From 63c10a40241350841bd096a09df953bd6c33a75b Mon Sep 17 00:00:00 2001 From: Thomas Penteker Date: Sat, 17 Jan 2015 14:45:43 +0100 Subject: [PATCH] gitweb: update to 1.9.0, allow direct port download in tree view --- gitweb/gitweb.cgi | 7509 ++++++++++++++++++++++++++++++++++----------- gitweb/gitweb.js | 1579 ++++++++++ gitweb/index.aux | 2 +- 3 files changed, 7355 insertions(+), 1735 deletions(-) create mode 100644 gitweb/gitweb.js diff --git a/gitweb/gitweb.cgi b/gitweb/gitweb.cgi index 078af2b..cc1cc84 100755 --- a/gitweb/gitweb.cgi +++ b/gitweb/gitweb.cgi @@ -7,21 +7,32 @@ # # 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 $ENV{'MOD_PERL'}; +} + + +our ($my_url, $my_uri, $base_url, $path_info, $home_link); our $cgi = new CGI; -our $version = "1.4.4.2"; -our $my_url = $cgi->url(); -our $my_uri = $cgi->url(-absolute => 1); +our $version = "1.9.0"; +#our $my_url = $cgi->url(); +$my_uri = $cgi->url(-absolute => 1); # core git executable to use # this can just be "git" if your webserver has a sensible PATH @@ -32,7 +43,7 @@ our $GIT = "/usr/bin/git"; our $projectroot = "/home/crux/scm"; # target of the home link on top of all pages -our $home_link = $my_uri || "/"; +$home_link = $my_uri || "/"; # string of the home link on top of all pages our $home_link_str = "projects"; @@ -49,6 +60,9 @@ our $home_text = "indextext.html"; # filename of html text to include at bottom of each page our $site_footer = ""; +# URI of gitweb.js (JavaScript code for gitweb) +our $javascript = "gitweb.js"; + # URI of stylesheets our @stylesheets = ("gitweb.css"); # URI of a single stylesheet, which can be overridden in GITWEB_CONFIG. @@ -86,6 +100,156 @@ our $default_text_plain_charset = undef; # (relative to the current git repository) our $mimetypes_file = undef; +# 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 $maxload = 300; + +# show repository only if this subroutine returns true +# when given the path to the project, for example: +# sub { return -e "$_[0]/git-daemon-export-ok"; } +our $export_auth_hook = undef; + +# information about snapshot formats that gitweb is capable of serving +our %known_snapshot_formats = ( + # name => { + # 'display' => display name, + # 'type' => mime type, + # 'suffix' => filename suffix, + # 'format' => --format for git-archive, + # 'compressor' => [compressor command and arguments] + # (array reference, optional) + # 'disabled' => boolean (optional)} + # + 'tgz' => { + 'display' => 'tar.gz', + 'type' => 'application/x-gzip', + 'suffix' => '.tar.gz', + 'format' => 'tar', + 'compressor' => ['gzip', '-n']}, + + 'tbz2' => { + 'display' => 'tar.bz2', + 'type' => 'application/x-bzip2', + 'suffix' => '.tar.bz2', + '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', + 'suffix' => '.zip', + 'format' => 'zip'}, +); + +# Aliases so we understand old gitweb.snapshot values in repository +# configuration. +our %known_snapshot_format_aliases = ( + 'gzip' => 'tgz', + 'bzip2' => 'tbz2', + 'xz' => 'txz', + + # backward compatibility: legacy gitweb config support + 'x-gzip' => undef, 'gz' => undef, + 'x-bzip2' => undef, 'bz2' => undef, + 'x-zip' => undef, '' => undef, +); + +# assume this charset if line contains non-UTF-8 characters; +# it should be valid encoding (see Encoding::Supported(3pm) for list), +# for which encoding all byte sequences are valid, for example +# 'iso-8859-1' aka 'latin1' (it is decoded without checking, so it +# could be even 'utf-8' for the old behavior) +our $fallback_encoding = 'latin1'; + +# 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 +); + +# configuration for 'highlight' (http://www.andre-simon.de/) +# match by basename +our %highlight_basename = ( + #'Program' => 'py', + #'Library' => 'py', + 'SConstruct' => 'py', # SCons equivalent of Makefile + 'Makefile' => 'make', +); +# match by extension +our %highlight_ext = ( + # main extensions, defining name of syntax; + # see files in /usr/share/highlight/langDefs/ directory + (map { $_ => $_ } qw(py rb java css js tex bib xml awk bat ini spec tcl sql)), + # alternate extensions, see /etc/highlight/filetypes.conf + (map { $_ => 'c' } qw(c h)), + (map { $_ => 'sh' } qw(sh bash zsh ksh)), + (map { $_ => 'cpp' } qw(cpp cxx c++ cc)), + (map { $_ => 'php' } qw(php php3 php4 php5 phps)), + (map { $_ => 'pl' } qw(pl perl pm)), # perhaps also 'cgi' + (map { $_ => 'make'} qw(make mak mk)), + (map { $_ => 'xml' } qw(xml xhtml html htm)), +); + +# rename detection options for git-diff and git-diff-tree +# - default is '-M', with the cost proportional to +# (number of removed files) * (number of new files). +# - more costly is '-C' (which implies '-M'), with the cost proportional to +# (number of changed files + number of removed files) * (number of new files) +# - even more costly is '-C', '--find-copies-harder' with cost +# (number of files in the original tree) * (number of new files) +# - 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"; + +# extra breadcrumbs preceding the home link +our @extra_breadcrumbs = (); + +# html snippet to include in the section of each page +our $site_html_head_string = ""; + +# 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 = ""; + +# don't generate age column on the projects list page +our $omit_age_column = 0; + +# default order of projects list +# valid values are none, project, descr, owner, and age +our $default_projects_order = "project"; + +# don't generate information about owners of repositories +our $omit_owner=0; + + # You define site-wide feature defaults here; override them with # $GITWEB_CONFIG as necessary. our %feature = ( @@ -187,7 +351,7 @@ our %default_heads = ( "ports/e17.git" => "3.0", "ports/sip.git" => "2.4", "ports/kde.git" => "2.5", - "ports/kde4.git" => "2.8", + "ports/kde4.git" => "3.0", "system/iso.git" => "3.0", "ports/core-x86_64.git" => "2.8", "ports/opt-x86_64.git" => "2.8", @@ -195,81 +359,137 @@ our %default_heads = ( "ports/compat-32.git" => "3.0" ); -sub gitweb_get_default_head { - my $project = shift; - exists $default_heads{$project} && return $default_heads{$project}; - return "HEAD"; +sub evaluate_uri { + our $cgi; + + our $my_url = $cgi->url(); + our $my_uri = $cgi->url(-absolute => 1); + + # Base URL for relative URLs in gitweb ($logo, $favicon, ...), + # needed and used only for URLs with nonempty PATH_INFO + our $base_url = $my_url; + + # When the script is used as DirectoryIndex, the URL does not contain the name + # of the script file itself, and $cgi->url() fails to strip PATH_INFO, so we + # have to do it ourselves. We make $path_info global because it's also used + # later on. + # + # Another issue with the script being the DirectoryIndex is that the resulting + # $my_url data is not the full script URL: this is good, because we want + # generated links to keep implying the script name if it wasn't explicitly + # indicated in the URL we're handling, but it means that $my_url cannot be used + # as base URL. + # Therefore, if we needed to strip PATH_INFO, then we know that we have + # to build the base URL ourselves: + our $path_info = decode_utf8($ENV{"PATH_INFO"}); + if ($path_info) { + # $path_info has already been URL-decoded by the web server, but + # $my_url and $my_uri have not. URL-decode them so we can properly + # strip $path_info. + $my_url = unescape($my_url); + $my_uri = unescape($my_uri); + if ($my_url =~ s,\Q$path_info\E$,, && + $my_uri =~ s,\Q$path_info\E$,, && + defined $ENV{'SCRIPT_NAME'}) { + $base_url = $cgi->url(-base => 1) . $ENV{'SCRIPT_NAME'}; + } + } + + # target of the home link on top of all pages + our $home_link = $my_uri || "/"; } -sub nospam { - my $committer = shift; - $committer =~ s/\./ dot /g; - $committer =~ s/\@/ at /g; - return $committer; -} - -sub gitweb_check_feature { +sub gitweb_get_feature { my ($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'); - - if ($val eq 'true') { - return 1; - } elsif ($val eq 'false') { - return 0; - } - - return $_[0]; +# 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]; } -sub feature_snapshot { - my ($ctype, $suffix, $command) = @_; - my ($val) = git_get_project_config('snapshot'); +sub feature_bool { + my $key = shift; + my ($val) = git_get_project_config($key, '--bool'); - if ($val eq 'gzip') { - return ('x-gzip', 'gz', 'gzip'); - } elsif ($val eq 'bzip2') { - return ('x-bzip2', 'bz2', 'bzip2'); - } elsif ($val eq 'none') { - return (); - } - - return ($ctype, $suffix, $command); -} - -sub gitweb_have_snapshot { - my ($ctype, $suffix, $command) = gitweb_check_feature('snapshot'); - my $have_snapshot = (defined $ctype && defined $suffix); - - return $have_snapshot; -} - -sub feature_pickaxe { - my ($val) = git_get_project_config('pickaxe', '--bool'); - - if ($val eq 'true') { + if (!defined $val) { + return ($_[0]); + } elsif ($val eq 'true') { return (1); } elsif ($val eq 'false') { return (0); } +} + +sub feature_snapshot { + my (@fmts) = @_; + + my ($val) = git_get_project_config('snapshot'); + + if ($val) { + @fmts = ($val eq 'none' ? () : split /\s*[,\s]\s*/, $val); + } + + return @fmts; +} + +sub feature_patches { + my @val = (git_get_project_config('patches', '--int')); + + if (@val) { + return @val; + } return ($_[0]); } +sub feature_avatar { + my @val = (git_get_project_config('avatar')); + + return @val ? @val : @_; +} + +sub feature_extra_branch_refs { + my (@branch_refs) = @_; + my $values = git_get_project_config('extrabranchrefs'); + + if ($values) { + $values = config_to_multi ($values); + @branch_refs = (); + foreach my $value (@{$values}) { + push @branch_refs, split /\s+/, $value; + } + } + + return @branch_refs; +} + # checking HEAD file with -e is fragile if the repository was # initialized long time ago (i.e. symlink HEAD) and was pack-ref'ed # and then pruned. @@ -283,167 +503,163 @@ sub check_head_link { sub check_export_ok { my ($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))); } -# rename detection options for git-diff and git-diff-tree -# - default is '-M', with the cost proportional to -# (number of removed files) * (number of new files). -# - more costly is '-C' (or '-C', '-M'), with the cost proportional to -# (number of changed files + number of removed files) * (number of new files) -# - even more costly is '-C', '--find-copies-harder' with cost -# (number of files in the original tree) * (number of new files) -# - one might want to include '-B' option, e.g. '-B', '-M' -our @diff_opts = ('-M'); # taken from git_commit +# process alternate names for backward compatibility +# filter out unsupported (unknown) snapshot formats +sub filter_snapshot_fmts { + my @fmts = @_; -our $GITWEB_CONFIG = $ENV{'GITWEB_CONFIG'} || "gitweb_config.perl"; -do $GITWEB_CONFIG if -e $GITWEB_CONFIG; + @fmts = map { + exists $known_snapshot_format_aliases{$_} ? + $known_snapshot_format_aliases{$_} : $_} @fmts; + @fmts = grep { + exists $known_snapshot_formats{$_} && + !$known_snapshot_formats{$_}{'disabled'}} @fmts; +} + +sub filter_and_validate_refs { + my @refs = @_; + my %unique_refs = (); + + foreach my $ref (@refs) { + die_error(500, "Invalid ref '$ref' in 'extra-branch-refs' feature") unless (is_valid_ref_format($ref)); + # 'heads' are added implicitly in get_branch_refs(). + $unique_refs{$ref} = 1 if ($ref ne 'heads'); + } + return sort keys %unique_refs; +} + +# If it is set to code reference, it is code that it is to be run once per +# request, allowing updating configurations that change with each request, +# while running other code in config file only once. +# +# Otherwise, if it is false then gitweb would process config file only once; +# if it is true then gitweb config would be run for each request. +our $per_request_config = 1; + +# read and parse gitweb config file given by its parameter. +# returns true on success, false on recoverable error, allowing +# to chain this subroutine, using first file that exists. +# dies on errors during parsing config file, as it is unrecoverable. +sub read_config_file { + my $filename = shift; + return unless defined $filename; + # die if there are errors parsing config file + if (-e $filename) { + do $filename; + die $@ if $@; + return 1; + } + return; +} + +our ($GITWEB_CONFIG, $GITWEB_CONFIG_SYSTEM, $GITWEB_CONFIG_COMMON); +sub evaluate_gitweb_config { + our $GITWEB_CONFIG = $ENV{'GITWEB_CONFIG'} || "gitweb_config.perl"; + our $GITWEB_CONFIG_SYSTEM = $ENV{'GITWEB_CONFIG_SYSTEM'} || "/etc/gitweb.conf"; + our $GITWEB_CONFIG_COMMON = $ENV{'GITWEB_CONFIG_COMMON'} || "/etc/gitweb-common.conf"; + + # Protect against duplications of file names, to not read config twice. + # Only one of $GITWEB_CONFIG and $GITWEB_CONFIG_SYSTEM is used, so + # there possibility of duplication of filename there doesn't matter. + $GITWEB_CONFIG = "" if ($GITWEB_CONFIG eq $GITWEB_CONFIG_COMMON); + $GITWEB_CONFIG_SYSTEM = "" if ($GITWEB_CONFIG_SYSTEM eq $GITWEB_CONFIG_COMMON); + + # Common system-wide settings for convenience. + # Those settings can be ovverriden by GITWEB_CONFIG or GITWEB_CONFIG_SYSTEM. + read_config_file($GITWEB_CONFIG_COMMON); + + # Use first config file that exists. This means use the per-instance + # GITWEB_CONFIG if exists, otherwise use GITWEB_SYSTEM_CONFIG. + read_config_file($GITWEB_CONFIG) and return; + read_config_file($GITWEB_CONFIG_SYSTEM); +} + +# Get loadavg of system, to compare against $maxload. +# Currently it requires '/proc/loadavg' present to get loadavg; +# if it is not present it returns 0, which means no load checking. +sub get_loadavg { + if( -e '/proc/loadavg' ){ + open my $fd, '<', '/proc/loadavg' + or return 0; + my @load = split(/\s+/, scalar <$fd>); + close $fd; + + # The first three columns measure CPU and IO utilization of the last one, + # five, and 10 minute periods. The fourth column shows the number of + # currently running processes and the total number of processes in the m/n + # format. The last column displays the last process ID used. + return $load[0] || 0; + } + # additional checks for load average should go here for things that don't export + # /proc/loadavg + + return 0; +} # version of the core git binary -our $git_version = qx($GIT --version) =~ m/git version (.*)$/ ? $1 : "unknown"; +our $git_version; +sub evaluate_git_version { + our $git_version = qx("$GIT" --version) =~ m/git version (.*)$/ ? $1 : "unknown"; + $number_of_git_cmds++; +} -$projects_list ||= $projectroot; +sub check_loadavg { + if (defined $maxload && get_loadavg() > $maxload) { + die_error(503, "The load average on the server is too high"); + } +} # ====================================================================== # input validation and dispatch -our $action = $cgi->param('a'); -if (defined $action) { - if ($action =~ m/[^0-9a-zA-Z\.\-_]/) { - die_error(undef, "Invalid action parameter"); - } -} -# 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"); - } -} +# 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 -our $file_name = $cgi->param('f'); -if (defined $file_name) { - if (!validate_pathname($file_name)) { - die_error(undef, "Invalid file parameter"); - } -} +our %input_params = (); -our $file_parent = $cgi->param('fp'); -if (defined $file_parent) { - if (!validate_pathname($file_parent)) { - die_error(undef, "Invalid file parent parameter"); - } -} +# 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. -# parameters which are refnames -our $hash = $cgi->param('h'); -if (defined $hash) { - if (!validate_refname($hash)) { - die_error(undef, "Invalid hash parameter"); - } -} +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; -our $hash_parent = $cgi->param('hp'); -if (defined $hash_parent) { - if (!validate_refname($hash_parent)) { - die_error(undef, "Invalid hash parent parameter"); - } -} - -our $hash_base = $cgi->param('hb'); -if (defined $hash_base) { - if (!validate_refname($hash_base)) { - die_error(undef, "Invalid hash base parameter"); - } -} - -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"); - } -} - -# other parameters -our $page = $cgi->param('pg'); -if (defined $page) { - if ($page =~ m/[^0-9]/) { - die_error(undef, "Invalid page parameter"); - } -} - -our $searchtext = $cgi->param('s'); -if (defined $searchtext) { - if ($searchtext =~ m/[^a-zA-Z0-9_\.\/\-\+\:\@ ]/) { - die_error(undef, "Invalid search parameter"); - } - $searchtext = quotemeta $searchtext; -} - -our $searchtype = $cgi->param('st'); -if (defined $searchtype) { - if ($searchtype =~ m/[^a-z]/) { - die_error(undef, "Invalid searchtype parameter"); - } -} - -# 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(); - -# path to the current git repository -our $git_dir; -$git_dir = "$projectroot/$project" if $project; - -# 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, @@ -455,7 +671,11 @@ 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, "search_help" => \&git_search_help, "shortlog" => \&git_shortlog, @@ -464,77 +684,616 @@ my %actions = ( "tags" => \&git_tags, "tree" => \&git_tree, "snapshot" => \&git_snapshot, + "object" => \&git_object, # those below don't need $project "opml" => \&git_opml, "project_list" => \&git_project_list, "project_index" => \&git_project_index, ); -if (defined $project) { - $action ||= 'summary'; +# 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 $action) { + if (!is_valid_action($action)) { + die_error(400, "Invalid action parameter"); + } + } + + # parameters which are pathnames + our $project = $input_params{'project'}; + if (defined $project) { + if (!is_valid_project($project)) { + undef $project; + die_error(404, "No such project"); + } + } + + our $project_filter = $input_params{'project_filter'}; + if (defined $project_filter) { + if (!is_valid_pathname($project_filter)) { + die_error(404, "Invalid project_filter parameter"); + } + } + + our $file_name = $input_params{'file_name'}; + if (defined $file_name) { + if (!is_valid_pathname($file_name)) { + die_error(400, "Invalid file parameter"); + } + } + + our $file_parent = $input_params{'file_parent'}; + if (defined $file_parent) { + if (!is_valid_pathname($file_parent)) { + die_error(400, "Invalid file parent parameter"); + } + } + + # parameters which are refnames + our $hash = $input_params{'hash'}; + if (defined $hash) { + if (!is_valid_refname($hash)) { + die_error(400, "Invalid hash parameter"); + } + } + + our $hash_parent = $input_params{'hash_parent'}; + if (defined $hash_parent) { + if (!is_valid_refname($hash_parent)) { + die_error(400, "Invalid hash parent parameter"); + } + } + + our $hash_base = $input_params{'hash_base'}; + if (defined $hash_base) { + if (!is_valid_refname($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 $hash_parent_base) { + if (!is_valid_refname($hash_parent_base)) { + die_error(400, "Invalid hash parent base parameter"); + } + } + + # other parameters + our $page = $input_params{'page'}; + if (defined $page) { + if ($page =~ m/[^0-9]/) { + die_error(400, "Invalid page parameter"); + } + } + + 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 = undef; + if (defined $searchtext) { + if (length($searchtext) < 2) { + die_error(403, "At least two characters are required for search parameter"); + } + if ($search_use_regexp) { + $search_regexp = $searchtext; + if (!eval { qr/$search_regexp/; 1; }) { + (my $error = $@) =~ s/ at \S+ line \d+.*\n?//; + die_error(400, "Invalid search regexp '$search_regexp'", + esc_html($error)); + } + } else { + $search_regexp = quotemeta $searchtext; + } + } +} + +# 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, @extra_branch_refs); +sub configure_gitweb_features { + # list of supported snapshot formats + our @snapshot_fmts = gitweb_get_feature('snapshot'); + @snapshot_fmts = filter_snapshot_fmts(@snapshot_fmts); + + # check that the avatar feature is set to a known provider name, + # and for each provider check if the dependencies are satisfied. + # if the provider name is invalid or the dependencies are not met, + # reset $git_avatar to the empty string. + our ($git_avatar) = gitweb_get_feature('avatar'); + if ($git_avatar eq 'gravatar') { + $git_avatar = '' unless (eval { require Digest::MD5; 1; }); + } elsif ($git_avatar eq 'picon') { + # no dependencies + } else { + $git_avatar = ''; + } + + our @extra_branch_refs = gitweb_get_feature('extra-branch-refs'); + @extra_branch_refs = filter_and_validate_refs (@extra_branch_refs); +} + +sub get_branch_refs { + return ('heads', @extra_branch_refs); +} + +# custom error handler: 'die ' is Internal Server Error +sub handle_errors_html { + my $msg = shift; # it is already HTML escaped + + # to avoid infinite loop where error occurs in die_error, + # change handler to default handler, disabling handle_errors_html + set_message("Error occurred when inside die_error:\n$msg"); + + # 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}->(); +} + +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 { - $action ||= 'project_list'; + # pure CGI script, serving single request + exit; } -if (!defined($actions{$action})) { - die_error(undef, "Unknown action"); -} -if ($action !~ m/^(opml|project_list|project_index)$/ && - !$project) { - die_error(undef, "Project needed"); -} -$actions{$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 = @_; - my $href = $my_uri; + # 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", - ); - 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}) { - push @result, $symbol . "=" . esc_param($params{$name}); + if (ref($params{$name}) eq "ARRAY") { + foreach my $par (@{$params{$name}}) { + push @result, $symbol . "=" . esc_param($par); + } + } else { + push @result, $symbol . "=" . esc_param($params{$name}); + } } } $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; } @@ -542,9 +1301,30 @@ sub href(%) { ## ====================================================================== ## validation, quoting/unquoting and escaping -sub validate_pathname { - my $input = shift || return undef; +sub is_valid_action { + my $input = shift; + return undef unless exists $actions{$input}; + return 1; +} +sub is_valid_project { + my $input = shift; + + return unless defined $input; + if (!is_valid_pathname($input) || + !(-d "$projectroot/$input") || + !check_export_ok("$projectroot/$input") || + ($strict_export && !project_in_list($input))) { + return undef; + } else { + return 1; + } +} + +sub is_valid_pathname { + my $input = shift; + + return undef unless defined $input; # no '.' or '..' as elements of path, i.e. no '.' nor '..' # at the beginning, at the end, and between slashes. # also this catches doubled slashes @@ -555,58 +1335,95 @@ sub validate_pathname { if ($input =~ m!\0!) { return undef; } - return $input; + return 1; } -sub validate_refname { - my $input = shift || return undef; +sub is_valid_ref_format { + my $input = shift; - # textual hashes are O.K. - if ($input =~ m/^[0-9a-fA-F]{40}$/) { - return $input; - } - # it must be correct pathname - $input = validate_pathname($input) - or return undef; + return undef unless defined $input; # restrictions on ref name according to git-check-ref-format if ($input =~ m!(/\.|\.\.|[\000-\040\177 ~^:?*\[]|/$)!) { return undef; } - return $input; + return 1; } -# very thin wrapper for decode("utf8", $str, Encode::FB_DEFAULT); +sub is_valid_refname { + my $input = shift; + + return undef unless defined $input; + # textual hashes are O.K. + if ($input =~ m/^[0-9a-fA-F]{40}$/) { + return 1; + } + # it must be correct pathname + is_valid_pathname($input) or return undef; + # check git-check-ref-format restrictions + is_valid_ref_format($input) or return undef; + return 1; +} + +# decode sequences of octets in utf8 into Perl's internal form, +# which is utf-8 with utf8 flag set if needed. gitweb writes out +# in utf-8 thanks to "binmode STDOUT, ':utf8'" at beginning sub to_utf8 { my $str = shift; - return decode("utf8", $str, Encode::FB_DEFAULT); + return undef unless defined $str; + + if (utf8::is_utf8($str) || utf8::decode($str)) { + return $str; + } else { + return decode($fallback_encoding, $str, Encode::FB_DEFAULT); + } } # quote unsafe chars, but keep the slash, even when it's not # 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); - $str = escapeHTML($str); + $str = $cgi->escapeHTML($str); if ($opts{'-nbsp'}) { $str =~ s/ / /g; } @@ -614,42 +1431,72 @@ sub esc_html ($;%) { return $str; } -# Make control characterss "printable". -sub quot_cec { - my $cntrl = shift; - 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) - ); - my $chr = ( (exists $es{$cntrl}) - ? $es{$cntrl} - : sprintf('\%03o', ord($cntrl)) ); - return "$chr"; -} - -# Alternatively use unicode control pictures codepoints. -sub quot_upr { - my $cntrl = shift; - my $chr = sprintf('&#%04d;', 0x2400+ord($cntrl)); - return "$chr"; -} - # quote control characters and escape filename to HTML sub esc_path { my $str = shift; + my %opts = @_; - $str = esc_html($str); + return undef unless defined $str; + + $str = to_utf8($str); + $str = $cgi->escapeHTML($str); + if ($opts{'-nbsp'}) { + $str =~ s/ / /g; + } $str =~ s|([[:cntrl:]])|quot_cec($1)|eg; 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:]])|(index("\t\n\r", $1) != -1 ? $1 : quot_cec($1))|eg; + return $str; +} + +# Make control characters "printable", using character escape codes (CEC) +sub quot_cec { + my $cntrl = shift; + my %opts = @_; + my %es = ( # character escape codes, aka escape sequences + "\t" => '\t', # tab (HT) + "\n" => '\n', # line feed (LF) + "\r" => '\r', # carrige return (CR) + "\f" => '\f', # form feed (FF) + "\b" => '\b', # backspace (BS) + "\a" => '\a', # alarm (bell) (BEL) + "\e" => '\e', # escape (ESC) + "\013" => '\v', # vertical tab (VT) + "\000" => '\0', # nul character (NUL) + ); + my $chr = ( (exists $es{$cntrl}) + ? $es{$cntrl} + : sprintf('\%2x', ord($cntrl)) ); + if ($opts{-nohtml}) { + return $chr; + } else { + return "$chr"; + } +} + +# 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)); + if ($opts{-nohtml}) { + return $chr; + } else { + return "$chr"; + } +} + # git may return quoted and escaped filenames sub unquote { my $str = shift; @@ -672,7 +1519,7 @@ sub unquote { return chr(oct($seq)); } elsif (exists $es{$seq}) { # C escape sequence, aka character escape code - return $es{$seq} + return $es{$seq}; } # quoted ordinary character return $seq; @@ -709,21 +1556,171 @@ 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($str)); # filler is length 4 } - return "$body$tail"; + + # 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$tail"; + } +} + +# takes the same arguments as chop_str, but also wraps a around the +# result with a title attribute if it does get chopped. Additionally, the +# string is HTML-escaped. +sub chop_and_escape_str { + my ($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($chopped)); + } +} + +# Highlight selected fragments of string, using given CSS class, +# and escape HTML. It is assumed that fragments do not overlap. +# Regions are passed as list of pairs (array references). +# +# Example: esc_html_hl_regions("foobar", "mark", [ 0, 3 ]) returns +# 'foobar' +sub esc_html_hl_regions { + my ($str, $css_class, @sel) = @_; + my %opts = grep { ref($_) ne 'ARRAY' } @sel; + @sel = grep { ref($_) eq 'ARRAY' } @sel; + return esc_html($str, %opts) unless @sel; + + my $out = ''; + my $pos = 0; + + for my $s (@sel) { + my ($begin, $end) = @$s; + + # Don't create empty elements. + next if $end <= $begin; + + my $escaped = esc_html(substr($str, $begin, $end - $begin), + %opts); + + $out .