1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124
|
#!/usr/bin/perl
# Copyright (C) 2000-2023 The Xastir Group
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; either version 2
# of the License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
# 02111-1307, USA.
#
# Look at the README for more information on the program.
# Run it like this:
#
# cd xastir/config
# ../scripts/langOldeEnglish.pl -split <language-English.sys >language-OldeEnglish.sys
# or
# ../scripts/langOldeEnglish.pl <some-input-file >some-output-file
#
# "-split": Translate 2nd part of line only (Xastir language file).
# Without it: Translate entire text.
# Regex strings derived from:
# http://www.faqs.org/docs/diveintopython/dialect_divein.html
# http://www.siafoo.net/snippet/133
# Check whether we're translating an Xastir language file or plain
# text:
# "-split" present: Translate the 2nd piece of each line.
# "-split" absent: Translate the entire text.
my $a;
if ($#ARGV < 0) { $a = ""; }
else { $a = shift; }
$do_split = 0;
if (length($a) > 0 && $a =~ m/-split/) {
$do_split = 1;
}
# Add these two lines to show that we translated the file.
print "# language-OldeEnglish.sys, translated from language-English.sys\n";
print "# Please do not edit this derived file.\n";
while ( <> ) {
# Skip other comment lines
if (m/^#/) {
next;
}
if ($do_split) {
# Split each incoming line by the '|' character
@pieces = split /\|/;
# Translate the second portion of each line only
$_ = $pieces[1];
}
s/i([bcdfghjklmnpqrstvwxyz])e\b/y$1/g;
s/i([bcdfghjklmnpqrstvwxyz])e/y$1$1e/g;
s/ick\b/yk/g;
s/ia([bcdfghjklmnpqrstvwxyz])/e$1e/g;
s/e[ea]([bcdfghjklmnpqrstvwxyz])/e$1e/g;
s/([bcdfghjklmnpqrstvwxyz])y/$1ee/g;
s/([bcdfghjklmnpqrstvwxyz])er/$1re/g;
s/([aeiou])re\b/$1r/g;
s/ia([bcdfghjklmnpqrstvwxyz])/i$1e/g;
s/tion\b/cioun/g;
s/ion\b/ioun/g;
s/aid/ayde/g;
s/ai/ey/g;
s/ay\b/y/g;
s/ay/ey/g;
s/ant/aunt/g;
s/ea/ee/g;
s/oa/oo/g;
s/ue/e/g;
s/oe/o/g;
s/ou/ow/g;
s/ow/ou/g;
s/\bhe/hi/g;
s/ve\b/veth/g;
s/se\b/e/g;
s/\'s\b/es/g;
s/ic\b/ick/g;
s/ics\b/icc/g;
s/ical\b/ick/g;
s/tle\b/til/g;
s/ll\b/l/g;
s/ould\b/olde/g;
s/own\b/oune/g;
s/un\b/onne/g;
s/rry\b/rye/g;
s/est\b/este/g;
s/pt\b/pte/g;
s/th\b/the/g;
s/ch\b/che/g;
s/ss\b/sse/g;
s/([wybdp])\b/$1e/g;
s/([rnt])\b/$1$1e/g;
s/from/fro/g;
s/when/whan/g;
if ($do_split) {
# Combine the line again for output to STDOUT
$pieces[1] = $_;
print join '|', @pieces;
}
else {
print;
}
}
|