X-Git-Url: https://git.ladys.computer/Gitweb/blobdiff_plain/d0a0ccb4d27d63a2fb051d330f0b7be40f79cfac59125cc6bef13cd764bb6656..7e49981d34284e6250b9f617ef1be11ef601d5a3aa0570dfb3962af6886ea144:/gitweb.perl diff --git a/gitweb.perl b/gitweb.perl index 9199e56..2bfdcca 100755 --- a/gitweb.perl +++ b/gitweb.perl @@ -85,6 +85,8 @@ our $home_link_str = "++GITWEB_HOME_LINK_STR++"; our $site_name = "++GITWEB_SITENAME++" || ($ENV{'SERVER_NAME'} || "Untitled") . " Git"; +# html snippet to include in the section of each page +our $site_html_head_string = "++GITWEB_SITE_HTML_HEAD_STRING++"; # filename of html text to include at top of each page our $site_header = "++GITWEB_SITE_HEADER++"; # html text to include at home page @@ -666,13 +668,25 @@ sub read_config_file { return; } -our ($GITWEB_CONFIG, $GITWEB_CONFIG_SYSTEM); +our ($GITWEB_CONFIG, $GITWEB_CONFIG_SYSTEM, $GITWEB_CONFIG_COMMON); sub evaluate_gitweb_config { our $GITWEB_CONFIG = $ENV{'GITWEB_CONFIG'} || "++GITWEB_CONFIG++"; our $GITWEB_CONFIG_SYSTEM = $ENV{'GITWEB_CONFIG_SYSTEM'} || "++GITWEB_CONFIG_SYSTEM++"; + our $GITWEB_CONFIG_COMMON = $ENV{'GITWEB_CONFIG_COMMON'} || "++GITWEB_CONFIG_COMMON++"; - # use first config file that exists - read_config_file($GITWEB_CONFIG) or + # Protect agains duplications of file names, to not read config twice. + # Only one of $GITWEB_CONFIG and $GITWEB_CONFIG_SYSTEM is used, so + # there possibility of duplication of filename there doesn't matter. + $GITWEB_CONFIG = "" if ($GITWEB_CONFIG eq $GITWEB_CONFIG_COMMON); + $GITWEB_CONFIG_SYSTEM = "" if ($GITWEB_CONFIG_SYSTEM eq $GITWEB_CONFIG_COMMON); + + # Common system-wide settings for convenience. + # Those settings can be ovverriden by GITWEB_CONFIG or GITWEB_CONFIG_SYSTEM. + read_config_file($GITWEB_CONFIG_COMMON); + + # Use first config file that exists. This means use the per-instance + # GITWEB_CONFIG if exists, otherwise use GITWEB_SYSTEM_CONFIG. + read_config_file($GITWEB_CONFIG) and return; read_config_file($GITWEB_CONFIG_SYSTEM); } @@ -746,6 +760,7 @@ our @cgi_param_mapping = ( extra_options => "opt", search_use_regexp => "sr", ctag => "by_tag", + diff_style => "ds", # this must be last entry (for manipulation from JavaScript) javascript => "js" ); @@ -1109,8 +1124,10 @@ sub dispatch { if (!defined $action) { if (defined $hash) { $action = git_get_type($hash); + $action or die_error(404, "Object does not exist"); } elsif (defined $hash_base && defined $file_name) { $action = git_get_type("$hash_base:$file_name"); + $action or die_error(404, "File or directory does not exist"); } elsif (defined $project) { $action = 'summary'; } else { @@ -1429,8 +1446,8 @@ sub validate_refname { sub to_utf8 { my $str = shift; return undef unless defined $str; - if (utf8::valid($str)) { - utf8::decode($str); + + if (utf8::is_utf8($str) || utf8::decode($str)) { return $str; } else { return decode($fallback_encoding, $str, Encode::FB_DEFAULT); @@ -1506,6 +1523,17 @@ sub esc_path { return $str; } +# Sanitize for use in XHTML + application/xml+xhtm (valid XML 1.0) +sub sanitize { + my $str = shift; + + return undef unless defined $str; + + $str = to_utf8($str); + $str =~ s|([[:cntrl:]])|($1 =~ /[\t\n\r]/ ? $1 : quot_cec($1))|eg; + return $str; +} + # Make control characters "printable", using character escape codes (CEC) sub quot_cec { my $cntrl = shift; @@ -1671,6 +1699,7 @@ sub chop_and_escape_str { my ($str) = @_; my $chopped = chop_str(@_); + $str = to_utf8($str); if ($chopped eq $str) { return esc_html($chopped); } else { @@ -2201,93 +2230,119 @@ sub format_diff_cc_simplified { return $result; } -# format patch (diff) line (not to be used for diff headers) -sub format_diff_line { - my $line = shift; - my ($from, $to) = @_; - my $diff_class = ""; - - chomp $line; +sub diff_line_class { + my ($line, $from, $to) = @_; + # ordinary diff + my $num_sign = 1; + # combined diff if ($from && $to && ref($from->{'href'}) eq "ARRAY") { - # combined diff - my $prefix = substr($line, 0, scalar @{$from->{'href'}}); - if ($line =~ m/^\@{3}/) { - $diff_class = " chunk_header"; - } elsif ($line =~ m/^\\/) { - $diff_class = " incomplete"; - } elsif ($prefix =~ tr/+/+/) { - $diff_class = " add"; - } elsif ($prefix =~ tr/-/-/) { - $diff_class = " rem"; - } - } else { - # assume ordinary diff - my $char = substr($line, 0, 1); - if ($char eq '+') { - $diff_class = " add"; - } elsif ($char eq '-') { - $diff_class = " rem"; - } elsif ($char eq '@') { - $diff_class = " chunk_header"; - } elsif ($char eq "\\") { - $diff_class = " incomplete"; - } + $num_sign = scalar @{$from->{'href'}}; + } + + my @diff_line_classifier = ( + { regexp => qr/^\@\@{$num_sign} /, class => "chunk_header"}, + { regexp => qr/^\\/, class => "incomplete" }, + { regexp => qr/^ {$num_sign}/, class => "ctx" }, + # classifier for context must come before classifier add/rem, + # or we would have to use more complicated regexp, for example + # qr/(?= {0,$m}\+)[+ ]{$num_sign}/, where $m = $num_sign - 1; + { regexp => qr/^[+ ]{$num_sign}/, class => "add" }, + { regexp => qr/^[- ]{$num_sign}/, class => "rem" }, + ); + for my $clsfy (@diff_line_classifier) { + return $clsfy->{'class'} + if ($line =~ $clsfy->{'regexp'}); } - $line = untabify($line); - if ($from && $to && $line =~ m/^\@{2} /) { - my ($from_text, $from_start, $from_lines, $to_text, $to_start, $to_lines, $section) = - $line =~ m/^\@{2} (-(\d+)(?:,(\d+))?) (\+(\d+)(?:,(\d+))?) \@{2}(.*)$/; - $from_lines = 0 unless defined $from_lines; - $to_lines = 0 unless defined $to_lines; + # fallback + return ""; +} - if ($from->{'href'}) { - $from_text = $cgi->a({-href=>"$from->{'href'}#l$from_start", - -class=>"list"}, $from_text); - } - if ($to->{'href'}) { - $to_text = $cgi->a({-href=>"$to->{'href'}#l$to_start", - -class=>"list"}, $to_text); - } - $line = "@@ $from_text $to_text @@" . - "" . esc_html($section, -nbsp=>1) . ""; - return "
$line
\n"; - } elsif ($from && $to && $line =~ m/^\@{3}/) { - my ($prefix, $ranges, $section) = $line =~ m/^(\@+) (.*?) \@+(.*)$/; - my (@from_text, @from_start, @from_nlines, $to_text, $to_start, $to_nlines); +# assumes that $from and $to are defined and correctly filled, +# and that $line holds a line of chunk header for unified diff +sub format_unidiff_chunk_header { + my ($line, $from, $to) = @_; - @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); - } + my ($from_text, $from_start, $from_lines, $to_text, $to_start, $to_lines, $section) = + $line =~ m/^\@{2} (-(\d+)(?:,(\d+))?) (\+(\d+)(?:,(\d+))?) \@{2}(.*)$/; - $to_text = pop @from_text; - $to_start = pop @from_start; - $to_nlines = pop @from_nlines; + $from_lines = 0 unless defined $from_lines; + $to_lines = 0 unless defined $to_lines; - $line = "$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"}, $to_text); + if ($from->{'href'}) { + $from_text = $cgi->a({-href=>"$from->{'href'}#l$from_start", + -class=>"list"}, $from_text); + } + if ($to->{'href'}) { + $to_text = $cgi->a({-href=>"$to->{'href'}#l$to_start", + -class=>"list"}, $to_text); + } + $line = "@@ $from_text $to_text @@" . + "" . esc_html($section, -nbsp=>1) . ""; + return $line; +} + +# assumes that $from and $to are defined and correctly filled, +# and that $line holds a line of chunk header for combined diff +sub format_cc_diff_chunk_header { + my ($line, $from, $to) = @_; + + my ($prefix, $ranges, $section) = $line =~ m/^(\@+) (.*?) \@+(.