= esc_html(substr($str, $pos, $begin - $pos), %opts) + if ($begin - $pos > 0); + $out .= $cgi->span({-class => $css_class}, $escaped); + + $pos = $end; + } + $out .= esc_html(substr($str, $pos), %opts) + if ($pos < length($str)); + + return $out; +} + +# return positions of beginning and end of each match +sub matchpos_list { + my ($str, $regexp) = @_; + return unless (defined $str && defined $regexp); + + my @matches; + while ($str =~ /$regexp/g) { + push @matches, [$-[0], $+[0]]; + } + return @matches; +} + +# highlight match (if any), and escape HTML +sub esc_html_match_hl { + my ($str, $regexp) = @_; + return esc_html($str) unless defined $regexp; + + my @matches = matchpos_list($str, $regexp); + return esc_html($str) unless @matches; + + return esc_html_hl_regions($str, 'match', @matches); +} + + +# highlight match (if any) of shortened string, and escape HTML +sub esc_html_match_hl_chopped { + my ($str, $chopped, $regexp) = @_; + return esc_html_match_hl($str, $regexp) unless defined $chopped; + + my @matches = matchpos_list($str, $regexp); + return esc_html($chopped) unless @matches; + + # filter matches so that we mark chopped string + my $tail = "... "; # see chop_str + unless ($chopped =~ s/\Q$tail\E$//) { + $tail = ''; + } + my $chop_len = length($chopped); + my $tail_len = length($tail); + my @filtered; + + for my $m (@matches) { + if ($m->[0] > $chop_len) { + push @filtered, [ $chop_len, $chop_len + $tail_len ] if ($tail_len > 0); + last; + } elsif ($m->[1] > $chop_len) { + push @filtered, [ $m->[0], $chop_len + $tail_len ]; + last; + } + push @filtered, $m; + } + + return esc_html_hl_regions($chopped . $tail, 'match', @filtered); } ## ---------------------------------------------------------------------- @@ -733,7 +1730,9 @@ sub chop_str { sub age_class { my $age = shift; - if ($age < 60*60*2) { + if (!defined $age) { + return "noage"; + } elsif ($age < 60*60*2) { return "age0"; } elsif ($age < 60*60*24*2) { return "age1"; @@ -774,11 +1773,25 @@ sub age_string { return $age_str; } +use constant { + S_IFINVALID => 0030000, + S_IFGITLINK => 0160000, +}; + +# submodule/subproject, a commit object reference +sub S_ISGITLINK { + my $mode = shift; + + return (($mode & S_IFMT) == S_IFGITLINK) +} + # convert file mode in octal to symbolic file mode string sub mode_str { my $mode = oct shift; - if (S_ISDIR($mode & S_IFMT)) { + if (S_ISGITLINK($mode)) { + return 'm---------'; + } elsif (S_ISDIR($mode & S_IFMT)) { return 'drwxr-xr-x'; } elsif (S_ISLNK($mode)) { return 'lrwxrwxrwx'; @@ -804,7 +1817,9 @@ sub file_type { $mode = oct $mode; } - if (S_ISDIR($mode & S_IFMT)) { + if (S_ISGITLINK($mode)) { + return "submodule"; + } elsif (S_ISDIR($mode & S_IFMT)) { return "directory"; } elsif (S_ISLNK($mode)) { return "symlink"; @@ -825,7 +1840,9 @@ sub file_type_long { $mode = oct $mode; } - if (S_ISDIR($mode & S_IFMT)) { + if (S_ISGITLINK($mode)) { + return "submodule"; + } elsif (S_ISDIR($mode & S_IFMT)) { return "directory"; } elsif (S_ISLNK($mode)) { return "symlink"; @@ -843,33 +1860,39 @@ sub file_type_long { ## ---------------------------------------------------------------------- ## functions returning short HTML fragments, or transforming HTML fragments -## which don't beling to other sections +## which don't belong to other sections # format line of commit message. sub format_log_line_html { my $line = shift; $line = esc_html($line, -nbsp=>1); - if ($line =~ m/([0-9a-fA-F]{40})/) { - my $hash_text = $1; - if (git_get_type($hash_text) eq "commit") { - my $link = - $cgi->a({-href => href(action=>"commit", hash=>$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; @@ -879,7 +1902,29 @@ sub format_ref_marker { $name = $ref; } - $markers .= " " . esc_html($name) . ""; + 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 .= " " . + $link . ""; } } @@ -896,33 +1941,510 @@ 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; } } -sub format_diff_line { - my $line = shift; - my $char = substr($line, 0, 1); - my $diff_class = ""; +# 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 = (); - chomp $line; - - if ($char eq '+') { - $diff_class = " add"; - } elsif ($char eq "-") { - $diff_class = " rem"; - } elsif ($char eq "@") { - $diff_class = " chunk_header"; - } elsif ($char eq "\\") { - $diff_class = " incomplete"; +# Compute the picon url for a given email, by using the picon search service over at +# http://www.cs.indiana.edu/picons/search.html +sub picon_url { + my $email = lc shift; + if (!$avatar_cache{$email}) { + my ($user, $domain) = split('@', $email); + $avatar_cache{$email} = + "//www.cs.indiana.edu/cgi-pub/kinzler/piconsearch.cgi/" . + "$domain/$user/" . + "users+domains+unknown/up/single"; } - $line = untabify($line); - return "
" . esc_html($line, -nbsp=>1) . "
\n"; + return $avatar_cache{$email}; +} + +# Compute the gravatar url for a given email, if it's not in the cache already. +# Gravatar stores only the part of the URL before the size, since that's the +# one computationally more expensive. This also allows reuse of the cache for +# different sizes (for this particular engine). +sub gravatar_url { + my $email = lc shift; + my $size = shift; + $avatar_cache{$email} ||= + "//www.gravatar.com/avatar/" . + 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 . + "" . $post_white; + } else { + return ""; + } +} + +sub format_search_author { + my ($author, $searchtype, $displaytext) = @_; + my $have_search = gitweb_check_feature('search'); + + if ($have_search) { + my $performed = ""; + if ($searchtype eq 'author') { + $performed = "authored"; + } elsif ($searchtype eq 'committer') { + $performed = "committed"; + } + + return $cgi->a({-href => href(action=>"search", hash=>$hash, + searchtext=>$author, + searchtype=>$searchtype), class=>"list", + title=>"Search for commits $performed by $author"}, + $displaytext); + + } else { + return $displaytext; + } +} + +# format the author name of the given commit with the given tag +# the author name is chopped and escaped according to the other +# optional parameters (see chop_str). +sub format_author_html { + my $tag = shift; + my $co = shift; + my $author = chop_and_escape_str($co->{'author_name'}, @_); + return "<$tag class=\"author\">" . + format_search_author($co->{'author_name'}, "author", + git_get_avatar($co->{'author_email'}, -pad_after => 1) . + $author) . + ""; +} + +# format git diff header line, i.e. "diff --(git|combined|cc) ..." +sub format_git_diff_header_line { + my $line = shift; + my $diffinfo = shift; + my ($from, $to) = @_; + + if ($diffinfo->{'nparents'}) { + # combined diff + $line =~ s!^(diff (.*?) )"?.*$!$1!; + if ($to->{'href'}) { + $line .= $cgi->a({-href => $to->{'href'}, -class => "path"}, + esc_path($to->{'file'})); + } else { # file was deleted (no href) + $line .= esc_path($to->{'file'}); + } + } else { + # "ordinary" diff + $line =~ s!^(diff (.*?) )"?a/.*$!$1!; + if ($from->{'href'}) { + $line .= $cgi->a({-href => $from->{'href'}, -class => "path"}, + 'a/' . esc_path($from->{'file'})); + } else { # file was added (no href) + $line .= 'a/' . esc_path($from->{'file'}); + } + $line .= ' '; + if ($to->{'href'}) { + $line .= $cgi->a({-href => $to->{'href'}, -class => "path"}, + 'b/' . esc_path($to->{'file'})); + } else { # file was deleted + $line .= 'b/' . esc_path($to->{'file'}); + } + } + + return "
$line
\n"; +} + +# format extended diff header line, before patch itself +sub format_extended_diff_header_line { + my $line = shift; + my $diffinfo = shift; + my ($from, $to) = @_; + + # match + if ($line =~ s!^((copy|rename) from ).*$!$1! && $from->{'href'}) { + $line .= $cgi->a({-href=>$from->{'href'}, -class=>"path"}, + esc_path($from->{'file'})); + } + if ($line =~ s!^((copy|rename) to ).*$!$1! && $to->{'href'}) { + $line .= $cgi->a({-href=>$to->{'href'}, -class=>"path"}, + esc_path($to->{'file'})); + } + # match single + if ($line =~ m/\s(\d{6})$/) { + $line .= ' (' . + file_type_long($1) . + ')'; + } + # match + if ($line =~ m/^index [0-9a-fA-F]{40},[0-9a-fA-F]{40}/) { + # can match only for combined diff + $line = 'index '; + for (my $i = 0; $i < $diffinfo->{'nparents'}; $i++) { + if ($from->{'href'}[$i]) { + $line .= $cgi->a({-href=>$from->{'href'}[$i], + -class=>"hash"}, + substr($diffinfo->{'from_id'}[$i],0,7)); + } else { + $line .= '0' x 7; + } + # separator + $line .= ',' if ($i < $diffinfo->{'nparents'} - 1); + } + $line .= '..'; + if ($to->{'href'}) { + $line .= $cgi->a({-href=>$to->{'href'}, -class=>"hash"}, + substr($diffinfo->{'to_id'},0,7)); + } else { + $line .= '0' x 7; + } + + } elsif ($line =~ m/^index [0-9a-fA-F]{40}..[0-9a-fA-F]{40}/) { + # can match only for ordinary diff + my ($from_link, $to_link); + if ($from->{'href'}) { + $from_link = $cgi->a({-href=>$from->{'href'}, -class=>"hash"}, + substr($diffinfo->{'from_id'},0,7)); + } else { + $from_link = '0' x 7; + } + if ($to->{'href'}) { + $to_link = $cgi->a({-href=>$to->{'href'}, -class=>"hash"}, + substr($diffinfo->{'to_id'},0,7)); + } else { + $to_link = '0' x 7; + } + my ($from_id, $to_id) = ($diffinfo->{'from_id'}, $diffinfo->{'to_id'}); + $line =~ s!$from_id\.\.$to_id!$from_link..$to_link!; + } + + return $line . "
\n"; +} + +# format from-file/to-file diff header +sub format_diff_from_to_header { + my ($from_line, $to_line, $diffinfo, $from, $to, @parents) = @_; + my $line; + my $result = ''; + + $line = $from_line; + #assert($line =~ m/^---/) if DEBUG; + # no extra formatting for "^--- /dev/null" + if (! $diffinfo->{'nparents'}) { + # ordinary (single parent) diff + if ($line =~ m!^--- "?a/!) { + if ($from->{'href'}) { + $line = '--- a/' . + $cgi->a({-href=>$from->{'href'}, -class=>"path"}, + esc_path($from->{'file'})); + } else { + $line = '--- a/' . + esc_path($from->{'file'}); + } + } + $result .= qq!
$line
\n!; + + } else { + # combined diff (merge commit) + for (my $i = 0; $i < $diffinfo->{'nparents'}; $i++) { + if ($from->{'href'}[$i]) { + $line = '--- ' . + $cgi->a({-href=>href(action=>"blobdiff", + hash_parent=>$diffinfo->{'from_id'}[$i], + hash_parent_base=>$parents[$i], + file_parent=>$from->{'file'}[$i], + hash=>$diffinfo->{'to_id'}, + hash_base=>$hash, + file_name=>$to->{'file'}), + -class=>"path", + -title=>"diff" . ($i+1)}, + $i+1) . + '/' . + $cgi->a({-href=>$from->{'href'}[$i], -class=>"path"}, + esc_path($from->{'file'}[$i])); + } else { + $line = '--- /dev/null'; + } + $result .= qq!
$line
\n!; + } + } + + $line = $to_line; + #assert($line =~ m/^\+\+\+/) if DEBUG; + # no extra formatting for "^+++ /dev/null" + if ($line =~ m!^\+\+\+ "?b/!) { + if ($to->{'href'}) { + $line = '+++ b/' . + $cgi->a({-href=>$to->{'href'}, -class=>"path"}, + esc_path($to->{'file'})); + } else { + $line = '+++ b/' . + esc_path($to->{'file'}); + } + } + $result .= qq!
$line
\n!; + + return $result; +} + +# create note for patch simplified by combined diff +sub format_diff_cc_simplified { + my ($diffinfo, @parents) = @_; + my $result = ''; + + $result .= "
" . + "diff --cc "; + if (!is_deleted($diffinfo)) { + $result .= $cgi->a({-href => href(action=>"blob", + hash_base=>$hash, + hash=>$diffinfo->{'to_id'}, + file_name=>$diffinfo->{'to_file'}), + -class => "path"}, + esc_path($diffinfo->{'to_file'})); + } else { + $result .= esc_path($diffinfo->{'to_file'}); + } + $result .= "
\n" . # class="diff header" + "
" . + "Simple merge" . + "
\n"; # class="diff nodifferences" + + return $result; +} + +sub diff_line_class { + my ($line, $from, $to) = @_; + + # ordinary diff + my $num_sign = 1; + # combined diff + if ($from && $to && ref($from->{'href'}) eq "ARRAY") { + $num_sign = scalar @{$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'}); + } + + # fallback + return ""; +} + +# 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, $to) = @_; + + my ($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 $to_lines; + + if ($from->{'href'}) { + $from_text = $cgi->a({-href=>"$from->{'href'}#l$from_start", + -class=>"list"}, $from_text); + } + if ($to->{'href'}) { + $to_text = $cgi->a({-href=>"$to->{'href'}#l$to_start", + -class=>"list"}, $to_text); + } + $line = "@@ $from_text $to_text @@" . + "" . esc_html($section, -nbsp=>1) . ""; + return $line; +} + +# assumes that $from and $to are defined and correctly filled, +# and that $line holds a line of chunk header for combined diff +sub format_cc_diff_chunk_header { + my ($line, $from, $to) = @_; + + my ($prefix, $ranges, $section) = $line =~ m/^(\@+) (.*?) \@+(.*)$/; + my (@from_text, @from_start, @from_nlines, $to_text, $to_start, $to_nlines); + + @from_text = split(' ', $ranges); + for (my $i = 0; $i < @from_text; ++$i) { + ($from_start[$i], $from_nlines[$i]) = + (split(',', substr($from_text[$i], 1)), 0); + } + + $to_text = pop @from_text; + $to_start = pop @from_start; + $to_nlines = pop @from_nlines; + + $line = "$prefix "; + for (my $i = 0; $i < @from_text; ++$i) { + if ($from->{'href'}[$i]) { + $line .= $cgi->a({-href=>"$from->{'href'}[$i]#l$from_start[$i]", + -class=>"list"}, $from_text[$i]); + } else { + $line .= $from_text[$i]; + } + $line .= " "; + } + if ($to->{'href'}) { + $line .= $cgi->a({-href=>"$to->{'href'}#l$to_start", + -class=>"list"}, $to_text); + } else { + $line .= $to_text; + } + $line .= " $prefix" . + "" . esc_html($section, -nbsp=>1) . ""; + return $line; +} + +# process patch (diff) line (not to be used for diff headers), +# returning HTML-formatted (but not wrapped) line. +# If the line is passed as a reference, it is treated as HTML and not +# esc_html()'ed. +sub format_diff_line { + my ($line, $diff_class, $from, $to) = @_; + + if (ref($line)) { + $line = $$line; + } else { + chomp $line; + $line = untabify($line); + + if ($from && $to && $line =~ m/^\@{2} /) { + $line = format_unidiff_chunk_header($line, $from, $to); + } elsif ($from && $to && $line =~ m/^\@{3}/) { + $line = format_cc_diff_chunk_header($line, $from, $to); + } else { + $line = esc_html($line, -nbsp=>1); + } + } + + my $diff_classes = "diff"; + $diff_classes .= " $diff_class" if ($diff_class); + $line = "
$line
\n"; + + return $line; +} + +# Generates undef or something like "_snapshot_" or "snapshot (_tbz2_ _zip_)", +# linked. Pass the hash of the tree/commit to snapshot. +sub format_snapshot_links { + my ($hash) = @_; + my $num_fmts = @snapshot_fmts; + if ($num_fmts > 1) { + # A parenthesized list of links bearing format names. + # e.g. "snapshot (_tar.gz_ _zip_)" + return "snapshot (" . join(' ', map + $cgi->a({ + -href => href( + action=>"snapshot", + hash=>$hash, + snapshot_format=>$_ + ) + }, $known_snapshot_formats{$_}{'display'}) + , @snapshot_fmts) . ")"; + } elsif ($num_fmts == 1) { + # A single "snapshot" link whose tooltip bears the format name. + # i.e. "_snapshot_" + my ($fmt) = @snapshot_fmts; + return + $cgi->a({ + -href => href( + action=>"snapshot", + hash=>$hash, + snapshot_format=>$fmt + ), + -title => "in format: $known_snapshot_formats{$fmt}{'display'}" + }, "snapshot"); + } else { # $num_fmts == 0 + return undef; + } +} + +## ...................................................................... +## 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)); + my $matched_ref = 0; + + # feed links are possible only for project views + return unless (defined $project); + # some views should link to OPML, or to generic project feed, + # or don't have specific feed yet (so they should use generic) + return if (!$action || $action =~ /^(?:tags|heads|forks|tag|search)$/x); + + my $branch = undef; + # branches refs uses 'refs/' + $get_branch_refs()[x] + '/' prefix + # (fullname) to differentiate from tag links; this also makes + # possible to detect branch links + for my $ref (get_branch_refs()) { + if ((defined $hash_base && $hash_base =~ m!^refs/\Q$ref\E/(.*)$!) || + (defined $hash && $hash =~ m!^refs/\Q$ref\E/(.*)$!)) { + $branch = $1; + $matched_ref = $ref; + last; + } + } + # find log type for feed description (title) + my $type = 'log'; + 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 $branch ? "refs/$matched_ref/$branch" : undef); + $res{'file_name'} = $file_name; + + return %res; } ## ---------------------------------------------------------------------- @@ -930,27 +2452,42 @@ sub format_diff_line { # 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; - my $head = gitweb_get_default_head($project); + 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; @@ -969,20 +2506,137 @@ sub git_get_type { return $type; } +# repository configuration +our $config_file = ''; +our %config; + +# store multiple values for single key as anonymous array reference +# single values stored directly in the hash, not as [ ] +sub hash_set_multi { + my ($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, $type) = @_; - return unless ($key); - $key =~ s/^gitweb\.//; - return if ($key =~ m/\W/); + return unless defined $git_dir; - my @x = (git_cmd(), 'repo-config'); - if (defined $type) { push @x, $type; } - push @x, "--get"; - push @x, "gitweb.$key"; - my $val = qx(@x); - chomp $val; - return ($val); + # key sanity check + return unless ($key); + # only subsection, if exists, is case sensitive, + # and not lowercased by 'git config -z -l' + if (my ($hi, $mi, $lo) = ($key =~ /^([^.]*)\.(.*)\.([^.]*)$/)) { + $lo =~ s/_//g; + $key = join(".", lc($hi), $mi, lc($lo)); + return if ($lo =~ /\W/ || $hi =~ /\W/); + } else { + $key = lc($key); + $key =~ s/_//g; + return if ($key =~ /\W/); + } + $key =~ s/^gitweb\.//; + + # 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 @@ -994,10 +2648,15 @@ 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; + if (!defined $line) { + # there is no tree or hash given by $path at $base + return undef; + } + #'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa panic.c' $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t/; if (defined $type && $type ne $2) { @@ -1007,23 +2666,192 @@ sub git_get_hash_by_path { return $3; } +# get path of entry with given hash at given tree-ish (ref) +# used to get 'from' filename for combined diff (merge commit) for renames +sub git_get_path_by_hash { + my $base = shift || return; + my $hash = shift || return; + + local $/ = "\0"; + + open my $fd, "-|", git_cmd(), "ls-tree", '-r', '-t', '-z', $base + or return undef; + while (my $line = <$fd>) { + chomp $line; + + #'040000 tree 595596a6a9117ddba9fe379b6b012b558bac8423 gitweb' + #'100644 blob e02e90f0429be0d2a69b76571101f20b8f75530f gitweb/README' + if ($line =~ m/(?:[0-9]+) (?:.+) $hash\t(.+)$/) { + close $fd; + return $1; + } + } + close $fd; + return undef; +} + ## ...................................................................... ## git utility functions, directly accessing git repository +# get the value of config variable either from file named as the variable +# itself in the repository ($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; - chomp $descr; - return $descr; +sub git_get_project_category { + my $path = shift; + return git_get_file_or_project_config($path, 'category'); +} + + +# supported formats: +# * $GIT_DIR/ctags/ file (in 'ctags' subdirectory) +# - if its contents is a number, use it as tag weight, +# - otherwise add a tag with weight 1 +# * $GIT_DIR/ctags file, each line is a tag (with weight 1) +# the same value multiple times increases tag weight +# * `gitweb.ctag' multi-valued repo config variable +sub git_get_project_ctags { + my $project = shift; + my $ctags = {}; + + $git_dir = "$projectroot/$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) { + $title = qq($title); + } + $cloud->add($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) { + $title = qq($title); + } + $cloud->{$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 + '
' . + join (', ', map { + $cloud->{$_}->{'ctag'} + } splice(@tags, 0, $count)) . + '
'; + } } 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 $fd; @@ -1031,36 +2859,50 @@ sub git_get_project_url_list { } sub git_get_projects_list { - my ($filter) = @_; + my $filter = shift || ''; + my $paranoid = shift; my @list; - $filter ||= ''; - $filter =~ s/\.git$//; - 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 ($check_forks) = gitweb_check_feature('forks'); + 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 $_); - - my $subdir = substr($File::Find::name, $pfxlen + 1); - # we check related file in $projectroot - if ($check_forks and $subdir =~ m#/.#) { + # 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) { $File::Find::prune = 1; - } elsif (check_export_ok("$projectroot/$filter/$subdir")) { - push @list, { path => ($filter ? "$filter/" : '') . $subdir }; + return; + } + + my $path = substr($File::Find::name, $pfxlen + 1); + # paranoidly only filter here + if ($paranoid && $filter && $path !~ m!^\Q$filter\E/!) { + next; + } + # we check related file in $projectroot + if (check_export_ok("$projectroot/$path")) { + push @list, { path => $path }; $File::Find::prune = 1; } }, @@ -1071,7 +2913,8 @@ sub git_get_projects_list { # 'git%2Fgit.git Linus+Torvalds' # 'libs%2Fklibc%2Fklibc.git H.+Peter+Anvin' # 'linux%2Fhotplug%2Fudev.git Greg+Kroah-Hartman' - open my ($fd), $projects_list or return; + open my $fd, '<', $projects_list or return; + PROJECT: while (my $line = <$fd>) { chomp $line; my ($path, $owner) = split ' ', $line; @@ -1080,57 +2923,163 @@ 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; - } - my $sfx = substr($path, length($filter)); - if ($sfx !~ /^\/.*\.git$/) { - next; - } + # 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 }; - push @list, $pr + if ($owner) { + $pr->{'owner'} = to_utf8($owner); + } + push @list, $pr; } } close $fd; } - @list = sort {$a->{'path'} cmp $b->{'path'}} @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 { + + return if (defined $gitweb_project_owner); + + $gitweb_project_owner = {}; + # read from file (url-encoded): + # 'git%2Fgit.git Linus+Torvalds' + # 'libs%2Fklibc%2Fklibc.git H.+Peter+Anvin' + # 'linux%2Fhotplug%2Fudev.git Greg+Kroah-Hartman' + if (-f $projects_list) { + open(my $fd, '<', $projects_list); + while (my $line = <$fd>) { + chomp $line; + my ($pr, $ow) = split ' ', $line; + $pr = unescape($pr); + $ow = unescape($ow); + $gitweb_project_owner->{$pr} = to_utf8($ow); + } + close $fd; + } +} + sub git_get_project_owner { my $project = shift; my $owner; return undef unless $project; + $git_dir = "$projectroot/$project"; - # read from file (url-encoded): - # 'git%2Fgit.git Linus+Torvalds' - # 'libs%2Fklibc%2Fklibc.git H.+Peter+Anvin' - # 'linux%2Fhotplug%2Fudev.git Greg+Kroah-Hartman' - if (-f $projects_list) { - open (my $fd , $projects_list); - while (my $line = <$fd>) { - chomp $line; - my ($pr, $ow) = split ' ', $line; - $pr = unescape($pr); - $ow = unescape($ow); - if ($pr eq $project) { - $owner = to_utf8($ow); - last; - } - } - close $fd; + if (!defined $gitweb_project_owner) { + git_get_project_list_from_file(); + } + + 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; @@ -1142,29 +3091,71 @@ sub git_get_last_activity { $git_dir = "$projectroot/$path"; open($fd, "-|", git_cmd(), 'for-each-ref', - '--format=%(refname) %(committer)', + '--format=%(committer)', '--sort=-committerdate', - 'refs/heads') or return; + '--count=1', + map { "refs/$_" } get_branch_refs ()) or return; my $most_recent = <$fd>; close $fd or return; - if ($most_recent =~ / (\d+) [-+][01]\d\d\d$/) { + if (defined $most_recent && + $most_recent =~ / (\d+) [-+][01]\d\d\d$/) { my $timestamp = $1; my $age = time - $timestamp; return ($age, age_string($age)); } + 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; - # 5dc01c595e6c6ec9ccda4f6f69c131c0dd945f8c refs/tags/v2.6.11 - # c39ae07f393806ccf406ef966e9a15afc43cc36a refs/tags/v2.6.11^{} - open my $fd, "-|", $GIT, "peek-remote", "$projectroot/$project/" + # 5dc01c595e6c6ec9ccda4f6f69c131c0dd945f8c refs/tags/v2.6.11 + # c39ae07f393806ccf406ef966e9a15afc43cc36a refs/tags/v2.6.11^{} + open my $fd, "-|", git_cmd(), "show-ref", "--dereference", + ($type ? ("--", "refs/$type") : ()) # use -- if $type or return; while (my $line = <$fd>) { chomp $line; - if ($line =~ m/^([0-9a-fA-F]{40})\trefs\/($type\/?[^\^]+)/) { + if ($line =~ m!^([0-9a-fA-F]{40})\srefs/($type.*)$!) { if (defined $refs{$1}) { push @{$refs{$1}}, $2; } else { @@ -1208,20 +3199,24 @@ sub parse_date { $date{'mday'} = $mday; $date{'day'} = $days[$wday]; $date{'month'} = $months[$mon]; - $date{'rfc2822'} = sprintf "%s, %d %s %4d %02d:%02d:%02d +0000", - $days[$wday], $mday, $months[$mon], 1900+$year, $hour ,$min, $sec; + $date{'rfc2822'} = sprintf "%s, %d %s %4d %02d:%02d:%02d +0000", + $days[$wday], $mday, $months[$mon], 1900+$year, $hour ,$min, $sec; $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, 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; $date{'tz_local'} = $tz; - $date{'iso-tz'} = sprintf ("%04d-%02d-%02d %02d:%02d:%02d %s", - 1900+$year, $mon+1, $mday, - $hour, $min, $sec, $tz); + $date{'iso-tz'} = sprintf("%04d-%02d-%02d %02d:%02d:%02d %s", + 1900+$year, $mon+1, $mday, + $hour, $min, $sec, $tz); return %date; } @@ -1242,8 +3237,14 @@ 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; @@ -1260,56 +3261,55 @@ sub parse_tag { return %tag } -sub parse_commit { - my $commit_id = shift; - my $commit_text = shift; - - my @commit_lines; +sub parse_commit_text { + my ($commit_text, $withparents) = @_; + my @commit_lines = split '\n', $commit_text; my %co; - if (defined $commit_text) { - @commit_lines = @$commit_text; - } else { - local $/ = "\0"; - open my $fd, "-|", git_cmd(), "rev-list", - "--header", "--parents", "--max-count=1", - $commit_id, "--" - or return; - @commit_lines = split '\n', <$fd>; - close $fd or return; - pop @commit_lines; + pop @commit_lines; # Remove '\0' + + if (! @commit_lines) { + return; } + my $header = shift @commit_lines; - if (!($header =~ m/^[0-9a-fA-F]{40}/)) { + if ($header !~ m/^[0-9a-fA-F]{40}/) { return; } ($co{'id'}, my @parents) = split ' ', $header; - $co{'parents'} = \@parents; - $co{'parent'} = $parents[0]; while (my $line = shift @commit_lines) { last if $line eq "\n"; if ($line =~ m/^tree ([0-9a-fA-F]{40})$/) { $co{'tree'} = $1; + } 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/^([^<]+) ]*)>/) { + $co{'author_name'} = $1; + $co{'author_email'} = $2; } else { $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'}; - $co{'committer_name'} =~ s/ <.*//; + if ($co{'committer'} =~ m/^([^<]+) <([^>]*)>/) { + $co{'committer_name'} = $1; + $co{'committer_email'} = $2; + } else { + $co{'committer_name'} = $co{'committer'}; + } } } if (!defined $co{'tree'}) { return; }; + $co{'parents'} = \@parents; + $co{'parent'} = $parents[0]; foreach my $title (@commit_lines) { $title =~ s/^ //; @@ -1336,7 +3336,7 @@ sub parse_commit { last; } } - if ($co{'title'} eq "") { + if (! defined $co{'title'} || $co{'title'} eq "") { $co{'title'} = $co{'title_short'} = '(no commit message)'; } # remove added spaces @@ -1359,47 +3359,51 @@ sub parse_commit { return %co; } -# 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; +sub parse_commit { + my ($commit_id) = @_; + my %co; - $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; + local $/ = "\0"; + + open my $fd, "-|", git_cmd(), "rev-list", + "--parents", + "--header", + "--max-count=1", + $commit_id, + "--", + or die_error(500, "Open git-rev-list failed"); + %co = parse_commit_text(<$fd>, 1); + close $fd; + + return %co; +} + +sub parse_commits { + my ($commit_id, $maxcount, $skip, $filename, @args) = @_; + my @cos; + + $maxcount ||= 1; + $skip ||= 0; + + local $/ = "\0"; + + open my $fd, "-|", git_cmd(), "rev-list", + "--header", + @args, + ("--max-count=" . $maxcount), + ("--skip=" . $skip), + @extra_options, + $commit_id, + "--", + ($filename ? ($filename) : ()) + or die_error(500, "Open git-rev-list failed"); + while (my $line = <$fd>) { + my %co = parse_commit_text($line); + push @cos, \%co; } + close $fd; - return %ref_item; + return wantarray ? @cos : \@cos; } # parse line of git-diff-tree "raw" output @@ -1419,9 +3423,20 @@ sub parse_difftree_raw_line { if ($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($7); } } + # '::100755 100755 100755 60e79ca1b01bc8b057abe17ddab484699a7f5fdb 94067cc5f73388f33722d52ae02f44692bc07490 94067cc5f73388f33722d52ae02f44692bc07490 MR git-gui/git-gui.sh' + # combined diff (for merge commit) + elsif ($line =~ s/^(::+)((?:[0-7]{6} )+)((?:[0-9a-fA-F]{40} )+)([a-zA-Z]+)\t(.*)$//) { + $res{'nparents'} = length($1); + $res{'from_mode'} = [ split(' ', $2) ]; + $res{'to_mode'} = pop @{$res{'from_mode'}}; + $res{'from_id'} = [ split(' ', $3) ]; + $res{'to_id'} = pop @{$res{'from_id'}}; + $res{'status'} = [ split('', $4) ]; + $res{'to_file'} = unquote($5); + } # 'c512b523472485aef4fff9e57b229d9d243c967f' elsif ($line =~ m/^([0-9a-fA-F]{40})$/) { $res{'commit'} = $1; @@ -1430,38 +3445,114 @@ 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($4); + } } return wantarray ? %res : \%res; } +# generates _two_ hashes, references to which are passed as 2 and 3 argument +sub parse_from_to_diffinfo { + my ($diffinfo, $from, $to, @parents) = @_; + + if ($diffinfo->{'nparents'}) { + # combined diff + $from->{'file'} = []; + $from->{'href'} = []; + fill_from_file_info($diffinfo, @parents) + unless exists $diffinfo->{'from_file'}; + for (my $i = 0; $i < $diffinfo->{'nparents'}; $i++) { + $from->{'file'}[$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], + hash=>$diffinfo->{'from_id'}[$i], + file_name=>$from->{'file'}[$i]); + } else { + $from->{'href'}[$i] = undef; + } + } + } else { + # 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=>$diffinfo->{'from_id'}, + file_name=>$from->{'file'}); + } else { + delete $from->{'href'}; + } + } + + $to->{'file'} = $diffinfo->{'to_file'}; + if (!is_deleted($diffinfo)) { # file exists in result + $to->{'href'} = href(action=>"blob", hash_base=>$hash, + hash=>$diffinfo->{'to_id'}, + file_name=>$to->{'file'}); + } else { + delete $to->{'href'}; + } +} + ## ...................................................................... ## parse to array of hashes functions sub git_get_heads_list { - my $limit = shift; + my ($limit, @classes) = @_; + @classes = get_branch_refs() unless @classes; + my @patterns = map { "refs/$_" } @classes; my @headslist; open my $fd, '-|', git_cmd(), 'for-each-ref', ($limit ? '--count='.($limit+1) : ()), '--sort=-committerdate', '--format=%(objectname) %(refname) %(subject)%00%(committer)', - 'refs/heads' + @patterns or return; while (my $line = <$fd>) { my %ref_item; @@ -1471,9 +3562,17 @@ 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; + my $strip_refs = join '|', map { quotemeta } get_branch_refs(); + $name =~ s!^refs/($strip_refs|remotes)/!!; + $ref_item{'name'} = $name; + # for refs neither in 'heads' nor 'remotes' we want to + # show their ref dir + my $ref_dir = (defined $1) ? $1 : ''; + if ($ref_dir ne '' and $ref_dir ne 'heads' and $ref_dir ne 'remotes') { + $ref_item{'name'} .= ' (' . $ref_dir . ')'; + } - $ref_item{'name'} = $name; $ref_item{'id'} = $hash; $ref_item{'title'} = $title || '(no commit message)'; $ref_item{'epoch'} = $epoch; @@ -1508,6 +3607,7 @@ sub git_get_tags_list { my ($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'} = $type; @@ -1554,6 +3654,15 @@ sub get_file_owner { return to_utf8($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 @@ -1563,18 +3672,15 @@ sub mimetype_guess_file { -r $mimemap or return undef; my %mimemap; - open(MIME, $mimemap) or return undef; - while () { + open(my $mh, '<', $mimemap) or return undef; + while (<$mh>) { next if m/^#/; # skip comments - my ($mime, $exts) = split(/\t+/); - if (defined $exts) { - my @exts = split(/\s+/, $exts); - foreach my $ext (@exts) { - $mimemap{$ext} = $mime; - } + my ($mimetype, @exts) = split(/\s+/); + foreach my $ext (@exts) { + $mimemap{$ext} = $mimetype; } } - close(MIME); + close($mh); $filename =~ /\.([^.]*)$/; return $mimemap{$1}; @@ -1610,8 +3716,7 @@ 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$/i) { @@ -1625,27 +3730,75 @@ sub blob_mimetype { } } +sub blob_contenttype { + my ($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 .= " - $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 @@ -1653,13 +3806,165 @@ 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'; } - $content_type = '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 "\n"; + + $href_params{'extra_options'} = '--no-merges'; + $link_attr{'-href'} = href(%href_params); + $link_attr{'-title'} .= ' (no merges)'; + print "\n"; + } + + } else { + printf(''."\n", + esc_attr($site_name), href(project=>undef, action=>"project_index")); + printf(''."\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 ''."\n"; + } else { + foreach my $stylesheet (@stylesheets) { + next unless $stylesheet; + print ''."\n"; + } + } + print_feed_meta() + if ($status eq '200 OK'); + if (defined $favicon) { + print qq(\n); + } +} + +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 = @_; + + for my $crumb (@extra_breadcrumbs, [ $home_link_str => $home_link ]) { + print $cgi->a({-href => esc_url($crumb->[1])}, $crumb->[0]) . " / "; + } + if (defined $project) { + my @dirname = split '/', $project; + my $projectbasename = pop @dirname; + 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 => $action) . + "
\n" . + (!$use_pathinfo && + $cgi->input({-name=>"p", -value=>$project, -type=>"hidden"}) . "\n") . + $cgi->input({-name=>"a", -value=>"search", -type=>"hidden"}) . "\n" . + $cgi->input({-name=>"h", -value=>$search_hash, -type=>"hidden"}) . "\n" . + $cgi->popup_menu(-name => 'st', -default => 'commit', + -values => ['commit', 'grep', 'author', 'committer', 'pickaxe']) . + " " . $cgi->a({-href => href(action=>"search_help"), + -title => "search help" }, "?") . " search:\n", + $cgi->textfield(-name => "s", -value => $searchtext, -override => 1) . "\n" . + "" . + $cgi->checkbox(-name => 'sr', -value => 1, -label => 're', + -checked => $search_use_regexp) . + "" . + "
" . + $cgi->end_form() . "\n"; +} + +sub git_header_html { + my $status = shift || "200 OK"; + my $expires = shift; + my %opts = @_; + + my $title = get_page_title(); + 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 < @@ -1668,127 +3973,170 @@ sub git_header_html { - + $title EOF -# print out each stylesheet that exist - if (defined $stylesheet) { -#provides backwards capability for those people who define style sheet in a config file - print ''."\n"; - } else { - foreach my $stylesheet (@stylesheets) { - next unless $stylesheet; - print ''."\n"; - } + # the stylesheet, favicon etc urls won't work correctly with path_info + # unless we set the appropriate base URL + if ($ENV{'PATH_INFO'}) { + print "\n"; } - if (defined $project) { - printf(''."\n", - esc_param($project), href(action=>"rss")); - } else { - printf(''."\n", - $site_name, href(project=>undef, action=>"project_index")); - printf(''."\n", - $site_name, href(project=>undef, action=>"opml")); - } - if (defined $favicon) { - print qq(\n); + print_header_links($status); + + if (defined $site_html_head_string) { + print to_utf8($site_html_head_string); } print "\n" . "\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 "
\n" . - $cgi->a({-href => esc_url($logo_url), - -title => $logo_label}, - qq()); - 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"; - 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"; - } - $cgi->param("a", "search"); - $cgi->param("h", $search_hash); - $cgi->param("p", $project); - print $cgi->startform(-method => "get", -action => $my_uri) . - "
\n" . - $cgi->hidden(-name => "p") . "\n" . - $cgi->hidden(-name => "a") . "\n" . - $cgi->hidden(-name => gitweb_get_default_head($project)) . "\n" . - $cgi->popup_menu(-name => 'st', -default => 'commit', - -values => ['commit', 'author', 'committer', 'pickaxe']) . - $cgi->sup($cgi->a({-href => href(action=>"search_help")}, "?")) . - " search:\n", - $cgi->textfield(-name => "s", -value => $searchtext) . "\n" . - "
" . - $cgi->end_form() . "\n"; + print "
\n"; + if (defined $logo) { + print $cgi->a({-href => esc_url($logo_url), + -title => $logo_label}, + $cgi->img({-src => esc_url($logo), + -width => 72, -height => 27, + -alt => "git", + -class => "logo"})); } - print "
\n"; + print_nav_breadcrumbs(%opts); + print "
\n"; + + my $have_search = gitweb_check_feature('search'); + if (defined $project && $have_search && 0) { + print_search_form(); + } + print "
\n"; + } sub git_footer_html { - print "
\n"; + print "
\n"; + my $feed_class = 'rss_logo'; + + print "
\n"; if (defined $project) { my $descr = git_get_project_description($project); if (defined $descr) { print "
" . esc_html($descr) . "
\n"; } - print $cgi->a({-href => href(action=>"rss"), - -class => "rss_logo"}, "RSS") . "\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 "
\n" ; - if (-f $site_footer) { - open (my $fd, $site_footer); - print <$fd>; - close $fd; + 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", + 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 "
\n"; # class="page_footer" + + if (defined $t0 && gitweb_check_feature('timed')) { + print "
\n"; + print 'This page took '. + ''. + tv_interval($t0, [ gettimeofday() ]). + ' seconds '. + ' and '. + ''. + $number_of_git_cmds. + ' git commands '. + " to generate.\n"; + print "
\n"; # class="page_footer" + } + + if (defined $site_footer && -f $site_footer) { + insert_file($site_footer); + } + + print qq!\n!; + if (defined $action && + $action eq 'blame_incremental') { + print qq!\n!; + } else { + my ($jstimezone, $tz_cookie, $datetime_class) = + gitweb_get_feature('javascript-timezone'); + + print qq!\n!; } print "\n" . ""; } +# die_error(, [, ]) +# 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 <

$status - $error
- EOF + if (defined $extra) { + print "
\n" . + "$extra\n"; + } + print "\n"; + git_footer_html(); - exit; + goto DONE_GITWEB + unless ($opts{'-error_handler'}); } ## ---------------------------------------------------------------------- @@ -1806,48 +4154,83 @@ sub git_print_page_nav { my %arg = map { $_ => {action=>$_} } @navs; if (defined $head) { for (qw(commit commitdiff)) { - $arg{$_}{hash} = $head; + $arg{$_}{'hash'} = $head; } if ($current =~ m/^(tree | log | shortlog | commit | commitdiff | search)$/x) { for (qw(shortlog log)) { - $arg{$_}{hash} = $head; + $arg{$_}{'hash'} = $head; } } } - $arg{tree}{hash} = $treehead if defined $treehead; - $arg{tree}{hash_base} = $treebase if defined $treebase; + + $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 "
\n" . (join " | ", map { $_ eq $current ? - $_ : $cgi->a({-href => href(%{$arg{$_}})}, "$_") + $_ : $cgi->a({-href => ($arg{$_}{_href} ? $arg{$_}{_href} : href(%{$arg{$_}}))}, "$_") } @navs); + if ($file_name && $project =~ /^ports\//) { + print " | Download port"; + } +# print "
"; +# print $file_name; +# print "
"; +# print $file_name; +# } print "
\n$extra
\n" . "
\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 { $paging_nav .= " ⋅ next"; @@ -1863,9 +4246,9 @@ sub git_print_header_div { my ($action, $title, $hash, $hash_base) = @_; my %args = (); - $args{action} = $action; - $args{hash} = $hash if $hash; - $args{hash_base} = $hash_base if $hash_base; + $args{'action'} = $action; + $args{'hash'} = $hash if $hash; + $args{'hash_base'} = $hash_base if $hash_base; print "
\n" . $cgi->a({-href => href(%args), -class => "title"}, @@ -1873,22 +4256,111 @@ sub git_print_header_div { "\n
\n"; } -#sub git_print_authorship (\%) { +sub format_repo_url { + my ($name, $url) = @_; + return "$name$url\n"; +} + +# Group output by placing it in a DIV element and adding a header. +# Options for start_div() can be provided by passing a hash reference as the +# first parameter to the function. +# Options to git_print_header_div() can be provided by passing an array +# reference. This must follow the options to start_div if they are present. +# The content can be a scalar, which is output as-is, a scalar reference, which +# is output after html escaping, an IO handle passed either as *handle or +# *handle{IO}, or a function reference. In the latter case all following +# parameters will be taken as argument to the content function call. +sub git_print_section { + my ($div_args, $header_args, $content); + my $arg = shift; + if (ref($arg) eq 'HASH') { + $div_args = $arg; + $arg = shift; + } + if (ref($arg) eq 'ARRAY') { + $header_args = $arg; + $arg = shift; + } + $content = $arg; + + print $cgi->start_div($div_args); + git_print_header_div(@$header_args); + + if (ref($content) eq 'CODE') { + $content->(@_); + } elsif (ref($content) eq 'SCALAR') { + print esc_html($$content); + } elsif (ref($content) eq 'GLOB' or ref($content) eq 'IO::Handle') { + print <$content>; + } elsif (!ref($content) && defined($content)) { + print $content; + } + + print $cgi->end_div; +} + +sub format_timestamp_html { + my $date = shift; + my $strtime = $date->{'rfc2822'}; + + my (undef, undef, $datetime_class) = + gitweb_get_feature('javascript-timezone'); + if ($datetime_class) { + $strtime = qq!$strtime!; + } + + my $localtime_format = '(%02d:%02d %s)'; + if ($date->{'hour_local'} < 6) { + $localtime_format = '(%02d:%02d %s)'; + } + $strtime .= ' ' . + sprintf($localtime_format, + $date->{'hour_local'}, $date->{'minute_local'}, $date->{'tz_local'}); + + return $strtime; +} + +# Outputs the author name and date in long form sub git_print_authorship { my $co = shift; + my %opts = @_; + my $tag = $opts{-tag} || 'div'; + my $author = $co->{'author_name'}; my %ad = parse_date($co->{'author_epoch'}, $co->{'author_tz'}); - print "
" . - esc_html($co->{'author_name'}) . - " [$ad{'rfc2822'}"; - if ($ad{'hour_local'} < 6) { - printf(" (%02d:%02d %s)", - $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); - } else { - printf(" (%02d:%02d %s)", - $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); + print "<$tag class=\"author_date\">" . + format_search_author($author, "author", esc_html($author)) . + " [".format_timestamp_html(\%ad)."]". + git_get_avatar($co->{'author_email'}, -pad_before => 1) . + "\n"; +} + +# Outputs table rows containing the full author or committer information, +# in the format expected for 'commit' view (& similar). +# Parameters are a commit hash reference, followed by the list of people +# to output information for. If the list is empty it defaults to both +# author and committer. +sub git_print_authorship_rows { + my $co = shift; + # too bad we can't use @people = @_ || ('author', 'committer') + my @people = @_; + @people = ('author', 'committer') unless @people; + foreach my $who (@people) { + my %wd = parse_date($co->{"${who}_epoch"}, $co->{"${who}_tz"}); + print "$who" . + format_search_author($co->{"${who}_name"}, $who, + esc_html($co->{"${who}_name"})) . " " . + format_search_author($co->{"${who}_email"}, $who, + esc_html("<" . $co->{"${who}_email"} . ">")) . + "" . + git_get_avatar($co->{"${who}_email"}, -size => 'double') . + "\n" . + "" . + "" . + format_timestamp_html(\%wd) . + "" . + "\n"; } - print "]
\n"; } sub git_print_page_path { @@ -1899,7 +4371,7 @@ sub git_print_page_path { print "
"; print $cgi->a({-href => href(action=>"tree", hash_base=>$hb), - -title => 'tree root'}, "[$project]"); + -title => 'tree root'}, to_utf8("[$project]")); print " / "; if (defined $name) { my @dirname = split '/', $name; @@ -1910,17 +4382,17 @@ sub git_print_page_path { $fullname .= ($fullname ? '/' : '') . $dir; print $cgi->a({-href => href(action=>"tree", file_name=>$fullname, hash_base=>$hb), - -title => esc_html($fullname)}, esc_path($dir)); + -title => $fullname}, esc_path($dir)); print " / "; } if (defined $type && $type eq 'blob') { print $cgi->a({-href => href(action=>"blob_plain", file_name=>$file_name, hash_base=>$hb), - -title => esc_html($name)}, esc_path($basename)); + -title => $name}, esc_path($basename)); } elsif (defined $type && $type eq 'tree') { print $cgi->a({-href => href(action=>"tree", file_name=>$file_name, hash_base=>$hb), - -title => esc_html($name)}, esc_path($basename)); + -title => $name}, esc_path($basename)); print " / "; } else { print esc_path($basename); @@ -1929,8 +4401,7 @@ sub git_print_page_path { print "
\n"; } -# sub git_print_log (\@;%) { -sub git_print_log ($;%) { +sub git_print_log { my $log = shift; my %opts = @_; @@ -1944,30 +4415,33 @@ sub git_print_log ($;%) { } # print log - my $signoff = 0; - my $empty = 0; + my $skip_blank_line = 0; foreach my $line (@$log) { - if ($line =~ m/^ *(signed[ \-]off[ \-]by[ :]|acked[ \-]by[ :]|cc[ :])/i) { - $signoff = 1; - $empty = 0; + if ($line =~ m/^\s*([A-Z][-A-Za-z]*-[Bb]y|C[Cc]): /) { if (! $opts{'-remove_signoff'}) { print "" . esc_html($line) . "
\n"; - next; - } else { - # remove signoff lines - next; + $skip_blank_line = 1; } - } else { - $signoff = 0; + next; + } + + if ($line =~ m,\s*([a-z]*link): (https?://\S+),i) { + if (! $opts{'-remove_signoff'}) { + print "" . esc_html($1) . ": " . + "" . esc_html($2) . "" . + "
\n"; + $skip_blank_line = 1; + } + next; } # print only one empty line # do not print empty line after signoff if ($line eq "") { - next if ($empty || $signoff); - $empty = 1; + next if ($skip_blank_line); + $skip_blank_line = 1; } else { - $empty = 0; + $skip_blank_line = 0; } print format_log_line_html($line) . "
\n"; @@ -1975,36 +4449,112 @@ sub git_print_log ($;%) { if ($opts{'-final_empty_line'}) { # end with single empty line - print "
\n" unless $empty; + print "
\n" unless $skip_blank_line; } } +# return link target (what link points to) +sub git_get_link_target { + my $hash = shift; + my $link_target; + + # read link + open my $fd, "-|", git_cmd(), "cat-file", "blob", $hash + or return; + { + local $/ = undef; + $link_target = <$fd>; + } + close $fd + or return; + + return $link_target; +} + +# given link target, and the directory (basedir) the link is in, +# return target of link relative to top directory (top tree); +# return undef if it is not possible (including absolute links). +sub normalize_link_target { + my ($link_target, $basedir) = @_; + + # absolute symlinks (beginning with '/') cannot be normalized + return if (substr($link_target, 0, 1) eq '/'); + + # normalize link target to path from top (root) tree (dir) + my $path; + if ($basedir) { + $path = $basedir . '/' . $link_target; + } else { + # we are in top (root) tree (dir) + $path = $link_target; + } + + # remove //, /./, and /../ + my @path_parts; + foreach my $part (split('/', $path)) { + # discard '.' and '' + next if (!$part || $part eq '.'); + # handle '..' + if ($part eq '..') { + if (@path_parts) { + pop @path_parts; + } else { + # link leads outside repository (outside top dir) + return; + } + } else { + push @path_parts, $part; + } + } + $path = join('/', @path_parts); + + return $path; +} + # print tree entry (row of git_tree), but without encompassing element sub git_print_tree_entry { my ($t, $basedir, $hash_base, $have_blame) = @_; my %base_key = (); - $base_key{hash_base} = $hash_base if defined $hash_base; + $base_key{'hash_base'} = $hash_base if defined $hash_base; # The format of a table row is: mode list link. Where mode is # the mode of the entry, list is the name of the entry, an href, # and link is the action links of the entry. print "" . mode_str($t->{'mode'}) . "\n"; + if (exists $t->{'size'}) { + print "$t->{'size'}\n"; + } if ($t->{'type'} eq "blob") { print "" . $cgi->a({-href => href(action=>"blob", hash=>$t->{'hash'}, file_name=>"$basedir$t->{'name'}", %base_key), - -class => "list"}, esc_path($t->{'name'})) . "\n"; + -class => "list"}, esc_path($t->{'name'})); + 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); + if (defined $norm_target) { + print " -> " . + $cgi->a({-href => href(action=>"object", hash_base=>$hash_base, + file_name=>$norm_target), + -title => $norm_target}, esc_path($link_target)); + } else { + print " -> " . esc_path($link_target); + } + } + } + print "\n"; print ""; print $cgi->a({-href => href(action=>"blob", hash=>$t->{'hash'}, - file_name=>"$basedir$t->{'name'}", %base_key)}, - "blob"); + file_name=>"$basedir$t->{'name'}", %base_key)}, + "blob"); if ($have_blame) { print " | " . $cgi->a({-href => href(action=>"blame", hash=>$t->{'hash'}, - file_name=>"$basedir$t->{'name'}", %base_key)}, - "blame"); + file_name=>"$basedir$t->{'name'}", %base_key)}, + "blame"); } if (defined $hash_base) { print " | " . @@ -2021,19 +4571,38 @@ sub git_print_tree_entry { } elsif ($t->{'type'} eq "tree") { print ""; print $cgi->a({-href => href(action=>"tree", hash=>$t->{'hash'}, - file_name=>"$basedir$t->{'name'}", %base_key)}, + file_name=>"$basedir$t->{'name'}", + %base_key)}, esc_path($t->{'name'})); print "\n"; print ""; print $cgi->a({-href => href(action=>"tree", hash=>$t->{'hash'}, - file_name=>"$basedir$t->{'name'}", %base_key)}, - "tree"); + file_name=>"$basedir$t->{'name'}", + %base_key)}, + "tree"); if (defined $hash_base) { print " | " . $cgi->a({-href => href(action=>"history", hash_base=>$hash_base, file_name=>"$basedir$t->{'name'}")}, "history"); } + if ($project =~ /^ports\//) { + print " | {'name'}\">Download port"; + } + print "\n"; + } else { + # unknown object: we can only present history for it + # (this includes 'commit' object, i.e. submodule support) + print "" . + esc_path($t->{'name'}) . + "\n"; + print ""; + if (defined $hash_base) { + print $cgi->a({-href => href(action=>"history", + hash_base=>$hash_base, + file_name=>"$basedir$t->{'name'}")}, + "history"); + } print "\n"; } } @@ -2041,20 +4610,79 @@ 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) = @_; + + $diff->{'from_file'} = [ ]; + $diff->{'from_file'}[$diff->{'nparents'} - 1] = undef; + for (my $i = 0; $i < $diff->{'nparents'}; $i++) { + if ($diff->{'status'}[$i] eq 'R' || + $diff->{'status'}[$i] eq 'C') { + $diff->{'from_file'}[$i] = + git_get_path_by_hash($parents[$i], $diff->{'from_id'}[$i]); + } + } + + return $diff; +} + +# 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, $parent) = @_; - my ($have_blame) = gitweb_check_feature('blame'); + my ($difftree, $hash, @parents) = @_; + my ($parent) = $parents[0]; + my $have_blame = gitweb_check_feature('blame'); print "
\n"; if ($#{$difftree} > 10) { print(($#{$difftree} + 1) . " files changed:\n"); } print "
\n"; - print "\n"; + print "
1 ? "combined " : "") . + "diff_tree\">\n"; + + # header only for combined diff in 'commitdiff' view + my $has_header = @$difftree && @parents > 1 && $action eq 'commitdiff'; + if ($has_header) { + # table header + print "\n" . + "\n"; # filename, patchN link + for (my $i = 0; $i < @parents; $i++) { + my $par = $parents[$i]; + print "\n"; + } + print "\n\n"; + } + my $alternate = 1; my $patchno = 0; foreach my $line (@{$difftree}) { - my %diff = parse_difftree_raw_line($line); + my $diff = parsed_difftree_line($line); if ($alternate) { print "\n"; @@ -2063,76 +4691,170 @@ sub git_difftree_body { } $alternate ^= 1; + if (exists $diff->{'nparents'}) { # combined diff + + fill_from_file_info($diff, @parents) + unless exists $diff->{'from_file'}; + + if (!is_deleted($diff)) { + # file exists in the result (child) commit + print "\n"; + } else { + print "\n"; + } + + if ($action eq 'commitdiff') { + # link to patch + $patchno++; + print "\n"; + } + + my $has_history = 0; + my $not_deleted = 0; + for (my $i = 0; $i < $diff->{'nparents'}; $i++) { + my $hash_parent = $parents[$i]; + my $from_hash = $diff->{'from_id'}[$i]; + my $from_path = $diff->{'from_file'}[$i]; + my $status = $diff->{'status'}[$i]; + + $has_history ||= ($status ne 'A'); + $not_deleted ||= ($status ne 'D'); + + if ($status eq 'A') { + print "\n"; + } elsif ($status eq 'D') { + print "\n"; + } else { + if ($diff->{'to_id'} eq $from_hash) { + print "\n"; + } + } + + print "\n"; + + print "\n"; + next; # instead of 'else' clause, to avoid extra indent + } + # else ordinary diff + my ($to_mode_oct, $to_mode_str, $to_file_type); my ($from_mode_oct, $from_mode_str, $from_file_type); - if ($diff{'to_mode'} ne ('0' x 6)) { - $to_mode_oct = oct $diff{'to_mode'}; + if ($diff->{'to_mode'} ne ('0' x 6)) { + $to_mode_oct = oct $diff->{'to_mode'}; if (S_ISREG($to_mode_oct)) { # only for regular file $to_mode_str = sprintf("%04o", $to_mode_oct & 0777); # permission bits } - $to_file_type = file_type($diff{'to_mode'}); + $to_file_type = file_type($diff->{'to_mode'}); } - 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 ($diff->{'from_mode'} ne ('0' x 6)) { + $from_mode_oct = oct $diff->{'from_mode'}; + if (S_ISREG($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'}); + $from_file_type = file_type($diff->{'from_mode'}); } - if ($diff{'status'} eq "A") { # created + if ($diff->{'status'} eq "A") { # created my $mode_chng = "[new $to_file_type"; $mode_chng .= " with mode: $to_mode_str" if $to_mode_str; $mode_chng .= "]"; print "\n"; print "\n"; print "\n"; - } elsif ($diff{'status'} eq "D") { # deleted + } elsif ($diff->{'status'} eq "D") { # deleted my $mode_chng = "[deleted $from_file_type]"; print "\n"; print "\n"; print "\n"; - } elsif ($diff{'status'} eq "M" || $diff{'status'} eq "T") { # modified, or type changed + } elsif ($diff->{'status'} eq "M" || $diff->{'status'} eq "T") { # modified, or type changed my $mode_chnge = ""; - if ($diff{'from_mode'} != $diff{'to_mode'}) { + if ($diff->{'from_mode'} != $diff->{'to_mode'}) { $mode_chnge = "[changed"; - if ($from_file_type != $to_file_type) { + if ($from_file_type ne $to_file_type) { $mode_chnge .= " from $from_file_type to $to_file_type"; } if (($from_mode_oct & 0777) != ($to_mode_oct & 0777)) { @@ -2145,347 +4867,712 @@ sub git_difftree_body { $mode_chnge .= "]\n"; } print "\n"; print "\n"; print "\n"; - } elsif ($diff{'status'} eq "R" || $diff{'status'} eq "C") { # renamed or copied + } elsif ($diff->{'status'} eq "R" || $diff->{'status'} eq "C") { # renamed or copied my %status_name = ('R' => 'moved', 'C' => 'copied'); - my $nstatus = $status_name{$diff{'status'}}; + my $nstatus = $status_name{$diff->{'status'}}; my $mode_chng = ""; - if ($diff{'from_mode'} != $diff{'to_mode'}) { + if ($diff->{'from_mode'} != $diff->{'to_mode'}) { # mode also for directories, so we cannot use $to_mode_str $mode_chng = sprintf(", mode: %04o", $to_mode_oct & 0777); } print "\n" . + hash=>$diff->{'to_id'}, file_name=>$diff->{'to_file'}), + -class => "list"}, esc_path($diff->{'to_file'})) . "\n" . "\n" . + hash=>$diff->{'from_id'}, file_name=>$diff->{'from_file'}), + -class => "list"}, esc_path($diff->{'from_file'})) . + " with " . (int $diff->{'similarity'}) . "% similarity$mode_chng]\n" . "\n"; } # we should not encounter Unmerged (U) or Unknown (X) status print "\n"; } + print "" if $has_header; print "
" . + $cgi->a({-href => href(action=>"commitdiff", + hash=>$hash, hash_parent=>$par), + -title => 'commitdiff to parent number ' . + ($i+1) . ': ' . substr($par,0,7)}, + $i+1) . + " 
" . + $cgi->a({-href => href(action=>"blob", hash=>$diff->{'to_id'}, + file_name=>$diff->{'to_file'}, + hash_base=>$hash), + -class => "list"}, esc_path($diff->{'to_file'})) . + "" . + esc_path($diff->{'to_file'}) . + "" . + $cgi->a({-href => href(-anchor=>"patch$patchno")}, + "patch") . + " | " . + " | " . + $cgi->a({-href => href(action=>"blob", + hash_base=>$hash, + hash=>$from_hash, + file_name=>$from_path)}, + "blob" . ($i+1)) . + " | "; + } else { + print ""; + } + print $cgi->a({-href => href(action=>"blobdiff", + hash=>$diff->{'to_id'}, + hash_parent=>$from_hash, + hash_base=>$hash, + hash_parent_base=>$hash_parent, + file_name=>$diff->{'to_file'}, + file_parent=>$from_path)}, + "diff" . ($i+1)) . + " | "; + if ($not_deleted) { + print $cgi->a({-href => href(action=>"blob", + hash=>$diff->{'to_id'}, + file_name=>$diff->{'to_file'}, + hash_base=>$hash)}, + "blob"); + print " | " if ($has_history); + } + if ($has_history) { + print $cgi->a({-href => href(action=>"history", + file_name=>$diff->{'to_file'}, + hash_base=>$hash)}, + "history"); + } + print "
"; - print $cgi->a({-href => href(action=>"blob", hash=>$diff{'to_id'}, - hash_base=>$hash, file_name=>$diff{'file'}), - -class => "list"}, esc_path($diff{'file'})); + print $cgi->a({-href => href(action=>"blob", hash=>$diff->{'to_id'}, + hash_base=>$hash, file_name=>$diff->{'file'}), + -class => "list"}, esc_path($diff->{'file'})); print "$mode_chng"; if ($action eq 'commitdiff') { # link to patch $patchno++; - print $cgi->a({-href => "#patch$patchno"}, "patch"); + 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'})}, + "blob"); print ""; - print $cgi->a({-href => href(action=>"blob", hash=>$diff{'from_id'}, - hash_base=>$parent, file_name=>$diff{'file'}), - -class => "list"}, esc_path($diff{'file'})); + print $cgi->a({-href => href(action=>"blob", hash=>$diff->{'from_id'}, + hash_base=>$parent, file_name=>$diff->{'file'}), + -class => "list"}, esc_path($diff->{'file'})); print "$mode_chng"; 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'})}, - "blob") . " | "; + print $cgi->a({-href => href(action=>"blob", hash=>$diff->{'from_id'}, + hash_base=>$parent, file_name=>$diff->{'file'})}, + "blob") . " | "; if ($have_blame) { - print $cgi->a({-href => - href(action=>"blame", - hash_base=>$parent, - file_name=>$diff{'file'})}, - "blame") . " | "; + print $cgi->a({-href => href(action=>"blame", hash_base=>$parent, + file_name=>$diff->{'file'})}, + "blame") . " | "; } print $cgi->a({-href => href(action=>"history", hash_base=>$parent, - file_name=>$diff{'file'})}, + file_name=>$diff->{'file'})}, "history"); print ""; - print $cgi->a({-href => href(action=>"blob", hash=>$diff{'to_id'}, - hash_base=>$hash, file_name=>$diff{'file'}), - -class => "list"}, esc_path($diff{'file'})); + print $cgi->a({-href => href(action=>"blob", hash=>$diff->{'to_id'}, + hash_base=>$hash, file_name=>$diff->{'file'}), + -class => "list"}, esc_path($diff->{'file'})); print "$mode_chnge"; 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 $diff{'from_id'}) { + } elsif ($diff->{'to_id'} ne $diff->{'from_id'}) { # "commit" view and modified file (not onlu mode changed) print $cgi->a({-href => href(action=>"blobdiff", - hash=>$diff{'to_id'}, hash_parent=>$diff{'from_id'}, + hash=>$diff->{'to_id'}, hash_parent=>$diff->{'from_id'}, hash_base=>$hash, hash_parent_base=>$parent, - file_name=>$diff{'file'})}, + file_name=>$diff->{'file'})}, "diff") . " | "; } - print $cgi->a({-href => href(action=>"blob", hash=>$diff{'to_id'}, - hash_base=>$hash, file_name=>$diff{'file'})}, - "blob") . " | "; + print $cgi->a({-href => href(action=>"blob", hash=>$diff->{'to_id'}, + hash_base=>$hash, file_name=>$diff->{'file'})}, + "blob") . " | "; if ($have_blame) { - print $cgi->a({-href => href(action=>"blame", - hash_base=>$hash, - file_name=>$diff{'file'})}, - "blame") . " | "; + print $cgi->a({-href => href(action=>"blame", hash_base=>$hash, + file_name=>$diff->{'file'})}, + "blame") . " | "; } print $cgi->a({-href => href(action=>"history", hash_base=>$hash, - file_name=>$diff{'file'})}, + file_name=>$diff->{'file'})}, "history"); print "" . $cgi->a({-href => href(action=>"blob", hash_base=>$hash, - hash=>$diff{'to_id'}, file_name=>$diff{'to_file'}), - -class => "list"}, esc_path($diff{'to_file'})) . "[$nstatus from " . $cgi->a({-href => href(action=>"blob", hash_base=>$parent, - hash=>$diff{'from_id'}, file_name=>$diff{'from_file'}), - -class => "list"}, esc_path($diff{'from_file'})) . - " with " . (int $diff{'similarity'}) . "% similarity$mode_chng]"; 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 $diff{'from_id'}) { + } elsif ($diff->{'to_id'} ne $diff->{'from_id'}) { # "commit" view and modified file (not only pure rename or copy) print $cgi->a({-href => href(action=>"blobdiff", - hash=>$diff{'to_id'}, hash_parent=>$diff{'from_id'}, + hash=>$diff->{'to_id'}, hash_parent=>$diff->{'from_id'}, hash_base=>$hash, hash_parent_base=>$parent, - file_name=>$diff{'to_file'}, file_parent=>$diff{'from_file'})}, + file_name=>$diff->{'to_file'}, file_parent=>$diff->{'from_file'})}, "diff") . " | "; } - print $cgi->a({-href => href(action=>"blob", hash=>$diff{'from_id'}, - hash_base=>$parent, file_name=>$diff{'from_file'})}, - "blob") . " | "; + print $cgi->a({-href => href(action=>"blob", hash=>$diff->{'to_id'}, + hash_base=>$parent, file_name=>$diff->{'to_file'})}, + "blob") . " | "; if ($have_blame) { - print $cgi->a({-href => href(action=>"blame", - hash_base=>$hash, - file_name=>$diff{'to_file'})}, - "blame") . " | "; + print $cgi->a({-href => href(action=>"blame", hash_base=>$hash, + file_name=>$diff->{'to_file'})}, + "blame") . " | "; } - print $cgi->a({-href => href(action=>"history", hash_base=>$parent, - file_name=>$diff{'from_file'})}, + print $cgi->a({-href => href(action=>"history", hash_base=>$hash, + file_name=>$diff->{'to_file'})}, "history"); print "
\n"; } -sub git_patchset_body { - my ($fd, $difftree, $hash, $hash_parent) = @_; +# Print context lines and then rem/add lines in a side-by-side manner. +sub print_sidebyside_diff_lines { + my ($ctx, $rem, $add) = @_; + # print context block before add/rem block + if (@$ctx) { + print join '', + '
', + '
', + @$ctx, + '
', + '
', + @$ctx, + '
', + '
'; + } + + if (!@$add) { + # pure removal + print join '', + '
', + '
', + @$rem, + '
', + '
'; + } elsif (!@$rem) { + # pure addition + print join '', + '
', + '
', + @$add, + '
', + '
'; + } else { + print join '', + '
', + '
', + @$rem, + '
', + '
', + @$add, + '
', + '
'; + } +} + +# Print context lines and then rem/add lines in inline manner. +sub print_inline_diff_lines { + my ($ctx, $rem, $add) = @_; + + print @$ctx, @$rem, @$add; +} + +# Format removed and added line, mark changed part and HTML-format them. +# Implementation is based on contrib/diff-highlight +sub format_rem_add_lines_pair { + my ($rem, $add, $num_parents) = @_; + + # We need to untabify lines before split()'ing them; + # otherwise offsets would be invalid. + chomp $rem; + chomp $add; + $rem = untabify($rem); + $add = untabify($add); + + my @rem = split(//, $rem); + my @add = split(//, $add); + my ($esc_rem, $esc_add); + # Ignore leading +/- characters for each parent. + my ($prefix_len, $suffix_len) = ($num_parents, 0); + my ($prefix_has_nonspace, $suffix_has_nonspace); + + my $shorter = (@rem < @add) ? @rem : @add; + while ($prefix_len < $shorter) { + last if ($rem[$prefix_len] ne $add[$prefix_len]); + + $prefix_has_nonspace = 1 if ($rem[$prefix_len] !~ /\s/); + $prefix_len++; + } + + while ($prefix_len + $suffix_len < $shorter) { + last if ($rem[-1 - $suffix_len] ne $add[-1 - $suffix_len]); + + $suffix_has_nonspace = 1 if ($rem[-1 - $suffix_len] !~ /\s/); + $suffix_len++; + } + + # Mark lines that are different from each other, but have some common + # part that isn't whitespace. If lines are completely different, don't + # mark them because that would make output unreadable, especially if + # diff consists of multiple lines. + if ($prefix_has_nonspace || $suffix_has_nonspace) { + $esc_rem = esc_html_hl_regions($rem, 'marked', + [$prefix_len, @rem - $suffix_len], -nbsp=>1); + $esc_add = esc_html_hl_regions($add, 'marked', + [$prefix_len, @add - $suffix_len], -nbsp=>1); + } else { + $esc_rem = esc_html($rem, -nbsp=>1); + $esc_add = esc_html($add, -nbsp=>1); + } + + return format_diff_line(\$esc_rem, 'rem'), + format_diff_line(\$esc_add, 'add'); +} + +# HTML-format diff context, removed and added lines. +sub format_ctx_rem_add_lines { + my ($ctx, $rem, $add, $num_parents) = @_; + my (@new_ctx, @new_rem, @new_add); + my $can_highlight = 0; + my $is_combined = ($num_parents > 1); + + # Highlight if every removed line has a corresponding added line. + if (@$add > 0 && @$add == @$rem) { + $can_highlight = 1; + + # Highlight lines in combined diff only if the chunk contains + # diff between the same version, e.g. + # + # - a + # - b + # + c + # + d + # + # Otherwise the highlightling would be confusing. + if ($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, $diff_style, $difftree, $hash, @hash_parents) = @_; + my ($hash_parent) = $hash_parents[0]; + + my $is_combined = (@hash_parents > 1); my $patch_idx = 0; - my $in_header = 0; - my $patch_found = 0; + my $patch_number = 0; + my $patch_line; my $diffinfo; + my $to_name; my (%from, %to); + my @chunk; # for side-by-side diff print "
\n"; - LINE: - while (my $patch_line = <$fd>) { + # skip to first patch + while ($patch_line = <$fd>) { chomp $patch_line; - if ($patch_line =~ m/^diff /) { # "git diff" header - # beginning of patch (in patchset) - if ($patch_found) { - # close extended header for previous empty patch - if ($in_header) { - print "
\n" # class="diff extended_header" - } - # close previous patch - print "\n"; # class="patch" - } else { - # first patch in patchset - $patch_found = 1; - } - print "
\n"; + last if ($patch_line =~ m/^diff /); + } + + PATCH: + while ($patch_line) { + + # parse "git diff" header line + if ($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 { + $to_name = undef; + } + + # check if current patch belong to current raw line + # and parse raw git-diff line if needed + if (is_patch_split($diffinfo, { 'to_file' => $to_name })) { + # this is continuation of a split patch + print "
\n"; + } else { + # advance raw git-diff output if needed + $patch_idx++ if defined $diffinfo; # read and prepare patch information - if (ref($difftree->[$patch_idx]) eq "HASH") { - # pre-parsed (or generated by hand) - $diffinfo = $difftree->[$patch_idx]; - } else { - $diffinfo = parse_difftree_raw_line($difftree->[$patch_idx]); - } - $from{'file'} = $diffinfo->{'from_file'} || $diffinfo->{'file'}; - $to{'file'} = $diffinfo->{'to_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'}); - } - if ($diffinfo->{'status'} ne "D") { # not deleted file - $to{'href'} = href(action=>"blob", hash_base=>$hash, - hash=>$diffinfo->{'to_id'}, - file_name=>$to{'file'}); - } - $patch_idx++; + $diffinfo = parsed_difftree_line($difftree->[$patch_idx]); - # print "git diff" header - $patch_line =~ s!^(diff (.*?) )"?a/.*$!$1!; - if ($from{'href'}) { - $patch_line .= $cgi->a({-href => $from{'href'}, -class => "path"}, - 'a/' . esc_path($from{'file'})); - } else { # file was added - $patch_line .= 'a/' . esc_path($from{'file'}); - } - $patch_line .= ' '; - if ($to{'href'}) { - $patch_line .= $cgi->a({-href => $to{'href'}, -class => "path"}, - 'b/' . esc_path($to{'file'})); - } else { # file was deleted - $patch_line .= 'b/' . esc_path($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 $diffinfo->{'to_file'}) { + print "
\n" . + format_diff_cc_simplified($diffinfo, @hash_parents) . + "
\n"; # class="patch" + + $patch_idx++; + $patch_number++; + + last if $patch_idx > $#$difftree; + $diffinfo = parsed_difftree_line($difftree->[$patch_idx]); + } } - print "
$patch_line
\n"; - print "
\n"; - $in_header = 1; - next LINE; + # modifies %from, %to hashes + parse_from_to_diffinfo($diffinfo, \%from, \%to, @hash_parents); + + # this is first patch for raw difftree line with $patch_idx index + # we index @$difftree array from 0, but number patches from 1 + print "
\n"; } - if ($in_header) { - if ($patch_line !~ m/^---/) { - # match - if ($patch_line =~ s!^((copy|rename) from ).*$!$1! && $from{'href'}) { - $patch_line .= $cgi->a({-href=>$from{'href'}, -class=>"path"}, - esc_path($from{'file'})); - } - if ($patch_line =~ s!^((copy|rename) to ).*$!$1! && $to{'href'}) { - $patch_line = $cgi->a({-href=>$to{'href'}, -class=>"path"}, - esc_path($to{'file'})); - } - # match - if ($patch_line =~ m/\s(\d{6})$/) { - $patch_line .= ' (' . - file_type_long($1) . - ')'; - } - # match - if ($patch_line =~ m/^index/) { - my ($from_link, $to_link); - if ($from{'href'}) { - $from_link = $cgi->a({-href=>$from{'href'}, -class=>"hash"}, - substr($diffinfo->{'from_id'},0,7)); - } else { - $from_link = '0' x 7; - } - if ($to{'href'}) { - $to_link = $cgi->a({-href=>$to{'href'}, -class=>"hash"}, - substr($diffinfo->{'to_id'},0,7)); - } else { - $to_link = '0' x 7; - } - my ($from_id, $to_id) = ($diffinfo->{'from_id'}, $diffinfo->{'to_id'}); - $patch_line =~ s!$from_id\.\.$to_id!$from_link..$to_link!; - } - print $patch_line . "
\n"; + # git diff header + #assert($patch_line =~ m/^diff /) if DEBUG; + #assert($patch_line !~ m!$/$!) if DEBUG; # is chomp-ed + $patch_number++; + # print "git diff" header + print format_git_diff_header_line($patch_line, $diffinfo, + \%from, \%to); - } else { - #$in_header && $patch_line =~ m/^---/; - print "
\n"; # class="diff extended_header" - $in_header = 0; + # print extended diff header + print "
\n"; + EXTENDED_HEADER: + while ($patch_line = <$fd>) { + chomp $patch_line; - if ($from{'href'}) { - $patch_line = '--- a/' . - $cgi->a({-href=>$from{'href'}, -class=>"path"}, - esc_path($from{'file'})); - } - print "
$patch_line
\n"; + last EXTENDED_HEADER if ($patch_line =~ m/^--- |^diff /); - $patch_line = <$fd>; - chomp $patch_line; + print format_extended_diff_header_line($patch_line, $diffinfo, + \%from, \%to); + } + print "
\n"; # class="diff extended_header" - #$patch_line =~ m/^+++/; - if ($to{'href'}) { - $patch_line = '+++ b/' . - $cgi->a({-href=>$to{'href'}, -class=>"path"}, - esc_path($to{'file'})); - } - print "
$patch_line
\n"; + # from-file/to-file diff header + if (! $patch_line) { + print "
\n"; # class="patch" + last PATCH; + } + next PATCH if ($patch_line =~ m/^diff /); + #assert($patch_line =~ m/^---/) if DEBUG; + my $last_patch_line = $patch_line; + $patch_line = <$fd>; + chomp $patch_line; + #assert($patch_line =~ m/^\+\+\+/) if DEBUG; + + print format_diff_from_to_header($last_patch_line, $patch_line, + $diffinfo, \%from, \%to, + @hash_parents); + + # the patch itself + LINE: + while ($patch_line = <$fd>) { + chomp $patch_line; + + next PATCH if ($patch_line =~ m/^diff /); + + 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 = (); } - next LINE; + push @chunk, [ $class, $patch_line ]; } - print format_diff_line($patch_line); + } continue { + if (@chunk) { + print_diff_chunk($diff_style, scalar @hash_parents, \%from, \%to, @chunk); + @chunk = (); + } + print "
\n"; # class="patch" } - print "
\n" if $in_header; # extended header - print "\n" if $patch_found; # class="patch" + # for compact combined (--cc) format, with chunk and patch simplification + # the patchset might be empty, but there might be unprocessed raw lines + for (++$patch_idx if $patch_number > 0; + $patch_idx < @$difftree; + ++$patch_idx) { + # read and prepare patch information + $diffinfo = parsed_difftree_line($difftree->[$patch_idx]); + + # generate anchor for "patch" links in difftree / whatchanged part + print "
\n" . + format_diff_cc_simplified($diffinfo, @hash_parents) . + "
\n"; # class="patch" + + $patch_number++; + } + + if ($patch_number == 0) { + if (@hash_parents > 1) { + print "
Trivial merge
\n"; + } else { + print "
No differences found
\n"; + } + } print "\n"; # class="patchset" } # . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . -sub git_project_list_body { - my ($projlist, $order, $from, $to, $extra, $no_header) = @_; +sub git_project_search_form { + my ($searchtext, $search_use_regexp) = @_; - my ($check_forks) = gitweb_check_feature('forks'); + my $limit = ''; + if ($project_filter) { + $limit = " in '$project_filter/'"; + } + print "
\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" . + "" . + $cgi->checkbox(-name => 'sr', -value => 1, -label => 're', + -checked => $search_use_regexp) . + "\n" . + $cgi->submit(-name => 'btnS', -value => 'Search') . + $cgi->end_form() . "\n" . + $cgi->a({-href => href(project => undef, searchtext => undef, + project_filter => $project_filter)}, + esc_html("List all projects$limit")) . "
\n"; + print "
\n"; +} + +# entry for given @keys needs filling if at least one of keys in list +# is not present in %$project_info +sub project_info_needs_filling { + my ($project_info, @keys) = @_; + + # return List::MoreUtils::any { !exists $project_info->{$_} } @keys; + foreach my $key (@keys) { + if (!exists $project_info->{$key}) { + return 1; + } + } + return; +} + +# fills project list info (age, description, owner, category, forks, etc.) +# for each project in the list, removing invalid projects from +# returned list, or fill only specified info. +# +# Invalid projects are removed from the returned list if and only if you +# ask 'age' or 'age_string' to be filled, because they are the only fields +# that run unconditionally git command that requires repository, and +# therefore do always check if project repository is invalid. +# +# USAGE: +# * fill_project_list_info(\@project_list, 'descr_long', 'ctags') +# ensures that 'descr_long' and 'ctags' fields are filled +# * @project_list = fill_project_list_info(\@project_list) +# ensures that all fields are filled (and invalid projects removed) +# +# NOTE: modifies $projlist, but does not remove entries from it +sub fill_project_list_info { + my ($projlist, @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'}) || ""; - $pr->{'descr'} = chop_str($descr, 25, 5); + $descr = to_utf8($descr); + $pr->{'descr_long'} = $descr; + $pr->{'descr'} = chop_str($descr, $projects_list_description_width, 5); } - if (!defined $pr->{'owner'}) { - $pr->{'owner'} = get_file_owner("$projectroot/$pr->{'path'}") || ""; + if (project_info_needs_filling($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 ||= "project"; - $from = 0 unless defined $from; - $to = $#projects if (!defined $to || $#projects < $to); + return @projects; +} - print "\n"; - unless ($no_header) { - print "\n"; - if ($check_forks) { - print "\n"; - } - if ($order eq "project") { - @projects = sort {$a->{'path'} cmp $b->{'path'}} @projects; - print "\n"; - } else { - print "\n"; - } - if ($order eq "descr") { - @projects = sort {$a->{'descr'} cmp $b->{'descr'}} @projects; - print "\n"; - } else { - print "\n"; - } - if ($order eq "owner") { - @projects = sort {$a->{'owner'} cmp $b->{'owner'}} @projects; - print "\n"; - } else { - print "\n"; - } - if ($order eq "age") { - @projects = sort {$a->{'age'} <=> $b->{'age'}} @projects; - print "\n"; - } else { - print "\n"; - } - print "\n" . - "\n"; +sub sort_projects_list { + my ($projlist, $order) = @_; + + sub order_str { + my $key = shift; + return sub { $a->{$key} cmp $b->{$key} }; } + + sub order_num_then_undef { + my $key = shift; + return sub { + defined $a->{$key} ? + (defined $b->{$key} ? $a->{$key} <=> $b->{$key} : -1) : + (defined $b->{$key} ? 1 : 0) + }; + } + + my %orderings = ( + project => order_str('path'), + descr => order_str('descr_long'), + owner => order_str('owner'), + age => order_num_then_undef('age'), + ); + + my $ordering = $orderings{$order}; + return defined $ordering ? sort $ordering @$projlist : @$projlist; +} + +# returns a hash of categories, containing the list of project +# belonging to each category +sub build_projlist_by_category { + my ($projlist, $from, $to) = @_; + my %categories; + + $from = 0 unless defined $from; + $to = $#$projlist if (!defined $to || $#$projlist < $to); + + for (my $i = $from; $i <= $to; $i++) { + my $pr = $projlist->[$i]; + push @{$categories{ $pr->{'category'} }}, $pr; + } + + return wantarray ? %categories : \%categories; +} + +# print 'sort by' \n"; + } else { + $sort_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 "\n"; } else { print "\n"; } $alternate ^= 1; + if ($check_forks) { print "\n"; } print "\n" . - "\n" . - "\n"; - print "\n" . - "\n" . + "\n"; +# "\n"; + unless ($omit_owner) { + print "\n"; + } + unless ($omit_age_column) { + print "\n"; + } + print"\n" . "\n"; } +} + +sub git_project_list_body { + # actually uses global variable $project + my ($projlist, $order, $from, $to, $extra, $no_header) = @_; + my @projects = @$projlist; + + my $check_forks = gitweb_check_feature('forks'); + my $show_ctags = gitweb_check_feature('ctags'); + my $tagfilter = $show_ctags ? $input_params{'ctag'} : undef; + $check_forks = undef + if ($tagfilter || $search_regexp); + + # filtering out forks before filling info allows to do less work + @projects = filter_forks_from_projects_list(\@projects) + if ($check_forks); + # search_projects_list pre-fills required info + @projects = search_projects_list(\@projects, + 'search_regexp' => $search_regexp, + 'tagfilter' => $tagfilter) + if ($tagfilter || $search_regexp); + # fill the rest + my @all_fields = ('descr', 'descr_long', 'ctags', 'category'); + push @all_fields, ('age', 'age_string') unless($omit_age_column); + push @all_fields, 'owner' unless($omit_owner); + @projects = fill_project_list_info(\@projects, @all_fields); + + $order ||= $default_projects_order; + $from = 0 unless defined $from; + $to = $#projects if (!defined $to || $#projects < $to); + + # short circuit + if ($from > $to) { + print "
\n". + "No such projects found
\n". + "Click ".$cgi->a({-href=>href(project=>undef)},"here")." to view all projects
\n". + "
\n
\n"; + return; + } + + @projects = sort_projects_list(\@projects, $order); + + if ($show_ctags) { + my $ctags = git_gather_all_ctags(\@projects); + my $cloud = git_populate_project_tagcloud($ctags); + print git_show_project_tagcloud($cloud, 64); + } + + print "
Project" . - $cgi->a({-href => href(project=>undef, order=>'project'), - -class => "header"}, "Project") . - "Description" . - $cgi->a({-href => href(project=>undef, order=>'descr'), - -class => "header"}, "Description") . - "Owner" . - $cgi->a({-href => href(project=>undef, order=>'owner'), - -class => "header"}, "Owner") . - "Last Change" . - $cgi->a({-href => href(project=>undef, order=>'age'), - -class => "header"}, "Last Change") . - "
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) { + $sort_th .= "$header" . + $cgi->a({-href => href(-replay=>1, order=>$name), + -class => "header"}, $header) . + "
"; if ($pr->{'forks'}) { - print "\n"; - print $cgi->a({-href => href(project=>$pr->{'path'}, action=>"forks")}, "+"); + my $nforks = scalar @{$pr->{'forks'}}; + if ($nforks > 0) { + print $cgi->a({-href => href(project=>$pr->{'path'}, action=>"forks"), + -title => "$nforks forks"}, "+"); + } else { + print $cgi->span({-title => "$nforks forks"}, "+"); + } } print "" . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"summary"), - -class => "list"}, esc_html($pr->{'path'})) . "" . esc_html($pr->{'descr'}) . "" . chop_str($pr->{'owner'}, 15) . "{'age'}) . "\">" . - $pr->{'age_string'} . "" . + -class => "list"}, + esc_html_match_hl($pr->{'path'}, $search_regexp)) . + "" . esc_html($pr->{'descr'}) . + "" . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"summary"), +# -class => "list", +# -title => $pr->{'descr_long'}}, +# $search_regexp +# ? esc_html_match_hl_chopped($pr->{'descr_long'}, +# $pr->{'descr'}, $search_regexp) +# : esc_html($pr->{'descr'})) . +# "" . chop_and_escape_str($pr->{'owner'}, 15) . "{'age'}) . "\">" . + (defined $pr->{'age_string'} ? $pr->{'age_string'} : "No commits") . "" . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"summary")}, "summary") . " | " . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"shortlog")}, "shortlog") . " | " . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"log")}, "log") . " | " . @@ -2494,6 +5581,88 @@ sub git_project_list_body { "
\n"; + unless ($no_header) { + print "\n"; + if ($check_forks) { + print "\n"; + } + print_sort_th('project', $order, 'Project'); + print_sort_th('descr', $order, 'Description'); + print_sort_th('owner', $order, 'Owner') unless $omit_owner; + print_sort_th('age', $order, 'Last Change') unless $omit_age_column; + print "\n" . # for links + "\n"; + } + + if ($projects_list_group_categories) { + # only display categories with projects in the $from-$to window + @projects = sort {$a->{'category'} cmp $b->{'category'}} @projects[$from..$to]; + my %categories = build_projlist_by_category(\@projects, $from, $to); + foreach my $cat (sort keys %categories) { + unless ($cat eq "") { + print "\n"; + if ($check_forks) { + print "\n"; + } + print "\n"; + print "\n"; + } + + git_project_list_rows($categories{$cat}, undef, undef, $check_forks); + } + } else { + git_project_list_rows(\@projects, $from, $to, $check_forks); + } + if (defined $extra) { print "\n"; if ($check_forks) { @@ -2505,20 +5674,58 @@ sub git_project_list_body { print "
".esc_html($cat)."
