diff options
| author | Andrew Dolgov <fox@fakecake.org> | 2026-05-25 14:12:01 +0300 |
|---|---|---|
| committer | Andrew Dolgov <fox@fakecake.org> | 2026-05-25 14:12:01 +0300 |
| commit | 9600be1703ba3083c38386930fa940938394f53e (patch) | |
| tree | a8fcbc476914881915eab236ee99f88459dfb09b /vendor/phpstan/phpdoc-parser/src/Lexer/Lexer.php | |
| parent | cae514dddfc59f533a93a47afc283371d5949843 (diff) | |
| download | the-epube-9600be1703ba3083c38386930fa940938394f53e.tar.gz the-epube-9600be1703ba3083c38386930fa940938394f53e.tar.xz | |
add phpunit
Diffstat (limited to 'vendor/phpstan/phpdoc-parser/src/Lexer/Lexer.php')
| -rw-r--r-- | vendor/phpstan/phpdoc-parser/src/Lexer/Lexer.php | 197 |
1 files changed, 197 insertions, 0 deletions
diff --git a/vendor/phpstan/phpdoc-parser/src/Lexer/Lexer.php b/vendor/phpstan/phpdoc-parser/src/Lexer/Lexer.php new file mode 100644 index 0000000..e2e0e57 --- /dev/null +++ b/vendor/phpstan/phpdoc-parser/src/Lexer/Lexer.php @@ -0,0 +1,197 @@ +<?php declare(strict_types = 1); + +namespace PHPStan\PhpDocParser\Lexer; + +use PHPStan\PhpDocParser\ParserConfig; +use function implode; +use function preg_match_all; +use const PREG_SET_ORDER; + +/** + * Implementation based on Nette Tokenizer (New BSD License; https://github.com/nette/tokenizer) + */ +class Lexer +{ + + public const TOKEN_REFERENCE = 0; + public const TOKEN_UNION = 1; + public const TOKEN_INTERSECTION = 2; + public const TOKEN_NULLABLE = 3; + public const TOKEN_OPEN_PARENTHESES = 4; + public const TOKEN_CLOSE_PARENTHESES = 5; + public const TOKEN_OPEN_ANGLE_BRACKET = 6; + public const TOKEN_CLOSE_ANGLE_BRACKET = 7; + public const TOKEN_OPEN_SQUARE_BRACKET = 8; + public const TOKEN_CLOSE_SQUARE_BRACKET = 9; + public const TOKEN_COMMA = 10; + public const TOKEN_VARIADIC = 11; + public const TOKEN_DOUBLE_COLON = 12; + public const TOKEN_DOUBLE_ARROW = 13; + public const TOKEN_EQUAL = 14; + public const TOKEN_OPEN_PHPDOC = 15; + public const TOKEN_CLOSE_PHPDOC = 16; + public const TOKEN_PHPDOC_TAG = 17; + public const TOKEN_DOCTRINE_TAG = 18; + public const TOKEN_FLOAT = 19; + public const TOKEN_INTEGER = 20; + public const TOKEN_SINGLE_QUOTED_STRING = 21; + public const TOKEN_DOUBLE_QUOTED_STRING = 22; + public const TOKEN_DOCTRINE_ANNOTATION_STRING = 23; + public const TOKEN_IDENTIFIER = 24; + public const TOKEN_THIS_VARIABLE = 25; + public const TOKEN_VARIABLE = 26; + public const TOKEN_HORIZONTAL_WS = 27; + public const TOKEN_PHPDOC_EOL = 28; + public const TOKEN_OTHER = 29; + public const TOKEN_END = 30; + public const TOKEN_COLON = 31; + public const TOKEN_WILDCARD = 32; + public const TOKEN_OPEN_CURLY_BRACKET = 33; + public const TOKEN_CLOSE_CURLY_BRACKET = 34; + public const TOKEN_NEGATED = 35; + public const TOKEN_ARROW = 36; + + public const TOKEN_COMMENT = 37; + + public const TOKEN_LABELS = [ + self::TOKEN_REFERENCE => '\'&\'', + self::TOKEN_UNION => '\'|\'', + self::TOKEN_INTERSECTION => '\'&\'', + self::TOKEN_NULLABLE => '\'?\'', + self::TOKEN_NEGATED => '\'!\'', + self::TOKEN_OPEN_PARENTHESES => '\'(\'', + self::TOKEN_CLOSE_PARENTHESES => '\')\'', + self::TOKEN_OPEN_ANGLE_BRACKET => '\'<\'', + self::TOKEN_CLOSE_ANGLE_BRACKET => '\'>\'', + self::TOKEN_OPEN_SQUARE_BRACKET => '\'[\'', + self::TOKEN_CLOSE_SQUARE_BRACKET => '\']\'', + self::TOKEN_OPEN_CURLY_BRACKET => '\'{\'', + self::TOKEN_CLOSE_CURLY_BRACKET => '\'}\'', + self::TOKEN_COMMA => '\',\'', + self::TOKEN_COMMENT => '\'//\'', + self::TOKEN_COLON => '\':\'', + self::TOKEN_VARIADIC => '\'...\'', + self::TOKEN_DOUBLE_COLON => '\'::\'', + self::TOKEN_DOUBLE_ARROW => '\'=>\'', + self::TOKEN_ARROW => '\'->\'', + self::TOKEN_EQUAL => '\'=\'', + self::TOKEN_OPEN_PHPDOC => '\'/**\'', + self::TOKEN_CLOSE_PHPDOC => '\'*/\'', + self::TOKEN_PHPDOC_TAG => 'TOKEN_PHPDOC_TAG', + self::TOKEN_DOCTRINE_TAG => 'TOKEN_DOCTRINE_TAG', + self::TOKEN_PHPDOC_EOL => 'TOKEN_PHPDOC_EOL', + self::TOKEN_FLOAT => 'TOKEN_FLOAT', + self::TOKEN_INTEGER => 'TOKEN_INTEGER', + self::TOKEN_SINGLE_QUOTED_STRING => 'TOKEN_SINGLE_QUOTED_STRING', + self::TOKEN_DOUBLE_QUOTED_STRING => 'TOKEN_DOUBLE_QUOTED_STRING', + self::TOKEN_DOCTRINE_ANNOTATION_STRING => 'TOKEN_DOCTRINE_ANNOTATION_STRING', + self::TOKEN_IDENTIFIER => 'type', + self::TOKEN_THIS_VARIABLE => '\'$this\'', + self::TOKEN_VARIABLE => 'variable', + self::TOKEN_HORIZONTAL_WS => 'TOKEN_HORIZONTAL_WS', + self::TOKEN_OTHER => 'TOKEN_OTHER', + self::TOKEN_END => 'TOKEN_END', + self::TOKEN_WILDCARD => '*', + ]; + + public const VALUE_OFFSET = 0; + public const TYPE_OFFSET = 1; + public const LINE_OFFSET = 2; + + private ParserConfig $config; // @phpstan-ignore property.onlyWritten + + private ?string $regexp = null; + + public function __construct(ParserConfig $config) + { + $this->config = $config; + } + + /** + * @return list<array{string, int, int}> + */ + public function tokenize(string $s): array + { + if ($this->regexp === null) { + $this->regexp = $this->generateRegexp(); + } + + preg_match_all($this->regexp, $s, $matches, PREG_SET_ORDER); + + $tokens = []; + $line = 1; + foreach ($matches as $match) { + $type = (int) $match['MARK']; + $tokens[] = [$match[0], $type, $line]; + if ($type !== self::TOKEN_PHPDOC_EOL) { + continue; + } + + $line++; + } + + $tokens[] = ['', self::TOKEN_END, $line]; + + return $tokens; + } + + private function generateRegexp(): string + { + $patterns = [ + self::TOKEN_HORIZONTAL_WS => '[\\x09\\x20]++', + + self::TOKEN_IDENTIFIER => '(?:[\\\\]?+[a-z_\\x80-\\xFF][0-9a-z_\\x80-\\xFF-]*+)++', + self::TOKEN_THIS_VARIABLE => '\\$this(?![0-9a-z_\\x80-\\xFF])', + self::TOKEN_VARIABLE => '\\$[a-z_\\x80-\\xFF][0-9a-z_\\x80-\\xFF]*+', + + // '&' followed by TOKEN_VARIADIC, TOKEN_VARIABLE, TOKEN_EQUAL, TOKEN_EQUAL or TOKEN_CLOSE_PARENTHESES + self::TOKEN_REFERENCE => '&(?=\\s*+(?:[.,=)]|(?:\\$(?!this(?![0-9a-z_\\x80-\\xFF])))))', + self::TOKEN_UNION => '\\|', + self::TOKEN_INTERSECTION => '&', + self::TOKEN_NULLABLE => '\\?', + self::TOKEN_NEGATED => '!', + + self::TOKEN_OPEN_PARENTHESES => '\\(', + self::TOKEN_CLOSE_PARENTHESES => '\\)', + self::TOKEN_OPEN_ANGLE_BRACKET => '<', + self::TOKEN_CLOSE_ANGLE_BRACKET => '>', + self::TOKEN_OPEN_SQUARE_BRACKET => '\\[', + self::TOKEN_CLOSE_SQUARE_BRACKET => '\\]', + self::TOKEN_OPEN_CURLY_BRACKET => '\\{', + self::TOKEN_CLOSE_CURLY_BRACKET => '\\}', + + self::TOKEN_COMMA => ',', + self::TOKEN_COMMENT => '\/\/[^\\r\\n]*(?=\n|\r|\*/)', + self::TOKEN_VARIADIC => '\\.\\.\\.', + self::TOKEN_DOUBLE_COLON => '::', + self::TOKEN_DOUBLE_ARROW => '=>', + self::TOKEN_ARROW => '->', + self::TOKEN_EQUAL => '=', + self::TOKEN_COLON => ':', + + self::TOKEN_OPEN_PHPDOC => '/\\*\\*(?=\\s)\\x20?+', + self::TOKEN_CLOSE_PHPDOC => '\\*/', + self::TOKEN_PHPDOC_TAG => '@(?:[a-z][a-z0-9-\\\\]+:)?[a-z][a-z0-9-\\\\]*+', + self::TOKEN_DOCTRINE_TAG => '@[a-z_\\\\][a-z0-9_\:\\\\]*[a-z_][a-z0-9_]*', + self::TOKEN_PHPDOC_EOL => '\\r?+\\n[\\x09\\x20]*+(?:\\*(?!/)\\x20?+)?', + + self::TOKEN_FLOAT => '[+\-]?(?:(?:[0-9]++(_[0-9]++)*\\.[0-9]*+(_[0-9]++)*(?:e[+\-]?[0-9]++(_[0-9]++)*)?)|(?:[0-9]*+(_[0-9]++)*\\.[0-9]++(_[0-9]++)*(?:e[+\-]?[0-9]++(_[0-9]++)*)?)|(?:[0-9]++(_[0-9]++)*e[+\-]?[0-9]++(_[0-9]++)*))', + self::TOKEN_INTEGER => '[+\-]?(?:(?:0b[0-1]++(_[0-1]++)*)|(?:0o[0-7]++(_[0-7]++)*)|(?:0x[0-9a-f]++(_[0-9a-f]++)*)|(?:[0-9]++(_[0-9]++)*))', + self::TOKEN_SINGLE_QUOTED_STRING => '\'(?:\\\\[^\\r\\n]|[^\'\\r\\n\\\\])*+\'', + self::TOKEN_DOUBLE_QUOTED_STRING => '"(?:\\\\[^\\r\\n]|[^"\\r\\n\\\\])*+"', + self::TOKEN_DOCTRINE_ANNOTATION_STRING => '"(?:""|[^"])*+"', + + self::TOKEN_WILDCARD => '\\*', + + // anything but TOKEN_CLOSE_PHPDOC or TOKEN_HORIZONTAL_WS or TOKEN_EOL + self::TOKEN_OTHER => '(?:(?!\\*/)[^\\s])++', + ]; + + foreach ($patterns as $type => &$pattern) { + $pattern = '(?:' . $pattern . ')(*MARK:' . $type . ')'; + } + + return '~' . implode('|', $patterns) . '~Asi'; + } + +} |
