List of usage examples for org.apache.lucene.queryparser.flexible.core.nodes FieldQueryNode getTextAsString
public String getTextAsString()
From source file:at.ac.univie.mminf.luceneSKOS.queryparser.flexible.standard.processors.SKOSQueryNodeProcessor.java
License:Apache License
@Override protected QueryNode postProcessNode(QueryNode node) throws QueryNodeException { if (node instanceof TextableQueryNode && !(node instanceof WildcardQueryNode) && !(node instanceof FuzzyQueryNode) && !(node instanceof RegexpQueryNode) && !(node.getParent() instanceof RangeQueryNode)) { FieldQueryNode fieldNode = ((FieldQueryNode) node); String text = fieldNode.getTextAsString(); String field = fieldNode.getFieldAsString(); TokenStream source;/*w w w.ja va2 s . co m*/ try { source = this.analyzer.tokenStream(field, text); source.reset(); } catch (IOException e1) { throw new RuntimeException(e1); } CachingTokenFilter buffer = new CachingTokenFilter(source); PositionIncrementAttribute posIncrAtt = null; int numTokens = 0; int positionCount = 0; boolean severalTokensAtSamePosition = false; if (buffer.hasAttribute(PositionIncrementAttribute.class)) { posIncrAtt = buffer.getAttribute(PositionIncrementAttribute.class); } try { while (buffer.incrementToken()) { numTokens++; int positionIncrement = (posIncrAtt != null) ? posIncrAtt.getPositionIncrement() : 1; if (positionIncrement != 0) { positionCount += positionIncrement; } else { severalTokensAtSamePosition = true; } } } catch (IOException e) { // ignore } try { // rewind the buffer stream buffer.reset(); // close original stream - all tokens buffered source.close(); } catch (IOException e) { // ignore } if (!buffer.hasAttribute(CharTermAttribute.class)) { return new NoTokenFoundQueryNode(); } CharTermAttribute termAtt = buffer.getAttribute(CharTermAttribute.class); if (numTokens == 0) { return new NoTokenFoundQueryNode(); } else if (numTokens == 1) { String term = null; try { boolean hasNext; hasNext = buffer.incrementToken(); assert hasNext == true; term = termAtt.toString(); } catch (IOException e) { // safe to ignore, because we know the number of tokens } fieldNode.setText(term); return fieldNode; } else if (severalTokensAtSamePosition || !(node instanceof QuotedFieldQueryNode)) { if (positionCount == 1 || !(node instanceof QuotedFieldQueryNode)) { // no phrase query: LinkedList<QueryNode> children = new LinkedList<QueryNode>(); for (int i = 0; i < numTokens; i++) { String term = null; try { boolean hasNext = buffer.incrementToken(); assert hasNext == true; term = termAtt.toString(); } catch (IOException e) { // safe to ignore, because we know the number of tokens } if (buffer.hasAttribute(SKOSTypeAttribute.class) && boosts != null) { SKOSTypeAttribute skosAttr = buffer.getAttribute(SKOSTypeAttribute.class); children.add(new BoostQueryNode(new FieldQueryNode(field, term, -1, -1), getBoost(skosAttr.getSkosType()))); } else { children.add(new FieldQueryNode(field, term, -1, -1)); } } return new GroupQueryNode(new StandardBooleanQueryNode(children, positionCount == 1)); } else { // phrase query: MultiPhraseQueryNode mpq = new MultiPhraseQueryNode(); List<FieldQueryNode> multiTerms = new ArrayList<FieldQueryNode>(); int position = -1; int i = 0; int termGroupCount = 0; for (; i < numTokens; i++) { String term = null; int positionIncrement = 1; try { boolean hasNext = buffer.incrementToken(); assert hasNext == true; term = termAtt.toString(); if (posIncrAtt != null) { positionIncrement = posIncrAtt.getPositionIncrement(); } } catch (IOException e) { // safe to ignore, because we know the number of tokens } if (positionIncrement > 0 && multiTerms.size() > 0) { for (FieldQueryNode termNode : multiTerms) { if (this.positionIncrementsEnabled) { termNode.setPositionIncrement(position); } else { termNode.setPositionIncrement(termGroupCount); } mpq.add(termNode); } // Only increment once for each "group" of // terms that were in the same position: termGroupCount++; multiTerms.clear(); } position += positionIncrement; multiTerms.add(new