summaryrefslogtreecommitdiff
path: root/pro-train/mr_pro_generate_mapper_input.pl
diff options
context:
space:
mode:
authorChris Dyer <cdyer@cs.cmu.edu>2011-07-11 20:39:45 -0400
committerChris Dyer <cdyer@cs.cmu.edu>2011-07-11 20:39:45 -0400
commitbde4a34bab96052570c248f7d9ccc299a9a3f097 (patch)
treeb74180cb2d36e373eafc1fd6a74968a969287ead /pro-train/mr_pro_generate_mapper_input.pl
parent95deb840699f9b6f8fe499b374bd726bce97365c (diff)
sort of working hopkins&may optimizer
Diffstat (limited to 'pro-train/mr_pro_generate_mapper_input.pl')
-rwxr-xr-xpro-train/mr_pro_generate_mapper_input.pl18
1 files changed, 18 insertions, 0 deletions
diff --git a/pro-train/mr_pro_generate_mapper_input.pl b/pro-train/mr_pro_generate_mapper_input.pl
new file mode 100755
index 00000000..b30fc4fd
--- /dev/null
+++ b/pro-train/mr_pro_generate_mapper_input.pl
@@ -0,0 +1,18 @@
+#!/usr/bin/perl -w
+use strict;
+
+die "Usage: $0 HG_DIR\n" unless scalar @ARGV == 1;
+my $d = shift @ARGV;
+die "Can't find directory $d" unless -d $d;
+
+opendir(DIR, $d) or die "Can't read $d: $!";
+my @hgs = grep { /\.gz$/ } readdir(DIR);
+closedir DIR;
+
+for my $hg (@hgs) {
+ my $file = $hg;
+ my $id = $hg;
+ $id =~ s/(\.json)?\.gz//;
+ print "$d/$file $id\n";
+}
+