serialized-form.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

<PRE>
long <B>earliestNextURIEmitTime</B></PRE>
<DL>
<DL>
</DL>
</DL>

<P>
<A NAME="org.archive.crawler.datamodel.CrawlOrder"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#CCCCFF" CLASS="TableSubHeadingColor">
<TH ALIGN="left" COLSPAN="2"><FONT SIZE="+2">
<B>Class <A HREF="org/archive/crawler/datamodel/CrawlOrder.html" title="class in org.archive.crawler.datamodel">org.archive.crawler.datamodel.CrawlOrder</A> extends <A HREF="org/archive/crawler/settings/ModuleType.html" title="class in org.archive.crawler.settings">ModuleType</A> implements Serializable</B></FONT></TH>
</TR>
</TABLE>

<P>

<P>
<A NAME="org.archive.crawler.datamodel.CrawlServer"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#CCCCFF" CLASS="TableSubHeadingColor">
<TH ALIGN="left" COLSPAN="2"><FONT SIZE="+2">
<B>Class <A HREF="org/archive/crawler/datamodel/CrawlServer.html" title="class in org.archive.crawler.datamodel">org.archive.crawler.datamodel.CrawlServer</A> extends java.lang.Object implements Serializable</B></FONT></TH>
</TR>
</TABLE>

<P>
<A NAME="serialized_methods"><!-- --></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>Serialization Methods</B></FONT></TH>
</TR>
</TABLE>

<P>
<A NAME="readObject(java.io.ObjectInputStream)"><!-- --></A><H3>
readObject</H3>
<PRE>
private void <B>readObject</B>(java.io.ObjectInputStream&nbsp;stream)
                 throws java.io.IOException,
                        java.lang.ClassNotFoundException</PRE>
<DL>
<DD>Called when object is being deserialized.
 In addition to the default java deserialization, this method
 re-establishes the references to settings handler and robots honoring
 policy.
<P>
<DD><DL>

<DT><B>Throws:</B>
<DD><CODE>java.io.IOException</CODE> - if I/O errors occur
<DD><CODE>java.lang.ClassNotFoundException</CODE> - If the class for an object being restored
         cannot be found.</DD>
</DL>
</DL>
<A NAME="serializedForm"><!-- --></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>Serialized Fields</B></FONT></TH>
</TR>
</TABLE>

<H3>
server</H3>
<PRE>
java.lang.String <B>server</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>
<H3>
port</H3>
<PRE>
int <B>port</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>
<H3>
robots</H3>
<PRE>
<A HREF="org/archive/crawler/datamodel/RobotsExclusionPolicy.html" title="class in org.archive.crawler.datamodel">RobotsExclusionPolicy</A> <B>robots</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>
<H3>
robotsFetched</H3>
<PRE>
long <B>robotsFetched</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>
<H3>
validRobots</H3>
<PRE>
boolean <B>validRobots</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>
<H3>
robotstxtChecksum</H3>
<PRE>
java.util.zip.Checksum <B>robotstxtChecksum</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>
<H3>
substats</H3>
<PRE>
<A HREF="org/archive/crawler/datamodel/CrawlSubstats.html" title="class in org.archive.crawler.datamodel">CrawlSubstats</A> <B>substats</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>
<H3>
consecutiveConnectionErrors</H3>
<PRE>
int <B>consecutiveConnectionErrors</B></PRE>
<DL>
<DL>
</DL>
</DL>

<P>
<A NAME="org.archive.crawler.datamodel.CrawlSubstats"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#CCCCFF" CLASS="TableSubHeadingColor">
<TH ALIGN="left" COLSPAN="2"><FONT SIZE="+2">
<B>Class <A HREF="org/archive/crawler/datamodel/CrawlSubstats.html" title="class in org.archive.crawler.datamodel">org.archive.crawler.datamodel.CrawlSubstats</A> extends java.lang.Object implements Serializable</B></FONT></TH>
</TR>
</TABLE>

<P>
<A NAME="serializedForm"><!-- --></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>Serialized Fields</B></FONT></TH>
</TR>
</TABLE>

<H3>
fetchSuccesses</H3>
<PRE>
long <B>fetchSuccesses</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>
<H3>
fetchResponses</H3>
<PRE>
long <B>fetchResponses</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>
<H3>
successBytes</H3>
<PRE>
long <B>successBytes</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>
<H3>
totalBytes</H3>
<PRE>
long <B>totalBytes</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>
<H3>
fetchNonResponses</H3>
<PRE>
long <B>fetchNonResponses</B></PRE>
<DL>
<DL>
</DL>
</DL>

