This is an automated email from the ASF dual-hosted git repository.
zhangbutao pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/hive.git
The following commit(s) were added to refs/heads/master by this push:
new 35b8ab30d12 HIVE-29133: Support Z-order indexing for Iceberg tables
via CREATE TABLE DDL (#6095)
35b8ab30d12 is described below
commit 35b8ab30d12bd62bb1f0c8a9add00ef35eb16c6a
Author: kokila-19 <[email protected]>
AuthorDate: Thu Oct 16 13:14:21 2025 +0530
HIVE-29133: Support Z-order indexing for Iceberg tables via CREATE TABLE
DDL (#6095)
- Supported WRITE LOCALLY ZORDER BY (col1, col2, ...) syntax in CREATE
TABLE to enable Z-order sort.
- Persisted Z-order information in HMS for iceberg tables using sort.order
and sort.columns.
- Implemented GenericUDFIcebergZorder UDF (iceberg_zorder) to compute
Z-order values and sort data in ascending order.
- Ensured INSERT operations respect Z-order sorting.
---
.../org/apache/iceberg/mr/InputFormatConfig.java | 3 +
.../iceberg/mr/hive/BaseHiveIcebergMetaHook.java | 88 ++-
.../iceberg/mr/hive/HiveIcebergStorageHandler.java | 60 ++
.../mr/hive/udf/GenericUDFIcebergZorder.java | 175 ++++++
.../iceberg_create_locally_zordered_table.q | 110 ++++
.../iceberg_create_locally_zordered_table.q.out | 608 +++++++++++++++++++++
.../test/resources/testconfiguration.properties | 2 +
.../apache/hadoop/hive/ql/parse/CreateDDLParser.g | 13 +-
.../apache/hadoop/hive/ql/parse/HiveLexerParent.g | 1 +
.../org/apache/hadoop/hive/ql/parse/HiveParser.g | 10 +
.../hadoop/hive/ql/parse/IdentifiersParser.g | 1 +
.../hive/ql/ddl/misc/sortoder/ZOrderFieldDesc.java | 44 ++
.../hive/ql/ddl/misc/sortoder/ZOrderFields.java | 47 ++
.../ql/ddl/table/create/CreateTableAnalyzer.java | 28 +
.../hadoop/hive/ql/exec/FunctionRegistry.java | 2 +
.../clientpositive/llap/show_functions.q.out | 2 +
16 files changed, 1176 insertions(+), 18 deletions(-)
diff --git
a/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/InputFormatConfig.java
b/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/InputFormatConfig.java
index 823c7a37ba3..d20fb0c1753 100644
---
a/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/InputFormatConfig.java
+++
b/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/InputFormatConfig.java
@@ -78,6 +78,9 @@ private InputFormatConfig() {
public static final String CATALOG_CONFIG_PREFIX = "iceberg.catalog.";
+ public static final String SORT_ORDER = "sort.order";
+ public static final String SORT_COLUMNS = "sort.columns";
+
public enum InMemoryDataModel {
HIVE,
GENERIC // Default data model is of Iceberg Generics
diff --git
a/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/BaseHiveIcebergMetaHook.java
b/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/BaseHiveIcebergMetaHook.java
index 58fd7a7bd58..021738bb82a 100644
---
a/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/BaseHiveIcebergMetaHook.java
+++
b/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/BaseHiveIcebergMetaHook.java
@@ -19,6 +19,7 @@
package org.apache.iceberg.mr.hive;
+import com.fasterxml.jackson.databind.JsonNode;
import com.fasterxml.jackson.databind.ObjectMapper;
import java.util.Arrays;
import java.util.Collection;
@@ -41,6 +42,8 @@
import org.apache.hadoop.hive.metastore.api.hive_metastoreConstants;
import org.apache.hadoop.hive.ql.ddl.misc.sortoder.SortFieldDesc;
import org.apache.hadoop.hive.ql.ddl.misc.sortoder.SortFields;
+import org.apache.hadoop.hive.ql.ddl.misc.sortoder.ZOrderFieldDesc;
+import org.apache.hadoop.hive.ql.ddl.misc.sortoder.ZOrderFields;
import org.apache.hadoop.hive.ql.util.NullOrdering;
import org.apache.iceberg.BaseMetastoreTableOperations;
import org.apache.iceberg.BaseTable;
@@ -74,6 +77,8 @@
import org.slf4j.LoggerFactory;
import static org.apache.iceberg.RowLevelOperationMode.MERGE_ON_READ;
+import static org.apache.iceberg.mr.InputFormatConfig.SORT_COLUMNS;
+import static org.apache.iceberg.mr.InputFormatConfig.SORT_ORDER;
public class BaseHiveIcebergMetaHook implements HiveMetaHook {
private static final Logger LOG =
LoggerFactory.getLogger(BaseHiveIcebergMetaHook.class);
@@ -217,28 +222,83 @@ private void validateCatalogConfigsDefined() {
}
}
+ /**
+ * Persists the table's write sort order based on the HMS property
'default-sort-order'
+ * that is populated by the DDL layer.
+ * <p>
+ * Behaviour:
+ * - If the JSON represents Z-order, we remove DEFAULT_SORT_ORDER
+ * as Iceberg does not have Z-order support in its spec.
+ * So, we persist Z-order metadata in {@link
org.apache.iceberg.mr.InputFormatConfig#SORT_ORDER}
+ * and {@link org.apache.iceberg.mr.InputFormatConfig#SORT_COLUMNS} to be
used by Hive Writer.
+ * <p>
+ * - Otherwise, the JSON is a list of SortFields; we convert it to Iceberg
+ * SortOrder JSON and keep it in DEFAULT_SORT_ORDER for Iceberg to use it.
+ */
private void setSortOrder(org.apache.hadoop.hive.metastore.api.Table
hmsTable, Schema schema,
Properties properties) {
- String sortOderJSONString =
hmsTable.getParameters().get(TableProperties.DEFAULT_SORT_ORDER);
- SortFields sortFields = null;
- if (!Strings.isNullOrEmpty(sortOderJSONString)) {
- try {
- sortFields = JSON_OBJECT_MAPPER.reader().readValue(sortOderJSONString,
SortFields.class);
- } catch (Exception e) {
- LOG.warn("Can not read write order json: {}", sortOderJSONString, e);
- return;
- }
+ String sortOrderJSONString =
hmsTable.getParameters().get(TableProperties.DEFAULT_SORT_ORDER);
+ if (Strings.isNullOrEmpty(sortOrderJSONString)) {
+ return;
+ }
+
+ if (isZOrderJSON(sortOrderJSONString)) {
+ properties.remove(TableProperties.DEFAULT_SORT_ORDER);
+ setZOrderSortOrder(sortOrderJSONString, properties);
+ return;
+ }
+
+ try {
+ SortFields sortFields =
JSON_OBJECT_MAPPER.reader().readValue(sortOrderJSONString, SortFields.class);
if (sortFields != null && !sortFields.getSortFields().isEmpty()) {
- SortOrder.Builder sortOderBuilder = SortOrder.builderFor(schema);
+ SortOrder.Builder sortOrderBuilder = SortOrder.builderFor(schema);
sortFields.getSortFields().forEach(fieldDesc -> {
NullOrder nullOrder = fieldDesc.getNullOrdering() ==
NullOrdering.NULLS_FIRST ?
- NullOrder.NULLS_FIRST : NullOrder.NULLS_LAST;
+ NullOrder.NULLS_FIRST : NullOrder.NULLS_LAST;
SortDirection sortDirection = fieldDesc.getDirection() ==
SortFieldDesc.SortDirection.ASC ?
- SortDirection.ASC : SortDirection.DESC;
- sortOderBuilder.sortBy(fieldDesc.getColumnName(), sortDirection,
nullOrder);
+ SortDirection.ASC : SortDirection.DESC;
+ sortOrderBuilder.sortBy(fieldDesc.getColumnName(), sortDirection,
nullOrder);
});
- properties.put(TableProperties.DEFAULT_SORT_ORDER,
SortOrderParser.toJson(sortOderBuilder.build()));
+ properties.put(TableProperties.DEFAULT_SORT_ORDER,
SortOrderParser.toJson(sortOrderBuilder.build()));
}
+ } catch (Exception e) {
+ LOG.warn("Can not read write order json: {}", sortOrderJSONString);
+ }
+ }
+
+ /**
+ * Configures the Z-order sort order metadata in the given properties
+ * based on the specified Z-order fields.
