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 2007/11/18 23:21:13 UTC
svn commit: r596146 [32/36] - in /incubator/tika/site: ./ apidocs/
apidocs/org/ apidocs/org/apache/ apidocs/org/apache/tika/
apidocs/org/apache/tika/config/ apidocs/org/apache/tika/config/class-use/
apidocs/org/apache/tika/exception/ apidocs/org/apache...
Added: 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=596146&view=auto
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/microsoft/PowerPointExtractor.html (added)
+++ incubator/tika/site/xref/org/apache/tika/parser/microsoft/PowerPointExtractor.html Sun Nov 18 14:20:54 2007
@@ -0,0 +1,453 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+<head>
+<meta http-equiv="content-type" content="text/html; charset=ISO-8859-1" />
+<title>PowerPointExtractor xref</title>
+<link type="text/css" rel="stylesheet" href="../../../../../stylesheet.css" />
+</head>
+<body>
+<div id="overview"><a href="../../../../../../apidocs/org/apache/tika/parser/microsoft/PowerPointExtractor.html">View Javadoc</a></div><pre>
+
+<a name="1" href="#1">1</a> <em class="jxr_javadoccomment">/**</em>
+<a name="2" href="#2">2</a> <em class="jxr_javadoccomment"> * Licensed to the Apache Software Foundation (ASF) under one or more</em>
+<a name="3" href="#3">3</a> <em class="jxr_javadoccomment"> * contributor license agreements. See the NOTICE file distributed with</em>
+<a name="4" href="#4">4</a> <em class="jxr_javadoccomment"> * this work for additional information regarding copyright ownership.</em>
+<a name="5" href="#5">5</a> <em class="jxr_javadoccomment"> * The ASF licenses this file to You under the Apache License, Version 2.0</em>
+<a name="6" href="#6">6</a> <em class="jxr_javadoccomment"> * (the "License"); you may not use this file except in compliance with</em>
+<a name="7" href="#7">7</a> <em class="jxr_javadoccomment"> * the License. You may obtain a copy of the License at</em>
+<a name="8" href="#8">8</a> <em class="jxr_javadoccomment"> *</em>
+<a name="9" href="#9">9</a> <em class="jxr_javadoccomment"> * <a href="http://www.apache.org/licenses/LICENSE-2.0" target="alexandria_uri">http://www.apache.org/licenses/LICENSE-2.0</a></em>
+<a name="10" href="#10">10</a> <em class="jxr_javadoccomment"> *</em>
+<a name="11" href="#11">11</a> <em class="jxr_javadoccomment"> * Unless required by applicable law or agreed to in writing, software</em>
+<a name="12" href="#12">12</a> <em class="jxr_javadoccomment"> * distributed under the License is distributed on an "AS IS" BASIS,</em>
+<a name="13" href="#13">13</a> <em class="jxr_javadoccomment"> * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</em>
+<a name="14" href="#14">14</a> <em class="jxr_javadoccomment"> * See the License for the specific language governing permissions and</em>
+<a name="15" href="#15">15</a> <em class="jxr_javadoccomment"> * limitations under the License.</em>
+<a name="16" href="#16">16</a> <em class="jxr_javadoccomment"> */</em>
+<a name="17" href="#17">17</a> <strong class="jxr_keyword">package</strong> org.apache.tika.parser.microsoft;
+<a name="18" href="#18">18</a>
+<a name="19" href="#19">19</a> <strong class="jxr_keyword">import</strong> java.io.InputStream;
+<a name="20" href="#20">20</a> <strong class="jxr_keyword">import</strong> java.util.Enumeration;
+<a name="21" href="#21">21</a> <strong class="jxr_keyword">import</strong> java.util.Hashtable;
+<a name="22" href="#22">22</a> <strong class="jxr_keyword">import</strong> java.util.List;
+<a name="23" href="#23">23</a> <strong class="jxr_keyword">import</strong> java.util.Vector;
+<a name="24" href="#24">24</a>
+<a name="25" href="#25">25</a> <strong class="jxr_keyword">import</strong> org.apache.log4j.Logger;
+<a name="26" href="#26">26</a> <strong class="jxr_keyword">import</strong> org.apache.poi.hdf.extractor.Utils;
+<a name="27" href="#27">27</a> <strong class="jxr_keyword">import</strong> org.apache.poi.util.LittleEndian;
+<a name="28" href="#28">28</a> <strong class="jxr_keyword">import</strong> org.apache.poi.util.StringUtil;
+<a name="29" href="#29">29</a>
+<a name="30" href="#30">30</a> <strong class="jxr_keyword">class</strong> <a href="../../../../../org/apache/tika/parser/microsoft/PowerPointExtractor.html">PowerPointExtractor</a> {
+<a name="31" href="#31">31</a>
+<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="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="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>
+<a name="44" href="#44">44</a> <em class="jxr_javadoccomment">/**</em>
+<a name="45" href="#45">45</a> <em class="jxr_javadoccomment"> * Reads the internal PowerPoint document stream.</em>
+<a name="46" href="#46">46</a> <em class="jxr_javadoccomment"> */</em>
+<a name="47" href="#47">47</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">void</strong> extract(InputStream dis) {
+<a name="48" href="#48">48</a> <strong class="jxr_keyword">try</strong> {
+<a name="49" href="#49">49</a> <strong class="jxr_keyword">final</strong> byte pptdata[] = <strong class="jxr_keyword">new</strong> byte[dis.available()];
+<a name="50" href="#50">50</a> dis.read(pptdata, 0, dis.available());
+<a name="51" href="#51">51</a> <strong class="jxr_keyword">int</strong> offset = 0;
+<a name="52" href="#52">52</a> <strong class="jxr_keyword">long</strong> offsetPD = 0;
+<a name="53" href="#53">53</a>
+<a name="54" href="#54">54</a> <em class="jxr_comment">/*</em>
+<a name="55" href="#55">55</a> <em class="jxr_comment"> * Traverse Bytearray to get CurrentUserEditAtom Call to extract the</em>
+<a name="56" href="#56">56</a> <em class="jxr_comment"> * Text in all PlaceHolders to hold PPTClientTextBox objects for</em>
+<a name="57" href="#57">57</a> <em class="jxr_comment"> * mapping into Slide Objects</em>
+<a name="58" href="#58">58</a> <em class="jxr_comment"> */</em>
+<a name="59" href="#59">59</a> Hashtable<em class="jxr_comment">/*<em class="jxr_comment"> <Long, TextBox> */</em>containerTextBox = <strong class="jxr_keyword">new</strong> Hashtable/*</em>
+<a name="60" href="#60">60</a> * <Long,
+<a name="61" href="#61">61</a> * TextBox>
+<a name="62" href="#62">62</a> */();
+<a name="63" href="#63">63</a> <em class="jxr_comment">// Traverse ByteArray to identiy edit paths of ClientTextBoxes</em>
+<a name="64" href="#64">64</a> <strong class="jxr_keyword">long</strong> n = pptdata.length - 20;
+<a name="65" href="#65">65</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">long</strong> i = 0; i < n; i++) {
+<a name="66" href="#66">66</a>
+<a name="67" href="#67">67</a> <strong class="jxr_keyword">final</strong> <strong class="jxr_keyword">long</strong> type = LittleEndian.getUShort(pptdata, (<strong class="jxr_keyword">int</strong>) i + 2);
+<a name="68" href="#68">68</a> <em class="jxr_comment">// final long size = LittleEndian.getUInt(pptdata, (int) i + 4);</em>
+<a name="69" href="#69">69</a>
+<a name="70" href="#70">70</a> <strong class="jxr_keyword">if</strong> (PPTConstants.PPT_ATOM_USEREDIT == type) {
+<a name="71" href="#71">71</a> <em class="jxr_comment">/*</em>
+<a name="72" href="#72">72</a> <em class="jxr_comment"> * Checking the Record Header (UserEditAtom)</em>
+<a name="73" href="#73">73</a> <em class="jxr_comment"> */</em>
+<a name="74" href="#74">74</a> <em class="jxr_comment">// final long lastSlideID = LittleEndian.getInt(pptdata,</em>
+<a name="75" href="#75">75</a> <em class="jxr_comment">// (int) i + 8);</em>
+<a name="76" href="#76">76</a> <em class="jxr_comment">// final long version = LittleEndian.getUInt(pptdata, (int)</em>
+<a name="77" href="#77">77</a> <em class="jxr_comment">// i + 12);</em>
+<a name="78" href="#78">78</a> offset = (<strong class="jxr_keyword">int</strong>) LittleEndian.getUInt(pptdata, (<strong class="jxr_keyword">int</strong>) i + 16);
+<a name="79" href="#79">79</a> offsetPD = LittleEndian.getUInt(pptdata, (<strong class="jxr_keyword">int</strong>) i + 20);
+<a name="80" href="#80">80</a>
+<a name="81" href="#81">81</a> <em class="jxr_comment">/*</em>
+<a name="82" href="#82">82</a> <em class="jxr_comment"> * Call to extract ClientTextBox text in each UserEditAtom</em>
+<a name="83" href="#83">83</a> <em class="jxr_comment"> */</em>
+<a name="84" href="#84">84</a> containerTextBox = extractTextBoxes(containerTextBox,
+<a name="85" href="#85">85</a> offset, pptdata, offsetPD);
+<a name="86" href="#86">86</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (PPTConstants.PPT_ATOM_DRAWINGGROUP == type) {
+<a name="87" href="#87">87</a> <em class="jxr_comment">// if (LOG.isTraceEnabled()) {</em>
+<a name="88" href="#88">88</a> <em class="jxr_comment">// LOG.trace("PPT_DRAWINGGROUP_ATOM ignored: " + type);</em>
+<a name="89" href="#89">89</a> <em class="jxr_comment">// }</em>
+<a name="90" href="#90">90</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (PPTConstants.PPT_ATOM_TEXTBYTE == type) {
+<a name="91" href="#91">91</a> <em class="jxr_comment">// if (LOG.isTraceEnabled()) {</em>
+<a name="92" href="#92">92</a> <em class="jxr_comment">// LOG.trace("PPT_TEXTBYTE_ATOM ignored: " + type);</em>
+<a name="93" href="#93">93</a> <em class="jxr_comment">// }</em>
+<a name="94" href="#94">94</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (PPTConstants.PPT_ATOM_TEXTCHAR == type) {
+<a name="95" href="#95">95</a> <em class="jxr_comment">// if (LOG.isTraceEnabled()) {</em>
+<a name="96" href="#96">96</a> <em class="jxr_comment">// LOG.trace("PPT_TEXTCHAR_ATOM ignored: " + type);</em>
+<a name="97" href="#97">97</a> <em class="jxr_comment">// }</em>
+<a name="98" href="#98">98</a> } <strong class="jxr_keyword">else</strong> {
+<a name="99" href="#99">99</a> <em class="jxr_comment">// no action</em>
+<a name="100" href="#100">100</a> <em class="jxr_comment">// if (LOG.isTraceEnabled()) {</em>
+<a name="101" href="#101">101</a> <em class="jxr_comment">// LOG.trace("type not handled: " + type);</em>
+<a name="102" href="#102">102</a> <em class="jxr_comment">// }</em>
+<a name="103" href="#103">103</a> }
+<a name="104" href="#104">104</a> }
+<a name="105" href="#105">105</a>
+<a name="106" href="#106">106</a> <strong class="jxr_keyword">final</strong> List<em class="jxr_comment">/*<em class="jxr_comment"> <PPTSlide> */</em>slides = extractSlides(offset, pptdata,</em>
+<a name="107" href="#107">107</a> offsetPD);
+<a name="108" href="#108">108</a>
+<a name="109" href="#109">109</a> <strong class="jxr_keyword">if</strong> (slides.size() == 0) {
+<a name="110" href="#110">110</a> <strong class="jxr_keyword">if</strong> (LOG.isInfoEnabled()) {
+<a name="111" href="#111">111</a> LOG.info(<span class="jxr_string">"No slides extracted!"</span>);
+<a name="112" href="#112">112</a> }
+<a name="113" href="#113">113</a>
+<a name="114" href="#114">114</a> } <strong class="jxr_keyword">else</strong> {
+<a name="115" href="#115">115</a> <a href="../../../../../org/apache/tika/parser/microsoft/Slide.html">Slide</a> slide = (Slide) slides.get(slides.size() - 1);
+<a name="116" href="#116">116</a>
+<a name="117" href="#117">117</a> <strong class="jxr_keyword">for</strong> (Enumeration enumeration = containerTextBox.elements(); enumeration
+<a name="118" href="#118">118</a> .hasMoreElements();) {
+<a name="119" href="#119">119</a> <strong class="jxr_keyword">final</strong> <a href="../../../../../org/apache/tika/parser/microsoft/TextBox.html">TextBox</a> textBox = (TextBox) enumeration.nextElement();
+<a name="120" href="#120">120</a> slide.addContent(textBox.getContent());
+<a name="121" href="#121">121</a> }
+<a name="122" href="#122">122</a>
+<a name="123" href="#123">123</a> <em class="jxr_comment">/*</em>
+<a name="124" href="#124">124</a> <em class="jxr_comment"> * Merging TextBox data with Slide Data Printing the text from</em>
+<a name="125" href="#125">125</a> <em class="jxr_comment"> * Slides vector object.</em>
+<a name="126" href="#126">126</a> <em class="jxr_comment"> */</em>
+<a name="127" href="#127">127</a> List scontent;
+<a name="128" href="#128">128</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">int</strong> i = 0; i < slides.size(); i++) {
+<a name="129" href="#129">129</a> slide = (Slide) slides.get(i);
+<a name="130" href="#130">130</a> scontent = slide.getContent();
+<a name="131" href="#131">131</a> String contentText;
+<a name="132" href="#132">132</a>
+<a name="133" href="#133">133</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">int</strong> j = 0; j < scontent.size(); j++) {
+<a name="134" href="#134">134</a> contentText = scontent.get(j).toString();
+<a name="135" href="#135">135</a> builder.append(contentText);
+<a name="136" href="#136">136</a>
+<a name="137" href="#137">137</a> <em class="jxr_comment">// to avoid concatinated words we add a blank additional</em>
+<a name="138" href="#138">138</a> <strong class="jxr_keyword">if</strong> (contentText.length() > 0
+<a name="139" href="#139">139</a> && !(contentText.endsWith(<span class="jxr_string">"\r"</span>) || contentText
+<a name="140" href="#140">140</a> .endsWith(<span class="jxr_string">"\n"</span>))) {
+<a name="141" href="#141">141</a> builder.append(<span class="jxr_string">" "</span>);
+<a name="142" href="#142">142</a> }
+<a name="143" href="#143">143</a> }
+<a name="144" href="#144">144</a> }
+<a name="145" href="#145">145</a> }
+<a name="146" href="#146">146</a> } <strong class="jxr_keyword">catch</strong> (Throwable ex) {
+<a name="147" href="#147">147</a> <em class="jxr_comment">// because of not killing complete crawling all Throwables are</em>
+<a name="148" href="#148">148</a> <em class="jxr_comment">// catched.</em>
+<a name="149" href="#149">149</a>
+<a name="150" href="#150">150</a> LOG.error(<span class="jxr_string">"processPOIFSReaderEvent"</span>, ex);
+<a name="151" href="#151">151</a> }
+<a name="152" href="#152">152</a> }
+<a name="153" href="#153">153</a>
+<a name="154" href="#154">154</a> <em class="jxr_javadoccomment">/**</em>
+<a name="155" href="#155">155</a> <em class="jxr_javadoccomment"> * Extracts the client text boxes of a slide.</em>
+<a name="156" href="#156">156</a> <em class="jxr_javadoccomment"> * </em>
+<a name="157" href="#157">157</a> <em class="jxr_javadoccomment"> * @param containerTextBox</em>
+<a name="158" href="#158">158</a> <em class="jxr_javadoccomment"> * @param offset</em>
+<a name="159" href="#159">159</a> <em class="jxr_javadoccomment"> * @param pptdata</em>
+<a name="160" href="#160">160</a> <em class="jxr_javadoccomment"> * @param offsetPD</em>
+<a name="161" href="#161">161</a> <em class="jxr_javadoccomment"> * @return Hashtable</em>
+<a name="162" href="#162">162</a> <em class="jxr_javadoccomment"> * @see TextBox</em>
+<a name="163" href="#163">163</a> <em class="jxr_javadoccomment"> */</em>
+<a name="164" href="#164">164</a> <strong class="jxr_keyword">protected</strong> Hashtable<em class="jxr_comment">/*<em class="jxr_comment"> <Long, TextBox> */</em>extractTextBoxes(</em>
+<a name="165" href="#165">165</a> <strong class="jxr_keyword">final</strong> Hashtable<em class="jxr_comment">/*<em class="jxr_comment"> <Long, TextBox> */</em>containerTextBox,</em>
+<a name="166" href="#166">166</a> <strong class="jxr_keyword">final</strong> <strong class="jxr_keyword">int</strong> offset, <strong class="jxr_keyword">final</strong> byte[] pptdata, <strong class="jxr_keyword">final</strong> <strong class="jxr_keyword">long</strong> offsetPD) {
+<a name="167" href="#167">167</a>
+<a name="168" href="#168">168</a> <em class="jxr_comment">// To hold temporary data</em>
+<a name="169" href="#169">169</a> <a href="../../../../../org/apache/tika/parser/microsoft/FilteredStringWriter.html">FilteredStringWriter</a> outStream = <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/parser/microsoft/FilteredStringWriter.html">FilteredStringWriter</a>();
+<a name="170" href="#170">170</a>
+<a name="171" href="#171">171</a> <a href="../../../../../org/apache/tika/parser/microsoft/TextBox.html">TextBox</a> textBox;
+<a name="172" href="#172">172</a>
+<a name="173" href="#173">173</a> <em class="jxr_comment">// Traversing the bytearray up to Presist directory position</em>
+<a name="174" href="#174">174</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">int</strong> i = offset; i < offsetPD - 20; i++) {
+<a name="175" href="#175">175</a> <strong class="jxr_keyword">try</strong> {
+<a name="176" href="#176">176</a> <em class="jxr_comment">// Record info</em>
+<a name="177" href="#177">177</a> <em class="jxr_comment">// final long rinfo = LittleEndian.getUShort(pptdata, (int) i);</em>
+<a name="178" href="#178">178</a> <em class="jxr_comment">// Record Type</em>
+<a name="179" href="#179">179</a> <strong class="jxr_keyword">final</strong> <strong class="jxr_keyword">long</strong> recordType = LittleEndian.getUShort(pptdata, i + 2);
+<a name="180" href="#180">180</a> <em class="jxr_comment">// Record Size</em>
