public class IndexingJob extends NutchTool implements Tool
currentJob, currentJobNum, numJobs, results, status| Constructor and Description |
|---|
IndexingJob() |
IndexingJob(Configuration conf) |
| Modifier and Type | Method and Description |
|---|---|
void |
index(Path crawlDb,
Path linkDb,
java.util.List<Path> segments,
boolean noCommit) |
void |
index(Path crawlDb,
Path linkDb,
java.util.List<Path> segments,
boolean noCommit,
boolean deleteGone) |
void |
index(Path crawlDb,
Path linkDb,
java.util.List<Path> segments,
boolean noCommit,
boolean deleteGone,
java.lang.String params) |
void |
index(Path crawlDb,
Path linkDb,
java.util.List<Path> segments,
boolean noCommit,
boolean deleteGone,
java.lang.String params,
boolean filter,
boolean normalize) |
void |
index(Path crawlDb,
Path linkDb,
java.util.List<Path> segments,
boolean noCommit,
boolean deleteGone,
java.lang.String params,
boolean filter,
boolean normalize,
boolean addBinaryContent) |
void |
index(Path crawlDb,
Path linkDb,
java.util.List<Path> segments,
boolean noCommit,
boolean deleteGone,
java.lang.String params,
boolean filter,
boolean normalize,
boolean addBinaryContent,
boolean base64) |
static void |
main(java.lang.String[] args) |
java.util.Map<java.lang.String,java.lang.Object> |
run(java.util.Map<java.lang.String,java.lang.Object> args,
java.lang.String crawlId)
Runs the tool, using a map of arguments.
|
int |
run(java.lang.String[] args) |
getProgress, getStatus, killJob, stopJobgetConf, setConfclone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitgetConf, setConfpublic IndexingJob()
public IndexingJob(Configuration conf)
public void index(Path crawlDb, Path linkDb, java.util.List<Path> segments, boolean noCommit) throws java.io.IOException, java.lang.InterruptedException, java.lang.ClassNotFoundException
java.io.IOExceptionjava.lang.InterruptedExceptionjava.lang.ClassNotFoundExceptionpublic void index(Path crawlDb, Path linkDb, java.util.List<Path> segments, boolean noCommit, boolean deleteGone) throws java.io.IOException, java.lang.InterruptedException, java.lang.ClassNotFoundException
java.io.IOExceptionjava.lang.InterruptedExceptionjava.lang.ClassNotFoundExceptionpublic void index(Path crawlDb, Path linkDb, java.util.List<Path> segments, boolean noCommit, boolean deleteGone, java.lang.String params) throws java.io.IOException, java.lang.InterruptedException, java.lang.ClassNotFoundException
java.io.IOExceptionjava.lang.InterruptedExceptionjava.lang.ClassNotFoundExceptionpublic void index(Path crawlDb, Path linkDb, java.util.List<Path> segments, boolean noCommit, boolean deleteGone, java.lang.String params, boolean filter, boolean normalize) throws java.io.IOException, java.lang.InterruptedException, java.lang.ClassNotFoundException
java.io.IOExceptionjava.lang.InterruptedExceptionjava.lang.ClassNotFoundExceptionpublic void index(Path crawlDb, Path linkDb, java.util.List<Path> segments, boolean noCommit, boolean deleteGone, java.lang.String params, boolean filter, boolean normalize, boolean addBinaryContent) throws java.io.IOException, java.lang.InterruptedException, java.lang.ClassNotFoundException
java.io.IOExceptionjava.lang.InterruptedExceptionjava.lang.ClassNotFoundExceptionpublic void index(Path crawlDb, Path linkDb, java.util.List<Path> segments, boolean noCommit, boolean deleteGone, java.lang.String params, boolean filter, boolean normalize, boolean addBinaryContent, boolean base64) throws java.io.IOException, java.lang.InterruptedException, java.lang.ClassNotFoundException
java.io.IOExceptionjava.lang.InterruptedExceptionjava.lang.ClassNotFoundExceptionpublic int run(java.lang.String[] args)
throws java.lang.Exception
public static void main(java.lang.String[] args)
throws java.lang.Exception
java.lang.Exceptionpublic java.util.Map<java.lang.String,java.lang.Object> run(java.util.Map<java.lang.String,java.lang.Object> args,
java.lang.String crawlId)
throws java.lang.Exception
NutchToolCopyright © 2019 The Apache Software Foundation