With Tom's \u commit, we now run over 10K examples in 1.9 CI.

spec/tags/1.9/ruby/core/encoding/converter/replacement_tags.txt

@@ -5,3 +5,4 @@ fails:Encoding::Converter#replacement= raises an TypeError if assigned a non-Str
 fails:Encoding::Converter#replacement= sets #replacement
 fails:Encoding::Converter#replacement= raises an UndefinedConversionError is the argument cannot be converted into the destination encoding
 fails:Encoding::Converter#replacement= does not change the replacement character if the argument cannot be converted into the destination encoding
+fails:Encoding::Converter#replacement returns � when the destination encoding is UTF-8

spec/tags/1.9/ruby/core/string/chars_tags.txt

@@ -1,4 +1 @@
 fails:String#chars is unicode aware
-fails:String#chars works with multibyte characters
-fails:String#chars returns a different character if the String is transcoded
-fails:String#chars uses the String's encoding to determine what characters it contains

spec/tags/1.9/ruby/core/string/chr_tags.txt

@@ -1,2 +1 @@
-fails:String#chr understands multi-byte characters
 fails:String#chr understands Strings that contain a mixture of character widths

spec/tags/1.9/ruby/core/string/codepoints_tags.txt

@@ -1,3 +1 @@
-fails:String#codepoints works for multibyte characters
-fails:String#codepoints returns the codepoint corresponding to the character's position in the String's encoding
 fails:String#codepoints round-trips to the original String using Integer#chr

spec/tags/1.9/ruby/core/string/each_char_tags.txt

@@ -1,4 +1 @@
 fails:String#each_char is unicode aware
-fails:String#each_char works with multibyte characters
-fails:String#each_char returns a different character if the String is transcoded
-fails:String#each_char uses the String's encoding to determine what characters it contains

spec/tags/1.9/ruby/core/string/each_codepoint_tags.txt

@@ -1,3 +1 @@
-fails:String#each_codepoint works for multibyte characters
-fails:String#each_codepoint returns the codepoint corresponding to the character's position in the String's encoding
 fails:String#each_codepoint round-trips to the original String using Integer#chr

spec/tags/1.9/ruby/core/string/encode_tags.txt

@@ -1,18 +1,13 @@
 fails:String#encode transcodes to the default internal encoding with no argument
-fails:String#encode transcodes self to the given encoding
 fails:String#encode raises UndefinedConversionError if the String contains characters invalid for the target     encoding
 fails:String#encode replaces invalid characters
-fails:String#encode replaces undefined characters
 fails:String#encode replaces xml characters
 fails:String#encode replaces xml characters and quotes the result
-fails:String#encode returns a copy of self when called with only a target encoding
 fails:String#encode returns self when called with only a target encoding
 fails:String#encode returns a String with the given encoding
 fails:String#encode! transcodes to the default internal encoding with no argument
-fails:String#encode! transcodes self to the given encoding
 fails:String#encode! raises UndefinedConversionError if the String contains characters invalid for the target     encoding
 fails:String#encode! replaces invalid characters
-fails:String#encode! replaces undefined characters
 fails:String#encode! replaces xml characters
 fails:String#encode! replaces xml characters and quotes the result
 fails:String#encode! tags the String with the given encoding

spec/tags/1.9/ruby/core/string/encoding_tags.txt

@@ -3,9 +3,7 @@ fails:String#encoding for US-ASCII Strings returns US-ASCII if self is US-ASCII
 fails:String#encoding for US-ASCII Strings returns US-ASCII if self is US-ASCII only, despite the default external encoding being different
 fails:String#encoding for US-ASCII Strings returns US-ASCII if self is US-ASCII only, despite the default internal and external encodings being different
 fails:String#encoding for US-ASCII Strings returns US-ASCII if self is US-ASCII only, despite the default encodings being different
-fails:String#encoding for Strings with \u escapes returns UTF-8
 fails:String#encoding for Strings with \u escapes returns US-ASCII if self is US-ASCII only
-fails:String#encoding for Strings with \u escapes returns UTF-8 if self isn't US-ASCII only
 fails:String#encoding for Strings with \u escapes is not affected by the default internal encoding
 fails:String#encoding for Strings with \u escapes is not affected by the default external encoding
 fails:String#encoding for Strings with \u escapes is not affected by both the default internal and external encoding being set at the same time

spec/tags/1.9/ruby/core/string/force_encoding_tags.txt

@@ -1,3 +1 @@
 fails:String#force_encoding tags the String with the given encoding
-fails:String#force_encoding does not care if self would be invalid in given encoding
-fails:String#force_encoding does not care if self is already tagged with the given encoding

spec/tags/1.9/ruby/core/string/valid_encoding_tags.txt

@@ -1,2 +1 @@
 fails:String#valid_encoding? returns true for all encodings self is valid in
-fails:String#valid_encoding? returns false if self is valid in one encoding, but invalid in the one it's tagged with

spec/tags/1.9/ruby/language/regexp/character_classes_tags.txt

@@ -1,91 +1,15 @@
 fails:Regexp with character classes matches Unicode letter characters with [[:alnum:]]
-fails:Regexp with character classes matches Unicode digits with [[:alnum:]]
 fails:Regexp with character classes matches Unicode marks with [[:alnum:]]
-fails:Regexp with character classes doesn't match Unicode control characters with [[:alnum:]]
-fails:Regexp with character classes doesn't match Unicode punctuation characters with [[:alnum:]]
 fails:Regexp with character classes matches Unicode letter characters with [[:alpha:]]
-fails:Regexp with character classes doesn't match Unicode digits with [[:alpha:]]
 fails:Regexp with character classes matches Unicode marks with [[:alpha:]]
-fails:Regexp with character classes doesn't match Unicode control characters with [[:alpha:]]
-fails:Regexp with character classes doesn't match Unicode punctuation characters with [[:alpha:]]
-fails:Regexp with character classes matches Unicode space characters with [[:blank:]]
-fails:Regexp with character classes matches Unicode control characters with [[:cntrl:]]
-fails:Regexp with character classes matches Unicode digits with [[:digit:]]
-fails:Regexp with character classes doesn't match Unicode marks with [[:digit:]]
-fails:Regexp with character classes doesn't match Unicode punctuation characters with [[:digit:]]
-fails:Regexp with character classes doesn't match Unicode control characters with [[:digit:]]
-fails:Regexp with character classes doesn't match Unicode format characters with [[:digit:]]
-fails:Regexp with character classes doesn't match Unicode private-use characters with [[:digit:]]
 fails:Regexp with character classes matches Unicode letter characters with [[:graph:]]
-fails:Regexp with character classes matches Unicode digits with [[:graph:]]
-fails:Regexp with character classes matches Unicode marks with [[:graph:]]
-fails:Regexp with character classes matches Unicode punctuation characters with [[:graph:]]
-fails:Regexp with character classes doesn't match Unicode control characters with [[:graph:]]
 fails:Regexp with character classes doesn't match Unicode format characters with [[:graph:]]
 fails:Regexp with character classes doesn't match Unicode private-use characters with [[:graph:]]
-fails:Regexp with character classes matches Unicode lowercase letter characters with [[:lower:]]
-fails:Regexp with character classes doesn't match Unicode uppercase letter characters with [[:lower:]]
-fails:Regexp with character classes doesn't match Unicode title-case characters with [[:lower:]]
-fails:Regexp with character classes doesn't match Unicode digits with [[:lower:]]
-fails:Regexp with character classes doesn't match Unicode marks with [[:lower:]]
-fails:Regexp with character classes doesn't match Unicode punctuation characters with [[:lower:]]
-fails:Regexp with character classes doesn't match Unicode control characters with [[:lower:]]
-fails:Regexp with character classes doesn't match Unicode format characters with [[:lower:]]
-fails:Regexp with character classes doesn't match Unicode private-use characters with [[:lower:]]
-fails:Regexp with character classes matches Unicode lowercase letter characters with [[:print:]]
-fails:Regexp with character classes matches Unicode uppercase letter characters with [[:print:]]
-fails:Regexp with character classes matches Unicode title-case characters with [[:print:]]
-fails:Regexp with character classes matches Unicode digits with [[:print:]]
-fails:Regexp with character classes matches Unicode marks with [[:print:]]
-fails:Regexp with character classes matches Unicode punctuation characters with [[:print:]]
-fails:Regexp with character classes doesn't match Unicode control characters with [[:print:]]
 fails:Regexp with character classes doesn't match Unicode format characters with [[:print:]]
 fails:Regexp with character classes doesn't match Unicode private-use characters with [[:print:]]
