zhengruifeng commented on code in PR #46711:
URL: https://github.com/apache/spark/pull/46711#discussion_r1610916678
##########
python/pyspark/sql/tests/test_types.py:
##########
@@ -1411,6 +1412,72 @@ def test_tree_string(self):
],
)
+ def test_tree_string_for_builtin_types(self):
+ schema = (
+ StructType()
+ .add("n", NullType())
+ .add("str", StringType())
+ .add("c", CharType(10))
+ .add("v", VarcharType(10))
+ .add("bin", BinaryType())
+ .add("bool", BooleanType())
+ .add("date", DateType())
+ .add("ts", TimestampType())
+ .add("ts_ntz", TimestampNTZType())
+ .add("dec", DecimalType(10, 2))
+ .add("double", DoubleType())
+ .add("float", FloatType())
+ .add("long", LongType())
+ .add("int", IntegerType())
+ .add("short", ShortType())
+ .add("byte", ByteType())
+ .add("ym_interval_1", YearMonthIntervalType())
+ .add("ym_interval_2",
YearMonthIntervalType(YearMonthIntervalType.YEAR))
+ .add(
+ "ym_interval_3",
+ YearMonthIntervalType(YearMonthIntervalType.YEAR,
YearMonthIntervalType.MONTH),
+ )
+ .add("dt_interval_1", DayTimeIntervalType())
+ .add("dt_interval_2", DayTimeIntervalType(DayTimeIntervalType.DAY))
+ .add(
+ "dt_interval_3",
+ DayTimeIntervalType(DayTimeIntervalType.HOUR,
DayTimeIntervalType.SECOND),
+ )
+ .add("cal_interval", CalendarIntervalType())
+ .add("var", VariantType())
+ )
+ self.assertEqual(
+ schema.treeString().split("\n"),
+ [
+ "root",
+ " |-- n: void (nullable = true)",
+ " |-- str: string (nullable = true)",
+ " |-- c: char(10) (nullable = true)",
+ " |-- v: varchar(10) (nullable = true)",
+ " |-- bin: binary (nullable = true)",
+ " |-- bool: boolean (nullable = true)",
+ " |-- date: date (nullable = true)",
+ " |-- ts: timestamp (nullable = true)",
+ " |-- ts_ntz: timestamp_ntz (nullable = true)",
+ " |-- dec: decimal(10,2) (nullable = true)",
+ " |-- double: double (nullable = true)",
+ " |-- float: float (nullable = true)",
+ " |-- long: long (nullable = true)",
+ " |-- int: integer (nullable = true)",
+ " |-- short: short (nullable = true)",
+ " |-- byte: byte (nullable = true)",
+ " |-- ym_interval_1: interval year to month (nullable = true)",
+ " |-- ym_interval_2: interval year (nullable = true)",
+ " |-- ym_interval_3: interval year to month (nullable = true)",
+ " |-- dt_interval_1: interval day to second (nullable = true)",
+ " |-- dt_interval_2: interval day (nullable = true)",
+ " |-- dt_interval_3: interval hour to second (nullable =
true)",
+ " |-- cal_interval: interval (nullable = true)",
+ " |-- var: variant (nullable = true)",
+ "",
+ ],
+ )
Review Comment:
checked with scala side:
```
scala> val schema = new StructType().add("n", NullType).add("str",
StringType).add("c", CharType(10)).add("v", VarcharType(10)).add("bin",
BinaryType).add("bool", BooleanType).add("date", DateType).add("ts",
TimestampType).add("ts_ntz", TimestampNTZType).add("dec", DecimalType(10,
2)).add("double", DoubleType).add("float", FloatType).add("long",
LongType).add("int", IntegerType).add("short", ShortType).add("byte",
ByteType).add("ym_interval_1", YearMonthIntervalType()).add("ym_interval_2",
YearMonthIntervalType(YearMonthIntervalType.YEAR)).add("ym_interval_3",YearMonthIntervalType(YearMonthIntervalType.YEAR,
YearMonthIntervalType.MONTH)).add("dt_interval_1",
DayTimeIntervalType()).add("dt_interval_2",
DayTimeIntervalType(DayTimeIntervalType.DAY)).add("dt_interval_3",
DayTimeIntervalType(DayTimeIntervalType.HOUR,
DayTimeIntervalType.SECOND)).add("cal_interval",
CalendarIntervalType).add("var", VariantType)
val schema: org.apache.spark.sql.types.StructType =
StructType(StructField(n,NullType,true),StructField(str,StringType,true),StructField(c,CharType(10),true),StructField(v,VarcharType(10),true),StructField(bin,BinaryType,true),StructField(bool,BooleanType,true),StructField(date,DateType,true),StructField(ts,TimestampType,true),StructField(ts_ntz,TimestampNTZType,true),StructField(dec,DecimalType(10,2),true),StructField(double,DoubleType,true),StructField(float,FloatType,true),StructField(long,LongType,true),StructField(int,IntegerType,true),StructField(short,ShortType,true),StructField(byte,ByteType,true),StructField(ym_interval_1,YearMonthIntervalType(0,1),true),StructField(ym_interval_2,YearMonthIntervalType(0,0),true),StructField(ym_interval_3,YearMonthInter...
scala> println(schema.treeString)
root
|-- n: void (nullable = true)
|-- str: string (nullable = true)
|-- c: char(10) (nullable = true)
|-- v: varchar(10) (nullable = true)
|-- bin: binary (nullable = true)
|-- bool: boolean (nullable = true)
|-- date: date (nullable = true)
|-- ts: timestamp (nullable = true)
|-- ts_ntz: timestamp_ntz (nullable = true)
|-- dec: decimal(10,2) (nullable = true)
|-- double: double (nullable = true)
|-- float: float (nullable = true)
|-- long: long (nullable = true)
|-- int: integer (nullable = true)
|-- short: short (nullable = true)
|-- byte: byte (nullable = true)
|-- ym_interval_1: interval year to month (nullable = true)
|-- ym_interval_2: interval year (nullable = true)
|-- ym_interval_3: interval year to month (nullable = true)
|-- dt_interval_1: interval day to second (nullable = true)
|-- dt_interval_2: interval day (nullable = true)
|-- dt_interval_3: interval hour to second (nullable = true)
|-- cal_interval: interval (nullable = true)
|-- var: variant (nullable = true)
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
