X-Git-Url: https://git.ladys.computer/Gitweb/blobdiff_plain/4a5ce424e69c73a4367a78e7f977b1fec1a3b2b261278f8c3da9325540e4e6db..HEAD:/gitweb.perl?ds=inline diff --git a/gitweb.perl b/gitweb.perl index 280319a..8c96a1d 100755 --- a/gitweb.perl +++ b/gitweb.perl @@ -7,33 +7,75 @@ # # This program is licensed under the GPLv2 +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); +use CGI::Carp qw(fatalsToBrowser set_message); use Encode; 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; + BEGIN { CGI->compile() if $ENV{'MOD_PERL'}; } -our $cgi = new CGI; our $version = "++GIT_VERSION++"; -our $my_url = $cgi->url(); -our $my_uri = $cgi->url(-absolute => 1); -# if we're called with PATH_INFO, we have to strip that -# from the URL to find our real URL -# we make $path_info global because it's also used later on -my $path_info = $ENV{"PATH_INFO"}; -if ($path_info) { - $my_url =~ s,\Q$path_info\E$,,; - $my_uri =~ s,\Q$path_info\E$,,; +our ($my_url, $my_uri, $base_url, $path_info, $home_link); +sub evaluate_uri { + our $cgi; + + our $my_url = $cgi->url(); + our $my_uri = $cgi->url(-absolute => 1); + + # Base URL for relative URLs in gitweb ($logo, $favicon, ...), + # needed and used only for URLs with nonempty PATH_INFO + our $base_url = $my_url; + + # When the script is used as DirectoryIndex, the URL does not contain the name + # of the script file itself, and $cgi->url() fails to strip PATH_INFO, so we + # have to do it ourselves. We make $path_info global because it's also used + # later on. + # + # Another issue with the script being the DirectoryIndex is that the resulting + # $my_url data is not the full script URL: this is good, because we want + # generated links to keep implying the script name if it wasn't explicitly + # indicated in the URL we're handling, but it means that $my_url cannot be used + # as base URL. + # Therefore, if we needed to strip PATH_INFO, then we know that we have + # to build the base URL ourselves: + our $path_info = decode_utf8($ENV{"PATH_INFO"}); + if ($path_info) { + # $path_info has already been URL-decoded by the web server, but + # $my_url and $my_uri have not. URL-decode them so we can properly + # strip $path_info. + $my_url = unescape($my_url); + $my_uri = unescape($my_uri); + if ($my_url =~ s,\Q$path_info\E$,, && + $my_uri =~ s,\Q$path_info\E$,, && + defined $ENV{'SCRIPT_NAME'}) { + $base_url = $cgi->url(-base => 1) . $ENV{'SCRIPT_NAME'}; + } + } + + # target of the home link on top of all pages + our $home_link = $my_uri || "/"; } # core git executable to use @@ -48,17 +90,19 @@ our $projectroot = "++GITWEB_PROJECTROOT++"; # the number is relative to the projectroot our $project_maxdepth = "++GITWEB_PROJECT_MAXDEPTH++"; -# target of the home link on top of all pages -our $home_link = $my_uri || "/"; - # 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 $site_name = "++GITWEB_SITENAME++" || ($ENV{'SERVER_NAME'} || "Untitled") . " Git"; +# html snippet to include in the section of each page +our $site_html_head_string = "++GITWEB_SITE_HTML_HEAD_STRING++"; # filename of html text to include at top of each page our $site_header = "++GITWEB_SITE_HEADER++"; # html text to include at home page @@ -75,11 +119,13 @@ our $stylesheet = undef; our $logo = "++GITWEB_LOGO++"; # URI of GIT favicon, assumed to be image/png type our $favicon = "++GITWEB_FAVICON++"; +# URI of gitweb.js (JavaScript code for gitweb) +our $javascript = "++GITWEB_JS++"; # URI and label (title) of GIT logo link #our $logo_url = "http://www.kernel.org/pub/software/scm/git/docs/"; #our $logo_label = "git documentation"; -our $logo_url = "http://git.or.cz/"; +our $logo_url = "http://git-scm.com/"; our $logo_label = "git homepage"; # source of projects list @@ -88,6 +134,14 @@ our $projects_list = "++GITWEB_LIST++"; # the width (in characters) of the projects list "Description" column our $projects_list_description_width = 25; +# group projects by category on the projects list +# (enabled if this variable evaluates to true) +our $projects_list_group_categories = 0; + +# default category if none specified +# (leave the empty string for no category) +our $project_list_default_category = ""; + # default order of projects list # valid values are none, project, descr, owner, and age our $default_projects_order = "project"; @@ -96,6 +150,17 @@ our $default_projects_order = "project"; # (only effective if this variable evaluates to true) our $export_ok = "++GITWEB_EXPORT_OK++"; +# don't generate age column on the projects list page +our $omit_age_column = 0; + +# don't generate information about owners of repositories +our $omit_owner=0; + +# show repository only if this subroutine returns true +# when given the path to the project, for example: +# sub { return -e "$_[0]/git-daemon-export-ok"; } +our $export_auth_hook = undef; + # only allow viewing of repositories also shown on the overview page our $strict_export = "++GITWEB_STRICT_EXPORT++"; @@ -128,6 +193,16 @@ our $fallback_encoding = 'latin1'; # - one might want to include '-B' option, e.g. '-B', '-M' our @diff_opts = ('-M'); # taken from git_commit +# Disables features that would allow repository owners to inject script into +# the gitweb domain. +our $prevent_xss = 0; + +# Path to the highlight executable to use (must be the one from +# http://www.andre-simon.de due to assumptions about parameters and output). +# Useful if highlight is not installed on your webserver's PATH. +# [Default: highlight] +our $highlight_bin = "++HIGHLIGHT_BIN++"; + # information about snapshot formats that gitweb is capable of serving our %known_snapshot_formats = ( # name => { @@ -136,14 +211,15 @@ our %known_snapshot_formats = ( # 'suffix' => filename suffix, # 'format' => --format for git-archive, # 'compressor' => [compressor command and arguments] - # (array reference, optional)} + # (array reference, optional) + # 'disabled' => boolean (optional)} # 'tgz' => { 'display' => 'tar.gz', 'type' => 'application/x-gzip', 'suffix' => '.tar.gz', 'format' => 'tar', - 'compressor' => ['gzip']}, + 'compressor' => ['gzip', '-n']}, 'tbz2' => { 'display' => 'tar.bz2', @@ -152,6 +228,14 @@ our %known_snapshot_formats = ( 'format' => 'tar', 'compressor' => ['bzip2']}, + 'txz' => { + 'display' => 'tar.xz', + 'type' => 'application/x-xz', + 'suffix' => '.tar.xz', + 'format' => 'tar', + 'compressor' => ['xz'], + 'disabled' => 1}, + 'zip' => { 'display' => 'zip', 'type' => 'application/x-zip', @@ -164,6 +248,7 @@ our %known_snapshot_formats = ( our %known_snapshot_format_aliases = ( 'gzip' => 'tgz', 'bzip2' => 'tbz2', + 'xz' => 'txz', # backward compatibility: legacy gitweb config support 'x-gzip' => undef, 'gz' => undef, @@ -171,6 +256,43 @@ our %known_snapshot_format_aliases = ( 'x-zip' => undef, '' => undef, ); +# Pixel sizes for icons and avatars. If the default font sizes or lineheights +# are changed, it may be appropriate to change these values too via +# $GITWEB_CONFIG. +our %avatar_size = ( + 'default' => 16, + 'double' => 32 +); + +# Used to set the maximum load that we will still respond to gitweb queries. +# If server load exceed this value then return "503 server busy" error. +# If gitweb cannot determined server load, it is taken to be 0. +# Leave it undefined (or set to 'undef') to turn off load checking. +our $maxload = 300; + +# configuration for 'highlight' (http://www.andre-simon.de/) +# match by basename +our %highlight_basename = ( + #'Program' => 'py', + #'Library' => 'py', + 'SConstruct' => 'py', # SCons equivalent of Makefile + 'Makefile' => 'make', +); +# match by extension +our %highlight_ext = ( + # main extensions, defining name of syntax; + # see files in /usr/share/highlight/langDefs/ directory + (map { $_ => $_ } qw(py rb java css js tex bib xml awk bat ini spec tcl sql)), + # alternate extensions, see /etc/highlight/filetypes.conf + (map { $_ => 'c' } qw(c h)), + (map { $_ => 'sh' } qw(sh bash zsh ksh)), + (map { $_ => 'cpp' } qw(cpp cxx c++ cc)), + (map { $_ => 'php' } qw(php php3 php4 php5 phps)), + (map { $_ => 'pl' } qw(pl perl pm)), # perhaps also 'cgi' + (map { $_ => 'make'} qw(make mak mk)), + (map { $_ => 'xml' } qw(xml xhtml html htm)), +); + # You define site-wide feature defaults here; override them with # $GITWEB_CONFIG as necessary. our %feature = ( @@ -184,9 +306,11 @@ our %feature = ( # return value of feature-sub indicates if to enable specified feature # # if there is no 'sub' key (no feature-sub), then feature cannot be - # overriden + # overridden # - # use gitweb_check_feature() to check if is enabled + # use gitweb_get_feature() to retrieve the value + # (an array) or gitweb_check_feature() to check if + # is enabled # Enable the 'blame' blob view, showing the last commit that modified # each line in the file. This can be very CPU-intensive. @@ -197,7 +321,7 @@ our %feature = ( # $feature{'blame'}{'override'} = 1; # and in project config gitweb.blame = 0|1; 'blame' => { - 'sub' => \&feature_blame, + 'sub' => sub { feature_bool('blame', @_) }, 'override' => 0, 'default' => [0]}, @@ -221,6 +345,10 @@ our %feature = ( # Enable text search, which will list the commits which match author, # committer or commit text to a given string. Enabled by default. # Project specific override is not supported. + # + # Note that this controls all search features, which means that if + # it is disabled, then 'grep' and 'pickaxe' search would also be + # disabled. 'search' => { 'override' => 0, 'default' => [1]}, @@ -228,6 +356,7 @@ our %feature = ( # Enable grep search, which will list the files in currently selected # tree containing the given string. Enabled by default. This can be # potentially CPU-intensive, of course. + # Note that you need to have 'search' feature enabled too. # To enable system wide have in $GITWEB_CONFIG # $feature{'grep'}{'default'} = [1]; @@ -235,12 +364,14 @@ our %feature = ( # $feature{'grep'}{'override'} = 1; # and in project config gitweb.grep = 0|1; 'grep' => { + 'sub' => sub { feature_bool('grep', @_) }, 'override' => 0, 'default' => [1]}, # Enable the pickaxe search, which will list the commits that modified # a given string in a file. This can be practical and quite faster # alternative to 'blame', but still potentially CPU-intensive. + # Note that you need to have 'search' feature enabled too. # To enable system wide have in $GITWEB_CONFIG # $feature{'pickaxe'}{'default'} = [1]; @@ -248,7 +379,20 @@ our %feature = ( # $feature{'pickaxe'}{'override'} = 1; # and in project config gitweb.pickaxe = 0|1; 'pickaxe' => { - 'sub' => \&feature_pickaxe, + 'sub' => sub { feature_bool('pickaxe', @_) }, + 'override' => 0, + 'default' => [1]}, + + # Enable showing size of blobs in a 'tree' view, in a separate + # column, similar to what 'ls -l' does. This cost a bit of IO. + + # To disable system wide have in $GITWEB_CONFIG + # $feature{'show-sizes'}{'default'} = [0]; + # To have project specific config enable override in $GITWEB_CONFIG + # $feature{'show-sizes'}{'override'} = 1; + # and in project config gitweb.showsizes = 0|1; + 'show-sizes' => { + 'sub' => sub { feature_bool('showsizes', @_) }, 'override' => 0, 'default' => [1]}, @@ -306,50 +450,183 @@ our %feature = ( 'override' => 0, 'default' => []}, - # Allow gitweb scan project content tags described in ctags/ - # of project repository, and display the popular Web 2.0-ish - # "tag cloud" near the project list. Note that this is something - # COMPLETELY different from the normal Git tags. + # Allow gitweb scan project content tags of project repository, + # and display the popular Web 2.0-ish "tag cloud" near the projects + # list. Note that this is something COMPLETELY different from the + # normal Git tags. # gitweb by itself can show existing tags, but it does not handle - # tagging itself; you need an external application for that. - # For an example script, check Girocco's cgi/tagproj.cgi. + # tagging itself; you need to do it externally, outside gitweb. + # The format is described in git_get_project_ctags() subroutine. # You may want to install the HTML::TagCloud Perl module to get # a pretty tag cloud instead of just a list of tags. # To enable system wide have in $GITWEB_CONFIG - # $feature{'ctags'}{'default'} = ['path_to_tag_script']; + # $feature{'ctags'}{'default'} = [1]; # Project specific override is not supported. + + # In the future whether ctags editing is enabled might depend + # on the value, but using 1 should always mean no editing of ctags. 'ctags' => { 'override' => 0, 'default' => [0]}, + + # The maximum number of patches in a patchset generated in patch + # view. Set this to 0 or undef to disable patch view, or to a + # negative number to remove any limit. + + # To disable system wide have in $GITWEB_CONFIG + # $feature{'patches'}{'default'} = [0]; + # To have project specific config enable override in $GITWEB_CONFIG + # $feature{'patches'}{'override'} = 1; + # and in project config gitweb.patches = 0|n; + # where n is the maximum number of patches allowed in a patchset. + 'patches' => { + 'sub' => \&feature_patches, + 'override' => 0, + 'default' => [16]}, + + # Avatar support. When this feature is enabled, views such as + # shortlog or commit will display an avatar associated with + # the email of the committer(s) and/or author(s). + + # Currently available providers are gravatar and picon. + # If an unknown provider is specified, the feature is disabled. + + # Picon currently relies on the indiana.edu database. + + # To enable system wide have in $GITWEB_CONFIG + # $feature{'avatar'}{'default'} = ['']; + # where is either gravatar or picon. + # To have project specific config enable override in $GITWEB_CONFIG + # $feature{'avatar'}{'override'} = 1; + # and in project config gitweb.avatar = ; + 'avatar' => { + 'sub' => \&feature_avatar, + 'override' => 0, + 'default' => ['']}, + + # Enable displaying how much time and how many git commands + # it took to generate and display page. Disabled by default. + # Project specific override is not supported. + 'timed' => { + 'override' => 0, + 'default' => [0]}, + + # Enable turning some links into links to actions which require + # JavaScript to run (like 'blame_incremental'). Not enabled by + # default. Project specific override is currently not supported. + 'javascript-actions' => { + 'override' => 0, + 'default' => [0]}, + + # Enable and configure ability to change common timezone for dates + # in gitweb output via JavaScript. Enabled by default. + # Project specific override is not supported. + 'javascript-timezone' => { + 'override' => 0, + 'default' => [ + 'local', # default timezone: 'utc', 'local', or '(-|+)HHMM' format, + # or undef to turn off this feature + 'gitweb_tz', # name of cookie where to store selected timezone + 'datetime', # CSS class used to mark up dates for manipulation + ]}, + + # Syntax highlighting support. This is based on Daniel Svensson's + # and Sham Chukoury's work in gitweb-xmms2.git. + # It requires the 'highlight' program present in $PATH, + # and therefore is disabled by default. + + # To enable system wide have in $GITWEB_CONFIG + # $feature{'highlight'}{'default'} = [1]; + + 'highlight' => { + 'sub' => sub { feature_bool('highlight', @_) }, + 'override' => 0, + 'default' => [0]}, + + # Enable displaying of remote heads in the heads list + + # To enable system wide have in $GITWEB_CONFIG + # $feature{'remote_heads'}{'default'} = [1]; + # To have project specific config enable override in $GITWEB_CONFIG + # $feature{'remote_heads'}{'override'} = 1; + # and in project config gitweb.remoteheads = 0|1; + 'remote_heads' => { + '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 + # $feature{'email-privacy'}{'default'} = [1]; + 'email-privacy' => { + 'sub' => sub { feature_bool('email-privacy', @_) }, + 'override' => 1, + 'default' => [0]}, ); -sub gitweb_check_feature { +sub gitweb_get_feature { my ($name) = @_; return unless exists $feature{$name}; my ($sub, $override, @defaults) = ( $feature{$name}{'sub'}, $feature{$name}{'override'}, @{$feature{$name}{'default'}}); - if (!$override) { return @defaults; } + # project specific override is possible only if we have project + our $git_dir; # global variable, declared later + if (!$override || !defined $git_dir) { + return @defaults; + } if (!defined $sub) { - warn "feature $name is not overrideable"; + warn "feature $name is not overridable"; return @defaults; } return $sub->(@defaults); } -sub feature_blame { - my ($val) = git_get_project_config('blame', '--bool'); +# A wrapper to check if a given feature is enabled. +# With this, you can say +# +# my $bool_feat = gitweb_check_feature('bool_feat'); +# gitweb_check_feature('bool_feat') or somecode; +# +# instead of +# +# my ($bool_feat) = gitweb_get_feature('bool_feat'); +# (gitweb_get_feature('bool_feat'))[0] or somecode; +# +sub gitweb_check_feature { + return (gitweb_get_feature(@_))[0]; +} + - if ($val eq 'true') { - return 1; +sub feature_bool { + my $key = shift; + my ($val) = git_get_project_config($key, '--bool'); + + if (!defined $val) { + return ($_[0]); + } elsif ($val eq 'true') { + return (1); } elsif ($val eq 'false') { - return 0; + return (0); } - - return $_[0]; } sub feature_snapshot { @@ -364,28 +641,35 @@ sub feature_snapshot { return @fmts; } -sub feature_grep { - my ($val) = git_get_project_config('grep', '--bool'); +sub feature_patches { + my @val = (git_get_project_config('patches', '--int')); - if ($val eq 'true') { - return (1); - } elsif ($val eq 'false') { - return (0); + if (@val) { + return @val; } return ($_[0]); } -sub feature_pickaxe { - my ($val) = git_get_project_config('pickaxe', '--bool'); +sub feature_avatar { + my @val = (git_get_project_config('avatar')); - if ($val eq 'true') { - return (1); - } elsif ($val eq 'false') { - return (0); + 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+/, $value; + } } - return ($_[0]); + return @branch_refs; } # checking HEAD file with -e is fragile if the repository was @@ -401,7 +685,8 @@ sub check_head_link { sub check_export_ok { my ($dir) = @_; return (check_head_link($dir) && - (!$export_ok || -e "$dir/$export_ok")); + (!$export_ok || -e "$dir/$export_ok") && + (!$export_auth_hook || $export_auth_hook->($dir))); } # process alternate names for backward compatibility @@ -412,32 +697,145 @@ sub filter_snapshot_fmts { @fmts = map { exists $known_snapshot_format_aliases{$_} ? $known_snapshot_format_aliases{$_} : $_} @fmts; - @fmts = grep(exists $known_snapshot_formats{$_}, @fmts); + @fmts = grep { + exists $known_snapshot_formats{$_} && + !$known_snapshot_formats{$_}{'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. +# +# Otherwise, if it is false then gitweb would process config file only once; +# if it is true then gitweb config would be run for each request. +our $per_request_config = 1; + +# read and parse gitweb config file given by its parameter. +# returns true on success, false on recoverable error, allowing +# to chain this subroutine, using first file that exists. +# dies on errors during parsing config file, as it is unrecoverable. +sub read_config_file { + my $filename = shift; + return unless defined $filename; + # die if there are errors parsing config file + if (-e $filename) { + do $filename; + die $@ if $@; + return 1; + } + return; } -our $GITWEB_CONFIG = $ENV{'GITWEB_CONFIG'} || "++GITWEB_CONFIG++"; -if (-e $GITWEB_CONFIG) { - do $GITWEB_CONFIG; -} else { +our ($GITWEB_CONFIG, $GITWEB_CONFIG_SYSTEM, $GITWEB_CONFIG_COMMON); +sub evaluate_gitweb_config { + our $GITWEB_CONFIG = $ENV{'GITWEB_CONFIG'} || "++GITWEB_CONFIG++"; our $GITWEB_CONFIG_SYSTEM = $ENV{'GITWEB_CONFIG_SYSTEM'} || "++GITWEB_CONFIG_SYSTEM++"; - do $GITWEB_CONFIG_SYSTEM if -e $GITWEB_CONFIG_SYSTEM; + our $GITWEB_CONFIG_COMMON = $ENV{'GITWEB_CONFIG_COMMON'} || "++GITWEB_CONFIG_COMMON++"; + + # 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 $GITWEB_CONFIG_COMMON); + + # Common system-wide settings for convenience. + # Those settings can be overridden by GITWEB_CONFIG or GITWEB_CONFIG_SYSTEM. + read_config_file($GITWEB_CONFIG_COMMON); + + # Use first config file that exists. This means use the per-instance + # GITWEB_CONFIG if exists, otherwise use GITWEB_SYSTEM_CONFIG. + read_config_file($GITWEB_CONFIG) and return; + read_config_file($GITWEB_CONFIG_SYSTEM); +} + +# Get loadavg of system, to compare against $maxload. +# Currently it requires '/proc/loadavg' present to get loadavg; +# if it is not present it returns 0, which means no load checking. +sub get_loadavg { + if( -e '/proc/loadavg' ){ + open my $fd, '<', '/proc/loadavg' + or return 0; + my @load = split(/\s+/, scalar <$fd>); + close $fd; + + # The first three columns measure CPU and IO utilization of the last one, + # five, and 10 minute periods. The fourth column shows the number of + # currently running processes and the total number of processes in the m/n + # format. The last column displays the last process ID used. + return $load[0] || 0; + } + # additional checks for load average should go here for things that don't export + # /proc/loadavg + + return 0; } # version of the core git binary -our $git_version = qx("$GIT" --version) =~ m/git version (.*)$/ ? $1 : "unknown"; +our $git_version; +sub evaluate_git_version { + our $git_version = qx("$GIT" --version) =~ m/git version (.*)$/ ? $1 : "unknown"; + $number_of_git_cmds++; +} -$projects_list ||= $projectroot; +sub check_loadavg { + if (defined $maxload && get_loadavg() > $maxload) { + die_error(503, "The load average on the server is too high"); + } +} # ====================================================================== # 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 # agnostic of the parameter origin -my %input_params = (); +our %input_params = (); # input parameters are stored with the long parameter name as key. This will # also be used in the href subroutine to convert parameters to their CGI @@ -447,7 +845,7 @@ my %input_params = (); # XXX: Warning: If you touch this, check the search form for updating, # too. -my @cgi_param_mapping = ( +our @cgi_param_mapping = ( project => "p", action => "a", file_name => "f", @@ -463,12 +861,19 @@ my @cgi_param_mapping = ( snapshot_format => "sf", extra_options => "opt", search_use_regexp => "sr", + ctag => "by_tag", + diff_style => "ds", + project_filter => "pf", + # this must be last entry (for manipulation from JavaScript) + javascript => "js" ); -my %cgi_param_mapping = @cgi_param_mapping; +our %cgi_param_mapping = @cgi_param_mapping; # we will also need to know the possible actions, for validation -my %actions = ( +our %actions = ( "blame" => \&git_blame, + "blame_incremental" => \&git_blame_incremental, + "blame_data" => \&git_blame_data, "blobdiff" => \&git_blobdiff, "blobdiff_plain" => \&git_blobdiff_plain, "blob" => \&git_blob, @@ -480,6 +885,9 @@ my %actions = ( "heads" => \&git_heads, "history" => \&git_history, "log" => \&git_log, + "patch" => \&git_patch, + "patches" => \&git_patches, + "remotes" => \&git_remotes, "rss" => \&git_rss, "atom" => \&git_atom, "search" => \&git_search, @@ -499,7 +907,7 @@ my %actions = ( # finally, we have the hash of allowed extra_options for the commands that # allow them -my %allowed_options = ( +our %allowed_options = ( "--no-merges" => [ qw(rss atom log shortlog history) ], ); @@ -507,11 +915,15 @@ my %allowed_options = ( # should be single values, but opt can be an array. We should probably # build an array of parameters that can be multi-valued, but since for the time # being it's only this one, we just single it out -while (my ($name, $symbol) = each %cgi_param_mapping) { - if ($symbol eq 'opt') { - $input_params{$name} = [ $cgi->param($symbol) ]; - } else { - $input_params{$name} = $cgi->param($symbol); +sub evaluate_query_params { + our $cgi; + + while (my ($name, $symbol) = each %cgi_param_mapping) { + if ($symbol eq 'opt') { + $input_params{$name} = [ map { decode_utf8($_) } $cgi->multi_param($symbol) ]; + } else { + $input_params{$name} = decode_utf8($cgi->param($symbol)); + } } } @@ -550,10 +962,10 @@ sub evaluate_path_info { 'history', ); - # we want to catch + # we want to catch, among others # [$hash_parent_base[:$file_parent]..]$hash_parent[:$file_name] my ($parentrefname, $parentpathname, $refname, $pathname) = - ($path_info =~ /^(?:(.+?)(?::(.+))?\.\.)?(.+?)(?::(.