ViewVC Help
View File | Revision Log | Show Annotations | Download File
/cvs/rxvt-unicode/src/perl/selection
(Generate patch)

Comparing rxvt-unicode/src/perl/selection (file contents):
Revision 1.20 by root, Thu Jan 12 03:32:56 2006 UTC vs.
Revision 1.34 by root, Mon Jan 23 23:13:03 2006 UTC

7 and $self->selection (map { y/A-Za-z/N-ZA-Mn-za-m/; $_ } $self->selection); 7 and $self->selection (map { y/A-Za-z/N-ZA-Mn-za-m/; $_ } $self->selection);
8 8
9 () 9 ()
10} 10}
11 11
12sub on_init {
13 my ($self) = @_;
14
15 for (my $idx = 0; defined (my $res = $self->x_resource ("selection.pattern-$idx")); $idx++) {
16 $res = $self->locale_decode ($res);
17 utf8::encode $res;
18 push @{ $self->{patterns} }, qr/$res/;
19 }
20
21 ()
22}
23
12# "find interetsing things"-patterns 24# "find interesting things"-patterns
13my @mark_patterns = ( 25my @mark_patterns = (
14 qr{([[:alnum:]]+)},
15
16 # common "parentheses" 26 # common types of "parentheses"
17 qr{(?:^|\s) ‘ ([^‘’]+?) ’ (?:\s|\)|$)}x, 27 qr{ (?<![^[:space:]]) ‘ ([^‘’]+) ’ (?![^[:space]]) }x,
18 qr{(?:^|\s) ` ([^`']+?) ' (?:\s|\)|$)}x, 28 qr{ (?<![^[:space:]]) ` ([^`']+) ' (?![^[:space]]) }x,
19 qr{ \{ ([^{}]+?) \} }x, 29 qr{ (?<![^[:space:]]) (" [^[:space:]] [^"]* ") }x,
20 qr{ \[ ([^{}]+?) \] }x, 30 qr{ (" [^"]* [^[:space:]] ") (?![^[:space]]) }x,
31 qr{ \< ([^<>[:space:]]+) \> }x,
32 qr{ \{ ([^{}[:space:]]+) \} }x,
33 qr{ \[ ([^{}[:space:]]+) \] }x,
34 qr{ \( ([^()[:space:]]+) \) }x,
21 35
22 # urls, just a heuristic 36 # urls, just a heuristic
23 qr{( 37 qr{(
24 (?:https?|ftp|news|mailto|file)://[ab-zA-Z0-9\-\@;\/?:&=%\$_.+!*\x27(),~]+ 38 (?:https?|ftp|news|mailto|file)://[ab-zA-Z0-9\-\@;\/?:&=%\$_.+!*\x27(),~]+
25 [ab-zA-Z0-9\-\@;\/?:&=%\$_+!*\x27()~] # exclude some trailing characters (heuristic) 39 [ab-zA-Z0-9\-\@;\/?:&=%\$_+!*\x27()~] # exclude some trailing characters (heuristic)
26 )}x, 40 )}x,
27 41
28 # shell-like argument quoting, basically always matches 42 # shell-like argument quoting, basically always matches
29 qr{\G [\ \t|&;<>()] *( 43 qr{\G [\ \t|&;<>()]* (
30 (?: 44 (?:
31 [^\\"'\ \t|&;<>()]+ 45 [^\\"'\ \t|&;<>()]+
32 | \\. 46 | \\.
33 | " (?: [^\\"]+ | \\. )* " 47 | " (?: [^\\"]+ | \\. )* "
34 | ' [^']* ' 48 | ' [^']* '
41 qr{^"([^\\"'\ \t|&;<>()*?]+)"$}, # "simple" => simple 55 qr{^"([^\\"'\ \t|&;<>()*?]+)"$}, # "simple" => simple
42 qr{^(.*)[,\-]$}, # strip off trailing , and - 56 qr{^(.*)[,\-]$}, # strip off trailing , and -
43); 57);
44 58
45sub on_sel_extend { 59sub on_sel_extend {
46 my ($self) = @_; 60 my ($self, $time) = @_;
47 61
48 my ($row, $col) = $self->selection_mark; 62 my ($row, $col) = $self->selection_mark;
49 my $line = $self->line ($row); 63 my $line = $self->line ($row);
