基于Druid的HiveSQL血缘解析

String sql_format=formatMysql(sql_4);
final DbType dbType = JdbcConstants.HIVE;
// SQLStatement就是AST
List stmtList = SQLUtils.parseStatements(sql_4, dbType);
System.out.println(stmtList);

package com.alibaba.druid.sql.ast.expr;
 
// SQLName是一种的SQLExpr的Expr，包括SQLIdentifierExpr、SQLPropertyExpr等
public interface SQLName extends SQLExpr {}
 
// 例如 ID = 3 这里的ID是一个SQLIdentifierExpr
class SQLIdentifierExpr implements SQLExpr, SQLName {
    String name;
} 
 
// 例如 A.ID = 3 这里的A.ID是一个SQLPropertyExpr
class SQLPropertyExpr implements SQLExpr, SQLName {
    SQLExpr owner;
    String name;
} 
 
// 例如 ID = 3 这是一个SQLBinaryOpExpr
// left是ID (SQLIdentifierExpr)
// right是3 (SQLIntegerExpr)
class SQLBinaryOpExpr implements SQLExpr {
    SQLExpr left;
    SQLExpr right;
    SQLBinaryOperator operator;
}
 
// 例如 select * from where id = ?，这里的?是一个SQLVariantRefExpr，name是'?'
class SQLVariantRefExpr extends SQLExprImpl { 
    String name;
}
 
// 例如 ID = 3 这里的3是一个SQLIntegerExpr
public class SQLIntegerExpr extends SQLNumericLiteralExpr implements SQLValuableExpr { 
    Number number;
 
    // 所有实现了SQLValuableExpr接口的SQLExpr都可以直接调用这个方法求值
    @Override
    public Object getValue() {
        return this.number;
    }
}
 
// 例如 NAME = 'jobs' 这里的'jobs'是一个SQLCharExpr
public class SQLCharExpr extends SQLTextLiteralExpr implements SQLValuableExpr{
    String text;
}

package com.alibaba.druid.sql.ast.statement;
 
class SQLSelectStatement implements SQLStatement {
    SQLSelect select;
}
class SQLUpdateStatement implements SQLStatement {
    SQLExprTableSource tableSource;
     List items;
     SQLExpr where;
}
class SQLDeleteStatement implements SQLStatement {
    SQLTableSource tableSource; 
    SQLExpr where;
}
class SQLInsertStatement implements SQLStatement {
    SQLExprTableSource tableSource;
    List columns;
    SQLSelect query;
}

CREATE EXTERNAL TABLE dwd_database.table_name( 
id                BIGINT,
user_id           STRING,
gmt_modified      TIMESTAMP,
gmt_create        TIMESTAMP,
pending_reward    INT,
description       STRING
)
PARTITIONED BY ( 
pt STRING 
)
row format delimited fields terminated by '\t'
STORED AS TEXTFILE
location 'hdfs://nameservice1/user/hive/warehouse/dwd_database.db/table_name';

create table table_name
        as   
       select *  from t_table_name where pt='20210829';

INSERT OVERWRITE TABLE tablename [PARTITION (partcol1=val1, partcol2=val2 ...)] select_statement1 FROM from_statement;
INSERT INTO TABLE tablename [PARTITION (partcol1=val1, partcol2=val2 ...)] select_statement1 FROM from_statement;
INSERT INTO TABLE tablename [PARTITION (partcol1=val1, partcol2=val2 ...)](z, y) select_statement1 FROM from_statement;

FROM from_statement
INSERT OVERWRITE TABLE tablename [PARTITION (partcol1=val1, partcol2=val2 ...)] select_statement1
[INSERT OVERWRITE TABLE tablename2 [PARTITION ...] select_statement2]
[INSERT INTO TABLE tablename2 [PARTITION ...] select_statement2];