warcrecord.html

用JAVA编写的,在做实验的时候留下来的,本来想删的,但是传上来,大家分享吧

<a name="111" href="#111">111</a>         <strong>super</strong>(in, <strong>null</strong>, 0, digest, strict);
<a name="112" href="#112">112</a>         setHeader(parseHeaders(in, identifier, offset, strict));
<a name="113" href="#113">113</a>     }
<a name="114" href="#114">114</a>     
<a name="115" href="#115">115</a>     <em>/**<em>*</em></em>
<a name="116" href="#116">116</a> <em>     * Parse WARC Header Line and Named Fields.</em>
<a name="117" href="#117">117</a> <em>     * @param in Stream to read.</em>
<a name="118" href="#118">118</a> <em>     * @param identifier Identifier for the hosting Reader.</em>
<a name="119" href="#119">119</a> <em>     * @param offset Absolute offset into Reader.</em>
<a name="120" href="#120">120</a> <em>     * @param strict Whether to be loose parsing or not.</em>
<a name="121" href="#121">121</a> <em>     * @return An ArchiveRecordHeader.</em>
<a name="122" href="#122">122</a> <em>     * @throws IOException </em>
<a name="123" href="#123">123</a> <em>     */</em>
<a name="124" href="#124">124</a>     <strong>protected</strong> <a href="../../../../org/archive/io/ArchiveRecordHeader.html">ArchiveRecordHeader</a> parseHeaders(<strong>final</strong> InputStream in,
<a name="125" href="#125">125</a>         <strong>final</strong> String identifier, <strong>final</strong> <strong>long</strong> offset, <strong>final</strong> <strong>boolean</strong> strict)
<a name="126" href="#126">126</a>     throws IOException {
<a name="127" href="#127">127</a>     	<strong>final</strong> Map&lt;Object, Object> m = <strong>new</strong> HashMap&lt;Object, Object>();
<a name="128" href="#128">128</a>     	m.put(ABSOLUTE_OFFSET_KEY, <strong>new</strong> Long(offset));
<a name="129" href="#129">129</a>     	m.put(READER_IDENTIFIER_FIELD_KEY, identifier);
<a name="130" href="#130">130</a>         <em class="comment">// Here we start reading off the inputstream but we're reading the</em>
<a name="131" href="#131">131</a>         <em class="comment">// stream direct rather than going via WARCRecord#read.  The latter will</em>
<a name="132" href="#132">132</a>         <em class="comment">// keep count of bytes read, digest and fail properly if EOR too soon...</em>
<a name="133" href="#133">133</a>         <em class="comment">// We don't want digesting while reading Header Line and Named Fields.</em>
<a name="134" href="#134">134</a>         <em class="comment">// </em>
<a name="135" href="#135">135</a>         <em class="comment">// The returned length includes terminating CRLF.</em>
<a name="136" href="#136">136</a>         <strong>int</strong> headLineLength = parseHeaderLine(in, m, strict);
<a name="137" href="#137">137</a>         
<a name="138" href="#138">138</a>         <em class="comment">// Now, doing the ANVL parse, hard to know how many bytes have been</em>
<a name="139" href="#139">139</a>         <em class="comment">// read since passed Stream doesn't keep count and the ANVL parse can</em>
<a name="140" href="#140">140</a>         <em class="comment">// throw away bytes (e.g. if white space padding at start of a folded</em>
<a name="141" href="#141">141</a>         <em class="comment">// Value or if a Value has a newline in it and it gets converted to a</em>
<a name="142" href="#142">142</a>         <em class="comment">// CRNL in the ANVL representation).  Wrap the stream in a</em>
<a name="143" href="#143">143</a>         <em class="comment">// byte-counting stream.</em>
<a name="144" href="#144">144</a>         <em class="comment">//</em>
<a name="145" href="#145">145</a>         <em class="comment">// TODO: Buffering.  Currently, we rely on the deflate buffer when</em>
<a name="146" href="#146">146</a>         <em class="comment">// file is gzipped.  Otherwise, if uncompressed, no buffering.</em>
<a name="147" href="#147">147</a>         <strong>final</strong> <a href="../../../../org/archive/util/LongWrapper.html">LongWrapper</a> anvlParseLength = <strong>new</strong> <a href="../../../../org/archive/util/LongWrapper.html">LongWrapper</a>(0);
<a name="148" href="#148">148</a>         InputStream countingStream = <strong>new</strong> InputStream() {
<a name="149" href="#149">149</a>             @Override
<a name="150" href="#150">150</a>             <strong>public</strong> <strong>int</strong> read() throws IOException {
<a name="151" href="#151">151</a>                 <strong>int</strong> c = in.read();
<a name="152" href="#152">152</a>                 <strong>if</strong> (c != -1) {
<a name="153" href="#153">153</a>                     anvlParseLength.longValue++;
<a name="154" href="#154">154</a>                 }
<a name="155" href="#155">155</a>                 <strong>return</strong> c;
<a name="156" href="#156">156</a>             }
<a name="157" href="#157">157</a>         };
<a name="158" href="#158">158</a>         parseNamedFields(countingStream, m);
<a name="159" href="#159">159</a>         <em class="comment">// Set offset at which content begins. Its the Header Line length plus</em>
