diff options
Diffstat (limited to 'test/csv')
31 files changed, 5049 insertions, 1753 deletions
diff --git a/test/csv/helper.rb b/test/csv/helper.rb new file mode 100644 index 0000000000..1f9cf96979 --- /dev/null +++ b/test/csv/helper.rb @@ -0,0 +1,42 @@ +require "tempfile" +require "test/unit" + +require "csv" + +require_relative "../lib/with_different_ofs" + +module Helper + def with_chunk_size(chunk_size) + chunk_size_keep = ENV["CSV_PARSER_SCANNER_TEST_CHUNK_SIZE"] + begin + ENV["CSV_PARSER_SCANNER_TEST_CHUNK_SIZE"] = chunk_size + yield + ensure + ENV["CSV_PARSER_SCANNER_TEST_CHUNK_SIZE"] = chunk_size_keep + end + end + + def with_verbose(verbose) + original = $VERBOSE + begin + $VERBOSE = verbose + yield + ensure + $VERBOSE = original + end + end + + def with_default_internal(encoding) + original = Encoding.default_internal + begin + with_verbose(false) do + Encoding.default_internal = encoding + end + yield + ensure + with_verbose(false) do + Encoding.default_internal = original + end + end + end +end diff --git a/test/csv/interface/test_delegation.rb b/test/csv/interface/test_delegation.rb new file mode 100644 index 0000000000..349257633b --- /dev/null +++ b/test/csv/interface/test_delegation.rb @@ -0,0 +1,47 @@ +# frozen_string_literal: false + +require_relative "../helper" + +class TestCSVInterfaceDelegation < Test::Unit::TestCase + class TestStringIO < self + def setup + @csv = CSV.new("h1,h2") + end + + def test_flock + assert_raise(NotImplementedError) do + @csv.flock(File::LOCK_EX) + end + end + + def test_ioctl + assert_raise(NotImplementedError) do + @csv.ioctl(0) + end + end + + def test_stat + assert_raise(NotImplementedError) do + @csv.stat + end + end + + def test_to_i + assert_raise(NotImplementedError) do + @csv.to_i + end + end + + def test_binmode? + assert_equal(false, @csv.binmode?) + end + + def test_path + assert_equal(nil, @csv.path) + end + + def test_to_io + assert_instance_of(StringIO, @csv.to_io) + end + end +end diff --git a/test/csv/interface/test_read.rb b/test/csv/interface/test_read.rb new file mode 100644 index 0000000000..4266ef0578 --- /dev/null +++ b/test/csv/interface/test_read.rb @@ -0,0 +1,381 @@ +# frozen_string_literal: false + +require_relative "../helper" + +class TestCSVInterfaceRead < Test::Unit::TestCase + extend DifferentOFS + + def setup + super + @data = "" + @data << "1\t2\t3\r\n" + @data << "4\t5\r\n" + @input = Tempfile.new(["interface-read", ".csv"], binmode: true) + @input << @data + @input.rewind + @rows = [ + ["1", "2", "3"], + ["4", "5"], + ] + end + + def teardown + @input.close(true) + super + end + + def test_foreach + rows = [] + CSV.foreach(@input.path, col_sep: "\t", row_sep: "\r\n").each do |row| + rows << row + end + assert_equal(@rows, rows) + end + + if respond_to?(:ractor) + ractor + def test_foreach_in_ractor + ractor = Ractor.new(@input.path) do |path| + rows = [] + CSV.foreach(path, col_sep: "\t", row_sep: "\r\n").each do |row| + rows << row + end + rows + end + rows = [ + ["1", "2", "3"], + ["4", "5"], + ] + assert_equal(rows, ractor.take) + end + end + + def test_foreach_mode + rows = [] + CSV.foreach(@input.path, "r", col_sep: "\t", row_sep: "\r\n").each do |row| + rows << row + end + assert_equal(@rows, rows) + end + + def test_foreach_enumurator + rows = CSV.foreach(@input.path, col_sep: "\t", row_sep: "\r\n").to_a + assert_equal(@rows, rows) + end + + def test_closed? + csv = CSV.open(@input.path, "r+", col_sep: "\t", row_sep: "\r\n") + assert_not_predicate(csv, :closed?) + csv.close + assert_predicate(csv, :closed?) + end + + def test_open_auto_close + csv = nil + CSV.open(@input.path) do |_csv| + csv = _csv + end + assert_predicate(csv, :closed?) + end + + def test_open_closed + csv = nil + CSV.open(@input.path) do |_csv| + csv = _csv + csv.close + end + assert_predicate(csv, :closed?) + end + + def test_open_block_return_value + return_value = CSV.open(@input.path) do + "Return value." + end + assert_equal("Return value.", return_value) + end + + def test_open_encoding_valid + # U+1F600 GRINNING FACE + # U+1F601 GRINNING FACE WITH SMILING EYES + File.open(@input.path, "w") do |file| + file << "\u{1F600},\u{1F601}" + end + CSV.open(@input.path, encoding: "utf-8") do |csv| + assert_equal([["\u{1F600}", "\u{1F601}"]], + csv.to_a) + end + end + + def test_open_encoding_invalid + # U+1F600 GRINNING FACE + # U+1F601 GRINNING FACE WITH SMILING EYES + File.open(@input.path, "w") do |file| + file << "\u{1F600},\u{1F601}" + end + CSV.open(@input.path, encoding: "EUC-JP") do |csv| + error = assert_raise(CSV::MalformedCSVError) do + csv.shift + end + assert_equal("Invalid byte sequence in EUC-JP in line 1.", + error.message) + end + end + + def test_open_encoding_nonexistent + _output, error = capture_output do + CSV.open(@input.path, encoding: "nonexistent") do + end + end + assert_equal("path:0: warning: Unsupported encoding nonexistent ignored\n", + error.gsub(/\A.+:\d+: /, "path:0: ")) + end + + def test_open_encoding_utf_8_with_bom + # U+FEFF ZERO WIDTH NO-BREAK SPACE, BOM + # U+1F600 GRINNING FACE + # U+1F601 GRINNING FACE WITH SMILING EYES + File.open(@input.path, "w") do |file| + file << "\u{FEFF}\u{1F600},\u{1F601}" + end + CSV.open(@input.path, encoding: "bom|utf-8") do |csv| + assert_equal([["\u{1F600}", "\u{1F601}"]], + csv.to_a) + end + end + + def test_open_invalid_byte_sequence_in_utf_8 + CSV.open(@input.path, "w", encoding: Encoding::CP932) do |rows| + error = assert_raise(Encoding::InvalidByteSequenceError) do + rows << ["\x82\xa0"] + end + assert_equal('"\x82" on UTF-8', + error.message) + end + end + + def test_open_with_invalid_nil + CSV.open(@input.path, "w", encoding: Encoding::CP932, invalid: nil) do |rows| + error = assert_raise(Encoding::InvalidByteSequenceError) do + rows << ["\x82\xa0"] + end + assert_equal('"\x82" on UTF-8', + error.message) + end + end + + def test_open_with_invalid_replace + CSV.open(@input.path, "w", encoding: Encoding::CP932, invalid: :replace) do |rows| + rows << ["\x82\xa0".force_encoding(Encoding::UTF_8)] + end + CSV.open(@input.path, encoding: Encoding::CP932) do |csv| + assert_equal([["??"]], + csv.to_a) + end + end + + def test_open_with_invalid_replace_and_replace_string + CSV.open(@input.path, "w", encoding: Encoding::CP932, invalid: :replace, replace: "X") do |rows| + rows << ["\x82\xa0".force_encoding(Encoding::UTF_8)] + end + CSV.open(@input.path, encoding: Encoding::CP932) do |csv| + assert_equal([["XX"]], + csv.to_a) + end + end + + def test_open_with_undef_replace + # U+00B7 Middle Dot + CSV.open(@input.path, "w", encoding: Encoding::CP932, undef: :replace) do |rows| + rows << ["\u00B7"] + end + CSV.open(@input.path, encoding: Encoding::CP932) do |csv| + assert_equal([["?"]], + csv.to_a) + end + end + + def test_open_with_undef_replace_and_replace_string + # U+00B7 Middle Dot + CSV.open(@input.path, "w", encoding: Encoding::CP932, undef: :replace, replace: "X") do |rows| + rows << ["\u00B7"] + end + CSV.open(@input.path, encoding: Encoding::CP932) do |csv| + assert_equal([["X"]], + csv.to_a) + end + end + + def test_open_with_newline + CSV.open(@input.path, col_sep: "\t", universal_newline: true) do |csv| + assert_equal(@rows, csv.to_a) + end + File.binwrite(@input.path, "1,2,3\r\n" "4,5\n") + CSV.open(@input.path, newline: :universal) do |csv| + assert_equal(@rows, csv.to_a) + end + end + + def test_parse + assert_equal(@rows, + CSV.parse(@data, col_sep: "\t", row_sep: "\r\n")) + end + + def test_parse_block + rows = [] + CSV.parse(@data, col_sep: "\t", row_sep: "\r\n") do |row| + rows << row + end + assert_equal(@rows, rows) + end + + def test_parse_enumerator + rows = CSV.parse(@data, col_sep: "\t", row_sep: "\r\n").to_a + assert_equal(@rows, rows) + end + + def test_parse_headers_only + table = CSV.parse("a,b,c", headers: true) + assert_equal([ + ["a", "b", "c"], + [], + ], + [ + table.headers, + table.each.to_a, + ]) + end + + def test_parse_line + assert_equal(["1", "2", "3"], + CSV.parse_line("1;2;3", col_sep: ";")) + end + + def test_parse_line_shortcut + assert_equal(["1", "2", "3"], + "1;2;3".parse_csv(col_sep: ";")) + end + + def test_parse_line_empty + assert_equal(nil, CSV.parse_line("")) # to signal eof + end + + def test_parse_line_empty_line + assert_equal([], CSV.parse_line("\n1,2,3")) + end + + def test_read + assert_equal(@rows, + CSV.read(@input.path, col_sep: "\t", row_sep: "\r\n")) + end + + if respond_to?(:ractor) + ractor + def test_read_in_ractor + ractor = Ractor.new(@input.path) do |path| + CSV.read(path, col_sep: "\t", row_sep: "\r\n") + end + rows = [ + ["1", "2", "3"], + ["4", "5"], + ] + assert_equal(rows, ractor.take) + end + end + + def test_readlines + assert_equal(@rows, + CSV.readlines(@input.path, col_sep: "\t", row_sep: "\r\n")) + end + + def test_open_read + rows = CSV.open(@input.path, col_sep: "\t", row_sep: "\r\n") do |csv| + csv.read + end + assert_equal(@rows, rows) + end + + def test_open_readlines + rows = CSV.open(@input.path, col_sep: "\t", row_sep: "\r\n") do |csv| + csv.readlines + end + assert_equal(@rows, rows) + end + + def test_table + table = CSV.table(@input.path, col_sep: "\t", row_sep: "\r\n") + assert_equal(CSV::Table.new([ + CSV::Row.new([:"1", :"2", :"3"], [4, 5, nil]), + ]), + table) + end + + def test_shift # aliased as gets() and readline() + CSV.open(@input.path, "rb+", col_sep: "\t", row_sep: "\r\n") do |csv| + rows = [ + csv.shift, + csv.shift, + csv.shift, + ] + assert_equal(@rows + [nil], + rows) + end + end + + def test_enumerator + CSV.open(@input.path, col_sep: "\t", row_sep: "\r\n") do |csv| + assert_equal(@rows, csv.each.to_a) + end + end + + def test_shift_and_each + CSV.open(@input.path, col_sep: "\t", row_sep: "\r\n") do |csv| + rows = [] + rows << csv.shift + rows.concat(csv.each.to_a) + assert_equal(@rows, rows) + end + end + + def test_each_twice + CSV.open(@input.path, col_sep: "\t", row_sep: "\r\n") do |csv| + assert_equal([ + @rows, + [], + ], + [ + csv.each.to_a, + csv.each.to_a, + ]) + end + end + + def test_eof? + eofs = [] + CSV.open(@input.path, col_sep: "\t", row_sep: "\r\n") do |csv| + eofs << csv.eof? + csv.shift + eofs << csv.eof? + csv.shift + eofs << csv.eof? + end + assert_equal([false, false, true], + eofs) + end + + def test_new_nil + assert_raise_with_message ArgumentError, "Cannot parse nil as CSV" do + CSV.new(nil) + end + end + + def test_options_not_modified + options = {}.freeze + CSV.foreach(@input.path, **options) + CSV.open(@input.path, **options) {} + CSV.parse("", **options) + CSV.parse_line("", **options) + CSV.read(@input.path, **options) + CSV.readlines(@input.path, **options) + CSV.table(@input.path, **options) + end +end diff --git a/test/csv/interface/test_read_write.rb b/test/csv/interface/test_read_write.rb new file mode 100644 index 0000000000..c371e9c5fc --- /dev/null +++ b/test/csv/interface/test_read_write.rb @@ -0,0 +1,124 @@ +# frozen_string_literal: false + +require_relative "../helper" + +class TestCSVInterfaceReadWrite < Test::Unit::TestCase + extend DifferentOFS + + def test_filter + input = <<-CSV.freeze +1;2;3 +4;5 + CSV + output = "" + CSV.filter(input, output, + in_col_sep: ";", + out_col_sep: ",", + converters: :all) do |row| + row.map! {|n| n * 2} + row << "Added\r" + end + assert_equal(<<-CSV, output) +2,4,6,"Added\r" +8,10,"Added\r" + CSV + end + + def test_filter_headers_true + input = <<-CSV.freeze +Name,Value +foo,0 +bar,1 +baz,2 + CSV + output = "" + CSV.filter(input, output, headers: true) do |row| + row[0] += "X" + row[1] = row[1].to_i + 1 + end + assert_equal(<<-CSV, output) +fooX,1 +barX,2 +bazX,3 + CSV + end + + def test_filter_headers_true_write_headers + input = <<-CSV.freeze +Name,Value +foo,0 +bar,1 +baz,2 + CSV + output = "" + CSV.filter(input, output, headers: true, out_write_headers: true) do |row| + if row.is_a?(Array) + row[0] += "X" + row[1] += "Y" + else + row[0] += "X" + row[1] = row[1].to_i + 1 + end + end + assert_equal(<<-CSV, output) +NameX,ValueY +fooX,1 +barX,2 +bazX,3 + CSV + end + + def test_filter_headers_array_write_headers + input = <<-CSV.freeze +foo,0 +bar,1 +baz,2 + CSV + output = "" + CSV.filter(input, output, + headers: ["Name", "Value"], + out_write_headers: true) do |row| + row[0] += "X" + row[1] = row[1].to_i + 1 + end + assert_equal(<<-CSV, output) +Name,Value +fooX,1 +barX,2 +bazX,3 + CSV + end + + def test_instance_same + data = "" + assert_equal(CSV.instance(data, col_sep: ";").object_id, + CSV.instance(data, col_sep: ";").object_id) + end + + def test_instance_append + output = "" + CSV.instance(output, col_sep: ";") << ["a", "b", "c"] + assert_equal(<<-CSV, output) +a;b;c + CSV + CSV.instance(output, col_sep: ";") << [1, 2, 3] + assert_equal(<<-CSV, output) +a;b;c +1;2;3 + CSV + end + + def test_instance_shortcut + assert_equal(CSV.instance, + CSV {|csv| csv}) + end + + def test_instance_shortcut_with_io + io = StringIO.new + from_instance = CSV.instance(io, col_sep: ";") { |csv| csv << ["a", "b", "c"] } + from_shortcut = CSV(io, col_sep: ";") { |csv| csv << ["e", "f", "g"] } + + assert_equal(from_instance, from_shortcut) + assert_equal(from_instance.string, "a;b;c\ne;f;g\n") + end +end diff --git a/test/csv/interface/test_write.rb b/test/csv/interface/test_write.rb new file mode 100644 index 0000000000..0cd39a7663 --- /dev/null +++ b/test/csv/interface/test_write.rb @@ -0,0 +1,217 @@ +# frozen_string_literal: false + +require_relative "../helper" + +class TestCSVInterfaceWrite < Test::Unit::TestCase + extend DifferentOFS + + def setup + super + @output = Tempfile.new(["interface-write", ".csv"]) + end + + def teardown + @output.close(true) + super + end + + def test_generate_default + csv_text = CSV.generate do |csv| + csv << [1, 2, 3] << [4, nil, 5] + end + assert_equal(<<-CSV, csv_text) +1,2,3 +4,,5 + CSV + end + + if respond_to?(:ractor) + ractor + def test_generate_default_in_ractor + ractor = Ractor.new do + CSV.generate do |csv| + csv << [1, 2, 3] << [4, nil, 5] + end + end + assert_equal(<<-CSV, ractor.take) +1,2,3 +4,,5 + CSV + end + end + + def test_generate_append + csv_text = <<-CSV +1,2,3 +4,,5 + CSV + CSV.generate(csv_text) do |csv| + csv << ["last", %Q{"row"}] + end + assert_equal(<<-CSV, csv_text) +1,2,3 +4,,5 +last,"""row""" + CSV + end + + def test_generate_no_new_line + csv_text = CSV.generate("test") do |csv| + csv << ["row"] + end + assert_equal(<<-CSV, csv_text) +testrow + CSV + end + + def test_generate_line_col_sep + line = CSV.generate_line(["1", "2", "3"], col_sep: ";") + assert_equal(<<-LINE, line) +1;2;3 + LINE + end + + def test_generate_line_row_sep + line = CSV.generate_line(["1", "2"], row_sep: nil) + assert_equal(<<-LINE.chomp, line) +1,2 + LINE + end + + def test_generate_line_shortcut + line = ["1", "2", "3"].to_csv(col_sep: ";") + assert_equal(<<-LINE, line) +1;2;3 + LINE + end + + def test_generate_lines + lines = CSV.generate_lines([["foo", "bar"], [1, 2], [3, 4]]) + assert_equal(<<-LINES, lines) +foo,bar +1,2 +3,4 + LINES + end + + def test_headers_detection + headers = ["a", "b", "c"] + CSV.open(@output.path, "w", headers: true) do |csv| + csv << headers + csv << ["1", "2", "3"] + assert_equal(headers, csv.headers) + end + end + + def test_lineno + CSV.open(@output.path, "w") do |csv| + n_lines = 20 + n_lines.times do + csv << ["a", "b", "c"] + end + assert_equal(n_lines, csv.lineno) + end + end + + def test_append_row + CSV.open(@output.path, "wb") do |csv| + csv << + CSV::Row.new([], ["1", "2", "3"]) << + CSV::Row.new([], ["a", "b", "c"]) + end + assert_equal(<<-CSV, File.read(@output.path, mode: "rb")) +1,2,3 +a,b,c + CSV + end + + + if respond_to?(:ractor) + ractor + def test_append_row_in_ractor + ractor = Ractor.new(@output.path) do |path| + CSV.open(path, "wb") do |csv| + csv << + CSV::Row.new([], ["1", "2", "3"]) << + CSV::Row.new([], ["a", "b", "c"]) + end + end + ractor.take + assert_equal(<<-CSV, File.read(@output.path, mode: "rb")) +1,2,3 +a,b,c + CSV + end + end + + def test_append_hash + CSV.open(@output.path, "wb", headers: true) do |csv| + csv << [:a, :b, :c] + csv << {a: 1, b: 2, c: 3} + csv << {a: 4, b: 5, c: 6} + end + assert_equal(<<-CSV, File.read(@output.path, mode: "rb")) +a,b,c +1,2,3 +4,5,6 + CSV + end + + def test_append_hash_headers_array + CSV.open(@output.path, "wb", headers: [:b, :a, :c]) do |csv| + csv << {a: 1, b: 2, c: 3} + csv << {a: 4, b: 5, c: 6} + end + assert_equal(<<-CSV, File.read(@output.path, mode: "rb")) +2,1,3 +5,4,6 + CSV + end + + def test_append_hash_headers_string + CSV.open(@output.path, "wb", headers: "b|a|c", col_sep: "|") do |csv| + csv << {"a" => 1, "b" => 2, "c" => 3} + csv << {"a" => 4, "b" => 5, "c" => 6} + end + assert_equal(<<-CSV, File.read(@output.path, mode: "rb")) +2|1|3 +5|4|6 + CSV + end + + def test_write_headers + CSV.open(@output.path, + "wb", + headers: "b|a|c", + write_headers: true, + col_sep: "|" ) do |csv| + csv << {"a" => 1, "b" => 2, "c" => 3} + csv << {"a" => 4, "b" => 5, "c" => 6} + end + assert_equal(<<-CSV, File.read(@output.path, mode: "rb")) +b|a|c +2|1|3 +5|4|6 + CSV + end + + def test_write_headers_empty + CSV.open(@output.path, + "wb", + headers: "b|a|c", + write_headers: true, + col_sep: "|" ) do |csv| + end + assert_equal(<<-CSV, File.read(@output.path, mode: "rb")) +b|a|c + CSV + end + + def test_options_not_modified + options = {}.freeze + CSV.generate(**options) {} + CSV.generate_line([], **options) + CSV.filter("", "", **options) + CSV.instance("", **options) + end +end diff --git a/test/csv/line_endings.gz b/test/csv/line_endings.gz Binary files differnew file mode 100644 index 0000000000..39e1729ee4 --- /dev/null +++ b/test/csv/line_endings.gz diff --git a/test/csv/parse/test_column_separator.rb b/test/csv/parse/test_column_separator.rb new file mode 100644 index 0000000000..d6eaa7b6de --- /dev/null +++ b/test/csv/parse/test_column_separator.rb @@ -0,0 +1,40 @@ +# -*- coding: utf-8 -*- +# frozen_string_literal: false + +require_relative "../helper" + +class TestCSVParseColumnSeparator < Test::Unit::TestCase + extend DifferentOFS + + def test_comma + assert_equal([["a", "b", nil, "d"]], + CSV.parse("a,b,,d", col_sep: ",")) + end + + def test_space + assert_equal([["a", "b", nil, "d"]], + CSV.parse("a b d", col_sep: " ")) + end + + def test_tab + assert_equal([["a", "b", nil, "d"]], + CSV.parse("a\tb\t\td", col_sep: "\t")) + end + + def test_multiple_characters_include_sub_separator + assert_equal([["a b", nil, "d"]], + CSV.parse("a b d", col_sep: " ")) + end + + def test_multiple_characters_leading_empty_fields + data = <<-CSV +<=><=>A<=>B<=>C +1<=>2<=>3 + CSV + assert_equal([ + [nil, nil, "A", "B", "C"], + ["1", "2", "3"], + ], + CSV.parse(data, col_sep: "<=>")) + end +end diff --git a/test/csv/parse/test_convert.rb b/test/csv/parse/test_convert.rb new file mode 100644 index 0000000000..c9195c71d9 --- /dev/null +++ b/test/csv/parse/test_convert.rb @@ -0,0 +1,165 @@ +# -*- coding: utf-8 -*- +# frozen_string_literal: false + +require_relative "../helper" + +class TestCSVParseConvert < Test::Unit::TestCase + extend DifferentOFS + + def setup + super + @data = "Numbers,:integer,1,:float,3.015" + @parser = CSV.new(@data) + + @custom = lambda {|field| /\A:(\S.*?)