Created
July 4, 2012 02:14
-
-
Save fbettag/3044807 to your computer and use it in GitHub Desktop.
Scala CSV Parser returning List[Map[String, String]]
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| // Original Code from http://stackoverflow.com/questions/5063022/use-scala-parser-combinator-to-parse-csv-files | |
| import scala.util.parsing.combinator._ | |
| class CSV(COMMA: String = ",") extends RegexParsers { | |
| override protected val whiteSpace = """[ \t]""".r | |
| def DQUOTE = "\"" | |
| def DQUOTE2 = "\"\"" ^^ { case _ => "\"" } | |
| def CR = "\r" | |
| def LF = "\n" | |
| def CRLF = "\r\n" | |
| def TXT = "[^\"%s\r\n]".format(COMMA).r | |
| def file: Parser[List[List[String]]] = repsep(record, CRLF) <~ opt(CRLF) | |
| def record: Parser[List[String]] = rep1sep(field, COMMA) | |
| def field: Parser[String] = (escaped|nonescaped) | |
| def escaped: Parser[String] = (DQUOTE~>((TXT|COMMA|CR|LF|DQUOTE2)*)<~DQUOTE) ^^ { case ls => ls.mkString("")} | |
| def nonescaped: Parser[String] = (TXT*) ^^ { case ls => ls.mkString("") } | |
| def parse(i: scala.io.BufferedSource): List[Map[String, String]] = parse(i.getLines.mkString("\r\n")) | |
| def parse(s: String): List[Map[String, String]] = parseAll(file, s) match { | |
| case Success(alllines, _) => | |
| val head = alllines.head | |
| alllines.drop(1) map { line => | |
| var theMap = Map[String, String]() | |
| head.zipWithIndex.map { e => | |
| val fieldName = e._1.replaceAll("\\s+", "") | |
| if (fieldName != "") theMap = theMap ++ Map(fieldName -> line(e._2)) | |
| } | |
| theMap | |
| } | |
| case _ => List[Map[String, String]]() | |
| } | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment