PageRenderTime 79ms CodeModel.GetById 18ms RepoModel.GetById 0ms app.codeStats 0ms

/old/txt2tags-2.1.py

http://txt2tags.googlecode.com/
Python | 4229 lines | 3805 code | 158 blank | 266 comment | 160 complexity | 4e16129e62cf5a83c262b3a3d8a3d1c0 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. 

    121. 

  121. ##############################################################################
    122. 

  122. 

  123. # User config (1=ON, 0=OFF)
    124. 

  124. 

  125. USE_I18N    = 1   # use gettext for i18ned messages?        (default is 1)
    126. 

  126. COLOR_DEBUG = 1   # show debug messages in colors?          (default is 1)
    127. 

  127. HTML_LOWER  = 0   # use lowercased HTML tags instead upper? (default is 0)
    128. 

  128. 

  129. ##############################################################################
    130. 

  130. 

  131. 

  132. # these are all the core Python modules used by txt2tags (KISS!)
    133. 

  133. import re, string, os, sys, time, getopt
    134. 

  134. 

  135. # program information
    136. 

  136. my_url = 'http://txt2tags.sf.net'
    137. 

  137. my_name = 'txt2tags'
    138. 

  138. my_email = 'verde@aurelio.net'
    139. 

  139. my_version = '2.1'
    140. 

  140. 

  141. # i18n - just use if available
    142. 

  142. if USE_I18N:
    143. 

  143. 	try:
    144. 

  144. 		import gettext
    145. 

  145. 		# if your locale dir is different, change it here
    146. 

  146. 		cat = gettext.Catalog('txt2tags',localedir='/usr/share/locale/')
    147. 

  147. 		_ = cat.gettext
    148. 

  148. 	except:
    149. 

  149. 		_ = lambda x:x
    150. 

  150. else:
    151. 

  151. 	_ = lambda x:x
    152. 

  152. 

  153. # FLAGS   : the conversion related flags  , may be used in %!options
    154. 

  154. # OPTIONS : the conversion related options, may be used in %!options
    155. 

  155. # ACTIONS : the other behaviour modifiers, valid on command line only
    156. 

  156. # MACROS  : the valid macros with their default values for formatting
    157. 

  157. # SETTINGS: global miscelaneous settings, valid on RC file only
    158. 

  158. # CONFIG_KEYWORDS: the valid %!key:val keywords
    159. 

  159. #
    160. 

  160. # FLAGS and OPTIONS are configs that affect the converted document.
    161. 

  161. # They usually have also a --no-<option> to turn them OFF.
    162. 

  162. # ACTIONS are needed because when doing multiple input files, strange
    163. 

  163. # behaviour would be found, as use command line interface for the
    164. 

  164. # first file and gui for the second. There is no --no-<action>.
    165. 

  165. # --version and --help inside %!options are also odd
    166. 

  166. #
    167. 

  167. TARGETS  = ['html', 'xhtml', 'sgml', 'tex', 'man', 'mgp', 'moin', 'pm6', 'txt']
    168. 

  168. FLAGS    = {'headers'    :1 , 'enum-title' :0 , 'mask-email' :0 ,
    169. 

  169.             'toc-only'   :0 , 'toc'        :0 , 'rc'         :1 ,
    170. 

  170.             'css-sugar'  :0 , 'css-suggar' :0 , 'quiet'      :0 }
    171. 

  171. OPTIONS  = {'target'     :'', 'toc-level'  :3 , 'style'      :'',
    172. 

  172.             'infile'     :'', 'outfile'    :'', 'encoding'   :'',
    173. 

  173.             'split'      :0 , 'lang'       :''}
    174. 

  174. ACTIONS  = {'help'       :0 , 'version'    :0 , 'gui'        :0 ,
    175. 

  175.             'verbose'    :0 , 'debug'      :0 , 'dump-config':0 }
    176. 

  176. MACROS   = {'date' : '%Y%m%d',  'infile': '%f',
    177. 

  177.             'mtime': '%Y%m%d', 'outfile': '%f'}
    178. 

  178. SETTINGS = {}         # for future use
    179. 

  179. CONFIG_KEYWORDS = [
    180. 

  180.             'target', 'encoding', 'style', 'options', 'preproc','postproc',
    181. 

  181.             'guicolors']
    182. 

  182. TARGET_NAMES = {
    183. 

  183.   'html' : _('HTML page'),
    184. 

  184.   'xhtml': _('XHTML page'),
    185. 

  185.   'sgml' : _('SGML document'),
    186. 

  186.   'tex'  : _('LaTeX document'),
    187. 

  187.   'man'  : _('UNIX Manual page'),
    188. 

  188.   'mgp'  : _('Magic Point presentation'),
    189. 

  189.   'moin' : _('MoinMoin page'),
    190. 

  190.   'pm6'  : _('PageMaker 6.0 document'),
    191. 

  191.   'txt'  : _('Plain Text'),
    192. 

  192. }
    193. 

  193. 

  194. DEBUG = 0     # do not edit here, please use --debug
    195. 

  195. VERBOSE = 0   # do not edit here, please use -v, -vv or -vvv
    196. 

  196. QUIET = 0     # do not edit here, please use --quiet
    197. 

  197. GUI = 0
    198. 

  198. AUTOTOC = 1
    199. 

  199. RC_RAW = []
    200. 

  200. CMDLINE_RAW = []
    201. 

  201. CONF = {}
    202. 

  202. BLOCK = None
    203. 

  203. regex = {}
    204. 

  204. TAGS = {}
    205. 

  205. rules = {}
    206. 

  206. 

  207. lang = 'english'
    208. 

  208. TARGET = ''
    209. 

  209. 

  210. STDIN = STDOUT = '-'
    211. 

  211. ESCCHAR   = '\x00'
    212. 

  212. SEPARATOR = '\x01'
    213. 

  213. LISTNAMES = {'-':'list', '+':'numlist', ':':'deflist'}
    214. 

  214. LINEBREAK = {'default':'\n', 'win':'\r\n', 'mac':'\r'}
    215. 

  215. RCFILE    = {'default':'.txt2tagsrc', 'win':'_t2trc'}
    216. 

  216. 

  217. # plataform specific settings
    218. 

  218. LB = LINEBREAK.get(sys.platform[:3]) or LINEBREAK['default']
    219. 

  219. RC =    RCFILE.get(sys.platform[:3]) or    RCFILE['default']
    220. 

  220. 

  221. # identify a development version
    222. 

  222. #dev_suffix = '-dev'+time.strftime('%m%d',time.localtime(time.time()))
    223. 

  223. #my_version = my_version + dev_suffix
    224. 

  224. 

  225. VERSIONSTR = _("%s version %s <%s>")%(my_name,my_version,my_url)
    226. 

  226. 

  227. USAGE = string.join([
    228. 

  228. '',
    229. 

  229. _("Usage: %s [OPTIONS] [infile.t2t ...]") % my_name,
    230. 

  230. '',
    231. 

  231. _("  -t, --target        set target document type. currently supported:"),
    232. 

  232. '                      %s' % re.sub(r"[]'[]",'',repr(TARGETS)),
    233. 

  233. _("  -i, --infile=FILE   set FILE as the input file name ('-' for STDIN)"),
    234. 

  234. _("  -o, --outfile=FILE  set FILE as the output file name ('-' for STDOUT)"),
    235. 

  235. _("  -n, --enum-title    enumerate all title lines as 1, 1.1, 1.1.1, etc"),
    236. 

  236. _("  -H, --no-headers    suppress header, title and footer contents"),
    237. 

  237. _("      --headers       show header, title and footer contents (default ON)"),
    238. 

  238. _("      --encoding      set target file encoding (utf-8, iso-8859-1, etc)"),
    239. 

  239. _("      --style=FILE    use FILE as the document style (like HTML CSS)"),
    240. 

  240. _("      --css-sugar     insert CSS-friendly tags for HTML and XHTML targets"),
    241. 

  241. _("      --mask-email    hide email from spam robots. x@y.z turns <x (a) y z>"),
    242. 

  242. _("      --toc           add TOC (Table of Contents) to target document"),
    243. 

  243. _("      --toc-only      print document TOC and exit"),
    244. 

  244. _("      --toc-level=N   set maximum TOC level (depth) to N"),
    245. 

  245. _("      --rc            read user config file ~/.txt2tagsrc (default ON)"),
    246. 

  246. _("      --gui           invoke Graphical Tk Interface"),
    247. 

  247. _("  -q, --quiet         quiet mode, suppress all output (except errors)"),
    248. 

  248. _("  -v, --verbose       print informative messages during conversion"),
    249. 

  249. _("  -h, --help          print this help information and exit"),
    250. 

  250. _("  -V, --version       print program version and exit"),
    251. 

  251. _("      --dump-config   print all the config found and exit"),
    252. 

  252. '',
    253. 

  253. _("Turn OFF options:"),
    254. 

  254. "     --no-outfile, --no-infile, --no-style, --no-encoding, --no-headers",
    255. 

  255. "     --no-toc, --no-toc-only, --no-mask-email, --no-enum-title, --no-rc",
    256. 

  256. "     --no-css-sugar, --no-quiet",
    257. 

  257. '',
    258. 

  258. _("Example:\n     %s -t html --toc myfile.t2t") % my_name,
    259. 

  259. '',
    260. 

  260. _("By default, converted output is saved to 'infile.<target>'."),
    261. 

  261. _("Use --outfile to force an output file name."),
    262. 

  262. _("If  input file is '-', reads from STDIN."),
    263. 

  263. _("If output file is '-', dumps output to STDOUT."),
    264. 

  264. ''
    265. 

  265. ], '\n')
    266. 

  266. 

  267. 

  268. ##############################################################################
    269. 

  269. 

  270. 

  271. # here is all the target's templates
    272. 

  272. # you may edit them to fit your needs
    273. 

  273. #  - the %(HEADERn)s strings represent the Header lines
    274. 

  274. #  - the %(STYLE)s string is changed by --style contents
    275. 

  275. #  - the %(ENCODING)s string is changed by --encoding contents
    276. 

  276. #  - if any of the above is empty, the full line is removed
    277. 

  277. #  - use %% to represent a literal %
    278. 

  278. #
    279. 

  279. HEADER_TEMPLATE = {
    280. 

  280.   'txt': """\
    281. 

  281. %(HEADER1)s
    282. 

  282. %(HEADER2)s
    283. 

  283. %(HEADER3)s
    284. 

  284. """,
    285. 

    286. 

  286.   'sgml': """\
    287. 

  287. <!doctype linuxdoc system>
    288. 

  288. <article>
    289. 

  289. <title>%(HEADER1)s
    290. 

  290. <author>%(HEADER2)s
    291. 

  291. <date>%(HEADER3)s
    292. 

  292. """,
    293. 

    294. 

  294.   'html': """\
    295. 

  295. <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
    296. 

  296. <HTML>
    297. 

  297. <HEAD>
    298. 

  298. <META NAME="generator" CONTENT="http://txt2tags.sf.net">
    299. 

  299. <META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=%(ENCODING)s">
    300. 

  300. <LINK REL="stylesheet" TYPE="text/css" HREF="%(STYLE)s">
    301. 

  301. <TITLE>%(HEADER1)s</TITLE>
    302. 

  302. </HEAD><BODY BGCOLOR="white" TEXT="black">
    303. 

  303. <P ALIGN="center"><CENTER><H1>%(HEADER1)s</H1>
    304. 

  304. <FONT SIZE="4">
    305. 

  305. <I>%(HEADER2)s</I><BR>
    306. 

  306. %(HEADER3)s
    307. 

  307. </FONT></CENTER>
    308. 

  308. """,
    309. 

    310. 

  310.   'htmlcss': """\
    311. 

  311. <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
    312. 

  312. <HTML>
    313. 

  313. <HEAD>
    314. 

  314. <META NAME="generator" CONTENT="http://txt2tags.sf.net">
    315. 

  315. <META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=%(ENCODING)s">
    316. 

  316. <LINK REL="stylesheet" TYPE="text/css" HREF="%(STYLE)s">
    317. 

  317. <TITLE>%(HEADER1)s</TITLE>
    318. 

  318. </HEAD>
    319. 

  319. <BODY>
    320. 

  320. 

  321. <DIV CLASS="header" ID="header">
    322. 

  322. <H1>%(HEADER1)s</H1>
    323. 

  323. <H2>%(HEADER2)s</H2>
    324. 

  324. <H3>%(HEADER3)s</H3>
    325. 

  325. </DIV>
    326. 

  326. """,
    327. 

    328. 

  328.   'xhtml': """\
    329. 

  329. <?xml version="1.0"?>
    330. 

  330. <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"\
    331. 

  331.  "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
    332. 

  332. <html xmlns="http://www.w3.org/1999/xhtml">
    333. 

  333. <head>
    334. 

  334. <title>%(HEADER1)s</title>
    335. 

  335. <meta name="generator" content="http://txt2tags.sf.net" />
    336. 

  336. <meta http-equiv="Content-Type" content="text/html; charset=%(ENCODING)s" />
    337. 

  337. <link rel="stylesheet" type="text/css" href="%(STYLE)s" />
    338. 

  338. </head>
    339. 

  339. <body bgcolor="white" text="black">
    340. 

  340. <div align="center">
    341. 

  341. <h1>%(HEADER1)s</h1>
    342. 

  342. <h2>%(HEADER2)s</h2>
    343. 

  343. <h3>%(HEADER3)s</h3>
    344. 

  344. </div>
    345. 

  345. """,
    346. 

    347. 

  347.   'xhtmlcss': """\
    348. 

  348. <?xml version="1.0"?>
    349. 

  349. <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"\
    350. 

  350.  "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
    351. 

  351. <html xmlns="http://www.w3.org/1999/xhtml">
    352. 

  352. <head>
    353. 

  353. <title>%(HEADER1)s</title>
    354. 

  354. <meta name="generator" content="http://txt2tags.sf.net" />
    355. 

  355. <meta http-equiv="Content-Type" content="text/html; charset=%(ENCODING)s" />
    356. 

  356. <link rel="stylesheet" type="text/css" href="%(STYLE)s" />
    357. 

  357. </head>
    358. 

  358. <body>
    359. 

  359. 

  360. <div class="header" id="header">
    361. 

  361. <h1>%(HEADER1)s</h1>
    362. 

  362. <h2>%(HEADER2)s</h2>
    363. 

  363. <h3>%(HEADER3)s</h3>
    364. 

  364. </div>
    365. 

  365. """,
    366. 

    367. 

  367.   'man': """\
    368. 

  368. .TH "%(HEADER1)s" 1 "%(HEADER3)s" "%(HEADER2)s"
    369. 

  369. """,
    370. 

    371. 

  371. # TODO style to <HR>
    372. 

  372.   'pm6': """\
    373. 

  373. <PMTags1.0 win><C-COLORTABLE ("Preto" 1 0 0 0)
    374. 

  374. ><@Normal=
    375. 

  375.   <FONT "Times New Roman"><CCOLOR "Preto"><SIZE 11>
    376. 

  376.   <HORIZONTAL 100><LETTERSPACE 0><CTRACK 127><CSSIZE 70><C+SIZE 58.3>
    377. 

  377.   <C-POSITION 33.3><C+POSITION 33.3><P><CBASELINE 0><CNOBREAK 0><CLEADING -0.05>
    378. 

  378.   <GGRID 0><GLEFT 7.2><GRIGHT 0><GFIRST 0><G+BEFORE 7.2><G+AFTER 0>
    379. 

  379.   <GALIGNMENT "justify"><GMETHOD "proportional"><G& "ENGLISH">
    380. 

  380.   <GPAIRS 12><G%% 120><GKNEXT 0><GKWIDOW 0><GKORPHAN 0><GTABS $>
    381. 

  381.   <GHYPHENATION 2 34 0><GWORDSPACE 75 100 150><GSPACE -5 0 25>
    382. 

  382. ><@Bullet=<@-PARENT "Normal"><FONT "Abadi MT Condensed Light">
    383. 

  383.   <GLEFT 14.4><G+BEFORE 2.15><G%% 110><GTABS(25.2 l "")>
    384. 

  384. ><@PreFormat=<@-PARENT "Normal"><FONT "Lucida Console"><SIZE 8><CTRACK 0>
    385. 

  385.   <GLEFT 0><G+BEFORE 0><GALIGNMENT "left"><GWORDSPACE 100 100 100><GSPACE 0 0 0>
    386. 

  386. ><@Title1=<@-PARENT "Normal"><FONT "Arial"><SIZE 14><B>
    387. 

  387.   <GCONTENTS><GLEFT 0><G+BEFORE 0><GALIGNMENT "left">
    388. 

  388. ><@Title2=<@-PARENT "Title1"><SIZE 12><G+BEFORE 3.6>
    389. 

  389. ><@Title3=<@-PARENT "Title1"><SIZE 10><GLEFT 7.2><G+BEFORE 7.2>
    390. 

  390. ><@Title4=<@-PARENT "Title3">
    391. 

  391. ><@Title5=<@-PARENT "Title3">
    392. 

  392. ><@Quote=<@-PARENT "Normal"><SIZE 10><I>>
    393. 

  393. 

  394. %(HEADER1)s
    395. 

  395. %(HEADER2)s
    396. 

  396. %(HEADER3)s
    397. 

  397. """,
    398. 

    399. 

  399.   'mgp': """\
    400. 

  400. #!/usr/X11R6/bin/mgp -t 90
    401. 

  401. %%deffont "normal"    xfont  "utopia-medium-r", charset "iso8859-1"
    402. 

  402. %%deffont "normal-i"  xfont  "utopia-medium-i", charset "iso8859-1"
    403. 

  403. %%deffont "normal-b"  xfont  "utopia-bold-r"  , charset "iso8859-1"
    404. 

  404. %%deffont "normal-bi" xfont  "utopia-bold-i"  , charset "iso8859-1"
    405. 

  405. %%deffont "mono"      xfont "courier-medium-r", charset "iso8859-1"
    406. 

  406. %%default 1 size 5
    407. 

  407. %%default 2 size 8, fore "yellow", font "normal-b", center
    408. 

  408. %%default 3 size 5, fore "white",  font "normal", left, prefix "  "
    409. 

  409. %%tab 1 size 4, vgap 30, prefix "     ", icon arc "red" 40, leftfill
    410. 

  410. %%tab 2 prefix "            ", icon arc "orange" 40, leftfill
    411. 

  411. %%tab 3 prefix "                   ", icon arc "brown" 40, leftfill
    412. 

  412. %%tab 4 prefix "                          ", icon arc "darkmagenta" 40, leftfill
    413. 

  413. %%tab 5 prefix "                                ", icon arc "magenta" 40, leftfill
    414. 

  414. %%%%------------------------- end of headers -----------------------------
    415. 

  415. %%page
    416. 

  416. 

  417. 

  418. 

  419. 

  420. 

  421. %%size 10, center, fore "yellow"
    422. 

  422. %(HEADER1)s
    423. 

  423. 

  424. %%font "normal-i", size 6, fore "white", center
    425. 

  425. %(HEADER2)s
    426. 

  426. 

  427. %%font "mono", size 7, center
    428. 

  428. %(HEADER3)s
    429. 

  429. """,
    430. 

    431. 

  431. # TODO please, improve me!
    432. 

  432.   'moin': """\
    433. 

  433. '''%(HEADER1)s'''
    434. 

  434. 

  435. ''%(HEADER2)s''
    436. 

  436. 

  437. %(HEADER3)s
    438. 

  438. """,
    439. 

    440. 

  440.   'tex': \
    441. 

  441. r"""\documentclass[11pt,a4paper]{article}
    442. 

  442. \usepackage{amsfonts,graphicx,url}
    443. 

  443. \usepackage[%(ENCODING)s]{inputenc}  %% char encoding
    444. 

  444. \usepackage{%(STYLE)s}  %% user defined package
    445. 

  445. \pagestyle{plain}   %% do page numbering ('empty' turns off)
    446. 

  446. \frenchspacing      %% no aditional spaces after periods
    447. 

  447. \setlength{\parskip}{8pt}\parindent=0pt  %% no paragraph indentation
    448. 

  448. %% uncomment next line for fancy PDF output on Adobe Acrobat Reader
    449. 

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

  450. 

  451. \title{%(HEADER1)s}
    452. 

  452. \author{%(HEADER2)s}
    453. 

  453. \begin{document}
    454. 

  454. \date{%(HEADER3)s}
    455. 

  455. \maketitle
    456. 

  456. \clearpage
    457. 

  457. """
    458. 

  458. }
    459. 

  459. 

  460. 

  461. ##############################################################################
    462. 

  462. 

  463. 

  464. def getTags(config):
    465. 

  465. 	"Returns all the known tags for the specified target"
    466. 

  466. 	
    467. 

  467. 	keys = [
    468. 

  468. 	'paragraphOpen','paragraphClose',
    469. 

  469. 	'title1','title2','title3','title4','title5',
    470. 

  470. 	'numtitle1','numtitle2','numtitle3','numtitle4','numtitle5',
    471. 

  471. 	'blockVerbOpen','blockVerbClose',
    472. 

  472. 	'blockQuoteOpen','blockQuoteClose','blockQuoteLine',
    473. 

  473. 	'fontMonoOpen','fontMonoClose',
    474. 

  474. 	'fontBoldOpen','fontBoldClose',
    475. 

  475. 	'fontItalicOpen','fontItalicClose',
    476. 

  476. 	'fontUnderlineOpen','fontUnderlineClose',
    477. 

  477. 	'listOpen','listClose',
    478. 

  478. 	'listItemOpen','listItemClose','listItemLine',
    479. 

  479. 	'numlistOpen','numlistClose',
    480. 

  480. 	'numlistItemOpen','numlistItemClose','numlistItemLine',
    481. 

  481. 	'deflistOpen','deflistClose',
    482. 

  482. 	'deflistItem1Open','deflistItem1Close',
    483. 

  483. 	'deflistItem2Open','deflistItem2Close',
    484. 

  484. 	'bar1','bar2',
    485. 

  485. 	'url','urlMark','email','emailMark',
    486. 

  486. 	'img',
    487. 

  487. 	'tableOpen','tableClose',
    488. 

  488. 	'tableRowOpen','tableRowClose','tableRowSep',
    489. 

  489. 	'tableCellOpen','tableCellClose','tableCellSep',
    490. 

  490. 	'tableTitleCellOpen','tableTitleCellClose','tableTitleCellSep',
    491. 

  491. 	'tableTitleRowOpen','tableTitleRowClose',
    492. 

  492. 	'tableBorder', 'tableAlignLeft', 'tableAlignCenter',
    493. 

  493. 	'tableCellAlignLeft','tableCellAlignRight','tableCellAlignCenter',
    494. 

  494. 	'tableColAlignLeft','tableColAlignRight','tableColAlignCenter',
    495. 

  495. 	'tableColAlignSep',
    496. 

  496. 	'anchor','comment','pageBreak',
    497. 

  497. 	'TOC','tocOpen','tocClose',
    498. 

  498. 	'bodyOpen','bodyClose',
    499. 

  499. 	'EOD'
    500. 

  500. 	]
    501. 

  501. 	
    502. 

  502. 	alltags = {
    503. 

  503. 	
    504. 

  504. 	'txt': {
    505. 

  505. 	   'title1'              : '  \a'      ,
    506. 

  506. 	   'title2'              : '\t\a'      ,
    507. 

  507. 	   'title3'              : '\t\t\a'    ,
    508. 

  508. 	   'title4'              : '\t\t\t\a'  ,
    509. 

  509. 	   'title5'              : '\t\t\t\t\a',
    510. 

  510. 	   'blockQuoteLine'      : '\t'        ,
    511. 

  511. 	   'listItemOpen'        : '- '        ,
    512. 

  512. 	   'numlistItemOpen'     : '\a. '      ,
    513. 

  513. 	   'bar1'                : '\a'        ,
    514. 

  514. 	   'bar2'                : '\a'        ,
    515. 

  515. 	   'url'                 : '\a'        ,
    516. 

  516. 	   'urlMark'             : '\a (\a)'   ,
    517. 

  517. 	   'email'               : '\a'        ,
    518. 

  518. 	   'emailMark'           : '\a (\a)'   ,
    519. 

  519. 	   'img'                 : '[\a]'      ,
    520. 

  520. 	},
    521. 

  521. 	
    522. 

  522. 	'html': {
    523. 

  523. 	   'paragraphOpen'       : '<P>'            ,
    524. 

  524. 	   'paragraphClose'      : '</P>'           ,
    525. 

  525. 	   'title1'              : '~A~<H1>\a</H1>' ,
    526. 

  526. 	   'title2'              : '~A~<H2>\a</H2>' ,
    527. 

  527. 	   'title3'              : '~A~<H3>\a</H3>' ,
    528. 

  528. 	   'title4'              : '~A~<H4>\a</H4>' ,
    529. 

  529. 	   'title5'              : '~A~<H5>\a</H5>' ,
    530. 

  530. 	   'blockVerbOpen'       : '<PRE>'          ,
    531. 

  531. 	   'blockVerbClose'      : '</PRE>'         ,
    532. 

  532. 	   'blockQuoteOpen'      : '<BLOCKQUOTE>'   ,
    533. 

  533. 	   'blockQuoteClose'     : '</BLOCKQUOTE>'  ,
    534. 

  534. 	   'fontMonoOpen'        : '<CODE>'         ,
    535. 

  535. 	   'fontMonoClose'       : '</CODE>'        ,
    536. 

  536. 	   'fontBoldOpen'        : '<B>'            ,
    537. 

  537. 	   'fontBoldClose'       : '</B>'           ,
    538. 

  538. 	   'fontItalicOpen'      : '<I>'            ,
    539. 

  539. 	   'fontItalicClose'     : '</I>'           ,
    540. 

  540. 	   'fontUnderlineOpen'   : '<U>'            ,
    541. 

  541. 	   'fontUnderlineClose'  : '</U>'           ,
    542. 

  542. 	   'listOpen'            : '<UL>'           ,
    543. 

  543. 	   'listClose'           : '</UL>'          ,
    544. 

  544. 	   'listItemOpen'        : '<LI>'           ,
    545. 

  545. 	   'numlistOpen'         : '<OL>'           ,
    546. 

  546. 	   'numlistClose'        : '</OL>'          ,
    547. 

  547. 	   'numlistItemOpen'     : '<LI>'           ,
    548. 

  548. 	   'deflistOpen'         : '<DL>'           ,
    549. 

  549. 	   'deflistClose'        : '</DL>'          ,
    550. 

  550. 	   'deflistItem1Open'    : '<DT>'           ,
    551. 

  551. 	   'deflistItem1Close'   : '</DT>'          ,
    552. 

  552. 	   'deflistItem2Open'    : '<DD>'           ,
    553. 

  553. 	   'bar1'                : '<HR NOSHADE SIZE=1>'        ,
    554. 

  554. 	   'bar2'                : '<HR NOSHADE SIZE=5>'        ,
    555. 

  555. 	   'url'                 : '<A HREF="\a">\a</A>'        ,
    556. 

  556. 	   'urlMark'             : '<A HREF="\a">\a</A>'        ,
    557. 

  557. 	   'email'               : '<A HREF="mailto:\a">\a</A>' ,
    558. 

  558. 	   'emailMark'           : '<A HREF="mailto:\a">\a</A>' ,
    559. 

  559. 	   'img'                :'<IMG ALIGN="~A~" SRC="\a" BORDER="0" ALT="">',
    560. 

  560. 	   'tableOpen'           : '<TABLE~A~ CELLPADDING="4"~B~>',
    561. 

  561. 	   'tableClose'          : '</TABLE>'       ,
    562. 

  562. 	   'tableRowOpen'        : '<TR>'           ,
    563. 

  563. 	   'tableRowClose'       : '</TR>'          ,
    564. 

  564. 	   'tableCellOpen'       : '<TD\a>'         ,
    565. 

  565. 	   'tableCellClose'      : '</TD>'          ,
    566. 

  566. 	   'tableTitleCellOpen'  : '<TH>'           ,
    567. 

  567. 	   'tableTitleCellClose' : '</TH>'          ,
    568. 

  568. 	   'tableBorder'         : ' BORDER="1"'    ,
    569. 

  569. 	   'tableAlignCenter'    : ' ALIGN="center"',
    570. 

  570. 	   'tableCellAlignRight' : ' ALIGN="right"' ,
    571. 

  571. 	   'tableCellAlignCenter': ' ALIGN="center"',
    572. 

  572. 	   'anchor'              : '<A NAME="\a"></A>\n',
    573. 

  573. 	   'comment'             : '<!-- \a -->'    ,
    574. 

  574. 	   'EOD'                 : '</BODY></HTML>'
    575. 

  575. 	},
    576. 

  576. 	
    577. 

  577. 	#TIP xhtml inherits all HTML definitions (lowercased)
    578. 

  578. 	#TIP http://www.w3.org/TR/xhtml1/#guidelines
    579. 

  579. 	#TIP http://www.htmlref.com/samples/Chapt17/17_08.htm
    580. 

  580. 	'xhtml': {
    581. 

  581. 	   'listItemClose'       : '</li>'          ,
    582. 

  582. 	   'numlistItemClose'    : '</li>'          ,
    583. 

  583. 	   'deflistItem2Close'   : '</dd>'          ,
    584. 

  584. 	   'bar1'                : '<hr class="light" />',
    585. 

  585. 	   'bar2'                : '<hr class="heavy" />',
    586. 

  586. 	   'anchor'              : '<a id="\a" name="\a"></a>\n',
    587. 

  587. 	   'img'               :'<img align="~A~" src="\a" border="0" alt=""/>',
    588. 

  588. 	},
    589. 

  589. 	
    590. 

  590. 	'sgml': {
    591. 

  591. 	   'paragraphOpen'       : '<p>'                ,
    592. 

  592. 	   'title1'              : '<sect>\a~A~<p>'     ,
    593. 

  593. 	   'title2'              : '<sect1>\a~A~<p>'    ,
    594. 

  594. 	   'title3'              : '<sect2>\a~A~<p>'    ,
    595. 

  595. 	   'title4'              : '<sect3>\a~A~<p>'    ,
    596. 

  596. 	   'title5'              : '<sect4>\a~A~<p>'    ,
    597. 

  597. 	   'blockVerbOpen'       : '<tscreen><verb>'    ,
    598. 

  598. 	   'blockVerbClose'      : '</verb></tscreen>'  ,
    599. 

  599. 	   'blockQuoteOpen'      : '<quote>'            ,
    600. 

  600. 	   'blockQuoteClose'     : '</quote>'           ,
    601. 

  601. 	   'fontMonoOpen'        : '<tt>'               ,
    602. 

  602. 	   'fontMonoClose'       : '</tt>'              ,
    603. 

  603. 	   'fontBoldOpen'        : '<bf>'               ,
    604. 

  604. 	   'fontBoldClose'       : '</bf>'              ,
    605. 

  605. 	   'fontItalicOpen'      : '<em>'               ,
    606. 

  606. 	   'fontItalicClose'     : '</em>'              ,
    607. 

  607. 	   'fontUnderlineOpen'   : '<bf><em>'           ,
    608. 

  608. 	   'fontUnderlineClose'  : '</em></bf>'         ,
    609. 

  609. 	   'listOpen'            : '<itemize>'          ,
    610. 

  610. 	   'listClose'           : '</itemize>'         ,
    611. 

  611. 	   'listItemOpen'        : '<item>'             ,
    612. 

  612. 	   'numlistOpen'         : '<enum>'             ,
    613. 

  613. 	   'numlistClose'        : '</enum>'            ,
    614. 

  614. 	   'numlistItemOpen'     : '<item>'             ,
    615. 

  615. 	   'deflistOpen'         : '<descrip>'          ,
    616. 

