Search in sources :

Example 16 with INTEGER

use of io.trino.spi.type.IntegerType.INTEGER in project trino by trinodb.

the class RcFileTester method preprocessWriteValueOld.

private static Object preprocessWriteValueOld(Format format, Type type, Object value) {
    if (value == null) {
        return null;
    }
    if (type.equals(BOOLEAN)) {
        return value;
    }
    if (type.equals(TINYINT)) {
        return ((Number) value).byteValue();
    }
    if (type.equals(SMALLINT)) {
        return ((Number) value).shortValue();
    }
    if (type.equals(INTEGER)) {
        return ((Number) value).intValue();
    }
    if (type.equals(BIGINT)) {
        return ((Number) value).longValue();
    }
    if (type.equals(REAL)) {
        return ((Number) value).floatValue();
    }
    if (type.equals(DOUBLE)) {
        return ((Number) value).doubleValue();
    }
    if (type instanceof VarcharType) {
        return value;
    }
    if (type.equals(VARBINARY)) {
        return ((SqlVarbinary) value).getBytes();
    }
    if (type.equals(DATE)) {
        return Date.ofEpochDay(((SqlDate) value).getDays());
    }
    if (type.equals(TIMESTAMP_MILLIS)) {
        long millis = ((SqlTimestamp) value).getMillis();
        if (format == Format.BINARY) {
            millis = HIVE_STORAGE_TIME_ZONE.convertLocalToUTC(millis, false);
        }
        return Timestamp.ofEpochMilli(millis);
    }
    if (type instanceof DecimalType) {
        return HiveDecimal.create(((SqlDecimal) value).toBigDecimal());
    }
    if (type instanceof ArrayType) {
        Type elementType = type.getTypeParameters().get(0);
        return ((List<?>) value).stream().map(element -> preprocessWriteValueOld(format, elementType, element)).collect(toList());
    }
    if (type instanceof MapType) {
        Type keyType = type.getTypeParameters().get(0);
        Type valueType = type.getTypeParameters().get(1);
        Map<Object, Object> newMap = new HashMap<>();
        for (Entry<?, ?> entry : ((Map<?, ?>) value).entrySet()) {
            newMap.put(preprocessWriteValueOld(format, keyType, entry.getKey()), preprocessWriteValueOld(format, valueType, entry.getValue()));
        }
        return newMap;
    }
    if (type instanceof RowType) {
        List<?> fieldValues = (List<?>) value;
        List<Type> fieldTypes = type.getTypeParameters();
        List<Object> newStruct = new ArrayList<>();
        for (int fieldId = 0; fieldId < fieldValues.size(); fieldId++) {
            newStruct.add(preprocessWriteValueOld(format, fieldTypes.get(fieldId), fieldValues.get(fieldId)));
        }
        return newStruct;
    }
    throw new IllegalArgumentException("unsupported type: " + type);
}
Also used : SnappyCodec(org.apache.hadoop.io.compress.SnappyCodec) PRESTO_RCFILE_WRITER_VERSION_METADATA_KEY(io.trino.rcfile.RcFileWriter.PRESTO_RCFILE_WRITER_VERSION_METADATA_KEY) DateTimeZone(org.joda.time.DateTimeZone) PrimitiveObjectInspectorFactory.javaByteObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaByteObjectInspector) Text(org.apache.hadoop.io.Text) PrimitiveObjectInspectorFactory.javaLongObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaLongObjectInspector) Writable(org.apache.hadoop.io.Writable) PrimitiveObjectInspectorFactory.javaTimestampObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaTimestampObjectInspector) Date(org.apache.hadoop.hive.common.type.Date) PrimitiveObjectInspectorFactory.javaDateObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaDateObjectInspector) Decimals.rescale(io.trino.spi.type.Decimals.rescale) FileSplit(org.apache.hadoop.mapred.FileSplit) RcFileDecoderUtils.findFirstSyncPosition(io.trino.rcfile.RcFileDecoderUtils.findFirstSyncPosition) RCFileInputFormat(org.apache.hadoop.hive.ql.io.RCFileInputFormat) Files.createTempDirectory(java.nio.file.Files.createTempDirectory) Slices(io.airlift.slice.Slices) Configuration(org.apache.hadoop.conf.Configuration) Map(java.util.Map) BigInteger(java.math.BigInteger) ObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector) Assert.assertFalse(org.testng.Assert.assertFalse) LazyBinaryArray(org.apache.hadoop.hive.serde2.lazybinary.LazyBinaryArray) IntWritable(org.apache.hadoop.io.IntWritable) SMALLINT(io.trino.spi.type.SmallintType.SMALLINT) SERIALIZATION_LIB(org.apache.hadoop.hive.serde.serdeConstants.SERIALIZATION_LIB) PrimitiveObjectInspectorFactory.javaByteArrayObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaByteArrayObjectInspector) BytesRefArrayWritable(org.apache.hadoop.hive.serde2.columnar.BytesRefArrayWritable) META_TABLE_COLUMN_TYPES(org.apache.hadoop.hive.metastore.api.hive_metastoreConstants.META_TABLE_COLUMN_TYPES) PrimitiveObjectInspectorFactory.javaFloatObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaFloatObjectInspector) LazyMap(org.apache.hadoop.hive.serde2.lazy.LazyMap) PrimitiveObjectInspectorFactory.javaDoubleObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaDoubleObjectInspector) LazyArray(org.apache.hadoop.hive.serde2.lazy.LazyArray) Set(java.util.Set) READ_ALL_COLUMNS(org.apache.hadoop.hive.serde2.ColumnProjectionUtils.READ_ALL_COLUMNS) MICROSECONDS_PER_MILLISECOND(io.trino.type.DateTimes.MICROSECONDS_PER_MILLISECOND) UncheckedIOException(java.io.UncheckedIOException) BooleanWritable(org.apache.hadoop.io.BooleanWritable) RecordReader(org.apache.hadoop.mapred.RecordReader) TypeSignatureParameter(io.trino.spi.type.TypeSignatureParameter) DATE(io.trino.spi.type.DateType.DATE) REAL(io.trino.spi.type.RealType.REAL) PrimitiveObjectInspectorFactory.javaIntObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaIntObjectInspector) StructField(org.apache.hadoop.hive.serde2.objectinspector.StructField) Lz4Codec(org.apache.hadoop.io.compress.Lz4Codec) Iterables(com.google.common.collect.Iterables) Slice(io.airlift.slice.Slice) TIMESTAMP_MILLIS(io.trino.spi.type.TimestampType.TIMESTAMP_MILLIS) MEGABYTE(io.airlift.units.DataSize.Unit.MEGABYTE) StructObject(org.apache.hadoop.hive.serde2.StructObject) Page(io.trino.spi.Page) SqlDecimal(io.trino.spi.type.SqlDecimal) Functions.constant(com.google.common.base.Functions.constant) BOOLEAN(io.trino.spi.type.BooleanType.BOOLEAN) META_TABLE_COLUMNS(org.apache.hadoop.hive.metastore.api.hive_metastoreConstants.META_TABLE_COLUMNS) ArrayList(java.util.ArrayList) NONE(io.trino.rcfile.RcFileTester.Compression.NONE) VARCHAR(io.trino.spi.type.VarcharType.VARCHAR) Lists(com.google.common.collect.Lists) ALLOW_INSECURE(com.google.common.io.RecursiveDeleteOption.ALLOW_INSECURE) BZIP2(io.trino.rcfile.RcFileTester.Compression.BZIP2) PrimitiveObjectInspectorFactory.javaShortObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaShortObjectInspector) ThreadLocalRandom(java.util.concurrent.ThreadLocalRandom) VARBINARY(io.trino.spi.type.VarbinaryType.VARBINARY) HadoopNative(io.trino.hadoop.HadoopNative) LinkedHashSet(java.util.LinkedHashSet) Int128(io.trino.spi.type.Int128) Properties(java.util.Properties) MapType(io.trino.spi.type.MapType) AbstractIterator(com.google.common.collect.AbstractIterator) TESTING_TYPE_MANAGER(io.trino.type.InternalTypeManager.TESTING_TYPE_MANAGER) FileOutputStream(java.io.FileOutputStream) IOException(java.io.IOException) ObjectInspectorFactory.getStandardStructObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory.getStandardStructObjectInspector) DecimalTypeInfo(org.apache.hadoop.hive.serde2.typeinfo.DecimalTypeInfo) File(java.io.File) NULL(org.apache.hadoop.mapred.Reporter.NULL) SettableStructObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.SettableStructObjectInspector) DOUBLE(io.trino.spi.type.DoubleType.DOUBLE) SqlVarbinary(io.trino.spi.type.SqlVarbinary) SIZE_OF_LONG(io.airlift.slice.SizeOf.SIZE_OF_LONG) Deserializer(org.apache.hadoop.hive.serde2.Deserializer) TINYINT(io.trino.spi.type.TinyintType.TINYINT) BlockBuilder(io.trino.spi.block.BlockBuilder) SerDeException(org.apache.hadoop.hive.serde2.SerDeException) FloatWritable(org.apache.hadoop.io.FloatWritable) RecordWriter(org.apache.hadoop.hive.ql.exec.FileSinkOperator.RecordWriter) BinaryRcFileEncoding(io.trino.rcfile.binary.BinaryRcFileEncoding) DateTimeTestingUtils.sqlTimestampOf(io.trino.testing.DateTimeTestingUtils.sqlTimestampOf) Iterables.transform(com.google.common.collect.Iterables.transform) LazyBinaryColumnarSerDe(org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe) MoreFiles.deleteRecursively(com.google.common.io.MoreFiles.deleteRecursively) GzipCodec(org.apache.hadoop.io.compress.GzipCodec) LongWritable(org.apache.hadoop.io.LongWritable) SNAPPY(io.trino.rcfile.RcFileTester.Compression.SNAPPY) TextRcFileEncoding(io.trino.rcfile.text.TextRcFileEncoding) SqlTimestamp(io.trino.spi.type.SqlTimestamp) TimestampWritableV2(org.apache.hadoop.hive.serde2.io.TimestampWritableV2) Block(io.trino.spi.block.Block) PRESTO_RCFILE_WRITER_VERSION(io.trino.rcfile.RcFileWriter.PRESTO_RCFILE_WRITER_VERSION) InputFormat(org.apache.hadoop.mapred.InputFormat) Path(org.apache.hadoop.fs.Path) KILOBYTE(io.airlift.units.DataSize.Unit.KILOBYTE) INTEGER(io.trino.spi.type.IntegerType.INTEGER) ShortWritable(org.apache.hadoop.hive.serde2.io.ShortWritable) RowType(io.trino.spi.type.RowType) SIZE_OF_INT(io.airlift.slice.SizeOf.SIZE_OF_INT) ImmutableSet(com.google.common.collect.ImmutableSet) DateWritableV2(org.apache.hadoop.hive.serde2.io.DateWritableV2) ImmutableMap(com.google.common.collect.ImmutableMap) Collections.nCopies(java.util.Collections.nCopies) RCFileOutputFormat(org.apache.hadoop.hive.ql.io.RCFileOutputFormat) SESSION(io.trino.testing.TestingConnectorSession.SESSION) ArrayType(io.trino.spi.type.ArrayType) StructObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector) SqlDate(io.trino.spi.type.SqlDate) ColumnarSerDe(org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe) Objects(java.util.Objects) DataSize(io.airlift.units.DataSize) List(java.util.List) BIGINT(io.trino.spi.type.BigintType.BIGINT) Decimals(io.trino.spi.type.Decimals) Entry(java.util.Map.Entry) LZ4(io.trino.rcfile.RcFileTester.Compression.LZ4) Optional(java.util.Optional) READ_COLUMN_IDS_CONF_STR(org.apache.hadoop.hive.serde2.ColumnProjectionUtils.READ_COLUMN_IDS_CONF_STR) DecimalType(io.trino.spi.type.DecimalType) MAP(io.trino.spi.type.StandardTypes.MAP) LazyPrimitive(org.apache.hadoop.hive.serde2.lazy.LazyPrimitive) Assert.assertNull(org.testng.Assert.assertNull) LazyBinaryMap(org.apache.hadoop.hive.serde2.lazybinary.LazyBinaryMap) PrimitiveObjectInspectorFactory.javaBooleanObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaBooleanObjectInspector) Type(io.trino.spi.type.Type) Assert.assertEquals(org.testng.Assert.assertEquals) HashMap(java.util.HashMap) DoubleWritable(org.apache.hadoop.io.DoubleWritable) PrimitiveObjectInspectorFactory.getPrimitiveJavaObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.getPrimitiveJavaObjectInspector) VarcharType(io.trino.spi.type.VarcharType) OutputStreamSliceOutput(io.airlift.slice.OutputStreamSliceOutput) COMPRESS_CODEC(org.apache.hadoop.mapreduce.lib.output.FileOutputFormat.COMPRESS_CODEC) ImmutableList(com.google.common.collect.ImmutableList) ByteWritable(org.apache.hadoop.io.ByteWritable) BytesWritable(org.apache.hadoop.io.BytesWritable) Math.toIntExact(java.lang.Math.toIntExact) Iterator(java.util.Iterator) Timestamp(org.apache.hadoop.hive.common.type.Timestamp) Iterators.advance(com.google.common.collect.Iterators.advance) FileInputStream(java.io.FileInputStream) JobConf(org.apache.hadoop.mapred.JobConf) BZip2Codec(org.apache.hadoop.io.compress.BZip2Codec) Collectors.toList(java.util.stream.Collectors.toList) ObjectInspectorFactory(org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory) Serializer(org.apache.hadoop.hive.serde2.Serializer) HiveDecimal(org.apache.hadoop.hive.common.type.HiveDecimal) Closeable(java.io.Closeable) Assert.assertTrue(org.testng.Assert.assertTrue) PrimitiveObjectInspectorFactory.javaStringObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaStringObjectInspector) HiveDecimalWritable(org.apache.hadoop.hive.serde2.io.HiveDecimalWritable) Collections(java.util.Collections) InputStream(java.io.InputStream) ZLIB(io.trino.rcfile.RcFileTester.Compression.ZLIB) VarcharType(io.trino.spi.type.VarcharType) HashMap(java.util.HashMap) SqlVarbinary(io.trino.spi.type.SqlVarbinary) ArrayList(java.util.ArrayList) RowType(io.trino.spi.type.RowType) SqlTimestamp(io.trino.spi.type.SqlTimestamp) MapType(io.trino.spi.type.MapType) ArrayType(io.trino.spi.type.ArrayType) MapType(io.trino.spi.type.MapType) RowType(io.trino.spi.type.RowType) ArrayType(io.trino.spi.type.ArrayType) DecimalType(io.trino.spi.type.DecimalType) Type(io.trino.spi.type.Type) VarcharType(io.trino.spi.type.VarcharType) DecimalType(io.trino.spi.type.DecimalType) ArrayList(java.util.ArrayList) List(java.util.List) ImmutableList(com.google.common.collect.ImmutableList) Collectors.toList(java.util.stream.Collectors.toList) StructObject(org.apache.hadoop.hive.serde2.StructObject) Map(java.util.Map) LazyMap(org.apache.hadoop.hive.serde2.lazy.LazyMap) ImmutableMap(com.google.common.collect.ImmutableMap) LazyBinaryMap(org.apache.hadoop.hive.serde2.lazybinary.LazyBinaryMap) HashMap(java.util.HashMap)

