cpython/Parser/tokenizer.h

66 lines
2.3 KiB
C
Raw Normal View History

#ifndef Py_TOKENIZER_H
#define Py_TOKENIZER_H
#ifdef __cplusplus
extern "C" {
#endif
#include "object.h"
1991-02-19 08:39:46 -04:00
1990-10-14 09:07:46 -03:00
/* 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 */
/* NB an entire line is held in the buffer */
char *buf; /* Input buffer, or NULL; malloc'ed if fp != NULL */
1990-10-14 09:07:46 -03:00
char *cur; /* Next character in buffer */
char *inp; /* End of data in buffer */
char *end; /* End of input buffer if buf != NULL */
1994-08-30 05:27:36 -03:00
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!!! */
1990-10-14 09:07:46 -03:00
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 */
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 */
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;
int cont_line; /* whether we are in a continuation line. */
#ifndef PGEN
PyObject *decoding_readline; /* codecs.open(...).readline */
PyObject *decoding_buffer;
#endif
const char* enc;
const char* str;
1990-10-14 09:07:46 -03:00
};
extern struct tok_state *PyTokenizer_FromString(char *);
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 **);
#ifdef __cplusplus
}
#endif
#endif /* !Py_TOKENIZER_H */