diff options
| -rw-r--r-- | IkiWiki/Plugin/parentlinks.pm | 2 | ||||
| -rw-r--r-- | IkiWiki/Plugin/po.pm | 904 | ||||
| -rw-r--r-- | debian/control | 2 | ||||
| -rw-r--r-- | debian/copyright | 4 | ||||
| -rw-r--r-- | doc/ikiwiki/pagespec.mdwn | 2 | ||||
| -rw-r--r-- | doc/ikiwiki/pagespec/po.mdwn | 16 | ||||
| -rw-r--r-- | doc/plugins/po.mdwn | 623 | ||||
| -rwxr-xr-x | t/po.t | 173 | ||||
| -rwxr-xr-x | t/syntax.t | 2 | ||||
| l--------- | underlays/basewiki/ikiwiki/pagespec/po.mdwn | 1 |
10 files changed, 1726 insertions, 3 deletions
diff --git a/IkiWiki/Plugin/parentlinks.pm b/IkiWiki/Plugin/parentlinks.pm index a8b3641e9..9095dabda 100644 --- a/IkiWiki/Plugin/parentlinks.pm +++ b/IkiWiki/Plugin/parentlinks.pm @@ -36,7 +36,7 @@ sub parentlinks ($) { #{{{ $depth=$i; $height=($pagedepth - $depth); push @ret, { - url => urlto($path, $page), + url => urlto(bestlink($page, $path), $page), page => $title, depth => $depth, height => $height, diff --git a/IkiWiki/Plugin/po.pm b/IkiWiki/Plugin/po.pm new file mode 100644 index 000000000..ae97a2f38 --- /dev/null +++ b/IkiWiki/Plugin/po.pm @@ -0,0 +1,904 @@ +#!/usr/bin/perl +# .po as a wiki page type +# Licensed under GPL v2 or greater +# Copyright (C) 2008 intrigeri <intrigeri@boum.org> +# inspired by the GPL'd po4a-translate, +# which is Copyright 2002, 2003, 2004 by Martin Quinson (mquinson#debian.org) +package IkiWiki::Plugin::po; + +use warnings; +use strict; +use IkiWiki 2.00; +use Encode; +use Locale::Po4a::Chooser; +use Locale::Po4a::Po; +use File::Basename; +use File::Copy; +use File::Spec; +use File::Temp; +use Memoize; +use UNIVERSAL; + +my %translations; +my @origneedsbuild; +my %origsubs; + +memoize("istranslatable"); +memoize("_istranslation"); +memoize("percenttranslated"); + +sub import { #{{{ + hook(type => "getsetup", id => "po", call => \&getsetup); + hook(type => "checkconfig", id => "po", call => \&checkconfig); + hook(type => "needsbuild", id => "po", call => \&needsbuild); + hook(type => "scan", id => "po", call => \&scan, last =>1); + hook(type => "filter", id => "po", call => \&filter); + hook(type => "htmlize", id => "po", call => \&htmlize); + hook(type => "pagetemplate", id => "po", call => \&pagetemplate, last => 1); + hook(type => "renamepage", id => "po", call => \&renamepage); + hook(type => "delete", id => "po", call => \&mydelete); + hook(type => "change", id => "po", call => \&change); + hook(type => "editcontent", id => "po", call => \&editcontent); + + $origsubs{'bestlink'}=\&IkiWiki::bestlink; + inject(name => "IkiWiki::bestlink", call => \&mybestlink); + $origsubs{'beautify_urlpath'}=\&IkiWiki::beautify_urlpath; + inject(name => "IkiWiki::beautify_urlpath", call => \&mybeautify_urlpath); + $origsubs{'targetpage'}=\&IkiWiki::targetpage; + inject(name => "IkiWiki::targetpage", call => \&mytargetpage); + $origsubs{'urlto'}=\&IkiWiki::urlto; + inject(name => "IkiWiki::urlto", call => \&myurlto); +} #}}} + + +# ,---- +# | Table of contents +# `---- + +# 1. Hooks +# 2. Injected functions +# 3. Blackboxes for private data +# 4. Helper functions +# 5. PageSpec's + + +# ,---- +# | Hooks +# `---- + +sub getsetup () { #{{{ + return + plugin => { + safe => 0, + rebuild => 1, + }, + po_master_language => { + type => "string", + example => { + 'code' => 'en', + 'name' => 'English' + }, + description => "master language (non-PO files)", + safe => 1, + rebuild => 1, + }, + po_slave_languages => { + type => "string", + example => { + 'fr' => 'Français', + 'es' => 'Castellano', + 'de' => 'Deutsch' + }, + description => "slave languages (PO files)", + safe => 1, + rebuild => 1, + }, + po_translatable_pages => { + type => "pagespec", + example => "!*/Discussion", + description => "PageSpec controlling which pages are translatable", + link => "ikiwiki/PageSpec", + safe => 1, + rebuild => 1, + }, + po_link_to => { + type => "string", + example => "current", + description => "internal linking behavior (default/current/negotiated)", + safe => 1, + rebuild => 1, + }, +} #}}} + +sub checkconfig () { #{{{ + foreach my $field (qw{po_master_language po_slave_languages}) { + if (! exists $config{$field} || ! defined $config{$field}) { + error(sprintf(gettext("Must specify %s"), $field)); + } + } + if (! (keys %{$config{po_slave_languages}})) { + error(gettext("At least one slave language must be defined in po_slave_languages")); + } + map { + islanguagecode($_) + or error(sprintf(gettext("%s is not a valid language code"), $_)); + } ($config{po_master_language}{code}, keys %{$config{po_slave_languages}}); + if (! exists $config{po_translatable_pages} || + ! defined $config{po_translatable_pages}) { + $config{po_translatable_pages}=""; + } + if (! exists $config{po_link_to} || + ! defined $config{po_link_to}) { + $config{po_link_to}='default'; + } + elsif (! grep { + $config{po_link_to} eq $_ + } ('default', 'current', 'negotiated')) { + warn(sprintf(gettext('po_link_to=%s is not a valid setting, falling back to po_link_to=default'), + $config{po_link_to})); + $config{po_link_to}='default'; + } + elsif ($config{po_link_to} eq "negotiated" && ! $config{usedirs}) { + warn(gettext('po_link_to=negotiated requires usedirs to be enabled, falling back to po_link_to=default')); + $config{po_link_to}='default'; + } + push @{$config{wiki_file_prune_regexps}}, qr/\.pot$/; +} #}}} + +sub needsbuild () { #{{{ + my $needsbuild=shift; + + # backup @needsbuild content so that change() can know whether + # a given master page was rendered because its source file was changed + @origneedsbuild=(@$needsbuild); + + flushmemoizecache(); + buildtranslationscache(); + + # make existing translations depend on the corresponding master page + foreach my $master (keys %translations) { + map add_depends($_, $master), values %{otherlanguages($master)}; + } +} #}}} + +# Massage the recorded state of internal links so that: +# - it matches the actually generated links, rather than the links as written +# in the pages' source +# - backlinks are consistent in all cases +sub scan (@) { #{{{ + my %params=@_; + my $page=$params{page}; + my $content=$params{content}; + + return unless UNIVERSAL::can("IkiWiki::Plugin::link", "import"); + + if (istranslation($page)) { + foreach my $destpage (@{$links{$page}}) { + if (istranslatable($destpage)) { + # replace one occurence of $destpage in $links{$page} + # (we only want to replace the one that was added by + # IkiWiki::Plugin::link::scan, other occurences may be + # there for other reasons) + for (my $i=0; $i<@{$links{$page}}; $i++) { + if (@{$links{$page}}[$i] eq $destpage) { + @{$links{$page}}[$i] = $destpage . '.' . lang($page); + last; + } + } + } + } + } + elsif (! istranslatable($page) && ! istranslation($page)) { + foreach my $destpage (@{$links{$page}}) { + if (istranslatable($destpage)) { + # make sure any destpage's translations has + # $page in its backlinks + push @{$links{$page}}, + values %{otherlanguages($destpage)}; + } + } + } +} #}}} + +# We use filter to convert PO to the master page's format, +# since the rest of ikiwiki should not work on PO files. +sub filter (@) { #{{{ + my %params = @_; + + my $page = $params{page}; + my $destpage = $params{destpage}; + my $content = decode_utf8(encode_utf8($params{content})); + + return $content if ( ! istranslation($page) + || alreadyfiltered($page, $destpage) ); + + # CRLF line terminators make poor Locale::Po4a feel bad + $content=~s/\r\n/\n/g; + + # Implementation notes + # + # 1. Locale::Po4a reads/writes from/to files, and I'm too lazy + # to learn how to disguise a variable as a file. + # 2. There are incompatibilities between some File::Temp versions + # (including 0.18, bundled with Lenny's perl-modules package) + # and others (e.g. 0.20, previously present in the archive as + # a standalone package): under certain circumstances, some + # return a relative filename, whereas others return an absolute one; + # we here use this module in a way that is at least compatible + # with 0.18 and 0.20. Beware, hit'n'run refactorers! + my $infile = new File::Temp(TEMPLATE => "ikiwiki-po-filter-in.XXXXXXXXXX", + DIR => File::Spec->tmpdir, + UNLINK => 1)->filename; + my $outfile = new File::Temp(TEMPLATE => "ikiwiki-po-filter-out.XXXXXXXXXX", + DIR => File::Spec->tmpdir, + UNLINK => 1)->filename; + + writefile(basename($infile), File::Spec->tmpdir, $content); + + my $masterfile = srcfile($pagesources{masterpage($page)}); + my (@pos,@masters); + push @pos,$infile; + push @masters,$masterfile; + my %options = ( + "markdown" => (pagetype($masterfile) eq 'mdwn') ? 