mirror of
https://github.com/apache/poi.git
synced 2026-02-27 20:40:08 +08:00
482 lines
18 KiB
HTML
482 lines
18 KiB
HTML
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
|
|
<html>
|
|
<head>
|
|
<META http-equiv="Content-Type" content="text/html; charset=UTF-8">
|
|
<meta content="Apache Forrest" name="Generator">
|
|
<meta name="Forrest-version" content="0.9">
|
|
<meta name="Forrest-skin-name" content="pelt">
|
|
<title>Apache POI™ - Text Extraction</title>
|
|
<link type="text/css" href="skin/basic.css" rel="stylesheet">
|
|
<link media="screen" type="text/css" href="skin/screen.css" rel="stylesheet">
|
|
<link media="print" type="text/css" href="skin/print.css" rel="stylesheet">
|
|
<link type="text/css" href="skin/profile.css" rel="stylesheet">
|
|
<script src="skin/getBlank.js" language="javascript" type="text/javascript"></script><script src="skin/getMenu.js" language="javascript" type="text/javascript"></script><script src="skin/fontsize.js" language="javascript" type="text/javascript"></script>
|
|
<link rel="shortcut icon" href="images/favicon.ico">
|
|
</head>
|
|
<body onload="init()">
|
|
<script type="text/javascript">ndeSetTextSize();</script>
|
|
<div id="top">
|
|
<!--+
|
|
|breadtrail
|
|
+-->
|
|
<div class="breadtrail">
|
|
<a href="https://www.apache.org">Apache Software Foundation</a> > <a href="https://poi.apache.org">Apache POI</a><script src="skin/breadcrumbs.js" language="JavaScript" type="text/javascript"></script>
|
|
</div>
|
|
<!--+
|
|
|header
|
|
+-->
|
|
<div class="header">
|
|
<!--+
|
|
|start group logo
|
|
+-->
|
|
<div class="grouplogo">
|
|
<a href="https://www.apache.org"><img class="logoImage" alt="Apache Software Foundation" src="images/asflogo_horizontal_color.svg" title="The Apache Software Foundation is a cornerstone of the modern Open Source software ecosystem – supporting some of the most widely used and important software solutions powering today's Internet economy."></a>
|
|
</div>
|
|
<!--+
|
|
|end group logo
|
|
+-->
|
|
<!--+
|
|
|start Project Logo
|
|
+-->
|
|
<div class="projectlogo">
|
|
<a href="https://poi.apache.org"><img class="logoImage" alt="Apache POI" src="images/project-header.png" title="Apache POI is well-known in the Java field as a library for reading and writing Microsoft Office file formats, such as Excel, PowerPoint, Word, Visio, Publisher and Outlook. It supports both the older (OLE2) and new (OOXML - Office Open XML) formats."></a>
|
|
</div>
|
|
<!--+
|
|
|end Project Logo
|
|
+-->
|
|
<!--+
|
|
|start Search
|
|
+-->
|
|
<div class="searchbox">
|
|
<form action="https://www.google.com/search" method="get" class="roundtopsmall">
|
|
<input value="poi.apache.org" name="sitesearch" type="hidden"><input onFocus="getBlank (this, 'Search the site with google');" size="25" name="q" id="query" type="text" value="Search the site with google">
|
|
<input name="Search" value="Search" type="submit">
|
|
</form>
|
|
</div>
|
|
<!--+
|
|
|end search
|
|
+-->
|
|
<!--+
|
|
|start Tabs
|
|
+-->
|
|
<ul id="tabs">
|
|
<li class="current">
|
|
<a class="selected" href="index.html">Home</a>
|
|
</li>
|
|
<li>
|
|
<a class="unselected" href="help/index.html">Help</a>
|
|
</li>
|
|
<li>
|
|
<a class="unselected" href="components/index.html">Component APIs</a>
|
|
</li>
|
|
<li>
|
|
<a class="unselected" href="devel/index.html">Getting Involved</a>
|
|
</li>
|
|
</ul>
|
|
<!--+
|
|
|end Tabs
|
|
+-->
|
|
</div>
|
|
</div>
|
|
<div id="main">
|
|
<div id="publishedStrip">
|
|
<!--+
|
|
|start Subtabs
|
|
+-->
|
|
<div id="level2tabs"></div>
|
|
<!--+
|
|
|end Endtabs
|
|
+-->
|
|
<script type="text/javascript"><!--
|
|
document.write("Last Published: " + document.lastModified);
|
|
// --></script>
|
|
</div>
|
|
<!--+
|
|
|breadtrail
|
|
+-->
|
|
<div class="breadtrail">
|
|
|
|
|
|
</div>
|
|
<!--+
|
|
|start Menu, mainarea
|
|
+-->
|
|
<!--+
|
|
|start Menu
|
|
+-->
|
|
<div id="menu">
|
|
<div onclick="SwitchMenu('menu_selected_1.1', 'skin/')" id="menu_selected_1.1Title" class="menutitle" style="background-image: url('skin/images/chapter_open.gif');">Overview</div>
|
|
<div id="menu_selected_1.1" class="selectedmenuitemgroup" style="display: block;">
|
|
<div class="menuitem">
|
|
<a href="index.html">Home</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="download.html">Download</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="versioning.html">Versioning</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="changes.html">Changelog</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="apidocs/index.html">Javadocs</a>
