From cac90382a16016b546442e9bbcfedf91a3cc28a5 Mon Sep 17 00:00:00 2001
From: jrfnl <jrfnl@users.noreply.github.com>
Date: Tue, 21 May 2024 15:58:39 +0200
Subject: [PATCH] Tokenizer/PHP: efficiency improvement for DNF type handling

The PHP::processAdditional()` method walks _back_ from the end of the file to the beginning.

With that in mind, and knowing that a type can never end on an open parenthesis, and an open parenthesis can never be seen in a type before the close parenthesis has been seen (at least for valid/non-parse error types), it makes no sense to trigger the type handling logic for open parentheses.

This should make the tokenizer slightly more efficient as (open) parentheses are used a lot in code ;-)

It also prevents the type handling layer from acting on these type of invalid/parse error types, while it previously would.

Includes tests safeguarding the behaviour of the type handling layer for this type of invalid/parse error types.

Of these tests, the type for the OO constant and for the property were previously not handled consistently/correctly.
The parameter type + the return type were fine.
---
 src/Tokenizers/PHP.php                        |  1 -
 .../Tokenizer/PHP/DNFTypesParseError1Test.inc | 17 +++++
 .../Tokenizer/PHP/DNFTypesParseError1Test.php | 69 +++++++++++++++++++
 3 files changed, 86 insertions(+), 1 deletion(-)
 create mode 100644 tests/Core/Tokenizer/PHP/DNFTypesParseError1Test.inc
 create mode 100644 tests/Core/Tokenizer/PHP/DNFTypesParseError1Test.php

diff --git a/src/Tokenizers/PHP.php b/src/Tokenizers/PHP.php
index 23dab0a60e..3e7be371cf 100644
--- a/src/Tokenizers/PHP.php
+++ b/src/Tokenizers/PHP.php
@@ -3036,7 +3036,6 @@ protected function processAdditional()
                 continue;
             } else if ($this->tokens[$i]['code'] === T_BITWISE_OR
                 || $this->tokens[$i]['code'] === T_BITWISE_AND
-                || $this->tokens[$i]['code'] === T_OPEN_PARENTHESIS
                 || $this->tokens[$i]['code'] === T_CLOSE_PARENTHESIS
             ) {
                 /*
diff --git a/tests/Core/Tokenizer/PHP/DNFTypesParseError1Test.inc b/tests/Core/Tokenizer/PHP/DNFTypesParseError1Test.inc
new file mode 100644
index 0000000000..a6cf511c2e
--- /dev/null
+++ b/tests/Core/Tokenizer/PHP/DNFTypesParseError1Test.inc
@@ -0,0 +1,17 @@
+<?php
+
+// Parentheses in broken DNF type declarations will remain tokenized as normal parentheses.
+// This test is in a separate file as the 'nested_parenthesis' indexes will be off after this code.
+class ParseErrors {
+    /* testBrokenConstDNFTypeEndOnOpenParenthesis */
+    const A|(B PARSE_ERROR = null;
+
+    /* testBrokenPropertyDNFTypeEndOnOpenParenthesis */
+    public A|(B $parseError;
+
+    function unmatchedParens {
+        /* testBrokenParamDNFTypeEndOnOpenParenthesis */
+        A|(B $parseError,
+    /* testBrokenReturnDNFTypeEndOnOpenParenthesis */
+    ) : A|(B {}
+}
diff --git a/tests/Core/Tokenizer/PHP/DNFTypesParseError1Test.php b/tests/Core/Tokenizer/PHP/DNFTypesParseError1Test.php
new file mode 100644
index 0000000000..fe1761c890
--- /dev/null
+++ b/tests/Core/Tokenizer/PHP/DNFTypesParseError1Test.php
@@ -0,0 +1,69 @@
+<?php
+/**
+ * Tests that parentheses tokens are not converted to type parentheses tokens in broken DNF types.
+ *
+ * @author    Juliette Reinders Folmer <phpcs_nospam@adviesenzo.nl>
+ * @copyright 2024 PHPCSStandards and contributors
+ * @license   https://github.com/PHPCSStandards/PHP_CodeSniffer/blob/master/licence.txt BSD Licence
+ */
+
+namespace PHP_CodeSniffer\Tests\Core\Tokenizer\PHP;
+
+use PHP_CodeSniffer\Tests\Core\Tokenizer\AbstractTokenizerTestCase;
+
+final class DNFTypesParseError1Test extends AbstractTokenizerTestCase
+{
+
+
+    /**
+     * Document handling for a DNF type / parse error where the last significant type specific token is an open parenthesis.
+     *
+     * @param string $testMarker The comment prefacing the target token.
+     *
+     * @dataProvider dataBrokenDNFTypeCantEndOnOpenParenthesis
+     * @covers       PHP_CodeSniffer\Tokenizers\PHP::processAdditional
+     *
+     * @return void
+     */
+    public function testBrokenDNFTypeCantEndOnOpenParenthesis($testMarker)
+    {
+        $tokens = $this->phpcsFile->getTokens();
+
+        $openPtr = $this->getTargetToken($testMarker, [T_OPEN_PARENTHESIS, T_TYPE_OPEN_PARENTHESIS], '(');
+        $token   = $tokens[$openPtr];
+
+        // Verify that the open parenthesis is tokenized as a normal parenthesis.
+        $this->assertSame(T_OPEN_PARENTHESIS, $token['code'], 'Token tokenized as '.$token['type'].', not T_OPEN_PARENTHESIS (code)');
+        $this->assertSame('T_OPEN_PARENTHESIS', $token['type'], 'Token tokenized as '.$token['type'].', not T_OPEN_PARENTHESIS (type)');
+
+        // Verify that the type union is still tokenized as T_BITWISE_OR as the type declaration
+        // is not recognized as a valid type declaration.
+        $unionPtr = $this->getTargetToken($testMarker, [T_BITWISE_OR, T_TYPE_UNION], '|');
+        $token    = $tokens[$unionPtr];
+
+        $this->assertSame(T_BITWISE_OR, $token['code'], 'Token tokenized as '.$token['type'].', not T_BITWISE_OR (code)');
+        $this->assertSame('T_BITWISE_OR', $token['type'], 'Token tokenized as '.$token['type'].', not T_BITWISE_OR (type)');
+
+    }//end testBrokenDNFTypeCantEndOnOpenParenthesis()
+
+
+    /**
+     * Data provider.
+     *
+     * @see testBrokenDNFTypeCantEndOnOpenParenthesis()
+     *
+     * @return array<string, array<string, string>>
+     */
+    public static function dataBrokenDNFTypeCantEndOnOpenParenthesis()
+    {
+        return [
+            'OO const type'    => ['/* testBrokenConstDNFTypeEndOnOpenParenthesis */'],
+            'OO property type' => ['/* testBrokenPropertyDNFTypeEndOnOpenParenthesis */'],
+            'Parameter type'   => ['/* testBrokenParamDNFTypeEndOnOpenParenthesis */'],
+            'Return type'      => ['/* testBrokenReturnDNFTypeEndOnOpenParenthesis */'],
+        ];
+
+    }//end dataBrokenDNFTypeCantEndOnOpenParenthesis()
+
+
+}//end class