philib/csv.cpp at master · suyjuris/philib · GitHub

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


struct Csv {
    Array<u8> data;
    s64 index;
    Status* status;
    u8 sep = ',';
};

void csv_init(Csv* csv, Array<u8> data, Status* status=nullptr) {
    if (os_status_initp(&status)) return;
    csv->status = status;
    csv->data = data;
    csv->index = 0;
}

void csv_open(Csv* csv, Array<u8> path, Status* status=nullptr) {
    csv_init(csv, os_read_file(path, status), status);
}

void csv_free(Csv* csv) {
    array_free(&csv->data);
    csv->index = -1;
}

bool csv_empty(Csv* csv) {
    if (csv->status->bad()) return true;
    return csv->index >= csv->data.size;
}

Array<u8> csv_str(Csv* csv) {
    if (csv->status->bad()) return {};

    if (csv_empty(csv)) {
        os_error_print(csv->status, 20240111011, "Cannot read string from csv, eof\n");
        return {};
    }

    s64 start = csv->index;

    if (csv->data[csv->index] == '"') {
        s64 j = start;
        ++csv->index;
        for (; csv->index < csv->data.size; ++csv->index) {
            u8 c = csv->data[csv->index];
            u8 cc = csv->index+1 < csv->data.size ? csv->data[csv->index+1] : 0;
            if (c == '"' and cc == '"') {
                ++csv->index;
            } else if (c == '"') {
                ++csv->index;
                if (cc == ',') {
                    ++csv->index;
                } else {
                    if (cc != '\n') {
                        os_error_print(csv->status, 20240111013, "csv quoted string must be followed by , or newline\n");
                        return {};
                    }
                }
                break;
            }
            csv->data[j++] = c;
        }

        return array_subarray(csv->data, start, j);
    } else {
        s64 end = -1;
        for (; csv->index < csv->data.size; ++csv->index) {
            u8 c = csv->data[csv->index];
            if (c == csv->sep) {
                end = csv->index;
                ++csv->index; break;
            } else if (c == '\n') {
                end = csv->index;
                break;
            }
        }

        if (csv->index == csv->data.size) {
            os_error_print(csv->status, 20240111012, "csv does not end in newline\n");
            return {};
        }

        return array_subarray(csv->data, start, end);
    }
}

s64 csv_int(Csv* csv) {
    auto arr = csv_str(csv);
    u64 number = 0;
    bool sign = false;
    s64 i = 0;
    for (; i < arr.size && arr[i] == '-'; ++i) {
        sign ^= 1;
    }
    for (; i < arr.size; ++i) {
        u8 c = arr[i];
        if ('0' <= c and c <= '9') {
            number = 10*number + c - '0';
        } else {
            os_error_print(csv->status, 20240111014, "csv int contains invalid characters\n");
            return 0;
        }
    }
    return sign ? -number : number;
}

#ifdef PHILIB_NUMBER

float csv_float(Csv* csv) {
    auto arr = csv_str(csv);
    return number_parse<float>(arr, csv->status);
}
double csv_double(Csv* csv) {
    auto arr = csv_str(csv);
    return number_parse<double>(arr, csv->status);
}

#endif

void csv_row(Csv* csv) {
    if (csv->index >= csv->data.size or csv->data[csv->index] != '\n') {
        return os_error_print(csv->status, 20240111015, "csv row does not end\n");
    }
    ++csv->index;
}