blob: 236e353b1b0fe6c08dcb0dbe0a63769772c9cc30 (
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
54
55
56
57
58
59
60
61
62
63
64
|
{
open Tokens
exception Error of string
}
rule letter = parse
| '|' { Sep }
| 'a' { A }
| 'b' { B }
| 'c' { C }
| 'd' { D }
| 'e' { E }
| '\233' { E_ACUTE }
| '\xC3' '\xA9' { E_ACUTE }
| 'f' { F }
| 'g' { G }
| "gu" { G }
| 'h' { H }
| 'i' { I }
| 'j' { J }
| 'k' { K }
| 'l' { L }
| 'm' { M }
| "mm" { M }
| 'n' { N }
| "nn" { N }
| 'o' { O }
| 'p' { P }
| "ph" { F }
| 'q' { Q }
| "qu" { K }
| 'r' { R }
| 'u' { U }
| 's' { S }
| "ss" { SS }
| 't' { T }
| 'u' { U }
| 'v' { V }
| 'w' { W }
| 'x' { X }
| 'y' { Y }
| 'z' { Z }
| ' ' { Space }
| '\n' { EOL }
| eof { EOL }
(* This rule looks for a single line, terminated with '\n' or eof.
It returns a pair of an optional string (the line that was found)
and a Boolean flag (false if eof was reached). *)
and line = parse
| ([^'\n']* '\n') as line
(* Normal case: one line, no eof. *)
{ Some line, true }
| eof
(* Normal case: no data, eof. *)
{ None, false }
| ([^'\n']+ as line) eof
(* Special case: some data but missing '\n', then eof.
Consider this as the last line, and add the missing '\n'. *)
{ Some (line), false }
|
