SNOW-1348700 Fix to_char's implementation when incoming column has in…

…consecutive row index (#1702)

CHANGELOG.md

@@ -6,7 +6,6 @@
 
 #### Improvements
 
-
 #### Bug Fixes
 
 - Fixed a bug where python stored procedure with table return type fails when run in a task.
@@ -22,6 +21,7 @@
 - Fixed a bug in convert_timezone that made the setting the source_timezone parameter return an error.
 - Fixed a bug where creating DataFrame with empty data of type `DateType` raises `AttributeError`.
 - Fixed a bug that table merge fails when update clause exists but no update takes place.
+- Fixed a bug in mock implementation of `to_char` that raises `IndexError` when incoming column has inconsecutive row index.
 
 ### Snowpark pandas API Updates
 

src/snowflake/snowpark/mock/_functions.py

@@ -906,12 +906,10 @@ def mock_to_char(
     """
     source_datatype = column.sf_type.datatype
 
-    fmt = [fmt] * len(column) if not isinstance(fmt, ColumnEmulator) else fmt
-
-    def convert_char(row):
-        _fmt = fmt[row.name]
-        data = row[0]
+    if not isinstance(fmt, ColumnEmulator):
+        fmt = ColumnEmulator([fmt] * len(column), index=column.index)
 
+    def convert_char(data, _fmt):
         if isinstance(source_datatype, _NumericType):
             if _fmt:
                 # SNOW-1372863 to support https://docs.snowflake.com/en/sql-reference/sql-format-models
@@ -1025,8 +1023,7 @@ def convert_char(row):
                 raise_error=NotImplementedError,
             )
 
-    # row index information is needed to retrieve format information in another pd series, thus calling to_frame here
-    res = column.to_frame().apply(convert_char, axis=1)
+    res = column.combine(fmt, convert_char)
     res.sf_type = ColumnType(StringType(), column.sf_type.nullable)
     return res
 

tests/mock/test_functions.py

@@ -18,6 +18,7 @@
     lit,
     max,
     min,
+    to_char,
     to_date,
 )
 
@@ -281,3 +282,10 @@ def test_show(session):
 |3....|4   |de...|
 ----------------\n""".lstrip()
     )
+
+
+def test_to_char_is_row_index_agnostic(session):
+    df = session.create_dataframe([[1, 2], [3, 4], [5, 6]], schema=["a", "b"])
+    assert df.filter(col("a") > 3).select(to_char(col("a")), col("b")).collect() == [
+        Row("5", 6)
+    ]