| 1 | #! perl |
1 | #! perl |
| 2 | use Digest::MD5 qw/md5_hex/; |
|
|
| 3 | |
|
|
| 4 | my $timers = {}; |
|
|
| 5 | my $pastebin_cmd; |
|
|
| 6 | my $pastebin_url; |
|
|
| 7 | |
|
|
| 8 | sub on_start { |
|
|
| 9 | my ($self) = @_; |
|
|
| 10 | $pastebin_cmd = |
|
|
| 11 | (urxvt::untaint $self->x_resource ("selection-pastebin-cmd")) |
|
|
| 12 | or "scp -p % ruth:/var/www/www.ta-sa.org/files/txt/"; |
|
|
| 13 | |
|
|
| 14 | $pastebin_url = |
|
|
| 15 | (urxvt::untaint $self->x_resource ("selection-pastebin-url")) |
|
|
| 16 | or "http://www.ta-sa.org/files/txt/"; |
|
|
| 17 | (); |
|
|
| 18 | } |
|
|
| 19 | |
|
|
| 20 | sub upload_paste { |
|
|
| 21 | my ($self) = @_; |
|
|
| 22 | |
|
|
| 23 | my $txt = $self->selection; |
|
|
| 24 | my $h = md5_hex ($txt); |
|
|
| 25 | |
|
|
| 26 | my $fn = "/tmp/$h.txt"; |
|
|
| 27 | |
|
|
| 28 | my $msg = "uploaded $h.txt"; |
|
|
| 29 | |
|
|
| 30 | if (open my $o, ">" . $fn) { |
|
|
| 31 | print $o $txt; |
|
|
| 32 | close $o; |
|
|
| 33 | } else { |
|
|
| 34 | $msg = "couldn't write $fn: $!"; |
|
|
| 35 | } |
|
|
| 36 | |
|
|
| 37 | my $cmd = $pastebin_cmd; |
|
|
| 38 | $cmd =~ s/%/$fn/; |
|
|
| 39 | unless (system ($cmd) == 0) { |
|
|
| 40 | $msg = "couldn't upload, '$cmd' failed"; |
|
|
| 41 | } |
|
|
| 42 | |
|
|
| 43 | $self->selection ($pastebin_url . "$h.txt"); |
|
|
| 44 | |
|
|
| 45 | my $ov = $timers->{ov} = $self->overlay (-1, 0, length ($msg), 1, urxvt::OVERLAY_RSTYLE, 0); |
|
|
| 46 | $ov->set (0, 0, $msg); |
|
|
| 47 | |
|
|
| 48 | $timers->{t1} = |
|
|
| 49 | urxvt::timer |
|
|
| 50 | ->new |
|
|
| 51 | ->start ((int urxvt::NOW) + 5) # make sure we update "on" the second |
|
|
| 52 | ->interval (1) |
|
|
| 53 | ->cb (sub { delete $timers->{ov}; delete $timers->{t1}; }); |
|
|
| 54 | } |
|
|
| 55 | |
2 | |
| 56 | sub on_keyboard_command { |
3 | sub on_keyboard_command { |
| 57 | my ($self, $cmd) = @_; |
4 | my ($self, $cmd) = @_; |
| 58 | |
5 | |
| 59 | $cmd eq "selection:rot13" |
6 | $cmd eq "selection:rot13" |
| 60 | 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); |
| 61 | |
8 | |
| 62 | $cmd eq "selection:remote-pastebin" |
|
|
| 63 | and upload_paste ($self); |
|
|
| 64 | |
|
|
| 65 | () |
9 | () |
| 66 | } |
10 | } |
| 67 | |
11 | |
| 68 | sub on_init { |
12 | sub on_init { |
| 69 | my ($self) = @_; |
13 | my ($self) = @_; |
| 70 | |
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 | |
| 71 | for (my $idx = 0; defined (my $res = $self->x_resource ("selection.pattern-$idx")); $idx++) { |
20 | for (my $idx = 0; defined (my $res = $self->x_resource ("selection.pattern-$idx")); $idx++) { |
| 72 | no re 'eval'; # just to be sure |
|
|
| 73 | $res = utf8::encode $self->locale_decode ($res); |
21 | $res = $self->locale_decode ($res); |
|
|
22 | utf8::encode $res; |
| 74 | push @{ $self->{patterns} }, qr/$res/; |
23 | push @{ $self->{patterns} }, qr/$res/; |
| 75 | } |
24 | } |
| 76 | |
25 | |
| 77 | () |
26 | () |
| 78 | } |
27 | } |
| 79 | |
28 | |
| 80 | # "find interetsing things"-patterns |
29 | # "find interesting things"-patterns |
| 81 | my @mark_patterns = ( |
30 | my @mark_patterns = ( |
| 82 | # common types of "parentheses" |
31 | # common types of "parentheses" |
| 83 | qr{ (?<![^[:space:]]) ‘ ([^‘’]+) ’ (?![^[:space]]) }x, |
32 | qr{ (?<![^[:space:]]) ‘ ([^‘’]+) ’ (?![^[:space]]) }x, |
| 84 | qr{ (?<![^[:space:]]) ` ([^`']+) ' (?![^[:space]]) }x, |
33 | qr{ (?<![^[:space:]]) ` ([^`']+) ' (?![^[:space]]) }x, |
| 85 | qr{ (?<![^[:space:]]) (" [^[:space:]] [^"]* ") }x, |
34 | qr{ (?<![^[:space:]]) (" [^[:space:]] [^"]* ") }x, |
| … | |
… | |
| 94 | (?:https?|ftp|news|mailto|file)://[ab-zA-Z0-9\-\@;\/?:&=%\$_.+!*\x27(),~]+ |
43 | (?:https?|ftp|news|mailto|file)://[ab-zA-Z0-9\-\@;\/?:&=%\$_.+!*\x27(),~]+ |
