use 5.008;
use strict;
use warnings;
+# handle ACL in file access tests
+use filetest 'access';
use CGI qw(:standard :escapeHTML -nosticky);
use CGI::Util qw(unescape);
use CGI::Carp qw(fatalsToBrowser set_message);
use File::Find qw();
use File::Basename qw(basename);
use Time::HiRes qw(gettimeofday tv_interval);
+use Digest::MD5 qw(md5_hex);
+
binmode STDOUT, ':utf8';
+if (!defined($CGI::VERSION) || $CGI::VERSION < 4.08) {
+ eval 'sub CGI::multi_param { CGI::param(@_) }'
+}
+
our $t0 = [ gettimeofday() ];
our $number_of_git_cmds = 0;
# Currently available providers are gravatar and picon.
# If an unknown provider is specified, the feature is disabled.
- # Gravatar depends on Digest::MD5.
# Picon currently relies on the indiana.edu database.
# To enable system wide have in $GITWEB_CONFIG
'sub' => sub { feature_bool('remote_heads', @_) },
'override' => 0,
'default' => [0]},
+
+ # Enable showing branches under other refs in addition to heads
+
+ # To set system wide extra branch refs have in $GITWEB_CONFIG
+ # $feature{'extra-branch-refs'}{'default'} = ['dirs', 'of', 'choice'];
+ # To have project specific config enable override in $GITWEB_CONFIG
+ # $feature{'extra-branch-refs'}{'override'} = 1;
+ # and in project config gitweb.extrabranchrefs = dirs of choice
+ # Every directory is separated with whitespace.
+
+ 'extra-branch-refs' => {
+ 'sub' => \&feature_extra_branch_refs,
+ 'override' => 0,
+ 'default' => []},
+
+ # Redact e-mail addresses.
+
+ # To enable system wide have in $GITWEB_CONFIG
+ # $feature{'email-privacy'}{'default'} = [1];
+ 'email-privacy' => {
+ 'sub' => sub { feature_bool('email-privacy', @_) },
+ 'override' => 1,
+ 'default' => [0]},
);
sub gitweb_get_feature {
return @val ? @val : @_;
}
+sub feature_extra_branch_refs {
+ my (@branch_refs) = @_;
+ my $values = git_get_project_config('extrabranchrefs');
+
+ if ($values) {
+ $values = config_to_multi ($values);
+ @branch_refs = ();
+ foreach my $value (@{$values}) {
+ push @branch_refs, split /\s+/, $value;
+ }
+ }
+
+ return @branch_refs;
+}
+
# checking HEAD file with -e is fragile if the repository was
# initialized long time ago (i.e. symlink HEAD) and was pack-ref'ed
# and then pruned.
!$known_snapshot_formats{$_}{'disabled'}} @fmts;
}
+sub filter_and_validate_refs {
+ my @refs = @_;
+ my %unique_refs = ();
+
+ foreach my $ref (@refs) {
+ die_error(500, "Invalid ref '$ref' in 'extra-branch-refs' feature") unless (is_valid_ref_format($ref));
+ # 'heads' are added implicitly in get_branch_refs().
+ $unique_refs{$ref} = 1 if ($ref ne 'heads');
+ }
+ return sort keys %unique_refs;
+}
+
# If it is set to code reference, it is code that it is to be run once per
# request, allowing updating configurations that change with each request,
# while running other code in config file only once.
$GITWEB_CONFIG_SYSTEM = "" if ($GITWEB_CONFIG_SYSTEM eq $GITWEB_CONFIG_COMMON);
# Common system-wide settings for convenience.
- # Those settings can be ovverriden by GITWEB_CONFIG or GITWEB_CONFIG_SYSTEM.
+ # Those settings can be overridden by GITWEB_CONFIG or GITWEB_CONFIG_SYSTEM.
read_config_file($GITWEB_CONFIG_COMMON);
# Use first config file that exists. This means use the per-instance
# ======================================================================
# 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(?:$y)?)/;
+}
+
# input parameters can be collected from a variety of sources (presently, CGI
# and PATH_INFO), so we define an %input_params hash that collects them all
# together during validation: this allows subsequent uses (e.g. href()) to be
while (my ($name, $symbol) = each %cgi_param_mapping) {
if ($symbol eq 'opt') {
- $input_params{$name} = [ map { decode_utf8($_) } $cgi->param($symbol) ];
+ $input_params{$name} = [ map { decode_utf8($_) } $cgi->multi_param($symbol) ];
} else {
$input_params{$name} = decode_utf8($cgi->param($symbol));
}
sub evaluate_and_validate_params {
our $action = $input_params{'action'};
if (defined $action) {
- if (!validate_action($action)) {
+ if (!is_valid_action($action)) {
die_error(400, "Invalid action parameter");
}
}
# parameters which are pathnames
our $project = $input_params{'project'};
if (defined $project) {
- if (!validate_project($project)) {
+ if (!is_valid_project($project)) {
undef $project;
die_error(404, "No such project");
}
our $project_filter = $input_params{'project_filter'};
if (defined $project_filter) {
- if (!validate_pathname($project_filter)) {
+ if (!is_valid_pathname($project_filter)) {
die_error(404, "Invalid project_filter parameter");
}
}
our $file_name = $input_params{'file_name'};
if (defined $file_name) {
- if (!validate_pathname($file_name)) {
+ if (!is_valid_pathname($file_name)) {
die_error(400, "Invalid file parameter");
}
}
our $file_parent = $input_params{'file_parent'};
if (defined $file_parent) {
- if (!validate_pathname($file_parent)) {
+ if (!is_valid_pathname($file_parent)) {
die_error(400, "Invalid file parent parameter");
}
}
# parameters which are refnames
our $hash = $input_params{'hash'};
if (defined $hash) {
- if (!validate_refname($hash)) {
+ if (!is_valid_refname($hash)) {
die_error(400, "Invalid hash parameter");
}
}
our $hash_parent = $input_params{'hash_parent'};
if (defined $hash_parent) {
- if (!validate_refname($hash_parent)) {
+ if (!is_valid_refname($hash_parent)) {
die_error(400, "Invalid hash parent parameter");
}
}
our $hash_base = $input_params{'hash_base'};
if (defined $hash_base) {
- if (!validate_refname($hash_base)) {
+ if (!is_valid_refname($hash_base)) {
die_error(400, "Invalid hash base parameter");
}
}
our $hash_parent_base = $input_params{'hash_parent_base'};
if (defined $hash_parent_base) {
- if (!validate_refname($hash_parent_base)) {
+ if (!is_valid_refname($hash_parent_base)) {
die_error(400, "Invalid hash parent base parameter");
}
}
our $git_dir = "$projectroot/$project" if $project;
}
-our (@snapshot_fmts, $git_avatar);
+our (@snapshot_fmts, $git_avatar, @extra_branch_refs);
sub configure_gitweb_features {
# list of supported snapshot formats
our @snapshot_fmts = gitweb_get_feature('snapshot');
@snapshot_fmts = filter_snapshot_fmts(@snapshot_fmts);
- # check that the avatar feature is set to a known provider name,
- # and for each provider check if the dependencies are satisfied.
- # if the provider name is invalid or the dependencies are not met,
- # reset $git_avatar to the empty string.
our ($git_avatar) = gitweb_get_feature('avatar');
- if ($git_avatar eq 'gravatar') {
- $git_avatar = '' unless (eval { require Digest::MD5; 1; });
- } elsif ($git_avatar eq 'picon') {
- # no dependencies
- } else {
- $git_avatar = '';
- }
+ $git_avatar = '' unless $git_avatar =~ /^(?:gravatar|picon)$/s;
+
+ our @extra_branch_refs = gitweb_get_feature('extra-branch-refs');
+ @extra_branch_refs = filter_and_validate_refs (@extra_branch_refs);
+}
+
+sub get_branch_refs {
+ return ('heads', @extra_branch_refs);
}
# custom error handler: 'die <message>' is Internal Server Error
our ($pre_dispatch_hook, $post_dispatch_hook, $pre_listen_hook);
our $CGI = 'CGI';
our $cgi;
+our $FCGI_Stream_PRINT_raw = \&FCGI::Stream::PRINT;
sub configure_as_fcgi {
require CGI::Fast;
our $CGI = 'CGI::Fast';
+ # FCGI is not Unicode aware hence the UTF-8 encoding must be done manually.
+ # However no encoding must be done within git_blob_plain() and git_snapshot()
+ # which must still output in raw binary mode.
