正则表达式划分CSV

《精通正则表达式》 第401页

    public static List splitCSV(String txt) {

        String reg = "\\G(?:^|,)(?:\"([^\"]*+(?:\"\"[^\"]*+)*+)\"|([^\",]*+))";
      // 即 \G(?:^|,)(?:"([^"]*+(?:""[^"]*+)*+)"|([^",]*+))

        Matcher matcherMain = Pattern.compile(reg).matcher("");
        Matcher matcherQuoto = Pattern.compile("\"\"").matcher("");

        matcherMain.reset(txt);
        System.out.println(matcherMain.groupCount());
        List strList = new ArrayList();
        while (matcherMain.find()) {
            String field;
            if (matcherMain.start(2) >= 0) {
                field = matcherMain.group(2);
            } else {
                field = matcherQuoto.reset(matcherMain.group(1)).replaceAll("\"");
            }
            strList.add(field);
        }
        return strList;
    }

  //测试
  public static void main(String[] args) {
        String txt = "The Thousand,10000, 2700 ,,\"10,000\",\"It's \"\"10 Grand\"\",baby\",10K ";
         //即 The Thousand,10000, 2700 ,,"10,000","It's ""10 Grand"",baby",10K 
        List splits = splitCSV(txt);
        for (String s : splits) {
            System.out.println(s);
        }
    }

打印:
2
The Thousand
10000
 2700 

10,000
It's "10 Grand",baby
10K 

posted @ 2014-05-28 08:47  lihui1625  阅读(787)  评论(0编辑  收藏  举报