+<a name="181" href="#181">181</a> <strong class="jxr_keyword">final</strong> <strong class="jxr_keyword">long</strong> recordSize = LittleEndian.getUInt(pptdata, i + 4);
+<a name="182" href="#182">182</a>
+<a name="183" href="#183">183</a> <strong class="jxr_keyword">if</strong> (recordType == PPTConstants.PPT_ATOM_DRAWINGGROUP) {
+<a name="184" href="#184">184</a> <em class="jxr_comment">/*</em>
+<a name="185" href="#185">185</a> <em class="jxr_comment"> * Record type is of Drawing Group</em>
+<a name="186" href="#186">186</a> <em class="jxr_comment"> */</em>
+<a name="187" href="#187">187</a>
+<a name="188" href="#188">188</a> <em class="jxr_comment">// Total number of objects</em>
+<a name="189" href="#189">189</a> <em class="jxr_comment">// final long objectCount = LittleEndian.getUInt(pptdata,</em>
+<a name="190" href="#190">190</a> <em class="jxr_comment">// (int) i +</em>
+<a name="191" href="#191">191</a> <em class="jxr_comment">// 8);</em>
+<a name="192" href="#192">192</a> <em class="jxr_comment">// currentID = Group ID+number of objects</em>
+<a name="193" href="#193">193</a> <strong class="jxr_keyword">long</strong> currentID = LittleEndian.getInt(pptdata, i + 12);
+<a name="194" href="#194">194</a> currentID = ((<strong class="jxr_keyword">int</strong>) (currentID / 1024)) * 1024;
+<a name="195" href="#195">195</a>
+<a name="196" href="#196">196</a> <strong class="jxr_keyword">if</strong> (currentID == PPTConstants.PPT_MASTERSLIDE) {
+<a name="197" href="#197">197</a> <em class="jxr_comment">// Ignore Master Slide objects</em>
+<a name="198" href="#198">198</a> <strong class="jxr_keyword">if</strong> (LOG.isTraceEnabled()) {
+<a name="199" href="#199">199</a> LOG.trace(<span class="jxr_string">"Ignore master slide."</span>);
+<a name="200" href="#200">200</a> }
+<a name="201" href="#201">201</a> i++;
+<a name="202" href="#202">202</a> <strong class="jxr_keyword">continue</strong>;
+<a name="203" href="#203">203</a> }
+<a name="204" href="#204">204</a>
+<a name="205" href="#205">205</a> <em class="jxr_comment">// Check for the ClientTextBox GroupID existence</em>
+<a name="206" href="#206">206</a> <strong class="jxr_keyword">if</strong> (containerTextBox.containsKey(<strong class="jxr_keyword">new</strong> Long(currentID))) {
+<a name="207" href="#207">207</a> <em class="jxr_comment">// If exists get Client Textbox Group</em>
+<a name="208" href="#208">208</a> textBox = (TextBox) containerTextBox.get(<strong class="jxr_keyword">new</strong> Long(
+<a name="209" href="#209">209</a> currentID));
+<a name="210" href="#210">210</a> textBox.setContent(<span class="jxr_string">""</span>);
+<a name="211" href="#211">211</a>
+<a name="212" href="#212">212</a> } <strong class="jxr_keyword">else</strong> {
+<a name="213" href="#213">213</a> textBox = <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/parser/microsoft/TextBox.html">TextBox</a>(currentID);
+<a name="214" href="#214">214</a> containerTextBox.put(<strong class="jxr_keyword">new</strong> Long(currentID), textBox);
+<a name="215" href="#215">215</a> }
+<a name="216" href="#216">216</a>
+<a name="217" href="#217">217</a> <em class="jxr_comment">/*</em>
+<a name="218" href="#218">218</a> <em class="jxr_comment"> * Iterating the bytearray for TextCharAtoms and</em>
+<a name="219" href="#219">219</a> <em class="jxr_comment"> * TextBytesAtom</em>
+<a name="220" href="#220">220</a> <em class="jxr_comment"> */</em>
+<a name="221" href="#221">221</a> <strong class="jxr_keyword">if</strong> ((offsetPD - 20) != recordSize) {
+<a name="222" href="#222">222</a> <em class="jxr_comment">// TODO something wrong? Probably an OLE-Object, which</em>
+<a name="223" href="#223">223</a> <em class="jxr_comment">// we ignore.</em>
+<a name="224" href="#224">224</a> <strong class="jxr_keyword">if</strong> (LOG.isDebugEnabled()) {
+<a name="225" href="#225">225</a> LOG.debug(<span class="jxr_string">"offsetPD - 20="</span> + (offsetPD - 20)
+<a name="226" href="#226">226</a> + <span class="jxr_string">" recordsize="</span> + recordSize);
+<a name="227" href="#227">227</a> }
+<a name="228" href="#228">228</a> } <strong class="jxr_keyword">else</strong> {
+<a name="229" href="#229">229</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">int</strong> startPos = i + 8; startPos < offsetPD - 20
+<a name="230" href="#230">230</a> && startPos < recordSize; startPos++) { <em class="jxr_comment">// &&</em>
+<a name="231" href="#231">231</a> <em class="jxr_comment">// startPos</em>
+<a name="232" href="#232">232</a> <em class="jxr_comment">// <</em>
+<a name="233" href="#233">233</a> <em class="jxr_comment">// recordSize??</em>
+<a name="234" href="#234">234</a> <strong class="jxr_keyword">try</strong> {
+<a name="235" href="#235">235</a>
+<a name="236" href="#236">236</a> <em class="jxr_comment">// Record info</em>
+<a name="237" href="#237">237</a> <em class="jxr_comment">// final long nrinfo =</em>
+<a name="238" href="#238">238</a> <em class="jxr_comment">// LittleEndian.getUShort(pptdata, (int) j);</em>
+<a name="239" href="#239">239</a>
+<a name="240" href="#240">240</a> <em class="jxr_comment">// Record Type</em>
+<a name="241" href="#241">241</a> <strong class="jxr_keyword">final</strong> <strong class="jxr_keyword">long</strong> ntype = LittleEndian.getUShort(
+<a name="242" href="#242">242</a> pptdata, startPos + 2);
+<a name="243" href="#243">243</a>
+<a name="244" href="#244">244</a> <em class="jxr_comment">// Record size</em>
+<a name="245" href="#245">245</a> <em class="jxr_comment">// Note that the size doesn't include the 8 byte</em>
+<a name="246" href="#246">246</a> <em class="jxr_comment">// atom header</em>
+<a name="247" href="#247">247</a> <strong class="jxr_keyword">final</strong> <strong class="jxr_keyword">long</strong> nsize = LittleEndian.getUInt(
+<a name="248" href="#248">248</a> pptdata, startPos + 4);
+<a name="249" href="#249">249</a>
+<a name="250" href="#250">250</a> <strong class="jxr_keyword">if</strong> (ntype == PPTConstants.PPT_ATOM_DRAWINGGROUP) {
+<a name="251" href="#251">251</a> <em class="jxr_comment">/*</em>
+<a name="252" href="#252">252</a> <em class="jxr_comment"> * Break the loop if next GroupID found</em>
+<a name="253" href="#253">253</a> <em class="jxr_comment"> */</em>
+<a name="254" href="#254">254</a> i = startPos - 1;
+<a name="255" href="#255">255</a> <strong class="jxr_keyword">break</strong>;
+<a name="256" href="#256">256</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (ntype == PPTConstants.PPT_ATOM_TEXTBYTE) {
+<a name="257" href="#257">257</a> <em class="jxr_comment">// TextByteAtom record</em>
+<a name="258" href="#258">258</a> outStream = <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/parser/microsoft/FilteredStringWriter.html">FilteredStringWriter</a>();
+<a name="259" href="#259">259</a> <strong class="jxr_keyword">long</strong> ii = 0;
+<a name="260" href="#260">260</a> <strong class="jxr_keyword">for</strong> (ii = startPos + 6; ii <= startPos + 6
+<a name="261" href="#261">261</a> + nsize; ii++) {
+<a name="262" href="#262">262</a> <em class="jxr_comment">// For loop to changed to a function</em>
+<a name="263" href="#263">263</a> <em class="jxr_comment">// if ((ii + 2) >= pptdata.length)</em>
+<a name="264" href="#264">264</a> <em class="jxr_comment">// break; // FIXME</em>
+<a name="265" href="#265">265</a> outStream
+<a name="266" href="#266">266</a> .write((<strong class="jxr_keyword">char</strong>) (pptdata[(<strong class="jxr_keyword">int</strong>) ii + 2]));
+<a name="267" href="#267">267</a> }
+<a name="268" href="#268">268</a>
+<a name="269" href="#269">269</a> <em class="jxr_comment">// Setting the identified text for Current</em>
+<a name="270" href="#270">270</a> <em class="jxr_comment">// groupID</em>
+<a name="271" href="#271">271</a> textBox.setContent(textBox.getContent()
+<a name="272" href="#272">272</a> + outStream.toString());
+<a name="273" href="#273">273</a>
+<a name="274" href="#274">274</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (ntype == PPTConstants.PPT_ATOM_TEXTCHAR) {
+<a name="275" href="#275">275</a> <em class="jxr_comment">// TextCharAtom record</em>
+<a name="276" href="#276">276</a>
+<a name="277" href="#277">277</a> <strong class="jxr_keyword">final</strong> String strTempContent = <strong class="jxr_keyword">new</strong> String(
+<a name="278" href="#278">278</a> pptdata, startPos + 6,
