fastercsv 1.0.0 → 1.1.0

data/CHANGELOG

@@ -2,6 +2,15 @@
 
 Below is a complete listing of changes for each revision of FasterCSV.
 
+== 1.1.0
+
+* Added empty?(), length(), and size() methods to FasterCSV::Row and
+  FasterCSV::Table.
+* Cleaned up bug fix regression tests.
+* Fixed bug causing Arrays to be returned for blank rows when header processing
+  is active.
+* Added a <tt>:skip_blanks</tt> option for ignoring empty rows.
+
 == 1.0.0
 
 * Fixed FasterCSV.rewind() to reset the FasterCSV.lineno() counter.

data/TODO

@@ -3,4 +3,4 @@
 The following is a list of planned expansions for FasterCSV, in no particular
 order.
 
-  * Rent this space!
+  * Rent this space...

data/examples/csv_converters.rb

@@ -0,0 +1,28 @@
+#!/usr/local/bin/ruby -w
+
+# csv_converters.rb
+#
+#  Created by James Edward Gray II on 2006-11-05.
+#  Copyright 2006 Gray Productions. All rights reserved.
+
+require "faster_csv"
+
+# convert a specific column
+options = {
+  :headers           => true,
+  :header_converters => :symbol,
+  :converters        => [
+    lambda { |f, info| info.index.zero?       ? f.to_i : f },
+    lambda { |f, info| info.header == :floats ? f.to_f : f }
+  ]
+}
+table = FCSV(DATA, options) { |csv| csv.read }
+
+table[:ints]    # => [1, 2, 3]
+table[:floats]  # => [1.0, 2.0, 3.0]
+
+__END__
+ints,floats
+1,1.000
+2,2
+3,3.0

data/lib/faster_csv.rb

@@ -75,7 +75,7 @@ require "stringio"
 # 
 class FasterCSV
   # The version of the installed library.
-  VERSION = "1.0.0".freeze
+  VERSION = "1.1.0".freeze
   
   # 
   # A FasterCSV::Row is part Array and part Hash.  It retains an order for the
@@ -95,6 +95,13 @@ class FasterCSV
     # FasterCSV::Row.header_row?() and FasterCSV::Row.field_row?(), that this is
     # a header row.  Otherwise, the row is assumes to be a field row.
     # 
+    # A FasterCSV::Row object supports the following Array methods through
+    # delegation:
+    # 
+    # * empty?()
+    # * length()
+    # * size()
+    # 
     def initialize(headers, fields, header_row = false)
       @header_row = header_row
       
@@ -109,6 +116,11 @@ class FasterCSV
     # Internal data format used to compare equality.
     attr_reader :row
     protected   :row
+
+    ### Array Delegation ###
+
+    extend Forwardable
+    def_delegators :@row, :empty?, :length, :size
     
     # Returns +true+ if this is a header row.
     def header_row?
@@ -367,6 +379,13 @@ class FasterCSV
     # to be FasterCSV::Row objects.  All rows are assumed to have the same 
     # headers.
     # 
+    # A FasterCSV::Table object supports the following Array methods through
+    # delegation:
+    # 
+    # * empty?()
+    # * length()
+    # * size()
+    # 
     def initialize(array_of_rows)
       @table = array_of_rows
       @mode  = :col_or_row
@@ -378,6 +397,11 @@ class FasterCSV
     # Internal data format used to compare equality.
     attr_reader :table
     protected   :table
+
+    ### Array Delegation ###
+
+    extend Forwardable
+    def_delegators :@table, :empty?, :length, :size
     
     # 
     # Returns a duplicate table object, in column mode.  This is handy for 
@@ -749,6 +773,7 @@ class FasterCSV
   # <b><tt>:headers</tt></b>::            +false+
   # <b><tt>:return_headers</tt></b>::     +false+
   # <b><tt>:header_converters</tt></b>::  +nil+
+  # <b><tt>:skip_blanks</tt></b>::        +false+
   # 
   DEFAULT_OPTIONS = { :col_sep            => ",",
                       :row_sep            => :auto,
@@ -756,7 +781,8 @@ class FasterCSV
                       :unconverted_fields => nil,
                       :headers            => false,
                       :return_headers     => false,
-                      :header_converters  => nil }.freeze
+                      :header_converters  => nil,
+                      :skip_blanks        => false }.freeze
   
   # 
   # This method will build a drop-in replacement for many of the standard CSV
@@ -1263,6 +1289,9 @@ class FasterCSV
   #                                       <tt>:converters</tt> save that the
   #                                       conversions are only made to header
   #                                       rows.
+  # <b><tt>:skip_blanks</tt></b>::        When set to a +true+ value, FasterCSV
+  #                                       will skip over any rows with no
+  #                                       content.
   # 
   # See FasterCSV::DEFAULT_OPTIONS for the default settings.
   # 
@@ -1289,14 +1318,14 @@ class FasterCSV
     @lineno = 0
   end
   
-  ### IO and StringIO Delegation ###
-  
   # 
   # The line number of the last row read from this file.  Fields with nested 
   # line-end characters will not affect this count.
   # 
   attr_reader :lineno
   
+  ### IO and StringIO Delegation ###
+  
   extend Forwardable
   def_delegators :@io, :binmode, :close, :close_read, :close_write, :closed?,
                        :eof, :eof?, :fcntl, :fileno, :flush, :fsync, :ioctl,
@@ -1432,11 +1461,11 @@ class FasterCSV
     # handle headers not based on document content
     if header_row? and @return_headers and
        [Array, String].include? @use_headers.class
-       if @unconverted_fields
-         return add_unconverted_fields(parse_headers, Array.new)
-       else
-         return parse_headers
-       end
+      if @unconverted_fields
+        return add_unconverted_fields(parse_headers, Array.new)
+      else
+        return parse_headers
+      end
     end
     
