本文将详细介绍Flink-CDC如何全量及增量采集Sqlserver数据源，准备适配Sqlserver数据源的小伙伴们可以参考本文，希望本文能给你带来一定的帮助。
一、Sqlserver的安装及开启事务日志
如果没有Sqlserver环境，但你又想学习这块的内容，那你只能自己动手通过docker安装一个 myself sqlserver来用作学习，当然，如果你有现成环境，那就检查一下Sqlserver是否开启了代理(sqlagent.enabled)服务和CDC功能。
1.1 docker拉取镜像
看Github上写Flink-CDC目前支持的Sqlserver版本为2012, 2014, 2016, 2017, 2019，但我想全部拉到最新（事实证明，2022-latest 和latest是一样的，因为imagId都是一致的，且在后续测试也是没有问题的），所以我在docker上拉取镜像时，直接采用如下命令：
docker pull mcr.microsoft.com/mssql/server:latest1.2 运行Sqlserver并设置代理
标准启动模式，没什么好说的，主要设置一下密码(密码要求比较严格，建议直接在网上搜个随机密码生成器来搞一下)。
代码语言：bash复制docker run -e 'ACCEPT_EULA=Y' -e 'SA_PASSWORD=${your_password}'
-p 1433:1433 --name sqlserver
-d mcr.microsoft.com/mssql/server:latest设置代理sqlagent.enabled,代理设置完成后，需要重启Sqlserver，因为我们是docker安装的，直接用docker restart sqlserver就行了。
[root@hdp-01 ~]# docker exec -it --user root sqlserver bash
root@0274812d0c10:/# /opt/mssql/bin/mssql-conf set sqlagent.enabled true
SQL Server needs to be restarted in order to apply this setting. Please run
'systemctl restart mssql-server.service'.
root@0274812d0c10:/# exit
exit
[root@hdp-01 ~]# docker restart sqlserver
sqlserver1.3 启用CDC功能
按照如下步骤执行命令，如果看到is_cdc_enabled = 1，则说明当前数据库
root@0274812d0c10:/# /opt/mssql-tools/bin/sqlcmd -S localhost -U SA -P "${your_password}"
1> create databases test;
2> go
1> use test;
2> go
Changed database context to 'test'.
1> EXEC sys.sp_cdc_enable_db;
2> go
1> SELECT is_cdc_enabled FROM sys.databases WHERE name = 'test';
2> go
is_cdc_enabled
--------------
1
(1 rows affected)
1> CREATE TABLE t_info (id int,order_date date,purchaser int,quantity int,product_id int,PRIMARY KEY ([id]))
2> go
1>
2>
3> EXEC sys.sp_cdc_enable_table
4> @source_schema = 'dbo',
5> @source_name = 't_info',
6> @role_name = 'cdc_role';
7> go
Update mask evaluation will be disabled in net_changes_function because the CLR configuration option is disabled.
Job 'cdc.zeus_capture' started successfully.
Job 'cdc.zeus_cleanup' started successfully.
1> select * from t_info;
2> go
id order_date purchaser quantity product_id
----------- ---------------- ----------- ----------- -----------
(0 rows affected)1.4 检查CDC是否正常开启
用客户端连接Sqlserver，查看test库下的INFORMATION_SCHEMA.TABLES中是否出现TABLE_SCHEMA = cdc的表，如果出现，说明已经成功安装Sqlserver并启用了CDC。
1> use test;
2> go
Changed database context to 'test'.
1> select * from INFORMATION_SCHEMA.TABLES;
2> goTABLE_CATALOG TABLE_SCHEMA TABLE_NAME TABLE_TYPE
test dbo user_info BASE TABLE
test dbo systranschemas BASE TABLE
test cdc change_tables BASE TABLE
test cdc ddl_history BASE TABLE
test cdc lsn_time_mapping BASE TABLE
test cdc captured_columns BASE TABLE
test cdc index_columns BASE TABLE
test dbo orders BASE TABLE
test cdc dbo_orders_CT BASE TABLE二、具体实现
2.1 Flik-CDC采集SqlServer主程序
添加依赖包：
代码语言：xml复制 <dependency>
<groupId>com.ververica</groupId>
<artifactId>flink-connector-sqlserver-cdc</artifactId>
<version>3.0.0</version>
</dependency>编写主函数：
代码语言：java复制 public static void main(String[] args) throws Exception {
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
// 设置全局并行度
env.setParallelism(1);
// 设置时间语义为ProcessingTime
env.getConfig().setAutoWatermarkInterval(0);
// 每隔60s启动一个检查点
env.enableCheckpointing(60000, CheckpointingMode.EXACTLY_ONCE);
// checkpoint最小间隔
env.getCheckpointConfig().setMinPauseBetweenCheckpoints(1000);
// checkpoint超时时间
env.getCheckpointConfig().setCheckpointTimeout(60000);
// 同一时间只允许一个checkpoint
// env.getCheckpointConfig().setMaxConcurrentCheckpoints(1);
// Flink处理程序被cancel后，会保留Checkpoint数据
// env.getCheckpointConfig().setExternalizedCheckpointCleanup(CheckpointConfig.ExternalizedCheckpointCleanup.RETAIN_ON_CANCELLATION);
SourceFunction<String> sqlServerSource = SqlServerSource.<String>builder()
.hostname("localhost")
.port(1455)
.username("SA")
.password("")
.database("test")
.tableList("dbo.t_info")
.startupOptions(StartupOptions.initial())
.debeziumProperties(getDebeziumProperties())
.deserializer(new CustomerDeserializationSchemaSqlserver())
.build();
DataStreamSource<String> dataStreamSource = env.addSource(sqlServerSource, "_transaction_log_source");
dataStreamSource.print().setParallelism(1);
env.execute("sqlserver-cdc-test");
}
public static Properties getDebeziumProperties() {
Properties properties = new Properties();
properties.put("converters", "sqlserverDebeziumConverter");
properties.put("sqlserverDebeziumConverter.type", "SqlserverDebeziumConverter");
properties.put("sqlserverDebeziumConverter.database.type", "sqlserver");
// 自定义格式，可选
properties.put("sqlserverDebeziumConverter.format.datetime", "yyyy-MM-dd HH:mm:ss");
properties.put("sqlserverDebeziumConverter.format.date", "yyyy-MM-dd");
properties.put("sqlserverDebeziumConverter.format.time", "HH:mm:ss");
return properties;
}2.2 自定义Sqlserver反序列化格式：
Flink-CDC底层技术为debezium，它捕获到Sqlserver数据变更(CRUD)的数据格式如下：
#初始化
Struct{after=Struct{id=1,order_date=2024-01-30,purchaser=1,quantity=100,product_id=1},source=Struct{version=1.9.7.Final,connector=sqlserver,name=sqlserver_transaction_log_source,ts_ms=1706574924473,snapshot=true,db=zeus,schema=dbo,table=orders,commit_lsn=0000002b:00002280:0003},op=r,ts_ms=1706603724432}
#新增
Struct{after=Struct{id=12,order_date=2024-01-11,purchaser=6,quantity=233,product_id=63},source=Struct{version=1.9.7.Final,connector=sqlserver,name=sqlserver_transaction_log_source,ts_ms=1706603786187,db=zeus,schema=dbo,table=orders,change_lsn=0000002b:00002480:0002,commit_lsn=0000002b:00002480:0003,event_serial_no=1},op=c,ts_ms=1706603788461}
#更新
Struct{before=Struct{id=12,order_date=2024-01-11,purchaser=6,quantity=233,product_id=63},after=Struct{id=12,order_date=2024-01-11,purchaser=8,quantity=233,product_id=63},source=Struct{version=1.9.7.Final,connector=sqlserver,name=sqlserver_transaction_log_source,ts_ms=1706603845603,db=zeus,schema=dbo,table=orders,change_lsn=0000002b:00002500:0002,commit_lsn=0000002b:00002500:0003,event_serial_no=2},op=u,ts_ms=1706603850134}
#删除
