if (length($searchtext) < 2) {
die_error(403, "At least two characters are required for search parameter");
}
- $search_regexp = $search_use_regexp ? $searchtext : quotemeta $searchtext;
+ if ($search_use_regexp) {
+ $search_regexp = $searchtext;
+ if (!eval { qr/$search_regexp/; 1; }) {
+ (my $error = $@) =~ s/ at \S+ line \d+.*\n?//;
+ die_error(400, "Invalid search regexp '$search_regexp'",
+ esc_html($error));
+ }
+ } else {
+ $search_regexp = quotemeta $searchtext;
+ }
}
}
}
}
+# Highlight selected fragments of string, using given CSS class,
+# and escape HTML. It is assumed that fragments do not overlap.
+# Regions are passed as list of pairs (array references).
+#
+# Example: esc_html_hl_regions("foobar", "mark", [ 0, 3 ]) returns
+# '<span class="mark">foo</span>bar'
+sub esc_html_hl_regions {
+ my ($str, $css_class, @sel) = @_;
+ my %opts = grep { ref($_) ne 'ARRAY' } @sel;
+ @sel = grep { ref($_) eq 'ARRAY' } @sel;
+ return esc_html($str, %opts) unless @sel;
+
+ my $out = '';
+ my $pos = 0;
+
+ for my $s (@sel) {
+ my ($begin, $end) = @$s;
+
+ # Don't create empty <span> elements.
+ next if $end <= $begin;
+
+ my $escaped = esc_html(substr($str, $begin, $end - $begin),
+ %opts);
+
+ $out .= esc_html(substr($str, $pos, $begin - $pos), %opts)
+ if ($begin - $pos > 0);
+ $out .= $cgi->span({-class => $css_class}, $escaped);
+
+ $pos = $end;
+ }
+ $out .= esc_html(substr($str, $pos), %opts)
+ if ($pos < length($str));
+
+ return $out;
+}
+
+# return positions of beginning and end of each match
+sub matchpos_list {
+ my ($str, $regexp) = @_;
+ return unless (defined $str && defined $regexp);
+
+ my @matches;
+ while ($str =~ /$regexp/g) {
+ push @matches, [$-[0], $+[0]];
+ }
+ return @matches;
+}
+
+# highlight match (if any), and escape HTML
+sub esc_html_match_hl {
+ my ($str, $regexp) = @_;
+ return esc_html($str) unless defined $regexp;
+
+ my @matches = matchpos_list($str, $regexp);
+ return esc_html($str) unless @matches;
+
+ return esc_html_hl_regions($str, 'match', @matches);
+}
+
+
+# highlight match (if any) of shortened string, and escape HTML
+sub esc_html_match_hl_chopped {
+ my ($str, $chopped, $regexp) = @_;
+ return esc_html_match_hl($str, $regexp) unless defined $chopped;
+
+ my @matches = matchpos_list($str, $regexp);
+ return esc_html($chopped) unless @matches;
+
+ # filter matches so that we mark chopped string
+ my $tail = "... "; # see chop_str
+ unless ($chopped =~ s/\Q$tail\E$//) {
+ $tail = '';
+ }
+ my $chop_len = length($chopped);
+ my $tail_len = length($tail);
+ my @filtered;
+
+ for my $m (@matches) {
+ if ($m->[0] > $chop_len) {
+ push @filtered, [ $chop_len, $chop_len + $tail_len ] if ($tail_len > 0);
+ last;
+ } elsif ($m->[1] > $chop_len) {
+ push @filtered, [ $m->[0], $chop_len + $tail_len ];
+ last;
+ }
+ push @filtered, $m;
+ }
+
+ return esc_html_hl_regions($chopped . $tail, 'match', @filtered);
+}
+
## ----------------------------------------------------------------------
## functions returning short strings
}
# process patch (diff) line (not to be used for diff headers),
-# returning class and HTML-formatted (but not wrapped) line
-sub process_diff_line {
- my $line = shift;
- my ($from, $to) = @_;
-
- my $diff_class = diff_line_class($line, $from, $to);
-
- chomp $line;
- $line = untabify($line);
+# returning HTML-formatted (but not wrapped) line.
