You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@drill.apache.org by GitBox <gi...@apache.org> on 2020/05/02 20:31:04 UTC
[GitHub] [drill] vvysotskyi commented on a change in pull request #2067: DRILL-7716: Create Format Plugin for SPSS Files
vvysotskyi commented on a change in pull request #2067:
URL: https://github.com/apache/drill/pull/2067#discussion_r419001452
##########
File path: contrib/format-spss/README.md
##########
@@ -0,0 +1,87 @@
+# Format Plugin for SPSS (SAV) Files
+This format plugin enables Apache Drill to read and query Statistical Package for the Social Sciences (SPSS) (or Statistical Product and Service Solutions) data files. According
+ to Wikipedia: [1]
+
+ SPSS is a widely used program for statistical analysis in social science. It is also used by market researchers, health researchers, survey companies, government, education researchers, marketing organizations, data miners, and others. The original SPSS manual (Nie, Bent & Hull, 1970) has been described as one of "sociology's most influential books" for allowing ordinary researchers to do their own statistical analysis. In addition to statistical analysis, data management (case selection, file reshaping, creating derived data) and data documentation (a metadata dictionary is stored in the datafile) are features of the base software.
Review comment:
Blockquote may be used for quoting from Wiki.
##########
File path: contrib/format-spss/README.md
##########
@@ -0,0 +1,87 @@
+# Format Plugin for SPSS (SAV) Files
+This format plugin enables Apache Drill to read and query Statistical Package for the Social Sciences (SPSS) (or Statistical Product and Service Solutions) data files. According
+ to Wikipedia: [1]
+
+ SPSS is a widely used program for statistical analysis in social science. It is also used by market researchers, health researchers, survey companies, government, education researchers, marketing organizations, data miners, and others. The original SPSS manual (Nie, Bent & Hull, 1970) has been described as one of "sociology's most influential books" for allowing ordinary researchers to do their own statistical analysis. In addition to statistical analysis, data management (case selection, file reshaping, creating derived data) and data documentation (a metadata dictionary is stored in the datafile) are features of the base software.
+
+
+## Configuration
+To configure Drill to read SPSS files, simply add the following code to the formats section of your file-based storage plugin. This should happen automatically for the default
+ `cp`, `dfs`, and `S3` storage plugins.
+
+ Other than the file extensions, there are no variables to configure.
+
+```json
+"spss": {
Review comment:
Please fix the formatting.
##########
File path: contrib/format-spss/README.md
##########
@@ -0,0 +1,87 @@
+# Format Plugin for SPSS (SAV) Files
+This format plugin enables Apache Drill to read and query Statistical Package for the Social Sciences (SPSS) (or Statistical Product and Service Solutions) data files. According
+ to Wikipedia: [1]
Review comment:
Wikipedia may be made as a reference instead of putting the long at the end of the doc.
##########
File path: contrib/format-spss/src/main/java/org/apache/drill/exec/store/spss/SpssBatchReader.java
##########
@@ -0,0 +1,242 @@
+/*
+ * 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.drill.exec.store.spss;
+
+import com.bedatadriven.spss.SpssDataFileReader;
+import com.bedatadriven.spss.SpssVariable;
+import org.apache.drill.common.exceptions.UserException;
+import org.apache.drill.common.types.TypeProtos;
+import org.apache.drill.exec.physical.impl.scan.file.FileScanFramework.FileSchemaNegotiator;
+import org.apache.drill.exec.physical.impl.scan.framework.ManagedReader;
+import org.apache.drill.exec.physical.resultSet.ResultSetLoader;
+import org.apache.drill.exec.physical.resultSet.RowSetLoader;
+import org.apache.drill.exec.record.metadata.SchemaBuilder;
+import org.apache.drill.exec.record.metadata.TupleMetadata;
+import org.apache.drill.exec.vector.accessor.ScalarWriter;
+import org.apache.hadoop.mapred.FileSplit;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.io.IOException;
+import java.io.InputStream;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Map;
+
+public class SpssBatchReader implements ManagedReader<FileSchemaNegotiator> {
+
+ private static final Logger logger = LoggerFactory.getLogger(SpssBatchReader.class);
+
+ private static final String VALUE_LABEL = "_value";
+
+ private final SpssReaderConfig readerConfig;
+
+ private FileSplit split;
+
+ private InputStream fsStream;
+
+ private SpssDataFileReader spssReader;
+
+ private RowSetLoader rowWriter;
+
+ private List<SpssVariable> variableList;
+
+ private List<SpssColumnWriter> writerList;
+
+
+ public static class SpssReaderConfig {
+
+ protected final SpssFormatPlugin plugin;
+
+ public SpssReaderConfig(SpssFormatPlugin plugin) {
+ this.plugin = plugin;
+ }
+ }
+
+ public SpssBatchReader(SpssReaderConfig readerConfig) {
+ this.readerConfig = readerConfig;
+ }
+
+ @Override
+ public boolean open(FileSchemaNegotiator negotiator) {
+ split = negotiator.split();
+ openFile(negotiator);
+ negotiator.tableSchema(buildSchema(), true);
+ ResultSetLoader loader = negotiator.build();
+ rowWriter = loader.writer();
+ buildReaderList();
+
+ return true;
+ }
+
+ @Override
+ public boolean next() {
+ while (!rowWriter.isFull()) {
+ if (!processNextRow()) {
+ return false;
+ }
+ }
+ return true;
+ }
+
+ @Override
+ public void close() {
+ if (fsStream != null) {
+ try {
+ fsStream.close();
+ } catch (IOException e) {
+ logger.warn("Error when closing SPSS File Stream resource: {}", e.getMessage());
+ }
+ fsStream = null;
+ }
+ }
+
+ private void openFile(FileSchemaNegotiator negotiator) {
+ try {
+ fsStream = negotiator.fileSystem().openPossiblyCompressedStream(split.getPath());
+ spssReader = new SpssDataFileReader(fsStream);
+ } catch (IOException e) {
+ throw UserException
+ .dataReadError(e)
+ .message("Unable to open SPSS File %s", split.getPath())
+ .addContext(e.getMessage())
+ .build(logger);
+ }
+ }
+
+ private boolean processNextRow() {
+ try {
+ SpssColumnWriter currentColumn;
Review comment:
Looks like using this variable may be omitted.
##########
File path: contrib/format-spss/src/main/java/org/apache/drill/exec/store/spss/SpssBatchReader.java
##########
@@ -0,0 +1,242 @@
+/*
+ * 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.drill.exec.store.spss;
+
+import com.bedatadriven.spss.SpssDataFileReader;
+import com.bedatadriven.spss.SpssVariable;
+import org.apache.drill.common.exceptions.UserException;
+import org.apache.drill.common.types.TypeProtos;
+import org.apache.drill.exec.physical.impl.scan.file.FileScanFramework.FileSchemaNegotiator;
+import org.apache.drill.exec.physical.impl.scan.framework.ManagedReader;
+import org.apache.drill.exec.physical.resultSet.ResultSetLoader;
+import org.apache.drill.exec.physical.resultSet.RowSetLoader;
+import org.apache.drill.exec.record.metadata.SchemaBuilder;
+import org.apache.drill.exec.record.metadata.TupleMetadata;
+import org.apache.drill.exec.vector.accessor.ScalarWriter;
+import org.apache.hadoop.mapred.FileSplit;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.io.IOException;
+import java.io.InputStream;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Map;
+
+public class SpssBatchReader implements ManagedReader<FileSchemaNegotiator> {
+
+ private static final Logger logger = LoggerFactory.getLogger(SpssBatchReader.class);
+
+ private static final String VALUE_LABEL = "_value";
+
+ private final SpssReaderConfig readerConfig;
Review comment:
This field is newer used.
##########
File path: contrib/format-spss/src/main/java/org/apache/drill/exec/store/spss/SpssBatchReader.java
##########
@@ -0,0 +1,242 @@
+/*
+ * 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.drill.exec.store.spss;
+
+import com.bedatadriven.spss.SpssDataFileReader;
+import com.bedatadriven.spss.SpssVariable;
+import org.apache.drill.common.exceptions.UserException;
+import org.apache.drill.common.types.TypeProtos;
+import org.apache.drill.exec.physical.impl.scan.file.FileScanFramework.FileSchemaNegotiator;
+import org.apache.drill.exec.physical.impl.scan.framework.ManagedReader;
+import org.apache.drill.exec.physical.resultSet.ResultSetLoader;
+import org.apache.drill.exec.physical.resultSet.RowSetLoader;
+import org.apache.drill.exec.record.metadata.SchemaBuilder;
+import org.apache.drill.exec.record.metadata.TupleMetadata;
+import org.apache.drill.exec.vector.accessor.ScalarWriter;
+import org.apache.hadoop.mapred.FileSplit;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.io.IOException;
+import java.io.InputStream;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Map;
+
+public class SpssBatchReader implements ManagedReader<FileSchemaNegotiator> {
+
+ private static final Logger logger = LoggerFactory.getLogger(SpssBatchReader.class);
+
+ private static final String VALUE_LABEL = "_value";
+
+ private final SpssReaderConfig readerConfig;
+
+ private FileSplit split;
+
+ private InputStream fsStream;
+
+ private SpssDataFileReader spssReader;
+
+ private RowSetLoader rowWriter;
+
+ private List<SpssVariable> variableList;
+
+ private List<SpssColumnWriter> writerList;
+
+
+ public static class SpssReaderConfig {
+
+ protected final SpssFormatPlugin plugin;
+
+ public SpssReaderConfig(SpssFormatPlugin plugin) {
+ this.plugin = plugin;
+ }
+ }
+
+ public SpssBatchReader(SpssReaderConfig readerConfig) {
+ this.readerConfig = readerConfig;
+ }
+
+ @Override
+ public boolean open(FileSchemaNegotiator negotiator) {
+ split = negotiator.split();
+ openFile(negotiator);
+ negotiator.tableSchema(buildSchema(), true);
+ ResultSetLoader loader = negotiator.build();
+ rowWriter = loader.writer();
+ buildReaderList();
+
+ return true;
+ }
+
+ @Override
+ public boolean next() {
+ while (!rowWriter.isFull()) {
+ if (!processNextRow()) {
+ return false;
+ }
+ }
+ return true;
+ }
+
+ @Override
+ public void close() {
+ if (fsStream != null) {
+ try {
+ fsStream.close();
+ } catch (IOException e) {
+ logger.warn("Error when closing SPSS File Stream resource: {}", e.getMessage());
+ }
+ fsStream = null;
+ }
+ }
+
+ private void openFile(FileSchemaNegotiator negotiator) {
+ try {
+ fsStream = negotiator.fileSystem().openPossiblyCompressedStream(split.getPath());
+ spssReader = new SpssDataFileReader(fsStream);
+ } catch (IOException e) {
+ throw UserException
+ .dataReadError(e)
+ .message("Unable to open SPSS File %s", split.getPath())
+ .addContext(e.getMessage())
+ .build(logger);
+ }
+ }
+
+ private boolean processNextRow() {
+ try {
+ SpssColumnWriter currentColumn;
+
+ // Stop reading when you run out of data
+ if (!spssReader.readNextCase() ) {
Review comment:
```suggestion
if (!spssReader.readNextCase()) {
```
##########
File path: contrib/format-spss/src/main/java/org/apache/drill/exec/store/spss/SpssBatchReader.java
##########
@@ -0,0 +1,242 @@
+/*
+ * 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.drill.exec.store.spss;
+
+import com.bedatadriven.spss.SpssDataFileReader;
+import com.bedatadriven.spss.SpssVariable;
+import org.apache.drill.common.exceptions.UserException;
+import org.apache.drill.common.types.TypeProtos;
+import org.apache.drill.exec.physical.impl.scan.file.FileScanFramework.FileSchemaNegotiator;
+import org.apache.drill.exec.physical.impl.scan.framework.ManagedReader;
+import org.apache.drill.exec.physical.resultSet.ResultSetLoader;
+import org.apache.drill.exec.physical.resultSet.RowSetLoader;
+import org.apache.drill.exec.record.metadata.SchemaBuilder;
+import org.apache.drill.exec.record.metadata.TupleMetadata;
+import org.apache.drill.exec.vector.accessor.ScalarWriter;
+import org.apache.hadoop.mapred.FileSplit;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.io.IOException;
+import java.io.InputStream;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Map;
+
+public class SpssBatchReader implements ManagedReader<FileSchemaNegotiator> {
+
+ private static final Logger logger = LoggerFactory.getLogger(SpssBatchReader.class);
+
+ private static final String VALUE_LABEL = "_value";
+
+ private final SpssReaderConfig readerConfig;
+
+ private FileSplit split;
+
+ private InputStream fsStream;
+
+ private SpssDataFileReader spssReader;
+
+ private RowSetLoader rowWriter;
+
+ private List<SpssVariable> variableList;
+
+ private List<SpssColumnWriter> writerList;
+
+
+ public static class SpssReaderConfig {
+
+ protected final SpssFormatPlugin plugin;
+
+ public SpssReaderConfig(SpssFormatPlugin plugin) {
+ this.plugin = plugin;
+ }
+ }
+
+ public SpssBatchReader(SpssReaderConfig readerConfig) {
+ this.readerConfig = readerConfig;
+ }
+
+ @Override
+ public boolean open(FileSchemaNegotiator negotiator) {
+ split = negotiator.split();
+ openFile(negotiator);
+ negotiator.tableSchema(buildSchema(), true);
+ ResultSetLoader loader = negotiator.build();
+ rowWriter = loader.writer();
+ buildReaderList();
+
+ return true;
+ }
+
+ @Override
+ public boolean next() {
+ while (!rowWriter.isFull()) {
+ if (!processNextRow()) {
+ return false;
+ }
+ }
+ return true;
+ }
+
+ @Override
+ public void close() {
+ if (fsStream != null) {
+ try {
+ fsStream.close();
+ } catch (IOException e) {
+ logger.warn("Error when closing SPSS File Stream resource: {}", e.getMessage());
+ }
+ fsStream = null;
+ }
+ }
+
+ private void openFile(FileSchemaNegotiator negotiator) {
+ try {
+ fsStream = negotiator.fileSystem().openPossiblyCompressedStream(split.getPath());
+ spssReader = new SpssDataFileReader(fsStream);
+ } catch (IOException e) {
+ throw UserException
+ .dataReadError(e)
+ .message("Unable to open SPSS File %s", split.getPath())
+ .addContext(e.getMessage())
+ .build(logger);
+ }
+ }
+
+ private boolean processNextRow() {
+ try {
+ SpssColumnWriter currentColumn;
+
+ // Stop reading when you run out of data
+ if (!spssReader.readNextCase() ) {
+ return false;
+ }
+
+ rowWriter.start();
+ for (SpssColumnWriter spssColumnWriter : writerList) {
+ currentColumn = spssColumnWriter;
+ currentColumn.load(spssReader);
+ }
+ rowWriter.save();
+
+ } catch (IOException e) {
+ throw UserException
+ .dataReadError(e)
+ .message("Error reading SPSS File.")
+ .addContext(e.getMessage())
+ .build(logger);
+ }
+ return true;
+ }
+
+ private TupleMetadata buildSchema() {
+ SchemaBuilder builder = new SchemaBuilder();
+ variableList = spssReader.getVariables();
+
+ for(SpssVariable variable : variableList) {
+ String varName = variable.getVariableName();
+
+ if (variable.isNumeric()) {
+ builder.addNullable(varName, TypeProtos.MinorType.FLOAT8);
+
+ // Check if the column has lookups associated with it
+ if (variable.getValueLabels() != null && variable.getValueLabels().size() > 0) {
+ builder.addNullable(varName + VALUE_LABEL, TypeProtos.MinorType.VARCHAR);
+ }
+
+ } else {
+ builder.addNullable(varName, TypeProtos.MinorType.VARCHAR);
+ }
+ }
+ return builder.buildSchema();
+ }
+
+ private void buildReaderList() {
+ writerList = new ArrayList<>();
+
+ for(SpssVariable variable : variableList) {
+ if (variable.isNumeric()) {
+ writerList.add(new NumericSpssColumnWriter(variable.getVariableName(), rowWriter, spssReader));
+ } else {
+ writerList.add(new StringSpssColumnWriter(variable.getVariableName(), rowWriter));
+ }
+ }
+ }
+
+ public abstract static class SpssColumnWriter {
+ String columnName;
+
+ ScalarWriter writer;
+
+ public boolean isNumeric;
Review comment:
This field is newer accessed, so can we remove it?
##########
File path: contrib/format-spss/src/main/java/org/apache/drill/exec/store/spss/SpssBatchReader.java
##########
@@ -0,0 +1,242 @@
+/*
+ * 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.drill.exec.store.spss;
+
+import com.bedatadriven.spss.SpssDataFileReader;
+import com.bedatadriven.spss.SpssVariable;
+import org.apache.drill.common.exceptions.UserException;
+import org.apache.drill.common.types.TypeProtos;
+import org.apache.drill.exec.physical.impl.scan.file.FileScanFramework.FileSchemaNegotiator;
+import org.apache.drill.exec.physical.impl.scan.framework.ManagedReader;
+import org.apache.drill.exec.physical.resultSet.ResultSetLoader;
+import org.apache.drill.exec.physical.resultSet.RowSetLoader;
+import org.apache.drill.exec.record.metadata.SchemaBuilder;
+import org.apache.drill.exec.record.metadata.TupleMetadata;
+import org.apache.drill.exec.vector.accessor.ScalarWriter;
+import org.apache.hadoop.mapred.FileSplit;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.io.IOException;
+import java.io.InputStream;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Map;
+
+public class SpssBatchReader implements ManagedReader<FileSchemaNegotiator> {
+
+ private static final Logger logger = LoggerFactory.getLogger(SpssBatchReader.class);
+
+ private static final String VALUE_LABEL = "_value";
+
+ private final SpssReaderConfig readerConfig;
+
+ private FileSplit split;
+
+ private InputStream fsStream;
+
+ private SpssDataFileReader spssReader;
+
+ private RowSetLoader rowWriter;
+
+ private List<SpssVariable> variableList;
+
+ private List<SpssColumnWriter> writerList;
+
+
+ public static class SpssReaderConfig {
+
+ protected final SpssFormatPlugin plugin;
+
+ public SpssReaderConfig(SpssFormatPlugin plugin) {
+ this.plugin = plugin;
+ }
+ }
+
+ public SpssBatchReader(SpssReaderConfig readerConfig) {
+ this.readerConfig = readerConfig;
+ }
+
+ @Override
+ public boolean open(FileSchemaNegotiator negotiator) {
+ split = negotiator.split();
+ openFile(negotiator);
+ negotiator.tableSchema(buildSchema(), true);
+ ResultSetLoader loader = negotiator.build();
+ rowWriter = loader.writer();
+ buildReaderList();
+
+ return true;
+ }
+
+ @Override
+ public boolean next() {
+ while (!rowWriter.isFull()) {
+ if (!processNextRow()) {
+ return false;
+ }
+ }
+ return true;
+ }
+
+ @Override
+ public void close() {
+ if (fsStream != null) {
+ try {
+ fsStream.close();
+ } catch (IOException e) {
+ logger.warn("Error when closing SPSS File Stream resource: {}", e.getMessage());
+ }
+ fsStream = null;
+ }
+ }
+
+ private void openFile(FileSchemaNegotiator negotiator) {
+ try {
+ fsStream = negotiator.fileSystem().openPossiblyCompressedStream(split.getPath());
+ spssReader = new SpssDataFileReader(fsStream);
+ } catch (IOException e) {
+ throw UserException
+ .dataReadError(e)
+ .message("Unable to open SPSS File %s", split.getPath())
+ .addContext(e.getMessage())
+ .build(logger);
+ }
+ }
+
+ private boolean processNextRow() {
+ try {
+ SpssColumnWriter currentColumn;
+
+ // Stop reading when you run out of data
+ if (!spssReader.readNextCase() ) {
+ return false;
+ }
+
+ rowWriter.start();
+ for (SpssColumnWriter spssColumnWriter : writerList) {
+ currentColumn = spssColumnWriter;
+ currentColumn.load(spssReader);
+ }
+ rowWriter.save();
+
+ } catch (IOException e) {
+ throw UserException
+ .dataReadError(e)
+ .message("Error reading SPSS File.")
+ .addContext(e.getMessage())
+ .build(logger);
+ }
+ return true;
+ }
+
+ private TupleMetadata buildSchema() {
+ SchemaBuilder builder = new SchemaBuilder();
+ variableList = spssReader.getVariables();
+
+ for(SpssVariable variable : variableList) {
+ String varName = variable.getVariableName();
+
+ if (variable.isNumeric()) {
+ builder.addNullable(varName, TypeProtos.MinorType.FLOAT8);
+
+ // Check if the column has lookups associated with it
+ if (variable.getValueLabels() != null && variable.getValueLabels().size() > 0) {
+ builder.addNullable(varName + VALUE_LABEL, TypeProtos.MinorType.VARCHAR);
+ }
+
+ } else {
+ builder.addNullable(varName, TypeProtos.MinorType.VARCHAR);
+ }
+ }
+ return builder.buildSchema();
+ }
+
+ private void buildReaderList() {
+ writerList = new ArrayList<>();
+
+ for(SpssVariable variable : variableList) {
+ if (variable.isNumeric()) {
+ writerList.add(new NumericSpssColumnWriter(variable.getVariableName(), rowWriter, spssReader));
+ } else {
+ writerList.add(new StringSpssColumnWriter(variable.getVariableName(), rowWriter));
+ }
+ }
+ }
+
+ public abstract static class SpssColumnWriter {
+ String columnName;
Review comment:
You may introduce a constructor which accepts these fields and make them final.
##########
File path: contrib/format-spss/src/main/resources/bootstrap-format-plugins.json
##########
@@ -0,0 +1,37 @@
+{
+ "storage":{
Review comment:
```suggestion
"storage": {
```
##########
File path: protocol/src/main/protobuf/UserBitShared.proto
##########
@@ -379,7 +379,11 @@ enum CoreOperatorType {
SHP_SUB_SCAN = 65;
METADATA_HANDLER = 66;
METADATA_CONTROLLER = 67;
+ // 68 Reserved for Apache Druid
Review comment:
Please remove these comments. When plugins are merged, new values will be introduced. Protobufs will be regenerated in both cases.
