[GitHub] [drill] cgivre commented on a change in pull request #2359: DRILL-8028: Add PDF Format Plugin

[GitBox <gi...@apache.org>]

cgivre commented on a change in pull request #2359:
URL: https://github.com/apache/drill/pull/2359#discussion_r768094421



##########
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) {

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.

To unsubscribe, e-mail: dev-unsubscribe@drill.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org