Example 17 with INTEGER

use of io.trino.spi.type.IntegerType.INTEGER in project trino by trinodb.

the class TestMergingPageIterator method testMerging.

@Test
public void testMerging() {
    List<Type> types = ImmutableList.of(INTEGER, INTEGER);
    List<Integer> sortIndexes = ImmutableList.of(1);
    List<SortOrder> sortOrders = ImmutableList.of(SortOrder.ASC_NULLS_FIRST);
    List<List<Page>> pageLists = new ArrayList<>();
    PageBuilder pageBuilder = new PageBuilder(types);
    for (int i = 0; i < 10; i++) {
        Iterator<Integer> values = IntStream.range(0, 1000).map(ignored -> ThreadLocalRandom.current().nextInt(100_000)).mapToObj(n -> ((n % 100) == 0) ? null : n).sorted(nullsFirst(naturalOrder())).iterator();
        List<Page> pages = new ArrayList<>();
        for (int j = 0; j < 10; j++) {
            for (int k = 0; k < 100; k++) {
                Integer n = values.next();
                pageBuilder.declarePosition();
                if (n == null) {
                    pageBuilder.getBlockBuilder(0).appendNull();
                    pageBuilder.getBlockBuilder(1).appendNull();
                } else {
                    INTEGER.writeLong(pageBuilder.getBlockBuilder(0), n);
                    INTEGER.writeLong(pageBuilder.getBlockBuilder(1), n * 22L);
                }
            }
            pages.add(pageBuilder.build());
            pageBuilder.reset();
        }
        pageLists.add(pages);
        assertFalse(values.hasNext());
    }
    List<Iterator<Page>> pages = pageLists.stream().map(List::iterator).collect(toList());
    Iterator<Page> iterator = new MergingPageIterator(pages, types, sortIndexes, sortOrders, new TypeOperators());
    List<Long> values = new ArrayList<>();
    while (iterator.hasNext()) {
        Page page = iterator.next();
        for (int i = 0; i < page.getPositionCount(); i++) {
            if (page.getBlock(0).isNull(i)) {
                assertTrue(page.getBlock(1).isNull(i));
                values.add(null);
            } else {
                long x = INTEGER.getLong(page.getBlock(0), i);
                long y = INTEGER.getLong(page.getBlock(1), i);
                assertEquals(y, x * 22);
                values.add(x);
            }
        }
    }
    assertThat(values).isSortedAccordingTo(nullsFirst(naturalOrder()));
}
Also used : IntStream(java.util.stream.IntStream) Comparator.nullsFirst(java.util.Comparator.nullsFirst) Iterator(java.util.Iterator) Comparator.naturalOrder(java.util.Comparator.naturalOrder) PageBuilder(io.trino.spi.PageBuilder) Assertions.assertThat(org.assertj.core.api.Assertions.assertThat) Type(io.trino.spi.type.Type) Page(io.trino.spi.Page) Assert.assertEquals(org.testng.Assert.assertEquals) Test(org.testng.annotations.Test) TypeOperators(io.trino.spi.type.TypeOperators) SortOrder(io.trino.spi.connector.SortOrder) ArrayList(java.util.ArrayList) List(java.util.List) Collectors.toList(java.util.stream.Collectors.toList) ImmutableList(com.google.common.collect.ImmutableList) ThreadLocalRandom(java.util.concurrent.ThreadLocalRandom) Assert.assertTrue(org.testng.Assert.assertTrue) INTEGER(io.trino.spi.type.IntegerType.INTEGER) Assert.assertFalse(org.testng.Assert.assertFalse) ArrayList(java.util.ArrayList) SortOrder(io.trino.spi.connector.SortOrder) Page(io.trino.spi.Page) PageBuilder(io.trino.spi.PageBuilder) Type(io.trino.spi.type.Type) Iterator(java.util.Iterator) ArrayList(java.util.ArrayList) List(java.util.List) Collectors.toList(java.util.stream.Collectors.toList) ImmutableList(com.google.common.collect.ImmutableList) TypeOperators(io.trino.spi.type.TypeOperators) Test(org.testng.annotations.Test)

Example 18 with INTEGER

use of io.trino.spi.type.IntegerType.INTEGER in project trino by trinodb.

the class KuduBucketFunction method getBucket.

@Override
public int getBucket(Page page, int position) {
    checkArgument(this.bucketChannelTypes.size() == page.getChannelCount());
    PartialRow partialRow = new PartialRow(this.schema);
    List<Integer> bucketIds = this.hashBucketSchemas.stream().map(hashBucketSchema -> this.calculateSchemaLevelBucketId(page, partialRow, hashBucketSchema, position)).collect(toImmutableList());
    return getBucket(bucketIds, hashBucketSchemas);
}
Also used : BucketFunction(io.trino.spi.connector.BucketFunction) Type(io.trino.spi.type.Type) Page(io.trino.spi.Page) BOOLEAN(io.trino.spi.type.BooleanType.BOOLEAN) Shorts(com.google.common.primitives.Shorts) Schema(org.apache.kudu.Schema) Preconditions.checkArgument(com.google.common.base.Preconditions.checkArgument) VARCHAR(io.trino.spi.type.VarcharType.VARCHAR) ImmutableList(com.google.common.collect.ImmutableList) Block(io.trino.spi.block.Block) Objects.requireNonNull(java.util.Objects.requireNonNull) Math.toIntExact(java.lang.Math.toIntExact) INTEGER(io.trino.spi.type.IntegerType.INTEGER) SMALLINT(io.trino.spi.type.SmallintType.SMALLINT) PartialRow(org.apache.kudu.client.PartialRow) ImmutableList.toImmutableList(com.google.common.collect.ImmutableList.toImmutableList) SignedBytes(com.google.common.primitives.SignedBytes) KuduTable(org.apache.kudu.client.KuduTable) KeyEncoderAccessor(org.apache.kudu.client.KeyEncoderAccessor) DOUBLE(io.trino.spi.type.DoubleType.DOUBLE) List(java.util.List) BIGINT(io.trino.spi.type.BigintType.BIGINT) HashBucketSchema(org.apache.kudu.client.PartitionSchema.HashBucketSchema) TINYINT(io.trino.spi.type.TinyintType.TINYINT) MoreObjects.toStringHelper(com.google.common.base.MoreObjects.toStringHelper) PartialRow(org.apache.kudu.client.PartialRow)

