/Parser/tokenizer.h

 1#ifndef Py_TOKENIZER_H
 2#define Py_TOKENIZER_H
 3#ifdef __cplusplus
 4extern "C" {
 5#endif
 6
 7#include "object.h"
 8
 9/* Tokenizer interface */
10
11#include "token.h"	/* For token types */
12
13#define MAXINDENT 100	/* Max indentation level */
14
15/* Tokenizer state */
16struct tok_state {
17	/* Input state; buf <= cur <= inp <= end */
18	/* NB an entire line is held in the buffer */
19	char *buf;	/* Input buffer, or NULL; malloc'ed if fp != NULL */
20	char *cur;	/* Next character in buffer */
21	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	int done;	/* E_OK normally, E_EOF at EOF, otherwise error code */
25	/* NB If done != E_OK, cur must be == inp!!! */
26	FILE *fp;	/* Rest of input; NULL if tokenizing a string */
27	int tabsize;	/* Tab spacing */
28	int indent;	/* Current indentation index */
29	int indstack[MAXINDENT];	/* Stack of indents */
30	int atbol;	/* Nonzero if at begin of new line */
31	int pendin;	/* Pending indents (if > 0) or dedents (if < 0) */
32	char *prompt, *nextprompt;	/* For interactive prompting */
33	int lineno;	/* Current line number */
34	int level;	/* () [] {} Parentheses nesting level */
35			/* Used to allow free continuations inside them */
36	/* Stuff for checking on different tab sizes */
37	const char *filename;	/* For error messages */
38	int altwarning;	/* Issue warning if alternate tabs don't match */
39	int alterror;	/* Issue error if alternate tabs don't match */
40	int alttabsize;	/* Alternate tab spacing */
41	int altindstack[MAXINDENT];	/* Stack of alternate indents */
42	/* Stuff for PEP 0263 */
43	int decoding_state;	/* -1:decoding, 0:init, 1:raw */
44	int decoding_erred;	/* whether erred in decoding  */
45	int read_coding_spec;	/* whether 'coding:...' has been read  */
46	char *encoding;
47	int cont_line;          /* whether we are in a continuation line. */
48	const char* line_start;	/* pointer to start of current line */
49#ifndef PGEN
50	PyObject *decoding_readline; /* codecs.open(...).readline */
51	PyObject *decoding_buffer;
52#endif
53	const char* enc;
54	const char* str;
55};
56
57extern struct tok_state *PyTokenizer_FromString(const char *);
58extern struct tok_state *PyTokenizer_FromFile(FILE *, char *, char *);
59extern void PyTokenizer_Free(struct tok_state *);
60extern int PyTokenizer_Get(struct tok_state *, char **, char **);
61#if defined(PGEN) || defined(Py_USING_UNICODE)
62extern char * PyTokenizer_RestoreEncoding(struct tok_state* tok, 
63					  int len, int *offset);
64#endif
65
66#ifdef __cplusplus
67}
68#endif
69#endif /* !Py_TOKENIZER_H */