warcconstants.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="101" href="#101">101</a> <em>     * </em>
<a name="102" href="#102">102</a> <em>     * &lt;p>TODO: ARC uses ISO-8859-1.  In general, we should use UTF-8 but we</em>
<a name="103" href="#103">103</a> <em>     * probably need a single byte encoding if we're out for preserving the</em>
<a name="104" href="#104">104</a> <em>     * binary data as received over the net (We probably don't want to transform</em>
<a name="105" href="#105">105</a> <em>     * the supra-ASCII characters to UTF-8 before storing in ARC).  For now,</em>
<a name="106" href="#106">106</a> <em>     * till we figure it, DEFAULT_ENCODING is single-byte charset -- same as</em>
<a name="107" href="#107">107</a> <em>     * ARCs.</em>
<a name="108" href="#108">108</a> <em>     */</em>
<a name="109" href="#109">109</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String DEFAULT_ENCODING = <span class="string">"ISO-8859-1"</span>;
<a name="110" href="#110">110</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String HEADER_LINE_ENCODING = DEFAULT_ENCODING;
<a name="111" href="#111">111</a>     
<a name="112" href="#112">112</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String [] HEADER_FIELD_KEYS = {
<a name="113" href="#113">113</a>         VERSION_FIELD_KEY,
<a name="114" href="#114">114</a>         LENGTH_FIELD_KEY,
<a name="115" href="#115">115</a>         TYPE_FIELD_KEY,
<a name="116" href="#116">116</a>         URL_FIELD_KEY,
<a name="117" href="#117">117</a>         DATE_FIELD_KEY,
<a name="118" href="#118">118</a>         RECORD_IDENTIFIER_FIELD_KEY,
<a name="119" href="#119">119</a>         MIMETYPE_FIELD_KEY
<a name="120" href="#120">120</a>     };
<a name="121" href="#121">121</a>     
<a name="122" href="#122">122</a>     <em>/**<em>*</em></em>
<a name="123" href="#123">123</a> <em>     * WARC Record Types.</em>
<a name="124" href="#124">124</a> <em>     */</em>
<a name="125" href="#125">125</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String WARCINFO = <span class="string">"warcinfo"</span>;
<a name="126" href="#126">126</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String RESPONSE = <span class="string">"response"</span>;
<a name="127" href="#127">127</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String RESOURCE = <span class="string">"resource"</span>;
<a name="128" href="#128">128</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String REQUEST = <span class="string">"request"</span>;
<a name="129" href="#129">129</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String METADATA = <span class="string">"metadata"</span>;
<a name="130" href="#130">130</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String REVISIT = <span class="string">"revist"</span>;
<a name="131" href="#131">131</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String CONVERSION = <span class="string">"conversion"</span>;
<a name="132" href="#132">132</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String CONTINUATION = <span class="string">"continuation"</span>;
<a name="133" href="#133">133</a>     
<a name="134" href="#134">134</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String TYPE = <span class="string">"type"</span>;
<a name="135" href="#135">135</a>     
<a name="136" href="#136">136</a>     <em class="comment">// List of all WARC Record TYPES</em>
<a name="137" href="#137">137</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String [] TYPES = {WARCINFO, RESPONSE, RESOURCE,
<a name="138" href="#138">138</a>     	REQUEST, METADATA, REVISIT, CONVERSION, CONTINUATION};
<a name="139" href="#139">139</a>     
<a name="140" href="#140">140</a>     <em class="comment">// Indices into TYPES array.</em>
<a name="141" href="#141">141</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> <strong>int</strong> WARCINFO_INDEX = 0;
<a name="142" href="#142">142</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> <strong>int</strong> RESPONSE_INDEX = 1;
<a name="143" href="#143">143</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> <strong>int</strong> RESOURCE_INDEX = 2;
<a name="144" href="#144">144</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> <strong>int</strong> REQUEST_INDEX = 3;
<a name="145" href="#145">145</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> <strong>int</strong> METADATA_INDEX = 4;
<a name="146" href="#146">146</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> <strong>int</strong> REVISIT_INDEX = 5;
<a name="147" href="#147">147</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> <strong>int</strong> CONVERSION_INDEX = 6;
<a name="148" href="#148">148</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> <strong>int</strong> CONTINUATION_INDEX = 7;
<a name="149" href="#149">149</a>     
<a name="150" href="#150">150</a>     <em class="comment">// TYPES as List.</em>
<a name="151" href="#151">151</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> List TYPES_LIST = Arrays.asList(TYPES);
<a name="152" href="#152">152</a>     
<a name="153" href="#153">153</a>     <em>/**<em>*</em></em>
