List of usage examples for org.apache.solr.client.solrj.impl CloudSolrClient getById
public SolrDocument getById(String collection, String id) throws SolrServerException, IOException
From source file:fr.jetoile.hadoopunit.component.SolrCloudBootstrapTest.java
License:Apache License
@Test public void solrCloudShouldStart() throws IOException, SolrServerException, KeeperException, InterruptedException, NotFoundServiceException { String collectionName = configuration.getString(SolrCloudBootstrap.SOLR_COLLECTION_NAME); // String zkHostString = configuration.getString(Config.ZOOKEEPER_HOST_KEY) + ":" + configuration.getInt(Config.ZOOKEEPER_PORT_KEY); // CloudSolrClient client = new CloudSolrClient(zkHostString); CloudSolrClient client = ((SolrCloudBootstrap) HadoopBootstrap.INSTANCE.getService(Component.SOLRCLOUD)) .getClient();/*from w w w . ja v a2 s . co m*/ for (int i = 0; i < 1000; ++i) { SolrInputDocument doc = new SolrInputDocument(); doc.addField("cat", "book"); doc.addField("id", "book-" + i); doc.addField("name", "The Legend of the Hobbit part " + i); client.add(collectionName, doc); if (i % 100 == 0) client.commit(collectionName); // periodically flush } client.commit("collection1"); SolrDocument collection1 = client.getById(collectionName, "book-1"); assertNotNull(collection1); assertThat(collection1.getFieldValue("name")).isEqualTo("The Legend of the Hobbit part 1"); client.close(); }
From source file:fr.jetoile.hadoopunit.integrationtest.IntegrationBootstrapTest.java
License:Apache License
@Test public void solrCloudShouldStart() throws IOException, SolrServerException, KeeperException, InterruptedException { String collectionName = configuration.getString(SolrCloudBootstrap.SOLR_COLLECTION_NAME); String zkHostString = configuration.getString(Config.ZOOKEEPER_HOST_KEY) + ":" + configuration.getInt(Config.ZOOKEEPER_PORT_KEY); CloudSolrClient client = new CloudSolrClient(zkHostString); for (int i = 0; i < 1000; ++i) { SolrInputDocument doc = new SolrInputDocument(); doc.addField("cat", "book"); doc.addField("id", "book-" + i); doc.addField("name", "The Legend of the Hobbit part " + i); client.add(collectionName, doc); if (i % 100 == 0) client.commit(collectionName); // periodically flush }// ww w . j av a 2 s . c o m client.commit("collection1"); SolrDocument collection1 = client.getById(collectionName, "book-1"); assertNotNull(collection1); assertThat(collection1.getFieldValue("name")).isEqualTo("The Legend of the Hobbit part 1"); client.close(); }
From source file:fr.jetoile.hadoopunit.integrationtest.SparkSolrIntegrationTest.java
License:Apache License
@Test public void spark_should_read_parquet_file_and_index_into_solr() throws IOException, SolrServerException { //given// ww w .ja va2 s.com SparkConf conf = new SparkConf().setMaster("local[*]").setAppName("test"); JavaSparkContext context = new JavaSparkContext(conf); //read hive-site from classpath HiveContext hiveContext = new HiveContext(context.sc()); DataFrame sql = hiveContext.sql("SELECT * FROM default.test"); sql.write().parquet("hdfs://localhost:" + configuration.getInt(Config.HDFS_NAMENODE_PORT_KEY) + "/khanh/test_parquet/file.parquet"); FileSystem fileSystem = HdfsUtils.INSTANCE.getFileSystem(); assertThat(fileSystem.exists(new Path("hdfs://localhost:" + configuration.getInt(Config.HDFS_NAMENODE_PORT_KEY) + "/khanh/test_parquet/file.parquet"))) .isTrue(); context.close(); //when context = new JavaSparkContext(conf); SQLContext sqlContext = new SQLContext(context); DataFrame file = sqlContext.read().parquet("hdfs://localhost:" + configuration.getInt(Config.HDFS_NAMENODE_PORT_KEY) + "/khanh/test_parquet/file.parquet"); DataFrame select = file.select("id", "value"); JavaRDD<SolrInputDocument> solrInputDocument = select.toJavaRDD().map(r -> { SolrInputDocument solr = new SolrInputDocument(); solr.setField("id", r.getInt(0)); solr.setField("value_s", r.getString(1)); return solr; }); String collectionName = configuration.getString(SolrCloudBootstrap.SOLR_COLLECTION_NAME); String zkHostString = configuration.getString(Config.ZOOKEEPER_HOST_KEY) + ":" + configuration.getInt(Config.ZOOKEEPER_PORT_KEY); SolrSupport.indexDocs(zkHostString, collectionName, 1000, solrInputDocument); //then CloudSolrClient client = new CloudSolrClient(zkHostString); SolrDocument collection1 = client.getById(collectionName, "1"); assertNotNull(collection1); assertThat(collection1.getFieldValue("value_s")).isEqualTo("value1"); client.close(); context.close(); }
From source file:fr.jetoile.hadoopunit.sample.ParquetToSolrJobIntegrationTest.java
License:Apache License
@Test public void spark_should_read_parquet_file_and_index_into_solr() throws IOException, SolrServerException { //given//from ww w.j a va 2 s.c o m SparkSession sqlContext = SparkSession.builder().appName("test").master("local[*]").getOrCreate(); Dataset<Row> df = sqlContext.read().format("com.databricks.spark.csv").option("header", "true") // Use first line of all files as header .option("inferSchema", "true") // Automatically infer data types .load("hdfs://localhost:" + configuration.getInt(HadoopUnitClientConfig.HDFS_NAMENODE_PORT_KEY) + "/khanh/test/test.csv"); df.write().parquet("hdfs://localhost:" + configuration.getInt(HadoopUnitClientConfig.HDFS_NAMENODE_PORT_KEY) + "/khanh/test_parquet/file.parquet"); FileSystem fileSystem = HdfsUtils.INSTANCE.getFileSystem(); assertThat(fileSystem.exists( new Path("hdfs://localhost:" + configuration.getInt(HadoopUnitClientConfig.HDFS_NAMENODE_PORT_KEY) + "/khanh/test_parquet/file.parquet"))).isTrue(); sqlContext.close(); //when sqlContext = SparkSession.builder().appName("test").master("local[*]").getOrCreate(); ParquetToSolrJob parquetToSolrJob = new ParquetToSolrJob(sqlContext); parquetToSolrJob.run(); String zkHostString = configuration.getString("zookeeper.host") + ":" + configuration.getInt("zookeeper.port"); //then CloudSolrClient client = new CloudSolrClient(zkHostString); SolrDocument collection1 = client.getById("collection1", "1"); assertNotNull(collection1); assertThat(collection1.getFieldValue("value_s")).isEqualTo("value1"); client.close(); sqlContext.close(); }
From source file:fr.jetoile.hadoopunit.sample.ParquetToSolrJobTest.java
License:Apache License
@Test public void spark_should_read_parquet_file_and_index_into_solr() throws IOException, SolrServerException { //given/*from w w w .ja v a 2s . co m*/ SparkConf conf = new SparkConf().setMaster("local[*]").setAppName("test"); JavaSparkContext context = new JavaSparkContext(conf); //read hive-site from classpath HiveContext hiveContext = new HiveContext(context.sc()); DataFrame sql = hiveContext.sql("SELECT * FROM default.test"); sql.write().parquet("hdfs://localhost:" + configuration.getInt(HadoopUnitConfig.HDFS_NAMENODE_PORT_KEY) + "/khanh/test_parquet/file.parquet"); FileSystem fileSystem = HdfsUtils.INSTANCE.getFileSystem(); assertThat(fileSystem .exists(new Path("hdfs://localhost:" + configuration.getInt(HadoopUnitConfig.HDFS_NAMENODE_PORT_KEY) + "/khanh/test_parquet/file.parquet"))).isTrue(); context.close(); //when context = new JavaSparkContext(conf); ParquetToSolrJob parquetToSolrJob = new ParquetToSolrJob(context); parquetToSolrJob.run(); String zkHostString = configuration.getString(HadoopUnitConfig.ZOOKEEPER_HOST_KEY) + ":" + configuration.getInt(HadoopUnitConfig.ZOOKEEPER_PORT_KEY); //then CloudSolrClient client = new CloudSolrClient(zkHostString); SolrDocument collection1 = client.getById("collection1", "1"); assertNotNull(collection1); assertThat(collection1.getFieldValue("value_s")).isEqualTo("value1"); client.close(); context.close(); }