|
|
</div>
|
|
<div class="menupage">
|
|
<div class="menupagetitle">Text Extraction</div>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="encryption.html">Encryption support</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="security.html">Secure processing</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="casestudies.html">Case Studies</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="related-projects.html">Related projects</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="commercial-support.html">Commercial Support</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="legal.html">Legal</a>
|
|
</div>
|
|
</div>
|
|
<div onclick="SwitchMenu('menu_1.2', 'skin/')" id="menu_1.2Title" class="menutitle">Apache Wide</div>
|
|
<div id="menu_1.2" class="menuitemgroup">
|
|
<div class="menuitem">
|
|
<a href="https://www.apache.org/">Apache Software Foundation</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="https://www.apache.org/licenses/">License</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="https://www.apache.org/security/">Security</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="https://privacy.apache.org/policies/privacy-policy-public.html">Privacy</a>
|
|
</div>
|
|
</div>
|
|
<div id="credit"></div>
|
|
<div id="roundbottom">
|
|
<img style="display: none" class="corner" height="15" width="15" alt="" src="skin/images/rc-b-l-15-1body-2menu-3menu.png"></div>
|
|
<!--+
|
|
|alternative credits
|
|
+-->
|
|
<div id="credit2">
|
|
<a href="https://donate.apache.org/"><img border="0" title="Support Apache" alt="Support Apache - logo" src="images/support-asf.png" style="width: 125px;height: 125px;"></a><a href="https://www.apache.org/foundation/press/kit/#poweredby"><img border="0" title="powered by POI" alt="powered by POI - logo" src="images/poweredby-poi-logo.png" style="width: 125px;height: 125px;"></a>
|
|
</div>
|
|
</div>
|
|
<!--+
|
|
|end Menu
|
|
+-->
|
|
<!--+
|
|
|start content
|
|
+-->
|
|
<div id="content">
|
|
<h1>Apache POI™ - Text Extraction</h1>
|
|
<div id="front-matter"></div>
|
|
|
|
<a name="Overview"></a>
|
|
<h2 class="boxed">Overview</h2>
|
|
<div class="section">
|
|
<p>For a number of years now, Apache POI has provided basic
|
|
text extraction for all the project supported file formats. In
|
|
addition, as well as the (plain) text, these provides access to
|
|
the metadata associated with a given file, such as title and
|
|
author.</p>
|
|
<p>For more advanced text extraction needs, including Rich Text
|
|
extraction (such as formatting and styling), along with XML and
|
|
HTML output, Apache POI works closely with
|
|
<a href="https://tika.apache.org/">Apache Tika</a> to deliver
|
|
POI-powered Tika Parsers for all the project supported file formats.</p>
|
|
<p>If you are after turn-key text extraction, including the latest
|
|
support, styles etc, you are strongly advised to make use of
|
|
<a href="https://tika.apache.org/">Apache Tika</a>, which builds
|
|
on top of POI to provide Text and Metadata extraction. If you wish
|
|
to have something very simple and stand-alone, or you wish to make
|
|
heavy modifications, then the POI provided text extractors documented
|
|
below might be a better fit for your needs.</p>
|
|
</div>
|
|
|
|
|
|
<a name="Common+functionality"></a>
|
|
<h2 class="boxed">Common functionality</h2>
|
|
<div class="section">
|
|
<p>All of the POI text extractors extend from
|
|
<em>org.apache.poi.extractor.POITextExtractor</em>. This provides a common
|
|
method across all extractors, getText(). For many cases, the text
|
|
returned will be all you need. However, many extractors do provide
|
|
more targeted text extraction methods, so you may wish to use
|
|
these in some cases.</p>
|
|
<p>All POIFS / OLE 2 based text extractors also extend from
|
|
<em>org.apache.poi.extractor.POIOLE2TextExtractor</em>. This additionally
|
|
provides common methods to get at the <a href="hpfs/">HPFS
|
|
document metadata</a>.</p>
|
|
<p>All OOXML based text extractors also extend from
|
|
<em>org.apache.poi.POIOOXMLTextExtractor</em>. This additionally
|
|
provides common methods to get at the OOXML metadata.</p>
|
|
</div>
|
|
|
|
|
|
<a name="Text+Extractor+Factory"></a>
|
|
<h2 class="boxed">Text Extractor Factory</h2>
|
|
<div class="section">
|
|
<p>POI provides a common class to select the appropriate text extractor
|
|
for you, based on the supplied document's contents.
|
|
<em>ExtractorFactory</em> provides a
|
|
similar function to WorkbookFactory. You simply pass it an
|
|
InputStream, a File, a POIFSFileSystem or a OOXML Package. It
|
|
figures out the correct text extractor for you, and returns it.</p>
|
|
<p>For complete detection and text extractor auto-selection, users
|
|
are strongly encouraged to investigate
|
|
<a href="https://tika.apache.org/">Apache Tika</a>.</p>
|
|
</div>
|
|
|
|
|
|
<a name="Excel"></a>
|
|
<h2 class="boxed">Excel</h2>
|
|
<div class="section">
|
|
<p>For .xls files, there is
|
|
<em>org.apache.poi.hssf.extractor.ExcelExtractor</em>, which will
|
|
return text, optionally with formulas instead of their contents.
|
|
Similarly, for .xlsx files there is
|
|
<em>org.apache.poi.xssf.extractor.XSSFExcelExtractor</em>, which
|
|
provides the same functionality.</p>
|
|
<p>For those working in constrained memory footprints, there are
|
|
two more Excel text extractors available. For .xls files, it's
|
|
<em>org.apache.poi.hssf.extractor.EventBasedExcelExtractor</em>,
|
|
based on the streaming EventUserModel code, and will generally
|
|
deliver a lower memory footprint for extraction. However, it will
|
|
have problems correctly outputting more complex formulas, as it
|
|
works with records as they pass, and so doesn't have access to all
|
|
parts of complex and shared formulas. For .xlsx files the equivalent is
|
|
<em>org.apache.poi.xssf.extractor.XSSFEventBasedExcelExtractor</em>,
|
|
which is based on the XSSF SAX Event codebase.</p>
|
|
</div>
|
|
|
|
|
|
<a name="Word"></a>
|
|
<h2 class="boxed">Word</h2>
|
|
<div class="section">
|
|
<p>For .doc files from Word 97 - Word 2003, in scratchpad there is
|
|
<em>org.apache.poi.hwpf.extractor.WordExtractor</em>, which will
|
|
return text for your document.</p>
|
|
<p>You can also extract simple textual content from
|
|
older Word 6 and Word 95 files, using the scratchpad class
|
|
<em>org.apache.poi.hwpf.extractor.Word6Extractor</em>.</p>
|
|
<p>For .docx files, the relevant class is
|
|
<em>org.apache.poi.xwpf.extractor.XWPFWordExtractor</em>
|
|
</p>
|
|
</div>
|
|
|
|
|
|
<a name="PowerPoint"></a>
|
|
<h2 class="boxed">PowerPoint</h2>
|
|
<div class="section">
|
|
<p>For .ppt and .pptx files, there is common extractor
|
|
<em>org.apache.poi.sl.extractor.SlideShowExtractor.SlideShowExtractor</em>, which
|
|
will return text for your slideshow, optionally restricted to just
|
|
slides text or notes text. For .ppt you need to add the poi-scratchpad.jar
|
|
and for .pptx the poi-ooxml.jar and its dependencies are needed</p>
|
|
</div>
|
|
|
|
|
|
<a name="Publisher"></a>
|
|
<h2 class="boxed">Publisher</h2>
|
|
<div class="section">
|
|
<p>For .pub files, in scratchpad there is
|
|
<em>org.apache.poi.hpbf.extractor.PublisherExtractor</em>, which
|
|
will return text for your file.</p>
|
|
</div>
|
|
|
|
|
|
<a name="Visio"></a>
|
|
<h2 class="boxed">Visio</h2>
|
|
<div class="section">
|
|
<p>For .vsd files, in scratchpad there is
|
|
<em>org.apache.poi.hdgf.extractor.VisioTextExtractor</em>, which
|
|
will return text for your file.</p>
|
|
</div>
|
|
|
|
|
|
<a name="Embedded+Objects"></a>
|
|
<h2 class="boxed">Embedded Objects</h2>
|
|
<div class="section">
|
|
<p>Extractors already exist for Excel, Word, PowerPoint and Visio;
|
|
if one of these objects is embedded into a worksheet, the ExtractorFactory class can be used to recover an extractor for it.