\s*\Z/ =~ field ? $1.to_sym : field} + + @time = Time.utc(2018, 12, 30, 6, 41, 29) + @windows_safe_time_data = @time.strftime("%a %b %d %H:%M:%S %Y") + + @preserving_converter = lambda do |field, info| + f = field.encode(CSV::ConverterEncoding) + return f if info.quoted? + begin + Integer(f, 10) + rescue + f + end + end + + @quoted_header_converter = lambda do |field, info| + f = field.encode(CSV::ConverterEncoding) + return f if info.quoted? + f.to_sym + end + end + + def test_integer + @parser.convert(:integer) + assert_equal(["Numbers", ":integer", 1, ":float", "3.015"], + @parser.shift) + end + + def test_float + @parser.convert(:float) + assert_equal(["Numbers", ":integer", 1.0, ":float", 3.015], + @parser.shift) + end + + def test_float_integer + @parser.convert(:float) + @parser.convert(:integer) + assert_equal(["Numbers", ":integer", 1.0, ":float", 3.015], + @parser.shift) + end + + def test_integer_float + @parser.convert(:integer) + @parser.convert(:float) + assert_equal(["Numbers", ":integer", 1, ":float", 3.015], + @parser.shift) + end + + def test_numeric + @parser.convert(:numeric) + assert_equal(["Numbers", ":integer", 1, ":float", 3.015], + @parser.shift) + end + + def test_all + @data << ",#{@windows_safe_time_data}" + @parser = CSV.new(@data) + @parser.convert(:all) + assert_equal(["Numbers", ":integer", 1, ":float", 3.015, @time.to_datetime], + @parser.shift) + end + + def test_custom + @parser.convert do |field| + /\A:(\S.*?)\s*\Z/ =~ field ? $1.to_sym : field + end + assert_equal(["Numbers", :integer, "1", :float, "3.015"], + @parser.shift) + end + + def test_builtin_custom + @parser.convert(:numeric) + @parser.convert(&@custom) + assert_equal(["Numbers", :integer, 1, :float, 3.015], + @parser.shift) + end + + def test_custom_field_info_line + @parser.convert do |field, info| + assert_equal(1, info.line) + info.index == 4 ? Float(field).floor : field + end + assert_equal(["Numbers", ":integer", "1", ":float", 3], + @parser.shift) + end + + def test_custom_field_info_header + headers = ["one", "two", "three", "four", "five"] + @parser = CSV.new(@data, headers: headers) + @parser.convert do |field, info| + info.header == "three" ? Integer(field) * 100 : field + end + assert_equal(CSV::Row.new(headers, + ["Numbers", ":integer", 100, ":float", "3.015"]), + @parser.shift) + end + + def test_custom_blank_field + converter = lambda {|field| field.nil?} + row = CSV.parse_line('nil,', converters: converter) + assert_equal([false, true], row) + end + + def test_nil_value + assert_equal(["nil", "", "a"], + CSV.parse_line(',"",a', nil_value: "nil")) + end + + def test_empty_value + assert_equal([nil, "empty", "a"], + CSV.parse_line(',"",a', empty_value: "empty")) + end + + def test_quoted_parse_line + row = CSV.parse_line('1,"2",3', converters: @preserving_converter) + assert_equal([1, "2", 3], row) + end + + def test_quoted_parse + expected = [["quoted", "unquoted"], ["109", 1], ["10A", 2]] + rows = CSV.parse(<<~CSV, converters: @preserving_converter) + "quoted",unquoted + "109",1 + "10A",2 + CSV + assert_equal(expected, rows) + end + + def test_quoted_alternating_quote + row = CSV.parse_line('"1",2,"3"', converters: @preserving_converter) + assert_equal(['1', 2, '3'], row) + end + + def test_quoted_parse_headers + expected = [["quoted", :unquoted], ["109", "1"], ["10A", "2"]] + table = CSV.parse(<<~CSV, headers: true, header_converters: @quoted_header_converter) + "quoted",unquoted + "109",1 + "10A",2 + CSV + assert_equal(expected, table.to_a) + end + + def test_quoted_parse_with_string_headers + expected = [["quoted", :unquoted], %w[109 1], %w[10A 2]] + table = CSV.parse(<<~CSV, headers: '"quoted",unquoted', header_converters: @quoted_header_converter) + "109",1 + "10A",2 + CSV + assert_equal(expected, table.to_a) + end +end diff --git a/test/csv/parse/test_each.rb b/test/csv/parse/test_each.rb new file mode 100644 index 0000000000..ce0b71d058 --- /dev/null +++ b/test/csv/parse/test_each.rb @@ -0,0 +1,23 @@ +# -*- coding: utf-8 -*- +# frozen_string_literal: false + +require_relative "../helper" + +class TestCSVParseEach < Test::Unit::TestCase + extend DifferentOFS + + def test_twice + data = <<-CSV +Ruby,2.6.0,script + CSV + csv = CSV.new(data) + assert_equal([ + [["Ruby", "2.6.0", "script"]], + [], + ], + [ + csv.to_a, + csv.to_a, + ]) + end +end diff --git a/test/csv/parse/test_general.rb b/test/csv/parse/test_general.rb new file mode 100644 index 0000000000..902be2ce4a --- /dev/null +++ b/test/csv/parse/test_general.rb @@ -0,0 +1,334 @@ +# -*- coding: utf-8 -*- +# frozen_string_literal: false + +require "timeout" + +require_relative "../helper" + +# +# 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 TestCSVParseGeneral < Test::Unit::TestCase + extend DifferentOFS + + BIG_DATA = "123456789\n" * 512 + + 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" ], + CSV.parse_line(ex) ) + end + + # Old Ruby 1.8 CSV library tests. + 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, CSV.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, CSV.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, CSV.parse_line(edge_case.first)) + end + end + + def test_james_edge_cases + # A read at eof? should return nil. + assert_equal(nil, CSV.parse_line("")) + # + # With Ruby 1.8 CSV it's impossible to tell an empty line from a line + # containing a single +nil+ field. The old CSV library returns + # <tt>[nil]</tt> in these cases, but <tt>Array.new</tt> makes more sense to + # me. + # + assert_equal(Array.new, CSV.parse_line("\n1,2,3\n")) + end + + def test_rob_edge_cases + [ [%Q{"a\nb"}, ["a\nb"]], + [%Q{"\n\n\n"}, ["\n\n\n"]], + [%Q{a,"b\n\nc"}, ['a', "b\n\nc"]], + [%Q{,"\r\n"}, [nil,"\r\n"]], + [%Q{,"\r\n."}, [nil,"\r\n."]], + [%Q{"a\na","one newline"}, ["a\na", 'one newline']], + [%Q{"a\n\na","two newlines"}, ["a\n\na", 'two newlines']], + [%Q{"a\r\na","one CRLF"}, ["a\r\na", 'one CRLF']], + [%Q{"a\r\n\r\na","two CRLFs"}, ["a\r\n\r\na", 'two CRLFs']], + [%Q{with blank,"start\n\nfinish"\n}, ['with blank', "start\n\nfinish"]], + ].each do |edge_case| + assert_equal(edge_case.last, CSV.parse_line(edge_case.first)) + end + end + + def test_non_regex_edge_cases + # An early version of the non-regex parser fails this test + [ [ "foo,\"foo,bar,baz,foo\",\"foo\"", + ["foo", "foo,bar,baz,foo", "foo"] ] ].each do |edge_case| + assert_equal(edge_case.last, CSV.parse_line(edge_case.first)) + end + + assert_raise(CSV::MalformedCSVError) do + CSV.parse_line("1,\"23\"4\"5\", 6") + end + end + + def test_malformed_csv_cr_first_line + error = assert_raise(CSV::MalformedCSVError) do + CSV.parse_line("1,2\r,3", row_sep: "\n") + end + assert_equal("Unquoted fields do not allow new line <\"\\r\"> in line 1.", + error.message) + end + + def test_malformed_csv_cr_middle_line + csv = <<-CSV +line,1,abc +line,2,"def\nghi" + +line,4,some\rjunk +line,5,jkl + CSV + + error = assert_raise(CSV::MalformedCSVError) do + CSV.parse(csv) + end + assert_equal("Unquoted fields do not allow new line <\"\\r\"> in line 4.", + error.message) + end + + def test_malformed_csv_unclosed_quote + error = assert_raise(CSV::MalformedCSVError) do + CSV.parse_line('1,2,"3...') + end + assert_equal("Unclosed quoted field in line 1.", + error.message) + end + + def test_malformed_csv_illegal_quote_middle_line + csv = <<-CSV +line,1,abc +line,2,"def\nghi" + +line,4,8'10" +line,5,jkl + CSV + + error = assert_raise(CSV::MalformedCSVError) do + CSV.parse(csv) + end + assert_equal("Illegal quoting in line 4.", + error.message) + end + + def test_the_parse_fails_fast_when_it_can_for_unquoted_fields + assert_parse_errors_out('valid,fields,bad start"' + BIG_DATA) + end + + def test_the_parse_fails_fast_when_it_can_for_unescaped_quotes + assert_parse_errors_out('valid,fields,"bad start"unescaped' + BIG_DATA) + end + + def test_field_size_limit_controls_lookahead + assert_parse_errors_out( 'valid,fields,"' + BIG_DATA + '"', + field_size_limit: 2048 ) + end + + def test_field_size_limit_max_allowed + column = "abcde" + assert_equal([[column]], + CSV.parse("\"#{column}\"", + field_size_limit: column.size + 1)) + end + + def test_field_size_limit_quote_simple + column = "abcde" + assert_parse_errors_out("\"#{column}\"", + field_size_limit: column.size) + end + + def test_field_size_limit_no_quote_implicitly + column = "abcde" + assert_parse_errors_out("#{column}", + field_size_limit: column.size) + end + + def test_field_size_limit_no_quote_explicitly + column = "abcde" + assert_parse_errors_out("#{column}", + field_size_limit: column.size, + quote_char: nil) + end + + def test_field_size_limit_in_extended_column_not_exceeding + data = <<~DATA + "a","b" + " + 2 + ","" + DATA + assert_nothing_raised(CSV::MalformedCSVError) do + CSV.parse(data, field_size_limit: 4) + end + end + + def test_field_size_limit_in_extended_column_exceeding + data = <<~DATA + "a","b" + " + 2345 + ","" + DATA + assert_parse_errors_out(data, field_size_limit: 5) + end + + def test_max_field_size_controls_lookahead + assert_parse_errors_out( 'valid,fields,"' + BIG_DATA + '"', + max_field_size: 2048 ) + end + + def test_max_field_size_max_allowed + column = "abcde" + assert_equal([[column]], + CSV.parse("\"#{column}\"", + max_field_size: column.size)) + end + + def test_max_field_size_quote_simple + column = "abcde" + assert_parse_errors_out("\"#{column}\"", + max_field_size: column.size - 1) + end + + def test_max_field_size_no_quote_implicitly + column = "abcde" + assert_parse_errors_out("#{column}", + max_field_size: column.size - 1) + end + + def test_max_field_size_no_quote_explicitly + column = "abcde" + assert_parse_errors_out("#{column}", + max_field_size: column.size - 1, + quote_char: nil) + end + + def test_max_field_size_in_extended_column_not_exceeding + data = <<~DATA + "a","b" + " + 2 + ","" + DATA + assert_nothing_raised(CSV::MalformedCSVError) do + CSV.parse(data, max_field_size: 3) + end + end + + def test_max_field_size_in_extended_column_exceeding + data = <<~DATA + "a","b" + " + 2345 + ","" + DATA + assert_parse_errors_out(data, max_field_size: 4) + end + + def test_row_sep_auto_cr + assert_equal([["a"]], CSV.parse("a\r")) + end + + def test_row_sep_auto_lf + assert_equal([["a"]], CSV.parse("a\n")) + end + + def test_row_sep_auto_cr_lf + assert_equal([["a"]], CSV.parse("a\r\n")) + end + + def test_seeked_string_io + input_with_bom = StringIO.new("\ufeffあ,い,う\r\na,b,c\r\n") + input_with_bom.read(3) + assert_equal([ + ["あ", "い", "う"], + ["a", "b", "c"], + ], + CSV.new(input_with_bom).each.to_a) + end + + private + def assert_parse_errors_out(data, **options) + assert_raise(CSV::MalformedCSVError) do + Timeout.timeout(0.2) do + CSV.parse(data, **options) + fail("Parse didn't error out") + end + end + end +end diff --git a/test/csv/parse/test_header.rb b/test/csv/parse/test_header.rb new file mode 100644 index 0000000000..e8c3786d68 --- /dev/null +++ b/test/csv/parse/test_header.rb @@ -0,0 +1,342 @@ +# -*- coding: utf-8 -*- +# frozen_string_literal: false + +require_relative "../helper" + +class TestCSVHeaders < Test::Unit::TestCase + extend DifferentOFS + + def setup + super + @data = <<-CSV +first,second,third +A,B,C +1,2,3 + CSV + end + + def test_first_row + [:first_row, true].each do |setting| # two names for the same setting + # activate headers + csv = nil + assert_nothing_raised(Exception) do + csv = CSV.parse(@data, headers: setting) + end + + # first data row - skipping headers + row = csv[0] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([%w{first A}, %w{second B}, %w{third C}], row.to_a) + + # second data row + row = csv[1] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([%w{first 1}, %w{second 2}, %w{third 3}], row.to_a) + + # empty + assert_nil(csv[2]) + end + end + + def test_array_of_headers + # activate headers + csv = nil + assert_nothing_raised(Exception) do + csv = CSV.parse(@data, headers: [:my, :new, :headers]) + end + + # first data row - skipping headers + row = csv[0] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal( [[:my, "first"], [:new, "second"], [:headers, "third"]], + row.to_a ) + + # second data row + row = csv[1] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([[:my, "A"], [:new, "B"], [:headers, "C"]], row.to_a) + + # third data row + row = csv[2] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([[:my, "1"], [:new, "2"], [:headers, "3"]], row.to_a) + + # empty + assert_nil(csv[3]) + + # with return and convert + assert_nothing_raised(Exception) do + csv = CSV.parse( @data, headers: [:my, :new, :headers], + return_headers: true, + header_converters: lambda { |h| h.to_s } ) + end + row = csv[0] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([["my", :my], ["new", :new], ["headers", :headers]], row.to_a) + assert_predicate(row, :header_row?) + assert_not_predicate(row, :field_row?) + end + + def test_csv_header_string + # activate headers + csv = nil + assert_nothing_raised(Exception) do + csv = CSV.parse(@data, headers: "my,new,headers") + end + + # first data row - skipping headers + row = csv[0] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([%w{my first}, %w{new second}, %w{headers third}], row.to_a) + + # second data row + row = csv[1] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([%w{my A}, %w{new B}, %w{headers C}], row.to_a) + + # third data row + row = csv[2] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([%w{my 1}, %w{new 2}, %w{headers 3}], row.to_a) + + # empty + assert_nil(csv[3]) + + # with return and convert + assert_nothing_raised(Exception) do + csv = CSV.parse( @data, headers: "my,new,headers", + return_headers: true, + header_converters: :symbol ) + end + row = csv[0] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([[:my, "my"], [:new, "new"], [:headers, "headers"]], row.to_a) + assert_predicate(row, :header_row?) + assert_not_predicate(row, :field_row?) + end + + def test_csv_header_string_inherits_separators + # parse with custom col_sep + csv = nil + assert_nothing_raised(Exception) do + csv = CSV.parse( @data.tr(",", "|"), col_sep: "|", + headers: "my|new|headers" ) + end + + # verify headers were recognized + row = csv[0] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([%w{my first}, %w{new second}, %w{headers third}], row.to_a) + end + + def test_return_headers + # activate headers and request they are returned + csv = nil + assert_nothing_raised(Exception) do + csv = CSV.parse(@data, headers: true, return_headers: true) + end + + # header row + row = csv[0] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal( [%w{first first}, %w{second second}, %w{third third}], + row.to_a ) + assert_predicate(row, :header_row?) + assert_not_predicate(row, :field_row?) + + # first data row - skipping headers + row = csv[1] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([%w{first A}, %w{second B}, %w{third C}], row.to_a) + assert_not_predicate(row, :header_row?) + assert_predicate(row, :field_row?) + + # second data row + row = csv[2] + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([%w{first 1}, %w{second 2}, %w{third 3}], row.to_a) + assert_not_predicate(row, :header_row?) + assert_predicate(row, :field_row?) + + # empty + assert_nil(csv[3]) + end + + def test_converters + # create test data where headers and fields look alike + data = <<-CSV +1,2,3 +1,2,3 + CSV + + # normal converters do not affect headers + csv = CSV.parse( data, headers: true, + return_headers: true, + converters: :numeric ) + assert_equal([%w{1 1}, %w{2 2}, %w{3 3}], csv[0].to_a) + assert_equal([["1", 1], ["2", 2], ["3", 3]], csv[1].to_a) + assert_nil(csv[2]) + + # header converters do affect headers (only) + assert_nothing_raised(Exception) do + csv = CSV.parse( data, headers: true, + return_headers: true, + converters: :numeric, + header_converters: :symbol ) + end + assert_equal([[:"1", "1"], [:"2", "2"], [:"3", "3"]], csv[0].to_a) + assert_equal([[:"1", 1], [:"2", 2], [:"3", 3]], csv[1].to_a) + assert_nil(csv[2]) + end + + def test_builtin_downcase_converter + csv = CSV.parse( "One,TWO Three", headers: true, + return_headers: true, + header_converters: :downcase ) + assert_equal(%w{one two\ three}, csv.headers) + end + + def test_builtin_symbol_converter + # Note that the trailing space is intentional + csv = CSV.parse( "One,TWO Three ", headers: true, + return_headers: true, + header_converters: :symbol ) + assert_equal([:one, :two_three], csv.headers) + end + + def test_builtin_symbol_raw_converter + csv = CSV.parse( "a b,c d", headers: true, + return_headers: true, + header_converters: :symbol_raw ) + assert_equal([:"a b", :"c d"], csv.headers) + end + + def test_builtin_symbol_converter_with_punctuation + csv = CSV.parse( "One, Two & Three ($)", headers: true, + return_headers: true, + header_converters: :symbol ) + assert_equal([:one, :two_three], csv.headers) + end + + def test_builtin_converters_with_blank_header + csv = CSV.parse( "one,,three", headers: true, + return_headers: true, + header_converters: [:downcase, :symbol, :symbol_raw] ) + assert_equal([:one, nil, :three], csv.headers) + end + + def test_custom_converter + converter = lambda { |header| header.tr(" ", "_") } + csv = CSV.parse( "One,TWO Three", + headers: true, + return_headers: true, + header_converters: converter ) + assert_equal(%w{One TWO_Three}, csv.headers) + end + + def test_table_support + csv = nil + assert_nothing_raised(Exception) do + csv = CSV.parse(@data, headers: true) + end + + assert_instance_of(CSV::Table, csv) + end + + def test_skip_blanks + @data = <<-CSV + + +A,B,C + +1,2,3 + + + + CSV + + expected = [%w[1 2 3]] + CSV.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]] + CSV.parse( @data, + headers: true, + return_headers: true, + skip_blanks: true ) do |row| + assert_equal(expected.shift, row.fields) + end + end + + def test_headers_reader + # no headers + assert_nil(CSV.new(@data).headers) + + # headers + csv = CSV.new(@data, headers: true) + assert_equal(true, csv.headers) # before headers are read + csv.shift # set headers + assert_equal(%w[first second third], csv.headers) # after headers are read + end + + def test_blank_row + @data += "\n#{@data}" # add a blank row + + # ensure that everything returned is a Row object + CSV.parse(@data, headers: true) do |row| + assert_instance_of(CSV::Row, row) + end + end + + def test_nil_row_header + @data = <<-CSV +A + +1 + CSV + + csv = CSV.parse(@data, headers: true) + + # ensure nil row creates Row object with headers + row = csv[0] + assert_equal([["A"], [nil]], + [row.headers, row.fields]) + end + + def test_parse_empty + assert_equal(CSV::Table.new([]), + CSV.parse("", headers: true)) + end + + def test_parse_empty_line + assert_equal(CSV::Table.new([]), + CSV.parse("\n", headers: true)) + end + + def test_specified_empty + assert_equal(CSV::Table.new([], + headers: ["header1"]), + CSV.parse("", headers: ["header1"])) + end + + def test_specified_empty_line + assert_equal(CSV::Table.new([CSV::Row.new(["header1"], [])], + headers: ["header1"]), + CSV.parse("\n", headers: ["header1"])) + end +end diff --git a/test/csv/parse/test_inputs_scanner.rb b/test/csv/parse/test_inputs_scanner.rb new file mode 100644 index 0000000000..06e1c845d5 --- /dev/null +++ b/test/csv/parse/test_inputs_scanner.rb @@ -0,0 +1,63 @@ +require_relative "../helper" + +class TestCSVParseInputsScanner < Test::Unit::TestCase + include Helper + + def test_scan_keep_over_chunks_nested_back + input = CSV::Parser::UnoptimizedStringIO.new("abcdefghijklmnl") + scanner = CSV::Parser::InputsScanner.new([input], + Encoding::UTF_8, + nil, + chunk_size: 2) + scanner.keep_start + assert_equal("abc", scanner.scan_all(/[a-c]+/)) + scanner.keep_start + assert_equal("def", scanner.scan_all(/[d-f]+/)) + scanner.keep_back + scanner.keep_back + assert_equal("abcdefg", scanner.scan_all(/[a-g]+/)) + end + + def test_scan_keep_over_chunks_nested_drop_back + input = CSV::Parser::UnoptimizedStringIO.new("abcdefghijklmnl") + scanner = CSV::Parser::InputsScanner.new([input], + Encoding::UTF_8, + nil, + chunk_size: 3) + scanner.keep_start + assert_equal("ab", scanner.scan(/../)) + scanner.keep_start + assert_equal("c", scanner.scan(/./)) + assert_equal("d", scanner.scan(/./)) + scanner.keep_drop + scanner.keep_back + assert_equal("abcdefg", scanner.scan_all(/[a-g]+/)) + end + + def test_each_line_keep_over_chunks_multibyte + input = CSV::Parser::UnoptimizedStringIO.new("ab\n\u{3000}a\n") + scanner = CSV::Parser::InputsScanner.new([input], + Encoding::UTF_8, + nil, + chunk_size: 1) + each_line = scanner.each_line("\n") + assert_equal("ab\n", each_line.next) + scanner.keep_start + assert_equal("\u{3000}a\n", each_line.next) + scanner.keep_back + assert_equal("\u{3000}a\n", scanner.scan_all(/[^,]+/)) + end + + def test_each_line_keep_over_chunks_fit_chunk_size + input = CSV::Parser::UnoptimizedStringIO.new("\na") + scanner = CSV::Parser::InputsScanner.new([input], + Encoding::UTF_8, + nil, + chunk_size: 1) + each_line = scanner.each_line("\n") + assert_equal("\n", each_line.next) + scanner.keep_start + assert_equal("a", each_line.next) + scanner.keep_back + end +end diff --git a/test/csv/parse/test_invalid.rb b/test/csv/parse/test_invalid.rb new file mode 100644 index 0000000000..ddb59e2b9a --- /dev/null +++ b/test/csv/parse/test_invalid.rb @@ -0,0 +1,52 @@ +# -*- coding: utf-8 -*- +# frozen_string_literal: false + +require_relative "../helper" + +class TestCSVParseInvalid < Test::Unit::TestCase + def test_no_column_mixed_new_lines + error = assert_raise(CSV::MalformedCSVError) do + CSV.parse("\n" + + "\r") + end + assert_equal("New line must be <\"\\n\"> not <\"\\r\"> in line 2.", + error.message) + end + + def test_ignore_invalid_line + csv = CSV.new(<<-CSV, headers: true, return_headers: true) +head1,head2,head3 +aaa,bbb,ccc +ddd,ee"e.fff +ggg,hhh,iii + CSV + headers = ["head1", "head2", "head3"] + assert_equal(CSV::Row.new(headers, headers), + csv.shift) + assert_equal(CSV::Row.new(headers, ["aaa", "bbb", "ccc"]), + csv.shift) + assert_equal(false, csv.eof?) + error = assert_raise(CSV::MalformedCSVError) do + csv.shift + end + assert_equal("Illegal quoting in line 3.", + error.message) + assert_equal(false, csv.eof?) + assert_equal(CSV::Row.new(headers, ["ggg", "hhh", "iii"]), + csv.shift) + assert_equal(true, csv.eof?) + end + + def test_ignore_invalid_line_cr_lf + data = <<-CSV +"1","OK"\r +"2",""NOT" OK"\r +"3","OK"\r +CSV + csv = CSV.new(data) + + assert_equal(['1', 'OK'], csv.shift) + assert_raise(CSV::MalformedCSVError) { csv.shift } + assert_equal(['3', 'OK'], csv.shift) + end +end diff --git a/test/csv/parse/test_liberal_parsing.rb b/test/csv/parse/test_liberal_parsing.rb new file mode 100644 index 0000000000..5796d10828 --- /dev/null +++ b/test/csv/parse/test_liberal_parsing.rb @@ -0,0 +1,171 @@ +# -*- coding: utf-8 -*- +# frozen_string_literal: false + +require_relative "../helper" + +class TestCSVParseLiberalParsing < Test::Unit::TestCase + extend DifferentOFS + + def test_middle_quote_start + input = '"Johnson, Dwayne",Dwayne "The Rock" Johnson' + error = assert_raise(CSV::MalformedCSVError) do + CSV.parse_line(input) + end + assert_equal("Illegal quoting in line 1.", + error.message) + assert_equal(["Johnson, Dwayne", 'Dwayne "The Rock" Johnson'], + CSV.parse_line(input, liberal_parsing: true)) + end + + def test_middle_quote_end + input = '"quoted" field' + error = assert_raise(CSV::MalformedCSVError) do + CSV.parse_line(input) + end + assert_equal("Any value after quoted field isn't allowed in line 1.", + error.message) + assert_equal(['"quoted" field'], + CSV.parse_line(input, liberal_parsing: true)) + end + + def test_endline_after_quoted_field_end + csv = CSV.new("A\r\n\"B\"\nC\r\n", liberal_parsing: true) + assert_equal(["A"], csv.gets) + error = assert_raise(CSV::MalformedCSVError) do + csv.gets + end + assert_equal('Illegal end-of-line sequence outside of a quoted field <"\n"> in line 2.', + error.message) + assert_equal(["C"], csv.gets) + end + + def test_quote_after_column_separator + error = assert_raise(CSV::MalformedCSVError) do + CSV.parse_line('is,this "three," or four,fields', liberal_parsing: true) + end + assert_equal("Unclosed quoted field in line 1.", + error.message) + end + + def test_quote_before_column_separator + assert_equal(["is", 'this "three', ' or four"', "fields"], + CSV.parse_line('is,this "three, or four",fields', + liberal_parsing: true)) + end + + def test_backslash_quote + assert_equal([ + "1", + "\"Hamlet says, \\\"Seems", + "\\\" madam! Nay it is; I know not \\\"seems.\\\"\"", + ], + CSV.parse_line('1,' + + '"Hamlet says, \"Seems,' + + '\" madam! Nay it is; I know not \"seems.\""', + liberal_parsing: true)) + end + + def test_space_quote + input = <<~CSV + Los Angeles, 34°03'N, 118°15'W + New York City, 40°42'46"N, 74°00'21"W + Paris, 48°51'24"N, 2°21'03"E + CSV + assert_equal( + [ + ["Los Angeles", " 34°03'N", " 118°15'W"], + ["New York City", " 40°42'46\"N", " 74°00'21\"W"], + ["Paris", " 48°51'24\"N", " 2°21'03\"E"], + ], + CSV.parse(input, liberal_parsing: true)) + end + + def test_double_quote_outside_quote + data = %Q{a,""b""} + error = assert_raise(CSV::MalformedCSVError) do + CSV.parse(data) + end + assert_equal("Any value after quoted field isn't allowed in line 1.", + error.message) + assert_equal([ + [["a", %Q{""b""}]], + [["a", %Q{"b"}]], + ], + [ + CSV.parse(data, liberal_parsing: true), + CSV.parse(data, + liberal_parsing: { + double_quote_outside_quote: true, + }), + ]) + end + + class TestBackslashQuote < Test::Unit::TestCase + extend ::DifferentOFS + + def test_double_quote_outside_quote + data = %Q{a,""b""} + assert_equal([ + [["a", %Q{""b""}]], + [["a", %Q{"b"}]], + ], + [ + CSV.parse(data, + liberal_parsing: { + backslash_quote: true + }), + CSV.parse(data, + liberal_parsing: { + backslash_quote: true, + double_quote_outside_quote: true + }), + ]) + end + + def test_unquoted_value + data = %q{\"\"a\"\"} + assert_equal([ + [[%q{\"\"a\"\"}]], + [[%q{""a""}]], + ], + [ + CSV.parse(data, liberal_parsing: true), + CSV.parse(data, + liberal_parsing: { + backslash_quote: true + }), + ]) + end + + def test_unquoted_value_multiple_characters_col_sep + data = %q{a<\\"b<=>x} + assert_equal([[%Q{a<"b}, "x"]], + CSV.parse(data, + col_sep: "<=>", + liberal_parsing: { + backslash_quote: true + })) + end + + def test_quoted_value + data = %q{"\"\"a\"\""} + assert_equal([ + [[%q{"\"\"a\"\""}]], + [[%q{""a""}]], + [[%q{""a""}]], + ], + [ + CSV.parse(data, liberal_parsing: true), + CSV.parse(data, + liberal_parsing: { + backslash_quote: true + }), + CSV.parse(data, + liberal_parsing: { + backslash_quote: true, + double_quote_outside_quote: true + }), + ]) + end + end +end diff --git a/test/csv/parse/test_quote_char_nil.rb b/test/csv/parse/test_quote_char_nil.rb new file mode 100644 index 0000000000..fc3b646759 --- /dev/null +++ b/test/csv/parse/test_quote_char_nil.rb @@ -0,0 +1,93 @@ +# -*- coding: utf-8 -*- +# frozen_string_literal: false + +require_relative "../helper" + +class TestCSVParseQuoteCharNil < Test::Unit::TestCase + extend DifferentOFS + + def test_full + assert_equal(["a", "b"], CSV.parse_line(%Q{a,b}, quote_char: nil)) + end + + def test_end_with_nil + assert_equal(["a", nil, nil, nil], CSV.parse_line(%Q{a,,,}, quote_char: nil)) + end + + def test_nil_nil + assert_equal([nil, nil], CSV.parse_line(%Q{,}, quote_char: nil)) + end + + def test_unquoted_value_multiple_characters_col_sep + data = %q{a<b<=>x} + assert_equal([[%Q{a<b}, "x"]], CSV.parse(data, col_sep: "<=>", quote_char: nil)) + end + + def test_csv_header_string + data = <<~DATA + first,second,third + A,B,C + 1,2,3 + DATA + assert_equal( + CSV::Table.new([ + CSV::Row.new(["my", "new", "headers"], ["first", "second", "third"]), + CSV::Row.new(["my", "new", "headers"], ["A", "B", "C"]), + CSV::Row.new(["my", "new", "headers"], ["1", "2", "3"]) + ]), + CSV.parse(data, headers: "my,new,headers", quote_char: nil) + ) + end + + def test_comma + assert_equal([["a", "b", nil, "d"]], + CSV.parse("a,b,,d", col_sep: ",", quote_char: nil)) + end + + def test_space + assert_equal([["a", "b", nil, "d"]], + CSV.parse("a b d", col_sep: " ", quote_char: nil)) + end + + def encode_array(array, encoding) + array.collect do |element| + element ? element.encode(encoding) : element + end + end + + def test_space_no_ascii + encoding = Encoding::UTF_16LE + assert_equal([encode_array(["a", "b", nil, "d"], encoding)], + CSV.parse("a b d".encode(encoding), + col_sep: " ".encode(encoding), + quote_char: nil)) + end + + def test_multiple_space + assert_equal([["a b", nil, "d"]], + CSV.parse("a b d", col_sep: " ", quote_char: nil)) + end + + def test_multiple_characters_leading_empty_fields + data = <<-CSV +<=><=>A<=>B<=>C +1<=>2<=>3 + CSV + assert_equal([ + [nil, nil, "A", "B", "C"], + ["1", "2", "3"], + ], + CSV.parse(data, col_sep: "<=>", quote_char: nil)) + end + + def test_line + lines = [ + "abc,def\n", + ] + csv = CSV.new(lines.join(""), quote_char: nil) + lines.each do |line| + csv.shift + assert_equal(line, csv.line) + end + end +end diff --git a/test/csv/parse/test_rewind.rb b/test/csv/parse/test_rewind.rb new file mode 100644 index 0000000000..0aa403b756 --- /dev/null +++ b/test/csv/parse/test_rewind.rb @@ -0,0 +1,40 @@ +# -*- coding: utf-8 -*- +# frozen_string_literal: false + +require_relative "../helper" + +class TestCSVParseRewind < Test::Unit::TestCase + extend DifferentOFS + + def parse(data, **options) + csv = CSV.new(data, **options) + records = csv.to_a + csv.rewind + [records, csv.to_a] + end + + def test_default + data = <<-CSV +Ruby,2.6.0,script + CSV + assert_equal([ + [["Ruby", "2.6.0", "script"]], + [["Ruby", "2.6.0", "script"]], + ], + parse(data)) + end + + def test_have_headers + data = <<-CSV +Language,Version,Type +Ruby,2.6.0,script + CSV + assert_equal([ + [CSV::Row.new(["Language", "Version", "Type"], + ["Ruby", "2.6.0", "script"])], + [CSV::Row.new(["Language", "Version", "Type"], + ["Ruby", "2.6.0", "script"])], + ], + parse(data, headers: true)) + end +end diff --git a/test/csv/parse/test_row_separator.rb b/test/csv/parse/test_row_separator.rb new file mode 100644 index 0000000000..eaf6adc910 --- /dev/null +++ b/test/csv/parse/test_row_separator.rb @@ -0,0 +1,16 @@ +# -*- coding: utf-8 -*- +# frozen_string_literal: false + +require_relative "../helper" + +class TestCSVParseRowSeparator < Test::Unit::TestCase + extend DifferentOFS + include Helper + + def test_multiple_characters + with_chunk_size("1") do + assert_equal([["a"], ["b"]], + CSV.parse("a\r\nb\r\n", row_sep: "\r\n")) + end + end +end diff --git a/test/csv/parse/test_skip_lines.rb b/test/csv/parse/test_skip_lines.rb new file mode 100644 index 0000000000..98d67ae51c --- /dev/null +++ b/test/csv/parse/test_skip_lines.rb @@ -0,0 +1,118 @@ +# frozen_string_literal: false + +require_relative "../helper" + +class TestCSVParseSkipLines < Test::Unit::TestCase + extend DifferentOFS + include Helper + + def test_default + csv = CSV.new("a,b,c\n") + assert_nil(csv.skip_lines) + end + + def test_regexp + csv = <<-CSV +1 +#2 + #3 +4 + CSV + assert_equal([ + ["1"], + ["4"], + ], + CSV.parse(csv, :skip_lines => /\A\s*#/)) + end + + def test_regexp_quoted + csv = <<-CSV +1 +#2 +"#3" +4 + CSV + assert_equal([ + ["1"], + ["#3"], + ["4"], + ], + CSV.parse(csv, :skip_lines => /\A\s*#/)) + end + + def test_string + csv = <<-CSV +1 +.2 +3. +4 + CSV + assert_equal([ + ["1"], + ["4"], + ], + CSV.parse(csv, :skip_lines => ".")) + end + + class RegexStub + end + + def test_not_matchable + regex_stub = RegexStub.new + csv = CSV.new("1\n", :skip_lines => regex_stub) + error = assert_raise(ArgumentError) do + csv.shift + end + assert_equal(":skip_lines has to respond to #match: #{regex_stub.inspect}", + error.message) + end + + class Matchable + def initialize(pattern) + @pattern = pattern + end + + def match(line) + @pattern.match(line) + end + end + + def test_matchable + csv = <<-CSV +1 +# 2 +3 +# 4 + CSV + assert_equal([ + ["1"], + ["3"], + ], + CSV.parse(csv, :skip_lines => Matchable.new(/\A#/))) + end + + def test_multibyte_data + # U+3042 HIRAGANA LETTER A + # U+3044 HIRAGANA LETTER I + # U+3046 HIRAGANA LETTER U + value = "\u3042\u3044\u3046" + with_chunk_size("5") do + assert_equal([[value], [value]], + CSV.parse("#{value}\n#{value}\n", + :skip_lines => /\A#/)) + end + end + + def test_empty_line_and_liberal_parsing + assert_equal([["a", "b"]], + CSV.parse("a,b\n", + :liberal_parsing => true, + :skip_lines => /^$/)) + end + + def test_crlf + assert_equal([["a", "b"]], + CSV.parse("a,b\r\n,\r\n", + :skip_lines => /^,+$/)) + end +end diff --git a/test/csv/parse/test_strip.rb b/test/csv/parse/test_strip.rb new file mode 100644 index 0000000000..c5e35209cc --- /dev/null +++ b/test/csv/parse/test_strip.rb @@ -0,0 +1,112 @@ +# -*- coding: utf-8 -*- +# frozen_string_literal: false + +require_relative "../helper" + +class TestCSVParseStrip < Test::Unit::TestCase + extend DifferentOFS + + def test_both + assert_equal(["a", "b"], + CSV.parse_line(%Q{ a , b }, strip: true)) + end + + def test_left + assert_equal(["a", "b"], + CSV.parse_line(%Q{ a, b}, strip: true)) + end + + def test_right + assert_equal(["a", "b"], + CSV.parse_line(%Q{a ,b }, strip: true)) + end + + def test_middle + assert_equal(["a b"], + CSV.parse_line(%Q{a b}, strip: true)) + end + + def test_quoted + assert_equal([" a ", " b "], + CSV.parse_line(%Q{" a "," b "}, strip: true)) + end + + def test_liberal_parsing + assert_equal([" a ", "b", " c ", " d "], + CSV.parse_line(%Q{" a ", b , " c "," d " }, + strip: true, + liberal_parsing: true)) + end + + def test_string + assert_equal(["a", " b"], + CSV.parse_line(%Q{ a , " b" }, + strip: " ")) + end + + def test_no_quote + assert_equal([" a ", " b "], + CSV.parse_line(%Q{" a ", b }, + strip: %Q{"}, + quote_char: nil)) + end + + def test_do_not_strip_cr + assert_equal([ + ["a", "b "], + ["a", "b "], + ], + CSV.parse(%Q{"a" ,"b " \r} + + %Q{"a" ,"b " \r}, + strip: true)) + end + + def test_do_not_strip_lf + assert_equal([ + ["a", "b "], + ["a", "b "], + ], + CSV.parse(%Q{"a" ,"b " \n} + + %Q{"a" ,"b " \n}, + strip: true)) + end + + def test_do_not_strip_crlf + assert_equal([ + ["a", "b "], + ["a", "b "], + ], + CSV.parse(%Q{"a" ,"b " \r\n} + + %Q{"a" ,"b " \r\n}, + strip: true)) + end + + def test_col_sep_incompatible_true + message = "The provided strip (true) and " \ + "col_sep (\\t) options are incompatible." + assert_raise_with_message(ArgumentError, message) do + CSV.parse_line(%Q{"a"\t"b"\n}, + col_sep: "\t", + strip: true) + end + end + + def test_col_sep_incompatible_string + message = "The provided strip (\\t) and " \ + "col_sep (\\t) options are incompatible." + assert_raise_with_message(ArgumentError, message) do + CSV.parse_line(%Q{"a"\t"b"\n}, + col_sep: "\t", + strip: "\t") + end + end + + def test_col_sep_compatible_string + assert_equal( + ["a", "b"], + CSV.parse_line(%Q{\va\tb\v\n}, + col_sep: "\t", + strip: "\v") + ) + end +end diff --git a/test/csv/parse/test_unconverted_fields.rb b/test/csv/parse/test_unconverted_fields.rb new file mode 100644 index 0000000000..437124ebd3 --- /dev/null +++ b/test/csv/parse/test_unconverted_fields.rb @@ -0,0 +1,117 @@ +# -*- coding: utf-8 -*- +# frozen_string_literal: false + +require_relative "../helper" + +class TestCSVParseUnconvertedFields < Test::Unit::TestCase + extend DifferentOFS + + def setup + super + @custom = lambda {|field| /\A:(\S.*?)\s*\Z/ =~ field ? $1.to_sym : field} + + @headers = ["first", "second", "third"] + @data = <<-CSV +first,second,third +1,2,3 + CSV + end + + + def test_custom + row = CSV.parse_line("Numbers,:integer,1,:float,3.015", + converters: [:numeric, @custom], + unconverted_fields: true) + assert_equal([ + ["Numbers", :integer, 1, :float, 3.015], + ["Numbers", ":integer", "1", ":float", "3.015"], + ], + [ + row, + row.unconverted_fields, + ]) + end + + def test_no_fields + row = CSV.parse_line("\n", + converters: [:numeric, @custom], + unconverted_fields: true) + assert_equal([ + [], + [], + ], + [ + row, + row.unconverted_fields, + ]) + end + + def test_parsed_header + row = CSV.parse_line(@data, + converters: :numeric, + unconverted_fields: true, + headers: :first_row) + assert_equal([ + CSV::Row.new(@headers, + [1, 2, 3]), + ["1", "2", "3"], + ], + [ + row, + row.unconverted_fields, + ]) + end + + def test_return_headers + row = CSV.parse_line(@data, + converters: :numeric, + unconverted_fields: true, + headers: :first_row, + return_headers: true) + assert_equal([ + CSV::Row.new(@headers, + @headers), + @headers, + ], + [ + row, + row.unconverted_fields, + ]) + end + + def test_header_converters + row = CSV.parse_line(@data, + converters: :numeric, + unconverted_fields: true, + headers: :first_row, + return_headers: true, + header_converters: :symbol) + assert_equal([ + CSV::Row.new(@headers.collect(&:to_sym), + @headers), + @headers, + ], + [ + row, + row.unconverted_fields, + ]) + end + + def test_specified_headers + row = CSV.parse_line("\n", + converters: :numeric, + unconverted_fields: true, + headers: %w{my new headers}, + return_headers: true, + header_converters: :symbol) + assert_equal([ + CSV::Row.new([:my, :new, :headers], + ["my", "new", "headers"]), + [], + ], + [ + row, + row.unconverted_fields, + ]) + end +end diff --git a/test/csv/test_csv.rb b/test/csv/test_csv.rb deleted file mode 100644 index 1db540921b..0000000000 --- a/test/csv/test_csv.rb +++ /dev/null @@ -1,1753 +0,0 @@ -require 'test/unit' -require 'tempfile' -require 'fileutils' - -require 'csv' - -class CSV - class StreamBuf - # Let buffer work hard. - remove_const("BufSize") - BufSize = 2 - end -end - - -module CSVTestSupport - def d(data) - data - end -end - - -class TestCSV < Test::Unit::TestCase - file = Tempfile.new("crlf") - file << "\n" - file.open - file.binmode - RSEP = file.read - file.close - - include CSVTestSupport - - class << self - include CSVTestSupport - end - - @@simpleCSVData = { - [nil] => '', - [''] => '""', - [nil, nil] => ',', - [nil, nil, nil] => ',,', - ['foo'] => 'foo', - [','] => '","', - [',', ','] => '",",","', - [';'] => ';', - [';', ';'] => ';,;', - ["\"\r", "\"\r"] => "\"\"\"\r\",\"\"\"\r\"", - ["\"\n", "\"\n"] => "\"\"\"\n\",\"\"\"\n\"", - ["\t"] => "\t", - ["\t", "\t"] => "\t,\t", - ['foo', 'bar'] => 'foo,bar', - ['foo', '"bar"', 'baz'] => 'foo,"""bar""",baz', - ['foo', 'foo,bar', 'baz'] => 'foo,"foo,bar",baz', - ['foo', '""', 'baz'] => 'foo,"""""",baz', - ['foo', '', 'baz'] => 'foo,"",baz', - ['foo', nil, 'baz'] => 'foo,,baz', - [nil, 'foo', 'bar'] => ',foo,bar', - ['foo', 'bar', nil] => 'foo,bar,', - ['foo', "\r", 'baz'] => "foo,\"\r\",baz", - ['foo', "\n", 'baz'] => "foo,\"\n\",baz", - ['foo', "\r\n\r", 'baz'] => "foo,\"\r\n\r\",baz", - ['foo', "\r\n", 'baz'] => "foo,\"\r\n\",baz", - ['foo', "\r.\n", 'baz'] => "foo,\"\r.\n\",baz", - ['foo', "\r\n\n", 'baz'] => "foo,\"\r\n\n\",baz", - ['foo', '"', 'baz'] => 'foo,"""",baz', - } - - @@fullCSVData = { - [d(nil)] => '', - [d('')] => '""', - [d(nil), d(nil)] => ',', - [d(nil), d(nil), d(nil)] => ',,', - [d('foo')] => 'foo', - [d('foo'), d('bar')] => 'foo,bar', - [d('foo'), d('"bar"'), d('baz')] => 'foo,"""bar""",baz', - [d('foo'), d('foo,bar'), d('baz')] => 'foo,"foo,bar",baz', - [d('foo'), d('""'), d('baz')] => 'foo,"""""",baz', - [d('foo'), d(''), d('baz')] => 'foo,"",baz', - [d('foo'), d(nil), d('baz')] => 'foo,,baz', - [d('foo'), d("\r"), d('baz')] => "foo,\"\r\",baz", - [d('foo'), d("\n"), d('baz')] => "foo,\"\n\",baz", - [d('foo'), d("\r\n"), d('baz')] => "foo,\"\r\n\",baz", - [d('foo'), d("\r.\n"), d('baz')] => "foo,\"\r.\n\",baz", - [d('foo'), d("\r\n\n"), d('baz')] => "foo,\"\r\n\n\",baz", - [d('foo'), d('"'), d('baz')] => 'foo,"""",baz', - } - - @@fullCSVDataArray = @@fullCSVData.collect { |key, value| key } - - def ssv2csv(ssvStr, row_sep = nil) - sepConv(ssvStr, ?;, ?,, row_sep) - end - - def csv2ssv(csvStr, row_sep = nil) - sepConv(csvStr, ?,, ?;, row_sep) - end - - def tsv2csv(tsvStr, row_sep = nil) - sepConv(tsvStr, ?\t, ?,, row_sep) - end - - def csv2tsv(csvStr, row_sep = nil) - sepConv(csvStr, ?,, ?