@@ -9,10 +9,11 @@ CREATE TABLE tableName(
99 WATERMARK FOR colName AS withOffset( colName , delayTime )
1010 )WITH(
1111 type ='kafka09',
12- kafka.bootstrap.servers ='ip:port,ip:port...',
13- kafka.zookeeper.quorum ='ip:port,ip:port/zkparent',
14- kafka.auto.offset.reset ='latest',
15- kafka.topic ='topicName',
12+ bootstrapServers ='ip:port,ip:port...',
13+ zookeeperQuorum ='ip:port,ip:port/zkparent',
14+ offsetReset ='latest',
15+ topic ='topicName',
16+ groupId='test',
1617 parallelism ='parllNum',
1718 --timezone='America/Los_Angeles',
1819 timezone='Asia/Shanghai',
@@ -39,16 +40,45 @@ CREATE TABLE tableName(
3940| 参数名称| 含义| 是否必填| 默认值|
4041| ----| ---| ---| ---|
4142| type | kafka09 | 是| kafka08、kafka09、kafka10、kafka11、kafka(对应kafka1.0及以上版本)|
42- | kafka.group.id | 需要读取的 groupId 名称| 否||
43- | kafka.bootstrap.servers | kafka bootstrap-server 地址信息(多个用逗号隔开)| 是||
44- | kafka.zookeeper.quorum | kafka zk地址信息(多个之间用逗号分隔)| 是||
45- | kafka. topic | 需要读取的 topic 名称| 是||
46- |patterntopic | topic是否是正则表达式格式(true| ; false) |否| false
47- | kafka.auto.offset.reset | 读取的topic 的offset初始位置[ latest| ; earliest| ; 指定offset值({"0":12312,"1":12321,"2":12312},{"partition_no": offset_value })] | 否| latest|
43+ | groupId | 需要读取的 groupId 名称| 否||
44+ | bootstrapServers | kafka bootstrap-server 地址信息(多个用逗号隔开)| 是||
45+ | zookeeperQuorum | kafka zk地址信息(多个之间用逗号分隔)| 是||
46+ | topic | 需要读取的 topic 名称| 是||
47+ |topicIsPattern | topic是否是正则表达式格式(true| ; false) |否| false
48+ | offsetReset | 读取的topic 的offset初始位置[ latest| ; earliest| ; 指定offset值({"0":12312,"1":12321,"2":12312},{"partition_no": offset_value })] | 否| latest|
4849| parallelism | 并行度设置| 否| 1|
4950| sourcedatatype | 数据类型| 否| json|
5051|timezone|时区设置[ timezone支持的参数] ( timeZone.md ) |否|'Asia/Shanghai'
5152** kafka相关参数可以自定义,使用kafka.开头即可。**
53+ ```
54+ kafka.consumer.id
55+ kafka.socket.timeout.ms
56+ kafka.fetch.message.max.bytes
57+ kafka.num.consumer.fetchers
58+ kafka.auto.commit.enable
59+ kafka.auto.commit.interval.ms
60+ kafka.queued.max.message.chunks
61+ kafka.rebalance.max.retries
62+ kafka.fetch.min.bytes
63+ kafka.fetch.wait.max.ms
64+ kafka.rebalance.backoff.ms
65+ kafka.refresh.leader.backoff.ms
66+ kafka.consumer.timeout.ms
67+ kafka.exclude.internal.topics
68+ kafka.partition.assignment.strategy
69+ kafka.client.id
70+ kafka.zookeeper.session.timeout.ms
71+ kafka.zookeeper.connection.timeout.ms
72+ kafka.zookeeper.sync.time.ms
73+ kafka.offsets.storage
74+ kafka.offsets.channel.backoff.ms
75+ kafka.offsets.channel.socket.timeout.ms
76+ kafka.offsets.commit.max.retries
77+ kafka.dual.commit.enabled
78+ kafka.partition.assignment.strategy
79+ kafka.socket.receive.buffer.bytes
80+ kafka.fetch.min.bytes
81+ ```
5282
5383## 5.样例:
5484```
@@ -60,12 +90,12 @@ CREATE TABLE MyTable(
6090 CHARACTER_LENGTH(channel) AS timeLeng
6191 )WITH(
6292 type ='kafka09',
63- kafka.bootstrap.servers ='172.16.8.198:9092',
64- kafka.zookeeper.quorum ='172.16.8.198:2181/kafka',
65- kafka.auto.offset.reset ='latest',
66- kafka. topic ='nbTest1,nbTest2,nbTest3',