1 : 0, + ); + my $doc=Locale::Po4a::Chooser::new('text',%options); + $doc->process( + 'po_in_name' => \@pos, + 'file_in_name' => \@masters, + 'file_in_charset' => 'utf-8', + 'file_out_charset' => 'utf-8', + ) or error("[po/filter:$page]: failed to translate"); + $doc->write($outfile) or error("[po/filter:$page] could not write $outfile"); + $content = readfile($outfile) or error("[po/filter:$page] could not read $outfile"); + + # Unlinking should happen automatically, thanks to File::Temp, + # but it does not work here, probably because of the way writefile() + # and Locale::Po4a::write() work. + unlink $infile, $outfile; + + setalreadyfiltered($page, $destpage); + return $content; +} #}}} + +sub htmlize (@) { #{{{ + my %params=@_; + + my $page = $params{page}; + my $content = $params{content}; + + # ignore PO files this plugin did not create + return $content unless istranslation($page); + + # force content to be htmlize'd as if it was the same type as the master page + return IkiWiki::htmlize($page, $page, + pagetype(srcfile($pagesources{masterpage($page)})), + $content); +} #}}} + +sub pagetemplate (@) { #{{{ + my %params=@_; + my $page=$params{page}; + my $destpage=$params{destpage}; + my $template=$params{template}; + + my ($masterpage, $lang) = istranslation($page); + + if (istranslation($page) && $template->query(name => "percenttranslated")) { + $template->param(percenttranslated => percenttranslated($page)); + } + if ($template->query(name => "istranslation")) { + $template->param(istranslation => scalar istranslation($page)); + } + if ($template->query(name => "istranslatable")) { + $template->param(istranslatable => istranslatable($page)); + } + if ($template->query(name => "HOMEPAGEURL")) { + $template->param(homepageurl => homepageurl($page)); + } + if ($template->query(name => "otherlanguages")) { + $template->param(otherlanguages => [otherlanguagesloop($page)]); + map add_depends($page, $_), (values %{otherlanguages($page)}); + } + # Rely on IkiWiki::Render's genpage() to decide wether + # a discussion link should appear on $page; this is not + # totally accurate, though: some broken links may be generated + # when cgiurl is disabled. + # This compromise avoids some code duplication, and will probably + # prevent future breakage when ikiwiki internals change. + # Known limitations are preferred to future random bugs. + if ($template->param('discussionlink') && istranslation($page)) { + $template->param('discussionlink' => htmllink( + $page, + $destpage, + $masterpage . '/' . gettext("Discussion"), + noimageinline => 1, + forcesubpage => 0, + linktext => gettext("Discussion"), + )); + } + # Remove broken parentlink to ./index.html on home page's translations. + # It works because this hook has the "last" parameter set, to ensure it + # runs after parentlinks' own pagetemplate hook. + if ($template->param('parentlinks') + && istranslation($page) + && $masterpage eq "index") { + $template->param('parentlinks' => []); + } +} # }}} + +# Save information about master page rename, so that: +# - our delete hook can ignore the translations not renamed already +# - our change hook can rename the translations accordingly. +# +# FIXME: +# This hook is called once per page linking to the old page, which +# means our delete hook won't know it should not delete a renamed orphan +# page's translation. +# +# Moreover, we can't recognize such pages at delete stage: +# existing links are fixed in the renaming process, so every +# renamed page's old location will be an orphan anyway at this time. +sub renamepage(@) { #{{{ + my %params=@_; + my $oldpage=$params{oldpage}; + my $newpage=$params{newpage}; + + setrenamed($oldpage, $newpage) if istranslatable($oldpage); + return $params{content}; +} #}}} + +sub mydelete(@) { #{{{ + my @deleted=@_; + + map { + deletetranslations($_); + } grep { istranslatablefile($_) && ! renamed(pagename($_))} @deleted; +} #}}} + +sub change(@) { #{{{ + my @rendered=@_; + + my $eachrenamed=eachrenamed(); + while (my ($oldpage, $newpage) = $eachrenamed->()) { + renametranslations($oldpage, $newpage); + } + resetrenamed(); + + my $updated_po_files=0; + + # Refresh/create POT and PO files as needed. + foreach my $file (@rendered) { + next unless istranslatablefile($file); + my $page=pagename($file); + my $masterfile=srcfile($file); + my $updated_pot_file=0; + # Only refresh Pot file if it does not exist, or if + # $pagesources{$page} was changed: don't if only the HTML was + # refreshed, e.g. because of a dependency. + if ((grep { $_ eq $pagesources{$page} } @origneedsbuild) + || ! -e potfile($masterfile)) { + refreshpot($masterfile); + $updated_pot_file=1; + } + my @pofiles; + map { + push @pofiles, $_ if ($updated_pot_file || ! -e $_); + } (pofiles($masterfile)); + if (@pofiles) { + refreshpofiles($masterfile, @pofiles); + map { IkiWiki::rcs_add($_); } @pofiles if ($config{rcs}); + $updated_po_files=1; + } + } + + if ($updated_po_files) { + # Check staged changes in. + if ($config{rcs}) { + IkiWiki::disable_commit_hook(); + IkiWiki::rcs_commit_staged(gettext("updated PO files"), + "IkiWiki::Plugin::po::change", "127.0.0.1"); + IkiWiki::enable_commit_hook(); + IkiWiki::rcs_update(); + } + # Reinitialize module's private variables. + resetalreadyfiltered(); + resettranslationscache(); + flushmemoizecache(); + # Trigger a wiki refresh. + require IkiWiki::Render; + # without preliminary saveindex/loadindex, refresh() + # complains about a lot of uninitialized variables + IkiWiki::saveindex(); + IkiWiki::loadindex(); + IkiWiki::refresh(); + IkiWiki::saveindex(); + } +} #}}} + +# As we're previewing or saving a page, the content may have +# changed, so tell the next filter() invocation it must not be lazy. +sub editcontent () { #{{{ + my %params=@_; + + unsetalreadyfiltered($params{page}, $params{page}); + return $params{content}; +} #}}} + + +# ,---- +# | Injected functions +# `---- + +# Implement po_link_to 'current' and 'negotiated' settings. +sub mybestlink ($$) { #{{{ + my $page=shift; + my $link=shift; + + my $res=$origsubs{'bestlink'}->(masterpage($page), $link); + if (length $res + && ($config{po_link_to} eq "current" || $config{po_link_to} eq "negotiated") + && istranslatable($res) + && istranslation($page)) { + return $res . "." . lang($page); + } + return $res; +} #}}} + +sub mybeautify_urlpath ($) { #{{{ + my $url=shift; + + my $res=$origsubs{'beautify_urlpath'}->($url); + if ($config{po_link_to} eq "negotiated") { + $res =~ s!/\Qindex.$config{po_master_language}{code}.$config{htmlext}\E$!/!; + $res =~ s!/\Qindex.$config{htmlext}\E$!/!; + map { + $res =~ s!/\Qindex.$_.$config{htmlext}\E$!/!; + } (keys %{$config{po_slave_languages}}); + } + return $res; +} #}}} + +sub mytargetpage ($$) { #{{{ + my $page=shift; + my $ext=shift; + + if (istranslation($page) || istranslatable($page)) { + my ($masterpage, $lang) = (masterpage($page), lang($page)); + if (! $config{usedirs} || $masterpage eq 'index') { + return $masterpage . "." . $lang . "." . $ext; + } + else { + return $masterpage . "/index." . $lang . "." . $ext; + } + } + return $origsubs{'targetpage'}->($page, $ext); +} #}}} + +sub myurlto ($$;$) { #{{{ + my $to=shift; + my $from=shift; + my $absolute=shift; + + # workaround hard-coded /index.$config{htmlext} in IkiWiki::urlto() + if (! length $to + && $config{po_link_to} eq "current" + && istranslatable('index')) { + return IkiWiki::beautify_urlpath(IkiWiki::baseurl($from) . "index." . lang($from) . ".$config{htmlext}"); + } + return $origsubs{'urlto'}->($to,$from,$absolute); +} #}}} + + +# ,---- +# | Blackboxes for private data +# `---- + +{ + my %filtered; + + sub alreadyfiltered($$) { #{{{ + my $page=shift; + my $destpage=shift; + + return ( exists $filtered{$page}{$destpage} + && $filtered{$page}{$destpage} eq 1 ); + } #}}} + + sub setalreadyfiltered($$) { #{{{ + my $page=shift; + my $destpage=shift; + + $filtered{$page}{$destpage}=1; + } #}}} + + sub unsetalreadyfiltered($$) { #{{{ + my $page=shift; + my $destpage=shift; + + if (exists $filtered{$page}{$destpage}) { + delete $filtered{$page}{$destpage}; + } + } #}}} + + sub resetalreadyfiltered() { #{{{ + undef %filtered; + } #}}} +} + +{ + my %renamed; + + sub renamed ($) { #{{{ + my $page=shift; + + if (exists $renamed{$page} && + defined $renamed{$page}) { + return $renamed{$page}; + } + return; + } #}}} + + sub setrenamed ($$) { #{{{ + my $oldpage=shift; + my $newpage=shift; + + $renamed{$oldpage}=$newpage; + } #}}} + + sub resetrenamed () { #{{{ + undef %renamed; + } #}}} + + sub eachrenamed () { #{{{ + return sub { each %renamed }; + } #}}} +} + +# ,---- +# | Helper functions +# `---- + +sub maybe_add_leading_slash ($;$) { #{{{ + my $str=shift; + my $add=shift; + $add=1 unless defined $add; + return '/' . $str if $add; + return $str; +} #}}} + +sub istranslatablefile ($) { #{{{ + my $file=shift; + + return 0 unless defined $file; + return 0 if (defined pagetype($file) && pagetype($file) eq 'po'); + return 0 if $file =~ /\.pot$/; + return 1 if pagespec_match(pagename($file), $config{po_translatable_pages}); + return; +} #}}} + +sub istranslatable ($) { #{{{ + my $page=shift; + + $page=~s#^/##; + return 1 if istranslatablefile($pagesources{$page}); + return; +} #}}} + +sub _istranslation ($) { #{{{ + my $page=shift; + + my $hasleadingslash = ($page=~s#^/##); + my $file=$pagesources{$page}; + return 0 unless (defined $file + && defined pagetype($file) + && pagetype($file) eq 'po'); + return 0 if $file =~ /\.pot$/; + + my ($masterpage, $lang) = ($page =~ /(.*)[.]([a-z]{2})$/); + return 0 unless (defined $masterpage && defined $lang + && length $masterpage && length $lang + && defined $pagesources{$masterpage} + && defined $config{po_slave_languages}{$lang}); + + return (maybe_add_leading_slash($masterpage, $hasleadingslash), $lang) + if istranslatable($masterpage); +} #}}} + +sub istranslation ($) { #{{{ + my $page=shift; + + if (1 < (my ($masterpage, $lang) = _istranslation($page))) { + my $hasleadingslash = ($masterpage=~s#^/##); + $translations{$masterpage}{$lang}=$page unless exists $translations{$masterpage}{$lang}; + return (maybe_add_leading_slash($masterpage, $hasleadingslash), $lang); + } + return; +} #}}} + +sub masterpage ($) { #{{{ + my $page=shift; + + if ( 1 < (my ($masterpage, $lang) = _istranslation($page))) { + return $masterpage; + } + return $page; +} #}}} + +sub lang ($) { #{{{ + my $page=shift; + + if (1 < (my ($masterpage, $lang) = _istranslation($page))) { + return $lang; + } + return $config{po_master_language}{code}; +} #}}} + +sub islanguagecode ($) { #{{{ + my $code=shift; + + return ($code =~ /^[a-z]{2}$/); +} #}}} + +sub otherlanguage ($$) { #{{{ + my $page=shift; + my $code=shift; + + return masterpage($page) if $code eq $config{po_master_language}{code}; + return masterpage($page) . '.' . $code; +} #}}} + +sub otherlanguages ($) { #{{{ + my $page=shift; + + my %ret; + return \%ret unless (istranslation($page) || istranslatable($page)); + my $curlang=lang($page); + foreach my $lang + ($config{po_master_language}{code}, keys %{$config{po_slave_languages}}) { + next if $lang eq $curlang; + $ret{$lang}=otherlanguage($page, $lang); + } + return \%ret; +} #}}} + +sub potfile ($) { #{{{ + my $masterfile=shift; + + (my $name, my $dir, my $suffix) = fileparse($masterfile, qr/\.[^.]*/); + $dir='' if $dir eq './'; + return File::Spec->catpath('', $dir, $name . ".pot"); +} #}}} + +sub pofile ($$) { #{{{ + my $masterfile=shift; + my $lang=shift; + + (my $name, my $dir, my $suffix) = fileparse($masterfile, qr/\.[^.]*/); + $dir='' if $dir eq './'; + return File::Spec->catpath('', $dir, $name . "." . $lang . ".po"); +} #}}} + +sub pofiles ($) { #{{{ + my $masterfile=shift; + + return map pofile($masterfile, $_), (keys %{$config{po_slave_languages}}); +} #}}} + +sub refreshpot ($) { #{{{ + my $masterfile=shift; + + my $potfile=potfile($masterfile); + my %options = ("markdown" => (pagetype($masterfile) eq 'mdwn') ? 1 : 0); + my $doc=Locale::Po4a::Chooser::new('text',%options); + $doc->{TT}{utf_mode} = 1; + $doc->{TT}{file_in_charset} = 'utf-8'; + $doc->{TT}{file_out_charset} = 'utf-8'; + $doc->read($masterfile); + # let's cheat a bit to force porefs option to be passed to Locale::Po4a::Po; + # this is undocument use of internal Locale::Po4a::TransTractor's data, + # compulsory since this module prevents us from using the porefs option. + my %po_options = ('porefs' => 'none'); + $doc->{TT}{po_out}=Locale::Po4a::Po->new(\%po_options); + $doc->{TT}{po_out}->set_charset('utf-8'); + # do the actual work + $doc->parse; + IkiWiki::prep_writefile(basename($potfile),dirname($potfile)); + $doc->writepo($potfile); +} #}}} + +sub refreshpofiles ($@) { #{{{ + my $masterfile=shift; + my @pofiles=@_; + + my $potfile=potfile($masterfile); + error("[po/refreshpofiles] POT file ($potfile) does not exist") unless (-e $potfile); + + foreach my $pofile (@pofiles) { + IkiWiki::prep_writefile(basename($pofile),dirname($pofile)); + if (-e $pofile) { + system("msgmerge", "-U", "--backup=none", $pofile, $potfile) == 0 + or error("[po/refreshpofiles:$pofile] failed to update"); + } + else { + File::Copy::syscopy($potfile,$pofile) + or error("[po/refreshpofiles:$pofile] failed to copy the POT file"); + } + } +} #}}} + +sub buildtranslationscache() { #{{{ + # use istranslation's side-effect + map istranslation($_), (keys %pagesources); +} #}}} + +sub resettranslationscache() { #{{{ + undef %translations; +} #}}} + +sub flushmemoizecache() { #{{{ + Memoize::flush_cache("istranslatable"); + Memoize::flush_cache("_istranslation"); + Memoize::flush_cache("percenttranslated"); +} #}}} + +sub urlto_with_orig_beautiful_urlpath($$) { #{{{ + my $to=shift; + my $from=shift; + + inject(name => "IkiWiki::beautify_urlpath", call => $origsubs{'beautify_urlpath'}); + my $res=urlto($to, $from); + inject(name => "IkiWiki::beautify_urlpath", call => \&mybeautify_urlpath); + + return $res; +} #}}} + +sub percenttranslated ($) { #{{{ + my $page=shift; + + return gettext("N/A") unless istranslation($page); + my $file=srcfile($pagesources{$page}); + my $masterfile = srcfile($pagesources{masterpage($page)}); + my (@pos,@masters); + push @pos,$file; + push @masters,$masterfile; + my %options = ( + "markdown" => (pagetype($masterfile) eq 'mdwn') ? 