+<a name="279" href="#279">279</a> (<strong class="jxr_keyword">int</strong>) (nsize) + 2);
+<a name="280" href="#280">280</a> <strong class="jxr_keyword">final</strong> byte bytes[] = strTempContent
+<a name="281" href="#281">281</a> .getBytes();
+<a name="282" href="#282">282</a> <strong class="jxr_keyword">if</strong> (<strong class="jxr_keyword">true</strong>) {
+<a name="283" href="#283">283</a> outStream = <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/parser/microsoft/FilteredStringWriter.html">FilteredStringWriter</a>();
+<a name="284" href="#284">284</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">int</strong> ii = 0; ii < bytes.length - 1; ii += 2) {
+<a name="285" href="#285">285</a> <em class="jxr_comment">// For loop to changed to a function</em>
+<a name="286" href="#286">286</a> outStream
+<a name="287" href="#287">287</a> .write((<strong class="jxr_keyword">char</strong>) (pptdata[ii + 2]));
+<a name="288" href="#288">288</a> }
+<a name="289" href="#289">289</a> textBox.setContent(textBox.getContent()
+<a name="290" href="#290">290</a> + outStream.toString());
+<a name="291" href="#291">291</a> } <strong class="jxr_keyword">else</strong> {
+<a name="292" href="#292">292</a> <em class="jxr_comment">// this version is used within POI</em>
+<a name="293" href="#293">293</a> String text = StringUtil
+<a name="294" href="#294">294</a> .getFromCompressedUnicode(
+<a name="295" href="#295">295</a> bytes, 0, bytes.length);
+<a name="296" href="#296">296</a> textBox.setContent(textBox.getContent()
+<a name="297" href="#297">297</a> + text);
+<a name="298" href="#298">298</a> }
+<a name="299" href="#299">299</a>
+<a name="300" href="#300">300</a> } <strong class="jxr_keyword">else</strong> {
+<a name="301" href="#301">301</a> <em class="jxr_comment">// ignored</em>
+<a name="302" href="#302">302</a> <em class="jxr_comment">// if (LOG.isTraceEnabled()) {</em>
+<a name="303" href="#303">303</a> <em class="jxr_comment">// LOG.trace("Ignored atom type: " + type);</em>
+<a name="304" href="#304">304</a> <em class="jxr_comment">// }</em>
+<a name="305" href="#305">305</a> }
+<a name="306" href="#306">306</a> } <strong class="jxr_keyword">catch</strong> (Throwable e) {
+<a name="307" href="#307">307</a>
+<a name="308" href="#308">308</a> LOG.error(<span class="jxr_string">"extractTextBoxes"</span>, e);
+<a name="309" href="#309">309</a>
+<a name="310" href="#310">310</a> <strong class="jxr_keyword">break</strong>;
+<a name="311" href="#311">311</a> }
+<a name="312" href="#312">312</a> }
+<a name="313" href="#313">313</a> }
+<a name="314" href="#314">314</a> } <strong class="jxr_keyword">else</strong> {
+<a name="315" href="#315">315</a> <em class="jxr_comment">// Record type is ignored</em>
+<a name="316" href="#316">316</a> <em class="jxr_comment">// if (LOG.isTraceEnabled()) {</em>
+<a name="317" href="#317">317</a> <em class="jxr_comment">// LOG.trace("Ignored record type: " + type);</em>
+<a name="318" href="#318">318</a> <em class="jxr_comment">// }</em>
+<a name="319" href="#319">319</a> }
+<a name="320" href="#320">320</a> } <strong class="jxr_keyword">catch</strong> (Throwable ee) {
+<a name="321" href="#321">321</a>
+<a name="322" href="#322">322</a> LOG.error(<span class="jxr_string">"extractClientTextBoxes"</span>, ee);
+<a name="323" href="#323">323</a>
+<a name="324" href="#324">324</a> <strong class="jxr_keyword">break</strong>;
+<a name="325" href="#325">325</a> }
+<a name="326" href="#326">326</a> }
+<a name="327" href="#327">327</a> <strong class="jxr_keyword">return</strong> containerTextBox;
+<a name="328" href="#328">328</a> }
+<a name="329" href="#329">329</a>
+<a name="330" href="#330">330</a> <em class="jxr_javadoccomment">/**</em>
+<a name="331" href="#331">331</a> <em class="jxr_javadoccomment"> * Returns the Powerpoint <code>Slide</code> s of document as vector.</em>
+<a name="332" href="#332">332</a> <em class="jxr_javadoccomment"> * </em>
+<a name="333" href="#333">333</a> <em class="jxr_javadoccomment"> * @param offset</em>
+<a name="334" href="#334">334</a> <em class="jxr_javadoccomment"> * @param pptdata</em>
+<a name="335" href="#335">335</a> <em class="jxr_javadoccomment"> * @param offsetPD</em>
+<a name="336" href="#336">336</a> <em class="jxr_javadoccomment"> * @return Vector of the powerpoint slides. Contains</em>
+<a name="337" href="#337">337</a> <em class="jxr_javadoccomment"> * <code>{@link Slide Slide}</code></em>
+<a name="338" href="#338">338</a> <em class="jxr_javadoccomment"> * @see Slide</em>
+<a name="339" href="#339">339</a> <em class="jxr_javadoccomment"> */</em>
+<a name="340" href="#340">340</a> <strong class="jxr_keyword">protected</strong> List <em class="jxr_comment">/*<em class="jxr_comment"> <Slide> */</em>extractSlides(<strong class="jxr_keyword">final</strong> <strong class="jxr_keyword">long</strong> offset,</em>
+<a name="341" href="#341">341</a> <strong class="jxr_keyword">final</strong> byte[] pptdata, <strong class="jxr_keyword">final</strong> <strong class="jxr_keyword">long</strong> offsetPD) {
+<a name="342" href="#342">342</a>
+<a name="343" href="#343">343</a> <strong class="jxr_keyword">int</strong> sNum = 0;
+<a name="344" href="#344">344</a>
+<a name="345" href="#345">345</a> <em class="jxr_comment">// List of all slides found</em>
+<a name="346" href="#346">346</a> <strong class="jxr_keyword">final</strong> List<em class="jxr_comment">/*<em class="jxr_comment"> <Slide> */</em>slides = <strong class="jxr_keyword">new</strong> Vector/* <Slide> */();</em>
+<a name="347" href="#347">347</a>
+<a name="348" href="#348">348</a> <em class="jxr_comment">// current slide data</em>
+<a name="349" href="#349">349</a> <a href="../../../../../org/apache/tika/parser/microsoft/Slide.html">Slide</a> currentSlide = <strong class="jxr_keyword">null</strong>;
+<a name="350" href="#350">350</a>
+<a name="351" href="#351">351</a> <em class="jxr_comment">// To store data found in TextCharAtoms and TextBytesAtoms</em>
+<a name="352" href="#352">352</a> <a href="../../../../../org/apache/tika/parser/microsoft/FilteredStringWriter.html">FilteredStringWriter</a> outStream;
+<a name="353" href="#353">353</a>
+<a name="354" href="#354">354</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">long</strong> i = offset; i < pptdata.length - 20; i++) {
+<a name="355" href="#355">355</a>
+<a name="356" href="#356">356</a> <strong class="jxr_keyword">final</strong> <strong class="jxr_keyword">long</strong> recordInfo = LittleEndian.getUShort(pptdata, (<strong class="jxr_keyword">int</strong>) i);
+<a name="357" href="#357">357</a> <strong class="jxr_keyword">final</strong> <strong class="jxr_keyword">long</strong> atomType = LittleEndian.getUShort(pptdata, (<strong class="jxr_keyword">int</strong>) i + 2);
+<a name="358" href="#358">358</a> <strong class="jxr_keyword">final</strong> <strong class="jxr_keyword">long</strong> atomSize = LittleEndian.getUInt(pptdata, (<strong class="jxr_keyword">int</strong>) i + 4);
+<a name="359" href="#359">359</a>
+<a name="360" href="#360">360</a> <strong class="jxr_keyword">if</strong> (atomType == PPTConstants.PPT_ATOM_TEXTBYTE) {
+<a name="361" href="#361">361</a> <em class="jxr_comment">/*</em>
+<a name="362" href="#362">362</a> <em class="jxr_comment"> * TextByteAtom record</em>
+<a name="363" href="#363">363</a> <em class="jxr_comment"> */</em>
+<a name="364" href="#364">364</a> outStream = <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/parser/microsoft/FilteredStringWriter.html">FilteredStringWriter</a>();
+<a name="365" href="#365">365</a>
+<a name="366" href="#366">366</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">long</strong> ii = i + 6; (ii <= i + 6 + atomSize)
+<a name="367" href="#367">367</a> && (ii + 2 < pptdata.length); ii++) {
+<a name="368" href="#368">368</a> <strong class="jxr_keyword">try</strong> {
+<a name="369" href="#369">369</a> <em class="jxr_comment">// if(ii+2 >= pptdata.length) break; //FIXME</em>
+<a name="370" href="#370">370</a> byte value = pptdata[(<strong class="jxr_keyword">int</strong>) ii + 2];
+<a name="371" href="#371">371</a> outStream.write(value);
+<a name="372" href="#372">372</a> } <strong class="jxr_keyword">catch</strong> (ArrayIndexOutOfBoundsException ex) {
+<a name="373" href="#373">373</a> <strong class="jxr_keyword">if</strong> (LOG.isTraceEnabled()) {
+<a name="374" href="#374">374</a> LOG.trace(<span class="jxr_string">"size="</span> + pptdata.length);
+<a name="375" href="#375">375</a> }
+<a name="376" href="#376">376</a>
+<a name="377" href="#377">377</a> LOG.error(<span class="jxr_string">"extractSlides"</span>, ex);
+<a name="378" href="#378">378</a>
+<a name="379" href="#379">379</a> }
+<a name="380" href="#380">380</a> }
+<a name="381" href="#381">381</a>
+<a name="382" href="#382">382</a> <em class="jxr_comment">// Setting the identified text for Current Slide</em>
+<a name="383" href="#383">383</a> <strong class="jxr_keyword">if</strong> (currentSlide != <strong class="jxr_keyword">null</strong>) {
+<a name="384" href="#384">384</a> currentSlide.addContent(outStream.toString());
+<a name="385" href="#385">385</a> }
+<a name="386" href="#386">386</a>
+<a name="387" href="#387">387</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (atomType == PPTConstants.PPT_ATOM_TEXTCHAR) {
+<a name="388" href="#388">388</a> <em class="jxr_comment">/*</em>
+<a name="389" href="#389">389</a> <em class="jxr_comment"> * TextCharAtom record</em>
+<a name="390" href="#390">390</a> <em class="jxr_comment"> */</em>
+<a name="391" href="#391">391</a> outStream = <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/parser/microsoft/FilteredStringWriter.html">FilteredStringWriter</a>();
+<a name="392" href="#392">392</a> <strong class="jxr_keyword">final</strong> String strTempContent = <strong class="jxr_keyword">new</strong> String(pptdata, (<strong class="jxr_keyword">int</strong>) i + 6,
+<a name="393" href="#393">393</a> (<strong class="jxr_keyword">int</strong>) (atomSize) + 2);
+<a name="394" href="#394">394</a> <strong class="jxr_keyword">final</strong> byte bytes[] = strTempContent.getBytes();
+<a name="395" href="#395">395</a>
+<a name="396" href="#396">396</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">int</strong> ii = 0; ii < bytes.length - 1; ii += 2) {
+<a name="397" href="#397">397</a> outStream.write(Utils.getUnicodeCharacter(bytes, ii));
+<a name="398" href="#398">398</a> }
+<a name="399" href="#399">399</a>
+<a name="400" href="#400">400</a> <em class="jxr_comment">// Setting the identified text for Current Slide</em>
+<a name="401" href="#401">401</a> <strong class="jxr_keyword">if</strong> (currentSlide != <strong class="jxr_keyword">null</strong>) {
+<a name="402" href="#402">402</a> currentSlide.addContent(outStream.toString());
+<a name="403" href="#403">403</a> }
+<a name="404" href="#404">404</a>
+<a name="405" href="#405">405</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (atomType == PPTConstants.PPT_ATOM_SLIDEPERSISTANT) {
+<a name="406" href="#406">406</a> <em class="jxr_comment">/*</em>
+<a name="407" href="#407">407</a> <em class="jxr_comment"> * SlidePresistAtom Record</em>
+<a name="408" href="#408">408</a> <em class="jxr_comment"> */</em>
+<a name="409" href="#409">409</a> <strong class="jxr_keyword">if</strong> (sNum != 0) {
+<a name="410" href="#410">410</a> outStream = <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/parser/microsoft/FilteredStringWriter.html">FilteredStringWriter</a>();
+<a name="411" href="#411">411</a>
+<a name="412" href="#412">412</a> <strong class="jxr_keyword">final</strong> <strong class="jxr_keyword">long</strong> slideID = LittleEndian.getUInt(pptdata,
+<a name="413" href="#413">413</a> (<strong class="jxr_keyword">int</strong>) i + 20);
+<a name="414" href="#414">414</a>
+<a name="415" href="#415">415</a> currentSlide = <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/parser/microsoft/Slide.html">Slide</a>(slideID);
+<a name="416" href="#416">416</a> <em class="jxr_comment">// currentSlide.addContent(outStream.toString());</em>
+<a name="417" href="#417">417</a> slides.add(currentSlide);
+<a name="418" href="#418">418</a> }
+<a name="419" href="#419">419</a> sNum++;
+<a name="420" href="#420">420</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (atomType == PPTConstants.PPT_ATOM_DRAWINGGROUP) {
+<a name="421" href="#421">421</a> <em class="jxr_comment">/*</em>
+<a name="422" href="#422">422</a> <em class="jxr_comment"> * Diagram records are ignored</em>
+<a name="423" href="#423">423</a> <em class="jxr_comment"> */</em>
+<a name="424" href="#424">424</a> <strong class="jxr_keyword">if</strong> (LOG.isTraceEnabled()) {
+<a name="425" href="#425">425</a> LOG.trace(<span class="jxr_string">"Drawing Groups are ignored."</span>);
+<a name="426" href="#426">426</a> }
+<a name="427" href="#427">427</a> <strong class="jxr_keyword">break</strong>;
+<a name="428" href="#428">428</a> } <strong class="jxr_keyword">else</strong> {
+<a name="429" href="#429">429</a> <em class="jxr_comment">// ignored</em>
+<a name="430" href="#430">430</a> <em class="jxr_comment">// if (LOG.isTraceEnabled()) {</em>
+<a name="431" href="#431">431</a> <em class="jxr_comment">// LOG.trace("Unhandled atomType: " + atomType);</em>
+<a name="432" href="#432">432</a> <em class="jxr_comment">// }</em>
+<a name="433" href="#433">433</a> }
+<a name="434" href="#434">434</a> }
+<a name="435" href="#435">435</a>
+<a name="436" href="#436">436</a> <strong class="jxr_keyword">return</strong> slides;
+<a name="437" href="#437">437</a> }
+<a name="438" href="#438">438</a>
+<a name="439" href="#439">439</a> }
+</pre>
+<hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body>
+</html>
+
Added: 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=596146&view=auto
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/microsoft/PowerPointParser.html (added)
+++ incubator/tika/site/xref/org/apache/tika/parser/microsoft/PowerPointParser.html Sun Nov 18 14:20:54 2007
@@ -0,0 +1,65 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+<head>
+<meta http-equiv="content-type" content="text/html; charset=ISO-8859-1" />
+<title>PowerPointParser xref</title>
+<link type="text/css" rel="stylesheet" href="../../../../../stylesheet.css" />
+</head>
+<body>
+<div id="overview"><a href="../../../../../../apidocs/org/apache/tika/parser/microsoft/PowerPointParser.html">View Javadoc</a></div><pre>
+
+<a name="1" href="#1">1</a> <em class="jxr_javadoccomment">/**</em>
+<a name="2" href="#2">2</a> <em class="jxr_javadoccomment"> * Licensed to the Apache Software Foundation (ASF) under one or more</em>
+<a name="3" href="#3">3</a> <em class="jxr_javadoccomment"> * contributor license agreements. See the NOTICE file distributed with</em>
+<a name="4" href="#4">4</a> <em class="jxr_javadoccomment"> * this work for additional information regarding copyright ownership.</em>
+<a name="5" href="#5">5</a> <em class="jxr_javadoccomment"> * The ASF licenses this file to You under the Apache License, Version 2.0</em>
+<a name="6" href="#6">6</a> <em class="jxr_javadoccomment"> * (the "License"); you may not use this file except in compliance with</em>
+<a name="7" href="#7">7</a> <em class="jxr_javadoccomment"> * the License. You may obtain a copy of the License at</em>
+<a name="8" href="#8">8</a> <em class="jxr_javadoccomment"> *</em>
+<a name="9" href="#9">9</a> <em class="jxr_javadoccomment"> * <a href="http://www.apache.org/licenses/LICENSE-2.0" target="alexandria_uri">http://www.apache.org/licenses/LICENSE-2.0</a></em>
+<a name="10" href="#10">10</a> <em class="jxr_javadoccomment"> *</em>
+<a name="11" href="#11">11</a> <em class="jxr_javadoccomment"> * Unless required by applicable law or agreed to in writing, software</em>
+<a name="12" href="#12">12</a> <em class="jxr_javadoccomment"> * distributed under the License is distributed on an "AS IS" BASIS,</em>
+<a name="13" href="#13">13</a> <em class="jxr_javadoccomment"> * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</em>
+<a name="14" href="#14">14</a> <em class="jxr_javadoccomment"> * See the License for the specific language governing permissions and</em>
+<a name="15" href="#15">15</a> <em class="jxr_javadoccomment"> * limitations under the License.</em>
+<a name="16" href="#16">16</a> <em class="jxr_javadoccomment"> */</em>
+<a name="17" href="#17">17</a> <strong class="jxr_keyword">package</strong> org.apache.tika.parser.microsoft;
+<a name="18" href="#18">18</a>
+<a name="19" href="#19">19</a> <strong class="jxr_keyword">import</strong> java.io.IOException;
+<a name="20" href="#20">20</a> <strong class="jxr_keyword">import</strong> java.io.InputStream;
+<a name="21" href="#21">21</a>
+<a name="22" href="#22">22</a> <strong class="jxr_keyword">import</strong> org.apache.poi.poifs.filesystem.POIFSFileSystem;
+<a name="23" href="#23">23</a>
+<a name="24" href="#24">24</a> <em class="jxr_javadoccomment">/**</em>
+<a name="25" href="#25">25</a> <em class="jxr_javadoccomment"> * Power point parser</em>
+<a name="26" href="#26">26</a> <em class="jxr_javadoccomment"> */</em>
+<a name="27" href="#27">27</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">class</strong> <a href="../../../../../org/apache/tika/parser/microsoft/PowerPointParser.html">PowerPointParser</a> <strong class="jxr_keyword">extends</strong> <a href="../../../../../org/apache/tika/parser/microsoft/OfficeParser.html">OfficeParser</a> {
+<a name="28" href="#28">28</a>
+<a name="29" href="#29">29</a> <em class="jxr_javadoccomment">/**</em>
+<a name="30" href="#30">30</a> <em class="jxr_javadoccomment"> * Name of a PowerPoint document within a POIFS file system</em>
+<a name="31" href="#31">31</a> <em class="jxr_javadoccomment"> */</em>
+<a name="32" href="#32">32</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">static</strong> <strong class="jxr_keyword">final</strong> String POWERPOINT = <span class="jxr_string">"PowerPoint Document"</span>;
+<a name="33" href="#33">33</a>
+<a name="34" href="#34">34</a> <strong class="jxr_keyword">protected</strong> String getContentType() {
+<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="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> }
+</pre>
+<hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body>
+</html>
+
Added: incubator/tika/site/xref/org/apache/tika/parser/microsoft/Slide.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/microsoft/Slide.html?rev=596146&view=auto
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/microsoft/Slide.html (added)
+++ incubator/tika/site/xref/org/apache/tika/parser/microsoft/Slide.html Sun Nov 18 14:20:54 2007
@@ -0,0 +1,86 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+<head>
+<meta http-equiv="content-type" content="text/html; charset=ISO-8859-1" />
+<title>Slide xref</title>
+<link type="text/css" rel="stylesheet" href="../../../../../stylesheet.css" />
+</head>
+<body>
+<div id="overview"><a href="../../../../../../apidocs/org/apache/tika/parser/microsoft/Slide.html">View Javadoc</a></div><pre>
+
+<a name="1" href="#1">1</a> <em class="jxr_javadoccomment">/**</em>
+<a name="2" href="#2">2</a> <em class="jxr_javadoccomment"> * Licensed to the Apache Software Foundation (ASF) under one or more</em>
+<a name="3" href="#3">3</a> <em class="jxr_javadoccomment"> * contributor license agreements. See the NOTICE file distributed with</em>
+<a name="4" href="#4">4</a> <em class="jxr_javadoccomment"> * this work for additional information regarding copyright ownership.</em>
+<a name="5" href="#5">5</a> <em class="jxr_javadoccomment"> * The ASF licenses this file to You under the Apache License, Version 2.0</em>
+<a name="6" href="#6">6</a> <em class="jxr_javadoccomment"> * (the "License"); you may not use this file except in compliance with</em>
+<a name="7" href="#7">7</a> <em class="jxr_javadoccomment"> * the License. You may obtain a copy of the License at</em>
+<a name="8" href="#8">8</a> <em class="jxr_javadoccomment"> *</em>
+<a name="9" href="#9">9</a> <em class="jxr_javadoccomment"> * <a href="http://www.apache.org/licenses/LICENSE-2.0" target="alexandria_uri">http://www.apache.org/licenses/LICENSE-2.0</a></em>
+<a name="10" href="#10">10</a> <em class="jxr_javadoccomment"> *</em>
+<a name="11" href="#11">11</a> <em class="jxr_javadoccomment"> * Unless required by applicable law or agreed to in writing, software</em>
+<a name="12" href="#12">12</a> <em class="jxr_javadoccomment"> * distributed under the License is distributed on an "AS IS" BASIS,</em>
+<a name="13" href="#13">13</a> <em class="jxr_javadoccomment"> * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</em>
+<a name="14" href="#14">14</a> <em class="jxr_javadoccomment"> * See the License for the specific language governing permissions and</em>
+<a name="15" href="#15">15</a> <em class="jxr_javadoccomment"> * limitations under the License.</em>
+<a name="16" href="#16">16</a> <em class="jxr_javadoccomment"> */</em>
+<a name="17" href="#17">17</a> <strong class="jxr_keyword">package</strong> org.apache.tika.parser.microsoft;
+<a name="18" href="#18">18</a>
+<a name="19" href="#19">19</a> <strong class="jxr_keyword">import</strong> java.util.List;
+<a name="20" href="#20">20</a> <strong class="jxr_keyword">import</strong> java.util.Vector;
+<a name="21" href="#21">21</a>
+<a name="22" href="#22">22</a> <em class="jxr_javadoccomment">/**</em>
+<a name="23" href="#23">23</a> <em class="jxr_javadoccomment"> * Package protected class for a MS Powerpoint slide.</em>
+<a name="24" href="#24">24</a> <em class="jxr_javadoccomment"> * </em>
+<a name="25" href="#25">25</a> <em class="jxr_javadoccomment"> * </em>
+<a name="26" href="#26">26</a> <em class="jxr_javadoccomment"> */</em>
+<a name="27" href="#27">27</a> <strong class="jxr_keyword">class</strong> <a href="../../../../../org/apache/tika/parser/microsoft/Slide.html">Slide</a> {
+<a name="28" href="#28">28</a>
+<a name="29" href="#29">29</a>
+<a name="30" href="#30">30</a> <em class="jxr_javadoccomment">/**</em><em class="jxr_javadoccomment"> Holds the <a href="../../../../../org/apache/tika/parser/microsoft/Slide.html">Slide</a> Number */</em>
+<a name="31" href="#31">31</a> <strong class="jxr_keyword">protected</strong> <strong class="jxr_keyword">transient</strong> <strong class="jxr_keyword">final</strong> <strong class="jxr_keyword">long</strong> slideNumber;
+<a name="32" href="#32">32</a>
+<a name="33" href="#33">33</a> <em class="jxr_javadoccomment">/**</em><em class="jxr_javadoccomment"> Holds the contents of the <a href="../../../../../org/apache/tika/parser/microsoft/Slide.html">Slide</a> */</em>
+<a name="34" href="#34">34</a> <strong class="jxr_keyword">protected</strong> <strong class="jxr_keyword">transient</strong> <strong class="jxr_keyword">final</strong> List<em class="jxr_comment">/*<em class="jxr_comment"> <String> */</em>contents;</em>
+<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"> * Initialise the Object for holding the contents of Power Point Slide</em>
+<a name="38" href="#38">38</a> <em class="jxr_javadoccomment"> * </em>
+<a name="39" href="#39">39</a> <em class="jxr_javadoccomment"> * @param number</em>
+<a name="40" href="#40">40</a> <em class="jxr_javadoccomment"> */</em>
+<a name="41" href="#41">41</a> <strong class="jxr_keyword">public</strong> <a href="../../../../../org/apache/tika/parser/microsoft/Slide.html">Slide</a>(<strong class="jxr_keyword">long</strong> number) {
+<a name="42" href="#42">42</a> <strong class="jxr_keyword">this</strong>.slideNumber = number;
+<a name="43" href="#43">43</a> <strong class="jxr_keyword">this</strong>.contents = <strong class="jxr_keyword">new</strong> Vector<em class="jxr_comment">/*<em class="jxr_comment"> <String> */</em>();</em>
+<a name="44" href="#44">44</a> }
+<a name="45" href="#45">45</a>
+<a name="46" href="#46">46</a> <em class="jxr_javadoccomment">/**</em>
+<a name="47" href="#47">47</a> <em class="jxr_javadoccomment"> * Add the Content of Slide to this Object</em>
+<a name="48" href="#48">48</a> <em class="jxr_javadoccomment"> * </em>
+<a name="49" href="#49">49</a> <em class="jxr_javadoccomment"> * @param content</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> addContent(String content) {
+<a name="52" href="#52">52</a> <strong class="jxr_keyword">this</strong>.contents.add(content);
+<a name="53" href="#53">53</a> }
+<a name="54" href="#54">54</a>
+<a name="55" href="#55">55</a> <em class="jxr_javadoccomment">/**</em>
+<a name="56" href="#56">56</a> <em class="jxr_javadoccomment"> * returns the contents of slide as a vector object</em>
+<a name="57" href="#57">57</a> <em class="jxr_javadoccomment"> * </em>
+<a name="58" href="#58">58</a> <em class="jxr_javadoccomment"> * @return Vector</em>
+<a name="59" href="#59">59</a> <em class="jxr_javadoccomment"> */</em>
+<a name="60" href="#60">60</a> <strong class="jxr_keyword">public</strong> List getContent() {
+<a name="61" href="#61">61</a> <strong class="jxr_keyword">return</strong> <strong class="jxr_keyword">this</strong>.contents;
+<a name="62" href="#62">62</a> }
+<a name="63" href="#63">63</a>
+<a name="64" href="#64">64</a> <em class="jxr_javadoccomment">/**</em>
