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
|
# Generated by re2py
# re2py $INPUT -o $OUTPUT
from enum import Enum
import os
BUFSIZE = 4096
YYMAXFILL = 1
class State:
def __init__(self, fname):
self.file = open(fname, "rb")
self.yyinput = bytearray(BUFSIZE)
self.yylimit = BUFSIZE - YYMAXFILL
self.yycursor = self.yylimit
self.yymarker = self.yylimit
self.token = self.yylimit
self.eof = False
def __del__(self):
self.file.close()
class Status(Enum):
OK = 0
EOF = 1
LONG_LEXEME = 2
def fill(st, need):
if st.eof:
return Status.EOF
# Error: lexeme too long. In real life could reallocate a larger buffer.
if st.token < need:
return Status.LONG_LEXEME
# Shift buffer contents (discard everything up to the current token).
st.yyinput = st.yyinput[st.token:st.yylimit]
st.yycursor -= st.token;
st.yymarker -= st.token;
st.yylimit -= st.token;
st.token = 0;
# Fill free space at the end of buffer with new data from file.
bytes = st.file.read(BUFSIZE - st.yylimit - 1) # -1 for sentinel
if not bytes:
st.eof = True # end of file
st.yylimit += YYMAXFILL
st.yyinput += b"\0" * YYMAXFILL
else:
st.yylimit += len(bytes);
st.yyinput += bytes
return Status.OK
def lex(yyrecord):
count = 0
while True:
yyrecord.token = yyrecord.yycursor
yystate = 0
while True:
match yystate:
case 0:
if yyrecord.yylimit <= yyrecord.yycursor:
if fill(yyrecord, 1) != Status.OK: return -1
yych = yyrecord.yyinput[yyrecord.yycursor]
yyrecord.yycursor += 1
if yych <= 0x20:
if yych <= 0x00:
yystate = 1
continue
if yych <= 0x1F:
yystate = 2
continue
yystate = 3
continue
else:
if yych == 0x27:
yystate = 4
continue
yystate = 2
continue
case 1:
# Check that it is the sentinel, not some unexpected null.
return count if yyrecord.token == yyrecord.yylimit - YYMAXFILL else -1
case 2:
return -1
case 3:
if yyrecord.yylimit <= yyrecord.yycursor:
if fill(yyrecord, 1) != Status.OK: return -1
yych = yyrecord.yyinput[yyrecord.yycursor]
if yych == 0x20:
yyrecord.yycursor += 1
yystate = 3
continue
break
case 4:
if yyrecord.yylimit <= yyrecord.yycursor:
if fill(yyrecord, 1) != Status.OK: return -1
yych = yyrecord.yyinput[yyrecord.yycursor]
yyrecord.yycursor += 1
if yych == 0x27:
yystate = 5
continue
if yych == 0x5C:
yystate = 6
continue
yystate = 4
continue
case 5:
count += 1
break
case 6:
if yyrecord.yylimit <= yyrecord.yycursor:
if fill(yyrecord, 1) != Status.OK: return -1
yyrecord.yycursor += 1
yystate = 4
continue
case _:
raise "internal lexer error"
def main():
fname = "input"
# Prepare input file.
f = open(fname, "w")
for i in range(BUFSIZE):
f.write("'qu\0tes' 'are' 'fine: \\'' ")
f.close()
# Run lexer on the prepared file.
st = State(fname)
assert lex(st) == 3 * BUFSIZE
# Cleanup.
os.remove(fname)
if __name__ == '__main__':
main()
|
