spacifier 1.0.0.pre.alpha2 → 1.0.0.pre.alpha3

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
  SHA1:
3
- metadata.gz: 9d9f70f6f9b9efdb04de2cc4c4838c6a36e8d68b
4
- data.tar.gz: 747190451b7c1f70f7e74562d8f28caa295e7f12
3
+ metadata.gz: 65d49016c156ab3983ebae779feeb7c2cdf050ae
4
+ data.tar.gz: dbbf28808141bbb4e74d90f203548e9cc97f41cf
5
5
  SHA512:
6
- metadata.gz: 18a00994e46eeefcf821d48b436f5c5c9983eefc5e4ebf81539b2c3e829a6f897e045debc161518c495c343d162829535aa6f31df299b629c3d99b05ea1e78a2
7
- data.tar.gz: a2f41e63fd3b5ef7aab0fa8bbc305abe7c8b5a2533042bacd1d956a38edb625e1996cea2f7dd9e600b5f6bf9f0d6b883d70d86b86dd251500b75ed44da536ff2
6
+ metadata.gz: aa8da243d339b5ca87f92b394610ec5603ae761e6de3a9de4c3aa6a3b689357945d8190f38349b4369b6df22c339e863540c398aa41269cfb07098c08e581575
7
+ data.tar.gz: 60f1cd64093a3b29a35b529ee062fc93ecc53869a2a434eb25cca3998acf28ba91e29d0f7c6bb5f725e0e83729f17b6554e9046fe4e41ff0a8e94a813b89e363
@@ -1,11 +1,9 @@
1
1
  # encoding: utf-8
2
2
 
3
3
  module Spacifier
4
- CHINESE_PUNCTUATIONS = ",。/、()【】「」·~《》?".freeze
5
-
6
4
  class << self
7
- def is_chinese_punctuation(c)
8
- CHINESE_PUNCTUATIONS.include? c
5
+ def is_punctuation(c)
6
+ !(/\p{P}/.match(c) == nil)
9
7
  end
10
8
  end
11
9
  end
@@ -1,3 +1,3 @@
1
1
  module Spacifier
2
- VERSION = "1.0.0-alpha2".freeze
2
+ VERSION = "1.0.0-alpha3".freeze
3
3
  end
data/lib/spacifier.rb CHANGED
@@ -14,8 +14,15 @@ module Spacifier
14
14
  last_word_type = nil # 0 for cn, 1 for en
15
15
  # iterate chars
16
16
  words.each_char do |c|
17
- if is_chinese_punctuation(c)
17
+ if c == " "
18
18
  new_words << c
19
+ last_word_type = nil
20
+ elsif /\d/.match(c) != nil
21
+ new_words << c
22
+ last_word_type = nil
23
+ elsif is_punctuation(c)
24
+ new_words << c
25
+ last_word_type = nil
19
26
  elsif /\p{Han}/.match(c) == nil
20
27
  new_words << " " if last_word_type == 0
21
28
  new_words << c
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: spacifier
3
3
  version: !ruby/object:Gem::Version
4
- version: 1.0.0.pre.alpha2
4
+ version: 1.0.0.pre.alpha3
5
5
  platform: ruby
6
6
  authors:
7
7
  - David Zhang