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
|
#!perl -w
use strict;
use Test::More tests => 11;
{ package H;
sub new { bless {}, shift; }
sub header {
my $self = shift;
my $key = uc(shift);
my $old = $self->{$key};
if (@_) { $self->{$key} = shift; }
$old;
}
sub push_header {
my($self, $k, $v) = @_;
$k = uc($k);
if (exists $self->{$k}) {
$self->{$k} = [ $self->{$k} ] unless ref $self->{$k};
push(@{$self->{$k}}, $v);
} else {
$self->{$k} = $v;
}
}
sub as_string {
my $self = shift;
my $str = "";
for (sort keys %$self) {
if (ref($self->{$_})) {
my $v;
for $v (@{$self->{$_}}) {
$str .= "$_: $v\n";
}
} else {
$str .= "$_: $self->{$_}\n";
}
}
$str;
}
}
my $HTML = <<'EOT';
<title>Å vre eller å ikke vre</title>
<meta http-equiv="Expires" content="Soon">
<meta http-equiv="Foo" content="Bar">
<link href="mailto:gisle@aas.no" rev=made title="Gisle Aas">
<script>
"</script>"
ignore this
</script>
<base href="http://www.sn.no">
<meta name="Keywords" content="test, test, test,...">
<meta name="Keywords" content="more">
Dette er vanlig tekst. Denne teksten definerer ogs slutten p
<head> delen av dokumentet.
<style>
"</style>"
ignore this too
</style>
<isindex>
Dette er ogs vanlig tekst som ikke skal blir parset i det hele tatt.
EOT
$| = 1;
#$HTML::HeadParser::DEBUG = 1;
require HTML::HeadParser;
my $p = HTML::HeadParser->new( H->new );
if ($p->parse($HTML)) {
fail("Need more data which should not happen");
} else {
#diag $p->as_string;
pass();
}
like($p->header('Title'), qr/ vre eller ikke vre/);
is($p->header('Expires'), 'Soon');
is($p->header('Content-Base'), 'http://www.sn.no');
like($p->header('Link'), qr/<mailto:gisle\@aas.no>/);
# This header should not be present because the head ended
ok(!$p->header('Isindex'));
# Try feeding one char at a time
my $expected = $p->as_string;
my $nl = 1;
$p = HTML::HeadParser->new(H->new);
while ($HTML =~ /(.)/sg) {
#print STDERR '#' if $nl;
#print STDERR $1;
$nl = $1 eq "\n";
$p->parse($1) or last;
}
is($p->as_string, $expected);
# Try reading it from a file
my $file = "hptest$$.html";
die "$file already exists" if -e $file;
open(FILE, ">$file") or die "Can't create $file: $!";
binmode(FILE);
print FILE $HTML;
print FILE "<p>This is more content...</p>\n" x 2000;
print FILE "<title>Buuuh!</title>\n" x 200;
close FILE or die "Can't close $file: $!";
$p = HTML::HeadParser->new(H->new);
$p->parse_file($file);
unlink($file) or warn "Can't unlink $file: $!";
is($p->header("Title"), " vre eller ikke vre");
# We got into an infinite loop on data without tags and no EOL.
# This was actually a HTML::Parser bug.
open(FILE, ">$file") or die "Can't create $file: $!";
print FILE "Foo";
close(FILE);
$p = HTML::HeadParser->new(H->new);
$p->parse_file($file);
unlink($file) or warn "Can't unlink $file: $!";
ok(!$p->as_string);
SKIP: {
skip "Need Unicode support", 2 if $] < 5.008;
# Test that the Unicode BOM does not confuse us?
$p = HTML::HeadParser->new(H->new);
ok($p->parse("\x{FEFF}\n<title>Hi <foo></title>"));
$p->eof;
is($p->header("title"), "Hi <foo>");
}
|
