tc211-termbase 0.1.1 → 0.1.2

data/db/version

@@ -0,0 +1 @@
+0.4.1

data/lib/tc211/termbase/relaton_db.rb

@@ -0,0 +1,21 @@
+require "singleton"
+require "relaton"
+
+module Tc211
+  module Termbase
+    # Relaton cach singleton.
+    class RelatonDb
+      include Singleton
+
+      def initialize
+        @db = Relaton::Db.new "db", nil
+      end
+
+      # @param code [String] reference
+      # @return [RelatonIso::IsoBibliongraphicItem]
+      def fetch(code)
+        @db.fetch code
+      end
+    end
+  end
+end

data/lib/tc211/termbase/terms_section.rb

@@ -1,151 +1,174 @@
 require_relative "sheet_section"
 require_relative "term"
+require_relative "relaton_db"
 
 module Tc211::Termbase
 
-class TermsSection < SheetSection
-  attr_accessor :structure
-  attr_accessor :header_row
-
-  TERM_HEADER_ROW_MATCH = {
-    "A" => ["ISO 19135 Field\nRE_RegisterItem.itemIdentifier"],
-    "B" => ["ISO 19135 Field\nRE_RegisterItem.name"],
-    "C" => ["ISO 19135 Field\nRE_RegisterItem.\nalternativeExpression"],
-    "D" => ["Country_Code"],
-    # ... We don't need to match all the cells
-  }
-
-  TERM_BODY_COLUMN_MAP = {
-    "Term_ID" => "id",
-    "Term" => "term",
-    "Term .OPERATING LANGUAGE." => "term",
-    # In the English sheet, column is named "Term Abbreviation"
-    "Term Abbreviation" => "abbrev",
-    # In other sheets, column named "Term_Abbreviation"
-    "Term_Abbreviation .OPERATING LANGUAGE." => "abbrev",
-    "Country code" => "country-code",
-    "Definition" => "definition",
-    "Term .OPERATING LANGUAGE - ALTERNATIVE CHARACTER SET." => "alt",
-    "Term in English" => nil,
-    "Entry Status" => "entry-status",
-    ## Must be one of 'notValid' 'valid' 'superseded' 'retired'
-    "Term Clasification" => "classification",
-    ## Must be one of the following 'preferred' 'admitted' 'deprecated'
-    "Review Indicator" => "review-indicator",
-    ## Must be one of the following <empty field> 'Under Review in Source Document'",
-    "Authoritative Source" => "authoritative-source",
-    "Similarity to Authoritative Source" => "authoritative-source-similarity",
-    ## Must be one of the following codes: 'identical' = 1 'restyled' = 2 'context added' = 3 'generalisation' = 4 'specialisation' = 5 'unspecified' = 6",
-    "Lineage Source" => "lineage-source",
-    "Similarity to Lineage Source" => "lineage-source-similarity",
-    ## Must be one of the following codes: 'identical' = 1 'restyled' = 2 'context added' = 3 'generalisation' = 4 'specialisation' = 5 'unspecified' = 6",
-    "Term Synonyms" => "synonyms",
-    "Date Accepted" => "date-accepted", # yyyy-mm-dd,
-    "Date Amended" => "date-amended",   # yyyy-mm-dd,
-    "Review Date" => "review-date",     # yyyy-mm-dd,
-    "Review Status" => "review-status", ## Must be one of 'pending' 'tentative' 'final'",
-    "Review Type" => "review-type",     ## Must be one of 'supersession', 'retirement'",
-    "Review Decision" => "review-decision", ## Must be one of 'withdrawn', 'accepted' 'notAccepted'",
-    "Review Decision Date" => "review-decision-date", # yyyy-mm-dd
-    "Review Decision Event" => "review-decision-event",
-    "Review Decision Notes" => "review-decision-notes",
-    "Example_1" => "example-1",
-    "Note_1" => "note-1",
-    "Example_2" => "example-2",
-    "Note_2" => "note-2",
-    "Example_3" => "example-3",
-    "Note_3" => "note-3",
-    "Example_4" => "example-4",
-    "Note_4" => "note-4",
-    "Example_5" => "example-5",
-    "Note_5" => "note-5",
-    "Example_6" => "example-6",
-    "Note_6" => "note-6",
-    "Example_7" => "example-7",
-    "Note_7" => "note-7",
-    "Example_8" => "example-8",
-    "Note_8" => "note-8",
-    "Glossary Release" => "release"
-    ## Must be one of the following codes 'release1' = 1 'release1_retired' = -1 'release2' = 2 'release2_retired' = -2 etc "
-  }
-
-  def initialize(rows, options={})
-    super
-    raise StandardError.new("Does not match TermsSection header!") unless self.class.match_header(@rows[0])
