From ef028446f3640e007215b4576a4dc52a9c9de6db Mon Sep 17 00:00:00 2001 From: Jeroen Vermeulen Date: Fri, 29 May 2015 18:30:26 +0700 Subject: Add license notices to scripts. This is not pleasant to read (and much, much less pleasant to write!) but sort of necessary in an open project. Right now it's quite hard to figure out what is licensed how, which doesn't matter much to most people but can suddenly become very important when people want to know what they're being allowed to do. I kept the notices as short as I could. As far as I could see, everything without a clear license notice is LGPL v2.1 or later. --- scripts/tokenizer/deescape-special-chars-PTB.perl | 3 +++ scripts/tokenizer/deescape-special-chars.perl | 3 +++ scripts/tokenizer/detokenizer.perl | 3 +++ scripts/tokenizer/escape-special-chars.perl | 3 +++ scripts/tokenizer/lowercase.perl | 3 +++ scripts/tokenizer/normalize-punctuation.perl | 3 +++ scripts/tokenizer/pre-tok-clean.perl | 3 +++ scripts/tokenizer/pre-tokenizer.perl | 3 +++ scripts/tokenizer/pre_tokenize_cleaning.py | 3 +++ scripts/tokenizer/remove-non-printing-char.perl | 3 +++ scripts/tokenizer/replace-unicode-punctuation.perl | 3 +++ scripts/tokenizer/tokenizer.perl | 3 +++ scripts/tokenizer/tokenizer_PTB.perl | 3 +++ 13 files changed, 39 insertions(+) (limited to 'scripts/tokenizer') diff --git a/scripts/tokenizer/deescape-special-chars-PTB.perl b/scripts/tokenizer/deescape-special-chars-PTB.perl index f9601924f..ad2529b21 100755 --- a/scripts/tokenizer/deescape-special-chars-PTB.perl +++ b/scripts/tokenizer/deescape-special-chars-PTB.perl @@ -1,4 +1,7 @@ #!/usr/bin/env perl +# +# This file is part of moses. Its use is licensed under the GNU Lesser General +# Public License version 2.1 or, at your option, any later version. use warnings; use strict; diff --git a/scripts/tokenizer/deescape-special-chars.perl b/scripts/tokenizer/deescape-special-chars.perl index 002955e62..b9d1ad74c 100755 --- a/scripts/tokenizer/deescape-special-chars.perl +++ b/scripts/tokenizer/deescape-special-chars.perl @@ -1,4 +1,7 @@ #!/usr/bin/env perl +# +# This file is part of moses. Its use is licensed under the GNU Lesser General +# Public License version 2.1 or, at your option, any later version. use warnings; use strict; diff --git a/scripts/tokenizer/detokenizer.perl b/scripts/tokenizer/detokenizer.perl index 3a92bd024..881b93dd1 100755 --- a/scripts/tokenizer/detokenizer.perl +++ b/scripts/tokenizer/detokenizer.perl @@ -4,6 +4,9 @@ # Sample De-Tokenizer # written by Josh Schroeder, based on code by Philipp Koehn # further modifications by Ondrej Bojar +# +# This file is part of moses. Its use is licensed under the GNU Lesser General +# Public License version 2.1 or, at your option, any later version. binmode(STDIN, ":utf8"); binmode(STDOUT, ":utf8"); diff --git a/scripts/tokenizer/escape-special-chars.perl b/scripts/tokenizer/escape-special-chars.perl index fbbbae292..143e85490 100755 --- a/scripts/tokenizer/escape-special-chars.perl +++ b/scripts/tokenizer/escape-special-chars.perl @@ -1,4 +1,7 @@ #!/usr/bin/env perl +# +# This file is part of moses. Its use is licensed under the GNU Lesser General +# Public License version 2.1 or, at your option, any later version. use warnings; use strict; diff --git a/scripts/tokenizer/lowercase.perl b/scripts/tokenizer/lowercase.perl index e5c41bbed..bc75e5e5c 100755 --- a/scripts/tokenizer/lowercase.perl +++ b/scripts/tokenizer/lowercase.perl @@ -1,4 +1,7 @@ #!/usr/bin/env perl +# +# This file is part of moses. Its use is licensed under the GNU Lesser General +# Public License version 2.1 or, at your option, any later version. use warnings; use strict; diff --git a/scripts/tokenizer/normalize-punctuation.perl b/scripts/tokenizer/normalize-punctuation.perl index 13e9fd3fc..7dab7543a 100755 --- a/scripts/tokenizer/normalize-punctuation.perl +++ b/scripts/tokenizer/normalize-punctuation.perl @@ -1,4 +1,7 @@ #!