cpython/Parser/tokenizer.h
Georg Brandl f55aa80b37 Merged revisions 85820,85823,85825,85840,85843-85845,85849-85851,85855,85867,85875,85907-85908,85911,85914 via svnmerge from
svn+ssh://svn.python.org/python/branches/py3k

........
  r85820 | georg.brandl | 2010-10-24 16:20:22 +0200 (So, 24 Okt 2010) | 1 line

  Remove usage of exception indexing.
........
  r85823 | georg.brandl | 2010-10-24 16:32:45 +0200 (So, 24 Okt 2010) | 1 line

  Fix style.
........
  r85825 | georg.brandl | 2010-10-24 17:16:02 +0200 (So, 24 Okt 2010) | 1 line

  Add documentation about the default warnings filters.
........
  r85840 | georg.brandl | 2010-10-25 19:50:20 +0200 (Mo, 25 Okt 2010) | 1 line

  #3018: tkinter demo fixes for py3k.
........
  r85843 | georg.brandl | 2010-10-26 08:59:23 +0200 (Di, 26 Okt 2010) | 1 line

  Markup fix.
........
  r85844 | georg.brandl | 2010-10-26 12:39:14 +0200 (Di, 26 Okt 2010) | 1 line

  Work a bit more on tkinter demos.
........
  r85845 | georg.brandl | 2010-10-26 12:42:16 +0200 (Di, 26 Okt 2010) | 1 line

  faqwiz is removed.
........
  r85849 | georg.brandl | 2010-10-26 21:31:06 +0200 (Di, 26 Okt 2010) | 1 line

  #10200: typo.
........
  r85850 | georg.brandl | 2010-10-26 21:58:11 +0200 (Di, 26 Okt 2010) | 1 line

  #10200: typo.
........
  r85851 | georg.brandl | 2010-10-26 22:12:37 +0200 (Di, 26 Okt 2010) | 1 line

  Fix import.
........
  r85855 | georg.brandl | 2010-10-27 09:21:54 +0200 (Mi, 27 Okt 2010) | 1 line

  Encoding fix.
........
  r85867 | georg.brandl | 2010-10-27 22:01:51 +0200 (Mi, 27 Okt 2010) | 1 line

  Add David.
........
  r85875 | georg.brandl | 2010-10-28 10:38:30 +0200 (Do, 28 Okt 2010) | 1 line

  Fix bytes/str issues in get-remote-certificate.py.
........
  r85907 | georg.brandl | 2010-10-29 06:54:13 +0200 (Fr, 29 Okt 2010) | 1 line

  #10222: fix for overzealous AIX compiler.
........
  r85908 | georg.brandl | 2010-10-29 07:22:17 +0200 (Fr, 29 Okt 2010) | 1 line

  send_bytes obviously needs bytes...
........
  r85911 | georg.brandl | 2010-10-29 07:36:28 +0200 (Fr, 29 Okt 2010) | 1 line

  Fix markup error and update false positive entries from "make suspicious".
........
  r85914 | georg.brandl | 2010-10-29 08:17:38 +0200 (Fr, 29 Okt 2010) | 1 line

  (?:...) is a non-capturing, but still grouping construct.
........
2010-11-26 08:59:40 +00:00

78 lines
3.2 KiB
C

#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; /* encoded to the filesystem encoding */
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. */
};
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 *, 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 */