extractpatterns 0.0.2 → 0.0.3

Sign up to get free protection for your applications and to get access to all the features.
Files changed (3) hide show
  1. checksums.yaml +4 -4
  2. data/lib/extractpatterns.rb +5 -4
  3. metadata +1 -1
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA1:
3
- metadata.gz: b4839a2718581a04fd0fba727ebe49a555d0e429
4
- data.tar.gz: 6ff61dbdb39ca8db3d994a928ead04b90924706a
3
+ metadata.gz: 17d17e273a60c9543bb78b5c193d88f908c174c3
4
+ data.tar.gz: fcc30f5af578d856446c0090a5e466200c729a3e
5
5
  SHA512:
6
- metadata.gz: b227fcfdb2fbca4a5bb8c127d7b293d85ebcc738a1c0ad6b23fd86115b3d7439b8ba65459b1eac1835f3fe2358f6b9bd25ef74c42f4605c0ec233c21950c9ad4
7
- data.tar.gz: 55f286d1d433963fd58c94527de287268e69e6e7f229eb9bb6ae5d13a5396c7a6daea2ab78ae9668b29e34696a820c143fa113e5843cb6589b2c9753941ad40e
6
+ metadata.gz: bde3529e9d77807d00fbf0f23d2884d80ccd9e3d69fd57e8c2fde7dccbc1d140c4eff99c3e2e37509cc35706d2635b44159df74c0a11ce7e3221ac9803b922e8
7
+ data.tar.gz: ce78a9713e51829aae58cf551c9d718c45ffa21cda1f656dcf92e61cd7aff0abe3aa6248c109bdba25ed75eede7c4fab444534b7ad355fda6213bbd51afad055
@@ -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(JSON.pretty_generate([item]), [field], "extracted_codewords")
45
+ d = TermExtractor.new(fixEncode(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
@@ -90,10 +90,10 @@ class ExtractPatterns
90
90
  list_results = comma_list_matches(item[field])
91
91
  allcaps_results = get_allcaps(item[field], allcaps_length)
92
92
  merge_results = item[merge_field] ? item[merge_field] : []
93
- known_terms_results = find_known_terms(item, field, extract_list)
93
+ #known_terms_results = find_known_terms(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 | known_terms_results),
96
+ item[@match_name] = item[@match_name] | normalize_results((allcaps_results | list_results | merge_results ),
97
97
  extract_list)
98
98
  end
99
99
 
@@ -139,5 +139,6 @@ end
139
139
  # end
140
140
  #end
141
141
 
142
- #e = ExtractPatterns.new(File.read("MECWEDB.json"), ["description", "summary"], "tools_mentioned")
142
+ #e = ExtractPatterns.new(File.read("/home/shidash/Data/unknown_test/Never_Shake_A_Baby_SIGINT.json"), ["additional_info", "job_description", "skills", "summary"], "tools_mentioned")
143
+ #puts e.search_fields(6, "extract_list.json", nil)
143
144
  #puts e.ranked_hash_output(overalloutput)
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: extractpatterns
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.0.2
4
+ version: 0.0.3
5
5
  platform: ruby
6
6
  authors:
7
7
  - M. C. McGrath