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
|
#pike __REAL_VERSION__
//! Returns the provided string with Python code as
//! an array with tokens.
array(string) split(string data) {
int pos;
array(string) ret = ({});
data += "\0\0\0"; // end sentinel
while(1) {
int start = pos;
switch(data[pos]) {
case 0:
return ret;
case '\r':
// End of line
pos++;
if(data[pos]=='\n') pos++;
break;
case '\n':
// End of line
pos++;
if(data[pos]=='\r') pos++;
break;
case ' ':
case '\t':
case '\f':
// Spaces and tabs
while( (< ' ', '\t' >)[data[++pos]] );
break;
case '\\':
// Line joiner
pos++;
break;
case '#':
// Comment. Ends at end of physical line.
while(!(< '\r', '\n' >)[data[++pos]]);
break;
case 'a'..'z':
case 'A'..'Z':
case '_':
while(1) {
switch(data[pos]) {
case 'a'..'z':
case 'A'..'Z':
case '0'..'9':
case '_':
pos++;
continue;
}
break;
}
break;
case '.':
pos++;
if( data[pos]<'0' || data[pos]>'9' ) break;
// fallthrough
case '0'..'9':
// Hexdigit
if( data[pos]=='0' && (< 'x', 'X' >)[data[pos+1]] ) {
pos += 2;
while( (< '0','1','2','3','4','5','6','7','8','9',
'a','b','c','d','e','f','A','B','C','D',
'E','F' >)[data[++pos]] );
}
else {
// Octal, decimal and floats except exponent.
while( (< '0','1','2','3','4','5','6','7','8','9',
'.' >)[data[++pos]] );
}
// Long integer
if( (< 'l', 'L' >)[data[pos]] ) {
pos++;
break;
}
if( (< 'e', 'E' >)[data[pos]] ) {
pos++;
if( (< '+', '-' >)[data[pos]] ) pos++;
while( (< '0','1','2','3','4','5','6','7','8','9' >)[data[++pos]] );
}
// Imaginary number
if( (< 'j', 'J' >)[data[pos]] ) pos++;
break;
case '\'':
if( data[pos+1]=='\'' && data[pos+2]=='\'' ) {
pos += 2;
while( !(data[++pos]=='\'' && data[pos+1]=='\'' && data[pos+2]=='\'') )
if( data[pos]=='\\' ) pos++;
pos += 2;
}
else
while( data[++pos]!='\'' )
if( data[pos]=='\\' ) pos++;
pos++;
break;
case '"':
if( data[pos+1]=='\"' && data[pos+2]=='\"' ) {
pos += 2;
while( !(data[++pos]=='\"' && data[pos+1]=='\"' && data[pos+2]=='\"') )
if( data[pos]=='\\' ) pos++;
pos += 2;
}
else
while( data[++pos]!='\"' )
if( data[pos]=='\\' ) pos++;
pos++;
break;
case '<': case '>':
pos++;
if( (< '<', '=', '>' >)[data[pos]]) pos++;
if( data[pos]=='=' ) pos++;
break;
case '*':
if(data[pos+1]=='*') pos++;
// fallthrough
case '+': case '-':
case '/': case '%':
case '&': case '|': case '^':
case '=':
pos ++;
if( data[pos]=='=' ) pos++;
break;
case '!':
pos++;
if(data[pos]=='=') pos++;
break;
case '(': case ')':
case '[': case ']':
case '{': case '}':
case ':': case ';':
case '~':
case ',':
pos++;
break;
default:
error("Parser error at %d (%O).\n", pos, data[pos..pos+20]);
}
ret += ({ data[start..pos-1] });
}
}
|
