#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 || "/";
our $searchtext = $cgi->param('s');
our $search_regexp;
if (defined $searchtext) {
- if ($searchtype ne 'grep' and $searchtype ne 'pickaxe' and $searchtext =~ m/[^a-zA-Z0-9_\.\/\-\+\:\@ ]/) {
- die_error(undef, "Invalid search parameter");
- }
if (length($searchtext) < 2) {
die_error(undef, "At least two characters are required for search parameter");
}
return "$body$tail";
}
+# takes the same arguments as chop_str, but also wraps a <span> 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 = shift;
+ my $len = shift;
+ my $add_len = shift || 10;
+
+ my $chopped = chop_str($str, $len, $add_len);
+ if ($chopped eq $str) {
+ return esc_html($chopped);
+ } else {
+ return qq{<span title="} . esc_html($str) . qq{">} .
+ esc_html($chopped) . qq{</span>};
+ }
+}
+
## ----------------------------------------------------------------------
## functions returning short strings
# remove the trailing "/"
$dir =~ s!/+$!!;
my $pfxlen = length("$dir");
+ 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
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 ($;%) {
my $line = shift;
}
}
} else {
+ # ordinary (not combined) diff
$from->{'file'} = $diffinfo->{'from_file'} || $diffinfo->{'file'};
if ($diffinfo->{'status'} ne "A") { # not new (added) file
$from->{'href'} = href(action=>"blob", hash_base=>$hash_parent,
## ......................................................................
## functions printing large fragments of HTML
+# get pre-image filenames for merge (combined) diff
sub fill_from_file_info {
my ($diff, @parents) = @_;
return $diff;
}
-# parameters can be strings, or references to arrays of strings
-sub from_ids_eq {
- my ($a, $b) = @_;
-
- if (ref($a) eq "ARRAY" && ref($b) eq "ARRAY" && @$a == @$b) {
- for (my $i = 0; $i < @$a; ++$i) {
- return 0 unless ($a->[$i] eq $b->[$i]);
- }
- return 1;
- } elsif (!ref($a) && !ref($b)) {
- return $a eq $b;
- } else {
- return 0;
- }
-}
-
+# 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'} || $diffinfo->{'file'}) eq $patchinfo->{'to_file'};
+}
+
+
sub git_difftree_body {
my ($difftree, $hash, @parents) = @_;
my ($parent) = $parents[0];
"diff_tree\">\n";
# header only for combined diff in 'commitdiff' view
- my $has_header = @parents > 1 && $action eq 'commitdiff';
+ my $has_header = @$difftree && @parents > 1 && $action eq 'commitdiff';
if ($has_header) {
# table header
print "<thead><tr>\n" .
my $alternate = 1;
my $patchno = 0;
foreach my $line (@{$difftree}) {
- my $diff;
- if (ref($line) eq "HASH") {
- # pre-parsed (or generated by hand)
- $diff = $line;
- } else {
- $diff = parse_difftree_raw_line($line);
- }
+ my $diff = parsed_difftree_line($line);
if ($alternate) {
print "<tr class=\"dark\">\n";
my ($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 $to_name;
my (%from, %to);
print "<div class=\"patchset\">\n";
PATCH:
while ($patch_line) {
- my @diff_header;
- my ($from_id, $to_id);
-
- # git diff header
- #assert($patch_line =~ m/^diff /) if DEBUG;
- #assert($patch_line !~ m!$/$!) if DEBUG; # is chomp-ed
- $patch_number++;
- push @diff_header, $patch_line;
-
- # extended diff header
- EXTENDED_HEADER:
- while ($patch_line = <$fd>) {
- chomp $patch_line;
-
- last EXTENDED_HEADER if ($patch_line =~ m/^--- |^diff /);
-
- if ($patch_line =~ m/^index ([0-9a-fA-F]{40})..([0-9a-fA-F]{40})/) {
- $from_id = $1;
- $to_id = $2;
- } elsif ($patch_line =~ m/^index ((?:[0-9a-fA-F]{40},)+[0-9a-fA-F]{40})..([0-9a-fA-F]{40})/) {
- $from_id = [ split(',', $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;
}
- 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 &&
- defined $from_id && defined $to_id &&
- from_ids_eq($diffinfo->{'from_id'}, $from_id) &&
- $diffinfo->{'to_id'} eq $to_id) {
+ if (is_patch_split($diffinfo, { 'to_file' => $to_name })) {
# this is continuation of a split patch
print "<div class=\"patch cont\">\n";
} else {
# advance raw git-diff output if needed
$patch_idx++ if defined $diffinfo;
- # compact combined diff output can have some patches skipped
- # find which patch (using pathname of result) we are at now
- my $to_name;
- if ($diff_header[0] =~ m!^diff --cc "?(.*)"?$!) {
- $to_name = $1;
- }
+ # read and prepare patch information
+ $diffinfo = parsed_difftree_line($difftree->[$patch_idx]);
- do {
- # read and prepare patch information
- if (ref($difftree->[$patch_idx]) eq "HASH") {
- # pre-parsed (or generated by hand)
- $diffinfo = $difftree->[$patch_idx];
- } else {
- $diffinfo = parse_difftree_raw_line($difftree->[$patch_idx]);
- }
-
- # check if current raw line has no patch (it got simplified)
- if (defined $to_name && $to_name ne $diffinfo->{'to_file'}) {
+ # compact combined diff output can have some patches skipped
+ # find which patch (using pathname of result) we are at now;
+ if ($is_combined) {
+ while ($to_name ne $diffinfo->{'to_file'}) {
print "<div class=\"patch\" id=\"patch". ($patch_idx+1) ."\">\n" .
format_diff_cc_simplified($diffinfo, @hash_parents) .
"</div>\n"; # class="patch"
$patch_idx++;
$patch_number++;
+
+ last if $patch_idx > $#$difftree;
+ $diffinfo = parsed_difftree_line($difftree->[$patch_idx]);
}
- } until (!defined $to_name || $to_name eq $diffinfo->{'to_file'} ||
- $patch_idx > $#$difftree);
+ }
+
# modifies %from, %to hashes
parse_from_to_diffinfo($diffinfo, \%from, \%to, @hash_parents);
- if ($diffinfo->{'nparents'}) {
- # combined diff
- $from{'file'} = [];
- $from{'href'} = [];
- fill_from_file_info($diffinfo, @hash_parents)
- unless exists $diffinfo->{'from_file'};
- for (my $i = 0; $i < $diffinfo->{'nparents'}; $i++) {
- $from{'file'}[$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=>$hash_parents[$i],
- hash=>$diffinfo->{'from_id'}[$i],
- file_name=>$from{'file'}[$i]);
- } else {
- $from{'href'}[$i] = undef;
- }
- }
- } else {
- $from{'file'} = $diffinfo->{'from_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'});
- } else {
- delete $from{'href'};
- }
- }
- $to{'file'} = $diffinfo->{'to_file'} || $diffinfo->{'file'};
- if (!is_deleted($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'};
- }
# this is first patch for raw difftree line with $patch_idx index
# we index @$difftree array from 0, but number patches from 1
print "<div class=\"patch\" id=\"patch". ($patch_idx+1) ."\">\n";
}
+ # git diff header
+ #assert($patch_line =~ m/^diff /) if DEBUG;
+ #assert($patch_line !~ m!$/$!) if DEBUG; # is chomp-ed
+ $patch_number++;
# print "git diff" header
- $patch_line = shift @diff_header;
print format_git_diff_header_line($patch_line, $diffinfo,
\%from, \%to);
# print extended diff header
- print "<div class=\"diff extended_header\">\n" if (@diff_header > 0);
+ print "<div class=\"diff extended_header\">\n";
EXTENDED_HEADER:
- foreach $patch_line (@diff_header) {
+ while ($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 "</div>\n" if (@diff_header > 0); # class="diff extended_header"
+ print "</div>\n"; # class="diff extended_header"
# from-file/to-file diff header
- $patch_line = $last_patch_line;
if (! $patch_line) {
print "</div>\n"; # class="patch"
last PATCH;
}
next PATCH if ($patch_line =~ m/^diff /);
#assert($patch_line =~ m/^---/) if DEBUG;
- #assert($patch_line eq $last_patch_line) if DEBUG;
+ my $last_patch_line = $patch_line;
$patch_line = <$fd>;
chomp $patch_line;
#assert($patch_line =~ m/^\+\+\+/) if DEBUG;
# 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 $patch_number > 0;
+ for (++$patch_idx if $patch_number > 0;
$patch_idx < @$difftree;
- $patch_idx++) {
+ ++$patch_idx) {
# 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]);
- }
+ $diffinfo = parsed_difftree_line($difftree->[$patch_idx]);
# generate anchor for "patch" links in difftree / whatchanged part
print "<div class=\"patch\" id=\"patch". ($patch_idx+1) ."\">\n" .
