Merge branch 'prestodb:master' into xiao2602241updatepath

Author: duxiao1212

presto-analyzer/src/main/java/com/facebook/presto/sql/analyzer/utils/StatementUtils.java

@@ -28,6 +28,7 @@
 import com.facebook.presto.sql.tree.CreateSchema;
 import com.facebook.presto.sql.tree.CreateTable;
 import com.facebook.presto.sql.tree.CreateTableAsSelect;
+import com.facebook.presto.sql.tree.CreateTag;
 import com.facebook.presto.sql.tree.CreateType;
 import com.facebook.presto.sql.tree.CreateView;
 import com.facebook.presto.sql.tree.Deallocate;
@@ -133,6 +134,7 @@ private StatementUtils() {}
         builder.put(AddColumn.class, QueryType.DATA_DEFINITION);
         builder.put(CreateTable.class, QueryType.DATA_DEFINITION);
         builder.put(CreateBranch.class, QueryType.DATA_DEFINITION);
+        builder.put(CreateTag.class, QueryType.DATA_DEFINITION);
         builder.put(RenameTable.class, QueryType.DATA_DEFINITION);
         builder.put(RenameColumn.class, QueryType.DATA_DEFINITION);
         builder.put(DropColumn.class, QueryType.DATA_DEFINITION);

presto-docs/src/main/sphinx/connector/hive.rst

@@ -164,9 +164,18 @@ Property Name                                            Description
                                                          absolutely necessary to access HDFS.
                                                          Example: ``/etc/hdfs-site.xml``
 
-``hive.storage-format``                                  The default file format used when creating new tables.       ``ORC``
-
-``hive.compression-codec``                               The compression codec to use when writing files.             ``GZIP``
+``hive.storage-format``                                  The default file format used when creating new tables. The   ``ORC``
+                                                         available values are ``ORC``, ``PARQUET``, ``AVRO``,
+                                                         ``RCBINARY``, ``RCTEXT``, ``SEQUENCEFILE``, ``JSON``,
+                                                         and ``TEXTFILE``.
+
+``hive.compression-codec``                               The compression codec to use when writing files. The         ``GZIP``
+                                                         available values are ``NONE``, ``SNAPPY``, ``GZIP``,
+                                                         ``LZ4``, and ``ZSTD``.
+                                                         
+                                                         Note: ``LZ4`` is only available when
+                                                         ``hive.storage-format=ORC``. ``ZSTD`` is available
+                                                         for both ``ORC`` and ``PARQUET`` formats.
 
 ``hive.force-local-scheduling``                          Force splits to be scheduled on the same node as the Hadoop  ``false``
                                                          DataNode process serving the split data. This is useful for

presto-docs/src/main/sphinx/connector/iceberg.rst

@@ -1621,6 +1621,22 @@ Alter table operations are supported in the Iceberg connector::
 
      ALTER TABLE iceberg.default.mytable CREATE OR REPLACE BRANCH 'audit-branch-time' FOR SYSTEM_TIME AS OF TIMESTAMP '2026-01-02 17:30:35.247 Asia/Kolkata';
 
+     ALTER TABLE iceberg.default.mytable CREATE TAG 'audit-tag';
+
+     ALTER TABLE iceberg.default.mytable CREATE TAG IF NOT EXISTS 'audit-tag';
+
+     ALTER TABLE iceberg.default.mytable CREATE OR REPLACE TAG 'audit-tag';
+
+     ALTER TABLE iceberg.default.mytable CREATE TAG 'audit-tag-system' FOR SYSTEM_VERSION AS OF 4176642711908913940;
+
+     ALTER TABLE iceberg.default.mytable CREATE TAG IF NOT EXISTS 'audit-tag-system' FOR SYSTEM_VERSION AS OF 4176642711908913940;
+
+     ALTER TABLE iceberg.default.mytable CREATE TAG 'audit-tag-retain' FOR SYSTEM_VERSION AS OF 4176642711908913940 RETAIN 7 DAYS;
+
+     ALTER TABLE iceberg.default.mytable CREATE TAG 'audit-tag-snap-retain' FOR SYSTEM_VERSION AS OF 4176642711908913940 RETAIN 7 DAYS WITH SNAPSHOT RETENTION 2 SNAPSHOTS 2 DAYS;
+
+     ALTER TABLE iceberg.default.mytable CREATE OR REPLACE TAG 'audit-tag-time' FOR SYSTEM_TIME AS OF TIMESTAMP '2026-01-02 17:30:35.247 Asia/Kolkata';
+
 To add a new column as a partition column, identify the transform functions for the column.
 The table is partitioned by the transformed value of the column::
 

presto-docs/src/main/sphinx/presto-cpp.rst

@@ -9,6 +9,7 @@ Note: Presto C++ is in active development. See :doc:`Limitations </presto_cpp/li
 
