1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
|
#! /usr/bin/env python3
"""
this file converts simple html text into a docbook xml variant.
The mapping of markups and links is far from perfect. But all we
want is the docbook-to-pdf converter and similar technology being
present in the world of docbook-to-anything converters. """
from datetime import date
from zzipdoc.match import Match
import sys
m = Match
class htm2dbk_conversion_base:
regexlist = [
m()("</[hH]2>(.*)", "m") >> "</title>\n<subtitle>\\1</subtitle>",
m()("<[hH]2>") >> "<sect1 id=\"--filename--\"><title>",
m()("<[Pp]([> ])","m") >> "<para\\1",
m()("</[Pp]>") >> "</para>",
m()("<(pre|PRE)>") >> "<screen>",
m()("</(pre|PRE)>") >> "</screen>",
m()("<[hH]3>") >> "<sect2><title>",
m()("</[hH]3>((?:.(?!<sect2>))*.?)", "s") >> "</title>\\1</sect2>",
m()("<!doctype [^<>]*>","s") >> "",
m()("<!DOCTYPE [^<>]*>","s") >> "",
m()("(<\w+\b[^<>]*\swidth=)(\d+\%)","s") >> "\\1\"\\2\"",
m()("(<\w+\b[^<>]*\s\w+=)(\d+)","s") >> "\\1\"\\2\"",
m()("&&") >> "\&\;\&\;",
m()("\$\<") >> "\$\<\;",
m()("&(\w+[\),])") >> "\&\;\\1",
m()("(</?)span(\s[^<>]*)?>","s") >> "\\1phrase\\2>",
m()("(</?)small(\s[^<>]*)?>","s") >> "\\1note\\2>",
m()("(</?)(b|em|i)>")>> "\\1emphasis>",
m()("(</?)(li)>") >> "\\1listitem>",
m()("(</?)(ul)>") >> "\\1itemizedlist>",
m()("(</?)(ol)>") >> "\\1orderedlist>",
m()("(</?)(dl)>") >> "\\1variablelist>",
m()("<dt\b([^<>]*)>","s") >> "<varlistentry\\1><term>",
m()("</dt\b([^<>]*)>","s") >> "</term>",
m()("<dd\b([^<>]*)>","s") >> "<listitem\\1>",
m()("</dd\b([^<>]*)>","s") >> "</listitem></varlistentry>",
m()("<table\b([^<>]*)>","s")
>> "<informaltable\\1><tgroup cols=\"2\"><tbody>",
m()("</table\b([^<>]*)>","s") >> "</tbody></tgroup></informaltable>",
m()("(</?)tr(\s[^<>]*)?>","s") >> "\\1row\\2>",
m()("(</?)td(\s[^<>]*)?>","s") >> "\\1entry\\2>",
m()("<informaltable\b[^<>]*>\s*<tgroup\b[^<>]*>\s*<tbody>"+
"\s*<row\b[^<>]*>\s*<entry\b[^<>]*>\s*<informaltable\b","s")
>> "<informaltable",
m()("</informaltable>\s*</entry>\s*</row>"+
"\s*</tbody>\s*</tgroup>\s*</informaltable>", "s")
>> "</informaltable>",
m()("(<informaltable[^<>]*\swidth=\"100\%\")","s") >> "\\1 pgwide=\"1\"",
m()("(<tbody>\s*<row[^<>]*>\s*<entry[^<>]*\s)(width=\"50\%\")","s")
>> "<colspec colwidth=\"1*\" /><colspec colwidth=\"1*\" />\n\\1\\2",
m()("<nobr>([\'\`]*)<tt>") >> "<cmdsynopsis>\\1",
m()("</tt>([\'\`]*)</nobr>") >> "\\1</cmdsynopsis>",
m()("<nobr><(?:tt|code)>([\`\"\'])") >> "<cmdsynopsis>\\1",
m()("<(?:tt|code)><nobr>([\`\"\'])") >> "<cmdsynopsis>\\1",
m()("([\`\"\'])</(?:tt|code)></nobr>") >> "\\1</cmdsynopsis>",
m()("([\`\"\'])</nobr></(?:tt|code)>") >> "\\1</cmdsynopsis>",
m()("(</?)tt>") >> "\\1constant>",
m()("(</?)code>") >> "\\1literal>",
m()(">([^<>]+)<br>","s") >> "><highlights>\\1</highlights>",
m()("<br>") >> "<br />",
# m()("<date>") >> "<sect1info><date>",
# m()("</date>") >> "</date></sect1info>",
m()("<reference>") >> "<reference id=\"reference\">" >> 1,
m()("<a\s+href=\"((?:http|ftp|mailto):[^<>]+)\"\s*>((?:.(?!</a>))*.)</a>"
,"s") >> "<ulink url=\"\\1\">\\2</ulink>",
m()("<a\s+href=\"zziplib.html\#([\w_]+)\"\s*>((?:.(?!</a>))*.)</a>","s")
