gn_crossmap 0.1.6 → 0.1.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 216f6c9075440bcd561f162c87444ff276062423
-  data.tar.gz: 4a615a04bc5fcc97530edddf62e62c66fee97761
+  metadata.gz: 9f528c813176d1683a162444e5a70917e9efd2bb
+  data.tar.gz: bd398879ac5ffd7cf104d89b0dc4d6060e2cdd64
 SHA512:
-  metadata.gz: c9284eefdad5f12f171eecc67dce4c3b6684a0a2e6b52a8ec0eac01afe03ee862625dabd32f4f3985381fe9ede398a6ceb8ade60a4752d5ea15bd89b9e96afb8
-  data.tar.gz: 0dd26bd181ee96669f2fa52714ea358a4b92fb0df6123daf3c5c3ac139cb032481be2c47333ee31f76c8bfe147bd81aa474b76da365c026834a159efcc82a0cb
+  metadata.gz: 873f228e5f5e52c565df39771e788978d13f5f020cc739b37d5ef982df3d1e3477a1e535e95cd19bc6c92bd23983b799eddb52701005e8a59b3f5518c0b2da80
+  data.tar.gz: d10af8cf20f2e00f2508f155edd768eaee53faa1ff0046c3d740067d784d1d442067c1c1ba7e04cf3a07f6455725ade882d47a66d318e0895a286eb1b9053835

data/CHANGELOG.md

@@ -1,5 +1,21 @@
 gn_crossmap CHANGELOG
 =====================
+0.1.7
+-----
+
+* @dimus - #13 - make it possible wo ingest field names like dwc:scientificName
+                 or http://example.org/term/sommeTerm
+
+* @dimus - #12 - fix a bug which prevents so salvage most of the names from a
+                 failing batch (if a batch of names has one name that breaks
+                 resolution on GN-resolver end)
+
+* @dimus - #11 - add taxonID from resolved data to results
+
+* @dimus - #10 - in resulting csv moved "match_type" field to be the first one
+                 to make it easier to see what matched and what did not
+
+* @dimus - #9 - fixed another problem with rank inffering
 
 0.1.6
 -----

data/gn_crossmap.gemspec

@@ -35,4 +35,5 @@ Gem::Specification.new do |gem|
   gem.add_development_dependency "rspec", "~> 3.2"
   gem.add_development_dependency "rubocop", "~> 0.31"
   gem.add_development_dependency "coveralls", "~> 0.8"
+  gem.add_development_dependency "gn_uuid", "~> 0.5"
 end

data/lib/gn_crossmap/collector.rb

@@ -17,12 +17,17 @@ module GnCrossmap
     private
 
     def init_fields_collector
-      @fields = @row.map { |f| f.to_s.strip.downcase.to_sym }
+      @fields = @row.map { |f| prepare_field(f) }
       @collector = collector_factory
       err = "taxonID must be present in the csv header"
       fail GnCrossmapError, err unless @fields.include?(:taxonid)
     end
 
+    def prepare_field(field)
+      field = field.to_s.gsub(":", "/")
+      field.split("/")[-1].strip.downcase.to_sym
+    end
+
     def collect_data
       @row = @fields.zip(@row).to_h
       data = @collector.id_name_rank(@row)

data/lib/gn_crossmap/resolver.rb

@@ -52,7 +52,7 @@ module GnCrossmap
       names.split("\n").each do |name|
         begin
           res = RestClient.post(URL, data: name, data_source_ids: @ds_id)
-          @processor.process(res)
+          @processor.process(res, @current_data)
         rescue RestClient::Exception => e
           GnCrossmap.logger.error("Resolver broke on '#{name}': #{e.message}")
           next

data/lib/gn_crossmap/result_processor.rb

@@ -2,6 +2,7 @@ module GnCrossmap
   # Processes data received from the GN Resolver
   class ResultProcessor
     MATCH_TYPES = {
+      0 => "No match",
       1 => "Exact match",
       2 => "Canonical form exact match",
       3 => "Canonical form fuzzy match",
@@ -33,8 +34,9 @@ module GnCrossmap
 
     def write_empty_result(datum)
       res = @original_data[datum[:supplied_id]]
-      res += [datum[:supplied_name_string], nil, nil,
-              @input[datum[:supplied_id]][:rank], nil, nil, nil, nil]
+      res += [MATCH_TYPES[0], datum[:supplied_name_string], nil,
+              nil, @input[datum[:supplied_id]][:rank], nil,
+              nil, nil, nil]
       @writer.write(res)
     end
 
@@ -45,11 +47,14 @@ module GnCrossmap
     end
 
     def compile_result(datum, result)
-      @original_data[datum[:supplied_id]] +
-        [datum[:supplied_name_string], result[:name_string],
-         result[:canonical_form], @input[datum[:supplied_id]][:rank],
-         matched_rank(result), matched_type(result),
-         result[:edit_distance], result[:score]]
+      @original_data[datum[:supplied_id]] + new_data(datum, result)
+    end
+
+    def new_data(datum, result)
+      [matched_type(result), datum[:supplied_name_string],
+       result[:name_string], result[:canonical_form],
+       @input[datum[:supplied_id]][:rank], matched_rank(result),
+       result[:edit_distance], result[:score], result[:taxon_id]]
     end
 
     def matched_rank(record)

data/lib/gn_crossmap/sci_name_collector.rb

@@ -18,10 +18,10 @@ module GnCrossmap
     private
 
     def find_name
-      name = @row[:scientificname].strip
+      name = @row[:scientificname].to_s.strip
       authorship = @row[:scientificnameauthorship].to_s.strip
       name = "#{name} #{authorship}" if authorship != ""
-      name
+      name.strip == "" ? nil : name.strip
     end
 
     def parse_rank
@@ -29,11 +29,9 @@ module GnCrossmap
       return nil if !@parsed_name[:canonical] || @parsed_name[:hybrid]
       words_num = @parsed_name[:canonical].split(" ").size
       infer_rank(words_num)
-    rescue RuntimeError
+    rescue StandardError
       @parser = ScientificNameParser.new
       nil
-    rescue NoMethodError
-      nil
     end
 
     def infer_rank(words_in_canonical_form)

data/lib/gn_crossmap/version.rb

@@ -1,6 +1,6 @@
 # Namespace module for crossmapping checklists to GN sources
 module GnCrossmap
-  VERSION = "0.1.6"
+  VERSION = "0.1.7"
 
   def self.version
     VERSION

data/lib/gn_crossmap/writer.rb

@@ -21,9 +21,9 @@ module GnCrossmap
     private
 
     def output_fields(original_fields)
-      original_fields + [:inputName, :matchedName, :matchedCanonicalForm,
-                         :inputRank, :matchedRank, :matchedType,
-                         :matchedEditDistance, :marchedScore]
+      original_fields + [:matchedType, :inputName, :matchedName,
+                         :matchedCanonicalForm, :inputRank, :matchedRank,
+                         :matchedEditDistance, :marchedScore, :matchTaxonID]
     end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: gn_crossmap
 version: !ruby/object:Gem::Version
-  version: 0.1.6
+  version: 0.1.7
 platform: ruby
 authors:
 - Dmitry Mozzherin
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2015-05-31 00:00:00.000000000 Z
+date: 2015-06-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: trollop
@@ -136,6 +136,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.8'
+- !ruby/object:Gem::Dependency
+  name: gn_uuid
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.5'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.5'
 description: Gem uses a checklist in a comma-separated format as an input, and returns
   back a new comma-separated list crossmapping the scientific names to one of the
   data sources from http://resolver.globalnames.org