gzip

src/main/java/eu/dnetlib/apps/oai/OaiService.java

@@ -23,6 +23,7 @@ import eu.dnetlib.apps.oai.domain.OaiPage;
 import eu.dnetlib.apps.oai.domain.OaiRecord;
 import eu.dnetlib.apps.oai.domain.OaiSet;
 import eu.dnetlib.apps.oai.utils.DateUtils;
+import eu.dnetlib.apps.oai.utils.GzipUtils;
 import eu.dnetlib.apps.oai.utils.XsltTransformerFactory;
 
 @Service
@@ -136,9 +137,11 @@ public class OaiService {
 	private RowMapper<OaiRecord> rowMapper(final String metadataPrefix) {
 		final Function<String, String> mapper = prepareXsltMapper(metadataPrefix);
 		return (rs, rowNum) -> {
+			final String xml = GzipUtils.decompress(rs.getBytes("body"));
+
 			final OaiRecord r = new OaiRecord();
 			r.setId(rs.getString("id"));
-			r.setBody(mapper != null ? mapper.apply(rs.getString("body")) : rs.getString("body"));
+			r.setBody(mapper != null ? mapper.apply(xml) : xml);
 			r.setDate(Instant.ofEpochMilli(rs.getLong("date"))
 				.atZone(ZoneId.systemDefault())
 				.toLocalDateTime());

src/main/java/eu/dnetlib/apps/oai/utils/GzipUtils.java

@@ -0,0 +1,37 @@
+package eu.dnetlib.apps.oai.utils;
+
+import java.io.ByteArrayInputStream;
+import java.io.ByteArrayOutputStream;
+import java.io.IOException;
+import java.util.zip.GZIPInputStream;
+import java.util.zip.GZIPOutputStream;
+
+import org.apache.commons.io.IOUtils;
+import org.apache.commons.lang3.StringUtils;
+
+public class GzipUtils {
+
+	public static byte[] compress(final String data) {
+		if (StringUtils.isBlank(data)) { return null; }
+
+		try (final ByteArrayOutputStream bos = new ByteArrayOutputStream(data.length());
+			final GZIPOutputStream gzip = new GZIPOutputStream(bos)) {
+			gzip.write(data.getBytes());
+			gzip.flush();
+			return bos.toByteArray();
+		} catch (final IOException e) {
+			throw new RuntimeException("error in gzip", e);
+		}
+	}
+
+	public static String decompress(final byte[] bytes) {
+		if (bytes == null || bytes.length == 0) { return null; }
+		try (final ByteArrayInputStream bis = new ByteArrayInputStream(bytes);
+			final GZIPInputStream gis = new GZIPInputStream(bis)) {
+			return IOUtils.toString(gis, "UTF-8");
+		} catch (final IOException e) {
+			throw new RuntimeException("error in gunzip", e);
+		}
+	}
+
+}

src/main/resources/sql/schema.sql

@@ -1,6 +1,6 @@
 CREATE TABLE oai_data(
 	id      text PRIMARY KEY,
-	body    text,
+	body    bytea,
 	date    timestamp NOT NULL DEFAULT now(),
 	sets    text[]    NOT NULL DEFAULT '{}'
 );