  616. 	   'deflistClose'        : '</descrip>'         ,
    617. 

  617. 	   'deflistItem1Open'    : '<tag>'              ,
    618. 

  618. 	   'deflistItem1Close'   : '</tag>'             ,
    619. 

  619. 	   'bar1'                : '<!-- \a -->'        ,
    620. 

  620. 	   'bar2'                : '<!-- \a -->'        ,
    621. 

  621. 	   'url'                 : '<htmlurl url="\a" name="\a">'        ,
    622. 

  622. 	   'urlMark'             : '<htmlurl url="\a" name="\a">'        ,
    623. 

  623. 	   'email'               : '<htmlurl url="mailto:\a" name="\a">' ,
    624. 

  624. 	   'emailMark'           : '<htmlurl url="mailto:\a" name="\a">' ,
    625. 

  625. 	   'img'                 : '<figure><ph vspace=""><img src="\a">'+\
    626. 

  626. 	                           '</figure>'                           ,
    627. 

  627. 	   'tableOpen'           : '<table><tabular ca="~C~">'           ,
    628. 

  628. 	   'tableClose'          : '</tabular></table>' ,
    629. 

  629. 	   'tableRowSep'         : '<rowsep>'           ,
    630. 

  630. 	   'tableCellSep'        : '<colsep>'           ,
    631. 

  631. 	   'tableColAlignLeft'   : 'l'                  ,
    632. 

  632. 	   'tableColAlignRight'  : 'r'                  ,
    633. 

  633. 	   'tableColAlignCenter' : 'c'                  ,
    634. 

  634. 	   'comment'             : '<!-- \a -->'        ,
    635. 

  635. 	   'anchor'              : '<label id="\a">'    ,
    636. 

  636. 	   'TOC'                 : '<toc>'              ,
    637. 

  637. 	   'EOD'                 : '</article>'
    638. 

  638. 	},
    639. 

  639. 	
    640. 

  640. 	'tex': {
    641. 

  641. 	   'title1'              : '\n\section*{\a}',
    642. 

  642. 	   'title2'              : '\\subsection*{\a}'       ,
    643. 

  643. 	   'title3'              : '\\subsubsection*{\a}'    ,
    644. 

  644. 	   # title 4/5: DIRTY: para+BF+\\+\n
    645. 

  645. 	   'title4'              : '\\paragraph{}\\textbf{\a}\\\\\n',
    646. 

  646. 	   'title5'              : '\\paragraph{}\\textbf{\a}\\\\\n',
    647. 

  647. 	   'numtitle1'           : '\n\section{\a}',
    648. 

  648. 	   'numtitle2'           : '\\subsection{\a}'       ,
    649. 

  649. 	   'numtitle3'           : '\\subsubsection{\a}'    ,
    650. 

  650. 	   'blockVerbOpen'       : '\\begin{verbatim}'   ,
    651. 

  651. 	   'blockVerbClose'      : '\\end{verbatim}'     ,
    652. 

  652. 	   'blockQuoteOpen'      : '\\begin{quotation}'  ,
    653. 

  653. 	   'blockQuoteClose'     : '\\end{quotation}'    ,
    654. 

  654. 	   'fontMonoOpen'        : '\\texttt{'           ,
    655. 

  655. 	   'fontMonoClose'       : '}'                   ,
    656. 

  656. 	   'fontBoldOpen'        : '\\textbf{'           ,
    657. 

  657. 	   'fontBoldClose'       : '}'                   ,
    658. 

  658. 	   'fontItalicOpen'      : '\\textit{'           ,
    659. 

  659. 	   'fontItalicClose'     : '}'                   ,
    660. 

  660. 	   'fontUnderlineOpen'   : '\\underline{'        ,
    661. 

  661. 	   'fontUnderlineClose'  : '}'                   ,
    662. 

  662. 	   'listOpen'            : '\\begin{itemize}'    ,
    663. 

  663. 	   'listClose'           : '\\end{itemize}'      ,
    664. 

  664. 	   'listItemOpen'        : '\\item '             ,
    665. 

  665. 	   'numlistOpen'         : '\\begin{enumerate}'  ,
    666. 

  666. 	   'numlistClose'        : '\\end{enumerate}'    ,
    667. 

  667. 	   'numlistItemOpen'     : '\\item '             ,
    668. 

  668. 	   'deflistOpen'         : '\\begin{description}',
    669. 

  669. 	   'deflistClose'        : '\\end{description}'  ,
    670. 

  670. 	   'deflistItem1Open'    : '\\item['             ,
    671. 

  671. 	   'deflistItem1Close'   : ']'                   ,
    672. 

  672. 	   'bar1'                : '\n\\hrulefill{}\n'   ,
    673. 

  673. 	   'bar2'                : '\n\\rule{\linewidth}{1mm}\n',
    674. 

  674. 	   'url'                 : '\\url{\a}'                  ,
    675. 

  675. 	   'urlMark'             : '\\textit{\a} (\\url{\a})'   ,
    676. 

  676. 	   'email'               : '\\url{\a}'                  ,
    677. 

  677. 	   'emailMark'           : '\\textit{\a} (\\url{\a})'   ,
    678. 

  678. 	   'img'                 : '\\includegraphics{\a}',
    679. 

  679. 	   'tableOpen'           : '\\begin{center}\\begin{tabular}{|~C~|}',
    680. 

  680. 	   'tableClose'          : '\\end{tabular}\\end{center}',
    681. 

  681. 	   'tableRowOpen'        : '\\hline ' ,
    682. 

  682. 	   'tableRowClose'       : ' \\\\'    ,
    683. 

  683. 	   'tableCellSep'        : ' & '      ,
    684. 

  684. 	   'tableColAlignLeft'   : 'l'        ,
    685. 

  685. 	   'tableColAlignRight'  : 'r'        ,
    686. 

  686. 	   'tableColAlignCenter' : 'c'        ,
    687. 

  687. 	   'tableColAlignSep'    : '|'        ,
    688. 

  688. 	   'comment'             : '% \a'     ,
    689. 

  689. 	   'TOC'                 : '\\tableofcontents',
    690. 

  690. 	   'pageBreak'           : '\\clearpage',
    691. 

  691. 	   'EOD'                 : '\\end{document}'
    692. 

  692. 	},
    693. 

  693. 	
    694. 

  694. 	'moin': {
    695. 

  695. 	   'title1'              : '= \a ='        ,
    696. 

  696. 	   'title2'              : '== \a =='      ,
    697. 

  697. 	   'title3'              : '=== \a ==='    ,
    698. 

  698. 	   'title4'              : '==== \a ===='  ,
    699. 

  699. 	   'title5'              : '===== \a =====',
    700. 

  700. 	   'blockVerbOpen'       : '{{{'           ,
    701. 

  701. 	   'blockVerbClose'      : '}}}'           ,
    702. 

  702. 	   'blockQuoteLine'      : '  '            ,
    703. 

  703. 	   'fontMonoOpen'        : '{{{'           ,
    704. 

  704. 	   'fontMonoClose'       : '}}}'           ,
    705. 

  705. 	   'fontBoldOpen'        : "'''"           ,
    706. 

  706. 	   'fontBoldClose'       : "'''"           ,
    707. 

  707. 	   'fontItalicOpen'      : "''"            ,
    708. 

  708. 	   'fontItalicClose'     : "''"            ,
    709. 

  709. 	   'fontUnderlineOpen'   : "__"            ,
    710. 

  710. 	   'fontUnderlineClose'  : "__"            ,
    711. 

  711. 	   'listItemOpen'        : ' * '           ,
    712. 

  712. 	   'numlistItemOpen'     : ' \a. '         ,
    713. 

  713. 	   'bar1'                : '----'          ,
    714. 

  714. 	   'bar2'                : '----'          ,
    715. 

  715. 	   'url'                 : '[\a]'          ,
    716. 

  716. 	   'urlMark'             : '[\a \a]'       ,
    717. 

  717. 	   'email'               : '[\a]'          ,
    718. 

  718. 	   'emailMark'           : '[\a \a]'       ,
    719. 

  719. 	   'img'                 : '[\a]'          ,
    720. 

  720. 	   'tableRowOpen'        : '||'            ,
    721. 

  721. 	   'tableCellOpen'       : '\a'            ,
    722. 

  722. 	   'tableCellClose'      : '||'            ,
    723. 

  723. 	   'tableTitleCellClose' : '||'            ,
    724. 

  724. 	   'tableCellAlignRight' : '<)>'           ,
    725. 

  725. 	   'tableCellAlignCenter': '<:>'           ,
    726. 

  726. 	   'comment'             : '## \a'         ,
    727. 

  727. 	   'TOC'                 : '[[TableOfContents]]'
    728. 

  728. 	},
    729. 

  729. 	
    730. 

  730. 	'mgp': {
    731. 

  731. 	   'paragraphOpen'       : '%font "normal", size 5'     ,
    732. 

  732. 	   'title1'              : '%page\n\n\a\n'              ,
    733. 

  733. 	   'title2'              : '%page\n\n\a\n'              ,
    734. 

  734. 	   'title3'              : '%page\n\n\a\n'              ,
    735. 

  735. 	   'title4'              : '%page\n\n\a\n'              ,
    736. 

  736. 	   'title5'              : '%page\n\n\a\n'              ,
    737. 

  737. 	   'blockVerbOpen'       : '%font "mono"'               ,
    738. 

  738. 	   'blockVerbClose'      : '%font "normal"'             ,
    739. 

  739. 	   'blockQuoteOpen'      : '%prefix "       "'          ,
    740. 

  740. 	   'blockQuoteClose'     : '%prefix "  "'               ,
    741. 

  741. 	   'fontMonoOpen'        : '\n%cont, font "mono"\n'     ,
    742. 

  742. 	   'fontMonoClose'       : '\n%cont, font "normal"\n'   ,
    743. 

  743. 	   'fontBoldOpen'        : '\n%cont, font "normal-b"\n' ,
    744. 

  744. 	   'fontBoldClose'       : '\n%cont, font "normal"\n'   ,
    745. 

  745. 	   'fontItalicOpen'      : '\n%cont, font "normal-i"\n' ,
    746. 

  746. 	   'fontItalicClose'     : '\n%cont, font "normal"\n'   ,
    747. 

  747. 	   'fontUnderlineOpen'   : '\n%cont, fore "cyan"\n'     ,
    748. 

  748. 	   'fontUnderlineClose'  : '\n%cont, fore "white"\n'    ,
    749. 

  749. 	   'listItemLine'        : '\t'                         ,
    750. 

  750. 	   'numlistItemLine'     : '\t'                         ,
    751. 

  751. 	   'deflistItem1Open'    : '\t\n%cont, font "normal-b"\n',
    752. 

  752. 	   'deflistItem1Close'   : '\n%cont, font "normal"\n'   ,
    753. 

  753. 	   'bar1'                : '%bar "white" 5'             ,
    754. 

  754. 	   'bar2'                : '%pause'                     ,
    755. 

  755. 	   'url'                 : '\n%cont, fore "cyan"\n\a'   +\
    756. 

  756. 	                           '\n%cont, fore "white"\n'    ,
    757. 

  757. 	   'urlMark'             : '\a \n%cont, fore "cyan"\n\a'+\
    758. 

  758. 	                           '\n%cont, fore "white"\n'    ,
    759. 

  759. 	   'email'               : '\n%cont, fore "cyan"\n\a'   +\
    760. 

  760. 	                           '\n%cont, fore "white"\n'    ,
    761. 

  761. 	   'emailMark'           : '\a \n%cont, fore "cyan"\n\a'+\
    762. 

  762. 	                           '\n%cont, fore "white"\n'    ,
    763. 

  763. 	   'img'                 : '\n%~A~\n%newimage "\a"\n%left\n',
    764. 

  764. 	   'comment'             : '%% \a'                      ,
    765. 

  765. 	   'pageBreak'           : '%page\n\n\n'                ,
    766. 

  766. 	   'EOD'                 : '%%EOD'
    767. 

  767. 	},
    768. 

  768. 	
    769. 

  769. 	# man groff_man ; man 7 groff
    770. 

  770. 	'man': {
    771. 

  771. 	   'paragraphOpen'       : '.P'     ,
    772. 

  772. 	   'title1'              : '.SH \a' ,
    773. 

  773. 	   'title2'              : '.SS \a' ,
    774. 

  774. 	   'title3'              : '.SS \a' ,
    775. 

  775. 	   'title4'              : '.SS \a' ,
    776. 

  776. 	   'title5'              : '.SS \a' ,
    777. 

  777. 	   'blockVerbOpen'       : '.nf'    ,
    778. 

  778. 	   'blockVerbClose'      : '.fi\n'  ,
    779. 

  779. 	   'blockQuoteOpen'      : '.RS'    ,
    780. 

  780. 	   'blockQuoteClose'     : '.RE'    ,
    781. 

  781. 	   'fontBoldOpen'        : '\\fB'   ,
    782. 

  782. 	   'fontBoldClose'       : '\\fR'   ,
    783. 

  783. 	   'fontItalicOpen'      : '\\fI'   ,
    784. 

  784. 	   'fontItalicClose'     : '\\fR'   ,
    785. 

  785. 	   'listOpen'            : '.RS'    ,
    786. 

  786. 	   'listItemOpen'        : '.IP \(bu 3\n',
    787. 

  787. 	   'listClose'           : '.RE'    ,
    788. 

  788. 	   'numlistOpen'         : '.RS'    ,
    789. 

  789. 	   'numlistItemOpen'     : '.IP \a. 3\n',
    790. 

  790. 	   'numlistClose'        : '.RE'    ,
    791. 

  791. 	   'deflistItem1Open'    : '.TP\n'  ,
    792. 

  792. 	   'bar1'                : '\n\n'   ,
    793. 

  793. 	   'bar2'                : '\n\n'   ,
    794. 

  794. 	   'url'                 : '\a'     ,
    795. 

  795. 	   'urlMark'             : '\a (\a)',
    796. 

  796. 	   'email'               : '\a'     ,
    797. 

  797. 	   'emailMark'           : '\a (\a)',
    798. 

  798. 	   'img'                 : '\a'     ,
    799. 

  799. 	   'tableOpen'           : '.TS\n~A~~B~tab(^); ~C~.',
    800. 

  800. 	   'tableClose'          : '.TE'     ,
    801. 

  801. 	   'tableRowOpen'        : ' '       ,
    802. 

  802. 	   'tableCellSep'        : '^'       ,
    803. 

  803. 	   'tableAlignCenter'    : 'center, ',
    804. 

  804. 	   'tableBorder'         : 'allbox, ',
    805. 

  805. 	   'tableColAlignLeft'   : 'l'       ,
    806. 

  806. 	   'tableColAlignRight'  : 'r'       ,
    807. 

  807. 	   'tableColAlignCenter' : 'c'       ,
    808. 

  808. 	   'comment'             : '.\\" \a'
    809. 

  809. 	},
    810. 

  810. 	
    811. 

  811. 	'pm6': {
    812. 

  812. 	   'paragraphOpen'       : '<@Normal:>'    ,
    813. 

  813. 	   'title1'              : '\n<@Title1:>\a',
    814. 

  814. 	   'title2'              : '\n<@Title2:>\a',
    815. 

  815. 	   'title3'              : '\n<@Title3:>\a',
    816. 

  816. 	   'title4'              : '\n<@Title4:>\a',
    817. 

  817. 	   'title5'              : '\n<@Title5:>\a',
    818. 

  818. 	   'blockVerbOpen'       : '<@PreFormat:>' ,
    819. 

  819. 	   'blockQuoteLine'      : '<@Quote:>'     ,
    820. 

  820. 	   'fontMonoOpen'        : '<FONT "Lucida Console"><SIZE 9>' ,
    821. 

  821. 	   'fontMonoClose'       : '<SIZE$><FONT$>',
    822. 

  822. 	   'fontBoldOpen'        : '<B>'           ,
    823. 

  823. 	   'fontBoldClose'       : '<P>'           ,
    824. 

  824. 	   'fontItalicOpen'      : '<I>'           ,
    825. 

  825. 	   'fontItalicClose'     : '<P>'           ,
    826. 

  826. 	   'fontUnderlineOpen'   : '<U>'           ,
    827. 

  827. 	   'fontUnderlineClose'  : '<P>'           ,
    828. 

  828. 	   'listOpen'            : '<@Bullet:>'    ,
    829. 

  829. 	   'listItemOpen'        : '\x95\t'        ,  # \x95 == ~U
    830. 

  830. 	   'numlistOpen'         : '<@Bullet:>'    ,
    831. 

  831. 	   'numlistItemOpen'     : '\x95\t'        ,
    832. 

  832. 	   'bar1'                : '\a'            ,
    833. 

  833. 	   'bar2'                : '\a'            ,
    834. 

  834. 	   'url'                 : '<U>\a<P>'      ,  # underline
    835. 

  835. 	   'urlMark'             : '\a <U>\a<P>'   ,
    836. 

  836. 	   'email'               : '\a'            ,
    837. 

  837. 	   'emailMark'           : '\a \a'         ,
    838. 

  838. 	   'img'                 : '\a'
    839. 

  839. 	}
    840. 

  840. 	}
    841. 

  841. 	
    842. 

  842. 	# exceptions for --css-sugar
    843. 

  843. 	if config['css-sugar'] and config['target'] in ('html','xhtml'):
    844. 

  844. 		# change just HTML because XHTML inherits it
    845. 

  845. 		htmltags = alltags['html']
    846. 

  846. 		# table with no cellpadding
    847. 

  847. 		htmltags['tableOpen'] = string.replace(
    848. 

  848. 			htmltags['tableOpen'], ' CELLPADDING="4"', '')
    849. 

  849. 		# DIVs
    850. 

  850. 		htmltags['tocOpen' ] = '<DIV CLASS="toc" ID="toc">'
    851. 

  851. 		htmltags['tocClose'] = '</DIV>'
    852. 

  852. 		htmltags['bodyOpen'] = '<DIV CLASS="body" ID="body">'
    853. 

  853. 		htmltags['bodyClose']= '</DIV>'
    854. 

  854. 	
    855. 

  855. 	# make the HTML -> XHTML inheritance
    856. 

  856. 	xhtml = alltags['html'].copy()
    857. 

  857. 	for key in xhtml.keys(): xhtml[key] = string.lower(xhtml[key])
    858. 

  858. 	# some like HTML tags as lowercase, some don't... (headers out)
    859. 

  859. 	if HTML_LOWER: alltags['html'] = xhtml.copy()
    860. 

  860. 	xhtml.update(alltags['xhtml'])
    861. 

  861. 	alltags['xhtml'] = xhtml.copy()
    862. 

  862. 	
    863. 

  863. 	# compose the target tags dictionary
    864. 

  864. 	tags = {}
    865. 

  865. 	target_tags = alltags[config['target']].copy()
    866. 

  866. 	
    867. 

  867. 	for key in keys: tags[key] = ''     # create empty keys
    868. 

  868. 	for key in target_tags.keys():
    869. 

  869. 		tags[key] = maskEscapeChar(target_tags[key]) # populate
    870. 

  870. 	
    871. 

  871. 	return tags
    872. 

  872. 

  873. 

  874. ##############################################################################
    875. 

  875. 

  876. 

  877. def getRules(config):
    878. 

  878. 	"Returns all the target-specific syntax rules"
    879. 

  879. 	
    880. 

  880. 	ret = {}
    881. 

  881. 	allrules = [
    882. 

  882. 	
    883. 

  883. 	 # target rules (ON/OFF)
    884. 

  884. 	  'linkable',             # target supports external links
    885. 

  885. 	  'tableable',            # target supports tables
    886. 

  886. 	  'imglinkable',          # target supports images as links
    887. 

  887. 	  'imgalignable',         # target supports image alignment
    888. 

  888. 	  'imgasdefterm',         # target supports image as definition term
    889. 

  889. 	  'autonumberlist',       # target supports numbered lists natively
    890. 

  890. 	  'autonumbertitle',      # target supports numbered titles natively
    891. 

  891. 	  'parainsidelist',       # lists items supports paragraph
    892. 

  892. 	  'spacedlistitem',       # lists support blank lines between items
    893. 

  893. 	  'listnotnested',        # lists cannot be nested
    894. 

  894. 	  'quotenotnested',       # quotes cannot be nested
    895. 

  895. 	  'verbblocknotescaped',  # don't escape specials in verb block
    896. 

  896. 	  'verbblockfinalescape', # do final escapes in verb block
    897. 

  897. 	  'escapeurl',            # escape special in link URL
    898. 

  898. 	  'onelinepara',          # dump paragraph as a single long line
    899. 

  899. 	  'tabletitlerowinbold',  # manually bold any cell on table titles
    900. 

  900. 	  'tablecellstrip',       # strip extra spaces from each table cell
    901. 

  901. 	  'barinsidequote',       # bars are allowed inside quote blocks
    902. 

  902. 	  'finalescapetitle',     # perform final escapes on title lines
    903. 

  903. 	  'autotocnewpagebefore', # break page before automatic TOC
    904. 

  904. 	  'autotocnewpageafter',  # break page after automatic TOC
    905. 

  905. 	  'autotocwithbars',      # automatic TOC surrounded by bars
    906. 

  906. 	
    907. 

  907. 	# target code beautify (ON/OFF)
    908. 

  908. 	  'indentverbblock',      # add leading spaces to verb block lines
    909. 

  909. 	  'breaktablecell',       # break lines after any table cell
    910. 

  910. 	  'breaktablelineopen',   # break line after opening table line
    911. 

  911. 	  'notbreaklistopen',     # don't break line after opening a new list
    912. 

  912. 	  'notbreakparaopen',     # don't break line after opening a new para
    913. 

  913. 	  'keepquoteindent',      # don't remove the leading TABs on quotes
    914. 

  914. 	  'keeplistindent',       # don't remove the leading spaces on lists
    915. 

  915. 	  'blankendmotherlist',   # append a blank line at the mother list end
    916. 

  916. 	  'blankendtable',        # append a blank line at the table end
    917. 

  917. 	  'blankendautotoc',      # append a blank line at the auto TOC end
    918. 

  918. 	  'tagnotindentable',     # tags must be placed at the line begining
    919. 

  919. 	
    920. 

  920. 	# value settings
    921. 

  921. 	  'listmaxdepth',         # maximum depth for lists
    922. 

  922. 	  'tablecellaligntype'    # type of table cell align: cell, column
    923. 

  923. 	]
    924. 

  924. 	
    925. 

  925. 	rules_bank = {
    926. 

  926. 	  'txt' : {
    927. 

  927. 	    'indentverbblock':1,
    928. 

  928. 	    'spacedlistitem':1,
    929. 

  929. 	    'parainsidelist':1,
    930. 

  930. 	    'keeplistindent':1,
    931. 

  931. 	    'barinsidequote':1,
    932. 

  932. 	    'autotocwithbars':1,
    933. 

  933. 	    'blankendmotherlist':1
    934. 

  934. 	    },
    935. 

  935. 	  'html': {
    936. 

  936. 	    'indentverbblock':1,
    937. 

  937. 	    'linkable':1,
    938. 

  938. 	    'escapeurl':1,
    939. 

  939. 	    'imglinkable':1,
    940. 

  940. 	    'imgalignable':1,
    941. 

  941. 	    'imgasdefterm':1,
    942. 

  942. 	    'autonumberlist':1,
    943. 

  943. 	    'spacedlistitem':1,
    944. 

  944. 	    'parainsidelist':1,
    945. 

  945. 	    'blankendmotherlist':1,
    946. 

  946. 	    'tableable':1,
    947. 

  947. 	    'tablecellstrip':1,
    948. 

  948. 	    'blankendtable':1,
    949. 

  949. 	    'breaktablecell':1,
    950. 

  950. 	    'breaktablelineopen':1,
    951. 

  951. 	    'keeplistindent':1,
    952. 

  952. 	    'keepquoteindent':1,
    953. 

  953. 	    'barinsidequote':1,
    954. 

  954. 	    'autotocwithbars':1,
    955. 

  955. 	    'tablecellaligntype':'cell'
    956. 

  956. 	    },
    957. 

  957. 	  #TIP xhtml inherits all HTML rules
    958. 

  958. 	  'xhtml': {
    959. 

  959. 	    },
    960. 

  960. 	  'sgml': {
    961. 

  961. 	    'linkable':1,
    962. 

  962. 	    'escapeurl':1,
    963. 

  963. 	    'autonumberlist':1,
    964. 

  964. 	    'spacedlistitem':1,
    965. 

  965. 	    'blankendmotherlist':1,
    966. 

  966. 	    'tableable':1,
    967. 

  967. 	    'tablecellstrip':1,
    968. 

  968. 	    'blankendtable':1,
    969. 

  969. 	    'blankendautotoc':1,
    970. 

  970. 	    'quotenotnested':1,
    971. 

  971. 	    'keeplistindent':1,
    972. 

  972. 	    'keepquoteindent':1,
    973. 

  973. 	    'barinsidequote':1,
    974. 

  974. 	    'finalescapetitle':1,
    975. 

  975. 	    'tablecellaligntype':'column'
    976. 

  976. 	    },
    977. 

  977. 	  'mgp' : {
    978. 

  978. 	    'blankendmotherlist':1,
    979. 

  979. 	    'tagnotindentable':1,
    980. 

  980. 	    'spacedlistitem':1,
    981. 

  981. 	    'imgalignable':1,
    982. 

  982. 	    'autotocnewpagebefore':1,
    983. 

  983. 	    },
    984. 

  984. 	  'tex' : {
    985. 

  985. 	    'autonumberlist':1,
    986. 

  986. 	    'autonumbertitle':1,
    987. 

  987. 	    'spacedlistitem':1,
    988. 

  988. 	    'blankendmotherlist':1,
    989. 

  989. 	    'tableable':1,
    990. 

  990. 	    'tablecellstrip':1,
    991. 

  991. 	    'tabletitlerowinbold':1,
    992. 

  992. 	    'blankendtable':1,
    993. 

  993. 	    'verbblocknotescaped':1,
    994. 

  994. 	    'keeplistindent':1,
    995. 

  995. 	    'listmaxdepth':4,
    996. 

  996. 	    'barinsidequote':1,
    997. 

  997. 	    'finalescapetitle':1,
    998. 

  998. 	    'autotocnewpageafter':1,
    999. 

  999. 	    'tablecellaligntype':'column'
    1000. 

  1000. 	    },
    1001. 

  1001. 	  'moin': {
    1002. 

  1002. 	    'spacedlistitem':1,
    1003. 

  1003. 	    'linkable':1,
    1004. 

  1004. 	    'blankendmotherlist':1,
    1005. 

  1005. 	    'keeplistindent':1,
    1006. 

  1006. 	    'tableable':1,
    1007. 

  1007. 	    'barinsidequote':1,
    1008. 

  1008. 	    'blankendtable':1,
    1009. 

  1009. 	    'tabletitlerowinbold':1,
    1010. 

  1010. 	    'tablecellstrip':1,
    1011. 

  1011. 	    'autotocwithbars':1,
    1012. 

  1012. 	    'tablecellaligntype':'cell'
    1013. 

  1013. 	    },
    1014. 

  1014. 	  'man' : {
    1015. 

  1015. 	    'spacedlistitem':1,
    1016. 

  1016. 	    'indentverbblock':1,
    1017. 

  1017. 	    'blankendmotherlist':1,
    1018. 

  1018. 	    'tagnotindentable':1,
    1019. 

  1019. 	    'tableable':1,
    1020. 

  1020. 	    'tablecellaligntype':'column',
    1021. 

  1021. 	    'tabletitlerowinbold':1,
    1022. 

  1022. 	    'tablecellstrip':1,
    1023. 

  1023. 	    'blankendtable':1,
    1024. 

  1024. 	    'keeplistindent':0,
    1025. 

  1025. 	    'barinsidequote':1,
    1026. 

  1026. 	    'parainsidelist':0,
    1027. 

  1027. 	    },
    1028. 

  1028. 	  'pm6' : {
    1029. 

  1029. 	    'keeplistindent':1,
    1030. 

  1030. 	    'verbblockfinalescape':1,
    1031. 

  1031. 	    #TODO add support for these - maybe set a JOINNEXT char and
    1032. 

  1032. 	    #     do it on addLineBreaks()
    1033. 

  1033. 	    'notbreaklistopen':1,
    1034. 

  1034. 	    'notbreakparaopen':1,
    1035. 

  1035. 	    'barinsidequote':1,
    1036. 

  1036. 	    'autotocwithbars':1,
    1037. 

  1037. 	    'onelinepara':1,
    1038. 

  1038. 	    }
    1039. 

  1039. 	}
    1040. 

  1040. 	
    1041. 

  1041. 	# exceptions for --css-sugar
    1042. 

  1042. 	if config['css-sugar'] and config['target'] in ('html','xhtml'):
    1043. 

  1043. 		rules_bank['html']['indentverbblock'] = 0
    1044. 

  1044. 		rules_bank['html']['autotocwithbars'] = 0
    1045. 

  1045. 	
    1046. 

  1046. 	# get the target specific rules
    1047. 

  1047. 	if config['target'] == 'xhtml':
    1048. 

  1048. 		myrules = rules_bank['html'].copy()   # inheritance
    1049. 

  1049. 		myrules.update(rules_bank['xhtml'])   # get XHTML specific
    1050. 

  1050. 	else:
    1051. 

  1051. 		myrules = rules_bank[config['target']].copy()
    1052. 

  1052. 	
    1053. 

  1053. 	# populate return dictionary
    1054. 

  1054. 	for key in allrules: ret[key] = 0        # reset all
    1055. 

  1055. 	ret.update(myrules)                      # get rules
    1056. 

  1056. 	
    1057. 

  1057. 	return ret
    1058. 

  1058. 

  1059. 

  1060. ##############################################################################
    1061. 

  1061. 

  1062. 

  1063. def getRegexes():
    1064. 

  1064. 	"Returns all the regexes used to find the t2t marks"
    1065. 

  1065. 	
    1066. 

  1066. 	bank = {
    1067. 

  1067. 	'blockVerbOpen':
    1068. 

  1068. 		re.compile(r'^```\s*$'),
    1069. 

  1069. 	'blockVerbClose':
    1070. 

  1070. 		re.compile(r'^```\s*$'),
    1071. 

  1071. 	'blockRawOpen':
    1072. 

  1072. 		re.compile(r'^"""\s*$'),
    1073. 

  1073. 	'blockRawClose':
    1074. 

  1074. 		re.compile(r'^"""\s*$'),
    1075. 

  1075. 	'quote':
    1076. 

  1076. 		re.compile(r'^\t+'),
    1077. 

  1077. 	'1lineVerb':
    1078. 

  1078. 		re.compile(r'^``` (?=.)'),
    1079. 

  1079. 	'1lineRaw':
    1080. 

  1080. 		re.compile(r'^""" (?=.)'),
    1081. 

  1081. 	# mono, raw, bold, italic, underline:
    1082. 

  1082. 	# - marks must be glued with the contents, no boundary spaces
    1083. 

  1083. 	# - they are greedy, so in ****bold****, turns to <b>**bold**</b>
    1084. 

  1084. 	'fontMono':
    1085. 

  1085. 		re.compile(  r'``([^\s](|.*?[^\s])`*)``'),
    1086. 

  1086. 	'raw':
    1087. 

  1087. 		re.compile(  r'""([^\s](|.*?[^\s])"*)""'),
    1088. 

  1088. 	'fontBold':
    1089. 

  1089. 		re.compile(r'\*\*([^\s](|.*?[^\s])\**)\*\*'),
    1090. 

  1090. 	'fontItalic':
    1091. 

  1091. 		re.compile(  r'//([^\s](|.*?[^\s])/*)//'),
    1092. 

