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
170
|
#!/usr/bin/perl -w
# Script parses the XML file for the appendix on preseeding and extracts
# example snippts to form the raw preseed example file. Section titles are
# added as headers.
# The script will include all text between <informalexample> tags that have
# the attribute 'role="example"' set, except if a 'condition' attribute is
# in force that does not match the specified release or if an 'arch' attribute
# is in force that does not match the specified architecture.
# Define module to use
use HTML::Parser();
use Getopt::Std;
local %tagstatus;
local %example;
local %ignore;
local $prevtag = '';
local $titletag;
local $settitle = 0;
$example{'print'} = 0;
$example{'in_sect'} = 0;
$example{'first'} = 1;
$example{'new'} = 0;
getopts('hda:r:') || die "Unknown command line arguments! Try $0 -h\n";
use vars qw($opt_h $opt_d $opt_a $opt_r);
if ($opt_h) {
print <<END;
preseed.pl: parses preseed appendix xml file to extract preseed example file
Usage: $0 [-hdac] <xml-file>
Options:
-h display this help information
-d debug mode
-a <arch> architecture for which to generate the example
(default: i386)
-r <release> release for which to generate the example (required)
END
exit 0;
}
die "Must specify release for which to generate example." if ! $opt_r;
my $xmlfile = shift;
die "Must specify XML file to parse!" if ! $xmlfile;
die "Specified XML file \"$xmlfile\" not found." if ! -f $xmlfile;
my $arch = $opt_a ? "$opt_a" : "i386";
my $release = $opt_r;
# Create instance
$p = HTML::Parser->new(
start_h => [\&start_rtn, 'tagname, text, attr'],
text_h => [\&text_rtn, 'text'],
end_h => [\&end_rtn, 'tagname']);
# Start parsing the specified file
$p->parse_file($xmlfile);
# Execute when start tag is encountered
sub start_rtn {
my ($tagname, $text, $attr) = @_;
print STDERR "\nStart: $tagname\n" if $opt_d;
if ( $tagname =~ /appendix|sect1|sect2|sect3|para/ ) {
$tagstatus{$tagname}{'count'} += 1;
print STDERR "$tagname $tagstatus{$tagname}{'count'}\n" if $opt_d;
if ( ! exists $ignore{'tag'} ) {
if ( exists $attr->{condition} ) {
print STDERR "Condition: $attr->{condition}\n" if $opt_d;
if ( $attr->{condition} ne $release ) {
$ignore{'tag'} = $tagname;
$ignore{'depth'} = $tagstatus{$tagname}{'count'};
print STDERR "Start ignore because of condition" if $opt_d;
}
}
if ( exists $attr->{arch} ) {
print STDERR "Architecture: $attr->{arch}\n" if $opt_d;
if ( $attr->{arch} ne $arch ) {
$ignore{'tag'} = $tagname;
$ignore{'depth'} = $tagstatus{$tagname}{'count'};
print STDERR "Start ignore because of architecture" if $opt_d;
}
}
}
}
# Assumes that <title> is the first tag after a section tag
if ( $prevtag =~ /sect1|sect2|sect3/ ) {
$settitle = ( $tagname eq 'title' );
$titletag = $prevtag;
$example{'in_sect'} = 0;
}
$prevtag = $tagname;
if ( $tagname eq 'informalexample' && ! exists $ignore{'tag'} ) {
if ( exists $attr->{role} && $attr->{role} eq "example" ) {
$example{'print'} = 1;
$example{'new'} = 1;
}
}
}
# Execute when text is encountered
sub text_rtn {
my ($text) = @_;
if ( $settitle ) {
# Clean leading and trailing whitespace for titles
$text =~ s/^[[:space:]]*//;
$text =~ s/[[:space:]]*$//;
$tagstatus{$titletag}{'title'} = $text;
$settitle = 0;
}
if ( $example{'print'} ) {
# Print section headers
for ($s=1; $s<=3; $s++) {
my $sect="sect$s";
if ( $tagstatus{$sect}{'title'} ) {
print "\n" if ( $s == 1 && ! $example{'first'} );
for ( $i = 1; $i <= 5 - $s; $i++ ) { print "#"; };
print " $tagstatus{$sect}{'title'}\n";
delete $tagstatus{$sect}{'title'};
}
}
# Clean leading whitespace
if ( $example{'new'} ) {
$text =~ s/^[[:space:]]*//;
}
# Replace entities in examples
# FIXME: should maybe be extracted from entity definition
$text =~ s/&archive-mirror;/http.us.debian.org/;
print "$text";
$example{'first'} = 0;
$example{'new'} = 0;
$example{'in_sect'} = 1;
}
}
# Execute when the end tag is encountered
sub end_rtn {
my ($tagname) = @_;
print STDERR "\nEnd: $tagname\n" if $opt_d;
if ( $tagname eq 'informalexample' ) {
$example{'print'} = 0;
}
if ( $tagname =~ /appendix|sect1|sect2|sect3|para/ ) {
delete $tagstatus{$tagname}{'title'} if exists $tagstatus{$tagname}{'title'};
if ( exists $ignore{'tag'} ) {
if ( $ignore{'tag'} eq $tagname && $ignore{'depth'} == $tagstatus{$tagname}{'count'} ) {
delete $ignore{'tag'};
}
}
if ( $example{'in_sect'} ) {
print "\n";
$example{'in_sect'} = 0;
}
$tagstatus{$tagname}{'count'} -= 1;
print STDERR "$tagname $tagstatus{$tagname}{'count'}\n" if $opt_d;
die "Invalid XML file: negative count for tag <$tagname>!" if $tagstatus{$tagname}{'count'} < 0;
}
}
|
