Remove 'log' from navlink, update cu response, change to lup.

5 files changed, 368 insertions, 0 deletions

diff --git a/cgi-bin/_site/feed.xml b/cgi-bin/_site/feed.xml
new file mode 100644
index 0000000..66f8d32
--- /dev/null
+++ b/cgi-bin/_site/feed.xml
@@ -0,0 +1 @@
+<?xml version="1.0" encoding="utf-8"?><feed xmlns="http://www.w3.org/2005/Atom" ><generator uri="https://jekyllrb.com/" version="4.4.1">Jekyll</generator><link href="http://localhost:4000/feed.xml" rel="self" type="application/atom+xml" /><link href="http://localhost:4000/" rel="alternate" type="text/html" /><updated>2026-01-03T14:43:24+08:00</updated><id>http://localhost:4000/feed.xml</id></feed>
\ No newline at end of file
diff --git a/cgi-bin/_site/find.cgi b/cgi-bin/_site/find.cgi
new file mode 100644
index 0000000..ab066dd
--- /dev/null
+++ b/cgi-bin/_site/find.cgi
@@ -0,0 +1,247 @@
+#!/usr/bin/perl
+
+use strict;
+use warnings;
+use Storable qw(retrieve);
+use Encode qw(decode_utf8 encode_utf8);
+use URI::Escape qw(uri_unescape);
+use HTML::Escape qw(escape_html);
+
+# Configuration
+my $max_parallel   = 50;                    # Max parallel search requests
+my $lock_timeout   = 30;                    # Seconds before dropping stale locks
+my $max_results    = 20;                    # Max search results to display
+my $sa_file        = 'sa.bin';              # Suffix Array index
+my $cp_file        = 'corpus.bin';          # Raw text corpus
+my $map_file       = 'file_map.dat';        # File metadata
+my $lock_dir       = '/tmp/search_locks';   # Semaphore directory
+
+# Concurrency control
+mkdir $lock_dir, 0777 unless -d $lock_dir;
+my $active_count = 0;
+my $now = time();
+
+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);
+
+# Template variables
+my $year = (localtime)[5] + 1900;
+my $search_text = '';
+
+# Busy check
+if ($active_count >= $max_parallel) {
+    print "Content-Type: text/html\n\n";
+    render_html("<p>Server busy. Please try again in a few seconds.</p>", "", $year);
+    exit;
+}
+
+# Create semaphore lock
+my $lock_file = "$lock_dir/$$.lock";
+open(my $fh_lock, '>', $lock_file);
+
+# Query decoding
+if (($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;
+}
+
+my $safe_search_text = escape_html($search_text);
+
+print "Content-Type: text/html\n\n";
+
+if ($search_text eq '') {
+    final_output("<p>Please enter a search term above.</p>");
+}
+
+# Binary search 
+my @results;
+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 = $mid + 1;
+        }
+    }
+
+    # Collect results if found
+    if ($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;
+            }
+        }
+
+        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}}++) {
+                        # Capture more than 50 chars for trimming
+                        my $snip_start = ($offset - 30 < $m->{start}) ? $m->{start} : $offset - 30;
+                        my $max_len = $m->{end} - $snip_start;
+                        my $read_len = ($max_len > 120) ? 120 : $max_len;
+                        seek($fh_cp, $snip_start, 0);
+                        read($fh_cp, my $raw_snip, $read_len);
+                        
+                        my $snippet = decode_utf8($raw_snip, Encode::FB_QUIET) // $raw_snip;
+                        $snippet =~ s/\s+/ /g; # Normalize whitespace
+
+                        # Trim start: Partial word removal
+                        if ($snip_start > $m->{start}) {
+                            $snippet =~ s/^[^\s]*\s//; 
+                        }
+
+                        # Trim end: Length limit and partial word removal
+                        my $has_more = 0;
+                        if (length($snippet) > 50) {
+                            $snippet = substr($snippet, 0, 50);
+                            $has_more = 1 if $snippet =~ s/\s+[^\s]*$//;
+                        }
+                        elsif ($snip_start + $read_len < $m->{end}) {
+                            # This check handles snippets that are naturally short but 
+                            # there's still more text in the article we didn't read
+                            $has_more = 1; 
+                        }
+
+                        # Cleanup & capitalize
+                        $snippet = ucfirst($snippet);
+                        $snippet = escape_html($snippet) . ($has_more ? "..." : "");
+
+                        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);
+}
+
+# --- Formatting & Output ---
+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($list_html);
+
+# --- Helpers ---
+sub final_output {
+    my ($content) = @_;
+    render_html($content, $safe_search_text, $year);
+    if ($fh_lock) { close($fh_lock); unlink($lock_file); }
+    exit;
+}
+
+sub render_html {
+    my ($content, $q_val, $yr) = @_;
+    print <<"HTML";
+<!DOCTYPE html>
+<html lang="en-us">
+<head>
+    <meta charset="utf-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <title>Search</title>
+    <link rel="stylesheet" href="/assets/css/main.css">
+    <link rel="stylesheet" href="/assets/css/skeleton.css">
+</head>
+<body>
+    <div id="nav-container" class="container">
+        <ul id="navlist" class="left">
