extractpatterns 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/lib/extractpatterns.rb +10 -1
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: b4839a2718581a04fd0fba727ebe49a555d0e429
|
4
|
+
data.tar.gz: 6ff61dbdb39ca8db3d994a928ead04b90924706a
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: b227fcfdb2fbca4a5bb8c127d7b293d85ebcc738a1c0ad6b23fd86115b3d7439b8ba65459b1eac1835f3fe2358f6b9bd25ef74c42f4605c0ec233c21950c9ad4
|
7
|
+
data.tar.gz: 55f286d1d433963fd58c94527de287268e69e6e7f229eb9bb6ae5d13a5396c7a6daea2ab78ae9668b29e34696a820c143fa113e5843cb6589b2c9753941ad40e
|
data/lib/extractpatterns.rb
CHANGED
@@ -43,10 +43,19 @@ class ExtractPatterns
|
|
43
43
|
# Extract set terms
|
44
44
|
def find_known_terms(item, field, extract_list)
|
45
45
|
d = TermExtractor.new(JSON.pretty_generate([item]), [field], "extracted_codewords")
|
46
|
-
d.extractSetTerms(File.read(extract_list), ["codeword"], "case_sensitive")
|
46
|
+
d.extractSetTerms(fixEncode(File.read(extract_list)), ["codeword"], "case_sensitive")
|
47
47
|
return JSON.parse(d.getAllOutput).first["extracted_codewords"]
|
48
48
|
end
|
49
49
|
|
50
|
+
# Fix encoding errors
|
51
|
+
def fixEncode(str)
|
52
|
+
if str.is_a?(String)
|
53
|
+
return str.unpack('C*').pack('U*')
|
54
|
+
else
|
55
|
+
return str
|
56
|
+
end
|
57
|
+
end
|
58
|
+
|
50
59
|
# Normalize and match synonyms and deduplicate
|
51
60
|
def normalize_results(extracted_raw, synonym_list)
|
52
61
|
synonyms = JSON.parse(File.read(synonym_list))
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: extractpatterns
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- M. C. McGrath
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2015-12-
|
11
|
+
date: 2015-12-28 00:00:00.000000000 Z
|
12
12
|
dependencies: []
|
13
13
|
description: Extracts entities and terms from any JSON.
|
14
14
|
email: shidash@shidash.com
|