Repository: doctrine/lexer Branch: 3.0.x Commit: c2db835430a2 Files: 30 Total size: 47.6 KB Directory structure: gitextract_ls_k7a7l/ ├── .doctrine-project.json ├── .gitattributes ├── .github/ │ ├── FUNDING.yml │ ├── dependabot.yml │ └── workflows/ │ ├── coding-standards.yml │ ├── composer-lint.yml │ ├── continuous-integration.yml │ ├── release-on-milestone-closed.yml │ ├── static-analysis.yml │ └── website-schema.yml ├── .gitignore ├── LICENSE ├── README.md ├── UPGRADE.md ├── composer.json ├── docs/ │ └── en/ │ ├── dql-parser.rst │ ├── index.rst │ ├── sidebar.rst │ └── simple-parser-example.rst ├── phpcs.xml.dist ├── phpstan.neon.dist ├── phpunit.xml.dist ├── src/ │ ├── AbstractLexer.php │ └── Token.php └── tests/ ├── AbstractLexerTest.php ├── ConcreteLexer.php ├── EnumLexer.php ├── MutableLexer.php ├── TokenTest.php └── TokenType.php ================================================ FILE CONTENTS ================================================ ================================================ FILE: .doctrine-project.json ================================================ { "active": true, "name": "Lexer", "slug": "lexer", "docsSlug": "doctrine-lexer", "versions": [ { "name": "3.1", "branchName": "3.1.x", "slug": "latest", "upcoming": true }, { "name": "3.0", "branchName": "3.0.x", "slug": "3.1", "current": true }, { "name": "2.1", "branchName": "2.1.x", "slug": "2.1", "maintained": false }, { "name": "2.0", "branchName": "2.0.x", "slug": "2.0", "maintained": false }, { "name": "1.2", "branchName": "1.2.x", "slug": "1.2", "maintained": false }, { "name": "1.1", "branchName": "1.1", "slug": "1.1", "maintained": false }, { "name": "1.0", "branchName": "1.0", "slug": "1.0", "maintained": false } ] } ================================================ FILE: .gitattributes ================================================ # Auto-detect text files, ensure they use LF. * text=auto eol=lf # Exclude non-essential files from dist /.github export-ignore /docs export-ignore /tests export-ignore /.doctrine-project.json export-ignore /.gitattributes export-ignore /.gitignore export-ignore /phpcs.xml.dist export-ignore /phpstan.neon.dist export-ignore /phpunit.xml.dist export-ignore ================================================ FILE: .github/FUNDING.yml ================================================ patreon: phpdoctrine tidelift: packagist/doctrine%2Flexer custom: https://www.doctrine-project.org/sponsorship.html ================================================ FILE: .github/dependabot.yml ================================================ version: 2 updates: - package-ecosystem: "github-actions" directory: "/" schedule: interval: "weekly" labels: - "CI" ================================================ FILE: .github/workflows/coding-standards.yml ================================================ name: "Coding Standards" on: pull_request: branches: - "*.x" paths: - .github/workflows/coding-standards.yml - composer.* - src/** - phpcs.xml.dist - tests/** push: branches: - "*.x" paths: - .github/workflows/coding-standards.yml - composer.* - src/** - phpcs.xml.dist - tests/** jobs: coding-standards: name: "Coding Standards" uses: "doctrine/.github/.github/workflows/coding-standards.yml@14.0.0" ================================================ FILE: .github/workflows/composer-lint.yml ================================================ name: "Composer Lint" on: pull_request: branches: - "*.x" paths: - .github/workflows/composer-lint.yml - composer.json push: branches: - "*.x" paths: - .github/workflows/composer-lint.yml - composer.json jobs: composer-lint: name: "Composer Lint" uses: "doctrine/.github/.github/workflows/composer-lint.yml@13.1.0" ================================================ FILE: .github/workflows/continuous-integration.yml ================================================ name: "Continuous Integration" on: pull_request: branches: - "*.x" paths: - .github/workflows/continuous-integration.yml - composer.* - src/** - phpunit.xml.dist - tests/** push: branches: - "*.x" paths: - .github/workflows/continuous-integration.yml - composer.* - src/** - phpunit.xml.dist - tests/** jobs: phpunit: name: "PHPUnit" uses: "doctrine/.github/.github/workflows/continuous-integration.yml@14.0.0" with: php-versions: '["8.1", "8.2", "8.3", "8.4", "8.5"]' secrets: CODECOV_TOKEN: "${{ secrets.CODECOV_TOKEN }}" ================================================ FILE: .github/workflows/release-on-milestone-closed.yml ================================================ name: "Automatic Releases" on: milestone: types: - "closed" jobs: release: name: "Git tag, release & create merge-up PR" uses: "doctrine/.github/.github/workflows/release-on-milestone-closed.yml@14.0.0" secrets: GIT_AUTHOR_EMAIL: ${{ secrets.GIT_AUTHOR_EMAIL }} GIT_AUTHOR_NAME: ${{ secrets.GIT_AUTHOR_NAME }} ORGANIZATION_ADMIN_TOKEN: ${{ secrets.ORGANIZATION_ADMIN_TOKEN }} SIGNING_SECRET_KEY: ${{ secrets.SIGNING_SECRET_KEY }} ================================================ FILE: .github/workflows/static-analysis.yml ================================================ name: "Static Analysis" on: pull_request: branches: - "*.x" paths: - .github/workflows/static-analysis.yml - composer.* - src/** - phpstan* - tests/** push: branches: - "*.x" paths: - .github/workflows/static-analysis.yml - composer.* - src/** - phpstan* - tests/** jobs: static-analysis: name: "Static Analysis" uses: "doctrine/.github/.github/workflows/phpstan.yml@14.0.0" ================================================ FILE: .github/workflows/website-schema.yml ================================================ name: "Website config validation" on: pull_request: branches: - "*.x" paths: - ".doctrine-project.json" - ".github/workflows/website-schema.yml" push: branches: - "*.x" paths: - ".doctrine-project.json" - ".github/workflows/website-schema.yml" jobs: json-validate: name: "Validate JSON schema" uses: "doctrine/.github/.github/workflows/website-schema.yml@14.0.0" ================================================ FILE: .gitignore ================================================ /vendor /composer.lock /phpunit.xml /.phpunit.cache /phpcs.xml /.phpcs-cache ================================================ FILE: LICENSE ================================================ Copyright (c) 2006-2018 Doctrine Project Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. ================================================ FILE: README.md ================================================ # Doctrine Lexer [![Build Status](https://github.com/doctrine/lexer/workflows/Continuous%20Integration/badge.svg)](https://github.com/doctrine/lexer/actions) Base library for a lexer that can be used in Top-Down, Recursive Descent Parsers. This lexer is used in Doctrine Annotations and in Doctrine ORM (DQL). https://www.doctrine-project.org/projects/lexer.html ================================================ FILE: UPGRADE.md ================================================ Note about upgrading: Doctrine uses static and runtime mechanisms to raise awareness about deprecated code. - Use of `@deprecated` docblock that is detected by IDEs (like PHPStorm) or Static Analysis tools (like Psalm, phpstan) - Use of our low-overhead runtime deprecation API, details: https://github.com/doctrine/deprecations/ # Upgrade to 3.0.0 `Doctrine\Common\Lexer\Token` no longer implements `ArrayAccess`. Parameter type declarations have been added to `Doctrine\Common\Lexer\AbstractLexer` and `Doctrine\Common\Lexer\Token`. You should add both parameter type declarations and return type declarations to your lexers, based on the `@return` phpdoc. # Upgrade to 2.0.0 `AbstractLexer::glimpse()` and `AbstractLexer::peek()` now return instances of `Doctrine\Common\Lexer\Token`, which is an array-like class Using it as an array is deprecated in favor of using properties of that class. Using `count()` on it is deprecated with no replacement. ================================================ FILE: composer.json ================================================ { "name": "doctrine/lexer", "description": "PHP Doctrine Lexer parser library that can be used in Top-Down, Recursive Descent Parsers.", "license": "MIT", "type": "library", "keywords": [ "php", "parser", "lexer", "annotations", "docblock" ], "authors": [ { "name": "Guilherme Blanco", "email": "guilhermeblanco@gmail.com" }, { "name": "Roman Borschel", "email": "roman@code-factory.org" }, { "name": "Johannes Schmitt", "email": "schmittjoh@gmail.com" } ], "homepage": "https://www.doctrine-project.org/projects/lexer.html", "require": { "php": "^8.1" }, "require-dev": { "doctrine/coding-standard": "^14", "phpstan/phpstan": "^2", "phpunit/phpunit": "^10.5.58 || ^12.5.4" }, "autoload": { "psr-4": { "Doctrine\\Common\\Lexer\\": "src" } }, "autoload-dev": { "psr-4": { "Doctrine\\Tests\\Common\\Lexer\\": "tests" } }, "config": { "allow-plugins": { "composer/package-versions-deprecated": true, "dealerdirect/phpcodesniffer-composer-installer": true }, "sort-packages": true } } ================================================ FILE: docs/en/dql-parser.rst ================================================ DQL Lexer ========= Here is a more complicated example from the Doctrine ORM project. The ``Doctrine\ORM\Query\Lexer`` implementation for DQL looks something like the following: .. code-block:: php = 100 public const T_ALIASED_NAME = 100; public const T_FULLY_QUALIFIED_NAME = 101; public const T_IDENTIFIER = 102; // All keyword tokens should be >= 200 public const T_ALL = 200; public const T_AND = 201; public const T_ANY = 202; public const T_AS = 203; public const T_ASC = 204; public const T_AVG = 205; public const T_BETWEEN = 206; public const T_BOTH = 207; public const T_BY = 208; public const T_CASE = 209; public const T_COALESCE = 210; public const T_COUNT = 211; public const T_DELETE = 212; public const T_DESC = 213; public const T_DISTINCT = 214; public const T_ELSE = 215; public const T_EMPTY = 216; public const T_END = 217; public const T_ESCAPE = 218; public const T_EXISTS = 219; public const T_FALSE = 220; public const T_FROM = 221; public const T_GROUP = 222; public const T_HAVING = 223; public const T_HIDDEN = 224; public const T_IN = 225; public const T_INDEX = 226; public const T_INNER = 227; public const T_INSTANCE = 228; public const T_IS = 229; public const T_JOIN = 230; public const T_LEADING = 231; public const T_LEFT = 232; public const T_LIKE = 233; public const T_MAX = 234; public const T_MEMBER = 235; public const T_MIN = 236; public const T_NEW = 237; public const T_NOT = 238; public const T_NULL = 239; public const T_NULLIF = 240; public const T_OF = 241; public const T_OR = 242; public const T_ORDER = 243; public const T_OUTER = 244; public const T_PARTIAL = 245; public const T_SELECT = 246; public const T_SET = 247; public const T_SOME = 248; public const T_SUM = 249; public const T_THEN = 250; public const T_TRAILING = 251; public const T_TRUE = 252; public const T_UPDATE = 253; public const T_WHEN = 254; public const T_WHERE = 255; public const T_WITH = 256; /** * Creates a new query scanner object. * * @param string $input A query string. */ public function __construct(string $input) { $this->setInput($input); } /** * {@inheritdoc} */ protected function getCatchablePatterns(): array { return [ '[a-z_][a-z0-9_]*\:[a-z_][a-z0-9_]*(?:\\\[a-z_][a-z0-9_]*)*', // aliased name '[a-z_\\\][a-z0-9_]*(?:\\\[a-z_][a-z0-9_]*)*', // identifier or qualified name '(?:[0-9]+(?:[\.][0-9]+)*)(?:e[+-]?[0-9]+)?', // numbers "'(?:[^']|'')*'", // quoted strings '\?[0-9]*|:[a-z_][a-z0-9_]*', // parameters ]; } /** * {@inheritdoc} */ protected function getNonCatchablePatterns(): array { return ['\s+', '(.)']; } /** * {@inheritdoc} */ protected function getType(&$value): int { $type = self::T_NONE; switch (true) { // Recognize numeric values case (is_numeric($value)): if (strpos($value, '.') !== false || stripos($value, 'e') !== false) { return self::T_FLOAT; } return self::T_INTEGER; // Recognize quoted strings case ($value[0] === "'"): $value = str_replace("''", "'", substr($value, 1, strlen($value) - 2)); return self::T_STRING; // Recognize identifiers, aliased or qualified names case (ctype_alpha($value[0]) || $value[0] === '_' || $value[0] === '\\'): $name = 'Doctrine\ORM\Query\Lexer::T_' . strtoupper($value); if (defined($name)) { $type = constant($name); if ($type > 100) { return $type; } } if (strpos($value, ':') !== false) { return self::T_ALIASED_NAME; } if (strpos($value, '\\') !== false) { return self::T_FULLY_QUALIFIED_NAME; } return self::T_IDENTIFIER; // Recognize input parameters case ($value[0] === '?' || $value[0] === ':'): return self::T_INPUT_PARAMETER; // Recognize symbols case ($value === '.'): return self::T_DOT; case ($value === ','): return self::T_COMMA; case ($value === '('): return self::T_OPEN_PARENTHESIS; case ($value === ')'): return self::T_CLOSE_PARENTHESIS; case ($value === '='): return self::T_EQUALS; case ($value === '>'): return self::T_GREATER_THAN; case ($value === '<'): return self::T_LOWER_THAN; case ($value === '+'): return self::T_PLUS; case ($value === '-'): return self::T_MINUS; case ($value === '*'): return self::T_MULTIPLY; case ($value === '/'): return self::T_DIVIDE; case ($value === '!'): return self::T_NEGATE; case ($value === '{'): return self::T_OPEN_CURLY_BRACE; case ($value === '}'): return self::T_CLOSE_CURLY_BRACE; // Default default: // Do nothing } return $type; } } This is roughly what the DQL Parser looks like that uses the above Lexer implementation: .. note:: You can see the full implementation `here `_. .. code-block:: php lexer = new Lexer(); $this->lexer->setInput($dql); } // ... public function getAST(): AST\SelectStatement|AST\UpdateStatement|AST\DeleteStatement { // Parse & build AST $AST = $this->QueryLanguage(); // ... return $AST; } public function QueryLanguage(): AST\SelectStatement|AST\UpdateStatement|AST\DeleteStatement { $this->lexer->moveNext(); switch ($this->lexer->lookahead->type) { case Lexer::T_SELECT: $statement = $this->SelectStatement(); break; case Lexer::T_UPDATE: $statement = $this->UpdateStatement(); break; case Lexer::T_DELETE: $statement = $this->DeleteStatement(); break; default: $this->syntaxError('SELECT, UPDATE or DELETE'); } // Check for end of string if ($this->lexer->lookahead !== null) { $this->syntaxError('end of string'); } return $statement; } // ... } Now the AST is used to transform the DQL query in to portable SQL for whatever relational database you are using! .. code-block:: php getAST(); // returns \Doctrine\ORM\Query\AST\SelectStatement What is an AST? =============== AST stands for `Abstract syntax tree `_. In computer science, an abstract syntax tree (AST), or just syntax tree, is a tree representation of the abstract syntactic structure of source code written in a programming language. Each node of the tree denotes a construct occurring in the source code. ================================================ FILE: docs/en/index.rst ================================================ Introduction ============ Doctrine Lexer is a library that can be used in Top-Down, Recursive Descent Parsers. This lexer is used in Doctrine Annotations and in Doctrine ORM (DQL). To write your own parser you just need to extend ``Doctrine\Common\Lexer\AbstractLexer`` and implement the following three abstract methods. .. code-block:: php /** * Lexical catchable patterns. * * @return string[] */ abstract protected function getCatchablePatterns(); /** * Lexical non-catchable patterns. * * @return string[] */ abstract protected function getNonCatchablePatterns(); /** Retrieve token type. Also processes the token value if necessary. */ abstract protected function getType(string &$value): int; These methods define the `lexical `_ catchable and non-catchable patterns and a method for returning the type of a token and filtering the value if necessary. The Lexer is responsible for giving you an API to walk across a string one character at a time and analyze the type of each character, value and position of each token in the string. The low level API of the lexer is pretty simple: - ``setInput($input)`` - Sets the input data to be tokenized. The Lexer is immediately reset and the new input tokenized. - ``reset()`` - Resets the lexer. - ``resetPeek()`` - Resets the peek pointer to 0. - ``resetPosition($position = 0)`` - Resets the lexer position on the input to the given position. - ``isNextToken($token)`` - Checks whether a given token matches the current lookahead. - ``isNextTokenAny(array $tokens)`` - Checks whether any of the given tokens matches the current lookahead. - ``moveNext()`` - Moves to the next token in the input string. - ``skipUntil($type)`` - Tells the lexer to skip input tokens until it sees a token with the given value. - ``isA($value, $token)`` - Checks if given value is identical to the given token. - ``peek()`` - Moves the lookahead token forward. - ``glimpse()`` - Peeks at the next token, returns it and immediately resets the peek. ================================================ FILE: docs/en/sidebar.rst ================================================ .. toctree:: :depth: 3 index simple-parser-example dql-parser ================================================ FILE: docs/en/simple-parser-example.rst ================================================ Simple Parser Example ===================== Extend the ``Doctrine\Common\Lexer\AbstractLexer`` class and implement the ``getCatchablePatterns``, ``getNonCatchablePatterns``, and ``getType`` methods. Here is a very simple example lexer implementation named ``CharacterTypeLexer``. It tokenizes a string to ``T_UPPER``, ``T_LOWER`` and``T_NUMBER`` tokens: .. code-block:: php */ class CharacterTypeLexer extends AbstractLexer { const T_UPPER = 1; const T_LOWER = 2; const T_NUMBER = 3; protected function getCatchablePatterns(): array { return [ '[a-zA-Z0-9]', ]; } protected function getNonCatchablePatterns(): array { return []; } protected function getType(&$value): int { if (is_numeric($value)) { return self::T_NUMBER; } if (strtoupper($value) === $value) { return self::T_UPPER; } if (strtolower($value) === $value) { return self::T_LOWER; } } } Use ``CharacterTypeLexer`` to extract an array of upper case characters: .. code-block:: php */ public function getUpperCaseCharacters(string $string): array { $this->lexer->setInput($string); $this->lexer->moveNext(); $upperCaseChars = []; while (true) { if (!$this->lexer->lookahead) { break; } $this->lexer->moveNext(); if ($this->lexer->token->isA(CharacterTypeLexer::T_UPPER)) { $upperCaseChars[] = $this->lexer->token->value; } } return $upperCaseChars; } } $upperCaseCharacterExtractor = new UpperCaseCharacterExtracter(new CharacterTypeLexer()); $upperCaseCharacters = $upperCaseCharacterExtractor->getUpperCaseCharacters('1aBcdEfgHiJ12'); print_r($upperCaseCharacters); The variable ``$upperCaseCharacters`` contains all of the upper case characters: .. code-block:: php Array ( [0] => B [1] => E [2] => H [3] => J ) This is a simple example but it should demonstrate the low level API that can be used to build more complex parsers. ================================================ FILE: phpcs.xml.dist ================================================ src tests ================================================ FILE: phpstan.neon.dist ================================================ parameters: level: max paths: - %rootDir%/../../../src - %rootDir%/../../../tests ================================================ FILE: phpunit.xml.dist ================================================ tests src ================================================ FILE: src/AbstractLexer.php ================================================ > */ private array $tokens = []; /** * Current lexer position in input string. */ private int $position = 0; /** * Current peek of current lexer position. */ private int $peek = 0; /** * The next token in the input. * * @var Token|null */ public Token|null $lookahead; /** * The last matched/seen token. * * @var Token|null */ public Token|null $token; /** * Composed regex for input parsing. * * @var non-empty-string|null */ private string|null $regex = null; /** * Sets the input data to be tokenized. * * The Lexer is immediately reset and the new input tokenized. * Any unprocessed tokens from any previous input are lost. * * @param string $input The input to be tokenized. * * @return void */ public function setInput(string $input) { $this->input = $input; $this->tokens = []; $this->reset(); $this->scan($input); } /** * Resets the lexer. * * @return void */ public function reset() { $this->lookahead = null; $this->token = null; $this->peek = 0; $this->position = 0; } /** * Resets the peek pointer to 0. * * @return void */ public function resetPeek() { $this->peek = 0; } /** * Resets the lexer position on the input to the given position. * * @param int $position Position to place the lexical scanner. * * @return void */ public function resetPosition(int $position = 0) { $this->position = $position; } /** * Retrieve the original lexer's input until a given position. * * @return string */ public function getInputUntilPosition(int $position) { return substr($this->input, 0, $position); } /** * Checks whether a given token matches the current lookahead. * * @param T $type * * @return bool * * @phpstan-assert-if-true !=null $this->lookahead */ public function isNextToken(int|string|UnitEnum $type) { return $this->lookahead !== null && $this->lookahead->isA($type); } /** * Checks whether any of the given tokens matches the current lookahead. * * @param list $types * * @return bool * * @phpstan-assert-if-true !=null $this->lookahead */ public function isNextTokenAny(array $types) { return $this->lookahead !== null && $this->lookahead->isA(...$types); } /** * Moves to the next token in the input string. * * @return bool * * @phpstan-impure * @phpstan-assert-if-true !null $this->lookahead */ public function moveNext() { $this->peek = 0; $this->token = $this->lookahead; $this->lookahead = isset($this->tokens[$this->position]) ? $this->tokens[$this->position++] : null; return $this->lookahead !== null; } /** * Tells the lexer to skip input tokens until it sees a token with the given value. * * @param T $type The token type to skip until. * * @return void */ public function skipUntil(int|string|UnitEnum $type) { while ($this->lookahead !== null && ! $this->lookahead->isA($type)) { $this->moveNext(); } } /** * Checks if given value is identical to the given token. * * @return bool */ public function isA(string $value, int|string|UnitEnum $token) { return $this->getType($value) === $token; } /** * Moves the lookahead token forward. * * @return Token|null The next token or NULL if there are no more tokens ahead. */ public function peek() { if (isset($this->tokens[$this->position + $this->peek])) { return $this->tokens[$this->position + $this->peek++]; } return null; } /** * Peeks at the next token, returns it and immediately resets the peek. * * @return Token|null The next token or NULL if there are no more tokens ahead. * * @phpstan-impure */ public function glimpse() { $peek = $this->peek(); $this->peek = 0; return $peek; } /** * Scans the input string for tokens. * * @param string $input A query string. * * @return void */ protected function scan(string $input) { if (! isset($this->regex)) { $this->regex = sprintf( '/(%s)|%s/%s', implode(')|(', $this->getCatchablePatterns()), implode('|', $this->getNonCatchablePatterns()), $this->getModifiers(), ); } $flags = PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_OFFSET_CAPTURE; $matches = preg_split($this->regex, $input, -1, $flags); if ($matches === false) { // Work around https://bugs.php.net/78122 $matches = [[$input, 0]]; } foreach ($matches as $match) { // Must remain before 'value' assignment since it can change content $firstMatch = $match[0]; $type = $this->getType($firstMatch); $this->tokens[] = new Token( $firstMatch, $type, $match[1], ); } } /** * Gets the literal for a given token. * * @param T $token * * @return int|string */ public function getLiteral(int|string|UnitEnum $token) { if ($token instanceof UnitEnum) { return $token::class . '::' . $token->name; } $className = static::class; $reflClass = new ReflectionClass($className); $constants = $reflClass->getConstants(); foreach ($constants as $name => $value) { if ($value === $token) { return $className . '::' . $name; } } return $token; } /** * Regex modifiers * * @return string */ protected function getModifiers() { return 'iu'; } /** * Lexical catchable patterns. * * @return string[] */ abstract protected function getCatchablePatterns(); /** * Lexical non-catchable patterns. * * @return string[] */ abstract protected function getNonCatchablePatterns(); /** * Retrieve token type. Also processes the token value if necessary. * * @return T|null * * @param-out V $value */ abstract protected function getType(string &$value); } ================================================ FILE: src/Token.php ================================================ value = $value; $this->type = $type; $this->position = $position; } /** @param T ...$types */ public function isA(...$types): bool { return in_array($this->type, $types, true); } } ================================================ FILE: tests/AbstractLexerTest.php ================================================ concreteLexer = new ConcreteLexer(); } public function tearDown(): void { setlocale(LC_ALL, null); } /** @phpstan-return list>}> */ public static function dataProvider(): array { return [ [ 'price=10', [ new Token('price', 'string', 0), new Token('=', 'operator', 5), new Token(10, 'int', 6), ], ], ]; } public function testResetPeek(): void { $expectedTokens = [ new Token('price', 'string', 0), new Token('=', 'operator', 5), new Token(10, 'int', 6), ]; $this->concreteLexer->setInput('price=10'); $this->assertEquals($expectedTokens[0], $this->concreteLexer->peek()); $this->assertEquals($expectedTokens[1], $this->concreteLexer->peek()); $this->concreteLexer->resetPeek(); $this->assertEquals($expectedTokens[0], $this->concreteLexer->peek()); } public function testResetPosition(): void { $expectedTokens = [ new Token('price', 'string', 0), new Token('=', 'operator', 5), new Token(10, 'int', 6), ]; $this->concreteLexer->setInput('price=10'); $this->assertNull($this->concreteLexer->lookahead); $this->assertTrue($this->concreteLexer->moveNext()); $this->assertEquals($expectedTokens[0], $this->concreteLexer->lookahead); $this->assertTrue($this->concreteLexer->moveNext()); $this->assertEquals($expectedTokens[1], $this->concreteLexer->lookahead); $this->concreteLexer->resetPosition(0); $this->assertTrue($this->concreteLexer->moveNext()); $this->assertEquals($expectedTokens[0], $this->concreteLexer->lookahead); } /** @phpstan-param list> $expectedTokens */ #[DataProvider('dataProvider')] public function testMoveNext(string $input, array $expectedTokens): void { $this->concreteLexer->setInput($input); $this->assertNull($this->concreteLexer->lookahead); for ($i = 0; $i < count($expectedTokens); $i++) { $this->assertTrue($this->concreteLexer->moveNext()); $this->assertEquals($expectedTokens[$i], $this->concreteLexer->lookahead); } $this->assertFalse($this->concreteLexer->moveNext()); $this->assertNull($this->concreteLexer->lookahead); } public function testSkipUntil(): void { $this->concreteLexer->setInput('price=10'); $this->assertTrue($this->concreteLexer->moveNext()); $this->concreteLexer->skipUntil('operator'); $this->assertEquals( new Token('=', 'operator', 5), $this->concreteLexer->lookahead, ); } public function testUtf8Mismatch(): void { $this->concreteLexer->setInput("\xE9=10"); $this->assertTrue($this->concreteLexer->moveNext()); $this->assertEquals( new Token("\xE9=10", 'string', 0), $this->concreteLexer->lookahead, ); } /** @phpstan-param list> $expectedTokens */ #[DataProvider('dataProvider')] public function testPeek(string $input, array $expectedTokens): void { $this->concreteLexer->setInput($input); foreach ($expectedTokens as $expectedToken) { $actualToken = $this->concreteLexer->peek(); assert($actualToken !== null); $this->assertEquals($expectedToken, $actualToken); $this->assertSame($expectedToken->value, $actualToken->value); $this->assertSame($expectedToken->type, $actualToken->type); $this->assertSame($expectedToken->position, $actualToken->position); } $this->assertNull($this->concreteLexer->peek()); } /** @phpstan-param list> $expectedTokens */ #[DataProvider('dataProvider')] public function testGlimpse(string $input, array $expectedTokens): void { $this->concreteLexer->setInput($input); foreach ($expectedTokens as $expectedToken) { $actualToken = $this->concreteLexer->glimpse(); assert($actualToken !== null); $this->assertEquals($expectedToken, $actualToken); $this->assertEquals($expectedToken, $this->concreteLexer->glimpse()); $this->assertSame($expectedToken->value, $actualToken->value); $this->assertSame($expectedToken->type, $actualToken->type); $this->assertSame($expectedToken->position, $actualToken->position); $this->concreteLexer->moveNext(); } $this->assertNull($this->concreteLexer->peek()); } /** @phpstan-return list */ public static function inputUntilPositionDataProvider(): array { return [ ['price=10', 5, 'price'], ]; } #[DataProvider('inputUntilPositionDataProvider')] public function testGetInputUntilPosition( string $input, int $position, string $expectedInput, ): void { $this->concreteLexer->setInput($input); $this->assertSame($expectedInput, $this->concreteLexer->getInputUntilPosition($position)); } /** @phpstan-param list> $expectedTokens */ #[DataProvider('dataProvider')] public function testIsNextToken(string $input, array $expectedTokens): void { $this->concreteLexer->setInput($input); $this->concreteLexer->moveNext(); for ($i = 0; $i < count($expectedTokens); $i++) { assert($expectedTokens[$i]->type !== null); $this->assertTrue($this->concreteLexer->isNextToken($expectedTokens[$i]->type)); $this->concreteLexer->moveNext(); } } /** @phpstan-param list> $expectedTokens */ #[DataProvider('dataProvider')] public function testIsNextTokenAny(string $input, array $expectedTokens): void { $allTokenTypes = array_map(static function ($token): string { assert($token->type !== null); return $token->type; }, $expectedTokens); $this->concreteLexer->setInput($input); $this->concreteLexer->moveNext(); for ($i = 0; $i < count($expectedTokens); $i++) { assert($expectedTokens[$i]->type !== null); $this->assertTrue($this->concreteLexer->isNextTokenAny([$expectedTokens[$i]->type])); $this->assertTrue($this->concreteLexer->isNextTokenAny($allTokenTypes)); $this->concreteLexer->moveNext(); } } public function testGetLiteral(): void { $this->assertSame('Doctrine\Tests\Common\Lexer\ConcreteLexer::INT', $this->concreteLexer->getLiteral('int')); $this->assertSame('fake_token', $this->concreteLexer->getLiteral('fake_token')); } public function testGetLiteralWithEnumLexer(): void { $enumLexer = new EnumLexer(); $this->assertSame( 'Doctrine\Tests\Common\Lexer\TokenType::OPERATOR', $enumLexer->getLiteral(TokenType::OPERATOR), ); } public function testIsA(): void { $this->assertTrue($this->concreteLexer->isA('11', 'int')); $this->assertTrue($this->concreteLexer->isA('1.1', 'int')); $this->assertTrue($this->concreteLexer->isA('=', 'operator')); $this->assertTrue($this->concreteLexer->isA('>', 'operator')); $this->assertTrue($this->concreteLexer->isA('<', 'operator')); $this->assertTrue($this->concreteLexer->isA('fake_text', 'string')); } public function testAddCatchablePatternsToMutableLexer(): void { $mutableLexer = new MutableLexer(); $mutableLexer->addCatchablePattern('[a-z]'); $mutableLexer->setInput('one'); $token = $mutableLexer->glimpse(); $this->assertNotNull($token); $this->assertEquals('o', $token->value); $mutableLexer = new MutableLexer(); $mutableLexer->addCatchablePattern('[a-z]+'); $mutableLexer->setInput('one'); $token = $mutableLexer->glimpse(); $this->assertNotNull($token); $this->assertEquals('one', $token->value); } public function testMarkerAnnotationLocaleTr(): void { setlocale(LC_ALL, 'tr_TR.utf8', 'tr_TR'); $mutableLexer = new MutableLexer(); $mutableLexer->addCatchablePattern('[a-z_\\\][a-z0-9_\:\\\]*[a-z_][a-z0-9_]*'); $mutableLexer->addCatchablePattern('(?:[+-]?