[PATCH 2/3] search: support "patchid:" prefix (git patch-id --stable)

[Eric Wong <e@80x24.org>]

This allows easy searching via patch-id from a git commit.

Currently, abbreviations are not supported, and it seems
needless to support them since AFAIK (git) doesn't generate
nor resolve abbreviated patch-ids anywhere.
---
 TODO                         |  3 ---
 lib/PublicInbox/Search.pm    |  5 +++--
 lib/PublicInbox/SearchIdx.pm | 15 +++++++++++++++
 t/extsearch.t                |  7 ++++++-
 t/v2mda.t                    | 10 ++++++++--
 5 files changed, 32 insertions(+), 8 deletions(-)

diff --git a/TODO b/TODO
index 5be4b5e3..43eee063 100644
--- a/TODO
+++ b/TODO
@@ -137,9 +137,6 @@ all need to be considered for everything we introduce)
 * make "git cat-file --batch" detect unlinked packfiles so we don't
   have to restart processes (very long-term)
 
-* support searching based on `git-patch-id --stable` to improve
-  bidirectional mapping of commits <=> emails
-
 * linter to check validity of config file
 
 * linter option and WWW endpoint to graph relationships and flows
diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index 523003b3..6f9fdde1 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2015-2021 all contributors <meta@public-inbox.org>
+# Copyright (C) all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 # based on notmuch, but with no concept of folders, files or flags
 #
@@ -118,9 +118,10 @@ my %bool_pfx_external = (
 	dfpre => 'XDFPRE',
 	dfpost => 'XDFPOST',
 	dfblob => 'XDFPRE XDFPOST',
+	patchid => 'XDFID',
 );
 
-my $non_quoted_body = 'XNQ XDFN XDFA XDFB XDFHH XDFCTX XDFPRE XDFPOST';
+my $non_quoted_body = 'XNQ XDFN XDFA XDFB XDFHH XDFCTX XDFPRE XDFPOST XDFID';
 my %prob_prefix = (
 	# for mairix compatibility
 	s => 'S',
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 50e26050..53ec23a5 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -18,6 +18,7 @@ use PublicInbox::MsgIter;
 use PublicInbox::IdxStack;
 use Carp qw(croak carp);
 use POSIX qw(strftime);
+use Fcntl qw(SEEK_SET);
 use Time::Local qw(timegm);
 use PublicInbox::OverIdx;
 use PublicInbox::Spawn qw(spawn);
@@ -349,6 +350,20 @@ sub index_xapian { # msg_iter callback
 	defined $s or return;
 	$_[0]->[0] = $part = undef; # free memory
 
+	if ($s =~ /^(?:diff|---|\+\+\+) /ms) {
+		open(my $fh, '+>:utf8', undef) or die "open: $!";
+		open(my $eh, '+>', undef) or die "open: $!";
+		$fh->autoflush(1);
+		print $fh $s or die "print: $!";
+		sysseek($fh, 0, SEEK_SET) or die "sysseek: $!";
+		my $id = ($self->{ibx} // $self->{eidx})->git->qx(
+						[qw(patch-id --stable)],
+						{}, { 0 => $fh, 2 => $eh });
+		$id =~ /\A([a-f0-9]{40,})/ and $doc->add_term('XDFID'.$1);
+		seek($eh, 0, SEEK_SET) or die "seek: $!";
+		while (<$eh>) { warn $_ }
+	}
+
 	# split off quoted and unquoted blocks:
 	my @sections = PublicInbox::MsgIter::split_quotes($s);
 	undef $s; # free memory
diff --git a/t/extsearch.t b/t/extsearch.t
index 09cbdabe..2d7375d6 100644
--- a/t/extsearch.t
+++ b/t/extsearch.t
@@ -314,7 +314,12 @@ if ('reindex catches missed messages') {
 	is($new->{subject}, $eml->header('Subject'), 'new message added');
 
 	$es->{xdb}->reopen;
-	my $mset = $es->mset("mid:$new->{mid}");
+	# git patch-id --stable <t/data/0001.patch | awk '{print $1}'
+	my $patchid = '91ee6b761fc7f47cad9f2b09b10489f313eb5b71';
+	my $mset = $es->search->mset("patchid:$patchid");
+	is($mset->size, 1, 'patchid search works');
+
+	$mset = $es->mset("mid:$new->{mid}");
 	is($mset->size, 1, 'previously unseen, now indexed in Xapian');
 
 	ok($im->remove($eml), 'remove new message from v2 inbox');
diff --git a/t/v2mda.t b/t/v2mda.t
index 3dfc569e..8f2f335d 100644
--- a/t/v2mda.t
+++ b/t/v2mda.t
@@ -1,7 +1,8 @@
-# Copyright (C) 2018-2021 all contributors <meta@public-inbox.org>
+#!perl -w
+# Copyright (C) all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+use v5.10.1;
 use strict;
-use warnings;
 use Test::More;
 use Fcntl qw(SEEK_SET);
 use Cwd;
@@ -88,6 +89,11 @@ is($eml->as_string, $mime->as_string, 'injected message');
 	$pre = $ibx->search->mset_to_smsg($ibx, $pre);
 	$post = $ibx->search->mset_to_smsg($ibx, $post);
 	is($post->[0]->{blob}, $pre->[0]->{blob}, 'same message in both cases');
+
+	# git patch-id --stable <t/data/0001.patch | awk '{print $1}'
+	my $patchid = '91ee6b761fc7f47cad9f2b09b10489f313eb5b71';
+	my $mset = $ibx->search->mset("patchid:$patchid");
+	is($mset->size, 1, 'patchid search works');
 }
 
 done_testing();