Struct{before=Struct{id=11,order_date=2024-01-11,purchaser=6,quantity=233,product_id=63},source=Struct{version=1.9.7.Final,connector=sqlserver,name=sqlserver_transaction_log_source,ts_ms=1706603973023,db=zeus,schema=dbo,table=orders,change_lsn=0000002b:000025e8:0002,commit_lsn=0000002b:000025e8:0005,event_serial_no=1},op=d,ts_ms=1706603973859}因此，可以根据自己需要自定义反序列化格式，将数据按照标准统一数据输出，下面是我自定义的格式，供大家参考：
代码语言：java复制import com.alibaba.fastjson2.JSON;
import com.alibaba.fastjson2.JSONObject;
import com.alibaba.fastjson2.JSONWriter;
import com.ververica.cdc.debezium.DebeziumDeserializationSchema;
import io.debezium.data.Envelope;
import org.apache.flink.api.common.typeinfo.BasicTypeInfo;
import org.apache.flink.api.common.typeinfo.TypeInformation;
import org.apache.flink.util.Collector;
import org.apache.kafka.connect.data.Field;
import org.apache.kafka.connect.data.Schema;
import org.apache.kafka.connect.data.Struct;
import org.apache.kafka.connect.source.SourceRecord;
import java.util.HashMap;
import java.util.Map;
public class CustomerDeserializationSchemaSqlserver implements DebeziumDeserializationSchema<String> {
private static final long serialVersionUID = -1L;
@Override
public void deserialize(SourceRecord sourceRecord, Collector collector) {
Map<String, Object> resultMap = new HashMap<>();
String topic = sourceRecord.topic();
String[] split = topic.split("[.]");
String database = split[1];
String table = split[2];
resultMap.put("db", database);
resultMap.put("tableName", table);
//获取操作类型
Envelope.Operation operation = Envelope.operationFor(sourceRecord);
//获取数据本身
Struct struct = (Struct) sourceRecord.value();
Struct after = struct.getStruct("after");
Struct before = struct.getStruct("before");
String op = operation.name();
resultMap.put("op", op);
//新增,更新或者初始化
if (op.equals(Envelope.Operation.CREATE.name()) || op.equals(Envelope.Operation.READ.name()) || op.equals(Envelope.Operation.UPDATE.name())) {
JSONObject afterJson = new JSONObject();
if (after != null) {
Schema schema = after.schema();
for (Field field : schema.fields()) {
afterJson.put(field.name(), after.get(field.name()));
}
resultMap.put("after", afterJson);
}
}
if (op.equals(Envelope.Operation.DELETE.name())) {
JSONObject beforeJson = new JSONObject();
if (before != null) {
Schema schema = before.schema();
for (Field field : schema.fields()) {
beforeJson.put(field.name(), before.get(field.name()));
}
resultMap.put("before", beforeJson);
}
}
collector.collect(JSON.toJSONString(resultMap, JSONWriter.Feature.FieldBased, JSONWriter.Feature.LargeObject));
}
@Override
public TypeInformation<String> getProducedType() {
return BasicTypeInfo.STRING_TYPE_INFO;
}
}2.3 自定义日期格式转换器
debezium会将日期转为5位数字，日期时间位13位的数字，因此我们需要根据Sqlserver的日期类型转换成标准的时期或者时间格式。Sqlserver的日期类型主要包含以下几种：
字段类型 | 快照类型(jdbc type) | cdc类型(jdbc type) |
|---|---|---|
DATE | java.sql.Date(91) | java.sql.Date(91) |
TIME | java.sql.Timestamp(92) | java.sql.Time(92) |
DATETIME | java.sql.Timestamp(93) | java.sql.Timestamp(93) |
DATETIME2 | java.sql.Timestamp(93) | java.sql.Timestamp(93) |
DATETIMEOFFSET | microsoft.sql.DateTimeOffset(-155) | microsoft.sql.DateTimeOffset(-155) |
SMALLDATETIME | java.sql.Timestamp(93) | java.sql.Timestamp(93) |
import io.debezium.spi.converter.CustomConverter;
import io.debezium.spi.converter.RelationalColumn;
import org.apache.kafka.connect.data.SchemaBuilder;
import java.time.ZoneOffset;
import java.time.format.DateTimeFormatter;
import java.util.Properties;
@Sl4j
public class SqlserverDebeziumConverter implements CustomConverter<SchemaBuilder, RelationalColumn> {
private static final String DATE_FORMAT = "yyyy-MM-dd";
private static final String TIME_FORMAT = "HH:mm:ss";
private static final String DATETIME_FORMAT = "yyyy-MM-dd HH:mm:ss";
private DateTimeFormatter dateFormatter;
private DateTimeFormatter timeFormatter;
private DateTimeFormatter datetimeFormatter;
