List of usage examples for org.apache.solr.search DocList size
@Override public int size();
From source file:com.mindquarry.search.solr.request.JSONWriter.java
License:Open Source License
public void writeDocList(String name, DocList ids, Set<String> fields, Map otherFields) throws IOException { boolean includeScore = false; if (fields != null) { includeScore = fields.contains("score"); if (fields.size() == 0 || (fields.size() == 1 && includeScore) || fields.contains("*")) { fields = null; // null means return all stored fields }/* w ww . j av a2 s . co m*/ } int sz = ids.size(); writer.write('{'); incLevel(); writeKey("numFound", false); writeInt(null, ids.matches()); writer.write(','); writeKey("start", false); writeInt(null, ids.offset()); if (includeScore) { writer.write(','); writeKey("maxScore", false); writeFloat(null, ids.maxScore()); } writer.write(','); // indent(); writeKey("docs", false); writer.write('['); incLevel(); boolean first = true; DocIterator iterator = ids.iterator(); for (int i = 0; i < sz; i++) { int id = iterator.nextDoc(); Document doc = searcher.doc(id); if (first) { first = false; } else { writer.write(','); } indent(); writeDoc(null, doc, fields, (includeScore ? iterator.score() : 0.0f), includeScore); } decLevel(); writer.write(']'); if (otherFields != null) { writeMap(null, otherFields, true, false); } decLevel(); indent(); writer.write('}'); }
From source file:com.mindquarry.search.solr.request.QuickSearchSearchJSONWriter.java
License:Open Source License
public void writeDocList(String name, DocList ids, Set<String> fields, Map otherFields) throws IOException { boolean includeScore = false; if (fields != null) { includeScore = fields.contains("score"); //$NON-NLS-1$ if (fields.size() == 0 || (fields.size() == 1 && includeScore) || fields.contains("*")) { //$NON-NLS-1$ fields = null; // null means return all stored fields }//from w ww .j a v a 2 s . c o m } int sz = ids.size(); writer.write('{'); incLevel(); writeKey("numFound", false); //$NON-NLS-1$ writeInt(null, ids.matches()); writer.write(','); writeKey("start", false); //$NON-NLS-1$ writeInt(null, ids.offset()); if (includeScore) { writer.write(','); writeKey("maxScore", false); //$NON-NLS-1$ writeFloat(null, ids.maxScore()); } writer.write(','); writeKey("docs", false); //$NON-NLS-1$ writer.write('{'); incLevel(); HashMap<String, List<DocWithScore>> sets = new HashMap<String, List<DocWithScore>>(); DocIterator iterator = ids.iterator(); for (int i = 0; i < sz; i++) { int id = iterator.nextDoc(); Document doc = searcher.doc(id); for (Fieldable ff : (List<Fieldable>) doc.getFields()) { String fname = ff.name(); String fval = ff.stringValue(); if (fname.equals("type")) { //$NON-NLS-1$ String type = fval; if (type.equals("wiki")) { //$NON-NLS-1$ type = type.replaceFirst("w", "W"); //$NON-NLS-1$ //$NON-NLS-2$ } else if (type.equals("tasks")) { //$NON-NLS-1$ type = type.replaceFirst("t", "T"); //$NON-NLS-1$ //$NON-NLS-2$ } if (!sets.containsKey(type)) { sets.put(type, new ArrayList<DocWithScore>()); } if (includeScore) { sets.get(type).add(new DocWithScore(doc, iterator.score())); } else { sets.get(type).add(new DocWithScore(doc, 0.0f)); } } } } boolean firstSet = true; Set<String> keys = sets.keySet(); Iterator<String> kIt = keys.iterator(); while (kIt.hasNext()) { String key = kIt.next(); List<DocWithScore> docs = sets.get(key); if (firstSet) { firstSet = false; } else { writer.write(','); } indent(); writeKey(key, false); writer.write('['); incLevel(); boolean firstDoc = true; for (Iterator iter = docs.iterator(); iter.hasNext();) { DocWithScore doc = (DocWithScore) iter.next(); if (firstDoc) { firstDoc = false; } else { writer.write(','); } writer.write('{'); boolean firstEntry = true; for (Fieldable ff : (List<Fieldable>) doc.getDoc().getFields()) { String fname = ff.name(); if ((fname.equals("location")) || (fname.equals("title"))) { //$NON-NLS-1$ //$NON-NLS-2$ if (firstEntry) { firstEntry = false; } else { writer.write(','); } indent(); writeKey(fname, false); if (fname.equals("location")) { //$NON-NLS-1$ writeStr(null, transformToWebPath(ff.stringValue()), true); } else { writeStr(null, ff.stringValue(), true); } } } // write score if (includeScore) { writer.write(','); indent(); writeKey("score", false); //$NON-NLS-1$ Float score = doc.getScore() * 100; int absScore = score.intValue(); writeInt(null, absScore); } indent(); writer.write('}'); } writer.write(']'); } decLevel(); indent(); writer.write('}'); if (otherFields != null) { writeMap(null, otherFields, true, false); } decLevel(); indent(); writer.write('}'); }
From source file:com.o19s.solr.swan.highlight.SwanHighlighter.java
License:Apache License
/** * Generates a list of Highlighted query fragments for each item in a list * of documents, or returns null if highlighting is disabled. * * @param docs query results/*from ww w. jav a 2 s.co m*/ * @param query the query * @param req the current request * @param defaultFields default list of fields to summarize * * @return NamedList containing a NamedList for each document, which in * turns contains sets (field, summary) pairs. */ @Override @SuppressWarnings("unchecked") public NamedList<Object> doHighlighting(DocList docs, Query query, SolrQueryRequest req, String[] defaultFields) throws IOException { NamedList fragments = new SimpleOrderedMap(); SolrParams params = req.getParams(); if (!isHighlightingEnabled(params)) return null; SolrIndexSearcher searcher = req.getSearcher(); IndexSchema schema = searcher.getSchema(); String[] fieldNames = getHighlightFields(query, req, defaultFields); Set<String> fset = new HashSet<String>(); { // pre-fetch documents using the Searcher's doc cache Collections.addAll(fset, fieldNames); // fetch unique key if one exists. SchemaField keyField = schema.getUniqueKeyField(); if (null != keyField) fset.add(keyField.getName()); } //CHANGE start // int[] docIds = new int[docs.swordize()]; TreeSet<Integer> docIds = new TreeSet<Integer>(); DocIterator iterator = docs.iterator(); for (int i = 0; i < docs.size(); i++) { docIds.add(iterator.nextDoc()); } // Get Frag list builder String fragListBuilderString = params.get(HighlightParams.FRAG_LIST_BUILDER).toLowerCase(); FragListBuilder fragListBuilder; if (fragListBuilderString.equals("single")) { fragListBuilder = new SingleFragListBuilder(); } else { fragListBuilder = new com.o19s.solr.swan.highlight.SimpleFragListBuilder(); } // get FastVectorHighlighter instance out of the processing loop SpanAwareFastVectorHighlighter safvh = new SpanAwareFastVectorHighlighter( // FVH cannot process hl.usePhraseHighlighter parameter per-field basis params.getBool(HighlightParams.USE_PHRASE_HIGHLIGHTER, true), // FVH cannot process hl.requireFieldMatch parameter per-field basis params.getBool(HighlightParams.FIELD_MATCH, false), fragListBuilder, //new com.o19s.solr.swan.highlight.ScoreOrderFragmentsBuilder(), new WordHashFragmentsBuilder(), // List of docIds to filter spans docIds); safvh.setPhraseLimit(params.getInt(HighlightParams.PHRASE_LIMIT, Integer.MAX_VALUE)); SpanAwareFieldQuery fieldQuery = safvh.getFieldQuery(query, searcher.getIndexReader(), docIds); // Highlight each document for (int docId : docIds) { Document doc = searcher.doc(docId, fset); NamedList docSummaries = new SimpleOrderedMap(); for (String fieldName : fieldNames) { fieldName = fieldName.trim(); if (useFastVectorHighlighter(params, schema, fieldName)) doHighlightingByFastVectorHighlighter(safvh, fieldQuery, req, docSummaries, docId, doc, fieldName); else doHighlightingByHighlighter(query, req, docSummaries, docId, doc, fieldName); } String printId = schema.printableUniqueKey(doc); fragments.add(printId == null ? null : printId, docSummaries); } //CHANGE end return fragments; }
From source file:com.search.MySearchHandler.java
License:Apache License
@Override public void handleRequestBody(SolrQueryRequest req, SolrQueryResponse rsp) throws Exception { // int sleep = req.getParams().getInt("sleep",0); // if (sleep > 0) {log.error("SLEEPING for " + sleep); // Thread.sleep(sleep);} /*** Pre-processing of the Query by REGEX starts here -------------- ***/ SolrParams originalParams = req.getOriginalParams(); SolrParams psuedoParams = req.getParams(); // These psuedoParams keep // changing/* www . j a v a 2 s . co m*/ if (originalParams.get(CommonParams.Q) != null) { String finalQuery; String originalQuery = originalParams.get(CommonParams.Q); rsp.add("Original query", originalQuery); SchemaField keyField = null; keyField = req.getCore().getLatestSchema().getUniqueKeyField(); if (keyField != null) { fieldSet.add(keyField.getName()); } /*** * START CODE TO PARSE QUERY * * Arafath's code to prepare query starts here The query should be * in the following format -> * * * * Example : Original Query: * "Which musical object did russ conway play" Temporary Query : * "relations:instrument AND entity:enty" // Generate the relation * Final Query : "name:"russ conway" AND occupation:musician" */ ParsedQuestion parsedq = new ParsedQuestion(); parsedq = parseQues(originalQuery); if (parsedq != null) { System.out.println(parsedq); Map<Integer, String> relationstr = getRelation(parsedq.getRelationKeyWord(), parsedq.getWhtype(), req); /** * END CODE TO PARSE QUERY */ /*** Final Phase starts here ***/ finalQuery = "title:\"" + parsedq.getSearchName() + "\""; NamedList finalparamsList = req.getParams().toNamedList(); finalparamsList.setVal(finalparamsList.indexOf(CommonParams.Q, 0), finalQuery); psuedoParams = SolrParams.toSolrParams(finalparamsList); if (psuedoParams.get(CommonParams.SORT) == null) { finalparamsList.add(CommonParams.SORT, "score desc"); } else { finalparamsList.setVal(finalparamsList.indexOf(CommonParams.SORT, 0), "score desc"); } int documentsRetrieved = 0; if (relationstr != null) { rsp.add("total relations retrieved", relationstr.size()); rsp.add("relations", relationstr); NamedList finaldocresults = new NamedList(); NamedList forwarddocresults = new NamedList(); Set<String> checkDocuments = new HashSet<String>(); for (int i = 0; i < relationstr.size() && (documentsRetrieved < 10); i++) { NamedList relationdocresults = new NamedList(); String desiredField = relationstr.get(i); Set<String> tempFieldSet = new HashSet<String>(); int docsRetrievedforThisRelation = 0; tempFieldSet.add(desiredField); psuedoParams = SolrParams.toSolrParams(finalparamsList); if (psuedoParams.get(CommonParams.FL) == null) { finalparamsList.add(CommonParams.FL, desiredField); } else { finalparamsList.setVal(finalparamsList.indexOf(CommonParams.FL, 0), desiredField); } SolrQueryRequest finalreq = new LocalSolrQueryRequest(req.getCore(), finalparamsList); rsp.add("Final Query", finalreq.getParams().get(CommonParams.Q)); SolrQueryResponse finalrsp = new SolrQueryResponse(); ResponseBuilder finalrb = new ResponseBuilder(finalreq, finalrsp, components); for (SearchComponent c : components) { c.prepare(finalrb); c.process(finalrb); } DocList finaldocs = finalrb.getResults().docList; if (finaldocs == null || finaldocs.size() == 0) { log.debug("No results"); // support for reverse query } else { DocIterator finaliterator = finaldocs.iterator(); Document finaldoc; for (int j = 0; j < finaldocs.size(); j++) { try { if (finaliterator.hasNext()) { int finaldocid = finaliterator.nextDoc(); finaldoc = finalrb.req.getSearcher().doc(finaldocid, tempFieldSet); if (!checkDocuments.contains(finaldoc.get("id"))) { if (finaldoc.get(desiredField) != null) { checkDocuments.add(finaldoc.get("id")); docsRetrievedforThisRelation++; documentsRetrieved++; relationdocresults.add(finaldoc.get("title"), finaldoc); if (documentsRetrieved >= 10) { break; } } } } } catch (IOException ex) { java.util.logging.Logger.getLogger(MySearchHandler.class.getName()) .log(Level.SEVERE, null, ex); } } if (docsRetrievedforThisRelation > 0) { rsp.add("docs retrieved for : " + desiredField, docsRetrievedforThisRelation); forwarddocresults.add(desiredField, relationdocresults); } } finalreq.close(); if (documentsRetrieved > 0) { rsp.add("type", "forward"); rsp.add("final results", forwarddocresults); } } if (documentsRetrieved == 0) { NamedList reversedocresults = new NamedList(); relationstr = getRelationReverse(parsedq.getRelationKeyWord(), req); System.out.println(relationstr); StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_46); String reversequery = ""; for (int i = 0; i < relationstr.size(); i++) { QueryParser relationsparser = new QueryParser(Version.LUCENE_46, relationstr.get(i), analyzer); try { reversequery += relationsparser.parse(parsedq.getSearchName()).toString() + " "; } catch (ParseException e) { e.printStackTrace(); } } QueryParser relationsparser = new QueryParser(Version.LUCENE_46, "infotype", analyzer); reversequery += relationsparser.parse(parsedq.getWhtype().firstKey().toLowerCase()); NamedList reverseList = req.getParams().toNamedList(); psuedoParams = SolrParams.toSolrParams(reverseList); reverseList.setVal(reverseList.indexOf(CommonParams.Q, 0), reversequery); SolrQueryRequest reversereq = new LocalSolrQueryRequest(req.getCore(), reverseList); SolrQueryResponse reversersp = new SolrQueryResponse(); ResponseBuilder reverserb = new ResponseBuilder(reversereq, reversersp, components); for (SearchComponent c : components) { try { c.prepare(reverserb); c.process(reverserb); } catch (IOException ex) { java.util.logging.Logger.getLogger(MySearchHandler.class.getName()) .log(Level.SEVERE, null, ex); } } DocList reversedocs = reverserb.getResults().docList; if (reversedocs == null || reversedocs.size() == 0) { log.debug("No results"); // GET SECOND entry from WHTYPE .. search with that .. } else { // NamedList docresults = new NamedList(); DocIterator reverseiterator = reversedocs.iterator(); Document reversedoc; int docScore = 0; for (int m = 0; m < reversedocs.size(); m++) { try { int reversedocid = reverseiterator.nextDoc(); reversedoc = reverserb.req.getSearcher().doc(reversedocid, fieldSet); if (reversedoc.get("title") != null) { documentsRetrieved++; reversedocresults.add(reversedoc.get("title"), reversedoc); if (documentsRetrieved >= 10) { break; } } } catch (IOException ex) { java.util.logging.Logger.getLogger(MySearchHandler.class.getName()) .log(Level.SEVERE, null, ex); } } } if (documentsRetrieved == 0) { rsp.add("message", "No Results found. Try another query!"); } else { rsp.add("type", "reverse"); rsp.add("final results", reversedocresults); } reversereq.close(); } } else { if (documentsRetrieved == 0) { rsp.add("message", "No Results found. Please rephrase the query!"); } } } else { rsp.add("message", "This is not a valid query!"); } } else { rsp.add("message", "User should provide at least one word as a query!"); } }
From source file:com.search.MySearchHandler.java
License:Apache License
private Map<Integer, String> getRelationReverse(String value, SolrQueryRequest req) { /*** Galla's modified code starts here ---- > * //from w w w. j a v a 2 s . c om */ StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_46); QueryParser relationsparser = new QueryParser(Version.LUCENE_46, "relations", analyzer); QueryParser entityparser = new QueryParser(Version.LUCENE_46, "entity", analyzer); QueryParser fieldidparser = new QueryParser(Version.LUCENE_46, "fieldid", analyzer); Map<Integer, String> desiredFieldList = null; int desiredFieldsCount = 0; String desiredRelation = null; Set<String> checkRelation = null; if (desiredFieldsCount < 5) { desiredFieldList = new HashMap<Integer, String>(); checkRelation = new HashSet<String>(); NamedList tempparamsList = req.getParams().toNamedList(); SolrParams psuedoParams = SolrParams.toSolrParams(tempparamsList); if (psuedoParams.get(CommonParams.SORT) == null) { tempparamsList.add(CommonParams.SORT, "score desc"); } else { tempparamsList.setVal(tempparamsList.indexOf(CommonParams.SORT, 0), "score desc"); } SolrQueryRequest firstreq = null; SolrQueryResponse firstrsp = null; ResponseBuilder firstrb = null; DocList docs = null; String relString = ""; String fieldString = ""; try { relString = relationsparser.parse(value).toString(); fieldString = fieldidparser.parse(value).toString(); } catch (ParseException e) { e.printStackTrace(); } // (+relations:"children" and +entity:"num") or (relations:"children" and fieldid:"children") or (fieldid:"children" and entity:"num") String tempQuery = "(" + relString + ")" + " OR (" + fieldString + ")"; System.out.println(tempQuery); tempparamsList.setVal(tempparamsList.indexOf(CommonParams.Q, 0), tempQuery); firstreq = new LocalSolrQueryRequest(req.getCore(), tempparamsList); firstrsp = new SolrQueryResponse(); firstrb = new ResponseBuilder(firstreq, firstrsp, components); for (SearchComponent c : components) { try { c.prepare(firstrb); c.process(firstrb); } catch (IOException ex) { java.util.logging.Logger.getLogger(MySearchHandler.class.getName()).log(Level.SEVERE, null, ex); } } docs = firstrb.getResults().docList; if (docs == null || docs.size() == 0) { log.debug("No results"); // GET SECOND entry from WHTYPE .. search with that .. } else { // NamedList docresults = new NamedList(); DocIterator iterator = docs.iterator(); Document doc; int docScore = 0; for (int i = 0; i < docs.size(); i++) { try { int docid = iterator.nextDoc(); doc = firstrb.req.getSearcher().doc(docid, fieldSet); desiredRelation = doc.get("fieldid"); if (!checkRelation.contains(desiredRelation)) { checkRelation.add(desiredRelation); desiredFieldList.put(desiredFieldsCount++, desiredRelation); System.out.println("vgalla's relation : " + desiredRelation); if (desiredFieldsCount >= 5) { return desiredFieldList; } } } catch (IOException ex) { java.util.logging.Logger.getLogger(MySearchHandler.class.getName()).log(Level.SEVERE, null, ex); } } } firstreq.close(); /*** Galla's code ends here ----- > * */ } return desiredFieldList; }
From source file:com.search.MySearchHandler.java
License:Apache License
private static Map<Integer, String> getRelation(String value, TreeMap<String, Double> whtype, SolrQueryRequest req) {/*from w ww.j a v a 2 s.co m*/ /*** * Galla's modified code starts here ---- > * */ Map<Integer, String> desiredFieldList = null; if (whtype != null) { StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_46); QueryParser relationsparser = new QueryParser(Version.LUCENE_46, "relations", analyzer); QueryParser entityparser = new QueryParser(Version.LUCENE_46, "entity", analyzer); QueryParser fieldidparser = new QueryParser(Version.LUCENE_46, "fieldid", analyzer); int desiredFieldsCount = 0; String desiredRelation = null; Set<String> whtypeSet = whtype.keySet(); Set<String> checkRelation = null; if (!whtypeSet.isEmpty() && (desiredFieldsCount < 5)) { desiredFieldList = new HashMap<Integer, String>(); checkRelation = new HashSet<String>(); NamedList tempparamsList = req.getParams().toNamedList(); SolrParams psuedoParams = SolrParams.toSolrParams(tempparamsList); if (psuedoParams.get(CommonParams.SORT) == null) { tempparamsList.add(CommonParams.SORT, "score desc"); } else { tempparamsList.setVal(tempparamsList.indexOf(CommonParams.SORT, 0), "score desc"); } SolrQueryRequest firstreq = null; SolrQueryResponse firstrsp = null; ResponseBuilder firstrb = null; DocList docs = null; for (String tempStr : whtypeSet) { String tempType = tempStr.toLowerCase().trim(); String relString = ""; String entyString = ""; String fieldString = ""; try { relString = relationsparser.parse(value).toString(); entyString = entityparser.parse(tempType).toString(); fieldString = fieldidparser.parse(value).toString(); } catch (ParseException e) { e.printStackTrace(); } // (+relations:"children" and +entity:"num") or // (relations:"children" and fieldid:"children") or // (fieldid:"children" and entity:"num") String tempQuery = "(" + relString + " AND " + entyString + ")" + " OR " + "(" + relString + " AND " + fieldString + ")" + " OR " + "(" + fieldString + " AND " + entyString + ")"; System.out.println(tempQuery); tempparamsList.setVal(tempparamsList.indexOf(CommonParams.Q, 0), tempQuery); firstreq = new LocalSolrQueryRequest(req.getCore(), tempparamsList); firstrsp = new SolrQueryResponse(); firstrb = new ResponseBuilder(firstreq, firstrsp, components); for (SearchComponent c : components) { try { c.prepare(firstrb); c.process(firstrb); } catch (IOException ex) { java.util.logging.Logger.getLogger(MySearchHandler.class.getName()).log(Level.SEVERE, null, ex); } } docs = firstrb.getResults().docList; if (docs == null || docs.size() == 0) { log.debug("No results"); // GET SECOND entry from WHTYPE .. search with that .. } else { // NamedList docresults = new NamedList(); DocIterator iterator = docs.iterator(); Document doc; int docScore = 0; for (int i = 0; i < docs.size(); i++) { try { int docid = iterator.nextDoc(); doc = firstrb.req.getSearcher().doc(docid, fieldSet); desiredRelation = doc.get("fieldid"); if (!checkRelation.contains(desiredRelation)) { checkRelation.add(desiredRelation); desiredFieldList.put(desiredFieldsCount++, desiredRelation); System.out.println("vgalla's relation : " + desiredRelation); if (desiredFieldsCount >= 5) { return desiredFieldList; } } } catch (IOException ex) { java.util.logging.Logger.getLogger(MySearchHandler.class.getName()) .log(Level.SEVERE, null, ex); } } } firstreq.close(); /*** * Galla's code ends here ----- > * */ String exrelstring = ""; String[] strarray = value.split(" "); for (int i = 0; i < strarray.length; i++) { if (exrelmap.containsKey(strarray[i].toLowerCase().trim())) { exrelstring += exrelmap.get(strarray[i].toLowerCase().trim()); } } if (!exrelstring.equals("")) { String[] temp = exrelstring.split("~~"); for (int i = 0; i < temp.length; i++) { if (!temp[i].trim().equals("")) { String mapdetect = mappingmap.get(temp[i].trim()); if (mapdetect.toLowerCase().trim().equals(tempType)) { desiredRelation = temp[i].trim(); if (!checkRelation.contains(desiredRelation)) { checkRelation.add(desiredRelation); desiredFieldList.put(desiredFieldsCount++, desiredRelation); System.out.println("arafath's relation : " + desiredRelation); if (desiredFieldsCount >= 5) { return desiredFieldList; } } } } } } } } } return desiredFieldList; }
