Merge pull request #11092 from weirdan/fix-invalid-utf8-output-in-jso…

…n-reports

Fix JSON formatter crashes with invalid UTF in error messages

src/Psalm/Internal/Json/Json.php

@@ -4,8 +4,12 @@
 
 use RuntimeException;
 
+use function array_walk_recursive;
+use function bin2hex;
+use function is_string;
 use function json_encode;
 use function json_last_error_msg;
+use function preg_replace_callback;
 
 use const JSON_PRETTY_PRINT;
 use const JSON_UNESCAPED_SLASHES;
@@ -19,28 +23,80 @@
 final class Json
 {
     public const PRETTY = JSON_PRETTY_PRINT | JSON_UNESCAPED_SLASHES | JSON_UNESCAPED_UNICODE;
+    // from https://stackoverflow.com/a/11709412
+    private const INVALID_UTF_REGEXP = <<<'EOF'
+    /(
+        [\xC0-\xC1] # Invalid UTF-8 Bytes
+        | [\xF5-\xFF] # Invalid UTF-8 Bytes
+        | \xE0[\x80-\x9F] # Overlong encoding of prior code point
+        | \xF0[\x80-\x8F] # Overlong encoding of prior code point
+        | [\xC2-\xDF](?![\x80-\xBF]) # Invalid UTF-8 Sequence Start
+        | [\xE0-\xEF](?![\x80-\xBF]{2}) # Invalid UTF-8 Sequence Start
+        | [\xF0-\xF4](?![\x80-\xBF]{3}) # Invalid UTF-8 Sequence Start
+        | (?<=[\x00-\x7F\xF5-\xFF])[\x80-\xBF] # Invalid UTF-8 Sequence Middle
+        | (?<!
+            [\xC2-\xDF]
+            |[\xE0-\xEF]
+            |[\xE0-\xEF][\x80-\xBF]
+            |[\xF0-\xF4]
+            |[\xF0-\xF4][\x80-\xBF]
+            |[\xF0-\xF4][\x80-\xBF]{2}
+        )[\x80-\xBF] # Overlong Sequence
+        | (?<=[\xE0-\xEF])[\x80-\xBF](?![\x80-\xBF]) # Short 3 byte sequence
+        | (?<=[\xF0-\xF4])[\x80-\xBF](?![\x80-\xBF]{2}) # Short 4 byte sequence
+        | (?<=[\xF0-\xF4][\x80-\xBF])[\x80-\xBF](?![\x80-\xBF]) # Short 4 byte sequence (2)
+    )/x
+    EOF;
 
     /**
      * @var int
      */
     public const DEFAULT = 0;
 
     /**
-     * @param mixed $data
+     * @param array<array-key, mixed> $data
      * @psalm-pure
      */
-    public static function encode($data, ?int $options = null): string
+    public static function encode(array $data, ?int $options = null): string
     {
         if ($options === null) {
             $options = self::DEFAULT;
         }
 
         $result = json_encode($data, $options);
+
+        if ($result == false) {
+            $result = json_encode(self::scrub($data), $options);
+        }
+
         if ($result === false) {
             /** @psalm-suppress ImpureFunctionCall */
             throw new RuntimeException('Cannot create JSON string: '.json_last_error_msg());
         }
 
         return $result;
     }
+
+    /** @psalm-pure */
+    private static function scrub(array $data): array
+    {
+        /** @psalm-suppress ImpureFunctionCall */
+        array_walk_recursive(
+            $data,
+            /**
+             * @psalm-pure
+             * @param mixed $value
+             */
+            function (&$value): void {
+                if (is_string($value)) {
+                    $value = preg_replace_callback(
+                        self::INVALID_UTF_REGEXP,
+                        static fn(array $matches): string => '<Invalid UTF-8: 0x' . bin2hex($matches[0] ?? '') . '>',
+                        $value,
+                    );
+                }
+            },
+        );
+        return $data;
+    }
 }

tests/Internal/JsonTest.php

@@ -0,0 +1,15 @@
+<?php
+
+namespace Psalm\Tests\Internal;
+
+use Psalm\Internal\Json\Json;
+use Psalm\Tests\TestCase;
+
+final class JsonTest extends TestCase
+{
+    public function testConvertsInvalidUtf(): void
+    {
+        $invalidUtf = "\xd1"; // incomplete sequence like "ы"[0]
+        $this->assertEquals('{"data":"<Invalid UTF-8: 0xd1>"}', Json::encode(["data" => $invalidUtf]));
+    }
+}