Skip to content

Commit

Permalink
refactor(parser): simplify byte_search macro (#2552)
Browse files Browse the repository at this point in the history 
This PR greatly simplifies the `byte_search!` macro.

Mainly removing `cold_branch()` from the "not enough bytes remaining for a batch" branch, which allows refactoring so that `handle_match` and `continue_if` don't need to be repeated twice.

Result for performance is inconsistent - a little better on some benchmarks, a little worse on others. But not by significant amounts either way. In my view, the benefit of making the macro simpler outweighs a small speed loss anyway.
  • Loading branch information
@overlookmotel
overlookmotel authored Mar 1, 2024
1 parent 25e03cb commit 34ecdd5
Showing 1 changed file with 32 additions and 54 deletions.
86 changes: 32 additions & 54 deletions crates/oxc_parser/src/lexer/search.rs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -479,9 +479,8 @@ macro_rules! byte_search {

let mut $pos = $start;
#[allow(unused_unsafe)] // Silence warnings if macro called in unsafe code
'outer: loop {
#[allow(clippy::redundant_else)]
if $pos.addr() <= $lexer.source.end_for_batch_search_addr() {
let $match_byte = 'outer: loop {
let $continue_byte = if $pos.addr() <= $lexer.source.end_for_batch_search_addr() {
// Search a batch of `SEARCH_BATCH_SIZE` bytes.
//
// `'inner: loop {}` is not a real loop - it always exits on first turn.
Expand All @@ -494,7 +493,7 @@ macro_rules! byte_search {
// `$pos.addr() <= lexer.source.end_for_batch_search_addr()` check above ensures
// there are at least `SEARCH_BATCH_SIZE` bytes remaining in `lexer.source`.
// So calls to `$pos.read()` and `$pos.add(1)` in this loop cannot go out of bounds.
let $match_byte = 'inner: loop {
'inner: loop {
for _i in 0..crate::lexer::search::SEARCH_BATCH_SIZE {
// SAFETY: `$pos` cannot go out of bounds in this loop (see above)
let byte = unsafe { $pos.read() };
Expand All @@ -509,57 +508,17 @@ macro_rules! byte_search {
}
// No match in batch - search next batch
continue 'outer;
};

// Found match. Check if should continue.
{
let $continue_byte = $match_byte;
if $should_continue {
// Not a match after all - continue searching.
// SAFETY: `pos` is not at end of source, so safe to advance 1 byte.
// See above about UTF-8 character boundaries invariant.
$pos = unsafe { $pos.add(1) };
continue;
}
}

// Advance `lexer.source`'s position up to `$pos`, consuming unmatched bytes.
// SAFETY: See above about UTF-8 character boundaries invariant.
$lexer.source.set_position($pos);

let $match_start = $start;
return $match_handler;
} else {
// Not enough bytes remaining to process as a batch.
// This branch marked `#[cold]` as should be very uncommon in normal-length JS files.
// Very short JS files will be penalized, but they'll be very fast to parse anyway.
// TODO: Could extend very short files with padding during parser initialization
// to remove that problem.
return crate::lexer::cold_branch(|| {
let end_addr = $lexer.source.end_addr();
// Not enough bytes remaining for a batch. Process byte-by-byte.
// Same as above, `'inner: loop {}` is not a real loop here - always exits on first turn.
let end_addr = $lexer.source.end_addr();
'inner: loop {
while $pos.addr() < end_addr {
// SAFETY: `pos` is not at end of source, so safe to read a byte
let $match_byte = unsafe { $pos.read() };
if $table.matches($match_byte) {
// Found match.
// Check if should continue.
{
let $continue_byte = $match_byte;
if $should_continue {
// Not a match after all - continue searching.
// SAFETY: `pos` is not at end of source, so safe to advance 1 byte.
// See above about UTF-8 character boundaries invariant.
$pos = unsafe { $pos.add(1) };
continue;
}
}

// Advance `lexer.source`'s position up to `pos`, consuming unmatched bytes.
// SAFETY: See above about UTF-8 character boundaries invariant.
$lexer.source.set_position($pos);

let $match_start = $start;
return $match_handler;
let byte = unsafe { $pos.read() };
if $table.matches(byte) {
break 'inner byte;
}

// No match - continue searching
Expand All @@ -573,10 +532,29 @@ macro_rules! byte_search {
$lexer.source.set_position($pos);

let $eof_start = $start;
$eof_handler
});
return $eof_handler;
}
};

// Found match. Check if should continue.
if $should_continue {
// Not a match after all - continue searching.
// SAFETY: `pos` is not at end of source, so safe to advance 1 byte.
// See above about UTF-8 character boundaries invariant.
$pos = unsafe { $pos.add(1) };
continue;
}
}

// Match confirmed
break $continue_byte;
};

// Advance `lexer.source`'s position up to `$pos`, consuming unmatched bytes.
// SAFETY: See above about UTF-8 character boundaries invariant.
$lexer.source.set_position($pos);

let $match_start = $start;
return $match_handler;
}};
}
pub(crate) use byte_search;

0 comments on commit 34ecdd5

Please sign in to comment.