Add one-skill

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

@@ -0,0 +1,211 @@
+-- =====================================================================
+-- @Name:             KUDU-D-SQL-{表名}-CREATE
+-- @Version:          1.0
+-- @Desc:             Kudu (via Impala) 建表模板
+-- @TargetDatabase:   Apache Kudu (via Impala)
+-- @说明:             Kudu 通过 Impala 访问，使用 Impala DDL 操作 Kudu 表
+-- =====================================================================
+
+-- ============================================================================
+-- 场景1：基础表创建（Hash 分区）
+-- ============================================================================
+-- 适用：按主键 Hash 分布数据，写入和点查性能好
+
+CREATE TABLE IF NOT EXISTS db_name.kudu_basic (
+    -- 主键列（Kudu 表必须有主键）
+    id              BIGINT          NOT NULL COMMENT '主键ID',
+    
+    -- 业务字段
+    name            STRING          COMMENT '名称',
+    category        STRING          COMMENT '类别',
+    amount          DECIMAL(18,2)   COMMENT '金额',
+    status          STRING          COMMENT '状态',
+    created_at      TIMESTAMP       COMMENT '创建时间',
+    updated_at      TIMESTAMP       COMMENT '更新时间'
+)
+PRIMARY KEY (id)
+PARTITION BY HASH(id) PARTITIONS 8
+STORED AS KUDU
+TBLPROPERTIES (
+    'kudu.num_tablet_replicas' = '3'
+);
+
+-- ============================================================================
+-- 场景2：Hash + Range 组合分区
+-- ============================================================================
+-- 适用：按时间范围 + Hash 组合，兼顾范围查询和写入性能
+
+CREATE TABLE IF NOT EXISTS db_name.kudu_range_hash (
+    -- 主键列（必须包含分区列）
+    id              BIGINT          NOT NULL COMMENT '主键ID',
+    stat_date       STRING          NOT NULL COMMENT '统计日期 yyyy-MM-dd',
+    
+    -- 业务字段
+    department      STRING          COMMENT '部门',
+    metric_name     STRING          COMMENT '指标名称',
+    metric_value    DECIMAL(18,2)   COMMENT '指标值',
+    etl_time        TIMESTAMP       COMMENT '加工时间'
+)
+PRIMARY KEY (id, stat_date)
+PARTITION BY 
+    HASH(id) PARTITIONS 4,
+    RANGE(stat_date) (
+        PARTITION '2026-01-01' <= VALUES < '2026-02-01',
+        PARTITION '2026-02-01' <= VALUES < '2026-03-01',
+        PARTITION '2026-03-01' <= VALUES < '2026-04-01',
+        PARTITION '2026-04-01' <= VALUES < '2026-05-01',
+        PARTITION '2026-05-01' <= VALUES < '2026-06-01'
+    )
+STORED AS KUDU
+TBLPROPERTIES (
+    'kudu.num_tablet_replicas' = '3',
+    'kudu.compression' = 'LZ4'
+);
+
+-- ============================================================================
+-- 场景3：多列主键
+-- ============================================================================
+
+CREATE TABLE IF NOT EXISTS db_name.kudu_composite_pk (
+    user_id         BIGINT          NOT NULL COMMENT '用户ID',
+    order_date      STRING          NOT NULL COMMENT '订单日期',
+    order_seq       INT             NOT NULL COMMENT '当日订单序号',
+    
+    user_name       STRING          COMMENT '用户姓名',
+    product_name    STRING          COMMENT '商品名称',
+    quantity        INT             COMMENT '数量',
+    total_amount    DECIMAL(18,2)   COMMENT '总金额',
+    status          STRING          COMMENT '状态',
+    create_time     TIMESTAMP       COMMENT '创建时间'
+)
+PRIMARY KEY (user_id, order_date, order_seq)
+PARTITION BY 
+    HASH(user_id) PARTITIONS 8,
+    RANGE(order_date) (
+        PARTITION '2026-01-01' <= VALUES < '2026-02-01',
+        PARTITION '2026-02-01' <= VALUES < '2026-03-01',
+        PARTITION '2026-03-01' <= VALUES < '2026-04-01'
+    )
+STORED AS KUDU
+TBLPROPERTIES (
+    'kudu.num_tablet_replicas' = '3'
+);
+
+-- ============================================================================
+-- 场景4：纯 Range 分区
+-- ============================================================================
+-- 适用：按时间顺序写入，范围查询多
+
+CREATE TABLE IF NOT EXISTS db_name.kudu_range_only (
+    id              BIGINT          NOT NULL COMMENT '主键ID',
+    stat_date       STRING          NOT NULL COMMENT '统计日期',
+    metric_value    DECIMAL(18,2)   COMMENT '指标值',
+    dimension       STRING          COMMENT '维度',
+    etl_time        TIMESTAMP       COMMENT '加工时间'
+)
+PRIMARY KEY (id, stat_date)
+PARTITION BY RANGE(stat_date) (
+    PARTITION '2026-01-01' <= VALUES < '2026-04-01',
+    PARTITION '2026-04-01' <= VALUES < '2026-07-01',
+    PARTITION '2026-07-01' <= VALUES < '2026-10-01',
+    PARTITION '2026-10-01' <= VALUES < '2027-01-01'
+)
+STORED AS KUDU
+TBLPROPERTIES (
+    'kudu.num_tablet_replicas' = '3'
+);
+
+-- ============================================================================
+-- 场景5：外部表映射已有 Kudu 表
+-- ============================================================================
+
+CREATE EXTERNAL TABLE IF NOT EXISTS db_name.kudu_external
+STORED AS KUDU
+TBLPROPERTIES (
+    'kudu.master_addresses' = 'kudu-master-1:7051,kudu-master-2:7051,kudu-master-3:7051',
+    'kudu.table_name' = 'impala.db_name.existing_table'
+);
+
+-- ============================================================================
+-- 场景6：带压缩和副本配置
+-- ============================================================================
+
+CREATE TABLE IF NOT EXISTS db_name.kudu_with_props (
+    id              BIGINT          NOT NULL COMMENT '主键ID',
+    data_date       STRING          NOT NULL COMMENT '数据日期',
+    content         STRING          COMMENT '内容',
+    value           DOUBLE          COMMENT '数值'
+)
+PRIMARY KEY (id, data_date)
+PARTITION BY 
+    HASH(id) PARTITIONS 8,
+    RANGE(data_date) (
+        PARTITION '2026-01-01' <= VALUES < '2026-02-01',
+        PARTITION '2026-02-01' <= VALUES < '2026-03-01'
+    )
+STORED AS KUDU
+TBLPROPERTIES (
+    'kudu.num_tablet_replicas' = '3',
+    'kudu.compression' = 'LZ4',                        -- 压缩算法
+    'kudu.encryption' = 'false'                        -- 加密
+);
+
+-- ============================================================================
+-- 字段类型速查（Kudu 支持的类型）
+-- ============================================================================
+/*
+| 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               |
+| 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         |
+| STRING        | 变长字符串     | 名称、描述             |
+| VARCHAR(n)    | 变长字符串     | 限定长度字符串         |
+| CHAR(n)       | 定长字符串     | 固定长度编码           |
+| TIMESTAMP     | 时间戳         | 时间字段（微秒精度）   |
+| DATE          | 日期           | 日期字段               |
+| BINARY        | 二进制         | 二进制数据             |
+
+注意：Kudu 不支持 ARRAY, MAP, STRUCT 等复杂类型
+*/
+
+-- ============================================================================
+-- 建表规范说明
+-- ============================================================================
+/*
+1. 主键约束（Kudu 特有）
+   - 每张 Kudu 表必须有 PRIMARY KEY
+   - 主键列不能为 NULL（必须 NOT NULL）
+   - 主键值不可 UPDATE（只能删除后重新插入）
