This is an automated email from the ASF dual-hosted git repository.
JingsongLi pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/paimon.git
The following commit(s) were added to refs/heads/master by this push:
new 087cbd2638 [docs] Sync procedure documentation (#9101)
087cbd2638 is described below
commit 087cbd26389f8310c363da683450e1b127b9e8ab
Author: huangxiaoping <[email protected]>
AuthorDate: Fri Aug 14 16:28:07 2026 +0800
[docs] Sync procedure documentation (#9101)
---
docs/docs/flink/procedures.md | 136 ++++++++++++++++++++++++++++++++++++------
docs/docs/spark/procedures.md | 11 ++++
2 files changed, 128 insertions(+), 19 deletions(-)
diff --git a/docs/docs/flink/procedures.md b/docs/docs/flink/procedures.md
index 69648969b9..79e735f39b 100644
--- a/docs/docs/flink/procedures.md
+++ b/docs/docs/flink/procedures.md
@@ -677,25 +677,6 @@ All available procedures are listed below.
CALL sys.migrate_table(connector => 'hive', source_table =>
'db01.t1', options => 'file.format=parquet', parallelism => 6)
</td>
</tr>
- <tr>
- <td>migrate_iceberg_table</td>
- <td>
- -- Use named argument<br/>
- CALL sys.migrate_iceberg_table(source_table =>
'database_name.table_name', iceberg_options => 'iceberg_options', options =>
'paimon_options', parallelism => parallelism);<br/><br/>
- -- Use indexed argument<br/>
- CALL sys.migrate_iceberg_table('source_table','iceberg_options',
'options', 'parallelism');
- </td>
- <td>
- To migrate iceberg table to paimon. Arguments:
- <li>source_table: string type, is used to specify the source
iceberg table to migrate, it's required.</li>
- <li>iceberg_options: string type, is used to specify the
configuration of migration, multiple configuration items are separated by
commas. it's required.</li>
- <li>options: string type, is used to specify the additional
options for the target paimon table, it's optional.</li>
- <li>parallelism: integer type, is used to specify the parallelism
of the migration job, it's optional.</li>
- </td>
- <td>
- CALL sys.migrate_iceberg_table(source_table =>
'iceberg_db.iceberg_tbl',iceberg_options =>
'metadata.iceberg.storage=hadoop-catalog,iceberg_warehouse=/path/to/iceberg/warehouse');
- </td>
- </tr>
<tr>
<td>expire_snapshots</td>
<td>
@@ -813,6 +794,20 @@ All available procedures are listed below.
<li>tableName: the target table identifier.</li>
</td>
<td>CALL sys.repair(`table` => 'test_db.T')</td>
+ </tr>
+ <tr>
+ <td>repair_earliest_snapshot</td>
+ <td>
+ CALL [catalog.]sys.repair_earliest_snapshot(`table` => 'identifier',
snapshot_id => snapshotId)
+ </td>
+ <td>
+ Repair the earliest snapshot hint for a table. Arguments:
+ <li>table: the target table identifier. Cannot be empty.</li>
+ <li>snapshot_id: the snapshot ID to set as the earliest
snapshot.</li>
+ </td>
+ <td>
+ CALL sys.repair_earliest_snapshot(`table` => 'default.T', snapshot_id
=> 10)
+ </td>
</tr>
<tr>
<td>rewrite_file_index</td>
@@ -1234,5 +1229,108 @@ All available procedures are listed below.
`where` => 'status = ''active''')
</td>
</tr>
+ <tr>
+ <td>alter_column_default_value</td>
+ <td>
+ CALL [catalog.]sys.alter_column_default_value(`table` =>
'identifier', `column` => 'columnName', default_value => 'value')
+ </td>
+ <td>
+ Update a column default value. Arguments:
+ <li>table: the target table identifier.</li>
+ <li>column: the column name; nested columns are separated by
dots.</li>
+ <li>default_value: the new default value.</li>
+ </td>
+ <td>
+ CALL sys.alter_column_default_value(`table` => 'default.T', `column`
=> 'status', default_value => 'active')
+ </td>
+ </tr>
+ <tr>
+ <td>clone</td>
+ <td>
+ CALL [catalog.]sys.clone(database => 'sourceDatabase', `table` =>
'sourceTable', target_database => 'targetDatabase', target_table =>
'targetTable'[, catalog_conf => 'key=value'][, target_catalog_conf =>
'key=value'][, parallelism => parallelism][, `where` => 'predicate'][,
included_tables => 'table1,table2'][, excluded_tables => 'table3'][,
prefer_file_format => 'parquet'][, clone_from => 'hive-or-paimon'][, meta_only
=> true][, clone_if_exists => true][, target_table_conf => ' [...]
