zhengruifeng commented on code in PR #49338:
URL: https://github.com/apache/spark/pull/49338#discussion_r1900491893
##########
python/pyspark/sql/functions/builtin.py:
##########
@@ -15341,13 +15341,32 @@ def regexp_count(str: "ColumnOrName", regexp:
"ColumnOrName") -> Column:
Examples
--------
+ >>> from pyspark.sql import functions as sf
>>> df = spark.createDataFrame([("1a 2b 14m", r"\d+")], ["str", "regexp"])
- >>> df.select(regexp_count('str', lit(r'\d+')).alias('d')).collect()
- [Row(d=3)]
- >>> df.select(regexp_count('str', lit(r'mmm')).alias('d')).collect()
- [Row(d=0)]
- >>> df.select(regexp_count("str", col("regexp")).alias('d')).collect()
- [Row(d=3)]
+ >>> df.select('*', sf.regexp_count('str', sf.lit(r'\d+'))).show()
+ +---------+------+----------------------+
+ | str|regexp|regexp_count(str, \d+)|
+ +---------+------+----------------------+
+ |1a 2b 14m| \d+| 3|
+ +---------+------+----------------------+
+ >>> df.select('*', sf.regexp_count('str', sf.lit(r'mmm'))).show()
+ +---------+------+----------------------+
+ | str|regexp|regexp_count(str, mmm)|
+ +---------+------+----------------------+
+ |1a 2b 14m| \d+| 0|
+ +---------+------+----------------------+
Review Comment:
```suggestion
+---------+------+----------------------+
```
##########
python/pyspark/sql/functions/builtin.py:
##########
@@ -15406,29 +15442,57 @@ def regexp_extract_all(
Parameters
----------
- str : :class:`~pyspark.sql.Column` or str
+ str : :class:`~pyspark.sql.Column` or column name
target column to work on.
- regexp : :class:`~pyspark.sql.Column` or str
+ regexp : :class:`~pyspark.sql.Column` or column name
regex pattern to apply.
- idx : int, optional
+ idx : :class:`~pyspark.sql.Column` or int, optional
matched group id.
Returns
-------
:class:`~pyspark.sql.Column`
all strings in the `str` that match a Java regex and corresponding to
the regex group index.
+ See Also
+ --------
+ :meth:`pyspark.sql.functions.regexp_extract`
+
Examples
--------
+ >>> from pyspark.sql import functions as sf
>>> df = spark.createDataFrame([("100-200, 300-400", r"(\d+)-(\d+)")],
["str", "regexp"])
- >>> df.select(regexp_extract_all('str',
lit(r'(\d+)-(\d+)')).alias('d')).collect()
- [Row(d=['100', '300'])]
- >>> df.select(regexp_extract_all('str', lit(r'(\d+)-(\d+)'),
1).alias('d')).collect()
- [Row(d=['100', '300'])]
- >>> df.select(regexp_extract_all('str', lit(r'(\d+)-(\d+)'),
2).alias('d')).collect()
- [Row(d=['200', '400'])]
- >>> df.select(regexp_extract_all('str',
col("regexp")).alias('d')).collect()
- [Row(d=['100', '300'])]
+ >>> df.select('*', sf.regexp_extract_all('str',
sf.lit(r'(\d+)-(\d+)'))).show()
+ +----------------+-----------+---------------------------------------+
+ | str| regexp|regexp_extract_all(str, (\d+)-(\d+), 1)|
+ +----------------+-----------+---------------------------------------+
+ |100-200, 300-400|(\d+)-(\d+)| [100, 300]|
+ +----------------+-----------+---------------------------------------+
+ >>> df.select('*', sf.regexp_extract_all('str', sf.lit(r'(\d+)-(\d+)'),
sf.lit(1))).show()
+ +----------------+-----------+---------------------------------------+
+ | str| regexp|regexp_extract_all(str, (\d+)-(\d+), 1)|
+ +----------------+-----------+---------------------------------------+
+ |100-200, 300-400|(\d+)-(\d+)| [100, 300]|
+ +----------------+-----------+---------------------------------------+
Review Comment:
```suggestion
+----------------+-----------+---------------------------------------+
```
##########
python/pyspark/sql/functions/builtin.py:
##########
@@ -15341,13 +15341,32 @@ def regexp_count(str: "ColumnOrName", regexp:
"ColumnOrName") -> Column:
Examples
