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
|
#! /usr/bin/env ruby
#
# Copyright (c) 2001 by Jim Menard <jimm@io.com>
#
# Released under the same license as Ruby. See
# http://www.ruby-lang.org/en/LICENSE.txt.
#
# I was going to use NQXML to parse README.sgml, but I can't because SGML
# is not XML. For example, the DOCTYPE tag's PUBLIC identifier takes one
# argument in SGML but two arguments in XML, and the Docbook <xref> tag
# has no end tag. Therefore, README.sgml is not a legal XML document.
#
FILL_COLUMN = 75
SCREEN_PREFIX = "\t "
PROGRAM_PREFIX = "\t"
titleCounters = Array.new(6, 0)
exampleXrefs = Hash.new()
exampleCounter = 0
def fillParagraph(prefix, txt)
para = Array.new()
txt = txt.gsub(/\s+/m, ' ') # turn whitespace into single spaces and dup
fillColumn = FILL_COLUMN - prefix.length
regex = /^(.{0,#{fillColumn}})[ \n]/m
while txt.length > fillColumn
if txt =~ regex
para << $1
txt = $'
else
para << txt
txt = ''
end
end
para << txt unless txt.empty?
return "\n" + prefix + para.join("\n" + prefix.gsub(/\S/, ' ')) + "\n"
end
# Slurp the whole file into `text'.
text = File.open(ARGV[0], 'r').read()
# Read ENTITY substitutions and replace them in the text. Must do this
# before we delete the entire DOCTYPE tag below.
text.scan(/<!ENTITY\s+(\w+)\s+"([^"]*)">/) { | name, value |
value.gsub!(/<.*?>/, '')
text.gsub!(/&#{name};/, value)
}
# Erase entire sections of the document.
text.gsub!(/\<artheader>.*<\/artheader>/m, '')
text.gsub!(/<!--(.*?)-->/m, '')
text.gsub!(/<!DOCTYPE.*?]>/m, '')
# Special entity substitutions.
text.gsub!(/</, '<')
text.gsub!(/>/, '>')
text.gsub!(/"/, '"')
text.gsub!(/'/, '\'')
text.gsub!(/©/, '(c)')
text.gsub!(/&/, '&')
# Replace ordered list listitems with numbers
text.gsub!(/<orderedlist>(.*?)<\/orderedlist>/m) {
items = $1
i = 0
items.gsub!(/<listitem>\s*<para>/m) { i += 1; " <para>#{i}. " }
items
}
# Miscellaneous tag replacement.
# FIX: replace <listitem> with number inside <orderedlist>.
text.gsub!(/<listitem>/, ' * ')
text.gsub!(/<replaceable>(.*?)<\/replaceable>/, '<\1>')
text.gsub!(/<email>(.*?)<\/email>/, '<\1>')
text.gsub!(/<firstterm>(.*?)<\/firstterm>/, '``\1\'\'')
# Example headings. Do this before generating cross-references.
text.gsub!(/<example(.*?)<title>(.*?)<\/title>/m) { |t|
id, title = $1, $2
exampleCounter += 1
if id =~ /id\s*=\s*"(.*)"/
exampleXrefs[$1] = exampleCounter
end
"Example #{exampleCounter}. #{title}"
}
# Cross-references.
text.gsub!(/<xref\s+linkend\s*=\s*"([^"]+)">/m) { |t|
if exampleXrefs[$1]
"Example #{exampleXrefs[$1]}"
else
"``#{$1}''"
end
}
# URLs.
text.gsub!(/<ulink\s+url="([^"]*)">(.*?)<\/ulink>/m, '\2 (\1)')
# Program and screen listings: put whitespace at the beginning of each line.
text.gsub!(/<(screen|programlisting)>(.*?)<\/\1>/m) { |t|
t.gsub(/\n/m, "\n" + ($1 == 'screen' ? SCREEN_PREFIX : PROGRAM_PREFIX))
}
# Citetitle. Put it in quotes.
text.gsub!(/<citetitle.*?>(.*?)<\/citetitle>/m, '"\1"')
# Delete start and end tags of a bunch of tags.
tags = %w(article classname filename(\s+class="directory")? function
itemizedlist application acronym literal screen programlisting token
markup option command)
text.gsub!(/<\/?(#{tags.join('|')})>/, '')
# Delete only the ends of these tags.
text.gsub!(/<\/(listitem|sect\d+|example)>/, '')
# Warnings.
text.gsub!(/\s*<warning>\s*/, "\n\n======== WARNING ========\n\n ")
text.gsub!(/\s*<\/warning>\s*/, "\n\n======== WARNING ========\n\n")
# Section headings
text.gsub!(/<sect(\d).*?<title>(.*?)<\/title>/m) { |t|
sect, title = $1.to_i, $2
case sect
when 1
titleCounters[1] += 1
titleCounters[2] = titleCounters[3] = titleCounters[4] = 0
title = "#{titleCounters[1]}. #{title.upcase()}"
title += "\n" + ('=' * title.length)
when 2
titleCounters[2] += 1
titleCounters[3] = 0
title = "#{titleCounters[1]}.#{titleCounters[2]}. #{title}"
title += "\n" + ('-' * title.length)
when 3
titleCounters[3] += 1
titleCounters[4] = 0
title = "#{titleCounters[1]}.#{titleCounters[2]}.#{titleCounters[3]}."+
" #{title}"
when 4
titleCounters[4] += 1
title = "#{titleCounters[1]}.#{titleCounters[2]}.#{titleCounters[3]}."+
"#{titleCounters[4]}. #{title}"
end
title + "\n"
}
# Wrap paragraphs.
text.gsub!(/\n([^\n]*?)<para>\s*(.*?)\s*<\/para>/m) { | txt |
fillParagraph($1, $2)
}
text.gsub!(/^\s+$/, '') # get rid of spaces in spaces-only lines
text.gsub!(/\n\n+/m, "\n\n") # multiple newlines
print text
|
