Libraryless. Click here for Pure Java version (107L/1K).
1 | // TODO: extended multi-line strings |
2 | |
3 | static LS javaTokWithUnifiedNumbersAndIdentifiers(String s) {
|
4 | ArrayList<String> tok = new ArrayList(); |
5 | int l = s == null ? 0 : s.length(); |
6 | |
7 | int i = 0, n = 0; |
8 | while (i < l) {
|
9 | int j = i; |
10 | char c, d; |
11 | |
12 | // scan for whitespace |
13 | while (j < l) {
|
14 | c = s.charAt(j); |
15 | d = j+1 >= l ? '\0' : s.charAt(j+1); |
16 | if (c == ' ' || c == '\t' || c == '\r' || c == '\n') |
17 | ++j; |
18 | else if (c == '/' && d == '*') {
|
19 | do ++j; while (j < l && !s.substring(j, Math.min(j+2, l)).equals("*/"));
|
20 | j = Math.min(j+2, l); |
21 | } else if (c == '/' && d == '/') {
|
22 | do ++j; while (j < l && "\r\n".indexOf(s.charAt(j)) < 0); |
23 | } else |
24 | break; |
25 | } |
26 | |
27 | tok.add(javaTok_substringN(s, i, j)); |
28 | ++n; |
29 | i = j; |
30 | if (i >= l) break; |
31 | c = s.charAt(i); |
32 | d = i+1 >= l ? '\0' : s.charAt(i+1); |
33 | |
34 | // scan for non-whitespace |
35 | |
36 | // Special JavaX syntax: 'identifier |
37 | if (c == '\'' && Character.isJavaIdentifierStart(d) && i+2 < l && "'\\".indexOf(s.charAt(i+2)) < 0) {
|
38 | j += 2; |
39 | while (j < l && Character.isJavaIdentifierPart(s.charAt(j))) |
40 | ++j; |
41 | } else if (c == '\'' || c == '"') {
|
42 | char opener = c; |
43 | ++j; |
44 | while (j < l) {
|
45 | int c2 = s.charAt(j); |
46 | if (c2 == opener || c2 == '\n' && opener == '\'') { // allow multi-line strings, but not for '
|
47 | ++j; |
48 | break; |
49 | } else if (c2 == '\\' && j+1 < l) |
50 | j += 2; |
51 | else |
52 | ++j; |
53 | } |
54 | } else if (Character.isJavaIdentifierStart(c) || Character.isDigit(c)) {
|
55 | do ++j; while (j < l && (Character.isJavaIdentifierPart(s.charAt(j)) || s.charAt(j) == '\'')); // for stuff like "don't" |
56 | } else if (c == '[' && d == '[') {
|
57 | do ++j; while (j+1 < l && !s.substring(j, j+2).equals("]]"));
|
58 | j = Math.min(j+2, l); |
59 | } else if (c == '[' && d == '=' && i+2 < l && s.charAt(i+2) == '[') {
|
60 | do ++j; while (j+2 < l && !s.substring(j, j+3).equals("]=]"));
|
61 | j = Math.min(j+3, l); |
62 | } else |
63 | ++j; |
64 | |
65 | tok.add(javaTok_substringC(s, i, j)); |
66 | ++n; |
67 | i = j; |
68 | } |
69 | |
70 | if ((tok.size() % 2) == 0) tok.add("");
|
71 | ret tok; |
72 | } |
Began life as a copy of #1000688
download show line numbers debug dex old transpilations
Travelled to 7 computer(s): bhatertpkbcr, mqqgnosmbjvj, pyentgdyhuwx, pzhvpgtvlbxg, tvejysmllsmz, vouqrxazstgt, xrpafgyirdlv
No comments. add comment
| Snippet ID: | #1027377 |
| Snippet name: | javaTokWithUnifiedNumbersAndIdentifiers |
| Eternal ID of this version: | #1027377/1 |
| Text MD5: | bacfd33bbb1accc32b6448fdc3aec223 |
| Transpilation MD5: | ec1aa8019d613083dd39a6c0b9ff638c |
| Author: | stefan |
| Category: | javax / parsing |
| Type: | JavaX fragment (include) |
| Public (visible to everyone): | Yes |
| Archived (hidden from active list): | No |
| Created/modified: | 2020-03-15 16:35:03 |
| Source code size: | 2253 bytes / 72 lines |
| Pitched / IR pitched: | No / No |
| Views / Downloads: | 391 / 520 |
| Referenced in: | [show references] |