lib/io_streams/tabular/header.rb in iostreams-1.7.0 vs lib/io_streams/tabular/header.rb in iostreams-1.8.0

@@ -1,9 +1,12 @@
 module IOStreams
   class Tabular
     # Process files / streams that start with a header.
     class Header
+      # Column names that begin with this prefix have been rejected and should be ignored.
+      IGNORE_PREFIX = "__rejected__".freeze
+
       attr_accessor :columns, :allowed_columns, :required_columns, :skip_unknown
 
       # Header
       #
       # Parameters
@@ -15,12 +18,12 @@
       #
       #   allowed_columns [Array<String>]
       #     List of columns to allow.
       #     Default: nil ( Allow all columns )
       #     Note:
-      #       When supplied any columns that are rejected will be returned in the cleansed columns
-      #       as nil so that they can be ignored during processing.
+      #     * So that rejected columns can be identified in subsequent steps, they will be prefixed with `__rejected__`.
+      #       For example, `Unknown Column` would be cleansed as `__rejected__Unknown Column`.
       #
       #   required_columns [Array<String>]
       #     List of columns that must be present, otherwise an Exception is raised.
       #
       #   skip_unknown [true|false]
@@ -42,23 +45,25 @@
       # - Leading and trailing whitespace is stripped.
       # - All characters converted to lower case.
       # - Spaces and '-' are converted to '_'.
       # - All characters except for letters, digits, and '_' are stripped.
       #
-      # Notes
-      # * Raises Tabular::InvalidHeader when there are no non-nil columns left after cleansing.
+      # Notes:
+      # * So that rejected columns can be identified in subsequent steps, they will be prefixed with `__rejected__`.
+      #   For example, `Unknown Column` would be cleansed as `__rejected__Unknown Column`.
+      # * Raises Tabular::InvalidHeader when there are no rejected columns left after cleansing.
       def cleanse!
         return [] if columns.nil? || columns.empty?
 
         ignored_columns = []
         self.columns    = columns.collect do |column|
           cleansed = cleanse_column(column)
           if allowed_columns.nil? || allowed_columns.include?(cleansed)
             cleansed
           else
             ignored_columns << column
-            nil
+            "#{IGNORE_PREFIX}#{column}"
           end
         end
 
         if !skip_unknown && !ignored_columns.empty?
           raise(IOStreams::Errors::InvalidHeader, "Unknown columns after cleansing: #{ignored_columns.join(',')}")
@@ -120,11 +125,11 @@
 
       private
 
       def array_to_hash(row)
         h = {}
-        columns.each_with_index { |col, i| h[col] = row[i] unless IOStreams::Utils.blank?(col) }
+        columns.each_with_index { |col, i| h[col] = row[i] unless IOStreams::Utils.blank?(col) || col.start_with?(IGNORE_PREFIX) }
         h
       end
 
       # Perform cleansing on returned Hash keys during the narrowing process.
       # For example, avoids issues with case etc.
@@ -132,15 +137,10 @@
         unmatched = columns - hash.keys
         unless unmatched.empty?
           hash = hash.dup
           unmatched.each { |name| hash[cleanse_column(name)] = hash.delete(name) }
         end
-        # Hash#slice as of Ruby 2.5
-        if hash.respond_to?(:slice)
-          hash.slice(*columns)
-        else
-          columns.each_with_object({}) { |column, new_hash| new_hash[column] = hash[column] }
-        end
+        hash.slice(*columns)
       end
 
       def cleanse_column(name)
         cleansed = name.to_s.strip.downcase
         cleansed.gsub!(/\s+/, "_")