X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSolverGit.pm;h=dd95f40043b14c3cf230393845ed812bf898d489;hb=38226be5fd4c24885658e00d4ce87ccee663063d;hp=baad981de8f6fbbae60bb812d610be15858fb25e;hpb=587cc7c14629a59fd39c9c5b991f0676217722e0;p=public-inbox.git
diff --git a/lib/PublicInbox/SolverGit.pm b/lib/PublicInbox/SolverGit.pm
index baad981d..dd95f400 100644
--- a/lib/PublicInbox/SolverGit.pm
+++ b/lib/PublicInbox/SolverGit.pm
@@ -1,20 +1,19 @@
-# Copyright (C) 2019 all contributors
+# Copyright (C) 2019-2020 all contributors
# License: AGPL-3.0+
# "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 v5.10.1;
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 +33,12 @@ 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 +47,7 @@ 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 +115,6 @@ sub extract_diff ($$) {
$s =~ s/\r\n/\n/sg;
}
- state $LF = qr!\r?\n!;
- state $ANY = qr![^\r\n]+!;
- state $MODE = '100644|120000|100755';
- state $FN = qr!(?:("?[^/\n]+/[^\r\n]+)|/dev/null)!;
$s =~ m!( # $1 start header lines we save for debugging:
@@ -174,8 +175,7 @@ sub extract_diff ($$) {
# 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) if @a;
$di->{path_b} = join('/', @b);
@@ -228,12 +228,11 @@ sub find_extract_diffs ($$$) {
}
}
- my $msgs = $srch->query($q, { relevance => 1 });
-
+ my $mset = $srch->mset($q, { relevance => 1 });
my $diffs = [];
- foreach my $smsg (@$msgs) {
- $ibx->smsg_mime($smsg) or next;
- msg_iter(delete $smsg->{mime}, \&extract_diff,
+ for my $smsg (@{$srch->mset_to_smsg($ibx, $mset)}) {
+ my $eml = $ibx->smsg_eml($smsg) or next;
+ $eml->each_part(\&extract_diff,
[$self, $diffs, $pre, $post, $ibx, $smsg], 1);
}
@$diffs ? $diffs : undef;
@@ -270,7 +269,7 @@ sub prepare_index ($) {
my $in = tmpfile("update-index.$oid_full") or die "tmpfile: $!";
print $in "$mode_a $oid_full\t$path_a\0" or die "print: $!";
$in->flush or die "flush: $!";
- sysseek($in, 0, 0) or die "seek: $!";
+ sysseek($in, 0, SEEK_SET) or die "seek: $!";
dbg($self, 'preparing index');
my $rdr = { 0 => $in };
@@ -530,7 +529,8 @@ sub resolve_patch ($$) {
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) };
@@ -548,7 +548,7 @@ 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:
@@ -592,7 +592,7 @@ 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