parsing - 提高 FParsec 解析器的可读性

Question

我有一个用 C# 编写的手写 CSS 解析器，它变得难以管理，并试图在 FParsec 中实现它以使其更易于维护。这是一个解析用正则表达式制作的 css 选择器元素的片段:

var tagRegex = @"(?<Tag>(?:[a-zA-Z][_\-0-9a-zA-Z]*|\*))";
var idRegex = @"(?:#(?<Id>[a-zA-Z][_\-0-9a-zA-Z]*))";
var classesRegex = @"(?<Classes>(?:\.[a-zA-Z][_\-0-9a-zA-Z]*)+)";
var pseudoClassRegex = @"(?::(?<PseudoClass>link|visited|hover|active|before|after|first-line|first-letter))";
var selectorRegex = new Regex("(?:(?:" + tagRegex + "?" + idRegex + ")|" +
                                 "(?:" + tagRegex + "?" + classesRegex + ")|" +
                                  tagRegex + ")" +
                               pseudoClassRegex + "?");

var m = selectorRegex.Match(str);

if (m.Length != str.Length) {
    cssParserTraceSwitch.WriteLine("Unrecognized selector: " + str);
    return null;
}

string tagName = m.Groups["Tag"].Value;

string pseudoClassString = m.Groups["PseudoClass"].Value;
CssPseudoClass pseudoClass;
if (pseudoClassString.IsEmpty()) {
    pseudoClass = CssPseudoClass.None;
} else {
    switch (pseudoClassString.ToLower()) {
        case "link":
            pseudoClass = CssPseudoClass.Link;
            break;
        case "visited":
            pseudoClass = CssPseudoClass.Visited;
            break;
        case "hover":
            pseudoClass = CssPseudoClass.Hover;
            break;
        case "active":
            pseudoClass = CssPseudoClass.Active;
            break;
        case "before":
            pseudoClass = CssPseudoClass.Before;
            break;
        case "after":
            pseudoClass = CssPseudoClass.After;
            break;
        case "first-line":
            pseudoClass = CssPseudoClass.FirstLine;
            break;
        case "first-letter":
            pseudoClass = CssPseudoClass.FirstLetter;
            break;
        default:
            cssParserTraceSwitch.WriteLine("Unrecognized selector: " + str);
            return null;
    }
}

string cssClassesString = m.Groups["Classes"].Value;
string[] cssClasses = cssClassesString.IsEmpty() ? EmptyArray<string>.Instance : cssClassesString.Substring(1).Split('.');
allCssClasses.AddRange(cssClasses);

return new CssSelectorElement(
    tagName.ToLower(),
    cssClasses,
    m.Groups["Id"].Value,
    pseudoClass);

我的第一次尝试得到了这个:

type CssPseudoClass =
    | None = 0
    | Link = 1
    | Visited = 2
    | Hover = 3
    | Active = 4
    | Before = 5
    | After = 6
    | FirstLine = 7
    | FirstLetter = 8

type CssSelectorElement = 
    { Tag : string
      Id : string
      Classes : string list    
      PseudoClass : CssPseudoClass } 
with
    static member Default = 
        { Tag = "";
          Id = "";
          Classes = [];
          PseudoClass = CssPseudoClass.None; }

open FParsec

let ws = spaces
let str = skipString
let strWithResult str result = skipString str >>. preturn result

let identifier =
    let isIdentifierFirstChar c = isLetter c || c = '-'
    let isIdentifierChar c = isLetter c || isDigit c || c = '_' || c = '-'    
    optional (str "-") >>. many1Satisfy2L isIdentifierFirstChar isIdentifierChar "identifier"

let stringFromOptional strOption =
    match strOption with
    | Some(str) -> str
    | None -> ""

let pseudoClassFromOptional pseudoClassOption =
    match pseudoClassOption with
    | Some(pseudoClassOption) -> pseudoClassOption
    | None -> CssPseudoClass.None

let parseCssSelectorElement =
    let tag = identifier <?> "tagName"
    let id = str "#" >>. identifier <?> "#id"
    let classes = many1 (str "." >>. identifier) <?> ".className"
    let parseCssPseudoClass =
        choiceL [ strWithResult "link" CssPseudoClass.Link;
                  strWithResult "visited" CssPseudoClass.Visited;
                  strWithResult "hover" CssPseudoClass.Hover;
                  strWithResult "active" CssPseudoClass.Active;
                  strWithResult "before" CssPseudoClass.Before;
                  strWithResult "after" CssPseudoClass.After;
                  strWithResult "first-line" CssPseudoClass.FirstLine;
                  strWithResult "first-letter" CssPseudoClass.FirstLetter]
                 "pseudo-class"    
    // (tag?id|tag?classes|tag)pseudoClass?
    pipe2 ((pipe2 (opt tag) 
                  id
                  (fun tag id -> 
                      { CssSelectorElement.Default with 
                          Tag = stringFromOptional tag;
                          Id = id })) |> attempt
           <|>
           (pipe2 (opt tag) 
                  classes
                  (fun tag classes -> 
                      { CssSelectorElement.Default with 
                          Tag = stringFromOptional tag;
                          Classes = classes })) |> attempt
           <|>
           (tag |>> (fun tag -> { CssSelectorElement.Default with Tag = tag })))
           (opt (str ":" >>. parseCssPseudoClass) |> attempt)
           (fun selectorElem pseudoClass -> { selectorElem with PseudoClass = pseudoClassFromOptional pseudoClass })

但我不太喜欢它的形成方式。我期待提出一些更容易理解的东西，但是解析 (tag?id|tag?classes|tag)pseudoClass 的部分？有几个 pipe2 和尝试真的很糟糕。

有没有在 FParsec 方面有更多经验的人来指导我如何更好地完成此任务？我正在考虑尝试 FSLex/Yacc 或 Boost.Spirit 而不是 FParsec 看看我是否可以用它们提出更好的代码

Answer 1

您可以将该复杂解析器的某些部分提取为变量，例如:

let tagid = 
    pipe2 (opt tag) 
      id
      (fun tag id -> 
          { CssSelectorElement.Default with 
              Tag = stringFromOptional tag
              Id = id })

您也可以尝试使用 applicative interface ，我个人觉得比 pipe2 更容易使用和思考:

let tagid =
    (fun tag id -> 
          { CssSelectorElement.Default with 
              Tag = stringFromOptional tag
              Id = id })
    <!> opt tag
    <*> id