bin/pyspark --packages org.apache.spark:spark-avro_2.11:2.4.0
from pyspark.sql.column import Column, _to_java_column
def from_avro(col, jsonFormatSchema):
sc = SparkContext._active_spark_context
avro = sc._jvm.org.apache.spark.sql.avro
f = getattr(getattr(avro, "package$"), "MODULE$").from_avro
return Column(f(_to_java_column(col), jsonFormatSchema))
def to_avro(col):
sc = SparkContext._active_spark_context
avro = sc._jvm.org.apache.spark.sql.avro
f = getattr(getattr(avro, "package$"), "MODULE$").to_avro
return Column(f(_to_java_column(col)))
from pyspark.sql.functions import col, struct
avro_type_struct = """
{
"type": "record",
"name": "struct",
"fields": [
{"name": "col1", "type": "long"},
{"name": "col2", "type": "string"}
]
}"""
df = spark.range(10).select(struct(
col("id"),
col("id").cast("string").alias("id2")
).alias("struct"))
avro_struct_df = df.select(to_avro(col("struct")).alias("avro"))
avro_struct_df.show(3)
+----------+
| avro|
+----------+
|[00 02 30]|
|[02 02 31]|
|[04 02 32]|
+----------+
only showing top 3 rows
avro_struct_df.select(from_avro("avro", avro_type_struct)).show(3)
+------------------------------------------------+
|from_avro(avro, struct<col1:bigint,col2:string>)|
+------------------------------------------------+
| [0, 0]|
| [1, 1]|
| [2, 2]|
+------------------------------------------------+
only showing top 3 rows
602392714
清零编程群