5

我需要从文本中解析占位符，例如abc $$FOO$$ cba. 我用 Scala 的解析器组合器破解了一些东西，但我对这个解决方案并不满意。

特别是，我在正则表达式中使用了零宽度匹配器(?=(\$\$|\z))来停止解析文本并开始解析占位符。这听起来非常接近于在scala 邮件列表中讨论的恶作剧和色彩缤纷的恶作剧（这激发了这个问题的标题。）

所以，挑战：修复我的解析器在没有这个黑客的情况下工作。我希望看到从问题到您的解决方案的清晰进展，因此我可以替换随机组装组合器直到测试通过的策略。

import scala.util.parsing.combinator.RegexParsers

object PlaceholderParser extends RegexParsers {
  sealed abstract class Element
  case class Text(text: String) extends Element
  case class Placeholder(key: String) extends Element

  override def skipWhitespace = false

  def parseElements(text: String): List[Element] = parseAll(elements, text) match {
    case Success(es, _) => es
    case NoSuccess(msg, _) => error("Could not parse: [%s]. Error: %s".format(text, msg))
  }

  def parseElementsOpt(text: String): ParseResult[List[Element]] = parseAll(elements, text)

  lazy val elements: Parser[List[Element]] = rep(element)
  lazy val element: Parser[Element] = placeholder ||| text
  lazy val text: Parser[Text] = """(?ims).+?(?=(\$\$|\z))""".r ^^ Text.apply
  lazy val placeholder: Parser[Placeholder] = delimiter ~> """[\w. ]+""".r <~ delimiter ^^ Placeholder.apply
  lazy val delimiter: Parser[String] = literal("$$")
}


import org.junit.{Assert, Test}

class PlaceholderParserTest {
  @Test
  def parse1 = check("a quick brown $$FOX$$ jumped over the lazy $$DOG$$")(Text("a quick brown "), Placeholder("FOX"), Text(" jumped over the lazy "), Placeholder("DOG"))

  @Test
  def parse2 = check("a quick brown $$FOX$$!")(Text("a quick brown "), Placeholder("FOX"), Text("!"))

  @Test
  def parse3 = check("a quick brown $$FOX$$!\n!")(Text("a quick brown "), Placeholder("FOX"), Text("!\n!"))

  @Test
  def parse4 = check("a quick brown $$F.O X$$")(Text("a quick brown "), Placeholder("F.O X"))

  def check(text: String)(expected: Element*) = Assert.assertEquals(expected.toList, parseElements(text))
}
4

1 回答 1

2

我找到了另一种方法。不再有 regex hack，但代码有点长。它将整个字符串解析为单个字符或Placeholder对象的列表。然后该compact函数压缩列表（即，它将连续的字符串转换为Text对象并且不接触Placeholder对象）：

object PlaceholderParser extends RegexParsers {
  sealed abstract class Element
  case class Text(text: String) extends Element
  case class Placeholder(key: String) extends Element

  override def skipWhitespace = false

  def parseElements(text: String): List[Element] = parseAll(elements, text) match {
    case Success(es, _) => es
    case NoSuccess(msg, _) => error("Could not parse: [%s]. Error: %s".format(text, msg))
  }

  def parseElementsOpt(text: String): ParseResult[List[Element]] = parseAll(elements, text)

  def compact(l: List[Any]): List[Element] = {
    val builder = new StringBuilder()
    val r = l.foldLeft(List.empty[Element])((l, e) => e match {
      case s: String =>
        builder.append(s)
        l
      case p: Placeholder =>
        val t = if (builder.size > 0) {
          val k = l ++ List(Text(builder.toString))
          builder.clear
          k
        } else {
          l
        }
        t ++ List(p)
    })
    if (builder.size > 0) r ++ List(Text(builder.toString)) else r
  }

  lazy val elements: Parser[List[Element]] = (placeholder ||| text).+ ^^ compact
  lazy val text: Parser[String] = """(?ims).""".r
  lazy val placeholder: Parser[Placeholder] = delimiter ~> """[\w. ]+""".r <~ delimiter ^^ Placeholder.apply
  lazy val delimiter: Parser[String] = literal("$$")
}

这不是一个完美的解决方案，但也许你可以开始。

于 2010-07-30T16:21:12.850 回答