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
|
#!/usr/bin/env perl
use warnings;
use strict;
my ($source_file,$target_file,$alignment_factors) = @ARGV;
# initialize data structures for factors
my (@SOURCE_FACTOR,@TARGET_FACTOR);
if (defined($alignment_factors)) {
my ($source,$target) = split(/\-/,$alignment_factors);
@SOURCE_FACTOR = split(/,/,$source);
@TARGET_FACTOR = split(/,/,$target);
}
# loop through corpus file
open(SOURCE,$source_file);
open(TARGET,$target_file);
while(my $source = <SOURCE>) {
my $target = <TARGET>;
chop($source);
chop($target);
# remove markup
foreach my $line (\$source,\$target) {
$$line =~ s/\<[^\>]+\>//g;
$$line =~ s/\s+/ /g;
$$line =~ s/^ //;
$$line =~ s/ $//;
}
# no factors
if (!defined($alignment_factors)) {
print "$source ||| $target\n";
next;
}
foreach (split(/\s+/,$source)) {
my @SOURCE_WORD = split(/\|/);
for(my $i=0; $i<scalar(@SOURCE_FACTOR); $i++) {
print "|" if $i;
print "$SOURCE_WORD[$SOURCE_FACTOR[$i]]";
}
print " ";
}
print "|||";
foreach (split(/\s+/,$target)) {
print " ";
my @TARGET_WORD = split(/\|/);
for(my $i=0; $i<scalar(@TARGET_FACTOR); $i++) {
print "|" if $i;
print "$TARGET_WORD[$TARGET_FACTOR[$i]]";
}
}
print "\n";
}
close(TARGET);
close(SOURCE);
|
