blob: 499671b44de5197122049d437ea1407a253f9f61 (
plain)
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
|
#!/usr/bin/env perl
# script for preprocessing language data prior to tokenization
# Start by Ulrich Germann, after noticing systematic preprocessing errors
# in some of the English Europarl data.
use warnings;
use strict;
use Getopt::Std;
binmode(STDIN, ":utf8");
binmode(STDOUT, ":utf8");
sub usage
{
print "Script for preprocessing of raw language data prior to tokenization\n";
print "Usage: $0 -l <language tag> [-b]\n";
print " -b: no buffering\n";
}
my %args;
getopt('l=s h b',\%args);
usage() && exit(0) if $args{'h'};
$|++ if $args{'b'};
if ($args{'l'} eq "en")
{
while (<>)
{
s/([[:alpha:]]\') s\b/$1s/g;
print;
}
}
elsif ($args{'l'} eq "fr")
{
while (<>)
{
s/\b([[:alpha:]]\')\s+(?=[[:alpha:]])/$1/g;
print;
}
}
else
{
print while <>;
}
|