--------
+ >>> from pyspark.sql import functions as sf
>>> df = spark.createDataFrame([("1a 2b 14m", r"\d+")], ["str", "regexp"])
- >>> df.select(regexp_count('str', lit(r'\d+')).alias('d')).collect()
- [Row(d=3)]
- >>> df.select(regexp_count('str', lit(r'mmm')).alias('d')).collect()
- [Row(d=0)]
- >>> df.select(regexp_count("str", col("regexp")).alias('d')).collect()
- [Row(d=3)]
+ >>> df.select('*', sf.regexp_count('str', sf.lit(r'\d+'))).show()
+ +---------+------+----------------------+
+ | str|regexp|regexp_count(str, \d+)|
+ +---------+------+----------------------+
+ |1a 2b 14m| \d+| 3|
+ +---------+------+----------------------+
+ >>> df.select('*', sf.regexp_count('str', sf.lit(r'mmm'))).show()
+ +---------+------+----------------------+
+ | str|regexp|regexp_count(str, mmm)|
+ +---------+------+----------------------+
+ |1a 2b 14m| \d+| 0|
+ +---------+------+----------------------+
+ >>> df.select('*', sf.regexp_count("str", sf.col("regexp"))).show()
+ +---------+------+-------------------------+
+ | str|regexp|regexp_count(str, regexp)|
+ +---------+------+-------------------------+
+ |1a 2b 14m| \d+| 3|
+ +---------+------+-------------------------+
Review Comment:
```suggestion
+---------+------+-------------------------+
```
##########
python/pyspark/sql/functions/builtin.py:
##########
@@ -15341,13 +15341,32 @@ def regexp_count(str: "ColumnOrName", regexp:
"ColumnOrName") -> Column:
Examples
--------
+ >>> from pyspark.sql import functions as sf
>>> df = spark.createDataFrame([("1a 2b 14m", r"\d+")], ["str", "regexp"])
- >>> df.select(regexp_count('str', lit(r'\d+')).alias('d')).collect()
- [Row(d=3)]
- >>> df.select(regexp_count('str', lit(r'mmm')).alias('d')).collect()
- [Row(d=0)]
- >>> df.select(regexp_count("str", col("regexp")).alias('d')).collect()
- [Row(d=3)]
+ >>> df.select('*', sf.regexp_count('str', sf.lit(r'\d+'))).show()
+ +---------+------+----------------------+
+ | str|regexp|regexp_count(str, \d+)|
+ +---------+------+----------------------+
+ |1a 2b 14m| \d+| 3|
+ +---------+------+----------------------+
Review Comment:
```suggestion
+---------+------+----------------------+
```
##########
python/pyspark/sql/functions/builtin.py:
##########
@@ -15376,17 +15395,34 @@ def regexp_extract(str: "ColumnOrName", pattern: str,
idx: int) -> Column:
:class:`~pyspark.sql.Column`
matched value specified by `idx` group id.
+ See Also
+ --------
+ :meth:`pyspark.sql.functions.regexp_extract_all`
+
Examples
--------
+ >>> from pyspark.sql import functions as sf
>>> df = spark.createDataFrame([('100-200',)], ['str'])
- >>> df.select(regexp_extract('str', r'(\d+)-(\d+)',
1).alias('d')).collect()
- [Row(d='100')]
+ >>> df.select('*', sf.regexp_extract('str', r'(\d+)-(\d+)', 1)).show()
+ +-------+-----------------------------------+
+ | str|regexp_extract(str, (\d+)-(\d+), 1)|
+ +-------+-----------------------------------+
+ |100-200| 100|
+ +-------+-----------------------------------+
Review Comment:
```suggestion
+-------+-----------------------------------+
```
##########
python/pyspark/sql/functions/builtin.py:
##########
@@ -15406,29 +15442,57 @@ def regexp_extract_all(
Parameters
----------
- str : :class:`~pyspark.sql.Column` or str
+ str : :class:`~pyspark.sql.Column` or column name
target column to work on.
- regexp : :class:`~pyspark.sql.Column` or str
+ regexp : :class:`~pyspark.sql.Column` or column name
regex pattern to apply.
- idx : int, optional
+ idx : :class:`~pyspark.sql.Column` or int, optional
matched group id.
Returns
-------
:class:`~pyspark.sql.Column`
all strings in the `str` that match a Java regex and corresponding to
the regex group index.
+ See Also
+ --------
+ :meth:`pyspark.sql.functions.regexp_extract`
+
Examples
--------
+ >>> from pyspark.sql import functions as sf
>>> df = spark.createDataFrame([("100-200, 300-400", r"(\d+)-(\d+)")],
["str", "regexp"])
- >>> df.select(regexp_extract_all('str',
lit(r'(\d+)-(\d+)')).alias('d')).collect()
- [Row(d=['100', '300'])]
- >>> df.select(regexp_extract_all('str', lit(r'(\d+)-(\d+)'),
1).alias('d')).collect()
- [Row(d=['100', '300'])]
- >>> df.select(regexp_extract_all('str', lit(r'(\d+)-(\d+)'),
2).alias('d')).collect()
- [Row(d=['200', '400'])]
- >>> df.select(regexp_extract_all('str',
col("regexp")).alias('d')).collect()
- [Row(d=['100', '300'])]
+ >>> df.select('*', sf.regexp_extract_all('str',
sf.lit(r'(\d+)-(\d+)'))).show()
+ +----------------+-----------+---------------------------------------+
+ | str| regexp|regexp_extract_all(str, (\d+)-(\d+), 1)|
+ +----------------+-----------+---------------------------------------+
+ |100-200, 300-400|(\d+)-(\d+)| [100, 300]|
+ +----------------+-----------+---------------------------------------+
+ >>> df.select('*', sf.regexp_extract_all('str', sf.lit(r'(\d+)-(\d+)'),
sf.lit(1))).show()
+ +----------------+-----------+---------------------------------------+
+ | str| regexp|regexp_extract_all(str, (\d+)-(\d+), 1)|
+ +----------------+-----------+---------------------------------------+
+ |100-200, 300-400|(\d+)-(\d+)| [100, 300]|
+ +----------------+-----------+---------------------------------------+
+ >>> df.select('*', sf.regexp_extract_all('str', sf.lit(r'(\d+)-(\d+)'),
2)).show()
+ +----------------+-----------+---------------------------------------+
+ | str| regexp|regexp_extract_all(str, (\d+)-(\d+), 2)|
+ +----------------+-----------+---------------------------------------+
+ |100-200, 300-400|(\d+)-(\d+)| [200, 400]|
+ +----------------+-----------+---------------------------------------+
+ >>> df.select('*', sf.regexp_extract_all('str', sf.col("regexp"))).show()
+ +----------------+-----------+----------------------------------+
+ | str| regexp|regexp_extract_all(str, regexp, 1)|
+ +----------------+-----------+----------------------------------+
+ |100-200, 300-400|(\d+)-(\d+)| [100, 300]|
+ +----------------+-----------+----------------------------------+
Review Comment:
```suggestion
+----------------+-----------+----------------------------------+
```
##########
python/pyspark/sql/functions/builtin.py:
##########
@@ -15406,29 +15442,57 @@ def regexp_extract_all(
Parameters
----------
- str : :class:`~pyspark.sql.Column` or str
+ str : :class:`~pyspark.sql.Column` or column name
target column to work on.
- regexp : :class:`~pyspark.sql.Column` or str
+ regexp : :class:`~pyspark.sql.Column` or column name
regex pattern to apply.
- idx : int, optional
+ idx : :class:`~pyspark.sql.Column` or int, optional
matched group id.
Returns
-------
:class:`~pyspark.sql.Column`
all strings in the `str` that match a Java regex and corresponding to
the regex group index.