+))?$/); + ($path_info =~ /^(?:(.+?)(?::(.+))?\.\.)?([^:]+?)?(?::(.+))?$/); # first, analyze the 'current' part if (defined $pathname) { @@ -589,8 +1001,15 @@ sub evaluate_path_info { # hash_base instead. It should also be noted that hand-crafted # links having 'history' as an action and no pathname or hash # set will fail, but that happens regardless of PATH_INFO. - $input_params{'action'} ||= "shortlog"; - if (grep { $_ eq $input_params{'action'} } @wants_base) { + if (defined $parentrefname) { + # if there is parent let the default be 'shortlog' action + # (for http://git.example.com/repo.git/A..B links); if there + # is no parent, dispatch will detect type of object and set + # action appropriately if required (if action is not set) + $input_params{'action'} ||= "shortlog"; + } + if ($input_params{'action'} && + grep { $_ eq $input_params{'action'} } @wants_base) { $input_params{'hash_base'} ||= $refname; } else { $input_params{'hash'} ||= $refname; @@ -640,11 +1059,12 @@ sub evaluate_path_info { # extensions. Allowed extensions are both the defined suffix # (which includes the initial dot already) and the snapshot # format key itself, with a prepended dot - while (my ($fmt, %opt) = each %known_snapshot_formats) { + while (my ($fmt, $opt) = each %known_snapshot_formats) { my $hash = $refname; - my $sfx; - $hash =~ s/(\Q$opt{'suffix'}\E|\Q.$fmt\E)$//; - next unless $sfx = $1; + unless ($hash =~ s/(\Q$opt->{'suffix'}\E|\Q.$fmt\E)$//) { + next; + } + my $sfx = $1; # a valid suffix was found, so set the snapshot format # and reset the hash parameter $input_params{'snapshot_format'} = $fmt; @@ -657,144 +1077,327 @@ sub evaluate_path_info { } } } -evaluate_path_info(); -our $action = $input_params{'action'}; -if (defined $action) { - if (!validate_action($action)) { - die_error(400, "Invalid action parameter"); +our ($action, $project, $file_name, $file_parent, $hash, $hash_parent, $hash_base, + $hash_parent_base, @extra_options, $page, $searchtype, $search_use_regexp, + $searchtext, $search_regexp, $project_filter); +sub evaluate_and_validate_params { + our $action = $input_params{'action'}; + if (defined $action) { + if (!is_valid_action($action)) { + die_error(400, "Invalid action parameter"); + } } -} -# parameters which are pathnames -our $project = $input_params{'project'}; -if (defined $project) { - if (!validate_project($project)) { - undef $project; - die_error(404, "No such project"); + # parameters which are pathnames + our $project = $input_params{'project'}; + if (defined $project) { + if (!is_valid_project($project)) { + undef $project; + die_error(404, "No such project"); + } } -} -our $file_name = $input_params{'file_name'}; -if (defined $file_name) { - if (!validate_pathname($file_name)) { - die_error(400, "Invalid file parameter"); + our $project_filter = $input_params{'project_filter'}; + if (defined $project_filter) { + if (!is_valid_pathname($project_filter)) { + die_error(404, "Invalid project_filter parameter"); + } } -} -our $file_parent = $input_params{'file_parent'}; -if (defined $file_parent) { - if (!validate_pathname($file_parent)) { - die_error(400, "Invalid file parent parameter"); + our $file_name = $input_params{'file_name'}; + if (defined $file_name) { + if (!is_valid_pathname($file_name)) { + die_error(400, "Invalid file parameter"); + } } -} -# parameters which are refnames -our $hash = $input_params{'hash'}; -if (defined $hash) { - if (!validate_refname($hash)) { - die_error(400, "Invalid hash parameter"); + our $file_parent = $input_params{'file_parent'}; + if (defined $file_parent) { + if (!is_valid_pathname($file_parent)) { + die_error(400, "Invalid file parent parameter"); + } } -} -our $hash_parent = $input_params{'hash_parent'}; -if (defined $hash_parent) { - if (!validate_refname($hash_parent)) { - die_error(400, "Invalid hash parent parameter"); + # parameters which are refnames + our $hash = $input_params{'hash'}; + if (defined $hash) { + if (!is_valid_refname($hash)) { + die_error(400, "Invalid hash parameter"); + } } -} -our $hash_base = $input_params{'hash_base'}; -if (defined $hash_base) { - if (!validate_refname($hash_base)) { - die_error(400, "Invalid hash base parameter"); + our $hash_parent = $input_params{'hash_parent'}; + if (defined $hash_parent) { + if (!is_valid_refname($hash_parent)) { + die_error(400, "Invalid hash parent parameter"); + } } -} -our @extra_options = @{$input_params{'extra_options'}}; -# @extra_options is always defined, since it can only be (currently) set from -# CGI, and $cgi->param() returns the empty array in array context if the param -# is not set -foreach my $opt (@extra_options) { - if (not exists $allowed_options{$opt}) { - die_error(400, "Invalid option parameter"); + our $hash_base = $input_params{'hash_base'}; + if (defined $hash_base) { + if (!is_valid_refname($hash_base)) { + die_error(400, "Invalid hash base parameter"); + } } - if (not grep(/^$action$/, @{$allowed_options{$opt}})) { - die_error(400, "Invalid option parameter for this action"); + + our @extra_options = @{$input_params{'extra_options'}}; + # @extra_options is always defined, since it can only be (currently) set from + # CGI, and $cgi->param() returns the empty array in array context if the param + # is not set + foreach my $opt (@extra_options) { + if (not exists $allowed_options{$opt}) { + die_error(400, "Invalid option parameter"); + } + if (not grep(/^$action$/, @{$allowed_options{$opt}})) { + die_error(400, "Invalid option parameter for this action"); + } } -} -our $hash_parent_base = $input_params{'hash_parent_base'}; -if (defined $hash_parent_base) { - if (!validate_refname($hash_parent_base)) { - die_error(400, "Invalid hash parent base parameter"); + our $hash_parent_base = $input_params{'hash_parent_base'}; + if (defined $hash_parent_base) { + if (!is_valid_refname($hash_parent_base)) { + die_error(400, "Invalid hash parent base parameter"); + } } -} -# other parameters -our $page = $input_params{'page'}; -if (defined $page) { - if ($page =~ m/[^0-9]/) { - die_error(400, "Invalid page parameter"); + # other parameters + our $page = $input_params{'page'}; + if (defined $page) { + if ($page =~ m/[^0-9]/) { + die_error(400, "Invalid page parameter"); + } } -} -our $searchtype = $input_params{'searchtype'}; -if (defined $searchtype) { - if ($searchtype =~ m/[^a-z]/) { - die_error(400, "Invalid searchtype parameter"); + our $searchtype = $input_params{'searchtype'}; + if (defined $searchtype) { + if ($searchtype =~ m/[^a-z]/) { + die_error(400, "Invalid searchtype parameter"); + } } -} -our $search_use_regexp = $input_params{'search_use_regexp'}; + our $search_use_regexp = $input_params{'search_use_regexp'}; -our $searchtext = $input_params{'searchtext'}; -our $search_regexp; -if (defined $searchtext) { - if (length($searchtext) < 2) { - die_error(403, "At least two characters are required for search parameter"); + our $searchtext = $input_params{'searchtext'}; + our $search_regexp = undef; + if (defined $searchtext) { + if (length($searchtext) < 2) { + die_error(403, "At least two characters are required for search parameter"); + } + if ($search_use_regexp) { + $search_regexp = $searchtext; + if (!eval { qr/$search_regexp/; 1; }) { + (my $error = $@) =~ s/ at \S+ line \d+.*\n?//; + die_error(400, "Invalid search regexp '$search_regexp'", + esc_html($error)); + } + } else { + $search_regexp = quotemeta $searchtext; + } } - $search_regexp = $search_use_regexp ? $searchtext : quotemeta $searchtext; } # path to the current git repository our $git_dir; -$git_dir = "$projectroot/$project" if $project; +sub evaluate_git_dir { + our $git_dir = "$projectroot/$project" if $project; +} + +our (@snapshot_fmts, $git_avatar, @extra_branch_refs); +sub configure_gitweb_features { + # list of supported snapshot formats + our @snapshot_fmts = gitweb_get_feature('snapshot'); + @snapshot_fmts = filter_snapshot_fmts(@snapshot_fmts); + + our ($git_avatar) = gitweb_get_feature('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 +sub handle_errors_html { + my $msg = shift; # it is already HTML escaped + + # to avoid infinite loop where error occurs in die_error, + # change handler to default handler, disabling handle_errors_html + set_message("Error occurred when inside die_error:\n$msg"); -# list of supported snapshot formats -our @snapshot_fmts = gitweb_check_feature('snapshot'); -@snapshot_fmts = filter_snapshot_fmts(@snapshot_fmts); + # you cannot jump out of die_error when called as error handler; + # the subroutine set via CGI::Carp::set_message is called _after_ + # HTTP headers are already written, so it cannot write them itself + die_error(undef, undef, $msg, -error_handler => 1, -no_http_header => 1); +} +set_message(\&handle_errors_html); # dispatch -if (!defined $action) { - if (defined $hash) { - $action = git_get_type($hash); - } elsif (defined $hash_base && defined $file_name) { - $action = git_get_type("$hash_base:$file_name"); - } elsif (defined $project) { - $action = 'summary'; - } else { - $action = 'project_list'; +sub dispatch { + if (!defined $action) { + if (defined $hash) { + $action = git_get_type($hash); + $action or die_error(404, "Object does not exist"); + } elsif (defined $hash_base && defined $file_name) { + $action = git_get_type("$hash_base:$file_name"); + $action or die_error(404, "File or directory does not exist"); + } elsif (defined $project) { + $action = 'summary'; + } else { + $action = 'project_list'; + } + } + if (!defined($actions{$action})) { + die_error(400, "Unknown action"); + } + if ($action !~ m/^(?:opml|project_list|project_index)$/ && + !$project) { + die_error(400, "Project needed"); + } + $actions{$action}->(); +} + +sub reset_timer { + our $t0 = [ gettimeofday() ] + if defined $t0; + our $number_of_git_cmds = 0; +} + +our $first_request = 1; +sub run_request { + reset_timer(); + + evaluate_uri(); + if ($first_request) { + evaluate_gitweb_config(); + evaluate_git_version(); + } + if ($per_request_config) { + if (ref($per_request_config) eq 'CODE') { + $per_request_config->(); + } elsif (!$first_request) { + evaluate_gitweb_config(); + } } + check_loadavg(); + + # $projectroot and $projects_list might be set in gitweb config file + $projects_list ||= $projectroot; + + evaluate_query_params(); + evaluate_path_info(); + evaluate_and_validate_params(); + evaluate_git_dir(); + + configure_gitweb_features(); + + dispatch(); +} + +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 + our $is_last_request = sub { ++$request_number > 100 }; +} +sub evaluate_argv { + my $script_name = $ENV{'SCRIPT_NAME'} || $ENV{'SCRIPT_FILENAME'} || __FILE__; + configure_as_fcgi() + if $script_name =~ /\.fcgi$/; + + return unless (@ARGV); + + require Getopt::Long; + Getopt::Long::GetOptions( + 'fastcgi|fcgi|f' => \&configure_as_fcgi, + 'nproc|n=i' => sub { + my ($arg, $val) = @_; + return unless eval { require FCGI::ProcManager; 1; }; + my $proc_manager = FCGI::ProcManager->new({ + n_processes => $val, + }); + our $pre_listen_hook = sub { $proc_manager->pm_manage() }; + our $pre_dispatch_hook = sub { $proc_manager->pm_pre_dispatch() }; + our $post_dispatch_hook = sub { $proc_manager->pm_post_dispatch() }; + }, + ); } -if (!defined($actions{$action})) { - die_error(400, "Unknown action"); + +sub run { + evaluate_argv(); + + $first_request = 1; + $pre_listen_hook->() + if $pre_listen_hook; + + REQUEST: + while ($cgi = $CGI->new()) { + $pre_dispatch_hook->() + if $pre_dispatch_hook; + + run_request(); + + $post_dispatch_hook->() + if $post_dispatch_hook; + $first_request = 0; + + last REQUEST if ($is_last_request->()); + } + + DONE_GITWEB: + 1; } -if ($action !~ m/^(opml|project_list|project_index)$/ && - !$project) { - die_error(400, "Project needed"); + +run(); + +if (defined caller) { + # wrapped in a subroutine processing requests, + # e.g. mod_perl with ModPerl::Registry, or PSGI with Plack::App::WrapCGI + return; +} else { + # pure CGI script, serving single request + exit; } -$actions{$action}->(); -exit; ## ====================================================================== ## action links -sub href (%) { +# possible values of extra options +# -full => 0|1 - use absolute/full URL ($my_uri/$my_url as base) +# -replay => 1 - start from a current view (replay with modifications) +# -path_info => 0|1 - don't use/use path_info URL (if possible) +# -anchor => ANCHOR - add #ANCHOR to end of URL, implies -replay if used alone +sub href { my %params = @_; # default is to use -absolute url() i.e. $my_uri my $href = $params{-full} ? $my_url : $my_uri; + # implicit -replay, must be first of implicit params + $params{-replay} = 1 if (keys %params == 1 && $params{-anchor}); + $params{'project'} = $project unless exists $params{'project'}; if ($params{-replay}) { @@ -805,13 +1408,15 @@ sub href (%) { } } - my ($use_pathinfo) = gitweb_check_feature('pathinfo'); - if ($use_pathinfo) { + my $use_pathinfo = gitweb_check_feature('pathinfo'); + if (defined $params{'project'} && + (exists $params{-path_info} ? $params{-path_info} : $use_pathinfo)) { # try to put as many parameters as possible in PATH_INFO: # - project name # - action # - hash_parent or hash_parent_base:/file_parent # - hash or hash_base:/filename + # - the snapshot_format as an appropriate suffix # When the script is the root DirectoryIndex for the domain, # $href here would be something like http://gitweb.example.com/ @@ -820,13 +1425,18 @@ sub href (%) { $href =~ s,/$,,; # Then add the project name, if present - $href .= "/".esc_url($params{'project'}) if defined $params{'project'}; + $href .= "/".esc_path_info($params{'project'}); delete $params{'project'}; + # since we destructively absorb parameters, we keep this + # boolean that remembers if we're handling a snapshot + my $is_snapshot = $params{'action'} eq 'snapshot'; + # Summary just uses the project path URL, any other action is # added to the URL if (defined $params{'action'}) { - $href .= "/".esc_url($params{'action'}) unless $params{'action'} eq 'summary'; + $href .= "/".esc_path_info($params{'action'}) + unless $params{'action'} eq 'summary'; delete $params{'action'}; } @@ -836,32 +1446,47 @@ sub href (%) { || $params{'hash_parent'} || $params{'hash'}); if (defined $params{'hash_base'}) { if (defined $params{'hash_parent_base'}) { - $href .= esc_url($params{'hash_parent_base'}); + $href .= esc_path_info($params{'hash_parent_base'}); # skip the file_parent if it's the same as the file_name - delete $params{'file_parent'} if $params{'file_parent'} eq $params{'file_name'}; - if (defined $params{'file_parent'} && $params{'file_parent'} !~ /\.\./) { - $href .= ":/".esc_url($params{'file_parent'}); - delete $params{'file_parent'}; + if (defined $params{'file_parent'}) { + if (defined $params{'file_name'} && $params{'file_parent'} eq $params{'file_name'}) { + delete $params{'file_parent'}; + } elsif ($params{'file_parent'} !~ /\.\./) { + $href .= ":/".esc_path_info($params{'file_parent'}); + delete $params{'file_parent'}; + } } $href .= ".."; delete $params{'hash_parent'}; delete $params{'hash_parent_base'}; } elsif (defined $params{'hash_parent'}) { - $href .= esc_url($params{'hash_parent'}). ".."; + $href .= esc_path_info($params{'hash_parent'}). ".."; delete $params{'hash_parent'}; } - $href .= esc_url($params{'hash_base'}); + $href .= esc_path_info($params{'hash_base'}); if (defined $params{'file_name'} && $params{'file_name'} !~ /\.\./) { - $href .= ":/".esc_url($params{'file_name'}); + $href .= ":/".esc_path_info($params{'file_name'}); delete $params{'file_name'}; } delete $params{'hash'}; delete $params{'hash_base'}; } elsif (defined $params{'hash'}) { - $href .= esc_url($params{'hash'}); + $href .= esc_path_info($params{'hash'}); delete $params{'hash'}; } + + # If the action was a snapshot, we can absorb the + # snapshot_format parameter too + if ($is_snapshot) { + my $fmt = $params{'snapshot_format'}; + # snapshot_format should always be defined when href() + # is called, but just in case some code forgets, we + # fall back to the default + $fmt ||= $snapshot_fmts[0]; + $href .= $known_snapshot_formats{$fmt}{'suffix'}; + delete $params{'snapshot_format'}; + } } # now encode the parameters explicitly @@ -880,6 +1505,13 @@ sub href (%) { } $href .= "?" . join(';', @result) if scalar @result; + # final transformation: trailing spaces must be escaped (URI-encoded) + $href =~ s/(\s+)$/CGI::escape($1)/e; + + if ($params{-anchor}) { + $href .= "#".esc_param($params{-anchor}); + } + return $href; } @@ -887,29 +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_head_link("$projectroot/$input") || - ($export_ok && !(-e "$projectroot/$input/$export_ok")) || + !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!(^|/)(|\.|\.\.)(/|$)!) { @@ -919,24 +1553,33 @@ sub validate_pathname { if ($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, @@ -944,8 +1587,9 @@ sub validate_refname { # in utf-8 thanks to "binmode STDOUT, ':utf8'" at beginning sub to_utf8 { my $str = shift; - if (utf8::valid($str)) { - utf8::decode($str); + return undef unless defined $str; + + if (utf8::is_utf8($str) || utf8::decode($str)) { return $str; } else { return decode($fallback_encoding, $str, Encode::FB_DEFAULT); @@ -956,26 +1600,46 @@ sub to_utf8 { # correct, but quoted slashes look too horrible in bookmarks sub esc_param { my $str = shift; - $str =~ s/([^A-Za-z0-9\-_.~()\/:@])/sprintf("%%%02X", ord($1))/eg; - $str =~ s/\+/%2B/g; + return undef unless defined $str; + $str =~ s/([^A-Za-z0-9\-_.~()\/:@ ]+)/CGI::escape($1)/eg; $str =~ s/ /\+/g; return $str; } -# quote unsafe chars in whole URL, so some charactrs cannot be quoted +# the quoting rules for path_info fragment are slightly different +sub esc_path_info { + my $str = shift; + return undef unless defined $str; + + # path_info doesn't treat '+' as space (specially), but '?' must be escaped + $str =~ s/([^A-Za-z0-9\-_.~();\/;:@&= +]+)/CGI::escape($1)/eg; + + return $str; +} + +# quote unsafe chars in whole URL, so some characters cannot be quoted sub esc_url { my $str = shift; - $str =~ s/([^A-Za-z0-9\-_.~();\/;?:@&=])/sprintf("%%%02X", ord($1))/eg; - $str =~ s/\+/%2B/g; + return undef unless defined $str; + $str =~ s/([^A-Za-z0-9\-_.~();\/;?:@&= ]+)/CGI::escape($1)/eg; $str =~ s/ /\+/g; return $str; } +# quote unsafe characters in HTML attributes +sub esc_attr { + + # for XHTML conformance escaping '"' to '"' is not enough + return esc_html(@_); +} + # replace invalid utf8 character with SUBSTITUTION sequence -sub esc_html ($;%) { +sub esc_html { my $str = shift; my %opts = @_; + return undef unless defined $str; + $str = to_utf8($str); $str = $cgi->escapeHTML($str); if ($opts{'-nbsp'}) { @@ -990,6 +1654,8 @@ sub esc_path { my $str = shift; my %opts = @_; + return undef unless defined $str; + $str = to_utf8($str); $str = $cgi->escapeHTML($str); if ($opts{'-nbsp'}) { @@ -999,20 +1665,31 @@ sub esc_path { return $str; } +# 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:]])|(index("\t\n\r", $1) != -1 ? $1 : quot_cec($1))|eg; + return $str; +} + # Make control characters "printable", using character escape codes (CEC) 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} @@ -1132,7 +1809,6 @@ sub chop_str { $str =~ m/^(.*?)($begre)$/; my ($lead, $body) = ($1, $2); if (length($lead) > 4) { - $body =~ s/^[^;]*;// if ($lead =~ m/&[^;]*$/); $lead = " ..."; } return "$lead$body"; @@ -1143,8 +1819,6 @@ sub chop_str { $str =~ m/^(.*?)($begre)$/; my ($mid, $right) = ($1, $2); if (length($mid) > 5) { - $left =~ s/&[^;]*$//; - $right =~ s/^[^;]*;// if ($mid =~ m/&[^;]*$/); $mid = " ... "; } return "$left$mid$right"; @@ -1154,7 +1828,6 @@ sub chop_str { my $body = $1; my $tail = $2; if (length($tail) > 4) { - $body =~ s/&[^;]*$//; $tail = "... "; } return "$body$tail"; @@ -1168,15 +1841,107 @@ sub chop_and_escape_str { my ($str) = @_; my $chopped = chop_str(@_); + $str = to_utf8($str); if ($chopped eq $str) { return esc_html($chopped); } else { - $str =~ s/([[:cntrl:]])/?/g; + $str =~ s/[[:cntrl:]]/?/g; return $cgi->span({-title=>$str}, esc_html($chopped)); } } -## ---------------------------------------------------------------------- +# Highlight selected fragments of string, using given CSS class, +# and escape HTML. It is assumed that fragments do not overlap. +# Regions are passed as list of pairs (array references). +# +# Example: esc_html_hl_regions("foobar", "mark", [ 0, 3 ]) returns +# 'foobar' +sub esc_html_hl_regions { + my ($str, $css_class, @sel) = @_; + my %opts = grep { ref($_) ne 'ARRAY' } @sel; + @sel = grep { ref($_) eq 'ARRAY' } @sel; + return esc_html($str, %opts) unless @sel; + + my $out = ''; + my $pos = 0; + + for my $s (@sel) { + my ($begin, $end) = @$s; + + # Don't create empty elements. + next if $end <= $begin; + + my $escaped = esc_html(substr($str, $begin, $end - $begin), + %opts); + + $out .= esc_html(substr($str, $pos, $begin - $pos), %opts) + if ($begin - $pos > 0); + $out .= $cgi->span({-class => $css_class}, $escaped); + + $pos = $end; + } + $out .= esc_html(substr($str, $pos), %opts) + if ($pos < length($str)); + + return $out; +} + +# return positions of beginning and end of each match +sub matchpos_list { + my ($str, $regexp) = @_; + return unless (defined $str && defined $regexp); + + my @matches; + while ($str =~ /$regexp/g) { + push @matches, [$-[0], $+[0]]; + } + return @matches; +} + +# highlight match (if any), and escape HTML +sub esc_html_match_hl { + my ($str, $regexp) = @_; + return esc_html($str) unless defined $regexp; + + my @matches = matchpos_list($str, $regexp); + return esc_html($str) unless @matches; + + return esc_html_hl_regions($str, 'match', @matches); +} + + +# highlight match (if any) of shortened string, and escape HTML +sub esc_html_match_hl_chopped { + my ($str, $chopped, $regexp) = @_; + return esc_html_match_hl($str, $regexp) unless defined $chopped; + + my @matches = matchpos_list($str, $regexp); + return esc_html($chopped) unless @matches; + + # filter matches so that we mark chopped string + my $tail = "... "; # see chop_str + unless ($chopped =~ s/\Q$tail\E$//) { + $tail = ''; + } + my $chop_len = length($chopped); + my $tail_len = length($tail); + my @filtered; + + for my $m (@matches) { + if ($m->[0] > $chop_len) { + push @filtered, [ $chop_len, $chop_len + $tail_len ] if ($tail_len > 0); + last; + } elsif ($m->[1] > $chop_len) { + push @filtered, [ $m->[0], $chop_len + $tail_len ]; + last; + } + push @filtered, $m; + } + + return esc_html_hl_regions($chopped . $tail, 'match', @filtered); +} + +## ---------------------------------------------------------------------- ## functions returning short strings # CSS class for given age value (in seconds) @@ -1232,7 +1997,7 @@ use constant { }; # submodule/subproject, a commit object reference -sub S_ISGITLINK($) { +sub S_ISGITLINK { my $mode = shift; return (($mode & S_IFMT) == S_IFGITLINK) @@ -1319,14 +2084,29 @@ 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); - if ($line =~ m/([0-9a-fA-F]{8,40})/) { - my $hash_text = $1; - my $link = - $cgi->a({-href => href(action=>"object", hash=>$hash_text), - -class => "text"}, $hash_text); - $line =~ s/$hash_text/$link/; - } + $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); + }egx; + return $line; } @@ -1376,9 +2156,9 @@ sub format_ref_marker { -href => href( action=>$dest_action, hash=>$dest - )}, $name); + )}, esc_html($name)); - $markers .= " " . + $markers .= " " . $link . ""; } } @@ -1396,15 +2176,117 @@ sub format_subject_html { $extra = '' unless defined($extra); if (length($short) < length($long)) { + $long =~ s/[[:cntrl:]]/?/g; return $cgi->a({-href => $href, -class => "list subject", -title => to_utf8($long)}, - esc_html($short) . $extra); + esc_html($short)) . $extra; } else { return $cgi->a({-href => $href, -class => "list subject"}, - esc_html($long) . $extra); + esc_html($long)) . $extra; + } +} + +# Rather than recomputing the url for an email multiple times, we cache it +# after the first hit. This gives a visible benefit in views where the avatar +# for the same email is used repeatedly (e.g. shortlog). +# The cache is shared by all avatar engines (currently gravatar only), which +# are free to use it as preferred. Since only one avatar engine is used for any +# given page, there's no risk for cache conflicts. +our %avatar_cache = (); + +# Compute the picon url for a given email, by using the picon search service over at +# http://www.cs.indiana.edu/picons/search.html +sub picon_url { + my $email = lc shift; + if (!