gn_crossmap 3.1.5 → 3.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: c2c789845b44b7024403fad224e24dffce133d23
-  data.tar.gz: 9257b08c532e69c141dadec5aa1f9d185dd50968
+  metadata.gz: bfd0f87bbaf73d66c33e130c124e087104994879
+  data.tar.gz: 11020365c22465b4d804faaf2cf13c6ee168b051
 SHA512:
-  metadata.gz: 2ca3260ab4a2985692b44bac76274a65a9079aef9b21254475ebb558d770f9e9cc4f05a35f28c4b802575c1799cc8785390192222cbe4400b0cfa669181e2043
-  data.tar.gz: 5339a56423169e8bc84dc72d83437d47409ba4c752bef77e7de00bbf91c3ef983389c99a0ab302b10bd6358510b2f85f759ef316f7baa3e1c3275ac1e1d34e1b
+  metadata.gz: 5ca351156f9007cc6aaa879b3d86852b2a1aeb2584182351ccd3d228997cbccb47604bf97654bd583e58bc1a7280d0f0acb9f6903095db783e4bf0e614cebddf
+  data.tar.gz: 5580be6d8d50f4385e05b798b37a987338e54270d132560df1465f7d2a8cd101b22394a867481577861f03fea28efdd412542092f7f8b5928bf9d8654c434321

data/CHANGELOG.md

@@ -1,5 +1,9 @@
 # ``gn_crossmap`` CHANGELOG
 
+## 3.2.0
+
+* @dimus - Add a column `matchSize` with number of matches for each name
+
 ## 3.1.5
 
 * @dimus - Fix number of columns in the output when there is no taxon_id given

data/README.md

@@ -251,15 +251,17 @@ More examples can be found in [spec/files][files] directory
 
 Field                | Description
 ---------------------|-----------------------------------------------------------
-taxonID              | original ID attached to a name in the checklist
-scientificName       | name from the checklist
-matchedScientificName| name matched from the GN Reolver data source
+classification       | classification path of the data source (if available)
+editDistance         | for fuzzy-matching -- how many characters differ between checklist and data source name
+matchSize            | number of returned matches for a name
+matchType            | what kind of match it is
 matchedCanonicalForm | canonical form of the matched name
-rank                 | rank from the source (if it was given/inferred)
 matchedRank          | corresponding rank from the data source
-matchType            | what kind of match it is
-editDistance         | for fuzzy-matching -- how many characters differ between checklist and data source name
+matchedScientificName| name matched from the GN Reolver data source
+rank                 | rank from the source (if it was given/inferred)
+scientificName       | name from the checklist
 score                | heuristic score from 0 to 1 where 1 is a good match, 0.5 match requires further human investigation
+taxonID              | original ID attached to a name in the checklist
 
 #### Types of Matches
 

data/lib/gn_crossmap.rb

@@ -61,7 +61,11 @@ module GnCrossmap
     end
 
     def find_id(row, name)
-      row.key?(:taxonid) ? row[:taxonid].strip : GnUUID.uuid(name)
+      if row.key?(:taxonid) && row[:taxonid]
+        row[:taxonid].to_s.strip
+      else
+        GnUUID.uuid(name.to_s)
+      end
     end
 
     private

data/lib/gn_crossmap/result_processor.rb

@@ -36,7 +36,7 @@ module GnCrossmap
 
     def compile_empty_result(datum)
       res = @original_data[datum[:supplied_id]]
-      res += [GnCrossmap::MATCH_TYPES[0], datum[:supplied_name_string],
+      res += [GnCrossmap::MATCH_TYPES[0], 0, datum[:supplied_name_string],
               nil, nil, nil, nil,
               @input[datum[:supplied_id]][:rank], nil, nil, nil, nil, nil]
       res <<  nil if @with_classification
@@ -45,8 +45,9 @@ module GnCrossmap
 
     def write_result(datum)
       collect_stats(datum)
+      match_size = datum[:results].size
       datum[:results].each do |result|
-        @writer.write(compile_result(datum, result))
+        @writer.write(compile_result(datum, result, match_size))
       end
     end
 
@@ -56,15 +57,16 @@ module GnCrossmap
       @stats.stats[:resolved_records] += 1
     end
 
-    def compile_result(datum, result)
-      @original_data[datum[:supplied_id]] + new_data(datum, result)
+    def compile_result(datum, result, match_size)
+      @original_data[datum[:supplied_id]] + new_data(datum,
+                                                     result, match_size)
     end
 
     # rubocop:disable Metrics/AbcSize
 
-    def new_data(datum, result)
+    def new_data(datum, result, match_size)
       synonym = result[:current_name_string] ? "synonym" : nil
-      res = [matched_type(result), datum[:supplied_name_string],
+      res = [matched_type(result), match_size, datum[:supplied_name_string],
              result[:name_string], canonical(datum[:supplied_name_string]),
              result[:canonical_form], result[:edit_distance],
              @input[datum[:supplied_id]][:rank], matched_rank(result), synonym,

data/lib/gn_crossmap/version.rb

@@ -2,7 +2,7 @@
 
 # Namespace module for crossmapping checklists to GN sources
 module GnCrossmap
-  VERSION = "3.1.5"
+  VERSION = "3.2.0"
 
   def self.version
     VERSION

data/lib/gn_crossmap/writer.rb

@@ -26,8 +26,9 @@ module GnCrossmap
     private
 
     def output_fields(original_fields)
-      original_fields + %i[matchedType inputName matchedName inputCanonicalForm
-                           matchedCanonicalForm matchedEditDistance inputRank
+      original_fields + %i[matchedType matchSize inputName matchedName
+                           inputCanonicalForm matchedCanonicalForm
+                           matchedEditDistance inputRank
                            matchedRank synonymStatus acceptedName
                            matchedScore matchTaxonID]
     end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: gn_crossmap
 version: !ruby/object:Gem::Version
-  version: 3.1.5
+  version: 3.2.0
 platform: ruby
 authors:
 - Dmitry Mozzherin
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-08-10 00:00:00.000000000 Z
+date: 2017-08-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: biodiversity