-    @mapping_rows = @rows[0..1]
-    @header_row = @rows[2]
-    @body_rows = @rows[3..-1]
-    @language_code = options.delete(:language_code)
-    self
-  end
+  class TermsSection < SheetSection
+    attr_accessor :structure
+    attr_accessor :header_row
+
+    TERM_HEADER_ROW_MATCH = {
+      "A" => ["ISO 19135 Field\nRE_RegisterItem.itemIdentifier"],
+      "B" => ["ISO 19135 Field\nRE_RegisterItem.name"],
+      "C" => ["ISO 19135 Field\nRE_RegisterItem.\nalternativeExpression"],
+      "D" => ["Country_Code"],
+      # ... We don't need to match all the cells
+    }
+
+    TERM_BODY_COLUMN_MAP = {
+      "Term_ID" => "id",
+      "Term" => "term",
+      "Term .OPERATING LANGUAGE." => "term",
+      # In the English sheet, column is named "Term Abbreviation"
+      "Term Abbreviation" => "abbrev",
+      # In other sheets, column named "Term_Abbreviation"
+      "Term_Abbreviation .OPERATING LANGUAGE." => "abbrev",
+      "Country code" => "country-code",
+      "Definition" => "definition",
+      "Term .OPERATING LANGUAGE - ALTERNATIVE CHARACTER SET." => "alt",
+      "Term in English" => nil,
+      "Entry Status" => "entry-status",
+      ## Must be one of 'notValid' 'valid' 'superseded' 'retired'
+      "Term Clasification" => "classification",
+      ## Must be one of the following 'preferred' 'admitted' 'deprecated'
+      "Review Indicator" => "review-indicator",
+      ## Must be one of the following <empty field> 'Under Review in Source Document'",
+      "Authoritative Source" => "authoritative-source",
+      "Similarity to Authoritative Source" => "authoritative-source-similarity",
+      ## Must be one of the following codes: 'identical' = 1 'restyled' = 2 'context added' = 3 'generalisation' = 4 'specialisation' = 5 'unspecified' = 6",
+      "Lineage Source" => "lineage-source",
+      "Similarity to Lineage Source" => "lineage-source-similarity",
+      ## Must be one of the following codes: 'identical' = 1 'restyled' = 2 'context added' = 3 'generalisation' = 4 'specialisation' = 5 'unspecified' = 6",
+      "Term Synonyms" => "synonyms",
+      "Date Accepted" => "date-accepted", # yyyy-mm-dd,
+      "Date Amended" => "date-amended",   # yyyy-mm-dd,
+      "Review Date" => "review-date",     # yyyy-mm-dd,
+      "Review Status" => "review-status", ## Must be one of 'pending' 'tentative' 'final'",
+      "Review Type" => "review-type",     ## Must be one of 'supersession', 'retirement'",
+      "Review Decision" => "review-decision", ## Must be one of 'withdrawn', 'accepted' 'notAccepted'",
+      "Review Decision Date" => "review-decision-date", # yyyy-mm-dd
+      "Review Decision Event" => "review-decision-event",
+      "Review Decision Notes" => "review-decision-notes",
+      "Example_1" => "example-1",
+      "Note_1" => "note-1",
+      "Example_2" => "example-2",
+      "Note_2" => "note-2",
+      "Example_3" => "example-3",
+      "Note_3" => "note-3",
+      "Example_4" => "example-4",
+      "Note_4" => "note-4",
+      "Example_5" => "example-5",
+      "Note_5" => "note-5",
+      "Example_6" => "example-6",
+      "Note_6" => "note-6",
+      "Example_7" => "example-7",
+      "Note_7" => "note-7",
+      "Example_8" => "example-8",
+      "Note_8" => "note-8",
+      "Glossary Release" => "release"
+      ## Must be one of the following codes 'release1' = 1 'release1_retired' = -1 'release2' = 2 'release2_retired' = -2 etc "
+    }
+
+    def initialize(rows, options={})
+      super
+      raise StandardError.new("Does not match TermsSection header!") unless self.class.match_header(@rows[0])
+      @mapping_rows = @rows[0..1]
+      @header_row = @rows[2]
+      @body_rows = @rows[3..-1]
+      @language_code = options.delete(:language_code)
+      self
+    end
+
+    def structure
+      @structure ||= @header_row.inject({}) do |acc, (key, value)|
+        # puts "#{key}, #{value}, #{GLOSSARY_HEADER_TITLES[value]}"
 