+ no warnings 'redefine';
+ my $enc = Encode::find_encoding('UTF-8');
+ *FCGI::Stream::PRINT = sub {
+ my @OUTPUT = @_;
+ for (my $i = 1; $i < @_; $i++) {
+ $OUTPUT[$i] = $enc->encode($_[$i], Encode::FB_CROAK|Encode::LEAVE_SRC);
+ }
+ @_ = @OUTPUT;
+ goto $FCGI_Stream_PRINT_raw;
+ };
my $request_number = 0;
# let each child service 100 requests
## ======================================================================
## validation, quoting/unquoting and escaping
-sub validate_action {
- my $input = shift || return undef;
+sub is_valid_action {
+ my $input = shift;
return undef unless exists $actions{$input};
- return $input;
+ return 1;
}
-sub validate_project {
- my $input = shift || return undef;
- if (!validate_pathname($input) ||
+sub is_valid_project {
+ my $input = shift;
+
+ return unless defined $input;
+ if (!is_valid_pathname($input) ||
!(-d "$projectroot/$input") ||
!check_export_ok("$projectroot/$input") ||
($strict_export && !project_in_list($input))) {
return undef;
} else {
- return $input;
+ return 1;
}
}
-sub validate_pathname {
- my $input = shift || return undef;
+sub is_valid_pathname {
+ my $input = shift;
- # no '.' or '..' as elements of path, i.e. no '.' nor '..'
+ return undef unless defined $input;
+ # no '.' or '..' as elements of path, i.e. no '.' or '..'
# at the beginning, at the end, and between slashes.
# also this catches doubled slashes
if ($input =~ m!(^|/)(|\.|\.\.)(/|$)!) {
if ($input =~ m!\0!) {
return undef;
}
- return $input;
+ return 1;
}
-sub validate_refname {
- my $input = shift || return undef;
+sub is_valid_ref_format {
+ my $input = shift;
- # textual hashes are O.K.
- if ($input =~ m/^[0-9a-fA-F]{40}$/) {
- return $input;
- }
- # it must be correct pathname
- $input = validate_pathname($input)
- or return undef;
+ return undef unless defined $input;
# restrictions on ref name according to git-check-ref-format
if ($input =~ m!(/\.|\.\.|[\000-\040\177 ~^:?*\[]|/$)!) {
return undef;
}
- return $input;
+ return 1;
+}
+
+sub is_valid_refname {
+ my $input = shift;
+
+ return undef unless defined $input;
+ # textual hashes are O.K.
+ if ($input =~ m/^$oid_regex$/) {
+ return 1;
+ }
+ # it must be correct pathname
+ is_valid_pathname($input) or return undef;
+ # check git-check-ref-format restrictions
+ is_valid_ref_format($input) or return undef;
+ return 1;
}
# decode sequences of octets in utf8 into Perl's internal form,
return $str;
}
-# Sanitize for use in XHTML + application/xml+xhtm (valid XML 1.0)
+# Sanitize for use in XHTML + application/xml+xhtml (valid XML 1.0)
sub sanitize {
my $str = shift;
my $cntrl = shift;
my %opts = @_;
my %es = ( # character escape codes, aka escape sequences
- "\t" => '\t', # tab (HT)
- "\n" => '\n', # line feed (LF)
- "\r" => '\r', # carrige return (CR)
- "\f" => '\f', # form feed (FF)
- "\b" => '\b', # backspace (BS)
- "\a" => '\a', # alarm (bell) (BEL)
- "\e" => '\e', # escape (ESC)
- "\013" => '\v', # vertical tab (VT)
- "\000" => '\0', # nul character (NUL)
+ "\t" => '\t', # tab (HT)
+ "\n" => '\n', # line feed (LF)
+ "\r" => '\r', # carriage return (CR)
+ "\f" => '\f', # form feed (FF)
+ "\b" => '\b', # backspace (BS)
+ "\a" => '\a', # alarm (bell) (BEL)
+ "\e" => '\e', # escape (ESC)
+ "\013" => '\v', # vertical tab (VT)
+ "\000" => '\0', # nul character (NUL)
);
my $chr = ( (exists $es{$cntrl})
? $es{$cntrl}
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([0-9a-fA-F]{8,40})\b}{
+ $line =~ s{
+ \b
+ (
+ # The output of "git describe", e.g. v2.10.0-297-gf6727b0
+ # or hadoop-20160921-113441-20-g094fb7d
+ (?<!-) # see strbuf_check_tag_ref(). Tags can't start with -
+ [A-Za-z0-9.-]+
+ (?!\.) # refs can't end with ".", see check_refname_format()
+ -g$regex
+ |
+ # Just a normal looking Git SHA1
+ $regex
+ )
+ \b
+ }{
$cgi->a({-href => href(action=>"object", hash=>$1),
-class => "text"}, $1);
- }eg;
+ }egx;
return $line;
}
-href => href(
action=>$dest_action,
hash=>$dest
- )}, $name);
+ )}, esc_html($name));
$markers .= " <span class=\"".esc_attr($class)."\" title=\"".esc_attr($ref)."\">" .
