ATLAS-3953: Export: ZipSink: Specify character endcoding when writing to ZIP file.

repository/src/main/java/org/apache/atlas/repository/impexp/HdfsPathEntityCreator.java

@@ -59,7 +59,7 @@ public class HdfsPathEntityCreator {
     }
 
     public AtlasEntity.AtlasEntityWithExtInfo getCreateEntity(AtlasObjectId item) throws AtlasBaseException {
-        if(!item.getUniqueAttributes().containsKey(HDFS_PATH_ATTRIBUTE_NAME_PATH)) {
+        if(item.getUniqueAttributes() == null || !item.getUniqueAttributes().containsKey(HDFS_PATH_ATTRIBUTE_NAME_PATH)) {
             return null;
         }
 

repository/src/main/java/org/apache/atlas/repository/impexp/ZipSink.java

@@ -22,12 +22,13 @@ import org.apache.atlas.model.impexp.AtlasExportResult;
 import org.apache.atlas.model.instance.AtlasEntity;
 import org.apache.atlas.model.typedef.AtlasTypesDef;
 import org.apache.atlas.type.AtlasType;
-import org.apache.commons.lang.StringUtils;
+import org.apache.commons.io.IOUtils;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
 import java.io.IOException;
 import java.io.OutputStream;
+import java.nio.charset.StandardCharsets;
 import java.util.HashSet;
 import java.util.List;
 import java.util.Set;
@@ -109,24 +110,7 @@ public class ZipSink {
     }
 
     private void writeBytes(String payload) throws IOException {
-        splitAndWriteBytes(payload, 10 * 1024 * 1024, zipOutputStream);
-    }
-
-    static void splitAndWriteBytes(String msg, int bufferSize, OutputStream os) throws IOException {
-        int numberOfSplits = (int) Math.ceil(((float) msg.length()) / bufferSize);
-        if (numberOfSplits == 0) {
-            numberOfSplits = 1;
-        } else {
-            if (LOG.isDebugEnabled()) {
-                LOG.info("ZipSink: number of splits: {}", numberOfSplits);
-            }
-        }
-
-        for (int i = 0, start = 0; i < numberOfSplits; i++, start += bufferSize) {
-            int end = bufferSize + start;
-            String s = StringUtils.substring(msg, start, end);
-            os.write(s.getBytes());
-        }
+        IOUtils.copy(IOUtils.toInputStream(payload, StandardCharsets.UTF_8), zipOutputStream);
     }
 
     public boolean hasEntity(String guid) {

repository/src/test/java/org/apache/atlas/repository/impexp/ZipSinkTest.java

@@ -30,15 +30,16 @@ import org.testng.annotations.Test;
 import java.io.ByteArrayInputStream;
 import java.io.ByteArrayOutputStream;
 import java.io.IOException;
-import java.io.OutputStream;
 import java.util.ArrayList;
 import java.util.Arrays;
 import java.util.List;
 import java.util.zip.ZipEntry;
 import java.util.zip.ZipInputStream;
 
-import static org.mockito.Mockito.mock;
-import static org.testng.Assert.*;
+import static org.testng.Assert.assertEquals;
+import static org.testng.Assert.assertFalse;
+import static org.testng.Assert.assertNotNull;
+import static org.testng.Assert.assertTrue;
 
 public class ZipSinkTest {
     private ByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream();
@@ -47,23 +48,6 @@ public class ZipSinkTest {
     private AtlasExportResult defaultExportResult;
     private String knownEntityGuidFormat = "111-222-333-%s";
 
-    private class MockOutputStream extends OutputStream {
-        List<byte[]> collected = new ArrayList<>();
-
-        @Override
-        public void write(int b) throws IOException {
-        }
-
-        @Override
-        public void write(byte[] bytes) {
-            collected.add(bytes);
-        }
-
-        public List<byte[]> getCollected()  {
-            return collected;
-        }
-    };
-
     private void initZipSinkWithExportOrder() throws AtlasBaseException {
         zipSink = new ZipSink(byteArrayOutputStream);
         zipSink.setExportOrder(defaultExportOrder);
@@ -146,7 +130,6 @@ public class ZipSinkTest {
 
     @Test
     public void zipWithExactlyTwoEntries_ContentsVerified() throws AtlasBaseException, IOException {
-
         ByteArrayOutputStream byteOutputStream = new ByteArrayOutputStream();
         useZipSinkToCreateEntries(byteOutputStream);
 
@@ -225,26 +208,4 @@ public class ZipSinkTest {
         String json = AtlasType.toJson(defaultExportResult);
         return json.equals(s);
     }
-
-    @Test
-    public void splitTest() throws IOException {
-        assertSplit("ABCDEFGHIJKLMNOPQRSTUVWXYZ01", 7, new String[] {"ABCDEFG", "HIJKLMN", "OPQRSTU", "VWXYZ01"});
-        assertSplit("ABCDEFGHIJKLMNOPQRSTUVWXYZ", 7, new String[] {"ABCDEFG", "HIJKLMN", "OPQRSTU", "VWXYZ"});
-    }
-
-    private void assertSplit(String msg, int bufferSize, String[] splits) throws IOException {
-        MockOutputStream os = getOutputStream();
-        ZipSink.splitAndWriteBytes(msg, bufferSize, os);
-        assertEquals(os.getCollected().size(), splits.length);
-
-        for (int i = 0; i < os.collected.size(); i++) {
-            byte[] bytes = os.getCollected().get(i);
-            String s = new String(bytes);
-            assertEquals(s, splits[i]);
-        }
-    }
-
-    private MockOutputStream getOutputStream() {
-        return new MockOutputStream();
-    }
 }