##########
File path: contrib/format-spss/src/main/java/org/apache/drill/exec/store/spss/SpssBatchReader.java
##########
@@ -0,0 +1,242 @@
+/*
+ * 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.drill.exec.store.spss;
+
+import com.bedatadriven.spss.SpssDataFileReader;
+import com.bedatadriven.spss.SpssVariable;
+import org.apache.drill.common.exceptions.UserException;
+import org.apache.drill.common.types.TypeProtos;
+import org.apache.drill.exec.physical.impl.scan.file.FileScanFramework.FileSchemaNegotiator;
+import org.apache.drill.exec.physical.impl.scan.framework.ManagedReader;
+import org.apache.drill.exec.physical.resultSet.ResultSetLoader;
+import org.apache.drill.exec.physical.resultSet.RowSetLoader;
+import org.apache.drill.exec.record.metadata.SchemaBuilder;
+import org.apache.drill.exec.record.metadata.TupleMetadata;
+import org.apache.drill.exec.vector.accessor.ScalarWriter;
+import org.apache.hadoop.mapred.FileSplit;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.io.IOException;
+import java.io.InputStream;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Map;
+
+public class SpssBatchReader implements ManagedReader<FileSchemaNegotiator> {
+
+ private static final Logger logger = LoggerFactory.getLogger(SpssBatchReader.class);
+
+ private static final String VALUE_LABEL = "_value";
+
+ private final SpssReaderConfig readerConfig;
+
+ private FileSplit split;
+
+ private InputStream fsStream;
+
+ private SpssDataFileReader spssReader;
+
+ private RowSetLoader rowWriter;
+
+ private List<SpssVariable> variableList;
+
+ private List<SpssColumnWriter> writerList;
+
+
+ public static class SpssReaderConfig {
+
+ protected final SpssFormatPlugin plugin;
+
+ public SpssReaderConfig(SpssFormatPlugin plugin) {
+ this.plugin = plugin;
+ }
+ }
+
+ public SpssBatchReader(SpssReaderConfig readerConfig) {
+ this.readerConfig = readerConfig;
+ }
+
+ @Override
+ public boolean open(FileSchemaNegotiator negotiator) {
+ split = negotiator.split();
+ openFile(negotiator);
+ negotiator.tableSchema(buildSchema(), true);
+ ResultSetLoader loader = negotiator.build();
+ rowWriter = loader.writer();
+ buildReaderList();
+
+ return true;
+ }
+
+ @Override
+ public boolean next() {
+ while (!rowWriter.isFull()) {
+ if (!processNextRow()) {
+ return false;
+ }
+ }
+ return true;
+ }
+
+ @Override
+ public void close() {
+ if (fsStream != null) {
+ try {
+ fsStream.close();
+ } catch (IOException e) {
+ logger.warn("Error when closing SPSS File Stream resource: {}", e.getMessage());
+ }
+ fsStream = null;
+ }
+ }
+
+ private void openFile(FileSchemaNegotiator negotiator) {
+ try {
+ fsStream = negotiator.fileSystem().openPossiblyCompressedStream(split.getPath());
+ spssReader = new SpssDataFileReader(fsStream);
+ } catch (IOException e) {
+ throw UserException
+ .dataReadError(e)
+ .message("Unable to open SPSS File %s", split.getPath())
+ .addContext(e.getMessage())
+ .build(logger);
+ }
+ }
+
+ private boolean processNextRow() {
+ try {
+ SpssColumnWriter currentColumn;
+
+ // Stop reading when you run out of data
+ if (!spssReader.readNextCase() ) {
+ return false;
+ }
+
+ rowWriter.start();
+ for (SpssColumnWriter spssColumnWriter : writerList) {
+ currentColumn = spssColumnWriter;
+ currentColumn.load(spssReader);
+ }
+ rowWriter.save();
+
+ } catch (IOException e) {
+ throw UserException
+ .dataReadError(e)
+ .message("Error reading SPSS File.")
+ .addContext(e.getMessage())
+ .build(logger);
+ }
+ return true;
+ }
+
+ private TupleMetadata buildSchema() {
+ SchemaBuilder builder = new SchemaBuilder();
+ variableList = spssReader.getVariables();
+
+ for(SpssVariable variable : variableList) {
Review comment:
```suggestion
for (SpssVariable variable : variableList) {
```
##########
File path: exec/java-exec/src/test/java/org/apache/drill/test/ClusterTest.java
##########
@@ -125,4 +139,29 @@ public static void run(String query, Object... args) throws Exception {
public QueryBuilder queryBuilder( ) {
return client.queryBuilder();
}
+
+ /**
+ * Generates a compressed file for testing
+ * @param fileName the input file to be compressed
+ * @param codecName the CODEC to be used for compression
+ * @param outFileName the output file name
+ * @throws IOException Throws IO exception if the file cannot be found or any other IO error
+ */
+ public void generateCompressedFile(String fileName, String codecName, String outFileName) throws IOException {
Review comment:
Please make it static and move to a more suitable place, for example to `QueryTestUtil`.
----------------------------------------------------------------
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:
users@infra.apache.org