []
    2669. 

  2669. 		if block not in self.allblocks:
    2670. 

  2670. 			Error("Invalid block '%s'"%block)
    2671. 

  2671. 		# first, let's close other possible open blocks
    2672. 

  2672. 		while self.block() and block not in self.contains[self.block()]:
    2673. 

  2673. 			ret.extend(self.blockout())
    2674. 

  2674. 		# now we can gladly add this new one
    2675. 

  2675. 		self.BLK.append(block)
    2676. 

  2676. 		self.HLD.append([])
    2677. 

  2677. 		self.PRP.append({})
    2678. 

  2678. 		if block == 'table': self.tableparser = TableMaster()
    2679. 

  2679. 		# deeper and deeper
    2680. 

  2680. 		self.depth = len(self.BLK)
    2681. 

  2681. 		Debug('block ++ (%s): %s' % (block,self.BLK), 3)
    2682. 

  2682. 		return ret
    2683. 

  2683. 	
    2684. 

  2684. 	def blockout(self):
    2685. 

  2685. 		if not self.BLK: Error('No block to pop')
    2686. 

  2686. 		self.last = self.BLK.pop()
    2687. 

  2687. 		tagged = getattr(self, self.last)()
    2688. 

  2688. 		parsed = self.HLD.pop()
    2689. 

  2689. 		self.PRP.pop()
    2690. 

  2690. 		self.depth = len(self.BLK)
    2691. 

  2691. 		if self.last == 'table': del self.tableparser
    2692. 

  2692. 		# inserting a nested block into mother
    2693. 

  2693. 		if self.block():
    2694. 

  2694. 			if self.block()[-4:] == 'list':
    2695. 

  2695. 				self.HLD[-1][-1].append(tagged)
    2696. 

  2696. 			else:
    2697. 

  2697. 				self.HLD[-1].append(tagged)
    2698. 

  2698. 			tagged = []   # reset. mother will have it all
    2699. 

  2699. 		Debug('block -- (%s): %s' % (self.last,self.BLK), 3)
    2700. 

  2700. 		Debug('RELEASED (%s): %s' % (self.last,parsed), 3)
    2701. 

  2701. 		if tagged: Debug('BLOCK: %s'%tagged, 6)
    2702. 

  2702. 		return tagged
    2703. 

  2703. 	
    2704. 

  2704. 	def _last_escapes(self, line):
    2705. 

  2705. 		return doFinalEscape(TARGET, line)
    2706. 

  2706. 	
    2707. 

  2707. 	def _get_escaped_hold(self):
    2708. 

  2708. 		ret = []
    2709. 

  2709. 		for line in self.hold():
    2710. 

  2710. 			linetype = type(line)
    2711. 

  2711. 			if linetype == type(''):
    2712. 

  2712. 				ret.append(self._last_escapes(line))
    2713. 

  2713. 			elif linetype == type([]):
    2714. 

  2714. 				ret.extend(line)
    2715. 

  2715. 			else:
    2716. 

  2716. 				Error("BlockMaster: Unknown HOLD item type:"
    2717. 

  2717. 				      " %s"%linetype)
    2718. 

  2718. 		return ret
    2719. 

  2719. 	
    2720. 

  2720. 	def _remove_twoblanks(self, lastitem):
    2721. 

  2721. 		if len(lastitem) > 1 and lastitem[-2:] == ['','']:
    2722. 

  2722. 			return lastitem[:-2]
    2723. 

  2723. 		return lastitem
    2724. 

  2724. 	
    2725. 

  2725. 	def passthru(self):
    2726. 

  2726. 		return self.hold()
    2727. 

  2727. 	
    2728. 

  2728. 	def raw(self):
    2729. 

  2729. 		lines = self.hold()
    2730. 

  2730. 		return map(lambda x: doEscape(TARGET, x), lines)
    2731. 

  2731. 	
    2732. 

  2732. 	def para(self):
    2733. 

  2733. 		tagged = []
    2734. 

  2734. 		open  = TAGS['paragraphOpen']
    2735. 

  2735. 		close = TAGS['paragraphClose']
    2736. 

  2736. 		lines = self._get_escaped_hold()
    2737. 

  2737. 		# open (or not) paragraph
    2738. 

  2738. 		if not open+close and self.last == 'para':
    2739. 

  2739. 			pass # avoids multiple blank lines
    2740. 

  2740. 		else:
    2741. 

  2741. 			tagged.append(open)
    2742. 

  2742. 		# pagemaker likes a paragraph as a single long line
    2743. 

  2743. 		if rules['onelinepara']:
    2744. 

  2744. 			tagged.append(string.join(lines,' '))
    2745. 

  2745. 		# others are normal :)
    2746. 

  2746. 		else:
    2747. 

  2747. 			tagged.extend(lines)
    2748. 

  2748. 		tagged.append(close)
    2749. 

  2749. 		
    2750. 

  2750. 		# very very very very very very very very very UGLY fix
    2751. 

  2751. 		# needed because <center> can't appear inside <p>
    2752. 

  2752. 		try:
    2753. 

  2753. 			if len(lines) == 1 and \
    2754. 

  2754. 			   TARGET in ('html', 'xhtml') and \
    2755. 

  2755. 			   re.match('^\s*<center>.*</center>\s*$', lines[0]):
    2756. 

  2756. 				tagged = [lines[0]]
    2757. 

  2757. 		except: pass
    2758. 

  2758. 		
    2759. 

  2759. 		return tagged
    2760. 

  2760. 	
    2761. 

  2761. 	def verb(self):
    2762. 

  2762. 		"Verbatim lines are not masked, so there's no need to unmask"
    2763. 

  2763. 		tagged = []
    2764. 

  2764. 		tagged.append(TAGS['blockVerbOpen'])
    2765. 

  2765. 		for line in self.hold():
    2766. 

  2766. 			if self.prop('mapped') == 'table':
    2767. 

  2767. 				line = MacroMaster().expand(line)
    2768. 

  2768. 			if not rules['verbblocknotescaped']:
    2769. 

  2769. 				line = doEscape(TARGET,line)
    2770. 

  2770. 			if rules['indentverbblock']:
    2771. 

  2771. 				line = '  '+line
    2772. 

  2772. 			if rules['verbblockfinalescape']:
    2773. 

  2773. 				line = doFinalEscape(TARGET, line)
    2774. 

  2774. 			tagged.append(line)
    2775. 

  2775. 		#TODO maybe use if not TAGS['blockVerbClose']
    2776. 

  2776. 		if TARGET != 'pm6':
    2777. 

  2777. 			tagged.append(TAGS['blockVerbClose'])
    2778. 

  2778. 		return tagged
    2779. 

  2779. 	
    2780. 

  2780. 	def table(self):
    2781. 

  2781. 		# rewrite all table cells by the unmasked and escaped data
    2782. 

  2782. 		lines = self._get_escaped_hold()
    2783. 

  2783. 		for i in range(len(lines)):
    2784. 

  2784. 			cells = string.split(lines[i], SEPARATOR)
    2785. 

  2785. 			self.tableparser.rows[i]['cells'] = cells
    2786. 

  2786. 		
    2787. 

  2787. 		return self.tableparser.dump()
    2788. 

  2788. 	
    2789. 

  2789. 	def quote(self):
    2790. 

  2790. 		tagged = []
    2791. 

  2791. 		myre   = regex['quote']
    2792. 

  2792. 		open   = TAGS['blockQuoteOpen']            # block based
    2793. 

  2793. 		close  = TAGS['blockQuoteClose']
    2794. 

  2794. 		qline  = TAGS['blockQuoteLine']            # line based
    2795. 

  2795. 		indent = tagindent = '\t'*self.depth
    2796. 

  2796. 		if rules['tagnotindentable']: tagindent = ''
    2797. 

  2797. 		if not rules['keepquoteindent']: indent = ''
    2798. 

  2798. 		
    2799. 

  2799. 		if open: tagged.append(tagindent+open)     # open block
    2800. 

  2800. 		for item in self.hold():
    2801. 

  2801. 			if type(item) == type([]):
    2802. 

  2802. 				tagged.extend(item)        # subquotes
    2803. 

  2803. 			else:
    2804. 

  2804. 				item = myre.sub('', item)  # del TABs
    2805. 

  2805. 				if rules['barinsidequote']:
    2806. 

  2806. 					item = get_tagged_bar(item)
    2807. 

  2807. 				item = self._last_escapes(item)
    2808. 

  2808. 				item = qline*self.depth + item
    2809. 

  2809. 				tagged.append(indent+item) # quote line
    2810. 

  2810. 		if close: tagged.append(tagindent+close)   # close block
    2811. 

  2811. 		return tagged
    2812. 

  2812. 	
    2813. 

  2813. 	def deflist(self): return self.list('deflist')
    2814. 

  2814. 	def numlist(self): return self.list('numlist')
    2815. 

  2815. 	def list(self, name='list'):
    2816. 

  2816. 		tagged    = []
    2817. 

  2817. 		items     = self.hold()
    2818. 

  2818. 		indent    = self.prop('indent')
    2819. 

  2819. 		tagindent = indent
    2820. 

  2820. 		listopen  = TAGS.get(name+'Open')
    2821. 

  2821. 		listclose = TAGS.get(name+'Close')
    2822. 

  2822. 		listline  = TAGS.get(name+'ItemLine')
    2823. 

  2823. 		itemcount = 0
    2824. 

  2824. 		if rules['tagnotindentable']: tagindent = ''
    2825. 

  2825. 		if not rules['keeplistindent']: indent = ''
    2826. 

  2826. 		
    2827. 

  2827. 		if name == 'deflist':
    2828. 

  2828. 			itemopen  = TAGS[name+'Item1Open']
    2829. 

  2829. 			itemclose = TAGS[name+'Item2Close']
    2830. 

  2830. 			itemsep   = TAGS[name+'Item1Close']+\
    2831. 

  2831. 			            TAGS[name+'Item2Open']
    2832. 

  2832. 		else:
    2833. 

  2833. 			itemopen  = TAGS[name+'ItemOpen']
    2834. 

  2834. 			itemclose = TAGS[name+'ItemClose']
    2835. 

  2835. 			itemsep   = ''
    2836. 

  2836. 		
    2837. 

  2837. 		# ItemLine: number of leading chars identifies list depth
    2838. 

  2838. 		if listline:
    2839. 

  2839. 			itemopen  = listline*self.depth
    2840. 

  2840. 			# dirty fix for mgp
    2841. 

  2841. 			if name == 'numlist': itemopen = itemopen + '\a. '
    2842. 

  2842. 		
    2843. 

  2843. 		# remove two-blanks from list ending mark, to avoid <p>
    2844. 

  2844. 		items[-1] = self._remove_twoblanks(items[-1])
    2845. 

  2845. 		
    2846. 

  2846. 		# open list (not nestable lists are only opened at mother)
    2847. 

  2847. 		if listopen and not \
    2848. 

  2848. 		   (rules['listnotnested'] and BLOCK.depth != 1):
    2849. 

  2849. 			tagged.append(tagindent+listopen)
    2850. 

  2850. 		
    2851. 

  2851. 		# tag each list item (multine items)
    2852. 

  2852. 		itemopenorig = itemopen
    2853. 

  2853. 		for item in items:
    2854. 

  2854. 			
    2855. 

  2855. 			# add "manual" item count for noautonum targets
    2856. 

  2856. 			itemcount = itemcount + 1
    2857. 

  2857. 			if name == 'numlist' and not rules['autonumberlist']:
    2858. 

  2858. 				n = str(itemcount)
    2859. 

  2859. 				itemopen = regex['x'].sub(n, itemopenorig)
    2860. 

  2860. 				del n
    2861. 

  2861. 			
    2862. 

  2862. 			item[0] = self._last_escapes(item[0])
    2863. 

  2863. 			if name == 'deflist':
    2864. 

  2864. 				term, rest = string.split(item[0],SEPARATOR,1)
    2865. 

  2865. 				item[0] = rest
    2866. 

  2866. 				if not item[0]: del item[0]      # to avoid <p>
    2867. 

  2867. 				tagged.append(tagindent+itemopen+term+itemsep)
    2868. 

  2868. 			else:
    2869. 

  2869. 				fullitem = tagindent+itemopen
    2870. 

  2870. 				tagged.append(string.replace(
    2871. 

  2871. 				              item[0], SEPARATOR, fullitem))
    2872. 

  2872. 				del item[0]
    2873. 

  2873. 			
    2874. 

  2874. 			# process next lines for this item (if any)
    2875. 

  2875. 			for line in item:
    2876. 

  2876. 				if type(line) == type([]): # sublist inside
    2877. 

  2877. 					tagged.extend(line)
    2878. 

  2878. 				else:
    2879. 

  2879. 					line = self._last_escapes(line)
    2880. 

  2880. 					# blank lines turns to <p>
    2881. 

  2881. 					if not line and rules['parainsidelist']:
    2882. 

  2882. 						line = string.rstrip(indent   +\
    2883. 

  2883. 						         TAGS['paragraphOpen']+\
    2884. 

  2884. 						         TAGS['paragraphClose'])
    2885. 

  2885. 					if not rules['keeplistindent']:
    2886. 

  2886. 						line = string.lstrip(line)
    2887. 

  2887. 					tagged.append(line)
    2888. 

  2888. 			
    2889. 

  2889. 			# close item (if needed)
    2890. 

  2890. 			if itemclose: tagged.append(tagindent+itemclose)
    2891. 

  2891. 		
    2892. 

  2892. 		# close list (not nestable lists are only closed at mother)
    2893. 

  2893. 		if listclose and not \
    2894. 

  2894. 		   (rules['listnotnested'] and BLOCK.depth != 1):
    2895. 

  2895. 			tagged.append(tagindent+listclose)
    2896. 

  2896. 		
    2897. 

  2897. 		if rules['blankendmotherlist'] and BLOCK.depth == 1:
    2898. 

  2898. 			tagged.append('')
    2899. 

  2899. 		
    2900. 

  2900. 		return tagged
    2901. 

  2901. 

  2902. 

  2903. ##############################################################################
    2904. 

  2904. 

  2905. 

  2906. class MacroMaster:
    2907. 

  2907. 	def __init__(self, config={}):
    2908. 

