From 21cabc7c65b8e190b5bc342e96a31bea35545263 Mon Sep 17 00:00:00 2001
From: Bichitra Kumar Sahoo <32828151+bichitra95@users.noreply.github.com>
Date: Mon, 24 Jul 2023 17:37:47 +0530
Subject: [PATCH] fix databricks datatype cast and support for int type decimal

---
 soda/spark/soda/data_sources/spark_data_source.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/soda/spark/soda/data_sources/spark_data_source.py b/soda/spark/soda/data_sources/spark_data_source.py
index b66b60eae..033f4ed82 100644
--- a/soda/spark/soda/data_sources/spark_data_source.py
+++ b/soda/spark/soda/data_sources/spark_data_source.py
@@ -425,6 +425,7 @@ class SparkDataSource(SparkSQLBase):
 
     def __init__(self, logs: Logs, data_source_name: str, data_source_properties: dict):
         super().__init__(logs, data_source_name, data_source_properties)
+        self.NUMERIC_TYPES_FOR_PROFILING = ["integer", "int", "double", "float", "decimal"]
 
         self.method = data_source_properties.get("method", "hive")
         self.host = data_source_properties.get("host", "localhost")
@@ -474,3 +475,6 @@ def connect(self):
             self.connection = connection
         except Exception as e:
             raise DataSourceConnectionError(self.type, e)
+
+    def cast_to_text(self, expr: str) -> str:
+        return f"CAST({expr} AS VARCHAR(100))"