extractpatterns 0.0.7 → 0.0.8
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 +5 -5
- 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: 6e1d12367c3b10102a6e8e5869f916db672fffbe
|
|
4
|
+
data.tar.gz: a18f2d9de28356f0dccf631ee0494278fd01ef11
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 02e1683ffbed193381bd2244ec59b9eedf8f25fb51c7ac276a0afb72356ae4a67ce5f3181dcc02f546fabf42e164d58aa393332426d1cf707f4d3d3a371dded8
|
|
7
|
+
data.tar.gz: 6576f9eda00e58d8157ae98d32c623e92dda16eec2852105762e0b4fc45e116b8f12dea1b6db2f84b43461ab0378be6d957a4fd1c1835dcf8d31dad30fcec346
|
data/lib/extractpatterns.rb
CHANGED
|
@@ -42,7 +42,7 @@ class ExtractPatterns
|
|
|
42
42
|
|
|
43
43
|
# Extract set terms
|
|
44
44
|
def find_known_terms(item, field, extract_list)
|
|
45
|
-
d = TermExtractor.new(
|
|
45
|
+
d = TermExtractor.new(JSON.pretty_generate([item]), [field], "extracted_codewords")
|
|
46
46
|
d.extractSetTerms(fixEncode(File.read(extract_list)), ["codeword"], "case_sensitive")
|
|
47
47
|
return JSON.parse(d.getAllOutput).first["extracted_codewords"]
|
|
48
48
|
end
|
|
@@ -87,13 +87,13 @@ class ExtractPatterns
|
|
|
87
87
|
|
|
88
88
|
@fields.each do |field|
|
|
89
89
|
# Extract list results, allcaps, and known codewords from each field
|
|
90
|
-
list_results = comma_list_matches(
|
|
91
|
-
allcaps_results = get_allcaps(
|
|
90
|
+
list_results = comma_list_matches(item[field])
|
|
91
|
+
allcaps_results = get_allcaps(item[field], allcaps_length)
|
|
92
92
|
merge_results = item[merge_field] ? item[merge_field] : []
|
|
93
|
-
|
|
93
|
+
# known_terms_results = find_known_terms(fixEncode(item), field, extract_list)
|
|
94
94
|
|
|
95
95
|
# Merge results and post-process
|
|
96
|
-
item[@match_name] = item[@match_name] | normalize_results((allcaps_results | list_results | merge_results
|
|
96
|
+
item[@match_name] = item[@match_name] | normalize_results((allcaps_results | list_results | merge_results ),extract_list)
|
|
97
97
|
end
|
|
98
98
|
|
|
99
99
|
# Push updated item out
|