Search in sources :

Example 6 with EventType

use of com.alibaba.otter.shared.etl.model.EventType in project otter by alibaba.

the class MessageParser method internParse.

/**
     * 解析出从canal中获取的Event事件<br>
     * Oracle:有变更的列值. <br>
     * <i>insert:从afterColumns中获取所有的变更数据<br>
     * <i>delete:从beforeColumns中获取所有的变更数据<br>
     * <i>update:在before中存放所有的主键和变化前的非主键值,在after中存放变化后的主键和非主键值,如果是复合主键,只会存放变化的主键<br>
     * Mysql:可以得到所有变更前和变更后的数据.<br>
     * <i>insert:从afterColumns中获取所有的变更数据<br>
     * <i>delete:从beforeColumns中获取所有的变更数据<br>
     * <i>update:在beforeColumns中存放变更前的所有数据,在afterColumns中存放变更后的所有数据<br>
     */
private EventData internParse(Pipeline pipeline, Entry entry, RowChange rowChange, RowData rowData) {
    EventData eventData = new EventData();
    eventData.setTableName(entry.getHeader().getTableName());
    eventData.setSchemaName(entry.getHeader().getSchemaName());
    eventData.setEventType(EventType.valueOf(rowChange.getEventType().name()));
    eventData.setExecuteTime(entry.getHeader().getExecuteTime());
    EventType eventType = eventData.getEventType();
    TableInfoHolder tableHolder = null;
    if (!StringUtils.equalsIgnoreCase(pipeline.getParameters().getSystemSchema(), eventData.getSchemaName())) {
        boolean useTableTransform = pipeline.getParameters().getUseTableTransform();
        Table table = null;
        DataMediaPair dataMediaPair = ConfigHelper.findDataMediaPairBySourceName(pipeline, eventData.getSchemaName(), eventData.getTableName());
        DataMedia dataMedia = dataMediaPair.getSource();
        eventData.setTableId(dataMedia.getId());
        // 获取目标表
        DataMedia targetDataMedia = dataMediaPair.getTarget();
        if (useTableTransform || dataMedia.getSource().getType().isOracle()) {
            // oracle需要反查一次meta
            // 如果设置了需要进行table meta转化,则反查一下table信息
            // 比如oracle erosa解析时可能使用了非物理主键,需要直接使用,信任erosa的信息
            DbDialect dbDialect = dbDialectFactory.getDbDialect(pipeline.getId(), (DbMediaSource) dataMedia.getSource());
            // 查询一下meta信息
            table = dbDialect.findTable(eventData.getSchemaName(), eventData.getTableName());
            if (table == null) {
                logger.warn("find table[{}.{}] is null , may be drop table.", eventData.getSchemaName(), eventData.getTableName());
            }
            // 获取一下目标库的拆分字段,设置源表为主键
            // 首先要求源和目标的库名表名是一致的
            DbDialect targetDbDialect = dbDialectFactory.getDbDialect(pipeline.getId(), (DbMediaSource) targetDataMedia.getSource());
            if (targetDbDialect.isDRDS()) {
                String schemaName = buildName(eventData.getSchemaName(), dataMedia.getNamespaceMode(), targetDataMedia.getNamespaceMode());
                String tableName = buildName(eventData.getSchemaName(), dataMedia.getNameMode(), targetDataMedia.getNameMode());
                String shardColumns = targetDbDialect.getShardColumns(schemaName, tableName);
                if (StringUtils.isNotEmpty(shardColumns)) {
                    String[] columns = StringUtils.split(shardColumns, ',');
                    for (String key : columns) {
                        org.apache.ddlutils.model.Column col = table.findColumn(key, false);
                        if (col != null) {
                            col.setPrimaryKey(true);
                        } else {
                            logger.warn(String.format("shardColumn %s in table[%s.%s] is not found", key, eventData.getSchemaName(), eventData.getTableName()));
                        }
                    }
                }
            }
            tableHolder = new TableInfoHolder(dbDialect, table, useTableTransform);
        }
    }
    List<Column> beforeColumns = rowData.getBeforeColumnsList();
    List<Column> afterColumns = rowData.getAfterColumnsList();
    String tableName = eventData.getSchemaName() + "." + eventData.getTableName();
    // 判断一下是否需要all columns
    // 如果是rowMode模式,所有字段都需要标记为updated
    boolean isRowMode = pipeline.getParameters().getSyncMode().isRow();
    boolean needAllColumns = isRowMode || checkNeedAllColumns(pipeline);
    // 变更后的主键
    Map<String, EventColumn> keyColumns = new LinkedHashMap<String, EventColumn>();
    // 变更前的主键
    Map<String, EventColumn> oldKeyColumns = new LinkedHashMap<String, EventColumn>();
    // 有变化的非主键
    Map<String, EventColumn> notKeyColumns = new LinkedHashMap<String, EventColumn>();
    if (eventType.isInsert()) {
        for (Column column : afterColumns) {
            if (isKey(tableHolder, tableName, column)) {
                keyColumns.put(column.getName(), copyEventColumn(column, true, tableHolder));
            } else {
                // mysql 有效
                notKeyColumns.put(column.getName(), copyEventColumn(column, true, tableHolder));
            }
        }
    } else if (eventType.isDelete()) {
        for (Column column : beforeColumns) {
