Gitiles
Code Review
Sign In
korap.ids-mannheim.de
/
KorAP
/
Tokenizer-Evaluation
/
a6b4597e51ac4d313db406fba64c110411b983c5
/
.
/
benchmarks
/
cleanup
/
tokenize_eos.pl
blob: 42f5ae794d96acb3231007f247f0d8dd2e12320e [
file
] [
log
] [
blame
]
#!/usr/bin/env perl
use
strict
;
use
warnings
;
my
$c
=
''
;
foreach
(<>)
{
$c
.=
$_
;
};
foreach
my
$c
(
split
(
"</eos>"
,
$c
))
{
$c
=~
s
/[
\s\n\t
]+//
g
;
print
$c
,
"\n"
;
};