Compressed string component

marginalia_nu/build.gradle

@@ -106,8 +106,9 @@ dependencies {
 
     implementation group: 'org.yaml', name: 'snakeyaml', version: '1.30'
 
-    implementation 'com.syncthemall:boilerpipe:1.2.2'
     implementation 'com.github.luben:zstd-jni:1.5.2-2'
+    implementation 'org.lz4:lz4-java:1.8.0'
+
     implementation 'com.github.vladimir-bukhtoyarov:bucket4j-core:7.5.0'
     implementation 'de.rototor.jeuclid:jeuclid-core:3.1.14'
 
@@ -126,7 +127,6 @@ dependencies {
     implementation 'org.roaringbitmap:RoaringBitmap:0.9.32'
 
     implementation group: 'mysql', name: 'mysql-connector-java', version: '8.0.29'
-
     implementation 'com.github.Marcono1234:gson-record-type-adapter-factory:0.2.0'
 
     testImplementation 'org.junit.jupiter:junit-jupiter-api:5.8.2'

marginalia_nu/src/main/java/nu/marginalia/util/bigstring/BigString.java

@@ -0,0 +1,17 @@
+package nu.marginalia.util.bigstring;
+
+public interface BigString {
+    static BigString encode(String stringValue) {
+        if (stringValue.length() > 64) {
+            return new CompressedBigString(stringValue);
+        }
+        else {
+            return new PlainBigString(stringValue);
+        }
+    }
+    String decode();
+
+    byte[] getBytes();
+
+    int length();
+}

marginalia_nu/src/main/java/nu/marginalia/util/bigstring/CompressedBigString.java

@@ -0,0 +1,39 @@
+package nu.marginalia.util.bigstring;
+
+import net.jpountz.lz4.LZ4Compressor;
+import net.jpountz.lz4.LZ4Factory;
+import net.jpountz.lz4.LZ4FastDecompressor;
+
+import java.nio.charset.StandardCharsets;
+
+public class CompressedBigString implements BigString {
+    private final int originalSize;
+    private final int length;
+    private final byte[] encoded;
+
+    private static final LZ4Factory lz4Factory = LZ4Factory.fastestInstance();;
+    private static final LZ4Compressor compressor = lz4Factory.fastCompressor();
+    private static final LZ4FastDecompressor decompressor = lz4Factory.fastDecompressor();
+
+    public CompressedBigString(String stringValue) {
+        byte[] byteValue = stringValue.getBytes(StandardCharsets.UTF_16);
+        originalSize = byteValue.length;
+        encoded = compressor.compress(byteValue);
+        length = stringValue.length();
+    }
+
+    @Override
+    public String decode() {
+        return new String(getBytes(), StandardCharsets.UTF_16);
+    }
+
+    @Override
+    public byte[] getBytes() {
+        return decompressor.decompress(encoded, originalSize);
+    }
+
+    @Override
+    public int length() {
+        return length;
+    }
+}

marginalia_nu/src/main/java/nu/marginalia/util/bigstring/PlainBigString.java

@@ -0,0 +1,26 @@
+package nu.marginalia.util.bigstring;
+
+import java.nio.charset.StandardCharsets;
+
+public class PlainBigString implements BigString {
+    private final String value;
+
+    public PlainBigString(String value) {
+        this.value = value;
+    }
+
+    @Override
+    public String decode() {
+        return value;
+    }
+
+    @Override
+    public byte[] getBytes() {
+        return value.getBytes(StandardCharsets.UTF_8);
+    }
+
+    @Override
+    public int length() {
+        return value.length();
+    }
+}