Add one-skill

one-skill/smart-data-developer/references/sql/templates/doris/create-table-template.sql

@@ -0,0 +1,209 @@
+-- =====================================================================
+-- @Name:             DORIS-D-SQL-{表名}-CREATE
+-- @Version:          1.0
+-- @Desc:             Apache Doris 建表模板（OLAP 多模型）
+-- @TargetDatabase:   Apache Doris
+-- =====================================================================
+
+-- ============================================================================
+-- 场景1：Duplicate Key 模型（明细表）
+-- ============================================================================
+-- 适用：保留原始明细数据，不做预聚合，数据无冗余
+-- 特点：数据按 Key 排序存储，支持所有列的查询和聚合
+
+CREATE TABLE IF NOT EXISTS db_name.detail_table (
+    -- Key 列（排序字段）
+    order_id        BIGINT          COMMENT '订单ID',
+    order_date      DATE            COMMENT '订单日期',
+    user_id         BIGINT          COMMENT '用户ID',
+
+    -- Value 列
+    user_name       VARCHAR(50)     COMMENT '用户姓名',
+    product_id      BIGINT          COMMENT '商品ID',
+    product_name    VARCHAR(200)    COMMENT '商品名称',
+    quantity        INT             COMMENT '购买数量',
+    unit_price      DECIMAL(18,2)   COMMENT '单价',
+    total_amount    DECIMAL(18,2)   COMMENT '总金额',
+    status          VARCHAR(20)     COMMENT '订单状态',
+    create_time     DATETIME        COMMENT '创建时间'
+)
+DUPLICATE KEY(order_id, order_date, user_id)
+COMMENT '订单明细表'
+PARTITION BY RANGE(order_date) (
+    PARTITION p202601 VALUES LESS THAN ('2026-02-01'),
+    PARTITION p202602 VALUES LESS THAN ('2026-03-01'),
+    PARTITION p202603 VALUES LESS THAN ('2026-04-01')
+)
+DISTRIBUTED BY HASH(order_id) BUCKETS 8
+PROPERTIES (
+    'replication_num' = '3',
+    'storage_format' = 'V2'
+);
+
+-- ============================================================================
+-- 场景2：Aggregate Key 模型（聚合表）
+-- ============================================================================
+-- 适用：预聚合场景，相同 Key 的数据自动合并
+-- 特点：Value 列必须指定聚合函数（SUM, REPLACE, MAX, MIN, HLL_UNION, BITMAP_UNION）
+
+CREATE TABLE IF NOT EXISTS db_name.agg_table (
+    -- Key 列（聚合维度）
+    stat_date       DATE            COMMENT '统计日期',
+    department      VARCHAR(100)    COMMENT '部门名称',
+    region          VARCHAR(100)    COMMENT '地区',
+
+    -- Value 列（带聚合函数）
+    order_count     BIGINT          SUM         COMMENT '订单总数',
+    total_amount    DECIMAL(18,2)   SUM         COMMENT '总金额',
+    unique_users    BIGINT          REPLACE     COMMENT '去重用户数（预计算值）',
+    max_amount      DECIMAL(18,2)   MAX         COMMENT '最大金额',
+    last_update     DATETIME        REPLACE     COMMENT '最后更新时间'
+)
+AGGREGATE KEY(stat_date, department, region)
+COMMENT '部门销售聚合表'
+PARTITION BY RANGE(stat_date) (
+    PARTITION p202601 VALUES LESS THAN ('2026-02-01'),
+    PARTITION p202602 VALUES LESS THAN ('2026-03-01')
+)
+DISTRIBUTED BY HASH(department) BUCKETS 8
+PROPERTIES (
+    'replication_num' = '3',
+    'storage_format' = 'V2'
+);
+
+-- ============================================================================
+-- 场景3：Unique Key 模型（唯一主键表）
+-- ============================================================================
+-- 适用：需要按主键更新/去重的场景
