diff options
Diffstat (limited to 'gitweb/gitweb.perl')
| -rwxr-xr-x | gitweb/gitweb.perl | 6022 |
1 files changed, 4348 insertions, 1674 deletions
diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl index b2bae1b250..55e0e9ea38 100755 --- a/gitweb/gitweb.perl +++ b/gitweb/gitweb.perl @@ -7,25 +7,63 @@ # # This program is licensed under the GPLv2 +use 5.008; use strict; use warnings; 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); binmode STDOUT, ':utf8'; +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 = $cgi->url(-absolute => 1); + +our ($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 ($path_info) { + if ($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 # this can just be "git" if your webserver has a sensible PATH @@ -35,8 +73,9 @@ our $GIT = "++GIT_BINDIR++/git"; #our $projectroot = "/pub/scm"; our $projectroot = "++GITWEB_PROJECTROOT++"; -# target of the home link on top of all pages -our $home_link = $my_uri || "/"; +# fs traversing limit for getting project list +# the number is relative to the projectroot +our $project_maxdepth = "++GITWEB_PROJECT_MAXDEPTH++"; # string of the home link on top of all pages our $home_link_str = "++GITWEB_HOME_LINK_STR++"; @@ -46,6 +85,8 @@ our $home_link_str = "++GITWEB_HOME_LINK_STR++"; our $site_name = "++GITWEB_SITENAME++" || ($ENV{'SERVER_NAME'} || "Untitled") . " Git"; +# html snippet to include in the <head> 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 @@ -61,11 +102,13 @@ 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 @@ -74,6 +117,14 @@ 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"; @@ -82,6 +133,17 @@ 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++"; @@ -114,6 +176,16 @@ 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 => { @@ -122,14 +194,15 @@ 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', @@ -138,6 +211,14 @@ 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', @@ -150,6 +231,7 @@ 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, @@ -157,6 +239,44 @@ 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 c cpp rb java css php sh pl js tex bib xml awk bat ini spec tcl sql make), + # alternate extensions, see /etc/highlight/filetypes.conf + 'h' => 'c', + map { $_ => 'sh' } qw(bash zsh ksh), + map { $_ => 'cpp' } qw(cxx c++ cc), + map { $_ => 'php' } qw(php3 php4 php5 phps), + map { $_ => 'pl' } qw(perl pm), # perhaps also 'cgi' + map { $_ => 'make'} qw(mak mk), + map { $_ => 'xml' } qw(xhtml html htm), +); + # You define site-wide feature defaults here; override them with # $GITWEB_CONFIG as necessary. our %feature = ( @@ -170,9 +290,11 @@ 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(<feature>) to check if <feature> is enabled + # use gitweb_get_feature(<feature>) to retrieve the <feature> value + # (an array) or gitweb_check_feature(<feature>) to check if <feature> + # is enabled # Enable the 'blame' blob view, showing the last commit that modified # each line in the file. This can be very CPU-intensive. @@ -183,7 +305,7 @@ 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]}, @@ -207,6 +329,10 @@ 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]}, @@ -214,6 +340,7 @@ 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]; @@ -221,12 +348,14 @@ 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]; @@ -234,7 +363,20 @@ 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]}, @@ -271,33 +413,182 @@ our %feature = ( 'forks' => { 'override' => 0, 'default' => [0]}, + + # Insert custom links to the action bar of all project pages. + # This enables you mainly to link to third-party scripts integrating + # into gitweb; e.g. git-browser for graphical history representation + # or custom web-based repository administration interface. + + # The 'default' value consists of a list of triplets in the form + # (label, link, position) where position is the label after which + # to insert the link and link is a format string where %n expands + # to the project name, %f to the project path within the filesystem, + # %h to the current hash (h gitweb parameter) and %b to the current + # hash base (hb gitweb parameter); %% expands to %. + + # To enable system wide have in $GITWEB_CONFIG e.g. + # $feature{'actions'}{'default'} = [('graphiclog', + # '/git-browser/by-commit.html?r=%n', 'summary')]; + # Project specific override is not supported. + 'actions' => { + 'override' => 0, + 'default' => []}, + + # 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 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'} = [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. + + # Gravatar depends on Digest::MD5. + # Picon currently relies on the indiana.edu database. + + # To enable system wide have in $GITWEB_CONFIG + # $feature{'avatar'}{'default'} = ['<provider>']; + # where <provider> 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 = <provider>; + '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 + # $feature{'remote_heads'}{'override'} = 1; + # and in project config gitweb.remote_heads = 0|1; + 'remote_heads' => { + 'sub' => sub { feature_bool('remote_heads', @_) }, + 'override' => 0, + 'default' => [0]}, ); -sub gitweb_check_feature { +sub gitweb_get_feature { my ($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 $_[0]; } sub feature_snapshot { @@ -312,28 +603,20 @@ sub feature_snapshot { return @fmts; } -sub feature_grep { - my ($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'); - - if ($val eq 'true') { - return (1); - } elsif ($val eq 'false') { - return (0); - } +sub feature_avatar { + my @val = (git_get_project_config('avatar')); - return ($_[0]); + return @val ? @val : @_; } # checking HEAD file with -e is fragile if the repository was @@ -349,7 +632,8 @@ sub check_head_link { sub check_export_ok { my ($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 @@ -360,175 +644,139 @@ 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; } -our $GITWEB_CONFIG = $ENV{'GITWEB_CONFIG'} || "++GITWEB_CONFIG++"; -do $GITWEB_CONFIG if -e $GITWEB_CONFIG; - -# version of the core git binary -our $git_version = qx($GIT --version) =~ m/git version (.*)$/ ? $1 : "unknown"; - -$projects_list ||= $projectroot; - -# ====================================================================== -# input validation and dispatch -our $action = $cgi->param('a'); -if (defined $action) { - if ($action =~ m/[^0-9a-zA-Z\.\-_]/) { - die_error(undef, "Invalid action parameter"); +# 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; } -# parameters which are pathnames -our $project = $cgi->param('p'); -if (defined $project) { - if (!validate_pathname($project) || - !(-d "$projectroot/$project") || - !check_head_link("$projectroot/$project") || - ($export_ok && !(-e "$projectroot/$project/$export_ok")) || - ($strict_export && !project_in_list($project))) { - undef $project; - die_error(undef, "No such project"); - } -} +our ($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++"; + our $GITWEB_CONFIG_COMMON = $ENV{'GITWEB_CONFIG_COMMON'} || "++GITWEB_CONFIG_COMMON++"; -our $file_name = $cgi->param('f'); -if (defined $file_name) { - if (!validate_pathname($file_name)) { - die_error(undef, "Invalid file parameter"); - } -} + # Protect agains 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); -our $file_parent = $cgi->param('fp'); -if (defined $file_parent) { - if (!validate_pathname($file_parent)) { - die_error(undef, "Invalid file parent parameter"); - } -} + # Common system-wide settings for convenience. + # Those settings can be ovverriden by GITWEB_CONFIG or GITWEB_CONFIG_SYSTEM. + read_config_file($GITWEB_CONFIG_COMMON); -# parameters which are refnames -our $hash = $cgi->param('h'); -if (defined $hash) { - if (!validate_refname($hash)) { - die_error(undef, "Invalid hash parameter"); - } + # 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); } -our $hash_parent = $cgi->param('hp'); -if (defined $hash_parent) { - if (!validate_refname($hash_parent)) { - die_error(undef, "Invalid hash parent parameter"); - } -} +# 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; -our $hash_base = $cgi->param('hb'); -if (defined $hash_base) { - if (!validate_refname($hash_base)) { - die_error(undef, "Invalid hash base parameter"); + # 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; } -} - -my %allowed_options = ( - "--no-merges" => [ qw(rss atom log shortlog history) ], -); + # additional checks for load average should go here for things that don't export + # /proc/loadavg -our @extra_options = $cgi->param('opt'); -if (defined @extra_options) { - foreach my $opt (@extra_options) { - if (not exists $allowed_options{$opt}) { - die_error(undef, "Invalid option parameter"); - } - if (not grep(/^$action$/, @{$allowed_options{$opt}})) { - die_error(undef, "Invalid option parameter for this action"); - } - } + return 0; } -our $hash_parent_base = $cgi->param('hpb'); -if (defined $hash_parent_base) { - if (!validate_refname($hash_parent_base)) { - die_error(undef, "Invalid hash parent base parameter"); - } +# version of the core git binary +our $git_version; +sub evaluate_git_version { + our $git_version = qx("$GIT" --version) =~ m/git version (.*)$/ ? $1 : "unknown"; + $number_of_git_cmds++; } -# other parameters -our $page = $cgi->param('pg'); -if (defined $page) { - if ($page =~ m/[^0-9]/) { - die_error(undef, "Invalid page parameter"); +sub check_loadavg { + if (defined $maxload && get_loadavg() > $maxload) { + die_error(503, "The load average on the server is too high"); } } -our $searchtype = $cgi->param('st'); -if (defined $searchtype) { - if ($searchtype =~ m/[^a-z]/) { - die_error(undef, "Invalid searchtype parameter"); - } -} +# ====================================================================== +# input validation and dispatch -our $searchtext = $cgi->param('s'); -our $search_regexp; -if (defined $searchtext) { - if (length($searchtext) < 2) { - die_error(undef, "At least two characters are required for search parameter"); - } - $search_regexp = quotemeta $searchtext; -} +# 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 -# now read PATH_INFO and use it as alternative to parameters -sub evaluate_path_info { - return if defined $project; - my $path_info = $ENV{"PATH_INFO"}; - return if !$path_info; - $path_info =~ s,^/+,,; - return if !$path_info; - # find which part of PATH_INFO is project - $project = $path_info; - $project =~ s,/+$,,; - while ($project && !check_head_link("$projectroot/$project")) { - $project =~ s,/*[^/]*$,,; - } - # validate project - $project = validate_pathname($project); - if (!$project || - ($export_ok && !-e "$projectroot/$project/$export_ok") || - ($strict_export && !project_in_list($project))) { - undef $project; - return; - } - # do not change any parameters if an action is given using the query string - return if $action; - $path_info =~ s,^$project/*,,; - my ($refname, $pathname) = split(/:/, $path_info, 2); - if (defined $pathname) { - # we got "project.git/branch:filename" or "project.git/branch:dir/" - # we could use git_get_type(branch:pathname), but it needs $git_dir - $pathname =~ s,^/+,,; - if (!$pathname || substr($pathname, -1) eq "/") { - $action ||= "tree"; - $pathname =~ s,/$,,; - } else { - $action ||= "blob_plain"; - } - $hash_base ||= validate_refname($refname); - $file_name ||= validate_pathname($pathname); - } elsif (defined $refname) { - # we got "project.git/branch" - $action ||= "shortlog"; - $hash ||= validate_refname($refname); - } -} -evaluate_path_info(); +our %input_params = (); -# path to the current git repository -our $git_dir; -$git_dir = "$projectroot/$project" if $project; +# 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 +# equivalent, and since the href() usage is the most frequent one, we store +# the name -> CGI key mapping here, instead of the reverse. +# +# XXX: Warning: If you touch this, check the search form for updating, +# too. + +our @cgi_param_mapping = ( + project => "p", + action => "a", + file_name => "f", + file_parent => "fp", + hash => "h", + hash_parent => "hp", + hash_base => "hb", + hash_parent_base => "hpb", + page => "pg", + order => "o", + searchtext => "s", + searchtype => "st", + 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" +); +our %cgi_param_mapping = @cgi_param_mapping; -# dispatch -my %actions = ( - "blame" => \&git_blame2, +# we will also need to know the possible actions, for validation +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, @@ -540,6 +788,9 @@ 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, @@ -557,74 +808,583 @@ my %actions = ( "project_index" => \&git_project_index, ); -if (!defined $action) { +# finally, we have the hash of allowed extra_options for the commands that +# allow them +our %allowed_options = ( + "--no-merges" => [ qw(rss atom log shortlog history) ], +); + +# fill %input_params with the CGI parameters. All values except for 'opt' +# 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 +sub evaluate_query_params { + our $cgi; + + while (my ($name, $symbol) = each %cgi_param_mapping) { + if ($symbol eq 'opt') { + $input_params{$name} = [ map { decode_utf8($_) } $cgi->param($symbol) ]; + } else { + $input_params{$name} = decode_utf8($cgi->param($symbol)); + } + } +} + +# now read PATH_INFO and update the parameter list for missing parameters +sub evaluate_path_info { + return if defined $input_params{'project'}; + return if !$path_info; + $path_info =~ s,^/+,,; + return if !$path_info; + + # find which part of PATH_INFO is project + my $project = $path_info; + $project =~ s,/+$,,; + while ($project && !check_head_link("$projectroot/$project")) { + $project =~ s,/*[^/]*$,,; + } + return unless $project; + $input_params{'project'} = $project; + + # do not change any parameters if an action is given using the query string + return if $input_params{'action'}; + $path_info =~ s,^\Q$project\E/*,,; + + # next, check if we have an action + my $action = $path_info; + $action =~ s,/.*$,,; + if (exists $actions{$action}) { + $path_info =~ s,^$action/*,,; + $input_params{'action'} = $action; + } + + # list of actions that want hash_base instead of hash, but can have no + # pathname (f) parameter + my @wants_base = ( + 'tree', + 'history', + ); + + # we want to catch, among others + # [$hash_parent_base[:$file_parent]..]$hash_parent[:$file_name] + my ($parentrefname, $parentpathname, $refname, $pathname) = + ($path_info =~ /^(?:(.+?)(?::(.+))?\.\.)?([^:]+?)?(?::(.+))?$/); + + # first, analyze the 'current' part + if (defined $pathname) { + # we got "branch:filename" or "branch:dir/" + # we could use git_get_type(branch:pathname), but: + # - it needs $git_dir + # - it does a git() call + # - the convention of terminating directories with a slash + # makes it superfluous + # - embedding the action in the PATH_INFO would make it even + # more superfluous + $pathname =~ s,^/+,,; + if (!$pathname || substr($pathname, -1) eq "/") { + $input_params{'action'} ||= "tree"; + $pathname =~ s,/$,,; + } else { + # the default action depends on whether we had parent info + # or not + if ($parentrefname) { + $input_params{'action'} ||= "blobdiff_plain"; + } else { + $input_params{'action'} ||= "blob_plain"; + } + } + $input_params{'hash_base'} ||= $refname; + $input_params{'file_name'} ||= $pathname; + } elsif (defined $refname) { + # we got "branch". In this case we have to choose if we have to + # set hash or hash_base. + # + # Most of the actions without a pathname only want hash to be + # set, except for the ones specified in @wants_base that want + # 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. + 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; + } + } + + # next, handle the 'parent' part, if present + if (defined $parentrefname) { + # a missing pathspec defaults to the 'current' filename, allowing e.g. + # someproject/blobdiff/oldrev..newrev:/filename + if ($parentpathname) { + $parentpathname =~ s,^/+,,; + $parentpathname =~ s,/$,,; + $input_params{'file_parent'} ||= $parentpathname; + } else { + $input_params{'file_parent'} ||= $input_params{'file_name'}; + } + # we assume that hash_parent_base is wanted if a path was specified, + # or if the action wants hash_base instead of hash + if (defined $input_params{'file_parent'} || + grep { $_ eq $input_params{'action'} } @wants_base) { + $input_params{'hash_parent_base'} ||= $parentrefname; + } else { + $input_params{'hash_parent'} ||= $parentrefname; + } + } + + # for the snapshot action, we allow URLs in the form + # $project/snapshot/$hash.ext + # where .ext determines the snapshot and gets removed from the + # passed $refname to provide the $hash. + # + # To be able to tell that $refname includes the format extension, we + # require the following two conditions to be satisfied: + # - the hash input parameter MUST have been set from the $refname part + # of the URL (i.e. they must be equal) + # - the snapshot format MUST NOT have been defined already (e.g. from + # CGI parameter sf) + # It's also useless to try any matching unless $refname has a dot, + # so we check for that too + if (defined $input_params{'action'} && + $input_params{'action'} eq 'snapshot' && + defined $refname && index($refname, '.') != -1 && + $refname eq $input_params{'hash'} && + !defined $input_params{'snapshot_format'}) { + # We loop over the known snapshot formats, checking for + # extensions. Allowed extensions are both the defined suffix + # (which includes the initial dot already) and the snapshot + # format key itself, with a prepended dot + while (my ($fmt, $opt) = each %known_snapshot_formats) { + my $hash = $refname; + unless ($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; + $input_params{'hash'} = $hash; + # we also set the format suffix to the one requested + # in the URL: this way a request for e.g. .tgz returns + # a .tgz instead of a .tar.gz + $known_snapshot_formats{$fmt}{'suffix'} = $sfx; + last; + } + } +} + +our ($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 $action) { + if (!validate_action($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"); + } + } + + our $project_filter = $input_params{'project_filter'}; + if (defined $project_filter) { + if (!validate_pathname($project_filter)) { + die_error(404, "Invalid project_filter parameter"); + } + } + + our $file_name = $input_params{'file_name'}; + if (defined $file_name) { + if (!validate_pathname($file_name)) { + die_error(400, "Invalid file parameter"); + } + } + + our $file_parent = $input_params{'file_parent'}; + if (defined $file_parent) { + if (!validate_pathname($file_parent)) { + die_error(400, "Invalid file parent parameter"); + } + } + + # parameters which are refnames + our $hash = $input_params{'hash'}; 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) { - $action = 'summary'; + if (!validate_refname($hash)) { + die_error(400, "Invalid hash parameter"); + } + } + + our $hash_parent = $input_params{'hash_parent'}; + if (defined $hash_parent) { + if (!validate_refname($hash_parent)) { + die_error(400, "Invalid hash parent parameter"); + } + } + + our $hash_base = $input_params{'hash_base'}; + if (defined $hash_base) { + if (!validate_refname($hash_base)) { + die_error(400, "Invalid hash base 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"); + } + 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"); + } + } + + # 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 $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"); + } + 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; + } + } +} + +# path to the current git repository +our $git_dir; +sub evaluate_git_dir { + our $git_dir = "$projectroot/$project" if $project; +} + +our (@snapshot_fmts, $git_avatar); +sub configure_gitweb_features { + # list of supported snapshot formats + our @snapshot_fmts = gitweb_get_feature('snapshot'); + @snapshot_fmts = filter_snapshot_fmts(@snapshot_fmts); + + # check that the avatar feature is set to a known provider name, + # and for each provider check if the dependencies are satisfied. + # if the provider name is invalid or the dependencies are not met, + # reset $git_avatar to the empty string. + our ($git_avatar) = gitweb_get_feature('avatar'); + if ($git_avatar eq 'gravatar') { + $git_avatar = '' unless (eval { require Digest::MD5; 1; }); + } elsif ($git_avatar eq 'picon') { + # no dependencies } else { - $action = 'project_list'; + $git_avatar = ''; } } -if (!defined($actions{$action})) { - die_error(undef, "Unknown action"); + +# custom error handler: 'die <message>' is Internal Server Error +sub handle_errors_html { + my $msg = shift; # it is already HTML escaped + + # to avoid infinite loop where error occurs in die_error, + # change handler to default handler, disabling handle_errors_html + set_message("Error occured when inside die_error:\n$msg"); + + # you cannot jump out of die_error when called as error handler; + # the subroutine set via CGI::Carp::set_message is called _after_ + # 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 +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}->(); } -if ($action !~ m/^(opml|project_list|project_index)$/ && - !$project) { - die_error(undef, "Project needed"); + +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; +sub configure_as_fcgi { + require CGI::Fast; + our $CGI = 'CGI::Fast'; + + 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() }; + }, + ); +} + +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; +} + +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; - # XXX: Warning: If you touch this, check the search form for updating, - # too. - - my @mapping = ( - project => "p", - action => "a", - file_name => "f", - file_parent => "fp", - hash => "h", - hash_parent => "hp", - hash_base => "hb", - hash_parent_base => "hpb", - page => "pg", - order => "o", - searchtext => "s", - searchtype => "st", - snapshot_format => "sf", - extra_options => "opt", - ); - my %mapping = @mapping; + # implicit -replay, must be first of implicit params + $params{-replay} = 1 if (keys %params == 1 && $params{-anchor}); $params{'project'} = $project unless exists $params{'project'}; - my ($use_pathinfo) = gitweb_check_feature('pathinfo'); - if ($use_pathinfo) { - # use PATH_INFO for project name - $href .= "/$params{'project'}" if defined $params{'project'}; + if ($params{-replay}) { + while (my ($name, $symbol) = each %cgi_param_mapping) { + if (!exists $params{$name}) { + $params{$name} = $input_params{$name}; + } + } + } + + 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/ + # Thus, we strip any trailing / from $href, to spare us double + # slashes in the final URL + $href =~ s,/$,,; + + # Then add the project name, if present + $href .= "/".esc_path_info($params{'project'}); delete $params{'project'}; - # Summary just uses the project path URL - if (defined $params{'action'} && $params{'action'} eq 'summary') { + # 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'}) { + $href .= "/".esc_path_info($params{'action'}) + unless $params{'action'} eq 'summary'; delete $params{'action'}; } + + # Next, we put hash_parent_base:/file_parent..hash_base:/file_name, + # stripping nonexistent or useless pieces + $href .= "/" if ($params{'hash_base'} || $params{'hash_parent_base'} + || $params{'hash_parent'} || $params{'hash'}); + if (defined $params{'hash_base'}) { + if (defined $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 + 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'}) { + $href .= esc_path_info($params{'hash_parent'}). ".."; + delete $params{'hash_parent'}; + } + + $href .= esc_path_info($params{'hash_base'}); + if (defined $params{'file_name'} && $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'}) { + $href .= esc_path_info($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 my @result = (); - for (my $i = 0; $i < @mapping; $i += 2) { - my ($name, $symbol) = ($mapping[$i], $mapping[$i+1]); + for (my $i = 0; $i < @cgi_param_mapping; $i += 2) { + my ($name, $symbol) = ($cgi_param_mapping[$i], $cgi_param_mapping[$i+1]); if (defined $params{$name}) { if (ref($params{$name}) eq "ARRAY") { foreach my $par (@{$params{$name}}) { @@ -637,6 +1397,13 @@ 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; } @@ -644,6 +1411,24 @@ sub href(%) { ## ====================================================================== ## validation, quoting/unquoting and escaping +sub validate_action { + my $input = shift || return undef; + return undef unless exists $actions{$input}; + return $input; +} + +sub validate_project { + my $input = shift || return undef; + if (!validate_pathname($input) || + !(-d "$projectroot/$input") || + !check_export_ok("$projectroot/$input") || + ($strict_export && !project_in_list($input))) { + return undef; + } else { + return $input; + } +} + sub validate_pathname { my $input = shift || return undef; @@ -682,10 +1467,10 @@ sub validate_refname { # in utf-8 thanks to "binmode STDOUT, ':utf8'" at beginning sub to_utf8 { my $str = shift; - my $res; - eval { $res = decode_utf8($str, Encode::FB_CROAK); }; - if (defined $res) { - return $res; + return undef unless defined $str; + + if (utf8::is_utf8($str) || utf8::decode($str)) { + return $str; } else { return decode($fallback_encoding, $str, Encode::FB_DEFAULT); } @@ -695,26 +1480,46 @@ 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'}) { @@ -729,6 +1534,8 @@ sub esc_path { my $str = shift; my %opts = @_; + return undef unless defined $str; + $str = to_utf8($str); $str = $cgi->escapeHTML($str); if ($opts{'-nbsp'}) { @@ -738,32 +1545,54 @@ sub esc_path { return $str; } +# Sanitize for use in XHTML + application/xml+xhtm (valid XML 1.0) +sub sanitize { + my $str = shift; + + return undef unless defined $str; + + $str = to_utf8($str); + $str =~ s|([[:cntrl:]])|($1 =~ /[\t\n\r]/ ? $1 : quot_cec($1))|eg; + 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', # 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) + ); my $chr = ( (exists $es{$cntrl}) ? $es{$cntrl} - : sprintf('\%03o', ord($cntrl)) ); - return "<span class=\"cntrl\">$chr</span>"; + : sprintf('\%2x', ord($cntrl)) ); + if ($opts{-nohtml}) { + return $chr; + } else { + return "<span class=\"cntrl\">$chr</span>"; + } } # Alternatively use unicode control pictures codepoints, # Unicode "printable representation" (PR) sub quot_upr { my $cntrl = shift; + my %opts = @_; + my $chr = sprintf('&#%04d;', 0x2400+ord($cntrl)); - return "<span class=\"cntrl\">$chr</span>"; + if ($opts{-nohtml}) { + return $chr; + } else { + return "<span class=\"cntrl\">$chr</span>"; + } } # git may return quoted and escaped filenames @@ -788,7 +1617,7 @@ sub unquote { return chr(oct($seq)); } elsif (exists $es{$seq}) { # C escape sequence, aka character escape code - return $es{$seq} + return $es{$seq}; } # quoted ordinary character return $seq; @@ -825,21 +1654,171 @@ sub project_in_list { ## ---------------------------------------------------------------------- ## HTML aware string manipulation +# Try to chop given string on a word boundary between position +# $len and $len+$add_len. If there is no word boundary there, +# chop at $len+$add_len. Do not chop if chopped part plus ellipsis +# (marking chopped part) would be longer than given string. sub chop_str { my $str = shift; my $len = shift; my $add_len = shift || 10; + my $where = shift || 'right'; # 'left' | 'center' | 'right' + + # Make sure perl knows it is utf8 encoded so we don't + # cut in the middle of a utf8 multibyte char. + $str = to_utf8($str); # allow only $len chars, but don't cut a word if it would fit in $add_len # if it doesn't fit, cut it if it's still longer than the dots we would add - $str =~ m/^(.{0,$len}[^ \/\-_:\.@]{0,$add_len})(.*)/; - my $body = $1; - my $tail = $2; - if (length($tail) > 4) { - $tail = " ..."; - $body =~ s/&[^;]*$//; # remove chopped character entities + # remove chopped character entities entirely + + # when chopping in the middle, distribute $len into left and right part + # return early if chopping wouldn't make string shorter + if ($where eq 'center') { + return $str if ($len + 5 >= length($str)); # filler is length 5 + $len = int($len/2); + } else { + return $str if ($len + 4 >= length($str)); # filler is length 4 + } + + # regexps: ending and beginning with word part up to $add_len + my $endre = qr/.{$len}\w{0,$add_len}/; + my $begre = qr/\w{0,$add_len}.{$len}/; + + if ($where eq 'left') { + $str =~ m/^(.*?)($begre)$/; + my ($lead, $body) = ($1, $2); + if (length($lead) > 4) { + $lead = " ..."; + } + return "$lead$body"; + + } elsif ($where eq 'center') { + $str =~ m/^($endre)(.*)$/; + my ($left, $str) = ($1, $2); + $str =~ m/^(.*?)($begre)$/; + my ($mid, $right) = ($1, $2); + if (length($mid) > 5) { + $mid = " ... "; + } + return "$left$mid$right"; + + } else { + $str =~ m/^($endre)(.*)$/; + my $body = $1; + my $tail = $2; + if (length($tail) > 4) { + $tail = "... "; + } + return "$body$tail"; } - return "$body$tail"; +} + +# takes the same arguments as chop_str, but also wraps a <span> around the +# result with a title attribute if it does get chopped. Additionally, the +# string is HTML-escaped. +sub chop_and_escape_str { + my ($str) = @_; + + my $chopped = chop_str(@_); + $str = to_utf8($str); + if ($chopped eq $str) { + return esc_html($chopped); + } else { + $str =~ s/[[:cntrl:]]/?/g; + return $cgi->span({-title=>$str}, esc_html($chopped)); + } +} + +# Highlight selected fragments of string, using given CSS class, +# and escape HTML. It is assumed that fragments do not overlap. +# Regions are passed as list of pairs (array references). +# +# Example: esc_html_hl_regions("foobar", "mark", [ 0, 3 ]) returns +# '<span class="mark">foo</span>bar' +sub esc_html_hl_regions { + my ($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 <span> 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 . $tail, 'match', @filtered); } ## ---------------------------------------------------------------------- @@ -898,7 +1877,7 @@ use constant { }; # submodule/subproject, a commit object reference -sub S_ISGITLINK($) { +sub S_ISGITLINK { my $mode = shift; return (($mode & S_IFMT) == S_IFGITLINK) @@ -986,24 +1965,32 @@ sub format_log_line_html { my $line = shift; $line = esc_html($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([0-9a-fA-F]{8,40})\b}{ + $cgi->a({-href => href(action=>"object", hash=>$1), + -class => "text"}, $1); + }eg; + return $line; } # format marker of refs pointing to given object + +# the destination action is chosen based on object type and current context: +# - for annotated tags, we choose the tag view unless it's the current view +# already, in which case we go to shortlog view +# - for other refs, we keep the current view if we're in history, shortlog or +# log view, and select shortlog otherwise sub format_ref_marker { my ($refs, $id) = @_; my $markers = ''; if (defined $refs->{$id}) { foreach my $ref (@{$refs->{$id}}) { + # this code exploits the fact that non-lightweight tags are the + # only indirect objects, and that they are the only objects for which + # we want to use tag instead of shortlog as action my ($type, $name) = qw(); + my $indirect = ($ref =~ s/\^\{\}$//); # e.g. tags/v2.6.11 or heads/next if ($ref =~ m!^(.*?)s?/(.*)$!) { $type = $1; @@ -1013,8 +2000,29 @@ sub format_ref_marker { $name = $ref; } - $markers .= " <span class=\"$type\" title=\"$ref\">" . - esc_html($name) . "</span>"; + my $class = $type; + $class .= " indirect" if $indirect; + + my $dest_action = "shortlog"; + + if ($indirect) { + $dest_action = "tag" unless $action eq "tag"; + } elsif ($action =~ /^(history|(short)?log)$/) { + $dest_action = $action; + } + + my $dest = ""; + $dest .= "refs/" unless $ref =~ m!^refs/!; + $dest .= $ref; + + my $link = $cgi->a({ + -href => href( + action=>$dest_action, + hash=>$dest + )}, $name); + + $markers .= " <span class=\"".esc_attr($class)."\" title=\"".esc_attr($ref)."\">" . + $link . "</span>"; } } @@ -1031,15 +2039,117 @@ 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} = + "http://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} ||= + "http://www.gravatar.com/avatar/" . + Digest::MD5::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 $pre_white . + "<img width=\"$size\" " . + "class=\"avatar\" " . + "src=\"".esc_url($url)."\" " . + "alt=\"\" " . + "/>" . $post_white; + } else { + return ""; + } +} + +sub format_search_author { + my ($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) . + $author) . + "</$tag>"; +} + # format git diff header line, i.e. "diff --(git|combined|cc) ..." sub format_git_diff_header_line { my $line = shift; @@ -1233,101 +2343,131 @@ 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 = "<span class=\"chunk_info\">@@ $from_text $to_text @@</span>" . - "<span class=\"section\">" . esc_html($section, -nbsp=>1) . "</span>"; - return "<div class=\"diff$diff_class\">$line</div>\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) = + $line =~ m/^\@{2} (-(\d+)(?:,(\d+))?) (\+(\d+)(?:,(\d+))?) \@{2}(.*)$/; - $line = "<span class=\"chunk_info\">$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 = "<span class=\"chunk_info\">@@ $from_text $to_text @@</span>" . + "<span class=\"section\">" . esc_html($section, -nbsp=>1) . "</span>"; + 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; + + $line = "<span class=\"chunk_info\">$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 .= " $prefix</span>" . + "<span class=\"section\">" . esc_html($section, -nbsp=>1) . "</span>"; + 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 .= " $prefix</span>" . - "<span class=\"section\">" . esc_html($section, -nbsp=>1) . "</span>"; - return "<div class=\"diff$diff_class\">$line</div>\n"; } - return "<div class=\"diff$diff_class\">" . esc_html($line, -nbsp=>1) . "</div>\n"; + + my $diff_classes = "diff"; + $diff_classes .= " $diff_class" if ($diff_class); + $line = "<div class=\"$diff_classes\">$line</div>\n"; + + return $line; } # Generates undef or something like "_snapshot_" or "snapshot (_tbz2_ _zip_)", # linked. Pass the hash of the tree/commit to snapshot. sub format_snapshot_links { my ($hash) = @_; - my @snapshot_fmts = gitweb_check_feature('snapshot'); - @snapshot_fmts = filter_snapshot_fmts(@snapshot_fmts); my $num_fmts = @snapshot_fmts; if ($num_fmts > 1) { # A parenthesized list of links bearing format names. @@ -1359,31 +2499,87 @@ sub format_snapshot_links { } } +## ...................................................................... +## functions returning values to be passed, perhaps after some +## transformation, to other functions; e.g. returning arguments to href() + +# returns hash to be passed to href to generate gitweb URL +# in -title key it returns description of link +sub get_feed_info { + my $format = shift || 'Atom'; + my %res = (action => lc($format)); + + # 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 || $action =~ /^(?:tags|heads|forks|tag|search)$/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; + } + # find log type for feed description (title) + my $type = 'log'; + if (defined $file_name) { + $type = "history of $file_name"; + $type .= "/" if ($action eq 'tree'); + $type .= " on '$branch'" if (defined $branch); + } else { + $type = "log of $branch" if (defined $branch); + } + + $res{-title} = $type; + $res{'hash'} = (defined $branch ? "refs/heads/$branch" : undef); + $res{'file_name'} = $file_name; + + return %res; +} + ## ---------------------------------------------------------------------- ## git utility subroutines, invoking git commands # 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; } -# returns path to the core git executable and the --git-dir parameter as string -sub git_cmd_str { - return join(' ', git_cmd()); +# quote the given arguments for passing them to the shell +# quote_command("command", "arg 1", "arg with ' and ! characters") +# => "'command' 'arg 1' 'arg with '\'' and '\!' characters'" +# Try to avoid using this function wherever possible. +sub quote_command { + return join(' ', + 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; @@ -1402,20 +2598,134 @@ sub git_get_type { return $type; } +# repository configuration +our $config_file = ''; +our %config; + +# store multiple values for single key as anonymous array reference +# single values stored directly in the hash, not as [ <value> ] +sub hash_set_multi { + my ($hash, $key, $value) = @_; + + if (!exists $hash->{$key}) { + $hash->{$key} = $value; + } elsif (!ref $hash->{$key}) { + $hash->{$key} = [ $hash->{$key}, $value ]; + } else { + push @{$hash->{$key}}, $value; + } +} + +# return hash of git project configuration +# optionally limited to some section, e.g. 'gitweb' +sub git_parse_project_config { + my $section_regexp = shift; + my %config; + + local $/ = "\0"; + + open my $fh, "-|", git_cmd(), "config", '-z', '-l', + or return; + + while (my $keyval = <$fh>) { + chomp $keyval; + my ($key, $value) = split(/\n/, $keyval, 2); + + hash_set_multi(\%config, $key, $value) + if (!defined $section_regexp || $key =~ /^(?:$section_regexp)\./o); + } + close $fh; + + return %config; +} + +# 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 (($val =~ /^\d+$/ && $val) || # section.key = 1 + ($val =~ /^(?:true|yes)$/i)); # section.key = true +} + +# convert config value to simple decimal number +# an optional value suffix of 'k', 'm', or 'g' will cause the value +# to be multiplied by 1024, 1048576, or 1073741824 +sub config_to_int { + my $val = shift; + + # strip leading and trailing whitespace + $val =~ s/^\s+//; + $val =~ s/\s+$//; + + if (my ($num, $unit) = ($val =~ /^([0-9]*)([kmg])$/i)) { + $unit = lc($unit); + # unknown unit is treated as 1 + return $num * ($unit eq 'g' ? 1073741824 : + $unit eq 'm' ? 1048576 : + $unit eq 'k' ? 1024 : 1); + } + return $val; +} + +# convert config value to array reference, if needed +sub config_to_multi { + my $val = shift; + + return ref($val) ? $val : (defined($val) ? [ $val ] : []); +} + sub git_get_project_config { my ($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 =~ /^([^.]*)\.(.*)\.([^.]*)$/)) { + $key = join(".", lc($hi), $mi, lc($lo)); + } else { + $key = lc($key); + } $key =~ s/^gitweb\.//; return if ($key =~ m/\W/); - my @x = (git_cmd(), 'config'); - if (defined $type) { push @x, $type; } - push @x, "--get"; - push @x, "gitweb.$key"; - my $val = qx(@x); - chomp $val; - return ($val); + # type sanity check + if (defined $type) { + $type =~ s/^--//; + $type = undef + unless ($type eq 'bool' || $type eq 'int'); + } + + # get config + if (!defined $config_file || + $config_file ne "$git_dir/config") { + %config = git_parse_project_config('gitweb'); + $config_file = "$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"}; + } elsif ($type eq 'bool') { + # backward compatibility: 'git config --bool' returns true/false + return config_to_bool($config{"gitweb.$key"}) ? 'true' : 'false'; + } elsif ($type eq 'int') { + return config_to_int($config{"gitweb.$key"}); + } + return $config{"gitweb.$key"}; } # get hash of given path at given ref @@ -1427,7 +2737,7 @@ sub git_get_hash_by_path { $path =~ s,/+$,,; open my $fd, "-|", git_cmd(), "ls-tree", $base, "--", $path - or die_error(undef, "Open git-ls-tree failed"); + or die_error(500, "Open git-ls-tree failed"); my $line = <$fd>; close $fd or return undef; @@ -1472,22 +2782,165 @@ sub git_get_path_by_hash { ## ...................................................................... ## git utility functions, directly accessing git repository +# get the value of config variable either from file named as the variable +# itself in the repository ($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/$name" + or return git_get_project_config($name); + my $conf = <$fd>; + close $fd; + if (defined $conf) { + chomp $conf; + } + return $conf; +} + sub git_get_project_description { my $path = shift; + return git_get_file_or_project_config($path, 'description'); +} - open my $fd, "$projectroot/$path/description" or return undef; - my $descr = <$fd>; - close $fd; - if (defined $descr) { - chomp $descr; +sub git_get_project_category { + my $path = shift; + return git_get_file_or_project_config($path, 'category'); +} + + +# supported formats: +# * $GIT_DIR/ctags/<tagname> 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/$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}++; + } + } + + 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}; + } + } + + return $ctags; +} + +sub git_populate_project_tagcloud { + my $ctags = shift; + + # First, merge different-cased tags; tags vote on casing + my %ctags_lc; + foreach (keys %$ctags) { + $ctags_lc{lc $_}->{count} += $ctags->{$_}; + if (not $ctags_lc{lc $_}->{topcount} + or $ctags_lc{lc $_}->{topcount} < $ctags->{$_}) { + $ctags_lc{lc $_}->{topcount} = $ctags->{$_}; + $ctags_lc{lc $_}->{topname} = $_; + } + } + + my $cloud; + my $matched = $input_params{'ctag'}; + if (eval { require HTML::TagCloud; 1; }) { + $cloud = HTML::TagCloud->new; + foreach my $ctag (sort keys %ctags_lc) { + # Pad the title with spaces so that the cloud looks + # less crammed. + my $title = esc_html($ctags_lc{$ctag}->{topname}); + $title =~ s/ / /g; + $title =~ s/^/ /g; + $title =~ s/$/ /g; + if (defined $matched && $matched eq $ctag) { + $title = qq(<span class="match">$title</span>); + } + $cloud->add($title, href(project=>undef, ctag=>$ctag), + $ctags_lc{$ctag}->{count}); + } + } else { + $cloud = {}; + foreach my $ctag (keys %ctags_lc) { + my $title = esc_html($ctags_lc{$ctag}->{topname}, -nbsp=>1); + if (defined $matched && $matched eq $ctag) { + $title = qq(<span class="match">$title</span>); + } + $cloud->{$ctag}{count} = $ctags_lc{$ctag}->{count}; + $cloud->{$ctag}{ctag} = + $cgi->a({-href=>href(project=>undef, ctag=>$ctag)}, $title); + } + } + return $cloud; +} + +sub git_show_project_tagcloud { + my ($cloud, $count) = @_; + if (ref $cloud eq 'HTML::TagCloud') { + return $cloud->html_and_css($count); + } else { + my @tags = sort { $cloud->{$a}->{'count'} <=> $cloud->{$b}->{'count'} } keys %$cloud; + return + '<div id="htmltagcloud"'.($project ? '' : ' align="center"').'>' . + join (', ', map { + $cloud->{$_}->{'ctag'} + } splice(@tags, 0, $count)) . + '</div>'; } - return $descr; } sub git_get_project_url_list { my $path = shift; - open my $fd, "$projectroot/$path/cloneurl" or return; + $git_dir = "$projectroot/$path"; + 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')); my @git_project_url_list = map { chomp; $_ } <$fd>; close $fd; @@ -1495,37 +2948,50 @@ sub git_get_project_url_list { } sub git_get_projects_list { - my ($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 $_); + # 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_forks and $subdir =~ m#/.#) { - $File::Find::prune = 1; - } elsif (check_export_ok("$projectroot/$filter/$subdir")) { - push @list, { path => ($filter ? "$filter/" : '') . $subdir }; + if (check_export_ok("$projectroot/$path")) { + push @list, { path => $path }; $File::Find::prune = 1; } }, @@ -1536,8 +3002,7 @@ sub git_get_projects_list { # 'git%2Fgit.git Linus+Torvalds' # 'libs%2Fklibc%2Fklibc.git H.+Peter+Anvin' # 'linux%2Fhotplug%2Fudev.git Greg+Kroah-Hartman' - my %paths; - open my ($fd), $projects_list or return; + open my $fd, '<', $projects_list or return; PROJECT: while (my $line = <$fd>) { chomp $line; @@ -1547,41 +3012,18 @@ 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; @@ -1589,6 +3031,102 @@ sub git_get_projects_list { return @list; } +# written with help of Tree::Trie module (Perl Artistic License, GPL compatibile) +# 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 { @@ -1600,7 +3138,7 @@ 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; @@ -1617,6 +3155,7 @@ sub git_get_project_owner { my $owner; return undef unless $project; + $git_dir = "$projectroot/$project"; if (!defined $gitweb_project_owner) { git_get_project_list_from_file(); @@ -1625,8 +3164,11 @@ sub git_get_project_owner { if (exists $gitweb_project_owner->{$project}) { $owner = $gitweb_project_owner->{$project}; } + if (!defined $owner){ + $owner = git_get_project_config('owner'); + } if (!defined $owner) { - $owner = get_file_owner("$projectroot/$project"); + $owner = get_file_owner("$git_dir"); } return $owner; @@ -1653,6 +3195,44 @@ 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; @@ -1664,7 +3244,7 @@ sub git_get_references { while (my $line = <$fd>) { chomp $line; - if ($line =~ m!^([0-9a-fA-F]{40})\srefs/($type/?[^^]+)!) { + if ($line =~ m!^([0-9a-fA-F]{40})\srefs/($type.*)$!) { if (defined $refs{$1}) { push @{$refs{$1}}, $2; } else { @@ -1713,10 +3293,12 @@ sub parse_date { $date{'mday-time'} = sprintf "%d %s %02d:%02d", $mday, $months[$mon], $hour ,$min; $date{'iso-8601'} = sprintf "%04d-%02d-%02dT%02d:%02d:%02dZ", - 1900+$year, $mon, $mday, $hour ,$min, $sec; + 1900+$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; @@ -1744,8 +3326,14 @@ sub parse_tag { $tag{'name'} = $1; } elsif ($line =~ m/^tagger (.*) ([0-9]+) (.*)$/) { $tag{'author'} = $1; - $tag{'epoch'} = $2; - $tag{'tz'} = $3; + $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; @@ -1785,7 +3373,7 @@ sub parse_commit_text { } elsif ((!defined $withparents) && ($line =~ m/^parent ([0-9a-fA-F]{40})$/)) { push @parents, $1; } elsif ($line =~ m/^author (.*) ([0-9]+) (.*)$/) { - $co{'author'} = $1; + $co{'author'} = to_utf8($1); $co{'author_epoch'} = $2; $co{'author_tz'} = $3; if ($co{'author'} =~ m/^([^<]+) <([^>]*)>/) { @@ -1795,10 +3383,9 @@ sub parse_commit_text { $co{'author_name'} = $co{'author'}; } } elsif ($line =~ m/^committer (.*) ([0-9]+) (.*)$/) { - $co{'committer'} = $1; + $co{'committer'} = 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'} = $2; @@ -1838,7 +3425,7 @@ sub parse_commit_text { last; } } - if ($co{'title'} eq "") { + if (! defined $co{'title'} || $co{'title'} eq "") { $co{'title'} = $co{'title_short'} = '(no commit message)'; } # remove added spaces @@ -1873,7 +3460,7 @@ sub parse_commit { "--max-count=1", $commit_id, "--", - or die_error(undef, "Open git-rev-list failed"); + or die_error(500, "Open git-rev-list failed"); %co = parse_commit_text(<$fd>, 1); close $fd; @@ -1881,7 +3468,7 @@ sub parse_commit { } sub parse_commits { - my ($commit_id, $maxcount, $skip, $arg, $filename) = @_; + my ($commit_id, $maxcount, $skip, $filename, @args) = @_; my @cos; $maxcount ||= 1; @@ -1891,14 +3478,14 @@ sub parse_commits { open my $fd, "-|", git_cmd(), "rev-list", "--header", - ($arg ? ($arg) : ()), + @args, ("--max-count=" . $maxcount), ("--skip=" . $skip), @extra_options, $commit_id, "--", ($filename ? ($filename) : ()) - or die_error(undef, "Open git-rev-list failed"); + or die_error(500, "Open git-rev-list failed"); while (my $line = <$fd>) { my %co = parse_commit_text($line); push @cos, \%co; @@ -1908,49 +3495,6 @@ sub parse_commits { return wantarray ? @cos : \@cos; } -# parse ref from ref_file, given by ref_id, with given type -sub parse_ref { - my $ref_file = shift; - my $ref_id = shift; - my $type = shift || git_get_type($ref_id); - my %ref_item; - - $ref_item{'type'} = $type; - $ref_item{'id'} = $ref_id; - $ref_item{'epoch'} = 0; - $ref_item{'age'} = "unknown"; - if ($type eq "tag") { - my %tag = parse_tag($ref_id); - $ref_item{'comment'} = $tag{'comment'}; - if ($tag{'type'} eq "commit") { - my %co = parse_commit($tag{'object'}); - $ref_item{'epoch'} = $co{'committer_epoch'}; - $ref_item{'age'} = $co{'age_string'}; - } elsif (defined($tag{'epoch'})) { - my $age = time - $tag{'epoch'}; - $ref_item{'epoch'} = $tag{'epoch'}; - $ref_item{'age'} = age_string($age); - } - $ref_item{'reftype'} = $tag{'type'}; - $ref_item{'name'} = $tag{'name'}; - $ref_item{'refid'} = $tag{'object'}; - } elsif ($type eq "commit"){ - my %co = parse_commit($ref_id); - $ref_item{'reftype'} = "commit"; - $ref_item{'name'} = $ref_file; - $ref_item{'title'} = $co{'title'}; - $ref_item{'refid'} = $ref_id; - $ref_item{'epoch'} = $co{'committer_epoch'}; - $ref_item{'age'} = $co{'age_string'}; - } else { - $ref_item{'reftype'} = $type; - $ref_item{'name'} = $ref_file; - $ref_item{'refid'} = $ref_id; - } - - return %ref_item; -} - # parse line of git-diff-tree "raw" output sub parse_difftree_raw_line { my $line = shift; @@ -1968,7 +3512,7 @@ sub parse_difftree_raw_line { if ($res{'status'} eq 'R' || $res{'status'} eq 'C') { # renamed or copied ($res{'from_file'}, $res{'to_file'}) = map { unquote($_) } split("\t", $7); } else { - $res{'file'} = unquote($7); + $res{'from_file'} = $res{'to_file'} = $res{'file'} = unquote($7); } } # '::100755 100755 100755 60e79ca1b01bc8b057abe17ddab484699a7f5fdb 94067cc5f73388f33722d52ae02f44692bc07490 94067cc5f73388f33722d52ae02f44692bc07490 MR git-gui/git-gui.sh' @@ -1990,22 +3534,50 @@ sub parse_difftree_raw_line { return wantarray ? %res : \%res; } +# wrapper: return parsed line of git-diff-tree "raw" output +# (the argument might be raw line, or parsed info) +sub parsed_difftree_line { + my $line_or_ref = shift; + + if (ref($line_or_ref) eq "HASH") { + # pre-parsed (or generated by hand) + return $line_or_ref; + } else { + return parse_difftree_raw_line($line_or_ref); + } +} + # 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' + $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40}) +(-|[0-9]+)\t(.+)$/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' + $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t(.+)$/s; + + $res{'mode'} = $1; + $res{'type'} = $2; + $res{'hash'} = $3; + if ($opts{'-z'}) { + $res{'name'} = $4; + } else { + $res{'name'} = unquote($4); + } } return wantarray ? %res : \%res; @@ -2022,7 +3594,10 @@ sub parse_from_to_diffinfo { fill_from_file_info($diffinfo, @parents) unless exists $diffinfo->{'from_file'}; for (my $i = 0; $i < $diffinfo->{'nparents'}; $i++) { - $from->{'file'}[$i] = $diffinfo->{'from_file'}[$i] || $diffinfo->{'to_file'}; + $from->{'file'}[$i] = + defined $diffinfo->{'from_file'}[$i] ? + $diffinfo->{'from_file'}[$i] : + $diffinfo->{'to_file'}; if ($diffinfo->{'status'}[$i] ne "A") { # not new (added) file $from->{'href'}[$i] = href(action=>"blob", hash_base=>$parents[$i], @@ -2033,7 +3608,8 @@ sub parse_from_to_diffinfo { } } } else { - $from->{'file'} = $diffinfo->{'from_file'} || $diffinfo->{'file'}; + # ordinary (not combined) diff + $from->{'file'} = $diffinfo->{'from_file'}; if ($diffinfo->{'status'} ne "A") { # not new (added) file $from->{'href'} = href(action=>"blob", hash_base=>$hash_parent, hash=>$diffinfo->{'from_id'}, @@ -2043,7 +3619,7 @@ sub parse_from_to_diffinfo { } } - $to->{'file'} = $diffinfo->{'to_file'} || $diffinfo->{'file'}; + $to->{'file'} = $diffinfo->{'to_file'}; if (!is_deleted($diffinfo)) { # file exists in result $to->{'href'} = href(action=>"blob", hash_base=>$hash, hash=>$diffinfo->{'to_id'}, @@ -2057,13 +3633,15 @@ sub parse_from_to_diffinfo { ## parse to array of hashes functions sub git_get_heads_list { - my $limit = shift; + my ($limit, @classes) = @_; + @classes = ('heads') unless @classes; + my @patterns = map { "refs/$_" } @classes; my @headslist; open my $fd, '-|', git_cmd(), 'for-each-ref', ($limit ? '--count='.($limit+1) : ()), '--sort=-committerdate', '--format=%(objectname) %(refname) %(subject)%00%(committer)', - 'refs/heads' + @patterns or return; while (my $line = <$fd>) { my %ref_item; @@ -2073,7 +3651,8 @@ sub git_get_heads_list { my ($hash, $name, $title) = split(' ', $refinfo, 3); my ($committer, $epoch, $tz) = ($committerinfo =~ /^(.*) ([0-9]+) (.*)$/); - $name =~ s!^refs/heads/!!; + $ref_item{'fullname'} = $name; + $name =~ s!^refs/(?:head|remote)s/!!; $ref_item{'name'} = $name; $ref_item{'id'} = $hash; @@ -2110,6 +3689,7 @@ sub git_get_tags_list { my ($id, $type, $name, $refid, $reftype, $title) = split(' ', $refinfo, 6); my ($creator, $epoch, $tz) = ($creatorinfo =~ /^(.*) ([0-9]+) (.*)$/); + $ref_item{'fullname'} = $name; $name =~ s!^refs/tags/!!; $ref_item{'type'} = $type; @@ -2156,6 +3736,15 @@ sub get_file_owner { return to_utf8($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 @@ -2165,18 +3754,15 @@ sub mimetype_guess_file { -r $mimemap or return undef; my %mimemap; - open(MIME, $mimemap) or return undef; - while (<MIME>) { + 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}; @@ -2212,8 +3798,7 @@ sub blob_mimetype { return $default_blob_plain_mimetype unless $fd; if (-T $fd) { - return 'text/plain' . - ($default_text_plain_charset ? '; charset='.$default_text_plain_charset : ''); + return 'text/plain'; } elsif (! $filename) { return 'application/octet-stream'; } elsif ($filename =~ m/\.png$/i) { @@ -2227,27 +3812,75 @@ sub blob_mimetype { } } +sub blob_contenttype { + my ($fd, $file_name, $type) = @_; + + $type ||= blob_mimetype($fd, $file_name); + if ($type eq 'text/plain' && defined $default_text_plain_charset) { + $type .= "; charset=$default_text_plain_charset"; + } + + 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, $mimetype, $file_name) = @_; + return undef unless ($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 && defined $syntax); + + close $fd; + open $fd, quote_command(git_cmd(), "cat-file", "blob", $hash)." | ". + quote_command($highlight_bin). + " --replace-tabs=8 --fragment --syntax $syntax |" + 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; } - my $content_type; + $title .= " - " . to_utf8($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 .= "/"; + } + + 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 @@ -2255,12 +3888,162 @@ 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'; + 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)) { + my $type = lc($format); + my %link_attr = ( + '-rel' => 'alternate', + '-title' => esc_attr("$project - $href_params{'-title'} - $format feed"), + '-type' => "application/$type+xml" + ); + + $href_params{'extra_options'} = undef; + $href_params{'action'} = $type; + $link_attr{'-href'} = href(%href_params); + print "<link ". + "rel=\"$link_attr{'-rel'}\" ". + "title=\"$link_attr{'-title'}\" ". + "href=\"$link_attr{'-href'}\" ". + "type=\"$link_attr{'-type'}\" ". + "/>\n"; + + $href_params{'extra_options'} = '--no-merges'; + $link_attr{'-href'} = href(%href_params); + $link_attr{'-title'} .= ' (no merges)'; + print "<link ". + "rel=\"$link_attr{'-rel'}\" ". + "title=\"$link_attr{'-title'}\" ". + "href=\"$link_attr{'-href'}\" ". + "type=\"$link_attr{'-type'}\" ". + "/>\n"; + } + + } else { + printf('<link rel="alternate" title="%s projects list" '. + 'href="%s" type="text/plain; charset=utf-8" />'."\n", + esc_attr($site_name), href(project=>undef, action=>"project_index")); + printf('<link rel="alternate" title="%s projects feeds" '. + 'href="%s" type="text/x-opml" />'."\n", + esc_attr($site_name), 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 $stylesheet) { + print '<link rel="stylesheet" type="text/css" href="'.esc_url($stylesheet).'"/>'."\n"; + } else { + foreach my $stylesheet (@stylesheets) { + next unless $stylesheet; + print '<link rel="stylesheet" type="text/css" href="'.esc_url($stylesheet).'"/>'."\n"; + } + } + print_feed_meta() + if ($status eq '200 OK'); + if (defined $favicon) { + print qq(<link rel="shortcut icon" href=").esc_url($favicon).qq(" type="image/png" />\n); + } +} + +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)) . " / "; + } +} + +sub print_nav_breadcrumbs { + my %opts = @_; + + print $cgi->a({-href => esc_url($home_link)}, $home_link_str) . " / "; + if (defined $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) { + 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->startform(-method => "get", -action => $action) . + "<div class=\"search\">\n" . + (!$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, -override => 1) . "\n" . + "<span title=\"Extended regular expression\">" . + $cgi->checkbox(-name => 'sr', -value => 1, -label => 're', + -checked => $search_use_regexp) . + "</span>" . + "</div>" . + $cgi->end_form() . "\n"; +} + +sub git_header_html { + my $status = shift || "200 OK"; + my $expires = shift; + my %opts = @_; + + my $title = get_page_title(); + my $content_type = get_content_type_html(); print $cgi->header(-type=>$content_type, -charset => 'utf-8', - -status=> $status, -expires => $expires); + -status=> $status, -expires => $expires) + unless ($opts{'-no_http_header'}); my $mod_perl_version = $ENV{'MOD_PERL'} ? " $ENV{'MOD_PERL'}" : ''; print <<EOF; <?xml version="1.0" encoding="utf-8"?> @@ -2274,146 +4057,163 @@ sub git_header_html { <meta name="robots" content="index, nofollow"/> <title>$title</title> EOF -# print out each stylesheet that exist - if (defined $stylesheet) { -#provides backwards capability for those people who define style sheet in a config file - print '<link rel="stylesheet" type="text/css" href="'.$stylesheet.'"/>'."\n"; - } else { - foreach my $stylesheet (@stylesheets) { - next unless $stylesheet; - print '<link rel="stylesheet" type="text/css" href="'.$stylesheet.'"/>'."\n"; - } - } - if (defined $project) { - printf('<link rel="alternate" title="%s log RSS feed" '. - 'href="%s" type="application/rss+xml" />'."\n", - esc_param($project), href(action=>"rss")); - printf('<link rel="alternate" title="%s log RSS feed (no merges)" '. - 'href="%s" type="application/rss+xml" />'."\n", - esc_param($project), href(action=>"rss", - extra_options=>"--no-merges")); - printf('<link rel="alternate" title="%s log Atom feed" '. - 'href="%s" type="application/atom+xml" />'."\n", - esc_param($project), href(action=>"atom")); - printf('<link rel="alternate" title="%s log Atom feed (no merges)" '. - 'href="%s" type="application/atom+xml" />'."\n", - esc_param($project), href(action=>"atom", - extra_options=>"--no-merges")); - } else { - printf('<link rel="alternate" title="%s projects list" '. - 'href="%s" type="text/plain; charset=utf-8"/>'."\n", - $site_name, href(project=>undef, action=>"project_index")); - printf('<link rel="alternate" title="%s projects feeds" '. - 'href="%s" type="text/x-opml"/>'."\n", - $site_name, href(project=>undef, action=>"opml")); + # the stylesheet, favicon etc urls won't work correctly with path_info + # unless we set the appropriate base URL + if ($ENV{'PATH_INFO'}) { + print "<base href=\"".esc_url($base_url)."\" />\n"; } - if (defined $favicon) { - print qq(<link rel="shortcut icon" href="$favicon" type="image/png"/>\n); + print_header_links($status); + + if (defined $site_html_head_string) { + print to_utf8($site_html_head_string); } print "</head>\n" . "<body>\n"; - if (-f $site_header) { - open (my $fd, $site_header); - print <$fd>; - close $fd; + if (defined $site_header && -f $site_header) { + insert_file($site_header); } - print "<div class=\"page_header\">\n" . - $cgi->a({-href => esc_url($logo_url), - -title => $logo_label}, - qq(<img src="$logo" width="72" height="27" alt="git" class="logo"/>)); - print $cgi->a({-href => esc_url($home_link)}, $home_link_str) . " / "; - if (defined $project) { - print $cgi->a({-href => href(action=>"summary")}, esc_html($project)); - if (defined $action) { - print " / $action"; - } - print "\n"; + print "<div class=\"page_header\">\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 "</div>\n"; - 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) { - $action .= "/$project"; - } else { - $cgi->param("p", $project); - } - $cgi->param("a", "search"); - $cgi->param("h", $search_hash); - print $cgi->startform(-method => "get", -action => $action) . - "<div class=\"search\">\n" . - (!$use_pathinfo && $cgi->hidden(-name => "p") . "\n") . - $cgi->hidden(-name => "a") . "\n" . - $cgi->hidden(-name => "h") . "\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" . - "</div>" . - $cgi->end_form() . "\n"; + my $have_search = gitweb_check_feature('search'); + if (defined $project && $have_search) { + print_search_form(); } } sub git_footer_html { + my $feed_class = 'rss_logo'; + print "<div class=\"page_footer\">\n"; if (defined $project) { my $descr = git_get_project_description($project); if (defined $descr) { print "<div class=\"page_footer_text\">" . esc_html($descr) . "</div>\n"; } - print $cgi->a({-href => href(action=>"rss"), - -class => "rss_logo"}, "RSS") . " "; - print $cgi->a({-href => href(action=>"atom"), - -class => "rss_logo"}, "Atom") . "\n"; + + my %href_params = get_feed_info(); + if (!%href_params) { + $feed_class .= ' generic'; + } + $href_params{'-title'} ||= 'log'; + + foreach my $format (qw(RSS Atom)) { + $href_params{'action'} = lc($format); + print $cgi->a({-href => href(%href_params), + -title => "$href_params{'-title'} $format feed", + -class => $feed_class}, $format)."\n"; + } + } else { - print $cgi->a({-href => href(project=>undef, action=>"opml"), - -class => "rss_logo"}, "OPML") . " "; - print $cgi->a({-href => href(project=>undef, action=>"project_index"), - -class => "rss_logo"}, "TXT") . "\n"; - } - print "</div>\n" ; + 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", + project_filter => $project_filter), + -class => $feed_class}, "TXT") . "\n"; + } + print "</div>\n"; # class="page_footer" + + if (defined $t0 && gitweb_check_feature('timed')) { + print "<div id=\"generating_info\">\n"; + print 'This page took '. + '<span id="generating_time" class="time_span">'. + tv_interval($t0, [ gettimeofday() ]). + ' seconds </span>'. + ' and '. + '<span id="generating_cmd">'. + $number_of_git_cmds. + '</span> git commands '. + " to generate.\n"; + print "</div>\n"; # class="page_footer" + } + + if (defined $site_footer && -f $site_footer) { + insert_file($site_footer); + } + + print qq!<script type="text/javascript" src="!.esc_url($javascript).qq!"></script>\n!; + if (defined $action && + $action eq 'blame_incremental') { + print qq!<script type="text/javascript">\n!. + qq!startBlame("!. href(action=>"blame_data", -replay=>1) .qq!",\n!. + qq! "!. href() .qq!");\n!. + qq!</script>\n!; + } else { + my ($jstimezone, $tz_cookie, $datetime_class) = + gitweb_get_feature('javascript-timezone'); - if (-f $site_footer) { - open (my $fd, $site_footer); - print <$fd>; - close $fd; + print qq!<script type="text/javascript">\n!. + qq!window.onload = function () {\n!; + if (gitweb_check_feature('javascript-actions')) { + print qq! fixLinks();\n!; + } + if ($jstimezone && $tz_cookie && $datetime_class) { + print qq! var tz_cookie = { name: '$tz_cookie', expires: 14, path: '/' };\n!. # in days + qq! onloadTZSetup('$jstimezone', tz_cookie, '$datetime_class');\n!; + } + print qq!};\n!. + qq!</script>\n!; } print "</body>\n" . "</html>"; } +# die_error(<http_status_code>, <error_message>[, <detailed_html_description>]) +# 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 +# requested object exists but has wrong type. +# 403: Requested feature (like "pickaxe" or "snapshot") not enabled on +# this server or project. +# 404: Requested object/revision/project doesn't exist. +# 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 || "403 Forbidden"; - my $error = shift || "Malformed query, file missing or permission denied"; + my $status = shift || 500; + my $error = esc_html(shift) || "Internal Server Error"; + my $extra = shift; + my %opts = @_; - git_header_html($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 <<EOF; <div class="page_body"> <br /><br /> $status - $error <br /> -</div> EOF + if (defined $extra) { + print "<hr />\n" . + "$extra\n"; + } + print "</div>\n"; + git_footer_html(); - exit; + goto DONE_GITWEB + unless ($opts{'-error_handler'}); } ## ---------------------------------------------------------------------- @@ -2439,40 +4239,67 @@ sub git_print_page_nav { } } } + $arg{'tree'}{'hash'} = $treehead if defined $treehead; $arg{'tree'}{'hash_base'} = $treebase if defined $treebase; + my @actions = gitweb_get_feature('actions'); + my %repl = ( + '%' => '%', + 'n' => $project, # project name + 'f' => $git_dir, # project path within filesystem + 'h' => $treehead || '', # current hash ('h' parameter) + 'b' => $treebase || '', # hash base ('hb' parameter) + ); + while (@actions) { + my ($label, $link, $pos) = splice(@actions,0,3); + # insert + @navs = map { $_ eq $pos ? ($_, $label) : $_ } @navs; + # munch munch + $link =~ s/%([%nfhb])/$repl{$1}/g; + $arg{$label}{'_href'} = $link; + } + print "<div class=\"page_nav\">\n" . (join " | ", map { $_ eq $current ? - $_ : $cgi->a({-href => href(%{$arg{$_}})}, "$_") + $_ : $cgi->a({-href => ($arg{$_}{_href} ? $arg{$_}{_href} : href(%{$arg{$_}}))}, "$_") } @navs); print "<br/>\n$extra<br/>\n" . "</div>\n"; } +# returns a submenu for the nagivation 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, $nrevs) = @_; + my ($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 .= " ⋅ " . - $cgi->a({-href => href(action=>$action, hash=>$hash, page=>$page-1), + $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"; + $paging_nav .= "first ⋅ prev"; } - if ($nrevs >= (100 * ($page+1)-1)) { + if ($has_next_link) { $paging_nav .= " ⋅ " . - $cgi->a({-href => href(action=>$action, hash=>$hash, page=>$page+1), + $cgi->a({-href => href(-replay=>1, page=>$page+1), -accesskey => "n", -title => "Alt-n"}, "next"); } else { $paging_nav .= " ⋅ next"; @@ -2498,22 +4325,111 @@ sub git_print_header_div { "\n</div>\n"; } -#sub git_print_authorship (\%) { +sub format_repo_url { + my ($name, $url) = @_; + return "<tr class=\"metadata_url\"><td>$name</td><td>$url</td></tr>\n"; +} + +# Group output by placing it in a DIV element and adding a header. +# Options for start_div() can be provided by passing a hash reference as the +# first parameter to the function. +# Options to git_print_header_div() can be provided by passing an array +# reference. This must follow the options to start_div if they are present. +# The content can be a scalar, which is output as-is, a scalar reference, which +# is output after html escaping, an IO handle passed either as *handle or +# *handle{IO}, or a function reference. In the latter case all following +# parameters will be taken as argument to the content function call. +sub git_print_section { + my ($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) { + $strtime = qq!<span class="$datetime_class">$strtime</span>!; + } + + my $localtime_format = '(%02d:%02d %s)'; + if ($date->{'hour_local'} < 6) { + $localtime_format = '(<span class="atnight">%02d:%02d</span> %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'}, $co->{'author_tz'}); - print "<div class=\"author_date\">" . - esc_html($co->{'author_name'}) . - " [$ad{'rfc2822'}"; - if ($ad{'hour_local'} < 6) { - printf(" (<span class=\"atnight\">%02d:%02d</span> %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($co->{'author_email'}, -pad_before => 1) . + "</$tag>\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 "<tr><td>$who</td><td>" . + format_search_author($co->{"${who}_name"}, $who, + esc_html($co->{"${who}_name"})) . " " . + format_search_author($co->{"${who}_email"}, $who, + esc_html("<" . $co->{"${who}_email"} . ">")) . + "</td><td rowspan=\"2\">" . + git_get_avatar($co->{"${who}_email"}, -size => 'double') . + "</td></tr>\n" . + "<tr>" . + "<td></td><td>" . + format_timestamp_html(\%wd) . + "</td>" . + "</tr>\n"; } - print "]</div>\n"; } sub git_print_page_path { @@ -2554,8 +4470,7 @@ sub git_print_page_path { print "<br/></div>\n"; } -# sub git_print_log (\@;%) { -sub git_print_log ($;%) { +sub git_print_log { my $log = shift; my %opts = @_; @@ -2613,7 +4528,7 @@ sub git_get_link_target { open my $fd, "-|", git_cmd(), "cat-file", "blob", $hash or return; { - local $/; + local $/ = undef; $link_target = <$fd>; } close $fd @@ -2626,10 +4541,7 @@ sub git_get_link_target { # return target of link relative to top directory (top tree); # return undef if it is not possible (including absolute links). sub normalize_link_target { - my ($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 '/'); @@ -2677,6 +4589,9 @@ sub git_print_tree_entry { # and link is the action links of the entry. print "<td class=\"mode\">" . mode_str($t->{'mode'}) . "</td>\n"; + if (exists $t->{'size'}) { + print "<td class=\"size\">$t->{'size'}</td>\n"; + } if ($t->{'type'} eq "blob") { print "<td class=\"list\">" . $cgi->a({-href => href(action=>"blob", hash=>$t->{'hash'}, @@ -2685,7 +4600,7 @@ 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, @@ -2722,12 +4637,14 @@ sub git_print_tree_entry { } elsif ($t->{'type'} eq "tree") { print "<td class=\"list\">"; 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 "</td>\n"; print "<td class=\"link\">"; 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 $hash_base) { print " | " . @@ -2756,6 +4673,7 @@ sub git_print_tree_entry { ## ...................................................................... ## functions printing large fragments of HTML +# get pre-image filenames for merge (combined) diff sub fill_from_file_info { my ($diff, @parents) = @_; @@ -2772,32 +4690,29 @@ sub fill_from_file_info { return $diff; } -# parameters can be strings, or references to arrays of strings -sub from_ids_eq { - my ($a, $b) = @_; - - if (ref($a) eq "ARRAY" && ref($b) eq "ARRAY" && @$a == @$b) { - for (my $i = 0; $i < @$a; ++$i) { - return 0 unless ($a->[$i] eq $b->[$i]); - } - return 1; - } elsif (!ref($a) && !ref($b)) { - return $a eq $b; - } else { - return 0; - } -} - +# is current raw difftree line of file deletion sub is_deleted { my $diffinfo = shift; return $diffinfo->{'to_id'} eq ('0' x 40); } +# does patch correspond to [previous] difftree raw line +# $diffinfo - hashref of parsed raw diff format +# $patchinfo - hashref of parsed patch diff format +# (the same keys as in $diffinfo) +sub is_patch_split { + my ($diffinfo, $patchinfo) = @_; + + return defined $diffinfo && defined $patchinfo + && $diffinfo->{'to_file'} eq $patchinfo->{'to_file'}; +} + + sub git_difftree_body { my ($difftree, $hash, @parents) = @_; my ($parent) = $parents[0]; - my ($have_blame) = gitweb_check_feature('blame'); + my $have_blame = gitweb_check_feature('blame'); print "<div class=\"list_head\">\n"; if ($#{$difftree} > 10) { print(($#{$difftree} + 1) . " files changed:\n"); @@ -2809,7 +4724,7 @@ sub git_difftree_body { "diff_tree\">\n"; # header only for combined diff in 'commitdiff' view - my $has_header = @parents > 1 && $action eq 'commitdiff'; + my $has_header = @$difftree && @parents > 1 && $action eq 'commitdiff'; if ($has_header) { # table header print "<thead><tr>\n" . @@ -2830,13 +4745,7 @@ sub git_difftree_body { my $alternate = 1; my $patchno = 0; foreach my $line (@{$difftree}) { - my $diff; - if (ref($line) eq "HASH") { - # pre-parsed (or generated by hand) - $diff = $line; - } else { - $diff = parse_difftree_raw_line($line); - } + my $diff = parsed_difftree_line($line); if ($alternate) { print "<tr class=\"dark\">\n"; @@ -2868,7 +4777,8 @@ sub git_difftree_body { # link to patch $patchno++; print "<td class=\"link\">" . - $cgi->a({-href => "#patch$patchno"}, "patch") . + $cgi->a({-href => href(-anchor=>"patch$patchno")}, + "patch") . " | " . "</td>\n"; } @@ -2945,7 +4855,7 @@ 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'}); @@ -2965,8 +4875,9 @@ 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'})}, @@ -2985,8 +4896,9 @@ 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'})}, @@ -3027,7 +4939,8 @@ 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 $diff->{'from_id'}) { # "commit" view and modified file (not onlu mode changed) @@ -3072,7 +4985,8 @@ sub git_difftree_body { if ($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 $diff->{'from_id'}) { # "commit" view and modified file (not only pure rename or copy) @@ -3103,15 +5017,249 @@ sub git_difftree_body { print "</table>\n"; } +# Print context lines and then rem/add lines in a side-by-side manner. +sub print_sidebyside_diff_lines { + my ($ctx, $rem, $add) = @_; + + # print context block before add/rem block + if (@$ctx) { + print join '', + '<div class="chunk_block ctx">', + '<div class="old">', + @$ctx, + '</div>', + '<div class="new">', + @$ctx, + '</div>', + '</div>'; + } + + if (!@$add) { + # pure removal + print join '', + '<div class="chunk_block rem">', + '<div class="old">', + @$rem, + '</div>', + '</div>'; + } elsif (!@$rem) { + # pure addition + print join '', + '<div class="chunk_block add">', + '<div class="new">', + @$add, + '</div>', + '</div>'; + } else { + print join '', + '<div class="chunk_block chg">', + '<div class="old">', + @$rem, + '</div>', + '<div class="new">', + @$add, + '</div>', + '</div>'; + } +} + +# 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) { + $can_highlight = 1; + + # Highlight lines in combined diff only if the chunk contains + # diff between the same version, e.g. + # + # - a + # - b + # + c + # + d + # + # Otherwise the highlightling would be confusing. + if ($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); my $patch_idx = 0; my $patch_number = 0; my $patch_line; my $diffinfo; + my $to_name; my (%from, %to); + my @chunk; # for side-by-side diff print "<div class=\"patchset\">\n"; @@ -3124,140 +5272,85 @@ sub git_patchset_body { PATCH: while ($patch_line) { - my @diff_header; - my ($from_id, $to_id); - - # git diff header - #assert($patch_line =~ m/^diff /) if DEBUG; - #assert($patch_line !