Use character array for utfstring

psalm-baseline.xml

@@ -1092,11 +1092,6 @@
       <code><![CDATA[isset(self::$translator)]]></code>
     </RedundantPropertyInitializationCheck>
   </file>
-  <file src="src/UtfString.php">
-    <PossiblyUnusedProperty>
-      <code><![CDATA[$byteLen]]></code>
-    </PossiblyUnusedProperty>
-  </file>
   <file src="src/Utils/BufferedQuery.php">
     <PossiblyNullOperand>
       <code><![CDATA[$this->status]]></code>
@@ -1567,6 +1562,12 @@
      * }]]></code>
     </InvalidReturnType>
   </file>
+  <file src="tests/UtfStringSerializer.php">
+    <PossiblyUnusedMethod>
+      <code><![CDATA[serialize]]></code>
+      <code><![CDATA[unserialize]]></code>
+    </PossiblyUnusedMethod>
+  </file>
   <file src="tests/Utils/BufferedQueryTest.php">
     <PossiblyUnusedMethod>
       <code><![CDATA[extractProvider]]></code>

src/Tools/TestGenerator.php

@@ -10,7 +10,9 @@
 use PhpMyAdmin\SqlParser\Exceptions\ParserException;
 use PhpMyAdmin\SqlParser\Lexer;
 use PhpMyAdmin\SqlParser\Parser;
+use PhpMyAdmin\SqlParser\Tests\UtfStringSerializer;
 use PhpMyAdmin\SqlParser\Token;
+use PhpMyAdmin\SqlParser\UtfString;
 
 use function dirname;
 use function file_exists;
@@ -168,7 +170,9 @@ public static function build(
 
         // unset mode, reset to default every time, to be sure
         Context::setMode();
-        $serializer = new CustomJsonSerializer();
+        $serializer = new CustomJsonSerializer(null, [
+            UtfString::class => new UtfStringSerializer(),
+        ]);
         // Writing test's data.
         $encoded = $serializer->serialize($test);
 

src/UtfString.php

@@ -8,12 +8,10 @@
 use Exception;
 use Stringable;
 
+use function count;
+use function implode;
 use function mb_check_encoding;
-use function mb_strlen;
-use function mb_substr;
-use function ord;
-use function strlen;
-use function substr;
+use function mb_str_split;
 
 /**
  * Implementation for UTF-8 strings.
@@ -32,44 +30,19 @@
 class UtfString implements ArrayAccess, Stringable
 {
     /**
-     * The raw, multi-byte string.
-     */
-    public string $str = '';
-
-    /**
-     * The index of current byte.
-     *
-     * For ASCII strings, the byte index is equal to the character index.
-     */
-    public int $byteIdx = 0;
-
-    /**
-     * The index of current character.
+     * The multi-byte characters.
      *
-     * For non-ASCII strings, some characters occupy more than one byte and
-     * the character index will have a lower value than the byte index.
-     */
-    public int $charIdx = 0;
-
-    /**
-     * The length of the string (in bytes).
+     * @var list<string>
      */
-    public int $byteLen = 0;
-
-    /**
-     * The length of the string (in characters).
-     */
-    public int $charLen = 0;
+    public array $characters;
 
     /** @param string $str the string */
     public function __construct(string $str)
     {
-        $this->str = $str;
-        $this->byteLen = mb_strlen($str, '8bit');
-        if (! mb_check_encoding($str, 'UTF-8')) {
-            $this->charLen = 0;
+        if (mb_check_encoding($str, 'UTF-8')) {
+            $this->characters = mb_str_split($str, 1, 'UTF-8');
         } else {
-            $this->charLen = mb_strlen($str, 'UTF-8');
+            $this->characters = [];
         }
     }
 
@@ -80,7 +53,7 @@ public function __construct(string $str)
      */
     public function offsetExists(mixed $offset): bool
     {
-        return ($offset >= 0) && ($offset < $this->charLen);
+        return $offset >= 0 && $offset < count($this->characters);
     }
 
