sentence_it 0.1.1 → 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 +4 -4
- data/lib/sentence_it/sentence_it.so +0 -0
- data/lib/sentence_it.rb +12 -12
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: b13c4a2146af990fa60dd88267d9f0c54b2eea072bf6ea1442a15e983ce11160
|
|
4
|
+
data.tar.gz: d768a6c3047cebf23fa94c207537559ff75eca38ac7c94eb3a04041e2b403826
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 163f39c6a0a62fecfd9d58433d16722a35e85f99a0a6c15644135969b4aaf059ed33ff72e4674654cd3bb1237555eb9ccd7f13c8f49f6be842292be7f796f165
|
|
7
|
+
data.tar.gz: 2b6e60de39fadbf537643596e0675cdb47e4273b5cb49a57d20c2bc197d9602fb6e639eadd92ac673e271e9a78f032eb41d8365c07a9bdc36576f07254ec7ea8
|
|
Binary file
|
data/lib/sentence_it.rb
CHANGED
|
@@ -2,25 +2,25 @@ 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
|
-
['
|
|
10
|
-
['
|
|
8
|
+
['[.!?]$', '^[0-9A-Z]'],
|
|
9
|
+
[':$', '^[0-9]'],
|
|
10
|
+
[':$', '^[A-Z][a-z]']
|
|
11
11
|
],
|
|
12
12
|
negative_rules: [
|
|
13
|
-
['(Mrs|Mmes|Mr|Messrs|Ms|Prof|Dr|Drs|Rev|Hon|Sen|St)
|
|
14
|
-
['(Sr|Jr)
|
|
15
|
-
['\b[A-Z][a-z]
|
|
16
|
-
['(cf|vs)
|
|
17
|
-
['e\.g
|
|
18
|
-
['i\.e
|
|
19
|
-
['(Sec|Chap|Fig|Eq)
|
|
13
|
+
['(Mrs|Mmes|Mr|Messrs|Ms|Prof|Dr|Drs|Rev|Hon|Sen|St)\.$', '^[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
|
|
|
23
|
-
|
|
23
|
+
def self.update_rules(rules)
|
|
24
24
|
DEFAULT_RULES.merge(rules)
|
|
25
25
|
end
|
|
26
26
|
end
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: sentence_it
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.1.
|
|
4
|
+
version: 0.1.3
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Jin-Dong Kim
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2024-08-
|
|
11
|
+
date: 2024-08-03 00:00:00.000000000 Z
|
|
12
12
|
dependencies: []
|
|
13
13
|
description: It is a reimplementation text_sentencer, which is originally written
|
|
14
14
|
in ruby, using C extension for a better performance.
|