+ See Also
+ --------
+ :meth:`pyspark.sql.functions.regexp_extract`
+
Examples
--------
+ >>> from pyspark.sql import functions as sf
>>> df = spark.createDataFrame([("100-200, 300-400", r"(\d+)-(\d+)")],
["str", "regexp"])
- >>> df.select(regexp_extract_all('str',
lit(r'(\d+)-(\d+)')).alias('d')).collect()
- [Row(d=['100', '300'])]
- >>> df.select(regexp_extract_all('str', lit(r'(\d+)-(\d+)'),
1).alias('d')).collect()
- [Row(d=['100', '300'])]
- >>> df.select(regexp_extract_all('str', lit(r'(\d+)-(\d+)'),
2).alias('d')).collect()
- [Row(d=['200', '400'])]
- >>> df.select(regexp_extract_all('str',
col("regexp")).alias('d')).collect()
- [Row(d=['100', '300'])]
+ >>> df.select('*', sf.regexp_extract_all('str',
sf.lit(r'(\d+)-(\d+)'))).show()
+ +----------------+-----------+---------------------------------------+
+ | str| regexp|regexp_extract_all(str, (\d+)-(\d+), 1)|
+ +----------------+-----------+---------------------------------------+
+ |100-200, 300-400|(\d+)-(\d+)| [100, 300]|
+ +----------------+-----------+---------------------------------------+
+ >>> df.select('*', sf.regexp_extract_all('str', sf.lit(r'(\d+)-(\d+)'),
sf.lit(1))).show()
+ +----------------+-----------+---------------------------------------+
+ | str| regexp|regexp_extract_all(str, (\d+)-(\d+), 1)|
+ +----------------+-----------+---------------------------------------+
+ |100-200, 300-400|(\d+)-(\d+)| [100, 300]|
+ +----------------+-----------+---------------------------------------+
+ >>> df.select('*', sf.regexp_extract_all('str', sf.lit(r'(\d+)-(\d+)'),
2)).show()
+ +----------------+-----------+---------------------------------------+
+ | str| regexp|regexp_extract_all(str, (\d+)-(\d+), 2)|
+ +----------------+-----------+---------------------------------------+
+ |100-200, 300-400|(\d+)-(\d+)| [200, 400]|
+ +----------------+-----------+---------------------------------------+
Review Comment:
```suggestion
+----------------+-----------+---------------------------------------+
```
##########
python/pyspark/sql/functions/builtin.py:
##########
@@ -15376,17 +15395,34 @@ def regexp_extract(str: "ColumnOrName", pattern: str,
idx: int) -> Column:
:class:`~pyspark.sql.Column`
matched value specified by `idx` group id.
+ See Also
+ --------
+ :meth:`pyspark.sql.functions.regexp_extract_all`
+
Examples
--------
+ >>> from pyspark.sql import functions as sf
>>> df = spark.createDataFrame([('100-200',)], ['str'])
- >>> df.select(regexp_extract('str', r'(\d+)-(\d+)',
1).alias('d')).collect()
- [Row(d='100')]
+ >>> df.select('*', sf.regexp_extract('str', r'(\d+)-(\d+)', 1)).show()
+ +-------+-----------------------------------+
+ | str|regexp_extract(str, (\d+)-(\d+), 1)|
+ +-------+-----------------------------------+
+ |100-200| 100|
+ +-------+-----------------------------------+
>>> df = spark.createDataFrame([('foo',)], ['str'])
- >>> df.select(regexp_extract('str', r'(\d+)', 1).alias('d')).collect()
- [Row(d='')]
+ >>> df.select('*', sf.regexp_extract('str', r'(\d+)', 1)).show()
+ +---+-----------------------------+
+ |str|regexp_extract(str, (\d+), 1)|
+ +---+-----------------------------+
+ |foo| |
+ +---+-----------------------------+
Review Comment:
```suggestion
+---+-----------------------------+
```
##########
python/pyspark/sql/functions/builtin.py:
##########
@@ -15406,29 +15442,57 @@ def regexp_extract_all(
Parameters
----------
- str : :class:`~pyspark.sql.Column` or str
+ str : :class:`~pyspark.sql.Column` or column name
target column to work on.
- regexp : :class:`~pyspark.sql.Column` or str
+ regexp : :class:`~pyspark.sql.Column` or column name
regex pattern to apply.
- idx : int, optional
+ idx : :class:`~pyspark.sql.Column` or int, optional
matched group id.
Returns
-------
:class:`~pyspark.sql.Column`
all strings in the `str` that match a Java regex and corresponding to
the regex group index.