     /**
@@ -90,37 +63,7 @@ public function offsetExists(mixed $offset): bool
      */
     public function offsetGet(mixed $offset): string|null
     {
-        // This function moves the internal byte and character pointer to the requested offset.
-        // This function is part of hot code so the aim is to do the following
-        // operations as efficiently as possible.
-        // UTF-8 character encoding is a variable length encoding that encodes Unicode
-        // characters in 1-4 bytes. Thus we fetch 4 bytes from the current offset and then use mb_substr
-        // to get the first UTF-8 character in it. We then use strlen to get the character's size in bytes.
-        if (($offset < 0) || ($offset >= $this->charLen)) {
-            return null;
-        }
-
-        $delta = $offset - $this->charIdx;
-
-        if ($delta > 0) {
-            // Fast forwarding.
-            $this->byteIdx += strlen(mb_substr(substr($this->str, $this->byteIdx, 4 * $delta), 0, $delta));
-            $this->charIdx += $delta;
-        } elseif ($delta < 0) {
-            // Rewinding.
-            while ($delta++ < 0) {
-                // We rewind byte by byte and only count characters that are not continuation bytes,
-                // i.e. ASCII characters and first octets of multibyte characters
-                do {
-                    $byte = ord($this->str[--$this->byteIdx]);
-                } while (($byte >= 128) && ($byte < 192));
-
-                --$this->charIdx;
-            }
-        }
-
-        // Fetch the first Unicode character within the next 4 bytes in the string.
-        return mb_substr(substr($this->str, $this->byteIdx, 4), 0, 1);
+        return $this->characters[$offset] ?? null;
     }
 
     /**
@@ -153,14 +96,14 @@ public function offsetUnset(mixed $offset): void
      */
     public function length(): int
     {
-        return $this->charLen;
+        return count($this->characters);
     }
 
     /**
      * Returns the contained string.
      */
     public function __toString(): string
     {
-        return $this->str;
+        return implode('', $this->characters);
     }
 }

tests/TestCase.php

@@ -12,6 +12,7 @@
 use PhpMyAdmin\SqlParser\Token;
 use PhpMyAdmin\SqlParser\TokensList;
 use PhpMyAdmin\SqlParser\Tools\CustomJsonSerializer;
+use PhpMyAdmin\SqlParser\UtfString;
 use PHPUnit\Framework\TestCase as BaseTestCase;
 
 use function file_get_contents;
@@ -95,7 +96,9 @@ public function getData(string $name): array
         $serializedData = file_get_contents('tests/data/' . $name . '.out');
         $this->assertIsString($serializedData);
 
-        $serializer = new CustomJsonSerializer();
+        $serializer = new CustomJsonSerializer(null, [
+            UtfString::class => new UtfStringSerializer(),
+        ]);
         $data = $serializer->unserialize($serializedData);
 
         $this->assertIsArray($data);

tests/UtfStringSerializer.php

@@ -0,0 +1,28 @@
+<?php
+
+declare(strict_types=1);
+
+namespace PhpMyAdmin\SqlParser\Tests;
+
+use PhpMyAdmin\SqlParser\UtfString;
+
+class UtfStringSerializer
+{
+    /**
+     * @return array<string,string>
+     * @psalm-return array{str: string}
+     */
+    public function serialize(UtfString $str): array
+    {
+        return ['str' => (string) $str];
+    }
+
+    /**
+     * @param array<string,string> $data
+     * @psalm-param array{str: string} $data
+     */
+    public function unserialize(array $data): UtfString
+    {
+        return new UtfString($data['str']);
+    }
+}

tests/data/lexer/lexUtf8.out

@@ -6,11 +6,7 @@
         "errors": [],
         "str": {
             "@type": "PhpMyAdmin\\SqlParser\\UtfString",
-            "str": "select * from école",
-            "byteIdx": 19,
-            "charIdx": 18,
-            "byteLen": 20,
-            "charLen": 19
+            "str": "select * from école"
         },
         "len": 19,
         "last": 19,

tests/data/parser/parseCreateProcedure3.out

@@ -6,11 +6,7 @@
         "errors": [],
         "str": {
             "@type": "PhpMyAdmin\\SqlParser\\UtfString",
-            "str": "DELIMITER $$\nCREATE DEFINER=`user`@`localhost` PROCEDURE `multiDBqueryRun_V1`(IN `query` TEXT, IN `table_name_var` VARCHAR(255), IN `columns_used_var` TEXT, IN `where_text_var` TEXT, IN `separator_value_var` VARCHAR(255)) COMMENT 'Query: SingleDB → MultiDB (All DBs) + run it' NOT DETERMINISTIC MODIFIES SQL DATA SQL SECURITY INVOKER BEGIN\nSET @TABLE_NAME = table_name_var;\nSET @WHERE_TEXT = where_text_var;\nSET @COLUMNS_USED = columns_used_var;\nSET @MULTIDB_QUERY = CONCAT('SELECT \"$MULTIDB\" FROM `$MULTIDB`.', @TABLE_NAME, @WHERE_TEXT);\n\n-- EXECUTION --\nCREATE TEMPORARY TABLE `MULTIDB_TEMP_DB_TBL_COLS` AS\nSELECT * FROM (\n  SELECT TABLE_SCHEMA, TABLE_NAME, COLUMN_NAME\n  FROM INFORMATION_SCHEMA.COLUMNS\n  WHERE\n    TABLE_SCHEMA NOT IN('mysql', 'test', 'tmp', 'information_schema', 'sys', 'performance_schema') AND\n    TABLE_NAME = @TABLE_NAME AND\n    FIND_IN_SET(COLUMN_NAME, @COLUMNS_USED)\n) tbl\nGROUP BY\n  TABLE_SCHEMA,\n  TABLE_NAME;\n\nSELECT GROUP_CONCAT(REPLACE(@MULTIDB_QUERY, '$MULTIDB', CONCAT('', TABLE_SCHEMA, '')) SEPARATOR \"\\nUNION ALL\\n\")\nINTO @stmt_sql\nFROM `MULTIDB_TEMP_DB_TBL_COLS`;\n\nPREPARE stmt FROM @stmt_sql;\nEXECUTE stmt;\nDEALLOCATE PREPARE stmt;\nEND",
-            "byteIdx": 1174,
-            "charIdx": 1172,
-            "byteLen": 1175,
-            "charLen": 1173
+            "str": "DELIMITER $$\nCREATE DEFINER=`user`@`localhost` PROCEDURE `multiDBqueryRun_V1`(IN `query` TEXT, IN `table_name_var` VARCHAR(255), IN `columns_used_var` TEXT, IN `where_text_var` TEXT, IN `separator_value_var` VARCHAR(255)) COMMENT 'Query: SingleDB → MultiDB (All DBs) + run it' NOT DETERMINISTIC MODIFIES SQL DATA SQL SECURITY INVOKER BEGIN\nSET @TABLE_NAME = table_name_var;\nSET @WHERE_TEXT = where_text_var;\nSET @COLUMNS_USED = columns_used_var;\nSET @MULTIDB_QUERY = CONCAT('SELECT \"$MULTIDB\" FROM `$MULTIDB`.', @TABLE_NAME, @WHERE_TEXT);\n\n-- EXECUTION --\nCREATE TEMPORARY TABLE `MULTIDB_TEMP_DB_TBL_COLS` AS\nSELECT * FROM (\n  SELECT TABLE_SCHEMA, TABLE_NAME, COLUMN_NAME\n  FROM INFORMATION_SCHEMA.COLUMNS\n  WHERE\n    TABLE_SCHEMA NOT IN('mysql', 'test', 'tmp', 'information_schema', 'sys', 'performance_schema') AND\n    TABLE_NAME = @TABLE_NAME AND\n    FIND_IN_SET(COLUMN_NAME, @COLUMNS_USED)\n) tbl\nGROUP BY\n  TABLE_SCHEMA,\n  TABLE_NAME;\n\nSELECT GROUP_CONCAT(REPLACE(@MULTIDB_QUERY, '$MULTIDB', CONCAT('', TABLE_SCHEMA, '')) SEPARATOR \"\\nUNION ALL\\n\")\nINTO @stmt_sql\nFROM `MULTIDB_TEMP_DB_TBL_COLS`;\n\nPREPARE stmt FROM @stmt_sql;\nEXECUTE stmt;\nDEALLOCATE PREPARE stmt;\nEND"
         },
         "len": 1173,
         "last": 1173,

