pragmatic_tokenizer 0.1.7 → 0.1.8
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/README.md +1 -1
- data/lib/pragmatic_tokenizer/tokenizer.rb +1 -1
- data/lib/pragmatic_tokenizer/version.rb +1 -1
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 0fb5eb30905feb61b0f41d91cca8a3d449b7ad42
|
|
4
|
+
data.tar.gz: b38edd49314a297b0d154dc5df4ce0c85e3a9519
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 2340ad7a611d6b31f7d49685f75f036c9dd3e20222f85bd8d2b73a1dd7cb7a7253b62f6dde9244b3101913be8a346deefa0d77dc7c68016f50d95f935fcaab6e
|
|
7
|
+
data.tar.gz: 20402fb55744f2b58f8ceec560565f3fdb6063750b52234ee673205d6553d727da7f48e2e9e9debb6281b12d9f65c59912e7e54b18aef49349a2d55bea10a92c
|
data/README.md
CHANGED
|
@@ -61,7 +61,7 @@ Or install it yourself as:
|
|
|
61
61
|
##### `clean`
|
|
62
62
|
**default** = `'false'`
|
|
63
63
|
- `true`
|
|
64
|
-
Removes tokens consisting of only hypens, underscores, or periods as well as some special characters (®, ©, ™).
|
|
64
|
+
Removes tokens consisting of only hypens, underscores, or periods as well as some special characters (®, ©, ™). Also removes long tokens or tokens with a backslash.
|
|
65
65
|
- `false`
|
|
66
66
|
Leaves tokens as is.
|
|
67
67
|
|
|
@@ -65,7 +65,7 @@ module PragmaticTokenizer
|
|
|
65
65
|
|
|
66
66
|
def cleaner(tokens)
|
|
67
67
|
return tokens unless clean
|
|
68
|
-
tokens.delete_if { |t| t =~ /\A_+\z/ || t =~ /\A-+\z/ || PragmaticTokenizer::Languages::Common::SPECIAL_CHARACTERS.include?(t) || t =~ /\A\.{2,}\z/ }
|
|
68
|
+
tokens.delete_if { |t| t =~ /\A_+\z/ || t =~ /\A-+\z/ || PragmaticTokenizer::Languages::Common::SPECIAL_CHARACTERS.include?(t) || t =~ /\A\.{2,}\z/ || t.include?("\\") || t.length > 50 }
|
|
69
69
|
end
|
|
70
70
|
|
|
71
71
|
def remove_punctuation(tokens)
|