From source file:com.searchbox.solr.CategoryLikeThis.java
License:Apache License
@Override public void handleRequestBody(SolrQueryRequest req, SolrQueryResponse rsp) throws Exception { numRequests++;/* w w w . ja v a 2 s. c o m*/ long startTime = System.currentTimeMillis(); if (!keystate) { LOGGER.error( "License key failure, not performing clt query. Please email contact@searchbox.com for more information."); return; } try { SolrParams params = req.getParams(); String senseField = params.get(SenseParams.SENSE_FIELD, SenseParams.DEFAULT_SENSE_FIELD); BooleanQuery catfilter = new BooleanQuery(); // Set field flags ReturnFields returnFields = new SolrReturnFields(req); rsp.setReturnFields(returnFields); int flags = 0; if (returnFields.wantsScore()) { flags |= SolrIndexSearcher.GET_SCORES; } String defType = params.get(QueryParsing.DEFTYPE, QParserPlugin.DEFAULT_QTYPE); String q = params.get(CommonParams.Q); Query query = null; SortSpec sortSpec = null; List<Query> filters = new LinkedList<Query>(); List<RealTermFreqVector> prototypetfs = new LinkedList<RealTermFreqVector>(); try { if (q != null) { QParser parser = QParser.getParser(q, defType, req); query = parser.getQuery(); sortSpec = parser.getSort(true); } String[] fqs = req.getParams().getParams(CommonParams.FQ); if (fqs != null && fqs.length != 0) { for (String fq : fqs) { if (fq != null && fq.trim().length() != 0) { QParser fqp = QParser.getParser(fq, null, req); filters.add(fqp.getQuery()); } } } } catch (Exception e) { numErrors++; throw new SolrException(SolrException.ErrorCode.BAD_REQUEST, e); } SolrIndexSearcher searcher = req.getSearcher(); DocListAndSet cltDocs = null; // Parse Required Params // This will either have a single Reader or valid query Reader reader = null; try { if (q == null || q.trim().length() < 1) { Iterable<ContentStream> streams = req.getContentStreams(); if (streams != null) { Iterator<ContentStream> iter = streams.iterator(); if (iter.hasNext()) { reader = iter.next().getReader(); } if (iter.hasNext()) { numErrors++; throw new SolrException(SolrException.ErrorCode.BAD_REQUEST, "SenseLikeThis does not support multiple ContentStreams"); } } } int start = params.getInt(CommonParams.START, 0); int rows = params.getInt(CommonParams.ROWS, 10); // Find documents SenseLikeThis - either with a reader or a query // -------------------------------------------------------------------------------- if (reader != null) { numErrors++; throw new RuntimeException("SLT based on a reader is not yet implemented"); } else if (q != null) { LOGGER.debug("Query for category:\t" + query); DocList match = searcher.getDocList(query, null, null, 0, 10, flags); // get first 10 if (match.size() == 0) { // no docs to make prototype! LOGGER.info("No documents found for prototype!"); rsp.add("response", new DocListAndSet()); return; } HashMap<String, Float> overallFreqMap = new HashMap<String, Float>(); // Create the TF of blah blah blah DocIterator iterator = match.iterator(); while (iterator.hasNext()) { // do a MoreLikeThis query for each document in results int id = iterator.nextDoc(); LOGGER.trace("Working on doc:\t" + id); RealTermFreqVector rtv = new RealTermFreqVector(id, searcher.getIndexReader(), senseField); for (int zz = 0; zz < rtv.getSize(); zz++) { Float prev = overallFreqMap.get(rtv.getTerms()[zz]); if (prev == null) { prev = 0f; } overallFreqMap.put(rtv.getTerms()[zz], rtv.getFreqs()[zz] + prev); } prototypetfs.add(rtv); } List<String> sortedKeys = Ordering.natural().onResultOf(Functions.forMap(overallFreqMap)) .immutableSortedCopy(overallFreqMap.keySet()); int keyiter = Math.min(sortedKeys.size() - 1, BooleanQuery.getMaxClauseCount() - 1); LOGGER.debug("I have this many terms:\t" + sortedKeys.size()); LOGGER.debug("And i'm going to use this many:\t" + keyiter); for (; keyiter >= 0; keyiter--) { TermQuery tq = new TermQuery(new Term(senseField, sortedKeys.get(keyiter))); catfilter.add(tq, BooleanClause.Occur.SHOULD); } } else { numErrors++; throw new SolrException(SolrException.ErrorCode.BAD_REQUEST, "CategoryLikeThis requires either a query (?q=) or text to find similar documents."); } LOGGER.debug("document filter is: \t" + catfilter); CategorizationBase model = new CategorizationBase(prototypetfs); CategoryQuery clt = CategoryQuery.CategoryQueryForDocument(catfilter, model, searcher.getIndexReader(), senseField); DocSet filtered = searcher.getDocSet(filters); cltDocs = searcher.getDocListAndSet(clt, filtered, Sort.RELEVANCE, start, rows, flags); } finally { if (reader != null) { reader.close(); } } if (cltDocs == null) { numEmpty++; cltDocs = new DocListAndSet(); // avoid NPE } rsp.add("response", cltDocs.docList); // maybe facet the results if (params.getBool(FacetParams.FACET, false)) { if (cltDocs.docSet == null) { rsp.add("facet_counts", null); } else { SimpleFacets f = new SimpleFacets(req, cltDocs.docSet, params); rsp.add("facet_counts", f.getFacetCounts()); } } } catch (Exception e) { numErrors++; } finally { totalTime += System.currentTimeMillis() - startTime; } }
From source file:com.searchbox.solr.SenseLikeThisHandler.java
License:Apache License
