Github user HyukjinKwon commented on a diff in the pull request:
https://github.com/apache/spark/pull/22775#discussion_r228504453
--- Diff: python/pyspark/sql/functions.py ---
@@ -2365,30 +2365,32 @@ def to_json(col, options={}):
@ignore_unicode_prefix
@since(2.4)
-def schema_of_json(col, options={}):
+def schema_of_json(json, options={}):
"""
- Parses a column containing a JSON string and infers its schema in DDL
format.
+ Parses a JSON string and infers its schema in DDL format.
- :param col: string column in json format
+ :param json: a JSON string or a string literal containing a JSON
string.
:param options: options to control parsing. accepts the same options
as the JSON datasource
.. versionchanged:: 3.0
It accepts `options` parameter to control schema inferring.
- >>> from pyspark.sql.types import *
- >>> data = [(1, '{"a": 1}')]
- >>> df = spark.createDataFrame(data, ("key", "value"))
- >>> df.select(schema_of_json(df.value).alias("json")).collect()
- [Row(json=u'struct<a:bigint>')]
+ >>> df = spark.range(1)
>>> df.select(schema_of_json(lit('{"a": 0}')).alias("json")).collect()
[Row(json=u'struct<a:bigint>')]
- >>> schema = schema_of_json(lit('{a: 1}'),
{'allowUnquotedFieldNames':'true'})
+ >>> schema = schema_of_json('{a: 1}',
{'allowUnquotedFieldNames':'true'})
>>> df.select(schema.alias("json")).collect()
[Row(json=u'struct<a:bigint>')]
"""
+ if isinstance(json, basestring):
--- End diff --
+1
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
