diff options
Diffstat (limited to 'unifmt.pl')
| -rw-r--r-- | unifmt.pl | 611 |
1 files changed, 611 insertions, 0 deletions
diff --git a/unifmt.pl b/unifmt.pl new file mode 100644 index 0000000..7622c0f --- /dev/null +++ b/unifmt.pl @@ -0,0 +1,611 @@ +#!/usr/bin/perl + +# TODO: +# Braille. + +# to read the docs outside of irssi: perldoc /path/to/unifmt.pl +# in irssi, "/script load unifmt.pl", then "/unifmt_help" + +=encoding utf8 + +=pod + +=head1 NAME + +unifmt.pl - unicode text formatting for irssi + +=head1 SYNOPSIS + +in shell: cp unifmt.pl ~/.irssi/scripts/ + +in irssi: /script load unifmt.pl + +=head1 DESCRIPTION + +unifmt.pl adds keystrokes to irssi that allow you to type double-width +ASCII (Unicode FF00 block) characters, blackletter characters, and +use Unicode combining characters to make your text appear underlined +(single or double line), struck out, or "slashed" out. + +Rather than executing the script as an irssi slash-command, the modes are +controlled via keystrokes. This allows the formatted text to be mixed +with normal or differently-formatted text on the same line of input. + +There are 2 classes of formatting: "transforms", which convert plain +Latin alphabetics to other characters (such as fraktur or italic), and +"combines", which use plain Latin alphabetics followed by a combining +character (such as an underline). + +You can mix combines and transforms, e.g. underlined fraktur, but only +one combine and one transform can be enabled at a time (so you can't +do e.g. both underline and strikethrough, or both subscript and bold +serif). + +=head1 KEYSTROKES + +All the formatting controls must be preceded by a prefix character, +which defaults B<^F> (control-F). + +=over 4 + +=head2 Transforms + +=item B<^F w> + +Enables wide formatting. Each character you type is replaced by its +double-width equivalent from the Unicode B<U+FF01-U+FFE1> range, if +it has one. Only characters B<U+0021-U+007E> (AKA the printable ASCII +charset) have double-width equivalents. As a special case, the space +(B<U+0020>) character is replaced with B<U+3000>, B<IDEOGRAPHIC SPACE>, which +is a double-width space. All other characters are treated normally. + + Example: Ｔｈｉｓ ｉｓ ｗｉｄｅ ｔｅｘｔ + +=item B<^F b> + +Bold sans serif. + + Example: 𝗧𝗵𝗶𝘀 𝗶𝘀 𝗯𝗼𝗹𝗱 𝘀𝗮𝗻𝘀 + +=item B<^F i> + +Italic sans serif + + Example: 𝘛𝘩𝘪𝘴 𝘪𝘴 𝘪𝘵𝘢𝘭𝘪𝘤 𝘴𝘢𝘯𝘴 + +=item B<^F j> + +Bold italic sans serif + + Example: 𝙏𝙝𝙞𝙨 𝙞𝙨 𝙗𝙤𝙡𝙙 𝙞𝙩𝙖𝙡𝙞𝙘 𝙨𝙖𝙣𝙨 + +=item B<^F B> + +Bold serif. + + Example: 𝐓𝐡𝐢𝐬 𝐢𝐬 𝐛𝐨𝐥𝐝 𝐬𝐞𝐫𝐢𝐟 + +=item B<^F I> + +Italic serif + + Example: 𝑇ℎ𝑖𝑠 𝑖𝑠 𝑖𝑡𝑎𝑙𝑖𝑐 𝑠𝑒𝑟𝑖𝑓 + +=item B<^F J> + +Bold italic serif + + Example: 𝑻𝒉𝒊𝒔 𝒊𝒔 𝒃𝒐𝒍𝒅 𝒊𝒕𝒂𝒍𝒊𝒄 𝒔𝒆𝒓𝒊𝒇 + +=item B<^F 2> + +Double-struck + + Example: 𝕋𝕙𝕚𝕤 𝕚𝕤 𝕕𝕠𝕦𝕓𝕝𝕖-𝕤𝕥𝕣𝕦𝕔𝕜 + +=item B<^F c> + +Cursive + + Example: 𝒯𝒽𝒾𝓈 𝒾𝓈 𝒸𝓊𝓇𝓈𝒾𝓋ℯ + +=item B<^F C> + +Bold cursive + + Example: 𝓣𝓱𝓲𝓼 𝓲𝓼 𝓫𝓸𝓵𝓭 𝓬𝓾𝓻𝓼𝓲𝓿𝓮 + +=item B<^F k> + +Fraktur (aka blackletter) + + Example: 𝔗𝔥𝔦𝔰 𝔦𝔰 𝔣𝔯𝔞𝔨𝔱𝔲𝔯 + +I am aware that the Mathematical Fraktur symbols were never intended +for use as text, but this script is for fun, not for standards compliance. + +=item B<^F K> + + Example: 𝔗𝔥𝔦𝔰 𝔦𝔰 𝔣𝔯𝔞𝔨𝔱𝔲𝔯 + +Bold fraktur (aka blackletter) + + Example: 𝕿𝖍𝖎𝖘 𝖎𝖘 𝖇𝖔𝖑𝖉 𝖋𝖗𝖆𝖐𝖙𝖚𝖗 + +=item B<^F ^> + +Superscript. This isn't perfect: a few superscripted letters only +exist in Unicode as either uppercase or lowercase, so e.g. all +lowercase B<i> characters will display as superscripted capital B<I>. + + Example: ᵀʰᶦˢ ᶦˢ ˢᵘᵖᵉʳˢᶜʳᶦᵖᵗ + +=head2 Combines + +=item B<^F _> + +Enables underlining. Each character you type is followed by the Unicode +combining character B<U+0332>, B<COMBINING LOW LINE>. Example: U̲n̲d̲e̲r̲l̲i̲n̲e̲d̲ + +=item B<^F => + +Enables double underlining. Each character you type is followed by the Unicode +combining character B<U+0333>, B<COMBINING DOUBLE LOW LINE>. Example: U̳n̳d̳e̳r̳l̳i̳n̳e̳d̳ + +=item B<^F -> + +Enables strikethrough. Each character you type is followed by the Unicode +combining character B<U+0336>, B<COMBINING LONG STROKE OVERLAY>. Example: S̶t̶r̶i̶k̶e̶t̶h̶r̶o̶u̶g̶h̶ + +=item B<^F /> + +Enables slashthrough. Each character you type is followed by the Unicode +combining character B<U+0338>, B<COMBINING LONG SOLIDUS OVERLAY>. Example: S̸l̸a̸s̸h̸o̸u̸t̸ + +=item B<^F ^F> + +Acts like a single B<^F> was pressed. Does not disable formatting. If +you have a regular irssi keybinding for B<^F>, it will be acted on. +Otherwise, a B<^F> will be inserted into the input buffer. + +=item B<^F F> + +Disables all the formatting modes. Actually, B<^F> followed by any character +not listed above will do the same thing, but I promise not to change +the B<^F F> combo in any future versions of this script. + +=back + +=head1 SETTINGS + +=over 4 + +=item B<unifmt_keys> + +String, the 6 remappable keystrokes used to enable the formatting +modes. This defaults to B<fw_=-/>. The order is: Prefix, Wide, +Underline, Double-Underline, Strikethrough, Slashthrough (note: only +the combines are currently remappable; transforms are not). The prefix +key is used as a control key, but when you set it, use a regular +alphabetic (e.g. don't say B<^X>, just say B<x> or B<X>). + +=item B<unifmt_spaces> + +Boolean, whether or not to apply combines to spaces (default: false). + +=back + +=head1 NOTES + +For any of this to work, you'll have to enable UTF-8 in irssi, and use +a UTF-8 capable terminal. This applies to everyone else too: if you're +sending UTF-8 encoded Unicode to them, their client (and terminal if +it's a terminal client) will have to know how to display it. If not, +they'll see garbage in place of what you intended. + +This script was developed with urxvt (AKA rxvt-unicode). It should work +with any terminal that fully supports UTF-8 and Unicode... but you want +a terminal that supports looking up glyphs from a list of fonts, like +urxvt does. Otherwise, you might have a hard time finding a single font +that has all the glyphs you'll need. + +The editing keys (arrows, home/end, pgup/pgdn, and any alt-? combos) +might act strangely while the formatting modes are enabled, depending +on your terminal and TERM environment variable. Backspace and ^U +(kill line) should still work OK. This will probably be fixed in the +future. Tab-completing nicks doesn't work either, but fixing that will +be a huge PITA (or maybe impossible). + +None of the formatting modes persist past the end of the current line of +input. Pressing Enter always clears all the modes. This is to minimize +annoyance, as there's no visual indicator of which mode(s) you're in. + +Before you use this script on a public channel, you'd better make sure +the channel doesn't have rules against using fancy Unicode. You may +annoy the other users, and/or find yourself banned. + +tmux doesn't seem to be capable of actually displaying the wide + +combining character combinations. They render as plain wide. If you +copy/paste them to another window (a terminal not running tmux for +instance), they show up correctly. So tmux "knows" the formatting is +there, but doesn't display it. + +The underline, strike, slashout combinations don't work with screen, +and probably never will. I'd love to be proven wrong, so let me know if +you get it working there. I at least can see the wide characters with +"screen -U". + +=head1 AUTHOR + +Urchlay <urchlay@slackware.uk> + +=head1 LICENSE + +WTFPL: Do WTF you want with this. + +=head1 SEE ALSO + +irssi(1), urxvt(1), unicode(7), utf-8(7) + +=cut + +use utf8; +use feature 'unicode_strings'; + +our $VERSION = "0.2"; +our %IRSSI = ( + authors => 'Urchlay', + contact => 'Urchlay on FreeNode', + name => 'unifmt', + description => 'Fancy Unicode text formatting', + license => 'WTFPL', + url => 'https://slackware.uk/~urchlay/repos/misc-scripts', +); + +use warnings; +use strict; + +# 20200827 bkw: adding gui_input_get_pos to the list of imports causes +# this script to fail to autoload when irssi starts (but it'll load OK +# if manually loaded after startup). I only use it for debugging anyway. +use Irssi qw{ + command command_bind parse_special signal_register + signal_add_first signal_add_last signal_continue signal_emit + signal_stop settings_set_str settings_get_str