public class XpathExtractor extends PartExtractor
Modifier and Type | Class and Description |
---|---|
protected static interface |
XpathExtractor.DocumentParser
DocumentParser *
|
PartExtractor.ExtractCtx, PartExtractor.ExtractCtxBase
Modifier and Type | Field and Description |
---|---|
protected java.util.List<XpathExtractor.DocumentParser> |
htmlParsers |
protected static org.apache.log4j.Logger |
lg |
static java.lang.String |
PARSER_HTMLCLEANER |
static java.lang.String |
PARSER_TAGSOUP |
static java.lang.String |
PARSER_XML |
protected java.util.List<XpathExtractor.DocumentParser> |
xmlParsers |
protected java.util.List<com.exalead.indexing.analysis.processors.XpathExtractor.XpathRule> |
xpathRules |
log
condition
Constructor and Description |
---|
XpathExtractor(java.util.List<java.lang.String> metaNames,
java.util.List<java.lang.String> xpaths,
java.util.List<java.lang.Boolean> concatMutiMatches,
java.lang.String docParserToUse) |
Modifier and Type | Method and Description |
---|---|
protected boolean |
evaluateXpath(org.w3c.dom.Node node,
com.exalead.indexing.analysis.processors.XpathExtractor.XpathRule xpathRule,
AnalysisProcessableDocument doc) |
protected void |
evaluateXpaths(org.w3c.dom.Node node,
AnalysisProcessableDocument doc) |
void |
handlePart(PartExtractor.ExtractCtx ctx) |
canHandlePart, getDirective, partHasNoIndexDirective, process
getCondition, init, release, setCondition
public static final java.lang.String PARSER_XML
public static final java.lang.String PARSER_TAGSOUP
public static final java.lang.String PARSER_HTMLCLEANER
protected java.util.List<com.exalead.indexing.analysis.processors.XpathExtractor.XpathRule> xpathRules
protected java.util.List<XpathExtractor.DocumentParser> htmlParsers
protected java.util.List<XpathExtractor.DocumentParser> xmlParsers
protected static org.apache.log4j.Logger lg
public XpathExtractor(java.util.List<java.lang.String> metaNames, java.util.List<java.lang.String> xpaths, java.util.List<java.lang.Boolean> concatMutiMatches, java.lang.String docParserToUse) throws com.exalead.util.TypedException
com.exalead.util.TypedException
public void handlePart(PartExtractor.ExtractCtx ctx)
handlePart
in class PartExtractor
protected void evaluateXpaths(org.w3c.dom.Node node, AnalysisProcessableDocument doc) throws javax.xml.xpath.XPathExpressionException, javax.xml.transform.TransformerException
javax.xml.xpath.XPathExpressionException
javax.xml.transform.TransformerException
protected boolean evaluateXpath(org.w3c.dom.Node node, com.exalead.indexing.analysis.processors.XpathExtractor.XpathRule xpathRule, AnalysisProcessableDocument doc) throws javax.xml.xpath.XPathExpressionException, javax.xml.transform.TransformerException
javax.xml.xpath.XPathExpressionException
javax.xml.transform.TransformerException
Copyright © 2013 Dassault Systèmes, All Rights Reserved.