1 : 0, + ); + my $doc=Locale::Po4a::Chooser::new('text',%options); + $doc->process( + 'po_in_name' => \@pos, + 'file_in_name' => \@masters, + 'file_in_charset' => 'utf-8', + 'file_out_charset' => 'utf-8', + ) or error("[po/percenttranslated:$page]: failed to translate"); + my ($percent,$hit,$queries) = $doc->stats(); + return $percent; +} #}}} + +sub languagename ($) { #{{{ + my $code=shift; + + return $config{po_master_language}{name} + if $code eq $config{po_master_language}{code}; + return $config{po_slave_languages}{$code} + if defined $config{po_slave_languages}{$code}; + return; +} #}}} + +sub otherlanguagesloop ($) { #{{{ + my $page=shift; + + my @ret; + my %otherpages=%{otherlanguages($page)}; + while (my ($lang, $otherpage) = each %otherpages) { + if (istranslation($page) && masterpage($page) eq $otherpage) { + push @ret, { + url => urlto_with_orig_beautiful_urlpath($otherpage, $page), + code => $lang, + language => languagename($lang), + master => 1, + }; + } + else { + push @ret, { + url => urlto_with_orig_beautiful_urlpath($otherpage, $page), + code => $lang, + language => languagename($lang), + percent => percenttranslated($otherpage), + } + } + } + return sort { + return -1 if $a->{code} eq $config{po_master_language}{code}; + return 1 if $b->{code} eq $config{po_master_language}{code}; + return $a->{language} cmp $b->{language}; + } @ret; +} #}}} + +sub homepageurl (;$) { #{{{ + my $page=shift; + + return urlto('', $page); +} #}}} + +# - do *not* implement this until the renamepage hook works +# - do *not* delete translations of pages that were orphans +# before being renamed (see renamepage hook comments above) +sub deletetranslations ($) { #{{{ + my $deletedmasterfile=shift; + + debug "po(deletetranslations): TODO: delete translations of $deletedmasterfile"; +} #}}} + +sub renametranslations (@) { #{{{ + my ($oldpage, $newpage)=shift; + + debug "po(renametranslations): TODO: rename translations of $oldpage to $newpage"; +} #}}} + + +# ,---- +# | PageSpec's +# `---- + +package IkiWiki::PageSpec; +use warnings; +use strict; +use IkiWiki 2.00; + +sub match_istranslation ($;@) { #{{{ + my $page=shift; + + if (IkiWiki::Plugin::po::istranslation($page)) { + return IkiWiki::SuccessReason->new("is a translation page"); + } + else { + return IkiWiki::FailReason->new("is not a translation page"); + } +} #}}} + +sub match_istranslatable ($;@) { #{{{ + my $page=shift; + + if (IkiWiki::Plugin::po::istranslatable($page)) { + return IkiWiki::SuccessReason->new("is set as translatable in po_translatable_pages"); + } + else { + return IkiWiki::FailReason->new("is not set as translatable in po_translatable_pages"); + } +} #}}} + +sub match_lang ($$;@) { #{{{ + my $page=shift; + my $wanted=shift; + + my $regexp=IkiWiki::glob2re($wanted); + my $lang=IkiWiki::Plugin::po::lang($page); + if ($lang!~/^$regexp$/i) { + return IkiWiki::FailReason->new("file language is $lang, not $wanted"); + } + else { + return IkiWiki::SuccessReason->new("file language is $wanted"); + } +} #}}} + +sub match_currentlang ($$;@) { #{{{ + my $page=shift; + shift; + my %params=@_; + + return IkiWiki::FailReason->new("no location provided") unless exists $params{location}; + + my $currentlang=IkiWiki::Plugin::po::lang($params{location}); + my $lang=IkiWiki::Plugin::po::lang($page); + + if ($lang eq $currentlang) { + return IkiWiki::SuccessReason->new("file language is the same as current one, i.e. $currentlang"); + } + else { + return IkiWiki::FailReason->new("file language is $lang, whereas current language is $currentlang"); + } +} #}}} + +1 diff --git a/debian/control b/debian/control index fdf2a3a36..04283532b 100644 --- a/debian/control +++ b/debian/control @@ -14,7 +14,7 @@ Package: ikiwiki Architecture: all Depends: ${perl:Depends}, markdown | libtext-markdown-perl, libhtml-scrubber-perl, libhtml-template-perl, libhtml-parser-perl, liburi-perl Recommends: gcc | c-compiler, libc6-dev | libc-dev, subversion | git-core (>= 1:1.5.0) | tla | bzr (>= 0.91) | mercurial | monotone (>= 0.38), libxml-simple-perl, libnet-openid-consumer-perl, liblwpx-paranoidagent-perl, libtimedate-perl, libcgi-formbuilder-perl (>= 3.05), libcgi-session-perl (>= 4.14-1), libmail-sendmail-perl, libauthen-passphrase-perl -Suggests: viewvc | gitweb | viewcvs, libsearch-xapian-perl, xapian-omega (>= 1.0.5), librpc-xml-perl, libtext-wikiformat-perl, python, python-docutils, polygen, tidy, libxml-feed-perl, libmailtools-perl, perlmagick, libfile-mimeinfo-perl, libcrypt-ssleay-perl, liblocale-gettext-perl (>= 1.05-1), libtext-typography-perl, libtext-csv-perl, libdigest-sha1-perl, graphviz, libnet-amazon-s3-perl, sparkline-php, texlive, dvipng +Suggests: viewvc | gitweb | viewcvs, libsearch-xapian-perl, xapian-omega (>= 1.0.5), librpc-xml-perl, libtext-wikiformat-perl, python, python-docutils, polygen, tidy, libxml-feed-perl, libmailtools-perl, perlmagick, libfile-mimeinfo-perl, libcrypt-ssleay-perl, liblocale-gettext-perl (>= 1.05-1), libtext-typography-perl, libtext-csv-perl, libdigest-sha1-perl, graphviz, libnet-amazon-s3-perl, sparkline-php, texlive, dvipng, po4a Conflicts: ikiwiki-plugin-table Replaces: ikiwiki-plugin-table Provides: ikiwiki-plugin-table diff --git a/debian/copyright b/debian/copyright index f257234dd..fe5db8af8 100644 --- a/debian/copyright +++ b/debian/copyright @@ -108,6 +108,10 @@ Files: google.pm Copyright: Copyright (C) 2008 Peter Simons <simons@cryp.to> License: GPL-2+ +Files: po.pm +Copyright: (C) 2008 intrigeri <intrigeri@boum.org> +License: GPL-2+ + Files: doc/logo/* Copyright: © 2006 Recai Oktaş <roktas@debian.org> License: GPL-2+ diff --git a/doc/ikiwiki/pagespec.mdwn b/doc/ikiwiki/pagespec.mdwn index c78666c40..176228e4b 100644 --- a/doc/ikiwiki/pagespec.mdwn +++ b/doc/ikiwiki/pagespec.mdwn @@ -47,6 +47,8 @@ Some more elaborate limits can be added to what matches using these functions: wiki admins. * "`ip(address)`" - tests whether a modification is being made from the specified IP address. +* Some additional special-purpose limits may be enabled, for matching + [[attachments|attachment]] and [[translations|po]]. For example, to match all pages in a blog that link to the page about music and were written in 2005: diff --git a/doc/ikiwiki/pagespec/po.mdwn b/doc/ikiwiki/pagespec/po.mdwn new file mode 100644 index 000000000..a5f88cf66 --- /dev/null +++ b/doc/ikiwiki/pagespec/po.mdwn @@ -0,0 +1,16 @@ +[[!if test="enabled(po)" + then="This wiki has po support **enabled**." + else="This wiki has po support **disabled**."]] + +If the [po](plugins/po) plugin is enabled, the regular +[[ikiwiki/PageSpec]] syntax is expanded with the following additional +tests that can be used to improve user navigation in a multi-lingual +wiki: + +* "`lang(LL)`" - Tests whether a page is written in the language + specified as a ISO639-1 (two-letter) language code. +* "`currentlang()`" - Tests whether a page is written in the same + language as the current page. + +Note: every non-po page is considered to be written in +`po_master_language`, as specified in `ikiwiki.setup`. diff --git a/doc/plugins/po.mdwn b/doc/plugins/po.mdwn new file mode 100644 index 000000000..ea1e89278 --- /dev/null +++ b/doc/plugins/po.mdwn @@ -0,0 +1,623 @@ +[[!template id=plugin name=po core=0 author="[[intrigeri]]"]] +[[!tag type/format]] + +This plugin adds support for multi-lingual wikis, translated with +gettext, using [po4a](http://po4a.alioth.debian.org/). + +It depends on the Perl `Locale::Po4a::Po` library (`apt-get install po4a`). + +[[!toc levels=2]] + +Introduction +============ + +A language is chosen as the "master" one, and any other supported +language is a "slave" one. + +A page written in the "master" language is a "master" page. It can be +of any page type supported by ikiwiki, except `po`. It does not have to be +named a special way: migration to this plugin does not imply any page +renaming work. + +Example: `bla/page.mdwn` is a "master" Markdown page written in +English; if `usedirs` is enabled, it is rendered as +`bla/page/index.en.html`, else as `bla/page.en.html`. + +Any translation of a "master" page into a "slave" language is called +a "slave" page; it is written in the gettext PO format. `po` is now +a page type supported by ikiwiki. + +Example: `bla/page.fr.po` is the PO "message catalog" used to +translate `bla/page.mdwn` into French; if `usedirs` is enabled, it is +rendered as `bla/page/index.fr.html`, else as `bla/page.fr.html` + + +Configuration +============= + +Supported languages +------------------- + +`po_master_language` is used to set the "master" language in +`ikiwiki.setup`, such as: + + po_master_language => { 'code' => 'en', 'name' => 'English' } + +`po_slave_languages` is used to set the list of supported "slave" +languages, such as: + + po_slave_languages => { 'fr' => 'Français', + 'es' => 'Castellano', + 'de' => 'Deutsch', + } + +Decide which pages are translatable +----------------------------------- + +The `po_translatable_pages` setting configures what pages are +translatable. It is a [[ikiwiki/PageSpec]], so you have lots of +control over what kind of pages are translatable. + +The `.po` files are not considered as being translatable, so you don't need to +worry about excluding them explicitly from this [[ikiwiki/PageSpec]]. + +Internal links +-------------- + +The `po_link_to` option in `ikiwiki.setup` is used to decide how +internal links should be generated, depending on web server features +and site-specific preferences. + +### Default linking behavior + +If `po_link_to` is unset, or set to `default`, ikiwiki's default +linking behavior is preserved: `\[[destpage]]` links to the master +language's page. + +### Link to current language + +If `po_link_to` is set to `current`, `\[[destpage]]` links to the +`destpage`'s version written in the current page's language, if +available, *i.e.*: + +- `foo/destpage/index.LL.html` if `usedirs` is enabled +- `foo/destpage.LL.html` if `usedirs` is disabled + +### Link to negotiated language + +If `po_link_to` is set to `negotiated`, `\[[page]]` links to the +negotiated preferred language, *i.e.* `foo/page/`. + +(In)compatibility notes: + +- if `usedirs` is disabled, it does not make sense to set `po_link_to` + to `negotiated`; this option combination is neither implemented + nor allowed. +- if the web server does not support Content Negotiation, setting + `po_link_to` to `negotiated` will produce a unusable website. + + +Server support +============== + +Apache +------ + +Using Apache `mod_negotiation` makes it really easy to have Apache +serve any page in the client's preferred language, if available. +This is the default Debian Apache configuration. + +When `usedirs` is enabled, one has to set `DirectoryIndex index` for +the wiki context. + +Setting `DefaultLanguage LL` (replace `LL` with your default MIME +language code) for the wiki context can help to ensure +`bla/page/index.en.html` is served as `Content-Language: LL`. + +lighttpd +-------- + +lighttpd unfortunately does not support content negotiation. + +**FIXME**: does `mod_magnet` provide the functionality needed to + emulate this? + + +Usage +===== + +Templates +--------- + +When `po_link_to` is not set to `negotiated`, one should replace some +occurrences of `BASEURL` with `HOMEPAGEURL` to get correct links to +the wiki homepage. + +The `ISTRANSLATION` and `ISTRANSLATABLE` variables can be used to +display things only on translatable or translation pages. + +### Display page's versions in other languages + +The `OTHERLANGUAGES` loop provides ways to display other languages' +versions of the same page, and the translations' status. + +One typically adds the following code to `templates/page.tmpl`: + + <TMPL_IF NAME="OTHERLANGUAGES"> + <div id="otherlanguages"> + <ul> + <TMPL_LOOP NAME="OTHERLANGUAGES"> + <li> + <a href="<TMPL_VAR NAME="URL">"><TMPL_VAR NAME="LANGUAGE"></a> + <TMPL_UNLESS NAME="MASTER"> + (<TMPL_VAR NAME="PERCENT"> %) + </TMPL_UNLESS> + </li> + </TMPL_LOOP> + </ul> + </div> + </TMPL_IF> + +The following variables are available inside the loop (for every page in): + +- `URL` - url to the page +- `CODE` - two-letters language code +- `LANGUAGE` - language name (as defined in `po_slave_languages`) +- `MASTER` - is true (1) if, and only if the page is a "master" page +- `PERCENT` - for "slave" pages, is set to the translation completeness, in percents + +### Display the current translation status + +The `PERCENTTRANSLATED` variable is set to the translation +completeness, expressed in percent, on "slave" pages. + +One can use it this way: + + <TMPL_IF NAME="ISTRANSLATION"> + <div id="percenttranslated"> + <TMPL_VAR NAME="PERCENTTRANSLATED"> + </div> + </TMPL_IF> + +Additional PageSpec tests +------------------------- + +This plugin enhances the regular [[ikiwiki/PageSpec]] syntax with some +additional tests that are documented [[here|ikiwiki/pagespec/po]]. + +Automatic PO file update +------------------------ + +Committing changes to a "master" page: + +1. updates the POT file and the PO files for the "slave" languages; + the updated PO files are then put under version control; +2. triggers a refresh of the corresponding HTML slave pages. + +Also, when the plugin has just been enabled, or when a page has just +been declared as being translatable, the needed POT and PO files are +created, and the PO files are checked into version control. + +Discussion pages and other sub-pages +------------------------------------ + +Discussion should happen in the language in which the pages are +written for real, *i.e.* the "master" one. If discussion pages are +enabled, "slave" pages therefore link to the "master" page's +discussion page. + +Likewise, "slave" pages are not supposed to have sub-pages; +[[WikiLinks|wikilink]] that appear on a "slave" page therefore link to +the master page's sub-pages. + +Translating +----------- + +One can edit the PO files using ikiwiki's CGI (a message-by-message +interface could also be implemented at some point). + +If [[tips/untrusted_git_push]] is setup, one can edit the PO files in one's +preferred `$EDITOR`, without needing to be online. + +TODO +==== + +Security checks +--------------- + +### Security history + +The only past security issues I could find in GNU gettext and po4a +are: + +- [CVE-2004-0966](http://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2004-0966), + *i.e.* [Debian bug #278283](http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=278283): + the autopoint and gettextize scripts in the GNU gettext package + 1.14 and later versions, as used in Trustix Secure Linux 1.5 + through 2.1 and other operating systems, allows local users to + overwrite files via a symlink attack on temporary files. +- [CVE-2007-4462](http://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2007-4462): + `lib/Locale/Po4a/Po.pm` in po4a before 0.32 allows local users to + overwrite arbitrary files via a symlink attack on the + gettextization.failed.po temporary file. + +**FIXME**: check whether this plugin would have been a possible attack +vector to exploit these vulnerabilities. + +Depending on my mood, the lack of found security issues can either +indicate that there are none, or reveal that no-one ever bothered to +find (and publish) them. + +### PO file features + +Can any sort of directives be put in po files that will cause mischief +(ie, include other files, run commands, crash gettext, whatever)? + +> No [documented](http://www.gnu.org/software/gettext/manual/gettext.html#PO-Files) +> directive is supposed to do so. [[--intrigeri]] + +### Running po4a on untrusted content + +Are there any security issues on running po4a on untrusted content? + +To say the least, this issue is not well covered, at least publicly: + +- the documentation does not talk about it; +- grep'ing the source code for `security` or `trust` gives no answer. + +On the other hand, a po4a developer answered my questions in +a convincing manner, stating that processing untrusted content was not +an initial goal, and analysing in detail the possible issues. + +#### Already checked + +- the core (`Po.pm`, `Transtractor.pm`) should be safe +- po4a source code was fully checked for other potential symlink + attacks, after discovery of one such issue +- the only external program run by the core is `diff`, in `Po.pm` (in + parts of its code we don't use) +- `Locale::gettext`: only used to display translated error messages +- Nicolas François "hopes" `DynaLoader` is safe, and has "no reason to + think that `Encode` is not safe" +- Nicolas François has "no reason to think that `Encode::Guess` is not + safe". The po plugin nevertheless avoids using it by defining the + input charset (`file_in_charset`) before asking `Transtractor` to + read any file. NB: this hack depends on po4a internals to stay + the same. + +#### To be checked + +##### Locale::Po4a modules + +The modules we want to use have to be checked, as not all are safe +(e.g. the LaTeX module's behaviour is changed by commands included in +the content); they may use regexps generated from the content. + +`Chooser.pm` only loads the plugin we tell it too: currently, this +means the `Text` module only. + +`Text` module (I checked the CVS version): + +- it does not run any external program +- only `do_paragraph()` builds regexp's that expand untrusted + variables; they seem safe to me, but someone more expert than me + will need to check. Joey? + + > Freaky code, but seems ok due to use of `quotementa`. + +##### Text::WrapI18N + +`Text::WrapI18N` can cause DoS (see the +[Debian bug #470250](http://bugs.debian.org/470250)), but it is +optional and we do not need the features it provides. + +It is loaded if available by `Locale::Po4a::Common`; looking at the +code, I'm not sure we can prevent this at all, but maybe some symbol +table manipulation tricks could work; overriding +`Locale::Po4a::Common::wrapi18n` may be easier. I'm no expert at all +in this field. Joey? [[--intrigeri]] + +> Update: Nicolas François suggests we add an option to po4a to +> disable it. It would do the trick, but only for people running +> a brand new po4a (probably too late for Lenny). Anyway, this option +> would have to take effect in a `BEGIN` / `eval` that I'm not +> familiar with. I can learn and do it, in case no Perl wizard +> volunteers to provide the po4a patch. [[--intrigeri]] + +>> That doesn't really need to be in a BEGIN. This patch moves it to +>> `import`, and makes this disable wrap18n: +>> `use Locale::Po4a::Common q{nowrapi18n}` --[[Joey]] + +<pre> +--- /usr/share/perl5/Locale/Po4a/Common.pm 2008-07-21 14:54:52.000000000 -0400 ++++ Common.pm 2008-11-11 18:27:34.000000000 -0500 +@@ -30,8 +30,16 @@ + use strict; + use warnings; + +-BEGIN { +- if (eval { require Text::WrapI18N }) { ++sub import { ++ my $class=shift; ++ my $wrapi18n=1; ++ if ($_[0] eq 'nowrapi18n') { ++ shift; ++ $wrapi18n=0; ++ } ++ $class->export_to_level(1, $class, @_); ++ ++ if ($wrapi18n && eval { require Text::WrapI18N }) { + + # Don't bother determining the wrap column if we cannot wrap. + my $col=$ENV{COLUMNS}; +</pre> + +##### Term::ReadKey + +`Term::ReadKey` is not a hard dependency in our case, *i.e.* po4a +works nicely without it. But the po4a Debian package recommends +`libterm-readkey-perl`, so it will probably be installed on most +systems using the po plugin. + +If `$ENV{COLUMNS}` is not set, `Locale::Po4a::Common` uses +`Term::ReadKey::GetTerminalSize()` to get the terminal size. How safe +is this? + +Part of `Term::ReadKey` is written in C. Depending on the runtime +platform, this function use ioctl, environment, or C library function +calls, and may end up running the `resize` command (without +arguments). + +IMHO, using Term::ReadKey has too far reaching implications for us to +be able to guarantee anything wrt. security. Since it is anyway of no +use in our case, I suggest we define `ENV{COLUMNS}` before loading +`Locale::Po4a::Common`, just to be on the safe side. Joey? +[[--intrigeri]] + +> Update: adding an option to disable `Text::WrapI18N`, as Nicolas +> François suggested, would as a bonus disable `Term::ReadKey` +> as well. [[--intrigeri]] + +### msgmerge + +`refreshpofiles()` runs this external program. A po4a developer +answered he does "not expect any security issues from it". + +### Fuzzing input + +I was not able to find any public information about gettext or po4a +having been tested with a fuzzing program, such as `zzuf` or `fusil`. +Moreover, some gettext parsers seem to be quite +[easy to crash](http://fusil.hachoir.org/trac/browser/trunk/fuzzers/fusil-gettext), +so it might be useful to bang msgmerge/po4a's heads against such +a program in order to easily detect some of the most obvious DoS. +[[--intrigeri]] + +> po4a was not fuzzy-tested, but according to one of its developers, +> "it would be really appreciated". [[--intrigeri]] + +Test conditions: + +- a 21M file containing 100 concatenated copies of all the files in my + `/usr/share/common-licenses/`; I had no existing PO file or + translated versions at hand, which renders these tests + quite incomplete. +- po4a was the Debian 0.34-2 package; the same tests were also run + after replacing the `Text` module with the CVS one (the core was not + changed in CVS since 0.34-2 was released), without any significant + difference in the results. +- Perl 5.10.0-16 + +#### po4a-gettextize + +`po4a-gettextize` uses more or less the same po4a features as our +`refreshpot` function. + +Without specifying an input charset, zzuf'ed `po4a-gettextize` quickly +errors out, complaining it was not able to detect the input charset; +it leaves no incomplete file on disk. + +So I had to pretend the input was in UTF-8, as does the po plugin. + +Two ways of crashing were revealed by this command-line: + + zzuf -vc -s 0:100 -r 0.1:0.5 \ + po4a-gettextize -f text -o markdown -M utf-8 -L utf-8 \ + -m LICENSES >/dev/null + +They are: + + Malformed UTF-8 character (UTF-16 surrogate 0xdcc9) in substitution iterator at /usr/share/perl5/Locale/Po4a/Po.pm line 1443. + Malformed UTF-8 character (fatal) at /usr/share/perl5/Locale/Po4a/Po.pm line 1443. + +and + + Malformed UTF-8 character (UTF-16 surrogate 0xdcec) in substitution (s///) at /usr/share/perl5/Locale/Po4a/Po.pm line 1443. + Malformed UTF-8 character (fatal) at /usr/share/perl5/Locale/Po4a/Po.pm line 1443. + +Perl seems to exit cleanly, and an incomplete PO file is written on +disk. I not sure whether if this is a bug in Perl or in `Po.pm`. + +> It's fairly standard perl behavior when fed malformed utf-8. As long as it doesn't +> crash ikiwiki, it's probably acceptable. Ikiwiki can do some similar things itself when fed malformed utf-8 (doesn't crash tho) --[[Joey]] + +#### po4a-translate + +`po4a-translate` uses more or less the same po4a features as our +`filter` function. + +Without specifying an input charset, same behaviour as +`po4a-gettextize`, so let's specify