You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ma...@apache.org on 2008/01/07 04:06:42 UTC
svn commit: r609491 [9/11] - in /incubator/tika/site: ./ apidocs/
apidocs/org/apache/tika/config/ apidocs/org/apache/tika/config/class-use/
apidocs/org/apache/tika/exception/
apidocs/org/apache/tika/exception/class-use/
apidocs/org/apache/tika/metadata...
Modified: incubator/tika/site/xref/org/apache/tika/parser/html/package-frame.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/html/package-frame.html?rev=609491&r1=609490&r2=609491&view=diff
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/html/package-frame.html (original)
+++ incubator/tika/site/xref/org/apache/tika/parser/html/package-frame.html Sun Jan 6 19:06:26 2008
@@ -3,7 +3,7 @@
<html xml:lang="en" lang="en">
<head>
<meta http-equiv="content-type" content="text/html; charset=ISO-8859-1" />
- <title>Apache Tika 0.1-SNAPSHOT Reference Package org.apache.tika.parser.html</title>
+ <title>Apache Tika 0.2-SNAPSHOT Reference Package org.apache.tika.parser.html</title>
<link rel="stylesheet" type="text/css" href="../../../../../stylesheet.css" title="style" />
</head>
<body>
Modified: incubator/tika/site/xref/org/apache/tika/parser/html/package-summary.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/html/package-summary.html?rev=609491&r1=609490&r2=609491&view=diff
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/html/package-summary.html (original)
+++ incubator/tika/site/xref/org/apache/tika/parser/html/package-summary.html Sun Jan 6 19:06:26 2008
@@ -3,7 +3,7 @@
<html xml:lang="en" lang="en">
<head>
<meta http-equiv="content-type" content="text/html; charset=ISO-8859-1" />
- <title>Apache Tika 0.1-SNAPSHOT Reference Package org.apache.tika.parser.html</title>
+ <title>Apache Tika 0.2-SNAPSHOT Reference Package org.apache.tika.parser.html</title>
<link rel="stylesheet" type="text/css" href="../../../../../stylesheet.css" title="style" />
</head>
<body>
@@ -72,6 +72,6 @@
</ul>
</div>
<hr />
- Copyright © 2007 The Apache Software Foundation. All Rights Reserved.
+ Copyright © 2008 The Apache Software Foundation. All Rights Reserved.
</body>
</html>
Modified: incubator/tika/site/xref/org/apache/tika/parser/microsoft/ExcelParser.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/microsoft/ExcelParser.html?rev=609491&r1=609490&r2=609491&view=diff
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/microsoft/ExcelParser.html (original)
+++ incubator/tika/site/xref/org/apache/tika/parser/microsoft/ExcelParser.html Sun Jan 6 19:06:26 2008
@@ -43,59 +43,54 @@
<a name="33" href="#33">33</a> <strong class="jxr_keyword">return</strong> <span class="jxr_string">"application/vnd.ms-excel"</span>;
<a name="34" href="#34">34</a> }
<a name="35" href="#35">35</a>
-<a name="36" href="#36">36</a> <strong class="jxr_keyword">protected</strong> String extractText(POIFSFileSystem filesystem) <strong class="jxr_keyword">throws</strong> IOException{
-<a name="37" href="#37">37</a> StringBuilder builder = <strong class="jxr_keyword">new</strong> StringBuilder();
-<a name="38" href="#38">38</a> extractText(<strong class="jxr_keyword">new</strong> HSSFWorkbook(filesystem), builder);
-<a name="39" href="#39">39</a> <strong class="jxr_keyword">return</strong> builder.toString();
-<a name="40" href="#40">40</a> }
-<a name="41" href="#41">41</a>
-<a name="42" href="#42">42</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> extractText(HSSFWorkbook book, StringBuilder builder) {
-<a name="43" href="#43">43</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">int</strong> i = 0; book != <strong class="jxr_keyword">null</strong> && i < book.getNumberOfSheets(); i++) {
-<a name="44" href="#44">44</a> extractText(book.getSheetAt(i), builder);
-<a name="45" href="#45">45</a> }
-<a name="46" href="#46">46</a> }
-<a name="47" href="#47">47</a>
-<a name="48" href="#48">48</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> extractText(HSSFSheet sheet, StringBuilder builder) {
-<a name="49" href="#49">49</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">int</strong> i = 0; sheet != <strong class="jxr_keyword">null</strong> && i <= sheet.getLastRowNum(); i++) {
-<a name="50" href="#50">50</a> extractText(sheet.getRow(i), builder);
-<a name="51" href="#51">51</a> }
-<a name="52" href="#52">52</a> }
-<a name="53" href="#53">53</a>
-<a name="54" href="#54">54</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> extractText(HSSFRow row, StringBuilder builder) {
-<a name="55" href="#55">55</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">short</strong> i = 0; row != <strong class="jxr_keyword">null</strong> && i < row.getLastCellNum(); i++) {
-<a name="56" href="#56">56</a> extractText(row.getCell(i), builder);
-<a name="57" href="#57">57</a> }
-<a name="58" href="#58">58</a> }
-<a name="59" href="#59">59</a>
-<a name="60" href="#60">60</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> extractText(HSSFCell cell, StringBuilder builder) {
-<a name="61" href="#61">61</a> <strong class="jxr_keyword">if</strong> (cell != <strong class="jxr_keyword">null</strong>) {
-<a name="62" href="#62">62</a> <strong class="jxr_keyword">switch</strong> (cell.getCellType()) {
-<a name="63" href="#63">63</a> <strong class="jxr_keyword">case</strong> HSSFCell.CELL_TYPE_STRING:
-<a name="64" href="#64">64</a> addText(cell.getRichStringCellValue().getString(), builder);
-<a name="65" href="#65">65</a> <strong class="jxr_keyword">break</strong>;
-<a name="66" href="#66">66</a> <strong class="jxr_keyword">case</strong> HSSFCell.CELL_TYPE_NUMERIC:
-<a name="67" href="#67">67</a> <strong class="jxr_keyword">case</strong> HSSFCell.CELL_TYPE_FORMULA:
-<a name="68" href="#68">68</a> addText(Double.toString(cell.getNumericCellValue()), builder);
-<a name="69" href="#69">69</a> <strong class="jxr_keyword">break</strong>;
-<a name="70" href="#70">70</a> <strong class="jxr_keyword">default</strong>:
-<a name="71" href="#71">71</a> <em class="jxr_comment">// ignore</em>
-<a name="72" href="#72">72</a> }
-<a name="73" href="#73">73</a> }
-<a name="74" href="#74">74</a> }
-<a name="75" href="#75">75</a>
-<a name="76" href="#76">76</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> addText(String text, StringBuilder builder) {
-<a name="77" href="#77">77</a> <strong class="jxr_keyword">if</strong> (text != <strong class="jxr_keyword">null</strong>) {
-<a name="78" href="#78">78</a> text = text.trim();
-<a name="79" href="#79">79</a> <strong class="jxr_keyword">if</strong> (text.length() > 0) {
-<a name="80" href="#80">80</a> <strong class="jxr_keyword">if</strong> (builder.length() > 0) {
-<a name="81" href="#81">81</a> builder.append(' ');
-<a name="82" href="#82">82</a> }
-<a name="83" href="#83">83</a> builder.append(text);
-<a name="84" href="#84">84</a> }
-<a name="85" href="#85">85</a> }
-<a name="86" href="#86">86</a> }
-<a name="87" href="#87">87</a>
-<a name="88" href="#88">88</a> }
+<a name="36" href="#36">36</a> <strong class="jxr_keyword">protected</strong> <strong class="jxr_keyword">void</strong> extractText(POIFSFileSystem filesystem, Appendable builder) <strong class="jxr_keyword">throws</strong> IOException{
+<a name="37" href="#37">37</a> extractText(<strong class="jxr_keyword">new</strong> HSSFWorkbook(filesystem), builder);
+<a name="38" href="#38">38</a> }
+<a name="39" href="#39">39</a>
+<a name="40" href="#40">40</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> extractText(HSSFWorkbook book, Appendable builder) <strong class="jxr_keyword">throws</strong> IOException {
+<a name="41" href="#41">41</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">int</strong> i = 0; book != <strong class="jxr_keyword">null</strong> && i < book.getNumberOfSheets(); i++) {
+<a name="42" href="#42">42</a> extractText(book.getSheetAt(i), builder);
+<a name="43" href="#43">43</a> }
+<a name="44" href="#44">44</a> }
+<a name="45" href="#45">45</a>
+<a name="46" href="#46">46</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> extractText(HSSFSheet sheet, Appendable builder) <strong class="jxr_keyword">throws</strong> IOException {
+<a name="47" href="#47">47</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">int</strong> i = 0; sheet != <strong class="jxr_keyword">null</strong> && i <= sheet.getLastRowNum(); i++) {
+<a name="48" href="#48">48</a> extractText(sheet.getRow(i), builder);
+<a name="49" href="#49">49</a> }
+<a name="50" href="#50">50</a> }
+<a name="51" href="#51">51</a>
+<a name="52" href="#52">52</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> extractText(HSSFRow row, Appendable builder) <strong class="jxr_keyword">throws</strong> IOException {
+<a name="53" href="#53">53</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">short</strong> i = 0; row != <strong class="jxr_keyword">null</strong> && i < row.getLastCellNum(); i++) {
+<a name="54" href="#54">54</a> extractText(row.getCell(i), builder);
+<a name="55" href="#55">55</a> }
+<a name="56" href="#56">56</a> }
+<a name="57" href="#57">57</a>
+<a name="58" href="#58">58</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> extractText(HSSFCell cell, Appendable builder) <strong class="jxr_keyword">throws</strong> IOException {
+<a name="59" href="#59">59</a> <strong class="jxr_keyword">if</strong> (cell != <strong class="jxr_keyword">null</strong>) {
+<a name="60" href="#60">60</a> <strong class="jxr_keyword">switch</strong> (cell.getCellType()) {
+<a name="61" href="#61">61</a> <strong class="jxr_keyword">case</strong> HSSFCell.CELL_TYPE_STRING:
+<a name="62" href="#62">62</a> addText(cell.getRichStringCellValue().getString(), builder);
+<a name="63" href="#63">63</a> <strong class="jxr_keyword">break</strong>;
+<a name="64" href="#64">64</a> <strong class="jxr_keyword">case</strong> HSSFCell.CELL_TYPE_NUMERIC:
+<a name="65" href="#65">65</a> <strong class="jxr_keyword">case</strong> HSSFCell.CELL_TYPE_FORMULA:
+<a name="66" href="#66">66</a> addText(Double.toString(cell.getNumericCellValue()), builder);
+<a name="67" href="#67">67</a> <strong class="jxr_keyword">break</strong>;
+<a name="68" href="#68">68</a> <strong class="jxr_keyword">default</strong>:
+<a name="69" href="#69">69</a> <em class="jxr_comment">// ignore</em>
+<a name="70" href="#70">70</a> }
+<a name="71" href="#71">71</a> }
+<a name="72" href="#72">72</a> }
+<a name="73" href="#73">73</a>
+<a name="74" href="#74">74</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> addText(String text, Appendable builder) <strong class="jxr_keyword">throws</strong> IOException {
+<a name="75" href="#75">75</a> <strong class="jxr_keyword">if</strong> (text != <strong class="jxr_keyword">null</strong>) {
+<a name="76" href="#76">76</a> text = text.trim();
+<a name="77" href="#77">77</a> <strong class="jxr_keyword">if</strong> (text.length() > 0) {
+<a name="78" href="#78">78</a> builder.append(text).append(' ');
+<a name="79" href="#79">79</a> }
+<a name="80" href="#80">80</a> }
+<a name="81" href="#81">81</a> }
+<a name="82" href="#82">82</a>
+<a name="83" href="#83">83</a> }
</pre>
<hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body>
</html>
Modified: incubator/tika/site/xref/org/apache/tika/parser/microsoft/OfficeParser.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/microsoft/OfficeParser.html?rev=609491&r1=609490&r2=609491&view=diff
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/microsoft/OfficeParser.html (original)
+++ incubator/tika/site/xref/org/apache/tika/parser/microsoft/OfficeParser.html Sun Jan 6 19:06:26 2008
@@ -39,155 +39,158 @@
<a name="29" href="#29">29</a> <strong class="jxr_keyword">import</strong> org.apache.tika.exception.TikaException;
<a name="30" href="#30">30</a> <strong class="jxr_keyword">import</strong> org.apache.tika.metadata.Metadata;
<a name="31" href="#31">31</a> <strong class="jxr_keyword">import</strong> org.apache.tika.parser.Parser;
-<a name="32" href="#32">32</a> <strong class="jxr_keyword">import</strong> org.apache.tika.sax.XHTMLContentHandler;
-<a name="33" href="#33">33</a> <strong class="jxr_keyword">import</strong> org.xml.sax.ContentHandler;
-<a name="34" href="#34">34</a> <strong class="jxr_keyword">import</strong> org.xml.sax.SAXException;
-<a name="35" href="#35">35</a>
-<a name="36" href="#36">36</a> <em class="jxr_javadoccomment">/**</em>
-<a name="37" href="#37">37</a> <em class="jxr_javadoccomment"> * Defines a Microsoft document content extractor.</em>
-<a name="38" href="#38">38</a> <em class="jxr_javadoccomment"> */</em>
-<a name="39" href="#39">39</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">abstract</strong> <strong class="jxr_keyword">class</strong> <a href="../../../../../org/apache/tika/parser/microsoft/OfficeParser.html">OfficeParser</a> implements <a href="../../../../../org/apache/tika/parser/Parser.html">Parser</a> {
-<a name="40" href="#40">40</a>
-<a name="41" href="#41">41</a> <em class="jxr_javadoccomment">/**</em>
-<a name="42" href="#42">42</a> <em class="jxr_javadoccomment"> * Extracts properties and text from an MS Document input stream</em>
-<a name="43" href="#43">43</a> <em class="jxr_javadoccomment"> */</em>
-<a name="44" href="#44">44</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">void</strong> parse(
-<a name="45" href="#45">45</a> InputStream stream, ContentHandler handler, <a href="../../../../../org/apache/tika/metadata/Metadata.html">Metadata</a> metadata)
-<a name="46" href="#46">46</a> <strong class="jxr_keyword">throws</strong> IOException, SAXException, <a href="../../../../../org/apache/tika/exception/TikaException.html">TikaException</a> {
-<a name="47" href="#47">47</a> POIFSFileSystem filesystem = <strong class="jxr_keyword">new</strong> POIFSFileSystem(stream);
-<a name="48" href="#48">48</a>
-<a name="49" href="#49">49</a> metadata.set(Metadata.CONTENT_TYPE, getContentType());
-<a name="50" href="#50">50</a> getMetadata(
-<a name="51" href="#51">51</a> filesystem, SummaryInformation.DEFAULT_STREAM_NAME, metadata);
-<a name="52" href="#52">52</a> getMetadata(
-<a name="53" href="#53">53</a> filesystem, DocumentSummaryInformation.DEFAULT_STREAM_NAME,
-<a name="54" href="#54">54</a> metadata);
-<a name="55" href="#55">55</a>
-<a name="56" href="#56">56</a> <a href="../../../../../org/apache/tika/sax/XHTMLContentHandler.html">XHTMLContentHandler</a> xhtml =
-<a name="57" href="#57">57</a> <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/sax/XHTMLContentHandler.html">XHTMLContentHandler</a>(handler, metadata);
-<a name="58" href="#58">58</a> xhtml.startDocument();
-<a name="59" href="#59">59</a> xhtml.element(<span class="jxr_string">"p"</span>, extractText(filesystem));
-<a name="60" href="#60">60</a> xhtml.endDocument();
-<a name="61" href="#61">61</a> }
-<a name="62" href="#62">62</a>
-<a name="63" href="#63">63</a> <em class="jxr_javadoccomment">/**</em>
-<a name="64" href="#64">64</a> <em class="jxr_javadoccomment"> * The content type of the document being parsed.</em>
-<a name="65" href="#65">65</a> <em class="jxr_javadoccomment"> *</em>
-<a name="66" href="#66">66</a> <em class="jxr_javadoccomment"> * @return MIME content type</em>
-<a name="67" href="#67">67</a> <em class="jxr_javadoccomment"> */</em>
-<a name="68" href="#68">68</a> <strong class="jxr_keyword">protected</strong> <strong class="jxr_keyword">abstract</strong> String getContentType();
-<a name="69" href="#69">69</a>
-<a name="70" href="#70">70</a> <em class="jxr_javadoccomment">/**</em>
-<a name="71" href="#71">71</a> <em class="jxr_javadoccomment"> * Extracts the text content from a Microsoft document input stream.</em>
-<a name="72" href="#72">72</a> <em class="jxr_javadoccomment"> */</em>
-<a name="73" href="#73">73</a> <strong class="jxr_keyword">protected</strong> <strong class="jxr_keyword">abstract</strong> String extractText(POIFSFileSystem filesystem)
-<a name="74" href="#74">74</a> <strong class="jxr_keyword">throws</strong> IOException, TikaException;
-<a name="75" href="#75">75</a>
-<a name="76" href="#76">76</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> getMetadata(
-<a name="77" href="#77">77</a> POIFSFileSystem filesystem, String name, <a href="../../../../../org/apache/tika/metadata/Metadata.html">Metadata</a> metadata) {
-<a name="78" href="#78">78</a> <strong class="jxr_keyword">try</strong> {
-<a name="79" href="#79">79</a> InputStream stream = filesystem.createDocumentInputStream(name);
-<a name="80" href="#80">80</a> <strong class="jxr_keyword">try</strong> {
-<a name="81" href="#81">81</a> getMetadata(stream, metadata);
-<a name="82" href="#82">82</a> } <strong class="jxr_keyword">finally</strong> {
-<a name="83" href="#83">83</a> stream.close();
-<a name="84" href="#84">84</a> }
-<a name="85" href="#85">85</a> } <strong class="jxr_keyword">catch</strong> (Exception e) {
-<a name="86" href="#86">86</a> <em class="jxr_comment">// summary information not available, ignore</em>
-<a name="87" href="#87">87</a> }
-<a name="88" href="#88">88</a> }
-<a name="89" href="#89">89</a>
-<a name="90" href="#90">90</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> getMetadata(InputStream stream, <a href="../../../../../org/apache/tika/metadata/Metadata.html">Metadata</a> metadata)
-<a name="91" href="#91">91</a> <strong class="jxr_keyword">throws</strong> HPSFException, IOException {
-<a name="92" href="#92">92</a> PropertySet set = PropertySetFactory.create(stream);
-<a name="93" href="#93">93</a> <strong class="jxr_keyword">if</strong> (set instanceof SummaryInformation) {
-<a name="94" href="#94">94</a> getMetadata((SummaryInformation) set, metadata);
-<a name="95" href="#95">95</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (set instanceof DocumentSummaryInformation) {
-<a name="96" href="#96">96</a> getMetadata((DocumentSummaryInformation) set, metadata);
-<a name="97" href="#97">97</a> }
-<a name="98" href="#98">98</a> }
-<a name="99" href="#99">99</a>
-<a name="100" href="#100">100</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> getMetadata(
-<a name="101" href="#101">101</a> SummaryInformation information, <a href="../../../../../org/apache/tika/metadata/Metadata.html">Metadata</a> metadata) {
-<a name="102" href="#102">102</a> <strong class="jxr_keyword">if</strong> (information.getTitle() != <strong class="jxr_keyword">null</strong>) {
-<a name="103" href="#103">103</a> metadata.set(Metadata.TITLE, information.getTitle());
-<a name="104" href="#104">104</a> }
-<a name="105" href="#105">105</a> <strong class="jxr_keyword">if</strong> (information.getAuthor() != <strong class="jxr_keyword">null</strong>) {
-<a name="106" href="#106">106</a> metadata.set(Metadata.AUTHOR, information.getAuthor());
+<a name="32" href="#32">32</a> <strong class="jxr_keyword">import</strong> org.apache.tika.sax.AppendableAdaptor;
+<a name="33" href="#33">33</a> <strong class="jxr_keyword">import</strong> org.apache.tika.sax.XHTMLContentHandler;
+<a name="34" href="#34">34</a> <strong class="jxr_keyword">import</strong> org.xml.sax.ContentHandler;
+<a name="35" href="#35">35</a> <strong class="jxr_keyword">import</strong> org.xml.sax.SAXException;
+<a name="36" href="#36">36</a>
+<a name="37" href="#37">37</a> <em class="jxr_javadoccomment">/**</em>
+<a name="38" href="#38">38</a> <em class="jxr_javadoccomment"> * Defines a Microsoft document content extractor.</em>
+<a name="39" href="#39">39</a> <em class="jxr_javadoccomment"> */</em>
+<a name="40" href="#40">40</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">abstract</strong> <strong class="jxr_keyword">class</strong> <a href="../../../../../org/apache/tika/parser/microsoft/OfficeParser.html">OfficeParser</a> implements <a href="../../../../../org/apache/tika/parser/Parser.html">Parser</a> {
+<a name="41" href="#41">41</a>
+<a name="42" href="#42">42</a> <em class="jxr_javadoccomment">/**</em>
+<a name="43" href="#43">43</a> <em class="jxr_javadoccomment"> * Extracts properties and text from an MS Document input stream</em>
+<a name="44" href="#44">44</a> <em class="jxr_javadoccomment"> */</em>
+<a name="45" href="#45">45</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">void</strong> parse(
+<a name="46" href="#46">46</a> InputStream stream, ContentHandler handler, <a href="../../../../../org/apache/tika/metadata/Metadata.html">Metadata</a> metadata)
+<a name="47" href="#47">47</a> <strong class="jxr_keyword">throws</strong> IOException, SAXException, <a href="../../../../../org/apache/tika/exception/TikaException.html">TikaException</a> {
+<a name="48" href="#48">48</a> POIFSFileSystem filesystem = <strong class="jxr_keyword">new</strong> POIFSFileSystem(stream);
+<a name="49" href="#49">49</a>
+<a name="50" href="#50">50</a> metadata.set(Metadata.CONTENT_TYPE, getContentType());
+<a name="51" href="#51">51</a> getMetadata(
+<a name="52" href="#52">52</a> filesystem, SummaryInformation.DEFAULT_STREAM_NAME, metadata);
+<a name="53" href="#53">53</a> getMetadata(
+<a name="54" href="#54">54</a> filesystem, DocumentSummaryInformation.DEFAULT_STREAM_NAME,
+<a name="55" href="#55">55</a> metadata);
+<a name="56" href="#56">56</a>
+<a name="57" href="#57">57</a> <a href="../../../../../org/apache/tika/sax/XHTMLContentHandler.html">XHTMLContentHandler</a> xhtml =
+<a name="58" href="#58">58</a> <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/sax/XHTMLContentHandler.html">XHTMLContentHandler</a>(handler, metadata);
+<a name="59" href="#59">59</a> xhtml.startDocument();
+<a name="60" href="#60">60</a> xhtml.startElement(<span class="jxr_string">"p"</span>);
+<a name="61" href="#61">61</a> extractText(filesystem, <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/sax/AppendableAdaptor.html">AppendableAdaptor</a>(xhtml));
+<a name="62" href="#62">62</a> xhtml.endElement(<span class="jxr_string">"p"</span>);
+<a name="63" href="#63">63</a> xhtml.endDocument();
+<a name="64" href="#64">64</a> }
+<a name="65" href="#65">65</a>
+<a name="66" href="#66">66</a> <em class="jxr_javadoccomment">/**</em>
+<a name="67" href="#67">67</a> <em class="jxr_javadoccomment"> * The content type of the document being parsed.</em>
+<a name="68" href="#68">68</a> <em class="jxr_javadoccomment"> *</em>
+<a name="69" href="#69">69</a> <em class="jxr_javadoccomment"> * @return MIME content type</em>
+<a name="70" href="#70">70</a> <em class="jxr_javadoccomment"> */</em>
+<a name="71" href="#71">71</a> <strong class="jxr_keyword">protected</strong> <strong class="jxr_keyword">abstract</strong> String getContentType();
+<a name="72" href="#72">72</a>
+<a name="73" href="#73">73</a> <em class="jxr_javadoccomment">/**</em>
+<a name="74" href="#74">74</a> <em class="jxr_javadoccomment"> * Extracts the text content from a Microsoft document input stream.</em>
+<a name="75" href="#75">75</a> <em class="jxr_javadoccomment"> */</em>
+<a name="76" href="#76">76</a> <strong class="jxr_keyword">protected</strong> <strong class="jxr_keyword">abstract</strong> <strong class="jxr_keyword">void</strong> extractText(POIFSFileSystem filesystem, Appendable appendable)
+<a name="77" href="#77">77</a> <strong class="jxr_keyword">throws</strong> IOException, TikaException;
+<a name="78" href="#78">78</a>
+<a name="79" href="#79">79</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> getMetadata(
+<a name="80" href="#80">80</a> POIFSFileSystem filesystem, String name, <a href="../../../../../org/apache/tika/metadata/Metadata.html">Metadata</a> metadata) {
+<a name="81" href="#81">81</a> <strong class="jxr_keyword">try</strong> {
+<a name="82" href="#82">82</a> InputStream stream = filesystem.createDocumentInputStream(name);
+<a name="83" href="#83">83</a> <strong class="jxr_keyword">try</strong> {
+<a name="84" href="#84">84</a> getMetadata(stream, metadata);
+<a name="85" href="#85">85</a> } <strong class="jxr_keyword">finally</strong> {
+<a name="86" href="#86">86</a> stream.close();
+<a name="87" href="#87">87</a> }
+<a name="88" href="#88">88</a> } <strong class="jxr_keyword">catch</strong> (Exception e) {
+<a name="89" href="#89">89</a> <em class="jxr_comment">// summary information not available, ignore</em>
+<a name="90" href="#90">90</a> }
+<a name="91" href="#91">91</a> }
+<a name="92" href="#92">92</a>
+<a name="93" href="#93">93</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> getMetadata(InputStream stream, <a href="../../../../../org/apache/tika/metadata/Metadata.html">Metadata</a> metadata)
+<a name="94" href="#94">94</a> <strong class="jxr_keyword">throws</strong> HPSFException, IOException {
+<a name="95" href="#95">95</a> PropertySet set = PropertySetFactory.create(stream);
+<a name="96" href="#96">96</a> <strong class="jxr_keyword">if</strong> (set instanceof SummaryInformation) {
+<a name="97" href="#97">97</a> getMetadata((SummaryInformation) set, metadata);
+<a name="98" href="#98">98</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (set instanceof DocumentSummaryInformation) {
+<a name="99" href="#99">99</a> getMetadata((DocumentSummaryInformation) set, metadata);
+<a name="100" href="#100">100</a> }
+<a name="101" href="#101">101</a> }
+<a name="102" href="#102">102</a>
+<a name="103" href="#103">103</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> getMetadata(
+<a name="104" href="#104">104</a> SummaryInformation information, <a href="../../../../../org/apache/tika/metadata/Metadata.html">Metadata</a> metadata) {
+<a name="105" href="#105">105</a> <strong class="jxr_keyword">if</strong> (information.getTitle() != <strong class="jxr_keyword">null</strong>) {
+<a name="106" href="#106">106</a> metadata.set(Metadata.TITLE, information.getTitle());
<a name="107" href="#107">107</a> }
-<a name="108" href="#108">108</a> <strong class="jxr_keyword">if</strong> (information.getKeywords() != <strong class="jxr_keyword">null</strong>) {
-<a name="109" href="#109">109</a> metadata.set(Metadata.KEYWORDS, information.getKeywords());
+<a name="108" href="#108">108</a> <strong class="jxr_keyword">if</strong> (information.getAuthor() != <strong class="jxr_keyword">null</strong>) {
+<a name="109" href="#109">109</a> metadata.set(Metadata.AUTHOR, information.getAuthor());
<a name="110" href="#110">110</a> }
-<a name="111" href="#111">111</a> <strong class="jxr_keyword">if</strong> (information.getSubject() != <strong class="jxr_keyword">null</strong>) {
-<a name="112" href="#112">112</a> metadata.set(Metadata.SUBJECT, information.getSubject());
+<a name="111" href="#111">111</a> <strong class="jxr_keyword">if</strong> (information.getKeywords() != <strong class="jxr_keyword">null</strong>) {
+<a name="112" href="#112">112</a> metadata.set(Metadata.KEYWORDS, information.getKeywords());
<a name="113" href="#113">113</a> }
-<a name="114" href="#114">114</a> <strong class="jxr_keyword">if</strong> (information.getLastAuthor() != <strong class="jxr_keyword">null</strong>) {
-<a name="115" href="#115">115</a> metadata.set(Metadata.LAST_AUTHOR, information.getLastAuthor());
+<a name="114" href="#114">114</a> <strong class="jxr_keyword">if</strong> (information.getSubject() != <strong class="jxr_keyword">null</strong>) {
+<a name="115" href="#115">115</a> metadata.set(Metadata.SUBJECT, information.getSubject());
<a name="116" href="#116">116</a> }
-<a name="117" href="#117">117</a> <strong class="jxr_keyword">if</strong> (information.getComments() != <strong class="jxr_keyword">null</strong>) {
-<a name="118" href="#118">118</a> metadata.set(Metadata.COMMENTS, information.getComments());
+<a name="117" href="#117">117</a> <strong class="jxr_keyword">if</strong> (information.getLastAuthor() != <strong class="jxr_keyword">null</strong>) {
+<a name="118" href="#118">118</a> metadata.set(Metadata.LAST_AUTHOR, information.getLastAuthor());
<a name="119" href="#119">119</a> }
-<a name="120" href="#120">120</a> <strong class="jxr_keyword">if</strong> (information.getTemplate() != <strong class="jxr_keyword">null</strong>) {
-<a name="121" href="#121">121</a> metadata.set(Metadata.TEMPLATE, information.getTemplate());
+<a name="120" href="#120">120</a> <strong class="jxr_keyword">if</strong> (information.getComments() != <strong class="jxr_keyword">null</strong>) {
+<a name="121" href="#121">121</a> metadata.set(Metadata.COMMENTS, information.getComments());
<a name="122" href="#122">122</a> }
-<a name="123" href="#123">123</a> <strong class="jxr_keyword">if</strong> (information.getApplicationName() != <strong class="jxr_keyword">null</strong>) {
-<a name="124" href="#124">124</a> metadata.set(
-<a name="125" href="#125">125</a> Metadata.APPLICATION_NAME,
-<a name="126" href="#126">126</a> information.getApplicationName());
-<a name="127" href="#127">127</a> }
-<a name="128" href="#128">128</a> <strong class="jxr_keyword">if</strong> (information.getRevNumber() != <strong class="jxr_keyword">null</strong>) {
-<a name="129" href="#129">129</a> metadata.set(Metadata.REVISION_NUMBER, information.getRevNumber());
+<a name="123" href="#123">123</a> <strong class="jxr_keyword">if</strong> (information.getTemplate() != <strong class="jxr_keyword">null</strong>) {
+<a name="124" href="#124">124</a> metadata.set(Metadata.TEMPLATE, information.getTemplate());
+<a name="125" href="#125">125</a> }
+<a name="126" href="#126">126</a> <strong class="jxr_keyword">if</strong> (information.getApplicationName() != <strong class="jxr_keyword">null</strong>) {
+<a name="127" href="#127">127</a> metadata.set(
+<a name="128" href="#128">128</a> Metadata.APPLICATION_NAME,
+<a name="129" href="#129">129</a> information.getApplicationName());