FieldQueryNode(field, term, -1, -1)); } for (FieldQueryNode termNode : multiTerms) { if (this.positionIncrementsEnabled) { termNode.setPositionIncrement(position); } else { termNode.setPositionIncrement(termGroupCount); } mpq.add(termNode); } return mpq; } } else { TokenizedPhraseQueryNode pq = new TokenizedPhraseQueryNode(); int position = -1; for (int i = 0; i < numTokens; i++) { String term = null; int positionIncrement = 1; try { boolean hasNext = buffer.incrementToken(); assert hasNext == true; term = termAtt.toString(); if (posIncrAtt != null) { positionIncrement = posIncrAtt.getPositionIncrement(); } } catch (IOException e) { // safe to ignore, because we know the number of tokens } FieldQueryNode newFieldNode = new FieldQueryNode(field, term, -1, -1); if (this.positionIncrementsEnabled) { position += positionIncrement; newFieldNode.setPositionIncrement(position); } else { newFieldNode.setPositionIncrement(i); } pq.add(newFieldNode); } return pq; } } return node; }
From source file:com.sindicetech.siren.qparser.keyword.builders.FieldQueryNodeBuilder.java
License:Open Source License
public NodeQuery build(QueryNode queryNode) throws QueryNodeException { final FieldQueryNode fieldNode = (FieldQueryNode) queryNode; // if it is tagged as a span query if (fieldNode.getTag(QueryTypeProcessor.QUERYTYPE_TAG) == QueryTypeProcessor.SPAN_QUERYTYPE) { // create the term span query TermSpanQuery tsq = new TermSpanQuery( new Term(fieldNode.getFieldAsString(), fieldNode.getTextAsString())); // assign the datatype. We must always have a datatype assigned. tsq.setDatatype((String) queryNode.getTag(DatatypeQueryNode.DATATYPE_TAGID)); return tsq; } else {/* www . jav a2 s . c o m*/ // create the node term query NodeTermQuery ntq = new NodeTermQuery( new Term(fieldNode.getFieldAsString(), fieldNode.getTextAsString())); // assign the datatype. We must always have a datatype assigned. ntq.setDatatype((String) queryNode.getTag(DatatypeQueryNode.DATATYPE_TAGID)); return ntq; } }
From source file:com.sindicetech.siren.qparser.keyword.builders.NodeTermRangeQueryNodeBuilder.java
License:Open Source License
public NodeQuery build(final QueryNode queryNode) throws QueryNodeException { final TermRangeQueryNode rangeNode = (TermRangeQueryNode) queryNode; final FieldQueryNode upper = rangeNode.getUpperBound(); final FieldQueryNode lower = rangeNode.getLowerBound(); final String field = StringUtils.toString(rangeNode.getField()); String lowerText = lower.getTextAsString(); String upperText = upper.getTextAsString(); if (lowerText.length() == 0) { lowerText = null;/*from ww w .ja v a 2s.c o m*/ } if (upperText.length() == 0) { upperText = null; } final NodeTermRangeQuery rangeQuery = NodeTermRangeQuery.newStringRange(field, lowerText, upperText, rangeNode.isLowerInclusive(), rangeNode.isUpperInclusive()); final MultiNodeTermQuery.RewriteMethod method = (MultiNodeTermQuery.RewriteMethod) queryNode .getTag(MultiNodeTermRewriteMethodProcessor.TAG_ID); if (method != null) { rangeQuery.setRewriteMethod(method); } // if it is tagged as a span query if (rangeNode.getTag(QueryTypeProcessor.QUERYTYPE_TAG) == QueryTypeProcessor.SPAN_QUERYTYPE) { return new MultiTermSpanQuery<>(rangeQuery); } else { return rangeQuery; } }
From source file:com.sindicetech.siren.qparser.keyword.processors.DatatypeAnalyzerProcessor.java
License:Open Source License
private CachingTokenFilter getBuffer(Analyzer analyzer, FieldQueryNode fieldNode) { final TokenStream source; final String text = fieldNode.getTextAsString(); final String field = fieldNode.getFieldAsString(); try {/*from w ww.j a v a2s. co m*/ source = analyzer.tokenStream(field, new StringReader(text)); source.reset(); } catch (final IOException e1) { throw new RuntimeException(e1); } return new CachingTokenFilter(source); }
From source file:com.sindicetech.siren.qparser.keyword.processors.NodeNumericQueryNodeProcessor.java
License:Open Source License