            if (isKey(tableHolder, tableName, column)) {
                keyColumns.put(column.getName(), copyEventColumn(column, true, tableHolder));
            } else {
                // mysql 有效
                notKeyColumns.put(column.getName(), copyEventColumn(column, true, tableHolder));
            }
        }
    } else if (eventType.isUpdate()) {
        // 获取变更前的主键.
        for (Column column : beforeColumns) {
            if (isKey(tableHolder, tableName, column)) {
                oldKeyColumns.put(column.getName(), copyEventColumn(column, true, tableHolder));
                // 同时记录一下new
                // key,因为mysql5.6之后出现了minimal模式,after里会没有主键信息,需要在before记录中找
                keyColumns.put(column.getName(), copyEventColumn(column, true, tableHolder));
            } else {
                if (needAllColumns && entry.getHeader().getSourceType() == CanalEntry.Type.ORACLE) {
                    // 针对行记录同步时,针对oracle记录一下非主键的字段,因为update时针对未变更的字段在aftercolume里没有
                    notKeyColumns.put(column.getName(), copyEventColumn(column, isRowMode, tableHolder));
                }
            }
        }
        for (Column column : afterColumns) {
            if (isKey(tableHolder, tableName, column)) {
                // 获取变更后的主键
                keyColumns.put(column.getName(), copyEventColumn(column, true, tableHolder));
            } else if (needAllColumns || entry.getHeader().getSourceType() == CanalEntry.Type.ORACLE || column.getUpdated()) {
                // 在update操作时,oracle和mysql存放变更的非主键值的方式不同,oracle只有变更的字段;
                // mysql会把变更前和变更后的字段都发出来,只需要取有变更的字段.
                // 如果是oracle库,after里一定为对应的变更字段
                boolean isUpdate = true;
                if (entry.getHeader().getSourceType() == CanalEntry.Type.MYSQL) {
                    // mysql的after里部分数据为未变更,oracle里after里为变更字段
                    isUpdate = column.getUpdated();
                }
                // 如果是rowMode,所有字段都为updated
                notKeyColumns.put(column.getName(), copyEventColumn(column, isRowMode || isUpdate, tableHolder));
            }
        }
        if (entry.getHeader().getSourceType() == CanalEntry.Type.ORACLE) {
            // 针对oracle进行特殊处理
            checkUpdateKeyColumns(oldKeyColumns, keyColumns);
        }
    }
    List<EventColumn> keys = new ArrayList<EventColumn>(keyColumns.values());
    List<EventColumn> oldKeys = new ArrayList<EventColumn>(oldKeyColumns.values());
    List<EventColumn> columns = new ArrayList<EventColumn>(notKeyColumns.values());
    Collections.sort(keys, new EventColumnIndexComparable());
    Collections.sort(oldKeys, new EventColumnIndexComparable());
    Collections.sort(columns, new EventColumnIndexComparable());
    if (!keyColumns.isEmpty()) {
        eventData.setKeys(keys);
        if (eventData.getEventType().isUpdate() && !oldKeys.equals(keys)) {
            // update类型,如果存在主键不同,则记录下old
            // keys为变更前的主键
            eventData.setOldKeys(oldKeys);
        }
        eventData.setColumns(columns);
    // } else if (CanalEntry.Type.MYSQL ==
    // entry.getHeader().getSourceType()) {
    // // 只支持mysql无主键同步
    // if (eventType.isUpdate()) {
    // List<EventColumn> oldColumns = new ArrayList<EventColumn>();
    // List<EventColumn> newColumns = new ArrayList<EventColumn>();
    // for (Column column : beforeColumns) {
    // oldColumns.add(copyEventColumn(column, true, tableHolder));
    // }
    //
    // for (Column column : afterColumns) {
    // newColumns.add(copyEventColumn(column, true, tableHolder));
    // }
    // Collections.sort(oldColumns, new EventColumnIndexComparable());
    // Collections.sort(newColumns, new EventColumnIndexComparable());
    // eventData.setOldKeys(oldColumns);// 做为老主键
    // eventData.setKeys(newColumns);// 做为新主键,需要保证新老主键字段数量一致
    // } else {
    // // 针对无主键,等同为所有都是主键进行处理
    // eventData.setKeys(columns);
    // }
    } else {
        throw new SelectException("this rowdata has no pks , entry: " + entry.toString() + " and rowData: " + rowData);
    }
    return eventData;
}
Also used : Table(org.apache.ddlutils.model.Table) DataMediaPair(com.alibaba.otter.shared.common.model.config.data.DataMediaPair) EventType(com.alibaba.otter.shared.etl.model.EventType) EventColumn(com.alibaba.otter.shared.etl.model.EventColumn) ArrayList(java.util.ArrayList) SelectException(com.alibaba.otter.node.etl.select.exceptions.SelectException) EventData(com.alibaba.otter.shared.etl.model.EventData) LinkedHashMap(java.util.LinkedHashMap) EventColumnIndexComparable(com.alibaba.otter.shared.etl.model.EventColumnIndexComparable) EventColumn(com.alibaba.otter.shared.etl.model.EventColumn) Column(com.alibaba.otter.canal.protocol.CanalEntry.Column) DbDialect(com.alibaba.otter.node.etl.common.db.dialect.DbDialect) DataMedia(com.alibaba.otter.shared.common.model.config.data.DataMedia)

