wcc-text-analysis 0.0.1 → 0.0.2
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/.gitignore +2 -1
- data/lib/wcc/text_analysis.rb +15 -8
- data/lib/wcc/text_analysis/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: 66a18a3f32298d0124f6e045f4e83db791fd2d67502c327be659fed2ab82ffad
|
|
4
|
+
data.tar.gz: fee8ce474ebaa139fc0ea4fb8fa706cdb5646fe2b9b3eda768ed8ef23994d137
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: e69ce56fe1ffec9d057e9694ff0b45cda625e894b42abca76c94c8b14992c94dbdcca4045be5452c50f496877cd2842ee9489027fde95a55d7a418057f488e63
|
|
7
|
+
data.tar.gz: 88730022fd77784a9ae04c34ff7ddc32dff8c75414065ed53e078e1471a2af980f495b5587c62753252d156ad1da12cb5f1569d4e073e798300673083ef781a2
|
data/.gitignore
CHANGED
|
@@ -1 +1,2 @@
|
|
|
1
|
-
Gemfile.lock
|
|
1
|
+
Gemfile.lock
|
|
2
|
+
pkg/*
|
data/lib/wcc/text_analysis.rb
CHANGED
|
@@ -8,11 +8,22 @@ module WCC
|
|
|
8
8
|
|
|
9
9
|
attr_reader :normalized, :stripped
|
|
10
10
|
|
|
11
|
-
def self.extract_terms(
|
|
12
|
-
File.read(
|
|
11
|
+
def self.extract_terms(db_file)
|
|
12
|
+
File.read(
|
|
13
|
+
File.join(File.dirname(__FILE__), '../../db', db_file),
|
|
14
|
+
).split("\n")
|
|
13
15
|
end
|
|
14
16
|
|
|
15
|
-
|
|
17
|
+
# Stopwords from http://www.ranks.nl/stopwords
|
|
18
|
+
def self.default_stopwords
|
|
19
|
+
@default_stopwords ||= extract_terms('stop_words.txt')
|
|
20
|
+
end
|
|
21
|
+
|
|
22
|
+
def self.default_exclusions
|
|
23
|
+
@default_exclusions ||= extract_terms('transcript_exclusions.txt')
|
|
24
|
+
end
|
|
25
|
+
|
|
26
|
+
def initialize(string, stop_words: self.class.default_stopwords)
|
|
16
27
|
@original = string
|
|
17
28
|
@stop_words = stop_words
|
|
18
29
|
end
|
|
@@ -61,11 +72,7 @@ module WCC
|
|
|
61
72
|
end
|
|
62
73
|
|
|
63
74
|
def remove_ignored_tokens(string)
|
|
64
|
-
string - (@stop_words +
|
|
75
|
+
string - (@stop_words + self.class.default_exclusions)
|
|
65
76
|
end
|
|
66
|
-
|
|
67
|
-
# Stopwords from http://www.ranks.nl/stopwords
|
|
68
|
-
STOPWORDS = extract_terms("stop_words").freeze
|
|
69
|
-
EXCLUSIONS = extract_terms("transcript_exclusions").freeze
|
|
70
77
|
end
|
|
71
78
|
end
|