Replaced SA search with Regex search.

1 files changed, 207 insertions, 0 deletions

diff --git a/cgi-bin/search.cgi b/cgi-bin/search.cgi
new file mode 100644
index 0000000..67815c8
--- /dev/null
+++ b/cgi-bin/search.cgi
@@ -0,0 +1,207 @@
+#!/usr/bin/perl
+
+use strict;
+use warnings;
+use File::Spec;
+use Encode qw(decode_utf8);
+use URI::Escape qw(uri_unescape);
+use HTML::Escape qw(escape_html);
+
+binmode(STDOUT, ":utf8");
+
+# --- Configuration ---
+my $max_parallel   = 50;
+my $lock_timeout    = 30;
+my $max_results     = 20;
+my $lock_dir        = '/tmp/search_locks';
+my $directory       = '../log/';
+
+# --- Concurrency Control ---
+mkdir $lock_dir, 0777 unless -d $lock_dir;
+my $active_count = 0;
+my $now = time();
+
+opendir(my $dh_lock, $lock_dir);
+while (my $file = readdir($dh_lock)) {
+	next unless $file =~ /\.lock$/;
+	my $path = "$lock_dir/$file";
+	my $mtime = (stat($path))[9] || 0;
+	($now - $mtime > $lock_timeout) ? unlink($path) : $active_count++;
+}
+closedir($dh_lock);
+
+if ($active_count >= $max_parallel) {
+    render_html("<p>Server busy. Please try again in a few seconds.</p>", "");
+    exit;
+}
+
+my $lock_file = "$lock_dir/$$.lock";
+open(my $fh_lock, '>', $lock_file) or die "Cannot create lock: $!";
+
+# --- Query Decoding ---
+my $search_text = '';
+if (($ENV{QUERY_STRING} || '') =~ /^q=([^&]*)/) {
+	my $raw_q = $1;
+	$raw_q =~ tr/+/ /;
+	$search_text = uri_unescape($raw_q);
+	$search_text = decode_utf8($search_text // "");
+	$search_text =~ s/\P{Print}//g; 
+	$search_text = substr($search_text, 0, 64);
+	$search_text =~ s/^\s+|\s+$//g;
+}
+
+if ($search_text eq '') {
+    final_output("<p>Please enter a search term above.</p>");
+}
+
+# --- Search ---
+my @results;
+my $files_read = 0;
+
+if ($search_text =~ /\S/) {
+	my @stack = ($directory);
+
+	while (@stack) {
+		# Exit search immediately if limit reached
+		last if scalar @results >= $max_results;
+
+		my $current_path = pop @stack;
+
+		if (-d $current_path) {
+			if (opendir(my $dh, $current_path)) {
+				while (my $entry = readdir($dh)) {
+					next if $entry =~ /^\.\.?$/;
+					push @stack, File::Spec->catfile($current_path, $entry);
+				}
+				closedir($dh);
+			}
+		}
+		elsif (-f $current_path && $current_path =~ /index\.html$/) {
+			if (open my $fh, '<:utf8', $current_path) {
+				$files_read++;
+				my $raw_content = do { local $/; <$fh> };
+				close $fh;
+
+				my ($article) = $raw_content =~ /<article[^>]*>(.*?)<\/article>/is;
+				$article =~ s/<pre.*?>.*?<\/pre>//isg;
+				$article =~ s/<code.*?>.*?<\/code>//isg;
+				next unless $article;
+
+				# Clean for accurate regex offsets
+				my $clean_text = $article;
+				$clean_text =~ s/<[^>]*>/ /g; # Tags to space to prevent word mashing
+				$clean_text =~ s/\s+/ /g;
+				$clean_text =~ s/^\s+|\s+$//g;
+
+				if ($clean_text =~ /(\Q$search_text\E)/i) {
+					my $match_pos = "$-[0]";
+					my $match_end = "$+[0]";
+
+					# Grab a context window (120 chars padding)
+					my $grab_start = ($match_pos > 120) ? $match_pos - 120 : 0;
+					my $grab_len   = ($match_end - $grab_start) + 120;
+					my $raw_chunk  = substr($clean_text, $grab_start, $grab_len);
+					
+					my $is_start = ($grab_start == 0);
+					my $is_end   = ($grab_start + $grab_len >= length($clean_text));
+
+					my $snippet = trim_and_clean_snippet($raw_chunk, $is_start, $is_end);
+
+					my ($title) = $raw_content =~ /<title>(.*?)<\/title>/is;
+					push @results, { 
+						path    => $current_path,
+						title   => $title || $current_path, 
+						snippet => $snippet
+					};
+				}
+			}
+		}
+	}
+}
+
+my $safe_search_text = escape_html($search_text);
+
+my $list_html = "";
+if (@results == 0) {
+    $list_html = "<p>No results found for \"<b>$safe_search_text</b>\".</p>";
+} else {
+    $list_html = "<ul>" . join('', map { 
+        "<li><a href=\"/$_->{path}\">$_->{title}</a><br><small>$_->{snippet}</small></li>" 
+    } @results) . "</ul>";
+}
+
+final_output($list_html);
+
+sub final_output {
+    my ($content) = @_;
+    render_html($content, $safe_search_text);
+    if ($fh_lock) { close($fh_lock); unlink($lock_file); }
+    exit;
+}
+
+sub trim_and_clean_snippet {
+	my ($raw_chunk, $is_start, $is_end) = @_;
+
+	# Start check:
+	# If we aren't at the very start of the article, we likely have a leading fragment.
+	# We search for the first space to drop the partial word.
+	if (!$is_start) {
+		$raw_chunk =~ s/^[^\s]*\s//;
+	}
+
+	# Length and end Check:
+	my $show_ellipsis = !$is_end;
+
+	if (length($raw_chunk) > 160) {
+		$raw_chunk = substr($raw_chunk, 0, 160);
+		
+		# Look for the last space within our 160 chars to avoid cutting a word in half.
+		# If we find a space and trim, we add the ellipsis.
+		if ($raw_chunk =~ s/\s+[^\s]*$//) {
+			$show_ellipsis = 1;
+		}
+	}
+
+	# Sometimes leading punctuation or weird fragments remain after the trim.
+	$raw_chunk =~ s/^[:;,.?!\s]+//; # Remove leading punctuation/space
+	
+	# Final polish
+	$raw_chunk = ucfirst($raw_chunk);
+	
+	# Ensure it ends cleanly: if it doesn't end in terminal punctuation, add ellipsis
+	my $final_text = escape_html($raw_chunk);
+	if ($show_ellipsis && $raw_chunk !~ /[.!?]$/) {
+		$final_text .= "...";
+	}
+
+	return $final_text;
+}
+
+sub render_html {
+    my ($content, $q_val) = @_;
+	print "Content-Type: text/html; charset=UTF-8\n\n";
+    print <<"HTML";
+<!DOCTYPE html>
+<html lang="en-us">
+<head>
+    <meta charset="utf-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <title>Journal | Search</title>
+    <link rel="stylesheet" href="/assets/css/main.css">
+</head>
+<body>
+    <header>
+        <h1><a href="/">Journal</a></h1> / 
+        <h1><a href="/cgi-bin/search.cgi">Search</a></h1>
+    </header>
+    <article>
+        <form id="search-bar" action="" method="GET">
+            <input id="search-box" type="text" name="q" value="$q_val">
+            <input id="search-btn" type="submit" value="Search">
+        </form>
+        $content
+    </article>
+</body>
+</html>
+HTML
+}