| 95 | [ab-zA-Z0-9\-\@;\/?:&=%\$_+!*\x27()~] # exclude some trailing characters (heuristic) |
44 | [ab-zA-Z0-9\-\@;\/?:&=%\$_+!*\x27()~] # exclude some trailing characters (heuristic) |
| 96 | )}x, |
45 | )}x, |
| 97 | |
46 | |
| 98 | # shell-like argument quoting, basically always matches |
47 | # shell-like argument quoting, basically always matches |
| 99 | qr{\G [\ \t|&;<>()] *( |
48 | qr{\G [\ \t|&;<>()]* ( |
| 100 | (?: |
49 | (?: |
| 101 | [^\\"'\ \t|&;<>()]+ |
50 | [^\\"'\ \t|&;<>()]+ |
| 102 | | \\. |
51 | | \\. |
| 103 | | " (?: [^\\"]+ | \\. )* " |
52 | | " (?: [^\\"]+ | \\. )* " |
| 104 | | ' [^']* ' |
53 | | ' [^']* ' |
| … | |
… | |
| 122 | my $curlen = $line->offset_of ($self->selection_end) |
71 | my $curlen = $line->offset_of ($self->selection_end) |
| 123 | - $line->offset_of ($self->selection_beg); |
72 | - $line->offset_of ($self->selection_beg); |
| 124 | |
73 | |
| 125 | my @matches; |
74 | my @matches; |
| 126 | |
75 | |
| 127 | # not doing matches in unicode mode helps speed |
76 | if ($markofs < $line->l) { |
| 128 | # enourmously here. working in utf-8 should be |
77 | # convert markofs form character to UTF-8 offset space |
| 129 | # equivalent due to the magic of utf-8 encoding. |
78 | { |
|
|
79 | my $prefix = substr $text, 0, $markofs; |
| 130 | utf8::encode $text; |
80 | utf8::encode $prefix; |
| 131 | study $text; # _really_ helps, too :) |
81 | $markofs = length $prefix; |
|
|
82 | } |
| 132 | |
83 | |
| 133 | for my $regex (@mark_patterns, @{ $self->{patterns} }) { |
84 | # not doing matches in unicode mode helps speed |
| 134 | while ($text =~ /$regex/g) { |
85 | # enourmously here. working in utf-8 should be |
| 135 | if ($-[1] <= $markofs and $markofs <= $+[1]) { |
86 | # equivalent due to the magic of utf-8 encoding. |
| 136 | my $ofs = $-[1]; |
87 | utf8::encode $text; |
| 137 | my $match = $1; |
88 | study $text; # _really_ helps, too :) |
| 138 | |
89 | |
|
|
90 | for my $regex (@mark_patterns, @{ $self->{patterns} }) { |
|
|
91 | while ($text =~ /$regex/g) { |
|
|
92 | if ($-[1] <= $markofs and $markofs <= $+[1]) { |
|
|
93 | my $ofs = $-[1]; |
|
|
94 | my $match = $1; |
|
|
95 | |
| 139 | for my $regex (@simplify_patterns) { |
96 | for my $regex (@simplify_patterns) { |
| 140 | if ($match =~ $regex) { |
97 | if ($match =~ $regex) { |
| 141 | $match = $1; |
98 | $match = $1; |
| 142 | $ofs += $-[1]; |
99 | $ofs += $-[1]; |
|
|
100 | } |
| 143 | } |
101 | } |
|
|
102 | |
|
|
103 | push @matches, [$ofs, length $match]; |
| 144 | } |
104 | } |
| 145 | |
|
|
| 146 | push @matches, [$ofs, length $match]; |
|
|
| 147 | } |
105 | } |
| 148 | } |
106 | } |
| 149 | } |
107 | } |
| 150 | |
108 | |
| 151 | # whole line |
109 | # whole line |
| … | |
… | |
| 154 | for (sort { $a->[1] <=> $b->[1] or $b->[0] <=> $a->[0] } @matches) { |
112 | for (sort { $a->[1] <=> $b->[1] or $b->[0] <=> $a->[0] } @matches) { |
| 155 | my ($ofs, $len) = @$_; |
113 | my ($ofs, $len) = @$_; |
| 156 | |
114 | |
| 157 | next if $len <= $curlen; |
115 | next if $len <= $curlen; |
| 158 | |
116 | |
|
|
117 | # convert back from UTF-8 offset space to character space |
|
|
118 | { |
|
|
119 | my $length = substr "$text ", $ofs, $len; |
|
|
120 | utf8::decode $length; |
|
|
121 | $len = length $length; |
|
|
122 | } |
|
|
123 | { |
|
|
124 | my $prefix = substr $text, 0, $ofs; |
|
|
125 | utf8::decode $prefix; |
|
|
126 | $ofs = length $prefix; |
|
|
127 | } |
|
|
128 | |
| 159 | $self->selection_beg ($line->coord_of ($ofs)); |
129 | $self->selection_beg ($line->coord_of ($ofs)); |
| 160 | $self->selection_end ($line->coord_of ($ofs + $len)); |
130 | $self->selection_end ($line->coord_of ($ofs + $len)); |
| 161 | return 1; |
131 | return 1; |
| 162 | } |
132 | } |
| 163 | |
133 | |
