summaryrefslogtreecommitdiff
path: root/test/commitbt.lm
blob: fcbb22ab62f4d120655854ac34ecafe42a75750b (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
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
##### LM #####
# 2010: I'm not sure what the following means.

#
# Local commit:
# 		-clears reparse flags underneath
# 		-must be possible to backtrack after
# Global commit (revertOn)
# 		-clears all reparse flags
# 		-must be possible to backtrack after
# Global commit (!revertOn)
# 		-clears all reparse flags
# 		-clears all 'parsed' reverse code
# 		-clears all reverse code
# 		-clears all alg structures
#

# This test shows that a global commit with revertOn correctly does not clear
# 'parsed' items because it must entertain the possibility of backtracking.

lex
	ignore /[\t\n ]+/
	literal '^', '|', '-', ',', ':', '!', '?', '.'
	literal '(', ')', '{', '}', '*', '&', '+'

	literal '--', ':>', ':>>', '<:', '->', '**'

	token word /[a-zA-Z_][a-zA-Z0-9_]*/
	token uint /[0-9]+/
end


def expression [term expression_op*]

def expression_op
	['|' term]
|	['&' term]
|	['-' term]
|	['--' term]

def term [factor_rep term_rest]

# This list is done manually to get shortest match.
def term_rest
	[]
|	[term_op term_rest]

def term_op
	[factor_rep]
|	['.' factor_rep]
|	[':>' factor_rep]
|	[':>>' factor_rep]
|	['<:' factor_rep]

def factor_rep 
	[factor_neg factor_rep_op*]

def factor_rep_op
	['*']
|	['**']
|	['?']
|	['+']
|	['{' factor_rep_num '}']
|	['{' ',' factor_rep_num '}']
|	['{' factor_rep_num ',' '}']
|	['{' factor_rep_num ',' factor_rep_num '}']

def factor_rep_num [uint]

def factor_neg 
	['!' factor_neg]
|	['^' factor_neg]
|	[factor]

def factor 
	[alphabet_num]
|	[word]
|	['(' expression ')']

def alphabet_num 
	[uint]

def suint
	i: int
	[uint]

def sub
	[suint* '*']

token item
	S: sub
	/[0-9]+/
	{
		M: str = input.pull(match_length)
		parse_stop S: sub[input]
		input.push( make_token( typeid<item> M S ) )
	}

def stuff
	[item* '!']
|	[sub]

parse S: stuff[ stdin ]
print_xml( S )
print( '\n' )
##### IN #####
1 2 3 * !
##### EXP #####
<stuff><_repeat_item><item>1</item></_repeat_item><_literal_000d>!</_literal_000d></stuff>