java CEDICT的正则表达式

[java]代码库

//http://cc-cedict.org/wiki/start

    Pattern line_pattern = Pattern.compile("([^\\s]+)\\s([^\\s]+)\\s(\\[.+\\])\\s(/.+/)");

    Matcher matcher = line_pattern.matcher(line);
    boolean matchFound = matcher.find();
    while(matchFound) {
    System.out.println(matcher.start() + "-" + matcher.end());
    for(int i = 0; i <= matcher.groupCount(); i++) {
    String groupStr = matcher.group(i);
    System.out.println(i + ":" + groupStr);
    }
    if(matcher.end() + 1 <= line.length()) {
    matchFound = matcher.find(matcher.end());
    }
    else{
    break;
    }
    }

    T字帳 T字帐 [T zi4 zhang4] /T-account (accounting)/
    0-47
    0:T字帳 T字帐 [T zi4 zhang4] /T-account (accounting)/
    1:T字帳
    2:T字帐
    3:[T zi4 zhang4]
    4:/T-account (accounting)/