PageRenderTime 99ms CodeModel.GetById 25ms RepoModel.GetById 1ms app.codeStats 1ms

/old/txt2tags-2.4.py

http://txt2tags.googlecode.com/
Python | 4715 lines | 4247 code | 184 blank | 284 comment | 199 complexity | c383d7cb0d3fbb2ec403bd96a4d14473 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, 2005, 2006 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. #   BORING CODE EXPLANATION AHEAD
    22. 

  22. #
    23. 

  23. # Just read if you wish to understand how the txt2tags code works
    24. 

  24. #
    25. 

  25. ########################################################################
    26. 

  26. #
    27. 

  27. # Version 2.0 was a complete rewrite for the program 'core'.
    28. 

  28. #
    29. 

  29. # Now the code that [1] parses the marked text is separated from the
    30. 

  30. # code that [2] insert the target tags.
    31. 

  31. #
    32. 

  32. #   [1] made by: def convert()
    33. 

  33. #   [2] made by: class BlockMaster
    34. 

  34. #
    35. 

  35. # The structures of the marked text are identified and its contents are
    36. 

  36. # extracted into a data holder (Python lists and dictionaries).
    37. 

  37. #
    38. 

  38. # When parsing the source file, the blocks (para, lists, quote, table)
    39. 

  39. # are opened with BlockMaster, right when found. Then its contents,
    40. 

  40. # which spans on several lines, are feeded into a special holder on the
    41. 

  41. # BlockMaster instance. Just when the block is closed, the target tags
    42. 

  42. # are inserted for the full block as a whole, in one pass. This way, we
    43. 

  43. # have a better control on blocks. Much better than the previous line by
    44. 

  44. # line approach.
    45. 

  45. #
    46. 

  46. # In other words, whenever inside a block, the parser *holds* the tag
    47. 

  47. # insertion process, waiting until the full block is read. That was
    48. 

  48. # needed primary to close paragraphs for the new XHTML target, but
    49. 

  49. # proved to be a very good adding, improving many other processing.
    50. 

  50. #
    51. 

  51. # -------------------------------------------------------------------
    52. 

  52. #
    53. 

  53. # There is also a brand new code for the Configuration schema, 100%
    54. 

  54. # rewritten. There are new classes, all self documented: CommandLine,
    55. 

  55. # SourceDocument, ConfigMaster and ConfigLines. In short, a new RAW
    56. 

  56. # Config format was created, and all kind of configuration is first
    57. 

  57. # converted to this format, and then a generic method parses it.
    58. 

  58. #
    59. 

  59. # The init processing was changed also, and now the functions which
    60. 

  60. # gets informations about the input files are: get_infiles_config(),
    61. 

  61. #  process_source_file() and convert_this_files()
    62. 

  62. #
    63. 

  63. # Other parts are untouched, and remains the same as in v1.7, as the
    64. 

  64. # marks regexes, target Headers and target Tags & Rules.
    65. 

  65. #
    66. 

  66. ########################################################################
    67. 

  67. 

  68. # Now I think the code is nice, easier to read and understand
    69. 

  69. 

  70. #XXX Python coding warning
    71. 

  71. # Avoid common mistakes:
    72. 

  72. # - do NOT use newlist=list instead newlist=list[:]
    73. 

  73. # - do NOT use newdic=dic   instead newdic=dic.copy()
    74. 

  74. # - do NOT use dic[key]     instead dic.get(key)
    75. 

  75. # - do NOT use del dic[key] without has_key() before
    76. 

  76. 

  77. #XXX Smart Image Align don't work if the image is a link
    78. 

  78. # Can't fix that because the image is expanded together with the
    79. 

  79. # link, at the linkbank filling moment. Only the image is passed
    80. 

  80. # to parse_images(), not the full line, so it is always 'middle'.
    81. 

  81. 

  82. #XXX Paragraph separation not valid inside Quote
    83. 

  83. # Quote will not have <p></p> inside, instead will close and open
    84. 

  84. # again the <blockquote>. This really sux in CSS, when defining a
    85. 

  85. # different background color. Still don't know how to fix it.
    86. 

    87. 

  87. #XXX TODO (maybe)
    88. 

  88. # New mark or macro which expands to an anchor full title.
    89. 

  89. # It is necessary to parse the full document in this order:
    90. 

  90. #  DONE  1st scan: HEAD: get all settings, including %!includeconf
    91. 

  91. #  DONE  2nd scan: BODY: expand includes & apply %!preproc
    92. 

  92. #        3rd scan: BODY: read titles and compose TOC info
    93. 

  93. #        4th scan: BODY: full parsing, expanding [#anchor] 1st
    94. 

  94. # Steps 2 and 3 can be made together, with no tag adding.
    95. 

  95. # Two complete body scans will be *slow*, don't know if it worths.
    96. 

  96. # One solution may be add the titles as postproc rules
    97. 

  97. 

  98. 

  99. ##############################################################################
    100. 

  100. 

  101. # User config (1=ON, 0=OFF)
    102. 

  102. 

  103. USE_I18N    = 1   # use gettext for i18ned messages?        (default is 1)
    104. 

  104. COLOR_DEBUG = 1   # show debug messages in colors?          (default is 1)
    105. 

  105. BG_LIGHT    = 0   # your terminal background color is light (default is 0)
    106. 

  106. HTML_LOWER  = 0   # use lowercased HTML tags instead upper? (default is 0)
    107. 

  107. 

  108. ##############################################################################
    109. 

  109. 

  110. 

  111. # These are all the core Python modules used by txt2tags (KISS!)
    112. 

  112. import re, string, os, sys, time, getopt
    113. 

  113. 

  114. # Program information
    115. 

  115. my_url = 'http://txt2tags.sf.net'
    116. 

  116. my_name = 'txt2tags'
    117. 

  117. my_email = 'verde@aurelio.net'
    118. 

  118. my_version = '2.4'
    119. 

  119. 

  120. # i18n - just use if available
    121. 

  121. if USE_I18N:
    122. 

  122. 	try:
    123. 

  123. 		import gettext
    124. 

  124. 		# If your locale dir is different, change it here
    125. 

  125. 		cat = gettext.Catalog('txt2tags',localedir='/usr/share/locale/')
    126. 

  126. 		_ = cat.gettext
    127. 

  127. 	except:
    128. 

  128. 		_ = lambda x:x
    129. 

  129. else:
    130. 

  130. 	_ = lambda x:x
    131. 

  131. 

  132. # FLAGS   : the conversion related flags  , may be used in %!options
    133. 

  133. # OPTIONS : the conversion related options, may be used in %!options
    134. 

  134. # ACTIONS : the other behavior modifiers, valid on command line only
    135. 

  135. # MACROS  : the valid macros with their default values for formatting
    136. 

  136. # SETTINGS: global miscellaneous settings, valid on RC file only
    137. 

  137. # NO_TARGET: actions that don't require a target specification
    138. 

  138. # NO_MULTI_INPUT: actions that don't accept more than one input file
    139. 

  139. # CONFIG_KEYWORDS: the valid %!key:val keywords
    140. 

  140. #
    141. 

  141. # FLAGS and OPTIONS are configs that affect the converted document.
    142. 

  142. # They usually have also a --no-<option> to turn them OFF.
    143. 

  143. # ACTIONS are needed because when doing multiple input files, strange
    144. 

  144. # behavior would be found, as use command line interface for the
    145. 

  145. # first file and gui for the second. There is no --no-<action>.
    146. 

  146. # --version and --help inside %!options are also odd
    147. 

  147. #
    148. 

  148. TARGETS  = ['html', 'xhtml', 'sgml', 'tex', 'lout', 'man', 'mgp',
    149. 

  149.             'moin', 'pm6'  , 'txt']
    150. 

  150. FLAGS    = {'headers'    :1 , 'enum-title' :0 , 'mask-email' :0 ,
    151. 

  151.             'toc-only'   :0 , 'toc'        :0 , 'rc'         :1 ,
    152. 

  152.             'css-sugar'  :0 , 'css-suggar' :0 , 'css-inside' :0 ,
    153. 

  153.             'quiet'      :0 }
    154. 

  154. OPTIONS  = {'target'     :'', 'toc-level'  :3 , 'style'      :'',
    155. 

  155.             'infile'     :'', 'outfile'    :'', 'encoding'   :'',
    156. 

  156.             'config-file':'', 'split'      :0 , 'lang'       :''}
    157. 

  157. ACTIONS  = {'help'       :0 , 'version'    :0 , 'gui'        :0 ,
    158. 

  158.             'verbose'    :0 , 'debug'      :0 , 'dump-config':0 ,
    159. 

  159.             'dump-source':0 }
    160. 

  160. MACROS   = {'date' : '%Y%m%d',  'infile': '%f',
    161. 

  161.             'mtime': '%Y%m%d', 'outfile': '%f'}
    162. 

  162. SETTINGS = {}         # for future use
    163. 

  163. NO_TARGET = ['help', 'version', 'gui', 'toc-only', 'dump-config', 'dump-source']
    164. 

  164. NO_MULTI_INPUT = ['gui','dump-config','dump-source']
    165. 

  165. CONFIG_KEYWORDS = [
    166. 

  166.             'target', 'encoding', 'style', 'options', 'preproc','postproc',
    167. 

  167.             'guicolors']
    168. 

  168. TARGET_NAMES = {
    169. 

  169.   'html' : _('HTML page'),
    170. 

  170.   'xhtml': _('XHTML page'),
    171. 

  171.   'sgml' : _('SGML document'),
    172. 

  172.   'tex'  : _('LaTeX document'),
    173. 

  173.   'lout' : _('Lout document'),
    174. 

  174.   'man'  : _('UNIX Manual page'),
    175. 

  175.   'mgp'  : _('MagicPoint presentation'),
    176. 

  176.   'moin' : _('MoinMoin page'),
    177. 

  177.   'pm6'  : _('PageMaker document'),
    178. 

  178.   'txt'  : _('Plain Text'),
    179. 

  179. }
    180. 

  180. 

  181. DEBUG = 0     # do not edit here, please use --debug
    182. 

  182. VERBOSE = 0   # do not edit here, please use -v, -vv or -vvv
    183. 

  183. QUIET = 0     # do not edit here, please use --quiet
    184. 

  184. GUI = 0       # do not edit here, please use --gui
    185. 

  185. AUTOTOC = 1   # do not edit here, please use --no-toc or %%toc
    186. 

  186. 

  187. RC_RAW = []
    188. 

  188. CMDLINE_RAW = []
    189. 

  189. CONF = {}
    190. 

  190. BLOCK = None
    191. 

  191. regex = {}
    192. 

  192. TAGS = {}
    193. 

  193. rules = {}
    194. 

  194. 

  195. lang = 'english'
    196. 

  196. TARGET = ''
    197. 

  197. 

  198. STDIN = STDOUT = '-'
    199. 

  199. MODULEIN = MODULEOUT = '-module-'
    200. 

  200. ESCCHAR   = '\x00'
    201. 

  201. SEPARATOR = '\x01'
    202. 

  202. LISTNAMES = {'-':'list', '+':'numlist', ':':'deflist'}
    203. 

  203. LINEBREAK = {'default':'\n', 'win':'\r\n', 'mac':'\r'}
    204. 

  204. 

  205. # Platform specific settings
    206. 

  206. LB = LINEBREAK.get(sys.platform[:3]) or LINEBREAK['default']
    207. 

  207. 

  208. VERSIONSTR = _("%s version %s <%s>")%(my_name,my_version,my_url)
    209. 

  209. 

  210. USAGE = string.join([
    211. 

  211. '',
    212. 

  212. _("Usage: %s [OPTIONS] [infile.t2t ...]") % my_name,
    213. 

  213. '',
    214. 

  214. _("  -t, --target=TYPE   set target document type. currently supported:"),
    215. 

  215. '                      %s' % re.sub(r"[]'[]",'',repr(TARGETS)),
    216. 

  216. _("  -i, --infile=FILE   set FILE as the input file name ('-' for STDIN)"),
    217. 

  217. _("  -o, --outfile=FILE  set FILE as the output file name ('-' for STDOUT)"),
    218. 

  218. _("  -H, --no-headers    suppress header, title and footer contents"),
    219. 

  219. _("      --headers       show header, title and footer contents (default ON)"),
    220. 

  220. _("      --encoding=ENC  set target file encoding (utf-8, iso-8859-1, etc)"),
    221. 

  221. _("      --style=FILE    use FILE as the document style (like HTML CSS)"),
    222. 

  222. _("      --css-sugar     insert CSS-friendly tags for HTML and XHTML targets"),
    223. 

  223. _("      --css-inside    insert CSS file contents inside HTML/XHTML headers"),
    224. 

  224. _("      --mask-email    hide email from spam robots. x@y.z turns <x (a) y z>"),
    225. 

  225. _("      --toc           add TOC (Table of Contents) to target document"),
    226. 

  226. _("      --toc-only      print document TOC and exit"),
    227. 

  227. _("      --toc-level=N   set maximum TOC level (depth) to N"),
    228. 

  228. _("  -n, --enum-title    enumerate all titles as 1, 1.1, 1.1.1, etc"),
    229. 

  229. _("  -C, --config-file=F read config from file F"),
    230. 

  230. _("      --rc            read user config file ~/.txt2tagsrc (default ON)"),
    231. 

  231. _("      --gui           invoke Graphical Tk Interface"),
    232. 

  232. _("  -q, --quiet         quiet mode, suppress all output (except errors)"),
    233. 

  233. _("  -v, --verbose       print informative messages during conversion"),
    234. 

  234. _("  -h, --help          print this help information and exit"),
    235. 

  235. _("  -V, --version       print program version and exit"),
    236. 

  236. _("      --dump-config   print all the config found and exit"),
    237. 

  237. _("      --dump-source   print the document source, with includes expanded"),
    238. 

  238. '',
    239. 

  239. _("Turn OFF options:"),
    240. 

  240. "     --no-outfile, --no-infile, --no-style, --no-encoding, --no-headers",
    241. 

  241. "     --no-toc, --no-toc-only, --no-mask-email, --no-enum-title, --no-rc",
    242. 

  242. "     --no-css-sugar, --no-css-inside, --no-quiet, --no-dump-config",
    243. 

  243. "     --no-dump-source",
    244. 

  244. '',
    245. 

  245. _("Example:\n     %s -t html --toc myfile.t2t") % my_name,
    246. 

  246. '',
    247. 

  247. _("By default, converted output is saved to 'infile.<target>'."),
    248. 

  248. _("Use --outfile to force an output file name."),
    249. 

  249. _("If  input file is '-', reads from STDIN."),
    250. 

  250. _("If output file is '-', dumps output to STDOUT."),
    251. 

  251. '',
    252. 

  252. 'http://txt2tags.sourceforge.net',
    253. 

  253. ''
    254. 

  254. ], '\n')
    255. 

  255. 

  256. 

  257. ##############################################################################
    258. 

  258. 

  259. 

  260. # Here is all the target's templates
    261. 

  261. # You may edit them to fit your needs
    262. 

  262. #  - the %(HEADERn)s strings represent the Header lines
    263. 

  263. #  - the %(STYLE)s string is changed by --style contents
    264. 

  264. #  - the %(ENCODING)s string is changed by --encoding contents
    265. 

  265. #  - if any of the above is empty, the full line is removed
    266. 

  266. #  - use %% to represent a literal %
    267. 

  267. #
    268. 

  268. HEADER_TEMPLATE = {
    269. 

  269.   'txt': """\
    270. 

  270. %(HEADER1)s
    271. 

  271. %(HEADER2)s
    272. 

  272. %(HEADER3)s
    273. 

  273. """,
    274. 

    275. 

  275.   'sgml': """\
    276. 

  276. <!doctype linuxdoc system>
    277. 

  277. <article>
    278. 

  278. <title>%(HEADER1)s
    279. 

  279. <author>%(HEADER2)s
    280. 

  280. <date>%(HEADER3)s
    281. 

  281. """,
    282. 

    283. 

  283.   'html': """\
    284. 

  284. <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
    285. 

  285. <HTML>
    286. 

  286. <HEAD>
    287. 

  287. <META NAME="generator" CONTENT="http://txt2tags.sf.net">
    288. 

  288. <META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=%(ENCODING)s">
    289. 

  289. <LINK REL="stylesheet" TYPE="text/css" HREF="%(STYLE)s">
    290. 

  290. <TITLE>%(HEADER1)s</TITLE>
    291. 

  291. </HEAD><BODY BGCOLOR="white" TEXT="black">
    292. 

  292. <P ALIGN="center"><CENTER><H1>%(HEADER1)s</H1>
    293. 

  293. <FONT SIZE="4">
    294. 

  294. <I>%(HEADER2)s</I><BR>
    295. 

  295. %(HEADER3)s
    296. 

  296. </FONT></CENTER>
    297. 

  297. """,
    298. 

    299. 

  299.   'htmlcss': """\
    300. 

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

  301. <HTML>
    302. 

  302. <HEAD>
    303. 

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

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

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

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

  307. </HEAD>
    308. 

  308. <BODY>
    309. 

  309. 

  310. <DIV CLASS="header" ID="header">
    311. 

  311. <H1>%(HEADER1)s</H1>
    312. 

  312. <H2>%(HEADER2)s</H2>
    313. 

  313. <H3>%(HEADER3)s</H3>
    314. 

  314. </DIV>
    315. 

  315. """,
    316. 

    317. 

  317.   'xhtml': """\
    318. 

  318. <?xml version="1.0"
    319. 

  319.       encoding="%(ENCODING)s"
    320. 

  320. ?>
    321. 

  321. <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"\
    322. 

  322.  "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
    323. 

  323. <html xmlns="http://www.w3.org/1999/xhtml">
    324. 

  324. <head>
    325. 

  325. <title>%(HEADER1)s</title>
    326. 

  326. <meta name="generator" content="http://txt2tags.sf.net" />
    327. 

  327. <link rel="stylesheet" type="text/css" href="%(STYLE)s" />
    328. 

  328. </head>
    329. 

  329. <body bgcolor="white" text="black">
    330. 

  330. <div align="center">
    331. 

  331. <h1>%(HEADER1)s</h1>
    332. 

  332. <h2>%(HEADER2)s</h2>
    333. 

  333. <h3>%(HEADER3)s</h3>
    334. 

  334. </div>
    335. 

  335. """,
    336. 

    337. 

  337.   'xhtmlcss': """\
    338. 

  338. <?xml version="1.0"
    339. 

  339.       encoding="%(ENCODING)s"
    340. 

  340. ?>
    341. 

  341. <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"\
    342. 

  342.  "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
    343. 

  343. <html xmlns="http://www.w3.org/1999/xhtml">
    344. 

  344. <head>
    345. 

  345. <title>%(HEADER1)s</title>
    346. 

  346. <meta name="generator" content="http://txt2tags.sf.net" />
    347. 

  347. <link rel="stylesheet" type="text/css" href="%(STYLE)s" />
    348. 

  348. </head>
    349. 

  349. <body>
    350. 

  350. 

  351. <div class="header" id="header">
    352. 

  352. <h1>%(HEADER1)s</h1>
    353. 

  353. <h2>%(HEADER2)s</h2>
    354. 

  354. <h3>%(HEADER3)s</h3>
    355. 

  355. </div>
    356. 

  356. """,
    357. 

    358. 

  358.   'man': """\
    359. 

  359. .TH "%(HEADER1)s" 1 "%(HEADER3)s" "%(HEADER2)s"
    360. 

  360. """,
    361. 

    362. 

  362. # TODO style to <HR>
    363. 

  363.   'pm6': """\
    364. 

  364. <PMTags1.0 win><C-COLORTABLE ("Preto" 1 0 0 0)
    365. 

  365. ><@Normal=
    366. 

  366.   <FONT "Times New Roman"><CCOLOR "Preto"><SIZE 11>
    367. 

  367.   <HORIZONTAL 100><LETTERSPACE 0><CTRACK 127><CSSIZE 70><C+SIZE 58.3>
    368. 

  368.   <C-POSITION 33.3><C+POSITION 33.3><P><CBASELINE 0><CNOBREAK 0><CLEADING -0.05>
    369. 

  369.   <GGRID 0><GLEFT 7.2><GRIGHT 0><GFIRST 0><G+BEFORE 7.2><G+AFTER 0>
    370. 

  370.   <GALIGNMENT "justify"><GMETHOD "proportional"><G& "ENGLISH">
    371. 

  371.   <GPAIRS 12><G%% 120><GKNEXT 0><GKWIDOW 0><GKORPHAN 0><GTABS $>
    372. 

  372.   <GHYPHENATION 2 34 0><GWORDSPACE 75 100 150><GSPACE -5 0 25>
    373. 

  373. ><@Bullet=<@-PARENT "Normal"><FONT "Abadi MT Condensed Light">
    374. 

  374.   <GLEFT 14.4><G+BEFORE 2.15><G%% 110><GTABS(25.2 l "")>
    375. 

  375. ><@PreFormat=<@-PARENT "Normal"><FONT "Lucida Console"><SIZE 8><CTRACK 0>
    376. 

  376.   <GLEFT 0><G+BEFORE 0><GALIGNMENT "left"><GWORDSPACE 100 100 100><GSPACE 0 0 0>
    377. 

  377. ><@Title1=<@-PARENT "Normal"><FONT "Arial"><SIZE 14><B>
    378. 

  378.   <GCONTENTS><GLEFT 0><G+BEFORE 0><GALIGNMENT "left">
    379. 

  379. ><@Title2=<@-PARENT "Title1"><SIZE 12><G+BEFORE 3.6>
    380. 

  380. ><@Title3=<@-PARENT "Title1"><SIZE 10><GLEFT 7.2><G+BEFORE 7.2>
    381. 

  381. ><@Title4=<@-PARENT "Title3">
    382. 

  382. ><@Title5=<@-PARENT "Title3">
    383. 

  383. ><@Quote=<@-PARENT "Normal"><SIZE 10><I>>
    384. 

  384. 

  385. %(HEADER1)s
    386. 

  386. %(HEADER2)s
    387. 

  387. %(HEADER3)s
    388. 

  388. """,
    389. 

    390. 

  390.   'mgp': """\
    391. 

  391. #!/usr/X11R6/bin/mgp -t 90
    392. 

  392. %%deffont "normal"    xfont  "utopia-medium-r", charset "iso8859-1"
    393. 

  393. %%deffont "normal-i"  xfont  "utopia-medium-i", charset "iso8859-1"
    394. 

  394. %%deffont "normal-b"  xfont  "utopia-bold-r"  , charset "iso8859-1"
    395. 

  395. %%deffont "normal-bi" xfont  "utopia-bold-i"  , charset "iso8859-1"
    396. 

  396. %%deffont "mono"      xfont "courier-medium-r", charset "iso8859-1"
    397. 

  397. %%default 1 size 5
    398. 

  398. %%default 2 size 8, fore "yellow", font "normal-b", center
    399. 

  399. %%default 3 size 5, fore "white",  font "normal", left, prefix "  "
    400. 

  400. %%tab 1 size 4, vgap 30, prefix "     ", icon arc "red" 40, leftfill
    401. 

  401. %%tab 2 prefix "            ", icon arc "orange" 40, leftfill
    402. 

  402. %%tab 3 prefix "                   ", icon arc "brown" 40, leftfill
    403. 

  403. %%tab 4 prefix "                          ", icon arc "darkmagenta" 40, leftfill
    404. 

  404. %%tab 5 prefix "                                ", icon arc "magenta" 40, leftfill
    405. 

  405. %%%%------------------------- end of headers -----------------------------
    406. 

  406. %%page
    407. 

  407. 

  408. 

  409. 

  410. 

  411. 

  412. %%size 10, center, fore "yellow"
    413. 

  413. %(HEADER1)s
    414. 

  414. 

  415. %%font "normal-i", size 6, fore "white", center
    416. 

  416. %(HEADER2)s
    417. 

  417. 

  418. %%font "mono", size 7, center
    419. 

  419. %(HEADER3)s
    420. 

  420. """,
    421. 

    422. 

  422.   'moin': """\
    423. 

  423. '''%(HEADER1)s'''
    424. 

  424. 

  425. ''%(HEADER2)s''
    426. 

  426. 

  427. %(HEADER3)s
    428. 

  428. """,
    429. 

    430. 

  430.   'tex': \
    431. 

  431. r"""\documentclass{article}
    432. 

  432. \usepackage{graphicx}
    433. 

  433. \usepackage[urlcolor=blue,colorlinks=true]{hyperref}
    434. 

  434. \usepackage[%(ENCODING)s]{inputenc}  %% char encoding
    435. 

  435. \usepackage{%(STYLE)s}  %% user defined
    436. 

  436. 

  437. \title{%(HEADER1)s}
    438. 

  438. \author{%(HEADER2)s}
    439. 

  439. \begin{document}
    440. 

  440. \date{%(HEADER3)s}
    441. 

  441. \maketitle
    442. 

  442. \clearpage
    443. 

  443. """,
    444. 

    445. 

  445.   'lout': """\
    446. 

  446. @SysInclude { doc }
    447. 

  447. @Document
    448. 

  448.   @InitialFont { Times Base 12p }  # Times, Courier, Helvetica, ...
    449. 

  449.   @PageOrientation { Portrait }    # Portrait, Landscape
    450. 

  450.   @ColumnNumber { 1 }              # Number of columns (2, 3, ...)
    451. 

  451.   @PageHeaders { Simple }          # None, Simple, Titles, NoTitles
    452. 

  452.   @InitialLanguage { English }     # German, French, Portuguese, ...
    453. 

  453.   @OptimizePages { Yes }           # Yes/No smart page break feature
    454. 

  454. //
    455. 

  455. @Text @Begin
    456. 

  456. @Display @Heading { %(HEADER1)s }
    457. 

  457. @Display @I { %(HEADER2)s }
    458. 

  458. @Display { %(HEADER3)s }
    459. 

  459. #@NP                               # Break page after Headers
    460. 

  460. """
    461. 

  461. # @SysInclude { tbl }                   # Tables support
    462. 

  462. # setup: @MakeContents { Yes }          # show TOC
    463. 

  463. # setup: @SectionGap                    # break page at each section
    464. 

  464. }
    465. 

  465. 

  466. 

  467. ##############################################################################
    468. 

  468. 

  469. 

  470. def getTags(config):
    471. 

  471. 	"Returns all the known tags for the specified target"
    472. 

  472. 	
    473. 

  473. 	keys = [
    474. 

  474. 	'paragraphOpen','paragraphClose',
    475. 

  475. 	'title1','title2','title3','title4','title5',
    476. 

  476. 	'title1Open','title1Close','title2Open','title2Close',
    477. 

  477. 	'blocktitle1Open','title1Close','title2Open','title2Close',
    478. 

  478. 	'title3Open','title3Close','title4Open','title4Close',
    479. 

  479. 	'title5Open','title5Close',
    480. 

  480. 	'numtitle1','numtitle2','numtitle3','numtitle4','numtitle5',
    481. 

  481. 	'blockVerbOpen','blockVerbClose',
    482. 

  482. 	'blockQuoteOpen','blockQuoteClose','blockQuoteLine',
    483. 

  483. 	'blockCommentOpen','blockCommentClose',
    484. 

  484. 	'fontMonoOpen','fontMonoClose',
    485. 

  485. 	'fontBoldOpen','fontBoldClose',
    486. 

  486. 	'fontItalicOpen','fontItalicClose',
    487. 

  487. 	'fontUnderlineOpen','fontUnderlineClose',
    488. 

  488. 	'listOpen','listClose',
    489. 

  489. 	'listItemOpen','listItemClose','listItemLine',
    490. 

  490. 	'numlistOpen','numlistClose',
    491. 

  491. 	'numlistItemOpen','numlistItemClose','numlistItemLine',
    492. 

  492. 	'deflistOpen','deflistClose',
    493. 

  493. 	'deflistItem1Open','deflistItem1Close',
    494. 

  494. 	'deflistItem2Open','deflistItem2Close',
    495. 

  495. 	'bar1','bar2',
    496. 

  496. 	'url','urlMark','email','emailMark',
    497. 

  497. 	'img','imgAlignLeft','imgAlignRight','imgAlignCenter',
    498. 

  498. 	'tableOpen','tableClose',
    499. 

  499. 	'tableRowOpen','tableRowClose','tableRowSep',
    500. 

  500. 	'tableCellOpen','tableCellClose','tableCellSep',
    501. 

  501. 	'tableTitleCellOpen','tableTitleCellClose','tableTitleCellSep',
    502. 

  502. 	'tableTitleRowOpen','tableTitleRowClose',
    503. 

  503. 	'tableBorder', 'tableAlignLeft', 'tableAlignCenter',
    504. 

  504. 	'tableCellAlignLeft','tableCellAlignRight','tableCellAlignCenter',
    505. 

  505. 	'tableColAlignLeft','tableColAlignRight','tableColAlignCenter',
    506. 

  506. 	'tableColAlignSep', 'tableCellColSpan',
    507. 

  507. 	'anchor','comment','pageBreak',
    508. 

  508. 	'TOC','tocOpen','tocClose',
    509. 

  509. 	'cssOpen', 'cssClose',
    510. 

  510. 	'bodyOpen','bodyClose',
    511. 

  511. 	'EOD'
    512. 

  512. 	]
    513. 

  513. 	
    514. 

  514. 	# TIP: \a represents the current text on the mark
    515. 

  515. 	# TIP: ~A~, ~B~ and ~C~ are expanded to other tags parts
    516. 

  516. 	
    517. 

  517. 	alltags = {
    518. 

  518. 	
    519. 

  519. 	'txt': {
    520. 

  520. 	   'title1'              : '  \a'      ,
    521. 

  521. 	   'title2'              : '\t\a'      ,
    522. 

  522. 	   'title3'              : '\t\t\a'    ,
    523. 

  523. 	   'title4'              : '\t\t\t\a'  ,
    524. 

  524. 	   'title5'              : '\t\t\t\t\a',
    525. 

  525. 	   'blockQuoteLine'      : '\t'        ,
    526. 

  526. 	   'listItemOpen'        : '- '        ,
    527. 

  527. 	   'numlistItemOpen'     : '\a. '      ,
    528. 

  528. 	   'bar1'                : '\a'        ,
    529. 

  529. 	   'url'                 : '\a'        ,
    530. 

  530. 	   'urlMark'             : '\a (\a)'   ,
    531. 

  531. 	   'email'               : '\a'        ,
    532. 

  532. 	   'emailMark'           : '\a (\a)'   ,
    533. 

  533. 	   'img'                 : '[\a]'      ,
    534. 

  534. 	},
    535. 

  535. 	
    536. 

  536. 	'html': {
    537. 

  537. 	   'paragraphOpen'       : '<P>'            ,
    538. 

  538. 	   'paragraphClose'      : '</P>'           ,
    539. 

  539. 	   'title1'              : '~A~<H1>\a</H1>' ,
    540. 

  540. 	   'title2'              : '~A~<H2>\a</H2>' ,
    541. 

  541. 	   'title3'              : '~A~<H3>\a</H3>' ,
    542. 

  542. 	   'title4'              : '~A~<H4>\a</H4>' ,
    543. 

  543. 	   'title5'              : '~A~<H5>\a</H5>' ,
    544. 

  544. 	   'blockVerbOpen'       : '<PRE>'          ,
    545. 

  545. 	   'blockVerbClose'      : '</PRE>'         ,
    546. 

  546. 	   'blockQuoteOpen'      : '<BLOCKQUOTE>'   ,
    547. 

  547. 	   'blockQuoteClose'     : '</BLOCKQUOTE>'  ,
    548. 

  548. 	   'fontMonoOpen'        : '<CODE>'         ,
    549. 

  549. 	   'fontMonoClose'       : '</CODE>'        ,
    550. 

  550. 	   'fontBoldOpen'        : '<B>'            ,
    551. 

  551. 	   'fontBoldClose'       : '</B>'           ,
    552. 

  552. 	   'fontItalicOpen'      : '<I>'            ,
    553. 

  553. 	   'fontItalicClose'     : '</I>'           ,
    554. 

  554. 	   'fontUnderlineOpen'   : '<U>'            ,
    555. 

  555. 	   'fontUnderlineClose'  : '</U>'           ,
    556. 

  556. 	   'listOpen'            : '<UL>'           ,
    557. 

  557. 	   'listClose'           : '</UL>'          ,
    558. 

  558. 	   'listItemOpen'        : '<LI>'           ,
    559. 

  559. 	   'numlistOpen'         : '<OL>'           ,
    560. 

  560. 	   'numlistClose'        : '</OL>'          ,
    561. 

  561. 	   'numlistItemOpen'     : '<LI>'           ,
    562. 

  562. 	   'deflistOpen'         : '<DL>'           ,
    563. 

  563. 	   'deflistClose'        : '</DL>'          ,
    564. 

  564. 	   'deflistItem1Open'    : '<DT>'           ,
    565. 

  565. 	   'deflistItem1Close'   : '</DT>'          ,
    566. 

  566. 	   'deflistItem2Open'    : '<DD>'           ,
    567. 

  567. 	   'bar1'                : '<HR NOSHADE SIZE=1>'        ,
    568. 

  568. 	   'bar2'                : '<HR NOSHADE SIZE=5>'        ,
    569. 

  569. 	   'url'                 : '<A HREF="\a">\a</A>'        ,
    570. 

  570. 	   'urlMark'             : '<A HREF="\a">\a</A>'        ,
    571. 

  571. 	   'email'               : '<A HREF="mailto:\a">\a</A>' ,
    572. 

  572. 	   'emailMark'           : '<A HREF="mailto:\a">\a</A>' ,
    573. 

  573. 	   'img'                 : '<IMG~A~ SRC="\a" BORDER="0" ALT="">',
    574. 

  574. 	   'imgAlignLeft'        : ' ALIGN="left"'  ,
    575. 

  575. 	   'imgAlignCenter'      : ' ALIGN="middle"',
    576. 

  576. 	   'imgAlignRight'       : ' ALIGN="right"' ,
    577. 

  577. 	   'tableOpen'           : '<TABLE~A~ CELLPADDING="4"~B~>',
    578. 

  578. 	   'tableClose'          : '</TABLE>'       ,
    579. 

  579. 	   'tableRowOpen'        : '<TR>'           ,
    580. 

  580. 	   'tableRowClose'       : '</TR>'          ,
    581. 

  581. 	   'tableCellOpen'       : '<TD~A~~S~>'      ,
    582. 

  582. 	   'tableCellClose'      : '</TD>'          ,
    583. 

  583. 	   'tableTitleCellOpen'  : '<TH~S~>'        ,
    584. 

  584. 	   'tableTitleCellClose' : '</TH>'          ,
    585. 

  585. 	   'tableBorder'         : ' BORDER="1"'    ,
    586. 

  586. 	   'tableAlignCenter'    : ' ALIGN="center"',
    587. 

  587. 	   'tableCellAlignRight' : ' ALIGN="right"' ,
    588. 

  588. 	   'tableCellAlignCenter': ' ALIGN="center"',
    589. 

  589. 	   'tableCellColSpan'    : ' COLSPAN="\a"'  ,
    590. 

  590. 	   'anchor'              : '<A NAME="\a"></A>\n',
    591. 

  591. 	   'cssOpen'             : '<STYLE TYPE="text/css">',
    592. 

  592. 	   'cssClose'            : '</STYLE>'       ,
    593. 

  593. 	   'comment'             : '<!-- \a -->'    ,
    594. 

  594. 	   'EOD'                 : '</BODY></HTML>'
    595. 

  595. 	},
    596. 

  596. 	
    597. 

  597. 	#TIP xhtml inherits all HTML definitions (lowercased)
    598. 

  598. 	#TIP http://www.w3.org/TR/xhtml1/#guidelines
    599. 

  599. 	#TIP http://www.htmlref.com/samples/Chapt17/17_08.htm
    600. 

  600. 	'xhtml': {
    601. 

  601. 	   'listItemClose'       : '</li>'          ,
    602. 

  602. 	   'numlistItemClose'    : '</li>'          ,
    603. 

  603. 	   'deflistItem2Close'   : '</dd>'          ,
    604. 

  604. 	   'bar1'                : '<hr class="light" />',
    605. 

  605. 	   'bar2'                : '<hr class="heavy" />',
    606. 

  606. 	   'anchor'              : '<a id="\a" name="\a"></a>\n',
    607. 