50 my $text = $line->t; 64 my $text = $line->t;
51 my $markofs = $line->offset_of ($row, $col); 65 my $markofs = $line->offset_of ($row, $col);
52 my $curlen = $line->offset_of ($self->selection_end) 66 my $curlen = $line->offset_of ($self->selection_end)
53 - $line->offset_of ($self->selection_beg); 67 - $line->offset_of ($self->selection_beg);
54 68
55 my @matches; 69 my @matches;
56 70
57 for my $regex (@mark_patterns) { 71 if ($markofs < $line->l) {
58 while ($text =~ /$regex/g) { 72 # convert markofs form character to UTF-8 offset space
59 if ($-[1] <= $markofs and $markofs <= $+[1]) { 73 {
60 my $ofs = $-[1]; 74 my $prefix = substr $text, 0, $markofs;
61 my $match = $1; 75 utf8::encode $prefix;
76 $markofs = length $prefix;
77 }
62 78
63 push @matches, [$ofs, length $match]; 79 # not doing matches in unicode mode helps speed
80 # enourmously here. working in utf-8 should be
81 # equivalent due to the magic of utf-8 encoding.
82 utf8::encode $text;
83 study $text; # _really_ helps, too :)
64 84
85 for my $regex (@mark_patterns, @{ $self->{patterns} }) {
86 while ($text =~ /$regex/g) {
87 if ($-[1] <= $markofs and $markofs <= $+[1]) {
88 my $ofs = $-[1];
89 my $match = $1;
90
65 for my $regex (@simplify_patterns) { 91 for my $regex (@simplify_patterns) {
66 if ($match =~ $regex) { 92 if ($match =~ $regex) {
67 $match = $1; 93 $match = $1;
68 $ofs += $-[1]; 94 $ofs += $-[1];
95 }
69 } 96 }
97
98 push @matches, [$ofs, length $match];
70 } 99 }
71
72 push @matches, [$ofs, length $match];
73 } 100 }
74 } 101 }
75 } 102 }
103
104 # whole line
105 push @matches, [0, ($line->end - $line->beg + 1) * $self->ncol];
76 106
77 for (sort { $a->[1] <=> $b->[1] or $b->[0] <=> $a->[0] } @matches) { 107 for (sort { $a->[1] <=> $b->[1] or $b->[0] <=> $a->[0] } @matches) {
78 my ($ofs, $len) = @$_; 108 my ($ofs, $len) = @$_;
79 109
80 next if $len <= $curlen; 110 next if $len <= $curlen;
81 111
112 # convert back from UTF-8 offset space to character space
113 {
114 my $length = substr "$text ", $ofs, $len;
115 utf8::decode $length;
116 $len = length $length;
117 }
118 {
119 my $prefix = substr $text, 0, $ofs;
120 utf8::decode $prefix;
121 $ofs = length $prefix;
122 }
123
82 $self->selection_beg ($line->coord_of ($ofs)); 124 $self->selection_beg ($line->coord_of ($ofs));
83 $self->selection_end ($line->coord_of ($ofs + $len)); 125 $self->selection_end ($line->coord_of ($ofs + $len));
84 return 1; 126 return 1;
85 } 127 }
86 128
87 # whole line 129 ()
88 $self->selection_beg ($line->beg, 0);
89 $self->selection_end ($line->end, $self->ncol);
90
91 return 1;
92} 130}

Diff Legend

Removed lines
+ Added lines
< Changed lines
> Changed lines