  1092. 	'fontUnderline':
    1093. 

  1093. 		re.compile(  r'__([^\s](|.*?[^\s])_*)__'),
    1094. 

  1094. 	'list':
    1095. 

  1095. 		re.compile(r'^( *)(-) (?=[^ ])'),
    1096. 

  1096. 	'numlist':
    1097. 

  1097. 		re.compile(r'^( *)(\+) (?=[^ ])'),
    1098. 

  1098. 	'deflist':
    1099. 

  1099. 		re.compile(r'^( *)(:) (.*)$'),
    1100. 

  1100. 	'listclose':
    1101. 

  1101. 		re.compile(r'^( *)([-+:])\s*$'),
    1102. 

  1102. 	'bar':
    1103. 

  1103. 		re.compile(r'^(\s*)([_=-]{20,})\s*$'),
    1104. 

  1104. 	'table':
    1105. 

  1105. 		re.compile(r'^ *\|\|? '),
    1106. 

  1106. 	'blankline':
    1107. 

  1107. 		re.compile(r'^\s*$'),
    1108. 

  1108. 	'comment':
    1109. 

  1109. 		re.compile(r'^%'),
    1110. 

  1110. 	
    1111. 

  1111. 	# auxiliar tag regexes
    1112. 

  1112. 	'_imgAlign'     : re.compile(r'~A~',re.I),
    1113. 

  1113. 	'_tableAlign'   : re.compile(r'~A~',re.I),
    1114. 

  1114. 	'_anchor'       : re.compile(r'~A~',re.I),
    1115. 

  1115. 	'_tableBorder'  : re.compile(r'~B~',re.I),
    1116. 

  1116. 	'_tableColAlign': re.compile(r'~C~',re.I),
    1117. 

  1117. 	}
    1118. 

  1118. 	
    1119. 

  1119. 	# special char to place data on TAGs contents  (\a == bell)
    1120. 

  1120. 	bank['x'] = re.compile('\a')
    1121. 

  1121. 	
    1122. 

  1122. 	# %%macroname [ (formatting) ]
    1123. 

  1123. 	bank['macros'] = re.compile(r'%%%%(?P<name>%s)\b(\((?P<fmt>.*?)\))?'%(
    1124. 

  1124. 	                            string.join(MACROS.keys(), '|')), re.I)
    1125. 

  1125. 	
    1126. 

  1126. 	# %%TOC special macro for TOC positioning
    1127. 

  1127. 	bank['toc'] = re.compile(r'^ *%%toc\s*$', re.I)
    1128. 

  1128. 	
    1129. 

  1129. 	# almost complicated title regexes ;)
    1130. 

  1130. 	titskel = r'^ *(?P<id>%s)(?P<txt>%s)\1(\[(?P<label>[\w-]*)\])?\s*$'
    1131. 

  1131. 	bank[   'title'] = re.compile(titskel%('[=]{1,5}','[^=](|.*[^=])'))
    1132. 

  1132. 	bank['numtitle'] = re.compile(titskel%('[+]{1,5}','[^+](|.*[^+])'))
    1133. 

  1133. 	
    1134. 

  1134. 	### complicated regexes begin here ;)
    1135. 

  1135. 	#
    1136. 

  1136. 	# textual descriptions on --help's style: [...] is optional, | is OR
    1137. 

  1137. 	
    1138. 

  1138. 	
    1139. 

  1139. 	### first, some auxiliar variables
    1140. 

  1140. 	#
    1141. 

  1141. 	
    1142. 

  1142. 	# [image.EXT]
    1143. 

  1143. 	patt_img = r'\[([\w_,.+%$#@!?+~/-]+\.(png|jpe?g|gif|eps|bmp))\]'
    1144. 

  1144. 	
    1145. 

  1145. 	# link things
    1146. 

  1146. 	urlskel = {
    1147. 

  1147. 	  'proto' : r'(https?|ftp|news|telnet|gopher|wais)://',
    1148. 

  1148. 	  'guess' : r'(www[23]?|ftp)\.',         # w/out proto, try to guess
    1149. 

  1149. 	  'login' : r'A-Za-z0-9_.-',             # for ftp://login@domain.com
    1150. 

  1150. 	  'pass'  : r'[^ @]*',                   # for ftp://login:pass@dom.com
    1151. 

  1151. 	  'chars' : r'A-Za-z0-9%._/~:,=$@&+-',   # %20(space), :80(port), D&D
    1152. 

  1152. 	  'anchor': r'A-Za-z0-9%._-',            # %nn(encoded)
    1153. 

  1153. 	  'form'  : r'A-Za-z0-9/%&=+;.,$@*_-',   # .,@*_-(as is)
    1154. 

  1154. 	  'punct' : r'.,;:!?'
    1155. 

  1155. 	}
    1156. 

  1156. 	
    1157. 

  1157. 	# username [ :password ] @
    1158. 

  1158. 	patt_url_login = r'([%s]+(:%s)?@)?'%(urlskel['login'],urlskel['pass'])
    1159. 

  1159. 	
    1160. 

  1160. 	# [ http:// ] [ username:password@ ] domain.com [ / ]
    1161. 

  1161. 	#     [ #anchor | ?form=data ]
    1162. 

  1162. 	retxt_url = r'\b(%s%s|%s)[%s]+\b/*(\?[%s]+)?(#[%s]+)?'%(
    1163. 

  1163. 	             urlskel['proto'],patt_url_login, urlskel['guess'],
    1164. 

  1164. 	             urlskel['chars'],urlskel['form'],urlskel['anchor'])
    1165. 

  1165. 	
    1166. 

  1166. 	# filename | [ filename ] #anchor
    1167. 

  1167. 	retxt_url_local = r'[%s]+|[%s]*(#[%s]+)'%(
    1168. 

  1168. 	             urlskel['chars'],urlskel['chars'],urlskel['anchor'])
    1169. 

  1169. 	
    1170. 

  1170. 	# user@domain [ ?form=data ]
    1171. 

  1171. 	patt_email = r'\b[%s]+@([A-Za-z0-9_-]+\.)+[A-Za-z]{2,4}\b(\?[%s]+)?'%(
    1172. 

  1172. 	             urlskel['login'],urlskel['form'])
    1173. 

  1173. 	
    1174. 

  1174. 	# saving for future use
    1175. 

  1175. 	bank['_urlskel'] = urlskel
    1176. 

  1176. 	
    1177. 

  1177. 	### and now the real regexes
    1178. 

  1178. 	#
    1179. 

  1179. 	
    1180. 

  1180. 	bank['email'] = re.compile(patt_email,re.I)
    1181. 

  1181. 	
    1182. 

  1182. 	# email | url
    1183. 

  1183. 	bank['link'] = re.compile(r'%s|%s'%(retxt_url,patt_email), re.I)
    1184. 

  1184. 	
    1185. 

  1185. 	# \[ label | imagetag    url | email | filename \]
    1186. 

  1186. 	bank['linkmark'] = re.compile(
    1187. 

  1187. 		r'\[(?P<label>%s|[^]]+) (?P<link>%s|%s|%s)\]'%(
    1188. 

  1188. 		  patt_img, retxt_url, patt_email, retxt_url_local),
    1189. 

  1189. 		re.L+re.I)
    1190. 

  1190. 	
    1191. 

  1191. 	# image
    1192. 

  1192. 	bank['img'] = re.compile(patt_img, re.L+re.I)
    1193. 

  1193. 	
    1194. 

  1194. 	# special things
    1195. 

  1195. 	bank['special'] = re.compile(r'^%!\s*')
    1196. 

  1196. 	return bank
    1197. 

  1197. ### END OF regex nightmares
    1198. 

  1198. 

  1199. 

  1200. ##############################################################################
    1201. 

  1201. 

  1202. 

  1203. def echo(msg):   # for quick debug
    1204. 

  1204. 	print '\033[32;1m%s\033[m'%msg
    1205. 

  1205. def Quit(msg, exitcode=0):
    1206. 

  1206. 	print msg
    1207. 

  1207. 	sys.exit(exitcode)
    1208. 

  1208. def Error(msg):
    1209. 

  1209. 	sys.stderr.write(_("%s: Error: ")%my_name + "%s\n"%msg)
    1210. 

  1210. 	sys.stderr.flush()
    1211. 

  1211. 	sys.exit(1)
    1212. 

  1212. def ShowTraceback():
    1213. 

  1213. 	try:
    1214. 

  1214. 		from traceback import print_exc
    1215. 

  1215. 		print_exc() ; print ; print
    1216. 

  1216. 	except: pass
    1217. 

  1217. def Message(msg,level):
    1218. 

  1218. 	if level <= VERBOSE and not QUIET:
    1219. 

  1219. 		prefix = '-'*5
    1220. 

  1220. 		print "%s %s"%(prefix*level, msg)
    1221. 

  1221. def Debug(msg,color=0,linenr=None):
    1222. 

  1222. 	"0gray=init,1red=conf,3yellow=line,6cyan=block,2green=detail,5pink=gui"
    1223. 

  1223. 	if QUIET or not DEBUG: return
    1224. 

  1224. 	if COLOR_DEBUG: msg = '\033[3%s;1m%s\033[m'%(color,msg)
    1225. 

  1225. 	if linenr is not None: msg = "LINE %04d: %s"%(linenr,msg)
    1226. 

  1226. 	print "** %s"%msg
    1227. 

  1227. def Readfile(file, remove_linebreaks=0):
    1228. 

  1228. 	if file == '-':
    1229. 

  1229. 		try: data = sys.stdin.readlines()
    1230. 

  1230. 		except: Error(_('You must feed me with data on STDIN!'))
    1231. 

  1231. 	else:
    1232. 

  1232. 		try: f = open(file); data = f.readlines() ; f.close()
    1233. 

  1233. 		except: Error(_("Cannot read file:")+"\n    %s"%file)
    1234. 

  1234. 	if remove_linebreaks:
    1235. 

  1235. 		data = map(lambda x:re.sub('[\n\r]+$','',x), data)
    1236. 

  1236. 	Message(_("Readed file (%d lines): %s")%(len(data),file),2)
    1237. 

  1237. 	return data
    1238. 

  1238. def Savefile(file, contents):
    1239. 

  1239. 	try: f = open(file, 'wb')
    1240. 

  1240. 	except: Error(_("Cannot open file for writing:")+"\n    %s"%file)
    1241. 

  1241. 	if type(contents) == type([]): doit = f.writelines
    1242. 

  1242. 	else: doit = f.write
    1243. 

  1243. 	doit(contents) ; f.close()
    1244. 

  1244. 

  1245. def showdic(dic):
    1246. 

  1246. 	for k in dic.keys(): print "%15s : %s" % (k,dic[k])
    1247. 

  1247. def dotted_spaces(txt=''):
    1248. 

  1248. 	return string.replace(txt,' ','.')
    1249. 

  1249. 

  1250. def get_rc_path():
    1251. 

  1251. 	"Return the full path for the users' RC file"
    1252. 

  1252. 	rc_file = RC
    1253. 

  1253. 	# search the RC dir on the specified system variables
    1254. 

  1254. 	# TIP: win: http://www.winnetmag.com/Article/ArticleID/23873/23873.html
    1255. 

  1255. 	rc_dir_search = ['HOME', 'HOMEPATH']
    1256. 

  1256. 	for var in rc_dir_search:
    1257. 

  1257. 		rc_dir = os.environ.get(var)
    1258. 

  1258. 		if rc_dir: break
    1259. 

  1259. 	if rc_dir:
    1260. 

  1260. 		# compose path and return it if the file exists
    1261. 

  1261. 		rc_path = os.path.join(rc_dir, rc_file)
    1262. 

  1262. 		# on windows, prefix with the drive (%homedrive%: 2k/XP/NT)
    1263. 

  1263. 		if sys.platform[:3] == 'win':
    1264. 

  1264. 			rc_drive = os.environ.get('HOMEDRIVE')
    1265. 

  1265. 			rc_path = os.path.join(rc_drive,rc_path)
    1266. 

  1266. 		return rc_path
    1267. 

  1267. 	return ''
    1268. 

  1268. 

  1269. 

  1270. 

  1271. ##############################################################################
    1272. 

  1272. 

  1273. class CommandLine:
    1274. 

  1274. 	"""
    1275. 

  1275. 	Command Line class - Masters command line
    1276. 

  1276. 

  1277. 	This class checks and extract data from the provided command line.
    1278. 

  1278. 	The --long options and flags are taken from the global OPTIONS,
    1279. 

  1279. 	FLAGS and ACTIONS dictionaries. The short options are registered
    1280. 

  1280. 	here, and also their equivalence to the long ones.
    1281. 

  1281. 

  1282. 	METHODS:
    1283. 

  1283. 	  _compose_short_opts() -> str
    1284. 

  1284. 	  _compose_long_opts() -> list
    1285. 

  1285. 	      Compose the valid short and long options list, on the
    1286. 

  1286. 	      'getopt' format.
    1287. 

  1287. 	  
    1288. 

  1288. 	  parse() -> (opts, args)
    1289. 

  1289. 	      Call getopt to check and parse the command line.
    1290. 

  1290. 	      It expects to receive the command line as a list, and
    1291. 

  1291. 	      without the program name (sys.argv[1:]).
    1292. 

  1292. 	  
    1293. 

  1293. 	  get_raw_config() -> [RAW config]
    1294. 

  1294. 	      Scans command line and convert the data to the RAW config
    1295. 

  1295. 	      format. See ConfigMaster class to the RAW format description.
    1296. 

  1296. 	      Optional 'ignore' and 'filter' arguments are used to filter
    1297. 

  1297. 	      in or out specified keys.
    1298. 

  1298. 	  
    1299. 

  1299. 	  compose_cmdline(dict) -> [Command line]
    1300. 

  1300. 	      Compose a command line list from an already parsed config
    1301. 

  1301. 	      dictionary, generated from RAW by ConfigMaster(). Use
    1302. 

  1302. 	      this to compose an optimal command line for a group of
    1303. 

  1303. 	      options.
    1304. 

  1304. 	
    1305. 

  1305. 	The get_raw_config() calls parse(), so the tipical use of this
    1306. 

  1306. 	class is:
    1307. 

  1307. 	
    1308. 

  1308.             raw = CommandLine().get_raw_config(sys.argv[1:])
    1309. 

  1309. 	"""
    1310. 

  1310. 	def __init__(self):
    1311. 

  1311. 		self.all_options = OPTIONS.keys()
    1312. 

  1312. 		self.all_flags   = FLAGS.keys()
    1313. 

  1313. 		self.all_actions = ACTIONS.keys()
    1314. 

  1314. 		
    1315. 

  1315. 		# short:long options equivalence
    1316. 

  1316. 		self.short_long = {
    1317. 

  1317. 		  'h':'help'     ,   'V':'version',
    1318. 

  1318. 		  'n':'enum-title',  'i':'infile' ,
    1319. 

  1319. 		  'H':'no-headers',  'o':'outfile',
    1320. 

  1320. 		  'v':'verbose'   ,  't':'target' ,
    1321. 

  1321. 		  'q':'quiet'
    1322. 

  1322. 		}
    1323. 

  1323. 		
    1324. 

  1324. 		# compose valid short and long options data for getopt
    1325. 

  1325. 		self.short_opts = self._compose_short_opts()
    1326. 

  1326. 		self.long_opts  = self._compose_long_opts()
    1327. 

  1327. 	
    1328. 

  1328. 	def _compose_short_opts(self):
    1329. 

  1329. 		"Returns a string like 'hVt:o' with all short options/flags"
    1330. 

  1330. 		ret = []
    1331. 

  1331. 		for opt in self.short_long.keys():
    1332. 

  1332. 			long = self.short_long[opt]
    1333. 

  1333. 			if long in self.all_options: # is flag or option?
    1334. 

  1334. 				opt = opt+':'        # option: have param
    1335. 

  1335. 			ret.append(opt)
    1336. 

  1336. 		Debug('Valid SHORT options: %s'%ret)
    1337. 

  1337. 		return string.join(ret, '')
    1338. 

  1338. 	
    1339. 

  1339. 	def _compose_long_opts(self):
    1340. 

  1340. 		"Returns a list with all the valid long options/flags"
    1341. 

  1341. 		ret = map(lambda x:x+'=', self.all_options)       # add =
    1342. 

  1342. 		ret.extend(self.all_flags)                        # flag ON
    1343. 

  1343. 		ret.extend(self.all_actions)                      # acts
    1344. 

  1344. 		ret.extend(map(lambda x:'no-'+x, self.all_flags)) # add no-*
    1345. 

  1345. 		ret.extend(['no-style'])                   # turn OFF option
    1346. 

  1346. 		ret.extend(['no-encoding'])                # turn OFF option
    1347. 

  1347. 		ret.extend(['no-outfile'])                 # turn OFF option
    1348. 

  1348. 		Debug('Valid LONG options: %s'%ret)
    1349. 

  1349. 		return ret
    1350. 

  1350. 	
    1351. 

  1351. 	def _tokenize(self, cmd_string=''):
    1352. 

  1352. 		"Convert a command line string to a list"
    1353. 

  1353. 		#TODO protect quotes contents
    1354. 

  1354. 		return string.split(cmd_string)
    1355. 

  1355. 	
    1356. 

  1356. 	def parse(self, cmdline=[]):
    1357. 

  1357. 		"Check/Parse a command line list     TIP: no program name!"
    1358. 

  1358. 		# get the valid options
    1359. 

  1359. 		short, long = self.short_opts, self.long_opts
    1360. 

  1360. 		# parse it!
    1361. 

  1361. 		try:
    1362. 

  1362. 			opts, args = getopt.getopt(cmdline, short, long)
    1363. 

  1363. 		except getopt.error, errmsg:
    1364. 

  1364. 			Error(_("%s (try --help)")%errmsg)
    1365. 

  1365. 		return (opts, args)
    1366. 

  1366. 	
    1367. 

  1367. 	def get_raw_config(self, cmdline=[], ignore=[], filter=[]):
    1368. 

  1368. 		"Returns the options/arguments found as RAW config"
    1369. 

  1369. 		if not cmdline: return []
    1370. 

  1370. 		ret = []
    1371. 

  1371. 		# we need lists, not strings
    1372. 

  1372. 		if type(cmdline) == type(''): cmdline = self._tokenize(cmdline)
    1373. 

  1373. 		Debug("cmdline: %s"%cmdline)
    1374. 

  1374. 		opts, args = self.parse(cmdline[:])
    1375. 

  1375. 		# get infile, if any
    1376. 

  1376. 		while args:
    1377. 

  1377. 			infile = args.pop(0)
    1378. 

  1378. 			ret.append(['infile', infile])
    1379. 

  1379. 		# parse all options
    1380. 

  1380. 		for name,value in opts:
    1381. 

  1381. 			# remove leading - and --
    1382. 

  1382. 			name = re.sub('^--?', '', name)
    1383. 

  1383. 			# alias to old mispelled 'suGGar'
    1384. 

  1384. 			if   name ==    'css-suggar': name =    'css-sugar'
    1385. 

  1385. 			elif name == 'no-css-suggar': name = 'no-css-sugar'
    1386. 

  1386. 			# translate short opt to long
    1387. 

  1387. 			if len(name) == 1: name = self.short_long.get(name)
    1388. 

  1388. 			# save it
    1389. 

  1389. 			ret.append([name, value])
    1390. 

  1390. 		# apply 'ignore' and 'filter' rules (filter is stronger)
    1391. 

  1391. 		temp = ret[:] ; ret = []
    1392. 

  1392. 		for name,value in temp:
    1393. 

  1393. 			if (not filter and not ignore) or \
    1394. 

  1394. 			   (filter and name in filter) or \
    1395. 

  1395. 			   (ignore and name not in ignore):
    1396. 

  1396. 				ret.append( ['all', name, value] )
    1397. 

  1397. 		# add the original command line string as 'realcmdline'
    1398. 

  1398. 		ret.append( ['all', 'realcmdline', cmdline] )
    1399. 

  1399. 		return ret
    1400. 

  1400. 	
    1401. 

  1401. 	def compose_cmdline(self, conf={}, no_check=0):
    1402. 

  1402. 		"compose a full (and diet) command line from CONF dict"
    1403. 

  1403. 		if not conf: return []
    1404. 

  1404. 		args = []
    1405. 

  1405. 		dft_options = OPTIONS.copy()
    1406. 

  1406. 		cfg = conf.copy()
    1407. 

  1407. 		valid_opts = self.all_options + self.all_flags
    1408. 

  1408. 		use_short = {'no-headers':'H', 'enum-title':'n'}
    1409. 

  1409. 		# remove useless options
    1410. 

  1410. 		if not no_check and cfg.get('toc-only'):
    1411. 

  1411. 			if cfg.has_key('no-headers'):
    1412. 

  1412. 				del cfg['no-headers']
    1413. 

  1413. 			if cfg.has_key('outfile'):
    1414. 

  1414. 				del cfg['outfile']      # defaults to STDOUT
    1415. 

  1415. 			if cfg.get('target') == 'txt':
    1416. 

  1416. 				del cfg['target']       # already default
    1417. 

  1417. 			args.append('--toc-only')  # must be the first
    1418. 

  1418. 			del cfg['toc-only']
    1419. 

  1419. 		# add target type
    1420. 

  1420. 		if cfg.has_key('target'):
    1421. 

  1421. 			args.append('-t '+cfg['target'])
    1422. 

  1422. 			del cfg['target']
    1423. 

  1423. 		# add other options
    1424. 

  1424. 		for key in cfg.keys():
    1425. 

  1425. 			if key not in valid_opts: continue  # may be a %!setting
    1426. 

  1426. 			if key in ['outfile','infile']: continue   # later
    1427. 

  1427. 			val = cfg[key]
    1428. 

  1428. 			if not val: continue
    1429. 

  1429. 			# default values are useless on cmdline
    1430. 

  1430. 			if val == dft_options.get(key): continue
    1431. 

  1431. 			# -short format
    1432. 

  1432. 			if key in use_short.keys():
    1433. 

  1433. 				args.append('-'+use_short[key])
    1434. 

  1434. 				continue
    1435. 

  1435. 			# --long format
    1436. 

  1436. 			if key in self.all_flags: # add --option
    1437. 

  1437. 				args.append('--'+key)
    1438. 

  1438. 			else:                     # add --option=value
    1439. 

  1439. 				args.append('--%s=%s'%(key,val))
    1440. 

  1440. 		# the outfile using -o
    1441. 

  1441. 		if cfg.has_key('outfile') and \
    1442. 

  1442. 		   cfg['outfile'] != dft_options.get('outfile'):
    1443. 

  1443. 			args.append('-o '+cfg['outfile'])
    1444. 

  1444. 		# place input file(s) always at the end
    1445. 

  1445. 		if cfg.has_key('infile'):
    1446. 

  1446. 			args.append(string.join(cfg['infile'],' '))
    1447. 

  1447. 		# return as a nice list
    1448. 

  1448. 		Debug("Diet command line: %s"%string.join(args,' '), 1)
    1449. 

  1449. 		return args
    1450. 

  1450. 

  1451. ##############################################################################
    1452. 

  1452. 

  1453. class SourceDocument:
    1454. 

  1454. 	"""
    1455. 

  1455. 	SourceDocument class - scan document structure, extract data
    1456. 

  1456. 	
    1457. 

  1457. 	It knows about full files. It reads a file and identify all
    1458. 

  1458. 	the areas begining (Head,Conf,Body). With this info it can
    1459. 

  1459. 	extract each area contents.
    1460. 

  1460. 	Note: the original line break is removed.
    1461. 

  1461. 	
    1462. 

  1462. 	DATA:
    1463. 

  1463. 	  self.arearef - Save Head, Conf, Body init line number
    1464. 

  1464. 	  self.areas   - Store the area names which are not empty
    1465. 

  1465. 	  self.buffer  - The full file contents (with NO \\r, \\n)
    1466. 

  1466. 

  1467. 	METHODS:
    1468. 

  1468. 	  get()   - Access the contents of an Area. Example:
    1469. 

  1469. 	            config = SourceDocument(file).get('conf')
    1470. 

  1470. 	
    1471. 

  1471. 	  split() - Get all the document Areas at once. Example:
    1472. 

  1472. 	            head, conf, body = SourceDocument(file).split()
    1473. 

  1473. 	
    1474. 

  1474. 	RULES:
    1475. 

  1475. 	    * The document parts are sequential: Head, Conf and Body.
    1476. 

  1476. 	    * One ends when the next begins.
    1477. 

  1477. 	    * The Conf Area is optional, so a document can have just
    1478. 

  1478. 	      Head and Body Areas.
    1479. 

  1479. 	
    1480. 

  1480. 	    These are the Areas limits:
    1481. 

  1481. 	      - Head Area: the first three lines
    1482. 

  1482. 	      - Body Area: from the first valid text line to the end
    1483. 

  1483. 	      - Conf Area: the comments between Head and Body Areas
    1484. 

  1484. 

  1485. 	    Exception: If the first line is blank, this means no
    1486. 

  1486. 	    header info, so the Head Area is just the first line.
    1487. 

  1487. 	"""
    1488. 

  1488. 	def __init__(self, filename=''):
    1489. 

  1489. 		self.areas = ['head','conf','body']
    1490. 

  1490. 		self.arearef = []
    1491. 

  1491. 		self.areas_fancy = ''
    1492. 

  1492. 		self.filename = filename
    1493. 

  1493. 		self.buffer = []
    1494. 

  1494. 		if filename: self.scan(filename)
    1495. 

  1495. 	
    1496. 

  1496. 	def split(self):
    1497. 

  1497. 		"Returns all document parts, splitted into lists."
    1498. 

  1498. 		return self.get('head'), self.get('conf'), self.get('body')
    1499. 

  1499. 	
    1500. 

  1500. 	def get(self, areaname):
    1501. 

  1501. 		"Returns head|conf|body contents from self.buffer"
    1502. 

  1502. 		# sanity
    1503. 

  1503. 		if areaname not in self.areas: return []
    1504. 

  1504. 		if not self.buffer           : return []
    1505. 

  1505. 		# go get it
    1506. 

  1506. 		bufini = 1
    1507. 

  1507. 		bufend = len(self.buffer)
    1508. 

  1508. 		if   areaname == 'head':
    1509. 

  1509. 			ini = bufini
    1510. 

  1510. 			end = self.arearef[1] or self.arearef[2] or bufend
    1511. 

  1511. 		elif areaname == 'conf':
    1512. 

  1512. 			ini = self.arearef[1]
    1513. 

  1513. 			end = self.arearef[2] or bufend
    1514. 

  1514. 		elif areaname == 'body':
    1515. 

  1515. 			ini = self.arearef[2]
    1516. 

  1516. 			end = bufend
    1517. 

  1517. 		else:
    1518. 

  1518. 			Error("Unknown Area name '%s'"%areaname)
    1519. 

  1519. 		lines = self.buffer[ini:end]
    1520. 

  1520. 		# make sure head will always have 3 lines
    1521. 

  1521. 		while areaname == 'head' and len(lines) < 3:
    1522. 

  1522. 			lines.append('')
    1523. 

  1523. 		return lines
    1524. 

  1524. 	
    1525. 

  1525. 	def scan(self, filename):
    1526. 

  1526. 		"Run through source file and identify head/conf/body areas"
    1527. 

  1527. 		Debug("source file: %s"%filename)
    1528. 

  1528. 		Message(_("Loading source document"),1)
    1529. 

  1529. 		buf = Readfile(filename, remove_linebreaks=1)
    1530. 

  1530. 		if len(buf) == 0:
    1531. 

  1531. 			Error(_('The input file is empty: %s')%filename)
    1532. 

  1532. 		cfg_parser = ConfigLines().parse_line
    1533. 

  1533. 		buf.insert(0, '')                         # text start at pos 1
    1534. 

  1534. 		ref = [1,4,0]
    1535. 

  1535. 		if not string.strip(buf[1]):              # no header
    1536. 

  1536. 			ref[0] = 0 ; ref[1] = 2
    1537. 

  1537. 		rgx = getRegexes()
    1538. 

  1538. 		for i in range(ref[1],len(buf)):          # find body init:
    1539. 

  1539. 			if string.strip(buf[i]) and (     # ... not blank and
    1540. 

  1540. 			   buf[i][0] != '%' or            # ... not comment or
    1541. 

  1541. 			   rgx['macros'].match(buf[i]) or # ... %%macro
    1542. 

  1542. 			   rgx['toc'].match(buf[i])    or # ... %%toc
    1543. 

  1543. 			   cfg_parser(buf[i],'include')[1]): # ... %!include
    1544. 

  1544. 				ref[2] = i ; break
    1545. 

  1545. 		if ref[1] == ref[2]: ref[1] = 0           # no conf area
    1546. 

  1546. 		for i in 0,1,2:                           # del !existent
    1547. 

  1547. 			if ref[i] >= len(buf): ref[i] = 0 # title-only
    1548. 

  1548. 			if not ref[i]: self.areas[i] = ''
    1549. 

  1549. 		Debug('Head,Conf,Body start line: %s'%ref)
    1550. 

  1550. 		self.arearef = ref                        # save results
    1551. 

  1551. 		self.buffer  = buf
    1552. 

  1552. 		# fancyness sample: head conf body (1 4 8)
    1553. 

  1553. 		self.areas_fancy = "%s (%s)"%(
    1554. 

  1554. 		     string.join(self.areas),
    1555. 

  1555. 		     string.join(map(str, map(lambda x:x or '', ref))))
    1556. 

  1556. 		Message(_("Areas found: %s")%self.areas_fancy, 2)
    1557. 

  1557. 	
    1558. 

  1558. 	def get_raw_config(self):
    1559. 

  1559. 		"Handy method to get the CONF area RAW config (if any)"
    1560. 

  1560. 		if not self.areas.count('conf'): return []
    1561. 

  1561. 		Message(_("Scanning source document CONF area"),1)
    1562. 

  1562. 		raw = ConfigLines(
    1563. 

  1563. 		      file=self.filename, lines=self.get('conf'),
    1564. 

  1564. 		      first_line=self.arearef[1]).get_raw_config()
    1565. 

  1565. 		Debug("document raw config: %s"%raw, 1)
    1566. 

  1566. 		return raw
    1567. 

  1567. 

  1568. ##############################################################################
    1569. 

  1569. 

  1570. class ConfigMaster:
    1571. 

  1571. 	"""
    1572. 

  1572. 	ConfigMaster class - the configuration wizard
    1573. 

  1573. 	
    1574. 

  1574. 	This class is the configuration master. It knows how to handle
    1575. 

  1575. 	the RAW and PARSED config format. It also performs the sanity
    1576. 

  1576. 	checkings for a given configuration.
    1577. 

  1577. 	
    1578. 

  1578. 	DATA:
    1579. 

  1579. 	  self.raw         - Stores the config on the RAW format
    1580. 

  1580. 	  self.parsed      - Stores the config on the PARSED format
    1581. 

  1581. 	  self.defaults    - Stores the default values for all keys
    1582. 

  1582. 	  self.off         - Stores the OFF values for all keys
    1583. 

  1583. 	  self.multi       - List of keys which can have multiple values
    1584. 

  1584. 	  self.numeric     - List of keys which value must be a number
    1585. 

  1585. 	  self.incremental - List of keys which are incremental
    1586. 

  1586. 	
    1587. 

  1587.         RAW FORMAT:
    1588. 

  1588. 	  The RAW format is a list of lists, being each mother list item
    1589. 

  1589. 	  a full configuration entry. Any entry is a 3 item list, on
    1590. 

  1590. 	  the following format: [ TARGET, KEY, VALUE ]
    1591. 

  1591. 	  Being a list, the order is preserved, so it's easy to use
    1592. 

  1592. 	  different kinds of configs, as CONF area and command line,
    1593. 

