X-Git-Url: https://git.ladys.computer/Gitweb/blobdiff_plain/8ed2f8a3ee11810853865c6a45d4c9561d9fff8ad5b83d118bdfb5137eb308bb..ec228e58276bb35869df7e82d96951cdf1730c2f6f0197571a54f5c0db0c8ebb:/gitweb.perl diff --git a/gitweb.perl b/gitweb.perl index 7543059..5d5401f 100755 --- a/gitweb.perl +++ b/gitweb.perl @@ -10,6 +10,8 @@ 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); @@ -18,8 +20,14 @@ use Fcntl ':mode'; 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; @@ -85,6 +93,9 @@ our $project_maxdepth = "++GITWEB_PROJECT_MAXDEPTH++"; # string of the home link on top of all pages our $home_link_str = "++GITWEB_HOME_LINK_STR++"; +# extra breadcrumbs preceding the home link +our @extra_breadcrumbs = (); + # name of your site or organization to appear in page titles # replace this with something more descriptive for clearer bookmarks our $site_name = "++GITWEB_SITENAME++" @@ -482,7 +493,6 @@ our %feature = ( # 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 @@ -546,6 +556,29 @@ our %feature = ( '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 { @@ -624,6 +657,21 @@ sub feature_avatar { 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+/, $value; + } + } + + return @branch_refs; +} + # checking HEAD file with -e is fragile if the repository was # initialized long time ago (i.e. symlink HEAD) and was pack-ref'ed # and then pruned. @@ -654,6 +702,18 @@ sub filter_snapshot_fmts { !$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. @@ -684,14 +744,14 @@ sub evaluate_gitweb_config { our $GITWEB_CONFIG_SYSTEM = $ENV{'GITWEB_CONFIG_SYSTEM'} || "++GITWEB_CONFIG_SYSTEM++"; our $GITWEB_CONFIG_COMMON = $ENV{'GITWEB_CONFIG_COMMON'} || "++GITWEB_CONFIG_COMMON++"; - # Protect agains duplications of file names, to not read config twice. + # Protect against duplications of file names, to not read config twice. # Only one of $GITWEB_CONFIG and $GITWEB_CONFIG_SYSTEM is used, so # there possibility of duplication of filename there doesn't matter. $GITWEB_CONFIG = "" if ($GITWEB_CONFIG eq $GITWEB_CONFIG_COMMON); $GITWEB_CONFIG_SYSTEM = "" if ($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 @@ -738,6 +798,38 @@ 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(?:$y)?)/; +} + # input parameters can be collected from a variety of sources (presently, CGI # and PATH_INFO), so we define an %input_params hash that collects them all # together during validation: this allows subsequent uses (e.g. href()) to be @@ -828,7 +920,7 @@ sub evaluate_query_params { while (my ($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)); } @@ -992,7 +1084,7 @@ our ($action, $project, $file_name, $file_parent, $hash, $hash_parent, $hash_bas 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"); } } @@ -1000,7 +1092,7 @@ sub evaluate_and_validate_params { # 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"); } @@ -1008,21 +1100,21 @@ sub evaluate_and_validate_params { 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"); } } @@ -1030,21 +1122,21 @@ sub evaluate_and_validate_params { # 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"); } } @@ -1064,7 +1156,7 @@ sub evaluate_and_validate_params { 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"); } } @@ -1087,7 +1179,7 @@ sub evaluate_and_validate_params { our $search_use_regexp = $input_params{'search_use_regexp'}; our $searchtext = $input_params{'searchtext'}; - our $search_regexp; + our $search_regexp = undef; if (defined $searchtext) { if (length($searchtext) < 2) { die_error(403, "At least two characters are required for search parameter"); @@ -1111,24 +1203,21 @@ sub evaluate_git_dir { 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 ' is Internal Server Error @@ -1137,7 +1226,7 @@ sub handle_errors_html { # to avoid infinite loop where error occurs in die_error, # change handler to default handler, disabling handle_errors_html - set_message("Error occured when inside die_error:\n$msg"); + set_message("Error occurred when inside die_error:\n$msg"); # you cannot jump out of die_error when called as error handler; # the subroutine set via CGI::Carp::set_message is called _after_ @@ -1212,9 +1301,23 @@ our $is_last_request = sub { 1 }; our ($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 @@ -1416,28 +1519,31 @@ sub href { ## ====================================================================== ## 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!(^|/)(|\.|\.\.)