aboutsummaryrefslogtreecommitdiffstats
path: root/test/csv/tc_encodings.rb
diff options
context:
space:
mode:
authorjeg2 <jeg2@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2008-10-18 15:30:24 +0000
committerjeg2 <jeg2@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2008-10-18 15:30:24 +0000
commitb7be78d774daf5b9a9fdd63e6d20e30309b9efa0 (patch)
treef7272b9cfeace2b5ee9a3a283c0085ad15b398a0 /test/csv/tc_encodings.rb
parent54e2cb81799f0ff7e443758b50e906ea5b1833d3 (diff)
downloadruby-b7be78d774daf5b9a9fdd63e6d20e30309b9efa0.tar.gz
* test/csv/*: Renamed tc_* files to test_* to fit in within Ruby's
testing process. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@19843 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Diffstat (limited to 'test/csv/tc_encodings.rb')
-rw-r--r--test/csv/tc_encodings.rb256
1 files changed, 0 insertions, 256 deletions
diff --git a/test/csv/tc_encodings.rb b/test/csv/tc_encodings.rb
deleted file mode 100644
index 0a300af291..0000000000
--- a/test/csv/tc_encodings.rb
+++ /dev/null
@@ -1,256 +0,0 @@
-#!/usr/bin/env ruby -w
-# encoding: UTF-8
-
-# tc_encodings.rb
-#
-# Created by James Edward Gray II on 2008-09-13.
-# Copyright 2008 James Edward Gray II. You can redistribute or modify this code
-# under the terms of Ruby's license.
-
-require "test/unit"
-
-require "csv"
-
-class TestEncodings < Test::Unit::TestCase
- def setup
- @temp_csv_path = File.join(File.dirname(__FILE__), "temp.csv")
- end
-
- def teardown
- File.unlink(@temp_csv_path) if File.exist? @temp_csv_path
- end
-
- ########################################
- ### Hand Test Some Popular Encodings ###
- ########################################
-
- def test_parses_utf8_encoding
- assert_parses( [ %w[ one two … ],
- %w[ 1 … 3 ],
- %w[ … 5 6 ] ], "UTF-8" )
- end
-
- def test_parses_latin1_encoding
- assert_parses( [ %w[ one two Résumé ],
- %w[ 1 Résumé 3 ],
- %w[ Résumé 5 6 ] ], "ISO-8859-1" )
- end
-
- def test_parses_utf16be_encoding
- assert_parses( [ %w[ one two … ],
- %w[ 1 … 3 ],
- %w[ … 5 6 ] ], "UTF-16BE" )
- end
-
- def test_parses_shift_jis_encoding
- assert_parses( [ %w[ 一 二 三 ],
- %w[ 四 五 六 ],
- %w[ 七 八 九 ] ], "Shift_JIS" )
- end
-
- ###########################################################
- ### Try Simple Reading for All Non-dummy Ruby Encodings ###
- ###########################################################
-
- def test_reading_with_most_encodings
- each_encoding do |encoding|
- begin
- assert_parses( [ %w[ abc def ],
- %w[ ghi jkl ] ], encoding )
- rescue Encoding::ConverterNotFoundError
- fail("Failed to support #{encoding.name}.")
- end
- end
- end
-
- def test_regular_expression_escaping
- each_encoding do |encoding|
- begin
- assert_parses( [ %w[ abc def ],
- %w[ ghi jkl ] ], encoding, col_sep: "|" )
- rescue Encoding::ConverterNotFoundError
- fail("Failed to properly escape #{encoding.name}.")
- end
- end
- end
-
- #######################################################################
- ### Stress Test ASCII Compatible and Non-ASCII Compatible Encodings ###
- #######################################################################
-
- def test_auto_line_ending_detection
- # arrange data to place a \r at the end of CSV's read ahead point
- encode_for_tests([["a" * 509]], row_sep: "\r\n") do |data|
- assert_equal("\r\n".encode(data.encoding), CSV.new(data).row_sep)
- end
- end
-
- def test_csv_chars_are_transcoded
- encode_for_tests([%w[abc def]]) do |data|
- %w[col_sep row_sep quote_char].each do |csv_char|
- assert_equal( "|".encode(data.encoding),
- CSV.new(data, csv_char.to_sym => "|").send(csv_char) )
- end
- end
- end
-
- def test_parser_works_with_encoded_headers
- encode_for_tests([%w[one two three], %w[1 2 3]]) do |data|
- parsed = CSV.parse(data, headers: true)
- assert( parsed.headers.all? { |h| h.encoding == data.encoding },
- "Wrong data encoding." )
- parsed.each do |row|
- assert( row.fields.all? { |f| f.encoding == data.encoding },
- "Wrong data encoding." )
- end
- end
- end
-
- def test_built_in_converters_transcode_to_utf_8_then_convert
- encode_for_tests([%w[one two three], %w[1 2 3]]) do |data|
- parsed = CSV.parse(data, converters: :integer)
- assert( parsed[0].all? { |f| f.encoding == data.encoding },
- "Wrong data encoding." )
- assert_equal([1, 2, 3], parsed[1])
- end
- end
-
- def test_built_in_header_converters_transcode_to_utf_8_then_convert
