-
Notifications
You must be signed in to change notification settings - Fork 2
/
my_lexer.py
276 lines (236 loc) · 7.37 KB
/
my_lexer.py
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
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
from my_grammar import *
from decimal import Decimal
class Token(object):
def __init__(self, token_type, value, line_num, indent_level, value_type=None):
self.type = token_type
self.value = value
self.value_type = value_type
self.line_num = line_num
self.indent_level = indent_level
def __str__(self):
return 'Token(type={type}, value={value}, line_num={line_num}, indent_level={indent_level})'.format(
type=self.type,
value=repr(self.value),
line_num=self.line_num,
indent_level=self.indent_level
)
__repr__ = __str__
class Lexer(object):
def __init__(self, text, file_name=None):
self.text = text
self.file_name = file_name
self.pos = 0
self.current_char = self.text[self.pos]
self.char_type = None
self.word = ''
self.word_type = None
self._line_num = 1
self._indent_level = 0
self.current_token = None
def next_char(self):
self.pos += 1
if self.pos > len(self.text) - 1:
self.current_char = None
self.char_type = None
else:
self.current_char = self.text[self.pos]
self.char_type = self.get_type(self.current_char)
def reset_word(self):
old_word = self.word
self.word = ''
self.word_type = None
return old_word
def peek(self, num):
peek_pos = self.pos + num
if peek_pos > len(self.text) - 1:
return None
else:
return self.text[peek_pos]
def preview_token(self, num=1):
if num < 1:
raise ValueError('num argument must be 1 or greater')
next_token = None
current_pos = self.pos
current_char = self.current_char
current_char_type = self.char_type
current_word = self.word
current_word_type = self.word_type
current_line_num = self.line_num
current_indent_level = self.indent_level
for _ in range(num):
next_token = self.get_next_token()
self.pos = current_pos
self.current_char = current_char
self.char_type = current_char_type
self.word = current_word
self.word_type = current_word_type
self._line_num = current_line_num
self._indent_level = current_indent_level
return next_token
def skip_whitespace(self):
if self.peek(-1) == '\n':
raise SyntaxError('Only tab characters can indent')
while self.current_char is not None and self.current_char.isspace():
self.next_char()
self.reset_word()
def skip_comment(self):
while self.current_char != '\n':
self.next_char()
if self.current_char is None:
return self.eof()
self.eat_newline()
if self.current_char == '#':
self.skip_comment()
def increment_line_num(self):
self._line_num += 1
@property
def line_num(self):
return self._line_num
@property
def indent_level(self):
return self._indent_level
def reset_indent_level(self):
self._indent_level = 0
return self._indent_level
def decriment_indent_level(self):
self._indent_level -= 1
return self._indent_level
def increment_indent_level(self):
self._indent_level += 1
return self._indent_level
def eat_newline(self):
self.reset_word()
token = Token(NEWLINE, '\n', self.line_num, self.indent_level)
self.reset_indent_level()
self.increment_line_num()
self.next_char()
return token
def skip_indent(self):
while self.current_char is not None and self.current_char == '\t':
self.reset_word()
self.increment_indent_level()
self.next_char()
def eof(self):
return Token(EOF, EOF, self.line_num, self.indent_level)
@staticmethod
def get_type(char):
if char.isspace():
return WHITESPACE
if char == '#':
return COMMENT
if char == '\\':
return ESCAPE
if char in OPERATORS:
return OPERATIC
if char.isdigit():
return NUMERIC
else:
return ALPHANUMERIC
def get_next_token(self):
if self.current_char is None:
return self.eof()
if self.current_char == '\n':
return self.eat_newline()
elif self.current_char == '\t':
self.skip_indent()
if self.current_char.isspace():
self.skip_whitespace()
if self.current_char == '#':
self.skip_comment()
return self.get_next_token()
if self.current_char == '"':
self.next_char()
while self.current_char != '"':
if self.current_char == '\\' and self.peek(1) == '"':
self.next_char()
self.word += self.current_char
self.next_char()
self.next_char()
return Token(STRING, self.reset_word(), self.line_num, self.indent_level)
if self.current_char == "'":
self.next_char()
while self.current_char != "'":
if self.current_char == '\\' and self.peek(1) == "'":
self.next_char()
self.word += self.current_char
self.next_char()
self.next_char()
return Token(STRING, self.reset_word(), self.line_num, self.indent_level)
if not self.char_type:
self.char_type = self.get_type(self.current_char)
if not self.word_type:
self.word_type = self.char_type
if self.word_type == OPERATIC:
while self.char_type == OPERATIC:
self.word += self.current_char
self.next_char()
if self.current_char in SINGLE_OPERATORS or self.word in SINGLE_OPERATORS:
break
return Token(OP, self.reset_word(), self.line_num, self.indent_level)
if self.word_type == ALPHANUMERIC:
while self.char_type == ALPHANUMERIC or self.char_type == NUMERIC:
self.word += self.current_char
self.next_char()
if self.word in OPERATORS:
if self.word in MULTI_WORD_OPERATORS and self.preview_token(1).value in MULTI_WORD_OPERATORS:
self.next_char()
self.word += ' '
while self.char_type == ALPHANUMERIC or self.char_type == NUMERIC:
self.word += self.current_char
self.next_char()
return Token(OP, self.reset_word(), self.line_num, self.indent_level)
else:
return Token(OP, self.reset_word(), self.line_num, self.indent_level)
if self.word in KEYWORDS:
if self.word in MULTI_WORD_KEYWORDS and self.preview_token(1).value in MULTI_WORD_KEYWORDS:
self.next_char()
self.word += ' '
while self.char_type == ALPHANUMERIC or self.char_type == NUMERIC:
self.word += self.current_char
self.next_char()
return Token(KEYWORD, self.reset_word(), self.line_num, self.indent_level)
else:
return Token(KEYWORD, self.reset_word(), self.line_num, self.indent_level)
elif self.word in TYPES:
return Token(TYPE, self.reset_word(), self.line_num, self.indent_level)
elif self.word in CONSTANTS:
return Token(CONSTANT, self.reset_word(), self.line_num, self.indent_level)
else:
return Token(NAME, self.reset_word(), self.line_num, self.indent_level)
if self.word_type == NUMERIC:
while self.char_type == NUMERIC or self.current_char == DOT and self.peek(1) != DOT:
self.word += self.current_char
self.next_char()
if self.char_type == ALPHANUMERIC:
raise SyntaxError('Variables cannot start with numbers')
value = self.reset_word()
if '.' in value:
value = Decimal(value)
value_type = DEC
else:
value = int(value)
value_type = INT
return Token(NUMBER, value, self.line_num, self.indent_level, value_type=value_type)
if self.char_type == ESCAPE:
self.reset_word()
self.next_char()
line_num = self.line_num
if self.current_char == '\n':
self.increment_line_num()
self.next_char()
return Token(ESCAPE, '\\', line_num, self.indent_level)
raise SyntaxError('Unknown character')
def analyze(self):
token = self.get_next_token()
while token.type != EOF:
yield token
token = self.get_next_token()
yield token
if __name__ == '__main__':
file = 'test.my'
lexer = Lexer(open(file).read(), file)
for t in lexer.analyze():
if t.type == NEWLINE:
print(t)
else:
print(t, end=' ')