/** * check if a given document, identified by url hash as document id exists * * @param id the url hash and document id * @return the load date if any entry in solr exists, -1 otherwise * @throws IOException */ @Override public LoadTimeURL getLoadTimeURL(String id) throws IOException { int responseCount = 0; DocListSearcher docListSearcher = null; try { docListSearcher = new DocListSearcher( "{!cache=false raw f=" + CollectionSchema.id.getSolrFieldName() + "}" + id, null, 0, 1, CollectionSchema.id.getSolrFieldName(), CollectionSchema.load_date_dt.getSolrFieldName()); responseCount = docListSearcher.response.size(); if (responseCount == 0) return null; SolrIndexSearcher searcher = docListSearcher.request.getSearcher(); DocIterator iterator = docListSearcher.response.iterator(); // for (int i = 0; i < responseCount; i++) { Document doc = searcher.doc(iterator.nextDoc(), AbstractSolrConnector.SOLR_ID_and_LOAD_DATE_FIELDS); if (doc == null) return null; return AbstractSolrConnector.getLoadTimeURL(doc); // } } catch (Throwable e) { ConcurrentLog.logException(e); throw new IOException(e.getMessage()); } finally { if (docListSearcher != null) docListSearcher.close(); } }
public void writeResponse() throws IOException { Boolean omitHeader = req.getParams().getBool(CommonParams.OMIT_HEADER); if (omitHeader != null && omitHeader) rsp.getValues().remove("responseHeader"); SolrIndexSearcher searcher = req.getSearcher(); if (liveDocs == null) { liveDocs = searcher.getLeafReader().getLiveDocs(); } int maxDoc = searcher.maxDoc(); try { // responseWriter.write(sw,req,rsp); ReturnFields fields = rsp.getReturnFields(); // return everything Set<String> fnames = fields.getLuceneFieldNames(); int docCounter = 0; for (int i = 0; i < maxDoc; i++) { if (liveDocs != null && !liveDocs.get(i)) { continue; } Document doc = searcher.doc(i); SolrDocument sdoc = toSolrDocument(doc, schema); writeSolrDocument(null, sdoc, fields, docCounter++); getWriter().write("\n"); } } finally { close(); writer.write('\n'); // ending with a newline looks much better from the command line writer.close(); } }
/** * conversion from a SolrQueryResponse (which is a solr-internal data format) to SolrDocumentList * (which is a solrj-format) The conversion is done inside the solrj api using the * BinaryResponseWriter and a very complex unfolding process via * org.apache.solr.common.util.JavaBinCodec.marshal. * * @param request * @param sqr * @return */ public SolrDocumentList SolrQueryResponse2SolrDocumentList( final SolrQueryRequest req, final SolrQueryResponse rsp) { SolrDocumentList sdl = new SolrDocumentList(); NamedList<?> nl = rsp.getValues(); ResultContext resultContext = (ResultContext) nl.get("response"); DocList response = resultContext == null ? new DocSlice(0, 0, new int[0], new float[0], 0, 0.0f) : resultContext.docs; sdl.setNumFound(response == null ? 0 : response.matches()); sdl.setStart(response == null ? 0 : response.offset()); String originalName = Thread.currentThread().getName(); if (response != null) { try { SolrIndexSearcher searcher = req.getSearcher(); final int responseCount = response.size(); DocIterator iterator = response.iterator(); for (int i = 0; i < responseCount; i++) { int docid = iterator.nextDoc(); Thread.currentThread() .setName("EmbeddedSolrConnector.SolrQueryResponse2SolrDocumentList: " + docid); Document responsedoc = searcher.doc(docid, (Set<String>) null); SolrDocument sordoc = doc2SolrDoc(responsedoc); sdl.add(sordoc); } } catch (IOException e) { ConcurrentLog.logException(e); } } Thread.currentThread().setName(originalName); return sdl; }
@Override 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 } } int sz = ids.size(); writeMapOpener(includeScore ? 4 : 3); incLevel(); writeKey("numFound", false); writeInt(null, ids.matches()); writeMapSeparator(); writeKey("start", false); writeInt(null, ids.offset()); if (includeScore) { writeMapSeparator(); writeKey("maxScore", false); writeFloat(null, ids.maxScore()); } writeMapSeparator(); // indent(); writeKey("docs", false); writeArrayOpener(sz); incLevel(); boolean first = true; SolrIndexSearcher searcher = req.getSearcher(); DocIterator iterator = ids.iterator(); for (int i = 0; i < sz; i++) { int id = iterator.nextDoc(); Document doc = searcher.doc(id, fields); if (first) { first = false; } else { writeArraySeparator(); } indent(); writeDoc(null, doc, fields, (includeScore ? iterator.score() : 0.0f), includeScore); } decLevel(); writeArrayCloser(); if (otherFields != null) { writeMap(null, otherFields, true, false); } decLevel(); indent(); writeMapCloser(); }
