fastercsv 0.1.0

data/test/tc_csv_parsing.rb

@@ -0,0 +1,121 @@
+#!/usr/local/bin/ruby -w
+
+# tc_csv_parsing.rb
+#
+#  Created by James Edward Gray II on 2005-10-31.
+#  Copyright 2005 Gray Productions. All rights reserved.
+
+require "test/unit"
+
+require "faster_csv"
+
+# 
+# Following tests are my interpretation of the 
+# {CSV RCF}[http://www.ietf.org/rfc/rfc4180.txt].  I only deviate from that 
+# document in one place (intentionally) and that is to make the default row
+# separator <tt>$/</tt>.
+# 
+class TestCSVParsing < Test::Unit::TestCase
+  def test_mastering_regex_example
+    ex = %Q{Ten Thousand,10000, 2710 ,,"10,000","It's ""10 Grand"", baby",10K}
+    assert_equal( [ "Ten Thousand", "10000", " 2710 ", nil, "10,000",
+                    "It's \"10 Grand\", baby", "10K" ],
+                  FasterCSV.parse_line(ex) )
+  end
+  
+  # Pulled from:  http://www.ruby-lang.org/cgi-bin/cvsweb.cgi/ruby/test/csv/test_csv.rb?rev=1.12.2.2;content-type=text%2Fplain
+  def test_std_lib_csv
+    [ ["\t", ["\t"]],
+      ["foo,\"\"\"\"\"\",baz", ["foo", "\"\"", "baz"]],
+      ["foo,\"\"\"bar\"\"\",baz", ["foo", "\"bar\"", "baz"]],
+      ["\"\"\"\n\",\"\"\"\n\"", ["\"\n", "\"\n"]],
+      ["foo,\"\r\n\",baz", ["foo", "\r\n", "baz"]],
+      ["\"\"", [""]],
+      ["foo,\"\"\"\",baz", ["foo", "\"", "baz"]],
+      ["foo,\"\r.\n\",baz", ["foo", "\r.\n", "baz"]],
+      ["foo,\"\r\",baz", ["foo", "\r", "baz"]],
+      ["foo,\"\",baz", ["foo", "", "baz"]],
+      ["\",\"", [","]],
+      ["foo", ["foo"]],
+      [",,", [nil, nil, nil]],
+      [",", [nil, nil]],
+      ["foo,\"\n\",baz", ["foo", "\n", "baz"]],
+      ["foo,,baz", ["foo", nil, "baz"]],
+      ["\"\"\"\r\",\"\"\"\r\"", ["\"\r", "\"\r"]],
+      ["\",\",\",\"", [",", ","]],
+      ["foo,bar,", ["foo", "bar", nil]],
+      [",foo,bar", [nil, "foo", "bar"]],
+      ["foo,bar", ["foo", "bar"]],
+      [";", [";"]],
+      ["\t,\t", ["\t", "\t"]],
+      ["foo,\"\r\n\r\",baz", ["foo", "\r\n\r", "baz"]],
+      ["foo,\"\r\n\n\",baz", ["foo", "\r\n\n", "baz"]],
+      ["foo,\"foo,bar\",baz", ["foo", "foo,bar", "baz"]],
+      [";,;", [";", ";"]] ].each do |csv_test|
+      assert_equal(csv_test.last, FasterCSV.parse_line(csv_test.first))
+    end
+
+    [ ["foo,\"\"\"\"\"\",baz", ["foo", "\"\"", "baz"]],
+      ["foo,\"\"\"bar\"\"\",baz", ["foo", "\"bar\"", "baz"]],
+      ["foo,\"\r\n\",baz", ["foo", "\r\n", "baz"]],
+      ["\"\"", [""]],
+      ["foo,\"\"\"\",baz", ["foo", "\"", "baz"]],
+      ["foo,\"\r.\n\",baz", ["foo", "\r.\n", "baz"]],
+      ["foo,\"\r\",baz", ["foo", "\r", "baz"]],
+      ["foo,\"\",baz", ["foo", "", "baz"]],
+      ["foo", ["foo"]],
+      [",,", [nil, nil, nil]],
+      [",", [nil, nil]],
+      ["foo,\"\n\",baz", ["foo", "\n", "baz"]],
+      ["foo,,baz", ["foo", nil, "baz"]],
+      ["foo,bar", ["foo", "bar"]],
+      ["foo,\"\r\n\n\",baz", ["foo", "\r\n\n", "baz"]],
+      ["foo,\"foo,bar\",baz", ["foo", "foo,bar", "baz"]] ].each do |csv_test|
+      assert_equal(csv_test.last, FasterCSV.parse_line(csv_test.first))
+    end
+  end
+  
+  # From:  http://ruby-talk.org/cgi-bin/scat.rb/ruby/ruby-core/6496
+  def test_aras_edge_cases
+    [ [%Q{a,b},               ["a", "b"]],
+      [%Q{a,"""b"""},         ["a", "\"b\""]],
+      [%Q{a,"""b"},           ["a", "\"b"]],
+      [%Q{a,"b"""},           ["a", "b\""]],
+      [%Q{a,"\nb"""},         ["a", "\nb\""]],
+      [%Q{a,"""\nb"},         ["a", "\"\nb"]],
+      [%Q{a,"""\nb\n"""},     ["a", "\"\nb\n\""]],
+      [%Q{a,"""\nb\n""",\nc}, ["a", "\"\nb\n\"", nil]],
+      [%Q{a,,,},              ["a", nil, nil, nil]],
+      [%Q{,},                 [nil, nil]],
+      [%Q{"",""},             ["", ""]],
+      [%Q{""""},              ["\""]],
+      [%Q{"""",""},           ["\"",""]],
+      [%Q{,""},               [nil,""]],
+      [%Q{,"\r"},             [nil,"\r"]],
+      [%Q{"\r\n,"},           ["\r\n,"]],
+      [%Q{"\r\n,",},          ["\r\n,", nil]] ].each do |edge_case|
+        assert_equal(edge_case.last, FasterCSV.parse_line(edge_case.first))
+      end
+  end
+  
+  def test_james_edge_cases
+    # A read at eof? should return nil.
+    assert_equal(nil, FasterCSV.parse_line(""))
+    # 
+    # With CSV it's impossible to tell an empty line from a line containing a
+    # single +nil+ field.  The standard CSV library returns <tt>[nil]</tt>
+    # in these cases, but <tt>Array.new</tt> makes more sense to me.
+    # 
+    assert_equal(Array.new, FasterCSV.parse_line("\n1,2,3\n"))
+  end
+  
+  def test_malformed_csv
+    assert_raise(FasterCSV::MalformedCSVError) do 
+      FasterCSV.parse_line("1,2\r,3")
+    end
+
+    assert_raise(FasterCSV::MalformedCSVError) do 
+      FasterCSV.parse_line('1,2,"3...')
+    end
+  end
+end