  607. 	   'img'                 : '<img~A~ src="\a" border="0" alt=""/>',
    608. 

  608. 	},
    609. 

  609. 	
    610. 

  610. 	'sgml': {
    611. 

  611. 	   'paragraphOpen'       : '<p>'                ,
    612. 

  612. 	   'title1'              : '<sect>\a~A~<p>'     ,
    613. 

  613. 	   'title2'              : '<sect1>\a~A~<p>'    ,
    614. 

  614. 	   'title3'              : '<sect2>\a~A~<p>'    ,
    615. 

  615. 	   'title4'              : '<sect3>\a~A~<p>'    ,
    616. 

  616. 	   'title5'              : '<sect4>\a~A~<p>'    ,
    617. 

  617. 	   'blockVerbOpen'       : '<tscreen><verb>'    ,
    618. 

  618. 	   'blockVerbClose'      : '</verb></tscreen>'  ,
    619. 

  619. 	   'blockQuoteOpen'      : '<quote>'            ,
    620. 

  620. 	   'blockQuoteClose'     : '</quote>'           ,
    621. 

  621. 	   'fontMonoOpen'        : '<tt>'               ,
    622. 

  622. 	   'fontMonoClose'       : '</tt>'              ,
    623. 

  623. 	   'fontBoldOpen'        : '<bf>'               ,
    624. 

  624. 	   'fontBoldClose'       : '</bf>'              ,
    625. 

  625. 	   'fontItalicOpen'      : '<em>'               ,
    626. 

  626. 	   'fontItalicClose'     : '</em>'              ,
    627. 

  627. 	   'fontUnderlineOpen'   : '<bf><em>'           ,
    628. 

  628. 	   'fontUnderlineClose'  : '</em></bf>'         ,
    629. 

  629. 	   'listOpen'            : '<itemize>'          ,
    630. 

  630. 	   'listClose'           : '</itemize>'         ,
    631. 

  631. 	   'listItemOpen'        : '<item>'             ,
    632. 

  632. 	   'numlistOpen'         : '<enum>'             ,
    633. 

  633. 	   'numlistClose'        : '</enum>'            ,
    634. 

  634. 	   'numlistItemOpen'     : '<item>'             ,
    635. 

  635. 	   'deflistOpen'         : '<descrip>'          ,
    636. 

  636. 	   'deflistClose'        : '</descrip>'         ,
    637. 

  637. 	   'deflistItem1Open'    : '<tag>'              ,
    638. 

  638. 	   'deflistItem1Close'   : '</tag>'             ,
    639. 

  639. 	   'bar1'                : '<!-- \a -->'        ,
    640. 

  640. 	   'url'                 : '<htmlurl url="\a" name="\a">'        ,
    641. 

  641. 	   'urlMark'             : '<htmlurl url="\a" name="\a">'        ,
    642. 

  642. 	   'email'               : '<htmlurl url="mailto:\a" name="\a">' ,
    643. 

  643. 	   'emailMark'           : '<htmlurl url="mailto:\a" name="\a">' ,
    644. 

  644. 	   'img'                 : '<figure><ph vspace=""><img src="\a">'+\
    645. 

  645. 	                           '</figure>'                           ,
    646. 

  646. 	   'tableOpen'           : '<table><tabular ca="~C~">'           ,
    647. 

  647. 	   'tableClose'          : '</tabular></table>' ,
    648. 

  648. 	   'tableRowSep'         : '<rowsep>'           ,
    649. 

  649. 	   'tableCellSep'        : '<colsep>'           ,
    650. 

  650. 	   'tableColAlignLeft'   : 'l'                  ,
    651. 

  651. 	   'tableColAlignRight'  : 'r'                  ,
    652. 

  652. 	   'tableColAlignCenter' : 'c'                  ,
    653. 

  653. 	   'comment'             : '<!-- \a -->'        ,
    654. 

  654. 	   'anchor'              : '<label id="\a">'    ,
    655. 

  655. 	   'TOC'                 : '<toc>'              ,
    656. 

  656. 	   'EOD'                 : '</article>'
    657. 

  657. 	},
    658. 

  658. 	
    659. 

  659. 	'tex': {
    660. 

  660. 	   'title1'              : '\n\section*{\a}'     ,
    661. 

  661. 	   'title2'              : '\\subsection*{\a}'   ,
    662. 

  662. 	   'title3'              : '\\subsubsection*{\a}',
    663. 

  663. 	   # title 4/5: DIRTY: para+BF+\\+\n
    664. 

  664. 	   'title4'              : '\\paragraph{}\\textbf{\a}\\\\\n',
    665. 

  665. 	   'title5'              : '\\paragraph{}\\textbf{\a}\\\\\n',
    666. 

  666. 	   'numtitle1'           : '\n\section{\a}'      ,
    667. 

  667. 	   'numtitle2'           : '\\subsection{\a}'    ,
    668. 

  668. 	   'numtitle3'           : '\\subsubsection{\a}' ,
    669. 

  669. 	   'blockVerbOpen'       : '\\begin{verbatim}'   ,
    670. 

  670. 	   'blockVerbClose'      : '\\end{verbatim}'     ,
    671. 

  671. 	   'blockQuoteOpen'      : '\\begin{quotation}'  ,
    672. 

  672. 	   'blockQuoteClose'     : '\\end{quotation}'    ,
    673. 

  673. 	   'fontMonoOpen'        : '\\texttt{'           ,
    674. 

  674. 	   'fontMonoClose'       : '}'                   ,
    675. 

  675. 	   'fontBoldOpen'        : '\\textbf{'           ,
    676. 

  676. 	   'fontBoldClose'       : '}'                   ,
    677. 

  677. 	   'fontItalicOpen'      : '\\textit{'           ,
    678. 

  678. 	   'fontItalicClose'     : '}'                   ,
    679. 

  679. 	   'fontUnderlineOpen'   : '\\underline{'        ,
    680. 

  680. 	   'fontUnderlineClose'  : '}'                   ,
    681. 

  681. 	   'listOpen'            : '\\begin{itemize}'    ,
    682. 

  682. 	   'listClose'           : '\\end{itemize}'      ,
    683. 

  683. 	   'listItemOpen'        : '\\item '             ,
    684. 

  684. 	   'numlistOpen'         : '\\begin{enumerate}'  ,
    685. 

  685. 	   'numlistClose'        : '\\end{enumerate}'    ,
    686. 

  686. 	   'numlistItemOpen'     : '\\item '             ,
    687. 

  687. 	   'deflistOpen'         : '\\begin{description}',
    688. 

  688. 	   'deflistClose'        : '\\end{description}'  ,
    689. 

  689. 	   'deflistItem1Open'    : '\\item['             ,
    690. 

  690. 	   'deflistItem1Close'   : ']'                   ,
    691. 

  691. 	   'bar1'                : '\n\\hrulefill{}\n'   ,
    692. 

  692. 	   'bar2'                : '\n\\rule{\linewidth}{1mm}\n',
    693. 

  693. 	   'url'                 : '\\htmladdnormallink{\a}{\a}',
    694. 

  694. 	   'urlMark'             : '\\htmladdnormallink{\a}{\a}',
    695. 

  695. 	   'email'               : '\\htmladdnormallink{\a}{mailto:\a}',
    696. 

  696. 	   'emailMark'           : '\\htmladdnormallink{\a}{mailto:\a}',
    697. 

  697. 	   'img'                 : '\\includegraphics{\a}',
    698. 

  698. 	   'tableOpen'           : '\\begin{center}\\begin{tabular}{|~C~|}',
    699. 

  699. 	   'tableClose'          : '\\end{tabular}\\end{center}',
    700. 

  700. 	   'tableRowOpen'        : '\\hline ' ,
    701. 

  701. 	   'tableRowClose'       : ' \\\\'    ,
    702. 

  702. 	   'tableCellSep'        : ' & '      ,
    703. 

  703. 	   'tableColAlignLeft'   : 'l'        ,
    704. 

  704. 	   'tableColAlignRight'  : 'r'        ,
    705. 

  705. 	   'tableColAlignCenter' : 'c'        ,
    706. 

  706. 	   'tableColAlignSep'    : '|'        ,
    707. 

  707. 	   'comment'             : '% \a'     ,
    708. 

  708. 	   'TOC'                 : '\\tableofcontents',
    709. 

  709. 	   'pageBreak'           : '\\clearpage',
    710. 

  710. 	   'EOD'                 : '\\end{document}'
    711. 

  711. 	},
    712. 

  712. 	
    713. 

  713. 	'lout': {
    714. 

  714. 	   'paragraphOpen'       : '@LP'                     ,
    715. 

  715. 	   'blockTitle1Open'     : '@BeginSections'          ,
    716. 

  716. 	   'blockTitle1Close'    : '@EndSections'            ,
    717. 

  717. 	   'blockTitle2Open'     : ' @BeginSubSections'      ,
    718. 

  718. 	   'blockTitle2Close'    : ' @EndSubSections'        ,
    719. 

  719. 	   'blockTitle3Open'     : '  @BeginSubSubSections'  ,
    720. 

  720. 	   'blockTitle3Close'    : '  @EndSubSubSections'    ,
    721. 

  721. 	   'title1Open'          : '\n@Section @Title { \a } @Begin',
    722. 

  722. 	   'title1Close'         : '@End @Section'           ,
    723. 

  723. 	   'title2Open'          : '\n @SubSection @Title { \a } @Begin',
    724. 

  724. 	   'title2Close'         : ' @End @SubSection'       ,
    725. 

  725. 	   'title3Open'          : '\n  @SubSubSection @Title { \a } @Begin',
    726. 

  726. 	   'title3Close'         : '  @End @SubSubSection'   ,
    727. 

  727. 	   'title4Open'          : '\n@LP @LeftDisplay @B { \a }',
    728. 

  728. 	   'title5Open'          : '\n@LP @LeftDisplay @B { \a }',
    729. 

  729. 	   'anchor'              : '@Tag { \a }'             ,
    730. 

  730. 	   'blockVerbOpen'       : '@LP @ID @F @RawVerbatim @Begin',
    731. 

  731. 	   'blockVerbClose'      : '@End @RawVerbatim'   ,
    732. 

  732. 	   'blockQuoteOpen'      : '@QD {'               ,
    733. 

  733. 	   'blockQuoteClose'     : '}'                   ,
    734. 

  734. 	   # enclosed inside {} to deal with joined**words**
    735. 

  735. 	   'fontMonoOpen'        : '{@F {'               ,
    736. 

  736. 	   'fontMonoClose'       : '}}'                  ,
    737. 

  737. 	   'fontBoldOpen'        : '{@B {'               ,
    738. 

  738. 	   'fontBoldClose'       : '}}'                  ,
    739. 

  739. 	   'fontItalicOpen'      : '{@II {'              ,
    740. 

  740. 	   'fontItalicClose'     : '}}'                  ,
    741. 

  741. 	   'fontUnderlineOpen'   : '{@Underline{'        ,
    742. 

  742. 	   'fontUnderlineClose'  : '}}'                  ,
    743. 

  743. 	   # the full form is more readable, but could be BL EL LI NL TL DTI
    744. 

  744. 	   'listOpen'            : '@BulletList'         ,
    745. 

  745. 	   'listClose'           : '@EndList'            ,
    746. 

  746. 	   'listItemOpen'        : '@ListItem{'          ,
    747. 

  747. 	   'listItemClose'       : '}'                   ,
    748. 

  748. 	   'numlistOpen'         : '@NumberedList'       ,
    749. 

  749. 	   'numlistClose'        : '@EndList'            ,
    750. 

  750. 	   'numlistItemOpen'     : '@ListItem{'          ,
    751. 

  751. 	   'numlistItemClose'    : '}'                   ,
    752. 

  752. 	   'deflistOpen'         : '@TaggedList'         ,
    753. 

  753. 	   'deflistClose'        : '@EndList'            ,
    754. 

  754. 	   'deflistItem1Open'    : '@DropTagItem {'      ,
    755. 

  755. 	   'deflistItem1Close'   : '}'                   ,
    756. 

  756. 	   'deflistItem2Open'    : '{'                   ,
    757. 

  757. 	   'deflistItem2Close'   : '}'                   ,
    758. 

  758. 	   'bar1'                : '\n@DP @FullWidthRule\n'     ,
    759. 

  759. 	   'url'                 : '{blue @Colour { \a }}'      ,
    760. 

  760. 	   'urlMark'             : '\a ({blue @Colour { \a }})' ,
    761. 

  761. 	   'email'               : '{blue @Colour { \a }}'      ,
    762. 

  762. 	   'emailMark'           : '\a ({blue Colour{ \a }})'   ,
    763. 

  763. 	   'img'                 : '~A~@IncludeGraphic { \a }'  ,  # eps only!
    764. 

  764. 	   'imgAlignLeft'        : '@LeftDisplay '              ,
    765. 

  765. 	   'imgAlignRight'       : '@RightDisplay '             ,
    766. 

  766. 	   'imgAlignCenter'      : '@CentredDisplay '           ,
    767. 

  767. 	   # lout tables are *way* complicated, no support for now
    768. 

  768. 	   #'tableOpen'          : '~A~@Tbl~B~\naformat{ @Cell A | @Cell B } {',
    769. 

  769. 	   #'tableClose'         : '}'     ,
    770. 

  770. 	   #'tableRowOpen'       : '@Rowa\n'       ,
    771. 

  771. 	   #'tableTitleRowOpen'  : '@HeaderRowa'       ,
    772. 

  772. 	   #'tableCenterAlign'   : '@CentredDisplay '         ,
    773. 

  773. 	   #'tableCellOpen'      : '\a {'                     ,  # A, B, ...
    774. 

  774. 	   #'tableCellClose'     : '}'                        ,
    775. 

  775. 	   #'tableBorder'        : '\nrule {yes}'             ,
    776. 

  776. 	   'comment'             : '# \a'                     ,
    777. 

  777. 	   # @MakeContents must be on the config file
    778. 

  778. 	   'TOC'                 : '@DP @ContentsGoesHere @DP',
    779. 

  779. 	   'pageBreak'           : '\n@NP\n'                  ,
    780. 

  780. 	   'EOD'                 : '@End @Text'
    781. 

  781. 	},
    782. 

  782. 	
    783. 

  783. 	'moin': {
    784. 

  784. 	   'title1'              : '= \a ='        ,
    785. 

  785. 	   'title2'              : '== \a =='      ,
    786. 

  786. 	   'title3'              : '=== \a ==='    ,
    787. 

  787. 	   'title4'              : '==== \a ===='  ,
    788. 

  788. 	   'title5'              : '===== \a =====',
    789. 

  789. 	   'blockVerbOpen'       : '{{{'           ,
    790. 

  790. 	   'blockVerbClose'      : '}}}'           ,
    791. 

  791. 	   'blockQuoteLine'      : '  '            ,
    792. 

  792. 	   'fontMonoOpen'        : '{{{'           ,
    793. 

  793. 	   'fontMonoClose'       : '}}}'           ,
    794. 

  794. 	   'fontBoldOpen'        : "'''"           ,
    795. 

  795. 	   'fontBoldClose'       : "'''"           ,
    796. 

  796. 	   'fontItalicOpen'      : "''"            ,
    797. 

  797. 	   'fontItalicClose'     : "''"            ,
    798. 

  798. 	   'fontUnderlineOpen'   : "__"            ,
    799. 

  799. 	   'fontUnderlineClose'  : "__"            ,
    800. 

  800. 	   'listItemOpen'        : ' * '           ,
    801. 

  801. 	   'numlistItemOpen'     : ' \a. '         ,
    802. 

  802. 	   'bar1'                : '----'          ,
    803. 

  803. 	   'url'                 : '[\a]'          ,
    804. 

  804. 	   'urlMark'             : '[\a \a]'       ,
    805. 

  805. 	   'email'               : '[\a]'          ,
    806. 

  806. 	   'emailMark'           : '[\a \a]'       ,
    807. 

  807. 	   'img'                 : '[\a]'          ,
    808. 

  808. 	   'tableRowOpen'        : '||'            ,
    809. 

  809. 	   'tableCellOpen'       : '~A~'           ,
    810. 

  810. 	   'tableCellClose'      : '||'            ,
    811. 

  811. 	   'tableTitleCellClose' : '||'            ,
    812. 

  812. 	   'tableCellAlignRight' : '<)>'           ,
    813. 

  813. 	   'tableCellAlignCenter': '<:>'           ,
    814. 

  814. 	   'comment'             : '## \a'         ,
    815. 

  815. 	   'TOC'                 : '[[TableOfContents]]'
    816. 

  816. 	},
    817. 

  817. 	
    818. 

  818. 	'mgp': {
    819. 

  819. 	   'paragraphOpen'       : '%font "normal", size 5'     ,
    820. 

  820. 	   'title1'              : '%page\n\n\a\n'              ,
    821. 

  821. 	   'title2'              : '%page\n\n\a\n'              ,
    822. 

  822. 	   'title3'              : '%page\n\n\a\n'              ,
    823. 

  823. 	   'title4'              : '%page\n\n\a\n'              ,
    824. 

  824. 	   'title5'              : '%page\n\n\a\n'              ,
    825. 

  825. 	   'blockVerbOpen'       : '%font "mono"'               ,
    826. 

  826. 	   'blockVerbClose'      : '%font "normal"'             ,
    827. 

  827. 	   'blockQuoteOpen'      : '%prefix "       "'          ,
    828. 

  828. 	   'blockQuoteClose'     : '%prefix "  "'               ,
    829. 

  829. 	   'fontMonoOpen'        : '\n%cont, font "mono"\n'     ,
    830. 

  830. 	   'fontMonoClose'       : '\n%cont, font "normal"\n'   ,
    831. 

  831. 	   'fontBoldOpen'        : '\n%cont, font "normal-b"\n' ,
    832. 

  832. 	   'fontBoldClose'       : '\n%cont, font "normal"\n'   ,
    833. 

  833. 	   'fontItalicOpen'      : '\n%cont, font "normal-i"\n' ,
    834. 

  834. 	   'fontItalicClose'     : '\n%cont, font "normal"\n'   ,
    835. 

  835. 	   'fontUnderlineOpen'   : '\n%cont, fore "cyan"\n'     ,
    836. 

  836. 	   'fontUnderlineClose'  : '\n%cont, fore "white"\n'    ,
    837. 

  837. 	   'listItemLine'        : '\t'                         ,
    838. 

  838. 	   'numlistItemLine'     : '\t'                         ,
    839. 

  839. 	   'deflistItem1Open'    : '\t\n%cont, font "normal-b"\n',
    840. 

  840. 	   'deflistItem1Close'   : '\n%cont, font "normal"\n'   ,
    841. 

  841. 	   'bar1'                : '%bar "white" 5'             ,
    842. 

  842. 	   'bar2'                : '%pause'                     ,
    843. 

  843. 	   'url'                 : '\n%cont, fore "cyan"\n\a'   +\
    844. 

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

  845. 	   'urlMark'             : '\a \n%cont, fore "cyan"\n\a'+\
    846. 

  846. 	                           '\n%cont, fore "white"\n'    ,
    847. 

  847. 	   'email'               : '\n%cont, fore "cyan"\n\a'   +\
    848. 

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

  849. 	   'emailMark'           : '\a \n%cont, fore "cyan"\n\a'+\
    850. 

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

  851. 	   'img'                 : '~A~\n%newimage "\a"\n%left\n',
    852. 

  852. 	   'imgAlignLeft'        : '\n%left'                    ,
    853. 

  853. 	   'imgAlignRight'       : '\n%right'                   ,
    854. 

  854. 	   'imgAlignCenter'      : '\n%center'                  ,
    855. 

  855. 	   'comment'             : '%% \a'                      ,
    856. 

  856. 	   'pageBreak'           : '%page\n\n\n'                ,
    857. 

  857. 	   'EOD'                 : '%%EOD'
    858. 

  858. 	},
    859. 

  859. 	
    860. 

  860. 	# man groff_man ; man 7 groff
    861. 

  861. 	'man': {
    862. 

  862. 	   'paragraphOpen'       : '.P'     ,
    863. 

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

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

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

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

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

  868. 	   'blockVerbOpen'       : '.nf'    ,
    869. 

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

  870. 	   'blockQuoteOpen'      : '.RS'    ,
    871. 

  871. 	   'blockQuoteClose'     : '.RE'    ,
    872. 

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

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

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

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

  876. 	   'listOpen'            : '.RS'    ,
    877. 

  877. 	   'listItemOpen'        : '.IP \(bu 3\n',
    878. 

  878. 	   'listClose'           : '.RE'    ,
    879. 

  879. 	   'numlistOpen'         : '.RS'    ,
    880. 

  880. 	   'numlistItemOpen'     : '.IP \a. 3\n',
    881. 

  881. 	   'numlistClose'        : '.RE'    ,
    882. 

  882. 	   'deflistItem1Open'    : '.TP\n'  ,
    883. 

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

  884. 	   'url'                 : '\a'     ,
    885. 

  885. 	   'urlMark'             : '\a (\a)',
    886. 

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

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

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

  889. 	   'tableOpen'           : '.TS\n~A~~B~tab(^); ~C~.',
    890. 

  890. 	   'tableClose'          : '.TE'     ,
    891. 

  891. 	   'tableRowOpen'        : ' '       ,
    892. 

  892. 	   'tableCellSep'        : '^'       ,
    893. 

  893. 	   'tableAlignCenter'    : 'center, ',
    894. 

  894. 	   'tableBorder'         : 'allbox, ',
    895. 

  895. 	   'tableColAlignLeft'   : 'l'       ,
    896. 

  896. 	   'tableColAlignRight'  : 'r'       ,
    897. 

  897. 	   'tableColAlignCenter' : 'c'       ,
    898. 

  898. 	   'comment'             : '.\\" \a'
    899. 

  899. 	},
    900. 

  900. 	
    901. 

  901. 	'pm6': {
    902. 

  902. 	   'paragraphOpen'       : '<@Normal:>'    ,
    903. 

  903. 	   'title1'              : '\n<@Title1:>\a',
    904. 

  904. 	   'title2'              : '\n<@Title2:>\a',
    905. 

  905. 	   'title3'              : '\n<@Title3:>\a',
    906. 

  906. 	   'title4'              : '\n<@Title4:>\a',
    907. 

  907. 	   'title5'              : '\n<@Title5:>\a',
    908. 

  908. 	   'blockVerbOpen'       : '<@PreFormat:>' ,
    909. 

  909. 	   'blockQuoteLine'      : '<@Quote:>'     ,
    910. 

  910. 	   'fontMonoOpen'        : '<FONT "Lucida Console"><SIZE 9>' ,
    911. 

  911. 	   'fontMonoClose'       : '<SIZE$><FONT$>',
    912. 

  912. 	   'fontBoldOpen'        : '<B>'           ,
    913. 

  913. 	   'fontBoldClose'       : '<P>'           ,
    914. 

  914. 	   'fontItalicOpen'      : '<I>'           ,
    915. 

  915. 	   'fontItalicClose'     : '<P>'           ,
    916. 

  916. 	   'fontUnderlineOpen'   : '<U>'           ,
    917. 

  917. 	   'fontUnderlineClose'  : '<P>'           ,
    918. 

  918. 	   'listOpen'            : '<@Bullet:>'    ,
    919. 

  919. 	   'listItemOpen'        : '\x95\t'        ,  # \x95 == ~U
    920. 

  920. 	   'numlistOpen'         : '<@Bullet:>'    ,
    921. 

  921. 	   'numlistItemOpen'     : '\x95\t'        ,
    922. 

  922. 	   'bar1'                : '\a'            ,
    923. 

  923. 	   'url'                 : '<U>\a<P>'      ,  # underline
    924. 

  924. 	   'urlMark'             : '\a <U>\a<P>'   ,
    925. 

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

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

  927. 	   'img'                 : '\a'
    928. 

  928. 	}
    929. 

  929. 	}
    930. 

  930. 	
    931. 

  931. 	# Exceptions for --css-sugar
    932. 

  932. 	if config['css-sugar'] and config['target'] in ('html','xhtml'):
    933. 

  933. 		# Change just HTML because XHTML inherits it
    934. 

  934. 		htmltags = alltags['html']
    935. 

  935. 		# Table with no cellpadding
    936. 

  936. 		htmltags['tableOpen'] = string.replace(
    937. 

  937. 			htmltags['tableOpen'], ' CELLPADDING="4"', '')
    938. 

  938. 		# DIVs
    939. 

  939. 		htmltags['tocOpen' ] = '<DIV CLASS="toc" ID="toc">'
    940. 

  940. 		htmltags['tocClose'] = '</DIV>'
    941. 

  941. 		htmltags['bodyOpen'] = '<DIV CLASS="body" ID="body">'
    942. 

  942. 		htmltags['bodyClose']= '</DIV>'
    943. 

  943. 	
    944. 

  944. 	# Make the HTML -> XHTML inheritance
    945. 

  945. 	xhtml = alltags['html'].copy()
    946. 

  946. 	for key in xhtml.keys(): xhtml[key] = string.lower(xhtml[key])
    947. 

  947. 	# Some like HTML tags as lowercase, some don't... (headers out)
    948. 

  948. 	if HTML_LOWER: alltags['html'] = xhtml.copy()
    949. 

  949. 	xhtml.update(alltags['xhtml'])
    950. 

  950. 	alltags['xhtml'] = xhtml.copy()
    951. 

  951. 	
    952. 

  952. 	# Compose the target tags dictionary
    953. 

  953. 	tags = {}
    954. 

  954. 	target_tags = alltags[config['target']].copy()
    955. 

  955. 	
    956. 

  956. 	for key in keys: tags[key] = ''     # create empty keys
    957. 

  957. 	for key in target_tags.keys():
    958. 

  958. 		tags[key] = maskEscapeChar(target_tags[key]) # populate
    959. 

  959. 	
    960. 

  960. 	# Map strong line to separator if not defined
    961. 

  961. 	if not tags['bar2'] and tags['bar1']:
    962. 

  962. 		tags['bar2'] = tags['bar1']
    963. 

  963. 	
    964. 

  964. 	return tags
    965. 

  965. 

  966. 

  967. ##############################################################################
    968. 

  968. 

  969. 

  970. def getRules(config):
    971. 

  971. 	"Returns all the target-specific syntax rules"
    972. 

  972. 	
    973. 

  973. 	ret = {}
    974. 

  974. 	allrules = [
    975. 

  975. 	
    976. 

  976. 	 # target rules (ON/OFF)
    977. 

  977. 	  'linkable',             # target supports external links
    978. 

  978. 	  'tableable',            # target supports tables
    979. 

  979. 	  'imglinkable',          # target supports images as links
    980. 

  980. 	  'imgalignable',         # target supports image alignment
    981. 

  981. 	  'imgasdefterm',         # target supports image as definition term
    982. 

  982. 	  'autonumberlist',       # target supports numbered lists natively
    983. 

  983. 	  'autonumbertitle',      # target supports numbered titles natively
    984. 

  984. 	  'stylable',             # target supports external style files
    985. 

  985. 	  'parainsidelist',       # lists items supports paragraph
    986. 

  986. 	  'spacedlistitem',       # lists support blank lines between items
    987. 

  987. 	  'listnotnested',        # lists cannot be nested
    988. 

  988. 	  'quotenotnested',       # quotes cannot be nested
    989. 

  989. 	  'verbblocknotescaped',  # don't escape specials in verb block
    990. 

  990. 	  'verbblockfinalescape', # do final escapes in verb block
    991. 

  991. 	  'escapeurl',            # escape special in link URL
    992. 

  992. 	  'onelinepara',          # dump paragraph as a single long line
    993. 

  993. 	  'tabletitlerowinbold',  # manually bold any cell on table titles
    994. 

  994. 	  'tablecellstrip',       # strip extra spaces from each table cell
    995. 

  995. 	  'tablecellspannable',   # the table cells can have span attribute
    996. 

  996. 	  'barinsidequote',       # bars are allowed inside quote blocks
    997. 

  997. 	  'finalescapetitle',     # perform final escapes on title lines
    998. 

  998. 	  'autotocnewpagebefore', # break page before automatic TOC
    999. 

  999. 	  'autotocnewpageafter',  # break page after automatic TOC
    1000. 

  1000. 	  'autotocwithbars',      # automatic TOC surrounded by bars
    1001. 

  1001. 	  'mapbar2pagebreak',     # map the strong bar to a page break
    1002. 

  1002. 	  'titleblocks',          # titles must be on open/close section blocks
    1003. 

  1003. 	
    1004. 

  1004. 	# Target code beautify (ON/OFF)
    1005. 

  1005. 	  'indentverbblock',      # add leading spaces to verb block lines
    1006. 

  1006. 	  'breaktablecell',       # break lines after any table cell
    1007. 

  1007. 	  'breaktablelineopen',   # break line after opening table line
    1008. 

  1008. 	  'notbreaklistopen',     # don't break line after opening a new list
    1009. 

  1009. 	  'notbreakparaopen',     # don't break line after opening a new para
    1010. 

  1010. 	  'keepquoteindent',      # don't remove the leading TABs on quotes
    1011. 

  1011. 	  'keeplistindent',       # don't remove the leading spaces on lists
    1012. 

  1012. 	  'blankendmotherlist',   # append a blank line at the mother list end
    1013. 

  1013. 	  'blankendtable',        # append a blank line at the table end
    1014. 

  1014. 	  'blankendautotoc',      # append a blank line at the auto TOC end
    1015. 

  1015. 	  'tagnotindentable',     # tags must be placed at the line begining
    1016. 

  1016. 	
    1017. 

  1017. 	# Value settings
    1018. 

  1018. 	  'listmaxdepth',         # maximum depth for lists
    1019. 

  1019. 	  'quotemaxdepth',        # maximum depth for quotes
    1020. 

  1020. 	  'tablecellaligntype'    # type of table cell align: cell, column
    1021. 

  1021. 	]
    1022. 

  1022. 	
    1023. 

  1023. 	rules_bank = {
    1024. 

  1024. 	  'txt' : {
    1025. 

  1025. 	    'indentverbblock':1,
    1026. 

  1026. 	    'spacedlistitem':1,
    1027. 

  1027. 	    'parainsidelist':1,
    1028. 

  1028. 	    'keeplistindent':1,
    1029. 

  1029. 	    'barinsidequote':1,
    1030. 

  1030. 	    'autotocwithbars':1,
    1031. 

  1031. 	    'blankendmotherlist':1
    1032. 

  1032. 	    },
    1033. 

  1033. 	  'html': {
    1034. 

  1034. 	    'indentverbblock':1,
    1035. 

  1035. 	    'linkable':1,
    1036. 

  1036. 	    'stylable':1,
    1037. 

  1037. 	    'escapeurl':1,
    1038. 

  1038. 	    'imglinkable':1,
    1039. 

  1039. 	    'imgalignable':1,
    1040. 

  1040. 	    'imgasdefterm':1,
    1041. 

  1041. 	    'autonumberlist':1,
    1042. 

  1042. 	    'spacedlistitem':1,
    1043. 

  1043. 	    'parainsidelist':1,
    1044. 

  1044. 	    'blankendmotherlist':1,
    1045. 

  1045. 	    'tableable':1,
    1046. 

  1046. 	    'tablecellstrip':1,
    1047. 

  1047. 	    'blankendtable':1,
    1048. 

  1048. 	    'breaktablecell':1,
    1049. 

  1049. 	    'breaktablelineopen':1,
    1050. 

  1050. 	    'keeplistindent':1,
    1051. 

  1051. 	    'keepquoteindent':1,
    1052. 

  1052. 	    'barinsidequote':1,
    1053. 

  1053. 	    'autotocwithbars':1,
    1054. 

  1054. 	    'tablecellspannable':1,
    1055. 

  1055. 	    'tablecellaligntype':'cell'
    1056. 

  1056. 	    },
    1057. 

  1057. 	  #TIP xhtml inherits all HTML rules
    1058. 

  1058. 	  'xhtml': {
    1059. 

  1059. 	    },
    1060. 

  1060. 	  'sgml': {
    1061. 

  1061. 	    'linkable':1,
    1062. 

  1062. 	    'escapeurl':1,
    1063. 

  1063. 	    'autonumberlist':1,
    1064. 

  1064. 	    'spacedlistitem':1,
    1065. 

  1065. 	    'blankendmotherlist':1,
    1066. 

  1066. 	    'tableable':1,
    1067. 

  1067. 	    'tablecellstrip':1,
    1068. 

  1068. 	    'blankendtable':1,
    1069. 

  1069. 	    'blankendautotoc':1,
    1070. 

  1070. 	    'quotenotnested':1,
    1071. 

  1071. 	    'keeplistindent':1,
    1072. 

  1072. 	    'keepquoteindent':1,
    1073. 

  1073. 	    'barinsidequote':1,
    1074. 

  1074. 	    'finalescapetitle':1,
    1075. 

  1075. 	    'tablecellaligntype':'column'
    1076. 

  1076. 	    },
    1077. 

  1077. 	  'mgp' : {
    1078. 

  1078. 	    'blankendmotherlist':1,
    1079. 

  1079. 	    'tagnotindentable':1,
    1080. 

  1080. 	    'spacedlistitem':1,
    1081. 

  1081. 	    'imgalignable':1,
    1082. 

  1082. 	    'autotocnewpagebefore':1,
    1083. 

  1083. 	    },
    1084. 

  1084. 	  'tex' : {
    1085. 

  1085. 	    'stylable':1,
    1086. 

  1086. 	    'escapeurl':1,
    1087. 

  1087. 	    'autonumberlist':1,
    1088. 

  1088. 	    'autonumbertitle':1,
    1089. 

  1089. 	    'spacedlistitem':1,
    1090. 

  1090. 	    'blankendmotherlist':1,
    1091. 

  1091. 	    'tableable':1,
    1092. 

  1092. 	    'tablecellstrip':1,
    1093. 

  1093. 	    'tabletitlerowinbold':1,
    1094. 

  1094. 	    'blankendtable':1,
    1095. 

  1095. 	    'verbblocknotescaped':1,
    1096. 

  1096. 	    'keeplistindent':1,
    1097. 

  1097. 	    'listmaxdepth':4,  # deflist is 6
    1098. 

  1098. 	    'quotemaxdepth':6,
    1099. 

  1099. 	    'barinsidequote':1,
    1100. 

  1100. 	    'finalescapetitle':1,
    1101. 

  1101. 	    'autotocnewpageafter':1,
    1102. 

  1102. 	    'mapbar2pagebreak':1,
    1103. 

  1103. 	    'tablecellaligntype':'column'
    1104. 

  1104. 	    },
    1105. 

  1105. 	  'lout': {
    1106. 

  1106. 	    'keepquoteindent':1,
    1107. 

  1107. 	    'escapeurl':1,
    1108. 

  1108. 	    'verbblocknotescaped':1,
    1109. 

  1109. 	    'imgalignable':1,
    1110. 

  1110. 	    'mapbar2pagebreak':1,
    1111. 

  1111. 	    'titleblocks':1,
    1112. 

  1112. 	    'notbreakparaopen':1
    1113. 

  1113. 	    },
    1114. 

  1114. 	  'moin': {
    1115. 

  1115. 	    'spacedlistitem':1,
    1116. 

  1116. 	    'linkable':1,
    1117. 

  1117. 	    'blankendmotherlist':1,
    1118. 

  1118. 	    'keeplistindent':1,
    1119. 

  1119. 	    'tableable':1,
    1120. 

  1120. 	    'barinsidequote':1,
    1121. 

  1121. 	    'blankendtable':1,
    1122. 

  1122. 	    'tabletitlerowinbold':1,
    1123. 

  1123. 	    'tablecellstrip':1,
    1124. 

  1124. 	    'autotocwithbars':1,
    1125. 

  1125. 	    'tablecellaligntype':'cell'
    1126. 

  1126. 	    },
    1127. 

  1127. 	  'man' : {
    1128. 

  1128. 	    'spacedlistitem':1,
    1129. 

  1129. 	    'indentverbblock':1,
    1130. 

  1130. 	    'blankendmotherlist':1,
    1131. 

  1131. 	    'tagnotindentable':1,
    1132. 

  1132. 	    'tableable':1,
    1133. 

  1133. 	    'tablecellaligntype':'column',
    1134. 

  1134. 	    'tabletitlerowinbold':1,
    1135. 

  1135. 	    'tablecellstrip':1,
    1136. 

  1136. 	    'blankendtable':1,
    1137. 

  1137. 	    'keeplistindent':0,
    1138. 

  1138. 	    'barinsidequote':1,
    1139. 

  1139. 	    'parainsidelist':0,
    1140. 

  1140. 	    },
    1141. 

  1141. 	  'pm6' : {
    1142. 

  1142. 	    'keeplistindent':1,
    1143. 

  1143. 	    'verbblockfinalescape':1,
    1144. 

  1144. 	    #TODO add support for these - maybe set a JOINNEXT char and
    1145. 

  1145. 	    #     do it on addLineBreaks()
    1146. 

  1146. 	    'notbreaklistopen':1,
    1147. 

  1147. 	    'notbreakparaopen':1,
    1148. 

  1148. 	    'barinsidequote':1,
    1149. 

  1149. 	    'autotocwithbars':1,
    1150. 

  1150. 	    'onelinepara':1,
    1151. 

  1151. 	    }
    1152. 

  1152. 	}
    1153. 

  1153. 	
    1154. 

  1154. 	# Exceptions for --css-sugar
    1155. 

  1155. 	if config['css-sugar'] and config['target'] in ('html','xhtml'):
    1156. 

  1156. 		rules_bank['html']['indentverbblock'] = 0
    1157. 

  1157. 		rules_bank['html']['autotocwithbars'] = 0
    1158. 

  1158. 	
    1159. 

  1159. 	# Get the target specific rules
    1160. 

  1160. 	if config['target'] == 'xhtml':
    1161. 

  1161. 		myrules = rules_bank['html'].copy()   # inheritance
    1162. 

  1162. 		myrules.update(rules_bank['xhtml'])   # get XHTML specific
    1163. 

  1163. 	else:
    1164. 

  1164. 		myrules = rules_bank[config['target']].copy()
    1165. 

  1165. 	
    1166. 

  1166. 	# Populate return dictionary
    1167. 

  1167. 	for key in allrules: ret[key] = 0        # reset all
    1168. 

  1168. 	ret.update(myrules)                      # get rules
    1169. 

  1169. 	
    1170. 

  1170. 	return ret
    1171. 

  1171. 

  1172. 

  1173. ##############################################################################
    1174. 

  1174. 

  1175. 

  1176. def getRegexes():
    1177. 

  1177. 	"Returns all the regexes used to find the t2t marks"
    1178. 

  1178. 	
    1179. 

  1179. 	bank = {
    1180. 

  1180. 	'blockVerbOpen':
    1181. 

  1181. 		re.compile(r'^```\s*$'),
    1182. 

  1182. 	'blockVerbClose':
    1183. 

  1183. 		re.compile(r'^```\s*$'),
    1184. 

  1184. 	'blockRawOpen':
    1185. 

  1185. 		re.compile(r'^"""\s*$'),
    1186. 

  1186. 	'blockRawClose':
    1187. 

  1187. 		re.compile(r'^"""\s*$'),
    1188. 

  1188. 	'blockCommentOpen':
    1189. 

  1189. 		re.compile(r'^%%%\s*$'),
    1190. 

  1190. 	'blockCommentClose':
    1191. 

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

  1192. 	'quote':
    1193. 

  1193. 		re.compile(r'^\t+'),
    1194. 

  1194. 	'1lineVerb':
    1195. 

  1195. 		re.compile(r'^``` (?=.)'),
    1196. 

  1196. 	'1lineRaw':
    1197. 

  1197. 		re.compile(r'^""" (?=.)'),
    1198. 

  1198. 	# mono, raw, bold, italic, underline:
    1199. 

  1199. 	# - marks must be glued with the contents, no boundary spaces
    1200. 

  1200. 	# - they are greedy, so in ****bold****, turns to <b>**bold**</b>
    1201. 

  1201. 	'fontMono':
    1202. 

  1202. 		re.compile(  r'``([^\s](|.*?[^\s])`*)``'),
    1203. 

  1203. 	'raw':
    1204. 

  1204. 		re.compile(  r'""([^\s](|.*?[^\s])"*)""'),
    1205. 

  1205. 	'fontBold':
    1206. 

  1206. 		re.compile(r'\*\*([^\s](|.*?[^\s])\**)\*\*'),
    1207. 

  1207. 	'fontItalic':
    1208. 

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

  1209. 	'fontUnderline':
    1210. 

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

  1211. 	'list':
    1212. 

  1212. 		re.compile(r'^( *)(-) (?=[^ ])'),
    1213. 

  1213. 	'numlist':
    1214. 

  1214. 		re.compile(r'^( *)(\+) (?=[^ ])'),
    1215. 

  1215. 	'deflist':
    1216. 

  1216. 		re.compile(r'^( *)(:) (.*)$'),
    1217. 

  1217. 	'listclose':
    1218. 

  1218. 		re.compile(r'^( *)([-+:])\s*$'),
    1219. 

  1219. 	'bar':
    1220. 

  1220. 		re.compile(r'^(\s*)([_=-]{20,})\s*$'),
    1221. 

  1221. 	'table':
    1222. 

  1222. 		re.compile(r'^ *\|\|? '),
    1223. 

  1223. 	'blankline':
    1224. 

  1224. 		re.compile(r'^\s*$'),
    1225. 

  1225. 	'comment':
    1226. 

  1226. 		re.compile(r'^%'),
    1227. 

  1227. 	
    1228. 

  1228. 	# Auxiliary tag regexes
    1229. 

  1229. 	'_imgAlign'        : re.compile(r'~A~', re.I),
    1230. 

  1230. 	'_tableAlign'      : re.compile(r'~A~', re.I),
    1231. 

  1231. 	'_anchor'          : re.compile(r'~A~', re.I),
    1232. 

  1232. 	'_tableBorder'     : re.compile(r'~B~', re.I),
    1233. 

  1233. 	'_tableColAlign'   : re.compile(r'~C~', re.I),
    1234. 

  1234. 	'_tableCellColSpan': re.compile(r'~S~', re.I),
    1235. 

  1235. 	'_tableCellAlign'  : re.compile(r'~A~', re.I),
    1236. 

  1236. 	}
    1237. 

  1237. 	
    1238. 

  1238. 	# Special char to place data on TAGs contents  (\a == bell)
    1239. 

  1239. 	bank['x'] = re.compile('\a')
    1240. 

  1240. 	
    1241. 

  1241. 	# %%macroname [ (formatting) ]
    1242. 

  1242. 	bank['macros'] = re.compile(r'%%%%(?P<name>%s)\b(\((?P<fmt>.*?)\))?'%(
    1243. 

  1243. 	                            string.join(MACROS.keys(), '|')), re.I)
    1244. 

  1244. 	
    1245. 

  1245. 	# %%TOC special macro for TOC positioning
    1246. 

  1246. 	bank['toc'] = re.compile(r'^ *%%toc\s*$', re.I)
    1247. 

  1247. 	
    1248. 

  1248. 	# Almost complicated title regexes ;)
    1249. 

  1249. 	titskel = r'^ *(?P<id>%s)(?P<txt>%s)\1(\[(?P<label>[\w-]*)\])?\s*$'
    1250. 

  1250. 	bank[   'title'] = re.compile(titskel%('[=]{1,5}','[^=](|.*[^=])'))
    1251. 

  1251. 	bank['numtitle'] = re.compile(titskel%('[+]{1,5}','[^+](|.*[^+])'))
    1252. 

  1252. 	
    1253. 

  1253. 	### Complicated regexes begin here ;)
    1254. 

  1254. 	#
    1255. 

  1255. 	# Textual descriptions on --help's style: [...] is optional, | is OR
    1256. 

  1256. 	
    1257. 

  1257. 	
    1258. 

  1258. 	### First, some auxiliary variables
    1259. 

  1259. 	#
    1260. 

  1260. 	
    1261. 

  1261. 	# [image.EXT]
    1262. 

  1262. 	patt_img = r'\[([\w_,.+%$#@!?+~/-]+\.(png|jpe?g|gif|eps|bmp))\]'
    1263. 

  1263. 	
    1264. 

  1264. 	# Link things
    1265. 

  1265. 	# http://www.gbiv.com/protocols/uri/rfc/rfc3986.html
    1266. 

  1266. 	# pchar: A-Za-z._~- / %FF / !$&'()*+,;= / :@
    1267. 

  1267. 	# Recomended order: scheme://user:pass@domain/path?query=foo#anchor
    1268. 

  1268. 	# Also works      : scheme://user:pass@domain/path#anchor?query=foo
    1269. 

  1269. 	# TODO form: !'():
    1270. 

  1270. 	urlskel = {
    1271. 

  1271. 	  'proto' : r'(https?|ftp|news|telnet|gopher|wais)://',
    1272. 

  1272. 	  'guess' : r'(www[23]?|ftp)\.',         # w/out proto, try to guess
    1273. 

  1273. 	  'login' : r'A-Za-z0-9_.-',             # for ftp://login@domain.com
    1274. 

  1274. 	  'pass'  : r'[^ @]*',                   # for ftp://login:pass@dom.com
    1275. 

  1275. 	  'chars' : r'A-Za-z0-9%._/~:,=$@&+-',   # %20(space), :80(port), D&D
    1276. 

  1276. 	  'anchor': r'A-Za-z0-9%._-',            # %nn(encoded)
    1277. 

  1277. 	  'form'  : r'A-Za-z0-9/%&=+;.,$@*_-',   # .,@*_-(as is)
    1278. 

  1278. 	  'punct' : r'.,;:!?'
    1279. 

  1279. 	}
    1280. 

  1280. 	
    1281. 

  1281. 	# username [ :password ] @
    1282. 

  1282. 	patt_url_login = r'([%s]+(:%s)?@)?'%(urlskel['login'],urlskel['pass'])
    1283. 

  1283. 	
    1284. 

  1284. 	# [ http:// ] [ username:password@ ] domain.com [ / ]
    1285. 

  1285. 	#     [ #anchor | ?form=data ]
    1286. 

  1286. 	retxt_url = r'\b(%s%s|%s)[%s]+\b/*(\?[%s]+)?(#[%s]*)?'%(
    1287. 

  1287. 	             urlskel['proto'],patt_url_login, urlskel['guess'],
    1288. 

  1288. 	             urlskel['chars'],urlskel['form'],urlskel['anchor'])
    1289. 

  1289. 	
    1290. 

  1290. 	# filename | [ filename ] #anchor
    1291. 

  1291. 	retxt_url_local = r'[%s]+|[%s]*(#[%s]*)'%(
    1292. 

  1292. 	             urlskel['chars'],urlskel['chars'],urlskel['anchor'])
    1293. 

  1293. 	
    1294. 

  1294. 	# user@domain [ ?form=data ]
    1295. 

  1295. 	patt_email = r'\b[%s]+@([A-Za-z0-9_-]+\.)+[A-Za-z]{2,4}\b(\?[%s]+)?'%(
    1296. 

  1296. 	             urlskel['login'],urlskel['form'])
    1297. 

  1297. 	
    1298. 

  1298. 	# Saving for future use
    1299. 

  1299. 	bank['_urlskel'] = urlskel
    1300. 

  1300. 	
    1301. 

  1301. 	### And now the real regexes
    1302. 

  1302. 	#
    1303. 

  1303. 	
    1304. 

  1304. 	bank['email'] = re.compile(patt_email,re.I)
    1305. 

  1305. 	
    1306. 

  1306. 	# email | url
    1307. 

  1307. 	bank['link'] = re.compile(r'%s|%s'%(retxt_url,patt_email), re.I)
    1308. 

  1308. 	
    1309. 

  1309. 	# \[ label | imagetag    url | email | filename \]
    1310. 

  1310. 	bank['linkmark'] = re.compile(
    1311. 

  1311. 		r'\[(?P<label>%s|[^]]+) (?P<link>%s|%s|%s)\]'%(
    1312. 

  1312. 		  patt_img, retxt_url, patt_email, retxt_url_local),
    1313. 

  1313. 		re.L+re.I)
    1314. 

  1314. 	
    1315. 

  1315. 	# Image
    1316. 

  1316. 	bank['img'] = re.compile(patt_img, re.L+re.I)
    1317. 

  1317. 	
    1318. 

  1318. 	# Special things
    1319. 

  1319. 	bank['special'] = re.compile(r'^%!\s*')
    1320. 

  1320. 	return bank
    1321. 

  1321. ### END OF regex nightmares
    1322. 

  1322. 

  1323. 

  1324. ##############################################################################
    1325. 

  1325. 

  1326. class error(Exception):
    1327. 

  1327. 	pass
    1328. 

  1328. def echo(msg):   # for quick debug
    1329. 

  1329. 	print '\033[32;1m%s\033[m'%msg
    1330. 

  1330. def Quit(msg=''):
    1331. 

  1331. 	if msg: print msg
    1332. 

  1332. 	sys.exit(0)
    1333. 

  1333. def Error(msg):
    1334. 

  1334. 	msg = _("%s: Error: ")%my_name + msg
    1335. 

  1335. 	raise error, msg
    1336. 

  1336. def getTraceback():
    1337. 

  1337. 	try:
    1338. 

  1338. 		from traceback import format_exception
    1339. 

  1339. 		etype, value, tb = sys.exc_info()
    1340. 

  1340. 		return string.join(format_exception(etype, value, tb), '')
    1341. 

  1341. 	except: pass
    1342. 

  1342. def getUnknownErrorMessage():
    1343. 

  1343. 	msg = '%s\n%s (%s):\n\n%s'%(
    1344. 

  1344. 	  _('Sorry! Txt2tags aborted by an unknown error.'),
    1345. 

  1345. 	  _('Please send the following Error Traceback to the author'),
    1346. 

  1346. 	  my_email, getTraceback())
    1347. 

  1347. 	return msg
    1348. 

  1348. def Message(msg,level):
    1349. 

  1349. 	if level <= VERBOSE and not QUIET:
    1350. 

  1350. 		prefix = '-'*5
    1351. 

  1351. 		print "%s %s"%(prefix*level, msg)
    1352. 

  1352. def Debug(msg,id=0,linenr=None):
    1353. 

  1353. 	"Show debug messages, categorized (colored or not)"
    1354. 

  1354. 	if QUIET or not DEBUG: return
    1355. 

  1355. 	if int(id) not in range(8): id = 0
    1356. 

  1356. 	# 0:black 1:red 2:green 3:yellow 4:blue 5:pink 6:cyan 7:white ;1:light
    1357. 

  1357. 	ids            = ['INI','CFG','SRC','BLK','HLD','GUI','OUT','DET']
    1358. 

  1358. 	colors_bgdark  = ['7;1','1;1','3;1','6;1','4;1','5;1','2;1','7;1']
    1359. 

  1359. 	colors_bglight = ['0'  ,'1'  ,'3'  ,'6'  ,'4'  ,'5'  ,'2'  ,'0'  ]
    1360. 

  1360. 	if linenr is not None: msg = "LINE %04d: %s"%(linenr,msg)
    1361. 

  1361. 	if COLOR_DEBUG:
    1362. 

  1362. 		if BG_LIGHT: color = colors_bglight[id]
    1363. 

  1363. 		else       : color = colors_bgdark[id]
    1364. 

  1364. 		msg = '\033[3%sm%s\033[m'%(color,msg)
    1365. 

  1365. 	print "++ %s: %s"%(ids[id],msg)
    1366. 

  1366. def Readfile(file, remove_linebreaks=0, ignore_error=0):
    1367. 

  1367. 	data = []
    1368. 

  1368. 	if file == '-':
    1369. 

  1369. 		try: data = sys.stdin.readlines()
    1370. 

  1370. 		except:
    1371. 

  1371. 			if not ignore_error:
    1372. 

  1372. 				Error(_('You must feed me with data on STDIN!'))
    1373. 

  1373. 	else:
    1374. 

  1374. 		try: f = open(file); data = f.readlines() ; f.close()
    1375. 

  1375. 		except:
    1376. 

  1376. 			if not ignore_error:
    1377. 

  1377. 				Error(_("Cannot read file:")+" %s"%file)
    1378. 

  1378. 	if remove_linebreaks:
    1379. 

  1379. 		data = map(lambda x:re.sub('[\n\r]+$','',x), data)
    1380. 

  1380. 	Message(_("File read (%d lines): %s")%(len(data),file),2)
    1381. 

  1381. 	return data
    1382. 

  1382. def Savefile(file, contents):
    1383. 

  1383. 	try: f = open(file, 'wb')
    1384. 

  1384. 	except: Error(_("Cannot open file for writing:")+" %s"%file)
    1385. 

  1385. 	if type(contents) == type([]): doit = f.writelines
    1386. 

  1386. 	else: doit = f.write
    1387. 

  1387. 	doit(contents) ; f.close()
    1388. 

  1388. 

  1389. def showdic(dic):
    1390. 

  1390. 	for k in dic.keys(): print "%15s : %s" % (k,dic[k])
    1391. 

  1391. def dotted_spaces(txt=''):
    1392. 

  1392. 	return string.replace(txt,' ','.')
    1393. 

  1393. 

  1394. # TIP: win env vars http://www.winnetmag.com/Article/ArticleID/23873/23873.html
    1395. 

  1395. def get_rc_path():
    1396. 

  1396. 	"Return the full path for the users' RC file"
    1397. 

  1397. 	# Try to get the path from an env var. if yes, we're done
    1398. 

  1398. 	user_defined = os.environ.get('T2TCONFIG')
    1399. 

  1399. 	if user_defined: return user_defined
    1400. 

  1400. 	# Env var not found, so perform automatic path composing
    1401. 

  1401. 	# Set default filename according system platform
    1402. 

  1402. 	rc_names = {'default':'.txt2tagsrc', 'win':'_t2trc'}
    1403. 

  1403. 	rc_file = rc_names.get(sys.platform[:3]) or rc_names['default']
    1404. 

  1404. 	# The file must be on the user directory, but where is this dir?
    1405. 

  1405. 	rc_dir_search = ['HOME', 'HOMEPATH']
    1406. 

  1406. 	for var in rc_dir_search:
    1407. 

  1407. 		rc_dir = os.environ.get(var)
    1408. 

  1408. 		if rc_dir: break
    1409. 

  1409. 	# rc dir found, now we must join dir+file to compose the full path
    1410. 

  1410. 	if rc_dir:
    1411. 

  1411. 		# Compose path and return it if the file exists
    1412. 

  1412. 		rc_path = os.path.join(rc_dir, rc_file)
    1413. 

  1413. 		# On windows, prefix with the drive (%homedrive%: 2k/XP/NT)
    1414. 

  1414. 		if sys.platform[:3] == 'win':
    1415. 

  1415. 			rc_drive = os.environ.get('HOMEDRIVE')
    1416. 

  1416. 			rc_path = os.path.join(rc_drive,rc_path)
    1417. 

  1417. 		return rc_path
    1418. 

  1418. 	# Sorry, not found
    1419. 

  1419. 	return ''
    1420. 

  1420. 

  1421. 

  1422. 

  1423. ##############################################################################
    1424. 

  1424. 

  1425. class CommandLine:
    1426. 

  1426. 	"""
    1427. 

  1427. 	Command Line class - Masters command line
    1428. 

  1428. 

  1429. 	This class checks and extract data from the provided command line.
    1430. 

  1430. 	The --long options and flags are taken from the global OPTIONS,
    1431. 

  1431. 	FLAGS and ACTIONS dictionaries. The short options are registered
    1432. 

  1432. 	here, and also their equivalence to the long ones.
    1433. 

  1433. 

  1434. 	METHODS:
    1435. 

  1435. 	  _compose_short_opts() -> str
    1436. 

  1436. 	  _compose_long_opts() -> list
    1437. 

  1437. 	      Compose the valid short and long options list, on the
    1438. 

  1438. 	      'getopt' format.
    1439. 

  1439. 	  
    1440. 

  1440. 	  parse() -> (opts, args)
    1441. 

  1441. 	      Call getopt to check and parse the command line.
    1442. 

  1442. 	      It expects to receive the command line as a list, and
    1443. 

  1443. 	      without the program name (sys.argv[1:]).
    1444. 

  1444. 	  
    1445. 

  1445. 	  get_raw_config() -> [RAW config]
    1446. 

  1446. 	      Scans command line and convert the data to the RAW config
    1447. 

  1447. 	      format. See ConfigMaster class to the RAW format description.
    1448. 

  1448. 	      Optional 'ignore' and 'filter' arguments are used to filter
    1449. 

  1449. 	      in or out specified keys.
    1450. 

  1450. 	  
    1451. 

  1451. 	  compose_cmdline(dict) -> [Command line]
    1452. 

  1452. 	      Compose a command line list from an already parsed config
    1453. 

  1453. 	      dictionary, generated from RAW by ConfigMaster(). Use
    1454. 

  1454. 	      this to compose an optimal command line for a group of
    1455. 

  1455. 	      options.
    1456. 

  1456. 	
    1457. 

  1457. 	The get_raw_config() calls parse(), so the tipical use of this
    1458. 

  1458. 	class is:
    1459. 

  1459. 	
    1460. 

  1460.             raw = CommandLine().get_raw_config(sys.argv[1:])
    1461. 

  1461. 	"""
    1462. 

  1462. 	def __init__(self):
    1463. 

  1463. 		self.all_options = OPTIONS.keys()
    1464. 

  1464. 		self.all_flags   = FLAGS.keys()
    1465. 

  1465. 		self.all_actions = ACTIONS.keys()
    1466. 

  1466. 		
    1467. 

  1467. 		# short:long options equivalence
    1468. 

  1468. 		self.short_long = {
    1469. 

  1469. 		  'h':'help'     ,   'V':'version',
    1470. 

  1470. 		  'n':'enum-title',  'i':'infile' ,
    1471. 

  1471. 		  'H':'no-headers',  'o':'outfile',
    1472. 

  1472. 		  'v':'verbose'   ,  't':'target' ,
    1473. 

  1473. 		  'q':'quiet'     ,  'C':'config-file'
    1474. 

  1474. 		}
    1475. 

  1475. 		
    1476. 

  1476. 		# Compose valid short and long options data for getopt
    1477. 

  1477. 		self.short_opts = self._compose_short_opts()
    1478. 

  1478. 		self.long_opts  = self._compose_long_opts()
    1479. 

  1479. 	
    1480. 

  1480. 	def _compose_short_opts(self):
    1481. 

  1481. 		"Returns a string like 'hVt:o' with all short options/flags"
    1482. 

  1482. 		ret = []
    1483. 

  1483. 		for opt in self.short_long.keys():
    1484. 

  1484. 			long = self.short_long[opt]
    1485. 

  1485. 			if long in self.all_options: # is flag or option?
    1486. 

  1486. 				opt = opt+':'        # option: have param
    1487. 

  1487. 			ret.append(opt)
    1488. 

  1488. 		#Debug('Valid SHORT options: %s'%ret)
    1489. 

  1489. 		return string.join(ret, '')
    1490. 

  1490. 	
    1491. 

  1491. 	def _compose_long_opts(self):
    1492. 

  1492. 		"Returns a list with all the valid long options/flags"
    1493. 

  1493. 		ret = map(lambda x:x+'=', self.all_options)          # add =
    1494. 

  1494. 		ret.extend(self.all_flags)                           # flag ON
    1495. 

  1495. 		ret.extend(self.all_actions)                         # acts
    1496. 

  1496. 		ret.extend(map(lambda x:'no-'+x, self.all_flags))    # add no-*
    1497. 

  1497. 		ret.extend(['no-style','no-encoding'])               # turn OFF
    1498. 

  1498. 		ret.extend(['no-outfile','no-infile'])               # turn OFF
    1499. 

  1499. 		ret.extend(['no-dump-config', 'no-dump-source'])     # turn OFF
    1500. 

  1500. 		#Debug('Valid LONG options: %s'%ret)
    1501. 

  1501. 		return ret
    1502. 

  1502. 	
    1503. 

  1503. 	def _tokenize(self, cmd_string=''):
    1504. 

  1504. 		"Convert a command line string to a list"
    1505. 

  1505. 		#TODO protect quotes contents
    1506. 

  1506. 		return string.split(cmd_string)
    1507. 

  1507. 	
    1508. 

  1508. 	def parse(self, cmdline=[]):
    1509. 

  1509. 		"Check/Parse a command line list     TIP: no program name!"
    1510. 

  1510. 		# Get the valid options
    1511. 

  1511. 		short, long = self.short_opts, self.long_opts
    1512. 

  1512. 		# Parse it!
    1513. 

  1513. 		try:
    1514. 

  1514. 			opts, args = getopt.getopt(cmdline, short, long)
    1515. 

  1515. 		except getopt.error, errmsg:
    1516. 

  1516. 			Error(_("%s (try --help)")%errmsg)
    1517. 

  1517. 		return (opts, args)
    1518. 

  1518. 	
    1519. 

  1519. 	def get_raw_config(self, cmdline=[], ignore=[], filter=[], relative=0):
    1520. 

  1520. 		"Returns the options/arguments found as RAW config"
    1521. 

  1521. 		if not cmdline: return []
    1522. 

  1522. 		ret = []
    1523. 

  1523. 		# We need lists, not strings
    1524. 

  1524. 		if type(cmdline) == type(''): cmdline = self._tokenize(cmdline)
    1525. 

  1525. 		opts, args = self.parse(cmdline[:])
    1526. 

  1526. 		# Parse all options
    1527. 

  1527. 		for name,value in opts:
    1528. 

  1528. 			# Remove leading - and --
    1529. 

  1529. 			name = re.sub('^--?', '', name)
    1530. 

  1530. 			# Alias to old misspelled 'suGGar'
    1531. 

  1531. 			if   name ==    'css-suggar': name =    'css-sugar'
    1532. 

  1532. 			elif name == 'no-css-suggar': name = 'no-css-sugar'
    1533. 

  1533. 			# Translate short opt to long
    1534. 

  1534. 			if len(name) == 1: name = self.short_long.get(name)
    1535. 

  1535. 			# Outfile exception: path relative to PWD
    1536. 

  1536. 			if name == 'outfile' and relative \
    1537. 

  1537. 			   and value not in [STDOUT, MODULEOUT]:
    1538. 

  1538. 				value = os.path.abspath(value)
    1539. 

  1539. 			# config-file inclusion, path relative to PWD
    1540. 

  1540. 			if name == 'config-file':
    1541. 

  1541. 				configs = ConfigLines().include_config_file(
    1542. 

  1542. 				          value)
    1543. 

  1543. 				# Remove the 'target' item of all configs
    1544. 

  1544. 				configs = map(lambda c: [c[1],c[2]], configs)
    1545. 

  1545. 				ret.extend(configs)
    1546. 

  1546. 				continue
    1547. 

  1547. 			# Save it
    1548. 

  1548. 			ret.append([name, value])
    1549. 

  1549. 		# Get infile, if any
    1550. 

  1550. 		while args:
    1551. 

  1551. 			infile = args.pop(0)
    1552. 

  1552. 			ret.append(['infile', infile])
    1553. 

  1553. 		# Apply 'ignore' and 'filter' rules (filter is stronger)
    1554. 

  1554. 		temp = ret[:] ; ret = []
    1555. 

  1555. 		for name,value in temp:
    1556. 

  1556. 			if (not filter and not ignore) or \
    1557. 

  1557. 			   (filter and name in filter) or \
    1558. 

  1558. 			   (ignore and name not in ignore):
    1559. 

  1559. 				ret.append( ['all', name, value] )
    1560. 

  1560. 		# Add the original command line string as 'realcmdline'
    1561. 

  1561. 		ret.append( ['all', 'realcmdline', cmdline] )
    1562. 

  1562. 		return ret
    1563. 

  1563. 	
    1564. 

  1564. 	def compose_cmdline(self, conf={}, no_check=0):
    1565. 

  1565. 		"compose a full (and diet) command line from CONF dict"
    1566. 

  1566. 		if not conf: return []
    1567. 

  1567. 		args = []
    1568. 

  1568. 		dft_options = OPTIONS.copy()
    1569. 

  1569. 		cfg = conf.copy()
    1570. 

  1570. 		valid_opts = self.all_options + self.all_flags
    1571. 

  1571. 		use_short = {'no-headers':'H', 'enum-title':'n'}
    1572. 

  1572. 		# Remove useless options
    1573. 

  1573. 		if not no_check and cfg.get('toc-only'):
    1574. 

  1574. 			if cfg.has_key('no-headers'):
    1575. 

  1575. 				del cfg['no-headers']
    1576. 

  1576. 			if cfg.has_key('outfile'):
    1577. 

  1577. 				del cfg['outfile']      # defaults to STDOUT
    1578. 

  1578. 			if cfg.get('target') == 'txt':
    1579. 

  1579. 				del cfg['target']       # already default
    1580. 

  1580. 			args.append('--toc-only')  # must be the first
    1581. 

  1581. 			del cfg['toc-only']
    1582. 

  1582. 		# Add target type
    1583. 

  1583. 		if cfg.has_key('target'):
    1584. 

  1584. 			args.append('-t '+cfg['target'])
    1585. 

  1585. 			del cfg['target']
    1586. 

  1586. 		# Add other options
    1587. 

  1587. 		for key in cfg.keys():
    1588. 

  1588. 			if key not in valid_opts: continue  # may be a %!setting
    1589. 

  1589. 			if key == 'outfile' or key == 'infile': continue # later
    1590. 

  1590. 			val = cfg[key]
    1591. 

  1591. 			if not val: continue
    1592. 

  1592. 			# Default values are useless on cmdline
    1593. 

  1593. 			if val == dft_options.get(key): continue
    1594. 

  1594. 			# -short format
    1595. 

  1595. 			if key in use_short.keys():
    1596. 

  1596. 				args.append('-'+use_short[key])
    1597. 

  1597. 				continue
    1598. 

  1598. 			# --long format
    1599. 

  1599. 			if key in self.all_flags: # add --option
    1600. 

  1600. 				args.append('--'+key)
    1601. 

  1601. 			else:                     # add --option=value
    1602. 

  1602. 				args.append('--%s=%s'%(key,val))
    1603. 

  1603. 		# The outfile using -o
    1604. 

  1604. 		if cfg.has_key('outfile') and \
    1605. 

  1605. 		   cfg['outfile'] != dft_options.get('outfile'):
    1606. 

  1606. 			args.append('-o '+cfg['outfile'])
    1607. 

  1607. 		# Place input file(s) always at the end
    1608. 

  1608. 		if cfg.has_key('infile'):
    1609. 

  1609. 			args.append(string.join(cfg['infile'],' '))
    1610. 

  1610. 		# Return as a nice list
    1611. 

  1611. 		Debug("Diet command line: %s"%string.join(args,' '), 1)
    1612. 

  1612. 		return args
    1613. 

  1613. 

  1614. ##############################################################################
    1615. 

  1615. 

  1616. class SourceDocument:
    1617. 

  1617. 	"""
    1618. 

  1618. 	SourceDocument class - scan document structure, extract data
    1619. 

  1619. 	
    1620. 

  1620. 	It knows about full files. It reads a file and identify all
    1621. 

  1621. 	the areas begining (Head,Conf,Body). With this info it can
    1622. 

  1622. 	extract each area contents.
    1623. 

  1623. 	Note: the original line break is removed.
    1624. 

  1624. 	
    1625. 

  1625. 	DATA:
    1626. 

  1626. 	  self.arearef - Save Head, Conf, Body init line number
    1627. 

  1627. 	  self.areas   - Store the area names which are not empty
    1628. 

  1628. 	  self.buffer  - The full file contents (with NO \\r, \\n)
    1629. 

  1629. 

  1630. 	METHODS:
    1631. 

  1631. 	  get()   - Access the contents of an Area. Example:
    1632. 

  1632. 	            config = SourceDocument(file).get('conf')
    1633. 

  1633. 	
    1634. 

  1634. 	  split() - Get all the document Areas at once. Example:
    1635. 

  1635. 	            head, conf, body = SourceDocument(file).split()
    1636. 

  1636. 	
    1637. 

  1637. 	RULES:
    1638. 

  1638. 	    * The document parts are sequential: Head, Conf and Body.
    1639. 

  1639. 	    * One ends when the next begins.
    1640. 

  1640. 	    * The Conf Area is optional, so a document can have just
    1641. 

  1641. 	      Head and Body Areas.
    1642. 

  1642. 	
    1643. 

  1643. 	    These are the Areas limits:
    1644. 

  1644. 	      - Head Area: the first three lines
    1645. 

  1645. 	      - Body Area: from the first valid text line to the end
    1646. 

  1646. 	      - Conf Area: the comments between Head and Body Areas
    1647. 

  1647. 

  1648. 	    Exception: If the first line is blank, this means no
    1649. 

  1649. 	    header info, so the Head Area is just the first line.
    1650. 

  1650. 	"""
    1651. 

  1651. 	def __init__(self, filename='', contents=[]):
    1652. 

  1652. 		self.areas = ['head','conf','body']
    1653. 

  1653. 		self.arearef = []
    1654. 

  1654. 		self.areas_fancy = ''
    1655. 

  1655. 		self.filename = filename
    1656. 

  1656. 		self.buffer = []
    1657. 

  1657. 		if filename:
    1658. 

  1658. 			self.scan_file(filename)
    1659. 

  1659. 		elif contents:
    1660. 

  1660. 			self.scan(contents)
    1661. 

  1661. 	
    1662. 

  1662. 	def split(self):
    1663. 

  1663. 		"Returns all document parts, splitted into lists."
    1664. 

  1664. 		return self.get('head'), self.get('conf'), self.get('body')
    1665. 

  1665. 	
    1666. 

  1666. 	def get(self, areaname):
    1667. 

  1667. 		"Returns head|conf|body contents from self.buffer"
    1668. 

  1668. 		# Sanity
    1669. 

  1669. 		if areaname not in self.areas: return []
    1670. 

  1670. 		if not self.buffer           : return []
    1671. 

  1671. 		# Go get it
    1672. 

  1672. 		bufini = 1
    1673. 

  1673. 		bufend = len(self.buffer)
    1674. 

  1674. 		if   areaname == 'head':
    1675. 

  1675. 			ini = bufini
    1676. 

  1676. 			end = self.arearef[1] or self.arearef[2] or bufend
    1677. 

  1677. 		elif areaname == 'conf':
    1678. 

  1678. 			ini = self.arearef[1]
    1679. 

  1679. 			end = self.arearef[2] or bufend
    1680. 

  1680. 		elif areaname == 'body':
    1681. 

  1681. 			ini = self.arearef[2]
    1682. 

  1682. 			end = bufend
    1683. 

  1683. 		else:
    1684. 

  1684. 			Error("Unknown Area name '%s'"%areaname)
    1685. 

  1685. 		lines = self.buffer[ini:end]
    1686. 

  1686. 		# Make sure head will always have 3 lines
    1687. 

  1687. 		while areaname == 'head' and len(lines) < 3:
    1688. 

  1688. 			lines.append('')
    1689. 

  1689. 		return lines
    1690. 

  1690. 	
    1691. 

  1691. 	def scan_file(self, filename):
    1692. 

  1692. 		Debug("source file: %s"%filename)
    1693. 

  1693. 		Message(_("Loading source document"),1)
    1694. 

  1694. 		buf = Readfile(filename, remove_linebreaks=1)
    1695. 

  1695. 		self.scan(buf)
    1696. 

  1696. 	
    1697. 

  1697. 	def scan(self, lines):
    1698. 

  1698. 		"Run through source file and identify head/conf/body areas"
    1699. 

  1699. 		buf = lines
    1700. 

  1700. 		if len(buf) == 0:
    1701. 

  1701. 			Error(_('The input file is empty: %s')%self.filename)
    1702. 

  1702. 		cfg_parser = ConfigLines().parse_line
    1703. 

  1703. 		buf.insert(0, '')                         # text start at pos 1
    1704. 

  1704. 		ref = [1,4,0]
    1705. 

  1705. 		if not string.strip(buf[1]):              # no header
    1706. 

  1706. 			ref[0] = 0 ; ref[1] = 2
    1707. 

  1707. 		rgx = getRegexes()
    1708. 

  1708. 		on_comment_block = 0
    1709. 

  1709. 		for i in xrange(ref[1],len(buf)):         # find body init:
    1710. 

  1710. 			# Handle comment blocks inside config area
    1711. 

  1711. 			if not on_comment_block \
    1712. 

  1712. 			   and rgx['blockCommentOpen'].search(buf[i]):
    1713. 

  1713. 				on_comment_block = 1
    1714. 

  1714. 				continue
    1715. 

  1715. 			if on_comment_block \
    1716. 

  1716. 			   and rgx['blockCommentOpen'].search(buf[i]):
    1717. 

  1717. 				on_comment_block = 0
    1718. 

  1718. 				continue
    1719. 

  1719. 			if on_comment_block: continue
    1720. 

  1720. 			
    1721. 

  1721. 			if string.strip(buf[i]) and (     # ... not blank and
    1722. 

  1722. 			   buf[i][0] != '%' or            # ... not comment or
    1723. 

  1723. 			   rgx['macros'].match(buf[i]) or # ... %%macro
    1724. 

  1724. 			   rgx['toc'].match(buf[i])    or # ... %%toc
    1725. 

  1725. 			   cfg_parser(buf[i],'include')[1]): # ... %!include
    1726. 

  1726. 				ref[2] = i ; break
    1727. 

  1727. 		if ref[1] == ref[2]: ref[1] = 0           # no conf area
    1728. 

  1728. 		for i in 0,1,2:                           # del !existent
    1729. 

  1729. 			if ref[i] >= len(buf): ref[i] = 0 # title-only
    1730. 

  1730. 			if not ref[i]: self.areas[i] = ''
    1731. 

  1731. 		Debug('Head,Conf,Body start line: %s'%ref)
    1732. 

  1732. 		self.arearef = ref                        # save results
    1733. 

  1733. 		self.buffer  = buf
    1734. 

  1734. 		# Fancyness sample: head conf body (1 4 8)
    1735. 

  1735. 		self.areas_fancy = "%s (%s)"%(
    1736. 

  1736. 		     string.join(self.areas),
    1737. 

  1737. 		     string.join(map(str, map(lambda x:x or '', ref))))
    1738. 

  1738. 		Message(_("Areas found: %s")%self.areas_fancy, 2)
    1739. 

  1739. 	
    1740. 

  1740. 	def get_raw_config(self):
    1741. 

  1741. 		"Handy method to get the CONF area RAW config (if any)"
    1742. 

  1742. 		if not self.areas.count('conf'): return []
    1743. 

  1743. 		Message(_("Scanning source document CONF area"),1)
    1744. 

  1744. 		raw = ConfigLines(
    1745. 

  1745. 		      file=self.filename, lines=self.get('conf'),
    1746. 

  1746. 		      first_line=self.arearef[1]).get_raw_config()
    1747. 

  1747. 		Debug("document raw config: %s"%raw, 1)
    1748. 

  1748. 		return raw
    1749. 

  1749. 

  1750. ##############################################################################
    1751. 

  1751. 

  1752. class ConfigMaster:
    1753. 

  1753. 	"""
    1754. 

  1754. 	ConfigMaster class - the configuration wizard
    1755. 

  1755. 	
    1756. 

  1756. 	This class is the configuration master. It knows how to handle
    1757. 

  1757. 	the RAW and PARSED config format. It also performs the sanity
    1758. 

  1758. 	checking for a given configuration.
    1759. 

  1759. 	
    1760. 

  1760. 	DATA:
    1761. 

  1761. 	  self.raw         - Stores the config on the RAW format
    1762. 

  1762. 	  self.parsed      - Stores the config on the PARSED format
    1763. 

  1763. 	  self.defaults    - Stores the default values for all keys
    1764. 

  1764. 	  self.off         - Stores the OFF values for all keys
    1765. 

  1765. 	  self.multi       - List of keys which can have multiple values
    1766. 

  1766. 	  self.numeric     - List of keys which value must be a number
    1767. 

  1767. 	  self.incremental - List of keys which are incremental
    1768. 

  1768. 	
    1769. 

  1769.         RAW FORMAT:
    1770. 

  1770. 	  The RAW format is a list of lists, being each mother list item
    1771. 

  1771. 	  a full configuration entry. Any entry is a 3 item list, on
    1772. 

  1772. 	  the following format: [ TARGET, KEY, VALUE ]
    1773. 

  1773. 	  Being a list, the order is preserved, so it's easy to use
    1774. 

  1774. 	  different kinds of configs, as CONF area and command line,
    1775. 

  1775. 	  respecting the precedence.
    1776. 

  1776. 	  The special target 'all' is used when no specific target was
    1777. 

  1777. 	  defined on the original config.
    1778. 

  1778. 	
    1779. 

  1779. 	PARSED FORMAT:
    1780. 

  1780. 	  The PARSED format is a dictionary, with all the 'key : value'
    1781. 

  1781. 	  found by reading the RAW config. The self.target contents
    1782. 

  1782. 	  matters, so this dictionary only contains the target's
    1783. 

  1783. 	  config. The configs of other targets are ignored.
    1784. 

  1784. 	
    1785. 

  1785. 	The CommandLine and ConfigLines classes have the get_raw_config()
    1786. 

  1786. 	method which convert the configuration found to the RAW format.
    1787. 

  1787. 	Just feed it to parse() and get a brand-new ready-to-use config
    1788. 

  1788. 	dictionary. Example:
    1789. 

  1789. 	
    1790. 

  1790. 	    >>> raw = CommandLine().get_raw_config(['-n', '-H'])
    1791. 

  1791. 	    >>> print raw
    1792. 

  1792. 	    [['all', 'enum-title', ''], ['all', 'no-headers', '']]
    1793. 

  1793. 	    >>> parsed = ConfigMaster(raw).parse()
    1794. 

  1794. 	    >>> print parsed
    1795. 

  1795. 	    {'enum-title': 1, 'headers': 0}
    1796. 

  1796. 	"""
    1797. 

  1797. 	def __init__(self, raw=[], target=''):
    1798. 

  1798. 		self.raw          = raw
    1799. 

  1799. 		self.target       = target
    1800. 

  1800. 		self.parsed       = {}
    1801. 

  1801. 		self.dft_options  = OPTIONS.copy()
    1802. 

  1802. 		self.dft_flags    = FLAGS.copy()
    1803. 

  1803. 		self.dft_actions  = ACTIONS.copy()
    1804. 

  1804. 		self.dft_settings = SETTINGS.copy()
    1805. 

  1805. 		self.defaults     = self._get_defaults()
    1806. 

  1806. 		self.off          = self._get_off()
    1807. 

  1807. 		self.incremental  = ['verbose']
    1808. 

  1808. 		self.numeric      = ['toc-level','split']
    1809. 

  1809. 		self.multi        = ['infile', 'preproc', 'postproc',
    1810. 

  1810. 		                     'options', 'style']
    1811. 

  1811. 	
    1812. 

  1812. 	def _get_defaults(self):
    1813. 

  1813. 		"Get the default values for all config/options/flags"
    1814. 

  1814. 		empty = {}
    1815. 

  1815. 		for kw in CONFIG_KEYWORDS: empty[kw] = ''
    1816. 

  1816. 		empty.update(self.dft_options)
    1817. 

  1817. 		empty.update(self.dft_flags)
    1818. 

  1818. 		empty.update(self.dft_actions)
    1819. 

  1819. 		empty.update(self.dft_settings)
    1820. 

  1820. 		empty['realcmdline'] = ''  # internal use only
    1821. 

  1821. 		empty['sourcefile']  = ''  # internal use only
    1822. 

  1822. 		return empty
    1823. 

  1823. 	
    1824. 

  1824. 	def _get_off(self):
    1825. 

  1825. 		"Turns OFF all the config/options/flags"
    1826. 

  1826. 		off = {}
    1827. 

  1827. 		for key in self.defaults.keys():
    1828. 

  1828. 			kind = type(self.defaults[key])
    1829. 

  1829. 			if kind == type(9):
    1830. 

  1830. 				off[key] = 0
    1831. 

  1831. 			elif kind == type(''):
    1832. 

  1832. 				off[key] = ''
    1833. 

  1833. 			elif kind == type([]):
    1834. 

  1834. 				off[key] = []
    1835. 

  1835. 			else:
    1836. 

  1836. 				Error('ConfigMaster: %s: Unknown type'+key)
    1837. 

  1837. 		return off
    1838. 

  1838. 	
    1839. 

  1839. 	def _check_target(self):
    1840. 

  1840. 		"Checks if the target is already defined. If not, do it"
    1841. 

  1841. 		if not self.target:
    1842. 

  1842. 			self.target = self.find_value('target')
    1843. 

  1843. 	
    1844. 

  1844. 	def get_target_raw(self):
    1845. 

  1845. 		"Returns the raw config for self.target or 'all'"
    1846. 

  1846. 		ret = []
    1847. 

  1847. 		self._check_target()
    1848. 

  1848. 		for entry in self.raw:
    1849. 

  1849. 			if entry[0] == self.target or entry[0] == 'all':
    1850. 

  1850. 				ret.append(entry)
    1851. 

  1851. 		return ret
    1852. 

  1852. 	
    1853. 

  1853. 	def add(self, key, val):
    1854. 

  1854. 		"Adds the key:value pair to the config dictionary (if needed)"
    1855. 

  1855. 		# %!options
    1856. 

  1856. 		if key == 'options':
    1857. 

  1857. 			ignoreme = self.dft_actions.keys() + ['target']
    1858. 

  1858. 			ignoreme.remove('dump-config')
    1859. 

  1859. 			ignoreme.remove('dump-source')
    1860. 

  1860. 			raw_opts = CommandLine().get_raw_config(
    1861. 

  1861. 			             val, ignore=ignoreme)
    1862. 

  1862. 			for target, key, val in raw_opts:
    1863. 

  1863. 				self.add(key, val)
    1864. 

  1864. 			return
    1865. 

  1865. 		# The no- prefix turns OFF this key
    1866. 

  1866. 		if key[:3] == 'no-':
    1867. 

  1867. 			key = key[3:]              # remove prefix
    1868. 

  1868. 			val = self.off.get(key)    # turn key OFF
    1869. 

  1869. 		# Is this key valid?
    1870. 

  1870. 		if key not in self.defaults.keys():
    1871. 

  1871. 			Debug('Bogus Config %s:%s'%(key,val),1)
    1872. 

  1872. 			return
    1873. 

  1873. 		# Is this value the default one?
    1874. 

  1874. 		if val == self.defaults.get(key):
    1875. 

  1875. 			# If default value, remove previous key:val
    1876. 

  1876. 			if self.parsed.has_key(key):
    1877. 

  1877. 				del self.parsed[key]
    1878. 

  1878. 			# Nothing more to do
    1879. 

  1879. 			return
    1880. 

  1880. 		# Flags ON comes empty. we'll add the 1 value now
    1881. 

  1881. 		if val == '' and (
    1882. 

  1882. 		   key in self.dft_flags.keys() or
    1883. 

  1883. 		   key in self.dft_actions.keys()):
    1884. 

  1884. 			val = 1
    1885. 

  1885. 		# Multi value or single?
    1886. 

  1886. 		if key in self.multi:
    1887. 

  1887. 			# First one? start new list
    1888. 

  1888. 			if not self.parsed.has_key(key):
    1889. 

  1889. 				self.parsed[key] = []
    1890. 

  1890. 			self.parsed[key].append(val)
    1891. 

  1891. 		# Incremental value? so let's add it
    1892. 

  1892. 		elif key in self.incremental:
    1893. 

  1893. 			self.parsed[key] = (self.parsed.get(key) or 0) + val
    1894. 

  1894. 		else:
    1895. 

  1895. 			self.parsed[key] = val
    1896. 

  1896. 		fancykey = dotted_spaces("%12s"%key)
    1897. 

  1897. 		Message(_("Added config %s : %s")%(fancykey,val),3)
    1898. 

  1898. 	
    1899. 

  1899. 	def get_outfile_name(self, config={}):
    1900. 

  1900. 		"Dirname is the same for {in,out}file"
    1901. 

  1901. 		infile, outfile = config['sourcefile'], config['outfile']
    1902. 

  1902. 		if outfile and outfile not in (STDOUT, MODULEOUT) \
    1903. 

  1903. 		   and not os.path.isabs(outfile):
    1904. 

  1904. 			outfile = os.path.join(os.path.dirname(infile), outfile)
    1905. 

  1905. 		if infile == STDIN    and not outfile: outfile = STDOUT
    1906. 

  1906. 		if infile == MODULEIN and not outfile: outfile = MODULEOUT
    1907. 

  1907. 		if not outfile and (infile and config.get('target')):
    1908. 

  1908. 			basename = re.sub('\.(txt|t2t)$','',infile)
    1909. 

  1909. 			outfile = "%s.%s"%(basename, config['target'])
    1910. 

  1910. 		Debug(" infile: '%s'"%infile , 1)
    1911. 

  1911. 		Debug("outfile: '%s'"%outfile, 1)
    1912. 

  1912. 		return outfile
    1913. 

  1913. 	
    1914. 

  1914. 	def sanity(self, config, gui=0):
    1915. 

  1915. 		"Basic config sanity checking"
    1916. 

  1916. 		if not config: return {}
    1917. 

  1917. 		target = config.get('target')
    1918. 

  1918. 		# Some actions don't require target specification
    1919. 

  1919. 		if not target:
    1920. 

  1920. 			for action in NO_TARGET:
    1921. 

  1921. 				if config.get(action):
    1922. 

  1922. 					target = 'txt'
    1923. 

  1923. 					break
    1924. 

  1924. 		# On GUI, some checking are skipped
    1925. 

  1925. 		if not gui:
    1926. 

  1926. 			# We *need* a target
    1927. 

  1927. 			if not target:
    1928. 

  1928. 				Error(_('No target specified (try --help)')+\
    1929. 

  1929. 				'\n\n'+\
    1930. 

  1930. 				_('Maybe trying to convert an old v1.x file?'))
    1931. 

  1931. 			# And of course, an infile also
    1932. 

  1932. 			if not config.get('infile'):
    1933. 

  1933. 				Error(_('Missing input file (try --help)'))
    1934. 

  1934. 			# Is the target valid?
    1935. 

  1935. 			if not TARGETS.count(target):
    1936. 

  1936. 				Error(_("Invalid target '%s' (try --help)")%\
    1937. 

  1937. 				     target)
    1938. 

  1938. 		# Ensure all keys are present
    1939. 

  1939. 		empty = self.defaults.copy() ; empty.update(config)
    1940. 

  1940. 		config = empty.copy()
    1941. 

  1941. 		# Check integers options
    1942. 

  1942. 		for key in config.keys():
    1943. 

  1943. 			if key in self.numeric:
    1944. 

  1944. 				try: config[key] = int(config[key])
    1945. 

  1945. 				except: Error(_('--%s value must be a number'
    1946. 

  1946. 				                )%key)
    1947. 

  1947. 		# Check split level value
    1948. 

  1948. 		if config['split'] not in (0,1,2):
    1949. 

  1949. 			Error(_('Option --split must be 0, 1 or 2'))
    1950. 

  1950. 		# --toc-only is stronger than others
    1951. 

  1951. 		if config['toc-only']:
    1952. 

  1952. 			config['headers'] = 0
    1953. 

  1953. 			config['toc']     = 0
    1954. 

  1954. 			config['split']   = 0
    1955. 

  1955. 			config['gui']     = 0
    1956. 

  1956. 			config['outfile'] = config['outfile'] or STDOUT
    1957. 

  1957. 		# Splitting is disable for now (future: HTML only, no STDOUT)
    1958. 

  1958. 		config['split'] = 0
    1959. 

  1959. 		# Restore target
    1960. 

  1960. 		config['target'] = target
    1961. 

  1961. 		# Set output file name
    1962. 

  1962. 		config['outfile'] = self.get_outfile_name(config)
    1963. 

  1963. 		# Checking suicide
    1964. 

  1964. 		if config['sourcefile'] == config['outfile'] and \
    1965. 

  1965. 		   config['outfile'] not in [STDOUT,MODULEOUT] and not gui:
    1966. 

  1966. 			Error(_("Input and Output files are the same: %s")%(
    1967. 

  1967. 			config['outfile']))
    1968. 

  1968. 		return config
    1969. 

  1969. 	
    1970. 

  1970. 	def parse(self):
    1971. 

  1971. 		"Returns the parsed config for the current target"
    1972. 

  1972. 		raw = self.get_target_raw()
    1973. 

  1973. 		for target, key, value in raw:
    1974. 

  1974. 			self.add(key, value)
    1975. 

  1975. 		Message(_("Added the following keys: %s")%string.join(
    1976. 

  1976. 		         self.parsed.keys(),', '),2)
    1977. 

  1977. 		return self.parsed.copy()
    1978. 

  1978. 	
    1979. 

  1979. 	def find_value(self, key='', target=''):
    1980. 

  1980. 		"Scans ALL raw config to find the desired key"
    1981. 

  1981. 		ret = []
    1982. 

  1982. 		# Scan and save all values found
    1983. 

  1983. 		for targ, k, val in self.raw:
    1984. 

  1984. 			if k == key and (targ == target or targ == 'all'):
    1985. 

  1985. 				ret.append(val)
    1986. 

  1986. 		if not ret: return ''
    1987. 

  1987. 		# If not multi value, return only the last found
    1988. 

  1988. 		if key in self.multi: return ret
    1989. 

  1989. 		else                : return ret[-1]
    1990. 

  1990. 

  1991. ########################################################################
    1992. 

  1992. 

  1993. class ConfigLines:
    1994. 

  1994. 	"""
    1995. 

  1995. 	ConfigLines class - the config file data extractor
    1996. 

  1996. 	
    1997. 

  1997. 	This class reads and parse the config lines on the %!key:val
    1998. 

  1998. 	format, converting it to RAW config. It deals with user
    1999. 

  1999. 	config file (RC file), source document CONF area and
    2000. 

  2000. 	%!includeconf directives.
    2001. 

  2001. 

  2002. 	Call it passing a file name or feed the desired config lines.
    2003. 

  2003. 	Then just call the get_raw_config() method and wait to
    2004. 

  2004. 	receive the full config data on the RAW format. This method
    2005. 

  2005. 	also follows the possible %!includeconf directives found on
    2006. 

  2006. 	the config lines. Example:
    2007. 

  2007. 

  2008. 	    raw = ConfigLines(file=".txt2tagsrc").get_raw_config()
    2009. 

  2009. 

  2010. 	The parse_line() method is also useful to be used alone,
    2011. 

  2011. 	to identify and tokenize a single config line. For example,
    2012. 

  2012. 	to get the %!include command components, on the source
    2013. 

  2013. 	document BODY:
    2014. 

  2014. 	
    2015. 

  2015. 	    target, key, value = ConfigLines().parse_line(body_line)
    2016. 

  2016. 	"""
    2017. 

  2017. 	def __init__(self, file='', lines=[], first_line=1):
    2018. 

  2018. 		self.file = file or 'NOFILE'
    2019. 

  2019. 		self.lines = lines
    2020. 

  2020. 		self.first_line = first_line
    2021. 

  2021. 	
    2022. 

  2022. 	def load_lines(self):
    2023. 

  2023. 		"Make sure we've loaded the file contents into buffer"
    2024. 

  2024. 		if not self.lines and not self.file:
    2025. 

  2025. 			Error("ConfigLines: No file or lines provided")
    2026. 

  2026. 		if not self.lines:
    2027. 

  2027. 			self.lines = self.read_config_file(self.file)
    2028. 

  2028. 	
    2029. 

  2029. 	def read_config_file(self, filename=''):
    2030. 

  2030. 		"Read a Config File contents, aborting on invalid line"
    2031. 

  2031. 		if not filename: return []
    2032. 

  2032. 		errormsg = _("Invalid CONFIG line on %s")+"\n%03d:%s"
    2033. 

  2033. 		lines = Readfile(filename, remove_linebreaks=1)
    2034. 

  2034. 		# Sanity: try to find invalid config lines
    2035. 

  2035. 		for i in xrange(len(lines)):
    2036. 

  2036. 			line = string.rstrip(lines[i])
    2037. 

  2037. 			if not line: continue  # empty
    2038. 

  2038. 			if line[0] != '%': Error(errormsg%(filename,i+1,line))
    2039. 

  2039. 		return lines
    2040. 

  2040. 	
    2041. 

  2041. 	def include_config_file(self, file=''):
    2042. 

  2042. 		"Perform the %!includeconf action, returning RAW config"
    2043. 

  2043. 		if not file: return []
    2044. 

  2044. 		# Current dir relative to the current file (self.file)
    2045. 

  2045. 		current_dir = os.path.dirname(self.file)
    2046. 

  2046. 		file = os.path.join(current_dir, file)
    2047. 

  2047. 		# Read and parse included config file contents
    2048. 

  2048. 		lines = self.read_config_file(file)
    2049. 

  2049. 		return ConfigLines(file=file, lines=lines).get_raw_config()
    2050. 

  2050. 	
    2051. 

  2051. 	def get_raw_config(self):
    2052. 

  2052. 		"Scan buffer and extract all config as RAW (including includes)"
    2053. 

  2053. 		ret = []
    2054. 

  2054. 		self.load_lines()
    2055. 

  2055. 		first = self.first_line
    2056. 

  2056. 		for i in xrange(len(self.lines)):
    2057. 

  2057. 			line = self.lines[i]
    2058. 

  2058. 			Message(_("Processing line %03d: %s")%(first+i,line),2)
    2059. 

  2059. 			target, key, val = self.parse_line(line)
    2060. 

  2060. 			if not key: continue    # no config on this line
    2061. 

  2061. 			if key == 'includeconf':
    2062. 

  2062. 				err = _('A file cannot include itself (loop!)')
    2063. 

  2063. 				if val == self.file:
    2064. 

  2064. 					Error("%s: %%!includeconf: %s"%(
    2065. 

  2065. 						err, self.file))
    2066. 

  2066. 				more_raw = self.include_config_file(val)
    2067. 

  2067. 				ret.extend(more_raw)
    2068. 

  2068. 				Message(_("Finished Config file inclusion: %s"
    2069. 

  2069. 				          )%(val),2)
    2070. 

  2070. 			else:
    2071. 

  2071. 				ret.append([target, key, val])
    2072. 

  2072. 				Message(_("Added %s")%key,3)
    2073. 

  2073. 		return ret
    2074. 

  2074. 	
    2075. 

  2075. 	def parse_line(self, line='', keyname='', target=''):
    2076. 

  2076. 		"Detects %!key:val config lines and extract data from it"
    2077. 

  2077. 		empty = ['', '', '']
    2078. 

  2078. 		if not line: return empty
    2079. 

  2079. 		no_target = ['target', 'includeconf']
    2080. 

  2080. 		re_name   = keyname or '[a-z]+'
    2081. 

  2081. 		re_target = target  or '[a-z]*'
    2082. 

  2082. 		# XXX TODO <value>\S.+?  requires TWO chars, breaks %!include:a
    2083. 

  2083. 		cfgregex  = re.compile("""
    2084. 

  2084. 		  ^%%!\s*               # leading id with opt spaces
    2085. 

  2085. 		  (?P<name>%s)\s*       # config name
    2086. 

  2086. 		  (\((?P<target>%s)\))? # optional target spec inside ()
    2087. 

  2087. 		  \s*:\s*               # key:value delimiter with opt spaces
    2088. 

  2088. 		  (?P<value>\S.+?)      # config value
    2089. 

  2089. 		  \s*$                  # rstrip() spaces and hit EOL
    2090. 

  2090. 		  """%(re_name,re_target), re.I+re.VERBOSE)
    2091. 

  2091. 		prepostregex = re.compile("""
    2092. 

  2092. 		                        # ---[ PATTERN ]---
    2093. 

  2093. 		  ^( "([^"]*)"          # "double quoted" or
    2094. 

  2094. 		   | '([^']*)'          # 'single quoted' or
    2095. 

  2095. 		   | ([^\s]+)           # single_word
    2096. 

  2096. 		   )
    2097. 

  2097. 		    \s+                 # separated by spaces
    2098. 

  2098. 		
    2099. 

  2099. 		                        # ---[ REPLACE ]---
    2100. 

  2100. 		       ( "([^"]*)"      # "double quoted" or
    2101. 

  2101. 		       | '([^']*)'      # 'single quoted' or
    2102. 

  2102. 		       | (.*)           # anything
    2103. 

  2103. 		           )
    2104. 

  2104. 		            \s*$
    2105. 

  2105. 		  """, re.VERBOSE)
    2106. 

  2106. 		guicolors = re.compile("^([^\s]+\s+){3}[^\s]+") # 4 tokens
    2107. 

  2107. 		match = cfgregex.match(line)
    2108. 

  2108. 		if not match: return empty
    2109. 

  2109. 		
    2110. 

  2110. 		name   = string.lower(match.group('name') or '')
    2111. 

  2111. 		target = string.lower(match.group('target') or 'all')
    2112. 

  2112. 		value  = match.group('value')
    2113. 

  2113. 		
    2114. 

  2114. 		# NO target keywords: force all targets
    2115. 

  2115. 		if name in no_target: target = 'all'
    2116. 

  2116. 		
    2117. 

  2117. 		# Special config for GUI colors
    2118. 

  2118. 		if name == 'guicolors':
    2119. 

  2119. 			valmatch = guicolors.search(value)
    2120. 

  2120. 			if not valmatch: return empty
    2121. 

  2121. 			value = re.split('\s+', value)
    2122. 

  2122. 		
    2123. 

  2123. 		# Special config with two quoted values (%!preproc: "foo" 'bar')
    2124. 

  2124. 		if name == 'preproc' or name == 'postproc':
    2125. 

  2125. 			valmatch = prepostregex.search(value)
    2126. 

  2126. 			if not valmatch: return empty
    2127. 

  2127. 			getval = valmatch.group
    2128. 

  2128. 			patt   = getval(2) or getval(3) or getval(4) or ''
    2129. 

  2129. 			repl   = getval(6) or getval(7) or getval(8) or ''
    2130. 

  2130. 			value  = (patt, repl)
    2131. 

  2131. 		return [target, name, value]
    2132. 

  2132. 

  2133. ##############################################################################
    2134. 

  2134. 

  2135. class MaskMaster:
    2136. 

  2136. 	"(Un)Protect important structures from escaping and formatting"
    2137. 

  2137. 	def __init__(self):
    2138. 

  2138. 		self.linkmask  = 'vvvLINKvvv'
    2139. 

  2139. 		self.monomask  = 'vvvMONOvvv'
    2140. 

  2140. 		self.macromask = 'vvvMACROvvv'
    2141. 

  2141. 		self.rawmask   = 'vvvRAWvvv'
    2142. 

  2142. 		self.tocmask   = 'vvvTOCvvv'
    2143. 

  2143. 		self.macroman  = MacroMaster()
    2144. 

  2144. 		self.reset()
    2145. 

  2145. 	
    2146. 

  2146. 	def reset(self):
    2147. 

  2147. 		self.linkbank = []
    2148. 

  2148. 		self.monobank = []
    2149. 

  2149. 		self.macrobank = []
    2150. 

  2150. 		self.rawbank = []
    2151. 

  2151. 	
    2152. 

  2152. 	def mask(self, line=''):
    2153. 

  2153. 		global AUTOTOC
    2154. 

  2154. 		
    2155. 

  2155. 		# Protect raw text
    2156. 

  2156. 		while regex['raw'].search(line):
    2157. 

  2157. 			txt = regex['raw'].search(line).group(1)
    2158. 

  2158. 			txt = doEscape(TARGET,txt)
    2159. 

  2159. 			self.rawbank.append(txt)
    2160. 

  2160. 			line = regex['raw'].sub(self.rawmask,line,1)
    2161. 

  2161. 		
    2162. 

  2162. 		# Protect pre-formatted font text
    2163. 

  2163. 		while regex['fontMono'].search(line):
    2164. 

  2164. 			txt = regex['fontMono'].search(line).group(1)
    2165. 

  2165. 			txt = doEscape(TARGET,txt)
    2166. 

  2166. 			self.monobank.append(txt)
    2167. 

  2167. 			line = regex['fontMono'].sub(self.monomask,line,1)
    2168. 

  2168. 		
    2169. 

  2169. 		# Protect macros
    2170. 

  2170. 		while regex['macros'].search(line):
    2171. 

  2171. 			txt = regex['macros'].search(line).group()
    2172. 

  2172. 			self.macrobank.append(txt)
    2173. 

  2173. 			line = regex['macros'].sub(self.macromask,line,1)
    2174. 

  2174. 		
    2175. 

  2175. 		# Protect TOC location
    2176. 

  2176. 		while regex['toc'].search(line):
    2177. 

  2177. 			line = regex['toc'].sub(self.tocmask,line)
    2178. 

  2178. 			AUTOTOC = 0
    2179. 

  2179. 		
    2180. 

  2180. 		# Protect URLs and emails
    2181. 

  2181. 		while regex['linkmark'].search(line) or \
    2182. 

  2182. 		      regex['link'    ].search(line):
    2183. 

  2183. 			
    2184. 

  2184. 			# Try to match plain or named links
    2185. 

  2185. 			match_link  = regex['link'].search(line)
    2186. 

  2186. 			match_named = regex['linkmark'].search(line)
    2187. 

  2187. 			
    2188. 

  2188. 			# Define the current match
    2189. 

  2189. 			if match_link and match_named:
    2190. 

  2190. 				# Both types found, which is the first?
    2191. 

  2191. 				m = match_link
    2192. 

  2192. 				if match_named.start() < match_link.start():
    2193. 

  2193. 					m = match_named
    2194. 

  2194. 			else:
    2195. 

  2195. 				# Just one type found, we're fine
    2196. 

  2196. 				m = match_link or match_named
    2197. 

  2197. 			
    2198. 

  2198. 			# Extract link data and apply mask
    2199. 

  2199. 			if m == match_link:              # plain link
    2200. 

  2200. 				link = m.group()
    2201. 

  2201. 				label = ''
    2202. 

  2202. 				link_re = regex['link']
    2203. 

  2203. 			else:                            # named link
    2204. 

  2204. 				link = m.group('link')
    2205. 

  2205. 				label = string.rstrip(m.group('label'))
    2206. 

  2206. 				link_re = regex['linkmark']
    2207. 

  2207. 			line = link_re.sub(self.linkmask,line,1)
    2208. 

  2208. 			
    2209. 

  2209. 			# Save link data to the link bank
    2210. 

  2210. 			self.linkbank.append((label, link))
    2211. 

  2211. 		return line
    2212. 

  2212. 	
    2213. 

  2213. 	def undo(self, line):
    2214. 

  2214. 		
    2215. 

  2215. 		# url & email
    2216. 

  2216. 		for label,url in self.linkbank:
    2217. 

  2217. 			link = get_tagged_link(label, url)
    2218. 

  2218. 			line = string.replace(line, self.linkmask, link, 1)
    2219. 

  2219. 		
    2220. 

  2220. 		# Expand macros
    2221. 

  2221. 		for macro in self.macrobank:
    2222. 

  2222. 			macro = self.macroman.expand(macro)
    2223. 

  2223. 			line = string.replace(line, self.macromask, macro, 1)
    2224. 

  2224. 		
    2225. 

  2225. 		# Expand verb
    2226. 

  2226. 		for mono in self.monobank:
    2227. 

  2227. 			open,close = TAGS['fontMonoOpen'],TAGS['fontMonoClose']
    2228. 

  2228. 			tagged = open+mono+close
    2229. 

  2229. 			line = string.replace(line, self.monomask, tagged, 1)
    2230. 

  2230. 		
    2231. 

  2231. 		# Expand raw
    2232. 

  2232. 		for raw in self.rawbank:
    2233. 

  2233. 			line = string.replace(line, self.rawmask, raw, 1)
    2234. 

  2234. 		
    2235. 

  2235. 		return line
    2236. 

  2236. 

  2237. 

  2238. ##############################################################################
    2239. 

  2239. 

  2240. 

  2241. class TitleMaster:
    2242. 

  2242. 	"Title things"
    2243. 

  2243. 	def __init__(self):
    2244. 

  2244. 		self.count = ['',0,0,0,0,0]
    2245. 

  2245. 		self.toc   = []
    2246. 

  2246. 		self.level = 0
    2247. 

  2247. 		self.kind  = ''
    2248. 

  2248. 		self.txt   = ''
    2249. 

  2249. 		self.label = ''
    2250. 

  2250. 		self.tag   = ''
    2251. 

  2251. 		self.tag_hold = []
    2252. 

  2252. 		self.last_level = 0
    2253. 

  2253. 		self.count_id = ''
    2254. 

  2254. 		self.user_labels = {}
    2255. 

  2255. 		self.anchor_count = 0
    2256. 

  2256. 		self.anchor_prefix = 'toc'
    2257. 

  2257. 	
    2258. 

  2258. 	def _open_close_blocks(self):
    2259. 

  2259. 		"Open new title blocks, closing the previous (if any)"
    2260. 

  2260. 		if not rules['titleblocks']: return
    2261. 

  2261. 		tag = ''
    2262. 

  2262. 		last = self.last_level
    2263. 

  2263. 		curr = self.level
    2264. 

  2264. 		
    2265. 

  2265. 		# Same level, just close the previous
    2266. 

  2266. 		if curr == last:
    2267. 

  2267. 			tag = TAGS.get('title%dClose'%last)
    2268. 

  2268. 			if tag: self.tag_hold.append(tag)
    2269. 

  2269. 		
    2270. 

  2270. 		# Section -> subsection, more depth
    2271. 

  2271. 		while curr > last:
    2272. 

  2272. 			last = last + 1
    2273. 

  2273. 			
    2274. 

  2274. 			# Open the new block of subsections
    2275. 

  2275. 			tag = TAGS.get('blockTitle%dOpen'%last)
    2276. 

  2276. 			if tag: self.tag_hold.append(tag)
    2277. 

  2277. 			
    2278. 

  2278. 			# Jump from title1 to title3 or more
    2279. 

  2279. 			# Fill the gap with an empty section
    2280. 

  2280. 			if curr - last > 0:
    2281. 

  2281. 				tag = TAGS.get('title%dOpen'%last)
    2282. 

  2282. 				tag = regex['x'].sub('', tag)      # del \a
    2283. 

  2283. 				if tag: self.tag_hold.append(tag)
    2284. 

  2284. 		
    2285. 

  2285. 		# Section <- subsection, less depth
    2286. 

  2286. 		while curr < last:
    2287. 

  2287. 			# Close the current opened subsection
    2288. 

  2288. 			tag = TAGS.get('title%dClose'%last)
    2289. 

  2289. 			if tag: self.tag_hold.append(tag)
    2290. 

  2290. 			
    2291. 

  2291. 			# Close the current opened block of subsections
    2292. 

  2292. 			tag = TAGS.get('blockTitle%dClose'%last)
    2293. 

  2293. 			if tag: self.tag_hold.append(tag)
    2294. 

  2294. 			
    2295. 

  2295. 			last = last - 1
    2296. 

  2296. 			
    2297. 

  2297. 			# Close the previous section of the same level
    2298. 

  2298. 			# The subsections were under it
    2299. 

  2299. 			if curr == last:
    2300. 

  2300. 				tag = TAGS.get('title%dClose'%last)
    2301. 

  2301. 				if tag: self.tag_hold.append(tag)
    2302. 

  2302. 	
    2303. 

  2303. 	def add(self, line):
    2304. 

  2304. 		"Parses a new title line."
    2305. 

  2305. 		if not line: return
    2306. 

  2306. 		self._set_prop(line)
    2307. 

  2307. 		self._open_close_blocks()
    2308. 

  2308. 		self._set_count_id()
    2309. 

  2309. 		self._set_label()
    2310. 

  2310. 		self._save_toc_info()
    2311. 

  2311. 	
    2312. 

  2312. 	def close_all(self):
    2313. 

  2313. 		"Closes all opened title blocks"
    2314. 

  2314. 		ret = []
    2315. 

  2315. 		ret.extend(self.tag_hold)
    2316. 

  2316. 		while self.level:
    2317. 

  2317. 			tag = TAGS.get('title%dClose'%self.level)
    2318. 

  2318. 			if tag: ret.append(tag)
    2319. 

  2319. 			tag = TAGS.get('blockTitle%dClose'%self.level)
    2320. 

  2320. 			if tag: ret.append(tag)
    2321. 

  2321. 			self.level = self.level - 1
    2322. 

  2322. 		return ret
    2323. 

  2323. 	
    2324. 

  2324. 	def _save_toc_info(self):
    2325. 

  2325. 		"Save TOC info, used by self.dump_marked_toc()"
    2326. 

  2326. 		self.toc.append((self.level, self.count_id,
    2327. 

  2327. 		                 self.txt  , self.label   ))
    2328. 

  2328. 	
    2329. 

  2329. 	def _set_prop(self, line=''):
    2330. 

  2330. 		"Extract info from original line and set data holders."
    2331. 

  2331. 		# Detect title type (numbered or not)
    2332. 

  2332. 		id = string.lstrip(line)[0]
    2333. 

  2333. 		if   id == '=': kind = 'title'
    2334. 

  2334. 		elif id == '+': kind = 'numtitle'
    2335. 

  2335. 		else: Error("Unknown Title ID '%s'"%id)
    2336. 

  2336. 		# Extract line info
    2337. 

  2337. 		match = regex[kind].search(line)
    2338. 

  2338. 		level = len(match.group('id'))
    2339. 

  2339. 		txt   = string.strip(match.group('txt'))
    2340. 

  2340. 		label = match.group('label')
    2341. 

  2341. 		# Parse info & save
    2342. 

  2342. 		if CONF['enum-title']: kind = 'numtitle'  # force
    2343. 

  2343. 		if rules['titleblocks']:
    2344. 

  2344. 			self.tag = TAGS.get('%s%dOpen'%(kind,level)) or \
    2345. 

  2345. 			           TAGS.get('title%dOpen'%level)
    2346. 

  2346. 		else:
    2347. 

  2347. 			self.tag = TAGS.get(kind+`level`) or \
    2348. 

  2348. 			           TAGS.get('title'+`level`)
    2349. 

  2349. 		self.last_level = self.level
    2350. 

  2350. 		self.kind  = kind
    2351. 

  2351. 		self.level = level
    2352. 

  2352. 		self.txt   = txt
    2353. 

  2353. 		self.label = label
    2354. 

  2354. 	
    2355. 

  2355. 	def _set_count_id(self):
    2356. 

  2356. 		"Compose and save the title count identifier (if needed)."
    2357. 

  2357. 		count_id = ''
    2358. 

  2358. 		if self.kind == 'numtitle' and not rules['autonumbertitle']:
    2359. 

  2359. 			# Manually increase title count
    2360. 

  2360. 			self.count[self.level] = self.count[self.level] +1
    2361. 

  2361. 			# Reset sublevels count (if any)
    2362. 

  2362. 			max_levels = len(self.count)
    2363. 

  2363. 			if self.level < max_levels-1:
    2364. 

  2364. 				for i in xrange(self.level+1, max_levels):
    2365. 

  2365. 					self.count[i] = 0
    2366. 

  2366. 			# Compose count id from hierarchy
    2367. 

  2367. 			for i in xrange(self.level):
    2368. 

  2368. 				count_id= "%s%d."%(count_id, self.count[i+1])
    2369. 

  2369. 		self.count_id = count_id
    2370. 

  2370. 	
    2371. 

  2371. 	def _set_label(self):
    2372. 

  2372. 		"Compose and save title label, used by anchors."
    2373. 

  2373. 		# Remove invalid chars from label set by user
    2374. 

  2374. 		self.label = re.sub('[^A-Za-z0-9_-]', '', self.label or '')
    2375. 

  2375. 		# Generate name as 15 first :alnum: chars
    2376. 

  2376. 		#TODO how to translate safely accented chars to plain?
    2377. 

  2377. 		#self.label = re.sub('[^A-Za-z0-9]', '', self.txt)[:15]
    2378. 

  2378. 		# 'tocN' label - sequential count, ignoring 'toc-level'
    2379. 

  2379. 		#self.label = self.anchor_prefix + str(len(self.toc)+1)
    2380. 

  2380. 	
    2381. 

  2381. 	def _get_tagged_anchor(self):
    2382. 

  2382. 		"Return anchor if user defined a label, or TOC is on."
    2383. 

  2383. 		ret = ''
    2384. 

  2384. 		label = self.label
    2385. 

  2385. 		if CONF['toc'] and self.level <= CONF['toc-level']:
    2386. 

  2386. 			# This count is needed bcos self.toc stores all
    2387. 

  2387. 			# titles, regardless of the 'toc-level' setting,
    2388. 

  2388. 			# so we can't use self.toc length to number anchors
    2389. 

  2389. 			self.anchor_count = self.anchor_count + 1
    2390. 

  2390. 			# Autonumber label (if needed)
    2391. 

  2391. 			label = label or '%s%s'%(
    2392. 

  2392. 			        self.anchor_prefix, self.anchor_count)
    2393. 

  2393. 		if label and TAGS['anchor']:
    2394. 

  2394. 			ret = regex['x'].sub(label,TAGS['anchor'])
    2395. 

  2395. 		return ret
    2396. 

  2396. 	
    2397. 

  2397. 	def _get_full_title_text(self):
    2398. 

  2398. 		"Returns the full title contents, already escaped."
    2399. 

  2399. 		ret = self.txt
    2400. 

  2400. 		# Insert count_id (if any) before text
    2401. 

  2401. 		if self.count_id:
    2402. 

  2402. 			ret = '%s %s'%(self.count_id, ret)
    2403. 

  2403. 		# Escape specials
    2404. 

  2404. 		ret = doEscape(TARGET, ret)
    2405. 

  2405. 		# Same targets needs final escapes on title lines
    2406. 

  2406. 		# It's here because there is a 'continue' after title
    2407. 

  2407. 		if rules['finalescapetitle']:
    2408. 

  2408. 			ret = doFinalEscape(TARGET, ret)
    2409. 

  2409. 		return ret
    2410. 

  2410. 	
    2411. 

  2411. 	def get(self):
    2412. 

  2412. 		"Returns the tagged title as a list."
    2413. 

  2413. 		ret = []
    2414. 

  2414. 		
    2415. 

  2415. 		# Maybe some anchoring before?
    2416. 

  2416. 		anchor = self._get_tagged_anchor()
    2417. 

  2417. 		self.tag = regex['_anchor'].sub(anchor, self.tag)
    2418. 

  2418. 		
    2419. 

  2419. 		### Compose & escape title text (TOC uses unescaped)
    2420. 

  2420. 		full_title = self._get_full_title_text()
    2421. 

  2421. 		
    2422. 

  2422. 		# Close previous section area
    2423. 

  2423. 		ret.extend(self.tag_hold)
    2424. 

  2424. 		self.tag_hold = []
    2425. 

  2425. 		 
    2426. 

  2426. 		# Finish title, adding "underline" on TXT target
    2427. 

  2427. 		tagged = regex['x'].sub(full_title, self.tag)
    2428. 

  2428. 		if TARGET == 'txt':
    2429. 

  2429. 			ret.append('') # blank line before
    2430. 

  2430. 			ret.append(tagged)
    2431. 

  2431. 			ret.append(regex['x'].sub('='*len(full_title),self.tag))
    2432. 

  2432. 			ret.append('') # blank line after
    2433. 

  2433. 		else:
    2434. 

  2434. 			ret.append(tagged)
    2435. 

  2435. 		return ret
    2436. 

  2436. 	
    2437. 

  2437. 	def dump_marked_toc(self, max_level=99):
    2438. 

  2438. 		"Dumps all toc itens as a valid t2t markup list"
    2439. 

  2439. 		#TODO maybe use quote+linebreaks instead lists
    2440. 

  2440. 		ret = []
    2441. 

  2441. 		toc_count = 1
    2442. 

  2442. 		for level, count_id, txt, label in self.toc:
    2443. 

  2443. 			if level > max_level: continue   # ignore
    2444. 

  2444. 			indent = '  '*level
    2445. 

  2445. 			id_txt = string.lstrip('%s %s'%(count_id, txt))
    2446. 

  2446. 			label = label or self.anchor_prefix+`toc_count`
    2447. 

  2447. 			toc_count = toc_count + 1
    2448. 

  2448. 			# TOC will have links
    2449. 

  2449. 			if TAGS['anchor']:
    2450. 

  2450. 				# TOC is more readable with master topics
    2451. 

  2451. 				# not linked at number. This is a stoled
    2452. 

  2452. 				# idea from Windows .CHM help files
    2453. 

  2453. 				if CONF['enum-title'] and level == 1:
    2454. 

  2454. 					tocitem = '%s+ [""%s"" #%s]'%(
    2455. 

  2455. 					          indent, txt, label)
    2456. 

  2456. 				else:
    2457. 

  2457. 					tocitem = '%s- [""%s"" #%s]'%(
    2458. 

  2458. 					          indent, id_txt, label)
    2459. 

  2459. 			# No links on TOC, just text
    2460. 

  2460. 			else:
    2461. 

  2461. 				# man don't reformat TOC lines, cool!
    2462. 

  2462. 				if TARGET == 'txt' or TARGET == 'man':
    2463. 

  2463. 					tocitem = '%s""%s""' %(
    2464. 

  2464. 					          indent, id_txt)
    2465. 

  2465. 				else:
    2466. 

  2466. 					tocitem = '%s- ""%s""'%(
    2467. 

  2467. 					          indent, id_txt)
    2468. 

  2468. 			ret.append(tocitem)
    2469. 

  2469. 		return ret
    2470. 

  2470. 

  2471. 

  2472. ##############################################################################
    2473. 

  2473. 

  2474. #TODO check all this table mess
    2475. 

  2475. # Trata linhas TABLE, com as prop do parse_row
    2476. 

  2476. # O metodo table() do BLOCK xunxa e troca as celulas pelas parseadas
    2477. 

  2477. class TableMaster:
    2478. 

  2478. 	def __init__(self, line=''):
    2479. 

  2479. 		self.rows      = []
    2480. 

  2480. 		self.border    = 0
    2481. 

  2481. 		self.align     = 'Left'
    2482. 

  2482. 		self.cellalign = []
    2483. 

  2483. 		self.cellspan  = []
    2484. 

  2484. 		if line:
    2485. 

  2485. 			prop = self.parse_row(line)
    2486. 

  2486. 			self.border    = prop['border']
    2487. 

  2487. 			self.align     = prop['align']
    2488. 

  2488. 			self.cellalign = prop['cellalign']
    2489. 

  2489. 			self.cellspan  = prop['cellspan']
    2490. 

  2490. 	
    2491. 

  2491. 	def _get_open_tag(self):
    2492. 

  2492. 		topen     = TAGS['tableOpen']
    2493. 

  2493. 		tborder   = TAGS['tableBorder']
    2494. 

  2494. 		talign    = TAGS['tableAlign'+self.align]
    2495. 

  2495. 		calignsep = TAGS['tableColAlignSep']
    2496. 

  2496. 		calign    = ''
    2497. 

  2497. 		
    2498. 

  2498. 		# The first line defines if table has border or not
    2499. 

  2499. 		if not self.border: tborder = ''
    2500. 

  2500. 		# Set the columns alignment
    2501. 

  2501. 		if rules['tablecellaligntype'] == 'column':
    2502. 

  2502. 			calign = map(lambda x: TAGS['tableColAlign%s'%x],
    2503. 

  2503. 			             self.cellalign)
    2504. 

  2504. 			calign = string.join(calign, calignsep)
    2505. 

  2505. 		# Align full table, set border and Column align (if any)
    2506. 

  2506. 		topen = regex['_tableAlign'   ].sub(talign , topen)
    2507. 

  2507. 		topen = regex['_tableBorder'  ].sub(tborder, topen)
    2508. 

  2508. 		topen = regex['_tableColAlign'].sub(calign , topen)
    2509. 

  2509. 		# Tex table spec, border or not: {|l|c|r|} , {lcr}
    2510. 

  2510. 		if calignsep and not self.border:
    2511. 

  2511. 			# Remove cell align separator
    2512. 

  2512. 			topen = string.replace(topen, calignsep, '')
    2513. 

  2513. 		return topen
    2514. 

  2514. 	
    2515. 

  2515. 	def _get_cell_align(self, cells):
    2516. 

  2516. 		ret = []
    2517. 

  2517. 		for cell in cells:
    2518. 

  2518. 			align = 'Left'
    2519. 

  2519. 			if string.strip(cell):
    2520. 

  2520. 				if cell[0] == ' ' and cell[-1] == ' ':
    2521. 

  2521. 					align = 'Center'
    2522. 

  2522. 				elif cell[0] == ' ':
    2523. 

  2523. 					align = 'Right'
    2524. 

  2524. 			ret.append(align)
    2525. 

  2525. 		return ret
    2526. 

  2526. 	
    2527. 

  2527. 	def _get_cell_span(self, cells):
    2528. 

  2528. 		ret = []
    2529. 

  2529. 		for cell in cells:
    2530. 

  2530. 			span = 0
    2531. 

  2531. 			m = re.search('\a(\|+)$', cell)
    2532. 

  2532. 			if m: span = len(m.group(1))+1
    2533. 

  2533. 			ret.append(span)
    2534. 

  2534. 		return ret
    2535. 

  2535. 	
    2536. 

  2536. 	def _tag_cells(self, rowdata):
    2537. 

  2537. 		row = []
    2538. 

  2538. 		cells  = rowdata['cells']
    2539. 

  2539. 		open   = TAGS['tableCellOpen']
    2540. 

  2540. 		close  = TAGS['tableCellClose']
    2541. 

  2541. 		sep    = TAGS['tableCellSep']
    2542. 

  2542. 		calign = map(lambda x: TAGS['tableCellAlign'+x],
    2543. 

  2543. 		             rowdata['cellalign'])
    2544. 

  2544. 		# Populate the span tag
    2545. 

  2545. 		cspan = []
    2546. 

  2546. 		for i in rowdata['cellspan']:
    2547. 

  2547. 			if i > 0:
    2548. 

  2548. 				cspan.append(regex['x'].sub(
    2549. 

  2549. 				str(i), TAGS['tableCellColSpan']))
    2550. 

  2550. 			else:
    2551. 

  2551. 				cspan.append('')
    2552. 

  2552. 		
    2553. 

  2553. 		# Maybe is it a title row?
    2554. 

  2554. 		if rowdata['title']:
    2555. 

  2555. 			open  = TAGS['tableTitleCellOpen']  or open
    2556. 

  2556. 			close = TAGS['tableTitleCellClose'] or close
    2557. 

  2557. 			sep   = TAGS['tableTitleCellSep']   or sep
    2558. 

  2558. 		
    2559. 

  2559. 		# Should we break the line on *each* table cell?
    2560. 

  2560. 		if rules['breaktablecell']: close = close+'\n'
    2561. 

  2561. 		
    2562. 

  2562. 		# Cells pre processing
    2563. 

  2563. 		if rules['tablecellstrip']:
    2564. 

  2564. 			cells = map(lambda x: string.strip(x), cells)
    2565. 

  2565. 		if rowdata['title'] and rules['tabletitlerowinbold']:
    2566. 

  2566. 			cells = map(lambda x: enclose_me('fontBold',x), cells)
    2567. 

  2567. 		
    2568. 

  2568. 		# Add cell BEGIN/END tags
    2569. 

  2569. 		for cell in cells:
    2570. 

  2570. 			copen = open
    2571. 

  2571. 			# Make sure we will pop from some filled lists
    2572. 

  2572. 			# Fixes empty line bug '| |'
    2573. 

  2573. 			this_align = this_span = ''
    2574. 

  2574. 			if calign: this_align = calign.pop(0)
    2575. 

  2575. 			if cspan : this_span = cspan.pop(0)
    2576. 

  2576. 			# Insert cell align into open tag (if cell is alignable)
    2577. 

  2577. 			if rules['tablecellaligntype'] == 'cell':
    2578. 

  2578. 				copen = regex['_tableCellAlign'].sub(
    2579. 

  2579. 					this_align, copen)
    2580. 

  2580. 			if rules['tablecellspannable']:
    2581. 

  2581. 				copen = regex['_tableCellColSpan'].sub(
    2582. 

  2582. 					this_span, copen)
    2583. 

  2583. 			row.append(copen + cell + close)
    2584. 

  2584. 		
    2585. 

  2585. 		# Maybe there are cell separators?
    2586. 

  2586. 		return string.join(row, sep)
    2587. 

  2587. 	
    2588. 

  2588. 	def add_row(self, cells):
    2589. 

  2589. 		self.rows.append(cells)
    2590. 

  2590. 	
    2591. 

  2591. 	def parse_row(self, line):
    2592. 

  2592. 		# Default table properties
    2593. 

  2593. 		ret = {'border':0,'title':0,'align':'Left',
    2594. 

  2594. 		       'cells':[],'cellalign':[], 'cellspan':[]}
    2595. 

  2595. 		# Detect table align (and remove spaces mark)
    2596. 

  2596. 		if line[0] == ' ': ret['align'] = 'Center'
    2597. 

  2597. 		line = string.lstrip(line)
    2598. 

  2598. 		# Detect title mark
    2599. 

  2599. 		if line[1] == '|': ret['title'] = 1
    2600. 

  2600. 		# Detect border mark and normalize the EOL
    2601. 

  2601. 		m = re.search(' (\|+) *$', line)
    2602. 

  2602. 		if m: line = line+' ' ; ret['border'] = 1
    2603. 

  2603. 		else: line = line+' | '
    2604. 

  2604. 		# Delete table mark
    2605. 

  2605. 		line = regex['table'].sub('', line)
    2606. 

  2606. 		# Detect colspan  | foo | bar baz |||
    2607. 

  2607. 		line = re.sub(' (\|+)\| ', '\a\\1 | ', line)
    2608. 

  2608. 		# Split cells (the last is fake)
    2609. 

  2609. 		ret['cells'] = string.split(line, ' | ')[:-1]
    2610. 

  2610. 		# Find cells span
    2611. 

  2611. 		ret['cellspan'] = self._get_cell_span(ret['cells'])
    2612. 

  2612. 		# Remove span ID
    2613. 

  2613. 		ret['cells'] = map(lambda x:re.sub('\a\|+$','',x),ret['cells'])
    2614. 

  2614. 		# Find cells align
    2615. 

  2615. 		ret['cellalign'] = self._get_cell_align(ret['cells'])
    2616. 

  2616. 		# Hooray!
    2617. 

  2617. 		Debug('Table Prop: %s' % ret, 7)
    2618. 

  2618. 		return ret
    2619. 

  2619. 	
    2620. 

  2620. 	def dump(self):
    2621. 

  2621. 		open  = self._get_open_tag()
    2622. 

  2622. 		rows  = self.rows
    2623. 

  2623. 		close = TAGS['tableClose']
    2624. 

  2624. 		
    2625. 

  2625. 		rowopen     = TAGS['tableRowOpen']
    2626. 

  2626. 		rowclose    = TAGS['tableRowClose']
    2627. 

  2627. 		rowsep      = TAGS['tableRowSep']
    2628. 

  2628. 		titrowopen  = TAGS['tableTitleRowOpen']  or rowopen
    2629. 

  2629. 		titrowclose = TAGS['tableTitleRowClose'] or rowclose
    2630. 

  2630. 		
    2631. 

  2631. 		if rules['breaktablelineopen']:
    2632. 

  2632. 			rowopen = rowopen + '\n'
    2633. 

  2633. 			titrowopen = titrowopen + '\n'
    2634. 

  2634. 		
    2635. 

  2635. 		# Tex gotchas
    2636. 

  2636. 		if TARGET == 'tex':
    2637. 

  2637. 			if not self.border:
    2638. 

  2638. 				rowopen = titrowopen = ''
    2639. 

  2639. 			else:
    2640. 

  2640. 				close = rowopen + close
    2641. 

  2641. 		
    2642. 

  2642. 		# Now we tag all the table cells on each row
    2643. 

  2643. 		#tagged_cells = map(lambda x: self._tag_cells(x), rows) #!py15
    2644. 

  2644. 		tagged_cells = []
    2645. 

  2645. 		for cell in rows: tagged_cells.append(self._tag_cells(cell))
    2646. 

  2646. 		
    2647. 

  2647. 		# Add row separator tags between lines
    2648. 

  2648. 		tagged_rows = []
    2649. 

  2649. 		if rowsep:
    2650. 

  2650. 			#!py15
    2651. 

  2651. 			#tagged_rows = map(lambda x:x+rowsep, tagged_cells)
    2652. 

  2652. 			for cell in tagged_cells:
    2653. 

  2653. 				tagged_rows.append(cell+rowsep)
    2654. 

  2654. 			# Remove last rowsep, because the table is over
    2655. 

  2655. 			tagged_rows[-1] = string.replace(
    2656. 

  2656. 			                  tagged_rows[-1], rowsep, '')
    2657. 

  2657. 		# Add row BEGIN/END tags for each line
    2658. 

  2658. 		else:
    2659. 

  2659. 			for rowdata in rows:
    2660. 

  2660. 				if rowdata['title']:
    2661. 

  2661. 					o,c = titrowopen, titrowclose
    2662. 

  2662. 				else:
    2663. 

  2663. 					o,c = rowopen, rowclose
    2664. 

  2664. 				row = tagged_cells.pop(0)
    2665. 

  2665. 				tagged_rows.append(o + row + c)
    2666. 

  2666. 		
    2667. 

  2667. 		fulltable = [open] + tagged_rows + [close]
    2668. 

  2668. 		
    2669. 

  2669. 		if rules['blankendtable']: fulltable.append('')
    2670. 

  2670. 		return fulltable
    2671. 

  2671. 

  2672. 

  2673. ##############################################################################
    2674. 

  2674. 

  2675. 

  2676. class BlockMaster:
    2677. 

  2677. 	"TIP: use blockin/out to add/del holders"
    2678. 

  2678. 	def __init__(self):
    2679. 

  2679. 		self.BLK = []
    2680. 

  2680. 		self.HLD = []
    2681. 

  2681. 		self.PRP = []
    2682. 

  2682. 		self.depth = 0
    2683. 

  2683. 		self.last = ''
    2684. 

  2684. 		self.tableparser = None
    2685. 

  2685. 		self.contains = {
    2686. 

  2686. 		  'para'    :['comment','raw'],
    2687. 

  2687. 		  'verb'    :[],
    2688. 

  2688. 		  'table'   :['comment'],
    2689. 

  2689. 		  'raw'     :[],
    2690. 

  2690. 		  'tagged'  :[],
    2691. 

  2691. 		  'comment' :[],
    2692. 

  2692. 		  'quote'   :['quote','comment','raw'],
    2693. 

  2693. 		  'list'    :['list' ,'numlist' ,'deflist','para','verb',
    2694. 

  2694. 		              'comment', 'raw'],
    2695. 

  2695. 		  'numlist' :['list' ,'numlist' ,'deflist','para','verb',
    2696. 

  2696. 		              'comment', 'raw'],
    2697. 

  2697. 		  'deflist' :['list' ,'numlist' ,'deflist','para','verb',
    2698. 

  2698. 		              'comment', 'raw']
    2699. 

  2699. 		}
    2700. 

  2700. 		self.allblocks = self.contains.keys()
    2701. 

  2701. 		# If one found inside another, ignore the marks
    2702. 

  2702. 		self.exclusive = ['comment','verb','raw']
    2703. 

  2703. 	
    2704. 

  2704. 	def block(self):
    2705. 

  2705. 		if not self.BLK: return ''
    2706. 

  2706. 		return self.BLK[-1]
    2707. 

  2707. 	
    2708. 

  2708. 	def isblock(self, name=''):
    2709. 

  2709. 		return self.block() == name
    2710. 

  2710. 	
    2711. 

  2711. 	def prop(self, key):
    2712. 

  2712. 		if not self.PRP: return ''
    2713. 

  2713. 		return self.PRP[-1].get(key) or ''
    2714. 

  2714. 	
    2715. 

  2715. 	def propset(self, key, val):
    2716. 

  2716. 		self.PRP[-1][key] = val
    2717. 

  2717. 		#Debug('BLOCK prop ++: %s->%s'%(key,repr(val)), 1)
    2718. 

  2718. 		#Debug('BLOCK props: %s'%(repr(self.PRP)), 1)
    2719. 

  2719. 	
    2720. 

  2720. 	def hold(self):
    2721. 

  2721. 		if not self.HLD: return []
    2722. 

  2722. 		return self.HLD[-1]
    2723. 

  2723. 	
    2724. 

  2724. 	def holdadd(self, line):
    2725. 

  2725. 		if self.block()[-4:] == 'list': line = [line]
    2726. 

  2726. 		self.HLD[-1].append(line)
    2727. 

  2727. 		Debug('HOLD add: %s'%repr(line), 4)
    2728. 

  2728. 		Debug('FULL HOLD: %s'%self.HLD, 4)
    2729. 

  2729. 	
    2730. 

  2730. 	def holdaddsub(self, line):
    2731. 

  2731. 		self.HLD[-1][-1].append(line)
    2732. 

  2732. 		Debug('HOLD addsub: %s'%repr(line), 4)
    2733. 

  2733. 		Debug('FULL HOLD: %s'%self.HLD, 4)
    2734. 

  2734. 	
    2735. 

  2735. 	def holdextend(self, lines):
    2736. 

  2736. 		if self.block()[-4:] == 'list': lines = [lines]
    2737. 

  2737. 		self.HLD[-1].extend(lines)
    2738. 

  2738. 		Debug('HOLD extend: %s'%repr(lines), 4)
    2739. 

  2739. 		Debug('FULL HOLD: %s'%self.HLD, 4)
    2740. 

  2740. 	
    2741. 

  2741. 	def blockin(self, block):
    2742. 

  2742. 		ret = []
    2743. 

  2743. 		if block not in self.allblocks:
    2744. 

  2744. 			Error("Invalid block '%s'"%block)
    2745. 

  2745. 		# First, let's close other possible open blocks
    2746. 

  2746. 		while self.block() and block not in self.contains[self.block()]:
    2747. 

  2747. 			ret.extend(self.blockout())
    2748. 

  2748. 		# Now we can gladly add this new one
    2749. 

  2749. 		self.BLK.append(block)
    2750. 

  2750. 		self.HLD.append([])
    2751. 

  2751. 		self.PRP.append({})
    2752. 

  2752. 		if block == 'table': self.tableparser = TableMaster()
    2753. 

  2753. 		# Deeper and deeper
    2754. 

  2754. 		self.depth = len(self.BLK)
    2755. 

  2755. 		Debug('block ++ (%s): %s' % (block,self.BLK), 3)
    2756. 

  2756. 		return ret
    2757. 

  2757. 	
    2758. 

  2758. 	def blockout(self):
    2759. 

  2759. 		if not self.BLK: Error('No block to pop')
    2760. 

  2760. 		self.last = self.BLK.pop()
    2761. 

  2761. 		result = getattr(self, self.last)()
    2762. 

  2762. 		parsed = self.HLD.pop()
    2763. 

  2763. 		self.PRP.pop()
    2764. 

  2764. 		self.depth = len(self.BLK)
    2765. 

  2765. 		if self.last == 'table': del self.tableparser
    2766. 

  2766. 		# Inserting a nested block into mother
    2767. 

  2767. 		if self.block():
    2768. 

  2768. 			if self.last != 'comment': # ignore comment blocks
    2769. 

  2769. 				if self.block()[-4:] == 'list':
    2770. 

  2770. 					self.HLD[-1][-1].append(result)
    2771. 

  2771. 				else:
    2772. 

  2772. 					self.HLD[-1].append(result)
    2773. 

  2773. 			# Reset now. Mother block will have it all
    2774. 

  2774. 			result = []
    2775. 

  2775. 		Debug('block -- (%s): %s' % (self.last,self.BLK), 3)
    2776. 

  2776. 		Debug('RELEASED (%s): %s' % (self.last,parsed), 3)
    2777. 

  2777. 		if result: Debug('BLOCK: %s'%result, 6)
    2778. 

  2778. 		return result
    2779. 

  2779. 	
    2780. 

  2780. 	def _last_escapes(self, line):
    2781. 

  2781. 		return doFinalEscape(TARGET, line)
    2782. 

  2782. 	
    2783. 

  2783. 	def _get_escaped_hold(self):
    2784. 

  2784. 		ret = []
    2785. 

  2785. 		for line in self.hold():
    2786. 

  2786. 			linetype = type(line)
    2787. 

  2787. 			if linetype == type(''):
    2788. 

  2788. 				ret.append(self._last_escapes(line))
    2789. 

  2789. 			elif linetype == type([]):
    2790. 

  2790. 				ret.extend(line)
    2791. 

  2791. 			else:
    2792. 

  2792. 				Error("BlockMaster: Unknown HOLD item type:"
    2793. 

  2793. 				      " %s"%linetype)
    2794. 

  2794. 		return ret
    2795. 

  2795. 	
    2796. 

  2796. 	def _remove_twoblanks(self, lastitem):
    2797. 

  2797. 		if len(lastitem) > 1 and lastitem[-2:] == ['','']:
    2798. 

  2798. 			return lastitem[:-2]
    2799. 

  2799. 		return lastitem
    2800. 

  2800. 	
    2801. 

  2801. 	def tagged(self):
    2802. 

  2802. 		return self.hold()
    2803. 

  2803. 	
    2804. 

  2804. 	def comment(self):
    2805. 

  2805. 		return ''
    2806. 

  2806. 	
    2807. 

  2807. 	def raw(self):
    2808. 

  2808. 		lines = self.hold()
    2809. 

  2809. 		return map(lambda x: doEscape(TARGET, x), lines)
    2810. 

  2810. 	
    2811. 

  2811. 	def para(self):
    2812. 

  2812. 		result = []
    2813. 

  2813. 		open  = TAGS['paragraphOpen']
    2814. 

  2814. 		close = TAGS['paragraphClose']
    2815. 

  2815. 		lines = self._get_escaped_hold()
    2816. 

  2816. 		# Open (or not) paragraph
    2817. 

  2817. 		if not open+close and self.last == 'para':
    2818. 

  2818. 			pass # avoids multiple blank lines
    2819. 

  2819. 		else:
    2820. 

  2820. 			result.append(open)
    2821. 

  2821. 		# Pagemaker likes a paragraph as a single long line
    2822. 

  2822. 		if rules['onelinepara']:
    2823. 

  2823. 			result.append(string.join(lines,' '))
    2824. 

  2824. 		# Others are normal :)
    2825. 

  2825. 		else:
    2826. 

  2826. 			result.extend(lines)
    2827. 

  2827. 		result.append(close)
    2828. 

  2828. 		
    2829. 

  2829. 		# Very very very very very very very very very UGLY fix
    2830. 

  2830. 		# Needed because <center> can't appear inside <p>
    2831. 

  2831. 		try:
    2832. 

  2832. 			if len(lines) == 1 and \
    2833. 

  2833. 			   TARGET in ('html', 'xhtml') and \
    2834. 

  2834. 			   re.match('^\s*<center>.*</center>\s*$', lines[0]):
    2835. 

  2835. 				result = [lines[0]]
    2836. 

  2836. 		except: pass
    2837. 

  2837. 		
    2838. 

  2838. 		return result
    2839. 

  2839. 	
    2840. 

  2840. 	def verb(self):
    2841. 

  2841. 		"Verbatim lines are not masked, so there's no need to unmask"
    2842. 

  2842. 		result = []
    2843. 

  2843. 		result.append(TAGS['blockVerbOpen'])
    2844. 

  2844. 		for line in self.hold():
    2845. 

  2845. 			if self.prop('mapped') == 'table':
    2846. 

  2846. 				line = MacroMaster().expand(line)
    2847. 

  2847. 			if not rules['verbblocknotescaped']:
    2848. 

  2848. 				line = doEscape(TARGET,line)
    2849. 

  2849. 			if rules['indentverbblock']:
    2850. 

  2850. 				line = '  '+line
    2851. 

  2851. 			if rules['verbblockfinalescape']:
    2852. 

  2852. 				line = doFinalEscape(TARGET, line)
    2853. 

  2853. 			result.append(line)
    2854. 

  2854. 		#TODO maybe use if not TAGS['blockVerbClose']
    2855. 

  2855. 		if TARGET != 'pm6':
    2856. 

  2856. 			result.append(TAGS['blockVerbClose'])
    2857. 

  2857. 		return result
    2858. 

  2858. 	
    2859. 

  2859. 	def table(self):
    2860. 

  2860. 		# Rewrite all table cells by the unmasked and escaped data
    2861. 

  2861. 		lines = self._get_escaped_hold()
    2862. 

  2862. 		for i in xrange(len(lines)):
    2863. 

  2863. 			cells = string.split(lines[i], SEPARATOR)
    2864. 

  2864. 			self.tableparser.rows[i]['cells'] = cells
    2865. 

  2865. 		
    2866. 

  2866. 		return self.tableparser.dump()
    2867. 

  2867. 	
    2868. 

  2868. 	def quote(self):
    2869. 

  2869. 		result = []
    2870. 

  2870. 		myre   = regex['quote']
    2871. 

  2871. 		open   = TAGS['blockQuoteOpen']            # block based
    2872. 

  2872. 		close  = TAGS['blockQuoteClose']
    2873. 

  2873. 		qline  = TAGS['blockQuoteLine']            # line based
    2874. 

  2874. 		indent = tagindent = '\t'*self.depth
    2875. 

  2875. 		if rules['tagnotindentable']: tagindent = ''
    2876. 

  2876. 		if not rules['keepquoteindent']: indent = ''
    2877. 

  2877. 		
    2878. 

  2878. 		if open: result.append(tagindent+open)     # open block
    2879. 

  2879. 		for item in self.hold():
    2880. 

  2880. 			if type(item) == type([]):
    2881. 

  2881. 				result.extend(item)        # subquotes
    2882. 

  2882. 			else:
    2883. 

  2883. 				item = myre.sub('', item)  # del TABs
    2884. 

  2884. 				if rules['barinsidequote']:
    2885. 

  2885. 					item = get_tagged_bar(item)
    2886. 

  2886. 				item = self._last_escapes(item)
    2887. 

  2887. 				item = qline*self.depth + item
    2888. 

  2888. 				result.append(indent+item) # quote line
    2889. 

  2889. 		if close: result.append(tagindent+close)   # close block
    2890. 

  2890. 		return result
    2891. 

  2891. 	
    2892. 

  2892. 	def deflist(self): return self.list('deflist')
    2893. 

  2893. 	def numlist(self): return self.list('numlist')
    2894. 

  2894. 	def list(self, name='list'):
    2895. 

  2895. 		result    = []
    2896. 

  2896. 		items     = self.hold()
    2897. 

  2897. 		indent    = self.prop('indent')
    2898. 

  2898. 		tagindent = indent
    2899. 

  2899. 		listopen  = TAGS.get(name+'Open')
    2900. 

  2900. 		listclose = TAGS.get(name+'Close')
    2901. 

  2901. 		listline  = TAGS.get(name+'ItemLine')
    2902. 

  2902. 		itemcount = 0
    2903. 

  2903. 		if rules['tagnotindentable']: tagindent = ''
    2904. 

  2904. 		if not rules['keeplistindent']: indent = ''
    2905. 

  2905. 		
    2906. 

  2906. 		if name == 'deflist':
    2907. 

  2907. 			itemopen  = TAGS[name+'Item1Open']
    2908. 

  2908. 			itemclose = TAGS[name+'Item2Close']
    2909. 

  2909. 			itemsep   = TAGS[name+'Item1Close']+\
    2910. 

  2910. 			            TAGS[name+'Item2Open']
    2911. 

  2911. 		else:
    2912. 

  2912. 			itemopen  = TAGS[name+'ItemOpen']
    2913. 

  2913. 			itemclose = TAGS[name+'ItemClose']
    2914. 

  2914. 			itemsep   = ''
    2915. 

  2915. 		
    2916. 

  2916. 		# ItemLine: number of leading chars identifies list depth
    2917. 

  2917. 		if listline:
    2918. 

  2918. 			itemopen  = listline*self.depth
    2919. 

  2919. 			# Dirty fix for mgp
    2920. 

  2920. 			if name == 'numlist': itemopen = itemopen + '\a. '
    2921. 

  2921. 		
    2922. 

  2922. 		# Remove two-blanks from list ending mark, to avoid <p>
    2923. 

  2923. 		items[-1] = self._remove_twoblanks(items[-1])
    2924. 

  2924. 		
    2925. 

  2925. 		# Open list (not nestable lists are only opened at mother)
    2926. 

  2926. 		if listopen and not \
    2927. 

  2927. 		   (rules['listnotnested'] and BLOCK.depth != 1):
    2928. 

  2928. 			result.append(tagindent+listopen)
    2929. 

