本文整理汇总了Java中org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe类的典型用法代码示例。如果您正苦于以下问题:Java ParquetHiveSerDe类的具体用法?Java ParquetHiveSerDe怎么用?Java ParquetHiveSerDe使用的例子?那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。
ParquetHiveSerDe类属于org.apache.hadoop.hive.ql.io.parquet.serde包,在下文中一共展示了ParquetHiveSerDe类的9个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于我们的系统推荐出更棒的Java代码示例。
示例1: testParquet
import org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe; //导入依赖的package包/类
@Test
public void testParquet()
throws Exception
{
List<TestColumn> testColumns = getTestColumnsSupportedByParquet();
HiveOutputFormat<?, ?> outputFormat = new MapredParquetOutputFormat();
InputFormat<?, ?> inputFormat = new MapredParquetInputFormat();
@SuppressWarnings("deprecation")
SerDe serde = new ParquetHiveSerDe();
File file = File.createTempFile("presto_test", "parquet");
file.delete();
try {
FileSplit split = createTestFile(file.getAbsolutePath(), outputFormat, serde, null, testColumns, NUM_ROWS);
HiveRecordCursorProvider cursorProvider = new ParquetRecordCursorProvider(false);
testCursorProvider(cursorProvider, split, inputFormat, serde, testColumns, NUM_ROWS);
}
finally {
//noinspection ResultOfMethodCallIgnored
file.delete();
}
}
开发者ID:y-lan,项目名称:presto,代码行数:23,代码来源:TestHiveFileFormats.java
示例2: testParquetPageSource
import org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe; //导入依赖的package包/类
@Test(enabled = false)
public void testParquetPageSource()
throws Exception
{
List<TestColumn> testColumns = getTestColumnsSupportedByParquet();
testColumns = testColumns.stream()
.filter(column -> column.getObjectInspector().getCategory() == Category.PRIMITIVE)
.collect(toList());
HiveOutputFormat<?, ?> outputFormat = new MapredParquetOutputFormat();
InputFormat<?, ?> inputFormat = new MapredParquetInputFormat();
@SuppressWarnings("deprecation")
SerDe serde = new ParquetHiveSerDe();
File file = File.createTempFile("presto_test", "parquet");
file.delete();
try {
FileSplit split = createTestFile(file.getAbsolutePath(), outputFormat, serde, null, testColumns, NUM_ROWS);
TestingConnectorSession session = new TestingConnectorSession(
new HiveSessionProperties(new HiveClientConfig().setParquetOptimizedReaderEnabled(true)).getSessionProperties());
testPageSourceFactory(new ParquetPageSourceFactory(TYPE_MANAGER, false), split, inputFormat, serde, testColumns, session);
}
finally {
//noinspection ResultOfMethodCallIgnored
file.delete();
}
}
开发者ID:y-lan,项目名称:presto,代码行数:27,代码来源:TestHiveFileFormats.java
示例3: testParquetUseColumnNames
import org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe; //导入依赖的package包/类
@Test
public void testParquetUseColumnNames()
throws Exception
{
List<TestColumn> testColumns = getTestColumnsSupportedByParquet();
HiveOutputFormat<?, ?> outputFormat = new MapredParquetOutputFormat();
InputFormat<?, ?> inputFormat = new MapredParquetInputFormat();
@SuppressWarnings("deprecation")
SerDe serde = new ParquetHiveSerDe();
File file = File.createTempFile("presto_test", "parquet");
file.delete();
try {
FileSplit split = createTestFile(file.getAbsolutePath(), outputFormat, serde, null, testColumns, NUM_ROWS);
// Reverse the order of the columns to test access by name, not by index
Collections.reverse(testColumns);
HiveRecordCursorProvider cursorProvider = new ParquetRecordCursorProvider(true);
testCursorProvider(cursorProvider, split, inputFormat, serde, testColumns, NUM_ROWS);
}
finally {
//noinspection ResultOfMethodCallIgnored
file.delete();
}
}
开发者ID:y-lan,项目名称:presto,代码行数:25,代码来源:TestHiveFileFormats.java
示例4: deserializeAndSerializeLazySimple
import org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe; //导入依赖的package包/类
private void deserializeAndSerializeLazySimple(final ParquetHiveSerDe serDe, final ArrayWritable t) throws SerDeException {
// Get the row structure
final StructObjectInspector oi = (StructObjectInspector) serDe.getObjectInspector();
// Deserialize
final Object row = serDe.deserialize(t);
assertEquals("deserialization gives the wrong object class", row.getClass(), ArrayWritable.class);
assertEquals("size correct after deserialization", serDe.getSerDeStats().getRawDataSize(), t.get().length);
assertEquals("deserialization gives the wrong object", t, row);
// Serialize
final ArrayWritable serializedArr = (ArrayWritable) serDe.serialize(row, oi);
assertEquals("size correct after serialization", serDe.getSerDeStats().getRawDataSize(), serializedArr.get().length);
assertTrue("serialized object should be equal to starting object", arrayWritableEquals(t, serializedArr));
}
开发者ID:apache,项目名称:parquet-mr,代码行数:17,代码来源:TestParquetSerDe.java
示例5: getDataFormat
import org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe; //导入依赖的package包/类
public static String getDataFormat(StorageDescriptor descriptor) {
Preconditions.checkNotNull(descriptor);
String serde = descriptor.getSerdeInfo().getSerializationLib();
String inputFormat = descriptor.getInputFormat();
if (LazySimpleSerDe.class.getName().equals(serde)) {
if (TextInputFormat.class.getName().equals(inputFormat)) {
return BuiltinStorages.TEXT;
} else if (SequenceFileInputFormat.class.getName().equals(inputFormat)) {
return BuiltinStorages.SEQUENCE_FILE;
} else {
throw new TajoRuntimeException(new UnknownDataFormatException(inputFormat));
}
} else if (LazyBinarySerDe.class.getName().equals(serde)) {
if (SequenceFileInputFormat.class.getName().equals(inputFormat)) {
return BuiltinStorages.SEQUENCE_FILE;
} else {
throw new TajoRuntimeException(new UnknownDataFormatException(inputFormat));
}
} else if (LazyBinaryColumnarSerDe.class.getName().equals(serde) || ColumnarSerDe.class.getName().equals(serde)) {
if (RCFileInputFormat.class.getName().equals(inputFormat)) {
return BuiltinStorages.RCFILE;
} else {
throw new TajoRuntimeException(new UnknownDataFormatException(inputFormat));
}
} else if (ParquetHiveSerDe.class.getName().equals(serde)) {
return BuiltinStorages.PARQUET;
} else if (AvroSerDe.class.getName().equals(serde)) {
return BuiltinStorages.AVRO;
} else if (OrcSerde.class.getName().equals(serde)) {
return BuiltinStorages.ORC;
} else if (RegexSerDe.class.getName().equals(serde)) {
return BuiltinStorages.REGEX;
} else {
throw new TajoRuntimeException(new UnknownDataFormatException(inputFormat));
}
}
开发者ID:apache,项目名称:tajo,代码行数:39,代码来源:HiveCatalogUtil.java
示例6: convertMapType
import org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe; //导入依赖的package包/类
private static GroupType convertMapType(final String name, final MapTypeInfo typeInfo) {
final Type keyType = convertType(ParquetHiveSerDe.MAP_KEY.toString(),
typeInfo.getMapKeyTypeInfo(), Repetition.REQUIRED);
final Type valueType = convertType(ParquetHiveSerDe.MAP_VALUE.toString(),
typeInfo.getMapValueTypeInfo());
return ConversionPatterns.mapType(Repetition.OPTIONAL, name, keyType, valueType);
}
开发者ID:apache,项目名称:parquet-mr,代码行数:8,代码来源:HiveSchemaConverter.java
示例7: testParquetThrift
import org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe; //导入依赖的package包/类
@Test
public void testParquetThrift()
throws Exception
{
RowType nameType = new RowType(ImmutableList.of(VARCHAR, VARCHAR), Optional.empty());
RowType phoneType = new RowType(ImmutableList.of(VARCHAR, VARCHAR), Optional.empty());
RowType personType = new RowType(ImmutableList.of(nameType, BIGINT, VARCHAR, new ArrayType(phoneType)), Optional.empty());
List<TestColumn> testColumns = ImmutableList.<TestColumn>of(
new TestColumn(
"persons",
getStandardListObjectInspector(
getStandardStructObjectInspector(
