replace most uses of PublicInbox::MIME with Eml

[public-inbox.git] / lib / PublicInbox / V2Writable.pm

diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index 1c78ef24f2116ff1e7bc0135df5b0dbe70a84738..f599e0a03d80af5ec2bd64800c3ca2756ca6d80e 100644 (file)
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -9,7 +9,7 @@ use warnings;
 use base qw(PublicInbox::Lock);
 use 5.010_001;
 use PublicInbox::SearchIdxShard;
-use PublicInbox::MIME;
+use PublicInbox::Eml;
 use PublicInbox::Git;
 use PublicInbox::Import;
 use PublicInbox::MID qw(mids references);
@@ -120,6 +120,7 @@ sub new {
                last_commit => [], # git repo -> commit
        };
        $self->{shards} = count_shards($self) || nproc_shards($creat);
+       $self->{index_max_size} = $v2ibx->{index_max_size};
        bless $self, $class;
 }
 
@@ -356,9 +357,10 @@ sub content_ids ($) {
        my ($mime) = @_;
        my @cids = ( content_id($mime) );
 
+       # We still support Email::MIME, here, and
        # Email::MIME->as_string doesn't always round-trip, so we may
        # use a second content_id
-       my $rt = content_id(PublicInbox::MIME->new(\($mime->as_string)));
+       my $rt = content_id(PublicInbox::Eml->new(\($mime->as_string)));
        push @cids, $rt if $cids[0] ne $rt;
        \@cids;
 }
@@ -404,7 +406,7 @@ sub rewrite_internal ($$;$$$) {
                                next; # continue
                        }
                        my $orig = $$msg;
-                       my $cur = PublicInbox::MIME->new($msg);
+                       my $cur = PublicInbox::Eml->new($msg);
                        if (content_matches($cids, $cur)) {
                                $gone{$smsg->{num}} = [ $smsg, $cur, \$orig ];
                        }
@@ -730,9 +732,8 @@ sub fill_alternates ($$) {
 sub git_init {
        my ($self, $epoch) = @_;
        my $git_dir = "$self->{-inbox}->{inboxdir}/git/$epoch.git";
-       my @cmd = (qw(git init --bare -q), $git_dir);
-       PublicInbox::Import::run_die(\@cmd);
-       @cmd = (qw/git config/, "--file=$git_dir/config",
+       PublicInbox::Import::init_bare($git_dir);
+       my @cmd = (qw/git config/, "--file=$git_dir/config",
                        'include.path', '../../all.git/config');
        PublicInbox::Import::run_die(\@cmd);
        fill_alternates($self, $epoch);
@@ -842,7 +843,7 @@ sub content_exists ($$$) {
                        warn "broken smsg for $mid\n";
                        next;
                }
-               my $cur = PublicInbox::MIME->new($msg);
+               my $cur = PublicInbox::Eml->new($msg);
                return 1 if content_matches($cids, $cur);
 
                # XXX DEBUG_DIFF is experimental and may be removed
@@ -868,8 +869,9 @@ sub atfork_child {
 
 sub mark_deleted ($$$$) {
        my ($self, $sync, $git, $oid) = @_;
+       return if PublicInbox::SearchIdx::too_big($self, $git, $oid);
        my $msgref = $git->cat_file($oid);
-       my $mime = PublicInbox::MIME->new($$msgref);
+       my $mime = PublicInbox::Eml->new($$msgref);
        my $mids = mids($mime->header_obj);
        my $cid = content_id($mime);
        foreach my $mid (@$mids) {
@@ -900,7 +902,7 @@ sub reindex_oid_m ($$$$;$) {
        $self->{current_info} = "multi_mid $oid";
        my ($num, $mid0, $len);
        my $msgref = $git->cat_file($oid, \$len);
-       my $mime = PublicInbox::MIME->new($$msgref);
+       my $mime = PublicInbox::Eml->new($$msgref);
        my $mids = mids($mime->header_obj);
        my $cid = content_id($mime);
        die "BUG: reindex_oid_m called for <=1 mids" if scalar(@$mids) <= 1;
@@ -980,18 +982,6 @@ sub check_unindexed ($$$) {
        }
 }
 
-# reuse Msgmap to store num => oid mapping (rather than num => mid)
-sub multi_mid_q_new () {
-       my ($fh, $fn) = tempfile('multi_mid-XXXXXXX', EXLOCK => 0, TMPDIR => 1);
-       my $multi_mid = PublicInbox::Msgmap->new_file($fn, 1);
-       $multi_mid->{dbh}->do('PRAGMA synchronous = OFF');
-       # for Msgmap->DESTROY:
-       $multi_mid->{tmp_name} = $fn;
-       $multi_mid->{pid} = $$;
-       close $fh or die "failed to close $fn: $!";
-       $multi_mid
-}
-
 sub multi_mid_q_push ($$$) {
        my ($self, $sync, $oid) = @_;
        my $multi_mid = $sync->{multi_mid} //= PublicInbox::MultiMidQueue->new;
@@ -1006,10 +996,11 @@ sub multi_mid_q_push ($$$) {
 
 sub reindex_oid ($$$$) {
        my ($self, $sync, $git, $oid) = @_;
+       return if PublicInbox::SearchIdx::too_big($self, $git, $oid);
        my ($num, $mid0, $len);
        my $msgref = $git->cat_file($oid, \$len);
        return if $len == 0; # purged
-       my $mime = PublicInbox::MIME->new($$msgref);
+       my $mime = PublicInbox::Eml->new($$msgref);
        my $mids = mids($mime->header_obj);
        my $cid = content_id($mime);
 
@@ -1203,7 +1194,7 @@ sub unindex_oid ($$$;$) {
        my ($self, $git, $oid, $unindexed) = @_;
        my $mm = $self->{mm};
        my $msgref = $git->cat_file($oid);
-       my $mime = PublicInbox::MIME->new($msgref);
+       my $mime = PublicInbox::Eml->new($msgref);
        my $mids = mids($mime->header_obj);
        $mime = $msgref = undef;
        my $over = $self->{over};