  2929. 		
    2930. 

  2930. 		# Tag each list item (multiline items)
    2931. 

  2931. 		itemopenorig = itemopen
    2932. 

  2932. 		for item in items:
    2933. 

  2933. 			
    2934. 

  2934. 			# Add "manual" item count for noautonum targets
    2935. 

  2935. 			itemcount = itemcount + 1
    2936. 

  2936. 			if name == 'numlist' and not rules['autonumberlist']:
    2937. 

  2937. 				n = str(itemcount)
    2938. 

  2938. 				itemopen = regex['x'].sub(n, itemopenorig)
    2939. 

  2939. 				del n
    2940. 

  2940. 			
    2941. 

  2941. 			item[0] = self._last_escapes(item[0])
    2942. 

  2942. 			if name == 'deflist':
    2943. 

  2943. 				z,term,rest = string.split(item[0],SEPARATOR,2)
    2944. 

  2944. 				item[0] = rest
    2945. 

  2945. 				if not item[0]: del item[0]      # to avoid <p>
    2946. 

  2946. 				result.append(tagindent+itemopen+term+itemsep)
    2947. 

  2947. 			else:
    2948. 

  2948. 				fullitem = tagindent+itemopen
    2949. 

  2949. 				result.append(string.replace(
    2950. 

  2950. 				              item[0], SEPARATOR, fullitem))
    2951. 

  2951. 				del item[0]
    2952. 

  2952. 			
    2953. 

  2953. 			# Process next lines for this item (if any)
    2954. 

  2954. 			for line in item:
    2955. 

  2955. 				if type(line) == type([]): # sublist inside
    2956. 

  2956. 					result.extend(line)
    2957. 

  2957. 				else:
    2958. 

  2958. 					line = self._last_escapes(line)
    2959. 

  2959. 					# Blank lines turns to <p>
    2960. 

  2960. 					if not line and rules['parainsidelist']:
    2961. 

  2961. 						line = string.rstrip(indent   +\
    2962. 

  2962. 						         TAGS['paragraphOpen']+\
    2963. 

  2963. 						         TAGS['paragraphClose'])
    2964. 

  2964. 					if not rules['keeplistindent']:
    2965. 

  2965. 						line = string.lstrip(line)
    2966. 

  2966. 					result.append(line)
    2967. 

  2967. 			
    2968. 

  2968. 			# Close item (if needed)
    2969. 

  2969. 			if itemclose: result.append(tagindent+itemclose)
    2970. 

  2970. 		
    2971. 

  2971. 		# Close list (not nestable lists are only closed at mother)
    2972. 

  2972. 		if listclose and not \
    2973. 

  2973. 		   (rules['listnotnested'] and BLOCK.depth != 1):
    2974. 

  2974. 			result.append(tagindent+listclose)
    2975. 

  2975. 		
    2976. 

  2976. 		if rules['blankendmotherlist'] and BLOCK.depth == 1:
    2977. 

  2977. 			result.append('')
    2978. 

  2978. 		
    2979. 

  2979. 		return result
    2980. 

  2980. 

  2981. 

  2982. ##############################################################################
    2983. 

  2983. 

  2984. 

  2985. class MacroMaster:
    2986. 

  2986. 	def __init__(self, config={}):
    2987. 

  2987. 		self.name     = ''
    2988. 

  2988. 		self.config   = config or CONF
    2989. 

  2989. 		self.infile   = self.config['sourcefile']
    2990. 

  2990. 		self.outfile  = self.config['outfile']
    2991. 

  2991. 		self.currdate = time.localtime(time.time())
    2992. 

  2992. 		self.rgx      = regex.get('macros') or getRegexes()['macros']
    2993. 

  2993. 		self.fileinfo = { 'infile': None, 'outfile': None }
    2994. 

  2994. 		self.dft_fmt  = MACROS
    2995. 

  2995. 	
    2996. 

  2996. 	def walk_file_format(self, fmt):
    2997. 

  2997. 		"Walks the %%{in/out}file format string, expanding the % flags"
    2998. 

  2998. 		i = 0; ret = ''                                 # counter/hold
    2999. 

  2999. 		while i < len(fmt):                             # char by char
    3000. 

  3000. 			c = fmt[i]; i = i + 1
    3001. 

  3001. 			if c == '%':                            # hot char!
    3002. 

  3002. 				if i == len(fmt):               # % at the end
    3003. 

  3003. 					ret = ret + c
    3004. 

  3004. 					break
    3005. 

  3005. 				c = fmt[i]; i = i + 1           # read next
    3006. 

  3006. 				ret = ret + self.expand_file_flag(c)
    3007. 

  3007. 			else:
    3008. 

  3008. 				ret = ret +c                    # common char
    3009. 

  3009. 		return ret
    3010. 

  3010. 	
    3011. 

  3011. 	def expand_file_flag(self, flag):
    3012. 

  3012. 		"%f: filename          %F: filename (w/o extension)"
    3013. 

  3013. 		"%d: dirname           %D: dirname (only parent dir)"
    3014. 

  3014. 		"%p: file path         %e: extension"
    3015. 

  3015. 		info = self.fileinfo[self.name]           # get dict
    3016. 

  3016. 		if   flag == '%': x = '%'                 # %% -> %
    3017. 

  3017. 		elif flag == 'f': x = info['name']
    3018. 

  3018. 		elif flag == 'F': x = re.sub('\.[^.]*$','',info['name'])
    3019. 

  3019. 		elif flag == 'd': x = info['dir']
    3020. 

  3020. 		elif flag == 'D': x = os.path.split(info['dir'])[-1]
    3021. 

  3021. 		elif flag == 'p': x = info['path']
    3022. 

  3022. 		elif flag == 'e': x = re.search('.(\.([^.]+))?$',info['name']
    3023. 

  3023. 		                                ).group(2) or ''
    3024. 

  3024. 		#TODO simpler way for %e ?
    3025. 

  3025. 		else            : x = '%'+flag            # false alarm
    3026. 

  3026. 		return x
    3027. 

  3027. 	
    3028. 

  3028. 	def set_file_info(self, macroname):
    3029. 

  3029. 		if self.fileinfo.get(macroname): return   # already done
    3030. 

  3030. 		file = getattr(self, self.name)           # self.infile
    3031. 

  3031. 		if file == STDOUT or file == MODULEOUT:
    3032. 

  3032. 			dir = ''; path = name = file
    3033. 

  3033. 		else:
    3034. 

  3034. 			path = os.path.abspath(file)
    3035. 

  3035. 			dir  = os.path.dirname(path)
    3036. 

  3036. 			name = os.path.basename(path)
    3037. 

  3037. 		self.fileinfo[macroname] = {'path':path,'dir':dir,'name':name}
    3038. 

  3038. 	
    3039. 

  3039. 	def expand(self, line=''):
    3040. 

  3040. 		"Expand all macros found on the line"
    3041. 

  3041. 		while self.rgx.search(line):
    3042. 

  3042. 			m = self.rgx.search(line)
    3043. 

  3043. 			name = self.name = string.lower(m.group('name'))
    3044. 

  3044. 			fmt = m.group('fmt') or self.dft_fmt.get(name)
    3045. 

  3045. 			if name == 'date':
    3046. 

  3046. 				txt = time.strftime(fmt,self.currdate)
    3047. 

  3047. 			elif name == 'mtime':
    3048. 

  3048. 				if self.infile in (STDIN, MODULEIN):
    3049. 

  3049. 					fdate = self.currdate
    3050. 

  3050. 				else:
    3051. 

  3051. 					mtime = os.path.getmtime(self.infile)
    3052. 

  3052. 					fdate = time.localtime(mtime)
    3053. 

  3053. 				txt = time.strftime(fmt,fdate)
    3054. 

  3054. 			elif name == 'infile' or name == 'outfile':
    3055. 

  3055. 				self.set_file_info(name)
    3056. 

  3056. 				txt = self.walk_file_format(fmt)
    3057. 

  3057. 			else:
    3058. 

  3058. 				Error("Unknown macro name '%s'"%name)
    3059. 

  3059. 			line = self.rgx.sub(txt,line,1)
    3060. 

  3060. 		return line
    3061. 

  3061. 

  3062. 

  3063. ##############################################################################
    3064. 

  3064. 

  3065. 

  3066. def dumpConfig(source_raw, parsed_config):
    3067. 

  3067. 	onoff = {1:_('ON'), 0:_('OFF')}
    3068. 

  3068. 	data = [
    3069. 

  3069. 	  (_('RC file')        , RC_RAW     ),
    3070. 

  3070. 	  (_('source document'), source_raw ),
    3071. 

  3071. 	  (_('command line')   , CMDLINE_RAW)
    3072. 

  3072. 	]
    3073. 

  3073. 	# First show all RAW data found
    3074. 

  3074. 	for label, cfg in data:
    3075. 

  3075. 		print _('RAW config for %s')%label
    3076. 

  3076. 		for target,key,val in cfg:
    3077. 

  3077. 			target = '(%s)'%target
    3078. 

  3078. 			key    = dotted_spaces("%-14s"%key)
    3079. 

  3079. 			val    = val or _('ON')
    3080. 

  3080. 			print '  %-8s %s: %s'%(target,key,val)
    3081. 

  3081. 		print
    3082. 

  3082. 	# Then the parsed results of all of them
    3083. 

  3083. 	print _('Full PARSED config')
    3084. 

  3084. 	keys = parsed_config.keys() ; keys.sort()  # sorted
    3085. 

  3085. 	for key in keys:
    3086. 

  3086. 		val = parsed_config[key]
    3087. 

  3087. 		# Filters are the last
    3088. 

  3088. 		if key == 'preproc' or key == 'postproc':
    3089. 

  3089. 			continue
    3090. 

  3090. 		# Flag beautifier
    3091. 

  3091. 		if key in FLAGS.keys() or key in ACTIONS.keys():
    3092. 

  3092. 			val = onoff.get(val) or val
    3093. 

  3093. 		# List beautifier
    3094. 

  3094. 		if type(val) == type([]):
    3095. 

  3095. 			if key == 'options': sep = ' '
    3096. 

  3096. 			else               : sep = ', '
    3097. 

  3097. 			val = string.join(val, sep)
    3098. 

  3098. 		print "%25s: %s"%(dotted_spaces("%-14s"%key),val)
    3099. 

  3099. 	print
    3100. 

  3100. 	print _('Active filters')
    3101. 

  3101. 	for filter in ['preproc','postproc']:
    3102. 

  3102. 		for rule in parsed_config.get(filter) or []:
    3103. 

  3103. 			print "%25s: %s  ->  %s"%(
    3104. 

  3104. 			   dotted_spaces("%-14s"%filter),rule[0],rule[1])
    3105. 

  3105. 

  3106. 

  3107. def get_file_body(file):
    3108. 

  3108. 	"Returns all the document BODY lines"
    3109. 

  3109. 	return process_source_file(file, noconf=1)[1][2]
    3110. 

  3110. 

  3111. 

  3112. def finish_him(outlist, config):
    3113. 

  3113. 	"Writing output to screen or file"
    3114. 

  3114. 	outfile = config['outfile']
    3115. 

  3115. 	outlist = unmaskEscapeChar(outlist)
    3116. 

  3116. 	outlist = expandLineBreaks(outlist)
    3117. 

  3117. 	
    3118. 

  3118. 	# Apply PostProc filters
    3119. 

  3119. 	if config['postproc']:
    3120. 

  3120. 		filters = compile_filters(config['postproc'],
    3121. 

  3121. 		                        _('Invalid PostProc filter regex'))
    3122. 

  3122. 		postoutlist = []
    3123. 

  3123. 		errmsg = _('Invalid PostProc filter replacement')
    3124. 

  3124. 		for line in outlist:
    3125. 

  3125. 			for rgx,repl in filters:
    3126. 

  3126. 				try: line = rgx.sub(repl, line)
    3127. 

  3127. 				except: Error("%s: '%s'"%(errmsg, repl))
    3128. 

  3128. 			postoutlist.append(line)
    3129. 

  3129. 		outlist = postoutlist[:]
    3130. 

  3130. 	
    3131. 

  3131. 	if outfile == MODULEOUT:
    3132. 

  3132. 		return outlist
    3133. 

  3133. 	elif outfile == STDOUT:
    3134. 

  3134. 		if GUI:
    3135. 

  3135. 			return outlist, config
    3136. 

  3136. 		else:
    3137. 

  3137. 			for line in outlist: print line
    3138. 

  3138. 	else:
    3139. 

  3139. 		Savefile(outfile, addLineBreaks(outlist))
    3140. 

  3140. 		if not GUI and not QUIET:
    3141. 

  3141. 			print _('%s wrote %s')%(my_name,outfile)
    3142. 

  3142. 	
    3143. 

  3143. 	if config['split']:
    3144. 

  3144. 		if not QUIET: print "--- html..."
    3145. 

  3145. 		sgml2html = 'sgml2html -s %s -l %s %s'%(
    3146. 

  3146. 		            config['split'],config['lang'] or lang,outfile)
    3147. 

  3147. 		if not QUIET: print "Running system command:", sgml2html
    3148. 

  3148. 		os.system(sgml2html)
    3149. 

  3149. 

  3150. 

  3151. def toc_inside_body(body, toc, config):
    3152. 

  3152. 	ret = []
    3153. 

  3153. 	if AUTOTOC: return body                     # nothing to expand
    3154. 

  3154. 	toc_mark = MaskMaster().tocmask
    3155. 

  3155. 	# Expand toc mark with TOC contents
    3156. 

  3156. 	for line in body:
    3157. 

  3157. 		if string.count(line, toc_mark):    # toc mark found
    3158. 

  3158. 			if config['toc']:
    3159. 

  3159. 				ret.extend(toc)     # include if --toc
    3160. 

  3160. 			else:
    3161. 

  3161. 				pass                # or remove %%toc line
    3162. 

  3162. 		else:
    3163. 

  3163. 			ret.append(line)            # common line
    3164. 

  3164. 	return ret
    3165. 

  3165. 

  3166. def toc_tagger(toc, config):
    3167. 

  3167. 	"Convert t2t-marked TOC (it is a list) to target-tagged TOC"
    3168. 

  3168. 	ret = []
    3169. 

  3169. 	# Tag if TOC-only TOC "by hand" (target don't have a TOC tag)
    3170. 

  3170. 	if config['toc-only'] or (config['toc'] and not TAGS['TOC']):
    3171. 

  3171. 		fakeconf = config.copy()
    3172. 

  3172. 		fakeconf['headers']    = 0
    3173. 

  3173. 		fakeconf['toc-only']   = 0
    3174. 

  3174. 		fakeconf['mask-email'] = 0
    3175. 

  3175. 		fakeconf['preproc']    = []
    3176. 

  3176. 		fakeconf['postproc']   = []
    3177. 

  3177. 		fakeconf['css-sugar']  = 0
    3178. 

  3178. 		ret,foo = convert(toc, fakeconf)
    3179. 

  3179. 		set_global_config(config)   # restore config
    3180. 

  3180. 	# Target TOC is a tag
    3181. 

  3181. 	elif config['toc'] and TAGS['TOC']:
    3182. 

  3182. 		ret = [TAGS['TOC']]
    3183. 

  3183. 	return ret
    3184. 

  3184. 

  3185. def toc_formatter(toc, config):
    3186. 

  3186. 	"Formats TOC for automatic placement between headers and body"
    3187. 

  3187. 	if config['toc-only']: return toc              # no formatting needed
    3188. 

  3188. 	if not config['toc'] : return []               # TOC disabled
    3189. 

  3189. 	ret = toc
    3190. 

  3190. 	# TOC open/close tags (if any)
    3191. 

  3191. 	if TAGS['tocOpen' ]: ret.insert(0, TAGS['tocOpen'])
    3192. 

  3192. 	if TAGS['tocClose']: ret.append(TAGS['tocClose'])
    3193. 

  3193. 	# Autotoc specific formatting
    3194. 

  3194. 	if AUTOTOC:
    3195. 

  3195. 		if rules['autotocwithbars']:           # TOC between bars
    3196. 

  3196. 			para = TAGS['paragraphOpen']+TAGS['paragraphClose']
    3197. 

  3197. 			bar  = regex['x'].sub('-'*72,TAGS['bar1'])
    3198. 

  3198. 			tocbar = [para, bar, para]
    3199. 

  3199. 			ret = tocbar + ret + tocbar
    3200. 

  3200. 		if rules['blankendautotoc']:           # blank line after TOC
    3201. 

  3201. 			ret.append('')
    3202. 

  3202. 		if rules['autotocnewpagebefore']:      # page break before TOC
    3203. 

  3203. 			ret.insert(0,TAGS['pageBreak'])
    3204. 

  3204. 		if rules['autotocnewpageafter']:       # page break after TOC
    3205. 

  3205. 			ret.append(TAGS['pageBreak'])
    3206. 

  3206. 	return ret
    3207. 

  3207. 

  3208. 

  3209. def doHeader(headers, config):
    3210. 

  3210. 	if not config['headers']: return []
    3211. 

  3211. 	if not headers: headers = ['','','']
    3212. 

  3212. 	target = config['target']
    3213. 

  3213. 	if not HEADER_TEMPLATE.has_key(target):
    3214. 

  3214. 		Error("doheader: Unknow target '%s'"%target)
    3215. 

  3215. 	
    3216. 

  3216. 	if target in ('html','xhtml') and config.get('css-sugar'):
    3217. 

  3217. 		template = string.split(HEADER_TEMPLATE[target+'css'], '\n')
    3218. 

  3218. 	else:
    3219. 

  3219. 		template = string.split(HEADER_TEMPLATE[target], '\n')
    3220. 

  3220. 	
    3221. 

  3221. 	head_data = {'STYLE':[], 'ENCODING':''}
    3222. 

  3222. 	for key in head_data.keys():
    3223. 

  3223. 		val = config.get(string.lower(key))
    3224. 

  3224. 		# Remove .sty extension from each style filename (freaking tex)
    3225. 

  3225. 		# XXX Can't handle --style foo.sty,bar.sty
    3226. 

  3226. 		if target == 'tex' and key == 'STYLE':
    3227. 

  3227. 			val = map(lambda x:re.sub('(?i)\.sty$','',x), val)
    3228. 

  3228. 		if key == 'ENCODING':
    3229. 

  3229. 			val = get_encoding_string(val, target)
    3230. 

  3230. 		head_data[key] = val
    3231. 

  3231. 	# Parse header contents
    3232. 

  3232. 	for i in 0,1,2:
    3233. 

  3233. 		# Expand macros
    3234. 

  3234. 		contents = MacroMaster(config=config).expand(headers[i])
    3235. 

  3235. 		# Escapes - on tex, just do it if any \tag{} present
    3236. 

  3236. 		if target != 'tex' or \
    3237. 

  3237. 		  (target == 'tex' and re.search(r'\\\w+{', contents)):
    3238. 

  3238. 			contents = doEscape(target, contents)
    3239. 

  3239. 		if target == 'lout':
    3240. 

  3240. 			contents = doFinalEscape(target, contents)
    3241. 

  3241. 		
    3242. 

  3242. 		head_data['HEADER%d'%(i+1)] = contents
    3243. 

  3243. 	# css-inside removes STYLE line
    3244. 

  3244. 	#XXX In tex, this also removes the modules call (%!style:amsfonts)
    3245. 

  3245. 	if target in ('html','xhtml') and config.get('css-inside') and \
    3246. 

  3246. 	   config.get('style'):
    3247. 

  3247. 		head_data['STYLE'] = []
    3248. 

  3248. 	Debug("Header Data: %s"%head_data, 1)
    3249. 

  3249. 	# Scan for empty dictionary keys
    3250. 

  3250. 	# If found, scan template lines for that key reference
    3251. 

  3251. 	# If found, remove the reference
    3252. 

  3252. 	# If there isn't any other key reference on the same line, remove it
    3253. 

  3253. 	#TODO loop by template line > key
    3254. 

  3254. 	for key in head_data.keys():
    3255. 

  3255. 		if head_data.get(key): continue
    3256. 

  3256. 		for line in template:
    3257. 

  3257. 			if string.count(line, '%%(%s)s'%key):
    3258. 

  3258. 				sline = string.replace(line, '%%(%s)s'%key, '')
    3259. 

  3259. 				if not re.search(r'%\([A-Z0-9]+\)s', sline):
    3260. 

  3260. 					template.remove(line)
    3261. 

  3261. 	# Style is a multiple tag.
    3262. 

  3262. 	# - If none or just one, use default template
    3263. 

  3263. 	# - If two or more, insert extra lines in a loop (and remove original)
    3264. 

  3264. 	styles = head_data['STYLE']
    3265. 

  3265. 	if len(styles) == 1:
    3266. 

  3266. 		head_data['STYLE'] = styles[0]
    3267. 

  3267. 	elif len(styles) > 1:
    3268. 

  3268. 		style_mark = '%(STYLE)s'
    3269. 

  3269. 		for i in xrange(len(template)):
    3270. 

  3270. 			if string.count(template[i], style_mark):
    3271. 

  3271. 				while styles:
    3272. 

  3272. 					template.insert(i+1,
    3273. 

  3273. 						string.replace(
    3274. 

  3274. 							template[i],
    3275. 

  3275. 							style_mark,
    3276. 

  3276. 							styles.pop()))
    3277. 

  3277. 				del template[i]
    3278. 

  3278. 				break
    3279. 

  3279. 	# Populate template with data (dict expansion)
    3280. 

  3280. 	template = string.join(template, '\n') % head_data
    3281. 

  3281. 	
    3282. 

  3282. 	# Adding CSS contents into template (for --css-inside)
    3283. 

  3283. 	# This code sux. Dirty++
    3284. 

  3284. 	if target in ('html','xhtml') and config.get('css-inside') and \
    3285. 

  3285. 	   config.get('style'):
    3286. 

  3286. 		set_global_config(config) # usually on convert(), needed here
    3287. 

  3287. 		for i in xrange(len(config['style'])):
    3288. 

  3288. 			cssfile = config['style'][i]
    3289. 

  3289. 			if not os.path.isabs(cssfile):
    3290. 

  3290. 				infile = config.get('sourcefile')
    3291. 

  3291. 				cssfile = os.path.join(
    3292. 

  3292. 					os.path.dirname(infile), cssfile)
    3293. 

  3293. 			try:
    3294. 

  3294. 				contents = Readfile(cssfile, 1)
    3295. 

  3295. 				css = "\n%s\n%s\n%s\n%s\n" % (
    3296. 

  3296. 					doCommentLine("Included %s" % cssfile),
    3297. 

  3297. 					TAGS['cssOpen'],
    3298. 

  3298. 					string.join(contents, '\n'),
    3299. 

  3299. 					TAGS['cssClose'])
    3300. 

  3300. 				# Style now is content, needs escaping (tex)
    3301. 

  3301. 				#css = maskEscapeChar(css)
    3302. 

  3302. 			except:
    3303. 

  3303. 				errmsg = "CSS include failed for %s" % cssfile
    3304. 

  3304. 				css = "\n%s\n" % (doCommentLine(errmsg))
    3305. 

  3305. 			# Insert this CSS file contents on the template
    3306. 

  3306. 			template = re.sub('(?i)(</HEAD>)', css+r'\1', template)
    3307. 

  3307. 			# template = re.sub(r'(?i)(\\begin{document})',
    3308. 

  3308. 			#		css+'\n'+r'\1', template) # tex
    3309. 

  3309. 		
    3310. 

  3310. 		# The last blank line to keep everything separated
    3311. 

  3311. 		template = re.sub('(?i)(</HEAD>)', '\n'+r'\1', template)
    3312. 

  3312. 	
    3313. 

  3313. 	return string.split(template, '\n')
    3314. 

  3314. 

  3315. def doCommentLine(txt):
    3316. 

  3316. 	# The -- string ends a (h|sg|xht)ml comment :(
    3317. 

  3317. 	txt = maskEscapeChar(txt)
    3318. 

  3318. 	if string.count(TAGS['comment'], '--') and \
    3319. 

  3319. 	   string.count(txt, '--'):
    3320. 

  3320. 		txt = re.sub('-(?=-)', r'-\\', txt)
    3321. 

  3321. 	
    3322. 

  3322. 	if TAGS['comment']:
    3323. 

  3323. 		return regex['x'].sub(txt, TAGS['comment'])
    3324. 

  3324. 	return ''
    3325. 

  3325. 

  3326. def doFooter(config):
    3327. 

  3327. 	if not config['headers']: return []
    3328. 

  3328. 	ret = []
    3329. 

  3329. 	target = config['target']
    3330. 

  3330. 	cmdline = config['realcmdline']
    3331. 

  3331. 	typename = target
    3332. 

  3332. 	if target == 'tex': typename = 'LaTeX2e'
    3333. 

  3333. 	ppgd = '%s code generated by %s %s (%s)'%(
    3334. 

  3334. 	        typename,my_name,my_version,my_url)
    3335. 

  3335. 	cmdline = 'cmdline: %s %s'%(my_name, string.join(cmdline, ' '))
    3336. 

  3336. 	ret.append('')
    3337. 

  3337. 	ret.append(doCommentLine(ppgd))
    3338. 

  3338. 	ret.append(doCommentLine(cmdline))
    3339. 

  3339. 	ret.append(TAGS['EOD'])
    3340. 

  3340. 	return ret
    3341. 

  3341. 

  3342. def doEscape(target,txt):
    3343. 

  3343. 	"Target-specific special escapes. Apply *before* insert any tag."
    3344. 

  3344. 	tmpmask = 'vvvvThisEscapingSuxvvvv'
    3345. 

  3345. 	if target in ('html','sgml','xhtml'):
    3346. 

  3346. 		txt = re.sub('&','&amp;',txt)
    3347. 

  3347. 		txt = re.sub('<','&lt;',txt)
    3348. 

  3348. 		txt = re.sub('>','&gt;',txt)
    3349. 

  3349. 		if target == 'sgml':
    3350. 

  3350. 			txt = re.sub('\xff','&yuml;',txt)  # "+y
    3351. 

  3351. 	elif target == 'pm6':
    3352. 

  3352. 		txt = re.sub('<','<\#60>',txt)
    3353. 

  3353. 	elif target == 'mgp':
    3354. 

  3354. 		txt = re.sub('^%',' %',txt)  # add leading blank to avoid parse
    3355. 

  3355. 	elif target == 'man':
    3356. 

  3356. 		txt = re.sub("^([.'])", '\\&\\1',txt)           # command ID
    3357. 

  3357. 		txt = string.replace(txt,ESCCHAR, ESCCHAR+'e')  # \e
    3358. 

  3358. 	elif target == 'lout':
    3359. 

  3359. 		# TIP: / moved to FinalEscape to avoid //italic//
    3360. 

  3360. 		# TIP: these are also converted by lout:  ...  ---  --
    3361. 

  3361. 		txt = string.replace(txt, ESCCHAR, tmpmask)             # \
    3362. 

  3362. 		txt = string.replace(txt, '"', '"%s""'%ESCCHAR)         # "\""
    3363. 

  3363. 		txt = re.sub('([|&{}@#^~])', '"\\1"',txt)               # "@"
    3364. 

  3364. 		txt = string.replace(txt, tmpmask, '"%s"'%(ESCCHAR*2))  # "\\"
    3365. 

  3365. 	elif target == 'tex':
    3366. 

  3366. 		# Mark literal \ to be changed to $\backslash$ later
    3367. 

  3367. 		txt = string.replace( txt, ESCCHAR, tmpmask)
    3368. 

  3368. 		txt = re.sub('([#$&%{}])', ESCCHAR+r'\1'  , txt)  # \%
    3369. 

  3369. 		txt = re.sub('([~^])'    , ESCCHAR+r'\1{}', txt)  # \~{}
    3370. 

  3370. 		txt = re.sub('([<|>])'   ,         r'$\1$', txt)  # $>$
    3371. 

  3371. 		txt = string.replace(txt, tmpmask,
    3372. 

  3372. 		                     maskEscapeChar(r'$\backslash$'))
    3373. 

  3373. 		# TIP the _ is escaped at the end
    3374. 

  3374. 	return txt
    3375. 

  3375. 

  3376. # TODO man: where - really needs to be escaped?
    3377. 

  3377. def doFinalEscape(target, txt):
    3378. 

  3378. 	"Last escapes of each line"
    3379. 

  3379. 	if   target == 'pm6' : txt = string.replace(txt,ESCCHAR+'<',r'<\#92><')
    3380. 

  3380. 	elif target == 'man' : txt = string.replace(txt, '-', r'\-')
    3381. 

  3381. 	elif target == 'sgml': txt = string.replace(txt, '[', '&lsqb;')
    3382. 

  3382. 	elif target == 'lout': txt = string.replace(txt, '/', '"/"')
    3383. 

  3383. 	elif target == 'tex' :
    3384. 

  3384. 		txt = string.replace(txt, '_', r'\_')
    3385. 

  3385. 		txt = string.replace(txt, 'vvvvTexUndervvvv', '_')  # shame!
    3386. 

  3386. 	return txt
    3387. 

  3387. 

  3388. def EscapeCharHandler(action, data):
    3389. 

  3389. 	"Mask/Unmask the Escape Char on the given string"
    3390. 

  3390. 	if not string.strip(data): return data
    3391. 

  3391. 	if action not in ('mask','unmask'):
    3392. 

  3392. 		Error("EscapeCharHandler: Invalid action '%s'"%action)
    3393. 

  3393. 	if action == 'mask': return string.replace(data,'\\',ESCCHAR)
    3394. 

  3394. 	else:                return string.replace(data,ESCCHAR,'\\')
    3395. 

  3395. 

  3396. def maskEscapeChar(data):
    3397. 

  3397. 	"Replace any Escape Char \ with a text mask (Input: str or list)"
    3398. 

  3398. 	if type(data) == type([]):
    3399. 

  3399. 		return map(lambda x: EscapeCharHandler('mask', x), data)
    3400. 

  3400. 	return EscapeCharHandler('mask',data)
    3401. 

  3401. 

  3402. def unmaskEscapeChar(data):
    3403. 

  3403. 	"Undo the Escape char \ masking (Input: str or list)"
    3404. 

  3404. 	if type(data) == type([]):
    3405. 

  3405. 		return map(lambda x: EscapeCharHandler('unmask', x), data)
    3406. 

  3406. 	return EscapeCharHandler('unmask',data)
    3407. 

  3407. 

  3408. def addLineBreaks(mylist):
    3409. 

  3409. 	"use LB to respect sys.platform"
    3410. 

  3410. 	ret = []
    3411. 

  3411. 	for line in mylist:
    3412. 

  3412. 		line = string.replace(line,'\n',LB)  # embedded \n's
    3413. 

  3413. 		ret.append(line+LB)                  # add final line break
    3414. 

  3414. 	return ret
    3415. 

  3415. 

  3416. # Convert ['foo\nbar'] to ['foo', 'bar']
    3417. 

  3417. def expandLineBreaks(mylist):
    3418. 

  3418. 	ret = []
    3419. 

  3419. 	for line in mylist:
    3420. 

  3420. 		ret.extend(string.split(line, '\n'))
    3421. 

  3421. 	return ret
    3422. 

  3422. 

  3423. def compile_filters(filters, errmsg='Filter'):
    3424. 

  3424. 	if filters:
    3425. 

  3425. 		for i in xrange(len(filters)):
    3426. 

  3426. 			patt,repl = filters[i]
    3427. 

  3427. 			try: rgx = re.compile(patt)
    3428. 

  3428. 			except: Error("%s: '%s'"%(errmsg, patt))
    3429. 

  3429. 			filters[i] = (rgx,repl)
    3430. 

  3430. 	return filters
    3431. 

  3431. 

  3432. def enclose_me(tagname, txt):
    3433. 

  3433. 	return TAGS.get(tagname+'Open') + txt + TAGS.get(tagname+'Close')
    3434. 

  3434. 

  3435. def beautify_me(name, line):
    3436. 

  3436. 	"where name is: bold, italic or underline"
    3437. 

  3437. 	name  = 'font%s' % string.capitalize(name)
    3438. 

  3438. 	open  = TAGS['%sOpen'%name]
    3439. 

  3439. 	close = TAGS['%sClose'%name]
    3440. 

  3440. 	txt = r'%s\1%s'%(open, close)
    3441. 

  3441. 	line = regex[name].sub(txt,line)
    3442. 

  3442. 	return line
    3443. 

  3443. 

  3444. def get_tagged_link(label, url):
    3445. 

  3445. 	ret = ''
    3446. 

  3446. 	target = CONF['target']
    3447. 

  3447. 	image_re = regex['img']
    3448. 

  3448. 	
    3449. 

  3449. 	# Set link type
    3450. 

  3450. 	if regex['email'].match(url):
    3451. 

  3451. 		linktype = 'email'
    3452. 

  3452. 	else:
    3453. 

  3453. 		linktype = 'url';
    3454. 

  3454. 	
    3455. 

  3455. 	# Escape specials from TEXT parts
    3456. 

  3456. 	label = doEscape(target,label)
    3457. 

  3457. 	
    3458. 

  3458. 	# Escape specials from link URL
    3459. 

  3459. 	if not rules['linkable'] or rules['escapeurl']:
    3460. 

  3460. 		url = doEscape(target, url)
    3461. 

  3461. 	
    3462. 

  3462. 	# Adding protocol to guessed link
    3463. 

  3463. 	guessurl = ''
    3464. 

  3464. 	if linktype == 'url' and \
    3465. 

  3465. 	   re.match('(?i)'+regex['_urlskel']['guess'], url):
    3466. 

  3466. 		if url[0] in 'Ww': guessurl = 'http://' +url
    3467. 

  3467. 		else             : guessurl =  'ftp://' +url
    3468. 

  3468. 		
    3469. 

  3469. 		# Not link aware targets -> protocol is useless
    3470. 

  3470. 		if not rules['linkable']: guessurl = ''
    3471. 

  3471. 	
    3472. 

  3472. 	# Simple link (not guessed)
    3473. 

  3473. 	if not label and not guessurl:
    3474. 

  3474. 		if CONF['mask-email'] and linktype == 'email':
    3475. 

  3475. 			# Do the email mask feature (no TAGs, just text)
    3476. 

  3476. 			url = string.replace(url,'@',' (a) ')
    3477. 

  3477. 			url = string.replace(url,'.',' ')
    3478. 

  3478. 			url = "<%s>" % url
    3479. 

  3479. 			if rules['linkable']: url = doEscape(target, url)
    3480. 

  3480. 			ret = url
    3481. 

  3481. 		else:
    3482. 

  3482. 			# Just add link data to tag
    3483. 

  3483. 			tag = TAGS[linktype]
    3484. 

  3484. 			ret = regex['x'].sub(url,tag)
    3485. 

  3485. 	
    3486. 

  3486. 	# Named link or guessed simple link
    3487. 

  3487. 	else:
    3488. 

  3488. 		# Adjusts for guessed link
    3489. 

  3489. 		if not label: label = url         # no   protocol
    3490. 

  3490. 		if guessurl : url   = guessurl    # with protocol
    3491. 

  3491. 		
    3492. 

  3492. 		# Image inside link!
    3493. 

  3493. 		if image_re.match(label):
    3494. 

  3494. 			if rules['imglinkable']:  # get image tag
    3495. 

  3495. 				label = parse_images(label)
    3496. 

  3496. 			else:                     #  img@link !supported
    3497. 

  3497. 				label = "(%s)"%image_re.match(label).group(1)
    3498. 

  3498. 		
    3499. 

  3499. 		# Putting data on the right appearance order
    3500. 

  3500. 		if rules['linkable']:
    3501. 

  3501. 			urlorder = [url, label]   # link before label
    3502. 

  3502. 		else:
    3503. 

  3503. 			urlorder = [label, url]   # label before link
    3504. 

  3504. 		
    3505. 

  3505. 		# Add link data to tag (replace \a's)
    3506. 

  3506. 		ret = TAGS["%sMark"%linktype]
    3507. 

  3507. 		for data in urlorder:
    3508. 

  3508. 			ret = regex['x'].sub(data,ret,1)
    3509. 

  3509. 	
    3510. 

  3510. 	return ret
    3511. 

  3511. 

  3512. 

  3513. def parse_deflist_term(line):
    3514. 

  3514. 	"Extract and parse definition list term contents"
    3515. 

  3515. 	img_re = regex['img']
    3516. 

