From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on dcvr.yhbt.net X-Spam-Level: X-Spam-ASN: X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,BAYES_00 shortcircuit=no autolearn=ham autolearn_force=no version=3.4.0 Received: from localhost (dcvr.yhbt.net [127.0.0.1]) by dcvr.yhbt.net (Postfix) with ESMTP id 8EE3120D12 for ; Wed, 14 Jun 2017 00:14:50 +0000 (UTC) From: Eric Wong To: meta@public-inbox.org Subject: [PATCH 3/3] search: allow searching within mail diffs Date: Wed, 14 Jun 2017 00:14:48 +0000 Message-Id: <20170614001448.27098-4-e@80x24.org> In-Reply-To: <20170614001448.27098-1-e@80x24.org> References: <20170614001448.27098-1-e@80x24.org> List-Id: This can be tied into a repository browser to browse in-flight topics on a mailing list. --- lib/PublicInbox/Search.pm | 20 +++++-- lib/PublicInbox/SearchIdx.pm | 137 +++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 148 insertions(+), 9 deletions(-) diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm index 67837f4..c7c5455 100644 --- a/lib/PublicInbox/Search.pm +++ b/lib/PublicInbox/Search.pm @@ -75,6 +75,14 @@ my %prob_prefix = ( q => 'XQUOT', nq => 'XNQ', + dfn => 'XDFN', + dfa => 'XDFA', + dfb => 'XDFB', + dfhh => 'XDFHH', + dfctx => 'XDFCTX', + dfpre => 'XDFPRE', + dfpost => 'XDFPOST', + dfblob => 'XDFPRE XDFPOST', # default: '' => 'XMID S A XNQ XQUOT XFN', @@ -98,12 +106,16 @@ EOF 'a:' => 'match within the To, Cc, and From headers', 'tc:' => 'match within the To and Cc headers', 'bs:' => 'match within the Subject and body', + 'dfn:' => 'match filename from diff', + 'dfa:' => 'match diff removed (-) lines', + 'dfb:' => 'match diff added (+) lines', + 'dfhh:' => 'match diff hunk header context (usually a function name)', + 'dfctx:' => 'match diff context lines', + 'dfpre:' => 'match pre-image git blob ID', + 'dfpost:' => 'match post-image git blob ID', + 'dfblob:' => 'match either pre or post-image git blob ID', ); chomp @HELP; -# TODO: -# df (filenames from diff) -# da (diff a/ removed lines) -# db (diff b/ added lines) my $mail_query = Search::Xapian::Query->new('T' . 'mail'); diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm index 30d3fe9..9ba9437 100644 --- a/lib/PublicInbox/SearchIdx.pm +++ b/lib/PublicInbox/SearchIdx.pm @@ -28,8 +28,28 @@ use constant { PERM_GROUP => 0660, PERM_EVERYBODY => 0664, BATCH_BYTES => 1_000_000, + DEBUG => !!$ENV{DEBUG}, }; +my %GIT_ESC = ( + a => "\a", + b => "\b", + f => "\f", + n => "\n", + r => "\r", + t => "\t", + v => "\013", +); + +sub git_unquote ($) { + my ($s) = @_; + return $s unless ($s =~ /\A"(.*)"\z/); + $s = $1; + $s =~ s/\\([abfnrtv])/$GIT_ESC{$1}/g; + $s =~ s/\\([0-7]{1,3})/chr(oct($1))/ge; + $s; +} + sub new { my ($class, $inbox, $creat) = @_; my $git_dir = $inbox; @@ -134,11 +154,108 @@ sub index_users ($$) { $tg->increase_termpos; } +sub index_text_inc ($$$) { + my ($tg, $text, $pfx) = @_; + $tg->index_text($text, 1, $pfx); + $tg->increase_termpos; +} + +sub index_old_diff_fn { + my ($tg, $seen, $fa, $fb) = @_; + + # no renames or space support for traditional diffs, + # find the number of leading common paths to strip: + my @fa = split('/', $fa); + my @fb = split('/', $fb); + while (scalar(@fa) && scalar(@fb)) { + $fa = join('/', @fa); + $fb = join('/', @fb); + if ($fa eq $fb) { + index_text_inc($tg, $fa,'XDFN') unless $seen->{$fa}++; + return 1; + } + shift @fa; + shift @fb; + } + 0; +} + +sub index_diff ($$$) { + my ($tg, $lines, $doc) = @_; + my %seen; + my $in_diff; + foreach (@$lines) { + if ($in_diff && s/^ //) { # diff context + index_text_inc($tg, $_, 'XDFCTX'); + } elsif (/^-- $/) { # email signature begins + $in_diff = undef; + } elsif (m!