(/|$)!) { @@ -1447,24 +1553,33 @@ sub validate_pathname { if ($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, @@ -1550,14 +1665,14 @@ sub esc_path { 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; return undef unless defined $str; $str = to_utf8($str); - $str =~ s|([[:cntrl:]])|($1 =~ /[\t\n\r]/ ? $1 : quot_cec($1))|eg; + $str =~ s|([[:cntrl:]])|(index("\t\n\r", $1) != -1 ? $1 : quot_cec($1))|eg; return $str; } @@ -1566,15 +1681,15 @@ sub quot_cec { 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} @@ -1969,11 +2084,28 @@ 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([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 + (?a({-href => href(action=>"object", hash=>$1), -class => "text"}, $1); - }eg; + }egx; return $line; } @@ -2024,7 +2156,7 @@ sub format_ref_marker { -href => href( action=>$dest_action, hash=>$dest - )}, $name); + )}, esc_html($name)); $markers .= " " . $link . ""; @@ -2069,7 +2201,7 @@ sub picon_url { if (!$avatar_cache{$email}) { my ($user, $domain) = split('@', $email); $avatar_cache{$email} = - "http://www.cs.indiana.edu/cgi-pub/kinzler/piconsearch.cgi/" . + "//www.cs.indiana.edu/cgi-pub/kinzler/piconsearch.cgi/" . "$domain/$user/" . "users+domains+unknown/up/single"; } @@ -2084,8 +2216,8 @@ sub gravatar_url { my $email = lc shift; my $size = shift; $avatar_cache{$email} ||= - "http://www.gravatar.com/avatar/" . - Digest::MD5::md5_hex($email) . "?s="; + "//www.gravatar.com/avatar/" . + md5_hex($email) . "?s="; return $avatar_cache{$email} . $size; } @@ -2213,7 +2345,8 @@ sub format_extended_diff_header_line { ')'; } # match - if ($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++) { @@ -2235,7 +2368,8 @@ 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'}) { @@ -2513,6 +2647,7 @@ sub format_snapshot_links { 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 $project); @@ -2520,12 +2655,17 @@ sub get_feed_info { # or don't have specific feed yet (so they should use generic) return if (!$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'; @@ -2538,7 +2678,7 @@ sub get_feed_info { } $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; @@ -2755,7 +2895,7 @@ 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 $2) { # type doesn't match return undef; @@ -2985,6 +3125,8 @@ sub git_get_projects_list { return if (m!^[/.]$!); # 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) { @@ -3039,7 +3181,7 @@ sub git_get_projects_list { 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 $projects = shift; @@ -3191,7 +3333,7 @@ sub git_get_last_activity { '--format=%(committer)', '--sort=-committerdate', '--count=1', - 'refs/heads') or return; + map { "refs/$_" } get_branch_refs ()) or return; my $most_recent = <$fd>; close $fd or return; if (defined $most_recent && @@ -3252,7 +3394,7 @@ 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 { @@ -3317,6 +3459,13 @@ sub parse_date { return %date; } +sub hide_mailaddrs_if_private { + my $line = shift; + return $line unless gitweb_check_feature('email-privacy'); + $line =~ s/<[^@>]+@[^>]+>//g; + return $line; +} + sub parse_tag { my $tag_id = shift; my %tag; @@ -3326,14 +3475,14 @@ 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'} = $1; } elsif ($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/^([^<]+) <([^>]*)>/) { @@ -3370,18 +3519,18 @@ 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); + $co{'author'} = hide_mailaddrs_if_private(to_utf8($1)); $co{'author_epoch'} = $2; $co{'author_tz'} = $3; if ($co{'author'} =~ m/^([^<]+) <([^>]*)>/) { @@ -3391,7 +3540,7 @@ sub parse_commit_text { $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/^([^<]+) <([^>]*)>/) { @@ -3436,9 +3585,10 @@ sub parse_commit_text { 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); } $co{'comment'} = \@commit_lines; @@ -3510,7 +3660,7 @@ sub parse_difftree_raw_line { # ':100644 100644 03b218260e99b78c6df0ed378e59ed9205ccc96d 3b93d5e7cc7f7dd4ebed13a5cc1a4ad976fc94d8 M ls-files.c' # ':100644 100644 7f9281985086971d3877aca27704f2aaf9c448ce bc190ebc71bbd923f2b728e505408f5e54bd073a M rev-tree.c' - if ($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'} = $3; @@ -3525,7 +3675,7 @@ sub parse_difftree_raw_line { } # '::100755 100755 100755 60e79ca1b01bc8b057abe17ddab484699a7f5fdb 94067cc5f73388f33722d52ae02f44692bc07490 94067cc5f73388f33722d52ae02f44692bc07490 MR git-gui/git-gui.sh' # combined diff (for merge commit) - elsif ($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'}}; @@ -3535,7 +3685,7 @@ 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'} = $1; } @@ -3563,7 +3713,7 @@ sub parse_ls_tree_line { if ($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; @@ -3576,7 +3726,7 @@ 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'} = $2; @@ -3642,12 +3792,13 @@ sub parse_from_to_diffinfo { sub git_get_heads_list { my ($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='.($limit+1) : ()), + '--sort=-HEAD', '--sort=-committerdate', '--format=%(objectname) %(refname) %(subject)%00%(committer)', @patterns or return; @@ -3660,9 +3811,16 @@ sub git_get_heads_list { my ($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'} = $epoch; @@ -3834,7 +3992,7 @@ sub blob_contenttype { # guess file syntax for syntax highlighting; return undef if no highlighting # the name of syntax can (in the future) depend on syntax highlighter used sub guess_file_syntax { - my ($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} @@ -3852,12 +4010,16 @@ sub guess_file_syntax { # 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; } @@ -3919,7 +4081,7 @@ sub print_feed_meta { $href_params{'extra_options'} = undef; $href_params{'action'} = $type; - $link_attr{'-href'} = href(%href_params); + $link_attr{'-href'} = esc_attr(href(%href_params)); print "\n"; $href_params{'extra_options'} = '--no-merges'; - $link_attr{'-href'} = href(%href_params); + $link_attr{'-href'} = esc_attr(href(%href_params)); $link_attr{'-title'} .= ' (no merges)'; print "'."\n", - esc_attr($site_name), href(project=>undef, action=>"project_index")); + esc_attr($site_name), + esc_attr(href(project=>undef, action=>"project_index"))); printf(''."\n", - esc_attr($site_name), href(project=>undef, action=>"opml")); + esc_attr($site_name), + esc_attr(href(project=>undef, action=>"opml"))); } } @@ -3983,7 +4147,9 @@ sub print_nav_breadcrumbs_path { sub print_nav_breadcrumbs { my %opts = @_; - print $cgi->a({-href => esc_url($home_link)}, $home_link_str) . " / "; + for my $crumb (@extra_breadcrumbs, [ $home_link_str => $home_link ]) { + print $cgi->a({-href => esc_url($crumb->[1])}, $crumb->[0]) . " / "; + } if (defined $project) { my @dirname = split '/', $project; my $projectbasename = pop @dirname; @@ -4023,7 +4189,7 @@ sub print_search_form { if ($use_pathinfo) { $action .= "/".esc_url($project); } - print $cgi->startform(-method => "get", -action => $action) . + print $cgi->start_form(-method => "get", -action => $action) . "
\n" . (!$use_pathinfo && $cgi->input({-name=>"p", -value=>$project, -type=>"hidden"}) . "\n") . @@ -4031,8 +4197,8 @@ sub print_search_form { $cgi->input({-name=>"h", -value=>$search_hash, -type=>"hidden"}) . "\n" . $cgi->popup_menu(-name => 'st', -default => 'commit', -values => ['commit', 'grep', 'author', 'committer', 'pickaxe']) . - $cgi->sup($cgi->a({-href => href(action=>"search_help")}, "?")) . - " search:\n", + " " . $cgi->a({-href => href(action=>"search_help"), + -title => "search help" }, "?") . " search:\n", $cgi->textfield(-name => "s", -value => $searchtext, -override => 1) . "\n" . "" . $cgi->checkbox(-name => 'sr', -value => 1, -label => 're', @@ -4048,19 +4214,20 @@ sub git_header_html { 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'}" : ''; print < - + + +]> - $title @@ -4156,8 +4323,8 @@ sub git_footer_html { if (defined $action && $action eq 'blame_incremental') { print qq!\n!; } else { my ($jstimezone, $tz_cookie, $datetime_class) = @@ -4277,7 +4444,7 @@ sub git_print_page_nav { "
\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 { @@ -4494,7 +4661,7 @@ sub git_print_log { # 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 (! $opts{'-remove_signoff'}) { print "" . esc_html($line) . "
\n"; $skip_blank_line = 1; @@ -4705,7 +4872,7 @@ 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) || $diffinfo->{'to_id'} eq ('0' x 64); } # does patch correspond to [previous] difftree raw line @@ -5152,7 +5319,7 @@ sub format_ctx_rem_add_lines { # + c # + d # - # Otherwise the highlightling would be confusing. + # Otherwise the highlighting would be confusing. if ($is_combined) { for (my $i = 0; $i < @$add; $i++) { my $prefix_rem = substr($rem->[$i], 0, $num_parents); @@ -5433,7 +5600,7 @@ sub git_project_search_form { } print "
\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); @@ -5866,6 +6033,9 @@ sub git_history_body { $cgi->a({-href => href(action=>"commitdiff", hash=>$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 $blob_parent && @@ -6188,7 +6358,7 @@ sub git_search_changes { -class => "list subject"}, chop_and_escape_str($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'}), @@ -6464,7 +6634,7 @@ sub git_summary { print "
 
\n"; print "\n" . "\n"; - unless ($omit_owner) { + if ($owner and not $omit_owner) { print "\n"; } if (defined $cd{'rfc2822'}) { @@ -6627,6 +6797,7 @@ sub git_blame_common { $hash_base, '--', $file_name or die_error(500, "Open git-blame --porcelain failed"); } + binmode $fd, ':utf8'; # incremental blame data returns early if ($format eq 'data') { @@ -6731,7 +6902,7 @@ 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 }; } @@ -6781,7 +6952,7 @@ 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($2); } @@ -6898,7 +7069,7 @@ sub git_blob_plain { } else { die_error(400, "No file name defined"); } - } elsif ($hash =~ m/^[0-9a-fA-F]{40}$/) { + } elsif ($hash =~ m/^$oid_regex$/) { # blobs defined by non-textual hash id's can be cached $expires = "+1d"; } @@ -6942,6 +7113,7 @@ sub git_blob_plain { ($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 @@ -6959,7 +7131,7 @@ 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"; } @@ -6977,9 +7149,8 @@ sub git_blob { $have_blame &&= ($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 $formats_nav = ''; @@ -7016,13 +7187,13 @@ sub git_blob { git_print_page_path($file_name, "blob", $hash_base); print "
\n"; if ($mimetype =~ m!^image/!) { - print qq!!.esc_attr($file_name).qq!$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; @@ -7032,7 +7203,7 @@ sub git_blob { $line = untabify($line); printf qq!
%4i %s
\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 @@ -7151,6 +7322,15 @@ sub git_tree { 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) = @_; @@ -7158,9 +7338,7 @@ sub snapshot_name { # 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]+$/) { @@ -7174,13 +7352,25 @@ sub snapshot_name { $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"; @@ -7262,6 +7452,7 @@ sub git_snapshot { 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 @@ -7318,7 +7509,8 @@ sub git_log_generic { -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 .= " ⋅ " . $cgi->a({-href => href(action=>"patches", -replay=>1)}, @@ -7379,7 +7571,8 @@ sub git_commit { } @$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"); @@ -7399,7 +7592,7 @@ 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(); @@ -7475,7 +7668,7 @@ sub git_object { 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"); @@ -7486,14 +7679,14 @@ sub git_object { system(git_cmd(), "cat-file", '-e', $hash_base) == 0 or die_error(404, "Base object does not exist"); - # here errors should not hapen + # here errors should not happen open my $fd, "-|", git_cmd(), "ls-tree", $hash_base, "--", $file_name or die_error(500, "Open git-ls-tree failed"); my $line = <$fd>; 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; @@ -7533,7 +7726,7 @@ 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 @@ -7543,7 +7736,7 @@ 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"); @@ -7566,8 +7759,8 @@ 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'; } @@ -7692,7 +7885,8 @@ sub git_commitdiff { $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"); @@ -7703,7 +7897,7 @@ 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 .= @@ -7812,7 +8006,7 @@ 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"; } @@ -7967,7 +8161,7 @@ sub git_search_help {

Pattern 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 re checkbox, the pattern entered is recognized as the POSIX extended -regular expression (also case +regular expression (also case insensitive).

commit
@@ -8086,6 +8280,7 @@ sub git_feed { } else { $alt_url = href(-full=>1, action=>"summary"); } + $alt_url = esc_attr($alt_url); print qq!\n!; if ($format eq 'rss') { print <' . "\n" . '' . "\n" . - "" . href(-full=>1) . "\n" . + "" . esc_url(href(-full=>1)) . "\n" . # use project owner for feed author "$owner\n"; if (defined $favicon) { @@ -8169,7 +8364,7 @@ XML "" . esc_html($co{'author'}) . "\n" . "$cd{'rfc2822'}\n" . "$co_url\n" . - "$co_url\n" . + "" . esc_html($co_url) . "\n" . "" . esc_html($co{'title'}) . "\n" . "" . "\n" . "$cd{'iso-8601'}\n" . - "\n" . - "$co_url\n" . + "\n" . + "" . esc_html($co_url) . "\n" . "\n" . "
\n"; } @@ -8299,8 +8494,8 @@ XML } my $path = esc_html(chop_str($proj{'path'}, 25, 5)); - my $rss = href('project' => $proj{'path'}, 'action' => 'rss', -full => 1); - my $html = href('project' => $proj{'path'}, 'action' => 'summary', -full => 1); + my $rss = esc_attr(href('project' => $proj{'path'}, 'action' => 'rss', -full => 1)); + my $html = esc_attr(href('project' => $proj{'path'}, 'action' => 'summary', -full => 1)); print "\n"; } print <
description" . esc_html($descr) . "
owner" . esc_html($owner) . "