diff options
Diffstat (limited to 'source/lexer.c')
| -rw-r--r-- | source/lexer.c | 80 |
1 files changed, 0 insertions, 80 deletions
diff --git a/source/lexer.c b/source/lexer.c deleted file mode 100644 index decfb7a..0000000 --- a/source/lexer.c +++ /dev/null | |||
| @@ -1,80 +0,0 @@ | |||
| 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 | |||
| 38 | b32 FL = TRUE; | ||
| 39 | |||
| 40 | if(buffer.size < 0) return NULL; | ||
| 41 | for(s32 index = 0; buffer.data[index] != '\0'; ++index) | ||
| 42 | { | ||
| 43 | token *tok = PushStruct(arena, token); | ||
| 44 | u8 point = buffer.data[index]; | ||
| 45 | |||
| 46 | s32 start = 0; | ||
| 47 | s32 end = 0; | ||
| 48 | |||
| 49 | if(is_whitespace(point)) | ||
| 50 | { | ||
| 51 | print("csv file is invalid"); | ||
| 52 | return NULL; | ||
| 53 | } | ||
| 54 | |||
| 55 | switch(point) | ||
| 56 | { | ||
| 57 | case('\n'): | ||
| 58 | { | ||
| 59 | if(FL) tok->flags |= END_FL; | ||
| 60 | break; | ||
| 61 | } | ||
| 62 | |||
| 63 | case(','): | ||
| 64 | { | ||
| 65 | end = index - 1; | ||
| 66 | start = index + 1; | ||
| 67 | break; | ||
| 68 | } | ||
| 69 | default: | ||
| 70 | { | ||
| 71 | break; | ||
| 72 | } | ||
| 73 | } | ||
| 74 | |||
| 75 | tok->lexeme = String8Cast(&buffer.data[start], end - start); | ||
| 76 | tok->next = tok; | ||
| 77 | } | ||
| 78 | |||
| 79 | return NULL; | ||
| 80 | } | ||