|
|
</p>
|
|
<div class="code">
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"></span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody">FileInputStream fis = new FileInputStream(inputFile);</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody">POIFSFileSystem fileSystem = new POIFSFileSystem(fis);</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody">// Firstly, get an extractor for the Workbook</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody">POIOLE2TextExtractor oleTextExtractor = </span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> ExtractorFactory.createExtractor(fileSystem);</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody">// Then a List of extractors for any embedded Excel, Word, PowerPoint</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody">// or Visio objects embedded into it.</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody">POITextExtractor[] embeddedExtractors =</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> ExtractorFactory.getEmbededDocsTextExtractors(oleTextExtractor);</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody">for (POITextExtractor textExtractor : embeddedExtractors) {</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> // If the embedded object was an Excel spreadsheet.</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> if (textExtractor instanceof ExcelExtractor) {</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> ExcelExtractor excelExtractor = (ExcelExtractor) textExtractor;</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> System.out.println(excelExtractor.getText());</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> }</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> // A Word Document</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> else if (textExtractor instanceof WordExtractor) {</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> WordExtractor wordExtractor = (WordExtractor) textExtractor;</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> String[] paragraphText = wordExtractor.getParagraphText();</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> for (String paragraph : paragraphText) {</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> System.out.println(paragraph);</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> }</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> // Display the document's header and footer text</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> System.out.println("Footer text: " + wordExtractor.getFooterText());</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> System.out.println("Header text: " + wordExtractor.getHeaderText());</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> }</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> // PowerPoint Presentation.</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> else if (textExtractor instanceof PowerPointExtractor) {</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> PowerPointExtractor powerPointExtractor =</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> (PowerPointExtractor) textExtractor;</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> System.out.println("Text: " + powerPointExtractor.getText());</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> System.out.println("Notes: " + powerPointExtractor.getNotes());</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> }</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> // Visio Drawing</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> else if (textExtractor instanceof VisioTextExtractor) {</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> VisioTextExtractor visioTextExtractor = </span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> (VisioTextExtractor) textExtractor;</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> System.out.println("Text: " + visioTextExtractor.getText());</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> }</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody">}</span>
|
|
</div>
|
|
<div class="codeline">
|
|
<span class="lineno"></span><span class="codebody"> </span>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
<p align="right">
|
|
<font size="-2">by Nick Burch</font>
|
|
</p>
|
|
</div>
|
|
<!--+
|
|
|end content
|
|
+-->
|
|
<div class="clearboth"> </div>
|
|
</div>
|
|
<div id="footer">
|
|
<!--+
|
|
|start bottomstrip
|
|
+-->
|
|
<div class="lastmodified">
|
|
<script type="text/javascript"><!--
|
|
document.write("Last Published: " + document.lastModified);
|
|
// --></script>
|
|
</div>
|
|
<div class="copyright">
|
|
Copyright ©
|
|
2001-2026 <a href="https://www.apache.org/">The Apache Software Foundation</a>
|
|
<br>
|
|
Apache POI, POI, Apache, the Apache logo, and the Apache
|
|
POI project logo are trademarks of The Apache Software Foundation.
|
|
</div>
|
|
<div id="feedback">
|
|
Send feedback about the website to:
|
|
<a id="feedbackto" href="mailto:dev@poi.apache.org?subject=Feedback%C2%A0text-extraction.html">dev@poi.apache.org</a>
|
|
</div>
|
|
<!--+
|
|
|end bottomstrip
|
|
+-->
|
|
</div>
|
|
</body>
|
|
</html>
|