From b5aba69e60dec153ecab3263ebc3fa5e93662a46 Mon Sep 17 00:00:00 2001 From: naruse Date: Mon, 15 Apr 2019 09:22:11 +0000 Subject: merge revision(s) 66720: separate downloading of Unicode property files and auxiliary files Separate downloading of Unicode property files in ucd and in ucd/auxiliary. This is needed because we need information from separate index.html files to discover the exact file names of property files during a beta period. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/branches/ruby_2_6@67562 b2dd03c8-39d4-4d8f-98ff-823fe69b080e --- test/csv/helper.rb | 13 + test/csv/interface/test_delegation.rb | 47 ++++ test/csv/interface/test_read.rb | 277 ++++++++++++++++++++ test/csv/interface/test_read_write.rb | 51 ++++ test/csv/interface/test_write.rb | 174 +++++++++++++ test/csv/parse/test_general.rb | 4 +- test/csv/parse/test_invalid.rb | 36 +++ test/csv/parse/test_liberal_parsing.rb | 75 +++++- test/csv/parse/test_quote_char_nil.rb | 93 +++++++ test/csv/parse/test_row_separator.rb | 16 ++ test/csv/parse/test_skip_lines.rb | 105 ++++++++ test/csv/parse/test_strip.rb | 48 ++++ test/csv/test_encodings.rb | 11 +- test/csv/test_features.rb | 74 +----- test/csv/test_interface.rb | 450 --------------------------------- test/csv/write/test_converters.rb | 53 ++++ 16 files changed, 993 insertions(+), 534 deletions(-) create mode 100644 test/csv/interface/test_delegation.rb create mode 100644 test/csv/interface/test_read.rb create mode 100644 test/csv/interface/test_read_write.rb create mode 100644 test/csv/interface/test_write.rb create mode 100644 test/csv/parse/test_invalid.rb create mode 100644 test/csv/parse/test_quote_char_nil.rb create mode 100644 test/csv/parse/test_row_separator.rb create mode 100644 test/csv/parse/test_skip_lines.rb create mode 100644 test/csv/parse/test_strip.rb delete mode 100755 test/csv/test_interface.rb create mode 100644 test/csv/write/test_converters.rb (limited to 'test') diff --git a/test/csv/helper.rb b/test/csv/helper.rb index 4f7b00244b..2542cc9c97 100644 --- a/test/csv/helper.rb +++ b/test/csv/helper.rb @@ -1,5 +1,18 @@ +require "tempfile" require "test/unit" require "csv" require_relative "../lib/with_different_ofs.rb" + +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 +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..393619b763 --- /dev/null +++ b/test/csv/interface/test_read.rb @@ -0,0 +1,277 @@ +# 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"], options: {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 + + 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_io 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_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 + + 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..9ce3553d61 --- /dev/null +++ b/test/csv/interface/test_read_write.rb @@ -0,0 +1,51 @@ +# frozen_string_literal: false + +require_relative "../helper" + +class TestCSVInterfaceReadWrite < Test::Unit::TestCase + extend DifferentOFS + + def test_filter + rows = [[1, 2, 3], [4, 5]] + input = <<-CSV +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_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 +end diff --git a/test/csv/interface/test_write.rb b/test/csv/interface/test_write.rb new file mode 100644 index 0000000000..8511204ef0 --- /dev/null +++ b/test/csv/interface/test_write.rb @@ -0,0 +1,174 @@ +# 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 + + 