use warnings;
use strict;
-use File::Spec;
use IkiWiki;
-
-sub linkify ($$) { #{{{
- my $content=shift;
- my $page=shift;
-
- $content =~ s{(\\?)$config{wiki_link_regexp}}{
- $2 ? ( $1 ? "[[$2|$3]]" : htmllink($page, titlepage($3), 0, 0, pagetitle($2)))
- : ( $1 ? "[[$3]]" : htmllink($page, titlepage($3)))
- }eg;
-
- return $content;
-} #}}}
-
-my $_scrubber;
-sub scrubber { #{{{
- return $_scrubber if defined $_scrubber;
-
- eval q{use HTML::Scrubber};
- # Lists based on http://feedparser.org/docs/html-sanitization.html
- $_scrubber = HTML::Scrubber->new(
- allow => [qw{
- a abbr acronym address area b big blockquote br
- button caption center cite code col colgroup dd del
- dfn dir div dl dt em fieldset font form h1 h2 h3 h4
- h5 h6 hr i img input ins kbd label legend li map
- menu ol optgroup option p pre q s samp select small
- span strike strong sub sup table tbody td textarea
- tfoot th thead tr tt u ul var
- }],
- default => [undef, { map { $_ => 1 } qw{
- abbr accept accept-charset accesskey action
- align alt axis border cellpadding cellspacing
- char charoff charset checked cite class
- clear cols colspan color compact coords
- datetime dir disabled enctype for frame
- headers height href hreflang hspace id ismap
- label lang longdesc maxlength media method
- multiple name nohref noshade nowrap prompt
- readonly rel rev rows rowspan rules scope
- selected shape size span src start summary
- tabindex target title type usemap valign
- value vspace width
- }}],
- );
- return $_scrubber;
-} # }}}
-
-sub htmlize ($$) { #{{{
- my $type=shift;
- my $content=shift;
-
- if (! $INC{"/usr/bin/markdown"}) {
- no warnings 'once';
- $blosxom::version="is a proper perl module too much to ask?";
- use warnings 'all';
- do "/usr/bin/markdown";
- }
-
- if ($type eq '.mdwn') {
- $content=Markdown::Markdown($content);
- }
- else {
- error("htmlization of $type not supported");
- }
-
- if ($config{sanitize}) {
- $content=scrubber()->scrub($content);
+use Encode;
+
+my %backlinks;
+my $backlinks_calculated=0;
+
+sub calculate_backlinks () { #{{{
+ return if $backlinks_calculated;
+ %backlinks=();
+ foreach my $page (keys %links) {
+ foreach my $link (@{$links{$page}}) {
+ my $bestlink=bestlink($page, $link);
+ if (length $bestlink && $bestlink ne $page) {
+ $backlinks{$bestlink}{$page}=1;
+ }
+ }
}
-
- return $content;
+ $backlinks_calculated=1;
} #}}}
sub backlinks ($) { #{{{
my $page=shift;
+ calculate_backlinks();
+
my @links;
- foreach my $p (keys %links) {
- next if bestlink($page, $p) eq $page;
- if (grep { length $_ && bestlink($p, $_) eq $page } @{$links{$p}}) {
- my $href=File::Spec->abs2rel(htmlpage($p), dirname($page));
-
- # Trim common dir prefixes from both pages.
- my $p_trimmed=$p;
- my $page_trimmed=$page;
- my $dir;
- 1 while (($dir)=$page_trimmed=~m!^([^/]+/)!) &&
- defined $dir &&
- $p_trimmed=~s/^\Q$dir\E// &&
- $page_trimmed=~s/^\Q$dir\E//;
-
- push @links, { url => $href, page => $p_trimmed };
- }
+ foreach my $p (keys %{$backlinks{$page}}) {
+ my $href=urlto($p, $page);
+
+ # Trim common dir prefixes from both pages.
