rust/ripgrep
1
0
Fork 0
mirror of https://github.com/BurntSushi/ripgrep.git synced 2024-12-07 11:13:17 +02:00
Code Issues Releases Activity

globset: optimize character escaping

Browse Source 
Rewrites the char_to_escaped_literal and bytes_to_escaped_literal
functions in a way that minimizes heap allocations. After this, the
resulting string is the only allocation remaining.

I believe when this code was originally written, the routines available
to avoid heap allocations didn't exist.

I'm skeptical that this matters in the grand scheme of things, but I
think this is still worth doing for "good sense" reasons.

PR #2833
This commit is contained in:
Tobias Decking 2024-06-05 15:56:00 +02:00 committed by GitHub
parent dec0dc3196
commit c9ebcbd8ab
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 8 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
crates/globset/src/glob.rs
View File

@ -1,3 +1,4 @@
use std::fmt::Write;
use std::path::{is_separator, Path}; use std::path::{is_separator, Path};
use regex_automata::meta::Regex; use regex_automata::meta::Regex;
@ -732,7 +733,9 @@ impl Tokens {
/// Convert a Unicode scalar value to an escaped string suitable for use as /// Convert a Unicode scalar value to an escaped string suitable for use as
/// a literal in a non-Unicode regex. /// a literal in a non-Unicode regex.
fn char_to_escaped_literal(c: char) -> String { fn char_to_escaped_literal(c: char) -> String {
bytes_to_escaped_literal(&c.to_string().into_bytes()) let mut buf = [0; 4];
let bytes = c.encode_utf8(&mut buf).as_bytes();
bytes_to_escaped_literal(bytes)
} }
/// Converts an arbitrary sequence of bytes to a UTF-8 string. All non-ASCII /// Converts an arbitrary sequence of bytes to a UTF-8 string. All non-ASCII
@ -741,11 +744,12 @@ fn bytes_to_escaped_literal(bs: &[u8]) -> String {
let mut s = String::with_capacity(bs.len()); let mut s = String::with_capacity(bs.len());
for &b in bs { for &b in bs {
if b <= 0x7F { if b <= 0x7F {
s.push_str(&regex_syntax::escape( regex_syntax::escape_into(
char::from(b).encode_utf8(&mut [0; 4]), char::from(b).encode_utf8(&mut [0; 4]),
)); &mut s,
);
} else { } else {
s.push_str(&format!("\\x{:02x}", b)); write!(&mut s, "\\x{:02x}", b).unwrap();
} }
} }
s s