/usr/bin/env perl +# +# This file is part of moses. Its use is licensed under the GNU Lesser General +# Public License version 2.1 or, at your option, any later version. use warnings; use strict; diff --git a/scripts/tokenizer/pre-tok-clean.perl b/scripts/tokenizer/pre-tok-clean.perl index 900e992ee..064f7b187 100755 --- a/scripts/tokenizer/pre-tok-clean.perl +++ b/scripts/tokenizer/pre-tok-clean.perl @@ -1,4 +1,7 @@ #!/usr/bin/env perl +# +# This file is part of moses. Its use is licensed under the GNU Lesser General +# Public License version 2.1 or, at your option, any later version. use strict; diff --git a/scripts/tokenizer/pre-tokenizer.perl b/scripts/tokenizer/pre-tokenizer.perl index 514d8da8d..541ce77fb 100755 --- a/scripts/tokenizer/pre-tokenizer.perl +++ b/scripts/tokenizer/pre-tokenizer.perl @@ -3,6 +3,9 @@ # script for preprocessing language data prior to tokenization # Start by Ulrich Germann, after noticing systematic preprocessing errors # in some of the English Europarl data. +# +# This file is part of moses. Its use is licensed under the GNU Lesser General +# Public License version 2.1 or, at your option, any later version. use warnings; use strict; diff --git a/scripts/tokenizer/pre_tokenize_cleaning.py b/scripts/tokenizer/pre_tokenize_cleaning.py index 096a45dc4..c03af8f66 100644 --- a/scripts/tokenizer/pre_tokenize_cleaning.py +++ b/scripts/tokenizer/pre_tokenize_cleaning.py @@ -1,4 +1,7 @@ #!/usr/bin/env python -*- coding: utf-8 -*- +# +# This file is part of moses. Its use is licensed under the GNU Lesser General +# Public License version 2.1 or, at your option, any later version. """ The Gacha filter cleans out sentence pairs that have global character mean diff --git a/scripts/tokenizer/remove-non-printing-char.perl b/scripts/tokenizer/remove-non-printing-char.perl index 9125b7691..92f6ade16 100755 --- a/scripts/tokenizer/remove-non-printing-char.perl +++ b/scripts/tokenizer/remove-non-printing-char.perl @@ -1,4 +1,7 @@ #!/usr/bin/env perl +# +# This file is part of moses. Its use is licensed under the GNU Lesser General +# Public License version 2.1 or, at your option, any later version. use warnings; use utf8; diff --git a/scripts/tokenizer/replace-unicode-punctuation.perl b/scripts/tokenizer/replace-unicode-punctuation.perl index cda69ddf7..c2c7088d6 100755 --- a/scripts/tokenizer/replace-unicode-punctuation.perl +++ b/scripts/tokenizer/replace-unicode-punctuation.perl @@ -1,4 +1,7 @@ #!/usr/bin/env perl +# +# This file is part of moses. Its use is licensed under the GNU Lesser General +# Public License version 2.1 or, at your option, any later version. use warnings; use strict; diff --git a/scripts/tokenizer/tokenizer.perl b/scripts/tokenizer/tokenizer.perl index a5d4fadd3..e08bac941 100755 --- a/scripts/tokenizer/tokenizer.perl +++ b/scripts/tokenizer/tokenizer.perl @@ -1,4 +1,7 @@ #!/usr/bin/env perl +# +# This file is part of moses. Its use is licensed under the GNU Lesser General +# Public License version 2.1 or, at your option, any later version. use warnings; diff --git a/scripts/tokenizer/tokenizer_PTB.perl b/scripts/tokenizer/tokenizer_PTB.perl index 6fff8d7f7..46b14775c 100755 --- a/scripts/tokenizer/tokenizer_PTB.perl +++ b/scripts/tokenizer/tokenizer_PTB.perl @@ -1,4 +1,7 @@ #!/usr/bin/env perl +# +# This file is part of moses. Its use is licensed under the GNU Lesser General +# Public License version 2.1 or, at your option, any later version. # Sample Tokenizer ### Version 1.1 -- cgit v1.2.3