diff options
Diffstat (limited to 'lib/PublicInbox/ExtMsg.pm')
| -rw-r--r-- | lib/PublicInbox/ExtMsg.pm | 186 |
1 files changed, 101 insertions, 85 deletions
diff --git a/lib/PublicInbox/ExtMsg.pm b/lib/PublicInbox/ExtMsg.pm index 6356c324..67ce0407 100644 --- a/lib/PublicInbox/ExtMsg.pm +++ b/lib/PublicInbox/ExtMsg.pm @@ -8,79 +8,77 @@ package PublicInbox::ExtMsg; use strict; use warnings; -use URI::Escape qw(uri_escape_utf8); use PublicInbox::Hval; use PublicInbox::MID qw/mid2path/; +use PublicInbox::WwwStream; # TODO: user-configurable our @EXT_URL = ( - 'http://mid.gmane.org/%s', - 'https://lists.debian.org/msgid-search/%s', # leading "//" denotes protocol-relative (http:// or https://) - '//mid.mail-archive.com/%s', '//marc.info/?i=%s', + '//mid.mail-archive.com/%s', + 'http://mid.gmane.org/%s', + 'https://lists.debian.org/msgid-search/%s', + '//docs.FreeBSD.org/cgi/mid.cgi?db=mid&id=%s', + 'https://www.w3.org/mid/%s', + 'http://www.postgresql.org/message-id/%s', + 'https://lists.debconf.org/cgi-lurker/keyword.cgi?'. + 'doc-url=/lurker&format=en.html&query=id:%s' ); sub ext_msg { my ($ctx) = @_; - my $pi_config = $ctx->{pi_config}; - my $listname = $ctx->{listname}; + my $cur = $ctx->{-inbox}; my $mid = $ctx->{mid}; - my $cgi = $ctx->{cgi}; - my $env = $cgi->{env}; eval { require PublicInbox::Search }; my $have_xap = $@ ? 0 : 1; - my (@nox, @pfx); + my (@nox, @ibx, @found); - foreach my $k (keys %$pi_config) { - $k =~ /\Apublicinbox\.([A-Z0-9a-z-]+)\.url\z/ or next; - my $list = $1; - next if $list eq $listname; + $ctx->{www}->{pi_config}->each_inbox(sub { + my ($other) = @_; + return if $other->{name} eq $cur->{name} || !$other->base_url; - my $git_dir = $pi_config->{"publicinbox.$list.mainrepo"}; - defined $git_dir or next; - - my $url = $pi_config->{"publicinbox.$list.url"}; - defined $url or next; - - $url =~ s!/+\z!!; - $url = PublicInbox::Hval::prurl($env, $url); + my $s = $other->search; + if (!$s) { + push @nox, $other; + return; + } # try to find the URL with Xapian to avoid forking - if ($have_xap) { - my $s; - my $doc_id = eval { - $s = PublicInbox::Search->new($git_dir); - $s->find_unique_doc_id('mid', $mid); - }; - if ($@) { - # xapian not configured for this repo - } else { - # maybe we found it! - return r302($url, $mid) if (defined $doc_id); - - # no point in trying the fork fallback if we - # know Xapian is up-to-date but missing the - # message in the current repo - push @pfx, { git_dir => $git_dir, url => $url }; - next; - } + my $doc_id = eval { $s->find_unique_doc_id('mid', $mid) }; + if ($@) { + # xapian not configured properly for this repo + push @nox, $other; + return; } - # queue up for forking after we've tried Xapian on all of them - push @nox, { git_dir => $git_dir, url => $url }; - } + # maybe we found it! + if (defined $doc_id) { + push @found, $other; + } else { + # no point in trying the fork fallback if we + # know Xapian is up-to-date but missing the + # message in the current repo + push @ibx, $other; + } + }); - # Xapian not installed or configured for some repos - my $path = "HEAD:" . mid2path($mid); + return exact($ctx, \@found, $mid) if @found; - foreach my $n (@nox) { - # TODO: reuse existing PublicInbox::Git objects to save forks - my $git = PublicInbox::Git->new($n->{git_dir}); - my (undef, $type, undef) = $git->check($path); - return r302($n->{url}, $mid) if ($type && $type eq 'blob'); + # Xapian not installed or configured for some repos, + # do a full MID check (this is expensive...): + if (@nox) { + my $path = mid2path($mid); + foreach my $other (@nox) { + my (undef, $type, undef) = $other->path_check($path); + + if ($type && $type eq 'blob') { + push @found, $other; + } + } } + return exact($ctx, \@found, $mid) if @found; # fall back to partial MID matching my $n_partial = 0; @@ -88,22 +86,15 @@ sub ext_msg { eval { require PublicInbox::Msgmap }; my $have_mm = $@ ? 0 : 1; - my $base_url = $cgi->base->as_string; if ($have_mm) { my $tmp_mid = $mid; - my $url; again: - $url = $base_url . $listname; - unshift @pfx, { git_dir => $ctx->{git_dir}, url => $url }; - foreach my $pfx (@pfx) { - my $git_dir = delete $pfx->{git_dir} or next; - my $mm = eval { PublicInbox::Msgmap->new($git_dir) }; - - $mm or next; + unshift @ibx, $cur; + foreach my $ibx (@ibx) { + my $mm = $ibx->mm or next; if (my $res = $mm->mid_prefixes($tmp_mid)) { $n_partial += scalar(@$res); - $pfx->{res} = $res; - push @partial, $pfx; + push @partial, [ $ibx, $res ]; } } # fixup common errors: @@ -113,51 +104,76 @@ again: } my $code = 404; - my $h = PublicInbox::Hval->new_msgid($mid, 1); - my $href = $h->as_href; + my $h = PublicInbox::Hval->new_msgid($mid); + my $href = $h->{href}; my $html = $h->as_html; - my $title = "Message-ID <$html> not found"; - my $s = "<html><head><title>$title</title>" . - "</head><body><pre><b>$title</b>\n"; - + my $title = "<$html> not found"; + my $s = "<pre>Message-ID <$html>\nnot found\n"; if ($n_partial) { $code = 300; my $es = $n_partial == 1 ? '' : 'es'; - $s.= "\n$n_partial partial match$es found:\n\n"; - foreach my $pfx (@partial) { - my $u = $pfx->{url}; - foreach my $m (@{$pfx->{res}}) { + $s .= "\n$n_partial partial match$es found:\n\n"; + my $cur_name = $cur->{name}; + foreach my $pair (@partial) { + my ($ibx, $res) = @$pair; + my $env = $ctx->{env} if $ibx->{name} eq $cur_name; + my $u = $ibx->base_url($env) or next; + foreach my $m (@$res) { my $p = PublicInbox::Hval->new_msgid($m); - my $r = $p->as_href; + my $r = $p->{href}; my $t = $p->as_html; - $s .= qq{<a\nhref="$u/$r/">$u/$t/</a>\n}; + $s .= qq{<a\nhref="$u$r/">$u$t/</a>\n}; } } } + my $ext = ext_urls($ctx, $mid, $href, $html); + if ($ext ne '') { + $s .= $ext; + $code = 300; + } + $ctx->{-html_tip} = $s .= '</pre>'; + $ctx->{-title_html} = $title; + $ctx->{-upfx} = '../'; + PublicInbox::WwwStream->response($ctx, $code); +} + +sub ext_urls { + my ($ctx, $mid, $href, $html) = @_; # Fall back to external repos if configured if (@EXT_URL && index($mid, '@') >= 0) { - $code = 300; - $s .= "\nPerhaps try an external site:\n\n"; + my $env = $ctx->{env}; + my $e = "\nPerhaps try an external site:\n\n"; foreach my $url (@EXT_URL) { my $u = PublicInbox::Hval::prurl($env, $url); my $r = sprintf($u, $href); my $t = sprintf($u, $html); - $s .= qq{<a\nhref="$r">$t</a>\n}; + $e .= qq{<a\nhref="$r">$t</a>\n}; } + return $e; } - $s .= '</pre></body></html>'; - - [$code, ['Content-Type'=>'text/html; charset=UTF-8'], [$s]]; + '' } -# Redirect to another public-inbox which is mapped by $pi_config -sub r302 { - my ($url, $mid) = @_; - $url .= '/' . uri_escape_utf8($mid) . '/'; - [ 302, - [ 'Location' => $url, 'Content-Type' => 'text/plain' ], - [ "Redirecting to\n$url\n" ] ] +sub exact { + my ($ctx, $found, $mid) = @_; + my $h = PublicInbox::Hval->new_msgid($mid); + my $href = $h->{href}; + my $html = $h->as_html; + my $title = "<$html> found in "; + my $end = @$found == 1 ? 'another inbox' : 'other inboxes'; + $ctx->{-title_html} = $title . $end; + $ctx->{-upfx} = '../'; + my $ext_urls = ext_urls($ctx, $mid, $href, $html); + my $code = (@$found == 1 && $ext_urls eq '') ? 200 : 300; + $ctx->{-html_tip} = join('', + "<pre>Message-ID: <$html>\nfound in $end:\n\n", + (map { + my $u = $_->base_url; + qq(<a\nhref="$u$href/">$u$html/</a>\n) + } @$found), + $ext_urls, '</pre>'); + PublicInbox::WwwStream->response($ctx, $code); } 1; |