[HUDI-764] [HUDI-765] ORC reader writer Implementation (#2999)

Co-authored-by: Qingyun (Teresa) Kang <kteresa@uber.com>

hudi-common/src/test/java/org/apache/hudi/common/util/TestAvroOrcUtils.java

@@ -0,0 +1,76 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.hudi.common.util;
+
+import static org.apache.hudi.common.testutils.HoodieTestDataGenerator.AVRO_SCHEMA;
+
+import java.util.Arrays;
+import java.util.List;
+import org.apache.avro.Schema;
+import org.apache.hudi.common.testutils.HoodieCommonTestHarness;
+import org.apache.orc.TypeDescription;
+
+import org.junit.jupiter.params.ParameterizedTest;
+import org.junit.jupiter.params.provider.Arguments;
+import org.junit.jupiter.params.provider.MethodSource;
+
+import static org.junit.jupiter.api.Assertions.assertEquals;
+
+public class TestAvroOrcUtils extends HoodieCommonTestHarness {
+
+  public static List<Arguments> testCreateOrcSchemaArgs() {
+    // the ORC schema is constructed in the order as AVRO_SCHEMA:
+    // TRIP_SCHEMA_PREFIX, EXTRA_TYPE_SCHEMA, MAP_TYPE_SCHEMA, FARE_NESTED_SCHEMA, TIP_NESTED_SCHEMA, TRIP_SCHEMA_SUFFIX
+    // The following types are tested:
+    // DATE, DECIMAL, LONG, INT, BYTES, ARRAY, RECORD, MAP, STRING, FLOAT, DOUBLE
+    TypeDescription orcSchema = TypeDescription.fromString("struct<"
+        + "timestamp:bigint,_row_key:string,rider:string,driver:string,begin_lat:double,"
+        + "begin_lon:double,end_lat:double,end_lon:double,"
+        + "distance_in_meters:int,seconds_since_epoch:bigint,weight:float,nation:binary,"
+        + "current_date:date,current_ts:bigint,height:decimal(10,6),"
+        + "city_to_state:map<string,string>,"
+        + "fare:struct<amount:double,currency:string>,"
+        + "tip_history:array<struct<amount:double,currency:string>>,"
+        + "_hoodie_is_deleted:boolean>");
+
+    // Tests the types FIXED, UNION
+    String structField = "{\"type\":\"record\", \"name\":\"fare\",\"fields\": "
+        + "[{\"name\": \"amount\",\"type\": \"double\"},{\"name\": \"currency\", \"type\": \"string\"}]}";
+    Schema avroSchemaWithMoreTypes = new Schema.Parser().parse(
+        "{\"type\": \"record\"," + "\"name\": \"triprec\"," + "\"fields\": [ "
+            + "{\"name\" : \"age\", \"type\":{\"type\": \"fixed\", \"size\": 16, \"name\": \"fixedField\" }},"
+            + "{\"name\" : \"height\", \"type\": [\"int\", \"null\"] },"
+            + "{\"name\" : \"id\", \"type\": [\"int\", \"string\"] },"
+            + "{\"name\" : \"fare\", \"type\": [" + structField + ", \"null\"] }]}");
+    TypeDescription orcSchemaWithMoreTypes = TypeDescription.fromString(
+        "struct<age:binary,height:int,id:uniontype<int,string>,fare:struct<amount:double,currency:string>>");
+
+    return Arrays.asList(
+        Arguments.of(AVRO_SCHEMA, orcSchema),
+        Arguments.of(avroSchemaWithMoreTypes, orcSchemaWithMoreTypes)
+    );
+  }
+
+  @ParameterizedTest
+  @MethodSource("testCreateOrcSchemaArgs")
+  public void testCreateOrcSchema(Schema avroSchema, TypeDescription orcSchema) {
+    TypeDescription convertedSchema = AvroOrcUtils.createOrcSchema(avroSchema);
+    assertEquals(orcSchema, convertedSchema);
+  }
+}

hudi-common/src/test/java/org/apache/hudi/common/util/TestOrcReaderIterator.java

@@ -0,0 +1,92 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.hudi.common.util;
+
+import org.apache.avro.Schema;
+import org.apache.avro.generic.GenericRecord;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.Path;
+import org.apache.orc.CompressionKind;
+import org.apache.orc.OrcFile;
+import org.apache.orc.Reader;
+import org.apache.orc.RecordReader;
+import org.apache.orc.TypeDescription;
+import org.apache.orc.Writer;
+import org.apache.orc.storage.ql.exec.vector.BytesColumnVector;
+import org.apache.orc.storage.ql.exec.vector.LongColumnVector;
+import org.apache.orc.storage.ql.exec.vector.VectorizedRowBatch;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Test;
+
+import java.io.File;
+import java.nio.charset.StandardCharsets;
+import java.util.Iterator;
+
+import static org.apache.hudi.common.testutils.SchemaTestUtil.getSchemaFromResource;
+import static org.junit.jupiter.api.Assertions.assertEquals;
+
+public class TestOrcReaderIterator {
+  private final Path filePath = new Path(System.getProperty("java.io.tmpdir") + "/f1_1-0-1_000.orc");
+
+  @BeforeEach
+  @AfterEach
+  public void clearTempFile() {
+    File file = new File(filePath.toString());
+    if (file.exists()) {
+      file.delete();
+    }
+  }
+
+  @Test
+  public void testOrcIteratorReadData() throws Exception {
+    final Configuration conf = new Configuration();
+    Schema avroSchema = getSchemaFromResource(TestOrcReaderIterator.class, "/simple-test.avsc");
+    TypeDescription orcSchema = AvroOrcUtils.createOrcSchema(avroSchema);
+    OrcFile.WriterOptions options = OrcFile.writerOptions(conf).setSchema(orcSchema).compress(CompressionKind.ZLIB);
+    Writer writer = OrcFile.createWriter(filePath, options);
+    VectorizedRowBatch batch = orcSchema.createRowBatch();
+    BytesColumnVector nameColumns = (BytesColumnVector) batch.cols[0];
+    LongColumnVector numberColumns = (LongColumnVector) batch.cols[1];
+    BytesColumnVector colorColumns = (BytesColumnVector) batch.cols[2];
+    for (int r = 0; r < 5; ++r) {
+      int row = batch.size++;
+      byte[] name = ("name" + r).getBytes(StandardCharsets.UTF_8);
+      nameColumns.setVal(row, name);
+      byte[] color = ("color" + r).getBytes(StandardCharsets.UTF_8);
+      colorColumns.setVal(row, color);
+      numberColumns.vector[row] = r;
+    }
+    writer.addRowBatch(batch);
+    writer.close();
+
+    Reader reader = OrcFile.createReader(filePath, OrcFile.readerOptions(conf));
+    RecordReader recordReader = reader.rows(new Reader.Options(conf).schema(orcSchema));
+    Iterator<GenericRecord> iterator = new OrcReaderIterator<>(recordReader, avroSchema, orcSchema);
+    int recordCount = 0;
+    while (iterator.hasNext()) {
+      GenericRecord record = iterator.next();
+      assertEquals("name" + recordCount, record.get("name").toString());
+      assertEquals("color" + recordCount, record.get("favorite_color").toString());
+      assertEquals(recordCount, record.get("favorite_number"));
+      recordCount++;
+    }
+    assertEquals(5, recordCount);
+  }
+}

hudi-common/src/test/java/org/apache/hudi/io/storage/TestHoodieFileReaderFactory.java

@@ -44,11 +44,16 @@ public class TestHoodieFileReaderFactory {
     HoodieFileReader<IndexedRecord> parquetReader = HoodieFileReaderFactory.getFileReader(hadoopConf, parquetPath);
     assertTrue(parquetReader instanceof HoodieParquetReader);
 
-    // other file format exception.
+    // log file format.
     final Path logPath = new Path("/partition/path/f.b51192a8-574b-4a85-b246-bcfec03ac8bf_100.log.2_1-0-1");
     final Throwable thrown = assertThrows(UnsupportedOperationException.class, () -> {
       HoodieFileReader<IndexedRecord> logWriter = HoodieFileReaderFactory.getFileReader(hadoopConf, logPath);
     }, "should fail since log storage reader is not supported yet.");
     assertTrue(thrown.getMessage().contains("format not supported yet."));
+
+    // Orc file format.
+    final Path orcPath = new Path("/partition/path/f1_1-0-1_000.orc");
+    HoodieFileReader<IndexedRecord> orcReader = HoodieFileReaderFactory.getFileReader(hadoopConf, orcPath);
+    assertTrue(orcReader instanceof HoodieOrcReader);
   }
 }