X-Git-Url: https://git.ladys.computer/Gitweb/blobdiff_plain/c42d564e03ca059403526e93a50db155ece3ffd72ec9d8b42cca3542cc0a4410..4a7fb0bc24b3a9ff745a1faae8d8df828563cf61e603d9cffbfdbb5641844581:/gitweb.perl diff --git a/gitweb.perl b/gitweb.perl index 108c3cc..03900fa 100755 --- a/gitweb.perl +++ b/gitweb.perl @@ -18,11 +18,46 @@ use File::Find qw(); use File::Basename qw(basename); binmode STDOUT, ':utf8'; +our $t0; +if (eval { require Time::HiRes; 1; }) { + $t0 = [Time::HiRes::gettimeofday()]; +} +our $number_of_git_cmds = 0; + +BEGIN { + CGI->compile() if $ENV{'MOD_PERL'}; +} + our $cgi = new CGI; our $version = "++GIT_VERSION++"; our $my_url = $cgi->url(); our $my_uri = $cgi->url(-absolute => 1); +# Base URL for relative URLs in gitweb ($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 = $ENV{"PATH_INFO"}; +if ($path_info) { + if ($my_url =~ s,\Q$path_info\E$,, && + $my_uri =~ s,\Q$path_info\E$,, && + defined $ENV{'SCRIPT_NAME'}) { + $base_url = $cgi->url(-base => 1) . $ENV{'SCRIPT_NAME'}; + } +} + # core git executable to use # this can just be "git" if your webserver has a sensible PATH our $GIT = "++GIT_BINDIR++/git"; @@ -31,6 +66,10 @@ our $GIT = "++GIT_BINDIR++/git"; #our $projectroot = "/pub/scm"; our $projectroot = "++GITWEB_PROJECTROOT++"; +# fs traversing limit for getting project list +# the number is relative to the projectroot +our $project_maxdepth = "++GITWEB_PROJECT_MAXDEPTH++"; + # target of the home link on top of all pages our $home_link = $my_uri || "/"; @@ -58,20 +97,34 @@ our $stylesheet = undef; our $logo = "++GITWEB_LOGO++"; # URI of GIT favicon, assumed to be image/png type our $favicon = "++GITWEB_FAVICON++"; +# URI of gitweb.js (JavaScript code for gitweb) +our $javascript = "++GITWEB_JS++"; # URI and label (title) of GIT logo link #our $logo_url = "http://www.kernel.org/pub/software/scm/git/docs/"; #our $logo_label = "git documentation"; -our $logo_url = "http://git.or.cz/"; +our $logo_url = "http://git-scm.com/"; our $logo_label = "git homepage"; # source of projects list our $projects_list = "++GITWEB_LIST++"; +# the width (in characters) of the projects list "Description" column +our $projects_list_description_width = 25; + +# default order of projects list +# valid values are none, project, descr, owner, and age +our $default_projects_order = "project"; + # show repository only if this file exists # (only effective if this variable evaluates to true) our $export_ok = "++GITWEB_EXPORT_OK++"; +# show repository only if this subroutine returns true +# when given the path to the project, for example: +# sub { return -e "$_[0]/git-daemon-export-ok"; } +our $export_auth_hook = undef; + # only allow viewing of repositories also shown on the overview page our $strict_export = "++GITWEB_STRICT_EXPORT++"; @@ -87,6 +140,88 @@ our $default_text_plain_charset = undef; # (relative to the current git repository) our $mimetypes_file = 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'; + +# 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; + +# 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']}, + + '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, +); + +# 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 +); + # You define site-wide feature defaults here; override them with # $GITWEB_CONFIG as necessary. our %feature = ( @@ -95,11 +230,16 @@ our %feature = ( # 'override' => allow-override (boolean), # 'default' => [ default options...] (array reference)} # - # if feature is overridable (it means that allow-override has true value, + # if feature is overridable (it means that allow-override has true value), # then feature-sub will be called with default options as parameters; # return value of feature-sub indicates if to enable specified feature # - # use gitweb_check_feature() to check if is enabled + # if there is no 'sub' key (no feature-sub), then feature cannot be + # overriden + # + # use gitweb_get_feature() to retrieve the value + # (an array) or gitweb_check_feature() to check if + # is enabled # Enable the 'blame' blob view, showing the last commit that modified # each line in the file. This can be very CPU-intensive. @@ -110,31 +250,48 @@ our %feature = ( # $feature{'blame'}{'override'} = 1; # and in project config gitweb.blame = 0|1; 'blame' => { - 'sub' => \&feature_blame, + 'sub' => sub { feature_bool('blame', @_) }, 'override' => 0, 'default' => [0]}, - # Enable the 'snapshot' link, providing a compressed tarball of any + # Enable the 'snapshot' link, providing a compressed archive of any # tree. This can potentially generate high traffic if you have large # project. + # Value is a list of formats defined in %known_snapshot_formats that + # you wish to offer. # To disable system wide have in $GITWEB_CONFIG - # $feature{'snapshot'}{'default'} = [undef]; + # $feature{'snapshot'}{'default'} = []; # To have project specific config enable override in $GITWEB_CONFIG # $feature{'snapshot'}{'override'} = 1; - # and in project config gitweb.snapshot = none|gzip|bzip2; + # and in project config, a comma-separated list of formats or "none" + # to disable. Example: gitweb.snapshot = tbz2,zip; 'snapshot' => { 'sub' => \&feature_snapshot, 'override' => 0, - # => [content-encoding, suffix, program] - 'default' => ['x-gzip', 'gz', 'gzip']}, + 'default' => ['tgz']}, # Enable text search, which will list the commits which match author, # committer or commit text to a given string. Enabled by default. + # Project specific override is not supported. 'search' => { 'override' => 0, 'default' => [1]}, + # Enable grep search, which will list the files in currently selected + # tree containing the given string. Enabled by default. This can be + # potentially CPU-intensive, of course. + + # To enable system wide have in $GITWEB_CONFIG + # $feature{'grep'}{'default'} = [1]; + # To have project specific config enable override in $GITWEB_CONFIG + # $feature{'grep'}{'override'} = 1; + # and in project config gitweb.grep = 0|1; + 'grep' => { + 'sub' => sub { feature_bool('grep', @_) }, + 'override' => 0, + 'default' => [1]}, + # Enable the pickaxe search, which will list the commits that modified # a given string in a file. This can be practical and quite faster # alternative to 'blame', but still potentially CPU-intensive. @@ -145,7 +302,20 @@ our %feature = ( # $feature{'pickaxe'}{'override'} = 1; # and in project config gitweb.pickaxe = 0|1; 'pickaxe' => { - 'sub' => \&feature_pickaxe, + 'sub' => sub { feature_bool('pickaxe', @_) }, + 'override' => 0, + 'default' => [1]}, + + # Enable showing size of blobs in a 'tree' view, in a separate + # column, similar to what 'ls -l' does. This cost a bit of IO. + + # To disable system wide have in $GITWEB_CONFIG + # $feature{'show-sizes'}{'default'} = [0]; + # To have project specific config enable override in $GITWEB_CONFIG + # $feature{'show-sizes'}{'override'} = 1; + # and in project config gitweb.showsizes = 0|1; + 'show-sizes' => { + 'sub' => sub { feature_bool('showsizes', @_) }, 'override' => 0, 'default' => [1]}, @@ -173,8 +343,8 @@ our %feature = ( # projects matching $projname/*.git will not be shown in the main # projects list, instead a '+' mark will be added to $projname # there and a 'forks' view will be enabled for the project, listing - # all the forks. This feature is supported only if project list - # is taken from a directory, not file. + # all the forks. If project list is taken from a file, forks have + # to be listed after the main project. # To enable system wide have in $GITWEB_CONFIG # $feature{'forks'}{'default'} = [1]; @@ -182,9 +352,90 @@ our %feature = ( 'forks' => { 'override' => 0, 'default' => [0]}, + + # Insert custom links to the action bar of all project pages. + # This enables you mainly to link to third-party scripts integrating + # into gitweb; e.g. git-browser for graphical history representation + # or custom web-based repository administration interface. + + # The 'default' value consists of a list of triplets in the form + # (label, link, position) where position is the label after which + # to insert the link and link is a format string where %n expands + # to the project name, %f to the project path within the filesystem, + # %h to the current hash (h gitweb parameter) and %b to the current + # hash base (hb gitweb parameter); %% expands to %. + + # To enable system wide have in $GITWEB_CONFIG e.g. + # $feature{'actions'}{'default'} = [('graphiclog', + # '/git-browser/by-commit.html?r=%n', 'summary')]; + # Project specific override is not supported. + 'actions' => { + 'override' => 0, + 'default' => []}, + + # Allow gitweb scan project content tags described in ctags/ + # of project repository, and display the popular Web 2.0-ish + # "tag cloud" near the project list. Note that this is something + # COMPLETELY different from the normal Git tags. + + # gitweb by itself can show existing tags, but it does not handle + # tagging itself; you need an external application for that. + # For an example script, check Girocco's cgi/tagproj.cgi. + # You may want to install the HTML::TagCloud Perl module to get + # a pretty tag cloud instead of just a list of tags. + + # To enable system wide have in $GITWEB_CONFIG + # $feature{'ctags'}{'default'} = ['path_to_tag_script']; + # Project specific override is not supported. + 'ctags' => { + 'override' => 0, + 'default' => [0]}, + + # The maximum number of patches in a patchset generated in patch + # view. Set this to 0 or undef to disable patch view, or to a + # negative number to remove any limit. + + # To disable system wide have in $GITWEB_CONFIG + # $feature{'patches'}{'default'} = [0]; + # To have project specific config enable override in $GITWEB_CONFIG + # $feature{'patches'}{'override'} = 1; + # and in project config gitweb.patches = 0|n; + # where n is the maximum number of patches allowed in a patchset. + 'patches' => { + 'sub' => \&feature_patches, + 'override' => 0, + 'default' => [16]}, + + # Avatar support. When this feature is enabled, views such as + # shortlog or commit will display an avatar associated with + # the email of the committer(s) and/or author(s). + + # Currently available providers are gravatar and picon. + # If an unknown provider is specified, the feature is disabled. + + # Gravatar depends on Digest::MD5. + # Picon currently relies on the indiana.edu database. + + # To enable system wide have in $GITWEB_CONFIG + # $feature{'avatar'}{'default'} = ['']; + # where is either gravatar or picon. + # To have project specific config enable override in $GITWEB_CONFIG + # $feature{'avatar'}{'override'} = 1; + # and in project config gitweb.avatar = ; + 'avatar' => { + 'sub' => \&feature_avatar, + 'override' => 0, + 'default' => ['']}, + + # Enable displaying how much time and how many git commands + # it took to generate and display page. Disabled by default. + # Project specific override is not supported. + 'timed' => { + 'override' => 0, + 'default' => [0]}, ); -sub gitweb_check_feature { +sub gitweb_get_feature { my ($name) = @_; return unless exists $feature{$name}; my ($sub, $override, @defaults) = ( @@ -193,59 +444,69 @@ sub gitweb_check_feature { @{$feature{$name}{'default'}}); if (!$override) { return @defaults; } if (!defined $sub) { - warn "feature $name is not overrideable"; + warn "feature $name is not overridable"; return @defaults; } return $sub->(@defaults); } -sub feature_blame { - my ($val) = git_get_project_config('blame', '--bool'); +# A wrapper to check if a given feature is enabled. +# With this, you can say +# +# my $bool_feat = gitweb_check_feature('bool_feat'); +# gitweb_check_feature('bool_feat') or somecode; +# +# instead of +# +# my ($bool_feat) = gitweb_get_feature('bool_feat'); +# (gitweb_get_feature('bool_feat'))[0] or somecode; +# +sub gitweb_check_feature { + return (gitweb_get_feature(@_))[0]; +} + + +sub feature_bool { + my $key = shift; + my ($val) = git_get_project_config($key, '--bool'); - if ($val eq 'true') { - return 1; + if (!defined $val) { + return ($_[0]); + } elsif ($val eq 'true') { + return (1); } elsif ($val eq 'false') { - return 0; + return (0); } - - return $_[0]; } sub feature_snapshot { - my ($ctype, $suffix, $command) = @_; + my (@fmts) = @_; my ($val) = git_get_project_config('snapshot'); - if ($val eq 'gzip') { - return ('x-gzip', 'gz', 'gzip'); - } elsif ($val eq 'bzip2') { - return ('x-bzip2', 'bz2', 'bzip2'); - } elsif ($val eq 'none') { - return (); + if ($val) { + @fmts = ($val eq 'none' ? () : split /\s*[,\s]\s*/, $val); } - return ($ctype, $suffix, $command); -} - -sub gitweb_have_snapshot { - my ($ctype, $suffix, $command) = gitweb_check_feature('snapshot'); - my $have_snapshot = (defined $ctype && defined $suffix); - - return $have_snapshot; + return @fmts; } -sub feature_pickaxe { - my ($val) = git_get_project_config('pickaxe', '--bool'); +sub feature_patches { + my @val = (git_get_project_config('patches', '--int')); - if ($val eq 'true') { - return (1); - } elsif ($val eq 'false') { - return (0); + if (@val) { + return @val; } return ($_[0]); } +sub feature_avatar { + my @val = (git_get_project_config('avatar')); + + return @val ? @val : @_; +} + # checking HEAD file with -e is fragile if the repository was # initialized long time ago (i.e. symlink HEAD) and was pack-ref'ed # and then pruned. @@ -259,209 +520,411 @@ sub check_head_link { sub check_export_ok { my ($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 = @_; + + @fmts = map { + exists $known_snapshot_format_aliases{$_} ? + $known_snapshot_format_aliases{$_} : $_} @fmts; + @fmts = grep { + exists $known_snapshot_formats{$_} && + !$known_snapshot_formats{$_}{'disabled'}} @fmts; +} our $GITWEB_CONFIG = $ENV{'GITWEB_CONFIG'} || "++GITWEB_CONFIG++"; -do $GITWEB_CONFIG if -e $GITWEB_CONFIG; +if (-e $GITWEB_CONFIG) { + do $GITWEB_CONFIG; +} else { + our $GITWEB_CONFIG_SYSTEM = $ENV{'GITWEB_CONFIG_SYSTEM'} || "++GITWEB_CONFIG_SYSTEM++"; + do $GITWEB_CONFIG_SYSTEM if -e $GITWEB_CONFIG_SYSTEM; +} # version of the core git binary -our $git_version = qx($GIT --version) =~ m/git version (.*)$/ ? $1 : "unknown"; +our $git_version = qx("$GIT" --version) =~ m/git version (.*)$/ ? $1 : "unknown"; +$number_of_git_cmds++; $projects_list ||= $projectroot; # ====================================================================== # input validation and dispatch -our $action = $cgi->param('a'); + +# 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 %input_params = (); + +# input parameters are stored with the long parameter name as key. This will +# also be used in the href subroutine to convert parameters to their CGI +# equivalent, and since the href() usage is the most frequent one, we store +# the name -> CGI key mapping here, instead of the reverse. +# +# XXX: Warning: If you touch this, check the search form for updating, +# too. + +our @cgi_param_mapping = ( + project => "p", + action => "a", + file_name => "f", + file_parent => "fp", + hash => "h", + hash_parent => "hp", + hash_base => "hb", + hash_parent_base => "hpb", + page => "pg", + order => "o", + searchtext => "s", + searchtype => "st", + snapshot_format => "sf", + extra_options => "opt", + search_use_regexp => "sr", + # this must be last entry (for manipulation from JavaScript) + javascript => "js" +); +our %cgi_param_mapping = @cgi_param_mapping; + +# 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, + "blob_plain" => \&git_blob_plain, + "commitdiff" => \&git_commitdiff, + "commitdiff_plain" => \&git_commitdiff_plain, + "commit" => \&git_commit, + "forks" => \&git_forks, + "heads" => \&git_heads, + "history" => \&git_history, + "log" => \&git_log, + "patch" => \&git_patch, + "patches" => \&git_patches, + "rss" => \&git_rss, + "atom" => \&git_atom, + "search" => \&git_search, + "search_help" => \&git_search_help, + "shortlog" => \&git_shortlog, + "summary" => \&git_summary, + "tag" => \&git_tag, + "tags" => \&git_tags, + "tree" => \&git_tree, + "snapshot" => \&git_snapshot, + "object" => \&git_object, + # those below don't need $project + "opml" => \&git_opml, + "project_list" => \&git_project_list, + "project_index" => \&git_project_index, +); + +# finally, we have the hash of allowed extra_options for the commands that +# allow them +our %allowed_options = ( + "--no-merges" => [ qw(rss atom log shortlog history) ], +); + +# fill %input_params with the CGI parameters. All values except for 'opt' +# should be single values, but opt can be an array. We should probably +# build an array of parameters that can be multi-valued, but since for the time +# being it's only this one, we just single it out +while (my ($name, $symbol) = each %cgi_param_mapping) { + if ($symbol eq 'opt') { + $input_params{$name} = [ $cgi->param($symbol) ]; + } else { + $input_params{$name} = $cgi->param($symbol); + } +} + +# 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'} = $action; + } + + # list of actions that want hash_base instead of hash, but can have no + # pathname (f) parameter + my @wants_base = ( + 'tree', + 'history', + ); + + # we want to catch + # [$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. + $input_params{'action'} ||= "shortlog"; + if (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; + } + } +} +evaluate_path_info(); + +our $action = $input_params{'action'}; if (defined $action) { - if ($action =~ m/[^0-9a-zA-Z\.\-_]/) { - die_error(undef, "Invalid action parameter"); + if (!validate_action($action)) { + die_error(400, "Invalid action parameter"); } } # parameters which are pathnames -our $project = $cgi->param('p'); +our $project = $input_params{'project'}; 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))) { + if (!validate_project($project)) { undef $project; - die_error(undef, "No such project"); + die_error(404, "No such project"); } } -our $file_name = $cgi->param('f'); +our $file_name = $input_params{'file_name'}; if (defined $file_name) { if (!validate_pathname($file_name)) { - die_error(undef, "Invalid file parameter"); + die_error(400, "Invalid file parameter"); } } -our $file_parent = $cgi->param('fp'); +our $file_parent = $input_params{'file_parent'}; if (defined $file_parent) { if (!validate_pathname($file_parent)) { - die_error(undef, "Invalid file parent parameter"); + die_error(400, "Invalid file parent parameter"); } } # parameters which are refnames -our $hash = $cgi->param('h'); +our $hash = $input_params{'hash'}; if (defined $hash) { if (!validate_refname($hash)) { - die_error(undef, "Invalid hash parameter"); + die_error(400, "Invalid hash parameter"); } } -our $hash_parent = $cgi->param('hp'); +our $hash_parent = $input_params{'hash_parent'}; if (defined $hash_parent) { if (!validate_refname($hash_parent)) { - die_error(undef, "Invalid hash parent parameter"); + die_error(400, "Invalid hash parent parameter"); } } -our $hash_base = $cgi->param('hb'); +our $hash_base = $input_params{'hash_base'}; if (defined $hash_base) { if (!validate_refname($hash_base)) { - die_error(undef, "Invalid hash base parameter"); + 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 = $cgi->param('hpb'); +our $hash_parent_base = $input_params{'hash_parent_base'}; if (defined $hash_parent_base) { if (!validate_refname($hash_parent_base)) { - die_error(undef, "Invalid hash parent base parameter"); + die_error(400, "Invalid hash parent base parameter"); } } # other parameters -our $page = $cgi->param('pg'); +our $page = $input_params{'page'}; 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"); - } - if (length($searchtext) < 2) { - die_error(undef, "At least two characters are required for search parameter"); + die_error(400, "Invalid page parameter"); } - $searchtext = quotemeta $searchtext; } -our $searchtype = $cgi->param('st'); +our $searchtype = $input_params{'searchtype'}; if (defined $searchtype) { if ($searchtype =~ m/[^a-z]/) { - die_error(undef, "Invalid searchtype parameter"); + die_error(400, "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); +our $search_use_regexp = $input_params{'search_use_regexp'}; + +our $searchtext = $input_params{'searchtext'}; +our $search_regexp; +if (defined $searchtext) { + if (length($searchtext) < 2) { + die_error(403, "At least two characters are required for search parameter"); } + $search_regexp = $search_use_regexp ? $searchtext : quotemeta $searchtext; } -evaluate_path_info(); # path to the current git repository our $git_dir; $git_dir = "$projectroot/$project" if $project; -# dispatch -my %actions = ( - "blame" => \&git_blame2, - "blobdiff" => \&git_blobdiff, - "blobdiff_plain" => \&git_blobdiff_plain, - "blob" => \&git_blob, - "blob_plain" => \&git_blob_plain, - "commitdiff" => \&git_commitdiff, - "commitdiff_plain" => \&git_commitdiff_plain, - "commit" => \&git_commit, - "forks" => \&git_forks, - "heads" => \&git_heads, - "history" => \&git_history, - "log" => \&git_log, - "rss" => \&git_rss, - "atom" => \&git_atom, - "search" => \&git_search, - "search_help" => \&git_search_help, - "shortlog" => \&git_shortlog, - "summary" => \&git_summary, - "tag" => \&git_tag, - "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'; +# list of supported snapshot formats +our @snapshot_fmts = gitweb_get_feature('snapshot'); +@snapshot_fmts = filter_snapshot_fmts(@snapshot_fmts); + +# check that the avatar feature is set to a known provider name, +# and for each provider check if the dependencies are satisfied. +# if the provider name is invalid or the dependencies are not met, +# reset $git_avatar to the empty string. +our ($git_avatar) = gitweb_get_feature('avatar'); +if ($git_avatar eq 'gravatar') { + $git_avatar = '' unless (eval { require Digest::MD5; 1; }); +} elsif ($git_avatar eq 'picon') { + # no dependencies } else { - $action ||= 'project_list'; + $git_avatar = ''; +} + +# dispatch +if (!defined $action) { + if (defined $hash) { + $action = git_get_type($hash); + } elsif (defined $hash_base && defined $file_name) { + $action = git_get_type("$hash_base:$file_name"); + } elsif (defined $project) { + $action = 'summary'; + } else { + $action = 'project_list'; + } } if (!defined($actions{$action})) { - die_error(undef, "Unknown action"); + die_error(400, "Unknown action"); } -if ($action !~ m/^(opml|project_list|project_index)$/ && +if ($action !~ m/^(?:opml|project_list|project_index)$/ && !$project) { - die_error(undef, "Project needed"); + die_error(400, "Project needed"); } $actions{$action}->(); exit; @@ -469,50 +932,112 @@ exit; ## ====================================================================== ## action links -sub href(%) { +sub href { my %params = @_; # default is to use -absolute url() i.e. $my_uri my $href = $params{-full} ? $my_url : $my_uri; - # XXX: Warning: If you touch this, check the search form for updating, - # too. - - my @mapping = ( - project => "p", - action => "a", - file_name => "f", - file_parent => "fp", - hash => "h", - hash_parent => "hp", - hash_base => "hb", - hash_parent_base => "hpb", - page => "pg", - order => "o", - searchtext => "s", - searchtype => "st", - ); - my %mapping = @mapping; - $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 $use_pathinfo = gitweb_check_feature('pathinfo'); + if ($use_pathinfo and defined $params{'project'}) { + # 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 + $href .= "/".esc_url($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'}) { + $href .= "/".esc_url($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'}) { + $href .= esc_url($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'} !~ /\.\./) { + $href .= ":/".esc_url($params{'file_parent'}); + delete $params{'file_parent'}; + } + } + $href .= ".."; + delete $params{'hash_parent'}; + delete $params{'hash_parent_base'}; + } elsif (defined $params{'hash_parent'}) { + $href .= esc_url($params{'hash_parent'}). ".."; + delete $params{'hash_parent'}; + } + + $href .= esc_url($params{'hash_base'}); + if (defined $params{'file_name'} && $params{'file_name'} !~ /\.\./) { + $href .= ":/".esc_url($params{'file_name'}); + delete $params{'file_name'}; + } + delete $params{'hash'}; + delete $params{'hash_base'}; + } elsif (defined $params{'hash'}) { + $href .= esc_url($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; @@ -524,6 +1049,24 @@ sub href(%) { ## ====================================================================== ## validation, quoting/unquoting and escaping +sub validate_action { + my $input = shift || return undef; + return undef unless exists $actions{$input}; + return $input; +} + +sub validate_project { + my $input = shift || return undef; + if (!validate_pathname($input) || + !(-d "$projectroot/$input") || + !check_export_ok("$projectroot/$input") || + ($strict_export && !project_in_list($input))) { + return undef; + } else { + return $input; + } +} + sub validate_pathname { my $input = shift || return undef; @@ -557,10 +1100,17 @@ sub validate_refname { return $input; } -# very thin wrapper for decode("utf8", $str, Encode::FB_DEFAULT); +# 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", $str, Encode::FB_DEFAULT); + if (utf8::valid($str)) { + utf8::decode($str); + return $str; + } else { + return decode($fallback_encoding, $str, Encode::FB_DEFAULT); + } } # quote unsafe chars, but keep the slash, even when it's not @@ -583,12 +1133,12 @@ sub esc_url { } # replace invalid utf8 character with SUBSTITUTION sequence -sub esc_html ($;%) { +sub esc_html { my $str = shift; my %opts = @_; $str = to_utf8($str); - $str = escapeHTML($str); + $str = $cgi->escapeHTML($str); if ($opts{'-nbsp'}) { $str =~ s/ / /g; } @@ -602,7 +1152,7 @@ sub esc_path { my %opts = @_; $str = to_utf8($str); - $str = escapeHTML($str); + $str = $cgi->escapeHTML($str); if ($opts{'-nbsp'}) { $str =~ s/ / /g; } @@ -613,29 +1163,40 @@ sub esc_path { # Make control characters "printable", using character escape codes (CEC) sub quot_cec { my $cntrl = shift; + my %opts = @_; my %es = ( # character escape codes, aka escape sequences - "\t" => '\t', # tab (HT) - "\n" => '\n', # line feed (LF) - "\r" => '\r', # carrige return (CR) - "\f" => '\f', # form feed (FF) - "\b" => '\b', # backspace (BS) - "\a" => '\a', # alarm (bell) (BEL) - "\e" => '\e', # escape (ESC) - "\013" => '\v', # vertical tab (VT) - "\000" => '\0', # nul character (NUL) - ); + "\t" => '\t', # tab (HT) + "\n" => '\n', # line feed (LF) + "\r" => '\r', # carrige return (CR) + "\f" => '\f', # form feed (FF) + "\b" => '\b', # backspace (BS) + "\a" => '\a', # alarm (bell) (BEL) + "\e" => '\e', # escape (ESC) + "\013" => '\v', # vertical tab (VT) + "\000" => '\0', # nul character (NUL) + ); my $chr = ( (exists $es{$cntrl}) ? $es{$cntrl} - : sprintf('\%03o', ord($cntrl)) ); - return "$chr"; + : 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)); - return "$chr"; + if ($opts{-nohtml}) { + return $chr; + } else { + return "$chr"; + } } # git may return quoted and escaped filenames @@ -660,7 +1221,7 @@ 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; @@ -697,21 +1258,83 @@ sub project_in_list { ## ---------------------------------------------------------------------- ## HTML aware string manipulation +# Try to chop given string on a word boundary between position +# $len and $len+$add_len. If there is no word boundary there, +# chop at $len+$add_len. Do not chop if chopped part plus ellipsis +# (marking chopped part) would be longer than given string. sub chop_str { my $str = shift; my $len = shift; my $add_len = shift || 10; + my $where = shift || 'right'; # 'left' | 'center' | 'right' + + # Make sure perl knows it is utf8 encoded so we don't + # cut in the middle of a utf8 multibyte char. + $str = to_utf8($str); # allow only $len chars, but don't cut a word if it would fit in $add_len # if it doesn't fit, cut it if it's still longer than the dots we would add - $str =~ m/^(.{0,$len}[^ \/\-_:\.@]{0,$add_len})(.*)/; - my $body = $1; - my $tail = $2; - if (length($tail) > 4) { - $tail = " ..."; - $body =~ s/&[^;]*$//; # remove chopped character entities + # remove chopped character entities entirely + + # when chopping in the middle, distribute $len into left and right part + # return early if chopping wouldn't make string shorter + if ($where eq 'center') { + return $str if ($len + 5 >= length($str)); # filler is length 5 + $len = int($len/2); + } else { + return $str if ($len + 4 >= length($str)); # filler is length 4 + } + + # regexps: ending and beginning with word part up to $add_len + my $endre = qr/.{$len}\w{0,$add_len}/; + my $begre = qr/\w{0,$add_len}.{$len}/; + + if ($where eq 'left') { + $str =~ m/^(.*?)