+   - 主键列必须包含在分区列中
+
+2. 分区策略
+   - Hash 分区：均匀分布，适合写入和点查
+   - Range 分区：按范围查询，适合时间序列
+   - Hash + Range 组合：兼顾两者优势（推荐）
+   - 分区数 = tablet 数量，影响并行度
+
+3. 分区设计建议
+   - Hash 分区数：建议 4 的倍数，参考数据量
+   - Range 分区：按时间维度，定期添加新分区
+   - 单个 tablet 建议 1GB~10GB
+
+4. 副本数
+   - 生产环境建议 3 副本（默认）
+   - Raft 协议保证一致性
+
+5. 压缩
+   - 推荐 LZ4（速度和压缩比平衡）
+   - 可选：SNAPPY, ZLIB, LZ4
+
+6. 与 Hive/Spark 表的区别
+   - Kudu 表支持 UPDATE 和 DELETE
+   - Kudu 表不支持 INSERT OVERWRITE
+   - Kudu 表不支持复杂类型（ARRAY, MAP, STRUCT）
+   - Kudu 表主键有约束，Hive/Spark 无约束
+*/

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

@@ -0,0 +1,146 @@
+-- =====================================================================
+-- @Name:             KUDU-D-SQL-{表名}-ETL
+-- @Version:          2.0
+-- @Desc:             Kudu (via Impala) ETL 数据处理模板（临时表链式处理）
+-- @TargetDatabase:   Apache Kudu (via Impala)
+-- @说明:             统一规范：禁止 CTE，每步物化为临时表，先 DROP 再 CREATE
+--                   最后一步用 UPSERT INTO 写入 Kudu 目标表
+-- =====================================================================
+
+-- ============================================================================
+-- 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 ${db_tmp_env}.tmp_xxx_01 AS
+SELECT 
+    order_id,
+    user_id,
+    dept_id,
+    product_id,
+    quantity,
+    amount,
+    status,
+    stat_date
+FROM db_name.source_table
+WHERE stat_date = '${day_id}'
+  AND status IN ('completed', 'shipped')     -- 业务过滤
+  AND 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：${db_tmp_env}.tmp_xxx_01, dim_department, dim_product
+-- 输出：${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.amount,
+    a.quantity,
+    b.dept_name,                             -- 维度补全：部门名称
+    c.category_name,                         -- 维度补全：类别名称
+    a.stat_date
+FROM ${db_tmp_env}.tmp_xxx_01 a
+LEFT JOIN db_name.dim_department b 
+    ON a.dept_id = b.dept_id
+LEFT JOIN db_name.dim_product c 
+    ON a.product_id = c.product_id;
+
+-- ============================================================================
+-- Step03: 聚合计算与指标生成
+-- ============================================================================
+-- 说明：按业务维度聚合，计算统计指标
+-- 输入：${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 
+    stat_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(amount) AS total_amount,             -- 总金额
+    SUM(quantity) AS total_quantity,         -- 总数量
+    AVG(amount) AS avg_amount,               -- 平均金额
+    MAX(amount) AS max_amount                -- 最大金额
+FROM ${db_tmp_env}.tmp_xxx_02
+GROUP BY stat_date, dept_name, category_name;
+
+-- ============================================================================
+-- Step04: 最终输出写入 Kudu 目标表
+-- ============================================================================
+-- 说明：使用 UPSERT 写入 Kudu 目标表
+-- 输入：${db_tmp_env}.tmp_xxx_03
+-- 输出：Kudu 目标表
+
+-- 方式1：UPSERT（推荐，主键存在则更新，不存在则插入）
+UPSERT INTO ${db_eda_env}.target_table
+SELECT 
+    -- 主键字段（Kudu 表必须有主键）
+    dept_name,
+    category_name,
+    stat_date,
+    
+    -- 指标字段
+    record_count,
+    unique_users,
+    total_amount,
+    total_quantity,
+    avg_amount,
+    max_amount,
+    
+    -- 技术字段
+    NOW() AS etl_time                        -- 数据加工时间
+FROM ${db_tmp_env}.tmp_xxx_03;
+
+-- 方式2：需要全量刷新时（先删后插）
+-- DELETE FROM ${db_eda_env}.target_table WHERE stat_date = '${day_id}';
+-- INSERT INTO ${db_eda_env}.target_table
+-- SELECT ... 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. Kudu 写入方式
+   - 推荐 UPSERT INTO（Kudu 核心优势）
+   - 主键存在 → 更新（整行替换）
+   - 主键不存在 → 插入新行
+   - 需要全量刷新 → 先 DELETE 再 INSERT
+
+4. Kudu 表约束
+   - 不支持 INSERT OVERWRITE（用 UPSERT 或 DELETE + INSERT 替代）
+   - 必须有 PRIMARY KEY
+   - 主键列不能为 NULL
+   - 支持 UPDATE 和 DELETE
+
+5. 过滤条件前置
+   - 所有过滤在最早阶段应用
+   - 减少中间数据量
+
+6. 临时表命名规范
+   - 格式：tmp_{业务简称}_{步骤序号}
+
+7. Kudu 特有注意事项
+   - CONCAT 只接受 2 个参数，多参数用 CONCAT_WS
+   - 不支持 collect_list/collect_set，用 GROUP_CONCAT 替代
+   - 近似去重用 NDV() 函数
+*/

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

@@ -0,0 +1,160 @@
+-- =====================================================================
+-- @Name:             KUDU-D-SQL-{表名}-INSERT
+-- @Version:          1.0
+-- @Desc:             Kudu (via Impala) 数据插入模板
+-- @TargetDatabase:   Apache Kudu (via Impala)
+-- @说明:             Kudu 表不支持 INSERT OVERWRITE，支持 INSERT INTO 和 UPSERT
+-- =====================================================================
+
+-- ============================================================================
+-- 场景1：INSERT INTO（追加写入）
+-- ============================================================================
+-- 适用：向 Kudu 表追加新数据
+
+INSERT INTO db_name.kudu_table
+SELECT 
+    id,
+    stat_date,
+    name,
+    department,
+    amount,
+    current_timestamp() AS etl_time
+FROM db_name.source_table
+WHERE stat_date = '${day_id}';
+
+-- ============================================================================
+-- 场景2：UPSERT INTO（更新插入，Kudu 特有）
+-- ============================================================================
+-- 适用：如果主键存在则更新，不存在则插入
+-- 这是 Kudu 的核心优势，其他 Hive/Spark 表不支持
+
+-- 基础 UPSERT
+UPSERT INTO db_name.kudu_table
+SELECT 
+    id,
+    stat_date,
+    name,
+    department,
+    amount,
+    current_timestamp() AS etl_time
+FROM db_name.staging_table
+WHERE stat_date = '${day_id}';
+
+-- 聚合后 UPSERT（增量更新指标表）
+UPSERT INTO db_name.kudu_metrics
+SELECT 
+    department,
+    '${day_id}' AS stat_date,
+    COUNT(*) AS order_count,
+    SUM(amount) AS total_amount,
+    current_timestamp() AS etl_time
+FROM db_name.incremental_orders
+WHERE stat_date = '${day_id}'
+GROUP BY department;
+
+-- ============================================================================
+-- 场景3：UPDATE（Kudu 表特有）
+-- ============================================================================
+-- 适用：修改已有数据
+-- 注意：主键列不能被 UPDATE
+
+-- 单条更新
+UPDATE db_name.kudu_table
+SET status = 'processed',
+    updated_at = current_timestamp()
+WHERE id = 12345;
+
+-- 批量条件更新
+UPDATE db_name.kudu_table
+SET status = 'expired',
+    updated_at = current_timestamp()
+WHERE stat_date < '2026-01-01'
+  AND status = 'active';
+
+-- 关联更新（用子查询）
+UPDATE db_name.kudu_table t
+SET t.department = d.new_dept_name
+FROM db_name.dept_mapping d
+WHERE t.department = d.old_dept_name;
+
+-- ============================================================================
+-- 场景4：DELETE（Kudu 表特有）
+-- ============================================================================
+-- 适用：删除数据
+-- 注意：Kudu 的 DELETE 比 Hive/Spark 方便得多
+
+-- 条件删除
+DELETE FROM db_name.kudu_table
+WHERE stat_date < '2026-01-01';
+
+-- 按主键删除
+DELETE FROM db_name.kudu_table
+WHERE id IN (1001, 1002, 1003);
+
+-- 关联删除（用子查询）
+DELETE FROM db_name.kudu_table
+WHERE user_id IN (
+    SELECT user_id FROM db_name.blacklist
+);
+
+-- ============================================================================
+-- 场景5：从查询结果写入
+-- ============================================================================
+
+-- 简单 ETL：清洗后写入
+INSERT INTO db_name.kudu_target
+SELECT 
+    id,
+    '${day_id}' AS stat_date,
+    name,
+    COALESCE(department, '未知') AS department,
+    amount,
+    current_timestamp() AS etl_time
+FROM db_name.raw_data
+WHERE stat_date = '${day_id}'
+  AND id IS NOT NULL
+  AND amount > 0;
+
+-- ============================================================================
+-- 场景6：批量 VALUES 写入
+-- ============================================================================
+
+INSERT INTO db_name.kudu_table (id, stat_date, name, amount)
+VALUES 
+    (1, '2026-05-01', '测试1', 100.00),
+    (2, '2026-05-01', '测试2', 200.00),
+    (3, '2026-05-01', '测试3', 300.00);
+
+-- ============================================================================
+-- 关键规则说明
+-- ============================================================================
+/*
+1. Kudu 表与 Hive/Spark 表的核心区别
+   - 支持 INSERT INTO：✅
+   - 支持 INSERT OVERWRITE：❌（不支持！）
+   - 支持 UPSERT：✅（Kudu 独有，核心能力）
+   - 支持 UPDATE：✅（Kudu 独有）
+   - 支持 DELETE：✅（Kudu 独有）
+
+2. UPSERT 是 Kudu 的核心优势
+   - 主键存在 → 更新（整行替换）
+   - 主键不存在 → 插入新行
+   - 适用于：增量更新、数据修正、指标回填
+
+3. INSERT INTO 注意事项
+   - 如果主键冲突会报错（不会自动去重）
+   - 需要确保写入数据的主键不重复，或使用 UPSERT
+
+4. UPDATE 限制
+   - 主键列不能被 UPDATE
+   - WHERE 条件建议包含主键或分区列（性能）
+
+5. DELETE 建议
+   - 删除大量数据时按分区范围删除
+   - 定期清理历史数据
+
+6. 性能建议
+   - 批量写入优于逐条写入
+   - UPSERT 比 DELETE + INSERT 更高效
+   - 利用主键做点查，避免全表扫描
+*/

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

@@ -0,0 +1,179 @@
+-- =====================================================================
+-- @Name:             KUDU-D-SQL-{表名}-QUERY
+-- @Version:          1.0
+-- @Desc:             Kudu (via Impala) 查询模板
+-- @TargetDatabase:   Apache Kudu (via Impala)
+-- =====================================================================
+
+-- ============================================================================
+-- 1. 单表查询
+-- ============================================================================
+
+SELECT 
+    id,
+    name,
+    amount,
+    created_at
+FROM db_name.kudu_table
+WHERE stat_date = '${day_id}'
+  AND status = 'active'
+ORDER BY created_at DESC
+LIMIT 1000;
+
+-- ============================================================================
+-- 2. JOIN 查询
+-- ============================================================================
+
+-- 两表 JOIN（Kudu 表 JOIN 非 Kudu 表也支持）
+SELECT 
+    k.id,
+    k.name,
+    k.amount,
+    d.dept_name
+FROM db_name.kudu_table k
+JOIN db_name.dim_department d ON k.dept_id = d.dept_id
+WHERE k.stat_date = '${day_id}';
+
+-- 多表 JOIN
+SELECT 
+    k.id,
+    k.user_name,
+    p.product_name,
+    k.quantity,
+    k.total_amount
+FROM db_name.kudu_orders k
+JOIN db_name.dim_users u ON k.user_id = u.user_id
+JOIN db_name.dim_products p ON k.product_id = p.product_id
+WHERE k.stat_date BETWEEN '${start_date}' AND '${end_date}';
+
+-- ============================================================================
+-- 3. 聚合查询
+-- ============================================================================
+
+SELECT 
+    department,
+    COUNT(*) AS record_count,
+    SUM(amount) AS total_amount,
+    AVG(amount) AS avg_amount,
+    MAX(amount) AS max_amount,
