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 [33/36] - 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/Word6Extractor.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/microsoft/Word6Extractor.html?rev=596146&view=auto
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/microsoft/Word6Extractor.html (added)
+++ incubator/tika/site/xref/org/apache/tika/parser/microsoft/Word6Extractor.html Sun Nov 18 14:20:54 2007
@@ -0,0 +1,243 @@
+<!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>Word6Extractor xref</title>
+<link type="text/css" rel="stylesheet" href="../../../../../stylesheet.css" />
+</head>
+<body>
+<div id="overview"><a href="../../../../../../apidocs/org/apache/tika/parser/microsoft/Word6Extractor.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>
+<a name="19" href="#19">19</a>
+<a name="20" href="#20">20</a> <strong class="jxr_keyword">import</strong> org.apache.poi.util.LittleEndian;
+<a name="21" href="#21">21</a> <strong class="jxr_keyword">import</strong> org.apache.poi.hwpf.model.*;
+<a name="22" href="#22">22</a>
+<a name="23" href="#23">23</a> <strong class="jxr_keyword">import</strong> java.io.IOException;
+<a name="24" href="#24">24</a> <strong class="jxr_keyword">import</strong> java.util.*;
+<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"> * This class is used to extract text from Word 6 documents only. It should</em>
+<a name="28" href="#28">28</a> <em class="jxr_javadoccomment"> * only be called from the org.textmining.text.extraction.WordExtractor because</em>
+<a name="29" href="#29">29</a> <em class="jxr_javadoccomment"> * it will automatically determine the version.</em>
+<a name="30" href="#30">30</a> <em class="jxr_javadoccomment"> *</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> <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="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> }
+</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/WordParser.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/microsoft/WordParser.html?rev=596146&view=auto
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/microsoft/WordParser.html (added)
+++ incubator/tika/site/xref/org/apache/tika/parser/microsoft/WordParser.html Sun Nov 18 14:20:54 2007
@@ -0,0 +1,210 @@
+<!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>WordParser xref</title>
+<link type="text/css" rel="stylesheet" href="../../../../../stylesheet.css" />
+</head>
+<body>
+<div id="overview"><a href="../../../../../../apidocs/org/apache/tika/parser/microsoft/WordParser.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.util.Iterator;
+<a name="21" href="#21">21</a> <strong class="jxr_keyword">import</strong> java.util.List;
+<a name="22" href="#22">22</a>
+<a name="23" href="#23">23</a> <strong class="jxr_keyword">import</strong> org.apache.poi.hwpf.model.CHPBinTable;
+<a name="24" href="#24">24</a> <strong class="jxr_keyword">import</strong> org.apache.poi.hwpf.model.CHPX;
+<a name="25" href="#25">25</a> <strong class="jxr_keyword">import</strong> org.apache.poi.hwpf.model.ComplexFileTable;
+<a name="26" href="#26">26</a> <strong class="jxr_keyword">import</strong> org.apache.poi.hwpf.model.TextPiece;
+<a name="27" href="#27">27</a> <strong class="jxr_keyword">import</strong> org.apache.poi.hwpf.model.TextPieceTable;
+<a name="28" href="#28">28</a> <strong class="jxr_keyword">import</strong> org.apache.poi.hwpf.sprm.SprmIterator;
+<a name="29" href="#29">29</a> <strong class="jxr_keyword">import</strong> org.apache.poi.hwpf.sprm.SprmOperation;
+<a name="30" href="#30">30</a> <strong class="jxr_keyword">import</strong> org.apache.poi.poifs.filesystem.DocumentEntry;
+<a name="31" href="#31">31</a> <strong class="jxr_keyword">import</strong> org.apache.poi.poifs.filesystem.DocumentInputStream;
+<a name="32" href="#32">32</a> <strong class="jxr_keyword">import</strong> org.apache.poi.poifs.filesystem.POIFSFileSystem;
+<a name="33" href="#33">33</a> <strong class="jxr_keyword">import</strong> org.apache.poi.util.LittleEndian;
+<a name="34" href="#34">34</a> <strong class="jxr_keyword">import</strong> org.apache.tika.exception.TikaException;
+<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"> * Word parser</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">class</strong> <a href="../../../../../org/apache/tika/parser/microsoft/WordParser.html">WordParser</a> <strong class="jxr_keyword">extends</strong> <a href="../../../../../org/apache/tika/parser/microsoft/OfficeParser.html">OfficeParser</a> {
+<a name="40" href="#40">40</a>
+<a name="41" href="#41">41</a> <strong class="jxr_keyword">protected</strong> String getContentType() {
+<a name="42" href="#42">42</a> <strong class="jxr_keyword">return</strong> <span class="jxr_string">"application/msword"</span>;
+<a name="43" href="#43">43</a> }
+<a name="44" href="#44">44</a>
+<a name="45" href="#45">45</a> <em class="jxr_javadoccomment">/**</em>
+<a name="46" href="#46">46</a> <em class="jxr_javadoccomment"> * Gets the text from a Word document.</em>
+<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="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 =
+<a name="54" href="#54">54</a> (DocumentEntry) fsys.getRoot().getEntry(<span class="jxr_string">"WordDocument"</span>);
+<a name="55" href="#55">55</a> DocumentInputStream din = fsys.createDocumentInputStream(<span class="jxr_string">"WordDocument"</span>);
+<a name="56" href="#56">56</a> byte[] header = <strong class="jxr_keyword">new</strong> byte[headerProps.getSize()];
+<a name="57" href="#57">57</a>
+<a name="58" href="#58">58</a> din.read(header);
+<a name="59" href="#59">59</a> din.close();
+<a name="60" href="#60">60</a>
+<a name="61" href="#61">61</a> <strong class="jxr_keyword">int</strong> info = LittleEndian.getShort(header, 0xa);
+<a name="62" href="#62">62</a> <strong class="jxr_keyword">if</strong> ((info & 0x4) != 0) {
+<a name="63" href="#63">63</a> <strong class="jxr_keyword">throw</strong> <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/exception/TikaException.html">TikaException</a>(<span class="jxr_string">"Fast-saved files are unsupported"</span>);
+<a name="64" href="#64">64</a> }
+<a name="65" href="#65">65</a> <strong class="jxr_keyword">if</strong> ((info & 0x100) != 0) {
+<a name="66" href="#66">66</a> <strong class="jxr_keyword">throw</strong> <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/exception/TikaException.html">TikaException</a>(<span class="jxr_string">"This document is password protected"</span>);
+<a name="67" href="#67">67</a> }
+<a name="68" href="#68">68</a>
+<a name="69" href="#69">69</a> <em class="jxr_comment">// determine the version of Word this document came from.</em>
+<a name="70" href="#70">70</a> <strong class="jxr_keyword">int</strong> nFib = LittleEndian.getShort(header, 0x2);
+<a name="71" href="#71">71</a> <strong class="jxr_keyword">switch</strong> (nFib) {
+<a name="72" href="#72">72</a> <strong class="jxr_keyword">case</strong> 101:
+<a name="73" href="#73">73</a> <strong class="jxr_keyword">case</strong> 102:
+<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="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>
+<a name="82" href="#82">82</a> <strong class="jxr_keyword">int</strong> complexOffset = LittleEndian.getInt(header, 0x1a2);
+<a name="83" href="#83">83</a>
+<a name="84" href="#84">84</a> <em class="jxr_comment">// determine which table stream we must use.</em>
+<a name="85" href="#85">85</a> <em class="jxr_comment">//Get the information we need from the header</em>
+<a name="86" href="#86">86</a> String tableName = <strong class="jxr_keyword">null</strong>;
+<a name="87" href="#87">87</a> <strong class="jxr_keyword">boolean</strong> useTable1 = (info & 0x200) != 0;
+<a name="88" href="#88">88</a> <strong class="jxr_keyword">if</strong> (useTable1) {
+<a name="89" href="#89">89</a> tableName = <span class="jxr_string">"1Table"</span>;
+<a name="90" href="#90">90</a> } <strong class="jxr_keyword">else</strong> {
+<a name="91" href="#91">91</a> tableName = <span class="jxr_string">"0Table"</span>;
+<a name="92" href="#92">92</a> }
+<a name="93" href="#93">93</a>
+<a name="94" href="#94">94</a> DocumentEntry table = (DocumentEntry)fsys.getRoot().getEntry(tableName);
+<a name="95" href="#95">95</a> byte[] tableStream = <strong class="jxr_keyword">new</strong> byte[table.getSize()];
+<a name="96" href="#96">96</a>
+<a name="97" href="#97">97</a> din = fsys.createDocumentInputStream(tableName);
+<a name="98" href="#98">98</a>
+<a name="99" href="#99">99</a> din.read(tableStream);
+<a name="100" href="#100">100</a> din.close();
+<a name="101" href="#101">101</a>
+<a name="102" href="#102">102</a> <strong class="jxr_keyword">int</strong> chpOffset = LittleEndian.getInt(header, 0xfa);
+<a name="103" href="#103">103</a> <strong class="jxr_keyword">int</strong> chpSize = LittleEndian.getInt(header, 0xfe);
+<a name="104" href="#104">104</a> <strong class="jxr_keyword">int</strong> fcMin = LittleEndian.getInt(header, 0x18);
+<a name="105" href="#105">105</a> CHPBinTable cbt = <strong class="jxr_keyword">new</strong> CHPBinTable(header, tableStream, chpOffset, chpSize, fcMin);
+<a name="106" href="#106">106</a>
+<a name="107" href="#107">107</a> <em class="jxr_comment">// load our text pieces and our character runs</em>
+<a name="108" href="#108">108</a> ComplexFileTable cft = <strong class="jxr_keyword">new</strong> ComplexFileTable(header, tableStream, complexOffset, fcMin);
+<a name="109" href="#109">109</a> TextPieceTable tpt = cft.getTextPieceTable();
+<a name="110" href="#110">110</a> List textPieces = tpt.getTextPieces();
+<a name="111" href="#111">111</a>
+<a name="112" href="#112">112</a> <em class="jxr_comment">// make the POIFS objects available for garbage collection</em>
+<a name="113" href="#113">113</a> din = <strong class="jxr_keyword">null</strong>;
+<a name="114" href="#114">114</a> fsys = <strong class="jxr_keyword">null</strong>;
+<a name="115" href="#115">115</a> table = <strong class="jxr_keyword">null</strong>;
+<a name="116" href="#116">116</a> headerProps = <strong class="jxr_keyword">null</strong>;
+<a name="117" href="#117">117</a>
+<a name="118" href="#118">118</a> List textRuns = cbt.getTextRuns();
+<a name="119" href="#119">119</a> Iterator runIt = textRuns.iterator();
+<a name="120" href="#120">120</a> Iterator textIt = textPieces.iterator();
+<a name="121" href="#121">121</a>
+<a name="122" href="#122">122</a> TextPiece currentPiece = (TextPiece)textIt.next();
+<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="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>
+<a name="130" href="#130">130</a> <strong class="jxr_keyword">while</strong> (runIt.hasNext()) {
+<a name="131" href="#131">131</a> CHPX chpx = (CHPX)runIt.next();
+<a name="132" href="#132">132</a> <strong class="jxr_keyword">boolean</strong> deleted = isDeleted(chpx.getGrpprl());
+<a name="133" href="#133">133</a> <strong class="jxr_keyword">if</strong> (deleted) {
+<a name="134" href="#134">134</a> <strong class="jxr_keyword">continue</strong>;
+<a name="135" href="#135">135</a> }
+<a name="136" href="#136">136</a>
+<a name="137" href="#137">137</a> <strong class="jxr_keyword">int</strong> runStart = chpx.getStart();
+<a name="138" href="#138">138</a> <strong class="jxr_keyword">int</strong> runEnd = chpx.getEnd();