+ *
+ * @param jsonString the JSON string representing sort orders
+ * @param properties the Properties object to store sort order metadata
+ */
+ private void setZOrderSortOrder(String jsonString, Properties properties) {
+ try {
+ ZOrderFields zorderFields =
JSON_OBJECT_MAPPER.reader().readValue(jsonString, ZOrderFields.class);
+ if (zorderFields != null && !zorderFields.getZOrderFields().isEmpty()) {
+ List<String> columnNames = zorderFields.getZOrderFields().stream()
+ .map(ZOrderFieldDesc::getColumnName)
+ .collect(Collectors.toList());
+
+ LOG.info("Setting Z-order sort order for columns: {}", columnNames);
+
+ properties.put(SORT_ORDER, "ZORDER");
+ properties.put(SORT_COLUMNS, String.join(",", columnNames));
+
+ LOG.info("Z-order sort order configured for Iceberg table with
columns: {}", columnNames);
+ }
+ } catch (Exception e) {
+ LOG.warn("Failed to parse Z-order sort order", e);
+ }
+ }
+
+ private boolean isZOrderJSON(String jsonString) {
+ try {
+ JsonNode node = JSON_OBJECT_MAPPER.readTree(jsonString);
+ return node.has("zorderFields");
+ } catch (Exception e) {
+ return false;
}
}
diff --git
a/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/HiveIcebergStorageHandler.java
b/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/HiveIcebergStorageHandler.java
index c6e80626c7f..2674aa2aac4 100644
---
a/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/HiveIcebergStorageHandler.java
+++
b/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/HiveIcebergStorageHandler.java
@@ -82,6 +82,7 @@
import org.apache.hadoop.hive.ql.ddl.table.create.like.CreateTableLikeDesc;
import
org.apache.hadoop.hive.ql.ddl.table.misc.properties.AlterTableSetPropertiesDesc;
import org.apache.hadoop.hive.ql.exec.ColumnInfo;
+import org.apache.hadoop.hive.ql.exec.UDFArgumentException;
import org.apache.hadoop.hive.ql.exec.Utilities;
import org.apache.hadoop.hive.ql.hooks.WriteEntity;
import org.apache.hadoop.hive.ql.io.IOConstants;
@@ -119,6 +120,7 @@
import org.apache.hadoop.hive.ql.session.SessionState;
import org.apache.hadoop.hive.ql.session.SessionStateUtil;
import org.apache.hadoop.hive.ql.stats.Partish;
+import org.apache.hadoop.hive.ql.udf.generic.GenericUDF;
import org.apache.hadoop.hive.ql.util.NullOrdering;
import org.apache.hadoop.hive.serde2.AbstractSerDe;
import org.apache.hadoop.hive.serde2.Deserializer;
@@ -184,6 +186,7 @@
import org.apache.iceberg.mr.InputFormatConfig;
import org.apache.iceberg.mr.hive.actions.HiveIcebergDeleteOrphanFiles;
import org.apache.iceberg.mr.hive.plan.IcebergBucketFunction;
+import org.apache.iceberg.mr.hive.udf.GenericUDFIcebergZorder;
import org.apache.iceberg.puffin.Blob;
import org.apache.iceberg.puffin.BlobMetadata;
import org.apache.iceberg.puffin.Puffin;
@@ -218,6 +221,8 @@
import static org.apache.iceberg.SnapshotSummary.TOTAL_FILE_SIZE_PROP;
import static org.apache.iceberg.SnapshotSummary.TOTAL_POS_DELETES_PROP;
import static org.apache.iceberg.SnapshotSummary.TOTAL_RECORDS_PROP;
+import static org.apache.iceberg.mr.InputFormatConfig.SORT_COLUMNS;
+import static org.apache.iceberg.mr.InputFormatConfig.SORT_ORDER;
public class HiveIcebergStorageHandler extends DefaultStorageHandler
implements HiveStoragePredicateHandler {
private static final Logger LOG =
LoggerFactory.getLogger(HiveIcebergStorageHandler.class);
@@ -929,9 +934,64 @@ public DynamicPartitionCtx createDPContext(
addCustomSortExpr(table, hmsTable, writeOperation, dpCtx,
getSortTransformSpec(table));
}
+ // Even if table has no explicit sort order, honor z-order if configured
+ Map<String, String> props = table.properties();
+ if ("ZORDER".equalsIgnoreCase(props.getOrDefault(SORT_ORDER, ""))) {
+ createZOrderCustomSort(props, dpCtx, table, hmsTable, writeOperation);
+ }
+
return dpCtx;
}
+ /**
+ * Adds a custom sort expression to the DynamicPartitionCtx that performs
local Z-ordering on write.
+ *
+ * Behavior:
+ * - Reads Z-order properties from 'sort.order' and 'sort.columns'
(comma-separated).
+ * - Resolves the referenced columns to their positions in the physical row
(taking into account
+ * ACID virtual columns offset for overwrite/update operations).
+ * - Configures a single ASC sort key with NULLS FIRST and injects a custom
key expression for
+ * Z-order
+ */
+ private void createZOrderCustomSort(Map<String, String> props,
DynamicPartitionCtx dpCtx, Table table,
+ org.apache.hadoop.hive.ql.metadata.Table hmsTable, Operation
writeOperation) {
+ String colsProp = props.get(SORT_COLUMNS);
+ if (StringUtils.isNotBlank(colsProp)) {
+ List<String> zCols = Arrays.stream(colsProp.split(",")).map(String::trim)
+ .filter(s -> !s.isEmpty()).collect(Collectors.toList());
+
+ Map<String, Integer> fieldOrderMap = Maps.newHashMap();
+ List<Types.NestedField> fields = table.schema().columns();
+ for (int i = 0; i < fields.size(); ++i) {
+ fieldOrderMap.put(fields.get(i).name(), i);
+ }
+ int offset = (shouldOverwrite(hmsTable, writeOperation) ?
+ ACID_VIRTUAL_COLS_AS_FIELD_SCHEMA : acidSelectColumns(hmsTable,
writeOperation)).size();
+
+ List<Integer> zIndices = zCols.stream().map(col -> {
+ Integer base = fieldOrderMap.get(col);
+ Preconditions.checkArgument(base != null, "Z-order column not found in
schema: %s", col);
+ return base + offset;
+ }).collect(Collectors.toList());
+
+
dpCtx.setCustomSortOrder(Lists.newArrayList(Collections.singletonList(1)));
+
dpCtx.setCustomSortNullOrder(Lists.newArrayList(Collections.singletonList(NullOrdering.NULLS_FIRST.getCode())));
+
+ dpCtx.addCustomSortExpressions(Collections.singletonList(allCols -> {
+ List<ExprNodeDesc> args =
Lists.newArrayListWithExpectedSize(zIndices.size());
+ for (Integer idx : zIndices) {
+ args.add(allCols.get(idx));
+ }
+ try {
+ GenericUDF udf = new GenericUDFIcebergZorder();
+ return ExprNodeGenericFuncDesc.newInstance(udf, "iceberg_zorder",
args);
+ } catch (UDFArgumentException e) {
+ throw new RuntimeException(e);
+ }
+ }));
+ }
+ }
+
private void addCustomSortExpr(Table table,
org.apache.hadoop.hive.ql.metadata.Table hmsTable,
Operation writeOperation, DynamicPartitionCtx dpCtx,
List<TransformSpec> transformSpecs) {
diff --git
a/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/udf/GenericUDFIcebergZorder.java
b/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/udf/GenericUDFIcebergZorder.java
new file mode 100644
index 00000000000..92fb2b7c8b2
--- /dev/null
+++
b/iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/udf/GenericUDFIcebergZorder.java
@@ -0,0 +1,175 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.iceberg.mr.hive.udf;
+
+import java.nio.ByteBuffer;
+import java.nio.charset.StandardCharsets;
+import org.apache.hadoop.hive.ql.exec.Description;
+import org.apache.hadoop.hive.ql.exec.UDFArgumentException;
+import org.apache.hadoop.hive.ql.exec.UDFArgumentTypeException;
+import org.apache.hadoop.hive.ql.metadata.HiveException;
+import org.apache.hadoop.hive.ql.udf.generic.GenericUDF;
+import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
+import org.apache.hadoop.hive.serde2.objectinspector.PrimitiveObjectInspector;
+import
org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory;
+import org.apache.hadoop.io.BytesWritable;
+import org.apache.iceberg.util.ZOrderByteUtils;
+
+/**
+ * Hive UDF to compute the Z-order value of given input columns using
Iceberg's ZOrderByteUtils.
+ * Supports various primitive types and converts inputs into interleaved
binary representation.
