private QueryExpression create(Request request, ResourceDefinition resourceDefinition)
throws InvalidQueryException {
String queryString;
if (request.getCardinality() == Request.Cardinality.INSTANCE) {
String idPropertyName = resourceDefinition.getIdPropertyName();
queryString =
String.format("%s:%s", idPropertyName, request.<String>getProperty(idPropertyName));
} else {
queryString = request.getQueryString();
}
QueryExpression queryExpression;
if (queryString != null && !queryString.isEmpty()) {
QueryParser queryParser = new QueryParser(Version.LUCENE_48, "name", new KeywordAnalyzer());
queryParser.setLowercaseExpandedTerms(false);
queryParser.setAllowLeadingWildcard(true);
Query query;
try {
query = queryParser.parse((String) escape(queryString));
} catch (ParseException e) {
throw new InvalidQueryException(e.getMessage());
}
LOG.info("LuceneQuery: " + query);
queryExpression = create(query, resourceDefinition);
} else {
queryExpression = new AlwaysQueryExpression();
}
// add query properties to request so that they are returned
request.addAdditionalSelectProperties(queryExpression.getProperties());
return queryExpression;
}
/**
* give the id list of sentences, from Lucene index
*
* @param input input word
* @param catalogName catalog (domain) name which we'd like to search in
* @param limit how many hits are needed (0 means all)
*/
public List<String> query(String input, String catalogName, int limit) {
List<String> res = new ArrayList<String>();
try {
catalog c = catalogs.get(catalogName);
IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(c.indexPath)));
IndexSearcher searcher = new IndexSearcher(reader);
QueryParser parser = new QueryParser("contents", analyzer);
Query query = parser.parse(QueryParser.escape(input));
int n = limit > 0 ? limit : searcher.count(query);
if (n == 0) n = 1;
TopDocs results = searcher.search(query, n);
int endPos = limit;
if (limit != 0) endPos = Math.min(results.totalHits, limit); // 1st n hits
else endPos = results.totalHits; // all hits
for (int i = 0; i < endPos; i++) {
int id = results.scoreDocs[i].doc;
Document doc = searcher.doc(id);
res.add(doc.get("filename"));
}
reader.close();
return res;
} catch (ParseException e) {
log(e.getMessage());
} catch (IOException e) {
log(e.getMessage());
}
return res;
}
/** This function is only for test search. */
public static List<String> searchQuery(
String indexDir, String queryString, int numResults, CharArraySet stopwords) {
String field = "contents";
List<String> hitPaths = new ArrayList<String>();
try {
IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(indexDir)));
IndexSearcher searcher = new IndexSearcher(reader);
Analyzer analyzer = new MyAnalyzer(Version.LUCENE_44, stopwords);
QueryParser parser = new QueryParser(Version.LUCENE_44, field, analyzer);
Query query;
query = parser.parse(QueryParser.escape(queryString));
TopDocs results = searcher.search(query, null, numResults);
for (ScoreDoc hit : results.scoreDocs) {
String path = searcher.doc(hit.doc).get("path");
hitPaths.add(path.substring(0, path.length() - 4)); // chop off the file extension (".txt")
}
} catch (IOException e) {
System.out.println(" caught a " + e.getClass() + "\n with message: " + e.getMessage());
} catch (ParseException e) {
System.out.println(" caught a " + e.getClass() + "\n with message: " + e.getMessage());
}
return hitPaths;
}
/** This function is only for test search. */
public static List<String> searchQuery(
String indexDir, String queryString, int numResults, CharArraySet stopwords) {
String field = "contents";
List<String> hitPaths = new ArrayList<String>();
try {
IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(indexDir)));
IndexSearcher searcher = new IndexSearcher(reader);
// Used with mySimilarity.java for part E
mySimilarity sim = new mySimilarity();
searcher.setSimilarity(sim);
// Used in part F
// String field="Search_Field";
// the second parameter calls the getAvgLength method and automatically calculates the
// Average Length value
// BM25Parameters.setAverageLength(field,getAvgLen(reader,field));
// BM25Parameters.setB(0.75f);
// BM25Parameters.setK1(2f);
// BM25BooleanQuery query = new BM25BooleanQuery( "Cystic hydroma" ,field,analyzer);
// System.out.println ("Searching for: " + query.toString(field));
// TopDocs top=searcher.search(query, 10);
// ScoreDoc[] docs = top.scoreDocs;
// for (int i = 0; i < 10; i++){
// System.out.println("the document with id= " + docs[i].doc + " has score ="+docs[i].score);
// }
Analyzer analyzer = new MyAnalyzer(Version.LUCENE_44, stopwords);
QueryParser parser = new QueryParser(Version.LUCENE_44, field, analyzer);
Query query;
query = parser.parse(QueryParser.escape(queryString));
TopDocs results = searcher.search(query, null, numResults);
for (ScoreDoc hit : results.scoreDocs) {
String path = searcher.doc(hit.doc).get("path");
hitPaths.add(path.substring(0, path.length() - 4)); // chop off the file extension (".txt")
}
} catch (IOException e) {
System.out.println(" caught a " + e.getClass() + "\n with message: " + e.getMessage());
} catch (ParseException e) {
System.out.println(" caught a " + e.getClass() + "\n with message: " + e.getMessage());
}
return hitPaths;
}
public String giveHelp(String[] words) {
// TODO Add here for example credits, copyright, license
if (words.length <= 1) {
IntroHelp.print(stdout);
return "";
}
if (!indexAvailable()) {
return "";
}
Analyzer multiFieldAnalyzer = Onthology.multiFieldAnalyzer();
try {
String searchFields[] = {"index", "synopsis", "doc"};
QueryParser parser = new MultiFieldQueryParser(searchFields, multiFieldAnalyzer);
StringBuilder sb = new StringBuilder();
for (int i = 1; i < words.length; i++) {
sb.append(" ").append(escapeForQuery(words[i]));
}
Query query;
try {
query = parser.parse(sb.toString());
} catch (ParseException e) {
stderr.println("Cannot parse query: " + sb + ", " + e.getMessage());
return "";
}
if (words[0].equals("help")) {
return reportHelp(words, indexSearcher.search(query, maxSearch).scoreDocs);
} else {
return reportApropos(words, indexSearcher.search(query, maxSearch).scoreDocs);
}
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
return "";
}
@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());
}
}
@ExceptionHandler({ParseException.class})
public String parseExceptionHandler(ParseException pe) {
return "ParseException: query parse exception!" + pe.getMessage();
}