zhengruifeng commented on code in PR #48143:
URL: https://github.com/apache/spark/pull/48143#discussion_r1772793721
##########
python/pyspark/sql/connect/functions/builtin.py:
##########
@@ -2578,6 +2594,16 @@ def regexp_like(str: "ColumnOrName", regexp:
"ColumnOrName") -> Column:
regexp_like.__doc__ = pysparkfuncs.regexp_like.__doc__
+def randstr(length: Union[Column, int], seed: Optional[Union[Column, int]] =
None) -> Column:
+ if seed is None:
+ return _invoke_function_over_columns("randstr", length,
lit(random.randint(0, sys.maxsize)))
Review Comment:
```suggestion
return _invoke_function_over_columns("randstr", lit(length),
lit(random.randint(0, sys.maxsize)))
```
##########
python/pyspark/sql/connect/functions/builtin.py:
##########
@@ -2578,6 +2594,16 @@ def regexp_like(str: "ColumnOrName", regexp:
"ColumnOrName") -> Column:
regexp_like.__doc__ = pysparkfuncs.regexp_like.__doc__
+def randstr(length: Union[Column, int], seed: Optional[Union[Column, int]] =
None) -> Column:
+ if seed is None:
+ return _invoke_function_over_columns("randstr", length,
lit(random.randint(0, sys.maxsize)))
+ else:
+ return _invoke_function_over_columns("randstr", length, seed)
Review Comment:
```suggestion
return _invoke_function_over_columns("randstr", lit(length),
lit(seed))
```
##########
python/pyspark/sql/connect/functions/builtin.py:
##########
@@ -1008,6 +1008,22 @@ def unhex(col: "ColumnOrName") -> Column:
unhex.__doc__ = pysparkfuncs.unhex.__doc__
+def uniform(
+ min: Union[Column, int, float],
+ max: Union[Column, int, float],
+ seed: Optional[Union[Column, int]] = None,
+) -> Column:
+ if seed is None:
+ return _invoke_function_over_columns(
+ "uniform", min, max, lit(random.randint(0, sys.maxsize))
+ )
+ else:
+ return _invoke_function_over_columns("uniform", min, max, seed)
Review Comment:
```suggestion
return _invoke_function_over_columns("uniform", lit(min), lit(max),
lit(seed))
```
##########
python/pyspark/sql/connect/functions/builtin.py:
##########
@@ -1008,6 +1008,22 @@ def unhex(col: "ColumnOrName") -> Column:
unhex.__doc__ = pysparkfuncs.unhex.__doc__
+def uniform(
+ min: Union[Column, int, float],
+ max: Union[Column, int, float],
+ seed: Optional[Union[Column, int]] = None,
+) -> Column:
+ if seed is None:
+ return _invoke_function_over_columns(
+ "uniform", min, max, lit(random.randint(0, sys.maxsize))
Review Comment:
`_invoke_function_over_columns` requires arguments be columns or column names
```suggestion
"uniform", lit(min), lit(max), lit(random.randint(0,
sys.maxsize))
```
##########
python/pyspark/sql/functions/builtin.py:
##########
@@ -11861,6 +11861,47 @@ def regexp_like(str: "ColumnOrName", regexp:
"ColumnOrName") -> Column:
return _invoke_function_over_columns("regexp_like", str, regexp)
+@_try_remote_functions
+def randstr(length: Union[Column, int], seed: Optional[Union[Column, int]] =
None) -> Column:
+ """Returns a string of the specified length whose characters are chosen
uniformly at random from
+ the following pool of characters: 0-9, a-z, A-Z. The random seed is
optional. The string length
+ must be a constant two-byte or four-byte integer (SMALLINT or INT,
respectively).
+
+ .. versionadded:: 4.0.0
+
+ Parameters
+ ----------
+ length : :class:`~pyspark.sql.Column` or int
+ Number of characters in the string to generate.
+ seed : :class:`~pyspark.sql.Column` or int
+ Optional random number seed to use.
+
+ Returns
+ -------
+ :class:`~pyspark.sql.Column`
+ The generated random string with the specified length.
+
+ Examples
+ --------
+ >>> spark.createDataFrame([('3',)], ['a']) \\
+ ... .select(randstr(lit(5), lit(0)).alias('result')) \\
+ ... .selectExpr("length(result) > 0").show()
+ +--------------------+
+ |(length(result) > 0)|
+ +--------------------+
+ | true|
+ +--------------------+
+ """
+ length = _enum_to_value(length)
+ length = lit(length) if isinstance(length, int) else length
Review Comment:
nit: `lit` function accepts both literals and Column
--
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