<P>
<A NAME="org.archive.crawler.datamodel.CrawlURI"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#CCCCFF" CLASS="TableSubHeadingColor">
<TH ALIGN="left" COLSPAN="2"><FONT SIZE="+2">
<B>Class <A HREF="org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">org.archive.crawler.datamodel.CrawlURI</A> extends <A HREF="org/archive/crawler/datamodel/CandidateURI.html" title="class in org.archive.crawler.datamodel">CandidateURI</A> implements Serializable</B></FONT></TH>
</TR>
</TABLE>

<P>
<A NAME="serialized_methods"><!-- --></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>Serialization Methods</B></FONT></TH>
</TR>
</TABLE>

<P>
<A NAME="readObject(java.io.ObjectInputStream)"><!-- --></A><H3>
readObject</H3>
<PRE>
private void <B>readObject</B>(java.io.ObjectInputStream&nbsp;stream)
                 throws java.io.IOException,
                        java.lang.ClassNotFoundException</PRE>
<DL>
<DD>Custom deserialization recreating empty HashSet from null in 'outLinks'
 slot.
<P>
<DD><DL>

<DT><B>Throws:</B>
<DD><CODE>java.io.IOException</CODE>
<DD><CODE>java.lang.ClassNotFoundException</CODE></DD>
</DL>
</DL>
<HR>
<A NAME="writeObject(java.io.ObjectOutputStream)"><!-- --></A><H3>
writeObject</H3>
<PRE>
private void <B>writeObject</B>(java.io.ObjectOutputStream&nbsp;stream)
                  throws java.io.IOException</PRE>
<DL>
<DD>Custom serialization writing an empty 'outLinks' as null. Estimated
 to save ~20 bytes in serialized form.
<P>
<DD><DL>

<DT><B>Throws:</B>
<DD><CODE>java.io.IOException</CODE></DD>
</DL>
</DL>
<A NAME="serializedForm"><!-- --></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>Serialized Fields</B></FONT></TH>
</TR>
</TABLE>

<H3>
fetchStatus</H3>
<PRE>
int <B>fetchStatus</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>
<H3>
deferrals</H3>
<PRE>
int <B>deferrals</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>
<H3>
fetchAttempts</H3>
<PRE>
int <B>fetchAttempts</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>
<H3>
linkHopCount</H3>
<PRE>
int <B>linkHopCount</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>
<H3>
embedHopCount</H3>
<PRE>
int <B>embedHopCount</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>
<H3>
userAgent</H3>
<PRE>
java.lang.String <B>userAgent</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>
<H3>
contentSize</H3>
<PRE>
long <B>contentSize</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>
<H3>
contentLength</H3>
<PRE>
long <B>contentLength</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>
<H3>
contentType</H3>
<PRE>
java.lang.String <B>contentType</B></PRE>
<DL>
<DD>Content type of a successfully fetched URI.

 May be null even on successfully fetched URI.
<P>
<DL>
</DL>
</DL>
<HR>
<H3>
prerequisite</H3>
<PRE>
boolean <B>prerequisite</B></PRE>
<DL>
<DD>True if this CrawlURI has been deemed a prerequisite by the
 <A HREF="org/archive/crawler/prefetch/PreconditionEnforcer.html" title="class in org.archive.crawler.prefetch"><CODE>PreconditionEnforcer</CODE></A>.

 This flag is used at least inside in the precondition enforcer so that
 subsequent prerequisite tests know to let this CrawlURI through because
 its a prerequisite needed by an earlier prerequisite tests (e.g. If
 this is a robots.txt, then the subsequent login credentials prereq
 test must not throw it out because its not a login curi).
<P>
<DL>
</DL>
</DL>
<HR>
<H3>
post</H3>
<PRE>
boolean <B>post</B></PRE>
<DL>
<DD>Set to true if this <code>curi</code> is to be POST'd rather than GET-d.
<P>
<DL>
</DL>
</DL>
<HR>
<H3>
ordinal</H3>
<PRE>
long <B>ordinal</B></PRE>
<DL>
<DD>Monotonically increasing number within a crawl;
 useful for tending towards breadth-first ordering.
 Will sometimes be truncated to 48 bits, so behavior
 over 281 trillion instantiated CrawlURIs may be 
 buggy
<P>
<DL>
</DL>
</DL>
<HR>
<H3>
cachedCrawlURIString</H3>
<PRE>
java.lang.String <B>cachedCrawlURIString</B></PRE>
<DL>
<DD>Cache of this candidate uuri as a string.

 Profiling shows us spending about 1-2% of total elapsed time in
 toString.
<P>
<DL>
</DL>
</DL>
<HR>
<H3>
contentDigest</H3>
<PRE>
byte[] <B>contentDigest</B></PRE>
<DL>
<DD>A digest (hash, usually SHA1) of retrieved content-body.
<P>
<DL>
</DL>
</DL>
<HR>
<H3>
contentDigestScheme</H3>
<PRE>
java.lang.String <B>contentDigestScheme</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>
<H3>
holderCost</H3>
<PRE>
int <B>holderCost</B></PRE>
<DL>