tests/data/parser/parseCreateProcedure4.out

@@ -6,11 +6,7 @@
         "errors": [],
         "str": {
             "@type": "PhpMyAdmin\\SqlParser\\UtfString",
-            "str": "DELIMITER $$\nCREATE DEFINER=`user`@`localhost` PROCEDURE `multiDBqueryRun_V12`(IN `query` TEXT, IN `table_name_var` VARCHAR(255), IN `columns_used_var` TEXT, IN `where_text_var` TEXT, IN `separator_value_var` VARCHAR(255)) COMMENT 'Query: SingleDB → MultiDB (All DBs) + run it' NOT DETERMINISTIC MODIFIES SQL DATA SQL SECURITY INVOKER BEGIN\nSET @TABLE_NAME = table_name_var;\nSET @WHERE_TEXT = where_text_var;\nSET @COLUMNS_USED = columns_used_var;\nSET @MULTIDB_QUERY = CONCAT('SELECT \"$MULTIDB\" FROM `$MULTIDB`.', @TABLE_NAME, @WHERE_TEXT);\n\n-- EXECUTION --\nCREATE TEMPORARY TABLE `MULTIDB_TEMP_DB_TBL_COLS` AS\nSELECT * FROM (\n  SELECT TABLE_SCHEMA, TABLE_NAME, COLUMN_NAME\n  FROM INFORMATION_SCHEMA.COLUMNS\n  WHERE\n    TABLE_SCHEMA NOT IN('mysql', 'test', 'tmp', 'information_schema', 'sys', 'performance_schema') AND\n    TABLE_NAME = @TABLE_NAME AND\n    FIND_IN_SET(COLUMN_NAME, @COLUMNS_USED)\n) tbl\nGROUP BY\n  TABLE_SCHEMA,\n  TABLE_NAME;\n\nSELECT GROUP_CONCAT(REPLACE(@MULTIDB_QUERY, '$MULTIDB', CONCAT('', TABLE_SCHEMA, '')) SEPARATOR \"\\nUNION ALL\\n\")\nINTO @stmt_sql\nFROM `MULTIDB_TEMP_DB_TBL_COLS`;\n\nPREPARE stmt FROM @stmt_sql;\nEXECUTE stmt;\nDEALLOCATE PREPARE stmt;\nEND$$\n\n--\n-- Functions\n--\nDELIMITER $$\nCREATE DEFINER=`root`@`localhost` FUNCTION `attrParentShiftIds` (`parent_id` TEXT, `option_id_shift` INT, `option_value_id_shift` INT) RETURNS TEXT CHARSET utf8mb4 COLLATE utf8mb4_unicode_520_ci DETERMINISTIC READS SQL DATA SQL SECURITY INVOKER BEGIN\n  DECLARE i INT UNSIGNED DEFAULT 0;\n  DECLARE pair_count INT UNSIGNED;\n  DECLARE result TEXT DEFAULT '';\n\n  DECLARE pair VARCHAR(255) DEFAULT '';\n  DECLARE oid INT DEFAULT '';\n  DECLARE vid INT DEFAULT '';\n\n  SET pair_count = substrCount(parent_id, ',') + 1;\n\n  WHILE i < pair_count DO\n    SET result = CONCAT(result, IF(i <= 0, '', ','));\n\n    SET pair = split(parent_id, ',', i + 1);\n\n    SET oid = split(pair, '-', 1) + option_id_shift;\n    SET vid = split(pair, '-', 2) + option_value_id_shift;\n\n    SET pair = CONCAT(oid, '-', vid);\n    SET