parser/example.py at main · cangareijo/parser · GitHub

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
# To the extent possible under law, the person who associated CC0 with
# this project has waived all copyright and related or neighboring rights
# to this project.

# You should have received a copy of the CC0 legalcode along with this
# work. If not, see <http://creativecommons.org/publicdomain/zero/1.0/>.

from sys import argv

from parser import Parser

parser = Parser()

parser.add_token(r":=")
parser.add_token(r"print")
parser.add_token(r"\\/")
parser.add_token(r"/\\")
parser.add_token(r"!=")
parser.add_token(r"<=")
parser.add_token(r">=")
parser.add_token(r"<<")
parser.add_token(r">>")

parser.add_token(r";")
parser.add_token(r"=")
parser.add_token(r"<")
parser.add_token(r">")
parser.add_token(r"\+")
parser.add_token(r"-")
parser.add_token(r"\*")
parser.add_token(r"/")
parser.add_token(r"\^")
parser.add_token(r"[0-9]+")
parser.add_token(r"[a-z]+")
parser.add_token(r"\(")
parser.add_token(r"\)")

parser.add_rule("B", [r"^", "C", r"$"])

parser.add_rule("C", ["S", r";"])
parser.add_rule("C", ["S", r";", "C"])

parser.add_rule("S", [r"[a-z]+", r":=", "E"])
parser.add_rule("S", [r"print", "E"])

parser.add_rule("E", ["E1"])
parser.add_rule("E", ["E", r"\\/", "E1"])

parser.add_rule("E1", ["E2"])
parser.add_rule("E1", ["E1", r"/\\", "E2"])

parser.add_rule("E2", ["ES"])
parser.add_rule("E2", ["E2", r"=", "ES"])
parser.add_rule("E2", ["E2", r"=!", "ES"])
parser.add_rule("E2", ["E2", r"<", "ES"])
parser.add_rule("E2", ["E2", r"<=", "ES"])
parser.add_rule("E2", ["E2", r">", "ES"])
parser.add_rule("E2", ["E2", r">=", "ES"])

parser.add_rule("ES", ["E3"])
parser.add_rule("ES", ["ES", r"<<", "E3"])
parser.add_rule("ES", ["ES", r">>", "E3"])

parser.add_rule("E3", ["E4"])
parser.add_rule("E3", ["E3", r"\+", "E4"])
parser.add_rule("E3", ["E3", r"-", "E4"])

parser.add_rule("E4", ["E5"])
parser.add_rule("E4", ["E4", r"\*", "E5"])
parser.add_rule("E4", ["E4", r"/", "E5"])

parser.add_rule("E5", ["E6"])
parser.add_rule("E5", [r"\+", "E5"])
parser.add_rule("E5", [r"-", "E5"])

parser.add_rule("E6", ["E7"])
parser.add_rule("E6", ["E7", r"\^", "E6"])

parser.add_rule("E7", [r"[0-9]+"])
parser.add_rule("E7", [r"[a-z]+"])
parser.add_rule("E7", [r"\(", "E", r"\)"])