Example 7 with EventType

use of com.alibaba.otter.shared.etl.model.EventType in project otter by alibaba.

the class MessageParser method internParse.

private List<EventData> internParse(Pipeline pipeline, Entry entry) {
    RowChange rowChange = null;
    try {
        rowChange = RowChange.parseFrom(entry.getStoreValue());
    } catch (Exception e) {
        throw new SelectException("parser of canal-event has an error , data:" + entry.toString(), e);
    }
    if (rowChange == null) {
        return null;
    }
    String schemaName = entry.getHeader().getSchemaName();
    String tableName = entry.getHeader().getTableName();
    EventType eventType = EventType.valueOf(rowChange.getEventType().name());
    // 处理下DDL操作
    if (eventType.isQuery()) {
        // 直接忽略query事件
        return null;
    }
    // 首先判断是否为系统表
    if (StringUtils.equalsIgnoreCase(pipeline.getParameters().getSystemSchema(), schemaName)) {
        // do noting
        if (eventType.isDdl()) {
            return null;
        }
        if (StringUtils.equalsIgnoreCase(pipeline.getParameters().getSystemDualTable(), tableName)) {
            // 心跳表数据直接忽略
            return null;
        }
    } else {
        if (eventType.isDdl()) {
            boolean notExistReturnNull = false;
            if (eventType.isRename()) {
                notExistReturnNull = true;
            }
            DataMedia dataMedia = ConfigHelper.findSourceDataMedia(pipeline, schemaName, tableName, notExistReturnNull);
            // DataMediaInfo;并且把CREATE/ALTER类型的事件丢弃掉.
            if (dataMedia != null && (eventType.isCreate() || eventType.isAlter() || eventType.isRename())) {
                DbDialect dbDialect = dbDialectFactory.getDbDialect(pipeline.getId(), (DbMediaSource) dataMedia.getSource());
                // 更新下meta信息
                dbDialect.reloadTable(schemaName, tableName);
            }
            boolean ddlSync = pipeline.getParameters().getDdlSync();
            if (ddlSync) {
                // 处理下ddl操作
                EventData eventData = new EventData();
                eventData.setSchemaName(schemaName);
                eventData.setTableName(tableName);
                eventData.setEventType(eventType);
                eventData.setExecuteTime(entry.getHeader().getExecuteTime());
                eventData.setSql(rowChange.getSql());
                eventData.setDdlSchemaName(rowChange.getDdlSchemaName());
                eventData.setTableId(dataMedia.getId());
                return Arrays.asList(eventData);
            } else {
                return null;
            }
        }
    }
    List<EventData> eventDatas = new ArrayList<EventData>();
    for (RowData rowData : rowChange.getRowDatasList()) {
        EventData eventData = internParse(pipeline, entry, rowChange, rowData);
        if (eventData != null) {
            eventDatas.add(eventData);
        }
    }
    return eventDatas;
}
Also used : RowData(com.alibaba.otter.canal.protocol.CanalEntry.RowData) RowChange(com.alibaba.otter.canal.protocol.CanalEntry.RowChange) EventType(com.alibaba.otter.shared.etl.model.EventType) DbDialect(com.alibaba.otter.node.etl.common.db.dialect.DbDialect) SelectException(com.alibaba.otter.node.etl.select.exceptions.SelectException) ArrayList(java.util.ArrayList) SelectException(com.alibaba.otter.node.etl.select.exceptions.SelectException) TransformException(com.alibaba.otter.node.etl.transform.exception.TransformException) DataMedia(com.alibaba.otter.shared.common.model.config.data.DataMedia) EventData(com.alibaba.otter.shared.etl.model.EventData)

