Skip to content

perf(view): improve lexer performance #2216

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
brendt merged 2 commits into from
Jul 17, 2026
+55 −23
Merged

perf(view): improve lexer performance #2216

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ac85244
wip
brendt Jul 16, 2026
904e9df
wip
brendt Jul 16, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
78 changes: 55 additions & 23 deletions packages/view/src/Parser/TempestViewLexer.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,17 +24,17 @@ public function lex(): TokenCollection
$tokens = [];

while ($this->current !== null) {
if ($this->comesNext('<?xml')) {
if ($this->comesNext('<?xml', 5)) {
$tokens[] = $this->lexXml();
} elseif ($this->comesNext('<?')) {
} elseif ($this->comesNext('<?', 2)) {
$tokens[] = $this->lexPhp();
} elseif ($this->comesNext('<!--')) {
} elseif ($this->comesNext('<!--', 4)) {
$tokens[] = $this->lexComment();
} elseif ($this->comesNext('<!doctype') || $this->comesNext('<!DOCTYPE')) {
} elseif ($this->comesNext('<!doctype', 9) || $this->comesNext('<!DOCTYPE', 9)) {
$tokens[] = $this->lexDocType();
} elseif ($this->comesNext('<![CDATA')) {
} elseif ($this->comesNext('<![CDATA', 8)) {
$tokens = [...$tokens, ...$this->lexCharacterData()];
} elseif ($this->comesNext('<')) {
} elseif ($this->comesNext('<', 1)) {
$tokens = [...$tokens, ...$this->lexTag()];
} elseif (str_contains(self::WHITESPACE, $this->current)) {
$tokens[] = $this->lexWhitespace();
Expand All @@ -46,13 +46,23 @@ public function lex(): TokenCollection
return new TokenCollection($tokens);
}

private function comesNext(string $search): bool
private function comesNext(string $search, ?int $length = null): bool
{
return $this->seek(strlen($search)) === $search;
$length ??= strlen($search);

if ($length === 1) {
return ($this->html[$this->position] ?? null) === $search;
}

return substr_compare($this->html, $search, $this->position, $length) === 0;
}

private function seek(int $length = 1, int $offset = 0): ?string
{
if ($length === 1) {
return $this->html[$this->position + $offset] ?? null;
}

$seek = substr($this->html, $this->position + $offset, $length);

if ($seek === '') {
Expand All @@ -62,18 +72,28 @@ private function seek(int $length = 1, int $offset = 0): ?string
return $seek;
}

private function seekIgnoringWhitespace(int $length = 1): ?string
private function seekIgnoringWhitespace(): ?string
{
$offset = strspn($this->html, self::WHITESPACE, $this->position);

return $this->seek(length: $length, offset: $offset);
return $this->seek(
// Whitespace offset
offset: strspn($this->html, self::WHITESPACE, $this->position),
);
}

private function consume(int $length = 1): string
{
if ($length === 0) {
return '';
}

if ($length === 1) {
$char = $this->html[$this->position++] ?? null;
$this->current = $this->html[$this->position] ?? null;
return $char ?? '';
}

$buffer = substr($this->html, $this->position, $length);
$this->position += $length;
$this->line += substr_count($buffer, "\n");
$this->current = $this->html[$this->position] ?? null;

return $buffer;
Expand Down Expand Up @@ -124,8 +144,15 @@ private function lexTag(): array
} else {
$tokens[] = $this->makeToken($tag, TokenType::OPEN_TAG_START, $tagLine);

while ($this->seek() !== null && $this->seekIgnoringWhitespace() !== '>' && $this->seekIgnoringWhitespace() !== '/') {
if ($this->seekIgnoringWhitespace(2) === '<?') {
while ($this->current !== null) {
$whitespaceOffset = strspn($this->html, self::WHITESPACE, $this->position);
$next = $this->seek(offset: $whitespaceOffset);

if ($next === '>' || $next === '/') {
break;
}

if ($next === '<' && $this->seek(length: 2, offset: $whitespaceOffset) === '<?') {
$tokens[] = $this->lexPhp();
continue;
}
Expand All @@ -135,7 +162,7 @@ private function lexTag(): array

$attributeName .= $this->consumeUntil(self::WHITESPACE . '=/>');

$hasValue = $this->seek() === '=';
$hasValue = $this->comesNext('=', 1);

if ($hasValue) {
$attributeName .= $this->consume();
Expand All @@ -148,7 +175,7 @@ private function lexTag(): array
);

if ($hasValue) {
$quote = $this->seek() === "'"
$quote = $this->comesNext("'", 1)
? "'"
: '"';

Expand All @@ -164,15 +191,20 @@ private function lexTag(): array
}
}

if ($this->seekIgnoringWhitespace() === '>') {
$next = $this->seek(
// Whitespace offset
offset: strspn($this->html, self::WHITESPACE, $this->position),
);

if ($next === '>') {
$openTagEndLine = $this->line;

$tokens[] = $this->makeToken(
content: $this->consumeIncluding('>'),
type: TokenType::OPEN_TAG_END,
line: $openTagEndLine,
);
} elseif ($this->seekIgnoringWhitespace() === '/') {
} elseif ($next === '/') {
$selfClosingTagEndLine = $this->line;

$tokens[] = $this->makeToken(
Expand All @@ -191,7 +223,7 @@ private function lexXml(): Token
$line = $this->line;
$buffer = '';

while ($this->seek(2) !== '?>' && $this->current !== null) {
while (! $this->comesNext('?>', 2) && $this->current !== null) {
$buffer .= $this->consume();
}

Expand All @@ -205,7 +237,7 @@ private function lexPhp(): Token
$line = $this->line;
$buffer = '';

while ($this->seek(2) !== '?>' && $this->current !== null) {
while (! $this->comesNext('?>', 2) && $this->current !== null) {
$buffer .= $this->consume();
}

Expand All @@ -227,7 +259,7 @@ private function lexComment(): Token
$line = $this->line;
$buffer = '';

while ($this->seek(3) !== '-->' && $this->current !== null) {
while (! $this->comesNext('-->', 3) && $this->current !== null) {
$buffer .= $this->consume();
}

Expand Down Expand Up @@ -264,7 +296,7 @@ private function lexCharacterData(): array

$contentLine = $this->line;

while ($this->seek(3) !== ']]>' && $this->current !== null) {
while (! $this->comesNext(']]>', 3) && $this->current !== null) {
$buffer .= $this->consume();
}

Expand Down
Loading