Example 19 with INTEGER

use of io.trino.spi.type.IntegerType.INTEGER in project trino by trinodb.

the class HiveUtil method createRecordReader.

public static RecordReader<?, ?> createRecordReader(Configuration configuration, Path path, long start, long length, Properties schema, List<HiveColumnHandle> columns) {
    // determine which hive columns we will read
    List<HiveColumnHandle> readColumns = columns.stream().filter(column -> column.getColumnType() == REGULAR).collect(toImmutableList());
    // Projected columns are not supported here
    readColumns.forEach(readColumn -> checkArgument(readColumn.isBaseColumn(), "column %s is not a base column", readColumn.getName()));
    List<Integer> readHiveColumnIndexes = readColumns.stream().map(HiveColumnHandle::getBaseHiveColumnIndex).collect(toImmutableList());
    // Tell hive the columns we would like to read, this lets hive optimize reading column oriented files
    configuration = copy(configuration);
    setReadColumns(configuration, readHiveColumnIndexes);
    InputFormat<?, ?> inputFormat = getInputFormat(configuration, schema, true);
    JobConf jobConf = toJobConf(configuration);
    FileSplit fileSplit = new FileSplit(path, start, length, (String[]) null);
    // propagate serialization configuration to getRecordReader
    schema.stringPropertyNames().stream().filter(name -> name.startsWith("serialization.")).forEach(name -> jobConf.set(name, schema.getProperty(name)));
    configureCompressionCodecs(jobConf);
    try {
        // raw type on WritableComparable can't be fixed because Utilities#skipHeader takes them raw
        @SuppressWarnings({ "rawtypes", "unchecked" }) RecordReader<WritableComparable, Writable> recordReader = (RecordReader<WritableComparable, Writable>) inputFormat.getRecordReader(fileSplit, jobConf, Reporter.NULL);
        int headerCount = getHeaderCount(schema);
        // Only skip header rows when the split is at the beginning of the file
        if (start == 0 && headerCount > 0) {
            Utilities.skipHeader(recordReader, headerCount, recordReader.createKey(), recordReader.createValue());
        }
        int footerCount = getFooterCount(schema);
        if (footerCount > 0) {
            recordReader = new FooterAwareRecordReader<>(recordReader, footerCount, jobConf);
        }
        return recordReader;
    } catch (IOException e) {
        if (e instanceof TextLineLengthLimitExceededException) {
            throw new TrinoException(HIVE_BAD_DATA, "Line too long in text file: " + path, e);
        }
        throw new TrinoException(HIVE_CANNOT_OPEN_SPLIT, format("Error opening Hive split %s (offset=%s, length=%s) using %s: %s", path, start, length, getInputFormatName(schema), firstNonNull(e.getMessage(), e.getClass().getName())), e);
    }
}
Also used : DateTimeZone(org.joda.time.DateTimeZone) ORC_BLOOM_FILTER_FPP(io.trino.plugin.hive.HiveTableProperties.ORC_BLOOM_FILTER_FPP) FileSystem(org.apache.hadoop.fs.FileSystem) HIVE_CANNOT_OPEN_SPLIT(io.trino.plugin.hive.HiveErrorCode.HIVE_CANNOT_OPEN_SPLIT) DECIMAL_TYPE_NAME(org.apache.hadoop.hive.serde.serdeConstants.DECIMAL_TYPE_NAME) HiveBucketing.isSupportedBucketing(io.trino.plugin.hive.util.HiveBucketing.isSupportedBucketing) Writable(org.apache.hadoop.io.Writable) HiveColumnHandle.isBucketColumnHandle(io.trino.plugin.hive.HiveColumnHandle.isBucketColumnHandle) Short.parseShort(java.lang.Short.parseShort) AbstractSerDe(org.apache.hadoop.hive.serde2.AbstractSerDe) BigDecimal(java.math.BigDecimal) NOT_SUPPORTED(io.trino.spi.StandardErrorCode.NOT_SUPPORTED) FileSplit(org.apache.hadoop.mapred.FileSplit) Matcher(java.util.regex.Matcher) Column(io.trino.plugin.hive.metastore.Column) Slices(io.airlift.slice.Slices) Configuration(org.apache.hadoop.conf.Configuration) Map(java.util.Map) StructTypeInfo(org.apache.hadoop.hive.serde2.typeinfo.StructTypeInfo) Slices.utf8Slice(io.airlift.slice.Slices.utf8Slice) ObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector) Chars.trimTrailingSpaces(io.trino.spi.type.Chars.trimTrailingSpaces) ENGLISH(java.util.Locale.ENGLISH) HiveColumnHandle.isFileSizeColumnHandle(io.trino.plugin.hive.HiveColumnHandle.isFileSizeColumnHandle) SMALLINT(io.trino.spi.type.SmallintType.SMALLINT) Double.parseDouble(java.lang.Double.parseDouble) SERIALIZATION_LIB(org.apache.hadoop.hive.serde.serdeConstants.SERIALIZATION_LIB) LzoCodec(io.airlift.compress.lzo.LzoCodec) Table(io.trino.plugin.hive.metastore.Table) ImmutableList.toImmutableList(com.google.common.collect.ImmutableList.toImmutableList) DateTimeEncoding.packDateTimeWithZone(io.trino.spi.type.DateTimeEncoding.packDateTimeWithZone) READ_ALL_COLUMNS(org.apache.hadoop.hive.serde2.ColumnProjectionUtils.READ_ALL_COLUMNS) AvroSerDe(org.apache.hadoop.hive.serde2.avro.AvroSerDe) HiveColumnHandle.fileSizeColumnHandle(io.trino.plugin.hive.HiveColumnHandle.fileSizeColumnHandle) ASCENDING(io.trino.plugin.hive.metastore.SortingColumn.Order.ASCENDING) Collectors.joining(java.util.stream.Collectors.joining) InvocationTargetException(java.lang.reflect.InvocationTargetException) Lists.newArrayList(com.google.common.collect.Lists.newArrayList) DESCENDING(io.trino.plugin.hive.metastore.SortingColumn.Order.DESCENDING) TextLineLengthLimitExceededException(io.trino.hadoop.TextLineLengthLimitExceededException) DateTimePrinter(org.joda.time.format.DateTimePrinter) RecordReader(org.apache.hadoop.mapred.RecordReader) DATE(io.trino.spi.type.DateType.DATE) REAL(io.trino.spi.type.RealType.REAL) Joiner(com.google.common.base.Joiner) HiveColumnHandle.bucketColumnHandle(io.trino.plugin.hive.HiveColumnHandle.bucketColumnHandle) HiveColumnHandle.isFileModifiedTimeColumnHandle(io.trino.plugin.hive.HiveColumnHandle.isFileModifiedTimeColumnHandle) Slice(io.airlift.slice.Slice) DateTimeFormatterBuilder(org.joda.time.format.DateTimeFormatterBuilder) NullableValue(io.trino.spi.predicate.NullableValue) Decimals.isLongDecimal(io.trino.spi.type.Decimals.isLongDecimal) TIMESTAMP_MILLIS(io.trino.spi.type.TimestampType.TIMESTAMP_MILLIS) ConfigurationUtils.toJobConf(io.trino.plugin.hive.util.ConfigurationUtils.toJobConf) WritableComparable(org.apache.hadoop.io.WritableComparable) BOOLEAN(io.trino.spi.type.BooleanType.BOOLEAN) HIVE_SERDE_NOT_FOUND(io.trino.plugin.hive.HiveErrorCode.HIVE_SERDE_NOT_FOUND) HiveType(io.trino.plugin.hive.HiveType) Float.floatToRawIntBits(java.lang.Float.floatToRawIntBits) HIVE_INVALID_METADATA(io.trino.plugin.hive.HiveErrorCode.HIVE_INVALID_METADATA) TIMESTAMP_TZ_MILLIS(io.trino.spi.type.TimestampWithTimeZoneType.TIMESTAMP_TZ_MILLIS) Byte.parseByte(java.lang.Byte.parseByte) HIVE_INVALID_PARTITION_VALUE(io.trino.plugin.hive.HiveErrorCode.HIVE_INVALID_PARTITION_VALUE) COLLECTION_DELIM(org.apache.hadoop.hive.serde.serdeConstants.COLLECTION_DELIM) TEXTFILE(io.trino.plugin.hive.HiveStorageFormat.TEXTFILE) HiveColumnHandle.isPathColumnHandle(io.trino.plugin.hive.HiveColumnHandle.isPathColumnHandle) Math.floorDiv(java.lang.Math.floorDiv) Nullable(javax.annotation.Nullable) SKIP_HEADER_COUNT_KEY(io.trino.plugin.hive.HiveMetadata.SKIP_HEADER_COUNT_KEY) Int128(io.trino.spi.type.Int128) HIVE_BAD_DATA(io.trino.plugin.hive.HiveErrorCode.HIVE_BAD_DATA) CompressionCodecFactory(org.apache.hadoop.io.compress.CompressionCodecFactory) Properties(java.util.Properties) DecimalType.createDecimalType(io.trino.spi.type.DecimalType.createDecimalType) MapType(io.trino.spi.type.MapType) Reporter(org.apache.hadoop.mapred.Reporter) HIVE_UNSUPPORTED_FORMAT(io.trino.plugin.hive.HiveErrorCode.HIVE_UNSUPPORTED_FORMAT) IOException(java.io.IOException) Field(java.lang.reflect.Field) ORC_BLOOM_FILTER_COLUMNS_KEY(io.trino.plugin.hive.HiveMetadata.ORC_BLOOM_FILTER_COLUMNS_KEY) DOUBLE(io.trino.spi.type.DoubleType.DOUBLE) VarbinaryType(io.trino.spi.type.VarbinaryType) OrcWriterOptions(io.trino.orc.OrcWriterOptions) CharType(io.trino.spi.type.CharType) Deserializer(org.apache.hadoop.hive.serde2.Deserializer) HiveColumnHandle.pathColumnHandle(io.trino.plugin.hive.HiveColumnHandle.pathColumnHandle) HiveType.toHiveTypes(io.trino.plugin.hive.HiveType.toHiveTypes) TINYINT(io.trino.spi.type.TinyintType.TINYINT) SerDeException(org.apache.hadoop.hive.serde2.SerDeException) Long.parseLong(java.lang.Long.parseLong) ReflectionUtils(org.apache.hadoop.util.ReflectionUtils) PARTITION_KEY(io.trino.plugin.hive.HiveColumnHandle.ColumnType.PARTITION_KEY) DateTimeParser(org.joda.time.format.DateTimeParser) MICROSECONDS_PER_MILLISECOND(io.trino.spi.type.Timestamps.MICROSECONDS_PER_MILLISECOND) HiveColumnHandle.partitionColumnHandle(io.trino.plugin.hive.HiveColumnHandle.partitionColumnHandle) ORC_BLOOM_FILTER_FPP_KEY(io.trino.plugin.hive.HiveMetadata.ORC_BLOOM_FILTER_FPP_KEY) Float.parseFloat(java.lang.Float.parseFloat) CompressionCodec(org.apache.hadoop.io.compress.CompressionCodec) Preconditions.checkArgument(com.google.common.base.Preconditions.checkArgument) ParquetHiveSerDe(org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe) InputFormat(org.apache.hadoop.mapred.InputFormat) Path(org.apache.hadoop.fs.Path) HiveColumnHandle(io.trino.plugin.hive.HiveColumnHandle) INTEGER(io.trino.spi.type.IntegerType.INTEGER) Splitter(com.google.common.base.Splitter) Method(java.lang.reflect.Method) SliceUtf8(io.airlift.slice.SliceUtf8) DateTimeFormat(org.joda.time.format.DateTimeFormat) ISODateTimeFormat(org.joda.time.format.ISODateTimeFormat) RowType(io.trino.spi.type.RowType) ImmutableSet(com.google.common.collect.ImmutableSet) TrinoException(io.trino.spi.TrinoException) ArrayType(io.trino.spi.type.ArrayType) HiveTimestampPrecision(io.trino.plugin.hive.HiveTimestampPrecision) StructObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector) String.format(java.lang.String.format) List(java.util.List) BIGINT(io.trino.spi.type.BigintType.BIGINT) ErrorCodeSupplier(io.trino.spi.ErrorCodeSupplier) Optional(java.util.Optional) MoreObjects.firstNonNull(com.google.common.base.MoreObjects.firstNonNull) READ_COLUMN_IDS_CONF_STR(org.apache.hadoop.hive.serde2.ColumnProjectionUtils.READ_COLUMN_IDS_CONF_STR) Pattern(java.util.regex.Pattern) FileUtils.unescapePathName(org.apache.hadoop.hive.common.FileUtils.unescapePathName) DecimalType(io.trino.spi.type.DecimalType) TextInputFormat(org.apache.hadoop.mapred.TextInputFormat) ConfigurationUtils.copy(io.trino.plugin.hive.util.ConfigurationUtils.copy) ROUND_UNNECESSARY(java.math.BigDecimal.ROUND_UNNECESSARY) Type(io.trino.spi.type.Type) IOConstants(org.apache.hadoop.hive.ql.io.IOConstants) OptionalInt(java.util.OptionalInt) LzopCodec(io.airlift.compress.lzo.LzopCodec) SymlinkTextInputFormat(org.apache.hadoop.hive.ql.io.SymlinkTextInputFormat) Utilities(org.apache.hadoop.hive.ql.exec.Utilities) Category(org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector.Category) VarcharType(io.trino.spi.type.VarcharType) MapredParquetInputFormat(org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat) ImmutableList(com.google.common.collect.ImmutableList) HiveStorageFormat(io.trino.plugin.hive.HiveStorageFormat) HiveColumnHandle.createBaseColumn(io.trino.plugin.hive.HiveColumnHandle.createBaseColumn) HIVE_DEFAULT_DYNAMIC_PARTITION(io.trino.plugin.hive.HivePartitionKey.HIVE_DEFAULT_DYNAMIC_PARTITION) Decimals.isShortDecimal(io.trino.spi.type.Decimals.isShortDecimal) VerifyException(com.google.common.base.VerifyException) DateTimeFormatter(org.joda.time.format.DateTimeFormatter) UTF_8(java.nio.charset.StandardCharsets.UTF_8) HivePartitionKey(io.trino.plugin.hive.HivePartitionKey) HiveColumnHandle.isPartitionColumnHandle(io.trino.plugin.hive.HiveColumnHandle.isPartitionColumnHandle) SKIP_FOOTER_COUNT_KEY(io.trino.plugin.hive.HiveMetadata.SKIP_FOOTER_COUNT_KEY) Integer.parseInt(java.lang.Integer.parseInt) TrinoAvroSerDe(io.trino.plugin.hive.avro.TrinoAvroSerDe) GENERIC_INTERNAL_ERROR(io.trino.spi.StandardErrorCode.GENERIC_INTERNAL_ERROR) JavaUtils(org.apache.hadoop.hive.common.JavaUtils) JobConf(org.apache.hadoop.mapred.JobConf) TimeUnit(java.util.concurrent.TimeUnit) SortingColumn(io.trino.plugin.hive.metastore.SortingColumn) FILE_INPUT_FORMAT(org.apache.hadoop.hive.metastore.api.hive_metastoreConstants.FILE_INPUT_FORMAT) TypeManager(io.trino.spi.type.TypeManager) HiveColumnHandle.fileModifiedTimeColumnHandle(io.trino.plugin.hive.HiveColumnHandle.fileModifiedTimeColumnHandle) REGULAR(io.trino.plugin.hive.HiveColumnHandle.ColumnType.REGULAR) RecordReader(org.apache.hadoop.mapred.RecordReader) Writable(org.apache.hadoop.io.Writable) IOException(java.io.IOException) FileSplit(org.apache.hadoop.mapred.FileSplit) TextLineLengthLimitExceededException(io.trino.hadoop.TextLineLengthLimitExceededException) WritableComparable(org.apache.hadoop.io.WritableComparable) TrinoException(io.trino.spi.TrinoException) ConfigurationUtils.toJobConf(io.trino.plugin.hive.util.ConfigurationUtils.toJobConf) JobConf(org.apache.hadoop.mapred.JobConf) HiveColumnHandle(io.trino.plugin.hive.HiveColumnHandle)

