Not logged in.  Login/Logout/Register | List snippets | | Create snippet | Upload image | Upload data

63
LINES

< > BotCompany Repo | #1004582 - javaTokC - codeTokensOnly+javaTok

JavaX fragment (include)

static L<S> javaTokC(S s) {
  if (s == null) null;
  int l = s.length();
  new ArrayList<S> tok;
  
  int i = 0;
  while (i < l) {
    int j = i;
    char c, d;
    
    // scan for whitespace
    while (j < l) {
      c = s.charAt(j);
      d = j+1 >= l ? '\0' : s.charAt(j+1);
      if (c == ' ' || c == '\t' || c == '\r' || c == '\n')
        ++j;
      else if (c == '/' && d == '*') {
        do ++j; while (j < l && !s.substring(j, Math.min(j+2, l)).equals("*/"));
        j = Math.min(j+2, l);
      } else if (c == '/' && d == '/') {
        do ++j; while (j < l && "\r\n".indexOf(s.charAt(j)) < 0);
      } else
        break;
    }
    
    i = j;
    if (i >= l) break;
    c = s.charAt(i);
    d = i+1 >= l ? '\0' : s.charAt(i+1);

    // scan for non-whitespace
    if (c == '\'' || c == '"') {
      char opener = c;
      ++j;
      while (j < l) {
        if (s.charAt(j) == opener || s.charAt(j) == '\n') { // end at \n to not propagate unclosed string literal errors
          ++j;
          break;
        } else if (s.charAt(j) == '\\' && j+1 < l)
          j += 2;
        else
          ++j;
      }
    } else if (Character.isJavaIdentifierStart(c))
      do ++j; while (j < l && (Character.isJavaIdentifierPart(s.charAt(j)) || "'".indexOf(s.charAt(j)) >= 0)); // for stuff like "don't"
    else if (Character.isDigit(c)) {
      do ++j; while (j < l && Character.isDigit(s.charAt(j)));
      if (j < l && s.charAt(j) == 'L') ++j; // Long constants like 1L
    } else if (c == '[' && d == '[') {
      do ++j; while (j+1 < l && !s.substring(j, j+2).equals("]]"));
      j = Math.min(j+2, l);
    } else if (c == '[' && d == '=' && i+2 < l && s.charAt(i+2) == '[') {
      do ++j; while (j+2 < l && !s.substring(j, j+3).equals("]=]"));
      j = Math.min(j+3, l);
    } else
      ++j;
      
    tok.add(javaTok_substringC(s, i, j));
    i = j;
  }
  
  return tok;
}

download  show line numbers  debug dex   

Travelled to 11 computer(s): aoiabmzegqzx, cbybwowwnfue, cfunsshuasjs, ddnzoavkxhuk, gwrvuhgaqvyk, ishqpsrjomds, lpdgvwnxivlt, mqqgnosmbjvj, tslmcundralx, tvejysmllsmz, whxojlpjdney

No comments. add comment

Snippet ID: #1004582
Snippet name: javaTokC - codeTokensOnly+javaTok
Eternal ID of this version: #1004582/5
Text MD5: 45076a1d00d1ecc2a47a2ecd0aa21dc2
Author: stefan
Category: javax / parsing
Type: JavaX fragment (include)
Public (visible to everyone): Yes
Archived (hidden from active list): No
Created/modified: 2017-11-05 04:45:17
Source code size: 1952 bytes / 63 lines
Pitched / IR pitched: No / No
Views / Downloads: 382 / 568
Version history: 4 change(s)
Referenced in: [show references]

Formerly at http://tinybrain.de/1004582 & http://1004582.tinybrain.de