@Override public void handleRequestBody(SolrQueryRequest req, SolrQueryResponse rsp) throws Exception { NamedList<Object> timinginfo = new NamedList<Object>(); numRequests++;//from ww w .j a v a 2 s .c om long startTime = System.currentTimeMillis(); long lstartTime = System.currentTimeMillis(); if (!keystate) { LOGGER.error( "License key failure, not performing sense query. Please email contact@searchbox.com for more information."); return; } boolean fromcache = false; try { SolrParams params = req.getParams(); int start = params.getInt(CommonParams.START, 0); int rows = params.getInt(CommonParams.ROWS, 10); HashSet<String> toIgnore = (new HashSet<String>()); toIgnore.add("start"); toIgnore.add("rows"); toIgnore.add("fl"); toIgnore.add("wt"); toIgnore.add("indent"); SolrCacheKey key = new SolrCacheKey(params, toIgnore); // Set field flags ReturnFields returnFields = new SolrReturnFields(req); rsp.setReturnFields(returnFields); int flags = 0; if (returnFields.wantsScore()) { flags |= SolrIndexSearcher.GET_SCORES; } String defType = params.get(QueryParsing.DEFTYPE, QParserPlugin.DEFAULT_QTYPE); String q = params.get(CommonParams.Q); Query query = null; QueryReductionFilter qr = null; SortSpec sortSpec = null; List<Query> filters = new ArrayList<Query>(); try { if (q != null) { QParser parser = QParser.getParser(q, defType, req); query = parser.getQuery(); sortSpec = parser.getSort(true); } String[] fqs = req.getParams().getParams(CommonParams.FQ); if (fqs != null && fqs.length != 0) { for (String fq : fqs) { if (fq != null && fq.trim().length() != 0) { QParser fqp = QParser.getParser(fq, null, req); filters.add(fqp.getQuery()); } } } } catch (Exception e) { numErrors++; throw new SolrException(SolrException.ErrorCode.BAD_REQUEST, e); } timinginfo.add("Parse Query time", System.currentTimeMillis() - lstartTime); LOGGER.debug("Parsed Query Time:\t" + (System.currentTimeMillis() - lstartTime)); lstartTime = System.currentTimeMillis(); SolrIndexSearcher searcher = req.getSearcher(); SchemaField uniqueKeyField = searcher.getSchema().getUniqueKeyField(); // Parse Required Params // This will either have a single Reader or valid query // Find documents SenseLikeThis - either with a reader or a query // -------------------------------------------------------------------------------- SenseQuery slt = null; if (q == null) { numErrors++; throw new SolrException(SolrException.ErrorCode.BAD_REQUEST, "SenseLikeThis requires either a query (?q=) or text to find similar documents."); } // Matching options boolean includeMatch = params.getBool(MoreLikeThisParams.MATCH_INCLUDE, true); int matchOffset = params.getInt(MoreLikeThisParams.MATCH_OFFSET, 0); // Find the base match DocList match = searcher.getDocList(query, null, null, matchOffset, 1, flags); // only get the first one... if (includeMatch) { rsp.add("match", match); } DocIterator iterator = match.iterator(); if (!iterator.hasNext()) { numErrors++; throw new SolrException(SolrException.ErrorCode.BAD_REQUEST, "SenseLikeThis no document found matching request."); } int id = iterator.nextDoc(); timinginfo.add("Find Query Doc", System.currentTimeMillis() - lstartTime); LOGGER.debug("Find Query Doc:\t" + (System.currentTimeMillis() - lstartTime)); lstartTime = System.currentTimeMillis(); SolrCache sc = searcher.getCache("com.searchbox.sltcache"); DocListAndSet sltDocs = null; if (sc != null) { //try to get from cache sltDocs = (DocListAndSet) sc.get(key.getSet()); } else { LOGGER.error("com.searchbox.sltcache not defined, can't cache slt queries"); } sltDocs = (DocListAndSet) sc.get(key.getSet()); if (start + rows > 1000 || sltDocs == null || !params.getBool(CommonParams.CACHE, true)) { //not in cache, need to do search BooleanQuery bq = new BooleanQuery(); Document doc = searcher.getIndexReader().document(id); bq.add(new TermQuery(new Term(uniqueKeyField.getName(), uniqueKeyField.getType().storedToIndexed(doc.getField(uniqueKeyField.getName())))), BooleanClause.Occur.MUST_NOT); filters.add(bq); String[] senseFields = splitList .split(params.get(SenseParams.SENSE_FIELD, SenseParams.DEFAULT_SENSE_FIELD)); String senseField = (senseFields[0] != null) ? senseFields[0] : SenseParams.DEFAULT_SENSE_FIELD; //TODO more intelligent handling of multiple fields , can probably do a boolean junction of multiple sensequeries, but this will be slow long maxlength = -1; for (String possibleField : senseFields) { try { long flength = doc.getField(possibleField).stringValue().length(); if (flength > maxlength) { senseField = possibleField; maxlength = flength; } } catch (Exception e) { System.out.println("Error: " + e.getMessage()); } } LOGGER.debug("Using sense field :\t" + (senseField)); String CKBid = params.get(SenseParams.SENSE_CKB, SenseParams.SENSE_CKB_DEFAULT); RealTermFreqVector rtv = new RealTermFreqVector(id, searcher.getIndexReader(), senseField); timinginfo.add("Make real term freq vector", System.currentTimeMillis() - lstartTime); lstartTime = System.currentTimeMillis(); qr = new QueryReductionFilter(rtv, CKBid, searcher, senseField); qr.setNumtermstouse(params.getInt(SenseParams.SENSE_QR_NTU, SenseParams.SENSE_QR_NTU_DEFAULT)); qr.setThreshold(params.getInt(SenseParams.SENSE_QR_THRESH, SenseParams.SENSE_QR_THRESH_DEFAULT)); qr.setMaxDocSubSet(params.getInt(SenseParams.SENSE_QR_MAXDOC, SenseParams.SENSE_QR_MAXDOC_DEFAULT)); qr.setMinDocSetSizeForFilter( params.getInt(SenseParams.SENSE_MINDOC4QR, SenseParams.SENSE_MINDOC4QR_DEFAULT)); numTermsUsed += qr.getNumtermstouse(); numTermsConsidered += rtv.getSize(); timinginfo.add("Setup SLT query", System.currentTimeMillis() - lstartTime); LOGGER.debug("Setup SLT query:\t" + (System.currentTimeMillis() - lstartTime)); lstartTime = System.currentTimeMillis(); DocList subFiltered = qr.getSubSetToSearchIn(filters); timinginfo.add("Do Query Redux", System.currentTimeMillis() - lstartTime); LOGGER.debug("Do query redux:\t" + (System.currentTimeMillis() - lstartTime)); lstartTime = System.currentTimeMillis(); numFiltered += qr.getFiltered().docList.size(); numSubset += subFiltered.size(); LOGGER.info("Number of documents to search:\t" + subFiltered.size()); slt = new SenseQuery(rtv, senseField, CKBid, params.getFloat(SenseParams.SENSE_WEIGHT, SenseParams.DEFAULT_SENSE_WEIGHT), null); LOGGER.debug("Setup sense query:\t" + (System.currentTimeMillis() - lstartTime)); timinginfo.add("Setup sense query", System.currentTimeMillis() - lstartTime); lstartTime = System.currentTimeMillis(); sltDocs = searcher.getDocListAndSet(slt, subFiltered, Sort.RELEVANCE, 0, 1000, flags); timinginfo.add("Do sense query", System.currentTimeMillis() - lstartTime); lstartTime = System.currentTimeMillis(); LOGGER.debug("Adding this keyto cache:\t" + key.getSet().toString()); searcher.getCache("com.searchbox.sltcache").put(key.getSet(), sltDocs); } else { fromcache = true; timinginfo.add("Getting from cache", System.currentTimeMillis() - lstartTime); LOGGER.debug("Got result from cache"); lstartTime = System.currentTimeMillis(); } if (sltDocs == null) { numEmpty++; sltDocs = new DocListAndSet(); // avoid NPE } rsp.add("response", sltDocs.docList.subset(start, rows)); // maybe facet the results if (params.getBool(FacetParams.FACET, false)) { if (sltDocs.docSet == null) { rsp.add("facet_counts", null); } else { SimpleFacets f = new SimpleFacets(req, sltDocs.docSet, params); rsp.add("facet_counts", f.getFacetCounts()); } } timinginfo.add("Facet parts", System.currentTimeMillis() - lstartTime); LOGGER.debug("Facet parts:\t" + (System.currentTimeMillis() - lstartTime)); // Debug info, not doing it for the moment. boolean dbg = req.getParams().getBool(CommonParams.DEBUG_QUERY, false); boolean dbgQuery = false, dbgResults = false; if (dbg == false) {//if it's true, we are doing everything anyway. String[] dbgParams = req.getParams().getParams(CommonParams.DEBUG); if (dbgParams != null) { for (int i = 0; i < dbgParams.length; i++) { if (dbgParams[i].equals(CommonParams.QUERY)) { dbgQuery = true; } else if (dbgParams[i].equals(CommonParams.RESULTS)) { dbgResults = true; } } } } else { dbgQuery = true; dbgResults = true; } // Copied from StandardRequestHandler... perhaps it should be added to doStandardDebug? if (dbg == true) { try { lstartTime = System.currentTimeMillis(); NamedList<Object> dbgInfo = SolrPluginUtils.doStandardDebug(req, q, slt, sltDocs.docList.subset(start, rows), dbgQuery, dbgResults); dbgInfo.add("Query freqs", slt.getAllTermsasString()); if (null != dbgInfo) { if (null != filters) { dbgInfo.add("filter_queries", req.getParams().getParams(CommonParams.FQ)); List<String> fqs = new ArrayList<String>(filters.size()); for (Query fq : filters) { fqs.add(QueryParsing.toString(fq, req.getSchema())); } dbgInfo.add("parsed_filter_queries", fqs); } if (null != qr) { dbgInfo.add("QueryReduction", qr.getDbgInfo()); } if (null != slt) { dbgInfo.add("SLT", slt.getDbgInfo()); } dbgInfo.add("fromcache", fromcache); rsp.add("debug", dbgInfo); timinginfo.add("Debugging parts", System.currentTimeMillis() - lstartTime); dbgInfo.add("timings", timinginfo); } } catch (Exception e) { SolrException.log(SolrCore.log, "Exception during debug", e); rsp.add("exception_during_debug", SolrException.toStr(e)); } } } catch (Exception e) { numErrors++; e.printStackTrace(); } finally { totalTime += System.currentTimeMillis() - startTime; } }
From source file:com.searchbox.solr.SenseQueryHandler.java
private static NamedList<Explanation> getExplanations(Query query, DocList docs, SolrIndexSearcher searcher, IndexSchema schema) throws IOException { NamedList<Explanation> explainList = new SimpleOrderedMap<Explanation>(); DocIterator iterator = docs.iterator(); for (int i = 0; i < docs.size(); i++) { int id = iterator.nextDoc(); Document doc = searcher.doc(id); String strid = schema.printableUniqueKey(doc); explainList.add(strid, searcher.explain(query, id)); }//from ww w .ja v a 2s .c om return explainList; }
From source file:com.searchbox.solr.SenseQueryHandler.java
@Override public void handleRequestBody(SolrQueryRequest req, SolrQueryResponse rsp) throws Exception { NamedList<Object> timinginfo = new NamedList<Object>(); numRequests++;/*from www. java2s . com*/ long startTime = System.currentTimeMillis(); long lstartTime = System.currentTimeMillis(); if (!keystate) { LOGGER.error( "License key failure, not performing sense query. Please email contact@searchbox.com for more information."); return; } boolean fromcache = false; try { SolrParams params = req.getParams(); HashSet<String> toIgnore = new HashSet<String>(); toIgnore.add("start"); toIgnore.add("rows"); toIgnore.add("fl"); toIgnore.add("wt"); toIgnore.add("indent"); SolrCacheKey key = new SolrCacheKey(params, toIgnore); // Set field flags ReturnFields returnFields = new SolrReturnFields(req); rsp.setReturnFields(returnFields); int flags = 0; if (returnFields.wantsScore()) { flags |= SolrIndexSearcher.GET_SCORES; } String defType = params.get(QueryParsing.DEFTYPE, QParserPlugin.DEFAULT_QTYPE); String q = params.get(CommonParams.Q); Query query = null; QueryReductionFilter qr = null; List<Query> filters = new ArrayList<Query>(); try { if (q != null) { QParser parser = QParser.getParser(q, defType, req); query = parser.getQuery(); } String[] fqs = req.getParams().getParams(CommonParams.FQ); if (fqs != null && fqs.length != 0) { for (String fq : fqs) { if (fq != null && fq.trim().length() != 0) { QParser fqp = QParser.getParser(fq, null, req); filters.add(fqp.getQuery()); } } } } catch (Exception e) { numErrors++; throw new SolrException(SolrException.ErrorCode.BAD_REQUEST, e); } int start = params.getInt(CommonParams.START, 0); int rows = params.getInt(CommonParams.ROWS, 10); SenseQuery slt = null; if (q == null) { numErrors++; throw new SolrException(SolrException.ErrorCode.BAD_REQUEST, "SenseLikeThis requires either a query (?q=) or text to find similar documents."); } timinginfo.add("Parse Query time", System.currentTimeMillis() - lstartTime); LOGGER.debug("Parsed Query Time:\t" + (System.currentTimeMillis() - lstartTime)); lstartTime = System.currentTimeMillis(); SolrIndexSearcher searcher = req.getSearcher(); SolrCache sc = searcher.getCache("com.searchbox.sltcache"); DocListAndSet sltDocs = null; if (sc != null) { //try to get from cache sltDocs = (DocListAndSet) sc.get(key.getSet()); } else { LOGGER.error("com.searchbox.sltcache not defined, can't cache slt queries"); } if (start + rows > 1000 || sltDocs == null || !params.getBool(CommonParams.CACHE, true)) { //not in cache, need to do search String CKBid = params.get(SenseParams.SENSE_CKB, SenseParams.SENSE_CKB_DEFAULT); String senseField = params.get(SenseParams.SENSE_FIELD, SenseParams.DEFAULT_SENSE_FIELD); RealTermFreqVector rtv = new RealTermFreqVector(q, SenseQuery.getAnalyzerForField(req.getSchema(), senseField)); timinginfo.add("Make real term freq vector", System.currentTimeMillis() - lstartTime); lstartTime = System.currentTimeMillis(); qr = new QueryReductionFilter(rtv, CKBid, searcher, senseField); qr.setNumtermstouse(params.getInt(SenseParams.SENSE_QR_NTU, SenseParams.SENSE_QR_NTU_DEFAULT)); numTermsUsed += qr.getNumtermstouse(); numTermsConsidered += rtv.getSize(); qr.setThreshold(params.getInt(SenseParams.SENSE_QR_THRESH, SenseParams.SENSE_QR_THRESH_DEFAULT)); qr.setMaxDocSubSet(params.getInt(SenseParams.SENSE_QR_MAXDOC, SenseParams.SENSE_QR_MAXDOC_DEFAULT)); qr.setMinDocSetSizeForFilter( params.getInt(SenseParams.SENSE_MINDOC4QR, SenseParams.SENSE_MINDOC4QR_DEFAULT)); timinginfo.add("Setup Sense query", System.currentTimeMillis() - lstartTime); LOGGER.debug("Setup Sense query:\t" + (System.currentTimeMillis() - lstartTime)); lstartTime = System.currentTimeMillis(); DocList subFiltered = qr.getSubSetToSearchIn(filters); timinginfo.add("Do Query Redux", System.currentTimeMillis() - lstartTime); LOGGER.debug("Do query redux:\t" + (System.currentTimeMillis() - lstartTime)); lstartTime = System.currentTimeMillis(); numFiltered += qr.getFiltered().docList.size(); numSubset += subFiltered.size(); LOGGER.info("Number of documents to search:\t" + subFiltered.size()); slt = new SenseQuery(rtv, senseField, CKBid, params.getFloat(SenseParams.SENSE_WEIGHT, SenseParams.DEFAULT_SENSE_WEIGHT), null); LOGGER.debug("Setup sense query:\t" + (System.currentTimeMillis() - lstartTime)); timinginfo.add("Setup sense query", System.currentTimeMillis() - lstartTime); lstartTime = System.currentTimeMillis(); sltDocs = searcher.getDocListAndSet(slt, subFiltered, Sort.RELEVANCE, 0, 1000, flags); timinginfo.add("Do sense query", System.currentTimeMillis() - lstartTime); lstartTime = System.currentTimeMillis(); LOGGER.debug("Adding this keyto cache:\t" + key.getSet().toString()); searcher.getCache("com.searchbox.sltcache").put(key.getSet(), sltDocs); } else { fromcache = true; timinginfo.add("Getting from cache", System.currentTimeMillis() - lstartTime); LOGGER.debug("Got result from cache"); lstartTime = System.currentTimeMillis(); } if (sltDocs == null) { numEmpty++; sltDocs = new DocListAndSet(); // avoid NPE } rsp.add("response", sltDocs.docList.subset(start, rows)); // --------- OLD CODE BELOW // maybe facet the results if (params.getBool(FacetParams.FACET, false)) { if (sltDocs.docSet == null) { rsp.add("facet_counts", null); } else { SimpleFacets f = new SimpleFacets(req, sltDocs.docSet, params); rsp.add("facet_counts", f.getFacetCounts()); } } // Debug info, not doing it for the moment. boolean dbg = req.getParams().getBool(CommonParams.DEBUG_QUERY, false); boolean dbgQuery = false, dbgResults = false; if (dbg == false) {//if it's true, we are doing everything anyway. String[] dbgParams = req.getParams().getParams(CommonParams.DEBUG); if (dbgParams != null) { for (int i = 0; i < dbgParams.length; i++) { if (dbgParams[i].equals(CommonParams.QUERY)) { dbgQuery = true; } else if (dbgParams[i].equals(CommonParams.RESULTS)) { dbgResults = true; } } } } else { dbgQuery = true; dbgResults = true; } if (dbg == true) { try { NamedList dbgInfo = new SimpleOrderedMap(); dbgInfo.add("Query freqs", slt.getAllTermsasString()); dbgInfo.addAll( getExplanations(slt, sltDocs.docList.subset(start, rows), searcher, req.getSchema())); if (null != filters) { dbgInfo.add("filter_queries", req.getParams().getParams(CommonParams.FQ)); List<String> fqs = new ArrayList<String>(filters.size()); for (Query fq : filters) { fqs.add(QueryParsing.toString(fq, req.getSchema())); } dbgInfo.add("parsed_filter_queries", fqs); } if (null != qr) { dbgInfo.add("QueryReduction", qr.getDbgInfo()); } if (null != slt) { dbgInfo.add("SLT", slt.getDbgInfo()); } dbgInfo.add("fromcache", fromcache); rsp.add("debug", dbgInfo); timinginfo.add("Debugging parts", System.currentTimeMillis() - lstartTime); dbgInfo.add("timings", timinginfo); } catch (Exception e) { SolrException.log(SolrCore.log, "Exception during debug", e); rsp.add("exception_during_debug", SolrException.toStr(e)); } } } catch (Exception e) { e.printStackTrace(); numErrors++; } finally { totalTime += System.currentTimeMillis() - startTime; } }