+<a name="65" href="#65">65</a> <em class="jxr_javadoccomment"> * returns the slide value</em>
+<a name="66" href="#66">66</a> <em class="jxr_javadoccomment"> * </em>
+<a name="67" href="#67">67</a> <em class="jxr_javadoccomment"> * @return long</em>
+<a name="68" href="#68">68</a> <em class="jxr_javadoccomment"> */</em>
+<a name="69" href="#69">69</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">long</strong> getSlideNumber() {
+<a name="70" href="#70">70</a> <strong class="jxr_keyword">return</strong> <strong class="jxr_keyword">this</strong>.slideNumber;
+<a name="71" href="#71">71</a> }
+<a name="72" href="#72">72</a> }
+</pre>
+<hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body>
+</html>
+
Added: incubator/tika/site/xref/org/apache/tika/parser/microsoft/TextBox.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/microsoft/TextBox.html?rev=596146&view=auto
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/microsoft/TextBox.html (added)
+++ incubator/tika/site/xref/org/apache/tika/parser/microsoft/TextBox.html Sun Nov 18 14:20:54 2007
@@ -0,0 +1,101 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+<head>
+<meta http-equiv="content-type" content="text/html; charset=ISO-8859-1" />
+<title>TextBox xref</title>
+<link type="text/css" rel="stylesheet" href="../../../../../stylesheet.css" />
+</head>
+<body>
+<div id="overview"><a href="../../../../../../apidocs/org/apache/tika/parser/microsoft/TextBox.html">View Javadoc</a></div><pre>
+
+<a name="1" href="#1">1</a> <em class="jxr_javadoccomment">/**</em>
+<a name="2" href="#2">2</a> <em class="jxr_javadoccomment"> * Licensed to the Apache Software Foundation (ASF) under one or more</em>
+<a name="3" href="#3">3</a> <em class="jxr_javadoccomment"> * contributor license agreements. See the NOTICE file distributed with</em>
+<a name="4" href="#4">4</a> <em class="jxr_javadoccomment"> * this work for additional information regarding copyright ownership.</em>
+<a name="5" href="#5">5</a> <em class="jxr_javadoccomment"> * The ASF licenses this file to You under the Apache License, Version 2.0</em>
+<a name="6" href="#6">6</a> <em class="jxr_javadoccomment"> * (the "License"); you may not use this file except in compliance with</em>
+<a name="7" href="#7">7</a> <em class="jxr_javadoccomment"> * the License. You may obtain a copy of the License at</em>
+<a name="8" href="#8">8</a> <em class="jxr_javadoccomment"> *</em>
+<a name="9" href="#9">9</a> <em class="jxr_javadoccomment"> * <a href="http://www.apache.org/licenses/LICENSE-2.0" target="alexandria_uri">http://www.apache.org/licenses/LICENSE-2.0</a></em>
+<a name="10" href="#10">10</a> <em class="jxr_javadoccomment"> *</em>
+<a name="11" href="#11">11</a> <em class="jxr_javadoccomment"> * Unless required by applicable law or agreed to in writing, software</em>
+<a name="12" href="#12">12</a> <em class="jxr_javadoccomment"> * distributed under the License is distributed on an "AS IS" BASIS,</em>
+<a name="13" href="#13">13</a> <em class="jxr_javadoccomment"> * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</em>
+<a name="14" href="#14">14</a> <em class="jxr_javadoccomment"> * See the License for the specific language governing permissions and</em>
+<a name="15" href="#15">15</a> <em class="jxr_javadoccomment"> * limitations under the License.</em>
+<a name="16" href="#16">16</a> <em class="jxr_javadoccomment"> */</em>
+<a name="17" href="#17">17</a> <strong class="jxr_keyword">package</strong> org.apache.tika.parser.microsoft;
+<a name="18" href="#18">18</a>
+<a name="19" href="#19">19</a> <em class="jxr_javadoccomment">/**</em>
+<a name="20" href="#20">20</a> <em class="jxr_javadoccomment"> * Package protected class for the MS Powerpoint TextBox content</em>
+<a name="21" href="#21">21</a> <em class="jxr_javadoccomment"> * </em>
+<a name="22" href="#22">22</a> <em class="jxr_javadoccomment"> * </em>
+<a name="23" href="#23">23</a> <em class="jxr_javadoccomment"> */</em>
+<a name="24" href="#24">24</a> <strong class="jxr_keyword">class</strong> <a href="../../../../../org/apache/tika/parser/microsoft/TextBox.html">TextBox</a> {
+<a name="25" href="#25">25</a>
+<a name="26" href="#26">26</a> <em class="jxr_javadoccomment">/**</em>
+<a name="27" href="#27">27</a> <em class="jxr_javadoccomment"> * Current id of a text box</em>
+<a name="28" href="#28">28</a> <em class="jxr_javadoccomment"> */</em>
+<a name="29" href="#29">29</a> <strong class="jxr_keyword">protected</strong> <strong class="jxr_keyword">transient</strong> <strong class="jxr_keyword">final</strong> <strong class="jxr_keyword">long</strong> currentID;
+<a name="30" href="#30">30</a>
+<a name="31" href="#31">31</a> <em class="jxr_javadoccomment">/**</em>
+<a name="32" href="#32">32</a> <em class="jxr_javadoccomment"> * Content of text box</em>
+<a name="33" href="#33">33</a> <em class="jxr_javadoccomment"> */</em>
+<a name="34" href="#34">34</a> <strong class="jxr_keyword">protected</strong> String content;
+<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"> * Instantiates the text box object</em>
+<a name="38" href="#38">38</a> <em class="jxr_javadoccomment"> * </em>
+<a name="39" href="#39">39</a> <em class="jxr_javadoccomment"> * @param textBoxId</em>
+<a name="40" href="#40">40</a> <em class="jxr_javadoccomment"> * id of text box</em>
+<a name="41" href="#41">41</a> <em class="jxr_javadoccomment"> */</em>
+<a name="42" href="#42">42</a> <strong class="jxr_keyword">public</strong> <a href="../../../../../org/apache/tika/parser/microsoft/TextBox.html">TextBox</a>(<strong class="jxr_keyword">final</strong> <strong class="jxr_keyword">long</strong> textBoxId) {
+<a name="43" href="#43">43</a> <strong class="jxr_keyword">this</strong>.currentID = textBoxId;
+<a name="44" href="#44">44</a> <strong class="jxr_keyword">this</strong>.content = <span class="jxr_string">""</span>;
+<a name="45" href="#45">45</a> }
+<a name="46" href="#46">46</a>
+<a name="47" href="#47">47</a> <em class="jxr_javadoccomment">/**</em>
+<a name="48" href="#48">48</a> <em class="jxr_javadoccomment"> * Instantiates the text box object</em>
+<a name="49" href="#49">49</a> <em class="jxr_javadoccomment"> * </em>
+<a name="50" href="#50">50</a> <em class="jxr_javadoccomment"> * @param textBoxId</em>
+<a name="51" href="#51">51</a> <em class="jxr_javadoccomment"> * id of text box</em>
+<a name="52" href="#52">52</a> <em class="jxr_javadoccomment"> * @param content</em>
+<a name="53" href="#53">53</a> <em class="jxr_javadoccomment"> * content of text box</em>
+<a name="54" href="#54">54</a> <em class="jxr_javadoccomment"> */</em>
+<a name="55" href="#55">55</a> <strong class="jxr_keyword">public</strong> <a href="../../../../../org/apache/tika/parser/microsoft/TextBox.html">TextBox</a>(<strong class="jxr_keyword">final</strong> <strong class="jxr_keyword">long</strong> textBoxId, <strong class="jxr_keyword">final</strong> String content) {
+<a name="56" href="#56">56</a> <strong class="jxr_keyword">this</strong>.currentID = textBoxId;
+<a name="57" href="#57">57</a> <strong class="jxr_keyword">this</strong>.content = content;
+<a name="58" href="#58">58</a> }
+<a name="59" href="#59">59</a>
+<a name="60" href="#60">60</a> <em class="jxr_javadoccomment">/**</em>
+<a name="61" href="#61">61</a> <em class="jxr_javadoccomment"> * Sets the content of the text box</em>
+<a name="62" href="#62">62</a> <em class="jxr_javadoccomment"> * </em>
+<a name="63" href="#63">63</a> <em class="jxr_javadoccomment"> * @param content</em>
+<a name="64" href="#64">64</a> <em class="jxr_javadoccomment"> * content of text Box</em>
+<a name="65" href="#65">65</a> <em class="jxr_javadoccomment"> */</em>
+<a name="66" href="#66">66</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">void</strong> setContent(<strong class="jxr_keyword">final</strong> String content) {
+<a name="67" href="#67">67</a> <strong class="jxr_keyword">this</strong>.content = content;
+<a name="68" href="#68">68</a> }
+<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"> * Returns the content of the text box</em>
+<a name="72" href="#72">72</a> <em class="jxr_javadoccomment"> * </em>
+<a name="73" href="#73">73</a> <em class="jxr_javadoccomment"> * @return content of text box</em>
+<a name="74" href="#74">74</a> <em class="jxr_javadoccomment"> */</em>
+<a name="75" href="#75">75</a> <strong class="jxr_keyword">public</strong> String getContent() {
