summaryrefslogtreecommitdiff
path: root/corpus/tokenize-anything.sh
diff options
context:
space:
mode:
authorPatrick Simianer <p@simianer.de>2014-01-27 10:39:36 +0100
committerPatrick Simianer <p@simianer.de>2014-01-27 10:39:36 +0100
commite12ec2d3599bafd5042841c87b9c5323d587f176 (patch)
treea89bcb660f668aec30196478615478a5c94fa2ff /corpus/tokenize-anything.sh
parenta1f3f7fb262b6efefb106a7bddaf81d2a3a6df93 (diff)
parentf7e051a05d65ef25c2ada0b84cd82bfb375ef265 (diff)
Merge remote-tracking branch 'upstream/master'
Diffstat (limited to 'corpus/tokenize-anything.sh')
-rwxr-xr-xcorpus/tokenize-anything.sh1
1 files changed, 1 insertions, 0 deletions
diff --git a/corpus/tokenize-anything.sh b/corpus/tokenize-anything.sh
index 5b7933d8..bca954d1 100755
--- a/corpus/tokenize-anything.sh
+++ b/corpus/tokenize-anything.sh
@@ -14,6 +14,7 @@ fi
$SUPPORT/utf8-normalize.sh $NORMARGS |
$SUPPORT/quote-norm.pl |
$SUPPORT/tokenizer.pl |
+ $SUPPORT/fix-eos.pl |
sed $SEDFLAGS -e 's/ al - / al-/g' |
$SUPPORT/fix-contract.pl |
sed $SEDFLAGS -e 's/^ //' | sed $SEDFLAGS -e 's/ $//' |