Last active
December 3, 2015 01:55
-
-
Save apivovarov/16ed9a703a821fd66259 to your computer and use it in GitHub Desktop.
CSV parser in Scala
This file contains 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
/* | |
* Licensed to the Apache Software Foundation (ASF) under one | |
* or more contributor license agreements. See the NOTICE file | |
* distributed with this work for additional information | |
* regarding copyright ownership. The ASF licenses this file | |
* to you under the Apache License, Version 2.0 (the | |
* "License"); you may not use this file except in compliance | |
* with the License. You may obtain a copy of the License at | |
* | |
* http://www.apache.org/licenses/LICENSE-2.0 | |
* | |
* Unless required by applicable law or agreed to in writing, software | |
* distributed under the License is distributed on an "AS IS" BASIS, | |
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |
* See the License for the specific language governing permissions and | |
* limitations under the License. | |
*/ | |
import scala.language.postfixOps | |
import scala.util.parsing.combinator.RegexParsers | |
// A CSV parser based on RFC4180 | |
// http://tools.ietf.org/html/rfc4180 | |
object CSV extends RegexParsers { | |
override val skipWhitespace = false // meaningful spaces in CSV | |
def COMMA = "," | |
def DQUOTE = "\"" | |
def DQUOTE2 = "\"\"" ^^ { case _ => "\"" } // combine 2 dquotes into 1 | |
def CRLF = "\r\n" | "\n" | |
def TXT = "[^\",\r\n]".r | |
def SPACES = "[ \t]+".r | |
def file: Parser[List[List[String]]] = repsep(record, CRLF) <~ (CRLF?) | |
def record: Parser[List[String]] = repsep(field, COMMA) | |
def field: Parser[String] = escaped|nonescaped | |
def escaped: Parser[String] = { | |
((SPACES?)~>DQUOTE~>((TXT|COMMA|CRLF|DQUOTE2)*)<~DQUOTE<~(SPACES?)) ^^ { | |
case ls => ls.mkString("") | |
} | |
} | |
def nonescaped: Parser[String] = (TXT*) ^^ { case ls => ls.mkString("") } | |
def parse(s: String): List[List[String]] = parseAll(file, s) match { | |
case Success(res, _) => res | |
case e => throw new Exception(e.toString) | |
} | |
def parseLine(s: String): List[String] = parse(s).head | |
def main(args: Array[String]) { | |
assert(CSV.parseLine( """"a",2,"b","c's'",5""") == List("a", "2", "b", "c's'", "5")) | |
assert(CSV.parseLine( """1997,Ford,E350,"Super, ""luxurious"" truck"""") == | |
List("1997", "Ford", "E350", """Super, "luxurious" truck""")) | |
assert(CSV.parseLine("") == List("")) | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment