Deployment script and replace regex search with SA search.

1 files changed, 163 insertions, 125 deletions

diff --git a/cgi-bin/search.cgi b/cgi-bin/search.cgi
index 67815c8..c5ea024 100644
--- a/cgi-bin/search.cgi
+++ b/cgi-bin/search.cgi
@@ -2,43 +2,47 @@
 
 use strict;
 use warnings;
-use File::Spec;
-use Encode qw(decode_utf8);
+use Storable qw(retrieve);
+use Encode qw(decode_utf8 encode_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 $sa_file         = 'sa.bin';
+my $cp_file         = 'corpus.bin';
+my $map_file        = 'file_map.dat';
 my $lock_dir        = '/tmp/search_locks';
-my $directory       = '../log/';
 
-# --- Concurrency Control ---
+binmode(STDOUT, ":utf8");
+
+# --- 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)) {
+opendir(my $dh, $lock_dir);
+while (my $file = readdir($dh)) {
 	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);
+closedir($dh);
 
+my $lock_file = "$lock_dir/$$.lock";
+my $fh_lock;
+
+# Busy check
 if ($active_count >= $max_parallel) {
-    render_html("<p>Server busy. Please try again in a few seconds.</p>", "");
-    exit;
+	render_html("<p>Server busy. Please try again in a few seconds.</p>", "");
 }
 
-my $lock_file = "$lock_dir/$$.lock";
-open(my $fh_lock, '>', $lock_file) or die "Cannot create lock: $!";
+# Create semaphore lock
+open($fh_lock, '>', $lock_file) or die "Cannot create lock: $!";
 
-# --- Query Decoding ---
 my $search_text = '';
 if (($ENV{QUERY_STRING} || '') =~ /^q=([^&]*)/) {
 	my $raw_q = $1;
@@ -50,158 +54,192 @@ if (($ENV{QUERY_STRING} || '') =~ /^q=([^&]*)/) {
 	$search_text =~ s/^\s+|\s+$//g;
 }
 
+my $safe_search_text = escape_html($search_text);
+
 if ($search_text eq '') {
-    final_output("<p>Please enter a search term above.</p>");
+	render_html("<p>Please enter a search term above.</p>", "");
 }
 
-# --- Search ---
+# --- Suffix array binary 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;
+my $query = encode_utf8(lc($search_text));
+my $query_len = length($query);
+
+if (-f $sa_file && -f $cp_file) {
+	open(my $fh_sa, '<', $sa_file) or die $!;
+	open(my $fh_cp, '<', $cp_file) or die $!;
+	binmode($fh_sa);
+	binmode($fh_cp);
+
+	my $file_map = retrieve($map_file);
+	my $total_suffixes = (-s $sa_file) / 4;
+
+	# Find left boundary
+	my ($low, $high) = (0, $total_suffixes - 1);
+	my $first_hit = -1;
+
+	while ($low <= $high) {
+		my $mid = int(($low + $high) / 2);
+		seek($fh_sa, $mid * 4, 0);
+		read($fh_sa, my $bin_off, 4);
+		my $off = unpack("L", $bin_off);
+		seek($fh_cp, $off, 0);
+		read($fh_cp, my $text, $query_len);
+		
+		my $cmp = $text cmp $query;
+		if ($cmp >= 0) {
+			$first_hit = $mid if $cmp == 0;
+			$high = $mid - 1;
+		} else {
+			$low = $mid + 1;
+		}
+	}
 
-		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);
+	# Collect results
+	if ($first_hit != -1) {
+		my $last_hit = $first_hit;
+		($low, $high) = ($first_hit, $total_suffixes - 1);
+		
+		# Find right boundary
+		while ($low <= $high) {
+			my $mid = int(($low + $high) / 2);
+			seek($fh_sa, $mid * 4, 0);
+			read($fh_sa, my $bin_off, 4);
+			my $off = unpack("L", $bin_off);
+			seek($fh_cp, $off, 0);
+			read($fh_cp, my $text, $query_len);
+			
+			if (($text cmp $query) <= 0) {
+				$last_hit = $mid if $text eq $query;
+				$low = $mid + 1;
+			} else {
+				$high = $mid - 1;
 			}
 		}
-		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 %seen;
+		for my $i ($first_hit .. $last_hit) {
+			seek($fh_sa, $i * 4, 0);
+			read($fh_sa, my $bin_off, 4);
+			my $offset = unpack("L", $bin_off);
+
+			foreach my $m (@$file_map) {
+				if ($offset >= $m->{start} && $offset < $m->{end}) {
+					if (!$seen{$m->{path}}++) {
+						# Grab context window around the match byte offset
+						my $grab_start = ($offset > 150) ? $offset - 150 : $m->{start};
+						if ($grab_start < $m->{start}) { $grab_start = $m->{start}; }
+						
+						my $grab_len = ($offset - $grab_start) + 300; 
+						if ($grab_start + $grab_len > $m->{end}) {
+							$grab_len = $m->{end} - $grab_start;
+						}
+
+						seek($fh_cp, $grab_start, 0);
+						read($fh_cp, my $raw_chunk, $grab_len);
+						
+						my $is_start = ($grab_start == $m->{start});
+						my $is_end   = ($grab_start + $grab_len >= $m->{end});
+
+						my $snippet = trim_and_clean_snippet($raw_chunk, $is_start, $is_end);
+
+						my $clean_path = $m->{path};
+						$clean_path =~ s|^\.\./_site/||;
+
+						push @results, {
+							path    => $clean_path,
+							title   => $m->{title},
+							snippet => $snippet
+						};
+					}
+					last;
 				}
 			}
+			last if scalar @results >= $max_results;
 		}
 	}
+	close($fh_sa);
+	close($fh_cp);
 }
 
-my $safe_search_text = escape_html($search_text);
-
+# Prepare output
 my $list_html = "";
 if (@results == 0) {
-    $list_html = "<p>No results found for \"<b>$safe_search_text</b>\".</p>";
+	$list_html = "<p>No results found for \"<b>$safe_search_text</b>\".</p>";
 } else {
-    $list_html = "<ul>" . join('', map { 
-        "<li><a href=\"/$_->{path}\">$_->{title}</a><br><small>$_->{snippet}</small></li>" 
-    } @results) . "</ul>";
+	$list_html = "<ul>" . join('', map { 
+		"<li><a href=\"/$_->{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;
-}
+render_html($list_html, $safe_search_text);
 
 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.
+	# Decode and normalize
+	my $text = decode_utf8($raw_chunk, Encode::FB_QUIET) // $raw_chunk;
+	$text =~ s/\s+/ /g;
+	$text =~ s/^\s+|\s+$//g;
+
+	# Front-end trim: remove partial leading word
 	if (!$is_start) {
-		$raw_chunk =~ s/^[^\s]*\s//;
+		$text =~ s/^[^\s]*\s//;
 	}
 
-	# Length and end Check:
+	# Length control: target ~160 characters
 	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 ($raw_chunk =~ s/\s+[^\s]*$//) {
+	if (length($text) > 160) {
+		$text = substr($text, 0, 160);
+		if ($text =~ s/\s+[^\s]*$//) {
 			$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 .= "...";
-	}
+	# Clean leading punctuation, then capitalize
+	$text =~ s/^[:;,.?!\s]+//;
+	$text = ucfirst($text);
 
-	return $final_text;
+	my $html = escape_html($text);
+	if ($show_ellipsis && $text !~ /[.!?]$/) {
+		$html .= "...";
+	}
+	return $html;
 }
 
 sub render_html {
-    my ($content, $q_val) = @_;
+	my ($content, $q_val) = @_;
+
 	print "Content-Type: text/html; charset=UTF-8\n\n";
-    print <<"HTML";
+	print <<"HTML";
 <!DOCTYPE html>
 <html lang="en-us">
 <head>
-    <meta charset="utf-8">
-    <meta name="viewport" content="width=device-width, initial-scale=1">
-    <title>Journal | Search</title>
-    <link rel="stylesheet" href="/assets/css/main.css">
+	<meta charset="utf-8">
+	<meta name="viewport" content="width=device-width, initial-scale=1">
+	<title>Journal | Search</title>
+	<link rel="stylesheet" href="/assets/css/main.css">
 </head>
 <body>
-    <header>
-        <h1><a href="/">Journal</a></h1> / 
-        <h1><a href="/cgi-bin/search.cgi">Search</a></h1>
-    </header>
-    <article>
-        <form id="search-bar" action="" method="GET">
-            <input id="search-box" type="text" name="q" value="$q_val">
-            <input id="search-btn" type="submit" value="Search">
-        </form>
-        $content
-    </article>
+	<header>
+		<h1><a href="/">Journal</a></h1> / 
+		<h1><a href="/cgi-bin/search.cgi">Search</a></h1>
+	</header>
+	<article>
+		<form id="search-bar" action="" method="GET">
+			<input id="search-box" type="text" name="q" value="$q_val">
+			<input id="search-btn" type="submit" value="Search">
+		</form>
+		$content
+	</article>
 </body>
 </html>
 HTML
+
+	# Final cleanup and exit
+	if (defined $fh_lock) { 
+		close($fh_lock); 
+		unlink($lock_file) if -e $lock_file; 
+	}
+	exit;
 }