[02/32] incubator-joshua git commit: comments

[mj...@apache.org]

comments


Project: http://git-wip-us.apache.org/repos/asf/incubator-joshua/repo
Commit: http://git-wip-us.apache.org/repos/asf/incubator-joshua/commit/2ef15515
Tree: http://git-wip-us.apache.org/repos/asf/incubator-joshua/tree/2ef15515
Diff: http://git-wip-us.apache.org/repos/asf/incubator-joshua/diff/2ef15515

Branch: refs/heads/JOSHUA-252
Commit: 2ef15515c23e6bed3530f32f731e639b476f8681
Parents: f02bd27
Author: Matt Post <po...@cs.jhu.edu>
Authored: Wed May 18 09:55:42 2016 -0400
Committer: Matt Post <po...@cs.jhu.edu>
Committed: Wed May 18 09:55:42 2016 -0400

----------------------------------------------------------------------
 scripts/support/split2files              | 4 ++--
 scripts/training/trim_parallel_corpus.pl | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/incubator-joshua/blob/2ef15515/scripts/support/split2files
----------------------------------------------------------------------
diff --git a/scripts/support/split2files b/scripts/support/split2files
index 866ab0e..76bbdba 100755
--- a/scripts/support/split2files
+++ b/scripts/support/split2files
@@ -3,7 +3,7 @@
 # Reads any number of file names from the command line, then split()s
 # STDIN on tabs and writes them to those files. Example usage:
 #
-# paste file1 file2 file3 ... | splittabs file1.new file2.new file3.new.gz ...
+# paste file1 file2 file3 ... | split2files file1.new file2.new file3.new.gz ...
 #
 # If there are more fields on STDIN that files on the command-line, the extra
 # fields are silently discarded.
@@ -17,7 +17,7 @@ my @fh;
 $| = 1;   # don't buffer output
 
 if (@ARGV < 0) {
-  print "Usage: cat tabbed-file | splittabs file1 [file2 [file3 ...]]\n";
+  print "Usage: cat tabbed-file | split2files file1 [file2 [file3 ...]]\n";
   exit;
 }
 

http://git-wip-us.apache.org/repos/asf/incubator-joshua/blob/2ef15515/scripts/training/trim_parallel_corpus.pl
----------------------------------------------------------------------
diff --git a/scripts/training/trim_parallel_corpus.pl b/scripts/training/trim_parallel_corpus.pl
index 39b635c..00cf5bf 100755
--- a/scripts/training/trim_parallel_corpus.pl
+++ b/scripts/training/trim_parallel_corpus.pl
@@ -5,7 +5,7 @@
 # the first two fields has mroe than N tokens, the line is skipped.
 
 # e.g.,
-# paste corpus.en corpus.fr | trim_parallel_corpus.pl 40 | splittabs en.trimmed.40 fr.trimmed.40
+# paste corpus.en corpus.fr | trim_parallel_corpus.pl 40 | split2files en.trimmed.40 fr.trimmed.40
 
 my $thresh = shift || 100;