  3516. 	term   = regex['deflist'].search(line).group(3)
    3517. 

  3517. 	
    3518. 

  3518. 	# Mask image inside term as (image.jpg), where not supported
    3519. 

  3519. 	if not rules['imgasdefterm'] and img_re.search(term):
    3520. 

  3520. 		while img_re.search(term):
    3521. 

  3521. 			imgfile = img_re.search(term).group(1)
    3522. 

  3522. 			term = img_re.sub('(%s)'%imgfile, term, 1)
    3523. 

  3523. 	
    3524. 

  3524. 	#TODO tex: escape ] on term. \], \rbrack{} and \verb!]! don't work :(
    3525. 

  3525. 	return term
    3526. 

  3526. 

  3527. 

  3528. def get_tagged_bar(line):
    3529. 

  3529. 	m = regex['bar'].search(line)
    3530. 

  3530. 	if not m: return line
    3531. 

  3531. 	txt = m.group(2)
    3532. 

  3532. 	
    3533. 

  3533. 	# Map strong bar to pagebreak
    3534. 

  3534. 	if rules['mapbar2pagebreak'] and TAGS['pageBreak']:
    3535. 

  3535. 		TAGS['bar2'] = TAGS['pageBreak']
    3536. 

  3536. 	
    3537. 

  3537. 	# Set bar type
    3538. 

  3538. 	if txt[0] == '=': bar = TAGS['bar2']
    3539. 

  3539. 	else            : bar = TAGS['bar1']
    3540. 

  3540. 	
    3541. 

  3541. 	# To avoid comment tag confusion like <!-- ------ -->
    3542. 

  3542. 	if string.count(TAGS['comment'], '--'):
    3543. 

  3543. 		txt = string.replace(txt,'--','__')
    3544. 

  3544. 	
    3545. 

  3545. 	# Tag line
    3546. 

  3546. 	return regex['x'].sub(txt, bar)
    3547. 

  3547. 

  3548. 

  3549. def get_image_align(line):
    3550. 

  3550. 	"Return the image (first found) align for the given line"
    3551. 

  3551. 	
    3552. 

  3552. 	# First clear marks that can mess align detection
    3553. 

  3553. 	line = re.sub(SEPARATOR+'$', '', line)  # remove deflist sep
    3554. 

  3554. 	line = re.sub('^'+SEPARATOR, '', line)  # remove list sep
    3555. 

  3555. 	line = re.sub('^[\t]+'     , '', line)  # remove quote mark
    3556. 

  3556. 	
    3557. 

  3557. 	# Get image position on the line
    3558. 

  3558. 	m = regex['img'].search(line)
    3559. 

  3559. 	ini = m.start() ; head = 0
    3560. 

  3560. 	end = m.end()   ; tail = len(line)
    3561. 

  3561. 	
    3562. 

  3562. 	# The align detection algorithm
    3563. 

  3563. 	if   ini == head and end != tail: align = 'left'   # ^img + text$
    3564. 

  3564. 	elif ini != head and end == tail: align = 'right'  # ^text + img$
    3565. 

  3565. 	else                            : align = 'center' # default align
    3566. 

  3566. 	
    3567. 

  3567. 	# Some special cases
    3568. 

  3568. 	if BLOCK.isblock('table'): align = 'center'    # ignore when table
    3569. 

  3569. #	if TARGET == 'mgp' and align == 'center': align = 'center'
    3570. 

  3570. 	
    3571. 

  3571. 	return align
    3572. 

  3572. 

  3573. 

  3574. # Reference: http://www.iana.org/assignments/character-sets
    3575. 

  3575. # http://www.drclue.net/F1.cgi/HTML/META/META.html
    3576. 

  3576. def get_encoding_string(enc, target):
    3577. 

  3577. 	if not enc: return ''
    3578. 

  3578. 	# Target specific translation table
    3579. 

  3579. 	translate = {
    3580. 

  3580. 	'tex': {
    3581. 

  3581. 	  # missing: ansinew , applemac , cp437 , cp437de , cp865
    3582. 

  3582. 	  'us-ascii'    : 'ascii',
    3583. 

  3583. 	  'windows-1250': 'cp1250',
    3584. 

  3584. 	  'windows-1252': 'cp1252',
    3585. 

  3585. 	  'ibm850'      : 'cp850',
    3586. 

  3586. 	  'ibm852'      : 'cp852',
    3587. 

  3587. 	  'iso-8859-1'  : 'latin1',
    3588. 

  3588. 	  'iso-8859-2'  : 'latin2',
    3589. 

  3589. 	  'iso-8859-3'  : 'latin3',
    3590. 

  3590. 	  'iso-8859-4'  : 'latin4',
    3591. 

  3591. 	  'iso-8859-5'  : 'latin5',
    3592. 

  3592. 	  'iso-8859-9'  : 'latin9',
    3593. 

  3593. 	  'koi8-r'      : 'koi8-r'
    3594. 

  3594. 	  }
    3595. 

  3595. 	}
    3596. 

  3596. 	# Normalization
    3597. 

  3597. 	enc = re.sub('(?i)(us[-_]?)?ascii|us|ibm367','us-ascii'  , enc)
    3598. 

  3598. 	enc = re.sub('(?i)(ibm|cp)?85([02])'        ,'ibm85\\2'  , enc)
    3599. 

  3599. 	enc = re.sub('(?i)(iso[_-]?)?8859[_-]?'     ,'iso-8859-' , enc)
    3600. 

  3600. 	enc = re.sub('iso-8859-($|[^1-9]).*'        ,'iso-8859-1', enc)
    3601. 

  3601. 	# Apply translation table
    3602. 

  3602. 	try: enc = translate[target][string.lower(enc)]
    3603. 

  3603. 	except: pass
    3604. 

  3604. 	return enc
    3605. 

  3605. 

  3606. 

  3607. ##############################################################################
    3608. 

  3608. ##MerryChristmas,IdontwanttofighttonightwithyouImissyourbodyandIneedyourlove##
    3609. 

  3609. ##############################################################################
    3610. 

  3610. 

  3611. 

  3612. def process_source_file(file='', noconf=0, contents=[]):
    3613. 

  3613. 	"""
    3614. 

  3614. 	Find and Join all the configuration available for a source file.
    3615. 

  3615. 	No sanity checking is done on this step.
    3616. 

  3616. 	It also extracts the source document parts into separate holders.
    3617. 

  3617. 	
    3618. 

  3618. 	The config scan order is:
    3619. 

  3619. 	   1. The user configuration file (i.e. $HOME/.txt2tagsrc)
    3620. 

  3620. 	   2. The source document's CONF area
    3621. 

  3621. 	   3. The command line options
    3622. 

  3622. 

  3623. 	The return data is a tuple of two items:
    3624. 

  3624. 	   1. The parsed config dictionary
    3625. 

  3625. 	   2. The document's parts, as a (head, conf, body) tuple
    3626. 

  3626. 	
    3627. 

  3627. 	All the conversion process will be based on the data and
    3628. 

  3628. 	configuration returned by this function.
    3629. 

  3629. 	The source files is read on this step only.
    3630. 

  3630. 	"""
    3631. 

  3631. 	if contents:
    3632. 

  3632. 		source = SourceDocument(contents=contents)
    3633. 

  3633. 	else:
    3634. 

  3634. 		source = SourceDocument(file)
    3635. 

  3635. 	head, conf, body = source.split()
    3636. 

  3636. 	Message(_("Source document contents stored"),2)
    3637. 

  3637. 	if not noconf:
    3638. 

  3638. 		# Read document config
    3639. 

  3639. 		source_raw = source.get_raw_config()
    3640. 

  3640. 		# Join all the config directives found, then parse it
    3641. 

  3641. 		full_raw = RC_RAW + source_raw + CMDLINE_RAW
    3642. 

  3642. 		Message(_("Parsing and saving all config found (%03d items)")%(
    3643. 

  3643. 		        len(full_raw)),1)
    3644. 

  3644. 		full_parsed = ConfigMaster(full_raw).parse()
    3645. 

  3645. 		# Add manually the filename to the conf dic
    3646. 

  3646. 		if contents:
    3647. 

  3647. 			full_parsed['sourcefile'] = MODULEIN
    3648. 

  3648. 			full_parsed['infile'] = MODULEIN
    3649. 

  3649. 			full_parsed['outfile'] = MODULEOUT
    3650. 

  3650. 		else:
    3651. 

  3651. 			full_parsed['sourcefile'] = file
    3652. 

  3652. 		# Maybe should we dump the config found?
    3653. 

  3653. 		if full_parsed.get('dump-config'):
    3654. 

  3654. 			dumpConfig(source_raw, full_parsed)
    3655. 

  3655. 			Quit()
    3656. 

  3656. 		# Okay, all done
    3657. 

  3657. 		Debug("FULL config for this file: %s"%full_parsed, 1)
    3658. 

  3658. 	else:
    3659. 

  3659. 		full_parsed = {}
    3660. 

  3660. 	return full_parsed, (head,conf,body)
    3661. 

  3661. 

  3662. def get_infiles_config(infiles):
    3663. 

  3663. 	"""
    3664. 

  3664. 	Find and Join into a single list, all configuration available
    3665. 

  3665. 	for each input file. This function is supposed to be the very
    3666. 

  3666. 	first one to be called, before any processing.
    3667. 

  3667. 	"""
    3668. 

  3668. 	return map(process_source_file, infiles)
    3669. 

  3669. 

  3670. def convert_this_files(configs):
    3671. 

  3671. 	global CONF
    3672. 

  3672. 	for myconf,doc in configs:                 # multifile support
    3673. 

  3673. 		target_head = []
    3674. 

  3674. 		target_toc  = []
    3675. 

  3675. 		target_body = []
    3676. 

  3676. 		target_foot = []
    3677. 

  3677. 		source_head, source_conf, source_body = doc
    3678. 

  3678. 		myconf = ConfigMaster().sanity(myconf)
    3679. 

  3679. 		# Compose the target file Headers
    3680. 

  3680. 		#TODO escape line before?
    3681. 

  3681. 		#TODO see exceptions by tex and mgp
    3682. 

  3682. 		Message(_("Composing target Headers"),1)
    3683. 

  3683. 		target_head = doHeader(source_head, myconf)
    3684. 

  3684. 		# Parse the full marked body into tagged target
    3685. 

  3685. 		first_body_line = (len(source_head) or 1)+ len(source_conf) + 1
    3686. 

  3686. 		Message(_("Composing target Body"),1)
    3687. 

  3687. 		target_body, marked_toc = convert(source_body, myconf,
    3688. 

  3688. 		                          firstlinenr=first_body_line)
    3689. 

  3689. 		# If dump-source, we're done
    3690. 

  3690. 		if myconf['dump-source']:
    3691. 

  3691. 			for line in source_head+source_conf+target_body:
    3692. 

  3692. 				print line
    3693. 

  3693. 			return
    3694. 

  3694. 		# Make TOC (if needed)
    3695. 

  3695. 		Message(_("Composing target TOC"),1)
    3696. 

  3696. 		tagged_toc  = toc_tagger(marked_toc, myconf)
    3697. 

  3697. 		target_toc  = toc_formatter(tagged_toc, myconf)
    3698. 

  3698. 		target_body = toc_inside_body(target_body, target_toc, myconf)
    3699. 

  3699. 		if not AUTOTOC and not myconf['toc-only']: target_toc = []
    3700. 

  3700. 		# Compose the target file Footer
    3701. 

  3701. 		Message(_("Composing target Footer"),1)
    3702. 

  3702. 		target_foot = doFooter(myconf)
    3703. 

  3703. 		# Finally, we have our document
    3704. 

  3704. 		outlist = target_head + target_toc + target_body + target_foot
    3705. 

  3705. 		# If on GUI, abort before finish_him
    3706. 

  3706. 		# If module, return finish_him as list
    3707. 

  3707. 		# Else, write results to file or STDOUT
    3708. 

  3708. 		if GUI:
    3709. 

  3709. 			return outlist, myconf
    3710. 

  3710. 		elif myconf.get('outfile') == MODULEOUT:
    3711. 

  3711. 			return finish_him(outlist, myconf), myconf
    3712. 

  3712. 		else:
    3713. 

  3713. 			Message(_("Saving results to the output file"),1)
    3714. 

  3714. 			finish_him(outlist, myconf)
    3715. 

  3715. 

  3716. 

  3717. def parse_images(line):
    3718. 

  3718. 	"Tag all images found"
    3719. 

  3719. 	while regex['img'].search(line) and TAGS['img'] != '[\a]':
    3720. 

  3720. 		txt = regex['img'].search(line).group(1)
    3721. 

  3721. 		tag = TAGS['img']
    3722. 

  3722. 		
    3723. 

  3723. 		# HTML, XHTML and mgp!
    3724. 

  3724. 		if rules['imgalignable']:
    3725. 

  3725. 			align = get_image_align(line)
    3726. 

  3726. 			# Add align on tag
    3727. 

  3727. 			align_name = string.capitalize(align)
    3728. 

  3728. 			align_tag = TAGS['imgAlign'+align_name]
    3729. 

  3729. 			tag = regex['_imgAlign'].sub(align_tag, tag, 1)
    3730. 

  3730. 			# Dirty fix to allow centered solo images
    3731. 

  3731. 			if align == 'center' and TARGET in ('html','xhtml'):
    3732. 

  3732. 				rest = regex['img'].sub('',line,1)
    3733. 

  3733. 				if re.match('^\s+$', rest):
    3734. 

  3734. 					tag = "<center>%s</center>" %tag
    3735. 

  3735. 		
    3736. 

  3736. 		if TARGET == 'tex':
    3737. 

  3737. 			tag = re.sub(r'\\b',r'\\\\b',tag)
    3738. 

  3738. 			txt = string.replace(txt, '_', 'vvvvTexUndervvvv')
    3739. 

  3739. 		
    3740. 

  3740. 		line = regex['img'].sub(tag,line,1)
    3741. 

  3741. 		line = regex['x'].sub(txt,line,1)
    3742. 

  3742. 	return line
    3743. 

  3743. 

  3744. 

  3745. def add_inline_tags(line):
    3746. 

  3746. 	# Beautifiers
    3747. 

  3747. 	for beauti in ('Bold', 'Italic', 'Underline'):
    3748. 

  3748. 		if regex['font%s'%beauti].search(line):
    3749. 

  3749. 			line = beautify_me(beauti, line)
    3750. 

  3750. 	
    3751. 

  3751. 	line = parse_images(line)
    3752. 

  3752. 	return line
    3753. 

  3753. 

  3754. 

  3755. def get_include_contents(file, path=''):
    3756. 

  3756. 	"Parses %!include: value and extract file contents"
    3757. 

  3757. 	ids = {'`':'verb', '"':'raw', "'":'tagged' }
    3758. 

  3758. 	id = 't2t'
    3759. 

  3759. 	# Set include type and remove identifier marks
    3760. 

  3760. 	mark = file[0]
    3761. 

  3761. 	if mark in ids.keys():
    3762. 

  3762. 		if file[:2] == file[-2:] == mark*2:
    3763. 

  3763. 			id = ids[mark]     # set type
    3764. 

  3764. 			file = file[2:-2]  # remove marks
    3765. 

  3765. 	# Handle remote dir execution
    3766. 

  3766. 	filepath = os.path.join(path, file)
    3767. 

  3767. 	# Read included file contents
    3768. 

  3768. 	lines = Readfile(filepath, remove_linebreaks=1)
    3769. 

  3769. 	# Default txt2tags marked text, just BODY matters
    3770. 

  3770. 	if id == 't2t':
    3771. 

  3771. 		lines = get_file_body(filepath)
    3772. 

  3772. 		lines.insert(0, '%%INCLUDED(%s) starts here: %s'%(id,file))
    3773. 

  3773. 		# This appears when included hit EOF with verbatim area open
    3774. 

  3774. 		#lines.append('%%INCLUDED(%s) ends here: %s'%(id,file))
    3775. 

  3775. 	return id, lines
    3776. 

  3776. 

  3777. 

  3778. def set_global_config(config):
    3779. 

  3779. 	global CONF, TAGS, regex, rules, TARGET
    3780. 

  3780. 	CONF   = config
    3781. 

  3781. 	TAGS   = getTags(CONF)
    3782. 

  3782. 	rules  = getRules(CONF)
    3783. 

  3783. 	regex  = getRegexes()
    3784. 

  3784. 	TARGET = config['target']  # save for buggy functions that need global
    3785. 

  3785. 

  3786. 

  3787. def convert(bodylines, config, firstlinenr=1):
    3788. 

  3788. 	global BLOCK
    3789. 

  3789. 	
    3790. 

  3790. 	set_global_config(config)
    3791. 

  3791. 	
    3792. 

  3792. 	target = config['target']
    3793. 

  3793. 	BLOCK = BlockMaster()
    3794. 

  3794. 	MASK  =  MaskMaster()
    3795. 

  3795. 	TITLE = TitleMaster()
    3796. 

  3796. 	
    3797. 

  3797. 	ret = []
    3798. 

  3798. 	dump_source = []
    3799. 

  3799. 	f_lastwasblank = 0
    3800. 

  3800. 	
    3801. 

  3801. 	# Compiling all PreProc regexes
    3802. 

  3802. 	pre_filter = compile_filters(
    3803. 

  3803. 		CONF['preproc'], _('Invalid PreProc filter regex'))
    3804. 

  3804. 	
    3805. 

  3805. 	# Let's mark it up!
    3806. 

  3806. 	linenr = firstlinenr-1
    3807. 

  3807. 	lineref = 0
    3808. 

  3808. 	while lineref < len(bodylines):
    3809. 

  3809. 		# Defaults
    3810. 

  3810. 		MASK.reset()
    3811. 

  3811. 		results_box = ''
    3812. 

  3812. 		
    3813. 

  3813. 		untouchedline = bodylines[lineref]
    3814. 

  3814. 		dump_source.append(untouchedline)
    3815. 

  3815. 		
    3816. 

  3816. 		line = re.sub('[\n\r]+$','',untouchedline)   # del line break
    3817. 

  3817. 		
    3818. 

  3818. 		# Apply PreProc filters
    3819. 

  3819. 		if pre_filter:
    3820. 

  3820. 			errmsg = _('Invalid PreProc filter replacement')
    3821. 

  3821. 			for rgx,repl in pre_filter:
    3822. 

  3822. 				try: line = rgx.sub(repl, line)
    3823. 

  3823. 				except: Error("%s: '%s'"%(errmsg, repl))
    3824. 

  3824. 		
    3825. 

  3825. 		line = maskEscapeChar(line)                  # protect \ char
    3826. 

  3826. 		linenr  = linenr  +1
    3827. 

  3827. 		lineref = lineref +1
    3828. 

  3828. 		
    3829. 

  3829. 		Debug(repr(line), 2, linenr)  # heavy debug: show each line
    3830. 

  3830. 		
    3831. 

  3831. 		#------------------[ Comment Block ]------------------------
    3832. 

  3832. 		
    3833. 

  3833. 		# We're already on a comment block
    3834. 

  3834. 		if BLOCK.block() == 'comment':
    3835. 

  3835. 		
    3836. 

  3836. 			# Closing comment
    3837. 

  3837. 			if regex['blockCommentClose'].search(line):
    3838. 

  3838. 				ret.extend(BLOCK.blockout() or [])
    3839. 

  3839. 				continue
    3840. 

  3840. 			
    3841. 

  3841. 			# Normal comment-inside line. Ignore it.
    3842. 

  3842. 			continue
    3843. 

  3843. 		
    3844. 

  3844. 		# Detecting comment block init
    3845. 

  3845. 		if regex['blockCommentOpen'].search(line) \
    3846. 

  3846. 		   and BLOCK.block() not in BLOCK.exclusive:
    3847. 

  3847. 			ret.extend(BLOCK.blockin('comment'))
    3848. 

  3848. 			continue
    3849. 

  3849. 		
    3850. 

  3850. 		#-------------------------[ Raw Text ]----------------------
    3851. 

  3851. 		
    3852. 

  3852. 		# We're already on a raw block
    3853. 

  3853. 		if BLOCK.block() == 'raw':
    3854. 

  3854. 		
    3855. 

  3855. 			# Closing raw
    3856. 

  3856. 			if regex['blockRawClose'].search(line):
    3857. 

  3857. 				ret.extend(BLOCK.blockout())
    3858. 

  3858. 				continue
    3859. 

  3859. 			
    3860. 

  3860. 			# Normal raw-inside line
    3861. 

  3861. 			BLOCK.holdadd(line)
    3862. 

  3862. 			continue
    3863. 

  3863. 		
    3864. 

  3864. 		# Detecting raw block init
    3865. 

  3865. 		if regex['blockRawOpen'].search(line) \
    3866. 

  3866. 		   and BLOCK.block() not in BLOCK.exclusive:
    3867. 

  3867. 			ret.extend(BLOCK.blockin('raw'))
    3868. 

  3868. 			continue
    3869. 

  3869. 		
    3870. 

  3870. 		# One line raw text
    3871. 

  3871. 		if regex['1lineRaw'].search(line) \
    3872. 

  3872. 		   and BLOCK.block() not in BLOCK.exclusive:
    3873. 

  3873. 			ret.extend(BLOCK.blockin('raw'))
    3874. 

  3874. 			line = regex['1lineRaw'].sub('',line)
    3875. 

  3875. 			BLOCK.holdadd(line)
    3876. 

  3876. 			ret.extend(BLOCK.blockout())
    3877. 

  3877. 			continue
    3878. 

  3878. 		
    3879. 

  3879. 		#------------------------[ Verbatim  ]----------------------
    3880. 

  3880. 		
    3881. 

  3881. 		#TIP We'll never support beautifiers inside verbatim
    3882. 

  3882. 		
    3883. 

  3883. 		# Closing table mapped to verb
    3884. 

  3884. 		if BLOCK.block() == 'verb' \
    3885. 

  3885. 		   and BLOCK.prop('mapped') == 'table' \
    3886. 

  3886. 		   and not regex['table'].search(line):
    3887. 

  3887. 			ret.extend(BLOCK.blockout())
    3888. 

  3888. 		
    3889. 

  3889. 		# We're already on a verb block
    3890. 

  3890. 		if BLOCK.block() == 'verb':
    3891. 

  3891. 			
    3892. 

  3892. 			# Closing verb
    3893. 

  3893. 			if regex['blockVerbClose'].search(line):
    3894. 

  3894. 				ret.extend(BLOCK.blockout())
    3895. 

  3895. 				continue
    3896. 

  3896. 			
    3897. 

  3897. 			# Normal verb-inside line
    3898. 

  3898. 			BLOCK.holdadd(line)
    3899. 

  3899. 			continue
    3900. 

  3900. 		
    3901. 

  3901. 		# Detecting verb block init
    3902. 

  3902. 		if regex['blockVerbOpen'].search(line) \
    3903. 

  3903. 		   and BLOCK.block() not in BLOCK.exclusive:
    3904. 

  3904. 			ret.extend(BLOCK.blockin('verb'))
    3905. 

  3905. 			f_lastwasblank = 0
    3906. 

  3906. 			continue
    3907. 

  3907. 		
    3908. 

  3908. 		# One line verb-formatted text
    3909. 

  3909. 		if regex['1lineVerb'].search(line) \
    3910. 

  3910. 		   and BLOCK.block() not in BLOCK.exclusive:
    3911. 

  3911. 			ret.extend(BLOCK.blockin('verb'))
    3912. 

  3912. 			line = regex['1lineVerb'].sub('',line)
    3913. 

  3913. 			BLOCK.holdadd(line)
    3914. 

  3914. 			ret.extend(BLOCK.blockout())
    3915. 

  3915. 			f_lastwasblank = 0
    3916. 

  3916. 			continue
    3917. 

  3917. 		
    3918. 

  3918. 		# Tables are mapped to verb when target is not table-aware
    3919. 

  3919. 		if not rules['tableable'] and regex['table'].search(line):
    3920. 

  3920. 			if not BLOCK.isblock('verb'):
    3921. 

  3921. 				ret.extend(BLOCK.blockin('verb'))
    3922. 

  3922. 				BLOCK.propset('mapped', 'table')
    3923. 

  3923. 				BLOCK.holdadd(line)
    3924. 

  3924. 				continue
    3925. 

  3925. 		
    3926. 

  3926. 		#---------------------[ blank lines ]-----------------------
    3927. 

  3927. 		
    3928. 

  3928. 		if regex['blankline'].search(line):
    3929. 

  3929. 			
    3930. 

  3930. 			# Close open paragraph
    3931. 

  3931. 			if BLOCK.isblock('para'):
    3932. 

  3932. 				ret.extend(BLOCK.blockout())
    3933. 

  3933. 				f_lastwasblank = 1
    3934. 

  3934. 				continue
    3935. 

  3935. 			
    3936. 

  3936. 			# Close all open tables
    3937. 

  3937. 			if BLOCK.isblock('table'):
    3938. 

  3938. 				ret.extend(BLOCK.blockout())
    3939. 

  3939. 				f_lastwasblank = 1
    3940. 

  3940. 				continue
    3941. 

  3941. 			
    3942. 

  3942. 			# Close all open quotes
    3943. 

  3943. 			while BLOCK.isblock('quote'):
    3944. 

  3944. 				ret.extend(BLOCK.blockout())
    3945. 

  3945. 			
    3946. 

  3946. 			# Closing all open lists
    3947. 

  3947. 			if f_lastwasblank:          # 2nd consecutive blank
    3948. 

  3948. 				if BLOCK.block()[-4:] == 'list':
    3949. 

  3949. 					BLOCK.holdaddsub('')   # helps parser
    3950. 

  3950. 				while BLOCK.depth:  # closes list (if any)
    3951. 

  3951. 					ret.extend(BLOCK.blockout())
    3952. 

  3952. 				continue            # ignore consecutive blanks
    3953. 

  3953. 			
    3954. 

  3954. 			# Paragraph (if any) is wanted inside lists also
    3955. 

  3955. 			if BLOCK.block()[-4:] == 'list':
    3956. 

  3956. 				BLOCK.holdaddsub('')
    3957. 

  3957. 			else:
    3958. 

  3958. 				# html: show blank line (needs tag)
    3959. 

  3959. 				if target in ('html','xhtml'):
    3960. 

  3960. 					ret.append(TAGS['paragraphOpen']+\
    3961. 

  3961. 					           TAGS['paragraphClose'])
    3962. 

  3962. 				# Otherwise we just show a blank line
    3963. 

  3963. 				else:
    3964. 

  3964. 					ret.append('')
    3965. 

  3965. 			
    3966. 

  3966. 			f_lastwasblank = 1
    3967. 

  3967. 			continue
    3968. 

  3968. 		
    3969. 

  3969. 		
    3970. 

  3970. 		#---------------------[ special ]---------------------------
    3971. 

  3971. 		
    3972. 

  3972. 		if regex['special'].search(line):
    3973. 

  3973. 			# Include command
    3974. 

  3974. 			targ, key, val = ConfigLines().parse_line(
    3975. 

  3975. 			                   line, 'include', target)
    3976. 

  3976. 			if key:
    3977. 

  3977. 				Debug("Found config '%s', value '%s'"%(
    3978. 

  3978. 				       key,val),1,linenr)
    3979. 

  3979. 				
    3980. 

  3980. 				incpath = os.path.dirname(CONF['sourcefile'])
    3981. 

  3981. 				incfile = val
    3982. 

  3982. 				err = _('A file cannot include itself (loop!)')
    3983. 

  3983. 				if CONF['sourcefile'] == incfile:
    3984. 

  3984. 					Error("%s: %s"%(err,incfile))
    3985. 

  3985. 				inctype, inclines = get_include_contents(
    3986. 

  3986. 				                      incfile, incpath)
    3987. 

  3987. 				# Verb, raw and tagged are easy
    3988. 

  3988. 				if inctype != 't2t':
    3989. 

  3989. 					ret.extend(BLOCK.blockin(inctype))
    3990. 

  3990. 					BLOCK.holdextend(inclines)
    3991. 

  3991. 					ret.extend(BLOCK.blockout())
    3992. 

  3992. 				else:
    3993. 

  3993. 					# Insert include lines into body
    3994. 

  3994. 					#TODO include maxdepth limit
    3995. 

  3995. 					bodylines = bodylines[:lineref] \
    3996. 

  3996. 					           +inclines \
    3997. 

  3997. 					           +bodylines[lineref:]
    3998. 

  3998. 					#TODO fix path if include@include
    3999. 

  3999. 					# Remove %!include call
    4000. 

  4000. 					if CONF['dump-source']:
    4001. 

  4001. 						dump_source.pop()
    4002. 

  4002. 				continue
    4003. 

  4003. 			else:
    4004. 

  4004. 				Debug('Bogus Special Line',1,linenr)
    4005. 

  4005. 		
    4006. 

  4006. 		#---------------------[ dump-source ]-----------------------
    4007. 

  4007. 		
    4008. 

  4008. 		# We don't need to go any further
    4009. 

  4009. 		if CONF['dump-source']:
    4010. 

  4010. 			continue
    4011. 

  4011. 		
    4012. 

  4012. 		#---------------------[ Comments ]--------------------------
    4013. 

  4013. 		
    4014. 

  4014. 		# Just skip them (if not macro)
    4015. 

  4015. 		if regex['comment'].search(line) and not \
    4016. 

  4016. 		   regex['macros'].match(line) and not \
    4017. 

  4017. 		   regex['toc'].match(line):
    4018. 

  4018. 			continue
    4019. 

  4019. 		
    4020. 

  4020. 		#---------------------[ Triggers ]--------------------------
    4021. 

  4021. 		
    4022. 

  4022. 		# Valid line, reset blank status
    4023. 

  4023. 		f_lastwasblank = 0
    4024. 

  4024. 		
    4025. 

  4025. 		# Any NOT quote line closes all open quotes
    4026. 

  4026. 		if BLOCK.isblock('quote') and not regex['quote'].search(line):
    4027. 

  4027. 			while BLOCK.isblock('quote'):
    4028. 

  4028. 				ret.extend(BLOCK.blockout())
    4029. 

  4029. 		
    4030. 

  4030. 		# Any NOT table line closes an open table
    4031. 

  4031. 		if BLOCK.isblock('table') and not regex['table'].search(line):
    4032. 

  4032. 			ret.extend(BLOCK.blockout())
    4033. 

  4033. 		
    4034. 

  4034. 		
    4035. 

  4035. 		#---------------------[ Horizontal Bar ]--------------------
    4036. 

  4036. 		
    4037. 

  4037. 		if regex['bar'].search(line):
    4038. 

  4038. 			
    4039. 

  4039. 			# A bar closes a paragraph
    4040. 

  4040. 			if BLOCK.isblock('para'):
    4041. 

  4041. 				ret.extend(BLOCK.blockout())
    4042. 

  4042. 			
    4043. 

  4043. 			# We need to close all opened quote blocks
    4044. 

  4044. 			# if bar isn't allowed inside or if not a quote line
    4045. 

  4045. 			if BLOCK.isblock('quote'):
    4046. 

  4046. 				if not rules['barinsidequote'] or \
    4047. 

  4047. 				   not regex['quote'].search(line):
    4048. 

  4048. 					while BLOCK.isblock('quote'):
    4049. 

  4049. 						ret.extend(BLOCK.blockout())
    4050. 

  4050. 			
    4051. 

  4051. 			# Quote + bar: continue processing for quoting
    4052. 

  4052. 			if rules['barinsidequote'] and \
    4053. 

  4053. 			   regex['quote'].search(line):
    4054. 

  4054. 				pass
    4055. 

  4055. 			
    4056. 

  4056. 			# Just bar: save tagged line and we're done
    4057. 

  4057. 			else:
    4058. 

  4058. 				line = get_tagged_bar(line)
    4059. 

  4059. 				if BLOCK.block()[-4:] == 'list':
    4060. 

  4060. 					BLOCK.holdaddsub(line)
    4061. 

  4061. 				elif BLOCK.block():
    4062. 

  4062. 					BLOCK.holdadd(line)
    4063. 

  4063. 				else:
    4064. 

  4064. 					ret.append(line)
    4065. 

  4065. 					Debug("BAR: %s"%line, 6)
    4066. 

  4066. 				continue
    4067. 

  4067. 		
    4068. 

  4068. 		#---------------------[ Title ]-----------------------------
    4069. 

  4069. 		
    4070. 

  4070. 		#TODO set next blank and set f_lastwasblank or f_lasttitle
    4071. 

  4071. 		if (regex['title'].search(line) or
    4072. 

  4072. 		    regex['numtitle'].search(line)) and \
    4073. 

  4073. 		    BLOCK.block()[-4:] != 'list':
    4074. 

  4074. 			
    4075. 

  4075. 			# A title closes a paragraph
    4076. 

  4076. 			if BLOCK.isblock('para'):
    4077. 

  4077. 				ret.extend(BLOCK.blockout())
    4078. 

  4078. 			
    4079. 

  4079. 			TITLE.add(line)
    4080. 

  4080. 			tagged_title = TITLE.get()
    4081. 

  4081. 			ret.extend(tagged_title)
    4082. 

  4082. 			Debug("TITLE: %s"%tagged_title, 6)
    4083. 

  4083. 			
    4084. 

  4084. 			f_lastwasblank = 1
    4085. 

  4085. 			continue
    4086. 

  4086. 		
    4087. 

  4087. 		#---------------------[ %%toc ]-----------------------
    4088. 

  4088. 		
    4089. 

  4089. 		# %%toc line closes paragraph
    4090. 

  4090. 		if BLOCK.block() == 'para' and regex['toc'].search(line):
    4091. 

  4091. 			ret.extend(BLOCK.blockout())
    4092. 

  4092. 		
    4093. 

  4093. 		#---------------------[ apply masks ]-----------------------
    4094. 

  4094. 		
    4095. 

  4095. 		line = MASK.mask(line)
    4096. 

  4096. 		
    4097. 

  4097. 		#XXX from here, only block-inside lines will pass
    4098. 

  4098. 		
    4099. 

  4099. 		#---------------------[ Quote ]-----------------------------
    4100. 

  4100. 		
    4101. 

  4101. 		if regex['quote'].search(line):
    4102. 

  4102. 			
    4103. 

  4103. 			# Store number of leading TABS
    4104. 

  4104. 			quotedepth = len(regex['quote'].search(line).group(0))
    4105. 

  4105. 			
    4106. 

  4106. 			# SGML doesn't support nested quotes
    4107. 

  4107. 			if rules['quotenotnested']: quotedepth = 1
    4108. 

  4108. 			
    4109. 

  4109. 			# Don't cross depth limit
    4110. 

  4110. 			maxdepth = rules['quotemaxdepth']
    4111. 

  4111. 			if maxdepth and quotedepth > maxdepth:
    4112. 

  4112. 				quotedepth = maxdepth
    4113. 

  4113. 			
    4114. 

  4114. 			# New quote
    4115. 

  4115. 			if not BLOCK.isblock('quote'):
    4116. 

  4116. 				ret.extend(BLOCK.blockin('quote'))
    4117. 

  4117. 			
    4118. 

  4118. 			# New subquotes
    4119. 

  4119. 			while BLOCK.depth < quotedepth:
    4120. 

  4120. 				BLOCK.blockin('quote')
    4121. 

  4121. 			
    4122. 

  4122. 			# Closing quotes
    4123. 

  4123. 			while quotedepth < BLOCK.depth:
    4124. 

  4124. 				ret.extend(BLOCK.blockout())
    4125. 

  4125. 		
    4126. 

  4126. 		#---------------------[ Lists ]-----------------------------
    4127. 

  4127. 		
    4128. 

  4128. 		# An empty item also closes the current list
    4129. 

  4129. 		if BLOCK.block()[-4:] == 'list':
    4130. 

  4130. 			m = regex['listclose'].match(line)
    4131. 

  4131. 			if m:
    4132. 

  4132. 				listindent = m.group(1)
    4133. 

  4133. 				listtype = m.group(2)
    4134. 

  4134. 				currlisttype = BLOCK.prop('type')
    4135. 

  4135. 				currlistindent = BLOCK.prop('indent')
    4136. 

  4136. 				if listindent == currlistindent and \
    4137. 

  4137. 				   listtype == currlisttype:
    4138. 

  4138. 					ret.extend(BLOCK.blockout())
    4139. 

  4139. 					continue
    4140. 