+<a name="76" href="#76">76</a> <strong class="jxr_keyword">return</strong> <strong class="jxr_keyword">this</strong>.content;
+<a name="77" href="#77">77</a> }
+<a name="78" href="#78">78</a>
+<a name="79" href="#79">79</a> <em class="jxr_javadoccomment">/**</em>
+<a name="80" href="#80">80</a> <em class="jxr_javadoccomment"> * Returns the current text box id</em>
+<a name="81" href="#81">81</a> <em class="jxr_javadoccomment"> * </em>
+<a name="82" href="#82">82</a> <em class="jxr_javadoccomment"> * @return long</em>
+<a name="83" href="#83">83</a> <em class="jxr_javadoccomment"> */</em>
+<a name="84" href="#84">84</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">long</strong> getCurrentId() {
+<a name="85" href="#85">85</a> <strong class="jxr_keyword">return</strong> <strong class="jxr_keyword">this</strong>.currentID;
+<a name="86" href="#86">86</a> }
+<a name="87" href="#87">87</a> }
+</pre>
+<hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body>
+</html>
+
Added: incubator/tika/site/xref/org/apache/tika/parser/microsoft/Word6CHPBinTable.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/microsoft/Word6CHPBinTable.html?rev=596146&view=auto
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/microsoft/Word6CHPBinTable.html (added)
+++ incubator/tika/site/xref/org/apache/tika/parser/microsoft/Word6CHPBinTable.html Sun Nov 18 14:20:54 2007
@@ -0,0 +1,91 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+<head>
+<meta http-equiv="content-type" content="text/html; charset=ISO-8859-1" />
+<title>Word6CHPBinTable xref</title>
+<link type="text/css" rel="stylesheet" href="../../../../../stylesheet.css" />
+</head>
+<body>
+<div id="overview"><a href="../../../../../../apidocs/org/apache/tika/parser/microsoft/Word6CHPBinTable.html">View Javadoc</a></div><pre>
+
+<a name="1" href="#1">1</a> <em class="jxr_comment">/*<em class="jxr_comment"> Copyright 2004 Ryan Ackley</em></em>
+<a name="2" href="#2">2</a> <em class="jxr_comment"> *</em>
+<a name="3" href="#3">3</a> <em class="jxr_comment"> * Licensed under the Apache License, Version 2.0 (the "License");</em>
+<a name="4" href="#4">4</a> <em class="jxr_comment"> * you may not use this file except in compliance with the License.</em>
+<a name="5" href="#5">5</a> <em class="jxr_comment"> * You may obtain a copy of the License at</em>
+<a name="6" href="#6">6</a> <em class="jxr_comment"> *</em>
+<a name="7" href="#7">7</a> <em class="jxr_comment"> * <a href="http://www.apache.org/licenses/LICENSE-2.0" target="alexandria_uri">http://www.apache.org/licenses/LICENSE-2.0</a></em>
+<a name="8" href="#8">8</a> <em class="jxr_comment"> *</em>
+<a name="9" href="#9">9</a> <em class="jxr_comment"> * Unless required by applicable law or agreed to in writing, software</em>
+<a name="10" href="#10">10</a> <em class="jxr_comment"> * distributed under the License is distributed on an "AS IS" BASIS,</em>
+<a name="11" href="#11">11</a> <em class="jxr_comment"> * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</em>
+<a name="12" href="#12">12</a> <em class="jxr_comment"> * See the License for the specific language governing permissions and</em>
+<a name="13" href="#13">13</a> <em class="jxr_comment"> * limitations under the License.</em>
+<a name="14" href="#14">14</a> <em class="jxr_comment"> */</em>
+<a name="15" href="#15">15</a>
+<a name="16" href="#16">16</a> <strong class="jxr_keyword">package</strong> org.apache.tika.parser.microsoft;
+<a name="17" href="#17">17</a>
+<a name="18" href="#18">18</a> <strong class="jxr_keyword">import</strong> java.util.List;
+<a name="19" href="#19">19</a> <strong class="jxr_keyword">import</strong> java.util.ArrayList;
+<a name="20" href="#20">20</a> <strong class="jxr_keyword">import</strong> java.io.OutputStream;
+<a name="21" href="#21">21</a> <strong class="jxr_keyword">import</strong> java.io.IOException;
+<a name="22" href="#22">22</a>
+<a name="23" href="#23">23</a> <strong class="jxr_keyword">import</strong> org.apache.poi.poifs.common.POIFSConstants;
+<a name="24" href="#24">24</a> <strong class="jxr_keyword">import</strong> org.apache.poi.util.LittleEndian;
+<a name="25" href="#25">25</a> <strong class="jxr_keyword">import</strong> org.apache.poi.hwpf.model.io.*;
+<a name="26" href="#26">26</a> <strong class="jxr_keyword">import</strong> org.apache.poi.hwpf.model.*;
+<a name="27" href="#27">27</a>
+<a name="28" href="#28">28</a> <em class="jxr_javadoccomment">/**</em>
+<a name="29" href="#29">29</a> <em class="jxr_javadoccomment"> * This class holds all of the character formatting properties from a Word</em>
+<a name="30" href="#30">30</a> <em class="jxr_javadoccomment"> * 6.0/95 document.</em>
+<a name="31" href="#31">31</a> <em class="jxr_javadoccomment"> *</em>
+<a name="32" href="#32">32</a> <em class="jxr_javadoccomment"> *</em>
+<a name="33" href="#33">33</a> <em class="jxr_javadoccomment"> */</em>
+<a name="34" href="#34">34</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">class</strong> Word6CHPBinTable
+<a name="35" href="#35">35</a> {
+<a name="36" href="#36">36</a> <em class="jxr_javadoccomment">/**</em><em class="jxr_javadoccomment"> List of character properties.*/</em>
+<a name="37" href="#37">37</a> ArrayList _textRuns = <strong class="jxr_keyword">new</strong> ArrayList();
+<a name="38" href="#38">38</a>
+<a name="39" href="#39">39</a> <em class="jxr_javadoccomment">/**</em>
+<a name="40" href="#40">40</a> <em class="jxr_javadoccomment"> * Constructor used to read a binTable in from a Word document.</em>
+<a name="41" href="#41">41</a> <em class="jxr_javadoccomment"> *</em>
+<a name="42" href="#42">42</a> <em class="jxr_javadoccomment"> * @param documentStream The POIFS "WordDocument" stream from a Word document</em>
+<a name="43" href="#43">43</a> <em class="jxr_javadoccomment"> * @param offset The offset of the Chp bin table in the main stream.</em>
+<a name="44" href="#44">44</a> <em class="jxr_javadoccomment"> * @param size The size of the Chp bin table in the main stream.</em>
+<a name="45" href="#45">45</a> <em class="jxr_javadoccomment"> * @param fcMin The start of text in the main stream.</em>
+<a name="46" href="#46">46</a> <em class="jxr_javadoccomment"> */</em>
+<a name="47" href="#47">47</a> <strong class="jxr_keyword">public</strong> Word6CHPBinTable(byte[] documentStream, <strong class="jxr_keyword">int</strong> offset,
+<a name="48" href="#48">48</a> <strong class="jxr_keyword">int</strong> size, <strong class="jxr_keyword">int</strong> fcMin)
+<a name="49" href="#49">49</a> {
+<a name="50" href="#50">50</a> PlexOfCps binTable = <strong class="jxr_keyword">new</strong> PlexOfCps(documentStream, offset, size, 2);
+<a name="51" href="#51">51</a>
+<a name="52" href="#52">52</a> <strong class="jxr_keyword">int</strong> length = binTable.length();
+<a name="53" href="#53">53</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">int</strong> x = 0; x < length; x++)
+<a name="54" href="#54">54</a> {
+<a name="55" href="#55">55</a> GenericPropertyNode node = binTable.getProperty(x);
+<a name="56" href="#56">56</a>
+<a name="57" href="#57">57</a> <strong class="jxr_keyword">int</strong> pageNum = LittleEndian.getShort((byte[])node.getBytes());
+<a name="58" href="#58">58</a> <strong class="jxr_keyword">int</strong> pageOffset = POIFSConstants.BIG_BLOCK_SIZE * pageNum;
+<a name="59" href="#59">59</a>
+<a name="60" href="#60">60</a> CHPFormattedDiskPage cfkp = <strong class="jxr_keyword">new</strong> CHPFormattedDiskPage(documentStream,
+<a name="61" href="#61">61</a> pageOffset, fcMin);
+<a name="62" href="#62">62</a>
+<a name="63" href="#63">63</a> <strong class="jxr_keyword">int</strong> fkpSize = cfkp.size();
+<a name="64" href="#64">64</a>
+<a name="65" href="#65">65</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">int</strong> y = 0; y < fkpSize; y++)
+<a name="66" href="#66">66</a> {
+<a name="67" href="#67">67</a> _textRuns.add(cfkp.getCHPX(y));
+<a name="68" href="#68">68</a> }
+<a name="69" href="#69">69</a> }
+<a name="70" href="#70">70</a> }
+<a name="71" href="#71">71</a>
+<a name="72" href="#72">72</a> <strong class="jxr_keyword">public</strong> List getTextRuns()
+<a name="73" href="#73">73</a> {
+<a name="74" href="#74">74</a> <strong class="jxr_keyword">return</strong> _textRuns;
+<a name="75" href="#75">75</a> }
+<a name="76" href="#76">76</a>
+<a name="77" href="#77">77</a> }
+</pre>
+<hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body>
+</html>
+