Alias filter operations to their Cascading equivalents, but prefer ve…

…rbs to nouns for operations

lib/cascading/assembly.rb

@@ -27,6 +27,11 @@ module Cascading
   # [input] c.p.Each argument selector
   # [into] c.o.Operation field declaration
   # [output] c.p.Each output selector
+  #
+  # A note on aliases: when a DSL method uniquely wraps a single Cascading
+  # operation, we attempt to provide an alias that matches the Cascading
+  # operation.  However, Cascading operations are often nouns rather than verbs,
+  # and the latter are preferable for a dataflow DSL.
   class Assembly < Cascading::Node
     attr_reader :head_pipe, :tail_pipe
 

lib/cascading/filter_operations.rb

@@ -27,15 +27,16 @@ module FilterOperations
     #
     # Example:
     #     filter :input => 'field1', :regex => /\t/, :remove_match => true
-    #     filter :expression => 'field1:long > 0 && "".equals(field2:string)', :remove_match => true
+    #     filter :expression => 'field1:long > 0 && "".equals(field2:string)'
     def filter(options = {})
       input_fields = options[:input] || all_fields
       expression = options[:expression]
       regex = options[:regex]
-      validate = options.has_key?(:validate) ? options[:validate] : true
-      validate_with = options[:validate_with] || {}
 
       if expression
+        validate = options.has_key?(:validate) ? options[:validate] : true
+        validate_with = options[:validate_with] || {}
+
         stub = expr(expression, { :validate => validate, :validate_with => validate_with })
         stub.validate_scope(scope)
 

lib/cascading/regex_operations.rb

@@ -41,6 +41,7 @@ def parse(input_field, regex, into_fields, options = {})
         :output => output
       )
     end
+    alias regex_parser parse
 
     # Splits the given input_field into multiple fields using the specified
     # regular expression.
@@ -59,6 +60,7 @@ def split(input_field, regex, into_fields, options = {})
         :output => output
       )
     end
+    alias regex_splitter split
 
     # Splits the given input_field into new rows using the specified regular
     # expression.
@@ -79,6 +81,7 @@ def split_rows(input_field, regex, into_field, options = {})
         :output => output
       )
     end
+    alias regex_split_generator split_rows
 
     # Emits a new row for each regex group matched in input_field using the
     # specified regular expression.
@@ -99,6 +102,7 @@ def match_rows(input_field, regex, into_field, options = {})
         :output => output
       )
     end
+    alias regex_generator match_rows
 
     # Performs a query/replace on the given input_field using the specified
     # regular expression and replacement.
@@ -124,5 +128,6 @@ def replace(input_field, regex, into_field, replacement, options = {})
         :output => output
       )
     end
+    alias regex_replace replace
   end
 end