spark structure streaming初探

原创

滕百川

修改于 2023-07-28 19:02:21

19500

代码可运行

文章被收录于专栏：spark流式计算技术

运行总次数：0

代码可运行

1.技术背景

//TODO

2.数据模型

2.1 输入流

2.2 编程模型

3. 代码示例

3.1 从kafka流式查询数据示例

// Subscribe to 1 topic
val df = spark
  .readStream
  .format("kafka")
  .option("kafka.bootstrap.servers", "host1:port1,host2:port2")
  .option("subscribe", "topic1")
  .load()
df.selectExpr("CAST(key AS STRING)", "CAST(value AS STRING)")
  .as[(String, String)]

// Subscribe to 1 topic, with headers
val df = spark
  .readStream
  .format("kafka")
  .option("kafka.bootstrap.servers", "host1:port1,host2:port2")
  .option("subscribe", "topic1")
  .option("includeHeaders", "true")
  .load()
df.selectExpr("CAST(key AS STRING)", "CAST(value AS STRING)", "headers")
  .as[(String, String, Map)]

// Subscribe to multiple topics
val df = spark
  .readStream
  .format("kafka")
  .option("kafka.bootstrap.servers", "host1:port1,host2:port2")
  .option("subscribe", "topic1,topic2")
  .load()
df.selectExpr("CAST(key AS STRING)", "CAST(value AS STRING)")
  .as[(String, String)]

// Subscribe to a pattern
val df = spark
  .readStream
  .format("kafka")
  .option("kafka.bootstrap.servers", "host1:port1,host2:port2")
  .option("subscribePattern", "topic.*")
  .load()
df.selectExpr("CAST(key AS STRING)", "CAST(value AS STRING)")
  .as[(String, String)]

3.2 从kafka批量查询数据示例

// Subscribe to 1 topic defaults to the earliest and latest offsets
val df = spark
  .read
  .format("kafka")
  .option("kafka.bootstrap.servers", "host1:port1,host2:port2")
  .option("subscribe", "topic1")
  .load()
df.selectExpr("CAST(key AS STRING)", "CAST(value AS STRING)")
  .as[(String, String)]

// Subscribe to multiple topics, specifying explicit Kafka offsets
val df = spark
  .read
  .format("kafka")
  .option("kafka.bootstrap.servers", "host1:port1,host2:port2")
  .option("subscribe", "topic1,topic2")
  .option("startingOffsets", """{"topic1":{"0":23,"1":-2},"topic2":{"0":-2}}""")
  .option("endingOffsets", """{"topic1":{"0":50,"1":-1},"topic2":{"0":-1}}""")
  .load()
df.selectExpr("CAST(key AS STRING)", "CAST(value AS STRING)")
  .as[(String, String)]

// Subscribe to a pattern, at the earliest and latest offsets
val df = spark
  .read
  .format("kafka")
  .option("kafka.bootstrap.servers", "host1:port1,host2:port2")
  .option("subscribePattern", "topic.*")
  .option("startingOffsets", "earliest")
  .option("endingOffsets", "latest")
  .load()
df.selectExpr("CAST(key AS STRING)", "CAST(value AS STRING)")
  .as[(String, String)]

3.3 为streaming queries创建kafka sink

// Write key-value data from a DataFrame to a specific Kafka topic specified in an option
val ds = df
  .selectExpr("CAST(key AS STRING)", "CAST(value AS STRING)")
  .writeStream
  .format("kafka")
  .option("kafka.bootstrap.servers", "host1:port1,host2:port2")
  .option("topic", "topic1")
  .start()

// Write key-value data from a DataFrame to Kafka using a topic specified in the data
val ds = df
  .selectExpr("topic", "CAST(key AS STRING)", "CAST(value AS STRING)")
  .writeStream
  .format("kafka")
  .option("kafka.bootstrap.servers", "host1:port1,host2:port2")
  .start()

3.4 批量查询输出到kafka

// Write key-value data from a DataFrame to a specific Kafka topic specified in an option
df.selectExpr("CAST(key AS STRING)", "CAST(value AS STRING)")
  .write
  .format("kafka")
  .option("kafka.bootstrap.servers", "host1:port1,host2:port2")
  .option("topic", "topic1")
  .save()

// Write key-value data from a DataFrame to Kafka using a topic specified in the data
df.selectExpr("topic", "CAST(key AS STRING)", "CAST(value AS STRING)")
  .write
  .format("kafka")
  .option("kafka.bootstrap.servers", "host1:port1,host2:port2")
  .save()