\n"; } -sub git_shortlog_body { +sub git_log_body { # uses global variable $project - my ($revlist, $from, $to, $refs, $extra) = @_; + my ($commitlist, $from, $to, $refs, $extra) = @_; $from = 0 unless defined $from; - $to = $#{$revlist} if (!defined $to || $#{$revlist} < $to); + $to = $#{$commitlist} if (!defined $to || $#{$commitlist} < $to); - print "\n"; + for (my $i = 0; $i <= $to; $i++) { + my %co = %{$commitlist->[$i]}; + next if !%co; + my $commit = $co{'id'}; + my $ref = format_ref_marker($refs, $commit); + git_print_header_div('commit', + "$co{'age_string'}" . + esc_html($co{'title'}) . $ref, + $commit); + print "
\n" . + "
\n" . + $cgi->a({-href => href(action=>"commit", hash=>$commit)}, "commit") . + " | " . + $cgi->a({-href => href(action=>"commitdiff", hash=>$commit)}, "commitdiff") . + " | " . + $cgi->a({-href => href(action=>"tree", hash=>$commit, hash_base=>$commit)}, "tree") . + "
\n" . + "
\n"; + git_print_authorship(\%co, -tag => 'span'); + print "
\n
\n"; + + print "
\n"; + git_print_log($co{'comment'}, -final_empty_line=> 1); + print "
\n"; + } + if ($extra) { + print "
\n"; + print "$extra\n"; + print "
\n"; + } +} + +sub git_shortlog_body { + # uses global variable $project + my ($commitlist, $from, $to, $refs, $extra) = @_; + + $from = 0 unless defined $from; + $to = $#{$commitlist} if (!defined $to || $#{$commitlist} < $to); + + print "
\n"; my $alternate = 1; for (my $i = $from; $i <= $to; $i++) { - my $commit = $revlist->[$i]; - #my $ref = defined $refs ? format_ref_marker($refs, $commit) : ''; + my %co = %{$commitlist->[$i]}; + my $commit = $co{'id'}; my $ref = format_ref_marker($refs, $commit); - my %co = parse_commit($commit); if ($alternate) { print "\n"; } else { @@ -2527,8 +5734,7 @@ sub git_shortlog_body { $alternate ^= 1; # git_summary() used print "\n" . print "\n" . - "\n" . - "\n" . @@ -2536,8 +5742,9 @@ sub git_shortlog_body { $cgi->a({-href => href(action=>"commit", hash=>$commit)}, "commit") . " | " . $cgi->a({-href => href(action=>"commitdiff", hash=>$commit)}, "commitdiff") . " | " . $cgi->a({-href => href(action=>"tree", hash=>$commit, hash_base=>$commit)}, "tree"); - if (gitweb_have_snapshot()) { - print " | " . $cgi->a({-href => href(action=>"snapshot", hash=>$commit)}, "snapshot"); + my $snapshot_links = format_snapshot_links($commit); + if (defined $snapshot_links) { + print " | " . $snapshot_links; } print "\n" . "\n"; @@ -2552,23 +5759,20 @@ sub git_shortlog_body { sub git_history_body { # Warning: assumes constant type (blob or tree) during history - my ($revlist, $from, $to, $refs, $hash_base, $ftype, $extra) = @_; + my ($commitlist, $from, $to, $refs, $extra, + $file_name, $file_hash, $ftype) = @_; $from = 0 unless defined $from; - $to = $#{$revlist} unless (defined $to && $to <= $#{$revlist}); + $to = $#{$commitlist} unless (defined $to && $to <= $#{$commitlist}); - print "
$co{'age_string'}$co{'age_string_date'}" . esc_html(chop_str($co{'author_name'}, 10)) . ""; + format_author_html('td', \%co, 10) . ""; print format_subject_html($co{'title'}, $co{'title_short'}, href(action=>"commit", hash=>$commit), $ref); print "
\n"; + print "
\n"; my $alternate = 1; for (my $i = $from; $i <= $to; $i++) { - if ($revlist->[$i] !~ m/^([0-9a-fA-F]{40})/) { - next; - } - - my $commit = $1; - my %co = parse_commit($commit); + my %co = %{$commitlist->[$i]}; if (!%co) { next; } + my $commit = $co{'id'}; my $ref = format_ref_marker($refs, $commit); @@ -2579,9 +5783,8 @@ sub git_history_body { } $alternate ^= 1; print "\n" . - # shortlog uses chop_str($co{'author_name'}, 10) - "\n" . - "\n". + "
$co{'age_string_date'}" . esc_html(chop_str($co{'author_name'}, 15, 3)) . ""; + # shortlog: format_author_html('td', \%co, 10) + format_author_html('td', \%co, 15, 3) . ""; # originally git_history used chop_str($co{'title'}, 50) print format_subject_html($co{'title'}, $co{'title_short'}, href(action=>"commit", hash=>$commit), $ref); @@ -2591,7 +5794,7 @@ 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) { @@ -2620,7 +5823,7 @@ sub git_tags_body { $from = 0 unless defined $from; $to = $#{$taglist} if (!defined $to || $#{$taglist} < $to); - print "\n"; + print "
\n"; my $alternate = 1; for (my $i = $from; $i <= $to; $i++) { my $entry = $taglist->[$i]; @@ -2636,8 +5839,12 @@ sub git_tags_body { print "\n"; } $alternate ^= 1; - print "\n" . - "\n"; + } else { + print "\n"; + } + print "\n" . @@ -2657,8 +5864,8 @@ sub git_tags_body { "" . + "" . + "" . + "\n"; } } - open my $fd, "-|", git_cmd(), "rev-list", "--max-count=17", - git_get_head_hash($project), "--" - or die_error(undef, "Open git-rev-list failed"); - my @revlist = map { chomp; $_ } <$fd>; - close $fd; - git_print_header_div('shortlog'); - git_shortlog_body(\@revlist, 0, 15, $refs, - $cgi->a({-href => href(action=>"shortlog")}, "...")); + print "
$tag{'age'}" . + if (defined $tag{'age'}) { + print "$tag{'age'}" . $cgi->a({-href => href(action=>$tag{'reftype'}, hash=>$tag{'refid'}), -class => "list name"}, esc_html($tag{'name'})) . "" . " | " . $cgi->a({-href => href(action=>$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"); } @@ -2675,16 +5882,16 @@ 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 "\n"; + print "
\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 "\n"; } else { @@ -2693,13 +5900,13 @@ sub git_heads_body { $alternate ^= 1; print "\n" . ($curr ? "\n" . "\n" . ""; } @@ -2711,42 +5918,410 @@ sub git_heads_body { print "
$ref{'age'}" : "") . - $cgi->a({-href => href(action=>"shortlog", hash=>$ref{'name'}), + $cgi->a({-href => href(action=>"shortlog", hash=>$ref{'fullname'}), -class => "list name"},esc_html($ref{'name'})) . "" . - $cgi->a({-href => href(action=>"shortlog", hash=>$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=>$ref{'fullname'})}, "tree") . "
\n"; } +# Display a single remote block +sub git_remote_block { + my ($remote, $rdata, $limit, $head) = @_; + + my $heads = $rdata->{'heads'}; + my $fetch = $rdata->{'fetch'}; + my $push = $rdata->{'push'}; + + my $urls_table = "\n" ; + + if (defined $fetch) { + if ($fetch eq $push) { + $urls_table .= format_repo_url("URL", $fetch); + } else { + $urls_table .= format_repo_url("Fetch URL", $fetch); + $urls_table .= format_repo_url("Push URL", $push) if defined $push; + } + } elsif (defined $push) { + $urls_table .= format_repo_url("Push URL", $push); + } else { + $urls_table .= format_repo_url("", "No remote URL"); + } + + $urls_table .= "
\n"; + + my $dots; + if (defined $limit && $limit < @$heads) { + $dots = $cgi->a({-href => href(action=>"remotes", hash=>$remote)}, "..."); + } + + print $urls_table; + git_heads_body($heads, $head, 0, $limit, $dots); +} + +# Display a list of remote names with the respective fetch and push URLs +sub git_remotes_list { + my ($remotedata, $limit) = @_; + print "\n"; + my $alternate = 1; + my @remotes = sort keys %$remotedata; + + my $limited = $limit && $limit < @remotes; + + $#remotes = $limit - 1 if $limited; + + while (my $remote = shift @remotes) { + my $rdata = $remotedata->{$remote}; + my $fetch = $rdata->{'fetch'}; + my $push = $rdata->{'push'}; + if ($alternate) { + print "\n"; + } else { + print "\n"; + } + $alternate ^= 1; + print ""; + print ""; + + print "\n"; + } + + if ($limited) { + print "\n" . + "\n" . "\n"; + } + + print "
" . + $cgi->a({-href=> href(action=>'remotes', hash=>$remote), + -class=> "list name"},esc_html($remote)) . + "" . + (defined $fetch ? $cgi->a({-href=> $fetch}, "fetch") : "fetch") . + " | " . + (defined $push ? $cgi->a({-href=> $push}, "push") : "push") . + "
" . + $cgi->a({-href => href(action=>"remotes")}, "...") . + "
"; +} + +# Display remote heads grouped by remote, unless there are too many +# remotes, in which case we only display the remote names +sub git_remotes_body { + my ($remotedata, $limit, $head) = @_; + if ($limit and $limit < keys %$remotedata) { + git_remotes_list($remotedata, $limit); + } else { + fill_remote_heads($remotedata); + while (my ($remote, $rdata) = each %$remotedata) { + git_print_section({-class=>"remote", -id=>$remote}, + ["remotes", $remote, $remote], sub { + git_remote_block($remote, $rdata, $limit, $head); + }); + } + } +} + +sub git_search_message { + my %co = @_; + + my $greptype; + if ($searchtype eq 'commit') { + $greptype = "--grep="; + } elsif ($searchtype eq 'author') { + $greptype = "--author="; + } elsif ($searchtype eq 'committer') { + $greptype = "--committer="; + } + $greptype .= $searchtext; + my @commitlist = parse_commits($hash, 101, (100 * $page), undef, + $greptype, '--regexp-ignore-case', + $search_use_regexp ? '--extended-regexp' : '--fixed-strings'); + + my $paging_nav = ''; + if ($page > 0) { + $paging_nav .= + $cgi->a({-href => href(-replay=>1, page=>undef)}, + "first") . + " ⋅ " . + $cgi->a({-href => href(-replay=>1, page=>$page-1), + -accesskey => "p", -title => "Alt-p"}, "prev"); + } else { + $paging_nav .= "first ⋅ prev"; + } + my $next_link = ''; + if ($#commitlist >= 100) { + $next_link = + $cgi->a({-href => href(-replay=>1, page=>$page+1), + -accesskey => "n", -title => "Alt-n"}, "next"); + $paging_nav .= " ⋅ $next_link"; + } else { + $paging_nav .= " ⋅ next"; + } + + git_header_html(); + + git_print_page_nav('','', $hash,$co{'tree'},$hash, $paging_nav); + git_print_header_div('commit', esc_html($co{'title'}), $hash); + if ($page == 0 && !@commitlist) { + print "

No match.

\n"; + } else { + git_search_grep_body(\@commitlist, 0, 99, $next_link); + } + + git_footer_html(); +} + +sub git_search_changes { + my %co = @_; + + local $/ = "\n"; + open my $fd, '-|', git_cmd(), '--no-pager', 'log', @diff_opts, + '--pretty=format:%H', '--no-abbrev', '--raw', "-S$searchtext", + ($search_use_regexp ? '--pickaxe-regex' : ()) + or die_error(500, "Open git-log failed"); + + git_header_html(); + + git_print_page_nav('','', $hash,$co{'tree'},$hash); + git_print_header_div('commit', esc_html($co{'title'}), $hash); + + print "\n"; + my $alternate = 1; + undef %co; + my @files; + while (my $line = <$fd>) { + chomp $line; + next unless $line; + + my %set = parse_difftree_raw_line($line); + if (defined $set{'commit'}) { + # finish previous commit + if (%co) { + print "\n" . + "\n" . + "\n"; + } + + if ($alternate) { + print "\n"; + } else { + print "\n"; + } + $alternate ^= 1; + %co = parse_commit($set{'commit'}); + my $author = chop_and_escape_str($co{'author_name'}, 15, 5); + print "\n" . + "\n" . + "\n" . + "\n" . + "\n"; + } + + print "
" . + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'})}, + "commit") . + " | " . + $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, + hash_base=>$co{'id'})}, + "tree") . + "
$co{'age_string_date'}$author" . + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), + -class => "list subject"}, + chop_and_escape_str($co{'title'}, 50) . "
"); + } elsif (defined $set{'to_id'}) { + next if ($set{'to_id'} =~ m/^0{40}$/); + + print $cgi->a({-href => href(action=>"blob", hash_base=>$co{'id'}, + hash=>$set{'to_id'}, file_name=>$set{'to_file'}), + -class => "list"}, + "" . esc_path($set{'file'}) . "") . + "
\n"; + } + } + close $fd; + + # finish last commit (warning: repetition!) + if (%co) { + print "		" . + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'})}, + "commit") . + " | " . + $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, + hash_base=>$co{'id'})}, + "tree") . + "
\n"; + + git_footer_html(); +} + +sub git_search_files { + my %co = @_; + + local $/ = "\n"; + open my $fd, "-|", git_cmd(), 'grep', '-n', '-z', + $search_use_regexp ? ('-E', '-i') : '-F', + $searchtext, $co{'tree'} + or die_error(500, "Open git-grep failed"); + + git_header_html(); + + git_print_page_nav('','', $hash,$co{'tree'},$hash); + git_print_header_div('commit', esc_html($co{'title'}), $hash); + + print "\n"; + my $alternate = 1; + my $matches = 0; + my $lastfile = ''; + my $file_href; + while (my $line = <$fd>) { + chomp $line; + my ($file, $lno, $ltext, $binary); + last if ($matches++ > 1000); + if ($line =~ /^Binary file (.+) matches$/) { + $file = $1; + $binary = 1; + } else { + ($file, $lno, $ltext) = split(/\0/, $line, 3); + $file =~ s/^$co{'tree'}://; + } + if ($file ne $lastfile) { + $lastfile and print "\n"; + if ($alternate++) { + print "\n"; + } else { + print "\n"; + } + $file_href = href(action=>"blob", hash_base=>$co{'id'}, + file_name=>$file); + print "\n"; + if ($matches > 1000) { + print "
Too many matches, listing trimmed
\n"; + } + } else { + print "
No matches found
\n"; + } + close $fd; + + print "
". + $cgi->a({-href => $file_href, -class => "list"}, esc_path($file)); + print "\n"; + $lastfile = $file; + } + if ($binary) { + print "
Binary file
\n"; + } else { + $ltext = untabify($ltext); + if ($ltext =~ m/^(.*)($search_regexp)(.*)$/i) { + $ltext = esc_html($1, -nbsp=>1); + $ltext .= ''; + $ltext .= esc_html($2, -nbsp=>1); + $ltext .= ''; + $ltext .= esc_html($3, -nbsp=>1); + } else { + $ltext = esc_html($ltext, -nbsp=>1); + } + print "
" . + $cgi->a({-href => $file_href.'#l'.$lno, + -class => "linenr"}, sprintf('%4i', $lno)) . + ' ' . $ltext . "
\n"; + } + } + if ($lastfile) { + print "
\n"; + + git_footer_html(); +} + +sub git_search_grep_body { + my ($commitlist, $from, $to, $extra) = @_; + $from = 0 unless defined $from; + $to = $#{$commitlist} if (!defined $to || $#{$commitlist} < $to); + + print "\n"; + my $alternate = 1; + for (my $i = $from; $i <= $to; $i++) { + my %co = %{$commitlist->[$i]}; + if (!%co) { + next; + } + my $commit = $co{'id'}; + if ($alternate) { + print "\n"; + } else { + print "\n"; + } + $alternate ^= 1; + print "\n" . + format_author_html('td', \%co, 15, 5) . + "\n" . + "\n" . + "\n"; + } + if (defined $extra) { + print "\n" . + "\n" . + "\n"; + } + print "
$co{'age_string_date'}" . + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), + -class => "list subject"}, + chop_and_escape_str($co{'title'}, 50) . "
"); + my $comment = $co{'comment'}; + foreach my $line (@$comment) { + 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 "$lead$match$trail
"; + } + } + print "		" . + $cgi->a({-href => href(action=>"commit", hash=>$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 "
$extra
\n"; +} + ## ====================================================================== ## ====================================================================== ## actions sub git_project_list { - my $order = $cgi->param('o'); - if (defined $order && $order !~ m/project|descr|owner|age/) { - die_error(undef, "Unknown order parameter"); + my $order = $input_params{'order'}; + if (defined $order && $order !~ m/none|project|descr|owner|age/) { + die_error(400, "Unknown order parameter"); } - my @list = git_get_projects_list(); + my @list = git_get_projects_list($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 "
\n"; - open (my $fd, $home_text); - print <$fd>; - close $fd; + insert_file($home_text); print "
\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'); - if (defined $order && $order !~ m/project|descr|owner|age/) { - die_error(undef, "Unknown order parameter"); + my $order = $input_params{'order'}; + if (defined $order && $order !~ m/none|project|descr|owner|age/) { + die_error(400, "Unknown order parameter"); } - my @list = git_get_projects_list($project); + my $filter = $project; + $filter =~ s/\.git$//; + my @list = git_get_projects_list($filter); if (!@list) { - die_error(undef, "No forks found"); + die_error(404, "No forks found"); } git_header_html(); @@ -2757,7 +6332,10 @@ sub git_forks { } sub git_project_index { - my @projects = git_get_projects_list($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', @@ -2766,7 +6344,7 @@ sub git_project_index { foreach my $pr (@projects) { if (!exists $pr->{'owner'}) { - $pr->{'owner'} = get_file_owner("$projectroot/$project"); + $pr->{'owner'} = git_get_project_owner("$pr->{'path'}"); } my ($path, $owner) = ($pr->{'path'}, $pr->{'owner'}); @@ -2782,30 +6360,46 @@ sub git_project_index { sub git_summary { my $descr = git_get_project_description($project) || "none"; - my $head = git_get_head_hash($project); - my %co = parse_commit($head); - my %cd = parse_date($co{'committer_epoch'}, $co{'committer_tz'}); + my %co = parse_commit("HEAD"); + my %cd = %co ? parse_date($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); my $refs = git_get_references(); - my @taglist = git_get_tags_list(15); - my @headlist = git_get_heads_list(15); + # These get_*_list functions return one more to allow us to see if + # 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 "
 
\n"; - print "\n" . - "\n" . - "\n" . - "\n"; + print "
description" . esc_html($descr) . "
owner$owner
last change$cd{'rfc2822'}
\n" . + "\n"; + if ($owner and not $omit_owner) { + print "\n"; + } + if (defined $cd{'rfc2822'}) { + print "" . + "\n"; + } + # use per project git URL list in $projectroot/$project/cloneurl # or make project git URL from git base URL and project name my $url_tag = "URL"; @@ -2813,58 +6407,88 @@ sub git_summary { @url_list = map { "$_/$project" } @git_base_url_list unless @url_list; foreach my $git_url (@url_list) { next unless $git_url; - print "\n"; + print format_repo_url($url_tag, $git_url); $url_tag = ""; } - print "
description" . esc_html($descr) . "
owner" . esc_html($owner) . "
last change".format_timestamp_html(\%cd)."
$url_tag$git_url
\n"; - if (-s "$projectroot/$project/README.html") { - if (open my $fd, "$projectroot/$project/README.html") { - print "
readme
\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 "
content tags".git_show_project_tagcloud($cloud, 48)."
\n"; + + # If XSS prevention is on, we don't include README.html. + # TODO: Allow a readme in some safe format. + if (!$prevent_xss && -s "$projectroot/$project/README.html") { + print "
readme
\n" . + "
\n"; + insert_file("$projectroot/$project/README.html"); + print "\n
\n"; # class="readme" + } + + # we need to request one more than 16 (0..15) to check if + # those 16 are all + my @commitlist = $head ? parse_commits($head, 17) : (); + if (@commitlist) { + git_print_header_div('shortlog'); + git_shortlog_body(\@commitlist, 0, 15, $refs, + $#commitlist <= 15 ? undef : + $cgi->a({-href => href(action=>"shortlog")}, "...")); + } if (@taglist) { git_print_header_div('tags'); git_tags_body(\@taglist, 0, 15, + $#taglist <= 15 ? undef : $cgi->a({-href => href(action=>"tags")}, "...")); } if (@headlist) { git_print_header_div('heads'); git_heads_body(\@headlist, $head, 0, 15, + $#headlist <= 15 ? undef : $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 : $cgi->a({-href => href(action=>"forks")}, "..."), - 'noheader'); + 'no_header'); } git_footer_html(); } sub git_tag { + my %tag = parse_tag($hash); + + if (! %tag) { + die_error(404, "Unknown tag object"); + } + my $head = git_get_head_hash($project); git_header_html(); git_print_page_nav('','', $head,undef,$head); - my %tag = parse_tag($hash); git_print_header_div('commit', esc_html($tag{'name'}), $hash); print "
\n" . - "\n" . + "
\n" . "\n" . "\n" . "\n" . "\n"; if (defined($tag{'author'})) { - my %ad = parse_date($tag{'epoch'}, $tag{'tz'}); - print "\n"; - print "\n"; + git_print_authorship_rows(\%tag, 'author'); } print "
object" . $cgi->a({-class => "list", -href => href(action=>$tag{'type'}, hash=>$tag{'object'})}, @@ -2873,228 +6497,269 @@ sub git_tag { $tag{'type'}) . "
author" . esc_html(nospam($tag{'author'})) . "
" . $ad{'rfc2822'} . - sprintf(" (%02d:%02d %s)", $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}) . - "
\n\n" . "
\n"; print "
"; my $comment = $tag{'comment'}; foreach my $line (@$comment) { - chomp($line); - print esc_html($line) . "
\n"; + chomp $line; + print esc_html($line, -nbsp=>1) . "
\n"; } print "
\n"; 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"); + } } - $ftype = git_get_type($hash); - if ($ftype !~ "blob") { - die_error("400 Bad Request", "Object is not a blob"); + + my $fd; + if ($format eq 'incremental') { + # get file contents (as base) + open $fd, "-|", git_cmd(), 'cat-file', 'blob', $hash + or die_error(500, "Open git-cat-file failed"); + } elsif ($format eq 'data') { + # run git-blame --incremental + open $fd, "-|", git_cmd(), "blame", "--incremental", + $hash_base, "--", $file_name + or die_error(500, "Open git-blame --incremental failed"); + } else { + # run git-blame --porcelain + open $fd, "-|", git_cmd(), "blame", '-p', + $hash_base, '--', $file_name + or die_error(500, "Open git-blame --porcelain failed"); } - open ($fd, "-|", git_cmd(), "blame", '-p', '--', - $file_name, $hash_base) - or die_error(undef, "Open git-blame failed"); + binmode $fd, ':utf8'; + + # incremental blame data returns early + if ($format eq 'data') { + print $cgi->header( + -type=>"text/plain", -charset => "utf-8", + -status=> "200 OK"); + local $| = 1; # output autoflush + while (my $line = <$fd>) { + print to_utf8($line); + } + close $fd + or print "ERROR $!\n"; + + print 'END'; + if (defined $t0 && gitweb_check_feature('timed')) { + print ' '. + tv_interval($t0, [ gettimeofday() ]). + ' '.$number_of_git_cmds; + } + print "\n"; + + return; + } + + # page header git_header_html(); my $formats_nav = - $cgi->a({-href => href(action=>"blob", hash=>$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 "\n"; + + print qq!
\n!; + } + + print qq!
\n!; + print qq!
... / ...
\n! + if ($format eq 'incremental'); + print qq!\n!. + #qq!\n!. + qq!\n!. + qq!\n!. + qq!\n!. + qq!\n!; + + my @rev_color = qw(light dark); my $num_colors = scalar(@rev_color); my $current_color = 0; - my $last_rev; - print < -
CommitLineData
- -HTML - my %metainfo = (); - while (1) { - $_ = <$fd>; - last unless defined $_; - my ($full_rev, $orig_lineno, $lineno, $group_size) = - /^([0-9a-f]{40}) (\d+) (\d+)(?: (\d+))?$/; - if (!exists $metainfo{$full_rev}) { - $metainfo{$full_rev} = {}; + + if ($format eq 'incremental') { + my $color_class = $rev_color[$current_color]; + + #contents of a file + my $linenr = 0; + LINE: + while (my $line = <$fd>) { + chomp $line; + $linenr++; + + print qq!!. + qq!!. + qq!!; + print qq!\n"; + print qq!\n!; } - my $meta = $metainfo{$full_rev}; - while (<$fd>) { - last if (s/^\t//); - if (/^(\S+) (.*)$/) { - $meta->{$1} = $2; + + } else { # porcelain, i.e. ordinary blame + my %metainfo = (); # saves information about commits + + # blame data + LINE: + while (my $line = <$fd>) { + chomp $line; + # the header: [] + # no for subsequent lines in group of lines + my ($full_rev, $orig_lineno, $lineno, $group_size) = + ($line =~ /^([0-9a-f]{40}) (\d+) (\d+)(?: (\d+))?$/); + if (!exists $metainfo{$full_rev}) { + $metainfo{$full_rev} = { 'nprevious' => 0 }; } - } - my $data = $_; - chomp($data); - my $rev = substr($full_rev, 0, 8); - my $author = $meta->{'author'}; - my %date = parse_date($meta->{'author-time'}, - $meta->{'author-tz'}); - my $date = $date{'iso-tz'}; - if ($group_size) { - $current_color = ++$current_color % $num_colors; - } - print "\n"; - if ($group_size) { - print "\n"; - } - my $blamed = href(action => 'blame', - file_name => $meta->{'filename'}, - hash_base => $full_rev); - print ""; - print "\n"; - print "\n"; + my $meta = $metainfo{$full_rev}; + my $data; + while ($data = <$fd>) { + chomp $data; + last if ($data =~ s/^\t//); # contents of line + if ($data =~ /^(\S+)(?: (.*))?$/) { + $meta->{$1} = $2 unless exists $meta->{$1}; + } + if ($data =~ /^previous /) { + $meta->{'nprevious'}++; + } + } + my $short_rev = substr($full_rev, 0, 8); + my $author = $meta->{'author'}; + my %date = + parse_date($meta->{'author-time'}, $meta->{'author-tz'}); + my $date = $date{'iso-tz'}; + if ($group_size) { + $current_color = ($current_color + 1) % $num_colors; + } + my $tr_class = $rev_color[$current_color]; + $tr_class .= ' boundary' if (exists $meta->{'boundary'}); + $tr_class .= ' no-previous' if ($meta->{'nprevious'} == 0); + $tr_class .= ' multiple-previous' if ($meta->{'nprevious'} > 1); + print "\n"; + if ($group_size) { + print "\n"; + } + # 'previous' + if (exists $meta->{'previous'} && + $meta->{'previous'} =~ /^([a-fA-F0-9]{40}) (.*)$/) { + $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 => $linenr_commit); + print ""; + print "\n"; + print "\n"; + } # end while + } - print "
CommitLineData
!. + qq!$linenr! . esc_html($line) . "
1); - print ">"; - print $cgi->a({-href => href(action=>"commit", - hash=>$full_rev, - file_name=>$file_name)}, - esc_html($rev)); - print ""; - print $cgi->a({ -href => "$blamed#l$orig_lineno", - -id => "l$lineno", - -class => "linenr" }, - esc_html($lineno)); - print "" . esc_html($data) . "
1); + print ">"; + print $cgi->a({-href => href(action=>"commit", + hash=>$full_rev, + file_name=>$file_name)}, + esc_html($short_rev)); + if ($group_size >= 2) { + my @author_initials = ($author =~ /\b([[:upper:]])\B/g); + if (@author_initials) { + print "
" . + esc_html(join('', @author_initials)); + # or join('.', ...) + } + } + print "		"; + print $cgi->a({ -href => "$blamed#l$orig_lineno", + -class => "linenr" }, + esc_html($lineno)); + print "" . esc_html($data) . "
\n"; - print "
"; + + # footer + print "
\n"; # class="blame" + print "\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 "
\n"; - print < - - Commit - Age - Author - Line - Data - -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( Unable to parse: $line\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 < - $long_rev)}" class="text">$short_rev.. - $age_str - $author - $lineno - $data - -HTML - } # while (my $line = <$fd>) - print "\n\n"; - close $fd - or print "Reading blob failed.\n"; - print "
"; - 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(); @@ -3107,7 +6772,7 @@ 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(); @@ -3117,29 +6782,63 @@ 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; @@ -3147,15 +6846,34 @@ 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 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; } @@ -3166,41 +6884,47 @@ 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\//) { + # 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", @@ -3208,24 +6932,37 @@ 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 "
\n" . "

\n" . - "
$hash
\n"; + "
".esc_html($hash)."
\n"; } git_print_page_path($file_name, "blob", $hash_base); print "
\n"; - my $nr; - while (my $line = <$fd>) { - chomp $line; - $nr++; - $line = untabify($line); - printf "
%4i %s
\n", - $nr, $nr, $nr, esc_html($line, -nbsp=>1); + if ($mimetype =~ m!^image/!) { + print qq!!.esc_attr($file_name).qq!$hash, + hash_base=>$hash_base, file_name=>$file_name) . + qq!" />\n!; + } else { + my $nr; + while (my $line = <$fd>) { + chomp $line; + $nr++; + $line = untabify($line); + printf qq!
%4i %s
\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"; @@ -3234,10 +6971,8 @@ sub git_blob { } sub git_tree { - my $have_snapshot = gitweb_have_snapshot(); - if (!defined $hash_base) { - $hash_base = gitweb_get_default_head($project); + $hash_base = "HEAD"; } if (!defined $hash) { if (defined $file_name) { @@ -3246,52 +6981,59 @@ 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)}, "HEAD"), } - if ($have_snapshot) { + my $snapshot_links = format_snapshot_links($hash); + if (defined $snapshot_links) { # FIXME: Should be available when we have no hash base as well. - push @views_nav, - $cgi->a({-href => href(action=>"snapshot", hash=>$hash)}, - "snapshot"); + push @views_nav, $snapshot_links; } - git_print_page_nav('tree','', $hash_base, undef, undef, join(' | ', @views_nav)); + git_print_page_nav('tree','', $hash_base, undef, undef, + join(' | ', @views_nav)); git_print_header_div('commit', esc_html($co{'title'}) . $ref, $hash_base); } else { undef $hash_base; print "
\n"; print "

\n"; - print "
$hash
\n"; + print "
".esc_html($hash)."
\n"; } if (defined $file_name) { $basedir = $file_name; if ($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 "
\n"; - print "\n"; + print "
\n"; my $alternate = 1; # '..' (top directory) link if possible if (defined $hash_base && @@ -3308,8 +7050,10 @@ sub git_tree { undef $up unless $up; # based on git_print_tree_entry print '\n"; + print ''."\n" if $show_sizes; print '\n"; @@ -3318,7 +7062,7 @@ sub git_tree { print "\n"; } foreach my $line (@entries) { - my %t = parse_ls_tree_line($line, -z => 1); + my %t = parse_ls_tree_line($line, -z => 1, -l => $show_sizes); if ($alternate) { print "\n"; @@ -3336,111 +7080,278 @@ sub git_tree { git_footer_html(); } +sub sanitize_for_filename { + my $name = shift; + + $name =~ s!/!-!g; + $name =~ s/[^[:alnum:]_.-]//g; + + return $name; +} + +sub snapshot_name { + my ($project, $hash) = @_; + + # path/to/project.git -> project + # path/to/project/.git -> project + my $name = to_utf8($project); + $name =~ s,([^/])/*\.git$,$1,; + $name = sanitize_for_filename(basename($name)); + + my $ver = $hash; + if ($hash =~ /^[0-9a-fA-F]+$/) { + # shorten SHA-1 hash + my $full_hash = git_get_full_hash($project, $hash); + if ($full_hash =~ /^$hash/ && length($hash) > 7) { + $ver = git_get_short_hash($project, $hash); + } + } elsif ($hash =~ m!^refs/tags/(.*)$!) { + # tags don't need shortened SHA-1 hash + $ver = $1; + } else { + # branches and other need shortened SHA-1 hash + my $strip_refs = join '|', map { quotemeta } get_branch_refs(); + if ($hash =~ m!^refs/($strip_refs|remotes)/(.*)$!) { + my $ref_dir = (defined $1) ? $1 : ''; + $ver = $2; + + $ref_dir = sanitize_for_filename($ref_dir); + # for refs neither in heads nor remotes we want to + # add a ref dir to archive name + if ($ref_dir ne '' and $ref_dir ne 'heads' and $ref_dir ne 'remotes') { + $ver = $ref_dir . '-' . $ver; + } + } + $ver .= '-' . git_get_short_hash($project, $hash); + } + # special case of sanitization for filename - we change + # slashes to dots instead of dashes + # in case of hierarchical branch names + $ver =~ s!/!.!g; + $ver =~ s/[^[:alnum:]_.-]//g; + + # name = project-version_string + $name = "$name-$ver"; + + return wantarray ? ($name, $name) : $name; +} + +sub exit_if_unmodified_since { + my ($latest_epoch) = @_; + our $cgi; + + my $if_modified = $cgi->http('IF_MODIFIED_SINCE'); + if (defined $if_modified) { + my $since; + if (eval { require HTTP::Date; 1; }) { + $since = HTTP::Date::str2time($if_modified); + } elsif (eval { require Time::ParseDate; 1; }) { + $since = Time::ParseDate::parsedate($if_modified, GMT => 1); + } + if (defined $since && $latest_epoch <= $since) { + my %latest_date = parse_date($latest_epoch); + print $cgi->header( + -last_modified => $latest_date{'rfc2822'}, + -status => '304 Not Modified'); + goto DONE_GITWEB; + } + } +} + sub git_snapshot { - my ($ctype, $suffix, $command) = gitweb_check_feature('snapshot'); - my $have_snapshot = (defined $ctype && defined $suffix); - if (!$have_snapshot) { - die_error('403 Permission denied', "Permission denied"); + my $format = $input_params{'snapshot_format'}; + if (!@snapshot_fmts) { + die_error(403, "Snapshots not allowed"); + } + # default to first supported snapshot format + $format ||= $snapshot_fmts[0]; + if ($format !~ m/^[a-z0-9]+$/) { + die_error(400, "Invalid snapshot format parameter"); + } elsif (!exists($known_snapshot_formats{$format})) { + die_error(400, "Unknown snapshot format"); + } elsif ($known_snapshot_formats{$format}{'disabled'}) { + die_error(403, "Snapshot format not allowed"); + } elsif (!grep($_ eq $format, @snapshot_fmts)) { + die_error(403, "Unsupported snapshot format"); } - if (!defined $hash) { - $hash = git_get_head_hash($project); + my $type = git_get_type("$hash^{}"); + if (!$type) { + die_error(404, 'Object does not exist'); + } elsif ($type eq 'blob') { + die_error(400, 'Object is not a tree-ish'); } - my $filename = basename($project) . "-$hash.tar.$suffix"; + my ($name, $prefix) = snapshot_name($project, $hash); + my $filename = "$name$known_snapshot_formats{$format}{'suffix'}"; + # Allow users to download a snapshot of the current directory/port. See + # http://stackoverflow.com/questions/14444593/gitweb-snapshot-of-sub-directory + if ($file_name) { + $filename = "$file_name-$hash$known_snapshot_formats{$format}{'suffix'}"; + $hash="$hash:$file_name"; + $prefix=$file_name; + #die_error(501, "HASH WAS SET TO " . $hash . " prefixed " . $prefix); + } + + my %co = parse_commit($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'}) { + $cmd .= ' | ' . quote_command(@{$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 => 'application/x-tar', - -content_encoding => $ctype, - -content_disposition => 'inline; filename="' . "$filename" . '"', + -type => $known_snapshot_formats{$format}{'type'}, + -content_disposition => 'inline; filename="' . $filename . '"', + %co ? (-last_modified => $latest_date{'rfc2822'}) : (), -status => '200 OK'); - my $git = git_cmd_str(); - my $name = $project; - $name =~ s/\047/\047\\\047\047/g; - open my $fd, "-|", - "$git archive --format=tar --prefix=\'$name\'/ $hash | $command" - or die_error(undef, "Execute git-tar-tree failed."); + open my $fd, "-|", $cmd + or die_error(500, "Execute git-archive failed"); binmode STDOUT, ':raw'; print <$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 $limit = sprintf("--max-count=%i", (100 * ($page+1))); - open my $fd, "-|", git_cmd(), "rev-list", $limit, $hash, "--" - or die_error(undef, "Open git-rev-list failed"); - my @revlist = map { chomp; $_ } <$fd>; - close $fd; + 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") : ()); - my $paging_nav = format_paging_nav('log', $hash, $head, $page, $#revlist); + 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"); + } + + + 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 $patch_max = gitweb_get_feature('patches'); + if ($patch_max && !defined $file_name) { + if ($patch_max < 0 || @commitlist <= $patch_max) { + $paging_nav .= " ⋅ " . + $cgi->a({-href => href(action=>"patches", -replay=>1)}, + "patches"); + } + } git_header_html(); - git_print_page_nav('log','', $hash,undef,undef, $paging_nav); - - if (!@revlist) { - my %co = parse_commit($hash); - - git_print_header_div('summary', $project); - print "
Last change $co{'age_string'}.

\n"; + 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) } - for (my $i = ($page * 100); $i <= $#revlist; $i++) { - my $commit = $revlist[$i]; - my $ref = format_ref_marker($refs, $commit); - my %co = parse_commit($commit); - next if !%co; - my %ad = parse_date($co{'author_epoch'}); - git_print_header_div('commit', - "$co{'age_string'}" . - esc_html($co{'title'}) . $ref, - $commit); - print "
\n" . - "
\n" . - $cgi->a({-href => href(action=>"commit", hash=>$commit)}, "commit") . - " | " . - $cgi->a({-href => href(action=>"commitdiff", hash=>$commit)}, "commitdiff") . - " | " . - $cgi->a({-href => href(action=>"tree", hash=>$commit, hash_base=>$commit)}, "tree") . - "
\n" . - "
\n" . - "" . esc_html($co{'author_name'}) . " [$ad{'rfc2822'}]
\n" . - "
\n"; + git_print_page_path($file_name, $ftype, $hash_base) + if (defined $file_name); + + $body_subr->(\@commitlist, 0, 99, $refs, $next_link, + $file_name, $file_hash, $ftype); - print "
\n"; - git_print_log($co{'comment'}, -final_empty_line=> 1); - print "
\n"; - } git_footer_html(); } -sub git_commit { - 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'}); +sub git_log { + git_log_generic('log', \&git_log_body, + $hash, $hash_parent); +} + +sub git_commit { + $hash ||= $hash_base || "HEAD"; + my %co = parse_commit($hash) + or die_error(404, "Unknown commit object"); + + my $parent = $co{'parent'}; + my $parents = $co{'parents'}; # listref + + # we need to prepare $formats_nav before any parameter munging + my $formats_nav; + if (!defined $parent) { + # --root commitdiff + $formats_nav .= '(initial)'; + } elsif (@$parents == 1) { + # single parent commit + $formats_nav .= + '(parent: ' . + $cgi->a({-href => href(action=>"commit", + hash=>$parent)}, + esc_html(substr($parent, 0, 7))) . + ')'; + } else { + # merge commit + $formats_nav .= + '(merge: ' . + join(' ', map { + $cgi->a({-href => href(action=>"commit", + hash=>$_)}, + esc_html(substr($_, 0, 7))); + } @$parents ) . + ')'; + } + if (gitweb_check_feature('patches') && @$parents <= 1) { + $formats_nav .= " | " . + $cgi->a({-href => href(action=>"patch", -replay=>1)}, + "patch"); + } - my $parent = $co{'parent'}; if (!defined $parent) { $parent = "--root"; } + my @difftree; open my $fd, "-|", git_cmd(), "diff-tree", '-r', "--no-commit-id", - @diff_opts, $parent, $hash, "--" - or die_error(undef, "Open git-diff-tree failed"); - my @difftree = map { chomp; $_ } <$fd>; - close $fd or die_error(undef, "Reading git-diff-tree failed"); + @diff_opts, + (@$parents <= 1 ? $parent : '-c'), + $hash, "--" + or die_error(500, "Open git-diff-tree failed"); + @difftree = map { chomp; $_ } <$fd>; + close $fd or die_error(404, "Reading git-diff-tree failed"); # non-textual hash id's can be cached my $expires; @@ -3450,18 +7361,10 @@ sub git_commit { my $refs = git_get_references(); my $ref = format_ref_marker($refs, $co{'id'}); - my $have_snapshot = gitweb_have_snapshot(); - - my @views_nav = (); - if (defined $file_name && defined $co{'parent'}) { - push @views_nav, - $cgi->a({-href => href(action=>"blame", hash_parent=>$parent, file_name=>$file_name)}, - "blame"); - } git_header_html(undef, $expires); git_print_page_nav('commit', '', $hash, $co{'tree'}, $hash, - join (' | ', @views_nav)); + $formats_nav); if (defined $co{'parent'}) { git_print_header_div('commitdiff', esc_html($co{'title'}) . $ref, $hash); @@ -3469,23 +7372,8 @@ sub git_commit { git_print_header_div('tree', esc_html($co{'title'}) . $ref, $co{'tree'}, $hash); } print "
\n" . - "
' . mode_str('040000') . " '; - print $cgi->a({-href => href(action=>"tree", hash_base=>$hash_base, + print $cgi->a({-href => href(action=>"tree", + hash_base=>$hash_base, file_name=>$up)}, ".."); print "
\n"; - print "\n". - "" . - "" . - "\n"; - print "\n"; - print "\n"; + "
author" . esc_html(nospam($co{'author'})) . "
$ad{'rfc2822'}"; - if ($ad{'hour_local'} < 6) { - printf(" (%02d:%02d %s)", - $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); - } else { - printf(" (%02d:%02d %s)", - $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); - } - print "
committer" . esc_html(nospam($co{'committer'})) . "
$cd{'rfc2822'}" . - sprintf(" (%02d:%02d %s)", $cd{'hour_local'}, $cd{'minute_local'}, $cd{'tz_local'}) . - "
\n"; + git_print_authorship_rows(\%co); print "\n"; print "" . "" . @@ -3496,13 +7384,13 @@ sub git_commit { "" . "\n"; - my $parents = $co{'parents'}; + foreach my $par (@$parents) { print "" . "" . @@ -3524,13 +7412,61 @@ sub git_commit { git_print_log($co{'comment'}); print "\n"; - git_difftree_body(\@difftree, $hash, $parent); + git_difftree_body(\@difftree, $hash, @$parents); git_footer_html(); } +sub git_object { + # object is defined by: + # - hash or hash_base alone + # - hash_base and file_name + my $type; + + # - hash or hash_base alone + if ($hash || ($hash_base && !defined $file_name)) { + my $object_id = $hash || $hash_base; + + 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 $fd + or die_error(404, "Object does not exist"); + + # - hash_base and file_name + } elsif ($hash_base && defined $file_name) { + $file_name =~ s,/+$,,; + + system(git_cmd(), "cat-file", '-e', $hash_base) == 0 + or die_error(404, "Base object does not exist"); + + # here errors should not happen + open my $fd, "-|", git_cmd(), "ls-tree", $hash_base, "--", $file_name + or die_error(500, "Open git-ls-tree failed"); + my $line = <$fd>; + close $fd; + + #'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa panic.c' + unless ($line && $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t/) { + die_error(404, "File or directory for given base does not exist"); + } + $type = $2; + $hash = $3; + } else { + die_error(400, "Not enough information to find object"); + } + + print $cgi->redirect(-uri => href(action=>$type, -full=>1, + hash=>$hash, hash_base=>$hash_base, + file_name=>$file_name), + -status => '302 Found'); +} + sub git_blobdiff { my $format = shift || 'html'; + my $diff_style = $input_params{'diff_style'} || 'inline'; my $fd; my @difftree; @@ -3544,13 +7480,13 @@ sub git_blobdiff { # read raw output open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, $hash_parent_base, $hash_base, - "--", $file_name - or die_error(undef, "Open git-diff-tree failed"); + "--", (defined $file_parent ? $file_parent : ()), $file_name + 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}/) { @@ -3559,28 +7495,28 @@ 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'}; @@ -3593,64 +7529,30 @@ sub git_blobdiff { # open patch output open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, - '-p', $hash_parent_base, $hash_base, - "--", $file_name - or die_error(undef, "Open git-diff-tree failed"); + '-p', ($format eq 'html' ? "--full-index" : ()), + $hash_parent_base, $hash_base, + "--", (defined $file_parent ? $file_parent : ()), $file_name + 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", '-p', @diff_opts, - $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 "

$formats_nav
\n"; - print "
$hash vs $hash_parent
\n"; + print "
".esc_html("$hash vs $hash_parent")."
\n"; } if (defined $file_name) { git_print_page_path($file_name, "blob", $hash_base); @@ -3668,14 +7570,15 @@ 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 "
\n"; - git_patchset_body($fd, [ \%diffinfo ], $hash_base, $hash_parent_base); + git_patchset_body($fd, $diff_style, + [ \%diffinfo ], $hash_base, $hash_parent_base); close $fd; print "
\n"; # class="page_body" @@ -3700,31 +7603,76 @@ sub git_blobdiff_plain { git_blobdiff('plain'); } +# assumes that it is added as later part of already existing navigation, +# so it returns "| foo | bar" rather than just "foo | bar" +sub diff_style_nav { + my ($diff_style, $is_combined) = @_; + $diff_style ||= 'inline'; + + return "" if ($is_combined); + + my @styles = (inline => 'inline', 'sidebyside' => 'side by side'); + my %styles = @styles; + @styles = + @styles[ map { $_ * 2 } 0..$#styles/2 ]; + + return join '', + map { " | ".$_ } + map { + $_ eq $diff_style ? $styles{$_} : + $cgi->a({-href => href(-replay=>1, diff_style => $_)}, $styles{$_}) + } @styles; +} + sub git_commitdiff { - my $format = shift || 'html'; - my %co = parse_commit($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; } - # we need to prepare $formats_nav before any parameter munging + $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'; + } + # we need to prepare $formats_nav before almost any parameter munging 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) { + if (defined $hash_parent && + $hash_parent ne '-c' && $hash_parent ne '--cc') { # commitdiff with two commits given my $hash_parent_short = $hash_parent; if ($hash_parent =~ m/^[0-9a-fA-F]{40}$/) { $hash_parent_short = substr($hash_parent, 0, 7); } $formats_nav .= - ' (from: ' . - $cgi->a({-href => href(action=>"commitdiff", - hash=>$hash_parent)}, + ' (from'; + for (my $i = 0; $i < @{$co{'parents'}}; $i++) { + if ($co{'parents'}[$i] eq $hash_parent) { + $formats_nav .= ' parent ' . ($i+1); + last; + } + } + $formats_nav .= ': ' . + $cgi->a({-href => href(-replay=>1, + hash=>$hash_parent, hash_base=>undef)}, esc_html($hash_parent_short)) . ')'; } elsif (!$co{'parent'}) { @@ -3734,25 +7682,39 @@ 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 .= ' | ' . + $cgi->a({-href => href(-replay=>1, + hash=>$hash, hash_parent=>'-c')}, + 'combined'); + } else { # $hash_parent eq '-c' + $formats_nav .= ' | ' . + $cgi->a({-href => href(-replay=>1, + hash=>$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'}} ) . ')'; } } - if (!defined $hash_parent) { - $hash_parent = $co{'parent'} || '--root'; + my $hash_parent_param = $hash_parent; + if (!defined $hash_parent_param) { + # --cc for multiple parents, --root for parentless + $hash_parent_param = + @{$co{'parents'}} > 1 ? '--cc' : $co{'parent'} || '--root'; } # read commitdiff @@ -3761,22 +7723,47 @@ sub git_commitdiff { if ($format eq 'html') { open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, "--no-commit-id", "--patch-with-raw", "--full-index", - $hash_parent, $hash, "--" - or die_error(undef, "Open git-diff-tree failed"); + $hash_parent_param, $hash, "--" + or die_error(500, "Open git-diff-tree failed"); - while (chomp(my $line = <$fd>)) { + while (my $line = <$fd>) { + chomp $line; # empty line ends raw part of diff-tree output last unless $line; - push @difftree, $line; + push @difftree, scalar parse_difftree_raw_line($line); } } elsif ($format eq 'plain') { open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, - '-p', $hash_parent, $hash, "--" - or die_error(undef, "Open git-diff-tree failed"); - + '-p', $hash_parent_param, $hash, "--" + or die_error(500, "Open git-diff-tree failed"); + } elsif ($format eq 'patch') { + # For commit ranges, we limit the output to the number of + # patches specified in the 'patches' feature. + # For single commits, we limit the output to a single patch, + # diverging from the git-format-patch default. + my @commit_spec = (); + if ($hash_parent) { + if ($patch_max > 0) { + push @commit_spec, "-$patch_max"; + } + push @commit_spec, '-n', "$hash_parent..$hash"; + } else { + if ($params{-single}) { + push @commit_spec, '-1'; + } else { + if ($patch_max > 0) { + push @commit_spec, "-$patch_max"; + } + push @commit_spec, "-n"; + } + push @commit_spec, '--root', $hash; + } + open $fd, "-|", git_cmd(), "format-patch", @diff_opts, + '--encoding=utf8', '--stdout', @commit_spec + or die_error(500, "Open git-format-patch failed"); } else { - die_error(undef, "Unknown commitdiff format"); + die_error(400, "Unknown commitdiff format"); } # non-textual hash id's can be cached @@ -3793,7 +7780,11 @@ sub git_commitdiff { git_header_html(undef, $expires); git_print_page_nav('commitdiff','', $hash,$co{'tree'},$hash, $formats_nav); git_print_header_div('commit', esc_html($co{'title'}) . $ref, $hash); - git_print_authorship(\%co); + print "
\n" . + "
commit$co{'id'}
tree" . $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, hash_base=>$hash)}, "tree"); - if ($have_snapshot) { - print " | " . - $cgi->a({-href => href(action=>"snapshot", hash=>$hash)}, "snapshot"); + my $snapshot_links = format_snapshot_links($hash); + if (defined $snapshot_links) { + print " | " . $snapshot_links; } print "
parent
\n"; + git_print_authorship_rows(\%co); + print "
". + "
\n"; print "
\n"; if (@{$co{'comment'}} > 1) { print "
\n"; @@ -3812,26 +7803,38 @@ sub git_commitdiff { -expires => $expires, -content_disposition => 'inline; filename="' . "$filename" . '"'); my %ad = parse_date($co{'author_epoch'}, $co{'author_tz'}); - print <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 if ($format eq 'html') { - git_difftree_body(\@difftree, $hash, $hash_parent); + my $use_parents = !defined $hash_parent || + $hash_parent eq '-c' || $hash_parent eq '--cc'; + git_difftree_body(\@difftree, $hash, + $use_parents ? @{$co{'parents'}} : $hash_parent); print "
\n"; - git_patchset_body($fd, \@difftree, $hash, $hash_parent); + git_patchset_body($fd, $diff_style, + \@difftree, $hash, + $use_parents ? @{$co{'parents'}} : $hash_parent); close $fd; print "
\n"; # class="page_body" git_footer_html(); @@ -3841,245 +7844,116 @@ TEXT print <$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'); +} + +# format-patch-style patches +sub git_patch { + git_commitdiff(-format => 'patch', -single => 1); +} + +sub git_patches { + git_commitdiff(-format => 'patch'); } 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"); - } - - my $refs = git_get_references(); - my $limit = sprintf("--max-count=%i", (100 * ($page+1))); - - if (!defined $hash && defined $file_name) { - $hash = git_get_hash_by_path($hash_base, $file_name); - } - if (defined $hash) { - $ftype = git_get_type($hash); - } - - open my $fd, "-|", - git_cmd(), "rev-list", $limit, "--full-history", $hash_base, "--", $file_name - or die_error(undef, "Open git-rev-list-failed"); - my @revlist = map { chomp; $_ } <$fd>; - close $fd - or die_error(undef, "Reading git-rev-list failed"); - - 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"; - $paging_nav .= " ⋅ prev"; - } - if ($#revlist >= (100 * ($page+1)-1)) { - $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"; - } - my $next_link = ''; - if ($#revlist >= (100 * ($page+1)-1)) { - $next_link = - $cgi->a({-href => href(action=>"history", hash=>$hash, hash_base=>$hash_base, - file_name=>$file_name, page=>$page+1), - -title => "Alt-n"}, "next"); - } - - 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, $hash_base); - - git_history_body(\@revlist, ($page * 100), $#revlist, - $refs, $hash_base, $ftype, $next_link); - - git_footer_html(); + git_log_generic('history', \&git_history_body, + $hash_base, $hash_parent_base, + $file_name, $hash); } sub git_search { + $searchtype ||= 'commit'; + + # check if appropriate features are enabled + gitweb_check_feature('search') + or die_error(403, "Search is disabled"); + if ($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"); + } + if ($searchtype eq 'grep') { + # grep search might be potentially CPU-intensive, too + gitweb_check_feature('grep') + or die_error(403, "Grep search is disabled"); + } + 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 '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_header_html(); - git_print_page_nav('','', $hash,$co{'tree'},$hash); - git_print_header_div('commit', esc_html($co{'title'}), $hash); - - print "\n"; - my $alternate = 1; - if ($searchtype eq 'commit' or $searchtype eq 'author' or $searchtype eq 'committer') { - $/ = "\0"; - open my $fd, "-|", git_cmd(), "rev-list", - "--header", "--parents", $hash, "--" - or next; - while (my $commit_text = <$fd>) { - if (!grep m/$searchtext/i, $commit_text) { - next; - } - if ($searchtype eq 'author' && !grep m/\nauthor .*$searchtext/i, $commit_text) { - next; - } - if ($searchtype eq 'committer' && !grep m/\ncommitter .*$searchtext/i, $commit_text) { - next; - } - my @commit_lines = split "\n", $commit_text; - my %co = parse_commit(undef, \@commit_lines); - if (!%co) { - next; - } - if ($alternate) { - print "\n"; - } else { - print "\n"; - } - $alternate ^= 1; - print "\n" . - "\n" . - "\n" . - "\n" . - "\n"; - } - close $fd; - } - - if ($searchtype eq 'pickaxe') { - $/ = "\n"; - my $git_command = git_cmd_str(); - open my $fd, "-|", "$git_command rev-list $hash | " . - "$git_command diff-tree -r --stdin -S\'$searchtext\'"; - 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 "\n"; - } else { - print "\n"; - } - $alternate ^= 1; - print "\n" . - "\n" . - "\n" . - "\n" . - "\n"; - } - %co = parse_commit($1); - } - } - close $fd; - } - print "
$co{'age_string_date'}" . esc_html(chop_str($co{'author_name'}, 15, 5)) . "" . - $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), -class => "list subject"}, - esc_html(chop_str($co{'title'}, 50)) . "
"); - my $comment = $co{'comment'}; - foreach my $line (@$comment) { - if ($line =~ m/^(.*)($searchtext)(.*)$/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$match$trail"; - print chop_str($text, 80, 5) . "
\n"; - } - } - print "		" . - $cgi->a({-href => href(action=>"commit", hash=>$co{'id'})}, "commit") . - " | " . - $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, hash_base=>$co{'id'})}, "tree"); - print "
$co{'age_string_date'}" . esc_html(chop_str($co{'author_name'}, 15, 5)) . "" . - $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), - -class => "list subject"}, - esc_html(chop_str($co{'title'}, 50)) . "
"); - 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"}, - "" . esc_path($set{'file'}) . "") . - "
\n"; - } - print "		" . - $cgi->a({-href => href(action=>"commit", hash=>$co{'id'})}, "commit") . - " | " . - $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, hash_base=>$co{'id'})}, "tree"); - print "
\n"; - git_footer_html(); } sub git_search_help { git_header_html(); git_print_page_nav('','', $hash,$hash,$hash); print <Pattern is by default a normal string that is matched precisely (but without +regard to case, except in the case of pickaxe). However, when you check the re checkbox, +the pattern entered is recognized as the POSIX extended +regular expression (also case +insensitive).

commit
-
The commit messages and authorship information will be scanned for the given string.
-
author
-
Name and e-mail of the change author and date of birth of the patch will be scanned for the given string.
-
committer
-
Name and e-mail of the committer and date of commit will be scanned for the given string.
+
The commit messages and authorship information will be scanned for the given pattern.
EOT - my ($have_pickaxe) = gitweb_check_feature('pickaxe'); + my $have_grep = gitweb_check_feature('grep'); + if ($have_grep) { + print <grep +
All files in the currently selected tree (HEAD unless you are explicitly browsing + 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.
+EOT + } + print <author +
Name and e-mail of the change author and date of birth of the patch will be scanned for the given pattern.
+
committer
+
Name and e-mail of the committer and date of commit will be scanned for the given pattern.
+EOT + my $have_pickaxe = gitweb_check_feature('pickaxe'); if ($have_pickaxe) { print <pickaxe
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.