result = CONCAT(result, pair);\n\n    SET i = i + 1;\n  END WHILE;\n\n  RETURN result;\nEND$$\n\nDELIMITER $$\nCREATE DEFINER=`user`@`localhost` FUNCTION `split` (`string` TEXT, `delim` TEXT, `n` INT) RETURNS TEXT CHARSET utf8mb4 COLLATE utf8mb4_unicode_520_ci DETERMINISTIC SQL SECURITY INVOKER RETURN IF(\n    (LENGTH(string) - LENGTH(REPLACE(string, delim, ''))) / LENGTH(delim) < n - 1,\n    NULL,\n    SUBSTRING_INDEX(SUBSTRING_INDEX(string, delim, n), delim, -1)\n)$$\n\nDELIMITER $$\nCREATE DEFINER=`root`@`localhost` FUNCTION `substrCount` (`s` VARCHAR(255), `ss` VARCHAR(255)) RETURNS TINYINT(3) UNSIGNED DETERMINISTIC READS SQL DATA SQL SECURITY INVOKER BEGIN\nDECLARE COUNT TINYINT(3) UNSIGNED;\nDECLARE OFFSET_I TINYINT(3) UNSIGNED;\nDECLARE CONTINUE HANDLER FOR SQLSTATE '02000' SET s = NULL;\n\nSET COUNT = 0;\nSET OFFSET_I = 1;\n\nREPEAT\nIF NOT ISNULL(s) AND OFFSET_I > 0 THEN\nSET OFFSET_I = LOCATE(ss, s, OFFSET_I);\nIF OFFSET_I > 0 THEN\nSET COUNT = COUNT + 1;\nSET OFFSET_I = OFFSET_I + 1;\nEND IF;\nEND IF;\nUNTIL ISNULL(s) OR OFFSET_I = 0 END REPEAT;\n\nRETURN COUNT;\nEND$$\n\nDELIMITER ;\n\n",
-            "byteIdx": 3084,
-            "charIdx": 3082,
-            "byteLen": 3085,
-            "charLen": 3083
+            "str": "DELIMITER $$\nCREATE DEFINER=`user`@`localhost` PROCEDURE `multiDBqueryRun_V12`(IN `query` TEXT, IN `table_name_var` VARCHAR(255), IN `columns_used_var` TEXT, IN `where_text_var` TEXT, IN `separator_value_var` VARCHAR(255)) COMMENT 'Query: SingleDB → MultiDB (All DBs) + run it' NOT DETERMINISTIC MODIFIES SQL DATA SQL SECURITY INVOKER BEGIN\nSET @TABLE_NAME = table_name_var;\nSET @WHERE_TEXT = where_text_var;\nSET @COLUMNS_USED = columns_used_var;\nSET @MULTIDB_QUERY = CONCAT('SELECT \"$MULTIDB\" FROM `$MULTIDB`.', @TABLE_NAME, @WHERE_TEXT);\n\n-- EXECUTION --\nCREATE TEMPORARY TABLE `MULTIDB_TEMP_DB_TBL_COLS` AS\nSELECT * FROM (\n  SELECT TABLE_SCHEMA, TABLE_NAME, COLUMN_NAME\n  FROM INFORMATION_SCHEMA.COLUMNS\n  WHERE\n    TABLE_SCHEMA NOT IN('mysql', 'test', 'tmp', 'information_schema', 'sys', 'performance_schema') AND\n    TABLE_NAME = @TABLE_NAME AND\n    FIND_IN_SET(COLUMN_NAME, @COLUMNS_USED)\n) tbl\nGROUP BY\n  TABLE_SCHEMA,\n  TABLE_NAME;\n\nSELECT