<a name="130" href="#130">130</a> }
-<a name="131" href="#131">131</a> <strong class="jxr_keyword">if</strong> (information.getCreateDateTime() != <strong class="jxr_keyword">null</strong>) {
-<a name="132" href="#132">132</a> metadata.set(
-<a name="133" href="#133">133</a> <span class="jxr_string">"creationdate"</span>,
-<a name="134" href="#134">134</a> information.getCreateDateTime().toString());
-<a name="135" href="#135">135</a> }
-<a name="136" href="#136">136</a> <strong class="jxr_keyword">if</strong> (information.getCharCount() > 0) {
-<a name="137" href="#137">137</a> metadata.set(
-<a name="138" href="#138">138</a> Metadata.CHARACTER_COUNT,
-<a name="139" href="#139">139</a> Integer.toString(information.getCharCount()));
-<a name="140" href="#140">140</a> }
-<a name="141" href="#141">141</a> <strong class="jxr_keyword">if</strong> (information.getEditTime() > 0) {
-<a name="142" href="#142">142</a> metadata.set(<span class="jxr_string">"edittime"</span>, Long.toString(information.getEditTime()));
+<a name="131" href="#131">131</a> <strong class="jxr_keyword">if</strong> (information.getRevNumber() != <strong class="jxr_keyword">null</strong>) {
+<a name="132" href="#132">132</a> metadata.set(Metadata.REVISION_NUMBER, information.getRevNumber());
+<a name="133" href="#133">133</a> }
+<a name="134" href="#134">134</a> <strong class="jxr_keyword">if</strong> (information.getCreateDateTime() != <strong class="jxr_keyword">null</strong>) {
+<a name="135" href="#135">135</a> metadata.set(
+<a name="136" href="#136">136</a> <span class="jxr_string">"creationdate"</span>,
+<a name="137" href="#137">137</a> information.getCreateDateTime().toString());
+<a name="138" href="#138">138</a> }
+<a name="139" href="#139">139</a> <strong class="jxr_keyword">if</strong> (information.getCharCount() > 0) {
+<a name="140" href="#140">140</a> metadata.set(
+<a name="141" href="#141">141</a> Metadata.CHARACTER_COUNT,
+<a name="142" href="#142">142</a> Integer.toString(information.getCharCount()));
<a name="143" href="#143">143</a> }
-<a name="144" href="#144">144</a> <strong class="jxr_keyword">if</strong> (information.getLastSaveDateTime() != <strong class="jxr_keyword">null</strong>) {
-<a name="145" href="#145">145</a> metadata.set(
-<a name="146" href="#146">146</a> Metadata.LAST_SAVED,
-<a name="147" href="#147">147</a> information.getLastSaveDateTime().toString());
-<a name="148" href="#148">148</a> }
-<a name="149" href="#149">149</a> <strong class="jxr_keyword">if</strong> (information.getPageCount() > 0) {
-<a name="150" href="#150">150</a> metadata.set(
-<a name="151" href="#151">151</a> Metadata.PAGE_COUNT,
-<a name="152" href="#152">152</a> Integer.toString(information.getPageCount()));
-<a name="153" href="#153">153</a> }
-<a name="154" href="#154">154</a> <strong class="jxr_keyword">if</strong> (information.getSecurity() > 0) {
-<a name="155" href="#155">155</a> metadata.set(
-<a name="156" href="#156">156</a> <span class="jxr_string">"security"</span>, Integer.toString(information.getSecurity()));
-<a name="157" href="#157">157</a> }
-<a name="158" href="#158">158</a> <strong class="jxr_keyword">if</strong> (information.getWordCount() > 0) {
-<a name="159" href="#159">159</a> metadata.set(
-<a name="160" href="#160">160</a> Metadata.WORD_COUNT,
-<a name="161" href="#161">161</a> Integer.toString(information.getWordCount()));
-<a name="162" href="#162">162</a> }
-<a name="163" href="#163">163</a> <strong class="jxr_keyword">if</strong> (information.getLastPrinted() != <strong class="jxr_keyword">null</strong>) {
-<a name="164" href="#164">164</a> metadata.set(
-<a name="165" href="#165">165</a> Metadata.LAST_PRINTED,
-<a name="166" href="#166">166</a> information.getLastPrinted().toString());
-<a name="167" href="#167">167</a> }
-<a name="168" href="#168">168</a> }
-<a name="169" href="#169">169</a>
-<a name="170" href="#170">170</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> getMetadata(
-<a name="171" href="#171">171</a> DocumentSummaryInformation information, <a href="../../../../../org/apache/tika/metadata/Metadata.html">Metadata</a> metadata) {
-<a name="172" href="#172">172</a> <strong class="jxr_keyword">if</strong> (information.getCompany() != <strong class="jxr_keyword">null</strong>) {
-<a name="173" href="#173">173</a> metadata.set(<span class="jxr_string">"company"</span>, information.getCompany());
-<a name="174" href="#174">174</a> }
-<a name="175" href="#175">175</a> <strong class="jxr_keyword">if</strong> (information.getManager() != <strong class="jxr_keyword">null</strong>) {
-<a name="176" href="#176">176</a> metadata.set(<span class="jxr_string">"manager"</span>, information.getManager());
+<a name="144" href="#144">144</a> <strong class="jxr_keyword">if</strong> (information.getEditTime() > 0) {
+<a name="145" href="#145">145</a> metadata.set(<span class="jxr_string">"edittime"</span>, Long.toString(information.getEditTime()));
+<a name="146" href="#146">146</a> }
+<a name="147" href="#147">147</a> <strong class="jxr_keyword">if</strong> (information.getLastSaveDateTime() != <strong class="jxr_keyword">null</strong>) {
+<a name="148" href="#148">148</a> metadata.set(
+<a name="149" href="#149">149</a> Metadata.LAST_SAVED,
+<a name="150" href="#150">150</a> information.getLastSaveDateTime().toString());
+<a name="151" href="#151">151</a> }
+<a name="152" href="#152">152</a> <strong class="jxr_keyword">if</strong> (information.getPageCount() > 0) {
+<a name="153" href="#153">153</a> metadata.set(
+<a name="154" href="#154">154</a> Metadata.PAGE_COUNT,
+<a name="155" href="#155">155</a> Integer.toString(information.getPageCount()));
+<a name="156" href="#156">156</a> }
+<a name="157" href="#157">157</a> <strong class="jxr_keyword">if</strong> (information.getSecurity() > 0) {
+<a name="158" href="#158">158</a> metadata.set(
+<a name="159" href="#159">159</a> <span class="jxr_string">"security"</span>, Integer.toString(information.getSecurity()));
+<a name="160" href="#160">160</a> }
+<a name="161" href="#161">161</a> <strong class="jxr_keyword">if</strong> (information.getWordCount() > 0) {
+<a name="162" href="#162">162</a> metadata.set(
+<a name="163" href="#163">163</a> Metadata.WORD_COUNT,
+<a name="164" href="#164">164</a> Integer.toString(information.getWordCount()));
+<a name="165" href="#165">165</a> }
+<a name="166" href="#166">166</a> <strong class="jxr_keyword">if</strong> (information.getLastPrinted() != <strong class="jxr_keyword">null</strong>) {
+<a name="167" href="#167">167</a> metadata.set(
+<a name="168" href="#168">168</a> Metadata.LAST_PRINTED,
+<a name="169" href="#169">169</a> information.getLastPrinted().toString());
+<a name="170" href="#170">170</a> }
+<a name="171" href="#171">171</a> }
+<a name="172" href="#172">172</a>
+<a name="173" href="#173">173</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> getMetadata(
+<a name="174" href="#174">174</a> DocumentSummaryInformation information, <a href="../../../../../org/apache/tika/metadata/Metadata.html">Metadata</a> metadata) {
+<a name="175" href="#175">175</a> <strong class="jxr_keyword">if</strong> (information.getCompany() != <strong class="jxr_keyword">null</strong>) {
+<a name="176" href="#176">176</a> metadata.set(<span class="jxr_string">"company"</span>, information.getCompany());
<a name="177" href="#177">177</a> }
-<a name="178" href="#178">178</a> }
-<a name="179" href="#179">179</a>
-<a name="180" href="#180">180</a> }
+<a name="178" href="#178">178</a> <strong class="jxr_keyword">if</strong> (information.getManager() != <strong class="jxr_keyword">null</strong>) {
+<a name="179" href="#179">179</a> metadata.set(<span class="jxr_string">"manager"</span>, information.getManager());
+<a name="180" href="#180">180</a> }
+<a name="181" href="#181">181</a> }
+<a name="182" href="#182">182</a>
+<a name="183" href="#183">183</a> }
</pre>
<hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body>
</html>
Modified: incubator/tika/site/xref/org/apache/tika/parser/microsoft/PowerPointExtractor.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/microsoft/PowerPointExtractor.html?rev=609491&r1=609490&r2=609491&view=diff
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/microsoft/PowerPointExtractor.html (original)
+++ incubator/tika/site/xref/org/apache/tika/parser/microsoft/PowerPointExtractor.html Sun Jan 6 19:06:26 2008
@@ -42,12 +42,12 @@
<a name="32" href="#32">32</a> <strong class="jxr_keyword">static</strong> Logger LOG = Logger.getRootLogger();
<a name="33" href="#33">33</a>
<a name="34" href="#34">34</a> <em class="jxr_javadoccomment">/**</em><em class="jxr_javadoccomment"> Buffer holding the content of the file */</em>
-<a name="35" href="#35">35</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">final</strong> StringBuilder builder;
+<a name="35" href="#35">35</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">final</strong> Appendable builder;
<a name="36" href="#36">36</a>
<a name="37" href="#37">37</a> <em class="jxr_javadoccomment">/**</em>
<a name="38" href="#38">38</a> <em class="jxr_javadoccomment"> * Constructs Listener to get content of PowerPoint file.</em>
<a name="39" href="#39">39</a> <em class="jxr_javadoccomment"> */</em>
-<a name="40" href="#40">40</a> <strong class="jxr_keyword">public</strong> <a href="../../../../../org/apache/tika/parser/microsoft/PowerPointExtractor.html">PowerPointExtractor</a>(StringBuilder builder) {
+<a name="40" href="#40">40</a> <strong class="jxr_keyword">public</strong> <a href="../../../../../org/apache/tika/parser/microsoft/PowerPointExtractor.html">PowerPointExtractor</a>(Appendable builder) {
<a name="41" href="#41">41</a> <strong class="jxr_keyword">this</strong>.builder = builder;
<a name="42" href="#42">42</a> }
<a name="43" href="#43">43</a>