@Override protected QueryNode postProcessNode(QueryNode node) throws QueryNodeException { if (node instanceof FieldQueryNode && !(node.getParent() instanceof RangeQueryNode)) { final FieldQueryNode fieldNode = (FieldQueryNode) node; String datatype = (String) DatatypeProcessor.getDatatype(this.getQueryConfigHandler(), node); final Map<String, Analyzer> dts = this.getQueryConfigHandler() .get(KeywordConfigurationKeys.DATATYPES_ANALYZERS); final Analyzer analyzer = dts.get(node.getTag(DatatypeQueryNode.DATATYPE_TAGID)); if (analyzer instanceof NumericAnalyzer) { final NumericAnalyzer na = (NumericAnalyzer) analyzer; final char[] text = fieldNode.getTextAsString().toCharArray(); final ReusableCharArrayReader textReader = new ReusableCharArrayReader(text); final Number number; try { number = na.getNumericParser().parse(textReader); } catch (final Exception e) { throw new QueryNodeParseException( new MessageImpl(QueryParserMessages.COULD_NOT_PARSE_NUMBER, text), e); }/* ww w.j a v a 2 s.c o m*/ final CharSequence field = fieldNode.getField(); final NodeNumericQueryNode lowerNode = new NodeNumericQueryNode(field, number); // assign datatype lowerNode.setTag(DatatypeQueryNode.DATATYPE_TAGID, datatype); final NodeNumericQueryNode upperNode = new NodeNumericQueryNode(field, number); // assign datatype upperNode.setTag(DatatypeQueryNode.DATATYPE_TAGID, datatype); // Create the NodeNumericRangeQueryNode node = new NodeNumericRangeQueryNode(lowerNode, upperNode, true, true, na); // assign datatype node.setTag(DatatypeQueryNode.DATATYPE_TAGID, datatype); } } return node; }
From source file:com.sindicetech.siren.qparser.keyword.processors.NodeNumericRangeQueryNodeProcessor.java
License:Open Source License
@Override protected QueryNode postProcessNode(QueryNode node) throws QueryNodeException { if (node instanceof TermRangeQueryNode) { final TermRangeQueryNode termRangeNode = (TermRangeQueryNode) node; String datatype = (String) DatatypeProcessor.getDatatype(this.getQueryConfigHandler(), node); final Map<String, Analyzer> dts = this.getQueryConfigHandler() .get(KeywordConfigurationKeys.DATATYPES_ANALYZERS); final Analyzer analyzer = dts.get(datatype); if (analyzer instanceof NumericAnalyzer) { final NumericAnalyzer na = (NumericAnalyzer) analyzer; final FieldQueryNode lower = termRangeNode.getLowerBound(); final FieldQueryNode upper = termRangeNode.getUpperBound(); final char[] lowerText = lower.getTextAsString().toCharArray(); final char[] upperText = upper.getTextAsString().toCharArray(); // Parse the lower and upper bound final NumericParser<?> parser = na.getNumericParser(); final Number lowerNumber; try { if (lowerText.length == 0) { // open bound lowerNumber = null;// www .ja va 2 s . c o m } else { final ReusableCharArrayReader lowerReader = new ReusableCharArrayReader(lowerText); lowerNumber = parser.parse(lowerReader); } } catch (final Exception e) { throw new QueryNodeParseException(new MessageImpl(QueryParserMessages.COULD_NOT_PARSE_NUMBER, lowerText, parser.getNumericType() + " parser"), e); } final Number upperNumber; try { if (upperText.length == 0) { // open bound upperNumber = null; } else { final ReusableCharArrayReader upperReader = new ReusableCharArrayReader(upperText); upperNumber = parser.parse(upperReader); } } catch (final Exception e) { throw new QueryNodeParseException(new MessageImpl(QueryParserMessages.COULD_NOT_PARSE_NUMBER, upperText, parser.getNumericType() + " parser"), e); } // Create two NodeNumericQueryNode for the lower and upper bound final CharSequence field = termRangeNode.getField(); final NodeNumericQueryNode lowerNode = new NodeNumericQueryNode(field, lowerNumber); // assign datatype lowerNode.setTag(DatatypeQueryNode.DATATYPE_TAGID, datatype); final NodeNumericQueryNode upperNode = new NodeNumericQueryNode(field, upperNumber); // assign datatype upperNode.setTag(DatatypeQueryNode.DATATYPE_TAGID, datatype); final boolean lowerInclusive = termRangeNode.isLowerInclusive(); final boolean upperInclusive = termRangeNode.isUpperInclusive(); // Create the NodeNumericRangeQueryNode node = new NodeNumericRangeQueryNode(lowerNode, upperNode, lowerInclusive, upperInclusive, na); // assign datatype node.setTag(DatatypeQueryNode.DATATYPE_TAGID, datatype); } } return node; }