     # begin with a blank line, so we can always add to it
@@ -1459,8 +1488,13 @@ class FasterCSV
       # 
       if parse.empty?
         @lineno += 1
-        if @unconverted_fields
+        if @skip_blanks
+          line = ""
+          next
+        elsif @unconverted_fields
           return add_unconverted_fields(Array.new, Array.new)
+        elsif @use_headers
+          return FasterCSV::Row.new(Array.new, Array.new)
         else
           return Array.new
         end
@@ -1581,6 +1615,9 @@ class FasterCSV
   
   # Pre-compiles parsers and stores them by name for access during reads.
   def init_parsers(options)
+    # store the parser behaviors
+    @skip_blanks = options.delete(:skip_blanks)
+    
     # prebuild Regexps for faster parsing
     @parsers    = {
       :leading_fields =>

data/test/tc_features.rb

@@ -98,23 +98,37 @@ class TestFasterCSVFeatures < Test::Unit::TestCase
     end
   end
   
-  def test_bug_fixes
-    # failing to escape <tt>:col_sep</tt> (reported by Kev Jackson)
+  def test_skip_blanks
+    assert_equal(4, @csv.to_a.size)
+
+    @csv  = FasterCSV.new(@sample_data, :skip_blanks => true)
+    
+    count = 0
+    @csv.each do |row|
+      count += 1
+      assert_equal("line", row.first)
+    end
+    assert_equal(3, count)
+  end
+  
+  # reported by Kev Jackson
+  def test_failing_to_escape_col_sep_bug_fix
     assert_nothing_raised(Exception) do 
       FasterCSV.new(String.new, :col_sep => "|")
     end
-    
-    # failing to reset header behavior on rewind() (reported by Chris Roos)
+  end
+  
+  # reported by Chris Roos
+  def test_failing_to_reset_headers_in_rewind_bug_fix
     csv = FasterCSV.new( "forename,surname", :headers        => true,
                                              :return_headers => true )
     csv.each { |row| assert row.header_row? }
     csv.rewind
     csv.each { |row| assert row.header_row? }
-    
-    # 
-    # leading empty fields with multibyte col_sep raises MalformedCSVError
-    # (reported by Dave Burt)
-    # 
+  end
+  
+  # reported by Dave Burt
+  def test_leading_empty_fields_with_multibyte_col_sep_bug_fix
     data = <<-END_DATA.gsub(/^\s+/, "")
     <=><=>A<=>B<=>C
     1<=>2<=>3

data/test/tc_headers.rb

@@ -224,4 +224,39 @@ class TestFasterCSVHeaders < Test::Unit::TestCase
     
     assert_instance_of(FasterCSV::Table, csv)
   end
+  
+  def test_skip_blanks
+    @data = <<-END_CSV.gsub(/^ +/, "")
+    
+
+    A,B,C
+    
+    1,2,3
+    
+    
+    
+    END_CSV
+    
+    expected = [%w[1 2 3]]
+    FasterCSV.parse(@data, :headers => true, :skip_blanks => true) do |row|
+      assert_equal(expected.shift, row.fields)
+    end
+    
+    expected = [%w[A B C], %w[1 2 3]]
+    FasterCSV.parse( @data,
+                     :headers        => true,
+                     :return_headers => true, 
+                     :skip_blanks    => true ) do |row|
+      assert_equal(expected.shift, row.fields)
+    end
+  end
+  
+  def test_blank_row_bug_fix
+    @data += "\n#{@data}"  # add a blank row
+    
+    # ensure that everything returned is a Row object
+    FasterCSV.parse(@data, :headers => true) do |row|
+      assert_instance_of(FasterCSV::Row, row)
+    end
+  end
 end

data/test/tc_row.rb

@@ -279,4 +279,10 @@ class TestFasterCSVRow < Test::Unit::TestCase
     assert_equal( "1|2|3|4|\r\n",
                   @row.to_csv(:col_sep => "|", :row_sep => "\r\n") )
   end
+  
+  def test_array_delegation
+    assert(!@row.empty?, "Row was empty.")
+    
+    assert_equal([@row.headers.size, @row.fields.size].max, @row.size)
+  end
 end

data/test/tc_table.rb

@@ -382,4 +382,10 @@ class TestFasterCSVTable < Test::Unit::TestCase
     assert_equal([[1, 3], [4, 6], [7, 9]], @table.by_col.values_at(0, 2))
     assert_equal(@rows.values_at(0, 2), @table.values_at(0, 2))
   end
+  
+  def test_array_delegation
+    assert(!@table.empty?, "Table was empty.")
+    
+    assert_equal(@rows.size, @table.size)
+  end
 end

metadata

@@ -3,8 +3,8 @@ rubygems_version: 0.8.11
 specification_version: 1
 name: fastercsv
 version: !ruby/object:Gem::Version 
-  version: 1.0.0
-date: 2006-11-05 00:00:00 -06:00
+  version: 1.1.0
+date: 2006-12-12 00:00:00 -06:00
 summary: FasterCSV is CSV, but faster, smaller, and cleaner.
 require_paths: 
 - lib
@@ -41,6 +41,7 @@ files:
 - test/tc_speed.rb
 - test/tc_table.rb
 - test/ts_all.rb
+- examples/csv_converters.rb
 - examples/csv_filter.rb
 - examples/csv_reading.rb
 - examples/csv_table.rb