+ */
+@Description(name = "iceberg_zorder",
+ value = "_FUNC_(value) - " +
+ "Returns the z-value calculated by Iceberg ZOrderByteUtils
class")
+public class GenericUDFIcebergZorder extends GenericUDF {
+ private PrimitiveObjectInspector[] argOIs;
+ // For variable-length types (e.g., strings), how many bytes contribute to
z-order
+ private final int varLengthContribution = 8;
+ private transient ByteBuffer[] reUseBuffer;
+ private static final int MAX_OUTPUT_SIZE = Integer.MAX_VALUE;
+ // Zero-filled byte array for representing NULL values
+ private static final byte[] NULL_ORDERED_BYTES = new
byte[ZOrderByteUtils.PRIMITIVE_BUFFER_SIZE];
+
+ /**
+ * Initializes the UDF, validating argument types are primitives and
preparing buffers.
+ */
+ @Override
+ public ObjectInspector initialize(ObjectInspector[] arguments) throws
UDFArgumentException {
+ if (arguments.length < 2) {
+ throw new UDFArgumentException("iceberg_zorder requires at least 2
arguments");
+ }
+ argOIs = new PrimitiveObjectInspector[arguments.length];
+ reUseBuffer = new ByteBuffer[arguments.length];
+ for (int i = 0; i < arguments.length; i++) {
+ if (!(arguments[i] instanceof PrimitiveObjectInspector poi)) {
+ throw new UDFArgumentTypeException(i, "Only primitive types supported
for z-order");
+ }
+ argOIs[i] = poi;
+ }
+ return PrimitiveObjectInspectorFactory.writableBinaryObjectInspector;
+ }
+
+ /**
+ * Evaluates the UDF by converting input values to ordered bytes,
interleaving them,
+ * and returning the resulting Z-order binary value.
+ */
+ @Override
+ public Object evaluate(DeferredObject[] arguments) throws HiveException {
+ byte[][] inputs = new byte[arguments.length][];
+ int totalLength = 0;
+
+ for (int i = 0; i < arguments.length; i++) {
+ byte[] orderedBytes = convertToOrderedBytes(arguments[i].get(),
argOIs[i], i);
+ inputs[i] = orderedBytes;
+ totalLength += orderedBytes.length;
+ }
+
+ int outputLength = Math.min(totalLength, MAX_OUTPUT_SIZE);
+ ByteBuffer buffer = ByteBuffer.allocate(outputLength);
+
+ byte[] interleaved = ZOrderByteUtils.interleaveBits(inputs, outputLength,
buffer);
+ return new BytesWritable(interleaved);
+ }
+
+ @Override
+ public String getDisplayString(String[] children) {
+ return "iceberg_zorder(" + String.join(", ", children) + ")";
+ }
+
+ /**
+ * Converts a single input value to its ordered byte representation based on
type.
+ * @return fixed-length byte arrays to be used in interleaving.
+ */
+ private byte[] convertToOrderedBytes(Object value, PrimitiveObjectInspector
oi,
+ int position) throws HiveException {
+ if (value == null) {
+ return NULL_ORDERED_BYTES;
+ }
+
+ if (reUseBuffer[position] == null) {
+ reUseBuffer[position] =
ByteBuffer.allocate(ZOrderByteUtils.PRIMITIVE_BUFFER_SIZE);
+ }
+ switch (oi.getPrimitiveCategory()) {
+ case BOOLEAN:
+ boolean boolValue = (Boolean) oi.getPrimitiveJavaObject(value);
+ return ZOrderByteUtils.intToOrderedBytes(boolValue ? 1 : 0,
reUseBuffer[position]).array();
+
+ case BYTE:
+ byte byteValue = (Byte) oi.getPrimitiveJavaObject(value);
+ return ZOrderByteUtils.tinyintToOrderedBytes(byteValue,
reUseBuffer[position]).array();
+
+ case SHORT:
+ short shortValue = (Short) oi.getPrimitiveJavaObject(value);
+ return ZOrderByteUtils.shortToOrderedBytes(shortValue,
reUseBuffer[position]).array();
+
+ case INT:
+ int intValue = (Integer) oi.getPrimitiveJavaObject(value);
+ return ZOrderByteUtils.intToOrderedBytes(intValue,
reUseBuffer[position]).array();
+
+ case LONG:
+ long longValue = (Long) oi.getPrimitiveJavaObject(value);
+ return ZOrderByteUtils.longToOrderedBytes(longValue,
reUseBuffer[position]).array();
+
+ case FLOAT:
+ float floatValue = (Float) oi.getPrimitiveJavaObject(value);
+ return ZOrderByteUtils.floatToOrderedBytes(floatValue,
reUseBuffer[position]).array();
+
+ case DOUBLE:
+ double doubleValue = (Double) oi.getPrimitiveJavaObject(value);
+ return ZOrderByteUtils.doubleToOrderedBytes(doubleValue,
reUseBuffer[position]).array();
+
+ case DATE:
+ // Convert DATE to epoch days (days since 1970-01-01 UTC)
+ Object dateValue = oi.getPrimitiveJavaObject(value);
+ long epochDays;
+ if (dateValue instanceof java.sql.Date dd) {
+ epochDays = dd.toLocalDate().toEpochDay();
+ } else if (dateValue instanceof
org.apache.hadoop.hive.common.type.Date dd) {
+ epochDays = dd.toEpochDay();
+ } else {
+ throw new HiveException("Unsupported DATE backing type: " +
dateValue.getClass());
+ }
+ return ZOrderByteUtils.longToOrderedBytes(epochDays,
reUseBuffer[position]).array();
+
+ case TIMESTAMP:
+ Object tsValue = oi.getPrimitiveJavaObject(value);
+ long tsInMillis;
+ if (tsValue instanceof org.apache.hadoop.hive.common.type.Timestamp
ts) {
+ tsInMillis = ts.toEpochMilli();
+ } else if (tsValue instanceof java.sql.Timestamp ts) {
+ tsInMillis = ts.getTime();
+ } else {
+ throw new HiveException("Unsupported TIMESTAMP backing type: " +
tsValue.getClass());
+ }
+ return ZOrderByteUtils.longToOrderedBytes(tsInMillis,
reUseBuffer[position]).array();
+
+ case CHAR:
+ case VARCHAR:
+ case STRING:
+ String strVal = String.valueOf(oi.getPrimitiveJavaObject(value));
+ return ZOrderByteUtils.stringToOrderedBytes(strVal,
varLengthContribution,
+ reUseBuffer[position],
StandardCharsets.UTF_8.newEncoder()).array();
+
+ default:
+ throw new HiveException("Unsupported type in z-order: " +
oi.getPrimitiveCategory());
+ }
+ }
+}
diff --git
a/iceberg/iceberg-handler/src/test/queries/positive/iceberg_create_locally_zordered_table.q
b/iceberg/iceberg-handler/src/test/queries/positive/iceberg_create_locally_zordered_table.q
new file mode 100644
index 00000000000..88c98abeabb
--- /dev/null
+++
b/iceberg/iceberg-handler/src/test/queries/positive/iceberg_create_locally_zordered_table.q
@@ -0,0 +1,110 @@
+-- Mask neededVirtualColumns due to non-strict order
+--! qt:replace:/(\s+neededVirtualColumns:\s)(.*)/$1#Masked#/
+-- Mask the totalSize value as it can have slight variability, causing test
flakiness
+--! qt:replace:/(\s+totalSize\s+)\S+(\s+)/$1#Masked#$2/
+-- Mask random uuid
+--! qt:replace:/(\s+uuid\s+)\S+(\s*)/$1#Masked#$2/
+-- Mask a random snapshot id
+--! qt:replace:/(\s+current-snapshot-id\s+)\S+(\s*)/$1#Masked#/
+-- Mask added file size
+--! qt:replace:/(\S\"added-files-size\\\":\\\")(\d+)(\\\")/$1#Masked#$3/
+-- Mask total file size
+--! qt:replace:/(\S\"total-files-size\\\":\\\")(\d+)(\\\")/$1#Masked#$3/
+-- Mask removed file size
+--! qt:replace:/(\S\"removed-files-size\\\":\\\")(\d+)(\\\")/$1#Masked#$3/
+-- Mask current-snapshot-timestamp-ms
+--! qt:replace:/(\s+current-snapshot-timestamp-ms\s+)\S+(\s*)/$1#Masked#$2/
+--!
qt:replace:/(MAJOR\s+succeeded\s+)[a-zA-Z0-9\-\.\s+]+(\s+manual)/$1#Masked#$2/
+-- Mask iceberg version
+--!
qt:replace:/(\S\"iceberg-version\\\":\\\")(\w+\s\w+\s\d+\.\d+\.\d+\s\(\w+\s\w+\))(\\\")/$1#Masked#$3/
+set hive.llap.io.enabled=true;
+set hive.vectorized.execution.enabled=true;
+set hive.optimize.shared.work.merge.ts.schema=true;
+
+-- Validates z-order on CREATE via clause.