\t, row_sep) - end - - def sepConv(srcStr, srcSep, destSep, row_sep = nil) - rows = [] - cols, idx = CSV.parse_row(srcStr, 0, rows, srcSep, row_sep) - destStr = '' - cols = CSV.generate_row(rows, rows.size, destStr, destSep, row_sep) - destStr - end - -public - - def setup - @tmpdir = File.join(Dir.tmpdir, "ruby_test_csv_tmp_#{$$}") - Dir.mkdir(@tmpdir) - @infile = File.join(@tmpdir, 'in.csv') - @infiletsv = File.join(@tmpdir, 'in.tsv') - @emptyfile = File.join(@tmpdir, 'empty.csv') - @outfile = File.join(@tmpdir, 'out.csv') - @bomfile = File.join(@tmpdir, "bom.csv") - @macfile = File.join(@tmpdir, "mac.csv") - - CSV.open(@infile, "wb") do |writer| - @@fullCSVDataArray.each do |row| - writer.add_row(row) - end - end - - CSV.open(@infiletsv, "wb", ?\t) do |writer| - @@fullCSVDataArray.each do |row| - writer.add_row(row) - end - end - - CSV.generate(@emptyfile) do |writer| - # Create empty file. - end - - File.open(@bomfile, "wb") do |f| - f.write("\357\273\277\"foo\"\r\n\"bar\"\r\n") - end - - File.open(@macfile, "wb") do |f| - f.write("\"Avenches\",\"aus Umgebung\"\r\"Bad Hersfeld\",\"Ausgrabung\"") - end - end - - def teardown - FileUtils.rm_rf(@tmpdir) - end - - #### CSV::Reader unit test - - def test_Reader_each - file = File.open(@infile, "rb") - begin - reader = CSV::Reader.create(file) - expectedArray = @@fullCSVDataArray.dup - first = true - ret = reader.each { |row| - if first - assert_instance_of(Array, row) - first = false - end - expected = expectedArray.shift - assert_equal(expected, row) - } - assert_nil(ret, "Return is nil") - assert(expectedArray.empty?) - ensure - file.close - end - - # Illegal format. - reader = CSV::Reader.create("a,b\r\na,b,\"c\"\ra") - assert_raises(CSV::IllegalFormatError) do - reader.each do |row| - end - end - - reader = CSV::Reader.create("a,b\r\n\"") - assert_raises(CSV::IllegalFormatError) do - reader.each do |row| - end - end - end - - def test_Reader_shift - file = File.open(@infile, "rb") - begin - reader = CSV::Reader.create(file) - first = true - checked = 0 - @@fullCSVDataArray.each do |expected| - actual = reader.shift - if first - assert_instance_of(Array, actual) - first = false - end - assert_equal(expected, actual) - checked += 1 - end - assert(checked == @@fullCSVDataArray.size) - ensure - file.close - end - - # Illegal format. - reader = CSV::Reader.create("a,b\r\na,b,\"c\"\ra") - assert_raises(CSV::IllegalFormatError) do - reader.shift - reader.shift - end - - reader = CSV::Reader.create("a,b\r\na,b,\"c\"\ra") - assert_raises(CSV::IllegalFormatError) do - reader.shift - reader.shift - end - end - - def test_Reader_getRow - if CSV::Reader.respond_to?(:allocate) - obj = CSV::Reader.allocate - assert_raises(NotImplementedError) do - row = [] - obj.shift - end - end - end - - def test_IOReader_close_on_terminate - f = File.open(@infile, "r") - reader = CSV::IOReader.create(f) - reader.close - assert(!f.closed?) - f.close - - f = File.open(@infile, "r") - writer = CSV::IOReader.create(f) - writer.close_on_terminate - writer.close - assert(f.closed?) - end - - def test_Reader_close - f = File.open(@infile, "r") - reader = CSV::IOReader.create(f) - reader.close_on_terminate - reader.close - assert(f.closed?) - end - - def test_Reader_s_new - assert_raises(RuntimeError) do - CSV::Reader.new(nil) - end - end - - def test_Reader_s_create - reader = CSV::Reader.create("abc") - assert_instance_of(CSV::StringReader, reader, "With a String") - - file = File.open(@infile, "rb") - reader = CSV::Reader.create(file) - assert_instance_of(CSV::IOReader, reader, 'With an IO') - - obj = Object.new - def obj.sysread(size) - "abc" - end - def obj.read(size) - "abc" - end - reader = CSV::Reader.create(obj) - assert_instance_of(CSV::IOReader, reader, "With not an IO or String") - - # No need to test Tempfile because it's a pseudo IO. I test this here - # fors other tests. - reader = CSV::Reader.create(Tempfile.new("in.csv")) - assert_instance_of(CSV::IOReader, reader, "With an pseudo IO.") - file.close - end - - def test_IOReader_s_create_binmode - file = File.open(@outfile, "wb") - file << "\"\r\n\",\"\r\",\"\n\"\r1,2,3" - file.close - - file = File.open(@outfile, "rb") - begin - reader = CSV::IOReader.new(file, ?,, ?\r) - assert_equal(["\r\n", "\r", "\n"], reader.shift.to_a) - assert_equal(["1", "2", "3"], reader.shift.to_a) - reader.close - ensure - file.close - end - - file = File.open(@outfile, "r") # not "rb" - begin - lfincell = (RSEP == "\n" ? "\r\n" : "\n") - reader = CSV::IOReader.new(file, ?,, ?\r) - assert_equal([lfincell, "\r", "\n"], reader.shift.to_a) - assert_equal(["1", "2", "3"], reader.shift.to_a) - reader.close - ensure - file.close - end - end - - def test_Reader_s_parse - ret = CSV::Reader.parse("a,b,c") { |row| - assert_instance_of(Array, row, "Block parameter") - } - assert_nil(ret, "Return is nil") - - ret = CSV::Reader.parse("a;b;c", ?;) { |row| - assert_instance_of(Array, row, "Block parameter") - } - - file = Tempfile.new("in.csv") - file << "a,b,c" - file.open - ret = CSV::Reader.parse(file) { |row| - assert_instance_of(Array, row, "Block parameter") - } - assert_nil(ret, "Return is nil") - - file = Tempfile.new("in.csv") - file << "a,b,c" - file.open - ret = CSV::Reader.parse(file, ?,) { |row| - assert_instance_of(Array, row, "Block parameter") - } - - # Illegal format. - assert_raises(CSV::IllegalFormatError) do - CSV::Reader.parse("a,b\r\na,b,\"c\"\ra") do |row| - end - end - - assert_raises(CSV::IllegalFormatError) do - CSV::Reader.parse("a,b\r\na,b\"") do |row| - end - end - end - - - #### CSV::Writer unit test - - def test_Writer_s_new - assert_raises(RuntimeError) do - CSV::Writer.new(nil) - end - end - - def test_Writer_s_generate - ret = CSV::Writer.generate(STDOUT) { |writer| - assert_instance_of(CSV::BasicWriter, writer, "Block parameter") - } - - ret = CSV::Writer.generate(STDOUT, ?;) { |writer| - assert_instance_of(CSV::BasicWriter, writer, "Block parameter") - } - - assert_nil(ret, "Return is nil") - end - - def test_Writer_s_create - writer = CSV::Writer.create(STDERR) - assert_instance_of(CSV::BasicWriter, writer, "String") - - writer = CSV::Writer.create(STDERR, ?;) - assert_instance_of(CSV::BasicWriter, writer, "String") - - writer = CSV::Writer.create(Tempfile.new("out.csv")) - assert_instance_of(CSV::BasicWriter, writer, "IO") - end - - def test_Writer_LSHIFT # '<<' - file = Tempfile.new("out.csv") - CSV::Writer.generate(file) do |writer| - ret = writer << ['a', 'b', 'c'] - assert_instance_of(CSV::BasicWriter, ret, 'Return is self') - - writer << [nil, 'e', 'f'] << [nil, nil, ''] - end - file.open - file.binmode - str = file.read - assert_equal("a,b,c#{RSEP},e,f#{RSEP},,\"\"#{RSEP}", str, 'Normal') - - file = Tempfile.new("out2.csv") - CSV::Writer.generate(file) do |writer| - ret = writer << [d('a'), d('b'), d('c')] - assert_instance_of(CSV::BasicWriter, ret, 'Return is self') - - writer << [d(nil), d('e'), d('f')] << [d(nil), d(nil), d('')] - end - file.open - file.binmode - str = file.read - assert_equal("a,b,c#{RSEP},e,f#{RSEP},,\"\"#{RSEP}", str, 'Normal') - end - - def test_Writer_add_row - file = Tempfile.new("out.csv") - CSV::Writer.generate(file) do |writer| - ret = writer.add_row( - [d('a'), d('b'), d('c')]) - assert_instance_of(CSV::BasicWriter, ret, 'Return is self') - - writer.add_row( - [d(nil), d('e'), d('f')] - ).add_row( - [d(nil), d(nil), d('')] - ) - end - file.open - file.binmode - str = file.read - assert_equal("a,b,c#{RSEP},e,f#{RSEP},,\"\"#{RSEP}", str, 'Normal') - end - - def test_Writer_close - f = File.open(@outfile, "w") - writer = CSV::BasicWriter.create(f) - writer.close_on_terminate - writer.close - assert(f.closed?) - end - - def test_BasicWriter_close_on_terminate - f = File.open(@outfile, "w") - writer = CSV::BasicWriter.create(f) - writer.close - assert(!f.closed?) - f.close - - f = File.open(@outfile, "w") - writer = CSV::BasicWriter.new(f) - writer.close_on_terminate - writer.close - assert(f.closed?) - end - - def test_BasicWriter_s_create_binmode - file = File.open(@outfile, "w") # not "wb" - begin - writer = CSV::BasicWriter.new(file, ?,, ?\r) - writer << ["\r\n", "\r", "\n"] - writer << ["1", "2", "3"] - writer.close - ensure - file.close - end - - file = File.open(@outfile, "rb") - str = file.read - file.close - assert_equal("\"\r#{RSEP}\",\"\r\",\"#{RSEP}\"\r1,2,3\r", str) - end - - #### CSV unit test - - def test_s_open_reader - assert_raises(ArgumentError, 'Illegal mode') do - CSV.open("temp", "a") - end - - assert_raises(ArgumentError, 'Illegal mode') do - CSV.open("temp", "a", ?;) - end - - reader = CSV.open(@infile, "r") - assert_instance_of(CSV::IOReader, reader) - reader.close - - reader = CSV.open(@infile, "rb") - assert_instance_of(CSV::IOReader, reader) - reader.close - - reader = CSV.open(@infile, "r", ?;) - assert_instance_of(CSV::IOReader, reader) - reader.close - - CSV.open(@infile, "r") do |row| - assert_instance_of(Array, row) - break - end - - CSV.open(@infiletsv, "r", ?\t) do |row| - assert_instance_of(Array, row) - break - end - - assert_raises(Errno::ENOENT) do - CSV.open("NoSuchFileOrDirectory", "r") - end - - assert_raises(Errno::ENOENT) do - CSV.open("NoSuchFileOrDirectory", "r", ?;) - end - - # Illegal format. - File.open(@outfile, "wb") do |f| - f << "a,b\r\na,b,\"c\"\ra" - end - assert_raises(CSV::IllegalFormatError) do - CSV.open(@outfile, "r") do |row| - end - end - - File.open(@outfile, "wb") do |f| - f << "a,b\r\na,b\"" - end - assert_raises(CSV::IllegalFormatError) do - CSV.open(@outfile, "r") do |row| - end - end - - CSV.open(@emptyfile, "r") do |row| - assert_fail("Must not reach here") - end - end - - def test_s_parse - result = CSV.parse(File.read(@infile)) - assert_instance_of(Array, result) - assert_instance_of(Array, result[0]) - - result = CSV.parse(File.read(@infile)) - assert_instance_of(Array, result) - assert_instance_of(Array, result[0]) - - assert_equal([], CSV.parse("")) - assert_equal([[nil]], CSV.parse("\n")) - - CSV.parse(File.read(@infile)) do |row| - assert_instance_of(Array, row) - break - end - - CSV.parse(File.read(@infiletsv), ?\t) do |row| - assert_instance_of(Array, row) - break - end - - CSV.parse("") do |row| - assert(false) - end - - count = 0 - CSV.parse("\n") do |row| - assert_equal([nil], row) - count += 1 - end - assert_equal(1, count) - - assert_equal([["a|b-c|d"]], CSV.parse("a|b-c|d")) - assert_equal([["a", "b"], ["c", "d"]], CSV.parse("a|b-c|d", "|", "-")) - end - - def test_s_open_writer - writer = CSV.open(@outfile, "w") - assert_instance_of(CSV::BasicWriter, writer) - writer.close - - writer = CSV.open(@outfile, "wb") - assert_instance_of(CSV::BasicWriter, writer) - writer.close - - writer = CSV.open(@outfile, "wb", ?;) - assert_instance_of(CSV::BasicWriter, writer) - writer.close - - CSV.open(@outfile, "w") do |writer| - assert_instance_of(CSV::BasicWriter, writer) - end - - CSV.open(@outfile, "w", ?;) do |writer| - assert_instance_of(CSV::BasicWriter, writer) - end - - begin - CSV.open(@tmpdir, "w") - assert(false) - rescue Exception => ex - assert(ex.is_a?(Errno::EEXIST) || ex.is_a?(Errno::EISDIR) || ex.is_a?(Errno::EACCES)) - end - end - - def test_s_generate - writer = CSV.generate(@outfile) - assert_instance_of(CSV::BasicWriter, writer) - writer.close - - writer = CSV.generate(@outfile, ?;) - assert_instance_of(CSV::BasicWriter, writer) - writer.close - - CSV.generate(@outfile) do |writer| - assert_instance_of(CSV::BasicWriter, writer) - end - - CSV.generate(@outfile, ?;) do |writer| - assert_instance_of(CSV::BasicWriter, writer) - end - - begin - CSV.generate(@tmpdir) - assert(false) - rescue Exception => ex - assert(ex.is_a?(Errno::EEXIST) || ex.is_a?(Errno::EISDIR) || ex.is_a?(Errno::EACCES)) - end - end - - def test_s_generate_line - str = CSV.generate_line([]) - assert_equal('', str, "Extra boundary check.") - - str = CSV.generate_line([], ?;) - assert_equal('', str, "Extra boundary check.") - - @@simpleCSVData.each do |col, str| - buf = CSV.generate_line(col) - assert_equal(str, buf) - end - - @@simpleCSVData.each do |col, str| - buf = CSV.generate_line(col, ?;) - assert_equal(str + "\n", ssv2csv(buf)) - end - - @@simpleCSVData.each do |col, str| - buf = CSV.generate_line(col, ?\t) - assert_equal(str + "\n", tsv2csv(buf)) - end - - str = CSV.generate_line(['a', 'b'], nil, ?|) - assert_equal('a,b', str) - - str = CSV.generate_line(['a', 'b'], nil, "a") - assert_equal('"a",b', str) - end - - def test_s_generate_row - buf = '' - cols = CSV.generate_row([], 0, buf) - assert_equal(0, cols) - assert_equal("\n", buf, "Extra boundary check.") - - buf = '' - cols = CSV.generate_row([], 0, buf, ?;) - assert_equal(0, cols) - assert_equal("\n", buf, "Extra boundary check.") - - buf = '' - cols = CSV.generate_row([], 0, buf, ?\t) - assert_equal(0, cols) - assert_equal("\n", buf, "Extra boundary check.") - - buf = '' - cols = CSV.generate_row([], 0, buf, ?\t, ?|) - assert_equal(0, cols) - assert_equal("|", buf, "Extra boundary check.") - - buf = '' - cols = CSV.generate_row([d('1')], 2, buf) - assert_equal('1,', buf) - - buf = '' - cols = CSV.generate_row([d('1')], 2, buf, ?;) - assert_equal('1;', buf) - - buf = '' - cols = CSV.generate_row([d('1')], 2, buf, ?\t) - assert_equal("1\t", buf) - - buf = '' - cols = CSV.generate_row([d('1')], 2, buf, ?\t, ?|) - assert_equal("1\t", buf) - - buf = '' - cols = CSV.generate_row([d('1'), d('2')], 1, buf) - assert_equal("1\n", buf) - - buf = '' - cols = CSV.generate_row([d('1'), d('2')], 1, buf, ?;) - assert_equal("1\n", buf) - - buf = '' - cols = CSV.generate_row([d('1'), d('2')], 1, buf, ?\t) - assert_equal("1\n", buf) - - buf = '' - cols = CSV.generate_row([d('1'), d('2')], 1, buf, ?\t, ?\n) - assert_equal("1\n", buf) - - buf = '' - cols = CSV.generate_row([d('1'), d('2')], 1, buf, ?\t, ?\r) - assert_equal("1\r", buf) - - buf = '' - cols = CSV.generate_row([d('1'), d('2')], 1, buf, ?\t, ?|) - assert_equal("1|", buf) - - @@fullCSVData.each do |col, str| - buf = '' - cols = CSV.generate_row(col, col.size, buf) - assert_equal(col.size, cols) - assert_equal(str + "\n", buf) - end - - @@fullCSVData.each do |col, str| - buf = '' - cols = CSV.generate_row(col, col.size, buf, ?;) - assert_equal(col.size, cols) - assert_equal(str + "\n", ssv2csv(buf)) - end - - @@fullCSVData.each do |col, str| - buf = '' - cols = CSV.generate_row(col, col.size, buf, ?\t) - assert_equal(col.size, cols) - assert_equal(str + "\n", tsv2csv(buf)) - end - - # row separator - @@fullCSVData.each do |col, str| - buf = '' - cols = CSV.generate_row(col, col.size, buf, ?,, ?|) - assert_equal(col.size, cols) - assert_equal(str + "|", buf) - end - - # col and row separator - @@fullCSVData.each do |col, str| - buf = '' - cols = CSV.generate_row(col, col.size, buf, ?\t, ?|) - assert_equal(col.size, cols) - assert_equal(str + "|", tsv2csv(buf, ?|)) - end - - buf = '' - toBe = '' - cols = 0 - colsToBe = 0 - @@fullCSVData.each do |col, str| - cols += CSV.generate_row(col, col.size, buf) - toBe << str << "\n" - colsToBe += col.size - end - assert_equal(colsToBe, cols) - assert_equal(toBe, buf) - - buf = '' - toBe = '' - cols = 0 - colsToBe = 0 - @@fullCSVData.each do |col, str| - lineBuf = '' - cols += CSV.generate_row(col, col.size, lineBuf, ?;) - buf << ssv2csv(lineBuf) << "\n" - toBe << ssv2csv(lineBuf) << "\n" - colsToBe += col.size - end - assert_equal(colsToBe, cols) - assert_equal(toBe, buf) - - buf = '' - toBe = '' - cols = 0 - colsToBe = 0 - @@fullCSVData.each do |col, str| - lineBuf = '' - cols += CSV.generate_row(col, col.size, lineBuf, ?\t) - buf << tsv2csv(lineBuf) << "\n" - toBe << tsv2csv(lineBuf) << "\n" - colsToBe += col.size - end - assert_equal(colsToBe, cols) - assert_equal(toBe, buf) - - buf = '' - toBe = '' - cols = 0 - colsToBe = 0 - @@fullCSVData.each do |col, str| - lineBuf = '' - cols += CSV.generate_row(col, col.size, lineBuf, ?|) - buf << tsv2csv(lineBuf, ?|) - toBe << tsv2csv(lineBuf, ?|) - colsToBe += col.size - end - assert_equal(colsToBe, cols) - assert_equal(toBe, buf) - end - - def test_s_parse_line - @@simpleCSVData.each do |col, str| - row = CSV.parse_line(str) - assert_instance_of(Array, row) - assert_equal(col.size, row.size) - assert_equal(col, row) - end - - @@simpleCSVData.each do |col, str| - str = csv2ssv(str) - row = CSV.parse_line(str, ?;) - assert_instance_of(Array, row) - assert_equal(col.size, row.size, str.inspect) - assert_equal(col, row, str.inspect) - end - - @@simpleCSVData.each do |col, str| - str = csv2tsv(str) - row = CSV.parse_line(str, ?\t) - assert_instance_of(Array, row) - assert_equal(col.size, row.size) - assert_equal(col, row) - end - - assert_equal(['a', 'b', 'c'], CSV.parse_line("a,b,c", nil, nil)) - assert_equal(['a', nil], CSV.parse_line("a,b,c", nil, ?b)) - assert_equal(['a', 'b', nil], CSV.parse_line("a,b,c", nil, "c")) - assert_equal([nil], CSV.parse_line("")) - assert_equal([nil], CSV.parse_line("\n")) - assert_equal([""], CSV.parse_line("\"\"\n")) - - # Illegal format. - buf = [] - row = CSV.parse_line("a,b,\"c\"\ra") - assert_instance_of(Array, row) - assert_equal(0, row.size) - - buf = Array.new - row = CSV.parse_line("a;b;\"c\"\ra", ?;) - assert_instance_of(Array, row) - assert_equal(0, row.size) - - buf = Array.new - row = CSV.parse_line("a\tb\t\"c\"\ra", ?\t) - assert_instance_of(Array, row) - assert_equal(0, row.size) - - row = CSV.parse_line("a,b\"") - assert_instance_of(Array, row) - assert_equal(0, row.size) - - row = CSV.parse_line("a;b\"", ?;) - assert_instance_of(Array, row) - assert_equal(0, row.size) - - row = CSV.parse_line("a\tb\"", ?\t) - assert_instance_of(Array, row) - assert_equal(0, row.size) - - row = CSV.parse_line("\"a,b\"\r,") - assert_instance_of(Array, row) - assert_equal(0, row.size) - - row = CSV.parse_line("\"a;b\"\r;", ?;) - assert_instance_of(Array, row) - assert_equal(0, row.size) - - row = CSV.parse_line("\"a\tb\"\r\t", ?\t) - assert_instance_of(Array, row) - assert_equal(0, row.size) - - row = CSV.parse_line("\"a,b\"\r\"") - assert_instance_of(Array, row) - assert_equal(0, row.size) - - row = CSV.parse_line("\"a;b\"\r\"", ?;) - assert_instance_of(Array, row) - assert_equal(0, row.size) - - row = CSV.parse_line("\"a\tb\"\r\"", ?\t) - assert_instance_of(Array, row) - assert_equal(0, row.size) - end - - def test_s_parse_row - @@fullCSVData.each do |col, str| - buf = Array.new - cols, idx = CSV.parse_row(str + "\r\n", 0, buf) - assert_equal(cols, buf.size, "Reported size.") - assert_equal(col.size, buf.size, "Size.") - assert_equal(col, buf, str.inspect) - - buf = Array.new - cols, idx = CSV.parse_row(str + "\n", 0, buf, ?,, ?\n) - assert_equal(cols, buf.size, "Reported size.") - assert_equal(col.size, buf.size, "Size.") - assert_equal(col, buf, str.inspect) - - # separator: | - buf = Array.new - cols, idx = CSV.parse_row(str + "|", 0, buf, ?,) - assert_not_equal(col, buf) - buf = Array.new - cols, idx = CSV.parse_row(str + "|", 0, buf, ?,, ?|) - assert_equal(cols, buf.size, "Reported size.") - assert_equal(col.size, buf.size, "Size.") - assert_equal(col, buf, str.inspect) - end - - @@fullCSVData.each do |col, str| - str = csv2ssv(str) - buf = Array.new - cols, idx = CSV.parse_row(str + "\r\n", 0, buf, ?;) - assert_equal(cols, buf.size, "Reported size.") - assert_equal(col.size, buf.size, "Size.") - assert_equal(col, buf, str) - end - - @@fullCSVData.each do |col, str| - str = csv2tsv(str) - buf = Array.new - cols, idx = CSV.parse_row(str + "\r\n", 0, buf, ?\t) - assert_equal(cols, buf.size, "Reported size.") - assert_equal(col.size, buf.size, "Size.") - assert_equal(col, buf, str) - end - - @@fullCSVData.each do |col, str| - str = csv2tsv(str, ?|) - buf = Array.new - cols, idx = CSV.parse_row(str + "|", 0, buf, ?\t, ?|) - assert_equal(cols, buf.size, "Reported size.") - assert_equal(col.size, buf.size, "Size.") - assert_equal(col, buf, str) - end - - buf = [] - CSV.parse_row("a,b,c", 0, buf, nil, nil) - assert_equal(['a', 'b', 'c'], buf) - - buf = [] - CSV.parse_row("a,b,c", 0, buf, nil, ?b) - assert_equal(['a', nil], buf) - - buf = [] - CSV.parse_row("a,b,c", 0, buf, nil, "c") - assert_equal(['a', 'b', nil], buf) - - buf = Array.new - cols, idx = CSV.parse_row("a,b,\"c\r\"", 0, buf) - assert_equal(["a", "b", "c\r"], buf.to_a) - - buf = Array.new - cols, idx = CSV.parse_row("a;b;\"c\r\"", 0, buf, ?;) - assert_equal(["a", "b", "c\r"], buf.to_a) - - buf = Array.new - cols, idx = CSV.parse_row("a\tb\t\"c\r\"", 0, buf, ?\t) - assert_equal(["a", "b", "c\r"], buf.to_a) - - buf = Array.new - cols, idx = CSV.parse_row("a,b,c\n", 0, buf, ?,, ?\n) - assert_equal(["a", "b", "c"], buf.to_a) - - buf = Array.new - cols, idx = CSV.parse_row("a\tb\tc\n", 0, buf, ?\t, ?\n) - assert_equal(["a", "b", "c"], buf.to_a) - - # Illegal format. - buf = Array.new - cols, idx = CSV.parse_row("a,b,c\"", 0, buf) - assert_equal(0, cols, "Illegal format; unbalanced double-quote.") - - buf = Array.new - cols, idx = CSV.parse_row("a;b;c\"", 0, buf, ?;) - assert_equal(0, cols, "Illegal format; unbalanced double-quote.") - - buf = Array.new - cols, idx = CSV.parse_row("a,b,\"c\"\ra", 0, buf) - assert_equal(0, cols) - assert_equal(0, idx) - - buf = Array.new - cols, idx = CSV.parse_row("a,b,\"c\"\ra", 0, buf, ?;) - assert_equal(0, cols) - assert_equal(0, idx) - - buf = Array.new - cols, idx = CSV.parse_row("a,b\"", 0, buf) - assert_equal(0, cols) - assert_equal(0, idx) - - buf = Array.new - cols, idx = CSV.parse_row("a;b\"", 0, buf, ?;) - assert_equal(0, cols) - assert_equal(0, idx) - - buf = Array.new - cols, idx = CSV.parse_row("\"a,b\"\r,", 0, buf) - assert_equal(0, cols) - assert_equal(0, idx) - - buf = Array.new - cols, idx = CSV.parse_row("a\r,", 0, buf) - assert_equal(0, cols) - assert_equal(0, idx) - - buf = Array.new - cols, idx = CSV.parse_row("a\r", 0, buf) - assert_equal(0, cols) - assert_equal(0, idx) - - buf = Array.new - cols, idx = CSV.parse_row("a\rbc", 0, buf) - assert_equal(0, cols) - assert_equal(0, idx) - - buf = Array.new - cols, idx = CSV.parse_row("a\r\"\"", 0, buf) - assert_equal(0, cols) - assert_equal(0, idx) - - buf = Array.new - cols, idx = CSV.parse_row("a\r\rabc,", 0, buf) - assert_equal(0, cols) - assert_equal(0, idx) - - buf = Array.new - cols, idx = CSV.parse_row("\"a;b\"\r;", 0, buf, ?;) - assert_equal(0, cols) - assert_equal(0, idx) - - buf = Array.new - cols, idx = CSV.parse_row("\"a,b\"\r\"", 0, buf) - assert_equal(0, cols) - assert_equal(0, idx) - - buf = Array.new - cols, idx = CSV.parse_row("\"a;b\"\r\"", 0, buf, ?;) - assert_equal(0, cols) - assert_equal(0, idx) - end - - def test_s_parse_rowEOF - @@fullCSVData.each do |col, str| - if str == '' - # String "" is not allowed. - next - end - buf = Array.new - cols, idx = CSV.parse_row(str, 0, buf) - assert_equal(col.size, cols, "Reported size.") - assert_equal(col.size, buf.size, "Size.") - assert_equal(col, buf) - end - end - - def test_s_parse_rowConcat - buf = '' - toBe = [] - @@fullCSVData.each do |col, str| - buf << str << "\r\n" - toBe.concat(col) - end - idx = 0 - cols = 0 - parsed = Array.new - parsedCols = 0 - begin - cols, idx = CSV.parse_row(buf, idx, parsed) - parsedCols += cols - end while cols > 0 - assert_equal(toBe.size, parsedCols) - assert_equal(toBe.size, parsed.size) - assert_equal(toBe, parsed) - - buf = '' - toBe = [] - @@fullCSVData.each do |col, str| - buf << str << "\n" - toBe.concat(col) - end - idx = 0 - cols = 0 - parsed = Array.new - parsedCols = 0 - begin - cols, idx = CSV.parse_row(buf, idx, parsed, ?,, ?\n) - parsedCols += cols - end while cols > 0 - assert_equal(toBe.size, parsedCols) - assert_equal(toBe.size, parsed.size) - assert_equal(toBe, parsed) - - buf = '' - toBe = [] - @@fullCSVData.sort { |a, b| - a[0].length <=> b[0].length - }.each do |col, str| - buf << str << "\n" - toBe.concat(col) - end - idx = 0 - cols = 0 - parsed = Array.new - parsedCols = 0 - begin - cols, idx = CSV.parse_row(buf, idx, parsed, ?,, ?\n) - parsedCols += cols - end while cols > 0 - assert_equal(toBe.size, parsedCols) - assert_equal(toBe.size, parsed.size) - assert_equal(toBe, parsed) - - buf = '' - toBe = [] - @@fullCSVData.each do |col, str| - buf << str << "|" - toBe.concat(col) - end - idx = 0 - cols = 0 - parsed = [] - parsedCols = 0 - begin - cols, idx = CSV.parse_row(buf, idx, parsed, ?,, ?|) - parsedCols += cols - end while cols > 0 - assert_equal(toBe.size, parsedCols) - assert_equal(toBe.size, parsed.size) - assert_equal(toBe, parsed) - end - - def test_utf8 - rows = [] - CSV.open(@bomfile, "r") do |row| - rows << row.to_a - end - assert_equal([["foo"], ["bar"]], rows) - - rows = [] - file = File.open(@bomfile) - CSV::Reader.parse(file) do |row| - rows << row.to_a - end - assert_equal([["foo"], ["bar"]], rows) - file.close - end - - def test_macCR - rows = [] - CSV.open(@macfile, "r", ?,, ?\r) do |row| - rows << row.to_a - end - assert_equal([["Avenches", "aus Umgebung"], ["Bad Hersfeld", "Ausgrabung"]], rows) - - rows = [] - assert_raises(CSV::IllegalFormatError) do - CSV.open(@macfile, "r") do |row| - rows << row.to_a - end - assert_equal([["Avenches", "aus Umgebung\r\"Bad Hersfeld", "Ausgrabung"]], rows) - end - - rows = [] - file = File.open(@macfile) - begin - CSV::Reader.parse(file, ?,, ?\r) do |row| - rows << row.to_a - end - assert_equal([["Avenches", "aus Umgebung"], ["Bad Hersfeld", "Ausgrabung"]], rows) - ensure - file.close - end - - rows = [] - file = File.open(@macfile) - begin - assert_raises(CSV::IllegalFormatError) do - CSV::Reader.parse(file, ?,) do |row| - rows << row.to_a - end - assert_equal([["Avenches", "aus Umgebung\r\"Bad Hersfeld", "Ausgrabung"]], rows) - end - ensure - file.close - end - end - - - #### CSV unit test - - InputStreamPattern = '0123456789' - InputStreamPatternSize = InputStreamPattern.size - def expChar(idx) - InputStreamPattern[idx % InputStreamPatternSize] - end - - def expStr(idx, n) - if n > InputStreamPatternSize - InputStreamPattern + expStr(0, n - InputStreamPatternSize) - else - InputStreamPattern[idx % InputStreamPatternSize, n] - end - end - - def setupInputStream(size, bufSize = nil) - setBufSize(bufSize) if bufSize - m = ((size / InputStreamPatternSize) + 1).to_i - File.open(@outfile, "wb") do |f| - f << (InputStreamPattern * m)[0, size] - end - file = File.open(@outfile, "rb") - buf = CSV::IOBuf.new(file) - if block_given? - yield(buf) - file.close - nil - else - buf - end - end - - def setBufSize(size) - CSV::StreamBuf.module_eval('remove_const("BufSize")') - CSV::StreamBuf.module_eval("BufSize = #{ size }") - end - - class StrBuf < CSV::StreamBuf - private - def initialize(string) - @str = string - @idx = 0 - super() - end - - def read(size) - str = @str[@idx, size] - if str.empty? - nil - else - @idx += str.size - str - end - end - end - - class ErrBuf < CSV::StreamBuf - class Error < RuntimeError; end - private - def initialize - @first = true - super() - end - - def read(size) - if @first - @first = false - "a" * size - else - raise ErrBuf::Error.new - end - end - end - - def test_StreamBuf_MyBuf - # At first, check ruby's behaviour. - s = "abc" - assert_equal(?a, s[0]) - assert_equal(?b, s[1]) - assert_equal(?c, s[2]) - assert_equal(nil, s[3]) - assert_equal("a", s[0, 1]) - assert_equal("b", s[1, 1]) - assert_equal("c", s[2, 1]) - assert_equal("", s[3, 1]) - assert_equal(nil, s[4, 1]) - - s = StrBuf.new("abc") - assert_equal(?a, s[0]) - assert_equal(?b, s.get(1)) - assert_equal(?c, s[2]) - assert_equal(nil, s.get(3)) - assert_equal("a", s[0, 1]) - assert_equal("b", s.get(1, 1)) - assert_equal("c", s[2, 1]) - assert_equal("", s.get(3, 1)) - assert_equal(nil, s[4, 1]) - - dropped = s.drop(1) - assert_equal(1, dropped) - assert_equal(?b, s[0]) - assert(!s.is_eos?) - dropped = s.drop(1) - assert_equal(1, dropped) - assert_equal(?c, s[0]) - assert(!s.is_eos?) - dropped = s.drop(1) - assert_equal(1, dropped) - assert_equal(nil, s[0]) - assert(s.is_eos?) - dropped = s.drop(1) - assert_equal(0, dropped) - assert_equal(nil, s[0]) - assert(s.is_eos?) - - s = StrBuf.new("") - assert_equal(nil, s[0]) - - s = StrBuf.new("") - dropped = s.drop(1) - assert_equal(0, dropped) - - assert_raises(TestCSV::ErrBuf::Error) do - s = ErrBuf.new - s[1024] - end - - assert_raises(TestCSV::ErrBuf::Error) do - s = ErrBuf.new - s.drop(1024) - end - end - - def test_StreamBuf_AREF # '[idx]' - setupInputStream(22, 1024) do |s| - [0, 1, 9, 10, 19, 20, 21].each do |idx| - assert_equal(expChar(idx), s[idx], idx.to_s) - end - [22, 23].each do |idx| - assert_equal(nil, s[idx], idx.to_s) - end - assert_equal(nil, s[-1]) - end - - setupInputStream(22, 1) do |s| - [0, 1, 9, 10, 19, 20, 21].each do |idx| - assert_equal(expChar(idx), s[idx], idx.to_s) - end - [22, 23].each do |idx| - assert_equal(nil, s[idx], idx.to_s) - end - end - - setupInputStream(1024, 1) do |s| - [1023, 0].each do |idx| - assert_equal(expChar(idx), s[idx], idx.to_s) - end - [1024, 1025].each do |idx| - assert_equal(nil, s[idx], idx.to_s) - end - end - - setupInputStream(1, 1) do |s| - [0].each do |idx| - assert_equal(expChar(idx), s[idx], idx.to_s) - end - [1, 2].each do |idx| - assert_equal(nil, s[idx], idx.to_s) - end - end - end - - def test_StreamBuf_AREF_n # '[idx, n]' - # At first, check ruby's behaviour. - assert_equal("", "abc"[3, 1]) - assert_equal(nil, "abc"[4, 1]) - - setupInputStream(22, 1024) do |s| - [0, 1, 9, 10, 19, 20, 21].each do |idx| - assert_equal(expStr(idx, 1), s[idx, 1], idx.to_s) - end - assert_equal("", s[22, 1]) - assert_equal(nil, s[23, 1]) - end - - setupInputStream(22, 1) do |s| - [0, 1, 9, 10, 19, 20, 21].each do |idx| - assert_equal(expStr(idx, 1), s[idx, 1], idx.to_s) - end - assert_equal("", s[22, 1]) - assert_equal(nil, s[23, 1]) - end - - setupInputStream(1024, 1) do |s| - [1023, 0].each do |idx| - assert_equal(expStr(idx, 1), s[idx, 1], idx.to_s) - end - assert_equal("", s[1024, 1]) - assert_equal(nil, s[1025, 1]) - end - - setupInputStream(1, 1) do |s| - [0].each do |idx| - assert_equal(expStr(idx, 1), s[idx, 1], idx.to_s) - end - assert_equal("", s[1, 1]) - assert_equal(nil, s[2, 1]) - end - - setupInputStream(22, 11) do |s| - [0, 1, 10, 11, 20].each do |idx| - assert_equal(expStr(idx, 2), s[idx, 2], idx.to_s) - end - assert_equal(expStr(21, 1), s[21, 2]) - - assert_equal(expStr(0, 12), s[0, 12]) - assert_equal(expStr(10, 12), s[10, 12]) - assert_equal(expStr(10, 12), s[10, 13]) - assert_equal(expStr(10, 12), s[10, 14]) - assert_equal(expStr(10, 12), s[10, 1024]) - - assert_equal(nil, s[0, -1]) - assert_equal(nil, s[21, -1]) - - assert_equal(nil, s[-1, 10]) - assert_equal(nil, s[-1, -1]) - end - end - - def test_StreamBuf_get - setupInputStream(22, 1024) do |s| - [0, 1, 9, 10, 19, 20, 21].each do |idx| - assert_equal(expChar(idx), s.get(idx), idx.to_s) - end - [22, 23].each do |idx| - assert_equal(nil, s.get(idx), idx.to_s) - end - assert_equal(nil, s.get(-1)) - end - end - - def test_StreamBuf_get_n - setupInputStream(22, 1024) do |s| - [0, 1, 9, 10, 19, 20, 21].each do |idx| - assert_equal(expStr(idx, 1), s.get(idx, 1), idx.to_s) - end - assert_equal("", s.get(22, 1)) - assert_equal(nil, s.get(23, 1)) - - assert_equal(nil, s.get(-1, 1)) - assert_equal(nil, s.get(-1, -1)) - end - end - - def test_StreamBuf_drop - setupInputStream(22, 1024) do |s| - assert_equal(expChar(0), s[0]) - assert_equal(expChar(21), s[21]) - assert_equal(nil, s[22]) - - dropped = s.drop(-1) - assert_equal(0, dropped) - assert_equal(expChar(0), s[0]) - - dropped = s.drop(0) - assert_equal(0, dropped) - assert_equal(expChar(0), s[0]) - - dropped = s.drop(1) - assert_equal(1, dropped) - assert_equal(expChar(1), s[0]) - assert_equal(expChar(2), s[1]) - - dropped = s.drop(1) - assert_equal(1, dropped) - assert_equal(expChar(2), s[0]) - assert_equal(expChar(3), s[1]) - end - - setupInputStream(4, 2) do |s| - dropped = s.drop(2) - assert_equal(2, dropped) - assert_equal(expChar(2), s[0]) - assert_equal(expChar(3), s[1]) - dropped = s.drop(1) - assert_equal(1, dropped) - assert_equal(expChar(3), s[0]) - assert_equal(nil, s[1]) - dropped = s.drop(1) - assert_equal(1, dropped) - assert_equal(nil, s[0]) - assert_equal(nil, s[1]) - dropped = s.drop(0) - assert_equal(0, dropped) - assert_equal(nil, s[0]) - assert_equal(nil, s[1]) - end - - setupInputStream(6, 3) do |s| - dropped = s.drop(2) - assert_equal(2, dropped) - dropped = s.drop(2) - assert_equal(2, dropped) - assert_equal(expChar(4), s[0]) - assert_equal(expChar(5), s[1]) - dropped = s.drop(3) - assert_equal(2, dropped) - assert_equal(nil, s[0]) - assert_equal(nil, s[1]) - end - end - - def test_StreamBuf_is_eos? - setupInputStream(3, 1024) do |s| - assert(!s.is_eos?) - s.drop(1) - assert(!s.is_eos?) - s.drop(1) - assert(!s.is_eos?) - s.drop(1) - assert(s.is_eos?) - s.drop(1) - assert(s.is_eos?) - end - - setupInputStream(3, 2) do |s| - assert(!s.is_eos?) - s.drop(1) - assert(!s.is_eos?) - s.drop(1) - assert(!s.is_eos?) - s.drop(1) - assert(s.is_eos?) - s.drop(1) - assert(s.is_eos?) - end - end - - def test_StreamBuf_s_new - # NotImplementedError should be raised from StreamBuf#read. - assert_raises(NotImplementedError) do - CSV::StreamBuf.new - end - end - - def test_IOBuf_close - f = File.open(@outfile, "wb") - f << "tst" - f.close - - f = File.open(@outfile, "rb") - iobuf = CSV::IOBuf.new(f) - iobuf.close - assert(true) # iobuf.close does not raise any exception. - f.close - end - - def test_IOBuf_s_new - iobuf = CSV::IOBuf.new(Tempfile.new("in.csv")) - assert_instance_of(CSV::IOBuf, iobuf) - end - - - #### CSV functional test - - # sample data - # - # 1 2 3 4 5 6 7 8 - # +------+-------+---------+-------+--------+------+----+------+ - # | foo | "foo" | foo,bar | "" |(empty) |(null)| \r | \r\n | - # +------+-------+---------+-------+--------+------+----+------+ - # | NaHi | "Na" | Na,Hi | \r.\n | \r\n\n | " | \n | \r\n | - # +------+-------+---------+-------+--------+------+----+------+ - # - def test_s_parseAndCreate - colSize = 8 - csvStr = "foo,!!!foo!!!,!foo,bar!,!!!!!!,!!,,!\r!,!\r\n!\nNaHi,!!!Na!!!,!Na,Hi!,!\r.\n!,!\r\n\n!,!!!!,!\n!,!\r\n!".gsub!('!', '"') - csvStrTerminated = csvStr + "\n" - - myStr = csvStr.dup - res1 = []; res2 = [] - idx = 0 - col, idx = CSV::parse_row(myStr, 0, res1) - col, idx = CSV::parse_row(myStr, idx, res2) - - buf = '' - col = CSV::generate_row(res1, colSize, buf) - col = CSV::generate_row(res2, colSize, buf) - assert_equal(csvStrTerminated, buf) - - parsed = [] - CSV::Reader.parse(csvStrTerminated) do |row| - parsed << row - end - - buf = '' - CSV::Writer.generate(buf) do |writer| - parsed.each do |row| - writer.add_row(row) - end - end - assert_equal(csvStrTerminated, buf) - - buf = '' - CSV::Writer.generate(buf) do |writer| - parsed.each do |row| - writer << row - end - end - assert_equal(csvStrTerminated, buf) - end - - def test_writer_fs_rs_generate - buf = '' - CSV::Writer.generate(buf, ",,") do |writer| - writer << [] - end - assert_equal("\n", buf) - - buf = '' - CSV::Writer.generate(buf, ",,") do |writer| - writer << [] << [] - end - assert_equal("\n\n", buf) - - buf = '' - CSV::Writer.generate(buf, ",,") do |writer| - writer << [1] - end - assert_equal("1\n", buf) - - buf = '' - CSV::Writer.generate(buf, ",,") do |writer| - writer << [1, 2, 3] - writer << [4, ",,", 5] - end - assert_equal("1,,2,,3\n4,,\",,\",,5\n", buf) - - buf = '' - CSV::Writer.generate(buf, ",,:", ",,;") do |writer| - writer << [nil, nil, nil] - writer << [nil, ",,", nil] - end - assert_equal(",,:,,:,,;,,:,,,,:,,;", buf) - - buf = '' - CSV::Writer.generate(buf, "---") do |writer| - writer << [1, 2, 3] - writer << [4, "---\"---", 5] - end - assert_equal("1---2---3\n4---\"---\"\"---\"---5\n", buf) - - buf = '' - CSV::Writer.generate(buf, nil) do |writer| - writer << [1, 2, 3] - writer << [4, ",\",", 5] - end - assert_equal("1,2,3\n4,\",\"\",\",5\n", buf) - end - - def test_writer_fs_rs_parse - reader = CSV::Reader.create('a||b--c||d', '||', '--') - assert_equal(['a', 'b'], reader.shift) - assert_equal(['c', 'd'], reader.shift) - - reader = CSV::Reader.create("a@|b@-c@|d", "@|", "@-") - assert_equal(['a', 'b'], reader.shift) - assert_equal(['c', 'd'], reader.shift) - - reader = CSV::Reader.create("ababfsababrs", "abfs", "abrs") - assert_equal(['ab', 'ab'], reader.shift) - - reader = CSV::Reader.create('"ab"abfsababrs', "abfs", "abrs") - assert_equal(['ab', 'ab'], reader.shift) - - reader = CSV::Reader.create('"ab"aabfsababrs', "abfs", "abrs") - assert_raises(CSV::IllegalFormatError) do - reader.shift - end - - # fs match while matching rs progress - reader = CSV::Reader.create("ab,ababrs", nil, "abrs") - assert_equal(['ab', 'ab'], reader.shift) - - reader = CSV::Reader.create(',ababrs', nil, "abrs") - assert_equal([nil, 'ab'], reader.shift) - - reader = CSV::Reader.create('"",ababrs', nil, "abrs") - assert_equal(['', 'ab'], reader.shift) - - reader = CSV::Reader.create('ab,"ab"abrs', nil, "abrs") - assert_equal(['ab', 'ab'], reader.shift) - - reader = CSV::Reader.create('ab,"ab"aabrs', nil, "abrs") - assert_raises(CSV::IllegalFormatError) do - reader.shift - end - - # rs match while matching fs progress - reader = CSV::Reader.create("ab|abc", 'ab-', "ab|") - assert_equal([nil], reader.shift) - assert_equal(['abc'], reader.shift) - - reader = CSV::Reader.create("ab\ncdabcef", "abc", "\n") - assert_equal(['ab'], reader.shift) - assert_equal(['cd', "ef"], reader.shift) - - # EOF while fs/rs matching - reader = CSV::Reader.create("ab", 'ab-', "xyz") - assert_equal(['ab'], reader.shift) - - reader = CSV::Reader.create("ab", 'xyz', "ab|") - assert_equal(['ab'], reader.shift) - - reader = CSV::Reader.create("ab", 'ab-', "ab|") - assert_equal(['ab'], reader.shift) - - reader = CSV::Reader.create(",,:,,:,,;,,:,,,,:,,;", ",,:", ",,;") - assert_equal([nil, nil, nil], reader.shift) - assert_equal([nil, ",,", nil], reader.shift) - end - - def test_s_foreach - File.open(@outfile, "w") do |f| - f << "1,2,3\n4,5,6" - end - row = [] - CSV.foreach(@outfile) { |line| - row << line - } - assert_equal([['1', '2', '3'], ['4', '5', '6']], row) - - File.open(@outfile, "w") do |f| - f << "1,2,3\r4,5,6" - end - row = [] - CSV.foreach(@outfile, "\r") { |line| - row << line - } - assert_equal([['1', '2', '3'], ['4', '5', '6']], row) - end - - def test_s_readlines - File.open(@outfile, "w") do |f| - f << "1,2,3\n4,5,6" - end - assert_equal([["1", "2", "3"], ["4", "5", "6"]], CSV.readlines(@outfile)) - assert_equal([["1", "2", nil], [nil, "5", "6"]], CSV.readlines(@outfile, "3\n4")) - end - - def test_s_read - File.open(@outfile, "w") do |f| - f << "1,2,3\n4,5,6" - end - assert_equal([["1", "2", "3"], ["4", "5", "6"]], CSV.read(@outfile)) - assert_equal([["1", "2"]], CSV.read(@outfile, 3)) - assert_equal([[nil], ["4", nil]], CSV.read(@outfile, 3, 5)) - end -end diff --git a/test/csv/test_data_converters.rb b/test/csv/test_data_converters.rb new file mode 100644 index 0000000000..c20a5d1f4b --- /dev/null +++ b/test/csv/test_data_converters.rb @@ -0,0 +1,190 @@ +# -*- coding: utf-8 -*- +# frozen_string_literal: false + +require_relative "helper" + +class TestCSVDataConverters < Test::Unit::TestCase + extend DifferentOFS + + def setup + super + @win_safe_time_str = Time.now.strftime("%a %b %d %H:%M:%S %Y") + end + + def test_builtin_integer_converter + # does convert + [-5, 1, 10000000000].each do |n| + assert_equal(n, CSV::Converters[:integer][n.to_s]) + end + + # does not convert + (%w{junk 1.0} + [""]).each do |str| + assert_equal(str, CSV::Converters[:integer][str]) + end + end + + def test_builtin_float_converter + # does convert + [-5.1234, 0, 2.3e-11].each do |n| + assert_equal(n, CSV::Converters[:float][n.to_s]) + end + + # does not convert + (%w{junk 1..0 .015F} + [""]).each do |str| + assert_equal(str, CSV::Converters[:float][str]) + end + end + + def test_builtin_date_converter + # does convert + assert_instance_of( + Date, + CSV::Converters[:date][@win_safe_time_str.sub(/\d+:\d+:\d+ /, "")] + ) + + # does not convert + assert_instance_of(String, CSV::Converters[:date]["junk"]) + end + + def test_builtin_date_time_converter + # does convert + assert_instance_of( DateTime, + CSV::Converters[:date_time][@win_safe_time_str] ) + + # does not convert + assert_instance_of(String, CSV::Converters[:date_time]["junk"]) + end + + def test_builtin_date_time_converter_iso8601_date + iso8601_string = "2018-01-14" + datetime = DateTime.new(2018, 1, 14) + assert_equal(datetime, + CSV::Converters[:date_time][iso8601_string]) + end + + def test_builtin_date_time_converter_iso8601_minute + iso8601_string = "2018-01-14T22:25" + datetime = DateTime.new(2018, 1, 14, 22, 25) + assert_equal(datetime, + CSV::Converters[:date_time][iso8601_string]) + end + + def test_builtin_date_time_converter_iso8601_second + iso8601_string = "2018-01-14T22:25:19" + datetime = DateTime.new(2018, 1, 14, 22, 25, 19) + assert_equal(datetime, + CSV::Converters[:date_time][iso8601_string]) + end + + def test_builtin_date_time_converter_iso8601_under_second + iso8601_string = "2018-01-14T22:25:19.1" + datetime = DateTime.new(2018, 1, 14, 22, 25, 19.1) + assert_equal(datetime, + CSV::Converters[:date_time][iso8601_string]) + end + + def test_builtin_date_time_converter_iso8601_under_second_offset + iso8601_string = "2018-01-14T22:25:19.1+09:00" + datetime = DateTime.new(2018, 1, 14, 22, 25, 19.1, "+9") + assert_equal(datetime, + CSV::Converters[:date_time][iso8601_string]) + end + + def test_builtin_date_time_converter_iso8601_offset + iso8601_string = "2018-01-14T22:25:19+09:00" + datetime = DateTime.new(2018, 1, 14, 22, 25, 19, "+9") + assert_equal(datetime, + CSV::Converters[:date_time][iso8601_string]) + end + + def test_builtin_date_time_converter_iso8601_utc + iso8601_string = "2018-01-14T22:25:19Z" + datetime = DateTime.new(2018, 1, 14, 22, 25, 19) + assert_equal(datetime, + CSV::Converters[:date_time][iso8601_string]) + end + + def test_builtin_date_time_converter_rfc3339_minute + rfc3339_string = "2018-01-14 22:25" + datetime = DateTime.new(2018, 1, 14, 22, 25) + assert_equal(datetime, + CSV::Converters[:date_time][rfc3339_string]) + end + + def test_builtin_date_time_converter_rfc3339_second + rfc3339_string = "2018-01-14 22:25:19" + datetime = DateTime.new(2018, 1, 14, 22, 25, 19) + assert_equal(datetime, + CSV::Converters[:date_time][rfc3339_string]) + end + + def test_builtin_date_time_converter_rfc3339_under_second + rfc3339_string = "2018-01-14 22:25:19.1" + datetime = DateTime.new(2018, 1, 14, 22, 25, 19.1) + assert_equal(datetime, + CSV::Converters[:date_time][rfc3339_string]) + end + + def test_builtin_date_time_converter_rfc3339_under_second_offset + rfc3339_string = "2018-01-14 22:25:19.1+09:00" + datetime = DateTime.new(2018, 1, 14, 22, 25, 19.1, "+9") + assert_equal(datetime, + CSV::Converters[:date_time][rfc3339_string]) + end + + def test_builtin_date_time_converter_rfc3339_offset + rfc3339_string = "2018-01-14 22:25:19+09:00" + datetime = DateTime.new(2018, 1, 14, 22, 25, 19, "+9") + assert_equal(datetime, + CSV::Converters[:date_time][rfc3339_string]) + end + + def test_builtin_date_time_converter_rfc3339_utc + rfc3339_string = "2018-01-14 22:25:19Z" + datetime = DateTime.new(2018, 1, 14, 22, 25, 19) + assert_equal(datetime, + CSV::Converters[:date_time][rfc3339_string]) + end + + def test_builtin_date_time_converter_rfc3339_tab_minute + rfc3339_string = "2018-01-14\t22:25" + datetime = DateTime.new(2018, 1, 14, 22, 25) + assert_equal(datetime, + CSV::Converters[:date_time][rfc3339_string]) + end + + def test_builtin_date_time_converter_rfc3339_tab_second + rfc3339_string = "2018-01-14\t22:25:19" + datetime = DateTime.new(2018, 1, 14, 22, 25, 19) + assert_equal(datetime, + CSV::Converters[:date_time][rfc3339_string]) + end + + def test_builtin_date_time_converter_rfc3339_tab_under_second + rfc3339_string = "2018-01-14\t22:25:19.1" + datetime = DateTime.new(2018, 1, 14, 22, 25, 19.1) + assert_equal(datetime, + CSV::Converters[:date_time][rfc3339_string]) + end + + def test_builtin_date_time_converter_rfc3339_tab_under_second_offset + rfc3339_string = "2018-01-14\t22:25:19.1+09:00" + datetime = DateTime.new(2018, 1, 14, 22, 25, 19.1, "+9") + assert_equal(datetime, + CSV::Converters[:date_time][rfc3339_string]) + end + + def test_builtin_date_time_converter_rfc3339_tab_offset + rfc3339_string = "2018-01-14\t22:25:19+09:00" + datetime = DateTime.new(2018, 1, 14, 22, 25, 19, "+9") + assert_equal(datetime, + CSV::Converters[:date_time][rfc3339_string]) + end + + def test_builtin_date_time_converter_rfc3339_tab_utc + rfc3339_string = "2018-01-14\t22:25:19Z" + datetime = DateTime.new(2018, 1, 14, 22, 25, 19) + assert_equal(datetime, + CSV::Converters[:date_time][rfc3339_string]) + end +end diff --git a/test/csv/test_encodings.rb b/test/csv/test_encodings.rb new file mode 100644 index 0000000000..f08d551f69 --- /dev/null +++ b/test/csv/test_encodings.rb @@ -0,0 +1,403 @@ +# -*- coding: utf-8 -*- +# frozen_string_literal: false + +require_relative "helper" + +class TestCSVEncodings < Test::Unit::TestCase + extend DifferentOFS + include Helper + + def setup + super + require 'tempfile' + @temp_csv_file = Tempfile.new(%w"test_csv. .csv") + @temp_csv_path = @temp_csv_file.path + @temp_csv_file.close + end + + def teardown + @temp_csv_file.close! + super + 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 + + def test_read_with_default_encoding + data = "abc" + default_external = Encoding.default_external + each_encoding do |encoding| + File.open(@temp_csv_path, "wb", encoding: encoding) {|f| f << data} + begin + no_warnings do + Encoding.default_external = encoding + end + result = CSV.read(@temp_csv_path)[0][0] + ensure + no_warnings do + Encoding.default_external = default_external + end + end + assert_equal(encoding, result.encoding) + 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_all?(parsed.headers, "Wrong data encoding.") {|h| h.encoding == data.encoding} + parsed.each do |row| + assert_all?(row.fields, "Wrong data encoding.") {|f| f.encoding == 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_all?(parsed[0], "Wrong data encoding.") {|f| f.encoding == 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_all?(parsed.headers, "Wrong data encoding.") {|h| h.encoding.name == "UTF-8"} + assert_all?(parsed[0].fields, "Wrong data encoding.") {|f| f.encoding == 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_all?(row, "Wrong data encoding.") {|f| f.encoding == 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_all?(row, "Wrong data encoding.") {|f| f.encoding == 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", encoding: data.encoding) { |f| f << data } + CSV.foreach(@temp_csv_path, encoding: data.encoding) do |row| + row.each {|f| assert_equal(f.encoding, 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_all?(row, "Wrong data encoding.") {|f| f.encoding == 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_all?(rows.flatten, "Wrong data encoding.") {|f| f.encoding == 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_all?(rows.flatten, "Wrong data encoding.") {|f| f.encoding == 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 + begin + csv = %w[abc d|ef].map { |f| f.encode(encoding) }. + to_csv(col_sep: "|", encoding: encoding.name) + rescue Encoding::ConverterNotFoundError + next + end + 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 + + def test_encoding_is_upgraded_during_writing_as_needed + data = ["foo".force_encoding("US-ASCII"), "\u3042"] + assert_equal("US-ASCII", data.first.encoding.name) + assert_equal("UTF-8", data.last.encoding.name) + assert_equal("UTF-8", data.join('').encoding.name) + assert_equal("UTF-8", data.to_csv.encoding.name) + end + + def test_encoding_is_upgraded_for_ascii_content_during_writing_as_needed + data = ["foo".force_encoding("ISO-8859-1"), "\u3042"] + assert_equal("ISO-8859-1", data.first.encoding.name) + assert_equal("UTF-8", data.last.encoding.name) + assert_equal("UTF-8", data.join('').encoding.name) + assert_equal("UTF-8", data.to_csv.encoding.name) + end + + def test_encoding_is_not_upgraded_for_non_ascii_content_during_writing_as_needed + data = ["\u00c0".encode("ISO-8859-1"), "\u3042"] + assert_equal([ + "ISO-8859-1", + "UTF-8", + ], + data.collect {|field| field.encoding.name}) + assert_raise(Encoding::CompatibilityError) do + data.to_csv + end + end + + def test_explicit_encoding + bug9766 = '[ruby-core:62113] [Bug #9766]' + s = CSV.generate(encoding: "Windows-31J") do |csv| + csv << ["foo".force_encoding("ISO-8859-1"), "\u3042"] + end + assert_equal(["foo,\u3042\n".encode(Encoding::Windows_31J), Encoding::Windows_31J], [s, s.encoding], bug9766) + end + + def test_encoding_with_default_internal + with_default_internal(Encoding::UTF_8) do + s = CSV.generate(String.new(encoding: Encoding::Big5), encoding: Encoding::Big5) do |csv| + csv << ["漢字"] + end + assert_equal(["漢字\n".encode(Encoding::Big5), Encoding::Big5], [s, s.encoding]) + end + end + + def test_row_separator_detection_with_invalid_encoding + csv = CSV.new("invalid,\xF8\r\nvalid,x\r\n".force_encoding("UTF-8"), + encoding: "UTF-8") + assert_equal("\r\n", csv.row_sep) + end + + def test_invalid_encoding_row_error + csv = CSV.new("valid,x\rinvalid,\xF8\r".force_encoding("UTF-8"), + encoding: "UTF-8", row_sep: "\r") + error = assert_raise(CSV::MalformedCSVError) do + csv.shift + csv.shift + end + assert_equal("Invalid byte sequence in UTF-8 in line 2.", + error.message) + end + + def test_string_input_transcode + # U+3042 HIRAGANA LETTER A + # U+3044 HIRAGANA LETTER I + # U+3046 HIRAGANA LETTER U + value = "\u3042\u3044\u3046" + csv = CSV.new(value, encoding: "UTF-8:EUC-JP") + assert_equal([[value.encode("EUC-JP")]], + csv.read) + end + + def test_string_input_set_encoding_string + # U+3042 HIRAGANA LETTER A + # U+3044 HIRAGANA LETTER I + # U+3046 HIRAGANA LETTER U + value = "\u3042\u3044\u3046".encode("EUC-JP") + csv = CSV.new(value.dup.force_encoding("UTF-8"), encoding: "EUC-JP") + assert_equal([[value.encode("EUC-JP")]], + csv.read) + end + + def test_string_input_set_encoding_encoding + # U+3042 HIRAGANA LETTER A + # U+3044 HIRAGANA LETTER I + # U+3046 HIRAGANA LETTER U + value = "\u3042\u3044\u3046".encode("EUC-JP") + csv = CSV.new(value.dup.force_encoding("UTF-8"), + encoding: Encoding.find("EUC-JP")) + assert_equal([[value.encode("EUC-JP")]], + csv.read) + end + + private + + def assert_parses(fields, encoding, **options) + encoding = Encoding.find(encoding) unless encoding.is_a? Encoding + orig_fields = fields + fields = encode_ary(fields, encoding) + data = ary_to_data(fields, **options) + parsed = CSV.parse(data, **options) + assert_equal(fields, parsed) + parsed.flatten.each_with_index do |field, i| + assert_equal(encoding, field.encoding, "Field[#{i + 1}] was transcoded.") + end + File.open(@temp_csv_path, "wb") {|f| f.print(data)} + CSV.open(@temp_csv_path, "rb:#{encoding}", **options) do |csv| + csv.each_with_index do |row, i| + assert_equal(fields[i], row) + end + end + begin + CSV.open(@temp_csv_path, + "rb:#{encoding}:#{__ENCODING__}", + **options) do |csv| + csv.each_with_index do |row, i| + assert_equal(orig_fields[i], row) + end + end unless encoding == __ENCODING__ + rescue Encoding::ConverterNotFoundError + end + options[:encoding] = encoding.name + CSV.open(@temp_csv_path, **options) do |csv| + csv.each_with_index do |row, i| + assert_equal(fields[i], row) + end + end + options.delete(:encoding) + options[:external_encoding] = encoding.name + options[:internal_encoding] = __ENCODING__.name + begin + CSV.open(@temp_csv_path, **options) do |csv| + csv.each_with_index do |row, i| + assert_equal(orig_fields[i], row) + end + end unless encoding == __ENCODING__ + rescue Encoding::ConverterNotFoundError + 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 + + def no_warnings + old_verbose, $VERBOSE = $VERBOSE, nil + yield + ensure + $VERBOSE = old_verbose + end +end diff --git a/test/csv/test_features.rb b/test/csv/test_features.rb new file mode 100644 index 0000000000..d6eb2dc13b --- /dev/null +++ b/test/csv/test_features.rb @@ -0,0 +1,359 @@ +# -*- coding: utf-8 -*- +# frozen_string_literal: false + +begin + require "zlib" +rescue LoadError +end + +require_relative "helper" +require "tempfile" + +class TestCSVFeatures < Test::Unit::TestCase + extend DifferentOFS + + 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 setup + super + @sample_data = <<-CSV +line,1,abc +line,2,"def\nghi" + +line,4,jkl + CSV + @csv = CSV.new(@sample_data) + end + + 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? }, + CSV.parse_line( test_case.first.tr(",", sep), + col_sep: sep ) ) + end + end + assert_equal([",,,", nil], CSV.parse_line(",,,;", col_sep: ";")) + end + + def test_col_sep_nil + assert_raise_with_message(ArgumentError, + ":col_sep must be 1 or more characters: nil") do + CSV.parse(@sample_data, col_sep: nil) + end + end + + def test_col_sep_empty + assert_raise_with_message(ArgumentError, + ":col_sep must be 1 or more characters: \"\"") do + CSV.parse(@sample_data, col_sep: "") + end + end + + def test_row_sep + error = assert_raise(CSV::MalformedCSVError) do + CSV.parse_line("1,2,3\n,4,5\r\n", row_sep: "\r\n") + end + assert_equal("Unquoted fields do not allow new line <\"\\n\"> in line 1.", + error.message) + assert_equal( ["1", "2", "3\n", "4", "5"], + CSV.parse_line(%Q{1,2,"3\n",4,5\r\n}, row_sep: "\r\n")) + end + + def test_quote_char + TEST_CASES.each do |test_case| + assert_equal(test_case.last.map {|t| t.tr('"', "'") unless t.nil?}, + CSV.parse_line(test_case.first.tr('"', "'"), + quote_char: "'" )) + end + end + + def test_quote_char_special_regexp_char + TEST_CASES.each do |test_case| + assert_equal(test_case.last.map {|t| t.tr('"', "|") unless t.nil?}, + CSV.parse_line(test_case.first.tr('"', "|"), + quote_char: "|")) + end + end + + def test_quote_char_special_regexp_char_liberal_parsing + TEST_CASES.each do |test_case| + assert_equal(test_case.last.map {|t| t.tr('"', "|") unless t.nil?}, + CSV.parse_line(test_case.first.tr('"', "|"), + quote_char: "|", + liberal_parsing: true)) + end + end + + def test_csv_char_readers + %w[col_sep row_sep quote_char].each do |reader| + csv = CSV.new("abc,def", reader.to_sym => "|") + assert_equal("|", csv.send(reader)) + end + end + + def test_row_sep_auto_discovery + ["\r\n", "\n", "\r"].each do |line_end| + data = "1,2,3#{line_end}4,5#{line_end}" + discovered = CSV.new(data).row_sep + assert_equal(line_end, discovered) + end + + assert_equal("\n", CSV.new("\n\r\n\r").row_sep) + + assert_equal($/, CSV.new("").row_sep) + + assert_equal($/, CSV.new(STDERR).row_sep) + end + + def test_line + lines = [ + %Q(\u{3000}abc,def\n), + %Q(\u{3000}abc,"d\nef"\n), + %Q(\u{3000}abc,"d\r\nef"\n), + %Q(\u{3000}abc,"d\ref") + ] + csv = CSV.new(lines.join('')) + lines.each do |line| + csv.shift + assert_equal(line, csv.line) + end + end + + def test_lineno + assert_equal(5, @sample_data.lines.to_a.size) + + 4.times do |line_count| + assert_equal(line_count, @csv.lineno) + assert_not_nil(@csv.shift) + assert_equal(line_count + 1, @csv.lineno) + end + assert_nil(@csv.shift) + end + + def test_readline + test_lineno + + @csv.rewind + + test_lineno + end + + def test_unknown_options + assert_raise_with_message(ArgumentError, /unknown keyword/) { + CSV.new(@sample_data, unknown: :error) + } + assert_raise_with_message(ArgumentError, /unknown keyword/) { + CSV.new(@sample_data, universal_newline: true) + } + end + + def test_skip_blanks + assert_equal(4, @csv.to_a.size) + + @csv = CSV.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 + + def test_csv_behavior_readers + %w[ unconverted_fields return_headers write_headers + skip_blanks force_quotes ].each do |behavior| + assert_not_predicate(CSV.new("abc,def"), "#{behavior}?", "Behavior defaulted to on.") + csv = CSV.new("abc,def", behavior.to_sym => true) + assert_predicate(csv, "#{behavior}?", "Behavior change now registered.") + end + end + + def test_converters_reader + # no change + assert_equal( [:integer], + CSV.new("abc,def", converters: [:integer]).converters ) + + # just one + assert_equal( [:integer], + CSV.new("abc,def", converters: :integer).converters ) + + # expanded + assert_equal( [:integer, :float], + CSV.new("abc,def", converters: :numeric).converters ) + + # custom + csv = CSV.new("abc,def", converters: [:integer, lambda { }]) + assert_equal(2, csv.converters.size) + assert_equal(:integer, csv.converters.first) + assert_instance_of(Proc, csv.converters.last) + end + + def test_header_converters_reader + # no change + hc = :header_converters + assert_equal([:downcase], CSV.new("abc,def", hc => [:downcase]).send(hc)) + + # just one + assert_equal([:downcase], CSV.new("abc,def", hc => :downcase).send(hc)) + + # custom + csv = CSV.new("abc,def", hc => [:symbol, lambda { }]) + assert_equal(2, csv.send(hc).size) + assert_equal(:symbol, csv.send(hc).first) + assert_instance_of(Proc, csv.send(hc).last) + end + + # reported by Kev Jackson + def test_failing_to_escape_col_sep + assert_nothing_raised(Exception) { CSV.new(String.new, col_sep: "|") } + end + + # reported by Chris Roos + def test_failing_to_reset_headers_in_rewind + csv = CSV.new("forename,surname", headers: true, return_headers: true) + csv.each {|row| assert_predicate row, :header_row?} + csv.rewind + csv.each {|row| assert_predicate row, :header_row?} + end + + def test_gzip_reader + zipped = nil + assert_nothing_raised(NoMethodError) do + zipped = CSV.new( + Zlib::GzipReader.open( + File.join(File.dirname(__FILE__), "line_endings.gz") + ) + ) + end + assert_equal("\r\n", zipped.row_sep) + ensure + zipped.close + end if defined?(Zlib::GzipReader) + + def test_gzip_writer + Tempfile.create(%w"temp .gz") {|tempfile| + tempfile.close + file = tempfile.path + zipped = nil + assert_nothing_raised(NoMethodError) do + zipped = CSV.new(Zlib::GzipWriter.open(file)) + end + zipped << %w[one two three] + zipped << [1, 2, 3] + zipped.close + + assert_include(Zlib::GzipReader.open(file) {|f| f.read}, + $INPUT_RECORD_SEPARATOR, "@row_sep did not default") + } + end if defined?(Zlib::GzipWriter) + + def test_inspect_is_smart_about_io_types + str = CSV.new("string,data").inspect + assert_include(str, "io_type:StringIO", "IO type not detected.") + + str = CSV.new($stderr).inspect + assert_include(str, "io_type:$stderr", "IO type not detected.") + + Tempfile.create(%w"temp .csv") {|tempfile| + tempfile.close + path = tempfile.path + File.open(path, "w") { |csv| csv << "one,two,three\n1,2,3\n" } + str = CSV.open(path) { |csv| csv.inspect } + assert_include(str, "io_type:File", "IO type not detected.") + } + end + + def test_inspect_shows_key_attributes + str = @csv.inspect + %w[lineno col_sep row_sep quote_char].each do |attr_name| + assert_match(/\b#{attr_name}:[^\s>]+/, str) + end + end + + def test_inspect_shows_headers_when_available + csv = CSV.new("one,two,three\n1,2,3\n", headers: true) + assert_include(csv.inspect, "headers:true", "Header hint not shown.") + csv.shift # load headers + assert_match(/headers:\[[^\]]+\]/, csv.inspect) + end + + def test_inspect_encoding_is_ascii_compatible + csv = CSV.new("one,two,three\n1,2,3\n".encode("UTF-16BE")) + assert_send([Encoding, :compatible?, + Encoding.find("US-ASCII"), csv.inspect.encoding], + "inspect() was not ASCII compatible.") + end + + def test_version + assert_not_nil(CSV::VERSION) + assert_instance_of(String, CSV::VERSION) + assert_predicate(CSV::VERSION, :frozen?) + assert_match(/\A\d\.\d\.