UTF-8 as input charset as of now. + + zzuf -cv \ + po4a-translate -d -f text -o markdown -M utf-8 -L utf-8 \ + -k 0 -m LICENSES -p LICENSES.fr.po -l test.fr + +... prints tons of occurences of the following error, but a complete +translated document is written (obviously with some weird chars +inside): + + Use of uninitialized value in string ne at /usr/share/perl5/Locale/Po4a/TransTractor.pm line 854. + Use of uninitialized value in string ne at /usr/share/perl5/Locale/Po4a/TransTractor.pm line 840. + Use of uninitialized value in pattern match (m//) at /usr/share/perl5/Locale/Po4a/Po.pm line 1002. + +While: + + zzuf -cv -s 0:10 -r 0.001:0.3 \ + po4a-translate -d -f text -o markdown -M utf-8 -L utf-8 \ + -k 0 -m LICENSES -p LICENSES.fr.po -l test.fr + +... seems to lose the fight, at the `readpo(LICENSES.fr.po)` step, +against some kind of infinite loop, deadlock, or any similar beast. +It does not seem to eat memory, though. + +Whatever format module is used does not change anything. This is thus +probably a bug in po4a's core or in a lib it depends on. + +The sub `read`, in `TransTractor.pm`, seems to be a good debugging +starting point. + +#### msgmerge + +`msgmerge` is run in our `refreshpofiles` function. I did not manage +to crash it with `zzuf`. + +gettext/po4a rough corners +-------------------------- + +- fix infinite loop when synchronizing two ikiwiki (when checkouts + live in different directories): say bla.fr.po has been updated in + repo2; pulling repo2 from repo1 seems to trigger a PO update, that + changes bla.fr.po in repo1; then pushing repo1 to repo2 triggers + a PO update, that changes bla.fr.po in repo2; etc.; quickly fixed in + `629968fc89bced6727981c0a1138072631751fee`, by disabling references + in Pot files. Using `Locale::Po4a::write_if_needed` might be + a cleaner solution. (warning: this function runs the external + `diff` program, have to check security) +- new translations created in the web interface must get proper + charset/encoding gettext metadata, else the next automatic PO update + removes any non-ascii chars; possible solution: put such metadata + into the Pot file, and let it propagate; should be fixed in + `773de05a7a1ee68d2bed173367cf5e716884945a`, time will tell. + +Better links +------------ + +### Page title in links + +To use the page titles set with the [[meta|plugins/meta]] plugin when +rendering links would be very much nicer, than the current +"filename.LL" format. This is actually a duplicate for +[[bugs/pagetitle_function_does_not_respect_meta_titles]]. + +Going to work on this in my `meta` branch. + +### Translation status in links + +See [[contrib/po]]. + +### Backlinks + +They are not updated when the source page changes (e.g. meta title). + +### Redirect after edit + +After editing master page, when using `po_link_to=negotiated`, one is +redirected to the page in her preferred language. Would be slightly +better to be redirected, in any case, to the just saved page. + +Page formats +------------ + +Markdown is well supported, great, but what about others? + +The [[po|plugins/po]] uses `Locale::Po4a::Text` for every page format; +this can be expected to work out of the box with most other wiki-like +formats supported by ikiwiki. Some of their ad-hoc syntax might be +parsed in a strange way, but the worst problems I can imagine would be +wrapping issues; e.g. there is code in po4a dedicated to prevent +re-wrapping the underlined Markdown headers. + +While it would be easy to better support formats such as [[html]] or +LaTeX, by using for each one the dedicated po4a module, this can be +problematic from a security point of view. + +**TODO**: test the more popular formats and write proper documentation +about it. + +Translation quality assurance +----------------------------- + +Modifying a PO file via the CGI must be forbidden if the new version +is not a valid PO file. As a bonus, check that it provides a more +complete translation than the existing one. + +A new `cansave` type of hook would be needed to implement this. + +Note: committing to the underlying repository is a way to bypass +this check. + +Creating new pages on the web +----------------------------- + +See [[contrib/po|contrib/po]]. + +Deleting/renaming pages +----------------------- + +- When a master page is renamed or deleted, its translations (and the + pot file?) must be renamed or deleted accordingly. +- Renaming a translation should be forbidden. + +Robustness tests +---------------- + +### Disabling the plugin + +- enabling the plugin with `po_translatable_pages` set +- enabling the plugin without `po_translatable_pages` set: **OK** +- disabling the plugin: **OK** + +### Changing the plugin config + +- adding existing pages to `po_translatable_pages`: **OK** +- removing existing pages from `po_translatable_pages`: **OK** +- adding a language to `po_slave_languages`: **OK** +- removing a language from `po_slave_languages`: **OK** +- changing `po_master_language`: **OK** +- replacing `po_master_language` with a language previously part of + `po_slave_languages`: needs two rebuilds, but **OK** (this is quite + a perverse test actually) + +### Creating pages + +- creating a master page via RCS: **OK** +- creating a master page via CGI: **OK** + +### Deleting pages + +- removing a master page via RCS +- removing a translation via RCS: **OK** +- removing a master page via CGI +- removing a translation via CGI: **OK** + +### Renaming pages + +- renaming a master page via RCS +- renaming a master page and its translations via RCS +- renaming a master page via CGI +- renaming a translation via RCS +- renaming a translation via CGI + +### Misc + +- general test with `usedirs` disabled: **OK** +- general test with `indexpages` enabled +- general test with `po_link_to=default` + +Documentation +------------- + +Maybe write separate documentation depending on the people it targets: +translators, wiki administrators, hackers. This plugin may be complex +enough to deserve this. @@ -0,0 +1,173 @@ +#!/usr/bin/perl +# -*- cperl-indent-level: 8; -*- +use warnings; +use strict; +use File::Temp qw{tempdir}; + +BEGIN { + unless (eval { require Locale::Po4a::Chooser }) { + eval q{ + use Test::More skip_all => "Locale::Po4a::Chooser::new is not available" + } + } + unless (eval { require Locale::Po4a::Po }) { + eval q{ + use Test::More skip_all => "Locale::Po4a::Po::new is not available" + } + } +} + +use Test::More tests => 65; + +BEGIN { use_ok("IkiWiki"); } + +my $msgprefix; + +my $dir = tempdir("ikiwiki-test-po.XXXXXXXXXX", + DIR => File::Spec->tmpdir, + CLEANUP => 1); + +### Init +%config=IkiWiki::defaultconfig(); +$config{srcdir} = "$dir/src"; +$config{destdir} = "$dir/dst"; +$config{discussion} = 0; +$config{po_master_language} = { code => 'en', + name => 'English' + }; +$config{po_slave_languages} = { + es => 'Castellano', + fr => "Français" + }; +$config{po_translatable_pages}='index or test1 or test2 or translatable'; +$config{po_link_to}='negotiated'; +IkiWiki::loadplugins(); +IkiWiki::checkconfig(); +ok(IkiWiki::loadplugin('po'), "po plugin loaded"); + +### seed %pagesources and %pagecase +$pagesources{'index'}='index.mdwn'; +$pagesources{'index.fr'}='index.fr.po'; +$pagesources{'index.es'}='index.es.po'; +$pagesources{'test1'}='test1.mdwn'; +$pagesources{'test1.fr'}='test1.fr.po'; +$pagesources{'test2'}='test2.mdwn'; +$pagesources{'test2.es'}='test2.es.po'; +$pagesources{'test2.fr'}='test2.fr.po'; +$pagesources{'test3'}='test3.mdwn'; +$pagesources{'test3.es'}='test3.es.mdwn'; +$pagesources{'translatable'}='translatable.mdwn'; +$pagesources{'translatable.fr'}='translatable.fr.po'; +$pagesources{'translatable.es'}='translatable.es.po'; +$pagesources{'nontranslatable'}='nontranslatable.mdwn'; +foreach my $page (keys %pagesources) { + $IkiWiki::pagecase{lc $page}=$page; +} + +### istranslatable/istranslation +# we run these tests twice because memoization attempts made them +# succeed once every two tries... +foreach (1, 2) { +ok(IkiWiki::Plugin::po::istranslatable('index'), "index is translatable"); +ok(IkiWiki::Plugin::po::istranslatable('/index'), "/index is translatable"); +ok(! IkiWiki::Plugin::po::istranslatable('index.fr'), "index.fr is not translatable"); +ok(! IkiWiki::Plugin::po::istranslatable('index.es'), "index.es is not translatable"); +ok(! IkiWiki::Plugin::po::istranslatable('/index.fr'), "/index.fr is not translatable"); +ok(! IkiWiki::Plugin::po::istranslation('index'), "index is not a translation"); +ok(IkiWiki::Plugin::po::istranslation('index.fr'), "index.fr is a translation"); +ok(IkiWiki::Plugin::po::istranslation('index.es'), "index.es is a translation"); +ok(IkiWiki::Plugin::po::istranslation('/index.fr'), "/index.fr is a translation"); +ok(IkiWiki::Plugin::po::istranslatable('test2'), "test2 is translatable"); +ok(! IkiWiki::Plugin::po::istranslation('test2'), "test2 is not a translation"); +ok(! IkiWiki::Plugin::po::istranslatable('test3'), "test3 is not translatable"); +ok(! IkiWiki::Plugin::po::istranslation('test3'), "test3 is not a translation"); +} + +### links +require IkiWiki::Render; + +sub refresh_n_scan(@) { + my @masterfiles_rel=@_; + foreach my $masterfile_rel (@masterfiles_rel) { + my $masterfile=srcfile($masterfile_rel); + IkiWiki::scan($masterfile_rel); + next unless IkiWiki::Plugin::po::istranslatable(pagename($masterfile_rel)); + my @pofiles=IkiWiki::Plugin::po::pofiles($masterfile); + IkiWiki::Plugin::po::refreshpot($masterfile); + IkiWiki::Plugin::po::refreshpofiles($masterfile, @pofiles); + map IkiWiki::scan(IkiWiki::abs2rel($_, $config{srcdir})), @pofiles; + } +} + +writefile('index.mdwn', $config{srcdir}, '[[translatable]] [[nontranslatable]]'); +writefile('translatable.mdwn', $config{srcdir}, '[[nontranslatable]]'); +writefile('nontranslatable.mdwn', $config{srcdir}, '[[/]] [[translatable]]'); + +$config{po_link_to}='negotiated'; +$msgprefix="links (po_link_to=negotiated)"; +refresh_n_scan('index.mdwn', 'translatable.mdwn', 'nontranslatable.mdwn'); +is_deeply(\@{$links{'index'}}, ['translatable', 'nontranslatable'], "$msgprefix index"); +is_deeply(\@{$links{'index.es'}}, ['translatable.es', 'nontranslatable'], "$msgprefix index.es"); +is_deeply(\@{$links{'index.fr'}}, ['translatable.fr', 'nontranslatable'], "$msgprefix index.fr"); +is_deeply(\@{$links{'translatable'}}, ['nontranslatable'], "$msgprefix translatable"); +is_deeply(\@{$links{'translatable.es'}}, ['nontranslatable'], "$msgprefix translatable.es"); +is_deeply(\@{$links{'translatable.fr'}}, ['nontranslatable'], "$msgprefix translatable.fr"); +is_deeply(\@{$links{'nontranslatable'}}, ['/', 'translatable', 'translatable.fr', 'translatable.es'], "$msgprefix nontranslatable"); + +$config{po_link_to}='current'; +$msgprefix="links (po_link_to=current)"; +refresh_n_scan('index.mdwn', 'translatable.mdwn', 'nontranslatable.mdwn'); +is_deeply(\@{$links{'index'}}, ['translatable', 'nontranslatable'], "$msgprefix index"); +is_deeply(\@{$links{'index.es'}}, [ map bestlink('index.es', $_), ('translatable.es', 'nontranslatable')], "$msgprefix index.es"); +is_deeply(\@{$links{'index.fr'}}, [ map bestlink('index.fr', $_), ('translatable.fr', 'nontranslatable')], "$msgprefix index.fr"); +is_deeply(\@{$links{'translatable'}}, [bestlink('translatable', 'nontranslatable')], "$msgprefix translatable"); +is_deeply(\@{$links{'translatable.es'}}, ['nontranslatable'], "$msgprefix translatable.es"); +is_deeply(\@{$links{'translatable.fr'}}, ['nontranslatable'], "$msgprefix translatable.fr"); +is_deeply(\@{$links{'nontranslatable'}}, ['/', 'translatable', 'translatable.fr', 'translatable.es'], "$msgprefix nontranslatable"); + +### targetpage +$config{usedirs}=0; +$msgprefix="targetpage (usedirs=0)"; +is(targetpage('test1', 'html'), 'test1.en.html', "$msgprefix test1"); +is(targetpage('test1.fr', 'html'), 'test1.fr.html', "$msgprefix test1.fr"); +$config{usedirs}=1; +$msgprefix="targetpage (usedirs=1)"; +is(targetpage('index', 'html'), 'index.en.html', "$msgprefix index"); +is(targetpage('index.fr', 'html'), 'index.fr.html', "$msgprefix index.fr"); +is(targetpage('test1', 'html'), 'test1/index.en.html', "$msgprefix test1"); +is(targetpage('test1.fr', 'html'), 'test1/index.fr.html', "$msgprefix test1.fr"); +is(targetpage('test3', 'html'), 'test3/index.html', "$msgprefix test3 (non-translatable page)"); +is(targetpage('test3.es', 'html'), 'test3.es/index.html', "$msgprefix test3.es (non-translatable page)"); + +### urlto -> index +$config{po_link_to}='current'; +$msgprefix="urlto (po_link_to=current)"; +is(urlto('', 'index'), './index.en.html', "$msgprefix index -> ''"); +is(urlto('', 'nontranslatable'), './../index.en.html', "$msgprefix nontranslatable -> ''"); +is(urlto('', 'translatable.fr'), './../index.fr.html', "$msgprefix translatable.fr -> ''"); +$config{po_link_to}='negotiated'; +$msgprefix="urlto (po_link_to=negotiated)"; +is(urlto('', 'index'), './', "$msgprefix index -> ''"); +is(urlto('', 'nontranslatable'), './../', "$msgprefix nontranslatable -> ''"); +is(urlto('', 'translatable.fr'), './../', "$msgprefix translatable.fr -> ''"); + +### bestlink +$config{po_link_to}='current'; +$msgprefix="bestlink (po_link_to=current)"; +is(bestlink('test1.fr', 'test2'), 'test2.fr', "$msgprefix test1.fr -> test2"); +is(bestlink('test1.fr', 'test2.es'), 'test2.es', "$msgprefix test1.fr -> test2.es"); +$config{po_link_to}='negotiated'; +$msgprefix="bestlink (po_link_to=negotiated)"; +is(bestlink('test1.fr', 'test2'), 'test2.fr', "$msgprefix test1.fr -> test2"); +is(bestlink('test1.fr', 'test2.es'), 'test2.es', "$msgprefix test1.fr -> test2.es"); + +### beautify_urlpath +$config{po_link_to}='default'; +$msgprefix="beautify_urlpath (po_link_to=default)"; +is(IkiWiki::beautify_urlpath('test1/index.en.html'), './test1/index.en.html', "$msgprefix test1/index.en.html"); +is(IkiWiki::beautify_urlpath('test1/index.fr.html'), './test1/index.fr.html', "$msgprefix test1/index.fr.html"); +$config{po_link_to}='negotiated'; +$msgprefix="beautify_urlpath (po_link_to=negotiated)"; +is(IkiWiki::beautify_urlpath('test1/index.html'), './test1/', "$msgprefix test1/index.html"); +is(IkiWiki::beautify_urlpath('test1/index.en.html'), './test1/', "$msgprefix test1/index.en.html"); +is(IkiWiki::beautify_urlpath('test1/index.fr.html'), './test1/', "$msgprefix test1/index.fr.html"); diff --git a/t/syntax.t b/t/syntax.t index d09d17f7f..8c96d1d84 100755 --- a/t/syntax.t +++ b/t/syntax.t @@ -6,7 +6,7 @@ use Test::More; my @progs="ikiwiki.in"; my @libs="IkiWiki.pm"; # monotone, external, amazon_s3 skipped since they need perl modules -push @libs, map { chomp; $_ } `find IkiWiki -type f -name \\*.pm | grep -v monotone.pm | grep -v external.pm | grep -v amazon_s3.pm`; +push @libs, map { chomp; $_ } `find IkiWiki -type f -name \\*.pm | grep -v monotone.pm | grep -v external.pm | grep -v amazon_s3.pm | grep -v po.pm`; push @libs, 'IkiWiki/Plugin/skeleton.pm.example'; plan(tests => (@progs + @libs)); diff --git a/underlays/basewiki/ikiwiki/pagespec/po.mdwn b/underlays/basewiki/ikiwiki/pagespec/po.mdwn new file mode 120000 index 000000000..255c3de9a --- /dev/null +++ b/underlays/basewiki/ikiwiki/pagespec/po.mdwn @@ -0,0 +1 @@ +../../../../doc/ikiwiki/pagespec/po.mdwn
\ No newline at end of file |