+CREATE TABLE default.zorder_it_nulls (
+ id int,
+ text string)
+WRITE LOCALLY ZORDER by (id, text)
+STORED BY iceberg
+STORED As orc;
+
+DESCRIBE FORMATTED default.zorder_it_nulls;
+EXPLAIN INSERT INTO default.zorder_it_nulls VALUES (3, "3"),(2, "2"),(4,
"4"),(5, "5"),(1, "1"),(2, "3"),(3,null),(2,null),(null,"a");
+INSERT INTO default.zorder_it_nulls VALUES
+ (3, "3"),
+ (2, "2"),
+ (4, "4"),
+ (5, "5"),
+ (1, "1"),
+ (2, "3"),
+ (3,null),
+ (2,null),
+ (null,"a");
+
+SELECT * FROM default.zorder_it_nulls;
+DROP TABLE default.zorder_it_nulls;
+
+
+CREATE TABLE default.zorder_dit (
+ id int,
+ text string,
+ bool_val boolean,
+ date_val date)
+WRITE LOCALLY ZORDER by (date_val, id, text)
+STORED BY iceberg
+STORED As orc;
+
+DESCRIBE FORMATTED default.zorder_dit;
+INSERT INTO default.zorder_dit VALUES
+ (0, 'a', false, DATE '2023-01-01'),
+ (255, 'z', true, DATE '2025-12-31'),
+ (0, 'z', false, DATE '2025-12-31'),
+ (255, 'a', true, DATE '2023-01-01'),
+ (128, 'm', true, DATE '2024-06-01'),
+ (64, 'c', false, DATE '2023-06-01'),
+ (192, 'x', true, DATE '2025-01-01'),
+ (32, 'b', true, DATE '2023-03-01'),
+ (96, 'd', false, DATE '2023-09-01'),
+ (160, 'v', true, DATE '2024-09-01');
+
+SELECT * FROM default.zorder_dit;
+DROP TABLE default.zorder_dit;
+
+CREATE TABLE default.zorder_tsdl (
+ ts timestamp,
+ dd double,
+ ll bigint)
+WRITE LOCALLY ZORDER by (ts, dd, ll)
+STORED BY iceberg
+STORED As orc;
+
+DESCRIBE FORMATTED default.zorder_tsdl;
+INSERT INTO default.zorder_tsdl VALUES
+ (TIMESTAMP '2022-01-01 00:00:00', 0.0, 0),
+ (TIMESTAMP '2030-12-31 23:59:59', 9999.99, 9999999),
+ (TIMESTAMP '2022-01-01 00:00:00', 9999.99, 9999999),
+ (TIMESTAMP '2030-12-31 23:59:59', 0.0, 0),
+ (TIMESTAMP '2026-06-15 12:00:00', 5000.5, 5000000),
+ (TIMESTAMP '2023-03-03 03:03:03', 9999.99, 0),
+ (TIMESTAMP '2023-03-03 03:03:03', 0.0, 9999999),
+ (TIMESTAMP '2025-05-05 05:05:05', 250.25, 54321),
+ (TIMESTAMP '2027-07-07 07:07:07', 8000.8, 8888888),
+ (TIMESTAMP '2024-04-04 04:04:04', 1000.1, 123456);
+
+SELECT * FROM default.zorder_tsdl;
+DROP TABLE default.zorder_tsdl;
+
+-- Validates z-order on CREATE via clause and via TBLPROPERTIES.
+CREATE TABLE default.zorder_props(id int, text string)
+STORED BY iceberg
+STORED As orc
+TBLPROPERTIES ("sort.order" = "zorder", "sort.columns" = "id,text");
+
+INSERT INTO default.zorder_props VALUES (3, 'B'),(1, 'A'),(7, 'C'),(2,
'A'),(9, 'B'),(6, 'C'),(4, 'A'),
+ (10, 'C'),(5, NULL),(8, 'B'),(NULL, 'A'),(12, 'C'),(11, 'A'),(13, NULL),
+ (14, 'B'),(15, 'C'),(16, 'A'),(19, 'B'),(17, 'C'),(18, 'A');
+
+DESCRIBE FORMATTED default.zorder_props;
+SELECT * FROM default.zorder_props;
+DROP TABLE default.zorder_props;
diff --git
a/iceberg/iceberg-handler/src/test/results/positive/llap/iceberg_create_locally_zordered_table.q.out
b/iceberg/iceberg-handler/src/test/results/positive/llap/iceberg_create_locally_zordered_table.q.out
new file mode 100644
index 00000000000..d54bf0daef8
--- /dev/null
+++
b/iceberg/iceberg-handler/src/test/results/positive/llap/iceberg_create_locally_zordered_table.q.out
@@ -0,0 +1,608 @@
+PREHOOK: query: CREATE TABLE default.zorder_it_nulls (
+ id int,
+ text string)
+WRITE LOCALLY ZORDER by (id, text)
+STORED BY iceberg
+STORED As orc
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@zorder_it_nulls
+POSTHOOK: query: CREATE TABLE default.zorder_it_nulls (
+ id int,
+ text string)
+WRITE LOCALLY ZORDER by (id, text)
+STORED BY iceberg
+STORED As orc
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@zorder_it_nulls
+PREHOOK: query: DESCRIBE FORMATTED default.zorder_it_nulls
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@zorder_it_nulls
+POSTHOOK: query: DESCRIBE FORMATTED default.zorder_it_nulls
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@zorder_it_nulls
+# col_name data_type comment
+id int
+text string
+
+# Detailed Table Information
+Database: default
+#### A masked pattern was here ####
+Retention: 0
+#### A masked pattern was here ####
+Table Type: EXTERNAL_TABLE
+Table Parameters:
+ COLUMN_STATS_ACCURATE
{\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"id\":\"true\",\"text\":\"true\"}}
+ EXTERNAL TRUE
+ bucketing_version 2
+ current-schema
{\"type\":\"struct\",\"schema-id\":0,\"fields\":[{\"id\":1,\"name\":\"id\",\"required\":false,\"type\":\"int\"},{\"id\":2,\"name\":\"text\",\"required\":false,\"type\":\"string\"}]}
+ format-version 2
+ iceberg.orc.files.only true
+#### A masked pattern was here ####
+ numFiles 0
+ numRows 0
+ parquet.compression zstd
+ rawDataSize 0
+ serialization.format 1
+ snapshot-count 0
+ sort.columns id,text
+ sort.order ZORDER
+ storage_handler
org.apache.iceberg.mr.hive.HiveIcebergStorageHandler
+ table_type ICEBERG
+ totalSize #Masked#
+#### A masked pattern was here ####
+ uuid #Masked#
+ write.delete.mode merge-on-read
+ write.format.default orc
+ write.merge.mode merge-on-read
+ write.update.mode merge-on-read
+
+# Storage Information
+SerDe Library: org.apache.iceberg.mr.hive.HiveIcebergSerDe
+InputFormat: org.apache.iceberg.mr.hive.HiveIcebergInputFormat
+OutputFormat: org.apache.iceberg.mr.hive.HiveIcebergOutputFormat
+Compressed: No
+Sort Columns: []
+PREHOOK: query: EXPLAIN INSERT INTO default.zorder_it_nulls VALUES (3,
"3"),(2, "2"),(4, "4"),(5, "5"),(1, "1"),(2, "3"),(3,null),(2,null),(null,"a")
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@zorder_it_nulls
+POSTHOOK: query: EXPLAIN INSERT INTO default.zorder_it_nulls VALUES (3,
"3"),(2, "2"),(4, "4"),(5, "5"),(1, "1"),(2, "3"),(3,null),(2,null),(null,"a")
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@zorder_it_nulls
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: _dummy_table
+ Row Limit Per Split: 1
+ Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE
Column stats: COMPLETE
+ Select Operator
+ expressions: array(const struct(3,'3'),const
struct(2,'2'),const struct(4,'4'),const struct(5,'5'),const struct(1,'1'),const
struct(2,'3'),const struct(3,null),const struct(2,null),const struct(null,'a'))
(type: array<struct<col1:int,col2:string>>)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 112 Basic stats:
COMPLETE Column stats: COMPLETE
+ UDTF Operator
+ Statistics: Num rows: 1 Data size: 112 Basic stats:
COMPLETE Column stats: COMPLETE
+ function name: inline
+ Select Operator
+ expressions: col1 (type: int), col2 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 8 Basic stats:
COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: iceberg_zorder(_col0, _col1) (type:
binary)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: iceberg_zorder(_col0,
_col1) (type: binary)
+ Statistics: Num rows: 1 Data size: 8 Basic stats:
COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int), _col1 (type:
string)
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: id, text
+ Statistics: Num rows: 1 Data size: 8 Basic stats:
COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: min(id), max(id), count(1),
count(id), compute_bit_vector_hll(id), max(length(text)),
avg(COALESCE(length(text),0)), count(text), compute_bit_vector_hll(text)
+ minReductionHashAggr: 0.4
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3,
_col4, _col5, _col6, _col7, _col8
+ Statistics: Num rows: 1 Data size: 400 Basic
stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 400 Basic
stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int), _col1
(type: int), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: binary),
_col5 (type: int), _col6 (type: struct<count:bigint,sum:double,input:int>),
_col7 (type: bigint), _col8 (type: binary)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: int), VALUE._col1 (type:
string), KEY.iceberg_zorder(_col0, _col1) (type: binary)
+ outputColumnNames: _col0, _col1, iceberg_zorder(_col0, _col1)
+ File Output Operator
+ compressed: false
+ Dp Sort State: PARTITION_SORTED
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE
Column stats: COMPLETE
+ table:
+ input format:
org.apache.iceberg.mr.hive.HiveIcebergInputFormat
+ output format:
org.apache.iceberg.mr.hive.HiveIcebergOutputFormat
+ serde: org.apache.iceberg.mr.hive.HiveIcebergSerDe
+ name: default.zorder_it_nulls
+ Reducer 3
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0), max(VALUE._col1),
count(VALUE._col2), count(VALUE._col3), compute_bit_vector_hll(VALUE._col4),
max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7),
compute_bit_vector_hll(VALUE._col8)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5,
_col6, _col7, _col8
+ Statistics: Num rows: 1 Data size: 332 Basic stats: COMPLETE
Column stats: COMPLETE
+ Select Operator
+ expressions: 'LONG' (type: string), UDFToLong(_col0) (type:
bigint), UDFToLong(_col1) (type: bigint), (_col2 - _col3) (type: bigint),
COALESCE(ndv_compute_bit_vector(_col4),0) (type: bigint), _col4 (type: binary),
'STRING' (type: string), UDFToLong(COALESCE(_col5,0)) (type: bigint),
COALESCE(_col6,0) (type: double), (_col2 - _col7) (type: bigint),
COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5,
_col6, _col7, _col8, _col9, _col10, _col11
+ Statistics: Num rows: 1 Data size: 530 Basic stats: COMPLETE
Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 530 Basic stats:
COMPLETE Column stats: COMPLETE
+ table:
+ input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde:
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: false
+ table:
+ input format: org.apache.iceberg.mr.hive.HiveIcebergInputFormat
+ output format: org.apache.iceberg.mr.hive.HiveIcebergOutputFormat
+ serde: org.apache.iceberg.mr.hive.HiveIcebergSerDe
+ name: default.zorder_it_nulls
+
+ Stage: Stage-3
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: id, text
+ Column Types: int, string
+ Table: default.zorder_it_nulls
+
+PREHOOK: query: INSERT INTO default.zorder_it_nulls VALUES
+ (3, "3"),
+ (2, "2"),
+ (4, "4"),
+ (5, "5"),
+ (1, "1"),
+ (2, "3"),
+ (3,null),
+ (2,null),
+ (null,"a")
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@zorder_it_nulls
+POSTHOOK: query: INSERT INTO default.zorder_it_nulls VALUES
+ (3, "3"),
+ (2, "2"),
+ (4, "4"),
+ (5, "5"),
+ (1, "1"),
+ (2, "3"),
+ (3,null),
+ (2,null),
+ (null,"a")
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@zorder_it_nulls
+PREHOOK: query: SELECT * FROM default.zorder_it_nulls
+PREHOOK: type: QUERY
+PREHOOK: Input: default@zorder_it_nulls
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM default.zorder_it_nulls
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@zorder_it_nulls
+#### A masked pattern was here ####
+NULL a
+2 NULL
+3 NULL
+1 1
+2 2
+2 3
+3 3
+4 4
+5 5
+PREHOOK: query: DROP TABLE default.zorder_it_nulls
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@zorder_it_nulls
+PREHOOK: Output: database:default
+PREHOOK: Output: default@zorder_it_nulls
+POSTHOOK: query: DROP TABLE default.zorder_it_nulls
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@zorder_it_nulls
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@zorder_it_nulls
+PREHOOK: query: CREATE TABLE default.zorder_dit (
+ id int,
+ text string,
+ bool_val boolean,
+ date_val date)
+WRITE LOCALLY ZORDER by (date_val, id, text)
+STORED BY iceberg
+STORED As orc
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@zorder_dit
+POSTHOOK: query: CREATE TABLE default.zorder_dit (
+ id int,
+ text string,
+ bool_val boolean,
+ date_val date)
+WRITE LOCALLY ZORDER by (date_val, id, text)
+STORED BY iceberg
+STORED As orc
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@zorder_dit
+PREHOOK: query: DESCRIBE FORMATTED default.zorder_dit
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@zorder_dit
+POSTHOOK: query: DESCRIBE FORMATTED default.zorder_dit
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@zorder_dit
+# col_name data_type comment
+id int
+text string
+bool_val boolean
+date_val date
+
+# Detailed Table Information
+Database: default
+#### A masked pattern was here ####
+Retention: 0
+#### A masked pattern was here ####
+Table Type: EXTERNAL_TABLE
+Table Parameters:
+ COLUMN_STATS_ACCURATE
{\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"bool_val\":\"true\",\"date_val\":\"true\",\"id\":\"true\",\"text\":\"true\"}}
+ EXTERNAL TRUE
+ bucketing_version 2
+ current-schema
{\"type\":\"struct\",\"schema-id\":0,\"fields\":[{\"id\":1,\"name\":\"id\",\"required\":false,\"type\":\"int\"},{\"id\":2,\"name\":\"text\",\"required\":false,\"type\":\"string\"},{\"id\":3,\"name\":\"bool_val\",\"required\":false,\"type\":\"boolean\"},{\"id\":4,\"name\":\"date_val\",\"required\":false,\"type\":\"date\"}]}
+ format-version 2
+ iceberg.orc.files.only true
+#### A masked pattern was here ####
+ numFiles 0
+ numRows 0
+ parquet.compression zstd
+ rawDataSize 0
+ serialization.format 1
+ snapshot-count 0
+ sort.columns date_val,id,text
+ sort.order ZORDER
+ storage_handler
org.apache.iceberg.mr.hive.HiveIcebergStorageHandler
+ table_type ICEBERG
+ totalSize #Masked#
+#### A masked pattern was here ####
+ uuid #Masked#
+ write.delete.mode merge-on-read
+ write.format.default orc
+ write.merge.mode merge-on-read
+ write.update.mode merge-on-read
+
+# Storage Information
+SerDe Library: org.apache.iceberg.mr.hive.HiveIcebergSerDe
+InputFormat: org.apache.iceberg.mr.hive.HiveIcebergInputFormat
+OutputFormat: org.apache.iceberg.mr.hive.HiveIcebergOutputFormat
+Compressed: No
+Sort Columns: []
+PREHOOK: query: INSERT INTO default.zorder_dit VALUES
+ (0, 'a', false, DATE '2023-01-01'),
+ (255, 'z', true, DATE '2025-12-31'),
+ (0, 'z', false, DATE '2025-12-31'),
+ (255, 'a', true, DATE '2023-01-01'),
+ (128, 'm', true, DATE '2024-06-01'),
+ (64, 'c', false, DATE '2023-06-01'),
+ (192, 'x', true, DATE '2025-01-01'),
+ (32, 'b', true, DATE '2023-03-01'),