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_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 + + 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/parse/test_general.rb b/test/csv/parse/test_general.rb index 2f235f16f6..49222c7159 100644 --- a/test/csv/parse/test_general.rb +++ b/test/csv/parse/test_general.rb @@ -142,7 +142,7 @@ class TestCSVParseGeneral < Test::Unit::TestCase error = assert_raise(CSV::MalformedCSVError) do CSV.parse_line("1,2\r,3", row_sep: "\n") end - assert_equal("Unquoted fields do not allow \\r or \\n in line 1.", + assert_equal("Unquoted fields do not allow new line <\"\\r\"> in line 1.", error.message) end @@ -158,7 +158,7 @@ line,5,jkl error = assert_raise(CSV::MalformedCSVError) do CSV.parse(csv) end - assert_equal("Unquoted fields do not allow \\r or \\n in line 4.", + assert_equal("Unquoted fields do not allow new line <\"\\r\"> in line 4.", error.message) end diff --git a/test/csv/parse/test_invalid.rb b/test/csv/parse/test_invalid.rb new file mode 100644 index 0000000000..b84707c2cc --- /dev/null +++ b/test/csv/parse/test_invalid.rb @@ -0,0 +1,36 @@ +# -*- 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) + error = assert_raise(CSV::MalformedCSVError) do + csv.shift + end + assert_equal("Illegal quoting in line 3.", + error.message) + assert_equal(CSV::Row.new(headers, ["ggg", "hhh", "iii"]), + csv.shift) + end +end diff --git a/test/csv/parse/test_liberal_parsing.rb b/test/csv/parse/test_liberal_parsing.rb index 22b1689a37..2f7b34689f 100644 --- a/test/csv/parse/test_liberal_parsing.rb +++ b/test/csv/parse/test_liberal_parsing.rb @@ -22,8 +22,7 @@ class TestCSVParseLiberalParsing < Test::Unit::TestCase error = assert_raise(CSV::MalformedCSVError) do CSV.parse_line(input) end - assert_equal("Do not allow except col_sep_split_separator " + - "after quoted fields in line 1.", + 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)) @@ -75,8 +74,7 @@ class TestCSVParseLiberalParsing < Test::Unit::TestCase error = assert_raise(CSV::MalformedCSVError) do CSV.parse(data) end - assert_equal("Do not allow except col_sep_split_separator " + - "after quoted fields in line 1.", + assert_equal("Any value after quoted field isn't allowed in line 1.", error.message) assert_equal([ [["a", %Q{""b""}]], @@ -90,4 +88,73 @@ class TestCSVParseLiberalParsing < Test::Unit::TestCase }), ]) 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{ax} + assert_equal([[%Q{a", 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_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..196858f1b0 --- /dev/null +++ b/test/csv/parse/test_skip_lines.rb @@ -0,0 +1,105 @@ +# 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 +end diff --git a/test/csv/parse/test_strip.rb b/test/csv/parse/test_strip.rb new file mode 100644 index 0000000000..160407bd94 --- /dev/null +++ b/test/csv/parse/test_strip.rb @@ -0,0 +1,48 @@ +# -*- 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_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 +end diff --git a/test/csv/test_encodings.rb b/test/csv/test_encodings.rb index 01101f1e09..64ea36a9a4 100755 --- a/test/csv/test_encodings.rb +++ b/test/csv/test_encodings.rb @@ -256,12 +256,13 @@ class TestCSVEncodings < Test::Unit::TestCase end def test_invalid_encoding_row_error - csv = CSV.new("invalid,\xF8\r\nvalid,x\r\n".force_encoding("UTF-8"), - encoding: "UTF-8") + 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 1.", + assert_equal("Invalid byte sequence in UTF-8 in line 2.", error.message) end @@ -270,9 +271,9 @@ class TestCSVEncodings < Test::Unit::TestCase def assert_parses(fields, encoding, options = { }) encoding = Encoding.find(encoding) unless encoding.is_a? Encoding orig_fields = fields - fields = encode_ary(fields, encoding) + fields = encode_ary(fields, encoding) data = ary_to_data(fields, options) - parsed = CSV.parse(data, 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.") diff --git a/test/csv/test_features.rb b/test/csv/test_features.rb index 0b92776026..306b880f6f 100755 --- a/test/csv/test_features.rb +++ b/test/csv/test_features.rb @@ -56,7 +56,7 @@ line,4,jkl 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 \\r or \\n in line 1.", + 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")) @@ -295,78 +295,6 @@ line,4,jkl assert_match(/\A\d\.\d\.\d\z/, CSV::VERSION) end - def test_accepts_comment_skip_lines_option - assert_nothing_raised(ArgumentError) do - CSV.new(@sample_data, :skip_lines => /\A\s*#/) - end - end - - def test_accepts_comment_defaults_to_nil - c = CSV.new(@sample_data) - assert_nil(c.skip_lines) - end - - class RegexStub - end - - def test_requires_skip_lines_to_call_match - regex_stub = RegexStub.new - csv = CSV.new(@sample_data, :skip_lines => regex_stub) - assert_raise_with_message(ArgumentError, /skip_lines/) do - csv.shift - end - end - - class Matchable - def initialize(pattern) - @pattern = pattern - end - - def match(line) - @pattern.match(line) - end - end - - def test_skip_lines_match - csv = <<-CSV.chomp -1 -# 2 -3 -# 4 - CSV - assert_equal([["1"], ["3"]], - CSV.parse(csv, :skip_lines => Matchable.new(/\A#/))) - end - - def test_comment_rows_are_ignored - sample_data = "line,1,a\n#not,a,line\nline,2,b\n #also,no,line" - c = CSV.new sample_data, :skip_lines => /\A\s*#/ - assert_equal [["line", "1", "a"], ["line", "2", "b"]], c.each.to_a - end - - def test_comment_rows_are_ignored_with_heredoc - sample_data = <<~EOL - 1,foo - .2,bar - 3,baz - EOL - - c = CSV.new(sample_data, skip_lines: ".") - assert_equal [["1", "foo"], ["3", "baz"]], c.each.to_a - end - - def test_quoted_skip_line_markers_are_ignored - sample_data = "line,1,a\n\"#not\",a,line\nline,2,b" - c = CSV.new sample_data, :skip_lines => /\A\s*#/ - assert_equal [["line", "1", "a"], ["#not", "a", "line"], ["line", "2", "b"]], c.each.to_a - end - - def test_string_works_like_a_regexp - sample_data = "line,1,a\n#(not,a,line\nline,2,b\n also,#no,line" - c = CSV.new sample_data, :skip_lines => "#" - assert_equal [["line", "1", "a"], ["line", "2", "b"]], c.each.to_a - end - def test_table_nil_equality assert_nothing_raised(NoMethodError) { CSV.parse("test", headers: true) == nil } end diff --git a/test/csv/test_interface.rb b/test/csv/test_interface.rb deleted file mode 100755 index 77730fa5db..0000000000 --- a/test/csv/test_interface.rb +++ /dev/null @@ -1,450 +0,0 @@ -# -*- coding: utf-8 -*- -# frozen_string_literal: false - -require_relative "helper" -require "tempfile" - -class TestCSVInterface < Test::Unit::TestCase - extend DifferentOFS - - def setup - super - @tempfile = Tempfile.new(%w"temp .csv") - @tempfile.close - @path = @tempfile.path - - File.open(@path, "wb") do |file| - file << "1\t2\t3\r\n" - file << "4\t5\r\n" - end - - @expected = [%w{1 2 3}, %w{4 5}] - end - - def teardown - @tempfile.close(true) - super - end - - ### Test Read Interface ### - - def test_foreach - CSV.foreach(@path, col_sep: "\t", row_sep: "\r\n") do |row| - assert_equal(@expected.shift, row) - end - end - - def test_foreach_enum - CSV.foreach(@path, col_sep: "\t", row_sep: "\r\n").zip(@expected) do |row, exp| - assert_equal(exp, row) - end - end - - def test_open_and_close - csv = CSV.open(@path, "r+", col_sep: "\t", row_sep: "\r\n") - assert_not_nil(csv) - assert_instance_of(CSV, csv) - assert_not_predicate(csv, :closed?) - csv.close - assert_predicate(csv, :closed?) - - ret = CSV.open(@path) do |new_csv| - csv = new_csv - assert_instance_of(CSV, new_csv) - "Return value." - end - assert_predicate(csv, :closed?) - assert_equal("Return value.", ret) - end - - def test_open_encoding_valid - # U+1F600 GRINNING FACE - # U+1F601 GRINNING FACE WITH SMILING EYES - File.open(@path, "w") do |file| - file << "\u{1F600},\u{1F601}" - end - CSV.open(@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(@path, "w") do |file| - file << "\u{1F600},\u{1F601}" - end - CSV.open(@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_io do - CSV.open(@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(@path, "w") do |file| - file << "\u{FEFF}\u{1F600},\u{1F601}" - end - CSV.open(@path, encoding: "bom|utf-8") do |csv| - assert_equal([["\u{1F600}", "\u{1F601}"]], - csv.to_a) - end - end - - def test_parse - data = File.binread(@path) - assert_equal( @expected, - CSV.parse(data, col_sep: "\t", row_sep: "\r\n") ) - - CSV.parse(data, col_sep: "\t", row_sep: "\r\n") do |row| - assert_equal(@expected.shift, row) - end - end - - def test_parse_line - row = CSV.parse_line("1;2;3", col_sep: ";") - assert_not_nil(row) - assert_instance_of(Array, row) - assert_equal(%w{1 2 3}, row) - - # shortcut interface - row = "1;2;3".parse_csv(col_sep: ";") - assert_not_nil(row) - assert_instance_of(Array, row) - assert_equal(%w{1 2 3}, row) - end - - def test_parse_line_with_empty_lines - assert_equal(nil, CSV.parse_line("")) # to signal eof - assert_equal(Array.new, CSV.parse_line("\n1,2,3")) - end - - def test_parse_header_only - table = CSV.parse("a,b,c", headers: true) - assert_equal([ - ["a", "b", "c"], - [], - ], - [ - table.headers, - table.each.to_a, - ]) - end - - def test_read_and_readlines - assert_equal( @expected, - CSV.read(@path, col_sep: "\t", row_sep: "\r\n") ) - assert_equal( @expected, - CSV.readlines(@path, col_sep: "\t", row_sep: "\r\n") ) - - - data = CSV.open(@path, col_sep: "\t", row_sep: "\r\n") do |csv| - csv.read - end - assert_equal(@expected, data) - data = CSV.open(@path, col_sep: "\t", row_sep: "\r\n") do |csv| - csv.readlines - end - assert_equal(@expected, data) - end - - def test_table - table = CSV.table(@path, col_sep: "\t", row_sep: "\r\n") - assert_instance_of(CSV::Table, table) - assert_equal([[:"1", :"2", :"3"], [4, 5, nil]], table.to_a) - end - - def test_shift # aliased as gets() and readline() - CSV.open(@path, "rb+", col_sep: "\t", row_sep: "\r\n") do |csv| - assert_equal(@expected.shift, csv.shift) - assert_equal(@expected.shift, csv.shift) - assert_equal(nil, csv.shift) - end - end - - def test_enumerators_are_supported - CSV.open(@path, col_sep: "\t", row_sep: "\r\n") do |csv| - enum = csv.each - assert_instance_of(Enumerator, enum) - assert_equal(@expected.shift, enum.next) - end - end - - def test_nil_is_not_acceptable - assert_raise_with_message ArgumentError, "Cannot parse nil as CSV" do - CSV.new(nil) - end - end - - def test_open_handles_prematurely_closed_file_descriptor_gracefully - assert_nothing_raised(Exception) do - CSV.open(@path) do |csv| - csv.close - end - end - end - - ### Test Write Interface ### - - def test_generate - str = CSV.generate do |csv| # default empty String - assert_instance_of(CSV, csv) - assert_equal(csv, csv << [1, 2, 3]) - assert_equal(csv, csv << [4, nil, 5]) - end - assert_not_nil(str) - assert_instance_of(String, str) - assert_equal("1,2,3\n4,,5\n", str) - - CSV.generate(str) do |csv| # appending to a String - assert_equal(csv, csv << ["last", %Q{"row"}]) - end - assert_equal(%Q{1,2,3\n4,,5\nlast,"""row"""\n}, str) - - out = CSV.generate("test") { |csv| csv << ["row"] } - assert_equal("testrow\n", out) - end - - def test_generate_line - line = CSV.generate_line(%w{1 2 3}, col_sep: ";") - assert_not_nil(line) - assert_instance_of(String, line) - assert_equal("1;2;3\n", line) - - # shortcut interface - line = %w{1 2 3}.to_csv(col_sep: ";") - assert_not_nil(line) - assert_instance_of(String, line) - assert_equal("1;2;3\n", line) - - line = CSV.generate_line(%w"1 2", row_sep: nil) - assert_equal("1,2", line) - end - - def test_write_header_detection - File.unlink(@path) - - headers = %w{a b c} - CSV.open(@path, "w", headers: true) do |csv| - csv << headers - csv << %w{1 2 3} - assert_equal(headers, csv.headers) - end - end - - def test_write_lineno - File.unlink(@path) - - CSV.open(@path, "w") do |csv| - lines = 20 - lines.times { csv << %w{a b c} } - assert_equal(lines, csv.lineno) - end - end - - def test_write_hash - File.unlink(@path) - - lines = [{a: 1, b: 2, c: 3}, {a: 4, b: 5, c: 6}] - CSV.open( @path, "wb", headers: true, - header_converters: :symbol ) do |csv| - csv << lines.first.keys - lines.each { |line| csv << line } - end - CSV.open( @path, "rb", headers: true, - converters: :all, - header_converters: :symbol ) do |csv| - csv.each { |line| assert_equal(lines.shift, line.to_hash) } - end - end - - def test_write_hash_with_string_keys - File.unlink(@path) - - lines = [{a: 1, b: 2, c: 3}, {a: 4, b: 5, c: 6}] - CSV.open( @path, "wb", headers: true ) do |csv| - csv << lines.first.keys - lines.each { |line| csv << line } - end - CSV.open( @path, "rb", headers: true ) do |csv| - csv.each do |line| - csv.headers.each_with_index do |header, h| - keys = line.to_hash.keys - assert_instance_of(String, keys[h]) - assert_same(header, keys[h]) - end - end - end - end - - def test_write_hash_with_headers_array - File.unlink(@path) - - lines = [{a: 1, b: 2, c: 3}, {a: 4, b: 5, c: 6}] - CSV.open(@path, "wb", headers: [:b, :a, :c]) do |csv| - lines.each { |line| csv << line } - end - - # test writing fields in the correct order - File.open(@path, "rb") do |f| - assert_equal("2,1,3", f.gets.strip) - assert_equal("5,4,6", f.gets.strip) - end - - # test reading CSV with headers - CSV.open( @path, "rb", headers: [:b, :a, :c], - converters: :all ) do |csv| - csv.each { |line| assert_equal(lines.shift, line.to_hash) } - end - end - - def test_write_hash_with_headers_string - File.unlink(@path) - - lines = [{"a" => 1, "b" => 2, "c" => 3}, {"a" => 4, "b" => 5, "c" => 6}] - CSV.open(@path, "wb", headers: "b|a|c", col_sep: "|") do |csv| - lines.each { |line| csv << line } - end - - # test writing fields in the correct order - File.open(@path, "rb") do |f| - assert_equal("2|1|3", f.gets.strip) - assert_equal("5|4|6", f.gets.strip) - end - - # test reading CSV with headers - CSV.open( @path, "rb", headers: "b|a|c", - col_sep: "|", - converters: :all ) do |csv| - csv.each { |line| assert_equal(lines.shift, line.to_hash) } - end - end - - def test_write_headers - File.unlink(@path) - - lines = [{"a" => 1, "b" => 2, "c" => 3}, {"a" => 4, "b" => 5, "c" => 6}] - CSV.open( @path, "wb", headers: "b|a|c", - write_headers: true, - col_sep: "|" ) do |csv| - lines.each { |line| csv << line } - end - - # test writing fields in the correct order - File.open(@path, "rb") do |f| - assert_equal("b|a|c", f.gets.strip) - assert_equal("2|1|3", f.gets.strip) - assert_equal("5|4|6", f.gets.strip) - end - - # test reading CSV with headers - CSV.open( @path, "rb", headers: true, - col_sep: "|", - converters: :all ) do |csv| - csv.each { |line| assert_equal(lines.shift, line.to_hash) } - end - end - - def test_write_headers_empty - File.unlink(@path) - - CSV.open( @path, "wb", headers: "b|a|c", - write_headers: true, - col_sep: "|" ) do |csv| - end - - File.open(@path, "rb") do |f| - assert_equal("b|a|c", f.gets.strip) - end - end - - def test_append # aliased add_row() and puts() - File.unlink(@path) - - CSV.open(@path, "wb", col_sep: "\t", row_sep: "\r\n") do |csv| - @expected.each { |row| csv << row } - end - - test_shift - - # same thing using CSV::Row objects - File.unlink(@path) - - CSV.open(@path, "wb", col_sep: "\t", row_sep: "\r\n") do |csv| - @expected.each { |row| csv << CSV::Row.new(Array.new, row) } - end - - test_shift - end - - ### Test Read and Write Interface ### - - def test_filter - assert_respond_to(CSV, :filter) - - expected = [[1, 2, 3], [4, 5]] - CSV.filter( "1;2;3\n4;5\n", (result = String.new), - in_col_sep: ";", out_col_sep: ",", - converters: :all ) do |row| - assert_equal(row, expected.shift) - row.map! { |n| n * 2 } - row << "Added\r" - end - assert_equal("2,4,6,\"Added\r\"\n8,10,\"Added\r\"\n", result) - end - - def test_instance - csv = String.new - - first = nil - assert_nothing_raised(Exception) do - first = CSV.instance(csv, col_sep: ";") - first << %w{a b c} - end - - assert_equal("a;b;c\n", csv) - - second = nil - assert_nothing_raised(Exception) do - second = CSV.instance(csv, col_sep: ";") - second << [1, 2, 3] - end - - assert_equal(first.object_id, second.object_id) - assert_equal("a;b;c\n1;2;3\n", csv) - - # shortcuts - assert_equal(STDOUT, CSV.instance.instance_eval { @io }) - assert_equal(STDOUT, CSV { |new_csv| new_csv.instance_eval { @io } }) - end - - def test_options_are_not_modified - opt = {}.freeze - assert_nothing_raised { CSV.foreach(@path, opt) } - assert_nothing_raised { CSV.open(@path, opt){} } - assert_nothing_raised { CSV.parse("", opt) } - assert_nothing_raised { CSV.parse_line("", opt) } - assert_nothing_raised { CSV.read(@path, opt) } - assert_nothing_raised { CSV.readlines(@path, opt) } - assert_nothing_raised { CSV.table(@path, opt) } - assert_nothing_raised { CSV.generate(opt){} } - assert_nothing_raised { CSV.generate_line([], opt) } - assert_nothing_raised { CSV.filter("", "", opt){} } - assert_nothing_raised { CSV.instance("", opt) } - end -end diff --git a/test/csv/write/test_converters.rb b/test/csv/write/test_converters.rb new file mode 100644 index 0000000000..a93b1040ac --- /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,c\n], + generate_line(["a", nil, "c"], + write_nil_value: "NaN")) + end + + def test_empty_value + assert_equal(%Q[a,,c\n], + generate_line(["a", "", "c"], + 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 -- cgit v1.2.3