gn_crossmap 0.2.2 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 0c5590798834035bde904c19913ec08731c58a31
-  data.tar.gz: 28d1b65e628d614f6aa7709094a7e49a3af26052
+  metadata.gz: 779a3a9193e896242a7e8717fd98bc779b417937
+  data.tar.gz: d8e9c4c7d72447a62d35f57fe26e33e9b5a69a29
 SHA512:
-  metadata.gz: 5cbb64951ae0aeae2d207c59012afe17666c1b7e599bdbe4444c0b51b27de5ebc48d20e69594a42c890c88d239ce6f9860ea68f119ebd48c09e03155ad494ca5
-  data.tar.gz: 9b2d6c03842b7fb969368d7ecdd0297a1df27b10f0eeee97eca67181fa455d5fa2c552ad37f2ea35ee11291eecaed52feda43f95bb7ba7a00e462afd9b881f73
+  metadata.gz: 83f6f2f6be28c5891d93e5f6e5e09ac54481f4334640ef3b500822301bb5d1ea2cf0d5ca94f4ba0a2eb7b7e7afcd67fed8b37ad76c61ac184c2d9932d080ccf3
+  data.tar.gz: ae609d842d36b96de15ffe3013fe49e762da963191609486757d7ba9bbc5e85cdf674a19e24916fdcac7214d37adb1a9c089c95cd89ba9c4c7360256858cca11

data/.gitignore

@@ -11,3 +11,4 @@ output.csv
 .vim.custom
 t
 gn_crossmap-*.gem
+.byebug_history

data/CHANGELOG.md

@@ -1,5 +1,13 @@
 # ``gn_crossmap`` CHANGELOG
 
+## 1.0.0
+
+* @dimus - #18 output file optionally removes original fields except `taxonID`
+
+* @dimus - #19 `acceptedName` field if filled for all matched names
+
+* @dimus - #22 output is now tab-separated instead of comma-separated
+
 ## 0.2.2
 
 * @dimus - gem update

data/README.md

@@ -27,37 +27,75 @@ gem 'gn_crossmap'
 
 And then execute:
 
-    bundle
+```bash
+bundle
+```
 
 Or install it yourself as:
 
-    gem install gn_crossmap
+```bash
+gem install gn_crossmap
+```
 
 ## Usage
 
 ### Usage from command line
 
-    # to see help
-    crossmap --help
+```bash
+# to see help
+crossmap --help
+
+# to compare with default source (Catalogue of Life)
+crossmap -i my_list.csv -o my_list_col.csv
+
+# to compare with other source (Index Fungorum in this example)
+crossmap -i my_list.csv -o my_list_if.csv -d 5
+
+# to use standard intput and/or output
+cat my_list.csv | crossmap -i - -o - > output
+
+# to keep only taxonID from original input
+cat my_list.csv | crossmap -i my_list.csv -s
+```
+
+### Usage as Ruby Library (API description)
+
+#### `GnCrossmap.run`
+
+Compares an input list to a data source from [GN Resolver][resolver] and
+writes result into an output file.
+
+```ruby
+GnCrossmap.run(input, output, data_source_id, skip_original)
+```
+
+``input``
+: (string) Either a path to a csv file with list of names, or "-" which
+designates `STDIN`
+
+``output``
+: (string) Either a path to the output file, or "-" which designates `STDOUT`
+
+``data_source_id``
+: (integer) id of a data source from [GN resolver][resolver]
 
-    # to compare with default source (Catalogue of Life)
-    crossmap -i my_list.csv -o my_list_col.csv
+``skip_original``
+: (boolean) if true only `taxonID` is preserved from original data. Otherwise
+all original data is preserved
 
-    # to compare with other source (Index Fungorum in this example)
-    crossmap -i my_list.csv -o my_list_if.csv -d 5
+#### `GnCrossmap.logger=`
 
-    # to use standard intput and/or output
-    cat my_list.csv | crossmap -i - -o - > output
+Allows to set logger to a custom logger (default is `STDERR`)
 
-### Usage as Ruby Library
+#### Usage Example
 
 ```ruby
 require "gn_crossmap"
 
-# If you want to change logger -- default Logging is to standard output
+# If you want to change logger -- default Logging is to standard error
 GnCrossmap.logger = MyCustomLogger.new
 
-GnCrossmap.run("path/to/input.csv", "path/to/output.csv", 5)
+GnCrossmap.run("path/to/input.csv", "path/to/output.csv", 5, true)
 ```
 
 ### Input file format
@@ -136,7 +174,7 @@ score                | heuristic score from 0 to 1 where 1 is a good match, 0.5
 
 The output fomat returns 7 possible types of matches:
 
-1. **Exact match** - The exact name was matched (but ignoring non-ascii characters)
+1. **Exact string match** - The exact name was matched (but ignoring non-ascii characters)
 2. **Exact match by canonical form of a name** - The canonical form of the name (a version of a scientific name that contains complete versions of the latin words, but lacks insertions of subtaxa, annotations, or authority information) was matched
 3. **Fuzzy match by canonical form** - The canonical form gave a fuzzy (detecting lexical or spelling variations of a name using Tony Rees' algorithm TAXAMATCH) match
 4. **Partial exact match by species part of canonical form** - The canonical form returned a partial but exact match
@@ -178,7 +216,7 @@ See [LICENSE][license] for details.
 [cov-link]: https://coveralls.io/r/GlobalNamesArchitecture/gn_crossmap?branch=master
 [code-badge]: https://codeclimate.com/github/GlobalNamesArchitecture/gn_crossmap/badges/gpa.svg
 [code-link]: https://codeclimate.com/github/GlobalNamesArchitecture/gn_crossmap
-[dep-badge]: https://gemnasium.com/GlobalNamesArchitecture/gn_crossmap.png
+[dep-badge]: https://gemnasium.com/GlobalNamesArchitecture/gn_crossmap.svg
 [dep-link]: https://gemnasium.com/GlobalNamesArchitecture/gn_crossmap
 [resolver]: http://resolver.globalnames.org/data_sources
 [rubygems]: https://rubygems.org

data/exe/crossmap

@@ -16,6 +16,8 @@ opts = Trollop.options do
   opt(:output, "Path to output file", default: OUTPUT)
   opt(:data_source_id, "Data source id from GN Resolver",
       default: CATALOGUE_OF_LIFE)
+  opt(:skip_original, "If given, only 'taxonID' is shown " \
+      "from the original input", type: :boolean)
 end
 
 Trollop.die :input, "must be set" if opts[:input].nil?
@@ -24,7 +26,8 @@ unless File.exist?(opts[:input]) || opts[:input] == "-"
 end
 
 begin
-  GnCrossmap.run(opts[:input], opts[:output], opts[:data_source_id])
+  GnCrossmap.run(opts[:input], opts[:output], opts[:data_source_id],
+                 opts[:skip_original])
 rescue GnCrossmapError => e
   GnCrossmap.logger.error(e.message)
 end

data/lib/gn_crossmap.rb

@@ -22,9 +22,9 @@ module GnCrossmap
   class << self
     attr_writer :logger
 
-    def run(input, output, data_source_id)
+    def run(input, output, data_source_id, skip_original)
       input_io, output_io = io(input, output)
-      reader = Reader.new(input_io, input_name(input))
+      reader = Reader.new(input_io, input_name(input), skip_original)
       data = reader.read
       writer = Writer.new(output_io, reader.original_fields,
                           output_name(output))

data/lib/gn_crossmap/collector.rb

@@ -3,10 +3,11 @@ module GnCrossmap
   class Collector
     attr_reader :data
 
-    def initialize
+    def initialize(skip_original)
       @data = []
       @fields = nil
       @collector = nil
+      @skip_original = skip_original
     end
 
     def process_row(row)
@@ -20,7 +21,12 @@ module GnCrossmap
       @fields = @row.map { |f| prepare_field(f) }
       @collector = collector_factory
       err = "taxonID must be present in the csv header"
-      raise GnCrossmapError, err unless @fields.include?(:taxonid)
+      raise GnCrossmapError, err unless taxon_id?
+    end
+
+    def taxon_id?
+      @taxon_id_index = @fields.index(:taxonid)
+      !@taxon_id_index.nil?
     end
 
     def prepare_field(field)
@@ -32,10 +38,14 @@ module GnCrossmap
       @row = @fields.zip(@row).to_h
       data = @collector.id_name_rank(@row)
       return unless data
-      data[:original] = @row.values
+      data[:original] = prepare_original
       @data << data
     end
 
+    def prepare_original
+      @skip_original ? [@row[:taxonid]] : @row.values
+    end
+
     def collector_factory
       if @fields.include?(:scientificname)
         SciNameCollector.new(@fields)

data/lib/gn_crossmap/reader.rb

@@ -4,11 +4,12 @@ module GnCrossmap
   class Reader
     attr_reader :original_fields
 
-    def initialize(csv_io, input_name)
+    def initialize(csv_io, input_name, skip_original)
       @csv_io = csv_io
       @col_sep = col_sep
       @original_fields = nil
       @input_name = input_name
+      @skip_original = skip_original
     end
 
     def read
@@ -25,15 +26,27 @@ module GnCrossmap
     end
 
     def parse_input
-      dc = Collector.new
+      dc = Collector.new(@skip_original)
       csv = CSV.new(@csv_io, col_sep: col_sep)
       csv.each_with_index do |row, i|
-        @original_fields = row.dup if @original_fields.nil?
+        @original_fields = headers(row) if @original_fields.nil?
         i += 1
         GnCrossmap.log("Ingesting #{i}th csv row") if (i % 10_000).zero?
         dc.process_row(row)
       end && @csv_io.close
       dc.data
     end
+
+    def headers(row)
+      hdrs = row.dup
+      @skip_original ? taxon_id_header(hdrs) : hdrs
+    end
+
+    def taxon_id_header(hdrs)
+      hdrs.each do |h|
+        return [h] if h =~ /taxonid\s*$/i
+      end
+      []
+    end
   end
 end

data/lib/gn_crossmap/result_processor.rb

@@ -3,7 +3,7 @@ module GnCrossmap
   class ResultProcessor
     MATCH_TYPES = {
       0 => "No match",
-      1 => "Exact match",
+      1 => "Exact string match",
       2 => "Canonical form exact match",
       3 => "Canonical form fuzzy match",
       4 => "Partial canonical form match",
@@ -55,7 +55,7 @@ module GnCrossmap
       [matched_type(result), datum[:supplied_name_string],
        result[:name_string], result[:canonical_form],
        @input[datum[:supplied_id]][:rank], matched_rank(result),
-       synonym, result[:current_name_string],
+       synonym, result[:current_name_string] || result[:name_string],
        result[:edit_distance], result[:score], result[:taxon_id]]
     end
 

data/lib/gn_crossmap/version.rb

@@ -1,6 +1,6 @@
 # Namespace module for crossmapping checklists to GN sources
 module GnCrossmap
-  VERSION = "0.2.2".freeze
+  VERSION = "1.0.0".freeze
 
   def self.version
     VERSION

data/lib/gn_crossmap/writer.rb

@@ -4,7 +4,7 @@ module GnCrossmap
     def initialize(output_io, original_fields, output_name)
       @output_io = output_io
       @output_fields = output_fields(original_fields)
-      @output = CSV.new(@output_io)
+      @output = CSV.new(@output_io, col_sep: "\t")
       @output << @output_fields
       @output_name = output_name
       GnCrossmap.log("Open output to #{@output_name}")
@@ -25,7 +25,7 @@ module GnCrossmap
       original_fields + [:matchedType, :inputName, :matchedName,
                          :matchedCanonicalForm, :inputRank, :matchedRank,
                          :synonymStatus, :acceptedName, :matchedEditDistance,
-                         :marchedScore, :matchTaxonID]
+                         :matchedScore, :matchTaxonID]
     end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: gn_crossmap
 version: !ruby/object:Gem::Version
-  version: 0.2.2
+  version: 1.0.0
 platform: ruby
 authors:
 - Dmitry Mozzherin
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2016-11-07 00:00:00.000000000 Z
+date: 2016-11-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: trollop