snuyanzin commented on code in PR #28688:
URL: https://github.com/apache/flink/pull/28688#discussion_r3619767662
##########
flink-python/pyflink/table/expression.py:
##########
@@ -2257,6 +2257,64 @@ def json_unquote(self) -> 'Expression':
"""
return _unary_op("jsonUnquote")(self)
+ def json_length(self, path = None) -> 'Expression':
+ """
+ Returns the number of elements in a JSON document, or the length of
the value at the
+ specified path if one is provided.
+
+ Returns None if the argument is None, the input is not valid JSON, or
the path
+ does not locate a value.
+
+ The length is determined as follows:
+
+ - Scalar values (number, string, boolean) have length 1.
+ - Arrays have a length equal to the number of their elements.
+ - Objects have a length equal to the number of their key-value pairs.
+
+ For the path argument, use the form:
+
+ path ::= '$' ( '.' <field> | '[' <index> ']' )*
+ field ::= a key in a JSON object
+ index ::= a zero-based position in a JSON array
+
+ When provided with a path that uses a wildcard and resolves to 2 or
more paths,
+ 'json_length' resolves to None.
+
+ Because a None result can mean several different things (the input is
not valid
+ JSON, the path does not match anything, or a wildcard path matched 2
or more
+ nodes), it is recommended to pair json_length with a helper function
so invalid
+ input is handled explicitly rather than silently returning None:
+
+ - Without a path, guard the call with is_json to separate malformed
input from a
+ real result.
+ - With a path, use json_exists to tell "the path is absent" apart from
"the path
+ matched but was ambiguous / matched 2 or more nodes".
+
+ ::
+
+ # returns the length only for valid JSON, otherwise None means
"invalid input"
+ >>> lit("[1,2,3]").is_json().then(lit("[1,2,3]").json_length(),
null_of(DataTypes.INT()))
+
+ # path is present even when json_length is None due to a
multi-match wildcard
+ >>> lit("{}").json_exists("$.items[*]")
+ >>> lit("{}").json_length("$.items[*]")
+
+ Examples:
+ ::
+
+ >>> lit('{"1": "hello", "2": "bye bye"}').json_length() # 2
+ >>> lit('[1,2,3,4,5]').json_length() # 5
+ >>> lit('"hello"').json_length() # 1
+
+ >>> lit('{"1": "hello", "2": "bye bye"}').json_length('$.1') # 1
+ >>> lit('{"1": [1,2,3], "2": "bye bye"}').json_length('$.1') # 3
+ >>> lit('[1,2,3,4,5]').json_length('$[3]') # 1
+
+ >>> lit('[1,2,3,4,5]').json_length('$.[7]') # None
+ >>> lit('{"1": "bad", "2": "syntax here ->"').json_length('$.1') #
None
+ """
+ return _unary_op("jsonLength")(self) if path is None else
_binary_op("jsonLength")(self, path)
Review Comment:
between different functions there should be exactly 1 newline
--
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]