ImmutableList.of("name", "id", "email", "phones"),
ImmutableList.<ObjectInspector>of(
getStandardStructObjectInspector(
ImmutableList.of("first_name", "last_name"),
ImmutableList.of(javaStringObjectInspector, javaStringObjectInspector)
),
javaIntObjectInspector,
javaStringObjectInspector,
getStandardListObjectInspector(
getStandardStructObjectInspector(
ImmutableList.of("number", "type"),
ImmutableList.of(javaStringObjectInspector, javaStringObjectInspector)
)
)
)
)
),
null,
arrayBlockOf(personType,
rowBlockOf(ImmutableList.of(nameType, BIGINT, VARCHAR, new ArrayType(phoneType)),
rowBlockOf(ImmutableList.of(VARCHAR, VARCHAR), "Bob", "Roberts"),
0,
"[email protected]",
arrayBlockOf(phoneType, rowBlockOf(ImmutableList.of(VARCHAR, VARCHAR), "1234567890", null))
)
)
)
);
InputFormat<?, ?> inputFormat = new MapredParquetInputFormat();
@SuppressWarnings("deprecation")
SerDe serde = new ParquetHiveSerDe();
File file = new File(this.getClass().getClassLoader().getResource("addressbook.parquet").getPath());
FileSplit split = new FileSplit(new Path(file.getAbsolutePath()), 0, file.length(), new String[0]);
HiveRecordCursorProvider cursorProvider = new ParquetRecordCursorProvider(false);
testCursorProvider(cursorProvider, split, inputFormat, serde, testColumns, 1);
}
开发者ID:y-lan,项目名称:presto,代码行数:51,代码来源:TestHiveFileFormats.java
示例8: convertArrayType
import org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe; //导入依赖的package包/类
private static GroupType convertArrayType(final String name, final ListTypeInfo typeInfo) {
final TypeInfo subType = typeInfo.getListElementTypeInfo();
return listWrapper(name, OriginalType.LIST, new GroupType(Repetition.REPEATED,
ParquetHiveSerDe.ARRAY.toString(), convertType("array_element", subType)));
}
开发者ID:apache,项目名称:parquet-mr,代码行数:6,代码来源:HiveSchemaConverter.java
示例9: testParquetHiveSerDe
import org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe; //导入依赖的package包/类
public void testParquetHiveSerDe() throws Throwable {
try {
// Create the SerDe
System.out.println("test: testParquetHiveSerDe");
final ParquetHiveSerDe serDe = new ParquetHiveSerDe();
final Configuration conf = new Configuration();
final Properties tbl = createProperties();
serDe.initialize(conf, tbl);
// Data
final Writable[] arr = new Writable[8];
arr[0] = new ByteWritable((byte) 123);
arr[1] = new ShortWritable((short) 456);
arr[2] = new IntWritable(789);
arr[3] = new LongWritable(1000l);
arr[4] = new DoubleWritable((double) 5.3);
arr[5] = new BinaryWritable(Binary.fromString("hive and hadoop and parquet. Big family."));
final Writable[] mapContainer = new Writable[1];
final Writable[] map = new Writable[3];
for (int i = 0; i < 3; ++i) {
final Writable[] pair = new Writable[2];
pair[0] = new BinaryWritable(Binary.fromString("key_" + i));
pair[1] = new IntWritable(i);
map[i] = new ArrayWritable(Writable.class, pair);
}
mapContainer[0] = new ArrayWritable(Writable.class, map);
arr[6] = new ArrayWritable(Writable.class, mapContainer);
final Writable[] arrayContainer = new Writable[1];
final Writable[] array = new Writable[5];
for (int i = 0; i < 5; ++i) {
array[i] = new BinaryWritable(Binary.fromString("elem_" + i));
}
arrayContainer[0] = new ArrayWritable(Writable.class, array);
arr[7] = new ArrayWritable(Writable.class, arrayContainer);
final ArrayWritable arrWritable = new ArrayWritable(Writable.class, arr);
// Test
deserializeAndSerializeLazySimple(serDe, arrWritable);
System.out.println("test: testParquetHiveSerDe - OK");
} catch (final Throwable e) {
e.printStackTrace();
throw e;
}
}
开发者ID:apache,项目名称:parquet-mr,代码行数:50,代码来源:TestParquetSerDe.java
注:本文中的org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe类示例整理自Github/MSDocs等源码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。 |
请发表评论