$link . "</span>";
my $size = shift;
$avatar_cache{$email} ||=
"//www.gravatar.com/avatar/" .
- Digest::MD5::md5_hex($email) . "?s=";
+ md5_hex($email) . "?s=";
return $avatar_cache{$email} . $size;
}
')</span>';
}
# match <hash>
- if ($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++) {
$line .= '0' x 7;
}
- } elsif ($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'}) {
sub get_feed_info {
my $format = shift || 'Atom';
my %res = (action => lc($format));
+ my $matched_ref = 0;
# feed links are possible only for project views
return unless (defined $project);
# or don't have specific feed yet (so they should use generic)
return if (!$action || $action =~ /^(?:tags|heads|forks|tag|search)$/x);
- my $branch;
- # branches refs uses 'refs/heads/' prefix (fullname) to differentiate
- # from tag links; this also makes possible to detect branch links
- if ((defined $hash_base && $hash_base =~ m!^refs/heads/(.*)$!) ||
- (defined $hash && $hash =~ m!^refs/heads/(.*)$!)) {
- $branch = $1;
+ my $branch = undef;
+ # branches refs uses 'refs/' + $get_branch_refs()[x] + '/' prefix
+ # (fullname) to differentiate from tag links; this also makes
+ # possible to detect branch links
+ for my $ref (get_branch_refs()) {
+ if ((defined $hash_base && $hash_base =~ m!^refs/\Q$ref\E/(.*)$!) ||
+ (defined $hash && $hash =~ m!^refs/\Q$ref\E/(.*)$!)) {
+ $branch = $1;
+ $matched_ref = $ref;
+ last;
+ }
}
# find log type for feed description (title)
my $type = 'log';
}
$res{-title} = $type;
- $res{'hash'} = (defined $branch ? "refs/heads/$branch" : undef);
+ $res{'hash'} = (defined $branch ? "refs/$matched_ref/$branch" : undef);
$res{'file_name'} = $file_name;
return %res;
}
#'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 $2) {
# type doesn't match
return undef;
return if (m!^[/.]$!);
# only directories can be git repositories
return unless (-d $_);
+ # need search permission
+ return unless (-x $_);
# don't traverse too deep (Find is super slow on os x)
# $project_maxdepth excludes depth of $projectroot
if (($File::Find::name =~ tr!/!!) - $pfxdepth > $project_maxdepth) {
return @list;
}
-# written with help of Tree::Trie module (Perl Artistic License, GPL compatibile)
+# written with help of Tree::Trie module (Perl Artistic License, GPL compatible)
# as side effects it sets 'forks' field to list of forks for forked projects
sub filter_forks_from_projects_list {
my $projects = shift;
'--format=%(committer)',
'--sort=-committerdate',
'--count=1',
- 'refs/heads') or return;
+ map { "refs/$_" } get_branch_refs ()) or return;
my $most_recent = <$fd>;
close $fd or return;
if (defined $most_recent &&
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 {
return %date;
}
+sub hide_mailaddrs_if_private {
+ my $line = shift;
+ return $line unless gitweb_check_feature('email-privacy');
+ $line =~ s/<[^@>]+@[^>]+>/<redacted>/g;
+ return $line;
+}
+
sub parse_tag {
my $tag_id = shift;
my %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'} = $1;
} elsif ($line =~ m/^tag (.+)$/) {
$tag{'name'} = $1;
} elsif ($line =~ m/^tagger (.*) ([0-9]+) (.*)$/) {
- $tag{'author'} = $1;
+ $tag{'author'} = hide_mailaddrs_if_private($1);
$tag{'author_epoch'} = $2;
$tag{'author_tz'} = $3;
if ($tag{'author'} =~ m/^([^<]+) <([^>]*)>/) {
}
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);
+ $co{'author'} = hide_mailaddrs_if_private(to_utf8($1));
$co{'author_epoch'} = $2;
$co{'author_tz'} = $3;
if ($co{'author'} =~ m/^([^<]+) <([^>]*)>/) {
$co{'author_name'} = $co{'author'};
}
} elsif ($line =~ m/^committer (.*) ([0-9]+) (.*)$/) {
- $co{'committer'} = to_utf8($1);
+ $co{'committer'} = hide_mailaddrs_if_private(to_utf8($1));
$co{'committer_epoch'} = $2;
$co{'committer_tz'} = $3;
if ($co{'committer'} =~ m/^([^<]+) <([^>]*)>/) {
if (! defined $co{'title'} || $co{'title'} eq "") {
$co{'title'} = $co{'title_short'} = '(no commit message)';
}
- # remove added spaces
+ # remove added spaces, redact e-mail addresses if applicable.
foreach my $line (@commit_lines) {
$line =~ s/^ //;
+ $line = hide_mailaddrs_if_private($line);
}
$co{'comment'} = \@commit_lines;
# ':100644 100644 03b218260e99b78c6df0ed378e59ed9205ccc96d 3b93d5e7cc7f7dd4ebed13a5cc1a4ad976fc94d8 M ls-files.c'
# ':100644 100644 7f9281985086971d3877aca27704f2aaf9c448ce bc190ebc71bbd923f2b728e505408f5e54bd073a M rev-tree.c'
- if ($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'} = $3;
}
# '::100755 100755 100755 60e79ca1b01bc8b057abe17ddab484699a7f5fdb 94067cc5f73388f33722d52ae02f44692bc07490 94067cc5f73388f33722d52ae02f44692bc07490 MR git-gui/git-gui.sh'
# combined diff (for merge commit)
- elsif ($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'}};
$res{'to_file'} = unquote($5);
}
# 'c512b523472485aef4fff9e57b229d9d243c967f'
- elsif ($line =~ m/^([0-9a-fA-F]{40})$/) {
+ elsif ($line =~ m/^($oid_regex)$/) {
$res{'commit'} = $1;
}
if ($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;
}
} 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'} = $2;
sub git_get_heads_list {
my ($limit, @classes) = @_;
- @classes = ('heads') unless @classes;
+ @classes = get_branch_refs() unless @classes;
my @patterns = map { "refs/$_" } @classes;
my @headslist;
open my $fd, '-|', git_cmd(), 'for-each-ref',
- ($limit ? '--count='.($limit+1) : ()), '--sort=-committerdate',
+ ($limit ? '--count='.($limit+1) : ()),
+ '--sort=-HEAD', '--sort=-committerdate',
'--format=%(objectname) %(refname) %(subject)%00%(committer)',
@patterns
or return;
my ($committer, $epoch, $tz) =
($committerinfo =~ /^(.*) ([0-9]+) (.*)$/);
$ref_item{'fullname'} = $name;
- $name =~ s!^refs/(?:head|remote)s/!!;
+ my $strip_refs = join '|', map { quotemeta } get_branch_refs();
+ $name =~ s!^refs/($strip_refs|remotes)/!!;
+ $ref_item{'name'} = $name;
+ # for refs neither in 'heads' nor 'remotes' we want to
+ # show their ref dir
+ my $ref_dir = (defined $1) ? $1 : '';
+ if ($ref_dir ne '' and $ref_dir ne 'heads' and $ref_dir ne 'remotes') {
+ $ref_item{'name'} .= ' (' . $ref_dir . ')';
+ }
- $ref_item{'name'} = $name;
$ref_item{'id'} = $hash;
$ref_item{'title'} = $title || '(no commit message)';
$ref_item{'epoch'} = $epoch;
# guess file syntax for syntax highlighting; return undef if no highlighting
# the name of syntax can (in the future) depend on syntax highlighter used
sub guess_file_syntax {
- my ($highlight, $mimetype, $file_name) = @_;
+ my ($highlight, $file_name) = @_;
return undef unless ($highlight && defined $file_name);
my $basename = basename($file_name, '.in');
return $highlight_basename{$basename}
# or return original FD if no highlighting
sub run_highlighter {
my ($fd, $highlight, $syntax) = @_;
- return $fd unless ($highlight && defined $syntax);
+ return $fd unless ($highlight);
close $fd;
+ my $syntax_arg = (defined $syntax) ? "--syntax $syntax" : "--force";
open $fd, quote_command(git_cmd(), "cat-file", "blob", $hash)." | ".
+ quote_command($^X, '-CO', '-MEncode=decode,FB_DEFAULT', '-pse',
+ '$_ = decode($fe, $_, FB_DEFAULT) if !utf8::decode($_);',
+ '--', "-fe=$fallback_encoding")." | ".
quote_command($highlight_bin).
- " --replace-tabs=8 --fragment --syntax $syntax |"
+ " --replace-tabs=8 --fragment $syntax_arg |"
or die_error(500, "Couldn't open file or run syntax highlighter");
return $fd;
}
$href_params{'extra_options'} = undef;
$href_params{'action'} = $type;
- $link_attr{'-href'} = href(%href_params);
+ $link_attr{'-href'} = esc_attr(href(%href_params));
print "<link ".
"rel=\"$link_attr{'-rel'}\" ".
"title=\"$link_attr{'-title'}\" ".
"/>\n";
$href_params{'extra_options'} = '--no-merges';
- $link_attr{'-href'} = href(%href_params);
+ $link_attr{'-href'} = esc_attr(href(%href_params));
$link_attr{'-title'} .= ' (no merges)';
print "<link ".
"rel=\"$link_attr{'-rel'}\" ".
} else {
printf('<link rel="alternate" title="%s projects list" '.
'href="%s" type="text/plain; charset=utf-8" />'."\n",
- esc_attr($site_name), href(project=>undef, action=>"project_index"));
+ esc_attr($site_name),
+ esc_attr(href(project=>undef, action=>"project_index")));
printf('<link rel="alternate" title="%s projects feeds" '.
'href="%s" type="text/x-opml" />'."\n",
- esc_attr($site_name), href(project=>undef, action=>"opml"));
+ esc_attr($site_name),
+ esc_attr(href(project=>undef, action=>"opml")));
}
}
if ($use_pathinfo) {
$action .= "/".esc_url($project);
}
- print $cgi->startform(-method => "get", -action => $action) .
+ print $cgi->start_form(-method => "get", -action => $action) .
"<div class=\"search\">\n" .
(!$use_pathinfo &&
$cgi->input({-name=>"p", -value=>$project, -type=>"hidden"}) . "\n") .
my %opts = @_;
my $title = get_page_title();
- my $content_type = get_content_type_html();
- print $cgi->header(-type=>$content_type, -charset => 'utf-8',
+ print $cgi->header(-type=>get_content_type_html(), -charset => 'utf-8',
-status=> $status, -expires => $expires)
unless ($opts{'-no_http_header'});
my $mod_perl_version = $ENV{'MOD_PERL'} ? " $ENV{'MOD_PERL'}" : '';
<!-- git web interface version $version, (C) 2005-2006, Kay Sievers <kay.sievers\@vrfy.org>, Christian Gierke -->
<!-- git core binaries version $git_version -->
<head>
-<meta http-equiv="content-type" content="$content_type; charset=utf-8"/>
<meta name="generator" content="gitweb/$version git/$git_version$mod_perl_version"/>
<meta name="robots" content="index, nofollow"/>
<title>$title</title>
if (defined $action &&
$action eq 'blame_incremental') {
print qq!<script type="text/javascript">\n!.
- qq!startBlame("!. href(action=>"blame_data", -replay=>1) .qq!",\n!.
- qq! "!. href() .qq!");\n!.
+ qq!startBlame("!. esc_attr(href(action=>"blame_data", -replay=>1)) .qq!",\n!.
+ qq! "!. esc_attr(href()) .qq!");\n!.
qq!</script>\n!;
} else {
my ($jstimezone, $tz_cookie, $datetime_class) =
"</div>\n";
}
-# returns a submenu for the nagivation of the refs views (tags, heads,
+# returns a submenu for the navigation of the refs views (tags, heads,
# remotes) with the current view disabled and the remotes view only
# available if the feature is enabled
sub format_ref_views {
# print log
my $skip_blank_line = 0;
foreach my $line (@$log) {
- if ($line =~ m/^\s*([A-Z][-A-Za-z]*-[Bb]y|C[Cc]): /) {
+ if ($line =~ m/^\s*([A-Z][-A-Za-z]*-([Bb]y|[Tt]o)|C[Cc]|(Clos|Fix)es): /) {
if (! $opts{'-remove_signoff'}) {
print "<span class=\"signoff\">" . esc_html($line) . "</span><br/>\n";
$skip_blank_line = 1;
sub is_deleted {
my $diffinfo = shift;
- return $diffinfo->{'to_id'} eq ('0' x 40);
+ return $diffinfo->{'to_id'} eq ('0' x 40) || $diffinfo->{'to_id'} eq ('0' x 64);
}
# does patch correspond to [previous] difftree raw line
# + c
# + d
#
- # Otherwise the highlightling would be confusing.
+ # Otherwise the highlighting would be confusing.
if ($is_combined) {
for (my $i = 0; $i < @$add; $i++) {
my $prefix_rem = substr($rem->[$i], 0, $num_parents);
}
print "<div class=\"projsearch\">\n";
- print $cgi->startform(-method => 'get', -action => $my_uri) .
