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
|
use Test::More tests => 17;
use strict;
use HTML::TokeParser;
# First we create an HTML document to test
my $file = "ttest$$.htm";
die "$file already exists" if -e $file;
open(F, ">$file") or die "Can't create $file: $!";
print F <<'EOT'; close(F);
<!--This is a test-->
<html><head><title>
This is the <title>
</title>
<base href="http://www.perl.com">
</head>
<body background="bg.gif">
<h1>This is the <b>title</b> again
</h1>
And this is a link to the <a href="http://www.perl.com"><img src="camel.gif" alt="Perl"> <!--nice isn't it-->Institute</a>
<br/><? process instruction >
</body>
</html>
EOT
END { unlink($file) || warn "Can't unlink $file: $!"; }
my $p;
$p = HTML::TokeParser->new($file) || die "Can't open $file: $!";
ok($p->unbroken_text);
if ($p->get_tag("foo", "title")) {
my $title = $p->get_trimmed_text;
#diag "Title: $title";
is($title, "This is the <title>");
}
undef($p);
# Test with reference to glob
open(F, $file) || die "Can't open $file: $!";
$p = HTML::TokeParser->new(\*F);
my $scount = 0;
my $ecount = 0;
my $tcount = 0;
my $pcount = 0;
while (my $token = $p->get_token) {
$scount++ if $token->[0] eq "S";
$ecount++ if $token->[0] eq "E";
$pcount++ if $token->[0] eq "PI";
}
undef($p);
close F;
# Test with glob
open(F, $file) || die "Can't open $file: $!";
$p = HTML::TokeParser->new(*F);
$tcount++ while $p->get_tag;
undef($p);
close F;
# Test with plain file name
$p = HTML::TokeParser->new($file) || die;
$tcount++ while $p->get_tag;
undef($p);
#diag "Number of tokens found: $tcount/2 = $scount + $ecount";
is($tcount, 34);
is($scount, 10);
is($ecount, 7);
is($pcount, 1);
is($tcount/2, $scount + $ecount);
ok(!HTML::TokeParser->new("/noT/thEre/$$"));
$p = HTML::TokeParser->new($file) || die;
$p->get_tag("a");
my $atext = $p->get_text;
undef($p);
is($atext, "Perl\240Institute");
# test parsing of embeded document
$p = HTML::TokeParser->new(\<<HTML);
<title>Title</title>
<H1>
Heading
</h1>
HTML
ok($p->get_tag("h1"));
is($p->get_trimmed_text, "Heading");
undef($p);
# test parsing of large embedded documents
my $doc = "<a href='foo'>foo is bar</a>\n\n\n" x 2022;
#use Time::HiRes qw(time);
my $start = time;
$p = HTML::TokeParser->new(\$doc);
#diag "Construction time: ", time - $start;
my $count;
while (my $t = $p->get_token) {
$count++ if $t->[0] eq "S";
}
#diag "Parse time: ", time - $start;
is($count, 2022);
$p = HTML::TokeParser->new(\<<'EOT');
<H1>This is a heading</H1>
This is s<b>o</b>me<hr>text.
<br />
This is some more text.
<p>
This is even some more.
EOT
$p->get_tag("/h1");
my $t = $p->get_trimmed_text("br", "p");
is($t, "This is some text.");
$p->get_tag;
$t = $p->get_trimmed_text("br", "p");
is($t,"This is some more text.");
undef($p);
$p = HTML::TokeParser->new(\<<'EOT');
<H1>This is a <b>bold</b> heading</H1>
This is some <i>italic</i> text.<br />This is some <span id=x>more text</span>.
<p>
This is even some more.
EOT
$p->get_tag("h1");
$t = $p->get_phrase;
is($t, "This is a bold heading");
$t = $p->get_phrase;
is($t, "");
$p->get_tag;
$t = $p->get_phrase;
is($t, "This is some italic text. This is some more text.");
undef($p);
|
