text_alignment 0.3.24 → 0.4
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/text_alignment/anchor_finder.rb +4 -3
- data/lib/text_alignment/version.rb +1 -1
- metadata +1 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 35f83f76cd3e9ca59604327710d2eac4684b8abca9dbd167b2b391d98ea561f9
|
4
|
+
data.tar.gz: 77007a1bfcf72d0681ac9d21b35221e7d519a291383f3d0d8fa0574d631b65ea
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 2f936569e072e6693f279b5d3a349965b286192d8f694fffbbf41110f66afbd5d80f865a9232c2bef60ec94920e0a814142c8756f0ba3ff29a109cbbe1f7abec
|
7
|
+
data.tar.gz: 955b85aa639f733361f354cc68ac3d8b14a17a14784f1e6ec24f240934ef0d160c6b8cf01232e1e4243c2eecffcaf1665999cc3e455bfb0e61c0dd905d2cb8b4
|
@@ -9,9 +9,10 @@ TextAlignment::TEXT_SIMILARITY_TRESHOLD = 0.8 unless defined? TextAlignment::TEX
|
|
9
9
|
|
10
10
|
class TextAlignment::AnchorFinder
|
11
11
|
|
12
|
-
def initialize(source_str, target_str, _size_ngram = nil, _size_window = nil)
|
12
|
+
def initialize(source_str, target_str, _size_ngram = nil, _size_window = nil, _text_similiarity_threshold = nil)
|
13
13
|
@size_ngram = _size_ngram || TextAlignment::SIZE_NGRAM
|
14
14
|
@size_window = _size_window || TextAlignment::SIZE_WINDOW
|
15
|
+
@sim_threshold = _size_window || TextAlignment::TEXT_SIMILARITY_TRESHOLD
|
15
16
|
|
16
17
|
@reverse = (target_str.length < source_str.length)
|
17
18
|
|
@@ -43,10 +44,10 @@ class TextAlignment::AnchorFinder
|
|
43
44
|
break if @beg_s1 > 0 && @beg_s2 > 0 && (@beg_s1 - @end_s1_prev < 5) && (@beg_s2 >= @end_s2_prev) && (@beg_s2 - @end_s2_prev < 5)
|
44
45
|
|
45
46
|
left_window_s1, left_window_s2 = get_left_windows
|
46
|
-
break if left_window_s1 && (text_similarity(left_window_s1, left_window_s2) >
|
47
|
+
break if left_window_s1 && (text_similarity(left_window_s1, left_window_s2) > @sim_threshold)
|
47
48
|
|
48
49
|
right_window_s1, right_window_s2 = get_right_windows
|
49
|
-
break if right_window_s2 && (text_similarity(right_window_s1, right_window_s2) >
|
50
|
+
break if right_window_s2 && (text_similarity(right_window_s1, right_window_s2) > @sim_threshold)
|
50
51
|
|
51
52
|
search_position = @beg_s2 + 1
|
52
53
|
end
|