www: drop --subject from "git send-email" instructions

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

diff --git a/lib/PublicInbox/LeiDedupe.pm b/lib/PublicInbox/LeiDedupe.pm
index 58eee53314777ecac2801762fd52e3bb274416b3..32f99cd0a30c3eafeed64940c7a0bd21940861ad 100644 (file)
--- a/lib/PublicInbox/LeiDedupe.pm
+++ b/lib/PublicInbox/LeiDedupe.pm
@@ -3,8 +3,8 @@
 package PublicInbox::LeiDedupe;
 use strict;
 use v5.10.1;
-use PublicInbox::SharedKV;
-use PublicInbox::ContentHash qw(content_hash);
+use PublicInbox::ContentHash qw(content_hash git_sha);
+use Digest::SHA ();
 
 # n.b. mutt sets most of these headers not sure about Bytes
 our @OID_IGNORE = qw(Status X-Status Content-Length Lines Bytes);
@@ -18,12 +18,7 @@ sub _regen_oid ($) {
                push @stash, [ $k, \@v ];
                $eml->header_set($k); # restore below
        }
-       my $dig = Digest::SHA->new(1); # XXX SHA256 later
-       my $buf = $eml->as_string;
-       $dig->add('blob '.length($buf)."\0");
-       $dig->add($buf);
-       undef $buf;
-
+       my $dig = git_sha(1, $eml);
        for my $kv (@stash) { # restore stashed headers
                my ($k, @v) = @$kv;
                $eml->header_set($k, @v);
@@ -43,11 +38,11 @@ sub smsg_hash ($) {
 }
 
 # the paranoid option
-sub dedupe_oid () {
-       my $skv = PublicInbox::SharedKV->new;
-       ($skv, sub { # may be called in a child process
-               my ($eml, $oid) = @_;
-               $skv->set_maybe(_oidbin($oid) // _regen_oid($eml), '');
+sub dedupe_oid ($) {
+       my ($skv) = @_;
+       (sub { # may be called in a child process
+               my ($eml, $oidhex) = @_;
+               $skv->set_maybe(_oidbin($oidhex) // _regen_oid($eml), '');
        }, sub {
                my ($smsg) = @_;
                $skv->set_maybe(_oidbin($smsg->{blob}), '');
@@ -55,12 +50,12 @@ sub dedupe_oid () {
 }
 
 # dangerous if there's duplicate messages with different Message-IDs
-sub dedupe_mid () {
-       my $skv = PublicInbox::SharedKV->new;
-       ($skv, sub { # may be called in a child process
-               my ($eml, $oid) = @_;
-               # TODO: lei will support non-public messages w/o Message-ID
-               my $mid = $eml->header_raw('Message-ID') // _oidbin($oid) //
+sub dedupe_mid ($) {
+       my ($skv) = @_;
+       (sub { # may be called in a child process
+               my ($eml, $oidhex) = @_;
+               # lei supports non-public drafts w/o Message-ID
+               my $mid = $eml->header_raw('Message-ID') // _oidbin($oidhex) //
                        content_hash($eml);
                $skv->set_maybe($mid, '');
        }, sub {
@@ -73,10 +68,10 @@ sub dedupe_mid () {
 }
 
 # our default deduplication strategy (used by v2, also)
-sub dedupe_content () {
-       my $skv = PublicInbox::SharedKV->new;
-       ($skv, sub { # may be called in a child process
-               my ($eml) = @_; # oid = $_[1], ignored
+sub dedupe_content ($) {
+       my ($skv) = @_;
+       (sub { # may be called in a child process
+               my ($eml) = @_; # $oidhex = $_[1], ignored
                $skv->set_maybe(content_hash($eml), '');
        }, sub {
                my ($smsg) = @_;
@@ -86,25 +81,31 @@ sub dedupe_content () {
 
 # no deduplication at all
 sub true { 1 }
-sub dedupe_none () { (undef, \&true, \&true) }
+sub dedupe_none ($) { (\&true, \&true) }
 
 sub new {
-       my ($cls, $lei, $dst) = @_;
+       my ($cls, $lei) = @_;
        my $dd = $lei->{opt}->{dedupe} // 'content';
+       my $dst = $lei->{ovv}->{dst};
 
        # allow "none" to bypass Eml->new if writing to directory:
        return if ($dd eq 'none' && substr($dst // '', -1) eq '/');
-
-       my $dd_new = $cls->can("dedupe_$dd") //
-                       die "unsupported dedupe strategy: $dd\n";
-       bless [ $dd_new->() ], $cls; # [ $skv, $cb ]
+       my $m = "dedupe_$dd";
+       $cls->can($m) or die "unsupported dedupe strategy: $dd\n";
+       my $skv;
+       if ($dd ne 'none') {
+               require PublicInbox::SharedKV;
+               $skv = PublicInbox::SharedKV->new;
+       }
+       # [ $skv, $eml_cb, $smsg_cb, "dedupe_$dd" ]
+       bless [ $skv, undef, undef, $m ], $cls;
 }
 
-# returns true on unseen messages according to the deduplication strategy,
-# returns false if seen
+# returns true on seen messages according to the deduplication strategy,
+# returns false if unseen
 sub is_dup {
-       my ($self, $eml, $oid) = @_;
-       !$self->[1]->($eml, $oid);
+       my ($self, $eml, $smsg) = @_;
+       !$self->[1]->($eml, $smsg ? $smsg->{blob} : undef);
 }
 
 sub is_smsg_dup {
@@ -115,13 +116,20 @@ sub is_smsg_dup {
 sub prepare_dedupe {
        my ($self) = @_;
        my $skv = $self->[0];
+       $self->[1] or @$self[1,2] = $self->can($self->[3])->($skv);
        $skv ? $skv->dbh : undef;
 }
 
 sub pause_dedupe {
        my ($self) = @_;
-       my $skv = $self->[0];
+       my $skv = $self->[0] or return;
+       $skv->dbh_release;
        delete($skv->{dbh}) if $skv;
 }
 
+sub has_entries {
+       my $skv = $_[0]->[0] or return undef;
+       $skv->has_entries;
+}
+
 1;