settings_add_str + settings_get_bool settings_add_bool + }; + +our $SELF = $IRSSI{name}; +our $default_keys = "fw_=-/"; + +##sub xf_wide { +## my $key = shift; +## if($key == 0x20) { +## $key = 0x3000; +## } elsif($key >= 0x21 && $key <= 0x7e) { +## $key += 0xfee0; +## } +## return $key; +##} + +our %transforms = ( + 'Wide' => \&xf_wide, + 'Bold Serif' => \&xf_boldserif, + 'Italic Serif' => \&xf_italserif, + 'Bold Italic Serif' => \&xf_bolditalserif, + 'Bold Sans' => \&xf_boldsans, + 'Italic Sans' => \&xf_italsans, + 'Bold Italic Sans' => \&xf_bolditalsans, + 'Double-struck' => \&xf_doublestrike, + 'Cursive' => \&xf_cursive, + 'Bold Cursive' => \&xf_boldcursive, + 'Fraktur' => \&xf_fraktur, + 'Bold Fraktur' => \&xf_boldfraktur, + 'Superscript' => \&xf_superscript, +); + +our %transform_keys = ( + w => 'Wide', + B => 'Bold Serif', + I => 'Italic Serif', + J => 'Bold Italic Serif', + b => 'Bold Sans', + i => 'Italic Sans', + j => 'Bold Italic Sans', + 2 => 'Double-struck', + c => 'Cursive', + C => 'Bold Cursive', + k => 'Fraktur', + K => 'Bold Fraktur', + '^' => 'Superscript', +); + + +# Holds a reference to one of the xf_* subs, or undef if no +# transform is active. +our $transform; + +# These 2 are controlled by setting unifmt_keys: +our $prefix_key; +our %combining_map; + +# Which of combining_map is active, or 0 for none +our $combining_char = 0; + +# True if the last keypress was ^F +our $was_prefix = 0; + +# 2 if the last keypress was escape, 1 if the last 2 were escape and [, +# 0 otherwise. +our $was_escape = 0; + + +# There's no way to enable debugging without editing the script. +our $DEBUG = 0; + +# Only used for debugging. +our $count = 0; + +# Ditto. +sub dump_buf { + my $buf = parse_special('$L', 0, 0); + my $len = length($buf); + my $pos = Irssi::gui_input_get_pos(); + my $out = "pos==" . $pos . " "; + for(my $i = 0; $i < $len; $i++) { + my $star = ($i == $len ? "*" : ""); + $out .= sprintf("$star%02x ", ord(substr($buf, $i, 1))); + } + print $out; +} + +#### +# transforms take numeric Unicode codepoint arg, and return +# a numeric Unicode codepoint. + +sub xf_wide { + my $key = shift; + + if($key == 0x20) { + $key = 0x3000; # wide space, maybe better to avoid this? + } elsif($key >= 0x21 && $key <= 0x7e) { + # unicode 0x0f01 to 0x0fee are wide versions of ASCII + $key += 0xfee0; + } + # else pass it through as-is + + return $key; +} + +sub xf_alpha_map { + my $k = shift; + my $map = shift; + + ## warn "k was $k"; + if($k >= 65 && $k <= 90) { # A-Z + $k = ord(substr($map, $k - 65)); + } elsif($k >= 97 && $k <= 122) { # a-z + $k = ord(substr($map, $k - 97 + 26)); + } + ## warn "k now $k"; + + return $k; +} + +sub xf_boldserif { + return