($begre)$/; + my ($lead, $body) = ($1, $2); + if (length($lead) > 4) { + $body =~ s/^[^;]*;// if ($lead =~ m/&[^;]*$/); + $lead = " ..."; + } + return "$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) { + $left =~ s/&[^;]*$//; + $right =~ s/^[^;]*;// if ($mid =~ m/&[^;]*$/); + $mid = " ... "; + } + return "$left$mid$right"; + + } else { + $str =~ m/^($endre)(.*)$/; + my $body = $1; + my $tail = $2; + if (length($tail) > 4) { + $body =~ s/&[^;]*$//; + $tail = "... "; + } + return "$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 $chopped = chop_str(@_); + if ($chopped eq $str) { + return esc_html($chopped); + } else { + $str =~ s/[[:cntrl:]]/?/g; + return $cgi->span({-title=>$str}, esc_html($chopped)); } - return "$body$tail"; } ## ---------------------------------------------------------------------- @@ -721,7 +1344,9 @@ 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"; @@ -762,11 +1387,25 @@ 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'; @@ -792,7 +1431,9 @@ 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"; @@ -813,7 +1454,9 @@ 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"; @@ -831,31 +1474,39 @@ 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]{8,40})/) { - my $hash_text = $1; - my $link = - $cgi->a({-href => href(action=>"object", hash=>$hash_text), - -class => "text"}, $hash_text); - $line =~ s/$hash_text/$link/; - } + $line =~ s{\b([0-9a-fA-F]{8,40})\b}{ + $cgi->a({-href => href(action=>"object", hash=>$1), + -class => "text"}, $1); + }eg; + return $line; } # format marker of refs pointing to given object + +# the destination action is chosen based on object type and current context: +# - for annotated tags, we choose the tag view unless it's the current view +# already, in which case we go to shortlog view +# - for other refs, we keep the current view if we're in history, shortlog or +# log view, and select shortlog otherwise sub format_ref_marker { my ($refs, $id) = @_; my $markers = ''; if (defined $refs->{$id}) { foreach my $ref (@{$refs->{$id}}) { + # this code exploits the fact that non-lightweight tags are the + # only indirect objects, and that they are the only objects for which + # we want to use tag instead of shortlog as action my ($type, $name) = qw(); + my $indirect = ($ref =~ s/\^\{\}$//); # e.g. tags/v2.6.11 or heads/next if ($ref =~ m!^(.*?)s?/(.*)$!) { $type = $1; @@ -865,8 +1516,29 @@ 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 . ""; } } @@ -883,32 +1555,317 @@ sub format_subject_html { $extra = '' unless defined($extra); if (length($short) < length($long)) { + $long =~ s/[[:cntrl:]]/?/g; return $cgi->a({-href => $href, -class => "list subject", -title => to_utf8($long)}, - esc_html($short) . $extra); + esc_html($short)) . $extra; } else { return $cgi->a({-href => $href, -class => "list subject"}, - esc_html($long) . $extra); + esc_html($long)) . $extra; + } +} + +# Rather than recomputing the url for an email multiple times, we cache it +# after the first hit. This gives a visible benefit in views where the avatar +# for the same email is used repeatedly (e.g. shortlog). +# The cache is shared by all avatar engines (currently gravatar only), which +# are free to use it as preferred. Since only one avatar engine is used for any +# given page, there's no risk for cache conflicts. +our %avatar_cache = (); + +# Compute the picon url for a given email, by using the picon search service over at +# http://www.cs.indiana.edu/picons/search.html +sub picon_url { + my $email = lc shift; + if (!$avatar_cache{$email}) { + my ($user, $domain) = split('@', $email); + $avatar_cache{$email} = + "http://www.cs.indiana.edu/cgi-pub/kinzler/piconsearch.cgi/" . + "$domain/$user/" . + "users+domains+unknown/up/single"; + } + return $avatar_cache{$email}; +} + +# Compute the gravatar url for a given email, if it's not in the cache already. +# Gravatar stores only the part of the URL before the size, since that's the +# one computationally more expensive. This also allows reuse of the cache for +# different sizes (for this particular engine). +sub gravatar_url { + my $email = lc shift; + my $size = shift; + $avatar_cache{$email} ||= + "http://www.gravatar.com/avatar/" . + Digest::MD5::md5_hex($email) . "?s="; + return $avatar_cache{$email} . $size; +} + +# Insert an avatar for the given $email at the given $size if the feature +# is enabled. +sub git_get_avatar { + my ($email, %opts) = @_; + my $pre_white = ($opts{-pad_before} ? " " : ""); + my $post_white = ($opts{-pad_after} ? " " : ""); + $opts{-size} ||= 'default'; + my $size = $avatar_size{$opts{-size}} || $avatar_size{'default'}; + my $url = ""; + if ($git_avatar eq 'gravatar') { + $url = gravatar_url($email, $size); + } elsif ($git_avatar eq 'picon') { + $url = picon_url($email); + } + # Other providers can be added by extending the if chain, defining $url + # as needed. If no variant puts something in $url, we assume avatars + # are completely disabled/unavailable. + if ($url) { + return $pre_white . + "" . $post_white; + } else { + return ""; + } +} + +# 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 "<$tag class=\"author\">" . + git_get_avatar($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; } -# format patch (diff) line (rather not to be used for diff headers) +# format patch (diff) line (not to be used for diff headers) sub format_diff_line { my $line = shift; my ($from, $to) = @_; - my $char = substr($line, 0, 1); my $diff_class = ""; chomp $line; - if ($char eq '+') { - $diff_class = " add"; - } elsif ($char eq "-") { - $diff_class = " rem"; - } elsif ($char eq "@") { - $diff_class = " chunk_header"; - } elsif ($char eq "\\") { - $diff_class = " incomplete"; + if ($from && $to && ref($from->{'href'}) eq "ARRAY") { + # combined diff + my $prefix = substr($line, 0, scalar @{$from->{'href'}}); + if ($line =~ m/^\@{3}/) { + $diff_class = " chunk_header"; + } elsif ($line =~ m/^\\/) { + $diff_class = " incomplete"; + } elsif ($prefix =~ tr/+/+/) { + $diff_class = " add"; + } elsif ($prefix =~ tr/-/-/) { + $diff_class = " rem"; + } + } else { + # assume ordinary diff + my $char = substr($line, 0, 1); + if ($char eq '+') { + $diff_class = " add"; + } elsif ($char eq '-') { + $diff_class = " rem"; + } elsif ($char eq '@') { + $diff_class = " chunk_header"; + } elsif ($char eq "\\") { + $diff_class = " incomplete"; + } } $line = untabify($line); if ($from && $to && $line =~ m/^\@{2} /) { @@ -929,21 +1886,134 @@ sub format_diff_line { $line = "@@ $from_text $to_text @@" . "" . esc_html($section, -nbsp=>1) . ""; return "
$line
\n"; + } elsif ($from && $to && $line =~ m/^\@{3}/) { + my ($prefix, $ranges, $section) = $line =~ m/^(\@+) (.*?) \@+(.*)$/; + my (@from_text, @from_start, @from_nlines, $to_text, $to_start, $to_nlines); + + @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 "
$line
\n"; } return "
" . esc_html($line, -nbsp=>1) . "
\n"; } +# 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)); + + # feed links are possible only for project views + return unless (defined $project); + # some views should link to OPML, or to generic project feed, + # or don't have specific feed yet (so they should use generic) + return if ($action =~ /^(?:tags|heads|forks|tag|search)$/x); + + my $branch; + # branches refs uses 'refs/heads/' prefix (fullname) to differentiate + # from tag links; this also makes possible to detect branch links + if ((defined $hash_base && $hash_base =~ m!^refs/heads/(.*)$!) || + (defined $hash && $hash =~ m!^refs/heads/(.*)$!)) { + $branch = $1; + } + # find log type for feed description (title) + my $type = 'log'; + if (defined $file_name) { + $type = "history of $file_name"; + $type .= "/" if ($action eq 'tree'); + $type .= " on '$branch'" if (defined $branch); + } else { + $type = "log of $branch" if (defined $branch); + } + + $res{-title} = $type; + $res{'hash'} = (defined $branch ? "refs/heads/$branch" : undef); + $res{'file_name'} = $file_name; + + return %res; +} + ## ---------------------------------------------------------------------- ## git utility subroutines, invoking git commands # returns path to the core git executable and the --git-dir parameter as list sub git_cmd { + $number_of_git_cmds++; return $GIT, '--git-dir='.$git_dir; } -# returns path to the core git executable and the --git-dir parameter as string -sub git_cmd_str { - return join(' ', git_cmd()); +# quote the given arguments for passing them to the shell +# quote_command("command", "arg 1", "arg with ' and ! characters") +# => "'command' 'arg 1' 'arg with '\'' and '\!' characters'" +# Try to avoid using this function wherever possible. +sub quote_command { + return join(' ', + map { my $a = $_; $a =~ s/(['!])/'\\$1'/g; "'$a'" } @_ ); } # get HEAD ref of given project as hash @@ -976,20 +2046,125 @@ 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, $type) = @_; + # key sanity check return unless ($key); $key =~ s/^gitweb\.//; return if ($key =~ m/\W/); - 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); + # 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 @@ -1001,10 +2176,15 @@ 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) { @@ -1014,23 +2194,119 @@ 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 sub git_get_project_description { my $path = shift; - open my $fd, "$projectroot/$path/description" or return undef; + $git_dir = "$projectroot/$path"; + open my $fd, '<', "$git_dir/description" + or return git_get_project_config('description'); my $descr = <$fd>; close $fd; - chomp $descr; + if (defined $descr) { + chomp $descr; + } return $descr; } +sub git_get_project_ctags { + my $path = shift; + my $ctags = {}; + + $git_dir = "$projectroot/$path"; + opendir my $dh, "$git_dir/ctags" + or return $ctags; + foreach (grep { -f $_ } map { "$git_dir/ctags/$_" } readdir($dh)) { + open my $ct, '<', $_ or next; + my $val = <$ct>; + chomp $val; + close $ct; + my $ctag = $_; $ctag =~ s#.*/##; + $ctags->{$ctag} = $val; + } + closedir $dh; + $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; + if (eval { require HTML::TagCloud; 1; }) { + $cloud = HTML::TagCloud->new; + foreach (sort keys %ctags_lc) { + # Pad the title with spaces so that the cloud looks + # less crammed. + my $title = $ctags_lc{$_}->{topname}; + $title =~ s/ / /g; + $title =~ s/^/ /g; + $title =~ s/$/ /g; + $cloud->add($title, $home_link."?by_tag=".$_, $ctags_lc{$_}->{count}); + } + } else { + $cloud = \%ctags_lc; + } + $cloud; +} + +sub git_show_project_tagcloud { + my ($cloud, $count) = @_; + print STDERR ref($cloud)."..\n"; + if (ref $cloud eq 'HTML::TagCloud') { + return $cloud->html_and_css($count); + } else { + my @tags = sort { $cloud->{$a}->{count} <=> $cloud->{$b}->{count} } keys %$cloud; + return '

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

'; + } +} + 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; @@ -1044,30 +2320,36 @@ sub git_get_projects_list { $filter ||= ''; $filter =~ s/\.git$//; + my $check_forks = gitweb_check_feature('forks'); + if (-d $projects_list) { # search in directory my $dir = $projects_list . ($filter ? "/$filter" : ''); # remove the trailing "/" $dir =~ s!/+$!!; my $pfxlen = length("$dir"); - - my ($check_forks) = gitweb_check_feature('forks'); + my $pfxdepth = ($dir =~ tr!/!!); File::Find::find({ follow_fast => 1, # follow symbolic links + follow_skip => 2, # ignore duplicates dangling_symlinks => 0, # ignore dangling symlinks, silently wanted => sub { # skip project-list toplevel, if we get it. return if (m!^[/.]$!); # only directories can be git repositories return unless (-d $_); + # don't traverse too deep (Find is super slow on os x) + if (($File::Find::name =~ tr!/!!) - $pfxdepth > $project_maxdepth) { + $File::Find::prune = 1; + return; + } my $subdir = substr($File::Find::name, $pfxlen + 1); # we check related file in $projectroot - if ($check_forks and $subdir =~ m#/.#) { - $File::Find::prune = 1; - } elsif (check_export_ok("$projectroot/$filter/$subdir")) { - push @list, { path => ($filter ? "$filter/" : '') . $subdir }; + my $path = ($filter ? "$filter/" : '') . $subdir; + if (check_export_ok("$projectroot/$path")) { + push @list, { path => $path }; $File::Find::prune = 1; } }, @@ -1078,7 +2360,9 @@ sub git_get_projects_list { # 'git%2Fgit.git Linus+Torvalds' # 'libs%2Fklibc%2Fklibc.git H.+Peter+Anvin' # 'linux%2Fhotplug%2Fudev.git Greg+Kroah-Hartman' - open my ($fd), $projects_list or return; + my %paths; + open my $fd, '<', $projects_list or return; + PROJECT: while (my $line = <$fd>) { chomp $line; my ($path, $owner) = split ' ', $line; @@ -1091,11 +2375,27 @@ sub git_get_projects_list { # looking for forks; my $pfx = substr($path, 0, length($filter)); if ($pfx ne $filter) { - next; + next PROJECT; } my $sfx = substr($path, length($filter)); if ($sfx !~ /^\/.*\.git$/) { - next; + next PROJECT; + } + } elsif ($check_forks) { + PATH: + foreach my $filter (keys %paths) { + # looking for forks; + my $pfx = substr($path, 0, length($filter)); + if ($pfx ne $filter) { + next PATH; + } + my $sfx = substr($path, length($filter)); + if ($sfx !~ /^\/.*\.git$/) { + next PATH; + } + # is a fork, don't include it in + # the list + next PROJECT; } } if (check_export_ok("$projectroot/$path")) { @@ -1103,41 +2403,58 @@ sub git_get_projects_list { path => $path, owner => to_utf8($owner), }; - push @list, $pr + push @list, $pr; + (my $forks_path = $path) =~ s/\.git$//; + $paths{$forks_path}++; } } close $fd; } - @list = sort {$a->{'path'} cmp $b->{'path'}} @list; return @list; } -sub git_get_project_owner { - my $project = shift; - my $owner; +our $gitweb_project_owner = undef; +sub git_get_project_list_from_file { - return undef unless $project; + 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); + 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; - } + $gitweb_project_owner->{$pr} = to_utf8($ow); } close $fd; } +} + +sub git_get_project_owner { + my $project = shift; + my $owner; + + return undef unless $project; + $git_dir = "$projectroot/$project"; + + 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; @@ -1155,11 +2472,13 @@ sub git_get_last_activity { 'refs/heads') 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); } sub git_get_references { @@ -1173,7 +2492,7 @@ sub git_get_references { while (my $line = <$fd>) { chomp $line; - if ($line =~ m!^([0-9a-fA-F]{40})\srefs/($type/?[^^]+)!) { + if ($line =~ m!^([0-9a-fA-F]{40})\srefs/($type.*)$!) { if (defined $refs{$1}) { push @{$refs{$1}}, $2; } else { @@ -1222,7 +2541,7 @@ sub parse_date { $date{'mday-time'} = sprintf "%d %s %02d:%02d", $mday, $months[$mon], $hour ,$min; $date{'iso-8601'} = sprintf "%04d-%02d-%02dT%02d:%02d:%02dZ", - 1900+$year, $mon, $mday, $hour ,$min, $sec; + 1900+$year, 1+$mon, $mday, $hour ,$min, $sec; $tz =~ m/^([+\-][0-9][0-9])([0-9][0-9])$/; my $local = $epoch + ((int $1 + ($2/60)) * 3600); @@ -1253,8 +2572,14 @@ 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, $line; last; @@ -1272,26 +2597,29 @@ sub parse_tag { } sub parse_commit_text { - my ($commit_text) = @_; + my ($commit_text, $withparents) = @_; my @commit_lines = split '\n', $commit_text; my %co; 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'} = $header; - my @parents; + ($co{'id'}, my @parents) = split ' ', $header; while (my $line = shift @commit_lines) { last if $line eq "\n"; if ($line =~ m/^tree ([0-9a-fA-F]{40})$/) { $co{'tree'} = $1; - } elsif ($line =~ m/^parent ([0-9a-fA-F]{40})$/) { + } 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/^([^<]+) <([^>]*)>/) { @@ -1301,10 +2629,9 @@ sub parse_commit_text { $co{'author_name'} = $co{'author'}; } } elsif ($line =~ m/^committer (.*) ([0-9]+) (.*)$/) { - $co{'committer'} = $1; + $co{'committer'} = to_utf8($1); $co{'committer_epoch'} = $2; $co{'committer_tz'} = $3; - $co{'committer_name'} = $co{'committer'}; if ($co{'committer'} =~ m/^([^<]+) <([^>]*)>/) { $co{'committer_name'} = $1; $co{'committer_email'} = $2; @@ -1344,7 +2671,7 @@ sub parse_commit_text { last; } } - if ($co{'title'} eq "") { + if (! defined $co{'title'} || $co{'title'} eq "") { $co{'title'} = $co{'title_short'} = '(no commit message)'; } # remove added spaces @@ -1374,57 +2701,37 @@ sub parse_commit { local $/ = "\0"; open my $fd, "-|", git_cmd(), "rev-list", + "--parents", "--header", "--max-count=1", $commit_id, "--", - or die_error(undef, "Open git-rev-list failed"); - %co = parse_commit_text(<$fd>); + 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, $arg, $filename) = @_; + my ($commit_id, $maxcount, $skip, $filename, @args) = @_; my @cos; $maxcount ||= 1; $skip ||= 0; - # Delete once rev-list supports the --skip option - if ($skip > 0) { - open my $fd, "-|", git_cmd(), "rev-list", - ($arg ? ($arg) : ()), - ("--max-count=" . ($maxcount + $skip)), - $commit_id, - "--", - ($filename ? ($filename) : ()) - or die_error(undef, "Open git-rev-list failed"); - while (my $line = <$fd>) { - if ($skip-- <= 0) { - chomp $line; - my %co = parse_commit($line); - push @cos, \%co; - } - } - close $fd; - - return wantarray ? @cos : \@cos; - } - local $/ = "\0"; open my $fd, "-|", git_cmd(), "rev-list", "--header", - ($arg ? ($arg) : ()), + @args, ("--max-count=" . $maxcount), - # Add once rev-list supports the --skip option - # ("--skip=" . $skip), + ("--skip=" . $skip), + @extra_options, $commit_id, "--", ($filename ? ($filename) : ()) - or die_error(undef, "Open git-rev-list failed"); + or die_error(500, "Open git-rev-list failed"); while (my $line = <$fd>) { my %co = parse_commit_text($line); push @cos, \%co; @@ -1434,49 +2741,6 @@ sub parse_commits { return wantarray ? @cos : \@cos; } -# parse ref from ref_file, given by ref_id, with given type -sub parse_ref { - my $ref_file = shift; - my $ref_id = shift; - my $type = shift || git_get_type($ref_id); - my %ref_item; - - $ref_item{'type'} = $type; - $ref_item{'id'} = $ref_id; - $ref_item{'epoch'} = 0; - $ref_item{'age'} = "unknown"; - if ($type eq "tag") { - my %tag = parse_tag($ref_id); - $ref_item{'comment'} = $tag{'comment'}; - if ($tag{'type'} eq "commit") { - my %co = parse_commit($tag{'object'}); - $ref_item{'epoch'} = $co{'committer_epoch'}; - $ref_item{'age'} = $co{'age_string'}; - } elsif (defined($tag{'epoch'})) { - my $age = time - $tag{'epoch'}; - $ref_item{'epoch'} = $tag{'epoch'}; - $ref_item{'age'} = age_string($age); - } - $ref_item{'reftype'} = $tag{'type'}; - $ref_item{'name'} = $tag{'name'}; - $ref_item{'refid'} = $tag{'object'}; - } elsif ($type eq "commit"){ - my %co = parse_commit($ref_id); - $ref_item{'reftype'} = "commit"; - $ref_item{'name'} = $ref_file; - $ref_item{'title'} = $co{'title'}; - $ref_item{'refid'} = $ref_id; - $ref_item{'epoch'} = $co{'committer_epoch'}; - $ref_item{'age'} = $co{'age_string'}; - } else { - $ref_item{'reftype'} = $type; - $ref_item{'name'} = $ref_file; - $ref_item{'refid'} = $ref_id; - } - - return %ref_item; -} - # parse line of git-diff-tree "raw" output sub parse_difftree_raw_line { my $line = shift; @@ -1494,9 +2758,20 @@ sub parse_difftree_raw_line { if ($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; @@ -1505,27 +2780,101 @@ 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 $to->{'href'}; + } +} + ## ...................................................................... ## parse to array of hashes functions @@ -1546,6 +2895,7 @@ sub git_get_heads_list { my ($hash, $name, $title) = split(' ', $refinfo, 3); my ($committer, $epoch, $tz) = ($committerinfo =~ /^(.*) ([0-9]+) (.*)$/); + $ref_item{'fullname'} = $name; $name =~ s!^refs/heads/!!; $ref_item{'name'} = $name; @@ -1583,6 +2933,7 @@ sub git_get_tags_list { my ($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'} = $type; @@ -1629,6 +2980,15 @@ sub get_file_owner { return to_utf8($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 @@ -1638,18 +2998,18 @@ 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, $exts) = split(/\t+/); + my ($mimetype, $exts) = split(/\t+/); if (defined $exts) { my @exts = split(/\s+/, $exts); foreach my $ext (@exts) { - $mimemap{$ext} = $mime; + $mimemap{$ext} = $mimetype; } } } - close(MIME); + close($mh); $filename =~ /\.([^.]*)$/; return $mimemap{$1}; @@ -1685,8 +3045,7 @@ 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$/i) { @@ -1700,6 +3059,17 @@ sub blob_mimetype { } } +sub blob_contenttype { + my ($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; +} + ## ====================================================================== ## functions printing HTML: header, footer, error page @@ -1709,7 +3079,7 @@ sub git_header_html { my $title = "$site_name"; if (defined $project) { - $title .= " - $project"; + $title .= " - " . to_utf8($project); if (defined $action) { $title .= "/$action"; if (defined $file_name) { @@ -1734,6 +3104,7 @@ sub git_header_html { } print $cgi->header(-type=>$content_type, -charset => 'utf-8', -status=> $status, -expires => $expires); + my $mod_perl_version = $ENV{'MOD_PERL'} ? " $ENV{'MOD_PERL'}" : ''; print < @@ -1742,13 +3113,18 @@ sub git_header_html { - + $title EOF -# print out each stylesheet that exist + # the stylesheet, favicon etc urls won't work correctly with path_info + # unless we set the appropriate base URL + if ($ENV{'PATH_INFO'}) { + print "\n"; + } + # print out each stylesheet that exist, providing backwards capability + # for those people who defined $stylesheet in a config file if (defined $stylesheet) { -#provides backwards capability for those people who define style sheet in a config file print ''."\n"; } else { foreach my $stylesheet (@stylesheets) { @@ -1757,31 +3133,56 @@ EOF } } if (defined $project) { - printf(''."\n", - esc_param($project), href(action=>"rss")); - printf(''."\n", - esc_param($project), href(action=>"atom")); + 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' => "$project - $href_params{'-title'} - $format feed", + '-type' => "application/$type+xml" + ); + + $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", + 'href="%s" type="text/plain; charset=utf-8" />'."\n", $site_name, href(project=>undef, action=>"project_index")); printf(''."\n", + 'href="%s" type="text/x-opml" />'."\n", $site_name, href(project=>undef, action=>"opml")); } if (defined $favicon) { - print qq(\n); + print qq(\n); } print "\n" . "\n"; if (-f $site_header) { - open (my $fd, $site_header); - print <$fd>; - close $fd; + insert_file($site_header); } print "
\n" . @@ -1796,8 +3197,10 @@ EOF } print "\n"; } - my ($have_search) = gitweb_check_feature('search'); - if ((defined $project) && ($have_search)) { + print "
\n"; + + my $have_search = gitweb_check_feature('search'); + if (defined $project && $have_search) { if (!defined $searchtext) { $searchtext = ""; } @@ -1809,59 +3212,116 @@ EOF } 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) . + 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" . - $cgi->hidden(-name => "p") . "\n" . - $cgi->hidden(-name => "a") . "\n" . - $cgi->hidden(-name => "h") . "\n" . + (!$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', 'author', 'committer', 'pickaxe']) . + -values => ['commit', 'grep', 'author', 'committer', 'pickaxe']) . $cgi->sup($cgi->a({-href => href(action=>"search_help")}, "?")) . " search:\n", $cgi->textfield(-name => "s", -value => $searchtext) . "\n" . + "" . + $cgi->checkbox(-name => 'sr', -value => 1, -label => 're', + -checked => $search_use_regexp) . + "" . "
" . $cgi->end_form() . "\n"; } - print "\n"; } sub git_footer_html { + 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") . " "; - print $cgi->a({-href => href(action=>"atom"), - -class => "rss_logo"}, "Atom") . "\n"; + + my %href_params = get_feed_info(); + if (!%href_params) { + $feed_class .= ' generic'; + } + $href_params{'-title'} ||= 'log'; + + foreach my $format qw(RSS Atom) { + $href_params{'action'} = lc($format); + print $cgi->a({-href => href(%href_params), + -title => "$href_params{'-title'} $format feed", + -class => $feed_class}, $format)."\n"; + } + } else { print $cgi->a({-href => href(project=>undef, action=>"opml"), - -class => "rss_logo"}, "OPML") . " "; + -class => $feed_class}, "OPML") . " "; print $cgi->a({-href => href(project=>undef, action=>"project_index"), - -class => "rss_logo"}, "TXT") . "\n"; + -class => $feed_class}, "TXT") . "\n"; + } + print "
\n"; # class="page_footer" + + if (defined $t0 && gitweb_check_feature('timed')) { + print "
\n"; + print 'This page took '. + ''. + Time::HiRes::tv_interval($t0, [Time::HiRes::gettimeofday()]). + ' seconds '. + ' and '. + ''. + $number_of_git_cmds. + ' git commands '. + " to generate.\n"; + print "
\n"; # class="page_footer" } - print "\n" ; if (-f $site_footer) { - open (my $fd, $site_footer); - print <$fd>; - close $fd; + insert_file($site_footer); + } + + print qq!\n!; + if ($action eq 'blame_incremental') { + print qq!\n!; + } else { + 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). sub die_error { - my $status = shift || "403 Forbidden"; - my $error = shift || "Malformed query, file missing or permission denied"; - - git_header_html($status); + my $status = shift || 500; + my $error = shift || "Internal server error"; + + my %http_responses = (400 => '400 Bad Request', + 403 => '403 Forbidden', + 404 => '404 Not Found', + 500 => '500 Internal Server Error'); + git_header_html($http_responses{$status}); print <

@@ -1888,28 +3348,46 @@ 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(%{$arg{$_}}))}, "$_") } @navs); print "
\n$extra
\n" . "
\n"; } sub format_paging_nav { - my ($action, $hash, $head, $page, $nrevs) = @_; + my ($action, $hash, $head, $page, $has_next_link) = @_; my $paging_nav; @@ -1921,15 +3399,15 @@ sub format_paging_nav { if ($page > 0) { $paging_nav .= " ⋅ " . - $cgi->a({-href => href(action=>$action, hash=>$hash, page=>$page-1), + $cgi->a({-href => href(-replay=>1, page=>$page-1), -accesskey => "p", -title => "Alt-p"}, "prev"); } else { $paging_nav .= " ⋅ prev"; } - if ($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 { $paging_nav .= " ⋅ next"; @@ -1945,9 +3423,9 @@ sub git_print_header_div { my ($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" . $cgi->a({-href => href(%args), -class => "title"}, @@ -1955,22 +3433,54 @@ sub git_print_header_div { "\n
\n"; } -#sub git_print_authorship (\%) { +sub print_local_time { + my %date = @_; + if ($date{'hour_local'} < 6) { + printf(" (%02d:%02d %s)", + $date{'hour_local'}, $date{'minute_local'}, $date{'tz_local'}); + } else { + printf(" (%02d:%02d %s)", + $date{'hour_local'}, $date{'minute_local'}, $date{'tz_local'}); + } +} + +# Outputs the author name and date in long form sub git_print_authorship { my $co = shift; + my %opts = @_; + my $tag = $opts{-tag} || 'div'; my %ad = parse_date($co->{'author_epoch'}, $co->{'author_tz'}); - print "
" . + print "<$tag class=\"author_date\">" . 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'}, $ad{'tz_local'}); + print_local_time(%ad) if ($opts{-localtime}); + print "]" . 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 (& similia). +# Parameters are a commit hash reference, followed by the list of people +# to output information for. If the list is empty it defalts 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 "$who" . esc_html($co->{$who}) . "" . + "" . + git_get_avatar($co->{"${who}_email"}, -size => 'double') . + "\n" . + "" . + " $wd{'rfc2822'}"; + print_local_time(%wd); + print "" . + "\n"; } - print "]
\n"; } sub git_print_page_path { @@ -1981,7 +3491,7 @@ 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; @@ -1992,17 +3502,17 @@ 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($basename); @@ -2011,8 +3521,7 @@ sub git_print_page_path { print "
\n"; } -# sub git_print_log (\@;%) { -sub git_print_log ($;%) { +sub git_print_log { my $log = shift; my %opts = @_; @@ -2070,7 +3579,7 @@ sub git_get_link_target { open my $fd, "-|", git_cmd(), "cat-file", "blob", $hash or return; { - local $/; + local $/ = undef; $link_target = <$fd>; } close $fd @@ -2083,10 +3592,7 @@ sub git_get_link_target { # return target of link relative to top directory (top tree); # return undef if it is not possible (including absolute links). sub normalize_link_target { - my ($link_target, $basedir, $hash_base) = @_; - - # we can normalize symlink target only if $hash_base is provided - return unless $hash_base; + my ($link_target, $basedir) = @_; # absolute symlinks (beginning with '/') cannot be normalized return if (substr($link_target, 0, 1) eq '/'); @@ -2134,6 +3640,9 @@ sub git_print_tree_entry { # and link is the action links of the entry. print "" . mode_str($t->{'mode'}) . "\n"; + if (exists $t->{'size'}) { + print "$t->{'size'}\n"; + } if ($t->{'type'} eq "blob") { print "" . $cgi->a({-href => href(action=>"blob", hash=>$t->{'hash'}, @@ -2142,7 +3651,7 @@ sub git_print_tree_entry { if (S_ISLNK(oct $t->{'mode'})) { my $link_target = git_get_link_target($t->{'hash'}); if ($link_target) { - my $norm_target = normalize_link_target($link_target, $basedir, $hash_base); + my $norm_target = normalize_link_target($link_target, $basedir); if (defined $norm_target) { print " -> " . $cgi->a({-href => href(action=>"object", hash_base=>$hash_base, @@ -2179,12 +3688,14 @@ sub git_print_tree_entry { } elsif ($t->{'type'} eq "tree") { print ""; print $cgi->a({-href => href(action=>"tree", hash=>$t->{'hash'}, - file_name=>"$basedir$t->{'name'}", %base_key)}, + file_name=>"$basedir$t->{'name'}", + %base_key)}, esc_path($t->{'name'})); print "\n"; print ""; print $cgi->a({-href => href(action=>"tree", hash=>$t->{'hash'}, - file_name=>"$basedir$t->{'name'}", %base_key)}, + file_name=>"$basedir$t->{'name'}", + %base_key)}, "tree"); if (defined $hash_base) { print " | " . @@ -2193,26 +3704,99 @@ sub git_print_tree_entry { "history"); } print "\n"; + } else { + # unknown object: we can only present history for it + # (this includes 'commit' object, i.e. submodule support) + print "" . + esc_path($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"; } } ## ...................................................................... ## 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"; @@ -2221,31 +3805,120 @@ 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 $diff{'from_mode'}; + if ($diff->{'from_mode'} ne ('0' x 6)) { + $from_mode_oct = oct $diff->{'from_mode'}; if (S_ISREG($to_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)) { @@ -2305,9 +3978,9 @@ 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'}) . + "" . + $cgi->a({-href => "#patch$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"; @@ -2255,17 +3928,17 @@ sub git_difftree_body { print $cgi->a({-href => "#patch$patchno"}, "patch"); print " | "; } - 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"); 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"; @@ -2275,24 +3948,24 @@ sub git_difftree_body { print $cgi->a({-href => "#patch$patchno"}, "patch"); print " | "; } - print $cgi->a({-href => href(action=>"blob", hash=>$diff{'from_id'}, - hash_base=>$parent, file_name=>$diff{'file'})}, + 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=>$diff{'file'})}, + file_name=>$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"; @@ -2316,87 +3989,91 @@ sub git_difftree_body { $patchno++; print $cgi->a({-href => "#patch$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'})}, + 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=>$diff{'file'})}, + file_name=>$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") . " | "; - } 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{'to_id'}, - hash_base=>$parent, file_name=>$diff{'to_file'})}, + 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=>$diff{'to_file'})}, + file_name=>$diff->{'to_file'})}, "blame") . " | "; } print $cgi->a({-href => href(action=>"history", hash_base=>$hash, - file_name=>$diff{'to_file'})}, + file_name=>$diff->{'to_file'})}, "history"); print "
\n"; } sub git_patchset_body { - my ($fd, $difftree, $hash, $hash_parent) = @_; + my ($fd, $difftree, $hash, @hash_parents) = @_; + my ($hash_parent) = $hash_parents[0]; + my $is_combined = (@hash_parents > 1); my $patch_idx = 0; + my $patch_number = 0; my $patch_line; my $diffinfo; + my $to_name; my (%from, %to); - my ($from_id, $to_id); print "
\n"; @@ -2409,152 +4086,92 @@ sub git_patchset_body { PATCH: while ($patch_line) { - my @diff_header; - - # git diff header - #assert($patch_line =~ m/^diff /) if DEBUG; - #assert($patch_line !~ m!$/$!) if DEBUG; # is chomp-ed - push @diff_header, $patch_line; - - # extended diff header - EXTENDED_HEADER: - while ($patch_line = <$fd>) { - chomp $patch_line; - - last EXTENDED_HEADER if ($patch_line =~ m/^--- /); - - if ($patch_line =~ m/^index ([0-9a-fA-F]{40})..([0-9a-fA-F]{40})/) { - $from_id = $1; - $to_id = $2; - } - push @diff_header, $patch_line; + # parse "git diff" header line + if ($patch_line =~ m/^diff --git (\"(?:[^\\\"]*(?:\\.[^\\\"]*)*)\"|[^ "]*) (.*)$/) { + # $1 is from_name, which we do not use + $to_name = unquote($2); + $to_name =~ s!^b/!!; + } elsif ($patch_line =~ m/^diff --(cc|combined) ("?.*"?)$/) { + # $1 is 'cc' or 'combined', which we do not use + $to_name = unquote($2); + } else { + $to_name = undef; } - #last PATCH unless $patch_line; - my $last_patch_line = $patch_line; # check if current patch belong to current raw line # and parse raw git-diff line if needed - if (defined $diffinfo && - $diffinfo->{'from_id'} eq $from_id && - $diffinfo->{'to_id'} eq $to_id) { - # this is split patch + if (is_patch_split($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'}); + $diffinfo = parsed_difftree_line($difftree->[$patch_idx]); + + # compact combined diff output can have some patches skipped + # find which patch (using pathname of result) we are at now; + if ($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->[$patch_idx]); + } } + + # modifies %from, %to hashes + parse_from_to_diffinfo($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"; } + # git diff header + #assert($patch_line =~ m/^diff /) if DEBUG; + #assert($patch_line !~ m!$/$!) if DEBUG; # is chomp-ed + $patch_number++; # print "git diff" header - $patch_line = shift @diff_header; - $patch_line =~ s!^(diff (.*?) )"?a/.*$!$1!; - if ($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'}); - } - print "
$patch_line
\n"; + print format_git_diff_header_line($patch_line, $diffinfo, + \%from, \%to); # print extended diff header - print "
\n" if (@diff_header > 0); + print "
\n"; EXTENDED_HEADER: - foreach $patch_line (@diff_header) { - # match - if ($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 { - $to_link = '0' x 7; - } - #affirm { - # my ($from_hash, $to_hash) = - # ($patch_line =~ m/^index ([0-9a-fA-F]{40})..([0-9a-fA-F]{40})/); - # my ($from_id, $to_id) = - # ($diffinfo->{'from_id'}, $diffinfo->{'to_id'}); - # ($from_hash eq $from_id) && ($to_hash eq $to_id); - #} if DEBUG; - my ($from_id, $to_id) = ($diffinfo->{'from_id'}, $diffinfo->{'to_id'}); - $patch_line =~ s!$from_id\.\.$to_id!$from_link..$to_link!; - } - print $patch_line . "
\n"; + while ($patch_line = <$fd>) { + chomp $patch_line; + + last EXTENDED_HEADER if ($patch_line =~ m/^--- |^diff /); + + print format_extended_diff_header_line($patch_line, $diffinfo, + \%from, \%to); } - print "
\n" if (@diff_header > 0); # class="diff extended_header" + print "
\n"; # class="diff extended_header" # from-file/to-file diff header - $patch_line = $last_patch_line; - #assert($patch_line =~ m/^---/) if DEBUG; - if ($from{'href'}) { - $patch_line = '--- a/' . - $cgi->a({-href=>$from{'href'}, -class=>"path"}, - esc_path($from{'file'})); + if (! $patch_line) { + print "
\n"; # class="patch" + last PATCH; } - print "
$patch_line
\n"; + next PATCH if ($patch_line =~ m/^diff /); + #assert($patch_line =~ m/^---/) if DEBUG; + my $last_patch_line = $patch_line; $patch_line = <$fd>; - #last PATCH unless $patch_line; chomp $patch_line; + #assert($patch_line =~ m/^\+\+\+/) if DEBUG; - #assert($patch_line =~ m/^+++/) if DEBUG; - if ($to{'href'}) { - $patch_line = '+++ b/' . - $cgi->a({-href=>$to{'href'}, -class=>"path"}, - esc_path($to{'file'})); - } - print "
$patch_line
\n"; + print format_diff_from_to_header($last_patch_line, $patch_line, + $diffinfo, \%from, \%to, + @hash_parents); # the patch itself LINE: @@ -2570,30 +4187,58 @@ sub git_patchset_body { print "
\n"; # class="patch" } + # for compact combined (--cc) format, with chunk and patch simpliciaction + # patchset might be empty, but there might be unprocessed raw lines + for (++$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, $no_header) = @_; - - my ($check_forks) = gitweb_check_feature('forks'); - +# fills project list info (age, description, owner, forks) for each +# project in the list, removing invalid projects from returned list +# NOTE: modifies $projlist, but does not remove entries from it +sub fill_project_list_info { + my ($projlist, $check_forks) = @_; my @projects; + + my $show_ctags = gitweb_check_feature('ctags'); + PROJECT: foreach my $pr (@$projlist) { - my (@aa) = git_get_last_activity($pr->{'path'}); - unless (@aa) { - next; + my (@activity) = git_get_last_activity($pr->{'path'}); + unless (@activity) { + next PROJECT; } - ($pr->{'age'}, $pr->{'age_string'}) = @aa; + ($pr->{'age'}, $pr->{'age_string'}) = @activity; if (!defined $pr->{'descr'}) { my $descr = git_get_project_description($pr->{'path'}) || ""; - $pr->{'descr_long'} = to_utf8($descr); - $pr->{'descr'} = chop_str($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'}") || ""; + $pr->{'owner'} = git_get_project_owner("$pr->{'path'}") || ""; } if ($check_forks) { my $pname = $pr->{'path'}; @@ -2601,66 +4246,98 @@ sub git_project_list_body { ($pname !~ /\/$/) && (-d "$projectroot/$pname")) { $pr->{'forks'} = "-d $projectroot/$pname"; - } - else { + } else { $pr->{'forks'} = 0; } } + $show_ctags and $pr->{'ctags'} = git_get_project_ctags($pr->{'path'}); push @projects, $pr; } - $order ||= "project"; + return @projects; +} + +# print 'sort by' element, generating 'sort by $name' replay link +# if that order is not selected +sub print_sort_th { + my ($name, $order, $header) = @_; + $header ||= ucfirst($name); + + if ($order eq $name) { + print "$header\n"; + } else { + print "" . + $cgi->a({-href => href(-replay=>1, order=>$name), + -class => "header"}, $header) . + "\n"; + } +} + +sub git_project_list_body { + # actually uses global variable $project + my ($projlist, $order, $from, $to, $extra, $no_header) = @_; + + my $check_forks = gitweb_check_feature('forks'); + my @projects = fill_project_list_info($projlist, $check_forks); + + $order ||= $default_projects_order; $from = 0 unless defined $from; $to = $#projects if (!defined $to || $#projects < $to); + my %order_info = ( + project => { key => 'path', type => 'str' }, + descr => { key => 'descr_long', type => 'str' }, + owner => { key => 'owner', type => 'str' }, + age => { key => 'age', type => 'num' } + ); + my $oi = $order_info{$order}; + if ($oi->{'type'} eq 'str') { + @projects = sort {$a->{$oi->{'key'}} cmp $b->{$oi->{'key'}}} @projects; + } else { + @projects = sort {$a->{$oi->{'key'}} <=> $b->{$oi->{'key'}}} @projects; + } + + my $show_ctags = gitweb_check_feature('ctags'); + if ($show_ctags) { + my %ctags; + foreach my $p (@projects) { + foreach my $ct (keys %{$p->{'ctags'}}) { + $ctags{$ct} += $p->{'ctags'}->{$ct}; + } + } + my $cloud = git_populate_project_tagcloud(\%ctags); + print git_show_project_tagcloud($cloud, 64); + } + print "\n"; unless ($no_header) { print "\n"; if ($check_forks) { print "\n"; } - 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" . + print_sort_th('project', $order, 'Project'); + print_sort_th('descr', $order, 'Description'); + print_sort_th('owner', $order, 'Owner'); + print_sort_th('age', $order, 'Last Change'); + print "\n" . # for links "\n"; } my $alternate = 1; + my $tagfilter = $cgi->param('by_tag'); for (my $i = $from; $i <= $to; $i++) { my $pr = $projects[$i]; + + next if $tagfilter and $show_ctags and not grep { lc $_ eq lc $tagfilter } keys %{$pr->{'ctags'}}; + next if $searchtext and not $pr->{'path'} =~ /$searchtext/ + and not $pr->{'descr_long'} =~ /$searchtext/; + # Weed out forks or non-matching entries of search + if ($check_forks) { + my $forkbase = $project; $forkbase ||= ''; $forkbase =~ s#\.git$#/#; + $forkbase="^$forkbase" if $forkbase; + next if not $searchtext and not $tagfilter and $show_ctags + and $pr->{'path'} =~ m#$forkbase.*/.*#; # regexp-safe + } + if ($alternate) { print "\n"; } else { @@ -2680,9 +4357,9 @@ sub git_project_list_body { "\n" . - "\n"; + "\n"; print "\n" . + (defined $pr->{'age_string'} ? $pr->{'age_string'} : "No commits") . "\n" . "
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") . - "
" . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"summary"), -class => "list", -title => $pr->{'descr_long'}}, esc_html($pr->{'descr'})) . "" . chop_str($pr->{'owner'}, 15) . "" . chop_and_escape_str($pr->{'owner'}, 15) . "{'age'}) . "\">" . - $pr->{'age_string'} . "" . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"summary")}, "summary") . " | " . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"shortlog")}, "shortlog") . " | " . @@ -2705,20 +4382,17 @@ sub git_project_list_body { sub git_shortlog_body { # uses global variable $project - my ($revlist, $from, $to, $refs, $extra) = @_; - - my $have_snapshot = gitweb_have_snapshot(); + my ($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"; + 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 { @@ -2727,8 +4401,7 @@ sub git_shortlog_body { $alternate ^= 1; # git_summary() used print "\n" . print "\n" . - "\n" . - "\n" . @@ -2736,8 +4409,9 @@ 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=>$commit)}, "tree"); - if ($have_snapshot) { - print " | " . $cgi->a({-href => href(action=>"snapshot", hash=>$commit)}, "snapshot"); + my $snapshot_links = format_snapshot_links($commit); + if (defined $snapshot_links) { + print " | " . $snapshot_links; } print "\n" . "\n"; @@ -2752,23 +4426,19 @@ sub git_shortlog_body { sub git_history_body { # Warning: assumes constant type (blob or tree) during history - my ($revlist, $from, $to, $refs, $hash_base, $ftype, $extra) = @_; + my ($commitlist, $from, $to, $refs, $hash_base, $ftype, $extra) = @_; $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); @@ -2779,9 +4449,8 @@ sub git_history_body { } $alternate ^= 1; print "\n" . - # shortlog uses chop_str($co{'author_name'}, 10) - "\n" . - "\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 + + } + + # footer + print "\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); @@ -2820,7 +4489,7 @@ 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]; @@ -2836,8 +4505,12 @@ sub git_tags_body { print "\n"; } $alternate ^= 1; - print "\n" . - "\n"; + } else { + print "\n"; + } + print "\n" . @@ -2857,8 +4530,8 @@ sub git_tags_body { " - - - - - - -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 $age_class; + git_print_page_path($file_name, $ftype, $hash_base); - 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 = $5; - } else { - print qq( \n); - next; + # page body + if ($format eq 'incremental') { + print "\n"; + + print qq!