From source file:com.sindicetech.siren.qparser.keyword.processors.PhraseQueryNodeProcessor.java
License:Open Source License
@Override protected QueryNode postProcessNode(final QueryNode node) throws QueryNodeException { if (node instanceof TextableQueryNode && !(node instanceof WildcardQueryNode) && !(node instanceof FuzzyQueryNode) && !(node instanceof RegexpQueryNode) && !(node instanceof ProtectedQueryNode) && !(node.getParent() instanceof RangeQueryNode)) { final FieldQueryNode fieldNode = ((FieldQueryNode) node); final String text = fieldNode.getTextAsString(); final String field = fieldNode.getFieldAsString(); final TokenStream source; try {//from w ww. j a v a 2 s .co m source = this.analyzer.tokenStream(field, new StringReader(text)); source.reset(); } catch (final IOException e1) { throw new RuntimeException(e1); } final CachingTokenFilter buffer = new CachingTokenFilter(source); int numTokens = 0; try { while (buffer.incrementToken()) { numTokens++; } } catch (final IOException e) { // ignore } try { // rewind the buffer stream buffer.reset(); // close original stream - all tokens buffered source.close(); } catch (final IOException e) { // ignore } if (!buffer.hasAttribute(CharTermAttribute.class)) { return new NoTokenFoundQueryNode(); } final CharTermAttribute termAtt = buffer.getAttribute(CharTermAttribute.class); if (numTokens == 0) { return new NoTokenFoundQueryNode(); } // phrase query else if (numTokens != 1) { String datatype = (String) DatatypeProcessor.getDatatype(this.getQueryConfigHandler(), node); final TokenizedPhraseQueryNode pq = new TokenizedPhraseQueryNode(); // assign datatype pq.setTag(DatatypeQueryNode.DATATYPE_TAGID, datatype); for (int i = 0; i < numTokens; i++) { String term = null; try { final boolean hasNext = buffer.incrementToken(); assert hasNext == true; term = termAtt.toString(); } catch (final IOException e) { // safe to ignore, because we know the number of tokens } final FieldQueryNode newFieldNode = new FieldQueryNode(field, term, -1, -1); // set position increment newFieldNode.setPositionIncrement(i); // assign datatype newFieldNode.setTag(DatatypeQueryNode.DATATYPE_TAGID, datatype); pq.add(newFieldNode); } return pq; } } return node; }
From source file:org.sindice.siren.qparser.keyword.builders.FieldQueryNodeBuilder.java
License:Apache License
public NodeTermQuery build(QueryNode queryNode) throws QueryNodeException { final FieldQueryNode fieldNode = (FieldQueryNode) queryNode; return new NodeTermQuery(new Term(fieldNode.getFieldAsString(), fieldNode.getTextAsString())); }
From source file:org.sindice.siren.qparser.keyword.builders.NodeTermRangeQueryNodeBuilder.java
License:Apache License
public NodeTermRangeQuery build(final QueryNode queryNode) throws QueryNodeException { final TermRangeQueryNode rangeNode = (TermRangeQueryNode) queryNode; final FieldQueryNode upper = rangeNode.getUpperBound(); final FieldQueryNode lower = rangeNode.getLowerBound(); final String field = StringUtils.toString(rangeNode.getField()); String lowerText = lower.getTextAsString(); String upperText = upper.getTextAsString(); if (lowerText.length() == 0) { lowerText = null;/*from w w w .ja va2 s . c om*/ } if (upperText.length() == 0) { upperText = null; } final NodeTermRangeQuery rangeQuery = NodeTermRangeQuery.newStringRange(field, lowerText, upperText, rangeNode.isLowerInclusive(), rangeNode.isUpperInclusive()); final MultiNodeTermQuery.RewriteMethod method = (MultiNodeTermQuery.RewriteMethod) queryNode .getTag(MultiNodeTermRewriteMethodProcessor.TAG_ID); if (method != null) { rangeQuery.setRewriteMethod(method); } return rangeQuery; }
From source file:org.sindice.siren.qparser.keyword.processors.DatatypeAnalyzerProcessor.java
License:Apache License
