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 2021/11/24 09:06:38 UTC
[GitHub] [drill] luocooong commented on a change in pull request #2359: DRILL-8028: Add PDF Format Plugin
luocooong commented on a change in pull request #2359:
URL: https://github.com/apache/drill/pull/2359#discussion_r755766696
##########
File path: contrib/format-pdf/src/main/java/org/apache/drill/exec/store/pdf/PdfFormatConfig.java
##########
@@ -0,0 +1,117 @@
+/*
+ * 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.pdf;
+
+import com.fasterxml.jackson.annotation.JsonCreator;
+import com.fasterxml.jackson.annotation.JsonInclude;
+import com.fasterxml.jackson.annotation.JsonInclude.Include;
+import com.fasterxml.jackson.annotation.JsonProperty;
+import com.fasterxml.jackson.annotation.JsonTypeName;
+
+import org.apache.drill.common.PlanStringBuilder;
+import org.apache.drill.common.logical.FormatPluginConfig;
+import org.apache.drill.shaded.guava.com.google.common.collect.ImmutableList;
+
+import java.util.Collections;
+import java.util.List;
+import java.util.Objects;
+
+@JsonTypeName(PdfFormatPlugin.DEFAULT_NAME)
+public class PdfFormatConfig implements FormatPluginConfig {
+
+ private final List<String> extensions;
+ private final boolean extractHeaders;
+ private final String extractionAlgorithm;
+ private final boolean combinePages;
+ private final int defaultTableIndex;
+
+ @JsonCreator
+ public PdfFormatConfig(@JsonProperty("extensions") List<String> extensions,
+ @JsonProperty("extractHeaders") boolean extractHeaders,
+ @JsonProperty("extractionAlgorithm") String extractionAlgorithm,
+ @JsonProperty("combinePages") boolean combinePages,
+ @JsonProperty("defaultTableIndex") int defaultTableIndex) {
+ this.extensions = extensions == null
+ ? Collections.singletonList("pdf")
Review comment:
Can also use the `PdfFormatPlugin.DEFAULT_NAME` instead of `"pdf"`.
##########
File path: contrib/format-pdf/src/main/resources/drill-module.conf
##########
@@ -0,0 +1,23 @@
+#
+# 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.
+#
+
+# This file tells Drill to consider this module when class path scanning.
+# This file can also include any supplementary configuration information.
+# This file is in HOCON format, see https://github.com/typesafehub/config/blob/master/HOCON.md for more information.
+
+drill.classpath.scanning.packages += "org.apache.drill.exec.store.pdf"
Review comment:
No newfile at end of file.
##########
File path: contrib/format-pdf/src/main/java/org/apache/drill/exec/store/pdf/PdfFormatConfig.java
##########
@@ -0,0 +1,117 @@
+/*
+ * 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.pdf;
+
+import com.fasterxml.jackson.annotation.JsonCreator;
+import com.fasterxml.jackson.annotation.JsonInclude;
+import com.fasterxml.jackson.annotation.JsonInclude.Include;
+import com.fasterxml.jackson.annotation.JsonProperty;
+import com.fasterxml.jackson.annotation.JsonTypeName;
+
+import org.apache.drill.common.PlanStringBuilder;
+import org.apache.drill.common.logical.FormatPluginConfig;
+import org.apache.drill.shaded.guava.com.google.common.collect.ImmutableList;
+
+import java.util.Collections;
+import java.util.List;
+import java.util.Objects;
+
+@JsonTypeName(PdfFormatPlugin.DEFAULT_NAME)
+public class PdfFormatConfig implements FormatPluginConfig {
+
+ private final List<String> extensions;
+ private final boolean extractHeaders;
+ private final String extractionAlgorithm;
+ private final boolean combinePages;
+ private final int defaultTableIndex;
+
+ @JsonCreator
+ public PdfFormatConfig(@JsonProperty("extensions") List<String> extensions,
+ @JsonProperty("extractHeaders") boolean extractHeaders,
+ @JsonProperty("extractionAlgorithm") String extractionAlgorithm,
+ @JsonProperty("combinePages") boolean combinePages,
+ @JsonProperty("defaultTableIndex") int defaultTableIndex) {
+ this.extensions = extensions == null
+ ? Collections.singletonList("pdf")
+ : ImmutableList.copyOf(extensions);
+ this.extractHeaders = extractHeaders;
+ this.extractionAlgorithm = extractionAlgorithm;
+ this.combinePages = combinePages;
+ this.defaultTableIndex = defaultTableIndex;
+ }
+
+ public PdfBatchReader.PdfReaderConfig getReaderConfig(PdfFormatPlugin plugin) {
+ return new PdfBatchReader.PdfReaderConfig(plugin);
+ }
+
+ @JsonInclude(Include.NON_DEFAULT)
+ @JsonProperty("extensions")
+ public List<String> getExtensions() {
+ return extensions;
+ }
+
+ @JsonInclude(Include.NON_DEFAULT)
+ @JsonProperty("combinePages")
+ public boolean getCombinePages() { return combinePages; }
Review comment:
Keep the code format of getter as consistent as possible.
```java
public boolean getX() {
return x;
}
```
or
```java
public boolean getX() { return x; }
```
##########
File path: contrib/format-pdf/src/main/java/org/apache/drill/exec/store/pdf/PdfBatchReader.java
##########
@@ -0,0 +1,549 @@
+/*
+ * 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.pdf;
+
+import org.apache.drill.common.types.TypeProtos.DataMode;
+import org.apache.drill.exec.record.MaterializedField;
+import org.apache.drill.shaded.guava.com.google.common.base.Strings;
+import org.apache.drill.common.AutoCloseables;
+import org.apache.drill.common.exceptions.CustomErrorContext;
+import org.apache.drill.common.exceptions.UserException;
+import org.apache.drill.common.types.TypeProtos;
+import org.apache.drill.common.types.TypeProtos.MinorType;
+import org.apache.drill.exec.physical.impl.scan.file.FileScanFramework;
+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.ColumnMetadata;
+import org.apache.drill.exec.record.metadata.MetadataUtils;
+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.drill.exec.vector.accessor.TupleWriter;
+import org.apache.hadoop.mapred.FileSplit;
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.pdmodel.PDDocumentInformation;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+import technology.tabula.RectangularTextContainer;
+import technology.tabula.Table;
+
+import java.io.InputStream;
+import java.text.ParseException;
+import java.text.SimpleDateFormat;
+import java.time.Instant;
+import java.time.LocalDate;
+import java.time.LocalTime;
+import java.time.format.DateTimeFormatter;
+import java.util.ArrayList;
+import java.util.Calendar;
+import java.util.Date;
+import java.util.List;
+
+public class PdfBatchReader implements ManagedReader<FileScanFramework.FileSchemaNegotiator> {
+
+ private static final Logger logger = LoggerFactory.getLogger(PdfBatchReader.class);
+ private static final String NEW_FIELD_PREFIX = "field_";
+ private final int maxRecords;
+
+ private final List<PdfColumnWriter> writers;
+ private FileSplit split;
+ private CustomErrorContext errorContext;
+ private RowSetLoader rowWriter;
+ private InputStream fsStream;
+ private PDDocument document;
+ private PdfReaderConfig config;
+
+ private SchemaBuilder builder;
+ private List<String> columnHeaders;
+ private int currentRowIndex;
+ private Table currentTable;
+ private int currentTableIndex;
+ private int startingTableIndex;
+ private FileScanFramework.FileSchemaNegotiator negotiator;
+
+ // Document Metadata Fields
+ private int pageCount;
+ private String title;
+ private String author;
+ private String subject;
+ private String keywords;
+ private String creator;
+ private String producer;
+ private Calendar creationDate;
+ private Calendar modificationDate;
+ private String trapped;
+ private int unregisteredColumnCount;
+ private int columns;
+ private int tableCount;
+ private int rows;
+ private int metadataIndex;
+
+
+ // Tables
+ private List<Table> tables;
+
+
+ static class PdfReaderConfig {
+ final PdfFormatPlugin plugin;
+
+ PdfReaderConfig(PdfFormatPlugin plugin) {
+ this.plugin = plugin;
+ }
+ }
+
+ public PdfBatchReader(PdfReaderConfig readerConfig, int maxRecords) {
+ this.maxRecords = maxRecords;
+ this.unregisteredColumnCount = 0;
+ this.writers = new ArrayList<>();
+ this.config = readerConfig;
+ this.startingTableIndex = readerConfig.plugin.getConfig().getDefaultTableIndex() < 0 ? 0 : readerConfig.plugin.getConfig().getDefaultTableIndex();
+ this.currentTableIndex = this.startingTableIndex;
+ this.columnHeaders = new ArrayList<>();
+ }
+
+ @Override
+ public boolean open(FileScanFramework.FileSchemaNegotiator negotiator) {
+ System.setProperty("java.awt.headless", "true");
Review comment:
This property has been set many times, maybe it can be done like this :
```java
if (System.getProperty("java.awt.headless") == null) {
System.setProperty("java.awt.headless", "true");
}
```
And remove the `Utils.java`, line 60. `PdfBatchReader.java`, line 164?
##########
File path: contrib/format-pdf/src/test/java/org/apache/drill/exec/store/pdf/testPDFUtils.java
##########
@@ -0,0 +1,78 @@
+/*
+ * 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.pdf;
+
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.junit.Test;
+import technology.tabula.Table;
+import java.io.File;
+import java.util.List;
+
+import static org.junit.Assert.assertEquals;
+
+
+public class testPDFUtils {
+
+ private static final String DATA_PATH = "src/test/resources/pdf/";
+
+ @Test
+ public void testTableExtractor() throws Exception {
+ PDDocument document = getDocument("argentina_diputados_voting_record.pdf");
+ List<Table> tableList = Utils.extractTablesFromPDF(document);
+ document.close();
+ assertEquals(tableList.size(), 1);
+
+ PDDocument document2 = getDocument("twotables.pdf");
+ List<Table> tableList2 = Utils.extractTablesFromPDF(document2);
+ document2.close();
+ assertEquals(tableList2.size(), 2);
+ }
+
+ @Test
+ public void testTableExtractorWithNoBoundingFrame() throws Exception {
+ PDDocument document = getDocument("spreadsheet_no_bounding_frame.pdf");
+ List<Table> tableList = Utils.extractTablesFromPDF(document);
+ document.close();
+ assertEquals(tableList.size(), 1);
+ }
+
+ @Test
+ public void testTableExtractorWitMultipage() throws Exception {
+ PDDocument document = getDocument("us-020.pdf");
+ List<Table> tableList = Utils.extractTablesFromPDF(document);
+ document.close();
+ assertEquals(tableList.size(), 4);
+ }
+
+ @Test
+ public void testFirstRowExtractor() throws Exception {
+ PDDocument document = getDocument("schools.pdf");
+ List<Table> tableList = Utils.extractTablesFromPDF(document);
+ document.close();
+
+ List<String> values = Utils.extractRowValues(tableList.get(0));
+ assertEquals(values.size(), 11);
+ }
+
+
Review comment:
Too many blank lines.
##########
File path: contrib/format-pdf/src/main/java/org/apache/drill/exec/store/pdf/PdfBatchReader.java
##########
@@ -0,0 +1,549 @@
+/*
+ * 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.pdf;
+
+import org.apache.drill.common.types.TypeProtos.DataMode;
+import org.apache.drill.exec.record.MaterializedField;
+import org.apache.drill.shaded.guava.com.google.common.base.Strings;
+import org.apache.drill.common.AutoCloseables;
+import org.apache.drill.common.exceptions.CustomErrorContext;
+import org.apache.drill.common.exceptions.UserException;
+import org.apache.drill.common.types.TypeProtos;
+import org.apache.drill.common.types.TypeProtos.MinorType;
+import org.apache.drill.exec.physical.impl.scan.file.FileScanFramework;
+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.ColumnMetadata;
+import org.apache.drill.exec.record.metadata.MetadataUtils;
+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.drill.exec.vector.accessor.TupleWriter;
+import org.apache.hadoop.mapred.FileSplit;
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.pdmodel.PDDocumentInformation;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+import technology.tabula.RectangularTextContainer;
+import technology.tabula.Table;
+
+import java.io.InputStream;
+import java.text.ParseException;
+import java.text.SimpleDateFormat;
+import java.time.Instant;
+import java.time.LocalDate;
+import java.time.LocalTime;
+import java.time.format.DateTimeFormatter;
+import java.util.ArrayList;
+import java.util.Calendar;
+import java.util.Date;
+import java.util.List;
+
+public class PdfBatchReader implements ManagedReader<FileScanFramework.FileSchemaNegotiator> {
+
+ private static final Logger logger = LoggerFactory.getLogger(PdfBatchReader.class);
+ private static final String NEW_FIELD_PREFIX = "field_";
+ private final int maxRecords;
+
+ private final List<PdfColumnWriter> writers;
+ private FileSplit split;
+ private CustomErrorContext errorContext;
+ private RowSetLoader rowWriter;
+ private InputStream fsStream;
+ private PDDocument document;
+ private PdfReaderConfig config;
+
+ private SchemaBuilder builder;
+ private List<String> columnHeaders;
+ private int currentRowIndex;
+ private Table currentTable;
+ private int currentTableIndex;
+ private int startingTableIndex;
+ private FileScanFramework.FileSchemaNegotiator negotiator;
+
+ // Document Metadata Fields
+ private int pageCount;
+ private String title;
+ private String author;
+ private String subject;
+ private String keywords;
+ private String creator;
+ private String producer;
+ private Calendar creationDate;
+ private Calendar modificationDate;
+ private String trapped;
+ private int unregisteredColumnCount;
+ private int columns;
+ private int tableCount;
+ private int rows;
+ private int metadataIndex;
+
+
+ // Tables
+ private List<Table> tables;
+
+
+ static class PdfReaderConfig {
+ final PdfFormatPlugin plugin;
+
+ PdfReaderConfig(PdfFormatPlugin plugin) {
+ this.plugin = plugin;
+ }
+ }
+
+ public PdfBatchReader(PdfReaderConfig readerConfig, int maxRecords) {
+ this.maxRecords = maxRecords;
+ this.unregisteredColumnCount = 0;
+ this.writers = new ArrayList<>();
+ this.config = readerConfig;
+ this.startingTableIndex = readerConfig.plugin.getConfig().getDefaultTableIndex() < 0 ? 0 : readerConfig.plugin.getConfig().getDefaultTableIndex();
+ this.currentTableIndex = this.startingTableIndex;
+ this.columnHeaders = new ArrayList<>();
+ }
+
+ @Override
+ public boolean open(FileScanFramework.FileSchemaNegotiator negotiator) {
+ System.setProperty("java.awt.headless", "true");
+ this.negotiator = negotiator;
+
+ split = negotiator.split();
+ errorContext = negotiator.parentErrorContext();
+ builder = new SchemaBuilder();
+
+ openFile();
+
+ // Get the tables
+ tables = Utils.extractTablesFromPDF(document);
+ populateMetadata();
+ logger.debug("Found {} tables", tables.size());
+
+ // Support provided schema
+ TupleMetadata schema = null;
+ if (this.negotiator.hasProvidedSchema()) {
+ schema = this.negotiator.providedSchema();
+ this.negotiator.tableSchema(schema, false);
+ } else {
+ this.negotiator.tableSchema(buildSchema(), false);
+ }
+ ResultSetLoader loader = this.negotiator.build();
+ rowWriter = loader.writer();
+
+ if (negotiator.hasProvidedSchema()) {
+ buildWriterListFromProvidedSchema(schema);
+ } else {
+ buildWriterList();
+ }
+ addImplicitColumnsToSchema();
+
+ // Prepare for reading
+ currentRowIndex = 1; // Skip the first line if there are headers
+ currentTable = tables.get(startingTableIndex);
+
+ return true;
+ }
+
+ @Override
+ public boolean next() {
+ System.setProperty("java.awt.headless", "true");
+
+ while(!rowWriter.isFull()) {
+ // Check to see if the limit has been reached
+ if (rowWriter.limitReached(maxRecords)) {
+ return false;
+ } else if (currentRowIndex >= currentTable.getRows().size() &&
Review comment:
Is this the logic to handle a table that spans multiple pages?
##########
File path: contrib/format-pdf/src/main/java/org/apache/drill/exec/store/pdf/PdfBatchReader.java
##########
@@ -0,0 +1,549 @@
+/*
+ * 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.pdf;
+
+import org.apache.drill.common.types.TypeProtos.DataMode;
+import org.apache.drill.exec.record.MaterializedField;
+import org.apache.drill.shaded.guava.com.google.common.base.Strings;
+import org.apache.drill.common.AutoCloseables;
+import org.apache.drill.common.exceptions.CustomErrorContext;
+import org.apache.drill.common.exceptions.UserException;
+import org.apache.drill.common.types.TypeProtos;
+import org.apache.drill.common.types.TypeProtos.MinorType;
+import org.apache.drill.exec.physical.impl.scan.file.FileScanFramework;
+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.ColumnMetadata;
+import org.apache.drill.exec.record.metadata.MetadataUtils;
+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.drill.exec.vector.accessor.TupleWriter;
+import org.apache.hadoop.mapred.FileSplit;
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.pdmodel.PDDocumentInformation;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+import technology.tabula.RectangularTextContainer;
+import technology.tabula.Table;
+
+import java.io.InputStream;
+import java.text.ParseException;
+import java.text.SimpleDateFormat;
+import java.time.Instant;
+import java.time.LocalDate;
+import java.time.LocalTime;
+import java.time.format.DateTimeFormatter;
+import java.util.ArrayList;
+import java.util.Calendar;
+import java.util.Date;
+import java.util.List;
+
+public class PdfBatchReader implements ManagedReader<FileScanFramework.FileSchemaNegotiator> {
+
+ private static final Logger logger = LoggerFactory.getLogger(PdfBatchReader.class);
+ private static final String NEW_FIELD_PREFIX = "field_";
+ private final int maxRecords;
+
+ private final List<PdfColumnWriter> writers;
+ private FileSplit split;
+ private CustomErrorContext errorContext;
+ private RowSetLoader rowWriter;
+ private InputStream fsStream;
+ private PDDocument document;
+ private PdfReaderConfig config;
+
+ private SchemaBuilder builder;
+ private List<String> columnHeaders;
+ private int currentRowIndex;
+ private Table currentTable;
+ private int currentTableIndex;
+ private int startingTableIndex;
+ private FileScanFramework.FileSchemaNegotiator negotiator;
+
+ // Document Metadata Fields
+ private int pageCount;
+ private String title;
+ private String author;
+ private String subject;
+ private String keywords;
+ private String creator;
+ private String producer;
+ private Calendar creationDate;
+ private Calendar modificationDate;
+ private String trapped;
+ private int unregisteredColumnCount;
+ private int columns;
+ private int tableCount;
+ private int rows;
+ private int metadataIndex;
+
+
+ // Tables
+ private List<Table> tables;
+
+
+ static class PdfReaderConfig {
+ final PdfFormatPlugin plugin;
+
+ PdfReaderConfig(PdfFormatPlugin plugin) {
+ this.plugin = plugin;
+ }
+ }
+
+ public PdfBatchReader(PdfReaderConfig readerConfig, int maxRecords) {
+ this.maxRecords = maxRecords;
+ this.unregisteredColumnCount = 0;
+ this.writers = new ArrayList<>();
+ this.config = readerConfig;
+ this.startingTableIndex = readerConfig.plugin.getConfig().getDefaultTableIndex() < 0 ? 0 : readerConfig.plugin.getConfig().getDefaultTableIndex();
+ this.currentTableIndex = this.startingTableIndex;
+ this.columnHeaders = new ArrayList<>();
+ }
+
+ @Override
+ public boolean open(FileScanFramework.FileSchemaNegotiator negotiator) {
+ System.setProperty("java.awt.headless", "true");
+ this.negotiator = negotiator;
+
+ split = negotiator.split();
+ errorContext = negotiator.parentErrorContext();
+ builder = new SchemaBuilder();
+
+ openFile();
+
+ // Get the tables
+ tables = Utils.extractTablesFromPDF(document);
+ populateMetadata();
+ logger.debug("Found {} tables", tables.size());
+
+ // Support provided schema
+ TupleMetadata schema = null;
+ if (this.negotiator.hasProvidedSchema()) {
+ schema = this.negotiator.providedSchema();
+ this.negotiator.tableSchema(schema, false);
+ } else {
+ this.negotiator.tableSchema(buildSchema(), false);
+ }
+ ResultSetLoader loader = this.negotiator.build();
+ rowWriter = loader.writer();
+
+ if (negotiator.hasProvidedSchema()) {
+ buildWriterListFromProvidedSchema(schema);
+ } else {
+ buildWriterList();
+ }
+ addImplicitColumnsToSchema();
+
+ // Prepare for reading
+ currentRowIndex = 1; // Skip the first line if there are headers
+ currentTable = tables.get(startingTableIndex);
+
+ return true;
+ }
+
+ @Override
+ public boolean next() {
+ System.setProperty("java.awt.headless", "true");
+
+ while(!rowWriter.isFull()) {
+ // Check to see if the limit has been reached
+ if (rowWriter.limitReached(maxRecords)) {
+ return false;
+ } else if (currentRowIndex >= currentTable.getRows().size() &&
+ currentTableIndex < tables.size() &&
+ config.plugin.getConfig().getCombinePages()) {
+ currentRowIndex = 0;
+ currentTable = tables.get(currentTableIndex++);
+ } else if (currentRowIndex >= currentTable.getRows().size()) {
+ return false;
+ }
+
+ // Process the row
+ processRow(currentTable.getRows().get(currentRowIndex));
+ currentRowIndex++;
+ }
+ return true;
+ }
+
+ private void processRow(List<RectangularTextContainer> row) {
+ if (row == null || row.size() == 0) {
+ return;
+ }
+
+ String value;
+ rowWriter.start();
+ for (int i = 0; i < row.size(); i++) {
+ value = row.get(i).getText();
+
+ if (Strings.isNullOrEmpty(value)) {
+ continue;
+ }
+ writers.get(i).load(row.get(i));
+ }
+ writeMetadata();
+ rowWriter.save();
+ }
+
+ @Override
+ public void close() {
+ if (fsStream != null) {
+ AutoCloseables.closeSilently(fsStream);
+ fsStream = null;
+ }
+
+ if (document != null) {
+ AutoCloseables.closeSilently(document.getDocument());
+ AutoCloseables.closeSilently(document);
+ document = null;
+ }
+ }
+
+ /**
+ * This method opens the PDF file, and finds the tables
+ */
+ private void openFile() {
+ try {
+ fsStream = negotiator.fileSystem().openPossiblyCompressedStream(split.getPath());
+ document = PDDocument.load(fsStream);
+ } catch (Exception e) {
+ throw UserException
+ .dataReadError(e)
+ .message("Failed to open open input file: %s", split.getPath().toString())
+ .addContext(e.getMessage())
+ .addContext(errorContext)
+ .build(logger);
+ }
+ }
+
+ /**
+ * Metadata fields are calculated once when the file is opened. This function populates
+ * the metadata fields so that these are only calculated once.
+ */
+ private void populateMetadata() {
+ PDDocumentInformation info = document.getDocumentInformation();
+ pageCount = document.getNumberOfPages();
+ title = info.getTitle();
+ author = info.getAuthor();
+ subject = info.getSubject();
+ keywords = info.getKeywords();
+ creator = info.getCreator();
+ producer = info.getProducer();
+ creationDate = info.getCreationDate();
+ modificationDate = info.getModificationDate();
+ trapped = info.getTrapped();
+ tableCount = tables.size();
+ }
+
+ private void addImplicitColumnsToSchema() {
+ metadataIndex = columns;
+ // Add to schema
+ addMetadataColumnToSchema("_page_count", MinorType.INT);
+ addMetadataColumnToSchema("_title", MinorType.VARCHAR);
+ addMetadataColumnToSchema("_author", MinorType.VARCHAR);
+ addMetadataColumnToSchema("_subject", MinorType.VARCHAR);
+ addMetadataColumnToSchema("_keywords", MinorType.VARCHAR);
+ addMetadataColumnToSchema("_creator", MinorType.VARCHAR);
+ addMetadataColumnToSchema("_producer", MinorType.VARCHAR);
+ addMetadataColumnToSchema("_creation_date", MinorType.TIMESTAMP);
+ addMetadataColumnToSchema("_modification_date", MinorType.TIMESTAMP);
+ addMetadataColumnToSchema("_trapped", MinorType.VARCHAR);
+ addMetadataColumnToSchema("_table_count", MinorType.INT);
+ }
+
+ private void addMetadataColumnToSchema(String columnName, MinorType dataType) {
+ int index = rowWriter.tupleSchema().index(columnName);
+ if (index == -1) {
+ ColumnMetadata colSchema = MetadataUtils.newScalar(columnName, dataType, DataMode.OPTIONAL);
+
+ // Exclude from wildcard queries
+ colSchema.setBooleanProperty(ColumnMetadata.EXCLUDE_FROM_WILDCARD, true);
+ metadataIndex++;
+
+ index = rowWriter.addColumn(colSchema);
+ }
+
+ writers.add(new StringPdfColumnWriter(index, columnName, rowWriter));
+ }
+
+ private void writeMetadata() {
+ int startingIndex = columnHeaders.size();
+ writers.get(startingIndex).getWriter().setInt(pageCount);
+ writeStringMetadataField(title, startingIndex+1);
+ writeStringMetadataField(author, startingIndex+2);
+ writeStringMetadataField(subject, startingIndex+3);
+ writeStringMetadataField(keywords, startingIndex+4);
+ writeStringMetadataField(creator, startingIndex+5);
+ writeStringMetadataField(producer, startingIndex+6);
+ writeTimestampMetadataField(creationDate, startingIndex+7);
+ writeTimestampMetadataField(modificationDate, startingIndex+8);
+ writeStringMetadataField(trapped, startingIndex+9);
+ writers.get(startingIndex+10).getWriter().setInt(tableCount);
+ }
+
+ private void writeStringMetadataField(String value, int index) {
+ if (value == null) {
+ return;
+ }
+ writers.get(index).getWriter().setString(value);
+ }
+
+ private void writeTimestampMetadataField(Calendar dateValue, int index) {
+ if (dateValue == null) {
+ return;
+ }
+
+ writers.get(index).getWriter().setTimestamp(Instant.ofEpochMilli(dateValue.getTimeInMillis()));
+ }
+
+ private void addUnknownColumnToSchemaAndCreateWriter (TupleWriter rowWriter, String name) {
Review comment:
This method is never used locally, the `metadataIndex` is only used in this method.
In this class, at line 95 and 322, the value of field is not used.
##########
File path: contrib/format-pdf/src/main/java/org/apache/drill/exec/store/pdf/Utils.java
##########
@@ -0,0 +1,102 @@
+/*
+ * 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.pdf;
+
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+import technology.tabula.ObjectExtractor;
+import technology.tabula.Page;
+import technology.tabula.PageIterator;
+import technology.tabula.Rectangle;
+import technology.tabula.RectangularTextContainer;
+import technology.tabula.Table;
+import technology.tabula.detectors.NurminenDetectionAlgorithm;
+import technology.tabula.extractors.BasicExtractionAlgorithm;
+import technology.tabula.extractors.ExtractionAlgorithm;
+import technology.tabula.extractors.SpreadsheetExtractionAlgorithm;
+
+import java.util.ArrayList;
+import java.util.List;
+
+public class Utils {
+
+ public static final ExtractionAlgorithm DEFAULT_ALGORITHM = new BasicExtractionAlgorithm();
+ private static final Logger logger = LoggerFactory.getLogger(Utils.class);
+
+ /**
+ * Returns a list of tables found in a given PDF document. There are several extraction algorithms
+ * available and this function uses the default Basic Extraction Algorithm.
+ * @param document The input PDF document to search for tables
+ * @return A list of tables found in the document.
+ */
+ public static List<Table> extractTablesFromPDF(PDDocument document) {
+ return extractTablesFromPDF(document, DEFAULT_ALGORITHM);
+ }
+
+ public static List<Table> extractTablesFromPDF(PDDocument document, ExtractionAlgorithm algorithm) {
+ System.setProperty("java.awt.headless", "true");
+
+ NurminenDetectionAlgorithm detectionAlgorithm = new NurminenDetectionAlgorithm();
+
+ ExtractionAlgorithm algExtractor;
+
+ SpreadsheetExtractionAlgorithm extractor = new SpreadsheetExtractionAlgorithm();
+
+ ObjectExtractor objectExtractor = new ObjectExtractor(document);
+ PageIterator pages = objectExtractor.extract();
+ List<Table> tables= new ArrayList<>();
+ while (pages.hasNext()) {
+ Page page = pages.next();
+
+ algExtractor = algorithm;
+ List<Rectangle> tablesOnPage = detectionAlgorithm.detect(page);
+
+ for (Rectangle guessRect : tablesOnPage) {
+ Page guess = page.getArea(guessRect);
+ tables.addAll(algExtractor.extract(guess));
+ }
+ }
+
+ try {
+ objectExtractor.close();
+ } catch (Exception e) {
+ logger.debug("Error closing Object extractor.");
+ }
+
+ return tables;
+ }
+
+ /**
+ * Returns the values contained in a PDF Table row
+ * @param table The source table
+ * @return A list of the header rows
+ */
+ public static List<String> extractRowValues(Table table) {
+ List<RectangularTextContainer> firstRow = table.getRows().get(0);
Review comment:
Is it possible to `table.getRows()` is null?
##########
File path: contrib/format-pdf/src/test/java/org/apache/drill/exec/store/pdf/TestPdfFormat.java
##########
@@ -0,0 +1,229 @@
+/*
+ * 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.pdf;
+
+import org.apache.drill.categories.RowSetTests;
+import org.apache.drill.common.types.TypeProtos.MinorType;
+import org.apache.drill.exec.physical.rowSet.RowSet;
+import org.apache.drill.exec.physical.rowSet.RowSetBuilder;
+import org.apache.drill.exec.record.metadata.SchemaBuilder;
+import org.apache.drill.exec.record.metadata.TupleMetadata;
+import org.apache.drill.exec.rpc.RpcException;
+import org.apache.drill.test.ClusterFixture;
+import org.apache.drill.test.ClusterTest;
+import org.apache.drill.test.QueryBuilder;
+import org.apache.drill.test.QueryBuilder.QuerySummary;
+import org.apache.drill.test.rowSet.RowSetComparison;
+import org.junit.BeforeClass;
+import org.junit.Test;
+import org.junit.experimental.categories.Category;
+
+import java.nio.file.Paths;
+import java.time.LocalDate;
+
+import static org.apache.drill.test.QueryTestUtil.generateCompressedFile;
+import static org.junit.Assert.assertEquals;
+
+@Category(RowSetTests.class)
+public class TestPdfFormat extends ClusterTest {
+
+ @BeforeClass
+ public static void setup() throws Exception {
+ ClusterTest.startCluster(ClusterFixture.builder(dirTestWatcher));
+
+ // Needed for compressed file unit test
+ dirTestWatcher.copyResourceToRoot(Paths.get("pdf/"));
+ }
+
+ @Test
+ public void testStarQuery() throws RpcException {
+ String sql = "SELECT * FROM cp.`pdf/argentina_diputados_voting_record.pdf` WHERE `Provincia` = 'Rio Negro'";
+
+ QueryBuilder q = client.queryBuilder().sql(sql);
+ RowSet results = q.rowSet();
+
+ TupleMetadata expectedSchema = new SchemaBuilder()
+ .addNullable("Apellido y Nombre", MinorType.VARCHAR)
+ .addNullable("Bloque político", MinorType.VARCHAR)
+ .addNullable("Provincia", MinorType.VARCHAR)
+ .addNullable("field_0", MinorType.VARCHAR)
+ .buildSchema();
+
+ RowSet expected = new RowSetBuilder(client.allocator(), expectedSchema)
+ .addRow("ALBRIEU, Oscar Edmundo Nicolas", "Frente para la Victoria - PJ", "Rio Negro", "AFIRMATIVO")
+ .addRow("AVOSCAN, Herman Horacio", "Frente para la Victoria - PJ", "Rio Negro", "AFIRMATIVO")
+ .addRow("CEJAS, Jorge Alberto", "Frente para la Victoria - PJ", "Rio Negro", "AFIRMATIVO")
+ .build();
+
+ new RowSetComparison(expected).verifyAndClearAll(results);
+ }
+
+ @Test
+ public void testExplicitQuery() throws RpcException {
+ String sql = "SELECT `Apellido y Nombre`, `Bloque político`, `Provincia`, `field_0` " +
+ "FROM cp.`pdf/argentina_diputados_voting_record.pdf` WHERE `Provincia` = 'Rio Negro'";
+
+ QueryBuilder q = client.queryBuilder().sql(sql);
+ RowSet results = q.rowSet();
+
+ TupleMetadata expectedSchema = new SchemaBuilder()
+ .addNullable("Apellido y Nombre", MinorType.VARCHAR)
+ .addNullable("Bloque político", MinorType.VARCHAR)
+ .addNullable("Provincia", MinorType.VARCHAR)
+ .addNullable("field_0", MinorType.VARCHAR)
Review comment:
A good solution to the blank header.