+<a name="139" href="#139">139</a>
+<a name="140" href="#140">140</a> <strong class="jxr_keyword">while</strong> (runStart >= currentTextEnd) {
+<a name="141" href="#141">141</a> currentPiece = (TextPiece) textIt.next ();
+<a name="142" href="#142">142</a> currentTextStart = currentPiece.getStart ();
+<a name="143" href="#143">143</a> currentTextEnd = currentPiece.getEnd ();
+<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">if</strong> (runEnd < currentTextEnd) {
+<a name="147" href="#147">147</a> String str = currentPiece.substring(runStart - currentTextStart, runEnd - currentTextStart);
+<a name="148" href="#148">148</a> finalTextBuf.append(str);
+<a name="149" href="#149">149</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (runEnd > currentTextEnd) {
+<a name="150" href="#150">150</a> <strong class="jxr_keyword">while</strong> (runEnd > currentTextEnd) {
+<a name="151" href="#151">151</a> String str = currentPiece.substring(runStart - currentTextStart,
+<a name="152" href="#152">152</a> currentTextEnd - currentTextStart);
+<a name="153" href="#153">153</a> finalTextBuf.append(str);
+<a name="154" href="#154">154</a> <strong class="jxr_keyword">if</strong> (textIt.hasNext()) {
+<a name="155" href="#155">155</a> currentPiece = (TextPiece) textIt.next ();
+<a name="156" href="#156">156</a> currentTextStart = currentPiece.getStart ();
+<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="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);
+<a name="164" href="#164">164</a> finalTextBuf.append(str);
+<a name="165" href="#165">165</a> } <strong class="jxr_keyword">else</strong> {
+<a name="166" href="#166">166</a> String str = currentPiece.substring(runStart - currentTextStart, runEnd - currentTextStart);
+<a name="167" href="#167">167</a> <strong class="jxr_keyword">if</strong> (textIt.hasNext()) {
+<a name="168" href="#168">168</a> currentPiece = (TextPiece) textIt.next();
+<a name="169" href="#169">169</a> currentTextStart = currentPiece.getStart();
+<a name="170" href="#170">170</a> currentTextEnd = currentPiece.getEnd();
+<a name="171" href="#171">171</a> }
+<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> }
+</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/WordTextBuffer.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/microsoft/WordTextBuffer.html?rev=596146&view=auto
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/microsoft/WordTextBuffer.html (added)
+++ incubator/tika/site/xref/org/apache/tika/parser/microsoft/WordTextBuffer.html Sun Nov 18 14:20:54 2007
@@ -0,0 +1,79 @@
+<!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>WordTextBuffer xref</title>
+<link type="text/css" rel="stylesheet" href="../../../../../stylesheet.css" />
+</head>
+<body>
+<div id="overview"><a href="../../../../../../apidocs/org/apache/tika/parser/microsoft/WordTextBuffer.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> <strong class="jxr_keyword">package</strong> org.apache.tika.parser.microsoft;
+<a name="16" href="#16">16</a>
+<a name="17" href="#17">17</a>
+<a name="18" href="#18">18</a> <em class="jxr_javadoccomment">/**</em>
+<a name="19" href="#19">19</a> <em class="jxr_javadoccomment"> * This class acts as a StringBuffer for text from a word document. It allows</em>
+<a name="20" href="#20">20</a> <em class="jxr_javadoccomment"> * processing of character before they</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> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">class</strong> <a href="../../../../../org/apache/tika/parser/microsoft/WordTextBuffer.html">WordTextBuffer</a>
+<a name="24" href="#24">24</a> {
+<a name="25" href="#25">25</a> StringBuffer _buf;
+<a name="26" href="#26">26</a> <strong class="jxr_keyword">boolean</strong> _hold;
+<a name="27" href="#27">27</a>
+<a name="28" href="#28">28</a> <strong class="jxr_keyword">public</strong> <a href="../../../../../org/apache/tika/parser/microsoft/WordTextBuffer.html">WordTextBuffer</a>()
+<a name="29" href="#29">29</a> {
+<a name="30" href="#30">30</a> _buf = <strong class="jxr_keyword">new</strong> StringBuffer();
+<a name="31" href="#31">31</a> _hold = false;
+<a name="32" href="#32">32</a> }
+<a name="33" href="#33">33</a>
+<a name="34" href="#34">34</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">void</strong> append(String text)
+<a name="35" href="#35">35</a> {
+<a name="36" href="#36">36</a> <strong class="jxr_keyword">char</strong>[] letters = text.toCharArray();
+<a name="37" href="#37">37</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">int</strong> x = 0; x < letters.length; x++)
+<a name="38" href="#38">38</a> {
+<a name="39" href="#39">39</a> <strong class="jxr_keyword">switch</strong>(letters[x])
+<a name="40" href="#40">40</a> {
+<a name="41" href="#41">41</a> <strong class="jxr_keyword">case</strong> '\r':
+<a name="42" href="#42">42</a> _buf.append(<span class="jxr_string">"\r\n"</span>);
+<a name="43" href="#43">43</a> <strong class="jxr_keyword">break</strong>;
+<a name="44" href="#44">44</a> <strong class="jxr_keyword">case</strong> 0x13:
+<a name="45" href="#45">45</a> _hold = <strong class="jxr_keyword">true</strong>;
+<a name="46" href="#46">46</a> <strong class="jxr_keyword">break</strong>;
+<a name="47" href="#47">47</a> <strong class="jxr_keyword">case</strong> 0x14:
+<a name="48" href="#48">48</a> _hold = false;
+<a name="49" href="#49">49</a> <strong class="jxr_keyword">break</strong>;
+<a name="50" href="#50">50</a> <strong class="jxr_keyword">default</strong>:
+<a name="51" href="#51">51</a> <strong class="jxr_keyword">if</strong> (!_hold)
+<a name="52" href="#52">52</a> {
