text_alignment 0.3.10 → 0.3.11
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/text_alignment/anchor_finder.rb +14 -20
- data/lib/text_alignment/version.rb +1 -1
- 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: 01525b6ca5f7e0ae1ebb9dfce2083006e095a66b3ab468ccef0a584bc3005556
|
|
4
|
+
data.tar.gz: bc1137052a12b8db97635b183f299518b0158f3ccecf36d42fa45d746b4f3792
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 9596bea2616c3b4d939c8314d026941a6e627f4380183409051df62722a0ee5e3b35302da3066b0d32e8322582c999877b05a09c54749d878a284a062247342e
|
|
7
|
+
data.tar.gz: 361e3e7a23697167b41e037e7d272bbd286ac397416defb125821ebbcb17bfa386341c75fecbb94fe7f9976cfbc2a8b5f7f9be7c150d23daf6d8c16410509b5d
|
|
@@ -27,35 +27,29 @@ class TextAlignment::AnchorFinder
|
|
|
27
27
|
|
|
28
28
|
def get_next_anchor
|
|
29
29
|
# find the position of an anchor ngram in s1 and s2
|
|
30
|
-
@beg_s2 = nil
|
|
31
30
|
while @beg_s1 < (@s1.length - @size_ngram)
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
end
|
|
39
|
-
break unless @beg_s2.nil?
|
|
40
|
-
@beg_s1 += 1
|
|
41
|
-
end
|
|
31
|
+
anchor = @s1[@beg_s1, @size_ngram]
|
|
32
|
+
|
|
33
|
+
search_position = 0
|
|
34
|
+
while @beg_s2 = @s2.index(anchor, search_position)
|
|
35
|
+
# if both the begining points are sufficiantly close to the end points of the last match
|
|
36
|
+
break if @end_s1_prev && (@beg_s1 - @end_s1_prev < 5) && (@beg_s2 - @end_s2_prev < 5)
|
|
42
37
|
|
|
43
|
-
|
|
44
|
-
|
|
38
|
+
left_window_s1, left_window_s2 = get_left_windows
|
|
39
|
+
break if left_window_s1 && text_similarity(left_window_s1, left_window_s2) > TextAlignment::TEXT_SIMILARITY_TRESHOLD
|
|
45
40
|
|
|
46
|
-
|
|
47
|
-
|
|
41
|
+
right_window_s1, right_window_s2 = get_right_windows
|
|
42
|
+
break if right_window_s2 && text_similarity(right_window_s1, left_window_s2) > TextAlignment::TEXT_SIMILARITY_TRESHOLD
|
|
48
43
|
|
|
49
|
-
|
|
50
|
-
|
|
44
|
+
search_position = @beg_s2 + 1
|
|
45
|
+
end
|
|
51
46
|
|
|
52
|
-
|
|
53
|
-
break if right_window_s2 && text_similarity(right_window_s1, left_window_s2) > TextAlignment::TEXT_SIMILARITY_TRESHOLD
|
|
47
|
+
break unless @beg_s2.nil?
|
|
54
48
|
|
|
55
49
|
@beg_s1 += 1
|
|
56
50
|
end
|
|
57
51
|
|
|
58
|
-
return nil if @
|
|
52
|
+
return nil if @beg_s1 >= (@s1.length - @size_ngram)
|
|
59
53
|
|
|
60
54
|
# extend the block
|
|
61
55
|
b1 = @beg_s1
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: text_alignment
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.3.
|
|
4
|
+
version: 0.3.11
|
|
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: 2020-
|
|
11
|
+
date: 2020-09-10 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: ruby-dictionary
|