*)$/; + my (@from_text, @from_start, @from_nlines, $to_text, $to_start, $to_nlines); + + @from_text = split(' ', $ranges); + for (my $i = 0; $i < @from_text; ++$i) { + ($from_start[$i], $from_nlines[$i]) = + (split(',', substr($from_text[$i], 1)), 0); + } + + $to_text = pop @from_text; + $to_start = pop @from_start; + $to_nlines = pop @from_nlines; + + $line = "$prefix "; + for (my $i = 0; $i < @from_text; ++$i) { + if ($from->{'href'}[$i]) { + $line .= $cgi->a({-href=>"$from->{'href'}[$i]#l$from_start[$i]", + -class=>"list"}, $from_text[$i]); } else { - $line .= $to_text; + $line .= $from_text[$i]; } - $line .= " $prefix" . - "" . esc_html($section, -nbsp=>1) . ""; - return "
$line
\n"; + $line .= " "; + } + if ($to->{'href'}) { + $line .= $cgi->a({-href=>"$to->{'href'}#l$to_start", + -class=>"list"}, $to_text); + } else { + $line .= $to_text; + } + $line .= " $prefix" . + "" . esc_html($section, -nbsp=>1) . ""; + return $line; +} + +# process patch (diff) line (not to be used for diff headers), +# returning 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); + + if ($from && $to && $line =~ m/^\@{2} /) { + $line = format_unidiff_chunk_header($line, $from, $to); + return $diff_class, $line; + + } elsif ($from && $to && $line =~ m/^\@{3}/) { + $line = format_cc_diff_chunk_header($line, $from, $to); + return $diff_class, $line; + } - return "
" . esc_html($line, -nbsp=>1) . "
\n"; + return $diff_class, esc_html($line, -nbsp=>1); } # Generates undef or something like "_snapshot_" or "snapshot (_tbz2_ _zip_)", @@ -2339,7 +2394,7 @@ sub get_feed_info { 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)$/x); + return if (!$action || $action =~ /^(?:tags|heads|forks|tag|search)$/x); my $branch; # branches refs uses 'refs/heads/' prefix (fullname) to differentiate @@ -2515,6 +2570,13 @@ sub git_get_project_config { # key sanity check return unless ($key); + # only subsection, if exists, is case sensitive, + # and not lowercased by 'git config -z -l' + if (my ($hi, $mi, $lo) = ($key =~ /^([^.]*)\.(.*)\.([^.]*)$/)) { + $key = join(".", lc($hi), $mi, lc($lo)); + } else { + $key = lc($key); + } $key =~ s/^gitweb\.//; return if ($key =~ m/\W/); @@ -2777,8 +2839,8 @@ sub git_get_projects_list { my $dir = $projects_list; # remove the trailing "/" $dir =~ s!/+$!!; - my $pfxlen = length("$projects_list"); - my $pfxdepth = ($projects_list =~ tr!/!!); + my $pfxlen = length("$dir"); + my $pfxdepth = ($dir =~ tr!/!!); # when filtering, search only given subdirectory if ($filter) { $dir .= "/$filter"; @@ -2857,7 +2919,7 @@ sub filter_forks_from_projects_list { $path =~ s/\.git$//; # forks of 'repo.git' are in 'repo/' directory next if ($path =~ m!/$!); # skip non-bare repositories, e.g. 'repo/.git' next unless ($path); # skip '.git' repository: tests, git-instaweb - next unless (-d $path); # containing directory exists + next unless (-d "$projectroot/$path"); # containing directory exists $pr->{'forks'} = []; # there can be 0 or more forks of project # add to trie @@ -3850,6 +3912,11 @@ EOF print "\n"; } print_header_links($status); + + if (defined $site_html_head_string) { + print to_utf8($site_html_head_string); + } + print "\n" . "\n"; @@ -4797,8 +4864,97 @@ sub git_difftree_body { print "\n"; } +sub print_sidebyside_diff_chunk { + my @chunk = @_; + my (@ctx, @rem, @add); + + return unless @chunk; + + # incomplete last line might be among removed or added lines, + # or both, or among context lines: find which + for (my $i = 1; $i < @chunk; $i++) { + if ($chunk[$i][0] eq 'incomplete') { + $chunk[$i][0] = $chunk[$i-1][0]; + } + } + + # guardian + push @chunk, ["", ""]; + + foreach my $line_info (@chunk) { + my ($class, $line) = @$line_info; + + # print chunk headers + if ($class && $class eq 'chunk_header') { + print $line; + next; + } + + ## print from accumulator when type of class of lines change + # empty contents block on start rem/add block, or end of chunk + if (@ctx && (!$class || $class eq 'rem' || $class eq 'add')) { + print join '', + '
', + '
', + @ctx, + '
', + '
', + @ctx, + '
', + '
'; + @ctx = (); + } + # empty add/rem block on start context block, or end of chunk + if ((@rem || @add) && (!$class || $class eq 'ctx')) { + if (!@add) { + # pure removal + print join '', + '
', + '
', + @rem, + '
', + '
'; + } elsif (!@rem) { + # pure addition + print join '', + '
', + '
', + @add, + '
', + '
'; + } else { + # assume that it is change + print join '', + '
', + '
', + @rem, + '
', + '
', + @add, + '
', + '
'; + } + @rem = @add = (); + } + + ## adding lines to accumulator + # guardian value + last unless $line; + # rem, add or change + if ($class eq 'rem') { + push @rem, $line; + } elsif ($class eq 'add') { + push @add, $line; + } + # context line + if ($class eq 'ctx') { + push @ctx, $line; + } + } +} + sub git_patchset_body { - my ($fd, $difftree, $hash, @hash_parents) = @_; + my ($fd, $diff_style, $difftree, $hash, @hash_parents) = @_; my ($hash_parent) = $hash_parents[0]; my $is_combined = (@hash_parents > 1); @@ -4808,6 +4964,7 @@ sub git_patchset_body { my $diffinfo; my $to_name; my (%from, %to); + my @chunk; # for side-by-side diff print "
\n"; @@ -4914,10 +5071,29 @@ sub git_patchset_body { next PATCH if ($patch_line =~ m/^diff /); - print format_diff_line($patch_line, \%from, \%to); + my ($class, $line) = process_diff_line($patch_line, \%from, \%to); + my $diff_classes = "diff"; + $diff_classes .= " $class" if ($class); + $line = "
$line
\n"; + + if ($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; + } } } continue { + if (@chunk) { + print_sidebyside_diff_chunk(@chunk); + @chunk = (); + } print "
\n"; # class="patch" } @@ -5663,7 +5839,7 @@ sub git_search_files { my %co = @_; local $/ = "\n"; - open my $fd, "-|", git_cmd(), 'grep', '-n', + open my $fd, "-|", git_cmd(), 'grep', '-n', '-z', $search_use_regexp ? ('-E', '-i') : '-F', $searchtext, $co{'tree'} or die_error(500, "Open git-grep failed"); @@ -5679,13 +5855,14 @@ sub git_search_files { my $lastfile = ''; while (my $line = <$fd>) { chomp $line; - my ($file, $lno, $ltext, $binary); + my ($file, $file_href, $lno, $ltext, $binary); last if ($matches++ > 1000); if ($line =~ /^Binary file (.+) matches$/) { $file = $1; $binary = 1; } else { - (undef, $file, $lno, $ltext) = split(/:/, $line, 4); + ($file, $lno, $ltext) = split(/\0/, $line, 3); + $file =~ s/^$co{'tree'}://; } if ($file ne $lastfile) { $lastfile and print "\n"; @@ -5694,10 +5871,10 @@ sub git_search_files { } else { print "\n"; } + $file_href = href(action=>"blob", hash_base=>$co{'id'}, + file_name=>$file); print "". - $cgi->a({-href => href(action=>"blob", hash=>$co{'hash'}, - file_name=>"$file"), - -class => "list"}, esc_path($file)); + $cgi->a({-href => $file_href, -class => "list"}, esc_path($file)); print "\n"; $lastfile = $file; } @@ -5715,10 +5892,9 @@ sub git_search_files { $ltext = esc_html($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"; + $cgi->a({-href => $file_href.'#l'.$lno, + -class => "linenr"}, sprintf('%4i', $lno)) . + ' ' . $ltext . "\n"; } } if ($lastfile) { @@ -6071,7 +6247,9 @@ sub git_blame_common { -type=>"text/plain", -charset => "utf-8", -status=> "200 OK"); local $| = 1; # output autoflush - print while <$fd>; + while (my $line = <$fd>) { + print to_utf8($line); + } close $fd or print "ERROR $!\n"; @@ -6466,7 +6644,8 @@ sub git_blob { $nr++; $line = untabify($line); printf qq!