+<a name="53" href="#53">53</a> _buf.append(letters[x]);
+<a name="54" href="#54">54</a> }
+<a name="55" href="#55">55</a> <strong class="jxr_keyword">break</strong>;
+<a name="56" href="#56">56</a> }
+<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">public</strong> String toString()
+<a name="61" href="#61">61</a> {
+<a name="62" href="#62">62</a> <strong class="jxr_keyword">return</strong> _buf.toString();
+<a name="63" href="#63">63</a> }
+<a name="64" href="#64">64</a>
+<a name="65" href="#65">65</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/WordTextPiece.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/microsoft/WordTextPiece.html?rev=596146&view=auto
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/microsoft/WordTextPiece.html (added)
+++ incubator/tika/site/xref/org/apache/tika/parser/microsoft/WordTextPiece.html Sun Nov 18 14:20:54 2007
@@ -0,0 +1,68 @@
+<!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>WordTextPiece xref</title>
+<link type="text/css" rel="stylesheet" href="../../../../../stylesheet.css" />
+</head>
+<body>
+<div id="overview"><a href="../../../../../../apidocs/org/apache/tika/parser/microsoft/WordTextPiece.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> <em class="jxr_javadoccomment">/**</em>
+<a name="19" href="#19">19</a> <em class="jxr_javadoccomment"> * This class stores info about the data structure describing a chunk of text</em>
+<a name="20" href="#20">20</a> <em class="jxr_javadoccomment"> * in a Word document. Specifically, whether or not a Range of text uses</em>
+<a name="21" href="#21">21</a> <em class="jxr_javadoccomment"> * unicode or Cp1252 encoding.</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> <em class="jxr_javadoccomment"> */</em>
+<a name="25" href="#25">25</a>
+<a name="26" href="#26">26</a> <strong class="jxr_keyword">class</strong> <a href="../../../../../org/apache/tika/parser/microsoft/WordTextPiece.html">WordTextPiece</a>
+<a name="27" href="#27">27</a> {
+<a name="28" href="#28">28</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">int</strong> _fcStart;
+<a name="29" href="#29">29</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">boolean</strong> _usesUnicode;
+<a name="30" href="#30">30</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">int</strong> _length;
+<a name="31" href="#31">31</a>
+<a name="32" href="#32">32</a> <strong class="jxr_keyword">public</strong> <a href="../../../../../org/apache/tika/parser/microsoft/WordTextPiece.html">WordTextPiece</a>(<strong class="jxr_keyword">int</strong> start, <strong class="jxr_keyword">int</strong> length, <strong class="jxr_keyword">boolean</strong> unicode)
+<a name="33" href="#33">33</a> {
+<a name="34" href="#34">34</a> _usesUnicode = unicode;
+<a name="35" href="#35">35</a> _length = length;
+<a name="36" href="#36">36</a> _fcStart = start;
+<a name="37" href="#37">37</a> }
+<a name="38" href="#38">38</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">boolean</strong> usesUnicode()
+<a name="39" href="#39">39</a> {
+<a name="40" href="#40">40</a> <strong class="jxr_keyword">return</strong> _usesUnicode;
+<a name="41" href="#41">41</a> }
+<a name="42" href="#42">42</a>
+<a name="43" href="#43">43</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">int</strong> getStart()
+<a name="44" href="#44">44</a> {
+<a name="45" href="#45">45</a> <strong class="jxr_keyword">return</strong> _fcStart;
+<a name="46" href="#46">46</a> }
+<a name="47" href="#47">47</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">int</strong> getLength()
+<a name="48" href="#48">48</a> {
+<a name="49" href="#49">49</a> <strong class="jxr_keyword">return</strong> _length;
+<a name="50" href="#50">50</a> }
+<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> }
+</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/package-frame.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/microsoft/package-frame.html?rev=596146&view=auto
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/microsoft/package-frame.html (added)
+++ incubator/tika/site/xref/org/apache/tika/parser/microsoft/package-frame.html Sun Nov 18 14:20:54 2007
@@ -0,0 +1,60 @@
+
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "DTD/xhtml1-transitional.dtd">
+<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.microsoft</title>
+ <link rel="stylesheet" type="text/css" href="../../../../../stylesheet.css" title="style" />
+ </head>
+ <body>
+
+ <h3>
+ <a href="package-summary.html" target="classFrame">org.apache.tika.parser.microsoft</a>
+ </h3>
+
+ <h3>Classes</h3>
+
+ <ul>
+ <li>
+ <a href="ExcelParser.html" target="classFrame">ExcelParser</a>
+ </li>
+ <li>
+ <a href="FilteredStringWriter.html" target="classFrame">FilteredStringWriter</a>
+ </li>
+ <li>
+ <a href="OfficeParser.html" target="classFrame">OfficeParser</a>
+ </li>
+ <li>
+ <a href="PPTConstants.html" target="classFrame">PPTConstants</a>
+ </li>
+ <li>
+ <a href="PowerPointExtractor.html" target="classFrame">PowerPointExtractor</a>
+ </li>
+ <li>
+ <a href="PowerPointParser.html" target="classFrame">PowerPointParser</a>
+ </li>
+ <li>
+ <a href="Slide.html" target="classFrame">Slide</a>
+ </li>
+ <li>
+ <a href="TextBox.html" target="classFrame">TextBox</a>
+ </li>
+ <li>
+ <a href="Word6CHPBinTable.html" target="classFrame">Word6CHPBinTable</a>
+ </li>
+ <li>
+ <a href="Word6Extractor.html" target="classFrame">Word6Extractor</a>
+ </li>
+ <li>
+ <a href="WordParser.html" target="classFrame">WordParser</a>
+ </li>
+ <li>
+ <a href="WordTextBuffer.html" target="classFrame">WordTextBuffer</a>
+ </li>
+ <li>
+ <a href="WordTextPiece.html" target="classFrame">WordTextPiece</a>
+ </li>
+ </ul>
+
+ </body>
+</html>
\ No newline at end of file
Added: incubator/tika/site/xref/org/apache/tika/parser/microsoft/package-summary.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/microsoft/package-summary.html?rev=596146&view=auto
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/microsoft/package-summary.html (added)
+++ incubator/tika/site/xref/org/apache/tika/parser/microsoft/package-summary.html Sun Nov 18 14:20:54 2007
@@ -0,0 +1,127 @@
+
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "DTD/xhtml1-transitional.dtd">
+<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.microsoft</title>
+ <link rel="stylesheet" type="text/css" href="../../../../../stylesheet.css" title="style" />
+ </head>
+ <body>
+ <div class="overview">
+ <ul>
+ <li>
+ <a href="../../../../../overview-summary.html">Overview</a>
+ </li>
+ <li class="selected">Package</li>
+ </ul>
+ </div>
+ <div class="framenoframe">
+ <ul>
+ <li>
+ <a href="../../../../../index.html" target="_top">FRAMES</a>
+ </li>
+ <li>
+ <a href="package-summary.html" target="_top">NO FRAMES</a>
+ </li>
+ </ul>
+ </div>
+
+ <h2>Package org.apache.tika.parser.microsoft</h2>
+
+ <table class="summary">
+ <thead>
+ <tr>
+ <th>Class Summary</th>
+ </tr>
+ </thead>
+ <tbody>
+ <tr>
+ <td>
+ <a href="ExcelParser.html" target="classFrame">ExcelParser</a>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <a href="FilteredStringWriter.html" target="classFrame">FilteredStringWriter</a>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <a href="OfficeParser.html" target="classFrame">OfficeParser</a>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <a href="PPTConstants.html" target="classFrame">PPTConstants</a>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <a href="PowerPointExtractor.html" target="classFrame">PowerPointExtractor</a>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <a href="PowerPointParser.html" target="classFrame">PowerPointParser</a>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <a href="Slide.html" target="classFrame">Slide</a>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <a href="TextBox.html" target="classFrame">TextBox</a>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <a href="Word6CHPBinTable.html" target="classFrame">Word6CHPBinTable</a>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <a href="Word6Extractor.html" target="classFrame">Word6Extractor</a>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <a href="WordParser.html" target="classFrame">WordParser</a>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <a href="WordTextBuffer.html" target="classFrame">WordTextBuffer</a>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <a href="WordTextPiece.html" target="classFrame">WordTextPiece</a>
+ </td>
+ </tr>
+ </tbody>
+ </table>
+
+ <div class="overview">
+ <ul>
+ <li>
+ <a href="../../../../../overview-summary.html">Overview</a>
+ </li>
+ <li class="selected">Package</li>
+ </ul>
+ </div>
+ <div class="framenoframe">
+ <ul>
+ <li>
+ <a href="../../../../../index.html" target="_top">FRAMES</a>
+ </li>
+ <li>
+ <a href="package-summary.html" target="_top">NO FRAMES</a>
+ </li>
+ </ul>
+ </div>
+ <hr />
+ Copyright © 2007 The Apache Software Foundation. All Rights Reserved.
+ </body>
+</html>
\ No newline at end of file
Added: incubator/tika/site/xref/org/apache/tika/parser/opendocument/OpenOfficeEntityResolver.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/opendocument/OpenOfficeEntityResolver.html?rev=596146&view=auto
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/opendocument/OpenOfficeEntityResolver.html (added)
+++ incubator/tika/site/xref/org/apache/tika/parser/opendocument/OpenOfficeEntityResolver.html Sun Nov 18 14:20:54 2007
@@ -0,0 +1,73 @@
+<!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>OpenOfficeEntityResolver xref</title>
+<link type="text/css" rel="stylesheet" href="../../../../../stylesheet.css" />
+</head>
+<body>
+<div id="overview"><a href="../../../../../../apidocs/org/apache/tika/parser/opendocument/OpenOfficeEntityResolver.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.opendocument;
+<a name="18" href="#18">18</a>
+<a name="19" href="#19">19</a> <strong class="jxr_keyword">import</strong> java.io.StringReader;
+<a name="20" href="#20">20</a>
+<a name="21" href="#21">21</a> <strong class="jxr_keyword">import</strong> org.xml.sax.EntityResolver;
+<a name="22" href="#22">22</a> <strong class="jxr_keyword">import</strong> org.xml.sax.InputSource;
+<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"> * OpenOffice entity resolver</em>
+<a name="26" href="#26">26</a> <em class="jxr_javadoccomment"> * </em>
+<a name="27" href="#27">27</a> <em class="jxr_javadoccomment"> * </em>
+<a name="28" href="#28">28</a> <em class="jxr_javadoccomment"> */</em>
+<a name="29" href="#29">29</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">class</strong> <a href="../../../../../org/apache/tika/parser/opendocument/OpenOfficeEntityResolver.html">OpenOfficeEntityResolver</a>
+<a name="30" href="#30">30</a>
+<a name="31" href="#31">31</a> implements EntityResolver {
+<a name="32" href="#32">32</a>
+<a name="33" href="#33">33</a> <strong class="jxr_keyword">public</strong> InputSource resolveEntity(String publicId, String systemId)
+<a name="34" href="#34">34</a>
+<a name="35" href="#35">35</a> {
+<a name="36" href="#36">36</a>
+<a name="37" href="#37">37</a> <strong class="jxr_keyword">if</strong> (systemId.endsWith(<span class="jxr_string">".dtd"</span>))
+<a name="38" href="#38">38</a>
+<a name="39" href="#39">39</a> {
+<a name="40" href="#40">40</a>
+<a name="41" href="#41">41</a> StringReader stringInput =
+<a name="42" href="#42">42</a>
+<a name="43" href="#43">43</a> <strong class="jxr_keyword">new</strong> StringReader(<span class="jxr_string">" "</span>);
+<a name="44" href="#44">44</a>
+<a name="45" href="#45">45</a> <strong class="jxr_keyword">return</strong> <strong class="jxr_keyword">new</strong> InputSource(stringInput);
+<a name="46" href="#46">46</a>
+<a name="47" href="#47">47</a> }
+<a name="48" href="#48">48</a>
+<a name="49" href="#49">49</a> <strong class="jxr_keyword">else</strong>
+<a name="50" href="#50">50</a>
+<a name="51" href="#51">51</a> {
+<a name="52" href="#52">52</a>
+<a name="53" href="#53">53</a> <strong class="jxr_keyword">return</strong> <strong class="jxr_keyword">null</strong>;
+<a name="54" href="#54">54</a>
+<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>
+<a name="59" href="#59">59</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/opendocument/OpenOfficeParser.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/opendocument/OpenOfficeParser.html?rev=596146&view=auto
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/opendocument/OpenOfficeParser.html (added)
+++ incubator/tika/site/xref/org/apache/tika/parser/opendocument/OpenOfficeParser.html Sun Nov 18 14:20:54 2007
@@ -0,0 +1,160 @@
+<!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>OpenOfficeParser xref</title>
+<link type="text/css" rel="stylesheet" href="../../../../../stylesheet.css" />
+</head>
+<body>
+<div id="overview"><a href="../../../../../../apidocs/org/apache/tika/parser/opendocument/OpenOfficeParser.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>
+<a name="18" href="#18">18</a> <strong class="jxr_keyword">package</strong> org.apache.tika.parser.opendocument;
+<a name="19" href="#19">19</a>
+<a name="20" href="#20">20</a> <strong class="jxr_keyword">import</strong> java.io.ByteArrayInputStream;
+<a name="21" href="#21">21</a> <strong class="jxr_keyword">import</strong> java.io.ByteArrayOutputStream;
+<a name="22" href="#22">22</a> <strong class="jxr_keyword">import</strong> java.io.IOException;
+<a name="23" href="#23">23</a> <strong class="jxr_keyword">import</strong> java.io.InputStream;
+<a name="24" href="#24">24</a> <strong class="jxr_keyword">import</strong> java.io.OutputStream;
+<a name="25" href="#25">25</a> <strong class="jxr_keyword">import</strong> java.util.ArrayList;
+<a name="26" href="#26">26</a> <strong class="jxr_keyword">import</strong> java.util.List;
+<a name="27" href="#27">27</a> <strong class="jxr_keyword">import</strong> java.util.zip.ZipEntry;
+<a name="28" href="#28">28</a> <strong class="jxr_keyword">import</strong> java.util.zip.ZipInputStream;
+<a name="29" href="#29">29</a>
+<a name="30" href="#30">30</a> <strong class="jxr_keyword">import</strong> org.apache.tika.exception.TikaException;
+<a name="31" href="#31">31</a> <strong class="jxr_keyword">import</strong> org.apache.tika.metadata.Metadata;
+<a name="32" href="#32">32</a> <strong class="jxr_keyword">import</strong> org.apache.tika.parser.Parser;
+<a name="33" href="#33">33</a> <strong class="jxr_keyword">import</strong> org.apache.tika.parser.xml.XMLParser;
+<a name="34" href="#34">34</a> <strong class="jxr_keyword">import</strong> org.apache.tika.sax.XHTMLContentHandler;
+<a name="35" href="#35">35</a>
+<a name="36" href="#36">36</a> <strong class="jxr_keyword">import</strong> org.apache.log4j.Logger;
+<a name="37" href="#37">37</a> <strong class="jxr_keyword">import</strong> org.jdom.Document;
+<a name="38" href="#38">38</a> <strong class="jxr_keyword">import</strong> org.jdom.Element;
+<a name="39" href="#39">39</a> <strong class="jxr_keyword">import</strong> org.jdom.JDOMException;
+<a name="40" href="#40">40</a> <strong class="jxr_keyword">import</strong> org.jdom.Namespace;
+<a name="41" href="#41">41</a> <strong class="jxr_keyword">import</strong> org.jdom.input.SAXBuilder;
+<a name="42" href="#42">42</a> <strong class="jxr_keyword">import</strong> org.xml.sax.ContentHandler;
+<a name="43" href="#43">43</a> <strong class="jxr_keyword">import</strong> org.xml.sax.SAXException;
+<a name="44" href="#44">44</a>
+<a name="45" href="#45">45</a> <em class="jxr_javadoccomment">/**</em>
+<a name="46" href="#46">46</a> <em class="jxr_javadoccomment"> * OpenOffice parser</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> <strong class="jxr_keyword">class</strong> <a href="../../../../../org/apache/tika/parser/opendocument/OpenOfficeParser.html">OpenOfficeParser</a> implements <a href="../../../../../org/apache/tika/parser/Parser.html">Parser</a> {
+<a name="49" href="#49">49</a> <strong class="jxr_keyword">static</strong> Logger logger = Logger.getRootLogger();
+<a name="50" href="#50">50</a>
+<a name="51" href="#51">51</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">final</strong> Namespace NS_DC = Namespace.getNamespace(<span class="jxr_string">"dc"</span>,
+<a name="52" href="#52">52</a> <span class="jxr_string">"http://purl.org/dc/elements/1.1/"</span>);
+<a name="53" href="#53">53</a>
+<a name="54" href="#54">54</a> <strong class="jxr_keyword">public</strong> org.jdom.Document parse(InputStream is) {
+<a name="55" href="#55">55</a> Document xmlDoc = <strong class="jxr_keyword">new</strong> org.jdom.Document();
+<a name="56" href="#56">56</a> org.jdom.Document xmlMeta = <strong class="jxr_keyword">new</strong> org.jdom.Document();
+<a name="57" href="#57">57</a> <strong class="jxr_keyword">try</strong> {
+<a name="58" href="#58">58</a> List files = unzip(is);
+<a name="59" href="#59">59</a> SAXBuilder builder = <strong class="jxr_keyword">new</strong> SAXBuilder();
+<a name="60" href="#60">60</a> builder.setEntityResolver(<strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/parser/opendocument/OpenOfficeEntityResolver.html">OpenOfficeEntityResolver</a>());
+<a name="61" href="#61">61</a> builder.setValidation(false);
+<a name="62" href="#62">62</a>
+<a name="63" href="#63">63</a> xmlDoc = builder.build((InputStream) files.get(0));
+<a name="64" href="#64">64</a> xmlMeta = builder.build((InputStream) files.get(1));
+<a name="65" href="#65">65</a> Element rootMeta = xmlMeta.getRootElement();
+<a name="66" href="#66">66</a> Element meta = <strong class="jxr_keyword">null</strong>;
+<a name="67" href="#67">67</a> List ls = rootMeta.getChildren();
+<a name="68" href="#68">68</a> <strong class="jxr_keyword">if</strong> (! ls.isEmpty()) {
+<a name="69" href="#69">69</a> meta = (Element) ls.get(0);
+<a name="70" href="#70">70</a> }
+<a name="71" href="#71">71</a> xmlDoc.getRootElement().addContent(meta.detach());
+<a name="72" href="#72">72</a> xmlDoc.getRootElement().addNamespaceDeclaration(NS_DC);
+<a name="73" href="#73">73</a> } <strong class="jxr_keyword">catch</strong> (JDOMException e) {
+<a name="74" href="#74">74</a> logger.error(e.getMessage());
+<a name="75" href="#75">75</a> } <strong class="jxr_keyword">catch</strong> (IOException e) {
+<a name="76" href="#76">76</a> logger.error(e.getMessage());
+<a name="77" href="#77">77</a> }
+<a name="78" href="#78">78</a> <strong class="jxr_keyword">return</strong> xmlDoc;
+<a name="79" href="#79">79</a> }
+<a name="80" href="#80">80</a>
+<a name="81" href="#81">81</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">void</strong> parse(
+<a name="82" href="#82">82</a> InputStream stream, ContentHandler handler, <a href="../../../../../org/apache/tika/metadata/Metadata.html">Metadata</a> metadata)
+<a name="83" href="#83">83</a> <strong class="jxr_keyword">throws</strong> IOException, SAXException, <a href="../../../../../org/apache/tika/exception/TikaException.html">TikaException</a> {
+<a name="84" href="#84">84</a> Document xmlDoc = parse(stream);
+<a name="85" href="#85">85</a> <a href="../../../../../org/apache/tika/parser/xml/XMLParser.html">XMLParser</a> xp = <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/parser/xml/XMLParser.html">XMLParser</a>();
+<a name="86" href="#86">86</a> xp.getAllDocumentNs(xmlDoc);
+<a name="87" href="#87">87</a> xp.extractContent(xmlDoc, Metadata.TITLE, <span class="jxr_string">"//dc:title"</span>, metadata);
+<a name="88" href="#88">88</a> xp.extractContent(xmlDoc, Metadata.SUBJECT, <span class="jxr_string">"//dc:subject"</span>, metadata);
+<a name="89" href="#89">89</a> xp.extractContent(xmlDoc, Metadata.CREATOR, <span class="jxr_string">"//dc:creator"</span>, metadata);
+<a name="90" href="#90">90</a> xp.extractContent(xmlDoc, Metadata.DESCRIPTION, <span class="jxr_string">"//dc:description"</span>, metadata);
+<a name="91" href="#91">91</a> xp.extractContent(xmlDoc, Metadata.LANGUAGE, <span class="jxr_string">"//dc:language"</span>, metadata);
+<a name="92" href="#92">92</a> xp.extractContent(xmlDoc, Metadata.KEYWORDS, <span class="jxr_string">"//meta:keyword"</span>, metadata);
+<a name="93" href="#93">93</a> xp.extractContent(xmlDoc, Metadata.DATE, <span class="jxr_string">"//dc:date"</span>, metadata);
+<a name="94" href="#94">94</a> xp.extractContent(xmlDoc, <span class="jxr_string">"nbTab"</span>, <span class="jxr_string">"//meta:document-statistic/@meta:table-count"</span>, metadata);
+<a name="95" href="#95">95</a> xp.extractContent(xmlDoc, <span class="jxr_string">"nbObject"</span>, <span class="jxr_string">"//meta:document-statistic/@meta:object-count"</span>, metadata);
+<a name="96" href="#96">96</a> xp.extractContent(xmlDoc, <span class="jxr_string">"nbImg"</span>, <span class="jxr_string">"//meta:document-statistic/@meta:image-count"</span>, metadata);
+<a name="97" href="#97">97</a> xp.extractContent(xmlDoc, <span class="jxr_string">"nbPage"</span>, <span class="jxr_string">"//meta:document-statistic/@meta:page-count"</span>, metadata);
+<a name="98" href="#98">98</a> xp.extractContent(xmlDoc, <span class="jxr_string">"nbPara"</span>, <span class="jxr_string">"//meta:document-statistic/@meta:paragraph-count"</span>, metadata);
+<a name="99" href="#99">99</a> xp.extractContent(xmlDoc, <span class="jxr_string">"nbWord"</span>, <span class="jxr_string">"//meta:document-statistic/@meta:word-count"</span>, metadata);
+<a name="100" href="#100">100</a> xp.extractContent(xmlDoc, <span class="jxr_string">"nbcharacter"</span>, <span class="jxr_string">"//meta:document-statistic/@meta:character-count"</span>, metadata);
+<a name="101" href="#101">101</a>
+<a name="102" href="#102">102</a> <a href="../../../../../org/apache/tika/sax/XHTMLContentHandler.html">XHTMLContentHandler</a> xhtml = <strong class="jxr_keyword">new</strong> <a href="../../../../../org/apache/tika/sax/XHTMLContentHandler.html">XHTMLContentHandler</a>(handler, metadata);
+<a name="103" href="#103">103</a> xhtml.startDocument();
+<a name="104" href="#104">104</a> xhtml.element(<span class="jxr_string">"p"</span>, xp.concatOccurrence(xmlDoc, <span class="jxr_string">"//*"</span>, <span class="jxr_string">" "</span>));
+<a name="105" href="#105">105</a> xhtml.endDocument();
+<a name="106" href="#106">106</a> }
+<a name="107" href="#107">107</a>
+<a name="108" href="#108">108</a> <strong class="jxr_keyword">public</strong> List unzip(InputStream is) {
+<a name="109" href="#109">109</a> List res = <strong class="jxr_keyword">new</strong> ArrayList();
+<a name="110" href="#110">110</a> <strong class="jxr_keyword">try</strong> {
+<a name="111" href="#111">111</a> ZipInputStream in = <strong class="jxr_keyword">new</strong> ZipInputStream(is);