\d\z/, CSV::VERSION) + end + + def test_table_nil_equality + assert_nothing_raised(NoMethodError) { CSV.parse("test", headers: true) == nil } + end + + # non-seekable input stream for testing https://github.com/ruby/csv/issues/44 + class DummyIO + extend Forwardable + def_delegators :@io, :gets, :read, :pos, :eof? # no seek or rewind! + def initialize(data) + @io = StringIO.new(data) + end + end + + def test_line_separator_autodetection_for_non_seekable_input_lf + c = CSV.new(DummyIO.new("one,two,three\nfoo,bar,baz\n")) + assert_equal [["one", "two", "three"], ["foo", "bar", "baz"]], c.each.to_a + end + + def test_line_separator_autodetection_for_non_seekable_input_cr + c = CSV.new(DummyIO.new("one,two,three\rfoo,bar,baz\r")) + assert_equal [["one", "two", "three"], ["foo", "bar", "baz"]], c.each.to_a + end + + def test_line_separator_autodetection_for_non_seekable_input_cr_lf + c = CSV.new(DummyIO.new("one,two,three\r\nfoo,bar,baz\r\n")) + assert_equal [["one", "two", "three"], ["foo", "bar", "baz"]], c.each.to_a + end + + def test_line_separator_autodetection_for_non_seekable_input_1024_over_lf + table = (1..10).map { |row| (1..200).map { |col| "row#{row}col#{col}" }.to_a }.to_a + input = table.map { |line| line.join(",") }.join("\n") + c = CSV.new(DummyIO.new(input)) + assert_equal table, c.each.to_a + end + + def test_line_separator_autodetection_for_non_seekable_input_1024_over_cr_lf + table = (1..10).map { |row| (1..200).map { |col| "row#{row}col#{col}" }.to_a }.to_a + input = table.map { |line| line.join(",") }.join("\r\n") + c = CSV.new(DummyIO.new(input)) + assert_equal table, c.each.to_a + end + + def test_line_separator_autodetection_for_non_seekable_input_many_cr_only + # input with lots of CRs (to make sure no bytes are lost due to look-ahead) + c = CSV.new(DummyIO.new("foo\r" + "\r" * 9999 + "bar\r")) + assert_equal [["foo"]] + [[]] * 9999 + [["bar"]], c.each.to_a + end +end diff --git a/test/csv/test_patterns.rb b/test/csv/test_patterns.rb new file mode 100644 index 0000000000..881f03a3a4 --- /dev/null +++ b/test/csv/test_patterns.rb @@ -0,0 +1,27 @@ +# frozen_string_literal: true + +require_relative "helper" + +class TestCSVPatternMatching < Test::Unit::TestCase + + def test_hash + case CSV::Row.new(%i{A B C}, [1, 2, 3]) + in B: b, C: c + assert_equal([2, 3], [b, c]) + end + end + + def test_hash_rest + case CSV::Row.new(%i{A B C}, [1, 2, 3]) + in B: b, **rest + assert_equal([2, { A: 1, C: 3 }], [b, rest]) + end + end + + def test_array + case CSV::Row.new(%i{A B C}, [1, 2, 3]) + in *, matched + assert_equal(3, matched) + end + end +end diff --git a/test/csv/test_row.rb b/test/csv/test_row.rb new file mode 100644 index 0000000000..b717945041 --- /dev/null +++ b/test/csv/test_row.rb @@ -0,0 +1,435 @@ +# -*- coding: utf-8 -*- +# frozen_string_literal: false + +require_relative "helper" + +class TestCSVRow < Test::Unit::TestCase + extend DifferentOFS + + def setup + super + @row = CSV::Row.new(%w{A B C A A}, [1, 2, 3, 4]) + end + + def test_initialize + # basic + row = CSV::Row.new(%w{A B C}, [1, 2, 3]) + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([["A", 1], ["B", 2], ["C", 3]], row.to_a) + + # missing headers + row = CSV::Row.new(%w{A}, [1, 2, 3]) + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([["A", 1], [nil, 2], [nil, 3]], row.to_a) + + # missing fields + row = CSV::Row.new(%w{A B C}, [1, 2]) + assert_not_nil(row) + assert_instance_of(CSV::Row, row) + assert_equal([["A", 1], ["B", 2], ["C", nil]], row.to_a) + end + + def test_row_type + # field rows + row = CSV::Row.new(%w{A B C}, [1, 2, 3]) # implicit + assert_not_predicate(row, :header_row?) + assert_predicate(row, :field_row?) + row = CSV::Row.new(%w{A B C}, [1, 2, 3], false) # explicit + assert_not_predicate(row, :header_row?) + assert_predicate(row, :field_row?) + + # header row + row = CSV::Row.new(%w{A B C}, [1, 2, 3], true) + assert_predicate(row, :header_row?) + assert_not_predicate(row, :field_row?) + end + + def test_headers + assert_equal(%w{A B C A A}, @row.headers) + end + + def test_field + # by name + assert_equal(2, @row.field("B")) + assert_equal(2, @row["B"]) # alias + + # by index + assert_equal(3, @row.field(2)) + + # by range + assert_equal([2,3], @row.field(1..2)) + + # missing + assert_nil(@row.field("Missing")) + assert_nil(@row.field(10)) + + # minimum index + assert_equal(1, @row.field("A")) + assert_equal(1, @row.field("A", 0)) + assert_equal(4, @row.field("A", 1)) + assert_equal(4, @row.field("A", 2)) + assert_equal(4, @row.field("A", 3)) + assert_equal(nil, @row.field("A", 4)) + assert_equal(nil, @row.field("A", 5)) + end + + def test_fetch + # only by name + assert_equal(2, @row.fetch('B')) + + # missing header raises KeyError + assert_raise KeyError do + @row.fetch('foo') + end + + # missing header yields itself to block + assert_equal 'bar', @row.fetch('foo') { |header| + header == 'foo' ? 'bar' : false } + + # missing header returns the given default value + assert_equal 'bar', @row.fetch('foo', 'bar') + + # more than one vararg raises ArgumentError + assert_raise ArgumentError do + @row.fetch('foo', 'bar', 'baz') + end + end + + def test_has_key? + assert_equal(true, @row.has_key?('B')) + assert_equal(false, @row.has_key?('foo')) + + # aliases + assert_equal(true, @row.header?('B')) + assert_equal(false, @row.header?('foo')) + + assert_equal(true, @row.include?('B')) + assert_equal(false, @row.include?('foo')) + + assert_equal(true, @row.member?('B')) + assert_equal(false, @row.member?('foo')) + + assert_equal(true, @row.key?('B')) + assert_equal(false, @row.key?('foo')) + end + + def test_set_field + # set field by name + assert_equal(100, @row["A"] = 100) + + # set field by index + assert_equal(300, @row[3] = 300) + + # set field by name and minimum index + assert_equal([:a, :b, :c], @row["A", 4] = [:a, :b, :c]) + + # verify the changes + assert_equal( [ ["A", 100], + ["B", 2], + ["C", 3], + ["A", 300], + ["A", [:a, :b, :c]] ], @row.to_a ) + + # assigning an index past the end + assert_equal("End", @row[10] = "End") + assert_equal( [ ["A", 100], + ["B", 2], + ["C", 3], + ["A", 300], + ["A", [:a, :b, :c]], + [nil, nil], + [nil, nil], + [nil, nil], + [nil, nil], + [nil, nil], + [nil, "End"] ], @row.to_a ) + + # assigning a new field by header + assert_equal("New", @row[:new] = "New") + assert_equal( [ ["A", 100], + ["B", 2], + ["C", 3], + ["A", 300], + ["A", [:a, :b, :c]], + [nil, nil], + [nil, nil], + [nil, nil], + [nil, nil], + [nil, nil], + [nil, "End"], + [:new, "New"] ], @row.to_a ) + end + + def test_append + # add a value + assert_equal(@row, @row << "Value") + assert_equal( [ ["A", 1], + ["B", 2], + ["C", 3], + ["A", 4], + ["A", nil], + [nil, "Value"] ], @row.to_a ) + + # add a pair + assert_equal(@row, @row << %w{Header Field}) + assert_equal( [ ["A", 1], + ["B", 2], + ["C", 3], + ["A", 4], + ["A", nil], + [nil, "Value"], + %w{Header Field} ], @row.to_a ) + + # a pair with Hash syntax + assert_equal(@row, @row << {key: :value}) + assert_equal( [ ["A", 1], + ["B", 2], + ["C", 3], + ["A", 4], + ["A", nil], + [nil, "Value"], + %w{Header Field}, + [:key, :value] ], @row.to_a ) + + # multiple fields at once + assert_equal(@row, @row.push(100, 200, [:last, 300])) + assert_equal( [ ["A", 1], + ["B", 2], + ["C", 3], + ["A", 4], + ["A", nil], + [nil, "Value"], + %w{Header Field}, + [:key, :value], + [nil, 100], + [nil, 200], + [:last, 300] ], @row.to_a ) + end + + def test_delete + # by index + assert_equal(["B", 2], @row.delete(1)) + + # by header + assert_equal(["C", 3], @row.delete("C")) + + end + + def test_delete_if + assert_equal(@row, @row.delete_if { |h, f| h == "A" and not f.nil? }) + assert_equal([["B", 2], ["C", 3], ["A", nil]], @row.to_a) + end + + def test_delete_if_without_block + enum = @row.delete_if + assert_instance_of(Enumerator, enum) + assert_equal(@row.size, enum.size) + + assert_equal(@row, enum.each { |h, f| h == "A" and not f.nil? }) + assert_equal([["B", 2], ["C", 3], ["A", nil]], @row.to_a) + end + + def test_fields + # all fields + assert_equal([1, 2, 3, 4, nil], @row.fields) + + # by header + assert_equal([1, 3], @row.fields("A", "C")) + + # by index + assert_equal([2, 3, nil], @row.fields(1, 2, 10)) + + # by both + assert_equal([2, 3, 4], @row.fields("B", "C", 3)) + + # with minimum indices + assert_equal([2, 3, 4], @row.fields("B", "C", ["A", 3])) + + # by header range + assert_equal([2, 3], @row.values_at("B".."C")) + end + + def test_index + # basic usage + assert_equal(0, @row.index("A")) + assert_equal(1, @row.index("B")) + assert_equal(2, @row.index("C")) + assert_equal(nil, @row.index("Z")) + + # with minimum index + assert_equal(0, @row.index("A")) + assert_equal(0, @row.index("A", 0)) + assert_equal(3, @row.index("A", 1)) + assert_equal(3, @row.index("A", 2)) + assert_equal(3, @row.index("A", 3)) + assert_equal(4, @row.index("A", 4)) + assert_equal(nil, @row.index("A", 5)) + end + + def test_queries + # fields + assert(@row.field?(4)) + assert(@row.field?(nil)) + assert(!@row.field?(10)) + end + + def test_each + # array style + ary = @row.to_a + @row.each do |pair| + assert_equal(ary.first.first, pair.first) + assert_equal(ary.shift.last, pair.last) + end + + # hash style + ary = @row.to_a + @row.each do |header, field| + assert_equal(ary.first.first, header) + assert_equal(ary.shift.last, field) + end + + # verify that we can chain the call + assert_equal(@row, @row.each { }) + + # without block + ary = @row.to_a + enum = @row.each + assert_instance_of(Enumerator, enum) + assert_equal(@row.size, enum.size) + enum.each do |pair| + assert_equal(ary.first.first, pair.first) + assert_equal(ary.shift.last, pair.last) + end + end + + def test_each_pair + assert_equal([ + ["A", 1], + ["B", 2], + ["C", 3], + ["A", 4], + ["A", nil], + ], + @row.each_pair.to_a) + end + + def test_enumerable + assert_equal( [["A", 1], ["A", 4], ["A", nil]], + @row.select { |pair| pair.first == "A" } ) + + assert_equal(10, @row.inject(0) { |sum, (_, n)| sum + (n || 0) }) + end + + def test_to_a + row = CSV::Row.new(%w{A B C}, [1, 2, 3]).to_a + assert_instance_of(Array, row) + row.each do |pair| + assert_instance_of(Array, pair) + assert_equal(2, pair.size) + end + assert_equal([["A", 1], ["B", 2], ["C", 3]], row) + end + + def test_to_hash + hash = @row.to_hash + assert_equal({"A" => @row["A"], "B" => @row["B"], "C" => @row["C"]}, hash) + hash.keys.each_with_index do |string_key, h| + assert_predicate(string_key, :frozen?) + assert_same(string_key, @row.headers[h]) + end + end + + def test_to_csv + # normal conversion + assert_equal("1,2,3,4,\n", @row.to_csv) + assert_equal("1,2,3,4,\n", @row.to_s) # alias + + # with options + assert_equal( "1|2|3|4|\r\n", + @row.to_csv(col_sep: "|", row_sep: "\r\n") ) + end + + def test_array_delegation + assert_not_empty(@row, "Row was empty.") + + assert_equal([@row.headers.size, @row.fields.size].max, @row.size) + end + + def test_inspect_shows_header_field_pairs + str = @row.inspect + @row.each do |header, field| + assert_include(str, "#{header.inspect}:#{field.inspect}", + "Header field pair not found.") + end + end + + def test_inspect_encoding_is_ascii_compatible + assert_send([Encoding, :compatible?, + Encoding.find("US-ASCII"), + @row.inspect.encoding], + "inspect() was not ASCII compatible.") + end + + def test_inspect_shows_symbol_headers_as_bare_attributes + str = CSV::Row.new(@row.headers.map { |h| h.to_sym }, @row.fields).inspect + @row.each do |header, field| + assert_include(str, "#{header}:#{field.inspect}", + "Header field pair not found.") + end + end + + def test_can_be_compared_with_other_classes + assert_not_nil(CSV::Row.new([ ], [ ]), "The row was nil") + end + + def test_can_be_compared_when_not_a_row + r = @row == [] + assert_equal false, r + end + + def test_dig_by_index + assert_equal(2, @row.dig(1)) + + assert_nil(@row.dig(100)) + end + + def test_dig_by_header + assert_equal(2, @row.dig("B")) + + assert_nil(@row.dig("Missing")) + end + + def test_dig_cell + row = CSV::Row.new(%w{A}, [["foo", ["bar", ["baz"]]]]) + + assert_equal("foo", row.dig(0, 0)) + assert_equal("bar", row.dig(0, 1, 0)) + + assert_equal("foo", row.dig("A", 0)) + assert_equal("bar", row.dig("A", 1, 0)) + end + + def test_dig_cell_no_dig + row = CSV::Row.new(%w{A}, ["foo"]) + + assert_raise(TypeError) do + row.dig(0, 0) + end + assert_raise(TypeError) do + row.dig("A", 0) + end + end + + def test_dup + row = CSV::Row.new(["A"], ["foo"]) + dupped_row = row.dup + dupped_row["A"] = "bar" + assert_equal(["foo", "bar"], + [row["A"], dupped_row["A"]]) + dupped_row.delete("A") + assert_equal(["foo", nil], + [row["A"], dupped_row["A"]]) + end +end diff --git a/test/csv/test_table.rb b/test/csv/test_table.rb new file mode 100644 index 0000000000..e8ab74044e --- /dev/null +++ b/test/csv/test_table.rb @@ -0,0 +1,691 @@ +# -*- coding: utf-8 -*- +# frozen_string_literal: false + +require_relative "helper" + +class TestCSVTable < Test::Unit::TestCase + extend DifferentOFS + + def setup + super + @rows = [ CSV::Row.new(%w{A B C}, [1, 2, 3]), + CSV::Row.new(%w{A B C}, [4, 5, 6]), + CSV::Row.new(%w{A B C}, [7, 8, 9]) ] + @table = CSV::Table.new(@rows) + + @header_table = CSV::Table.new( + [CSV::Row.new(%w{A B C}, %w{A B C}, true)] + @rows + ) + + @header_only_table = CSV::Table.new([], headers: %w{A B C}) + end + + def test_initialize + assert_not_nil(@table) + assert_instance_of(CSV::Table, @table) + end + + def test_modes + assert_equal(:col_or_row, @table.mode) + + # non-destructive changes, intended for one shot calls + cols = @table.by_col + assert_equal(:col_or_row, @table.mode) + assert_equal(:col, cols.mode) + assert_equal(@table, cols) + + rows = @table.by_row + assert_equal(:col_or_row, @table.mode) + assert_equal(:row, rows.mode) + assert_equal(@table, rows) + + col_or_row = rows.by_col_or_row + assert_equal(:row, rows.mode) + assert_equal(:col_or_row, col_or_row.mode) + assert_equal(@table, col_or_row) + + # destructive mode changing calls + assert_equal(@table, @table.by_row!) + assert_equal(:row, @table.mode) + assert_equal(@table, @table.by_col_or_row!) + assert_equal(:col_or_row, @table.mode) + end + + def test_headers + assert_equal(@rows.first.headers, @table.headers) + end + + def test_headers_empty + t = CSV::Table.new([]) + assert_equal Array.new, t.headers + end + + def test_headers_only + assert_equal(%w[A B C], @header_only_table.headers) + end + + def test_headers_modified_by_row + table = CSV::Table.new([], headers: ["A", "B"]) + table << ["a", "b"] + table.first << {"C" => "c"} + assert_equal(["A", "B", "C"], table.headers) + end + + def test_index + ################## + ### Mixed Mode ### + ################## + # by row + @rows.each_index { |i| assert_equal(@rows[i], @table[i]) } + assert_equal(nil, @table[100]) # empty row + + # by row with Range + assert_equal([@table[1], @table[2]], @table[1..2]) + + # by col + @rows.first.headers.each do |header| + assert_equal(@rows.map { |row| row[header] }, @table[header]) + end + assert_equal([nil] * @rows.size, @table["Z"]) # empty col + + # by cell, row then col + assert_equal(2, @table[0][1]) + assert_equal(6, @table[1]["C"]) + + # by cell, col then row + assert_equal(5, @table["B"][1]) + assert_equal(9, @table["C"][2]) + + # with headers (by col) + assert_equal(["B", 2, 5, 8], @header_table["B"]) + + ################### + ### Column Mode ### + ################### + @table.by_col! + + assert_equal([2, 5, 8], @table[1]) + assert_equal([2, 5, 8], @table["B"]) + + ################ + ### Row Mode ### + ################ + @table.by_row! + + assert_equal(@rows[1], @table[1]) + assert_raise(TypeError) { @table["B"] } + + ############################ + ### One Shot Mode Change ### + ############################ + assert_equal(@rows[1], @table[1]) + assert_equal([2, 5, 8], @table.by_col[1]) + assert_equal(@rows[1], @table[1]) + end + + def test_set_row_or_column + ################## + ### Mixed Mode ### + ################## + # set row + @table[2] = [10, 11, 12] + assert_equal([%w[A B C], [1, 2, 3], [4, 5, 6], [10, 11, 12]], @table.to_a) + + @table[3] = CSV::Row.new(%w[A B C], [13, 14, 15]) + assert_equal( [%w[A B C], [1, 2, 3], [4, 5, 6], [10, 11, 12], [13, 14, 15]], + @table.to_a ) + + # set col + @table["Type"] = "data" + assert_equal( [ %w[A B C Type], + [1, 2, 3, "data"], + [4, 5, 6, "data"], + [10, 11, 12, "data"], + [13, 14, 15, "data"] ], + @table.to_a ) + + @table["Index"] = [1, 2, 3] + assert_equal( [ %w[A B C Type Index], + [1, 2, 3, "data", 1], + [4, 5, 6, "data", 2], + [10, 11, 12, "data", 3], + [13, 14, 15, "data", nil] ], + @table.to_a ) + + @table["B"] = [100, 200] + assert_equal( [ %w[A B C Type Index], + [1, 100, 3, "data", 1], + [4, 200, 6, "data", 2], + [10, nil, 12, "data", 3], + [13, nil, 15, "data", nil] ], + @table.to_a ) + + # verify resulting table + assert_equal(<<-CSV, @table.to_csv) +A,B,C,Type,Index +1,100,3,data,1 +4,200,6,data,2 +10,,12,data,3 +13,,15,data, + CSV + + # with headers + @header_table["Type"] = "data" + assert_equal(%w[Type data data data], @header_table["Type"]) + + ################### + ### Column Mode ### + ################### + @table.by_col! + + @table[1] = [2, 5, 11, 14] + assert_equal( [ %w[A B C Type Index], + [1, 2, 3, "data", 1], + [4, 5, 6, "data", 2], + [10, 11, 12, "data", 3], + [13, 14, 15, "data", nil] ], + @table.to_a ) + + @table["Extra"] = "new stuff" + assert_equal( [ %w[A B C Type Index Extra], + [1, 2, 3, "data", 1, "new stuff"], + [4, 5, 6, "data", 2, "new stuff"], + [10, 11, 12, "data", 3, "new stuff"], + [13, 14, 15, "data", nil, "new stuff"] ], + @table.to_a ) + + ################ + ### Row Mode ### + ################ + @table.by_row! + + @table[1] = (1..6).to_a + assert_equal( [ %w[A B C Type Index Extra], + [1, 2, 3, "data", 1, "new stuff"], + [1, 2, 3, 4, 5, 6], + [10, 11, 12, "data", 3, "new stuff"], + [13, 14, 15, "data", nil, "new stuff"] ], + @table.to_a ) + + assert_raise(TypeError) { @table["Extra"] = nil } + end + + def test_set_by_col_with_header_row + r = [ CSV::Row.new(%w{X Y Z}, [97, 98, 99], true) ] + t = CSV::Table.new(r) + t.by_col! + t['A'] = [42] + assert_equal(['A'], t['A']) + end + + def test_each + ###################### + ### Mixed/Row Mode ### + ###################### + i = 0 + @table.each do |row| + assert_equal(@rows[i], row) + i += 1 + end + + # verify that we can chain the call + assert_equal(@table, @table.each { }) + + # without block + enum = @table.each + assert_instance_of(Enumerator, enum) + assert_equal(@table.size, enum.size) + + i = 0 + enum.each do |row| + assert_equal(@rows[i], row) + i += 1 + end + + ################### + ### Column Mode ### + ################### + @table.by_col! + + headers = @table.headers + @table.each do |header, column| + assert_equal(headers.shift, header) + assert_equal(@table[header], column) + end + + # without block + enum = @table.each + assert_instance_of(Enumerator, enum) + assert_equal(@table.headers.size, enum.size) + + headers = @table.headers + enum.each do |header, column| + assert_equal(headers.shift, header) + assert_equal(@table[header], column) + end + + ############################ + ### One Shot Mode Change ### + ############################ + @table.by_col_or_row! + + @table.each { |row| assert_instance_of(CSV::Row, row) } + @table.by_col.each { |tuple| assert_instance_of(Array, tuple) } + @table.each { |row| assert_instance_of(CSV::Row, row) } + end + + def test_each_by_col_duplicated_headers + table = CSV.parse(<<-CSV, headers: true) +a,a,,,b +1,2,3,4,5 +11,12,13,14,15 + CSV + assert_equal([ + ["a", ["1", "11"]], + ["a", ["2", "12"]], + [nil, ["3", "13"]], + [nil, ["4", "14"]], + ["b", ["5", "15"]], + ], + table.by_col.each.to_a) + end + + def test_each_split + yielded_values = [] + @table.each do |column1, column2, column3| + yielded_values << [column1, column2, column3] + end + assert_equal(@rows.collect(&:to_a), + yielded_values) + end + + def test_enumerable + assert_equal( @rows.values_at(0, 2), + @table.select { |row| (row["B"] % 2).zero? } ) + + assert_equal(@rows[1], @table.find { |row| row["C"] > 5 }) + end + + def test_to_a + assert_equal([%w[A B C], [1, 2, 3], [4, 5, 6], [7, 8, 9]], @table.to_a) + + # with headers + assert_equal( [%w[A B C], [1, 2, 3], [4, 5, 6], [7, 8, 9]], + @header_table.to_a ) + end + + def test_to_csv + csv = <<-CSV +A,B,C +1,2,3 +4,5,6 +7,8,9 + CSV + + # normal conversion + assert_equal(csv, @table.to_csv) + assert_equal(csv, @table.to_s) # alias + + # with options + assert_equal( csv.gsub(",", "|").gsub("\n", "\r\n"), + @table.to_csv(col_sep: "|", row_sep: "\r\n") ) + assert_equal( csv.lines.to_a[1..