private SchemaBuilder schemaBuilder;
private String databaseType;
private String schemaNamePrefix;
@Override
public void configure(Properties properties) {
// 必填参数：database.type，只支持sqlserver
this.databaseType = properties.getProperty("database.type");
// 如果未设置，或者设置的不是mysql、sqlserver，则抛出异常。
if (this.databaseType == null || !this.databaseType.equals("sqlserver"))) {
throw new IllegalArgumentException("database.type 必须设置为'sqlserver'");
}
// 选填参数：format.date、format.time、format.datetime。获取时间格式化的格式
String dateFormat = properties.getProperty("format.date", DATE_FORMAT);
String timeFormat = properties.getProperty("format.time", TIME_FORMAT);
String datetimeFormat = properties.getProperty("format.datetime", DATETIME_FORMAT);
// 获取自身类的包名 数据库类型为默认schema.name
String className = this.getClass().getName();
// 查看是否设置schema.name.prefix
this.schemaNamePrefix = properties.getProperty("schema.name.prefix", className "." this.databaseType);
// 初始化时间格式化器
dateFormatter = DateTimeFormatter.ofPattern(dateFormat);
timeFormatter = DateTimeFormatter.ofPattern(timeFormat);
datetimeFormatter = DateTimeFormatter.ofPattern(datetimeFormat);
}
// sqlserver的转换器
public void registerSqlserverConverter(String columnType, ConverterRegistration<SchemaBuilder> converterRegistration) {
String schemaName = this.schemaNamePrefix "." columnType.toLowerCase();
schemaBuilder = SchemaBuilder.string().name(schemaName);
switch (columnType) {
case "DATE":
converterRegistration.register(schemaBuilder, value -> {
if (value == null) {
return null;
} else if (value instanceof java.sql.Date) {
return dateFormatter.format(((java.sql.Date) value).toLocalDate());
} else {
return this.failConvert(value, schemaName);
}
});
break;
case "TIME":
converterRegistration.register(schemaBuilder, value -> {
if (value == null) {
return null;
} else if (value instanceof java.sql.Time) {
return timeFormatter.format(((java.sql.Time) value).toLocalTime());
} else if (value instanceof java.sql.Timestamp) {
return timeFormatter.format(((java.sql.Timestamp) value).toLocalDateTime().toLocalTime());
} else {
return this.failConvert(value, schemaName);
}
});
break;
case "DATETIME":
case "DATETIME2":
case "SMALLDATETIME":
case "DATETIMEOFFSET":
converterRegistration.register(schemaBuilder, value -> {
if (value == null) {
return null;
} else if (value instanceof java.sql.Timestamp) {
return datetimeFormatter.format(((java.sql.Timestamp) value).toLocalDateTime());
} else if (value instanceof microsoft.sql.DateTimeOffset) {
microsoft.sql.DateTimeOffset dateTimeOffset = (microsoft.sql.DateTimeOffset) value;
return datetimeFormatter.format(
dateTimeOffset.getOffsetDateTime().withOffsetSameInstant(ZoneOffset.UTC).toLocalDateTime());
} else {
return this.failConvert(value, schemaName);
}
});
break;
default:
schemaBuilder = null;
break;
}
}
@Override
public void converterFor(RelationalColumn relationalColumn, ConverterRegistration<SchemaBuilder> converterRegistration) {
// 获取字段类型
String columnType = relationalColumn.typeName().toUpperCase();
// 根据数据库类型调用不同的转换器
if (this.databaseType.equals("sqlserver")) {
this.registerSqlserverConverter(columnType, converterRegistration);
} else {
log.warn("不支持的数据库类型: {}", this.databaseType);
schemaBuilder = null;
}
}
private String getClassName(Object value) {
if (value == null) {
return null;
}
return value.getClass().getName();
}
// 类型转换失败时的日志打印
private String failConvert(Object value, String type) {
String valueClass = this.getClassName(value);
String valueString = valueClass == null ? null : value.toString();
return valueString;
}
}三、总计
目前Fink-CDC对这种增量采集传统数据库的技术已经封装的很好了，并且官方也给了详细的操作教程，但如果想要深入的学习一项技能，个人觉得还是要从头到尾操作一遍，一方面能够快速的提升自己，另一方面发现问题时，也能从不同的角度来思考解决方案，希望本篇文章能够给大家带来一点帮助。
我正在参与2024腾讯技术创作特训营最新征文，快来和我瓜分大奖！
