1
0
Fork 0
mirror of https://github.com/ruby/ruby.git synced 2022-11-09 12:17:21 -05:00

Cheaply derive code range for String#b return value

The result of String#b is a string with an ASCII_8BIT/BINARY encoding. That encoding is ASCII-compatible and has no byte sequences that are invalid for the encoding. If we know the receiver's code range, we can derive the resulting string's code range without needing to perform a full code range scan.
This commit is contained in:
Kevin Menard 2022-07-25 21:04:03 -04:00 committed by Jean Boussier
parent 9e6d07f346
commit 9a8f6e392f
Notes: git 2022-07-26 16:04:11 +09:00

View file

@ -10779,7 +10779,23 @@ rb_str_b(VALUE str)
str2 = str_alloc_embed(rb_cString, RSTRING_EMBED_LEN(str) + TERM_LEN(str));
}
str_replace_shared_without_enc(str2, str);
ENC_CODERANGE_CLEAR(str2);
// BINARY strings can never be broken; they're either 7-bit ASCII or VALID.
// If we know the receiver's code range then we know the result's code range.
int cr = ENC_CODERANGE(str);
switch (cr) {
case ENC_CODERANGE_7BIT:
ENC_CODERANGE_SET(str2, ENC_CODERANGE_7BIT);
break;
case ENC_CODERANGE_BROKEN:
case ENC_CODERANGE_VALID:
ENC_CODERANGE_SET(str2, ENC_CODERANGE_VALID);
break;
default:
ENC_CODERANGE_CLEAR(str2);
break;
}
return str2;
}