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

62
LINES

< > BotCompany Repo | #1025691 // javaTok_noMLS - javaTok without multi-line-strings (for unstructure)

JavaX fragment (include) [tags: use-pretranspiled]

Libraryless. Click here for Pure Java version (97L/1K).

static LS javaTok_noMLS(String s) {
  new ArrayList<String> tok;
  int l = s == null ? 0 : s.length();
  
  int i = 0, n = 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;
    }
    
    tok.add(javaTok_substringN(s, i, j));
    ++n;
    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) {
        int c2 = s.charAt(j);
        if (c2 == opener || c2 == '\n' && opener == '\'') { // allow multi-line strings, but not for '
          ++j;
          break;
        } else if (c2 == '\\' && j+1 < l)
          j += 2;
        else
          ++j;
      }
    } else if (Character.isJavaIdentifierStart(c))
      do ++j; while (j < l && Character.isJavaIdentifierPart(s.charAt(j)));
    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
      ++j;
      
    tok.add(javaTok_substringC(s, i, j));
    ++n;
    i = j;
  }
  
  if ((tok.size() % 2) == 0) tok.add("");
  return tok;
}

Author comment

Began life as a copy of #1000688

download  show line numbers  debug dex  old transpilations   

Travelled to 8 computer(s): bhatertpkbcr, mowyntqkapby, mqqgnosmbjvj, pyentgdyhuwx, pzhvpgtvlbxg, tvejysmllsmz, vouqrxazstgt, xrpafgyirdlv

No comments. add comment

Snippet ID: #1025691
Snippet name: javaTok_noMLS - javaTok without multi-line-strings (for unstructure)
Eternal ID of this version: #1025691/3
Text MD5: 3fe46623152e43c511f45b5895a9cc59
Transpilation MD5: ebcc55503555ec823dd935a8ab0eb104
Author: stefan
Category:
Type: JavaX fragment (include)
Public (visible to everyone): Yes
Archived (hidden from active list): No
Created/modified: 2019-10-13 20:04:05
Source code size: 1707 bytes / 62 lines
Pitched / IR pitched: No / No
Views / Downloads: 187 / 285
Version history: 2 change(s)
Referenced in: [show references]