source/libs/zziplib/zziplib-0.13.62/docs/zzipdoc/htm2dbk.py

   1 #! /usr/bin/env python
   2
   3 """
   4 this file converts simple html text into a docbook xml variant.
   5 The mapping of markups and links is far from perfect. But all we
   6 want is the docbook-to-pdf converter and similar technology being
   7 present in the world of docbook-to-anything converters. """
   8
   9 from datetime import date
  10 import match
  11 import sys
  12
  13 m = match.Match
  14
  15 class htm2dbk_conversion_base:
  16     regexlist = [
  17         m()("</[hH]2>(.*)", "m") >> "</title>\n<subtitle>\\1</subtitle>",
  18         m()("<[hH]2>") >> "<sect1 id=\"--filename--\"><title>",
  19         m()("<[Pp]([> ])","m") >> "<para\\1",
  20         m()("</[Pp]>") >> "</para>",
  21         m()("<(pre|PRE)>") >> "<screen>",
  22         m()("</(pre|PRE)>") >> "</screen>",
  23         m()("<[hH]3>") >> "<sect2><title>",
  24         m()("</[hH]3>((?:.(?!<sect2>))*.?)", "s") >> "</title>\\1</sect2>",
  25         m()("<!doctype [^<>]*>","s") >> "",
  26         m()("<!DOCTYPE [^<>]*>","s") >> "",
  27         m()("(<\w+\b[^<>]*\swidth=)(\d+\%)","s") >> "\\1\"\\2\"",
  28         m()("(<\w+\b[^<>]*\s\w+=)(\d+)","s") >> "\\1\"\\2\"",
  29         m()("&&") >> "\&amp\;\&amp\;",
  30         m()("\$\<") >> "\$\&lt\;",
  31         m()("&(\w+[\),])") >> "\&amp\;\\1",
  32         m()("(</?)span(\s[^<>]*)?>","s") >> "\\1phrase\\2>",
  33         m()("(</?)small(\s[^<>]*)?>","s") >> "\\1note\\2>",
  34         m()("(</?)(b|em|i)>")>> "\\1emphasis>",
  35         m()("(</?)(li)>") >> "\\1listitem>",
  36         m()("(</?)(ul)>") >> "\\1itemizedlist>",
  37         m()("(</?)(ol)>") >> "\\1orderedlist>",
  38         m()("(</?)(dl)>") >> "\\1variablelist>",
  39         m()("<dt\b([^<>]*)>","s") >> "<varlistentry\\1><term>",
  40         m()("</dt\b([^<>]*)>","s") >> "</term>",
  41         m()("<dd\b([^<>]*)>","s") >> "<listitem\\1>",
  42         m()("</dd\b([^<>]*)>","s") >> "</listitem></varlistentry>",
  43         m()("<table\b([^<>]*)>","s")
  44         >> "<informaltable\\1><tgroup cols=\"2\"><tbody>",
  45         m()("</table\b([^<>]*)>","s") >> "</tbody></tgroup></informaltable>",
  46         m()("(</?)tr(\s[^<>]*)?>","s") >> "\\1row\\2>",
  47         m()("(</?)td(\s[^<>]*)?>","s") >> "\\1entry\\2>",
  48         m()("<informaltable\b[^<>]*>\s*<tgroup\b[^<>]*>\s*<tbody>"+
  49           "\s*<row\b[^<>]*>\s*<entry\b[^<>]*>\s*<informaltable\b","s")
  50         >> "<informaltable",
  51         m()("</informaltable>\s*</entry>\s*</row>"+
  52           "\s*</tbody>\s*</tgroup>\s*</informaltable>", "s")
  53         >> "</informaltable>",
  54         m()("(<informaltable[^<>]*\swidth=\"100\%\")","s") >> "\\1 pgwide=\"1\"",
  55         m()("(<tbody>\s*<row[^<>]*>\s*<entry[^<>]*\s)(width=\"50\%\")","s")
  56         >> "<colspec colwidth=\"1*\" /><colspec colwidth=\"1*\" />\n\\1\\2",
  57         m()("<nobr>([\'\`]*)<tt>") >> "<cmdsynopsis>\\1",
  58         m()("</tt>([\'\`]*)</nobr>") >> "\\1</cmdsynopsis>",
  59         m()("<nobr><(?:tt|code)>([\`\"\'])") >> "<cmdsynopsis>\\1",
  60         m()("<(?:tt|code)><nobr>([\`\"\'])") >> "<cmdsynopsis>\\1",
  61         m()("([\`\"\'])</(?:tt|code)></nobr>") >> "\\1</cmdsynopsis>",
  62         m()("([\`\"\'])</nobr></(?:tt|code)>") >> "\\1</cmdsynopsis>",
  63         m()("(</?)tt>") >> "\\1constant>",
  64         m()("(</?)code>") >> "\\1literal>",
  65         m()(">([^<>]+)<br>","s") >> "><highlights>\\1</highlights>",
  66         m()("<br>") >> "<br />",
  67         #        m()("<date>") >> "<sect1info><date>",
  68         #        m()("</date>") >> "</date></sect1info>",
  69         m()("<reference>") >> "<reference id=\"reference\">" >> 1,
  70         m()("<a\s+href=\"((?:http|ftp|mailto):[^<>]+)\"\s*>((?:.(?!</a>))*.)</a>"
  71           ,"s") >> "<ulink url=\"\\1\">\\2</ulink>",
