[ViewVC] Diff of: cvs/rxvt-unicode/src/perl/matcher

Comparing rxvt-unicode/src/perl/matcher (file contents):
Revision 1.32 by sf-exg, Wed Jul 30 15:22:51 2014 UTC vs.
Revision 1.39 by root, Sun Nov 21 19:33:32 2021 UTC

 #! perl
 # Author: Tim Pope <rxvt-unicodeNOSPAM@tpope.org>
 #         Bob Farrell <robertanthonyfarrell@gmail.com>
+#         Emanuele Giaquinta
 #:META:RESOURCE:%.launcher:string:default launcher command
-#:META:RESOURCE:%.button:string:the button, yeah
+#:META:RESOURCE:%.button:string:the mouse button used to activate a match
 #:META:RESOURCE:%.pattern.:string:extra pattern to match
 #:META:RESOURCE:%.launcher.:string:custom launcher for pattern
 #:META:RESOURCE:%.rend.:string:custom rendition for pattern
 =head1 NAME
 It is possible to activate the most recently seen match or a list of matches
 from the keyboard.  Simply bind a keysym to "matcher:last" or
 "matcher:list" as seen in the example below.
-The 'matcher:select' action enables a mode in which it is possible to
+The C<matcher:select> action enables a mode in which it is possible to
 iterate over the matches using the keyboard and either activate them
 or copy them to the clipboard. While the mode is active, normal terminal
 input/output is suspended and the following bindings are recognized:
-=over 4
+=over
 =item C<Up>
 Search for a match upwards.
 =item C<y>
 Copy the current match to the clipboard.
 =back
+It is also possible to cycle through the matches using a key
+combination bound to the C<matcher:select> action.
 Example: load and use the matcher extension with defaults.
     URxvt.perl-ext:           default,matcher
     URxvt.matcher.button:     1
     URxvt.matcher.pattern.1:  \\bwww\\.[\\w-]+\\.[\\w./?&@#-]*[\\w/-]
     URxvt.matcher.pattern.2:  \\B(/\\S+?):(\\d+)(?=:|$)
     URxvt.matcher.launcher.2: gvim +$2 $1
+=head2 Regex encoding/wide character matching
+Urxvt stores all text as unicode, in a special encoding that uses
+one character/code point per column. For various reasons, the regular
+expressions are matched directly against this encoding, which means there are a few things
+you need to keep in mind:
+=over
+=item X resources/command line arguments are locale-encoded
+The regexes taken from the command line or resources will be converted
+from locale encoding to unicode. This can change the number of code points
+per character.
+=item Wide characters are column-padded with C<$urxvt::NOCHAR>
+Wide characters (such as kanji and sometimes tabs) are padded with
+a special character value (C<$urxvt::NOCHAR>). That means that
+constructs such as C<\w> or C<.> will only match part of a character, as
+C<$urxvt::NOCHAR> is not matched by C<\w> and both only match the first
+"column" of a wide character.
+That means you have to incorporate C<$urxvt::NOCHAR> into parts of regexes
+that may match wide characters. For example, to match C<\w+> you might
+want to use C<[\w$urxvt::NOCHAR]+> instead, and to match a single character
+(C<.>) you might want to use C<.$urxvt::NOCHAR*> instead.
+=back
 =cut
 my $url =
    qr{
       (?:https?://|ftp://|news://|mailto:|file://|\bwww\.)
-      [\w\-\@;\/?:&=%\$.+!*\x27,~#]*
+      [\w\-\@;\/?:&=%\$.+!*\x27,~#$urxvt::NOCHAR]*
       (
-         \([\w\-\@;\/?:&=%\$.+!*\x27,~#]*\)| # Allow a pair of matched parentheses
+         \([\w\-\@;\/?:&=%\$.+!*\x27,~#$urxvt::NOCHAR]*\)| # Allow a pair of matched parentheses
          [\w\-\@;\/?:&=%\$+*~]  # exclude some trailing characters (heuristic)
       )+
    }x;
 sub matchlist_key_press {
 # backwards compat
 sub on_user_command {
    my ($self, $cmd) = @_;
-   if ($cmd =~ s/^matcher:list\b//) {
+   if ($cmd eq "matcher:list") {
       $self->matchlist;
-   } else {
+   } elsif ($cmd eq "matcher:last") {
-      if ($cmd =~ s/^matcher:last\b//) {
-         $self->most_recent;
+      $self->most_recent;
+   } elsif ($cmd eq "matcher:select") {
+      $self->select_enter;
-      } elsif ($cmd =~ s/^matcher\b//) {
+   } elsif ($cmd eq "matcher") {
-         # for backward compatibility
+      # for backward compatibility
-         $self->most_recent;
+      $self->most_recent;
-      }
    }
    ()
 }
       }
    }
    my @defaults = ($url);
    my @matchers;
-   for (my $idx = 0; defined (my $res = $self->my_resource ("pattern.$idx") || $defaults[$idx]); $idx++) {
+   for (my $idx = 0; defined (my $res = $self->locale_decode ($self->my_resource ("pattern.$idx")) || $defaults[$idx]); $idx++) {
-      $res = $self->locale_decode ($res);
-      utf8::encode $res;
       my $launcher = $self->my_resource ("launcher.$idx");
       $launcher =~ s/\$&|\$\{&\}/\${0}/g if $launcher;
       my $rend = $self->parse_rend($self->my_resource ("rend.$idx"));
       unshift @matchers, [qr($res)x,$launcher,$rend];
    }
    my ($self, $row) = @_;
    # fetch the line that has changed
    my $line = $self->line ($row);
    my $text = $line->t;
+   my $rend;
    # find all urls (if any)
    for my $matcher (@{$self->{matchers}}) {
       while ($text =~ /$matcher->[0]/g) {
          #print "$&\n";
-         my $rend = $line->r;
+         $rend ||= $line->r;
          # mark all characters as underlined. we _must_ not toggle underline,
          # as we might get called on an already-marked url.
          &{$matcher->[2]}
             for @{$rend}[$-[0] .. $+[0] - 1];
-         $line->r ($rend);
       }
    }
+   $line->r ($rend) if $rend;
    ()
 }
 sub valid_button {
       if (@matches) {
          @matches = sort { $a->[0] <=> $b->[0] or $a->[1] <=> $b->[1] } @matches;
          $self->{matches} = \@matches;
          $self->{cur_row} = $row;
          $self->{id} = $dir < 0 ? @{ $self->{matches} } - 1 : 0;
-         $self->view_start (List::Util::min 0, $row - ($self->nrow >> 1));
+         $self->view_start ($row - ($self->nrow >> 1));
          $self->want_refresh;
-         return;
+         return 1;
       }
       $row = $dir < 0 ? $line->beg - 1 : $line->end + 1;
    }
    $self->scr_bell;
+   ()
 }
 sub select_refresh {
    my ($self) = @_;
       } else {
          my $line = $self->line ($self->{cur_row});
          $self->select_search (+1, $line->end + 1)
             if $line->end < $self->nrow;
       }
+   } elsif ($self->lookup_keysym ($keysym, $event->{state}) eq "matcher:select") {
+      if ($self->{id} > 0) {
+         $self->{id}--;
+         $self->want_refresh;
+      } else {
+         my $line = $self->line ($self->{cur_row});
+         $self->select_search (-1, $self->nrow - 1)
+            unless $self->select_search (-1, $line->beg - 1);
+      }
    }
    1
 }

Diff Legend

-–
+Removed lines
-+
+Added lines
-<
+Changed lines
->
+Changed lines

Comparing rxvt-unicode/src/perl/matcher (file contents): Revision 1.32 by sf-exg, Wed Jul 30 15:22:51 2014 UTC vs. Revision 1.39 by root, Sun Nov 21 19:33:32 2021 UTC

Diff Legend

Comparing rxvt-unicode/src/perl/matcher (file contents):
Revision 1.32 by sf-exg, Wed Jul 30 15:22:51 2014 UTC vs.
Revision 1.39 by root, Sun Nov 21 19:33:32 2021 UTC