org.galagosearch.core.tools
Class BuildIndex
java.lang.Object
org.galagosearch.core.tools.BuildIndex
public class BuildIndex
- extends java.lang.Object
- Author:
- trevor
|
Method Summary |
org.galagosearch.tupleflow.execution.Stage |
getCollectionLengthStage()
|
java.util.ArrayList<org.galagosearch.tupleflow.execution.Step> |
getExtractionSteps(java.lang.String outputName,
java.lang.Class extractionClass,
org.galagosearch.tupleflow.Order sortOrder)
|
org.galagosearch.tupleflow.execution.Job |
getIndexJob(java.lang.String indexDirectory,
java.lang.String[] indexInputs,
boolean extractAnchors,
boolean useStemming)
|
org.galagosearch.tupleflow.execution.Stage |
getLinkCombineStage()
|
org.galagosearch.tupleflow.execution.Stage |
getNumberDocumentsStage()
|
org.galagosearch.tupleflow.execution.Stage |
getNumberExtentsStage()
|
org.galagosearch.tupleflow.execution.Stage |
getNumberPostingsStage(java.lang.String stageName,
java.lang.String inputName,
java.lang.String outputName)
|
org.galagosearch.tupleflow.execution.Stage |
getParseLinksStage()
|
org.galagosearch.tupleflow.execution.Stage |
getParsePostingsStage()
|
org.galagosearch.tupleflow.execution.Stage |
getSplitStage(java.lang.String[] inputs)
|
org.galagosearch.tupleflow.execution.Stage |
getWriteDatesStage()
|
org.galagosearch.tupleflow.execution.Stage |
getWriteDocumentLengthsStage()
Writes document lengths to a document lengths file. |
org.galagosearch.tupleflow.execution.Stage |
getWriteDocumentNamesStage()
Writes document names to a document names file. |
org.galagosearch.tupleflow.execution.Stage |
getWriteExtentsStage()
|
org.galagosearch.tupleflow.execution.Stage |
getWriteManifestStage()
Write out document count and collection length information. |
org.galagosearch.tupleflow.execution.Stage |
getWritePostingsStage(java.lang.String stageName,
java.lang.String inputName,
java.lang.String indexName)
|
| Methods inherited from class java.lang.Object |
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
BuildIndex
public BuildIndex()
BuildIndex
public BuildIndex(java.lang.String indexPath)
getSplitStage
public org.galagosearch.tupleflow.execution.Stage getSplitStage(java.lang.String[] inputs)
throws java.io.IOException
- Throws:
java.io.IOException
getExtractionSteps
public java.util.ArrayList<org.galagosearch.tupleflow.execution.Step> getExtractionSteps(java.lang.String outputName,
java.lang.Class extractionClass,
org.galagosearch.tupleflow.Order sortOrder)
getParsePostingsStage
public org.galagosearch.tupleflow.execution.Stage getParsePostingsStage()
getParseLinksStage
public org.galagosearch.tupleflow.execution.Stage getParseLinksStage()
getLinkCombineStage
public org.galagosearch.tupleflow.execution.Stage getLinkCombineStage()
getCollectionLengthStage
public org.galagosearch.tupleflow.execution.Stage getCollectionLengthStage()
getWritePostingsStage
public org.galagosearch.tupleflow.execution.Stage getWritePostingsStage(java.lang.String stageName,
java.lang.String inputName,
java.lang.String indexName)
getWriteExtentsStage
public org.galagosearch.tupleflow.execution.Stage getWriteExtentsStage()
getWriteDatesStage
public org.galagosearch.tupleflow.execution.Stage getWriteDatesStage()
getWriteManifestStage
public org.galagosearch.tupleflow.execution.Stage getWriteManifestStage()
- Write out document count and collection length information.
getWriteDocumentLengthsStage
public org.galagosearch.tupleflow.execution.Stage getWriteDocumentLengthsStage()
- Writes document lengths to a document lengths file.
getWriteDocumentNamesStage
public org.galagosearch.tupleflow.execution.Stage getWriteDocumentNamesStage()
- Writes document names to a document names file.
getNumberDocumentsStage
public org.galagosearch.tupleflow.execution.Stage getNumberDocumentsStage()
getNumberPostingsStage
public org.galagosearch.tupleflow.execution.Stage getNumberPostingsStage(java.lang.String stageName,
java.lang.String inputName,
java.lang.String outputName)
getNumberExtentsStage
public org.galagosearch.tupleflow.execution.Stage getNumberExtentsStage()
getIndexJob
public org.galagosearch.tupleflow.execution.Job getIndexJob(java.lang.String indexDirectory,
java.lang.String[] indexInputs,
boolean extractAnchors,
boolean useStemming)
throws java.io.IOException
- Throws:
java.io.IOException
Copyright © 2009. All Rights Reserved.