andreacavalli/data-generator-runtime
Archived
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Only accept mappable and valid UTF-8 during serialization

Browse Source
This commit is contained in:
Andrea Cavalli 2021-10-09 00:38:42 +02:00
parent a303067976
commit d9de99a634
1 changed files with 39 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
src/main/java/it/cavallium/data/generator/nativedata/StringSerializer.java
View File

@ -4,18 +4,48 @@ import it.cavallium.data.generator.DataSerializer;
import java.io.DataInput; import java.io.DataInput;
import java.io.DataOutput; import java.io.DataOutput;
import java.io.IOException; import java.io.IOException;
import java.nio.ByteBuffer;
import java.nio.CharBuffer;
import java.nio.channels.Channels;
import java.nio.charset.CharacterCodingException;
import java.nio.charset.CharsetDecoder;
import java.nio.charset.CharsetEncoder;
import java.nio.charset.CodingErrorAction;
import java.nio.charset.MalformedInputException;
import java.nio.charset.StandardCharsets; import java.nio.charset.StandardCharsets;
import java.nio.charset.UnmappableCharacterException;
import org.jetbrains.annotations.NotNull; import org.jetbrains.annotations.NotNull;
public class StringSerializer implements DataSerializer<String> { public class StringSerializer implements DataSerializer<String> {
public static final StringSerializer INSTANCE = new StringSerializer(); public static final StringSerializer INSTANCE = new StringSerializer();
private static final ThreadLocal<CharsetEncoder> UTF8_ENCODER = ThreadLocal.withInitial(() -> StandardCharsets.UTF_8
.newEncoder()
.onUnmappableCharacter(CodingErrorAction.REPORT)
.onMalformedInput(CodingErrorAction.REPORT)
);
private static final ThreadLocal<CharsetDecoder> UTF8_DECODER = ThreadLocal.withInitial(() -> StandardCharsets.UTF_8
.newDecoder()
.onUnmappableCharacter(CodingErrorAction.REPORT)
.onMalformedInput(CodingErrorAction.REPORT)
);
@Override @Override
public void serialize(DataOutput dataOutput, @NotNull String data) throws IOException { public void serialize(DataOutput dataOutput, @NotNull String data) throws IOException {
byte[] bytes = data.getBytes(StandardCharsets.UTF_8); try {
dataOutput.writeInt(bytes.length); var bytes = UTF8_ENCODER.get().reset().encode(CharBuffer.wrap(data));
dataOutput.write(bytes);
dataOutput.writeInt(bytes.limit());
if (bytes.hasArray()) {
dataOutput.write(bytes.array(), bytes.arrayOffset(), bytes.limit());
} else {
while (bytes.hasRemaining()) {
dataOutput.writeByte(bytes.get());
}
}
} catch (IllegalStateException | CharacterCodingException ex) {
throw new IOException("Can't encode this UTF-8 string", ex);
}
} }
@NotNull @NotNull
@ -23,6 +53,11 @@ public class StringSerializer implements DataSerializer<String> {
public String deserialize(DataInput dataInput) throws IOException { public String deserialize(DataInput dataInput) throws IOException {
byte[] bytes = new byte[dataInput.readInt()]; byte[] bytes = new byte[dataInput.readInt()];
dataInput.readFully(bytes); dataInput.readFully(bytes);
return new String(bytes, StandardCharsets.UTF_8); try {
CharBuffer decoded = UTF8_DECODER.get().reset().decode(ByteBuffer.wrap(bytes));
return decoded.toString();
} catch (IllegalStateException | CharacterCodingException ex) {
throw new IOException("Can't decode this UTF-8 string", ex);
}
} }
} }