##########
File path: contrib/format-pdf/src/main/java/org/apache/drill/exec/store/pdf/PdfBatchReader.java
##########
@@ -0,0 +1,549 @@
+/*
+ * 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.pdf;
+
+import org.apache.drill.common.types.TypeProtos.DataMode;
+import org.apache.drill.exec.record.MaterializedField;
+import org.apache.drill.shaded.guava.com.google.common.base.Strings;
+import org.apache.drill.common.AutoCloseables;
+import org.apache.drill.common.exceptions.CustomErrorContext;
+import org.apache.drill.common.exceptions.UserException;
+import org.apache.drill.common.types.TypeProtos;
+import org.apache.drill.common.types.TypeProtos.MinorType;
+import org.apache.drill.exec.physical.impl.scan.file.FileScanFramework;
+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.ColumnMetadata;
+import org.apache.drill.exec.record.metadata.MetadataUtils;
+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.drill.exec.vector.accessor.TupleWriter;
+import org.apache.hadoop.mapred.FileSplit;
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.pdmodel.PDDocumentInformation;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+import technology.tabula.RectangularTextContainer;
+import technology.tabula.Table;
+
+import java.io.InputStream;
+import java.text.ParseException;
+import java.text.SimpleDateFormat;
+import java.time.Instant;
+import java.time.LocalDate;
+import java.time.LocalTime;
+import java.time.format.DateTimeFormatter;
+import java.util.ArrayList;
+import java.util.Calendar;
+import java.util.Date;
+import java.util.List;
+
+public class PdfBatchReader implements ManagedReader<FileScanFramework.FileSchemaNegotiator> {
+
+ private static final Logger logger = LoggerFactory.getLogger(PdfBatchReader.class);
+ private static final String NEW_FIELD_PREFIX = "field_";
+ private final int maxRecords;
+
+ private final List<PdfColumnWriter> writers;
+ private FileSplit split;
+ private CustomErrorContext errorContext;
+ private RowSetLoader rowWriter;
+ private InputStream fsStream;
+ private PDDocument document;
+ private PdfReaderConfig config;
+
+ private SchemaBuilder builder;
+ private List<String> columnHeaders;
+ private int currentRowIndex;
+ private Table currentTable;
+ private int currentTableIndex;
+ private int startingTableIndex;
+ private FileScanFramework.FileSchemaNegotiator negotiator;
+
+ // Document Metadata Fields
+ private int pageCount;
+ private String title;
+ private String author;
+ private String subject;
+ private String keywords;
+ private String creator;
+ private String producer;
+ private Calendar creationDate;
+ private Calendar modificationDate;
+ private String trapped;
+ private int unregisteredColumnCount;
+ private int columns;
+ private int tableCount;
+ private int rows;
+ private int metadataIndex;
+
+
+ // Tables
+ private List<Table> tables;
+
+
+ static class PdfReaderConfig {
+ final PdfFormatPlugin plugin;
+
+ PdfReaderConfig(PdfFormatPlugin plugin) {
+ this.plugin = plugin;
+ }
+ }
+
+ public PdfBatchReader(PdfReaderConfig readerConfig, int maxRecords) {
+ this.maxRecords = maxRecords;
+ this.unregisteredColumnCount = 0;
+ this.writers = new ArrayList<>();
+ this.config = readerConfig;
+ this.startingTableIndex = readerConfig.plugin.getConfig().getDefaultTableIndex() < 0 ? 0 : readerConfig.plugin.getConfig().getDefaultTableIndex();
+ this.currentTableIndex = this.startingTableIndex;
+ this.columnHeaders = new ArrayList<>();
+ }
+
+ @Override
+ public boolean open(FileScanFramework.FileSchemaNegotiator negotiator) {
+ System.setProperty("java.awt.headless", "true");
+ this.negotiator = negotiator;
+
+ split = negotiator.split();
+ errorContext = negotiator.parentErrorContext();
+ builder = new SchemaBuilder();
+
+ openFile();
+
+ // Get the tables
+ tables = Utils.extractTablesFromPDF(document);
+ populateMetadata();
+ logger.debug("Found {} tables", tables.size());
+
+ // Support provided schema
+ TupleMetadata schema = null;
+ if (this.negotiator.hasProvidedSchema()) {
+ schema = this.negotiator.providedSchema();
+ this.negotiator.tableSchema(schema, false);
+ } else {
+ this.negotiator.tableSchema(buildSchema(), false);
+ }
+ ResultSetLoader loader = this.negotiator.build();
+ rowWriter = loader.writer();
+
+ if (negotiator.hasProvidedSchema()) {
+ buildWriterListFromProvidedSchema(schema);
+ } else {
+ buildWriterList();
+ }
+ addImplicitColumnsToSchema();
+
+ // Prepare for reading
+ currentRowIndex = 1; // Skip the first line if there are headers
+ currentTable = tables.get(startingTableIndex);
Review comment:
What happens if `tables.size() < startingTableIndex`?
##########
File path: contrib/format-pdf/src/test/resources/logback-test.xml
##########
@@ -0,0 +1,57 @@
+<?xml version="1.0" encoding="UTF-8" ?>
Review comment:
Please remove this file or move to `/dev-support` folder.
##########
File path: contrib/format-pdf/src/test/java/org/apache/drill/exec/store/pdf/testPDFUtils.java
##########
@@ -0,0 +1,78 @@
+/*
+ * 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.pdf;
+
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.junit.Test;
+import technology.tabula.Table;
+import java.io.File;
+import java.util.List;
+
+import static org.junit.Assert.assertEquals;
+
+
+public class testPDFUtils {
Review comment:
Use the `TestPDFUtils`.
--
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.
To unsubscribe, e-mail: dev-unsubscribe@drill.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org