\n!; + } + + print qq!
\n!; + print qq!
... / ...
\n! + if ($format eq 'incremental'); + print qq!
$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"); } @@ -2879,7 +4552,7 @@ sub git_heads_body { $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]; @@ -2893,13 +4566,13 @@ sub git_heads_body { $alternate ^= 1; print "\n" . ($curr ? "\n" . "\n" . ""; } @@ -2912,18 +4585,18 @@ sub git_heads_body { } sub git_search_grep_body { - my ($greplist, $from, $to, $extra) = @_; + my ($commitlist, $from, $to, $extra) = @_; $from = 0 unless defined $from; - $to = $#{$greplist} if (!defined $to || $#{$greplist} < $to); + $to = $#{$commitlist} if (!defined $to || $#{$commitlist} < $to); - 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{'name'})}, "tree") . "
\n"; + print "
\n"; my $alternate = 1; for (my $i = $from; $i <= $to; $i++) { - my $commit = $greplist->[$i]; - my %co = parse_commit($commit); + my %co = %{$commitlist->[$i]}; if (!%co) { next; } + my $commit = $co{'id'}; if ($alternate) { print "\n"; } else { @@ -2931,26 +4604,34 @@ sub git_search_grep_body { } $alternate ^= 1; print "\n" . - "\n" . + format_author_html('td', \%co, 15, 5) . "\n" . "\n" . "\n"; @@ -2968,37 +4649,40 @@ sub git_search_grep_body { ## 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(); if (!@list) { - die_error(undef, "No projects found"); + die_error(404, "No projects found"); } git_header_html(); if (-f $home_text) { print "
\n"; - open (my $fd, $home_text); - print <$fd>; - close $fd; + insert_file($home_text); print "
\n"; } + print $cgi->startform(-method => "get") . + "

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

" . + $cgi->end_form() . "\n"; git_project_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); if (!@list) { - die_error(undef, "No forks found"); + die_error(404, "No forks found"); } git_header_html(); @@ -3018,7 +4702,7 @@ 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'}); @@ -3035,7 +4719,7 @@ sub git_project_index { sub git_summary { my $descr = git_get_project_description($project) || "none"; my %co = parse_commit("HEAD"); - my %cd = parse_date($co{'committer_epoch'}, $co{'committer_tz'}); + my %cd = %co ? parse_date($co{'committer_epoch'}, $co{'committer_tz'}) : (); my $head = $co{'id'}; my $owner = git_get_project_owner($project); @@ -3046,7 +4730,7 @@ sub git_summary { my @taglist = git_get_tags_list(16); my @headlist = git_get_heads_list(16); 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); @@ -3056,10 +4740,13 @@ sub git_summary { git_print_page_nav('summary','', $head); print "
 
\n"; - 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)) . "
"); + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), + -class => "list subject"}, + chop_and_escape_str($co{'title'}, 50) . "
"); my $comment = $co{'comment'}; foreach my $line (@$comment) { - if ($line =~ m/^(.*)($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($text, 80, 5) . "
\n"; + if ($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=>$co{'id'})}, "tree"); print "
\n" . - "\n" . - "\n" . - "\n"; + print "
description" . esc_html($descr) . "
owner$owner
last change$cd{'rfc2822'}
\n" . + "\n" . + "\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 $url_tag = "URL"; @@ -3067,30 +4754,43 @@ sub git_summary { @url_list = map { "$_/$project" } @git_base_url_list unless @url_list; foreach my $git_url (@url_list) { next unless $git_url; - print "\n"; + print "\n"; $url_tag = ""; } + + # Tag cloud + my $show_ctags = gitweb_check_feature('ctags'); + if ($show_ctags) { + my $ctags = git_get_project_ctags($project); + my $cloud = git_populate_project_tagcloud($ctags); + print "\n\n"; + } + print "
description" . esc_html($descr) . "
owner" . esc_html($owner) . "
last change$cd{'rfc2822'}
$url_tag$git_url
$url_tag$git_url
Content tags:
"; + print "		" unless %$ctags; + print "
Add:
"; + print "		" if %$ctags; + print git_show_project_tagcloud($cloud, 48); + print "
\n"; - if (-s "$projectroot/$project/README.html") { - if (open my $fd, "$projectroot/$project/README.html") { - print "
readme
\n"; - print $_ while (<$fd>); - close $fd; - } + # If XSS prevention is on, we don't include README.html. + # TODO: Allow a readme in some safe format. + if (!$prevent_xss && -s "$projectroot/$project/README.html") { + print "
readme
\n" . + "
\n"; + insert_file("$projectroot/$project/README.html"); + print "\n
\n"; # class="readme" } # we need to request one more than 16 (0..15) to check if # those 16 are all - open my $fd, "-|", git_cmd(), "rev-list", "--max-count=17", - $head, "--" - 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, - $#revlist <= 15 ? undef : - $cgi->a({-href => href(action=>"shortlog")}, "...")); + 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'); @@ -3108,10 +4808,10 @@ sub git_summary { 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(); @@ -3122,9 +4822,14 @@ sub git_tag { git_header_html(); git_print_page_nav('','', $head,undef,$head); my %tag = parse_tag($hash); + + if (! %tag) { + die_error(404, "Unknown tag object"); + } + git_print_header_div('commit', esc_html($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'})}, @@ -3133,11 +4838,7 @@ sub git_tag { $tag{'type'}) . "
author" . esc_html($tag{'author'}) . "
" . $ad{'rfc2822'} . - sprintf(" (%02d:%02d %s)", $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}) . - "
\n\n" . "
\n"; @@ -3151,206 +4852,237 @@ sub git_tag { git_footer_html(); } -sub git_blame2 { - my $fd; - my $ftype; - - my ($have_blame) = gitweb_check_feature('blame'); - if (!$have_blame) { - die_error('403 Permission denied', "Permission denied"); - } - die_error('404 Not Found', "File name not defined") if (!$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 looking up file"); - } - $ftype = git_get_type($hash); - if ($ftype !~ "blob") { - die_error("400 Bad Request", "Object is not a blob"); - } - open ($fd, "-|", git_cmd(), "blame", '-p', '--', - $file_name, $hash_base) - or die_error(undef, "Open git-blame 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, $ftype, $hash_base); - my @rev_color = (qw(light2 dark2)); - my $num_colors = scalar(@rev_color); - my $current_color = 0; - my $last_rev; - print < - - -HTML - my %metainfo = (); - while (1) { - $_ = <$fd>; - last unless defined $_; - my ($full_rev, $orig_lineno, $lineno, $group_size) = - /^([0-9a-f]{40}) (\d+) (\d+)(?: (\d+))?$/; - if (!exists $metainfo{$full_rev}) { - $metainfo{$full_rev} = {}; - } - my $meta = $metainfo{$full_rev}; - while (<$fd>) { - last if (s/^\t//); - if (/^(\S+) (.*)$/) { - $meta->{$1} = $2; - } - } - my $data = $_; - chomp $data; - my $rev = substr($full_rev, 0, 8); - my $author = $meta->{'author'}; - my %date = parse_date($meta->{'author-time'}, - $meta->{'author-tz'}); - my $date = $date{'iso-tz'}; - if ($group_size) { - $current_color = ++$current_color % $num_colors; - } - print "\n"; - if ($group_size) { - print "\n"; - } - my $blamed = href(action => 'blame', - file_name => $meta->{'filename'}, - hash_base => $full_rev); - print ""; - print "\n"; - print "\n"; +sub git_blame_common { + my $format = shift || 'porcelain'; + if ($format eq 'porcelain' && $cgi->param('js')) { + $format = 'incremental'; + $action = 'blame_incremental'; # for page title etc } - print "
CommitLineData
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) . "
\n"; - print ""; - close $fd - or print "Reading blob failed\n"; - git_footer_html(); -} -sub git_blame { - my $fd; + # permissions + gitweb_check_feature('blame') + or die_error(403, "Blame view not allowed"); - my ($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); + # 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 lookup file"); + or die_error(404, "Error looking up file"); + } else { + $ftype = git_get_type($hash); + if ($ftype !~ "blob") { + die_error(400, "Object is not a blob"); + } + } + + my $fd; + if ($format eq 'incremental') { + # get file contents (as base) + open $fd, "-|", git_cmd(), 'cat-file', 'blob', $hash + or die_error(500, "Open git-cat-file failed"); + } elsif ($format eq 'data') { + # run git-blame --incremental + open $fd, "-|", git_cmd(), "blame", "--incremental", + $hash_base, "--", $file_name + or die_error(500, "Open git-blame --incremental failed"); + } else { + # run git-blame --porcelain + open $fd, "-|", git_cmd(), "blame", '-p', + $hash_base, '--', $file_name + or die_error(500, "Open git-blame --porcelain failed"); + } + + # incremental blame data returns early + if ($format eq 'data') { + print $cgi->header( + -type=>"text/plain", -charset => "utf-8", + -status=> "200 OK"); + local $| = 1; # output autoflush + print while <$fd>; + close $fd + or print "ERROR $!\n"; + + print 'END'; + if (defined $t0 && gitweb_check_feature('timed')) { + print ' '. + Time::HiRes::tv_interval($t0, [Time::HiRes::gettimeofday()]). + ' '.$number_of_git_cmds; + } + print "\n"; + + return; } - open ($fd, "-|", git_cmd(), "annotate", '-l', '-t', '-r', $file_name, $hash_base) - or die_error(undef, "Open git-annotate failed"); + + # page header git_header_html(); my $formats_nav = - $cgi->a({-href => href(action=>"blob", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name)}, + $cgi->a({-href => href(action=>"blob", -replay=>1)}, "blob") . " | " . - $cgi->a({-href => href(action=>"history", hash=>$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, 'blob', $hash_base); - print "
\n"; - print < -
CommitAgeAuthorLineData
Unable to parse: $line
\n!. + #qq!\n!. + qq!\n!. + qq!\n!. + qq!\n!. + qq!\n!; + + my @rev_color = qw(light dark); + my $num_colors = scalar(@rev_color); + my $current_color = 0; + + if ($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!; } - $short_rev = substr ($long_rev, 0, 8); - $age = time () - $time; - $age_str = age_string ($age); - $age_str =~ s/ / /g; - $age_class = age_class($age); - $author = esc_html ($author); - $author =~ s/ / /g; - - $data = untabify($data); - $data = esc_html ($data); - - print < - - - - - - -HTML - } # while (my $line = <$fd>) - print "
CommitLineData
!. + qq!$linenr! . esc_html($line) . "
$long_rev)}" class="text">$short_rev..$age_str$author$lineno$data
\n\n"; + + } else { # porcelain, i.e. ordinary blame + my %metainfo = (); # saves information about commits + + # blame data + LINE: + while (my $line = <$fd>) { + chomp $line; + # the header: [] + # no for subsequent lines in group of lines + my ($full_rev, $orig_lineno, $lineno, $group_size) = + ($line =~ /^([0-9a-f]{40}) (\d+) (\d+)(?: (\d+))?$/); + if (!exists $metainfo{$full_rev}) { + $metainfo{$full_rev} = { 'nprevious' => 0 }; + } + my $meta = $metainfo{$full_rev}; + my $data; + while ($data = <$fd>) { + chomp $data; + last if ($data =~ s/^\t//); # contents of line + if ($data =~ /^(\S+)(?: (.*))?$/) { + $meta->{$1} = $2 unless exists $meta->{$1}; + } + if ($data =~ /^previous /) { + $meta->{'nprevious'}++; + } + } + my $short_rev = substr($full_rev, 0, 8); + my $author = $meta->{'author'}; + my %date = + parse_date($meta->{'author-time'}, $meta->{'author-tz'}); + my $date = $date{'iso-tz'}; + if ($group_size) { + $current_color = ($current_color + 1) % $num_colors; + } + my $tr_class = $rev_color[$current_color]; + $tr_class .= ' boundary' if (exists $meta->{'boundary'}); + $tr_class .= ' no-previous' if ($meta->{'nprevious'} == 0); + $tr_class .= ' multiple-previous' if ($meta->{'nprevious'} > 1); + print "