~ m!$/$!) if DEBUG; # is chomp-ed - $patch_number++; - push @diff_header, $patch_line; - - # extended diff header - EXTENDED_HEADER: - while ($patch_line = <$fd>) { - chomp $patch_line; - - last EXTENDED_HEADER if ($patch_line =~ m/^--- |^diff /); - if ($patch_line =~ m/^index ([0-9a-fA-F]{40})..([0-9a-fA-F]{40})/) { - $from_id = $1; - $to_id = $2; - } elsif ($patch_line =~ m/^index ((?:[0-9a-fA-F]{40},)+[0-9a-fA-F]{40})..([0-9a-fA-F]{40})/) { - $from_id = [ split(',', $1) ]; - $to_id = $2; - } - - push @diff_header, $patch_line; + # parse "git diff" header line + if ($patch_line =~ m/^diff --git (\"(?:[^\\\"]*(?:\\.[^\\\"]*)*)\"|[^ "]*) (.*)$/) { + # $1 is from_name, which we do not use + $to_name = unquote($2); + $to_name =~ s!^b/!!; + } elsif ($patch_line =~ m/^diff --(cc|combined) ("?.*"?)$/) { + # $1 is 'cc' or 'combined', which we do not use + $to_name = unquote($2); + } else { + $to_name = undef; } - my $last_patch_line = $patch_line; # check if current patch belong to current raw line # and parse raw git-diff line if needed - if (defined $diffinfo && - defined $from_id && defined $to_id && - from_ids_eq($diffinfo->{'from_id'}, $from_id) && - $diffinfo->{'to_id'} eq $to_id) { + if (is_patch_split($diffinfo, { 'to_file' => $to_name })) { # this is continuation of a split patch print "<div class=\"patch cont\">\n"; } else { # advance raw git-diff output if needed $patch_idx++ if defined $diffinfo; - # compact combined diff output can have some patches skipped - # find which patch (using pathname of result) we are at now - my $to_name; - if ($diff_header[0] =~ m!^diff --cc "?(.*)"?$!) { - $to_name = $1; - } - - do { - # read and prepare patch information - if (ref($difftree->[$patch_idx]) eq "HASH") { - # pre-parsed (or generated by hand) - $diffinfo = $difftree->[$patch_idx]; - } else { - $diffinfo = parse_difftree_raw_line($difftree->[$patch_idx]); - } + # read and prepare patch information + $diffinfo = parsed_difftree_line($difftree->[$patch_idx]); - # check if current raw line has no patch (it got simplified) - if (defined $to_name && $to_name ne $diffinfo->{'to_file'}) { + # compact combined diff output can have some patches skipped + # find which patch (using pathname of result) we are at now; + if ($is_combined) { + while ($to_name ne $diffinfo->{'to_file'}) { print "<div class=\"patch\" id=\"patch". ($patch_idx+1) ."\">\n" . format_diff_cc_simplified($diffinfo, @hash_parents) . "</div>\n"; # class="patch" $patch_idx++; $patch_number++; + + last if $patch_idx > $#$difftree; + $diffinfo = parsed_difftree_line($difftree->[$patch_idx]); } - } until (!defined $to_name || $to_name eq $diffinfo->{'to_file'} || - $patch_idx > $#$difftree); + } + # modifies %from, %to hashes parse_from_to_diffinfo($diffinfo, \%from, \%to, @hash_parents); - if ($diffinfo->{'nparents'}) { - # combined diff - $from{'file'} = []; - $from{'href'} = []; - fill_from_file_info($diffinfo, @hash_parents) - unless exists $diffinfo->{'from_file'}; - for (my $i = 0; $i < $diffinfo->{'nparents'}; $i++) { - $from{'file'}[$i] = $diffinfo->{'from_file'}[$i] || $diffinfo->{'to_file'}; - if ($diffinfo->{'status'}[$i] ne "A") { # not new (added) file - $from{'href'}[$i] = href(action=>"blob", - hash_base=>$hash_parents[$i], - hash=>$diffinfo->{'from_id'}[$i], - file_name=>$from{'file'}[$i]); - } else { - $from{'href'}[$i] = undef; - } - } - } else { - $from{'file'} = $diffinfo->{'from_file'} || $diffinfo->{'file'}; - if ($diffinfo->{'status'} ne "A") { # not new (added) file - $from{'href'} = href(action=>"blob", hash_base=>$hash_parent, - hash=>$diffinfo->{'from_id'}, - file_name=>$from{'file'}); - } else { - delete $from{'href'}; - } - } - $to{'file'} = $diffinfo->{'to_file'} || $diffinfo->{'file'}; - if (!is_deleted($diffinfo)) { # file exists in result - $to{'href'} = href(action=>"blob", hash_base=>$hash, - hash=>$diffinfo->{'to_id'}, - file_name=>$to{'file'}); - } else { - delete $to{'href'}; - } # this is first patch for raw difftree line with $patch_idx index # we index @$difftree array from 0, but number patches from 1 print "<div class=\"patch\" id=\"patch". ($patch_idx+1) ."\">\n"; } + # git diff header + #assert($patch_line =~ m/^diff /) if DEBUG; + #assert($patch_line !~ m!$/$!) if DEBUG; # is chomp-ed + $patch_number++; # print "git diff" header - $patch_line = shift @diff_header; print format_git_diff_header_line($patch_line, $diffinfo, \%from, \%to); # print extended diff header - print "<div class=\"diff extended_header\">\n" if (@diff_header > 0); + print "<div class=\"diff extended_header\">\n"; EXTENDED_HEADER: - foreach $patch_line (@diff_header) { + while ($patch_line = <$fd>) { + chomp $patch_line; + + last EXTENDED_HEADER if ($patch_line =~ m/^--- |^diff /); + print format_extended_diff_header_line($patch_line, $diffinfo, \%from, \%to); } - print "</div>\n" if (@diff_header > 0); # class="diff extended_header" + print "</div>\n"; # class="diff extended_header" # from-file/to-file diff header - $patch_line = $last_patch_line; if (! $patch_line) { print "</div>\n"; # class="patch" last PATCH; } next PATCH if ($patch_line =~ m/^diff /); #assert($patch_line =~ m/^---/) if DEBUG; - #assert($patch_line eq $last_patch_line) if DEBUG; + my $last_patch_line = $patch_line; $patch_line = <$fd>; chomp $patch_line; #assert($patch_line =~ m/^\+\+\+/) if DEBUG; @@ -3273,25 +5366,31 @@ 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 "</div>\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 ($patch_idx++ if $patch_number > 0; + # for compact combined (--cc) format, with chunk and patch simplification + # the patchset might be empty, but there might be unprocessed raw lines + for (++$patch_idx if $patch_number > 0; $patch_idx < @$difftree; - $patch_idx++) { + ++$patch_idx) { # read and prepare patch information - if (ref($difftree->[$patch_idx]) eq "HASH") { - # pre-parsed (or generated by hand) - $diffinfo = $difftree->[$patch_idx]; - } else { - $diffinfo = parse_difftree_raw_line($difftree->[$patch_idx]); - } + $diffinfo = parsed_difftree_line($difftree->[$patch_idx]); # generate anchor for "patch" links in difftree / whatchanged part print "<div class=\"patch\" id=\"patch". ($patch_idx+1) ."\">\n" . @@ -3314,115 +5413,220 @@ sub git_patchset_body { # . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . -sub git_project_list_body { - my ($projlist, $order, $from, $to, $extra, $no_header) = @_; +sub git_project_search_form { + my ($searchtext, $search_use_regexp) = @_; + + my $limit = ''; + if ($project_filter) { + $limit = " in '$project_filter/'"; + } + + print "<div class=\"projsearch\">\n"; + print $cgi->startform(-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" . + "<span title=\"Extended regular expression\">" . + $cgi->checkbox(-name => 'sr', -value => 1, -label => 're', + -checked => $search_use_regexp) . + "</span>\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")) . "<br />\n"; + print "</div>\n"; +} - my ($check_forks) = gitweb_check_feature('forks'); +# entry for given @keys needs filling if at least one of keys in list +# is not present in %$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, @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 (@aa) = git_get_last_activity($pr->{'path'}); - unless (@aa) { - next; + if (project_info_needs_filling($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'}) = @aa; - if (!defined $pr->{'descr'}) { + if (project_info_needs_filling($pr, $filter_set->('descr', 'descr_long'))) { my $descr = git_get_project_description($pr->{'path'}) || ""; - $pr->{'descr_long'} = to_utf8($descr); + $descr = to_utf8($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); } + push @projects, $pr; } - $order ||= $default_projects_order; + return @projects; +} + +sub sort_projects_list { + my ($projlist, $order) = @_; + my @projects; + + 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}; + return @$projlist unless defined $oi; + if ($oi->{'type'} eq 'str') { + @projects = sort {$a->{$oi->{'key'}} cmp $b->{$oi->{'key'}}} @$projlist; + } else { + @projects = sort {$a->{$oi->{'key'}} <=> $b->{$oi->{'key'}}} @$projlist; + } + + return @projects; +} + +# returns a hash of categories, containing the list of project +# belonging to each category +sub build_projlist_by_category { + my ($projlist, $from, $to) = @_; + my %categories; + $from = 0 unless defined $from; - $to = $#projects if (!defined $to || $#projects < $to); + $to = $#$projlist if (!defined $to || $#$projlist < $to); - print "<table class=\"project_list\">\n"; - unless ($no_header) { - print "<tr>\n"; - if ($check_forks) { - print "<th></th>\n"; - } - if ($order eq "project") { - @projects = sort {$a->{'path'} cmp $b->{'path'}} @projects; - print "<th>Project</th>\n"; - } else { - print "<th>" . - $cgi->a({-href => href(project=>undef, order=>'project'), - -class => "header"}, "Project") . - "</th>\n"; - } - if ($order eq "descr") { - @projects = sort {$a->{'descr'} cmp $b->{'descr'}} @projects; - print "<th>Description</th>\n"; - } else { - print "<th>" . - $cgi->a({-href => href(project=>undef, order=>'descr'), - -class => "header"}, "Description") . - "</th>\n"; - } - if ($order eq "owner") { - @projects = sort {$a->{'owner'} cmp $b->{'owner'}} @projects; - print "<th>Owner</th>\n"; - } else { - print "<th>" . - $cgi->a({-href => href(project=>undef, order=>'owner'), - -class => "header"}, "Owner") . - "</th>\n"; - } - if ($order eq "age") { - @projects = sort {$a->{'age'} <=> $b->{'age'}} @projects; - print "<th>Last Change</th>\n"; - } else { - print "<th>" . - $cgi->a({-href => href(project=>undef, order=>'age'), - -class => "header"}, "Last Change") . - "</th>\n"; - } - print "<th></th>\n" . - "</tr>\n"; + for (my $i = $from; $i <= $to; $i++) { + my $pr = $projlist->[$i]; + push @{$categories{ $pr->{'category'} }}, $pr; } + + return wantarray ? %categories : \%categories; +} + +# print 'sort by' <th> 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) { + $sort_th .= "<th>$header</th>\n"; + } else { + $sort_th .= "<th>" . + $cgi->a({-href => href(-replay=>1, order=>$name), + -class => "header"}, $header) . + "</th>\n"; + } + + return $sort_th; +} + +sub git_project_list_rows { + my ($projlist, $from, $to, $check_forks) = @_; + + $from = 0 unless defined $from; + $to = $#$projlist if (!defined $to || $#$projlist < $to); + my $alternate = 1; for (my $i = $from; $i <= $to; $i++) { - my $pr = $projects[$i]; + my $pr = $projlist->[$i]; + if ($alternate) { print "<tr class=\"dark\">\n"; } else { print "<tr class=\"light\">\n"; } $alternate ^= 1; + if ($check_forks) { print "<td>"; if ($pr->{'forks'}) { - print "<!-- $pr->{'forks'} -->\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 "</td>\n"; } print "<td>" . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"summary"), - -class => "list"}, esc_html($pr->{'path'})) . "</td>\n" . + -class => "list"}, + esc_html_match_hl($pr->{'path'}, $search_regexp)) . + "</td>\n" . "<td>" . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"summary"), - -class => "list", -title => $pr->{'descr_long'}}, - esc_html($pr->{'descr'})) . "</td>\n" . - "<td><i>" . esc_html(chop_str($pr->{'owner'}, 15)) . "</i></td>\n"; - print "<td class=\"". age_class($pr->{'age'}) . "\">" . - (defined $pr->{'age_string'} ? $pr->{'age_string'} : "No commits") . "</td>\n" . - "<td class=\"link\">" . + -class => "list", + -title => $pr->{'descr_long'}}, + $search_regexp + ? esc_html_match_hl_chopped($pr->{'descr_long'}, + $pr->{'descr'}, $search_regexp) + : esc_html($pr->{'descr'})) . + "</td>\n"; + unless ($omit_owner) { + print "<td><i>" . chop_and_escape_str($pr->{'owner'}, 15) . "</i></td>\n"; + } + unless ($omit_age_column) { + print "<td class=\"". age_class($pr->{'age'}) . "\">" . + (defined $pr->{'age_string'} ? $pr->{'age_string'} : "No commits") . "</td>\n"; + } + print"<td class=\"link\">" . $cgi->a({-href => href(project=>$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") . " | " . @@ -3431,6 +5635,88 @@ sub git_project_list_body { "</td>\n" . "</tr>\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 > $to) { + print "<center>\n". + "<b>No such projects found</b><br />\n". + "Click ".$cgi->a({-href=>href(project=>undef)},"here")." to view all projects<br />\n". + "</center>\n<br />\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($cloud, 64); + } + + print "<table class=\"project_list\">\n"; + unless ($no_header) { + print "<tr>\n"; + if ($check_forks) { + print "<th></th>\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 $omit_age_column; + print "<th></th>\n" . # for links + "</tr>\n"; + } + + if ($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 "<tr>\n"; + if ($check_forks) { + print "<td></td>\n"; + } + print "<td class=\"category\" colspan=\"5\">".esc_html($cat)."</td>\n"; + print "</tr>\n"; + } + + git_project_list_rows($categories{$cat}, undef, undef, $check_forks); + } + } else { + git_project_list_rows(\@projects, $from, $to, $check_forks); + } + if (defined $extra) { print "<tr>\n"; if ($check_forks) { @@ -3442,6 +5728,45 @@ sub git_project_list_body { print "</table>\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, $commit); + git_print_header_div('commit', + "<span class=\"age\">$co{'age_string'}</span>" . + esc_html($co{'title'}) . $ref, + $commit); + print "<div class=\"title_text\">\n" . + "<div class=\"log_link\">\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=>$commit)}, "tree") . + "<br/>\n" . + "</div>\n"; + git_print_authorship(\%co, -tag => 'span'); + print "<br/>\n</div>\n"; + + print "<div class=\"log_body\">\n"; + git_print_log($co{'comment'}, -final_empty_line=> 1); + print "</div>\n"; + } + if ($extra) { + print "<div class=\"page_nav\">\n"; + print "$extra\n"; + print "</div>\n"; + } +} + sub git_shortlog_body { # uses global variable $project my ($commitlist, $from, $to, $refs, $extra) = @_; @@ -3449,7 +5774,7 @@ sub git_shortlog_body { $from = 0 unless defined $from; $to = $#{$commitlist} if (!defined $to || $#{$commitlist} < $to); - print "<table class=\"shortlog\" cellspacing=\"0\">\n"; + print "<table class=\"shortlog\">\n"; my $alternate = 1; for (my $i = $from; $i <= $to; $i++) { my %co = %{$commitlist->[$i]}; @@ -3463,8 +5788,7 @@ sub git_shortlog_body { $alternate ^= 1; # git_summary() used print "<td><i>$co{'age_string'}</i></td>\n" . print "<td title=\"$co{'age_string_age'}\"><i>$co{'age_string_date'}</i></td>\n" . - "<td><i>" . esc_html(chop_str($co{'author_name'}, 10)) . "</i></td>\n" . - "<td>"; + format_author_html('td', \%co, 10) . "<td>"; print format_subject_html($co{'title'}, $co{'title_short'}, href(action=>"commit", hash=>$commit), $ref); print "</td>\n" . @@ -3489,12 +5813,13 @@ sub git_shortlog_body { sub git_history_body { # Warning: assumes constant type (blob or tree) during history - my ($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}); - print "<table class=\"history\" cellspacing=\"0\">\n"; + print "<table class=\"history\">\n"; my $alternate = 1; for (my $i = $from; $i <= $to; $i++) { my %co = %{$commitlist->[$i]}; @@ -3512,9 +5837,8 @@ sub git_history_body { } $alternate ^= 1; print "<td title=\"$co{'age_string_age'}\"><i>$co{'age_string_date'}</i></td>\n" . - # shortlog uses chop_str($co{'author_name'}, 10) - "<td><i>" . esc_html(chop_str($co{'author_name'}, 15, 3)) . "</i></td>\n" . - "<td>"; + # shortlog: format_author_html('td', \%co, 10) + format_author_html('td', \%co, 15, 3) . "<td>"; # originally git_history used chop_str($co{'title'}, 50) print format_subject_html($co{'title'}, $co{'title_short'}, href(action=>"commit", hash=>$commit), $ref); @@ -3524,7 +5848,7 @@ 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); + 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) { @@ -3553,7 +5877,7 @@ sub git_tags_body { $from = 0 unless defined $from; $to = $#{$taglist} if (!defined $to || $#{$taglist} < $to); - print "<table class=\"tags\" cellspacing=\"0\">\n"; + print "<table class=\"tags\">\n"; my $alternate = 1; for (my $i = $from; $i <= $to; $i++) { my $entry = $taglist->[$i]; @@ -3594,8 +5918,8 @@ sub git_tags_body { "<td class=\"link\">" . " | " . $cgi->a({-href => href(action=>$tag{'reftype'}, hash=>$tag{'refid'})}, $tag{'reftype'}); if ($tag{'reftype'} eq "commit") { - print " | " . $cgi->a({-href => href(action=>"shortlog", hash=>$tag{'name'})}, "shortlog") . - " | " . $cgi->a({-href => href(action=>"log", hash=>$tag{'name'})}, "log"); + print " | " . $cgi->a({-href => href(action=>"shortlog", hash=>$tag{'fullname'})}, "shortlog") . + " | " . $cgi->a({-href => href(action=>"log", hash=>$tag{'fullname'})}, "log"); } elsif ($tag{'reftype'} eq "blob") { print " | " . $cgi->a({-href => href(action=>"blob_plain", hash=>$tag{'refid'})}, "raw"); } @@ -3612,16 +5936,16 @@ 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); - print "<table class=\"heads\" cellspacing=\"0\">\n"; + print "<table class=\"heads\">\n"; my $alternate = 1; 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 "<tr class=\"dark\">\n"; } else { @@ -3630,13 +5954,13 @@ sub git_heads_body { $alternate ^= 1; print "<td><i>$ref{'age'}</i></td>\n" . ($curr ? "<td class=\"current_head\">" : "<td>") . - $cgi->a({-href => href(action=>"shortlog", hash=>$ref{'name'}), + $cgi->a({-href => href(action=>"shortlog", hash=>$ref{'fullname'}), -class => "list name"},esc_html($ref{'name'})) . "</td>\n" . "<td class=\"link\">" . - $cgi->a({-href => href(action=>"shortlog", hash=>$ref{'name'})}, "shortlog") . " | " . - $cgi->a({-href => href(action=>"log", hash=>$ref{'name'})}, "log") . " | " . - $cgi->a({-href => href(action=>"tree", hash=>$ref{'name'}, hash_base=>$ref{'name'})}, "tree") . + $cgi->a({-href => href(action=>"shortlog", hash=>$ref{'fullname'})}, "shortlog") . " | " . + $cgi->a({-href => href(action=>"log", hash=>$ref{'fullname'})}, "log") . " | " . + $cgi->a({-href => href(action=>"tree", hash=>$ref{'fullname'}, hash_base=>$ref{'fullname'})}, "tree") . "</td>\n" . "</tr>"; } @@ -3648,12 +5972,318 @@ sub git_heads_body { print "</table>\n"; } +# Display a single remote block +sub git_remote_block { + my ($remote, $rdata, $limit, $head) = @_; + + my $heads = $rdata->{'heads'}; + my $fetch = $rdata->{'fetch'}; + my $push = $rdata->{'push'}; + + my $urls_table = "<table class=\"projects_list\">\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 .