Modified: incubator/tika/site/xref/org/apache/tika/parser/microsoft/PowerPointParser.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/microsoft/PowerPointParser.html?rev=609491&r1=609490&r2=609491&view=diff
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/microsoft/PowerPointParser.html (original)
+++ incubator/tika/site/xref/org/apache/tika/parser/microsoft/PowerPointParser.html Sun Jan 6 19:06:26 2008
@@ -45,20 +45,17 @@
<a name="35" href="#35">35</a> <strong class="jxr_keyword">return</strong> <span class="jxr_string">"application/vnd.ms-powerpoint"</span>;
<a name="36" href="#36">36</a> }
<a name="37" href="#37">37</a>
-<a name="38" href="#38">38</a> <strong class="jxr_keyword">protected</strong> String extractText(POIFSFileSystem filesystem) <strong class="jxr_keyword">throws</strong> IOException {
-<a name="39" href="#39">39</a> StringBuilder builder = <strong class="jxr_keyword">new</strong> StringBuilder();
-<a name="40" href="#40">40</a>
-<a name="41" href="#41">41</a> InputStream stream = filesystem.createDocumentInputStream(POWERPOINT);
-<a name="42" href="#42">42</a> <strong class="jxr_keyword">try</strong> {
-<a name="43" href="#43">43</a> <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/parser/microsoft/PowerPointExtractor.html">PowerPointExtractor</a>(builder).extract(stream);
-<a name="44" href="#44">44</a> } <strong class="jxr_keyword">finally</strong> {
-<a name="45" href="#45">45</a> stream.close();
-<a name="46" href="#46">46</a> }
+<a name="38" href="#38">38</a> <strong class="jxr_keyword">protected</strong> <strong class="jxr_keyword">void</strong> extractText(POIFSFileSystem filesystem, Appendable builder) <strong class="jxr_keyword">throws</strong> IOException {
+<a name="39" href="#39">39</a>
+<a name="40" href="#40">40</a> InputStream stream = filesystem.createDocumentInputStream(POWERPOINT);
+<a name="41" href="#41">41</a> <strong class="jxr_keyword">try</strong> {
+<a name="42" href="#42">42</a> <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/parser/microsoft/PowerPointExtractor.html">PowerPointExtractor</a>(builder).extract(stream);
+<a name="43" href="#43">43</a> } <strong class="jxr_keyword">finally</strong> {
+<a name="44" href="#44">44</a> stream.close();
+<a name="45" href="#45">45</a> }
+<a name="46" href="#46">46</a> }
<a name="47" href="#47">47</a>
-<a name="48" href="#48">48</a> <strong class="jxr_keyword">return</strong> builder.toString();
-<a name="49" href="#49">49</a> }
-<a name="50" href="#50">50</a>
-<a name="51" href="#51">51</a> }
+<a name="48" href="#48">48</a> }
</pre>
<hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body>
</html>
Modified: incubator/tika/site/xref/org/apache/tika/parser/microsoft/Word6Extractor.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/microsoft/Word6Extractor.html?rev=609491&r1=609490&r2=609491&view=diff
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/microsoft/Word6Extractor.html (original)
+++ incubator/tika/site/xref/org/apache/tika/parser/microsoft/Word6Extractor.html Sun Jan 6 19:06:26 2008
@@ -43,200 +43,201 @@
<a name="33" href="#33">33</a> <strong class="jxr_keyword">class</strong> Word6Extractor
<a name="34" href="#34">34</a> {
<a name="35" href="#35">35</a>
-<a name="36" href="#36">36</a> <strong class="jxr_keyword">public</strong> Word6Extractor()
-<a name="37" href="#37">37</a> {
-<a name="38" href="#38">38</a> }
-<a name="39" href="#39">39</a>
-<a name="40" href="#40">40</a> <em class="jxr_javadoccomment">/**</em>
-<a name="41" href="#41">41</a> <em class="jxr_javadoccomment"> * Extracts the text</em>
-<a name="42" href="#42">42</a> <em class="jxr_javadoccomment"> *</em>
-<a name="43" href="#43">43</a> <em class="jxr_javadoccomment"> * @param mainStream The POIFS document stream entitled "WordDocument".</em>
-<a name="44" href="#44">44</a> <em class="jxr_javadoccomment"> *</em>
-<a name="45" href="#45">45</a> <em class="jxr_javadoccomment"> * @return The text from the document</em>
-<a name="46" href="#46">46</a> <em class="jxr_javadoccomment"> * @throws Exception If there are any unexpected exceptions.</em>
-<a name="47" href="#47">47</a> <em class="jxr_javadoccomment"> */</em>
-<a name="48" href="#48">48</a> <strong class="jxr_keyword">public</strong> String extractText(byte[] mainStream) <strong class="jxr_keyword">throws</strong> IOException {
-<a name="49" href="#49">49</a> <strong class="jxr_keyword">int</strong> fcMin = LittleEndian.getInt(mainStream, 0x18);
-<a name="50" href="#50">50</a> <strong class="jxr_keyword">int</strong> fcMax = LittleEndian.getInt(mainStream, 0x1C);
-<a name="51" href="#51">51</a>
-<a name="52" href="#52">52</a> <strong class="jxr_keyword">int</strong> chpTableOffset = LittleEndian.getInt(mainStream, 0xb8);
-<a name="53" href="#53">53</a> <strong class="jxr_keyword">int</strong> chpTableSize = LittleEndian.getInt(mainStream, 0xbc);
+<a name="36" href="#36">36</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">final</strong> Appendable appendable;
+<a name="37" href="#37">37</a>
+<a name="38" href="#38">38</a> <strong class="jxr_keyword">public</strong> Word6Extractor(Appendable appendable)
+<a name="39" href="#39">39</a> {
+<a name="40" href="#40">40</a> <strong class="jxr_keyword">this</strong>.appendable = appendable;
+<a name="41" href="#41">41</a> }
+<a name="42" href="#42">42</a>
+<a name="43" href="#43">43</a> <em class="jxr_javadoccomment">/**</em>
+<a name="44" href="#44">44</a> <em class="jxr_javadoccomment"> * Extracts the text</em>
+<a name="45" href="#45">45</a> <em class="jxr_javadoccomment"> *</em>
+<a name="46" href="#46">46</a> <em class="jxr_javadoccomment"> * @param mainStream The POIFS document stream entitled "WordDocument".</em>
+<a name="47" href="#47">47</a> <em class="jxr_javadoccomment"> *</em>
+<a name="48" href="#48">48</a> <em class="jxr_javadoccomment"> * @return The text from the document</em>
+<a name="49" href="#49">49</a> <em class="jxr_javadoccomment"> * @throws Exception If there are any unexpected exceptions.</em>
+<a name="50" href="#50">50</a> <em class="jxr_javadoccomment"> */</em>
+<a name="51" href="#51">51</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">void</strong> extractText(byte[] mainStream) <strong class="jxr_keyword">throws</strong> IOException {
+<a name="52" href="#52">52</a> <strong class="jxr_keyword">int</strong> fcMin = LittleEndian.getInt(mainStream, 0x18);
+<a name="53" href="#53">53</a> <strong class="jxr_keyword">int</strong> fcMax = LittleEndian.getInt(mainStream, 0x1C);
<a name="54" href="#54">54</a>
-<a name="55" href="#55">55</a> <em class="jxr_comment">// get a list of character properties</em>
-<a name="56" href="#56">56</a> Word6CHPBinTable chpTable = <strong class="jxr_keyword">new</strong> Word6CHPBinTable(mainStream, chpTableOffset,
-<a name="57" href="#57">57</a> chpTableSize, fcMin);
-<a name="58" href="#58">58</a> List textRuns = chpTable.getTextRuns();
-<a name="59" href="#59">59</a>
-<a name="60" href="#60">60</a> <em class="jxr_comment">// iterate through the</em>
-<a name="61" href="#61">61</a> <a href="../../../../../org/apache/tika/parser/microsoft/WordTextBuffer.html">WordTextBuffer</a> finalTextBuf = <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/parser/microsoft/WordTextBuffer.html">WordTextBuffer</a>();
-<a name="62" href="#62">62</a> Iterator runsIt = textRuns.iterator();
-<a name="63" href="#63">63</a> <strong class="jxr_keyword">while</strong>(runsIt.hasNext())
-<a name="64" href="#64">64</a> {
-<a name="65" href="#65">65</a> CHPX chpx = (CHPX)runsIt.next();
-<a name="66" href="#66">66</a> <strong class="jxr_keyword">int</strong> runStart = chpx.getStart() + fcMin;
-<a name="67" href="#67">67</a> <strong class="jxr_keyword">int</strong> runEnd = chpx.getEnd() + fcMin;
-<a name="68" href="#68">68</a>
-<a name="69" href="#69">69</a> <strong class="jxr_keyword">if</strong> (!isDeleted(chpx.getGrpprl()))
-<a name="70" href="#70">70</a> {
-<a name="71" href="#71">71</a> String s = <strong class="jxr_keyword">new</strong> String(mainStream, runStart, Math.min(runEnd, fcMax) - runStart, <span class="jxr_string">"Cp1252"</span>);
-<a name="72" href="#72">72</a> finalTextBuf.append(s);
-<a name="73" href="#73">73</a> <strong class="jxr_keyword">if</strong> (runEnd >= fcMax)
-<a name="74" href="#74">74</a> {
-<a name="75" href="#75">75</a> <strong class="jxr_keyword">break</strong>;
-<a name="76" href="#76">76</a> }
-<a name="77" href="#77">77</a> }
-<a name="78" href="#78">78</a> }
-<a name="79" href="#79">79</a>
-<a name="80" href="#80">80</a> <strong class="jxr_keyword">return</strong> finalTextBuf.toString();
-<a name="81" href="#81">81</a> }
-<a name="82" href="#82">82</a>
-<a name="83" href="#83">83</a> <em class="jxr_javadoccomment">/**</em>
-<a name="84" href="#84">84</a> <em class="jxr_javadoccomment"> * Used to determine if a run of text has been deleted.</em>
-<a name="85" href="#85">85</a> <em class="jxr_javadoccomment"> * @param grpprl The list of sprms for this run of text.</em>
-<a name="86" href="#86">86</a> <em class="jxr_javadoccomment"> * @return</em>
-<a name="87" href="#87">87</a> <em class="jxr_javadoccomment"> */</em>
-<a name="88" href="#88">88</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">boolean</strong> isDeleted(byte[] grpprl)
-<a name="89" href="#89">89</a> {
-<a name="90" href="#90">90</a> <strong class="jxr_keyword">int</strong> offset = 0;
-<a name="91" href="#91">91</a> <strong class="jxr_keyword">boolean</strong> deleted = false;
-<a name="92" href="#92">92</a> <strong class="jxr_keyword">while</strong> (offset < grpprl.length)
-<a name="93" href="#93">93</a> {
-<a name="94" href="#94">94</a> <strong class="jxr_keyword">switch</strong> (LittleEndian.getUnsignedByte(grpprl, offset++))
-<a name="95" href="#95">95</a> {
-<a name="96" href="#96">96</a> <strong class="jxr_keyword">case</strong> 65:
-<a name="97" href="#97">97</a> deleted = grpprl[offset++] != 0;
-<a name="98" href="#98">98</a> <strong class="jxr_keyword">break</strong>;
-<a name="99" href="#99">99</a> <strong class="jxr_keyword">case</strong> 66:
-<a name="100" href="#100">100</a> offset++;
-<a name="101" href="#101">101</a> <strong class="jxr_keyword">break</strong>;
-<a name="102" href="#102">102</a> <strong class="jxr_keyword">case</strong> 67:
-<a name="103" href="#103">103</a> offset++;
-<a name="104" href="#104">104</a> <strong class="jxr_keyword">break</strong>;
-<a name="105" href="#105">105</a> <strong class="jxr_keyword">case</strong> 68:
-<a name="106" href="#106">106</a> offset += grpprl[offset];
-<a name="107" href="#107">107</a> <strong class="jxr_keyword">break</strong>;
-<a name="108" href="#108">108</a> <strong class="jxr_keyword">case</strong> 69:
-<a name="109" href="#109">109</a> offset += 2;
-<a name="110" href="#110">110</a> <strong class="jxr_keyword">break</strong>;
-<a name="111" href="#111">111</a> <strong class="jxr_keyword">case</strong> 70:
-<a name="112" href="#112">112</a> offset += 4;
-<a name="113" href="#113">113</a> <strong class="jxr_keyword">break</strong>;
-<a name="114" href="#114">114</a> <strong class="jxr_keyword">case</strong> 71:
-<a name="115" href="#115">115</a> offset++;
-<a name="116" href="#116">116</a> <strong class="jxr_keyword">break</strong>;
-<a name="117" href="#117">117</a> <strong class="jxr_keyword">case</strong> 72:
-<a name="118" href="#118">118</a> offset += 2;
-<a name="119" href="#119">119</a> <strong class="jxr_keyword">break</strong>;
-<a name="120" href="#120">120</a> <strong class="jxr_keyword">case</strong> 73:
-<a name="121" href="#121">121</a> offset += 3;
-<a name="122" href="#122">122</a> <strong class="jxr_keyword">break</strong>;
-<a name="123" href="#123">123</a> <strong class="jxr_keyword">case</strong> 74:
-<a name="124" href="#124">124</a> offset += grpprl[offset];
-<a name="125" href="#125">125</a> <strong class="jxr_keyword">break</strong>;
-<a name="126" href="#126">126</a> <strong class="jxr_keyword">case</strong> 75:
-<a name="127" href="#127">127</a> offset++;
-<a name="128" href="#128">128</a> <strong class="jxr_keyword">break</strong>;
-<a name="129" href="#129">129</a> <strong class="jxr_keyword">case</strong> 80:
-<a name="130" href="#130">130</a> offset += 2;
-<a name="131" href="#131">131</a> <strong class="jxr_keyword">break</strong>;
-<a name="132" href="#132">132</a> <strong class="jxr_keyword">case</strong> 81:
-<a name="133" href="#133">133</a> offset += grpprl[offset];
-<a name="134" href="#134">134</a> <strong class="jxr_keyword">break</strong>;
-<a name="135" href="#135">135</a> <strong class="jxr_keyword">case</strong> 82:
-<a name="136" href="#136">136</a> offset += grpprl[offset];
-<a name="137" href="#137">137</a> <strong class="jxr_keyword">break</strong>;
-<a name="138" href="#138">138</a> <strong class="jxr_keyword">case</strong> 83:
-<a name="139" href="#139">139</a> <strong class="jxr_keyword">break</strong>;
-<a name="140" href="#140">140</a> <strong class="jxr_keyword">case</strong> 85:
-<a name="141" href="#141">141</a> offset++;
-<a name="142" href="#142">142</a> <strong class="jxr_keyword">break</strong>;
-<a name="143" href="#143">143</a> <strong class="jxr_keyword">case</strong> 86:
-<a name="144" href="#144">144</a> offset++;
-<a name="145" href="#145">145</a> <strong class="jxr_keyword">break</strong>;
-<a name="146" href="#146">146</a> <strong class="jxr_keyword">case</strong> 87:
-<a name="147" href="#147">147</a> offset++;
-<a name="148" href="#148">148</a> <strong class="jxr_keyword">break</strong>;
-<a name="149" href="#149">149</a> <strong class="jxr_keyword">case</strong> 88:
-<a name="150" href="#150">150</a> offset++;
-<a name="151" href="#151">151</a> <strong class="jxr_keyword">break</strong>;
-<a name="152" href="#152">152</a> <strong class="jxr_keyword">case</strong> 89:
-<a name="153" href="#153">153</a> offset++;
-<a name="154" href="#154">154</a> <strong class="jxr_keyword">break</strong>;
-<a name="155" href="#155">155</a> <strong class="jxr_keyword">case</strong> 90:
-<a name="156" href="#156">156</a> offset++;
-<a name="157" href="#157">157</a> <strong class="jxr_keyword">break</strong>;
-<a name="158" href="#158">158</a> <strong class="jxr_keyword">case</strong> 91:
-<a name="159" href="#159">159</a> offset++;
-<a name="160" href="#160">160</a> <strong class="jxr_keyword">break</strong>;
-<a name="161" href="#161">161</a> <strong class="jxr_keyword">case</strong> 92:
-<a name="162" href="#162">162</a> offset++;
-<a name="163" href="#163">163</a> <strong class="jxr_keyword">break</strong>;
-<a name="164" href="#164">164</a> <strong class="jxr_keyword">case</strong> 93:
-<a name="165" href="#165">165</a> offset += 2;
-<a name="166" href="#166">166</a> <strong class="jxr_keyword">break</strong>;
-<a name="167" href="#167">167</a> <strong class="jxr_keyword">case</strong> 94:
-<a name="168" href="#168">168</a> offset++;
-<a name="169" href="#169">169</a> <strong class="jxr_keyword">break</strong>;
-<a name="170" href="#170">170</a> <strong class="jxr_keyword">case</strong> 95:
-<a name="171" href="#171">171</a> offset += 3;
-<a name="172" href="#172">172</a> <strong class="jxr_keyword">break</strong>;
-<a name="173" href="#173">173</a> <strong class="jxr_keyword">case</strong> 96:
-<a name="174" href="#174">174</a> offset += 2;
-<a name="175" href="#175">175</a> <strong class="jxr_keyword">break</strong>;
-<a name="176" href="#176">176</a> <strong class="jxr_keyword">case</strong> 97:
-<a name="177" href="#177">177</a> offset += 2;
-<a name="178" href="#178">178</a> <strong class="jxr_keyword">break</strong>;
-<a name="179" href="#179">179</a> <strong class="jxr_keyword">case</strong> 98:
-<a name="180" href="#180">180</a> offset++;
-<a name="181" href="#181">181</a> <strong class="jxr_keyword">break</strong>;
-<a name="182" href="#182">182</a> <strong class="jxr_keyword">case</strong> 99:
-<a name="183" href="#183">183</a> offset++;
-<a name="184" href="#184">184</a> <strong class="jxr_keyword">break</strong>;
-<a name="185" href="#185">185</a> <strong class="jxr_keyword">case</strong> 100:
-<a name="186" href="#186">186</a> offset++;
-<a name="187" href="#187">187</a> <strong class="jxr_keyword">break</strong>;
-<a name="188" href="#188">188</a> <strong class="jxr_keyword">case</strong> 101:
-<a name="189" href="#189">189</a> offset++;
-<a name="190" href="#190">190</a> <strong class="jxr_keyword">break</strong>;
-<a name="191" href="#191">191</a> <strong class="jxr_keyword">case</strong> 102:
-<a name="192" href="#192">192</a> offset++;
-<a name="193" href="#193">193</a> <strong class="jxr_keyword">break</strong>;
-<a name="194" href="#194">194</a> <strong class="jxr_keyword">case</strong> 103:
-<a name="195" href="#195">195</a> offset += grpprl[offset];
-<a name="196" href="#196">196</a> <strong class="jxr_keyword">break</strong>;
-<a name="197" href="#197">197</a> <strong class="jxr_keyword">case</strong> 104:
-<a name="198" href="#198">198</a> offset++;
-<a name="199" href="#199">199</a> <strong class="jxr_keyword">break</strong>;
-<a name="200" href="#200">200</a> <strong class="jxr_keyword">case</strong> 105:
-<a name="201" href="#201">201</a> offset += grpprl[offset];
-<a name="202" href="#202">202</a> <strong class="jxr_keyword">break</strong>;
-<a name="203" href="#203">203</a> <strong class="jxr_keyword">case</strong> 106:
-<a name="204" href="#204">204</a> offset += grpprl[offset];
-<a name="205" href="#205">205</a> <strong class="jxr_keyword">break</strong>;
-<a name="206" href="#206">206</a> <strong class="jxr_keyword">case</strong> 107:
-<a name="207" href="#207">207</a> offset += 2;
-<a name="208" href="#208">208</a> <strong class="jxr_keyword">break</strong>;
-<a name="209" href="#209">209</a> <strong class="jxr_keyword">case</strong> 108:
-<a name="210" href="#210">210</a> offset += grpprl[offset];
-<a name="211" href="#211">211</a> <strong class="jxr_keyword">break</strong>;
-<a name="212" href="#212">212</a> <strong class="jxr_keyword">case</strong> 109:
-<a name="213" href="#213">213</a> offset += 2;
-<a name="214" href="#214">214</a> <strong class="jxr_keyword">break</strong>;
-<a name="215" href="#215">215</a> <strong class="jxr_keyword">case</strong> 110:
-<a name="216" href="#216">216</a> offset += 2;
-<a name="217" href="#217">217</a> <strong class="jxr_keyword">break</strong>;
-<a name="218" href="#218">218</a> <strong class="jxr_keyword">case</strong> 117:
-<a name="219" href="#219">219</a> offset++;
-<a name="220" href="#220">220</a> <strong class="jxr_keyword">break</strong>;
-<a name="221" href="#221">221</a> <strong class="jxr_keyword">case</strong> 118:
-<a name="222" href="#222">222</a> offset++;
-<a name="223" href="#223">223</a> <strong class="jxr_keyword">break</strong>;
-<a name="224" href="#224">224</a>
-<a name="225" href="#225">225</a> }
-<a name="226" href="#226">226</a> }
-<a name="227" href="#227">227</a> <strong class="jxr_keyword">return</strong> deleted;
-<a name="228" href="#228">228</a> }
-<a name="229" href="#229">229</a> }
+<a name="55" href="#55">55</a> <strong class="jxr_keyword">int</strong> chpTableOffset = LittleEndian.getInt(mainStream, 0xb8);
+<a name="56" href="#56">56</a> <strong class="jxr_keyword">int</strong> chpTableSize = LittleEndian.getInt(mainStream, 0xbc);
+<a name="57" href="#57">57</a>
+<a name="58" href="#58">58</a> <em class="jxr_comment">// get a list of character properties</em>
+<a name="59" href="#59">59</a> Word6CHPBinTable chpTable = <strong class="jxr_keyword">new</strong> Word6CHPBinTable(mainStream, chpTableOffset,
+<a name="60" href="#60">60</a> chpTableSize, fcMin);
+<a name="61" href="#61">61</a> List textRuns = chpTable.getTextRuns();
+<a name="62" href="#62">62</a>