+ (96, 'd', false, DATE '2023-09-01'),
+ (160, 'v', true, DATE '2024-09-01')
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@zorder_dit
+POSTHOOK: query: INSERT INTO default.zorder_dit VALUES
+ (0, 'a', false, DATE '2023-01-01'),
+ (255, 'z', true, DATE '2025-12-31'),
+ (0, 'z', false, DATE '2025-12-31'),
+ (255, 'a', true, DATE '2023-01-01'),
+ (128, 'm', true, DATE '2024-06-01'),
+ (64, 'c', false, DATE '2023-06-01'),
+ (192, 'x', true, DATE '2025-01-01'),
+ (32, 'b', true, DATE '2023-03-01'),
+ (96, 'd', false, DATE '2023-09-01'),
+ (160, 'v', true, DATE '2024-09-01')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@zorder_dit
+PREHOOK: query: SELECT * FROM default.zorder_dit
+PREHOOK: type: QUERY
+PREHOOK: Input: default@zorder_dit
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM default.zorder_dit
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@zorder_dit
+#### A masked pattern was here ####
+0 a false 2023-01-01
+255 a true 2023-01-01
+32 b true 2023-03-01
+64 c false 2023-06-01
+96 d false 2023-09-01
+128 m true 2024-06-01
+160 v true 2024-09-01
+192 x true 2025-01-01
+0 z false 2025-12-31
+255 z true 2025-12-31
+PREHOOK: query: DROP TABLE default.zorder_dit
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@zorder_dit
+PREHOOK: Output: database:default
+PREHOOK: Output: default@zorder_dit
+POSTHOOK: query: DROP TABLE default.zorder_dit
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@zorder_dit
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@zorder_dit
+PREHOOK: query: CREATE TABLE default.zorder_tsdl (
+ ts timestamp,
+ dd double,
+ ll bigint)
+WRITE LOCALLY ZORDER by (ts, dd, ll)
+STORED BY iceberg
+STORED As orc
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@zorder_tsdl
+POSTHOOK: query: CREATE TABLE default.zorder_tsdl (
+ ts timestamp,
+ dd double,
+ ll bigint)
+WRITE LOCALLY ZORDER by (ts, dd, ll)
+STORED BY iceberg
+STORED As orc
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@zorder_tsdl
+PREHOOK: query: DESCRIBE FORMATTED default.zorder_tsdl
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@zorder_tsdl
+POSTHOOK: query: DESCRIBE FORMATTED default.zorder_tsdl
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@zorder_tsdl
+# col_name data_type comment
+ts timestamp
+dd double
+ll bigint
+
+# Detailed Table Information
+Database: default
+#### A masked pattern was here ####
+Retention: 0
+#### A masked pattern was here ####
+Table Type: EXTERNAL_TABLE
+Table Parameters:
+ COLUMN_STATS_ACCURATE
{\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"dd\":\"true\",\"ll\":\"true\",\"ts\":\"true\"}}
+ EXTERNAL TRUE
+ bucketing_version 2
+ current-schema
{\"type\":\"struct\",\"schema-id\":0,\"fields\":[{\"id\":1,\"name\":\"ts\",\"required\":false,\"type\":\"timestamp\"},{\"id\":2,\"name\":\"dd\",\"required\":false,\"type\":\"double\"},{\"id\":3,\"name\":\"ll\",\"required\":false,\"type\":\"long\"}]}
+ format-version 2
+ iceberg.orc.files.only true
+#### A masked pattern was here ####
+ numFiles 0
+ numRows 0
+ parquet.compression zstd
+ rawDataSize 0
+ serialization.format 1
+ snapshot-count 0
+ sort.columns ts,dd,ll
+ sort.order ZORDER
+ storage_handler
org.apache.iceberg.mr.hive.HiveIcebergStorageHandler
+ table_type ICEBERG
+ totalSize #Masked#
+#### A masked pattern was here ####
+ uuid #Masked#
+ write.delete.mode merge-on-read
+ write.format.default orc
+ write.merge.mode merge-on-read
+ write.update.mode merge-on-read
+
+# Storage Information
+SerDe Library: org.apache.iceberg.mr.hive.HiveIcebergSerDe
+InputFormat: org.apache.iceberg.mr.hive.HiveIcebergInputFormat
+OutputFormat: org.apache.iceberg.mr.hive.HiveIcebergOutputFormat
+Compressed: No
+Sort Columns: []
+PREHOOK: query: INSERT INTO default.zorder_tsdl VALUES
+ (TIMESTAMP '2022-01-01 00:00:00', 0.0, 0),
+ (TIMESTAMP '2030-12-31 23:59:59', 9999.99, 9999999),
+ (TIMESTAMP '2022-01-01 00:00:00', 9999.99, 9999999),
+ (TIMESTAMP '2030-12-31 23:59:59', 0.0, 0),
+ (TIMESTAMP '2026-06-15 12:00:00', 5000.5, 5000000),
+ (TIMESTAMP '2023-03-03 03:03:03', 9999.99, 0),
+ (TIMESTAMP '2023-03-03 03:03:03', 0.0, 9999999),
+ (TIMESTAMP '2025-05-05 05:05:05', 250.25, 54321),
+ (TIMESTAMP '2027-07-07 07:07:07', 8000.8, 8888888),
+ (TIMESTAMP '2024-04-04 04:04:04', 1000.1, 123456)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@zorder_tsdl
+POSTHOOK: query: INSERT INTO default.zorder_tsdl VALUES
+ (TIMESTAMP '2022-01-01 00:00:00', 0.0, 0),
+ (TIMESTAMP '2030-12-31 23:59:59', 9999.99, 9999999),
+ (TIMESTAMP '2022-01-01 00:00:00', 9999.99, 9999999),
+ (TIMESTAMP '2030-12-31 23:59:59', 0.0, 0),
+ (TIMESTAMP '2026-06-15 12:00:00', 5000.5, 5000000),
+ (TIMESTAMP '2023-03-03 03:03:03', 9999.99, 0),
+ (TIMESTAMP '2023-03-03 03:03:03', 0.0, 9999999),
+ (TIMESTAMP '2025-05-05 05:05:05', 250.25, 54321),
+ (TIMESTAMP '2027-07-07 07:07:07', 8000.8, 8888888),
+ (TIMESTAMP '2024-04-04 04:04:04', 1000.1, 123456)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@zorder_tsdl
+PREHOOK: query: SELECT * FROM default.zorder_tsdl
+PREHOOK: type: QUERY
+PREHOOK: Input: default@zorder_tsdl
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM default.zorder_tsdl
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@zorder_tsdl
+#### A masked pattern was here ####
+2022-01-01 00:00:00 0.0 0
+2023-03-03 03:03:03 0.0 9999999
+2030-12-31 23:59:59 0.0 0
+2025-05-05 05:05:05 250.25 54321
+2024-04-04 04:04:04 1000.1 123456
+2026-06-15 12:00:00 5000.5 5000000
+2027-07-07 07:07:07 8000.8 8888888
+2022-01-01 00:00:00 9999.99 9999999
+2023-03-03 03:03:03 9999.99 0
+2030-12-31 23:59:59 9999.99 9999999
+PREHOOK: query: DROP TABLE default.zorder_tsdl
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@zorder_tsdl
+PREHOOK: Output: database:default
+PREHOOK: Output: default@zorder_tsdl
+POSTHOOK: query: DROP TABLE default.zorder_tsdl
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@zorder_tsdl
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@zorder_tsdl
+PREHOOK: query: CREATE TABLE default.zorder_props(id int, text string)
+STORED BY iceberg
+STORED As orc
+TBLPROPERTIES ("sort.order" = "zorder", "sort.columns" = "id,text")
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@zorder_props
+POSTHOOK: query: CREATE TABLE default.zorder_props(id int, text string)
+STORED BY iceberg
+STORED As orc
+TBLPROPERTIES ("sort.order" = "zorder", "sort.columns" = "id,text")
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@zorder_props
+PREHOOK: query: INSERT INTO default.zorder_props VALUES (3, 'B'),(1, 'A'),(7,
'C'),(2, 'A'),(9, 'B'),(6, 'C'),(4, 'A'),
+ (10, 'C'),(5, NULL),(8, 'B'),(NULL, 'A'),(12, 'C'),(11, 'A'),(13, NULL),
+ (14, 'B'),(15, 'C'),(16, 'A'),(19, 'B'),(17, 'C'),(18, 'A')
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@zorder_props
+POSTHOOK: query: INSERT INTO default.zorder_props VALUES (3, 'B'),(1, 'A'),(7,
'C'),(2, 'A'),(9, 'B'),(6, 'C'),(4, 'A'),
+ (10, 'C'),(5, NULL),(8, 'B'),(NULL, 'A'),(12, 'C'),(11, 'A'),(13, NULL),
+ (14, 'B'),(15, 'C'),(16, 'A'),(19, 'B'),(17, 'C'),(18, 'A')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@zorder_props
+PREHOOK: query: DESCRIBE FORMATTED default.zorder_props
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@zorder_props
+POSTHOOK: query: DESCRIBE FORMATTED default.zorder_props
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@zorder_props
+# col_name data_type comment
+id int
+text string
+
+# Detailed Table Information
+Database: default
+#### A masked pattern was here ####
+Retention: 0
+#### A masked pattern was here ####
+Table Type: EXTERNAL_TABLE
+Table Parameters:
+ COLUMN_STATS_ACCURATE
{\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"id\":\"true\",\"text\":\"true\"}}
+ EXTERNAL TRUE
+ bucketing_version 2
+ current-schema
{\"type\":\"struct\",\"schema-id\":0,\"fields\":[{\"id\":1,\"name\":\"id\",\"required\":false,\"type\":\"int\"},{\"id\":2,\"name\":\"text\",\"required\":false,\"type\":\"string\"}]}
+ current-snapshot-id #Masked#
+ current-snapshot-summary
{\"added-data-files\":\"1\",\"added-records\":\"20\",\"added-files-size\":\"#Masked#\",\"changed-partition-count\":\"1\",\"total-records\":\"20\",\"total-files-size\":\"#Masked#\",\"total-data-files\":\"1\",\"total-delete-files\":\"0\",\"total-position-deletes\":\"0\",\"total-equality-deletes\":\"0\",\"iceberg-version\":\"#Masked#\"}
+ current-snapshot-timestamp-ms #Masked#
+ format-version 2
+ iceberg.orc.files.only true
+#### A masked pattern was here ####
+ numFiles 1
+ numRows 20
+ parquet.compression zstd
+#### A masked pattern was here ####
+ rawDataSize 0
+ serialization.format 1
+ snapshot-count 1
+ sort.columns id,text
+ sort.order zorder
+ storage_handler
org.apache.iceberg.mr.hive.HiveIcebergStorageHandler
+ table_type ICEBERG
+ totalSize #Masked#
+#### A masked pattern was here ####
+ uuid #Masked#
+ write.delete.mode merge-on-read
+ write.format.default orc
+ write.merge.mode merge-on-read
+ write.update.mode merge-on-read
+
+# Storage Information
+SerDe Library: org.apache.iceberg.mr.hive.HiveIcebergSerDe
+InputFormat: org.apache.iceberg.mr.hive.HiveIcebergInputFormat
+OutputFormat: org.apache.iceberg.mr.hive.HiveIcebergOutputFormat
+Compressed: No
+Sort Columns: []
+PREHOOK: query: SELECT * FROM default.zorder_props
+PREHOOK: type: QUERY
+PREHOOK: Input: default@zorder_props
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM default.zorder_props
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@zorder_props
+#### A masked pattern was here ####
+NULL A
+5 NULL
+13 NULL
+1 A
+2 A
+4 A
+11 A
+16 A
+18 A
+3 B
+8 B
+9 B
+14 B
+19 B
+6 C
+7 C
+10 C
+12 C
+15 C
+17 C
+PREHOOK: query: DROP TABLE default.zorder_props
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@zorder_props
+PREHOOK: Output: database:default
+PREHOOK: Output: default@zorder_props
+POSTHOOK: query: DROP TABLE default.zorder_props
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@zorder_props
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@zorder_props
diff --git a/itests/src/test/resources/testconfiguration.properties
b/itests/src/test/resources/testconfiguration.properties
index 14a8394d589..336a190c358 100644
--- a/itests/src/test/resources/testconfiguration.properties
+++ b/itests/src/test/resources/testconfiguration.properties
@@ -426,6 +426,7 @@ iceberg.llap.query.files=\
iceberg_bucket_map_join_8.q,\
iceberg_clustered.q,\
iceberg_create_locally_ordered_table.q,\
+ iceberg_create_locally_zordered_table.q,\
iceberg_merge_delete_files.q,\
iceberg_merge_files.q,\
llap_iceberg_read_orc.q,\
@@ -473,6 +474,7 @@ iceberg.llap.only.query.files=\
iceberg_bucket_map_join_8.q,\
iceberg_clustered.q,\
iceberg_create_locally_ordered_table.q,\
+ iceberg_create_locally_zordered_table.q,\
iceberg_merge_delete_files.q,\
iceberg_merge_files.q,\
llap_iceberg_read_orc.q,\
diff --git a/parser/src/java/org/apache/hadoop/hive/ql/parse/CreateDDLParser.g
b/parser/src/java/org/apache/hadoop/hive/ql/parse/CreateDDLParser.g
index 70b20472ff8..1c78a50edf9 100644
--- a/parser/src/java/org/apache/hadoop/hive/ql/parse/CreateDDLParser.g
+++ b/parser/src/java/org/apache/hadoop/hive/ql/parse/CreateDDLParser.g
@@ -49,6 +49,11 @@ likeTableOrFile
| (KW_LIKE likeName=tableName) -> ^(TOK_LIKETABLE $likeName)
;
+tableOrderOption
+ : tableWriteLocallyOrdered
+ | tableWriteLocallyZorder
+ ;
+
//----------------------- Rules for parsing createtable
-----------------------------
createTableStatement
@init { gParent.pushMsg("create table statement", state); }
@@ -64,7 +69,7 @@ createTableStatement
tableComment?
createTablePartitionSpec?
tableBuckets?
- tableWriteLocallyOrdered?
+ tableOrderOption?
tableSkewed?
tableRowFormat?
tableFileFormat?
@@ -78,7 +83,7 @@ createTableStatement
tableComment?
createTablePartitionSpec?
tableBuckets?
- tableWriteLocallyOrdered?
+ tableOrderOption?
tableSkewed?
tableRowFormat?
tableFileFormat?
@@ -96,7 +101,7 @@ createTableStatement
tableComment?
createTablePartitionSpec?
tableBuckets?
- tableWriteLocallyOrdered?
+ tableOrderOption?
tableSkewed?
tableRowFormat?
tableFileFormat?
@@ -110,7 +115,7 @@ createTableStatement
tableComment?
createTablePartitionSpec?
tableBuckets?
- tableWriteLocallyOrdered?
+ tableOrderOption?
tableSkewed?
tableRowFormat?
tableFileFormat?
diff --git a/parser/src/java/org/apache/hadoop/hive/ql/parse/HiveLexerParent.g
b/parser/src/java/org/apache/hadoop/hive/ql/parse/HiveLexerParent.g
index de06106b7b3..99ffa6cb48a 100644
--- a/parser/src/java/org/apache/hadoop/hive/ql/parse/HiveLexerParent.g
+++ b/parser/src/java/org/apache/hadoop/hive/ql/parse/HiveLexerParent.g
@@ -37,6 +37,7 @@ KW_DESC : 'DESC';
KW_NULLS : 'NULLS';
KW_LAST : 'LAST';
KW_ORDER : 'ORDER';
+KW_ZORDER : 'ZORDER';
KW_ORDERED : 'ORDERED';
KW_LOCALLY : 'LOCALLY';
KW_GROUP : 'GROUP';
diff --git a/parser/src/java/org/apache/hadoop/hive/ql/parse/HiveParser.g
b/parser/src/java/org/apache/hadoop/hive/ql/parse/HiveParser.g
index ddce6aa85af..13d7549128c 100644
--- a/parser/src/java/org/apache/hadoop/hive/ql/parse/HiveParser.g
+++ b/parser/src/java/org/apache/hadoop/hive/ql/parse/HiveParser.g
@@ -524,6 +524,7 @@ TOK_AS_OF_VERSION;
TOK_FROM_VERSION;
TOK_AS_OF_TAG;
TOK_WRITE_LOCALLY_ORDERED;
+TOK_WRITE_LOCALLY_ZORDER;
}
@@ -568,6 +569,7 @@ import org.apache.hadoop.hive.conf.HiveConf;
xlateMap.put("KW_NULLS", "NULLS");
xlateMap.put("KW_LAST", "LAST");
xlateMap.put("KW_ORDER", "ORDER");
+ xlateMap.put("KW_ZORDER", "ZORDER");
xlateMap.put("KW_ORDERED", "ORDERED");
xlateMap.put("KW_LOCALLY", "LOCALLY");
xlateMap.put("KW_BY", "BY");
@@ -1881,6 +1883,14 @@ tableWriteLocallyOrdered
KW_WRITE KW_LOCALLY KW_ORDERED KW_BY sortCols=columnNameOrderList
-> ^(TOK_WRITE_LOCALLY_ORDERED $sortCols?)
