public Query getQuery(Element e) throws ParserException {
String fieldName = DOMUtils.getAttributeWithInheritanceOrFail(e, "fieldName");
String text = DOMUtils.getNonBlankTextOrFail(e);
BooleanQuery bq = new BooleanQuery(DOMUtils.getAttribute(e, "disableCoord", false));
bq.setMinimumNumberShouldMatch(DOMUtils.getAttribute(e, "minimumNumberShouldMatch", 0));
try {
TokenStream ts = analyzer.tokenStream(fieldName, new StringReader(text));
TermToBytesRefAttribute termAtt = ts.addAttribute(TermToBytesRefAttribute.class);
Term term = null;
BytesRef bytes = termAtt.getBytesRef();
ts.reset();
while (ts.incrementToken()) {
termAtt.fillBytesRef();
term = new Term(fieldName, BytesRef.deepCopyOf(bytes));
bq.add(new BooleanClause(new TermQuery(term), BooleanClause.Occur.SHOULD));
}
ts.end();
ts.close();
} catch (IOException ioe) {
throw new RuntimeException("Error constructing terms from index:" + ioe);
}
bq.setBoost(DOMUtils.getAttribute(e, "boost", 1.0f));
return bq;
}
public SpanQuery getSpanQuery(Element e) throws ParserException {
String fieldName = DOMUtils.getAttributeWithInheritanceOrFail(e, "fieldName");
String value = DOMUtils.getNonBlankTextOrFail(e);
SpanTermQuery stq = new SpanTermQuery(new Term(fieldName, value));
stq.setBoost(DOMUtils.getAttribute(e, "boost", 1.0f));
return stq;
}
@Override
public SpanQuery getSpanQuery(Element e) throws ParserException {
String fieldName = DOMUtils.getAttributeWithInheritanceOrFail(e, "fieldName");
String value = DOMUtils.getNonBlankTextOrFail(e);
SpanTermQuery stq = new SpanTermQuery(new Term(fieldName, value));
float boost = DOMUtils.getAttribute(e, "boost", 1.0f);
return new SpanBoostQuery(stq, boost);
}
@Override
public TermRangeQuery getQuery(Element e) throws ParserException {
String fieldName = DOMUtils.getAttributeWithInheritance(e, "fieldName");
String lowerTerm = e.hasAttribute("lowerTerm") ? e.getAttribute("lowerTerm") : null;
String upperTerm = e.hasAttribute("upperTerm") ? e.getAttribute("upperTerm") : null;
boolean includeLower = DOMUtils.getAttribute(e, "includeLower", true);
boolean includeUpper = DOMUtils.getAttribute(e, "includeUpper", true);
return TermRangeQuery.newStringRange(
fieldName, lowerTerm, upperTerm, includeLower, includeUpper);
}
@Override
public Query getQuery(Element e) throws ParserException {
String field = DOMUtils.getAttributeWithInheritanceOrFail(e, "fieldName");
String value = DOMUtils.getNonBlankTextOrFail(e);
Query tq = new TermQuery(new Term(field, value));
float boost = DOMUtils.getAttribute(e, "boost", 1.0f);
if (boost != 1f) {
tq = new BoostQuery(tq, boost);
}
return tq;
}
public Query getQuery(Element e) throws ParserException {
float tieBreaker = DOMUtils.getAttribute(e, "tieBreaker", 0.0f);
DisjunctionMaxQuery dq = new DisjunctionMaxQuery(tieBreaker);
dq.setBoost(DOMUtils.getAttribute(e, "boost", 1.0f));
NodeList nl = e.getChildNodes();
for (int i = 0; i < nl.getLength(); i++) {
Node node = nl.item(i);
if (node instanceof Element) { // all elements are disjuncts.