  2908. 		self.name     = ''
    2909. 

  2909. 		self.config   = config or CONF
    2910. 

  2910. 		self.infile   = self.config['sourcefile']
    2911. 

  2911. 		self.outfile  = self.config['outfile']
    2912. 

  2912. 		self.currdate = time.localtime(time.time())
    2913. 

  2913. 		self.rgx      = regex.get('macros') or getRegexes()['macros']
    2914. 

  2914. 		self.fileinfo = { 'infile': None, 'outfile': None }
    2915. 

  2915. 		self.dft_fmt  = MACROS
    2916. 

  2916. 	
    2917. 

  2917. 	def walk_file_format(self, fmt):
    2918. 

  2918. 		"Walks the %%{in/out}file format string, expanding the % flags"
    2919. 

  2919. 		i = 0; ret = ''                                 # counter/hold
    2920. 

  2920. 		while i < len(fmt):                             # char by char
    2921. 

  2921. 			c = fmt[i]; i = i + 1
    2922. 

  2922. 			if c == '%':                            # hot char!
    2923. 

  2923. 				if i == len(fmt):               # % at the end
    2924. 

  2924. 					ret = ret + c
    2925. 

  2925. 					break
    2926. 

  2926. 				c = fmt[i]; i = i + 1           # read next
    2927. 

  2927. 				ret = ret + self.expand_file_flag(c)
    2928. 

  2928. 			else:
    2929. 

  2929. 				ret = ret +c                    # common char
    2930. 

  2930. 		return ret
    2931. 

  2931. 	
    2932. 

  2932. 	def expand_file_flag(self, flag):
    2933. 

  2933. 		"%f: filename          %F: filename (w/o extension)"
    2934. 

  2934. 		"%d: dirname           %D: dirname (only parent dir)"
    2935. 

  2935. 		"%p: file path         %e: extension"
    2936. 

  2936. 		info = self.fileinfo[self.name]           # get dict
    2937. 

  2937. 		if   flag == '%': x = '%'                 # %% -> %
    2938. 

  2938. 		elif flag == 'f': x = info['name']
    2939. 

  2939. 		elif flag == 'F': x = re.sub('\.[^.]*$','',info['name'])
    2940. 

  2940. 		elif flag == 'd': x = info['dir']
    2941. 

  2941. 		elif flag == 'D': x = os.path.split(info['dir'])[-1]
    2942. 

  2942. 		elif flag == 'p': x = info['path']
    2943. 

  2943. 		elif flag == 'e': x = re.search('.(\.([^.]+))?$',info['name']
    2944. 

  2944. 		                                ).group(2) or ''
    2945. 

  2945. 		#TODO simplier way for %e ?
    2946. 

  2946. 		else            : x = '%'+flag            # false alarm
    2947. 

  2947. 		return x
    2948. 

  2948. 	
    2949. 

  2949. 	def set_file_info(self, macroname):
    2950. 

  2950. 		if self.fileinfo.get(macroname): return   # already done
    2951. 

  2951. 		file = getattr(self, self.name)           # self.infile
    2952. 

  2952. 		if file == STDOUT:
    2953. 

  2953. 			dir = ''; path = name = STDOUT
    2954. 

  2954. 		else:
    2955. 

  2955. 			path = os.path.abspath(file)
    2956. 

  2956. 			dir  = os.path.dirname(path)
    2957. 

  2957. 			name = os.path.basename(path)
    2958. 

  2958. 		self.fileinfo[macroname] = {'path':path,'dir':dir,'name':name}
    2959. 

  2959. 	
    2960. 

  2960. 	def expand(self, line=''):
    2961. 

  2961. 		"Expand all macros found on the line"
    2962. 

  2962. 		while self.rgx.search(line):
    2963. 

  2963. 			m = self.rgx.search(line)
    2964. 

  2964. 			name = self.name = m.group('name')
    2965. 

  2965. 			fmt = m.group('fmt') or self.dft_fmt.get(name)
    2966. 

  2966. 			if name == 'date':
    2967. 

  2967. 				txt = time.strftime(fmt,self.currdate)
    2968. 

  2968. 			elif name == 'mtime':
    2969. 

  2969. 				if self.infile == STDIN:
    2970. 

  2970. 					fdate = self.currdate
    2971. 

  2971. 				else:
    2972. 

  2972. 					mtime = os.path.getmtime(self.infile)
    2973. 

  2973. 					fdate = time.localtime(mtime)
    2974. 

  2974. 				txt = time.strftime(fmt,fdate)
    2975. 

  2975. 			elif name in ['infile','outfile']:
    2976. 

  2976. 				self.set_file_info(name)
    2977. 

  2977. 				txt = self.walk_file_format(fmt)
    2978. 

  2978. 			else:
    2979. 

  2979. 				Error("Unknown macro name '%s'"%name)
    2980. 

  2980. 			line = self.rgx.sub(txt,line,1)
    2981. 

  2981. 		return line
    2982. 

  2982. 

  2983. 

  2984. ##############################################################################
    2985. 

  2985. 

  2986. 

  2987. def dumpConfig(source_raw, parsed_config):
    2988. 

  2988. 	onoff = {1:_('ON'), 0:_('OFF')}
    2989. 

  2989. 	data = [
    2990. 

  2990. 	  (_('RC file')        , RC_RAW     ),
    2991. 

  2991. 	  (_('source document'), source_raw ),
    2992. 

  2992. 	  (_('command line')   , CMDLINE_RAW)
    2993. 

  2993. 	]
    2994. 

  2994. 	# first show all RAW data found
    2995. 

  2995. 	for label, cfg in data:
    2996. 

  2996. 		print _('RAW config for %s')%label
    2997. 

  2997. 		for target,key,val in cfg:
    2998. 

  2998. 			target = '(%s)'%target
    2999. 

  2999. 			key    = dotted_spaces("%-14s"%key)
    3000. 

  3000. 			val    = val or _('ON')
    3001. 

  3001. 			print '  %-8s %s: %s'%(target,key,val)
    3002. 

  3002. 		print
    3003. 

  3003. 	# then the parsed results of all of them
    3004. 

  3004. 	print _('Full PARSED config')
    3005. 

  3005. 	keys = parsed_config.keys() ; keys.sort()  # sorted
    3006. 

  3006. 	for key in keys:
    3007. 

  3007. 		val = parsed_config[key]
    3008. 

  3008. 		# filters are the last
    3009. 

  3009. 		if key in ['preproc', 'postproc']:
    3010. 

  3010. 			continue
    3011. 

  3011. 		# flag beautifier
    3012. 

  3012. 		if key in FLAGS.keys()+ACTIONS.keys():
    3013. 

  3013. 			val = onoff.get(val) or val
    3014. 

  3014. 		# list beautifier
    3015. 

  3015. 		if type(val) == type([]):
    3016. 

  3016. 			if key == 'options': sep = ' '
    3017. 

  3017. 			else               : sep = ', '
    3018. 

  3018. 			val = string.join(val, sep)
    3019. 

  3019. 		print "%25s: %s"%(dotted_spaces("%-14s"%key),val)
    3020. 

  3020. 	print
    3021. 

  3021. 	print _('Active filters')
    3022. 

  3022. 	for filter in ['preproc','postproc']:
    3023. 

  3023. 		for rule in parsed_config.get(filter) or []:
    3024. 

  3024. 			print "%25s: %s  ->  %s"%(
    3025. 

  3025. 			   dotted_spaces("%-14s"%filter),rule[0],rule[1])
    3026. 

  3026. 

  3027. 

  3028. def get_file_body(file):
    3029. 

  3029. 	"Returns all the document BODY lines"
    3030. 

  3030. 	return process_source_file(file, noconf=1)[1][2]
    3031. 

  3031. 

  3032. 

  3033. def finish_him(outlist, config):
    3034. 

  3034. 	"Writing output to screen or file"
    3035. 

  3035. 	outfile = config['outfile']
    3036. 

  3036. 	outlist = unmaskEscapeChar(outlist)
    3037. 

  3037. 	
    3038. 

  3038. 	# apply PostProc filters
    3039. 

  3039. 	if config['postproc']:
    3040. 

  3040. 		filters = compile_filters(config['postproc'],
    3041. 

  3041. 		                        _('Invalid PostProc filter regex'))
    3042. 

  3042. 		postoutlist = []
    3043. 

  3043. 		for line in outlist:
    3044. 

  3044. 			for rgx,repl in filters:
    3045. 

  3045. 				line = rgx.sub(repl, line)
    3046. 

  3046. 			postoutlist.append(line)
    3047. 

  3047. 		outlist = postoutlist[:]
    3048. 

  3048. 	
    3049. 

  3049. 	if outfile == STDOUT:
    3050. 

  3050. 		if GUI:
    3051. 

  3051. 			return outlist, config
    3052. 

  3052. 		else:
    3053. 

  3053. 			for line in outlist: print line
    3054. 

  3054. 	else:
    3055. 

  3055. 		Savefile(outfile, addLineBreaks(outlist))
    3056. 

  3056. 		if not GUI and not QUIET:
    3057. 

  3057. 			print _('%s wrote %s')%(my_name,outfile)
    3058. 

  3058. 	
    3059. 

  3059. 	if config['split']:
    3060. 

  3060. 		if not QUIET: print "--- html..."
    3061. 

  3061. 		sgml2html = 'sgml2html -s %s -l %s %s'%(
    3062. 

  3062. 		            config['split'],config['lang'] or lang,outfile)
    3063. 

  3063. 		if not QUIET: print "Running system command:", sgml2html
    3064. 

  3064. 		os.system(sgml2html)
    3065. 

  3065. 

  3066. 

  3067. def toc_inside_body(body, toc, config):
    3068. 

  3068. 	ret = []
    3069. 

  3069. 	if AUTOTOC: return body                     # nothing to expand
    3070. 

  3070. 	toc_mark = MaskMaster().tocmask
    3071. 

  3071. 	# expand toc mark with TOC contents
    3072. 

  3072. 	for line in body:
    3073. 

  3073. 		if string.count(line, toc_mark):    # toc mark found
    3074. 

  3074. 			if config['toc']:
    3075. 

  3075. 				ret.extend(toc)     # include if --toc
    3076. 

  3076. 			else:
    3077. 

  3077. 				pass                # or remove %%toc line
    3078. 

  3078. 		else:
    3079. 

  3079. 			ret.append(line)            # common line
    3080. 

  3080. 	return ret
    3081. 

  3081. 

  3082. def toc_tagger(toc, config):
    3083. 

  3083. 	"Convert t2t-marked TOC (it is a list) to target-tagged TOC"
    3084. 

  3084. 	ret = []
    3085. 

  3085. 	# tag if TOC-only TOC "by hand" (target don't have a TOC tag)
    3086. 

  3086. 	if config['toc-only'] or (config['toc'] and not TAGS['TOC']):
    3087. 

  3087. 		fakeconf = config.copy()
    3088. 

  3088. 		fakeconf['headers']    = 0
    3089. 

  3089. 		fakeconf['toc-only']   = 0
    3090. 

  3090. 		fakeconf['mask-email'] = 0
    3091. 

  3091. 		fakeconf['preproc']    = []
    3092. 

  3092. 		fakeconf['postproc']   = []
    3093. 

  3093. 		fakeconf['css-sugar']  = 0
    3094. 

  3094. 		ret,foo = convert(toc, fakeconf)
    3095. 

  3095. 		set_global_config(config)   # restore config
    3096. 

  3096. 	# target TOC is a tag
    3097. 

  3097. 	elif config['toc'] and TAGS['TOC']:
    3098. 

  3098. 		ret = [TAGS['TOC']]
    3099. 

  3099. 	return ret
    3100. 

  3100. 

  3101. def toc_formatter(toc, config):
    3102. 

  3102. 	"Formats TOC for automatic placement between headers and body"
    3103. 

  3103. 	if config['toc-only']: return toc              # no formatting needed
    3104. 

  3104. 	if not config['toc'] : return []               # TOC disabled
    3105. 

  3105. 	ret = toc
    3106. 

  3106. 	# TOC open/close tags (if any)
    3107. 

  3107. 	if TAGS['tocOpen' ]: ret.insert(0, TAGS['tocOpen'])
    3108. 

  3108. 	if TAGS['tocClose']: ret.append(TAGS['tocClose'])
    3109. 

  3109. 	# autotoc specific formatting
    3110. 

  3110. 	if AUTOTOC:
    3111. 

  3111. 		if rules['autotocwithbars']:           # TOC between bars
    3112. 

  3112. 			para = TAGS['paragraphOpen']+TAGS['paragraphClose']
    3113. 

  3113. 			bar  = regex['x'].sub('-'*72,TAGS['bar1'])
    3114. 

  3114. 			tocbar = [para, bar, para]
    3115. 

  3115. 			ret = tocbar + ret + tocbar
    3116. 

  3116. 		if rules['blankendautotoc']:           # blank line after TOC
    3117. 

  3117. 			ret.append('')
    3118. 

  3118. 		if rules['autotocnewpagebefore']:      # page break before TOC
    3119. 

  3119. 			ret.insert(0,TAGS['pageBreak'])
    3120. 

  3120. 		if rules['autotocnewpageafter']:       # page break after TOC
    3121. 

  3121. 			ret.append(TAGS['pageBreak'])
    3122. 

  3122. 	return ret
    3123. 

  3123. 

  3124. 

  3125. def doHeader(headers, config):
    3126. 

  3126. 	if not config['headers']: return []
    3127. 

  3127. 	if not headers: headers = ['','','']
    3128. 

  3128. 	target = config['target']
    3129. 

  3129. 	if not HEADER_TEMPLATE.has_key(target):
    3130. 

  3130. 		Error("doheader: Unknow target '%s'"%target)
    3131. 

  3131. 	
    3132. 

  3132. 	if target in ['html','xhtml'] and config.get('css-sugar'):
    3133. 

  3133. 		template = string.split(HEADER_TEMPLATE[target+'css'], '\n')
    3134. 

  3134. 	else:
    3135. 

  3135. 		template = string.split(HEADER_TEMPLATE[target], '\n')
    3136. 

  3136. 	
    3137. 

  3137. 	head_data = {'STYLE':'', 'ENCODING':''}
    3138. 

