diff options
Diffstat (limited to 'source/lexer.c')
| -rw-r--r-- | source/lexer.c | 94 |
1 files changed, 94 insertions, 0 deletions
diff --git a/source/lexer.c b/source/lexer.c new file mode 100644 index 0000000..c84a831 --- /dev/null +++ b/source/lexer.c | |||
| @@ -0,0 +1,94 @@ | |||
| 1 | // the lexer acts as a table builder from a csv file | ||
| 2 | // and parsing indivudal rows and columns | ||
| 3 | // the next step would be building a the b-tree | ||
| 4 | internal b32 | ||
| 5 | is_alpha(u8 point) | ||
| 6 | { | ||
| 7 | return ((point >= 'a' && point <= 'z') || (point >= 'A' && point <= 'Z') || (point == '_')); | ||
| 8 | } | ||
| 9 | |||
| 10 | internal b32 | ||
| 11 | is_digit(u8 point) | ||
| 12 | { | ||
| 13 | return (point >= '0' && point <= '9'); | ||
| 14 | } | ||
| 15 | |||
| 16 | internal b32 | ||
| 17 | is_alpha_num(u8 point) | ||
| 18 | { | ||
| 19 | return (is_alpha(point) || is_digit(point)); | ||
| 20 | } | ||
| 21 | |||
| 22 | internal b32 | ||
| 23 | is_whitespace(u8 point) | ||
| 24 | { | ||
| 25 | return (point == '\n' || point == '\r' || point == ' ' || point == '\t'); | ||
| 26 | } | ||
| 27 | |||
| 28 | internal b32 | ||
| 29 | is_delimiter(u8 point) | ||
| 30 | { | ||
| 31 | return (point == ','); | ||
| 32 | } | ||
| 33 | |||
| 34 | internal token * | ||
| 35 | tokenize_csv(string8 buffer, mem_arena *arena) | ||
| 36 | { | ||
| 37 | s32 count = 0; | ||
| 38 | string8 **tokens = PushString(arena, buffer.size); | ||
| 39 | |||
| 40 | b32 FL = TRUE; | ||
| 41 | |||
| 42 | if(buffer.size < 0) return NULL; | ||
| 43 | for(s32 index = 0; | ||
| 44 | buffer.data[index] != '\0'; | ||
| 45 | ++index) | ||
| 46 | { | ||
| 47 | csv_row *row = PushStruct(arena, csv_row); | ||
| 48 | token *tok = PushStruct(arena, token); | ||
| 49 | |||
| 50 | u8 point = buffer.data[index]; | ||
| 51 | |||
| 52 | u8 *start = buffer.data; | ||
| 53 | u8 *end = NULL; | ||
| 54 | |||
| 55 | unused(row); | ||
| 56 | |||
| 57 | switch(point) | ||
| 58 | { | ||
| 59 | case('\n'): | ||
| 60 | { | ||
| 61 | |||
| 62 | if(FL) | ||
| 63 | { | ||
| 64 | FL = FALSE; | ||
| 65 | tok->flags |= END_FL; | ||
| 66 | } | ||
| 67 | |||
| 68 | break; | ||
| 69 | |||
| 70 | } | ||
| 71 | |||
| 72 | case(','): | ||
| 73 | { | ||
| 74 | end = start - 1; | ||
| 75 | break; | ||
| 76 | } | ||
| 77 | |||
| 78 | default: | ||
| 79 | { | ||
| 80 | printf("point: %c\n", point); | ||
| 81 | count++; | ||
| 82 | break; | ||
| 83 | } | ||
| 84 | } | ||
| 85 | |||
| 86 | token->lexeme = String8Cast(start, end - start); | ||
| 87 | |||
| 88 | *tokens = token; | ||
| 89 | ++tokens; | ||
| 90 | |||
| 91 | |||
| 92 | return NULL; | ||
| 93 | } | ||
| 94 | } | ||
