Menu
▾
▴
[Exist-commits] SF.net SVN: exist:[14349] branches/dizzzz/non-xml-indexing/extensions/ indexes/lucene/src/org/exist/xquery/modules/lucene
|
From: <di...@us...> - 2011-04-30 14:08:11
|
Revision: 14349
http://exist.svn.sourceforge.net/exist/?rev=14349&view=rev
Author: dizzzz
Date: 2011-04-30 14:08:03 +0000 (Sat, 30 Apr 2011)
Log Message:
-----------
[ignore] simplified function
Added Paths:
-----------
branches/dizzzz/non-xml-indexing/extensions/indexes/lucene/src/org/exist/xquery/modules/lucene/Search.java
Removed Paths:
-------------
branches/dizzzz/non-xml-indexing/extensions/indexes/lucene/src/org/exist/xquery/modules/lucene/Search.java
Deleted: branches/dizzzz/non-xml-indexing/extensions/indexes/lucene/src/org/exist/xquery/modules/lucene/Search.java
===================================================================
--- branches/dizzzz/non-xml-indexing/extensions/indexes/lucene/src/org/exist/xquery/modules/lucene/Search.java 2011-04-30 13:16:25 UTC (rev 14348)
+++ branches/dizzzz/non-xml-indexing/extensions/indexes/lucene/src/org/exist/xquery/modules/lucene/Search.java 2011-04-30 14:08:03 UTC (rev 14349)
@@ -1,315 +0,0 @@
-package org.exist.xquery.modules.lucene;
-
-import java.io.IOException;
-import java.util.ArrayList;
-import java.util.List;
-import java.util.Properties;
-
-import javax.xml.stream.XMLStreamException;
-import javax.xml.stream.XMLStreamReader;
-
-import org.apache.log4j.Logger;
-import org.apache.lucene.queryParser.ParseException;
-import org.exist.dom.DocumentSet;
-import org.exist.dom.NodeSet;
-import org.exist.dom.QName;
-import org.exist.dom.VirtualNodeSet;
-import org.exist.indexing.lucene.LuceneIndex;
-import org.exist.indexing.lucene.LuceneIndexWorker;
-import org.exist.storage.ElementValue;
-import org.exist.xquery.*;
-import org.exist.xquery.value.FunctionParameterSequenceType;
-import org.exist.xquery.value.FunctionReturnSequenceType;
-import org.exist.xquery.value.Item;
-import org.exist.xquery.value.NodeValue;
-import org.exist.xquery.value.Sequence;
-import org.exist.xquery.value.SequenceType;
-import org.exist.xquery.value.Type;
-import org.w3c.dom.Element;
-
-public class Search extends Function implements Optimizable {
-
- protected static final Logger logger = Logger.getLogger(Search.class);
-
- public final static FunctionSignature[] signatures = {
- new FunctionSignature(
- new QName("search", LuceneModule.NAMESPACE_URI, LuceneModule.PREFIX),
- "Queries a node set using a Lucene full text index; a lucene index " +
- "must already be defined on the nodes, because if no index is available " +
- "on a node, nothing will be found. Indexes on descendant nodes are not " +
- "used. The context of the Lucene query is determined by the given input " +
- "node set. The query is specified either as a query string based on " +
- "Lucene's default query syntax or as an XML fragment. " +
- "See http://exist-db.org/lucene.html#N1029E for complete documentation.",
- new SequenceType[] {
-// new FunctionParameterSequenceType("nodes", Type.NODE, Cardinality.ZERO_OR_MORE,
-// "The node set to search using a Lucene full text index which is defined on those nodes"),
- new FunctionParameterSequenceType("query", Type.ITEM, Cardinality.EXACTLY_ONE,
- "The query to search for, provided either as a string or text in Lucene's default query " +
- "syntax or as an XML fragment to bypass Lucene's default query parser")
- },
- new FunctionReturnSequenceType(Type.NODE, Cardinality.ZERO_OR_MORE,
- "all nodes from the input node set matching the query. match highlighting information " +
- "will be available for all returned nodes. Lucene's match score can be retrieved via " +
- "the ft:score function.")
