de.phleisch.app.itsucks.processing.download.http.impl
Class UrlExtractor
java.lang.Object
de.phleisch.app.itsucks.processing.download.http.impl.UrlExtractor
public class UrlExtractor
- extends java.lang.Object
|
Method Summary |
protected java.lang.String |
decodeHtmlExpressions(java.lang.String link)
|
protected java.lang.String |
encodeURIChars(java.lang.String pLink)
http://www.ietf.org/rfc/rfc2396.txt |
java.net.URI[] |
extractURLs(java.lang.String pData)
|
protected void |
initPatterns()
|
protected boolean |
isMatchExcluded(java.lang.String pMatch)
Checks if the match is excluded by a pattern. |
protected void |
loadPatterns(java.lang.String propertyName)
|
| Methods inherited from class java.lang.Object |
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
REGEXP_SEARCH_PREFIX
protected static final java.lang.String REGEXP_SEARCH_PREFIX
- See Also:
- Constant Field Values
REGEXP_EXCLUDE_PREFIX
protected static final java.lang.String REGEXP_EXCLUDE_PREFIX
- See Also:
- Constant Field Values
mLog
protected static final org.apache.commons.logging.Log mLog
mSearchPatterns
protected static UrlExtractor.PatternConfig[] mSearchPatterns
mExcludePatterns
protected static java.util.regex.Pattern[] mExcludePatterns
ALLOWED_URI_CHARS
protected static final char[] ALLOWED_URI_CHARS
mBaseURI
protected java.net.URI mBaseURI
UrlExtractor
public UrlExtractor(java.net.URI pBaseURI)
initPatterns
protected void initPatterns()
extractURLs
public java.net.URI[] extractURLs(java.lang.String pData)
isMatchExcluded
protected boolean isMatchExcluded(java.lang.String pMatch)
- Checks if the match is excluded by a pattern.
- Parameters:
pMatch -
- Returns:
decodeHtmlExpressions
protected java.lang.String decodeHtmlExpressions(java.lang.String link)
encodeURIChars
protected java.lang.String encodeURIChars(java.lang.String pLink)
- http://www.ietf.org/rfc/rfc2396.txt
- Parameters:
pLink -
- Returns:
loadPatterns
protected void loadPatterns(java.lang.String propertyName)
Copyright © 2010. All Rights Reserved.