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).

1  
static LS javaTok_noMLS(String s) {
2  
  new ArrayList<String> tok;
3  
  int l = s == null ? 0 : s.length();
4  
  
5  
  int i = 0, n = 0;
6  
  while (i < l) {
7  
    int j = i;
8  
    char c, d;
9  
    
10  
    // scan for whitespace
11  
    while (j < l) {
12  
      c = s.charAt(j);
13  
      d = j+1 >= l ? '\0' : s.charAt(j+1);
14  
      if (c == ' ' || c == '\t' || c == '\r' || c == '\n')
15  
        ++j;
16  
      else if (c == '/' && d == '*') {
17  
        do ++j; while (j < l && !s.substring(j, Math.min(j+2, l)).equals("*/"));
18  
        j = Math.min(j+2, l);
19  
      } else if (c == '/' && d == '/') {
20  
        do ++j; while (j < l && "\r\n".indexOf(s.charAt(j)) < 0);
21  
      } else
22  
        break;
23  
    }
24  
    
25  
    tok.add(javaTok_substringN(s, i, j));
26  
    ++n;
27  
    i = j;
28  
    if (i >= l) break;
29  
    c = s.charAt(i);
30  
    d = i+1 >= l ? '\0' : s.charAt(i+1);
31  
32  
    // scan for non-whitespace
33  
    
34  
    if (c == '\'' || c == '"') {
35  
      char opener = c;
36  
      ++j;
37  
      while (j < l) {
38  
        int c2 = s.charAt(j);
39  
        if (c2 == opener || c2 == '\n' && opener == '\'') { // allow multi-line strings, but not for '
40  
          ++j;
41  
          break;
42  
        } else if (c2 == '\\' && j+1 < l)
43  
          j += 2;
44  
        else
45  
          ++j;
46  
      }
47  
    } else if (Character.isJavaIdentifierStart(c))
48  
      do ++j; while (j < l && Character.isJavaIdentifierPart(s.charAt(j)));
49  
    else if (Character.isDigit(c)) {
50  
      do ++j; while (j < l && Character.isDigit(s.charAt(j)));
51  
      if (j < l && s.charAt(j) == 'L') ++j; // Long constants like 1L
52  
    } else
53  
      ++j;
54  
      
55  
    tok.add(javaTok_substringC(s, i, j));
56  
    ++n;
57  
    i = j;
58  
  }
59  
  
60  
  if ((tok.size() % 2) == 0) tok.add("");
61  
  return tok;
62  
}

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: 198 / 301
Version history: 2 change(s)
Referenced in: [show references]