= "</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 "<table class=\"heads\">\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 "<tr class=\"dark\">\n"; + } else { + print "<tr class=\"light\">\n"; + } + $alternate ^= 1; + print "<td>" . + $cgi->a({-href=> href(action=>'remotes', hash=>$remote), + -class=> "list name"},esc_html($remote)) . + "</td>"; + print "<td class=\"link\">" . + (defined $fetch ? $cgi->a({-href=> $fetch}, "fetch") : "fetch") . + " | " . + (defined $push ? $cgi->a({-href=> $push}, "push") : "push") . + "</td>"; + + print "</tr>\n"; + } + + if ($limited) { + print "<tr>\n" . + "<td colspan=\"3\">" . + $cgi->a({-href => href(action=>"remotes")}, "...") . + "</td>\n" . "</tr>\n"; + } + + print "</table>"; +} + +# Display remote heads grouped by remote, unless there are too many +# remotes, in which case we only display the remote names +sub git_remotes_body { + my ($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 "<p>No match.</p>\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 "<table class=\"pickaxe search\">\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 "</td>\n" . + "<td class=\"link\">" . + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'})}, + "commit") . + " | " . + $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, + hash_base=>$co{'id'})}, + "tree") . + "</td>\n" . + "</tr>\n"; + } + + if ($alternate) { + print "<tr class=\"dark\">\n"; + } else { + print "<tr class=\"light\">\n"; + } + $alternate ^= 1; + %co = parse_commit($set{'commit'}); + my $author = chop_and_escape_str($co{'author_name'}, 15, 5); + print "<td title=\"$co{'age_string_age'}\"><i>$co{'age_string_date'}</i></td>\n" . + "<td><i>$author</i></td>\n" . + "<td>" . + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), + -class => "list subject"}, + chop_and_escape_str($co{'title'}, 50) . "<br/>"); + } 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"}, + "<span class=\"match\">" . esc_path($set{'file'}) . "</span>") . + "<br/>\n"; + } + } + close $fd; + + # finish last commit (warning: repetition!) + if (%co) { + print "</td>\n" . + "<td class=\"link\">" . + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'})}, + "commit") . + " | " . + $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, + hash_base=>$co{'id'})}, + "tree") . + "</td>\n" . + "</tr>\n"; + } + + print "</table>\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 "<table class=\"grep_search\">\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) { + $lastfile and print "</td></tr>\n"; + if ($alternate++) { + print "<tr class=\"dark\">\n"; + } else { + print "<tr class=\"light\">\n"; + } + $file_href = href(action=>"blob", hash_base=>$co{'id'}, + file_name=>$file); + print "<td class=\"list\">". + $cgi->a({-href => $file_href, -class => "list"}, esc_path($file)); + print "</td><td>\n"; + $lastfile = $file; + } + if ($binary) { + print "<div class=\"binary\">Binary file</div>\n"; + } else { + $ltext = untabify($ltext); + if ($ltext =~ m/^(.*)($search_regexp)(.*)$/i) { + $ltext = esc_html($1, -nbsp=>1); + $ltext .= '<span class="match">'; + $ltext .= esc_html($2, -nbsp=>1); + $ltext .= '</span>'; + $ltext .= esc_html($3, -nbsp=>1); + } else { + $ltext = esc_html($ltext, -nbsp=>1); + } + print "<div class=\"pre\">" . + $cgi->a({-href => $file_href.'#l'.$lno, + -class => "linenr"}, sprintf('%4i', $lno)) . + ' ' . $ltext . "</div>\n"; + } + } + if ($lastfile) { + print "</td></tr>\n"; + if ($matches > 1000) { + print "<div class=\"diff nodifferences\">Too many matches, listing trimmed</div>\n"; + } + } else { + print "<div class=\"diff nodifferences\">No matches found</div>\n"; + } + close $fd; + + print "</table>\n"; + + git_footer_html(); +} + sub git_search_grep_body { my ($commitlist, $from, $to, $extra) = @_; $from = 0 unless defined $from; $to = $#{$commitlist} if (!defined $to || $#{$commitlist} < $to); - print "<table class=\"grep\" cellspacing=\"0\">\n"; + print "<table class=\"commit_search\">\n"; my $alternate = 1; for (my $i = $from; $i <= $to; $i++) { my %co = %{$commitlist->[$i]}; @@ -3668,26 +6298,34 @@ sub git_search_grep_body { } $alternate ^= 1; print "<td title=\"$co{'age_string_age'}\"><i>$co{'age_string_date'}</i></td>\n" . - "<td><i>" . esc_html(chop_str($co{'author_name'}, 15, 5)) . "</i></td>\n" . + format_author_html('td', \%co, 15, 5) . "<td>" . - $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), -class => "list subject"}, - esc_html(chop_str($co{'title'}, 50)) . "<br/>"); + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), + -class => "list subject"}, + chop_and_escape_str($co{'title'}, 50) . "<br/>"); my $comment = $co{'comment'}; foreach my $line (@$comment) { - if ($line =~ m/^(.*)($search_regexp)(.*)$/i) { - my $lead = esc_html($1) || ""; - $lead = chop_str($lead, 30, 10); - my $match = esc_html($2) || ""; - my $trail = esc_html($3) || ""; - $trail = chop_str($trail, 30, 10); - my $text = "$lead<span class=\"match\">$match</span>$trail"; - print chop_str($text, 80, 5) . "<br/>\n"; + if ($line =~ m/^(.*?)($search_regexp)(.*)$/i) { + my ($lead, $match, $trail) = ($1, $2, $3); + $match = chop_str($match, 70, 5, 'center'); + my $contextlen = int((80 - length($match))/2); + $contextlen = 30 if ($contextlen > 30); + $lead = chop_str($lead, $contextlen, 10, 'left'); + $trail = chop_str($trail, $contextlen, 10, 'right'); + + $lead = esc_html($lead); + $match = esc_html($match); + $trail = esc_html($trail); + + print "$lead<span class=\"match\">$match</span>$trail<br />"; } } print "</td>\n" . "<td class=\"link\">" . $cgi->a({-href => href(action=>"commit", hash=>$co{'id'})}, "commit") . " | " . + $cgi->a({-href => href(action=>"commitdiff", hash=>$co{'id'})}, "commitdiff") . + " | " . $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, hash_base=>$co{'id'})}, "tree"); print "</td>\n" . "</tr>\n"; @@ -3705,37 +6343,39 @@ sub git_search_grep_body { ## actions sub git_project_list { - my $order = $cgi->param('o'); + my $order = $input_params{'order'}; if (defined $order && $order !~ m/none|project|descr|owner|age/) { - die_error(undef, "Unknown order parameter"); + die_error(400, "Unknown order parameter"); } - my @list = git_get_projects_list(); + my @list = git_get_projects_list($project_filter, $strict_export); if (!@list) { - die_error(undef, "No projects found"); + die_error(404, "No projects found"); } git_header_html(); - if (-f $home_text) { + if (defined $home_text && -f $home_text) { print "<div class=\"index_include\">\n"; - open (my $fd, $home_text); - print <$fd>; - close $fd; + insert_file($home_text); print "</div>\n"; } + + git_project_search_form($searchtext, $search_use_regexp); git_project_list_body(\@list, $order); git_footer_html(); } sub git_forks { - my $order = $cgi->param('o'); + my $order = $input_params{'order'}; if (defined $order && $order !~ m/none|project|descr|owner|age/) { - die_error(undef, "Unknown order parameter"); + die_error(400, "Unknown order parameter"); } - my @list = git_get_projects_list($project); + my $filter = $project; + $filter =~ s/\.git$//; + my @list = git_get_projects_list($filter); if (!@list) { - die_error(undef, "No forks found"); + die_error(404, "No forks found"); } git_header_html(); @@ -3746,7 +6386,10 @@ sub git_forks { } sub git_project_index { - my @projects = git_get_projects_list($project); + my @projects = git_get_projects_list($project_filter, $strict_export); + if (!@projects) { + die_error(404, "No projects found"); + } print $cgi->header( -type => 'text/plain', @@ -3774,6 +6417,7 @@ sub git_summary { my %co = parse_commit("HEAD"); my %cd = %co ? parse_date($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); @@ -3782,22 +6426,32 @@ 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(); git_print_page_nav('summary','', $head); print "<div class=\"title\"> </div>\n"; - print "<table cellspacing=\"0\">\n" . - "<tr><td>description</td><td>" . esc_html($descr) . "</td></tr>\n" . - "<tr><td>owner</td><td>" . esc_html($owner) . "</td></tr>\n"; + print "<table class=\"projects_list\">\n" . + "<tr id=\"metadata_desc\"><td>description</td><td>" . esc_html($descr) . "</td></tr>\n"; + unless ($omit_owner) { + print "<tr id=\"metadata_owner\"><td>owner</td><td>" . esc_html($owner) . "</td></tr>\n"; + } if (defined $cd{'rfc2822'}) { - print "<tr><td>last change</td><td>$cd{'rfc2822'}</td></tr>\n"; + print "<tr id=\"metadata_lchange\"><td>last change</td>" . + "<td>".format_timestamp_html(\%cd)."</td></tr>\n"; } # use per project git URL list in $projectroot/$project/cloneurl @@ -3807,19 +6461,35 @@ sub git_summary { @url_list = map { "$_/$project" } @git_base_url_list unless @url_list; foreach my $git_url (@url_list) { next unless $git_url; - print "<tr><td>$url_tag</td><td>$git_url</td></tr>\n"; + print format_repo_url($url_tag, $git_url); $url_tag = ""; } - print "</table>\n"; - if (-s "$projectroot/$project/README.html") { - if (open my $fd, "$projectroot/$project/README.html") { - print "<div class=\"title\">readme</div>\n"; - print $_ while (<$fd>); - close $fd; + # Tag cloud + my $show_ctags = gitweb_check_feature('ctags'); + if ($show_ctags) { + my $ctags = git_get_project_ctags($project); + if (%$ctags) { + # without ability to add tags, don't show if there are none + my $cloud = git_populate_project_tagcloud($ctags); + print "<tr id=\"metadata_ctags\">" . + "<td>content tags</td>" . + "<td>".git_show_project_tagcloud($cloud, 48)."</td>" . + "</tr>\n"; } } + print "</table>\n"; + + # If XSS prevention is on, we don't include README.html. + # TODO: Allow a readme in some safe format. + if (!$prevent_xss && -s "$projectroot/$project/README.html") { + print "<div class=\"title\">readme</div>\n" . + "<div class=\"readme\">\n"; + insert_file("$projectroot/$project/README.html"); + print "\n</div>\n"; # class="readme" + } + # we need to request one more than 16 (0..15) to check if # those 16 are all my @commitlist = $head ? parse_commits($head, 17) : (); @@ -3844,30 +6514,35 @@ 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, undef, 0, 15, + git_project_list_body(\@forklist, 'age', 0, 15, $#forklist <= 15 ? undef : $cgi->a({-href => href(action=>"forks")}, "..."), - 'noheader'); + 'no_header'); } git_footer_html(); } 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(undef, "Unknown tag object"); + 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 "<div class=\"title_text\">\n" . - "<table cellspacing=\"0\">\n" . + "<table class=\"object_header\">\n" . "<tr>\n" . "<td>object</td>\n" . "<td>" . $cgi->a({-class => "list", -href => href(action=>$tag{'type'}, hash=>$tag{'object'})}, @@ -3876,11 +6551,7 @@ sub git_tag { $tag{'type'}) . "</td>\n" . "</tr>\n"; if (defined($tag{'author'})) { - my %ad = parse_date($tag{'epoch'}, $tag{'tz'}); - print "<tr><td>author</td><td>" . esc_html($tag{'author'}) . "</td></tr>\n"; - print "<tr><td></td><td>" . $ad{'rfc2822'} . - sprintf(" (%02d:%02d %s)", $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}) . - "</td></tr>\n"; + git_print_authorship_rows(\%tag, 'author'); } print "</table>\n\n" . "</div>\n"; @@ -3894,215 +6565,254 @@ sub git_tag { git_footer_html(); } -sub git_blame2 { - my $fd; - my $ftype; - - my ($have_blame) = gitweb_check_feature('blame'); - if (!$have_blame) { - die_error('403 Permission denied', "Permission denied"); +sub git_blame_common { + my $format = shift || 'porcelain'; + if ($format eq 'porcelain' && $input_params{'javascript'}) { + $format = 'incremental'; + $action = 'blame_incremental'; # for page title etc } - die_error('404 Not Found', "File name not defined") if (!$file_name); + + # permissions + gitweb_check_feature('blame') + 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(undef, "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(undef, "Reading commit failed"); + 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(undef, "Error looking up file"); + 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"); + } + } + + 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"); } - $ftype = git_get_type($hash); - if ($ftype !~ "blob") { - die_error('400 Bad Request', "Object is not a blob"); + + # incremental blame data returns early + if ($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() ]). + ' '.$number_of_git_cmds; + } + print "\n"; + + return; } - open ($fd, "-|", git_cmd(), "blame", '-p', '--', - $file_name, $hash_base) - or die_error(undef, "Open git-blame failed"); + + # page header git_header_html(); my $formats_nav = - $cgi->a({-href => href(action=>"blob", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name)}, + $cgi->a({-href => href(action=>"blob", -replay=>1)}, "blob") . + " | "; + if ($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 .= " | " . - $cgi->a({-href => href(action=>"history", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name)}, - "history") . + $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 "<noscript>\n<div class=\"error\"><center><b>\n". + "This page requires JavaScript to run.\n Use ". + $cgi->a({-href => href(action=>'blame',javascript=>0,-replay=>1)}, + 'this page'). + " instead.\n". + "</b></center></div>\n</noscript>\n"; + + print qq!<div id="progress_bar" style="width: 100%; background-color: yellow"></div>\n!; + } + + print qq!<div class="page_body">\n!; + print qq!<div id="progress_info">... / ...</div>\n! + if ($format eq 'incremental'); + print qq!<table id="blame_table" class="blame" width="100%">\n!. + #qq!<col width="5.5em" /><col width="2.5em" /><col width="*" />\n!. + qq!<thead>\n!. + qq!<tr><th>Commit</th><th>Line</th><th>Data</th></tr>\n!. + qq!</thead>\n!. + qq!<tbody>\n!; + + my @rev_color = qw(light dark); my $num_colors = scalar(@rev_color); my $current_color = 0; - my $last_rev; - print <<HTML; -<div class="page_body"> -<table class="blame"> -<tr><th>Commit</th><th>Line</th><th>Data</th></tr> -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 % $num_colors; - } - print "<tr class=\"$rev_color[$current_color]\">\n"; - if ($group_size) { - print "<td class=\"sha1\""; - print " title=\"". esc_html($author) . ", $date\""; - print " rowspan=\"$group_size\"" if ($group_size > 1); - print ">"; - print $cgi->a({-href => href(action=>"commit", - hash=>$full_rev, - file_name=>$file_name)}, - esc_html($rev)); - print "</td>\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; + $linenr++; + + print qq!<tr id="l$linenr" class="$color_class">!. + qq!<td class="sha1"><a href=""> </a></td>!. + qq!<td class="linenr">!. + qq!<a class="linenr" href="">$linenr</a></td>!; + print qq!<td class="pre">! . esc_html($line) . "</td>\n"; + print qq!</tr>\n!; } - open (my $dd, "-|", git_cmd(), "rev-parse", "$full_rev^") - or die_error(undef, "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 "<td class=\"linenr\">"; - print $cgi->a({ -href => "$blamed#l$orig_lineno", - -id => "l$lineno", - -class => "linenr" }, - esc_html($lineno)); - print "</td>"; - print "<td class=\"pre\">" . esc_html($data) . "</td>\n"; - print "</tr>\n"; + + } else { # porcelain, i.e. ordinary blame + my %metainfo = (); # saves information about commits + + # blame data + LINE: + while (my $line = <$fd>) { + chomp $line; + # the header: <SHA-1> <src lineno> <dst lineno> [<lines in group>] + # no <lines in group> for subsequent lines in group of lines + my ($full_rev, $orig_lineno, $lineno, $group_size) = + ($line =~ /^([0-9a-f]{40}) (\d+) (\d+)(?: (\d+))?$/); + 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 "<tr id=\"l$lineno\" class=\"$tr_class\">\n"; + if ($group_size) { + print "<td class=\"sha1\""; + print " title=\"". esc_html($author) . ", $date\""; + print " rowspan=\"$group_size\"" if ($group_size > 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 "<br />" . + esc_html(join('', @author_initials)); + # or join('.', ...) + } + } + print "</td>\n"; + } + # 'previous' <sha1 of parent commit> <filename at commit> + if (exists $meta->{'previous'} && + $meta->{'previous'} =~ /^([a-fA-F0-9]{40}) (.*)$/) { + $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 "<td class=\"linenr\">"; + print $cgi->a({ -href => "$blamed#l$orig_lineno", + -class => "linenr" }, + esc_html($lineno)); + print "</td>"; + print "<td class=\"pre\">" . esc_html($data) . "</td>\n"; + print "</tr>\n"; + } # end while + } - print "</table>\n"; - print "</div>"; + + # footer + print "</tbody>\n". + "</table>\n"; # class="blame" + print "</div>\n"; # class="blame_body" close $fd or print "Reading blob failed\n"; + git_footer_html(); } sub git_blame { - my $fd; + git_blame_common(); +} - my ($have_blame) = gitweb_check_feature('blame'); - if (!$have_blame) { - die_error('403 Permission denied', "Permission denied"); - } - die_error('404 Not Found', "File name not defined") if (!$file_name); - $hash_base ||= git_get_head_hash($project); - die_error(undef, "Couldn't find base commit") unless ($hash_base); - my %co = parse_commit($hash_base) - or die_error(undef, "Reading commit failed"); - if (!defined $hash) { - $hash = git_get_hash_by_path($hash_base, $file_name, "blob") - or die_error(undef, "Error lookup file"); - } - open ($fd, "-|", git_cmd(), "annotate", '-l', '-t', '-r', $file_name, $hash_base) - or die_error(undef, "Open git-annotate failed"); - git_header_html(); - my $formats_nav = - $cgi->a({-href => href(action=>"blob", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name)}, - "blob") . - " | " . - $cgi->a({-href => href(action=>"history", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name)}, - "history") . - " | " . - $cgi->a({-href => href(action=>"blame", file_name=>$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, 'blob', $hash_base); - print "<div class=\"page_body\">\n"; - print <<HTML; -<table class="blame"> - <tr> - <th>Commit</th> - <th>Age</th> - <th>Author</th> - <th>Line</th> - <th>Data</th> - </tr> -HTML - my @line_class = (qw(light dark)); - my $line_class_len = scalar (@line_class); - my $line_class_num = $#line_class; - while (my $line = <$fd>) { - my $long_rev; - my $short_rev; - my $author; - my $time; - my $lineno; - my $data; - my $age; - my $age_str; - my $age_class; +sub git_blame_incremental { + git_blame_common('incremental'); +} - chomp $line; - $line_class_num = ($line_class_num + 1) % $line_class_len; - - if ($line =~ m/^([0-9a-fA-F]{40})\t\(\s*([^\t]+)\t(\d+) [+-]\d\d\d\d\t(\d+)\)(.