[
https://issues.apache.org/jira/browse/DRILL-7716?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17098177#comment-17098177
]
ASF GitHub Bot commented on DRILL-7716:
---------------------------------------
cgivre commented on a change in pull request #2067:
URL: https://github.com/apache/drill/pull/2067#discussion_r419035541
##########
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:
Fixed
----------------------------------------------------------------
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:
us...@infra.apache.org
> Create Format Plugin for SPSS Files
> -----------------------------------
>
> Key: DRILL-7716
> URL: https://issues.apache.org/jira/browse/DRILL-7716
> Project: Apache Drill
> Issue Type: Improvement
> Components: Storage - Text & CSV
> Affects Versions: 1.17.0
> Reporter: Charles Givre
> Assignee: Charles Givre
> Priority: Major
> Labels: enhancement
> Fix For: 1.18.0
>
>
> # 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": {
> "type": "spss",
> "extensions": [
> "sav"
> ]
> }
> ```
> ## Data Model
> SPSS only supports two data types: Numeric and Strings. Drill maps these to
> `DOUBLE` and `VARCHAR` respectively. However, for some numeric columns, SPSS
> maps these numbers to
> text, similar to an `enum` field in Java.
>
> For instance, a field called `Survey` might have labels as shown below:
>
> <table>
> <tr>
> <th>Value</th>
> <th>Text</th>
> </tr>
> <tr>
> <td>1</td>
> <td>Yes</td>
> </tr>
> <tr>
> <td>2</td>
> <td>No</td>
> </tr>
> <tr>
> <td>99</td>
> <td>No Answer</td>
> </tr>
> </table>
> For situations like this, Drill will create two columns. In the example above
> you would get a column called `Survey` which has the numeric value (1,2 or
> 99) as well as a column
> called `Survey_value` which will map the integer to the appropriate value.
> Thus, the results would look something like this:
>
> <table>
> <tr>
> <th>`Survey`</th>
> <th>`Survey_value`</th>
> </tr>
> <tr>
> <td>1</td>
> <td>Yes</td>
> </tr>
> <tr>
> <td>1</td>
> <td>Yes</td>
> </tr>
> <tr>
> <td>1</td>
> <td>Yes</td>
> </tr>
> <tr>
> <td>2</td>
> <td>No</td>
> </tr>
> <tr>
> <td>1</td>
> <td>Yes</td>
> </tr>
> <tr>
> <td>2</td>
> <td>No</td>
> </tr>
> <tr>
> <td>99</td>
> <td>No Answer</td>
> </tr>
> </table>
> [1]: https://en.wikipedia.org/wiki/SPSS
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