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"; # class="blame" + print "\n"; # class="blame_body" close $fd - or print "Reading blob failed.\n"; - print ""; + or print "Reading blob failed\n"; + git_footer_html(); } +sub git_blame { + git_blame_common(); +} + +sub git_blame_incremental { + git_blame_common('incremental'); +} + +sub git_blame_data { + git_blame_common('data'); +} + sub git_tags { my $head = git_get_head_hash($project); git_header_html(); @@ -3378,28 +5110,29 @@ sub git_heads { } 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; @@ -3407,15 +5140,25 @@ 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 && + $type !~ m!^(?:text/plain|image/(?:gif|png|jpeg))$!; + 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; } @@ -3426,20 +5169,20 @@ sub git_blob { if (defined $file_name) { my $base = $hash_base || git_get_head_hash($project); $hash = git_get_hash_by_path($base, $file_name, "blob") - or die_error(undef, "Error lookup file"); + or die_error(404, "Cannot find file"); } else { - die_error(undef, "No file name defined"); + die_error(400, "No file name defined"); } } elsif ($hash =~ m/^[0-9a-fA-F]{40}$/) { # blobs defined by non-textual hash id's can be cached $expires = "+1d"; } - my ($have_blame) = gitweb_check_feature('blame'); + my $have_blame = gitweb_check_feature('blame'); open my $fd, "-|", git_cmd(), "cat-file", "blob", $hash - or die_error(undef, "Couldn't cat $file_name, $hash"); + or die_error(500, "Couldn't cat $file_name, $hash"); my $mimetype = blob_mimetype($fd, $file_name); - if ($mimetype !~ m!^(?:text/|image/(?:gif|png|jpeg)$)!) { + if ($mimetype !~ m!^(?:text/|image/(?:gif|png|jpeg)$)! && -B $fd) { close $fd; return git_blob_plain($mimetype); } @@ -3452,18 +5195,15 @@ sub git_blob { 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", @@ -3471,7 +5211,8 @@ 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'}), $hash_base); @@ -3482,16 +5223,7 @@ sub git_blob { } git_print_page_path($file_name, "blob", $hash_base); print "
\n"; - if ($mimetype =~ m!^text/!) { - my $nr; - while (my $line = <$fd>) { - chomp $line; - $nr++; - $line = untabify($line); - printf "
%4i %s
\n", - $nr, $nr, $nr, esc_html($line, -nbsp=>1); - } - } elsif ($mimetype =~ m!^image/!) { + if ($mimetype =~ m!^image/!) { print qq!$file_name"blob_plain", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name) . qq!" />\n!; + } else { + my $nr; + while (my $line = <$fd>) { + chomp $line; + $nr++; + $line = untabify($line); + printf "
%4i %s
\n", + $nr, $nr, $nr, esc_html($line, -nbsp=>1); + } } close $fd or print "Reading blob failed.\n"; @@ -3508,8 +5249,6 @@ sub git_blob { } sub git_tree { - my $have_snapshot = gitweb_have_snapshot(); - if (!defined $hash_base) { $hash_base = "HEAD"; } @@ -3520,36 +5259,43 @@ 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 $hash_base; @@ -3562,10 +5308,10 @@ sub git_tree { if ($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 && @@ -3582,8 +5328,10 @@ sub git_tree { undef $up unless $up; # based on git_print_tree_entry print '\n"; + print ''."\n" if $show_sizes; print '\n"; @@ -3592,7 +5340,7 @@ 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"; @@ -3611,34 +5359,52 @@ sub git_tree { } 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 $filename = basename($project) . "-$hash.tar.$suffix"; + my $name = $project; + $name =~ s,([^/])/*\.git$,$1,; + $name = basename($name); + my $filename = to_utf8($name); + $name =~ s/\047/\047\\\047\047/g; + my $cmd; + $filename .= "-$hash$known_snapshot_formats{$format}{'suffix'}"; + $cmd = quote_command( + git_cmd(), 'archive', + "--format=$known_snapshot_formats{$format}{'format'}", + "--prefix=$name/", $hash); + if (exists $known_snapshot_formats{$format}{'compressor'}) { + $cmd .= ' | ' . quote_command(@{$known_snapshot_formats{$format}{'compressor'}}); + } print $cgi->header( - -type => "application/$ctype", + -type => $known_snapshot_formats{$format}{'type'}, -content_disposition => 'inline; filename="' . "$filename" . '"', -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 { @@ -3651,28 +5417,34 @@ sub git_log { } 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 $fd; + my @commitlist = parse_commits($hash, 101, (100 * $page)); + + my $paging_nav = format_paging_nav('log', $hash, $head, $page, $#commitlist >= 100); - my $paging_nav = format_paging_nav('log', $hash, $head, $page, $#revlist); + my ($patch_max) = gitweb_get_feature('patches'); + if ($patch_max) { + if ($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, $paging_nav); - if (!@revlist) { + if (!@commitlist) { my %co = parse_commit($hash); git_print_header_div('summary', $project); print "
Last change $co{'age_string'}.

\n"; } - for (my $i = ($page * 100); $i <= $#revlist; $i++) { - my $commit = $revlist[$i]; - my $ref = format_ref_marker($refs, $commit); - my %co = parse_commit($commit); + my $to = ($#commitlist >= 99) ? (99) : ($#commitlist); + for (my $i = 0; $i <= $to; $i++) { + my %co = %{$commitlist[$i]}; next if !%co; + my $commit = $co{'id'}; + my $ref = format_ref_marker($refs, $commit); my %ad = parse_date($co{'author_epoch'}); git_print_header_div('commit', "$co{'age_string'}" . @@ -3686,25 +5458,27 @@ sub git_log { " | " . $cgi->a({-href => href(action=>"tree", hash=>$commit, hash_base=>$commit)}, "tree") . "
\n" . - "\n" . - "" . esc_html($co{'author_name'}) . " [$ad{'rfc2822'}]
\n" . "\n"; + git_print_authorship(\%co, -tag => 'span'); + print "
\n\n"; print "
\n"; git_print_log($co{'comment'}, -final_empty_line=> 1); print "
\n"; } + if ($#commitlist >= 100) { + print "
\n"; + print $cgi->a({-href => href(-replay=>1, page=>$page+1), + -accesskey => "n", -title => "Alt-n"}, "next"); + print "
\n"; + } git_footer_html(); } sub git_commit { $hash ||= $hash_base || "HEAD"; - my %co = parse_commit($hash); - if (!%co) { - die_error(undef, "Unknown commit object"); - } - my %ad = parse_date($co{'author_epoch'}, $co{'author_tz'}); - my %cd = parse_date($co{'committer_epoch'}, $co{'committer_tz'}); + my %co = parse_commit($hash) + or die_error(404, "Unknown commit object"); my $parent = $co{'parent'}; my $parents = $co{'parents'}; # listref @@ -3727,25 +5501,29 @@ sub git_commit { $formats_nav .= '(merge: ' . join(' ', map { - $cgi->a({-href => href(action=>"commitdiff", + $cgi->a({-href => href(action=>"commit", hash=>$_)}, esc_html(substr($_, 0, 7))); } @$parents ) . ')'; } + if (gitweb_check_feature('patches')) { + $formats_nav .= " | " . + $cgi->a({-href => href(action=>"patch", -replay=>1)}, + "patch"); + } if (!defined $parent) { $parent = "--root"; } my @difftree; - if (@$parents <= 1) { - # difftree output is not printed for merges - open my $fd, "-|", git_cmd(), "diff-tree", '-r', "--no-commit-id", - @diff_opts, $parent, $hash, "--" - or die_error(undef, "Open git-diff-tree failed"); - @difftree = map { chomp; $_ } <$fd>; - close $fd or die_error(undef, "Reading git-diff-tree failed"); - } + open my $fd, "-|", git_cmd(), "diff-tree", '-r', "--no-commit-id", + @diff_opts, + (@$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; @@ -3755,8 +5533,6 @@ sub git_commit { my $refs = git_get_references(); my $ref = format_ref_marker($refs, $co{'id'}); - my $have_snapshot = gitweb_have_snapshot(); - git_header_html(undef, $expires); git_print_page_nav('commit', '', $hash, $co{'tree'}, $hash, @@ -3768,23 +5544,8 @@ sub git_commit { git_print_header_div('tree', esc_html($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=>$up)}, ".."); print "
\n"; - print "\n". - "" . - "" . - "\n"; - print "\n"; - print "\n"; + "
author" . esc_html($co{'author'}) . "
$ad{'rfc2822'}"; - if ($ad{'hour_local'} < 6) { - printf(" (%02d:%02d %s)", - $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); - } else { - printf(" (%02d:%02d %s)", - $ad{'hour_local'}, $ad{'minute_local'}, $ad{'tz_local'}); - } - print "
committer" . esc_html($co{'committer'}) . "
$cd{'rfc2822'}" . - sprintf(" (%02d:%02d %s)", $cd{'hour_local'}, $cd{'minute_local'}, $cd{'tz_local'}) . - "
\n"; + git_print_authorship_rows(\%co); print "\n"; print "" . "" . @@ -3795,9 +5556,9 @@ sub git_commit { "" . "\n"; @@ -3823,10 +5584,7 @@ sub git_commit { git_print_log($co{'comment'}); print "\n"; - if (@$parents <= 1) { - # do not output difftree/whatchanged for merges - git_difftree_body(\@difftree, $hash, $parent); - } + git_difftree_body(\@difftree, $hash, @$parents); git_footer_html(); } @@ -3841,35 +5599,35 @@ sub git_object { if ($hash || ($hash_base && !defined $file_name)) { my $object_id = $hash || $hash_base; - my $git_command = git_cmd_str(); - open my $fd, "-|", "$git_command cat-file -t $object_id 2>/dev/null" - or die_error('404 Not Found', "Object does not exist"); + open my $fd, "-|", quote_command( + git_cmd(), 'cat-file', '-t', $object_id) . ' 2> /dev/null' + or die_error(404, "Object does not exist"); $type = <$fd>; chomp $type; close $fd - or die_error('404 Not Found', "Object does not exist"); + or die_error(404, "Object does not exist"); # - hash_base and file_name } elsif ($hash_base && defined $file_name) { $file_name =~ s,/+$,,; system(git_cmd(), "cat-file", '-e', $hash_base) == 0 - or die_error('404 Not Found', "Base object does not exist"); + or die_error(404, "Base object does not exist"); # here errors should not hapen open my $fd, "-|", git_cmd(), "ls-tree", $hash_base, "--", $file_name - or die_error(undef, "Open git-ls-tree failed"); + or die_error(500, "Open git-ls-tree failed"); my $line = <$fd>; close $fd; #'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa panic.c' unless ($line && $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t/) { - die_error('404 Not Found', "File or directory for given base does not exist"); + die_error(404, "File or directory for given base does not exist"); } $type = $2; $hash = $3; } else { - die_error('404 Not Found', "Not enough information to find object"); + die_error(400, "Not enough information to find object"); } print $cgi->redirect(-uri => href(action=>$type, -full=>1, @@ -3893,13 +5651,13 @@ 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}/) { @@ -3908,28 +5666,28 @@ 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'}; @@ -3942,56 +5700,21 @@ 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"); - } - - # 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}$/ && - $hash_parent =~ m/^[0-9a-fA-F]{40}$/) { - $expires = '+1d'; - } + '-p', ($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"); + } - # 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"); git_header_html(undef, $expires); if (defined $hash_base && (my %co = parse_commit($hash_base))) { @@ -4017,7 +5740,7 @@ 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 @@ -4050,29 +5773,50 @@ sub git_blobdiff_plain { } sub git_commitdiff { - my $format = shift || 'html'; - $hash ||= $hash_base || "HEAD"; - my %co = parse_commit($hash); - if (!%co) { - die_error(undef, "Unknown commit object"); + my %params = @_; + my $format = $params{-format} || 'html'; + + my ($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) { + $formats_nav .= " | " . + $cgi->a({-href => href(action=>"patch", -replay=>1)}, + "patch"); + } - 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: ' . + ' (from'; + for (my $i = 0; $i < @{$co{'parents'}}; $i++) { + if ($co{'parents'}[$i] eq $hash_parent) { + $formats_nav .= ' parent ' . ($i+1); + last; + } + } + $formats_nav .= ': ' . $cgi->a({-href => href(action=>"commitdiff", hash=>$hash_parent)}, esc_html($hash_parent_short)) . @@ -4090,6 +5834,17 @@ sub git_commitdiff { ')'; } else { # merge commit + if ($hash_parent eq '--cc') { + $formats_nav .= ' | ' . + $cgi->a({-href => href(action=>"commitdiff", + hash=>$hash, hash_parent=>'-c')}, + 'combined'); + } else { # $hash_parent eq '-c' + $formats_nav .= ' | ' . + $cgi->a({-href => href(action=>"commitdiff", + hash=>$hash, hash_parent=>'--cc')}, + 'compact'); + } $formats_nav .= ' (merge: ' . join(' ', map { @@ -4101,8 +5856,11 @@ sub git_commitdiff { } } - 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' : $co{'parent'} || '--root'; } # read commitdiff @@ -4111,23 +5869,47 @@ sub git_commitdiff { if ($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 (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", '--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 @@ -4144,7 +5926,11 @@ 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 " | " . $snapshot_links; } print "
\n"; + git_print_authorship_rows(\%co); + print "
". + "
\n"; print "
\n"; if (@{$co{'comment'}} > 1) { print "
\n"; @@ -4163,26 +5949,37 @@ 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, \@difftree, $hash, + $use_parents ? @{$co{'parents'}} : $hash_parent); close $fd; print "