+<a name="63" href="#63">63</a> <em class="jxr_comment">// iterate through the</em>
+<a name="64" href="#64">64</a> <a href="../../../../../org/apache/tika/parser/microsoft/WordTextBuffer.html">WordTextBuffer</a> finalTextBuf = <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/parser/microsoft/WordTextBuffer.html">WordTextBuffer</a>(appendable);
+<a name="65" href="#65">65</a> Iterator runsIt = textRuns.iterator();
+<a name="66" href="#66">66</a> <strong class="jxr_keyword">while</strong>(runsIt.hasNext())
+<a name="67" href="#67">67</a> {
+<a name="68" href="#68">68</a> CHPX chpx = (CHPX)runsIt.next();
+<a name="69" href="#69">69</a> <strong class="jxr_keyword">int</strong> runStart = chpx.getStart() + fcMin;
+<a name="70" href="#70">70</a> <strong class="jxr_keyword">int</strong> runEnd = chpx.getEnd() + fcMin;
+<a name="71" href="#71">71</a>
+<a name="72" href="#72">72</a> <strong class="jxr_keyword">if</strong> (!isDeleted(chpx.getGrpprl()))
+<a name="73" href="#73">73</a> {
+<a name="74" href="#74">74</a> String s = <strong class="jxr_keyword">new</strong> String(mainStream, runStart, Math.min(runEnd, fcMax) - runStart, <span class="jxr_string">"Cp1252"</span>);
+<a name="75" href="#75">75</a> finalTextBuf.append(s);
+<a name="76" href="#76">76</a> <strong class="jxr_keyword">if</strong> (runEnd >= fcMax)
+<a name="77" href="#77">77</a> {
+<a name="78" href="#78">78</a> <strong class="jxr_keyword">break</strong>;
+<a name="79" href="#79">79</a> }
+<a name="80" href="#80">80</a> }
+<a name="81" href="#81">81</a> }
+<a name="82" href="#82">82</a> }
+<a name="83" href="#83">83</a>
+<a name="84" href="#84">84</a> <em class="jxr_javadoccomment">/**</em>
+<a name="85" href="#85">85</a> <em class="jxr_javadoccomment"> * Used to determine if a run of text has been deleted.</em>
+<a name="86" href="#86">86</a> <em class="jxr_javadoccomment"> * @param grpprl The list of sprms for this run of text.</em>
+<a name="87" href="#87">87</a> <em class="jxr_javadoccomment"> * @return</em>
+<a name="88" href="#88">88</a> <em class="jxr_javadoccomment"> */</em>
+<a name="89" href="#89">89</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">boolean</strong> isDeleted(byte[] grpprl)
+<a name="90" href="#90">90</a> {
+<a name="91" href="#91">91</a> <strong class="jxr_keyword">int</strong> offset = 0;
+<a name="92" href="#92">92</a> <strong class="jxr_keyword">boolean</strong> deleted = false;
+<a name="93" href="#93">93</a> <strong class="jxr_keyword">while</strong> (offset < grpprl.length)
+<a name="94" href="#94">94</a> {
+<a name="95" href="#95">95</a> <strong class="jxr_keyword">switch</strong> (LittleEndian.getUnsignedByte(grpprl, offset++))
+<a name="96" href="#96">96</a> {
+<a name="97" href="#97">97</a> <strong class="jxr_keyword">case</strong> 65:
+<a name="98" href="#98">98</a> deleted = grpprl[offset++] != 0;
+<a name="99" href="#99">99</a> <strong class="jxr_keyword">break</strong>;
+<a name="100" href="#100">100</a> <strong class="jxr_keyword">case</strong> 66:
+<a name="101" href="#101">101</a> offset++;
+<a name="102" href="#102">102</a> <strong class="jxr_keyword">break</strong>;
+<a name="103" href="#103">103</a> <strong class="jxr_keyword">case</strong> 67:
+<a name="104" href="#104">104</a> offset++;
+<a name="105" href="#105">105</a> <strong class="jxr_keyword">break</strong>;
+<a name="106" href="#106">106</a> <strong class="jxr_keyword">case</strong> 68:
+<a name="107" href="#107">107</a> offset += grpprl[offset];
+<a name="108" href="#108">108</a> <strong class="jxr_keyword">break</strong>;
+<a name="109" href="#109">109</a> <strong class="jxr_keyword">case</strong> 69:
+<a name="110" href="#110">110</a> offset += 2;
+<a name="111" href="#111">111</a> <strong class="jxr_keyword">break</strong>;
+<a name="112" href="#112">112</a> <strong class="jxr_keyword">case</strong> 70:
+<a name="113" href="#113">113</a> offset += 4;
+<a name="114" href="#114">114</a> <strong class="jxr_keyword">break</strong>;
+<a name="115" href="#115">115</a> <strong class="jxr_keyword">case</strong> 71:
+<a name="116" href="#116">116</a> offset++;
+<a name="117" href="#117">117</a> <strong class="jxr_keyword">break</strong>;
+<a name="118" href="#118">118</a> <strong class="jxr_keyword">case</strong> 72:
+<a name="119" href="#119">119</a> offset += 2;
+<a name="120" href="#120">120</a> <strong class="jxr_keyword">break</strong>;
+<a name="121" href="#121">121</a> <strong class="jxr_keyword">case</strong> 73:
+<a name="122" href="#122">122</a> offset += 3;
+<a name="123" href="#123">123</a> <strong class="jxr_keyword">break</strong>;
+<a name="124" href="#124">124</a> <strong class="jxr_keyword">case</strong> 74:
+<a name="125" href="#125">125</a> offset += grpprl[offset];
+<a name="126" href="#126">126</a> <strong class="jxr_keyword">break</strong>;
+<a name="127" href="#127">127</a> <strong class="jxr_keyword">case</strong> 75:
+<a name="128" href="#128">128</a> offset++;
+<a name="129" href="#129">129</a> <strong class="jxr_keyword">break</strong>;
+<a name="130" href="#130">130</a> <strong class="jxr_keyword">case</strong> 80:
+<a name="131" href="#131">131</a> offset += 2;
+<a name="132" href="#132">132</a> <strong class="jxr_keyword">break</strong>;
+<a name="133" href="#133">133</a> <strong class="jxr_keyword">case</strong> 81:
+<a name="134" href="#134">134</a> offset += grpprl[offset];
+<a name="135" href="#135">135</a> <strong class="jxr_keyword">break</strong>;
+<a name="136" href="#136">136</a> <strong class="jxr_keyword">case</strong> 82:
+<a name="137" href="#137">137</a> offset += grpprl[offset];
+<a name="138" href="#138">138</a> <strong class="jxr_keyword">break</strong>;
+<a name="139" href="#139">139</a> <strong class="jxr_keyword">case</strong> 83:
+<a name="140" href="#140">140</a> <strong class="jxr_keyword">break</strong>;
+<a name="141" href="#141">141</a> <strong class="jxr_keyword">case</strong> 85:
+<a name="142" href="#142">142</a> offset++;
+<a name="143" href="#143">143</a> <strong class="jxr_keyword">break</strong>;
+<a name="144" href="#144">144</a> <strong class="jxr_keyword">case</strong> 86:
+<a name="145" href="#145">145</a> offset++;
+<a name="146" href="#146">146</a> <strong class="jxr_keyword">break</strong>;
+<a name="147" href="#147">147</a> <strong class="jxr_keyword">case</strong> 87:
+<a name="148" href="#148">148</a> offset++;
+<a name="149" href="#149">149</a> <strong class="jxr_keyword">break</strong>;
+<a name="150" href="#150">150</a> <strong class="jxr_keyword">case</strong> 88:
+<a name="151" href="#151">151</a> offset++;
+<a name="152" href="#152">152</a> <strong class="jxr_keyword">break</strong>;
+<a name="153" href="#153">153</a> <strong class="jxr_keyword">case</strong> 89:
+<a name="154" href="#154">154</a> offset++;
+<a name="155" href="#155">155</a> <strong class="jxr_keyword">break</strong>;
+<a name="156" href="#156">156</a> <strong class="jxr_keyword">case</strong> 90:
+<a name="157" href="#157">157</a> offset++;
+<a name="158" href="#158">158</a> <strong class="jxr_keyword">break</strong>;
+<a name="159" href="#159">159</a> <strong class="jxr_keyword">case</strong> 91:
+<a name="160" href="#160">160</a> offset++;
+<a name="161" href="#161">161</a> <strong class="jxr_keyword">break</strong>;
+<a name="162" href="#162">162</a> <strong class="jxr_keyword">case</strong> 92:
+<a name="163" href="#163">163</a> offset++;
+<a name="164" href="#164">164</a> <strong class="jxr_keyword">break</strong>;
+<a name="165" href="#165">165</a> <strong class="jxr_keyword">case</strong> 93:
+<a name="166" href="#166">166</a> offset += 2;
+<a name="167" href="#167">167</a> <strong class="jxr_keyword">break</strong>;
+<a name="168" href="#168">168</a> <strong class="jxr_keyword">case</strong> 94:
+<a name="169" href="#169">169</a> offset++;
+<a name="170" href="#170">170</a> <strong class="jxr_keyword">break</strong>;
+<a name="171" href="#171">171</a> <strong class="jxr_keyword">case</strong> 95:
+<a name="172" href="#172">172</a> offset += 3;
+<a name="173" href="#173">173</a> <strong class="jxr_keyword">break</strong>;
+<a name="174" href="#174">174</a> <strong class="jxr_keyword">case</strong> 96:
+<a name="175" href="#175">175</a> offset += 2;
+<a name="176" href="#176">176</a> <strong class="jxr_keyword">break</strong>;
+<a name="177" href="#177">177</a> <strong class="jxr_keyword">case</strong> 97:
+<a name="178" href="#178">178</a> offset += 2;
+<a name="179" href="#179">179</a> <strong class="jxr_keyword">break</strong>;
+<a name="180" href="#180">180</a> <strong class="jxr_keyword">case</strong> 98:
+<a name="181" href="#181">181</a> offset++;
+<a name="182" href="#182">182</a> <strong class="jxr_keyword">break</strong>;
+<a name="183" href="#183">183</a> <strong class="jxr_keyword">case</strong> 99:
+<a name="184" href="#184">184</a> offset++;
+<a name="185" href="#185">185</a> <strong class="jxr_keyword">break</strong>;
+<a name="186" href="#186">186</a> <strong class="jxr_keyword">case</strong> 100:
+<a name="187" href="#187">187</a> offset++;
+<a name="188" href="#188">188</a> <strong class="jxr_keyword">break</strong>;
+<a name="189" href="#189">189</a> <strong class="jxr_keyword">case</strong> 101:
+<a name="190" href="#190">190</a> offset++;
+<a name="191" href="#191">191</a> <strong class="jxr_keyword">break</strong>;
+<a name="192" href="#192">192</a> <strong class="jxr_keyword">case</strong> 102:
+<a name="193" href="#193">193</a> offset++;
+<a name="194" href="#194">194</a> <strong class="jxr_keyword">break</strong>;
+<a name="195" href="#195">195</a> <strong class="jxr_keyword">case</strong> 103:
+<a name="196" href="#196">196</a> offset += grpprl[offset];
+<a name="197" href="#197">197</a> <strong class="jxr_keyword">break</strong>;
+<a name="198" href="#198">198</a> <strong class="jxr_keyword">case</strong> 104:
+<a name="199" href="#199">199</a> offset++;
+<a name="200" href="#200">200</a> <strong class="jxr_keyword">break</strong>;
+<a name="201" href="#201">201</a> <strong class="jxr_keyword">case</strong> 105:
+<a name="202" href="#202">202</a> offset += grpprl[offset];
+<a name="203" href="#203">203</a> <strong class="jxr_keyword">break</strong>;
+<a name="204" href="#204">204</a> <strong class="jxr_keyword">case</strong> 106:
+<a name="205" href="#205">205</a> offset += grpprl[offset];
+<a name="206" href="#206">206</a> <strong class="jxr_keyword">break</strong>;
+<a name="207" href="#207">207</a> <strong class="jxr_keyword">case</strong> 107:
+<a name="208" href="#208">208</a> offset += 2;
+<a name="209" href="#209">209</a> <strong class="jxr_keyword">break</strong>;
+<a name="210" href="#210">210</a> <strong class="jxr_keyword">case</strong> 108:
+<a name="211" href="#211">211</a> offset += grpprl[offset];
+<a name="212" href="#212">212</a> <strong class="jxr_keyword">break</strong>;
+<a name="213" href="#213">213</a> <strong class="jxr_keyword">case</strong> 109:
+<a name="214" href="#214">214</a> offset += 2;
+<a name="215" href="#215">215</a> <strong class="jxr_keyword">break</strong>;
+<a name="216" href="#216">216</a> <strong class="jxr_keyword">case</strong> 110:
+<a name="217" href="#217">217</a> offset += 2;
+<a name="218" href="#218">218</a> <strong class="jxr_keyword">break</strong>;
+<a name="219" href="#219">219</a> <strong class="jxr_keyword">case</strong> 117:
+<a name="220" href="#220">220</a> offset++;
+<a name="221" href="#221">221</a> <strong class="jxr_keyword">break</strong>;
+<a name="222" href="#222">222</a> <strong class="jxr_keyword">case</strong> 118:
+<a name="223" href="#223">223</a> offset++;
+<a name="224" href="#224">224</a> <strong class="jxr_keyword">break</strong>;
+<a name="225" href="#225">225</a>
+<a name="226" href="#226">226</a> }
+<a name="227" href="#227">227</a> }
+<a name="228" href="#228">228</a> <strong class="jxr_keyword">return</strong> deleted;
+<a name="229" href="#229">229</a> }
+<a name="230" href="#230">230</a> }
</pre>
<hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body>
</html>
Modified: incubator/tika/site/xref/org/apache/tika/parser/microsoft/WordParser.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/microsoft/WordParser.html?rev=609491&r1=609490&r2=609491&view=diff
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/microsoft/WordParser.html (original)
+++ incubator/tika/site/xref/org/apache/tika/parser/microsoft/WordParser.html Sun Jan 6 19:06:26 2008
@@ -57,7 +57,7 @@
<a name="47" href="#47">47</a> <em class="jxr_javadoccomment"> *</em>
<a name="48" href="#48">48</a> <em class="jxr_javadoccomment"> * @param in The InputStream representing the Word file.</em>
<a name="49" href="#49">49</a> <em class="jxr_javadoccomment"> */</em>
-<a name="50" href="#50">50</a> <strong class="jxr_keyword">public</strong> String extractText(POIFSFileSystem fsys)
+<a name="50" href="#50">50</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">void</strong> extractText(POIFSFileSystem fsys, Appendable appendable)
<a name="51" href="#51">51</a> <strong class="jxr_keyword">throws</strong> IOException, <a href="../../../../../org/apache/tika/exception/TikaException.html">TikaException</a> {
<a name="52" href="#52">52</a> <em class="jxr_comment">// load our POIFS document streams.</em>
<a name="53" href="#53">53</a> DocumentEntry headerProps =
@@ -84,8 +84,8 @@
<a name="74" href="#74">74</a> <strong class="jxr_keyword">case</strong> 103:
<a name="75" href="#75">75</a> <strong class="jxr_keyword">case</strong> 104:
<a name="76" href="#76">76</a> <em class="jxr_comment">// this is a Word 6.0 doc send it to the extractor for that version.</em>
-<a name="77" href="#77">77</a> Word6Extractor oldExtractor = <strong class="jxr_keyword">new</strong> Word6Extractor();
-<a name="78" href="#78">78</a> <strong class="jxr_keyword">return</strong> oldExtractor.extractText(header);
+<a name="77" href="#77">77</a> Word6Extractor oldExtractor = <strong class="jxr_keyword">new</strong> Word6Extractor(appendable);
+<a name="78" href="#78">78</a> oldExtractor.extractText(header);
<a name="79" href="#79">79</a> }
<a name="80" href="#80">80</a>
<a name="81" href="#81">81</a> <em class="jxr_comment">//get the location of the piece table</em>
@@ -133,7 +133,7 @@
<a name="123" href="#123">123</a> <strong class="jxr_keyword">int</strong> currentTextStart = currentPiece.getStart();
<a name="124" href="#124">124</a> <strong class="jxr_keyword">int</strong> currentTextEnd = currentPiece.getEnd();
<a name="125" href="#125">125</a>
-<a name="126" href="#126">126</a> <a href="../../../../../org/apache/tika/parser/microsoft/WordTextBuffer.html">WordTextBuffer</a> finalTextBuf = <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/parser/microsoft/WordTextBuffer.html">WordTextBuffer</a>();
+<a name="126" href="#126">126</a> <a href="../../../../../org/apache/tika/parser/microsoft/WordTextBuffer.html">WordTextBuffer</a> finalTextBuf = <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/parser/microsoft/WordTextBuffer.html">WordTextBuffer</a>(appendable);
<a name="127" href="#127">127</a>
<a name="128" href="#128">128</a> <em class="jxr_comment">// iterate through all text runs extract the text only if they haven't been</em>
<a name="129" href="#129">129</a> <em class="jxr_comment">// deleted</em>
@@ -167,7 +167,7 @@
<a name="157" href="#157">157</a> runStart = currentTextStart;
<a name="158" href="#158">158</a> currentTextEnd = currentPiece.getEnd ();
<a name="159" href="#159">159</a> } <strong class="jxr_keyword">else</strong> {
-<a name="160" href="#160">160</a> <strong class="jxr_keyword">return</strong> finalTextBuf.toString();
+<a name="160" href="#160">160</a> <strong class="jxr_keyword">return</strong>;
<a name="161" href="#161">161</a> }
<a name="162" href="#162">162</a> }
<a name="163" href="#163">163</a> String str = currentPiece.substring(0, runEnd - currentTextStart);
@@ -182,28 +182,27 @@
<a name="172" href="#172">172</a> finalTextBuf.append(str);
<a name="173" href="#173">173</a> }
<a name="174" href="#174">174</a> }
-<a name="175" href="#175">175</a> <strong class="jxr_keyword">return</strong> finalTextBuf.toString();
-<a name="176" href="#176">176</a> }
-<a name="177" href="#177">177</a>
-<a name="178" href="#178">178</a> <em class="jxr_javadoccomment">/**</em>
-<a name="179" href="#179">179</a> <em class="jxr_javadoccomment"> * Used to determine if a run of text has been deleted.</em>
-<a name="180" href="#180">180</a> <em class="jxr_javadoccomment"> *</em>
-<a name="181" href="#181">181</a> <em class="jxr_javadoccomment"> * @param grpprl The list of sprms for a particular run of text.</em>
-<a name="182" href="#182">182</a> <em class="jxr_javadoccomment"> * @return true if this run of text has been deleted.</em>
-<a name="183" href="#183">183</a> <em class="jxr_javadoccomment"> */</em>
-<a name="184" href="#184">184</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">boolean</strong> isDeleted(byte[] grpprl) {
-<a name="185" href="#185">185</a> SprmIterator iterator = <strong class="jxr_keyword">new</strong> SprmIterator(grpprl,0);
-<a name="186" href="#186">186</a> <strong class="jxr_keyword">while</strong> (iterator.hasNext()) {
-<a name="187" href="#187">187</a> SprmOperation op = iterator.next();
-<a name="188" href="#188">188</a> <em class="jxr_comment">// 0 is the operation that signals a FDelRMark operation</em>
-<a name="189" href="#189">189</a> <strong class="jxr_keyword">if</strong> (op.getOperation() == 0 && op.getOperand() != 0) {
-<a name="190" href="#190">190</a> <strong class="jxr_keyword">return</strong> <strong class="jxr_keyword">true</strong>;
-<a name="191" href="#191">191</a> }
-<a name="192" href="#192">192</a> }
-<a name="193" href="#193">193</a> <strong class="jxr_keyword">return</strong> false;
-<a name="194" href="#194">194</a> }
-<a name="195" href="#195">195</a>
-<a name="196" href="#196">196</a> }
+<a name="175" href="#175">175</a> }
+<a name="176" href="#176">176</a>
+<a name="177" href="#177">177</a> <em class="jxr_javadoccomment">/**</em>
+<a name="178" href="#178">178</a> <em class="jxr_javadoccomment"> * Used to determine if a run of text has been deleted.</em>
+<a name="179" href="#179">179</a> <em class="jxr_javadoccomment"> *</em>
+<a name="180" href="#180">180</a> <em class="jxr_javadoccomment"> * @param grpprl The list of sprms for a particular run of text.</em>
+<a name="181" href="#181">181</a> <em class="jxr_javadoccomment"> * @return true if this run of text has been deleted.</em>
+<a name="182" href="#182">182</a> <em class="jxr_javadoccomment"> */</em>
+<a name="183" href="#183">183</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">boolean</strong> isDeleted(byte[] grpprl) {
+<a name="184" href="#184">184</a> SprmIterator iterator = <strong class="jxr_keyword">new</strong> SprmIterator(grpprl,0);
+<a name="185" href="#185">185</a> <strong class="jxr_keyword">while</strong> (iterator.hasNext()) {
+<a name="186" href="#186">186</a> SprmOperation op = iterator.next();
+<a name="187" href="#187">187</a> <em class="jxr_comment">// 0 is the operation that signals a FDelRMark operation</em>
+<a name="188" href="#188">188</a> <strong class="jxr_keyword">if</strong> (op.getOperation() == 0 && op.getOperand() != 0) {
+<a name="189" href="#189">189</a> <strong class="jxr_keyword">return</strong> <strong class="jxr_keyword">true</strong>;
+<a name="190" href="#190">190</a> }
+<a name="191" href="#191">191</a> }
+<a name="192" href="#192">192</a> <strong class="jxr_keyword">return</strong> false;
+<a name="193" href="#193">193</a> }
+<a name="194" href="#194">194</a>
+<a name="195" href="#195">195</a> }
</pre>
<hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body>
</html>