+# If the line is passed as a reference, it is treated as HTML and not
+# esc_html()'ed.
+sub format_diff_line {
+ my ($line, $diff_class, $from, $to) = @_;
+
+ if (ref($line)) {
+ $line = $$line;
+ } else {
+ chomp $line;
+ $line = untabify($line);
- if ($from && $to && $line =~ m/^\@{2} /) {
- $line = format_unidiff_chunk_header($line, $from, $to);
- return $diff_class, $line;
+ if ($from && $to && $line =~ m/^\@{2} /) {
+ $line = format_unidiff_chunk_header($line, $from, $to);
+ } elsif ($from && $to && $line =~ m/^\@{3}/) {
+ $line = format_cc_diff_chunk_header($line, $from, $to);
+ } else {
+ $line = esc_html($line, -nbsp=>1);
+ }
+ }
- } elsif ($from && $to && $line =~ m/^\@{3}/) {
- $line = format_cc_diff_chunk_header($line, $from, $to);
- return $diff_class, $line;
+ my $diff_classes = "diff";
+ $diff_classes .= " $diff_class" if ($diff_class);
+ $line = "<div class=\"$diff_classes\">$line</div>\n";
- }
- return $diff_class, esc_html($line, -nbsp=>1);
+ return $line;
}
# Generates undef or something like "_snapshot_" or "snapshot (_tbz2_ _zip_)",
sub search_projects_list {
my ($projlist, %opts) = @_;
my $tagfilter = $opts{'tagfilter'};
- my $searchtext = $opts{'searchtext'};
+ my $search_re = $opts{'search_regexp'};
return @$projlist
- unless ($tagfilter || $searchtext);
+ unless ($tagfilter || $search_re);
+ # searching projects require filling to be run before it;
+ fill_project_list_info($projlist,
+ $tagfilter ? 'ctags' : (),
+ $search_re ? ('path', 'descr') : ());
my @projects;
PROJECT:
foreach my $pr (@$projlist) {
grep { lc($_) eq lc($tagfilter) } keys %{$pr->{'ctags'}};
}
- if ($searchtext) {
+ if ($search_re) {
next unless
- $pr->{'path'} =~ /$searchtext/ ||
- $pr->{'descr_long'} =~ /$searchtext/;
+ $pr->{'path'} =~ /$search_re/ ||
+ $pr->{'descr_long'} =~ /$search_re/;
}
push @projects, $pr;
print "</table>\n";
}
-sub print_sidebyside_diff_chunk {
- my @chunk = @_;
+# Print context lines and then rem/add lines in a side-by-side manner.
+sub print_sidebyside_diff_lines {
+ my ($ctx, $rem, $add) = @_;
+
+ # print context block before add/rem block
+ if (@$ctx) {
+ print join '',
+ '<div class="chunk_block ctx">',
+ '<div class="old">',
+ @$ctx,
+ '</div>',
+ '<div class="new">',
+ @$ctx,
+ '</div>',
+ '</div>';
+ }
+
+ if (!@$add) {
+ # pure removal
+ print join '',
+ '<div class="chunk_block rem">',
+ '<div class="old">',
+ @$rem,
+ '</div>',
+ '</div>';
+ } elsif (!@$rem) {
+ # pure addition
+ print join '',
+ '<div class="chunk_block add">',
+ '<div class="new">',
+ @$add,
+ '</div>',
+ '</div>';
+ } else {
+ print join '',
+ '<div class="chunk_block chg">',
+ '<div class="old">',
+ @$rem,
+ '</div>',
+ '<div class="new">',
+ @$add,
+ '</div>',
+ '</div>';
+ }
+}
+
+# Print context lines and then rem/add lines in inline manner.
+sub print_inline_diff_lines {
+ my ($ctx, $rem, $add) = @_;
+
+ print @$ctx, @$rem, @$add;
+}
+
+# Format removed and added line, mark changed part and HTML-format them.
+# Implementation is based on contrib/diff-highlight
+sub format_rem_add_lines_pair {
+ my ($rem, $add) = @_;
+
+ # We need to untabify lines before split()'ing them;
+ # otherwise offsets would be invalid.