\n"; # class="page_body" git_footer_html(); @@ -4192,11 +5989,25 @@ TEXT print <$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 { @@ -4207,27 +6018,30 @@ sub git_history { $page = 0; } my $ftype; - my %co = parse_commit($hash_base); - if (!%co) { - die_error(undef, "Unknown commit object"); - } + my %co = parse_commit($hash_base) + or die_error(404, "Unknown commit object"); my $refs = git_get_references(); my $limit = sprintf("--max-count=%i", (100 * ($page+1))); + my @commitlist = parse_commits($hash_base, 101, (100 * $page), + $file_name, "--full-history") + or die_error(404, "No such file or directory on given branch"); + if (!defined $hash && defined $file_name) { - $hash = git_get_hash_by_path($hash_base, $file_name); + # some commits could have deleted file in question, + # and not have it in tree, but one of them has to have it + for (my $i = 0; $i <= @commitlist; $i++) { + $hash = git_get_hash_by_path($commitlist[$i]{'id'}, $file_name); + last if defined $hash; + } } if (defined $hash) { $ftype = git_get_type($hash); } - - 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"); + if (!defined $ftype) { + die_error(500, "Unknown type of object"); + } my $paging_nav = ''; if ($page > 0) { @@ -4236,54 +6050,44 @@ sub git_history { 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), + $cgi->a({-href => href(-replay=>1, page=>$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), + 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"; } - 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, + git_history_body(\@commitlist, 0, 99, $refs, $hash_base, $ftype, $next_link); git_footer_html(); } sub git_search { - my ($have_search) = gitweb_check_feature('search'); - if (!$have_search) { - die_error('403 Permission denied', "Permission denied"); - } + gitweb_check_feature('search') or die_error(403, "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) { $page = 0; @@ -4293,10 +6097,12 @@ sub git_search { if ($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"); - } + gitweb_check_feature('pickaxe') + or die_error(403, "Pickaxe is disabled"); + } + if ($searchtype eq 'grep') { + gitweb_check_feature('grep')[0] + or die_error(403, "Grep is disabled"); } git_header_html(); @@ -4310,100 +6116,63 @@ sub git_search { } elsif ($searchtype eq 'committer') { $greptype = "--committer="; } - open my $fd, "-|", git_cmd(), "rev-list", - ("--max-count=" . (100 * ($page+1))), - ($greptype . $searchtext), - $hash, "--" - or next; - my @revlist = map { chomp; $_ } <$fd>; - close $fd; + $greptype .= $searchtext; + my @commitlist = parse_commits($hash, 101, (100 * $page), undef, + $greptype, '--regexp-ignore-case', + $search_use_regexp ? '--extended-regexp' : '--fixed-strings'); my $paging_nav = ''; if ($page > 0) { $paging_nav .= $cgi->a({-href => href(action=>"search", hash=>$hash, - searchtext=>$searchtext, searchtype=>$searchtype)}, - "first"); + searchtext=>$searchtext, + searchtype=>$searchtype)}, + "first"); $paging_nav .= " ⋅ " . - $cgi->a({-href => href(action=>"search", hash=>$hash, - searchtext=>$searchtext, searchtype=>$searchtype, - page=>$page-1), - -accesskey => "p", -title => "Alt-p"}, "prev"); + $cgi->a({-href => href(-replay=>1, page=>$page-1), + -accesskey => "p", -title => "Alt-p"}, "prev"); } else { $paging_nav .= "first"; $paging_nav .= " ⋅ prev"; } - if ($#revlist >= (100 * ($page+1)-1)) { - $paging_nav .= " ⋅ " . - $cgi->a({-href => href(action=>"search", hash=>$hash, - searchtext=>$searchtext, searchtype=>$searchtype, - page=>$page+1), - -accesskey => "n", -title => "Alt-n"}, "next"); + 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"; } - my $next_link = ''; - if ($#revlist >= (100 * ($page+1)-1)) { - $next_link = - $cgi->a({-href => href(action=>"search", hash=>$hash, - searchtext=>$searchtext, searchtype=>$searchtype, - page=>$page+1), - -accesskey => "n", -title => "Alt-n"}, "next"); + + if ($#commitlist >= 100) { } git_print_page_nav('','', $hash,$co{'tree'},$hash, $paging_nav); git_print_header_div('commit', esc_html($co{'title'}), $hash); - git_search_grep_body(\@revlist, ($page * 100), $#revlist, $next_link); + git_search_grep_body(\@commitlist, 0, 99, $next_link); } if ($searchtype eq 'pickaxe') { git_print_page_nav('','', $hash,$co{'tree'},$hash); git_print_header_div('commit', esc_html($co{'title'}), $hash); - print "\n"; + print "
\n"; my $alternate = 1; - $/ = "\n"; - my $git_command = git_cmd_str(); - open my $fd, "-|", "$git_command rev-list $hash | " . - "$git_command diff-tree -r --stdin -S\'$searchtext\'"; + 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' : ()); 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 ($line =~ m/^([0-9a-fA-F]{40})$/){ + chomp $line; + next unless $line; + + my %set = parse_difftree_raw_line($line); + if (defined $set{'commit'}) { + # finish previous commit if (%co) { - if ($alternate) { - print "\n"; - } else { - print "\n"; - } - $alternate ^= 1; - print "\n" . - "\n" . - "\n" . "\n" . "\n"; } - %co = parse_commit($1); + + if ($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 "
$co{'age_string_date'}" . esc_html(chop_str($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") . @@ -4412,8 +6181,110 @@ sub git_search { print "
$co{'age_string_date'}$author" . + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), + -class => "list subject"}, + chop_and_escape_str($co{'title'}, 50) . "
"); + } elsif (defined $set{'to_id'}) { + next if ($set{'to_id'} =~ m/^0{40}$/); + + print $cgi->a({-href => href(action=>"blob", hash_base=>$co{'id'}, + hash=>$set{'to_id'}, file_name=>$set{'to_file'}), + -class => "list"}, + "" . esc_path($set{'file'}) . "") . + "
\n"; + } + } + close $fd; + + # finish last commit (warning: repetition!) + if (%co) { + print "		" . + $cgi->a({-href => href(action=>"commit", hash=>$co{'id'})}, "commit") . + " | " . + $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, hash_base=>$co{'id'})}, "tree"); + print "
\n"; + } + + if ($searchtype eq 'grep') { + git_print_page_nav('','', $hash,$co{'tree'},$hash); + git_print_header_div('commit', esc_html($co{'title'}), $hash); + + print "\n"; + my $alternate = 1; + my $matches = 0; + local $/ = "\n"; + open my $fd, "-|", git_cmd(), 'grep', '-n', + $search_use_regexp ? ('-E', '-i') : '-F', + $searchtext, $co{'tree'}; + my $lastfile = ''; + while (my $line = <$fd>) { + chomp $line; + my ($file, $lno, $ltext, $binary); + last if ($matches++ > 1000); + if ($line =~ /^Binary file (.+) matches$/) { + $file = $1; + $binary = 1; + } else { + (undef, $file, $lno, $ltext) = split(/:/, $line, 4); + } + if ($file ne $lastfile) { + $lastfile and print "\n"; + if ($alternate++) { + print "\n"; + } else { + print "\n"; + } + print "\n"; + if ($matches > 1000) { + print "
Too many matches, listing trimmed
\n"; } + } else { + print "
No matches found
\n"; } close $fd; @@ -4426,21 +6297,40 @@ 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.
+
The commit messages and authorship information will be scanned for the given pattern.
+EOT + 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 string.
+
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 string.
+
Name and e-mail of the committer and date of commit will be scanned for the given pattern.
EOT - my ($have_pickaxe) = gitweb_check_feature('pickaxe'); + my $have_pickaxe = gitweb_check_feature('pickaxe'); if ($have_pickaxe) { print <pickaxe
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"; @@ -4457,26 +6347,33 @@ sub git_shortlog { } 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 = $hash; + if (defined $hash_parent) { + $commit_hash = "$hash_parent..$hash"; + } + my @commitlist = parse_commits($commit_hash, 101, (100 * $page)); - my $paging_nav = format_paging_nav('shortlog', $hash, $head, $page, $#revlist); + my $paging_nav = format_paging_nav('shortlog', $hash, $head, $page, $#commitlist >= 100); my $next_link = ''; - if ($#revlist >= (100 * ($page+1)-1)) { + if ($#commitlist >= 100) { $next_link = - $cgi->a({-href => href(action=>"shortlog", hash=>$hash, page=>$page+1), - -title => "Alt-n"}, "next"); + $cgi->a({-href => href(-replay=>1, page=>$page+1), + -accesskey => "n", -title => "Alt-n"}, "next"); + } + my $patch_max = gitweb_check_feature('patches'); + if ($patch_max) { + 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('shortlog','', $hash,$hash,$hash, $paging_nav); git_print_header_div('summary', $project); - git_shortlog_body(\@revlist, ($page * 100), $#revlist, $refs, $next_link); + git_shortlog_body(\@commitlist, 0, 99, $refs, $next_link); git_footer_html(); } @@ -4486,21 +6383,17 @@ sub git_shortlog { sub git_feed { my $format = shift || 'atom'; - my ($have_blame) = gitweb_check_feature('blame'); + my $have_blame = gitweb_check_feature('blame'); # Atom: http://www.atomenabled.org/developers/syndication/ # RSS: http://www.notestips.com/80256B3A007F2692/1/NAMO5P9UPQ if ($format ne 'rss' && $format ne 'atom') { - die_error(undef, "Unknown web feed format"); + die_error(400, "Unknown web feed format"); } # log/feed of current (HEAD) branch, log of given branch, history of file/directory my $head = $hash || 'HEAD'; - open my $fd, "-|", git_cmd(), "rev-list", "--max-count=150", - $head, "--", (defined $file_name ? $file_name : ()) - or die_error(undef, "Open git-rev-list failed"); - my @revlist = map { chomp; $_ } <$fd>; - close $fd or die_error(undef, "Reading git-rev-list failed"); + my @commitlist = parse_commits($head, 150, 0, $file_name); my %latest_commit; my %latest_date; @@ -4510,9 +6403,27 @@ sub git_feed { # browser (feed reader) prefers text/xml $content_type = 'text/xml'; } - if (defined($revlist[0])) { - %latest_commit = parse_commit($revlist[0]); - %latest_date = parse_date($latest_commit{'author_epoch'}); + if (defined($commitlist[0])) { + %latest_commit = %{$commitlist[0]}; + my $latest_epoch = $latest_commit{'committer_epoch'}; + %latest_date = parse_date($latest_epoch); + 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) { + print $cgi->header( + -type => $content_type, + -charset => 'utf-8', + -last_modified => $latest_date{'rfc2822'}, + -status => '304 Not Modified'); + return; + } + } print $cgi->header( -type => $content_type, -charset => 'utf-8', @@ -4571,7 +6482,24 @@ XML print "$title\n" . "$alt_url\n" . "$descr\n" . - "en\n"; + "en\n" . + # project owner is responsible for 'editorial' content + "$owner\n"; + if (defined $logo || defined $favicon) { + # prefer the logo to the favicon, since RSS + # doesn't allow both + my $img = esc_url($logo || $favicon); + print "\n" . + "$img\n" . + "$title\n" . + "$alt_url\n" . + "\n"; + } + if (%latest_date) { + print "$latest_date{'rfc2822'}\n"; + print "$latest_date{'rfc2822'}\n"; + } + print "gitweb v.$version/$git_version\n"; } elsif ($format eq 'atom') { print < @@ -4598,12 +6526,13 @@ XML } else { print "$latest_date{'iso-8601'}\n"; } + print "gitweb\n"; } # contents - for (my $i = 0; $i <= $#revlist; $i++) { - my $commit = $revlist[$i]; - my %co = parse_commit($commit); + 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 - $co{'author_epoch'}) > 48*60*60)) { last; @@ -4611,15 +6540,16 @@ XML my %cd = parse_date($co{'author_epoch'}); # get list of changed files - open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, - $co{'parent'}, $co{'id'}, "--", (defined $file_name ? $file_name : ()) + 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 element (entry, item) - my $co_url = href(-full=>1, action=>"commit", hash=>$commit); + my $co_url = href(-full=>1, action=>"commitdiff", hash=>$commit); if ($format eq 'rss') { print "\n" . "" . esc_html($co{'title'}) . "\n" . @@ -4702,7 +6632,7 @@ XML # end of feed if ($format eq 'rss') { print "\n\n"; - } elsif ($format eq 'atom') { + } elsif ($format eq 'atom') { print "\n"; } } @@ -4718,7 +6648,11 @@ sub git_atom { sub git_opml { my @list = git_get_projects_list(); - print $cgi->header(-type => 'text/xml', -charset => 'utf-8'); + print $cgi->header( + -type => 'text/xml', + -charset => 'utf-8', + -content_disposition => 'inline; filename="opml.xml"'); + print < @@ -4742,8 +6676,8 @@ 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 <
". + $cgi->a({-href => href(action=>"blob", hash=>$co{'hash'}, + file_name=>"$file"), + -class => "list"}, esc_path($file)); + print "\n"; + $lastfile = $file; + } + if ($binary) { + print "
Binary file
\n"; + } else { + $ltext = untabify($ltext); + if ($ltext =~ m/^(.*)($search_regexp)(.*)$/i) { + $ltext = esc_html($1, -nbsp=>1); + $ltext .= ''; + $ltext .= esc_html($2, -nbsp=>1); + $ltext .= ''; + $ltext .= esc_html($3, -nbsp=>1); + } else { + $ltext = esc_html($ltext, -nbsp=>1); + } + print "
" . + $cgi->a({-href => href(action=>"blob", hash=>$co{'hash'}, + file_name=>"$file").'#l'.$lno, + -class => "linenr"}, sprintf('%4i', $lno)) + . ' ' . $ltext . "
\n"; + } + } + if ($lastfile) { + print "