📄 pdfparser.html
字号:
<!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=UTF-8" /><title>PDFParser xref</title><link type="text/css" rel="stylesheet" href="../../../../stylesheet.css" /></head><body><div id="overview"><a href="../../../../../apidocs/org/archive/crawler/extractor/PDFParser.html">View Javadoc</a></div><pre><a name="1" href="#1">1</a> <em class="comment">/*<em class="comment"> Copyright (C) 2003 Internet Archive.</em></em><a name="2" href="#2">2</a> <em class="comment"> *</em><a name="3" href="#3">3</a> <em class="comment"> * This file is part of the Heritrix web crawler (crawler.archive.org).</em><a name="4" href="#4">4</a> <em class="comment"> *</em><a name="5" href="#5">5</a> <em class="comment"> * Heritrix is free software; you can redistribute it and/or modify</em><a name="6" href="#6">6</a> <em class="comment"> * it under the terms of the GNU Lesser Public License as published by</em><a name="7" href="#7">7</a> <em class="comment"> * the Free Software Foundation; either version 2.1 of the License, or</em><a name="8" href="#8">8</a> <em class="comment"> * any later version.</em><a name="9" href="#9">9</a> <em class="comment"> *</em><a name="10" href="#10">10</a> <em class="comment"> * Heritrix is distributed in the hope that it will be useful,</em><a name="11" href="#11">11</a> <em class="comment"> * but WITHOUT ANY WARRANTY; without even the implied warranty of</em><a name="12" href="#12">12</a> <em class="comment"> * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the</em><a name="13" href="#13">13</a> <em class="comment"> * GNU Lesser Public License for more details.</em><a name="14" href="#14">14</a> <em class="comment"> *</em><a name="15" href="#15">15</a> <em class="comment"> * You should have received a copy of the GNU Lesser Public License</em><a name="16" href="#16">16</a> <em class="comment"> * along with Heritrix; if not, write to the Free Software</em><a name="17" href="#17">17</a> <em class="comment"> * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA</em><a name="18" href="#18">18</a> <em class="comment"> *</em><a name="19" href="#19">19</a> <em class="comment"> * Created on Jul 14, 2003</em><a name="20" href="#20">20</a> <em class="comment"> *</em><a name="21" href="#21">21</a> <em class="comment"> */</em><a name="22" href="#22">22</a> <strong>package</strong> <a href="../../../../org/archive/crawler/extractor/package-summary.html">org.archive.crawler.extractor</a>;<a name="23" href="#23">23</a> <a name="24" href="#24">24</a> <strong>import</strong> com.lowagie.text.pdf.PdfReader;<a name="25" href="#25">25</a> <strong>import</strong> com.lowagie.text.pdf.PdfName;<a name="26" href="#26">26</a> <strong>import</strong> com.lowagie.text.pdf.PdfObject;<a name="27" href="#27">27</a> <strong>import</strong> com.lowagie.text.pdf.PdfDictionary;<a name="28" href="#28">28</a> <strong>import</strong> com.lowagie.text.pdf.PRIndirectReference;<a name="29" href="#29">29</a> <strong>import</strong> com.lowagie.text.pdf.PdfArray;<a name="30" href="#30">30</a> <a name="31" href="#31">31</a> <strong>import</strong> java.io.*;<a name="32" href="#32">32</a> <strong>import</strong> java.util.*;<a name="33" href="#33">33</a> <a name="34" href="#34">34</a> <a name="35" href="#35">35</a> <em>/**<em>* Supports PDF parsing operations. For now this primarily means</em></em><a name="36" href="#36">36</a> <em> * extracting URIs, but the logic in extractURIs() could easily be adopted/extended</em><a name="37" href="#37">37</a> <em> * for a variety of PDF processing tasks.</em><a name="38" href="#38">38</a> <em> *</em><a name="39" href="#39">39</a> <em> * @author Parker Thompson</em><a name="40" href="#40">40</a> <em> *</em><a name="41" href="#41">41</a> <em> */</em><a name="42" href="#42">42</a> <em class="comment">//TODO make this more effecient, it currently had to read the whole file into memory</em><a name="43" href="#43">43</a> <em class="comment">// before processing can begin, and appears to take much longer than it "should"</em><a name="44" href="#44">44</a> <em class="comment">// to parse small, but admittedly complex, documents.</em><a name="45" href="#45">45</a> <strong>public</strong> <strong>class</strong> <a href="../../../../org/archive/crawler/extractor/PDFParser.html">PDFParser</a> {<a name="46" href="#46">46</a> <a name="47" href="#47">47</a> ArrayList foundURIs;<a name="48" href="#48">48</a> ArrayList encounteredReferences;<a name="49" href="#49">49</a> PdfReader documentReader;<a name="50" href="#50">50</a> byte[] document;<a name="51" href="#51">51</a> PdfDictionary catalog;<a name="52" href="#52">52</a> <a name="53" href="#53">53</a> <strong>public</strong> <a href="../../../../org/archive/crawler/extractor/PDFParser.html">PDFParser</a>(String doc) throws IOException {<a name="54" href="#54">54</a> resetState();<a name="55" href="#55">55</a> getInFromFile(doc);<a name="56" href="#56">56</a> initialize();<a name="57" href="#57">57</a> }<a name="58" href="#58">58</a> <strong>public</strong> <a href="../../../../org/archive/crawler/extractor/PDFParser.html">PDFParser</a>(byte[] doc) throws IOException{<a name="59" href="#59">59</a> resetState();<a name="60" href="#60">60</a> document = doc;<a name="61" href="#61">61</a> initialize();<a name="62" href="#62">62</a> }<a name="63" href="#63">63</a> <a name="64" href="#64">64</a> <em>/**<em>* Reinitialize the object as though a new one were created.</em></em><a name="65" href="#65">65</a> <em> */</em><a name="66" href="#66">66</a> <strong>protected</strong> <strong>void</strong> resetState(){<a name="67" href="#67">67</a> foundURIs = <strong>new</strong> ArrayList();<a name="68" href="#68">68</a> encounteredReferences = <strong>new</strong> ArrayList();<a name="69" href="#69">69</a> documentReader = <strong>null</strong>;<a name="70" href="#70">70</a> document = <strong>null</strong>;<a name="71" href="#71">71</a> catalog = <strong>null</strong>;<a name="72" href="#72">72</a> <a name="73" href="#73">73</a> <strong>for</strong>(<strong>int</strong> i=0; i < encounteredReferences.size(); i++){<a name="74" href="#74">74</a> encounteredReferences.add(<strong>new</strong> ArrayList());<a name="75" href="#75">75</a> }<a name="76" href="#76">76</a> }<a name="77" href="#77">77</a> <a name="78" href="#78">78</a> <em>/**<em>*</em></em><a name="79" href="#79">79</a> <em> * Reset the object and initialize it with a new byte array (the document).</em><a name="80" href="#80">80</a> <em> * @param doc</em><a name="81" href="#81">81</a> <em> * @throws IOException</em><a name="82" href="#82">82</a> <em> */</em><a name="83" href="#83">83</a> <strong>public</strong> <strong>void</strong> resetState(byte[] doc) throws IOException{<a name="84" href="#84">84</a> resetState();<a name="85" href="#85">85</a> document = doc;<a name="86" href="#86">86</a> initialize();<a name="87" href="#87">87</a> }<a name="88" href="#88">88</a> <a name="89" href="#89">89</a> <em>/**<em>* Reinitialize the object as though a new one were created, complete</em></em><a name="90" href="#90">90</a> <em> * with a valid pointer to a document that can be read</em><a name="91" href="#91">91</a> <em> * @param doc</em><a name="92" href="#92">92</a> <em> * @throws IOException</em><a name="93" href="#93">93</a> <em> */</em><a name="94" href="#94">94</a> <strong>public</strong> <strong>void</strong> resetState(String doc) throws IOException{<a name="95" href="#95">95</a> resetState();<a name="96" href="#96">96</a> getInFromFile(doc);<a name="97" href="#97">97</a> initialize();<a name="98" href="#98">98</a> }<a name="99" href="#99">99</a> <a name="100" href="#100">100</a> <em>/**<em>*</em></em><a name="101" href="#101">101</a> <em> * Read a file named 'doc' and store its' bytes for later processing.</em><a name="102" href="#102">102</a> <em> * @param doc</em><a name="103" href="#103">103</a> <em> * @throws IOException</em><a name="104" href="#104">104</a> <em> */</em><a name="105" href="#105">105</a> <strong>protected</strong> <strong>void</strong> getInFromFile(String doc) throws IOException{<a name="106" href="#106">106</a> File documentOnDisk = <strong>new</strong> File(doc);<a name="107" href="#107">107</a> <a name="108" href="#108">108</a> <strong>long</strong> length = documentOnDisk.length();<a name="109" href="#109">109</a> document = <strong>new</strong> byte[(<strong>int</strong>)length];<a name="110" href="#110">110</a> <a name="111" href="#111">111</a> FileInputStream inStream = <strong>new</strong> FileInputStream(documentOnDisk);<a name="112" href="#112">112</a> <a name="113" href="#113">113</a> inStream.read(document);<a name="114" href="#114">114</a> }<a name="115" href="#115">115</a> <a name="116" href="#116">116</a> <em>/**<em>*</em></em><a name="117" href="#117">117</a> <em> * Indicates, based on a PDFObject's generation/id pair whether</em><a name="118" href="#118">118</a> <em> * the parser has already encountered this object (or a reference to it)</em><a name="119" href="#119">119</a> <em> * so we don't infinitely loop on circuits within the PDF.</em><a name="120" href="#120">120</a> <em> * @param generation</em><a name="121" href="#121">121</a> <em> * @param id</em><a name="122" href="#122">122</a> <em> * @return True if already seen.</em><a name="123" href="#123">123</a> <em> */</em><a name="124" href="#124">124</a> <strong>protected</strong> <strong>boolean</strong> haveSeen(<strong>int</strong> generation, <strong>int</strong> id){<a name="125" href="#125">125</a> <a name="126" href="#126">126</a> <em class="comment">// if we can't store this generation grow our list until we can</em><a name="127" href="#127">127</a> <strong>if</strong>(generation >= encounteredReferences.size()){<a name="128" href="#128">128</a> <strong>for</strong>(<strong>int</strong> i=encounteredReferences.size(); i <= generation; i++){<a name="129" href="#129">129</a> encounteredReferences.add(<strong>new</strong> ArrayList());<a name="130" href="#130">130</a> }<a name="131" href="#131">131</a> <a name="132" href="#132">132</a> <em class="comment">// clearly we haven't seen it</em><a name="133" href="#133">133</a> <strong>return</strong> false;<a name="134" href="#134">134</a> }<a name="135" href="#135">135</a> ⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -