X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSolverGit.pm;h=ff8a49460b6fca00b0741f72f8431edec063d939;hb=80b887f29b2ec71d025b4c266a1c26314758994c;hp=5ac27988591c961a9335735727d8b3cf80f825a4;hpb=aa1e96cd44f6d5cd77a96648ac1f2dbcca9dc367;p=public-inbox.git

diff --git a/lib/PublicInbox/SolverGit.pm b/lib/PublicInbox/SolverGit.pm
index 5ac27988..ff8a4946 100644
--- a/lib/PublicInbox/SolverGit.pm
+++ b/lib/PublicInbox/SolverGit.pm
@@ -1,20 +1,20 @@
-# Copyright (C) 2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2019-2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # "Solve" blobs which don't exist in git code repositories by
 # searching inboxes for post-image blobs.
 
 # this emits a lot of debugging/tracing information which may be
-# publically viewed over HTTP(S).  Be careful not to expose
+# publicly viewed over HTTP(S).  Be careful not to expose
 # local filesystem layouts in the process.
 package PublicInbox::SolverGit;
 use strict;
 use warnings;
 use 5.010_001;
-use File::Temp 0.19 ();
+use File::Temp 0.19 (); # 0.19 for ->newdir
 use Fcntl qw(SEEK_SET);
 use PublicInbox::Git qw(git_unquote git_quote);
-use PublicInbox::MsgIter qw(msg_iter msg_part_text);
+use PublicInbox::MsgIter qw(msg_part_text);
 use PublicInbox::Qspawn;
 use PublicInbox::Tmpfile;
 use URI::Escape qw(uri_escape_utf8);
@@ -34,6 +34,12 @@ my $OID_MIN = 7;
 # work fairly.  Other PSGI servers may have trouble, though.
 my $MAX_PATCH = 9999;
 
+my $LF = qr!\r?\n!;
+my $ANY = qr![^\r\n]+!;
+my $MODE = '100644|120000|100755';
+my $FN = qr!(?:("?[^/\n]+/[^\r\n]+)|/dev/null)!;
+my %BAD_COMPONENT = ('' => 1, '.' => 1, '..' => 1);
+
 # di = diff info / a hashref with information about a diff ($di):
 # {
 #	oid_a => abbreviated pre-image oid,
@@ -42,7 +48,7 @@ my $MAX_PATCH = 9999;
 #	hdr_lines => string of various header lines for mode information
 #	mode_a => original mode of oid_a (string, not integer),
 #	ibx => PublicInbox::Inbox object containing the diff
-#	smsg => PublicInbox::SearchMsg object containing diff
+#	smsg => PublicInbox::Smsg object containing diff
 #	path_a => pre-image path
 #	path_b => post-image path
 #	n => numeric path of the patch (relative to worktree)
@@ -110,10 +116,6 @@ sub extract_diff ($$) {
 		$s =~ s/\r\n/\n/sg;
 	}
 
-	state $LF = qr!\r?\n!;
-	state $ANY = qr![^\r\n]+!;
-	state $MODE = '100644|120000|100755';
-	state $FN = qr!(?:("?[^/\n]+/[^\r\n]+)|/dev/null)!;
 
 	$s =~ m!( # $1 start header lines we save for debugging:
 
@@ -169,15 +171,14 @@ sub extract_diff ($$) {
 	my $patch = $9;
 
 	# don't care for leading 'a/' and 'b/'
-	my (undef, @a) = split(m{/}, git_unquote($path_a));
+	my (undef, @a) = split(m{/}, git_unquote($path_a)) if defined($path_a);
 	my (undef, @b) = split(m{/}, git_unquote($path_b));
 
 	# get rid of path-traversal attempts and junk patches:
 	# it's junk at best, an attack attempt at worse:
-	state $bad_component = { map { $_ => 1 } ('', '.', '..') };
-	foreach (@a, @b) { return if $bad_component->{$_} }
+	foreach (@a, @b) { return if $BAD_COMPONENT{$_} }
 
-	$di->{path_a} = join('/', @a);
+	$di->{path_a} = join('/', @a) if @a;
 	$di->{path_b} = join('/', @b);
 
 	my $path = ++$self->{tot};
@@ -228,14 +229,12 @@ sub find_extract_diffs ($$$) {
 		}
 	}
 
-	my $msgs = $srch->query($q, { relevance => 1 });
-
+	my $mset = $srch->mset($q, { relevance => 1 });
 	my $diffs = [];
-	foreach my $smsg (@$msgs) {
-		$ibx->smsg_mime($smsg) or next;
-		my $mime = delete $smsg->{mime};
-		msg_iter($mime, \&extract_diff,
-				[$self, $diffs, $pre, $post, $ibx, $smsg]);
+	for my $smsg (@{$srch->mset_to_smsg($ibx, $mset)}) {
+		my $eml = $ibx->smsg_eml($smsg) or next;
+		$eml->each_part(\&extract_diff,
+				[$self, $diffs, $pre, $post, $ibx, $smsg], 1);
 	}
 	@$diffs ? $diffs : undef;
 }
@@ -531,7 +530,8 @@ sub resolve_patch ($$) {
 	if (my $existing = solve_existing($self, $want)) {
 		my ($found_git, undef, $type, undef) = @$existing;
 		dbg($self, "found $cur_want in " .
-			join("\n", $found_git->pub_urls($self->{psgi_env})));
+			join(" ||\n\t",
+				$found_git->pub_urls($self->{psgi_env})));
 
 		if ($cur_want eq $self->{oid_want} || $type ne 'blob') {
 			eval { done($self, $existing) };
@@ -549,7 +549,7 @@ sub resolve_patch ($$) {
 
 		unshift @{$self->{patches}}, @$diffs;
 		dbg($self, "found $cur_want in ".
-			join("\n\t", map { di_url($self, $_) } @$diffs));
+			join(" ||\n\t", map { di_url($self, $_) } @$diffs));
 
 		# good, we can find a path to the oid we $want, now
 		# lets see if we need to apply more patches:
@@ -593,7 +593,7 @@ sub new {
 }
 
 # recreate $oid_want using $hints
-# hints keys: path_a, path_b, oid_a
+# hints keys: path_a, path_b, oid_a (note: `oid_b' is NOT a hint)
 # Calls {user_cb} with: [ ::Git object, oid_full, type, size, di (diff_info) ]
 # with found object, or undef if nothing was found
 # Calls {user_cb} with a string error on fatal errors