$avatar_cache{$email}) { + my ($user, $domain) = split('@', $email); + $avatar_cache{$email} = + "//www.cs.indiana.edu/cgi-pub/kinzler/piconsearch.cgi/" . + "$domain/$user/" . + "users+domains+unknown/up/single"; + } + return $avatar_cache{$email}; +} + +# Compute the gravatar url for a given email, if it's not in the cache already. +# Gravatar stores only the part of the URL before the size, since that's the +# one computationally more expensive. This also allows reuse of the cache for +# different sizes (for this particular engine). +sub gravatar_url { + my $email = lc shift; + my $size = shift; + $avatar_cache{$email} ||= + "//www.gravatar.com/avatar/" . + md5_hex($email) . "?s="; + return $avatar_cache{$email} . $size; +} + +# Insert an avatar for the given $email at the given $size if the feature +# is enabled. +sub git_get_avatar { + my ($email, %opts) = @_; + my $pre_white = ($opts{-pad_before} ? " " : ""); + my $post_white = ($opts{-pad_after} ? " " : ""); + $opts{-size} ||= 'default'; + my $size = $avatar_size{$opts{-size}} || $avatar_size{'default'}; + my $url = ""; + if ($git_avatar eq 'gravatar') { + $url = gravatar_url($email, $size); + } elsif ($git_avatar eq 'picon') { + $url = picon_url($email); + } + # Other providers can be added by extending the if chain, defining $url + # as needed. If no variant puts something in $url, we assume avatars + # are completely disabled/unavailable. + if ($url) { + return $pre_white . + "" . $post_white; + } else { + return ""; + } +} + +sub format_search_author { + my ($author, $searchtype, $displaytext) = @_; + my $have_search = gitweb_check_feature('search'); + + if ($have_search) { + my $performed = ""; + if ($searchtype eq 'author') { + $performed = "authored"; + } elsif ($searchtype eq 'committer') { + $performed = "committed"; + } + + return $cgi->a({-href => href(action=>"search", hash=>$hash, + searchtext=>$author, + searchtype=>$searchtype), class=>"list", + title=>"Search for commits $performed by $author"}, + $displaytext); + + } else { + return $displaytext; } } +# format the author name of the given commit with the given tag +# the author name is chopped and escaped according to the other +# optional parameters (see chop_str). +sub format_author_html { + my $tag = shift; + my $co = shift; + my $author = chop_and_escape_str($co->{'author_name'}, @_); + return "<$tag class=\"author\">" . + format_search_author($co->{'author_name'}, "author", + git_get_avatar($co->{'author_email'}, -pad_after => 1) . + $author) . + ""; +} + # format git diff header line, i.e. "diff --(git|combined|cc) ..." sub format_git_diff_header_line { my $line = shift; @@ -1463,7 +2345,8 @@ sub format_extended_diff_header_line { ')'; } # match - if ($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++) { @@ -1485,7 +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'}) { @@ -1598,93 +2482,125 @@ sub format_diff_cc_simplified { return $result; } -# format patch (diff) line (not to be used for diff headers) -sub format_diff_line { - my $line = shift; - my ($from, $to) = @_; - my $diff_class = ""; - - chomp $line; +sub diff_line_class { + my ($line, $from, $to) = @_; + # ordinary diff + my $num_sign = 1; + # combined diff if ($from && $to && ref($from->{'href'}) eq "ARRAY") { - # combined diff - my $prefix = substr($line, 0, scalar @{$from->{'href'}}); - if ($line =~ m/^\@{3}/) { - $diff_class = " chunk_header"; - } elsif ($line =~ m/^\\/) { - $diff_class = " incomplete"; - } elsif ($prefix =~ tr/+/+/) { - $diff_class = " add"; - } elsif ($prefix =~ tr/-/-/) { - $diff_class = " rem"; - } - } else { - # assume ordinary diff - my $char = substr($line, 0, 1); - if ($char eq '+') { - $diff_class = " add"; - } elsif ($char eq '-') { - $diff_class = " rem"; - } elsif ($char eq '@') { - $diff_class = " chunk_header"; - } elsif ($char eq "\\") { - $diff_class = " incomplete"; - } - } - $line = untabify($line); - if ($from && $to && $line =~ m/^\@{2} /) { - my ($from_text, $from_start, $from_lines, $to_text, $to_start, $to_lines, $section) = - $line =~ m/^\@{2} (-(\d+)(?:,(\d+))?) (\+(\d+)(?:,(\d+))?) \@{2}(.*)$/; - - $from_lines = 0 unless defined $from_lines; - $to_lines = 0 unless defined $to_lines; + $num_sign = scalar @{$from->{'href'}}; + } + + my @diff_line_classifier = ( + { regexp => qr/^\@\@{$num_sign} /, class => "chunk_header"}, + { regexp => qr/^\\/, class => "incomplete" }, + { regexp => qr/^ {$num_sign}/, class => "ctx" }, + # classifier for context must come before classifier add/rem, + # or we would have to use more complicated regexp, for example + # qr/(?= {0,$m}\+)[+ ]{$num_sign}/, where $m = $num_sign - 1; + { regexp => qr/^[+ ]{$num_sign}/, class => "add" }, + { regexp => qr/^[- ]{$num_sign}/, class => "rem" }, + ); + for my $clsfy (@diff_line_classifier) { + return $clsfy->{'class'} + if ($line =~ $clsfy->{'regexp'}); + } - if ($from->{'href'}) { - $from_text = $cgi->a({-href=>"$from->{'href'}#l$from_start", - -class=>"list"}, $from_text); - } - if ($to->{'href'}) { - $to_text = $cgi->a({-href=>"$to->{'href'}#l$to_start", - -class=>"list"}, $to_text); - } - $line = "@@ $from_text $to_text @@" . - "" . esc_html($section, -nbsp=>1) . ""; - return "
$line
\n"; - } elsif ($from && $to && $line =~ m/^\@{3}/) { - my ($prefix, $ranges, $section) = $line =~ m/^(\@+) (.*?) \@+(.*)$/; - my (@from_text, @from_start, @from_nlines, $to_text, $to_start, $to_nlines); + # fallback + return ""; +} - @from_text = split(' ', $ranges); - for (my $i = 0; $i < @from_text; ++$i) { - ($from_start[$i], $from_nlines[$i]) = - (split(',', substr($from_text[$i], 1)), 0); - } +# assumes that $from and $to are defined and correctly filled, +# and that $line holds a line of chunk header for unified diff +sub format_unidiff_chunk_header { + my ($line, $from, $to) = @_; - $to_text = pop @from_text; - $to_start = pop @from_start; - $to_nlines = pop @from_nlines; + my ($from_text, $from_start, $from_lines, $to_text, $to_start, $to_lines, $section) = + $line =~ m/^\@{2} (-(\d+)(?:,(\d+))?) (\+(\d+)(?:,(\d+))?) \@{2}(.*)$/; - $line = "$prefix "; - for (my $i = 0; $i < @from_text; ++$i) { - if ($from->{'href'}[$i]) { - $line .= $cgi->a({-href=>"$from->{'href'}[$i]#l$from_start[$i]", - -class=>"list"}, $from_text[$i]); - } else { - $line .= $from_text[$i]; - } - $line .= " "; + $from_lines = 0 unless defined $from_lines; + $to_lines = 0 unless defined $to_lines; + + if ($from->{'href'}) { + $from_text = $cgi->a({-href=>"$from->{'href'}#l$from_start", + -class=>"list"}, $from_text); + } + if ($to->{'href'}) { + $to_text = $cgi->a({-href=>"$to->{'href'}#l$to_start", + -class=>"list"}, $to_text); + } + $line = "@@ $from_text $to_text @@" . + "" . esc_html($section, -nbsp=>1) . ""; + return $line; +} + +# assumes that $from and $to are defined and correctly filled, +# and that $line holds a line of chunk header for combined diff +sub format_cc_diff_chunk_header { + my ($line, $from, $to) = @_; + + my ($prefix, $ranges, $section) = $line =~ m/^(\@+) (.*?) \@+(.*)$/; + my (@from_text, @from_start, @from_nlines, $to_text, $to_start, $to_nlines); + + @from_text = split(' ', $ranges); + for (my $i = 0; $i < @from_text; ++$i) { + ($from_start[$i], $from_nlines[$i]) = + (split(',', substr($from_text[$i], 1)), 0); + } + + $to_text = pop @from_text; + $to_start = pop @from_start; + $to_nlines = pop @from_nlines; + + $line = "$prefix "; + for (my $i = 0; $i < @from_text; ++$i) { + if ($from->{'href'}[$i]) { + $line .= $cgi->a({-href=>"$from->{'href'}[$i]#l$from_start[$i]", + -class=>"list"}, $from_text[$i]); + } else { + $line .= $from_text[$i]; } - if ($to->{'href'}) { - $line .= $cgi->a({-href=>"$to->{'href'}#l$to_start", - -class=>"list"}, $to_text); + $line .= " "; + } + if ($to->{'href'}) { + $line .= $cgi->a({-href=>"$to->{'href'}#l$to_start", + -class=>"list"}, $to_text); + } else { + $line .= $to_text; + } + $line .= " $prefix" . + "" . esc_html($section, -nbsp=>1) . ""; + return $line; +} + +# process patch (diff) line (not to be used for diff headers), +# returning HTML-formatted (but not wrapped) line. +# If the line is passed as a reference, it is treated as HTML and not +# esc_html()'ed. +sub format_diff_line { + my ($line, $diff_class, $from, $to) = @_; + + if (ref($line)) { + $line = $$line; + } else { + chomp $line; + $line = untabify($line); + + if ($from && $to && $line =~ m/^\@{2} /) { + $line = format_unidiff_chunk_header($line, $from, $to); + } elsif ($from && $to && $line =~ m/^\@{3}/) { + $line = format_cc_diff_chunk_header($line, $from, $to); } else { - $line .= $to_text; + $line = esc_html($line, -nbsp=>1); } - $line .= " $prefix" . - "" . esc_html($section, -nbsp=>1) . ""; - return "
$line
\n"; } - return "
" . esc_html($line, -nbsp=>1) . "
\n"; + + my $diff_classes = "diff"; + $diff_classes .= " $diff_class" if ($diff_class); + $line = "
$line
\n"; + + return $line; } # Generates undef or something like "_snapshot_" or "snapshot (_tbz2_ _zip_)", @@ -1731,19 +2647,25 @@ 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 $project); # some views should link to OPML, or to generic project feed, # or don't have specific feed yet (so they should use generic) - return if ($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 = $1; + return if (!$action || $action =~ /^(?:tags|heads|forks|tag|search)$/x); + + 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'; @@ -1756,7 +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; @@ -1767,6 +2689,7 @@ sub get_feed_info { # returns path to the core git executable and the --git-dir parameter as list sub git_cmd { + $number_of_git_cmds++; return $GIT, '--git-dir='.$git_dir; } @@ -1776,21 +2699,32 @@ sub git_cmd { # Try to avoid using this function wherever possible. sub quote_command { return join(' ', - map( { my $a = $_; $a =~ s/(['!])/'\\$1'/g; "'$a'" } @_ )); + map { my $a = $_; $a =~ s/(['!])/'\\$1'/g; "'$a'" } @_ ); } # get HEAD ref of given project as hash sub git_get_head_hash { - my $project = shift; + return git_get_full_hash(shift, 'HEAD'); +} + +sub git_get_full_hash { + return git_get_hash(@_); +} + +sub git_get_short_hash { + return git_get_hash(@_, '--short=7'); +} + +sub git_get_hash { + my ($project, $hash, @options) = @_; my $o_git_dir = $git_dir; my $retval = undef; $git_dir = "$projectroot/$project"; - if (open my $fd, "-|", git_cmd(), "rev-parse", "--verify", "HEAD") { - my $head = <$fd>; + if (open my $fd, '-|', git_cmd(), 'rev-parse', + '--verify', '-q', @options, $hash) { + $retval = <$fd>; + chomp $retval if defined $retval; close $fd; - if (defined $head && $head =~ /^([0-9a-fA-F]{40})$/) { - $retval = $1; - } } if (defined $o_git_dir) { $git_dir = $o_git_dir; @@ -1850,18 +2784,19 @@ sub git_parse_project_config { return %config; } -# convert config value to boolean, 'true' or 'false' +# convert config value to boolean: 'true' or 'false' # no value, number > 0, 'true' and 'yes' values are true # rest of values are treated as false (never as error) sub config_to_bool { my $val = shift; + return 1 if !defined $val; # section.key + # strip leading and trailing whitespace $val =~ s/^\s+//; $val =~ s/\s+$//; - return (!defined $val || # section.key - ($val =~ /^\d+$/ && $val) || # section.key = 1 + return (($val =~ /^\d+$/ && $val) || # section.key = 1 ($val =~ /^(?:true|yes)$/i)); # section.key = true } @@ -1895,10 +2830,22 @@ sub config_to_multi { sub git_get_project_config { my ($key, $type) = @_; + return unless defined $git_dir; + # key sanity check return unless ($key); + # only subsection, if exists, is case sensitive, + # and not lowercased by 'git config -z -l' + if (my ($hi, $mi, $lo) = ($key =~ /^([^.]*)\.(.*)\.([^.]*)$/)) { + $lo =~ s/_//g; + $key = join(".", lc($hi), $mi, lc($lo)); + return if ($lo =~ /\W/ || $hi =~ /\W/); + } else { + $key = lc($key); + $key =~ s/_//g; + return if ($key =~ /\W/); + } $key =~ s/^gitweb\.//; - return if ($key =~ m/\W/); # type sanity check if (defined $type) { @@ -1914,6 +2861,9 @@ sub git_get_project_config { $config_file = "$git_dir/config"; } + # check if config variable (key) exists + return unless exists $config{"gitweb.$key"}; + # ensure given type if (!defined $type) { return $config{"gitweb.$key"}; @@ -1945,7 +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; @@ -1980,38 +2930,94 @@ sub git_get_path_by_hash { ## ...................................................................... ## git utility functions, directly accessing git repository -sub git_get_project_description { - my $path = shift; +# get the value of config variable either from file named as the variable +# itself in the repository ($GIT_DIR/$name file), or from gitweb.$name +# configuration variable in the repository config file. +sub git_get_file_or_project_config { + my ($path, $name) = @_; $git_dir = "$projectroot/$path"; - open my $fd, "$git_dir/description" - or return git_get_project_config('description'); - my $descr = <$fd>; + open my $fd, '<', "$git_dir/$name" + or return git_get_project_config($name); + my $conf = <$fd>; close $fd; - if (defined $descr) { - chomp $descr; + if (defined $conf) { + chomp $conf; } - return $descr; + return $conf; } -sub git_get_project_ctags { +sub git_get_project_description { + my $path = shift; + return git_get_file_or_project_config($path, 'description'); +} + +sub git_get_project_category { my $path = shift; + return git_get_file_or_project_config($path, 'category'); +} + + +# supported formats: +# * $GIT_DIR/ctags/ file (in 'ctags' subdirectory) +# - if its contents is a number, use it as tag weight, +# - otherwise add a tag with weight 1 +# * $GIT_DIR/ctags file, each line is a tag (with weight 1) +# the same value multiple times increases tag weight +# * `gitweb.ctag' multi-valued repo config variable +sub git_get_project_ctags { + my $project = shift; my $ctags = {}; - $git_dir = "$projectroot/$path"; - unless (opendir D, "$git_dir/ctags") { - return $ctags; + $git_dir = "$projectroot/$project"; + if (opendir my $dh, "$git_dir/ctags") { + my @files = grep { -f $_ } map { "$git_dir/ctags/$_" } readdir($dh); + foreach my $tagfile (@files) { + open my $ct, '<', $tagfile + or next; + my $val = <$ct>; + chomp $val if $val; + close $ct; + + (my $ctag = $tagfile) =~ s#.*/##; + if ($val =~ /^\d+$/) { + $ctags->{$ctag} = $val; + } else { + $ctags->{$ctag} = 1; + } + } + closedir $dh; + + } elsif (open my $fh, '<', "$git_dir/ctags") { + while (my $line = <$fh>) { + chomp $line; + $ctags->{$line}++ if $line; + } + close $fh; + + } else { + my $taglist = config_to_multi(git_get_project_config('ctag')); + foreach my $tag (@$taglist) { + $ctags->{$tag}++; + } } - foreach (grep { -f $_ } map { "$git_dir/ctags/$_" } readdir(D)) { - open CT, $_ or next; - my $val = ; - chomp $val; - close CT; - my $ctag = $_; $ctag =~ s#.*/##; - $ctags->{$ctag} = $val; + + return $ctags; +} + +# return hash, where keys are content tags ('ctags'), +# and values are sum of weights of given tag in every project +sub git_gather_all_ctags { + my $projects = shift; + my $ctags = {}; + + foreach my $p (@$projects) { + foreach my $ct (keys %{$p->{'ctags'}}) { + $ctags->{$ct} += $p->{'ctags'}->{$ct}; + } } - closedir D; - $ctags; + + return $ctags; } sub git_populate_project_tagcloud { @@ -2029,33 +3035,49 @@ sub git_populate_project_tagcloud { } my $cloud; + my $matched = $input_params{'ctag'}; if (eval { require HTML::TagCloud; 1; }) { $cloud = HTML::TagCloud->new; - foreach (sort keys %ctags_lc) { + foreach my $ctag (sort keys %ctags_lc) { # Pad the title with spaces so that the cloud looks # less crammed. - my $title = $ctags_lc{$_}->{topname}; + my $title = esc_html($ctags_lc{$ctag}->{topname}); $title =~ s/ / /g; $title =~ s/^/ /g; $title =~ s/$/ /g; - $cloud->add($title, $home_link."?by_tag=".$_, $ctags_lc{$_}->{count}); + if (defined $matched && $matched eq $ctag) { + $title = qq($title); + } + $cloud->add($title, href(project=>undef, ctag=>$ctag), + $ctags_lc{$ctag}->{count}); } } else { - $cloud = \%ctags_lc; + $cloud = {}; + foreach my $ctag (keys %ctags_lc) { + my $title = esc_html($ctags_lc{$ctag}->{topname}, -nbsp=>1); + if (defined $matched && $matched eq $ctag) { + $title = qq($title); + } + $cloud->{$ctag}{count} = $ctags_lc{$ctag}->{count}; + $cloud->{$ctag}{ctag} = + $cgi->a({-href=>href(project=>undef, ctag=>$ctag)}, $title); + } } - $cloud; + return $cloud; } sub git_show_project_tagcloud { my ($cloud, $count) = @_; - print STDERR ref($cloud)."..\n"; if (ref $cloud eq 'HTML::TagCloud') { return $cloud->html_and_css($count); } else { - my @tags = sort { $cloud->{$a}->{count} <=> $cloud->{$b}->{count} } keys %$cloud; - return '

' . join (', ', map { - "$cloud->{$_}->{topname}" - } splice(@tags, 0, $count)) . '

'; + my @tags = sort { $cloud->{$a}->{'count'} <=> $cloud->{$b}->{'count'} } keys %$cloud; + return + '
' . + join (', ', map { + $cloud->{$_}->{'ctag'} + } splice(@tags, 0, $count)) . + '
'; } } @@ -2063,7 +3085,7 @@ sub git_get_project_url_list { my $path = shift; $git_dir = "$projectroot/$path"; - open my $fd, "$git_dir/cloneurl" + open my $fd, '<', "$git_dir/cloneurl" or return wantarray ? @{ config_to_multi(git_get_project_config('url')) } : config_to_multi(git_get_project_config('url')); @@ -2074,41 +3096,52 @@ sub git_get_project_url_list { } sub git_get_projects_list { - my ($filter) = @_; + my $filter = shift || ''; + my $paranoid = shift; my @list; - $filter ||= ''; - $filter =~ s/\.git$//; - - my ($check_forks) = gitweb_check_feature('forks'); - if (-d $projects_list) { # search in directory - my $dir = $projects_list . ($filter ? "/$filter" : ''); + my $dir = $projects_list; # remove the trailing "/" $dir =~ s!/+$!!; my $pfxlen = length("$dir"); my $pfxdepth = ($dir =~ tr!/!!); + # when filtering, search only given subdirectory + if ($filter && !$paranoid) { + $dir .= "/$filter"; + $dir =~ s!/+$!!; + } File::Find::find({ follow_fast => 1, # follow symbolic links follow_skip => 2, # ignore duplicates dangling_symlinks => 0, # ignore dangling symlinks, silently wanted => sub { + # global variables + our $project_maxdepth; + our $projectroot; # skip project-list toplevel, if we get it. return if (m!^[/.]$!); # 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) { $File::Find::prune = 1; return; } - my $subdir = substr($File::Find::name, $pfxlen + 1); + my $path = substr($File::Find::name, $pfxlen + 1); + # paranoidly only filter here + if ($paranoid && $filter && $path !~ m!^\Q$filter\E/!) { + next; + } # we check related file in $projectroot - if (check_export_ok("$projectroot/$filter/$subdir")) { - push @list, { path => ($filter ? "$filter/" : '') . $subdir }; + if (check_export_ok("$projectroot/$path")) { + push @list, { path => $path }; $File::Find::prune = 1; } }, @@ -2119,8 +3152,7 @@ sub git_get_projects_list { # 'git%2Fgit.git Linus+Torvalds' # 'libs%2Fklibc%2Fklibc.git H.+Peter+Anvin' # 'linux%2Fhotplug%2Fudev.git Greg+Kroah-Hartman' - my %paths; - open my ($fd), $projects_list or return; + open my $fd, '<', $projects_list or return; PROJECT: while (my $line = <$fd>) { chomp $line; @@ -2130,41 +3162,18 @@ sub git_get_projects_list { if (!defined $path) { next; } - if ($filter ne '') { - # looking for forks; - my $pfx = substr($path, 0, length($filter)); - if ($pfx ne $filter) { - next PROJECT; - } - my $sfx = substr($path, length($filter)); - if ($sfx !~ /^\/.*\.git$/) { - next PROJECT; - } - } elsif ($check_forks) { - PATH: - foreach my $filter (keys %paths) { - # looking for forks; - my $pfx = substr($path, 0, length($filter)); - if ($pfx ne $filter) { - next PATH; - } - my $sfx = substr($path, length($filter)); - if ($sfx !~ /^\/.*\.git$/) { - next PATH; - } - # is a fork, don't include it in - # the list - next PROJECT; - } + # if $filter is rpovided, check if $path begins with $filter + if ($filter && $path !~ m!^\Q$filter\E/!) { + next; } if (check_export_ok("$projectroot/$path")) { my $pr = { - path => $path, - owner => to_utf8($owner), + path => $path }; + if ($owner) { + $pr->{'owner'} = to_utf8($owner); + } push @list, $pr; - (my $forks_path = $path) =~ s/\.git$//; - $paths{$forks_path}++; } } close $fd; @@ -2172,6 +3181,102 @@ sub git_get_projects_list { return @list; } +# 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; + + my %trie; # prefix tree of directories (path components) + # generate trie out of those directories that might contain forks + foreach my $pr (@$projects) { + my $path = $pr->{'path'}; + $path =~ s/\.git$//; # forks of 'repo.git' are in 'repo/' directory + next if ($path =~ m!/$!); # skip non-bare repositories, e.g. 'repo/.git' + next unless ($path); # skip '.git' repository: tests, git-instaweb + next unless (-d "$projectroot/$path"); # containing directory exists + $pr->{'forks'} = []; # there can be 0 or more forks of project + + # add to trie + my @dirs = split('/', $path); + # walk the trie, until either runs out of components or out of trie + my $ref = \%trie; + while (scalar @dirs && + exists($ref->{$dirs[0]})) { + $ref = $ref->{shift @dirs}; + } + # create rest of trie structure from rest of components + foreach my $dir (@dirs) { + $ref = $ref->{$dir} = {}; + } + # create end marker, store $pr as a data + $ref->{''} = $pr if (!exists $ref->{''}); + } + + # filter out forks, by finding shortest prefix match for paths + my @filtered; + PROJECT: + foreach my $pr (@$projects) { + # trie lookup + my $ref = \%trie; + DIR: + foreach my $dir (split('/', $pr->{'path'})) { + if (exists $ref->{''}) { + # found [shortest] prefix, is a fork - skip it + push @{$ref->{''}{'forks'}}, $pr; + next PROJECT; + } + if (!exists $ref->{$dir}) { + # not in trie, cannot have prefix, not a fork + push @filtered, $pr; + next PROJECT; + } + # If the dir is there, we just walk one step down the trie. + $ref = $ref->{$dir}; + } + # we ran out of trie + # (shouldn't happen: it's either no match, or end marker) + push @filtered, $pr; + } + + return @filtered; +} + +# note: fill_project_list_info must be run first, +# for 'descr_long' and 'ctags' to be filled +sub search_projects_list { + my ($projlist, %opts) = @_; + my $tagfilter = $opts{'tagfilter'}; + my $search_re = $opts{'search_regexp'}; + + return @$projlist + unless ($tagfilter || $search_re); + + # searching projects require filling to be run before it; + fill_project_list_info($projlist, + $tagfilter ? 'ctags' : (), + $search_re ? ('path', 'descr') : ()); + my @projects; + PROJECT: + foreach my $pr (@$projlist) { + + if ($tagfilter) { + next unless ref($pr->{'ctags'}) eq 'HASH'; + next unless + grep { lc($_) eq lc($tagfilter) } keys %{$pr->{'ctags'}}; + } + + if ($search_re) { + next unless + $pr->{'path'} =~ /$search_re/ || + $pr->{'descr_long'} =~ /$search_re/; + } + + push @projects, $pr; + } + + return @projects; +} + our $gitweb_project_owner = undef; sub git_get_project_list_from_file { @@ -2183,7 +3288,7 @@ sub git_get_project_list_from_file { # 'libs%2Fklibc%2Fklibc.git H.+Peter+Anvin' # 'linux%2Fhotplug%2Fudev.git Greg+Kroah-Hartman' if (-f $projects_list) { - open (my $fd , $projects_list); + open(my $fd, '<', $projects_list); while (my $line = <$fd>) { chomp $line; my ($pr, $ow) = split ' ', $line; @@ -2228,7 +3333,7 @@ sub git_get_last_activity { '--format=%(committer)', '--sort=-committerdate', '--count=1', - 'refs/heads') or return; + map { "refs/$_" } get_branch_refs ()) or return; my $most_recent = <$fd>; close $fd or return; if (defined $most_recent && @@ -2240,6 +3345,44 @@ sub git_get_last_activity { return (undef, undef); } +# Implementation note: when a single remote is wanted, we cannot use 'git +# remote show -n' because that command always work (assuming it's a remote URL +# if it's not defined), and we cannot use 'git remote show' because that would +# try to make a network roundtrip. So the only way to find if that particular +# remote is defined is to walk the list provided by 'git remote -v' and stop if +# and when we find what we want. +sub git_get_remotes_list { + my $wanted = shift; + my %remotes = (); + + open my $fd, '-|' , git_cmd(), 'remote', '-v'; + return unless $fd; + while (my $remote = <$fd>) { + chomp $remote; + $remote =~ s!\t(.*?)\s+\((\w+)\)$!!; + next if $wanted and not $remote eq $wanted; + my ($url, $key) = ($1, $2); + + $remotes{$remote} ||= { 'heads' => () }; + $remotes{$remote}{$key} = $url; + } + close $fd or return; + return wantarray ? %remotes : \%remotes; +} + +# Takes a hash of remotes as first parameter and fills it by adding the +# available remote heads for each of the indicated remotes. +sub fill_remote_heads { + my $remotes = shift; + my @heads = map { "remotes/$_" } keys %$remotes; + my @remoteheads = git_get_heads_list(undef, @heads); + foreach my $remote (keys %$remotes) { + $remotes->{$remote}{'heads'} = [ grep { + $_->{'name'} =~ s!^$remote/!! + } @remoteheads ]; + } +} + sub git_get_references { my $type = shift || ""; my %refs; @@ -2251,7 +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 { @@ -2302,8 +3445,10 @@ sub parse_date { $date{'iso-8601'} = sprintf "%04d-%02d-%02dT%02d:%02d:%02dZ", 1900+$year, 1+$mon, $mday, $hour ,$min, $sec; - $tz =~ m/^([+\-][0-9][0-9])([0-9][0-9])$/; - my $local = $epoch + ((int $1 + ($2/60)) * 3600); + my ($tz_sign, $tz_hour, $tz_min) = + ($tz =~ m/^([-+])(\d\d)(\d\d)$/); + $tz_sign = ($tz_sign eq '-' ? -1 : +1); + my $local = $epoch + $tz_sign*((($tz_hour*60) + $tz_min)*60); ($sec, $min, $hour, $mday, $mon, $year, $wday, $yday) = gmtime($local); $date{'hour_local'} = $hour; $date{'minute_local'} = $min; @@ -2314,6 +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; @@ -2323,16 +3475,22 @@ 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{'epoch'} = $2; - $tag{'tz'} = $3; + $tag{'author'} = hide_mailaddrs_if_private($1); + $tag{'author_epoch'} = $2; + $tag{'author_tz'} = $3; + if ($tag{'author'} =~ m/^([^<]+) <([^>]*)>/) { + $tag{'author_name'} = $1; + $tag{'author_email'} = $2; + } else { + $tag{'author_name'} = $tag{'author'}; + } } elsif ($line =~ m/--BEGIN/) { push @comment, $line; last; @@ -2361,18 +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'} = $1; + $co{'author'} = hide_mailaddrs_if_private(to_utf8($1)); $co{'author_epoch'} = $2; $co{'author_tz'} = $3; if ($co{'author'} =~ m/^([^<]+) <([^>]*)>/) { @@ -2382,10 +3540,9 @@ sub parse_commit_text { $co{'author_name'} = $co{'author'}; } } elsif ($line =~ m/^committer (.*) ([0-9]+) (.*)$/) { - $co{'committer'} = $1; + $co{'committer'} = hide_mailaddrs_if_private(to_utf8($1)); $co{'committer_epoch'} = $2; $co{'committer_tz'} = $3; - $co{'committer_name'} = $co{'committer'}; if ($co{'committer'} =~ m/^([^<]+) <([^>]*)>/) { $co{'committer_name'} = $1; $co{'committer_email'} = $2; @@ -2404,23 +3561,6 @@ sub parse_commit_text { $title =~ s/^ //; if ($title ne "") { $co{'title'} = chop_str($title, 80, 5); - # remove leading stuff of merges to make the interesting part visible - if (length($title) > 50) { - $title =~ s/^Automatic //; - $title =~ s/^merge (of|with) /Merge ... /i; - if (length($title) > 50) { - $title =~ s/(http|rsync):\/\///; - } - if (length($title) > 50) { - $title =~ s/(master|www|rsync)\.//; - } - if (length($title) > 50) { - $title =~ s/kernel.org:?//; - } - if (length($title) > 50) { - $title =~ s/\/pub\/scm//; - } - } $co{'title_short'} = chop_str($title, 50, 5); last; } @@ -2428,9 +3568,10 @@ 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); } $co{'comment'} = \@commit_lines; @@ -2502,7 +3643,7 @@ sub parse_difftree_raw_line { # ':100644 100644 03b218260e99b78c6df0ed378e59ed9205ccc96d 3b93d5e7cc7f7dd4ebed13a5cc1a4ad976fc94d8 M ls-files.c' # ':100644 100644 7f9281985086971d3877aca27704f2aaf9c448ce bc190ebc71bbd923f2b728e505408f5e54bd073a M rev-tree.c' - if ($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'} = $3; @@ -2517,7 +3658,7 @@ sub parse_difftree_raw_line { } # '::100755 100755 100755 60e79ca1b01bc8b057abe17ddab484699a7f5fdb 94067cc5f73388f33722d52ae02f44692bc07490 94067cc5f73388f33722d52ae02f44692bc07490 MR git-gui/git-gui.sh' # combined diff (for merge commit) - elsif ($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'}}; @@ -2527,7 +3668,7 @@ 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'} = $1; } @@ -2548,21 +3689,36 @@ sub parsed_difftree_line { } # parse line of git-ls-tree output -sub parse_ls_tree_line ($;%) { +sub parse_ls_tree_line { my $line = shift; my %opts = @_; my %res; - #'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa panic.c' - $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t(.+)$/s; + if ($opts{'-l'}) { + #'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa 16717 panic.c' + $line =~ m/^([0-9]+) (.+) ($oid_regex) +(-|[0-9]+)\t(.+)$/s; - $res{'mode'} = $1; - $res{'type'} = $2; - $res{'hash'} = $3; - if ($opts{'-z'}) { - $res{'name'} = $4; + $res{'mode'} = $1; + $res{'type'} = $2; + $res{'hash'} = $3; + $res{'size'} = $4; + if ($opts{'-z'}) { + $res{'name'} = $5; + } else { + $res{'name'} = unquote($5); + } } else { - $res{'name'} = unquote($4); + #'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa panic.c' + $line =~ m/^([0-9]+) (.+) ($oid_regex)\t(.+)$/s; + + $res{'mode'} = $1; + $res{'type'} = $2; + $res{'hash'} = $3; + if ($opts{'-z'}) { + $res{'name'} = $4; + } else { + $res{'name'} = unquote($4); + } } return wantarray ? %res : \%res; @@ -2618,13 +3774,16 @@ sub parse_from_to_diffinfo { ## parse to array of hashes functions sub git_get_heads_list { - my $limit = shift; + my ($limit, @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)', - 'refs/heads' + @patterns or return; while (my $line = <$fd>) { my %ref_item; @@ -2635,9 +3794,16 @@ sub git_get_heads_list { my ($committer, $epoch, $tz) = ($committerinfo =~ /^(.*) ([0-9]+) (.*)$/); $ref_item{'fullname'} = $name; - $name =~ s!^refs/heads/!!; + 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'} = $epoch; @@ -2719,6 +3885,15 @@ sub get_file_owner { return to_utf8($owner); } +# assume that file exists +sub insert_file { + my $filename = shift; + + open my $fd, '<', $filename; + print map { to_utf8($_) } <$fd>; + close $fd; +} + ## ...................................................................... ## mimetype related functions @@ -2728,18 +3903,15 @@ sub mimetype_guess_file { -r $mimemap or return undef; my %mimemap; - open(MIME, $mimemap) or return undef; - while () { + open(my $mh, '<', $mimemap) or return undef; + while (<$mh>) { next if m/^#/; # skip comments - my ($mime, $exts) = split(/\t+/); - if (defined $exts) { - my @exts = split(/\s+/, $exts); - foreach my $ext (@exts) { - $mimemap{$ext} = $mime; - } + my ($mimetype, @exts) = split(/\s+/); + foreach my $ext (@exts) { + $mimemap{$ext} = $mimetype; } } - close(MIME); + close($mh); $filename =~ /\.([^.]*)$/; return $mimemap{$1}; @@ -2800,27 +3972,68 @@ sub blob_contenttype { return $type; } +# guess file syntax for syntax highlighting; return undef if no highlighting +# the name of syntax can (in the future) depend on syntax highlighter used +sub guess_file_syntax { + my ($highlight, $file_name) = @_; + return undef unless ($highlight && defined $file_name); + my $basename = basename($file_name, '.in'); + return $highlight_basename{$basename} + if exists $highlight_basename{$basename}; + + $basename =~ /\.([^.]*)$/; + my $ext = $1 or return undef; + return $highlight_ext{$ext} + if exists $highlight_ext{$ext}; + + return undef; +} + +# run highlighter and return FD of its output, +# or return original FD if no highlighting +sub run_highlighter { + my ($fd, $highlight, $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_arg |" + or die_error(500, "Couldn't open file or run syntax highlighter"); + return $fd; +} + ## ====================================================================== ## functions printing HTML: header, footer, error page -sub git_header_html { - my $status = shift || "200 OK"; - my $expires = shift; +sub get_page_title { + my $title = to_utf8($site_name); - my $title = "$site_name"; - if (defined $project) { - $title .= " - " . to_utf8($project); - if (defined $action) { - $title .= "/$action"; - if (defined $file_name) { - $title .= " - " . esc_path($file_name); - if ($action eq "tree" && $file_name !~ m|/$|) { - $title .= "/"; - } - } + unless (defined $project) { + if (defined $project_filter) { + $title .= " - projects in '" . esc_path($project_filter) . "'"; } + return $title; + } + $title .= " - " . to_utf8($project); + + return $title unless (defined $action); + $title .= "/$action"; # $action is US-ASCII (7bit ASCII) + + return $title unless (defined $file_name); + $title .= " - " . esc_path($file_name); + if ($action eq "tree" && $file_name !~ m|/$|) { + $title .= "/"; } - my $content_type; + + return $title; +} + +sub get_content_type_html { # require explicit support from the UA if we are to send the page as # 'application/xhtml+xml', otherwise send it as plain old 'text/html'. # we have to do this because MSIE sometimes globs '*/*', pretending to @@ -2828,51 +4041,30 @@ sub git_header_html { if (defined $cgi->http('HTTP_ACCEPT') && $cgi->http('HTTP_ACCEPT') =~ m/(,|;|\s|^)application\/xhtml\+xml(,|;|\s|$)/ && $cgi->Accept('application/xhtml+xml') != 0) { - $content_type = 'application/xhtml+xml'; + return 'application/xhtml+xml'; } else { - $content_type = 'text/html'; - } - print $cgi->header(-type=>$content_type, -charset => 'utf-8', - -status=> $status, -expires => $expires); - my $mod_perl_version = $ENV{'MOD_PERL'} ? " $ENV{'MOD_PERL'}" : ''; - print < - - - - - - - - -$title -EOF -# print out each stylesheet that exist - if (defined $stylesheet) { -#provides backwards capability for those people who define style sheet in a config file - print ''."\n"; - } else { - foreach my $stylesheet (@stylesheets) { - next unless $stylesheet; - print ''."\n"; - } + return 'text/html'; } +} + +sub print_feed_meta { if (defined $project) { my %href_params = get_feed_info(); if (!exists $href_params{'-title'}) { $href_params{'-title'} = 'log'; } - foreach my $format qw(RSS Atom) { + foreach my $format (qw(RSS Atom)) { my $type = lc($format); my %link_attr = ( '-rel' => 'alternate', - '-title' => "$project - $href_params{'-title'} - $format feed", + '-title' => esc_attr("$project - $href_params{'-title'} - $format feed"), '-type' => "application/$type+xml" ); + $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", - $site_name, href(project=>undef, action=>"project_index")); + esc_attr($site_name), + esc_attr(href(project=>undef, action=>"project_index"))); printf(''."\n", - $site_name, href(project=>undef, action=>"opml")); + esc_attr($site_name), + esc_attr(href(project=>undef, action=>"opml"))); + } +} + +sub print_header_links { + my $status = shift; + + # print out each stylesheet that exist, providing backwards capability + # for those people who defined $stylesheet in a config file + if (defined $stylesheet) { + print ''."\n"; + } else { + foreach my $stylesheet (@stylesheets) { + next unless $stylesheet; + print ''."\n"; + } } + print_feed_meta() + if ($status eq '200 OK'); if (defined $favicon) { - print qq(\n); + print qq(\n); } +} - print "\n" . - "\n"; - - if (-f $site_header) { - open (my $fd, $site_header); - print <$fd>; - close $fd; +sub print_nav_breadcrumbs_path { + my $dirprefix = undef; + while (my $part = shift) { + $dirprefix .= "/" if defined $dirprefix; + $dirprefix .= $part; + print $cgi->a({-href => href(project => undef, + project_filter => $dirprefix, + action => "project_list")}, + esc_html($part)) . " / "; } +} - print "
\n" . - $cgi->a({-href => esc_url($logo_url), - -title => $logo_label}, - qq()); - print $cgi->a({-href => esc_url($home_link)}, $home_link_str) . " / "; +sub print_nav_breadcrumbs { + my %opts = @_; + + for my $crumb (@extra_breadcrumbs, [ $home_link_str => $home_link ]) { + print $cgi->a({-href => esc_url($crumb->[1])}, $crumb->[0]) . " / "; + } if (defined $project) { - print $cgi->a({-href => href(action=>"summary")}, esc_html($project)); + my @dirname = split '/', $project; + my $projectbasename = pop @dirname; + print_nav_breadcrumbs_path(@dirname); + print $cgi->a({-href => href(action=>"summary")}, esc_html($projectbasename)); if (defined $action) { - print " / $action"; + my $action_print = $action ; + if (defined $opts{-action_extra}) { + $action_print = $cgi->a({-href => href(action=>$action)}, + $action); + } + print " / $action_print"; + } + if (defined $opts{-action_extra}) { + print " / $opts{-action_extra}"; } print "\n"; + } elsif (defined $project_filter) { + print_nav_breadcrumbs_path(split '/', $project_filter); + } +} + +sub print_search_form { + if (!defined $searchtext) { + $searchtext = ""; + } + my $search_hash; + if (defined $hash_base) { + $search_hash = $hash_base; + } elsif (defined $hash) { + $search_hash = $hash; + } else { + $search_hash = "HEAD"; + } + my $action = $my_uri; + my $use_pathinfo = gitweb_check_feature('pathinfo'); + if ($use_pathinfo) { + $action .= "/".esc_url($project); + } + print $cgi->start_form(-method => "get", -action => $action) . + "
\n" . + (!$use_pathinfo && + $cgi->input({-name=>"p", -value=>$project, -type=>"hidden"}) . "\n") . + $cgi->input({-name=>"a", -value=>"search", -type=>"hidden"}) . "\n" . + $cgi->input({-name=>"h", -value=>$search_hash, -type=>"hidden"}) . "\n" . + $cgi->popup_menu(-name => 'st', -default => 'commit', + -values => ['commit', 'grep', 'author', 'committer', 'pickaxe']) . + " " . $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', + -checked => $search_use_regexp) . + "" . + "
" . + $cgi->end_form() . "\n"; +} + +sub git_header_html { + my $status = shift || "200 OK"; + my $expires = shift; + my %opts = @_; + + my $title = get_page_title(); + 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 +EOF + # the stylesheet, favicon etc urls won't work correctly with path_info + # unless we set the appropriate base URL + if ($ENV{'PATH_INFO'}) { + print "\n"; + } + print_header_links($status); + + if (defined $site_html_head_string) { + print to_utf8($site_html_head_string); + } + + print "\n" . + "\n"; + + if (defined $site_header && -f $site_header) { + insert_file($site_header); } + + print "
\n"; + if (defined $logo) { + print $cgi->a({-href => esc_url($logo_url), + -title => $logo_label}, + $cgi->img({-src => esc_url($logo), + -width => 72, -height => 27, + -alt => "git", + -class => "logo"})); + } + print_nav_breadcrumbs(%opts); print "
\n"; - my ($have_search) = gitweb_check_feature('search'); + my $have_search = gitweb_check_feature('search'); if (defined $project && $have_search) { - if (!defined $searchtext) { - $searchtext = ""; - } - my $search_hash; - if (defined $hash_base) { - $search_hash = $hash_base; - } elsif (defined $hash) { - $search_hash = $hash; - } else { - $search_hash = "HEAD"; - } - my $action = $my_uri; - my ($use_pathinfo) = gitweb_check_feature('pathinfo'); - if ($use_pathinfo) { - $action .= "/".esc_url($project); - } - print $cgi->startform(-method => "get", -action => $action) . - "
\n" . - (!$use_pathinfo && - $cgi->input({-name=>"p", -value=>$project, -type=>"hidden"}) . "\n") . - $cgi->input({-name=>"a", -value=>"search", -type=>"hidden"}) . "\n" . - $cgi->input({-name=>"h", -value=>$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->textfield(-name => "s", -value => $searchtext) . "\n" . - "" . - $cgi->checkbox(-name => 'sr', -value => 1, -label => 're', - -checked => $search_use_regexp) . - "" . - "
" . - $cgi->end_form() . "\n"; + print_search_form(); } } @@ -2980,7 +4267,7 @@ sub git_footer_html { } $href_params{'-title'} ||= 'log'; - foreach my $format qw(RSS Atom) { + foreach my $format (qw(RSS Atom)) { $href_params{'action'} = lc($format); print $cgi->a({-href => href(%href_params), -title => "$href_params{'-title'} $format feed", @@ -2988,24 +4275,62 @@ sub git_footer_html { } } else { - print $cgi->a({-href => href(project=>undef, action=>"opml"), + print $cgi->a({-href => href(project=>undef, action=>"opml", + project_filter => $project_filter), -class => $feed_class}, "OPML") . " "; - print $cgi->a({-href => href(project=>undef, action=>"project_index"), + print $cgi->a({-href => href(project=>undef, action=>"project_index", + project_filter => $project_filter), -class => $feed_class}, "TXT") . "\n"; } print "
\n"; # class="page_footer" - if (-f $site_footer) { - open (my $fd, $site_footer); - print <$fd>; - close $fd; + if (defined $t0 && gitweb_check_feature('timed')) { + print "
\n"; + print 'This page took '. + ''. + tv_interval($t0, [ gettimeofday() ]). + ' seconds '. + ' and '. + ''. + $number_of_git_cmds. + ' git commands '. + " to generate.\n"; + print "
\n"; # class="page_footer" + } + + if (defined $site_footer && -f $site_footer) { + insert_file($site_footer); + } + + print qq!\n!; + if (defined $action && + $action eq 'blame_incremental') { + print qq!\n!; + } else { + my ($jstimezone, $tz_cookie, $datetime_class) = + gitweb_get_feature('javascript-timezone'); + + print qq!\n!; } print "\n" . ""; } -# die_error(, ) +# die_error(, [, ]) # Example: die_error(404, 'Hash not found') # By convention, use the following status codes (as defined in RFC 2616): # 400: Invalid or missing CGI parameters, or @@ -3016,24 +4341,37 @@ sub git_footer_html { # 500: The server isn't configured properly, or # an internal error occurred (e.g. failed assertions caused by bugs), or # an unknown error occurred (e.g. the git binary died unexpectedly). +# 503: The server is currently unavailable (because it is overloaded, +# or down for maintenance). Generally, this is a temporary state. sub die_error { my $status = shift || 500; - my $error = shift || "Internal server error"; + my $error = esc_html(shift) || "Internal Server Error"; + my $extra = shift; + my %opts = @_; - my %http_responses = (400 => '400 Bad Request', - 403 => '403 Forbidden', - 404 => '404 Not Found', - 500 => '500 Internal Server Error'); - git_header_html($http_responses{$status}); + my %http_responses = ( + 400 => '400 Bad Request', + 403 => '403 Forbidden', + 404 => '404 Not Found', + 500 => '500 Internal Server Error', + 503 => '503 Service Unavailable', + ); + git_header_html($http_responses{$status}, undef, %opts); print <

$status - $error
- EOF + if (defined $extra) { + print "
\n" . + "$extra\n"; + } + print "\n"; + git_footer_html(); - exit; + goto DONE_GITWEB + unless ($opts{'-error_handler'}); } ## ---------------------------------------------------------------------- @@ -3063,7 +4401,7 @@ sub git_print_page_nav { $arg{'tree'}{'hash'} = $treehead if defined $treehead; $arg{'tree'}{'hash_base'} = $treebase if defined $treebase; - my @actions = gitweb_check_feature('actions'); + my @actions = gitweb_get_feature('actions'); my %repl = ( '%' => '%', 'n' => $project, # project name @@ -3089,23 +4427,32 @@ sub git_print_page_nav { "\n"; } +# returns a submenu for the navigation of the refs views (tags, heads, +# remotes) with the current view disabled and the remotes view only +# available if the feature is enabled +sub format_ref_views { + my ($current) = @_; + my @ref_views = qw{tags heads}; + push @ref_views, 'remotes' if gitweb_check_feature('remote_heads'); + return join " | ", map { + $_ eq $current ? $_ : + $cgi->a({-href => href(action=>$_)}, $_) + } @ref_views +} + sub format_paging_nav { - my ($action, $hash, $head, $page, $has_next_link) = @_; + my ($action, $page, $has_next_link) = @_; my $paging_nav; - if ($hash ne $head || $page) { - $paging_nav .= $cgi->a({-href => href(action=>$action)}, "HEAD"); - } else { - $paging_nav .= "HEAD"; - } - if ($page > 0) { - $paging_nav .= " ⋅ " . + $paging_nav .= + $cgi->a({-href => href(-replay=>1, page=>undef)}, "first") . + " ⋅ " . $cgi->a({-href => href(-replay=>1, page=>$page-1), -accesskey => "p", -title => "Alt-p"}, "prev"); } else { - $paging_nav .= " ⋅ prev"; + $paging_nav .= "first ⋅ prev"; } if ($has_next_link) { @@ -3136,22 +4483,111 @@ sub git_print_header_div { "\n\n"; } -#sub git_print_authorship (\%) { +sub format_repo_url { + my ($name, $url) = @_; + return "$name$url\n"; +} + +# Group output by placing it in a DIV element and adding a header. +# Options for start_div() can be provided by passing a hash reference as the +# first parameter to the function. +# Options to git_print_header_div() can be provided by passing an array +# reference. This must follow the options to start_div if they are present. +# The content can be a scalar, which is output as-is, a scalar reference, which +# is output after html escaping, an IO handle passed either as *handle or +# *handle{IO}, or a function reference. In the latter case all following +# parameters will be taken as argument to the content function call. +sub git_print_section { + my ($div_args, $header_args, $content); + my $arg = shift; + if (ref($arg) eq 'HASH') { + $div_args = $arg; + $arg = shift; + } + if (ref($arg) eq 'ARRAY') { + $header_args = $arg; + $arg = shift; + } + $content = $arg; + + print $cgi->start_div($div_args); + git_print_header_div(@$header_args); + + if (ref($content) eq 'CODE') { + $content->(@_); + } elsif (ref($content) eq 'SCALAR') { + print esc_html($$content); + } elsif (ref($content) eq 'GLOB' or ref($content) eq 'IO::Handle') { + print <$content>; + } elsif (!ref($content) && defined($content)) { + print $content; + } + + print $cgi->end_div; +} + +sub format_timestamp_html { + my $date = shift; + my $strtime = $date->{'rfc2822'}; + + my (undef, undef, $datetime_class) = + gitweb_get_feature('javascript-timezone'); + if ($datetime_class) { + $strtime = qq!$strtime!; + } + + my $localtime_format = '(%02d:%02d %s)'; + if ($date->{'hour_local'} < 6) { + $localtime_format = '(%02d:%02d %s)'; + } + $strtime .= ' ' . + sprintf($localtime_format, + $date->{'hour_local'}, $date->{'minute_local'}, $date->{'tz_local'}); + + return $strtime; +} + +# Outputs the author name and date in long form sub git_print_authorship { my $co = shift; + my %opts = @_; + my $tag = $opts{-tag} || 'div'; + my $author = $co->{'author_name'}; my %ad = parse_date($co->{'author_epoch'}, $co->{'author_tz'}); - print "
" . - esc_html($co->{'author_name'}) . - " [$ad{'rfc2822'}"; - if ($ad{'hour_local'} < 6) { - printf(" (%02d:%02d %s)", - $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); - } else { - printf(" (%02d:%02d %s)", - $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); + print "<$tag class=\"author_date\">" . + format_search_author($author, "author", esc_html($author)) . + " [".format_timestamp_html(\%ad)."]". + git_get_avatar($co->{'author_email'}, -pad_before => 1) . + "\n"; +} + +# Outputs table rows containing the full author or committer information, +# in the format expected for 'commit' view (& similar). +# Parameters are a commit hash reference, followed by the list of people +# to output information for. If the list is empty it defaults to both +# author and committer. +sub git_print_authorship_rows { + my $co = shift; + # too bad we can't use @people = @_ || ('author', 'committer') + my @people = @_; + @people = ('author', 'committer') unless @people; + foreach my $who (@people) { + my %wd = parse_date($co->{"${who}_epoch"}, $co->{"${who}_tz"}); + print "$who" . + format_search_author($co->{"${who}_name"}, $who, + esc_html($co->{"${who}_name"})) . " " . + format_search_author($co->{"${who}_email"}, $who, + esc_html("<" . $co->{"${who}_email"} . ">")) . + "" . + git_get_avatar($co->{"${who}_email"}, -size => 'double') . + "\n" . + "" . + "" . + format_timestamp_html(\%wd) . + "" . + "\n"; } - print "]
\n"; } sub git_print_page_path { @@ -3192,8 +4628,7 @@ sub git_print_page_path { print "
\n"; } -# sub git_print_log (\@;%) { -sub git_print_log ($;%) { +sub git_print_log { my $log = shift; my %opts = @_; @@ -3207,30 +4642,33 @@ sub git_print_log ($;%) { } # print log - my $signoff = 0; - my $empty = 0; + my $skip_blank_line = 0; foreach my $line (@$log) { - if ($line =~ m/^ *(signed[ \-]off[ \-]by[ :]|acked[ \-]by[ :]|cc[ :])/i) { - $signoff = 1; - $empty = 0; + if ($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"; - next; - } else { - # remove signoff lines - next; + $skip_blank_line = 1; } - } else { - $signoff = 0; + next; + } + + if ($line =~ m,\s*([a-z]*link): (https?://\S+),i) { + if (! $opts{'-remove_signoff'}) { + print "" . esc_html($1) . ": " . + "" . esc_html($2) . "" . + "