+ See Also
+ --------
+ :meth:`pyspark.sql.functions.regexp_extract`
+
Examples
--------
+ >>> from pyspark.sql import functions as sf
>>> df = spark.createDataFrame([("100-200, 300-400", r"(\d+)-(\d+)")],
["str", "regexp"])
- >>> df.select(regexp_extract_all('str',
lit(r'(\d+)-(\d+)')).alias('d')).collect()
- [Row(d=['100', '300'])]
- >>> df.select(regexp_extract_all('str', lit(r'(\d+)-(\d+)'),
1).alias('d')).collect()
- [Row(d=['100', '300'])]
- >>> df.select(regexp_extract_all('str', lit(r'(\d+)-(\d+)'),
2).alias('d')).collect()
- [Row(d=['200', '400'])]
- >>> df.select(regexp_extract_all('str',
col("regexp")).alias('d')).collect()
- [Row(d=['100', '300'])]
+ >>> df.select('*', sf.regexp_extract_all('str',
sf.lit(r'(\d+)-(\d+)'))).show()
+ +----------------+-----------+---------------------------------------+
+ | str| regexp|regexp_extract_all(str, (\d+)-(\d+), 1)|
+ +----------------+-----------+---------------------------------------+
+ |100-200, 300-400|(\d+)-(\d+)| [100, 300]|
+ +----------------+-----------+---------------------------------------+
+ >>> df.select('*', sf.regexp_extract_all('str', sf.lit(r'(\d+)-(\d+)'),
sf.lit(1))).show()
+ +----------------+-----------+---------------------------------------+
+ | str| regexp|regexp_extract_all(str, (\d+)-(\d+), 1)|
+ +----------------+-----------+---------------------------------------+
+ |100-200, 300-400|(\d+)-(\d+)| [100, 300]|
+ +----------------+-----------+---------------------------------------+
+ >>> df.select('*', sf.regexp_extract_all('str', sf.lit(r'(\d+)-(\d+)'),
2)).show()
+ +----------------+-----------+---------------------------------------+
+ | str| regexp|regexp_extract_all(str, (\d+)-(\d+), 2)|
+ +----------------+-----------+---------------------------------------+
+ |100-200, 300-400|(\d+)-(\d+)| [200, 400]|
+ +----------------+-----------+---------------------------------------+
+ >>> df.select('*', sf.regexp_extract_all('str', sf.col("regexp"))).show()
+ +----------------+-----------+----------------------------------+
+ | str| regexp|regexp_extract_all(str, regexp, 1)|
+ +----------------+-----------+----------------------------------+
+ |100-200, 300-400|(\d+)-(\d+)| [100, 300]|
+ +----------------+-----------+----------------------------------+
+ >>> df.select('*', sf.regexp_extract_all(sf.col('str'), "regexp")).show()
+ +----------------+-----------+----------------------------------+
+ | str| regexp|regexp_extract_all(str, regexp, 1)|
+ +----------------+-----------+----------------------------------+
+ |100-200, 300-400|(\d+)-(\d+)| [100, 300]|
+ +----------------+-----------+----------------------------------+
+
Review Comment:
```suggestion
```
##########
python/pyspark/sql/functions/builtin.py:
##########
@@ -15406,29 +15442,57 @@ def regexp_extract_all(
Parameters
----------
- str : :class:`~pyspark.sql.Column` or str
+ str : :class:`~pyspark.sql.Column` or column name
target column to work on.
- regexp : :class:`~pyspark.sql.Column` or str
+ regexp : :class:`~pyspark.sql.Column` or column name
regex pattern to apply.
- idx : int, optional
+ idx : :class:`~pyspark.sql.Column` or int, optional
matched group id.
Returns
-------
:class:`~pyspark.sql.Column`
all strings in the `str` that match a Java regex and corresponding to
the regex group index.
+ See Also
+ --------
+ :meth:`pyspark.sql.functions.regexp_extract`
+
Examples
--------
+ >>> from pyspark.sql import functions as sf
>>> df = spark.createDataFrame([("100-200, 300-400", r"(\d+)-(\d+)")],
["str", "regexp"])
- >>> df.select(regexp_extract_all('str',
lit(r'(\d+)-(\d+)')).alias('d')).collect()
- [Row(d=['100', '300'])]
- >>> df.select(regexp_extract_all('str', lit(r'(\d+)-(\d+)'),
1).alias('d')).collect()
- [Row(d=['100', '300'])]
- >>> df.select(regexp_extract_all('str', lit(r'(\d+)-(\d+)'),
2).alias('d')).collect()
- [Row(d=['200', '400'])]
- >>> df.select(regexp_extract_all('str',
col("regexp")).alias('d')).collect()
- [Row(d=['100', '300'])]
+ >>> df.select('*', sf.regexp_extract_all('str',
sf.lit(r'(\d+)-(\d+)'))).show()
+ +----------------+-----------+---------------------------------------+
+ | str| regexp|regexp_extract_all(str, (\d+)-(\d+), 1)|
+ +----------------+-----------+---------------------------------------+
+ |100-200, 300-400|(\d+)-(\d+)| [100, 300]|
+ +----------------+-----------+---------------------------------------+
Review Comment:
```suggestion
+----------------+-----------+---------------------------------------+
```
--
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