[0-9]+(?:[\.][0-9]+)*)(?:[eE][+-]?[0-9]+)?'); $mutableLexer->addCatchablePattern('"(?:""|[^"])*+"'); $mutableLexer->setInput('@ODM\Id'); self::assertNull($mutableLexer->token); self::assertNull($mutableLexer->lookahead); self::assertTrue($mutableLexer->moveNext()); self::assertNull($mutableLexer->token); self::assertNotNull($mutableLexer->lookahead); self::assertEquals('@', $mutableLexer->lookahead->value); self::assertTrue($mutableLexer->moveNext()); self::assertNotNull($mutableLexer->token); self::assertEquals('@', $mutableLexer->token->value); self::assertEquals('ODM\Id', $mutableLexer->lookahead->value); } public function testCanTokenizeFloatValue(): void { $lexer = new /** @template-extends AbstractLexer */ class () extends AbstractLexer { final public const T_NONE = 1; final public const T_INTEGER = 2; final public const T_FLOAT = 4; final public const T_BOOL = 8; protected function getType(string|int|float|bool &$value): int { if ($value === 'y') { $value = true; return self::T_BOOL; } if (is_numeric($value)) { $value += 0; if (is_int($value)) { return self::T_INTEGER; } return self::T_FLOAT; } return self::T_NONE; } /** {@inheritDoc} */ protected function getCatchablePatterns(): array { return [ '(?:[0-9]+)(?:[\.][0-9]+)?(?:e[+-]?[0-9]+)?', 'y', ]; } /** {@inheritDoc} */ protected function getNonCatchablePatterns(): array { return ['\s+']; } }; $lexer->setInput('123.456'); $token = $lexer->peek(); assert($token !== null); self::assertSame(123.456, $token->value, 'expect a real float, not a numerical string'); $lexer->setInput('y'); $token = $lexer->peek(); assert($token !== null); self::assertTrue($token->value, 'expect a real bool, not a numerical string'); } } ================================================ FILE: tests/ConcreteLexer.php ================================================ */ class ConcreteLexer extends AbstractLexer { final public const INT = 'int'; /** * {@inheritDoc} */ protected function getCatchablePatterns(): array { return [ '=|<|>', '[a-z]+', '\d+', ]; } /** * {@inheritDoc} */ protected function getNonCatchablePatterns(): array { return [ '\s+', '(.)', ]; } protected function getType(string|int|float &$value): string { if (is_numeric($value)) { $value = (int) $value; return 'int'; } if (in_array($value, ['=', '<', '>'])) { return 'operator'; } return 'string'; } } ================================================ FILE: tests/EnumLexer.php ================================================ */ class EnumLexer extends AbstractLexer { /** * {@inheritDoc} */ protected function getCatchablePatterns(): array { return [ '=|<|>', '[a-z]+', '\d+', ]; } /** * {@inheritDoc} */ protected function getNonCatchablePatterns(): array { return [ '\s+', '(.)', ]; } protected function getType(string &$value): TokenType { if (is_numeric($value)) { $value = (int) $value; return TokenType::INT; } if (in_array($value, ['=', '<', '>'])) { return TokenType::OPERATOR; } return TokenType::STRING; } } ================================================ FILE: tests/MutableLexer.php ================================================ */ class MutableLexer extends AbstractLexer { /** @var string[] */ private array $catchablePatterns = []; public function addCatchablePattern(string $pattern): void { $this->catchablePatterns[] = $pattern; } /** * {@inheritDoc} */ protected function getCatchablePatterns(): array { return $this->catchablePatterns; } /** * {@inheritDoc} */ protected function getNonCatchablePatterns(): array { return ['[\s,]+']; } protected function getType(string &$value): int { return 1; } } ================================================ FILE: tests/TokenTest.php ================================================ $token */ $token = new Token('foo', 'string', 1); self::assertTrue($token->isA('string')); self::assertTrue($token->isA('int', 'string')); self::assertFalse($token->isA('int')); } } ================================================ FILE: tests/TokenType.php ================================================