  72         m()("<a\s+href=\"zziplib.html\#([\w_]+)\"\s*>((?:.(?!</a>))*.)</a>","s")
  73         >> "<link linkend=\"$1\">$2</link>",
  74         m()("<a\s+href=\"(zziplib.html)\"\s*>((?:.(?!</a>))*.)</a>","s")
  75         >> "<link linkend=\"reference\">$2</link>",
  76         m()("<a\s+href=\"([\w-]+[.]html)\"\s*>((?:.(?!</a>))*.)</a>","s")
  77         >> "<link linkend=\"\\1\">\\2</link>",
  78         m()("<a\s+href=\"([\w-]+[.](?:h|c|am|txt))\"\s*>((?:.(?!</a>))*.)</a>"
  79           ,"s") >> "<ulink url=\"file:\\1\">\\2</ulink>",
  80         m()("<a\s+href=\"([A-Z0-9]+[.][A-Z0-9]+)\"\s*>((?:.(?!</a>))*.)</a>","s")
  81         >> "<ulink url=\"file:\\1\">\\2</ulink>"
  82         # m()("(</?)subtitle>") >> "\\1para>"
  83         # $_ .= "</sect1>" if /<sect1[> ]/
  84         ]
  85     regexlist2 = [
  86         m()(r"<br\s*/?>") >> "",
  87         m()(r"(</?)em>") >> r"\1emphasis>",
  88         m()(r"<code>") >> "<userinput>",
  89         m()(r"</code>") >> "</userinput>",
  90         m()(r"<link>") >> "<function>",
  91         m()(r"</link>") >> "</function>",
  92         m()(r"(?s)\s*</screen>") >> "</screen>",
  93         # m()(r"<ul>") >> "</para><programlisting>\n",
  94         # m()(r"</ul>") >> "</programlisting><para>",
  95         m()(r"<ul>") >> "<itemizedlist>",
  96         m()(r"</ul>") >> "</itemizedlist>",
  97         # m()(r"<li>") >> "",
  98         # m()(r"</li>") >> ""
  99         m()(r"<li>") >> "<listitem><para>",
 100         m()(r"</li>") >> "</para></listitem>\n",
 101         ]
 102 class htm2dbk_conversion(htm2dbk_conversion_base):
 103     def __init__(self):
 104         self.version = "" # str(date.today)
 105         self.filename = "."
 106     def convert(self,text): # $text
 107         txt = text.replace("<!--VERSION-->", self.version)
 108         for conv in self.regexlist:
 109             txt &= conv
 110         return txt.replace("--filename--", self.filename)
 111     def convert2(self,text): # $text
 112         txt = text.replace("<!--VERSION-->", self.version)
 113         for conv in self.regexlist:
 114             txt &= conv
 115         return txt
 116
 117 class htm2dbk_document(htm2dbk_conversion):
 118     """ create document, add(text) and get the value() """
 119     doctype = (
 120         '<!DOCTYPE book PUBLIC "-//OASIS//DTD'+
 121         ' DocBook XML V4.1.2//EN"'+"\n"+
 122         '       "http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd">'+
 123         "\n")
 124     book_start = '<book><chapter><title>Documentation</title>'+"\n"
 125     book_end_chapters = '</chapter>'+"\n"
 126     book_end = '</book>'+"\n"
 127     def __init__(self):
 128         htm2dbk_conversion.__init__(self)
 129         self.text = self.doctype + self.book_start
 130     def add(self,text):
 131         if self.text & m()("<reference"):
 132             self.text += self.book_end_chapters ; self.book_end_chapters = ""
 133         self.text += self.convert(text).replace(
 134             "<br />","") & (
 135             m()("<link>([^<>]*)</link>") >> "<function>\\1</function>") & (
 136             m()("(?s)(<refentryinfo>\s*)<sect1info>" +
 137                 "(<date>[^<>]*</date>)</sect1info>") >> "\\1\\2")
 138     def value(self):
 139         return self.text + self.book_end_chapters + self.book_end
 140
 141 def htm2dbk_files(args):
 142     doc = htm2dbk_document()
 143     for filename in args:
 144         try:
 145             f = open(filename, "r")
 146             doc.filename = filename
 147             doc.add(f.read())
 148             f.close()
 149         except IOError, e:
 150             print >> sys.stderr, "can not open "+filename
 151     return doc.value()
 152
 153 def html2docbook(text):
 154     """ the C comment may contain html markup - simulate with docbook tags """
 155     return htm2dbk_conversion().convert2(text)
 156
 157 if __name__ == "__main__":
 158     print htm2dbk_files(sys.argv[1:])