+ chomp $rem;
+ chomp $add;
+ $rem = untabify($rem);
+ $add = untabify($add);
+
+ my @rem = split(//, $rem);
+ my @add = split(//, $add);
+ my ($esc_rem, $esc_add);
+ # Ignore +/- character, thus $prefix_len is set to 1.
+ my ($prefix_len, $suffix_len) = (1, 0);
+ my ($prefix_has_nonspace, $suffix_has_nonspace);
+
+ my $shorter = (@rem < @add) ? @rem : @add;
+ while ($prefix_len < $shorter) {
+ last if ($rem[$prefix_len] ne $add[$prefix_len]);
+
+ $prefix_has_nonspace = 1 if ($rem[$prefix_len] !~ /\s/);
+ $prefix_len++;
+ }
+
+ while ($prefix_len + $suffix_len < $shorter) {
+ last if ($rem[-1 - $suffix_len] ne $add[-1 - $suffix_len]);
+
+ $suffix_has_nonspace = 1 if ($rem[-1 - $suffix_len] !~ /\s/);
+ $suffix_len++;
+ }
+
+ # Mark lines that are different from each other, but have some common
+ # part that isn't whitespace. If lines are completely different, don't
+ # mark them because that would make output unreadable, especially if
+ # diff consists of multiple lines.
+ if ($prefix_has_nonspace || $suffix_has_nonspace) {
+ $esc_rem = esc_html_hl_regions($rem, 'marked',
+ [$prefix_len, @rem - $suffix_len], -nbsp=>1);
+ $esc_add = esc_html_hl_regions($add, 'marked',
+ [$prefix_len, @add - $suffix_len], -nbsp=>1);
+ } else {
+ $esc_rem = esc_html($rem, -nbsp=>1);
+ $esc_add = esc_html($add, -nbsp=>1);
+ }
+
+ return format_diff_line(\$esc_rem, 'rem'),
+ format_diff_line(\$esc_add, 'add');
+}
+
+# HTML-format diff context, removed and added lines.
+sub format_ctx_rem_add_lines {
+ my ($ctx, $rem, $add, $is_combined) = @_;
+ my (@new_ctx, @new_rem, @new_add);
+
+ # Highlight if every removed line has a corresponding added line.
+ # Combined diffs are not supported at this moment.
+ if (!$is_combined && @$add > 0 && @$add == @$rem) {
+ for (my $i = 0; $i < @$add; $i++) {
+ my ($line_rem, $line_add) = format_rem_add_lines_pair(
+ $rem->[$i], $add->[$i]);
+ push @new_rem, $line_rem;
+ push @new_add, $line_add;
+ }
+ } else {
+ @new_rem = map { format_diff_line($_, 'rem') } @$rem;
+ @new_add = map { format_diff_line($_, 'add') } @$add;
+ }
+
+ @new_ctx = map { format_diff_line($_, 'ctx') } @$ctx;
+
+ return (\@new_ctx, \@new_rem, \@new_add);
+}
+
+# Print context lines and then rem/add lines.
+sub print_diff_lines {
+ my ($ctx, $rem, $add, $diff_style, $is_combined) = @_;
+
+ ($ctx, $rem, $add) = format_ctx_rem_add_lines($ctx, $rem, $add,
+ $is_combined);
+
+ if ($diff_style eq 'sidebyside' && !$is_combined) {
+ print_sidebyside_diff_lines($ctx, $rem, $add);
+ } else {
+ # default 'inline' style and unknown styles
+ print_inline_diff_lines($ctx, $rem, $add);
+ }
+}
+
+sub print_diff_chunk {
+ my ($diff_style, $is_combined, $from, $to, @chunk) = @_;
my (@ctx, @rem, @add);
+ # The class of the previous line.
