automatically convert strings in Java Edition nbt to utf-8

Author: KurtThiemann

src/Deserializer/BedrockEditionNbtDeserializer.php

@@ -4,6 +4,7 @@
 
 use Aternos\Nbt\MachineByteOrder;
 use Aternos\Nbt\NbtFormat;
+use Aternos\Nbt\String\StringDataFormatException;
 use pocketmine\utils\Binary;
 
 class BedrockEditionNbtDeserializer extends NbtDeserializer
@@ -88,4 +89,18 @@ public function readDouble(): DeserializerFloatReadResult
         $raw = $this->getReader()->read(8);
         return new DeserializerFloatReadResult(Binary::readLDouble($raw), $raw);
     }
+
+    /**
+     * @inheritDoc
+     * @throws StringDataFormatException
+     */
+    public function readString(): DeserializerStringReadResult
+    {
+        $length = $this->readStringLengthPrefix();
+        $val = $this->getReader()->read($length->getValue());
+        if(strlen($val) !== $length->getValue()){
+            throw new StringDataFormatException("Failed to read string: expected length " . $length->getValue() . ", got " . strlen($val));
+        }
+        return new DeserializerStringReadResult($val, $length->getRawData() . $val);
+    }
 }

src/Deserializer/DeserializerStringReadResult.php

@@ -0,0 +1,35 @@
+<?php
+
+namespace Aternos\Nbt\Deserializer;
+
+class DeserializerStringReadResult extends DeserializerReadResult
+{
+    public function __construct(protected string $value, string $rawData)
+    {
+        parent::__construct($rawData);
+    }
+
+    /**
+     * @return string
+     */
+    public function getValue(): string
+    {
+        return $this->value;
+    }
+
+    /**
+     * @return int
+     */
+    public function getRawLength(): int
+    {
+        return strlen($this->getRawData());
+    }
+
+    /**
+     * @return int
+     */
+    public function getLength(): int
+    {
+        return strlen($this->value);
+    }
+}

src/Deserializer/JavaEditionNbtDeserializer.php

@@ -4,6 +4,8 @@
 
 use Aternos\Nbt\MachineByteOrder;
 use Aternos\Nbt\NbtFormat;
+use Aternos\Nbt\String\JavaEncoding;
+use Aternos\Nbt\String\StringDataFormatException;
 use pocketmine\utils\Binary;
 
 class JavaEditionNbtDeserializer extends NbtDeserializer
@@ -88,4 +90,18 @@ public function readDouble(): DeserializerFloatReadResult
         $raw = $this->getReader()->read(8);
         return new DeserializerFloatReadResult(Binary::readDouble($raw), $raw);
     }
+
+    /**
+     * @inheritDoc
+     * @throws StringDataFormatException
+     */
+    public function readString(): DeserializerStringReadResult
+    {
+        $length = $this->readStringLengthPrefix();
+        $val = $this->getReader()->read($length->getValue());
+        if(strlen($val) !== $length->getValue()){
+            throw new StringDataFormatException("Failed to read string: expected length " . $length->getValue() . ", got " . strlen($val));
+        }
+        return new DeserializerStringReadResult(JavaEncoding::getInstance()->decode($val), $length->getRawData() . $val);
+    }
 }

src/Deserializer/NbtDeserializer.php

@@ -54,6 +54,11 @@ abstract public function readFloat(): DeserializerFloatReadResult;
      */
     abstract public function readDouble(): DeserializerFloatReadResult;
 
+    /**
+     * @return DeserializerStringReadResult
+     */
+    abstract public function readString(): DeserializerStringReadResult;
+
     /**
      * @return int
      */

src/Serializer/BedrockEditionNbtSerializer.php

@@ -85,7 +85,17 @@ public function writeFloat(float $value): static
      */
     public function writeDouble(float $value): static
     {
-        $this->writer->write(Binary::writeLDouble($value));
+        $this->getWriter()->write(Binary::writeLDouble($value));
+        return $this;
+    }
+
+    /**
+     * @inheritDoc
+     */
+    public function writeString(string $value): static
+    {
+        $this->writeStringLengthPrefix(strlen($value));
+        $this->getWriter()->write($value);
         return $this;
     }
 }

src/Serializer/JavaEditionNbtSerializer.php

@@ -4,6 +4,7 @@
 
 use Aternos\Nbt\MachineByteOrder;
 use Aternos\Nbt\NbtFormat;
+use Aternos\Nbt\String\JavaEncoding;
 use pocketmine\utils\Binary;
 
 class JavaEditionNbtSerializer extends NbtSerializer
@@ -85,7 +86,18 @@ public function writeFloat(float $value): static
      */
     public function writeDouble(float $value): static
     {
-        $this->writer->write(Binary::writeDouble($value));
+        $this->getWriter()->write(Binary::writeDouble($value));
+        return $this;
+    }
+
+    /**
+     * @inheritDoc
+     */
+    public function writeString(string $value): static
+    {
+        $encoded = JavaEncoding::getInstance()->encode($value);
+        $this->writeStringLengthPrefix(strlen($encoded));
+        $this->getWriter()->write($encoded);
         return $this;
     }
 }

src/Serializer/NbtSerializer.php

@@ -62,6 +62,12 @@ abstract public function writeFloat(float $value): static;
      */
     abstract public function writeDouble(float $value): static;
 
+    /**
+     * @param string $value
+     * @return $this
+     */
+    abstract public function writeString(string $value): static;
+
     /**
      * @return int
      */

src/String/JavaEncoding.php

@@ -60,7 +60,7 @@ public function encode(string $string, string $sourceEncoding = "UTF-8"): string
             }
 
             $result .= chr(0xED);
-            $result .= chr(0xA0 | (($c >> 0x10) & 0x0F));
+            $result .= chr(0xA0 | ((($c >> 0x10) & 0x0F) - 1));
             $result .= chr(0x80 | (($c >> 0x0A) & 0x3f));
             $result .= chr(0xED);
             $result .= chr(0xb0 | (($c >> 0x06) & 0x0f));

src/Tag/StringTag.php

@@ -4,8 +4,6 @@
 
 use Aternos\Nbt\IO\Reader\Reader;
 use Aternos\Nbt\IO\Writer\Writer;
-use Aternos\Nbt\String\JavaEncoding;
-use Aternos\Nbt\String\StringDataFormatException;
 use Exception;
 
 class StringTag extends Tag
@@ -22,16 +20,6 @@ public function getValue(): string
         return $this->value;
     }
 
-    /**
-     * @param string $encoding
-     * @return string
-     * @throws StringDataFormatException
-     */
-    public function getDecodedValue(string $encoding = "UTF-8"): string
-    {
-        return JavaEncoding::getInstance()->decode($this->value, $encoding);
-    }
-
     /**
      * @param string $value
      * @return StringTag
@@ -42,17 +30,6 @@ public function setValue(string $value): StringTag
         return $this;
     }
 
-    /**
-     * @param string $value
-     * @param string $encoding
-     * @return StringTag
-     */
-    public function setDecodedValue(string $value, string $encoding = "UTF-8"): StringTag
-    {
-        $this->value = JavaEncoding::getInstance()->encode($value, $encoding);
-        return $this;
-    }
-
     /**
      * @return int
      */
@@ -71,8 +48,7 @@ public function writeContent(Writer $writer): static
         if ($length > 0xffff) {
             throw new Exception("String exceeds maximum length of " . 0xffff . " characters");
         }
-        $writer->getSerializer()->writeStringLengthPrefix($length);
-        $writer->write($this->value);
+        $writer->getSerializer()->writeString($this->value);
         return $this;
     }
 
@@ -81,8 +57,7 @@ public function writeContent(Writer $writer): static
      */
     protected function readContent(Reader $reader): static
     {
-        $length = $reader->getDeserializer()->readStringLengthPrefix()->getValue();
-        $this->value = $reader->read($length);
+        $this->value = $reader->getDeserializer()->readString()->getValue();
         return $this;
     }
 

src/Tag/Tag.php

@@ -159,12 +159,8 @@ public function getType(): int
     public function read(Reader $reader, bool $named = true): static
     {
         if ($named && static::canBeNamed()) {
-            $nameLength = $reader->getDeserializer()->readStringLengthPrefix()->getValue();
-            $name = $reader->read($nameLength);
-            if (strlen($name) !== $nameLength) {
-                throw new Exception("Failed to read name of " . static::class);
-            }
-            $this->setName($name);
+            $name = $reader->getDeserializer()->readString();
+            $this->setName($name->getValue());
         }
         return $this->readContent($reader);
     }
@@ -180,12 +176,8 @@ public static function readRaw(Reader $reader, TagOptions $options, bool $named
     {
         $result = "";
         if ($named && static::canBeNamed()) {
-            $nameLength = $reader->getDeserializer()->readStringLengthPrefix();
-            $name = $reader->read($nameLength->getValue());
-            if (strlen($name) !== $nameLength->getValue()) {
-                throw new Exception("Failed to read name of " . static::class);
-            }
-            $result .= $nameLength->getRawData() . $name;
+            $name = $reader->getDeserializer()->readString();
+            $result .= $name->getRawData();
         }
         $result .= static::readContentRaw($reader, $options);
         return $result;
@@ -210,8 +202,7 @@ public function writeData(Writer $writer, bool $named = true): static
             if (is_null($name)) {
                 throw new Exception("Cannot write named tag, because tag does not have a name value");
             }
-            $serializer->writeStringLengthPrefix(strlen($this->getName()));
-            $writer->write($this->getName());
+            $serializer->writeString($this->getName());
         }
         $this->writeContent($writer);
         $this->isBeingSerialized = false;