+<a name="112" href="#112">112</a> ZipEntry entry = <strong class="jxr_keyword">null</strong>;
+<a name="113" href="#113">113</a> <strong class="jxr_keyword">while</strong> ((entry = in.getNextEntry()) != <strong class="jxr_keyword">null</strong>) {
+<a name="114" href="#114">114</a> <strong class="jxr_keyword">if</strong> (entry.getName().equals(<span class="jxr_string">"meta.xml"</span>)
+<a name="115" href="#115">115</a> || entry.getName().equals(<span class="jxr_string">"content.xml"</span>)) {
+<a name="116" href="#116">116</a> ByteArrayOutputStream stream = <strong class="jxr_keyword">new</strong> ByteArrayOutputStream();
+<a name="117" href="#117">117</a> byte[] buf = <strong class="jxr_keyword">new</strong> byte[1024];
+<a name="118" href="#118">118</a> <strong class="jxr_keyword">int</strong> len;
+<a name="119" href="#119">119</a> <strong class="jxr_keyword">while</strong> ((len = in.read(buf)) > 0) {
+<a name="120" href="#120">120</a> stream.write(buf, 0, len);
+<a name="121" href="#121">121</a> }
+<a name="122" href="#122">122</a> InputStream isEntry = <strong class="jxr_keyword">new</strong> ByteArrayInputStream(stream
+<a name="123" href="#123">123</a> .toByteArray());
+<a name="124" href="#124">124</a> res.add(isEntry);
+<a name="125" href="#125">125</a> }
+<a name="126" href="#126">126</a> }
+<a name="127" href="#127">127</a> in.close();
+<a name="128" href="#128">128</a> } <strong class="jxr_keyword">catch</strong> (IOException e) {
+<a name="129" href="#129">129</a> logger.error(e.getMessage());
+<a name="130" href="#130">130</a> }
+<a name="131" href="#131">131</a> <strong class="jxr_keyword">return</strong> res;
+<a name="132" href="#132">132</a> }
+<a name="133" href="#133">133</a>
+<a name="134" href="#134">134</a> <strong class="jxr_keyword">protected</strong> <strong class="jxr_keyword">void</strong> copyInputStream(InputStream in, OutputStream out)
+<a name="135" href="#135">135</a> <strong class="jxr_keyword">throws</strong> IOException {
+<a name="136" href="#136">136</a> byte[] buffer = <strong class="jxr_keyword">new</strong> byte[1024];
+<a name="137" href="#137">137</a> <strong class="jxr_keyword">int</strong> len;
+<a name="138" href="#138">138</a>
+<a name="139" href="#139">139</a> <strong class="jxr_keyword">while</strong> ((len = in.read(buffer)) >= 0)
+<a name="140" href="#140">140</a> out.write(buffer, 0, len);
+<a name="141" href="#141">141</a>
+<a name="142" href="#142">142</a> in.close();
+<a name="143" href="#143">143</a> out.close();
+<a name="144" href="#144">144</a> }
+<a name="145" href="#145">145</a>
+<a name="146" href="#146">146</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/opendocument/package-frame.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/opendocument/package-frame.html?rev=596146&view=auto
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/opendocument/package-frame.html (added)
+++ incubator/tika/site/xref/org/apache/tika/parser/opendocument/package-frame.html Sun Nov 18 14:20:54 2007
@@ -0,0 +1,27 @@
+
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "DTD/xhtml1-transitional.dtd">
+<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.opendocument</title>
+ <link rel="stylesheet" type="text/css" href="../../../../../stylesheet.css" title="style" />
+ </head>
+ <body>
+
+ <h3>
+ <a href="package-summary.html" target="classFrame">org.apache.tika.parser.opendocument</a>
+ </h3>
+
+ <h3>Classes</h3>
+
+ <ul>
+ <li>
+ <a href="OpenOfficeEntityResolver.html" target="classFrame">OpenOfficeEntityResolver</a>
+ </li>
+ <li>
+ <a href="OpenOfficeParser.html" target="classFrame">OpenOfficeParser</a>
+ </li>
+ </ul>
+
+ </body>
+</html>
\ No newline at end of file
Added: incubator/tika/site/xref/org/apache/tika/parser/opendocument/package-summary.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/opendocument/package-summary.html?rev=596146&view=auto
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/opendocument/package-summary.html (added)
+++ incubator/tika/site/xref/org/apache/tika/parser/opendocument/package-summary.html Sun Nov 18 14:20:54 2007
@@ -0,0 +1,72 @@
+
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "DTD/xhtml1-transitional.dtd">
+<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.opendocument</title>
+ <link rel="stylesheet" type="text/css" href="../../../../../stylesheet.css" title="style" />
+ </head>
+ <body>
+ <div class="overview">
+ <ul>
+ <li>
+ <a href="../../../../../overview-summary.html">Overview</a>
+ </li>
+ <li class="selected">Package</li>
+ </ul>
+ </div>
+ <div class="framenoframe">
+ <ul>
+ <li>
+ <a href="../../../../../index.html" target="_top">FRAMES</a>
+ </li>
+ <li>
+ <a href="package-summary.html" target="_top">NO FRAMES</a>
+ </li>
+ </ul>
+ </div>
+
+ <h2>Package org.apache.tika.parser.opendocument</h2>
+
+ <table class="summary">
+ <thead>
+ <tr>
+ <th>Class Summary</th>
+ </tr>
+ </thead>
+ <tbody>
+ <tr>
+ <td>
+ <a href="OpenOfficeEntityResolver.html" target="classFrame">OpenOfficeEntityResolver</a>
+ </td>
+ </tr>
+ <tr>
+ <td>
+ <a href="OpenOfficeParser.html" target="classFrame">OpenOfficeParser</a>
+ </td>
+ </tr>
+ </tbody>
+ </table>
+
+ <div class="overview">
+ <ul>
+ <li>
+ <a href="../../../../../overview-summary.html">Overview</a>
+ </li>
+ <li class="selected">Package</li>
+ </ul>
+ </div>
+ <div class="framenoframe">
+ <ul>
+ <li>
+ <a href="../../../../../index.html" target="_top">FRAMES</a>
+ </li>
+ <li>
+ <a href="package-summary.html" target="_top">NO FRAMES</a>
+ </li>
+ </ul>
+ </div>
+ <hr />
+ Copyright © 2007 The Apache Software Foundation. All Rights Reserved.
+ </body>
+</html>
\ No newline at end of file