List of usage examples for org.apache.solr.client.solrj SolrQuery setTimeAllowed
public SolrQuery setTimeAllowed(Integer milliseconds)
From source file:org.pentaho.di.trans.steps.solrinput.SolrInput.java
License:Apache License
/** * Once the transformation starts executing, the processRow() method is called repeatedly * by PDI for as long as it returns true. To indicate that a step has finished processing rows * this method must call setOutputDone() and return false; * //from w w w. ja v a 2 s .c o m * Steps which process incoming rows typically call getRow() to read a single row from the * input stream, change or add row content, call putRow() to pass the changed row on * and return true. If getRow() returns null, no more rows are expected to come in, * and the processRow() implementation calls setOutputDone() and returns false to * indicate that it is done too. * * Steps which generate rows typically construct a new row Object[] using a call to * RowDataUtil.allocateRowData(numberOfFields), add row content, and call putRow() to * pass the new row on. Above process may happen in a loop to generate multiple rows, * at the end of which processRow() would call setOutputDone() and return false; * * @param smi the step meta interface containing the step settings * @param sdi the step data interface that should be used to store * * @return true to indicate that the function should be called again, false if the step is done */ public boolean processRow(StepMetaInterface smi, StepDataInterface sdi) throws KettleException { if (first) { first = false; // Create the output row meta-data data.outputRowMeta = new RowMeta(); meta.getFields(data.outputRowMeta, getStepname(), null, null, this, repository, metaStore); // For String to <type> conversions, we allocate a conversion meta data row as well... data.convertRowMeta = data.outputRowMeta.cloneToType(ValueMetaInterface.TYPE_STRING); // get real values boolean tryCursor = true; Integer startRecord = 0; Integer chunkRowSize = 20; String realURL = meta.getURL(); String realQ = meta.getQ(); String realSort = meta.getSort(); String realCursor = meta.getCursor(); String realFq = meta.getFq(); String realFl = meta.getFl(); String realFacetQuery = meta.getFacetQuery(); String realFacetField = meta.getFacetField(); /* Send and Get the report */ SolrQuery query = new SolrQuery(); query.set("rows", chunkRowSize); if (realQ != null && !realQ.equals("")) { query.set("q", realQ); } if (realSort != null && !realSort.equals("")) { query.set("sort", realSort); } else { tryCursor = false; } if (realCursor != null && !realCursor.equals("")) { if (realCursor.equals("No")) { tryCursor = false; } } if (realFl != null && !realFl.equals("")) { query.set("fl", realFl); } if (realFq != null && !realFq.equals("")) { query.set("fq", realFq); } if (realFacetField != null && !realFacetField.equals("")) { //TODO incorporate multiple facet fields at once //String[] facetFields = realFacetField.split("\\s*,\\s*"); //for(int i =0; i < facetFields.length; i++){ query.addFacetField(realFacetField); //} query.setFacet(true); query.setFacetLimit(-1); query.setFacetMinCount(0); query.setFacetSort("count"); query.set("rows", 0); tryCursor = false; data.facetRequested = true; } if (realFacetQuery != null && !realFacetQuery.equals("")) { query.addFacetQuery(realFacetQuery); } // You can't use "TimeAllowed" with "CursorMark" // The documentation says "Values <= 0 mean // no time restriction", so setting to 0. query.setTimeAllowed(0); HttpSolrServer solr = new HttpSolrServer(realURL); String cursorMark = CursorMarkParams.CURSOR_MARK_START; boolean done = false; QueryResponse rsp = null; while (!done) { if (tryCursor) { query.set(CursorMarkParams.CURSOR_MARK_PARAM, cursorMark); } else { query.setStart(startRecord); } try { rsp = solr.query(query); } catch (SolrServerException e) { e.printStackTrace(); } if (data.facetRequested) { data.facetCountName = rsp.getFacetFields().get(0).getName(); data.facetCounts = rsp.getFacetFields().get(0).getValues(); done = true; } else { SolrDocumentList theseDocs = rsp.getResults(); for (SolrDocument doc : theseDocs) { data.documentList.add(doc); } } if (tryCursor) { String nextCursorMark = rsp.getNextCursorMark(); if (cursorMark.equals(nextCursorMark)) { done = true; } else { cursorMark = nextCursorMark; } } else { startRecord = startRecord + chunkRowSize; if (startRecord >= rsp.getResults().getNumFound()) { done = true; } } } } Object[] outputRowData = null; try { if (data.facetRequested) { // get one row if we can if (data.facetCounts.size() - 1 < data.recordIndex) { setOutputDone(); return false; } FacetField.Count facetRecord = data.facetCounts.get(data.recordIndex); outputRowData = prepareFacetRecord(facetRecord); } else { // get one row if we can if (data.documentList.size() - 1 < data.recordIndex) { setOutputDone(); return false; } SolrDocument record = data.documentList.get(data.recordIndex); outputRowData = prepareRecord(record); } putRow(data.outputRowMeta, outputRowData); // copy row to output rowset(s); data.recordIndex++; return true; } catch (KettleException e) { boolean sendToErrorRow = false; String errorMessage = null; if (getStepMeta().isDoingErrorHandling()) { sendToErrorRow = true; errorMessage = e.toString(); } else { logError(BaseMessages.getString(PKG, "SolrInput.log.Exception", e.getMessage())); logError(Const.getStackTracker(e)); setErrors(1); stopAll(); setOutputDone(); // signal end to receiver(s) return false; } if (sendToErrorRow) { // Simply add this row to the error row putError(getInputRowMeta(), outputRowData, 1, errorMessage, null, "SolrInput001"); } } return true; }
From source file:org.pentaho.di.ui.trans.steps.solrinput.SolrInputDialog.java
License:Apache License
private void getFields() { try {//from w w w . j av a2 s .c o m SolrInputMeta meta = new SolrInputMeta(); getInfo(meta); // clear the current fields grid wFields.removeAll(); // get real values boolean tryCursor = true; boolean facetRequested = false; Integer startRecord = 0; Integer chunkRowSize = 20; String realURL = transMeta.environmentSubstitute(meta.getURL()); String realQ = transMeta.environmentSubstitute(meta.getQ()); String realSort = transMeta.environmentSubstitute(meta.getSort()); String realCursor = transMeta.environmentSubstitute(meta.getCursor()); String realFq = transMeta.environmentSubstitute(meta.getFq()); String realFl = transMeta.environmentSubstitute(meta.getFl()); String realFacetQuery = transMeta.environmentSubstitute(meta.getFacetQuery()); String realFacetField = transMeta.environmentSubstitute(meta.getFacetField()); /* Send and Get the report */ SolrQuery query = new SolrQuery(); query.set("rows", chunkRowSize); if (realQ != null && !realQ.equals("")) { query.set("q", realQ); } if (realSort != null && !realSort.equals("")) { query.set("sort", realSort); } else { tryCursor = false; } if (realCursor != null && !realCursor.equals("")) { if (realCursor.equals("No")) { tryCursor = false; } } if (realFl != null && !realFl.equals("")) { query.set("fl", realFl); } if (realFq != null && !realFq.equals("")) { query.set("fq", realFq); } if (realFacetField != null && !realFacetField.equals("")) { //TODO incorporate multiple facet fields at once //String[] facetFields = realFacetField.split("\\s*,\\s*"); //for(int i =0; i < facetFields.length; i++){ query.addFacetField(realFacetField); //} query.setFacet(true); query.setFacetLimit(-1); query.setFacetMinCount(0); query.setFacetSort("count"); query.set("rows", 0); tryCursor = false; facetRequested = true; } if (realFacetQuery != null && !realFacetQuery.equals("")) { query.addFacetQuery(realFacetQuery); } // You can't use "TimeAllowed" with "CursorMark" // The documentation says "Values <= 0 mean // no time restriction", so setting to 0. query.setTimeAllowed(0); HttpSolrServer solr = new HttpSolrServer(realURL); String cursorMark = CursorMarkParams.CURSOR_MARK_START; boolean done = false; List<String> headerNames = new ArrayList<String>(); QueryResponse rsp = null; while (!done) { if (tryCursor) { query.set(CursorMarkParams.CURSOR_MARK_PARAM, cursorMark); } else { query.setStart(startRecord); } try { rsp = solr.query(query); } catch (SolrServerException e) { e.printStackTrace(); } if (facetRequested) { headerNames.add(rsp.getFacetFields().get(0).getName()); headerNames.add("count"); done = true; } else { SolrDocumentList docs = rsp.getResults(); for (SolrDocument doc : docs) { Collection<String> thisNamesArray = doc.getFieldNames(); String[] a = thisNamesArray.toArray(new String[thisNamesArray.size()]); for (int j = 0; j < a.length; j++) { if (!headerNames.contains(a[j])) { headerNames.add(a[j]); } } } } if (tryCursor) { String nextCursorMark = rsp.getNextCursorMark(); if (cursorMark.equals(nextCursorMark)) { done = true; } else { cursorMark = nextCursorMark; } } else { startRecord = startRecord + chunkRowSize; if (startRecord >= rsp.getResults().getNumFound()) { done = true; } } } getTableView().table.setItemCount(headerNames.size()); for (int j = 0; j < headerNames.size(); j++) { TableItem item = getTableView().table.getItem(j); item.setText(1, headerNames.get(j)); } wFields.removeEmptyRows(); wFields.setRowNums(); wFields.optWidth(true); getInput().setChanged(); } catch (Exception e) { new ErrorDialog(shell, BaseMessages.getString(PKG, "SolrInputMeta.ErrorRetrieveData.DialogTitle"), BaseMessages.getString(PKG, "SolrInputMeta.ErrorRetrieveData.DialogMessage"), e); } }
From source file:org.sleuthkit.autopsy.keywordsearch.TermComponentQuery.java
License:Open Source License
protected SolrQuery createQuery() { final SolrQuery q = new SolrQuery(); q.setRequestHandler(TERMS_HANDLER);/*from w w w. j a v a2s. c o m*/ q.setTerms(true); q.setTermsLimit(TERMS_UNLIMITED); q.setTermsRegexFlag("case_insensitive"); //NON-NLS //q.setTermsLimit(200); //q.setTermsRegexFlag(regexFlag); //q.setTermsRaw(true); q.setTermsRegex(queryEscaped); q.addTermsField(TERMS_SEARCH_FIELD); q.setTimeAllowed(TERMS_TIMEOUT); return q; }
From source file:org.sleuthkit.autopsy.keywordsearch.TermsComponentQuery.java
License:Open Source License
/** * Executes the regex query as a two step operation. In the first step, the * Solr terms component is used to find any terms in the index that match * the regex. In the second step, term queries are executed for each matched * term to produce the set of keyword hits for the regex. * * @return A QueryResult object or null. * * @throws NoOpenCoreException/*w w w .j a va 2s. c o m*/ */ @Override public QueryResults performQuery() throws KeywordSearchModuleException, NoOpenCoreException { /* * Do a query using the Solr terms component to find any terms in the * index that match the regex. */ final SolrQuery termsQuery = new SolrQuery(); termsQuery.setRequestHandler(SEARCH_HANDLER); termsQuery.setTerms(true); termsQuery.setTermsRegexFlag(CASE_INSENSITIVE); termsQuery.setTermsRegex(searchTerm); termsQuery.addTermsField(SEARCH_FIELD); termsQuery.setTimeAllowed(TERMS_SEARCH_TIMEOUT); termsQuery.setShowDebugInfo(DEBUG_FLAG); termsQuery.setTermsLimit(MAX_TERMS_QUERY_RESULTS); List<Term> terms = KeywordSearch.getServer().queryTerms(termsQuery).getTerms(SEARCH_FIELD); /* * Do a term query for each term that matched the regex. */ QueryResults results = new QueryResults(this, keywordList); for (Term term : terms) { /* * If searching for credit card account numbers, do a Luhn check on * the term and discard it if it does not pass. */ if (keyword.getArtifactAttributeType() == ATTRIBUTE_TYPE.TSK_CARD_NUMBER) { Matcher matcher = CREDIT_CARD_NUM_PATTERN.matcher(term.getTerm()); matcher.find(); final String ccn = CharMatcher.anyOf(" -").removeFrom(matcher.group("ccn")); if (false == CREDIT_CARD_NUM_LUHN_CHECK.isValid(ccn)) { continue; } } /* * Do an ordinary query with the escaped term and convert the query * results into a single list of keyword hits without duplicates. * * Note that the filters field appears to be unused. There is an old * comment here, what does it mean? "Note: we can't set filter query * on terms query but setting filter query on fileResults query will * yield the same result." The filter is NOT being added to the term * query. */ String escapedTerm = KeywordSearchUtil.escapeLuceneQuery(term.getTerm()); LuceneQuery termQuery = new LuceneQuery(keywordList, new Keyword(escapedTerm, true)); filters.forEach(termQuery::addFilter); // This appears to be unused QueryResults termQueryResult = termQuery.performQuery(); Set<KeywordHit> termHits = new HashSet<>(); for (Keyword word : termQueryResult.getKeywords()) { termHits.addAll(termQueryResult.getResults(word)); } results.addResult(new Keyword(term.getTerm(), false), new ArrayList<>(termHits)); } return results; }