Example 20 with INTEGER

use of io.trino.spi.type.IntegerType.INTEGER in project trino by trinodb.

the class OrcTester method preprocessWriteValueHive.

private static Object preprocessWriteValueHive(Type type, Object value) {
    if (value == null) {
        return null;
    }
    if (type.equals(BOOLEAN)) {
        return value;
    }
    if (type.equals(TINYINT)) {
        return ((Number) value).byteValue();
    }
    if (type.equals(SMALLINT)) {
        return ((Number) value).shortValue();
    }
    if (type.equals(INTEGER)) {
        return ((Number) value).intValue();
    }
    if (type.equals(BIGINT)) {
        return ((Number) value).longValue();
    }
    if (type.equals(REAL)) {
        return ((Number) value).floatValue();
    }
    if (type.equals(DOUBLE)) {
        return ((Number) value).doubleValue();
    }
    if (type instanceof VarcharType) {
        return value;
    }
    if (type instanceof CharType) {
        return new HiveChar((String) value, ((CharType) type).getLength());
    }
    if (type.equals(VARBINARY)) {
        return ((SqlVarbinary) value).getBytes();
    }
    if (type.equals(DATE)) {
        return Date.ofEpochDay(((SqlDate) value).getDays());
    }
    if (type.equals(TIMESTAMP_MILLIS) || type.equals(TIMESTAMP_MICROS) || type.equals(TIMESTAMP_NANOS)) {
        LocalDateTime dateTime = ((SqlTimestamp) value).toLocalDateTime();
        return Timestamp.ofEpochSecond(dateTime.toEpochSecond(ZoneOffset.UTC), dateTime.getNano());
    }
    if (type.equals(TIMESTAMP_TZ_MILLIS) || type.equals(TIMESTAMP_TZ_MICROS) || type.equals(TIMESTAMP_TZ_NANOS)) {
        SqlTimestampWithTimeZone timestamp = (SqlTimestampWithTimeZone) value;
        int nanosOfMilli = roundDiv(timestamp.getPicosOfMilli(), PICOSECONDS_PER_NANOSECOND);
        return Timestamp.ofEpochMilli(timestamp.getEpochMillis(), nanosOfMilli);
    }
    if (type instanceof DecimalType) {
        return HiveDecimal.create(((SqlDecimal) value).toBigDecimal());
    }
    if (type instanceof ArrayType) {
        Type elementType = type.getTypeParameters().get(0);
        return ((List<?>) value).stream().map(element -> preprocessWriteValueHive(elementType, element)).collect(toList());
    }
    if (type instanceof MapType) {
        Type keyType = type.getTypeParameters().get(0);
        Type valueType = type.getTypeParameters().get(1);
        Map<Object, Object> newMap = new HashMap<>();
        for (Entry<?, ?> entry : ((Map<?, ?>) value).entrySet()) {
            newMap.put(preprocessWriteValueHive(keyType, entry.getKey()), preprocessWriteValueHive(valueType, entry.getValue()));
        }
        return newMap;
    }
    if (type instanceof RowType) {
        List<?> fieldValues = (List<?>) value;
        List<Type> fieldTypes = type.getTypeParameters();
        List<Object> newStruct = new ArrayList<>();
        for (int fieldId = 0; fieldId < fieldValues.size(); fieldId++) {
            newStruct.add(preprocessWriteValueHive(fieldTypes.get(fieldId), fieldValues.get(fieldId)));
        }
        return newStruct;
    }
    throw new IllegalArgumentException("unsupported type: " + type);
}
Also used : LocalDateTime(java.time.LocalDateTime) OrcUtil(org.apache.hadoop.hive.ql.io.orc.OrcUtil) DateTimeZone(org.joda.time.DateTimeZone) NamedTypeSignature(io.trino.spi.type.NamedTypeSignature) PrimitiveObjectInspectorFactory.javaByteObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaByteObjectInspector) Text(org.apache.hadoop.io.Text) TIMESTAMP_TZ_NANOS(io.trino.spi.type.TimestampWithTimeZoneType.TIMESTAMP_TZ_NANOS) PrimitiveObjectInspectorFactory.javaLongObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaLongObjectInspector) Writable(org.apache.hadoop.io.Writable) PrimitiveObjectInspectorFactory.javaTimestampObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaTimestampObjectInspector) Date(org.apache.hadoop.hive.common.type.Date) NANOSECONDS_PER_MICROSECOND(io.trino.spi.type.Timestamps.NANOSECONDS_PER_MICROSECOND) PrimitiveObjectInspectorFactory.javaDateObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaDateObjectInspector) LongTimestampWithTimeZone(io.trino.spi.type.LongTimestampWithTimeZone) NONE(io.trino.orc.metadata.CompressionKind.NONE) HiveChar(org.apache.hadoop.hive.common.type.HiveChar) OrcStruct(org.apache.hadoop.hive.ql.io.orc.OrcStruct) Decimals.rescale(io.trino.spi.type.Decimals.rescale) TimestampWithTimeZoneType(io.trino.spi.type.TimestampWithTimeZoneType) Arrays.asList(java.util.Arrays.asList) Slices(io.airlift.slice.Slices) Configuration(org.apache.hadoop.conf.Configuration) Map(java.util.Map) BigInteger(java.math.BigInteger) Slices.utf8Slice(io.airlift.slice.Slices.utf8Slice) ObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector) ZoneOffset(java.time.ZoneOffset) Assert.assertFalse(org.testng.Assert.assertFalse) IntWritable(org.apache.hadoop.io.IntWritable) SMALLINT(io.trino.spi.type.SmallintType.SMALLINT) PrimitiveObjectInspectorFactory.javaByteArrayObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaByteArrayObjectInspector) PrimitiveObjectInspectorFactory.javaFloatObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaFloatObjectInspector) PICOSECONDS_PER_MICROSECOND(io.trino.spi.type.Timestamps.PICOSECONDS_PER_MICROSECOND) PrimitiveObjectInspectorFactory.javaDoubleObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaDoubleObjectInspector) UTC_KEY(io.trino.spi.type.TimeZoneKey.UTC_KEY) ImmutableList.toImmutableList(com.google.common.collect.ImmutableList.toImmutableList) DateTimeEncoding.packDateTimeWithZone(io.trino.spi.type.DateTimeEncoding.packDateTimeWithZone) Set(java.util.Set) READ_ALL_COLUMNS(org.apache.hadoop.hive.serde2.ColumnProjectionUtils.READ_ALL_COLUMNS) ReaderOptions(org.apache.hadoop.hive.ql.io.orc.OrcFile.ReaderOptions) BooleanWritable(org.apache.hadoop.io.BooleanWritable) Lists.newArrayList(com.google.common.collect.Lists.newArrayList) TypeSignatureParameter(io.trino.spi.type.TypeSignatureParameter) DATE(io.trino.spi.type.DateType.DATE) REAL(io.trino.spi.type.RealType.REAL) PrimitiveObjectInspectorFactory.javaIntObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaIntObjectInspector) StructField(org.apache.hadoop.hive.serde2.objectinspector.StructField) JavaHiveCharObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.JavaHiveCharObjectInspector) Iterables(com.google.common.collect.Iterables) Slice(io.airlift.slice.Slice) TIMESTAMP_MILLIS(io.trino.spi.type.TimestampType.TIMESTAMP_MILLIS) MEGABYTE(io.airlift.units.DataSize.Unit.MEGABYTE) LocalDateTime(java.time.LocalDateTime) Page(io.trino.spi.Page) SqlDecimal(io.trino.spi.type.SqlDecimal) DataSize.succinctBytes(io.airlift.units.DataSize.succinctBytes) BOOLEAN(io.trino.spi.type.BooleanType.BOOLEAN) HiveCharWritable(org.apache.hadoop.hive.serde2.io.HiveCharWritable) PrimitiveObjectInspectorFactory.javaTimestampTZObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaTimestampTZObjectInspector) ArrayList(java.util.ArrayList) TIMESTAMP_TZ_MILLIS(io.trino.spi.type.TimestampWithTimeZoneType.TIMESTAMP_TZ_MILLIS) Lists(com.google.common.collect.Lists) PrimitiveObjectInspectorFactory.javaShortObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaShortObjectInspector) VARBINARY(io.trino.spi.type.VarbinaryType.VARBINARY) BOTH(io.trino.orc.OrcWriteValidation.OrcWriteValidationMode.BOTH) OrcType(io.trino.orc.metadata.OrcType) Int128(io.trino.spi.type.Int128) TIMESTAMP_TZ_MICROS(io.trino.spi.type.TimestampWithTimeZoneType.TIMESTAMP_TZ_MICROS) Properties(java.util.Properties) MapType(io.trino.spi.type.MapType) AbstractIterator(com.google.common.collect.AbstractIterator) TESTING_TYPE_MANAGER(io.trino.type.InternalTypeManager.TESTING_TYPE_MANAGER) StandardTypes(io.trino.spi.type.StandardTypes) FileOutputStream(java.io.FileOutputStream) IOException(java.io.IOException) ObjectInspectorFactory.getStandardStructObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory.getStandardStructObjectInspector) DecimalTypeInfo(org.apache.hadoop.hive.serde2.typeinfo.DecimalTypeInfo) CompressionKind(io.trino.orc.metadata.CompressionKind) File(java.io.File) ZLIB(io.trino.orc.metadata.CompressionKind.ZLIB) SettableStructObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.SettableStructObjectInspector) MAX_BATCH_SIZE(io.trino.orc.OrcReader.MAX_BATCH_SIZE) DOUBLE(io.trino.spi.type.DoubleType.DOUBLE) TIMESTAMP_MICROS(io.trino.spi.type.TimestampType.TIMESTAMP_MICROS) SqlVarbinary(io.trino.spi.type.SqlVarbinary) VarbinaryType(io.trino.spi.type.VarbinaryType) Varchars.truncateToLength(io.trino.spi.type.Varchars.truncateToLength) CharType(io.trino.spi.type.CharType) TINYINT(io.trino.spi.type.TinyintType.TINYINT) BlockBuilder(io.trino.spi.block.BlockBuilder) FloatWritable(org.apache.hadoop.io.FloatWritable) RecordWriter(org.apache.hadoop.hive.ql.exec.FileSinkOperator.RecordWriter) OrcFile(org.apache.hadoop.hive.ql.io.orc.OrcFile) DateTimeTestingUtils.sqlTimestampOf(io.trino.testing.DateTimeTestingUtils.sqlTimestampOf) TestingOrcPredicate.createOrcPredicate(io.trino.orc.TestingOrcPredicate.createOrcPredicate) LongWritable(org.apache.hadoop.io.LongWritable) Timestamps.roundDiv(io.trino.spi.type.Timestamps.roundDiv) OrcSerde(org.apache.hadoop.hive.ql.io.orc.OrcSerde) SqlTimestamp(io.trino.spi.type.SqlTimestamp) TimestampWritableV2(org.apache.hadoop.hive.serde2.io.TimestampWritableV2) Block(io.trino.spi.block.Block) OrcConf(org.apache.orc.OrcConf) RecordReader(org.apache.hadoop.hive.ql.io.orc.RecordReader) Path(org.apache.hadoop.fs.Path) Reader(org.apache.hadoop.hive.ql.io.orc.Reader) INTEGER(io.trino.spi.type.IntegerType.INTEGER) ShortWritable(org.apache.hadoop.hive.serde2.io.ShortWritable) RowType(io.trino.spi.type.RowType) ImmutableSet(com.google.common.collect.ImmutableSet) DateWritableV2(org.apache.hadoop.hive.serde2.io.DateWritableV2) ImmutableMap(com.google.common.collect.ImmutableMap) SESSION(io.trino.testing.TestingConnectorSession.SESSION) MICROSECONDS_PER_SECOND(io.trino.spi.type.Timestamps.MICROSECONDS_PER_SECOND) ArrayType(io.trino.spi.type.ArrayType) StructObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector) SqlDate(io.trino.spi.type.SqlDate) Objects(java.util.Objects) TIMESTAMP_NANOS(io.trino.spi.type.TimestampType.TIMESTAMP_NANOS) SqlTimestampWithTimeZone(io.trino.spi.type.SqlTimestampWithTimeZone) DataSize(io.airlift.units.DataSize) List(java.util.List) BIGINT(io.trino.spi.type.BigintType.BIGINT) Decimals(io.trino.spi.type.Decimals) Entry(java.util.Map.Entry) Optional(java.util.Optional) READ_COLUMN_IDS_CONF_STR(org.apache.hadoop.hive.serde2.ColumnProjectionUtils.READ_COLUMN_IDS_CONF_STR) OrcOutputFormat(org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat) DecimalType(io.trino.spi.type.DecimalType) IntStream(java.util.stream.IntStream) ORC_11(io.trino.orc.OrcTester.Format.ORC_11) TypeInfoFactory.getCharTypeInfo(org.apache.hadoop.hive.serde2.typeinfo.TypeInfoFactory.getCharTypeInfo) Assert.assertNull(org.testng.Assert.assertNull) AggregatedMemoryContext.newSimpleAggregatedMemoryContext(io.trino.memory.context.AggregatedMemoryContext.newSimpleAggregatedMemoryContext) PrimitiveObjectInspectorFactory.javaBooleanObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaBooleanObjectInspector) PICOSECONDS_PER_NANOSECOND(io.trino.spi.type.Timestamps.PICOSECONDS_PER_NANOSECOND) Type(io.trino.spi.type.Type) Assert.assertEquals(org.testng.Assert.assertEquals) HashMap(java.util.HashMap) DoubleWritable(org.apache.hadoop.io.DoubleWritable) ZSTD(io.trino.orc.metadata.CompressionKind.ZSTD) PrimitiveObjectInspectorFactory.getPrimitiveJavaObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.getPrimitiveJavaObjectInspector) VarcharType(io.trino.spi.type.VarcharType) ImmutableList(com.google.common.collect.ImmutableList) Chars.truncateToLengthAndTrimSpaces(io.trino.spi.type.Chars.truncateToLengthAndTrimSpaces) ByteWritable(org.apache.hadoop.io.ByteWritable) RowFieldName(io.trino.spi.type.RowFieldName) BytesWritable(org.apache.hadoop.io.BytesWritable) SNAPPY(io.trino.orc.metadata.CompressionKind.SNAPPY) ObjectInspectorFactory.getStandardMapObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory.getStandardMapObjectInspector) ORC_12(io.trino.orc.OrcTester.Format.ORC_12) Iterator(java.util.Iterator) Timestamp(org.apache.hadoop.hive.common.type.Timestamp) Iterators.advance(com.google.common.collect.Iterators.advance) LongTimestamp(io.trino.spi.type.LongTimestamp) NANOSECONDS_PER_MILLISECOND(io.trino.spi.type.Timestamps.NANOSECONDS_PER_MILLISECOND) ObjectInspectorFactory.getStandardListObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory.getStandardListObjectInspector) JobConf(org.apache.hadoop.mapred.JobConf) Collectors.toList(java.util.stream.Collectors.toList) Serializer(org.apache.hadoop.hive.serde2.Serializer) LZ4(io.trino.orc.metadata.CompressionKind.LZ4) HiveDecimal(org.apache.hadoop.hive.common.type.HiveDecimal) Assert.assertTrue(org.testng.Assert.assertTrue) PrimitiveObjectInspectorFactory.javaStringObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory.javaStringObjectInspector) HiveDecimalWritable(org.apache.hadoop.hive.serde2.io.HiveDecimalWritable) VarcharType(io.trino.spi.type.VarcharType) HashMap(java.util.HashMap) HiveChar(org.apache.hadoop.hive.common.type.HiveChar) SqlVarbinary(io.trino.spi.type.SqlVarbinary) Lists.newArrayList(com.google.common.collect.Lists.newArrayList) ArrayList(java.util.ArrayList) RowType(io.trino.spi.type.RowType) SqlTimestamp(io.trino.spi.type.SqlTimestamp) MapType(io.trino.spi.type.MapType) ArrayType(io.trino.spi.type.ArrayType) Arrays.asList(java.util.Arrays.asList) ImmutableList.toImmutableList(com.google.common.collect.ImmutableList.toImmutableList) Lists.newArrayList(com.google.common.collect.Lists.newArrayList) ArrayList(java.util.ArrayList) List(java.util.List) ImmutableList(com.google.common.collect.ImmutableList) Collectors.toList(java.util.stream.Collectors.toList) TimestampWithTimeZoneType(io.trino.spi.type.TimestampWithTimeZoneType) OrcType(io.trino.orc.metadata.OrcType) MapType(io.trino.spi.type.MapType) VarbinaryType(io.trino.spi.type.VarbinaryType) CharType(io.trino.spi.type.CharType) RowType(io.trino.spi.type.RowType) ArrayType(io.trino.spi.type.ArrayType) DecimalType(io.trino.spi.type.DecimalType) Type(io.trino.spi.type.Type) VarcharType(io.trino.spi.type.VarcharType) SqlTimestampWithTimeZone(io.trino.spi.type.SqlTimestampWithTimeZone) DecimalType(io.trino.spi.type.DecimalType) CharType(io.trino.spi.type.CharType) Map(java.util.Map) ImmutableMap(com.google.common.collect.ImmutableMap) HashMap(java.util.HashMap)

Aggregations

INTEGER (io.trino.spi.type.IntegerType.INTEGER)29 ImmutableList (com.google.common.collect.ImmutableList)27 Optional (java.util.Optional)24 Type (io.trino.spi.type.Type)22 List (java.util.List)20 ImmutableMap (com.google.common.collect.ImmutableMap)19 BIGINT (io.trino.spi.type.BigintType.BIGINT)19 DOUBLE (io.trino.spi.type.DoubleType.DOUBLE)16 Map (java.util.Map)16 Test (org.testng.annotations.Test)16 String.format (java.lang.String.format)14 ImmutableSet (com.google.common.collect.ImmutableSet)12 VARCHAR (io.trino.spi.type.VarcharType.VARCHAR)11 ImmutableList.toImmutableList (com.google.common.collect.ImmutableList.toImmutableList)10 Page (io.trino.spi.Page)10 Slice (io.airlift.slice.Slice)9 Assert.assertEquals (org.testng.Assert.assertEquals)9 Assert.assertFalse (org.testng.Assert.assertFalse)9 RowType (io.trino.spi.type.RowType)8 Session (io.trino.Session)7