diff options
Diffstat (limited to 'python/pyspark/sql.py')
| -rw-r--r-- | python/pyspark/sql.py | 15 |
1 files changed, 11 insertions, 4 deletions
diff --git a/python/pyspark/sql.py b/python/pyspark/sql.py index f0bd3cbd98..93bfc25bca 100644 --- a/python/pyspark/sql.py +++ b/python/pyspark/sql.py @@ -313,12 +313,15 @@ class StructField(DataType): """ - def __init__(self, name, dataType, nullable): + def __init__(self, name, dataType, nullable, metadata=None): """Creates a StructField :param name: the name of this field. :param dataType: the data type of this field. :param nullable: indicates whether values of this field can be null. + :param metadata: metadata of this field, which is a map from string + to simple type that can be serialized to JSON + automatically >>> (StructField("f1", StringType, True) ... == StructField("f1", StringType, True)) @@ -330,6 +333,7 @@ class StructField(DataType): self.name = name self.dataType = dataType self.nullable = nullable + self.metadata = metadata or {} def __repr__(self): return "StructField(%s,%s,%s)" % (self.name, self.dataType, @@ -338,13 +342,15 @@ class StructField(DataType): def jsonValue(self): return {"name": self.name, "type": self.dataType.jsonValue(), - "nullable": self.nullable} + "nullable": self.nullable, + "metadata": self.metadata} @classmethod def fromJson(cls, json): return StructField(json["name"], _parse_datatype_json_value(json["type"]), - json["nullable"]) + json["nullable"], + json["metadata"]) class StructType(DataType): @@ -423,7 +429,8 @@ def _parse_datatype_json_string(json_string): ... StructField("simpleArray", simple_arraytype, True), ... StructField("simpleMap", simple_maptype, True), ... StructField("simpleStruct", simple_structtype, True), - ... StructField("boolean", BooleanType(), False)]) + ... StructField("boolean", BooleanType(), False), + ... StructField("withMeta", DoubleType(), False, {"name": "age"})]) >>> check_datatype(complex_structtype) True >>> # Complex ArrayType. |