GROUP_CONCAT(REPLACE(@MULTIDB_QUERY, '$MULTIDB', CONCAT('', TABLE_SCHEMA, '')) SEPARATOR \"\\nUNION ALL\\n\")\nINTO @stmt_sql\nFROM `MULTIDB_TEMP_DB_TBL_COLS`;\n\nPREPARE stmt FROM @stmt_sql;\nEXECUTE stmt;\nDEALLOCATE PREPARE stmt;\nEND$$\n\n--\n-- Functions\n--\nDELIMITER $$\nCREATE DEFINER=`root`@`localhost` FUNCTION `attrParentShiftIds` (`parent_id` TEXT, `option_id_shift` INT, `option_value_id_shift` INT) RETURNS TEXT CHARSET utf8mb4 COLLATE utf8mb4_unicode_520_ci DETERMINISTIC READS SQL DATA SQL SECURITY INVOKER BEGIN\n  DECLARE i INT UNSIGNED DEFAULT 0;\n  DECLARE pair_count INT UNSIGNED;\n  DECLARE result TEXT DEFAULT '';\n\n  DECLARE pair VARCHAR(255) DEFAULT '';\n  DECLARE oid INT DEFAULT '';\n  DECLARE vid INT DEFAULT '';\n\n  SET pair_count = substrCount(parent_id, ',') + 1;\n\n  WHILE i < pair_count DO\n    SET result = CONCAT(result, IF(i <= 0, '', ','));\n\n    SET pair = split(parent_id, ',', i + 1);\n\n    SET oid = split(pair, '-', 1) + option_id_shift;\n    SET vid = split(pair, '-', 2) + option_value_id_shift;\n\n    SET pair = CONCAT(oid, '-', vid);\n    SET result = CONCAT(result, pair);\n\n    SET i = i + 1;\n  END WHILE;\n\n  RETURN result;\nEND$$\n\nDELIMITER $$\nCREATE DEFINER=`user`@`localhost` FUNCTION `split` (`string` TEXT, `delim` TEXT, `n` INT) RETURNS TEXT CHARSET utf8mb4 COLLATE utf8mb4_unicode_520_ci DETERMINISTIC SQL SECURITY INVOKER RETURN IF(\n    (LENGTH(string) - LENGTH(REPLACE(string, delim, ''))) / LENGTH(delim) < n - 1,\n    NULL,\n    SUBSTRING_INDEX(SUBSTRING_INDEX(string, delim, n), delim, -1)\n)$$\n\nDELIMITER $$\nCREATE DEFINER=`root`@`localhost` FUNCTION `substrCount` (`s` VARCHAR(255), `ss` VARCHAR(255)) RETURNS TINYINT(3) UNSIGNED DETERMINISTIC READS SQL DATA SQL SECURITY INVOKER BEGIN\nDECLARE COUNT TINYINT(3) UNSIGNED;\nDECLARE OFFSET_I TINYINT(3) UNSIGNED;\nDECLARE CONTINUE HANDLER FOR SQLSTATE '02000' SET s = NULL;\n\nSET COUNT = 0;\nSET OFFSET_I = 1;\n\nREPEAT\nIF NOT ISNULL(s) AND OFFSET_I > 0 THEN\nSET OFFSET_I = LOCATE(ss, s, OFFSET_I);\nIF OFFSET_I > 0 THEN\nSET COUNT = COUNT + 1;\nSET OFFSET_I = OFFSET_I + 1;\nEND IF;\nEND IF;\nUNTIL ISNULL(s) OR OFFSET_I = 0 END REPEAT;\n\nRETURN COUNT;\nEND$$\n\nDELIMITER ;\n\n"
         },
         "len": 3083,
         "last": 3083,