From 87c393639ec69f2076dbb5edc7bacdc95a956f94 Mon Sep 17 00:00:00 2001
From: jrfnl <jrfnl@users.noreply.github.com>
Date: Tue, 21 May 2024 18:12:21 +0200
Subject: [PATCH] Tokenizer/PHP: efficiency fix

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

The type handling retokenization layer is triggered for each `&`, `|` and `)` the tokenizer encounters.

When something is recognized as a valid type declaration, the relevant tokens will all be retokenized in one go the first time the type handling layer is triggered, which means that - as the type tokens will have been retokenized already -, the type handling layer will not be triggered again for any of the other type related tokens in the type.

However, if the type is *not* recognized as a valid type, the type handling layer will keep getting retriggered and will (correctly) keep concluding this is not a valid type.

The change in this PR, prevents the type handling layer from doing any work when it is retriggered on a token which was previously already seen and concluded to be, either not part of a type or part of an invalid type.

This should make the tokenizer marginally faster for complex types containing an error, like `(A&B|(C&D)|(E&F)`.
---
 src/Tokenizers/PHP.php | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/src/Tokenizers/PHP.php b/src/Tokenizers/PHP.php
index 60a0d41df8..7168231de6 100644
--- a/src/Tokenizers/PHP.php
+++ b/src/Tokenizers/PHP.php
@@ -2602,7 +2602,9 @@ protected function processAdditional()
 
         $this->createAttributesNestingMap();
 
-        $numTokens = count($this->tokens);
+        $numTokens         = count($this->tokens);
+        $lastSeenTypeToken = $numTokens;
+
         for ($i = ($numTokens - 1); $i >= 0; $i--) {
             // Check for any unset scope conditions due to alternate IF/ENDIF syntax.
             if (isset($this->tokens[$i]['scope_opener']) === true
@@ -3038,6 +3040,12 @@ protected function processAdditional()
                 || $this->tokens[$i]['code'] === T_BITWISE_AND
                 || $this->tokens[$i]['code'] === T_CLOSE_PARENTHESIS
             ) {
+                if ($lastSeenTypeToken < $i) {
+                    // We've already examined this code to check if it is a type declaration and concluded it wasn't.
+                    // No need to do it again.
+                    continue;
+                }
+
                 /*
                     Convert "|" to T_TYPE_UNION or leave as T_BITWISE_OR.
                     Convert "&" to T_TYPE_INTERSECTION or leave as T_BITWISE_AND.
@@ -3250,6 +3258,9 @@ protected function processAdditional()
                     break;
                 }//end for
 
+                // Remember the last token we examined as part of the (non-)"type declaration".
+                $lastSeenTypeToken = $x;
+
                 if ($confirmed === false
                     && $suspectedType === 'property or parameter'
                     && isset($this->tokens[$i]['nested_parenthesis']) === true