*)$/) { - $long_rev = $1; - $author = $2; - $time = $3; - $lineno = $4; - $data = $5; - } else { - print qq( <tr><td colspan="5" class="error">Unable to parse: $line</td></tr>\n); - next; - } - $short_rev = substr ($long_rev, 0, 8); - $age = time () - $time; - $age_str = age_string ($age); - $age_str =~ s/ / /g; - $age_class = age_class($age); - $author = esc_html ($author); - $author =~ s/ / /g; - - $data = untabify($data); - $data = esc_html ($data); - - print <<HTML; - <tr class="$line_class[$line_class_num]"> - <td class="sha1"><a href="${\href (action=>"commit", hash=>$long_rev)}" class="text">$short_rev..</a></td> - <td class="$age_class">$age_str</td> - <td>$author</td> - <td class="linenr"><a id="$lineno" href="#$lineno" class="linenr">$lineno</a></td> - <td class="pre">$data</td> - </tr> -HTML - } # while (my $line = <$fd>) - print "</table>\n\n"; - close $fd - or print "Reading blob failed.\n"; - print "</div>"; - git_footer_html(); +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(); @@ -4115,7 +6825,7 @@ 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(); @@ -4125,29 +6835,63 @@ 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; if (!defined $hash) { if (defined $file_name) { my $base = $hash_base || git_get_head_hash($project); $hash = git_get_hash_by_path($base, $file_name, "blob") - or die_error(undef, "Error lookup file"); + or die_error(404, "Cannot find file"); } else { - die_error(undef, "No file name defined"); + die_error(400, "No file name defined"); } } elsif ($hash =~ m/^[0-9a-fA-F]{40}$/) { # blobs defined by non-textual hash id's can be cached $expires = "+1d"; } - my $type = shift; open my $fd, "-|", git_cmd(), "cat-file", "blob", $hash - or die_error(undef, "Couldn't cat $file_name, $hash"); + or die_error(500, "Open git-cat-file blob '$hash' failed"); - $type ||= blob_mimetype($fd, $file_name); + # content-type (can include charset) + $type = blob_contenttype($fd, $file_name, $type); - # save as filename, even when no $file_name is given + # "save as" filename, even when no $file_name is given my $save_as = "$hash"; if (defined $file_name) { $save_as = $file_name; @@ -4155,15 +6899,34 @@ 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 <img> 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 $/; + -type => $type, + -expires => $expires, + -content_disposition => + ($sandbox ? 'attachment' : 'inline') + . '; filename="' . $save_as . '"'); + local $/ = undef; binmode STDOUT, ':raw'; print <$fd>; binmode STDOUT, ':utf8'; # as set at the beginning of gitweb.cgi - $/ = "\n"; close $fd; } @@ -4174,44 +6937,47 @@ sub git_blob { if (defined $file_name) { my $base = $hash_base || git_get_head_hash($project); $hash = git_get_hash_by_path($base, $file_name, "blob") - or die_error(undef, "Error lookup file"); + or die_error(404, "Cannot find file"); } else { - die_error(undef, "No file name defined"); + die_error(400, "No file name defined"); } } elsif ($hash =~ m/^[0-9a-fA-F]{40}$/) { # 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(undef, "Couldn't cat $file_name, $hash"); + or die_error(500, "Couldn't cat $file_name, $hash"); my $mimetype = blob_mimetype($fd, $file_name); - if ($mimetype !~ m!^(?:text/|image/(?:gif|png|jpeg)$)!) { + # use 'blob_plain' (aka 'raw') view for files that cannot be displayed + if ($mimetype !~ m!^(?:text/|image/(?:gif|png|jpeg)$)! && -B $fd) { close $fd; return git_blob_plain($mimetype); } # 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, $mimetype, $file_name); + $fd = run_highlighter($fd, $highlight, $syntax) + if $syntax; + git_header_html(undef, $expires); my $formats_nav = ''; if (defined $hash_base && (my %co = parse_commit($hash_base))) { if (defined $file_name) { if ($have_blame) { $formats_nav .= - $cgi->a({-href => href(action=>"blame", hash_base=>$hash_base, - hash=>$hash, file_name=>$file_name)}, + $cgi->a({-href => href(action=>"blame", -replay=>1)}, "blame") . " | "; } $formats_nav .= - $cgi->a({-href => href(action=>"history", hash_base=>$hash_base, - hash=>$hash, file_name=>$file_name)}, + $cgi->a({-href => href(action=>"history", -replay=>1)}, "history") . " | " . - $cgi->a({-href => href(action=>"blob_plain", - hash=>$hash, file_name=>$file_name)}, + $cgi->a({-href => href(action=>"blob_plain", -replay=>1)}, "raw") . " | " . $cgi->a({-href => href(action=>"blob", @@ -4219,35 +6985,37 @@ sub git_blob { "HEAD"); } else { $formats_nav .= - $cgi->a({-href => href(action=>"blob_plain", hash=>$hash)}, "raw"); + $cgi->a({-href => href(action=>"blob_plain", -replay=>1)}, + "raw"); } git_print_page_nav('','', $hash_base,$co{'tree'},$hash_base, $formats_nav); git_print_header_div('commit', esc_html($co{'title'}), $hash_base); } else { print "<div class=\"page_nav\">\n" . "<br/><br/></div>\n" . - "<div class=\"title\">$hash</div>\n"; + "<div class=\"title\">".esc_html($hash)."</div>\n"; } git_print_page_path($file_name, "blob", $hash_base); print "<div class=\"page_body\">\n"; - if ($mimetype =~ m!^text/!) { - my $nr; - while (my $line = <$fd>) { - chomp $line; - $nr++; - $line = untabify($line); - printf "<div class=\"pre\"><a id=\"l%i\" href=\"#l%i\" class=\"linenr\">%4i</a> %s</div>\n", - $nr, $nr, $nr, esc_html($line, -nbsp=>1); - } - } elsif ($mimetype =~ m!^image/!) { - print qq!<img type="$mimetype"!; + if ($mimetype =~ m!^image/!) { + print qq!<img type="!.esc_attr($mimetype).qq!"!; if ($file_name) { - print qq! alt="$file_name" title="$file_name"!; + print qq! alt="!.esc_attr($file_name).qq!" title="!.esc_attr($file_name).qq!"!; } print qq! src="! . href(action=>"blob_plain", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name) . qq!" />\n!; + } else { + my $nr; + while (my $line = <$fd>) { + chomp $line; + $nr++; + $line = untabify($line); + printf qq!<div class="pre"><a id="l%i" href="%s#l%i" class="linenr">%4i</a> %s</div>\n!, + $nr, esc_attr(href(-replay => 1)), $nr, $nr, + $syntax ? sanitize($line) : esc_html($line, -nbsp=>1); + } } close $fd or print "Reading blob failed.\n"; @@ -4266,24 +7034,31 @@ sub git_tree { $hash = $hash_base; } } - $/ = "\0"; - open my $fd, "-|", git_cmd(), "ls-tree", '-z', $hash - or die_error(undef, "Open git-ls-tree failed"); - my @entries = map { chomp; $_ } <$fd>; - close $fd or die_error(undef, "Reading tree failed"); - $/ = "\n"; + die_error(404, "No such tree") unless defined($hash); + + 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) { push @views_nav, - $cgi->a({-href => href(action=>"history", hash_base=>$hash_base, - hash=>$hash, file_name=>$file_name)}, + $cgi->a({-href => href(action=>"history", -replay=>1)}, "history"), $cgi->a({-href => href(action=>"tree", hash_base=>"HEAD", file_name=>$file_name)}, @@ -4294,23 +7069,24 @@ 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 $hash_base; print "<div class=\"page_nav\">\n"; print "<br/><br/></div>\n"; - print "<div class=\"title\">$hash</div>\n"; + print "<div class=\"title\">".esc_html($hash)."</div>\n"; } if (defined $file_name) { $basedir = $file_name; if ($basedir ne '' && substr($basedir, -1) ne '/') { $basedir .= '/'; } + git_print_page_path($file_name, 'tree', $hash_base); } - git_print_page_path($file_name, 'tree', $hash_base); print "<div class=\"page_body\">\n"; - print "<table cellspacing=\"0\">\n"; + print "<table class=\"tree\">\n"; my $alternate = 1; # '..' (top directory) link if possible if (defined $hash_base && @@ -4327,8 +7103,10 @@ sub git_tree { undef $up unless $up; # based on git_print_tree_entry print '<td class="mode">' . mode_str('040000') . "</td>\n"; + print '<td class="size"> </td>'."\n" if $show_sizes; print '<td class="list">'; - 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 "</td>\n"; @@ -4337,7 +7115,7 @@ sub git_tree { print "</tr>\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 "<tr class=\"dark\">\n"; @@ -4355,123 +7133,206 @@ sub git_tree { git_footer_html(); } -sub git_snapshot { - my @supported_fmts = gitweb_check_feature('snapshot'); - @supported_fmts = filter_snapshot_fmts(@supported_fmts); +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,; + $name = basename($name); + # sanitize name + $name =~ s/[[:cntrl:]]/?/g; + + 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 = $1; + } else { + # branches and other need shortened SHA-1 hash + if ($hash =~ m!^refs/(?:heads|remotes)/(.*)$!) { + $ver = $1; + } + $ver .= '-' . git_get_short_hash($project, $hash); + } + # in case of hierarchical branch names + $ver =~ s!/!.!g; - my $format = $cgi->param('sf'); - if (!@supported_fmts) { - die_error('403 Permission denied', "Permission denied"); + # 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) { + die_error(403, "Snapshots not allowed"); } # default to first supported snapshot format - $format ||= $supported_fmts[0]; + $format ||= $snapshot_fmts[0]; if ($format !~ m/^[a-z0-9]+$/) { - die_error(undef, "Invalid snapshot format parameter"); + die_error(400, "Invalid snapshot format parameter"); } elsif (!exists($known_snapshot_formats{$format})) { - die_error(undef, "Unknown snapshot format"); - } elsif (!grep($_ eq $format, @supported_fmts)) { - die_error(undef, "Unsupported snapshot format"); + die_error(400, "Unknown snapshot format"); + } elsif ($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 $git_command = git_cmd_str(); - 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'}"; - $cmd = "$git_command archive " . - "--format=$known_snapshot_formats{$format}{'format'} " . - "--prefix=\'$name\'/ $hash"; + my ($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{$format}{'format'}", + "--prefix=$prefix/", $hash); if (exists $known_snapshot_formats{$format}{'compressor'}) { - $cmd .= ' | ' . join ' ', @{$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, "-|", $cmd - or die_error(undef, "Execute git-archive failed"); + or die_error(500, "Execute git-archive failed"); binmode STDOUT, ':raw'; print <$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, $page, (100 * ($page+1))); + 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 "<div class=\"page_body\"> Last change $co{'age_string'}.<br/><br/></div>\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', - "<span class=\"age\">$co{'age_string'}</span>" . - esc_html($co{'title'}) . $ref, - $commit); - print "<div class=\"title_text\">\n" . - "<div class=\"log_link\">\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=>$commit)}, "tree") . - "<br/>\n" . - "</div>\n" . - "<i>" . esc_html($co{'author_name'}) . " [$ad{'rfc2822'}]</i><br/>\n" . - "</div>\n"; - - print "<div class=\"log_body\">\n"; - git_print_log($co{'comment'}, -final_empty_line=> 1); - print "</div>\n"; + my $patch_max = gitweb_get_feature('patches'); + if ($patch_max && !defined $file_name) { + if ($patch_max < 0 || @commitlist <= $patch_max) { + $paging_nav .= " ⋅ " . + $cgi->a({-href => href(action=>"patches", -replay=>1)}, + "patches"); + } } - if ($#commitlist >= 100) { - print "<div class=\"page_nav\">\n"; - print $cgi->a({-href => href(action=>"log", hash=>$hash, page=>$page+1), - -accesskey => "n", -title => "Alt-n"}, "next"); - print "</div>\n"; + + git_header_html(); + git_print_page_nav($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); - if (!%co) { - die_error(undef, "Unknown commit object"); - } - my %ad = parse_date($co{'author_epoch'}, $co{'author_tz'}); - my %cd = parse_date($co{'committer_epoch'}, $co{'committer_tz'}); + my %co = parse_commit($hash) + or die_error(404, "Unknown commit object"); my $parent = $co{'parent'}; my $parents = $co{'parents'}; # listref @@ -4500,6 +7361,11 @@ sub git_commit { } @$parents ) . ')'; } + if (gitweb_check_feature('patches') && @$parents <= 1) { + $formats_nav .= " | " . + $cgi->a({-href => href(action=>"patch", -replay=>1)}, + "patch"); + } if (!defined $parent) { $parent = "--root"; @@ -4509,9 +7375,9 @@ sub git_commit { @diff_opts, (@$parents <= 1 ? $parent : '-c'), $hash, "--" - or die_error(undef, "Open git-diff-tree failed"); + or die_error(500, "Open git-diff-tree failed"); @difftree = map { chomp; $_ } <$fd>; - close $fd or die_error(undef, "Reading git-diff-tree failed"); + close $fd or die_error(404, "Reading git-diff-tree failed"); # non-textual hash id's can be cached my $expires; @@ -4532,23 +7398,8 @@ sub git_commit { git_print_header_div('tree', esc_html($co{'title'}) . $ref, $co{'tree'}, $hash); } print "<div class=\"title_text\">\n" . - "<table cellspacing=\"0\">\n"; - print "<tr><td>author</td><td>" . esc_html($co{'author'}) . "</td></tr>\n". - "<tr>" . - "<td></td><td> $ad{'rfc2822'}"; - if ($ad{'hour_local'} < 6) { - printf(" (<span class=\"atnight\">%02d:%02d</span> %s)", - $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); - } else { - printf(" (%02d:%02d %s)", - $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); - } - print "</td>" . - "</tr>\n"; - print "<tr><td>committer</td><td>" . esc_html($co{'committer'}) . "</td></tr>\n"; - print "<tr><td></td><td> $cd{'rfc2822'}" . - sprintf(" (%02d:%02d %s)", $cd{'hour_local'}, $cd{'minute_local'}, $cd{'tz_local'}) . - "</td></tr>\n"; + "<table class=\"object_header\">\n"; + git_print_authorship_rows(\%co); print "<tr><td>commit</td><td class=\"sha1\">$co{'id'}</td></tr>\n"; print "<tr>" . "<td>tree</td>" . @@ -4602,35 +7453,35 @@ sub git_object { if ($hash || ($hash_base && !defined $file_name)) { my $object_id = $hash || $hash_base; - my $git_command = git_cmd_str(); - open my $fd, "-|", "$git_command cat-file -t $object_id 2>/dev/null" - or die_error('404 Not Found', "Object does not exist"); + open my $fd, "-|", quote_command( + git_cmd(), 'cat-file', '-t', $object_id) . ' 2> /dev/null' + or die_error(404, "Object does not exist"); $type = <$fd>; chomp $type; close $fd - or die_error('404 Not Found', "Object does not exist"); + or die_error(404, "Object does not exist"); # - hash_base and file_name } elsif ($hash_base && defined $file_name) { $file_name =~ s,/+$,,; system(git_cmd(), "cat-file", '-e', $hash_base) == 0 - or die_error('404 Not Found', "Base object does not exist"); + or die_error(404, "Base object does not exist"); # here errors should not hapen open my $fd, "-|", git_cmd(), "ls-tree", $hash_base, "--", $file_name - or die_error(undef, "Open git-ls-tree failed"); + 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/) { - die_error('404 Not Found', "File or directory for given base does not exist"); + die_error(404, "File or directory for given base does not exist"); } $type = $2; $hash = $3; } else { - die_error('404 Not Found', "Not enough information to find object"); + die_error(400, "Not enough information to find object"); } print $cgi->redirect(-uri => href(action=>$type, -full=>1, @@ -4641,6 +7492,7 @@ sub git_object { sub git_blobdiff { my $format = shift || 'html'; + my $diff_style = $input_params{'diff_style'} || 'inline'; my $fd; my @difftree; @@ -4655,12 +7507,12 @@ sub git_blobdiff { open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, $hash_parent_base, $hash_base, "--", (defined $file_parent ? $file_parent : ()), $file_name - or die_error(undef, "Open git-diff-tree failed"); + or die_error(500, "Open git-diff-tree failed"); @difftree = map { chomp; $_ } <$fd>; close $fd - or die_error(undef, "Reading git-diff-tree failed"); + or die_error(404, "Reading git-diff-tree failed"); @difftree - or die_error('404 Not Found', "Blob diff not found"); + or die_error(404, "Blob diff not found"); } elsif (defined $hash && $hash =~ /[0-9a-fA-F]{40}/) { @@ -4669,28 +7521,28 @@ sub git_blobdiff { # read filtered raw output open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, $hash_parent_base, $hash_base, "--" - or die_error(undef, "Open git-diff-tree failed"); + or die_error(500, "Open git-diff-tree failed"); @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/ } map { chomp; $_ } <$fd>; close $fd - or die_error(undef, "Reading git-diff-tree failed"); + or die_error(404, "Reading git-diff-tree failed"); @difftree - or die_error('404 Not Found', "Blob diff not found"); + or die_error(404, "Blob diff not found"); } else { - die_error('404 Not Found', "Missing one of the blob diff parameters"); + die_error(400, "Missing one of the blob diff parameters"); } if (@difftree > 1) { - die_error('404 Not Found', "Ambiguous blob diff specification"); + die_error(400, "Ambiguous blob diff specification"); } %diffinfo = parse_difftree_raw_line($difftree[0]); - $file_parent ||= $diffinfo{'from_file'} || $file_name || $diffinfo{'file'}; - $file_name ||= $diffinfo{'to_file'} || $diffinfo{'file'}; + $file_parent ||= $diffinfo{'from_file'} || $file_name; + $file_name ||= $diffinfo{'to_file'}; $hash_parent ||= $diffinfo{'from_id'}; $hash ||= $diffinfo{'to_id'}; @@ -4706,63 +7558,27 @@ sub git_blobdiff { '-p', ($format eq 'html' ? "--full-index" : ()), $hash_parent_base, $hash_base, "--", (defined $file_parent ? $file_parent : ()), $file_name - or die_error(undef, "Open git-diff-tree failed"); + 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, $hash, "--" - or die_error(undef, "Open git-diff failed"); - } else { + # old/legacy style URI -- not generated anymore since 1.4.3. + if (!%diffinfo) { die_error('404 Not Found', "Missing one of the blob diff parameters") - unless %diffinfo; } # header if ($format eq 'html') { my $formats_nav = - $cgi->a({-href => href(action=>"blobdiff_plain", - hash=>$hash, hash_parent=>$hash_parent, - hash_base=>$hash_base, hash_parent_base=>$hash_parent_base, - file_name=>$file_name, file_parent=>$file_parent)}, + $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'}), $hash_base); } else { print "<div class=\"page_nav\"><br/>$formats_nav<br/></div>\n"; - print "<div class=\"title\">$hash vs $hash_parent</div>\n"; + print "<div class=\"title\">".esc_html("$hash vs $hash_parent")."</div>\n"; } if (defined $file_name) { git_print_page_path($file_name, "blob", $hash_base); @@ -4780,14 +7596,15 @@ sub git_blobdiff { print "X-Git-Url: " . $cgi->self_url() . "\n\n"; } else { - die_error(undef, "Unknown blobdiff format"); + die_error(400, "Unknown blobdiff format"); } # patch if ($format eq 'html') { print "<div class=\"page_body\">\n"; - git_patchset_body($fd, [ \%diffinfo ], $hash_base, $hash_parent_base); + git_patchset_body($fd, $diff_style, + [ \%diffinfo ], $hash_base, $hash_parent_base); close $fd; print "</div>\n"; # class="page_body" @@ -4812,14 +7629,41 @@ sub git_blobdiff_plain { git_blobdiff('plain'); } +# assumes that it is added as later part of already existing navigation, +# so it returns "| foo | bar" rather than just "foo | bar" +sub diff_style_nav { + my ($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'; - $hash ||= $hash_base || "HEAD"; - my %co = parse_commit($hash); - if (!%co) { - die_error(undef, "Unknown commit object"); + 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"); + # choose format for commitdiff for merge if (! defined $hash_parent && @{$co{'parents'}} > 1) { $hash_parent = '--cc'; @@ -4828,9 +7672,14 @@ sub git_commitdiff { my $formats_nav; if ($format eq 'html') { $formats_nav = - $cgi->a({-href => href(action=>"commitdiff_plain", - hash=>$hash, hash_parent=>$hash_parent)}, + $cgi->a({-href => href(action=>"commitdiff_plain", -replay=>1)}, "raw"); + if ($patch_max && @{$co{'parents'}} <= 1) { + $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') { @@ -4848,8 +7697,8 @@ 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'}) { @@ -4859,28 +7708,28 @@ 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'}} ) . ')'; @@ -4901,7 +7750,7 @@ sub git_commitdiff { open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, "--no-commit-id", "--patch-with-raw", "--full-index", $hash_parent_param, $hash, "--" - or die_error(undef, "Open git-diff-tree failed"); + or die_error(500, "Open git-diff-tree failed"); while (my $line = <$fd>) { chomp $line; @@ -4913,10 +7762,34 @@ sub git_commitdiff { } elsif ($format eq 'plain') { open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, '-p', $hash_parent_param, $hash, "--" - or die_error(undef, "Open git-diff-tree failed"); - + or die_error(500, "Open git-diff-tree failed"); + } elsif ($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(undef, "Unknown commitdiff format"); + die_error(400, "Unknown commitdiff format"); } # non-textual hash id's can be cached @@ -4933,7 +7806,11 @@ 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, $hash); - git_print_authorship(\%co); + print "<div class=\"title_text\">\n" . + "<table class=\"object_header\">\n"; + git_print_authorship_rows(\%co); + print "</table>". + "</div>\n"; print "<div class=\"page_body\">\n"; if (@{$co{'comment'}} > 1) { print "<div class=\"log\">\n"; @@ -4952,18 +7829,25 @@ sub git_commitdiff { -expires => $expires, -content_disposition => 'inline; filename="' . "$filename" . '"'); my %ad = parse_date($co{'author_epoch'}, $co{'author_tz'}); - print <<TEXT; -From: $co{'author'} -Date: $ad{'rfc2822'} ($ad{'tz_local'}) -Subject: $co{'title'} -TEXT + print "From: " . to_utf8($co{'author'}) . "\n"; + print "Date: $ad{'rfc2822'} ($ad{'tz_local'})\n"; + print "Subject: " . to_utf8($co{'title'}) . "\n"; + print "X-Git-Tag: $tagname\n" if $tagname; print "X-Git-Url: " . $cgi->self_url() . "\n\n"; foreach my $line (@{$co{'comment'}}) { - print "$line\n"; + print to_utf8($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 @@ -4974,7 +7858,8 @@ TEXT $use_parents ? @{$co{'parents'}} : $hash_parent); print "<br/>\n"; - git_patchset_body($fd, \@difftree, $hash, + git_patchset_body($fd, $diff_style, + \@difftree, $hash, $use_parents ? @{$co{'parents'}} : $hash_parent); close $fd; print "</div>\n"; # class="page_body" @@ -4985,334 +7870,116 @@ TEXT print <$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); - if (!%co) { - die_error(undef, "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'); +} - if (!defined $hash && defined $file_name) { - $hash = git_get_hash_by_path($hash_base, $file_name); - } - if (defined $hash) { - $ftype = git_get_type($hash); - } +sub git_history { + git_log_generic('history', \&git_history_body, + $hash_base, $hash_parent_base, + $file_name, $hash); +} - my @commitlist = parse_commits($hash_base, 101, (100 * $page), "--full-history", $file_name); +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 .= " ⋅ " . - $cgi->a({-href => href(action=>"history", hash=>$hash, hash_base=>$hash_base, - file_name=>$file_name, page=>$page-1), - -accesskey => "p", -title => "Alt-p"}, "prev"); - } else { - $paging_nav .= "first"; - $paging_nav .= " ⋅ prev"; - } - if ($#commitlist >= 100) { - $paging_nav .= " ⋅ " . - $cgi->a({-href => href(action=>"history", hash=>$hash, hash_base=>$hash_base, - file_name=>$file_name, page=>$page+1), - -accesskey => "n", -title => "Alt-n"}, "next"); - } else { - $paging_nav .= " ⋅ next"; + # check if appropriate features are enabled + gitweb_check_feature('search') + or die_error(403, "Search is disabled"); + if ($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 = - $cgi->a({-href => href(action=>"history", hash=>$hash, hash_base=>$hash_base, - file_name=>$file_name, page=>$page+1), - -accesskey => "n", -title => "Alt-n"}, "next"); + if ($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, $next_link); - - git_footer_html(); -} - -sub git_search { - my ($have_search) = gitweb_check_feature('search'); - if (!$have_search) { - die_error('403 Permission denied', "Permission denied"); - } if (!defined $searchtext) { - die_error(undef, "Text field empty"); + die_error(400, "Text field is empty"); } if (!defined $hash) { $hash = git_get_head_hash($project); } my %co = parse_commit($hash); if (!%co) { - die_error(undef, "Unknown commit object"); + die_error(404, "Unknown commit object"); } if (!defined $page) { $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 - my ($have_pickaxe) = gitweb_check_feature('pickaxe'); - if (!$have_pickaxe) { - die_error('403 Permission denied', "Permission denied"); - } - } - if ($searchtype eq 'grep') { - my ($have_grep) = gitweb_check_feature('grep'); - if (!$have_grep) { - die_error('403 Permission denied', "Permission denied"); - } - } - - git_header_html(); - - if ($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 .= $search_regexp; - my @commitlist = parse_commits($hash, 101, (100 * $page), $greptype); - - my $paging_nav = ''; - if ($page > 0) { - $paging_nav .= - $cgi->a({-href => href(action=>"search", hash=>$hash, - searchtext=>$searchtext, searchtype=>$searchtype)}, - "first"); - $paging_nav .= " ⋅ " . - $cgi->a({-href => href(action=>"search", hash=>$hash, - searchtext=>$searchtext, searchtype=>$searchtype, - page=>$page-1), - -accesskey => "p", -title => "Alt-p"}, "prev"); - } else { - $paging_nav .= "first"; - $paging_nav .= " ⋅ prev"; - } - if ($#commitlist >= 100) { - $paging_nav .= " ⋅ " . - $cgi->a({-href => href(action=>"search", hash=>$hash, - searchtext=>$searchtext, searchtype=>$searchtype, - page=>$page+1), - -accesskey => "n", -title => "Alt-n"}, "next"); - } else { - $paging_nav .= " ⋅ next"; - } - my $next_link = ''; - if ($#commitlist >= 100) { - $next_link = - $cgi->a({-href => href(action=>"search", hash=>$hash, - searchtext=>$searchtext, searchtype=>$searchtype, - page=>$page+1), - -accesskey => "n", -title => "Alt-n"}, "next"); - } - - 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 "<table cellspacing=\"0\">\n"; - my $alternate = 1; - $/ = "\n"; - my $git_command = git_cmd_str(); - my $searchqtext = $searchtext; - $searchqtext =~ s/'/'\\''/; - open my $fd, "-|", "$git_command rev-list $hash | " . - "$git_command diff-tree -r --stdin -S\'$searchqtext\'"; - undef %co; - my @files; - while (my $line = <$fd>) { - if (%co && $line =~ m/^:([0-7]{6}) ([0-7]{6}) ([0-9a-fA-F]{40}) ([0-9a-fA-F]{40}) (.)\t(.*)$/) { - my %set; - $set{'file'} = $6; - $set{'from_id'} = $3; - $set{'to_id'} = $4; - $set{'id'} = $set{'to_id'}; - if ($set{'id'} =~ m/0{40}/) { - $set{'id'} = $set{'from_id'}; - } - if ($set{'id'} =~ m/0{40}/) { - next; - } - push @files, \%set; - } elsif ($line =~ m/^([0-9a-fA-F]{40})$/){ - if (%co) { - if ($alternate) { - print "<tr class=\"dark\">\n"; - } else { - print "<tr class=\"light\">\n"; - } - $alternate ^= 1; - print "<td title=\"$co{'age_string_age'}\"><i>$co{'age_string_date'}</i></td>\n" . - "<td><i>" . esc_html(chop_str($co{'author_name'}, 15, 5)) . "</i></td>\n" . - "<td>" . - $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), - -class => "list subject"}, - esc_html(chop_str($co{'title'}, 50)) . "<br/>"); - while (my $setref = shift @files) { - my %set = %$setref; - print $cgi->a({-href => href(action=>"blob", hash_base=>$co{'id'}, - hash=>$set{'id'}, file_name=>$set{'file'}), - -class => "list"}, - "<span class=\"match\">" . esc_path($set{'file'}) . "</span>") . - "<br/>\n"; - } - print "</td>\n" . - "<td class=\"link\">" . - $cgi->a({-href => href(action=>"commit", hash=>$co{'id'})}, "commit") . - " | " . - $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, hash_base=>$co{'id'})}, "tree"); - print "</td>\n" . - "</tr>\n"; - } - %co = parse_commit($1); - } - } - close $fd; - - print "</table>\n"; - } - - if ($searchtype eq 'grep') { - git_print_page_nav('','', $hash,$co{'tree'},$hash); - git_print_header_div('commit', esc_html($co{'title'}), $hash); - - print "<table cellspacing=\"0\">\n"; - my $alternate = 1; - my $matches = 0; - $/ = "\n"; - open my $fd, "-|", git_cmd(), 'grep', '-n', '-i', '-E', $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) { - $lastfile and print "</td></tr>\n"; - if ($alternate++) { - print "<tr class=\"dark\">\n"; - } else { - print "<tr class=\"light\">\n"; - } - print "<td class=\"list\">". - $cgi->a({-href => href(action=>"blob", hash=>$co{'hash'}, - file_name=>"$file"), - -class => "list"}, esc_path($file)); - print "</td><td>\n"; - $lastfile = $file; - } - if ($binary) { - print "<div class=\"binary\">Binary file</div>\n"; - } else { - $ltext = untabify($ltext); - if ($ltext =~ m/^(.*)($searchtext)(.*)$/i) { - $ltext = esc_html($1, -nbsp=>1); - $ltext .= '<span class="match">'; - $ltext .= esc_html($2, -nbsp=>1); - $ltext .= '</span>'; - $ltext .= esc_html($3, -nbsp=>1); - } else { - $ltext = esc_html($ltext, -nbsp=>1); - } - print "<div class=\"pre\">" . - $cgi->a({-href => href(action=>"blob", hash=>$co{'hash'}, - file_name=>"$file").'#l'.$lno, - -class => "linenr"}, sprintf('%4i', $lno)) - . ' ' . $ltext . "</div>\n"; - } - } - if ($lastfile) { - print "</td></tr>\n"; - if ($matches > 1000) { - print "<div class=\"diff nodifferences\">Too many matches, listing trimmed</div>\n"; - } - } else { - print "<div class=\"diff nodifferences\">No matches found</div>\n"; - } - close $fd; - - print "</table>\n"; + if ($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 { git_header_html(); git_print_page_nav('','', $hash,$hash,$hash); print <<EOT; +<p><strong>Pattern</strong> is by default a normal string that is matched precisely (but without +regard to case, except in the case of pickaxe). However, when you check the <em>re</em> checkbox, +the pattern entered is recognized as the POSIX extended +<a href="http://en.wikipedia.org/wiki/Regular_expression">regular expression</a> (also case +insensitive).</p> <dl> <dt><b>commit</b></dt> -<dd>The commit messages and authorship information will be scanned for the given string.</dd> +<dd>The commit messages and authorship information will be scanned for the given pattern.</dd> EOT - my ($have_grep) = gitweb_check_feature('grep'); + my $have_grep = gitweb_check_feature('grep'); if ($have_grep) { print <<EOT; <dt><b>grep</b></dt> <dd>All files in the currently selected tree (HEAD unless you are explicitly browsing - a different one) are searched for the given -<a href="http://en.wikipedia.org/wiki/Regular_expression">regular expression</a> -(POSIX extended) and the matches are listed. On large -trees, this search can take a while and put some strain on the server, so please use it with -some consideration.</dd> + a different one) are searched for the given pattern. On large trees, this search can take +a while and put some strain on the server, so please use it with some consideration. Note that +due to git-grep peculiarity, currently if regexp mode is turned off, the matches are +case-sensitive.</dd> EOT } print <<EOT; <dt><b>author</b></dt> -<dd>Name and e-mail of the change author and date of birth of the patch will be scanned for the given string.</dd> +<dd>Name and e-mail of the change author and date of birth of the patch will be scanned for the given pattern.</dd> <dt><b>committer</b></dt> -<dd>Name and e-mail of the committer and date of commit will be scanned for the given string.</dd> +<dd>Name and e-mail of the committer and date of commit will be scanned for the given pattern.</dd> EOT - my ($have_pickaxe) = gitweb_check_feature('pickaxe'); + my $have_pickaxe = gitweb_check_feature('pickaxe'); if ($have_pickaxe) { print <<EOT; <dt><b>pickaxe</b></dt> <dd>All commits that caused the string to appear or disappear from any file (changes that added, removed or "modified" the string) will be listed. This search can take a while and -takes a lot of strain on the server, so please use it wisely.</dd> +takes a lot of strain on the server, so please use it wisely. Note that since you may be +interested even in changes just changing the case as well, this search is case sensitive.</dd> EOT } print "</dl>\n"; @@ -5320,32 +7987,8 @@ EOT } sub git_shortlog { - my $head = git_get_head_hash($project); - if (!defined $hash) { - $hash = $head; - } - if (!defined $page) { - $page = 0; - } - my $refs = git_get_references(); - - my @commitlist = parse_commits($hash, 101, (100 * $page)); - - my $paging_nav = format_paging_nav('shortlog', $hash, $head, $page, (100 * ($page+1))); - my $next_link = ''; - if ($#commitlist >= 100) { - $next_link = - $cgi->a({-href => href(action=>"shortlog", hash=>$hash, 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); } ## ...................................................................... @@ -5353,17 +7996,17 @@ sub git_shortlog { sub git_feed { my $format = shift || 'atom'; - my ($have_blame) = gitweb_check_feature('blame'); + my $have_blame = gitweb_check_feature('blame'); # Atom: http://www.atomenabled.org/developers/syndication/ # RSS: http://www.notestips.com/80256B3A007F2692/1/NAMO5P9UPQ if ($format ne 'rss' && $format ne 'atom') { - die_error(undef, "Unknown web feed format"); + die_error(400, "Unknown web feed format"); } # log/feed of current (HEAD) branch, log of given branch, history of file/directory my $head = $hash || 'HEAD'; - my @commitlist = parse_commits($head, 150, 0, undef, $file_name); + my @commitlist = parse_commits($head, 150, 0, $file_name); my %latest_commit; my %latest_date; @@ -5375,16 +8018,15 @@ sub git_feed { } if (defined($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{'comitter_tz'}); } + print $cgi->header( + -type => $content_type, + -charset => 'utf-8', + %latest_date ? (-last_modified => $latest_date{'rfc2822'}) : (), + -status => '200 OK'); # Optimization: skip generating the body if client asks only # for Last-Modified date. @@ -5434,7 +8076,24 @@ XML print "<title>$title</title>\n" . "<link>$alt_url</link>\n" . "<description>$descr</description>\n" . - "<language>en</language>\n"; + "<language>en</language>\n" . + # project owner is responsible for 'editorial' content + "<managingEditor>$owner</managingEditor>\n"; + if (defined $logo || defined $favicon) { + # prefer the logo to the favicon, since RSS + # doesn't allow both + my $img = esc_url($logo || $favicon); + print "<image>\n" . + "<url>$img</url>\n" . + "<title>$title</title>\n" . + "<link>$alt_url</link>\n" . + "</image>\n"; + } + if (%latest_date) { + print "<pubDate>$latest_date{'rfc2822'}</pubDate>\n"; + print "<lastBuildDate>$latest_date{'rfc2822'}</lastBuildDate>\n"; + } + print "<generator>gitweb v.$version/$git_version</generator>\n"; } elsif ($format eq 'atom') { print <<XML; <feed xmlns="http://www.w3.org/2005/Atom"> @@ -5451,7 +8110,7 @@ XML if (defined $favicon) { print "<icon>" . esc_url($favicon) . "</icon>\n"; } - if (defined $logo_url) { + if (defined $logo) { # not twice as wide as tall: 72 x 27 pixels print "<logo>" . esc_url($logo) . "</logo>\n"; } @@ -5461,6 +8120,7 @@ XML } else { print "<updated>$latest_date{'iso-8601'}</updated>\n"; } + print "<generator version='$version/$git_version'>gitweb</generator>\n"; } # contents @@ -5471,7 +8131,7 @@ XML if (($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, @@ -5483,7 +8143,7 @@ XML or next; # print element (entry, item) - my $co_url = href(-full=>1, action=>"commit", hash=>$commit); + my $co_url = href(-full=>1, action=>"commitdiff", hash=>$commit); if ($format eq 'rss') { print "<item>\n" . "<title>" . esc_html($co{'title'}) . "</title>\n" . @@ -5566,7 +8226,7 @@ XML # end of feed if ($format eq 'rss') { print "</channel>\n</rss>\n"; - } elsif ($format eq 'atom') { + } elsif ($format eq 'atom') { print "</feed>\n"; } } @@ -5580,14 +8240,28 @@ sub git_atom { } sub git_opml { - my @list = git_get_projects_list(); + my @list = git_get_projects_list($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 { + $filter = ""; + } print <<XML; <?xml version="1.0" encoding="utf-8"?> <opml version="1.0"> <head> - <title>$site_name OPML Export</title> + <title>$title OPML Export$filter</title> </head> <body> <outline text="git RSS feeds"> @@ -5606,8 +8280,8 @@ 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 = href('project' => $proj{'path'}, 'action' => 'rss', -full => 1); + my $html = href('project' => $proj{'path'}, 'action' => 'summary', -full => 1); print "<outline type=\"rss\" text=\"$path\" title=\"$path\" xmlUrl=\"$rss\" htmlUrl=\"$html\"/>\n"; } print <<XML; |