+ my $p_trimmed=$p;
+ my $page_trimmed=$page;
+ my $dir;
+ 1 while (($dir)=$page_trimmed=~m!^([^/]+/)!) &&
+ defined $dir &&
+ $p_trimmed=~s/^\Q$dir\E// &&
+ $page_trimmed=~s/^\Q$dir\E//;
+
+ push @links, { url => $href, page => pagetitle($p_trimmed) };
}
-
- return sort { $a->{page} cmp $b->{page} } @links;
+ return @links;
} #}}}
sub parentlinks ($) { #{{{
my @ret;
my $pagelink="";
my $path="";
- my $skip=1;
- foreach my $dir (reverse split("/", $page)) {
- if (! $skip) {
- $path.="../";
- unshift @ret, { url => "$path$dir.html", page => $dir };
- }
- else {
- $skip=0;
- }
+ my $title=$config{wikiname};
+
+ return if $page eq 'index'; # toplevel
+ foreach my $dir (split("/", $page)) {
+ push @ret, { url => urlto($path, $page), page => $title };
+ $path.="/".$dir;
+ $title=pagetitle($dir);
}
- unshift @ret, { url => length $path ? $path : ".", page => $config{wikiname} };
return @ret;
} #}}}
-sub preprocess ($$) { #{{{
+sub genpage ($$$) { #{{{
my $page=shift;
my $content=shift;
+ my $mtime=shift;
- my $handle=sub {
- my $escape=shift;
- my $command=shift;
- my $params=shift;
- if (length $escape) {
- return "[[$command $params]]";
- }
- elsif (exists $plugins{preprocess}{$command}) {
- my %params;
- while ($params =~ /(\w+)=\"([^"]+)"(\s+|$)/g) {
- $params{$1}=$2;
- }
- return $plugins{preprocess}{$command}->(page => $page, %params);
+ my $templatefile;
+ run_hooks(templatefile => sub {
+ return if defined $templatefile;
+ my $file=shift->(page => $page);
+ if (defined $file && defined template_file($file)) {
+ $templatefile=$file;
}
- else {
- return "[[$command not processed]]";
- }
- };
-
- $content =~ s{(\\?)$config{wiki_processor_regexp}}{$handle->($1, $2, $3)}eg;
- return $content;
-} #}}}
+ });
+ my $template=template(defined $templatefile ? $templatefile : 'page.tmpl', blind_cache => 1);
+ my $actions=0;
-sub add_depends ($$) { #{{{
- my $page=shift;
- my $globlist=shift;
-
- if (! exists $depends{$page}) {
- $depends{$page}=$globlist;
- }
- else {
- $depends{$page}.=" ".$globlist;
- }
-} # }}}
-
-sub genpage ($$$) { #{{{
- my $content=shift;
- my $page=shift;
- my $mtime=shift;
-
- my $title=pagetitle(basename($page));
-
- my $template=HTML::Template->new(blind_cache => 1,
- filename => "$config{templatedir}/page.tmpl");
-
if (length $config{cgiurl}) {
- $template->param(editurl => cgiurl(do => "edit", page => $page));
+ $template->param(editurl => cgiurl(do => "edit", page => pagetitle($page, 1)));
$template->param(prefsurl => cgiurl(do => "prefs"));
if ($config{rcs}) {
$template->param(recentchangesurl => cgiurl(do => "recentchanges"));
}
+ $actions++;
}
if (length $config{historyurl}) {
my $u=$config{historyurl};
$u=~s/\[\[file\]\]/$pagesources{$page}/g;
$template->param(historyurl => $u);
+ $actions++;
+ }
+ if ($config{discussion}) {
+ my $discussionlink=gettext("discussion");
+ if ($page !~ /.*\/\Q$discussionlink\E$/ &&
+ (length $config{cgiurl} ||
+ exists $links{$page."/".$discussionlink})) {
+ $template->param(discussionlink => htmllink($page, $page, gettext("Discussion"), noimageinline => 1, forcesubpage => 1));
+ $actions++;
+ }
+ }
+
+ if ($actions) {
+ $template->param(have_actions => 1);
+ }
+
+ my @backlinks=sort { $a->{page} cmp $b->{page} } backlinks($page);
+ my ($backlinks, $more_backlinks);
+ if (@backlinks <= $config{numbacklinks} || ! $config{numbacklinks}) {
+ $backlinks=\@backlinks;
+ $more_backlinks=[];
}
- if ($config{hyperestraier}) {
- $template->param(hyperestraierurl => cgiurl());
+ else {
+ $backlinks=[@backlinks[0..$config{numbacklinks}-1]];
+ $more_backlinks=[@backlinks[$config{numbacklinks}..$#backlinks]];
}
$template->param(
- title => $title,
+ title => $page eq 'index'
+ ? $config{wikiname}
+ : pagetitle(basename($page)),
wikiname => $config{wikiname},
parentlinks => [parentlinks($page)],
content => $content,
- backlinks => [backlinks($page)],
- discussionlink => htmllink($page, "Discussion", 1, 1),
- mtime => scalar(gmtime($mtime)),
- styleurl => styleurl($page),
+ backlinks => $backlinks,
+ more_backlinks => $more_backlinks,
+ mtime => displaytime($mtime),
+ baseurl => baseurl($page),
);
-
- return $template->output;
-} #}}}
-sub check_overwrite ($$) { #{{{
- # Important security check. Make sure to call this before saving
- # any files to the source directory.
- my $dest=shift;
- my $src=shift;
+ run_hooks(pagetemplate => sub {
+ shift->(page => $page, destpage => $page, template => $template);
+ });
- if (! exists $renderedfiles{$src} && -e $dest && ! $config{rebuild}) {
- error("$dest already exists and was rendered from ".
- join(" ",(grep { $renderedfiles{$_} eq $dest } keys
- %renderedfiles)).
- ", before, so not rendering from $src");
- }
+ $content=$template->output;
+
+ run_hooks(format => sub {
+ $content=shift->(
+ page => $page,
+ content => $content,
+ );
+ });
+
+ return $content;
} #}}}
sub mtime ($) { #{{{
return (stat($file))[9];
} #}}}
-sub findlinks ($$) { #{{{
- my $content=shift;
- my $page=shift;
+sub scan ($) { #{{{
+ my $file=shift;
- my @links;
- while ($content =~ /(?<!\\)$config{wiki_link_regexp}/g) {
- push @links, titlepage($2);
+ my $type=pagetype($file);
+ if (defined $type) {
+ my $srcfile=srcfile($file);
+ my $content=readfile($srcfile);
+ my $page=pagename($file);
+ will_render($page, htmlpage($page), 1);
+
+ # Always needs to be done, since filters might add links
+ # to the content.
+ $content=filter($page, $page, $content);
+
+ my @links;
+ while ($content =~ /(?<!\\)$config{wiki_link_regexp}/g) {
+ push @links, linkpage($2);
+ }
+ if ($config{discussion}) {
+ # Discussion links are a special case since they're
+ # not in the text of the page, but on its template.
+ push @links, $page."/".gettext("discussion");
+ }
+ $links{$page}=\@links;
+
+ # Preprocess in scan-only mode.
+ preprocess($page, $page, $content, 1);
+ }
+ else {
+ will_render($file, $file, 1);
}
- # Discussion links are a special case since they're not in the text
- # of the page, but on its template.
