Question

我正在开发一个sql解析器，允许我们的程序员创建一个类似mysql的查询，然后根据你的需要自动转换为mssql或mysql查询。这允许在mysql和mssql数据库之间进行灵活的转换。

我目前已经开始创建，但有一个问题。

如果我运行这样的查询：

SELECT * FROM `x`.`y` WHERE `y`.`b` = 'hello'

字符串被视为标识符llo

这是我的语法

grammar Query;

query
    : (select_stmt|update_stmt|delete_stmt|insert_stmt|upsert_stmt) ';'? EOF
    ;

select_stmt
    : select 'FROM' select_table_exp where? groupby? orderby? limit?
    ;

update_stmt
    : 'UPDATE' table_exp set where?
    ;

delete_stmt
    : 'DELETE FROM ' table_exp where    
    ;

insert_stmt
    : 'INSERT INTO' table_exp fields values
    ;

upsert_stmt
    : 'UPSERT' table_exp set ?  
    ;

values
    : 'VALUES (' valuelist ')'
    ;

valuelist
    : value (',' valuelist)?where
    ;

fields
    : '(' groupbylist ')'
    ;

set
    : 'SET' (setlist)
    ;

setlist
    : setters (',' setlist)?
    ;

select
    : 'SELECT' fieldlist
    ;

where
    : 'WHERE' where_stmt 
    ;

limit
    : 'LIMIT' (INT|param) (',' (INT|param))?
    ;

groupby
    : 'GROUP BY' groupbylist    
    ;

orderby
    : 'ORDER BY' orderbylist
    ;

select_table_exp
    : table_exp (join_stmt)?    
    | '(' select_stmt ')' as
    ;

table_exp
    : identifier as?
    ;

fieldlist
    : 
      (
          function as
        | (identifier as?)
        | identifier_prefix? '*' // solve the problem of the `ID`.* problem
        | '(' select_stmt ')' as
      ) (',' fieldlist)?
    ;

function
    : 'COUNT(' (identifier|'*') ')' 
    | 'MAX(' identifier ')'
    | 'MIN(' identifier ')'
    | 'AVERAGE(' identifier ')'
    | 'CONCAT(' groupbylist ')'
    | 'CONCAT_WS(' CHAR ',' groupbylist ')' 
    ;

orderbylist
    : identifier ('ASC'|'DESC')? (',' orderbylist)? 
    ;

groupbylist
    : identifier (',' groupbylist)? 
    ;

as
    : 'AS' (ID | '`' ID '`')    
    ;

join_stmt
    : leftjoin (join_stmt)?
    | rightjoin (join_stmt)?
    | join (join_stmt)?
    ;

leftjoin
    : 'LEFT JOIN' (table_exp|('(' select_stmt ')' as)) on_stmt
    ;

rightjoin
    : 'RIGHT JOIN' (table_exp|('(' select_stmt ')' as)) on_stmt
    ;

join
    : 'JOIN' (table_exp|('(' select_stmt ')' as)) on_stmt
    ;

on_stmt
    : 'ON' where_stmt
    ;

where_stmt
    : where_exp ((BOOLEANAND|BOOLEANOR) where_stmt)?
    ;

where_exp
    : where_exp_identifier
    | value (WHEREOPERATORS|EQUALITYOPERATOR) identifier
    | '(' select_stmt ')' (WHEREOPERATORS|EQUALITYOPERATOR) identifier
    ;

where_exp_identifier
    : identifier (WHEREOPERATORS|EQUALITYOPERATOR) where_exp_identifier_operator_right
    | identifier 'BETWEEN' (numeric_value BOOLEANAND numeric_value)
    | identifier 'LIKE' string_value
    ;

where_exp_identifier_operator_right
    : value
    | identifier
    | '(' select_stmt ')'
    ;

setters
    : identifier EQUALITYOPERATOR value
    | value EQUALITYOPERATOR identifier
    | identifier EQUALITYOPERATOR '(' select_stmt ')'
    | '(' select_stmt ')' EQUALITYOPERATOR identifier
    ;

identifier_value
    : value
    | identifier
    ;

value
    : string_value
    | numeric_value
    | param
    ;

string_value
    : STRING
    | CHAR
    ;

numeric_value
    : INT
    | FLOAT
    ;

identifier_prefix
    : ID '.'
    | '`' ID '`.'   
    ;

identifier
    : identifier_prefix? ID 
    | identifier_prefix? '`' ID '`'
    ;

param
    : '@' ID
    ;

BOOLEANAND
    : 'AND'
    ;

BOOLEANOR
    : 'OR'
    ;

EQUALITYOPERATOR
    : '='
    ;

WHEREOPERATORS
    : ('!='|'<>'|'<'|'>'|'<='|'>=')
    ;

ID  :   ('a'..'z'|'A'..'Z'|'_') ('a'..'z'|'A'..'Z'|'0'..'9'|'_')*
    ;

INT :   '0'..'9'+
    ;

FLOAT
    :   ('0'..'9')+ '.' ('0'..'9')* EXPONENT?
    |   '.' ('0'..'9')+ EXPONENT?
    |   ('0'..'9')+ EXPONENT
    ;

COMMENT
    :   '//' ~('\n'|'\r')* '\r'? '\n' {$channel=HIDDEN;}
    |   '/*' ( options {greedy=false;} : . )* '*/' {$channel=HIDDEN;}
    ;

WS  :   ( ' '
        | '\t'
        | '\r'
        | '\n'
        ) {$channel=HIDDEN;}
    ;

STRING
    :  '"' ( ESC_SEQ | ~('\\'|'"') )* '"'
    ;

CHAR:  '\'' ( ESC_SEQ | ~('\''|'\\') ) '\''
    ;

fragment
EXPONENT : ('e'|'E') ('+'|'-')? ('0'..'9')+ ;

fragment
HEX_DIGIT : ('0'..'9'|'a'..'f'|'A'..'F') ;

fragment
ESC_SEQ
    :   '\\' ('b'|'t'|'n'|'f'|'r'|'\"'|'\''|'\\')
    |   UNICODE_ESC
    |   OCTAL_ESC
    ;

fragment
OCTAL_ESC
    :   '\\' ('0'..'3') ('0'..'7') ('0'..'7')
    |   '\\' ('0'..'7') ('0'..'7')
    |   '\\' ('0'..'7')
    ;

fragment
UNICODE_ESC
    :   '\\' 'u' HEX_DIGIT HEX_DIGIT HEX_DIGIT HEX_DIGIT
    ;

我离ANTLR专家很远，所以经过3个小时摆弄我的语法试图让语法在那个位置接受正确的字符串我决定请你们帮忙。也许这里的一些蚂蚁大师可以帮我解决这个问题。

非常感谢

Answer 1

您的输入'hello'未被标记为字符串，因为您定义了一个由双引号括起来的字符串。语法中的char被单引号括起来：

STRING
    :  '"' ( ESC_SEQ | ~('\\'|'"') )* '"'
    ;

CHAR:  '\'' ( ESC_SEQ | ~('\''|'\\') ) '\''
    ;

这是错误的原因。

ANTLR字符串被视为标识符

1 个答案: