diff options
Diffstat (limited to 'spec/ruby/core/encoding/converter')
8 files changed, 49 insertions, 33 deletions
diff --git a/spec/ruby/core/encoding/converter/convert_spec.rb b/spec/ruby/core/encoding/converter/convert_spec.rb index 95a9e0b758..7f249d90a3 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 -*- +# frozen_string_literal: true require_relative '../../../spec_helper' describe "Encoding::Converter#convert" do @@ -9,31 +10,31 @@ 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')) - -> { ec.convert("\u{6543}".force_encoding('UTF-8')) }.should \ + -> { ec.convert("\u{6543}".dup.force_encoding('UTF-8')) }.should \ raise_error(Encoding::UndefinedConversionError) end diff --git a/spec/ruby/core/encoding/converter/finish_spec.rb b/spec/ruby/core/encoding/converter/finish_spec.rb index 11ca7e8510..239243430b 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..78779be70b 100644 --- a/spec/ruby/core/encoding/converter/last_error_spec.rb +++ b/spec/ruby/core/encoding/converter/last_error_spec.rb @@ -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 1f7affc72b..db9c3364d7 100644 --- a/spec/ruby/core/encoding/converter/new_spec.rb +++ b/spec/ruby/core/encoding/converter/new_spec.rb @@ -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 802d8e7cb1..63f25eddef 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 -*- +# frozen_string_literal: false require_relative '../../../spec_helper' describe "Encoding::Converter#primitive_convert" do @@ -14,6 +15,10 @@ describe "Encoding::Converter#primitive_convert" do -> { @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 -> { @ec.primitive_convert("","", nil) }.should_not raise_error end diff --git a/spec/ruby/core/encoding/converter/primitive_errinfo_spec.rb b/spec/ruby/core/encoding/converter/primitive_errinfo_spec.rb index 1f836b259f..668eb9a924 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 -*- +# frozen_string_literal: false require_relative '../../../spec_helper' describe "Encoding::Converter#primitive_errinfo" do diff --git a/spec/ruby/core/encoding/converter/putback_spec.rb b/spec/ruby/core/encoding/converter/putback_spec.rb index 87495eaf3f..e19fe6c314 100644 --- a/spec/ruby/core/encoding/converter/putback_spec.rb +++ b/spec/ruby/core/encoding/converter/putback_spec.rb @@ -4,7 +4,7 @@ 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 5ca42e7e5a..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 @@ -38,33 +38,33 @@ describe "Encoding::Converter#replacement=" do 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 + 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 + 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" |