ASCIIMX | Log

Log

Search

+ + $content +

or use whole file + my ($text) = $content =~ m|

(.*?)

|is; + $text //= $content; + + # Strip tags and normalize whitespace + $text =~ s|]*>.*?| |gs; + $text =~ s|]*>.*?| |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 @@ + + + diff --git a/cgi-bin/find.cgi b/cgi-bin/find.cgi index ab066dd..d3c6cc4 100644 --- a/cgi-bin/find.cgi +++ b/cgi-bin/find.cgi @@ -216,10 +216,9 @@ sub render_html {

diff --git a/index.html b/index.html index 26da2fd..7d871bc 100644 --- a/index.html +++ b/index.html @@ -10,13 +10,13 @@ title: ASCIIMX $ cu -l /dev/asciimx

- NMI_LNK: SIG_ASSERT [0x53] + UNIX / EMBED / -O3

- {% include latest.html limit="10" %} + {% include latest.html limit="50" %} diff --git a/log.html b/log.html deleted file mode 100644 index 084173a..0000000 --- a/log.html +++ /dev/null @@ -1,13 +0,0 @@ ---- -title: Log -layout: default ---- - - -

- -

Log

- - {% include latest.html limit="50" %} - -

-- cgit v1.2.3

- Site search with Perl + CGI + SA -	- - 2026-01-02 - -
- Matrix Rain: 2025 refactor -	- - 2025-12-21 - -
- Fingerprint door lock (LP) -	- - 2025-08-18 - -
- High-side MOSFET switching -	- - 2025-06-22 - -
- ATmega328P at 3.3V and 5V -	- - 2025-06-10 - -
- Fingerprint door lock (RF) -	- - 2025-06-05 - -
- Bumblebee: browser automation -	- - 2025-04-02 - -
- Bare-metal ATSAM3X8E -	- - 2024-09-16 - -
- Etlas: e-paper dashboard -	- - 2024-09-05 - -
- ESP32 e-reader prototype -	- - 2023-10-24 - -
- Neo4j shortest path optimization -	- - 2018-03-06 - -