reduce scope of mbox From_ line removal

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

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 44b05813f9a43e371068071ac9b2b666c275d555..579b85e3927cfd70df044db9ff9a224335e2a1d9 100644 (file)
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -58,6 +58,7 @@ sub new {
                ibx_ver => $version,
                indexlevel => $indexlevel,
        }, $class;
+       $self->{-set_indexlevel_once} = 1 if $indexlevel eq 'medium';
        $ibx->umask_prepare;
        if ($version == 1) {
                $self->{lock_path} = "$inboxdir/ssoma.lock";
@@ -274,22 +275,8 @@ sub index_diff ($$$) {
        index_text($self, join("\n", @xnq), 1, 'XNQ');
 }
 
-sub index_body ($$$) {
-       my ($self, $txt, $doc) = @_;
-       if ($doc) {
-               # does it look like a diff?
-               if ($txt =~ /^(?:diff|---|\+\+\+) /ms) {
-                       index_diff($self, $txt, $doc);
-               } else {
-                       index_text($self, $txt, 1, 'XNQ');
-               }
-       } else {
-               index_text($self, $txt, 0, 'XQUOT');
-       }
-}
-
 sub index_xapian { # msg_iter callback
-       my ($part, $depth, @idx) = @{$_[0]};
+       my $part = $_[0]->[0]; # ignore $depth and @idx
        my ($self, $doc) = @{$_[1]};
        my $ct = $part->content_type || 'text/plain';
        my $fn = $part->filename;
@@ -299,11 +286,24 @@ sub index_xapian { # msg_iter callback
 
        my ($s, undef) = msg_part_text($part, $ct);
        defined $s or return;
+       $_[0]->[0] = $part = undef; # free memory
 
        # split off quoted and unquoted blocks:
-       my @sections = split(/((?:^>[^\n]*\n)+)/sm, $s);
-       $part = $s = undef;
-       index_body($self, $_, /\A>/ ? 0 : $doc) for @sections;
+       my @sections = PublicInbox::MsgIter::split_quotes($s);
+       undef $s; # free memory
+       for my $txt (@sections) {
+               if ($txt =~ /\A>/) {
+                       index_text($self, $txt, 0, 'XQUOT');
+               } else {
+                       # does it look like a diff?
+                       if ($txt =~ /^(?:diff|---|\+\+\+) /ms) {
+                               index_diff($self, $txt, $doc);
+                       } else {
+                               index_text($self, $txt, 1, 'XNQ');
+                       }
+               }
+               undef $txt; # free memory
+       }
 }
 
 sub add_xapian ($$$$) {
@@ -496,13 +496,13 @@ sub index_git_blob_id {
 
 sub unindex_blob {
        my ($self, $mime) = @_;
-       my $mid = eval { mid_clean(mid_mime($mime)) };
+       my $mid = eval { mid_mime($mime) };
        $self->remove_message($mid) if defined $mid;
 }
 
 sub index_mm {
        my ($self, $mime) = @_;
-       my $mid = mid_clean(mid_mime($mime));
+       my $mid = mid_mime($mime);
        my $mm = $self->{mm};
        my $num;
 
@@ -533,7 +533,7 @@ sub index_mm {
 
 sub unindex_mm {
        my ($self, $mime) = @_;
-       $self->{mm}->mid_delete(mid_clean(mid_mime($mime)));
+       $self->{mm}->mid_delete(mid_mime($mime));
 }
 
 sub index_both {
@@ -551,13 +551,9 @@ sub unindex_both {
 
 sub do_cat_mail {
        my ($git, $blob, $sizeref) = @_;
-       my $mime = eval {
-               my $str = $git->cat_file($blob, $sizeref);
-               # fixup bugs from import:
-               $$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
-               PublicInbox::MIME->new($str);
-       };
-       $@ ? undef : $mime;
+       my $str = $git->cat_file($blob, $sizeref) or
+               die "BUG: $blob not found in $git->{git_dir}";
+       PublicInbox::MIME->new($str);
 }
 
 # called by public-inbox-index
@@ -602,7 +598,7 @@ sub read_log {
                                }
                                next;
                        }
-                       my $mime = do_cat_mail($git, $blob, \$bytes) or next;
+                       my $mime = do_cat_mail($git, $blob, \$bytes);
                        my $smsg = bless {}, 'PublicInbox::Smsg';
                        batch_adjust(\$max, $bytes, $batch_cb, $latest, ++$nr);
                        $smsg->{blob} = $blob;
@@ -623,7 +619,7 @@ sub read_log {
        close($log) or die "git log failed: \$?=$?";
        # get the leftovers
        foreach my $blob (keys %D) {
-               my $mime = do_cat_mail($git, $blob, \$bytes) or next;
+               my $mime = do_cat_mail($git, $blob, \$bytes);
                $del_cb->($self, $mime);
        }
        $batch_cb->($nr, $latest, $newest);
@@ -634,7 +630,7 @@ sub _git_log {
        my $git = $self->{git};
 
        if (index($range, '..') < 0) {
-               # don't show annoying git errrors to users who run -index
+               # don't show annoying git errors to users who run -index
                # on empty inboxes
                $git->qx(qw(rev-parse -q --verify), "$range^0");
                if ($?) {
@@ -842,20 +838,27 @@ sub begin_txn_lazy {
        });
 }
 
+# store 'indexlevel=medium' in v2 shard=0 and v1 (only one shard)
+# This metadata is read by Admin::detect_indexlevel:
+sub set_indexlevel {
+       my ($self) = @_;
+
+       if (!$self->{shard} && # undef or 0, not >0
+                       delete($self->{-set_indexlevel_once})) {
+               my $xdb = $self->{xdb};
+               my $level = $xdb->get_metadata('indexlevel');
+               if (!$level || $level ne 'medium') {
+                       $xdb->set_metadata('indexlevel', 'medium');
+               }
+       }
+}
+
 sub commit_txn_lazy {
        my ($self) = @_;
        delete $self->{txn} or return;
        $self->{-inbox}->with_umask(sub {
                if (my $xdb = $self->{xdb}) {
-
-                       # store 'indexlevel=medium' in v2 shard=0 and
-                       # v1 (only one shard)
-                       # This metadata is read by Admin::detect_indexlevel:
-                       if (!$self->{shard} # undef or 0, not >0
-                           && $self->{indexlevel} eq 'medium') {
-                               $xdb->set_metadata('indexlevel', 'medium');
-                       }
-
+                       set_indexlevel($self);
                        $xdb->commit_transaction;
                }
                $self->{over}->commit_lazy if $self->{over};