\n"; + $skip_blank_line = 1; + } + next; } # print only one empty line # do not print empty line after signoff if ($line eq "") { - next if ($empty || $signoff); - $empty = 1; + next if ($skip_blank_line); + $skip_blank_line = 1; } else { - $empty = 0; + $skip_blank_line = 0; } print format_log_line_html($line) . "
\n"; @@ -3238,7 +4676,7 @@ sub git_print_log ($;%) { if ($opts{'-final_empty_line'}) { # end with single empty line - print "
\n" unless $empty; + print "
\n" unless $skip_blank_line; } } @@ -3251,7 +4689,7 @@ sub git_get_link_target { open my $fd, "-|", git_cmd(), "cat-file", "blob", $hash or return; { - local $/; + local $/ = undef; $link_target = <$fd>; } close $fd @@ -3264,10 +4702,7 @@ sub git_get_link_target { # return target of link relative to top directory (top tree); # return undef if it is not possible (including absolute links). sub normalize_link_target { - my ($link_target, $basedir, $hash_base) = @_; - - # we can normalize symlink target only if $hash_base is provided - return unless $hash_base; + my ($link_target, $basedir) = @_; # absolute symlinks (beginning with '/') cannot be normalized return if (substr($link_target, 0, 1) eq '/'); @@ -3315,6 +4750,9 @@ sub git_print_tree_entry { # and link is the action links of the entry. print "" . mode_str($t->{'mode'}) . "\n"; + if (exists $t->{'size'}) { + print "$t->{'size'}\n"; + } if ($t->{'type'} eq "blob") { print "" . $cgi->a({-href => href(action=>"blob", hash=>$t->{'hash'}, @@ -3323,7 +4761,7 @@ sub git_print_tree_entry { if (S_ISLNK(oct $t->{'mode'})) { my $link_target = git_get_link_target($t->{'hash'}); if ($link_target) { - my $norm_target = normalize_link_target($link_target, $basedir, $hash_base); + my $norm_target = normalize_link_target($link_target, $basedir); if (defined $norm_target) { print " -> " . $cgi->a({-href => href(action=>"object", hash_base=>$hash_base, @@ -3360,12 +4798,14 @@ sub git_print_tree_entry { } elsif ($t->{'type'} eq "tree") { print ""; print $cgi->a({-href => href(action=>"tree", hash=>$t->{'hash'}, - file_name=>"$basedir$t->{'name'}", %base_key)}, + file_name=>"$basedir$t->{'name'}", + %base_key)}, esc_path($t->{'name'})); print "\n"; print ""; print $cgi->a({-href => href(action=>"tree", hash=>$t->{'hash'}, - file_name=>"$basedir$t->{'name'}", %base_key)}, + file_name=>"$basedir$t->{'name'}", + %base_key)}, "tree"); if (defined $hash_base) { print " | " . @@ -3415,7 +4855,7 @@ 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) || $diffinfo->{'to_id'} eq ('0' x 64); } # does patch correspond to [previous] difftree raw line @@ -3433,7 +4873,7 @@ sub is_patch_split { sub git_difftree_body { my ($difftree, $hash, @parents) = @_; my ($parent) = $parents[0]; - my ($have_blame) = gitweb_check_feature('blame'); + my $have_blame = gitweb_check_feature('blame'); print "
\n"; if ($#{$difftree} > 10) { print(($#{$difftree} + 1) . " files changed:\n"); @@ -3498,7 +4938,8 @@ sub git_difftree_body { # link to patch $patchno++; print "" . - $cgi->a({-href => "#patch$patchno"}, "patch") . + $cgi->a({-href => href(-anchor=>"patch$patchno")}, + "patch") . " | " . "\n"; } @@ -3575,7 +5016,7 @@ sub git_difftree_body { } if ($diff->{'from_mode'} ne ('0' x 6)) { $from_mode_oct = oct $diff->{'from_mode'}; - if (S_ISREG($to_mode_oct)) { # only for regular file + if (S_ISREG($from_mode_oct)) { # only for regular file $from_mode_str = sprintf("%04o", $from_mode_oct & 0777); # permission bits } $from_file_type = file_type($diff->{'from_mode'}); @@ -3595,8 +5036,9 @@ sub git_difftree_body { if ($action eq 'commitdiff') { # link to patch $patchno++; - print $cgi->a({-href => "#patch$patchno"}, "patch"); - print " | "; + print $cgi->a({-href => href(-anchor=>"patch$patchno")}, + "patch") . + " | "; } print $cgi->a({-href => href(action=>"blob", hash=>$diff->{'to_id'}, hash_base=>$hash, file_name=>$diff->{'file'})}, @@ -3615,8 +5057,9 @@ sub git_difftree_body { if ($action eq 'commitdiff') { # link to patch $patchno++; - print $cgi->a({-href => "#patch$patchno"}, "patch"); - print " | "; + print $cgi->a({-href => href(-anchor=>"patch$patchno")}, + "patch") . + " | "; } print $cgi->a({-href => href(action=>"blob", hash=>$diff->{'from_id'}, hash_base=>$parent, file_name=>$diff->{'file'})}, @@ -3657,7 +5100,8 @@ sub git_difftree_body { if ($action eq 'commitdiff') { # link to patch $patchno++; - print $cgi->a({-href => "#patch$patchno"}, "patch") . + print $cgi->a({-href => href(-anchor=>"patch$patchno")}, + "patch") . " | "; } elsif ($diff->{'to_id'} ne $diff->{'from_id'}) { # "commit" view and modified file (not onlu mode changed) @@ -3702,7 +5146,8 @@ sub git_difftree_body { if ($action eq 'commitdiff') { # link to patch $patchno++; - print $cgi->a({-href => "#patch$patchno"}, "patch") . + print $cgi->a({-href => href(-anchor=>"patch$patchno")}, + "patch") . " | "; } elsif ($diff->{'to_id'} ne $diff->{'from_id'}) { # "commit" view and modified file (not only pure rename or copy) @@ -3733,8 +5178,239 @@ sub git_difftree_body { print "\n"; } +# Print context lines and then rem/add lines in a side-by-side manner. +sub print_sidebyside_diff_lines { + my ($ctx, $rem, $add) = @_; + + # print context block before add/rem block + if (@$ctx) { + print join '', + '
', + '
', + @$ctx, + '
', + '
', + @$ctx, + '
', + '
'; + } + + if (!@$add) { + # pure removal + print join '', + '
', + '
', + @$rem, + '
', + '
'; + } elsif (!@$rem) { + # pure addition + print join '', + '
', + '
', + @$add, + '
', + '
'; + } else { + print join '', + '
', + '
', + @$rem, + '
', + '
', + @$add, + '
', + '
'; + } +} + +# Print context lines and then rem/add lines in inline manner. +sub print_inline_diff_lines { + my ($ctx, $rem, $add) = @_; + + print @$ctx, @$rem, @$add; +} + +# Format removed and added line, mark changed part and HTML-format them. +# Implementation is based on contrib/diff-highlight +sub format_rem_add_lines_pair { + my ($rem, $add, $num_parents) = @_; + + # We need to untabify lines before split()'ing them; + # otherwise offsets would be invalid. + chomp $rem; + chomp $add; + $rem = untabify($rem); + $add = untabify($add); + + my @rem = split(//, $rem); + my @add = split(//, $add); + my ($esc_rem, $esc_add); + # Ignore leading +/- characters for each parent. + my ($prefix_len, $suffix_len) = ($num_parents, 0); + my ($prefix_has_nonspace, $suffix_has_nonspace); + + my $shorter = (@rem < @add) ? @rem : @add; + while ($prefix_len < $shorter) { + last if ($rem[$prefix_len] ne $add[$prefix_len]); + + $prefix_has_nonspace = 1 if ($rem[$prefix_len] !~ /\s/); + $prefix_len++; + } + + while ($prefix_len + $suffix_len < $shorter) { + last if ($rem[-1 - $suffix_len] ne $add[-1 - $suffix_len]); + + $suffix_has_nonspace = 1 if ($rem[-1 - $suffix_len] !~ /\s/); + $suffix_len++; + } + + # Mark lines that are different from each other, but have some common + # part that isn't whitespace. If lines are completely different, don't + # mark them because that would make output unreadable, especially if + # diff consists of multiple lines. + if ($prefix_has_nonspace || $suffix_has_nonspace) { + $esc_rem = esc_html_hl_regions($rem, 'marked', + [$prefix_len, @rem - $suffix_len], -nbsp=>1); + $esc_add = esc_html_hl_regions($add, 'marked', + [$prefix_len, @add - $suffix_len], -nbsp=>1); + } else { + $esc_rem = esc_html($rem, -nbsp=>1); + $esc_add = esc_html($add, -nbsp=>1); + } + + return format_diff_line(\$esc_rem, 'rem'), + format_diff_line(\$esc_add, 'add'); +} + +# HTML-format diff context, removed and added lines. +sub format_ctx_rem_add_lines { + my ($ctx, $rem, $add, $num_parents) = @_; + my (@new_ctx, @new_rem, @new_add); + my $can_highlight = 0; + my $is_combined = ($num_parents > 1); + + # Highlight if every removed line has a corresponding added line. + if (@$add > 0 && @$add == @$rem) { + $can_highlight = 1; + + # Highlight lines in combined diff only if the chunk contains + # diff between the same version, e.g. + # + # - a + # - b + # + c + # + d + # + # Otherwise the highlighting would be confusing. + if ($is_combined) { + for (my $i = 0; $i < @$add; $i++) { + my $prefix_rem = substr($rem->[$i], 0, $num_parents); + my $prefix_add = substr($add->[$i], 0, $num_parents); + + $prefix_rem =~ s/-/+/g; + + if ($prefix_rem ne $prefix_add) { + $can_highlight = 0; + last; + } + } + } + } + + if ($can_highlight) { + for (my $i = 0; $i < @$add; $i++) { + my ($line_rem, $line_add) = format_rem_add_lines_pair( + $rem->[$i], $add->[$i], $num_parents); + push @new_rem, $line_rem; + push @new_add, $line_add; + } + } else { + @new_rem = map { format_diff_line($_, 'rem') } @$rem; + @new_add = map { format_diff_line($_, 'add') } @$add; + } + + @new_ctx = map { format_diff_line($_, 'ctx') } @$ctx; + + return (\@new_ctx, \@new_rem, \@new_add); +} + +# Print context lines and then rem/add lines. +sub print_diff_lines { + my ($ctx, $rem, $add, $diff_style, $num_parents) = @_; + my $is_combined = $num_parents > 1; + + ($ctx, $rem, $add) = format_ctx_rem_add_lines($ctx, $rem, $add, + $num_parents); + + if ($diff_style eq 'sidebyside' && !$is_combined) { + print_sidebyside_diff_lines($ctx, $rem, $add); + } else { + # default 'inline' style and unknown styles + print_inline_diff_lines($ctx, $rem, $add); + } +} + +sub print_diff_chunk { + my ($diff_style, $num_parents, $from, $to, @chunk) = @_; + my (@ctx, @rem, @add); + + # The class of the previous line. + my $prev_class = ''; + + return unless @chunk; + + # incomplete last line might be among removed or added lines, + # or both, or among context lines: find which + for (my $i = 1; $i < @chunk; $i++) { + if ($chunk[$i][0] eq 'incomplete') { + $chunk[$i][0] = $chunk[$i-1][0]; + } + } + + # guardian + push @chunk, ["", ""]; + + foreach my $line_info (@chunk) { + my ($class, $line) = @$line_info; + + # print chunk headers + if ($class && $class eq 'chunk_header') { + print format_diff_line($line, $class, $from, $to); + next; + } + + ## print from accumulator when have some add/rem lines or end + # of chunk (flush context lines), or when have add and rem + # lines and new block is reached (otherwise add/rem lines could + # be reordered) + if (!$class || ((@rem || @add) && $class eq 'ctx') || + (@rem && @add && $class ne $prev_class)) { + print_diff_lines(\@ctx, \@rem, \@add, + $diff_style, $num_parents); + @ctx = @rem = @add = (); + } + + ## adding lines to accumulator + # guardian value + last unless $line; + # rem, add or change + if ($class eq 'rem') { + push @rem, $line; + } elsif ($class eq 'add') { + push @add, $line; + } + # context line + if ($class eq 'ctx') { + push @ctx, $line; + } + + $prev_class = $class; + } +} + sub git_patchset_body { - my ($fd, $difftree, $hash, @hash_parents) = @_; + my ($fd, $diff_style, $difftree, $hash, @hash_parents) = @_; my ($hash_parent) = $hash_parents[0]; my $is_combined = (@hash_parents > 1); @@ -3744,6 +5420,7 @@ sub git_patchset_body { my $diffinfo; my $to_name; my (%from, %to); + my @chunk; # for side-by-side diff print "
\n"; @@ -3850,15 +5527,26 @@ sub git_patchset_body { next PATCH if ($patch_line =~ m/^diff /); - print format_diff_line($patch_line, \%from, \%to); + my $class = diff_line_class($patch_line, \%from, \%to); + + if ($class eq 'chunk_header') { + print_diff_chunk($diff_style, scalar @hash_parents, \%from, \%to, @chunk); + @chunk = (); + } + + push @chunk, [ $class, $patch_line ]; } } continue { + if (@chunk) { + print_diff_chunk($diff_style, scalar @hash_parents, \%from, \%to, @chunk); + @chunk = (); + } print "
\n"; # class="patch" } - # for compact combined (--cc) format, with chunk and patch simpliciaction - # patchset might be empty, but there might be unprocessed raw lines + # for compact combined (--cc) format, with chunk and patch simplification + # the patchset might be empty, but there might be unprocessed raw lines for (++$patch_idx if $patch_number > 0; $patch_idx < @$difftree; ++$patch_idx) { @@ -3886,151 +5574,227 @@ sub git_patchset_body { # . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . -# fills project list info (age, description, owner, forks) for each -# project in the list, removing invalid projects from returned list +sub git_project_search_form { + my ($searchtext, $search_use_regexp) = @_; + + my $limit = ''; + if ($project_filter) { + $limit = " in '$project_filter/'"; + } + + print "
\n"; + 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); + print $cgi->textfield(-name => 's', -value => $searchtext, + -title => "Search project by name and description$limit", + -size => 60) . "\n" . + "" . + $cgi->checkbox(-name => 'sr', -value => 1, -label => 're', + -checked => $search_use_regexp) . + "\n" . + $cgi->submit(-name => 'btnS', -value => 'Search') . + $cgi->end_form() . "\n" . + $cgi->a({-href => href(project => undef, searchtext => undef, + project_filter => $project_filter)}, + esc_html("List all projects$limit")) . "
\n"; + print "
\n"; +} + +# entry for given @keys needs filling if at least one of keys in list +# is not present in %$project_info +sub project_info_needs_filling { + my ($project_info, @keys) = @_; + + # return List::MoreUtils::any { !exists $project_info->{$_} } @keys; + foreach my $key (@keys) { + if (!exists $project_info->{$key}) { + return 1; + } + } + return; +} + +# fills project list info (age, description, owner, category, forks, etc.) +# for each project in the list, removing invalid projects from +# returned list, or fill only specified info. +# +# Invalid projects are removed from the returned list if and only if you +# ask 'age' or 'age_string' to be filled, because they are the only fields +# that run unconditionally git command that requires repository, and +# therefore do always check if project repository is invalid. +# +# USAGE: +# * fill_project_list_info(\@project_list, 'descr_long', 'ctags') +# ensures that 'descr_long' and 'ctags' fields are filled +# * @project_list = fill_project_list_info(\@project_list) +# ensures that all fields are filled (and invalid projects removed) +# # NOTE: modifies $projlist, but does not remove entries from it sub fill_project_list_info { - my ($projlist, $check_forks) = @_; + my ($projlist, @wanted_keys) = @_; my @projects; + my $filter_set = sub { return @_; }; + if (@wanted_keys) { + my %wanted_keys = map { $_ => 1 } @wanted_keys; + $filter_set = sub { return grep { $wanted_keys{$_} } @_; }; + } my $show_ctags = gitweb_check_feature('ctags'); PROJECT: foreach my $pr (@$projlist) { - my (@activity) = git_get_last_activity($pr->{'path'}); - unless (@activity) { - next PROJECT; + if (project_info_needs_filling($pr, $filter_set->('age', 'age_string'))) { + my (@activity) = git_get_last_activity($pr->{'path'}); + unless (@activity) { + next PROJECT; + } + ($pr->{'age'}, $pr->{'age_string'}) = @activity; } - ($pr->{'age'}, $pr->{'age_string'}) = @activity; - if (!defined $pr->{'descr'}) { + if (project_info_needs_filling($pr, $filter_set->('descr', 'descr_long'))) { my $descr = git_get_project_description($pr->{'path'}) || ""; $descr = to_utf8($descr); $pr->{'descr_long'} = $descr; $pr->{'descr'} = chop_str($descr, $projects_list_description_width, 5); } - if (!defined $pr->{'owner'}) { + if (project_info_needs_filling($pr, $filter_set->('owner'))) { $pr->{'owner'} = git_get_project_owner("$pr->{'path'}") || ""; } - if ($check_forks) { - my $pname = $pr->{'path'}; - if (($pname =~ s/\.git$//) && - ($pname !~ /\/$/) && - (-d "$projectroot/$pname")) { - $pr->{'forks'} = "-d $projectroot/$pname"; - } else { - $pr->{'forks'} = 0; - } + if ($show_ctags && + project_info_needs_filling($pr, $filter_set->('ctags'))) { + $pr->{'ctags'} = git_get_project_ctags($pr->{'path'}); + } + if ($projects_list_group_categories && + project_info_needs_filling($pr, $filter_set->('category'))) { + my $cat = git_get_project_category($pr->{'path'}) || + $project_list_default_category; + $pr->{'category'} = to_utf8($cat); } - $show_ctags and $pr->{'ctags'} = git_get_project_ctags($pr->{'path'}); + push @projects, $pr; } return @projects; } +sub sort_projects_list { + my ($projlist, $order) = @_; + + sub order_str { + my $key = shift; + return sub { $a->{$key} cmp $b->{$key} }; + } + + sub order_num_then_undef { + my $key = shift; + return sub { + defined $a->{$key} ? + (defined $b->{$key} ? $a->{$key} <=> $b->{$key} : -1) : + (defined $b->{$key} ? 1 : 0) + }; + } + + my %orderings = ( + project => order_str('path'), + descr => order_str('descr_long'), + owner => order_str('owner'), + age => order_num_then_undef('age'), + ); + + my $ordering = $orderings{$order}; + return defined $ordering ? sort $ordering @$projlist : @$projlist; +} + +# returns a hash of categories, containing the list of project +# belonging to each category +sub build_projlist_by_category { + my ($projlist, $from, $to) = @_; + my %categories; + + $from = 0 unless defined $from; + $to = $#$projlist if (!defined $to || $#$projlist < $to); + + for (my $i = $from; $i <= $to; $i++) { + my $pr = $projlist->[$i]; + push @{$categories{ $pr->{'category'} }}, $pr; + } + + return wantarray ? %categories : \%categories; +} + # print 'sort by' element, generating 'sort by $name' replay link # if that order is not selected sub print_sort_th { + print format_sort_th(@_); +} + +sub format_sort_th { my ($name, $order, $header) = @_; + my $sort_th = ""; $header ||= ucfirst($name); if ($order eq $name) { - print "$header\n"; + $sort_th .= "$header\n"; } else { - print "" . - $cgi->a({-href => href(-replay=>1, order=>$name), - -class => "header"}, $header) . - "\n"; + $sort_th .= "" . + $cgi->a({-href => href(-replay=>1, order=>$name), + -class => "header"}, $header) . + "\n"; } -} -sub git_project_list_body { - # actually uses global variable $project - my ($projlist, $order, $from, $to, $extra, $no_header) = @_; + return $sort_th; +} - my ($check_forks) = gitweb_check_feature('forks'); - my @projects = fill_project_list_info($projlist, $check_forks); +sub git_project_list_rows { + my ($projlist, $from, $to, $check_forks) = @_; - $order ||= $default_projects_order; $from = 0 unless defined $from; - $to = $#projects if (!defined $to || $#projects < $to); + $to = $#$projlist if (!defined $to || $#$projlist < $to); - my %order_info = ( - project => { key => 'path', type => 'str' }, - descr => { key => 'descr_long', type => 'str' }, - owner => { key => 'owner', type => 'str' }, - age => { key => 'age', type => 'num' } - ); - my $oi = $order_info{$order}; - if ($oi->{'type'} eq 'str') { - @projects = sort {$a->{$oi->{'key'}} cmp $b->{$oi->{'key'}}} @projects; - } else { - @projects = sort {$a->{$oi->{'key'}} <=> $b->{$oi->{'key'}}} @projects; - } + my $alternate = 1; + for (my $i = $from; $i <= $to; $i++) { + my $pr = $projlist->[$i]; - my $show_ctags = gitweb_check_feature('ctags'); - if ($show_ctags) { - my %ctags; - foreach my $p (@projects) { - foreach my $ct (keys %{$p->{'ctags'}}) { - $ctags{$ct} += $p->{'ctags'}->{$ct}; - } - } - my $cloud = git_populate_project_tagcloud(\%ctags); - print git_show_project_tagcloud($cloud, 64); - } - - print "\n"; - unless ($no_header) { - print "\n"; - if ($check_forks) { - print "\n"; - } - print_sort_th('project', $order, 'Project'); - print_sort_th('descr', $order, 'Description'); - print_sort_th('owner', $order, 'Owner'); - print_sort_th('age', $order, 'Last Change'); - print "\n" . # for links - "\n"; - } - my $alternate = 1; - my $tagfilter = $cgi->param('by_tag'); - for (my $i = $from; $i <= $to; $i++) { - my $pr = $projects[$i]; - - next if $tagfilter and $show_ctags and not grep { lc $_ eq lc $tagfilter } keys %{$pr->{'ctags'}}; - next if $searchtext and not $pr->{'path'} =~ /$searchtext/ - and not $pr->{'descr_long'} =~ /$searchtext/; - # Weed out forks or non-matching entries of search - if ($check_forks) { - my $forkbase = $project; $forkbase ||= ''; $forkbase =~ s#\.git$#/#; - $forkbase="^$forkbase" if $forkbase; - next if not $searchtext and not $tagfilter and $show_ctags - and $pr->{'path'} =~ m#$forkbase.*/.*#; # regexp-safe - } - - if ($alternate) { - print "\n"; - } else { - print "\n"; + if ($alternate) { + print "\n"; + } else { + print "\n"; } $alternate ^= 1; + if ($check_forks) { print "\n"; } print "\n" . + -class => "list"}, + esc_html_match_hl($pr->{'path'}, $search_regexp)) . + "\n" . "\n" . - "\n"; - print "\n" . - "\n"; + unless ($omit_owner) { + print "\n"; + } + unless ($omit_age_column) { + print "\n"; + } + print"\n" . "\n"; } +} + +sub git_project_list_body { + # actually uses global variable $project + my ($projlist, $order, $from, $to, $extra, $no_header) = @_; + my @projects = @$projlist; + + my $check_forks = gitweb_check_feature('forks'); + my $show_ctags = gitweb_check_feature('ctags'); + my $tagfilter = $show_ctags ? $input_params{'ctag'} : undef; + $check_forks = undef + if ($tagfilter || $search_regexp); + + # filtering out forks before filling info allows to do less work + @projects = filter_forks_from_projects_list(\@projects) + if ($check_forks); + # search_projects_list pre-fills required info + @projects = search_projects_list(\@projects, + 'search_regexp' => $search_regexp, + 'tagfilter' => $tagfilter) + if ($tagfilter || $search_regexp); + # fill the rest + my @all_fields = ('descr', 'descr_long', 'ctags', 'category'); + push @all_fields, ('age', 'age_string') unless($omit_age_column); + push @all_fields, 'owner' unless($omit_owner); + @projects = fill_project_list_info(\@projects, @all_fields); + + $order ||= $default_projects_order; + $from = 0 unless defined $from; + $to = $#projects if (!defined $to || $#projects < $to); + + # short circuit + if ($from > $to) { + print "
\n". + "No such projects found
\n". + "Click ".$cgi->a({-href=>href(project=>undef)},"here")." to view all projects
\n". + "
\n
\n"; + return; + } + + @projects = sort_projects_list(\@projects, $order); + + if ($show_ctags) { + my $ctags = git_gather_all_ctags(\@projects); + my $cloud = git_populate_project_tagcloud($ctags); + print git_show_project_tagcloud($cloud, 64); + } + + print "
"; if ($pr->{'forks'}) { - print "\n"; - print $cgi->a({-href => href(project=>$pr->{'path'}, action=>"forks")}, "+"); + my $nforks = scalar @{$pr->{'forks'}}; + if ($nforks > 0) { + print $cgi->a({-href => href(project=>$pr->{'path'}, action=>"forks"), + -title => "$nforks forks"}, "+"); + } else { + print $cgi->span({-title => "$nforks forks"}, "+"); + } } print "" . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"summary"), - -class => "list"}, esc_html($pr->{'path'})) . "" . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"summary"), - -class => "list", -title => $pr->{'descr_long'}}, - esc_html($pr->{'descr'})) . "" . chop_and_escape_str($pr->{'owner'}, 15) . "{'age'}) . "\">" . - (defined $pr->{'age_string'} ? $pr->{'age_string'} : "No commits") . "" . + -class => "list", + -title => $pr->{'descr_long'}}, + $search_regexp + ? esc_html_match_hl_chopped($pr->{'descr_long'}, + $pr->{'descr'}, $search_regexp) + : esc_html($pr->{'descr'})) . + "" . chop_and_escape_str($pr->{'owner'}, 15) . "{'age'}) . "\">" . + (defined $pr->{'age_string'} ? $pr->{'age_string'} : "No commits") . "" . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"summary")}, "summary") . " | " . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"shortlog")}, "shortlog") . " | " . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"log")}, "log") . " | " . @@ -4039,6 +5803,88 @@ sub git_project_list_body { "
\n"; + unless ($no_header) { + print "\n"; + if ($check_forks) { + print "\n"; + } + print_sort_th('project', $order, 'Project'); + print_sort_th('descr', $order, 'Description'); + print_sort_th('owner', $order, 'Owner') unless $omit_owner; + print_sort_th('age', $order, 'Last Change') unless $omit_age_column; + print "\n" . # for links + "\n"; + } + + if ($projects_list_group_categories) { + # only display categories with projects in the $from-$to window + @projects = sort {$a->{'category'} cmp $b->{'category'}} @projects[$from..$to]; + my %categories = build_projlist_by_category(\@projects, $from, $to); + foreach my $cat (sort keys %categories) { + unless ($cat eq "") { + print "\n"; + if ($check_forks) { + print "\n"; + } + print "\n"; + print "\n"; + } + + git_project_list_rows($categories{$cat}, undef, undef, $check_forks); + } + } else { + git_project_list_rows(\@projects, $from, $to, $check_forks); + } + if (defined $extra) { print "\n"; if ($check_forks) { @@ -4050,6 +5896,45 @@ sub git_project_list_body { print "
".esc_html($cat)."