+            <li><a href="/" class="link-decor-none">hme</a></li>
+            <li><a href="/log/" class="link-decor-none">log</a></li>
+            <li><a href="/projects/" class="link-decor-none">poc</a></li>
+            <li><a href="/about/" class="link-decor-none">abt</a></li>
+            <li class="active"><a href="/cgi-bin/find.cgi" class="link-decor-none">sws</a></li>
+            <li><a href="/feed.xml" class="link-decor-none">rss</a></li>
+        </ul>
+    </div>
+    <main class="container" id="main">
+        <div class="container">
+            <h2>Search</h2>
+            <form action="" method="GET">
+                <input id="search-box" type="text" name="q" value="$q_val">
+                <input id="search-btn" type="submit" value="Search">
+            </form>
+            $content
+        </div>
+    </main>
+    <div class="footer">
+        <div class="container">
+            <div class="twelve columns right container-2">
+                <p id="footer-text">&copy; ASCIIMX - $yr</p>
+            </div>
+        </div>
+    </div>
+</body>
+</html>
+HTML
+}
+
diff --git a/cgi-bin/_site/indexer.pl b/cgi-bin/_site/indexer.pl
new file mode 100644
index 0000000..69f6838
--- /dev/null
+++ b/cgi-bin/_site/indexer.pl
@@ -0,0 +1,116 @@
+#!/usr/bin/perl
+
+use strict;
+use warnings;
+use File::Find;
+use Storable qw(store);
+use Encode qw(encode_utf8);
+use HTML::Entities qw(decode_entities);
+use Time::HiRes qw(gettimeofday tv_interval);
+
+my $dir         = '../_site/log';
+my $cgi_dir     = '../_site/cgi-bin/';
+my $corpus_file = "${cgi_dir}corpus.bin";
+my $sa_file     = "${cgi_dir}sa.bin";
+my $map_file    = "${cgi_dir}file_map.dat";
+
+my %excluded_files = (
+    'index.html'  => 1, # /log/index.html
+);
+
+# Start timing
+my $t0 = [gettimeofday];
+
+my $corpus = "";
+my @file_map;
+
+print "Building corpus...\n";
+
+find({
+    wanted => sub {
+        # Only index index.html files
+        return unless -f $_ && $_ eq 'index.html';
+
+        my $rel_path = $File::Find::name;
+        $rel_path =~ s|^\Q$dir\E/?||; 
+        return if $excluded_files{$rel_path};
+        
+        if (open my $fh, '<:encoding(UTF-8)', $_) {
+            my $content = do { local $/; <$fh> };
+            close $fh;
+
+            my ($title) = $content =~ m|<title>(.*?)</title>|is;
+            $title //= (split('/', $File::Find::name))[-2]; # Fallback to folder name
+            $title =~ s/^\s+|\s+$//g;
+
+            # Extract content from <main> or use whole file
+            my ($text) = $content =~ m|<main>(.*?)</main>|is;
+            $text //= $content; 
+
+            # Strip tags and normalize whitespace
+            $text =~ s|<pre[^>]*>.*?</pre>| |gs;
+            $text =~ s|<code[^>]*>.*?</code>| |gs;
+            $text =~ s|<[^>]+>| |g;
+            $text = decode_entities($text);
+            $text =~ s|\s+| |g;
+            $text =~ s/^\s+|\s+$//g;
+
+            # CRITICAL: Convert to lowercase and then to raw bytes
+            # This ensures length() and substr() work on byte offsets for seek()
+            my $raw_entry = encode_utf8(lc($text) . "\0");
+
+            my $start = length($corpus);
+            $corpus .= $raw_entry;
+            
+            push @file_map, { 
+                start => $start, 
+                end   => length($corpus), 
+                title => $title, 
+                path  => $File::Find::name 
+            };
+        }
+    },
+    no_chdir => 0,
+}, $dir);
+
+print "Sorting suffixes...\n";
+
+# Initialize the array of indices
+my @sa = 0 .. (length($corpus) - 1);
+
+# Use a block that forces byte-level comparison
+{
+    use bytes; 
+    @sa = sort { 
+        # First 64 bytes check (fast path)
+        (substr($corpus, $a, 64) cmp substr($corpus, $b, 64)) || 
+        # Full string fallback (required for correctness)
+        (substr($corpus, $a) cmp substr($corpus, $b))
+    } @sa;
+}
+
+print "Writing index files to disk...\n";
+
+open my $cfh, '>', $corpus_file or die "Cannot write $corpus_file: $!";
+binmode($cfh); # Raw byte mode
+print $cfh $corpus;
+close $cfh;
+
+open my $sfh, '>', $sa_file or die "Cannot write $sa_file: $!";
+binmode($sfh);
+# Pack as 32-bit unsigned integers (standard 'L')
+print $sfh pack("L*", @sa);
+close $sfh;
+
+store \@file_map, $map_file;
+
+my $elapsed = tv_interval($t0);
+my $c_size = -s $corpus_file;
+my $s_size = -s $sa_file;
+
+printf "\nIndexing Complete!\n";
+printf "Total Time:      %.4f seconds\n", $elapsed;
+printf "Corpus Size:     %.2f KB\n", $c_size / 1024;
+printf "Suffix Array:    %.2f KB\n", $s_size / 1024;
+printf "Files Processed: %d\n", scalar(@file_map);
+
diff --git a/cgi-bin/_site/robots.txt b/cgi-bin/_site/robots.txt
new file mode 100644
index 0000000..d297064
--- /dev/null
+++ b/cgi-bin/_site/robots.txt
@@ -0,0 +1 @@
+Sitemap: http://localhost:4000/sitemap.xml
diff --git a/cgi-bin/_site/sitemap.xml b/cgi-bin/_site/sitemap.xml
new file mode 100644
index 0000000..9bf9de2
--- /dev/null
+++ b/cgi-bin/_site/sitemap.xml
@@ -0,0 +1,3 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.sitemaps.org/schemas/sitemap/0.9 http://www.sitemaps.org/schemas/sitemap/0.9/sitemap.xsd" xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
+</urlset>