pragmatic_tokenizer 1.2.0 → 1.3.0
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/lib/pragmatic_tokenizer/pre_processor.rb +5 -0
- 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: 74b115265cde89758fa37abfbbe6e5fbf581819e
|
|
4
|
+
data.tar.gz: 7074d143fd81022852dca5af10800e1abe93f94e
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: ef9e49e20912c5e3c5324362dfa834bf7ad1d2a9b6ac83f82366b3863724d9a3be42114d672757e19594792b849b1f50bd2f74f1758e40bac0b88e01b1633b85
|
|
7
|
+
data.tar.gz: 79a3cfbd22546a8c7ac90501aa749311f927a8ca4d039d12dc64ec5d8bf5aa3db996ff6c66cbc4b8be8aab512f5d4f7c7b432eb2d2da695d6c586dc373578223
|
|
@@ -20,6 +20,7 @@ module PragmaticTokenizer
|
|
|
20
20
|
shift_semicolon(text)
|
|
21
21
|
shift_caret(text)
|
|
22
22
|
shift_hashtag(text)
|
|
23
|
+
shift_ampersand(text)
|
|
23
24
|
shift_vertical_bar(text)
|
|
24
25
|
convert_dbl_quotes(text)
|
|
25
26
|
convert_sgl_quotes(text)
|
|
@@ -100,6 +101,10 @@ module PragmaticTokenizer
|
|
|
100
101
|
text.gsub!(/(?<=\S)(#|＃)(?=\S)/, ' \1\2') || text
|
|
101
102
|
end
|
|
102
103
|
|
|
104
|
+
def shift_ampersand(text)
|
|
105
|
+
text.gsub!(/\&/, ' & ') || text
|
|
106
|
+
end
|
|
107
|
+
|
|
103
108
|
def shift_vertical_bar(text)
|
|
104
109
|
text.gsub!(/\|/, ' | ') || text
|
|
105
110
|
end
|