#!/usr/bin/perl -T use warnings; use strict; use File::Find; use Memoize; use File::Spec; BEGIN { $blosxom::version="is a proper perl module too much to ask?"; do "/usr/bin/markdown"; } memoize('pagename'); memoize('bestlink'); my ($srcdir)= shift =~ /(.*)/; # untaint my ($destdir)= shift =~ /(.*)/; # untaint my $link=qr/\[\[([^\s]+)\]\]/; my $verbose=1; my $wikiname="wiki"; my %links; my %oldpagemtime; my %renderedfiles; sub error ($) { die @_; } sub debug ($) { print "@_\n" if $verbose; } sub mtime ($) { my $page=shift; return (stat($page))[9]; } sub basename { my $file=shift; $file=~s!.*/!!; return $file; } sub dirname { my $file=shift; $file=~s!/?[^/]+$!!; return $file; } sub pagetype ($) { my $page=shift; if ($page =~ /\.mdwn$/) { return ".mdwn"; } else { return "unknown"; } } sub pagename ($) { my $file=shift; my $type=pagetype($file); my $page=$file; $page=~s/\Q$type\E*$// unless $type eq 'unknown'; return $page; } sub htmlpage ($) { my $page=shift; return $page.".html"; } sub readpage ($) { my $page=shift; local $/=undef; open (PAGE, "$srcdir/$page") || error("failed to read $page: $!"); my $ret=; close PAGE; return $ret; } sub writepage ($$) { my $page=shift; my $content=shift; my $dir=dirname("$destdir/$page"); if (! -d $dir) { my $d=""; foreach my $s (split(m!/+!, $dir)) { $d.="$s/"; if (! -d $d) { mkdir($d) || error("failed to create directory $d: $!"); } } } open (PAGE, ">$destdir/$page") || error("failed to write $page: $!"); print PAGE $content; close PAGE; } sub findlinks { my $content=shift; my @links; while ($content =~ /$link/g) { push @links, lc($1); } return @links; } # Given a page and the text of a link on the page, determine which existing # page that link best points to. Prefers pages under a subdirectory with # the same name as the source page, failing that goes down the directory tree # to the base looking for matching pages. sub bestlink ($$) { my $page=shift; my $link=lc(shift); my $cwd=$page; do { my $l=$cwd; $l.="/" if length $l; $l.=$link; if (exists $links{$l}) { #debug("for $page, \"$link\", use $l"); return $l; } } while $cwd=~s!/?[^/]+$!!; print STDERR "warning: page $page, broken link: $link\n"; return ""; } sub isinlinableimage ($) { my $file=shift; $file=~/\.(png|gif|jpg|jpeg)$/; } sub htmllink ($$) { my $page=shift; my $link=shift; my $bestlink=bestlink($page, $link); return $link if $page eq $bestlink; if (! grep { $_ eq $bestlink } values %renderedfiles) { $bestlink=htmlpage($bestlink); } if (! grep { $_ eq $bestlink } values %renderedfiles) { return "?$link" } $bestlink=File::Spec->abs2rel($bestlink, dirname($page)); if (isinlinableimage($bestlink)) { return "

"; } return "$link"; } sub linkify ($$) { my $content=shift; my $file=shift; $content =~ s/$link/htmllink(pagename($file), $1)/eg; return $content; } sub htmlize ($$) { my $type=shift; my $content=shift; if ($type eq '.mdwn') { return Markdown::Markdown($content); } else { error("htmlization of $type not supported"); } } sub finalize ($$) { my $content=shift; my $page=shift; my $title=basename($page); $title=~s/_/ /g; my $pagelink=""; my $path=""; foreach my $dir (reverse split("/", $page)) { if (length($pagelink)) { $pagelink="$dir/ $pagelink"; } else { $pagelink=$dir; } $path.="../"; } $path=~s/\.\.\/$/index.html/; $pagelink="$wikiname/ $pagelink"; $content="\n$title\n\n". "

$pagelink

\n". $content. "\n\n"; return $content; } sub render ($) { my $file=shift; my $type=pagetype($file); my $content=readpage($file); if ($type ne 'unknown') { my $page=pagename($file); $links{$page}=[findlinks($content)]; $content=linkify($content, $file); $content=htmlize($type, $content); $content=finalize($content, $page); writepage(htmlpage($page), $content); $oldpagemtime{$page}=time; $renderedfiles{$page}=htmlpage($page); } else { $links{$file}=[]; writepage($file, $content); $oldpagemtime{$file}=time; $renderedfiles{$file}=$file; } } sub loadindex () { open (IN, "$srcdir/.index") || return; while () { chomp; my ($mtime, $page, $rendered, @links)=split(' ', $_); $oldpagemtime{$page}=$mtime; $links{$page}=\@links; ($renderedfiles{$page})=$rendered=~m/(.*)/; # untaint } close IN; } sub saveindex () { open (OUT, ">$srcdir/.index") || error("cannot write to .index: $!"); foreach my $page (keys %oldpagemtime) { print OUT "$oldpagemtime{$page} $page $renderedfiles{$page} ". join(" ", @{$links{$page}})."\n" if $oldpagemtime{$page}; } close OUT; } sub prune ($) { my $file=shift; unlink($file); my $dir=dirname($file); while (rmdir($dir)) { $dir=dirname($dir); } } sub refresh () { # Find existing pages. my %exists; my @files; find({ no_chdir => 1, wanted => sub { if (/\/\.svn\//) { $File::Find::prune=1; } elsif (! -d $_ && ! /\.html$/ && ! /\/\./) { my ($f)=/(^[-A-Za-z0-9_.:\/+]+$)/; # untaint if (! defined $f) { warn("skipping bad filename $_\n"); } else { $f=~s/^\Q$srcdir\E\/?//; push @files, $f; $exists{pagename($f)}=1; } } }, }, $srcdir); # check for added or removed pages my @adddel; foreach my $file (@files) { my $page=pagename($file); if (! $oldpagemtime{$page}) { debug("new page $page"); push @adddel, $page; $links{$page}=[]; } } foreach my $page (keys %oldpagemtime) { if (! $exists{$page}) { debug("removing old page $page"); prune($destdir."/".$renderedfiles{$page}); delete $renderedfiles{$page}; $oldpagemtime{$page}=0; push @adddel, $page; } } # render any updated files foreach my $file (@files) { my $page=pagename($file); if (! exists $oldpagemtime{$page} || mtime("$srcdir/$file") > $oldpagemtime{$page}) { debug("rendering changed file $file"); render($file); } } # if any files were added or removed, check to see if each page # needs an update due to linking to them if (@adddel) { FILE: foreach my $file (@files) { my $page=pagename($file); foreach my $p (@adddel) { foreach my $link (@{$links{$page}}) { if (bestlink($page, $link) eq $p) { debug("rendering $file, which links to $p"); render($file); next FILE; } } } } } } loadindex(); refresh(); saveindex();