Advanced Search

regular expression for CEDICT

/ Published in: Java
Save to your folder(s)

Expand | Embed | Plain Text

Copy this code and paste it in your HTML 
  1. //http://cc-cedict.org/wiki/start
  2.  
  3.     Pattern line_pattern = Pattern.compile("([^\\s]+)\\s([^\\s]+)\\s(\\[.+\\])\\s(/.+/)");
  4.  
  5.     Matcher matcher = line_pattern.matcher(line);
  6.     boolean matchFound = matcher.find();
  7.     while(matchFound) {
  8.     System.out.println(matcher.start() + "-" + matcher.end());
  9.     for(int i = 0; i <= matcher.groupCount(); i++) {
  10.     String groupStr = matcher.group(i);
  11.     System.out.println(i + ":" + groupStr);
  12.     }
  13.     if(matcher.end() + 1 <= line.length()) {
  14.     matchFound = matcher.find(matcher.end());
  15.     }
  16.     else{
  17.     break;
  18.     }
  19.     }
  20.  
  21.     T字帳 T字帐 [T zi4 zhang4] /T-account (accounting)/
  22.     0-47
  23.     0:T字帳 T字帐 [T zi4 zhang4] /T-account (accounting)/
  24.     1:T字帳
  25.     2:T字帐
  26.     3:[T zi4 zhang4]
  27.     4:/T-account (accounting)/

Report this snippet


Comments

RSS Icon Subscribe to comments

You need to login to post a comment.