  3138. 	for key in head_data.keys():
    3139. 

  3139. 		val = config.get(string.lower(key))
    3140. 

  3140. 		if key == 'ENCODING': val = get_encoding_string(val, target)
    3141. 

  3141. 		head_data[key] = val
    3142. 

  3142. 	# parse header contents
    3143. 

  3143. 	for i in 0,1,2:
    3144. 

  3144. 		# expand macros
    3145. 

  3145. 		contents = MacroMaster(config=config).expand(headers[i])
    3146. 

  3146. 		# Escapes - on tex, just do it if any \tag{} present
    3147. 

  3147. 		if target != 'tex' or \
    3148. 

  3148. 		  (target == 'tex' and re.search(r'\\\w+{', contents)):
    3149. 

  3149. 			contents = doEscape(target, contents)
    3150. 

  3150. 		if target == 'lout':
    3151. 

  3151. 			contents = doFinalEscape(target, contents)
    3152. 

  3152. 		
    3153. 

  3153. 		head_data['HEADER%d'%(i+1)] = contents
    3154. 

  3154. 	# css-inside removes STYLE line	
    3155. 

  3155. 	if target in ['html','xhtml'] and config.get('css-inside') and \
    3156. 

  3156. 	   config.get('style'):
    3157. 

  3157. 		head_data['STYLE'] = ''   
    3158. 

  3158. 	Debug("Header Data: %s"%head_data, 1)
    3159. 

  3159. 	# scan for empty dictionary keys
    3160. 

  3160. 	# if found, scan template lines for that key reference
    3161. 

  3161. 	# if found, remove the reference
    3162. 

  3162. 	# if there isn't any other key reference on the same line, remove it
    3163. 

  3163. 	for key in head_data.keys():
    3164. 

  3164. 		if head_data.get(key): continue
    3165. 

  3165. 		for line in template:
    3166. 

  3166. 			if string.count(line, '%%(%s)s'%key):
    3167. 

  3167. 				sline = string.replace(line, '%%(%s)s'%key, '')
    3168. 

  3168. 				if not re.search(r'%\([A-Z0-9]+\)s', sline):
    3169. 

  3169. 					template.remove(line)
    3170. 

  3170. 	# populate template with data
    3171. 

  3171. 	template = string.join(template, '\n') % head_data
    3172. 

  3172. 	
    3173. 

  3173. 	# adding CSS contents into template (for --css-inside)
    3174. 

  3174. 	if target in ['html','xhtml'] and config.get('css-inside') and \
    3175. 

  3175. 	   config.get('style'):
    3176. 

  3176. 		TAGS = getTags(config)
    3177. 

  3177. 		cssfile = config['style']
    3178. 

  3178. 		if not os.path.isabs(cssfile):
    3179. 

  3179. 			infile = config.get('sourcefile')
    3180. 

  3180. 			cssfile = os.path.join(os.path.dirname(infile), cssfile)
    3181. 

  3181. 		css = string.join(Readfile(cssfile, 1, 1), '\n')
    3182. 

  3182. 		css = "%s\n%s\n%s\n" % (TAGS['cssOpen'], css, TAGS['cssClose'])
    3183. 

  3183. 		template = string.replace(template, '</HEAD>', css+'</HEAD>')
    3184. 

  3184. 	
    3185. 

  3185. 	return string.split(template, '\n')
    3186. 

  3186. 

  3187. def doCommentLine(txt):
    3188. 

  3188. 	# the -- string ends a (h|sg|xht)ml comment :(
    3189. 

  3189. 	txt = maskEscapeChar(txt)
    3190. 

  3190. 	if string.count(TAGS['comment'], '--') and \
    3191. 

  3191. 	   string.count(txt, '--'):
    3192. 

  3192. 		txt = re.sub('-(?=-)', r'-\\', txt)
    3193. 

  3193. 	
    3194. 

  3194. 	if TAGS['comment']:
    3195. 

  3195. 		return regex['x'].sub(txt, TAGS['comment'])
    3196. 

  3196. 	return ''
    3197. 

  3197. 

  3198. def doFooter(config):
    3199. 

  3199. 	if not config['headers']: return []
    3200. 

  3200. 	ret = []
    3201. 

  3201. 	target = config['target']
    3202. 

  3202. 	cmdline = config['realcmdline']
    3203. 

  3203. 	typename = target
    3204. 

  3204. 	if target == 'tex': typename = 'LaTeX2e'
    3205. 

  3205. 	ppgd = '%s code generated by %s %s (%s)'%(
    3206. 

  3206. 	        typename,my_name,my_version,my_url)
    3207. 

  3207. 	cmdline = 'cmdline: %s %s'%(my_name, string.join(cmdline, ' '))
    3208. 

  3208. 	ret.append('\n'+doCommentLine(ppgd))
    3209. 

  3209. 	ret.append(doCommentLine(cmdline))
    3210. 

  3210. 	ret.append(TAGS['EOD'])
    3211. 

  3211. 	return ret
    3212. 

  3212. 

  3213. def doEscape(target,txt):
    3214. 

  3214. 	"Target-specific special escapes. Apply *before* insert any tag."
    3215. 

  3215. 	tmpmask = 'vvvvThisEscapingSuxvvvv'
    3216. 

  3216. 	if target in ['html','sgml','xhtml']:
    3217. 

  3217. 		txt = re.sub('&','&amp;',txt)
    3218. 

  3218. 		txt = re.sub('<','&lt;',txt)
    3219. 

  3219. 		txt = re.sub('>','&gt;',txt)
    3220. 

  3220. 		if target == 'sgml':
    3221. 

  3221. 			txt = re.sub('\xff','&yuml;',txt)  # "+y
    3222. 

  3222. 	elif target == 'pm6':
    3223. 

  3223. 		txt = re.sub('<','<\#60>',txt)
    3224. 

  3224. 	elif target == 'mgp':
    3225. 

  3225. 		txt = re.sub('^%',' %',txt)  # add leading blank to avoid parse
    3226. 

  3226. 	elif target == 'man':
    3227. 

  3227. 		txt = re.sub("^([.'])", '\\&\\1',txt)           # command ID
    3228. 

  3228. 		txt = string.replace(txt,ESCCHAR, ESCCHAR+'e')  # \e
    3229. 

  3229. 	elif target == 'lout':
    3230. 

  3230. 		# TIP: / moved to FinalEscape to avoid //italic//
    3231. 

  3231. 		# TIP: these are also converted by lout:  ...  ---  --
    3232. 

  3232. 		txt = string.replace(txt, ESCCHAR, tmpmask)             # \
    3233. 

  3233. 		txt = string.replace(txt, '"', '"%s""'%ESCCHAR)         # "\""
    3234. 

  3234. 		txt = re.sub('([|&{}@#^~])', '"\\1"',txt)               # "@"
    3235. 

  3235. 		txt = string.replace(txt, tmpmask, '"%s"'%(ESCCHAR*2))  # "\\"
    3236. 

  3236. 	elif target == 'tex':
    3237. 

  3237. 		# mark literal \ to be changed to $\backslash$ later
    3238. 

  3238. 		txt = string.replace( txt, ESCCHAR, tmpmask)
    3239. 

  3239. 		txt = re.sub('([#$&%{}])', ESCCHAR+r'\1'  , txt)  # \%
    3240. 

  3240. 		txt = re.sub('([~^])'    , ESCCHAR+r'\1{}', txt)  # \~{}
    3241. 

  3241. 		txt = re.sub('([<|>])'   ,         r'$\1$', txt)  # $>$
    3242. 

  3242. 		txt = string.replace(txt, tmpmask,
    3243. 

  3243. 		                     maskEscapeChar(r'$\backslash$'))
    3244. 

  3244. 		# TIP the _ is escaped at the end
    3245. 

  3245. 	return txt
    3246. 

  3246. 

  3247. # TODO man: where - really needs to be escaped?
    3248. 

  3248. def doFinalEscape(target, txt):
    3249. 

  3249. 	"Last escapes of each line"
    3250. 

  3250. 	if   target == 'pm6' : txt = string.replace(txt,ESCCHAR+'<',r'<\#92><')
    3251. 

  3251. 	elif target == 'man' : txt = string.replace(txt, '-', r'\-')
    3252. 

  3252. 	elif target == 'sgml': txt = string.replace(txt, '[', '&lsqb;')
    3253. 

  3253. 	elif target == 'lout': txt = string.replace(txt, '/', '"/"')
    3254. 

  3254. 	elif target == 'tex' :
    3255. 

  3255. 		txt = string.replace(txt, '_', r'\_')
    3256. 

  3256. 		txt = string.replace(txt, 'vvvvTexUndervvvv', '_')  # shame!
    3257. 

  3257. 	return txt
    3258. 

  3258. 

  3259. def EscapeCharHandler(action, data):
    3260. 

  3260. 	"Mask/Unmask the Escape Char on the given string"
    3261. 

  3261. 	if not string.strip(data): return data
    3262. 

  3262. 	if action not in ['mask','unmask']:
    3263. 

  3263. 		Error("EscapeCharHandler: Invalid action '%s'"%action)
    3264. 

  3264. 	if action == 'mask': return string.replace(data,'\\',ESCCHAR)
    3265. 

  3265. 	else:                return string.replace(data,ESCCHAR,'\\')
    3266. 

  3266. 

  3267. def maskEscapeChar(data):
    3268. 

  3268. 	"Replace any Escape Char \ with a text mask (Input: str or list)"
    3269. 

  3269. 	if type(data) == type([]):
    3270. 

  3270. 		return map(lambda x: EscapeCharHandler('mask', x), data)
    3271. 

  3271. 	return EscapeCharHandler('mask',data)
    3272. 

  3272. 

  3273. def unmaskEscapeChar(data):
    3274. 

  3274. 	"Undo the Escape char \ masking (Input: str or list)"
    3275. 

  3275. 	if type(data) == type([]):
    3276. 

  3276. 		return map(lambda x: EscapeCharHandler('unmask', x), data)
    3277. 

  3277. 	return EscapeCharHandler('unmask',data)
    3278. 

  3278. 

  3279. def addLineBreaks(list):
    3280. 

  3280. 	"use LB to respect sys.platform"
    3281. 

  3281. 	ret = []
    3282. 

  3282. 	for line in list:
    3283. 

  3283. 		line = string.replace(line,'\n',LB)  # embedded \n's
    3284. 

  3284. 		ret.append(line+LB)                  # add final line break
    3285. 

  3285. 	return ret
    3286. 

  3286. 

  3287. def compile_filters(filters, errmsg='Filter'):
    3288. 

  3288. 	if filters:
    3289. 

  3289. 		for i in range(len(filters)):
    3290. 

  3290. 			patt,repl = filters[i]
    3291. 

  3291. 			try: rgx = re.compile(patt)
    3292. 

  3292. 			except: Error("%s: '%s'"%(errmsg, patt))
    3293. 

  3293. 			filters[i] = (rgx,repl)
    3294. 

  3294. 	return filters
    3295. 

  3295. 

  3296. def enclose_me(tagname, txt):
    3297. 

  3297. 	return TAGS.get(tagname+'Open') + txt + TAGS.get(tagname+'Close')
    3298. 

  3298. 

  3299. def beautify_me(name, line):
    3300. 

  3300. 	"where name is: bold, italic or underline"
    3301. 

  3301. 	name  = 'font%s' % string.capitalize(name)
    3302. 

  3302. 	open  = TAGS['%sOpen'%name]
    3303. 

  3303. 	close = TAGS['%sClose'%name]
    3304. 

  3304. 	txt = r'%s\1%s'%(open, close)
    3305. 

  3305. 	line = regex[name].sub(txt,line)
    3306. 

  3306. 	return line
    3307. 

  3307. 

  3308. def get_tagged_link(label, url):
    3309. 

  3309. 	ret = ''
    3310. 

  3310. 	target = CONF['target']
    3311. 

  3311. 	image_re = regex['img']
    3312. 

  3312. 	
    3313. 

  3313. 	# set link type
    3314. 

  3314. 	if regex['email'].match(url):
    3315. 

  3315. 		linktype = 'email'
    3316. 

  3316. 	else:
    3317. 

  3317. 		linktype = 'url';
    3318. 

  3318. 	
    3319. 

  3319. 	# escape specials from TEXT parts
    3320. 

  3320. 	label = doEscape(target,label)
    3321. 

  3321. 	
    3322. 

  3322. 	# escape specials from link URL
    3323. 

  3323. 	if rules['linkable'] and rules['escapeurl']:
    3324. 

  3324. 		url = doEscape(target, url)
    3325. 

  3325. 	
    3326. 

  3326. 	# if not linkable, the URL is plain text, that needs escape
    3327. 

  3327. 	if not rules['linkable']:
    3328. 

  3328. 		if target == 'tex':
    3329. 

  3329. 			url = re.sub('^#', '\#', url) # ugly, but compile
    3330. 

  3330. 		else:
    3331. 

  3331. 			url = doEscape(target,url)
    3332. 

  3332. 	
    3333. 

  3333. 	# adding protocol to guessed link
    3334. 

  3334. 	guessurl = ''
    3335. 

  3335. 	if linktype == 'url' and \
    3336. 

  3336. 	   re.match(regex['_urlskel']['guess'], url):
    3337. 

  3337. 		if url[0] == 'w': guessurl = 'http://' +url
    3338. 

  3338. 		else            : guessurl =  'ftp://' +url
    3339. 

  3339. 		
    3340. 

  3340. 		# not link aware targets -> protocol is useless
    3341. 

  3341. 		if not rules['linkable']: guessurl = ''
    3342. 

  3342. 	
    3343. 

  3343. 	# simple link (not guessed)
    3344. 

  3344. 	if not label and not guessurl:
    3345. 

  3345. 		if CONF['mask-email'] and linktype == 'email':
    3346. 

  3346. 			# do the email mask feature (no TAGs, just text)
    3347. 

  3347. 			url = string.replace(url,'@',' (a) ')
    3348. 

  3348. 			url = string.replace(url,'.',' ')
    3349. 

  3349. 			url = "<%s>" % url
    3350. 

  3350. 			if rules['linkable']: url = doEscape(target, url)
    3351. 

