use of org.apache.solr.client.solrj.io.SolrClientCache in project lucene-solr by apache.
the class StreamExpressionTest method testSortStream.
@Test
public void testSortStream() throws Exception {
new UpdateRequest().add(id, "0", "a_s", "hello0", "a_i", "0", "a_f", "0").add(id, "2", "a_s", "hello2", "a_i", "2", "a_f", "0").add(id, "3", "a_s", "hello3", "a_i", "3", "a_f", "3").add(id, "4", "a_s", "hello4", "a_i", "4", "a_f", "4").add(id, "1", "a_s", "hello1", "a_i", "1", "a_f", "1").add(id, "5", "a_s", "hello1", "a_i", "1", "a_f", "2").commit(cluster.getSolrClient(), COLLECTIONORALIAS);
StreamExpression expression;
TupleStream stream;
List<Tuple> tuples;
StreamContext streamContext = new StreamContext();
SolrClientCache solrClientCache = new SolrClientCache();
streamContext.setSolrClientCache(solrClientCache);
try {
StreamFactory factory = new StreamFactory().withCollectionZkHost(COLLECTIONORALIAS, cluster.getZkServer().getZkAddress()).withFunctionName("search", CloudSolrStream.class).withFunctionName("sort", SortStream.class);
// Basic test
stream = factory.constructStream("sort(search(" + COLLECTIONORALIAS + ", q=*:*, fl=\"id,a_s,a_i,a_f\", sort=\"a_f asc\"), by=\"a_i asc\")");
stream.setStreamContext(streamContext);
tuples = getTuples(stream);
assert (tuples.size() == 6);
assertOrder(tuples, 0, 1, 5, 2, 3, 4);
// Basic test desc
stream = factory.constructStream("sort(search(" + COLLECTIONORALIAS + ", q=*:*, fl=\"id,a_s,a_i,a_f\", sort=\"a_f asc\"), by=\"a_i desc\")");
stream.setStreamContext(streamContext);
tuples = getTuples(stream);
assert (tuples.size() == 6);
assertOrder(tuples, 4, 3, 2, 1, 5, 0);
// Basic w/multi comp
stream = factory.constructStream("sort(search(" + COLLECTIONORALIAS + ", q=*:*, fl=\"id,a_s,a_i,a_f\", sort=\"a_f asc\"), by=\"a_i asc, a_f desc\")");
stream.setStreamContext(streamContext);
tuples = getTuples(stream);
assert (tuples.size() == 6);
assertOrder(tuples, 0, 5, 1, 2, 3, 4);
} finally {
solrClientCache.close();
}
}
use of org.apache.solr.client.solrj.io.SolrClientCache in project lucene-solr by apache.
the class StreamExpressionTest method testParallelIntersectStream.
@Test
public void testParallelIntersectStream() throws Exception {
new UpdateRequest().add(id, "0", "a_s", "setA", "a_i", "0").add(id, "2", "a_s", "setA", "a_i", "1").add(id, "3", "a_s", "setA", "a_i", "2").add(id, "4", "a_s", "setA", "a_i", "3").add(id, "5", "a_s", "setB", "a_i", "2").add(id, "6", "a_s", "setB", "a_i", "3").add(id, "7", "a_s", "setAB", "a_i", "0").add(id, "8", "a_s", "setAB", "a_i", "6").commit(cluster.getSolrClient(), COLLECTIONORALIAS);
StreamFactory streamFactory = new StreamFactory().withCollectionZkHost("collection1", cluster.getZkServer().getZkAddress()).withFunctionName("search", CloudSolrStream.class).withFunctionName("intersect", IntersectStream.class).withFunctionName("parallel", ParallelStream.class);
// basic
StreamContext streamContext = new StreamContext();
SolrClientCache solrClientCache = new SolrClientCache();
streamContext.setSolrClientCache(solrClientCache);
try {
String zkHost = cluster.getZkServer().getZkAddress();
final TupleStream stream = streamFactory.constructStream("parallel(" + "collection1, " + "intersect(" + "search(collection1, q=a_s:(setA || setAB), fl=\"id,a_s,a_i\", sort=\"a_i asc, a_s asc\", partitionKeys=\"a_i\")," + "search(collection1, q=a_s:(setB || setAB), fl=\"id,a_s,a_i\", sort=\"a_i asc\", partitionKeys=\"a_i\")," + "on=\"a_i\")," + "workers=\"2\", zkHost=\"" + zkHost + "\", sort=\"a_i asc\")");
stream.setStreamContext(streamContext);
final List<Tuple> tuples = getTuples(stream);
assert (tuples.size() == 5);
assertOrder(tuples, 0, 7, 3, 4, 8);
} finally {
solrClientCache.close();
}
}
use of org.apache.solr.client.solrj.io.SolrClientCache in project lucene-solr by apache.
the class StreamExpressionTest method testExecutorStream.
@Test
public void testExecutorStream() throws Exception {
CollectionAdminRequest.createCollection("workQueue", "conf", 2, 1).process(cluster.getSolrClient());
AbstractDistribZkTestBase.waitForRecoveriesToFinish("workQueue", cluster.getSolrClient().getZkStateReader(), false, true, TIMEOUT);
CollectionAdminRequest.createCollection("mainCorpus", "conf", 2, 1).process(cluster.getSolrClient());
AbstractDistribZkTestBase.waitForRecoveriesToFinish("mainCorpus", cluster.getSolrClient().getZkStateReader(), false, true, TIMEOUT);
CollectionAdminRequest.createCollection("destination", "conf", 2, 1).process(cluster.getSolrClient());
AbstractDistribZkTestBase.waitForRecoveriesToFinish("destination", cluster.getSolrClient().getZkStateReader(), false, true, TIMEOUT);
UpdateRequest workRequest = new UpdateRequest();
UpdateRequest dataRequest = new UpdateRequest();
for (int i = 0; i < 500; i++) {
workRequest.add(id, String.valueOf(i), "expr_s", "update(destination, batchSize=50, search(mainCorpus, q=id:" + i + ", rows=1, sort=\"id asc\", fl=\"id, body_t, field_i\"))");
dataRequest.add(id, String.valueOf(i), "body_t", "hello world " + i, "field_i", Integer.toString(i));
}
workRequest.commit(cluster.getSolrClient(), "workQueue");
dataRequest.commit(cluster.getSolrClient(), "mainCorpus");
String url = cluster.getJettySolrRunners().get(0).getBaseUrl().toString() + "/destination";
TupleStream executorStream;
ModifiableSolrParams paramsLoc;
StreamFactory factory = new StreamFactory().withCollectionZkHost("workQueue", cluster.getZkServer().getZkAddress()).withCollectionZkHost("mainCorpus", cluster.getZkServer().getZkAddress()).withCollectionZkHost("destination", cluster.getZkServer().getZkAddress()).withFunctionName("search", CloudSolrStream.class).withFunctionName("executor", ExecutorStream.class).withFunctionName("update", UpdateStream.class);
String executorExpression = "executor(threads=3, search(workQueue, q=\"*:*\", fl=\"id, expr_s\", rows=1000, sort=\"id desc\"))";
executorStream = factory.constructStream(executorExpression);
StreamContext context = new StreamContext();
SolrClientCache clientCache = new SolrClientCache();
context.setSolrClientCache(clientCache);
executorStream.setStreamContext(context);
getTuples(executorStream);
//Destination collection should now contain all the records in the main corpus.
cluster.getSolrClient().commit("destination");
paramsLoc = new ModifiableSolrParams();
paramsLoc.set("expr", "search(destination, q=\"*:*\", fl=\"id, body_t, field_i\", rows=1000, sort=\"field_i asc\")");
paramsLoc.set("qt", "/stream");
SolrStream solrStream = new SolrStream(url, paramsLoc);
List<Tuple> tuples = getTuples(solrStream);
assertTrue(tuples.size() == 500);
for (int i = 0; i < 500; i++) {
Tuple tuple = tuples.get(i);
long ivalue = tuple.getLong("field_i");
String body = tuple.getString("body_t");
assertTrue(ivalue == i);
assertTrue(body.equals("hello world " + i));
}
solrStream.close();
clientCache.close();
CollectionAdminRequest.deleteCollection("workQueue").process(cluster.getSolrClient());
CollectionAdminRequest.deleteCollection("mainCorpus").process(cluster.getSolrClient());
CollectionAdminRequest.deleteCollection("destination").process(cluster.getSolrClient());
}
use of org.apache.solr.client.solrj.io.SolrClientCache in project lucene-solr by apache.
the class FeaturesSelectionStream method open.
/**
* Opens the CloudSolrStream
*
***/
public void open() throws IOException {
if (cache == null) {
isCloseCache = true;
cache = new SolrClientCache();
} else {
isCloseCache = false;
}
this.cloudSolrClient = this.cache.getCloudSolrClient(zkHost);
this.executorService = ExecutorUtil.newMDCAwareCachedThreadPool(new SolrjNamedThreadFactory("FeaturesSelectionStream"));
}
use of org.apache.solr.client.solrj.io.SolrClientCache in project lucene-solr by apache.
the class StreamingTest method testMergeStream.
@Test
public void testMergeStream() throws Exception {
new UpdateRequest().add(id, "0", "a_s", "hello0", "a_i", "0", "a_f", "0").add(id, "2", "a_s", "hello2", "a_i", "2", "a_f", "0").add(id, "3", "a_s", "hello3", "a_i", "3", "a_f", "3").add(id, "4", "a_s", "hello4", "a_i", "4", "a_f", "4").add(id, "1", "a_s", "hello1", "a_i", "1", "a_f", "1").commit(cluster.getSolrClient(), COLLECTIONORALIAS);
StreamContext streamContext = new StreamContext();
SolrClientCache solrClientCache = new SolrClientCache();
streamContext.setSolrClientCache(solrClientCache);
try {
//Test ascending
SolrParams sParamsA = mapParams("q", "id:(4 1)", "fl", "id,a_s,a_i", "sort", "a_i asc");
CloudSolrStream streamA = new CloudSolrStream(zkHost, COLLECTIONORALIAS, sParamsA);
SolrParams sParamsB = mapParams("q", "id:(0 2 3)", "fl", "id,a_s,a_i", "sort", "a_i asc");
CloudSolrStream streamB = new CloudSolrStream(zkHost, COLLECTIONORALIAS, sParamsB);
MergeStream mstream = new MergeStream(streamA, streamB, new FieldComparator("a_i", ComparatorOrder.ASCENDING));
mstream.setStreamContext(streamContext);
List<Tuple> tuples = getTuples(mstream);
assertEquals(5, tuples.size());
assertOrder(tuples, 0, 1, 2, 3, 4);
//Test descending
sParamsA = mapParams("q", "id:(4 1)", "fl", "id,a_s,a_i", "sort", "a_i desc");
streamA = new CloudSolrStream(zkHost, COLLECTIONORALIAS, sParamsA);
sParamsB = mapParams("q", "id:(0 2 3)", "fl", "id,a_s,a_i", "sort", "a_i desc");
streamB = new CloudSolrStream(zkHost, COLLECTIONORALIAS, sParamsB);
mstream = new MergeStream(streamA, streamB, new FieldComparator("a_i", ComparatorOrder.DESCENDING));
mstream.setStreamContext(streamContext);
tuples = getTuples(mstream);
assertEquals(5, tuples.size());
assertOrder(tuples, 4, 3, 2, 1, 0);
//Test compound sort
sParamsA = mapParams("q", "id:(2 4 1)", "fl", "id,a_s,a_i,a_f", "sort", "a_f asc,a_i asc");
streamA = new CloudSolrStream(zkHost, COLLECTIONORALIAS, sParamsA);
sParamsB = mapParams("q", "id:(0 3)", "fl", "id,a_s,a_i,a_f", "sort", "a_f asc,a_i asc");
streamB = new CloudSolrStream(zkHost, COLLECTIONORALIAS, sParamsB);
mstream = new MergeStream(streamA, streamB, new MultipleFieldComparator(new FieldComparator("a_f", ComparatorOrder.ASCENDING), new FieldComparator("a_i", ComparatorOrder.ASCENDING)));
mstream.setStreamContext(streamContext);
tuples = getTuples(mstream);
assertEquals(5, tuples.size());
assertOrder(tuples, 0, 2, 1, 3, 4);
sParamsA = mapParams("q", "id:(2 4 1)", "fl", "id,a_s,a_i,a_f", "sort", "a_f asc,a_i desc");
streamA = new CloudSolrStream(zkHost, COLLECTIONORALIAS, sParamsA);
sParamsB = mapParams("q", "id:(0 3)", "fl", "id,a_s,a_i,a_f", "sort", "a_f asc,a_i desc");
streamB = new CloudSolrStream(zkHost, COLLECTIONORALIAS, sParamsB);
mstream = new MergeStream(streamA, streamB, new MultipleFieldComparator(new FieldComparator("a_f", ComparatorOrder.ASCENDING), new FieldComparator("a_i", ComparatorOrder.DESCENDING)));
mstream.setStreamContext(streamContext);
tuples = getTuples(mstream);
assertEquals(5, tuples.size());
assertOrder(tuples, 2, 0, 1, 3, 4);
} finally {
solrClientCache.close();
}
}
Aggregations