+ </td>
+ <td>
+ Clone a table or a database. Arguments:
+ <li>database and table: source database and optional source
table.</li>
+ <li>catalog_conf and target_catalog_conf: source and target
catalog options.</li>
+ <li>target_database and target_table: target database and optional
target table.</li>
+ <li>clone_from: optional source type, either <code>hive</code> or
<code>paimon</code>.</li>
+ <li>parallelism, where, included_tables, excluded_tables,
prefer_file_format, meta_only, clone_if_exists and target_table_conf: optional
clone controls.</li>
+ </td>
+ <td>
+ CALL sys.clone(database => 'source_db', `table` => 'source_t',
target_database => 'target_db', target_table => 'target_t', clone_from =>
'hive')
+ </td>
+ </tr>
+ <tr>
+ <td>copy_files</td>
+ <td>
+ CALL [catalog.]sys.copy_files(warehouse => 'sourceWarehouse',
database => 'sourceDatabase', `table` => 'sourceTable', catalog_conf =>
'key=value', target_warehouse => 'targetWarehouse', target_database =>
'targetDatabase', target_table => 'targetTable', target_catalog_conf =>
'key=value', parallelism => parallelism)
+ </td>
+ <td>
+ Deprecated. This procedure is supported only by
<code>FileSystemCatalog</code> and does not commit a standard catalog snapshot.
Do not use it for normal table-copy workflows; use <code>clone</code> instead.
It copies files from a source table to a target table. Arguments:
+ <li>warehouse, database, table and catalog_conf: optional source
catalog configuration.</li>
+ <li>target_warehouse: the target warehouse. Cannot be empty.</li>
+ <li>target_database, target_table and target_catalog_conf:
optional target table and catalog configuration.</li>
+ <li>parallelism: optional copy job parallelism.</li>
+ </td>
+ <td>
+ CALL sys.copy_files(warehouse => 'hdfs:///source', database =>
'default', `table` => 'T', target_warehouse => 'hdfs:///target',
target_database => 'default', target_table => 'T')
+ </td>
+ </tr>
+ <tr>
+ <td>drop_partition</td>
+ <td>
+ CALL [catalog.]sys.drop_partition('identifier', 'partition1'[,
'partition2', ...])
+ </td>
+ <td>
+ Drop one or more partitions. This procedure is deprecated; use
<code>ALTER TABLE DROP PARTITION</code> instead.
+ </td>
+ <td>
+ CALL sys.drop_partition('default.T', 'dt=2024-07-01')
+ </td>
+ </tr>
+ <tr>
+ <td>mark_partition_done</td>
+ <td>
+ CALL [catalog.]sys.mark_partition_done(`table` => 'identifier',
partitions => 'partition1;partition2')
+ </td>
+ <td>
+ Mark partitions as done. Arguments:
+ <li>table: the target table identifier. Cannot be empty.</li>
+ <li>partitions: semicolon-separated partition specs.</li>
+ </td>
+ <td>
+ CALL sys.mark_partition_done(`table` => 'default.T', partitions =>
'day=2024-07-01;day=2024-07-02')
+ </td>
+ </tr>
+ <tr>
+ <td>query_service</td>
+ <td>
+ CALL [catalog.]sys.query_service(`table` => 'identifier', parallelism
=> parallelism)
+ </td>
+ <td>
+ Start a query service for a table. Arguments:
+ <li>table: the target table identifier.</li>
+ <li>parallelism: the query service parallelism.</li>
+ </td>
+ <td>
+ CALL sys.query_service(`table` => 'default.T', parallelism => 4)
+ </td>
+ </tr>
+ <tr>
+ <td>rename_tag</td>
+ <td>
+ CALL [catalog.]sys.rename_tag(`table` => 'identifier', tagName =>
'tagName', targetTagName => 'newTagName')
+ </td>
+ <td>
+ Rename a tag. Arguments:
+ <li>table: the target table identifier.</li>
+ <li>tagName: the existing tag name.</li>
+ <li>targetTagName: the new tag name.</li>
+ </td>
+ <td>
+ CALL sys.rename_tag(`table` => 'default.T', tagName => 'tag1',
targetTagName => 'tag2')
+ </td>
+ </tr>
</tbody>
</table>
diff --git a/docs/docs/spark/procedures.md b/docs/docs/spark/procedures.md
index 4e2a01c51c..bcd046fb73 100644
--- a/docs/docs/spark/procedures.md
+++ b/docs/docs/spark/procedures.md
@@ -337,6 +337,17 @@ This section introduce all available spark procedures
about paimon.
CALL sys.repair('test_db.T,test_db01,test_db.T2')
</td>
</tr>
+ <tr>
+ <td>repair_earliest_snapshot</td>
+ <td>
+ Repair the earliest snapshot hint for a table. Arguments:
+ <li>table: the target table identifier. Cannot be empty.</li>
+ <li>snapshot_id: the snapshot ID to set as the earliest
snapshot.</li>
+ </td>
+ <td>
+ CALL sys.repair_earliest_snapshot(table => 'test_db.T', snapshot_id
=> 10)
+ </td>
+ </tr>
<tr>
<td>create_branch</td>
<td>