xf_alpha_map($_[0], "𝐀𝐁𝐂𝐃𝐄𝐅𝐆𝐇𝐈𝐉𝐊𝐋𝐌𝐍𝐎𝐏𝐐𝐑𝐒𝐓𝐔𝐕𝐖𝐗𝐘𝐙𝐚𝐛𝐜𝐝𝐞𝐟𝐠𝐡𝐢𝐣𝐤𝐥𝐦𝐧𝐨𝐩𝐪𝐫𝐬𝐭𝐮𝐯𝐰𝐱𝐲𝐳"); +} + +sub xf_italserif { + return xf_alpha_map($_[0], "𝐴𝐵𝐶𝐷𝐸𝐹𝐺𝐻𝐼𝐽𝐾𝐿𝑀𝑁𝑂𝑃𝑄𝑅𝑆𝑇𝑈𝑉𝑊𝑋𝑌𝑍𝑎𝑏𝑐𝑑𝑒𝑓𝑔ℎ𝑖𝑗𝑘𝑙𝑚𝑛𝑜𝑝𝑞𝑟𝑠𝑡𝑢𝑣𝑤𝑥𝑦𝑧"); +} + +sub xf_bolditalserif { + return xf_alpha_map($_[0], "𝑨𝑩𝑪𝑫𝑬𝑭𝑮𝑯𝑰𝑱𝑲𝑳𝑴𝑵𝑶𝑷𝑸𝑹𝑺𝑻𝑼𝑽𝑾𝑿𝒀𝒁𝒂𝒃𝒄𝒅𝒆𝒇𝒈𝒉𝒊𝒋𝒌𝒍𝒎𝒏𝒐𝒑𝒒𝒓𝒔𝒕𝒖𝒗𝒘𝒙𝒚𝒛"); +} + +sub xf_boldsans { + return xf_alpha_map($_[0], "𝗔𝗕𝗖𝗗𝗘𝗙𝗚𝗛𝗜𝗝𝗞𝗟𝗠𝗡𝗢𝗣𝗤𝗥𝗦𝗧𝗨𝗩𝗪𝗫𝗬𝗭𝗮𝗯𝗰𝗱𝗲𝗳𝗴𝗵𝗶𝗷𝗸𝗹𝗺𝗻𝗼𝗽𝗾𝗿𝘀𝘁𝘂𝘃𝘄𝘅𝘆𝘇"); +} + +sub xf_italsans { + return xf_alpha_map($_[0], "𝘈𝘉𝘊𝘋𝘌𝘍𝘎𝘏𝘐𝘑𝘒𝘓𝘔𝘕𝘖𝘗𝘘𝘙𝘚𝘛𝘜𝘝𝘞𝘟𝘠𝘡𝘢𝘣𝘤𝘥𝘦𝘧𝘨𝘩𝘪𝘫𝘬𝘭𝘮𝘯𝘰𝘱𝘲𝘳𝘴𝘵𝘶𝘷𝘸𝘹𝘺𝘻"); +} + +sub xf_bolditalsans { + return xf_alpha_map($_[0], "𝘼𝘽𝘾𝘿𝙀𝙁𝙂𝙃𝙄𝙅𝙆𝙇𝙈𝙉𝙊𝙋𝙌𝙍𝙎𝙏𝙐𝙑𝙒𝙓𝙔𝙕𝙖𝙗𝙘𝙙𝙚𝙛𝙜𝙝𝙞𝙟𝙠𝙡𝙢𝙣𝙤𝙥𝙦𝙧𝙨𝙩𝙪𝙫𝙬𝙭𝙮𝙯"); +} + +sub xf_doublestrike { + return xf_alpha_map($_[0], "𝔸𝔹ℂ𝔻𝔼𝔽𝔾ℍ𝕀𝕁𝕂𝕃𝕄ℕ𝕆ℙℚℝ𝕊𝕋𝕌𝕍𝕎𝕏𝕐ℤ𝕒𝕓𝕔𝕕𝕖𝕗𝕘𝕙𝕚𝕛𝕜𝕝𝕞𝕟𝕠𝕡𝕢𝕣𝕤𝕥𝕦𝕧𝕨𝕩𝕪𝕫"); +} + +sub xf_cursive { + return xf_alpha_map($_[0], "𝒜ℬ𝒞𝒟ℰℱ𝒢ℋℐ𝒥𝒦ℒℳ𝒩𝒪𝒫𝒬ℛ𝒮𝒯𝒰𝒱𝒲𝒳𝒴𝒵𝒶𝒷𝒸𝒹ℯ𝒻ℊ𝒽𝒾𝒿𝓀𝓁𝓂𝓃ℴ𝓅𝓆𝓇𝓈𝓉𝓊𝓋𝓌𝓍𝓎𝓏"); +} + +sub xf_boldcursive { + return xf_alpha_map($_[0], "𝓐𝓑𝓒𝓓𝓔𝓕𝓖𝓗𝓘𝓙𝓚𝓛𝓜𝓝𝓞𝓟𝓠𝓡𝓢𝓣𝓤𝓥𝓦𝓧𝓨𝓩𝓪𝓫𝓬𝓭𝓮𝓯𝓰𝓱𝓲𝓳𝓴𝓵𝓶𝓷𝓸𝓹𝓺𝓻𝓼𝓽𝓾𝓿𝔀𝔁𝔂𝔃"); +} + +sub xf_fraktur { + return xf_alpha_map($_[0], "𝔄𝔅ℭ𝔇𝔈𝔉𝔊ℌℑ𝔍𝔎𝔏𝔐𝔑𝔒𝔓𝔔ℜ𝔖𝔗𝔘𝔙𝔚𝔛𝔜ℨ𝔞𝔟𝔠𝔡𝔢𝔣𝔤𝔥𝔦𝔧𝔨𝔩𝔪𝔫𝔬𝔭𝔮𝔯𝔰𝔱𝔲𝔳𝔴𝔵𝔶𝔷"); +} + +sub xf_boldfraktur { + return xf_alpha_map($_[0], "𝕬𝕭𝕮𝕯𝕰𝕱𝕲𝕳𝕴𝕵𝕶𝕷𝕸𝕹𝕺𝕻𝕼𝕽𝕾𝕿𝖀𝖁𝖂𝖃𝖄𝖅𝖆𝖇𝖈𝖉𝖊𝖋𝖌𝖍𝖎𝖏𝖐𝖑𝖒𝖓𝖔𝖕𝖖𝖗𝖘𝖙𝖚𝖛𝖜𝖝𝖞𝖟"); +} + +sub xf_superscript { + return xf_alpha_map($_[0], "ᴬᴮᶜᴰᴱᶠᴳᴴᴵᴶᴷᴸᴹᴺᴼᴾᑫᴿˢᵀᵁⱽᵂˣʸᶻᵃᵇᶜᵈᵉᶠᵍʰᶦʲᵏˡᵐⁿᵒᵖᑫʳˢᵗᵘᵛʷˣʸᶻ"); +} +#### + + +sub get_ctrl_key { + return ord(uc($_[0])) - 0x40; +} + +sub fmt_key { + # \002 is "toggle bold" + return "'\002" . $_[0] . "\002'"; +} + +sub init_keys { + our $default_keys; + + my $keys = settings_get_str('unifmt_keys'); + if(length $keys != 6) { + print "$SELF: Invalid unifmt_keys, should be 6 keystrokes, defaulting to '$default_keys'"; + settings_set_str('unifmt_keys', ($keys = $default_keys) ); + } + + my ($p, $w, $u, $d, $s, $l) = split "", $keys; + + $p = get_ctrl_key($p); + if($p < 0 || $p > 0x1f) { + my $pd = uc substr($default_keys, 0, 1); + print "$SELF: Invalid prefix key, defaulting to " . fmt_key("^" . $pd); + $p = get_ctrl_key($pd); + } + + our $prefix_key = $p; + + our %combining_map = ( + $u => 0x332, # underline + $d => 0x333, # double underline + $s => 0x336, # strikethrough + $l => 0x338, # slash-through + ); + + print "$SELF: " . + "prefix " . fmt_key("^" . chr($prefix_key + 0x40)) . ", " . + "underline " . fmt_key($u) . ", " . + "double " . fmt_key($d) . ", " . + "strike " . fmt_key($s) . ", " . + "slash " . fmt_key($l); + + for(sort { $transform_keys{$a} cmp $transform_keys{$b} } keys %transform_keys) { + print $transform_keys{$_} . ": " . $_; + } +} + +sub handle_keypress { + my $key = shift; + + if($DEBUG) { printf $count++ . ": got key 0x%x", $key; dump_buf(); } + + # hackish way to let most escape codes through unmodified. assumes + # (incorrectly) that