+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. EOT } print "
\n"; @@ -4087,115 +7961,282 @@ 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 $limit = sprintf("--max-count=%i", (100 * ($page+1))); - open my $fd, "-|", git_cmd(), "rev-list", $limit, $hash, "--" - or die_error(undef, "Open git-rev-list failed"); - my @revlist = map { chomp; $_ } <$fd>; - close $fd; - - my $paging_nav = format_paging_nav('shortlog', $hash, $head, $page, $#revlist); - my $next_link = ''; - if ($#revlist >= (100 * ($page+1)-1)) { - $next_link = - $cgi->a({-href => href(action=>"shortlog", hash=>$hash, page=>$page+1), - -title => "Alt-n"}, "next"); - } - - - git_header_html(); - git_print_page_nav('shortlog','', $hash,$hash,$hash, $paging_nav); - git_print_header_div('summary', $project); - - git_shortlog_body(\@revlist, ($page * 100), $#revlist, $refs, $next_link); - - git_footer_html(); + git_log_generic('shortlog', \&git_shortlog_body, + $hash, $hash_parent); } ## ...................................................................... -## feeds (RSS, OPML) +## feeds (RSS, Atom; OPML) -sub git_rss { - # http://www.notestips.com/80256B3A007F2692/1/NAMO5P9UPQ - open my $fd, "-|", git_cmd(), "rev-list", "--max-count=150", - git_get_head_hash($project), "--" - or die_error(undef, "Open git-rev-list failed"); - my @revlist = map { chomp; $_ } <$fd>; - close $fd or die_error(undef, "Reading git-rev-list failed"); - print $cgi->header(-type => 'text/xml', -charset => 'utf-8'); - print < +sub git_feed { + my $format = shift || 'atom'; + 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(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, $file_name); + + my %latest_commit; + my %latest_date; + my $content_type = "application/$format+xml"; + if (defined $cgi->http('HTTP_ACCEPT') && + $cgi->Accept('text/xml') > $cgi->Accept($content_type)) { + # browser (feed reader) prefers text/xml + $content_type = 'text/xml'; + } + if (defined($commitlist[0])) { + %latest_commit = %{$commitlist[0]}; + my $latest_epoch = $latest_commit{'committer_epoch'}; + exit_if_unmodified_since($latest_epoch); + %latest_date = parse_date($latest_epoch, $latest_commit{'committer_tz'}); + } + print $cgi->header( + -type => $content_type, + -charset => 'utf-8', + %latest_date ? (-last_modified => $latest_date{'rfc2822'}) : (), + -status => '200 OK'); + + # Optimization: skip generating the body if client asks only + # for Last-Modified date. + return if ($cgi->request_method() eq 'HEAD'); + + # header variables + my $title = "$site_name - $project/$action"; + my $feed_type = 'log'; + if (defined $hash) { + $title .= " - '$hash'"; + $feed_type = 'branch log'; + if (defined $file_name) { + $title .= " :: $file_name"; + $feed_type = 'history'; + } + } elsif (defined $file_name) { + $title .= " - $file_name"; + $feed_type = 'history'; + } + $title .= " $feed_type"; + $title = esc_html($title); + my $descr = git_get_project_description($project); + if (defined $descr) { + $descr = esc_html($descr); + } else { + $descr = "$project " . + ($format eq 'rss' ? 'RSS' : 'Atom') . + " feed"; + } + my $owner = git_get_project_owner($project); + $owner = esc_html($owner); + + #header + my $alt_url; + if (defined $file_name) { + $alt_url = href(-full=>1, action=>"history", hash=>$hash, file_name=>$file_name); + } elsif (defined $hash) { + $alt_url = href(-full=>1, action=>"log", hash=>$hash); + } else { + $alt_url = href(-full=>1, action=>"summary"); + } + print qq!\n!; + if ($format eq 'rss') { + print < -$project $my_uri $my_url -${\esc_html("$my_url?p=$project;a=summary")} -$project log -en XML + print "$title\n" . + "$alt_url\n" . + "$descr\n" . + "en\n" . + # project owner is responsible for 'editorial' content + "$owner\n"; + if (defined $logo || defined $favicon) { + # prefer the logo to the favicon, since RSS + # doesn't allow both + my $img = esc_url($logo || $favicon); + print "\n" . + "$img\n" . + "$title\n" . + "$alt_url\n" . + "\n"; + } + if (%latest_date) { + print "$latest_date{'rfc2822'}\n"; + print "$latest_date{'rfc2822'}\n"; + } + print "gitweb v.$version/$git_version\n"; + } elsif ($format eq 'atom') { + print < +XML + print "$title\n" . + "$descr\n" . + '' . "\n" . + '' . "\n" . + "" . href(-full=>1) . "\n" . + # use project owner for feed author + "$owner\n"; + if (defined $favicon) { + print "" . esc_url($favicon) . "\n"; + } + if (defined $logo) { + # not twice as wide as tall: 72 x 27 pixels + print "" . esc_url($logo) . "\n"; + } + if (! %latest_date) { + # dummy date to keep the feed valid until commits trickle in: + print "1970-01-01T00:00:00Z\n"; + } else { + print "$latest_date{'iso-8601'}\n"; + } + print "gitweb\n"; + } - for (my $i = 0; $i <= $#revlist; $i++) { - my $commit = $revlist[$i]; - my %co = parse_commit($commit); + # contents + for (my $i = 0; $i <= $#commitlist; $i++) { + my %co = %{$commitlist[$i]}; + my $commit = $co{'id'}; # we read 150, we always show 30 and the ones more recent than 48 hours - if (($i >= 20) && ((time - $co{'committer_epoch'}) > 48*60*60)) { + if (($i >= 20) && ((time - $co{'author_epoch'}) > 48*60*60)) { last; } - my %cd = parse_date($co{'committer_epoch'}); - open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, - $co{'parent'}, $co{'id'}, "--" + my %cd = parse_date($co{'author_epoch'}, $co{'author_tz'}); + + # get list of changed files + open my $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, + $co{'parent'} || "--root", + $co{'id'}, "--", (defined $file_name ? $file_name : ()) or next; my @difftree = map { chomp; $_ } <$fd>; close $fd or next; - print "\n" . - "" . - sprintf("%d %s %02d:%02d", $cd{'mday'}, $cd{'month'}, $cd{'hour'}, $cd{'minute'}) . " - " . esc_html($co{'title'}) . - "\n" . - "" . esc_html($co{'author'}) . "\n" . - "$cd{'rfc2822'}\n" . - "" . esc_html("$my_url?p=$project;a=commit;h=$commit") . "\n" . - "" . esc_html("$my_url?p=$project;a=commit;h=$commit") . "\n" . - "" . esc_html($co{'title'}) . "\n" . - "" . - "\n"; - } - print "
\n"; - foreach my $line (@difftree) { - if (!($line =~ m/^:([0-7]{6}) ([0-7]{6}) ([0-9a-fA-F]{40}) ([0-9a-fA-F]{40}) (.)([0-9]{0,3})\t(.*)$/)) { - next; + + # print element (entry, item) + my $co_url = href(-full=>1, action=>"commitdiff", hash=>$commit); + if ($format eq 'rss') { + print "\n" . + "" . esc_html($co{'title'}) . "\n" . + "" . esc_html($co{'author'}) . "\n" . + "$cd{'rfc2822'}\n" . + "$co_url\n" . + "$co_url\n" . + "" . esc_html($co{'title'}) . "\n" . + "" . + "\n" . + "" . esc_html($co{'title'}) . "\n" . + "$cd{'iso-8601'}\n" . + "\n" . + " " . esc_html($co{'author_name'}) . "\n"; + if ($co{'author_email'}) { + print " " . esc_html($co{'author_email'}) . "\n"; } - my $file = esc_path(unquote($7)); - $file = to_utf8($file); - print "$file
\n"; + print "\n" . + # use committer for contributor + "\n" . + " " . esc_html($co{'committer_name'}) . "\n"; + if ($co{'committer_email'}) { + print " " . esc_html($co{'committer_email'}) . "\n"; + } + print "\n" . + "$cd{'iso-8601'}\n" . + "\n" . + "$co_url\n" . + "\n" . + "
\n"; + } + my $comment = $co{'comment'}; + print "
\n";
+		foreach my $line (@$comment) {
+			$line = esc_html($line);
+			print "$line\n";
+		}
+		print "
    \n"; + foreach my $difftree_line (@difftree) { + my %difftree = parse_difftree_raw_line($difftree_line); + next if !$difftree{'from_id'}; + + my $file = $difftree{'file'} || $difftree{'to_file'}; + + print "
  • " . + "[" . + $cgi->a({-href => href(-full=>1, action=>"blobdiff", + hash=>$difftree{'to_id'}, hash_parent=>$difftree{'from_id'}, + hash_base=>$co{'id'}, hash_parent_base=>$co{'parent'}, + file_name=>$file, file_parent=>$difftree{'from_file'}), + -title => "diff"}, 'D'); + if ($have_blame) { + print $cgi->a({-href => href(-full=>1, action=>"blame", + file_name=>$file, hash_base=>$commit), + -title => "blame"}, 'B'); + } + # if this is not a feed of a file history + if (!defined $file_name || $file_name ne $file) { + print $cgi->a({-href => href(-full=>1, action=>"history", + file_name=>$file, hash=>$commit), + -title => "history"}, 'H'); + } + $file = esc_path($file); + print "] ". + "$file
    • \n"; + } + if ($format eq 'rss') { + print "
]]>\n" . + "\n" . + "\n"; + } elsif ($format eq 'atom') { + print "\n
\n" . + "\n" . + "\n"; } - print "]]>\n" . - "\n" . - "\n"; } - print ""; + + # end of feed + if ($format eq 'rss') { + print "\n\n"; + } elsif ($format eq 'atom') { + print "\n"; + } +} + +sub git_rss { + git_feed('rss'); +} + +sub git_atom { + git_feed('atom'); } sub git_opml { - my @list = git_get_projects_list(); + my @list = git_get_projects_list($project_filter, $strict_export); + if (!@list) { + die_error(404, "No projects found"); + } - print $cgi->header(-type => 'text/xml', -charset => 'utf-8'); + print $cgi->header( + -type => 'text/xml', + -charset => 'utf-8', + -content_disposition => 'inline; filename="opml.xml"'); + + my $title = esc_html($site_name); + my $filter = " within subdirectory "; + if (defined $project_filter) { + $filter .= esc_html($project_filter); + } else { + $filter = ""; + } print < - $site_name OPML Export + $title OPML Export$filter @@ -4214,8 +8255,8 @@ 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 "\n"; } print < +// 2007, Petr Baudis +// 2008-2011, Jakub Narebski + +/** + * @fileOverview Generic JavaScript code (helper functions) + * @license GPLv2 or later + */ + + +/* ============================================================ */ +/* ............................................................ */ +/* Padding */ + +/** + * pad INPUT on the left with STR that is assumed to have visible + * width of single character (for example nonbreakable spaces), + * to WIDTH characters + * + * example: padLeftStr(12, 3, '\u00A0') == '\u00A012' + * ('\u00A0' is nonbreakable space) + * + * @param {Number|String} input: number to pad + * @param {Number} width: visible width of output + * @param {String} str: string to prefix to string, defaults to '\u00A0' + * @returns {String} INPUT prefixed with STR x (WIDTH - INPUT.length) + */ +function padLeftStr(input, width, str) { + var prefix = ''; + if (typeof str === 'undefined') { + ch = '\u00A0'; // using ' ' doesn't work in all browsers + } + + width -= input.toString().length; + while (width > 0) { + prefix += str; + width--; + } + return prefix + input; +} + +/** + * Pad INPUT on the left to WIDTH, using given padding character CH, + * for example padLeft('a', 3, '_') is '__a' + * padLeft(4, 2) is '04' (same as padLeft(4, 2, '0')) + * + * @param {String} input: input value converted to string. + * @param {Number} width: desired length of output. + * @param {String} ch: single character to prefix to string, defaults to '0'. + * + * @returns {String} Modified string, at least SIZE length. + */ +function padLeft(input, width, ch) { + var s = input + ""; + if (typeof ch === 'undefined') { + ch = '0'; + } + + while (s.length < width) { + s = ch + s; + } + return s; +} + + +/* ............................................................ */ +/* Handling browser incompatibilities */ + +/** + * Create XMLHttpRequest object in cross-browser way + * @returns XMLHttpRequest object, or null + */ +function createRequestObject() { + try { + return new XMLHttpRequest(); + } catch (e) {} + try { + return window.createRequest(); + } catch (e) {} + try { + return new ActiveXObject("Msxml2.XMLHTTP"); + } catch (e) {} + try { + return new ActiveXObject("Microsoft.XMLHTTP"); + } catch (e) {} + + return null; +} + + +/** + * Insert rule giving specified STYLE to given SELECTOR at the end of + * first CSS stylesheet. + * + * @param {String} selector: CSS selector, e.g. '.class' + * @param {String} style: rule contents, e.g. 'background-color: red;' + */ +function addCssRule(selector, style) { + var stylesheet = document.styleSheets[0]; + + var theRules = []; + if (stylesheet.cssRules) { // W3C way + theRules = stylesheet.cssRules; + } else if (stylesheet.rules) { // IE way + theRules = stylesheet.rules; + } + + if (stylesheet.insertRule) { // W3C way + stylesheet.insertRule(selector + ' { ' + style + ' }', theRules.length); + } else if (stylesheet.addRule) { // IE way + stylesheet.addRule(selector, style); + } +} + + +/* ............................................................ */ +/* Support for legacy browsers */ + +/** + * Provides getElementsByClassName method, if there is no native + * implementation of this method. + * + * NOTE that there are limits and differences compared to native + * getElementsByClassName as defined by e.g.: + * https://developer.mozilla.org/en/DOM/document.getElementsByClassName + * http://www.whatwg.org/specs/web-apps/current-work/multipage/dom.html#dom-getelementsbyclassname + * http://www.whatwg.org/specs/web-apps/current-work/multipage/dom.html#dom-document-getelementsbyclassname + * + * Namely, this implementation supports only single class name as + * argument and not set of space-separated tokens representing classes, + * it returns Array of nodes rather than live NodeList, and has + * additional optional argument where you can limit search to given tags + * (via getElementsByTagName). + * + * Based on + * http://code.google.com/p/getelementsbyclassname/ + * http://www.dustindiaz.com/getelementsbyclass/ + * http://stackoverflow.com/questions/1818865/do-we-have-getelementsbyclassname-in-javascript + * + * See also http://ejohn.org/blog/getelementsbyclassname-speed-comparison/ + * + * @param {String} class: name of _single_ class to find + * @param {String} [taghint] limit search to given tags + * @returns {Node[]} array of matching elements + */ +if (!('getElementsByClassName' in document)) { + document.getElementsByClassName = function (classname, taghint) { + taghint = taghint || "*"; + var elements = (taghint === "*" && document.all) ? + document.all : + document.getElementsByTagName(taghint); + var pattern = new RegExp("(^|\\s)" + classname + "(\\s|$)"); + var matches= []; + for (var i = 0, j = 0, n = elements.length; i < n; i++) { + var el= elements[i]; + if (el.className && pattern.test(el.className)) { + // matches.push(el); + matches[j] = el; + j++; + } + } + return matches; + }; +} // end if + + +/* ............................................................ */ +/* unquoting/unescaping filenames */ + +/**#@+ + * @constant + */ +var escCodeRe = /\\([^0-7]|[0-7]{1,3})/g; +var octEscRe = /^[0-7]{1,3}$/; +var maybeQuotedRe = /^\"(.*)\"$/; +/**#@-*/ + +/** + * unquote maybe C-quoted filename (as used by git, i.e. it is + * in double quotes '"' if there is any escape character used) + * e.g. 'aa' -> 'aa', '"a\ta"' -> 'a a' + * + * @param {String} str: git-quoted string + * @returns {String} Unquoted and unescaped string + * + * @globals escCodeRe, octEscRe, maybeQuotedRe + */ +function unquote(str) { + function unq(seq) { + var es = { + // character escape codes, aka escape sequences (from C) + // replacements are to some extent JavaScript specific + t: "\t", // tab (HT, TAB) + n: "\n", // newline (NL) + r: "\r", // return (CR) + f: "\f", // form feed (FF) + b: "\b", // backspace (BS) + a: "\x07", // alarm (bell) (BEL) + e: "\x1B", // escape (ESC) + v: "\v" // vertical tab (VT) + }; + + if (seq.search(octEscRe) !== -1) { + // octal char sequence + return String.fromCharCode(parseInt(seq, 8)); + } else if (seq in es) { + // C escape sequence, aka character escape code + return es[seq]; + } + // quoted ordinary character + return seq; + } + + var match = str.match(maybeQuotedRe); + if (match) { + str = match[1]; + // perhaps str = eval('"'+str+'"'); would be enough? + str = str.replace(escCodeRe, + function (substr, p1, offset, s) { return unq(p1); }); + } + return str; +} + +/* end of common-lib.js */ +// Copyright (C) 2007, Fredrik Kuivinen +// 2007, Petr Baudis +// 2008-2011, Jakub Narebski + +/** + * @fileOverview Datetime manipulation: parsing and formatting + * @license GPLv2 or later + */ + + +/* ............................................................ */ +/* parsing and retrieving datetime related information */ + +/** + * used to extract hours and minutes from timezone info, e.g '-0900' + * @constant + */ +var tzRe = /^([+\-])([0-9][0-9])([0-9][0-9])$/; + +/** + * convert numeric timezone +/-ZZZZ to offset from UTC in seconds + * + * @param {String} timezoneInfo: numeric timezone '(+|-)HHMM' + * @returns {Number} offset from UTC in seconds for timezone + * + * @globals tzRe + */ +function timezoneOffset(timezoneInfo) { + var match = tzRe.exec(timezoneInfo); + var tz_sign = (match[1] === '-' ? -1 : +1); + var tz_hour = parseInt(match[2],10); + var tz_min = parseInt(match[3],10); + + return tz_sign*(((tz_hour*60) + tz_min)*60); +} + +/** + * return local (browser) timezone as offset from UTC in seconds + * + * @returns {Number} offset from UTC in seconds for local timezone + */ +function localTimezoneOffset() { + // getTimezoneOffset returns the time-zone offset from UTC, + // in _minutes_, for the current locale + return ((new Date()).getTimezoneOffset() * -60); +} + +/** + * return local (browser) timezone as numeric timezone '(+|-)HHMM' + * + * @returns {String} locat timezone as -/+ZZZZ + */ +function localTimezoneInfo() { + var tzOffsetMinutes = (new Date()).getTimezoneOffset() * -1; + + return formatTimezoneInfo(0, tzOffsetMinutes); +} + + +/** + * Parse RFC-2822 date into a Unix timestamp (into epoch) + * + * @param {String} date: date in RFC-2822 format, e.g. 'Thu, 21 Dec 2000 16:01:07 +0200' + * @returns {Number} epoch i.e. seconds since '00:00:00 1970-01-01 UTC' + */ +function parseRFC2822Date(date) { + // Date.parse accepts the IETF standard (RFC 1123 Section 5.2.14 and elsewhere) + // date syntax, which is defined in RFC 2822 (obsoletes RFC 822) + // and returns number of _milli_seconds since January 1, 1970, 00:00:00 UTC + return Date.parse(date) / 1000; +} + + +/* ............................................................ */ +/* formatting date */ + +/** + * format timezone offset as numerical timezone '(+|-)HHMM' or '(+|-)HH:MM' + * + * @param {Number} hours: offset in hours, e.g. 2 for '+0200' + * @param {Number} [minutes] offset in minutes, e.g. 30 for '-4030'; + * it is split into hours if not 0 <= minutes < 60, + * for example 1200 would give '+0100'; + * defaults to 0 + * @param {String} [sep] separator between hours and minutes part, + * default is '', might be ':' for W3CDTF (rfc-3339) + * @returns {String} timezone in '(+|-)HHMM' or '(+|-)HH:MM' format + */ +function formatTimezoneInfo(hours, minutes, sep) { + minutes = minutes || 0; // to be able to use formatTimezoneInfo(hh) + sep = sep || ''; // default format is +/-ZZZZ + + if (minutes < 0 || minutes > 59) { + hours = minutes > 0 ? Math.floor(minutes / 60) : Math.ceil(minutes / 60); + minutes = Math.abs(minutes - 60*hours); // sign of minutes is sign of hours + // NOTE: this works correctly because there is no UTC-00:30 timezone + } + + var tzSign = hours >= 0 ? '+' : '-'; + if (hours < 0) { + hours = -hours; // sign is stored in tzSign + } + + return tzSign + padLeft(hours, 2, '0') + sep + padLeft(minutes, 2, '0'); +} + +/** + * translate 'utc' and 'local' to numerical timezone + * @param {String} timezoneInfo: might be 'utc' or 'local' (browser) + */ +function normalizeTimezoneInfo(timezoneInfo) { + switch (timezoneInfo) { + case 'utc': + return '+0000'; + case 'local': // 'local' is browser timezone + return localTimezoneInfo(); + } + return timezoneInfo; +} + + +/** + * return date in local time formatted in iso-8601 like format + * 'yyyy-mm-dd HH:MM:SS +/-ZZZZ' e.g. '2005-08-07 21:49:46 +0200' + * + * @param {Number} epoch: seconds since '00:00:00 1970-01-01 UTC' + * @param {String} timezoneInfo: numeric timezone '(+|-)HHMM' + * @returns {String} date in local time in iso-8601 like format + */ +function formatDateISOLocal(epoch, timezoneInfo) { + // date corrected by timezone + var localDate = new Date(1000 * (epoch + + timezoneOffset(timezoneInfo))); + var localDateStr = // e.g. '2005-08-07' + localDate.getUTCFullYear() + '-' + + padLeft(localDate.getUTCMonth()+1, 2, '0') + '-' + + padLeft(localDate.getUTCDate(), 2, '0'); + var localTimeStr = // e.g. '21:49:46' + padLeft(localDate.getUTCHours(), 2, '0') + ':' + + padLeft(localDate.getUTCMinutes(), 2, '0') + ':' + + padLeft(localDate.getUTCSeconds(), 2, '0'); + + return localDateStr + ' ' + localTimeStr + ' ' + timezoneInfo; +} + +/** + * return date in local time formatted in rfc-2822 format + * e.g. 'Thu, 21 Dec 2000 16:01:07 +0200' + * + * @param {Number} epoch: seconds since '00:00:00 1970-01-01 UTC' + * @param {String} timezoneInfo: numeric timezone '(+|-)HHMM' + * @param {Boolean} [padDay] e.g. 'Sun, 07 Aug' if true, 'Sun, 7 Aug' otherwise + * @returns {String} date in local time in rfc-2822 format + */ +function formatDateRFC2882(epoch, timezoneInfo, padDay) { + // A short textual representation of a month, three letters + var months = ["Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"]; + // A textual representation of a day, three letters + var days = ["Sun", "Mon", "Tue", "Wed", "Thu", "Fri", "Sat"]; + // date corrected by timezone + var localDate = new Date(1000 * (epoch + + timezoneOffset(timezoneInfo))); + var localDateStr = // e.g. 'Sun, 7 Aug 2005' or 'Sun, 07 Aug 2005' + days[localDate.getUTCDay()] + ', ' + + (padDay ? padLeft(localDate.getUTCDate(),2,'0') : localDate.getUTCDate()) + ' ' + + months[localDate.getUTCMonth()] + ' ' + + localDate.getUTCFullYear(); + var localTimeStr = // e.g. '21:49:46' + padLeft(localDate.getUTCHours(), 2, '0') + ':' + + padLeft(localDate.getUTCMinutes(), 2, '0') + ':' + + padLeft(localDate.getUTCSeconds(), 2, '0'); + + return localDateStr + ' ' + localTimeStr + ' ' + timezoneInfo; +} + +/* end of datetime.js */ +/** + * @fileOverview Accessing cookies from JavaScript + * @license GPLv2 or later + */ + +/* + * Based on subsection "Cookies in JavaScript" of "Professional + * JavaScript for Web Developers" by Nicholas C. Zakas and cookie + * plugin from jQuery (dual licensed under the MIT and GPL licenses) + */ + + +/** + * Create a cookie with the given name and value, + * and other optional parameters. + * + * @example + * setCookie('foo', 'bar'); // will be deleted when browser exits + * setCookie('foo', 'bar', { expires: new Date(Date.parse('Jan 1, 2012')) }); + * setCookie('foo', 'bar', { expires: 7 }); // 7 days = 1 week + * setCookie('foo', 'bar', { expires: 14, path: '/' }); + * + * @param {String} sName: Unique name of a cookie (letters, numbers, underscores). + * @param {String} sValue: The string value stored in a cookie. + * @param {Object} [options] An object literal containing key/value pairs + * to provide optional cookie attributes. + * @param {String|Number|Date} [options.expires] Either literal string to be used as cookie expires, + * or an integer specifying the expiration date from now on in days, + * or a Date object to be used as cookie expiration date. + * If a negative value is specified or a date in the past), + * the cookie will be deleted. + * If set to null or omitted, the cookie will be a session cookie + * and will not be retained when the browser exits. + * @param {String} [options.path] Restrict access of a cookie to particular directory + * (default: path of page that created the cookie). + * @param {String} [options.domain] Override what web sites are allowed to access cookie + * (default: domain of page that created the cookie). + * @param {Boolean} [options.secure] If true, the secure attribute of the cookie will be set + * and the cookie would be accessible only from secure sites + * (cookie transmission will require secure protocol like HTTPS). + */ +function setCookie(sName, sValue, options) { + options = options || {}; + if (sValue === null) { + sValue = ''; + option.expires = 'delete'; + } + + var sCookie = sName + '=' + encodeURIComponent(sValue); + + if (options.expires) { + var oExpires = options.expires, sDate; + if (oExpires === 'delete') { + sDate = 'Thu, 01 Jan 1970 00:00:00 GMT'; + } else if (typeof oExpires === 'string') { + sDate = oExpires; + } else { + var oDate; + if (typeof oExpires === 'number') { + oDate = new Date(); + oDate.setTime(oDate.getTime() + (oExpires * 24 * 60 * 60 * 1000)); // days to ms + } else { + oDate = oExpires; + } + sDate = oDate.toGMTString(); + } + sCookie += '; expires=' + sDate; + } + + if (options.path) { + sCookie += '; path=' + (options.path); + } + if (options.domain) { + sCookie += '; domain=' + (options.domain); + } + if (options.secure) { + sCookie += '; secure'; + } + document.cookie = sCookie; +} + +/** + * Get the value of a cookie with the given name. + * + * @param {String} sName: Unique name of a cookie (letters, numbers, underscores) + * @returns {String|null} The string value stored in a cookie + */ +function getCookie(sName) { + var sRE = '(?:; )?' + sName + '=([^;]*);?'; + var oRE = new RegExp(sRE); + if (oRE.test(document.cookie)) { + return decodeURIComponent(RegExp['$1']); + } else { + return null; + } +} + +/** + * Delete cookie with given name + * + * @param {String} sName: Unique name of a cookie (letters, numbers, underscores) + * @param {Object} [options] An object literal containing key/value pairs + * to provide optional cookie attributes. + * @param {String} [options.path] Must be the same as when setting a cookie + * @param {String} [options.domain] Must be the same as when setting a cookie + */ +function deleteCookie(sName, options) { + options = options || {}; + options.expires = 'delete'; + + setCookie(sName, '', options); +} + +/* end of cookies.js */ +// Copyright (C) 2007, Fredrik Kuivinen +// 2007, Petr Baudis +// 2008-2011, Jakub Narebski + +/** + * @fileOverview Detect if JavaScript is enabled, and pass it to server-side + * @license GPLv2 or later + */ + + +/* ============================================================ */ +/* Manipulating links */ + +/** + * used to check if link has 'js' query parameter already (at end), + * and other reasons to not add 'js=1' param at the end of link + * @constant + */ +var jsExceptionsRe = /[;?]js=[01](#.*)?$/; + +/** + * Add '?js=1' or ';js=1' to the end of every link in the document + * that doesn't have 'js' query parameter set already. + * + * Links with 'js=1' lead to JavaScript version of given action, if it + * exists (currently there is only 'blame_incremental' for 'blame') + * + * To be used as `window.onload` handler + * + * @globals jsExceptionsRe + */ +function fixLinks() { + var allLinks = document.getElementsByTagName("a") || document.links; + for (var i = 0, len = allLinks.length; i < len; i++) { + var link = allLinks[i]; + if (!jsExceptionsRe.test(link)) { + link.href = link.href.replace(/(#|$)/, + (link.href.indexOf('?') === -1 ? '?' : ';') + 'js=1$1'); + } + } +} + +/* end of javascript-detection.js */ +// Copyright (C) 2011, John 'Warthog9' Hawley +// 2011, Jakub Narebski + +/** + * @fileOverview Manipulate dates in gitweb output, adjusting timezone + * @license GPLv2 or later + */ + +/** + * Get common timezone, add UI for changing timezones, and adjust + * dates to use requested common timezone. + * + * This function is called during onload event (added to window.onload). + * + * @param {String} tzDefault: default timezone, if there is no cookie + * @param {Object} tzCookieInfo: object literal with info about cookie to store timezone + * @param {String} tzCookieInfo.name: name of cookie to store timezone + * @param {String} tzClassName: denotes elements with date to be adjusted + */ +function onloadTZSetup(tzDefault, tzCookieInfo, tzClassName) { + var tzCookieTZ = getCookie(tzCookieInfo.name, tzCookieInfo); + var tz = tzDefault; + + if (tzCookieTZ) { + // set timezone to value saved in a cookie + tz = tzCookieTZ; + // refresh cookie, so its expiration counts from last use of gitweb + setCookie(tzCookieInfo.name, tzCookieTZ, tzCookieInfo); + } + + // add UI for changing timezone + addChangeTZ(tz, tzCookieInfo, tzClassName); + + // server-side of gitweb produces datetime in UTC, + // so if tz is 'utc' there is no need for changes + var nochange = tz === 'utc'; + + // adjust dates to use specified common timezone + fixDatetimeTZ(tz, tzClassName, nochange); +} + + +/* ...................................................................... */ +/* Changing dates to use requested timezone */ + +/** + * Replace RFC-2822 dates contained in SPAN elements with tzClassName + * CSS class with equivalent dates in given timezone. + * + * @param {String} tz: numeric timezone in '(-|+)HHMM' format, or 'utc', or 'local' + * @param {String} tzClassName: specifies elements to be changed + * @param {Boolean} nochange: markup for timezone change, but don't change it + */ +function fixDatetimeTZ(tz, tzClassName, nochange) { + // sanity check, method should be ensured by common-lib.js + if (!document.getElementsByClassName) { + return; + } + + // translate to timezone in '(-|+)HHMM' format + tz = normalizeTimezoneInfo(tz); + + // NOTE: result of getElementsByClassName should probably be cached + var classesFound = document.getElementsByClassName(tzClassName, "span"); + for (var i = 0, len = classesFound.length; i < len; i++) { + var curElement = classesFound[i]; + + curElement.title = 'Click to change timezone'; + if (!nochange) { + // we use *.firstChild.data (W3C DOM) instead of *.innerHTML + // as the latter doesn't always work everywhere in every browser + var epoch = parseRFC2822Date(curElement.firstChild.data); + var adjusted = formatDateRFC2882(epoch, tz); + + curElement.firstChild.data = adjusted; + } + } +} + + +/* ...................................................................... */ +/* Adding triggers, generating timezone menu, displaying and hiding */ + +/** + * Adds triggers for UI to change common timezone used for dates in + * gitweb output: it marks up and/or creates item to click to invoke + * timezone change UI, creates timezone UI fragment to be attached, + * and installs appropriate onclick trigger (via event delegation). + * + * @param {String} tzSelected: pre-selected timezone, + * 'utc' or 'local' or '(-|+)HHMM' + * @param {Object} tzCookieInfo: object literal with info about cookie to store timezone + * @param {String} tzClassName: specifies elements to install trigger + */ +function addChangeTZ(tzSelected, tzCookieInfo, tzClassName) { + // make link to timezone UI discoverable + addCssRule('.'+tzClassName + ':hover', + 'text-decoration: underline; cursor: help;'); + + // create form for selecting timezone (to be saved in a cookie) + var tzSelectFragment = document.createDocumentFragment(); + tzSelectFragment = createChangeTZForm(tzSelectFragment, + tzSelected, tzCookieInfo, tzClassName); + + // event delegation handler for timezone selection UI (clicking on entry) + // see http://www.nczonline.net/blog/2009/06/30/event-delegation-in-javascript/ + // assumes that there is no existing document.onclick handler + document.onclick = function onclickHandler(event) { + //IE doesn't pass in the event object + event = event || window.event; + + //IE uses srcElement as the target + var target = event.target || event.srcElement; + + switch (target.className) { + case tzClassName: + // don't display timezone menu if it is already displayed + if (tzSelectFragment.childNodes.length > 0) { + displayChangeTZForm(target, tzSelectFragment); + } + break; + } // end switch + }; +} + +/** + * Create DocumentFragment with UI for changing common timezone in + * which dates are shown in. + * + * @param {DocumentFragment} documentFragment: where attach UI + * @param {String} tzSelected: default (pre-selected) timezone + * @param {Object} tzCookieInfo: object literal with info about cookie to store timezone + * @returns {DocumentFragment} + */ +function createChangeTZForm(documentFragment, tzSelected, tzCookieInfo, tzClassName) { + var div = document.createElement("div"); + div.className = 'popup'; + + /* '