  1593. 	  respecting the precedence.
    1594. 

  1594. 	  The special target 'all' is used when no specific target was
    1595. 

  1595. 	  defined on the original config.
    1596. 

  1596. 	
    1597. 

  1597. 	PARSED FORMAT:
    1598. 

  1598. 	  The PARSED format is a dictionary, with all the 'key : value'
    1599. 

  1599. 	  found by reading the RAW config. The self.target contents
    1600. 

  1600. 	  matters, so this dictionary only contains the target's
    1601. 

  1601. 	  config. The configs of other targets are ignored.
    1602. 

  1602. 	
    1603. 

  1603. 	The CommandLine and ConfigLines classes have the get_raw_config()
    1604. 

  1604. 	method which convert the configuration found to the RAW format.
    1605. 

  1605. 	Just feed it to parse() and get a brand-new ready-to-use config
    1606. 

  1606. 	dictionary. Example:
    1607. 

  1607. 	
    1608. 

  1608. 	    >>> raw = CommandLine().get_raw_config(['-n', '-H'])
    1609. 

  1609. 	    >>> print raw
    1610. 

  1610. 	    [['all', 'enum-title', ''], ['all', 'no-headers', '']]
    1611. 

  1611. 	    >>> parsed = ConfigMaster(raw).parse()
    1612. 

  1612. 	    >>> print parsed
    1613. 

  1613. 	    {'enum-title': 1, 'headers': 0}
    1614. 

  1614. 	"""
    1615. 

  1615. 	def __init__(self, raw=[], target=''):
    1616. 

  1616. 		self.raw          = raw
    1617. 

  1617. 		self.target       = target
    1618. 

  1618. 		self.parsed       = {}
    1619. 

  1619. 		self.dft_options  = OPTIONS.copy()
    1620. 

  1620. 		self.dft_flags    = FLAGS.copy()
    1621. 

  1621. 		self.dft_actions  = ACTIONS.copy()
    1622. 

  1622. 		self.dft_settings = SETTINGS.copy()
    1623. 

  1623. 		self.defaults     = self._get_defaults()
    1624. 

  1624. 		self.off          = self._get_off()
    1625. 

  1625. 		self.multi        = ['infile', 'options','preproc','postproc']
    1626. 

  1626. 		self.incremental  = ['verbose']
    1627. 

  1627. 		self.numeric      = ['toc-level','split']
    1628. 

  1628. 	
    1629. 

  1629. 	def _get_defaults(self):
    1630. 

  1630. 		"Get the default values for all config/options/flags"
    1631. 

  1631. 		empty = {}
    1632. 

  1632. 		for kw in CONFIG_KEYWORDS: empty[kw] = ''
    1633. 

  1633. 		empty.update(self.dft_options)
    1634. 

  1634. 		empty.update(self.dft_flags)
    1635. 

  1635. 		empty.update(self.dft_actions)
    1636. 

  1636. 		empty.update(self.dft_settings)
    1637. 

  1637. 		empty['realcmdline'] = ''  # internal use only
    1638. 

  1638. 		empty['sourcefile']  = ''  # internal use only
    1639. 

  1639. 		return empty
    1640. 

  1640. 	
    1641. 

  1641. 	def _get_off(self):
    1642. 

  1642. 		"Turns OFF all the config/options/flags"
    1643. 

  1643. 		off = {}
    1644. 

  1644. 		for key in self.defaults.keys():
    1645. 

  1645. 			kind = type(self.defaults[key])
    1646. 

  1646. 			if kind == type(9):
    1647. 

  1647. 				off[key] = 0
    1648. 

  1648. 			elif kind == type(''):
    1649. 

  1649. 				off[key] = ''
    1650. 

  1650. 			elif kind == type([]):
    1651. 

  1651. 				off[key] = []
    1652. 

  1652. 			else:
    1653. 

  1653. 				Error('ConfigMaster: %s: Unknown type'+key)
    1654. 

  1654. 		return off
    1655. 

  1655. 	
    1656. 

  1656. 	def _check_target(self):
    1657. 

  1657. 		"Checks if the target is already defined. If not, do it"
    1658. 

  1658. 		if not self.target:
    1659. 

  1659. 			self.target = self.find_value('target')
    1660. 

  1660. 	
    1661. 

  1661. 	def get_target_raw(self):
    1662. 

  1662. 		"Returns the raw config for self.target or 'all'"
    1663. 

  1663. 		ret = []
    1664. 

  1664. 		self._check_target()
    1665. 

  1665. 		for entry in self.raw:
    1666. 

  1666. 			if entry[0] in [self.target, 'all']:
    1667. 

  1667. 				ret.append(entry)
    1668. 

  1668. 		return ret
    1669. 

  1669. 	
    1670. 

  1670. 	def add(self, key, val):
    1671. 

  1671. 		"Adds the key:value pair to the config dictionary (if needed)"
    1672. 

  1672. 		# %!options
    1673. 

  1673. 		if key == 'options':
    1674. 

  1674. 			ignoreme = self.dft_actions.keys() + ['target']
    1675. 

  1675. 			raw_opts = CommandLine().get_raw_config(
    1676. 

  1676. 			             val, ignore=ignoreme)
    1677. 

  1677. 			for target, key, val in raw_opts:
    1678. 

  1678. 				self.add(key, val)
    1679. 

  1679. 			return
    1680. 

  1680. 		# the no- prefix turns OFF this key
    1681. 

  1681. 		if key[:3] == 'no-':
    1682. 

  1682. 			key = key[3:]              # remove prefix
    1683. 

  1683. 			val = self.off.get(key)    # turn key OFF
    1684. 

  1684. 		# is this key valid?
    1685. 

  1685. 		if key not in self.defaults.keys():
    1686. 

  1686. 			Debug('Bogus Config %s:%s'%(key,val),1)
    1687. 

  1687. 			return
    1688. 

  1688. 		# is this value the default one?
    1689. 

  1689. 		if val == self.defaults.get(key):
    1690. 

  1690. 			# if default value, remove previous key:val
    1691. 

  1691. 			if self.parsed.has_key(key):
    1692. 

  1692. 				del self.parsed[key]
    1693. 

  1693. 			# nothing more to do
    1694. 

  1694. 			return
    1695. 

  1695. 		# flags ON comes empty. we'll add the 1 value now
    1696. 

  1696. 		if val == '' and \
    1697. 

  1697. 		   key in self.dft_flags.keys()+self.dft_actions.keys():
    1698. 

  1698. 			val = 1
    1699. 

  1699. 		# multi value or single?
    1700. 

  1700. 		if key in self.multi:
    1701. 

  1701. 			# first one? start new list
    1702. 

  1702. 			if not self.parsed.has_key(key):
    1703. 

  1703. 				self.parsed[key] = []
    1704. 

  1704. 			self.parsed[key].append(val)
    1705. 

  1705. 		# incremental value? so let's add it
    1706. 

  1706. 		elif key in self.incremental:
    1707. 

  1707. 			self.parsed[key] = (self.parsed.get(key) or 0) + val
    1708. 

  1708. 		else:
    1709. 

  1709. 			self.parsed[key] = val
    1710. 

  1710. 		fancykey = dotted_spaces("%12s"%key)
    1711. 

  1711. 		Message(_("Added config %s : %s")%(fancykey,val),3)
    1712. 

  1712. 	
    1713. 

  1713. 	def get_outfile_name(self, config={}):
    1714. 

  1714. 		"Dirname is the same for {in,out}file"
    1715. 

  1715. 		infile, outfile = config['sourcefile'], config['outfile']
    1716. 

  1716. 		if infile == STDIN and not outfile: outfile = STDOUT
    1717. 

  1717. 		if not outfile and (infile and config.get('target')):
    1718. 

  1718. 			basename = re.sub('\.(txt|t2t)$','',infile)
    1719. 

  1719. 			outfile = "%s.%s"%(basename, config['target'])
    1720. 

  1720. 		Debug(" infile: '%s'"%infile , 1)
    1721. 

  1721. 		Debug("outfile: '%s'"%outfile, 1)
    1722. 

  1722. 		return outfile
    1723. 

  1723. 	
    1724. 

  1724. 	def sanity(self, config, gui=0):
    1725. 

  1725. 		"Basic config sanity checkings"
    1726. 

  1726. 		if not config: return {}
    1727. 

  1727. 		target = config.get('target')
    1728. 

  1728. 		# --toc-only doesn't require target specification
    1729. 

  1729. 		if not target and config.get('toc-only'):
    1730. 

  1730. 			target = 'txt'
    1731. 

  1731. 		# on GUI, some checkings are skipped
    1732. 

  1732. 		if not gui:
    1733. 

  1733. 			# we *need* a target
    1734. 

  1734. 			if not target:
    1735. 

  1735. 				Error(_('No target specified (try --help)')+\
    1736. 

  1736. 				'\n\n'+\
    1737. 

  1737. 				_('Maybe trying to convert an old v1.x file?'))
    1738. 

  1738. 			# and of course, an infile also
    1739. 

  1739. 			if not config['infile']:
    1740. 

  1740. 				Error(_('Missing input file (try --help)'))
    1741. 

  1741. 			# is the target valid?
    1742. 

  1742. 			if not TARGETS.count(target):
    1743. 

  1743. 				Error(_("Invalid target '%s' (try --help)"
    1744. 

  1744. 				        )%target)
    1745. 

  1745. 		# ensure all keys are present
    1746. 

  1746. 		empty = self.defaults.copy() ; empty.update(config)
    1747. 

  1747. 		config = empty.copy()
    1748. 

  1748. 		# check integers options
    1749. 

  1749. 		for key in config.keys():
    1750. 

  1750. 			if key in self.numeric:
    1751. 

  1751. 				try: config[key] = int(config[key])
    1752. 

  1752. 				except: Error(_('--%s value must be a number'
    1753. 

  1753. 				                )%key)
    1754. 

  1754. 		# check split level value
    1755. 

  1755. 		if config['split'] not in [0,1,2]:
    1756. 

  1756. 			Error(_('Option --split must be 0, 1 or 2'))
    1757. 

  1757. 		# --toc-only is stronger than others
    1758. 

  1758. 		if config['toc-only']:
    1759. 

  1759. 			config['headers'] = 0
    1760. 

  1760. 			config['toc']     = 0
    1761. 

  1761. 			config['split']   = 0
    1762. 

  1762. 			config['gui']     = 0
    1763. 

  1763. 			config['outfile'] = config['outfile'] or STDOUT
    1764. 

  1764. 		# splitting is disable for now (future: HTML only, no STDOUT)
    1765. 

  1765. 		config['split'] = 0
    1766. 

  1766. 		# restore target
    1767. 

  1767. 		config['target'] = target
    1768. 

  1768. 		# set output file name
    1769. 

  1769. 		config['outfile'] = self.get_outfile_name(config)
    1770. 

  1770. 		# checking suicide
    1771. 

  1771. 		if config['sourcefile'] == config['outfile'] and \
    1772. 

  1772. 		   config['outfile'] != STDOUT and not gui:
    1773. 

  1773. 			Error(_("Input and Output files are the same: %s")%(
    1774. 

  1774. 			config['outfile']))
    1775. 

  1775. 		return config
    1776. 

  1776. 	
    1777. 

  1777. 	def parse(self):
    1778. 

  1778. 		"Returns the parsed config for the current target"
    1779. 

  1779. 		raw = self.get_target_raw()
    1780. 

  1780. 		for target, key, value in raw:
    1781. 

  1781. 			self.add(key, value)
    1782. 

  1782. 		Message(_("Added the following keys: %s")%string.join(
    1783. 

  1783. 		         self.parsed.keys(),', '),2)
    1784. 

  1784. 		return self.parsed.copy()
    1785. 

  1785. 	
    1786. 

  1786. 	def find_value(self, key='', target=''):
    1787. 

  1787. 		"Scans ALL raw config to find the desired key"
    1788. 

  1788. 		ret = []
    1789. 

  1789. 		# scan and save all values found
    1790. 

  1790. 		for targ, k, val in self.raw:
    1791. 

  1791. 			if targ in [target, 'all'] and k == key:
    1792. 

  1792. 				ret.append(val)
    1793. 

  1793. 		if not ret: return ''
    1794. 

  1794. 		# if not multi value, return only the last found
    1795. 

  1795. 		if key in self.multi: return ret
    1796. 

  1796. 		else                : return ret[-1]
    1797. 

  1797. 

  1798. ########################################################################
    1799. 

  1799. 

  1800. class ConfigLines:
    1801. 

  1801. 	"""
    1802. 

  1802. 	ConfigLines class - the config file data extractor
    1803. 

  1803. 	
    1804. 

  1804. 	This class reads and parse the config lines on the %!key:val
    1805. 

  1805. 	format, converting it to RAW config. It deals with user
    1806. 

  1806. 	config file (RC file), source document CONF area and
    1807. 

  1807. 	%!includeconf directives.
    1808. 

  1808. 

  1809. 	Call it passing a file name or feed the desired config lines.
    1810. 

  1810. 	Then just call the get_raw_config() method and wait to
    1811. 

  1811. 	receive the full config data on the RAW format. This method
    1812. 

  1812. 	also follows the possible %!includeconf directives found on
    1813. 

  1813. 	the config lines. Example:
    1814. 

  1814. 

  1815. 	    raw = ConfigLines(file=".txt2tagsrc").get_raw_config()
    1816. 

  1816. 

  1817. 	The parse_line() method is also useful to be used alone,
    1818. 

  1818. 	to identify and tokenize a single config line. For example,
    1819. 

  1819. 	to get the %!include command components, on the source
    1820. 

  1820. 	document BODY:
    1821. 

  1821. 	
    1822. 

  1822. 	    target, key, value = ConfigLines().parse_line(body_line)
    1823. 

  1823. 	"""
    1824. 

  1824. 	def __init__(self, file='', lines=[], first_line=1):
    1825. 

  1825. 		self.file = file or 'NOFILE'
    1826. 

  1826. 		self.lines = lines
    1827. 

  1827. 		self.first_line = first_line
    1828. 

  1828. 	
    1829. 

  1829. 	def load_lines(self):
    1830. 

  1830. 		"Make sure we've loaded the file contents into buffer"
    1831. 

  1831. 		if not self.lines and not self.file:
    1832. 

  1832. 			Error("ConfigLines: No file or lines provided")
    1833. 

  1833. 		if not self.lines:
    1834. 

  1834. 			self.lines = self.read_config_file(self.file)
    1835. 

  1835. 	
    1836. 

  1836. 	def read_config_file(self, filename=''):
    1837. 

  1837. 		"Read a Config File contents, aborting on invalid line"
    1838. 

  1838. 		if not filename: return []
    1839. 

  1839. 		errormsg = _("Invalid CONFIG line on %s")+"\n%03d:%s"
    1840. 

  1840. 		lines = Readfile(filename, remove_linebreaks=1)
    1841. 

  1841. 		# sanity: try to find invalid config lines
    1842. 

  1842. 		for i in range(len(lines)):
    1843. 

  1843. 			line = string.rstrip(lines[i])
    1844. 

  1844. 			if not line: continue  # empty
    1845. 

  1845. 			if line[0] != '%': Error(errormsg%(filename,i+1,line))
    1846. 

  1846. 		return lines
    1847. 

  1847. 	
    1848. 

  1848. 	def include_config_file(self, file=''):
    1849. 

  1849. 		"Perform the %!includeconf action, returning RAW config"
    1850. 

  1850. 		if not file: return []
    1851. 

  1851. 		# current dir relative to the current file (self.file)
    1852. 

  1852. 		current_dir = os.path.dirname(self.file)
    1853. 

  1853. 		file = os.path.join(current_dir, file)
    1854. 

  1854. 		# read and parse included config file contents
    1855. 

  1855. 		lines = self.read_config_file(file)
    1856. 

  1856. 		return ConfigLines(file=file, lines=lines).get_raw_config()
    1857. 

  1857. 	
    1858. 

  1858. 	def get_raw_config(self):
    1859. 

  1859. 		"Scan buffer and extract all config as RAW (including includes)"
    1860. 

  1860. 		ret = []
    1861. 

  1861. 		self.load_lines()
    1862. 

  1862. 		first = self.first_line
    1863. 

  1863. 		for i in range(len(self.lines)):
    1864. 

  1864. 			line = self.lines[i]
    1865. 

  1865. 			Message(_("Processing line %03d: %s")%(first+i,line),2)
    1866. 

  1866. 			target, key, val = self.parse_line(line)
    1867. 

  1867. 			if not key: continue    # no config on this line
    1868. 

  1868. 			if key == 'includeconf':
    1869. 

  1869. 				more_raw = self.include_config_file(val)
    1870. 

  1870. 				ret.extend(more_raw)
    1871. 

  1871. 				Message(_("Finished Config file inclusion: %s"
    1872. 

  1872. 				          )%(val),2)
    1873. 

  1873. 			else:
    1874. 

  1874. 				ret.append([target, key, val])
    1875. 

  1875. 				Message(_("Added %s")%key,3)
    1876. 

  1876. 		return ret
    1877. 

  1877. 	
    1878. 

  1878. 	def parse_line(self, line='', keyname='', target=''):
    1879. 

  1879. 		"Detects %!key:val config lines and extract data from it"
    1880. 

  1880. 		empty = ['', '', '']
    1881. 

  1881. 		if not line: return empty
    1882. 

  1882. 		no_target = ['target', 'includeconf']
    1883. 

  1883. 		re_name   = keyname or '[a-z]+'
    1884. 

  1884. 		re_target = target  or '[a-z]*'
    1885. 

  1885. 		cfgregex  = re.compile("""
    1886. 

  1886. 		  ^%%!\s*               # leading id with opt spaces
    1887. 

  1887. 		  (?P<name>%s)\s*       # config name
    1888. 

  1888. 		  (\((?P<target>%s)\))? # optional target spec inside ()
    1889. 

  1889. 		  \s*:\s*               # key:value delimiter with opt spaces
    1890. 

  1890. 		  (?P<value>\S.+?)      # config value
    1891. 

  1891. 		  \s*$                  # rstrip() spaces and hit EOL
    1892. 

  1892. 		  """%(re_name,re_target), re.I+re.VERBOSE)
    1893. 

  1893. 		prepostregex = re.compile("""
    1894. 

  1894. 		                        # ---[ PATTERN ]---
    1895. 

  1895. 		  ^( "([^"]*)"          # "double quoted" or
    1896. 

  1896. 		   | '([^']*)'          # 'single quoted' or
    1897. 

  1897. 		   | ([^\s]+)           # single_word
    1898. 

  1898. 		   )
    1899. 

  1899. 		    \s+                 # separated by spaces
    1900. 

  1900. 		
    1901. 

  1901. 		                        # ---[ REPLACE ]---
    1902. 

  1902. 		       ( "([^"]*)"      # "double quoted" or
    1903. 

  1903. 		       | '([^']*)'      # 'single quoted' or
    1904. 

  1904. 		       | (.*)           # anything
    1905. 

  1905. 		           )
    1906. 

  1906. 		            \s*$
    1907. 

  1907. 		  """, re.VERBOSE)
    1908. 

  1908. 		guicolors = re.compile("^([^\s]+\s+){3}[^\s]+") # 4 tokens
    1909. 

  1909. 		match = cfgregex.match(line)
    1910. 

  1910. 		if not match: return empty
    1911. 

  1911. 		
    1912. 

  1912. 		name   = string.lower(match.group('name') or '')
    1913. 

  1913. 		target = string.lower(match.group('target') or 'all')
    1914. 

  1914. 		value  = match.group('value')
    1915. 

  1915. 		
    1916. 

  1916. 		# NO target keywords: force all targets
    1917. 

  1917. 		if name in no_target: target = 'all'
    1918. 

  1918. 		
    1919. 

  1919. 		# special config for GUI colors
    1920. 

  1920. 		if name == 'guicolors':
    1921. 

  1921. 			valmatch = guicolors.search(value)
    1922. 

  1922. 			if not valmatch: return empty
    1923. 

  1923. 			value = re.split('\s+', value)
    1924. 

  1924. 		
    1925. 

  1925. 		# Special config with two quoted values (%!preproc: "foo" 'bar')
    1926. 

  1926. 		if name in ['preproc','postproc']:
    1927. 

  1927. 			valmatch = prepostregex.search(value)
    1928. 

  1928. 			if not valmatch: return empty
    1929. 

  1929. 			getval = valmatch.group
    1930. 

  1930. 			patt   = getval(2) or getval(3) or getval(4) or ''
    1931. 

  1931. 			repl   = getval(6) or getval(7) or getval(8) or ''
    1932. 

  1932. 			value  = (patt, repl)
    1933. 

  1933. 		return [target, name, value]
    1934. 

  1934. 

  1935. ##############################################################################
    1936. 

  1936. 

  1937. class MaskMaster:
    1938. 

  1938. 	"(Un)Protect important structures from escaping and formatting"
    1939. 

  1939. 	def __init__(self):
    1940. 

  1940. 		self.linkmask  = '@@@LINK@@@'
    1941. 

  1941. 		self.monomask  = '@@@MONO@@@'
    1942. 

  1942. 		self.macromask = '@@@MACRO@@@'
    1943. 

  1943. 		self.rawmask   = '@@@RAW@@@'
    1944. 

  1944. 		self.tocmask   = '@@@TOC@@@'
    1945. 

  1945. 		self.macroman  = MacroMaster()
    1946. 

  1946. 		self.reset()
    1947. 

  1947. 	
    1948. 

  1948. 	def reset(self):
    1949. 

  1949. 		self.linkbank = []
    1950. 

  1950. 		self.monobank = []
    1951. 

  1951. 		self.macrobank = []
    1952. 

  1952. 		self.rawbank = []
    1953. 

  1953. 	
    1954. 

  1954. 	def mask(self, line=''):
    1955. 

  1955. 		global AUTOTOC
    1956. 

  1956. 		
    1957. 

  1957. 		# protect raw text
    1958. 

  1958. 		while regex['raw'].search(line):
    1959. 

  1959. 			txt = regex['raw'].search(line).group(1)
    1960. 

  1960. 			txt = doEscape(TARGET,txt)
    1961. 

  1961. 			self.rawbank.append(txt)
    1962. 

  1962. 			line = regex['raw'].sub(self.rawmask,line,1)
    1963. 

  1963. 		
    1964. 

  1964. 		# protect pre-formatted font text
    1965. 

  1965. 		while regex['fontMono'].search(line):
    1966. 

  1966. 			txt = regex['fontMono'].search(line).group(1)
    1967. 

  1967. 			txt = doEscape(TARGET,txt)
    1968. 

  1968. 			self.monobank.append(txt)
    1969. 

  1969. 			line = regex['fontMono'].sub(self.monomask,line,1)
    1970. 

  1970. 		
    1971. 

  1971. 		# protect macros
    1972. 

  1972. 		while regex['macros'].search(line):
    1973. 

  1973. 			txt = regex['macros'].search(line).group()
    1974. 

  1974. 			self.macrobank.append(txt)
    1975. 

  1975. 			line = regex['macros'].sub(self.macromask,line,1)
    1976. 

  1976. 		
    1977. 

  1977. 		# protect TOC location
    1978. 

  1978. 		while regex['toc'].search(line):
    1979. 

  1979. 			line = regex['toc'].sub(self.tocmask,line)
    1980. 

  1980. 			AUTOTOC = 0
    1981. 

  1981. 		
    1982. 

  1982. 		# protect URLs and emails
    1983. 

  1983. 		while regex['linkmark'].search(line) or \
    1984. 

  1984. 		      regex['link'    ].search(line):
    1985. 

  1985. 			
    1986. 

  1986. 			# try to match plain or named links
    1987. 

  1987. 			match_link  = regex['link'].search(line)
    1988. 

  1988. 			match_named = regex['linkmark'].search(line)
    1989. 

  1989. 			
    1990. 

  1990. 			# define the current match
    1991. 

  1991. 			if match_link and match_named:
    1992. 

  1992. 				# both types found, which is the first?
    1993. 

  1993. 				m = match_link
    1994. 

  1994. 				if match_named.start() < match_link.start():
    1995. 

  1995. 					m = match_named
    1996. 

  1996. 			else:
    1997. 

  1997. 				# just one type found, we're fine
    1998. 

  1998. 				m = match_link or match_named
    1999. 

  1999. 			
    2000. 

  2000. 			# extract link data and apply mask
    2001. 

  2001. 			if m == match_link:              # plain link
    2002. 

  2002. 				link = m.group()
    2003. 

  2003. 				label = ''
    2004. 

  2004. 				link_re = regex['link']
    2005. 

  2005. 			else:                            # named link
    2006. 

  2006. 				link = m.group('link')
    2007. 

  2007. 				label = string.rstrip(m.group('label'))
    2008. 

  2008. 				link_re = regex['linkmark']
    2009. 

  2009. 			line = link_re.sub(self.linkmask,line,1)
    2010. 

  2010. 			
    2011. 

  2011. 			# save link data to the link bank
    2012. 

  2012. 			self.linkbank.append((label, link))
    2013. 

  2013. 		return line
    2014. 

  2014. 	
    2015. 

  2015. 	def undo(self, line):
    2016. 

  2016. 		
    2017. 

  2017. 		# url & email
    2018. 

  2018. 		for label,url in self.linkbank:
    2019. 

  2019. 			link = get_tagged_link(label, url)
    2020. 

  2020. 			line = string.replace(line, self.linkmask, link, 1)
    2021. 

  2021. 		
    2022. 

  2022. 		# expand macros
    2023. 

  2023. 		for macro in self.macrobank:
    2024. 

  2024. 			macro = self.macroman.expand(macro)
    2025. 

  2025. 			line = string.replace(line, self.macromask, macro,1)
    2026. 

  2026. 		
    2027. 

  2027. 		# expand verb
    2028. 

  2028. 		for mono in self.monobank:
    2029. 

  2029. 			open,close = TAGS['fontMonoOpen'],TAGS['fontMonoClose']
    2030. 

  2030. 			tagged = open+mono+close
    2031. 

  2031. 			line = string.replace(line,self.monomask,tagged,1)
    2032. 

  2032. 		
    2033. 

  2033. 		# expand raw
    2034. 

  2034. 		for raw in self.rawbank:
    2035. 

  2035. 			line = string.replace(line,self.rawmask,raw,1)
    2036. 

  2036. 		
    2037. 

  2037. 		return line
    2038. 

  2038. 

  2039. 

  2040. ##############################################################################
    2041. 

  2041. 

  2042. 

  2043. class TitleMaster:
    2044. 

  2044. 	"Title things"
    2045. 

  2045. 	def __init__(self):
    2046. 

  2046. 		self.count = ['',0,0,0,0,0]
    2047. 

  2047. 		self.toc   = []
    2048. 

  2048. 		self.level = 0
    2049. 

  2049. 		self.kind  = ''
    2050. 

  2050. 		self.txt   = ''
    2051. 

  2051. 		self.label = ''
    2052. 

  2052. 		self.tag   = ''
    2053. 

  2053. 		self.count_id = ''
    2054. 

  2054. 		self.user_labels = {}
    2055. 

  2055. 		self.anchor_count = 0
    2056. 

  2056. 		self.anchor_prefix = 'toc'
    2057. 

  2057. 	
    2058. 

  2058. 	def add(self, line):
    2059. 

  2059. 		"Parses a new title line."
    2060. 

  2060. 		if not line: return
    2061. 

  2061. 		self._set_prop(line)
    2062. 

  2062. 		self._set_count_id()
    2063. 

  2063. 		self._set_label()
    2064. 

  2064. 		self._save_toc_info()
    2065. 

  2065. 	
    2066. 

  2066. 	def _save_toc_info(self):
    2067. 

  2067. 		"Save TOC info, used by self.dump_marked_toc()"
    2068. 

  2068. 		self.toc.append((self.level, self.count_id,
    2069. 

  2069. 		                 self.txt  , self.label   ))
    2070. 

  2070. 	
    2071. 

  2071. 	def _set_prop(self, line=''):
    2072. 

  2072. 		"Extract info from original line and set data holders."
    2073. 

  2073. 		# detect title type (numbered or not)
    2074. 

  2074. 		id = string.lstrip(line)[0]
    2075. 

  2075. 		if   id == '=': kind = 'title'
    2076. 

  2076. 		elif id == '+': kind = 'numtitle'
    2077. 

  2077. 		else: Error("Unknown Title ID '%s'"%id)
    2078. 

  2078. 		# extract line info
    2079. 

  2079. 		match = regex[kind].search(line)
    2080. 

  2080. 		level = len(match.group('id'))
    2081. 

  2081. 		txt   = string.strip(match.group('txt'))
    2082. 

  2082. 		label = match.group('label')
    2083. 

  2083. 		# parse info & save
    2084. 

  2084. 		if CONF['enum-title']: kind = 'numtitle'  # force
    2085. 

  2085. 		self.tag   = TAGS[kind+`level`] or TAGS['title'+`level`]
    2086. 

  2086. 		self.kind  = kind
    2087. 

  2087. 		self.level = level
    2088. 

  2088. 		self.txt   = txt
    2089. 

  2089. 		self.label = label
    2090. 

  2090. 	
    2091. 

  2091. 	def _set_count_id(self):
    2092. 

  2092. 		"Compose and save the title count identifier (if needed)."
    2093. 

  2093. 		count_id = ''
    2094. 

  2094. 		if self.kind == 'numtitle' and not rules['autonumbertitle']:
    2095. 

  2095. 			# manually increase title count
    2096. 

  2096. 			self.count[self.level] = self.count[self.level] +1
    2097. 

  2097. 			# reset sublevels count (if any)
    2098. 

  2098. 			max_levels = len(self.count)
    2099. 

  2099. 			if self.level < max_levels-1:
    2100. 

  2100. 				for i in range(self.level+1, max_levels):
    2101. 

  2101. 					self.count[i] = 0
    2102. 

  2102. 			# compose count id from hierarchy
    2103. 

  2103. 			for i in range(self.level):
    2104. 

  2104. 				count_id= "%s%d."%(count_id, self.count[i+1])
    2105. 

  2105. 		self.count_id = count_id
    2106. 

  2106. 	
    2107. 

  2107. 	def _set_label(self):
    2108. 

  2108. 		"Compose and save title label, used by anchors."
    2109. 

  2109. 		# remove invalid chars from label set by user
    2110. 

  2110. 		self.label = re.sub('[^A-Za-z0-9_-]', '', self.label or '')
    2111. 

  2111. 		# generate name as 15 first :alnum: chars
    2112. 

  2112. 		#TODO how to translate safely accented chars to plain?
    2113. 

  2113. 		#self.label = re.sub('[^A-Za-z0-9]', '', self.txt)[:15]
    2114. 

  2114. 		# 'tocN' label - sequential count, ignoring 'toc-level'
    2115. 

  2115. 		#self.label = self.anchor_prefix + str(len(self.toc)+1)
    2116. 

  2116. 	
    2117. 

  2117. 	def _get_tagged_anchor(self):
    2118. 

  2118. 		"Return anchor if user defined a label, or TOC is on."
    2119. 

  2119. 		ret = ''
    2120. 

  2120. 		label = self.label
    2121. 

  2121. 		if CONF['toc'] and self.level <= CONF['toc-level']:
    2122. 

  2122. 			# this count is needed bcos self.toc stores all
    2123. 

  2123. 			# titles, regardless of the 'toc-level' setting,
    2124. 

  2124. 			# so we can't use self.toc lenght to number anchors
    2125. 

  2125. 			self.anchor_count = self.anchor_count + 1
    2126. 

  2126. 			# autonumber label (if needed)
    2127. 

  2127. 			label = label or '%s%s'%(
    2128. 

  2128. 			        self.anchor_prefix, self.anchor_count)
    2129. 

