blob: 1622c15bd504f8464737827c08cf0eeaddf369e5 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
|
type token = LPAR | RPAR | LAPAR | RAPAR | LSPAR | RSPAR
| PLUS
| MID
| PARAM of char list
| NONTERM of char list
| TERM of char list
let rec spaces = parser
[< ' (' ' | '\t' | '\n'); _ = spaces >] -> ()
| [< >] -> ()
let nonterm c =
let rec nonterm_rec l = parser
[< ' ('a'..'z' | 'A'..'Z' | '0'..'9' | '-' | '_') as c;
s = nonterm_rec (c :: l) >] -> s
| [< >] -> NONTERM l
in nonterm_rec [c]
let term =
let rec term_rec l = parser
[< ' ('\033'..'\038' | '\040'..'\091' | '\093'..'\126') as c;
s = term_rec (c :: l) >] -> s
| [< ' ('\\'); 'c; s = term_rec (c::l) >] -> s
| [< >] -> TERM l
in term_rec []
let param =
let rec param_rec l = parser
[< ' ('\033'..'\061' | '\063'..'\091' | '\093'..'\126') as c;
s = param_rec (c :: l) >] -> s
| [< ' ('\\'); 'c;
s = param_rec (c :: l) >] -> s
| [< >] -> PARAM l
in param_rec []
let rec lexer str = (spaces str;
match str
with parser
[< ' ('('); _ = spaces >] -> [< 'LPAR; lexer str >]
| [< ' (')'); _ = spaces >] -> [< 'RPAR; lexer str >]
| [< ' ('{'); _ = spaces >] -> [< 'LAPAR; lexer str >]
| [< ' ('}'); _ = spaces >] -> [< 'RAPAR; lexer str >]
| [< ' ('['); _ = spaces >] -> [< 'LSPAR; lexer str >]
| [< ' (']'); _ = spaces >] -> [< 'RSPAR; lexer str >]
| [< ' ('+'); _ = spaces >] -> [< 'PLUS; lexer str >]
| [< ' ('|'); _ = spaces >] -> [< 'MID; lexer str >]
| [< ' ('\''); tok = term; ' ('\''); _ = spaces >]
-> [< 'tok; lexer str >]
| [< ' ('<'); tok = param; ' ('>'); _ = spaces >]
-> [< 'tok; lexer str >]
| [< ' ('a'..'z' | 'A'..'Z' | '0'..'9' | '-' | '_') as c;
tok = nonterm c; _ = spaces >] -> [< 'tok; lexer str >]
)
|