-fails:Regexp with character classes doesn't match Unicode lowercase letter characters with [[:punct:]]
-fails:Regexp with character classes doesn't match Unicode uppercase letter characters with [[:punct:]]
-fails:Regexp with character classes doesn't match Unicode title-case characters with [[:punct:]]
-fails:Regexp with character classes doesn't match Unicode digits with [[:punct:]]
-fails:Regexp with character classes doesn't match Unicode marks with [[:punct:]]
-fails:Regexp with character classes matches Unicode Pc characters with [[:punct:]]
-fails:Regexp with character classes matches Unicode Pd characters with [[:punct:]]
-fails:Regexp with character classes matches Unicode Ps characters with [[:punct:]]
-fails:Regexp with character classes matches Unicode Pe characters with [[:punct:]]
-fails:Regexp with character classes matches Unicode Pi characters with [[:punct:]]
-fails:Regexp with character classes matches Unicode Pf characters with [[:punct:]]
-fails:Regexp with character classes matches Unicode Po characters with [[:punct:]]
-fails:Regexp with character classes doesn't match Unicode format characters with [[:punct:]]
-fails:Regexp with character classes doesn't match Unicode private-use characters with [[:punct:]]
-fails:Regexp with character classes matches Unicode Zs characters with [[:space:]]
-fails:Regexp with character classes matches Unicode Zl characters with [[:space:]]
-fails:Regexp with character classes matches Unicode Zp characters with [[:space:]]
-fails:Regexp with character classes doesn't match Unicode lowercase characters with [[:upper:]]
-fails:Regexp with character classes matches Unicode uppercase characters with [[:upper:]]
-fails:Regexp with character classes doesn't match Unicode title-case characters with [[:upper:]]
-fails:Regexp with character classes doesn't match Unicode digits with [[:upper:]]
-fails:Regexp with character classes doesn't match Unicode marks with [[:upper:]]
-fails:Regexp with character classes doesn't match Unicode punctuation characters with [[:upper:]]
-fails:Regexp with character classes doesn't match Unicode private-use characters with [[:upper:]]
-fails:Regexp with character classes doesn't match Unicode digits [^0-9] with [[:xdigit:]]
-fails:Regexp with character classes doesn't match Unicode marks with [[:xdigit:]]
-fails:Regexp with character classes doesn't match Unicode punctuation characters with [[:xdigit:]]
-fails:Regexp with character classes doesn't match Unicode control characters with [[:xdigit:]]
-fails:Regexp with character classes doesn't match Unicode format characters with [[:xdigit:]]
-fails:Regexp with character classes doesn't match Unicode private-use characters with [[:xdigit:]]
-fails:Regexp with character classes matches Unicode lowercase characters with [[:word:]]
-fails:Regexp with character classes matches Unicode uppercase characters with [[:word:]]
-fails:Regexp with character classes matches Unicode title-case characters with [[:word:]]
-fails:Regexp with character classes matches Unicode decimal digits with [[:word:]]
-fails:Regexp with character classes matches Unicode marks with [[:word:]]
 fails:Regexp with character classes doesn't match Unicode Nl characters with [[:word:]]
 fails:Regexp with character classes doesn't match Unicode No characters with [[:word:]]
-fails:Regexp with character classes doesn't match Unicode punctuation characters with [[:word:]]
-fails:Regexp with character classes doesn't match Unicode control characters with [[:word:]]
-fails:Regexp with character classes doesn't match Unicode format characters with [[:word:]]
-fails:Regexp with character classes doesn't match Unicode private-use characters with [[:word:]]
 fails:Regexp with character classes doesn't matches Unicode marks with [[:alnum:]]
 fails:Regexp with character classes doesn't matches Unicode marks with [[:alpha:]]
-fails:Regexp with character classes match Unicode format characters with [[:graph:]]
-fails:Regexp with character classes match Unicode private-use characters with [[:graph:]]
-fails:Regexp with character classes match Unicode format characters with [[:print:]]
-fails:Regexp with character classes match Unicode private-use characters with [[:print:]]
-fails:Regexp with character classes match Unicode Nl characters with [[:word:]]
+fails:Regexp with character classes doesn't match Unicode format characters with [[:cntrl:]]
+fails:Regexp with character classes doesn't match Unicode private-use characters with [[:cntrl:]]