@Test
public void testEsSchemaRDD1WriteWithMappingExclude() throws Exception {
DataFrame dataFrame = artistsAsDataFrame();
String target = "sparksql-test/scala-basic-write-exclude-mapping";
JavaEsSparkSQL.saveToEs(dataFrame, target, ImmutableMap.of(ES_MAPPING_EXCLUDE, "url"));
assertTrue(RestUtils.exists(target));
assertThat(RestUtils.get(target + "/_search?"), not(containsString("url")));
}
@Test
public void testEsdataFrame1Write() throws Exception {
DataFrame dataFrame = artistsAsDataFrame();
String target = "sparksql-test/scala-basic-write";
JavaEsSparkSQL.saveToEs(dataFrame, target);
assertTrue(RestUtils.exists(target));
assertThat(RestUtils.get(target + "/_search?"), containsString("345"));
}
@Test
public void testEsdataFrame1WriteWithId() throws Exception {
DataFrame dataFrame = artistsAsDataFrame();
String target = "sparksql-test/scala-basic-write-id-mapping";
JavaEsSparkSQL.saveToEs(dataFrame, target, ImmutableMap.of(ES_MAPPING_ID, "id"));
assertTrue(RestUtils.exists(target));
assertThat(RestUtils.get(target + "/_search?"), containsString("345"));
assertThat(RestUtils.exists(target + "/1"), is(true));
}
public static void main(String args[]) {
SparkConf conf = new SparkConf().setAppName("esh-spark").setMaster("local[4]");
conf.set("es.index.auto.create", "true");
JavaSparkContext context = new JavaSparkContext(conf);
JavaRDD<String> textFile = context.textFile("hdfs://localhost:9000/ch07/crimes_dataset.csv");
JavaRDD<Crime> dataSplits =
textFile.map(
line -> {
CSVParser parser = CSVParser.parse(line, CSVFormat.RFC4180);
Crime c = new Crime();
CSVRecord record = parser.getRecords().get(0);
c.setId(record.get(0));
c.setCaseNumber(record.get(1));
c.setEventDate(record.get(2));
c.setBlock(record.get(3));
c.setIucr(record.get(4));
c.setPrimaryType(record.get(5));
c.setDescription(record.get(6));
c.setLocation(record.get(7));
c.setArrest(Boolean.parseBoolean(record.get(8)));
c.setDomestic(Boolean.parseBoolean(record.get(9)));
String lat = record.get(10);
String lon = record.get(11);
Map<String, Double> geoLocation = new HashMap<>();
geoLocation.put("lat", StringUtils.isEmpty(lat) ? null : Double.parseDouble(lat));
geoLocation.put("lon", StringUtils.isEmpty(lon) ? null : Double.parseDouble(lon));
c.setGeoLocation(geoLocation);
return c;
});
SQLContext sqlContext = new SQLContext(context);
DataFrame df = sqlContext.createDataFrame(dataSplits, Crime.class);
JavaEsSparkSQL.saveToEs(df, "esh_sparksql/crimes_reflection");
}