Example 8 with EventType

use of com.alibaba.otter.shared.etl.model.EventType in project otter by alibaba.

the class RowDataTransformer method translateColumn.

private EventColumn translateColumn(EventData data, EventColumn scolumn, TableInfoHolder tableHolder, DataMediaPair dataMediaPair, Multimap<String, String> translateColumnNames) {
    EventType type = data.getEventType();
    EventColumn tcolumn = new EventColumn();
    tcolumn.setNull(scolumn.getColumnValue() == null);
    // 左右两边的主键值必须保持一样,可以不为物理主键
    tcolumn.setKey(scolumn.isKey());
    tcolumn.setIndex(scolumn.getIndex());
    tcolumn.setUpdate(scolumn.isUpdate());
    String columnName = translateColumnName(scolumn.getColumnName(), dataMediaPair, translateColumnNames);
    if (StringUtils.isBlank(columnName)) {
        throw new TransformException("can't translate column name:" + scolumn.getColumnName() + "in pair:" + dataMediaPair.toString());
    }
    // 特殊处理
    // columnName = StringUtils.remove(columnName, "`"); //
    // 处理下特殊字符,eromanga给了错误的字段名
    tcolumn.setColumnName(columnName);
    // 不反查,直接使用源库的类型
    tcolumn.setColumnType(scolumn.getColumnType());
    if (tableHolder != null) {
        // modify by ljh at 2013-01-23
        // 双向同步新增字段,在一边加了字段后,虽然新的字段没有产生业务变化,但会因为某些原因导致传递了新的字段到T模块
        // 此时在目标库并不存在这个字段,导致一直挂起。ps. mysql新增字段时间不是一般的长
        // 所以,做了一个容错处理,针对目标库不存在的字段,如果变更记录在源库不存在变更,并且是null值的,允许丢弃该字段(其实最好还是要判断源库的column的defaultValue和当前值是否一致)
        boolean canColumnsNotExist = tableHolder.isEnableCompatibleMissColumn();
        if (type == EventType.UPDATE) {
            // 非变更字段,且当前值为null
            canColumnsNotExist &= !scolumn.isUpdate() && scolumn.isNull();
        } else if (type == EventType.INSERT) {
            // 当前值为null
            canColumnsNotExist &= scolumn.isNull();
        } else if (type == EventType.DELETE) {
            // 主键不允许不存在
            canColumnsNotExist &= !scolumn.isKey();
        }
        Column matchDbColumn = getMatchColumn(tableHolder.getTable().getColumns(), tcolumn.getColumnName());
        // 匹配字段为空,可能源库发生过DDL操作,目标库重新载入一下meta信息
        if (matchDbColumn == null) {
            // 尝试reload一下table meta
            // 获取目标库的表信息
            DbMediaSource dbMediaSource = (DbMediaSource) dataMediaPair.getTarget().getSource();
            DbDialect dbDialect = dbDialectFactory.getDbDialect(dataMediaPair.getPipelineId(), dbMediaSource);
            String schemaName = tableHolder.getTable().getSchema();
            if (StringUtils.isEmpty(schemaName)) {
                schemaName = tableHolder.getTable().getCatalog();
            }
            // 强制反查一次,并放入cache
            Table table = dbDialect.findTable(schemaName, tableHolder.getTable().getName(), false);
            tableHolder.setTable(table);
            matchDbColumn = getMatchColumn(tableHolder.getTable().getColumns(), tcolumn.getColumnName());
            if (matchDbColumn == null) {
                if (canColumnsNotExist) {
                    return null;
                } else {
                    throw new TransformException(scolumn.getColumnName() + " is not found in " + table.toString() + " and source : " + dataMediaPair.getTarget().getNamespace() + "." + dataMediaPair.getTarget().getName());
                }
            }
        }
        if (tableHolder.isUseTableTransform()) {
            int sqlType = matchDbColumn.getTypeCode();
            tcolumn.setColumnType(sqlType);
        }
    }
    // if (dataMediaPair.getTarget().getSource().getType().isOracle()) {
    // // 特殊处理下oracle编码
    // String encodeValue = SqlUtils.encoding(scolumn.getColumnValue(),
    // scolumn.getColumnType(),
    // dataMediaPair.getSource().getSource().getEncode(),
    // dataMediaPair.getTarget().getSource().getEncode());
    // tcolumn.setColumnValue(encodeValue);
    // } else {
    // mysql编码转化已经在驱动层面上完成
    tcolumn.setColumnValue(scolumn.getColumnValue());
    // }
    // 删除映射关系,避免下次重复转换
    translateColumnNames.remove(scolumn.getColumnName(), columnName);
    return tcolumn;
}
Also used : Table(org.apache.ddlutils.model.Table) EventType(com.alibaba.otter.shared.etl.model.EventType) EventColumn(com.alibaba.otter.shared.etl.model.EventColumn) EventColumn(com.alibaba.otter.shared.etl.model.EventColumn) Column(org.apache.ddlutils.model.Column) DbDialect(com.alibaba.otter.node.etl.common.db.dialect.DbDialect) TransformException(com.alibaba.otter.node.etl.transform.exception.TransformException) DbMediaSource(com.alibaba.otter.shared.common.model.config.data.db.DbMediaSource)