+-- 特点：相同主键的数据保留最新一条（整行替换）
+
+CREATE TABLE IF NOT EXISTS db_name.unique_table (
+    -- Key 列（主键，必须唯一）
+    user_id         BIGINT          COMMENT '用户ID',
+
+    -- Value 列
+    user_name       VARCHAR(50)     COMMENT '用户姓名',
+    phone           VARCHAR(20)     COMMENT '手机号',
+    email           VARCHAR(100)    COMMENT '邮箱',
+    vip_level       INT             COMMENT 'VIP等级',
+    register_date   DATE            COMMENT '注册日期',
+    last_login      DATETIME        COMMENT '最后登录时间',
+    status          VARCHAR(10)     COMMENT '状态'
+)
+UNIQUE KEY(user_id)
+COMMENT '用户信息表（按主键更新）'
+DISTRIBUTED BY HASH(user_id) BUCKETS 16
+PROPERTIES (
+    'replication_num' = '3',
+    'enable_unique_key_merge_based_on_replica' = 'true'
+);
+
+-- ============================================================================
+-- 场景4：带动态分区属性
+-- ============================================================================
+-- 适用：按日自动创建和管理分区
+
+CREATE TABLE IF NOT EXISTS db_name.auto_partition_table (
+    stat_date       DATE            COMMENT '统计日期',
+    department      VARCHAR(100)    COMMENT '部门',
+    metric_value    DECIMAL(18,2)   SUM         COMMENT '指标值',
+    record_count    BIGINT          SUM         COMMENT '记录数'
+)
+AGGREGATE KEY(stat_date, department)
+COMMENT '自动分区示例表'
+PARTITION BY RANGE(stat_date) ()
+DISTRIBUTED BY HASH(department) BUCKETS 8
+PROPERTIES (
+    'replication_num' = '3',
+    'dynamic_partition.enable' = 'true',
+    'dynamic_partition.time_unit' = 'DAY',
+    'dynamic_partition.start' = '-30',          -- 保留30天历史
+    'dynamic_partition.end' = '3',              -- 预创建3天
+    'dynamic_partition.prefix' = 'p',
+    'dynamic_partition.buckets' = '8'
+);
+
+-- ============================================================================
+-- 场景5：多分区 + 多分桶
+-- ============================================================================
+
+CREATE TABLE IF NOT EXISTS db_name.multi_partition_table (
+    stat_date       DATE            COMMENT '统计日期',
+    region          VARCHAR(50)     COMMENT '地区',
+    city            VARCHAR(50)     COMMENT '城市',
+    user_id         BIGINT          COMMENT '用户ID',
+    amount          DECIMAL(18,2)   SUM         COMMENT '金额'
+)
+AGGREGATE KEY(stat_date, region, city, user_id)
+COMMENT '多维度分区示例'
+PARTITION BY RANGE(stat_date) (
+    PARTITION p202601 VALUES LESS THAN ('2026-02-01'),
+    PARTITION p202602 VALUES LESS THAN ('2026-03-01')
+)
+DISTRIBUTED BY HASH(user_id) BUCKETS 32
+PROPERTIES (
+    'replication_num' = '3',
+    'in_memory' = 'false',
+    'storage_format' = 'V2',
+    'compression' = 'LZ4'
+);
+
+-- ============================================================================
+-- 字段类型速查
+-- ============================================================================
+/*
+| 类型          | 说明           | 适用场景               |
+|---------------|----------------|------------------------|
+| BOOLEAN       | 布尔           | 状态标志               |
+| TINYINT       | 1字节整数      | 小范围枚举             |
+| SMALLINT      | 2字节整数      | 小范围数值             |
+| INT           | 4字节整数      | 数量、等级             |
+| BIGINT        | 8字节整数      | ID、计数、大数值       |
+| LARGEINT      | 16字节整数     | 超大数值               |
