diff options
Diffstat (limited to 'spec/ruby/optional/capi/string_spec.rb')
| -rw-r--r-- | spec/ruby/optional/capi/string_spec.rb | 272 |
1 files changed, 209 insertions, 63 deletions
diff --git a/spec/ruby/optional/capi/string_spec.rb b/spec/ruby/optional/capi/string_spec.rb index 3a47fa9762..72f20ee6a5 100644 --- a/spec/ruby/optional/capi/string_spec.rb +++ b/spec/ruby/optional/capi/string_spec.rb @@ -1,4 +1,5 @@ # encoding: utf-8 +# frozen_string_literal: false require_relative 'spec_helper' require_relative '../../shared/string/times' @@ -47,7 +48,7 @@ describe "C-API String function" do [Encoding::BINARY, Encoding::UTF_8].each do |enc| describe "rb_str_set_len on a #{enc.name} String" do before :each do - @str = "abcdefghij".force_encoding(enc) + @str = "abcdefghij".dup.force_encoding(enc) # Make sure to unshare the string @s.rb_str_modify(@str) end @@ -99,7 +100,7 @@ describe "C-API String function" do describe "rb_str_set_len on a UTF-16 String" do before :each do - @str = "abcdefghij".force_encoding(Encoding::UTF_16BE) + @str = "abcdefghij".dup.force_encoding(Encoding::UTF_16BE) # Make sure to unshare the string @s.rb_str_modify(@str) end @@ -112,7 +113,7 @@ describe "C-API String function" do describe "rb_str_set_len on a UTF-32 String" do before :each do - @str = "abcdefghijkl".force_encoding(Encoding::UTF_32BE) + @str = "abcdefghijkl".dup.force_encoding(Encoding::UTF_32BE) # Make sure to unshare the string @s.rb_str_modify(@str) end @@ -190,11 +191,19 @@ describe "C-API String function" do end it "returns a new String object filled with \\0 bytes" do - s = @s.rb_str_tmp_new(4) - s.encoding.should == Encoding::BINARY - s.bytesize.should == 4 - s.size.should == 4 - s.should == "\x00\x00\x00\x00" + lens = [4] + + ruby_version_is "4.0" do + lens << 100 + end + + lens.each do |len| + s = @s.rb_str_tmp_new(len) + s.encoding.should == Encoding::BINARY + s.bytesize.should == len + s.size.should == len + s.should == "\x00" * len + end end end @@ -231,7 +240,7 @@ describe "C-API String function" do describe "rb_usascii_str_new" do it "creates a new String with US-ASCII Encoding from a char buffer of len characters" do - str = "abc".force_encoding("us-ascii") + str = "abc".dup.force_encoding("us-ascii") result = @s.rb_usascii_str_new("abcdef", 3) result.should == str result.encoding.should == Encoding::US_ASCII @@ -247,14 +256,14 @@ describe "C-API String function" do it "returns US-ASCII string for non-US-ASCII string literal" do str = @s.rb_usascii_str_new_lit_non_ascii - str.should == "r\xC3\xA9sum\xC3\xA9".force_encoding(Encoding::US_ASCII) + str.should == "r\xC3\xA9sum\xC3\xA9".dup.force_encoding(Encoding::US_ASCII) str.encoding.should == Encoding::US_ASCII end end describe "rb_usascii_str_new_cstr" do it "creates a new String with US-ASCII Encoding" do - str = "abc".force_encoding("us-ascii") + str = "abc".dup.force_encoding("us-ascii") result = @s.rb_usascii_str_new_cstr("abc") result.should == str result.encoding.should == Encoding::US_ASCII @@ -418,7 +427,7 @@ describe "C-API String function" do describe "rb_enc_str_buf_cat" do it "concatenates a C string literal to a ruby string with the given encoding" do - input = "hello ".force_encoding(Encoding::US_ASCII) + input = "hello ".dup.force_encoding(Encoding::US_ASCII) result = @s.rb_enc_str_buf_cat(input, "résumé", Encoding::UTF_8) result.should == "hello résumé" result.encoding.should == Encoding::UTF_8 @@ -448,6 +457,20 @@ describe "C-API String function" do end end + describe "rb_str_strlen" do + it 'returns 0 as the length of an empty string' do + @s.rb_str_strlen('').should == 0 + end + + it 'returns the number of characters in a string' do + @s.rb_str_strlen('hello').should == 5 + end + + it 'returns the number of characters in a string with multi-byte characters' do + @s.rb_str_strlen('こんにちは').should == 5 + end + end + describe "rb_str_split" do it "splits strings over a splitter" do @s.rb_str_split("Hello,Goodbye").should == ["Hello", "Goodbye"] @@ -498,29 +521,10 @@ describe "C-API String function" do end end - describe "rb_fstring" do - it 'returns self if the String is frozen' do - input = 'foo'.freeze - output = @s.rb_fstring(input) - - output.should equal(input) - output.should.frozen? - end - - it 'returns a frozen copy if the String is not frozen' do - input = 'foo' - output = @s.rb_fstring(input) - - output.should.frozen? - output.should_not equal(input) - output.should == 'foo' - end - end - describe "rb_str_subseq" do it "returns a byte-indexed substring" do - str = "\x00\x01\x02\x03\x04".force_encoding("binary") - @s.rb_str_subseq(str, 1, 2).should == "\x01\x02".force_encoding("binary") + str = "\x00\x01\x02\x03\x04".dup.force_encoding("binary") + @s.rb_str_subseq(str, 1, 2).should == "\x01\x02".dup.force_encoding("binary") end end @@ -731,7 +735,7 @@ describe "C-API String function" do end it "increases the size of the string" do - expected = "test".force_encoding("US-ASCII") + expected = "test".dup.force_encoding("US-ASCII") str = @s.rb_str_resize(expected.dup, 12) str.size.should == 12 str.bytesize.should == 12 @@ -862,11 +866,11 @@ describe "C-API String function" do # it "transcodes a String to Encoding.default_internal if it is set" do # Encoding.default_internal = Encoding::EUC_JP # -# - a = "\xE3\x81\x82\xe3\x82\x8c".force_encoding("utf-8") +# - a = "\xE3\x81\x82\xe3\x82\x8c".dup.force_encoding("utf-8") # + a = [0xE3, 0x81, 0x82, 0xe3, 0x82, 0x8c].pack('C6').force_encoding("utf-8") # s = @s.rb_external_str_new_with_enc(a, a.bytesize, Encoding::UTF_8) # - -# - s.should == "\xA4\xA2\xA4\xEC".force_encoding("euc-jp") +# - s.should == "\xA4\xA2\xA4\xEC".dup.force_encoding("euc-jp") # + x = [0xA4, 0xA2, 0xA4, 0xEC].pack('C4')#.force_encoding('binary') # + s.should == x # s.encoding.should equal(Encoding::EUC_JP) @@ -886,7 +890,7 @@ describe "C-API String function" do describe "rb_locale_str_new" do it "returns a String with 'locale' encoding" do s = @s.rb_locale_str_new("abc", 3) - s.should == "abc".force_encoding(Encoding.find("locale")) + s.should == "abc".dup.force_encoding(Encoding.find("locale")) s.encoding.should equal(Encoding.find("locale")) end end @@ -894,33 +898,37 @@ describe "C-API String function" do describe "rb_locale_str_new_cstr" do it "returns a String with 'locale' encoding" do s = @s.rb_locale_str_new_cstr("abc") - s.should == "abc".force_encoding(Encoding.find("locale")) + s.should == "abc".dup.force_encoding(Encoding.find("locale")) s.encoding.should equal(Encoding.find("locale")) end end describe "rb_str_conv_enc" do it "returns the original String when to encoding is not specified" do - a = "abc".force_encoding("us-ascii") + a = "abc".dup.force_encoding("us-ascii") @s.rb_str_conv_enc(a, Encoding::US_ASCII, nil).should equal(a) end it "returns the original String if a transcoding error occurs" do - a = [0xEE].pack('C').force_encoding("utf-8") - @s.rb_str_conv_enc(a, Encoding::UTF_8, Encoding::EUC_JP).should equal(a) + a = [0xEE].pack('C').force_encoding(Encoding::UTF_8) + @s.rb_str_conv_enc(a, Encoding::UTF_8, Encoding::EUC_JP).should.equal?(a) + a.encoding.should == Encoding::UTF_8 + + a = "\x80".b + @s.rb_str_conv_enc(a, Encoding::BINARY, Encoding::UTF_8).should.equal?(a) + a.encoding.should == Encoding::BINARY end it "returns a transcoded String" do - a = "\xE3\x81\x82\xE3\x82\x8C".force_encoding("utf-8") + a = "\xE3\x81\x82\xE3\x82\x8C".dup.force_encoding(Encoding::UTF_8) result = @s.rb_str_conv_enc(a, Encoding::UTF_8, Encoding::EUC_JP) - x = [0xA4, 0xA2, 0xA4, 0xEC].pack('C4').force_encoding('utf-8') - result.should == x.force_encoding("euc-jp") - result.encoding.should equal(Encoding::EUC_JP) + result.should == [0xA4, 0xA2, 0xA4, 0xEC].pack('C4').force_encoding(Encoding::EUC_JP) + result.encoding.should == Encoding::EUC_JP end describe "when the String encoding is equal to the destination encoding" do it "returns the original String" do - a = "abc".force_encoding("us-ascii") + a = "abc".dup.force_encoding("us-ascii") @s.rb_str_conv_enc(a, Encoding::US_ASCII, Encoding::US_ASCII).should equal(a) end @@ -930,7 +938,7 @@ describe "C-API String function" do end it "returns the origin String if the destination encoding is BINARY" do - a = "abc".force_encoding("binary") + a = "abc".dup.force_encoding("binary") @s.rb_str_conv_enc(a, Encoding::US_ASCII, Encoding::BINARY).should equal(a) end end @@ -938,7 +946,7 @@ describe "C-API String function" do describe "rb_str_conv_enc_opts" do it "returns the original String when to encoding is not specified" do - a = "abc".force_encoding("us-ascii") + a = "abc".dup.force_encoding("us-ascii") @s.rb_str_conv_enc_opts(a, Encoding::US_ASCII, nil, 0, nil).should equal(a) end @@ -949,7 +957,7 @@ describe "C-API String function" do end it "returns a transcoded String" do - a = "\xE3\x81\x82\xE3\x82\x8C".force_encoding("utf-8") + a = "\xE3\x81\x82\xE3\x82\x8C".dup.force_encoding("utf-8") result = @s.rb_str_conv_enc_opts(a, Encoding::UTF_8, Encoding::EUC_JP, 0, nil) x = [0xA4, 0xA2, 0xA4, 0xEC].pack('C4').force_encoding('utf-8') result.should == x.force_encoding("euc-jp") @@ -958,7 +966,7 @@ describe "C-API String function" do describe "when the String encoding is equal to the destination encoding" do it "returns the original String" do - a = "abc".force_encoding("us-ascii") + a = "abc".dup.force_encoding("us-ascii") @s.rb_str_conv_enc_opts(a, Encoding::US_ASCII, Encoding::US_ASCII, 0, nil).should equal(a) end @@ -970,7 +978,7 @@ describe "C-API String function" do end it "returns the origin String if the destination encoding is BINARY" do - a = "abc".force_encoding("binary") + a = "abc".dup.force_encoding("binary") @s.rb_str_conv_enc_opts(a, Encoding::US_ASCII, Encoding::BINARY, 0, nil).should equal(a) end @@ -988,7 +996,7 @@ describe "C-API String function" do describe "rb_str_export_locale" do it "returns the original String with the locale encoding" do s = @s.rb_str_export_locale("abc") - s.should == "abc".force_encoding(Encoding.find("locale")) + s.should == "abc".dup.force_encoding(Encoding.find("locale")) s.encoding.should equal(Encoding.find("locale")) end end @@ -1012,7 +1020,7 @@ describe "C-API String function" do result = @s.rb_str_export_to_enc(source, Encoding::UTF_8) source.bytes.should == [0, 255] end -end + end describe "rb_sprintf" do it "replaces the parts like sprintf" do @@ -1040,11 +1048,19 @@ end @s.rb_sprintf3(true.class).should == s end - ruby_bug "#19167", ""..."3.2" do - it "formats a TrueClass VALUE as 'true' if sign specified in format" do - s = 'Result: TrueClass.' - @s.rb_sprintf4(true.class).should == s - end + it "formats a TrueClass VALUE as 'true' if sign specified in format" do + s = 'Result: TrueClass.' + @s.rb_sprintf4(true.class).should == s + end + + it "formats nil using to_s if sign not specified in format" do + s = 'Result: .' + @s.rb_sprintf3(nil).should == s + end + + it "formats nil using inspect if sign specified in format" do + s = 'Result: nil.' + @s.rb_sprintf4(nil).should == s end it "truncates a string to a supplied precision if that is shorter than the string" do @@ -1114,7 +1130,7 @@ end end it "tries to convert the passed argument to a string by calling #to_s" do - @s.rb_String({"bar" => "foo"}).should == '{"bar"=>"foo"}' + @s.rb_String({"bar" => "foo"}).should == {"bar" => "foo"}.to_s end end @@ -1203,28 +1219,158 @@ end describe "rb_str_locktmp" do it "raises an error when trying to lock an already locked string" do - str = "test" + str = +"test" @s.rb_str_locktmp(str).should == str -> { @s.rb_str_locktmp(str) }.should raise_error(RuntimeError, 'temporal locking already locked string') end it "locks a string so that modifications would raise an error" do - str = "test" + str = +"test" @s.rb_str_locktmp(str).should == str -> { str.upcase! }.should raise_error(RuntimeError, 'can\'t modify string; temporarily locked') end + + ruby_version_is "4.0" do + it "raises FrozenError if string is frozen" do + str = -"rb_str_locktmp" + -> { @s.rb_str_locktmp(str) }.should raise_error(FrozenError) + + str = +"rb_str_locktmp" + str.freeze + -> { @s.rb_str_locktmp(str) }.should raise_error(FrozenError) + end + end end describe "rb_str_unlocktmp" do it "unlocks a locked string" do - str = "test" + str = +"test" @s.rb_str_locktmp(str) @s.rb_str_unlocktmp(str).should == str str.upcase!.should == "TEST" end it "raises an error when trying to unlock an already unlocked string" do - -> { @s.rb_str_unlocktmp("test") }.should raise_error(RuntimeError, 'temporal unlocking already unlocked string') + -> { @s.rb_str_unlocktmp(+"test") }.should raise_error(RuntimeError, 'temporal unlocking already unlocked string') + end + + ruby_version_is "4.0" do + it "raises FrozenError if string is frozen" do + str = -"rb_str_locktmp" + -> { @s.rb_str_unlocktmp(str) }.should raise_error(FrozenError) + + str = +"rb_str_locktmp" + str.freeze + -> { @s.rb_str_unlocktmp(str) }.should raise_error(FrozenError) + end + end + end + + describe "rb_enc_interned_str_cstr" do + it "returns a frozen string" do + str = "hello" + val = @s.rb_enc_interned_str_cstr(str, Encoding::US_ASCII) + + val.should.is_a?(String) + val.encoding.should == Encoding::US_ASCII + val.should.frozen? + end + + it "returns the same frozen string" do + str = "hello" + result1 = @s.rb_enc_interned_str_cstr(str, Encoding::US_ASCII) + result2 = @s.rb_enc_interned_str_cstr(str, Encoding::US_ASCII) + result1.should.equal?(result2) + end + + it "returns different frozen strings for different encodings" do + str = "hello" + result1 = @s.rb_enc_interned_str_cstr(str, Encoding::US_ASCII) + result2 = @s.rb_enc_interned_str_cstr(str, Encoding::UTF_8) + result1.should_not.equal?(result2) + end + + it "returns the same string as String#-@" do + @s.rb_enc_interned_str_cstr("hello", Encoding::UTF_8).should.equal?(-"hello") + end + + ruby_bug "#20322", ""..."3.4" do + it "uses the default encoding if encoding is null" do + str = "hello" + val = @s.rb_enc_interned_str_cstr(str, nil) + val.encoding.should == Encoding::ASCII_8BIT + end + end + end + + describe "rb_enc_interned_str" do + it "returns a frozen string" do + str = "hello" + val = @s.rb_enc_interned_str(str, str.bytesize, Encoding::US_ASCII) + + val.should.is_a?(String) + val.encoding.should == Encoding::US_ASCII + val.should.frozen? + end + + it "returns the same frozen string" do + str = "hello" + result1 = @s.rb_enc_interned_str(str, str.bytesize, Encoding::US_ASCII) + result2 = @s.rb_enc_interned_str(str, str.bytesize, Encoding::US_ASCII) + result1.should.equal?(result2) + end + + it "returns different frozen strings for different encodings" do + str = "hello" + result1 = @s.rb_enc_interned_str(str, str.bytesize, Encoding::US_ASCII) + result2 = @s.rb_enc_interned_str(str, str.bytesize, Encoding::UTF_8) + result1.should_not.equal?(result2) + end + + it 'returns the same string when using non-ascii characters' do + str = 'こんにちは' + result1 = @s.rb_enc_interned_str(str, str.bytesize, Encoding::UTF_8) + result2 = @s.rb_enc_interned_str(str, str.bytesize, Encoding::UTF_8) + result1.should.equal?(result2) + end + + it "returns the same string as String#-@" do + str = "hello" + @s.rb_enc_interned_str(str, str.bytesize, Encoding::UTF_8).should.equal?(-str) + end + + ruby_bug "#20322", ""..."3.4" do + it "uses the default encoding if encoding is null" do + str = "hello" + val = @s.rb_enc_interned_str(str, str.bytesize, nil) + val.encoding.should == Encoding::ASCII_8BIT + end + end + end + + describe "rb_str_to_interned_str" do + it "returns a frozen string" do + str = "hello" + result = @s.rb_str_to_interned_str(str) + result.should.is_a?(String) + result.should.frozen? + end + + it "returns the same frozen string" do + str = "hello" + result1 = @s.rb_str_to_interned_str(str) + result2 = @s.rb_str_to_interned_str(str) + result1.should.equal?(result2) + end + + it "returns different frozen strings for different encodings" do + result1 = @s.rb_str_to_interned_str("hello".dup.force_encoding(Encoding::US_ASCII)) + result2 = @s.rb_str_to_interned_str("hello".dup.force_encoding(Encoding::UTF_8)) + result1.should_not.equal?(result2) + end + + it "returns the same string as String#-@" do + @s.rb_str_to_interned_str("hello").should.equal?(-"hello") end end end |