+ my $prev_class = '';
+
return unless @chunk;
# incomplete last line might be among removed or added lines,
# print chunk headers
if ($class && $class eq 'chunk_header') {
- print $line;
+ print format_diff_line($line, $class, $from, $to);
next;
}
- ## print from accumulator when type of class of lines change
- # empty contents block on start rem/add block, or end of chunk
- if (@ctx && (!$class || $class eq 'rem' || $class eq 'add')) {
- print join '',
- '<div class="chunk_block ctx">',
- '<div class="old">',
- @ctx,
- '</div>',
- '<div class="new">',
- @ctx,
- '</div>',
- '</div>';
- @ctx = ();
- }
- # empty add/rem block on start context block, or end of chunk
- if ((@rem || @add) && (!$class || $class eq 'ctx')) {
- if (!@add) {
- # pure removal
- print join '',
- '<div class="chunk_block rem">',
- '<div class="old">',
- @rem,
- '</div>',
- '</div>';
- } elsif (!@rem) {
- # pure addition
- print join '',
- '<div class="chunk_block add">',
- '<div class="new">',
- @add,
- '</div>',
- '</div>';
- } else {
- # assume that it is change
- print join '',
- '<div class="chunk_block chg">',
- '<div class="old">',
- @rem,
- '</div>',
- '<div class="new">',
- @add,
- '</div>',
- '</div>';
- }
- @rem = @add = ();
+ ## print from accumulator when have some add/rem lines or end
+ # of chunk (flush context lines), or when have add and rem
+ # lines and new block is reached (otherwise add/rem lines could
+ # be reordered)
+ if (!$class || ((@rem || @add) && $class eq 'ctx') ||
+ (@rem && @add && $class ne $prev_class)) {
+ print_diff_lines(\@ctx, \@rem, \@add,
+ $diff_style, $is_combined);
+ @ctx = @rem = @add = ();
}
## adding lines to accumulator
if ($class eq 'ctx') {
push @ctx, $line;
}
+
+ $prev_class = $class;
}
}
next PATCH if ($patch_line =~ m/^diff /);
- my ($class, $line) = process_diff_line($patch_line, \%from, \%to);
- my $diff_classes = "diff";
- $diff_classes .= " $class" if ($class);
- $line = "<div class=\"$diff_classes\">$line</div>\n";
+ my $class = diff_line_class($patch_line, \%from, \%to);
- if ($diff_style eq 'sidebyside' && !$is_combined) {
- if ($class eq 'chunk_header') {
- print_sidebyside_diff_chunk(@chunk);
- @chunk = ( [ $class, $line ] );
- } else {
- push @chunk, [ $class, $line ];
- }
- } else {
- # default 'inline' style and unknown styles
- print $line;
+ if ($class eq 'chunk_header') {
+ print_diff_chunk($diff_style, $is_combined, \%from, \%to, @chunk);
+ @chunk = ();
}
+
+ push @chunk, [ $class, $patch_line ];
}
} continue {
if (@chunk) {
- print_sidebyside_diff_chunk(@chunk);
+ print_diff_chunk($diff_style, $is_combined, \%from, \%to, @chunk);
@chunk = ();
}
print "</div>\n"; # class="patch"
# . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
sub git_project_search_form {
- my ($searchtext, $search_use_regexp);
+ my ($searchtext, $search_use_regexp) = @_;
my $limit = '';
if ($project_filter) {
print "</div>\n";
}
-# fills project list info (age, description, owner, category, forks)
+# entry for given @keys needs filling if at least one of keys in list
+# is not present in %$project_info
+sub project_info_needs_filling {
+ my ($project_info, @keys) = @_;
+
+ # return List::MoreUtils::any { !exists $project_info->{$_} } @keys;
+ foreach my $key (@keys) {
+ if (!exists $project_info->{$key}) {
+ return 1;
+ }
+ }
+ return;
+}
+
+# fills project list info (age, description, owner, category, forks, etc.)
# for each project in the list, removing invalid projects from
-# returned list
+# returned list, or fill only specified info.
+#
+# Invalid projects are removed from the returned list if and only if you
+# ask 'age' or 'age_string' to be filled, because they are the only fields
+# that run unconditionally git command that requires repository, and
+# therefore do always check if project repository is invalid.
