| … | |
… | |
| 67 | my $curlen = $line->offset_of ($self->selection_end) |
67 | my $curlen = $line->offset_of ($self->selection_end) |
| 68 | - $line->offset_of ($self->selection_beg); |
68 | - $line->offset_of ($self->selection_beg); |
| 69 | |
69 | |
| 70 | my @matches; |
70 | my @matches; |
| 71 | |
71 | |
| 72 | # not doing matches in unicode mode helps speed |
72 | if ($markofs < $line->l) { |
| 73 | # enourmously here. working in utf-8 should be |
73 | # convert markofs form character to UTF-8 offset space |
| 74 | # equivalent due to the magic of utf-8 encoding. |
74 | { |
|
|
75 | my $prefix = substr $text, 0, $markofs; |
| 75 | utf8::encode $text; |
76 | utf8::encode $prefix; |
| 76 | study $text; # _really_ helps, too :) |
77 | $markofs = length $prefix; |
|
|
78 | } |
| 77 | |
79 | |
| 78 | for my $regex (@mark_patterns, @{ $self->{patterns} }) { |
80 | # not doing matches in unicode mode helps speed |
| 79 | while ($text =~ /$regex/g) { |
81 | # enourmously here. working in utf-8 should be |
| 80 | if ($-[1] <= $markofs and $markofs <= $+[1]) { |
82 | # equivalent due to the magic of utf-8 encoding. |
| 81 | my $ofs = $-[1]; |
83 | utf8::encode $text; |
| 82 | my $match = $1; |
84 | study $text; # _really_ helps, too :) |
| 83 | |
85 | |
|
|
86 | for my $regex (@mark_patterns, @{ $self->{patterns} }) { |
|
|
87 | while ($text =~ /$regex/g) { |
|
|
88 | if ($-[1] <= $markofs and $markofs <= $+[1]) { |
|
|
89 | my $ofs = $-[1]; |
|
|
90 | my $match = $1; |
|
|
91 | |
| 84 | for my $regex (@simplify_patterns) { |
92 | for my $regex (@simplify_patterns) { |
| 85 | if ($match =~ $regex) { |
93 | if ($match =~ $regex) { |
| 86 | $match = $1; |
94 | $match = $1; |
| 87 | $ofs += $-[1]; |
95 | $ofs += $-[1]; |
|
|
96 | } |
| 88 | } |
97 | } |
|
|
98 | |
|
|
99 | push @matches, [$ofs, length $match]; |
| 89 | } |
100 | } |
| 90 | |
|
|
| 91 | push @matches, [$ofs, length $match]; |
|
|
| 92 | } |
101 | } |
| 93 | } |
102 | } |
| 94 | } |
103 | } |
| 95 | |
104 | |
| 96 | # whole line |
105 | # whole line |
| … | |
… | |
| 99 | for (sort { $a->[1] <=> $b->[1] or $b->[0] <=> $a->[0] } @matches) { |
108 | for (sort { $a->[1] <=> $b->[1] or $b->[0] <=> $a->[0] } @matches) { |
| 100 | my ($ofs, $len) = @$_; |
109 | my ($ofs, $len) = @$_; |
| 101 | |
110 | |
| 102 | next if $len <= $curlen; |
111 | next if $len <= $curlen; |
| 103 | |
112 | |
|
|
113 | # convert back from UTF-8 offset space to character space |
|
|
114 | { |
|
|
115 | my $length = substr $text, $ofs, $len; |
|
|
116 | utf8::decode $length; |
|
|
117 | $len = length $length; |
|
|
118 | } |
|
|
119 | { |
|
|
120 | my $prefix = substr $text, 0, $ofs; |
|
|
121 | utf8::decode $prefix; |
|
|
122 | $ofs = length $prefix; |
|
|
123 | } |
|
|
124 | |
| 104 | $self->selection_beg ($line->coord_of ($ofs)); |
125 | $self->selection_beg ($line->coord_of ($ofs)); |
| 105 | $self->selection_end ($line->coord_of ($ofs + $len)); |
126 | $self->selection_end ($line->coord_of ($ofs + $len)); |
| 106 | return 1; |
127 | return 1; |
| 107 | } |
128 | } |
| 108 | |
129 | |