+| FLOAT         | 4字节浮点      | 近似计算               |
+| DOUBLE        | 8字节浮点      | 科学计算               |
+| DECIMAL(p,s)  | 定点数         | 金额、精确数值         |
+| DATE          | 日期           | 日期字段（无时间）     |
+| DATETIME      | 日期时间       | 时间戳（精确到秒）     |
+| CHAR(n)       | 定长字符串     | 固定长度编码           |
+| VARCHAR(n)    | 变长字符串     | 名称、描述             |
+| STRING        | 变长字符串     | 大文本（无长度限制）   |
+| BITMAP        | 位图           | 精确去重（仅聚合模型） |
+| HLL           | HyperLogLog    | 近似去重（仅聚合模型） |
+| JSON          | JSON           | JSON数据存储           |
+*/
+
+-- ============================================================================
+-- 建表规范说明
+-- ============================================================================
+/*
+1. 模型选择
+   - Duplicate Key：保留原始明细，不做预聚合
+   - Aggregate Key：预聚合，相同 Key 的 Value 自动合并
+   - Unique Key：按主键去重，保留最新数据
+
+2. 分区设计
+   - 按时间字段 RANGE 分区（最常用）
+   - 支持动态分区自动管理
+   - 单分区数据量建议 1GB~10GB
+
+3. 分桶设计
+   - 使用高基数列做 HASH 分桶
+   - 分桶数 = BE节点数 × CPU核数（参考值）
+   - 单桶数据量建议 100MB~1GB
+
+4. 副本数
+   - 生产环境建议 3 副本
+   - 测试环境可设 1 副本
+
+5. Key 列选择
+   - Duplicate Key：高频过滤/排序字段
+   - Aggregate Key：聚合维度字段
+   - Unique Key：业务主键
+
+6. 注意事项
+   - Key 列必须在 Value 列之前
+   - 分区列必须是 Key 列
+   - 分桶列必须是 Key 列
+   - BITMAP/HLL 仅用于 Aggregate 模型的 Value 列
+*/

one-skill/smart-data-developer/references/sql/templates/doris/etl-template.sql

@@ -0,0 +1,128 @@
+-- =====================================================================
+-- @Name:             DORIS-D-SQL-{表名}-ETL
+-- @Version:          2.0
+-- @Desc:             Apache Doris ETL 数据处理模板（临时表链式处理）
+-- @TargetDatabase:   Apache Doris
+-- @说明:             统一规范：禁止 CTE，每步物化为临时表，先 DROP 再 CREATE
+-- =====================================================================
+
+-- ============================================================================
+-- Step01: 基础清洗与过滤
+-- ============================================================================
+-- 说明：从源表读取数据，进行基础过滤和清洗
+-- 输入：{源表名}
+-- 输出：${db_tmp_env}.tmp_xxx_01
+
+DROP TABLE IF EXISTS ${db_tmp_env}.tmp_xxx_01;
+CREATE TABLE ${db_tmp_env}.tmp_xxx_01 AS
+SELECT 
+    order_id,
+    user_id,
+    dept_id,
+    total_amount,
+    status,
+    order_date
+FROM db_name.source_table
+WHERE order_date = '${day_id}'
+  AND status IN ('completed', 'shipped')     -- 业务过滤
+  AND total_amount > 0                       -- 数据质量过滤
+  AND user_id IS NOT NULL;                   -- NULL过滤
+
+-- ============================================================================
+-- Step02: 多表关联与维度补全
+-- ============================================================================
+-- 说明：关联维度表，补全业务属性字段
+-- 输入：${db_tmp_env}.tmp_xxx_01, dim_department, dim_category
+-- 输出：${db_tmp_env}.tmp_xxx_02
+
+DROP TABLE IF EXISTS ${db_tmp_env}.tmp_xxx_02;
+CREATE TABLE ${db_tmp_env}.tmp_xxx_02 AS
+SELECT 
+    a.order_id,
+    a.user_id,
+    a.total_amount,
+    a.status,
+    b.dept_name,                             -- 维度补全：部门名称
+    c.category_name,                         -- 维度补全：类别名称
+    a.order_date
+FROM ${db_tmp_env}.tmp_xxx_01 a
+LEFT JOIN db_name.dim_department b 
+    ON a.dept_id = b.dept_id
+LEFT JOIN db_name.dim_category c 