+ print $cgi->start_form(-method => 'get', -action => $my_uri) .
$cgi->hidden(-name => 'a', -value => 'project_list') . "\n";
print $cgi->hidden(-name => 'pf', -value => $project_filter). "\n"
if (defined $project_filter);
$cgi->a({-href => href(action=>"commitdiff", hash=>$commit)}, "commitdiff");
if ($ftype eq 'blob') {
+ print " | " .
+ $cgi->a({-href => href(action=>"blob_plain", hash_base=>$commit, file_name=>$file_name)}, "raw");
+
my $blob_current = $file_hash;
my $blob_parent = git_get_hash_by_path($commit, $file_name);
if (defined $blob_current && defined $blob_parent &&
-class => "list subject"},
chop_and_escape_str($co{'title'}, 50) . "<br/>");
} 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'}),
# the header: <SHA-1> <src lineno> <dst lineno> [<lines in group>]
# no <lines in group> 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 };
}
}
# 'previous' <sha1 of parent commit> <filename at commit>
if (exists $meta->{'previous'} &&
- $meta->{'previous'} =~ /^([a-fA-F0-9]{40}) (.*)$/) {
+ $meta->{'previous'} =~ /^($oid_regex) (.*)$/) {
$meta->{'parent'} = $1;
$meta->{'file_parent'} = unquote($2);
}
} else {
die_error(400, "No file name defined");
}
- } elsif ($hash =~ m/^[0-9a-fA-F]{40}$/) {
+ } elsif ($hash =~ m/^$oid_regex$/) {
# blobs defined by non-textual hash id's can be cached
$expires = "+1d";
}
($sandbox ? 'attachment' : 'inline')
. '; filename="' . $save_as . '"');
local $/ = undef;
+ local *FCGI::Stream::PRINT = $FCGI_Stream_PRINT_raw;
binmode STDOUT, ':raw';
print <$fd>;
binmode STDOUT, ':utf8'; # as set at the beginning of gitweb.cgi
} 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";
}
$have_blame &&= ($mimetype =~ m!^text/!);
my $highlight = gitweb_check_feature('highlight');
- my $syntax = guess_file_syntax($highlight, $mimetype, $file_name);
- $fd = run_highlighter($fd, $highlight, $syntax)
- if $syntax;
+ my $syntax = guess_file_syntax($highlight, $file_name);
+ $fd = run_highlighter($fd, $highlight, $syntax);
git_header_html(undef, $expires);
my $formats_nav = '';
git_print_page_path($file_name, "blob", $hash_base);
print "<div class=\"page_body\">\n";
if ($mimetype =~ m!^image/!) {
- print qq!<img type="!.esc_attr($mimetype).qq!"!;
+ print qq!<img class="blob" type="!.esc_attr($mimetype).qq!"!;
if ($file_name) {
print qq! alt="!.esc_attr($file_name).qq!" title="!.esc_attr($file_name).qq!"!;
}
print qq! src="! .
- href(action=>"blob_plain", hash=>$hash,
- hash_base=>$hash_base, file_name=>$file_name) .
+ esc_attr(href(action=>"blob_plain", hash=>$hash,
+ hash_base=>$hash_base, file_name=>$file_name)) .
qq!" />\n!;
} else {
my $nr;
$line = untabify($line);
printf qq!<div class="pre"><a id="l%i" href="%s#l%i" class="linenr">%4i</a> %s</div>\n!,
$nr, esc_attr(href(-replay => 1)), $nr, $nr,
- $syntax ? sanitize($line) : esc_html($line, -nbsp=>1);
+ $highlight ? sanitize($line) : esc_html($line, -nbsp=>1);
}
}
close $fd
git_footer_html();
}
+sub sanitize_for_filename {
+ my $name = shift;
+
+ $name =~ s!/!-!g;
+ $name =~ s/[^[:alnum:]_.-]//g;
+
+ return $name;
+}
+
sub snapshot_name {
my ($project, $hash) = @_;
# path/to/project/.git -> project
my $name = to_utf8($project);
$name =~ s,([^/])/*\.git$,$1,;
- $name = basename($name);
- # sanitize name
- $name =~ s/[[:cntrl:]]/?/g;
+ $name = sanitize_for_filename(basename($name));
my $ver = $hash;
if ($hash =~ /^[0-9a-fA-F]+$/) {
$ver = $1;
} else {
# branches and other need shortened SHA-1 hash
- if ($hash =~ m!^refs/(?:heads|remotes)/(.*)$!) {
- $ver = $1;
+ my $strip_refs = join '|', map { quotemeta } get_branch_refs();
+ if ($hash =~ m!^refs/($strip_refs|remotes)/(.*)$!) {
+ my $ref_dir = (defined $1) ? $1 : '';
+ $ver = $2;
+
+ $ref_dir = sanitize_for_filename($ref_dir);
+ # for refs neither in heads nor remotes we want to
+ # add a ref dir to archive name
+ if ($ref_dir ne '' and $ref_dir ne 'heads' and $ref_dir ne 'remotes') {
+ $ver = $ref_dir . '-' . $ver;
+ }
}
$ver .= '-' . git_get_short_hash($project, $hash);
}
+ # special case of sanitization for filename - we change
+ # slashes to dots instead of dashes
# in case of hierarchical branch names
$ver =~ s!/!.!g;
+ $ver =~ s/[^[:alnum:]_.-]//g;
# name = project-version_string
$name = "$name-$ver";
open my $fd, "-|", $cmd
or die_error(500, "Execute git-archive failed");
+ local *FCGI::Stream::PRINT = $FCGI_Stream_PRINT_raw;
binmode STDOUT, ':raw';
print <$fd>;
binmode STDOUT, ':utf8'; # as set at the beginning of gitweb.cgi
-accesskey => "n", -title => "Alt-n"}, "next");
}
my $patch_max = gitweb_get_feature('patches');
- if ($patch_max && !defined $file_name) {
+ if ($patch_max && !defined $file_name &&
+ !gitweb_check_feature('email-privacy')) {
if ($patch_max < 0 || @commitlist <= $patch_max) {
$paging_nav .= " ⋅ " .
$cgi->a({-href => href(action=>"patches", -replay=>1)},
} @$parents ) .
')';
}
- if (gitweb_check_feature('patches') && @$parents <= 1) {
+ if (gitweb_check_feature('patches') && @$parents <= 1 &&
+ !gitweb_check_feature('email-privacy')) {
$formats_nav .= " | " .
$cgi->a({-href => href(action=>"patch", -replay=>1)},
"patch");
# 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();
git_cmd(), 'cat-file', '-t', $object_id) . ' 2> /dev/null'
or die_error(404, "Object does not exist");
$type = <$fd>;
- chomp $type;
+ defined $type && chomp $type;
close $fd
or die_error(404, "Object does not exist");
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;
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
@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");
$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';
}
$formats_nav =
$cgi->a({-href => href(action=>"commitdiff_plain", -replay=>1)},
"raw");
- if ($patch_max && @{$co{'parents'}} <= 1) {
+ if ($patch_max && @{$co{'parents'}} <= 1 &&
+ !gitweb_check_feature('email-privacy')) {
$formats_nav .= " | " .
$cgi->a({-href => href(action=>"patch", -replay=>1)},
"patch");
$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 .=
# 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";
}
<p><strong>Pattern</strong> is by default a normal string that is matched precisely (but without
regard to case, except in the case of pickaxe). However, when you check the <em>re</em> checkbox,
the pattern entered is recognized as the POSIX extended
-<a href="http://en.wikipedia.org/wiki/Regular_expression">regular expression</a> (also case
+<a href="https://en.wikipedia.org/wiki/Regular_expression">regular expression</a> (also case
insensitive).</p>
<dl>
<dt><b>commit</b></dt>
} else {
$alt_url = href(-full=>1, action=>"summary");
}
+ $alt_url = esc_attr($alt_url);
print qq!<?xml version="1.0" encoding="utf-8"?>\n!;
if ($format eq 'rss') {
print <<XML;
$alt_url . '" />' . "\n" .
'<link rel="self" type="' . $content_type . '" href="' .
$cgi->self_url() . '" />' . "\n" .
- "<id>" . href(-full=>1) . "</id>\n" .
+ "<id>" . esc_url(href(-full=>1)) . "</id>\n" .
# use project owner for feed author
"<author><name>$owner</name></author>\n";
if (defined $favicon) {
"<author>" . esc_html($co{'author'}) . "</author>\n" .
"<pubDate>$cd{'rfc2822'}</pubDate>\n" .
"<guid isPermaLink=\"true\">$co_url</guid>\n" .
- "<link>$co_url</link>\n" .
+ "<link>" . esc_html($co_url) . "</link>\n" .
"<description>" . esc_html($co{'title'}) . "</description>\n" .
"<content:encoded>" .
"<
Lady’s Gitweb / Gitweb / blobdiff