From 03cafc671109f8777e760cdf657463775978eb54 Mon Sep 17 00:00:00 2001 From: Joel Bernstein Date: Mon, 15 Jun 2015 02:51:36 +0000 Subject: [PATCH] SOLR-7560: Parallel SQL Support git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1685497 13f79535-47bb-0310-9956-ffa450edef68 --- lucene/ivy-versions.properties | 5 + solr/core/ivy.xml | 5 + .../org/apache/solr/handler/SQLHandler.java | 781 ++++++++++++++++ .../apache/solr/handler/StreamHandler.java | 2 +- .../solr/collection1/conf/schema-sql.xml | 599 +++++++++++++ .../solr/collection1/conf/solrconfig-sql.xml | 107 +++ .../apache/solr/handler/TestSQLHandler.java | 843 ++++++++++++++++++ solr/licenses/antlr4-runtime-4.5.jar.sha1 | 1 + solr/licenses/antlr4-runtime-LICENSE-BSD.txt | 26 + solr/licenses/antlr4-runtime-NOTICE.txt | 0 solr/licenses/presto-parser-0.107.jar.sha1 | 1 + solr/licenses/presto-parser-LICENSE-ASL.txt | 202 +++++ solr/licenses/presto-parser-NOTICE.txt | 0 solr/licenses/slice-0.10.jar.sha1 | 1 + solr/licenses/slice-LICENSE-ASL.txt | 202 +++++ solr/licenses/slice-NOTICE.txt | 0 .../apache/solr/client/solrj/io/Tuple.java | 18 +- .../solr/client/solrj/io/comp/HashKey.java | 80 ++ .../client/solrj/io/stream/RollupStream.java | 135 +++ .../solrj/io/stream/metrics/Bucket.java | 48 + .../solrj/io/stream/metrics/CountMetric.java | 44 + .../solrj/io/stream/metrics/MaxMetric.java | 67 ++ .../solrj/io/stream/metrics/MeanMetric.java | 70 ++ .../solrj/io/stream/metrics/Metric.java | 28 + .../solrj/io/stream/metrics/MinMetric.java | 66 ++ .../solrj/io/stream/metrics/SumMetric.java | 62 ++ .../solrj/io/stream/metrics/package-info.java | 24 + .../client/solrj/io/stream/StreamingTest.java | 248 +++++- 28 files changed, 3659 insertions(+), 6 deletions(-) create mode 100644 solr/core/src/java/org/apache/solr/handler/SQLHandler.java create mode 100644 solr/core/src/test-files/solr/collection1/conf/schema-sql.xml create mode 100644 solr/core/src/test-files/solr/collection1/conf/solrconfig-sql.xml create mode 100644 solr/core/src/test/org/apache/solr/handler/TestSQLHandler.java create mode 100644 solr/licenses/antlr4-runtime-4.5.jar.sha1 create mode 100644 solr/licenses/antlr4-runtime-LICENSE-BSD.txt create mode 100644 solr/licenses/antlr4-runtime-NOTICE.txt create mode 100644 solr/licenses/presto-parser-0.107.jar.sha1 create mode 100644 solr/licenses/presto-parser-LICENSE-ASL.txt create mode 100644 solr/licenses/presto-parser-NOTICE.txt create mode 100644 solr/licenses/slice-0.10.jar.sha1 create mode 100644 solr/licenses/slice-LICENSE-ASL.txt create mode 100644 solr/licenses/slice-NOTICE.txt create mode 100644 solr/solrj/src/java/org/apache/solr/client/solrj/io/comp/HashKey.java create mode 100644 solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/RollupStream.java create mode 100644 solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/Bucket.java create mode 100644 solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/CountMetric.java create mode 100644 solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/MaxMetric.java create mode 100644 solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/MeanMetric.java create mode 100644 solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/Metric.java create mode 100644 solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/MinMetric.java create mode 100644 solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/SumMetric.java create mode 100644 solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/package-info.java diff --git a/lucene/ivy-versions.properties b/lucene/ivy-versions.properties index 3b80ba86645..bd05786b493 100644 --- a/lucene/ivy-versions.properties +++ b/lucene/ivy-versions.properties @@ -20,6 +20,8 @@ com.codahale.metrics.version = 3.0.1 /com.cybozu.labs/langdetect = 1.1-20120112 /com.drewnoakes/metadata-extractor = 2.6.2 +/com.facebook.presto/presto-parser = 0.107 + com.fasterxml.jackson.core.version = 2.3.1 /com.fasterxml.jackson.core/jackson-annotations = ${com.fasterxml.jackson.core.version} /com.fasterxml.jackson.core/jackson-core = ${com.fasterxml.jackson.core.version} @@ -68,6 +70,7 @@ com.sun.jersey.version = 1.9 /de.l3s.boilerpipe/boilerpipe = 1.1.0 /dom4j/dom4j = 1.6.1 /hsqldb/hsqldb = 1.8.0.10 +/io.airlift/slice = 0.10 /io.netty/netty = 3.7.0.Final /it.unimi.dsi/fastutil = 6.5.11 /jakarta-regexp/jakarta-regexp = 1.4 @@ -89,6 +92,8 @@ com.sun.jersey.version = 1.9 /net.sourceforge.jmatio/jmatio = 1.0 /net.sourceforge.nekohtml/nekohtml = 1.9.17 /org.antlr/antlr-runtime = 3.5 +/org.antlr/antlr4-runtime = 4.5 + /org.apache.ant/ant = 1.8.2 /org.apache.avro/avro = 1.7.5 /org.apache.commons/commons-compress = 1.8.1 diff --git a/solr/core/ivy.xml b/solr/core/ivy.xml index b633c644005..79308d6810c 100644 --- a/solr/core/ivy.xml +++ b/solr/core/ivy.xml @@ -122,6 +122,11 @@ + + + + + diff --git a/solr/core/src/java/org/apache/solr/handler/SQLHandler.java b/solr/core/src/java/org/apache/solr/handler/SQLHandler.java new file mode 100644 index 00000000000..8edd44e0253 --- /dev/null +++ b/solr/core/src/java/org/apache/solr/handler/SQLHandler.java @@ -0,0 +1,781 @@ +package org.apache.solr.handler; + +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.io.IOException; +import java.util.ArrayList; +import java.util.Comparator; +import java.util.HashSet; +import java.util.Iterator; +import java.util.Locale; +import java.util.Map.Entry; +import java.util.Set; + +import com.facebook.presto.sql.ExpressionFormatter; +import com.facebook.presto.sql.tree.*; +import com.google.common.base.Strings; +import com.google.common.collect.Iterables; +import org.apache.solr.client.solrj.io.Tuple; +import org.apache.solr.client.solrj.io.comp.ComparatorOrder; +import org.apache.solr.client.solrj.io.comp.FieldComparator; +import org.apache.solr.client.solrj.io.comp.MultiComp; +import org.apache.solr.client.solrj.io.stream.CloudSolrStream; +import org.apache.solr.client.solrj.io.stream.ParallelStream; +import org.apache.solr.client.solrj.io.stream.RankStream; +import org.apache.solr.client.solrj.io.stream.RollupStream; +import org.apache.solr.client.solrj.io.stream.StreamContext; +import org.apache.solr.client.solrj.io.stream.TupleStream; +import org.apache.solr.common.params.CommonParams; +import org.apache.solr.common.params.SolrParams; +import org.apache.solr.common.util.NamedList; +import org.apache.solr.core.CoreContainer; +import org.apache.solr.core.SolrCore; +import org.apache.solr.request.SolrQueryRequest; +import org.apache.solr.response.SolrQueryResponse; +import org.apache.solr.util.plugin.SolrCoreAware; +import java.util.List; +import java.util.Map; +import java.util.HashMap; +import java.util.Optional; +import org.apache.solr.client.solrj.io.stream.metrics.*; + +import com.facebook.presto.sql.parser.SqlParser; + +public class SQLHandler extends RequestHandlerBase implements SolrCoreAware { + + private Map tableMappings = new HashMap(); + private String defaultZkhost = null; + private String defaultWorkerCollection = null; + + public void inform(SolrCore core) { + + CoreContainer coreContainer = core.getCoreDescriptor().getCoreContainer(); + + if(coreContainer.isZooKeeperAware()) { + defaultZkhost = core.getCoreDescriptor().getCoreContainer().getZkController().getZkServerAddress(); + defaultWorkerCollection = core.getCoreDescriptor().getCollectionName(); + } + + NamedList tableConf = (NamedList)initArgs.get("tables"); + + for(Entry entry : tableConf) { + String tableName = entry.getKey(); + if(entry.getValue().indexOf("@") > -1) { + String[] parts = entry.getValue().split("@"); + tableMappings.put(tableName, new TableSpec(parts[0], parts[1])); + } else { + String collection = entry.getValue(); + tableMappings.put(tableName, new TableSpec(collection, defaultZkhost)); + } + } + } + + public void handleRequestBody(SolrQueryRequest req, SolrQueryResponse rsp) throws Exception { + SolrParams params = req.getParams(); + String sql = params.get("sql"); + int numWorkers = params.getInt("numWorkers", 1); + String workerCollection = params.get("workerCollection", defaultWorkerCollection); + String workerZkhost = params.get("workerZkhost",defaultZkhost); + StreamContext context = new StreamContext(); + TupleStream tupleStream = SQLTupleStreamParser.parse(sql, tableMappings, numWorkers, workerCollection, workerZkhost); + context.numWorkers = numWorkers; + context.setSolrClientCache(StreamHandler.clientCache); + tupleStream.setStreamContext(context); + rsp.add("tuples", tupleStream); + } + + public String getDescription() { + return "SQLHandler"; + } + + public String getSource() { + return null; + } + + public static class SQLTupleStreamParser { + + public static TupleStream parse(String sql, + Map tableMap, + int numWorkers, + String workerCollection, + String workerZkhost) throws IOException { + SqlParser parser = new SqlParser(); + Statement statement = parser.createStatement(sql); + + SQLVisitor sqlVistor = new SQLVisitor(new StringBuilder()); + + sqlVistor.process(statement, new Integer(0)); + + TupleStream sqlStream = null; + + if(sqlVistor.groupByQuery) { + sqlStream = doGroupBy(sqlVistor, tableMap, numWorkers, workerCollection, workerZkhost); + } else { + sqlStream = doSelect(sqlVistor, tableMap, numWorkers, workerCollection, workerZkhost); + } + + return sqlStream; + } + } + + private static TupleStream doGroupBy(SQLVisitor sqlVisitor, + Map tableMap, + int numWorkers, + String workerCollection, + String workerZkHost) throws IOException { + + Set fieldSet = new HashSet(); + Bucket[] buckets = getBuckets(sqlVisitor.groupBy, fieldSet); + Metric[] metrics = getMetrics(sqlVisitor.fields, fieldSet); + + String fl = fields(fieldSet); + String sortDirection = getSortDirection(sqlVisitor.sorts); + String sort = bucketSort(buckets, sortDirection); + + TableSpec tableSpec = tableMap.get(sqlVisitor.table); + String zkHost = tableSpec.zkHost; + String collection = tableSpec.collection; + Map params = new HashMap(); + + params.put(CommonParams.FL, fl); + params.put(CommonParams.Q, sqlVisitor.query); + //Always use the /export handler for Group By Queries because it requires exporting full result sets. + params.put(CommonParams.QT, "/export"); + + if(numWorkers > 1) { + params.put("partitionKeys", getPartitionKeys(buckets)); + } + + params.put("sort", sort); + + TupleStream tupleStream = null; + + CloudSolrStream cstream = new CloudSolrStream(zkHost, collection, params); + tupleStream = new RollupStream(cstream, buckets, metrics); + + if(numWorkers > 1) { + // Do the rollups in parallel + // Maintain the sort of the Tuples coming from the workers. + Comparator comp = bucketSortComp(buckets, sortDirection); + tupleStream = new ParallelStream(workerZkHost, workerCollection, tupleStream, numWorkers, comp); + } + + //TODO: This should be done on the workers, but it won't serialize because it relies on Presto classes. + // Once we make this a Expressionable the problem will be solved. + + if(sqlVisitor.havingExpression != null) { + tupleStream = new HavingStream(tupleStream, sqlVisitor.havingExpression); + } + + if(sqlVisitor.sorts != null && sqlVisitor.sorts.size() > 0) { + if(!sortsEqual(buckets, sortDirection, sqlVisitor.sorts)) { + int limit = sqlVisitor.limit == -1 ? 100 : sqlVisitor.limit; + Comparator comp = getComp(sqlVisitor.sorts); + //Rank the Tuples + //If parallel stream is used ALL the Rolled up tuples from the workers will be ranked + //Providing a true Top or Bottom. + tupleStream = new RankStream(tupleStream, limit, comp); + } else { + // Sort is the same as the same as the underlying stream + // Only need to limit the result, not Rank the result + if(sqlVisitor.limit > -1) { + tupleStream = new LimitStream(tupleStream, sqlVisitor.limit); + } + } + } + + return tupleStream; + } + + private static TupleStream doSelect(SQLVisitor sqlVisitor, + Map tableMap, + int numWorkers, + String workerCollection, + String workerZkHost) throws IOException { + List fields = sqlVisitor.fields; + StringBuilder flbuf = new StringBuilder(); + boolean comma = false; + for(String field : fields) { + + if(comma) { + flbuf.append(","); + } + + comma = true; + flbuf.append(field); + } + + String fl = flbuf.toString(); + + List sorts = sqlVisitor.sorts; + + StringBuilder siBuf = new StringBuilder(); + + comma = false; + for(SortItem sortItem : sorts) { + if(comma) { + siBuf.append(","); + } + siBuf.append(stripQuotes(sortItem.getSortKey().toString()) + " " + ascDesc(sortItem.getOrdering().toString())); + } + + TableSpec tableSpec = tableMap.get(sqlVisitor.table); + String zkHost = tableSpec.zkHost; + String collection = tableSpec.collection; + Map params = new HashMap(); + + params.put("fl", fl.toString()); + params.put("q", sqlVisitor.query); + params.put("sort", siBuf.toString()); + + if(sqlVisitor.limit > -1) { + params.put("rows", Integer.toString(sqlVisitor.limit)); + return new LimitStream(new CloudSolrStream(zkHost, collection, params), sqlVisitor.limit); + } else { + //Only use the export handler when no limit is specified. + params.put(CommonParams.QT, "/export"); + return new CloudSolrStream(zkHost, collection, params); + } + } + + private static boolean sortsEqual(Bucket[] buckets, String direction, List sortItems) { + if(buckets.length != sortItems.size()) { + return false; + } + + for(int i=0; i< buckets.length; i++) { + Bucket bucket = buckets[i]; + SortItem sortItem = sortItems.get(i); + if(!bucket.toString().equals(stripQuotes(sortItem.getSortKey().toString()))) { + return false; + } + + + if(!sortItem.getOrdering().toString().toLowerCase(Locale.getDefault()).contains(direction.toLowerCase(Locale.getDefault()))) { + return false; + } + } + + return true; + } + + private static String bucketSort(Bucket[] buckets, String dir) { + StringBuilder buf = new StringBuilder(); + boolean comma = false; + for(Bucket bucket : buckets) { + if(comma) { + buf.append(","); + } + buf.append(bucket.toString()).append(" ").append(dir); + comma = true; + } + + return buf.toString(); + } + + private static String getPartitionKeys(Bucket[] buckets) { + StringBuilder buf = new StringBuilder(); + boolean comma = false; + for(Bucket bucket : buckets) { + if(comma) { + buf.append(","); + } + buf.append(bucket.toString()); + comma = true; + } + return buf.toString(); + } + + public static String getSortDirection(List sorts) { + if(sorts != null && sorts.size() > 0) { + for(SortItem item : sorts) { + return ascDesc(stripQuotes(item.getOrdering().toString())); + } + } + + return "asc"; + } + + private static Comparator bucketSortComp(Bucket[] buckets, String dir) { + Comparator[] comps = new Comparator[buckets.length]; + for(int i=0; i getComp(List sortItems) { + Comparator[] comps = new Comparator[sortItems.size()]; + for(int i=0; i fieldSet) { + StringBuilder buf = new StringBuilder(); + boolean comma = false; + for(String field : fieldSet) { + if(comma) { + buf.append(","); + } + buf.append(field); + comma = true; + } + + return buf.toString(); + } + + private static Metric[] getMetrics(List fields, Set fieldSet) { + List metrics = new ArrayList(); + for(String field : fields) { + + if(field.contains("(")) { + + field = field.substring(0, field.length()-1); + String[] parts = field.split("\\("); + String function = parts[0]; + String column = parts[1]; + if(function.equals("min")) { + metrics.add(new MinMetric(column)); + fieldSet.add(column); + } else if(function.equals("max")) { + metrics.add(new MaxMetric(column)); + fieldSet.add(column); + } else if(function.equals("sum")) { + metrics.add(new SumMetric(column)); + fieldSet.add(column); + } else if(function.equals("avg")) { + metrics.add(new MeanMetric(column)); + fieldSet.add(column); + } else if(function.equals("count")) { + metrics.add(new CountMetric()); + } + } + } + return metrics.toArray(new Metric[metrics.size()]); + } + + private static Bucket[] getBuckets(List fields, Set fieldSet) { + List buckets = new ArrayList(); + for(String field : fields) { + String f = stripQuotes(field); + buckets.add(new Bucket(f)); + fieldSet.add(f); + } + + return buckets.toArray(new Bucket[buckets.size()]); + } + + private static String ascDesc(String s) { + if(s.toLowerCase(Locale.getDefault()).contains("desc")) { + return "desc"; + } else { + return "asc"; + } + } + + private static ComparatorOrder ascDescComp(String s) { + if(s.toLowerCase(Locale.getDefault()).contains("desc")) { + return ComparatorOrder.DESCENDING; + } else { + return ComparatorOrder.ASCENDING; + } + } + + private static String stripQuotes(String s) { + StringBuilder buf = new StringBuilder(); + for(int i=0; i { + + protected Void visitLogicalBinaryExpression(LogicalBinaryExpression node, StringBuilder buf) { + buf.append("("); + process(node.getLeft(), buf); + buf.append(" ").append(node.getType().toString()).append(" "); + process(node.getRight(), buf); + buf.append(")"); + return null; + } + + protected Void visitNotExpression(NotExpression node, StringBuilder buf) { + buf.append("-"); + process(node.getValue(), buf); + return null; + } + + protected Void visitComparisonExpression(ComparisonExpression node, StringBuilder buf) { + String field = node.getLeft().toString(); + String value = node.getRight().toString(); + buf.append('(').append(stripQuotes(field) + ":" + stripSingleQuotes(value)).append(')'); + return null; + } + } + + static class SQLVisitor extends AstVisitor { + private final StringBuilder builder; + public String table; + public List fields = new ArrayList(); + public List groupBy = new ArrayList(); + public List sorts; + public String query ="*:*"; //If no query is specified pull all the records + public int limit = -1; + public boolean groupByQuery; + public Expression havingExpression; + + public SQLVisitor(StringBuilder builder) { + this.builder = builder; + } + + protected Void visitNode(Node node, Integer indent) { + throw new UnsupportedOperationException("not yet implemented: " + node); + } + + protected Void visitUnnest(Unnest node, Integer indent) { + return null; + } + + protected Void visitQuery(Query node, Integer indent) { + if(node.getWith().isPresent()) { + With confidence = (With)node.getWith().get(); + this.append(indent.intValue(), "WITH"); + if(confidence.isRecursive()) { + } + + Iterator queries = confidence.getQueries().iterator(); + + while(queries.hasNext()) { + WithQuery query = (WithQuery)queries.next(); + this.process(new TableSubquery(query.getQuery()), indent); + if(queries.hasNext()) { + } + } + } + + this.processRelation(node.getQueryBody(), indent); + if(!node.getOrderBy().isEmpty()) { + this.sorts = node.getOrderBy(); + } + + if(node.getLimit().isPresent()) { + } + + if(node.getApproximate().isPresent()) { + + } + + return null; + } + + protected Void visitQuerySpecification(QuerySpecification node, Integer indent) { + this.process(node.getSelect(), indent); + if(node.getFrom().isPresent()) { + this.process((Node)node.getFrom().get(), indent); + } + + if(node.getWhere().isPresent()) { + Expression ex = node.getWhere().get(); + ExpressionVisitor expressionVisitor = new ExpressionVisitor(); + StringBuilder buf = new StringBuilder(); + expressionVisitor.process(ex, buf); + this.query = buf.toString(); + } + + if(!node.getGroupBy().isEmpty()) { + this.groupByQuery = true; + List groups = node.getGroupBy(); + for(Expression group : groups) { + groupBy.add(stripQuotes(group.toString())); + + } + } + + if(node.getHaving().isPresent()) { + this.havingExpression = node.getHaving().get(); + } + + if(!node.getOrderBy().isEmpty()) { + this.sorts = node.getOrderBy(); + } + + if(node.getLimit().isPresent()) { + this.limit = Integer.parseInt(stripQuotes(node.getLimit().get())); + } + + return null; + } + + + + protected Void visitComparisonExpression(ComparisonExpression node, Integer index) { + String field = node.getLeft().toString(); + String value = node.getRight().toString(); + query = stripQuotes(field)+":"+stripQuotes(value); + return null; + } + + protected Void visitSelect(Select node, Integer indent) { + this.append(indent.intValue(), "SELECT"); + if(node.isDistinct()) { + + } + + if(node.getSelectItems().size() > 1) { + boolean first = true; + + for(Iterator var4 = node.getSelectItems().iterator(); var4.hasNext(); first = false) { + SelectItem item = (SelectItem)var4.next(); + this.process(item, indent); + } + } else { + this.process((Node) Iterables.getOnlyElement(node.getSelectItems()), indent); + } + + return null; + } + + protected Void visitSingleColumn(SingleColumn node, Integer indent) { + fields.add(stripQuotes(ExpressionFormatter.formatExpression(node.getExpression()))); + + if(node.getAlias().isPresent()) { + } + + return null; + } + + protected Void visitAllColumns(AllColumns node, Integer context) { + return null; + } + + protected Void visitTable(Table node, Integer indent) { + this.table = node.getName().toString(); + return null; + } + + protected Void visitAliasedRelation(AliasedRelation node, Integer indent) { + this.process(node.getRelation(), indent); + return null; + } + + protected Void visitValues(Values node, Integer indent) { + boolean first = true; + + for(Iterator var4 = node.getRows().iterator(); var4.hasNext(); first = false) { + Expression row = (Expression)var4.next(); + + } + + return null; + } + + private void processRelation(Relation relation, Integer indent) { + if(relation instanceof Table) { + } else { + this.process(relation, indent); + } + } + + private StringBuilder append(int indent, String value) { + return this.builder.append(indentString(indent)).append(value); + } + + private static String indentString(int indent) { + return Strings.repeat(" ", indent); + } + } + + private static class LimitStream extends TupleStream { + + private TupleStream stream; + private int limit; + private int count; + + public LimitStream(TupleStream stream, int limit) { + this.stream = stream; + this.limit = limit; + } + + public void open() throws IOException { + this.stream.open(); + } + + public void close() throws IOException { + this.stream.close(); + } + + public List children() { + List children = new ArrayList(); + children.add(stream); + return children; + } + + public void setStreamContext(StreamContext context) { + stream.setStreamContext(context); + } + + public Tuple read() throws IOException { + ++count; + if(count > limit) { + Map fields = new HashMap(); + fields.put("EOF", "true"); + return new Tuple(fields); + } + + Tuple tuple = stream.read(); + return tuple; + } + } + + public static class HavingStream extends TupleStream { + + private TupleStream stream; + private HavingVisitor havingVisitor; + private Expression havingExpression; + + public HavingStream(TupleStream stream, Expression havingExpression) { + this.stream = stream; + this.havingVisitor = new HavingVisitor(); + this.havingExpression = havingExpression; + } + + public void open() throws IOException { + this.stream.open(); + } + + public void close() throws IOException { + this.stream.close(); + } + + public List children() { + List children = new ArrayList(); + children.add(stream); + return children; + } + + public void setStreamContext(StreamContext context) { + stream.setStreamContext(context); + } + + public Tuple read() throws IOException { + while (true) { + Tuple tuple = stream.read(); + if (tuple.EOF) { + return tuple; + } + + if (havingVisitor.process(havingExpression, tuple)) { + return tuple; + } + } + } + } + + private static class HavingVisitor extends AstVisitor { + + protected Boolean visitLogicalBinaryExpression(LogicalBinaryExpression node, Tuple tuple) { + + Boolean b = process(node.getLeft(), tuple); + if(node.getType() == LogicalBinaryExpression.Type.AND) { + if(!b) { + //Short circuit + return false; + } else { + return process(node.getRight(), tuple); + } + } else { + if(b) { + //Short circuit + return true; + } else { + return process(node.getRight(), tuple); + } + } + } + + protected Boolean visitComparisonExpression(ComparisonExpression node, Tuple tuple) { + String field = stripQuotes(node.getLeft().toString()); + double d = Double.parseDouble(node.getRight().toString()); + double td = tuple.getDouble(field); + ComparisonExpression.Type t = node.getType(); + + switch(t) { + case LESS_THAN: + return td < d; + case LESS_THAN_OR_EQUAL: + return td <= d; + case NOT_EQUAL: + return td != d; + case EQUAL: + return td == d; + case GREATER_THAN: + return td <= d; + case GREATER_THAN_OR_EQUAL: + return td <= d; + default: + return false; + } + } + } + } diff --git a/solr/core/src/java/org/apache/solr/handler/StreamHandler.java b/solr/core/src/java/org/apache/solr/handler/StreamHandler.java index 536fe160259..4195351e2d5 100644 --- a/solr/core/src/java/org/apache/solr/handler/StreamHandler.java +++ b/solr/core/src/java/org/apache/solr/handler/StreamHandler.java @@ -45,7 +45,7 @@ import org.apache.solr.common.util.Base64; public class StreamHandler extends RequestHandlerBase implements SolrCoreAware { - private SolrClientCache clientCache = new SolrClientCache(); + static SolrClientCache clientCache = new SolrClientCache(); private StreamFactory streamFactory = new StreamFactory(); public void inform(SolrCore core) { diff --git a/solr/core/src/test-files/solr/collection1/conf/schema-sql.xml b/solr/core/src/test-files/solr/collection1/conf/schema-sql.xml new file mode 100644 index 00000000000..216fa2ce85b --- /dev/null +++ b/solr/core/src/test-files/solr/collection1/conf/schema-sql.xml @@ -0,0 +1,599 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + text + id + + + + + + + + + + + + + + + + + + + + + diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig-sql.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig-sql.xml new file mode 100644 index 00000000000..4fc231e851f --- /dev/null +++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig-sql.xml @@ -0,0 +1,107 @@ + + + + + + ${tests.luceneMatchVersion:LUCENE_CURRENT} + + ${useCompoundFile:false} + + ${solr.data.dir:} + + + + + ${solr.data.dir:} + + + + + + + true + + + + + + {!xport} + xsort + false + + + + query + + + + + + + + json + false + + + + + + json + false + + + collection1 + + + + + + + + + + + + + + + + + + *:* + + + all + + server-enabled.txt + + + + + solr + + + + diff --git a/solr/core/src/test/org/apache/solr/handler/TestSQLHandler.java b/solr/core/src/test/org/apache/solr/handler/TestSQLHandler.java new file mode 100644 index 00000000000..5470c2d7f19 --- /dev/null +++ b/solr/core/src/test/org/apache/solr/handler/TestSQLHandler.java @@ -0,0 +1,843 @@ +package org.apache.solr.handler; + +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.io.File; +import java.io.IOException; +import java.util.ArrayList; +import java.util.HashMap; +import java.util.List; +import java.util.Map; + + +import com.facebook.presto.sql.parser.SqlParser; +import com.facebook.presto.sql.tree.Statement; +import org.apache.solr.client.solrj.io.Tuple; +import org.apache.solr.client.solrj.io.stream.SolrStream; +import org.apache.solr.client.solrj.io.stream.TupleStream; +import org.apache.solr.cloud.AbstractFullDistribZkTestBase; +import org.apache.solr.common.params.CommonParams; +import org.junit.After; +import org.junit.AfterClass; +import org.junit.Before; +import org.junit.BeforeClass; +import org.junit.Test; + +public class TestSQLHandler extends AbstractFullDistribZkTestBase { + + + static { + schemaString = "schema-sql.xml"; + } + + public TestSQLHandler() { + sliceCount = 2; + } + + //@BeforeClass + //public static void beforeSuperClass() { + //AbstractZkTestCase.SOLRHOME = new File(SOLR_HOME()); + // } + + @AfterClass + public static void afterSuperClass() { + + } + + protected String getCloudSolrConfig() { + return "solrconfig-sql.xml"; + } + + @Before + @Override + public void setUp() throws Exception { + super.setUp(); + // we expect this time of exception as shards go up and down... + //ignoreException(".*"); + + System.setProperty("numShards", Integer.toString(sliceCount)); + } + + @Override + @After + public void tearDown() throws Exception { + super.tearDown(); + resetExceptionIgnores(); + } + + private void delete() throws Exception { + deleteCore(); + } + + @Test + public void doTest() throws Exception { + testPredicate(); + testBasicSelect(); + testBasicGrouping(); + testTimeSeriesGrouping(); + testParallelBasicGrouping(); + testParallelTimeSeriesGrouping(); + } + + private void testPredicate() throws Exception { + + SqlParser parser = new SqlParser(); + String sql = "select a from b where c = 'd'"; + Statement statement = parser.createStatement(sql); + SQLHandler.SQLVisitor sqlVistor = new SQLHandler.SQLVisitor(new StringBuilder()); + sqlVistor.process(statement, new Integer(0)); + + assert(sqlVistor.query.equals("(c:d)")); + + //Add parens + parser = new SqlParser(); + sql = "select a from b where (c = 'd')"; + statement = parser.createStatement(sql); + sqlVistor = new SQLHandler.SQLVisitor(new StringBuilder()); + sqlVistor.process(statement, new Integer(0)); + + assert(sqlVistor.query.equals("(c:d)")); + + //Phrase + parser = new SqlParser(); + sql = "select a from b where (c = '\"d d\"')"; + statement = parser.createStatement(sql); + sqlVistor = new SQLHandler.SQLVisitor(new StringBuilder()); + sqlVistor.process(statement, new Integer(0)); + + assert(sqlVistor.query.equals("(c:\"d d\")")); + + // AND + parser = new SqlParser(); + sql = "select a from b where ((c = 'd') AND (l = 'z'))"; + statement = parser.createStatement(sql); + sqlVistor = new SQLHandler.SQLVisitor(new StringBuilder()); + sqlVistor.process(statement, new Integer(0)); + + assert(sqlVistor.query.equals("((c:d) AND (l:z))")); + + // OR + + parser = new SqlParser(); + sql = "select a from b where ((c = 'd') OR (l = 'z'))"; + statement = parser.createStatement(sql); + sqlVistor = new SQLHandler.SQLVisitor(new StringBuilder()); + sqlVistor.process(statement, new Integer(0)); + + assert(sqlVistor.query.equals("((c:d) OR (l:z))")); + + // AND NOT + + parser = new SqlParser(); + sql = "select a from b where ((c = 'd') AND NOT (l = 'z'))"; + statement = parser.createStatement(sql); + sqlVistor = new SQLHandler.SQLVisitor(new StringBuilder()); + sqlVistor.process(statement, new Integer(0)); + + assert(sqlVistor.query.equals("((c:d) AND -(l:z))")); + + // NESTED + parser = new SqlParser(); + sql = "select a from b where ((c = 'd') OR ((l = 'z') AND (m = 'j')))"; + statement = parser.createStatement(sql); + sqlVistor = new SQLHandler.SQLVisitor(new StringBuilder()); + sqlVistor.process(statement, new Integer(0)); + + assert(sqlVistor.query.equals("((c:d) OR ((l:z) AND (m:j)))")); + + // NESTED NOT + parser = new SqlParser(); + sql = "select a from b where ((c = 'd') OR ((l = 'z') AND NOT (m = 'j')))"; + statement = parser.createStatement(sql); + sqlVistor = new SQLHandler.SQLVisitor(new StringBuilder()); + sqlVistor.process(statement, new Integer(0)); + + assert(sqlVistor.query.equals("((c:d) OR ((l:z) AND -(m:j)))")); + + // RANGE - Will have to do until SQL BETWEEN is supported. + // NESTED + parser = new SqlParser(); + sql = "select a from b where ((c = '[0 TO 100]') OR ((l = 'z') AND (m = 'j')))"; + statement = parser.createStatement(sql); + sqlVistor = new SQLHandler.SQLVisitor(new StringBuilder()); + sqlVistor.process(statement, new Integer(0)); + + assert(sqlVistor.query.equals("((c:[0 TO 100]) OR ((l:z) AND (m:j)))")); + + // Wildcard + parser = new SqlParser(); + sql = "select a from b where ((c = '[0 TO 100]') OR ((l = 'z*') AND (m = 'j')))"; + statement = parser.createStatement(sql); + sqlVistor = new SQLHandler.SQLVisitor(new StringBuilder()); + sqlVistor.process(statement, new Integer(0)); + assert(sqlVistor.query.equals("((c:[0 TO 100]) OR ((l:z*) AND (m:j)))")); + + // Complex Lucene/Solr Query + parser = new SqlParser(); + sql = "select a from b where ((c = '[0 TO 100]') OR ((l = 'z*') AND (m = '(j OR (k NOT s))')))"; + statement = parser.createStatement(sql); + sqlVistor = new SQLHandler.SQLVisitor(new StringBuilder()); + sqlVistor.process(statement, new Integer(0)); + assert(sqlVistor.query.equals("((c:[0 TO 100]) OR ((l:z*) AND (m:(j OR (k NOT s)))))")); + } + + private void testBasicSelect() throws Exception { + try { + + CloudJettyRunner jetty = this.cloudJettys.get(0); + + del("*:*"); + + commit(); + + indexr("id", "1", "text", "XXXX XXXX", "str_s", "a", "field_i", "7"); + indexr("id", "2", "text", "XXXX XXXX", "str_s", "b", "field_i", "8"); + indexr("id", "3", "text", "XXXX XXXX", "str_s", "a", "field_i", "20"); + indexr("id", "4", "text", "XXXX XXXX", "str_s", "b", "field_i", "11"); + indexr("id", "5", "text", "XXXX XXXX", "str_s", "c", "field_i", "30"); + indexr("id", "6", "text", "XXXX XXXX", "str_s", "c", "field_i", "40"); + indexr("id", "7", "text", "XXXX XXXX", "str_s", "c", "field_i", "50"); + indexr("id", "8", "text", "XXXX XXXX", "str_s", "c", "field_i", "60"); + commit(); + Map params = new HashMap(); + params.put(CommonParams.QT, "/sql"); + params.put("sql", "select id, field_i, str_s from mytable where text='XXXX' order by field_i desc"); + + SolrStream solrStream = new SolrStream(jetty.url, params); + List tuples = getTuples(solrStream); + + assert(tuples.size() == 8); + + Tuple tuple = null; + + tuple = tuples.get(0); + assert(tuple.getLong("id") == 8); + assert(tuple.getLong("field_i") == 60); + assert(tuple.get("str_s").equals("c")); + + tuple = tuples.get(1); + assert(tuple.getLong("id") == 7); + assert(tuple.getLong("field_i") == 50); + assert(tuple.get("str_s").equals("c")); + + tuple = tuples.get(2); + assert(tuple.getLong("id") == 6); + assert(tuple.getLong("field_i") == 40); + assert(tuple.get("str_s").equals("c")); + + tuple = tuples.get(3); + assert(tuple.getLong("id") == 5); + assert(tuple.getLong("field_i") == 30); + assert(tuple.get("str_s").equals("c")); + + tuple = tuples.get(4); + assert(tuple.getLong("id") == 3); + assert(tuple.getLong("field_i") == 20); + assert(tuple.get("str_s").equals("a")); + + tuple = tuples.get(5); + assert(tuple.getLong("id") == 4); + assert(tuple.getLong("field_i") == 11); + assert(tuple.get("str_s").equals("b")); + + tuple = tuples.get(6); + assert(tuple.getLong("id") == 2); + assert(tuple.getLong("field_i") == 8); + assert(tuple.get("str_s").equals("b")); + + tuple = tuples.get(7); + assert(tuple.getLong("id") == 1); + assert(tuple.getLong("field_i") == 7); + assert(tuple.get("str_s").equals("a")); + + params = new HashMap(); + params.put(CommonParams.QT, "/sql"); + params.put("sql", "select id, field_i, str_s from mytable where text='XXXX' order by field_i desc limit 1"); + + solrStream = new SolrStream(jetty.url, params); + tuples = getTuples(solrStream); + + assert(tuples.size() == 1); + + tuple = tuples.get(0); + assert(tuple.getLong("id") == 8); + assert(tuple.getLong("field_i") == 60); + assert(tuple.get("str_s").equals("c")); + + params = new HashMap(); + params.put(CommonParams.QT, "/sql"); + params.put("sql", "select id, field_i, str_s from mytable where text='XXXX' AND id='(1 2 3)' order by field_i desc"); + + solrStream = new SolrStream(jetty.url, params); + tuples = getTuples(solrStream); + + assert(tuples.size() == 3); + + tuple = tuples.get(0); + assert(tuple.getLong("id") == 3); + assert(tuple.getLong("field_i") == 20); + assert(tuple.get("str_s").equals("a")); + + tuple = tuples.get(1); + assert(tuple.getLong("id") == 2); + assert(tuple.getLong("field_i") == 8); + assert(tuple.get("str_s").equals("b")); + + tuple = tuples.get(2); + assert(tuple.getLong("id") == 1); + assert(tuple.getLong("field_i") == 7); + assert(tuple.get("str_s").equals("a")); + + } finally { + delete(); + } + } + + private void testBasicGrouping() throws Exception { + try { + + CloudJettyRunner jetty = this.cloudJettys.get(0); + + del("*:*"); + + commit(); + + indexr("id", "1", "text", "XXXX XXXX", "str_s", "a", "field_i", "7"); + indexr("id", "2", "text", "XXXX XXXX", "str_s", "b", "field_i", "8"); + indexr("id", "3", "text", "XXXX XXXX", "str_s", "a", "field_i", "20"); + indexr("id", "4", "text", "XXXX XXXX", "str_s", "b", "field_i", "11"); + indexr("id", "5", "text", "XXXX XXXX", "str_s", "c", "field_i", "30"); + indexr("id", "6", "text", "XXXX XXXX", "str_s", "c", "field_i", "40"); + indexr("id", "7", "text", "XXXX XXXX", "str_s", "c", "field_i", "50"); + indexr("id", "8", "text", "XXXX XXXX", "str_s", "c", "field_i", "60"); + commit(); + Map params = new HashMap(); + params.put(CommonParams.QT, "/sql"); + params.put("sql", "select str_s, count(*), sum(field_i), min(field_i), max(field_i), avg(field_i) from mytable where text='XXXX' group by str_s order by sum(field_i) asc limit 2"); + + SolrStream solrStream = new SolrStream(jetty.url, params); + List tuples = getTuples(solrStream); + + //Only two results because of the limit. + assert(tuples.size() == 2); + + Tuple tuple = null; + + tuple = tuples.get(0); + assert(tuple.get("str_s").equals("b")); + assert(tuple.getDouble("count(*)") == 2); + assert(tuple.getDouble("sum(field_i)") == 19); + assert(tuple.getDouble("min(field_i)") == 8); + assert(tuple.getDouble("max(field_i)") == 11); + assert(tuple.getDouble("avg(field_i)") == 9.5D); + + tuple = tuples.get(1); + assert(tuple.get("str_s").equals("a")); + assert(tuple.getDouble("count(*)") == 2); + assert(tuple.getDouble("sum(field_i)") == 27); + assert(tuple.getDouble("min(field_i)") == 7); + assert(tuple.getDouble("max(field_i)") == 20); + assert(tuple.getDouble("avg(field_i)") == 13.5D); + + params = new HashMap(); + params.put(CommonParams.QT, "/sql"); + params.put("sql", "select str_s, count(*), sum(field_i), min(field_i), max(field_i), avg(field_i) from mytable where (text='XXXX' AND NOT text='\"XXXX XXX\"') group by str_s order by str_s desc"); + + solrStream = new SolrStream(jetty.url, params); + tuples = getTuples(solrStream); + + //The sort by and order by match and no limit is applied. All the Tuples should be returned in + //this scenario. + + assert(tuples.size() == 3); + + tuple = tuples.get(0); + assert(tuple.get("str_s").equals("c")); + assert(tuple.getDouble("count(*)") == 4); + assert(tuple.getDouble("sum(field_i)") == 180); + assert(tuple.getDouble("min(field_i)") == 30); + assert(tuple.getDouble("max(field_i)") == 60); + assert(tuple.getDouble("avg(field_i)") == 45); + + tuple = tuples.get(1); + assert(tuple.get("str_s").equals("b")); + assert(tuple.getDouble("count(*)") == 2); + assert(tuple.getDouble("sum(field_i)") == 19); + assert(tuple.getDouble("min(field_i)") == 8); + assert(tuple.getDouble("max(field_i)") == 11); + assert(tuple.getDouble("avg(field_i)") == 9.5D); + + tuple = tuples.get(2); + assert(tuple.get("str_s").equals("a")); + assert(tuple.getDouble("count(*)") == 2); + assert(tuple.getDouble("sum(field_i)") == 27); + assert(tuple.getDouble("min(field_i)") == 7); + assert(tuple.getDouble("max(field_i)") == 20); + assert(tuple.getDouble("avg(field_i)") == 13.5D); + + + params = new HashMap(); + params.put(CommonParams.QT, "/sql"); + params.put("sql", "select str_s, count(*), sum(field_i), min(field_i), max(field_i), avg(field_i) from mytable where text='XXXX' group by str_s having sum(field_i) = 19"); + + solrStream = new SolrStream(jetty.url, params); + tuples = getTuples(solrStream); + + assert(tuples.size() == 1); + + tuple = tuples.get(0); + assert(tuple.get("str_s").equals("b")); + assert(tuple.getDouble("count(*)") == 2); + assert(tuple.getDouble("sum(field_i)") == 19); + assert(tuple.getDouble("min(field_i)") == 8); + assert(tuple.getDouble("max(field_i)") == 11); + assert(tuple.getDouble("avg(field_i)") == 9.5D); + + params = new HashMap(); + params.put(CommonParams.QT, "/sql"); + params.put("sql", "select str_s, count(*), sum(field_i), min(field_i), max(field_i), avg(field_i) from mytable where text='XXXX' group by str_s having ((sum(field_i) = 19) AND (min(field_i) = 8))"); + + solrStream = new SolrStream(jetty.url, params); + tuples = getTuples(solrStream); + + //Only two results because of the limit. + assert(tuples.size() == 1); + + tuple = tuples.get(0); + assert(tuple.get("str_s").equals("b")); + assert(tuple.getDouble("count(*)") == 2); + assert(tuple.getDouble("sum(field_i)") == 19); + assert(tuple.getDouble("min(field_i)") == 8); + assert(tuple.getDouble("max(field_i)") == 11); + assert(tuple.getDouble("avg(field_i)") == 9.5D); + + params = new HashMap(); + params.put(CommonParams.QT, "/sql"); + params.put("sql", "select str_s, count(*), sum(field_i), min(field_i), max(field_i), avg(field_i) from mytable where text='XXXX' group by str_s having ((sum(field_i) = 19) AND (min(field_i) = 100))"); + + solrStream = new SolrStream(jetty.url, params); + tuples = getTuples(solrStream); + + assert(tuples.size() == 0); + + + } finally { + delete(); + } + } + + private void testParallelBasicGrouping() throws Exception { + try { + + CloudJettyRunner jetty = this.cloudJettys.get(0); + + del("*:*"); + + commit(); + + indexr("id", "1", "text", "XXXX XXXX", "str_s", "a", "field_i", "7"); + indexr("id", "2", "text", "XXXX XXXX", "str_s", "b", "field_i", "8"); + indexr("id", "3", "text", "XXXX XXXX", "str_s", "a", "field_i", "20"); + indexr("id", "4", "text", "XXXX XXXX", "str_s", "b", "field_i", "11"); + indexr("id", "5", "text", "XXXX XXXX", "str_s", "c", "field_i", "30"); + indexr("id", "6", "text", "XXXX XXXX", "str_s", "c", "field_i", "40"); + indexr("id", "7", "text", "XXXX XXXX", "str_s", "c", "field_i", "50"); + indexr("id", "8", "text", "XXXX XXXX", "str_s", "c", "field_i", "60"); + commit(); + Map params = new HashMap(); + params.put(CommonParams.QT, "/sql"); + params.put("numWorkers", "2"); + params.put("sql", "select str_s, count(*), sum(field_i), min(field_i), max(field_i), avg(field_i) from mytable where text='XXXX' group by str_s order by sum(field_i) asc limit 2"); + + SolrStream solrStream = new SolrStream(jetty.url, params); + List tuples = getTuples(solrStream); + + //Only two results because of the limit. + assert(tuples.size() == 2); + + Tuple tuple = null; + + tuple = tuples.get(0); + assert(tuple.get("str_s").equals("b")); + assert(tuple.getDouble("count(*)") == 2); + assert(tuple.getDouble("sum(field_i)") == 19); + assert(tuple.getDouble("min(field_i)") == 8); + assert(tuple.getDouble("max(field_i)") == 11); + assert(tuple.getDouble("avg(field_i)") == 9.5D); + + tuple = tuples.get(1); + assert(tuple.get("str_s").equals("a")); + assert(tuple.getDouble("count(*)") == 2); + assert(tuple.getDouble("sum(field_i)") == 27); + assert(tuple.getDouble("min(field_i)") == 7); + assert(tuple.getDouble("max(field_i)") == 20); + assert(tuple.getDouble("avg(field_i)") == 13.5D); + + params = new HashMap(); + params.put(CommonParams.QT, "/sql"); + params.put("numWorkers", "2"); + params.put("sql", "select str_s, count(*), sum(field_i), min(field_i), max(field_i), avg(field_i) from mytable where text='XXXX' group by str_s order by str_s desc"); + + solrStream = new SolrStream(jetty.url, params); + tuples = getTuples(solrStream); + + //The sort by and order by match and no limit is applied. All the Tuples should be returned in + //this scenario. + + assert(tuples.size() == 3); + + tuple = tuples.get(0); + assert(tuple.get("str_s").equals("c")); + assert(tuple.getDouble("count(*)") == 4); + assert(tuple.getDouble("sum(field_i)") == 180); + assert(tuple.getDouble("min(field_i)") == 30); + assert(tuple.getDouble("max(field_i)") == 60); + assert(tuple.getDouble("avg(field_i)") == 45); + + tuple = tuples.get(1); + assert(tuple.get("str_s").equals("b")); + assert(tuple.getDouble("count(*)") == 2); + assert(tuple.getDouble("sum(field_i)") == 19); + assert(tuple.getDouble("min(field_i)") == 8); + assert(tuple.getDouble("max(field_i)") == 11); + assert(tuple.getDouble("avg(field_i)") == 9.5D); + + tuple = tuples.get(2); + assert(tuple.get("str_s").equals("a")); + assert(tuple.getDouble("count(*)") == 2); + assert(tuple.getDouble("sum(field_i)") == 27); + assert(tuple.getDouble("min(field_i)") == 7); + assert(tuple.getDouble("max(field_i)") == 20); + assert(tuple.getDouble("avg(field_i)") == 13.5D); + + params = new HashMap(); + params.put(CommonParams.QT, "/sql"); + params.put("numWorkers", "2"); + params.put("sql", "select str_s, count(*), sum(field_i), min(field_i), max(field_i), avg(field_i) from mytable where text='XXXX' group by str_s having sum(field_i) = 19"); + + solrStream = new SolrStream(jetty.url, params); + tuples = getTuples(solrStream); + + //Only two results because of the limit. + assert(tuples.size() == 1); + + tuple = tuples.get(0); + assert(tuple.get("str_s").equals("b")); + assert(tuple.getDouble("count(*)") == 2); + assert(tuple.getDouble("sum(field_i)") == 19); + assert(tuple.getDouble("min(field_i)") == 8); + assert(tuple.getDouble("max(field_i)") == 11); + assert(tuple.getDouble("avg(field_i)") == 9.5D); + + tuple = tuples.get(0); + assert(tuple.get("str_s").equals("b")); + assert(tuple.getDouble("count(*)") == 2); + assert(tuple.getDouble("sum(field_i)") == 19); + assert(tuple.getDouble("min(field_i)") == 8); + assert(tuple.getDouble("max(field_i)") == 11); + assert(tuple.getDouble("avg(field_i)") == 9.5D); + + params = new HashMap(); + params.put(CommonParams.QT, "/sql"); + params.put("numWorkers", "2"); + params.put("sql", "select str_s, count(*), sum(field_i), min(field_i), max(field_i), avg(field_i) from mytable where text='XXXX' group by str_s having ((sum(field_i) = 19) AND (min(field_i) = 8))"); + + solrStream = new SolrStream(jetty.url, params); + tuples = getTuples(solrStream); + + //Only two results because of the limit. + assert(tuples.size() == 1); + + tuple = tuples.get(0); + assert(tuple.get("str_s").equals("b")); + assert(tuple.getDouble("count(*)") == 2); + assert(tuple.getDouble("sum(field_i)") == 19); + assert(tuple.getDouble("min(field_i)") == 8); + assert(tuple.getDouble("max(field_i)") == 11); + assert(tuple.getDouble("avg(field_i)") == 9.5D); + + params = new HashMap(); + params.put(CommonParams.QT, "/sql"); + params.put("numWorkers", "2"); + params.put("sql", "select str_s, count(*), sum(field_i), min(field_i), max(field_i), avg(field_i) from mytable where text='XXXX' group by str_s having ((sum(field_i) = 19) AND (min(field_i) = 100))"); + + solrStream = new SolrStream(jetty.url, params); + tuples = getTuples(solrStream); + + assert(tuples.size() == 0); + + } finally { + delete(); + } + } + + private void testTimeSeriesGrouping() throws Exception { + try { + + CloudJettyRunner jetty = this.cloudJettys.get(0); + + del("*:*"); + + commit(); + + indexr("id", "1", "year_i", "2015", "month_i", "11", "day_i", "7", "item_i", "5"); + indexr("id", "2", "year_i", "2015", "month_i", "11", "day_i", "7", "item_i", "10"); + indexr("id", "3", "year_i", "2015", "month_i", "11", "day_i", "8", "item_i", "30"); + indexr("id", "4", "year_i", "2015", "month_i", "11", "day_i", "8", "item_i", "12"); + indexr("id", "5", "year_i", "2015", "month_i", "10", "day_i", "1", "item_i", "4"); + indexr("id", "6", "year_i", "2015", "month_i", "10", "day_i", "3", "item_i", "5"); + indexr("id", "7", "year_i", "2014", "month_i", "4", "day_i", "4", "item_i", "6"); + indexr("id", "8", "year_i", "2014", "month_i", "4", "day_i", "2", "item_i", "1"); + + commit(); + Map params = new HashMap(); + params.put(CommonParams.QT, "/sql"); + params.put("sql", "select year_i, sum(item_i) from mytable group by year_i order by year_i desc"); + + SolrStream solrStream = new SolrStream(jetty.url, params); + List tuples = getTuples(solrStream); + + //Only two results because of the limit. + assert(tuples.size() == 2); + + Tuple tuple = null; + + tuple = tuples.get(0); + assert(tuple.getLong("year_i") == 2015); + assert(tuple.getDouble("sum(item_i)") == 66); + + tuple = tuples.get(1); + assert(tuple.getLong("year_i") == 2014); + assert(tuple.getDouble("sum(item_i)") == 7); + + params.put("sql", "select year_i, month_i, sum(item_i) from mytable group by year_i, month_i order by year_i desc, month_i desc"); + + solrStream = new SolrStream(jetty.url, params); + tuples = getTuples(solrStream); + + //Only two results because of the limit. + assert(tuples.size() == 3); + + tuple = null; + + tuple = tuples.get(0); + assert(tuple.getLong("year_i") == 2015); + assert(tuple.getLong("month_i") == 11); + assert(tuple.getDouble("sum(item_i)") == 57); + + tuple = tuples.get(1); + assert(tuple.getLong("year_i") == 2015); + assert(tuple.getLong("month_i") == 10); + assert(tuple.getDouble("sum(item_i)") == 9); + + tuple = tuples.get(2); + assert(tuple.getLong("year_i") == 2014); + assert(tuple.getLong("month_i") == 4); + assert(tuple.getDouble("sum(item_i)") == 7); + + params = new HashMap(); + params.put(CommonParams.QT, "/sql"); + params.put("sql", "select year_i, month_i, day_i, sum(item_i) from mytable group by year_i, month_i, day_i order by year_i desc, month_i desc, day_i desc"); + + solrStream = new SolrStream(jetty.url, params); + tuples = getTuples(solrStream); + + //Only two results because of the limit. + assert(tuples.size() == 6); + + tuple = null; + + tuple = tuples.get(0); + assert(tuple.getLong("year_i") == 2015); + assert(tuple.getLong("month_i") == 11); + assert(tuple.getLong("day_i") == 8); + assert(tuple.getDouble("sum(item_i)") == 42); + + tuple = tuples.get(1); + assert(tuple.getLong("year_i") == 2015); + assert(tuple.getLong("month_i") == 11); + assert(tuple.getLong("day_i") == 7); + assert(tuple.getDouble("sum(item_i)") == 15); + + tuple = tuples.get(2); + assert(tuple.getLong("year_i") == 2015); + assert(tuple.getLong("month_i") == 10); + assert(tuple.getLong("day_i") == 3); + assert(tuple.getDouble("sum(item_i)") == 5); + + tuple = tuples.get(3); + assert(tuple.getLong("year_i") == 2015); + assert(tuple.getLong("month_i") == 10); + assert(tuple.getLong("day_i") == 1); + assert(tuple.getDouble("sum(item_i)") == 4); + + tuple = tuples.get(4); + assert(tuple.getLong("year_i") == 2014); + assert(tuple.getLong("month_i") == 4); + assert(tuple.getLong("day_i") == 4); + assert(tuple.getDouble("sum(item_i)") == 6); + + tuple = tuples.get(5); + assert(tuple.getLong("year_i") == 2014); + assert(tuple.getLong("month_i") == 4); + assert(tuple.getLong("day_i") == 2); + assert(tuple.getDouble("sum(item_i)") == 1); + + } finally { + delete(); + } + } + + private void testParallelTimeSeriesGrouping() throws Exception { + try { + + CloudJettyRunner jetty = this.cloudJettys.get(0); + + del("*:*"); + + commit(); + + indexr("id", "1", "year_i", "2015", "month_i", "11", "day_i", "7", "item_i", "5"); + indexr("id", "2", "year_i", "2015", "month_i", "11", "day_i", "7", "item_i", "10"); + indexr("id", "3", "year_i", "2015", "month_i", "11", "day_i", "8", "item_i", "30"); + indexr("id", "4", "year_i", "2015", "month_i", "11", "day_i", "8", "item_i", "12"); + indexr("id", "5", "year_i", "2015", "month_i", "10", "day_i", "1", "item_i", "4"); + indexr("id", "6", "year_i", "2015", "month_i", "10", "day_i", "3", "item_i", "5"); + indexr("id", "7", "year_i", "2014", "month_i", "4", "day_i", "4", "item_i", "6"); + indexr("id", "8", "year_i", "2014", "month_i", "4", "day_i", "2", "item_i", "1"); + + commit(); + Map params = new HashMap(); + params.put(CommonParams.QT, "/sql"); + params.put("numWorkers", 2); + params.put("sql", "select year_i, sum(item_i) from mytable group by year_i order by year_i desc"); + + SolrStream solrStream = new SolrStream(jetty.url, params); + List tuples = getTuples(solrStream); + + //Only two results because of the limit. + assert(tuples.size() == 2); + + Tuple tuple = null; + + tuple = tuples.get(0); + assert(tuple.getLong("year_i") == 2015); + assert(tuple.getDouble("sum(item_i)") == 66); + + tuple = tuples.get(1); + assert(tuple.getLong("year_i") == 2014); + assert(tuple.getDouble("sum(item_i)") == 7); + + new HashMap(); + params.put(CommonParams.QT, "/sql"); + params.put("numWorkers", 2); + params.put("sql", "select year_i, month_i, sum(item_i) from mytable group by year_i, month_i order by year_i desc, month_i desc"); + + solrStream = new SolrStream(jetty.url, params); + tuples = getTuples(solrStream); + + //Only two results because of the limit. + assert(tuples.size() == 3); + + tuple = null; + + tuple = tuples.get(0); + assert(tuple.getLong("year_i") == 2015); + assert(tuple.getLong("month_i") == 11); + assert(tuple.getDouble("sum(item_i)") == 57); + + tuple = tuples.get(1); + assert(tuple.getLong("year_i") == 2015); + assert(tuple.getLong("month_i") == 10); + assert(tuple.getDouble("sum(item_i)") == 9); + + tuple = tuples.get(2); + assert(tuple.getLong("year_i") == 2014); + assert(tuple.getLong("month_i") == 4); + assert(tuple.getDouble("sum(item_i)") == 7); + + + new HashMap(); + params.put(CommonParams.QT, "/sql"); + params.put("numWorkers", 2); + params.put("sql", "select year_i, month_i, day_i, sum(item_i) from mytable group by year_i, month_i, day_i order by year_i desc, month_i desc, day_i desc"); + + solrStream = new SolrStream(jetty.url, params); + tuples = getTuples(solrStream); + + //Only two results because of the limit. + assert(tuples.size() == 6); + + tuple = null; + + tuple = tuples.get(0); + assert(tuple.getLong("year_i") == 2015); + assert(tuple.getLong("month_i") == 11); + assert(tuple.getLong("day_i") == 8); + assert(tuple.getDouble("sum(item_i)") == 42); + + tuple = tuples.get(1); + assert(tuple.getLong("year_i") == 2015); + assert(tuple.getLong("month_i") == 11); + assert(tuple.getLong("day_i") == 7); + assert(tuple.getDouble("sum(item_i)") == 15); + + tuple = tuples.get(2); + assert(tuple.getLong("year_i") == 2015); + assert(tuple.getLong("month_i") == 10); + assert(tuple.getLong("day_i") == 3); + assert(tuple.getDouble("sum(item_i)") == 5); + + tuple = tuples.get(3); + assert(tuple.getLong("year_i") == 2015); + assert(tuple.getLong("month_i") == 10); + assert(tuple.getLong("day_i") == 1); + assert(tuple.getDouble("sum(item_i)") == 4); + + tuple = tuples.get(4); + assert(tuple.getLong("year_i") == 2014); + assert(tuple.getLong("month_i") == 4); + assert(tuple.getLong("day_i") == 4); + assert(tuple.getDouble("sum(item_i)") == 6); + + tuple = tuples.get(5); + assert(tuple.getLong("year_i") == 2014); + assert(tuple.getLong("month_i") == 4); + assert(tuple.getLong("day_i") == 2); + assert(tuple.getDouble("sum(item_i)") == 1); + + } finally { + delete(); + } + } + + protected List getTuples(TupleStream tupleStream) throws IOException { + tupleStream.open(); + List tuples = new ArrayList(); + for(;;) { + Tuple t = tupleStream.read(); + if(t.EOF) { + break; + } else { + tuples.add(t); + } + } + tupleStream.close(); + return tuples; + } +} diff --git a/solr/licenses/antlr4-runtime-4.5.jar.sha1 b/solr/licenses/antlr4-runtime-4.5.jar.sha1 new file mode 100644 index 00000000000..5299c19c73b --- /dev/null +++ b/solr/licenses/antlr4-runtime-4.5.jar.sha1 @@ -0,0 +1 @@ +29e48af049f17dd89153b83a7ad5d01b3b4bcdda diff --git a/solr/licenses/antlr4-runtime-LICENSE-BSD.txt b/solr/licenses/antlr4-runtime-LICENSE-BSD.txt new file mode 100644 index 00000000000..95d0a2554f6 --- /dev/null +++ b/solr/licenses/antlr4-runtime-LICENSE-BSD.txt @@ -0,0 +1,26 @@ +[The "BSD license"] +Copyright (c) 2015 Terence Parr, Sam Harwell +All rights reserved. + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions +are met: + + 1. Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + 2. Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + 3. The name of the author may not be used to endorse or promote products + derived from this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR +IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES +OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. +IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, +INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT +NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF +THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. diff --git a/solr/licenses/antlr4-runtime-NOTICE.txt b/solr/licenses/antlr4-runtime-NOTICE.txt new file mode 100644 index 00000000000..e69de29bb2d diff --git a/solr/licenses/presto-parser-0.107.jar.sha1 b/solr/licenses/presto-parser-0.107.jar.sha1 new file mode 100644 index 00000000000..0d0d9c66ae6 --- /dev/null +++ b/solr/licenses/presto-parser-0.107.jar.sha1 @@ -0,0 +1 @@ +f6f1363553855d1b70548721ce6cd5050b88a6bd \ No newline at end of file diff --git a/solr/licenses/presto-parser-LICENSE-ASL.txt b/solr/licenses/presto-parser-LICENSE-ASL.txt new file mode 100644 index 00000000000..d6456956733 --- /dev/null +++ b/solr/licenses/presto-parser-LICENSE-ASL.txt @@ -0,0 +1,202 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. diff --git a/solr/licenses/presto-parser-NOTICE.txt b/solr/licenses/presto-parser-NOTICE.txt new file mode 100644 index 00000000000..e69de29bb2d diff --git a/solr/licenses/slice-0.10.jar.sha1 b/solr/licenses/slice-0.10.jar.sha1 new file mode 100644 index 00000000000..7b86d91c215 --- /dev/null +++ b/solr/licenses/slice-0.10.jar.sha1 @@ -0,0 +1 @@ +159a81631ed2cc1bc865f3d8e51239c9e8a20bea diff --git a/solr/licenses/slice-LICENSE-ASL.txt b/solr/licenses/slice-LICENSE-ASL.txt new file mode 100644 index 00000000000..d6456956733 --- /dev/null +++ b/solr/licenses/slice-LICENSE-ASL.txt @@ -0,0 +1,202 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. diff --git a/solr/licenses/slice-NOTICE.txt b/solr/licenses/slice-NOTICE.txt new file mode 100644 index 00000000000..e69de29bb2d diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/Tuple.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/Tuple.java index 1cb7c2204c5..8baa8daa87a 100644 --- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/Tuple.java +++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/Tuple.java @@ -58,15 +58,27 @@ public class Tuple implements Cloneable { } public String getString(Object key) { - return (String)this.fields.get(key); + return this.fields.get(key).toString(); } public Long getLong(Object key) { - return (Long)this.fields.get(key); + Object o = this.fields.get(key); + if(o instanceof Long) { + return (Long)o; + } else { + //Attempt to parse the long + return Long.parseLong(o.toString()); + } } public Double getDouble(Object key) { - return (Double)this.fields.get(key); + Object o = this.fields.get(key); + if(o instanceof Double) { + return (Double)o; + } else { + //Attempt to parse the double + return Double.parseDouble(o.toString()); + } } public List getStrings(Object key) { diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/comp/HashKey.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/comp/HashKey.java new file mode 100644 index 00000000000..200446ef1e0 --- /dev/null +++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/comp/HashKey.java @@ -0,0 +1,80 @@ +package org.apache.solr.client.solrj.io.comp; +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.io.Serializable; + +import org.apache.solr.client.solrj.io.Tuple; + +public class HashKey implements Serializable { + + private static final long serialVersionUID = 1; + + private Object[] parts; + + + public HashKey(String value) { + parts = (Object[])value.split("::"); + } + + public HashKey(Tuple t, String[] keys) { + this.parts = new Object[keys.length]; + for(int i=0; i 0) { + buf.append("::"); + } + buf.append(parts[i].toString()); + } + + return buf.toString(); + } +} \ No newline at end of file diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/RollupStream.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/RollupStream.java new file mode 100644 index 00000000000..a6755b2bcb9 --- /dev/null +++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/RollupStream.java @@ -0,0 +1,135 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + + +package org.apache.solr.client.solrj.io.stream; + +import java.io.IOException; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.ArrayList; + +import org.apache.solr.client.solrj.io.Tuple; +import org.apache.solr.client.solrj.io.comp.HashKey; +import org.apache.solr.client.solrj.io.stream.metrics.Bucket; +import org.apache.solr.client.solrj.io.stream.metrics.Metric; + +public class RollupStream extends TupleStream { + + private static final long serialVersionUID = 1; + + private PushBackStream tupleStream; + private Bucket[] buckets; + private Metric[] metrics; + private HashKey currentKey = new HashKey("-"); + private Metric[] currentMetrics; + private boolean finished = false; + + public RollupStream(TupleStream tupleStream, + Bucket[] buckets, + Metric[] metrics) { + this.tupleStream = new PushBackStream(tupleStream); + this.buckets = buckets; + this.metrics = metrics; + } + + public void setStreamContext(StreamContext context) { + this.tupleStream.setStreamContext(context); + } + + public List children() { + List l = new ArrayList(); + l.add(tupleStream); + return l; + } + + public void open() throws IOException { + tupleStream.open(); + } + + public void close() throws IOException { + tupleStream.close(); + } + + public Tuple read() throws IOException { + + while(true) { + Tuple tuple = tupleStream.read(); + if(tuple.EOF) { + if(!finished) { + Map map = new HashMap(); + for(Metric metric : currentMetrics) { + map.put(metric.getName(), metric.getValue()); + } + + for(int i=0; i doubleMax) { + doubleMax = d; + } + } else { + long l = (long)o; + if(l > longMax) { + longMax = l; + } + } + } + + public Metric newInstance() { + return new MaxMetric(column); + } +} \ No newline at end of file diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/MeanMetric.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/MeanMetric.java new file mode 100644 index 00000000000..8132f6d5451 --- /dev/null +++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/MeanMetric.java @@ -0,0 +1,70 @@ +package org.apache.solr.client.solrj.io.stream.metrics; + +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.io.Serializable; +import java.util.Map; +import java.util.HashMap; + +import org.apache.solr.client.solrj.io.Tuple; + +public class MeanMetric implements Metric, Serializable { + + private static final long serialVersionUID = 1; + + private String column; + private double doubleSum; + private long longSum; + private long count; + + public MeanMetric(String column) { + this.column = column; + } + + public String getName() { + return "avg("+column+")"; + } + + public void update(Tuple tuple) { + ++count; + Object o = tuple.get(column); + if(o instanceof Double) { + Double d = (Double)tuple.get(column); + doubleSum += d.doubleValue(); + } else { + Long l = (Long)tuple.get(column); + longSum += l.doubleValue(); + } + } + + public Metric newInstance() { + return new MeanMetric(column); + } + + public double getValue() { + double dcount = (double)count; + if(longSum == 0) { + double ave = doubleSum/dcount; + return ave; + + } else { + double ave = longSum/dcount; + return ave; + } + } +} \ No newline at end of file diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/Metric.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/Metric.java new file mode 100644 index 00000000000..19f22dfde45 --- /dev/null +++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/Metric.java @@ -0,0 +1,28 @@ +package org.apache.solr.client.solrj.io.stream.metrics; + +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.io.Serializable; +import org.apache.solr.client.solrj.io.Tuple; + +public interface Metric extends Serializable { + public String getName(); + public double getValue(); + public void update(Tuple tuple); + public Metric newInstance(); +} \ No newline at end of file diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/MinMetric.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/MinMetric.java new file mode 100644 index 00000000000..630634d4f76 --- /dev/null +++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/MinMetric.java @@ -0,0 +1,66 @@ +package org.apache.solr.client.solrj.io.stream.metrics; + +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.io.Serializable; + +import org.apache.solr.client.solrj.io.Tuple; + +public class MinMetric implements Metric, Serializable { + + private static final long serialVersionUID = 1; + + private long longMin = Long.MAX_VALUE; + private double doubleMin = Double.MAX_VALUE; + private String column; + + public MinMetric(String column) { + this.column = column; + } + + public String getName() { + return "min("+column+")"; + } + + public double getValue() { + if(longMin == Long.MAX_VALUE) { + return doubleMin; + } else { + return longMin; + } + } + + public void update(Tuple tuple) { + Object o = tuple.get(column); + if(o instanceof Double) { + double d = (double)o; + if(d < doubleMin) { + doubleMin = d; + } + } else { + long l = (long)o; + if(l < longMin) { + longMin = l; + } + } + } + + public Metric newInstance() { + return new MinMetric(column); + } +} \ No newline at end of file diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/SumMetric.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/SumMetric.java new file mode 100644 index 00000000000..916b971f333 --- /dev/null +++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/SumMetric.java @@ -0,0 +1,62 @@ +package org.apache.solr.client.solrj.io.stream.metrics; + +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.io.Serializable; + +import org.apache.solr.client.solrj.io.Tuple; + +public class SumMetric implements Metric, Serializable { + + private static final long serialVersionUID = 1; + + private String column; + private double doubleSum; + private long longSum; + + public SumMetric(String column) { + this.column = column; + } + + public String getName() { + return "sum("+column+")"; + } + + public void update(Tuple tuple) { + Object o = tuple.get(column); + if(o instanceof Double) { + Double d = (Double)o; + doubleSum += d.doubleValue(); + } else { + Long l = (Long)o; + longSum += l.longValue(); + } + } + + public Metric newInstance() { + return new SumMetric(column); + } + + public double getValue() { + if(longSum == 0) { + return doubleSum; + } else { + return (double)longSum; + } + } +} \ No newline at end of file diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/package-info.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/package-info.java new file mode 100644 index 00000000000..a25732e9a2f --- /dev/null +++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/stream/metrics/package-info.java @@ -0,0 +1,24 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + + + +/** + * Metrics package + **/ +package org.apache.solr.client.solrj.io.stream.metrics; + diff --git a/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/StreamingTest.java b/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/StreamingTest.java index 32ba7f96454..4a0408c0c9e 100644 --- a/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/StreamingTest.java +++ b/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/StreamingTest.java @@ -39,6 +39,13 @@ import org.apache.solr.client.solrj.io.stream.ReducerStream; import org.apache.solr.client.solrj.io.stream.TupleStream; import org.apache.solr.client.solrj.io.stream.UniqueStream; import org.apache.solr.client.solrj.io.stream.expr.StreamFactory; +import org.apache.solr.client.solrj.io.stream.metrics.Bucket; +import org.apache.solr.client.solrj.io.stream.metrics.CountMetric; +import org.apache.solr.client.solrj.io.stream.metrics.MaxMetric; +import org.apache.solr.client.solrj.io.stream.metrics.MeanMetric; +import org.apache.solr.client.solrj.io.stream.metrics.Metric; +import org.apache.solr.client.solrj.io.stream.metrics.MinMetric; +import org.apache.solr.client.solrj.io.stream.metrics.SumMetric; import org.apache.solr.cloud.AbstractFullDistribZkTestBase; import org.apache.solr.cloud.AbstractZkTestCase; import org.apache.solr.common.SolrInputDocument; @@ -486,6 +493,241 @@ public class StreamingTest extends AbstractFullDistribZkTestBase { commit(); } + private void testRollupStream() throws Exception { + + indexr(id, "0", "a_s", "hello0", "a_i", "0", "a_f", "1"); + indexr(id, "2", "a_s", "hello0", "a_i", "2", "a_f", "2"); + indexr(id, "3", "a_s", "hello3", "a_i", "3", "a_f", "3"); + indexr(id, "4", "a_s", "hello4", "a_i", "4", "a_f", "4"); + indexr(id, "1", "a_s", "hello0", "a_i", "1", "a_f", "5"); + indexr(id, "5", "a_s", "hello3", "a_i", "10", "a_f", "6"); + indexr(id, "6", "a_s", "hello4", "a_i", "11", "a_f", "7"); + indexr(id, "7", "a_s", "hello3", "a_i", "12", "a_f", "8"); + indexr(id, "8", "a_s", "hello3", "a_i", "13", "a_f", "9"); + indexr(id, "9", "a_s", "hello0", "a_i", "14", "a_f", "10"); + + commit(); + + String zkHost = zkServer.getZkAddress(); + streamFactory.withCollectionZkHost("collection1", zkHost); + + Map paramsA = mapParams("q","*:*","fl","a_s,a_i,a_f","sort", "a_s asc"); + CloudSolrStream stream = new CloudSolrStream(zkHost, "collection1", paramsA); + + Bucket[] buckets = {new Bucket("a_s")}; + + Metric[] metrics = {new SumMetric("a_i"), + new SumMetric("a_f"), + new MinMetric("a_i"), + new MinMetric("a_f"), + new MaxMetric("a_i"), + new MaxMetric("a_f"), + new MeanMetric("a_i"), + new MeanMetric("a_f"), + new CountMetric()}; + + RollupStream rollupStream = new RollupStream(stream, buckets, metrics); + List tuples = getTuples(rollupStream); + + assert(tuples.size() == 3); + + //Test Long and Double Sums + + Tuple tuple = tuples.get(0); + String bucket = tuple.getString("a_s"); + Double sumi = tuple.getDouble("sum(a_i)"); + Double sumf = tuple.getDouble("sum(a_f)"); + Double mini = tuple.getDouble("min(a_i)"); + Double minf = tuple.getDouble("min(a_f)"); + Double maxi = tuple.getDouble("max(a_i)"); + Double maxf = tuple.getDouble("max(a_f)"); + Double avgi = tuple.getDouble("avg(a_i)"); + Double avgf = tuple.getDouble("avg(a_f)"); + Double count = tuple.getDouble("count(*)"); + + + assertTrue(bucket.equals("hello0")); + assertTrue(sumi.doubleValue() == 17.0D); + assertTrue(sumf.doubleValue() == 18.0D); + assertTrue(mini.doubleValue() == 0.0D); + assertTrue(minf.doubleValue() == 1.0D); + assertTrue(maxi.doubleValue() == 14.0D); + assertTrue(maxf.doubleValue() == 10.0D); + assertTrue(avgi.doubleValue() == 4.25D); + assertTrue(avgf.doubleValue() == 4.5D); + assertTrue(count.doubleValue() == 4); + + + tuple = tuples.get(1); + bucket = tuple.getString("a_s"); + sumi = tuple.getDouble("sum(a_i)"); + sumf = tuple.getDouble("sum(a_f)"); + mini = tuple.getDouble("min(a_i)"); + minf = tuple.getDouble("min(a_f)"); + maxi = tuple.getDouble("max(a_i)"); + maxf = tuple.getDouble("max(a_f)"); + avgi = tuple.getDouble("avg(a_i)"); + avgf = tuple.getDouble("avg(a_f)"); + count = tuple.getDouble("count(*)"); + + assertTrue(bucket.equals("hello3")); + assertTrue(sumi.doubleValue() == 38.0D); + assertTrue(sumf.doubleValue() == 26.0D); + assertTrue(mini.doubleValue() == 3.0D); + assertTrue(minf.doubleValue() == 3.0D); + assertTrue(maxi.doubleValue() == 13.0D); + assertTrue(maxf.doubleValue() == 9.0D); + assertTrue(avgi.doubleValue() == 9.5D); + assertTrue(avgf.doubleValue() == 6.5D); + assertTrue(count.doubleValue() == 4); + + + tuple = tuples.get(2); + bucket = tuple.getString("a_s"); + sumi = tuple.getDouble("sum(a_i)"); + sumf = tuple.getDouble("sum(a_f)"); + mini = tuple.getDouble("min(a_i)"); + minf = tuple.getDouble("min(a_f)"); + maxi = tuple.getDouble("max(a_i)"); + maxf = tuple.getDouble("max(a_f)"); + avgi = tuple.getDouble("avg(a_i)"); + avgf = tuple.getDouble("avg(a_f)"); + count = tuple.getDouble("count(*)"); + + assertTrue(bucket.equals("hello4")); + assertTrue(sumi.longValue() == 15); + assertTrue(sumf.doubleValue() == 11.0D); + assertTrue(mini.doubleValue() == 4.0D); + assertTrue(minf.doubleValue() == 4.0D); + assertTrue(maxi.doubleValue() == 11.0D); + assertTrue(maxf.doubleValue() == 7.0D); + assertTrue(avgi.doubleValue() == 7.5D); + assertTrue(avgf.doubleValue() == 5.5D); + assertTrue(count.doubleValue() == 2); + + + + del("*:*"); + commit(); + } + + + + + private void testParallelRollupStream() throws Exception { + + indexr(id, "0", "a_s", "hello0", "a_i", "0", "a_f", "1"); + indexr(id, "2", "a_s", "hello0", "a_i", "2", "a_f", "2"); + indexr(id, "3", "a_s", "hello3", "a_i", "3", "a_f", "3"); + indexr(id, "4", "a_s", "hello4", "a_i", "4", "a_f", "4"); + indexr(id, "1", "a_s", "hello0", "a_i", "1", "a_f", "5"); + indexr(id, "5", "a_s", "hello3", "a_i", "10", "a_f", "6"); + indexr(id, "6", "a_s", "hello4", "a_i", "11", "a_f", "7"); + indexr(id, "7", "a_s", "hello3", "a_i", "12", "a_f", "8"); + indexr(id, "8", "a_s", "hello3", "a_i", "13", "a_f", "9"); + indexr(id, "9", "a_s", "hello0", "a_i", "14", "a_f", "10"); + + commit(); + + String zkHost = zkServer.getZkAddress(); + streamFactory.withCollectionZkHost("collection1", zkHost); + + Map paramsA = mapParams("q","*:*","fl","a_s,a_i,a_f","sort", "a_s asc", "partitionKeys", "a_s"); + CloudSolrStream stream = new CloudSolrStream(zkHost, "collection1", paramsA); + + Bucket[] buckets = {new Bucket("a_s")}; + + Metric[] metrics = {new SumMetric("a_i"), + new SumMetric("a_f"), + new MinMetric("a_i"), + new MinMetric("a_f"), + new MaxMetric("a_i"), + new MaxMetric("a_f"), + new MeanMetric("a_i"), + new MeanMetric("a_f"), + new CountMetric()}; + + RollupStream rollupStream = new RollupStream(stream, buckets, metrics); + ParallelStream parallelStream = new ParallelStream(zkHost, "collection1", rollupStream, 2, new FieldComparator("a_s", ComparatorOrder.ASCENDING)); + List tuples = getTuples(parallelStream); + + assert(tuples.size() == 3); + + //Test Long and Double Sums + + Tuple tuple = tuples.get(0); + String bucket = tuple.getString("a_s"); + Double sumi = tuple.getDouble("sum(a_i)"); + Double sumf = tuple.getDouble("sum(a_f)"); + Double mini = tuple.getDouble("min(a_i)"); + Double minf = tuple.getDouble("min(a_f)"); + Double maxi = tuple.getDouble("max(a_i)"); + Double maxf = tuple.getDouble("max(a_f)"); + Double avgi = tuple.getDouble("avg(a_i)"); + Double avgf = tuple.getDouble("avg(a_f)"); + Double count = tuple.getDouble("count(*)"); + + assertTrue(bucket.equals("hello0")); + assertTrue(sumi.doubleValue() == 17.0D); + assertTrue(sumf.doubleValue() == 18.0D); + assertTrue(mini.doubleValue() == 0.0D); + assertTrue(minf.doubleValue() == 1.0D); + assertTrue(maxi.doubleValue() == 14.0D); + assertTrue(maxf.doubleValue() == 10.0D); + assertTrue(avgi.doubleValue() == 4.25D); + assertTrue(avgf.doubleValue() == 4.5D); + assertTrue(count.doubleValue() == 4); + + tuple = tuples.get(1); + bucket = tuple.getString("a_s"); + sumi = tuple.getDouble("sum(a_i)"); + sumf = tuple.getDouble("sum(a_f)"); + mini = tuple.getDouble("min(a_i)"); + minf = tuple.getDouble("min(a_f)"); + maxi = tuple.getDouble("max(a_i)"); + maxf = tuple.getDouble("max(a_f)"); + avgi = tuple.getDouble("avg(a_i)"); + avgf = tuple.getDouble("avg(a_f)"); + count = tuple.getDouble("count(*)"); + + assertTrue(bucket.equals("hello3")); + assertTrue(sumi.doubleValue() == 38.0D); + assertTrue(sumf.doubleValue() == 26.0D); + assertTrue(mini.doubleValue() == 3.0D); + assertTrue(minf.doubleValue() == 3.0D); + assertTrue(maxi.doubleValue() == 13.0D); + assertTrue(maxf.doubleValue() == 9.0D); + assertTrue(avgi.doubleValue() == 9.5D); + assertTrue(avgf.doubleValue() == 6.5D); + assertTrue(count.doubleValue() == 4); + + tuple = tuples.get(2); + bucket = tuple.getString("a_s"); + sumi = tuple.getDouble("sum(a_i)"); + sumf = tuple.getDouble("sum(a_f)"); + mini = tuple.getDouble("min(a_i)"); + minf = tuple.getDouble("min(a_f)"); + maxi = tuple.getDouble("max(a_i)"); + maxf = tuple.getDouble("max(a_f)"); + avgi = tuple.getDouble("avg(a_i)"); + avgf = tuple.getDouble("avg(a_f)"); + count = tuple.getDouble("count(*)"); + + assertTrue(bucket.equals("hello4")); + assertTrue(sumi.longValue() == 15); + assertTrue(sumf.doubleValue() == 11.0D); + assertTrue(mini.doubleValue() == 4.0D); + assertTrue(minf.doubleValue() == 4.0D); + assertTrue(maxi.doubleValue() == 11.0D); + assertTrue(maxf.doubleValue() == 7.0D); + assertTrue(avgi.doubleValue() == 7.5D); + assertTrue(avgf.doubleValue() == 5.5D); + assertTrue(count.doubleValue() == 2); + + del("*:*"); + commit(); + } + private void testZeroParallelReducerStream() throws Exception { indexr(id, "0", "a_s", "hello0", "a_i", "0", "a_f", "1"); @@ -782,8 +1024,8 @@ public class StreamingTest extends AbstractFullDistribZkTestBase { stream = new CloudSolrStream(zkHost, "collection1", params); tuples = getTuples(stream); - assert(tuples.size() == 5); - assertOrder(tuples, 0,2,1,3,4); + assert (tuples.size() == 5); + assertOrder(tuples, 0, 2, 1, 3, 4); del("*:*"); commit(); @@ -796,11 +1038,13 @@ public class StreamingTest extends AbstractFullDistribZkTestBase { testRankStream(); testMergeStream(); testReducerStream(); + testRollupStream(); testZeroReducerStream(); testParallelEOF(); testParallelUniqueStream(); testParallelRankStream(); testParallelMergeStream(); + testParallelRollupStream(); testParallelReducerStream(); testZeroParallelReducerStream(); }