%4i %s
\n!, - $nr, href(-replay => 1), $nr, $nr, $syntax ? $line : esc_html($line, -nbsp=>1); + $nr, esc_attr(href(-replay => 1)), $nr, $nr, + $syntax ? sanitize($line) : esc_html($line, -nbsp=>1); } } close $fd @@ -6912,6 +7091,7 @@ sub git_object { sub git_blobdiff { my $format = shift || 'html'; + my $diff_style = $input_params{'diff_style'} || 'inline'; my $fd; my @difftree; @@ -6990,6 +7170,7 @@ sub git_blobdiff { my $formats_nav = $cgi->a({-href => href(action=>"blobdiff_plain", -replay=>1)}, "raw"); + $formats_nav .= diff_style_nav($diff_style); git_header_html(undef, $expires); if (defined $hash_base && (my %co = parse_commit($hash_base))) { git_print_page_nav('','', $hash_base,$co{'tree'},$hash_base, $formats_nav); @@ -7021,7 +7202,8 @@ sub git_blobdiff { if ($format eq 'html') { print "
\n"; - git_patchset_body($fd, [ \%diffinfo ], $hash_base, $hash_parent_base); + git_patchset_body($fd, $diff_style, + [ \%diffinfo ], $hash_base, $hash_parent_base); close $fd; print "
\n"; # class="page_body" @@ -7046,9 +7228,31 @@ sub git_blobdiff_plain { git_blobdiff('plain'); } +# assumes that it is added as later part of already existing navigation, +# so it returns "| foo | bar" rather than just "foo | bar" +sub diff_style_nav { + my ($diff_style, $is_combined) = @_; + $diff_style ||= 'inline'; + + return "" if ($is_combined); + + my @styles = (inline => 'inline', 'sidebyside' => 'side by side'); + my %styles = @styles; + @styles = + @styles[ map { $_ * 2 } 0..$#styles/2 ]; + + return join '', + map { " | ".$_ } + map { + $_ eq $diff_style ? $styles{$_} : + $cgi->a({-href => href(-replay=>1, diff_style => $_)}, $styles{$_}) + } @styles; +} + sub git_commitdiff { my %params = @_; my $format = $params{-format} || 'html'; + my $diff_style = $input_params{'diff_style'} || 'inline'; my ($patch_max) = gitweb_get_feature('patches'); if ($format eq 'patch') { @@ -7074,6 +7278,7 @@ sub git_commitdiff { $cgi->a({-href => href(action=>"patch", -replay=>1)}, "patch"); } + $formats_nav .= diff_style_nav($diff_style, @{$co{'parents'}} > 1); if (defined $hash_parent && $hash_parent ne '-c' && $hash_parent ne '--cc') { @@ -7091,8 +7296,8 @@ sub git_commitdiff { } } $formats_nav .= ': ' . - $cgi->a({-href => href(action=>"commitdiff", - hash=>$hash_parent)}, + $cgi->a({-href => href(-replay=>1, + hash=>$hash_parent, hash_base=>undef)}, esc_html($hash_parent_short)) . ')'; } elsif (!$co{'parent'}) { @@ -7102,28 +7307,28 @@ sub git_commitdiff { # single parent commit $formats_nav .= ' (parent: ' . - $cgi->a({-href => href(action=>"commitdiff", - hash=>$co{'parent'})}, + $cgi->a({-href => href(-replay=>1, + hash=>$co{'parent'}, hash_base=>undef)}, esc_html(substr($co{'parent'}, 0, 7))) . ')'; } else { # merge commit if ($hash_parent eq '--cc') { $formats_nav .= ' | ' . - $cgi->a({-href => href(action=>"commitdiff", + $cgi->a({-href => href(-replay=>1, hash=>$hash, hash_parent=>'-c')}, 'combined'); } else { # $hash_parent eq '-c' $formats_nav .= ' | ' . - $cgi->a({-href => href(action=>"commitdiff", + $cgi->a({-href => href(-replay=>1, hash=>$hash, hash_parent=>'--cc')}, 'compact'); } $formats_nav .= ' (merge: ' . join(' ', map { - $cgi->a({-href => href(action=>"commitdiff", - hash=>$_)}, + $cgi->a({-href => href(-replay=>1, + hash=>$_, hash_base=>undef)}, esc_html(substr($_, 0, 7))); } @{$co{'parents'}} ) . ')'; @@ -7252,7 +7457,8 @@ sub git_commitdiff { $use_parents ? @{$co{'parents'}} : $hash_parent); print "
\n"; - git_patchset_body($fd, \@difftree, $hash, + git_patchset_body($fd, $diff_style, + \@difftree, $hash, $use_parents ? @{$co{'parents'}} : $hash_parent); close $fd; print "\n"; # class="page_body" @@ -7662,11 +7868,12 @@ sub git_opml { -charset => 'utf-8', -content_disposition => 'inline; filename="opml.xml"'); + my $title = esc_html($site_name); print < - $site_name OPML Export + $title OPML Export