all escape codes are either Esc-[-(something), + # 3 bytes... or else Esc-(something that isn't [), 2 bytes. This + # happens to let urxvt's arrow keys and alt-numbers through, at least. + if($was_escape) { + if($was_escape == 2 && $key != ord('[')) { + $was_escape = 0; + } else { + $was_escape--; + } + signal_continue($key); + return; + } + + # don't try to combine with combining chars! + for(values our %combining_map) { + # warn "$key $_"; + if($key == $_) { + signal_continue($key); + return; + } + } + + # ctrl-space is mapped to the null character. make it dump the + # current input buffer contents in hex, if debugging is active. + if($DEBUG && $key == 0) { + dump_buf(); + signal_stop(); + return; + } + + # ^F pressed once: set flag, but don't insert into buffer. + # Pressed twice = unset flag, inset into buffer. + if($key == $prefix_key) { + if($was_prefix) { + $was_prefix = 0; + signal_continue($key); + } else { + $was_prefix = 1; + signal_stop(); + } + return; + } + + # enter/return, turn off formatting + if($key == 0x0d || $key == 0x0a) { + $combining_char = $was_prefix = 0; + undef $transform; + signal_continue($key); + return; + } + + # backspace/delete and control characters are acted on normally, except + # that escape has to set a flag + if($key == 0x7f || $key < 0x20) { + if($key == 0x1b) { + $was_escape = 2; + } + signal_continue($key); + return; + } + + # last key pressed was ^F, act on it, but don't insert into the buffer + if($was_prefix) { + # warn "prefix key pressed before " . $key; + my $t = $transform_keys{chr($key)}; + if(defined($t)) { + # warn "transform key $key"; + $transform = $transforms{$t}; + } else { + $combining_char = $combining_map{chr($key)} || 0; + # unrecognized keys also turn off transform modes + undef $transform unless $combining_char; + } + + $was_prefix = 0; + signal_stop(); + return; + } + + if(defined $transform) { + $key = $transform->($key); + } + + signal_continue($key); + + # if it was a space and we're not formatting spaces, we're done + if(($key == 0x20 || $key == 0x3000) && !settings_get_bool('unifmt_spaces')) { + return; + } + + if($combining_char) { + if($DEBUG) { print "combining($key, $combining_char)"; } + signal_emit('gui key pressed', $combining_char); + } +} + +sub unifmt_help { + command("/exec - pod2text " . __FILE__); +} + +### main() +settings_add_str($SELF, 'unifmt_keys', $default_keys); +settings_add_bool($SELF, 'unifmt_spaces', 0); +init_keys(); + +signal_add_last('setup changed', \&init_keys); + +signal_register({ "gui key pressed", [ "integer" ] }); +signal_add_first("gui key pressed", \&handle_keypress); + +command_bind("unifmt_help", \&unifmt_help); + +print "$SELF.pl loaded, /unifmt_help for help" |