2007-10-27 17:57:10 -04:00
|
|
|
/* ====================================================================
|
|
|
|
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;
|
|
|
|
|
2013-06-17 03:53:59 -04:00
|
|
|
import java.io.Closeable;
|
|
|
|
import java.io.IOException;
|
|
|
|
|
2007-10-27 17:57:10 -04:00
|
|
|
/**
|
|
|
|
* Common Parent for Text Extractors
|
|
|
|
* of POI Documents.
|
|
|
|
* You will typically find the implementation of
|
|
|
|
* a given format's text extractor under
|
|
|
|
* org.apache.poi.[format].extractor .
|
|
|
|
* @see org.apache.poi.hssf.extractor.ExcelExtractor
|
|
|
|
* @see org.apache.poi.hslf.extractor.PowerPointExtractor
|
|
|
|
* @see org.apache.poi.hdgf.extractor.VisioTextExtractor
|
|
|
|
* @see org.apache.poi.hwpf.extractor.WordExtractor
|
|
|
|
*/
|
2013-06-17 03:53:59 -04:00
|
|
|
public abstract class POITextExtractor implements Closeable {
|
2007-10-27 17:57:10 -04:00
|
|
|
/** The POIDocument that's open */
|
|
|
|
protected POIDocument document;
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Creates a new text extractor for the given document
|
|
|
|
*/
|
|
|
|
public POITextExtractor(POIDocument document) {
|
|
|
|
this.document = document;
|
|
|
|
}
|
2008-08-12 14:44:50 -04:00
|
|
|
/**
|
|
|
|
* Creates a new text extractor, using the same
|
|
|
|
* document as another text extractor. Normally
|
|
|
|
* only used by properties extractors.
|
|
|
|
*/
|
|
|
|
protected POITextExtractor(POITextExtractor otherExtractor) {
|
|
|
|
this.document = otherExtractor.document;
|
|
|
|
}
|
2007-10-27 17:57:10 -04:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Retrieves all the text from the document.
|
|
|
|
* How cells, paragraphs etc are separated in the text
|
|
|
|
* is implementation specific - see the javadocs for
|
|
|
|
* a specific project for details.
|
|
|
|
* @return All the text from the document
|
|
|
|
*/
|
|
|
|
public abstract String getText();
|
2008-08-12 15:02:41 -04:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Returns another text extractor, which is able to
|
|
|
|
* output the textual content of the document
|
|
|
|
* metadata / properties, such as author and title.
|
|
|
|
*/
|
|
|
|
public abstract POITextExtractor getMetadataTextExtractor();
|
2013-06-17 03:53:59 -04:00
|
|
|
|
|
|
|
/**
|
|
|
|
* Allows to free resources of the Extractor as soon as
|
|
|
|
* it is not needed any more. This may include closing
|
|
|
|
* open file handles and freeing memory.
|
|
|
|
*
|
|
|
|
* The Extractor cannot be used after close has been called.
|
|
|
|
*/
|
|
|
|
public void close() throws IOException {
|
|
|
|
// nothing to do in abstract class, derived classes may perform actions.
|
|
|
|
}
|
2007-10-27 17:57:10 -04:00
|
|
|
}
|