;
+
+tableWriteLocallyZorder
+@init { pushMsg("table zorder sort specification", state); }
+@after { popMsg(state); }
+ :
+ KW_WRITE KW_LOCALLY KW_ZORDER KW_BY LPAREN sortCols=columnNameList RPAREN
+ -> ^(TOK_WRITE_LOCALLY_ZORDER $sortCols?)
+ ;
tableSkewed
@init { pushMsg("table skewed specification", state); }
diff --git
a/parser/src/java/org/apache/hadoop/hive/ql/parse/IdentifiersParser.g
b/parser/src/java/org/apache/hadoop/hive/ql/parse/IdentifiersParser.g
index 54ec367a677..6a22542429e 100644
--- a/parser/src/java/org/apache/hadoop/hive/ql/parse/IdentifiersParser.g
+++ b/parser/src/java/org/apache/hadoop/hive/ql/parse/IdentifiersParser.g
@@ -1040,6 +1040,7 @@ nonReserved
| KW_TIMESTAMPLOCALTZ
| KW_ORDERED
| KW_LOCALLY
+ | KW_ZORDER
;
//The following SQL2011 reserved keywords are used as function name only, but
not as identifiers.
diff --git
a/ql/src/java/org/apache/hadoop/hive/ql/ddl/misc/sortoder/ZOrderFieldDesc.java
b/ql/src/java/org/apache/hadoop/hive/ql/ddl/misc/sortoder/ZOrderFieldDesc.java
new file mode 100644
index 00000000000..1f2afd4d7ad
--- /dev/null
+++
b/ql/src/java/org/apache/hadoop/hive/ql/ddl/misc/sortoder/ZOrderFieldDesc.java
@@ -0,0 +1,44 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.hadoop.hive.ql.ddl.misc.sortoder;
+
+public class ZOrderFieldDesc {
+
+ private String columnName;
+
+ public ZOrderFieldDesc() {
+ }
+
+ public ZOrderFieldDesc(String columnName) {
+ this.columnName = columnName;
+ }
+
+ public String getColumnName() {
+ return columnName;
+ }
+
+ public void setColumnName(String columnName) {
+ this.columnName = columnName;
+ }
+
+ @Override
+ public String toString() {
+ return String.format("{columnName:%s}", columnName);
+ }
+}
diff --git
a/ql/src/java/org/apache/hadoop/hive/ql/ddl/misc/sortoder/ZOrderFields.java
b/ql/src/java/org/apache/hadoop/hive/ql/ddl/misc/sortoder/ZOrderFields.java
new file mode 100644
index 00000000000..023736d9308
--- /dev/null
+++ b/ql/src/java/org/apache/hadoop/hive/ql/ddl/misc/sortoder/ZOrderFields.java
@@ -0,0 +1,47 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.hadoop.hive.ql.ddl.misc.sortoder;
+
+import java.util.LinkedList;
+import java.util.List;
+
+public class ZOrderFields {
+
+ private List<ZOrderFieldDesc> zOrderFieldDescs;
+
+ public ZOrderFields() {
+ this.zOrderFieldDescs = new LinkedList<>();
+ }
+
+ public ZOrderFields(List<ZOrderFieldDesc> zOrderFields) {
+ if (zOrderFields == null) {
+ this.zOrderFieldDescs = new LinkedList<>();
+ } else {
+ this.zOrderFieldDescs = zOrderFields;
+ }
+ }
+
+ public List<ZOrderFieldDesc> getZOrderFields() {
+ return zOrderFieldDescs;
+ }
+
+ public void setZOrderFields(List<ZOrderFieldDesc> zOrderFields) {
+ this.zOrderFieldDescs = zOrderFields;
+ }
+}
diff --git
a/ql/src/java/org/apache/hadoop/hive/ql/ddl/table/create/CreateTableAnalyzer.java
b/ql/src/java/org/apache/hadoop/hive/ql/ddl/table/create/CreateTableAnalyzer.java
index 37858b8af0c..c6188df71aa 100644
---
a/ql/src/java/org/apache/hadoop/hive/ql/ddl/table/create/CreateTableAnalyzer.java
+++
b/ql/src/java/org/apache/hadoop/hive/ql/ddl/table/create/CreateTableAnalyzer.java
@@ -55,6 +55,8 @@
import org.apache.hadoop.hive.ql.ddl.DDLWork;
import org.apache.hadoop.hive.ql.ddl.misc.sortoder.SortFieldDesc;
import org.apache.hadoop.hive.ql.ddl.misc.sortoder.SortFields;
+import org.apache.hadoop.hive.ql.ddl.misc.sortoder.ZOrderFieldDesc;
+import org.apache.hadoop.hive.ql.ddl.misc.sortoder.ZOrderFields;
import org.apache.hadoop.hive.ql.ddl.table.constraint.ConstraintsUtils;
import org.apache.hadoop.hive.ql.ddl.table.convert.AlterTableConvertOperation;
import org.apache.hadoop.hive.ql.ddl.table.create.like.CreateTableLikeDesc;
@@ -189,6 +191,29 @@ private String getSortOrderJson(ASTNode ast) {
}
}
+ /**
+ * Converts AST child nodes to a JSON string of Z-order fields.
+ * Returns null if JSON serialization fails.
+ *
+ * @param ast AST node containing Z-order field names
+ * @return JSON string of Z-order fields or null on error
+ */
+ private String getZOrderJson(ASTNode ast) {
+ List<ZOrderFieldDesc> zOrderFieldDescs = new ArrayList<>();
+ ZOrderFields zOrderFields = new ZOrderFields(zOrderFieldDescs);
+ for (int i = 0; i < ast.getChildCount(); i++) {
+ ASTNode child = (ASTNode) ast.getChild(i);
+ String name = unescapeIdentifier(child.getText()).toLowerCase();
+ zOrderFieldDescs.add(new ZOrderFieldDesc(name));
+ }
+ try {
+ return JSON_OBJECT_MAPPER.writer().writeValueAsString(zOrderFields);
+ } catch (JsonProcessingException e) {
+ LOG.warn("Can not create z-order json. ", e);
+ return null;
+ }
+ }
+
/**
* This api is used to determine where to create acid tables are not.
* if the default table type is set to external, then create transactional
table should result in acid tables,
@@ -495,6 +520,9 @@ ASTNode analyzeCreateTable(ASTNode ast, QB qb,
PlannerContext plannerCtx)
case HiveParser.TOK_WRITE_LOCALLY_ORDERED:
sortOrder = getSortOrderJson((ASTNode) child.getChild(0));
break;
+ case HiveParser.TOK_WRITE_LOCALLY_ZORDER:
+ sortOrder = getZOrderJson((ASTNode) child.getChild(0));
+ break;
case HiveParser.TOK_TABLEROWFORMAT:
rowFormatParams.analyzeRowFormat(child);
break;
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/FunctionRegistry.java
b/ql/src/java/org/apache/hadoop/hive/ql/exec/FunctionRegistry.java
index 7991abc8433..5f9589ccb10 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/exec/FunctionRegistry.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/FunctionRegistry.java
@@ -804,6 +804,8 @@ public final class FunctionRegistry {
(Class<? extends GenericUDF>)
Class.forName("org.apache.iceberg.mr.hive.udf.GenericUDFIcebergDay"));
system.registerGenericUDF("iceberg_hour",
(Class<? extends GenericUDF>)
Class.forName("org.apache.iceberg.mr.hive.udf.GenericUDFIcebergHour"));
+ system.registerGenericUDF("iceberg_zorder",
+ (Class<? extends GenericUDF>)
Class.forName("org.apache.iceberg.mr.hive.udf.GenericUDFIcebergZorder"));
} catch (ClassNotFoundException e) {
LOG.warn("iceberg_bucket function could not be registered");
}
diff --git a/ql/src/test/results/clientpositive/llap/show_functions.q.out
b/ql/src/test/results/clientpositive/llap/show_functions.q.out
index cb8955e3808..d28610a55f5 100644
--- a/ql/src/test/results/clientpositive/llap/show_functions.q.out
+++ b/ql/src/test/results/clientpositive/llap/show_functions.q.out
@@ -223,6 +223,7 @@ iceberg_hour
iceberg_month
iceberg_truncate
iceberg_year
+iceberg_zorder
if
in
in_bloom_filter
@@ -862,6 +863,7 @@ iceberg_hour
iceberg_month
iceberg_truncate
iceberg_year
+iceberg_zorder
if
in
in_bloom_filter
