writerpoolprocessor.html

来自「网络爬虫开源代码」· HTML 代码 · 共 1,138 行 · 第 1/5 页

<DL>
<DD>Default as to whether we do compression of files.
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.WriterPoolProcessor.DEFAULT_COMPRESS">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="ATTR_PREFIX"><!-- --></A><H3>
ATTR_PREFIX</H3>
<PRE>
public static final java.lang.String <B>ATTR_PREFIX</B></PRE>
<DL>
<DD>Key to use asking settings for file prefix value.
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.WriterPoolProcessor.ATTR_PREFIX">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="ATTR_PATH"><!-- --></A><H3>
ATTR_PATH</H3>
<PRE>
public static final java.lang.String <B>ATTR_PATH</B></PRE>
<DL>
<DD>Key to use asking settings for arc path value.
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.WriterPoolProcessor.ATTR_PATH">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="ATTR_SUFFIX"><!-- --></A><H3>
ATTR_SUFFIX</H3>
<PRE>
public static final java.lang.String <B>ATTR_SUFFIX</B></PRE>
<DL>
<DD>Key to use asking settings for file suffix value.
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.WriterPoolProcessor.ATTR_SUFFIX">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="ATTR_MAX_SIZE_BYTES"><!-- --></A><H3>
ATTR_MAX_SIZE_BYTES</H3>
<PRE>
public static final java.lang.String <B>ATTR_MAX_SIZE_BYTES</B></PRE>
<DL>
<DD>Key to use asking settings for file max size value.
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.WriterPoolProcessor.ATTR_MAX_SIZE_BYTES">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="ATTR_POOL_MAX_ACTIVE"><!-- --></A><H3>
ATTR_POOL_MAX_ACTIVE</H3>
<PRE>
public static final java.lang.String <B>ATTR_POOL_MAX_ACTIVE</B></PRE>
<DL>
<DD>Key to get maximum pool size.

 This key is for maximum files active in the pool.
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.WriterPoolProcessor.ATTR_POOL_MAX_ACTIVE">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="ATTR_POOL_MAX_WAIT"><!-- --></A><H3>
ATTR_POOL_MAX_WAIT</H3>
<PRE>
public static final java.lang.String <B>ATTR_POOL_MAX_WAIT</B></PRE>
<DL>
<DD>Key to get maximum wait on pool object before we give up and
 throw IOException.
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.WriterPoolProcessor.ATTR_POOL_MAX_WAIT">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="ATTR_MAX_BYTES_WRITTEN"><!-- --></A><H3>
ATTR_MAX_BYTES_WRITTEN</H3>
<PRE>
public static final java.lang.String <B>ATTR_MAX_BYTES_WRITTEN</B></PRE>
<DL>
<DD>Key for the maximum bytes to write attribute.
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.WriterPoolProcessor.ATTR_MAX_BYTES_WRITTEN">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="ATTR_SKIP_IDENTICAL_DIGESTS"><!-- --></A><H3>
ATTR_SKIP_IDENTICAL_DIGESTS</H3>
<PRE>
public static final java.lang.String <B>ATTR_SKIP_IDENTICAL_DIGESTS</B></PRE>
<DL>
<DD>Key for whether to skip writing records of content-digest repeats
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.WriterPoolProcessor.ATTR_SKIP_IDENTICAL_DIGESTS">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="ANNOTATION_UNWRITTEN"><!-- --></A><H3>
ANNOTATION_UNWRITTEN</H3>
<PRE>
protected static final java.lang.String <B>ANNOTATION_UNWRITTEN</B></PRE>
<DL>
<DD>CrawlURI annotation indicating no record was written
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.WriterPoolProcessor.ANNOTATION_UNWRITTEN">Constant Field Values</A></DL>
</DL>

<!-- ========= CONSTRUCTOR DETAIL ======== -->

<A NAME="constructor_detail"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
<TH ALIGN="left" COLSPAN="1"><FONT SIZE="+2">
<B>Constructor Detail</B></FONT></TH>
</TR>
</TABLE>

<A NAME="WriterPoolProcessor(java.lang.String)"><!-- --></A><H3>
WriterPoolProcessor</H3>
<PRE>
public <B>WriterPoolProcessor</B>(java.lang.String&nbsp;name)</PRE>
<DL>
<DL>
<DT><B>Parameters:</B><DD><CODE>name</CODE> - Name of this processor.</DL>
</DL>
<HR>

<A NAME="WriterPoolProcessor(java.lang.String, java.lang.String)"><!-- --></A><H3>
WriterPoolProcessor</H3>
<PRE>
public <B>WriterPoolProcessor</B>(java.lang.String&nbsp;name,
                           java.lang.String&nbsp;description)</PRE>
<DL>
<DL>
<DT><B>Parameters:</B><DD><CODE>name</CODE> - Name of this processor.<DD><CODE>description</CODE> - Description for this processor.</DL>
</DL>

<!-- ============ METHOD DETAIL ========== -->

<A NAME="method_detail"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
<TH ALIGN="left" COLSPAN="1"><FONT SIZE="+2">
<B>Method Detail</B></FONT></TH>
</TR>
</TABLE>

<A NAME="getDefaultPath()"><!-- --></A><H3>
getDefaultPath</H3>
<PRE>
protected java.lang.String[] <B>getDefaultPath</B>()</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="initialTasks()"><!-- --></A><H3>
initialTasks</H3>
<PRE>
public void <B>initialTasks</B>()</PRE>
<DL>
<DD><B>Description copied from class: <CODE><A HREF="../../../../org/archive/crawler/framework/Processor.html#initialTasks()">Processor</A></CODE></B></DD>
<DD>Classes subclassing this one should override this method to perform
 processor specific actions.
 <p>

 This method is garanteed to be called after the crawl is set up, but
 before any URI-processing has occured.
<P>
<DD><DL>
<DT><B>Overrides:</B><DD><CODE><A HREF="../../../../org/archive/crawler/framework/Processor.html#initialTasks()">initialTasks</A></CODE> in class <CODE><A HREF="../../../../org/archive/crawler/framework/Processor.html" title="class in org.archive.crawler.framework">Processor</A></CODE></DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="getSerialNo()"><!-- --></A><H3>
getSerialNo</H3>
<PRE>
protected java.util.concurrent.atomic.AtomicInteger <B>getSerialNo</B>()</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="setupPool(java.util.concurrent.atomic.AtomicInteger)"><!-- --></A><H3>
setupPool</H3>
<PRE>
protected abstract void <B>setupPool</B>(java.util.concurrent.atomic.AtomicInteger&nbsp;serialNo)</PRE>
<DL>
<DD>Set up pool of files.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="innerProcess(org.archive.crawler.datamodel.CrawlURI)"><!-- --></A><H3>
innerProcess</H3>
<PRE>
protected abstract void <B>innerProcess</B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</PRE>