diff options
Diffstat (limited to 'spec/ruby/core/encoding')
35 files changed, 685 insertions, 199 deletions
diff --git a/spec/ruby/core/encoding/compatible_spec.rb b/spec/ruby/core/encoding/compatible_spec.rb index dc47a6553a..31376a3b75 100644 --- a/spec/ruby/core/encoding/compatible_spec.rb +++ b/spec/ruby/core/encoding/compatible_spec.rb @@ -1,4 +1,4 @@ -# -*- encoding: binary -*- +# encoding: binary require_relative '../../spec_helper' @@ -7,7 +7,7 @@ require_relative '../../spec_helper' describe "Encoding.compatible? String, String" do describe "when the first's Encoding is valid US-ASCII" do before :each do - @str = "abc".force_encoding Encoding::US_ASCII + @str = "abc".dup.force_encoding Encoding::US_ASCII end it "returns US-ASCII when the second's is US-ASCII" do @@ -33,28 +33,28 @@ describe "Encoding.compatible? String, String" do describe "when the first's Encoding is ASCII compatible and ASCII only" do it "returns the first's Encoding if the second is ASCII compatible and ASCII only" do - [ [Encoding, "abc".force_encoding("UTF-8"), "123".force_encoding("Shift_JIS"), Encoding::UTF_8], - [Encoding, "123".force_encoding("Shift_JIS"), "abc".force_encoding("UTF-8"), Encoding::Shift_JIS] + [ [Encoding, "abc".dup.force_encoding("UTF-8"), "123".dup.force_encoding("Shift_JIS"), Encoding::UTF_8], + [Encoding, "123".dup.force_encoding("Shift_JIS"), "abc".dup.force_encoding("UTF-8"), Encoding::Shift_JIS] ].should be_computed_by(:compatible?) end it "returns the first's Encoding if the second is ASCII compatible and ASCII only" do - [ [Encoding, "abc".force_encoding("BINARY"), "123".force_encoding("US-ASCII"), Encoding::BINARY], - [Encoding, "123".force_encoding("US-ASCII"), "abc".force_encoding("BINARY"), Encoding::US_ASCII] + [ [Encoding, "abc".dup.force_encoding("BINARY"), "123".dup.force_encoding("US-ASCII"), Encoding::BINARY], + [Encoding, "123".dup.force_encoding("US-ASCII"), "abc".dup.force_encoding("BINARY"), Encoding::US_ASCII] ].should be_computed_by(:compatible?) end it "returns the second's Encoding if the second is ASCII compatible but not ASCII only" do - [ [Encoding, "abc".force_encoding("UTF-8"), "\xff".force_encoding("Shift_JIS"), Encoding::Shift_JIS], - [Encoding, "123".force_encoding("Shift_JIS"), "\xff".force_encoding("UTF-8"), Encoding::UTF_8], - [Encoding, "abc".force_encoding("BINARY"), "\xff".force_encoding("US-ASCII"), Encoding::US_ASCII], - [Encoding, "123".force_encoding("US-ASCII"), "\xff".force_encoding("BINARY"), Encoding::BINARY], + [ [Encoding, "abc".dup.force_encoding("UTF-8"), "\xff".dup.force_encoding("Shift_JIS"), Encoding::Shift_JIS], + [Encoding, "123".dup.force_encoding("Shift_JIS"), "\xff".dup.force_encoding("UTF-8"), Encoding::UTF_8], + [Encoding, "abc".dup.force_encoding("BINARY"), "\xff".dup.force_encoding("US-ASCII"), Encoding::US_ASCII], + [Encoding, "123".dup.force_encoding("US-ASCII"), "\xff".dup.force_encoding("BINARY"), Encoding::BINARY], ].should be_computed_by(:compatible?) end it "returns nil if the second's Encoding is not ASCII compatible" do - a = "abc".force_encoding("UTF-8") - b = "123".force_encoding("UTF-16LE") + a = "abc".dup.force_encoding("UTF-8") + b = "1234".dup.force_encoding("UTF-16LE") Encoding.compatible?(a, b).should be_nil end end @@ -75,7 +75,7 @@ describe "Encoding.compatible? String, String" do describe "when the first's Encoding is not ASCII compatible" do before :each do - @str = "abc".force_encoding Encoding::UTF_7 + @str = "abc".dup.force_encoding Encoding::UTF_7 end it "returns nil when the second String is US-ASCII" do @@ -91,14 +91,14 @@ describe "Encoding.compatible? String, String" do end it "returns the Encoding when the second's Encoding is not ASCII compatible but the same as the first's Encoding" do - encoding = Encoding.compatible?(@str, "def".force_encoding("utf-7")) + encoding = Encoding.compatible?(@str, "def".dup.force_encoding("utf-7")) encoding.should == Encoding::UTF_7 end end describe "when the first's Encoding is invalid" do before :each do - @str = "\xff".force_encoding Encoding::UTF_8 + @str = "\xff".dup.force_encoding Encoding::UTF_8 end it "returns the first's Encoding when the second's Encoding is US-ASCII" do @@ -114,11 +114,11 @@ describe "Encoding.compatible? String, String" do end it "returns nil when the second's Encoding is invalid and ASCII only" do - Encoding.compatible?(@str, "\x7f".force_encoding("utf-16be")).should be_nil + Encoding.compatible?(@str, "\x7f\x7f".dup.force_encoding("utf-16be")).should be_nil end it "returns nil when the second's Encoding is invalid and not ASCII only" do - Encoding.compatible?(@str, "\xff".force_encoding("utf-16be")).should be_nil + Encoding.compatible?(@str, "\xff\xff".dup.force_encoding("utf-16be")).should be_nil end it "returns the Encoding when the second's Encoding is invalid but the same as the first" do @@ -129,7 +129,7 @@ describe "Encoding.compatible? String, String" do describe "when the first String is empty and the second is not" do describe "and the first's Encoding is ASCII compatible" do before :each do - @str = "".force_encoding("utf-8") + @str = "".dup.force_encoding("utf-8") end it "returns the first's encoding when the second String is ASCII only" do @@ -143,7 +143,7 @@ describe "Encoding.compatible? String, String" do describe "when the first's Encoding is not ASCII compatible" do before :each do - @str = "".force_encoding Encoding::UTF_7 + @str = "".dup.force_encoding Encoding::UTF_7 end it "returns the second string's encoding" do @@ -154,18 +154,391 @@ describe "Encoding.compatible? String, String" do describe "when the second String is empty" do before :each do - @str = "abc".force_encoding("utf-7") + @str = "abc".dup.force_encoding("utf-7") end it "returns the first Encoding" do Encoding.compatible?(@str, "").should == Encoding::UTF_7 end end + + # Encoding negotiation depends on whether encodings are ASCII-compatible, empty + # and contain only ASCII characters (that take 7 bits). Check US-ASCII, UTF-8 and + # BINARY encodings (as most common) as well as an ASCII-compatible, a non-ASCII-compatible and a dummy + # encodings in all possible combinations. + describe "compatibility matrix" do + +# Use the following script to regenerate the matrix: +# +# ``` +# # encoding: binary +# +# ENCODINGS = [ +# "US-ASCII", +# "UTF-8", +# "ASCII-8BIT", +# "ISO-8859-1", # ASCII-compatible +# "UTF-16BE", # non-ASCII-compatible +# "ISO-2022-JP" # dummy +# ] +# +# TYPES = [:empty, :"7bits", :non7bits] +# +# VALUES = { +# empty: "", +# :"7bits" => "\x01\x01", +# non7bits: "\x01\x81" +# } +# +# ENCODINGS.product(TYPES, ENCODINGS, TYPES).each do |encoding1, type1, encoding2, type2| +# value1 = VALUES[type1].dup.force_encoding(encoding1) +# value2 = VALUES[type2].dup.force_encoding(encoding2) +# +# result_encoding = Encoding.compatible?(value1, value2) +# +# puts "[#{encoding1.inspect}, #{value1.inspect}, #{encoding2.inspect}, #{value2.inspect}, #{result_encoding&.name.inspect}]," +# end +# ``` + + matrix = [ + ["US-ASCII", "", "US-ASCII", "", "US-ASCII"], + ["US-ASCII", "", "US-ASCII", "\x01\x01", "US-ASCII"], + ["US-ASCII", "", "US-ASCII", "\x01\x81", "US-ASCII"], + ["US-ASCII", "", "UTF-8", "", "US-ASCII"], + ["US-ASCII", "", "UTF-8", "\u0001\u0001", "US-ASCII"], + ["US-ASCII", "", "UTF-8", "\u0001\x81", "UTF-8"], + ["US-ASCII", "", "ASCII-8BIT", "", "US-ASCII"], + ["US-ASCII", "", "ASCII-8BIT", "\x01\x01", "US-ASCII"], + ["US-ASCII", "", "ASCII-8BIT", "\x01\x81", "ASCII-8BIT"], + ["US-ASCII", "", "ISO-8859-1", "", "US-ASCII"], + ["US-ASCII", "", "ISO-8859-1", "\x01\x01", "US-ASCII"], + ["US-ASCII", "", "ISO-8859-1", "\x01\x81", "ISO-8859-1"], + ["US-ASCII", "", "UTF-16BE", "", "US-ASCII"], + ["US-ASCII", "", "UTF-16BE", "\u0101", "UTF-16BE"], + ["US-ASCII", "", "UTF-16BE", "\u0181", "UTF-16BE"], + ["US-ASCII", "", "ISO-2022-JP", "", "US-ASCII"], + ["US-ASCII", "", "ISO-2022-JP", "\x01\x01", "ISO-2022-JP"], + ["US-ASCII", "", "ISO-2022-JP", "\x01\x81", "ISO-2022-JP"], + ["US-ASCII", "\x01\x01", "US-ASCII", "", "US-ASCII"], + ["US-ASCII", "\x01\x01", "US-ASCII", "\x01\x01", "US-ASCII"], + ["US-ASCII", "\x01\x01", "US-ASCII", "\x01\x81", "US-ASCII"], + ["US-ASCII", "\x01\x01", "UTF-8", "", "US-ASCII"], + ["US-ASCII", "\x01\x01", "UTF-8", "\u0001\u0001", "US-ASCII"], + ["US-ASCII", "\x01\x01", "UTF-8", "\u0001\x81", "UTF-8"], + ["US-ASCII", "\x01\x01", "ASCII-8BIT", "", "US-ASCII"], + ["US-ASCII", "\x01\x01", "ASCII-8BIT", "\x01\x01", "US-ASCII"], + ["US-ASCII", "\x01\x01", "ASCII-8BIT", "\x01\x81", "ASCII-8BIT"], + ["US-ASCII", "\x01\x01", "ISO-8859-1", "", "US-ASCII"], + ["US-ASCII", "\x01\x01", "ISO-8859-1", "\x01\x01", "US-ASCII"], + ["US-ASCII", "\x01\x01", "ISO-8859-1", "\x01\x81", "ISO-8859-1"], + ["US-ASCII", "\x01\x01", "UTF-16BE", "", "US-ASCII"], + ["US-ASCII", "\x01\x01", "UTF-16BE", "\u0101", nil], + ["US-ASCII", "\x01\x01", "UTF-16BE", "\u0181", nil], + ["US-ASCII", "\x01\x01", "ISO-2022-JP", "", "US-ASCII"], + ["US-ASCII", "\x01\x01", "ISO-2022-JP", "\x01\x01", nil], + ["US-ASCII", "\x01\x01", "ISO-2022-JP", "\x01\x81", nil], + ["US-ASCII", "\x01\x81", "US-ASCII", "", "US-ASCII"], + ["US-ASCII", "\x01\x81", "US-ASCII", "\x01\x01", "US-ASCII"], + ["US-ASCII", "\x01\x81", "US-ASCII", "\x01\x81", "US-ASCII"], + ["US-ASCII", "\x01\x81", "UTF-8", "", "US-ASCII"], + ["US-ASCII", "\x01\x81", "UTF-8", "\u0001\u0001", "US-ASCII"], + ["US-ASCII", "\x01\x81", "UTF-8", "\u0001\x81", nil], + ["US-ASCII", "\x01\x81", "ASCII-8BIT", "", "US-ASCII"], + ["US-ASCII", "\x01\x81", "ASCII-8BIT", "\x01\x01", "US-ASCII"], + ["US-ASCII", "\x01\x81", "ASCII-8BIT", "\x01\x81", nil], + ["US-ASCII", "\x01\x81", "ISO-8859-1", "", "US-ASCII"], + ["US-ASCII", "\x01\x81", "ISO-8859-1", "\x01\x01", "US-ASCII"], + ["US-ASCII", "\x01\x81", "ISO-8859-1", "\x01\x81", nil], + ["US-ASCII", "\x01\x81", "UTF-16BE", "", "US-ASCII"], + ["US-ASCII", "\x01\x81", "UTF-16BE", "\u0101", nil], + ["US-ASCII", "\x01\x81", "UTF-16BE", "\u0181", nil], + ["US-ASCII", "\x01\x81", "ISO-2022-JP", "", "US-ASCII"], + ["US-ASCII", "\x01\x81", "ISO-2022-JP", "\x01\x01", nil], + ["US-ASCII", "\x01\x81", "ISO-2022-JP", "\x01\x81", nil], + ["UTF-8", "", "US-ASCII", "", "UTF-8"], + ["UTF-8", "", "US-ASCII", "\x01\x01", "UTF-8"], + ["UTF-8", "", "US-ASCII", "\x01\x81", "US-ASCII"], + ["UTF-8", "", "UTF-8", "", "UTF-8"], + ["UTF-8", "", "UTF-8", "\u0001\u0001", "UTF-8"], + ["UTF-8", "", "UTF-8", "\u0001\x81", "UTF-8"], + ["UTF-8", "", "ASCII-8BIT", "", "UTF-8"], + ["UTF-8", "", "ASCII-8BIT", "\x01\x01", "UTF-8"], + ["UTF-8", "", "ASCII-8BIT", "\x01\x81", "ASCII-8BIT"], + ["UTF-8", "", "ISO-8859-1", "", "UTF-8"], + ["UTF-8", "", "ISO-8859-1", "\x01\x01", "UTF-8"], + ["UTF-8", "", "ISO-8859-1", "\x01\x81", "ISO-8859-1"], + ["UTF-8", "", "UTF-16BE", "", "UTF-8"], + ["UTF-8", "", "UTF-16BE", "\u0101", "UTF-16BE"], + ["UTF-8", "", "UTF-16BE", "\u0181", "UTF-16BE"], + ["UTF-8", "", "ISO-2022-JP", "", "UTF-8"], + ["UTF-8", "", "ISO-2022-JP", "\x01\x01", "ISO-2022-JP"], + ["UTF-8", "", "ISO-2022-JP", "\x01\x81", "ISO-2022-JP"], + ["UTF-8", "\u0001\u0001", "US-ASCII", "", "UTF-8"], + ["UTF-8", "\u0001\u0001", "US-ASCII", "\x01\x01", "UTF-8"], + ["UTF-8", "\u0001\u0001", "US-ASCII", "\x01\x81", "US-ASCII"], + ["UTF-8", "\u0001\u0001", "UTF-8", "", "UTF-8"], + ["UTF-8", "\u0001\u0001", "UTF-8", "\u0001\u0001", "UTF-8"], + ["UTF-8", "\u0001\u0001", "UTF-8", "\u0001\x81", "UTF-8"], + ["UTF-8", "\u0001\u0001", "ASCII-8BIT", "", "UTF-8"], + ["UTF-8", "\u0001\u0001", "ASCII-8BIT", "\x01\x01", "UTF-8"], + ["UTF-8", "\u0001\u0001", "ASCII-8BIT", "\x01\x81", "ASCII-8BIT"], + ["UTF-8", "\u0001\u0001", "ISO-8859-1", "", "UTF-8"], + ["UTF-8", "\u0001\u0001", "ISO-8859-1", "\x01\x01", "UTF-8"], + ["UTF-8", "\u0001\u0001", "ISO-8859-1", "\x01\x81", "ISO-8859-1"], + ["UTF-8", "\u0001\u0001", "UTF-16BE", "", "UTF-8"], + ["UTF-8", "\u0001\u0001", "UTF-16BE", "\u0101", nil], + ["UTF-8", "\u0001\u0001", "UTF-16BE", "\u0181", nil], + ["UTF-8", "\u0001\u0001", "ISO-2022-JP", "", "UTF-8"], + ["UTF-8", "\u0001\u0001", "ISO-2022-JP", "\x01\x01", nil], + ["UTF-8", "\u0001\u0001", "ISO-2022-JP", "\x01\x81", nil], + ["UTF-8", "\u0001\x81", "US-ASCII", "", "UTF-8"], + ["UTF-8", "\u0001\x81", "US-ASCII", "\x01\x01", "UTF-8"], + ["UTF-8", "\u0001\x81", "US-ASCII", "\x01\x81", nil], + ["UTF-8", "\u0001\x81", "UTF-8", "", "UTF-8"], + ["UTF-8", "\u0001\x81", "UTF-8", "\u0001\u0001", "UTF-8"], + ["UTF-8", "\u0001\x81", "UTF-8", "\u0001\x81", "UTF-8"], + ["UTF-8", "\u0001\x81", "ASCII-8BIT", "", "UTF-8"], + ["UTF-8", "\u0001\x81", "ASCII-8BIT", "\x01\x01", "UTF-8"], + ["UTF-8", "\u0001\x81", "ASCII-8BIT", "\x01\x81", nil], + ["UTF-8", "\u0001\x81", "ISO-8859-1", "", "UTF-8"], + ["UTF-8", "\u0001\x81", "ISO-8859-1", "\x01\x01", "UTF-8"], + ["UTF-8", "\u0001\x81", "ISO-8859-1", "\x01\x81", nil], + ["UTF-8", "\u0001\x81", "UTF-16BE", "", "UTF-8"], + ["UTF-8", "\u0001\x81", "UTF-16BE", "\u0101", nil], + ["UTF-8", "\u0001\x81", "UTF-16BE", "\u0181", nil], + ["UTF-8", "\u0001\x81", "ISO-2022-JP", "", "UTF-8"], + ["UTF-8", "\u0001\x81", "ISO-2022-JP", "\x01\x01", nil], + ["UTF-8", "\u0001\x81", "ISO-2022-JP", "\x01\x81", nil], + ["ASCII-8BIT", "", "US-ASCII", "", "ASCII-8BIT"], + ["ASCII-8BIT", "", "US-ASCII", "\x01\x01", "ASCII-8BIT"], + ["ASCII-8BIT", "", "US-ASCII", "\x01\x81", "US-ASCII"], + ["ASCII-8BIT", "", "UTF-8", "", "ASCII-8BIT"], + ["ASCII-8BIT", "", "UTF-8", "\u0001\u0001", "ASCII-8BIT"], + ["ASCII-8BIT", "", "UTF-8", "\u0001\x81", "UTF-8"], + ["ASCII-8BIT", "", "ASCII-8BIT", "", "ASCII-8BIT"], + ["ASCII-8BIT", "", "ASCII-8BIT", "\x01\x01", "ASCII-8BIT"], + ["ASCII-8BIT", "", "ASCII-8BIT", "\x01\x81", "ASCII-8BIT"], + ["ASCII-8BIT", "", "ISO-8859-1", "", "ASCII-8BIT"], + ["ASCII-8BIT", "", "ISO-8859-1", "\x01\x01", "ASCII-8BIT"], + ["ASCII-8BIT", "", "ISO-8859-1", "\x01\x81", "ISO-8859-1"], + ["ASCII-8BIT", "", "UTF-16BE", "", "ASCII-8BIT"], + ["ASCII-8BIT", "", "UTF-16BE", "\u0101", "UTF-16BE"], + ["ASCII-8BIT", "", "UTF-16BE", "\u0181", "UTF-16BE"], + ["ASCII-8BIT", "", "ISO-2022-JP", "", "ASCII-8BIT"], + ["ASCII-8BIT", "", "ISO-2022-JP", "\x01\x01", "ISO-2022-JP"], + ["ASCII-8BIT", "", "ISO-2022-JP", "\x01\x81", "ISO-2022-JP"], + ["ASCII-8BIT", "\x01\x01", "US-ASCII", "", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x01", "US-ASCII", "\x01\x01", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x01", "US-ASCII", "\x01\x81", "US-ASCII"], + ["ASCII-8BIT", "\x01\x01", "UTF-8", "", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x01", "UTF-8", "\u0001\u0001", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x01", "UTF-8", "\u0001\x81", "UTF-8"], + ["ASCII-8BIT", "\x01\x01", "ASCII-8BIT", "", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x01", "ASCII-8BIT", "\x01\x01", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x01", "ASCII-8BIT", "\x01\x81", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x01", "ISO-8859-1", "", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x01", "ISO-8859-1", "\x01\x01", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x01", "ISO-8859-1", "\x01\x81", "ISO-8859-1"], + ["ASCII-8BIT", "\x01\x01", "UTF-16BE", "", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x01", "UTF-16BE", "\u0101", nil], + ["ASCII-8BIT", "\x01\x01", "UTF-16BE", "\u0181", nil], + ["ASCII-8BIT", "\x01\x01", "ISO-2022-JP", "", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x01", "ISO-2022-JP", "\x01\x01", nil], + ["ASCII-8BIT", "\x01\x01", "ISO-2022-JP", "\x01\x81", nil], + ["ASCII-8BIT", "\x01\x81", "US-ASCII", "", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x81", "US-ASCII", "\x01\x01", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x81", "US-ASCII", "\x01\x81", nil], + ["ASCII-8BIT", "\x01\x81", "UTF-8", "", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x81", "UTF-8", "\u0001\u0001", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x81", "UTF-8", "\u0001\x81", nil], + ["ASCII-8BIT", "\x01\x81", "ASCII-8BIT", "", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x81", "ASCII-8BIT", "\x01\x01", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x81", "ASCII-8BIT", "\x01\x81", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x81", "ISO-8859-1", "", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x81", "ISO-8859-1", "\x01\x01", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x81", "ISO-8859-1", "\x01\x81", nil], + ["ASCII-8BIT", "\x01\x81", "UTF-16BE", "", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x81", "UTF-16BE", "\u0101", nil], + ["ASCII-8BIT", "\x01\x81", "UTF-16BE", "\u0181", nil], + ["ASCII-8BIT", "\x01\x81", "ISO-2022-JP", "", "ASCII-8BIT"], + ["ASCII-8BIT", "\x01\x81", "ISO-2022-JP", "\x01\x01", nil], + ["ASCII-8BIT", "\x01\x81", "ISO-2022-JP", "\x01\x81", nil], + ["ISO-8859-1", "", "US-ASCII", "", "ISO-8859-1"], + ["ISO-8859-1", "", "US-ASCII", "\x01\x01", "ISO-8859-1"], + ["ISO-8859-1", "", "US-ASCII", "\x01\x81", "US-ASCII"], + ["ISO-8859-1", "", "UTF-8", "", "ISO-8859-1"], + ["ISO-8859-1", "", "UTF-8", "\u0001\u0001", "ISO-8859-1"], + ["ISO-8859-1", "", "UTF-8", "\u0001\x81", "UTF-8"], + ["ISO-8859-1", "", "ASCII-8BIT", "", "ISO-8859-1"], + ["ISO-8859-1", "", "ASCII-8BIT", "\x01\x01", "ISO-8859-1"], + ["ISO-8859-1", "", "ASCII-8BIT", "\x01\x81", "ASCII-8BIT"], + ["ISO-8859-1", "", "ISO-8859-1", "", "ISO-8859-1"], + ["ISO-8859-1", "", "ISO-8859-1", "\x01\x01", "ISO-8859-1"], + ["ISO-8859-1", "", "ISO-8859-1", "\x01\x81", "ISO-8859-1"], + ["ISO-8859-1", "", "UTF-16BE", "", "ISO-8859-1"], + ["ISO-8859-1", "", "UTF-16BE", "\u0101", "UTF-16BE"], + ["ISO-8859-1", "", "UTF-16BE", "\u0181", "UTF-16BE"], + ["ISO-8859-1", "", "ISO-2022-JP", "", "ISO-8859-1"], + ["ISO-8859-1", "", "ISO-2022-JP", "\x01\x01", "ISO-2022-JP"], + ["ISO-8859-1", "", "ISO-2022-JP", "\x01\x81", "ISO-2022-JP"], + ["ISO-8859-1", "\x01\x01", "US-ASCII", "", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x01", "US-ASCII", "\x01\x01", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x01", "US-ASCII", "\x01\x81", "US-ASCII"], + ["ISO-8859-1", "\x01\x01", "UTF-8", "", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x01", "UTF-8", "\u0001\u0001", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x01", "UTF-8", "\u0001\x81", "UTF-8"], + ["ISO-8859-1", "\x01\x01", "ASCII-8BIT", "", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x01", "ASCII-8BIT", "\x01\x01", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x01", "ASCII-8BIT", "\x01\x81", "ASCII-8BIT"], + ["ISO-8859-1", "\x01\x01", "ISO-8859-1", "", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x01", "ISO-8859-1", "\x01\x01", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x01", "ISO-8859-1", "\x01\x81", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x01", "UTF-16BE", "", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x01", "UTF-16BE", "\u0101", nil], + ["ISO-8859-1", "\x01\x01", "UTF-16BE", "\u0181", nil], + ["ISO-8859-1", "\x01\x01", "ISO-2022-JP", "", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x01", "ISO-2022-JP", "\x01\x01", nil], + ["ISO-8859-1", "\x01\x01", "ISO-2022-JP", "\x01\x81", nil], + ["ISO-8859-1", "\x01\x81", "US-ASCII", "", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x81", "US-ASCII", "\x01\x01", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x81", "US-ASCII", "\x01\x81", nil], + ["ISO-8859-1", "\x01\x81", "UTF-8", "", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x81", "UTF-8", "\u0001\u0001", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x81", "UTF-8", "\u0001\x81", nil], + ["ISO-8859-1", "\x01\x81", "ASCII-8BIT", "", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x81", "ASCII-8BIT", "\x01\x01", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x81", "ASCII-8BIT", "\x01\x81", nil], + ["ISO-8859-1", "\x01\x81", "ISO-8859-1", "", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x81", "ISO-8859-1", "\x01\x01", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x81", "ISO-8859-1", "\x01\x81", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x81", "UTF-16BE", "", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x81", "UTF-16BE", "\u0101", nil], + ["ISO-8859-1", "\x01\x81", "UTF-16BE", "\u0181", nil], + ["ISO-8859-1", "\x01\x81", "ISO-2022-JP", "", "ISO-8859-1"], + ["ISO-8859-1", "\x01\x81", "ISO-2022-JP", "\x01\x01", nil], + ["ISO-8859-1", "\x01\x81", "ISO-2022-JP", "\x01\x81", nil], + ["UTF-16BE", "", "US-ASCII", "", "UTF-16BE"], + ["UTF-16BE", "", "US-ASCII", "\x01\x01", "US-ASCII"], + ["UTF-16BE", "", "US-ASCII", "\x01\x81", "US-ASCII"], + ["UTF-16BE", "", "UTF-8", "", "UTF-16BE"], + ["UTF-16BE", "", "UTF-8", "\u0001\u0001", "UTF-8"], + ["UTF-16BE", "", "UTF-8", "\u0001\x81", "UTF-8"], + ["UTF-16BE", "", "ASCII-8BIT", "", "UTF-16BE"], + ["UTF-16BE", "", "ASCII-8BIT", "\x01\x01", "ASCII-8BIT"], + ["UTF-16BE", "", "ASCII-8BIT", "\x01\x81", "ASCII-8BIT"], + ["UTF-16BE", "", "ISO-8859-1", "", "UTF-16BE"], + ["UTF-16BE", "", "ISO-8859-1", "\x01\x01", "ISO-8859-1"], + ["UTF-16BE", "", "ISO-8859-1", "\x01\x81", "ISO-8859-1"], + ["UTF-16BE", "", "UTF-16BE", "", "UTF-16BE"], + ["UTF-16BE", "", "UTF-16BE", "\u0101", "UTF-16BE"], + ["UTF-16BE", "", "UTF-16BE", "\u0181", "UTF-16BE"], + ["UTF-16BE", "", "ISO-2022-JP", "", "UTF-16BE"], + ["UTF-16BE", "", "ISO-2022-JP", "\x01\x01", "ISO-2022-JP"], + ["UTF-16BE", "", "ISO-2022-JP", "\x01\x81", "ISO-2022-JP"], + ["UTF-16BE", "\u0101", "US-ASCII", "", "UTF-16BE"], + ["UTF-16BE", "\u0101", "US-ASCII", "\x01\x01", nil], + ["UTF-16BE", "\u0101", "US-ASCII", "\x01\x81", nil], + ["UTF-16BE", "\u0101", "UTF-8", "", "UTF-16BE"], + ["UTF-16BE", "\u0101", "UTF-8", "\u0001\u0001", nil], + ["UTF-16BE", "\u0101", "UTF-8", "\u0001\x81", nil], + ["UTF-16BE", "\u0101", "ASCII-8BIT", "", "UTF-16BE"], + ["UTF-16BE", "\u0101", "ASCII-8BIT", "\x01\x01", nil], + ["UTF-16BE", "\u0101", "ASCII-8BIT", "\x01\x81", nil], + ["UTF-16BE", "\u0101", "ISO-8859-1", "", "UTF-16BE"], + ["UTF-16BE", "\u0101", "ISO-8859-1", "\x01\x01", nil], + ["UTF-16BE", "\u0101", "ISO-8859-1", "\x01\x81", nil], + ["UTF-16BE", "\u0101", "UTF-16BE", "", "UTF-16BE"], + ["UTF-16BE", "\u0101", "UTF-16BE", "\u0101", "UTF-16BE"], + ["UTF-16BE", "\u0101", "UTF-16BE", "\u0181", "UTF-16BE"], + ["UTF-16BE", "\u0101", "ISO-2022-JP", "", "UTF-16BE"], + ["UTF-16BE", "\u0101", "ISO-2022-JP", "\x01\x01", nil], + ["UTF-16BE", "\u0101", "ISO-2022-JP", "\x01\x81", nil], + ["UTF-16BE", "\u0181", "US-ASCII", "", "UTF-16BE"], + ["UTF-16BE", "\u0181", "US-ASCII", "\x01\x01", nil], + ["UTF-16BE", "\u0181", "US-ASCII", "\x01\x81", nil], + ["UTF-16BE", "\u0181", "UTF-8", "", "UTF-16BE"], + ["UTF-16BE", "\u0181", "UTF-8", "\u0001\u0001", nil], + ["UTF-16BE", "\u0181", "UTF-8", "\u0001\x81", nil], + ["UTF-16BE", "\u0181", "ASCII-8BIT", "", "UTF-16BE"], + ["UTF-16BE", "\u0181", "ASCII-8BIT", "\x01\x01", nil], + ["UTF-16BE", "\u0181", "ASCII-8BIT", "\x01\x81", nil], + ["UTF-16BE", "\u0181", "ISO-8859-1", "", "UTF-16BE"], + ["UTF-16BE", "\u0181", "ISO-8859-1", "\x01\x01", nil], + ["UTF-16BE", "\u0181", "ISO-8859-1", "\x01\x81", nil], + ["UTF-16BE", "\u0181", "UTF-16BE", "", "UTF-16BE"], + ["UTF-16BE", "\u0181", "UTF-16BE", "\u0101", "UTF-16BE"], + ["UTF-16BE", "\u0181", "UTF-16BE", "\u0181", "UTF-16BE"], + ["UTF-16BE", "\u0181", "ISO-2022-JP", "", "UTF-16BE"], + ["UTF-16BE", "\u0181", "ISO-2022-JP", "\x01\x01", nil], + ["UTF-16BE", "\u0181", "ISO-2022-JP", "\x01\x81", nil], + ["ISO-2022-JP", "", "US-ASCII", "", "ISO-2022-JP"], + ["ISO-2022-JP", "", "US-ASCII", "\x01\x01", "US-ASCII"], + ["ISO-2022-JP", "", "US-ASCII", "\x01\x81", "US-ASCII"], + ["ISO-2022-JP", "", "UTF-8", "", "ISO-2022-JP"], + ["ISO-2022-JP", "", "UTF-8", "\u0001\u0001", "UTF-8"], + ["ISO-2022-JP", "", "UTF-8", "\u0001\x81", "UTF-8"], + ["ISO-2022-JP", "", "ASCII-8BIT", "", "ISO-2022-JP"], + ["ISO-2022-JP", "", "ASCII-8BIT", "\x01\x01", "ASCII-8BIT"], + ["ISO-2022-JP", "", "ASCII-8BIT", "\x01\x81", "ASCII-8BIT"], + ["ISO-2022-JP", "", "ISO-8859-1", "", "ISO-2022-JP"], + ["ISO-2022-JP", "", "ISO-8859-1", "\x01\x01", "ISO-8859-1"], + ["ISO-2022-JP", "", "ISO-8859-1", "\x01\x81", "ISO-8859-1"], + ["ISO-2022-JP", "", "UTF-16BE", "", "ISO-2022-JP"], + ["ISO-2022-JP", "", "UTF-16BE", "\u0101", "UTF-16BE"], + ["ISO-2022-JP", "", "UTF-16BE", "\u0181", "UTF-16BE"], + ["ISO-2022-JP", "", "ISO-2022-JP", "", "ISO-2022-JP"], + ["ISO-2022-JP", "", "ISO-2022-JP", "\x01\x01", "ISO-2022-JP"], + ["ISO-2022-JP", "", "ISO-2022-JP", "\x01\x81", "ISO-2022-JP"], + ["ISO-2022-JP", "\x01\x01", "US-ASCII", "", "ISO-2022-JP"], + ["ISO-2022-JP", "\x01\x01", "US-ASCII", "\x01\x01", nil], + ["ISO-2022-JP", "\x01\x01", "US-ASCII", "\x01\x81", nil], + ["ISO-2022-JP", "\x01\x01", "UTF-8", "", "ISO-2022-JP"], + ["ISO-2022-JP", "\x01\x01", "UTF-8", "\u0001\u0001", nil], + ["ISO-2022-JP", "\x01\x01", "UTF-8", "\u0001\x81", nil], + ["ISO-2022-JP", "\x01\x01", "ASCII-8BIT", "", "ISO-2022-JP"], + ["ISO-2022-JP", "\x01\x01", "ASCII-8BIT", "\x01\x01", nil], + ["ISO-2022-JP", "\x01\x01", "ASCII-8BIT", "\x01\x81", nil], + ["ISO-2022-JP", "\x01\x01", "ISO-8859-1", "", "ISO-2022-JP"], + ["ISO-2022-JP", "\x01\x01", "ISO-8859-1", "\x01\x01", nil], + ["ISO-2022-JP", "\x01\x01", "ISO-8859-1", "\x01\x81", nil], + ["ISO-2022-JP", "\x01\x01", "UTF-16BE", "", "ISO-2022-JP"], + ["ISO-2022-JP", "\x01\x01", "UTF-16BE", "\u0101", nil], + ["ISO-2022-JP", "\x01\x01", "UTF-16BE", "\u0181", nil], + ["ISO-2022-JP", "\x01\x01", "ISO-2022-JP", "", "ISO-2022-JP"], + ["ISO-2022-JP", "\x01\x01", "ISO-2022-JP", "\x01\x01", "ISO-2022-JP"], + ["ISO-2022-JP", "\x01\x01", "ISO-2022-JP", "\x01\x81", "ISO-2022-JP"], + ["ISO-2022-JP", "\x01\x81", "US-ASCII", "", "ISO-2022-JP"], + ["ISO-2022-JP", "\x01\x81", "US-ASCII", "\x01\x01", nil], + ["ISO-2022-JP", "\x01\x81", "US-ASCII", "\x01\x81", nil], + ["ISO-2022-JP", "\x01\x81", "UTF-8", "", "ISO-2022-JP"], + ["ISO-2022-JP", "\x01\x81", "UTF-8", "\u0001\u0001", nil], + ["ISO-2022-JP", "\x01\x81", "UTF-8", "\u0001\x81", nil], + ["ISO-2022-JP", "\x01\x81", "ASCII-8BIT", "", "ISO-2022-JP"], + ["ISO-2022-JP", "\x01\x81", "ASCII-8BIT", "\x01\x01", nil], + ["ISO-2022-JP", "\x01\x81", "ASCII-8BIT", "\x01\x81", nil], + ["ISO-2022-JP", "\x01\x81", "ISO-8859-1", "", "ISO-2022-JP"], + ["ISO-2022-JP", "\x01\x81", "ISO-8859-1", "\x01\x01", nil], + ["ISO-2022-JP", "\x01\x81", "ISO-8859-1", "\x01\x81", nil], + ["ISO-2022-JP", "\x01\x81", "UTF-16BE", "", "ISO-2022-JP"], + ["ISO-2022-JP", "\x01\x81", "UTF-16BE", "\u0101", nil], + ["ISO-2022-JP", "\x01\x81", "UTF-16BE", "\u0181", nil], + ["ISO-2022-JP", "\x01\x81", "ISO-2022-JP", "", "ISO-2022-JP"], + ["ISO-2022-JP", "\x01\x81", "ISO-2022-JP", "\x01\x01", "ISO-2022-JP"], + ["ISO-2022-JP", "\x01\x81", "ISO-2022-JP", "\x01\x81", "ISO-2022-JP"], + ] + + matrix.each do |encoding1, value1, encoding2, value2, compatible_encoding| + it "returns #{compatible_encoding} for #{value1.inspect} in #{encoding1} and #{value2.inspect} in #{encoding2}" do + actual_encoding = Encoding.compatible?(value1.dup.force_encoding(encoding1), value2.dup.force_encoding(encoding2)) + actual_encoding&.name.should == compatible_encoding + end + end + end end describe "Encoding.compatible? String, Regexp" do it "returns US-ASCII if both are US-ASCII" do - str = "abc".force_encoding("us-ascii") + str = "abc".dup.force_encoding("us-ascii") Encoding.compatible?(str, /abc/).should == Encoding::US_ASCII end @@ -180,15 +553,15 @@ describe "Encoding.compatible? String, Regexp" do it "returns the String's Encoding if the String is not ASCII only" do [ [Encoding, "\xff", Encoding::BINARY], [Encoding, "\u3042".encode("utf-8"), Encoding::UTF_8], - [Encoding, "\xa4\xa2".force_encoding("euc-jp"), Encoding::EUC_JP], - [Encoding, "\x82\xa0".force_encoding("shift_jis"), Encoding::Shift_JIS], + [Encoding, "\xa4\xa2".dup.force_encoding("euc-jp"), Encoding::EUC_JP], + [Encoding, "\x82\xa0".dup.force_encoding("shift_jis"), Encoding::Shift_JIS], ].should be_computed_by(:compatible?, /abc/) end end describe "Encoding.compatible? String, Symbol" do it "returns US-ASCII if both are ASCII only" do - str = "abc".force_encoding("us-ascii") + str = "abc".dup.force_encoding("us-ascii") Encoding.compatible?(str, :abc).should == Encoding::US_ASCII end @@ -203,8 +576,8 @@ describe "Encoding.compatible? String, Symbol" do it "returns the String's Encoding if the String is not ASCII only" do [ [Encoding, "\xff", Encoding::BINARY], [Encoding, "\u3042".encode("utf-8"), Encoding::UTF_8], - [Encoding, "\xa4\xa2".force_encoding("euc-jp"), Encoding::EUC_JP], - [Encoding, "\x82\xa0".force_encoding("shift_jis"), Encoding::Shift_JIS], + [Encoding, "\xa4\xa2".dup.force_encoding("euc-jp"), Encoding::EUC_JP], + [Encoding, "\x82\xa0".dup.force_encoding("shift_jis"), Encoding::Shift_JIS], ].should be_computed_by(:compatible?, :abc) end end @@ -221,8 +594,8 @@ describe "Encoding.compatible? String, Encoding" do it "returns the String's encoding if the Encoding is US-ASCII" do [ [Encoding, "\xff", Encoding::BINARY], [Encoding, "\u3042".encode("utf-8"), Encoding::UTF_8], - [Encoding, "\xa4\xa2".force_encoding("euc-jp"), Encoding::EUC_JP], - [Encoding, "\x82\xa0".force_encoding("shift_jis"), Encoding::Shift_JIS], + [Encoding, "\xa4\xa2".dup.force_encoding("euc-jp"), Encoding::EUC_JP], + [Encoding, "\x82\xa0".dup.force_encoding("shift_jis"), Encoding::Shift_JIS], ].should be_computed_by(:compatible?, Encoding::US_ASCII) end @@ -242,7 +615,7 @@ end describe "Encoding.compatible? Regexp, String" do it "returns US-ASCII if both are US-ASCII" do - str = "abc".force_encoding("us-ascii") + str = "abc".dup.force_encoding("us-ascii") Encoding.compatible?