]> git.madduck.net Git - code/myrepos.git/blobdiff - webcheckout

madduck's git repository

Every one of the projects in this repository is available at the canonical URL git://git.madduck.net/madduck/pub/<projectpath> — see each project's metadata for the exact URL.

All patches and comments are welcome. Please squash your changes to logical commits before using git-format-patch and git-send-email to patches@git.madduck.net. If you'd read over the Git project's submission guidelines and adhered to them, I'd be especially grateful.

SSH access, as well as push access can be individually arranged.

If you use my repositories frequently, consider adding the following snippet to ~/.gitconfig and using the third clone URL listed for each project:

[url "git://git.madduck.net/madduck/"]
  insteadOf = madduck:

support <a> elements
[code/myrepos.git] / webcheckout
index 9467c9d3032b13ad2cac0c2a26d57853f257f9b2..a6ae94fd09de897ac9498f99e28309997ebefb59 100755 (executable)
@@ -127,23 +127,26 @@ sub doit {
 sub better {
        my ($a, $b)=@_;
 
-       my $firstanon=$b;
+       my @anon;
        foreach my $r (@anon_urls) {
                if ($a->{href} =~ /$r/) {
-                       $firstanon=$a;
-                       last;
+                       push @anon, $a;
                }
                elsif ($b->{href} =~ /$r/) {
-                       $firstanon=$b;
-                       last;
+                       push @anon, $b;
                }
        }
 
        if ($want_auth) {
-               return $firstanon != $a;
+               # Whichever is authed is better.
+               return 1 if ! @anon || ! grep { $_ eq $a } @anon;
+               return 0 if ! grep { $_ eq $b } @anon;
+               # Neither is authed, so the better anon method wins.
+               return $anon[0] == $a;
        }
        else {
-               return $firstanon == $a;
+               # Better anon method wins.
+               return @anon && $anon[0] == $a;
        }
 }
 
@@ -152,21 +155,26 @@ sub better {
 sub dedup {
        my %seenhref;
        my %bytitle;
+       my @others;
        foreach my $repo (@_) {
                if (exists $repo->{title} &&
-                   length $repo->{title} &&
-                   exists $bytitle{$repo->{title}}) {
-                       my $other=$bytitle{$repo->{title}};
-                       next unless better($repo, $other);
-                       delete $bytitle{$other->{title}}
+                   length $repo->{title}) {
+                       if (exists $bytitle{$repo->{title}}) {
+                               my $other=$bytitle{$repo->{title}};
+                               next unless better($repo, $other);
+                               delete $bytitle{$other->{title}}
+                       }
+
+                       if (! $seenhref{$repo->{href}}++) {
+                               $bytitle{$repo->{title}}=$repo;
+                       }
                }
-
-               if (! $seenhref{$repo->{href}}++) {
-                       $bytitle{$repo->{title}}=$repo;
+               else {
+                       push @others, $repo;
                }
        }
 
-       return values %bytitle;
+       return values %bytitle, @others;
 }
 
 sub parse {
@@ -174,15 +182,37 @@ sub parse {
 
        my @ret;
        my $parser=HTML::Parser->new(api_version => 3);
+       my $abody=undef;
+       my $aref=undef;
        $parser->handler(start => sub {
                my $tagname=shift;
                my $attr=shift;
-               return if lc $tagname ne 'link';
                return if ! exists $attr->{rel} || lc $attr->{rel} ne 'vcs';
                return if ! exists $attr->{href} || ! length $attr->{href};
                return if ! exists $attr->{type} || ! length $attr->{type};
+
+               # need to collect the body of the <a> tag if there is no title
+               if ($tagname eq "a" && ! exists $attr->{title}) {
+                       $abody="";
+                       $aref=$attr;
+               }
+
                push @ret, $attr;
        }, "tagname, attr");
+       $parser->handler(text => sub {
+               if (defined $aref) {
+                       $abody.=join(" ", @_);
+               }
+       }, "text");
+       $parser->handler(end => sub {
+               my $tagname=shift;
+               if ($tagname eq "a" && defined $aref) {
+                       $aref->{title}=$abody;
+                       $aref=undef;
+                       $abody=undef;
+               }
+       }, "tagname");
+       $parser->report_tags(qw{link a});
        $parser->parse($page);
        $parser->eof;
 
@@ -201,10 +231,16 @@ if (! @repos) {
        die "no repositories found on $url\n";
 }
 
+#use Data::Dumper;
+#print Dumper(\@repos);
+#exit;
+
 if (defined $destdir && @repos > 1) {
        # create subdirs of $destdir for the multiple repos
-       mkdir($destdir);
-       chdir($destdir) || die "failed to chdir to $destdir: $!";
+       if (! $noact) {
+               mkdir($destdir);
+               chdir($destdir) || die "failed to chdir to $destdir: $!";
+       }
        $destdir=undef;
 }
 
@@ -224,6 +260,3 @@ foreach my $repo (@repos) {
        }
 }
 exit($errors > 0);
-
-#use Data::Dumper;
-#print Dumper(\@repos);