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
65
66
67
|
lex start
{
ignore /[\t\n ]+/
literal '^', '|', '-', ',', ':', '!', '?', '.'
literal '(', ')', '{', '}', '*', '&', '+'
literal '--', ':>', ':>>', '<:', '->', '**'
token word /[a-zA-Z_][a-zA-Z0-9_]*/
token uint /[0-9]+/
}
def start
[expression]
{
print_xml( lhs )
}
def expression
[expression '|' term]
| [expression '&' term]
| [expression '-' term]
| [expression '--' term]
| [term]
def term
[factor_with_rep more_term]
# Can resolve the ambiguity by making more_term shortest match.
def more_term
[]
| [factor_with_rep more_term]
| ['.' factor_with_rep more_term]
| [':>' factor_with_rep more_term]
| [':>>' factor_with_rep more_term]
| ['<:' factor_with_rep more_term]
def factor_with_rep
[factor_with_rep '*']
| [factor_with_rep '**']
| [factor_with_rep '?']
| [factor_with_rep '+']
| [factor_with_rep '{' factor_rep_num '}']
| [factor_with_rep '{' ',' factor_rep_num '}']
| [factor_with_rep '{' factor_rep_num ',' '}']
| [factor_with_rep '{' factor_rep_num ',' factor_rep_num '}']
| [factor_with_neg]
def factor_rep_num
[uint]
def factor_with_neg
['!' factor_with_neg]
| ['^' factor_with_neg]
| [factor]
def factor
[alphabet_num]
| [word]
| ['(' expression ')']
def alphabet_num
[uint]
| ['-' uint]
parse start( stdin )
|
