diff options
Diffstat (limited to 'corpus')
| -rwxr-xr-x | corpus/tokenize-anything.sh | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/corpus/tokenize-anything.sh b/corpus/tokenize-anything.sh index a20a022f..c7adfa61 100755 --- a/corpus/tokenize-anything.sh +++ b/corpus/tokenize-anything.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/usr/bin/env bash ROOTDIR=`dirname $0` SUPPORT=$ROOTDIR/support @@ -12,8 +12,8 @@ fi $SUPPORT/utf8-normalize.sh $NORMARGS | $SUPPORT/quote-norm.pl | $SUPPORT/tokenizer.pl | - sed -u -e 's/ al - / al-/g' | + sed -e 's/ al - / al-/g' | $SUPPORT/fix-contract.pl | - sed -u -e 's/^ //' | sed -u -e 's/ $//' | + sed -e 's/^ //' | sed -e 's/ $//' | perl -e '$|++; while(<>){s/(\d+)(\.+)$/$1 ./; s/(\d+)(\.+) \|\|\|/$1 . |||/; print;}' |