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
|
from .structs import TokenType, Token
from .exceptions import LexError
import sys
types = {
":int": TokenType.INT_TYPE,
":float": TokenType.FLOAT_TYPE,
":number": TokenType.NUMBER_TYPE,
":string": TokenType.STRING_TYPE,
":list": TokenType.LIST_TYPE,
":any": TokenType.ANY_TYPE,
":literal": TokenType.LITERAL_TYPE,
":bool": TokenType.BOOL_TYPE }
keywords = {
"def": TokenType.DEF,
"lambda": TokenType.LAMBDA,
"&": TokenType.MANY,
"func": TokenType.FUNC }
WHITESPACE = [" ", "\n", "\t"]
SEPARATORS = WHITESPACE + [")", "]", "}"]
DIGITS = list("0123456789")
def lex(data):
start = 0
current = 0
line = 1
end = len(data)
tokens = []
while current < end:
char = data[current]
if char == ";":
while char != "\n" and current < end:
current += 1
char = data[current]
continue
if char == "\n":
line += 1
if char in WHITESPACE:
current += 1
continue
elif char == "(":
tokens.append(Token(TokenType.OPEN_PAREN, "(", None, line))
elif char == ")":
tokens.append(Token(TokenType.CLOSE_PAREN, ")", None, line))
elif char == "[":
tokens.append(Token(TokenType.OPEN_BRACKET, "[", None, line))
elif char == "]":
tokens.append(Token(TokenType.CLOSE_BRACKET, "]", None, line))
elif char == "{":
tokens.append(Token(TokenType.OPEN_BRACE, "{", None, line))
elif char == "}":
tokens.append(Token(TokenType.CLOSE_BRACE, "}", None, line))
elif char == ":":
tokens.append(Token(TokenType.COLON, ":", None, line))
# numbers
#elif char in DIGITS or char == ".":
elif char in DIGITS:
tok, length = get_number(data[current:], line)
tokens.append(tok)
current += length
# strings
elif char == '"':
tok, length, offset = get_string(data[current+1:], line)
tokens.append(tok)
current += length
line += offset
# bools
elif char == "#":
tok, length = get_bool(data[current+1:], line)
tokens.append(tok)
current += length
# single quotes
elif char == "'":
tokens.append(Token(TokenType.APOSTROPHE, "'", None, line))
# symbols
else:
tok, length = get_symbol(data[current:], line)
if tok.text in keywords:
tok.type_ = keywords[tok.text]
tokens.append(tok)
current += length
current += 1
tokens.append(Token(TokenType.EOF, "", None, line))
return tokens
def get_number(data, line):
counter = 0
value = ""
is_float = False
char = data[counter]
while char not in SEPARATORS:
if char in DIGITS:
value += char
elif char == ".":
if is_float:
raise LexError("too many '.' in number", line)
is_float = True
value += char
else:
raise Exception(f"invalid number: {value}")
counter += 1
if counter >= len(data):
break
char = data[counter]
if is_float:
return Token(TokenType.FLOAT, value, float(value), line), counter - 1
else:
return Token(TokenType.INT, value, int(value), line), counter - 1
def get_string(data, line):
offset = 0
counter = 0
string = ""
while data[counter] != '"':
if data[counter] == "\n":
offset += 1
# look ahead to see if it's a double quote
if data[counter] == "\\" and \
len(data) > counter and \
data[counter+1] == '"':
string += '"'
counter += 1
else:
string += data[counter]
counter += 1
if counter >= len(data):
raise Exception("couldn't parse string")
string = string.encode().decode("unicode_escape")
return Token(TokenType.STRING, str(string), str(string), line), counter + 1, offset
def get_bool(data, line):
counter = 0
value = ""
while data[counter] not in SEPARATORS:
value += data[counter]
counter += 1
if counter >= len(data):
break
if value == "true":
return Token(TokenType.TRUE, "#true", True, line), 4
elif value == "false":
return Token(TokenType.FALSE, "#false", False, line), 5
else:
raise LexError("couldn't parse boolean", line)
def get_symbol(data, line):
counter = 0
value = ""
while data[counter] not in SEPARATORS:
value += data[counter]
counter += 1
if counter >= len(data):
break
return Token(TokenType.SYMBOL, value, None, line), counter - 1
|
