[
https://issues.apache.org/jira/browse/DRILL-7554?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17096916#comment-17096916
]
ASF GitHub Bot commented on DRILL-7554:
---------------------------------------
cgivre commented on a change in pull request #1962:
URL: https://github.com/apache/drill/pull/1962#discussion_r418241396
##########
File path:
contrib/format-ltsv/src/main/java/org/apache/drill/exec/store/ltsv/LTSVFormatPlugin.java
##########
@@ -15,78 +15,77 @@
* See the License for the specific language governing permissions and
* limitations under the License.
*/
+
package org.apache.drill.exec.store.ltsv;
-import org.apache.drill.common.expression.SchemaPath;
import org.apache.drill.common.logical.StoragePluginConfig;
-import org.apache.drill.exec.ops.FragmentContext;
-import org.apache.drill.exec.planner.common.DrillStatsTable.TableStatistics;
+import org.apache.drill.common.types.TypeProtos;
+import org.apache.drill.common.types.Types;
+import
org.apache.drill.exec.physical.impl.scan.file.FileScanFramework.FileSchemaNegotiator;
+import
org.apache.drill.exec.physical.impl.scan.file.FileScanFramework.FileReaderFactory;
+import
org.apache.drill.exec.physical.impl.scan.file.FileScanFramework.FileScanBuilder;
+import org.apache.drill.exec.physical.impl.scan.framework.ManagedReader;
import org.apache.drill.exec.proto.UserBitShared;
import org.apache.drill.exec.server.DrillbitContext;
-import org.apache.drill.exec.store.RecordReader;
-import org.apache.drill.exec.store.RecordWriter;
-import org.apache.drill.exec.store.dfs.DrillFileSystem;
+import org.apache.drill.exec.server.options.OptionManager;
import org.apache.drill.exec.store.dfs.easy.EasyFormatPlugin;
-import org.apache.drill.exec.store.dfs.easy.EasyWriter;
-import org.apache.drill.exec.store.dfs.easy.FileWork;
+import org.apache.drill.exec.store.dfs.easy.EasySubScan;
+import org.apache.drill.shaded.guava.com.google.common.collect.Lists;
import org.apache.hadoop.conf.Configuration;
-import org.apache.hadoop.fs.FileSystem;
-import org.apache.hadoop.fs.Path;
-
-import java.util.List;
+/**
+ * Enables Drill to query data in Labeled Tab Separated Values (LTSV) format.
+ * <a href="http://ltsv.org"; target="_blank">LTSV Spec</a>
+ */
public class LTSVFormatPlugin extends EasyFormatPlugin<LTSVFormatPluginConfig>
{
- private static final boolean IS_COMPRESSIBLE = true;
-
private static final String DEFAULT_NAME = "ltsv";
- public LTSVFormatPlugin(String name, DrillbitContext context, Configuration
fsConf, StoragePluginConfig storageConfig) {
- this(name, context, fsConf, storageConfig, new
LTSVFormatPluginConfig(null));
- }
+ public static class LTSVReaderFactory extends FileReaderFactory {
+ private final LTSVFormatPluginConfig config;
- public LTSVFormatPlugin(String name, DrillbitContext context, Configuration
fsConf, StoragePluginConfig config, LTSVFormatPluginConfig formatPluginConfig) {
- super(name, context, fsConf, config, formatPluginConfig, true, false,
false, IS_COMPRESSIBLE, formatPluginConfig.getExtensions(), DEFAULT_NAME);
- }
+ public LTSVReaderFactory(LTSVFormatPluginConfig config) {
+ this.config = config;
+ }
- @Override
- public RecordReader getRecordReader(FragmentContext context, DrillFileSystem
dfs, FileWork fileWork, List<SchemaPath> columns, String userName) {
- return new LTSVRecordReader(context, fileWork.getPath(), dfs, columns);
+ @Override
+ public ManagedReader<? extends FileSchemaNegotiator> newReader() {
+ return new LTSVBatchReader();
+ }
}
-
- @Override
- public int getReaderOperatorType() {
- return UserBitShared.CoreOperatorType.LTSV_SUB_SCAN_VALUE;
+ public LTSVFormatPlugin(String name, DrillbitContext context,
+ Configuration fsConf, StoragePluginConfig
storageConfig,
+ LTSVFormatPluginConfig formatConfig) {
+ super(name, easyConfig(fsConf, formatConfig), context, storageConfig,
formatConfig);
}
- @Override
- public int getWriterOperatorType() {
- throw new UnsupportedOperationException("Drill doesn't currently support
writing to LTSV files.");
- }
-
- @Override
- public boolean supportsPushDown() {
- return true;
- }
-
- @Override
- public RecordWriter getRecordWriter(FragmentContext context, EasyWriter
writer) {
- throw new UnsupportedOperationException("Drill doesn't currently support
writing to LTSV files.");
- }
-
- @Override
- public boolean supportsStatistics() {
- return false;
+ private static EasyFormatConfig easyConfig(Configuration fsConf,
LTSVFormatPluginConfig pluginConfig) {
+ EasyFormatConfig config = new EasyFormatConfig();
+ config.readable = true;
+ config.writable = false;
+ config.blockSplittable = true;
Review comment:
IMHO this should be block splittable. It's a line by line parsed file.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
> Convert LTSV Format Plugin to EVF
> ---------------------------------
>
> Key: DRILL-7554
> URL: https://issues.apache.org/jira/browse/DRILL-7554
> Project: Apache Drill
> Issue Type: Improvement
> Components: Storage - Text & CSV
> Affects Versions: 1.17.0
> Reporter: Charles Givre
> Assignee: Charles Givre
> Priority: Major
> Fix For: 1.18.0
>
>
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