\n"; } +sub git_log_body { + # uses global variable $project + my ($commitlist, $from, $to, $refs, $extra) = @_; + + $from = 0 unless defined $from; + $to = $#{$commitlist} if (!defined $to || $#{$commitlist} < $to); + + for (my $i = 0; $i <= $to; $i++) { + my %co = %{$commitlist->[$i]}; + next if !%co; + my $commit = $co{'id'}; + my $ref = format_ref_marker($refs, $commit); + git_print_header_div('commit', + "$co{'age_string'}" . + esc_html($co{'title'}) . $ref, + $commit); + print "
\n" . + "
\n" . + $cgi->a({-href => href(action=>"commit", hash=>$commit)}, "commit") . + " | " . + $cgi->a({-href => href(action=>"commitdiff", hash=>$commit)}, "commitdiff") . + " | " . + $cgi->a({-href => href(action=>"tree", hash=>$commit, hash_base=>$commit)}, "tree") . + "
\n" . + "
\n"; + git_print_authorship(\%co, -tag => 'span'); + print "
\n
\n"; + + print "
\n"; + git_print_log($co{'comment'}, -final_empty_line=> 1); + print "
\n"; + } + if ($extra) { + print "
\n"; + print "$extra\n"; + print "
\n"; + } +} + sub git_shortlog_body { # uses global variable $project my ($commitlist, $from, $to, $refs, $extra) = @_; @@ -4069,11 +5954,9 @@ sub git_shortlog_body { print "\n"; } $alternate ^= 1; - my $author = chop_and_escape_str($co{'author_name'}, 10); # git_summary() used print "$co{'age_string'}\n" . print "$co{'age_string_date'}\n" . - "" . $author . "\n" . - ""; + format_author_html('td', \%co, 10) . ""; print format_subject_html($co{'title'}, $co{'title_short'}, href(action=>"commit", hash=>$commit), $ref); print "\n" . @@ -4098,7 +5981,8 @@ sub git_shortlog_body { sub git_history_body { # Warning: assumes constant type (blob or tree) during history - my ($commitlist, $from, $to, $refs, $hash_base, $ftype, $extra) = @_; + my ($commitlist, $from, $to, $refs, $extra, + $file_name, $file_hash, $ftype) = @_; $from = 0 unless defined $from; $to = $#{$commitlist} unless (defined $to && $to <= $#{$commitlist}); @@ -4120,11 +6004,9 @@ sub git_history_body { print "\n"; } $alternate ^= 1; - # shortlog uses chop_str($co{'author_name'}, 10) - my $author = chop_and_escape_str($co{'author_name'}, 15, 3); print "$co{'age_string_date'}\n" . - "" . $author . "\n" . - ""; + # shortlog: format_author_html('td', \%co, 10) + format_author_html('td', \%co, 15, 3) . ""; # originally git_history used chop_str($co{'title'}, 50) print format_subject_html($co{'title'}, $co{'title_short'}, href(action=>"commit", hash=>$commit), $ref); @@ -4134,7 +6016,10 @@ sub git_history_body { $cgi->a({-href => href(action=>"commitdiff", hash=>$commit)}, "commitdiff"); if ($ftype eq 'blob') { - my $blob_current = git_get_hash_by_path($hash_base, $file_name); + 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 && $blob_current ne $blob_parent) { @@ -4222,7 +6107,7 @@ sub git_tags_body { sub git_heads_body { # uses global variable $project - my ($headlist, $head, $from, $to, $extra) = @_; + my ($headlist, $head_at, $from, $to, $extra) = @_; $from = 0 unless defined $from; $to = $#{$headlist} if (!defined $to || $#{$headlist} < $to); @@ -4231,7 +6116,7 @@ sub git_heads_body { for (my $i = $from; $i <= $to; $i++) { my $entry = $headlist->[$i]; my %ref = %$entry; - my $curr = $ref{'id'} eq $head; + my $curr = defined $head_at && $ref{'id'} eq $head_at; if ($alternate) { print "\n"; } else { @@ -4246,7 +6131,7 @@ sub git_heads_body { "" . $cgi->a({-href => href(action=>"shortlog", hash=>$ref{'fullname'})}, "shortlog") . " | " . $cgi->a({-href => href(action=>"log", hash=>$ref{'fullname'})}, "log") . " | " . - $cgi->a({-href => href(action=>"tree", hash=>$ref{'fullname'}, hash_base=>$ref{'name'})}, "tree") . + $cgi->a({-href => href(action=>"tree", hash=>$ref{'fullname'}, hash_base=>$ref{'fullname'})}, "tree") . "\n" . ""; } @@ -4258,6 +6143,312 @@ sub git_heads_body { print "\n"; } +# Display a single remote block +sub git_remote_block { + my ($remote, $rdata, $limit, $head) = @_; + + my $heads = $rdata->{'heads'}; + my $fetch = $rdata->{'fetch'}; + my $push = $rdata->{'push'}; + + my $urls_table = "\n" ; + + if (defined $fetch) { + if ($fetch eq $push) { + $urls_table .= format_repo_url("URL", $fetch); + } else { + $urls_table .= format_repo_url("Fetch URL", $fetch); + $urls_table .= format_repo_url("Push URL", $push) if defined $push; + } + } elsif (defined $push) { + $urls_table .= format_repo_url("Push URL", $push); + } else { + $urls_table .= format_repo_url("", "No remote URL"); + } + + $urls_table .= "
\n"; + + my $dots; + if (defined $limit && $limit < @$heads) { + $dots = $cgi->a({-href => href(action=>"remotes", hash=>$remote)}, "..."); + } + + print $urls_table; + git_heads_body($heads, $head, 0, $limit, $dots); +} + +# Display a list of remote names with the respective fetch and push URLs +sub git_remotes_list { + my ($remotedata, $limit) = @_; + print "\n"; + my $alternate = 1; + my @remotes = sort keys %$remotedata; + + my $limited = $limit && $limit < @remotes; + + $#remotes = $limit - 1 if $limited; + + while (my $remote = shift @remotes) { + my $rdata = $remotedata->{$remote}; + my $fetch = $rdata->{'fetch'}; + my $push = $rdata->{'push'}; + if ($alternate) { + print "\n"; + } else { + print "\n"; + } + $alternate ^= 1; + print ""; + print ""; + + print "\n"; + } + + if ($limited) { + print "\n" . + "\n" . "\n"; + } + + print "
" . + $cgi->a({-href=> href(action=>'remotes', hash=>$remote), + -class=> "list name"},esc_html($remote)) . + "" . + (defined $fetch ? $cgi->a({-href=> $fetch}, "fetch") : "fetch") . + " | " . + (defined $push ? $cgi->a({-href=> $push}, "push") : "push") . + "
" . + $cgi->a({-href => href(action=>"remotes")}, "...") . + "
"; +} + +# Display remote heads grouped by remote, unless there are too many +# remotes, in which case we only display the remote names +sub git_remotes_body { + my ($remotedata, $limit, $head) = @_; + if ($limit and $limit < keys %$remotedata) { + git_remotes_list($remotedata, $limit); + } else { + fill_remote_heads($remotedata); + while (my ($remote, $rdata) = each %$remotedata) { + git_print_section({-class=>"remote", -id=>$remote}, + ["remotes", $remote, $remote], sub { + git_remote_block($remote, $rdata, $limit, $head); + }); + } + } +} + +sub git_search_message { + my %co = @_; + + my $greptype; + if ($searchtype eq 'commit') { + $greptype = "--grep="; + } elsif ($searchtype eq 'author') { + $greptype = "--author="; + } elsif ($searchtype eq 'committer') { + $greptype = "--committer="; + } + $greptype .= $searchtext; + my @commitlist = parse_commits($hash, 101, (100 * $page), undef, + $greptype, '--regexp-ignore-case', + $search_use_regexp ? '--extended-regexp' : '--fixed-strings'); + + my $paging_nav = ''; + if ($page > 0) { + $paging_nav .= + $cgi->a({-href => href(-replay=>1, page=>undef)}, + "first") . + " ⋅ " . + $cgi->a({-href => href(-replay=>1, page=>$page-1), + -accesskey => "p", -title => "Alt-p"}, "prev"); + } else { + $paging_nav .= "first ⋅ prev"; + } + my $next_link = ''; + if ($#commitlist >= 100) { + $next_link = + $cgi->a({-href => href(-replay=>1, page=>$page+1), + -accesskey => "n", -title => "Alt-n"}, "next"); + $paging_nav .= " ⋅ $next_link"; + } else { + $paging_nav .= " ⋅ next"; + } + + git_header_html(); + + git_print_page_nav('','', $hash,$co{'tree'},$hash, $paging_nav); + git_print_header_div('commit', esc_html($co{'title'}), $hash); + if ($page == 0 && !@commitlist) { + print "

No match.

\n"; + } else { + git_search_grep_body(\@commitlist, 0, 99, $next_link); + } + + git_footer_html(); +} + +sub git_search_changes { + my %co = @_; + + local $/ = "\n"; + open my $fd, '-|', git_cmd(), '--no-pager', 'log', @diff_opts, + '--pretty=format:%H', '--no-abbrev', '--raw', "-S$searchtext", + ($search_use_regexp ? '--pickaxe-regex' : ()) + or die_error(500, "Open git-log failed"); + + git_header_html(); + + git_print_page_nav('','', $hash,$co{'tree'},$hash); + git_print_header_div('commit', esc_html($co{'title'}), $hash); + + print "\n"; + my $alternate = 1; + undef %co; + my @files; + while (my $line = <$fd>) { + chomp $line; + next unless $line; + + my %set = parse_difftree_raw_line($line); + if (defined $set{'commit'}) { + # finish previous commit + if (%co) { + print "\n" . + "\n" . + "\n"; + } + + if ($alternate) { + print "\n"; + } else { + print "\n"; + } + $alternate ^= 1; + %co = parse_commit($set{'commit'}); + my $author = chop_and_escape_str($co{'author_name'}, 15, 5); + print "\n" . + "\n" . + "\n" . + "\n" . + "\n"; + } + + print "
" . + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'})}, + "commit") . + " | " . + $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, + hash_base=>$co{'id'})}, + "tree") . + "
$co{'age_string_date'}$author" . + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), + -class => "list subject"}, + chop_and_escape_str($co{'title'}, 50) . "
"); + } elsif (defined $set{'to_id'}) { + 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'}), + -class => "list"}, + "" . esc_path($set{'file'}) . "") . + "
\n"; + } + } + close $fd; + + # finish last commit (warning: repetition!) + if (%co) { + print "
" . + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'})}, + "commit") . + " | " . + $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, + hash_base=>$co{'id'})}, + "tree") . + "
\n"; + + git_footer_html(); +} + +sub git_search_files { + my %co = @_; + + local $/ = "\n"; + open my $fd, "-|", git_cmd(), 'grep', '-n', '-z', + $search_use_regexp ? ('-E', '-i') : '-F', + $searchtext, $co{'tree'} + or die_error(500, "Open git-grep failed"); + + git_header_html(); + + git_print_page_nav('','', $hash,$co{'tree'},$hash); + git_print_header_div('commit', esc_html($co{'title'}), $hash); + + print "\n"; + my $alternate = 1; + my $matches = 0; + my $lastfile = ''; + my $file_href; + while (my $line = <$fd>) { + chomp $line; + my ($file, $lno, $ltext, $binary); + last if ($matches++ > 1000); + if ($line =~ /^Binary file (.+) matches$/) { + $file = $1; + $binary = 1; + } else { + ($file, $lno, $ltext) = split(/\0/, $line, 3); + $file =~ s/^$co{'tree'}://; + } + if ($file ne $lastfile) { + $lastfile and print "\n"; + if ($alternate++) { + print "\n"; + } else { + print "\n"; + } + $file_href = href(action=>"blob", hash_base=>$co{'id'}, + file_name=>$file); + print "\n"; + if ($matches > 1000) { + print "
Too many matches, listing trimmed
\n"; + } + } else { + print "
No matches found
\n"; + } + close $fd; + + print "
". + $cgi->a({-href => $file_href, -class => "list"}, esc_path($file)); + print "\n"; + $lastfile = $file; + } + if ($binary) { + print "
Binary file
\n"; + } else { + $ltext = untabify($ltext); + if ($ltext =~ m/^(.*)($search_regexp)(.*)$/i) { + $ltext = esc_html($1, -nbsp=>1); + $ltext .= ''; + $ltext .= esc_html($2, -nbsp=>1); + $ltext .= ''; + $ltext .= esc_html($3, -nbsp=>1); + } else { + $ltext = esc_html($ltext, -nbsp=>1); + } + print "
" . + $cgi->a({-href => $file_href.'#l'.$lno, + -class => "linenr"}, sprintf('%4i', $lno)) . + ' ' . $ltext . "
\n"; + } + } + if ($lastfile) { + print "
\n"; + + git_footer_html(); +} + sub git_search_grep_body { my ($commitlist, $from, $to, $extra) = @_; $from = 0 unless defined $from; @@ -4277,9 +6468,8 @@ sub git_search_grep_body { print "\n"; } $alternate ^= 1; - my $author = chop_and_escape_str($co{'author_name'}, 15, 5); print "$co{'age_string_date'}\n" . - "" . $author . "\n" . + format_author_html('td', \%co, 15, 5) . "" . $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), -class => "list subject"}, @@ -4329,24 +6519,19 @@ sub git_project_list { die_error(400, "Unknown order parameter"); } - my @list = git_get_projects_list(); + my @list = git_get_projects_list($project_filter, $strict_export); if (!@list) { die_error(404, "No projects found"); } git_header_html(); - if (-f $home_text) { + if (defined $home_text && -f $home_text) { print "
\n"; - open (my $fd, $home_text); - print <$fd>; - close $fd; + insert_file($home_text); print "
\n"; } - print $cgi->startform(-method => "get") . - "

Search:\n" . - $cgi->textfield(-name => "s", -value => $searchtext) . "\n" . - "

" . - $cgi->end_form() . "\n"; + + git_project_search_form($searchtext, $search_use_regexp); git_project_list_body(\@list, $order); git_footer_html(); } @@ -4357,7 +6542,9 @@ sub git_forks { die_error(400, "Unknown order parameter"); } - my @list = git_get_projects_list($project); + my $filter = $project; + $filter =~ s/\.git$//; + my @list = git_get_projects_list($filter); if (!@list) { die_error(404, "No forks found"); } @@ -4370,7 +6557,10 @@ sub git_forks { } sub git_project_index { - my @projects = git_get_projects_list($project); + my @projects = git_get_projects_list($project_filter, $strict_export); + if (!@projects) { + die_error(404, "No projects found"); + } print $cgi->header( -type => 'text/plain', @@ -4398,6 +6588,7 @@ sub git_summary { my %co = parse_commit("HEAD"); my %cd = %co ? parse_date($co{'committer_epoch'}, $co{'committer_tz'}) : (); my $head = $co{'id'}; + my $remote_heads = gitweb_check_feature('remote_heads'); my $owner = git_get_project_owner($project); @@ -4406,11 +6597,18 @@ sub git_summary { # there are more ... my @taglist = git_get_tags_list(16); my @headlist = git_get_heads_list(16); + my %remotedata = $remote_heads ? git_get_remotes_list() : (); my @forklist; - my ($check_forks) = gitweb_check_feature('forks'); + my $check_forks = gitweb_check_feature('forks'); if ($check_forks) { - @forklist = git_get_projects_list($project); + # find forks of a project + my $filter = $project; + $filter =~ s/\.git$//; + @forklist = git_get_projects_list($filter); + # filter out forks of forks + @forklist = filter_forks_from_projects_list(\@forklist) + if (@forklist); } git_header_html(); @@ -4418,10 +6616,13 @@ sub git_summary { print "
 
\n"; print "\n" . - "\n" . - "\n"; + "\n"; + if ($owner and not $omit_owner) { + print "\n"; + } if (defined $cd{'rfc2822'}) { - print "\n"; + print "" . + "\n"; } # use per project git URL list in $projectroot/$project/cloneurl @@ -4431,33 +6632,33 @@ sub git_summary { @url_list = map { "$_/$project" } @git_base_url_list unless @url_list; foreach my $git_url (@url_list) { next unless $git_url; - print "\n"; + print format_repo_url($url_tag, $git_url); $url_tag = ""; } # Tag cloud - my $show_ctags = (gitweb_check_feature('ctags'))[0]; + my $show_ctags = gitweb_check_feature('ctags'); if ($show_ctags) { my $ctags = git_get_project_ctags($project); - my $cloud = git_populate_project_tagcloud($ctags); - print "\n\n"; + if (%$ctags) { + # without ability to add tags, don't show if there are none + my $cloud = git_populate_project_tagcloud($ctags); + print "" . + "" . + "" . + "\n"; + } } print "
description" . esc_html($descr) . "
owner" . esc_html($owner) . "
description" . esc_html($descr) . "
owner" . esc_html($owner) . "
last change$cd{'rfc2822'}
last change".format_timestamp_html(\%cd)."
Content tags:
"; - print "
" unless %$ctags; - print "
Add:
"; - print "
" if %$ctags; - print git_show_project_tagcloud($cloud, 48); - print "
content tags".git_show_project_tagcloud($cloud, 48)."
\n"; - if (-s "$projectroot/$project/README.html") { - if (open my $fd, "$projectroot/$project/README.html") { - print "
readme
\n" . - "
\n"; - print $_ while (<$fd>); - print "\n
\n"; # class="readme" - close $fd; - } + # If XSS prevention is on, we don't include README.html. + # TODO: Allow a readme in some safe format. + if (!$prevent_xss && -s "$projectroot/$project/README.html") { + print "
readme
\n" . + "
\n"; + insert_file("$projectroot/$project/README.html"); + print "\n
\n"; # class="readme" } # we need to request one more than 16 (0..15) to check if @@ -4484,6 +6685,11 @@ sub git_summary { $cgi->a({-href => href(action=>"heads")}, "...")); } + if (%remotedata) { + git_print_header_div('remotes'); + git_remotes_body(\%remotedata, 15, $head); + } + if (@forklist) { git_print_header_div('forks'); git_project_list_body(\@forklist, 'age', 0, 15, @@ -4496,15 +6702,15 @@ sub git_summary { } sub git_tag { - my $head = git_get_head_hash($project); - git_header_html(); - git_print_page_nav('','', $head,undef,$head); my %tag = parse_tag($hash); if (! %tag) { die_error(404, "Unknown tag object"); } + my $head = git_get_head_hash($project); + git_header_html(); + git_print_page_nav('','', $head,undef,$head); git_print_header_div('commit', esc_html($tag{'name'}), $hash); print "
\n" . "\n" . @@ -4516,11 +6722,7 @@ sub git_tag { $tag{'type'}) . "\n" . "\n"; if (defined($tag{'author'})) { - my %ad = parse_date($tag{'epoch'}, $tag{'tz'}); - print "\n"; - print "\n"; + git_print_authorship_rows(\%tag, 'author'); } print "
author" . esc_html($tag{'author'}) . "
" . $ad{'rfc2822'} . - sprintf(" (%02d:%02d %s)", $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}) . - "
\n\n" . "
\n"; @@ -4534,117 +6736,255 @@ sub git_tag { git_footer_html(); } -sub git_blame { - my $fd; - my $ftype; +sub git_blame_common { + my $format = shift || 'porcelain'; + if ($format eq 'porcelain' && $input_params{'javascript'}) { + $format = 'incremental'; + $action = 'blame_incremental'; # for page title etc + } + # permissions gitweb_check_feature('blame') - or die_error(403, "Blame view not allowed"); + or die_error(403, "Blame view not allowed"); + # error checking die_error(400, "No file name given") unless $file_name; $hash_base ||= git_get_head_hash($project); - die_error(404, "Couldn't find base commit") unless ($hash_base); + die_error(404, "Couldn't find base commit") unless $hash_base; my %co = parse_commit($hash_base) or die_error(404, "Commit not found"); + my $ftype = "blob"; if (!defined $hash) { $hash = git_get_hash_by_path($hash_base, $file_name, "blob") or die_error(404, "Error looking up file"); + } else { + $ftype = git_get_type($hash); + if ($ftype !~ "blob") { + die_error(400, "Object is not a blob"); + } } - $ftype = git_get_type($hash); - if ($ftype !~ "blob") { - die_error(400, "Object is not a blob"); + + my $fd; + if ($format eq 'incremental') { + # get file contents (as base) + open $fd, "-|", git_cmd(), 'cat-file', 'blob', $hash + or die_error(500, "Open git-cat-file failed"); + } elsif ($format eq 'data') { + # run git-blame --incremental + open $fd, "-|", git_cmd(), "blame", "--incremental", + $hash_base, "--", $file_name + or die_error(500, "Open git-blame --incremental failed"); + } else { + # run git-blame --porcelain + open $fd, "-|", git_cmd(), "blame", '-p', + $hash_base, '--', $file_name + or die_error(500, "Open git-blame --porcelain failed"); } - open ($fd, "-|", git_cmd(), "blame", '-p', '--', - $file_name, $hash_base) - or die_error(500, "Open git-blame failed"); + binmode $fd, ':utf8'; + + # incremental blame data returns early + if ($format eq 'data') { + print $cgi->header( + -type=>"text/plain", -charset => "utf-8", + -status=> "200 OK"); + local $| = 1; # output autoflush + while (my $line = <$fd>) { + print to_utf8($line); + } + close $fd + or print "ERROR $!\n"; + + print 'END'; + if (defined $t0 && gitweb_check_feature('timed')) { + print ' '. + tv_interval($t0, [ gettimeofday() ]). + ' '.$number_of_git_cmds; + } + print "\n"; + + return; + } + + # page header git_header_html(); my $formats_nav = $cgi->a({-href => href(action=>"blob", -replay=>1)}, "blob") . + " | "; + if ($format eq 'incremental') { + $formats_nav .= + $cgi->a({-href => href(action=>"blame", javascript=>0, -replay=>1)}, + "blame") . " (non-incremental)"; + } else { + $formats_nav .= + $cgi->a({-href => href(action=>"blame_incremental", -replay=>1)}, + "blame") . " (incremental)"; + } + $formats_nav .= " | " . $cgi->a({-href => href(action=>"history", -replay=>1)}, "history") . " | " . - $cgi->a({-href => href(action=>"blame", file_name=>$file_name)}, + $cgi->a({-href => href(action=>$action, file_name=>$file_name)}, "HEAD"); git_print_page_nav('','', $hash_base,$co{'tree'},$hash_base, $formats_nav); git_print_header_div('commit', esc_html($co{'title'}), $hash_base); git_print_page_path($file_name, $ftype, $hash_base); - my @rev_color = (qw(light2 dark2)); + + # page body + if ($format eq 'incremental') { + print "\n"; + + print qq!
