|
||||||||||
| PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
| SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD | |||||||||
java.lang.Objectorg.ow2.weblab.crawler.FolderCrawler
public class FolderCrawler
Use this component crawl a folder. This is a basic component, no thread, no complex timings, no data comparison. A real crawler could use multiple instances of this component.
| Field Summary | |
|---|---|
protected int |
bufferSize
|
protected org.ow2.weblab.content.ContentManager |
contentManager
|
protected static java.lang.String |
CRAWLER_CONTENT_ID
|
protected static java.lang.String |
CRAWLER_ID
|
protected static java.text.SimpleDateFormat |
DATE_FORMAT
|
protected java.io.FileFilter |
fileFilter
|
protected java.io.File |
folder
|
protected java.io.FileFilter |
folderFilter
|
protected boolean |
recursiveMode
|
| Constructor Summary | |
|---|---|
FolderCrawler(org.ow2.weblab.content.ContentManager contentManager,
java.io.File folder,
java.io.FileFilter fileFilter,
boolean recursiveMode)
Constructors |
|
FolderCrawler(org.ow2.weblab.content.ContentManager contentManager,
java.io.File folder,
java.io.FileFilter fileFilter,
boolean recursiveMode,
java.io.FileFilter folderFilter)
Constructors |
|
FolderCrawler(java.lang.String folderToCrawl)
Constructors |
|
FolderCrawler(java.lang.String folderToCrawl,
java.io.FileFilter fileFilter)
Constructors |
|
FolderCrawler(java.lang.String folderToCrawl,
java.io.FileFilter fileFilter,
boolean recursiveMode)
Constructors |
|
FolderCrawler(java.lang.String folderToCrawl,
java.io.FileFilter fileFilter,
boolean recursiveMode,
java.io.FileFilter folderFilter)
Constructors |
|
| Method Summary | |
|---|---|
org.ow2.weblab.core.model.ComposedResource |
getCrawledDocuments(int offset,
int limit)
|
int |
getNbFiles()
|
protected void |
listAndAddFiles(java.io.File newFolder)
|
void |
startCrawl()
Crawls the folder using the file filter and fills the crawled files list. |
java.lang.String |
toString()
|
| Methods inherited from class java.lang.Object |
|---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait |
| Field Detail |
|---|
protected final org.ow2.weblab.content.ContentManager contentManager
protected final java.io.File folder
protected final java.io.FileFilter fileFilter
protected final java.io.FileFilter folderFilter
protected final int bufferSize
protected final boolean recursiveMode
protected static final java.lang.String CRAWLER_ID
protected static final java.lang.String CRAWLER_CONTENT_ID
protected static final java.text.SimpleDateFormat DATE_FORMAT
| Constructor Detail |
|---|
public FolderCrawler(org.ow2.weblab.content.ContentManager contentManager,
java.io.File folder,
java.io.FileFilter fileFilter,
boolean recursiveMode,
java.io.FileFilter folderFilter)
throws org.ow2.weblab.core.extended.exception.WebLabCheckedException
contentManager - The content managerfolder - The folder to crawlfileFilter - The file filter to be usedrecursiveMode - Whether or not to crawl contained foldersfolderFilter - A filter on the folder
org.ow2.weblab.core.extended.exception.WebLabCheckedException - If one of the parameters is not correct or if the creation of
mimeinfo throws exception.
public FolderCrawler(org.ow2.weblab.content.ContentManager contentManager,
java.io.File folder,
java.io.FileFilter fileFilter,
boolean recursiveMode)
throws org.ow2.weblab.core.extended.exception.WebLabCheckedException
contentManager - The content managerfolder - The folder to crawlfileFilter - The file filter to be usedrecursiveMode - Whether or not to crawl contained folders
org.ow2.weblab.core.extended.exception.WebLabCheckedException - If one of the parameters is not correct or if the creation of
mimeinfo throws exception.
public FolderCrawler(java.lang.String folderToCrawl,
java.io.FileFilter fileFilter)
throws org.ow2.weblab.core.extended.exception.WebLabCheckedException
folderToCrawl - The folder to crawlfileFilter - The file filter to be used
org.ow2.weblab.core.extended.exception.WebLabCheckedException - If one of the parameters is not correct or if the creation of
mimeinfo throws exception.
public FolderCrawler(java.lang.String folderToCrawl,
java.io.FileFilter fileFilter,
boolean recursiveMode)
throws org.ow2.weblab.core.extended.exception.WebLabCheckedException
folderToCrawl - The folder to crawlfileFilter - The file filter to be usedrecursiveMode - Whether or not to crawl contained folders
org.ow2.weblab.core.extended.exception.WebLabCheckedException - If one of the parameters is not correct or if the creation of
mimeinfo throws exception.
public FolderCrawler(java.lang.String folderToCrawl,
java.io.FileFilter fileFilter,
boolean recursiveMode,
java.io.FileFilter folderFilter)
throws org.ow2.weblab.core.extended.exception.WebLabCheckedException
folderToCrawl - The folder to crawlfileFilter - The file filter to be usedrecursiveMode - Whether or not to crawl contained foldersfolderFilter - The folder filter to be used
org.ow2.weblab.core.extended.exception.WebLabCheckedException - If one of the parameters is not correct or if the creation of
mimeinfo throws exception.
public FolderCrawler(java.lang.String folderToCrawl)
throws org.ow2.weblab.core.extended.exception.WebLabCheckedException
internFolder - folderToCrawl -
org.ow2.weblab.core.extended.exception.WebLabCheckedException| Method Detail |
|---|
public int getNbFiles()
public void startCrawl()
protected void listAndAddFiles(java.io.File newFolder)
newFolder - The folder to be crawled
public org.ow2.weblab.core.model.ComposedResource getCrawledDocuments(int offset,
int limit)
offset - the starting point in the collection. If negative, 0 is used.limit - if negative of null, Integer.MAX_VALUE is used.
public java.lang.String toString()
toString in class java.lang.Object
|
||||||||||
| PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
| SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD | |||||||||