-1].join(''), + @table.to_csv(:write_headers => false) ) + + # with headers + assert_equal(csv, @header_table.to_csv) + end + + def test_to_csv_limit_positive + assert_equal(<<-CSV, @table.to_csv(limit: 2)) +A,B,C +1,2,3 +4,5,6 + CSV + end + + def test_to_csv_limit_positive_over + assert_equal(<<-CSV, @table.to_csv(limit: 5)) +A,B,C +1,2,3 +4,5,6 +7,8,9 + CSV + end + + def test_to_csv_limit_zero + assert_equal(<<-CSV, @table.to_csv(limit: 0)) +A,B,C + CSV + end + + def test_to_csv_limit_negative + assert_equal(<<-CSV, @table.to_csv(limit: -2)) +A,B,C +1,2,3 +4,5,6 + CSV + end + + def test_to_csv_limit_negative_over + assert_equal(<<-CSV, @table.to_csv(limit: -5)) +A,B,C + CSV + end + + def test_append + # verify that we can chain the call + assert_equal(@table, @table << [10, 11, 12]) + + # Array append + assert_equal(CSV::Row.new(%w[A B C], [10, 11, 12]), @table[-1]) + + # Row append + assert_equal(@table, @table << CSV::Row.new(%w[A B C], [13, 14, 15])) + assert_equal(CSV::Row.new(%w[A B C], [13, 14, 15]), @table[-1]) + end + + def test_delete_mixed_one + ################## + ### Mixed Mode ### + ################## + # delete a row + assert_equal(@rows[1], @table.delete(1)) + + # delete a col + assert_equal(@rows.map { |row| row["A"] }, @table.delete("A")) + + # verify resulting table + assert_equal(<<-CSV, @table.to_csv) +B,C +2,3 +8,9 + CSV + end + + def test_delete_mixed_multiple + ################## + ### Mixed Mode ### + ################## + # delete row and col + second_row = @rows[1] + a_col = @rows.map { |row| row["A"] } + a_col_without_second_row = a_col[0..0] + a_col[2..-1] + assert_equal([ + second_row, + a_col_without_second_row, + ], + @table.delete(1, "A")) + + # verify resulting table + assert_equal(<<-CSV, @table.to_csv) +B,C +2,3 +8,9 + CSV + end + + def test_delete_column + ################### + ### Column Mode ### + ################### + @table.by_col! + + assert_equal(@rows.map { |row| row[0] }, @table.delete(0)) + assert_equal(@rows.map { |row| row["C"] }, @table.delete("C")) + + # verify resulting table + assert_equal(<<-CSV, @table.to_csv) +B +2 +5 +8 + CSV + end + + def test_delete_row + ################ + ### Row Mode ### + ################ + @table.by_row! + + assert_equal(@rows[1], @table.delete(1)) + assert_raise(TypeError) { @table.delete("C") } + + # verify resulting table + assert_equal(<<-CSV, @table.to_csv) +A,B,C +1,2,3 +7,8,9 + CSV + end + + def test_delete_with_blank_rows + data = "col1,col2\nra1,ra2\n\nrb1,rb2" + table = CSV.parse(data, :headers => true) + assert_equal(["ra2", nil, "rb2"], table.delete("col2")) + end + + def test_delete_if_row + ###################### + ### Mixed/Row Mode ### + ###################### + # verify that we can chain the call + assert_equal(@table, @table.delete_if { |row| (row["B"] % 2).zero? }) + + # verify resulting table + assert_equal(<<-CSV, @table.to_csv) +A,B,C +4,5,6 + CSV + end + + def test_delete_if_row_without_block + ###################### + ### Mixed/Row Mode ### + ###################### + enum = @table.delete_if + assert_instance_of(Enumerator, enum) + assert_equal(@table.size, enum.size) + + # verify that we can chain the call + assert_equal(@table, enum.each { |row| (row["B"] % 2).zero? }) + + # verify resulting table + assert_equal(<<-CSV, @table.to_csv) +A,B,C +4,5,6 + CSV + end + + def test_delete_if_column + ################### + ### Column Mode ### + ################### + @table.by_col! + + assert_equal(@table, @table.delete_if { |h, v| h > "A" }) + assert_equal(<<-CSV, @table.to_csv) +A +1 +4 +7 + CSV + end + + def test_delete_if_column_without_block + ################### + ### Column Mode ### + ################### + @table.by_col! + + enum = @table.delete_if + assert_instance_of(Enumerator, enum) + assert_equal(@table.headers.size, enum.size) + + assert_equal(@table, enum.each { |h, v| h > "A" }) + assert_equal(<<-CSV, @table.to_csv) +A +1 +4 +7 + CSV + end + + def test_delete_headers_only + ################### + ### Column Mode ### + ################### + @header_only_table.by_col! + + # delete by index + assert_equal([], @header_only_table.delete(0)) + assert_equal(%w[B C], @header_only_table.headers) + + # delete by header + assert_equal([], @header_only_table.delete("C")) + assert_equal(%w[B], @header_only_table.headers) + end + + def test_values_at + ################## + ### Mixed Mode ### + ################## + # rows + assert_equal(@rows.values_at(0, 2), @table.values_at(0, 2)) + assert_equal(@rows.values_at(1..2), @table.values_at(1..2)) + + # cols + assert_equal([[1, 3], [4, 6], [7, 9]], @table.values_at("A", "C")) + assert_equal([[2, 3], [5, 6], [8, 9]], @table.values_at("B".."C")) + + ################### + ### Column Mode ### + ################### + @table.by_col! + + assert_equal([[1, 3], [4, 6], [7, 9]], @table.values_at(0, 2)) + assert_equal([[1, 3], [4, 6], [7, 9]], @table.values_at("A", "C")) + + ################ + ### Row Mode ### + ################ + @table.by_row! + + assert_equal(@rows.values_at(0, 2), @table.values_at(0, 2)) + assert_raise(TypeError) { @table.values_at("A", "C") } + + ############################ + ### One Shot Mode Change ### + ############################ + assert_equal(@rows.values_at(0, 2), @table.values_at(0, 2)) + 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_not_empty(@table, "Table was empty.") + + assert_equal(@rows.size, @table.size) + end + + def test_inspect_shows_current_mode + str = @table.inspect + assert_include(str, "mode:#{@table.mode}", "Mode not shown.") + + @table.by_col! + str = @table.inspect + assert_include(str, "mode:#{@table.mode}", "Mode not shown.") + end + + def test_inspect_encoding_is_ascii_compatible + assert_send([Encoding, :compatible?, + Encoding.find("US-ASCII"), + @table.inspect.encoding], + "inspect() was not ASCII compatible." ) + end + + def test_inspect_with_rows + additional_rows = [ CSV::Row.new(%w{A B C}, [101, 102, 103]), + CSV::Row.new(%w{A B C}, [104, 105, 106]), + CSV::Row.new(%w{A B C}, [107, 108, 109]) ] + table = CSV::Table.new(@rows + additional_rows) + str_table = table.inspect + + assert_equal(<<-CSV, str_table) +#<CSV::Table mode:col_or_row row_count:7> +A,B,C +1,2,3 +4,5,6 +7,8,9 +101,102,103 +104,105,106 + CSV + end + + def test_dig_mixed + # by row + assert_equal(@rows[0], @table.dig(0)) + assert_nil(@table.dig(100)) # empty row + + # by col + assert_equal([2, 5, 8], @table.dig("B")) + assert_equal([nil] * @rows.size, @table.dig("Z")) # empty col + + # by row then col + assert_equal(2, @table.dig(0, 1)) + assert_equal(6, @table.dig(1, "C")) + + # by col then row + assert_equal(5, @table.dig("B", 1)) + assert_equal(9, @table.dig("C", 2)) + end + + def test_dig_by_column + @table.by_col! + + assert_equal([2, 5, 8], @table.dig(1)) + assert_equal([2, 5, 8], @table.dig("B")) + + # by col then row + assert_equal(5, @table.dig("B", 1)) + assert_equal(9, @table.dig("C", 2)) + end + + def test_dig_by_row + @table.by_row! + + assert_equal(@rows[1], @table.dig(1)) + assert_raise(TypeError) { @table.dig("B") } + + # by row then col + assert_equal(2, @table.dig(0, 1)) + assert_equal(6, @table.dig(1, "C")) + end + + def test_dig_cell + table = CSV::Table.new([CSV::Row.new(["A"], [["foo", ["bar", ["baz"]]]])]) + + # by row, col then cell + assert_equal("foo", table.dig(0, "A", 0)) + assert_equal(["baz"], table.dig(0, "A", 1, 1)) + + # by col, row then cell + assert_equal("foo", table.dig("A", 0, 0)) + assert_equal(["baz"], table.dig("A", 0, 1, 1)) + end + + def test_dig_cell_no_dig + table = CSV::Table.new([CSV::Row.new(["A"], ["foo"])]) + + # by row, col then cell + assert_raise(TypeError) do + table.dig(0, "A", 0) + end + + # by col, row then cell + assert_raise(TypeError) do + table.dig("A", 0, 0) + end + end +end diff --git a/test/csv/write/test_converters.rb b/test/csv/write/test_converters.rb new file mode 100644 index 0000000000..0e0080b4c5 --- /dev/null +++ b/test/csv/write/test_converters.rb @@ -0,0 +1,53 @@ +# -*- coding: utf-8 -*- +# frozen_string_literal: false + +require_relative "../helper" + +module TestCSVWriteConverters + def test_one + assert_equal(%Q[=a,=b,=c\n], + generate_line(["a", "b", "c"], + write_converters: ->(value) {"=" + value})) + end + + def test_multiple + assert_equal(%Q[=a_,=b_,=c_\n], + generate_line(["a", "b", "c"], + write_converters: [ + ->(value) {"=" + value}, + ->(value) {value + "_"}, + ])) + end + + def test_nil_value + assert_equal(%Q[a,NaN,29\n], + generate_line(["a", nil, 29], + write_nil_value: "NaN")) + end + + def test_empty_value + assert_equal(%Q[a,,29\n], + generate_line(["a", "", 29], + write_empty_value: nil)) + end +end + +class TestCSVWriteConvertersGenerateLine < Test::Unit::TestCase + include TestCSVWriteConverters + extend DifferentOFS + + def generate_line(row, **kwargs) + CSV.generate_line(row, **kwargs) + end +end + +class TestCSVWriteConvertersGenerate < Test::Unit::TestCase + include TestCSVWriteConverters + extend DifferentOFS + + def generate_line(row, **kwargs) + CSV.generate(**kwargs) do |csv| + csv << row + end + end +end diff --git a/test/csv/write/test_force_quotes.rb b/test/csv/write/test_force_quotes.rb new file mode 100644 index 0000000000..622dcb021b --- /dev/null +++ b/test/csv/write/test_force_quotes.rb @@ -0,0 +1,78 @@ +# frozen_string_literal: false + +require_relative "../helper" + +module TestCSVWriteForceQuotes + def test_default + assert_equal(%Q[1,2,3#{$INPUT_RECORD_SEPARATOR}], + generate_line(["1", "2", "3"])) + end + + def test_true + assert_equal(%Q["1","2","3"#{$INPUT_RECORD_SEPARATOR}], + generate_line(["1", "2", "3"], + force_quotes: true)) + end + + def test_false + assert_equal(%Q[1,2,3#{$INPUT_RECORD_SEPARATOR}], + generate_line(["1", "2", "3"], + force_quotes: false)) + end + + def test_field_name + assert_equal(%Q["1",2,"3"#{$INPUT_RECORD_SEPARATOR}], + generate_line(["1", "2", "3"], + headers: ["a", "b", "c"], + force_quotes: ["a", :c])) + end + + def test_field_name_without_headers + force_quotes = ["a", "c"] + error = assert_raise(ArgumentError) do + generate_line(["1", "2", "3"], + force_quotes: force_quotes) + end + assert_equal(":headers is required when you use field name " + + "in :force_quotes: " + + "#{force_quotes.first.inspect}: #{force_quotes.inspect}", + error.message) + end + + def test_field_index + assert_equal(%Q["1",2,"3"#{$INPUT_RECORD_SEPARATOR}], + generate_line(["1", "2", "3"], + force_quotes: [0, 2])) + end + + def test_field_unknown + force_quotes = [1.1] + error = assert_raise(ArgumentError) do + generate_line(["1", "2", "3"], + force_quotes: force_quotes) + end + assert_equal(":force_quotes element must be field index or field name: " + + "#{force_quotes.first.inspect}: #{force_quotes.inspect}", + error.message) + end +end + +class TestCSVWriteForceQuotesGenerateLine < Test::Unit::TestCase + include TestCSVWriteForceQuotes + extend DifferentOFS + + def generate_line(row, **kwargs) + CSV.generate_line(row, **kwargs) + end +end + +class TestCSVWriteForceQuotesGenerate < Test::Unit::TestCase + include TestCSVWriteForceQuotes + extend DifferentOFS + + def generate_line(row, **kwargs) + CSV.generate(**kwargs) do |csv| + csv << row + end + end +end diff --git a/test/csv/write/test_general.rb b/test/csv/write/test_general.rb new file mode 100644 index 0000000000..677119e1ae --- /dev/null +++ b/test/csv/write/test_general.rb @@ -0,0 +1,246 @@ +# -*- coding: utf-8 -*- +# frozen_string_literal: false + +require_relative "../helper" + +module TestCSVWriteGeneral + include Helper + + def test_tab + assert_equal("\t#{$INPUT_RECORD_SEPARATOR}", + generate_line(["\t"])) + end + + def test_quote_character + assert_equal(%Q[foo,"""",baz#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo", %Q["], "baz"])) + end + + def test_quote_character_double + assert_equal(%Q[foo,"""""",baz#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo", %Q[""], "baz"])) + end + + def test_quote + assert_equal(%Q[foo,"""bar""",baz#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo", %Q["bar"], "baz"])) + end + + def test_quote_lf + assert_equal(%Q["""\n","""\n"#{$INPUT_RECORD_SEPARATOR}], + generate_line([%Q["\n], %Q["\n]])) + end + + def test_quote_cr + assert_equal(%Q["""\r","""\r"#{$INPUT_RECORD_SEPARATOR}], + generate_line([%Q["\r], %Q["\r]])) + end + + def test_quote_last + assert_equal(%Q[foo,"bar"""#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo", %Q[bar"]])) + end + + def test_quote_lf_last + assert_equal(%Q[foo,"\nbar"""#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo", %Q[\nbar"]])) + end + + def test_quote_lf_value_lf + assert_equal(%Q[foo,"""\nbar\n"""#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo", %Q["\nbar\n"]])) + end + + def test_quote_lf_value_lf_nil + assert_equal(%Q[foo,"""\nbar\n""",#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo", %Q["\nbar\n"], nil])) + end + + def test_cr + assert_equal(%Q[foo,"\r",baz#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo", "\r", "baz"])) + end + + def test_lf + assert_equal(%Q[foo,"\n",baz#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo", "\n", "baz"])) + end + + def test_cr_lf + assert_equal(%Q[foo,"\r\n",baz#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo", "\r\n", "baz"])) + end + + def test_cr_dot_lf + assert_equal(%Q[foo,"\r.\n",baz#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo", "\r.\n", "baz"])) + end + + def test_cr_lf_cr + assert_equal(%Q[foo,"\r\n\r",baz#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo", "\r\n\r", "baz"])) + end + + def test_cr_lf_lf + assert_equal(%Q[foo,"\r\n\n",baz#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo", "\r\n\n", "baz"])) + end + + def test_cr_lf_comma + assert_equal(%Q["\r\n,"#{$INPUT_RECORD_SEPARATOR}], + generate_line(["\r\n,"])) + end + + def test_cr_lf_comma_nil + assert_equal(%Q["\r\n,",#{$INPUT_RECORD_SEPARATOR}], + generate_line(["\r\n,", nil])) + end + + def test_comma + assert_equal(%Q[","#{$INPUT_RECORD_SEPARATOR}], + generate_line([","])) + end + + def test_comma_double + assert_equal(%Q[",",","#{$INPUT_RECORD_SEPARATOR}], + generate_line([",", ","])) + end + + def test_comma_and_value + assert_equal(%Q[foo,"foo,bar",baz#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo", "foo,bar", "baz"])) + end + + def test_one_element + assert_equal(%Q[foo#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo"])) + end + + def test_nil_values_only + assert_equal(%Q[,,#{$INPUT_RECORD_SEPARATOR}], + generate_line([nil, nil, nil])) + end + + def test_nil_double_only + assert_equal(%Q[,#{$INPUT_RECORD_SEPARATOR}], + generate_line([nil, nil])) + end + + def test_nil_values + assert_equal(%Q[foo,,,#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo", nil, nil, nil])) + end + + def test_nil_value_first + assert_equal(%Q[,foo,baz#{$INPUT_RECORD_SEPARATOR}], + generate_line([nil, "foo", "baz"])) + end + + def test_nil_value_middle + assert_equal(%Q[foo,,baz#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo", nil, "baz"])) + end + + def test_nil_value_last + assert_equal(%Q[foo,baz,#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo", "baz", nil])) + end + + def test_nil_empty + assert_equal(%Q[,""#{$INPUT_RECORD_SEPARATOR}], + generate_line([nil, ""])) + end + + def test_nil_cr + assert_equal(%Q[,"\r"#{$INPUT_RECORD_SEPARATOR}], + generate_line([nil, "\r"])) + end + + def test_values + assert_equal(%Q[foo,bar#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo", "bar"])) + end + + def test_semi_colon + assert_equal(%Q[;#{$INPUT_RECORD_SEPARATOR}], + generate_line([";"])) + end + + def test_semi_colon_values + assert_equal(%Q[;,;#{$INPUT_RECORD_SEPARATOR}], + generate_line([";", ";"])) + end + + def test_tab_values + assert_equal(%Q[\t,\t#{$INPUT_RECORD_SEPARATOR}], + generate_line(["\t", "\t"])) + end + + def test_col_sep + assert_equal(%Q[a;b;;c#{$INPUT_RECORD_SEPARATOR}], + generate_line(["a", "b", nil, "c"], + col_sep: ";")) + assert_equal(%Q[a\tb\t\tc#{$INPUT_RECORD_SEPARATOR}], + generate_line(["a", "b", nil, "c"], + col_sep: "\t")) + end + + def test_row_sep + assert_equal(%Q[a,b,,c\r\n], + generate_line(["a", "b", nil, "c"], + row_sep: "\r\n")) + end + + def test_force_quotes + assert_equal(%Q["1","b","","already ""quoted"""#{$INPUT_RECORD_SEPARATOR}], + generate_line([1, "b", nil, %Q{already "quoted"}], + force_quotes: true)) + end + + def test_encoding_utf8 + assert_equal(%Q[あ,い,う#{$INPUT_RECORD_SEPARATOR}], + generate_line(["あ" , "い", "う"])) + end + + def test_encoding_euc_jp + row = ["あ", "い", "う"].collect {|field| field.encode("EUC-JP")} + assert_equal(%Q[あ,い,う#{$INPUT_RECORD_SEPARATOR}].encode("EUC-JP"), + generate_line(row)) + end + + def test_encoding_with_default_internal + with_default_internal(Encoding::UTF_8) do + row = ["あ", "い", "う"].collect {|field| field.encode("EUC-JP")} + assert_equal(%Q[あ,い,う#{$INPUT_RECORD_SEPARATOR}].encode("EUC-JP"), + generate_line(row, encoding: Encoding::EUC_JP)) + end + end + + def test_with_default_internal + with_default_internal(Encoding::UTF_8) do + row = ["あ", "い", "う"].collect {|field| field.encode("EUC-JP")} + assert_equal(%Q[あ,い,う#{$INPUT_RECORD_SEPARATOR}].encode("EUC-JP"), + generate_line(row)) + end + end +end + +class TestCSVWriteGeneralGenerateLine < Test::Unit::TestCase + include TestCSVWriteGeneral + extend DifferentOFS + + def generate_line(row, **kwargs) + CSV.generate_line(row, **kwargs) + end +end + +class TestCSVWriteGeneralGenerate < Test::Unit::TestCase + include TestCSVWriteGeneral + extend DifferentOFS + + def generate_line(row, **kwargs) + CSV.generate(**kwargs) do |csv| + csv << row + end + end +end diff --git a/test/csv/write/test_quote_empty.rb b/test/csv/write/test_quote_empty.rb new file mode 100644 index 0000000000..70f73dad4a --- /dev/null +++ b/test/csv/write/test_quote_empty.rb @@ -0,0 +1,70 @@ +# -*- coding: utf-8 -*- +# frozen_string_literal: false + +require_relative "../helper" + +module TestCSVWriteQuoteEmpty + def test_quote_empty_default + assert_equal(%Q["""",""#{$INPUT_RECORD_SEPARATOR}], + generate_line([%Q["], ""])) + end + + def test_quote_empty_false + assert_equal(%Q["""",#{$INPUT_RECORD_SEPARATOR}], + generate_line([%Q["], ""], + quote_empty: false)) + end + + def test_empty_default + assert_equal(%Q[foo,"",baz#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo", "", "baz"])) + end + + def test_empty_false + assert_equal(%Q[foo,,baz#{$INPUT_RECORD_SEPARATOR}], + generate_line(["foo", "", "baz"], + quote_empty: false)) + end + + def test_empty_only_default + assert_equal(%Q[""#{$INPUT_RECORD_SEPARATOR}], + generate_line([""])) + end + + def test_empty_only_false + assert_equal(%Q[#{$INPUT_RECORD_SEPARATOR}], + generate_line([""], + quote_empty: false)) + end + + def test_empty_double_default + assert_equal(%Q["",""#{$INPUT_RECORD_SEPARATOR}], + generate_line(["", ""])) + end + + def test_empty_double_false + assert_equal(%Q[,#{$INPUT_RECORD_SEPARATOR}], + generate_line(["", ""], + quote_empty: false)) + end +end + +class TestCSVWriteQuoteEmptyGenerateLine < Test::Unit::TestCase + include TestCSVWriteQuoteEmpty + extend DifferentOFS + + def generate_line(row, **kwargs) + CSV.generate_line(row, **kwargs) + end +end + +class TestCSVWriteQuoteEmptyGenerate < Test::Unit::TestCase + include TestCSVWriteQuoteEmpty + extend DifferentOFS + + def generate_line(row, **kwargs) + CSV.generate(**kwargs) do |csv| + csv << row + end + end +end |