     presto_cpp/installation
     presto_cpp/features
+    presto_cpp/functions
     presto_cpp/sidecar
     presto_cpp/limitations
     presto_cpp/plugin

presto-docs/src/main/sphinx/presto_cpp/functions.rst

@@ -0,0 +1,8 @@
+********************
+Presto C++ Functions
+********************
+
+.. toctree::
+    :maxdepth: 1
+
+    functions/sketch.rst

presto-docs/src/main/sphinx/presto_cpp/functions/sketch.rst

@@ -0,0 +1,38 @@
+================
+Sketch Functions
+================
+
+Sketches are data structures that can approximately answer particular questions
+about a dataset when full accuracy is not required. Approximate answers are
+often faster and more efficient to compute than functions which result in full
+accuracy.
+
+Presto C++ provides support for computing some sketches available in the `Apache
+DataSketches`_ library.
+
+Theta Sketches
+--------------
+
+Theta sketches enable distinct value counting on datasets and also provide the
+ability to perform set operations. For more information on Theta sketches,
+please see the Apache DataSketches `Theta sketch documentation`_.
+
+.. function:: sketch_theta(x) -> varbinary
+
+    Computes a theta sketch from an input dataset. The output from
+    this function can be used as an input to any of the other ``sketch_theta_*``
+    family of functions.
+
+.. function:: sketch_theta_estimate(sketch) -> double
+
+    Returns the estimate of distinct values from the input sketch.
+
+.. function:: sketch_theta_summary(sketch) -> row(estimate double, theta double, upper_bound_std double, lower_bound_std double, retained_entries int)
+
+    Returns a summary of the input sketch which includes the distinct values
+    estimate alongside other useful information such as the sketch theta
+    parameter, current error bounds corresponding to 1 standard deviation, and
+    the number of retained entries in the sketch.
+
+.. _Apache DataSketches: https://datasketches.apache.org/
+.. _Theta sketch documentation: https://datasketches.apache.org/docs/Theta/ThetaSketches.html#theta-sketch-framework

presto-docs/src/main/sphinx/sql/alter-table.rst

@@ -22,6 +22,10 @@ Synopsis
     ALTER TABLE [ IF EXISTS ] name CREATE [ OR REPLACE ] BRANCH [ IF NOT EXISTS ] branch_name FOR SYSTEM_TIME AS OF timestamp
     ALTER TABLE [ IF EXISTS ] name CREATE [ OR REPLACE ] BRANCH [ IF NOT EXISTS ] branch_name FOR SYSTEM_VERSION AS OF version RETAIN retention_period
     ALTER TABLE [ IF EXISTS ] name CREATE [ OR REPLACE ] BRANCH [ IF NOT EXISTS ] branch_name FOR SYSTEM_VERSION AS OF version RETAIN retention_period WITH SNAPSHOT RETENTION min_snapshots SNAPSHOTS min_retention_period
+    ALTER TABLE [ IF EXISTS ] name CREATE [ OR REPLACE ] TAG [ IF NOT EXISTS ] tag_name
+    ALTER TABLE [ IF EXISTS ] name CREATE [ OR REPLACE ] TAG [ IF NOT EXISTS ] tag_name FOR SYSTEM_VERSION AS OF version
+    ALTER TABLE [ IF EXISTS ] name CREATE [ OR REPLACE ] TAG [ IF NOT EXISTS ] tag_name FOR SYSTEM_TIME AS OF timestamp
+    ALTER TABLE [ IF EXISTS ] name CREATE [ OR REPLACE ] TAG [ IF NOT EXISTS ] tag_name FOR SYSTEM_VERSION AS OF version RETAIN retention_period
 
 Description
 -----------
@@ -40,6 +44,12 @@ For ``CREATE BRANCH`` statements:
 * The optional ``IF NOT EXISTS`` clause causes the error to be suppressed if the branch already exists.
 * ``OR REPLACE`` and ``IF NOT EXISTS`` cannot be specified together.
 
+For ``CREATE TAG`` statements:
+
+* The optional ``OR REPLACE`` clause causes the tag to be replaced if it already exists.
+* The optional ``IF NOT EXISTS`` clause causes the error to be suppressed if the tag already exists.
+* ``OR REPLACE`` and ``IF NOT EXISTS`` cannot be specified together.
+
 Examples
 --------
 
@@ -147,6 +157,34 @@ Create branch ``branch1`` from the ``users`` table for system version as of vers
 
     ALTER TABLE users CREATE BRANCH 'branch1' FOR SYSTEM_VERSION AS OF 5 RETAIN INTERVAL 7 DAY WITH SNAPSHOT RETENTION 3 SNAPSHOTS INTERVAL 7 DAYS;
 
