Source file parser_components.ml
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
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
open Angstrom
let is_letter c =
match c with
| 'A'..'Z' -> true
| 'a'..'z' -> true
| _ -> false
let is_space c =
match c with
| ' ' -> true
| '\t' -> true
| '\n' -> true
| _ -> false
let is_not_space c =
not (is_space c)
let is_digit c =
match c with
| '0'..'9' -> true
| _ -> false
let digit : char t =
satisfy is_digit
let alpha_string : string t =
take_while1 is_letter
let any_string : string t = take_while (fun _ -> true)
let take_space : string t = take_while is_space
let optional_char target =
peek_char
>>= (fun c ->
match c with
| None -> return ()
| Some c ->
if c = target then
any_char *> return ()
else
return ()
)
let ident_string ~(reserved_words : string list) : string t =
let reserved_words = List.map String.lowercase_ascii reserved_words in
alpha_string
>>= fun s ->
if List.mem (String.lowercase_ascii s) reserved_words then
fail (Printf.sprintf "\"%s\" is a reserved word" s)
else return s
let skip_non_num_string ~end_markers =
skip_while (function
| '0' .. '9' -> false
| c -> (
match end_markers with
| None -> true
| Some x -> not (String.contains x c)))
let num_string : string t =
take_while1 (function '0' .. '9' -> true | _ -> false)
let nat_zero : int t =
num_string
>>= fun s ->
try return (int_of_string s)
with _ -> fail (Printf.sprintf "integer %s is out of range" s)
let nat_zero_w_original_str : (int * string) t =
num_string
>>= fun s ->
try return (int_of_string s, s)
with _ -> fail (Printf.sprintf "integer %s is out of range" s)
let one_digit_nat_zero : int t =
digit >>= fun c -> return (int_of_string (Printf.sprintf "%c" c))
let two_digit_nat_zero : int t =
digit
>>= fun c1 ->
digit
>>= fun c2 -> return (int_of_string (Printf.sprintf "%c%c" c1 c2))
let max_two_digit_nat_zero : int t =
two_digit_nat_zero
<|> (digit >>= fun c -> return (int_of_string (Printf.sprintf "%c" c)))
let float_non_neg : float t =
take_while1 is_digit
>>= fun x ->
char '.'
*> take_while1 is_digit
>>= fun y ->
let s = x ^ "." ^ y in
try return (float_of_string s)
with _ -> fail (Printf.sprintf "float %s is out of range" s)
let comma : char t = char ','
let dot : char t = char '.'
let hyphen : char t = char '-'
let non_square_bracket_string : string t =
take_while (function '[' | ']' -> false | _ -> true)
let non_curly_bracket_string : string t =
take_while (function '{' | '}' -> false | _ -> true)
let non_parenthesis_string : string t =
take_while (function '(' | ')' -> false | _ -> true)
let non_space_string : string t = take_while1 is_not_space
let spaces = skip_while is_space
let spaces1 = take_while1 is_space *> return ()
let sep_by_comma (p : 'a t) : 'a list t =
sep_by (spaces *> comma *> spaces) p
let sep_by_comma1 (p : 'a t) : 'a list t =
sep_by1 (spaces *> comma *> spaces) p
let invalid_syntax ~text ~pos =
fail (Printf.sprintf "invalid syntax: %s, pos: %d" text pos)
let ~end_markers =
spaces
*> pos
>>= fun pos ->
take_while (fun c -> not (String.contains end_markers c))
>>= fun s ->
match s with "" -> return () | text -> invalid_syntax ~text ~pos