Aggregations

EventType (com.alibaba.otter.shared.etl.model.EventType)8 DbDialect (com.alibaba.otter.node.etl.common.db.dialect.DbDialect)5 DataMedia (com.alibaba.otter.shared.common.model.config.data.DataMedia)3 EventColumn (com.alibaba.otter.shared.etl.model.EventColumn)3 EventData (com.alibaba.otter.shared.etl.model.EventData)3 ArrayList (java.util.ArrayList)3 Table (org.apache.ddlutils.model.Table)3 SelectException (com.alibaba.otter.node.etl.select.exceptions.SelectException)2 TransformException (com.alibaba.otter.node.etl.transform.exception.TransformException)2 Pipeline (com.alibaba.otter.shared.common.model.config.pipeline.Pipeline)2 Column (org.apache.ddlutils.model.Column)2 Column (com.alibaba.otter.canal.protocol.CanalEntry.Column)1 RowChange (com.alibaba.otter.canal.protocol.CanalEntry.RowChange)1 RowData (com.alibaba.otter.canal.protocol.CanalEntry.RowData)1 SqlTemplate (com.alibaba.otter.node.etl.common.db.dialect.SqlTemplate)1 OracleSqlTemplate (com.alibaba.otter.node.etl.common.db.dialect.oracle.OracleSqlTemplate)1 ConflictEventType (com.alibaba.otter.node.etl.conflict.model.ConflictEventType)1 ExtractException (com.alibaba.otter.node.etl.extract.exceptions.ExtractException)1 LoadCounter (com.alibaba.otter.node.etl.load.loader.LoadStatsTracker.LoadCounter)1 LoadThroughput (com.alibaba.otter.node.etl.load.loader.LoadStatsTracker.LoadThroughput)1