Skip to content

Drop offsets when tokenizing with RegularParser #111

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
thunderer merged 1 commit into from
Dec 20, 2024
Merged

Drop offsets when tokenizing with RegularParser #111

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
Drop offsets when tokenizing with RegularParser
  • Loading branch information
@funkjedi @thunderer
funkjedi authored and thunderer committed Dec 20, 2024
commit 08c2e6bbf982981fbfc392078deff453f178ed3c
16 changes: 8 additions & 8 deletions src/Parser/RegularParser.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -342,7 +342,7 @@ private function match($type, $ws)
*/
private function tokenize($text)
{
$count = preg_match_all($this->lexerRegex, $text, $matches, PREG_SET_ORDER | PREG_OFFSET_CAPTURE);
$count = preg_match_all($this->lexerRegex, $text, $matches, PREG_SET_ORDER);
if(false === $count || preg_last_error() !== PREG_NO_ERROR) {
throw new \RuntimeException(sprintf('PCRE failure `%s`.', preg_last_error()));
}
Expand All @@ -352,13 +352,13 @@ private function tokenize($text)

foreach($matches as $match) {
switch(true) {
case -1 !== $match['string'][1]: { $token = $match['string'][0]; $type = self::TOKEN_STRING; break; }
case -1 !== $match['ws'][1]: { $token = $match['ws'][0]; $type = self::TOKEN_WS; break; }
case -1 !== $match['marker'][1]: { $token = $match['marker'][0]; $type = self::TOKEN_MARKER; break; }
case -1 !== $match['delimiter'][1]: { $token = $match['delimiter'][0]; $type = self::TOKEN_DELIMITER; break; }
case -1 !== $match['separator'][1]: { $token = $match['separator'][0]; $type = self::TOKEN_SEPARATOR; break; }
case -1 !== $match['open'][1]: { $token = $match['open'][0]; $type = self::TOKEN_OPEN; break; }
case -1 !== $match['close'][1]: { $token = $match['close'][0]; $type = self::TOKEN_CLOSE; break; }
case array_key_exists('close', $match): { $token = $match['close']; $type = self::TOKEN_CLOSE; break; }
case array_key_exists('open', $match): { $token = $match['open']; $type = self::TOKEN_OPEN; break; }
case array_key_exists('separator', $match): { $token = $match['separator']; $type = self::TOKEN_SEPARATOR; break; }
case array_key_exists('delimiter', $match): { $token = $match['delimiter']; $type = self::TOKEN_DELIMITER; break; }
case array_key_exists('marker', $match): { $token = $match['marker']; $type = self::TOKEN_MARKER; break; }
case array_key_exists('ws', $match): { $token = $match['ws']; $type = self::TOKEN_WS; break; }
case array_key_exists('string', $match): { $token = $match['string']; $type = self::TOKEN_STRING; break; }
default: { throw new \RuntimeException('Invalid token.'); }
}
$tokens[] = array($type, $token, $position);
Expand Down
Loading