📄 mirrorwriterprocessor.html
字号:
<a name="131" href="#131">131</a> <em>/**<em>*</em></em><a name="132" href="#132">132</a> <em> * Key to use asking settings for maximum file system path length.</em><a name="133" href="#133">133</a> <em> */</em><a name="134" href="#134">134</a> <strong>public</strong> <strong>static</strong> <strong>final</strong> String ATTR_MAX_PATH_LEN = <span class="string">"max-path-length"</span>;<a name="135" href="#135">135</a> <a name="136" href="#136">136</a> <em>/**<em>*</em></em><a name="137" href="#137">137</a> <em> * Key to use asking settings for maximum file system path segment length.</em><a name="138" href="#138">138</a> <em> */</em><a name="139" href="#139">139</a> <strong>public</strong> <strong>static</strong> <strong>final</strong> String ATTR_MAX_SEG_LEN = <span class="string">"max-segment-length"</span>;<a name="140" href="#140">140</a> <a name="141" href="#141">141</a> <em>/**<em>*</em></em><a name="142" href="#142">142</a> <em> * Key to use asking settings for base directory path value.</em><a name="143" href="#143">143</a> <em> */</em><a name="144" href="#144">144</a> <strong>public</strong> <strong>static</strong> <strong>final</strong> String ATTR_PATH = <span class="string">"path"</span>;<a name="145" href="#145">145</a> <a name="146" href="#146">146</a> <em>/**<em>*</em></em><a name="147" href="#147">147</a> <em> * Key to use asking settings for port directory option.</em><a name="148" href="#148">148</a> <em> */</em><a name="149" href="#149">149</a> <strong>public</strong> <strong>static</strong> <strong>final</strong> String ATTR_PORT_DIRECTORY = <span class="string">"port-directory"</span>;<a name="150" href="#150">150</a> <a name="151" href="#151">151</a> <em>/**<em>*</em></em><a name="152" href="#152">152</a> <em> * Key to use asking settings for suffix at end option.</em><a name="153" href="#153">153</a> <em> */</em><a name="154" href="#154">154</a> <strong>public</strong> <strong>static</strong> <strong>final</strong> String ATTR_SUFFIX_AT_END = <span class="string">"suffix-at-end"</span>;<a name="155" href="#155">155</a> <a name="156" href="#156">156</a> <em>/**<em>*</em></em><a name="157" href="#157">157</a> <em> * Key to use asking settings for too-long directory.</em><a name="158" href="#158">158</a> <em> */</em><a name="159" href="#159">159</a> <strong>public</strong> <strong>static</strong> <strong>final</strong> String ATTR_TOO_LONG_DIRECTORY = <span class="string">"too-long-directory"</span>;<a name="160" href="#160">160</a> <a name="161" href="#161">161</a> <em>/**<em>*</em></em><a name="162" href="#162">162</a> <em> * Key to use asking settings for underscore set.</em><a name="163" href="#163">163</a> <em> */</em><a name="164" href="#164">164</a> <strong>public</strong> <strong>static</strong> <strong>final</strong> String ATTR_UNDERSCORE_SET = <span class="string">"underscore-set"</span>;<a name="165" href="#165">165</a> <a name="166" href="#166">166</a> <em>/**<em>* Default value for ATTR_DOT_BEGIN.*/</em></em><a name="167" href="#167">167</a> <strong>private</strong> <strong>static</strong> <strong>final</strong> String DEFAULT_DOT_BEGIN = <span class="string">"%2E"</span>;<a name="168" href="#168">168</a> <a name="169" href="#169">169</a> <em>/**<em>* Default maximum file system path length.*/</em></em><a name="170" href="#170">170</a> <strong>private</strong> <strong>static</strong> <strong>final</strong> <strong>int</strong> DEFAULT_MAX_PATH_LEN = 1023;<a name="171" href="#171">171</a> <a name="172" href="#172">172</a> <em>/**<em>* Default maximum file system path segment length.*/</em></em><a name="173" href="#173">173</a> <strong>private</strong> <strong>static</strong> <strong>final</strong> <strong>int</strong> DEFAULT_MAX_SEG_LEN = 255;<a name="174" href="#174">174</a> <a name="175" href="#175">175</a> <em>/**<em>* Default value for ATTR_TOO_LONG_DIRECTORY.*/</em></em><a name="176" href="#176">176</a> <strong>private</strong> <strong>static</strong> <strong>final</strong> String DEFAULT_TOO_LONG_DIRECTORY = <span class="string">"LONG"</span>;<a name="177" href="#177">177</a> <a name="178" href="#178">178</a> <em>/**<em>* An empty Map.*/</em></em><a name="179" href="#179">179</a> <strong>private</strong> <strong>static</strong> <strong>final</strong> Map EMPTY_MAP = <strong>new</strong> TreeMap();<a name="180" href="#180">180</a> <a name="181" href="#181">181</a> <em>/**<em>*</em></em><a name="182" href="#182">182</a> <em> Regular expression matching a file system path segment.</em><a name="183" href="#183">183</a> <em> The intent is one or more non-file-separator characters.</em><a name="184" href="#184">184</a> <em> The backslash is to quote File.separator if it's also backslash.</em><a name="185" href="#185">185</a> <em> */</em><a name="186" href="#186">186</a> <strong>private</strong> <strong>static</strong> <strong>final</strong> String PATH_SEGMENT_RE =<a name="187" href="#187">187</a> <span class="string">"[^//"</span> + File.separator + <span class="string">"]+"</span>;<a name="188" href="#188">188</a> <a name="189" href="#189">189</a> <em>/**<em>*</em></em><a name="190" href="#190">190</a> <em> Regular expression constraint on ATTR_DIRECTORY_FILE.</em><a name="191" href="#191">191</a> <em> The intent is one non-file-separator character,</em><a name="192" href="#192">192</a> <em> followed by zero or more characters.</em><a name="193" href="#193">193</a> <em> The backslash is to quote File.separator if it's also backslash.</em><a name="194" href="#194">194</a> <em> */</em><a name="195" href="#195">195</a> <strong>private</strong> <strong>static</strong> <strong>final</strong> String TOO_LONG_DIRECTORY_RE =<a name="196" href="#196">196</a> <span class="string">"[^//"</span> + File.separator + <span class="string">"].*"</span>;<a name="197" href="#197">197</a> <a name="198" href="#198">198</a> <em>/**<em>*</em></em><a name="199" href="#199">199</a> <em> * Logger.</em><a name="200" href="#200">200</a> <em> */</em><a name="201" href="#201">201</a> <strong>private</strong> <strong>static</strong> <strong>final</strong> Logger logger =<a name="202" href="#202">202</a> Logger.getLogger(MirrorWriterProcessor.<strong>class</strong>.getName());<a name="203" href="#203">203</a> <a name="204" href="#204">204</a> <em>/**<em>*</em></em><a name="205" href="#205">205</a> <em> * @param name Name of this processor.</em><a name="206" href="#206">206</a> <em> */</em><a name="207" href="#207">207</a> <strong>public</strong> <a href="../../../../org/archive/crawler/writer/MirrorWriterProcessor.html">MirrorWriterProcessor</a>(String name) {<a name="208" href="#208">208</a> <strong>super</strong>(name, <span class="string">"MirrorWriter processor. "</span> +<a name="209" href="#209">209</a> <span class="string">"A writer that writes each URL to a file on disk named for "</span> +<a name="210" href="#210">210</a> <span class="string">"a derivative of the URL."</span>);<a name="211" href="#211">211</a> <a href="../../../../org/archive/crawler/settings/Type.html">Type</a> e; <em class="comment">// Current element.</em><a name="212" href="#212">212</a> addElementToDefinition(<strong>new</strong> <a href="../../../../org/archive/crawler/settings/SimpleType.html">SimpleType</a>(ATTR_CASE_SENSITIVE,<a name="213" href="#213">213</a> <span class="string">"True if the file system is case-sensitive, like UNIX. "</span><a name="214" href="#214">214</a> + <span class="string">"False if the file system is case-insensitive, "</span><a name="215" href="#215">215</a> + <span class="string">"like Macintosh HFS+ and Windows."</span>,<a name="216" href="#216">216</a> Boolean.TRUE));<a name="217" href="#217">217</a> addElementToDefinition(<strong>new</strong> <a href="../../../../org/archive/crawler/settings/StringList.html">StringList</a>(ATTR_CHAR_MAP,<a name="218" href="#218">218</a> <span class="string">"This list is grouped in pairs. "</span><a name="219" href="#219">219</a> + <span class="string">"The first string in each pair must have a length of one. "</span><a name="220" href="#220">220</a> + <span class="string">"If it occurs in a URI path, "</span><a name="221" href="#221">221</a> + <span class="string">"it is replaced by the second string in the pair. "</span><a name="222" href="#222">222</a> + <span class="string">"For UNIX, no character mapping is normally needed. "</span><a name="223" href="#223">223</a> + <span class="string">"For Macintosh, the recommended value is [: %%3A]. "</span><a name="224" href="#224">224</a> + <span class="string">"For Windows, the recommended value is "</span><a name="225" href="#225">225</a> + <span class="string">"[' ' %%20 &quot; %%22 * %%2A : %%3A < %%3C "</span><a name="226" href="#226">226</a> + <span class="string">"//> %%3E ? %%3F //// %%5C ^ %%5E | %%7C]."</span>));<a name="227" href="#227">227</a> addElementToDefinition(<strong>new</strong> <a href="../../../../org/archive/crawler/settings/StringList.html">StringList</a>(ATTR_CONTENT_TYPE_MAP,<a name="228" href="#228">228</a> <span class="string">"This list is grouped in pairs. "</span><a name="229" href="#229">229</a> + <span class="string">"If the content type of a resource begins (case-insensitive) "</span><a name="230" href="#230">230</a> + <span class="string">"with the first string in a pair, the suffix is set to "</span><a name="231" href="#231">231</a> + <span class="string">"the second string in the pair, replacing any suffix that may "</span><a name="232" href="#232">232</a> + <span class="string">"have been in the URI. For example, to force all HTML files "</span><a name="233" href="#233">233</a> + <span class="string">"to have the same suffix, use [text/html html]."</span>));<a name="234" href="#234">234</a> e = addElementToDefinition(<strong>new</strong> <a href="../../../../org/archive/crawler/settings/SimpleType.html">SimpleType</a>(ATTR_DIRECTORY_FILE,<a name="235" href="#235">235</a> <span class="string">"Implicitly append this to a URI ending with '/'."</span>,<a name="236" href="#236">236</a> <span class="string">"index.html"</span>));<a name="237" href="#237">237</a> e.addConstraint(<strong>new</strong> <a href="../../../../org/archive/crawler/settings/RegularExpressionConstraint.html">RegularExpressionConstraint</a>(PATH_SEGMENT_RE,<a name="238" href="#238">238</a> Level.SEVERE, <span class="string">"This must be a simple file name."</span>));<a name="239" href="#239">239</a> e = addElementToDefinition(<strong>new</strong> <a href="../../../../org/archive/crawler/settings/SimpleType.html">SimpleType</a>(ATTR_DOT_BEGIN,<a name="240" href="#240">240</a> <span class="string">"If a segment starts with '.', the '.' is replaced by this."</span>,<a name="241" href="#241">241</a> DEFAULT_DOT_BEGIN));<a name="242" href="#242">242</a> e.addConstraint(<strong>new</strong> <a href="../../../../org/archive/crawler/settings/RegularExpressionConstraint.html">RegularExpressionConstraint</a>(PATH_SEGMENT_RE,<a name="243" href="#243">243</a> Level.SEVERE,<a name="244" href="#244">244</a> <span class="string">"This must not be empty, and must not contain "</span> + File.separator));<a name="245" href="#245">245</a> addElementToDefinition(<strong>new</strong> <a href="../../../../org/archive/crawler/settings/SimpleType.html">SimpleType</a>(ATTR_DOT_END,<a name="246" href="#246">246</a> <span class="string">"If a directory name ends with '.' it is replaced by this. "</span><a name="247" href="#247">247</a> + <span class="string">"For all file systems except Windows, '.' is recommended. "</span><a name="248" href="#248">248</a> + <span class="string">"For Windows, %%2E is recommended."</span>,<a name="249" href="#249">249</a> <span class="string">"."</span>));<a name="250" href="#250">250</a> addElementToDefinition(<strong>new</strong> <a href="../../../../org/archive/crawler/settings/StringList.html">StringList</a>(ATTR_HOST_MAP,<a name="251" href="#251">251</a> <span class="string">"This list is grouped in pairs. "</span><a name="252" href="#252">252</a> + <span class="string">"If a host name matches (case-insensitive) the first string "</span><a name="253" href="#253">253</a> + <span class="string">"in a pair, it is replaced by the second string in the pair. "</span><a name="254" href="#254">254</a> + <span class="string">"This can be used for consistency when several names are used "</span><a name="255" href="#255">255</a> + <span class="string">"for one host, for example "</span><a name="256" href="#256">256</a> + <span class="string">"[12.34.56.78 www42.foo.com]."</span>));<a name="257" href="#257">257</a> addElementToDefinition(<strong>new</strong> <a href="../../../../org/archive/crawler/settings/SimpleType.html">SimpleType</a>(ATTR_HOST_DIRECTORY,<a name="258" href="#258">258</a> <span class="string">"Create a subdirectory named for the host in the URI."</span>,<a name="259" href="#259">259</a> Boolean.TRUE));<a name="260" href="#260">260</a> addElementToDefinition(<strong>new</strong> <a href="../../../../org/archive/crawler/settings/SimpleType.html">SimpleType</a>(ATTR_PATH,<a name="261" href="#261">261</a> <span class="string">"Top-level directory for mirror files."</span>, <span class="string">"mirror"</span>));<a name="262" href="#262">262</a> <a name="263" href="#263">263</a> <em class="comment">// TODO: Add a new Constraint subclass so ATTR_MAX_PATH_LEN and</em><a name="264" href="#264">264</a> <em class="comment">// ATTR_MAX_SEG_LEN can be constained to reasonable values.</em><a name="265" href="#265">265</a> addElementToDefinition(<strong>new</strong> <a href="../../../../org/archive/crawler/settings/SimpleType.html">SimpleType</a>(ATTR_MAX_PATH_LEN,<a name="266" href="#266">266</a> <span class="string">"Maximum file system path length."</span>,<a name="267" href="#267">267</a> <strong>new</strong> Integer(DEFAULT_MAX_PATH_LEN)));<a name="268" href="#268">268</a> addElementToDefinition(<strong>new</strong> <a href="../../../../org/archive/crawler/settings/SimpleType.html">SimpleType</a>(ATTR_MAX_SEG_LEN,<a name="269" href="#269">269</a> <span class="string">"Maximum file system path segment length."</span>,
⌨️ 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 + -