| 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 = $self->x_resource ("selection-pastebin-cmd") |
|
|
| 11 | or "scp -p % ruth:/var/www/www.ta-sa.org/files/txt/"; |
|
|
| 12 | |
|
|
| 13 | $pastebin_url = $self->x_resource ("selection-pastebin-url") |
|
|
| 14 | or "http://www.ta-sa.org/files/txt/"; |
|
|
| 15 | (); |
|
|
| 16 | } |
|
|
| 17 | |
|
|
| 18 | sub upload_paste { |
|
|
| 19 | my ($self) = @_; |
|
|
| 20 | |
|
|
| 21 | my $txt = $self->selection; |
|
|
| 22 | my $filename = md5_hex ($txt) . ".txt"; |
|
|
| 23 | |
|
|
| 24 | my $tmpfile = "/tmp/$filename"; |
|
|
| 25 | |
|
|
| 26 | my $msg = "uploaded $filename"; |
|
|
| 27 | |
|
|
| 28 | if (open my $o, ">" . $tmpfile) { |
|
|
| 29 | print $o $txt; |
|
|
| 30 | close $o; |
|
|
| 31 | } else { |
|
|
| 32 | $msg = "couldn't write $tmpfile: $!"; |
|
|
| 33 | } |
|
|
| 34 | |
|
|
| 35 | my $cmd = $pastebin_cmd; |
|
|
| 36 | $cmd =~ s/%/$tmpfile/; |
|
|
| 37 | |
|
|
| 38 | if (system ($cmd) == 0) { |
|
|
| 39 | |
|
|
| 40 | my $url = $pastebin_url; |
|
|
| 41 | $url =~ s/%/$filename/; |
|
|
| 42 | |
|
|
| 43 | $self->selection ($url); |
|
|
| 44 | } else { |
|
|
| 45 | $msg = "couldn't upload, '$cmd' failed"; |
|
|
| 46 | } |
|
|
| 47 | |
|
|
| 48 | my $ov = $timers->{ov} = $self->overlay (-1, 0, length ($msg), 1, urxvt::OVERLAY_RSTYLE, 0); |
|
|
| 49 | $ov->set (0, 0, $msg); |
|
|
| 50 | |
|
|
| 51 | $timers->{t1} = |
|
|
| 52 | urxvt::timer |
|
|
| 53 | ->new |
|
|
| 54 | ->start ((int urxvt::NOW) + 5) # make sure we update "on" the second |
|
|
| 55 | ->interval (1) |
|
|
| 56 | ->cb (sub { delete $timers->{ov}; delete $timers->{t1}; }); |
|
|
| 57 | } |
|
|
| 58 | |
2 | |
| 59 | sub on_keyboard_command { |
3 | sub on_keyboard_command { |
| 60 | my ($self, $cmd) = @_; |
4 | my ($self, $cmd) = @_; |
| 61 | |
5 | |
| 62 | $cmd eq "selection:rot13" |
6 | $cmd eq "selection:rot13" |
| 63 | 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); |
| 64 | |
|
|
| 65 | $cmd eq "selection:remote-pastebin" |
|
|
| 66 | and upload_paste ($self); |
|
|
| 67 | |
8 | |
| 68 | () |
9 | () |
| 69 | } |
10 | } |
| 70 | |
11 | |
| 71 | sub on_init { |
12 | sub on_init { |
| 72 | my ($self) = @_; |
13 | my ($self) = @_; |
| 73 | |
14 | |
| 74 | for (my $idx = 0; defined (my $res = $self->x_resource ("selection.pattern-$idx")); $idx++) { |
15 | for (my $idx = 0; defined (my $res = $self->x_resource ("selection.pattern-$idx")); $idx++) { |
| 75 | no re 'eval'; # just to be sure |
|
|
| 76 | $res = utf8::encode $self->locale_decode ($res); |
16 | $res = $self->locale_decode ($res); |
|
|
17 | utf8::encode $res; |
| 77 | push @{ $self->{patterns} }, qr/$res/; |
18 | push @{ $self->{patterns} }, qr/$res/; |
| 78 | } |
19 | } |
| 79 | |
20 | |
| 80 | () |
21 | () |
| 81 | } |
22 | } |
| 82 | |
23 | |
| 83 | # "find interetsing things"-patterns |
24 | # "find interesting things"-patterns |
| 84 | my @mark_patterns = ( |
25 | my @mark_patterns = ( |
| 85 | # common types of "parentheses" |
26 | # common types of "parentheses" |
| 86 | qr{ (?<![^[:space:]]) ‘ ([^‘’]+) ’ (?![^[:space]]) }x, |
27 | qr{ (?<![^[:space:]]) ‘ ([^‘’]+) ’ (?![^[:space]]) }x, |
| 87 | qr{ (?<![^[:space:]]) ` ([^`']+) ' (?![^[:space]]) }x, |
28 | qr{ (?<![^[:space:]]) ` ([^`']+) ' (?![^[:space]]) }x, |
| 88 | qr{ (?<![^[:space:]]) (" [^[:space:]] [^"]* ") }x, |
29 | qr{ (?<![^[:space:]]) (" [^[:space:]] [^"]* ") }x, |
| … | |
… | |