  4140. 		
    4141. 

  4141. 		if   regex['list'].search(line) or \
    4142. 

  4142. 		  regex['numlist'].search(line) or \
    4143. 

  4143. 		  regex['deflist'].search(line):
    4144. 

  4144. 			
    4145. 

  4145. 			listindent = BLOCK.prop('indent')
    4146. 

  4146. 			listids = string.join(LISTNAMES.keys(), '')
    4147. 

  4147. 			m = re.match('^( *)([%s]) '%listids, line)
    4148. 

  4148. 			listitemindent = m.group(1)
    4149. 

  4149. 			listtype = m.group(2)
    4150. 

  4150. 			listname = LISTNAMES[listtype]
    4151. 

  4151. 			results_box = BLOCK.holdadd
    4152. 

  4152. 			
    4153. 

  4153. 			# Del list ID (and separate term from definition)
    4154. 

  4154. 			if listname == 'deflist':
    4155. 

  4155. 				term = parse_deflist_term(line)
    4156. 

  4156. 				line = regex['deflist'].sub(
    4157. 

  4157. 					SEPARATOR+term+SEPARATOR,line)
    4158. 

  4158. 			else:
    4159. 

  4159. 				line = regex[listname].sub(SEPARATOR,line)
    4160. 

  4160. 			
    4161. 

  4161. 			# Don't cross depth limit
    4162. 

  4162. 			maxdepth = rules['listmaxdepth']
    4163. 

  4163. 			if maxdepth and BLOCK.depth == maxdepth:
    4164. 

  4164. 				if len(listitemindent) > len(listindent):
    4165. 

  4165. 					listitemindent = listindent
    4166. 

  4166. 			
    4167. 

  4167. 			# List bumping (same indent, diff mark)
    4168. 

  4168. 			# Close the currently open list to clear the mess
    4169. 

  4169. 			if BLOCK.block()[-4:] == 'list' \
    4170. 

  4170. 			   and listname != BLOCK.block() \
    4171. 

  4171. 			   and len(listitemindent) == len(listindent):
    4172. 

  4172. 				ret.extend(BLOCK.blockout())
    4173. 

  4173. 				listindent = BLOCK.prop('indent')
    4174. 

  4174. 			
    4175. 

  4175. 			# Open mother list or sublist
    4176. 

  4176. 			if BLOCK.block()[-4:] != 'list' or \
    4177. 

  4177. 			   len(listitemindent) > len(listindent):
    4178. 

  4178. 				ret.extend(BLOCK.blockin(listname))
    4179. 

  4179. 				BLOCK.propset('indent',listitemindent)
    4180. 

  4180. 				BLOCK.propset('type',listtype)
    4181. 

  4181. 			
    4182. 

  4182. 			# Closing sublists
    4183. 

  4183. 			while len(listitemindent) < len(BLOCK.prop('indent')):
    4184. 

  4184. 				ret.extend(BLOCK.blockout())
    4185. 

  4185. 			
    4186. 

  4186. 			# O-oh, sublist before list ("\n\n  - foo\n- foo")
    4187. 

  4187. 			# Fix: close sublist (as mother), open another list
    4188. 

  4188. 			if BLOCK.block()[-4:] != 'list':
    4189. 

  4189. 				ret.extend(BLOCK.blockin(listname))
    4190. 

  4190. 				BLOCK.propset('indent',listitemindent)
    4191. 

  4191. 				BLOCK.propset('type',listtype)
    4192. 

  4192. 		
    4193. 

  4193. 		#---------------------[ Table ]-----------------------------
    4194. 

  4194. 		
    4195. 

  4195. 		#TODO escape undesired format inside table
    4196. 

  4196. 		#TODO add pm6 target
    4197. 

  4197. 		if regex['table'].search(line):
    4198. 

  4198. 			
    4199. 

  4199. 			if not BLOCK.isblock('table'):   # first table line!
    4200. 

  4200. 				ret.extend(BLOCK.blockin('table'))
    4201. 

  4201. 				BLOCK.tableparser.__init__(line)
    4202. 

  4202. 			
    4203. 

  4203. 			tablerow = TableMaster().parse_row(line)
    4204. 

  4204. 			BLOCK.tableparser.add_row(tablerow)     # save config
    4205. 

  4205. 			
    4206. 

  4206. 			# Maintain line to unmask and inlines
    4207. 

  4207. 			line = string.join(tablerow['cells'], SEPARATOR)
    4208. 

  4208. 		
    4209. 

  4209. 		#---------------------[ Paragraph ]-------------------------
    4210. 

  4210. 		
    4211. 

  4211. 		if not BLOCK.block() and \
    4212. 

  4212. 		   not string.count(line, MASK.tocmask): # new para!
    4213. 

  4213. 			ret.extend(BLOCK.blockin('para'))
    4214. 

  4214. 		
    4215. 

  4215. 		
    4216. 

  4216. 		############################################################
    4217. 

  4217. 		############################################################
    4218. 

  4218. 		############################################################
    4219. 

  4219. 		
    4220. 

  4220. 		
    4221. 

  4221. 		#---------------------[ Final Parses ]----------------------
    4222. 

  4222. 		
    4223. 

  4223. 		# The target-specific special char escapes for body lines
    4224. 

  4224. 		line = doEscape(target,line)
    4225. 

  4225. 		
    4226. 

  4226. 		line = add_inline_tags(line)
    4227. 

  4227. 		line = MASK.undo(line)
    4228. 

  4228. 		
    4229. 

  4229. 		
    4230. 

  4230. 		#---------------------[ Hold or Return? ]-------------------
    4231. 

  4231. 		
    4232. 

  4232. 		### Now we must choose where to put the parsed line
    4233. 

  4233. 		#
    4234. 

  4234. 		if not results_box:
    4235. 

  4235. 			# List item extra lines
    4236. 

  4236. 			if BLOCK.block()[-4:] == 'list':
    4237. 

  4237. 				results_box = BLOCK.holdaddsub
    4238. 

  4238. 			# Other blocks
    4239. 

  4239. 			elif BLOCK.block():
    4240. 

  4240. 				results_box = BLOCK.holdadd
    4241. 

  4241. 			# No blocks
    4242. 

  4242. 			else:
    4243. 

  4243. 				line = doFinalEscape(target, line)
    4244. 

  4244. 				results_box = ret.append
    4245. 

  4245. 		
    4246. 

  4246. 		results_box(line)
    4247. 

  4247. 	
    4248. 

  4248. 	# EOF: close any open para/verb/lists/table/quotes
    4249. 

  4249. 	Debug('EOF',7)
    4250. 

  4250. 	while BLOCK.block():
    4251. 

  4251. 		ret.extend(BLOCK.blockout())
    4252. 

  4252. 	
    4253. 

  4253. 	# Maybe close some opened title area?
    4254. 

  4254. 	if rules['titleblocks']:
    4255. 

  4255. 		ret.extend(TITLE.close_all())
    4256. 

  4256. 	
    4257. 

  4257. 	# Maybe a major tag to enclose body? (like DIV for CSS)
    4258. 

  4258. 	if TAGS['bodyOpen' ]: ret.insert(0, TAGS['bodyOpen'])
    4259. 

  4259. 	if TAGS['bodyClose']: ret.append(TAGS['bodyClose'])
    4260. 

  4260. 	
    4261. 

  4261. 	if CONF['toc-only']: ret = []
    4262. 

  4262. 	marked_toc = TITLE.dump_marked_toc(CONF['toc-level'])
    4263. 

  4263. 	
    4264. 

  4264. 	# If dump-source, all parsing is ignored
    4265. 

  4265. 	if CONF['dump-source']: ret = dump_source[:]
    4266. 

  4266. 	
    4267. 

  4267. 	return ret, marked_toc
    4268. 

  4268. 

  4269. 

  4270. 

  4271. ##############################################################################
    4272. 

  4272. ################################### GUI ######################################
    4273. 

  4273. ##############################################################################
    4274. 

  4274. #
    4275. 

  4275. # Tk help: http://python.org/topics/tkinter/
    4276. 

  4276. #    Tuto: http://ibiblio.org/obp/py4fun/gui/tkPhone.html
    4277. 

  4277. #          /usr/lib/python*/lib-tk/Tkinter.py
    4278. 

  4278. #
    4279. 

  4279. # grid table : row=0, column=0, columnspan=2, rowspan=2
    4280. 

  4280. # grid align : sticky='n,s,e,w' (North, South, East, West)
    4281. 

  4281. # pack place : side='top,bottom,right,left'
    4282. 

  4282. # pack fill  : fill='x,y,both,none', expand=1
    4283. 

  4283. # pack align : anchor='n,s,e,w' (North, South, East, West)
    4284. 

  4284. # padding    : padx=10, pady=10, ipadx=10, ipady=10 (internal)
    4285. 

  4285. # checkbox   : offvalue is return if the _user_ deselected the box
    4286. 

  4286. # label align: justify=left,right,center
    4287. 

  4287. 

  4288. def load_GUI_resources():
    4289. 

  4289. 	"Load all extra modules and methods used by GUI"
    4290. 

  4290. 	global askopenfilename, showinfo, showwarning, showerror, Tkinter
    4291. 

  4291. 	from tkFileDialog import askopenfilename
    4292. 

  4292. 	from tkMessageBox import showinfo,showwarning,showerror
    4293. 

  4293. 	import Tkinter
    4294. 

  4294. 

  4295. class Gui:
    4296. 

  4296. 	"Graphical Tk Interface"
    4297. 

  4297. 	def __init__(self, conf={}):
    4298. 

  4298. 		self.root = Tkinter.Tk()    # mother window, come to butthead
    4299. 

  4299. 		self.root.title(my_name)    # window title bar text
    4300. 

  4300. 		self.window = self.root     # variable "focus" for inclusion
    4301. 

  4301. 		self.row = 0                # row count for grid()
    4302. 

  4302. 		
    4303. 

  4303. 		self.action_length = 150    # left column length (pixel)
    4304. 

  4304. 		self.frame_margin  = 10     # frame margin size  (pixel)
    4305. 

  4305. 		self.frame_border  = 6      # frame border size  (pixel)
    4306. 

  4306. 		
    4307. 

  4307. 		# The default Gui colors, can be changed by %!guicolors
    4308. 

  4308. 		self.dft_gui_colors = ['#6c6','white','#cf9','#030']
    4309. 

  4309. 		self.gui_colors = []
    4310. 

  4310. 		self.bg1 = self.fg1 = self.bg2 = self.fg2 = ''
    4311. 

  4311. 		
    4312. 

  4312. 		# On Tk, vars need to be set/get using setvar()/get()
    4313. 

  4313. 		self.infile  = self.setvar('')
    4314. 

  4314. 		self.target  = self.setvar('')
    4315. 

  4315. 		self.target_name = self.setvar('')
    4316. 

  4316. 		
    4317. 

  4317. 		# The checks appearance order
    4318. 

  4318. 		self.checks  = [
    4319. 

  4319. 		  'headers','enum-title','toc','mask-email',
    4320. 

  4320. 		  'toc-only','stdout']
    4321. 

  4321. 		
    4322. 

  4322. 		# Creating variables for all checks
    4323. 

  4323. 		for check in self.checks:
    4324. 

  4324. 			setattr(self, 'f_'+check, self.setvar(''))
    4325. 

  4325. 		
    4326. 

  4326. 		# Load RC config
    4327. 

  4327. 		self.conf = {}
    4328. 

  4328. 		if conf: self.load_config(conf)
    4329. 

  4329. 	
    4330. 

  4330. 	def load_config(self, conf):
    4331. 

  4331. 		self.conf = conf
    4332. 

  4332. 		self.gui_colors = conf.get('guicolors') or self.dft_gui_colors
    4333. 

  4333. 		self.bg1, self.fg1, self.bg2, self.fg2 = self.gui_colors
    4334. 

  4334. 		self.root.config(bd=15,bg=self.bg1)
    4335. 

  4335. 	
    4336. 

  4336. 	### Config as dic for python 1.5 compat (**opts don't work :( )
    4337. 

  4337. 	def entry(self, **opts): return Tkinter.Entry(self.window, opts)
    4338. 

  4338. 	def label(self, txt='', bg=None, **opts):
    4339. 

  4339. 		opts.update({'text':txt,'bg':bg or self.bg1})
    4340. 

  4340. 		return Tkinter.Label(self.window, opts)
    4341. 

  4341. 	def button(self,name,cmd,**opts):
    4342. 

  4342. 		opts.update({'text':name,'command':cmd})
    4343. 

  4343. 		return Tkinter.Button(self.window, opts)
    4344. 

  4344. 	def check(self,name,checked=0,**opts):
    4345. 

  4345. 		bg, fg = self.bg2, self.fg2
    4346. 

  4346. 		opts.update({
    4347. 

  4347. 		  'text':name, 'onvalue':1, 'offvalue':0,
    4348. 

  4348. 		  'activeforeground':fg, 'fg':fg,
    4349. 

  4349. 		  'activebackground':bg, 'bg':bg,
    4350. 

  4350. 		  'highlightbackground':bg, 'anchor':'w'
    4351. 

  4351. 		})
    4352. 

  4352. 		chk = Tkinter.Checkbutton(self.window, opts)
    4353. 

  4353. 		if checked: chk.select()
    4354. 

  4354. 		chk.grid(columnspan=2, sticky='w', padx=0)
    4355. 

  4355. 	def menu(self,sel,items):
    4356. 

  4356. 		return apply(Tkinter.OptionMenu,(self.window,sel)+tuple(items))
    4357. 

  4357. 	
    4358. 

  4358. 	# Handy auxiliary functions
    4359. 

  4359. 	def action(self, txt):
    4360. 

  4360. 		self.label(txt, fg=self.fg1, bg=self.bg1,
    4361. 

  4361. 		     wraplength=self.action_length).grid(column=0,row=self.row)
    4362. 

  4362. 	def frame_open(self):
    4363. 

  4363. 		self.window = Tkinter.Frame(self.root,bg=self.bg2,
    4364. 

  4364. 		     borderwidth=self.frame_border)
    4365. 

  4365. 	def frame_close(self):
    4366. 

  4366. 		self.window.grid(column=1, row=self.row, sticky='w',
    4367. 

  4367. 		     padx=self.frame_margin)
    4368. 

  4368. 		self.window = self.root
    4369. 

  4369. 		self.label('').grid()
    4370. 

  4370. 		self.row = self.row + 2   # update row count
    4371. 

  4371. 	def target_name2key(self):
    4372. 

  4372. 		name = self.target_name.get()
    4373. 

  4373. 		target = filter(lambda x: TARGET_NAMES[x] == name, TARGETS)
    4374. 

  4374. 		try   : key = target[0]
    4375. 

  4375. 		except: key = ''
    4376. 

  4376. 		self.target = self.setvar(key)
    4377. 

  4377. 	def target_key2name(self):
    4378. 

  4378. 		key = self.target.get()
    4379. 

  4379. 		name = TARGET_NAMES.get(key) or key
    4380. 

  4380. 		self.target_name = self.setvar(name)
    4381. 

  4381. 	
    4382. 

  4382. 	def exit(self): self.root.destroy()
    4383. 

  4383. 	def setvar(self, val): z = Tkinter.StringVar() ; z.set(val) ; return z
    4384. 

  4384. 	
    4385. 

  4385. 	def askfile(self):
    4386. 

  4386. 		ftypes= [(_('txt2tags files'),('*.t2t','*.txt')),
    4387. 

  4387. 		         (_('All files'),'*')]
    4388. 

  4388. 		newfile = askopenfilename(filetypes=ftypes)
    4389. 

  4389. 		if newfile:
    4390. 

  4390. 			self.infile.set(newfile)
    4391. 

  4391. 			newconf = process_source_file(newfile)[0]
    4392. 

  4392. 			newconf = ConfigMaster().sanity(newconf, gui=1)
    4393. 

  4393. 			# Restate all checkboxes after file selection
    4394. 

  4394. 			#TODO how to make a refresh without killing it?
    4395. 

  4395. 			self.root.destroy()
    4396. 

  4396. 			self.__init__(newconf)
    4397. 

  4397. 			self.mainwindow()
    4398. 

  4398. 	
    4399. 

  4399. 	def scrollwindow(self, txt='no text!', title=''):
    4400. 

  4400. 		# Create components
    4401. 

  4401. 		win    = Tkinter.Toplevel() ; win.title(title)
    4402. 

  4402. 		frame  = Tkinter.Frame(win)
    4403. 

  4403. 		scroll = Tkinter.Scrollbar(frame)
    4404. 

  4404. 		text   = Tkinter.Text(frame,yscrollcommand=scroll.set)
    4405. 

  4405. 		button = Tkinter.Button(win)
    4406. 

  4406. 		# Config
    4407. 

  4407. 		text.insert(Tkinter.END, string.join(txt,'\n'))
    4408. 

  4408. 		scroll.config(command=text.yview)
    4409. 

  4409. 		button.config(text=_('Close'), command=win.destroy)
    4410. 

  4410. 		button.focus_set()
    4411. 

  4411. 		# Packing
    4412. 

  4412. 		text.pack(side='left', fill='both', expand=1)
    4413. 

  4413. 		scroll.pack(side='right', fill='y')
    4414. 

  4414. 		frame.pack(fill='both', expand=1)
    4415. 

  4415. 		button.pack(ipadx=30)
    4416. 

  4416. 	
    4417. 

  4417. 	def runprogram(self):
    4418. 

  4418. 		global CMDLINE_RAW
    4419. 

  4419. 		# Prepare
    4420. 

  4420. 		self.target_name2key()
    4421. 

  4421. 		infile, target = self.infile.get(), self.target.get()
    4422. 

  4422. 		# Sanity
    4423. 

  4423. 		if not target:
    4424. 

  4424. 			showwarning(my_name,_("You must select a target type!"))
    4425. 

  4425. 			return
    4426. 

  4426. 		if not infile:
    4427. 

  4427. 			showwarning(my_name,
    4428. 

  4428. 			   _("You must provide the source file location!"))
    4429. 

  4429. 			return
    4430. 

  4430. 		# Compose cmdline
    4431. 

  4431. 		guiflags = []
    4432. 

  4432. 		real_cmdline_conf = ConfigMaster(CMDLINE_RAW).parse()
    4433. 

  4433. 		if real_cmdline_conf.has_key('infile'):
    4434. 

  4434. 			del real_cmdline_conf['infile']
    4435. 

  4435. 		if real_cmdline_conf.has_key('target'):
    4436. 

  4436. 			del real_cmdline_conf['target']
    4437. 

  4437. 		real_cmdline = CommandLine().compose_cmdline(real_cmdline_conf)
    4438. 

  4438. 		default_outfile = ConfigMaster().get_outfile_name(
    4439. 

  4439. 		     {'sourcefile':infile, 'outfile':'', 'target':target})
    4440. 

  4440. 		for opt in self.checks:
    4441. 

  4441. 			val = int(getattr(self, 'f_%s'%opt).get() or "0")
    4442. 

  4442. 			if opt == 'stdout': opt = 'outfile'
    4443. 

  4443. 			on_config  = self.conf.get(opt) or 0
    4444. 

  4444. 			on_cmdline = real_cmdline_conf.get(opt) or 0
    4445. 

  4445. 			if opt == 'outfile':
    4446. 

  4446. 				if on_config  == STDOUT: on_config = 1
    4447. 

  4447. 				else: on_config = 0
    4448. 

  4448. 				if on_cmdline == STDOUT: on_cmdline = 1
    4449. 

  4449. 				else: on_cmdline = 0
    4450. 

  4450. 			if val != on_config or (
    4451. 

  4451. 			  val == on_config == on_cmdline and
    4452. 

  4452. 			  real_cmdline_conf.has_key(opt)):
    4453. 

  4453. 				if val:
    4454. 

  4454. 					# Was not set, but user selected on GUI
    4455. 

  4455. 					Debug("user turned  ON: %s"%opt)
    4456. 

  4456. 					if opt == 'outfile': opt = '-o-'
    4457. 

  4457. 					else: opt = '--%s'%opt
    4458. 

  4458. 				else:
    4459. 

  4459. 					# Was set, but user deselected on GUI
    4460. 

  4460. 					Debug("user turned OFF: %s"%opt)
    4461. 

  4461. 					if opt == 'outfile':
    4462. 

  4462. 						opt = "-o%s"%default_outfile
    4463. 

  4463. 					else: opt = '--no-%s'%opt
    4464. 

  4464. 				guiflags.append(opt)
    4465. 

  4465. 		cmdline = [my_name, '-t', target] +real_cmdline \
    4466. 

  4466. 		          +guiflags +[infile]
    4467. 

  4467. 		Debug('Gui/Tk cmdline: %s'%cmdline,5)
    4468. 

  4468. 		# Run!
    4469. 

  4469. 		cmdline_raw_orig = CMDLINE_RAW
    4470. 

  4470. 		try:
    4471. 

  4471. 			# Fake the GUI cmdline as the real one, and parse file
    4472. 

  4472. 			CMDLINE_RAW = CommandLine().get_raw_config(cmdline[1:])
    4473. 

  4473. 			data = process_source_file(infile)
    4474. 

  4474. 			# On GUI, convert_* returns the data, not finish_him()
    4475. 

  4475. 			outlist, config = convert_this_files([data])
    4476. 

  4476. 			# On GUI and STDOUT, finish_him() returns the data
    4477. 

  4477. 			result = finish_him(outlist, config)
    4478. 

  4478. 			# Show outlist in s a nice new window
    4479. 

  4479. 			if result:
    4480. 

  4480. 				outlist, config = result
    4481. 

  4481. 				title = _('%s: %s converted to %s')%(
    4482. 

  4482. 				  my_name, os.path.basename(infile),
    4483. 

  4483. 				  string.upper(config['target']))
    4484. 

  4484. 				self.scrollwindow(outlist, title)
    4485. 

  4485. 			# Show the "file saved" message
    4486. 

  4486. 			else:
    4487. 

  4487. 				msg = "%s\n\n  %s\n%s\n\n  %s\n%s"%(
    4488. 

  4488. 				      _('Conversion done!'),
    4489. 

  4489. 				      _('FROM:'), infile,
    4490. 

  4490. 				      _('TO:'), config['outfile'])
    4491. 

  4491. 				showinfo(my_name, msg)
    4492. 

  4492. 		except error:         # common error (windowed), not quit
    4493. 

  4493. 			pass
    4494. 

  4494. 		except:               # fatal error (windowed and printed)
    4495. 

  4495. 			errormsg = getUnknownErrorMessage()
    4496. 

  4496. 			print errormsg
    4497. 

  4497. 			showerror(_('%s FATAL ERROR!')%my_name,errormsg)
    4498. 

  4498. 			self.exit()
    4499. 

  4499. 		CMDLINE_RAW = cmdline_raw_orig
    4500. 

  4500. 	
    4501. 

  4501. 	def mainwindow(self):
    4502. 

  4502. 		self.infile.set(self.conf.get('sourcefile') or '')
    4503. 

  4503. 		self.target.set(self.conf.get('target') or \
    4504. 

  4504. 		              _('-- select one --'))
    4505. 

  4505. 		outfile = self.conf.get('outfile')
    4506. 

  4506. 		if outfile == STDOUT:                  # map -o-
    4507. 

  4507. 			self.conf['stdout'] = 1
    4508. 

  4508. 		if self.conf.get('headers') == None:
    4509. 

  4509. 			self.conf['headers'] = 1       # map default
    4510. 

  4510. 		
    4511. 

  4511. 		action1 = _("Enter the source file location:")
    4512. 

  4512. 		action2 = _("Choose the target document type:")
    4513. 

  4513. 		action3 = _("Some options you may check:")
    4514. 

  4514. 		action4 = _("Some extra options:")
    4515. 

  4515. 		checks_txt = {
    4516. 

  4516. 		  'headers'   : _("Include headers on output"),
    4517. 

  4517. 		  'enum-title': _("Number titles (1, 1.1, 1.1.1, etc)"),
    4518. 

  4518. 		  'toc'       : _("Do TOC also (Table of Contents)"),
    4519. 

  4519. 		  'mask-email': _("Hide e-mails from SPAM robots"),
    4520. 

  4520. 		
    4521. 

  4521. 		  'toc-only'  : _("Just do TOC, nothing more"),
    4522. 

  4522. 		  'stdout'    : _("Dump to screen (Don't save target file)")
    4523. 

  4523. 		}
    4524. 

  4524. 		targets_menu = map(lambda x: TARGET_NAMES[x], TARGETS)
    4525. 

  4525. 		
    4526. 

  4526. 		# Header
    4527. 

  4527. 		self.label("%s %s"%(string.upper(my_name), my_version),
    4528. 

  4528. 		     bg=self.bg2, fg=self.fg2).grid(columnspan=2, ipadx=10)
    4529. 

  4529. 		self.label(_("ONE source, MULTI targets")+'\n%s\n'%my_url,
    4530. 

  4530. 		     bg=self.bg1, fg=self.fg1).grid(columnspan=2)
    4531. 

  4531. 		self.row = 2
    4532. 

  4532. 		# Choose input file
    4533. 

  4533. 		self.action(action1) ; self.frame_open()
    4534. 

  4534. 		e_infile = self.entry(textvariable=self.infile,width=25)
    4535. 

  4535. 		e_infile.grid(row=self.row, column=0, sticky='e')
    4536. 

  4536. 		if not self.infile.get(): e_infile.focus_set()
    4537. 

  4537. 		self.button(_("Browse"), self.askfile).grid(
    4538. 

  4538. 		    row=self.row, column=1, sticky='w', padx=10)
    4539. 

  4539. 		# Show outfile name, style and encoding (if any)
    4540. 

  4540. 		txt = ''
    4541. 

  4541. 		if outfile:
    4542. 

  4542. 			txt = outfile
    4543. 

  4543. 			if outfile == STDOUT: txt = _('<screen>')
    4544. 

  4544. 			l_output = self.label(_('Output: ')+txt,
    4545. 

  4545. 			                fg=self.fg2,bg=self.bg2)
    4546. 

  4546. 			l_output.grid(columnspan=2, sticky='w')
    4547. 

  4547. 		for setting in ['style','encoding']:
    4548. 

  4548. 			if self.conf.get(setting):
    4549. 

  4549. 				name = string.capitalize(setting)
    4550. 

  4550. 				val  = self.conf[setting]
    4551. 

  4551. 				self.label('%s: %s'%(name, val),
    4552. 

  4552. 				     fg=self.fg2, bg=self.bg2).grid(
    4553. 

  4553. 				     columnspan=2, sticky='w')
    4554. 

  4554. 		# Choose target
    4555. 

  4555. 		self.frame_close() ; self.action(action2)
    4556. 

  4556. 		self.frame_open()
    4557. 

  4557. 		self.target_key2name()
    4558. 

  4558. 		self.menu(self.target_name, targets_menu).grid(
    4559. 

  4559. 		     columnspan=2, sticky='w')
    4560. 

  4560. 		# Options checkboxes label
    4561. 

  4561. 		self.frame_close() ; self.action(action3)
    4562. 

  4562. 		self.frame_open()
    4563. 

  4563. 		# Compose options check boxes, example:
    4564. 

  4564. 		# self.check(checks_txt['toc'],1,variable=self.f_toc)
    4565. 

  4565. 		for check in self.checks:
    4566. 

  4566. 			# Extra options label
    4567. 

  4567. 			if check == 'toc-only':
    4568. 

  4568. 				self.frame_close() ; self.action(action4)
    4569. 

  4569. 				self.frame_open()
    4570. 

  4570. 			txt = checks_txt[check]
    4571. 

  4571. 			var = getattr(self, 'f_'+check)
    4572. 

  4572. 			checked = self.conf.get(check)
    4573. 

  4573. 			self.check(txt,checked,variable=var)
    4574. 

  4574. 		self.frame_close()
    4575. 

  4575. 		# Spacer and buttons
    4576. 

  4576. 		self.label('').grid() ; self.row = self.row + 1
    4577. 

  4577. 		b_quit = self.button(_("Quit"), self.exit)
    4578. 

  4578. 		b_quit.grid(row=self.row, column=0, sticky='w', padx=30)
    4579. 

  4579. 		b_conv = self.button(_("Convert!"), self.runprogram)
    4580. 

  4580. 		b_conv.grid(row=self.row, column=1, sticky='e', padx=30)
    4581. 

  4581. 		if self.target.get() and self.infile.get():
    4582. 

  4582. 			b_conv.focus_set()
    4583. 

  4583. 		
    4584. 

  4584. 		# As documentation told me
    4585. 

  4585. 		if sys.platform[:3] == 'win':
    4586. 

  4586. 			self.root.iconify()
    4587. 

  4587. 			self.root.update()
    4588. 

  4588. 			self.root.deiconify()
    4589. 

  4589. 		
    4590. 

  4590. 		self.root.mainloop()
    4591. 

  4591. 

  4592. 

  4593. ##############################################################################
    4594. 

  4594. ##############################################################################
    4595. 

  4595. 

  4596. def exec_command_line(user_cmdline=[]):
    4597. 

  4597. 	global CMDLINE_RAW, RC_RAW, DEBUG, VERBOSE, QUIET, GUI, Error
    4598. 

  4598. 	
    4599. 

  4599. 	# Extract command line data
    4600. 

  4600. 	cmdline_data = user_cmdline or sys.argv[1:]
    4601. 

  4601. 	CMDLINE_RAW = CommandLine().get_raw_config(cmdline_data, relative=1)
    4602. 

  4602. 	cmdline_parsed = ConfigMaster(CMDLINE_RAW).parse()
    4603. 

  4603. 	DEBUG   = cmdline_parsed.get('debug'  ) or 0
    4604. 

  4604. 	VERBOSE = cmdline_parsed.get('verbose') or 0
    4605. 

  4605. 	QUIET   = cmdline_parsed.get('quiet'  ) or 0
    4606. 

  4606. 	GUI     = cmdline_parsed.get('gui'    ) or 0
    4607. 

  4607. 	infiles = cmdline_parsed.get('infile' ) or []
    4608. 

  4608. 	
    4609. 

  4609. 	Message(_("Txt2tags %s processing begins")%my_version,1)
    4610. 

  4610. 	
    4611. 

  4611. 	# The easy ones
    4612. 

  4612. 	if cmdline_parsed.get('help'   ): Quit(USAGE)
    4613. 

  4613. 	if cmdline_parsed.get('version'): Quit(VERSIONSTR)
    4614. 

  4614. 	
    4615. 

  4615. 	# Multifile haters
    4616. 

  4616. 	if len(infiles) > 1:
    4617. 

  4617. 		errmsg=_("Option --%s can't be used with multiple input files")
    4618. 

  4618. 		for option in NO_MULTI_INPUT:
    4619. 

  4619. 			if cmdline_parsed.get(option):
    4620. 

  4620. 				Error(errmsg%option)
    4621. 

  4621. 	
    4622. 

  4622. 	Debug("system platform: %s"%sys.platform)
    4623. 

  4623. 	Debug("python version: %s"%(string.split(sys.version,'(')[0]))
    4624. 

  4624. 	Debug("line break char: %s"%repr(LB))
    4625. 

  4625. 	Debug("command line: %s"%sys.argv)
    4626. 

  4626. 	Debug("command line raw config: %s"%CMDLINE_RAW,1)
    4627. 

  4627. 	
    4628. 

  4628. 	# Extract RC file config
    4629. 

  4629. 	if cmdline_parsed.get('rc') == 0:
    4630. 

  4630. 		Message(_("Ignoring user configuration file"),1)
    4631. 

  4631. 	else:
    4632. 

  4632. 		rc_file = get_rc_path()
    4633. 

  4633. 		if os.path.isfile(rc_file):
    4634. 

  4634. 			Message(_("Loading user configuration file"),1)
    4635. 

  4635. 			RC_RAW = ConfigLines(file=rc_file).get_raw_config()
    4636. 

  4636. 		
    4637. 

  4637. 		Debug("rc file: %s"%rc_file)
    4638. 

  4638. 		Debug("rc file raw config: %s"%RC_RAW,1)
    4639. 

  4639. 	
    4640. 

  4640. 	# Get all infiles config (if any)
    4641. 

  4641. 	infiles_config = get_infiles_config(infiles)
    4642. 

  4642. 	
    4643. 

  4643. 	# Is GUI available?
    4644. 

  4644. 	# Try to load and start GUI interface for --gui
    4645. 

  4645. 	# If program was called with no arguments, try GUI also
    4646. 

  4646. 	if GUI or not infiles:
    4647. 

  4647. 		try:
    4648. 

  4648. 			load_GUI_resources()
    4649. 

  4649. 			Debug("GUI resources OK (Tk module is installed)")
    4650. 

  4650. 			winbox = Gui()
    4651. 

  4651. 			Debug("GUI display OK")
    4652. 

  4652. 			GUI = 1
    4653. 

  4653. 		except:
    4654. 

  4654. 			Debug("GUI Error: no Tk module or no DISPLAY")
    4655. 

  4655. 			GUI = 0
    4656. 

  4656. 	
    4657. 

  4657. 	# User forced --gui, but it's not available
    4658. 

  4658. 	if cmdline_parsed.get('gui') and not GUI:
    4659. 

  4659. 		print getTraceback(); print
    4660. 

  4660. 		Error("Sorry, I can't run my Graphical Interface - GUI\n"
    4661. 

  4661. 		      "- Check if Python Tcl/Tk module is installed (Tkinter)\n"
    4662. 

  4662. 		      "- Make sure you are in a graphical environment (like X)")
    4663. 

  4663. 	
    4664. 

  4664. 	# Okay, we will use GUI
    4665. 

  4665. 	if GUI:
    4666. 

  4666. 		Message(_("We are on GUI interface"),1)
    4667. 

  4667. 		
    4668. 

  4668. 		# Redefine Error function to raise exception instead sys.exit()
    4669. 

  4669. 		def Error(msg):
    4670. 

  4670. 			showerror(_('txt2tags ERROR!'), msg)
    4671. 

  4671. 			raise error
    4672. 

  4672. 		
    4673. 

  4673. 		# If no input file, get RC+cmdline config, else full config
    4674. 

  4674. 		if not infiles:
    4675. 

  4675. 			gui_conf = ConfigMaster(RC_RAW+CMDLINE_RAW).parse()
    4676. 

  4676. 		else:
    4677. 

  4677. 			try   : gui_conf = infiles_config[0][0]
    4678. 

  4678. 			except: gui_conf = {}
    4679. 

  4679. 		
    4680. 

  4680. 		# Sanity is needed to set outfile and other things
    4681. 

  4681. 		gui_conf = ConfigMaster().sanity(gui_conf, gui=1)
    4682. 

  4682. 		Debug("GUI config: %s"%gui_conf,5)
    4683. 

  4683. 		
    4684. 

  4684. 		# Insert config and populate the nice window!
    4685. 

  4685. 		winbox.load_config(gui_conf)
    4686. 

  4686. 		winbox.mainwindow()
    4687. 

  4687. 	
    4688. 

  4688. 	# Console mode rocks forever!
    4689. 

  4689. 	else:
    4690. 

  4690. 		Message(_("We are on Command Line interface"),1)
    4691. 

  4691. 		
    4692. 

  4692. 		# Called with no arguments, show error
    4693. 

  4693. 		if not infiles: Error(_('Missing input file (try --help)'))
    4694. 

  4694. 		
    4695. 

  4695. 		convert_this_files(infiles_config)
    4696. 

  4696. 	
    4697. 

  4697. 	Message(_("Txt2tags finished sucessfuly"),1)
    4698. 

  4698. 

  4699. if __name__ == '__main__':
    4700. 

  4700. 	try:
    4701. 

  4701. 		exec_command_line()
    4702. 

  4702. 	except error, msg:
    4703. 

  4703. 		sys.stderr.write("%s\n"%msg)
    4704. 

  4704. 		sys.stderr.flush()
    4705. 

  4705. 		sys.exit(1)
    4706. 

  4706. 	except SystemExit:
    4707. 

  4707. 		pass
    4708. 

  4708. 	except:
    4709. 

  4709. 		sys.stderr.write(getUnknownErrorMessage())
    4710. 

  4710. 		sys.stderr.flush()
    4711. 

  4711. 		sys.exit(1)
    4712. 

  4712. 	Quit()
    4713. 

  4713. 

  4714. 

  4715. # vim: ts=8
    4716. 

  4716.