- return @links, "$page/discussion";
} #}}}
sub render ($) { #{{{
my $type=pagetype($file);
my $srcfile=srcfile($file);
- if ($type ne 'unknown') {
- my $content=readfile($srcfile);
+ if (defined $type) {
my $page=pagename($file);
-
- $links{$page}=[findlinks($content, $page)];
delete $depends{$page};
+ will_render($page, htmlpage($page), 1);
- $content=linkify($content, $page);
- $content=preprocess($page, $content);
- $content=htmlize($type, $content);
+ my $content=htmlize($page, $type,
+ linkify($page, $page,
+ preprocess($page, $page,
+ filter($page, $page,
+ readfile($srcfile)))));
- check_overwrite("$config{destdir}/".htmlpage($page), $page);
writefile(htmlpage($page), $config{destdir},
- genpage($content, $page, mtime($srcfile)));
- $oldpagemtime{$page}=time;
- $renderedfiles{$page}=htmlpage($page);
+ genpage($page, $content, mtime($srcfile)));
}
else {
- my $content=readfile($srcfile, 1);
- $links{$file}=[];
+ my $srcfd=readfile($srcfile, 1, 1);
delete $depends{$file};
- check_overwrite("$config{destdir}/$file", $file);
- writefile($file, $config{destdir}, $content, 1);
- $oldpagemtime{$file}=time;
- $renderedfiles{$file}=$file;
+ will_render($file, $file, 1);
+ writefile($file, $config{destdir}, undef, 1, sub {
+ my $destfd=shift;
+ my $cleanup=shift;
+
+ my $blksize = 16384;
+ my ($len, $buf, $written);
+ while ($len = sysread $srcfd, $buf, $blksize) {
+ if (! defined $len) {
+ next if $! =~ /^Interrupted/;
+ error("failed to read $srcfile: $!", $cleanup);
+ }
+ my $offset = 0;
+ while ($len) {
+ defined($written = syswrite $destfd, $buf, $len, $offset)
+ or error("failed to write $file: $!", $cleanup);
+ $len -= $written;
+ $offset += $written;
+ }
+ }
+ });
}
} #}}}
}
} #}}}
-sub estcfg () { #{{{
- my $estdir="$config{wikistatedir}/hyperestraier";
- my $cgi=basename($config{cgiurl});
- $cgi=~s/\..*$//;
- open(TEMPLATE, ">$estdir/$cgi.tmpl") ||
- error("write $estdir/$cgi.tmpl: $!");
- print TEMPLATE misctemplate("search",
- "<!--ESTFORM-->\n\n<!--ESTRESULT-->\n\n<!--ESTINFO-->\n\n");
- close TEMPLATE;
- open(TEMPLATE, ">$estdir/$cgi.conf") ||
- error("write $estdir/$cgi.conf: $!");
- my $template=HTML::Template->new(
- filename => "$config{templatedir}/estseek.conf"
- );
- eval q{use Cwd 'abs_path'};
- $template->param(
- index => $estdir,
- tmplfile => "$estdir/$cgi.tmpl",
- destdir => abs_path($config{destdir}),
- url => $config{url},
- );
- print TEMPLATE $template->output;
- close TEMPLATE;
- $cgi="$estdir/".basename($config{cgiurl});
- unlink($cgi);
- symlink("/usr/lib/estraier/estseek.cgi", $cgi) ||
- error("symlink $cgi: $!");
-} # }}}
-
-sub estcmd ($;@) { #{{{
- my @params=split(' ', shift);
- push @params, "-cl", "$config{wikistatedir}/hyperestraier";
- if (@_) {
- push @params, "-";
- }
-
- my $pid=open(CHILD, "|-");
- if ($pid) {
- # parent
- foreach (@_) {
- print CHILD "$_\n";
- }
- close(CHILD) || error("estcmd @params exited nonzero: $?");
- }
- else {
- # child
- open(STDOUT, "/dev/null"); # shut it up (closing won't work)
- exec("estcmd", @params) || error("can't run estcmd");
- }
-} #}}}
-
sub refresh () { #{{{
# find existing pages
my %exists;
my @files;
eval q{use File::Find};
+ error($@) if $@;
find({
no_chdir => 1,
wanted => sub {
- if (/$config{wiki_file_prune_regexp}/) {
+ $_=decode_utf8($_);
+ if (file_pruned($_, $config{srcdir})) {
$File::Find::prune=1;
}
elsif (! -d $_ && ! -l $_) {
my ($f)=/$config{wiki_file_regexp}/; # untaint
if (! defined $f) {
- warn("skipping bad filename $_\n");
+ warn(sprintf(gettext("skipping bad filename %s"), $_)."\n");
}
else {
$f=~s/^\Q$config{srcdir}\E\/?//;
}
},
}, $config{srcdir});
- find({
- no_chdir => 1,
- wanted => sub {
- if (/$config{wiki_file_prune_regexp}/) {
- $File::Find::prune=1;
- }
- elsif (! -d $_ && ! -l $_) {
- my ($f)=/$config{wiki_file_regexp}/; # untaint
- if (! defined $f) {
- warn("skipping bad filename $_\n");
+ foreach my $dir (@{$config{underlaydirs}}, $config{underlaydir}) {
+ find({
+ no_chdir => 1,
+ wanted => sub {
+ $_=decode_utf8($_);
+ if (file_pruned($_, $dir)) {
+ $File::Find::prune=1;
}
- else {
- # Don't add files that are in the
- # srcdir.
- $f=~s/^\Q$config{underlaydir}\E\/?//;
- if (! -e "$config{srcdir}/$f" &&
- ! -l "$config{srcdir}/$f") {
- push @files, $f;
- $exists{pagename($f)}=1;
+ elsif (! -d $_ && ! -l $_) {
+ my ($f)=/$config{wiki_file_regexp}/; # untaint
+ if (! defined $f) {
+ warn(sprintf(gettext("skipping bad filename %s"), $_)."\n");
+ }
+ else {
+ $f=~s/^\Q$dir\E\/?//;
+ # avoid underlaydir
+ # override attacks; see
+ # security.mdwn
+ if (! -e "$config{srcdir}/$f" &&
+ ! -l "$config{srcdir}/$f") {
+ my $page=pagename($f);
+ if (! $exists{$page}) {
+ push @files, $f;
+ $exists{$page}=1;
+ }
+ }
}
}
- }
- },
- }, $config{underlaydir});
+ },
+ }, $dir);
+ };
my %rendered;
my @add;
foreach my $file (@files) {
my $page=pagename($file);
- if (! $oldpagemtime{$page}) {
- debug("new page $page") unless exists $pagectime{$page};
+ $pagesources{$page}=$file;
+ if (! $pagemtime{$page}) {
push @add, $file;
- $links{$page}=[];
- $pagesources{$page}=$file;
- $pagectime{$page}=mtime(srcfile($file))
- unless exists $pagectime{$page};
+ $pagecase{lc $page}=$page;
+ if ($config{getctime} && -e "$config{srcdir}/$file") {
+ $pagectime{$page}=rcs_getctime("$config{srcdir}/$file");
+ }
+ elsif (! exists $pagectime{$page}) {
+ $pagectime{$page}=mtime(srcfile($file));
+ }
}
}
my @del;
- foreach my $page (keys %oldpagemtime) {
+ foreach my $page (keys %pagemtime) {
if (! $exists{$page}) {
- debug("removing old page $page");
+ debug(sprintf(gettext("removing old page %s"), $page));
push @del, $pagesources{$page};
- prune($config{destdir}."/".$renderedfiles{$page});
- delete $renderedfiles{$page};
- $oldpagemtime{$page}=0;
+ $links{$page}=[];
+ $renderedfiles{$page}=[];
+ $pagemtime{$page}=0;
+ prune($config{destdir}."/".$_)
+ foreach @{$oldrenderedfiles{$page}};
delete $pagesources{$page};
+ foreach (keys %destsources) {
+ if ($destsources{$_} eq $page) {
+ delete $destsources{$_};
+ }
+ }
}
}
-
- # render any updated files
+
+ # find changed and new files
+ my @needsbuild;
foreach my $file (@files) {
my $page=pagename($file);
- if (! exists $oldpagemtime{$page} ||
- mtime(srcfile($file)) > $oldpagemtime{$page}) {
- debug("rendering changed file $file");
- render($file);
- $rendered{$file}=1;
+ my $mtime=mtime(srcfile($file));
+ if (! exists $pagemtime{$page} ||
+ $mtime > $pagemtime{$page} ||
+ $forcerebuild{$page}) {
+ $pagemtime{$page}=$mtime;
+ push @needsbuild, $file;
}
}
+ run_hooks(needsbuild => sub { shift->(\@needsbuild) });
+
+ # scan and render files
+ foreach my $file (@needsbuild) {
+ debug(sprintf(gettext("scanning %s"), $file));
+ scan($file);
+ }
+ calculate_backlinks();
+ foreach my $file (@needsbuild) {
+ debug(sprintf(gettext("rendering %s"), $file));
+ render($file);
+ $rendered{$file}=1;
+ }
- # if any files were added or removed, check to see if each page
- # needs an update due to linking to them or inlining them.