- encode_for_tests([%w[one two three], %w[1 2 3]]) do |data|
- parsed = CSV.parse( data, headers: true,
- header_converters: :downcase )
- assert( parsed.headers.all? { |h| h.encoding.name == "UTF-8" },
- "Wrong data encoding." )
- assert( parsed[0].fields.all? { |f| f.encoding == data.encoding },
- "Wrong data encoding." )
- end
- end
-
- def test_open_allows_you_to_set_encodings
- encode_for_tests([%w[abc def]]) do |data|
- # read and write in encoding
- File.open(@temp_csv_path, "wb:#{data.encoding.name}") { |f| f << data }
- CSV.open(@temp_csv_path, "rb:#{data.encoding.name}") do |csv|
- csv.each do |row|
- assert( row.all? { |f| f.encoding == data.encoding },
- "Wrong data encoding." )
- end
- end
-
- # read and write with transcoding
- File.open(@temp_csv_path, "wb:UTF-32BE:#{data.encoding.name}") do |f|
- f << data
- end
- CSV.open(@temp_csv_path, "rb:UTF-32BE:#{data.encoding.name}") do |csv|
- csv.each do |row|
- assert( row.all? { |f| f.encoding == data.encoding },
- "Wrong data encoding." )
- end
- end
- end
- end
-
- def test_foreach_allows_you_to_set_encodings
- encode_for_tests([%w[abc def]]) do |data|
- # read and write in encoding
- File.open(@temp_csv_path, "wb:#{data.encoding.name}") { |f| f << data }
- CSV.foreach(@temp_csv_path, encoding: data.encoding.name) do |row|
- assert( row.all? { |f| f.encoding == data.encoding },
- "Wrong data encoding." )
- end
-
- # read and write with transcoding
- File.open(@temp_csv_path, "wb:UTF-32BE:#{data.encoding.name}") do |f|
- f << data
- end
- CSV.foreach( @temp_csv_path,
- encoding: "UTF-32BE:#{data.encoding.name}" ) do |row|
- assert( row.all? { |f| f.encoding == data.encoding },
- "Wrong data encoding." )
- end
- end
- end
-
- def test_read_allows_you_to_set_encodings
- encode_for_tests([%w[abc def]]) do |data|
- # read and write in encoding
- File.open(@temp_csv_path, "wb:#{data.encoding.name}") { |f| f << data }
- rows = CSV.read(@temp_csv_path, encoding: data.encoding.name)
- assert( rows.flatten.all? { |f| f.encoding == data.encoding },
- "Wrong data encoding." )
-
- # read and write with transcoding
- File.open(@temp_csv_path, "wb:UTF-32BE:#{data.encoding.name}") do |f|
- f << data
- end
- rows = CSV.read( @temp_csv_path,
- encoding: "UTF-32BE:#{data.encoding.name}" )
- assert( rows.flatten.all? { |f| f.encoding == data.encoding },
- "Wrong data encoding." )
- end
- end
-
- #################################
- ### Write CSV in any Encoding ###
- #################################
-
- def test_can_write_csv_in_any_encoding
- each_encoding do |encoding|
- # test generate_line with encoding hint
- csv = %w[abc d|ef].map { |f| f.encode(encoding) }.
- to_csv(col_sep: "|", encoding: encoding.name)
- assert_equal(encoding, csv.encoding)
-
- # test generate_line with encoding guessing from fields
- csv = %w[abc d|ef].map { |f| f.encode(encoding) }.to_csv(col_sep: "|")
- assert_equal(encoding, csv.encoding)
-
- # writing to files
- data = encode_ary([%w[abc d,ef], %w[123 456 ]], encoding)
- CSV.open(@temp_csv_path, "wb:#{encoding.name}") do |f|
- data.each { |row| f << row }
- end
- assert_equal(data, CSV.read(@temp_csv_path, encoding: encoding.name))
- end
- end
-
- private
-
- def assert_parses(fields, encoding, options = { })
- encoding = Encoding.find(encoding) unless encoding.is_a? Encoding
- fields = encode_ary(fields, encoding)
- parsed = CSV.parse(ary_to_data(fields, options), options)
- assert_equal(fields, parsed)
- parsed.flatten.each_with_index do |field, i|
- assert_equal(encoding, field.encoding, "Field[#{i + 1}] was transcoded.")
- end
- end
-
- def encode_ary(ary, encoding)
- ary.map { |row| row.map { |field| field.encode(encoding) } }
- end
-
- def ary_to_data(ary, options = { })
- encoding = ary.flatten.first.encoding
- quote_char = (options[:quote_char] || '"').encode(encoding)
- col_sep = (options[:col_sep] || ",").encode(encoding)
- row_sep = (options[:row_sep] || "\n").encode(encoding)
- ary.map { |row|
- row.map { |field|
- [quote_char, field.encode(encoding), quote_char].join
- }.join(col_sep) + row_sep
- }.join.encode(encoding)
- end
-
- def encode_for_tests(data, options = { })
- yield ary_to_data(encode_ary(data, "UTF-8"), options)
- yield ary_to_data(encode_ary(data, "UTF-16BE"), options)
- end
-
- def each_encoding
- Encoding.list.each do |encoding|
- next if encoding.dummy? # skip "dummy" encodings
- yield encoding
- end
- end
-end