| 97 | (?:https?|ftp|news|mailto|file)://[ab-zA-Z0-9\-\@;\/?:&=%\$_.+!*\x27(),~]+ |
38 | (?:https?|ftp|news|mailto|file)://[ab-zA-Z0-9\-\@;\/?:&=%\$_.+!*\x27(),~]+ |
| 98 | [ab-zA-Z0-9\-\@;\/?:&=%\$_+!*\x27()~] # exclude some trailing characters (heuristic) |
39 | [ab-zA-Z0-9\-\@;\/?:&=%\$_+!*\x27()~] # exclude some trailing characters (heuristic) |
| 99 | )}x, |
40 | )}x, |
| 100 | |
41 | |
| 101 | # shell-like argument quoting, basically always matches |
42 | # shell-like argument quoting, basically always matches |
| 102 | qr{\G [\ \t|&;<>()] *( |
43 | qr{\G [\ \t|&;<>()]* ( |
| 103 | (?: |
44 | (?: |
| 104 | [^\\"'\ \t|&;<>()]+ |
45 | [^\\"'\ \t|&;<>()]+ |
| 105 | | \\. |
46 | | \\. |
| 106 | | " (?: [^\\"]+ | \\. )* " |
47 | | " (?: [^\\"]+ | \\. )* " |
| 107 | | ' [^']* ' |
48 | | ' [^']* ' |
| … | |
… | |
| 125 | my $curlen = $line->offset_of ($self->selection_end) |
66 | my $curlen = $line->offset_of ($self->selection_end) |
| 126 | - $line->offset_of ($self->selection_beg); |
67 | - $line->offset_of ($self->selection_beg); |
| 127 | |
68 | |
| 128 | my @matches; |
69 | my @matches; |
| 129 | |
70 | |
| 130 | # not doing matches in unicode mode helps speed |
71 | if ($markofs < $line->l) { |
| 131 | # enourmously here. working in utf-8 should be |
72 | # convert markofs form character to UTF-8 offset space |
| 132 | # equivalent due to the magic of utf-8 encoding. |
73 | { |
|
|
74 | my $prefix = substr $text, 0, $markofs; |
| 133 | utf8::encode $text; |
75 | utf8::encode $prefix; |
| 134 | study $text; # _really_ helps, too :) |
76 | $markofs = length $prefix; |
|
|
77 | } |
| 135 | |
78 | |
| 136 | for my $regex (@mark_patterns, @{ $self->{patterns} }) { |
79 | # not doing matches in unicode mode helps speed |
| 137 | while ($text =~ /$regex/g) { |
80 | # enourmously here. working in utf-8 should be |
| 138 | if ($-[1] <= $markofs and $markofs <= $+[1]) { |
81 | # equivalent due to the magic of utf-8 encoding. |
| 139 | my $ofs = $-[1]; |
82 | utf8::encode $text; |
| 140 | my $match = $1; |
83 | study $text; # _really_ helps, too :) |
| 141 | |
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 | |
| 142 | for my $regex (@simplify_patterns) { |
91 | for my $regex (@simplify_patterns) { |
| 143 | if ($match =~ $regex) { |
92 | if ($match =~ $regex) { |
| 144 | $match = $1; |
93 | $match = $1; |
| 145 | $ofs += $-[1]; |
94 | $ofs += $-[1]; |
|
|
95 | } |
| 146 | } |
96 | } |
|
|
97 | |
|
|
98 | push @matches, [$ofs, length $match]; |
| 147 | } |
99 | } |
| 148 | |
|
|
| 149 | push @matches, [$ofs, length $match]; |
|
|
| 150 | } |
100 | } |
| 151 | } |
101 | } |
| 152 | } |
102 | } |
| 153 | |
103 | |
| 154 | # whole line |
104 | # whole line |
| … | |
… | |
| 157 | for (sort { $a->[1] <=> $b->[1] or $b->[0] <=> $a->[0] } @matches) { |
107 | for (sort { $a->[1] <=> $b->[1] or $b->[0] <=> $a->[0] } @matches) { |
| 158 | my ($ofs, $len) = @$_; |
108 | my ($ofs, $len) = @$_; |
| 159 | |
109 | |
| 160 | next if $len <= $curlen; |
110 | next if $len <= $curlen; |
| 161 | |
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 | |
| 162 | $self->selection_beg ($line->coord_of ($ofs)); |
124 | $self->selection_beg ($line->coord_of ($ofs)); |
| 163 | $self->selection_end ($line->coord_of ($ofs + $len)); |
125 | $self->selection_end ($line->coord_of ($ofs + $len)); |
| 164 | return 1; |
126 | return 1; |
| 165 | } |
127 | } |
| 166 | |
128 | |