  3351. 			ret = url
    3352. 

  3352. 		else:
    3353. 

  3353. 			# just add link data to tag
    3354. 

  3354. 			tag = TAGS[linktype]
    3355. 

  3355. 			ret = regex['x'].sub(url,tag)
    3356. 

  3356. 	
    3357. 

  3357. 	# named link or guessed simple link
    3358. 

  3358. 	else:
    3359. 

  3359. 		# adjusts for guessed link
    3360. 

  3360. 		if not label: label = url         # no   protocol
    3361. 

  3361. 		if guessurl : url   = guessurl    # with protocol
    3362. 

  3362. 		
    3363. 

  3363. 		# image inside link!
    3364. 

  3364. 		if image_re.match(label):
    3365. 

  3365. 			if rules['imglinkable']:  # get image tag
    3366. 

  3366. 				label = parse_images(label)
    3367. 

  3367. 			else:                     #  img@link !supported
    3368. 

  3368. 				label = "(%s)"%image_re.match(label).group(1)
    3369. 

  3369. 		
    3370. 

  3370. 		# putting data on the right appearance order
    3371. 

  3371. 		if rules['linkable']:
    3372. 

  3372. 			urlorder = [url, label]   # link before label
    3373. 

  3373. 		else:
    3374. 

  3374. 			urlorder = [label, url]   # label before link
    3375. 

  3375. 		
    3376. 

  3376. 		# add link data to tag (replace \a's)
    3377. 

  3377. 		ret = TAGS["%sMark"%linktype]
    3378. 

  3378. 		for data in urlorder:
    3379. 

  3379. 			ret = regex['x'].sub(data,ret,1)
    3380. 

  3380. 	
    3381. 

  3381. 	return ret
    3382. 

  3382. 

  3383. 

  3384. def parse_deflist_term(line):
    3385. 

  3385. 	"Extract and parse definition list term contents"
    3386. 

  3386. 	img_re = regex['img']
    3387. 

  3387. 	term   = regex['deflist'].search(line).group(3)
    3388. 

  3388. 	
    3389. 

  3389. 	# mask image inside term as (image.jpg), where not supported
    3390. 

  3390. 	if not rules['imgasdefterm'] and img_re.search(term):
    3391. 

  3391. 		while img_re.search(term):
    3392. 

  3392. 			imgfile = img_re.search(term).group(1)
    3393. 

  3393. 			term = img_re.sub('(%s)'%imgfile, term, 1)
    3394. 

  3394. 	
    3395. 

  3395. 	#TODO tex: escape ] on term. \], \rbrack{} and \verb!]! don't work :(
    3396. 

  3396. 	return term
    3397. 

  3397. 

  3398. 

  3399. def get_tagged_bar(line):
    3400. 

  3400. 	m = regex['bar'].search(line)
    3401. 

  3401. 	if not m: return line
    3402. 

  3402. 	txt = m.group(2)
    3403. 

  3403. 	
    3404. 

  3404. 	# map strong bar to pagebreak
    3405. 

  3405. 	if rules['mapbar2pagebreak'] and TAGS['pageBreak']:
    3406. 

  3406. 		TAGS['bar2'] = TAGS['pageBreak']
    3407. 

  3407. 	
    3408. 

  3408. 	# set bar type
    3409. 

  3409. 	if txt[0] == '=': bar = TAGS['bar2']
    3410. 

  3410. 	else            : bar = TAGS['bar1']
    3411. 

  3411. 	
    3412. 

  3412. 	# to avoid comment tag confusion like <!-- ------ -->
    3413. 

  3413. 	if string.count(TAGS['comment'], '--'):
    3414. 

  3414. 		txt = string.replace(txt,'--','__')
    3415. 

  3415. 	
    3416. 

  3416. 	# tag line
    3417. 

  3417. 	return regex['x'].sub(txt, bar)
    3418. 

  3418. 

  3419. 

  3420. def get_image_align(line):
    3421. 

  3421. 	"Return the image (first found) align for the given line"
    3422. 

  3422. 	
    3423. 

  3423. 	# first clear marks that can mess align detection
    3424. 

  3424. 	line = re.sub(SEPARATOR+'$', '', line)  # remove deflist sep
    3425. 

  3425. 	line = re.sub('^'+SEPARATOR, '', line)  # remove list sep
    3426. 

  3426. 	line = re.sub('^[\t]+'     , '', line)  # remove quote mark
    3427. 

  3427. 	
    3428. 

  3428. 	# get image position on the line
    3429. 

  3429. 	m = regex['img'].search(line)
    3430. 

  3430. 	ini = m.start() ; head = 0
    3431. 

  3431. 	end = m.end()   ; tail = len(line)
    3432. 

  3432. 	
    3433. 

  3433. 	# the align detection algorithm
    3434. 

  3434. 	if   ini == head and end != tail: align = 'left'   # ^img + text$
    3435. 

  3435. 	elif ini != head and end == tail: align = 'right'  # ^text + img$
    3436. 

  3436. 	else                            : align = 'center' # default align
    3437. 

  3437. 	
    3438. 

  3438. 	# some special cases
    3439. 

  3439. 	if BLOCK.isblock('table'): align = 'center'    # ignore when table
    3440. 

  3440. #	if TARGET == 'mgp' and align == 'center': align = 'center'
    3441. 

  3441. 	
    3442. 

  3442. 	return align
    3443. 

  3443. 

  3444. 

  3445. # reference: http://www.iana.org/assignments/character-sets
    3446. 

  3446. # http://www.drclue.net/F1.cgi/HTML/META/META.html
    3447. 

  3447. def get_encoding_string(enc, target):
    3448. 

  3448. 	if not enc: return ''
    3449. 

  3449. 	# target specific translation table
    3450. 

  3450. 	translate = {
    3451. 

  3451. 	'tex': {
    3452. 

  3452. 	  # missing: ansinew , applemac , cp437 , cp437de , cp865
    3453. 

  3453. 	  'us-ascii'    : 'ascii',
    3454. 

  3454. 	  'windows-1250': 'cp1250',
    3455. 

  3455. 	  'windows-1252': 'cp1252',
    3456. 

  3456. 	  'ibm850'      : 'cp850',
    3457. 

  3457. 	  'ibm852'      : 'cp852',
    3458. 

  3458. 	  'iso-8859-1'  : 'latin1',
    3459. 

  3459. 	  'iso-8859-2'  : 'latin2',
    3460. 

  3460. 	  'iso-8859-3'  : 'latin3',
    3461. 

  3461. 	  'iso-8859-4'  : 'latin4',
    3462. 

  3462. 	  'iso-8859-5'  : 'latin5',
    3463. 

  3463. 	  'iso-8859-9'  : 'latin9',
    3464. 

  3464. 	  'koi8-r'      : 'koi8-r'
    3465. 

  3465. 	  }
    3466. 

  3466. 	}
    3467. 

  3467. 	# normalization
    3468. 

  3468. 	enc = re.sub('(?i)(us[-_]?)?ascii|us|ibm367','us-ascii'  , enc)
    3469. 

  3469. 	enc = re.sub('(?i)(ibm|cp)?85([02])'        ,'ibm85\\2'  , enc)
    3470. 

  3470. 	enc = re.sub('(?i)(iso[_-]?)?8859[_-]?'     ,'iso-8859-' , enc)
    3471. 

  3471. 	enc = re.sub('iso-8859-($|[^1-9]).*'        ,'iso-8859-1', enc)
    3472. 

  3472. 	# apply translation table
    3473. 

  3473. 	try: enc = translate[target][string.lower(enc)]
    3474. 

  3474. 	except: pass
    3475. 

  3475. 	return enc
    3476. 

  3476. 

  3477. 

  3478. ##############################################################################
    3479. 

  3479. ##MerryChristmas,IdontwanttofighttonightwithyouImissyourbodyandIneedyourlove##
    3480. 

  3480. ##############################################################################
    3481. 

  3481. 

  3482. 

  3483. def process_source_file(file='', noconf=0, contents=[]):
    3484. 

  3484. 	"""
    3485. 

  3485. 	Find and Join all the configuration available for a source file.
    3486. 

  3486. 	No sanity checkings are done on this step.
    3487. 

  3487. 	It also extracts the source document parts into separate holders.
    3488. 

  3488. 	
    3489. 

  3489. 	The config scan order is:
    3490. 

  3490. 	   1. The user configuration file (i.e. $HOME/.txt2tagsrc)
    3491. 

  3491. 	   2. The source document's CONF area
    3492. 

  3492. 	   3. The command line options
    3493. 

  3493. 

  3494. 	The return data is a tuple of two items:
    3495. 

  3495. 	   1. The parsed config dictionary
    3496. 

  3496. 	   2. The document's parts, as a (head, conf, body) tuple
    3497. 

  3497. 	
    3498. 

  3498. 	All the conversion process will be based on the data and
    3499. 

  3499. 	configuration returned by this function.
    3500. 

  3500. 	The source files is readed on this step only.
    3501. 

  3501. 	"""
    3502. 

  3502. 	if contents:
    3503. 

  3503. 		source = SourceDocument(contents=contents)
    3504. 

  3504. 	else:
    3505. 

  3505. 		source = SourceDocument(file)
    3506. 

  3506. 	head, conf, body = source.split()
    3507. 

  3507. 	Message(_("Source document contents stored"),2)
    3508. 

  3508. 	if not noconf:
    3509. 

  3509. 		# read document config
    3510. 

  3510. 		source_raw = source.get_raw_config()
    3511. 

  3511. 		# join all the config directives found, then parse it
    3512. 

  3512. 		full_raw = RC_RAW + source_raw + CMDLINE_RAW
    3513. 

  3513. 		Message(_("Parsing and saving all config found (%03d items)")%(
    3514. 

  3514. 		        len(full_raw)),1)
    3515. 

  3515. 		full_parsed = ConfigMaster(full_raw).parse()
    3516. 

  3516. 		# add manually the filemane to the conf dic
    3517. 

  3517. 		if contents:
    3518. 

  3518. 			full_parsed['sourcefile'] = '-module-'
    3519. 

  3519. 			full_parsed['infile'] = '-module-'
    3520. 

  3520. 		else:
    3521. 

  3521. 			full_parsed['sourcefile'] = file
    3522. 

  3522. 		# maybe should we dump the config found?
    3523. 

  3523. 		if full_parsed.get('dump-config'):
    3524. 

  3524. 			dumpConfig(source_raw, full_parsed)
    3525. 

  3525. 			Quit()
    3526. 

  3526. 		# okay, all done
    3527. 

  3527. 		Debug("FULL config for this file: %s"%full_parsed, 1)
    3528. 

  3528. 	else:
    3529. 

  3529. 		full_parsed = {}
    3530. 

  3530. 	return full_parsed, (head,conf,body)
    3531. 

  3531. 

  3532. def get_infiles_config(infiles):
    3533. 

  3533. 	"""
    3534. 

  3534. 	Find and Join into a single list, all configuration available
    3535. 

  3535. 	for each input file. This function is supposed to be the very
    3536. 

  3536. 	first one to be called, before any processing.
    3537. 

  3537. 	"""
    3538. 

  3538. 	ret = []
    3539. 

  3539. 	if not infiles: return []
    3540. 

  3540. 	for infile in infiles:
    3541. 

  3541. 		ret.append((process_source_file(infile)))
    3542. 

  3542. 	return ret
    3543. 

  3543. 

  3544. def convert_this_files(configs, dump_results=0):
    3545. 

  3545. 	global CONF
    3546. 

  3546. 	for myconf,doc in configs:                 # multifile support
    3547. 

  3547. 		target_head = []
    3548. 

  3548. 		target_toc  = []
    3549. 

  3549. 		target_body = []
    3550. 

  3550. 		target_foot = []
    3551. 

  3551. 		source_head, source_conf, source_body = doc
    3552. 

  3552. 		myconf = ConfigMaster().sanity(myconf)
    3553. 

  3553. 		# compose the target file Headers
    3554. 

  3554. 		#TODO escape line before?
    3555. 

  3555. 		#TODO see exceptions by tex and mgp
    3556. 

  3556. 		Message(_("Composing target Headers"),1)
    3557. 

  3557. 		target_head = doHeader(source_head, myconf)
    3558. 

  3558. 		# parse the full marked body into tagged target
    3559. 

  3559. 		first_body_line = (len(source_head) or 1)+ len(source_conf) + 1
    3560. 

  3560. 		Message(_("Composing target Body"),1)
    3561. 

  3561. 		target_body, marked_toc = convert(source_body, myconf,
    3562. 

  3562. 		                          firstlinenr=first_body_line)
    3563. 

  3563. 		# make TOC (if needed)
    3564. 

  3564. 		Message(_("Composing target TOC"),1)
    3565. 

  3565. 		tagged_toc  = toc_tagger(marked_toc, myconf)
    3566. 

  3566. 		target_toc  = toc_formatter(tagged_toc, myconf)
    3567. 

  3567. 		target_body = toc_inside_body(target_body, target_toc, myconf)
    3568. 

  3568. 		if not AUTOTOC and not myconf['toc-only']: target_toc = []
    3569. 

  3569. 		# compose the target file Footer
    3570. 

  3570. 		Message(_("Composing target Footer"),1)
    3571. 

  3571. 		target_foot = doFooter(myconf)
    3572. 

  3572. 		# finally, we have our document
    3573. 

  3573. 		outlist = target_head + target_toc + target_body + target_foot
    3574. 

  3574. 		# if on GUI, abort before finish_him
    3575. 

  3575. 		# else, write results to file or STDOUT
    3576. 

  3576. 		if GUI or dump_results:
    3577. 

  3577. 			return outlist, myconf
    3578. 

  3578. 		else:
    3579. 

  3579. 			Message(_("Saving results to the output file"),1)
    3580. 

  3580. 			finish_him(outlist, myconf)
    3581. 

  3581. 

  3582. 

  3583. def parse_images(line):
    3584. 

  3584. 	"Tag all images found"
    3585. 

  3585. 	while regex['img'].search(line) and TAGS['img'] != '[\a]':
    3586. 

  3586. 		txt = regex['img'].search(line).group(1)
    3587. 

  3587. 		tag = TAGS['img']
    3588. 

