summaryrefslogtreecommitdiff
path: root/Parser/tokenizer.h
blob: c45dea1a8b0b87b1025da238629198cc0a6e6df4 (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
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
#ifndef Py_TOKENIZER_H
#define Py_TOKENIZER_H
#ifdef __cplusplus
extern "C" {
#endif

#include "object.h"

/* Tokenizer interface */

#include "token.h"	/* For token types */

#define MAXINDENT 100	/* Max indentation level */

enum decoding_state {
	STATE_INIT,
	STATE_RAW,
	STATE_NORMAL, /* have a codec associated with input */
};

/* Tokenizer state */
struct tok_state {
	/* Input state; buf <= cur <= inp <= end */
	/* NB an entire line is held in the buffer */
	char *buf;	/* Input buffer, or NULL; malloc'ed if fp != NULL */
	char *cur;	/* Next character in buffer */
	char *inp;	/* End of data in buffer */
	char *end;	/* End of input buffer if buf != NULL */
	char *start;	/* Start of current token if not NULL */
	int done;	/* E_OK normally, E_EOF at EOF, otherwise error code */
	/* NB If done != E_OK, cur must be == inp!!! */
	FILE *fp;	/* Rest of input; NULL if tokenizing a string */
	int tabsize;	/* Tab spacing */
	int indent;	/* Current indentation index */
	int indstack[MAXINDENT];	/* Stack of indents */
	int atbol;	/* Nonzero if at begin of new line */
	int pendin;	/* Pending indents (if > 0) or dedents (if < 0) */
	char *prompt, *nextprompt;	/* For interactive prompting */
	int lineno;	/* Current line number */
	int level;	/* () [] {} Parentheses nesting level */
			/* Used to allow free continuations inside them */
	/* Stuff for checking on different tab sizes */
	const char *filename;	/* For error messages */
	int altwarning;	/* Issue warning if alternate tabs don't match */
	int alterror;	/* Issue error if alternate tabs don't match */
	int alttabsize;	/* Alternate tab spacing */
	int altindstack[MAXINDENT];	/* Stack of alternate indents */
	/* Stuff for PEP 0263 */
	enum decoding_state decoding_state;
	int decoding_erred;	/* whether erred in decoding  */
	int read_coding_spec;	/* whether 'coding:...' has been read  */
	char *encoding;
	int cont_line;          /* whether we are in a continuation line. */
	const char* line_start;	/* pointer to start of current line */
#ifndef PGEN
	PyObject *decoding_readline; /* codecs.open(...).readline */
	PyObject *decoding_buffer;
#endif
	const char* enc;
	const char* str;
};

extern struct tok_state *PyTokenizer_FromString(const char *);
extern struct tok_state *PyTokenizer_FromFile(FILE *, char*,
					      char *, char *);
extern void PyTokenizer_Free(struct tok_state *);
extern int PyTokenizer_Get(struct tok_state *, char **, char **);
extern char * PyTokenizer_RestoreEncoding(struct tok_state* tok, 
					  int len, int *offset);
extern char * PyTokenizer_FindEncoding(int);

#ifdef __cplusplus
}
#endif
#endif /* !Py_TOKENIZER_H */