surt.html
来自「网络爬虫开源代码」· HTML 代码 · 共 223 行 · 第 1/2 页
HTML
223 行
<a name="104" href="#104">104</a> <strong>public</strong> <strong>static</strong> String fromURI(String s) {<a name="105" href="#105">105</a> <strong>return</strong> fromURI(s,false);<a name="106" href="#106">106</a> }<a name="107" href="#107">107</a> <a name="108" href="#108">108</a> <em>/**<em>*</em></em><a name="109" href="#109">109</a> <em> * Utility method for creating the SURT form of the URI in the</em><a name="110" href="#110">110</a> <em> * given String.</em><a name="111" href="#111">111</a> <em> * </em><a name="112" href="#112">112</a> <em> * If it appears a bit convoluted in its approach, note that it was</em><a name="113" href="#113">113</a> <em> * optimized to minimize object-creation after allocation-sites profiling </em><a name="114" href="#114">114</a> <em> * indicated this method was a top source of garbage in long-running crawls.</em><a name="115" href="#115">115</a> <em> * </em><a name="116" href="#116">116</a> <em> * Assumes that the String URI has already been cleaned/fixed (eg</em><a name="117" href="#117">117</a> <em> * by UURI fixup) in ways that put it in its crawlable form for </em><a name="118" href="#118">118</a> <em> * evaluation.</em><a name="119" href="#119">119</a> <em> * </em><a name="120" href="#120">120</a> <em> * @param s String URI to be converted to SURT form</em><a name="121" href="#121">121</a> <em> * @param preserveCase whether original case should be preserved</em><a name="122" href="#122">122</a> <em> * @return SURT form </em><a name="123" href="#123">123</a> <em> */</em><a name="124" href="#124">124</a> <strong>public</strong> <strong>static</strong> String fromURI(String s, <strong>boolean</strong> preserveCase) {<a name="125" href="#125">125</a> Matcher m = TextUtils.getMatcher(URI_SPLITTER,s);<a name="126" href="#126">126</a> <strong>if</strong>(!m.matches()) {<a name="127" href="#127">127</a> <em class="comment">// not an authority-based URI scheme; return unchanged</em><a name="128" href="#128">128</a> TextUtils.recycleMatcher(m);<a name="129" href="#129">129</a> <strong>return</strong> s;<a name="130" href="#130">130</a> }<a name="131" href="#131">131</a> <em class="comment">// preallocate enough space for SURT form, which includes</em><a name="132" href="#132">132</a> <em class="comment">// 3 extra characters ('(', ')', and one more ',' than '.'s</em><a name="133" href="#133">133</a> <em class="comment">// in original)</em><a name="134" href="#134">134</a> StringBuffer builder = <strong>new</strong> StringBuffer(s.length()+3);<a name="135" href="#135">135</a> append(builder,s,m.start(1),m.end(1)); <em class="comment">// scheme://</em><a name="136" href="#136">136</a> builder.append(BEGIN_TRANSFORMED_AUTHORITY); <em class="comment">// '('</em><a name="137" href="#137">137</a> <a name="138" href="#138">138</a> <strong>if</strong>(m.start(4)>-1) {<a name="139" href="#139">139</a> <em class="comment">// dotted-quad ip match: don't reverse</em><a name="140" href="#140">140</a> append(builder,s,m.start(4),m.end(4));<a name="141" href="#141">141</a> } <strong>else</strong> {<a name="142" href="#142">142</a> <em class="comment">// other hostname match: do reverse</em><a name="143" href="#143">143</a> <strong>int</strong> hostSegEnd = m.end(5);<a name="144" href="#144">144</a> <strong>int</strong> hostStart = m.start(5); <a name="145" href="#145">145</a> <strong>for</strong>(<strong>int</strong> i = m.end(5)-1; i>=hostStart; i--) {<a name="146" href="#146">146</a> <strong>if</strong>(s.charAt(i-1)!=DOT && i > hostStart) {<a name="147" href="#147">147</a> <strong>continue</strong>;<a name="148" href="#148">148</a> }<a name="149" href="#149">149</a> append(builder,s,i,hostSegEnd); <em class="comment">// rev host segment</em><a name="150" href="#150">150</a> builder.append(TRANSFORMED_HOST_DELIM); <em class="comment">// ','</em><a name="151" href="#151">151</a> hostSegEnd = i-1;<a name="152" href="#152">152</a> }<a name="153" href="#153">153</a> }<a name="154" href="#154">154</a> <a name="155" href="#155">155</a> append(builder,s,m.start(6),m.end(6)); <em class="comment">// :port</em><a name="156" href="#156">156</a> append(builder,s,m.start(3),m.end(3)); <em class="comment">// at</em><a name="157" href="#157">157</a> append(builder,s,m.start(2),m.end(2)); <em class="comment">// userinfo</em><a name="158" href="#158">158</a> builder.append(END_TRANSFORMED_AUTHORITY); <em class="comment">// ')'</em><a name="159" href="#159">159</a> append(builder,s,m.start(7),m.end(7)); <em class="comment">// path</em><a name="160" href="#160">160</a> <strong>if</strong> (!preserveCase) {<a name="161" href="#161">161</a> <strong>for</strong>(<strong>int</strong> i = 0; i < builder.length(); i++) {<a name="162" href="#162">162</a> builder.setCharAt(i,Character.toLowerCase(builder.charAt((i))));<a name="163" href="#163">163</a> }<a name="164" href="#164">164</a> }<a name="165" href="#165">165</a> TextUtils.recycleMatcher(m);<a name="166" href="#166">166</a> <strong>return</strong> builder.toString();<a name="167" href="#167">167</a> }<a name="168" href="#168">168</a> <a name="169" href="#169">169</a> <strong>private</strong> <strong>static</strong> <strong>void</strong> append(StringBuffer b, CharSequence cs, <strong>int</strong> start, <a name="170" href="#170">170</a> <strong>int</strong> end) {<a name="171" href="#171">171</a> <strong>if</strong> (start < 0) {<a name="172" href="#172">172</a> <strong>return</strong>;<a name="173" href="#173">173</a> }<a name="174" href="#174">174</a> b.append(cs, start, end);<a name="175" href="#175">175</a> }<a name="176" href="#176">176</a> <a name="177" href="#177">177</a> <em>/**<em>*</em></em><a name="178" href="#178">178</a> <em> * Allow class to be used as a command-line tool for converting </em><a name="179" href="#179">179</a> <em> * URL lists (or naked host or host/path fragments implied</em><a name="180" href="#180">180</a> <em> * to be HTTP URLs) to SURT form. Lines that cannot be converted</em><a name="181" href="#181">181</a> <em> * are returned unchanged. </em><a name="182" href="#182">182</a> <em> * </em><a name="183" href="#183">183</a> <em> *</em><a name="184" href="#184">184</a> <em> * Read from stdin or first file argument. Writes to stdout or </em><a name="185" href="#185">185</a> <em> * second argument filename</em><a name="186" href="#186">186</a> <em> * </em><a name="187" href="#187">187</a> <em> * @param args cmd-line arguments</em><a name="188" href="#188">188</a> <em> * @throws IOException</em><a name="189" href="#189">189</a> <em> */</em><a name="190" href="#190">190</a> <strong>public</strong> <strong>static</strong> <strong>void</strong> main(String[] args) throws IOException {<a name="191" href="#191">191</a> InputStream in = args.length > 0 ? <strong>new</strong> BufferedInputStream(<a name="192" href="#192">192</a> <strong>new</strong> FileInputStream(args[0])) : System.in;<a name="193" href="#193">193</a> PrintStream out = args.length > 1 ? <strong>new</strong> PrintStream(<a name="194" href="#194">194</a> <strong>new</strong> BufferedOutputStream(<strong>new</strong> FileOutputStream(args[1])))<a name="195" href="#195">195</a> : System.out;<a name="196" href="#196">196</a> BufferedReader br =<a name="197" href="#197">197</a> <strong>new</strong> BufferedReader(<strong>new</strong> InputStreamReader(in));<a name="198" href="#198">198</a> String line;<a name="199" href="#199">199</a> <strong>while</strong>((line = br.readLine())!=<strong>null</strong>) {<a name="200" href="#200">200</a> <strong>if</strong>(line.indexOf(<span class="string">"#"</span>)>0) line=line.substring(0,line.indexOf(<span class="string">"#"</span>));<a name="201" href="#201">201</a> line = line.trim();<a name="202" href="#202">202</a> <strong>if</strong>(line.length()==0) <strong>continue</strong>;<a name="203" href="#203">203</a> line = ArchiveUtils.addImpliedHttpIfNecessary(line);<a name="204" href="#204">204</a> out.println(SURT.fromURI(line));<a name="205" href="#205">205</a> }<a name="206" href="#206">206</a> br.close();<a name="207" href="#207">207</a> out.close();<a name="208" href="#208">208</a> }<a name="209" href="#209">209</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?