Flink CDC同步Oracle无主键表

问题背景

Flink CDC是一种很强大且实用的实时数据同步工具，官网如下。
链接: link
但是在实际使用过程中还是会有些不足之处，比如说同步Oracle数据库中无主键以及唯一键的表时，关于目标端的幂等性时无法保证的。

问题解决

在Oracle数据库中，表中有一个伪列ROWID，而在CDC同步过来的数据中是不包含此列的。
修改源码如下，使之携带ROWID信息传入flink程序中，并且在目标端建表时将ROWID设置为主键。
下面展示一些 内联代码片。

 类 debezium-1.9.7.Final\debezium-connector-oracle\src\main\java\io\debezium\connector\oracle\SourceInfo.java
 // 增加以下内容
 public static final String ROW_ID = "px_rowid";
 private String rowid;

    public String getRowId() {
        return rowid;
    }

    public void setRowid(String rowId) {
        this.rowid = rowId;
    }
```java
类 debezium-1.9.7.Final\debezium-connector-oracle\src\main\java\io\debezium\connector\oracle\OracleSourceInfoStructMaker.java
public OracleSourceInfoStructMaker(String connector, String version, CommonConnectorConfig connectorConfig) {
        super(connector, version, connectorConfig);
        final SchemaBuilder schemaBuilder = commonSchemaBuilder()
                .name("io.debezium.connector.oracle.Source")
                .field(SourceInfo.SCHEMA_NAME_KEY, Schema.STRING_SCHEMA)
                .field(SourceInfo.TABLE_NAME_KEY, Schema.STRING_SCHEMA)
                .field(SourceInfo.TXID_KEY, Schema.OPTIONAL_STRING_SCHEMA)
                .field(SourceInfo.ROW_ID, Schema.OPTIONAL_STRING_SCHEMA)
                .field(SourceInfo.EVENT_SCN_KEY, Schema.OPTIONAL_STRING_SCHEMA)
                .field(SourceInfo.COMMIT_SCN_KEY, Schema.OPTIONAL_STRING_SCHEMA)
                .field(SourceInfo.LCR_POSITION_KEY, Schema.OPTIONAL_STRING_SCHEMA)
                .field(CommitScn.ROLLBACK_SEGMENT_ID_KEY, Schema.OPTIONAL_STRING_SCHEMA)
                .field(CommitScn.SQL_SEQUENCE_NUMBER_KEY, Schema.OPTIONAL_INT32_SCHEMA);

        this.schema = CommitScn.schemaBuilder(schemaBuilder).build();
    }
    
public Struct struct(SourceInfo sourceInfo) {
        final String eventScn = sourceInfo.getEventScn() == null ? null : sourceInfo.getEventScn().toString();

        final Struct ret = super.commonStruct(sourceInfo)
                .put(SourceInfo.SCHEMA_NAME_KEY, sourceInfo.tableSchema())
                .put(SourceInfo.TABLE_NAME_KEY, sourceInfo.table())
                .put(SourceInfo.TXID_KEY, sourceInfo.getTransactionId())
                .put(SourceInfo.ROW_ID, sourceInfo.getRowId())
                .put(SourceInfo.EVENT_SCN_KEY, eventScn);

        if (sourceInfo.getLcrPosition() != null) {
            ret.put(SourceInfo.LCR_POSITION_KEY, sourceInfo.getLcrPosition());
        }
        if (sourceInfo.getRsId() != null) {
            ret.put(CommitScn.ROLLBACK_SEGMENT_ID_KEY, sourceInfo.getRsId());
        }

        ret.put(CommitScn.SQL_SEQUENCE_NUMBER_KEY, sourceInfo.getSsn());

        final CommitScn commitScn = sourceInfo.getCommitScn();
        if (commitScn != null) {
            commitScn.store(sourceInfo, ret);
        }

        return ret;
    }
类 debezium-1.9.7.Final\debezium-connector-oracle\src\main\java\io\debezium\connector\oracle\OracleOffsetContext.java
    // 添加以下方法 注意不要放在内部类build中
    public void setRowId(String rowId) {
        sourceInfo.setRowid(rowId);
    }
修改完以上内容后记得install依赖，否则修改cdc代码时会报错。

类 flink-cdc-release-3.0.1\flink-cdc-connect\flink-cdc-source-connectors\flink-connector-oracle-cdc\src\main\java\io\debezium\connector\oracle\logminer\processor\AbstractLogMinerEventProcessor.java
protected void handleCommit(OraclePartition partition, LogMinerEventRow row)
            throws InterruptedException {
        ...

                    @Override
                    public void accept(LogMinerEvent event, long eventsProcessed)
                            throws InterruptedException {
                        if (smallestScn.isNull() || commitScn.compareTo(smallestScn) < 0) {
                            offsetContext.setScn(event.getScn());
                            metrics.setOldestScn(event.getScn());
                        }

                        offsetContext.setEventScn(event.getScn());
                        offsetContext.setTransactionId(transactionId);
                        // 加入以下语句
                        offsetContext.setRowId(event.getRowId());

                        offsetContext.setSourceTime(
                                event.getChangeTime()
                                        .minusSeconds(databaseOffset.getTotalSeconds()));
                        offsetContext.setTableId(event.getTableId());
                        offsetContext.setRedoThread(row.getThread());
                        if (eventsProcessed == numEvents) {
                            // reached the last event update the commit scn in the offsets
                            offsetContext.getCommitScn().recordCommit(row);
                        }

         ...
    }