Github user HyukjinKwon commented on a diff in the pull request:
https://github.com/apache/spark/pull/21686#discussion_r199856590
--- Diff: python/pyspark/sql/functions.py ---
@@ -2235,6 +2240,28 @@ def to_json(col, options={}):
return Column(jc)
+@ignore_unicode_prefix
+@since(2.4)
+def schema_of_json(col):
+ """
+ Parses a column containing a JSON string and infers its schema in DDL
format.
+
+ :param col: string column in json format
+
+ >>> 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.select(schema_of_json(lit('''{"a":
0}''')).alias("json")).collect()
--- End diff --
minor nit `'''{"a": 0}'''` -> `'{"a": 0}'`
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
