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
|
.global _tokenizer_initialize
.section .rodata
raw_classes:
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "space\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "digit\n"
.ascii "digit\n"
.ascii "digit\n"
.ascii "digit\n"
.ascii "digit\n"
.ascii "digit\n"
.ascii "digit\n"
.ascii "digit\n"
.ascii "digit\n"
.ascii "digit\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "upper\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "lower\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.ascii "invalid\n"
.section .bss
.type class_names, @object
.size class_names, 1024
class_names: .zero 1024
.section .data
.type classes, @object
.size classes, 512 # 128 characters * 4 byte.
classes:
.section .text
# Initializes the classification table.
#
# Paramaters:
# a0 - Raw input for the classification table.
.type _tokenizer_classes, @function
_tokenizer_classes:
# Prologue.
addi sp, sp, -8
sw ra, 4(sp)
sw s0, 0(sp)
addi s0, sp, 8
# Epilogue.
lw ra, 4(sp)
lw s0, 0(sp)
addi sp, sp, 8
ret
# Initializes the lookup tables.
.type _tokenizer_initialize, @function
_tokenizer_initialize:
# Prologue.
addi sp, sp, -8
sw ra, 4(sp)
sw s0, 0(sp)
addi s0, sp, 8
la a0, raw_classes
call _tokenizer_classes
# Epilogue.
lw ra, 4(sp)
lw s0, 0(sp)
addi sp, sp, 8
ret
|
