README.rdoc in dwc-archive-0.5.13 vs README.rdoc in dwc-archive-0.5.14

@@ -23,11 +23,11 @@
     dwc.extensions[0].data # summary for an extension
 
     # read content of the core data file into memory or used with a block
     # it returns array of arrays of data
     # rows that had a wrong encoding will be collected into errors array
-    data, errors = dwc.core.read 
+    data, errors = dwc.core.read
 
     # read content using a block with getting back results in sets 100 rows each
     results = []
     tail_data, tail_errors = dwc.core.read(100) do |data, errors|
       results << [data, errors]
@@ -43,22 +43,38 @@
       results << [data, errors]
     end
     results << [tail_data, tail_errors]
 
     # normalize names in classification collecting together synonyms, canonical names,
-    # vernacular names and associating paths to taxons in a classification 
+    # vernacular names and associating paths to taxons in a classification
     # distributed as DwCA file
     # NOTE: this functionality requires biodiversity gem for ruby 1.8.x and
     # biodiversity19 gem for ruby 1.9.x
 
     result = dwc.normalize_classification
 
+    # for a finer control over normalization:
 
+    cn = DarwinCore::ClassificationNormalizer.new(dwc)
+    cn.normalize
+
+    # to get a flat hash of nodes with attached vernacular names and synonyms
+    normalized_data = cn.normalized_data
+
+    # to get a representation of tree organization as a hash
+    classification_tree = cn.tree
+
+    # to get list of all name strings used as scientific or vernacular names
+    all_name_strings = cn.name_strings
+
+    # to get list of errors generated during the normalization
+    errors = cn.error_names
+
     DarwinCore.clean_all   # remove all expanded archives
 
 == Creating a DarwinCore Archive file
-    
+
     gen = DarwinCore::Generator.new('/tmp/dwc_birches.tar.gz')
 
     core = [
       ["http://rs.tdwg.org/dwc/terms/taxonID", "http://rs.tdwg.org/dwc/terms/parentNameUsageID", "http://rs.tdwg.org/dwc/terms/scientificName", "http://rs.tdwg.org/dwc/terms/taxonRank"],
       [1, 0, "Plantae", "kingdom"],
@@ -75,11 +91,11 @@
       [3, "Wheeping Birch"],
       [3, "Береза плакучая"]
     ]
 
     synonyms = [
-      ["http://rs.tdwg.org/dwc/terms/TaxonID", "http://rs.tdwg.org/dwc/terms/scientificName", "http://rs.tdwg.org/dwc/terms/taxonomicStatus"], 
+      ["http://rs.tdwg.org/dwc/terms/TaxonID", "http://rs.tdwg.org/dwc/terms/scientificName", "http://rs.tdwg.org/dwc/terms/taxonomicStatus"],
       [1, "Betila Linnaeus, 1753", 'misspelling']
     ]
 
     eml = {
       :id => '1234',
@@ -87,11 +103,11 @@
       :authors => [
         { :first_name => 'John',
           :last_name => 'Doe',
           :email => '[e-mail]' },
           { :first_name => 'Jane',
-            :last_name => 'Doe', 
+            :last_name => 'Doe',
             :email => '[e-mail]' }
     ],
       :abstract => 'test classification',
       :citation => 'Test classification: Doe John, Doe Jane, Taxnonmy, 10, 1, 2010',
       :url => 'http://example.com'
@@ -104,10 +120,10 @@
     gen.add_eml_xml(eml)
     gen.pack
 
 
 == Note on Patches/Pull Requests
- 
+
 * Fork the project.
 * Make your feature addition or bug fix.
 * Add tests for it. This is important so I don't break it in a
   future version unintentionally.
 * Commit, do not mess with rakefile, version, or history.