(/abc/, str).should == Encoding::US_ASCII end @@ -256,8 +629,8 @@ describe "Encoding.compatible? Regexp, Regexp" do it "returns the first's Encoding if it is not US-ASCII and not ASCII only" do [ [Encoding, Regexp.new("\xff"), Encoding::BINARY], [Encoding, Regexp.new("\u3042".encode("utf-8")), Encoding::UTF_8], - [Encoding, Regexp.new("\xa4\xa2".force_encoding("euc-jp")), Encoding::EUC_JP], - [Encoding, Regexp.new("\x82\xa0".force_encoding("shift_jis")), Encoding::Shift_JIS], + [Encoding, Regexp.new("\xa4\xa2".dup.force_encoding("euc-jp")), Encoding::EUC_JP], + [Encoding, Regexp.new("\x82\xa0".dup.force_encoding("shift_jis")), Encoding::Shift_JIS], ].should be_computed_by(:compatible?, /abc/) end end @@ -270,15 +643,15 @@ describe "Encoding.compatible? Regexp, Symbol" do it "returns the first's Encoding if it is not US-ASCII and not ASCII only" do [ [Encoding, Regexp.new("\xff"), Encoding::BINARY], [Encoding, Regexp.new("\u3042".encode("utf-8")), Encoding::UTF_8], - [Encoding, Regexp.new("\xa4\xa2".force_encoding("euc-jp")), Encoding::EUC_JP], - [Encoding, Regexp.new("\x82\xa0".force_encoding("shift_jis")), Encoding::Shift_JIS], + [Encoding, Regexp.new("\xa4\xa2".dup.force_encoding("euc-jp")), Encoding::EUC_JP], + [Encoding, Regexp.new("\x82\xa0".dup.force_encoding("shift_jis")), Encoding::Shift_JIS], ].should be_computed_by(:compatible?, /abc/) end end describe "Encoding.compatible? Symbol, String" do it "returns US-ASCII if both are ASCII only" do - str = "abc".force_encoding("us-ascii") + str = "abc".dup.force_encoding("us-ascii") Encoding.compatible?(str, :abc).should == Encoding::US_ASCII end end @@ -291,8 +664,8 @@ describe "Encoding.compatible? Symbol, Regexp" do it "returns the Regexp's Encoding if it is not US-ASCII and not ASCII only" do a = Regexp.new("\xff") b = Regexp.new("\u3042".encode("utf-8")) - c = Regexp.new("\xa4\xa2".force_encoding("euc-jp")) - d = Regexp.new("\x82\xa0".force_encoding("shift_jis")) + c = Regexp.new("\xa4\xa2".dup.force_encoding("euc-jp")) + d = Regexp.new("\x82\xa0".dup.force_encoding("shift_jis")) [ [Encoding, :abc, a, Encoding::BINARY], [Encoding, :abc, b, Encoding::UTF_8], @@ -310,8 +683,8 @@ describe "Encoding.compatible? Symbol, Symbol" do it "returns the first's Encoding if it is not ASCII only" do [ [Encoding, "\xff".to_sym, Encoding::BINARY], [Encoding, "\u3042".encode("utf-8").to_sym, Encoding::UTF_8], - [Encoding, "\xa4\xa2".force_encoding("euc-jp").to_sym, Encoding::EUC_JP], - [Encoding, "\x82\xa0".force_encoding("shift_jis").to_sym, Encoding::Shift_JIS], + [Encoding, "\xa4\xa2".dup.force_encoding("euc-jp").to_sym, Encoding::EUC_JP], + [Encoding, "\x82\xa0".dup.force_encoding("shift_jis").to_sym, Encoding::Shift_JIS], ].should be_computed_by(:compatible?, :abc) end end @@ -377,3 +750,9 @@ describe "Encoding.compatible? Object, Object" do Encoding.compatible?(:sym, Object.new).should be_nil end end + +describe "Encoding.compatible? nil, nil" do + it "returns nil" do + Encoding.compatible?(nil, nil).should be_nil + end +end diff --git a/spec/ruby/core/encoding/converter/asciicompat_encoding_spec.rb b/spec/ruby/core/encoding/converter/asciicompat_encoding_spec.rb index e39d590e3a..1beb40af3f 100644 --- a/spec/ruby/core/encoding/converter/asciicompat_encoding_spec.rb +++ b/spec/ruby/core/encoding/converter/asciicompat_encoding_spec.rb @@ -2,7 +2,7 @@ require_relative '../../../spec_helper' describe "Encoding::Converter.asciicompat_encoding" do it "accepts an encoding name as a String argument" do - lambda { Encoding::Converter.asciicompat_encoding('UTF-8') }. + -> { Encoding::Converter.asciicompat_encoding('UTF-8') }. should_not raise_error end diff --git a/spec/ruby/core/encoding/converter/constants_spec.rb b/spec/ruby/core/encoding/converter/constants_spec.rb index 57b6a4d4e7..7d29bdb278 100644 --- a/spec/ruby/core/encoding/converter/constants_spec.rb +++ b/spec/ruby/core/encoding/converter/constants_spec.rb @@ -5,8 +5,8 @@ describe "Encoding::Converter::INVALID_MASK" do Encoding::Converter.should have_constant(:INVALID_MASK) end - it "has a Fixnum value" do - Encoding::Converter::INVALID_MASK.should be_an_instance_of(Fixnum) + it "has an Integer value" do + Encoding::Converter::INVALID_MASK.should be_an_instance_of(Integer) end end @@ -15,8 +15,8 @@ describe "Encoding::Converter::INVALID_REPLACE" do Encoding::Converter.should have_constant(:INVALID_REPLACE) end - it "has a Fixnum value" do - Encoding::Converter::INVALID_REPLACE.should be_an_instance_of(Fixnum) + it "has an Integer value" do + Encoding::Converter::INVALID_REPLACE.should be_an_instance_of(Integer) end end @@ -25,8 +25,8 @@ describe "Encoding::Converter::UNDEF_MASK" do Encoding::Converter.should have_constant(:UNDEF_MASK) end - it "has a Fixnum value" do - Encoding::Converter::UNDEF_MASK.should be_an_instance_of(Fixnum) + it "has an Integer value" do + Encoding::Converter::UNDEF_MASK.should be_an_instance_of(Integer) end end @@ -35,8 +35,8 @@ describe "Encoding::Converter::UNDEF_REPLACE" do Encoding::Converter.should have_constant(:UNDEF_REPLACE) end - it "has a Fixnum value" do - Encoding::Converter::UNDEF_REPLACE.should be_an_instance_of(Fixnum) + it "has an Integer value" do + Encoding::Converter::UNDEF_REPLACE.should be_an_instance_of(Integer) end end @@ -45,8 +45,8 @@ describe "Encoding::Converter::UNDEF_HEX_CHARREF" do Encoding::Converter.should have_constant(:UNDEF_HEX_CHARREF) end - it "has a Fixnum value" do - Encoding::Converter::UNDEF_HEX_CHARREF.should be_an_instance_of(Fixnum) + it "has an Integer value" do + Encoding::Converter::UNDEF_HEX_CHARREF.should be_an_instance_of(Integer) end end @@ -55,8 +55,8 @@ describe "Encoding::Converter::PARTIAL_INPUT" do Encoding::Converter.should have_constant(:PARTIAL_INPUT) end - it "has a Fixnum value" do - Encoding::Converter::PARTIAL_INPUT.should be_an_instance_of(Fixnum) + it "has an Integer value" do + Encoding::Converter::PARTIAL_INPUT.should be_an_instance_of(Integer) end end @@ -65,8 +65,8 @@ describe "Encoding::Converter::AFTER_OUTPUT" do Encoding::Converter.should have_constant(:AFTER_OUTPUT) end - it "has a Fixnum value" do - Encoding::Converter::AFTER_OUTPUT.should be_an_instance_of(Fixnum) + it "has an Integer value" do + Encoding::Converter::AFTER_OUTPUT.should be_an_instance_of(Integer) end end @@ -75,8 +75,8 @@ describe "Encoding::Converter::UNIVERSAL_NEWLINE_DECORATOR" do Encoding::Converter.should have_constant(:UNIVERSAL_NEWLINE_DECORATOR) end - it "has a Fixnum value" do - Encoding::Converter::UNIVERSAL_NEWLINE_DECORATOR.should be_an_instance_of(Fixnum) + it "has an Integer value" do + Encoding::Converter::UNIVERSAL_NEWLINE_DECORATOR.should be_an_instance_of(Integer) end end @@ -85,8 +85,8 @@ describe "Encoding::Converter::CRLF_NEWLINE_DECORATOR" do Encoding::Converter.should have_constant(:CRLF_NEWLINE_DECORATOR) end - it "has a Fixnum value" do - Encoding::Converter::CRLF_NEWLINE_DECORATOR.should be_an_instance_of(Fixnum) + it "has an Integer value" do + Encoding::Converter::CRLF_NEWLINE_DECORATOR.should be_an_instance_of(Integer) end end @@ -95,8 +95,8 @@ describe "Encoding::Converter::CR_NEWLINE_DECORATOR" do Encoding::Converter.should have_constant(:CR_NEWLINE_DECORATOR) end - it "has a Fixnum value" do - Encoding::Converter::CR_NEWLINE_DECORATOR.should be_an_instance_of(Fixnum) + it "has an Integer value" do + Encoding::Converter::CR_NEWLINE_DECORATOR.should be_an_instance_of(Integer) end end @@ -105,8 +105,8 @@ describe "Encoding::Converter::XML_TEXT_DECORATOR" do Encoding::Converter.should have_constant(:XML_TEXT_DECORATOR) end - it "has a Fixnum value" do - Encoding::Converter::XML_TEXT_DECORATOR.should be_an_instance_of(Fixnum) + it "has an Integer value" do + Encoding::Converter::XML_TEXT_DECORATOR.should be_an_instance_of(Integer) end end @@ -115,8 +115,8 @@ describe "Encoding::Converter::XML_ATTR_CONTENT_DECORATOR" do Encoding::Converter.should have_constant(:XML_ATTR_CONTENT_DECORATOR) end - it "has a Fixnum value" do - Encoding::Converter::XML_ATTR_CONTENT_DECORATOR.should be_an_instance_of(Fixnum) + it "has an Integer value" do + Encoding::Converter::XML_ATTR_CONTENT_DECORATOR.should be_an_instance_of(Integer) end end @@ -125,7 +125,7 @@ describe "Encoding::Converter::XML_ATTR_QUOTE_DECORATOR" do Encoding::Converter.should have_constant(:XML_ATTR_QUOTE_DECORATOR) end - it "has a Fixnum value" do - Encoding::Converter::XML_ATTR_QUOTE_DECORATOR.should be_an_instance_of(Fixnum) + it "has an Integer value" do + Encoding::Converter::XML_ATTR_QUOTE_DECORATOR.should be_an_instance_of(Integer) end end diff --git a/spec/ruby/core/encoding/converter/convert_spec.rb b/spec/ruby/core/encoding/converter/convert_spec.rb index 362e027a58..8533af4565 100644 --- a/spec/ruby/core/encoding/converter/convert_spec.rb +++ b/spec/ruby/core/encoding/converter/convert_spec.rb @@ -1,4 +1,5 @@ -# -*- encoding: binary -*- +# encoding: binary +# frozen_string_literal: true require_relative '../../../spec_helper' describe "Encoding::Converter#convert" do @@ -9,37 +10,37 @@ describe "Encoding::Converter#convert" do it "sets the encoding of the result to the target encoding" do ec = Encoding::Converter.new('ascii', 'utf-8') - str = 'glark'.force_encoding('ascii') + str = 'glark'.dup.force_encoding('ascii') ec.convert(str).encoding.should == Encoding::UTF_8 end it "transcodes the given String to the target encoding" do ec = Encoding::Converter.new("utf-8", "euc-jp") - ec.convert("\u3042".force_encoding('UTF-8')).should == \ - "\xA4\xA2".force_encoding('EUC-JP') + ec.convert("\u3042".dup.force_encoding('UTF-8')).should == \ + "\xA4\xA2".dup.force_encoding('EUC-JP') end it "allows Strings of different encodings to the source encoding" do ec = Encoding::Converter.new('ascii', 'utf-8') - str = 'glark'.force_encoding('SJIS') + str = 'glark'.dup.force_encoding('SJIS') ec.convert(str).encoding.should == Encoding::UTF_8 end it "reuses the given encoding pair if called multiple times" do ec = Encoding::Converter.new('ascii', 'SJIS') - ec.convert('a'.force_encoding('ASCII')).should == 'a'.force_encoding('SJIS') - ec.convert('b'.force_encoding('ASCII')).should == 'b'.force_encoding('SJIS') + ec.convert('a'.dup.force_encoding('ASCII')).should == 'a'.dup.force_encoding('SJIS') + ec.convert('b'.dup.force_encoding('ASCII')).should == 'b'.dup.force_encoding('SJIS') end it "raises UndefinedConversionError if the String contains characters invalid for the target encoding" do ec = Encoding::Converter.new('UTF-8', Encoding.find('macCyrillic')) - lambda { ec.convert("\u{6543}".force_encoding('UTF-8')) }.should \ + -> { ec.convert("\u{6543}".dup.force_encoding('UTF-8')) }.should \ raise_error(Encoding::UndefinedConversionError) end it "raises an ArgumentError if called on a finished stream" do ec = Encoding::Converter.new('UTF-8', Encoding.find('macCyrillic')) ec.finish - lambda { ec.convert("\u{65}") }.should raise_error(ArgumentError) + -> { ec.convert("\u{65}") }.should raise_error(ArgumentError) end end diff --git a/spec/ruby/core/encoding/converter/convpath_spec.rb b/spec/ruby/core/encoding/converter/convpath_spec.rb index 473f2db91e..23f1e5dc33 100644 --- a/spec/ruby/core/encoding/converter/convpath_spec.rb +++ b/spec/ruby/core/encoding/converter/convpath_spec.rb @@ -15,10 +15,10 @@ describe "Encoding::Converter#convpath" do end it "indicates if crlf_newline conversion would occur" do - ec = Encoding::Converter.new("ISo-8859-1", "EUC-JP", {crlf_newline: true}) + ec = Encoding::Converter.new("ISo-8859-1", "EUC-JP", crlf_newline: true) ec.convpath.last.should == "crlf_newline" - ec = Encoding::Converter.new("ASCII", "UTF-8", {crlf_newline: false}) + ec = Encoding::Converter.new("ASCII", "UTF-8", crlf_newline: false) ec.convpath.last.should_not == "crlf_newline" end end diff --git a/spec/ruby/core/encoding/converter/finish_spec.rb b/spec/ruby/core/encoding/converter/finish_spec.rb index 11ca7e8510..22e66df38c 100644 --- a/spec/ruby/core/encoding/converter/finish_spec.rb +++ b/spec/ruby/core/encoding/converter/finish_spec.rb @@ -16,8 +16,8 @@ describe "Encoding::Converter#finish" do end it "returns the last part of the converted String if it hasn't already" do - @ec.convert("\u{9999}").should == "\e$B9a".force_encoding('iso-2022-jp') - @ec.finish.should == "\e(B".force_encoding('iso-2022-jp') + @ec.convert("\u{9999}").should == "\e$B9a".dup.force_encoding('iso-2022-jp') + @ec.finish.should == "\e(B".dup.force_encoding('iso-2022-jp') end it "returns a String in the destination encoding" do diff --git a/spec/ruby/core/encoding/converter/last_error_spec.rb b/spec/ruby/core/encoding/converter/last_error_spec.rb index 68567737b7..ff2a2b4cbe 100644 --- a/spec/ruby/core/encoding/converter/last_error_spec.rb +++ b/spec/ruby/core/encoding/converter/last_error_spec.rb @@ -1,4 +1,4 @@ -# -*- encoding: binary -*- +# encoding: binary require_relative '../../../spec_helper' describe "Encoding::Converter#last_error" do @@ -9,45 +9,45 @@ describe "Encoding::Converter#last_error" do it "returns nil when the last conversion did not produce an error" do ec = Encoding::Converter.new('ascii','utf-8') - ec.convert('a'.force_encoding('ascii')) + ec.convert('a'.dup.force_encoding('ascii')) ec.last_error.should be_nil end it "returns nil when #primitive_convert last returned :destination_buffer_full" do ec = Encoding::Converter.new("utf-8", "iso-2022-jp") - ec.primitive_convert("\u{9999}", "", 0, 0, partial_input: false) \ + ec.primitive_convert(+"\u{9999}", +"", 0, 0, partial_input: false) \ .should == :destination_buffer_full ec.last_error.should be_nil end it "returns nil when #primitive_convert last returned :finished" do ec = Encoding::Converter.new("utf-8", "iso-8859-1") - ec.primitive_convert("glark".force_encoding('utf-8'),"").should == :finished + ec.primitive_convert("glark".dup.force_encoding('utf-8'), +"").should == :finished ec.last_error.should be_nil end it "returns nil if the last conversion succeeded but the penultimate failed" do ec = Encoding::Converter.new("utf-8", "iso-8859-1") - ec.primitive_convert("\xf1abcd","").should == :invalid_byte_sequence - ec.primitive_convert("glark".force_encoding('utf-8'),"").should == :finished + ec.primitive_convert(+"\xf1abcd", +"").should == :invalid_byte_sequence + ec.primitive_convert("glark".dup.force_encoding('utf-8'), +"").should == :finished ec.last_error.should be_nil end it "returns an Encoding::InvalidByteSequenceError when #primitive_convert last returned :invalid_byte_sequence" do ec = Encoding::Converter.new("utf-8", "iso-8859-1") - ec.primitive_convert("\xf1abcd","").should == :invalid_byte_sequence + ec.primitive_convert(+"\xf1abcd", +"").should == :invalid_byte_sequence ec.last_error.should be_an_instance_of(Encoding::InvalidByteSequenceError) end it "returns an Encoding::UndefinedConversionError when #primitive_convert last returned :undefined_conversion" do ec = Encoding::Converter.new("utf-8", "iso-8859-1") - ec.primitive_convert("\u{9876}","").should == :undefined_conversion + ec.primitive_convert(+"\u{9876}", +"").should == :undefined_conversion ec.last_error.should be_an_instance_of(Encoding::UndefinedConversionError) end it "returns an Encoding::InvalidByteSequenceError when #primitive_convert last returned :incomplete_input" do ec = Encoding::Converter.new("EUC-JP", "ISO-8859-1") - ec.primitive_convert("\xa4", "", nil, 10).should == :incomplete_input + ec.primitive_convert(+"\xa4", +"", nil, 10).should == :incomplete_input ec.last_error.should be_an_instance_of(Encoding::InvalidByteSequenceError) end diff --git a/spec/ruby/core/encoding/converter/new_spec.rb b/spec/ruby/core/encoding/converter/new_spec.rb index 6b9c76a093..a7bef53809 100644 --- a/spec/ruby/core/encoding/converter/new_spec.rb +++ b/spec/ruby/core/encoding/converter/new_spec.rb @@ -1,4 +1,4 @@ -# -*- encoding: binary -*- +# encoding: binary require_relative '../../../spec_helper' describe "Encoding::Converter.new" do @@ -23,7 +23,7 @@ describe "Encoding::Converter.new" do end it "raises an Encoding::ConverterNotFoundError if both encodings are the same" do - lambda do + -> do Encoding::Converter.new "utf-8", "utf-8" end.should raise_error(Encoding::ConverterNotFoundError) end @@ -47,10 +47,10 @@ describe "Encoding::Converter.new" do conv.replacement.should == "fubar" end - it "calls #to_hash to convert the options argument to a Hash if not a Fixnum" do + it "calls #to_hash to convert the options argument to a Hash if not an Integer" do opts = mock("encoding converter options") opts.should_receive(:to_hash).and_return({ replace: "fubar" }) - conv = Encoding::Converter.new("us-ascii", "utf-8", opts) + conv = Encoding::Converter.new("us-ascii", "utf-8", **opts) conv.replacement.should == "fubar" end @@ -65,25 +65,25 @@ describe "Encoding::Converter.new" do obj = mock("encoding converter replacement") obj.should_receive(:to_str).and_return(1) - lambda do + -> do Encoding::Converter.new("us-ascii", "utf-8", replace: obj) end.should raise_error(TypeError) end it "raises a TypeError if passed true for the replacement object" do - lambda do + -> do Encoding::Converter.new("us-ascii", "utf-8", replace: true) end.should raise_error(TypeError) end it "raises a TypeError if passed false for the replacement object" do - lambda do + -> do Encoding::Converter.new("us-ascii", "utf-8", replace: false) end.should raise_error(TypeError) end - it "raises a TypeError if passed a Fixnum for the replacement object" do - lambda do + it "raises a TypeError if passed an Integer for the replacement object" do + -> do Encoding::Converter.new("us-ascii", "utf-8", replace: 1) end.should raise_error(TypeError) end @@ -107,7 +107,7 @@ describe "Encoding::Converter.new" do it "sets the replacement String to '\\uFFFD'" do conv = Encoding::Converter.new("us-ascii", "utf-8", replace: nil) - conv.replacement.should == "\u{fffd}".force_encoding("utf-8") + conv.replacement.should == "\u{fffd}".dup.force_encoding("utf-8") end it "sets the replacement String encoding to UTF-8" do diff --git a/spec/ruby/core/encoding/converter/primitive_convert_spec.rb b/spec/ruby/core/encoding/converter/primitive_convert_spec.rb index 710cc262bb..e4aeed103e 100644 --- a/spec/ruby/core/encoding/converter/primitive_convert_spec.rb +++ b/spec/ruby/core/encoding/converter/primitive_convert_spec.rb @@ -1,4 +1,5 @@ -# -*- encoding: binary -*- +# encoding: binary +# frozen_string_literal: false require_relative '../../../spec_helper' describe "Encoding::Converter#primitive_convert" do @@ -7,19 +8,23 @@ describe "Encoding::Converter#primitive_convert" do end it "accepts a nil source buffer" do - lambda { @ec.primitive_convert(nil,"") }.should_not raise_error + -> { @ec.primitive_convert(nil,"") }.should_not raise_error end it "accepts a String as the source buffer" do - lambda { @ec.primitive_convert("","") }.should_not raise_error + -> { @ec.primitive_convert("","") }.should_not raise_error + end + + it "raises FrozenError when the destination buffer is a frozen String" do + -> { @ec.primitive_convert("", "".freeze) }.should raise_error(FrozenError) end it "accepts nil for the destination byte offset" do - lambda { @ec.primitive_convert("","", nil) }.should_not raise_error + -> { @ec.primitive_convert("","", nil) }.should_not raise_error end it "accepts an integer for the destination byte offset" do - lambda { @ec.primitive_convert("","a", 1) }.should_not raise_error + -> { @ec.primitive_convert("","a", 1) }.should_not raise_error end it "calls #to_int to convert the destination byte offset" do @@ -30,10 +35,10 @@ describe "Encoding::Converter#primitive_convert" do end it "raises an ArgumentError if the destination byte offset is greater than the bytesize of the destination buffer" do - lambda { @ec.primitive_convert("","am", 0) }.should_not raise_error - lambda { @ec.primitive_convert("","am", 1) }.should_not raise_error - lambda { @ec.primitive_convert("","am", 2) }.should_not raise_error - lambda { @ec.primitive_convert("","am", 3) }.should raise_error(ArgumentError) + -> { @ec.primitive_convert("","am", 0) }.should_not raise_error + -> { @ec.primitive_convert("","am", 1) }.should_not raise_error + -> { @ec.primitive_convert("","am", 2) }.should_not raise_error + -> { @ec.primitive_convert("","am", 3) }.should raise_error(ArgumentError) end it "uses the destination byte offset to determine where to write the result in the destination buffer" do @@ -49,19 +54,19 @@ describe "Encoding::Converter#primitive_convert" do end it "accepts nil for the destination bytesize" do - lambda { @ec.primitive_convert("","", nil, nil) }.should_not raise_error + -> { @ec.primitive_convert("","", nil, nil) }.should_not raise_error end it "accepts an integer for the destination bytesize" do - lambda { @ec.primitive_convert("","", nil, 0) }.should_not raise_error + -> { @ec.primitive_convert("","", nil, 0) }.should_not raise_error end it "allows a destination bytesize value greater than the bytesize of the source buffer" do - lambda { @ec.primitive_convert("am","", nil, 3) }.should_not raise_error + -> { @ec.primitive_convert("am","", nil, 3) }.should_not raise_error end it "allows a destination bytesize value less than the bytesize of the source buffer" do - lambda { @ec.primitive_convert("am","", nil, 1) }.should_not raise_error + -> { @ec.primitive_convert("am","", nil, 1) }.should_not raise_error end it "calls #to_int to convert the destination byte size" do @@ -85,7 +90,7 @@ describe "Encoding::Converter#primitive_convert" do end it "accepts an options hash" do - @ec.primitive_convert("","",nil,nil, {after_output: true}).should == :finished + @ec.primitive_convert("","",nil,nil, after_output: true).should == :finished end it "sets the destination buffer's encoding to the destination encoding if the conversion succeeded" do diff --git a/spec/ruby/core/encoding/converter/primitive_errinfo_spec.rb b/spec/ruby/core/encoding/converter/primitive_errinfo_spec.rb index e0a5378155..5ee8b1fecd 100644 --- a/spec/ruby/core/encoding/converter/primitive_errinfo_spec.rb +++ b/spec/ruby/core/encoding/converter/primitive_errinfo_spec.rb @@ -1,4 +1,5 @@ -# -*- encoding: binary -*- +# encoding: binary +# frozen_string_literal: false require_relative '../../../spec_helper' describe "Encoding::Converter#primitive_errinfo" do @@ -54,7 +55,7 @@ describe "Encoding::Converter#primitive_errinfo" do it "returns the state, source encoding, target encoding, erroneous bytes, and the read-again bytes when #convert last raised InvalidByteSequenceError" do ec = Encoding::Converter.new("utf-8", "iso-8859-1") - lambda { ec.convert("\xf1abcd") }.should raise_error(Encoding::InvalidByteSequenceError) + -> { ec.convert("\xf1abcd") }.should raise_error(Encoding::InvalidByteSequenceError) ec.primitive_errinfo.should == [:invalid_byte_sequence, "UTF-8", "ISO-8859-1", "\xF1", "a"] end @@ -62,7 +63,7 @@ describe "Encoding::Converter#primitive_errinfo" do it "returns the state, source encoding, target encoding, erroneous bytes, and the read-again bytes when #finish last raised InvalidByteSequenceError" do ec = Encoding::Converter.new("EUC-JP", "ISO-8859-1") ec.convert("\xa4") - lambda { ec.finish }.should raise_error(Encoding::InvalidByteSequenceError) + -> { ec.finish }.should raise_error(Encoding::InvalidByteSequenceError) ec.primitive_errinfo.should == [:incomplete_input, "EUC-JP", "UTF-8", "\xA4", ""] end end diff --git a/spec/ruby/core/encoding/converter/putback_spec.rb b/spec/ruby/core/encoding/converter/putback_spec.rb index 87495eaf3f..04bb565655 100644 --- a/spec/ruby/core/encoding/converter/putback_spec.rb +++ b/spec/ruby/core/encoding/converter/putback_spec.rb @@ -1,10 +1,10 @@ -# -*- encoding: binary -*- +# encoding: binary require_relative '../../../spec_helper' describe "Encoding::Converter#putback" do before :each do @ec = Encoding::Converter.new("EUC-JP", "ISO-8859-1") - @ret = @ec.primitive_convert(@src="abc\xa1def", @dst="", nil, 10) + @ret = @ec.primitive_convert(@src=+"abc\xa1def", @dst=+"", nil, 10) end it "returns a String" do @@ -34,14 +34,23 @@ describe "Encoding::Converter#putback" do @ec.putback.should == "" end + it "returns the problematic bytes for UTF-16LE" do + ec = Encoding::Converter.new("utf-16le", "iso-8859-1") + src = +"\x00\xd8\x61\x00" + dst = +"" + ec.primitive_convert(src, dst).should == :invalid_byte_sequence + ec.primitive_errinfo.should == [:invalid_byte_sequence, "UTF-16LE", "UTF-8", "\x00\xD8", "a\x00"] + ec.putback.should == "a\x00".dup.force_encoding("utf-16le") + ec.putback.should == "" + end + it "accepts an integer argument corresponding to the number of bytes to be put back" do ec = Encoding::Converter.new("utf-16le", "iso-8859-1") - src = "\x00\xd8\x61\x00" - dst = "" + src = +"\x00\xd8\x61\x00" + dst = +"" ec.primitive_convert(src, dst).should == :invalid_byte_sequence ec.primitive_errinfo.should == [:invalid_byte_sequence, "UTF-16LE", "UTF-8", "\x00\xD8", "a\x00"] - ec.putback(1).should == "\x00".force_encoding("utf-16le") - ec.putback.should == "a".force_encoding("utf-16le") + ec.putback(2).should == "a\x00".dup.force_encoding("utf-16le") ec.putback.should == "" end end diff --git a/spec/ruby/core/encoding/converter/replacement_spec.rb b/spec/ruby/core/encoding/converter/replacement_spec.rb index a23be74e9b..ea514ca8dd 100644 --- a/spec/ruby/core/encoding/converter/replacement_spec.rb +++ b/spec/ruby/core/encoding/converter/replacement_spec.rb @@ -13,7 +13,7 @@ describe "Encoding::Converter#replacement" do it "returns \\uFFFD when the destination encoding is UTF-8" do ec = Encoding::Converter.new("us-ascii", "utf-8") - ec.replacement.should == "\u{fffd}".force_encoding('utf-8') + ec.replacement.should == "\u{fffd}".dup.force_encoding('utf-8') ec.replacement.encoding.should == Encoding::UTF_8 end end @@ -33,38 +33,38 @@ describe "Encoding::Converter#replacement=" do it "raises a TypeError if assigned a non-String argument" do ec = Encoding::Converter.new("utf-8", "us-ascii") - lambda { ec.replacement = nil }.should raise_error(TypeError) + -> { ec.replacement = nil }.should raise_error(TypeError) end it "sets #replacement" do ec = Encoding::Converter.new("us-ascii", "utf-8") - ec.replacement.should == "\u{fffd}".force_encoding('utf-8') + ec.replacement.should == "\u{fffd}".dup.force_encoding('utf-8') ec.replacement = '?'.encode('utf-8') - ec.replacement.should == '?'.force_encoding('utf-8') + ec.replacement.should == '?'.dup.force_encoding('utf-8') end it "raises an UndefinedConversionError is the argument cannot be converted into the destination encoding" do ec = Encoding::Converter.new("sjis", "ascii") - utf8_q = "\u{986}".force_encoding('utf-8') - ec.primitive_convert(utf8_q.dup, "").should == :undefined_conversion - lambda { ec.replacement = utf8_q }.should \ + utf8_q = "\u{986}".dup.force_encoding('utf-8') + ec.primitive_convert(utf8_q.dup, +"").should == :undefined_conversion + -> { ec.replacement = utf8_q }.should \ raise_error(Encoding::UndefinedConversionError) end it "does not change the replacement character if the argument cannot be converted into the destination encoding" do ec = Encoding::Converter.new("sjis", "ascii") - utf8_q = "\u{986}".force_encoding('utf-8') - ec.primitive_convert(utf8_q.dup, "").should == :undefined_conversion - lambda { ec.replacement = utf8_q }.should \ + utf8_q = "\u{986}".dup.force_encoding('utf-8') + ec.primitive_convert(utf8_q.dup, +"").should == :undefined_conversion + -> { ec.replacement = utf8_q }.should \ raise_error(Encoding::UndefinedConversionError) - ec.replacement.should == "?".force_encoding('us-ascii') + ec.replacement.should == "?".dup.force_encoding('us-ascii') end it "uses the replacement character" do ec = Encoding::Converter.new("utf-8", "us-ascii", :invalid => :replace, :undef => :replace) ec.replacement = "!" - dest = "" - status = ec.primitive_convert "中文123", dest + dest = +"" + status = ec.primitive_convert(+"中文123", dest) status.should == :finished dest.should == "!!123" diff --git a/spec/ruby/core/encoding/converter/search_convpath_spec.rb b/spec/ruby/core/encoding/converter/search_convpath_spec.rb index bd7530405b..59fe4520c0 100644 --- a/spec/ruby/core/encoding/converter/search_convpath_spec.rb +++ b/spec/ruby/core/encoding/converter/search_convpath_spec.rb @@ -15,18 +15,16 @@ describe "Encoding::Converter.search_convpath" do end it "indicates if crlf_newline conversion would occur" do - cp = Encoding::Converter.search_convpath( - "ISO-8859-1", "EUC-JP", {crlf_newline: true}) + cp = Encoding::Converter.search_convpath("ISO-8859-1", "EUC-JP", crlf_newline: true) cp.last.should == "crlf_newline" - cp = Encoding::Converter.search_convpath( - "ASCII", "UTF-8", {crlf_newline: false}) + cp = Encoding::Converter.search_convpath("ASCII", "UTF-8", crlf_newline: false) cp.last.should_not == "crlf_newline" end it "raises an Encoding::ConverterNotFoundError if no conversion path exists" do - lambda do - Encoding::Converter.search_convpath(Encoding::BINARY, Encoding::Emacs_Mule) - end.should raise_error(Encoding::ConverterNotFoundError) + -> do + Encoding::Converter.search_convpath(Encoding::BINARY, Encoding::Emacs_Mule) + end.should raise_error(Encoding::ConverterNotFoundError) end end diff --git a/spec/ruby/core/encoding/default_external_spec.rb b/spec/ruby/core/encoding/default_external_spec.rb index 8973490901..9aae4976e0 100644 --- a/spec/ruby/core/encoding/default_external_spec.rb +++ b/spec/ruby/core/encoding/default_external_spec.rb @@ -17,6 +17,12 @@ describe "Encoding.default_external" do Encoding.default_external = Encoding::SHIFT_JIS Encoding.default_external.should == Encoding::SHIFT_JIS end + + platform_is :windows do + it 'is UTF-8 by default on Windows' do + Encoding.default_external.should == Encoding::UTF_8 + end + end end describe "Encoding.default_external=" do @@ -54,10 +60,10 @@ describe "Encoding.default_external=" do end it "raises a TypeError unless the argument is an Encoding or convertible to a String" do - lambda { Encoding.default_external = [] }.should raise_error(TypeError) + -> { Encoding.default_external = [] }.should raise_error(TypeError) end it "raises an ArgumentError if the argument is nil" do - lambda { Encoding.default_external = nil }.should raise_error(ArgumentError) + -> { Encoding.default_external = nil }.should raise_error(ArgumentError) end end diff --git a/spec/ruby/core/encoding/default_internal_spec.rb b/spec/ruby/core/encoding/default_internal_spec.rb index 47a6887eee..855f4e9f32 100644 --- a/spec/ruby/core/encoding/default_internal_spec.rb +++ b/spec/ruby/core/encoding/default_internal_spec.rb @@ -60,11 +60,11 @@ describe "Encoding.default_internal=" do obj = mock('string') obj.should_receive(:to_str).at_least(1).times.and_return(1) - lambda { Encoding.default_internal = obj }.should raise_error(TypeError) + -> { Encoding.default_internal = obj }.should raise_error(TypeError) end it "raises a TypeError when passed an object not providing #to_str" do - lambda { Encoding.default_internal = mock("encoding") }.should raise_error(TypeError) + -> { Encoding.default_internal = mock("encoding") }.should raise_error(TypeError) end it "accepts an argument of nil to unset the default internal encoding" do diff --git a/spec/ruby/core/encoding/find_spec.rb b/spec/ruby/core/encoding/find_spec.rb index 5635a51c69..9c34fe0e77 100644 --- a/spec/ruby/core/encoding/find_spec.rb +++ b/spec/ruby/core/encoding/find_spec.rb @@ -18,7 +18,7 @@ describe "Encoding.find" do end it "raises a TypeError if passed a Symbol" do - lambda { Encoding.find(:"utf-8") }.should raise_error(TypeError) + -> { Encoding.find(:"utf-8") }.should raise_error(TypeError) end it "returns the passed Encoding object" do @@ -50,7 +50,7 @@ describe "Encoding.find" do end it "raises an ArgumentError if the given encoding does not exist" do - lambda { Encoding.find('dh2dh278d') }.should raise_error(ArgumentError) + -> { Encoding.find('dh2dh278d') }.should raise_error(ArgumentError, 'unknown encoding name - dh2dh278d') end # Not sure how to do a better test, since locale depends on weird platform-specific stuff diff --git a/spec/ruby/core/encoding/fixtures/classes.rb b/spec/ruby/core/encoding/fixtures/classes.rb index 12e9a4f348..943865e8d8 100644 --- a/spec/ruby/core/encoding/fixtures/classes.rb +++ b/spec/ruby/core/encoding/fixtures/classes.rb @@ -1,4 +1,4 @@ -# -*- encoding: binary -*- +# encoding: binary module EncodingSpecs class UndefinedConversionError def self.exception diff --git a/spec/ruby/core/encoding/inspect_spec.rb b/spec/ruby/core/encoding/inspect_spec.rb index 9a930b2a77..df96141db9 100644 --- a/spec/ruby/core/encoding/inspect_spec.rb +++ b/spec/ruby/core/encoding/inspect_spec.rb @@ -5,9 +5,23 @@ describe "Encoding#inspect" do Encoding::UTF_8.inspect.should be_an_instance_of(String) end - it "returns #<Encoding:name> for a non-dummy encoding named 'name'" do - Encoding.list.to_a.reject {|e| e.dummy? }.each do |enc| - enc.inspect.should =~ /#<Encoding:#{enc.name}>/ + ruby_version_is ""..."3.4" do + it "returns #<Encoding:name> for a non-dummy encoding named 'name'" do + Encoding.list.to_a.reject {|e| e.dummy? }.each do |enc| + enc.inspect.should =~ /#<Encoding:#{enc.name}>/ + end + end + end + + ruby_version_is "3.4" do + it "returns #<Encoding:name> for a non-dummy encoding named 'name'" do + Encoding.list.to_a.reject {|e| e.dummy? }.each do |enc| + if enc.name == "ASCII-8BIT" + enc.inspect.should == "#<Encoding:BINARY (ASCII-8BIT)>" + else + enc.inspect.should =~ /#<Encoding:#{enc.name}>/ + end + end end end diff --git a/spec/ruby/core/encoding/invalid_byte_sequence_error/destination_encoding_name_spec.rb b/spec/ruby/core/encoding/invalid_byte_sequence_error/destination_encoding_name_spec.rb index f5fa6f55e3..2b15fc1a0f 100644 --- a/spec/ruby/core/encoding/invalid_byte_sequence_error/destination_encoding_name_spec.rb +++ b/spec/ruby/core/encoding/invalid_byte_sequence_error/destination_encoding_name_spec.rb @@ -1,3 +1,4 @@ +require_relative "../../../spec_helper" require_relative '../fixtures/classes' describe "Encoding::InvalidByteSequenceError#destination_encoding_name" do diff --git a/spec/ruby/core/encoding/invalid_byte_sequence_error/destination_encoding_spec.rb b/spec/ruby/core/encoding/invalid_byte_sequence_error/destination_encoding_spec.rb index 43be3ddd71..c2ed6de1d8 100644 --- a/spec/ruby/core/encoding/invalid_byte_sequence_error/destination_encoding_spec.rb +++ b/spec/ruby/core/encoding/invalid_byte_sequence_error/destination_encoding_spec.rb @@ -1,3 +1,4 @@ +require_relative "../../../spec_helper" require_relative '../fixtures/classes' describe "Encoding::InvalidByteSequenceError#destination_encoding" do diff --git a/spec/ruby/core/encoding/invalid_byte_sequence_error/error_bytes_spec.rb b/spec/ruby/core/encoding/invalid_byte_sequence_error/error_bytes_spec.rb index a8f7354b16..8b7e87960f 100644 --- a/spec/ruby/core/encoding/invalid_byte_sequence_error/error_bytes_spec.rb +++ b/spec/ruby/core/encoding/invalid_byte_sequence_error/error_bytes_spec.rb @@ -1,4 +1,5 @@ -# -*- encoding: binary -*- +# encoding: binary +require_relative "../../../spec_helper" require_relative '../fixtures/classes' describe "Encoding::InvalidByteSequenceError#error_bytes" do diff --git a/spec/ruby/core/encoding/invalid_byte_sequence_error/incomplete_input_spec.rb b/spec/ruby/core/encoding/invalid_byte_sequence_error/incomplete_input_spec.rb index e3ef3e4557..83606f77b4 100644 --- a/spec/ruby/core/encoding/invalid_byte_sequence_error/incomplete_input_spec.rb +++ b/spec/ruby/core/encoding/invalid_byte_sequence_error/incomplete_input_spec.rb @@ -1,15 +1,14 @@ -# -*- encoding: binary -*- +# encoding: binary require_relative '../../../spec_helper' describe "Encoding::InvalidByteSequenceError#incomplete_input?" do - it "returns nil by default" do Encoding::InvalidByteSequenceError.new.incomplete_input?.should be_nil end it "returns true if #primitive_convert returned :incomplete_input for the same data" do ec = Encoding::Converter.new("EUC-JP", "ISO-8859-1") - ec.primitive_convert("\xA1",'').should == :incomplete_input + ec.primitive_convert(+"\xA1", +'').should == :incomplete_input begin ec.convert("\xA1") rescue Encoding::InvalidByteSequenceError => e @@ -19,7 +18,7 @@ describe "Encoding::InvalidByteSequenceError#incomplete_input?" do it "returns false if #primitive_convert returned :invalid_byte_sequence for the same data" do ec = Encoding::Converter.new("ascii", "utf-8") - ec.primitive_convert("\xfffffffff",'').should == :invalid_byte_sequence + ec.primitive_convert(+"\xfffffffff", +'').should == :invalid_byte_sequence begin ec.convert("\xfffffffff") rescue Encoding::InvalidByteSequenceError => e diff --git a/spec/ruby/core/encoding/invalid_byte_sequence_error/readagain_bytes_spec.rb b/spec/ruby/core/encoding/invalid_byte_sequence_error/readagain_bytes_spec.rb index 93823b5db4..e5ad0a61bd 100644 --- a/spec/ruby/core/encoding/invalid_byte_sequence_error/readagain_bytes_spec.rb +++ b/spec/ruby/core/encoding/invalid_byte_sequence_error/readagain_bytes_spec.rb @@ -1,4 +1,5 @@ -# -*- encoding: binary -*- +# encoding: binary +require_relative "../../../spec_helper" require_relative '../fixtures/classes' describe "Encoding::InvalidByteSequenceError#readagain_bytes" do @@ -14,11 +15,11 @@ describe "Encoding::InvalidByteSequenceError#readagain_bytes" do it "returns the bytes to be read again" do @exception.readagain_bytes.size.should == 1 - @exception.readagain_bytes.should == "a".force_encoding('binary') + @exception.readagain_bytes.should == "a".dup.force_encoding('binary') @exception.readagain_bytes.should == @errinfo[-1] @exception2.readagain_bytes.size.should == 1 - @exception2.readagain_bytes.should == "\xFF".force_encoding('binary') + @exception2.readagain_bytes.should == "\xFF".dup.force_encoding('binary') @exception2.readagain_bytes.should == @errinfo2[-1] end diff --git a/spec/ruby/core/encoding/invalid_byte_sequence_error/source_encoding_name_spec.rb b/spec/ruby/core/encoding/invalid_byte_sequence_error/source_encoding_name_spec.rb index bd3a51cbc5..a9464114a8 100644 --- a/spec/ruby/core/encoding/invalid_byte_sequence_error/source_encoding_name_spec.rb +++ b/spec/ruby/core/encoding/invalid_byte_sequence_error/source_encoding_name_spec.rb @@ -1,3 +1,4 @@ +require_relative "../../../spec_helper" require_relative '../fixtures/classes' describe "Encoding::UndefinedConversionError#source_encoding_name" do diff --git a/spec/ruby/core/encoding/invalid_byte_sequence_error/source_encoding_spec.rb b/spec/ruby/core/encoding/invalid_byte_sequence_error/source_encoding_spec.rb index f43d6d5830..7fdc0a122b 100644 --- a/spec/ruby/core/encoding/invalid_byte_sequence_error/source_encoding_spec.rb +++ b/spec/ruby/core/encoding/invalid_byte_sequence_error/source_encoding_spec.rb @@ -1,3 +1,4 @@ +require_relative "../../../spec_helper" require_relative '../fixtures/classes' describe "Encoding::InvalidByteSequenceError#source_encoding" do diff --git a/spec/ruby/core/encoding/list_spec.rb b/spec/ruby/core/encoding/list_spec.rb index 2a2078974e..bd3d5b7bc0 100644 --- a/spec/ruby/core/encoding/list_spec.rb +++ b/spec/ruby/core/encoding/list_spec.rb @@ -12,7 +12,7 @@ describe "Encoding.list" do end it "returns each encoding only once" do - orig = Encoding.list.map {|e| e.name} + orig = Encoding.list.map { |e| e.name } orig.should == orig.uniq end @@ -33,7 +33,15 @@ describe "Encoding.list" do end it "includes dummy encodings" do - Encoding.list.select {|e| e.dummy?