diff options
author | Patrick Simianer <p@simianer.de> | 2012-03-13 09:24:47 +0100 |
---|---|---|
committer | Patrick Simianer <p@simianer.de> | 2012-03-13 09:24:47 +0100 |
commit | ef6085e558e26c8819f1735425761103021b6470 (patch) | |
tree | 5cf70e4c48c64d838e1326b5a505c8c4061bff4a /word-aligner/stemmers | |
parent | 10a232656a0c882b3b955d2bcfac138ce11e8a2e (diff) | |
parent | dfbc278c1057555fda9312291c8024049e00b7d8 (diff) |
merge with upstream
Diffstat (limited to 'word-aligner/stemmers')
-rwxr-xr-x | word-aligner/stemmers/ar.pl | 39 | ||||
-rwxr-xr-x | word-aligner/stemmers/ur.pl | 38 |
2 files changed, 77 insertions, 0 deletions
diff --git a/word-aligner/stemmers/ar.pl b/word-aligner/stemmers/ar.pl new file mode 100755 index 00000000..c85e883a --- /dev/null +++ b/word-aligner/stemmers/ar.pl @@ -0,0 +1,39 @@ +#!/usr/bin/perl -w + +use strict; +use utf8; + +binmode(STDIN, ":utf8"); +binmode(STDOUT,":utf8"); + +my $vocab = undef; +if (scalar @ARGV > 0) { + die "Only allow --vocab" unless ($ARGV[0] eq '--vocab' && scalar @ARGV == 1); + $vocab = 1; +} + +my %dict; +while(<STDIN>) { + chomp; + my @words = split /\s+/; + my @out = (); + for my $w (@words) { + my $tw = $dict{$w}; + if (!defined $tw) { + my $el = 4; + if ($w =~ /^(.st|.n|Al)/) { $el+=2; } + if ($w =~ /^(y|t|n)/) { $el++; } + if ($el > length($w)) { $el = length($w); } + $tw = substr $w, 0, $el; + $dict{$w} = $tw; + } + push @out, $tw; + } + if ($vocab) { + die "Expected exactly one word per line with --vocab: $_" unless scalar @out == 1; + print "$_ @out\n"; + } else { + print "@out\n"; + } +} + diff --git a/word-aligner/stemmers/ur.pl b/word-aligner/stemmers/ur.pl new file mode 100755 index 00000000..3a4f5a45 --- /dev/null +++ b/word-aligner/stemmers/ur.pl @@ -0,0 +1,38 @@ +#!/usr/bin/perl -w + +use strict; +use utf8; + +binmode(STDIN, ":utf8"); +binmode(STDOUT,":utf8"); + +my $vocab = undef; +if (scalar @ARGV > 0) { + die "Only allow --vocab" unless ($ARGV[0] eq '--vocab' && scalar @ARGV == 1); + $vocab = 1; +} + +my %dict; +while(<STDIN>) { + chomp; + my @words = split /\s+/; + my @out = (); + for my $w (@words) { + my $tw = $dict{$w}; + if (!defined $tw) { + my $el = 4; + if ($w =~ /^(al|Al)/) { $el++; } + if ($el > length($w)) { $el = length($w); } + $tw = substr $w, 0, $el; + $dict{$w} = $tw; + } + push @out, $tw; + } + if ($vocab) { + die "Expected exactly one word per line with --vocab: $_" unless scalar @out == 1; + print "$_ @out\n"; + } else { + print "@out\n"; + } +} + |