blob: 1a925f445400faa948270e83f6878d324f4ecf20 (
plain)
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
|
#include "Python.h"
#include "errcode.h"
#include "helpers.h"
#include "../lexer/state.h"
static int
tok_underflow_string(struct tok_state *tok) {
char *end = strchr(tok->inp, '\n');
if (end != NULL) {
end++;
}
else {
end = strchr(tok->inp, '\0');
if (end == tok->inp) {
tok->done = E_EOF;
return 0;
}
}
if (tok->start == NULL) {
tok->buf = tok->cur;
}
tok->line_start = tok->cur;
ADVANCE_LINENO();
tok->inp = end;
return 1;
}
/* Set up tokenizer for UTF-8 string */
struct tok_state *
_PyTokenizer_FromUTF8(const char *str, int exec_input, int preserve_crlf)
{
struct tok_state *tok = _PyTokenizer_tok_new();
char *translated;
if (tok == NULL)
return NULL;
tok->input = translated = _PyTokenizer_translate_newlines(str, exec_input, preserve_crlf, tok);
if (translated == NULL) {
_PyTokenizer_Free(tok);
return NULL;
}
tok->decoding_state = STATE_NORMAL;
tok->enc = NULL;
tok->str = translated;
tok->encoding = _PyTokenizer_new_string("utf-8", 5, tok);
if (!tok->encoding) {
_PyTokenizer_Free(tok);
return NULL;
}
tok->buf = tok->cur = tok->inp = translated;
tok->end = translated;
tok->underflow = &tok_underflow_string;
return tok;
}
|
