diff options
Diffstat (limited to 'gitweb')
| -rw-r--r-- | gitweb/INSTALL | 21 | ||||
| -rwxr-xr-x | gitweb/gitweb.perl | 516 |
2 files changed, 387 insertions, 150 deletions
diff --git a/gitweb/INSTALL b/gitweb/INSTALL index 26967e201..18c9ce35e 100644 --- a/gitweb/INSTALL +++ b/gitweb/INSTALL @@ -166,6 +166,27 @@ Gitweb repositories shows repositories only if this file exists in its object database (if directory has the magic file named $export_ok). +- Finally, it is possible to specify an arbitrary perl subroutine that + will be called for each project to determine if it can be exported. + The subroutine receives an absolute path to the project as its only + parameter. + + For example, if you use mod_perl to run the script, and have dumb + http protocol authentication configured for your repositories, you + can use the following hook to allow access only if the user is + authorized to read the files: + + $export_auth_hook = sub { + use Apache2::SubRequest (); + use Apache2::Const -compile => qw(HTTP_OK); + my $path = "$_[0]/HEAD"; + my $r = Apache2::RequestUtil->request; + my $sub = $r->lookup_file($path); + return $sub->filename eq $path + && $sub->status == Apache2::Const::HTTP_OK; + }; + + Generating projects list using gitweb ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl index cc6edbede..933e13738 100755 --- a/gitweb/gitweb.perl +++ b/gitweb/gitweb.perl @@ -29,7 +29,9 @@ our $my_uri = $cgi->url(-absolute => 1); # if we're called with PATH_INFO, we have to strip that # from the URL to find our real URL -if (my $path_info = $ENV{"PATH_INFO"}) { +# we make $path_info global because it's also used later on +our $path_info = $ENV{"PATH_INFO"}; +if ($path_info) { $my_url =~ s,\Q$path_info\E$,,; $my_uri =~ s,\Q$path_info\E$,,; } @@ -93,6 +95,11 @@ our $default_projects_order = "project"; # (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 $strict_export = "++GITWEB_STRICT_EXPORT++"; @@ -398,7 +405,8 @@ sub check_head_link { sub check_export_ok { my ($dir) = @_; return (check_head_link($dir) && - (!$export_ok || -e "$dir/$export_ok")); + (!$export_ok || -e "$dir/$export_ok") && + (!$export_auth_hook || $export_auth_hook->($dir))); } # process alternate names for backward compatibility @@ -428,34 +436,258 @@ $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", +); +our %cgi_param_mapping = @cgi_param_mapping; + +# we will also need to know the possible actions, for validation +our %actions = ( + "blame" => \&git_blame, + "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 $project + "opml" => \&git_opml, + "project_list" => \&git_project_list, + "project_index" => \&git_project_index, +); + +# finally, we have the hash of allowed extra_options for the commands that +# allow them +our %allowed_options = ( + "--no-merges" => [ qw(rss atom log shortlog history) ], +); + +# fill %input_params with the CGI parameters. All values except for 'opt' +# should be single values, but opt can be an array. We should probably +# build an array of parameters that can be multi-valued, but since for the time +# being it's only this one, we just single it out +while (my ($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; + my $sfx; + $hash =~ s/(\Q$opt{'suffix'}\E|\Q.$fmt\E)$//; + next unless $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\.\-_]/) { + 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(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(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(400, "Invalid file parent parameter"); @@ -463,44 +695,41 @@ if (defined $file_parent) { } # parameters which are refnames -our $hash = $cgi->param('h'); +our $hash = $input_params{'hash'}; if (defined $hash) { if (!validate_refname($hash)) { 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(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(400, "Invalid hash base parameter"); } } -my %allowed_options = ( - "--no-merges" => [ qw(rss atom log shortlog history) ], -); - -our @extra_options = $cgi->param('opt'); -if (defined @extra_options) { - 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 @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(400, "Invalid hash parent base parameter"); @@ -508,23 +737,23 @@ if (defined $hash_parent_base) { } # other parameters -our $page = $cgi->param('pg'); +our $page = $input_params{'page'}; if (defined $page) { if ($page =~ m/[^0-9]/) { die_error(400, "Invalid page parameter"); } } -our $searchtype = $cgi->param('st'); +our $searchtype = $input_params{'searchtype'}; if (defined $searchtype) { if ($searchtype =~ m/[^a-z]/) { die_error(400, "Invalid searchtype parameter"); } } -our $search_use_regexp = $cgi->param('sr'); +our $search_use_regexp = $input_params{'search_use_regexp'}; -our $searchtext = $cgi->param('s'); +our $searchtext = $input_params{'searchtext'}; our $search_regexp; if (defined $searchtext) { if (length($searchtext) < 2) { @@ -533,86 +762,15 @@ if (defined $searchtext) { $search_regexp = $search_use_regexp ? $searchtext : quotemeta $searchtext; } -# 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; - $path_info =~ s,^\Q$project\E/*,,; - my ($refname, $pathname) = split(/:/, $path_info, 2); - if (defined $pathname) { - # we got "project.git/branch:filename" or "project.git/branch:dir/" - # we could use git_get_type(branch:pathname), but it needs $git_dir - $pathname =~ s,^/+,,; - if (!$pathname || substr($pathname, -1) eq "/") { - $action ||= "tree"; - $pathname =~ s,/$,,; - } else { - $action ||= "blob_plain"; - } - $hash_base ||= validate_refname($refname); - $file_name ||= validate_pathname($pathname); - } elsif (defined $refname) { - # we got "project.git/branch" - $action ||= "shortlog"; - $hash ||= validate_refname($refname); - } -} -evaluate_path_info(); - # path to the current git repository our $git_dir; $git_dir = "$projectroot/$project" if $project; -# dispatch -my %actions = ( - "blame" => \&git_blame, - "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, -); +# list of supported snapshot formats +our @snapshot_fmts = gitweb_check_feature('snapshot'); +@snapshot_fmts = filter_snapshot_fmts(@snapshot_fmts); +# dispatch if (!defined $action) { if (defined $hash) { $action = git_get_type($hash); @@ -642,55 +800,96 @@ sub href (%) { # default is to use -absolute url() i.e. $my_uri my $href = $params{-full} ? $my_url : $my_uri; - # XXX: Warning: If you touch this, check the search form for updating, - # too. - - my @mapping = ( - project => "p", - action => "a", - file_name => "f", - file_parent => "fp", - hash => "h", - hash_parent => "hp", - hash_base => "hb", - hash_parent_base => "hpb", - page => "pg", - order => "o", - searchtext => "s", - searchtype => "st", - snapshot_format => "sf", - extra_options => "opt", - search_use_regexp => "sr", - ); - my %mapping = @mapping; - $params{'project'} = $project unless exists $params{'project'}; if ($params{-replay}) { - while (my ($name, $symbol) = each %mapping) { + while (my ($name, $symbol) = each %cgi_param_mapping) { if (!exists $params{$name}) { - # to allow for multivalued params we use arrayref form - $params{$name} = [ $cgi->param($symbol) ]; + $params{$name} = $input_params{$name}; } } } my ($use_pathinfo) = gitweb_check_feature('pathinfo'); if ($use_pathinfo) { - # use PATH_INFO for project name + # 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'}) if defined $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 + delete $params{'file_parent'} if $params{'file_parent'} eq $params{'file_name'}; + if (defined $params{'file_parent'} && $params{'file_parent'} !~ /\.\./) { + $href .= ":/".esc_url($params{'file_parent'}); + delete $params{'file_parent'}; + } + $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}) { if (ref($params{$name}) eq "ARRAY") { foreach my $par (@{$params{$name}}) { @@ -710,6 +909,24 @@ 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 $input = shift || return undef; @@ -1495,8 +1712,6 @@ sub format_diff_line { # linked. Pass the hash of the tree/commit to snapshot. sub format_snapshot_links { my ($hash) = @_; - my @snapshot_fmts = gitweb_check_feature('snapshot'); - @snapshot_fmts = filter_snapshot_fmts(@snapshot_fmts); my $num_fmts = @snapshot_fmts; if ($num_fmts > 1) { # A parenthesized list of links bearing format names. @@ -1805,7 +2020,10 @@ sub git_get_project_ctags { my $ctags = {}; $git_dir = "$projectroot/$path"; - foreach (<$git_dir/ctags/*>) { + unless (opendir D, "$git_dir/ctags") { + return $ctags; + } + foreach (grep { -f $_ } map { "$git_dir/ctags/$_" } readdir(D)) { open CT, $_ or next; my $val = <CT>; chomp $val; @@ -1813,6 +2031,7 @@ sub git_get_project_ctags { my $ctag = $_; $ctag =~ s#.*/##; $ctags->{$ctag} = $val; } + closedir D; $ctags; } @@ -4126,7 +4345,7 @@ sub git_search_grep_body { ## actions sub git_project_list { - my $order = $cgi->param('o'); + my $order = $input_params{'order'}; if (defined $order && $order !~ m/none|project|descr|owner|age/) { die_error(400, "Unknown order parameter"); } @@ -4154,7 +4373,7 @@ sub git_project_list { } sub git_forks { - my $order = $cgi->param('o'); + my $order = $input_params{'order'}; if (defined $order && $order !~ m/none|project|descr|owner|age/) { die_error(400, "Unknown order parameter"); } @@ -4699,20 +4918,17 @@ sub git_tree { } sub git_snapshot { - my @supported_fmts = gitweb_check_feature('snapshot'); - @supported_fmts = filter_snapshot_fmts(@supported_fmts); - - my $format = $cgi->param('sf'); - if (!@supported_fmts) { + my $format = $input_params{'snapshot_format'}; + if (!@snapshot_fmts) { die_error(403, "Snapshots not allowed"); } # default to first supported snapshot format - $format ||= $supported_fmts[0]; + $format ||= $snapshot_fmts[0]; if ($format !~ m/^[a-z0-9]+$/) { die_error(400, "Invalid snapshot format parameter"); } elsif (!exists($known_snapshot_formats{$format})) { die_error(400, "Unknown snapshot format"); - } elsif (!grep($_ eq $format, @supported_fmts)) { + } elsif (!grep($_ eq $format, @snapshot_fmts)) { die_error(403, "Unsupported snapshot format"); } |