X
' */ + var closeButton = document.createElement('div'); + closeButton.className = 'close-button'; + closeButton.title = '(click on this box to close)'; + closeButton.appendChild(document.createTextNode('X')); + closeButton.onclick = closeTZFormHandler(documentFragment, tzClassName); + div.appendChild(closeButton); + + /* 'Select timezone:
' */ + div.appendChild(document.createTextNode('Select timezone: ')); + var br = document.createElement('br'); + br.clear = 'all'; + div.appendChild(br); + + /* '' */ + var select = document.createElement("select"); + select.name = "tzoffset"; + //select.style.clear = 'all'; + select.appendChild(generateTZOptions(tzSelected)); + select.onchange = selectTZHandler(documentFragment, tzCookieInfo, tzClassName); + div.appendChild(select); + + documentFragment.appendChild(div); + + return documentFragment; +} + + +/** + * Hide (remove from DOM) timezone change UI, ensuring that it is not + * garbage collected and that it can be re-enabled later. + * + * @param {DocumentFragment} documentFragment: contains detached UI + * @param {HTMLSelectElement} target: select element inside of UI + * @param {String} tzClassName: specifies element where UI was installed + * @returns {DocumentFragment} documentFragment + */ +function removeChangeTZForm(documentFragment, target, tzClassName) { + // find containing element, where we appended timezone selection UI + // `target' is somewhere inside timezone menu + var container = target.parentNode, popup = target; + while (container && + container.className !== tzClassName) { + popup = container; + container = container.parentNode; + } + // safety check if we found correct container, + // and if it isn't deleted already + if (!container || !popup || + container.className !== tzClassName || + popup.className !== 'popup') { + return documentFragment; + } + + // timezone selection UI was appended as last child + // see also displayChangeTZForm function + var removed = popup.parentNode.removeChild(popup); + if (documentFragment.firstChild !== removed) { // the only child + // re-append it so it would be available for next time + documentFragment.appendChild(removed); + } + // all of inline style was added by this script + // it is not really needed to remove it, but it is a good practice + container.removeAttribute('style'); + + return documentFragment; +} + + +/** + * Display UI for changing common timezone for dates in gitweb output. + * To be used from 'onclick' event handler. + * + * @param {HTMLElement} target: where to install/display UI + * @param {DocumentFragment} tzSelectFragment: timezone selection UI + */ +function displayChangeTZForm(target, tzSelectFragment) { + // for absolute positioning to be related to target element + target.style.position = 'relative'; + target.style.display = 'inline-block'; + + // show/display UI for changing timezone + target.appendChild(tzSelectFragment); +} + + +/* ...................................................................... */ +/* List of timezones for timezone selection menu */ + +/** + * Generate list of timezones for creating timezone select UI + * + * @returns {Object[]} list of e.g. { value: '+0100', descr: 'GMT+01:00' } + */ +function generateTZList() { + var timezones = [ + { value: "utc", descr: "UTC/GMT"}, + { value: "local", descr: "Local (per browser)"} + ]; + + // generate all full hour timezones (no fractional timezones) + for (var x = -12, idx = timezones.length; x <= +14; x++, idx++) { + var hours = (x >= 0 ? '+' : '-') + padLeft(x >=0 ? x : -x, 2); + timezones[idx] = { value: hours + '00', descr: 'UTC' + hours + ':00'}; + if (x === 0) { + timezones[idx].descr = 'UTC\u00B100:00'; // 'UTC±00:00' + } + } + + return timezones; +} + +/** + * Generate elements for timezone select UI + * + * @param {String} tzSelected: default timezone + * @returns {DocumentFragment} list of options elements to appendChild + */ +function generateTZOptions(tzSelected) { + var elems = document.createDocumentFragment(); + var timezones = generateTZList(); + + for (var i = 0, len = timezones.length; i < len; i++) { + var tzone = timezones[i]; + var option = document.createElement("option"); + if (tzone.value === tzSelected) { + option.defaultSelected = true; + } + option.value = tzone.value; + option.appendChild(document.createTextNode(tzone.descr)); + + elems.appendChild(option); + } + + return elems; +} + + +/* ...................................................................... */ +/* Event handlers and/or their generators */ + +/** + * Create event handler that select timezone and closes timezone select UI. + * To be used as $('select[name="tzselect"]').onchange handler. + * + * @param {DocumentFragment} tzSelectFragment: timezone selection UI + * @param {Object} tzCookieInfo: object literal with info about cookie to store timezone + * @param {String} tzCookieInfo.name: name of cookie to save result of selection + * @param {String} tzClassName: specifies element where UI was installed + * @returns {Function} event handler + */ +function selectTZHandler(tzSelectFragment, tzCookieInfo, tzClassName) { + //return function selectTZ(event) { + return function (event) { + event = event || window.event; + var target = event.target || event.srcElement; + + var selected = target.options.item(target.selectedIndex); + removeChangeTZForm(tzSelectFragment, target, tzClassName); + + if (selected) { + selected.defaultSelected = true; + setCookie(tzCookieInfo.name, selected.value, tzCookieInfo); + fixDatetimeTZ(selected.value, tzClassName); + } + }; +} + +/** + * Create event handler that closes timezone select UI. + * To be used e.g. as $('.closebutton').onclick handler. + * + * @param {DocumentFragment} tzSelectFragment: timezone selection UI + * @param {String} tzClassName: specifies element where UI was installed + * @returns {Function} event handler + */ +function closeTZFormHandler(tzSelectFragment, tzClassName) { + //return function closeTZForm(event) { + return function (event) { + event = event || window.event; + var target = event.target || event.srcElement; + + removeChangeTZForm(tzSelectFragment, target, tzClassName); + }; +} + +/* end of adjust-timezone.js */ +// Copyright (C) 2007, Fredrik Kuivinen +// 2007, Petr Baudis +// 2008-2011, Jakub Narebski + +/** + * @fileOverview JavaScript side of Ajax-y 'blame_incremental' view in gitweb + * @license GPLv2 or later + */ + +/* ============================================================ */ +/* + * This code uses DOM methods instead of (nonstandard) innerHTML + * to modify page. + * + * innerHTML is non-standard IE extension, though supported by most + * browsers; however Firefox up to version 1.5 didn't implement it in + * a strict mode (application/xml+xhtml mimetype). + * + * Also my simple benchmarks show that using elem.firstChild.data = + * 'content' is slightly faster than elem.innerHTML = 'content'. It + * is however more fragile (text element fragment must exists), and + * less feature-rich (we cannot add HTML). + * + * Note that DOM 2 HTML is preferred over generic DOM 2 Core; the + * equivalent using DOM 2 Core is usually shown in comments. + */ + + +/* ............................................................ */ +/* utility/helper functions (and variables) */ + +var projectUrl; // partial query + separator ('?' or ';') + +// 'commits' is an associative map. It maps SHA1s to Commit objects. +var commits = {}; + +/** + * constructor for Commit objects, used in 'blame' + * @class Represents a blamed commit + * @param {String} sha1: SHA-1 identifier of a commit + */ +function Commit(sha1) { + if (this instanceof Commit) { + this.sha1 = sha1; + this.nprevious = 0; /* number of 'previous', effective parents */ + } else { + return new Commit(sha1); + } +} + +/* ............................................................ */ +/* progress info, timing, error reporting */ + +var blamedLines = 0; +var totalLines = '???'; +var div_progress_bar; +var div_progress_info; + +/** + * Detects how many lines does a blamed file have, + * This information is used in progress info + * + * @returns {Number|String} Number of lines in file, or string '...' + */ +function countLines() { + var table = + document.getElementById('blame_table') || + document.getElementsByTagName('table')[0]; + + if (table) { + return table.getElementsByTagName('tr').length - 1; // for header + } else { + return '...'; + } +} + +/** + * update progress info and length (width) of progress bar + * + * @globals div_progress_info, div_progress_bar, blamedLines, totalLines + */ +function updateProgressInfo() { + if (!div_progress_info) { + div_progress_info = document.getElementById('progress_info'); + } + if (!div_progress_bar) { + div_progress_bar = document.getElementById('progress_bar'); + } + if (!div_progress_info && !div_progress_bar) { + return; + } + + var percentage = Math.floor(100.0*blamedLines/totalLines); + + if (div_progress_info) { + div_progress_info.firstChild.data = blamedLines + ' / ' + totalLines + + ' (' + padLeftStr(percentage, 3, '\u00A0') + '%)'; + } + + if (div_progress_bar) { + //div_progress_bar.setAttribute('style', 'width: '+percentage+'%;'); + div_progress_bar.style.width = percentage + '%'; + } +} + + +var t_interval_server = ''; +var cmds_server = ''; +var t0 = new Date(); + +/** + * write how much it took to generate data, and to run script + * + * @globals t0, t_interval_server, cmds_server + */ +function writeTimeInterval() { + var info_time = document.getElementById('generating_time'); + if (!info_time || !t_interval_server) { + return; + } + var t1 = new Date(); + info_time.firstChild.data += ' + (' + + t_interval_server + ' sec server blame_data / ' + + (t1.getTime() - t0.getTime())/1000 + ' sec client JavaScript)'; + + var info_cmds = document.getElementById('generating_cmd'); + if (!info_time || !cmds_server) { + return; + } + info_cmds.firstChild.data += ' + ' + cmds_server; +} + +/** + * show an error message alert to user within page (in progress info area) + * @param {String} str: plain text error message (no HTML) + * + * @globals div_progress_info + */ +function errorInfo(str) { + if (!div_progress_info) { + div_progress_info = document.getElementById('progress_info'); + } + if (div_progress_info) { + div_progress_info.className = 'error'; + div_progress_info.firstChild.data = str; + } +} + +/* ............................................................ */ +/* coloring rows during blame_data (git blame --incremental) run */ + +/** + * used to extract N from 'colorN', where N is a number, + * @constant + */ +var colorRe = /\bcolor([0-9]*)\b/; + +/** + * return N if , otherwise return null + * (some browsers require CSS class names to begin with letter) + * + * @param {HTMLElement} tr: table row element to check + * @param {String} tr.className: 'class' attribute of tr element + * @returns {Number|null} N if tr.className == 'colorN', otherwise null + * + * @globals colorRe + */ +function getColorNo(tr) { + if (!tr) { + return null; + } + var className = tr.className; + if (className) { + var match = colorRe.exec(className); + if (match) { + return parseInt(match[1], 10); + } + } + return null; +} + +var colorsFreq = [0, 0, 0]; +/** + * return one of given possible colors (currently least used one) + * example: chooseColorNoFrom(2, 3) returns 2 or 3 + * + * @param {Number[]} arguments: one or more numbers + * assumes that 1 <= arguments[i] <= colorsFreq.length + * @returns {Number} Least used color number from arguments + * @globals colorsFreq + */ +function chooseColorNoFrom() { + // choose the color which is least used + var colorNo = arguments[0]; + for (var i = 1; i < arguments.length; i++) { + if (colorsFreq[arguments[i]-1] < colorsFreq[colorNo-1]) { + colorNo = arguments[i]; + } + } + colorsFreq[colorNo-1]++; + return colorNo; +} + +/** + * given two neighbor elements, find color which would be different + * from color of both of neighbors; used to 3-color blame table + * + * @param {HTMLElement} tr_prev + * @param {HTMLElement} tr_next + * @returns {Number} color number N such that + * colorN != tr_prev.className && colorN != tr_next.className + */ +function findColorNo(tr_prev, tr_next) { + var color_prev = getColorNo(tr_prev); + var color_next = getColorNo(tr_next); + + + // neither of neighbors has color set + // THEN we can use any of 3 possible colors + if (!color_prev && !color_next) { + return chooseColorNoFrom(1,2,3); + } + + // either both neighbors have the same color, + // or only one of neighbors have color set + // THEN we can use any color except given + var color; + if (color_prev === color_next) { + color = color_prev; // = color_next; + } else if (!color_prev) { + color = color_next; + } else if (!color_next) { + color = color_prev; + } + if (color) { + return chooseColorNoFrom((color % 3) + 1, ((color+1) % 3) + 1); + } + + // neighbors have different colors + // THEN there is only one color left + return (3 - ((color_prev + color_next) % 3)); +} + +/* ............................................................ */ +/* coloring rows like 'blame' after 'blame_data' finishes */ + +/** + * returns true if given row element (tr) is first in commit group + * to be used only after 'blame_data' finishes (after processing) + * + * @param {HTMLElement} tr: table row + * @returns {Boolean} true if TR is first in commit group + */ +function isStartOfGroup(tr) { + return tr.firstChild.className === 'sha1'; +} + +/** + * change colors to use zebra coloring (2 colors) instead of 3 colors + * concatenate neighbor commit groups belonging to the same commit + * + * @globals colorRe + */ +function fixColorsAndGroups() { + var colorClasses = ['light', 'dark']; + var linenum = 1; + var tr, prev_group; + var colorClass = 0; + var table = + document.getElementById('blame_table') || + document.getElementsByTagName('table')[0]; + + while ((tr = document.getElementById('l'+linenum))) { + // index origin is 0, which is table header; start from 1 + //while ((tr = table.rows[linenum])) { // <- it is slower + if (isStartOfGroup(tr, linenum, document)) { + if (prev_group && + prev_group.firstChild.firstChild.href === + tr.firstChild.firstChild.href) { + // we have to concatenate groups + var prev_rows = prev_group.firstChild.rowSpan || 1; + var curr_rows = tr.firstChild.rowSpan || 1; + prev_group.firstChild.rowSpan = prev_rows + curr_rows; + //tr.removeChild(tr.firstChild); + tr.deleteCell(0); // DOM2 HTML way + } else { + colorClass = (colorClass + 1) % 2; + prev_group = tr; + } + } + var tr_class = tr.className; + tr.className = tr_class.replace(colorRe, colorClasses[colorClass]); + linenum++; + } +} + + +/* ============================================================ */ +/* main part: parsing response */ + +/** + * Function called for each blame entry, as soon as it finishes. + * It updates page via DOM manipulation, adding sha1 info, etc. + * + * @param {Commit} commit: blamed commit + * @param {Object} group: object representing group of lines, + * which blame the same commit (blame entry) + * + * @globals blamedLines + */ +function handleLine(commit, group) { + /* + This is the structure of the HTML fragment we are working + with: + + + + 123 + # times (my ext3 doesn't). + + */ + + var resline = group.resline; + + // format date and time string only once per commit + if (!commit.info) { + /* e.g. 'Kay Sievers, 2005-08-07 21:49:46 +0200' */ + commit.info = commit.author + ', ' + + formatDateISOLocal(commit.authorTime, commit.authorTimezone); + } + + // color depends on group of lines, not only on blamed commit + var colorNo = findColorNo( + document.getElementById('l'+(resline-1)), + document.getElementById('l'+(resline+group.numlines)) + ); + + // loop over lines in commit group + for (var i = 0; i < group.numlines; i++, resline++) { + var tr = document.getElementById('l'+resline); + if (!tr) { + break; + } + /* + + + 123 + # times (my ext3 doesn't). + + */ + var td_sha1 = tr.firstChild; + var a_sha1 = td_sha1.firstChild; + var a_linenr = td_sha1.nextSibling.firstChild; + + /* */ + var tr_class = ''; + if (colorNo !== null) { + tr_class = 'color'+colorNo; + } + if (commit.boundary) { + tr_class += ' boundary'; + } + if (commit.nprevious === 0) { + tr_class += ' no-previous'; + } else if (commit.nprevious > 1) { + tr_class += ' multiple-previous'; + } + tr.className = tr_class; + + /* ? */ + if (i === 0) { + td_sha1.title = commit.info; + td_sha1.rowSpan = group.numlines; + + a_sha1.href = projectUrl + 'a=commit;h=' + commit.sha1; + if (a_sha1.firstChild) { + a_sha1.firstChild.data = commit.sha1.substr(0, 8); + } else { + a_sha1.appendChild( + document.createTextNode(commit.sha1.substr(0, 8))); + } + if (group.numlines >= 2) { + var fragment = document.createDocumentFragment(); + var br = document.createElement("br"); + var match = commit.author.match(/\b([A-Z])\B/g); + if (match) { + var text = document.createTextNode( + match.join('')); + } + if (br && text) { + var elem = fragment || td_sha1; + elem.appendChild(br); + elem.appendChild(text); + if (fragment) { + td_sha1.appendChild(fragment); + } + } + } + } else { + //tr.removeChild(td_sha1); // DOM2 Core way + tr.deleteCell(0); // DOM2 HTML way + } + + /* 123 */ + var linenr_commit = + ('previous' in commit ? commit.previous : commit.sha1); + var linenr_filename = + ('file_parent' in commit ? commit.file_parent : commit.filename); + a_linenr.href = projectUrl + 'a=blame_incremental' + + ';hb=' + linenr_commit + + ';f=' + encodeURIComponent(linenr_filename) + + '#l' + (group.srcline + i); + + blamedLines++; + + //updateProgressInfo(); + } +} + +// ---------------------------------------------------------------------- + +/**#@+ + * @constant + */ +var sha1Re = /^([0-9a-f]{40}) ([0-9]+) ([0-9]+) ([0-9]+)/; +var infoRe = /^([a-z-]+) ?(.*)/; +var endRe = /^END ?([^ ]*) ?(.*)/; +/**@-*/ + +var curCommit = new Commit(); +var curGroup = {}; + +/** + * Parse output from 'git blame --incremental [...]', received via + * XMLHttpRequest from server (blamedataUrl), and call handleLine + * (which updates page) as soon as blame entry is completed. + * + * @param {String[]} lines: new complete lines from blamedata server + * + * @globals commits, curCommit, curGroup, t_interval_server, cmds_server + * @globals sha1Re, infoRe, endRe + */ +function processBlameLines(lines) { + var match; + + for (var i = 0, len = lines.length; i < len; i++) { + + if ((match = sha1Re.exec(lines[i]))) { + var sha1 = match[1]; + var srcline = parseInt(match[2], 10); + var resline = parseInt(match[3], 10); + var numlines = parseInt(match[4], 10); + + var c = commits[sha1]; + if (!c) { + c = new Commit(sha1); + commits[sha1] = c; + } + curCommit = c; + + curGroup.srcline = srcline; + curGroup.resline = resline; + curGroup.numlines = numlines; + + } else if ((match = infoRe.exec(lines[i]))) { + var info = match[1]; + var data = match[2]; + switch (info) { + case 'filename': + curCommit.filename = unquote(data); + // 'filename' information terminates the entry + handleLine(curCommit, curGroup); + updateProgressInfo(); + break; + case 'author': + curCommit.author = data; + break; + case 'author-time': + curCommit.authorTime = parseInt(data, 10); + break; + case 'author-tz': + curCommit.authorTimezone = data; + break; + case 'previous': + curCommit.nprevious++; + // store only first 'previous' header + if (!'previous' in curCommit) { + var parts = data.split(' ', 2); + curCommit.previous = parts[0]; + curCommit.file_parent = unquote(parts[1]); + } + break; + case 'boundary': + curCommit.boundary = true; + break; + } // end switch + + } else if ((match = endRe.exec(lines[i]))) { + t_interval_server = match[1]; + cmds_server = match[2]; + + } else if (lines[i] !== '') { + // malformed line + + } // end if (match) + + } // end for (lines) +} + +/** + * Process new data and return pointer to end of processed part + * + * @param {String} unprocessed: new data (from nextReadPos) + * @param {Number} nextReadPos: end of last processed data + * @return {Number} end of processed data (new value for nextReadPos) + */ +function processData(unprocessed, nextReadPos) { + var lastLineEnd = unprocessed.lastIndexOf('\n'); + if (lastLineEnd !== -1) { + var lines = unprocessed.substring(0, lastLineEnd).split('\n'); + nextReadPos += lastLineEnd + 1 /* 1 == '\n'.length */; + + processBlameLines(lines); + } // end if + + return nextReadPos; +} + +/** + * Handle XMLHttpRequest errors + * + * @param {XMLHttpRequest} xhr: XMLHttpRequest object + * @param {Number} [xhr.pollTimer] ID of the timeout to clear + * + * @globals commits + */ +function handleError(xhr) { + errorInfo('Server error: ' + + xhr.status + ' - ' + (xhr.statusText || 'Error contacting server')); + + if (typeof xhr.pollTimer === "number") { + clearTimeout(xhr.pollTimer); + delete xhr.pollTimer; + } + commits = {}; // free memory +} + +/** + * Called after XMLHttpRequest finishes (loads) + * + * @param {XMLHttpRequest} xhr: XMLHttpRequest object + * @param {Number} [xhr.pollTimer] ID of the timeout to clear + * + * @globals commits + */ +function responseLoaded(xhr) { + if (typeof xhr.pollTimer === "number") { + clearTimeout(xhr.pollTimer); + delete xhr.pollTimer; + } + + fixColorsAndGroups(); + writeTimeInterval(); + commits = {}; // free memory +} + +/** + * handler for XMLHttpRequest onreadystatechange event + * @see startBlame + * + * @param {XMLHttpRequest} xhr: XMLHttpRequest object + * @param {Number} xhr.prevDataLength: previous value of xhr.responseText.length + * @param {Number} xhr.nextReadPos: start of unread part of xhr.responseText + * @param {Number} [xhr.pollTimer] ID of the timeout (to reset or cancel) + * @param {Boolean} fromTimer: if handler was called from timer + */ +function handleResponse(xhr, fromTimer) { + + /* + * xhr.readyState + * + * Value Constant (W3C) Description + * ------------------------------------------------------------------- + * 0 UNSENT open() has not been called yet. + * 1 OPENED send() has not been called yet. + * 2 HEADERS_RECEIVED send() has been called, and headers + * and status are available. + * 3 LOADING Downloading; responseText holds partial data. + * 4 DONE The operation is complete. + */ + + if (xhr.readyState !== 4 && xhr.readyState !== 3) { + return; + } + + // the server returned error + // try ... catch block is to work around bug in IE8 + try { + if (xhr.readyState === 3 && xhr.status !== 200) { + return; + } + } catch (e) { + return; + } + if (xhr.readyState === 4 && xhr.status !== 200) { + handleError(xhr); + return; + } + + // In konqueror xhr.responseText is sometimes null here... + if (xhr.responseText === null) { + return; + } + + + // extract new whole (complete) lines, and process them + if (xhr.prevDataLength !== xhr.responseText.length) { + xhr.prevDataLength = xhr.responseText.length; + var unprocessed = xhr.responseText.substring(xhr.nextReadPos); + xhr.nextReadPos = processData(unprocessed, xhr.nextReadPos); + } + + // did we finish work? + if (xhr.readyState === 4) { + responseLoaded(xhr); + return; + } + + // if we get from timer, we have to restart it + // otherwise onreadystatechange gives us partial response, timer not needed + if (fromTimer) { + setTimeout(function () { + handleResponse(xhr, true); + }, 1000); + + } else if (typeof xhr.pollTimer === "number") { + clearTimeout(xhr.pollTimer); + delete xhr.pollTimer; + } +} + +// ============================================================ +// ------------------------------------------------------------ + +/** + * Incrementally update line data in blame_incremental view in gitweb. + * + * @param {String} blamedataUrl: URL to server script generating blame data. + * @param {String} bUrl: partial URL to project, used to generate links. + * + * Called from 'blame_incremental' view after loading table with + * file contents, a base for blame view. + * + * @globals t0, projectUrl, div_progress_bar, totalLines +*/ +function startBlame(blamedataUrl, bUrl) { + + var xhr = createRequestObject(); + if (!xhr) { + errorInfo('ERROR: XMLHttpRequest not supported'); + return; + } + + t0 = new Date(); + projectUrl = bUrl + (bUrl.indexOf('?') === -1 ? '?' : ';'); + if ((div_progress_bar = document.getElementById('progress_bar'))) { + //div_progress_bar.setAttribute('style', 'width: 100%;'); + div_progress_bar.style.cssText = 'width: 100%;'; + } + totalLines = countLines(); + updateProgressInfo(); + + /* add extra properties to xhr object to help processing response */ + xhr.prevDataLength = -1; // used to detect if we have new data + xhr.nextReadPos = 0; // where unread part of response starts + + xhr.onreadystatechange = function () { + handleResponse(xhr, false); + }; + + xhr.open('GET', blamedataUrl); + xhr.setRequestHeader('Accept', 'text/plain'); + xhr.send(null); + + // not all browsers call onreadystatechange event on each server flush + // poll response using timer every second to handle this issue + xhr.pollTimer = setTimeout(function () { + handleResponse(xhr, true); + }, 1000); +} + +/* end of blame_incremental.js */ diff --git a/gitweb/index.aux b/gitweb/index.aux index 6dd2e2b..dcd6a7e 100644 --- a/gitweb/index.aux +++ b/gitweb/index.aux @@ -9,7 +9,7 @@ ports%2Fcore.git CRUX+System+Team ports%2Fopt.git CRUX+Ports+Team #ports%2Fopt-x86_64.git CRUX+Ports+Team ports%2Fxfce.git Jose+V+Beneyto -ports%2Fe17.git Victor+Martinez +ports%2Fenlightenment.git Victor+Martinez ports%2Fxorg.git CRUX+Xorg+Team #ports%2Fxorg-x86_64.git Tilman+Sauerbeck system%2Fiso.git CRUX+System+Team