diff options
| author | Benoit Daloze <[email protected]> | 2022-08-29 15:36:29 +0200 |
|---|---|---|
| committer | Benoit Daloze <[email protected]> | 2022-08-29 15:36:29 +0200 |
| commit | 4ee1a687768338a1928014fc6042c320a1a1af3e (patch) | |
| tree | 37c1717dcd7a2a757e343a41b827fd096397fbca /spec/ruby/optional/capi/encoding_spec.rb | |
| parent | a319d3cfdc1afef8497321fee7f690052b16739c (diff) | |
Update to ruby/spec@d01709f
Diffstat (limited to 'spec/ruby/optional/capi/encoding_spec.rb')
| -rw-r--r-- | spec/ruby/optional/capi/encoding_spec.rb | 42 |
1 files changed, 42 insertions, 0 deletions
diff --git a/spec/ruby/optional/capi/encoding_spec.rb b/spec/ruby/optional/capi/encoding_spec.rb index ae557b03d7..aa632b963b 100644 --- a/spec/ruby/optional/capi/encoding_spec.rb +++ b/spec/ruby/optional/capi/encoding_spec.rb @@ -63,6 +63,48 @@ describe "C-API Encoding function" do end end + describe "rb_enc_strlen" do + before :each do + @str = 'こにちわ' # Each codepoint in this string is 3 bytes in UTF-8 + end + + it "returns the correct string length for the encoding" do + @s.rb_enc_strlen(@str, @str.bytesize, Encoding::UTF_8).should == 4 + @s.rb_enc_strlen(@str, @str.bytesize, Encoding::BINARY).should == 12 + end + + it "returns the string length based on a fixed-width encoding's character length, even if the encoding is incompatible" do + @s.rb_enc_strlen(@str, @str.bytesize, Encoding::UTF_16BE).should == 6 + @s.rb_enc_strlen(@str, @str.bytesize, Encoding::UTF_16LE).should == 6 + @s.rb_enc_strlen(@str, @str.bytesize, Encoding::UTF_32BE).should == 3 + @s.rb_enc_strlen(@str, @str.bytesize, Encoding::UTF_32LE).should == 3 + end + + it "does not consider strings to be NUL-terminated" do + s = "abc\0def" + @s.rb_enc_strlen(s, s.bytesize, Encoding::US_ASCII).should == 7 + @s.rb_enc_strlen(s, s.bytesize, Encoding::UTF_8).should == 7 + end + + describe "handles broken strings" do + it "combines valid character and invalid character counts in UTF-8" do + # The result is 3 because `rb_enc_strlen` counts the first valid character and then adds + # the byte count for the invalid character that follows for 1 + 2. + @s.rb_enc_strlen(@str, 5, Encoding::UTF_8).should == 3 + end + + it "combines valid character and invalid character counts in UTF-16" do + @s.rb_enc_strlen(@str, 5, Encoding::UTF_16BE).should == 3 + end + + it "rounds up for fixed-width encodings" do + @s.rb_enc_strlen(@str, 7, Encoding::UTF_32BE).should == 2 + @s.rb_enc_strlen(@str, 7, Encoding::UTF_32LE).should == 2 + @s.rb_enc_strlen(@str, 5, Encoding::BINARY).should == 5 + end + end + end + describe "rb_enc_find" do it "returns the encoding of an Encoding" do @s.rb_enc_find("UTF-8").should == "UTF-8" |