inline
Explodes an array of structs into a table.
This function takes an input column containing an array of structs and returns a new column where each struct in the array is exploded into a separate row.
Syntax
Python
from pyspark.sql import functions as sf
sf.inline(col)
Parameters
Parameter | Type | Description |
|---|---|---|
|
| Input column of values to explode. |
Returns
pyspark.sql.Column: Generator expression with the inline exploded result.
Examples
Example 1: Using inline with a single struct array column
Python
import pyspark.sql.functions as sf
df = spark.sql('SELECT ARRAY(NAMED_STRUCT("a",1,"b",2), NAMED_STRUCT("a",3,"b",4)) AS a')
df.select('*', sf.inline(df.a)).show()
Output
+----------------+---+---+
| a| a| b|
+----------------+---+---+
|[{1, 2}, {3, 4}]| 1| 2|
|[{1, 2}, {3, 4}]| 3| 4|
+----------------+---+---+
Example 2: Using inline with a column name
Python
import pyspark.sql.functions as sf
df = spark.sql('SELECT ARRAY(NAMED_STRUCT("a",1,"b",2), NAMED_STRUCT("a",3,"b",4)) AS a')
df.select('*', sf.inline('a')).show()
Output
+----------------+---+---+
| a| a| b|
+----------------+---+---+
|[{1, 2}, {3, 4}]| 1| 2|
|[{1, 2}, {3, 4}]| 3| 4|
+----------------+---+---+
Example 3: Using inline with an alias
Python
import pyspark.sql.functions as sf
df = spark.sql('SELECT ARRAY(NAMED_STRUCT("a",1,"b",2), NAMED_STRUCT("a",3,"b",4)) AS a')
df.select('*', sf.inline('a').alias("c1", "c2")).show()
Output
+----------------+---+---+
| a| c1| c2|
+----------------+---+---+
|[{1, 2}, {3, 4}]| 1| 2|
|[{1, 2}, {3, 4}]| 3| 4|
+----------------+---+---+
Example 4: Using inline with multiple struct array columns
Python
import pyspark.sql.functions as sf
df = spark.sql('SELECT ARRAY(NAMED_STRUCT("a",1,"b",2), NAMED_STRUCT("a",3,"b",4)) AS a1, ARRAY(NAMED_STRUCT("c",5,"d",6), NAMED_STRUCT("c",7,"d",8)) AS a2')
df.select(
'*', sf.inline('a1')
).select('*', sf.inline('a2')).show()
Output
+----------------+----------------+---+---+---+---+
| a1| a2| a| b| c| d|
+----------------+----------------+---+---+---+---+
|[{1, 2}, {3, 4}]|[{5, 6}, {7, 8}]| 1| 2| 5| 6|
|[{1, 2}, {3, 4}]|[{5, 6}, {7, 8}]| 1| 2| 7| 8|
|[{1, 2}, {3, 4}]|[{5, 6}, {7, 8}]| 3| 4| 5| 6|
|[{1, 2}, {3, 4}]|[{5, 6}, {7, 8}]| 3| 4| 7| 8|
+----------------+----------------+---+---+---+---+
Example 5: Using inline with a nested struct array column
Python
import pyspark.sql.functions as sf
df = spark.sql('SELECT NAMED_STRUCT("a",1,"b",2,"c",ARRAY(NAMED_STRUCT("c",3,"d",4), NAMED_STRUCT("c",5,"d",6))) AS s')
df.select('*', sf.inline('s.c')).show(truncate=False)
Output
+------------------------+---+---+
|s |c |d |
+------------------------+---+---+
|{1, 2, [{3, 4}, {5, 6}]}|3 |4 |
|{1, 2, [{3, 4}, {5, 6}]}|5 |6 |
+------------------------+---+---+
Example 6: Using inline with a column containing: array containing null, empty array and null
Python
from pyspark.sql import functions as sf
df = spark.sql('SELECT * FROM VALUES (1,ARRAY(NAMED_STRUCT("a",1,"b",2), NULL, NAMED_STRUCT("a",3,"b",4))), (2,ARRAY()), (3,NULL) AS t(i,s)')
df.show(truncate=False)
Output
+---+----------------------+
|i |s |
+---+----------------------+
|1 |[{1, 2}, NULL, {3, 4}]|
|2 |[] |
|3 |NULL |
+---+----------------------+
Python
df.select('*', sf.inline('s')).show(truncate=False)
Output
+---+----------------------+----+----+
|i |s |a |b |
+---+----------------------+----+----+
|1 |[{1, 2}, NULL, {3, 4}]|1 |2 |
|1 |[{1, 2}, NULL, {3, 4}]|NULL|NULL|
|1 |[{1, 2}, NULL, {3, 4}]|3 |4 |
+---+----------------------+----+----+