tokenizer.h 2.33 KB
Newer Older
1 2 3 4 5 6
#ifndef Py_TOKENIZER_H
#define Py_TOKENIZER_H
#ifdef __cplusplus
extern "C" {
#endif

7
#include "object.h"
8

Guido van Rossum's avatar
Guido van Rossum committed
9 10 11 12 13 14 15 16 17
/* Tokenizer interface */

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

#define MAXINDENT 100	/* Max indentation level */

/* Tokenizer state */
struct tok_state {
	/* Input state; buf <= cur <= inp <= end */
18 19
	/* NB an entire line is held in the buffer */
	char *buf;	/* Input buffer, or NULL; malloc'ed if fp != NULL */
Guido van Rossum's avatar
Guido van Rossum committed
20 21
	char *cur;	/* Next character in buffer */
	char *inp;	/* End of data in buffer */
22
	char *end;	/* End of input buffer if buf != NULL */
23
	char *start;	/* Start of current token if not NULL */
24 25
	int done;	/* E_OK normally, E_EOF at EOF, otherwise error code */
	/* NB If done != E_OK, cur must be == inp!!! */
Guido van Rossum's avatar
Guido van Rossum committed
26 27 28 29 30 31 32 33
	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 */
34 35
	int level;	/* () [] {} Parentheses nesting level */
			/* Used to allow free continuations inside them */
36
	/* Stuff for checking on different tab sizes */
37
	const char *filename;	/* For error messages */
38 39 40 41
	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 */
42 43 44 45 46 47
	/* Stuff for PEP 0263 */
	int decoding_state;	/* -1:decoding, 0:init, 1:raw */
	int decoding_erred;	/* whether erred in decoding  */
	int read_coding_spec;	/* whether 'coding:...' has been read  */
	int issued_encoding_warning; /* whether non-ASCII warning was issued */
	char *encoding;
48
	int cont_line;          /* whether we are in a continuation line. */
49
#ifndef PGEN
50 51
	PyObject *decoding_readline; /* codecs.open(...).readline */
	PyObject *decoding_buffer;
52
#endif
53 54
	const char* enc;
	const char* str;
Guido van Rossum's avatar
Guido van Rossum committed
55 56
};

57
extern struct tok_state *PyTokenizer_FromString(const char *);
58 59 60
extern struct tok_state *PyTokenizer_FromFile(FILE *, char *, char *);
extern void PyTokenizer_Free(struct tok_state *);
extern int PyTokenizer_Get(struct tok_state *, char **, char **);
61 62 63 64 65

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