67- --kafka. topic ='mqTest.*',
68- --patterntopic ='true'
93+ bootstrapServers ='172.16.8.198:9092',
94+ zookeeperQuorum ='172.16.8.198:2181/kafka',
95+ offsetReset ='latest',
96+ topic ='nbTest1,nbTest2,nbTest3',
97+ --topic ='mqTest.*',
98+ --topicIsPattern ='true'
6999 parallelism ='1',
70100 sourcedatatype ='json' #可不设置
71101 );
@@ -146,10 +176,10 @@ CREATE TABLE MyTable(
146176| 参数名称| 含义| 是否必填| 默认值|
147177| ----| ---| ---| ---|
148178| type | kafka09 | 是||
149- | kafka.bootstrap.servers | kafka bootstrap-server 地址信息(多个用逗号隔开)| 是||
150- | kafka.zookeeper.quorum | kafka zk地址信息(多个之间用逗号分隔)| 是||
151- | kafka. topic | 需要读取的 topic 名称| 是||
152- | kafka.auto.offset.reset | 读取的topic 的offset初始位置[ latest| ; earliest] | 否| latest|
179+ | bootstrapServers | kafka bootstrap-server 地址信息(多个用逗号隔开)| 是||
180+ | zookeeperQuorum | kafka zk地址信息(多个之间用逗号分隔)| 是||
181+ | topic | 需要读取的 topic 名称| 是||
182+ | offsetReset | 读取的topic 的offset初始位置[ latest| ; earliest] | 否| latest|
153183| parallelism | 并行度设置 | 否| 1|
154184| sourcedatatype | 数据类型| 是 | csv|
155185| fielddelimiter | 字段分隔符| 是 ||
@@ -166,12 +196,12 @@ CREATE TABLE MyTable(
166196 CHARACTER_LENGTH(channel) AS timeLeng
167197 )WITH(
168198 type ='kafka09',
169- kafka.bootstrap.servers ='172.16.8.198:9092',
170- kafka.zookeeper.quorum ='172.16.8.198:2181/kafka',
171- kafka.auto.offset.reset ='latest',
172- kafka. topic ='nbTest1',
173- --kafka. topic ='mqTest.*',
174- --kafka. topicIsPattern='true'
199+ bootstrapServers ='172.16.8.198:9092',
200+ zookeeperQuorum ='172.16.8.198:2181/kafka',
201+ offsetReset ='latest',
202+ topic ='nbTest1',
203+ --topic ='mqTest.*',
204+ --topicIsPattern='true'
175205 parallelism ='1',
176206 sourcedatatype ='csv',
177207 fielddelimiter ='\|',
@@ -192,10 +222,10 @@ create table kafka_stream(
192222 _offset BIGINT,
193223) with (
194224 type ='kafka09',
195- kafka.bootstrap.servers ='172.16.8.198:9092',
196- kafka.zookeeper.quorum ='172.16.8.198:2181/kafka',
197- kafka.auto.offset.reset ='latest',
198- kafka. topic ='nbTest1',
225+ bootstrapServers ='172.16.8.198:9092',
226+ zookeeperQuorum ='172.16.8.198:2181/kafka',
227+ offsetReset ='latest',
228+ topic ='nbTest1',
199229 parallelism ='1',
200230 sourcedatatype='text'
201231 )
@@ -205,10 +235,10 @@ create table kafka_stream(
205235| 参数名称| 含义| 是否必填| 默认值|
206236| ----| ---| ---| ---|
207237| type | kafka09 | 是||
208- | kafka.bootstrap.servers | kafka bootstrap-server 地址信息(多个用逗号隔开)| 是||
209- | kafka.zookeeper.quorum | kafka zk地址信息(多个之间用逗号分隔)| 是||
210- | kafka. topic | 需要读取的 topic 名称| 是||
211- | kafka.auto.offset.reset | 读取的topic 的offset初始位置[ latest| ; earliest] | 否| latest|
238+ | bootstrapServers | kafka bootstrap-server 地址信息(多个用逗号隔开)| 是||
239+ | zookeeperQuorum | kafka zk地址信息(多个之间用逗号分隔)| 是||
240+ | topic | 需要读取的 topic 名称| 是||
241+ | offsetReset | 读取的topic 的offset初始位置[ latest| ; earliest] | 否| latest|
212242| parallelism | 并行度设置| 否| 1|
213243| sourcedatatype | 数据类型| 否| text|
214244** kafka相关参数可以自定义,使用kafka.开头即可。**
0 commit comments