"<td>" . $cgi->a({-href => href(project=>$pr->{'path'}, action=>"summary"),
-class => "list", -title => $pr->{'descr_long'}},
esc_html($pr->{'descr'})) . "</td>\n" .
- "<td><i>" . chop_str($pr->{'owner'}, 15) . "</i></td>\n";
+ "<td><i>" . chop_and_escape_str($pr->{'owner'}, 15) . "</i></td>\n";
print "<td class=\"". age_class($pr->{'age'}) . "\">" .
(defined $pr->{'age_string'} ? $pr->{'age_string'} : "No commits") . "</td>\n" .
"<td class=\"link\">" .
print "<tr class=\"light\">\n";
}
$alternate ^= 1;
+ my $author = chop_and_escape_str($co{'author_name'}, 10);
# git_summary() used print "<td><i>$co{'age_string'}</i></td>\n" .
print "<td title=\"$co{'age_string_age'}\"><i>$co{'age_string_date'}</i></td>\n" .
- "<td><i>" . esc_html(chop_str($co{'author_name'}, 10)) . "</i></td>\n" .
+ "<td><i>" . $author . "</i></td>\n" .
"<td>";
print format_subject_html($co{'title'}, $co{'title_short'},
href(action=>"commit", hash=>$commit), $ref);
print "<tr class=\"light\">\n";
}
$alternate ^= 1;
+ # shortlog uses chop_str($co{'author_name'}, 10)
+ my $author = chop_and_escape_str($co{'author_name'}, 15, 3);
print "<td title=\"$co{'age_string_age'}\"><i>$co{'age_string_date'}</i></td>\n" .
- # shortlog uses chop_str($co{'author_name'}, 10)
- "<td><i>" . esc_html(chop_str($co{'author_name'}, 15, 3)) . "</i></td>\n" .
+ "<td><i>" . $author . "</i></td>\n" .
"<td>";
# originally git_history used chop_str($co{'title'}, 50)
print format_subject_html($co{'title'}, $co{'title_short'},
print "<tr class=\"light\">\n";
}
$alternate ^= 1;
+ my $author = chop_and_escape_str($co{'author_name'}, 15, 5);
print "<td title=\"$co{'age_string_age'}\"><i>$co{'age_string_date'}</i></td>\n" .
- "<td><i>" . esc_html(chop_str($co{'author_name'}, 15, 5)) . "</i></td>\n" .
+ "<td><i>" . $author . "</i></td>\n" .
"<td>" .
$cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), -class => "list subject"},
- esc_html(chop_str($co{'title'}, 50)) . "<br/>");
+ chop_and_escape_str($co{'title'}, 50) . "<br/>");
my $comment = $co{'comment'};
foreach my $line (@$comment) {
if ($line =~ m/^(.*)($search_regexp)(.*)$/i) {
print "<div class=\"title\"> </div>\n";
print "<table cellspacing=\"0\">\n" .
"<tr><td>description</td><td>" . esc_html($descr) . "</td></tr>\n" .
- "<tr><td>owner</td><td>$owner</td></tr>\n";
+ "<tr><td>owner</td><td>" . esc_html($owner) . "</td></tr>\n";
if (defined $cd{'rfc2822'}) {
print "<tr><td>last change</td><td>$cd{'rfc2822'}</td></tr>\n";
}
print "<tr class=\"light\">\n";
}
$alternate ^= 1;
+ my $author = chop_and_escape_str($co{'author_name'}, 15, 5);
print "<td title=\"$co{'age_string_age'}\"><i>$co{'age_string_date'}</i></td>\n" .
- "<td><i>" . esc_html(chop_str($co{'author_name'}, 15, 5)) . "</i></td>\n" .
+ "<td><i>" . $author . "</i></td>\n" .
"<td>" .
$cgi->a({-href => href(action=>"commit", hash=>$co{'id'}),
-class => "list subject"},
- esc_html(chop_str($co{'title'}, 50)) . "<br/>");
+ chop_and_escape_str($co{'title'}, 50) . "<br/>");
while (my $setref = shift @files) {
my %set = %$setref;
print $cgi->a({-href => href(action=>"blob", hash_base=>$co{'id'},
# log/feed of current (HEAD) branch, log of given branch, history of file/directory
my $head = $hash || 'HEAD';
- my @commitlist = parse_commits($head, 150);
+ my @commitlist = parse_commits($head, 150, 0, undef, $file_name);
my %latest_commit;
my %latest_date;
projects / git.git / blobdiff