From 5344bade8efb6f12aa43fbfbbbc2e3c0c7d16d98 Mon Sep 17 00:00:00 2001 From: WeichenXu <WeichenXu123@outlook.com> Date: Thu, 30 Jun 2016 23:00:39 +0800 Subject: [PATCH] [SPARK-15820][PYSPARK][SQL] Add Catalog.refreshTable into python API ## What changes were proposed in this pull request? Add Catalog.refreshTable API into python interface for Spark-SQL. ## How was this patch tested? Existing test. Author: WeichenXu <WeichenXu123@outlook.com> Closes #13558 from WeichenXu123/update_python_sql_interface_refreshTable. --- python/pyspark/sql/catalog.py | 5 +++++ .../main/scala/org/apache/spark/sql/catalog/Catalog.scala | 2 +- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/python/pyspark/sql/catalog.py b/python/pyspark/sql/catalog.py index 3033f147bc..4af930a3cd 100644 --- a/python/pyspark/sql/catalog.py +++ b/python/pyspark/sql/catalog.py @@ -232,6 +232,11 @@ class Catalog(object): """Removes all cached tables from the in-memory cache.""" self._jcatalog.clearCache() + @since(2.0) + def refreshTable(self, tableName): + """Invalidate and refresh all the cached metadata of the given table.""" + self._jcatalog.refreshTable(tableName) + def _reset(self): """(Internal use only) Drop all existing databases (except "default"), tables, partitions and functions, and set the current database to "default". diff --git a/sql/core/src/main/scala/org/apache/spark/sql/catalog/Catalog.scala b/sql/core/src/main/scala/org/apache/spark/sql/catalog/Catalog.scala index 083a63c98c..91ed9b3258 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/catalog/Catalog.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/catalog/Catalog.scala @@ -214,7 +214,7 @@ abstract class Catalog { def clearCache(): Unit /** - * Invalidate and refresh all the cached the metadata of the given table. For performance reasons, + * Invalidate and refresh all the cached metadata of the given table. For performance reasons, * Spark SQL or the external data source library it uses might cache certain metadata about a * table, such as the location of blocks. When those change outside of Spark SQL, users should * call this function to invalidate the cache. -- GitLab