extractpatterns 0.0.3 → 0.0.4

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.
Files changed (3) hide show
  1. checksums.yaml +4 -4
  2. data/lib/extractpatterns.rb +7 -8
  3. metadata +1 -1
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA1:
3
- metadata.gz: 17d17e273a60c9543bb78b5c193d88f908c174c3
4
- data.tar.gz: fcc30f5af578d856446c0090a5e466200c729a3e
3
+ metadata.gz: fe82bbccbfb524bb8b970b56bbc43ce23c50ec51
4
+ data.tar.gz: 64f63a72db54336c1bc3d5f7e65509067df695f2
5
5
  SHA512:
6
- metadata.gz: bde3529e9d77807d00fbf0f23d2884d80ccd9e3d69fd57e8c2fde7dccbc1d140c4eff99c3e2e37509cc35706d2635b44159df74c0a11ce7e3221ac9803b922e8
7
- data.tar.gz: ce78a9713e51829aae58cf551c9d718c45ffa21cda1f656dcf92e61cd7aff0abe3aa6248c109bdba25ed75eede7c4fab444534b7ad355fda6213bbd51afad055
6
+ metadata.gz: 20f5903c04b111f14679a638c205a19a5c42eaffe27e4d3efb9d14dcdba31de6ff20e8249dcbf824515b8b2952345ccf21e845cd125e429b084df32985ee725b
7
+ data.tar.gz: e41d433ca8d40e41e05f878c571f88330c7989b53248f0c9fb08c565465e31e5c2998d276b019a57bdfb59d462a8fb4769820920addd8ca00fa8903920992fbd
@@ -87,16 +87,15 @@ 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(item[field])
91
- allcaps_results = get_allcaps(item[field], allcaps_length)
90
+ list_results = comma_list_matches(fixEncode(item[field]))
91
+ allcaps_results = get_allcaps(fixEncode(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 ),
97
- extract_list)
96
+ item[@match_name] = item[@match_name] | normalize_results((allcaps_results | list_results | merge_results | known_terms_results),extract_list)
98
97
  end
99
-
98
+
100
99
  # Push updated item out
101
100
  @output.push(item)
102
101
  end
@@ -139,6 +138,6 @@ end
139
138
  # end
140
139
  #end
141
140
 
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)
141
+ #e = ExtractPatterns.new(File.read("blackfin.json"), ["description", "summary"], "tools_mentioned")
142
+ #puts e.search_fields(6, "extract_list.json", "skills")
144
143
  #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: 0.0.3
4
+ version: 0.0.4
5
5
  platform: ruby
6
6
  authors:
7
7
  - M. C. McGrath