+    ON a.category_id = c.category_id;
+
+-- ============================================================================
+-- Step03: 聚合计算与指标生成
+-- ============================================================================
+-- 说明：按业务维度聚合，计算统计指标
+-- 输入：${db_tmp_env}.tmp_xxx_02
+-- 输出：${db_tmp_env}.tmp_xxx_03
+
+DROP TABLE IF EXISTS ${db_tmp_env}.tmp_xxx_03;
+CREATE TABLE ${db_tmp_env}.tmp_xxx_03 AS
+SELECT 
+    order_date,
+    dept_name,
+    category_name,
+    COUNT(*) AS record_count,                -- 记录数
+    COUNT(DISTINCT user_id) AS unique_users, -- 去重用户数
+    SUM(total_amount) AS total_amount,       -- 总金额
+    AVG(total_amount) AS avg_amount,         -- 平均金额
+    MAX(total_amount) AS max_amount          -- 最大金额
+FROM ${db_tmp_env}.tmp_xxx_02
+GROUP BY order_date, dept_name, category_name;
+
+-- ============================================================================
+-- Step04: 最终输出写入目标表
+-- ============================================================================
+-- 说明：补全目标表标准字段，写入结果表
+-- 输入：${db_tmp_env}.tmp_xxx_03
+-- 输出：目标表
+
+INSERT INTO ${db_eda_env}.target_table
+SELECT 
+    -- 业务字段
+    dept_name,
+    category_name,
+    record_count,
+    unique_users,
+    total_amount,
+    avg_amount,
+    max_amount,
+    
+    -- 技术字段
+    NOW() AS etl_time,                       -- 数据加工时间
+    '${day_id}' AS stat_date                 -- 统计日期
+FROM ${db_tmp_env}.tmp_xxx_03;
+
+-- ============================================================================
+-- 关键规则说明
+-- ============================================================================
+/*
+1. 禁止使用 CTE (WITH 子句)
+   - 每个步骤必须物化为临时表
+   - 原因：便于调试、断点续跑、统一编码规范
+
+2. 先 DROP 再 CREATE
+   - 每个临时表创建前必须先 DROP TABLE IF EXISTS
+   - 原因：防止表已存在导致失败
+
+3. Doris 写入方式
+   - 默认使用 INSERT INTO
+   - Aggregate Key 表：自动合并相同 Key 的数据
+   - Unique Key 表：自动按主键去重，保留最新数据
+   - Doris 2.0+ 也支持 INSERT OVERWRITE
+
+4. 过滤条件前置
+   - 所有过滤在最早阶段应用
+   - 减少中间数据量
+
+5. 临时表命名规范
+   - 格式：tmp_{业务简称}_{步骤序号}
+   - 示例：tmp_order_stats_01, tmp_order_stats_02
+
+6. Doris 特有注意事项
+   - 不支持 LEFT SEMI JOIN / LEFT ANTI JOIN
+   - 日期函数用 MySQL 风格：DATE_FORMAT, DATE_ADD(INTERVAL)
+   - 不支持 collect_list/collect_set，用 GROUP_CONCAT 替代
+*/

one-skill/smart-data-developer/references/sql/templates/doris/insert-template.sql

@@ -0,0 +1,147 @@
+-- =====================================================================
+-- @Name:             DORIS-D-SQL-{表名}-INSERT
+-- @Version:          1.0
+-- @Desc:             Apache Doris 数据插入模板
+-- @TargetDatabase:   Apache Doris
+-- =====================================================================
+
+-- ============================================================================
+-- 场景1：INSERT INTO（追加写入）
+-- ============================================================================
+-- 适用：向 Doris 表追加数据，不会删除已有数据
+
+INSERT INTO db_name.target_table
+SELECT 
+    stat_date,
+    department,
+    region,
+    order_count,
+    total_amount
+FROM db_name.source_table
+WHERE stat_date = '${day_id}';
+
+-- ============================================================================
+-- 场景2：INSERT OVERWRITE（覆盖写入）
+-- ============================================================================
+-- 适用：覆盖目标表（或指定分区）的全部数据
+-- 注意：Doris 2.0+ 支持，且仅适用于 Partition 表
+
+-- 覆盖整表
+INSERT OVERWRITE db_name.target_table
+SELECT 
+    stat_date,
+    department,
+    region,
+    order_count,
+    total_amount
+FROM db_name.source_table;
+
+-- 覆盖指定分区（推荐）
+INSERT OVERWRITE db_name.target_table
+PARTITION(p202605)
+SELECT 
+    department,
+    region,
+    order_count,
+    total_amount
+FROM db_name.source_table
+WHERE stat_date >= '2026-05-01'
+  AND stat_date < '2026-06-01';
+
+-- ============================================================================
+-- 场景3：从查询结果写入（ETL 场景）
+-- ============================================================================
+
+-- 简单转换后写入
+INSERT INTO db_name.target_table
+SELECT 
+    order_date,
+    department,
+    COUNT(*) AS order_count,
+    COUNT(DISTINCT user_id) AS unique_users,
+    SUM(total_amount) AS total_amount,
+    AVG(total_amount) AS avg_amount
+FROM db_name.source_orders o
+LEFT JOIN db_name.dim_department d ON o.dept_id = d.dept_id
+WHERE o.order_date = '${day_id}'
+GROUP BY order_date, department;
+
+-- ============================================================================
+-- 场景4：批量 VALUES 写入
+-- ============================================================================
+
+INSERT INTO db_name.target_table (stat_date, department, amount)
+VALUES 
+    ('2026-05-01', '市场部', 10000.00),
+    ('2026-05-01', '技术部', 25000.00),
+    ('2026-05-01', '运营部', 18000.00);
+
+-- ============================================================================
+-- 场景5：Stream Load（数据导入）
+-- ============================================================================
+-- 适用：大批量数据导入（百万级以上）
+-- 注意：Stream Load 通过 HTTP 协议提交，不是 SQL 语法
+
+/*
+-- curl 命令示例
+curl --location-trusted -u user:password \
+    -H "label:load_order_20260501" \
+    -H "column_separator:," \
+    -H "columns:order_id,order_date,user_id,total_amount" \
+    -T data.csv \
+    http://fe_host:8030/api/db_name/orders/_stream_load
+*/
+
+-- ============================================================================
+-- 场景6：Broker Load（外部数据源导入）
+-- ============================================================================
+
+/*
+LOAD LABEL db_name.load_label_20260501
+(
+    DATA INFILE('hdfs://namenode:8020/path/to/data/*')
+    INTO TABLE target_table
+    COLUMNS TERMINATED BY ','
+    (stat_date, department, region, amount)
+    SET (amount = amount * 1.0)
+)
+WITH BROKER 'broker_name'
+(
+    'username' = 'hdfs_user',
+    'password' = 'hdfs_password'
+)
+PROPERTIES
+(
+    'timeout' = '3600',
+    'max_filter_ratio' = '0.01'
+);
+*/
+
+-- ============================================================================
+-- 关键规则说明
+-- ============================================================================
+/*
+1. INSERT INTO vs INSERT OVERWRITE
+   - INSERT INTO：追加数据，不删除已有数据
+   - INSERT OVERWRITE：覆盖数据（Doris 2.0+ 支持）
+   - 日常增量推荐 INSERT INTO，全量刷新推荐 INSERT OVERWRITE
+
+2. Doris 不使用临时表链式处理
+   - 与 Spark 不同，Doris 通常用单条 SQL 或 CTE 完成 ETL
+   - 直接 INSERT INTO ... SELECT ... 即可
+
+3. 字段顺序
+   - SELECT 字段顺序必须与目标表列定义顺序一致
+   - 或显式指定列名：INSERT INTO table (col1, col2) SELECT ...