def evaluate(context, parse):
  if parse.nonterminal == "B" and len(parse.children) == 3:
    evaluate(context, parse.children[1])
  if parse.nonterminal == "C" and len(parse.children) == 2:
    evaluate(context, parse.children[0])
  if parse.nonterminal == "C" and len(parse.children) == 3:
    evaluate(context, parse.children[0])
    evaluate(context, parse.children[2])
  if parse.nonterminal == "S" and len(parse.children) == 3:
    context[parse.children[0].children] = evaluate(context, parse.children[2])
  if parse.nonterminal == "S" and len(parse.children) == 2:
    print(evaluate(context, parse.children[1]))
  if parse.nonterminal == "E" and len(parse.children) == 1:
    return evaluate(context, parse.children[0])
  if parse.nonterminal == "E" and len(parse.children) == 3 and parse.children[1].nonterminal == r"\\/":
    return evaluate(context, parse.children[0]) or evaluate(context, parse.children[2])
  if parse.nonterminal == "E1" and len(parse.children) == 1:
    return evaluate(context, parse.children[0])
  if parse.nonterminal == "E1" and len(parse.children) == 3 and parse.children[1].nonterminal == r"/\\":
    return evaluate(context, parse.children[0]) and evaluate(context, parse.children[2])
  if parse.nonterminal == "E2" and len(parse.children) == 1:
    return evaluate(context, parse.children[0])
  if parse.nonterminal == "E2" and len(parse.children) == 3 and parse.children[1].nonterminal == r"=":
    return 1 if evaluate(context, parse.children[0]) == evaluate(context, parse.children[2]) else 0
  if parse.nonterminal == "E2" and len(parse.children) == 3 and parse.children[1].nonterminal == r"!=":
    return evaluate(context, parse.children[0]) - evaluate(context, parse.children[2])
  if parse.nonterminal == "E2" and len(parse.children) == 3 and parse.children[1].nonterminal == r"<":
    return 1 if evaluate(context, parse.children[0]) < evaluate(context, parse.children[2]) else 0
  if parse.nonterminal == "E2" and len(parse.children) == 3 and parse.children[1].nonterminal == r"<=":
    return 1 if evaluate(context, parse.children[0]) <= evaluate(context, parse.children[2]) else 0
  if parse.nonterminal == "E2" and len(parse.children) == 3 and parse.children[1].nonterminal == r">":
    return 1 if evaluate(context, parse.children[0]) > evaluate(context, parse.children[2]) else 0
  if parse.nonterminal == "E2" and len(parse.children) == 3 and parse.children[1].nonterminal == r">=":
    return 1 if evaluate(context, parse.children[0]) >= evaluate(context, parse.children[2]) else 0
  if parse.nonterminal == "ES" and len(parse.children) == 1:
    return evaluate(context, parse.children[0])
  if parse.nonterminal == "ES" and len(parse.children) == 3 and parse.children[1].nonterminal == r"<<":
    return evaluate(context, parse.children[0]) << evaluate(context, parse.children[2])
  if parse.nonterminal == "ES" and len(parse.children) == 3 and parse.children[1].nonterminal == r">>":
    return evaluate(context, parse.children[0]) >> evaluate(context, parse.children[2])
  if parse.nonterminal == "E3" and len(parse.children) == 1:
    return evaluate(context, parse.children[0])
  if parse.nonterminal == "E3" and len(parse.children) == 3 and parse.children[1].nonterminal == r"\+":
    return evaluate(context, parse.children[0]) + evaluate(context, parse.children[2])
  if parse.nonterminal == "E3" and len(parse.children) == 3 and parse.children[1].nonterminal == r"-":
    return evaluate(context, parse.children[0]) - evaluate(context, parse.children[2])
  if parse.nonterminal == "E4" and len(parse.children) == 1:
    return evaluate(context, parse.children[0])
  if parse.nonterminal == "E4" and len(parse.children) == 3 and parse.children[1].nonterminal == r"\*":
    return evaluate(context, parse.children[0]) * evaluate(context, parse.children[2])
  if parse.nonterminal == "E4" and len(parse.children) == 3 and parse.children[1].nonterminal == r"/":
    return evaluate(context, parse.children[0]) // evaluate(context, parse.children[2])
  if parse.nonterminal == "E5" and len(parse.children) == 1:
    return evaluate(context, parse.children[0])
  if parse.nonterminal == "E5" and len(parse.children) == 2 and parse.children[0].nonterminal == r"\+":
    return evaluate(context, parse.children[1])
  if parse.nonterminal == "E5" and len(parse.children) == 2 and parse.children[0].nonterminal == r"-":
    return -evaluate(context, parse.children[1])
  if parse.nonterminal == "E6" and len(parse.children) == 1:
    return evaluate(context, parse.children[0])
  if parse.nonterminal == "E6" and len(parse.children) == 3 and parse.children[1].nonterminal == r"\^":
    return evaluate(context, parse.children[0]) ** evaluate(context, parse.children[2])
  if parse.nonterminal == "E7" and len(parse.children) == 1:
    return evaluate(context, parse.children[0])
  if parse.nonterminal == "E7" and len(parse.children) == 3:
    return evaluate(context, parse.children[1])
  if parse.nonterminal == r"[0-9]+":
    return int(parse.children)
  if parse.nonterminal == r"[a-z]+":
    return context[parse.children]

if len(argv) < 2:
  print("python example.py example")
  quit()

file = open(argv[1], "r", encoding = "utf-8")

if not file:
  print("Unable to open file")
  quit()

parses = parser.parse(file.read())

if len(parses) != 1:
  print("Parse error")
  quit()

evaluate({}, parses[0])