- ),
- new FunctionSignature(
- new QName("search", LuceneModule.NAMESPACE_URI, LuceneModule.PREFIX),
- "Queries a node set using a Lucene full text index; a lucene index " +
- "must already be defined on the nodes, because if no index is available " +
- "on a node, nothing will be found. Indexes on descendant nodes are not " +
- "used. The context of the Lucene query is determined by the given input " +
- "node set. The query is specified either as a query string based on " +
- "Lucene's default query syntax or as an XML fragment. " +
- "See http://exist-db.org/lucene.html#N1029E for complete documentation.",
- new SequenceType[] {
-// new FunctionParameterSequenceType("nodes", Type.NODE, Cardinality.ZERO_OR_MORE,
-// "The node set to search using a Lucene full text index which is defined on those nodes"),
- new FunctionParameterSequenceType("query", Type.ITEM, Cardinality.EXACTLY_ONE,
- "The query to search for, provided either as a string or text in Lucene's default query " +
- "syntax or as an XML fragment to bypass Lucene's default query parser"),
- new FunctionParameterSequenceType("options", Type.NODE, Cardinality.ZERO_OR_ONE,
- "An XML fragment containing options to be passed to Lucene's query parser. The following " +
- "options are supported (a description can be found in the docs):\n" +
- "<options>\n" +
- " <default-operator>and|or</default-operator>\n" +
- " <phrase-slop>number</phrase-slop>\n" +
- " <leading-wildcard>yes|no</leading-wildcard>\n" +
- " <filter-rewrite>yes|no</filter-rewrite>\n" +
- "</options>")
- },
- new FunctionReturnSequenceType(Type.NODE, Cardinality.ZERO_OR_MORE,
- "all nodes from the input node set matching the query. match highlighting information " +
- "will be available for all returned nodes. Lucene's match score can be retrieved via " +
- "the ft:score function.")
- )
- };
-
- private LocationStep contextStep = null;
- protected QName contextQName = null;
- protected int axis = Constants.UNKNOWN_AXIS;
- private NodeSet preselectResult = null;
- protected boolean optimizeSelf = false;
- protected boolean optimizeChild = false;
-
- public Search(XQueryContext context, FunctionSignature signature) {
- super(context, signature);
- }
-
- public void setArguments(List<Expression> arguments) throws XPathException {
- Expression path = arguments.get(0);
- steps.add(path);
-
-// Expression arg = arguments.get(1);
-// arg = new DynamicCardinalityCheck(context, Cardinality.EXACTLY_ONE, arg,
-// new org.exist.xquery.util.Error(org.exist.xquery.util.Error.FUNC_PARAM_CARDINALITY, "2", mySignature));
-// steps.add(arg);
-//
-// if (arguments.size() == 3) {
-// arg = arguments.get(2);
-// arg = new DynamicCardinalityCheck(context, Cardinality.EXACTLY_ONE, arg,
-// new org.exist.xquery.util.Error(org.exist.xquery.util.Error.FUNC_PARAM_CARDINALITY, "2", mySignature));
-// arg = new DynamicTypeCheck(context, Type.ELEMENT, arg);
-// steps.add(arg);
-// }
- }
-
- /* (non-Javadoc)
- * @see org.exist.xquery.PathExpr#analyze(org.exist.xquery.Expression)
- */
- public void analyze(AnalyzeContextInfo contextInfo) throws XPathException {
- super.analyze(new AnalyzeContextInfo(contextInfo));
-
- List<LocationStep> steps = BasicExpressionVisitor.findLocationSteps(getArgument(0));
- if (!steps.isEmpty()) {
- LocationStep firstStep = steps.get(0);
- LocationStep lastStep = steps.get(steps.size() - 1);
- if (steps.size() == 1 && firstStep.getAxis() == Constants.SELF_AXIS) {
- Expression outerExpr = contextInfo.getContextStep();
- if (outerExpr != null && outerExpr instanceof LocationStep) {
- LocationStep outerStep = (LocationStep) outerExpr;
- NodeTest test = outerStep.getTest();
- if (test.getName() == null)
- contextQName = new QName(null, null, null);
- else if (test.isWildcardTest())
- contextQName = test.getName();
- else
- contextQName = new QName(test.getName());
- if (outerStep.getAxis() == Constants.ATTRIBUTE_AXIS || outerStep.getAxis() == Constants.DESCENDANT_ATTRIBUTE_AXIS)
- contextQName.setNameType(ElementValue.ATTRIBUTE);
- contextStep = firstStep;
- axis = outerStep.getAxis();
- optimizeSelf = true;
- }
- } else {
- NodeTest test = lastStep.getTest();
- if (test.getName() == null)
- contextQName = new QName(null, null, null);
- else if (test.isWildcardTest())
- contextQName = test.getName();
- else
- contextQName = new QName(test.getName());
- if (lastStep.getAxis() == Constants.ATTRIBUTE_AXIS || lastStep.getAxis() == Constants.DESCENDANT_ATTRIBUTE_AXIS)
- contextQName.setNameType(ElementValue.ATTRIBUTE);
- axis = firstStep.getAxis();
- optimizeChild = steps.size() == 1 &&
- (axis == Constants.CHILD_AXIS || axis == Constants.ATTRIBUTE_AXIS);
- contextStep = lastStep;
- }
- }
- }
-
- public boolean canOptimize(Sequence contextSequence) {
- return contextQName != null;
- }
-
- public boolean optimizeOnSelf() {
- return optimizeSelf;
- }
-
- public boolean optimizeOnChild() {
- return optimizeChild;
- }
-
- public int getOptimizeAxis() {
- return axis;
- }
-
- public NodeSet preSelect(Sequence contextSequence, boolean useContext) throws XPathException {
- if (contextSequence != null && !contextSequence.isPersistentSet())
- // in-memory docs won't have an index
- return NodeSet.EMPTY_SET;
-
- long start = System.currentTimeMillis();
- // the expression can be called multiple times, so we need to clear the previous preselectResult
- preselectResult = null;
- LuceneIndexWorker index = (LuceneIndexWorker)
- context.getBroker().getIndexController().getWorkerByIndexId(LuceneIndex.ID);
- DocumentSet docs = contextSequence.getDocumentSet();
- Item key = getKey(contextSequence, null);
- List<QName> qnames = new ArrayList<QName>(1);
- qnames.add(contextQName);
- Properties options = parseOptions(contextSequence, null);
- try {
- if (Type.subTypeOf(key.getType(), Type.ELEMENT))
- preselectResult = index.query(context, getExpressionId(), docs, useContext ? contextSequence.toNodeSet() : null,
- qnames, (Element) ((NodeValue)key).getNode(), NodeSet.DESCENDANT, options);
- else
- preselectResult = index.query(context, getExpressionId(), docs, useContext ? contextSequence.toNodeSet() : null,
- qnames, key.getStringValue(), NodeSet.DESCENDANT, options);
- } catch (IOException e) {
- throw new XPathException(this, "Error while querying full text index: " + e.getMessage(), e);
- } catch (ParseException e) {
- throw new XPathException(this, "Error while querying full text index: " + e.getMessage(), e);
- }
- LOG.debug("Lucene query took " + (System.currentTimeMillis() - start));
- if( context.getProfiler().traceFunctions() ) {
- context.getProfiler().traceIndexUsage( context, "lucene", this, PerformanceStats.OPTIMIZED_INDEX, System.currentTimeMillis() - start );
- }
- return preselectResult;
- }
-
- public Sequence eval(Sequence contextSequence, Item contextItem) throws XPathException {
-
- if (contextItem != null)
- contextSequence = contextItem.toSequence();
-
- if (contextSequence != null && !contextSequence.isPersistentSet())
- // in-memory docs won't have an index
- return Sequence.EMPTY_SEQUENCE;
-
- NodeSet result;
- if (preselectResult == null) {
- long start = System.currentTimeMillis();
- Sequence input = getArgument(0).eval(contextSequence);
- if (!(input instanceof VirtualNodeSet) && input.isEmpty())
- result = NodeSet.EMPTY_SET;
- else {
- NodeSet inNodes = input.toNodeSet();
- DocumentSet docs = inNodes.getDocumentSet();
- LuceneIndexWorker index = (LuceneIndexWorker)
- context.getBroker().getIndexController().getWorkerByIndexId(LuceneIndex.ID);
-// Item key = getKey(contextSequence, contextItem);
- String query = getQuery(contextSequence, contextItem);
- List<QName> qnames = null;
- if (contextQName != null) {
- qnames = new ArrayList<QName>(1);
- qnames.add(contextQName);
- }
- Properties options = parseOptions(contextSequence, contextItem);
-// try {
-// if (Type.subTypeOf(key.getType(), Type.ELEMENT))
- result = index.search(context, docs, query);
-// else
-// result = index.search(context, docs, query); // options
-
-// } catch (IOException e) {
-// throw new XPathException(this, e.getMessage());
-// } catch (ParseException e) {
-// throw new XPathException(this, e.getMessage());
-// }
- }
- if( context.getProfiler().traceFunctions() ) {
- context.getProfiler().traceIndexUsage( context, "lucene", this, PerformanceStats.BASIC_INDEX, System.currentTimeMillis() - start );
- }
- } else {
- contextStep.setPreloadedData(contextSequence.getDocumentSet(), preselectResult);
- result = getArgument(0).eval(contextSequence).toNodeSet();
- }
- return result;
- }
-
- protected Item getKey(Sequence contextSequence, Item contextItem) throws XPathException {
- Sequence keySeq = getArgument(1).eval(contextSequence, contextItem);
- Item key = keySeq.itemAt(0);
- if (!(Type.subTypeOf(key.getType(), Type.STRING) || Type.subTypeOf(key.getType(), Type.NODE)))
- throw new XPathException(this, "Second argument to ft:query should either be a query string or " +
- "an XML element describing the query. Found: " + Type.getTypeName(key.getType()));
- return key;
- }
-
- protected String getQuery(Sequence contextSequence, Item contextItem) throws XPathException {
- Sequence keySeq = getArgument(0).eval(contextSequence, contextItem);
- Item key = keySeq.itemAt(0);
- return key.getStringValue();
- }
-
- public int getDependencies() {
- final Expression stringArg = getArgument(0);
- if (Type.subTypeOf(stringArg.returnsType(), Type.NODE) &&
- !Dependency.dependsOn(stringArg, Dependency.CONTEXT_ITEM)) {
- return Dependency.CONTEXT_SET;
- } else {
- return Dependency.CONTEXT_SET + Dependency.CONTEXT_ITEM;
- }
- }
-
- public int returnsType() {
- return Type.NODE;
- }
-
- protected Properties parseOptions(Sequence contextSequence, Item contextItem) throws XPathException {
- if (getArgumentCount() < 3)
- return null;
- Properties options = new Properties();
- Sequence optSeq = getArgument(2).eval(contextSequence, contextItem);
- NodeValue optRoot = (NodeValue) optSeq.itemAt(0);
- try {
- XMLStreamReader reader = context.getXMLStreamReader(optRoot);
- reader.next();
- reader.next();
- while (reader.hasNext()) {
- int status = reader.next();
- if (status == XMLStreamReader.START_ELEMENT) {
- options.put(reader.getLocalName(), reader.getElementText());
- }
- }
- return options;
- } catch (XMLStreamException e) {
- throw new XPathException(this, "Error while parsing options to ft:query: " + e.getMessage(), e);
- } catch (IOException e) {
- throw new XPathException(this, "Error while parsing options to ft:query: " + e.getMessage(), e);
- }
- }
-}
-
Copied: branches/dizzzz/non-xml-indexing/extensions/indexes/lucene/src/org/exist/xquery/modules/lucene/Search.java (from rev 14346, branches/dizzzz/non-xml-indexing/extensions/indexes/lucene/src/org/exist/xquery/modules/lucene/Index.java)
===================================================================
--- branches/dizzzz/non-xml-indexing/extensions/indexes/lucene/src/org/exist/xquery/modules/lucene/Search.java (rev 0)
+++ branches/dizzzz/non-xml-indexing/extensions/indexes/lucene/src/org/exist/xquery/modules/lucene/Search.java 2011-04-30 14:08:03 UTC (rev 14349)
@@ -0,0 +1,107 @@
+/*
+ * eXist Open Source Native XML Database
+ * Copyright (C) 2001-07 The eXist Project
+ * http://exist-db.org
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ *
+ * \$Id\$
+ */
+package org.exist.xquery.modules.lucene;
+
+import org.apache.log4j.Logger;
+
+import org.exist.dom.DocumentImpl;
+import org.exist.dom.QName;
+import org.exist.indexing.StreamListener;
+import org.exist.indexing.lucene.LuceneIndex;
+import org.exist.indexing.lucene.LuceneIndexWorker;
+import org.exist.storage.lock.Lock;
+import org.exist.xmldb.XmldbURI;
+
+import org.exist.xquery.*;
+import org.exist.xquery.value.*;
+
+public class Search extends BasicFunction {
+
+ private static final Logger logger = Logger.getLogger(Search.class);
+ public final static FunctionSignature signatures[] = {
+ new FunctionSignature(
+ new QName("search", LuceneModule.NAMESPACE_URI, LuceneModule.PREFIX),
+ "Search for (non-XML) data with lucene",
+ new SequenceType[]{
+ new FunctionParameterSequenceType("path", Type.STRING, Cardinality.ZERO_OR_MORE,
+ "Path of documents or document in database."),
+ new FunctionParameterSequenceType("query", Type.STRING, Cardinality.EXACTLY_ONE,
+ "query string")
+ },
+ new FunctionReturnSequenceType(Type.STRING, Cardinality.ZERO_OR_MORE,
+ "The documents that match the query"))
+ };
+
+ /*
+ * Constructor
+ */
+ public Search(XQueryContext context, FunctionSignature signature) {
+ super(context, signature);
+ }
+
+ @Override
+ public Sequence eval(Sequence[] args, Sequence contextSequence) throws XPathException {
+
+ DocumentImpl doc = null;
+ try {
+ // Get first parameter, this is the document
+ String path = args[0].itemAt(0).getStringValue();
+
+ doc = context.getBroker()
+ .getXMLResource(XmldbURI.xmldbUriFor(path), Lock.READ_LOCK);
+
+ if(doc==null){
+ throw new XPathException("Document "+path + " does not exist.");
+ }
+
+ // Get node from second parameter
+ NodeValue descriptor = (NodeValue) args[1].itemAt(0);
+
+ // Retrieve Lucene
+ LuceneIndexWorker index = (LuceneIndexWorker) context.getBroker()
+ .getIndexController().getWorkerByIndexId(LuceneIndex.ID);
+
+ // Order is important
+ index.setDocument(doc, StreamListener.STORE);
+ index.setMode(StreamListener.STORE);
+
+ // Pas document and index instructions to indexer
+ index.indexNonXML(doc, descriptor);
+
+ // Make sure things are written
+ // TODO: to be removed?
+ index.flush();
+
+ } catch (Exception ex) { // PermissionDeniedException
+ logger.error(ex);
+ throw new XPathException(ex);
+
+ } finally {
+ if (doc != null) {
+ doc.getUpdateLock().release(Lock.READ_LOCK);
+ }
+ }
+
+ // Return nothing [status would be nice]
+ return Sequence.EMPTY_SEQUENCE;
+ }
+}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|