/** * 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 * @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 { SolrParams params = req.getParams(); if (!isHighlightingEnabled(params)) return null; SolrIndexSearcher searcher = req.getSearcher(); IndexSchema schema = searcher.getSchema(); NamedList fragments = new SimpleOrderedMap(); String[] fieldNames = getHighlightFields(query, req, defaultFields); Set<String> fset = new HashSet<String>(); { // pre-fetch documents using the Searcher's doc cache for (String f : fieldNames) { fset.add(f); } // fetch unique key if one exists. SchemaField keyField = schema.getUniqueKeyField(); if (null != keyField) fset.add(keyField.getName()); } // get FastVectorHighlighter instance out of the processing loop FastVectorHighlighter fvh = new FastVectorHighlighter( // 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)); fvh.setPhraseLimit(params.getInt(HighlightParams.PHRASE_LIMIT, Integer.MAX_VALUE)); FieldQuery fieldQuery = fvh.getFieldQuery(query, searcher.getIndexReader()); // Highlight each document DocIterator iterator = docs.iterator(); for (int i = 0; i < docs.size(); i++) { int docId = iterator.nextDoc(); Document doc = searcher.doc(docId, fset); NamedList docSummaries = new SimpleOrderedMap(); for (String fieldName : fieldNames) { fieldName = fieldName.trim(); if (useFastVectorHighlighter(params, schema, fieldName)) doHighlightingByFastVectorHighlighter( fvh, 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); } return fragments; }
public static SolrInputDocument getInputDocument(SolrCore core, BytesRef idBytes) throws IOException { SolrInputDocument sid = null; RefCounted<SolrIndexSearcher> searcherHolder = null; try { SolrIndexSearcher searcher = null; UpdateLog ulog = core.getUpdateHandler().getUpdateLog(); if (ulog != null) { Object o = ulog.lookup(idBytes); if (o != null) { // should currently be a List<Oper,Ver,Doc/Id> List entry = (List) o; assert entry.size() >= 3; int oper = (Integer) entry.get(0) & UpdateLog.OPERATION_MASK; switch (oper) { case UpdateLog.ADD: sid = (SolrInputDocument) entry.get(entry.size() - 1); break; case UpdateLog.DELETE: return null; default: throw new SolrException( SolrException.ErrorCode.SERVER_ERROR, "Unknown Operation! " + oper); } } } if (sid == null) { // didn't find it in the update log, so it should be in the newest searcher opened if (searcher == null) { searcherHolder = core.getRealtimeSearcher(); searcher = searcherHolder.get(); } // SolrCore.verbose("RealTimeGet using searcher ", searcher); SchemaField idField = core.getLatestSchema().getUniqueKeyField(); int docid = searcher.getFirstMatch(new Term(idField.getName(), idBytes)); if (docid < 0) return null; StoredDocument luceneDocument = searcher.doc(docid); sid = toSolrInputDocument(luceneDocument, core.getLatestSchema()); } } finally { if (searcherHolder != null) { searcherHolder.decref(); } } return sid; }
protected void processIds( ResponseBuilder rb, DocList dl, IndexSchema schema, SolrIndexSearcher searcher) throws IOException { StringBuilder sb = new StringBuilder(); Set<String> fields = Collections.singleton(schema.getUniqueKeyField().getName()); for (DocIterator iter = dl.iterator(); iter.hasNext(); ) { sb.append(schema.printableUniqueKey(searcher.doc(iter.nextDoc(), fields))).append(','); } if (sb.length() > 0) { rb.rsp.addToLog("responseLog", sb.substring(0, sb.length() - 1)); } }
private void mockDocument(int docId, double price, double discount, boolean isCloseout) throws IOException { Document doc = PowerMockito.mock(Document.class); when(searcher.doc(eq(docId), any(Set.class))).thenReturn(doc); when(searcher.getSchema()).thenReturn(schema); IndexableField priceField = mock(IndexableField.class); when(doc.getField(FIELD_PRICE)).thenReturn(priceField); when(priceField.numericValue()).thenReturn(new Double(price)); IndexableField discountField = mock(IndexableField.class); when(doc.getField(FIELD_DISCOUNT)).thenReturn(discountField); when(discountField.numericValue()).thenReturn(new Double(discount)); IndexableField closeoutField = mock(IndexableField.class); when(doc.getField(FIELD_CLOSEOUT)).thenReturn(closeoutField); when(closeoutField.stringValue()).thenReturn(isCloseout ? "T" : "F"); }
@SuppressWarnings("unchecked") private static SimpleOrderedMap<Object> getIndexedFieldsInfo( final SolrIndexSearcher searcher, final Set<String> fields, final int numTerms) throws Exception { IndexReader reader = searcher.getReader(); IndexSchema schema = searcher.getSchema(); // Walk the term enum and keep a priority queue for each map in our set Map<String, TopTermQueue> ttinfo = null; if (numTerms > 0) { ttinfo = getTopTerms(reader, fields, numTerms, null); } SimpleOrderedMap<Object> finfo = new SimpleOrderedMap<Object>(); Collection<String> fieldNames = reader.getFieldNames(IndexReader.FieldOption.ALL); for (String fieldName : fieldNames) { if (fields != null && !fields.contains(fieldName)) { continue; // if a field is specified, only them } SimpleOrderedMap<Object> f = new SimpleOrderedMap<Object>(); SchemaField sfield = schema.getFieldOrNull(fieldName); FieldType ftype = (sfield == null) ? null : sfield.getType(); f.add("type", (ftype == null) ? null : ftype.getTypeName()); f.add("schema", getFieldFlags(sfield)); if (sfield != null && schema.isDynamicField(sfield.getName()) && schema.getDynamicPattern(sfield.getName()) != null) { f.add("dynamicBase", schema.getDynamicPattern(sfield.getName())); } // If numTerms==0, the call is just asking for a quick field list if (ttinfo != null && sfield != null && sfield.indexed()) { Query q = new TermRangeQuery(fieldName, null, null, false, false); TopDocs top = searcher.search(q, 1); if (top.totalHits > 0) { // Find a document with this field try { Document doc = searcher.doc(top.scoreDocs[0].doc); Fieldable fld = doc.getFieldable(fieldName); if (fld != null) { f.add("index", getFieldFlags(fld)); } else { // it is a non-stored field... f.add("index", "(unstored field)"); } } catch (Exception ex) { log.warn("error reading field: " + fieldName); } } f.add("docs", top.totalHits); TopTermQueue topTerms = ttinfo.get(fieldName); if (topTerms != null) { f.add("distinct", topTerms.distinctTerms); // Include top terms f.add("topTerms", topTerms.toNamedList(searcher.getSchema())); // Add a histogram f.add("histogram", topTerms.histogram.toNamedList()); } } // Add the field finfo.add(fieldName, f); } return finfo; }
@Override public void process(ResponseBuilder rb) throws IOException { SolrQueryRequest req = rb.req; SolrQueryResponse rsp = rb.rsp; SolrParams params = req.getParams(); if (!params.getBool(COMPONENT_NAME, true)) { return; } String val = params.get("getVersions"); if (val != null) { processGetVersions(rb); return; } val = params.get("getUpdates"); if (val != null) { processGetUpdates(rb); return; } String id[] = params.getParams("id"); String ids[] = params.getParams("ids"); if (id == null && ids == null) { return; } String[] allIds = id == null ? new String[0] : id; if (ids != null) { List<String> lst = new ArrayList<String>(); for (String s : allIds) { lst.add(s); } for (String idList : ids) { lst.addAll(StrUtils.splitSmart(idList, ",", true)); } allIds = lst.toArray(new String[lst.size()]); } SolrCore core = req.getCore(); SchemaField idField = core.getLatestSchema().getUniqueKeyField(); FieldType fieldType = idField.getType(); SolrDocumentList docList = new SolrDocumentList(); UpdateLog ulog = core.getUpdateHandler().getUpdateLog(); RefCounted<SolrIndexSearcher> searcherHolder = null; DocTransformer transformer = rsp.getReturnFields().getTransformer(); if (transformer != null) { TransformContext context = new TransformContext(); context.req = req; transformer.setContext(context); } try { SolrIndexSearcher searcher = null; BytesRef idBytes = new BytesRef(); for (String idStr : allIds) { fieldType.readableToIndexed(idStr, idBytes); if (ulog != null) { Object o = ulog.lookup(idBytes); if (o != null) { // should currently be a List<Oper,Ver,Doc/Id> List entry = (List) o; assert entry.size() >= 3; int oper = (Integer) entry.get(0) & UpdateLog.OPERATION_MASK; switch (oper) { case UpdateLog.ADD: SolrDocument doc = toSolrDoc( (SolrInputDocument) entry.get(entry.size() - 1), core.getLatestSchema()); if (transformer != null) { transformer.transform(doc, -1); // unknown docID } docList.add(doc); break; case UpdateLog.DELETE: break; default: throw new SolrException( SolrException.ErrorCode.SERVER_ERROR, "Unknown Operation! " + oper); } continue; } } // didn't find it in the update log, so it should be in the newest searcher opened if (searcher == null) { searcherHolder = core.getRealtimeSearcher(); searcher = searcherHolder.get(); } // SolrCore.verbose("RealTimeGet using searcher ", searcher); int docid = searcher.getFirstMatch(new Term(idField.getName(), idBytes)); if (docid < 0) continue; StoredDocument luceneDocument = searcher.doc(docid); SolrDocument doc = toSolrDoc(luceneDocument, core.getLatestSchema()); if (transformer != null) { transformer.transform(doc, docid); } docList.add(doc); } } finally { if (searcherHolder != null) { searcherHolder.decref(); } } // if the client specified a single id=foo, then use "doc":{ // otherwise use a standard doclist if (ids == null && allIds.length <= 1) { // if the doc was not found, then use a value of null. rsp.add("doc", docList.size() > 0 ? docList.get(0) : null); } else { docList.setNumFound(docList.size()); rsp.add("response", docList); } }