XML Files

# Primitive types (Int, String, etc) and Product types (case classes) encoders are
# supported by importing this when creating a Dataset.
# An XML dataset is pointed to by path.
# The path can be either a single xml file or more xml files
path = "examples/src/main/resources/people.xml"
peopleDF = spark.read.option("rowTag", "person").format("xml").load(path)

# The inferred schema can be visualized using the printSchema() method
peopleDF.printSchema()
# root
#  |-- age: long (nullable = true)
#  |-- name: string (nullable = true)

# Creates a temporary view using the DataFrame
peopleDF.createOrReplaceTempView("people")

# SQL statements can be run by using the sql methods provided by spark
teenagerNamesDF = spark.sql("SELECT name FROM people WHERE age BETWEEN 13 AND 19")
teenagerNamesDF.show()
# +------+
# |  name|
# +------+
# |Justin|
# +------+

# Alternatively, a DataFrame can be created for an XML dataset represented by a Dataset[String]
xmlStrings = ["""
      <person>
          <name>laglangyue</name>
          <job>Developer</job>
          <age>28</age>
      </person>
    """]
xmlRDD = spark.sparkContext.parallelize(xmlStrings)
otherPeople = spark.read \
    .option("rowTag", "person") \
    .xml(xmlRDD)
otherPeople.show()
# +---+---------+----------+
# |age|      job|      name|
# +---+---------+----------+
# | 28|Developer|laglangyue|
# +---+---------+----------+

// Primitive types (Int, String, etc) and Product types (case classes) encoders are
// supported by importing this when creating a Dataset.
import spark.implicits._
// An XML dataset is pointed to by path.
// The path can be either a single xml file or more xml files
val path = "examples/src/main/resources/people.xml"
val peopleDF = spark.read.option("rowTag", "person").xml(path)

// The inferred schema can be visualized using the printSchema() method
peopleDF.printSchema()
// root
//  |-- age: long (nullable = true)
//  |-- name: string (nullable = true)

// Creates a temporary view using the DataFrame
peopleDF.createOrReplaceTempView("people")

// SQL statements can be run by using the sql methods provided by spark
val teenagerNamesDF = spark.sql("SELECT name FROM people WHERE age BETWEEN 13 AND 19")
teenagerNamesDF.show()
// +------+
// |  name|
// +------+
// |Justin|
// +------+

// Alternatively, a DataFrame can be created for a XML dataset represented by a Dataset[String]
val otherPeopleDataset = spark.createDataset(
  """
    |<person>
    |    <name>laglangyue</name>
    |    <job>Developer</job>
    |    <age>28</age>
    |</person>
    |""".stripMargin :: Nil)
val otherPeople = spark.read
  .option("rowTag", "person")
  .xml(otherPeopleDataset)
otherPeople.show()
// +---+---------+----------+
// |age|      job|      name|
// +---+---------+----------+
// | 28|Developer|laglangyue|
// +---+---------+----------+

// Primitive types (Int, String, etc) and Product types (case classes) encoders are
// supported by importing this when creating a Dataset.

// An XML dataset is pointed to by path.
// The path can be either a single xml file or more xml files
String path = "examples/src/main/resources/people.xml";
Dataset<Row> peopleDF = spark.read().option("rowTag", "person").xml(path);

// The inferred schema can be visualized using the printSchema() method
peopleDF.printSchema();
// root
//  |-- age: long (nullable = true)
//  |-- name: string (nullable = true)

// Creates a temporary view using the DataFrame
peopleDF.createOrReplaceTempView("people");

// SQL statements can be run by using the sql methods provided by spark
Dataset<Row> teenagerNamesDF = spark.sql(
        "SELECT name FROM people WHERE age BETWEEN 13 AND 19");
teenagerNamesDF.show();
// +------+
// |  name|
// +------+
// |Justin|
// +------+

// Alternatively, a DataFrame can be created for an XML dataset represented by a Dataset[String]
List<String> xmlData = Collections.singletonList(
        "<person>" +
        "<name>laglangyue</name><job>Developer</job><age>28</age>" +
        "</person>");
Dataset<String> otherPeopleDataset = spark.createDataset(Lists.newArrayList(xmlData),
        Encoders.STRING());

Dataset<Row> otherPeople = spark.read()
    .option("rowTag", "person")
    .xml(otherPeopleDataset);
otherPeople.show();
// +---+---------+----------+
// |age|      job|      name|
// +---+---------+----------+
// | 28|Developer|laglangyue|
// +---+---------+----------+