^diff --git ("?a/.+) ("?b/.+)\z!) { + my ($fa, $fb) = ($1, $2); + my $fn = (split('/', git_unquote($fa), 2))[1]; + index_text_inc($tg, $fn, 'XDFN') unless $seen{$fn}++; + $fn = (split('/', git_unquote($fb), 2))[1]; + index_text_inc($tg, $fn, 'XDFN') unless $seen{$fn}++; + $in_diff = 1; + # traditional diff: + } elsif (m/^diff -(.+) (\S+) (\S+)$/) { + my ($opt, $fa, $fb) = ($1, $2, $3); + # only support unified: + next unless $opt =~ /[uU]/; + $in_diff = index_old_diff_fn($tg, \%seen, $fa, $fb); + } elsif (m!^--- ("?a/.+)!) { + my $fn = (split('/', git_unquote($1), 2))[1]; + index_text_inc($tg, $fn, 'XDFN') unless $seen{$fn}++; + $in_diff = 1; + } elsif (m!^\+\+\+ ("?b/.+)!) { + my $fn = (split('/', git_unquote($1), 2))[1]; + index_text_inc($tg, $fn, 'XDFN') unless $seen{$fn}++; + $in_diff = 1; + } elsif (/^--- (\S+)/) { + $in_diff = $1; + } elsif (defined $in_diff && /^\+\+\+ (\S+)/) { + $in_diff = index_old_diff_fn($tg, \%seen, $in_diff, $1); + } elsif ($in_diff && s/^\+//) { # diff added + index_text_inc($tg, $_, 'XDFB'); + } elsif ($in_diff && s/^-//) { # diff removed + index_text_inc($tg, $_, 'XDFA'); + } elsif (m!^index ([a-f0-9]+)\.\.([a-f0-9]+)!) { + my ($ba, $bb) = ($1, $2); + index_git_blob_id($doc, 'XDFPRE', $ba); + index_git_blob_id($doc, 'XDFPOST', $bb); + $in_diff = 1; + } elsif (/^@@ (?:\S+) (?:\S+) @@\s*$/) { + # traditional diff w/o -p + } elsif (/^@@ (?:\S+) (?:\S+) @@\s*(\S+.*)$/) { + # hunk header context + index_text_inc($tg, $1, 'XDFHH'); + # ignore the following lines: + } elsif (/^(?:dis)similarity index/) { + } elsif (/^(?:old|new) mode/) { + } elsif (/^(?:deleted|new) file mode/) { + } elsif (/^(?:copy|rename) (?:from|to) /) { + } elsif (/^(?:dis)?similarity index /) { + } elsif (/^\\ No newline at end of file/) { + } elsif (/^Binary files .* differ/) { + } elsif ($_ eq '') { + $in_diff = undef; + } else { + warn "non-diff line: $_\n" if DEBUG && $_ ne ''; + $in_diff = undef; + } + } +} + sub index_body ($$$) { - my ($tg, $lines, $inc) = @_; - $tg->index_text(join("\n", @$lines), $inc, $inc ? 'XNQ' : 'XQUOT'); - @$lines = (); + my ($tg, $lines, $doc) = @_; + my $txt = join("\n", @$lines); + $tg->index_text($txt, !!$doc, $doc ? 'XNQ' : 'XQUOT'); $tg->increase_termpos; + # does it look like a diff? + if ($doc && $txt =~ /^(?:diff|---|\+\+\+) /ms) { + $txt = undef; + index_diff($tg, $lines, $doc); + } + @$lines = (); } sub add_message { @@ -205,7 +322,7 @@ sub add_message { my @lines = split(/\n/, $body); while (defined(my $l = shift @lines)) { if ($l =~ /^>/) { - index_body($tg, \@orig, 1) if @orig; + index_body($tg, \@orig, $doc) if @orig; push @quot, $l; } else { index_body($tg, \@quot, 0) if @quot; @@ -213,7 +330,7 @@ sub add_message { } } index_body($tg, \@quot, 0) if @quot; - index_body($tg, \@orig, 1) if @orig; + index_body($tg, \@orig, $doc) if @orig; }); link_message($self, $smsg, $old_tid); @@ -339,6 +456,16 @@ sub index_blob { $self->add_message($mime, $bytes, $num, $blob); } +sub index_git_blob_id { + my ($doc, $pfx, $objid) = @_; + + my $len = length($objid); + for (my $len = length($objid); $len >= 7; ) { + $doc->add_term($pfx.$objid); + $objid = substr($objid, 0, --$len); + } +} + sub unindex_blob { my ($self, $mime) = @_; my $mid = eval { mid_clean(mid_mime($mime)) }; -- EW