SQLBot/backend/templates/sql_examples/Hive.yaml

template:
  quot_rule: |
    <rule>
      必须对数据库名、表名、字段名、别名外层加反引号（`）。
      <note>
        1. 点号（.）不能包含在引号内，必须写成 `database`.`table`
        2. 即使标识符不含特殊字符或非关键字，也需强制加反引号
        3. 在多表关联（JOIN）/ 多子查询的 SQL 中，只要多个表 / 子查询存在 同名字段，所有引用该字段的位置，必须显式指定 表别名
      </note>
    </rule>

  limit_rule: |
    <rule>
      当需要限制行数时，必须使用标准的LIMIT语法
    </rule>

  other_rule: |
    <rule>必须为每个表生成别名（不加AS）</rule>
    {multi_table_condition}
    <rule>禁止使用星号(*)，必须明确字段名</rule>
    <rule>中文/特殊字符字段需保留原名并添加英文别名</rule>
    <rule>不能用 + 拼接字符串，字符串必须使用单引号</rule>
    <rule>分组非常严格：SELECT 里的字段必须出现在 GROUP BY 里，或者是聚合函数</rule>
    <rule>函数字段必须加别名</rule>
    <rule>百分比字段保留两位小数并以%结尾</rule>
    <rule>WHERE 条件中不能使用 >、<、>=、<= 等比较运算符，必须使用 =</rule>
    <rule>HIVE 中没有 NOT IN 操作符，必须使用 LEFT JOIN 或 EXISTS 替代</rule>
    <rule>判空使用 NVL()函数</rule>
    <rule>避免与数据库关键字冲突</rule>

  basic_example: |
    <basic-examples>
      <intro>
        📌 以下示例严格遵循<Rules>中的 Hive 规范，展示符合要求的 SQL 写法与典型错误案例。
        ⚠️ 注意：示例中的表名、字段名均为演示虚构，实际使用时需替换为用户提供的真实标识符。
        🔍 重点观察：
          1. 反引号包裹所有数据库对象的规范用法
          2. 中英别名/百分比/函数等特殊字段的处理
          3. 关键字冲突的规避方式
      </intro>
      <example>
        <input>查询 ods.orders 表的前100条订单（含中文字段和百分比）</input>
        <output-bad>
          SELECT * FROM ods.orders LIMIT 100  -- 错误：未加引号、使用星号
          SELECT `订单ID`, `金额` FROM `ods`.`orders` `t1` LIMIT 100  -- 错误：缺少英文别名
          SELECT COUNT(`订单ID`) FROM `ods`.`orders` `t1`  -- 错误：函数未加别名
        </output-bad>
        <output-good>
          SELECT
            `t1`.`订单ID` AS `order_id`,
            `t1`.`金额` AS `amount`,
            COUNT(`t1`.`订单ID`) AS `total_orders`,
            CONCAT(CAST(ROUND(`t1`.`折扣率` * 100, 2) AS STRING), '%') AS `discount_percent`
          FROM `ods`.`orders` `t1`
          LIMIT 100
        </output-good>
      </example>

      <example>
        <input>统计 dim.users（含关键字字段user）的活跃占比</input>
        <output-bad>
          SELECT user, status FROM dim.users  -- 错误：未处理关键字和引号
          SELECT `user`, ROUND(active_ratio) FROM `dim`.`users`  -- 错误：百分比格式错误
        </output-bad>
        <output-good>
          SELECT
            `u`.`user` AS `username`,
            CONCAT(CAST(ROUND(`u`.`active_ratio` * 100, 2) AS STRING), '%') AS `active_percent`
          FROM `dim`.`users` `u`
          WHERE `u`.`status` = 1
        </output-good>
      </example>
    </basic-examples>

  example_engine: Apache Hive 2.X
  example_answer_1: |
    {"success":true,"sql":"SELECT `country` AS `country_name`, `continent` AS `continent_name`, `year` AS `year`, `gdp` AS `gdp` FROM `Sample_Database`.`sample_country_gdp` ORDER BY `country`, `year`","tables":["sample_country_gdp"],"chart-type":"line"}
  example_answer_1_with_limit: |
    {"success":true,"sql":"SELECT `country` AS `country_name`, `continent` AS `continent_name`, `year` AS `year`, `gdp` AS `gdp` FROM `Sample_Database`.`sample_country_gdp` ORDER BY `country`, `year` LIMIT 1000","tables":["sample_country_gdp"],"chart-type":"line"}
  example_answer_2: |
    {"success":true,"sql":"SELECT `country` AS `country_name`, `gdp` AS `gdp` FROM `Sample_Database`.`sample_country_gdp` WHERE `year` = '2024' ORDER BY `gdp` DESC","tables":["sample_country_gdp"],"chart-type":"pie"}
  example_answer_2_with_limit: |
    {"success":true,"sql":"SELECT `country` AS `country_name`, `gdp` AS `gdp` FROM `Sample_Database`.`sample_country_gdp` WHERE `year` = '2024' ORDER BY `gdp` DESC LIMIT 1000","tables":["sample_country_gdp"],"chart-type":"pie"}
  example_answer_3: |
    {"success":true,"sql":"SELECT `country` AS `country_name`, `gdp` AS `gdp` FROM `Sample_Database`.`sample_country_gdp` WHERE `year` = '2025' AND `country` = '中国'","tables":["sample_country_gdp"],"chart-type":"table"}
  example_answer_3_with_limit: |
    {"success":true,"sql":"SELECT `country` AS `country_name`, `gdp` AS `gdp` FROM `Sample_Database`.`sample_country_gdp` WHERE `year` = '2025' AND `country` = '中国' LIMIT 1000","tables":["sample_country_gdp"],"chart-type":"table"}