1 | #! perl |
1 | #! perl |
2 | |
2 | |
3 | sub on_keyboard_command { |
3 | sub on_user_command { |
4 | my ($self, $cmd) = @_; |
4 | my ($self, $cmd) = @_; |
5 | |
5 | |
6 | $cmd eq "selection:rot13" |
6 | $cmd eq "selection:rot13" |
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/; $_ } $self->selection); |
8 | |
8 | |
9 | () |
9 | () |
10 | } |
10 | } |
11 | |
11 | |
|
|
12 | sub on_init { |
|
|
13 | my ($self) = @_; |
|
|
14 | |
|
|
15 | if (defined (my $res = $self->resource ("cutchars"))) { |
|
|
16 | $res = $self->locale_decode ($res); |
|
|
17 | push @{ $self->{patterns} }, qr{\G [\Q$res\E[:space:]]* ([^\Q$res\E[:space:]]+) }x; |
|
|
18 | } |
|
|
19 | |
|
|
20 | for (my $idx = 0; defined (my $res = $self->x_resource ("selection.pattern-$idx")); $idx++) { |
|
|
21 | $res = $self->locale_decode ($res); |
|
|
22 | utf8::encode $res; |
|
|
23 | push @{ $self->{patterns} }, qr/$res/; |
|
|
24 | } |
|
|
25 | |
|
|
26 | $self->{enabled} = 1; |
|
|
27 | |
|
|
28 | push @{ $self->{term}{option_popup_hook} }, sub { |
|
|
29 | ("new selection" => $self->{enabled}, sub { $self->{enabled} = shift }) |
|
|
30 | }; |
|
|
31 | |
|
|
32 | () |
|
|
33 | } |
|
|
34 | |
12 | # "find interetsing things"-patterns |
35 | # "find interesting things"-patterns |
13 | my @mark_patterns = ( |
36 | my @mark_patterns = ( |
|
|
37 | qr{ ([[:word:]]+) }x, |
|
|
38 | qr{ ([^[:space:]]+) }x, |
|
|
39 | |
|
|
40 | # common types of "parentheses" |
|
|
41 | qr{ (?<![^[:space:]]) ` ([^‘’]+) ` (?![^[:space:]]) }x, |
|
|
42 | qr{ (?<![^[:space:]]) ‘ ([^‘’]+) ’ (?![^[:space:]]) }x, |
|
|
43 | qr{ (?<![^[:space:]]) ` ([^`']+) ' (?![^[:space:]]) }x, |
|
|
44 | |
|
|
45 | qr{ (?<![^[:space:]]) ‘ ([^`']+) ’ (?![^[:space:]]) }x, |
|
|
46 | qr{ (?<![^[:space:]]) “ ([^`']+) ” (?![^[:space:]]) }x, |
|
|
47 | |
|
|
48 | qr{ (?<![^[:space:]]) (' [^[:space:]] [^']* ') }x, |
|
|
49 | qr{ (' [^']* [^[:space:]] ') (?![^[:space:]]) }x, |
|
|
50 | qr{ (?<![^[:space:]]) (" [^[:space:]] [^"]* ") }x, |
|
|
51 | qr{ (" [^"]* [^[:space:]] ") (?![^[:space:]]) }x, |
|
|
52 | |
|
|
53 | qr{ \< ([^>]+) \> }x, |
|
|
54 | qr{ \( ([^)]+) \) }x, |
|
|
55 | qr{ \{ ([^}]+) \} }x, |
|
|
56 | qr{ \[ ([^]]+) \] }x, |
|
|
57 | |
14 | # urls, just a heuristic |
58 | # urls, just a heuristic |
15 | qr{( |
59 | qr{( |
16 | (?:https?|ftp|news|mailto|file)://[ab-zA-Z0-9\-\@;\/?:&=%\$_.+!*\x27(),~]+ |
60 | (?:https?://|ftp://|news://|mailto:|file://|\bwww\.)[ab-zA-Z0-9\-\@;\/?:&=%\$_.+!*\x27(),~#]+ |
17 | [ab-zA-Z0-9\-\@;\/?:&=%\$_+!*\x27(),~] # do not include a trailing dot, its wrong too often |
61 | [ab-zA-Z0-9\-\@;\/?:&=%\$_+*()~] # exclude some trailing characters (heuristic) |
18 | )}x, |
62 | )}x, |
19 | |
63 | |
20 | # common "parentheses" |
|
|
21 | qr{(?:^|\s) ‘ ([^‘’]+?) ’ (?:\s|\)|$)}x, |
|
|
22 | qr{(?:^|\s) ` ([^`']+?) ' (?:\s|\)|$)}x, |
|
|
23 | qr{ \{ ([^{}]+?) \} }x, |
|
|
24 | qr{ \[ ([^{}]+?) \] }x, |
|
|
25 | |
|
|
26 | # shell-like argument quoting, basically always matches |
64 | # shell-like argument quoting, basically always matches |
27 | qr{\G [\ \t|&;<>()] *( |
65 | qr{\G [\ \t|&;<>()]* ( |
28 | (?: |
66 | (?: |
29 | [^\\"'\ \t|&;<>()]+ |
67 | [^\\"'\ \t|&;<>()]+ |
30 | | \\. |
68 | | \\. |
31 | | " (?: [^\\"]+ | \\. )* " |
69 | | " (?: [^\\"]+ | \\. )* " |
32 | | ' [^']* ' |
70 | | ' [^']* ' |
… | |
… | |
39 | qr{^"([^\\"'\ \t|&;<>()*?]+)"$}, # "simple" => simple |
77 | qr{^"([^\\"'\ \t|&;<>()*?]+)"$}, # "simple" => simple |
40 | qr{^(.*)[,\-]$}, # strip off trailing , and - |
78 | qr{^(.*)[,\-]$}, # strip off trailing , and - |
41 | ); |
79 | ); |
42 | |
80 | |
43 | sub on_sel_extend { |
81 | sub on_sel_extend { |
44 | my ($self) = @_; |
82 | my ($self, $time) = @_; |
|
|
83 | |
|
|
84 | $self->{enabled} |
|
|
85 | or return; |
45 | |
86 | |
46 | my ($row, $col) = $self->selection_mark; |
87 | my ($row, $col) = $self->selection_mark; |
47 | my $line = $self->line ($row); |
88 | my $line = $self->line ($row); |
48 | my $offset = $line->offset_of ($row, $col); |
|
|
49 | my $text = $line->t; |
89 | my $text = $line->t; |
|
|
90 | my $markofs = $line->offset_of ($row, $col); |
|
|
91 | my $curlen = $line->offset_of ($self->selection_end) |
|
|
92 | - $line->offset_of ($self->selection_beg); |
50 | |
93 | |
51 | for my $regex (@mark_patterns) { |
94 | my @matches; |
52 | while ($text =~ /$regex/g) { |
|
|
53 | if ($-[1] <= $offset and $offset <= $+[1]) { |
|
|
54 | my $ofs = $-[1]; |
|
|
55 | my $match = $1; |
|
|
56 | |
95 | |
|
|
96 | if ($markofs < $line->l) { |
|
|
97 | # convert markofs from character to UTF-8 offset space |
|
|
98 | { |
|
|
99 | my $prefix = substr $text, 0, $markofs; |
|
|
100 | utf8::encode $prefix; |
|
|
101 | $markofs = length $prefix; |
|
|
102 | } |
|
|
103 | |
|
|
104 | # not doing matches in unicode mode helps speed |
|
|
105 | # enourmously here. working in utf-8 should be |
|
|
106 | # equivalent due to the magic of utf-8 encoding. |
|
|
107 | utf8::encode $text; |
|
|
108 | study $text; # _really_ helps, too :) |
|
|
109 | |
|
|
110 | for my $regex (@mark_patterns, @{ $self->{patterns} }) { |
|
|
111 | while ($text =~ /$regex/g) { |
|
|
112 | if ($-[1] <= $markofs and $markofs <= $+[1]) { |
|
|
113 | my $ofs = $-[1]; |
|
|
114 | my $match = $1; |
|
|
115 | |
57 | for my $regex (@simplify_patterns) { |
116 | for my $regex (@simplify_patterns) { |
58 | if ($match =~ $regex) { |
117 | if ($match =~ $regex) { |
59 | $match = $1; |
118 | $match = $1; |
60 | $ofs += $-[1]; |
119 | $ofs += $-[1]; |
|
|
120 | } |
61 | } |
121 | } |
|
|
122 | |
|
|
123 | push @matches, [$ofs, length $match]; |
62 | } |
124 | } |
63 | |
|
|
64 | $self->selection_beg ($line->coord_of ($ofs)); |
|
|
65 | $self->selection_end ($line->coord_of ($ofs + length $match)); |
|
|
66 | return 1; |
|
|
67 | } |
125 | } |
68 | } |
126 | } |
69 | } |
127 | } |
70 | |
128 | |
|
|
129 | # whole line |
|
|
130 | push @matches, [0, ($line->end - $line->beg + 1) * $self->ncol]; |
|
|
131 | |
|
|
132 | for (sort { $a->[1] <=> $b->[1] or $b->[0] <=> $a->[0] } @matches) { |
|
|
133 | my ($ofs, $len) = @$_; |
|
|
134 | |
|
|
135 | next if $len <= $curlen; |
|
|
136 | |
|
|
137 | # convert back from UTF-8 offset space to character space |
|
|
138 | { |
|
|
139 | my $length = substr "$text ", $ofs, $len; |
|
|
140 | utf8::decode $length; |
|
|
141 | $len = length $length; |
|
|
142 | } |
|
|
143 | { |
|
|
144 | my $prefix = substr $text, 0, $ofs; |
|
|
145 | utf8::decode $prefix; |
|
|
146 | $ofs = length $prefix; |
|
|
147 | } |
|
|
148 | |
|
|
149 | $self->selection_beg ($line->coord_of ($ofs)); |
|
|
150 | $self->selection_end ($line->coord_of ($ofs + $len)); |
|
|
151 | return 1; |
|
|
152 | } |
|
|
153 | |
71 | () |
154 | () |
72 | } |
155 | } |