我已经使用以下解析器来尝试解析BNF:
type Literal = Literal of string
type RuleName = RuleName of string
type Term = Literal of Literal
| RuleName of RuleName
type List = List of Term list
type Expression = Expression of List list
type Rule = Rule of RuleName * Expression
type BNF = Syntax of Rule list
let pBFN : Parser<BNF, unit> =
let pWS = skipMany (pchar ' ')
let pLineEnd = skipMany1 (pchar ' ' >>. newline)
let pLiteral =
let pL c = between (pchar c) (pchar c) (manySatisfy (isNoneOf ("\n" + string c)))
(pL '"') <|> (pL '\'') |>> Literal.Literal
let pRuleName = between (pchar '<') (pchar '>') (manySatisfy (isNoneOf "\n<>")) |>> RuleName.RuleName
let pTerm = (pLiteral |>> Term.Literal) <|> (pRuleName |>> Term.RuleName)
let pList = sepBy1 pTerm pWS |>> List.List
let pExpression = sepBy1 pList (pWS >>. (pchar '|') .>> pWS) |>> Expression.Expression
let pRule = pWS >>. pRuleName .>> pWS .>> pstring "::=" .>> pWS .>>. pExpression .>> pLineEnd |>> Rule.Rule
many1 pRule |>> BNF.Syntax
为了进行测试,我按照Wikipedia在BNF的BNF上运行它:
<syntax> ::= <rule> | <rule> <syntax>
<rule> ::= <opt-whitespace> "<" <rule-name> ">" <opt-whitespace> "::=" <opt-whitespace> <expression> <line-end>
<opt-whitespace> ::= " " <opt-whitespace> | ""
<expression> ::= <list> | <list> <opt-whitespace> "|" <opt-whitespace> <expression>
<line-end> ::= <opt-whitespace> <EOL> | <line-end> <line-end>
<list> ::= <term> | <term> <opt-whitespace> <list>
<term> ::= <literal> | "<" <rule-name> ">"
<literal> ::= '"' <text> '"' | "'" <text> "'"
但它始终因此错误而失败:
Error in Ln: 1 Col: 21
<syntax> ::= <rule> | <rule> <syntax>
^
Expecting: ' ', '"', '\'' or '<'
我做错了什么?
修改
我用来测试的功能:
let test =
let text = "<syntax> ::= <rule> | <rule> <syntax>
<rule> ::= <opt-whitespace> \"<\" <rule-name> \">\" <opt-whitespace> \"::=\" <opt-whitespace> <expression> <line-end>
<opt-whitespace> ::= \" \" <opt-whitespace> | \"\"
<expression> ::= <list> | <list> <opt-whitespace> \"|\" <opt-whitespace> <expression>
<line-end> ::= <opt-whitespace> <EOL> | <line-end> <line-end>
<list> ::= <term> | <term> <opt-whitespace> <list>
<term> ::= <literal> | \"<\" <rule-name> \">\"
<literal> ::= '\"' <text> '\"' | \"'\" <text> \"'\""
run pBNF text
答案 0 :(得分:4)
你的第一个问题是pList
:sepBy1
贪婪地抓住尾随空格,但是一旦它这样做,它就会期望跟随一个额外的术语而不是列表的结尾。解决此问题的最简单方法是使用sepEndBy1
代替。
这将暴露您的下一个问题:pEndLine
没有忠实地实现,因为您总是在寻找一个空格后面跟一个换行符,当您应该寻找任意数量的空格时(也就是说,你想要内部pWS >>. newline
,而不是pchar ' ' >>. newline
)。
最后,请注意,您的定义要求每个规则以换行符结束,因此您将无法按照给定的方式解析字符串(您需要在末尾附加一个空行)。相反,您可能希望将newline
从pRule
的定义中拉出来,并将主解析器定义为sepBy1 pRule pLineEnd |>> BNF.Syntax
。