Re-implement ORCRecordReader

- Support batch read
- Support most value types
- Support read only required fields
- Enhance tests to cover most value types

pinot-common/src/main/java/org/apache/pinot/common/utils/StringUtil.java

@@ -22,6 +22,7 @@
 import org.apache.commons.lang.StringUtils;
 
 
+// TODO: Use pinot-spi StringUtils instead
 public class StringUtil {
   private static final char NULL_CHARACTER = '\0';
   private static final String charSet = "UTF-8";

pinot-plugins/pinot-input-format/pinot-csv/src/test/java/org/apache/pinot/plugin/inputformat/csv/CSVRecordExtractorTest.java

@@ -21,20 +21,18 @@
 import java.io.File;
 import java.io.FileWriter;
 import java.io.IOException;
-import java.util.ArrayList;
 import java.util.Collection;
 import java.util.List;
 import java.util.Map;
 import org.apache.commons.csv.CSVFormat;
 import org.apache.commons.csv.CSVPrinter;
 import org.apache.commons.lang3.StringUtils;
-import org.apache.pinot.spi.data.Schema;
 import org.apache.pinot.spi.data.readers.AbstractRecordExtractorTest;
-import org.apache.pinot.spi.data.readers.AbstractRecordReaderTest;
 import org.apache.pinot.spi.data.readers.GenericRow;
 import org.apache.pinot.spi.data.readers.RecordReader;
 import org.testng.Assert;
 
+
 /**
  * Tests the {@link CSVRecordExtractor} using a schema containing groovy transform functions
  */
@@ -86,7 +84,7 @@ protected void checkValue(Map<String, Object> inputRecord, GenericRow genericRow
       Object expectedValue = entry.getValue();
       Object actualValue = genericRow.getValue(columnName);
       if (expectedValue instanceof Collection) {
-        List expectedArray = (ArrayList) expectedValue;
+        List expectedArray = (List) expectedValue;
         if (expectedArray.size() == 1) {
           // in CSV, cannot differentiate between array with single element vs actual single element
           Assert.assertEquals(actualValue, String.valueOf(expectedArray.get(0)));

pinot-plugins/pinot-input-format/pinot-orc/pom.xml

@@ -40,30 +40,14 @@
     <dependency>
       <groupId>org.apache.orc</groupId>
       <artifactId>orc-core</artifactId>
-      <exclusions>
-        <exclusion>
-          <groupId>org.apache.hadoop</groupId>
-          <artifactId>hadoop-annotations</artifactId>
-        </exclusion>
-        <exclusion>
-          <groupId>jdk.tools</groupId>
-          <artifactId>jdk.tools</artifactId>
-        </exclusion>
-      </exclusions>
     </dependency>
     <dependency>
-      <groupId>org.apache.orc</groupId>
-      <artifactId>orc-mapreduce</artifactId>
-      <exclusions>
-        <exclusion>
-          <groupId>org.apache.hadoop</groupId>
-          <artifactId>hadoop-yarn-common</artifactId>
-        </exclusion>
-        <exclusion>
-          <groupId>jdk.tools</groupId>
-          <artifactId>jdk.tools</artifactId>
-        </exclusion>
-      </exclusions>
+      <groupId>org.apache.hadoop</groupId>
+      <artifactId>hadoop-common</artifactId>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.hadoop</groupId>
+      <artifactId>hadoop-hdfs</artifactId>
     </dependency>
   </dependencies>
 </project>