sentence_it 0.1.2 → 0.1.3

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 CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: fe2d9ef46a4701766d6a7d71acaaf3525669520363f78c1a8223e8c3cd7b5106
4
- data.tar.gz: d34293c42105be7d0aecf9ec706879e6273ef18b4cbb7737e5665db1e9909042
3
+ metadata.gz: b13c4a2146af990fa60dd88267d9f0c54b2eea072bf6ea1442a15e983ce11160
4
+ data.tar.gz: d768a6c3047cebf23fa94c207537559ff75eca38ac7c94eb3a04041e2b403826
5
5
  SHA512:
6
- metadata.gz: 739dda96391e8831c4f8c83c151f74d6d441320212b8423b04440fbe32f0b5bb1033f514442dc13e7842293baaec7afd03d1f0551d53dcb1ed01077b51cf4dff
7
- data.tar.gz: e7a93abb15666dafd6e72e8b0691417e50330fee065e3f9ce9332fc62e5c57a4824b7cc51500c883c7ae97722845b70e552c06eed2c5cff46f98be6a8d5fceeb
6
+ metadata.gz: 163f39c6a0a62fecfd9d58433d16722a35e85f99a0a6c15644135969b4aaf059ed33ff72e4674654cd3bb1237555eb9ccd7f13c8f49f6be842292be7f796f165
7
+ data.tar.gz: 2b6e60de39fadbf537643596e0675cdb47e4273b5cb49a57d20c2bc197d9602fb6e639eadd92ac673e271e9a78f032eb41d8365c07a9bdc36576f07254ec7ea8
Binary file
data/lib/sentence_it.rb CHANGED
@@ -2,21 +2,21 @@ require 'sentence_it/sentence_it'
2
2
 
3
3
  class SentenceIt
4
4
  DEFAULT_RULES = {
5
- break_pattern: "([ \t]*\n+)+[ \t]*",
5
+ break_pattern: "([ \t]*\n+)+[ \t]*", # one or more consecutive blank lines
6
6
  candidate_pattern: "[ \t]+",
7
7
  positive_rules: [
8
- ['[.!?]', '[0-9A-Z]'],
9
- [':', '[0-9]'],
10
- [':', '[A-Z][a-z]']
8
+ ['[.!?]$', '^[0-9A-Z]'],
9
+ [':$', '^[0-9]'],
10
+ [':$', '^[A-Z][a-z]']
11
11
  ],
12
12
  negative_rules: [
13
- ['(Mrs|Mmes|Mr|Messrs|Ms|Prof|Dr|Drs|Rev|Hon|Sen|St)\.', '[A-Z][a-z]'],
14
- ['(Sr|Jr)\.', '[A-Z][a-z]'],
15
- ['\b[A-Z][a-z]*\.', '[0-9A-Z]'],
16
- ['(cf|vs)\.', ''],
17
- ['e\.g\.', ''],
18
- ['i\.e\.', ''],
19
- ['(Sec|Chap|Fig|Eq)\.', '[0-9A-Z]']
13
+ ['(Mrs|Mmes|Mr|Messrs|Ms|Prof|Dr|Drs|Rev|Hon|Sen|St)\.$', '^[A-Z][a-z]'],
14
+ ['(Sr|Jr)\.$', '^[A-Z][a-z]'],
15
+ ['\b[A-Z][a-z]*\.$', '^[0-9A-Z]'],
16
+ ['(cf|vs)\.$', ''],
17
+ ['e\.g\.$', ''],
18
+ ['i\.e\.$', ''],
19
+ ['(Sec|Chap|Fig|Eq)\.$', '^[0-9A-Z]']
20
20
  ]
21
21
  }
22
22
 
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: sentence_it
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.1.2
4
+ version: 0.1.3
5
5
  platform: ruby
6
6
  authors:
7
7
  - Jin-Dong Kim