CGI script for searching site.

3 files changed, 100 insertions, 126 deletions

diff --git a/README.txt b/README.txt
index 5f799c4..ebd6d3f 100644
--- a/README.txt
+++ b/README.txt
@@ -18,4 +18,6 @@ Checking CGI script errors in chroot:
 
 Search Perl deps:
 
-# pkg_add p5-HTML-Escape
+# doas pkg_add p5-File-Slurper
+# doas pkg_add p5-HTML-TreeBuilder-XPath
+
diff --git a/_site/cgi-bin/find.cgi b/_site/cgi-bin/find.cgi
index bad12e7..f0d2b3c 100644
--- a/_site/cgi-bin/find.cgi
+++ b/_site/cgi-bin/find.cgi
@@ -1,83 +1,62 @@
 #!/usr/bin/perl
 
-use File::Find;
-
-sub escape_html {
-    my $str = shift;
-    $str =~ s/&/&/g;
-    $str =~ s/</&lt;/g;
-    $str =~ s/>/&gt;/g;
-    $str =~ s/"/&quot;/g;
-    $str =~ s/'/&#39;/g;
-    return $str;
+use Encode qw(decode_utf8);
+use HTML::Escape qw(escape_html);
+
+my $search_text = '';
+
+if ($ENV{QUERY_STRING} =~ /^q=([^&]*)/) {
+    $search_text = decode_utf8($1 // "");
+    $search_text =~ s/\P{Print}//g;  # toss any non-printable utf-8 characters
+    $search_text = substr($search_text, 0, 64);
+    $search_text =~ s/^\s+|\s+$//g;
 }
 
-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 @results;
+
+# Search only index.html files inside the first level of subdirectories
+my $start_dir = '../log'; 
+my @files = glob("$start_dir/*/index.html");
+
+foreach my $path (@files) {
+    # Skip if the path is a symlink or not a file
+    next if -l $path || ! -f $path;
+
+    next unless open(my $fh, '<:utf8', $path);
+    my $html = do { local $/; <$fh> };
+    close($fh);
+  
+    my ($text) = $html =~ m|<main>(.*?)</main>|is;
+    $text =~ s|<[^>]+>| |g;
+    $text =~ s|\s+| |g;
+
+    next unless $text =~ /(.{0,40})(\Q$search_text\E)(.{0,40})/is;
+    my ($before, $actual, $after) = ($1, $2, $3);
+
+    # Trim if we cut into the middle of a sentence
+    $after =~ s/\s\S*$// if length($after) > 25;
+    $before =~ s/^.*?\s// if length($before) > 25;
+
+    if ($before =~ /\S/) { # If before has non-whitespace characters
+        $before = ucfirst($before);
+    } else {
+        $before = "";      # Clear any stray spaces
+        $actual = ucfirst($actual);
     }
-}
 
-my $search_text = $params{'q'} || '';
-$search_text = substr($search_text, 0, 64);
-$search_text =~ s/[^a-zA-Z0-9 ]//g; 
+    my $safe_before = escape_html($before);
+    my $safe_actual = escape_html($actual);
+    my $safe_after  = escape_html($after);
+    my $snippet = "${safe_before}<b>${safe_actual}</b>${safe_after}...";
 
-my $directory   = '../log/'; 
-my @results;
+    my ($title) = $html =~ m|<title>(.*?)</title>|is;
+    my $safe_title  = escape_html($title);
 
-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);
+    push @results, { 
+        path    => $path,
+        title   => $safe_title, 
+        snippet => $snippet 
+    };
 }
 
 print "Content-Type: text/html\n\n";
@@ -97,6 +76,7 @@ if ($search_text eq '') {
 }
 
 my $safe_search_text = escape_html($search_text);
+my $year = (localtime)[5] + 1900;
 
 print <<"HTML";
 <!DOCTYPE html>
@@ -132,7 +112,7 @@ print <<"HTML";
     <div class="footer">
         <div class="container">
             <div class="twelve columns right container-2">
-                <p id="footer-text">&copy; ASCIIMX - 2025</p>
+                <p id="footer-text">&copy; ASCIIMX - $year</p>
             </div>
         </div>
     </div>
diff --git a/cgi-bin/find.cgi b/cgi-bin/find.cgi
index f3f68f5..f0d2b3c 100644
--- a/cgi-bin/find.cgi
+++ b/cgi-bin/find.cgi
@@ -1,8 +1,6 @@
 #!/usr/bin/perl
 
 use Encode qw(decode_utf8);
-
-use File::Find;
 use HTML::Escape qw(escape_html);
 
 my $search_text = '';
@@ -11,60 +9,54 @@ if ($ENV{QUERY_STRING} =~ /^q=([^&]*)/) {
     $search_text = decode_utf8($1 // "");
     $search_text =~ s/\P{Print}//g;  # toss any non-printable utf-8 characters
     $search_text = substr($search_text, 0, 64);
+    $search_text =~ s/^\s+|\s+$//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);
+# Search only index.html files inside the first level of subdirectories
+my $start_dir = '../log'; 
+my @files = glob("$start_dir/*/index.html");
+
+foreach my $path (@files) {
+    # Skip if the path is a symlink or not a file
+    next if -l $path || ! -f $path;
+
+    next unless open(my $fh, '<:utf8', $path);
+    my $html = do { local $/; <$fh> };
+    close($fh);
+  
+    my ($text) = $html =~ m|<main>(.*?)</main>|is;
+    $text =~ s|<[^>]+>| |g;
+    $text =~ s|\s+| |g;
+
+    next unless $text =~ /(.{0,40})(\Q$search_text\E)(.{0,40})/is;
+    my ($before, $actual, $after) = ($1, $2, $3);
+
+    # Trim if we cut into the middle of a sentence
+    $after =~ s/\s\S*$// if length($after) > 25;
+    $before =~ s/^.*?\s// if length($before) > 25;
+
+    if ($before =~ /\S/) { # If before has non-whitespace characters
+        $before = ucfirst($before);
+    } else {
+        $before = "";      # Clear any stray spaces
+        $actual = ucfirst($actual);
+    }
+
+    my $safe_before = escape_html($before);
+    my $safe_actual = escape_html($actual);
+    my $safe_after  = escape_html($after);
+    my $snippet = "${safe_before}<b>${safe_actual}</b>${safe_after}...";
+
+    my ($title) = $html =~ m|<title>(.*?)</title>|is;
+    my $safe_title  = escape_html($title);
+
+    push @results, { 
+        path    => $path,
+        title   => $safe_title, 
+        snippet => $snippet 
+    };
 }
 
 print "Content-Type: text/html\n\n";