<a name="154" href="#154">154</a> <em>     * WARC-ID</em>
<a name="155" href="#155">155</a> <em>     */</em>
<a name="156" href="#156">156</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String WARC_ID = WARC_MAGIC + WARC_VERSION;
<a name="157" href="#157">157</a>         
<a name="158" href="#158">158</a>     <em>/**<em>*</em></em>
<a name="159" href="#159">159</a> <em>     * Header field seperator character.</em>
<a name="160" href="#160">160</a> <em>     */</em>
<a name="161" href="#161">161</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> <strong>char</strong> HEADER_FIELD_SEPARATOR = ' ';
<a name="162" href="#162">162</a>     
<a name="163" href="#163">163</a>     <em>/**<em>*</em></em>
<a name="164" href="#164">164</a> <em>     * WSP</em>
<a name="165" href="#165">165</a> <em>     * One of a space or horizontal tab character.</em>
<a name="166" href="#166">166</a> <em>     * TODO: WSP undefined.  Fix.</em>
<a name="167" href="#167">167</a> <em>     */</em>
<a name="168" href="#168">168</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> Character [] WSP = {HEADER_FIELD_SEPARATOR, '\t'};
<a name="169" href="#169">169</a> 
<a name="170" href="#170">170</a>     <em>/**<em>*</em></em>
<a name="171" href="#171">171</a> <em>     * Placeholder for length in Header line.</em>
<a name="172" href="#172">172</a> <em>     * Placeholder is same size as the fixed field size allocated for length,</em>
<a name="173" href="#173">173</a> <em>     * 12 characters.  12 characters allows records of size almost 1TB.</em>
<a name="174" href="#174">174</a> <em>     */</em>
<a name="175" href="#175">175</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String PLACEHOLDER_RECORD_LENGTH_STRING =
<a name="176" href="#176">176</a>         <span class="string">"000000000000"</span>;
<a name="177" href="#177">177</a>     
<a name="178" href="#178">178</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String NAMED_FIELD_IP_LABEL = <span class="string">"IP-Address"</span>;
<a name="179" href="#179">179</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String NAMED_FIELD_CHECKSUM_LABEL = <span class="string">"Checksum"</span>;
<a name="180" href="#180">180</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String NAMED_FIELD_RELATED_LABEL = <span class="string">"Related-Record-ID"</span>;
<a name="181" href="#181">181</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String NAMED_FIELD_WARCFILENAME = <span class="string">"Filename"</span>;
<a name="182" href="#182">182</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String NAMED_FIELD_DESCRIPTION = <span class="string">"Description"</span>;
<a name="183" href="#183">183</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String NAMED_FIELD_FILEDESC = <span class="string">"ARC-FileDesc"</span>;
<a name="184" href="#184">184</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String NAMED_FIELD_TRUNCATED = <span class="string">"Truncated"</span>;
<a name="185" href="#185">185</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String NAMED_FIELD_TRUNCATED_VALUE_TIME = <span class="string">"time"</span>;
<a name="186" href="#186">186</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String NAMED_FIELD_TRUNCATED_VALUE_LEN = <span class="string">"length"</span>;
<a name="187" href="#187">187</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String NAMED_FIELD_TRUNCATED_VALUE_HEAD =
<a name="188" href="#188">188</a>         <span class="string">"long-headers"</span>;
<a name="189" href="#189">189</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String NAMED_FIELD_TRUNCATED_VALUE_UNSPECIFIED = <strong>null</strong>;
<a name="190" href="#190">190</a>     
<a name="191" href="#191">191</a>     <em>/**<em>*</em></em>
<a name="192" href="#192">192</a> <em>     * To be safe, lets use application type rather than message. Regards </em>
<a name="193" href="#193">193</a> <em>     * 'message/http', RFC says "...provided that it obeys the MIME restrictions</em>
<a name="194" href="#194">194</a> <em>     * for all 'message' types regarding line length and encodings."  This</em>
<a name="195" href="#195">195</a> <em>     * usually means lines of 1000 octets max (unless a </em>
<a name="196" href="#196">196</a> <em>     * 'Content-Transfer-Encoding: binary' mime header is present).</em>
<a name="197" href="#197">197</a> <em>     * @see &lt;a href="<a href="http://www.w3.org/Protocols/rfc2616/rfc2616-sec19.html" target="alexandria_uri">http://www.w3.org/Protocols/rfc2616/rfc2616-sec19.html</a>#sec19.1">rfc2616 section 19.1&lt;/a></em>
<a name="198" href="#198">198</a> <em>     */</em>
<a name="199" href="#199">199</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String HTTP_REQUEST_MIMETYPE =
<a name="200" href="#200">200</a>     	<span class="string">"application/http;msgtype=request"</span>;
<a name="201" href="#201">201</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String HTTP_RESPONSE_MIMETYPE =
<a name="202" href="#202">202</a>     	<span class="string">"application/http;msgtype=response"</span>;
<a name="203" href="#203">203</a> }
</pre>
<hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body>
</html>