  3588. 		
    3589. 

  3589. 		# HTML, XHTML and mgp!
    3590. 

  3590. 		if rules['imgalignable']:
    3591. 

  3591. 			align = get_image_align(line)
    3592. 

  3592. 			# add align on tag
    3593. 

  3593. 			align_name = string.capitalize(align)
    3594. 

  3594. 			align_tag = TAGS['imgAlign'+align_name]
    3595. 

  3595. 			tag = regex['_imgAlign'].sub(align_tag, tag, 1)
    3596. 

  3596. 			# dirty fix to allow centered solo images
    3597. 

  3597. 			if align == 'center' and TARGET in ['html','xhtml']:
    3598. 

  3598. 				rest = regex['img'].sub('',line,1)
    3599. 

  3599. 				if re.match('^\s+$', rest):
    3600. 

  3600. 					tag = "<center>%s</center>" %tag
    3601. 

  3601. 		
    3602. 

  3602. 		if TARGET == 'tex':
    3603. 

  3603. 			tag = re.sub(r'\\b',r'\\\\b',tag)
    3604. 

  3604. 			txt = string.replace(txt, '_', 'vvvvTexUndervvvv')
    3605. 

  3605. 		
    3606. 

  3606. 		line = regex['img'].sub(tag,line,1)
    3607. 

  3607. 		line = regex['x'].sub(txt,line,1)
    3608. 

  3608. 	return line
    3609. 

  3609. 

  3610. 

  3611. def add_inline_tags(line):
    3612. 

  3612. 	# beautifiers
    3613. 

  3613. 	for beauti in ['Bold', 'Italic', 'Underline']:
    3614. 

  3614. 		if regex['font%s'%beauti].search(line):
    3615. 

  3615. 			line = beautify_me(beauti, line)
    3616. 

  3616. 	
    3617. 

  3617. 	line = parse_images(line)
    3618. 

  3618. 	return line
    3619. 

  3619. 

  3620. 

  3621. def get_include_contents(file, path=''):
    3622. 

  3622. 	"Parses %!include: value and extract file contents"
    3623. 

  3623. 	ids = {'`':'verb', '"':'raw', "'":'passthru' }
    3624. 

  3624. 	id = 't2t'
    3625. 

  3625. 	# set include type and remove identifier marks
    3626. 

  3626. 	mark = file[0]
    3627. 

  3627. 	if mark in ids.keys():
    3628. 

  3628. 		if file[:2] == file[-2:] == mark*2:
    3629. 

  3629. 			id = ids[mark]     # set type
    3630. 

  3630. 			file = file[2:-2]  # remove marks
    3631. 

  3631. 	# handle remote dir execution
    3632. 

  3632. 	filepath = os.path.join(path, file)
    3633. 

  3633. 	# read included file contents
    3634. 

  3634. 	lines = Readfile(filepath, remove_linebreaks=1)
    3635. 

  3635. 	# default txt2tags marked text, just BODY matters
    3636. 

  3636. 	if id == 't2t':
    3637. 

  3637. 		lines = get_file_body(filepath)
    3638. 

  3638. 		lines.insert(0, '%%INCLUDED(%s) starts here: %s'%(id,file))
    3639. 

  3639. 		lines.append('%%INCLUDED(%s) ends here: %s'%(id,file))
    3640. 

  3640. 	return id, lines
    3641. 

  3641. 

  3642. 

  3643. def set_global_config(config):
    3644. 

  3644. 	global CONF, TAGS, regex, rules, TARGET
    3645. 

  3645. 	CONF   = config
    3646. 

  3646. 	TAGS   = getTags(CONF)
    3647. 

  3647. 	rules  = getRules(CONF)
    3648. 

  3648. 	regex  = getRegexes()
    3649. 

  3649. 	TARGET = config['target']  # save for buggy functions that need global
    3650. 

  3650. 

  3651. 

  3652. def convert(bodylines, config, firstlinenr=1):
    3653. 

  3653. 	global BLOCK
    3654. 

  3654. 	
    3655. 

  3655. 	set_global_config(config)
    3656. 

  3656. 	
    3657. 

  3657. 	target = config['target']
    3658. 

  3658. 	BLOCK = BlockMaster()
    3659. 

  3659. 	MASK  =  MaskMaster()
    3660. 

  3660. 	TITLE = TitleMaster()
    3661. 

  3661. 	
    3662. 

  3662. 	ret = []
    3663. 

  3663. 	f_lastwasblank = 0
    3664. 

  3664. 	
    3665. 

  3665. 	# compiling all PreProc regexes
    3666. 

  3666. 	pre_filter = compile_filters(
    3667. 

  3667. 		CONF['preproc'], _('Invalid PreProc filter regex'))
    3668. 

  3668. 	
    3669. 

  3669. 	# let's mark it up!
    3670. 

  3670. 	linenr = firstlinenr-1
    3671. 

  3671. 	lineref = 0
    3672. 

  3672. 	while lineref < len(bodylines):
    3673. 

  3673. 		# defaults
    3674. 

  3674. 		MASK.reset()
    3675. 

  3675. 		results_box = ''
    3676. 

  3676. 		
    3677. 

  3677. 		untouchedline = bodylines[lineref]
    3678. 

  3678. 		line = re.sub('[\n\r]+$','',untouchedline)   # del line break
    3679. 

  3679. 		
    3680. 

  3680. 		# apply PreProc filters
    3681. 

  3681. 		if pre_filter:
    3682. 

  3682. 			for rgx,repl in pre_filter:
    3683. 

  3683. 				line = rgx.sub(repl, line)
    3684. 

  3684. 		
    3685. 

  3685. 		line = maskEscapeChar(line)                  # protect \ char
    3686. 

  3686. 		linenr  = linenr  +1
    3687. 

  3687. 		lineref = lineref +1
    3688. 

  3688. 		
    3689. 

  3689. 		Debug(repr(line), 2, linenr)  # heavy debug: show each line
    3690. 

  3690. 		
    3691. 

  3691. 		# any NOT table line (or comment), closes an open table
    3692. 

  3692. 		if ( BLOCK.isblock('table') or
    3693. 

  3693. 		      ( BLOCK.isblock('verb') and
    3694. 

  3694. 		        BLOCK.prop('mapped') == 'table'
    3695. 

  3695. 		       )
    3696. 

  3696. 		    ) \
    3697. 

  3697. 		   and not regex['table'].search(line) \
    3698. 

  3698. 		   and not regex['comment'].search(line):
    3699. 

  3699. 			ret.extend(BLOCK.blockout())
    3700. 

  3700. 		
    3701. 

  3701. 		# any NOT quote line (or comment) closes all open quotes
    3702. 

  3702. 		if BLOCK.isblock('quote') \
    3703. 

  3703. 		   and not regex['quote'].search(line) \
    3704. 

  3704. 		   and not regex['comment'].search(line):
    3705. 

  3705. 			while BLOCK.isblock('quote'):
    3706. 

  3706. 				ret.extend(BLOCK.blockout())
    3707. 

  3707. 		
    3708. 

  3708. 		
    3709. 

  3709. 		#-------------------------[ Raw Text ]----------------------
    3710. 

  3710. 		
    3711. 

  3711. 		# we're already on a raw block
    3712. 

  3712. 		if BLOCK.block() == 'raw':
    3713. 

  3713. 		
    3714. 

  3714. 			# closing raw
    3715. 

  3715. 			if regex['blockRawClose'].search(line):
    3716. 

  3716. 				ret.extend(BLOCK.blockout())
    3717. 

  3717. 				continue
    3718. 

  3718. 			
    3719. 

  3719. 			# normal raw-inside line
    3720. 

  3720. 			BLOCK.holdadd(line)
    3721. 

  3721. 			continue
    3722. 

  3722. 		
    3723. 

  3723. 		# detecting raw block init
    3724. 

  3724. 		if regex['blockRawOpen'].search(line):
    3725. 

  3725. 			ret.extend(BLOCK.blockin('raw'))
    3726. 

  3726. 			continue
    3727. 

  3727. 		
    3728. 

  3728. 		# one line verb-formatted text
    3729. 

  3729. 		if regex['1lineRaw'].search(line):
    3730. 

  3730. 			ret.extend(BLOCK.blockin('raw'))
    3731. 

  3731. 			line = regex['1lineRaw'].sub('',line)
    3732. 

  3732. 			BLOCK.holdadd(line)
    3733. 

  3733. 			ret.extend(BLOCK.blockout())
    3734. 

  3734. 			continue
    3735. 

  3735. 		
    3736. 

  3736. 		#-----------------[ Verbatim (PRE-formatted) ]--------------
    3737. 

  3737. 		
    3738. 

  3738. 		#TIP we'll never support beautifiers inside verbatim
    3739. 

  3739. 		
    3740. 

  3740. 		# we're already on a verb block
    3741. 

  3741. 		if BLOCK.block() == 'verb':
    3742. 

  3742. 			
    3743. 

  3743. 			# closing verb
    3744. 

  3744. 			if regex['blockVerbClose'].search(line):
    3745. 

  3745. 				ret.extend(BLOCK.blockout())
    3746. 

  3746. 				continue
    3747. 

  3747. 			
    3748. 

  3748. 			# normal verb-inside line
    3749. 

  3749. 			BLOCK.holdadd(line)
    3750. 

  3750. 			continue
    3751. 

  3751. 		
    3752. 

  3752. 		# detecting verb block init
    3753. 

  3753. 		if regex['blockVerbOpen'].search(line):
    3754. 

  3754. 			ret.extend(BLOCK.blockin('verb'))
    3755. 

  3755. 			f_lastwasblank = 0
    3756. 

  3756. 			continue
    3757. 

  3757. 		
    3758. 

  3758. 		# one line verb-formatted text
    3759. 

  3759. 		if regex['1lineVerb'].search(line):
    3760. 

  3760. 			ret.extend(BLOCK.blockin('verb'))
    3761. 

  3761. 			line = regex['1lineVerb'].sub('',line)
    3762. 

  3762. 			BLOCK.holdadd(line)
    3763. 

  3763. 			ret.extend(BLOCK.blockout())
    3764. 

  3764. 			f_lastwasblank = 0
    3765. 

  3765. 			continue
    3766. 

  3766. 		
    3767. 

  3767. 		# tables are mapped to verb when target is not table-aware
    3768. 

  3768. 		if not rules['tableable'] and regex['table'].search(line):
    3769. 

  3769. 			if not BLOCK.isblock('verb'):
    3770. 

  3770. 				ret.extend(BLOCK.blockin('verb'))
    3771. 

  3771. 				BLOCK.propset('mapped', 'table')
    3772. 

  3772. 				BLOCK.holdadd(line)
    3773. 

  3773. 				continue
    3774. 

  3774. 		
    3775. 

  3775. 		#---------------------[ blank lines ]-----------------------
    3776. 

  3776. 		
    3777. 

  3777. 		if regex['blankline'].search(line):
    3778. 

  3778. 			
    3779. 

  3779. 			# close open paragraph
    3780. 

  3780. 			if BLOCK.isblock('para'):
    3781. 

  3781. 				ret.extend(BLOCK.blockout())
    3782. 

  3782. 				f_lastwasblank = 1
    3783. 

  3783. 				continue
    3784. 

  3784. 			
    3785. 

  3785. 			# close all open quotes
    3786. 

  3786. 			while BLOCK.isblock('quote'):
    3787. 

  3787. 				ret.extend(BLOCK.blockout())
    3788. 

  3788. 			
    3789. 

  3789. 			# closing all open lists
    3790. 

  3790. 			if f_lastwasblank:          # 2nd consecutive blank
    3791. 

  3791. 				if BLOCK.block()[-4:] == 'list':
    3792. 

  3792. 					BLOCK.holdaddsub('')   # helps parser
    3793. 

  3793. 				while BLOCK.depth:  # closes list (if any)
    3794. 

  3794. 					ret.extend(BLOCK.blockout())
    3795. 

  3795. 				continue            # ignore consecutive blanks
    3796. 

  3796. 			
    3797. 

  3797. 			# paragraph (if any) is wanted inside lists also
    3798. 

  3798. 			if BLOCK.block()[-4:] == 'list':
    3799. 

  3799. 				BLOCK.holdaddsub('')
    3800. 

  3800. 			else:
    3801. 

  3801. 				# html: show blank line (needs tag)
    3802. 

  3802. 				if target in ['html','xhtml']:
    3803. 

  3803. 					ret.append(TAGS['paragraphOpen']+\
    3804. 

  3804. 					           TAGS['paragraphClose'])
    3805. 

  3805. 				# otherwise we just show a blank line
    3806. 

  3806. 				else:
    3807. 

  3807. 					ret.append('')
    3808. 

  3808. 			
    3809. 

  3809. 			f_lastwasblank = 1
    3810. 

  3810. 			continue
    3811. 

  3811. 		
    3812. 

  3812. 		
    3813. 

  3813. 		#---------------------[ special ]---------------------------
    3814. 

  3814. 		
    3815. 

  3815. 		if regex['special'].search(line):
    3816. 

  3816. 			# include command
    3817. 

  3817. 			targ, key, val = ConfigLines().parse_line(
    3818. 

  3818. 			                   line, 'include', target)
    3819. 

  3819. 			if key:
    3820. 

  3820. 				Debug("Found config '%s', value '%s'"%(
    3821. 

  3821. 				       key,val),1,linenr)
    3822. 

  3822. 				
    3823. 

  3823. 				incpath = os.path.dirname(CONF['sourcefile'])
    3824. 

  3824. 				incfile = val
    3825. 

  3825. 				err = _('A file cannot include itself (loop!)')
    3826. 

  3826. 				if CONF['sourcefile'] == incfile:
    3827. 

  3827. 					Error("%s: %s"%(err,incfile))
    3828. 

  3828. 				inctype, inclines = get_include_contents(
    3829. 

  3829. 				                      incfile, incpath)
    3830. 

  3830. 				# verb, raw and passthru are easy
    3831. 

  3831. 				if inctype != 't2t':
    3832. 

  3832. 					ret.extend(BLOCK.blockin(inctype))
    3833. 

  3833. 					BLOCK.holdextend(inclines)
    3834. 

  3834. 					ret.extend(BLOCK.blockout())
    3835. 