}.should_not == [] + Encoding.list.select { |e| e.dummy? }.should_not == [] + end + + it 'includes UTF-8 encoding' do + Encoding.list.should.include?(Encoding::UTF_8) + end + + it 'includes CESU-8 encoding' do + Encoding.list.should.include?(Encoding::CESU_8) end # TODO: Find example that illustrates this diff --git a/spec/ruby/core/encoding/locale_charmap_spec.rb b/spec/ruby/core/encoding/locale_charmap_spec.rb index 5963a8beb5..8143b9083a 100644 --- a/spec/ruby/core/encoding/locale_charmap_spec.rb +++ b/spec/ruby/core/encoding/locale_charmap_spec.rb @@ -7,11 +7,13 @@ describe "Encoding.locale_charmap" do # FIXME: Get this working on Windows platform_is :linux do - it "returns a value based on the LC_ALL environment variable" do - old_lc_all = ENV['LC_ALL'] - ENV['LC_ALL'] = 'C' - ruby_exe("print Encoding.locale_charmap").should == 'ANSI_X3.4-1968' - ENV['LC_ALL'] = old_lc_all + platform_is_not :android do + it "returns a value based on the LC_ALL environment variable" do + old_lc_all = ENV['LC_ALL'] + ENV['LC_ALL'] = 'C' + ruby_exe("print Encoding.locale_charmap").should == 'ANSI_X3.4-1968' + ENV['LC_ALL'] = old_lc_all + end end end @@ -33,6 +35,15 @@ describe "Encoding.locale_charmap" do end end + platform_is :android do + it "always returns UTF-8" do + old_lc_all = ENV['LC_ALL'] + ENV['LC_ALL'] = 'C' + ruby_exe("print Encoding.locale_charmap").should == 'UTF-8' + ENV['LC_ALL'] = old_lc_all + end + end + platform_is :bsd, :darwin, :linux do it "is unaffected by assigning to ENV['LC_ALL'] in the same process" do old_charmap = Encoding.locale_charmap diff --git a/spec/ruby/core/encoding/name_spec.rb b/spec/ruby/core/encoding/name_spec.rb index 5eadb1d2f5..dce9347978 100644 --- a/spec/ruby/core/encoding/name_spec.rb +++ b/spec/ruby/core/encoding/name_spec.rb @@ -1,3 +1,4 @@ +require_relative "../../spec_helper" require_relative 'shared/name' describe "Encoding#name" do diff --git a/spec/ruby/core/encoding/replicate_spec.rb b/spec/ruby/core/encoding/replicate_spec.rb index 717e9cea72..2da998837f 100644 --- a/spec/ruby/core/encoding/replicate_spec.rb +++ b/spec/ruby/core/encoding/replicate_spec.rb @@ -1,46 +1,88 @@ -# -*- encoding: binary -*- +# encoding: binary require_relative '../../spec_helper' describe "Encoding#replicate" do - before :all do - @i = 0 - end + ruby_version_is ""..."3.3" do + before :all do + @i = 0 + end - before :each do - @i += 1 - @prefix = "RS#{@i}" - end + before :each do + @i += 1 + @prefix = "RS#{@i}" + end - it "returns a replica of ASCII" do - name = @prefix + '-ASCII' - e = Encoding::ASCII.replicate(name) - e.name.should == name - "a".force_encoding(e).valid_encoding?.should be_true - "\x80".force_encoding(e).valid_encoding?.should be_false - end + it "returns a replica of ASCII" do + name = @prefix + '-ASCII' + e = suppress_warning { Encoding::ASCII.replicate(name) } + e.name.should == name + Encoding.find(name).should == e + + "a".dup.force_encoding(e).valid_encoding?.should be_true + "\x80".dup.force_encoding(e).valid_encoding?.should be_false + end + + it "returns a replica of UTF-8" do + name = @prefix + 'UTF-8' + e = suppress_warning { Encoding::UTF_8.replicate(name) } + e.name.should == name + Encoding.find(name).should == e + + "a".dup.force_encoding(e).valid_encoding?.should be_true + "\u3042".dup.force_encoding(e).valid_encoding?.should be_true + "\x80".dup.force_encoding(e).valid_encoding?.should be_false + end - it "returns a replica of UTF-8" do - name = @prefix + 'UTF-8' - e = Encoding::UTF_8.replicate(name) - e.name.should == name - "a".force_encoding(e).valid_encoding?.should be_true - "\u3042".force_encoding(e).valid_encoding?.should be_true - "\x80".force_encoding(e).valid_encoding?.should be_false + it "returns a replica of UTF-16BE" do + name = @prefix + 'UTF-16-BE' + e = suppress_warning { Encoding::UTF_16BE.replicate(name) } + e.name.should == name + Encoding.find(name).should == e + + "a".dup.force_encoding(e).valid_encoding?.should be_false + "\x30\x42".dup.force_encoding(e).valid_encoding?.should be_true + "\x80".dup.force_encoding(e).valid_encoding?.should be_false + end + + it "returns a replica of ISO-2022-JP" do + name = @prefix + 'ISO-2022-JP' + e = suppress_warning { Encoding::ISO_2022_JP.replicate(name) } + Encoding.find(name).should == e + + e.name.should == name + e.dummy?.should be_true + end + + # NOTE: it's unclear of the value of this (for the complexity cost of it), + # but it is the current CRuby behavior. + it "can be associated with a String" do + name = @prefix + '-US-ASCII' + e = suppress_warning { Encoding::US_ASCII.replicate(name) } + e.name.should == name + Encoding.find(name).should == e + + s = "abc".dup.force_encoding(e) + s.encoding.should == e + s.encoding.name.should == name + end end - it "returns a replica of UTF-16BE" do - name = @prefix + 'UTF-16-BE' - e = Encoding::UTF_16BE.replicate(name) - e.name.should == name - "a".force_encoding(e).valid_encoding?.should be_false - "\x30\x42".force_encoding(e).valid_encoding?.should be_true - "\x80".force_encoding(e).valid_encoding?.should be_false + ruby_version_is ""..."3.3" do + it "warns about deprecation" do + -> { + Encoding::US_ASCII.replicate('MY-US-ASCII') + }.should complain(/warning: Encoding#replicate is deprecated and will be removed in Ruby 3.3; use the original encoding instead/) + end + + it "raises EncodingError if too many encodings" do + code = '1_000.times {|i| Encoding::US_ASCII.replicate("R_#{i}") }' + ruby_exe(code, args: "2>&1", exit_status: 1).should.include?('too many encoding (> 256) (EncodingError)') + end end - it "returns a replica of ISO-2022-JP" do - name = @prefix + 'ISO-2022-JP' - e = Encoding::ISO_2022_JP.replicate(name) - e.name.should == name - e.dummy?.should be_true + ruby_version_is "3.3" do + it "has been removed" do + Encoding::US_ASCII.should_not.respond_to?(:replicate, true) + end end end diff --git a/spec/ruby/core/encoding/to_s_spec.rb b/spec/ruby/core/encoding/to_s_spec.rb index 82d282386b..bab394a888 100644 --- a/spec/ruby/core/encoding/to_s_spec.rb +++ b/spec/ruby/core/encoding/to_s_spec.rb @@ -1,3 +1,4 @@ +require_relative "../../spec_helper" require_relative 'shared/name' describe "Encoding#to_s" do diff --git a/spec/ruby/core/encoding/undefined_conversion_error/destination_encoding_name_spec.rb b/spec/ruby/core/encoding/undefined_conversion_error/destination_encoding_name_spec.rb index 106fc7ecac..a51a9f46a0 100644 --- a/spec/ruby/core/encoding/undefined_conversion_error/destination_encoding_name_spec.rb +++ b/spec/ruby/core/encoding/undefined_conversion_error/destination_encoding_name_spec.rb @@ -1,3 +1,4 @@ +require_relative "../../../spec_helper" require_relative '../fixtures/classes' describe "Encoding::UndefinedConversionError#destination_encoding_name" do diff --git a/spec/ruby/core/encoding/undefined_conversion_error/destination_encoding_spec.rb b/spec/ruby/core/encoding/undefined_conversion_error/destination_encoding_spec.rb index c6e24732fd..905556407c 100644 --- a/spec/ruby/core/encoding/undefined_conversion_error/destination_encoding_spec.rb +++ b/spec/ruby/core/encoding/undefined_conversion_error/destination_encoding_spec.rb @@ -1,3 +1,4 @@ +require_relative "../../../spec_helper" require_relative '../fixtures/classes' describe "Encoding::UndefinedConversionError#destination_encoding" do diff --git a/spec/ruby/core/encoding/undefined_conversion_error/error_char_spec.rb b/spec/ruby/core/encoding/undefined_conversion_error/error_char_spec.rb index 780d81c1ee..9cb55e6d95 100644 --- a/spec/ruby/core/encoding/undefined_conversion_error/error_char_spec.rb +++ b/spec/ruby/core/encoding/undefined_conversion_error/error_char_spec.rb @@ -1,3 +1,4 @@ +require_relative "../../../spec_helper" require_relative '../fixtures/classes' describe "Encoding::UndefinedConversionError#error_char" do diff --git a/spec/ruby/core/encoding/undefined_conversion_error/source_encoding_name_spec.rb b/spec/ruby/core/encoding/undefined_conversion_error/source_encoding_name_spec.rb index 3b697cb82f..d5e60e78db 100644 --- a/spec/ruby/core/encoding/undefined_conversion_error/source_encoding_name_spec.rb +++ b/spec/ruby/core/encoding/undefined_conversion_error/source_encoding_name_spec.rb @@ -1,3 +1,4 @@ +require_relative "../../../spec_helper" require_relative '../fixtures/classes' describe "Encoding::UndefinedConversionError#source_encoding_name" do diff --git a/spec/ruby/core/encoding/undefined_conversion_error/source_encoding_spec.rb b/spec/ruby/core/encoding/undefined_conversion_error/source_encoding_spec.rb index 9101d51e11..de456a4b5a 100644 --- a/spec/ruby/core/encoding/undefined_conversion_error/source_encoding_spec.rb +++ b/spec/ruby/core/encoding/undefined_conversion_error/source_encoding_spec.rb @@ -1,3 +1,4 @@ +require_relative "../../../spec_helper" require_relative '../fixtures/classes' describe "Encoding::UndefinedConversionError#source_encoding" do |