cpython/Parser/tokenizer.h

90 lines
3.7 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 */
1990-10-14 09:07:46 -03:00
#define MAXINDENT 100 /* Max indentation level */
1990-10-14 09:07:46 -03:00
enum decoding_state {
STATE_INIT,
STATE_RAW,
STATE_NORMAL /* have a codec associated with input */
};
1990-10-14 09:07:46 -03:00
/* 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) */
const 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 */
#ifndef PGEN
/* pgen doesn't have access to Python codecs, it cannot decode the input
filename. The bytes filename might be kept, but it is only used by
indenterror() and it is not really needed: pgen only compiles one file
(Grammar/Grammar). */
PyObject *filename;
#endif
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; /* Source 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; /* open(...).readline */
PyObject *decoding_buffer;
#endif
const char* enc; /* Encoding for the current str. */
const char* str;
const char* input; /* Tokenizer's newline translated copy of the string. */
int defstack[MAXINDENT]; /* stack if funcs & indents where they
were defined */
int deftypestack[MAXINDENT]; /* stack of func types
(0 not func; 1: "def name";
2: "async def name") */
int def; /* Length of stack of func types */
1990-10-14 09:07:46 -03:00
};
extern struct tok_state *PyTokenizer_FromString(const char *, int);
extern struct tok_state *PyTokenizer_FromUTF8(const char *, int);
extern struct tok_state *PyTokenizer_FromFile(FILE *, const char*,
const char *, const 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);
#ifdef __cplusplus
}
#endif
#endif /* !Py_TOKENIZER_H */