Examples with DbDialect com.alibaba.otter.node.etl.common.db.dialect.DbDialect used on opensource projects

Example 6 with DbDialect

use of com.alibaba.otter.node.etl.common.db.dialect.DbDialect in project otter by alibaba.

the class DatabaseExtractor method checkNeedDbForRowMode.

private boolean checkNeedDbForRowMode(Pipeline pipeline, EventData eventData) {
    // 获取数据表信息
    DataMedia dataMedia = ConfigHelper.findDataMedia(pipeline, eventData.getTableId());
    DbDialect dbDialect = dbDialectFactory.getDbDialect(pipeline.getId(), (DbMediaSource) dataMedia.getSource());
    Table table = dbDialect.findTable(eventData.getSchemaName(), eventData.getTableName());
    if (table.getColumnCount() == eventData.getColumns().size() + eventData.getKeys().size()) {
        return false;
    } else {
        return true;
    }
}

Example 7 with DbDialect

use of com.alibaba.otter.node.etl.common.db.dialect.DbDialect in project otter by alibaba.

the class FreedomExtractor method extract.

public void extract(DbBatch dbBatch) throws ExtractException {
    Assert.notNull(dbBatch);
    // 读取配置
    Pipeline pipeline = getPipeline(dbBatch.getRowBatch().getIdentity().getPipelineId());
    boolean skipFreedom = pipeline.getParameters().getSkipFreedom();
    String bufferSchema = pipeline.getParameters().getSystemSchema();
    String bufferTable = pipeline.getParameters().getSystemBufferTable();
    List<EventData> eventDatas = dbBatch.getRowBatch().getDatas();
    // 使用set，提升remove时的查找速度
    Set<EventData> removeDatas = new HashSet<EventData>();
    for (EventData eventData : eventDatas) {
        if (StringUtils.equalsIgnoreCase(bufferSchema, eventData.getSchemaName()) && StringUtils.equalsIgnoreCase(bufferTable, eventData.getTableName())) {
            if (eventData.getEventType().isDdl()) {
                continue;
            }
            if (skipFreedom) {
                // 判断是否需要忽略
                removeDatas.add(eventData);
                continue;
            }
            // 只处理insert / update记录
            if (eventData.getEventType().isInsert() || eventData.getEventType().isUpdate()) {
                // 重新改写一下EventData的数据，根据系统表的定义
                EventColumn tableIdColumn = getMatchColumn(eventData.getColumns(), TABLE_ID);
                // 获取到对应tableId的media信息
                try {
                    DataMedia dataMedia = null;
                    Long tableId = Long.valueOf(tableIdColumn.getColumnValue());
                    eventData.setTableId(tableId);
                    if (tableId <= 0) {
                        // 直接按照full_name进行查找
                        // 尝试直接根据schema+table name进行查找
                        EventColumn fullNameColumn = getMatchColumn(eventData.getColumns(), FULL_NAME);
                        if (fullNameColumn != null) {
                            String[] names = StringUtils.split(fullNameColumn.getColumnValue(), ".");
                            if (names.length >= 2) {
                                dataMedia = ConfigHelper.findSourceDataMedia(pipeline, names[0], names[1]);
                                eventData.setTableId(dataMedia.getId());
                            } else {
                                throw new ConfigException("no such DataMedia " + names);
                            }
                        }
                    } else {
                        // 如果指定了tableId，需要按照tableId进行严格查找，如果没找到，那说明不需要进行同步
                        dataMedia = ConfigHelper.findDataMedia(pipeline, Long.valueOf(tableIdColumn.getColumnValue()));
                    }
                    DbDialect dbDialect = dbDialectFactory.getDbDialect(pipeline.getId(), (DbMediaSource) dataMedia.getSource());
                    // 考虑offer[1-128]的配置模式
                    if (!dataMedia.getNameMode().getMode().isSingle() || !dataMedia.getNamespaceMode().getMode().isSingle()) {
                        boolean hasError = true;
                        EventColumn fullNameColumn = getMatchColumn(eventData.getColumns(), FULL_NAME);
                        if (fullNameColumn != null) {
                            String[] names = StringUtils.split(fullNameColumn.getColumnValue(), ".");
                            if (names.length >= 2) {
                                eventData.setSchemaName(names[0]);
                                eventData.setTableName(names[1]);
                                hasError = false;
                            }
                        }
                        if (hasError) {
                            // 出现异常，需要记录一下
                            logger.warn("dataMedia mode:{} , fullname:{} ", dataMedia.getMode(), fullNameColumn == null ? null : fullNameColumn.getColumnValue());
                            removeDatas.add(eventData);
                            // 跳过这条记录
                            continue;
                        }
                    } else {
                        eventData.setSchemaName(dataMedia.getNamespace());
                        eventData.setTableName(dataMedia.getName());
                    }
                    // 更新业务类型
                    EventColumn typeColumn = getMatchColumn(eventData.getColumns(), TYPE);
                    EventType eventType = EventType.valuesOf(typeColumn.getColumnValue());
                    eventData.setEventType(eventType);
                    if (eventType.isUpdate()) {
                        // 如果是update强制修改为insert，这样可以在目标端执行merge
                        // sql
                        eventData.setEventType(EventType.INSERT);
                    } else if (eventType.isDdl()) {
                        dbDialect.reloadTable(eventData.getSchemaName(), eventData.getTableName());
                        // 删除当前记录
                        removeDatas.add(eventData);
                        continue;
                    }
                    // 重新构建新的业务主键字段
                    EventColumn pkDataColumn = getMatchColumn(eventData.getColumns(), PK_DATA);
                    String pkData = pkDataColumn.getColumnValue();
                    String[] pks = StringUtils.split(pkData, PK_SPLIT);
                    Table table = dbDialect.findTable(eventData.getSchemaName(), eventData.getTableName());
                    List<EventColumn> newColumns = new ArrayList<EventColumn>();
                    Column[] primaryKeyColumns = table.getPrimaryKeyColumns();
                    if (primaryKeyColumns.length > pks.length) {
                        throw new ExtractException("data pk column size not match , data:" + eventData.toString());
                    }
                    // 构建字段
                    Column[] allColumns = table.getColumns();
                    int pkIndex = 0;
                    for (int i = 0; i < allColumns.length; i++) {
                        Column column = allColumns[i];
                        if (column.isPrimaryKey()) {
                            EventColumn newColumn = new EventColumn();
                            // 设置下标
                            newColumn.setIndex(i);
                            newColumn.setColumnName(column.getName());
                            newColumn.setColumnType(column.getTypeCode());
                            newColumn.setColumnValue(pks[pkIndex]);
                            newColumn.setKey(true);
                            newColumn.setNull(pks[pkIndex] == null);
                            newColumn.setUpdate(true);
                            // 添加到记录
                            newColumns.add(newColumn);
                            pkIndex++;
                        }
                    }
                    // 设置数据
                    eventData.setKeys(newColumns);
                    eventData.setOldKeys(new ArrayList<EventColumn>());
                    eventData.setColumns(new ArrayList<EventColumn>());
                    // 设置为行记录+反查
                    eventData.setSyncMode(SyncMode.ROW);
                    eventData.setSyncConsistency(SyncConsistency.MEDIA);
                    eventData.setRemedy(true);
                    // 默认为1kb，如果还是按照binlog大小计算的话，可能会采用rpc传输，导致内存不够用
                    eventData.setSize(1024);
                } catch (ConfigException e) {
                    // 忽略掉，因为系统表会被共享，所以这条记录会被不是该同步通道给获取到
                    logger.info("find DataMedia error " + eventData.toString(), e);
                    removeDatas.add(eventData);
                    continue;
                } catch (Throwable e) {
                    // 出现异常时忽略掉
                    logger.warn("process freedom data error " + eventData.toString(), e);
                    removeDatas.add(eventData);
                    continue;
                }
            } else {
                // 删除该记录
                removeDatas.add(eventData);
            }
        }
    }
    if (!CollectionUtils.isEmpty(removeDatas)) {
        eventDatas.removeAll(removeDatas);
    }
}

Example 8 with DbDialect

use of com.alibaba.otter.node.etl.common.db.dialect.DbDialect in project otter by alibaba.

the class OperationInterceptorFactory method getIntercetptor.

private LoadInterceptor[] getIntercetptor(DbLoadContext context, List<EventData> currentData) {
    if (currentData == null || currentData.size() == 0) {
        return empty;
    }
    DataMedia dataMedia = ConfigHelper.findDataMedia(context.getPipeline(), currentData.get(0).getTableId());
    DbDialect dbDialect = dbDialectFactory.getDbDialect(context.getIdentity().getPipelineId(), (DbMediaSource) dataMedia.getSource());
    if (dbDialect instanceof MysqlDialect) {
        return mysqlInterceptors;
    } else if (dbDialect instanceof OracleDialect) {
        return oracleInterceptors;
    } else {
        return empty;
    }
}

Example 9 with DbDialect

use of com.alibaba.otter.node.etl.common.db.dialect.DbDialect 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;
}

Example 10 with DbDialect

use of com.alibaba.otter.node.etl.common.db.dialect.DbDialect 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;
}