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.
- checksums.yaml +4 -4
- data/lib/extractpatterns.rb +7 -8
- 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: fe82bbccbfb524bb8b970b56bbc43ce23c50ec51
|
4
|
+
data.tar.gz: 64f63a72db54336c1bc3d5f7e65509067df695f2
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 20f5903c04b111f14679a638c205a19a5c42eaffe27e4d3efb9d14dcdba31de6ff20e8249dcbf824515b8b2952345ccf21e845cd125e429b084df32985ee725b
|
7
|
+
data.tar.gz: e41d433ca8d40e41e05f878c571f88330c7989b53248f0c9fb08c565465e31e5c2998d276b019a57bdfb59d462a8fb4769820920addd8ca00fa8903920992fbd
|
data/lib/extractpatterns.rb
CHANGED
@@ -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
|
-
|
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("
|
143
|
-
#puts e.search_fields(6, "extract_list.json",
|
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)
|