解析器如何用于解析跨越多行的记录?我需要解析树数据(并最终将其转换为树数据结构)。我在下面的代码中遇到了一个难以跟踪的解析错误,但不清楚这是否是 Scala 解析器的最佳方法。问题实际上更多是关于解决问题的方法,而不是调试现有代码。
EBNF-ish 语法是:
SP = " "
CRLF = "\r\n"
level = "0" | "1" | "2" | "3"
varName = {alphanum}
varValue = {alphnum}
recordBegin = "0", varName
recordItem = level, varName, [varValue]
record = recordBegin, {recordItem}
file = {record}
尝试实现和测试语法:
import util.parsing.combinator._
val input = """0 fruit
1 id 2
1 name apple
2 type red
3 size large
3 origin Texas, US
2 date 2 aug 2011
0 fruit
1 id 3
1 name apple
2 type green
3 size small
3 origin Florida, US
2 date 3 Aug 2011"""
object TreeParser extends JavaTokenParsers {
override val skipWhitespace = false
def CRLF = "\r\n" | "\n"
def BOF = "\\A".r
def EOF = "\\Z".r
def TXT = "[^\r\n]*".r
def TXTNOSP = "[^ \r\n]*".r
def SP = "\\s".r
def level: Parser[Int] = "[0-3]{1}".r ^^ {v => v.toInt}
def varName: Parser[String] = SP ~> TXTNOSP
def varValue: Parser[String] = SP ~> TXT
def recordBegin: Parser[Any] = "0" ~ SP ~ varName ~ CRLF
def recordItem: Parser[(Int,String,String)] = level ~ varValue ~ opt(varValue) <~ CRLF ^^
{case l ~ f ~ v => (l,f,v.map(_+"").getOrElse(""))}
def record: Parser[List[(Int,String,String)]] = recordBegin ~> rep(recordItem)
def file: Parser[List[List[(Int,String,String)]]] = rep(record) <~ EOF
def parse(input: String) = parseAll(file, input)
}
val result = TreeParser.parse(input).get
result.foreach(println)