  2129. 		if label and TAGS['anchor']:
    2130. 

  2130. 			ret = regex['x'].sub(label,TAGS['anchor'])
    2131. 

  2131. 		return ret
    2132. 

  2132. 	
    2133. 

  2133. 	def _get_full_title_text(self):
    2134. 

  2134. 		"Returns the full title contents, already escaped."
    2135. 

  2135. 		ret = self.txt
    2136. 

  2136. 		# insert count_id (if any) before text
    2137. 

  2137. 		if self.count_id:
    2138. 

  2138. 			ret = '%s %s'%(self.count_id, ret)
    2139. 

  2139. 		# escape specials
    2140. 

  2140. 		ret = doEscape(TARGET, ret)
    2141. 

  2141. 		# same targets needs final escapes on title lines
    2142. 

  2142. 		# it's here because there is a 'continue' after title
    2143. 

  2143. 		if rules['finalescapetitle']:
    2144. 

  2144. 			ret = doFinalEscape(TARGET, ret)
    2145. 

  2145. 		return ret
    2146. 

  2146. 	
    2147. 

  2147. 	def get(self):
    2148. 

  2148. 		"Returns the tagged title as a list."
    2149. 

  2149. 		ret = []
    2150. 

  2150. 		
    2151. 

  2151. 		# maybe some anchoring before?
    2152. 

  2152. 		anchor = self._get_tagged_anchor()
    2153. 

  2153. 		self.tag = regex['_anchor'].sub(anchor, self.tag)
    2154. 

  2154. 		
    2155. 

  2155. 		### compose & escape title text (TOC uses unescaped)
    2156. 

  2156. 		full_title = self._get_full_title_text()
    2157. 

  2157. 		
    2158. 

  2158. 		# finish title, adding "underline" on TXT target
    2159. 

  2159. 		tagged = regex['x'].sub(full_title, self.tag)
    2160. 

  2160. 		if TARGET == 'txt':
    2161. 

  2161. 			ret.append('') # blank line before
    2162. 

  2162. 			ret.append(tagged)
    2163. 

  2163. 			ret.append(regex['x'].sub('='*len(full_title),self.tag))
    2164. 

  2164. 			ret.append('') # blank line after
    2165. 

  2165. 		else:
    2166. 

  2166. 			ret.append(tagged)
    2167. 

  2167. 		return ret
    2168. 

  2168. 	
    2169. 

  2169. 	def dump_marked_toc(self, max_level=99):
    2170. 

  2170. 		"Dumps all toc itens as a valid t2t markup list"
    2171. 

  2171. 		#TODO maybe use quote+linebreaks instead lists
    2172. 

  2172. 		ret = []
    2173. 

  2173. 		toc_count = 1
    2174. 

  2174. 		for level, count_id, txt, label in self.toc:
    2175. 

  2175. 			if level > max_level: continue   # ignore
    2176. 

  2176. 			indent = '  '*level
    2177. 

  2177. 			id_txt = string.lstrip('%s %s'%(count_id, txt))
    2178. 

  2178. 			label = label or self.anchor_prefix+`toc_count`
    2179. 

  2179. 			toc_count = toc_count + 1
    2180. 

  2180. 			# TOC will have links
    2181. 

  2181. 			if TAGS['anchor']:
    2182. 

  2182. 				# TOC is more readable with master topics
    2183. 

  2183. 				# not linked at number. This is a stoled
    2184. 

  2184. 				# idea from Windows .CHM help files
    2185. 

  2185. 				if CONF['enum-title'] and level == 1:
    2186. 

  2186. 					tocitem = '%s+ [""%s"" #%s]'%(
    2187. 

  2187. 					          indent, txt, label)
    2188. 

  2188. 				else:
    2189. 

  2189. 					tocitem = '%s- [""%s"" #%s]'%(
    2190. 

  2190. 					          indent, id_txt, label)
    2191. 

  2191. 			# no links on TOC, just text
    2192. 

  2192. 			else:
    2193. 

  2193. 				# man don't reformat TOC lines, cool!
    2194. 

  2194. 				if TARGET in ['txt', 'man']:
    2195. 

  2195. 					tocitem = '%s""%s""' %(
    2196. 

  2196. 					          indent, id_txt)
    2197. 

  2197. 				else:
    2198. 

  2198. 					tocitem = '%s- ""%s""'%(
    2199. 

  2199. 					          indent, id_txt)
    2200. 

  2200. 			ret.append(tocitem)
    2201. 

  2201. 		return ret
    2202. 

  2202. 

  2203. 

  2204. ##############################################################################
    2205. 

  2205. 

  2206. #TODO check all this table mess
    2207. 

  2207. # trata linhas TABLE, com as prop do parse_row
    2208. 

  2208. # o metodo table() do BLOCK xunxa e troca as celulas pelas parseadas
    2209. 

  2209. class TableMaster:
    2210. 

  2210. 	def __init__(self, line=''):
    2211. 

  2211. 		self.rows      = []
    2212. 

  2212. 		self.border    = 0
    2213. 

  2213. 		self.align     = 'Left'
    2214. 

  2214. 		self.cellalign = []
    2215. 

  2215. 		if line:
    2216. 

  2216. 			prop = self.parse_row(line)
    2217. 

  2217. 			self.border    = prop['border']
    2218. 

  2218. 			self.align     = prop['align']
    2219. 

  2219. 			self.cellalign = prop['cellalign']
    2220. 

  2220. 	
    2221. 

  2221. 	def _get_open_tag(self):
    2222. 

  2222. 		topen     = TAGS['tableOpen']
    2223. 

  2223. 		tborder   = TAGS['tableBorder']
    2224. 

  2224. 		talign    = TAGS['tableAlign'+self.align]
    2225. 

  2225. 		calignsep = TAGS['tableColAlignSep']
    2226. 

  2226. 		calign    = ''
    2227. 

  2227. 		
    2228. 

  2228. 		# the first line defines if table has border or not
    2229. 

  2229. 		if not self.border: tborder = ''
    2230. 

  2230. 		# set the columns alignment
    2231. 

  2231. 		if rules['tablecellaligntype'] == 'column':
    2232. 

  2232. 			calign = map(lambda x: TAGS['tableColAlign%s'%x],
    2233. 

  2233. 			             self.cellalign)
    2234. 

  2234. 			calign = string.join(calign, calignsep)
    2235. 

  2235. 		# align full table, set border and Column align (if any)
    2236. 

  2236. 		topen = regex['_tableAlign'   ].sub(talign , topen)
    2237. 

  2237. 		topen = regex['_tableBorder'  ].sub(tborder, topen)
    2238. 

  2238. 		topen = regex['_tableColAlign'].sub(calign , topen)
    2239. 

  2239. 		# tex table spec, border or not: {|l|c|r|} , {lcr}
    2240. 

  2240. 		if calignsep and not self.border:
    2241. 

  2241. 			# remove cell align separator
    2242. 

  2242. 			topen = string.replace(topen, calignsep, '')
    2243. 

  2243. 		return topen
    2244. 

  2244. 	
    2245. 

  2245. 	def _get_cell_align(self, cells):
    2246. 

  2246. 		ret = []
    2247. 

  2247. 		for cell in cells:
    2248. 

  2248. 			align = 'Left'
    2249. 

  2249. 			if string.strip(cell):
    2250. 

  2250. 				if cell[0] == ' ' and cell[-1] == ' ':
    2251. 

  2251. 					align = 'Center'
    2252. 

  2252. 				elif cell[0] == ' ':
    2253. 

  2253. 					align = 'Right'
    2254. 

  2254. 			ret.append(align)
    2255. 

  2255. 		return ret
    2256. 

  2256. 	
    2257. 

  2257. 	def _tag_cells(self, rowdata):
    2258. 

  2258. 		row = []
    2259. 

  2259. 		cells  = rowdata['cells']
    2260. 

  2260. 		open   = TAGS['tableCellOpen']
    2261. 

  2261. 		close  = TAGS['tableCellClose']
    2262. 

  2262. 		sep    = TAGS['tableCellSep']
    2263. 

  2263. 		calign = map(lambda x: TAGS['tableCellAlign'+x],
    2264. 

  2264. 		             rowdata['cellalign'])
    2265. 

  2265. 		
    2266. 

  2266. 		# maybe is it a title row?
    2267. 

  2267. 		if rowdata['title']:
    2268. 

  2268. 			open  = TAGS['tableTitleCellOpen']  or open
    2269. 

  2269. 			close = TAGS['tableTitleCellClose'] or close
    2270. 

  2270. 			sep   = TAGS['tableTitleCellSep']   or sep
    2271. 

  2271. 		
    2272. 

  2272. 		# should we break the line on *each* table cell?
    2273. 

  2273. 		if rules['breaktablecell']: close = close+'\n'
    2274. 

  2274. 		
    2275. 

  2275. 		# cells pre processing
    2276. 

  2276. 		if rules['tablecellstrip']:
    2277. 

  2277. 			cells = map(lambda x: string.strip(x), cells)
    2278. 

  2278. 		if rowdata['title'] and rules['tabletitlerowinbold']:
    2279. 

  2279. 			cells = map(lambda x: enclose_me('fontBold',x), cells)
    2280. 

  2280. 		
    2281. 

  2281. 		# add cell BEGIN/END tags
    2282. 

  2282. 		for cell in cells:
    2283. 

  2283. 			# insert cell align into open tag (if cell is alignable)
    2284. 

  2284. 			if rules['tablecellaligntype'] == 'cell':
    2285. 

  2285. 				copen = string.replace(open,'\a',calign.pop(0))
    2286. 

  2286. 			else:
    2287. 

  2287. 				copen = open
    2288. 

  2288. 			row.append(copen + cell + close)
    2289. 

  2289. 		
    2290. 

  2290. 		# maybe there are cell separators?
    2291. 

  2291. 		return string.join(row, sep)
    2292. 

  2292. 	
    2293. 

  2293. 	def add_row(self, cells):
    2294. 

  2294. 		self.rows.append(cells)
    2295. 

  2295. 	
    2296. 

  2296. 	def parse_row(self, line):
    2297. 

  2297. 		# default table proprierties
    2298. 

  2298. 		ret = {'border':0,'title':0,'align':'Left',
    2299. 

  2299. 		       'cells':[],'cellalign':[]}
    2300. 

  2300. 		# detect table align (and remove spaces mark)
    2301. 

  2301. 		if line[0] == ' ': ret['align'] = 'Center'
    2302. 

  2302. 		line = string.lstrip(line)
    2303. 

  2303. 		# detect title mark
    2304. 

  2304. 		if line[1] == '|': ret['title'] = 1
    2305. 

  2305. 		# delete trailing spaces after last cell border
    2306. 

  2306. 		line = re.sub('\|\s*$','|', line)
    2307. 

  2307. 		# detect (and delete) border mark (and leading space)
    2308. 

  2308. 		if line[-1] == '|': ret['border'] = 1 ; line = line[:-2]
    2309. 

  2309. 		# delete table mark
    2310. 

  2310. 		line = regex['table'].sub('', line)
    2311. 

  2311. 		# split cells
    2312. 

  2312. 		ret['cells'] = string.split(line, ' | ')
    2313. 

  2313. 		# find cells align
    2314. 

  2314. 		ret['cellalign'] = self._get_cell_align(ret['cells'])
    2315. 

  2315. 		
    2316. 

  2316. 		Debug('Table Prop: %s' % ret, 2)
    2317. 

  2317. 		return ret
    2318. 

  2318. 	
    2319. 

  2319. 	def dump(self):
    2320. 

  2320. 		open  = self._get_open_tag()
    2321. 

  2321. 		rows  = self.rows
    2322. 

  2322. 		close = TAGS['tableClose']
    2323. 

  2323. 		
    2324. 

  2324. 		rowopen     = TAGS['tableRowOpen']
    2325. 

  2325. 		rowclose    = TAGS['tableRowClose']
    2326. 

  2326. 		rowsep      = TAGS['tableRowSep']
    2327. 

  2327. 		titrowopen  = TAGS['tableTitleRowOpen']  or rowopen
    2328. 

  2328. 		titrowclose = TAGS['tableTitleRowClose'] or rowclose
    2329. 

  2329. 		
    2330. 

  2330. 		if rules['breaktablelineopen']:
    2331. 

  2331. 			rowopen = rowopen + '\n'
    2332. 

  2332. 			titrowopen = titrowopen + '\n'
    2333. 

  2333. 		
    2334. 

  2334. 		# tex gotchas
    2335. 

  2335. 		if TARGET == 'tex':
    2336. 

  2336. 			if not self.border:
    2337. 

  2337. 				rowopen = titrowopen = ''
    2338. 

  2338. 			else:
    2339. 

  2339. 				close = rowopen + close
    2340. 

  2340. 		
    2341. 

  2341. 		# now we tag all the table cells on each row
    2342. 

  2342. 		#tagged_cells = map(lambda x: self._tag_cells(x), rows) #!py15
    2343. 

  2343. 		tagged_cells = []
    2344. 

  2344. 		for cell in rows: tagged_cells.append(self._tag_cells(cell))
    2345. 

  2345. 		
    2346. 

  2346. 		# add row separator tags between lines
    2347. 

  2347. 		tagged_rows = []
    2348. 

  2348. 		if rowsep:
    2349. 

  2349. 			#!py15
    2350. 

  2350. 			#tagged_rows = map(lambda x:x+rowsep, tagged_cells)
    2351. 

  2351. 			for cell in tagged_cells:
    2352. 

  2352. 				tagged_rows.append(cell+rowsep)
    2353. 

  2353. 			# remove last rowsep, because the table is over
    2354. 

  2354. 			tagged_rows[-1] = string.replace(
    2355. 

  2355. 			                  tagged_rows[-1], rowsep, '')
    2356. 

  2356. 		# add row BEGIN/END tags for each line
    2357. 

  2357. 		else:
    2358. 

  2358. 			for rowdata in rows:
    2359. 

  2359. 				if rowdata['title']:
    2360. 

  2360. 					o,c = titrowopen, titrowclose
    2361. 

  2361. 				else:
    2362. 

  2362. 					o,c = rowopen, rowclose
    2363. 

  2363. 				row = tagged_cells.pop(0)
    2364. 

  2364. 				tagged_rows.append(o + row + c)
    2365. 

  2365. 		
    2366. 

  2366. 		fulltable = [open] + tagged_rows + [close]
    2367. 

  2367. 		
    2368. 

  2368. 		if rules['blankendtable']: fulltable.append('')
    2369. 

  2369. 		return fulltable
    2370. 

  2370. 

  2371. 

  2372. ##############################################################################
    2373. 

  2373. 

  2374. 

  2375. class BlockMaster:
    2376. 

  2376. 	"TIP: use blockin/out to add/del holders"
    2377. 

  2377. 	def __init__(self):
    2378. 

  2378. 		self.BLK = []
    2379. 

  2379. 		self.HLD = []
    2380. 

  2380. 		self.PRP = []
    2381. 

  2381. 		self.depth = 0
    2382. 

  2382. 		self.last = ''
    2383. 

  2383. 		self.tableparser = None
    2384. 

  2384. 		self.contains = {
    2385. 

  2385. 		  'para'    :['passthru','raw'],
    2386. 

  2386. 		  'verb'    :[],
    2387. 

  2387. 		  'table'   :[],
    2388. 

  2388. 		  'raw'     :[],
    2389. 

  2389. 		  'passthru':[],
    2390. 

  2390. 		  'quote'   :['quote','passthru','raw'],
    2391. 

  2391. 		  'list'    :['list' ,'numlist' ,'deflist','para','verb',
    2392. 

  2392. 		              'raw'  ,'passthru'],
    2393. 

  2393. 		  'numlist' :['list' ,'numlist' ,'deflist','para','verb',
    2394. 

  2394. 		              'raw'  ,'passthru'],
    2395. 

  2395. 		  'deflist' :['list' ,'numlist' ,'deflist','para','verb',
    2396. 

  2396. 		              'raw'  ,'passthru']
    2397. 

  2397. 		}
    2398. 

  2398. 		self.allblocks = self.contains.keys()
    2399. 

  2399. 	
    2400. 

  2400. 	def block(self):
    2401. 

  2401. 		if not self.BLK: return ''
    2402. 

  2402. 		return self.BLK[-1]
    2403. 

  2403. 	
    2404. 

  2404. 	def isblock(self, name=''):
    2405. 

  2405. 		return self.block() == name
    2406. 

  2406. 	
    2407. 

  2407. 	def prop(self, key):
    2408. 

  2408. 		if not self.PRP: return ''
    2409. 

  2409. 		return self.PRP[-1].get(key) or ''
    2410. 

  2410. 	
    2411. 

  2411. 	def propset(self, key, val):
    2412. 

  2412. 		self.PRP[-1][key] = val
    2413. 

  2413. 		#Debug('BLOCK prop ++: %s->%s'%(key,repr(val)), 1)
    2414. 

  2414. 		#Debug('BLOCK props: %s'%(repr(self.PRP)), 1)
    2415. 

  2415. 	
    2416. 

  2416. 	def hold(self):
    2417. 

  2417. 		if not self.HLD: return []
    2418. 

  2418. 		return self.HLD[-1]
    2419. 

  2419. 	
    2420. 

  2420. 	def holdadd(self, line):
    2421. 

  2421. 		if self.block()[-4:] == 'list': line = [line]
    2422. 

  2422. 		self.HLD[-1].append(line)
    2423. 

  2423. 		Debug('HOLD add: %s'%repr(line), 5)
    2424. 

  2424. 		Debug('FULL HOLD: %s'%self.HLD, 2)
    2425. 

  2425. 	
    2426. 

  2426. 	def holdaddsub(self, line):
    2427. 

  2427. 		self.HLD[-1][-1].append(line)
    2428. 

  2428. 		Debug('HOLD addsub: %s'%repr(line), 5)
    2429. 

  2429. 		Debug('FULL HOLD: %s'%self.HLD, 2)
    2430. 

  2430. 	
    2431. 

  2431. 	def holdextend(self, lines):
    2432. 

  2432. 		if self.block()[-4:] == 'list': lines = [lines]
    2433. 

  2433. 		self.HLD[-1].extend(lines)
    2434. 

  2434. 		Debug('HOLD extend: %s'%repr(lines), 5)
    2435. 

  2435. 		Debug('FULL HOLD: %s'%self.HLD, 2)
    2436. 

  2436. 	
    2437. 

  2437. 	def blockin(self, block):
    2438. 

  2438. 		ret = []
    2439. 

  2439. 		if block not in self.allblocks:
    2440. 

  2440. 			Error("Invalid block '%s'"%block)
    2441. 

  2441. 		# first, let's close other possible open blocks
    2442. 

  2442. 		while self.block() and block not in self.contains[self.block()]:
    2443. 

  2443. 			ret.extend(self.blockout())
    2444. 

  2444. 		# now we can gladly add this new one
    2445. 

  2445. 		self.BLK.append(block)
    2446. 

  2446. 		self.HLD.append([])
    2447. 

  2447. 		self.PRP.append({})
    2448. 

  2448. 		if block == 'table': self.tableparser = TableMaster()
    2449. 

  2449. 		# deeper and deeper
    2450. 

  2450. 		self.depth = len(self.BLK)
    2451. 

  2451. 		Debug('block ++ (%s): %s' % (block,self.BLK), 6)
    2452. 

  2452. 		return ret
    2453. 

  2453. 	
    2454. 

  2454. 	def blockout(self):
    2455. 

  2455. 		if not self.BLK: Error('No block to pop')
    2456. 

  2456. 		self.last = self.BLK.pop()
    2457. 

  2457. 		tagged = getattr(self, self.last)()
    2458. 

  2458. 		parsed = self.HLD.pop()
    2459. 

  2459. 		self.PRP.pop()
    2460. 

  2460. 		self.depth = len(self.BLK)
    2461. 

  2461. 		if self.last == 'table': del self.tableparser
    2462. 

  2462. 		# inserting a nested block into mother
    2463. 

  2463. 		if self.block():
    2464. 

  2464. 			if self.block()[-4:] == 'list':
    2465. 

  2465. 				self.HLD[-1][-1].append(tagged)
    2466. 

  2466. 			else:
    2467. 

  2467. 				self.HLD[-1].append(tagged)
    2468. 

  2468. 			tagged = []   # reset. mother will have it all
    2469. 

  2469. 		Debug('block -- (%s): %s' % (self.last,self.BLK), 6)
    2470. 

  2470. 		Debug('RELEASED (%s): %s' % (self.last,parsed), 6)
    2471. 

  2471. 		if tagged: Debug('DUMPED: %s'%tagged, 2)
    2472. 

  2472. 		return tagged
    2473. 

  2473. 	
    2474. 

  2474. 	def _last_escapes(self, line):
    2475. 

  2475. 		return doFinalEscape(TARGET, line)
    2476. 

  2476. 	
    2477. 

  2477. 	def _get_escaped_hold(self):
    2478. 

  2478. 		ret = []
    2479. 

  2479. 		for line in self.hold():
    2480. 

  2480. 			linetype = type(line)
    2481. 

  2481. 			if linetype == type(''):
    2482. 

  2482. 				ret.append(self._last_escapes(line))
    2483. 

  2483. 			elif linetype == type([]):
    2484. 

  2484. 				ret.extend(line)
    2485. 

  2485. 			else:
    2486. 

  2486. 				Error("BlockMaster: Unknown HOLD item type:"
    2487. 

  2487. 				      " %s"%linetype)
    2488. 

  2488. 		return ret
    2489. 

  2489. 	
    2490. 

  2490. 	def _remove_twoblanks(self, lastitem):
    2491. 

  2491. 		if len(lastitem) > 1 and lastitem[-2:] == ['','']:
    2492. 

  2492. 			return lastitem[:-2]
    2493. 

  2493. 		return lastitem
    2494. 

  2494. 	
    2495. 

  2495. 	def passthru(self):
    2496. 

  2496. 		return self.hold()
    2497. 

  2497. 	
    2498. 

  2498. 	def raw(self):
    2499. 

  2499. 		lines = self.hold()
    2500. 

  2500. 		return map(lambda x: doEscape(TARGET, x), lines)
    2501. 

  2501. 	
    2502. 

  2502. 	def para(self):
    2503. 

  2503. 		tagged = []
    2504. 

  2504. 		open  = TAGS['paragraphOpen']
    2505. 

  2505. 		close = TAGS['paragraphClose']
    2506. 

  2506. 		lines = self._get_escaped_hold()
    2507. 

  2507. 		# open (or not) paragraph
    2508. 

  2508. 		if not open+close and self.last == 'para':
    2509. 

  2509. 			pass # avoids multiple blank lines
    2510. 

  2510. 		else:
    2511. 

  2511. 			tagged.append(open)
    2512. 

  2512. 		# pagemaker likes a paragraph as a single long line
    2513. 

  2513. 		if rules['onelinepara']:
    2514. 

  2514. 			tagged.append(string.join(lines,' '))
    2515. 

  2515. 		# others are normal :)
    2516. 

  2516. 		else:
    2517. 

  2517. 			tagged.extend(lines)
    2518. 

  2518. 		tagged.append(close)
    2519. 

  2519. 		
    2520. 

  2520. 		# very very very very very very very very very UGLY fix
    2521. 

  2521. 		# needed because <center> can't appear inside <p>
    2522. 

  2522. 		try:
    2523. 

  2523. 			if len(lines) == 1 and \
    2524. 

  2524. 			   TARGET in ('html', 'xhtml') and \
    2525. 

  2525. 			   re.match('^\s*<center>.*</center>\s*$', lines[0]):
    2526. 

  2526. 				tagged = [lines[0]]
    2527. 

  2527. 		except: pass
    2528. 

  2528. 		
    2529. 

  2529. 		return tagged
    2530. 

  2530. 	
    2531. 

  2531. 	def verb(self):
    2532. 

  2532. 		"Verbatim lines are not masked, so there's no need to unmask"
    2533. 

  2533. 		tagged = []
    2534. 

  2534. 		tagged.append(TAGS['blockVerbOpen'])
    2535. 

  2535. 		for line in self.hold():
    2536. 

  2536. 			if self.prop('mapped') == 'table':
    2537. 

  2537. 				line = MacroMaster().expand(line)
    2538. 

  2538. 			if not rules['verbblocknotescaped']:
    2539. 

  2539. 				line = doEscape(TARGET,line)
    2540. 

  2540. 			if rules['indentverbblock']:
    2541. 

  2541. 				line = '  '+line
    2542. 

  2542. 			if rules['verbblockfinalescape']:
    2543. 

  2543. 				line = doFinalEscape(TARGET, line)
    2544. 

  2544. 			tagged.append(line)
    2545. 

  2545. 		#TODO maybe use if not TAGS['blockVerbClose']
    2546. 

  2546. 		if TARGET != 'pm6':
    2547. 

  2547. 			tagged.append(TAGS['blockVerbClose'])
    2548. 

  2548. 		return tagged
    2549. 

  2549. 	
    2550. 

  2550. 	def table(self):
    2551. 

  2551. 		# rewrite all table cells by the unmasked and escaped data
    2552. 

  2552. 		lines = self._get_escaped_hold()
    2553. 

  2553. 		for i in range(len(lines)):
    2554. 

  2554. 			cells = string.split(lines[i], SEPARATOR)
    2555. 

  2555. 			self.tableparser.rows[i]['cells'] = cells
    2556. 

  2556. 		
    2557. 

  2557. 		return self.tableparser.dump()
    2558. 

  2558. 	
    2559. 

  2559. 	def quote(self):
    2560. 

  2560. 		tagged = []
    2561. 

  2561. 		myre   = regex['quote']
    2562. 

  2562. 		open   = TAGS['blockQuoteOpen']            # block based
    2563. 

  2563. 		close  = TAGS['blockQuoteClose']
    2564. 

  2564. 		qline  = TAGS['blockQuoteLine']            # line based
    2565. 

  2565. 		indent = tagindent = '\t'*self.depth
    2566. 

  2566. 		if rules['tagnotindentable']: tagindent = ''
    2567. 

  2567. 		if not rules['keepquoteindent']: indent = ''
    2568. 

  2568. 		
    2569. 

  2569. 		if open: tagged.append(tagindent+open)     # open block
    2570. 

  2570. 		for item in self.hold():
    2571. 

  2571. 			if type(item) == type([]):
    2572. 

  2572. 				tagged.extend(item)        # subquotes
    2573. 

  2573. 			else:
    2574. 

  2574. 				item = myre.sub('', item)  # del TABs
    2575. 

  2575. 				if rules['barinsidequote']:
    2576. 

  2576. 					item = get_tagged_bar(item)
    2577. 

  2577. 				item = self._last_escapes(item)
    2578. 

  2578. 				item = qline*self.depth + item
    2579. 

  2579. 				tagged.append(indent+item) # quote line
    2580. 

  2580. 		if close: tagged.append(tagindent+close)   # close block
    2581. 

  2581. 		return tagged
    2582. 

  2582. 	
    2583. 

  2583. 	def deflist(self): return self.list('deflist')
    2584. 

  2584. 	def numlist(self): return self.list('numlist')
    2585. 

  2585. 	def list(self, name='list'):
    2586. 

  2586. 		tagged    = []
    2587. 

  2587. 		items     = self.hold()
    2588. 

  2588. 		indent    = self.prop('indent')
    2589. 

  2589. 		tagindent = indent
    2590. 

  2590. 		listopen  = TAGS.get(name+'Open')
    2591. 

  2591. 		listclose = TAGS.get(name+'Close')
    2592. 

  2592. 		listline  = TAGS.get(name+'ItemLine')
    2593. 

  2593. 		itemcount = 0
    2594. 

  2594. 		if rules['tagnotindentable']: tagindent = ''
    2595. 

  2595. 		if not rules['keeplistindent']: indent = ''
    2596. 

  2596. 		
    2597. 

  2597. 		if name == 'deflist':
    2598. 

  2598. 			itemopen  = TAGS[name+'Item1Open']
    2599. 

  2599. 			itemclose = TAGS[name+'Item2Close']
    2600. 

  2600. 			itemsep   = TAGS[name+'Item1Close']+\
    2601. 

  2601. 			            TAGS[name+'Item2Open']
    2602. 

  2602. 		else:
    2603. 

  2603. 			itemopen  = TAGS[name+'ItemOpen']
    2604. 

  2604. 			itemclose = TAGS[name+'ItemClose']
    2605. 

  2605. 			itemsep   = ''
    2606. 

  2606. 		
    2607. 

  2607. 		# ItemLine: number of leading chars identifies list depth
    2608. 

  2608. 		if listline:
    2609. 

  2609. 			itemopen  = listline*self.depth
    2610. 

  2610. 			# dirty fix for mgp
    2611. 

  2611. 			if name == 'numlist': itemopen = itemopen + '\a. '
    2612. 

  2612. 		
    2613. 

  2613. 		# remove two-blanks from list ending mark, to avoid <p>
    2614. 

  2614. 		items[-1] = self._remove_twoblanks(items[-1])
    2615. 

  2615. 		
    2616. 

  2616. 		# open list (not nestable lists are only opened at mother)
    2617. 

  2617. 		if listopen and not \
    2618. 

  2618. 		   (rules['listnotnested'] and BLOCK.depth != 1):
    2619. 

  2619. 			tagged.append(tagindent+listopen)
    2620. 

  2620. 		
    2621. 

  2621. 		# tag each list item (multine items)
    2622. 

  2622. 		itemopenorig = itemopen
    2623. 

  2623. 		for item in items:
    2624. 

  2624. 			
    2625. 

  2625. 			# add "manual" item count for noautonum targets
    2626. 

  2626. 			itemcount = itemcount + 1
    2627. 

  2627. 			if name == 'numlist' and not rules['autonumberlist']:
    2628. 

  2628. 				n = str(itemcount)
    2629. 

  2629. 				itemopen = regex['x'].sub(n, itemopenorig)
    2630. 

  2630. 				del n
    2631. 

  2631. 			
    2632. 

  2632. 			item[0] = self._last_escapes(item[0])
    2633. 

  2633. 			if name == 'deflist':
    2634. 

  2634. 				term, rest = string.split(item[0],SEPARATOR,1)
    2635. 

  2635. 				item[0] = rest
    2636. 

  2636. 				if not item[0]: del item[0]      # to avoid <p>
    2637. 

  2637. 				tagged.append(tagindent+itemopen+term+itemsep)
    2638. 

  2638. 			else:
    2639. 

  2639. 				fullitem = tagindent+itemopen
    2640. 

  2640. 				tagged.append(string.replace(
    2641. 

  2641. 				              item[0], SEPARATOR, fullitem))
    2642. 

  2642. 				del item[0]
    2643. 

  2643. 			
    2644. 

  2644. 			# process next lines for this item (if any)
    2645. 

  2645. 			for line in item:
    2646. 

  2646. 				if type(line) == type([]): # sublist inside
    2647. 

  2647. 					tagged.extend(line)
    2648. 

  2648. 				else:
    2649. 

  2649. 					line = self._last_escapes(line)
    2650. 

  2650. 					# blank lines turns to <p>
    2651. 

  2651. 					if not line and rules['parainsidelist']:
    2652. 

  2652. 						line = string.rstrip(indent   +\
    2653. 

  2653. 						         TAGS['paragraphOpen']+\
    2654. 

  2654. 						         TAGS['paragraphClose'])
    2655. 

  2655. 					if not rules['keeplistindent']:
    2656. 

  2656. 						line = string.lstrip(line)
    2657. 

  2657. 					tagged.append(line)
    2658. 

  2658. 			
    2659. 

  2659. 			# close item (if needed)
    2660. 

  2660. 			if itemclose: tagged.append(tagindent+itemclose)
    2661. 

  2661. 		
    2662. 

  2662. 		# close list (not nestable lists are only closed at mother)
    2663. 

  2663. 		if listclose and not \
    2664. 

  2664. 		   (rules['listnotnested'] and BLOCK.depth != 1):
    2665. 

  2665. 			tagged.append(tagindent+listclose)
    2666. 

  2666. 		
    2667. 

  2667. 		if rules['blankendmotherlist'] and BLOCK.depth == 1:
    2668. 

  2668. 			tagged.append('')
    2669. 

  2669. 		
    2670. 

  2670. 		return tagged
    2671. 

  2671. 

  2672. 

  2673. ##############################################################################
    2674. 

  2674. 

  2675. 

  2676. class MacroMaster:
    2677. 

  2677. 	def __init__(self, config={}):
    2678. 

  2678. 		self.name     = ''
    2679. 

  2679. 		self.config   = config or CONF
    2680. 

  2680. 		self.infile   = self.config['sourcefile']
    2681. 

  2681. 		self.outfile  = self.config['outfile']
    2682. 

  2682. 		self.currdate = time.localtime(time.time())
    2683. 

  2683. 		self.rgx      = regex.get('macros') or getRegexes()['macros']
    2684. 

  2684. 		self.fileinfo = { 'infile': None, 'outfile': None }
    2685. 

  2685. 		self.dft_fmt  = MACROS
    2686. 

  2686. 	
    2687. 

  2687. 	def walk_file_format(self, fmt):
    2688. 

  2688. 		"Walks the %%{in/out}file format string, expanding the % flags"
    2689. 

  2689. 		i = 0; ret = ''                                 # counter/hold
    2690. 

  2690. 		while i < len(fmt):                             # char by char
    2691. 

  2691. 			c = fmt[i]; i = i + 1
    2692. 

  2692. 			if c == '%':                            # hot char!
    2693. 

  2693. 				if i == len(fmt):               # % at the end
    2694. 

  2694. 					ret = ret + c
    2695. 

  2695. 					break
    2696. 

  2696. 				c = fmt[i]; i = i + 1           # read next
    2697. 

  2697. 				ret = ret + self.expand_file_flag(c)
    2698. 

  2698. 			else:
    2699. 

  2699. 				ret = ret +c                    # common char
    2700. 

  2700. 		return ret
    2701. 

  2701. 	
    2702. 

  2702. 	def expand_file_flag(self, flag):
    2703. 

  2703. 		"%f: filename          %F: filename (w/o extension)"
    2704. 

  2704. 		"%d: dirname           %D: dirname (only parent dir)"
    2705. 

  2705. 		"%p: file path         %e: extension"
    2706. 

  2706. 		info = self.fileinfo[self.name]           # get dict
    2707. 

  2707. 		if   flag == '%': x = '%'                 # %% -> %
    2708. 

  2708. 		elif flag == 'f': x = info['name']
    2709. 

  2709. 		elif flag == 'F': x = re.sub('\.[^.]*$','',info['name'])
    2710. 

  2710. 		elif flag == 'd': x = info['dir']
    2711. 

  2711. 		elif flag == 'D': x = os.path.split(info['dir'])[-1]
    2712. 

  2712. 		elif flag == 'p': x = info['path']
    2713. 

  2713. 		elif flag == 'e': x = re.search('.(\.([^.]+))?$',info['name']
    2714. 

  2714. 		                                ).group(2) or ''
    2715. 

  2715. 		#TODO simplier way for %e ?
    2716. 

  2716. 		else            : x = '%'+flag            # false alarm
    2717. 

  2717. 		return x
    2718. 

  2718. 	
    2719. 

  2719. 	def set_file_info(self, macroname):
    2720. 

  2720. 		if self.fileinfo.get(macroname): return   # already done
    2721. 

  2721. 		file = getattr(self, self.name)           # self.infile
    2722. 

  2722. 		if file == STDOUT:
    2723. 

  2723. 			dir = ''; path = name = STDOUT
    2724. 

  2724. 		else:
    2725. 

  2725. 			path = os.path.abspath(file)
    2726. 

  2726. 			dir  = os.path.dirname(path)
    2727. 

  2727. 			name = os.path.basename(path)
    2728. 

  2728. 		self.fileinfo[macroname] = {'path':path,'dir':dir,'name':name}
    2729. 

  2729. 	
    2730. 

  2730. 	def expand(self, line=''):
    2731. 

  2731. 		"Expand all macros found on the line"
    2732. 

  2732. 		while self.rgx.search(line):
    2733. 

  2733. 			m = self.rgx.search(line)
    2734. 

  2734. 			name = self.name = m.group('name')
    2735. 

  2735. 			fmt = m.group('fmt') or self.dft_fmt.get(name)
    2736. 

  2736. 			if name == 'date':
    2737. 

  2737. 				txt = time.strftime(fmt,self.currdate)
    2738. 

  2738. 			elif name == 'mtime':
    2739. 

  2739. 				if self.infile == STDIN:
    2740. 

  2740. 					fdate = self.currdate
    2741. 

  2741. 				else:
    2742. 

  2742. 					mtime = os.path.getmtime(self.infile)
    2743. 

  2743. 					fdate = time.localtime(mtime)
    2744. 

  2744. 				txt = time.strftime(fmt,fdate)
    2745. 

  2745. 			elif name in ['infile','outfile']:
    2746. 

  2746. 				self.set_file_info(name)
    2747. 

  2747. 				txt = self.walk_file_format(fmt)
    2748. 

  2748. 			else:
    2749. 

  2749. 				Error("Unknown macro name '%s'"%name)
    2750. 

  2750. 			line = self.rgx.sub(txt,line,1)
    2751. 

  2751. 		return line
    2752. 

  2752. 

  2753. 

  2754. ##############################################################################
    2755. 

  2755. 

  2756. 

  2757. def dumpConfig(source_raw, parsed_config):
    2758. 

  2758. 	onoff = {1:_('ON'), 0:_('OFF')}
    2759. 

  2759. 	data = [
    2760. 

  2760. 	  (_('RC file')        , RC_RAW     ),
    2761. 

  2761. 	  (_('source document'), source_raw ),
    2762. 

  2762. 	  (_('command line')   , CMDLINE_RAW)
    2763. 

  2763. 	]
    2764. 

  2764. 	# first show all RAW data found
    2765. 

  2765. 	for label, cfg in data:
    2766. 

  2766. 		print _('RAW config for %s')%label
    2767. 

  2767. 		for target,key,val in cfg:
    2768. 

  2768. 			target = '(%s)'%target
    2769. 

  2769. 			key    = dotted_spaces("%-14s"%key)
    2770. 

  2770. 			val    = val or _('ON')
    2771. 

  2771. 			print '  %-8s %s: %s'%(target,key,val)
    2772. 

  2772. 		print
    2773. 

  2773. 	# then the parsed results of all of them
    2774. 

  2774. 	print _('Full PARSED config')
    2775. 

  2775. 	keys = parsed_config.keys() ; keys.sort()  # sorted
    2776. 

  2776. 	for key in keys:
    2777. 

  2777. 		val = parsed_config[key]
    2778. 

  2778. 		# filters are the last
    2779. 

  2779. 		if key in ['preproc', 'postproc']:
    2780. 

  2780. 			continue
    2781. 

  2781. 		# flag beautifier
    2782. 

  2782. 		if key in FLAGS.keys()+ACTIONS.keys():
    2783. 

  2783. 			val = onoff.get(val) or val
    2784. 

  2784. 		# list beautifier
    2785. 

  2785. 		if type(val) == type([]):
    2786. 

  2786. 			if key == 'options': sep = ' '
    2787. 

  2787. 			else               : sep = ', '
    2788. 

  2788. 			val = string.join(val, sep)
    2789. 

  2789. 		print "%25s: %s"%(dotted_spaces("%-14s"%key),val)
    2790. 

  2790. 	print
    2791. 

  2791. 	print _('Active filters')
    2792. 

  2792. 	for filter in ['preproc','postproc']:
    2793. 

  2793. 		for rule in parsed_config.get(filter) or []:
    2794. 

  2794. 			print "%25s: %s  ->  %s"%(
    2795. 

  2795. 			   dotted_spaces("%-14s"%filter),rule[0],rule[1])
    2796. 

  2796. 

  2797. 

  2798. def get_file_body(file):
    2799. 

  2799. 	"Returns all the document BODY lines"
    2800. 

  2800. 	return process_source_file(file, noconf=1)[1][2]
    2801. 

  2801. 

  2802. 

  2803. def finish_him(outlist, config):
    2804. 

  2804. 	"Writing output to screen or file"
    2805. 

  2805. 	outfile = config['outfile']
    2806. 

  2806. 	outlist = unmaskEscapeChar(outlist)
    2807. 

  2807. 	
    2808. 

  2808. 	# apply PostProc filters
    2809. 

  2809. 	if config['postproc']:
    2810. 

  2810. 		filters = compile_filters(config['postproc'],
    2811. 

  2811. 		                        _('Invalid PostProc filter regex'))
    2812. 

  2812. 		postoutlist = []
    2813. 

  2813. 		for line in outlist:
    2814. 

  2814. 			for rgx,repl in filters:
    2815. 

  2815. 				line = rgx.sub(repl, line)
    2816. 

  2816. 			postoutlist.append(line)
    2817. 

  2817. 		outlist = postoutlist[:]
    2818. 

  2818. 	
    2819. 

  2819. 	if outfile == STDOUT:
    2820. 

  2820. 		if GUI:
    2821. 

  2821. 			return outlist, config
    2822. 

  2822. 		else:
    2823. 

  2823. 			for line in outlist: print line
    2824. 

  2824. 	else:
    2825. 

  2825. 		Savefile(outfile, addLineBreaks(outlist))
    2826. 

  2826. 		if not GUI and not QUIET:
    2827. 

  2827. 			print _('%s wrote %s')%(my_name,outfile)
    2828. 

  2828. 	
    2829. 

  2829. 	if config['split']:
    2830. 

  2830. 		if not QUIET: print "--- html..."
    2831. 

  2831. 		sgml2html = 'sgml2html -s %s -l %s %s'%(
    2832. 

  2832. 		            config['split'],config['lang'] or lang,outfile)
    2833. 

  2833. 		if not QUIET: print "Running system command:", sgml2html
    2834. 

  2834. 		os.system(sgml2html)
    2835. 

  2835. 

  2836. 

  2837. def toc_inside_body(body, toc, config):
    2838. 

  2838. 	ret = []
    2839. 

  2839. 	if AUTOTOC: return body                     # nothing to expand
    2840. 

  2840. 	toc_mark = MaskMaster().tocmask
    2841. 

  2841. 	# expand toc mark with TOC contents
    2842. 

  2842. 	for line in body:
    2843. 

  2843. 		if string.count(line, toc_mark):    # toc mark found
    2844. 

  2844. 			if config['toc']:
    2845. 

  2845. 				ret.extend(toc)     # include if --toc
    2846. 

  2846. 			else:
    2847. 

  2847. 				pass                # or remove %%toc line
    2848. 

  2848. 		else:
    2849. 

  2849. 			ret.append(line)            # common line
    2850. 

  2850. 	return ret
    2851. 

  2851. 

  2852. def toc_tagger(toc, config):
    2853. 

  2853. 	"Convert t2t-marked TOC (it is a list) to target-tagged TOC"
    2854. 

  2854. 	ret = []
    2855. 

  2855. 	# tag if TOC-only TOC "by hand" (target don't have a TOC tag)
    2856. 

  2856. 	if config['toc-only'] or (config['toc'] and not TAGS['TOC']):
    2857. 

  2857. 		fakeconf = config.copy()
    2858. 

  2858. 		fakeconf['headers']    = 0
    2859. 

  2859. 		fakeconf['toc-only']   = 0
    2860. 

  2860. 		fakeconf['mask-email'] = 0
    2861. 

  2861. 		fakeconf['preproc']    = []
    2862. 

  2862. 		fakeconf['postproc']   = []
    2863. 

  2863. 		fakeconf['css-sugar']  = 0
    2864. 

  2864. 		ret,foo = convert(toc, fakeconf)
    2865. 

  2865. 		set_global_config(config)   # restore config
    2866. 

  2866. 	# target TOC is a tag
    2867. 

  2867. 	elif config['toc'] and TAGS['TOC']:
    2868. 

  2868. 		ret = [TAGS['TOC']]
    2869. 

  2869. 	return ret
    2870. 

  2870. 

  2871. def toc_formatter(toc, config):
    2872. 

  2872. 	"Formats TOC for automatic placement between headers and body"
    2873. 

  2873. 	if config['toc-only']: return toc              # no formatting needed
    2874. 

  2874. 	if not config['toc'] : return []               # TOC disabled
    2875. 

  2875. 	ret = toc
    2876. 

  2876. 	# TOC open/close tags (if any)
    2877. 

  2877. 	if TAGS['tocOpen' ]: ret.insert(0, TAGS['tocOpen'])
    2878. 

  2878. 	if TAGS['tocClose']: ret.append(TAGS['tocClose'])
    2879. 

  2879. 	# autotoc specific formatting
    2880. 

  2880. 	if AUTOTOC:
    2881. 

  2881. 		if rules['autotocwithbars']:           # TOC between bars
    2882. 

  2882. 			para = TAGS['paragraphOpen']+TAGS['paragraphClose']
    2883. 

  2883. 			bar  = regex['x'].sub('-'*72,TAGS['bar1'])
    2884. 

  2884. 			tocbar = [para, bar, para]
    2885. 

  2885. 			ret = tocbar + ret + tocbar
    2886. 

  2886. 		if rules['blankendautotoc']:           # blank line after TOC
    2887. 

  2887. 			ret.append('')
    2888. 

  2888. 		if rules['autotocnewpagebefore']:      # page break before TOC
    2889. 

  2889. 			ret.insert(0,TAGS['pageBreak'])
    2890. 

  2890. 		if rules['autotocnewpageafter']:       # page break after TOC
    2891. 

  2891. 			ret.append(TAGS['pageBreak'])
    2892. 

  2892. 	return ret
    2893. 

  2893. 

  2894. 

  2895. def doHeader(headers, config):
    2896. 

  2896. 	if not config['headers']: return []
    2897. 

  2897. 	if not headers: headers = ['','','']
    2898. 

  2898. 	target = config['target']
    2899. 

  2899. 	if not HEADER_TEMPLATE.has_key(target):
    2900. 

  2900. 		Error("doheader: Unknow target '%s'"%target)
    2901. 

  2901. 	
    2902. 

  2902. 	if target in ['html','xhtml'] and config.get('css-sugar'):
    2903. 

  2903. 		template = string.split(HEADER_TEMPLATE[target+'css'], '\n')
    2904. 

  2904. 	else:
    2905. 

  2905. 		template = string.split(HEADER_TEMPLATE[target], '\n')
    2906. 

  2906. 	
    2907. 

  2907. 	head_data = {'STYLE':'', 'ENCODING':''}
    2908. 

  2908. 	for key in head_data.keys():
    2909. 

  2909. 		val = config.get(string.lower(key))
    2910. 

  2910. 		if key == 'ENCODING': val = get_encoding_string(val, target)
    2911. 

  2911. 		head_data[key] = val
    2912. 

  2912. 	# parse header contents
    2913. 

  2913. 	for i in 0,1,2:
    2914. 

  2914. 		# expand macros
    2915. 

  2915. 		contents = MacroMaster(config=config).expand(headers[i])
    2916. 

  2916. 		# Escapes - on tex, just do it if any \tag{} present
    2917. 

  2917. 		if target != 'tex' or \
    2918. 

  2918. 		  (target == 'tex' and re.search(r'\\\w+{', contents)):
    2919. 

  2919. 			contents = doEscape(target, contents)
    2920. 

  2920. 		
    2921. 

  2921. 		head_data['HEADER%d'%(i+1)] = contents
    2922. 

  2922. 	Debug("Header Data: %s"%head_data, 1)
    2923. 

  2923. 	# scan for empty dictionary keys
    2924. 

  2924. 	# if found, scan template lines for that key reference
    2925. 

  2925. 	# if found, remove the reference
    2926. 

  2926. 	# if there isn't any other key reference on the same line, remove it
    2927. 

  2927. 	for key in head_data.keys():
    2928. 

  2928. 		if head_data.get(key): continue
    2929. 

  2929. 		for line in template:
    2930. 

  2930. 			if string.count(line, '%%(%s)s'%key):
    2931. 

  2931. 				sline = string.replace(line, '%%(%s)s'%key, '')
    2932. 

  2932. 				if not re.search(r'%\([A-Z0-9]+\)s', sline):
    2933. 

  2933. 					template.remove(line)
    2934. 

  2934. 	# populate template with data
    2935. 

  2935. 	template = string.join(template, '\n') % head_data
    2936. 

  2936. 	
    2937. 

  2937. 	return string.split(template, '\n')
    2938. 

  2938. 

  2939. def doCommentLine(txt):
    2940. 

  2940. 	# the -- string ends a (h|sg|xht)ml comment :(
    2941. 

  2941. 	txt = maskEscapeChar(txt)
    2942. 

  2942. 	if string.count(TAGS['comment'], '--') and \
    2943. 

  2943. 	   string.count(txt, '--'):
    2944. 

  2944. 		txt = re.sub('-(?=-)', r'-\\', txt)
    2945. 

  2945. 	
    2946. 

  2946. 	if TAGS['comment']:
    2947. 

  2947. 		return regex['x'].sub(txt, TAGS['comment'])
    2948. 

  2948. 	return ''
    2949. 

  2949. 

  2950. def doFooter(config):
    2951. 

  2951. 	if not config['headers']: return []
    2952. 

  2952. 	ret = []
    2953. 

  2953. 	target = config['target']
    2954. 

  2954. 	cmdline = config['realcmdline']
    2955. 

  2955. 	typename = target
    2956. 

  2956. 	if target == 'tex': typename = 'LaTeX2e'
    2957. 

  2957. 	ppgd = '%s code generated by %s %s (%s)'%(
    2958. 

  2958. 	        typename,my_name,my_version,my_url)
    2959. 

  2959. 	cmdline = 'cmdline: %s %s'%(my_name, string.join(cmdline, ' '))
    2960. 

  2960. 	ret.append('\n'+doCommentLine(ppgd))
    2961. 

  2961. 	ret.append(doCommentLine(cmdline))
    2962. 

  2962. 	ret.append(TAGS['EOD'])
    2963. 

  2963. 	return ret
    2964. 

  2964. 

  2965. def doEscape(target,txt):
    2966. 

  2966. 	"Target-specific special escapes. Apply *before* insert any tag."
    2967. 

  2967. 	if target in ['html','sgml','xhtml']:
    2968. 

  2968. 		txt = re.sub('&','&amp;',txt)
    2969. 

  2969. 		txt = re.sub('<','&lt;',txt)
    2970. 

  2970. 		txt = re.sub('>','&gt;',txt)
    2971. 

  2971. 		if target == 'sgml':
    2972. 

  2972. 			txt = re.sub('\xff','&yuml;',txt)  # "+y
    2973. 

  2973. 	elif target == 'pm6':
    2974. 

  2974. 		txt = re.sub('<','<\#60>',txt)
    2975. 

  2975. 	elif target == 'mgp':
    2976. 

  2976. 		txt = re.sub('^%',' %',txt)  # add leading blank to avoid parse
    2977. 

  2977. 	elif target == 'man':
    2978. 

  2978. 		txt = re.sub("^([.'])", '\\&\\1',txt)           # command ID
    2979. 

  2979. 		txt = string.replace(txt,ESCCHAR, ESCCHAR+'e')  # \e
    2980. 

  2980. 	elif target == 'tex':
    2981. 

  2981. 		# mark literal \ to be changed to $\backslash$ later
    2982. 

  2982. 		txt = string.replace( txt, ESCCHAR, '@@LaTeX-escaping-SUX@@')
    2983. 

  2983. 		txt = re.sub('([#$&%{}])', ESCCHAR+r'\1'  , txt)  # \%
    2984. 

  2984. 		txt = re.sub('([~^])'    , ESCCHAR+r'\1{}', txt)  # \~{}
    2985. 

  2985. 		txt = re.sub('([<|>])'   ,         r'$\1$', txt)  # $>$
    2986. 

  2986. 		txt = string.replace(txt, '@@LaTeX-escaping-SUX@@',
    2987. 

  2987. 		                     maskEscapeChar(r'$\backslash$'))
    2988. 

  2988. 		# TIP the _ is escaped at the end
    2989. 

  2989. 	return txt
    2990. 

  2990. 

  2991. # TODO man: where - really needs to be escaped?
    2992. 

  2992. def doFinalEscape(target, txt):
    2993. 

  2993. 	"Last escapes of each line"
    2994. 

  2994. 	if   target == 'pm6' : txt = string.replace(txt,ESCCHAR+'<',r'<\#92><')
    2995. 

  2995. 	elif target == 'man' : txt = string.replace(txt, '-', r'\-')
    2996. 

  2996. 	elif target == 'tex' : txt = string.replace(txt, '_', r'\_')
    2997. 

  2997. 	elif target == 'sgml': txt = string.replace(txt, '[', '&lsqb;')
    2998. 

  2998. 	return txt
    2999. 

  2999. 

  3000. def EscapeCharHandler(action, data):
    3001. 

  3001. 	"Mask/Unmask the Escape Char on the given string"
    3002. 

  3002. 	if not string.strip(data): return data
    3003. 

  3003. 	if action not in ['mask','unmask']:
    3004. 

  3004. 		Error("EscapeCharHandler: Invalid action '%s'"%action)
    3005. 

  3005. 	if action == 'mask': return string.replace(data,'\\',ESCCHAR)
    3006. 

  3006. 	else:                return string.replace(data,ESCCHAR,'\\')
    3007. 

  3007. 

  3008. def maskEscapeChar(data):
    3009. 

  3009. 	"Replace any Escape Char \ with a text mask (Input: str or list)"
    3010. 

  3010. 	if type(data) == type([]):
    3011. 

  3011. 		return map(lambda x: EscapeCharHandler('mask', x), data)
    3012. 

  3012. 	return EscapeCharHandler('mask',data)
    3013. 

  3013. 

  3014. def unmaskEscapeChar(data):
    3015. 

  3015. 	"Undo the Escape char \ masking (Input: str or list)"
    3016. 

  3016. 	if type(data) == type([]):
    3017. 

  3017. 		return map(lambda x: EscapeCharHandler('unmask', x), data)
    3018. 

  3018. 	return EscapeCharHandler('unmask',data)
    3019. 

  3019. 

  3020. def addLineBreaks(list):
    3021. 

  3021. 	"use LB to respect sys.platform"
    3022. 

  3022. 	ret = []
    3023. 

  3023. 	for line in list:
    3024. 

  3024. 		line = string.replace(line,'\n',LB)  # embedded \n's
    3025. 

  3025. 		ret.append(line+LB)                  # add final line break
    3026. 

  3026. 	return ret
    3027. 

  3027. 

  3028. def compile_filters(filters, errmsg='Filter'):
    3029. 

  3029. 	if filters:
    3030. 

  3030. 		for i in range(len(filters)):
    3031. 

  3031. 			patt,repl = filters[i]
    3032. 

  3032. 			try: rgx = re.compile(patt)
    3033. 

  3033. 			except: Error("%s: '%s'"%(errmsg, patt))
    3034. 

  3034. 			filters[i] = (rgx,repl)
    3035. 

  3035. 	return filters
    3036. 

  3036. 

  3037. def enclose_me(tagname, txt):
    3038. 

  3038. 	return TAGS.get(tagname+'Open') + txt + TAGS.get(tagname+'Close')
    3039. 

  3039. 

  3040. def beautify_me(name, line):
    3041. 

  3041. 	"where name is: bold, italic or underline"
    3042. 

  3042. 	name  = 'font%s' % string.capitalize(name)
    3043. 

  3043. 	open  = TAGS['%sOpen'%name]
    3044. 

  3044. 	close = TAGS['%sClose'%name]
    3045. 

  3045. 	txt = r'%s\1%s'%(open, close)
    3046. 

  3046. 	line = regex[name].sub(txt,line)
    3047. 

  3047. 	return line
    3048. 

  3048. 

  3049. def get_tagged_link(label, url):
    3050. 

  3050. 	ret = ''
    3051. 

  3051. 	target = CONF['target']
    3052. 

  3052. 	image_re = regex['img']
    3053. 

  3053. 	
    3054. 

  3054. 	# set link type
    3055. 

  3055. 	if regex['email'].match(url):
    3056. 

  3056. 		linktype = 'email'
    3057. 

  3057. 	else:
    3058. 

  3058. 		linktype = 'url';
    3059. 

  3059. 	
    3060. 

  3060. 	# escape specials from TEXT parts
    3061. 

  3061. 	label = doEscape(target,label)
    3062. 

  3062. 	
    3063. 

  3063. 	# escape specials from link URL
    3064. 

  3064. 	if rules['linkable'] and rules['escapeurl']:
    3065. 

  3065. 		url = doEscape(target, url)
    3066. 

  3066. 	
    3067. 

  3067. 	# if not linkable, the URL is plain text, that needs escape
    3068. 

  3068. 	if not rules['linkable']:
    3069. 

  3069. 		if target == 'tex':
    3070. 

  3070. 			url = re.sub('^#', '\#', url) # ugly, but compile
    3071. 

  3071. 		else:
    3072. 

  3072. 			url = doEscape(target,url)
    3073. 

  3073. 	
    3074. 

  3074. 	# adding protocol to guessed link
    3075. 

  3075. 	guessurl = ''
    3076. 

  3076. 	if linktype == 'url' and \
    3077. 

  3077. 	   re.match(regex['_urlskel']['guess'], url):
    3078. 

  3078. 		if url[0] == 'w': guessurl = 'http://' +url
    3079. 

  3079. 		else            : guessurl =  'ftp://' +url
    3080. 

  3080. 		
    3081. 

  3081. 		# not link aware targets -> protocol is useless
    3082. 

  3082. 		if not rules['linkable']: guessurl = ''
    3083. 

  3083. 	
    3084. 

  3084. 	# simple link (not guessed)
    3085. 

  3085. 	if not label and not guessurl:
    3086. 

  3086. 		if CONF['mask-email'] and linktype == 'email':
    3087. 

  3087. 			# do the email mask feature (no TAGs, just text)
    3088. 

  3088. 			url = string.replace(url,'@',' (a) ')
    3089. 

  3089. 			url = string.replace(url,'.',' ')
    3090. 

  3090. 			url = "<%s>" % url
    3091. 

  3091. 			if rules['linkable']: url = doEscape(target, url)
    3092. 

  3092. 			ret = url
    3093. 

  3093. 		else:
    3094. 

  3094. 			# just add link data to tag
    3095. 

  3095. 			tag = TAGS[linktype]
    3096. 

  3096. 			ret = regex['x'].sub(url,tag)
    3097. 

  3097. 	
    3098. 

  3098. 	# named link or guessed simple link
    3099. 

  3099. 	else:
    3100. 

  3100. 		# adjusts for guessed link
    3101. 

  3101. 		if not label: label = url         # no   protocol
    3102. 

  3102. 		if guessurl : url   = guessurl    # with protocol
    3103. 

  3103. 		
    3104. 

  3104. 		# image inside link!
    3105. 

  3105. 		if image_re.match(label):
    3106. 

  3106. 			if rules['imglinkable']:  # get image tag
    3107. 

  3107. 				label = parse_images(label)
    3108. 

  3108. 			else:                     #  img@link !supported
    3109. 

  3109. 				label = "(%s)"%image_re.match(label).group(1)
    3110. 

  3110. 		
    3111. 

  3111. 		# putting data on the right appearance order
    3112. 

  3112. 		if rules['linkable']:
    3113. 

  3113. 			urlorder = [url, label]   # link before label
    3114. 

  3114. 		else:
    3115. 

  3115. 			urlorder = [label, url]   # label before link
    3116. 

  3116. 		
    3117. 

  3117. 		# add link data to tag (replace \a's)
    3118. 

  3118. 		ret = TAGS["%sMark"%linktype]
    3119. 

  3119. 		for data in urlorder:
    3120. 

  3120. 			ret = regex['x'].sub(data,ret,1)
    3121. 

  3121. 	
    3122. 

  3122. 	return ret
    3123. 

  3123. 

  3124. 

  3125. def parse_deflist_term(line):
    3126. 

  3126. 	"Extract and parse definition list term contents"
    3127. 

  3127. 	img_re = regex['img']
    3128. 

  3128. 	term   = regex['deflist'].search(line).group(3)
    3129. 

  3129. 	
    3130. 

  3130. 	# mask image inside term as (image.jpg), where not supported
    3131. 

  3131. 	if not rules['imgasdefterm'] and img_re.search(term):
    3132. 

  3132. 		while img_re.search(term):
    3133. 

  3133. 			imgfile = img_re.search(term).group(1)
    3134. 

  3134. 			term = img_re.sub('(%s)'%imgfile, term, 1)
    3135. 

  3135. 	
    3136. 

  3136. 	#TODO tex: escape ] on term. \], \rbrack{} and \verb!]! don't work :(
    3137. 

  3137. 	return term
    3138. 

  3138. 

  3139. 

  3140. def get_tagged_bar(line):
    3141. 

  3141. 	m = regex['bar'].search(line)
    3142. 

  3142. 	if not m: return line
    3143. 

  3143. 	txt = m.group(2)
    3144. 

  3144. 	
    3145. 

  3145. 	# set bar type
    3146. 

  3146. 	if txt[0] == '=': bar = TAGS['bar2']
    3147. 

  3147. 	else            : bar = TAGS['bar1']
    3148. 

  3148. 	
    3149. 

  3149. 	# to avoid comment tag confusion like <!-- ------ -->
    3150. 

  3150. 	if string.count(TAGS['comment'], '--'):
    3151. 

  3151. 		txt = string.replace(txt,'--','__')
    3152. 

  3152. 	
    3153. 

  3153. 	# tag line
    3154. 

  3154. 	return regex['x'].sub(txt, bar)
    3155. 

  3155. 

  3156. 

  3157. def get_image_align(line):
    3158. 

  3158. 	"Return the image (first found) align for the given line"
    3159. 

  3159. 	
    3160. 

  3160. 	# first clear marks that can mess align detection
    3161. 

  3161. 	line = re.sub(SEPARATOR+'$', '', line)  # remove deflist sep
    3162. 

  3162. 	line = re.sub('^'+SEPARATOR, '', line)  # remove list sep
    3163. 

  3163. 	line = re.sub('^[\t]+'     , '', line)  # remove quote mark
    3164. 

  3164. 	
    3165. 

  3165. 	# get image position on the line
    3166. 

  3166. 	m = regex['img'].search(line)
    3167. 

  3167. 	ini = m.start() ; head = 0
    3168. 

  3168. 	end = m.end()   ; tail = len(line)
    3169. 

  3169. 	
    3170. 

  3170. 	# the align detection algorithm
    3171. 

  3171. 	if   ini == head and end != tail: align = 'left'   # ^img + text$
    3172. 

  3172. 	elif ini != head and end == tail: align = 'right'  # ^text + img$
    3173. 

  3173. 	else                            : align = 'middle' # default align
    3174. 

  3174. 	
    3175. 

  3175. 	# some special cases
    3176. 

  3176. 	if BLOCK.isblock('table'): align = 'middle'    # ignore when table
    3177. 

  3177. 	if TARGET == 'mgp' and align == 'middle': align = 'center'
    3178. 

  3178. 	
    3179. 

  3179. 	return align
    3180. 

  3180. 

  3181. 

  3182. # reference: http://www.iana.org/assignments/character-sets
    3183. 

  3183. # http://www.drclue.net/F1.cgi/HTML/META/META.html
    3184. 

  3184. def get_encoding_string(enc, target):
    3185. 

  3185. 	if not enc: return ''
    3186. 

  3186. 	# target specific translation table
    3187. 

  3187. 	translate = {
    3188. 

  3188. 	'tex': {
    3189. 

  3189. 	  # missing: ansinew , applemac , cp437 , cp437de , cp865
    3190. 

  3190. 	  'us-ascii'    : 'ascii',
    3191. 

  3191. 	  'windows-1250': 'cp1250',
    3192. 

  3192. 	  'windows-1252': 'cp1252',
    3193. 

  3193. 	  'ibm850'      : 'cp850',
    3194. 

  3194. 	  'ibm852'      : 'cp852',
    3195. 

  3195. 	  'iso-8859-1'  : 'latin1',
    3196. 

  3196. 	  'iso-8859-2'  : 'latin2',
    3197. 

  3197. 	  'iso-8859-3'  : 'latin3',
    3198. 

  3198. 	  'iso-8859-4'  : 'latin4',
    3199. 

  3199. 	  'iso-8859-5'  : 'latin5',
    3200. 

  3200. 	  'iso-8859-9'  : 'latin9',
    3201. 

  3201. 	  'koi8-r'      : 'koi8-r'
    3202. 

  3202. 	  }
    3203. 

  3203. 	}
    3204. 

  3204. 	# normalization
    3205. 

  3205. 	enc = re.sub('(?i)(us[-_]?)?ascii|us|ibm367','us-ascii'  , enc)
    3206. 

  3206. 	enc = re.sub('(?i)(ibm|cp)?85([02])'        ,'ibm85\\2'  , enc)
    3207. 

  3207. 	enc = re.sub('(?i)(iso[_-]?)?8859[_-]?'     ,'iso-8859-' , enc)
    3208. 

  3208. 	enc = re.sub('iso-8859-($|[^1-9]).*'        ,'iso-8859-1', enc)
    3209. 

  3209. 	# apply translation table
    3210. 

  3210. 	try: enc = translate[target][string.lower(enc)]
    3211. 

  3211. 	except: pass
    3212. 

  3212. 	return enc
    3213. 

  3213. 

  3214. 

  3215. ##############################################################################
    3216. 

  3216. ##MerryChristmas,IdontwanttofighttonightwithyouImissyourbodyandIneedyourlove##
    3217. 

  3217. ##############################################################################
    3218. 

  3218. 

  3219. 

  3220. def process_source_file(file, noconf=0):
    3221. 

  3221. 	"""
    3222. 

  3222. 	Find and Join all the configuration available for a source file.
    3223. 

  3223. 	No sanity checkings are done on this step.
    3224. 

  3224. 	It also extracts the source document parts into separate holders.
    3225. 

  3225. 	
    3226. 

  3226. 	The config scan order is:
    3227. 

  3227. 	   1. The user configuration file (i.e. $HOME/.txt2tagsrc)
    3228. 

  3228. 	   2. The source document's CONF area
    3229. 

  3229. 	   3. The command line options
    3230. 

  3230. 

  3231. 	The return data is a tuple of two items:
    3232. 

  3232. 	   1. The parsed config dictionary
    3233. 

  3233. 	   2. The document's parts, as a (head, conf, body) tuple
    3234. 

  3234. 	
    3235. 

  3235. 	All the conversion process will be based on the data and
    3236. 

  3236. 	configuration returned by this function.
    3237. 

  3237. 	The source files is readed on this step only.
    3238. 

  3238. 	"""
    3239. 

  3239. 	source = SourceDocument(file)
    3240. 

  3240. 	head, conf, body = source.split()
    3241. 

  3241. 	Message(_("Source document contents stored"),2)
    3242. 

  3242. 	if not noconf:
    3243. 

  3243. 		# read document config
    3244. 

  3244. 		source_raw = source.get_raw_config()
    3245. 

  3245. 		# join all the config directives found, then parse it
    3246. 

  3246. 		full_raw = RC_RAW + source_raw + CMDLINE_RAW
    3247. 

  3247. 		Message(_("Parsing and saving all config found (%03d items)")%(
    3248. 

  3248. 		        len(full_raw)),1)
    3249. 

  3249. 		full_parsed = ConfigMaster(full_raw).parse()
    3250. 

  3250. 		# add manually the filemane to the conf dic
    3251. 

  3251. 		full_parsed['sourcefile'] = file
    3252. 

  3252. 		# maybe should we dump the config found?
    3253. 

  3253. 		if full_parsed.get('dump-config'):
    3254. 

  3254. 			dumpConfig(source_raw, full_parsed)
    3255. 

  3255. 			sys.exit()
    3256. 

  3256. 		# okay, all done
    3257. 

  3257. 		Debug("FULL config for this file: %s"%full_parsed, 1)
    3258. 

  3258. 	else:
    3259. 

  3259. 		full_parsed = {}
    3260. 

  3260. 	return full_parsed, (head,conf,body)
    3261. 

  3261. 

  3262. def get_infiles_config(infiles):
    3263. 

  3263. 	"""
    3264. 

  3264. 	Find and Join into a single list, all configuration available
    3265. 

  3265. 	for each input file. This function is supposed to be the very
    3266. 

  3266. 	first one to be called, before any processing.
    3267. 

  3267. 	"""
    3268. 

  3268. 	ret = []
    3269. 

  3269. 	if not infiles: return []
    3270. 

  3270. 	for infile in infiles:
    3271. 

  3271. 		ret.append((process_source_file(infile)))
    3272. 

  3272. 	return ret
    3273. 

  3273. 

  3274. def convert_this_files(configs):
    3275. 

  3275. 	global CONF
    3276. 

  3276. 	for myconf,doc in configs:                 # multifile support
    3277. 

  3277. 		target_head = []
    3278. 

  3278. 		target_toc  = []
    3279. 

  3279. 		target_body = []
    3280. 

  3280. 		target_foot = []
    3281. 

  3281. 		source_head, source_conf, source_body = doc
    3282. 

  3282. 		myconf = ConfigMaster().sanity(myconf)
    3283. 

  3283. 		# compose the target file Headers
    3284. 

  3284. 		#TODO escape line before?
    3285. 

  3285. 		#TODO see exceptions by tex and mgp
    3286. 

  3286. 		Message(_("Composing target Headers"),1)
    3287. 

  3287. 		target_head = doHeader(source_head, myconf)
    3288. 

  3288. 		# parse the full marked body into tagged target
    3289. 

  3289. 		first_body_line = (len(source_head) or 1)+ len(source_conf) + 1
    3290. 

  3290. 		Message(_("Composing target Body"),1)
    3291. 

  3291. 		target_body, marked_toc = convert(source_body, myconf,
    3292. 

  3292. 		                          firstlinenr=first_body_line)
    3293. 

  3293. 		# make TOC (if needed)
    3294. 

  3294. 		Message(_("Composing target TOC"),1)
    3295. 

  3295. 		tagged_toc  = toc_tagger(marked_toc, myconf)
    3296. 

  3296. 		target_toc  = toc_formatter(tagged_toc, myconf)
    3297. 

  3297. 		target_body = toc_inside_body(target_body, target_toc, myconf)
    3298. 

  3298. 		if not AUTOTOC and not myconf['toc-only']: target_toc = []
    3299. 

  3299. 		# compose the target file Footer
    3300. 

  3300. 		Message(_("Composing target Footer"),1)
    3301. 

  3301. 		target_foot = doFooter(myconf)
    3302. 

  3302. 		# finally, we have our document
    3303. 

  3303. 		outlist = target_head + target_toc + target_body + target_foot
    3304. 

  3304. 		# if on GUI, abort before finish_him
    3305. 

  3305. 		# else, write results to file or STDOUT
    3306. 

  3306. 		if GUI:
    3307. 

  3307. 			return outlist, myconf
    3308. 

  3308. 		else:
    3309. 

  3309. 			Message(_("Saving results to the output file"),1)
    3310. 

  3310. 			finish_him(outlist, myconf)
    3311. 

  3311. 

  3312. 

  3313. def parse_images(line):
    3314. 

  3314. 	"Tag all images found"
    3315. 

  3315. 	while regex['img'].search(line) and TAGS['img'] != '[\a]':
    3316. 

  3316. 		txt = regex['img'].search(line).group(1)
    3317. 

  3317. 		tag = TAGS['img']
    3318. 

  3318. 		
    3319. 

  3319. 		# HTML, XHTML and mgp!
    3320. 

  3320. 		if rules['imgalignable']:
    3321. 

  3321. 			align = get_image_align(line)
    3322. 

  3322. 			# add align on tag
    3323. 

  3323. 			tag = regex['_imgAlign'].sub(align, tag, 1)
    3324. 

  3324. 			# dirty fix to allow centered solo images
    3325. 

  3325. 			if align == 'middle' and TARGET in ['html','xhtml']:
    3326. 

  3326. 				rest = regex['img'].sub('',line,1)
    3327. 

  3327. 				if re.match('^\s+$', rest):
    3328. 

  3328. 					tag = "<center>%s</center>" %tag
    3329. 

  3329. 		
    3330. 

  3330. 		if TARGET == 'tex': tag = re.sub(r'\\b',r'\\\\b',tag)
    3331. 

  3331. 		line = regex['img'].sub(tag,line,1)
    3332. 

  3332. 		line = regex['x'].sub(txt,line,1)
    3333. 

  3333. 	return line
    3334. 

  3334. 

  3335. 

  3336. def add_inline_tags(line):
    3337. 

  3337. 	# beautifiers
    3338. 

  3338. 	for beauti in ['Bold', 'Italic', 'Underline']:
    3339. 

  3339. 		if regex['font%s'%beauti].search(line):
    3340. 

  3340. 			line = beautify_me(beauti, line)
    3341. 

  3341. 	
    3342. 

  3342. 	line = parse_images(line)
    3343. 

  3343. 	return line
    3344. 

  3344. 

  3345. 

  3346. def get_include_contents(file, path=''):
    3347. 

  3347. 	"Parses %!include: value and extract file contents"
    3348. 

  3348. 	ids = {'`':'verb', '"':'raw', "'":'passthru' }
    3349. 

  3349. 	id = 't2t'
    3350. 

  3350. 	# set include type and remove identifier marks
    3351. 

  3351. 	mark = file[0]
    3352. 

  3352. 	if mark in ids.keys():
    3353. 

  3353. 		if file[:2] == file[-2:] == mark*2:
    3354. 

  3354. 			id = ids[mark]     # set type
    3355. 

  3355. 			file = file[2:-2]  # remove marks
    3356. 

  3356. 	# handle remote dir execution
    3357. 

  3357. 	filepath = os.path.join(path, file)
    3358. 

  3358. 	# read included file contents
    3359. 

  3359. 	lines = Readfile(filepath, remove_linebreaks=1)
    3360. 

  3360. 	# default txt2tags marked text, just BODY matters
    3361. 

  3361. 	if id == 't2t':
    3362. 

  3362. 		lines = get_file_body(filepath)
    3363. 

  3363. 		lines.insert(0, '%%INCLUDED(%s) starts here: %s'%(id,file))
    3364. 

  3364. 		lines.append('%%INCLUDED(%s) ends here: %s'%(id,file))
    3365. 

  3365. 	return id, lines
    3366. 

  3366. 

  3367. 

  3368. def set_global_config(config):
    3369. 

  3369. 	global CONF, TAGS, regex, rules, TARGET
    3370. 

  3370. 	CONF   = config
    3371. 

  3371. 	TAGS   = getTags(CONF)
    3372. 

  3372. 	rules  = getRules(CONF)
    3373. 

  3373. 	regex  = getRegexes()
    3374. 

  3374. 	TARGET = config['target']  # save for buggy functions that need global
    3375. 

  3375. 

  3376. 

  3377. def convert(bodylines, config, firstlinenr=1):
    3378. 

  3378. 	global BLOCK
    3379. 

  3379. 	
    3380. 

  3380. 	set_global_config(config)
    3381. 

  3381. 	
    3382. 

  3382. 	target = config['target']
    3383. 

  3383. 	BLOCK = BlockMaster()
    3384. 

  3384. 	MASK  =  MaskMaster()
    3385. 

  3385. 	TITLE = TitleMaster()
    3386. 

  3386. 	
    3387. 

  3387. 	ret = []
    3388. 

  3388. 	f_lastwasblank = 0
    3389. 

  3389. 	
    3390. 

  3390. 	# compiling all PreProc regexes
    3391. 

  3391. 	pre_filter = compile_filters(
    3392. 

  3392. 		CONF['preproc'], _('Invalid PreProc filter regex'))
    3393. 

  3393. 	
    3394. 

  3394. 	# let's mark it up!
    3395. 

  3395. 	linenr = firstlinenr-1
    3396. 

  3396. 	lineref = 0
    3397. 

  3397. 	while lineref < len(bodylines):
    3398. 

  3398. 		# defaults
    3399. 

  3399. 		MASK.reset()
    3400. 

  3400. 		results_box = ''
    3401. 

  3401. 		
    3402. 

  3402. 		untouchedline = bodylines[lineref]
    3403. 

  3403. 		line = re.sub('[\n\r]+$','',untouchedline)   # del line break
    3404. 

  3404. 		
    3405. 

  3405. 		# apply PreProc filters
    3406. 

  3406. 		if pre_filter:
    3407. 

  3407. 			for rgx,repl in pre_filter:
    3408. 

  3408. 				line = rgx.sub(repl, line)
    3409. 

  3409. 		
    3410. 

  3410. 		line = maskEscapeChar(line)                  # protect \ char
    3411. 

  3411. 		linenr  = linenr  +1
    3412. 

  3412. 		lineref = lineref +1
    3413. 

  3413. 		
    3414. 

  3414. 		Debug(repr(line), 3, linenr)  # heavy debug: show each line
    3415. 

  3415. 		
    3416. 

  3416. 		# any NOT table line (or comment), closes an open table
    3417. 

  3417. 		if ( BLOCK.isblock('table') or
    3418. 

  3418. 		      ( BLOCK.isblock('verb') and
    3419. 

  3419. 		        BLOCK.prop('mapped') == 'table'
    3420. 

  3420. 		       )
    3421. 

  3421. 		    ) \
    3422. 

  3422. 		   and not regex['table'].search(line) \
    3423. 

  3423. 		   and not regex['comment'].search(line):
    3424. 

  3424. 			ret.extend(BLOCK.blockout())
    3425. 

  3425. 		
    3426. 

  3426. 		# any NOT quote line (or comment) closes all open quotes
    3427. 

  3427. 		if BLOCK.isblock('quote') \
    3428. 

  3428. 		   and not regex['quote'].search(line) \
    3429. 

  3429. 		   and not regex['comment'].search(line):
    3430. 

  3430. 			while BLOCK.isblock('quote'):
    3431. 

  3431. 				ret.extend(BLOCK.blockout())
    3432. 

  3432. 		
    3433. 

  3433. 		
    3434. 

  3434. 		#-------------------------[ Raw Text ]----------------------
    3435. 

  3435. 		
    3436. 

  3436. 		# we're already on a raw block
    3437. 

  3437. 		if BLOCK.block() == 'raw':
    3438. 

  3438. 		
    3439. 

  3439. 			# closing raw
    3440. 

  3440. 			if regex['blockRawClose'].search(line):
    3441. 

  3441. 				ret.extend(BLOCK.blockout())
    3442. 

  3442. 				continue
    3443. 

  3443. 			
    3444. 

  3444. 			# normal raw-inside line
    3445. 

  3445. 			BLOCK.holdadd(line)
    3446. 

  3446. 			continue
    3447. 

  3447. 		
    3448. 

  3448. 		# detecting raw block init
    3449. 

  3449. 		if regex['blockRawOpen'].search(line):
    3450. 

  3450. 			ret.extend(BLOCK.blockin('raw'))
    3451. 

  3451. 			continue
    3452. 

  3452. 		
    3453. 

  3453. 		# one line verb-formatted text
    3454. 

  3454. 		if regex['1lineRaw'].search(line):
    3455. 

  3455. 			ret.extend(BLOCK.blockin('raw'))
    3456. 

  3456. 			line = regex['1lineRaw'].sub('',line)
    3457. 

  3457. 			BLOCK.holdadd(line)
    3458. 

  3458. 			ret.extend(BLOCK.blockout())
    3459. 

  3459. 			continue
    3460. 

  3460. 		
    3461. 

  3461. 		#-----------------[ Verbatim (PRE-formatted) ]--------------
    3462. 

  3462. 		
    3463. 

  3463. 		#TIP we'll never support beautifiers inside verbatim
    3464. 

  3464. 		
    3465. 

  3465. 		# we're already on a verb block
    3466. 

  3466. 		if BLOCK.block() == 'verb':
    3467. 

  3467. 			
    3468. 

  3468. 			# closing verb
    3469. 

  3469. 			if regex['blockVerbClose'].search(line):
    3470. 

  3470. 				ret.extend(BLOCK.blockout())
    3471. 

  3471. 				continue
    3472. 

  3472. 			
    3473. 

  3473. 			# normal verb-inside line
    3474. 

  3474. 			BLOCK.holdadd(line)
    3475. 

  3475. 			continue
    3476. 

  3476. 		
    3477. 

  3477. 		# detecting verb block init
    3478. 

  3478. 		if regex['blockVerbOpen'].search(line):
    3479. 

  3479. 			ret.extend(BLOCK.blockin('verb'))
    3480. 

  3480. 			f_lastwasblank = 0
    3481. 

  3481. 			continue
    3482. 

  3482. 		
    3483. 

  3483. 		# one line verb-formatted text
    3484. 

  3484. 		if regex['1lineVerb'].search(line):
    3485. 

  3485. 			ret.extend(BLOCK.blockin('verb'))
    3486. 

  3486. 			line = regex['1lineVerb'].sub('',line)
    3487. 

  3487. 			BLOCK.holdadd(line)
    3488. 

  3488. 			ret.extend(BLOCK.blockout())
    3489. 

  3489. 			f_lastwasblank = 0
    3490. 

  3490. 			continue
    3491. 

  3491. 		
    3492. 

  3492. 		# tables are mapped to verb when target is not table-aware
    3493. 

  3493. 		if not rules['tableable'] and regex['table'].search(line):
    3494. 

  3494. 			if not BLOCK.isblock('verb'):
    3495. 

  3495. 				ret.extend(BLOCK.blockin('verb'))
    3496. 

  3496. 				BLOCK.propset('mapped', 'table')
    3497. 

  3497. 				BLOCK.holdadd(line)
    3498. 

  3498. 				continue
    3499. 

  3499. 		
    3500. 

  3500. 		#---------------------[ blank lines ]-----------------------
    3501. 

  3501. 		
    3502. 

  3502. 		if regex['blankline'].search(line):
    3503. 

  3503. 			
    3504. 

  3504. 			# close open paragraph
    3505. 

  3505. 			if BLOCK.isblock('para'):
    3506. 

  3506. 				ret.extend(BLOCK.blockout())
    3507. 

  3507. 				f_lastwasblank = 1
    3508. 

  3508. 				continue
    3509. 

  3509. 			
    3510. 

  3510. 			# close all open quotes
    3511. 

  3511. 			while BLOCK.isblock('quote'):
    3512. 

  3512. 				ret.extend(BLOCK.blockout())
    3513. 

  3513. 			
    3514. 

  3514. 			# closing all open lists
    3515. 

  3515. 			if f_lastwasblank:          # 2nd consecutive blank
    3516. 

  3516. 				if BLOCK.block()[-4:] == 'list':
    3517. 

  3517. 					BLOCK.holdaddsub('')   # helps parser
    3518. 

  3518. 				while BLOCK.depth:  # closes list (if any)
    3519. 

  3519. 					ret.extend(BLOCK.blockout())
    3520. 

  3520. 				continue            # ignore consecutive blanks
    3521. 

  3521. 			
    3522. 

  3522. 			# paragraph (if any) is wanted inside lists also
    3523. 

  3523. 			if BLOCK.block()[-4:] == 'list':
    3524. 

  3524. 				BLOCK.holdaddsub('')
    3525. 

  3525. 			else:
    3526. 

  3526. 				# html: show blank line (needs tag)
    3527. 

  3527. 				if target in ['html','xhtml']:
    3528. 

  3528. 					ret.append(TAGS['paragraphOpen']+\
    3529. 

  3529. 					           TAGS['paragraphClose'])
    3530. 

  3530. 				# otherwise we just show a blank line
    3531. 

  3531. 				else:
    3532. 

  3532. 					ret.append('')
    3533. 

  3533. 			
    3534. 

  3534. 			f_lastwasblank = 1
    3535. 

  3535. 			continue
    3536. 

  3536. 		
    3537. 

  3537. 		
    3538. 

  3538. 		#---------------------[ special ]---------------------------
    3539. 

  3539. 		
    3540. 

  3540. 		if regex['special'].search(line):
    3541. 

  3541. 			# include command
    3542. 

  3542. 			targ, key, val = ConfigLines().parse_line(
    3543. 

  3543. 			                   line, 'include', target)
    3544. 

  3544. 			if key:
    3545. 

  3545. 				Debug("Found config '%s', value '%s'"%(
    3546. 

  3546. 				       key,val),1,linenr)
    3547. 

  3547. 				
    3548. 

  3548. 				incpath = os.path.dirname(CONF['sourcefile'])
    3549. 

  3549. 				incfile = val
    3550. 

  3550. 				err = _('A file cannot include itself (loop!)')
    3551. 

  3551. 				if CONF['sourcefile'] == incfile:
    3552. 

  3552. 					Error("%s: %s"%(err,incfile))
    3553. 

  3553. 				inctype, inclines = get_include_contents(
    3554. 

  3554. 				                      incfile, incpath)
    3555. 

  3555. 				# verb, raw and passthru are easy
    3556. 

  3556. 				if inctype != 't2t':
    3557. 

  3557. 					ret.extend(BLOCK.blockin(inctype))
    3558. 

  3558. 					BLOCK.holdextend(inclines)
    3559. 

  3559. 					ret.extend(BLOCK.blockout())
    3560. 

  3560. 				else:
    3561. 

  3561. 					# insert include lines into body
    3562. 

  3562. 					#TODO del %!include command call
    3563. 

  3563. 					#TODO include maxdepth limit
    3564. 

  3564. 					bodylines = bodylines[:lineref] \
    3565. 

  3565. 					           +inclines \
    3566. 

  3566. 					           +bodylines[lineref:]
    3567. 

  3567. 				continue
    3568. 

  3568. 			else:
    3569. 

  3569. 				Debug('Bogus Special Line',1,linenr)
    3570. 

  3570. 		
    3571. 

  3571. 		#---------------------[ comments ]--------------------------
    3572. 

  3572. 		
    3573. 

  3573. 		# just skip them (if not macro)
    3574. 

  3574. 		if regex['comment'].search(line) and not \
    3575. 

  3575. 		   regex['macros'].match(line) and not \
    3576. 

  3576. 		   regex['toc'].match(line):
    3577. 

  3577. 			continue
    3578. 

  3578. 		
    3579. 

  3579. 		# valid line, reset blank status
    3580. 

  3580. 		f_lastwasblank = 0
    3581. 

  3581. 		
    3582. 

  3582. 		#---------------------[ Horizontal Bar ]--------------------
    3583. 

  3583. 		
    3584. 

  3584. 		if regex['bar'].search(line):
    3585. 

  3585. 			
    3586. 

  3586. 			# a bar closes a paragraph
    3587. 

  3587. 			if BLOCK.isblock('para'):
    3588. 

  3588. 				ret.extend(BLOCK.blockout())
    3589. 

  3589. 			
    3590. 

  3590. 			# we need to close all opened quote blocks
    3591. 

  3591. 			# if bar isn't allowed inside or if not a quote line
    3592. 

  3592. 			if BLOCK.isblock('quote'):
    3593. 

  3593. 				if not rules['barinsidequote'] or \
    3594. 

  3594. 				   not regex['quote'].search(line):
    3595. 

  3595. 					while BLOCK.isblock('quote'):
    3596. 

  3596. 						ret.extend(BLOCK.blockout())
    3597. 

  3597. 			
    3598. 

  3598. 			# quote + bar: continue processing for quoting
    3599. 

  3599. 			if rules['barinsidequote'] and \
    3600. 

  3600. 			   regex['quote'].search(line):
    3601. 

  3601. 				pass
    3602. 

  3602. 			
    3603. 

  3603. 			# just quote: save tagged line and we're done
    3604. 

  3604. 			else:
    3605. 

  3605. 				line = get_tagged_bar(line)
    3606. 

  3606. 				if BLOCK.block()[-4:] == 'list':
    3607. 

  3607. 					BLOCK.holdaddsub(line)
    3608. 

  3608. 				elif BLOCK.block():
    3609. 

  3609. 					BLOCK.holdadd(line)
    3610. 

  3610. 				else:
    3611. 

  3611. 					ret.append(line)
    3612. 

  3612. 				continue
    3613. 

  3613. 		
    3614. 

  3614. 		#---------------------[ Title ]-----------------------------
    3615. 

  3615. 		
    3616. 

  3616. 		#TODO set next blank and set f_lastwasblank or f_lasttitle
    3617. 

  3617. 		if (regex['title'].search(line) or
    3618. 

  3618. 		    regex['numtitle'].search(line)) and \
    3619. 

  3619. 		    BLOCK.block()[-4:] != 'list':
    3620. 

  3620. 			
    3621. 

  3621. 			# a title closes a paragraph
    3622. 

  3622. 			if BLOCK.isblock('para'):
    3623. 

  3623. 				ret.extend(BLOCK.blockout())
    3624. 

  3624. 			
    3625. 

  3625. 			TITLE.add(line)
    3626. 

  3626. 			ret.extend(TITLE.get())
    3627. 

  3627. 			
    3628. 

  3628. 			f_lastwasblank = 1
    3629. 

  3629. 			continue
    3630. 

  3630. 		
    3631. 

  3631. 		#---------------------[ %%toc ]-----------------------
    3632. 

  3632. 		
    3633. 

  3633. 		# %%toc line closes paragraph
    3634. 

  3634. 		if BLOCK.block() == 'para' and regex['toc'].search(line):
    3635. 

  3635. 			ret.extend(BLOCK.blockout())
    3636. 

  3636. 		
    3637. 

  3637. 		#---------------------[ apply masks ]-----------------------
    3638. 

  3638. 		
    3639. 

  3639. 		line = MASK.mask(line)
    3640. 

  3640. 		
    3641. 

  3641. 		#XXX from here, only block-inside lines will pass
    3642. 

  3642. 		
    3643. 

  3643. 		#---------------------[ Quote ]-----------------------------
    3644. 

  3644. 		
    3645. 

  3645. 		if regex['quote'].search(line):
    3646. 

  3646. 			
    3647. 

  3647. 			# store number of leading TABS
    3648. 

  3648. 			quotedepth = len(regex['quote'].search(line).group(0))
    3649. 

  3649. 			
    3650. 

  3650. 			# SGML doesn't support nested quotes
    3651. 

  3651. 			if rules['quotenotnested']: quotedepth = 1
    3652. 

  3652. 			
    3653. 

  3653. 			# new quote
    3654. 

  3654. 			if not BLOCK.isblock('quote'):
    3655. 

  3655. 				ret.extend(BLOCK.blockin('quote'))
    3656. 

  3656. 			
    3657. 

  3657. 			# new subquotes
    3658. 

  3658. 			while BLOCK.depth < quotedepth:
    3659. 

  3659. 				BLOCK.blockin('quote')
    3660. 

  3660. 			
    3661. 

  3661. 			# closing quotes
    3662. 

  3662. 			while quotedepth < BLOCK.depth:
    3663. 

  3663. 				ret.extend(BLOCK.blockout())
    3664. 

  3664. 		
    3665. 

  3665. 		#---------------------[ Lists ]-----------------------------
    3666. 

  3666. 		
    3667. 

  3667. 		# an empty item also closes the current list
    3668. 

  3668. 		if BLOCK.block()[-4:] == 'list':
    3669. 

  3669. 			m = regex['listclose'].match(line)
    3670. 

  3670. 			if m:
    3671. 

  3671. 				listindent = m.group(1)
    3672. 

  3672. 				listtype = m.group(2)
    3673. 

  3673. 				currlisttype = BLOCK.prop('type')
    3674. 

  3674. 				currlistindent = BLOCK.prop('indent')
    3675. 

  3675. 				if listindent == currlistindent and \
    3676. 

  3676. 				   listtype == currlisttype:
    3677. 

  3677. 					ret.extend(BLOCK.blockout())
    3678. 

  3678. 					continue
    3679. 

  3679. 		
    3680. 

  3680. 		if   regex['list'].search(line) or \
    3681. 

  3681. 		  regex['numlist'].search(line) or \
    3682. 

  3682. 		  regex['deflist'].search(line):
    3683. 

  3683. 			
    3684. 

  3684. 			listindent = BLOCK.prop('indent')
    3685. 

  3685. 			listids = string.join(LISTNAMES.keys(), '')
    3686. 

  3686. 			m = re.match('^( *)([%s]) '%listids, line)
    3687. 

  3687. 			listitemindent = m.group(1)
    3688. 

  3688. 			listtype = m.group(2)
    3689. 

  3689. 			listname = LISTNAMES[listtype]
    3690. 

  3690. 			results_box = BLOCK.holdadd
    3691. 

  3691. 			
    3692. 

  3692. 			# del list ID (and separate term from definition)
    3693. 

  3693. 			if listname == 'deflist':
    3694. 

  3694. 				term = parse_deflist_term(line)
    3695. 

  3695. 				line = regex['deflist'].sub(term+SEPARATOR,line)
    3696. 

  3696. 			else:
    3697. 

  3697. 				line = regex[listname].sub(SEPARATOR,line)
    3698. 

  3698. 			
    3699. 

  3699. 			# don't cross depth limit
    3700. 

  3700. 			maxdepth = rules['listmaxdepth']
    3701. 

  3701. 			if maxdepth and BLOCK.depth == maxdepth:
    3702. 

  3702. 				if len(listitemindent) > len(listindent):
    3703. 

  3703. 					listitemindent = listindent
    3704. 

  3704. 			
    3705. 

  3705. 			# open mother list or sublist
    3706. 

  3706. 			if BLOCK.block()[-4:] != 'list' or \
    3707. 

  3707. 			   len(listitemindent) > len(listindent):
    3708. 

  3708. 				ret.extend(BLOCK.blockin(listname))
    3709. 

  3709. 				BLOCK.propset('indent',listitemindent)
    3710. 

  3710. 				BLOCK.propset('type',listtype)
    3711. 

  3711. 			
    3712. 

  3712. 			# closing sublists
    3713. 

  3713. 			while len(listitemindent) < len(BLOCK.prop('indent')):
    3714. 

  3714. 				ret.extend(BLOCK.blockout())
    3715. 

  3715. 			
    3716. 

  3716. 			# o-oh, sublist before list ("\n\n  - foo\n- foo")
    3717. 

  3717. 			# fix: close sublist (as mother), open another list
    3718. 

  3718. 			if BLOCK.block()[-4:] != 'list':
    3719. 

  3719. 				ret.extend(BLOCK.blockin(listname))
    3720. 

  3720. 				BLOCK.propset('indent',listitemindent)
    3721. 

  3721. 				BLOCK.propset('type',listtype)
    3722. 

  3722. 		
    3723. 

  3723. 		#---------------------[ Table ]-----------------------------
    3724. 

  3724. 		
    3725. 

  3725. 		#TODO escape undesired format inside table
    3726. 

  3726. 		#TODO add pm6 target
    3727. 

  3727. 		if regex['table'].search(line):
    3728. 

  3728. 			
    3729. 

  3729. 			if not BLOCK.isblock('table'):   # first table line!
    3730. 

  3730. 				ret.extend(BLOCK.blockin('table'))
    3731. 

  3731. 				BLOCK.tableparser.__init__(line)
    3732. 

  3732. 			
    3733. 

  3733. 			tablerow = TableMaster().parse_row(line)
    3734. 

  3734. 			BLOCK.tableparser.add_row(tablerow)     # save config
    3735. 

  3735. 			
    3736. 

  3736. 			# maintain line to unmask and inlines
    3737. 

  3737. 			line = string.join(tablerow['cells'], SEPARATOR)
    3738. 

  3738. 		
    3739. 

  3739. 		#---------------------[ Paragraph ]-------------------------
    3740. 

  3740. 		
    3741. 

  3741. 		if not BLOCK.block() and \
    3742. 

  3742. 		   not string.count(line, MASK.tocmask): # new para!
    3743. 

  3743. 			ret.extend(BLOCK.blockin('para'))
    3744. 

  3744. 		
    3745. 

  3745. 		
    3746. 

  3746. 		############################################################
    3747. 

  3747. 		############################################################
    3748. 

  3748. 		############################################################
    3749. 

  3749. 		
    3750. 

  3750. 		
    3751. 

  3751. 		#---------------------[ Final Parses ]----------------------
    3752. 

  3752. 		
    3753. 

  3753. 		# the target-specific special char escapes for body lines
    3754. 

  3754. 		line = doEscape(target,line)
    3755. 

  3755. 		
    3756. 

  3756. 		line = add_inline_tags(line)
    3757. 

  3757. 		line = MASK.undo(line)
    3758. 

  3758. 		
    3759. 

  3759. 		
    3760. 

  3760. 		#---------------------[ Hold or Return? ]-------------------
    3761. 

  3761. 		
    3762. 

  3762. 		### now we must choose here to put the parsed line
    3763. 

  3763. 		#
    3764. 

  3764. 		if not results_box:
    3765. 

  3765. 			# list item extra lines
    3766. 

  3766. 			if BLOCK.block()[-4:] == 'list':
    3767. 

  3767. 				results_box = BLOCK.holdaddsub
    3768. 

  3768. 			# other blocks
    3769. 

  3769. 			elif BLOCK.block():
    3770. 

  3770. 				results_box = BLOCK.holdadd
    3771. 

  3771. 			# no blocks
    3772. 

  3772. 			else:
    3773. 

  3773. 				line = doFinalEscape(target, line)
    3774. 

  3774. 				results_box = ret.append
    3775. 

  3775. 		
    3776. 

  3776. 		results_box(line)
    3777. 

  3777. 	
    3778. 

  3778. 	# EOF: close any open para/verb/lists/table/quotes
    3779. 

  3779. 	Debug('EOF',2)
    3780. 

  3780. 	while BLOCK.block():
    3781. 

  3781. 		ret.extend(BLOCK.blockout())
    3782. 

  3782. 	
    3783. 

  3783. 	# maybe a major tag to enclose body? (like DIV for CSS)
    3784. 

  3784. 	if TAGS['bodyOpen' ]: ret.insert(0, TAGS['bodyOpen'])
    3785. 

  3785. 	if TAGS['bodyClose']: ret.append(TAGS['bodyClose'])
    3786. 

  3786. 	
    3787. 

  3787. 	if CONF['toc-only']: ret = []
    3788. 

  3788. 	marked_toc = TITLE.dump_marked_toc(CONF['toc-level'])
    3789. 

  3789. 	return ret, marked_toc
    3790. 

  3790. 

  3791. 

  3792. 

  3793. ##############################################################################
    3794. 

  3794. ################################### GUI ######################################
    3795. 

  3795. ##############################################################################
    3796. 

  3796. #
    3797. 

  3797. # tk help: http://python.org/topics/tkinter/
    3798. 

  3798. #    tuto: http://ibiblio.org/obp/py4fun/gui/tkPhone.html
    3799. 

  3799. #          /usr/lib/python*/lib-tk/Tkinter.py
    3800. 

  3800. #
    3801. 

  3801. # grid table : row=0, column=0, columnspan=2, rowspan=2
    3802. 

  3802. # grid align : sticky='n,s,e,w' (North, South, East, West)
    3803. 

  3803. # pack place : side='top,bottom,right,left'
    3804. 

  3804. # pack fill  : fill='x,y,both,none', expand=1
    3805. 

  3805. # pack align : anchor='n,s,e,w' (North, South, East, West)
    3806. 

  3806. # padding    : padx=10, pady=10, ipadx=10, ipady=10 (internal)
    3807. 

  3807. # checkbox   : offvalue is return if the _user_ deselected the box
    3808. 

  3808. # label align: justify=left,right,center
    3809. 

  3809. 

  3810. def load_GUI_resources():
    3811. 

  3811. 	"Load all extra modules and methods used by GUI"
    3812. 

  3812. 	global askopenfilename, showinfo, showwarning, showerror, Tkinter
    3813. 

  3813. 	from tkFileDialog import askopenfilename
    3814. 

  3814. 	from tkMessageBox import showinfo,showwarning,showerror
    3815. 

  3815. 	import Tkinter
    3816. 

  3816. 

  3817. class Gui:
    3818. 

  3818. 	"Graphical Tk Interface"
    3819. 

  3819. 	def __init__(self, conf={}):
    3820. 

  3820. 		self.root = Tkinter.Tk()    # mother window, come to butthead
    3821. 

  3821. 		self.root.title(my_name)    # window title bar text
    3822. 

  3822. 		self.window = self.root     # variable "focus" for inclusion
    3823. 

  3823. 		self.row = 0                # row count for grid()
    3824. 

  3824. 		
    3825. 

  3825. 		self.action_lenght = 150    # left column lenght (pixel)
    3826. 

  3826. 		self.frame_margin  = 10     # frame margin size  (pixel)
    3827. 

  3827. 		self.frame_border  = 6      # frame border size  (pixel)
    3828. 

  3828. 		
    3829. 

  3829. 		# the default Gui colors, can be changed by %!guicolors
    3830. 

  3830. 		self.dft_gui_colors = ['blue','white','lightblue','black']
    3831. 

  3831. 		self.gui_colors = []
    3832. 

  3832. 		self.bg1 = self.fg1 = self.bg2 = self.fg2 = ''
    3833. 

  3833. 		
    3834. 

  3834. 		# on Tk, vars need to be set/get using setvar()/get()
    3835. 

  3835. 		self.infile  = self.setvar('')
    3836. 

  3836. 		self.target  = self.setvar('')
    3837. 

  3837. 		self.target_name = self.setvar('')
    3838. 

  3838. 		
    3839. 

  3839. 		# the checks appearance order
    3840. 

  3840. 		self.checks  = [
    3841. 

  3841. 		  'headers','enum-title','toc','mask-email',
    3842. 

  3842. 		  'toc-only','stdout']
    3843. 

  3843. 		
    3844. 

  3844. 		# creating variables for all checks
    3845. 

  3845. 		for check in self.checks:
    3846. 

  3846. 			setattr(self, 'f_'+check, self.setvar(''))
    3847. 

  3847. 		
    3848. 

  3848. 		# load RC config
    3849. 

  3849. 		self.conf = {}
    3850. 

  3850. 		if conf: self.load_config(conf)
    3851. 

  3851. 	
    3852. 

  3852. 	def load_config(self, conf):
    3853. 

  3853. 		self.conf = conf
    3854. 

  3854. 		self.gui_colors = conf.get('guicolors') or self.dft_gui_colors
    3855. 

  3855. 		self.bg1, self.fg1, self.bg2, self.fg2 = self.gui_colors
    3856. 

  3856. 		self.root.config(bd=15,bg=self.bg1)
    3857. 

  3857. 	
    3858. 

  3858. 	### config as dic for python 1.5 compat (**opts don't work :( )
    3859. 

  3859. 	def entry(self, **opts): return Tkinter.Entry(self.window, opts)
    3860. 

  3860. 	def label(self, txt='', bg=None, **opts):
    3861. 

  3861. 		opts.update({'text':txt,'bg':bg or self.bg1})
    3862. 

  3862. 		return Tkinter.Label(self.window, opts)
    3863. 

  3863. 	def button(self,name,cmd,**opts):
    3864. 

  3864. 		opts.update({'text':name,'command':cmd})
    3865. 

  3865. 		return Tkinter.Button(self.window, opts)
    3866. 

  3866. 	def check(self,name,checked=0,**opts):
    3867. 

  3867. 		bg, fg = self.bg2, self.fg2
    3868. 

  3868. 		opts.update({
    3869. 

  3869. 		  'text':name, 'onvalue':1, 'offvalue':0,
    3870. 

  3870. 		  'activeforeground':fg, 'fg':fg,
    3871. 

  3871. 		  'activebackground':bg, 'bg':bg,
    3872. 

  3872. 		  'highlightbackground':bg, 'anchor':'w'
    3873. 

  3873. 		})
    3874. 

  3874. 		chk = Tkinter.Checkbutton(self.window, opts)
    3875. 

  3875. 		if checked: chk.select()
    3876. 

  3876. 		chk.grid(columnspan=2, sticky='w', padx=0)
    3877. 

  3877. 	def menu(self,sel,items):
    3878. 

  3878. 		return apply(Tkinter.OptionMenu,(self.window,sel)+tuple(items))
    3879. 

  3879. 	
    3880. 

  3880. 	# handy auxiliar functions
    3881. 

  3881. 	def action(self, txt):
    3882. 

  3882. 		self.label(txt, fg=self.fg1, bg=self.bg1,
    3883. 

  3883. 		     wraplength=self.action_lenght).grid(column=0,row=self.row)
    3884. 

  3884. 	def frame_open(self):
    3885. 

  3885. 		self.window = Tkinter.Frame(self.root,bg=self.bg2,
    3886. 

  3886. 		     borderwidth=self.frame_border)
    3887. 

  3887. 	def frame_close(self):
    3888. 

  3888. 		self.window.grid(column=1, row=self.row, sticky='w',
    3889. 

  3889. 		     padx=self.frame_margin)
    3890. 

  3890. 		self.window = self.root
    3891. 

  3891. 		self.label('').grid()
    3892. 

  3892. 		self.row = self.row + 2   # update row count
    3893. 

  3893. 	def target_name2key(self):
    3894. 

  3894. 		name = self.target_name.get()
    3895. 

  3895. 		target = filter(lambda x: TARGET_NAMES[x] == name, TARGETS)
    3896. 

  3896. 		try   : key = target[0]
    3897. 

  3897. 		except: key = ''
    3898. 

  3898. 		self.target = self.setvar(key)
    3899. 

  3899. 	def target_key2name(self):
    3900. 

  3900. 		key = self.target.get()
    3901. 

  3901. 		name = TARGET_NAMES.get(key) or key
    3902. 

  3902. 		self.target_name = self.setvar(name)
    3903. 

  3903. 	
    3904. 

  3904. 	def exit(self): self.root.destroy()
    3905. 

  3905. 	def setvar(self, val): z = Tkinter.StringVar() ; z.set(val) ; return z
    3906. 

  3906. 	
    3907. 

  3907. 	def askfile(self):
    3908. 

  3908. 		ftypes= [(_('txt2tags files'),('*.t2t','*.txt')),
    3909. 

  3909. 		         (_('All files'),'*')]
    3910. 

  3910. 		newfile = askopenfilename(filetypes=ftypes)
    3911. 

  3911. 		if newfile:
    3912. 

  3912. 			self.infile.set(newfile)
    3913. 

  3913. 			newconf = process_source_file(newfile)[0]
    3914. 

  3914. 			newconf = ConfigMaster().sanity(newconf, gui=1)
    3915. 

  3915. 			# restate all checkboxes after file selection
    3916. 

  3916. 			#TODO how to make a refresh without killing it?
    3917. 

  3917. 			self.root.destroy()
    3918. 

  3918. 			self.__init__(newconf)
    3919. 

  3919. 			self.mainwindow()
    3920. 

  3920. 	
    3921. 

  3921. 	def scrollwindow(self, txt='no text!', title=''):
    3922. 

  3922. 		# create components
    3923. 

  3923. 		win    = Tkinter.Toplevel() ; win.title(title)
    3924. 

  3924. 		frame  = Tkinter.Frame(win)
    3925. 

  3925. 		scroll = Tkinter.Scrollbar(frame)
    3926. 

  3926. 		text   = Tkinter.Text(frame,yscrollcommand=scroll.set)
    3927. 

  3927. 		button = Tkinter.Button(win)
    3928. 

  3928. 		# config
    3929. 

  3929. 		text.insert(Tkinter.END, string.join(txt,'\n'))
    3930. 

  3930. 		scroll.config(command=text.yview)
    3931. 

  3931. 		button.config(text=_('Close'), command=win.destroy)
    3932. 

  3932. 		button.focus_set()
    3933. 

  3933. 		# packing
    3934. 

  3934. 		text.pack(side='left', fill='both', expand=1)
    3935. 

  3935. 		scroll.pack(side='right', fill='y')
    3936. 

  3936. 		frame.pack(fill='both', expand=1)
    3937. 

  3937. 		button.pack(ipadx=30)
    3938. 

  3938. 	
    3939. 

  3939. 	def runprogram(self):
    3940. 

  3940. 		global CMDLINE_RAW
    3941. 

  3941. 		# prepare
    3942. 

  3942. 		self.target_name2key()
    3943. 

  3943. 		infile, target = self.infile.get(), self.target.get()
    3944. 

  3944. 		# sanity
    3945. 

  3945. 		if not target:
    3946. 

  3946. 			showwarning(my_name,_("You must select a target type!"))
    3947. 

  3947. 			return
    3948. 

  3948. 		if not infile:
    3949. 

  3949. 			showwarning(my_name,
    3950. 

  3950. 			   _("You must provide the source file location!"))
    3951. 

  3951. 			return
    3952. 

  3952. 		# compose cmdline
    3953. 

  3953. 		guiflags = []
    3954. 

  3954. 		real_cmdline_conf = ConfigMaster(CMDLINE_RAW).parse()
    3955. 

  3955. 		if real_cmdline_conf.has_key('infile'):
    3956. 

  3956. 			del real_cmdline_conf['infile']
    3957. 

  3957. 		if real_cmdline_conf.has_key('target'):
    3958. 

  3958. 			del real_cmdline_conf['target']
    3959. 

  3959. 		real_cmdline = CommandLine().compose_cmdline(real_cmdline_conf)
    3960. 

  3960. 		default_outfile = ConfigMaster().get_outfile_name(
    3961. 

  3961. 		     {'sourcefile':infile, 'outfile':'', 'target':target})
    3962. 

  3962. 		for opt in self.checks:
    3963. 

  3963. 			val = int(getattr(self, 'f_%s'%opt).get() or "0")
    3964. 

  3964. 			if opt == 'stdout': opt = 'outfile'
    3965. 

  3965. 			on_config  = self.conf.get(opt) or 0
    3966. 

  3966. 			on_cmdline = real_cmdline_conf.get(opt) or 0
    3967. 

  3967. 			if opt == 'outfile':
    3968. 

  3968. 				if on_config  == STDOUT: on_config = 1
    3969. 

  3969. 				else: on_config = 0
    3970. 

  3970. 				if on_cmdline == STDOUT: on_cmdline = 1
    3971. 

  3971. 				else: on_cmdline = 0
    3972. 

  3972. 			if val != on_config or (
    3973. 

  3973. 			  val == on_config == on_cmdline and
    3974. 

  3974. 			  real_cmdline_conf.has_key(opt)):
    3975. 

  3975. 				if val:
    3976. 

  3976. 					# was not set, but user selected on GUI
    3977. 

  3977. 					Debug("user turned  ON: %s"%opt)
    3978. 

  3978. 					if opt == 'outfile': opt = '-o-'
    3979. 

  3979. 					else: opt = '--%s'%opt
    3980. 

  3980. 				else:
    3981. 

  3981. 					# was set, but user deselected on GUI
    3982. 

  3982. 					Debug("user turned OFF: %s"%opt)
    3983. 

  3983. 					if opt == 'outfile':
    3984. 

  3984. 						opt = "-o%s"%default_outfile
    3985. 

  3985. 					else: opt = '--no-%s'%opt
    3986. 

  3986. 				guiflags.append(opt)
    3987. 

  3987. 		cmdline = [my_name, '-t', target] +real_cmdline \
    3988. 

  3988. 		          +guiflags +[infile]
    3989. 

  3989. 		Debug('Gui/Tk cmdline: %s'%cmdline,5)
    3990. 

  3990. 		# run!
    3991. 

  3991. 		cmdline_raw_orig = CMDLINE_RAW
    3992. 

  3992. 		try:
    3993. 

  3993. 			# fake the GUI cmdline as the real one, and parse file
    3994. 

  3994. 			CMDLINE_RAW = CommandLine().get_raw_config(cmdline[1:])
    3995. 

  3995. 			data = process_source_file(infile)
    3996. 

  3996. 			# on GUI, convert_* returns the data, not finish_him()
    3997. 

  3997. 			outlist, config = convert_this_files([data])
    3998. 

  3998. 			# on GUI and STDOUT, finish_him() returns the data
    3999. 

  3999. 			result = finish_him(outlist, config)
    4000. 

  4000. 			# show outlist in s a nice new window
    4001. 

  4001. 			if result:
    4002. 

  4002. 				outlist, config = result
    4003. 

  4003. 				title = _('%s: %s converted to %s')%(
    4004. 

  4004. 				  my_name, os.path.basename(infile),
    4005. 

  4005. 				  string.upper(config['target']))
    4006. 

  4006. 				self.scrollwindow(outlist, title)
    4007. 

  4007. 			# show the "file saved" message
    4008. 

  4008. 			else:
    4009. 

  4009. 				msg = "%s\n\n  %s\n%s\n\n  %s\n%s"%(
    4010. 

  4010. 				      _('Conversion done!'),
    4011. 

  4011. 				      _('FROM:'), infile,
    4012. 

  4012. 				      _('TO:'), config['outfile'])
    4013. 

  4013. 				showinfo(my_name, msg)
    4014. 

  4014. 		except ZeroDivisionError:   # common error, not quit
    4015. 

  4015. 			pass
    4016. 

  4016. 		except:                     # fatal error
    4017. 

  4017. 			ShowTraceback()
    4018. 

  4018. 			print _('Sorry! txt2tags-Tk Fatal Error.')
    4019. 

  4019. 			errmsg = '%s\n\n%s\n    %s'%(
    4020. 

  4020. 			  _('Unknown error occurred.'),
    4021. 

  4021. 			  _('Please send the Error Traceback to the author:'),
    4022. 

  4022. 			  my_email)
    4023. 

  4023. 			showerror(_('%s FATAL ERROR!')%my_name,errmsg)
    4024. 

  4024. 			self.exit()
    4025. 

  4025. 		CMDLINE_RAW = cmdline_raw_orig
    4026. 

  4026. 	
    4027. 

  4027. 	def mainwindow(self):
    4028. 

  4028. 		self.infile.set(self.conf.get('sourcefile') or '')
    4029. 

  4029. 		self.target.set(self.conf.get('target') or \
    4030. 

  4030. 		              _('-- select one --'))
    4031. 

  4031. 		outfile = self.conf.get('outfile')
    4032. 

  4032. 		if outfile == STDOUT:                  # map -o-
    4033. 

  4033. 			self.conf['stdout'] = 1
    4034. 

  4034. 		if self.conf.get('headers') == None:
    4035. 

  4035. 			self.conf['headers'] = 1       # map default
    4036. 

  4036. 		
    4037. 

  4037. 		action1 = _("Enter the source file location:")
    4038. 

  4038. 		action2 = _("Choose the target document type:")
    4039. 

  4039. 		action3 = _("Some options you may check:")
    4040. 

  4040. 		action4 = _("Some extra options:")
    4041. 

  4041. 		checks_txt = {
    4042. 

  4042. 		  'headers'   : _("Include headers on output"),
    4043. 

  4043. 		  'enum-title': _("Number titles (1, 1.1, 1.1.1, etc)"),
    4044. 

  4044. 		  'toc'       : _("Do TOC also (Table of Contents)"),
    4045. 

  4045. 		  'mask-email': _("Hide e-mails from SPAM robots"),
    4046. 

  4046. 		
    4047. 

  4047. 		  'toc-only'  : _("Just do TOC, nothing more"),
    4048. 

  4048. 		  'stdout'    : _("Dump to screen (Don't save target file)")
    4049. 

  4049. 		}
    4050. 

  4050. 		targets_menu = map(lambda x: TARGET_NAMES[x], TARGETS)
    4051. 

  4051. 		
    4052. 

  4052. 		# header
    4053. 

  4053. 		self.label("%s %s"%(string.upper(my_name), my_version),
    4054. 

  4054. 		     bg=self.bg2, fg=self.fg2).grid(columnspan=2, ipadx=10)
    4055. 

  4055. 		self.label(_("ONE source, MULTI targets")+'\n%s\n'%my_url,
    4056. 

  4056. 		     bg=self.bg1, fg=self.fg1).grid(columnspan=2)
    4057. 

  4057. 		self.row = 2
    4058. 

  4058. 		# choose input file
    4059. 

  4059. 		self.action(action1) ; self.frame_open()
    4060. 

  4060. 		e_infile = self.entry(textvariable=self.infile,width=25)
    4061. 

  4061. 		e_infile.grid(row=self.row, column=0, sticky='e')
    4062. 

  4062. 		if not self.infile.get(): e_infile.focus_set()
    4063. 

  4063. 		self.button(_("Browse"), self.askfile).grid(
    4064. 

  4064. 		    row=self.row, column=1, sticky='w', padx=10)
    4065. 

  4065. 		# show outfile name, style and encoding (if any)
    4066. 

  4066. 		txt = ''
    4067. 

  4067. 		if outfile:
    4068. 

  4068. 			txt = outfile
    4069. 

  4069. 			if outfile == STDOUT: txt = _('<screen>')
    4070. 

  4070. 			l_output = self.label(_('Output: ')+txt,
    4071. 

  4071. 			                fg=self.fg2,bg=self.bg2)
    4072. 

  4072. 			l_output.grid(columnspan=2, sticky='w')
    4073. 

  4073. 		for setting in ['style','encoding']:
    4074. 

  4074. 			if self.conf.get(setting):
    4075. 

  4075. 				name = string.capitalize(setting)
    4076. 

  4076. 				val  = self.conf[setting]
    4077. 

  4077. 				self.label('%s: %s'%(name, val),
    4078. 

  4078. 				     fg=self.fg2, bg=self.bg2).grid(
    4079. 

  4079. 				     columnspan=2, sticky='w')
    4080. 

  4080. 		# choose target
    4081. 

  4081. 		self.frame_close() ; self.action(action2)
    4082. 

  4082. 		self.frame_open()
    4083. 

  4083. 		self.target_key2name()
    4084. 

  4084. 		self.menu(self.target_name, targets_menu).grid(
    4085. 

  4085. 		     columnspan=2, sticky='w')
    4086. 

  4086. 		# options checkboxes label
    4087. 

  4087. 		self.frame_close() ; self.action(action3)
    4088. 

  4088. 		self.frame_open()
    4089. 

  4089. 		# compose options check boxes, example:
    4090. 

  4090. 		# self.check(checks_txt['toc'],1,variable=self.f_toc)
    4091. 

  4091. 		for check in self.checks:
    4092. 

  4092. 			# extra options label
    4093. 

  4093. 			if check == 'toc-only':
    4094. 

  4094. 				self.frame_close() ; self.action(action4)
    4095. 

  4095. 				self.frame_open()
    4096. 

  4096. 			txt = checks_txt[check]
    4097. 

  4097. 			var = getattr(self, 'f_'+check)
    4098. 

  4098. 			checked = self.conf.get(check)
    4099. 

  4099. 			self.check(txt,checked,variable=var)
    4100. 

  4100. 		self.frame_close()
    4101. 

  4101. 		# spacer and buttons
    4102. 

  4102. 		self.label('').grid() ; self.row = self.row + 1
    4103. 

  4103. 		b_quit = self.button(_("Quit"), self.exit)
    4104. 

  4104. 		b_quit.grid(row=self.row, column=0, sticky='w', padx=30)
    4105. 

  4105. 		b_conv = self.button(_("Convert!"), self.runprogram)
    4106. 

  4106. 		b_conv.grid(row=self.row, column=1, sticky='e', padx=30)
    4107. 

  4107. 		if self.target.get() and self.infile.get():
    4108. 

  4108. 			b_conv.focus_set()
    4109. 

  4109. 		
    4110. 

  4110. 		# as documentation told me
    4111. 

  4111. 		if sys.platform[:3] == 'win':
    4112. 

  4112. 			self.root.iconify()
    4113. 

  4113. 			self.root.update()
    4114. 

  4114. 			self.root.deiconify()
    4115. 

  4115. 		
    4116. 

  4116. 		self.root.mainloop()
    4117. 

  4117. 

  4118. 

  4119. ##############################################################################
    4120. 

  4120. ##############################################################################
    4121. 

  4121. 

  4122. def exec_command_line(user_cmdline=[]):
    4123. 

  4123. 	global CMDLINE_RAW, RC_RAW, DEBUG, VERBOSE, QUIET, GUI, Error
    4124. 

  4124. 	
    4125. 

  4125. 	# extract command line data
    4126. 

  4126. 	cmdline_data = user_cmdline or sys.argv[1:]
    4127. 

  4127. 	CMDLINE_RAW = CommandLine().get_raw_config(cmdline_data)
    4128. 

  4128. 	cmdline_parsed = ConfigMaster(CMDLINE_RAW).parse()
    4129. 

  4129. 	DEBUG   = cmdline_parsed.get('debug'  ) or 0
    4130. 

  4130. 	VERBOSE = cmdline_parsed.get('verbose') or 0
    4131. 

  4131. 	QUIET   = cmdline_parsed.get('quiet'  ) or 0
    4132. 

  4132. 	GUI     = cmdline_parsed.get('gui'    ) or 0
    4133. 

  4133. 	infiles = cmdline_parsed.get('infile' ) or []
    4134. 

  4134. 	
    4135. 

  4135. 	Message(_("Txt2tags %s processing begins")%my_version,1)
    4136. 

  4136. 	
    4137. 

  4137. 	# the easy ones
    4138. 

  4138. 	if cmdline_parsed.get('help'   ): Quit(USAGE)
    4139. 

  4139. 	if cmdline_parsed.get('version'): Quit(VERSIONSTR)
    4140. 

  4140. 	
    4141. 

  4141. 	# multifile haters
    4142. 

  4142. 	if len(infiles) > 1:
    4143. 

  4143. 		errmsg=_("Option --%s can't be used with multiple input files")
    4144. 

  4144. 		for option in ['gui','dump-config']:
    4145. 

  4145. 			if cmdline_parsed.get(option):
    4146. 

  4146. 				Error(errmsg%option)
    4147. 

  4147. 	
    4148. 

  4148. 	Debug("system platform: %s"%sys.platform)
    4149. 

  4149. 	Debug("line break char: %s"%repr(LB))
    4150. 

  4150. 	Debug("command line: %s"%sys.argv)
    4151. 

  4151. 	Debug("command line raw config: %s"%CMDLINE_RAW,1)
    4152. 

  4152. 	
    4153. 

  4153. 	# extract RC file config
    4154. 

  4154. 	if cmdline_parsed.get('rc') == 0:
    4155. 

  4155. 		Message(_("Ignoring user configuration file"),1)
    4156. 

  4156. 	else:
    4157. 

  4157. 		rc_file = get_rc_path()
    4158. 

  4158. 		if os.path.isfile(rc_file):
    4159. 

  4159. 			Message(_("Loading user configuration file"),1)
    4160. 

  4160. 			RC_RAW = ConfigLines(file=rc_file).get_raw_config()
    4161. 

  4161. 		
    4162. 

  4162. 		Debug("rc file: %s"%rc_file)
    4163. 

  4163. 		Debug("rc file raw config: %s"%RC_RAW,1)
    4164. 

  4164. 	
    4165. 

  4165. 	# get all infiles config (if any)
    4166. 

  4166. 	infiles_config = get_infiles_config(infiles)
    4167. 

  4167. 	
    4168. 

  4168. 	# is GUI available?
    4169. 

  4169. 	# try to load and start GUI interface for --gui
    4170. 

  4170. 	# if program was called with no arguments, try GUI also
    4171. 

  4171. 	if GUI or not infiles:
    4172. 

  4172. 		try:
    4173. 

  4173. 			load_GUI_resources()
    4174. 

  4174. 			Debug("GUI resources OK (Tk module is installed)")
    4175. 

  4175. 			winbox = Gui()
    4176. 

  4176. 			Debug("GUI display OK")
    4177. 

  4177. 			GUI = 1
    4178. 

  4178. 		except:
    4179. 

  4179. 			Debug("GUI Error: no Tk module or no DISPLAY")
    4180. 

  4180. 			GUI = 0
    4181. 

  4181. 	
    4182. 

  4182. 	# user forced --gui, but it's not available
    4183. 

  4183. 	if cmdline_parsed.get('gui') and not GUI:
    4184. 

  4184. 		ShowTraceback()
    4185. 

  4185. 		Error("Sorry, I can't run my Graphical Interface - GUI\n"
    4186. 

  4186. 		      "- Check if Python Tcl/Tk module is installed (Tkinter)\n"
    4187. 

  4187. 		      "- Make sure you are in a graphical environment (like X)")
    4188. 

  4188. 	
    4189. 

  4189. 	# Okay, we will use GUI
    4190. 

  4190. 	if GUI:
    4191. 

  4191. 		Message(_("We are on GUI interface"),1)
    4192. 

  4192. 		
    4193. 

  4193. 		# redefine Error function to raise exception instead sys.exit()
    4194. 

  4194. 		def Error(msg):
    4195. 

  4195. 			showerror(_('txt2tags ERROR!'), msg)
    4196. 

  4196. 			raise ZeroDivisionError
    4197. 

  4197. 		
    4198. 

  4198. 		# if no input file, get RC+cmdline config, else full config
    4199. 

  4199. 		if not infiles:
    4200. 

  4200. 			gui_conf = ConfigMaster(RC_RAW+CMDLINE_RAW).parse()
    4201. 

  4201. 		else:
    4202. 

  4202. 			try   : gui_conf = infiles_config[0][0]
    4203. 

  4203. 			except: gui_conf = {}
    4204. 

  4204. 		
    4205. 

  4205. 		# sanity is needed to set outfile and other things
    4206. 

  4206. 		gui_conf = ConfigMaster().sanity(gui_conf, gui=1)
    4207. 

  4207. 		Debug("GUI config: %s"%gui_conf,5)
    4208. 

  4208. 		
    4209. 

  4209. 		# insert config and populate the nice window!
    4210. 

  4210. 		winbox.load_config(gui_conf)
    4211. 

  4211. 		winbox.mainwindow()
    4212. 

  4212. 	
    4213. 

  4213. 	# console mode rocks forever!
    4214. 

  4214. 	else:
    4215. 

  4215. 		Message(_("We are on Command Line interface"),1)
    4216. 

  4216. 		
    4217. 

  4217. 		# called with no arguments, show error
    4218. 

  4218. 		if not infiles: Error(_('Missing input file (try --help)'))
    4219. 

  4219. 		
    4220. 

  4220. 		convert_this_files(infiles_config)
    4221. 

  4221. 	
    4222. 

  4222. 	Message(_("Txt2tags finished sucessfuly"),1)
    4223. 

  4223. 	sys.exit(0)
    4224. 

  4224. 

  4225. if __name__ == '__main__':
    4226. 

  4226. 	exec_command_line()
    4227. 

  4227. 

  4228. 

  4229. # vim: ts=8
    4230. 

  4230.