+
+4. 数据导入方式选择
+   - 少量数据：INSERT INTO ... SELECT ... 或 INSERT INTO ... VALUES ...
+   - 大批量导入：Stream Load（HTTP PUT，最高性能）
+   - HDFS 导入：Broker Load
+   - 外部数据源：Routine Load（Kafka 等）
+
+5. 性能建议
+   - 批量写入优于逐条写入
+   - Stream Load 是最高性能的导入方式
+   - 建议攒批后一次性写入，避免频繁小批量导入
+*/

one-skill/smart-data-developer/references/sql/templates/doris/query-template.sql

@@ -0,0 +1,189 @@
+-- =====================================================================
+-- @Name:             DORIS-D-SQL-{表名}-QUERY
+-- @Version:          1.0
+-- @Desc:             Apache Doris 查询模板
+-- @TargetDatabase:   Apache Doris
+-- =====================================================================
+
+-- ============================================================================
+-- 1. 单表查询
+-- ============================================================================
+
+SELECT 
+    order_id,
+    user_name,
+    total_amount,
+    create_time
+FROM db_name.orders
+WHERE order_date = '${day_id}'
+  AND status = 'completed'
+ORDER BY total_amount DESC
+LIMIT 100;
+
+-- ============================================================================
+-- 2. JOIN 查询
+-- ============================================================================
+
+-- 两表 JOIN
+SELECT 
+    o.order_id,
+    o.total_amount,
+    u.user_name,
+    u.vip_level
+FROM db_name.orders o
+JOIN db_name.users u ON o.user_id = u.user_id
+WHERE o.order_date = '${day_id}'
+  AND o.status = 'completed';
+
+-- 多表 JOIN
+SELECT 
+    o.order_id,
+    u.user_name,
+    p.product_name,
+    oi.quantity,
+    oi.unit_price
+FROM db_name.orders o
+JOIN db_name.users u ON o.user_id = u.user_id
+JOIN db_name.order_items oi ON o.order_id = oi.order_id
+JOIN db_name.products p ON oi.product_id = p.product_id
+WHERE o.order_date BETWEEN '${start_date}' AND '${end_date}';
+
+-- ============================================================================
+-- 3. 聚合查询
+-- ============================================================================
+
+-- GROUP BY + HAVING
+SELECT 
+    department,
+    COUNT(*) AS order_count,
+    SUM(total_amount) AS total_amount,
+    AVG(total_amount) AS avg_amount
+FROM db_name.orders
+WHERE order_date = '${day_id}'
+GROUP BY department
+HAVING COUNT(*) >= 5
+ORDER BY total_amount DESC;
+
+-- 多字段分组 + 去重计数
+SELECT 
+    order_date,
+    region,
+    COUNT(*) AS order_count,
+    COUNT(DISTINCT user_id) AS unique_users,
+    SUM(total_amount) AS total_amount
+FROM db_name.orders
+WHERE order_date BETWEEN '${start_date}' AND '${end_date}'
+GROUP BY order_date, region;
+
+-- ============================================================================
+-- 4. 窗口函数
+-- ============================================================================
+
+-- ROW_NUMBER（分组取Top N）
+SELECT *
+FROM (
+    SELECT 
+        department,
+        user_name,
+        total_amount,
+        ROW_NUMBER() OVER (PARTITION BY department ORDER BY total_amount DESC) AS rn
+    FROM db_name.orders
+    WHERE order_date = '${day_id}'
+) t
+WHERE rn <= 3;
+
+-- 累计聚合
+SELECT 
