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
|
# File 'ext/csv_parser/parser.c', line 20
static VALUE parse_line(VALUE self, VALUE str)
{
if (NIL_P(str))
return Qnil;
const char *ptr = RSTRING_PTR(str);
int len = (int) RSTRING_LEN(str); /* cast to prevent warning in 64-bit OS */
if (len == 0)
return Qnil;
VALUE array = rb_ary_new2(DEF_ARRAY_LEN); /* default allocated size is 16 */
char value[len]; /* field value, no longer than line */
int state = 0;
int index = 0;
int i;
char c;
for (i = 0; i < len; i++)
{
c = ptr[i];
switch (c)
{
case ',':
if (state == UNQUOTED) {
rb_ary_push(array, (index == 0 ? Qnil: rb_str_new(value, index)));
index = 0;
}
else if (state == IN_QUOTED) {
value[index++] = c;
}
else if (state == QUOTE_IN_QUOTED) {
rb_ary_push(array, rb_str_new(value, index));
index = 0;
state = UNQUOTED;
}
break;
case '"':
if (state == UNQUOTED) {
state = IN_QUOTED;
}
else if (state == 1) {
state = QUOTE_IN_QUOTED;
}
else if (state == QUOTE_IN_QUOTED) {
value[index++] = c; /* escaped quote */
state = IN_QUOTED;
}
break;
case 13: /* \r */
case 10: /* \n */
if (state == IN_QUOTED) {
value[index++] = c;
}
else {
i = len; /* only parse first line if multiline */
}
break;
default:
value[index++] = c;
}
}
if (state == UNQUOTED) {
rb_ary_push(array, (index == 0 ? Qnil: rb_str_new(value, index)));
}
else if (state == QUOTE_IN_QUOTED) {
rb_ary_push(array, rb_str_new(value, index));
}
return array;
}
|