  3835. 				else:
    3836. 

  3836. 					# insert include lines into body
    3837. 

  3837. 					#TODO del %!include command call
    3838. 

  3838. 					#TODO include maxdepth limit
    3839. 

  3839. 					bodylines = bodylines[:lineref] \
    3840. 

  3840. 					           +inclines \
    3841. 

  3841. 					           +bodylines[lineref:]
    3842. 

  3842. 				continue
    3843. 

  3843. 			else:
    3844. 

  3844. 				Debug('Bogus Special Line',1,linenr)
    3845. 

  3845. 		
    3846. 

  3846. 		#---------------------[ comments ]--------------------------
    3847. 

  3847. 		
    3848. 

  3848. 		# just skip them (if not macro)
    3849. 

  3849. 		if regex['comment'].search(line) and not \
    3850. 

  3850. 		   regex['macros'].match(line) and not \
    3851. 

  3851. 		   regex['toc'].match(line):
    3852. 

  3852. 			continue
    3853. 

  3853. 		
    3854. 

  3854. 		# valid line, reset blank status
    3855. 

  3855. 		f_lastwasblank = 0
    3856. 

  3856. 		
    3857. 

  3857. 		#---------------------[ Horizontal Bar ]--------------------
    3858. 

  3858. 		
    3859. 

  3859. 		if regex['bar'].search(line):
    3860. 

  3860. 			
    3861. 

  3861. 			# a bar closes a paragraph
    3862. 

  3862. 			if BLOCK.isblock('para'):
    3863. 

  3863. 				ret.extend(BLOCK.blockout())
    3864. 

  3864. 			
    3865. 

  3865. 			# we need to close all opened quote blocks
    3866. 

  3866. 			# if bar isn't allowed inside or if not a quote line
    3867. 

  3867. 			if BLOCK.isblock('quote'):
    3868. 

  3868. 				if not rules['barinsidequote'] or \
    3869. 

  3869. 				   not regex['quote'].search(line):
    3870. 

  3870. 					while BLOCK.isblock('quote'):
    3871. 

  3871. 						ret.extend(BLOCK.blockout())
    3872. 

  3872. 			
    3873. 

  3873. 			# quote + bar: continue processing for quoting
    3874. 

  3874. 			if rules['barinsidequote'] and \
    3875. 

  3875. 			   regex['quote'].search(line):
    3876. 

  3876. 				pass
    3877. 

  3877. 			
    3878. 

  3878. 			# just bar: save tagged line and we're done
    3879. 

  3879. 			else:
    3880. 

  3880. 				line = get_tagged_bar(line)
    3881. 

  3881. 				if BLOCK.block()[-4:] == 'list':
    3882. 

  3882. 					BLOCK.holdaddsub(line)
    3883. 

  3883. 				elif BLOCK.block():
    3884. 

  3884. 					BLOCK.holdadd(line)
    3885. 

  3885. 				else:
    3886. 

  3886. 					ret.append(line)
    3887. 

  3887. 					Debug("BAR: %s"%line, 6)
    3888. 

  3888. 				continue
    3889. 

  3889. 		
    3890. 

  3890. 		#---------------------[ Title ]-----------------------------
    3891. 

  3891. 		
    3892. 

  3892. 		#TODO set next blank and set f_lastwasblank or f_lasttitle
    3893. 

  3893. 		if (regex['title'].search(line) or
    3894. 

  3894. 		    regex['numtitle'].search(line)) and \
    3895. 

  3895. 		    BLOCK.block()[-4:] != 'list':
    3896. 

  3896. 			
    3897. 

  3897. 			# a title closes a paragraph
    3898. 

  3898. 			if BLOCK.isblock('para'):
    3899. 

  3899. 				ret.extend(BLOCK.blockout())
    3900. 

  3900. 			
    3901. 

  3901. 			TITLE.add(line)
    3902. 

  3902. 			tagged_title = TITLE.get()
    3903. 

  3903. 			ret.extend(tagged_title)
    3904. 

  3904. 			Debug("TITLE: %s"%tagged_title, 6)
    3905. 

  3905. 			
    3906. 

  3906. 			f_lastwasblank = 1
    3907. 

  3907. 			continue
    3908. 

  3908. 		
    3909. 

  3909. 		#---------------------[ %%toc ]-----------------------
    3910. 

  3910. 		
    3911. 

  3911. 		# %%toc line closes paragraph
    3912. 

  3912. 		if BLOCK.block() == 'para' and regex['toc'].search(line):
    3913. 

  3913. 			ret.extend(BLOCK.blockout())
    3914. 

  3914. 		
    3915. 

  3915. 		#---------------------[ apply masks ]-----------------------
    3916. 

  3916. 		
    3917. 

  3917. 		line = MASK.mask(line)
    3918. 

  3918. 		
    3919. 

  3919. 		#XXX from here, only block-inside lines will pass
    3920. 

  3920. 		
    3921. 

  3921. 		#---------------------[ Quote ]-----------------------------
    3922. 

  3922. 		
    3923. 

  3923. 		if regex['quote'].search(line):
    3924. 

  3924. 			
    3925. 

  3925. 			# store number of leading TABS
    3926. 

  3926. 			quotedepth = len(regex['quote'].search(line).group(0))
    3927. 

  3927. 			
    3928. 

  3928. 			# SGML doesn't support nested quotes
    3929. 

  3929. 			if rules['quotenotnested']: quotedepth = 1
    3930. 

  3930. 			
    3931. 

  3931. 			# new quote
    3932. 

  3932. 			if not BLOCK.isblock('quote'):
    3933. 

  3933. 				ret.extend(BLOCK.blockin('quote'))
    3934. 

  3934. 			
    3935. 

  3935. 			# new subquotes
    3936. 

  3936. 			while BLOCK.depth < quotedepth:
    3937. 

  3937. 				BLOCK.blockin('quote')
    3938. 

  3938. 			
    3939. 

  3939. 			# closing quotes
    3940. 

  3940. 			while quotedepth < BLOCK.depth:
    3941. 

  3941. 				ret.extend(BLOCK.blockout())
    3942. 

  3942. 		
    3943. 

  3943. 		#---------------------[ Lists ]-----------------------------
    3944. 

  3944. 		
    3945. 

  3945. 		# an empty item also closes the current list
    3946. 

  3946. 		if BLOCK.block()[-4:] == 'list':
    3947. 

  3947. 			m = regex['listclose'].match(line)
    3948. 

  3948. 			if m:
    3949. 

  3949. 				listindent = m.group(1)
    3950. 

  3950. 				listtype = m.group(2)
    3951. 

  3951. 				currlisttype = BLOCK.prop('type')
    3952. 

  3952. 				currlistindent = BLOCK.prop('indent')
    3953. 

  3953. 				if listindent == currlistindent and \
    3954. 

  3954. 				   listtype == currlisttype:
    3955. 

  3955. 					ret.extend(BLOCK.blockout())
    3956. 

  3956. 					continue
    3957. 

  3957. 		
    3958. 

  3958. 		if   regex['list'].search(line) or \
    3959. 

  3959. 		  regex['numlist'].search(line) or \
    3960. 

  3960. 		  regex['deflist'].search(line):
    3961. 

  3961. 			
    3962. 

  3962. 			listindent = BLOCK.prop('indent')
    3963. 

  3963. 			listids = string.join(LISTNAMES.keys(), '')
    3964. 

  3964. 			m = re.match('^( *)([%s]) '%listids, line)
    3965. 

  3965. 			listitemindent = m.group(1)
    3966. 

  3966. 			listtype = m.group(2)
    3967. 

  3967. 			listname = LISTNAMES[listtype]
    3968. 

  3968. 			results_box = BLOCK.holdadd
    3969. 

  3969. 			
    3970. 

  3970. 			# del list ID (and separate term from definition)
    3971. 

  3971. 			if listname == 'deflist':
    3972. 

  3972. 				term = parse_deflist_term(line)
    3973. 

  3973. 				line = regex['deflist'].sub(term+SEPARATOR,line)
    3974. 

  3974. 			else:
    3975. 

  3975. 				line = regex[listname].sub(SEPARATOR,line)
    3976. 

  3976. 			
    3977. 

  3977. 			# don't cross depth limit
    3978. 

  3978. 			maxdepth = rules['listmaxdepth']
    3979. 

  3979. 			if maxdepth and BLOCK.depth == maxdepth:
    3980. 

  3980. 				if len(listitemindent) > len(listindent):
    3981. 

  3981. 					listitemindent = listindent
    3982. 

  3982. 			
    3983. 

  3983. 			# open mother list or sublist
    3984. 

  3984. 			if BLOCK.block()[-4:] != 'list' or \
    3985. 

  3985. 			   len(listitemindent) > len(listindent):
    3986. 

  3986. 				ret.extend(BLOCK.blockin(listname))
    3987. 

  3987. 				BLOCK.propset('indent',listitemindent)
    3988. 

  3988. 				BLOCK.propset('type',listtype)
    3989. 

  3989. 			
    3990. 

  3990. 			# closing sublists
    3991. 

  3991. 			while len(listitemindent) < len(BLOCK.prop('indent')):
    3992. 

  3992. 				ret.extend(BLOCK.blockout())
    3993. 

  3993. 			
    3994. 

  3994. 			# o-oh, sublist before list ("\n\n  - foo\n- foo")
    3995. 

  3995. 			# fix: close sublist (as mother), open another list
    3996. 

  3996. 			if BLOCK.block()[-4:] != 'list':
    3997. 

  3997. 				ret.extend(BLOCK.blockin(listname))
    3998. 

  3998. 				BLOCK.propset('indent',listitemindent)
    3999. 

  3999. 				BLOCK.propset('type',listtype)
    4000. 

  4000. 		
    4001. 

  4001. 		#---------------------[ Table ]-----------------------------
    4002. 

  4002. 		
    4003. 

  4003. 		#TODO escape undesired format inside table
    4004. 

  4004. 		#TODO add pm6 target
    4005. 

  4005. 		if regex['table'].search(line):
    4006. 

  4006. 			
    4007. 

  4007. 			if not BLOCK.isblock('table'):   # first table line!
    4008. 

  4008. 				ret.extend(BLOCK.blockin('table'))
    4009. 

  4009. 				BLOCK.tableparser.__init__(line)
    4010. 

  4010. 			
    4011. 

  4011. 			tablerow = TableMaster().parse_row(line)
    4012. 

  4012. 			BLOCK.tableparser.add_row(tablerow)     # save config
    4013. 

  4013. 			
    4014. 

  4014. 			# maintain line to unmask and inlines
    4015. 

  4015. 			line = string.join(tablerow['cells'], SEPARATOR)
    4016. 

  4016. 		
    4017. 

  4017. 		#---------------------[ Paragraph ]-------------------------
    4018. 

  4018. 		
    4019. 

  4019. 		if not BLOCK.block() and \
    4020. 

  4020. 		   not string.count(line, MASK.tocmask): # new para!
    4021. 

  4021. 			ret.extend(BLOCK.blockin('para'))
    4022. 

  4022. 		
    4023. 

  4023. 		
    4024. 

  4024. 		############################################################
    4025. 

  4025. 		############################################################
    4026. 

  4026. 		############################################################
    4027. 

  4027. 		
    4028. 

  4028. 		
    4029. 

  4029. 		#---------------------[ Final Parses ]----------------------
    4030. 

  4030. 		
    4031. 

  4031. 		# the target-specific special char escapes for body lines
    4032. 

  4032. 		line = doEscape(target,line)
    4033. 

  4033. 		
    4034. 

  4034. 		line = add_inline_tags(line)
    4035. 

  4035. 		line = MASK.undo(line)
    4036. 

  4036. 		
    4037. 

  4037. 		
    4038. 

  4038. 		#---------------------[ Hold or Return? ]-------------------
    4039. 

  4039. 		
    4040. 

  4040. 		### now we must choose here to put the parsed line
    4041. 

  4041. 		#
    4042. 

  4042. 		if not results_box:
    4043. 

  4043. 			# list item extra lines
    4044. 

  4044. 			if BLOCK.block()[-4:] == 'list':
    4045. 

  4045. 				results_box = BLOCK.holdaddsub
    4046. 

  4046. 			# other blocks
    4047. 

  4047. 			elif BLOCK.block():
    4048. 

  4048. 				results_box = BLOCK.holdadd
    4049. 

  4049. 			# no blocks
    4050. 

  4050. 			else:
    4051. 

  4051. 				line = doFinalEscape(target, line)
    4052. 

  4052. 				results_box = ret.append
    4053. 

  4053. 		
    4054. 

  4054. 		results_box(line)
    4055. 

  4055. 	
    4056. 

  4056. 	# EOF: close any open para/verb/lists/table/quotes
    4057. 

  4057. 	Debug('EOF',7)
    4058. 

  4058. 	while BLOCK.block():
    4059. 

  4059. 		ret.extend(BLOCK.blockout())
    4060. 

  4060. 	
    4061. 

  4061. 	# maybe close some opened title area?
    4062. 

  4062. 	if rules['titleblocks']:
    4063. 

  4063. 		ret.extend(TITLE.close_all())
    4064. 

  4064. 	
    4065. 

  4065. 	# maybe a major tag to enclose body? (like DIV for CSS)
    4066. 

  4066. 	if TAGS['bodyOpen' ]: ret.insert(0, TAGS['bodyOpen'])
    4067. 

  4067. 	if TAGS['bodyClose']: ret.append(TAGS['bodyClose'])
    4068. 

  4068. 	
    4069. 

  4069. 	if CONF['toc-only']: ret = []
    4070. 

  4070. 	marked_toc = TITLE.dump_marked_toc(CONF['toc-level'])
    4071. 

  4071. 	return ret, marked_toc
    4072. 

  4072. 

  4073. 

  4074. 

  4075. ##############################################################################
    4076. 

  4076. ################################### GUI ######################################
    4077. 

  4077. ##############################################################################
    4078. 

  4078. #
    4079. 

  4079. # tk help: http://python.org/topics/tkinter/
    4080. 

  4080. #    tuto: http://ibiblio.org/obp/py4fun/gui/tkPhone.html
    4081. 

  4081. #          /usr/lib/python*/lib-tk/Tkinter.py
    4082. 

  4082. #
    4083. 

  4083. # grid table : row=0, column=0, columnspan=2, rowspan=2
    4084. 

  4084. # grid align : sticky='n,s,e,w' (North, South, East, West)
    4085. 

  4085. # pack place : side='top,bottom,right,left'
    4086. 

  4086. # pack fill  : fill='x,y,both,none', expand=1
    4087. 

  4087. # pack align : anchor='n,s,e,w' (North, South, East, West)
    4088. 

  4088. # padding    : padx=10, pady=10, ipadx=10, ipady=10 (internal)
    4089. 

  4089. # checkbox   : offvalue is return if the _user_ deselected the box
    4090. 

  4090. # label align: justify=left,right,center
    4091. 

  4091. 

  4092. def load_GUI_resources():
    4093. 

  4093. 	"Load all extra modules and methods used by GUI"
    4094. 

  4094. 	global askopenfilename, showinfo, showwarning, showerror, Tkinter
    4095. 

  4095. 	from tkFileDialog import askopenfilename
    4096. 

  4096. 	from tkMessageBox import showinfo,showwarning,showerror
    4097. 

  4097. 	import Tkinter
    4098. 

  4098. 

  4099. class Gui:
    4100. 

  4100. 	"Graphical Tk Interface"
    4101. 

  4101. 	def __init__(self, conf={}):
    4102. 

  4102. 		self.root = Tkinter.Tk()    # mother window, come to butthead
    4103. 

  4103. 		self.root.title(my_name)    # window title bar text
    4104. 

  4104. 		self.window = self.root     # variable "focus" for inclusion
    4105. 

  4105. 		self.row = 0                # row count for grid()
    4106. 

  4106. 		
    4107. 

  4107. 		self.action_lenght = 150    # left column lenght (pixel)
    4108. 

  4108. 		self.frame_margin  = 10     # frame margin size  (pixel)
    4109. 

  4109. 		self.frame_border  = 6      # frame border size  (pixel)
    4110. 

  4110. 		
    4111. 

  4111. 		# the default Gui colors, can be changed by %!guicolors
    4112. 

  4112. 		self.dft_gui_colors = ['blue','white','lightblue','black']
    4113. 

  4113. 		self.gui_colors = []
    4114. 

  4114. 		self.bg1 = self.fg1 = self.bg2 = self.fg2 = ''
    4115. 

  4115. 		
    4116. 

  4116. 		# on Tk, vars need to be set/get using setvar()/get()
    4117. 

  4117. 		self.infile  = self.setvar('')
    4118. 

  4118. 		self.target  = self.setvar('')
    4119. 

  4119. 		self.target_name = self.setvar('')
    4120. 

  4120. 		
    4121. 

  4121. 		# the checks appearance order
    4122. 

  4122. 		self.checks  = [
    4123. 

  4123. 		  'headers','enum-title','toc','mask-email',
    4124. 

  4124. 		  'toc-only','stdout']
    4125. 

  4125. 		
    4126. 

  4126. 		# creating variables for all checks
    4127. 

  4127. 		for check in self.checks:
    4128. 

  4128. 			setattr(self, 'f_'+check, self.setvar(''))
    4129. 

  4129. 		
    4130. 

  4130. 		# load RC config
    4131. 

  4131. 		self.conf = {}
    4132. 

  4132. 		if conf: self.load_config(conf)
    4133. 

  4133. 	
    4134. 

  4134. 	def load_config(self, conf):
    4135. 

  4135. 		self.conf = conf
    4136. 

  4136. 		self.gui_colors = conf.get('guicolors') or self.dft_gui_colors
    4137. 

  4137. 		self.bg1, self.fg1, self.bg2, self.fg2 = self.gui_colors
    4138. 

  4138. 		self.root.config(bd=15,bg=self.bg1)
    4139. 

  4139. 	
    4140. 

  4140. 	### config as dic for python 1.5 compat (**opts don't work :( )
    4141. 

  4141. 	def entry(self, **opts): return Tkinter.Entry(self.window, opts)
    4142. 

  4142. 	def label(self, txt='', bg=None, **opts):
    4143. 

  4143. 		opts.update({'text':txt,'bg':bg or self.bg1})
    4144. 

  4144. 		return Tkinter.Label(self.window, opts)
    4145. 

  4145. 	def button(self,name,cmd,**opts):
    4146. 

  4146. 		opts.update({'text':name,'command':cmd})
    4147. 

  4147. 		return Tkinter.Button(self.window, opts)
    4148. 

  4148. 	def check(self,name,checked=0,**opts):
    4149. 

  4149. 		bg, fg = self.bg2, self.fg2
    4150. 

  4150. 		opts.update({
    4151. 

  4151. 		  'text':name, 'onvalue':1, 'offvalue':0,
    4152. 

  4152. 		  'activeforeground':fg, 'fg':fg,
    4153. 

  4153. 		  'activebackground':bg, 'bg':bg,
    4154. 

  4154. 		  'highlightbackground':bg, 'anchor':'w'
    4155. 

  4155. 		})
    4156. 

  4156. 		chk = Tkinter.Checkbutton(self.window, opts)
    4157. 

  4157. 		if checked: chk.select()
    4158. 

  4158. 		chk.grid(columnspan=2, sticky='w', padx=0)
    4159. 

  4159. 	def menu(self,sel,items):
    4160. 

  4160. 		return apply(Tkinter.OptionMenu,(self.window,sel)+tuple(items))
    4161. 

  4161. 	
    4162. 

  4162. 	# handy auxiliar functions
    4163. 

  4163. 	def action(self, txt):
    4164. 

  4164. 		self.label(txt, fg=self.fg1, bg=self.bg1,
    4165. 

  4165. 		     wraplength=self.action_lenght).grid(column=0,row=self.row)
    4166. 

  4166. 	def frame_open(self):
    4167. 

  4167. 		self.window = Tkinter.Frame(self.root,bg=self.bg2,
    4168. 

  4168. 		     borderwidth=self.frame_border)
    4169. 

  4169. 	def frame_close(self):
    4170. 

  4170. 		self.window.grid(column=1, row=self.row, sticky='w',
    4171. 

  4171. 		     padx=self.frame_margin)
    4172. 

  4172. 		self.window = self.root
    4173. 

  4173. 		self.label('').grid()
    4174. 

  4174. 		self.row = self.row + 2   # update row count
    4175. 

  4175. 	def target_name2key(self):
    4176. 

  4176. 		name = self.target_name.get()
    4177. 

  4177. 		target = filter(lambda x: TARGET_NAMES[x] == name, TARGETS)
    4178. 

  4178. 		try   : key = target[0]
    4179. 

  4179. 		except: key = ''
    4180. 

  4180. 		self.target = self.setvar(key)
    4181. 

  4181. 	def target_key2name(self):
    4182. 

  4182. 		key = self.target.get()
    4183. 

  4183. 		name = TARGET_NAMES.get(key) or key
    4184. 

  4184. 		self.target_name = self.setvar(name)
    4185. 

  4185. 	
    4186. 

  4186. 	def exit(self): self.root.destroy()
    4187. 

  4187. 	def setvar(self, val): z = Tkinter.StringVar() ; z.set(val) ; return z
    4188. 

  4188. 	
    4189. 

  4189. 	def askfile(self):
    4190. 

  4190. 		ftypes= [(_('txt2tags files'),('*.t2t','*.txt')),
    4191. 

  4191. 		         (_('All files'),'*')]
    4192. 

  4192. 		newfile = askopenfilename(filetypes=ftypes)
    4193. 

  4193. 		if newfile:
    4194. 

  4194. 			self.infile.set(newfile)
    4195. 

  4195. 			newconf = process_source_file(newfile)[0]
    4196. 

  4196. 			newconf = ConfigMaster().sanity(newconf, gui=1)
    4197. 

  4197. 			# restate all checkboxes after file selection
    4198. 

  4198. 			#TODO how to make a refresh without killing it?
    4199. 

  4199. 			self.root.destroy()
    4200. 

  4200. 			self.__init__(newconf)
    4201. 

  4201. 			self.mainwindow()
    4202. 

  4202. 	
    4203. 

  4203. 	def scrollwindow(self, txt='no text!', title=''):
    4204. 

  4204. 		# create components
    4205. 

  4205. 		win    = Tkinter.Toplevel() ; win.title(title)
    4206. 

  4206. 		frame  = Tkinter.Frame(win)
    4207. 

  4207. 		scroll = Tkinter.Scrollbar(frame)
    4208. 

  4208. 		text   = Tkinter.Text(frame,yscrollcommand=scroll.set)
    4209. 

  4209. 		button = Tkinter.Button(win)
    4210. 

  4210. 		# config
    4211. 

  4211. 		text.insert(Tkinter.END, string.join(txt,'\n'))
    4212. 

  4212. 		scroll.config(command=text.yview)
    4213. 

  4213. 		button.config(text=_('Close'), command=win.destroy)
    4214. 

  4214. 		button.focus_set()
    4215. 

  4215. 		# packing
    4216. 

  4216. 		text.pack(side='left', fill='both', expand=1)
    4217. 

  4217. 		scroll.pack(side='right', fill='y')
    4218. 

  4218. 		frame.pack(fill='both', expand=1)
    4219. 

  4219. 		button.pack(ipadx=30)
    4220. 

  4220. 	
    4221. 

  4221. 	def runprogram(self):
    4222. 

  4222. 		global CMDLINE_RAW
    4223. 

  4223. 		# prepare
    4224. 

  4224. 		self.target_name2key()
    4225. 

  4225. 		infile, target = self.infile.get(), self.target.get()
    4226. 

  4226. 		# sanity
    4227. 

  4227. 		if not target:
    4228. 

  4228. 			showwarning(my_name,_("You must select a target type!"))
    4229. 

  4229. 			return
    4230. 

  4230. 		if not infile:
    4231. 

  4231. 			showwarning(my_name,
    4232. 

  4232. 			   _("You must provide the source file location!"))
    4233. 

  4233. 			return
    4234. 

  4234. 		# compose cmdline
    4235. 

  4235. 		guiflags = []
    4236. 

  4236. 		real_cmdline_conf = ConfigMaster(CMDLINE_RAW).parse()
    4237. 

  4237. 		if real_cmdline_conf.has_key('infile'):
    4238. 

  4238. 			del real_cmdline_conf['infile']
    4239. 

  4239. 		if real_cmdline_conf.has_key('target'):
    4240. 

  4240. 			del real_cmdline_conf['target']
    4241. 

  4241. 		real_cmdline = CommandLine().compose_cmdline(real_cmdline_conf)
    4242. 

  4242. 		default_outfile = ConfigMaster().get_outfile_name(
    4243. 

  4243. 		     {'sourcefile':infile, 'outfile':'', 'target':target})
    4244. 

  4244. 		for opt in self.checks:
    4245. 

  4245. 			val = int(getattr(self, 'f_%s'%opt).get() or "0")
    4246. 

  4246. 			if opt == 'stdout': opt = 'outfile'
    4247. 

  4247. 			on_config  = self.conf.get(opt) or 0
    4248. 

  4248. 			on_cmdline = real_cmdline_conf.get(opt) or 0
    4249. 

  4249. 			if opt == 'outfile':
    4250. 

  4250. 				if on_config  == STDOUT: on_config = 1
    4251. 

  4251. 				else: on_config = 0
    4252. 

  4252. 				if on_cmdline == STDOUT: on_cmdline = 1
    4253. 

  4253. 				else: on_cmdline = 0
    4254. 

  4254. 			if val != on_config or (
    4255. 

  4255. 			  val == on_config == on_cmdline and
    4256. 

  4256. 			  real_cmdline_conf.has_key(opt)):
    4257. 

  4257. 				if val:
    4258. 

  4258. 					# was not set, but user selected on GUI
    4259. 

  4259. 					Debug("user turned  ON: %s"%opt)
    4260. 

  4260. 					if opt == 'outfile': opt = '-o-'
    4261. 

  4261. 					else: opt = '--%s'%opt
    4262. 

  4262. 				else:
    4263. 

  4263. 					# was set, but user deselected on GUI
    4264. 

  4264. 					Debug("user turned OFF: %s"%opt)
    4265. 

  4265. 					if opt == 'outfile':
    4266. 

  4266. 						opt = "-o%s"%default_outfile
    4267. 

  4267. 					else: opt = '--no-%s'%opt
    4268. 

  4268. 				guiflags.append(opt)
    4269. 

  4269. 		cmdline = [my_name, '-t', target] +real_cmdline \
    4270. 

  4270. 		          +guiflags +[infile]
    4271. 

  4271. 		Debug('Gui/Tk cmdline: %s'%cmdline,5)
    4272. 

  4272. 		# run!
    4273. 

  4273. 		cmdline_raw_orig = CMDLINE_RAW
    4274. 

  4274. 		try:
    4275. 

  4275. 			# fake the GUI cmdline as the real one, and parse file
    4276. 

  4276. 			CMDLINE_RAW = CommandLine().get_raw_config(cmdline[1:])
    4277. 

  4277. 			data = process_source_file(infile)
    4278. 

  4278. 			# on GUI, convert_* returns the data, not finish_him()
    4279. 

  4279. 			outlist, config = convert_this_files([data])
    4280. 

  4280. 			# on GUI and STDOUT, finish_him() returns the data
    4281. 

  4281. 			result = finish_him(outlist, config)
    4282. 

  4282. 			# show outlist in s a nice new window
    4283. 

  4283. 			if result:
    4284. 

  4284. 				outlist, config = result
    4285. 

  4285. 				title = _('%s: %s converted to %s')%(
    4286. 

  4286. 				  my_name, os.path.basename(infile),
    4287. 

  4287. 				  string.upper(config['target']))
    4288. 

  4288. 				self.scrollwindow(outlist, title)
    4289. 

  4289. 			# show the "file saved" message
    4290. 

  4290. 			else:
    4291. 

  4291. 				msg = "%s\n\n  %s\n%s\n\n  %s\n%s"%(
    4292. 

  4292. 				      _('Conversion done!'),
    4293. 

  4293. 				      _('FROM:'), infile,
    4294. 

  4294. 				      _('TO:'), config['outfile'])
    4295. 

  4295. 				showinfo(my_name, msg)
    4296. 

  4296. 		except error:         # common error (windowed), not quit
    4297. 

  4297. 			pass
    4298. 

  4298. 		except:               # fatal error (windowed and printed)
    4299. 

  4299. 			errormsg = getUnknownErrorMessage()
    4300. 

  4300. 			print errormsg
    4301. 

  4301. 			showerror(_('%s FATAL ERROR!')%my_name,errormsg)
    4302. 

  4302. 			self.exit()
    4303. 

  4303. 		CMDLINE_RAW = cmdline_raw_orig
    4304. 

  4304. 	
    4305. 

  4305. 	def mainwindow(self):
    4306. 

  4306. 		self.infile.set(self.conf.get('sourcefile') or '')
    4307. 

  4307. 		self.target.set(self.conf.get('target') or \
    4308. 

  4308. 		              _('-- select one --'))
    4309. 

  4309. 		outfile = self.conf.get('outfile')
    4310. 

  4310. 		if outfile == STDOUT:                  # map -o-
    4311. 

  4311. 			self.conf['stdout'] = 1
    4312. 

  4312. 		if self.conf.get('headers') == None:
    4313. 

  4313. 			self.conf['headers'] = 1       # map default
    4314. 

  4314. 		
    4315. 

  4315. 		action1 = _("Enter the source file location:")
    4316. 

  4316. 		action2 = _("Choose the target document type:")
    4317. 

  4317. 		action3 = _("Some options you may check:")
    4318. 

  4318. 		action4 = _("Some extra options:")
    4319. 

  4319. 		checks_txt = {
    4320. 

  4320. 		  'headers'   : _("Include headers on output"),
    4321. 

  4321. 		  'enum-title': _("Number titles (1, 1.1, 1.1.1, etc)"),
    4322. 

  4322. 		  'toc'       : _("Do TOC also (Table of Contents)"),
    4323. 

  4323. 		  'mask-email': _("Hide e-mails from SPAM robots"),
    4324. 

  4324. 		
    4325. 

  4325. 		  'toc-only'  : _("Just do TOC, nothing more"),
    4326. 

  4326. 		  'stdout'    : _("Dump to screen (Don't save target file)")
    4327. 

  4327. 		}
    4328. 

  4328. 		targets_menu = map(lambda x: TARGET_NAMES[x], TARGETS)
    4329. 

  4329. 		
    4330. 

  4330. 		# header
    4331. 

  4331. 		self.label("%s %s"%(string.upper(my_name), my_version),
    4332. 

  4332. 		     bg=self.bg2, fg=self.fg2).grid(columnspan=2, ipadx=10)
    4333. 

  4333. 		self.label(_("ONE source, MULTI targets")+'\n%s\n'%my_url,
    4334. 

  4334. 		     bg=self.bg1, fg=self.fg1).grid(columnspan=2)
    4335. 

  4335. 		self.row = 2
    4336. 

  4336. 		# choose input file
    4337. 

  4337. 		self.action(action1) ; self.frame_open()
    4338. 

  4338. 		e_infile = self.entry(textvariable=self.infile,width=25)
    4339. 

  4339. 		e_infile.grid(row=self.row, column=0, sticky='e')
    4340. 

  4340. 		if not self.infile.get(): e_infile.focus_set()
    4341. 

  4341. 		self.button(_("Browse"), self.askfile).grid(
    4342. 

  4342. 		    row=self.row, column=1, sticky='w', padx=10)
    4343. 

  4343. 		# show outfile name, style and encoding (if any)
    4344. 

  4344. 		txt = ''
    4345. 

  4345. 		if outfile:
    4346. 

  4346. 			txt = outfile
    4347. 

  4347. 			if outfile == STDOUT: txt = _('<screen>')
    4348. 

  4348. 			l_output = self.label(_('Output: ')+txt,
    4349. 

  4349. 			                fg=self.fg2,bg=self.bg2)
    4350. 

  4350. 			l_output.grid(columnspan=2, sticky='w')
    4351. 

  4351. 		for setting in ['style','encoding']:
    4352. 

  4352. 			if self.conf.get(setting):
    4353. 

  4353. 				name = string.capitalize(setting)
    4354. 

  4354. 				val  = self.conf[setting]
    4355. 

  4355. 				self.label('%s: %s'%(name, val),
    4356. 

  4356. 				     fg=self.fg2, bg=self.bg2).grid(
    4357. 

  4357. 				     columnspan=2, sticky='w')
    4358. 

  4358. 		# choose target
    4359. 

  4359. 		self.frame_close() ; self.action(action2)
    4360. 

  4360. 		self.frame_open()
    4361. 

  4361. 		self.target_key2name()
    4362. 

  4362. 		self.menu(self.target_name, targets_menu).grid(
    4363. 

  4363. 		     columnspan=2, sticky='w')
    4364. 

  4364. 		# options checkboxes label
    4365. 

  4365. 		self.frame_close() ; self.action(action3)
    4366. 

  4366. 		self.frame_open()
    4367. 

  4367. 		# compose options check boxes, example:
    4368. 

  4368. 		# self.check(checks_txt['toc'],1,variable=self.f_toc)
    4369. 

  4369. 		for check in self.checks:
    4370. 

  4370. 			# extra options label
    4371. 

  4371. 			if check == 'toc-only':
    4372. 

  4372. 				self.frame_close() ; self.action(action4)
    4373. 

  4373. 				self.frame_open()
    4374. 

  4374. 			txt = checks_txt[check]
    4375. 

  4375. 			var = getattr(self, 'f_'+check)
    4376. 

  4376. 			checked = self.conf.get(check)
    4377. 

  4377. 			self.check(txt,checked,variable=var)
    4378. 

  4378. 		self.frame_close()
    4379. 

  4379. 		# spacer and buttons
    4380. 

  4380. 		self.label('').grid() ; self.row = self.row + 1
    4381. 

  4381. 		b_quit = self.button(_("Quit"), self.exit)
    4382. 

  4382. 		b_quit.grid(row=self.row, column=0, sticky='w', padx=30)
    4383. 

  4383. 		b_conv = self.button(_("Convert!"), self.runprogram)
    4384. 

  4384. 		b_conv.grid(row=self.row, column=1, sticky='e', padx=30)
    4385. 

  4385. 		if self.target.get() and self.infile.get():
    4386. 

  4386. 			b_conv.focus_set()
    4387. 

  4387. 		
    4388. 

  4388. 		# as documentation told me
    4389. 

  4389. 		if sys.platform[:3] == 'win':
    4390. 

  4390. 			self.root.iconify()
    4391. 

  4391. 			self.root.update()
    4392. 

  4392. 			self.root.deiconify()
    4393. 

  4393. 		
    4394. 

  4394. 		self.root.mainloop()
    4395. 

  4395. 

  4396. 

  4397. ##############################################################################
    4398. 

  4398. ##############################################################################
    4399. 

  4399. 

  4400. def exec_command_line(user_cmdline=[]):
    4401. 

  4401. 	global CMDLINE_RAW, RC_RAW, DEBUG, VERBOSE, QUIET, GUI, Error
    4402. 

  4402. 	
    4403. 

  4403. 	# extract command line data
    4404. 

  4404. 	cmdline_data = user_cmdline or sys.argv[1:]
    4405. 

  4405. 	CMDLINE_RAW = CommandLine().get_raw_config(cmdline_data, relative=1)
    4406. 

  4406. 	cmdline_parsed = ConfigMaster(CMDLINE_RAW).parse()
    4407. 

  4407. 	DEBUG   = cmdline_parsed.get('debug'  ) or 0
    4408. 

  4408. 	VERBOSE = cmdline_parsed.get('verbose') or 0
    4409. 

  4409. 	QUIET   = cmdline_parsed.get('quiet'  ) or 0
    4410. 

  4410. 	GUI     = cmdline_parsed.get('gui'    ) or 0
    4411. 

  4411. 	infiles = cmdline_parsed.get('infile' ) or []
    4412. 

  4412. 	
    4413. 

  4413. 	Message(_("Txt2tags %s processing begins")%my_version,1)
    4414. 

  4414. 	
    4415. 

  4415. 	# the easy ones
    4416. 

  4416. 	if cmdline_parsed.get('help'   ): Quit(USAGE)
    4417. 

  4417. 	if cmdline_parsed.get('version'): Quit(VERSIONSTR)
    4418. 

  4418. 	
    4419. 

  4419. 	# multifile haters
    4420. 

  4420. 	if len(infiles) > 1:
    4421. 

  4421. 		errmsg=_("Option --%s can't be used with multiple input files")
    4422. 

  4422. 		for option in ['gui','dump-config']:
    4423. 

  4423. 			if cmdline_parsed.get(option):
    4424. 

  4424. 				Error(errmsg%option)
    4425. 

  4425. 	
    4426. 

  4426. 	Debug("system platform: %s"%sys.platform)
    4427. 

  4427. 	Debug("python version: %s"%(string.split(sys.version,'(')[0]))
    4428. 

  4428. 	Debug("line break char: %s"%repr(LB))
    4429. 

  4429. 	Debug("command line: %s"%sys.argv)
    4430. 

  4430. 	Debug("command line raw config: %s"%CMDLINE_RAW,1)
    4431. 

  4431. 	
    4432. 

  4432. 	# extract RC file config
    4433. 

  4433. 	if cmdline_parsed.get('rc') == 0:
    4434. 

  4434. 		Message(_("Ignoring user configuration file"),1)
    4435. 

  4435. 	else:
    4436. 

  4436. 		rc_file = get_rc_path()
    4437. 

  4437. 		if os.path.isfile(rc_file):
    4438. 

  4438. 			Message(_("Loading user configuration file"),1)
    4439. 

  4439. 			RC_RAW = ConfigLines(file=rc_file).get_raw_config()
    4440. 

  4440. 		
    4441. 

  4441. 		Debug("rc file: %s"%rc_file)
    4442. 

  4442. 		Debug("rc file raw config: %s"%RC_RAW,1)
    4443. 

  4443. 	
    4444. 

  4444. 	# get all infiles config (if any)
    4445. 

  4445. 	infiles_config = get_infiles_config(infiles)
    4446. 

  4446. 	
    4447. 

  4447. 	# is GUI available?
    4448. 

  4448. 	# try to load and start GUI interface for --gui
    4449. 

  4449. 	# if program was called with no arguments, try GUI also
    4450. 

  4450. 	if GUI or not infiles:
    4451. 

  4451. 		try:
    4452. 

  4452. 			load_GUI_resources()
    4453. 

  4453. 			Debug("GUI resources OK (Tk module is installed)")
    4454. 

  4454. 			winbox = Gui()
    4455. 

  4455. 			Debug("GUI display OK")
    4456. 

  4456. 			GUI = 1
    4457. 

  4457. 		except:
    4458. 

  4458. 			Debug("GUI Error: no Tk module or no DISPLAY")
    4459. 

  4459. 			GUI = 0
    4460. 

  4460. 	
    4461. 

  4461. 	# user forced --gui, but it's not available
    4462. 

  4462. 	if cmdline_parsed.get('gui') and not GUI:
    4463. 

  4463. 		print getTraceback(); print
    4464. 

  4464. 		Error("Sorry, I can't run my Graphical Interface - GUI\n"
    4465. 

  4465. 		      "- Check if Python Tcl/Tk module is installed (Tkinter)\n"
    4466. 

  4466. 		      "- Make sure you are in a graphical environment (like X)")
    4467. 

  4467. 	
    4468. 

  4468. 	# Okay, we will use GUI
    4469. 

  4469. 	if GUI:
    4470. 

  4470. 		Message(_("We are on GUI interface"),1)
    4471. 

  4471. 		
    4472. 

  4472. 		# redefine Error function to raise exception instead sys.exit()
    4473. 

  4473. 		def Error(msg):
    4474. 

  4474. 			showerror(_('txt2tags ERROR!'), msg)
    4475. 

  4475. 			raise error
    4476. 

  4476. 		
    4477. 

  4477. 		# if no input file, get RC+cmdline config, else full config
    4478. 

  4478. 		if not infiles:
    4479. 

  4479. 			gui_conf = ConfigMaster(RC_RAW+CMDLINE_RAW).parse()
    4480. 

  4480. 		else:
    4481. 

  4481. 			try   : gui_conf = infiles_config[0][0]
    4482. 

  4482. 			except: gui_conf = {}
    4483. 

  4483. 		
    4484. 

  4484. 		# sanity is needed to set outfile and other things
    4485. 

  4485. 		gui_conf = ConfigMaster().sanity(gui_conf, gui=1)
    4486. 

  4486. 		Debug("GUI config: %s"%gui_conf,5)
    4487. 

  4487. 		
    4488. 

  4488. 		# insert config and populate the nice window!
    4489. 

  4489. 		winbox.load_config(gui_conf)
    4490. 

  4490. 		winbox.mainwindow()
    4491. 

  4491. 	
    4492. 

  4492. 	# console mode rocks forever!
    4493. 

  4493. 	else:
    4494. 

  4494. 		Message(_("We are on Command Line interface"),1)
    4495. 

  4495. 		
    4496. 

  4496. 		# called with no arguments, show error
    4497. 

  4497. 		if not infiles: Error(_('Missing input file (try --help)'))
    4498. 

  4498. 		
    4499. 

  4499. 		convert_this_files(infiles_config)
    4500. 

  4500. 	
    4501. 

  4501. 	Message(_("Txt2tags finished sucessfuly"),1)
    4502. 

  4502. 

  4503. if __name__ == '__main__':
    4504. 

  4504. 	try:
    4505. 

  4505. 		exec_command_line()
    4506. 

  4506. 	except error, msg:
    4507. 

  4507. 		sys.stderr.write("%s\n"%msg)
    4508. 

  4508. 		sys.stderr.flush()
    4509. 

  4509. 		sys.exit(1)
    4510. 

  4510. 	except SystemExit:
    4511. 

  4511. 		pass
    4512. 

  4512. 	except:
    4513. 

  4513. 		print getUnknownErrorMessage()
    4514. 

  4514. 	Quit()
    4515. 

  4515. 

  4516. 

  4517. # vim: ts=8
    4518. 

  4518.