+    order_date,
+    daily_amount,
+    SUM(daily_amount) OVER (ORDER BY order_date) AS cumulative_amount,
+    AVG(daily_amount) OVER (
+        ORDER BY order_date
+        ROWS BETWEEN 6 PRECEDING AND CURRENT ROW
+    ) AS moving_avg_7d
+FROM (
+    SELECT order_date, SUM(total_amount) AS daily_amount
+    FROM db_name.orders
+    GROUP BY order_date
+) t;
+
+-- LAG/LEAD（环比计算）
+SELECT 
+    order_date,
+    daily_amount,
+    LAG(daily_amount, 1) OVER (ORDER BY order_date) AS prev_amount,
+    daily_amount - LAG(daily_amount, 1) OVER (ORDER BY order_date) AS daily_change,
+    ROUND(
+        (daily_amount - LAG(daily_amount, 1) OVER (ORDER BY order_date)) 
+        / LAG(daily_amount, 1) OVER (ORDER BY order_date) * 100, 2
+    ) AS growth_rate_pct
+FROM (
+    SELECT order_date, SUM(total_amount) AS daily_amount
+    FROM db_name.orders
+    GROUP BY order_date
+) t;
+
+-- ============================================================================
+-- 5. 分页查询
+-- ============================================================================
+
+-- LIMIT OFFSET 分页（Doris 原生支持）
+SELECT 
+    order_id, user_name, total_amount
+FROM db_name.orders
+WHERE order_date = '${day_id}'
+ORDER BY order_id
+LIMIT 20 OFFSET 0;          -- 第1页，每页20条
+
+-- ============================================================================
+-- 6. 子查询
+-- ============================================================================
+
+-- IN 子查询
+SELECT *
+FROM db_name.orders
+WHERE user_id IN (
+    SELECT user_id FROM db_name.users WHERE vip_level >= 3
+)
+AND order_date = '${day_id}';
+
+-- EXISTS 子查询
+SELECT *
+FROM db_name.products p
+WHERE EXISTS (
+    SELECT 1 FROM db_name.inventory i 
+    WHERE i.product_id = p.product_id 
+      AND i.quantity > 0
+);
+
+-- ============================================================================
+-- 7. 条件聚合（CASE WHEN + 聚合）
+-- ============================================================================
+
+SELECT 
+    order_date,
+    COUNT(*) AS total_orders,
+    SUM(CASE WHEN status = 'completed' THEN 1 ELSE 0 END) AS completed_count,
+    SUM(CASE WHEN status = 'cancelled' THEN 1 ELSE 0 END) AS cancelled_count,
+    SUM(CASE WHEN status = 'pending' THEN 1 ELSE 0 END) AS pending_count,
+    SUM(CASE WHEN total_amount > 1000 THEN total_amount ELSE 0 END) AS high_value_amount
+FROM db_name.orders
+WHERE order_date = '${day_id}'
+GROUP BY order_date;
+
+-- ============================================================================
+-- 8. Bitmap 精确去重（Doris 特有）
+-- ============================================================================
+
+-- 使用 bitmap 做精确去重（需要在 Aggregate Key 模型中定义 BITMAP 类型列）
+-- 注意：bitmap 函数只能用于包含 BITMAP 类型列的表
+
+-- 精确去重计数（预计算场景，在 Aggregate Key 表中使用 BITMAP_UNION）
+-- 建表时 Value 列定义：user_id_bitmap BITMAP BITMAP_UNION
+-- 查询时：
+-- SELECT date, bitmap_union_count(user_id_bitmap) AS uv FROM table GROUP BY date;
+
+-- HLL 近似去重
+-- 建表时 Value 列定义：user_id_hll HLL HLL_UNION
+-- 查询时：
+-- SELECT date, hll_union_agg(user_id_hll) AS approx_uv FROM table GROUP BY date;