>> "<link linkend=\"$1\">$2</link>",
m()("<a\s+href=\"(zziplib.html)\"\s*>((?:.(?!</a>))*.)</a>","s")
>> "<link linkend=\"reference\">$2</link>",
m()("<a\s+href=\"([\w-]+[.]html)\"\s*>((?:.(?!</a>))*.)</a>","s")
>> "<link linkend=\"\\1\">\\2</link>",
m()("<a\s+href=\"([\w-]+[.](?:h|c|am|txt))\"\s*>((?:.(?!</a>))*.)</a>"
,"s") >> "<ulink url=\"file:\\1\">\\2</ulink>",
m()("<a\s+href=\"([A-Z0-9]+[.][A-Z0-9]+)\"\s*>((?:.(?!</a>))*.)</a>","s")
>> "<ulink url=\"file:\\1\">\\2</ulink>"
# m()("(</?)subtitle>") >> "\\1para>"
# $_ .= "</sect1>" if /<sect1[> ]/
]
regexlist2 = [
m()(r"<br\s*/?>") >> "",
m()(r"(</?)em>") >> r"\1emphasis>",
m()(r"<code>") >> "<userinput>",
m()(r"</code>") >> "</userinput>",
m()(r"<link>") >> "<function>",
m()(r"</link>") >> "</function>",
m()(r"(?s)\s*</screen>") >> "</screen>",
# m()(r"<ul>") >> "</para><programlisting>\n",
# m()(r"</ul>") >> "</programlisting><para>",
m()(r"<ul>") >> "<itemizedlist>",
m()(r"</ul>") >> "</itemizedlist>",
# m()(r"<li>") >> "",
# m()(r"</li>") >> ""
m()(r"<li>") >> "<listitem><para>",
m()(r"</li>") >> "</para></listitem>\n",
]
class htm2dbk_conversion(htm2dbk_conversion_base):
def __init__(self):
self.version = "" # str(date.today)
self.filename = "."
def convert(self,text): # $text
txt = text.replace("<!--VERSION-->", self.version)
for conv in self.regexlist:
txt &= conv
return txt.replace("--filename--", self.filename)
def convert2(self,text): # $text
txt = text.replace("<!--VERSION-->", self.version)
for conv in self.regexlist:
txt &= conv
return txt
class htm2dbk_document(htm2dbk_conversion):
""" create document, add(text) and get the value() """
doctype = (
'<!DOCTYPE book PUBLIC "-//OASIS//DTD'+
' DocBook XML V4.1.2//EN"'+"\n"+
' "http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd">'+
"\n")
book_start = '<book><chapter><title>Documentation</title>'+"\n"
book_end_chapters = '</chapter>'+"\n"
book_end = '</book>'+"\n"
def __init__(self):
htm2dbk_conversion.__init__(self)
self.text = self.doctype + self.book_start
def add(self,text):
if self.text & m()("<reference"):
self.text += self.book_end_chapters ; self.book_end_chapters = ""
self.text += self.convert(text).replace(
"<br />","") & (
m()("<link>([^<>]*)</link>") >> "<function>\\1</function>") & (
m()("(?s)(<refentryinfo>\s*)<sect1info>" +
"(<date>[^<>]*</date>)</sect1info>") >> "\\1\\2")
def value(self):
return self.text + self.book_end_chapters + self.book_end
def htm2dbk_files(args):
doc = htm2dbk_document()
for filename in args:
try:
f = open(filename, "r")
doc.filename = filename
doc.add(f.read())
f.close()
except IOError:
print("can not open "+filename, file=sys.stderr)
return doc.value()
def html2docbook(text):
""" the C comment may contain html markup - simulate with docbook tags """
return htm2dbk_conversion().convert2(text)
if __name__ == "__main__":
from optparse import OptionParser
cmdline = OptionParser("%prog [options] files...")
cmdline.add_option("-o", "--into", metavar="FILE", default="")
opt, args = cmdline.parse_args()
result = htm2dbk_files(args)
if not opt.into:
print(result)
else:
f = open(opt.into, "w")
f.write(result)
f.close()
|