+Create tag ``tag1`` from the ``users`` table::
+
+    ALTER TABLE users CREATE TAG 'tag1';
+
+Create tag ``tag1`` from the ``users`` table only if it doesn't already exist::
+
+    ALTER TABLE users CREATE TAG IF NOT EXISTS 'tag1';
+
+Create or replace tag ``tag1`` from the ``users`` table::
+
+    ALTER TABLE users CREATE OR REPLACE TAG 'tag1';
+
+Create tag ``tag1`` from the ``users`` table for system version as of version 5::
+
+    ALTER TABLE users CREATE TAG 'tag1' FOR SYSTEM_VERSION AS OF 5;
+
+Create tag ``tag1`` from the ``users`` table for system version as of version 5, only if it doesn't exist::
+
+    ALTER TABLE users CREATE TAG IF NOT EXISTS 'tag1' FOR SYSTEM_VERSION AS OF 5;
+
+Create or replace tag ``tag1`` from the ``users`` table for system time as of timestamp '2026-01-02 17:30:35.247 Asia/Kolkata'::
+
+    ALTER TABLE users CREATE OR REPLACE TAG 'tag1' FOR SYSTEM_TIME AS OF TIMESTAMP '2026-01-02 17:30:35.247 Asia/Kolkata';
+
+Create tag ``tag1`` from the ``users`` table for system version as of version 5 with retention period of 30 days::
+
+    ALTER TABLE users CREATE TAG 'tag1' FOR SYSTEM_VERSION AS OF 5 RETAIN INTERVAL 30 DAY;
+
 See Also
 --------
 

presto-hive/src/main/java/com/facebook/presto/hive/security/LegacyAccessControl.java

@@ -306,6 +306,11 @@ public void checkCanCreateBranch(ConnectorTransactionHandle transactionHandle, C
     {
     }
 
+    @Override
+    public void checkCanCreateTag(ConnectorTransactionHandle transactionHandle, ConnectorIdentity identity, AccessControlContext context, SchemaTableName tableName)
+    {
+    }
+
     @Override
     public void checkCanDropTag(ConnectorTransactionHandle transactionHandle, ConnectorIdentity identity, AccessControlContext context, SchemaTableName tableName)
     {

presto-hive/src/main/java/com/facebook/presto/hive/security/SqlStandardAccessControl.java

@@ -61,6 +61,7 @@
 import static com.facebook.presto.spi.security.AccessDeniedException.denyCreateRole;
 import static com.facebook.presto.spi.security.AccessDeniedException.denyCreateSchema;
 import static com.facebook.presto.spi.security.AccessDeniedException.denyCreateTable;
+import static com.facebook.presto.spi.security.AccessDeniedException.denyCreateTag;
 import static com.facebook.presto.spi.security.AccessDeniedException.denyCreateView;
 import static com.facebook.presto.spi.security.AccessDeniedException.denyCreateViewWithSelect;
 import static com.facebook.presto.spi.security.AccessDeniedException.denyDeleteTable;
@@ -288,6 +289,24 @@ public void checkCanCreateBranch(ConnectorTransactionHandle transaction, Connect
         }
     }
 
+    @Override
+    public void checkCanCreateTag(ConnectorTransactionHandle transaction, ConnectorIdentity identity, AccessControlContext context, SchemaTableName tableName)
+    {
+        MetastoreContext metastoreContext = new MetastoreContext(
+                identity, context.getQueryId().getId(),
+                context.getClientInfo(),
+                context.getClientTags(),
+                context.getSource(),
+                Optional.empty(),
+                false,
+                HiveColumnConverterProvider.DEFAULT_COLUMN_CONVERTER_PROVIDER,
+                context.getWarningCollector(),
+                context.getRuntimeStats());
+        if (!isTableOwner(transaction, identity, metastoreContext, tableName)) {
+            denyCreateTag(tableName.toString());
+        }
+    }
+
     @Override
     public void checkCanDropTag(ConnectorTransactionHandle transaction, ConnectorIdentity identity, AccessControlContext context, SchemaTableName tableName)
     {

presto-hive/src/main/java/com/facebook/presto/hive/security/SystemTableAwareAccessControl.java

@@ -306,6 +306,12 @@ public void checkCanCreateBranch(ConnectorTransactionHandle transactionHandle, C
         delegate.checkCanCreateBranch(transactionHandle, identity, context, tableName);
     }
 
+    @Override
+    public void checkCanCreateTag(ConnectorTransactionHandle transactionHandle, ConnectorIdentity identity, AccessControlContext context, SchemaTableName tableName)
+    {
+        delegate.checkCanCreateTag(transactionHandle, identity, context, tableName);
+    }
+
     @Override
     public void checkCanDropTag(ConnectorTransactionHandle transactionHandle, ConnectorIdentity identity, AccessControlContext context, SchemaTableName tableName)
     {