www: avoid `state' usage to perform allocations up-front

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

diff --git a/lib/PublicInbox/SolverGit.pm b/lib/PublicInbox/SolverGit.pm
index eab8459bc341935545b2e28b4e92ce0a22958b93..f881e16e41c89cfdd74515401ad2b164394dde22 100644 (file)
--- a/lib/PublicInbox/SolverGit.pm
+++ b/lib/PublicInbox/SolverGit.pm
@@ -1,17 +1,17 @@
-# 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);
@@ -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,
@@ -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:
 
@@ -155,7 +157,7 @@ sub extract_diff ($$) {
                # the meat of the diff, including "^\\No newline ..."
                # We also allow for totally blank lines w/o leading spaces,
                # because git-apply(1) handles that case, too
-               (?:^(?:[\@\+\x20\-\\][^\r\n]*|)$LF)+
+               (?:^(?:[\@\+\x20\-\\][^\n]*|)$LF)+
        )!smx or return;
 
        my $di = {
@@ -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};
@@ -233,9 +234,8 @@ sub find_extract_diffs ($$$) {
        my $diffs = [];
        foreach my $smsg (@$msgs) {
                $ibx->smsg_mime($smsg) or next;
-               my $mime = delete $smsg->{mime};
-               msg_iter($mime, \&extract_diff,
-                               [$self, $diffs, $pre, $post, $ibx, $smsg]);
+               msg_iter(delete $smsg->{mime}, \&extract_diff,
+                               [$self, $diffs, $pre, $post, $ibx, $smsg], 1);
        }
        @$diffs ? $diffs : undef;
 }
@@ -531,7 +531,8 @@ sub resolve_patch ($$) {
        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 +550,7 @@ 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: