diff options
| author | Patrick Simianer <simianer@cl.uni-heidelberg.de> | 2013-03-03 12:06:43 +0100 |
|---|---|---|
| committer | Patrick Simianer <simianer@cl.uni-heidelberg.de> | 2013-03-03 12:06:43 +0100 |
| commit | f7f9048f8e4d34682f17bfd050d238005feb3ee3 (patch) | |
| tree | fa20fa16b0f5a8009a9254622b65ebeaec049399 /corpus/paste-files.pl | |
| parent | 9d306b30c9abba995ba35243e5cb461bb472a61f (diff) | |
| parent | 12f2eab0e7dc7167af47cddf8ef88968656277da (diff) | |
Merge branch 'master' of github.com:pks/cdec-dtrain
Diffstat (limited to 'corpus/paste-files.pl')
| -rwxr-xr-x | corpus/paste-files.pl | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/corpus/paste-files.pl b/corpus/paste-files.pl index 0b788386..4cb424ad 100755 --- a/corpus/paste-files.pl +++ b/corpus/paste-files.pl @@ -41,9 +41,9 @@ while(1) { } warn "$ARGV[$anum]:$lc contains a ||| symbol - please remove.\n" if $r =~ /\|\|\|/; $r =~ s/\|\|\|/ /g; - $r =~ s/ +//g; - $r =~ s/^ //; - $r =~ s/ $//; + $r =~ s/\s+/ /g; + $r =~ s/^ +//; + $r =~ s/ +$//; $anum++; push @line, $r; } @@ -56,5 +56,5 @@ for (my $i = 1; $i < scalar @fhs; $i++) { my $r = <$fh>; die "Mismatched number of lines.\n" if defined $r; } -print STDERR "Bad lines containing ||| were $bad\n"; +print STDERR "Number of lines containing ||| was: $bad\n" if $bad > 0; |