mirror of
https://github.com/ruby/ruby.git
synced 2025-08-15 05:29:10 +02:00

If the provided Hash doesn't have a default proc, we know for
sure that we'll never call into user provided code, hence the
string we allocate to access the Hash can't possibly escape.
So we don't actually have to allocate it, we can use a fake_str,
AKA a stack allocated string.
```
compare-ruby: ruby 3.5.0dev (2025-02-10T13:47:44Z master 3fb455adab
) +PRISM [arm64-darwin23]
built-ruby: ruby 3.5.0dev (2025-02-10T17:09:52Z opt-gsub-alloc ea5c28958f) +PRISM [arm64-darwin23]
warming up....
| |compare-ruby|built-ruby|
|:----------------|-----------:|---------:|
|escape | 3.374k| 3.722k|
| | -| 1.10x|
|escape_bin | 5.469k| 6.587k|
| | -| 1.20x|
|escape_utf8 | 3.465k| 3.734k|
| | -| 1.08x|
|escape_utf8_bin | 5.752k| 7.283k|
| | -| 1.27x|
```
43 lines
1 KiB
YAML
43 lines
1 KiB
YAML
prelude: |
|
|
# frozen_string_literal: true
|
|
STR = ((("a" * 31) + "<") * 1000).freeze
|
|
STR_UNICODE = ((("a" * 30) + "\u2028") * 1000).freeze
|
|
ESCAPED_CHARS_BINARY = {
|
|
"\u2028".b => '\u2028'.b,
|
|
"\u2029".b => '\u2029'.b,
|
|
">".b => '\u003e'.b.freeze,
|
|
"<".b => '\u003c'.b.freeze,
|
|
"&".b => '\u0026'.b.freeze,
|
|
}
|
|
BINARY_PATTERN = Regexp.union(ESCAPED_CHARS_BINARY.keys)
|
|
|
|
ESCAPED_CHARS = {
|
|
"\u2028" => '\u2028',
|
|
"\u2029" => '\u2029',
|
|
">" => '\u003e',
|
|
"<" => '\u003c',
|
|
"&" => '\u0026',
|
|
}
|
|
ESCAPE_PATTERN = Regexp.union(ESCAPED_CHARS.keys)
|
|
|
|
|
|
benchmark:
|
|
escape: |
|
|
str = STR.dup
|
|
str.gsub!(ESCAPE_PATTERN, ESCAPED_CHARS)
|
|
str
|
|
|
|
escape_bin: |
|
|
str = STR.b
|
|
str.gsub!(BINARY_PATTERN, ESCAPED_CHARS_BINARY)
|
|
str.force_encoding(Encoding::UTF_8)
|
|
|
|
escape_utf8: |
|
|
str = STR_UNICODE.dup
|
|
str.gsub!(ESCAPE_PATTERN, ESCAPED_CHARS)
|
|
str
|
|
|
|
escape_utf8_bin: |
|
|
str = STR_UNICODE.b
|
|
str.gsub!(BINARY_PATTERN, ESCAPED_CHARS_BINARY)
|
|
str.force_encoding(Encoding::UTF_8)
|