kuromoji-ruby 0.0.2 → 0.0.3
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/kuromoji/core.rb +4 -2
- data/lib/kuromoji/version.rb +1 -1
- data/test/kuromoji_test.rb +16 -0
- 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: 79695dc07004a11e3cbb3bdf811632947cf60013
|
4
|
+
data.tar.gz: 515f693f83989af2573be3976757119b6e098747
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 4cea18296084e75632c32e9fc8d9e3a6a6a94aea35157d1b22607138cc46ceebe7cac2944bf26d78c844983265bd936f58426db15c7bf8e1e048ab72724eeebc
|
7
|
+
data.tar.gz: b4ff9abf67c2c15b2cf97af1c3b4ee83e43e2d72085af1e0a11e4a26bd7605caf7f705ef34a891120561da5f23ec32f563483fbc8ad271f12a093e239f33568f
|
data/lib/kuromoji/core.rb
CHANGED
@@ -37,9 +37,10 @@ module Kuromoji
|
|
37
37
|
end
|
38
38
|
|
39
39
|
def tokenize_with_hash(sentence)
|
40
|
+
result = []
|
41
|
+
return result if sentence.nil?
|
40
42
|
list = @tokenizer.tokenize(sentence)
|
41
43
|
iterator = list.iterator
|
42
|
-
result = []
|
43
44
|
while iterator.has_next
|
44
45
|
item = iterator.next
|
45
46
|
result << item.to_kuromoji_hash
|
@@ -48,9 +49,10 @@ module Kuromoji
|
|
48
49
|
end
|
49
50
|
|
50
51
|
def process(method, sentence)
|
52
|
+
tokenized = {}
|
53
|
+
return tokenized if sentence.nil?
|
51
54
|
list = @tokenizer.tokenize(sentence)
|
52
55
|
iterator = list.iterator
|
53
|
-
tokenized = {}
|
54
56
|
while iterator.has_next
|
55
57
|
item = iterator.next
|
56
58
|
tokenized[item.surface_form] = item.send(method)
|
data/lib/kuromoji/version.rb
CHANGED
data/test/kuromoji_test.rb
CHANGED
@@ -34,4 +34,20 @@ class KuromojiTest < Minitest::Test
|
|
34
34
|
assert_equal token['surface_form'], check[i]
|
35
35
|
end
|
36
36
|
end
|
37
|
+
|
38
|
+
def test_nil
|
39
|
+
tokenized = @no_dictionary.tokenize_with_hash(nil)
|
40
|
+
assert_equal tokenized, []
|
41
|
+
|
42
|
+
tokenized = @no_dictionary.reading(nil)
|
43
|
+
assert_equal tokenized, {}
|
44
|
+
end
|
45
|
+
|
46
|
+
def test_empty
|
47
|
+
tokenized = @use_dictionary.tokenize_with_hash('')
|
48
|
+
assert_equal tokenized, []
|
49
|
+
|
50
|
+
tokenized = @no_dictionary.reading('')
|
51
|
+
assert_equal tokenized, {}
|
52
|
+
end
|
37
53
|
end
|