TinoDidriksen

FROM amd64/debian:sid

ENV LANG=C.UTF-8 LC_ALL=C.UTF-8 DEBIAN_FRONTEND=noninteractive DEBCONF_NONINTERACTIVE_SEEN=true

# Upgrade everything and install base builder dependencies
RUN apt-get -qy update && apt-get -qfy --no-install-recommends install apt-utils
RUN apt-get -qy update && apt-get -qfy --no-install-recommends dist-upgrade
RUN apt-get -qy update && apt-get -qfy --no-install-recommends install build-essential fakeroot time libgoogle-perftools-dev

# OS dependencies

TinoDidriksen

#!/usr/bin/env perl
# -*- mode: cperl; indent-tabs-mode: nil; tab-width: 3; cperl-indent-level: 3; -*-
use warnings;
use strict;
use utf8;

BEGIN {
   $| = 1;
   binmode(STDIN, ':encoding(UTF-8)');
   binmode(STDOUT, ':encoding(UTF-8)');

TinoDidriksen

-NickServ- Information on TinoDidriksen
-NickServ- Registered : Mar 21 17:25:41 2009

-ChanServ- Information on #apertium
-ChanServ- Founder    : spectei
-ChanServ- Registered : Jan 09 18:28:40 2007

-ChanServ- Information on #hfst
-ChanServ- Founder    : spectei, Nikerabbit
-ChanServ- Registered : Oct 07 11:15:41 2010

TinoDidriksen

// Upper-case because we compare them to DOM nodeName
let text_nodes = {'ADDRESS': true, 'ARTICLE': true, 'ASIDE': true, 'AUDIO': true, 'BLOCKQUOTE': true, 'BODY': true, 'CANVAS': true, 'DD': true, 'DIV': true, 'DL': true, 'FIELDSET': true, 'FIGCAPTION': true, 'FIGURE': true, 'FOOTER': true, 'FORM': true, 'H1': true, 'H2': true, 'H3': true, 'H4': true, 'H5': true, 'H6': true, 'HEADER': true, 'HGROUP': true, 'HTML': true, 'HR': true, 'LI': true, 'MAIN': true, 'NAV': true, 'NOSCRIPT': true, 'OL': true, 'OUTPUT': true, 'P': true, 'PRE': true, 'SECTION': true, 'TABLE': true, 'TD': true, 'TH': true, 'UL': true, 'VIDEO': true};

function findTextNodes(nodes, filter) {
  let tns = [], wsx = /\S/;

  if (!$.isArray(nodes)) {
    nodes = [nodes];
  }

TinoDidriksen

<word>En</word>
"<en>"
        "en" det mask ent kvant
        "en" adv
        "en" pron ent pers hum
        "ene" verb imp
<word>serbisk</word>
"<serbisk>"
        "serbisk" adj ub m/f ent pos
        "serbisk" adj nøyt ub ent pos

TinoDidriksen

grep -rl '<?php' * | xargs -r grep -rl '?>' | xargs -rn1 php -r '$f=file_get_contents($argv[1]); if (preg_match("~[?]>[\s\n]*$~", $f)) { $f = trim(preg_replace("~[?]>[\s\n]*$~", "", $f))."\n"; file_put_contents($argv[1], $f); }' --

TinoDidriksen

$ pacman -S cmake make mingw-w64-x86_64-gcc mingw-w64-x86_64-boost

TinoDidriksen

echo -e 'Nuuk\nQaanaaq\nAasiaat' | ~/langtech/kal/tools/shellscripts/kal-tokenise | cg-conv -c -F | grep -F Prop+Abs | lg-multi.pl

TinoDidriksen

aftagende
akut
almindelig
belgisk
betydningsfuld
blød
bæredygtig
cirkulær
delelig
deltagende

TinoDidriksen

#!/usr/bin/env php
<?php

/*
USAGE:
./cg-combsets.php kalcg.dansyn kalcg.dan kalcg.dep kalcg.extra kalcg.pre > sets.cg3

Parses all given grammars and spits out all sets used across all grammars, and marks conflicts for manual inspection.
Used to create a combined deduplicated sets.cg3 that multiple grammars can Include.