\n!; + } + + print qq!
\n!; + print qq!
... / ...
\n! + if ($format eq 'incremental'); + print qq!\n!. + #qq!\n!. + qq!\n!. + qq!\n!. + qq!\n!. + qq!\n!; + + my @rev_color = qw(light dark); my $num_colors = scalar(@rev_color); my $current_color = 0; - my $last_rev; - print < -
CommitLineData
- -HTML - my %metainfo = (); - while (1) { - $_ = <$fd>; - last unless defined $_; - my ($full_rev, $orig_lineno, $lineno, $group_size) = - /^([0-9a-f]{40}) (\d+) (\d+)(?: (\d+))?$/; - if (!exists $metainfo{$full_rev}) { - $metainfo{$full_rev} = {}; - } - my $meta = $metainfo{$full_rev}; - while (<$fd>) { - last if (s/^\t//); - if (/^(\S+) (.*)$/) { - $meta->{$1} = $2; - } - } - my $data = $_; - chomp $data; - my $rev = substr($full_rev, 0, 8); - my $author = $meta->{'author'}; - my %date = parse_date($meta->{'author-time'}, - $meta->{'author-tz'}); - my $date = $date{'iso-tz'}; - if ($group_size) { - $current_color = ++$current_color % $num_colors; - } - print "\n"; - if ($group_size) { - print "\n"; + + if ($format eq 'incremental') { + my $color_class = $rev_color[$current_color]; + + #contents of a file + my $linenr = 0; + LINE: + while (my $line = <$fd>) { + chomp $line; + $linenr++; + + print qq!!. + qq!!. + qq!!; + print qq!\n"; + print qq!\n!; } - open (my $dd, "-|", git_cmd(), "rev-parse", "$full_rev^") - or die_error(500, "Open git-rev-parse failed"); - my $parent_commit = <$dd>; - close $dd; - chomp($parent_commit); - my $blamed = href(action => 'blame', - file_name => $meta->{'filename'}, - hash_base => $parent_commit); - print ""; - print "\n"; - print "\n"; + + } else { # porcelain, i.e. ordinary blame + my %metainfo = (); # saves information about commits + + # blame data + LINE: + while (my $line = <$fd>) { + chomp $line; + # the header: [] + # no for subsequent lines in group of lines + my ($full_rev, $orig_lineno, $lineno, $group_size) = + ($line =~ /^($oid_regex) (\d+) (\d+)(?: (\d+))?$/); + if (!exists $metainfo{$full_rev}) { + $metainfo{$full_rev} = { 'nprevious' => 0 }; + } + my $meta = $metainfo{$full_rev}; + my $data; + while ($data = <$fd>) { + chomp $data; + last if ($data =~ s/^\t//); # contents of line + if ($data =~ /^(\S+)(?: (.*))?$/) { + $meta->{$1} = $2 unless exists $meta->{$1}; + } + if ($data =~ /^previous /) { + $meta->{'nprevious'}++; + } + } + my $short_rev = substr($full_rev, 0, 8); + my $author = $meta->{'author'}; + my %date = + parse_date($meta->{'author-time'}, $meta->{'author-tz'}); + my $date = $date{'iso-tz'}; + if ($group_size) { + $current_color = ($current_color + 1) % $num_colors; + } + my $tr_class = $rev_color[$current_color]; + $tr_class .= ' boundary' if (exists $meta->{'boundary'}); + $tr_class .= ' no-previous' if ($meta->{'nprevious'} == 0); + $tr_class .= ' multiple-previous' if ($meta->{'nprevious'} > 1); + print "\n"; + if ($group_size) { + print "\n"; + } + # 'previous' + if (exists $meta->{'previous'} && + $meta->{'previous'} =~ /^($oid_regex) (.*)$/) { + $meta->{'parent'} = $1; + $meta->{'file_parent'} = unquote($2); + } + my $linenr_commit = + exists($meta->{'parent'}) ? + $meta->{'parent'} : $full_rev; + my $linenr_filename = + exists($meta->{'file_parent'}) ? + $meta->{'file_parent'} : unquote($meta->{'filename'}); + my $blamed = href(action => 'blame', + file_name => $linenr_filename, + hash_base => $linenr_commit); + print ""; + print "\n"; + print "\n"; + } # end while + } - print "
CommitLineData
1); - print ">"; - print $cgi->a({-href => href(action=>"commit", - hash=>$full_rev, - file_name=>$file_name)}, - esc_html($rev)); - print "
!. + qq!$linenr! . esc_html($line) . "
"; - print $cgi->a({ -href => "$blamed#l$orig_lineno", - -id => "l$lineno", - -class => "linenr" }, - esc_html($lineno)); - print "" . esc_html($data) . "
1); + print ">"; + print $cgi->a({-href => href(action=>"commit", + hash=>$full_rev, + file_name=>$file_name)}, + esc_html($short_rev)); + if ($group_size >= 2) { + my @author_initials = ($author =~ /\b([[:upper:]])\B/g); + if (@author_initials) { + print "
" . + esc_html(join('', @author_initials)); + # or join('.', ...) + } + } + print "
"; + print $cgi->a({ -href => "$blamed#l$orig_lineno", + -class => "linenr" }, + esc_html($lineno)); + print "" . esc_html($data) . "
\n"; - print "
"; + + # footer + print "\n". + "\n"; # class="blame" + print "
\n"; # class="blame_body" close $fd or print "Reading blob failed\n"; + git_footer_html(); } +sub git_blame { + git_blame_common(); +} + +sub git_blame_incremental { + git_blame_common('incremental'); +} + +sub git_blame_data { + git_blame_common('data'); +} + sub git_tags { my $head = git_get_head_hash($project); git_header_html(); - git_print_page_nav('','', $head,undef,$head); + git_print_page_nav('','', $head,undef,$head,format_ref_views('tags')); git_print_header_div('summary', $project); my @tagslist = git_get_tags_list(); @@ -4657,7 +6997,7 @@ sub git_tags { sub git_heads { my $head = git_get_head_hash($project); git_header_html(); - git_print_page_nav('','', $head,undef,$head); + git_print_page_nav('','', $head,undef,$head,format_ref_views('heads')); git_print_header_div('summary', $project); my @headslist = git_get_heads_list(); @@ -4667,6 +7007,39 @@ sub git_heads { git_footer_html(); } +# used both for single remote view and for list of all the remotes +sub git_remotes { + gitweb_check_feature('remote_heads') + or die_error(403, "Remote heads view is disabled"); + + my $head = git_get_head_hash($project); + my $remote = $input_params{'hash'}; + + my $remotedata = git_get_remotes_list($remote); + die_error(500, "Unable to get remote information") unless defined $remotedata; + + unless (%$remotedata) { + die_error(404, defined $remote ? + "Remote $remote not found" : + "No remotes found"); + } + + git_header_html(undef, undef, -action_extra => $remote); + git_print_page_nav('', '', $head, undef, $head, + format_ref_views($remote ? '' : 'remotes')); + + fill_remote_heads($remotedata); + if (defined $remote) { + git_print_header_div('remotes', "$remote remote for $project"); + git_remote_block($remote, $remotedata->{$remote}, undef, $head); + } else { + git_print_header_div('summary', "$project remotes"); + git_remotes_body($remotedata, undef, $head); + } + + git_footer_html(); +} + sub git_blob_plain { my $type = shift; my $expires; @@ -4679,7 +7052,7 @@ sub git_blob_plain { } else { die_error(400, "No file name defined"); } - } elsif ($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"; } @@ -4698,15 +7071,35 @@ sub git_blob_plain { $save_as .= '.txt'; } + # With XSS prevention on, blobs of all types except a few known safe + # ones are served with "Content-Disposition: attachment" to make sure + # they don't run in our security domain. For certain image types, + # blob view writes an tag referring to blob_plain view, and we + # want to be sure not to break that by serving the image as an + # attachment (though Firefox 3 doesn't seem to care). + my $sandbox = $prevent_xss && + $type !~ m!^(?:text/[a-z]+|image/(?:gif|png|jpeg))(?:[ ;]|$)!; + + # serve text/* as text/plain + if ($prevent_xss && + ($type =~ m!^text/[a-z]+\b(.*)$! || + ($type =~ m!^[a-z]+/[a-z]\+xml\b(.*)$! && -T $fd))) { + my $rest = $1; + $rest = defined $rest ? $rest : ''; + $type = "text/plain$rest"; + } + print $cgi->header( -type => $type, -expires => $expires, - -content_disposition => 'inline; filename="' . $save_as . '"'); - undef $/; + -content_disposition => + ($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 - $/ = "\n"; close $fd; } @@ -4721,15 +7114,16 @@ sub git_blob { } else { die_error(400, "No file name defined"); } - } elsif ($hash =~ m/^[0-9a-fA-F]{40}$/) { + } elsif ($hash =~ m/^$oid_regex$/) { # blobs defined by non-textual hash id's can be cached $expires = "+1d"; } - my ($have_blame) = gitweb_check_feature('blame'); + my $have_blame = gitweb_check_feature('blame'); open my $fd, "-|", git_cmd(), "cat-file", "blob", $hash or die_error(500, "Couldn't cat $file_name, $hash"); my $mimetype = blob_mimetype($fd, $file_name); + # use 'blob_plain' (aka 'raw') view for files that cannot be displayed if ($mimetype !~ m!^(?:text/|image/(?:gif|png|jpeg)$)! && -B $fd) { close $fd; return git_blob_plain($mimetype); @@ -4737,6 +7131,10 @@ sub git_blob { # we can have blame only for text/* mimetype $have_blame &&= ($mimetype =~ m!^text/!); + my $highlight = gitweb_check_feature('highlight'); + my $syntax = guess_file_syntax($highlight, $file_name); + $fd = run_highlighter($fd, $highlight, $syntax); + git_header_html(undef, $expires); my $formats_nav = ''; if (defined $hash_base && (my %co = parse_commit($hash_base))) { @@ -4767,18 +7165,18 @@ sub git_blob { } else { print "
\n" . "

\n" . - "
$hash
\n"; + "
".esc_html($hash)."
\n"; } git_print_page_path($file_name, "blob", $hash_base); print "
\n"; if ($mimetype =~ m!^image/!) { - print qq!$file_name$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; @@ -4786,8 +7184,9 @@ sub git_blob { chomp $line; $nr++; $line = untabify($line); - printf "
%4i %s
\n", - $nr, $nr, $nr, esc_html($line, -nbsp=>1); + printf qq!
%4i %s
\n!, + $nr, esc_attr(href(-replay => 1)), $nr, $nr, + $highlight ? sanitize($line) : esc_html($line, -nbsp=>1); } } close $fd @@ -4808,18 +7207,25 @@ sub git_tree { } } die_error(404, "No such tree") unless defined($hash); - $/ = "\0"; - open my $fd, "-|", git_cmd(), "ls-tree", '-z', $hash - or die_error(500, "Open git-ls-tree failed"); - my @entries = map { chomp; $_ } <$fd>; - close $fd or die_error(404, "Reading tree failed"); - $/ = "\n"; + + my $show_sizes = gitweb_check_feature('show-sizes'); + my $have_blame = gitweb_check_feature('blame'); + + my @entries = (); + { + local $/ = "\0"; + open my $fd, "-|", git_cmd(), "ls-tree", '-z', + ($show_sizes ? '-l' : ()), @extra_options, $hash + or die_error(500, "Open git-ls-tree failed"); + @entries = map { chomp; $_ } <$fd>; + close $fd + or die_error(404, "Reading tree failed"); + } my $refs = git_get_references(); my $ref = format_ref_marker($refs, $hash_base); git_header_html(); my $basedir = ''; - my ($have_blame) = gitweb_check_feature('blame'); if (defined $hash_base && (my %co = parse_commit($hash_base))) { my @views_nav = (); if (defined $file_name) { @@ -4835,13 +7241,14 @@ sub git_tree { # FIXME: Should be available when we have no hash base as well. push @views_nav, $snapshot_links; } - git_print_page_nav('tree','', $hash_base, undef, undef, join(' | ', @views_nav)); + git_print_page_nav('tree','', $hash_base, undef, undef, + join(' | ', @views_nav)); git_print_header_div('commit', esc_html($co{'title'}) . $ref, $hash_base); } else { undef $hash_base; print "
\n"; print "

\n"; - print "
$hash
\n"; + print "
".esc_html($hash)."
\n"; } if (defined $file_name) { $basedir = $file_name; @@ -4868,8 +7275,10 @@ sub git_tree { undef $up unless $up; # based on git_print_tree_entry print '' . mode_str('040000') . "\n"; + print ' '."\n" if $show_sizes; print ''; - print $cgi->a({-href => href(action=>"tree", hash_base=>$hash_base, + print $cgi->a({-href => href(action=>"tree", + hash_base=>$hash_base, file_name=>$up)}, ".."); print "\n"; @@ -4878,7 +7287,7 @@ sub git_tree { print "\n"; } foreach my $line (@entries) { - my %t = parse_ls_tree_line($line, -z => 1); + my %t = parse_ls_tree_line($line, -z => 1, -l => $show_sizes); if ($alternate) { print "\n"; @@ -4896,6 +7305,84 @@ 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) = @_; + + # path/to/project.git -> project + # path/to/project/.git -> project + my $name = to_utf8($project); + $name =~ s,([^/])/*\.git$,$1,; + $name = sanitize_for_filename(basename($name)); + + my $ver = $hash; + if ($hash =~ /^[0-9a-fA-F]+$/) { + # shorten SHA-1 hash + my $full_hash = git_get_full_hash($project, $hash); + if ($full_hash =~ /^$hash/ && length($hash) > 7) { + $ver = git_get_short_hash($project, $hash); + } + } elsif ($hash =~ m!^refs/tags/(.*)$!) { + # tags don't need shortened SHA-1 hash + $ver = $1; + } else { + # branches and other need shortened SHA-1 hash + 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-$ver"; + + return wantarray ? ($name, $name) : $name; +} + +sub exit_if_unmodified_since { + my ($latest_epoch) = @_; + our $cgi; + + my $if_modified = $cgi->http('IF_MODIFIED_SINCE'); + if (defined $if_modified) { + my $since; + if (eval { require HTTP::Date; 1; }) { + $since = HTTP::Date::str2time($if_modified); + } elsif (eval { require Time::ParseDate; 1; }) { + $since = Time::ParseDate::parsedate($if_modified, GMT => 1); + } + if (defined $since && $latest_epoch <= $since) { + my %latest_date = parse_date($latest_epoch); + print $cgi->header( + -last_modified => $latest_date{'rfc2822'}, + -status => '304 Not Modified'); + goto DONE_GITWEB; + } + } +} + sub git_snapshot { my $format = $input_params{'snapshot_format'}; if (!@snapshot_fmts) { @@ -4907,107 +7394,138 @@ sub git_snapshot { die_error(400, "Invalid snapshot format parameter"); } elsif (!exists($known_snapshot_formats{$format})) { die_error(400, "Unknown snapshot format"); + } elsif ($known_snapshot_formats{$format}{'disabled'}) { + die_error(403, "Snapshot format not allowed"); } elsif (!grep($_ eq $format, @snapshot_fmts)) { die_error(403, "Unsupported snapshot format"); } - if (!defined $hash) { - $hash = git_get_head_hash($project); + my $type = git_get_type("$hash^{}"); + if (!$type) { + die_error(404, 'Object does not exist'); + } elsif ($type eq 'blob') { + die_error(400, 'Object is not a tree-ish'); } - my $name = $project; - $name =~ s,([^/])/*\.git$,$1,; - $name = basename($name); - my $filename = to_utf8($name); - $name =~ s/\047/\047\\\047\047/g; - my $cmd; - $filename .= "-$hash$known_snapshot_formats{$format}{'suffix'}"; - $cmd = quote_command( + my ($name, $prefix) = snapshot_name($project, $hash); + my $filename = "$name$known_snapshot_formats{$format}{'suffix'}"; + + my %co = parse_commit($hash); + exit_if_unmodified_since($co{'committer_epoch'}) if %co; + + my $cmd = quote_command( git_cmd(), 'archive', "--format=$known_snapshot_formats{$format}{'format'}", - "--prefix=$name/", $hash); + "--prefix=$prefix/", $hash); if (exists $known_snapshot_formats{$format}{'compressor'}) { $cmd .= ' | ' . quote_command(@{$known_snapshot_formats{$format}{'compressor'}}); } + $filename =~ s/(["\\])/\\$1/g; + my %latest_date; + if (%co) { + %latest_date = parse_date($co{'committer_epoch'}, $co{'committer_tz'}); + } + print $cgi->header( -type => $known_snapshot_formats{$format}{'type'}, - -content_disposition => 'inline; filename="' . "$filename" . '"', + -content_disposition => 'inline; filename="' . $filename . '"', + %co ? (-last_modified => $latest_date{'rfc2822'}) : (), -status => '200 OK'); 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 close $fd; } -sub git_log { +sub git_log_generic { + my ($fmt_name, $body_subr, $base, $parent, $file_name, $file_hash) = @_; + my $head = git_get_head_hash($project); - if (!defined $hash) { - $hash = $head; + if (!defined $base) { + $base = $head; } if (!defined $page) { $page = 0; } my $refs = git_get_references(); - my @commitlist = parse_commits($hash, 101, (100 * $page)); - - my $paging_nav = format_paging_nav('log', $hash, $head, $page, $#commitlist >= 100); + my $commit_hash = $base; + if (defined $parent) { + $commit_hash = "$parent..$base"; + } + my @commitlist = + parse_commits($commit_hash, 101, (100 * $page), + defined $file_name ? ($file_name, "--full-history") : ()); - git_header_html(); - git_print_page_nav('log','', $hash,undef,undef, $paging_nav); + my $ftype; + if (!defined $file_hash && defined $file_name) { + # some commits could have deleted file in question, + # and not have it in tree, but one of them has to have it + for (my $i = 0; $i < @commitlist; $i++) { + $file_hash = git_get_hash_by_path($commitlist[$i]{'id'}, $file_name); + last if defined $file_hash; + } + } + if (defined $file_hash) { + $ftype = git_get_type($file_hash); + } + if (defined $file_name && !defined $ftype) { + die_error(500, "Unknown type of object"); + } + my %co; + if (defined $file_name) { + %co = parse_commit($base) + or die_error(404, "Unknown commit object"); + } - if (!@commitlist) { - my %co = parse_commit($hash); - git_print_header_div('summary', $project); - print "
Last change $co{'age_string'}.

\n"; + my $paging_nav = format_paging_nav($fmt_name, $page, $#commitlist >= 100); + my $next_link = ''; + if ($#commitlist >= 100) { + $next_link = + $cgi->a({-href => href(-replay=>1, page=>$page+1), + -accesskey => "n", -title => "Alt-n"}, "next"); } - my $to = ($#commitlist >= 99) ? (99) : ($#commitlist); - for (my $i = 0; $i <= $to; $i++) { - my %co = %{$commitlist[$i]}; - next if !%co; - my $commit = $co{'id'}; - my $ref = format_ref_marker($refs, $commit); - my %ad = parse_date($co{'author_epoch'}); - git_print_header_div('commit', - "$co{'age_string'}" . - esc_html($co{'title'}) . $ref, - $commit); - print "
\n" . - "
\n" . - $cgi->a({-href => href(action=>"commit", hash=>$commit)}, "commit") . - " | " . - $cgi->a({-href => href(action=>"commitdiff", hash=>$commit)}, "commitdiff") . - " | " . - $cgi->a({-href => href(action=>"tree", hash=>$commit, hash_base=>$commit)}, "tree") . - "
\n" . - "
\n" . - "" . esc_html($co{'author_name'}) . " [$ad{'rfc2822'}]
\n" . - "
\n"; - - print "
\n"; - git_print_log($co{'comment'}, -final_empty_line=> 1); - print "
\n"; + my $patch_max = gitweb_get_feature('patches'); + if ($patch_max && !defined $file_name && + !gitweb_check_feature('email-privacy')) { + if ($patch_max < 0 || @commitlist <= $patch_max) { + $paging_nav .= " ⋅ " . + $cgi->a({-href => href(action=>"patches", -replay=>1)}, + "patches"); + } } - if ($#commitlist >= 100) { - print "
\n"; - print $cgi->a({-href => href(-replay=>1, page=>$page+1), - -accesskey => "n", -title => "Alt-n"}, "next"); - print "
\n"; + + git_header_html(); + git_print_page_nav($fmt_name,'', $hash,$hash,$hash, $paging_nav); + if (defined $file_name) { + git_print_header_div('commit', esc_html($co{'title'}), $base); + } else { + git_print_header_div('summary', $project) } + git_print_page_path($file_name, $ftype, $hash_base) + if (defined $file_name); + + $body_subr->(\@commitlist, 0, 99, $refs, $next_link, + $file_name, $file_hash, $ftype); + git_footer_html(); } +sub git_log { + git_log_generic('log', \&git_log_body, + $hash, $hash_parent); +} + sub git_commit { $hash ||= $hash_base || "HEAD"; my %co = parse_commit($hash) or die_error(404, "Unknown commit object"); - my %ad = parse_date($co{'author_epoch'}, $co{'author_tz'}); - my %cd = parse_date($co{'committer_epoch'}, $co{'committer_tz'}); my $parent = $co{'parent'}; my $parents = $co{'parents'}; # listref @@ -5036,6 +7554,12 @@ sub git_commit { } @$parents ) . ')'; } + if (gitweb_check_feature('patches') && @$parents <= 1 && + !gitweb_check_feature('email-privacy')) { + $formats_nav .= " | " . + $cgi->a({-href => href(action=>"patch", -replay=>1)}, + "patch"); + } if (!defined $parent) { $parent = "--root"; @@ -5051,7 +7575,7 @@ 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(); @@ -5069,22 +7593,7 @@ sub git_commit { } print "
\n" . "\n"; - print "\n". - "" . - "" . - "\n"; - print "\n"; - print "\n"; + git_print_authorship_rows(\%co); print "\n"; print "" . "" . @@ -5142,7 +7651,7 @@ 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"); @@ -5153,14 +7662,14 @@ 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; @@ -5177,6 +7686,7 @@ sub git_object { sub git_blobdiff { my $format = shift || 'html'; + my $diff_style = $input_params{'diff_style'} || 'inline'; my $fd; my @difftree; @@ -5199,7 +7709,7 @@ 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 @@ -5209,7 +7719,7 @@ 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"); @@ -5232,8 +7742,8 @@ 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'; } @@ -5245,43 +7755,9 @@ sub git_blobdiff { or die_error(500, "Open git-diff-tree failed"); } - # old/legacy style URI - if (!%diffinfo && # if new style URI failed - defined $hash && defined $hash_parent) { - # fake git-diff-tree raw output - $diffinfo{'from_mode'} = $diffinfo{'to_mode'} = "blob"; - $diffinfo{'from_id'} = $hash_parent; - $diffinfo{'to_id'} = $hash; - if (defined $file_name) { - if (defined $file_parent) { - $diffinfo{'status'} = '2'; - $diffinfo{'from_file'} = $file_parent; - $diffinfo{'to_file'} = $file_name; - } else { # assume not renamed - $diffinfo{'status'} = '1'; - $diffinfo{'from_file'} = $file_name; - $diffinfo{'to_file'} = $file_name; - } - } else { # no filename given - $diffinfo{'status'} = '2'; - $diffinfo{'from_file'} = $hash_parent; - $diffinfo{'to_file'} = $hash; - } - - # non-textual hash id's can be cached - if ($hash =~ m/^[0-9a-fA-F]{40}$/ && - $hash_parent =~ m/^[0-9a-fA-F]{40}$/) { - $expires = '+1d'; - } - - # open patch output - open $fd, "-|", git_cmd(), "diff", @diff_opts, - '-p', ($format eq 'html' ? "--full-index" : ()), - $hash_parent, $hash, "--" - or die_error(500, "Open git-diff failed"); - } else { - die_error(400, "Missing one of the blob diff parameters") - unless %diffinfo; + # old/legacy style URI -- not generated anymore since 1.4.3. + if (!%diffinfo) { + die_error('404 Not Found', "Missing one of the blob diff parameters") } # header @@ -5289,13 +7765,14 @@ sub git_blobdiff { my $formats_nav = $cgi->a({-href => href(action=>"blobdiff_plain", -replay=>1)}, "raw"); + $formats_nav .= diff_style_nav($diff_style); git_header_html(undef, $expires); if (defined $hash_base && (my %co = parse_commit($hash_base))) { git_print_page_nav('','', $hash_base,$co{'tree'},$hash_base, $formats_nav); git_print_header_div('commit', esc_html($co{'title'}), $hash_base); } else { print "

$formats_nav
\n"; - print "
$hash vs $hash_parent
\n"; + print "
".esc_html("$hash vs $hash_parent")."
