warcrecord.html
来自「网络爬虫开源代码」· HTML 代码 · 共 237 行 · 第 1/2 页
HTML
237 行
<a name="111" href="#111">111</a> <strong>long</strong> startPosition = -1;<a name="112" href="#112">112</a> <strong>if</strong> (in instanceof RepositionableStream) {<a name="113" href="#113">113</a> startPosition = ((RepositionableStream)in).position();<a name="114" href="#114">114</a> }<a name="115" href="#115">115</a> String firstLine =<a name="116" href="#116">116</a> <strong>new</strong> String(HttpParser.readLine(in, WARC_HEADER_ENCODING));<a name="117" href="#117">117</a> <strong>if</strong> (firstLine == <strong>null</strong> || firstLine.length() <=0) {<a name="118" href="#118">118</a> <strong>throw</strong> <strong>new</strong> IOException(<span class="string">"Failed to read WARC_MAGIC"</span>);<a name="119" href="#119">119</a> }<a name="120" href="#120">120</a> <strong>if</strong> (!firstLine.startsWith(WARC_MAGIC)) {<a name="121" href="#121">121</a> <strong>throw</strong> <strong>new</strong> IOException(<span class="string">"Failed to find WARC MAGIC: "</span> + firstLine);<a name="122" href="#122">122</a> }<a name="123" href="#123">123</a> <em class="comment">// Here we start reading off the inputstream but we're reading the</em><a name="124" href="#124">124</a> <em class="comment">// stream direct rather than going via WARCRecord#read. The latter will</em><a name="125" href="#125">125</a> <em class="comment">// keep count of bytes read, digest and fail properly if EOR too soon...</em><a name="126" href="#126">126</a> <em class="comment">// We don't want digesting while reading Headers.</em><a name="127" href="#127">127</a> <em class="comment">// </em><a name="128" href="#128">128</a> Header [] h = HttpParser.parseHeaders(in, WARC_HEADER_ENCODING);<a name="129" href="#129">129</a> <strong>for</strong> (<strong>int</strong> i = 0; i < h.length; i++) {<a name="130" href="#130">130</a> m.put(h[i].getName(), h[i].getValue());<a name="131" href="#131">131</a> }<a name="132" href="#132">132</a> <strong>int</strong> headerLength = -1;<a name="133" href="#133">133</a> <strong>if</strong> (in instanceof RepositionableStream) {<a name="134" href="#134">134</a> headerLength =<a name="135" href="#135">135</a> (<strong>int</strong>)(((RepositionableStream)in).position() - startPosition);<a name="136" href="#136">136</a> }<a name="137" href="#137">137</a> <strong>final</strong> <strong>int</strong> contentOffset = headerLength;<a name="138" href="#138">138</a> incrementPosition(contentOffset);<a name="139" href="#139">139</a> <a name="140" href="#140">140</a> <strong>return</strong> <strong>new</strong> <a href="../../../../org/archive/io/ArchiveRecordHeader.html">ArchiveRecordHeader</a>() {<a name="141" href="#141">141</a> <strong>private</strong> Map<Object, Object> headers = m;<a name="142" href="#142">142</a> <strong>private</strong> <strong>int</strong> contentBegin = contentOffset;<a name="143" href="#143">143</a> <a name="144" href="#144">144</a> <strong>public</strong> String getDate() {<a name="145" href="#145">145</a> <strong>return</strong> (String)<strong>this</strong>.headers.get(HEADER_KEY_DATE);<a name="146" href="#146">146</a> }<a name="147" href="#147">147</a> <a name="148" href="#148">148</a> <strong>public</strong> String getDigest() {<a name="149" href="#149">149</a> <strong>return</strong> (String)<strong>this</strong>.headers.get(HEADER_KEY_CHECKSUM);<a name="150" href="#150">150</a> }<a name="151" href="#151">151</a> <a name="152" href="#152">152</a> <strong>public</strong> String getReaderIdentifier() {<a name="153" href="#153">153</a> <strong>return</strong> (String)<strong>this</strong>.headers.get(READER_IDENTIFIER_FIELD_KEY);<a name="154" href="#154">154</a> }<a name="155" href="#155">155</a> <a name="156" href="#156">156</a> <strong>public</strong> Set getHeaderFieldKeys() {<a name="157" href="#157">157</a> <strong>return</strong> <strong>this</strong>.headers.keySet();<a name="158" href="#158">158</a> }<a name="159" href="#159">159</a> <a name="160" href="#160">160</a> <strong>public</strong> Map getHeaderFields() {<a name="161" href="#161">161</a> <strong>return</strong> <strong>this</strong>.headers;<a name="162" href="#162">162</a> }<a name="163" href="#163">163</a> <a name="164" href="#164">164</a> <strong>public</strong> Object getHeaderValue(String key) {<a name="165" href="#165">165</a> <strong>return</strong> <strong>this</strong>.headers.get(key);<a name="166" href="#166">166</a> }<a name="167" href="#167">167</a> <a name="168" href="#168">168</a> <strong>public</strong> <strong>long</strong> getLength() {<a name="169" href="#169">169</a> Object o = <strong>this</strong>.headers.get(CONTENT_LENGTH);<a name="170" href="#170">170</a> <strong>if</strong> (o == <strong>null</strong>) {<a name="171" href="#171">171</a> <strong>return</strong> -1;<a name="172" href="#172">172</a> }<a name="173" href="#173">173</a> <strong>long</strong> contentLength = (o instanceof Long)?<a name="174" href="#174">174</a> ((Long)o).longValue(): Long.parseLong((String)o);<a name="175" href="#175">175</a> <strong>return</strong> contentLength + contentOffset;<a name="176" href="#176">176</a> }<a name="177" href="#177">177</a> <a name="178" href="#178">178</a> <strong>public</strong> String getMimetype() {<a name="179" href="#179">179</a> <strong>return</strong> (String)<strong>this</strong>.headers.get(CONTENT_TYPE);<a name="180" href="#180">180</a> }<a name="181" href="#181">181</a> <a name="182" href="#182">182</a> <strong>public</strong> <strong>long</strong> getOffset() {<a name="183" href="#183">183</a> Object o = <strong>this</strong>.headers.get(ABSOLUTE_OFFSET_KEY);<a name="184" href="#184">184</a> <strong>if</strong> (o == <strong>null</strong>) {<a name="185" href="#185">185</a> <strong>return</strong> -1;<a name="186" href="#186">186</a> }<a name="187" href="#187">187</a> <strong>return</strong> (o instanceof Long)?<a name="188" href="#188">188</a> ((Long)o).longValue(): Long.parseLong((String)o);<a name="189" href="#189">189</a> }<a name="190" href="#190">190</a> <a name="191" href="#191">191</a> <strong>public</strong> String getRecordIdentifier() {<a name="192" href="#192">192</a> <strong>return</strong> (String)<strong>this</strong>.headers.get(RECORD_IDENTIFIER_FIELD_KEY);<a name="193" href="#193">193</a> }<a name="194" href="#194">194</a> <a name="195" href="#195">195</a> <strong>public</strong> String getUrl() {<a name="196" href="#196">196</a> <strong>return</strong> (String)<strong>this</strong>.headers.get(HEADER_KEY_URI);<a name="197" href="#197">197</a> }<a name="198" href="#198">198</a> <a name="199" href="#199">199</a> <strong>public</strong> String getVersion() {<a name="200" href="#200">200</a> <strong>return</strong> (String)<strong>this</strong>.headers.get(VERSION_FIELD_KEY);<a name="201" href="#201">201</a> }<a name="202" href="#202">202</a> <a name="203" href="#203">203</a> <strong>public</strong> <strong>int</strong> getContentBegin() {<a name="204" href="#204">204</a> <strong>return</strong> <strong>this</strong>.contentBegin;<a name="205" href="#205">205</a> }<a name="206" href="#206">206</a> <a name="207" href="#207">207</a> @Override<a name="208" href="#208">208</a> <strong>public</strong> String toString() {<a name="209" href="#209">209</a> <strong>return</strong> <strong>this</strong>.headers.toString();<a name="210" href="#210">210</a> }<a name="211" href="#211">211</a> };<a name="212" href="#212">212</a> }<a name="213" href="#213">213</a> <a name="214" href="#214">214</a> @Override<a name="215" href="#215">215</a> <strong>protected</strong> String getMimetype4Cdx(<a href="../../../../org/archive/io/ArchiveRecordHeader.html">ArchiveRecordHeader</a> h) {<a name="216" href="#216">216</a> <strong>final</strong> String m = <strong>super</strong>.getMimetype4Cdx(h);<a name="217" href="#217">217</a> <em class="comment">// Mimetypes can have spaces in WARCs. Emitting for CDX, just</em><a name="218" href="#218">218</a> <em class="comment">// squash them for now. Later, quote them since squashing spaces won't</em><a name="219" href="#219">219</a> <em class="comment">// work for params that have quoted-string values.</em><a name="220" href="#220">220</a> Matcher matcher = WHITESPACE.matcher(m);<a name="221" href="#221">221</a> <strong>return</strong> matcher.replaceAll(<span class="string">""</span>);<a name="222" href="#222">222</a> }<a name="223" href="#223">223</a> }</pre><hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body></html>
⌨️ 快捷键说明
复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?