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
|
#!/usr/bin/perl
use File::Find;
sub escape_html {
my $str = shift;
$str =~ s/&/&/g;
$str =~ s/</</g;
$str =~ s/>/>/g;
$str =~ s/"/"/g;
$str =~ s/'/'/g;
return $str;
}
my %params;
if ($ENV{QUERY_STRING}) {
foreach my $pair (split /&/, $ENV{QUERY_STRING}) {
my ($key, $value) = split /=/, $pair;
$value =~ tr/+/ /;
$value =~ s/%([a-fA-F0-9][a-fA-F0-9])/pack("C", hex($1))/eg;
$params{$key} = $value;
}
}
my $search_text = $params{'q'} || '';
$search_text = substr($search_text, 0, 64);
$search_text =~ s/[^a-zA-Z0-9 ]//g;
my $directory = '../_site/log/';
my @results;
my %excluded_files = (
'index.html' => 1, # /log/index.html
);
if ($search_text =~ /\S/) {
find({
wanted => sub {
# Ignore directories and only process index.html
return unless -f $_ && $_ eq 'index.html';
# Calculate the relative path for the URL (prevents leaking server file structure)
my $rel_path = $File::Find::name;
$rel_path =~ s|^\Q$directory\E/?||;
return if $excluded_files{$rel_path};
if (open my $fh, '<', $_) {
my $content = do { local $/; <$fh> };
close $fh;
if ($content =~ /\Q$search_text\E/i) {
# Extract Title
my ($title) = $content =~ /<title>(.*?)<\/title>/is;
$title = $title ? escape_html($title) : $rel_path;
# Extract the first <p> tag content
my ($p_content) = $content =~ /<p[^>]*>(.*?)<\/p>/is;
# Process the snippet
my $snippet = $p_content || "";
$snippet =~ s/<[^>]*>//g; # Remove internal tags
$snippet =~ s/\s+/ /g; # Collapse whitespace
# Escape HTML entities AFTER stripping tags
# but BEFORE sending to the user to prevent XSS.
$snippet = escape_html(substr($snippet, 0, 50));
$snippet .= "..." if length($p_content || "") > 50;
push @results, {
path => $File::Find::name,
title => $title,
snippet => $snippet
};
}
}
},
no_chdir => 0,
follow => 0,
}, $directory);
}
print "Content-Type: text/html\n\n";
my $list;
if ($search_text eq '') {
$list = "<p>Please enter a search term above.</p>";
} elsif (@results == 0) {
$list = "<p>No results found for \"<b>$search_text</b>\".</p>";
} else {
$list = "<ul>";
foreach my $res (@results) {
my $url = $res->{path};
$list .= "<li><a href=\"/$url\">$res->{title}</a><br><small>$res->{snippet}</small></li>";
}
$list .= "</ul>";
}
my $safe_search_text = escape_html($search_text);
my $year = (localtime)[5] + 1900;
print <<"HTML";
<!DOCTYPE html>
<html lang="en-us">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>Search</title>
<link rel="stylesheet" href="/assets/css/main.css">
<link rel="stylesheet" href="/assets/css/skeleton.css">
</head>
<body>
<div id="nav-container" class="container">
<ul id="navlist" class="left">
<li><a href="/" class="link-decor-none">hme</a></li>
<li><a href="/log/" class="link-decor-none">log</a></li>
<li><a href="/projects/" class="link-decor-none">poc</a></li>
<li><a href="/about/" class="link-decor-none">abt</a></li>
<li class="active"><a href="/cgi-bin/find.cgi" class="link-decor-none">sws</a></li>
<li><a href="/feed.xml" class="link-decor-none">rss</a></li>
</ul>
</div>
<main class="container" id="main">
<div class="container">
<h2>Search</h2>
<form action="" method="GET">
<input id="search-box" type="text" name="q" value="$safe_search_text">
<input id="search-btn" type="submit" value="Search">
</form>
$list
</div>
</main>
<div class="footer">
<div class="container">
<div class="twelve columns right container-2">
<p id="footer-text">© ASCIIMX - $year</p>
</div>
</div>
</div>
</body>
</html>
HTML
|