+#
+# USAGE:
+# * fill_project_list_info(\@project_list, 'descr_long', 'ctags')
+# ensures that 'descr_long' and 'ctags' fields are filled
+# * @project_list = fill_project_list_info(\@project_list)
+# ensures that all fields are filled (and invalid projects removed)
+#
# NOTE: modifies $projlist, but does not remove entries from it
sub fill_project_list_info {
- my $projlist = shift;
+ my ($projlist, @wanted_keys) = @_;
my @projects;
+ my $filter_set = sub { return @_; };
+ if (@wanted_keys) {
+ my %wanted_keys = map { $_ => 1 } @wanted_keys;
+ $filter_set = sub { return grep { $wanted_keys{$_} } @_; };
+ }
my $show_ctags = gitweb_check_feature('ctags');
PROJECT:
foreach my $pr (@$projlist) {
- my (@activity) = git_get_last_activity($pr->{'path'});
- unless (@activity) {
- next PROJECT;
+ if (project_info_needs_filling($pr, $filter_set->('age', 'age_string'))) {
+ my (@activity) = git_get_last_activity($pr->{'path'});
+ unless (@activity) {
+ next PROJECT;
+ }
+ ($pr->{'age'}, $pr->{'age_string'}) = @activity;
}
- ($pr->{'age'}, $pr->{'age_string'}) = @activity;
- if (!defined $pr->{'descr'}) {
+ if (project_info_needs_filling($pr, $filter_set->('descr', 'descr_long'))) {
my $descr = git_get_project_description($pr->{'path'}) || "";
$descr = to_utf8($descr);
$pr->{'descr_long'} = $descr;
$pr->{'descr'} = chop_str($descr, $projects_list_description_width, 5);
}
- if (!defined $pr->{'owner'}) {
+ if (project_info_needs_filling($pr, $filter_set->('owner'))) {
$pr->{'owner'} = git_get_project_owner("$pr->{'path'}") || "";
}
- if ($show_ctags) {
+ if ($show_ctags &&
+ project_info_needs_filling($pr, $filter_set->('ctags'))) {
$pr->{'ctags'} = git_get_project_ctags($pr->{'path'});
}
- if ($projects_list_group_categories && !defined $pr->{'category'}) {
+ if ($projects_list_group_categories &&
+ project_info_needs_filling($pr, $filter_set->('category'))) {
my $cat = git_get_project_category($pr->{'path'}) ||
$project_list_default_category;
$pr->{'category'} = to_utf8($cat);
print "</td>\n";
}
print "<td>" . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"summary"),
- -class => "list"}, esc_html($pr->{'path'})) . "</td>\n" .
+ -class => "list"},
+ esc_html_match_hl($pr->{'path'}, $search_regexp)) .
+ "</td>\n" .
"<td>" . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"summary"),
- -class => "list", -title => $pr->{'descr_long'}},
- esc_html($pr->{'descr'})) . "</td>\n" .
+ -class => "list",
+ -title => $pr->{'descr_long'}},
+ $search_regexp
+ ? esc_html_match_hl_chopped($pr->{'descr_long'},
+ $pr->{'descr'}, $search_regexp)
+ : esc_html($pr->{'descr'})) .
+ "</td>\n" .
"<td><i>" . chop_and_escape_str($pr->{'owner'}, 15) . "</i></td>\n";
print "<td class=\"". age_class($pr->{'age'}) . "\">" .
(defined $pr->{'age_string'} ? $pr->{'age_string'} : "No commits") . "</td>\n" .
my $show_ctags = gitweb_check_feature('ctags');
my $tagfilter = $show_ctags ? $input_params{'ctag'} : undef;
$check_forks = undef
- if ($tagfilter || $searchtext);
+ if ($tagfilter || $search_regexp);
# filtering out forks before filling info allows to do less work
@projects = filter_forks_from_projects_list(\@projects)
if ($check_forks);
- @projects = fill_project_list_info(\@projects);
- # searching projects require filling to be run before it
+ # search_projects_list pre-fills required info
@projects = search_projects_list(\@projects,
- 'searchtext' => $searchtext,
+ 'search_regexp' => $search_regexp,
'tagfilter' => $tagfilter)
- if ($tagfilter || $searchtext);
+ if ($tagfilter || $search_regexp);
+ # fill the rest
+ @projects = fill_project_list_info(\@projects);
$order ||= $default_projects_order;
$from = 0 unless defined $from;