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 | c3a9ea64251605532c7954959662643a6a927bb7 (patch) | |
tree | fed6048a5acdaf3834740107771c2bc48f26fd4d /sa-extract/escape-testset.pl | |
parent | 867bca3e5fa0cdd63bf032e5859fb5092d9a4ca1 (diff) | |
parent | a45af4a3704531a8382cd231f6445b3a33b598a3 (diff) |
merge with upstream
Diffstat (limited to 'sa-extract/escape-testset.pl')
-rwxr-xr-x | sa-extract/escape-testset.pl | 35 |
1 files changed, 35 insertions, 0 deletions
diff --git a/sa-extract/escape-testset.pl b/sa-extract/escape-testset.pl new file mode 100755 index 00000000..02fd7445 --- /dev/null +++ b/sa-extract/escape-testset.pl @@ -0,0 +1,35 @@ +#!/usr/bin/perl -w + +use utf8; +use strict; + +binmode(STDIN,":utf8"); +binmode(STDOUT,":utf8"); + +my @fh = (); +if (scalar @ARGV == 0) { + push @fh, \*STDIN; +} else { + for my $file (@ARGV) { + my $f; + open $f, "<$file" or die "Can't read $file: $!\n"; + binmode $f, ":utf8"; + push @fh, $f; + } +} + +my $id = -1; +for my $f (@fh) { + while(<$f>) { + chomp; + die "Empty line in test set" if /^\s*$/; + die "Please remove <seg> tags from input:\n$_" if /^\s*<seg/i; + $id++; + s/&/\&/g; + s/</\</g; + s/>/\>/g; + print "<seg id=\"$id\"> $_ </seg>\n"; + } +} + + |