- # TODO: inefficient; pages may get rendered above and again here;
- # problem is the bestlink may have changed and we won't know until
- # now
+ # rebuild pages that link to added or removed pages
if (@add || @del) {
-FILE: foreach my $file (@files) {
- my $page=pagename($file);
- foreach my $f (@add, @del) {
- my $p=pagename($f);
- foreach my $link (@{$links{$page}}) {
- if (bestlink($page, $link) eq $p) {
- debug("rendering $file, which links to $p");
- render($file);
- $rendered{$file}=1;
- next FILE;
- }
- }
+ foreach my $f (@add, @del) {
+ my $p=pagename($f);
+ foreach my $page (keys %{$backlinks{$p}}) {
+ my $file=$pagesources{$page};
+ next if $rendered{$file};
+ debug(sprintf(gettext("rendering %s, which links to %s"), $file, $p));
+ render($file);
+ $rendered{$file}=1;
}
}
}
- # Handle backlinks; if a page has added/removed links, update the
- # pages it links to. Also handles rebuilding dependat pages.
- # TODO: inefficient; pages may get rendered above and again here;
- # problem is the backlinks could be wrong in the first pass render
- # above
if (%rendered || @del) {
+ # rebuild dependant pages
foreach my $f (@files) {
+ next if $rendered{$f};
my $p=pagename($f);
if (exists $depends{$p}) {
foreach my $file (keys %rendered, @del) {
next if $f eq $file;
my $page=pagename($file);
- if (globlist_match($page, $depends{$p})) {
- debug("rendering $f, which depends on $page");
+ if (pagespec_match($page, $depends{$p}, location => $p)) {
+ debug(sprintf(gettext("rendering %s, which depends on %s"), $f, $page));
render($f);
$rendered{$f}=1;
last;
}
}
+ # handle backlinks; if a page has added/removed links,
+ # update the pages it links to
my %linkchanged;
foreach my $file (keys %rendered, @del) {
my $page=pagename($file);
foreach my $link (keys %linkchanged) {
my $linkfile=$pagesources{$link};
if (defined $linkfile) {
- debug("rendering $linkfile, to update its backlinks");
+ next if $rendered{$linkfile};
+ debug(sprintf(gettext("rendering %s, to update its backlinks"), $linkfile));
render($linkfile);
$rendered{$linkfile}=1;
}
}
}
- if ($config{hyperestraier} && (%rendered || @del)) {
- debug("updating hyperestraier search index");
- if (%rendered) {
- estcmd("gather -cm -bc -cl -sd",
- map { $config{destdir}."/".$renderedfiles{pagename($_)} }
- keys %rendered);
- }
- if (@del) {
- estcmd("purge -cl");
+ # remove no longer rendered files
+ foreach my $src (keys %rendered) {
+ my $page=pagename($src);
+ foreach my $file (@{$oldrenderedfiles{$page}}) {
+ if (! grep { $_ eq $file } @{$renderedfiles{$page}}) {
+ debug(sprintf(gettext("removing %s, no longer rendered by %s"), $file, $page));
+ prune($config{destdir}."/".$file);
+ }
}
-
- debug("generating hyperestraier cgi config");
- estcfg();
}
+
+ if (@del) {
+ run_hooks(delete => sub { shift->(@del) });
+ }
+ if (%rendered) {
+ run_hooks(change => sub { shift->(keys %rendered) });
+ }
+} #}}}
+
+sub commandline_render () { #{{{
+ loadplugins();
+ checkconfig();
+ lockwiki();
+ loadindex();
+ unlockwiki();
+
+ my $srcfile=possibly_foolish_untaint($config{render});
+ my $file=$srcfile;
+ $file=~s/\Q$config{srcdir}\E\/?//;
+
+ my $type=pagetype($file);
+ die sprintf(gettext("ikiwiki: cannot render %s"), $srcfile)."\n" unless defined $type;
+ my $content=readfile($srcfile);
+ my $page=pagename($file);
+ $pagesources{$page}=$file;
+ $content=filter($page, $page, $content);
+ $content=preprocess($page, $page, $content);
+ $content=linkify($page, $page, $content);
+ $content=htmlize($page, $type, $content);
+
+ print genpage($page, $content, mtime($srcfile));
+ exit 0;
} #}}}
1