-  def structure
-    @structure ||= @header_row.inject({}) do |acc, (key, value)|
-      # puts "#{key}, #{value}, #{GLOSSARY_HEADER_TITLES[value]}"
+        # convert whitespace to a single space
+        cleaned_value = value.gsub(/\s+/, ' ')
 
-      # convert whitespace to a single space
-      cleaned_value = value.gsub(/\s+/, ' ')
+        matches = TERM_BODY_COLUMN_MAP.map do |key, value|
+          # puts "key #{key}, value #{value}"
+          if cleaned_value[Regexp.new("^#{key}")]
+            [key, value]
+          end
+        end.compact
 
-      matches = TERM_BODY_COLUMN_MAP.map do |key, value|
-        # puts "key #{key}, value #{value}"
-        if cleaned_value[Regexp.new("^#{key}")]
-          [key, value]
+        discard, longest_match_key = matches.max_by do |(a, b)|
+          a.length
         end
-      end.compact
 
-      discard, longest_match_key = matches.max_by do |(a, b)|
-        a.length
-      end
+        # Here we need to skip "Term in English"
+        if key && longest_match_key
+          acc.merge!({ key => longest_match_key })
+        else
+          acc
+        end
 
-      # Here we need to skip "Term in English"
-      if key && longest_match_key
-        acc.merge!({ key => longest_match_key })
-      else
-        acc
       end
-
     end
-  end
 
-  def self.match_header(row)
-    # puts "row #{row}"
-    row.inject(true) do |acc, (key, value)|
-      # puts "#{key}, #{value}"
-      if TERM_HEADER_ROW_MATCH[key]
-        acc && TERM_HEADER_ROW_MATCH[key].include?(value)
-      else
-        acc
+    def self.match_header(row)
+      # puts "row #{row}"
+      row.inject(true) do |acc, (key, value)|
+        # puts "#{key}, #{value}"
+        if TERM_HEADER_ROW_MATCH[key]
+          acc && TERM_HEADER_ROW_MATCH[key].include?(value)
+        else
+          acc
+        end
       end
     end
-  end
 
-  def parse_row(row)
-    return nil if row.empty?
-    attributes = {}
+    def parse_row(row)
+      return nil if row.empty?
 
-    structure.each_pair do |key, value|
-      # puts "#{key}, #{value}, #{row[key]}"
-      attribute_key = value
-      attribute_value = row[key]
-      next if attribute_value.nil?
-      attributes[attribute_key] = attribute_value
-    end
+      attributes = {}
 
-    attributes
-  end
+      structure.each_pair do |key, value|
+        # puts "#{key}, #{value}, #{row[key]}"
+        attribute_key = value
+        next if row[key].nil?
+
+        attribute_value = fetch_attribute row[key], attribute_key
+        attributes[attribute_key] = attribute_value
+      end
 
-  def terms
-    @terms ||= @body_rows.map do |row|
-      Term.new(parse_row(row).merge("language_code" => @language_code))
+      attributes
     end
-  end
 
-  def to_hash
-    {
-      "terms" => terms.map(&:to_hash)
-    }
-  end
+    def terms
+      @terms ||= @body_rows.map do |row|
+        Term.new(parse_row(row).merge("language_code" => @language_code))
+      end
+    end
 
-end
+    def to_hash
+      {
+        "terms" => terms.map(&:to_hash)
+      }
+    end
 
+    private
+
+    # @param value [String]
+    # @param key [String]
+    # @return [Hash]
+    def fetch_attribute(value, key)
+      case key
+      when "authoritative-source"
+        begin
+          src = { "ref" => value }
+          item = RelatonDb.instance.fetch value
+          src["link"] = item.url if item
+          src
+        rescue RelatonBib::RequestError => e
+          warn e.message
+          src
+        end
+      else
+        value
+      end
+    end
+  end
 end

data/lib/tc211/termbase/version.rb

@@ -1,5 +1,5 @@
 module Tc211
   module Termbase
-    VERSION = "0.1.1"
+    VERSION = "0.1.2"
   end
 end

data/tc211-termbase.gemspec

@@ -24,8 +24,11 @@ Gem::Specification.new do |spec|
 
   spec.add_runtime_dependency "iso-639"
   spec.add_runtime_dependency "creek"
+  spec.add_runtime_dependency "relaton", "~>0.4.0"
 
-  spec.add_development_dependency "bundler", "~> 1.17"
+  spec.add_development_dependency "bundler", "~> 2.0.1"
+  spec.add_development_dependency "debase"
   spec.add_development_dependency "rake", "~> 10.0"
   spec.add_development_dependency "rspec", "~> 3.0"
+  spec.add_development_dependency "ruby-debug-ide"
 end