search: remove unnecessary abstractions and functionality

[public-inbox.git] / lib / PublicInbox / SearchIdx.pm

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 832d1cbfccc06aa3ab4e5948190b5856431bb5ac..316111bf0be4d8a8227be046a33867f6b8939fcf 100644 (file)
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -10,7 +10,7 @@ package PublicInbox::SearchIdx;
 use strict;
 use warnings;
 use Fcntl qw(:flock :DEFAULT);
-use Email::MIME;
+use PublicInbox::MIME;
 use Email::MIME::ContentType;
 $Email::MIME::ContentType::STRICT_PARAMS = 0;
 use base qw(PublicInbox::Search);
@@ -19,7 +19,6 @@ use PublicInbox::MsgIter;
 use Carp qw(croak);
 use POSIX qw(strftime);
 require PublicInbox::Git;
-*xpfx = *PublicInbox::Search::xpfx;
 
 use constant MAX_MID_SIZE => 244; # max term size - 1 in Xapian
 use constant {
@@ -155,17 +154,17 @@ sub add_message {
                if ($smsg) {
                        # convert a ghost to a regular message
                        # it will also clobber any existing regular message
-                       $doc_id = $smsg->doc_id;
+                       $doc_id = $smsg->{doc_id};
                        $old_tid = $smsg->thread_id;
                }
                $smsg = PublicInbox::SearchMsg->new($mime);
                my $doc = $smsg->{doc};
-               $doc->add_term(xpfx('mid') . $mid);
+               $doc->add_term('Q' . $mid);
 
                my $subj = $smsg->subject;
                if ($subj ne '') {
                        my $path = $self->subject_path($subj);
-                       $doc->add_term(xpfx('path') . id_compress($path));
+                       $doc->add_term('XPATH' . id_compress($path));
                }
 
                add_values($smsg, $bytes, $num);
@@ -289,15 +288,14 @@ sub link_message {
        my ($self, $smsg, $old_tid) = @_;
        my $doc = $smsg->{doc};
        my $mid = $smsg->mid;
-       my $mime = $smsg->mime;
+       my $mime = $smsg->{mime};
        my $hdr = $mime->header_obj;
-       my $refs = $hdr->header_raw('References');
-       my @refs = $refs ? ($refs =~ /<([^>]+)>/g) : ();
-       my $irt = $hdr->header_raw('In-Reply-To');
-       if (defined $irt) {
-               $irt = mid_clean($irt);
-               $irt = undef if $mid eq $irt;
-       }
+
+       # last References should be IRT, but some mail clients do things
+       # out of order, so trust IRT over References iff IRT exists
+       my @refs = ($hdr->header_raw('References'),
+                       $hdr->header_raw('In-Reply-To'));
+       @refs = ((join(' ', @refs)) =~ /<([^>]+)>/g);
 
        my $tid;
        if (@refs) {
@@ -305,15 +303,6 @@ sub link_message {
                my @orig_refs = @refs;
                @refs = ();
 
-               if (defined $irt) {
-                       # to check MAX_MID_SIZE
-                       push @orig_refs, $irt;
-
-                       # below, we will ensure IRT (if specified)
-                       # is the last References
-                       $uniq{$irt} = 1;
-               }
-
                # prevent circular references via References: here:
                foreach my $ref (@orig_refs) {
                        if (length($ref) > MAX_MID_SIZE) {
@@ -325,10 +314,6 @@ sub link_message {
                }
        }
 
-       # last References should be IRT, but some mail clients do things
-       # out of order, so trust IRT over References iff IRT exists
-       push @refs, $irt if defined $irt;
-
        if (@refs) {
                $smsg->{references} = '<'.join('> <', @refs).'>';
 
@@ -344,9 +329,9 @@ sub link_message {
                        merge_threads($self, $tid, $ptid);
                }
        } else {
-               $tid = $self->next_thread_id;
+               $tid = defined $old_tid ? $old_tid : $self->next_thread_id;
        }
-       $doc->add_term(xpfx('thread') . $tid);
+       $doc->add_term('G' . $tid);
 }
 
 sub index_blob {
@@ -400,7 +385,7 @@ sub do_cat_mail {
                my $str = $git->cat_file($blob, $sizeref);
                # fixup bugs from import:
                $$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
-               Email::MIME->new($str);
+               PublicInbox::MIME->new($str);
        };
        $@ ? undef : $mime;
 }
@@ -556,9 +541,9 @@ sub create_ghost {
 
        my $tid = $self->next_thread_id;
        my $doc = Search::Xapian::Document->new;
-       $doc->add_term(xpfx('mid') . $mid);
-       $doc->add_term(xpfx('thread') . $tid);
-       $doc->add_term(xpfx('type') . 'ghost');
+       $doc->add_term('Q' . $mid);
+       $doc->add_term('G' . $tid);
+       $doc->add_term('T' . 'ghost');
 
        my $smsg = PublicInbox::SearchMsg->wrap($doc, $mid);
        $self->{xdb}->add_document($doc);
@@ -569,15 +554,14 @@ sub create_ghost {
 sub merge_threads {
        my ($self, $winner_tid, $loser_tid) = @_;
        return if $winner_tid == $loser_tid;
-       my ($head, $tail) = $self->find_doc_ids('thread', $loser_tid);
-       my $thread_pfx = xpfx('thread');
+       my ($head, $tail) = $self->find_doc_ids('G' . $loser_tid);
        my $db = $self->{xdb};
 
        for (; $head != $tail; $head->inc) {
                my $docid = $head->get_docid;
                my $doc = $db->get_document($docid);
-               $doc->remove_term($thread_pfx . $loser_tid);
-               $doc->add_term($thread_pfx . $winner_tid);
+               $doc->remove_term('G' . $loser_tid);
+               $doc->add_term('G' . $winner_tid);
                $db->replace_document($docid, $doc);
        }
 }
@@ -634,7 +618,7 @@ sub with_umask {
        my $rv = eval { $cb->() };
        my $err = $@;
        umask $old;
-       die $err if $@;
+       die $err if $err;
        $rv;
 }