<a name="160" href="#160">160</a>         <em class="comment">// whatever we read parsing ANVL.</em>
<a name="161" href="#161">161</a>         <strong>final</strong> <strong>int</strong> contentOffset =
<a name="162" href="#162">162</a>             (<strong>int</strong>)(headLineLength + anvlParseLength.longValue);
<a name="163" href="#163">163</a>         incrementPosition(contentOffset);
<a name="164" href="#164">164</a>    
<a name="165" href="#165">165</a>     	<strong>return</strong> <strong>new</strong> <a href="../../../../org/archive/io/ArchiveRecordHeader.html">ArchiveRecordHeader</a>() {
<a name="166" href="#166">166</a>     		<strong>private</strong> Map&lt;Object, Object> fields = m;
<a name="167" href="#167">167</a>             <strong>private</strong> <strong>int</strong> contentBegin = contentOffset;
<a name="168" href="#168">168</a> 
<a name="169" href="#169">169</a> 			<strong>public</strong> String getDate() {
<a name="170" href="#170">170</a> 				<strong>return</strong> (String)<strong>this</strong>.fields.get(DATE_FIELD_KEY);
<a name="171" href="#171">171</a> 			}
<a name="172" href="#172">172</a> 
<a name="173" href="#173">173</a> 			<strong>public</strong> String getDigest() {
<a name="174" href="#174">174</a> 				<strong>return</strong> (String)<strong>this</strong>.fields.get(NAMED_FIELD_CHECKSUM_LABEL);
<a name="175" href="#175">175</a> 			}
<a name="176" href="#176">176</a> 
<a name="177" href="#177">177</a> 			<strong>public</strong> String getReaderIdentifier() {
<a name="178" href="#178">178</a> 				<strong>return</strong> (String)<strong>this</strong>.fields.get(READER_IDENTIFIER_FIELD_KEY);
<a name="179" href="#179">179</a> 			}
<a name="180" href="#180">180</a> 
<a name="181" href="#181">181</a> 			<strong>public</strong> Set getHeaderFieldKeys() {
<a name="182" href="#182">182</a> 				<strong>return</strong> <strong>this</strong>.fields.keySet();
<a name="183" href="#183">183</a> 			}
<a name="184" href="#184">184</a> 
<a name="185" href="#185">185</a> 			<strong>public</strong> Map getHeaderFields() {
<a name="186" href="#186">186</a> 				<strong>return</strong> <strong>this</strong>.fields;
<a name="187" href="#187">187</a> 			}
<a name="188" href="#188">188</a> 
<a name="189" href="#189">189</a> 			<strong>public</strong> Object getHeaderValue(String key) {
<a name="190" href="#190">190</a> 				<strong>return</strong> <strong>this</strong>.fields.get(key);
<a name="191" href="#191">191</a> 			}
<a name="192" href="#192">192</a> 
<a name="193" href="#193">193</a> 			<strong>public</strong> <strong>long</strong> getLength() {
<a name="194" href="#194">194</a> 				Object o = <strong>this</strong>.fields.get(LENGTH_FIELD_KEY);
<a name="195" href="#195">195</a> 				<strong>if</strong> (o == <strong>null</strong>) {
<a name="196" href="#196">196</a> 					<strong>return</strong> -1;
<a name="197" href="#197">197</a> 				}
<a name="198" href="#198">198</a> 				<strong>return</strong> ((Long)o).longValue();
<a name="199" href="#199">199</a> 			}
<a name="200" href="#200">200</a> 
<a name="201" href="#201">201</a> 			<strong>public</strong> String getMimetype() {
<a name="202" href="#202">202</a> 				<strong>return</strong> (String)<strong>this</strong>.fields.get(MIMETYPE_FIELD_KEY);
<a name="203" href="#203">203</a> 			}
<a name="204" href="#204">204</a> 
<a name="205" href="#205">205</a> 			<strong>public</strong> <strong>long</strong> getOffset() {
<a name="206" href="#206">206</a> 				Object o = <strong>this</strong>.fields.get(ABSOLUTE_OFFSET_KEY);
<a name="207" href="#207">207</a> 				<strong>if</strong> (o == <strong>null</strong>) {
<a name="208" href="#208">208</a> 					<strong>return</strong> -1;
<a name="209" href="#209">209</a> 				}
<a name="210" href="#210">210</a> 				<strong>return</strong> ((Long)o).longValue();
<a name="211" href="#211">211</a> 			}
<a name="212" href="#212">212</a> 
<a name="213" href="#213">213</a> 			<strong>public</strong> String getRecordIdentifier() {
<a name="214" href="#214">214</a> 				<strong>return</strong> (String)<strong>this</strong>.fields.get(RECORD_IDENTIFIER_FIELD_KEY);
<a name="215" href="#215">215</a> 			}
<a name="216" href="#216">216</a> 
<a name="217" href="#217">217</a> 			<strong>public</strong> String getUrl() {
<a name="218" href="#218">218</a> 				<strong>return</strong> (String)<strong>this</strong>.fields.get(URL_FIELD_KEY);
<a name="219" href="#219">219</a> 			}
<a name="220" href="#220">220</a> 
<a name="221" href="#221">221</a> 			<strong>public</strong> String getVersion() {
<a name="222" href="#222">222</a> 				<strong>return</strong> (String)<strong>this</strong>.fields.get(VERSION_FIELD_KEY);
<a name="223" href="#223">223</a> 			}
<a name="224" href="#224">224</a>             
<a name="225" href="#225">225</a>             <strong>public</strong> <strong>int</strong> getContentBegin() {
<a name="226" href="#226">226</a>                 <strong>return</strong> <strong>this</strong>.contentBegin;
<a name="227" href="#227">227</a>             }
<a name="228" href="#228">228</a>             
<a name="229" href="#229">229</a>             @Override