Support for extracting text from ooxml word documents

git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@607560 13f79535-47bb-0310-9956-ffa450edef68

src/scratchpad/ooxml-src/org/apache/poi/hssf/extractor/HXFExcelExtractor.java

@@ -16,12 +16,14 @@
 ==================================================================== */
 package org.apache.poi.hssf.extractor;
 
+import java.io.File;
 import java.io.IOException;
 
 import org.apache.poi.POIXMLTextExtractor;
 import org.apache.poi.hssf.HSSFXML;
 import org.apache.poi.hssf.usermodel.HSSFXMLCell;
 import org.apache.poi.hssf.usermodel.HSSFXMLWorkbook;
+import org.apache.poi.hxf.HXFDocument;
 import org.apache.xmlbeans.XmlException;
 import org.openxml4j.exceptions.OpenXML4JException;
 import org.openxml4j.opc.Package;
@@ -30,6 +32,9 @@ import org.openxmlformats.schemas.spreadsheetml.x2006.main.CTRow;
 import org.openxmlformats.schemas.spreadsheetml.x2006.main.CTSheet;
 import org.openxmlformats.schemas.spreadsheetml.x2006.main.CTWorksheet;
 
+/**
+ * Helper class to extract text from an OOXML Excel file
+ */
 public class HXFExcelExtractor extends POIXMLTextExtractor {
 	private HSSFXMLWorkbook workbook;
 	private boolean includeSheetNames = true;
@@ -45,6 +50,19 @@ public class HXFExcelExtractor extends POIXMLTextExtractor {
 		this.workbook = workbook;
 	}
 	
+	public static void main(String[] args) throws Exception {
+		if(args.length < 1) {
+			System.err.println("Use:");
+			System.err.println("  HXFExcelExtractor <filename.xlsx>");
+			System.exit(1);
+		}
+		POIXMLTextExtractor extractor = 
+			new HXFExcelExtractor(HXFDocument.openPackage(
+					new File(args[0])
+			));
+		System.out.println(extractor.getText());
+	}
+
 	/**
 	 * Should sheet names be included? Default is true
 	 */

src/scratchpad/ooxml-src/org/apache/poi/hssf/usermodel/HSSFXMLWorkbook.java

@@ -19,6 +19,12 @@ package org.apache.poi.hssf.usermodel;
 import org.apache.poi.POIXMLDocument;
 import org.apache.poi.hssf.HSSFXML;
 
+/**
+ * High level representation of a ooxml workbook.
+ * This is the first object most users will construct whether
+ *  they are reading or writing a workbook. It is also the
+ *  top level object for creating new sheets/etc.
+ */
 public class HSSFXMLWorkbook extends POIXMLDocument {
 	private HSSFXML hssfXML;
 	

src/scratchpad/ooxml-src/org/apache/poi/hwpf/extractor/HXFWordExtractor.java

@@ -0,0 +1,87 @@
+/* ====================================================================
+   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.poi.hwpf.extractor;
+
+import java.io.File;
+import java.io.IOException;
+
+import org.apache.poi.POIXMLTextExtractor;
+import org.apache.poi.hwpf.HWPFXML;
+import org.apache.poi.hwpf.usermodel.HWPFXMLDocument;
+import org.apache.poi.hxf.HXFDocument;
+import org.apache.xmlbeans.XmlException;
+import org.openxml4j.exceptions.OpenXML4JException;
+import org.openxml4j.opc.Package;
+import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTBody;
+import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTP;
+import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTR;
+import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTText;
+
+/**
+ * Helper class to extract text from an OOXML Word file
+ */
+public class HXFWordExtractor extends POIXMLTextExtractor {
+	private HWPFXMLDocument document;
+	
+	public HXFWordExtractor(Package container) throws XmlException, OpenXML4JException, IOException {
+		this(new HWPFXMLDocument(
+				new HWPFXML(container)
+		));
+	}
+	public HXFWordExtractor(HWPFXMLDocument document) {
+		super(document);
+		this.document = document;
+	}
+	
+	public static void main(String[] args) throws Exception {
+		if(args.length < 1) {
+			System.err.println("Use:");
+			System.err.println("  HXFWordExtractor <filename.xlsx>");
+			System.exit(1);
+		}
+		POIXMLTextExtractor extractor = 
+			new HXFWordExtractor(HXFDocument.openPackage(
+					new File(args[0])
+			));
+		System.out.println(extractor.getText());
+	}
+
+	public String getText() {
+		CTBody body = document._getHWPFXML().getDocumentBody();
+		StringBuffer text = new StringBuffer();
+		
+		// Loop over paragraphs
+		CTP[] ps = body.getPArray();
+		for (int i = 0; i < ps.length; i++) {
+			// Loop over ranges
+			CTR[] rs = ps[i].getRArray();
+			for (int j = 0; j < rs.length; j++) {
+				// Loop over text runs
+				CTText[] texts = rs[j].getTArray();
+				for (int k = 0; k < texts.length; k++) {
+					text.append(
+							texts[k].getStringValue()
+					);
+				}
+			}
+			// New line after each paragraph.
+			text.append("\n");
+		}
+		
+		return text.toString();
+	}
+}

src/scratchpad/ooxml-src/org/apache/poi/hwpf/usermodel/HWPFXMLDocument.java

@@ -0,0 +1,36 @@
+/* ====================================================================
+   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.poi.hwpf.usermodel;
+
+import org.apache.poi.POIXMLDocument;
+import org.apache.poi.hwpf.HWPFXML;
+
+/**
+ * High level representation of a ooxml text document.
+ */
+public class HWPFXMLDocument extends POIXMLDocument {
+	private HWPFXML hwpfXML;
+	
+	public HWPFXMLDocument(HWPFXML xml) {
+		super(xml);
+		this.hwpfXML = xml;
+	}
+	
+	public HWPFXML _getHWPFXML() {
+		return hwpfXML;
+	}
+}

src/scratchpad/ooxml-testcases/org/apache/poi/hwpf/TestHWPFXML.java

@@ -18,7 +18,6 @@ package org.apache.poi.hwpf;
 
 import java.io.File;
 
-import org.apache.poi.hssf.HSSFXML;
 import org.apache.poi.hxf.HXFDocument;
 import org.openxml4j.opc.Package;
 import org.openxml4j.opc.PackagePart;

src/scratchpad/ooxml-testcases/org/apache/poi/hwpf/extractor/TestHXFWordExtractor.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.poi.hwpf.extractor;
+
+import java.io.File;
+
+import org.apache.poi.hwpf.HWPFXML;
+import org.apache.poi.hwpf.usermodel.HWPFXMLDocument;
+import org.apache.poi.hxf.HXFDocument;
+
+import junit.framework.TestCase;
+
+/**
+ * Tests for HXFWordExtractor
+ */
+public class TestHXFWordExtractor extends TestCase {
+	/**
+	 * A very simple file
+	 */
+	private HWPFXML xmlA;
+	/**
+	 * A fairly complex file
+	 */
+	private HWPFXML xmlB;
+
+	protected void setUp() throws Exception {
+		super.setUp();
+		
+		File fileA = new File(
+				System.getProperty("HWPF.testdata.path") +
+				File.separator + "sample.docx"
+		);
+		File fileB = new File(
+				System.getProperty("HWPF.testdata.path") +
+				File.separator + "IllustrativeCases.docx"
+		);
+		
+		xmlA = new HWPFXML(HXFDocument.openPackage(fileA));
+		xmlB = new HWPFXML(HXFDocument.openPackage(fileB));
+	}
+
+	/**
+	 * Get text out of the simple file
+	 */
+	public void testGetSimpleText() throws Exception {
+		new HXFWordExtractor(xmlA.getPackage());
+		new HXFWordExtractor(new HWPFXMLDocument(xmlA));
+		
+		HXFWordExtractor extractor = 
+			new HXFWordExtractor(xmlA.getPackage());
+		extractor.getText();
+		
+		String text = extractor.getText();
+		assertTrue(text.length() > 0);
+		
+		// Check contents
+		assertTrue(text.startsWith(
+				"Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Nunc at risus vel erat tempus posuere. Aenean non ante. Suspendisse vehicula dolor sit amet odio."
+		));
+		assertTrue(text.endsWith(
+				"Phasellus ultricies mi nec leo. Sed tempus. In sit amet lorem at velit faucibus vestibulum.\n"
+		));
+		
+		// Check number of paragraphs
+		int ps = 0;
+		char[] t = text.toCharArray();
+		for (int i = 0; i < t.length; i++) {
+			if(t[i] == '\n') { ps++; }
+		}
+		assertEquals(3, ps);
+	}
+	
+	/**
+	 * Tests getting the text out of a complex file
+	 */
+	public void testGetComplexText() throws Exception {
+		HXFWordExtractor extractor = 
+			new HXFWordExtractor(xmlB.getPackage());
+		extractor.getText();
+		
+		String text = extractor.getText();
+		assertTrue(text.length() > 0);
+		
+		char euro = '\u20ac';
+		System.err.println("'"+text.substring(text.length() - 20) + "'");
+		
+		// Check contents
+		assertTrue(text.startsWith(
+				"  \n(V) ILLUSTRATIVE CASES\n\n"
+		));
+		assertTrue(text.endsWith(
+				"As well as gaining "+euro+"90 from child benefit increases, he will also receive the early childhood supplement of "+euro+"250 per quarter for Vincent for the full four quarters of the year.\n\n\n\n \n\n\n"
+		));
+		
+		// Check number of paragraphs
+		int ps = 0;
+		char[] t = text.toCharArray();
+		for (int i = 0; i < t.length; i++) {
+			if(t[i] == '\n') { ps++; }
+		}
+		assertEquals(79, ps);
+	}
+}