+    MIN(amount) AS min_amount
+FROM db_name.kudu_table
+WHERE stat_date = '${day_id}'
+GROUP BY department
+HAVING COUNT(*) >= 5
+ORDER BY total_amount DESC;
+
+-- 多字段分组 + 去重计数
+SELECT 
+    stat_date,
+    region,
+    COUNT(*) AS order_count,
+    COUNT(DISTINCT user_id) AS unique_users,
+    SUM(amount) AS total_amount
+FROM db_name.kudu_table
+WHERE stat_date BETWEEN '${start_date}' AND '${end_date}'
+GROUP BY stat_date, region;
+
+-- ============================================================================
+-- 4. 窗口函数
+-- ============================================================================
+
+-- ROW_NUMBER（分组取Top N）
+SELECT *
+FROM (
+    SELECT 
+        department,
+        user_name,
+        amount,
+        ROW_NUMBER() OVER (PARTITION BY department ORDER BY amount DESC) AS rn
+    FROM db_name.kudu_table
+    WHERE stat_date = '${day_id}'
+) t
+WHERE rn <= 3;
+
+-- 累计聚合
+SELECT 
+    stat_date,
+    daily_amount,
+    SUM(daily_amount) OVER (ORDER BY stat_date) AS cumulative_amount
+FROM (
+    SELECT stat_date, SUM(amount) AS daily_amount
+    FROM db_name.kudu_table
+    GROUP BY stat_date
+) t;
+
+-- LAG/LEAD（环比）
+SELECT 
+    stat_date,
+    daily_amount,
+    LAG(daily_amount, 1) OVER (ORDER BY stat_date) AS prev_amount,
+    daily_amount - LAG(daily_amount, 1) OVER (ORDER BY stat_date) AS daily_change
+FROM (
+    SELECT stat_date, SUM(amount) AS daily_amount
+    FROM db_name.kudu_table
+    GROUP BY stat_date
+) t;
+
+-- ============================================================================
+-- 5. 子查询
+-- ============================================================================
+
+-- IN 子查询
+SELECT *
+FROM db_name.kudu_table
+WHERE user_id IN (
+    SELECT user_id FROM db_name.vip_users WHERE vip_level >= 3
+)
+AND stat_date = '${day_id}';
+
+-- EXISTS 子查询
+SELECT *
+FROM db_name.kudu_products p
+WHERE EXISTS (
+    SELECT 1 FROM db_name.kudu_inventory i 
+    WHERE i.product_id = p.product_id 
+      AND i.quantity > 0
+);
+
+-- ============================================================================
+-- 6. 条件聚合（CASE WHEN + 聚合）
+-- ============================================================================
+
+SELECT 
+    stat_date,
+    COUNT(*) AS total_count,
+    SUM(CASE WHEN status = 'completed' THEN 1 ELSE 0 END) AS completed_count,
+    SUM(CASE WHEN status = 'cancelled' THEN 1 ELSE 0 END) AS cancelled_count,
+    SUM(CASE WHEN amount > 1000 THEN amount ELSE 0 END) AS high_value_amount
+FROM db_name.kudu_table
+WHERE stat_date = '${day_id}'
+GROUP BY stat_date;
+
+-- ============================================================================
+-- 7. LIMIT / OFFSET（分页）
+-- ============================================================================
+
+SELECT id, name, amount
+FROM db_name.kudu_table
+WHERE stat_date = '${day_id}'
+ORDER BY id
+LIMIT 20 OFFSET 0;
+
+-- ============================================================================
+-- 8. Kudu 特有：通过主键高效点查
+-- ============================================================================
+-- Kudu 主键查询可跳过扫描，直接定位 tablet
+
+-- 单主键点查
+SELECT * FROM db_name.kudu_table
+WHERE id = 12345;
+
+-- 复合主键点查
+SELECT * FROM db_name.kudu_composite_pk
+WHERE user_id = 1001
+  AND order_date = '2026-05-01'
+  AND order_seq = 1;
+
+-- 主键 IN 查询
+SELECT * FROM db_name.kudu_table
+WHERE id IN (1001, 1002, 1003, 1004, 1005);