zhengruifeng commented on code in PR #41561:
URL: https://github.com/apache/spark/pull/41561#discussion_r1232947734
##########
python/pyspark/sql/functions.py:
##########
@@ -8810,6 +8812,391 @@ def to_number(col: "ColumnOrName", format:
"ColumnOrName") -> Column:
return _invoke_function_over_columns("to_number", col, format)
+@try_remote_functions
+def char(col: "ColumnOrName") -> Column:
+ """
+ Returns the ASCII character having the binary equivalent to `col`. If col
is larger than 256 the
+ result is equivalent to char(col % 256)
+
+ .. versionadded:: 3.5.0
+
+ Parameters
+ ----------
+ col : :class:`~pyspark.sql.Column` or str
+ Input column or strings.
+
+ Examples
+ --------
+ >>> df = spark.createDataFrame([(65,)], ['a'])
+ >>> df.select(char(df.a).alias('r')).collect()
+ [Row(r='A')]
+ """
+ return _invoke_function_over_columns("char", col)
+
+
+@try_remote_functions
+def btrim(str: "ColumnOrName", trim: Optional["ColumnOrName"] = None) ->
Column:
+ """
+ Remove the leading and trailing `trim` characters from `str`.
+
+ .. versionadded:: 3.5.0
+
+ Parameters
+ ----------
+ str : :class:`~pyspark.sql.Column` or str
+ Input column or strings.
+ trim : :class:`~pyspark.sql.Column` or str
+ The trim string characters to trim, the default value is a single space
+
+ Examples
+ --------
+ >>> df = spark.createDataFrame([("SSparkSQLS", "SL", )], ['a', 'b'])
+ >>> df.select(btrim(df.a, df.b).alias('r')).collect()
+ [Row(r='parkSQ')]
+
+ >>> df = spark.createDataFrame([(" SparkSQL ",)], ['a'])
+ >>> df.select(btrim(df.a).alias('r')).collect()
+ [Row(r='SparkSQL')]
+ """
+ if trim is not None:
+ return _invoke_function_over_columns("btrim", str, trim)
+ else:
+ return _invoke_function_over_columns("btrim", str)
+
+
+@try_remote_functions
+def char_length(str: "ColumnOrName") -> Column:
+ """
+ Returns the character length of string data or number of bytes of binary
data.
+ The length of string data includes the trailing spaces.
+ The length of binary data includes binary zeros.
+
+ .. versionadded:: 3.5.0
+
+ Parameters
+ ----------
+ str : :class:`~pyspark.sql.Column` or str
+ Input column or strings.
+
+ Examples
+ --------
+ >>> df = spark.createDataFrame([("SparkSQL",)], ['a'])
+ >>> df.select(char_length(df.a).alias('r')).collect()
+ [Row(r=8)]
+ """
+ return _invoke_function_over_columns("char_length", str)
+
+
+@try_remote_functions
+def character_length(str: "ColumnOrName") -> Column:
+ """
+ Returns the character length of string data or number of bytes of binary
data.
+ The length of string data includes the trailing spaces.
+ The length of binary data includes binary zeros.
+
+ .. versionadded:: 3.5.0
+
+ Parameters
+ ----------
+ str : :class:`~pyspark.sql.Column` or str
+ Input column or strings.
+
+ Examples
+ --------
+ >>> df = spark.createDataFrame([("SparkSQL",)], ['a'])
+ >>> df.select(character_length(df.a).alias('r')).collect()
+ [Row(r=8)]
+ """
+ return _invoke_function_over_columns("character_length", str)
+
+
+@try_remote_functions
+def chr(col: "ColumnOrName") -> Column:
+ """
+ Returns the ASCII character having the binary equivalent to `col`.
+ If col is larger than 256 the result is equivalent to chr(col % 256)
+
+ .. versionadded:: 3.5.0
+
+ Parameters
+ ----------
+ col : :class:`~pyspark.sql.Column` or str
+ Input column or strings.
+
+ Examples
+ --------
+ >>> df = spark.createDataFrame([(65,)], ['a'])
+ >>> df.select(chr(df.a).alias('r')).collect()
+ [Row(r='A')]
+ """
+ return _invoke_function_over_columns("chr", col)
+
+
+@try_remote_functions
+def contains(left: "ColumnOrName", right: "ColumnOrName") -> Column:
+ """
+ Returns a boolean. The value is True if right is found inside left.
+ Returns NULL if either input expression is NULL. Otherwise, returns False.
+ Both left or right must be of STRING or BINARY type.
+
+ .. versionadded:: 3.5.0
+
+ Parameters
+ ----------
+ left : :class:`~pyspark.sql.Column` or str
+ The input column or strings to check, may be NULL.
+ right : :class:`~pyspark.sql.Column` or str
+ The input column or strings to find, may be NULL.
+
+ Examples
+ --------
+ >>> df = spark.createDataFrame([("Spark SQL", "Spark")], ['a', 'b'])
+ >>> df.select(contains(df.a, df.b).alias('r')).collect()
+ [Row(r=True)]
+ """
+ return _invoke_function_over_columns("contains", left, right)
+
+
+@try_remote_functions
+def elt(*inputs: "ColumnOrName") -> Column:
+ """
+ Returns the `n`-th input, e.g., returns `input2` when `n` is 2.
+ The function returns NULL if the index exceeds the length of the array
+ and `spark.sql.ansi.enabled` is set to false. If `spark.sql.ansi.enabled`
is set to true,
+ it throws ArrayIndexOutOfBoundsException for invalid indices.
+
+ .. versionadded:: 3.5.0
+
+ Parameters
+ ----------
+ inputs : :class:`~pyspark.sql.Column` or str
+ Input columns or strings.
+
+ Examples
+ --------
+ >>> df = spark.createDataFrame([(1, "scala", "java")], ['a', 'b', 'c'])
+ >>> df.select(elt(df.a, df.b, df.c).alias('r')).collect()
+ [Row(r='scala')]
+ """
+ sc = get_active_spark_context()
+ return _invoke_function("elt", _to_seq(sc, inputs, _to_java_column))
+
+
+@try_remote_functions
+def find_in_set(str: "ColumnOrName", str_array: "ColumnOrName") -> Column:
+ """
+ Returns the index (1-based) of the given string (`str`) in the
comma-delimited
+ list (`strArray`). Returns 0, if the string was not found or if the given
string (`str`)
+ contains a comma.
+
+ .. versionadded:: 3.5.0
+
+ Parameters
+ ----------
+ str : :class:`~pyspark.sql.Column` or str
+ The given string to be found.
+ str_array : :class:`~pyspark.sql.Column` or str
+ The comma-delimited list.
+
+ Examples
+ --------
+ >>> df = spark.createDataFrame([("ab", "abc,b,ab,c,def")], ['a', 'b'])
+ >>> df.select(find_in_set(df.a, df.b).alias('r')).collect()
+ [Row(r=3)]
+ """
+ return _invoke_function_over_columns("find_in_set", str, str_array)
+
+
+@try_remote_functions
+def like(
+ str: "ColumnOrName", pattern: "ColumnOrName", escapeChar: Optional["str"]
= None
Review Comment:
in this case, since `escapeChar` is a `Char` in the expression constructors,
I feel it is a bit confusing if we treat `str` input as a column name.
shall we follow the `Char` types in expression? or directly use `Column` for
both scala and python
also cc @HyukjinKwon
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