\n"; } if (defined $file_name) { git_print_page_path($file_name, "blob", $hash_base); @@ -5320,7 +7797,8 @@ sub git_blobdiff { if ($format eq 'html') { print "
\n"; - git_patchset_body($fd, [ \%diffinfo ], $hash_base, $hash_parent_base); + git_patchset_body($fd, $diff_style, + [ \%diffinfo ], $hash_base, $hash_parent_base); close $fd; print "
\n"; # class="page_body" @@ -5345,8 +7823,37 @@ sub git_blobdiff_plain { git_blobdiff('plain'); } +# assumes that it is added as later part of already existing navigation, +# so it returns "| foo | bar" rather than just "foo | bar" +sub diff_style_nav { + my ($diff_style, $is_combined) = @_; + $diff_style ||= 'inline'; + + return "" if ($is_combined); + + my @styles = (inline => 'inline', 'sidebyside' => 'side by side'); + my %styles = @styles; + @styles = + @styles[ map { $_ * 2 } 0..$#styles/2 ]; + + return join '', + map { " | ".$_ } + map { + $_ eq $diff_style ? $styles{$_} : + $cgi->a({-href => href(-replay=>1, diff_style => $_)}, $styles{$_}) + } @styles; +} + sub git_commitdiff { - my $format = shift || 'html'; + my %params = @_; + my $format = $params{-format} || 'html'; + my $diff_style = $input_params{'diff_style'} || 'inline'; + + my ($patch_max) = gitweb_get_feature('patches'); + if ($format eq 'patch') { + die_error(403, "Patch view not allowed") unless $patch_max; + } + $hash ||= $hash_base || "HEAD"; my %co = parse_commit($hash) or die_error(404, "Unknown commit object"); @@ -5361,12 +7868,19 @@ sub git_commitdiff { $formats_nav = $cgi->a({-href => href(action=>"commitdiff_plain", -replay=>1)}, "raw"); + if ($patch_max && @{$co{'parents'}} <= 1 && + !gitweb_check_feature('email-privacy')) { + $formats_nav .= " | " . + $cgi->a({-href => href(action=>"patch", -replay=>1)}, + "patch"); + } + $formats_nav .= diff_style_nav($diff_style, @{$co{'parents'}} > 1); if (defined $hash_parent && $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 .= @@ -5378,8 +7892,8 @@ sub git_commitdiff { } } $formats_nav .= ': ' . - $cgi->a({-href => href(action=>"commitdiff", - hash=>$hash_parent)}, + $cgi->a({-href => href(-replay=>1, + hash=>$hash_parent, hash_base=>undef)}, esc_html($hash_parent_short)) . ')'; } elsif (!$co{'parent'}) { @@ -5389,28 +7903,28 @@ sub git_commitdiff { # single parent commit $formats_nav .= ' (parent: ' . - $cgi->a({-href => href(action=>"commitdiff", - hash=>$co{'parent'})}, + $cgi->a({-href => href(-replay=>1, + hash=>$co{'parent'}, hash_base=>undef)}, esc_html(substr($co{'parent'}, 0, 7))) . ')'; } else { # merge commit if ($hash_parent eq '--cc') { $formats_nav .= ' | ' . - $cgi->a({-href => href(action=>"commitdiff", + $cgi->a({-href => href(-replay=>1, hash=>$hash, hash_parent=>'-c')}, 'combined'); } else { # $hash_parent eq '-c' $formats_nav .= ' | ' . - $cgi->a({-href => href(action=>"commitdiff", + $cgi->a({-href => href(-replay=>1, hash=>$hash, hash_parent=>'--cc')}, 'compact'); } $formats_nav .= ' (merge: ' . join(' ', map { - $cgi->a({-href => href(action=>"commitdiff", - hash=>$_)}, + $cgi->a({-href => href(-replay=>1, + hash=>$_, hash_base=>undef)}, esc_html(substr($_, 0, 7))); } @{$co{'parents'}} ) . ')'; @@ -5444,14 +7958,38 @@ sub git_commitdiff { open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, '-p', $hash_parent_param, $hash, "--" or die_error(500, "Open git-diff-tree failed"); - + } elsif ($format eq 'patch') { + # For commit ranges, we limit the output to the number of + # patches specified in the 'patches' feature. + # For single commits, we limit the output to a single patch, + # diverging from the git-format-patch default. + my @commit_spec = (); + if ($hash_parent) { + if ($patch_max > 0) { + push @commit_spec, "-$patch_max"; + } + push @commit_spec, '-n', "$hash_parent..$hash"; + } else { + if ($params{-single}) { + push @commit_spec, '-1'; + } else { + if ($patch_max > 0) { + push @commit_spec, "-$patch_max"; + } + push @commit_spec, "-n"; + } + push @commit_spec, '--root', $hash; + } + open $fd, "-|", git_cmd(), "format-patch", @diff_opts, + '--encoding=utf8', '--stdout', @commit_spec + or die_error(500, "Open git-format-patch failed"); } else { die_error(400, "Unknown commitdiff format"); } # 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"; } @@ -5463,7 +8001,11 @@ sub git_commitdiff { git_header_html(undef, $expires); git_print_page_nav('commitdiff','', $hash,$co{'tree'},$hash, $formats_nav); git_print_header_div('commit', esc_html($co{'title'}) . $ref, $hash); - git_print_authorship(\%co); + print "
\n" . + "
author" . esc_html($co{'author'}) . "
$ad{'rfc2822'}"; - if ($ad{'hour_local'} < 6) { - printf(" (%02d:%02d %s)", - $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); - } else { - printf(" (%02d:%02d %s)", - $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); - } - print "
committer" . esc_html($co{'committer'}) . "
$cd{'rfc2822'}" . - sprintf(" (%02d:%02d %s)", $cd{'hour_local'}, $cd{'minute_local'}, $cd{'tz_local'}) . - "
commit$co{'id'}
tree
\n"; + git_print_authorship_rows(\%co); + print "
". + "
\n"; print "
\n"; if (@{$co{'comment'}} > 1) { print "
\n"; @@ -5493,6 +8035,14 @@ sub git_commitdiff { print to_utf8($line) . "\n"; } print "---\n\n"; + } elsif ($format eq 'patch') { + my $filename = basename($project) . "-$hash.patch"; + + print $cgi->header( + -type => 'text/plain', + -charset => 'utf-8', + -expires => $expires, + -content_disposition => 'inline; filename="' . "$filename" . '"'); } # write patch @@ -5503,7 +8053,8 @@ sub git_commitdiff { $use_parents ? @{$co{'parents'}} : $hash_parent); print "
\n"; - git_patchset_body($fd, \@difftree, $hash, + git_patchset_body($fd, $diff_style, + \@difftree, $hash, $use_parents ? @{$co{'parents'}} : $hash_parent); close $fd; print "
\n"; # class="page_body" @@ -5514,82 +8065,51 @@ sub git_commitdiff { print <$fd>; close $fd or print "Reading git-diff-tree failed\n"; + } elsif ($format eq 'patch') { + local $/ = undef; + print <$fd>; + close $fd + or print "Reading git-format-patch failed\n"; } } sub git_commitdiff_plain { - git_commitdiff('plain'); + git_commitdiff(-format => 'plain'); } -sub git_history { - if (!defined $hash_base) { - $hash_base = git_get_head_hash($project); - } - if (!defined $page) { - $page = 0; - } - my $ftype; - my %co = parse_commit($hash_base) - or die_error(404, "Unknown commit object"); +# format-patch-style patches +sub git_patch { + git_commitdiff(-format => 'patch', -single => 1); +} - my $refs = git_get_references(); - my $limit = sprintf("--max-count=%i", (100 * ($page+1))); +sub git_patches { + git_commitdiff(-format => 'patch'); +} - my @commitlist = parse_commits($hash_base, 101, (100 * $page), - $file_name, "--full-history") - or die_error(404, "No such file or directory on given branch"); +sub git_history { + git_log_generic('history', \&git_history_body, + $hash_base, $hash_parent_base, + $file_name, $hash); +} - if (!defined $hash && defined $file_name) { - # some commits could have deleted file in question, - # and not have it in tree, but one of them has to have it - for (my $i = 0; $i <= @commitlist; $i++) { - $hash = git_get_hash_by_path($commitlist[$i]{'id'}, $file_name); - last if defined $hash; - } - } - if (defined $hash) { - $ftype = git_get_type($hash); - } - if (!defined $ftype) { - die_error(500, "Unknown type of object"); - } +sub git_search { + $searchtype ||= 'commit'; - my $paging_nav = ''; - if ($page > 0) { - $paging_nav .= - $cgi->a({-href => href(action=>"history", hash=>$hash, hash_base=>$hash_base, - file_name=>$file_name)}, - "first"); - $paging_nav .= " ⋅ " . - $cgi->a({-href => href(-replay=>1, page=>$page-1), - -accesskey => "p", -title => "Alt-p"}, "prev"); - } else { - $paging_nav .= "first"; - $paging_nav .= " ⋅ prev"; + # check if appropriate features are enabled + gitweb_check_feature('search') + or die_error(403, "Search is disabled"); + if ($searchtype eq 'pickaxe') { + # pickaxe may take all resources of your box and run for several minutes + # with every query - so decide by yourself how public you make this feature + gitweb_check_feature('pickaxe') + or die_error(403, "Pickaxe search is disabled"); } - my $next_link = ''; - if ($#commitlist >= 100) { - $next_link = - $cgi->a({-href => href(-replay=>1, page=>$page+1), - -accesskey => "n", -title => "Alt-n"}, "next"); - $paging_nav .= " ⋅ $next_link"; - } else { - $paging_nav .= " ⋅ next"; + if ($searchtype eq 'grep') { + # grep search might be potentially CPU-intensive, too + gitweb_check_feature('grep') + or die_error(403, "Grep search is disabled"); } - git_header_html(); - git_print_page_nav('history','', $hash_base,$co{'tree'},$hash_base, $paging_nav); - git_print_header_div('commit', esc_html($co{'title'}), $hash_base); - git_print_page_path($file_name, $ftype, $hash_base); - - git_history_body(\@commitlist, 0, 99, - $refs, $hash_base, $ftype, $next_link); - - git_footer_html(); -} - -sub git_search { - gitweb_check_feature('search') or die_error(403, "Search is disabled"); if (!defined $searchtext) { die_error(400, "Text field is empty"); } @@ -5604,204 +8124,17 @@ sub git_search { $page = 0; } - $searchtype ||= 'commit'; - if ($searchtype eq 'pickaxe') { - # pickaxe may take all resources of your box and run for several minutes - # with every query - so decide by yourself how public you make this feature - gitweb_check_feature('pickaxe') - or die_error(403, "Pickaxe is disabled"); - } - if ($searchtype eq 'grep') { - gitweb_check_feature('grep') - or die_error(403, "Grep is disabled"); - } - - git_header_html(); - - if ($searchtype eq 'commit' or $searchtype eq 'author' or $searchtype eq 'committer') { - my $greptype; - if ($searchtype eq 'commit') { - $greptype = "--grep="; - } elsif ($searchtype eq 'author') { - $greptype = "--author="; - } elsif ($searchtype eq 'committer') { - $greptype = "--committer="; - } - $greptype .= $searchtext; - my @commitlist = parse_commits($hash, 101, (100 * $page), undef, - $greptype, '--regexp-ignore-case', - $search_use_regexp ? '--extended-regexp' : '--fixed-strings'); - - my $paging_nav = ''; - if ($page > 0) { - $paging_nav .= - $cgi->a({-href => href(action=>"search", hash=>$hash, - searchtext=>$searchtext, - searchtype=>$searchtype)}, - "first"); - $paging_nav .= " ⋅ " . - $cgi->a({-href => href(-replay=>1, page=>$page-1), - -accesskey => "p", -title => "Alt-p"}, "prev"); - } else { - $paging_nav .= "first"; - $paging_nav .= " ⋅ prev"; - } - my $next_link = ''; - if ($#commitlist >= 100) { - $next_link = - $cgi->a({-href => href(-replay=>1, page=>$page+1), - -accesskey => "n", -title => "Alt-n"}, "next"); - $paging_nav .= " ⋅ $next_link"; - } else { - $paging_nav .= " ⋅ next"; - } - - if ($#commitlist >= 100) { - } - - git_print_page_nav('','', $hash,$co{'tree'},$hash, $paging_nav); - git_print_header_div('commit', esc_html($co{'title'}), $hash); - git_search_grep_body(\@commitlist, 0, 99, $next_link); - } - - if ($searchtype eq 'pickaxe') { - git_print_page_nav('','', $hash,$co{'tree'},$hash); - git_print_header_div('commit', esc_html($co{'title'}), $hash); - - print "\n"; - my $alternate = 1; - $/ = "\n"; - open my $fd, '-|', git_cmd(), '--no-pager', 'log', @diff_opts, - '--pretty=format:%H', '--no-abbrev', '--raw', "-S$searchtext", - ($search_use_regexp ? '--pickaxe-regex' : ()); - undef %co; - my @files; - while (my $line = <$fd>) { - chomp $line; - next unless $line; - - my %set = parse_difftree_raw_line($line); - if (defined $set{'commit'}) { - # finish previous commit - if (%co) { - print "\n" . - "\n" . - "\n"; - } - - if ($alternate) { - print "\n"; - } else { - print "\n"; - } - $alternate ^= 1; - %co = parse_commit($set{'commit'}); - my $author = chop_and_escape_str($co{'author_name'}, 15, 5); - print "\n" . - "\n" . - "\n" . - "\n" . - "\n"; - } - - print "
" . - $cgi->a({-href => href(action=>"commit", hash=>$co{'id'})}, "commit") . - " | " . - $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, hash_base=>$co{'id'})}, "tree"); - print "
$co{'age_string_date'}$author" . - $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), - -class => "list subject"}, - chop_and_escape_str($co{'title'}, 50) . "
"); - } elsif (defined $set{'to_id'}) { - next if ($set{'to_id'} =~ m/^0{40}$/); - - print $cgi->a({-href => href(action=>"blob", hash_base=>$co{'id'}, - hash=>$set{'to_id'}, file_name=>$set{'to_file'}), - -class => "list"}, - "" . esc_path($set{'file'}) . "") . - "
\n"; - } - } - close $fd; - - # finish last commit (warning: repetition!) - if (%co) { - print "
" . - $cgi->a({-href => href(action=>"commit", hash=>$co{'id'})}, "commit") . - " | " . - $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, hash_base=>$co{'id'})}, "tree"); - print "
\n"; - } - - if ($searchtype eq 'grep') { - git_print_page_nav('','', $hash,$co{'tree'},$hash); - git_print_header_div('commit', esc_html($co{'title'}), $hash); - - print "\n"; - my $alternate = 1; - my $matches = 0; - $/ = "\n"; - open my $fd, "-|", git_cmd(), 'grep', '-n', - $search_use_regexp ? ('-E', '-i') : '-F', - $searchtext, $co{'tree'}; - my $lastfile = ''; - while (my $line = <$fd>) { - chomp $line; - my ($file, $lno, $ltext, $binary); - last if ($matches++ > 1000); - if ($line =~ /^Binary file (.+) matches$/) { - $file = $1; - $binary = 1; - } else { - (undef, $file, $lno, $ltext) = split(/:/, $line, 4); - } - if ($file ne $lastfile) { - $lastfile and print "\n"; - if ($alternate++) { - print "\n"; - } else { - print "\n"; - } - print "\n"; - if ($matches > 1000) { - print "
Too many matches, listing trimmed
\n"; - } - } else { - print "
No matches found
\n"; - } - close $fd; - - print "
". - $cgi->a({-href => href(action=>"blob", hash=>$co{'hash'}, - file_name=>"$file"), - -class => "list"}, esc_path($file)); - print "\n"; - $lastfile = $file; - } - if ($binary) { - print "
Binary file
\n"; - } else { - $ltext = untabify($ltext); - if ($ltext =~ m/^(.*)($search_regexp)(.*)$/i) { - $ltext = esc_html($1, -nbsp=>1); - $ltext .= ''; - $ltext .= esc_html($2, -nbsp=>1); - $ltext .= ''; - $ltext .= esc_html($3, -nbsp=>1); - } else { - $ltext = esc_html($ltext, -nbsp=>1); - } - print "
" . - $cgi->a({-href => href(action=>"blob", hash=>$co{'hash'}, - file_name=>"$file").'#l'.$lno, - -class => "linenr"}, sprintf('%4i', $lno)) - . ' ' . $ltext . "
\n"; - } - } - if ($lastfile) { - print "
\n"; + if ($searchtype eq 'commit' || + $searchtype eq 'author' || + $searchtype eq 'committer') { + git_search_message(%co); + } elsif ($searchtype eq 'pickaxe') { + git_search_changes(%co); + } elsif ($searchtype eq 'grep') { + git_search_files(%co); + } else { + die_error(400, "Unknown search type"); } - git_footer_html(); } sub git_search_help { @@ -5811,13 +8144,13 @@ 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
The commit messages and authorship information will be scanned for the given pattern.
EOT - my ($have_grep) = gitweb_check_feature('grep'); + my $have_grep = gitweb_check_feature('grep'); if ($have_grep) { print <grep @@ -5834,7 +8167,7 @@ EOT
committer
Name and e-mail of the committer and date of commit will be scanned for the given pattern.
EOT - my ($have_pickaxe) = gitweb_check_feature('pickaxe'); + my $have_pickaxe = gitweb_check_feature('pickaxe'); if ($have_pickaxe) { print <pickaxe @@ -5849,36 +8182,8 @@ EOT } sub git_shortlog { - my $head = git_get_head_hash($project); - if (!defined $hash) { - $hash = $head; - } - if (!defined $page) { - $page = 0; - } - my $refs = git_get_references(); - - my $commit_hash = $hash; - if (defined $hash_parent) { - $commit_hash = "$hash_parent..$hash"; - } - my @commitlist = parse_commits($commit_hash, 101, (100 * $page)); - - my $paging_nav = format_paging_nav('shortlog', $hash, $head, $page, $#commitlist >= 100); - my $next_link = ''; - if ($#commitlist >= 100) { - $next_link = - $cgi->a({-href => href(-replay=>1, page=>$page+1), - -accesskey => "n", -title => "Alt-n"}, "next"); - } - - git_header_html(); - git_print_page_nav('shortlog','', $hash,$hash,$hash, $paging_nav); - git_print_header_div('summary', $project); - - git_shortlog_body(\@commitlist, 0, 99, $refs, $next_link); - - git_footer_html(); + git_log_generic('shortlog', \&git_shortlog_body, + $hash, $hash_parent); } ## ...................................................................... @@ -5886,7 +8191,7 @@ sub git_shortlog { sub git_feed { my $format = shift || 'atom'; - my ($have_blame) = gitweb_check_feature('blame'); + my $have_blame = gitweb_check_feature('blame'); # Atom: http://www.atomenabled.org/developers/syndication/ # RSS: http://www.notestips.com/80256B3A007F2692/1/NAMO5P9UPQ @@ -5908,16 +8213,15 @@ sub git_feed { } if (defined($commitlist[0])) { %latest_commit = %{$commitlist[0]}; - %latest_date = parse_date($latest_commit{'author_epoch'}); - print $cgi->header( - -type => $content_type, - -charset => 'utf-8', - -last_modified => $latest_date{'rfc2822'}); - } else { - print $cgi->header( - -type => $content_type, - -charset => 'utf-8'); + my $latest_epoch = $latest_commit{'committer_epoch'}; + exit_if_unmodified_since($latest_epoch); + %latest_date = parse_date($latest_epoch, $latest_commit{'committer_tz'}); } + print $cgi->header( + -type => $content_type, + -charset => 'utf-8', + %latest_date ? (-last_modified => $latest_date{'rfc2822'}) : (), + -status => '200 OK'); # Optimization: skip generating the body if client asks only # for Last-Modified date. @@ -5938,6 +8242,7 @@ sub git_feed { $feed_type = 'history'; } $title .= " $feed_type"; + $title = esc_html($title); my $descr = git_get_project_description($project); if (defined $descr) { $descr = esc_html($descr); @@ -5958,6 +8263,7 @@ sub git_feed { } else { $alt_url = href(-full=>1, action=>"summary"); } + $alt_url = esc_attr($alt_url); print qq!\n!; if ($format eq 'rss') { print <$title\n" . "$alt_url\n" . "$descr\n" . - "en\n"; + "en\n" . + # project owner is responsible for 'editorial' content + "$owner\n"; + if (defined $logo || defined $favicon) { + # prefer the logo to the favicon, since RSS + # doesn't allow both + my $img = esc_url($logo || $favicon); + print "\n" . + "$img\n" . + "$title\n" . + "$alt_url\n" . + "\n"; + } + if (%latest_date) { + print "$latest_date{'rfc2822'}\n"; + print "$latest_date{'rfc2822'}\n"; + } + print "gitweb v.$version/$git_version\n"; } elsif ($format eq 'atom') { print < @@ -5978,13 +8301,13 @@ XML $alt_url . '" />' . "\n" . '' . "\n" . - "" . href(-full=>1) . "\n" . + "" . esc_url(href(-full=>1)) . "\n" . # use project owner for feed author "$owner\n"; if (defined $favicon) { print "" . esc_url($favicon) . "\n"; } - if (defined $logo_url) { + if (defined $logo) { # not twice as wide as tall: 72 x 27 pixels print "" . esc_url($logo) . "\n"; } @@ -5994,6 +8317,7 @@ XML } else { print "$latest_date{'iso-8601'}\n"; } + print "gitweb\n"; } # contents @@ -6004,7 +8328,7 @@ XML if (($i >= 20) && ((time - $co{'author_epoch'}) > 48*60*60)) { last; } - my %cd = parse_date($co{'author_epoch'}); + my %cd = parse_date($co{'author_epoch'}, $co{'author_tz'}); # get list of changed files open my $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, @@ -6023,7 +8347,7 @@ XML "" . esc_html($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"; } @@ -6099,7 +8423,7 @@ XML # end of feed if ($format eq 'rss') { print "\n\n"; - } elsif ($format eq 'atom') { + } elsif ($format eq 'atom') { print "\n"; } } @@ -6113,14 +8437,28 @@ sub git_atom { } sub git_opml { - my @list = git_get_projects_list(); + my @list = git_get_projects_list($project_filter, $strict_export); + if (!@list) { + die_error(404, "No projects found"); + } + + print $cgi->header( + -type => 'text/xml', + -charset => 'utf-8', + -content_disposition => 'inline; filename="opml.xml"'); - print $cgi->header(-type => 'text/xml', -charset => 'utf-8'); + my $title = esc_html($site_name); + my $filter = " within subdirectory "; + if (defined $project_filter) { + $filter .= esc_html($project_filter); + } else { + $filter = ""; + } print < - $site_name OPML Export + $title OPML Export$filter @@ -6139,8 +8477,8 @@ XML } my $path = esc_html(chop_str($proj{'path'}, 25, 5)); - my $rss = "$my_url?p=$proj{'path'};a=rss"; - my $html = "$my_url?p=$proj{'path'};a=summary"; + 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 <