Element queryElem = (Element) node;
Query q = factory.getQuery(queryElem);
dq.add(q);
}
}
return dq;
}
@Override
public Filter getFilter(Element e) throws ParserException {
String field = DOMUtils.getAttributeWithInheritanceOrFail(e, "fieldName");
String lowerTerm = DOMUtils.getAttributeOrFail(e, "lowerTerm");
String upperTerm = DOMUtils.getAttributeOrFail(e, "upperTerm");
boolean lowerInclusive = DOMUtils.getAttribute(e, "includeLower", true);
boolean upperInclusive = DOMUtils.getAttribute(e, "includeUpper", true);
int precisionStep =
DOMUtils.getAttribute(e, "precisionStep", NumericUtils.PRECISION_STEP_DEFAULT);
String type = DOMUtils.getAttribute(e, "type", "int");
try {
Filter filter;
if (type.equalsIgnoreCase("int")) {
filter =
NumericRangeFilter.newIntRange(
field,
precisionStep,
Integer.valueOf(lowerTerm),
Integer.valueOf(upperTerm),
lowerInclusive,
upperInclusive);
} else if (type.equalsIgnoreCase("long")) {
filter =
NumericRangeFilter.newLongRange(
field,
precisionStep,
Long.valueOf(lowerTerm),
Long.valueOf(upperTerm),
lowerInclusive,
upperInclusive);
} else if (type.equalsIgnoreCase("double")) {
filter =
NumericRangeFilter.newDoubleRange(
field,
precisionStep,
Double.valueOf(lowerTerm),
Double.valueOf(upperTerm),
lowerInclusive,
upperInclusive);
} else if (type.equalsIgnoreCase("float")) {
filter =
NumericRangeFilter.newFloatRange(
field,
precisionStep,
Float.valueOf(lowerTerm),
Float.valueOf(upperTerm),
lowerInclusive,
upperInclusive);
} else {
throw new ParserException("type attribute must be one of: [long, int, double, float]");
}
return filter;
} catch (NumberFormatException nfe) {
if (strictMode) {
throw new ParserException("Could not parse lowerTerm or upperTerm into a number", nfe);
}
return NO_MATCH_FILTER;
}
}
@Override
public Query getQuery(Element e) throws ParserException {
String text = DOMUtils.getText(e);
try {
Query q = null;
if (unSafeParser != null) {
// synchronize on unsafe parser
synchronized (unSafeParser) {
q = unSafeParser.parse(text);
}
} else {
String fieldName = DOMUtils.getAttribute(e, "fieldName", defaultField);
// Create new parser
QueryParser parser = createQueryParser(fieldName, analyzer);
q = parser.parse(text);
}
q.setBoost(DOMUtils.getAttribute(e, "boost", 1.0f));
return q;
} catch (ParseException e1) {
throw new ParserException(e1.getMessage());
}
}
@Override
public SpanQuery getSpanQuery(Element e) throws ParserException {
String fieldName = DOMUtils.getAttributeWithInheritanceOrFail(e, "fieldName");
String value = DOMUtils.getNonBlankTextOrFail(e);
List<SpanQuery> clausesList = new ArrayList<>();
try (TokenStream ts = analyzer.tokenStream(fieldName, value)) {
TermToBytesRefAttribute termAtt = ts.addAttribute(TermToBytesRefAttribute.class);
ts.reset();
while (ts.incrementToken()) {
SpanTermQuery stq =
new SpanTermQuery(new Term(fieldName, BytesRef.deepCopyOf(termAtt.getBytesRef())));
clausesList.add(stq);
}
ts.end();
SpanOrQuery soq = new SpanOrQuery(clausesList.toArray(new SpanQuery[clausesList.size()]));
float boost = DOMUtils.getAttribute(e, "boost", 1.0f);
return new SpanBoostQuery(soq, boost);
} catch (IOException ioe) {
throw new ParserException("IOException parsing value:" + value);
}
}
/* (non-Javadoc)
* @see org.apache.lucene.xmlparser.QueryObjectBuilder#process(org.w3c.dom.Element)
*/
@Override
public Query getQuery(Element e) throws ParserException {
String fieldsList = e.getAttribute("fieldNames"); // a comma-delimited list of fields
String fields[] = defaultFieldNames;
if ((fieldsList != null) && (fieldsList.trim().length() > 0)) {
fields = fieldsList.trim().split(",");
// trim the fieldnames
for (int i = 0; i < fields.length; i++) {
fields[i] = fields[i].trim();
}
}
// Parse any "stopWords" attribute
// TODO MoreLikeThis needs to ideally have per-field stopWords lists - until then
// I use all analyzers/fields to generate multi-field compatible stop list
String stopWords = e.getAttribute("stopWords");
Set<String> stopWordsSet = null;
if ((stopWords != null) && (fields != null)) {
stopWordsSet = new HashSet<String>();
for (String field : fields) {
try (TokenStream ts = analyzer.tokenStream(field, stopWords)) {
CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
ts.reset();
while (ts.incrementToken()) {
stopWordsSet.add(termAtt.toString());
}
ts.end();
ts.close();
} catch (IOException ioe) {
throw new ParserException(
"IoException parsing stop words list in "
+ getClass().getName()
+ ":"
+ ioe.getLocalizedMessage());
}
}
}
MoreLikeThisQuery mlt = new MoreLikeThisQuery(DOMUtils.getText(e), fields, analyzer, fields[0]);
mlt.setMaxQueryTerms(DOMUtils.getAttribute(e, "maxQueryTerms", DEFAULT_MAX_QUERY_TERMS));
mlt.setMinTermFrequency(
DOMUtils.getAttribute(e, "minTermFrequency", DEFAULT_MIN_TERM_FREQUENCY));
mlt.setPercentTermsToMatch(
DOMUtils.getAttribute(e, "percentTermsToMatch", DEFAULT_PERCENT_TERMS_TO_MATCH) / 100);
mlt.setStopWords(stopWordsSet);
int minDocFreq = DOMUtils.getAttribute(e, "minDocFreq", -1);
if (minDocFreq >= 0) {
mlt.setMinDocFreq(minDocFreq);
}
mlt.setBoost(DOMUtils.getAttribute(e, "boost", 1.0f));
return mlt;
}