data/test/tc_csv_writing.rb

@@ -0,0 +1,90 @@
+#!/usr/local/bin/ruby -w
+
+# tc_csv_writing.rb
+#
+#  Created by James Edward Gray II on 2005-11-14.
+#  Copyright 2005 Gray Productions. All rights reserved.
+
+require "test/unit"
+
+require "faster_csv"
+
+class TestFasterCSVWriting < Test::Unit::TestCase
+  def test_writing
+    [ ["\t",                      ["\t"]],
+      ["foo,\"\"\"\"\"\",baz",    ["foo", "\"\"", "baz"]],
+      ["foo,\"\"\"bar\"\"\",baz", ["foo", "\"bar\"", "baz"]],
+      ["\"\"\"\n\",\"\"\"\n\"",   ["\"\n", "\"\n"]],
+      ["foo,\"\r\n\",baz",        ["foo", "\r\n", "baz"]],
+      ["\"\"",                    [""]],
+      ["foo,\"\"\"\",baz",        ["foo", "\"", "baz"]],
+      ["foo,\"\r.\n\",baz",       ["foo", "\r.\n", "baz"]],
+      ["foo,\"\r\",baz",          ["foo", "\r", "baz"]],
+      ["foo,\"\",baz",            ["foo", "", "baz"]],
+      ["\",\"",                   [","]],
+      ["foo",                     ["foo"]],
+      [",,",                      [nil, nil, nil]],
+      [",",                       [nil, nil]],
+      ["foo,\"\n\",baz",          ["foo", "\n", "baz"]],
+      ["foo,,baz",                ["foo", nil, "baz"]],
+      ["\"\"\"\r\",\"\"\"\r\"",   ["\"\r", "\"\r"]],
+      ["\",\",\",\"",             [",", ","]],
+      ["foo,bar,",                ["foo", "bar", nil]],
+      [",foo,bar",                [nil, "foo", "bar"]],
+      ["foo,bar",                 ["foo", "bar"]],
+      [";",                       [";"]],
+      ["\t,\t",                   ["\t", "\t"]],
+      ["foo,\"\r\n\r\",baz",      ["foo", "\r\n\r", "baz"]],
+      ["foo,\"\r\n\n\",baz",      ["foo", "\r\n\n", "baz"]],
+      ["foo,\"foo,bar\",baz",     ["foo", "foo,bar", "baz"]],
+      [";,;",                     [";", ";"]],
+      ["foo,\"\"\"\"\"\",baz",    ["foo", "\"\"", "baz"]],
+      ["foo,\"\"\"bar\"\"\",baz", ["foo", "\"bar\"", "baz"]],
+      ["foo,\"\r\n\",baz",        ["foo", "\r\n", "baz"]],
+      ["\"\"",                    [""]],
+      ["foo,\"\"\"\",baz",        ["foo", "\"", "baz"]],
+      ["foo,\"\r.\n\",baz",       ["foo", "\r.\n", "baz"]],
+      ["foo,\"\r\",baz",          ["foo", "\r", "baz"]],
+      ["foo,\"\",baz",            ["foo", "", "baz"]],
+      ["foo",                     ["foo"]],
+      [",,",                      [nil, nil, nil]],
+      [",",                       [nil, nil]],
+      ["foo,\"\n\",baz",          ["foo", "\n", "baz"]],
+      ["foo,,baz",                ["foo", nil, "baz"]],
+      ["foo,bar",                 ["foo", "bar"]],
+      ["foo,\"\r\n\n\",baz",      ["foo", "\r\n\n", "baz"]],
+      ["foo,\"foo,bar\",baz",     ["foo", "foo,bar", "baz"]],
+      [%Q{a,b},                   ["a", "b"]],
+      [%Q{a,"""b"""},             ["a", "\"b\""]],
+      [%Q{a,"""b"},               ["a", "\"b"]],
+      [%Q{a,"b"""},               ["a", "b\""]],
+      [%Q{a,"\nb"""},             ["a", "\nb\""]],
+      [%Q{a,"""\nb"},             ["a", "\"\nb"]],
+      [%Q{a,"""\nb\n"""},         ["a", "\"\nb\n\""]],
+      [%Q{a,"""\nb\n""",},        ["a", "\"\nb\n\"", nil]],
+      [%Q{a,,,},                  ["a", nil, nil, nil]],
+      [%Q{,},                     [nil, nil]],
+      [%Q{"",""},                 ["", ""]],
+      [%Q{""""},                  ["\""]],
+      [%Q{"""",""},               ["\"",""]],
+      [%Q{,""},                   [nil,""]],
+      [%Q{,"\r"},                 [nil,"\r"]],
+      [%Q{"\r\n,"},               ["\r\n,"]],
+      [%Q{"\r\n,",},              ["\r\n,", nil]] ].each do |test_case|
+        assert_equal( test_case.first + $/,
+                      FasterCSV.generate_line(test_case.last) )
+      end
+  end
+  
+  def test_col_sep
+    assert_equal( "a;b;;c\n", FasterCSV.generate_line( ["a", "b", nil, "c"],
+                                                       :col_sep => ";" ) )
+    assert_equal( "a\tb\t\tc\n", FasterCSV.generate_line( ["a", "b", nil, "c"],
+                                                          :col_sep => "\t" ) )
+  end
+  
+  def test_row_sep
+    assert_equal( "a,b,,c\r\n", FasterCSV.generate_line( ["a", "b", nil, "c"],
+                                                         :row_sep => "\r\n" ) )
+  end
+end

data/test/tc_features.rb

@@ -0,0 +1,51 @@
+#!/usr/local/bin/ruby -w
+
+# tc_features.rb
+#
+#  Created by James Edward Gray II on 2005-11-14.
+#  Copyright 2005 Gray Productions. All rights reserved.
+
+require "test/unit"
+
+require "faster_csv"
+
+class TestFasterCSVFeatures < Test::Unit::TestCase
+  TEST_CASES = [ [%Q{a,b},               ["a", "b"]],
+                 [%Q{a,"""b"""},         ["a", "\"b\""]],
+                 [%Q{a,"""b"},           ["a", "\"b"]],
+                 [%Q{a,"b"""},           ["a", "b\""]],
+                 [%Q{a,"\nb"""},         ["a", "\nb\""]],
+                 [%Q{a,"""\nb"},         ["a", "\"\nb"]],
+                 [%Q{a,"""\nb\n"""},     ["a", "\"\nb\n\""]],
+                 [%Q{a,"""\nb\n""",\nc}, ["a", "\"\nb\n\"", nil]],
+                 [%Q{a,,,},              ["a", nil, nil, nil]],
+                 [%Q{,},                 [nil, nil]],
+                 [%Q{"",""},             ["", ""]],
+                 [%Q{""""},              ["\""]],
+                 [%Q{"""",""},           ["\"",""]],
+                 [%Q{,""},               [nil,""]],
+                 [%Q{,"\r"},             [nil,"\r"]],
+                 [%Q{"\r\n,"},           ["\r\n,"]],
+                 [%Q{"\r\n,",},          ["\r\n,", nil]] ]
+  
+  def test_col_sep
+    [";", "\t"].each do |sep|
+      TEST_CASES.each do |test_case|
+        assert_equal( test_case.last.map { |t| t.tr(",", sep) unless t.nil? },
+                      FasterCSV.parse_line( test_case.first.tr(",", sep),
+                                            :col_sep => sep ) )
+      end
+    end
+    assert_equal( [",,,", nil],
+                  FasterCSV.parse_line(",,,;", :col_sep => ";") )
+  end
+  
+  def test_row_sep
+    assert_raise(FasterCSV::MalformedCSVError) do
+        FasterCSV.parse_line("1,2,3\n,4,5\r\n", :row_sep => "\r\n")
+    end
+    assert_equal( ["1", "2", "3\n", "4", "5"],
+                  FasterCSV.parse_line( %Q{1,2,"3\n",4,5\r\n},
+                                        :row_sep => "\r\n") )
+  end
+end

data/test/tc_interface.rb

@@ -0,0 +1,124 @@
+#!/usr/local/bin/ruby -w
+
+# tc_interface.rb
+#
+#  Created by James Edward Gray II on 2005-11-14.
+#  Copyright 2005 Gray Productions. All rights reserved.
+
+require "test/unit"
+
+require "faster_csv"
+
+class TestFasterCSVInterface < Test::Unit::TestCase
+  def setup
+    @path = File.join(File.dirname(__FILE__), "temp_test_data.csv")
+    
+    File.open(@path, "w") do |file|
+      file << "1\t2\t3\r\n"
+      file << "4\t5\r\n"
+    end
+
+    @expected = [%w{1 2 3}, %w{4 5}]
+  end
+  
+  def teardown
+    File.unlink(@path)
+  end
+  
+  ### Test Read Interface ###
+  
+  def test_foreach
+    FasterCSV.foreach(@path, :col_sep => "\t", :row_sep => "\r\n") do |row|
+      assert_equal(@expected.shift, row)
+    end
+  end
+  
+  def test_open_and_close
+    csv = FasterCSV.open(@path, "r+", :col_sep => "\t", :row_sep => "\r\n")
+    assert_not_nil(csv)
+    assert_instance_of(FasterCSV, csv)
+    assert_equal(false, csv.closed?)
+    csv.close
+    assert(csv.closed?)
+    
+    ret = FasterCSV.open(@path) do |csv|
+      assert_instance_of(FasterCSV, csv)
+      "Return value."
+    end
+    assert(csv.closed?)
+    assert_equal("Return value.", ret)
+  end
+  
+  def test_parse
+    data = File.read(@path)
+    assert_equal( @expected,
+                  FasterCSV.parse(data, :col_sep => "\t", :row_sep => "\r\n") )
+
+    FasterCSV.parse(data, :col_sep => "\t", :row_sep => "\r\n") do |row|
+      assert_equal(@expected.shift, row)
+    end
+  end
+  
+  def test_parse_line
+    row = FasterCSV.parse_line("1;2;3", :col_sep => ";")
+    assert_not_nil(row)
+    assert_instance_of(Array, row)
+    assert_equal(%w{1 2 3}, row)
+  end
+  
+  def test_read_and_readlines
+    assert_equal( @expected,
+                  FasterCSV.read(@path, :col_sep => "\t", :row_sep => "\r\n") )
+    assert_equal( @expected,
+                  FasterCSV.readlines( @path,
+                                       :col_sep => "\t", :row_sep => "\r\n") )
+    
+    
+    data = FasterCSV.open(@path, :col_sep => "\t", :row_sep => "\r\n") do |csv|
+      csv.read
+    end
+    assert_equal(@expected, data)
+    data = FasterCSV.open(@path, :col_sep => "\t", :row_sep => "\r\n") do |csv|
+      csv.readlines
+    end
+    assert_equal(@expected, data)
+  end
+  
+  def test_shift  # aliased as gets() and readline()
+    FasterCSV.open(@path, "r+", :col_sep => "\t", :row_sep => "\r\n") do |csv|
+      assert_equal(@expected.shift, csv.shift)
+      assert_equal(@expected.shift, csv.shift)
+      assert_equal(nil, csv.shift)
+    end
+  end
+  
+  ### Test Write Interface ###
+
+  def test_generate
+    str = FasterCSV.generate do |csv|
+      assert_instance_of(FasterCSV, csv)
+      assert_equal(csv, csv << [1, 2, 3])
+      assert_equal(csv, csv << [4, nil, 5])
+    end
+    assert_not_nil(str)
+    assert_instance_of(String, str)
+    assert_equal("1,2,3\n4,,5\n", str)
+  end
+  
+  def test_generate_line
+    line = FasterCSV.generate_line(%w{1 2 3}, :col_sep => ";")
+    assert_not_nil(line)
+    assert_instance_of(String, line)
+    assert_equal("1;2;3\n", line)
+  end
+  
+  def test_append  # aliased add_row() and puts()
+    File.unlink(@path)
+    
+    FasterCSV.open(@path, "w", :col_sep => "\t", :row_sep => "\r\n") do |csv|
+      @expected.each { |row| csv << row }
+    end
+
+    test_shift
+  end
+end

data/test/tc_speed.rb

@@ -0,0 +1,39 @@
+#!/usr/local/bin/ruby -w
+
+# tc_speed.rb
+#
+#  Created by James Edward Gray II on 2005-11-14.
+#  Copyright 2005 Gray Productions. All rights reserved.
+
+require "test/unit"
+
+require "faster_csv"
+require "csv"
+
+class TestFasterCSVSpeed < Test::Unit::TestCase
+  PATH = File.join(File.dirname(__FILE__), "test_data.csv")
+  
+  def test_that_we_are_doing_the_same_work
+    FasterCSV.open(PATH) do |csv|
+      CSV.foreach(PATH) do |row|
+        assert_equal(row, csv.shift)
+      end
+    end
+  end
+  
+  def test_speed_vs_csv
+    csv_time = Time.now
+    CSV.foreach(PATH) do |row|
+      # do nothing, we're just timing a read...
+    end
+    csv_time = Time.now - csv_time
+
+    faster_csv_time = Time.now
+    FasterCSV.foreach(PATH) do |row|
+      # do nothing, we're just timing a read...
+    end
+    faster_csv_time = Time.now - faster_csv_time
+    
+    assert(faster_csv_time < csv_time / 3)
+  end
+end

data/test/ts_all.rb

@@ -0,0 +1,14 @@
+#!/usr/local/bin/ruby -w
+
+# ts_all.rb
+#
+#  Created by James Edward Gray II on 2005-11-14.
+#  Copyright 2005 Gray Productions. All rights reserved.
+
+require "test/unit"
+
+require "tc_csv_parsing"
+require "tc_features"
+require "tc_interface"
+require "tc_csv_writing"
+require "tc_speed"

metadata

@@ -0,0 +1,65 @@
+!ruby/object:Gem::Specification 
+rubygems_version: 0.8.11
+specification_version: 1
+name: fastercsv
+version: !ruby/object:Gem::Version 
+  version: 0.1.0
+date: 2005-11-15 00:00:00 -06:00
+summary: FasterCSV is CSV, but faster, smaller, and cleaner.
+require_paths: 
+- lib
+email: james@grayproductions.net
+homepage: http://fastercsv.rubyforge.org
+rubyforge_project: fastercsv
+description: FasterCSV is intended as a complete replacement to the CSV standard library. It is significantly faster and smaller while still being pure Ruby code. It also strives for a better interface.
+autorequire: fastercsv
+default_executable: 
+bindir: bin
+has_rdoc: true
+required_ruby_version: !ruby/object:Gem::Version::Requirement 
+  requirements: 
+  - - ">"
+    - !ruby/object:Gem::Version 
+      version: 0.0.0
+  version: 
+platform: ruby
+signing_key: 
+cert_chain: 
+authors: 
+- James Edward Gray II
+files: 
+- lib/faster_csv.rb
+- test/tc_csv_parsing.rb
+- test/tc_csv_writing.rb
+- test/tc_features.rb
+- test/tc_interface.rb
+- test/tc_speed.rb
+- test/ts_all.rb
+- Rakefile
+- setup.rb
+- README
+- INSTALL
+- TODO
+- CHANGELOG
+- LICENSE
+test_files: 
+- test/ts_all.rb
+rdoc_options: 
+- --title
+- FasterCSV Documentation
+- --main
+- README
+extra_rdoc_files: 
+- README
+- INSTALL
+- TODO
+- CHANGELOG
+- LICENSE
+executables: []
+
+extensions: []
+
+requirements: []
+
+dependencies: []
+