diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl index 2594a4badb..7fef19fe59 100755 --- a/gitweb/gitweb.perl +++ b/gitweb/gitweb.perl @@ -788,6 +788,38 @@ sub check_loadavg { # ====================================================================== # input validation and dispatch +# Various hash size-related values. +my $sha1_len = 40; +my $sha256_extra_len = 24; +my $sha256_len = $sha1_len + $sha256_extra_len; + +# A regex matching $len hex characters. $len may be a range (e.g. 7,64). +sub oid_nlen_regex { + my $len = shift; + my $hchr = qr/[0-9a-fA-F]/; + return qr/(?:(?:$hchr){$len})/; +} + +# A regex matching two sets of $nlen hex characters, prefixed by the literal +# string $prefix and with the literal string $infix between them. +sub oid_nlen_prefix_infix_regex { + my $nlen = shift; + my $prefix = shift; + my $infix = shift; + + my $rx = oid_nlen_regex($nlen); + + return qr/^\Q$prefix\E$rx\Q$infix\E$rx$/; +} + +# A regex matching a valid object ID. +our $oid_regex; +{ + my $x = oid_nlen_regex($sha1_len); + my $y = oid_nlen_regex($sha256_extra_len); + $oid_regex = qr/(?:$x(?:$y)?)/; +} + # input parameters can be collected from a variety of sources (presently, CGI # and PATH_INFO), so we define an %input_params hash that collects them all # together during validation: this allows subsequent uses (e.g. href()) to be @@ -1516,7 +1548,7 @@ sub is_valid_refname { return undef unless defined $input; # textual hashes are O.K. - if ($input =~ m/^[0-9a-fA-F]{40}$/) { + if ($input =~ m/^$oid_regex$/) { return 1; } # it must be correct pathname @@ -2028,6 +2060,9 @@ sub file_type_long { sub format_log_line_html { my $line = shift; + # Potentially abbreviated OID. + my $regex = oid_nlen_regex("7,64"); + $line = esc_html($line, -nbsp=>1); $line =~ s{ \b @@ -2037,10 +2072,10 @@ sub format_log_line_html { (?'; } # match - if ($line =~ m/^index [0-9a-fA-F]{40},[0-9a-fA-F]{40}/) { + if ($line =~ oid_nlen_prefix_infix_regex($sha1_len, "index ", ",") | + $line =~ oid_nlen_prefix_infix_regex($sha256_len, "index ", ",")) { # can match only for combined diff $line = 'index '; for (my $i = 0; $i < $diffinfo->{'nparents'}; $i++) { @@ -2308,7 +2344,8 @@ sub format_extended_diff_header_line { $line .= '0' x 7; } - } elsif ($line =~ m/^index [0-9a-fA-F]{40}..[0-9a-fA-F]{40}/) { + } elsif ($line =~ oid_nlen_prefix_infix_regex($sha1_len, "index ", "..") | + $line =~ oid_nlen_prefix_infix_regex($sha256_len, "index ", "..")) { # can match only for ordinary diff my ($from_link, $to_link); if ($from->{'href'}) { @@ -2834,7 +2871,7 @@ sub git_get_hash_by_path { } #'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa panic.c' - $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t/; + $line =~ m/^([0-9]+) (.+) ($oid_regex)\t/; if (defined $type && $type ne $2) { # type doesn't match return undef; @@ -3333,7 +3370,7 @@ sub git_get_references { while (my $line = <$fd>) { chomp $line; - if ($line =~ m!^([0-9a-fA-F]{40})\srefs/($type.*)$!) { + if ($line =~ m!^($oid_regex)\srefs/($type.*)$!) { if (defined $refs{$1}) { push @{$refs{$1}}, $2; } else { @@ -3407,7 +3444,7 @@ sub parse_tag { $tag{'id'} = $tag_id; while (my $line = <$fd>) { chomp $line; - if ($line =~ m/^object ([0-9a-fA-F]{40})$/) { + if ($line =~ m/^object ($oid_regex)$/) { $tag{'object'} = $1; } elsif ($line =~ m/^type (.+)$/) { $tag{'type'} = $1; @@ -3451,15 +3488,15 @@ sub parse_commit_text { } my $header = shift @commit_lines; - if ($header !~ m/^[0-9a-fA-F]{40}/) { + if ($header !~ m/^$oid_regex/) { return; } ($co{'id'}, my @parents) = split ' ', $header; while (my $line = shift @commit_lines) { last if $line eq "\n"; - if ($line =~ m/^tree ([0-9a-fA-F]{40})$/) { + if ($line =~ m/^tree ($oid_regex)$/) { $co{'tree'} = $1; - } elsif ((!defined $withparents) && ($line =~ m/^parent ([0-9a-fA-F]{40})$/)) { + } elsif ((!defined $withparents) && ($line =~ m/^parent ($oid_regex)$/)) { push @parents, $1; } elsif ($line =~ m/^author (.*) ([0-9]+) (.*)$/) { $co{'author'} = to_utf8($1); @@ -3591,7 +3628,7 @@ sub parse_difftree_raw_line { # ':100644 100644 03b218260e99b78c6df0ed378e59ed9205ccc96d 3b93d5e7cc7f7dd4ebed13a5cc1a4ad976fc94d8 M ls-files.c' # ':100644 100644 7f9281985086971d3877aca27704f2aaf9c448ce bc190ebc71bbd923f2b728e505408f5e54bd073a M rev-tree.c' - if ($line =~ m/^:([0-7]{6}) ([0-7]{6}) ([0-9a-fA-F]{40}) ([0-9a-fA-F]{40}) (.)([0-9]{0,3})\t(.*)$/) { + if ($line =~ m/^:([0-7]{6}) ([0-7]{6}) ($oid_regex) ($oid_regex) (.)([0-9]{0,3})\t(.*)$/) { $res{'from_mode'} = $1; $res{'to_mode'} = $2; $res{'from_id'} = $3; @@ -3606,7 +3643,7 @@ sub parse_difftree_raw_line { } # '::100755 100755 100755 60e79ca1b01bc8b057abe17ddab484699a7f5fdb 94067cc5f73388f33722d52ae02f44692bc07490 94067cc5f73388f33722d52ae02f44692bc07490 MR git-gui/git-gui.sh' # combined diff (for merge commit) - elsif ($line =~ s/^(::+)((?:[0-7]{6} )+)((?:[0-9a-fA-F]{40} )+)([a-zA-Z]+)\t(.*)$//) { + elsif ($line =~ s/^(::+)((?:[0-7]{6} )+)((?:$oid_regex )+)([a-zA-Z]+)\t(.*)$//) { $res{'nparents'} = length($1); $res{'from_mode'} = [ split(' ', $2) ]; $res{'to_mode'} = pop @{$res{'from_mode'}}; @@ -3616,7 +3653,7 @@ sub parse_difftree_raw_line { $res{'to_file'} = unquote($5); } # 'c512b523472485aef4fff9e57b229d9d243c967f' - elsif ($line =~ m/^([0-9a-fA-F]{40})$/) { + elsif ($line =~ m/^($oid_regex)$/) { $res{'commit'} = $1; } @@ -3644,7 +3681,7 @@ sub parse_ls_tree_line { if ($opts{'-l'}) { #'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa 16717 panic.c' - $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40}) +(-|[0-9]+)\t(.+)$/s; + $line =~ m/^([0-9]+) (.+) ($oid_regex) +(-|[0-9]+)\t(.+)$/s; $res{'mode'} = $1; $res{'type'} = $2; @@ -3657,7 +3694,7 @@ sub parse_ls_tree_line { } } else { #'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa panic.c' - $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t(.+)$/s; + $line =~ m/^([0-9]+) (.+) ($oid_regex)\t(.+)$/s; $res{'mode'} = $1; $res{'type'} = $2; @@ -4799,7 +4836,7 @@ sub fill_from_file_info { sub is_deleted { my $diffinfo = shift; - return $diffinfo->{'to_id'} eq ('0' x 40); + return $diffinfo->{'to_id'} eq ('0' x 40) || $diffinfo->{'to_id'} eq ('0' x 64); } # does patch correspond to [previous] difftree raw line @@ -6285,7 +6322,7 @@ sub git_search_changes { -class => "list subject"}, chop_and_escape_str($co{'title'}, 50) . "
"); } elsif (defined $set{'to_id'}) { - next if ($set{'to_id'} =~ m/^0{40}$/); + next if is_deleted(\%set); print $cgi->a({-href => href(action=>"blob", hash_base=>$co{'id'}, hash=>$set{'to_id'}, file_name=>$set{'to_file'}), @@ -6829,7 +6866,7 @@ sub git_blame_common { # the header: [] # no for subsequent lines in group of lines my ($full_rev, $orig_lineno, $lineno, $group_size) = - ($line =~ /^([0-9a-f]{40}) (\d+) (\d+)(?: (\d+))?$/); + ($line =~ /^($oid_regex) (\d+) (\d+)(?: (\d+))?$/); if (!exists $metainfo{$full_rev}) { $metainfo{$full_rev} = { 'nprevious' => 0 }; } @@ -6879,7 +6916,7 @@ sub git_blame_common { } # 'previous' if (exists $meta->{'previous'} && - $meta->{'previous'} =~ /^([a-fA-F0-9]{40}) (.*)$/) { + $meta->{'previous'} =~ /^($oid_regex) (.*)$/) { $meta->{'parent'} = $1; $meta->{'file_parent'} = unquote($2); } @@ -6996,7 +7033,7 @@ sub git_blob_plain { } else { die_error(400, "No file name defined"); } - } elsif ($hash =~ m/^[0-9a-fA-F]{40}$/) { + } elsif ($hash =~ m/^$oid_regex$/) { # blobs defined by non-textual hash id's can be cached $expires = "+1d"; } @@ -7057,7 +7094,7 @@ sub git_blob { } else { die_error(400, "No file name defined"); } - } elsif ($hash =~ m/^[0-9a-fA-F]{40}$/) { + } elsif ($hash =~ m/^$oid_regex$/) { # blobs defined by non-textual hash id's can be cached $expires = "+1d"; } @@ -7515,7 +7552,7 @@ sub git_commit { # non-textual hash id's can be cached my $expires; - if ($hash =~ m/^[0-9a-fA-F]{40}$/) { + if ($hash =~ m/^$oid_regex$/) { $expires = "+1d"; } my $refs = git_get_references(); @@ -7609,7 +7646,7 @@ sub git_object { close $fd; #'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa panic.c' - unless ($line && $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t/) { + unless ($line && $line =~ m/^([0-9]+) (.+) ($oid_regex)\t/) { die_error(404, "File or directory for given base does not exist"); } $type = $2; @@ -7649,7 +7686,7 @@ sub git_blobdiff { or die_error(404, "Blob diff not found"); } elsif (defined $hash && - $hash =~ /[0-9a-fA-F]{40}/) { + $hash =~ $oid_regex) { # try to find filename from $hash # read filtered raw output @@ -7659,7 +7696,7 @@ sub git_blobdiff { @difftree = # ':100644 100644 03b21826... 3b93d5e7... M ls-files.c' # $hash == to_id - grep { /^:[0-7]{6} [0-7]{6} [0-9a-fA-F]{40} $hash/ } + grep { /^:[0-7]{6} [0-7]{6} $oid_regex $hash/ } map { chomp; $_ } <$fd>; close $fd or die_error(404, "Reading git-diff-tree failed"); @@ -7682,8 +7719,8 @@ sub git_blobdiff { $hash ||= $diffinfo{'to_id'}; # non-textual hash id's can be cached - if ($hash_base =~ m/^[0-9a-fA-F]{40}$/ && - $hash_parent_base =~ m/^[0-9a-fA-F]{40}$/) { + if ($hash_base =~ m/^$oid_regex$/ && + $hash_parent_base =~ m/^$oid_regex$/) { $expires = '+1d'; } @@ -7819,7 +7856,7 @@ sub git_commitdiff { $hash_parent ne '-c' && $hash_parent ne '--cc') { # commitdiff with two commits given my $hash_parent_short = $hash_parent; - if ($hash_parent =~ m/^[0-9a-fA-F]{40}$/) { + if ($hash_parent =~ m/^$oid_regex$/) { $hash_parent_short = substr($hash_parent, 0, 7); } $formats_nav .= @@ -7928,7 +7965,7 @@ sub git_commitdiff { # non-textual hash id's can be cached my $expires; - if ($hash =~ m/^[0-9a-fA-F]{40}$/) { + if ($hash =~ m/^$oid_regex$/) { $expires = "+1d"; }