@Override protected QueryNode postProcessNode(final QueryNode node) throws QueryNodeException { if (node instanceof TextableQueryNode && !(node instanceof WildcardQueryNode) && !(node instanceof FuzzyQueryNode) && !(node instanceof RegexpQueryNode) && !(node.getParent() instanceof RangeQueryNode)) { this.positionIncrementsEnabled = false; final Boolean positionIncrementsEnabled = this.getQueryConfigHandler() .get(ConfigurationKeys.ENABLE_POSITION_INCREMENTS); if (positionIncrementsEnabled != null) { this.positionIncrementsEnabled = positionIncrementsEnabled; }// w w w . j a v a 2s. c o m final FieldQueryNode fieldNode = ((FieldQueryNode) node); final String text = fieldNode.getTextAsString(); final String field = fieldNode.getFieldAsString(); final String datatype = (String) fieldNode.getTag(DatatypeQueryNode.DATATYPE_TAGID); if (datatype == null) { return node; } final Analyzer analyzer = this.getQueryConfigHandler().get(KeywordConfigurationKeys.DATATYPES_ANALYZERS) .get(datatype); if (analyzer == null) { throw new QueryNodeException(new MessageImpl(QueryParserMessages.INVALID_SYNTAX, "No analyzer associated with " + datatype)); } PositionIncrementAttribute posIncrAtt = null; int numTokens = 0; int positionCount = 0; boolean severalTokensAtSamePosition = false; final TokenStream source; try { source = analyzer.tokenStream(field, new StringReader(text)); source.reset(); } catch (final IOException e1) { throw new RuntimeException(e1); } final CachingTokenFilter buffer = new CachingTokenFilter(source); if (buffer.hasAttribute(PositionIncrementAttribute.class)) { posIncrAtt = buffer.getAttribute(PositionIncrementAttribute.class); } try { while (buffer.incrementToken()) { numTokens++; final int positionIncrement = (posIncrAtt != null) ? posIncrAtt.getPositionIncrement() : 1; if (positionIncrement != 0) { positionCount += positionIncrement; } else { severalTokensAtSamePosition = true; } } } catch (final IOException e) { // ignore } try { // rewind the buffer stream buffer.reset(); // close original stream - all tokens buffered source.close(); } catch (final IOException e) { // ignore } if (!buffer.hasAttribute(CharTermAttribute.class)) { return new NoTokenFoundQueryNode(); } final CharTermAttribute termAtt = buffer.getAttribute(CharTermAttribute.class); if (numTokens == 0) { if (nbTwigs != 0) { // Twig special case return new WildcardNodeQueryNode(); } return new NoTokenFoundQueryNode(); } else if (numTokens == 1) { String term = null; try { boolean hasNext; hasNext = buffer.incrementToken(); assert hasNext == true; term = termAtt.toString(); } catch (final IOException e) { // safe to ignore, because we know the number of tokens } fieldNode.setText(term); return fieldNode; } else { // no phrase query: final LinkedList<QueryNode> children = new LinkedList<QueryNode>(); int position = -1; for (int i = 0; i < numTokens; i++) { String term = null; final int positionIncrement = 1; try { final boolean hasNext = buffer.incrementToken(); assert hasNext == true; term = termAtt.toString(); } catch (final IOException e) { // safe to ignore, because we know the number of tokens } final FieldQueryNode newFieldNode = new FieldQueryNode(field, term, -1, -1); if (this.positionIncrementsEnabled) { position += positionIncrement; newFieldNode.setPositionIncrement(position); } else { newFieldNode.setPositionIncrement(i); } children.add(new FieldQueryNode(field, term, -1, -1)); } if (node.getParent() instanceof TokenizedPhraseQueryNode) { throw new QueryNodeException(new MessageImpl("Cannot build a MultiPhraseQuery")); } // If multiple terms at one single position, this must be a query // expansion. Perform a OR between the terms. if (severalTokensAtSamePosition && positionCount == 1) { return new GroupQueryNode(new OrQueryNode(children)); } // if several tokens at same position && position count > 1, then // results can be unexpected else { final TokenizedPhraseQueryNode pq = new TokenizedPhraseQueryNode(); for (int i = 0; i < children.size(); i++) { pq.add(children.get(i)); } return pq; } } } else if (node instanceof TwigQueryNode) { nbTwigs--; assert nbTwigs >= 0; } return node; }