Merged revisions 77389 via svnmerge from
[python/dscho.git] / Parser / tokenizer.h
blobe3328f1a5865defdf5a3a233aa369c88d5a28ce0
1 #ifndef Py_TOKENIZER_H
2 #define Py_TOKENIZER_H
3 #ifdef __cplusplus
4 extern "C" {
5 #endif
7 #include "object.h"
9 /* Tokenizer interface */
11 #include "token.h" /* For token types */
13 #define MAXINDENT 100 /* Max indentation level */
15 enum decoding_state {
16 STATE_INIT,
17 STATE_RAW,
18 STATE_NORMAL, /* have a codec associated with input */
21 /* Tokenizer state */
22 struct tok_state {
23 /* Input state; buf <= cur <= inp <= end */
24 /* NB an entire line is held in the buffer */
25 char *buf; /* Input buffer, or NULL; malloc'ed if fp != NULL */
26 char *cur; /* Next character in buffer */
27 char *inp; /* End of data in buffer */
28 char *end; /* End of input buffer if buf != NULL */
29 char *start; /* Start of current token if not NULL */
30 int done; /* E_OK normally, E_EOF at EOF, otherwise error code */
31 /* NB If done != E_OK, cur must be == inp!!! */
32 FILE *fp; /* Rest of input; NULL if tokenizing a string */
33 int tabsize; /* Tab spacing */
34 int indent; /* Current indentation index */
35 int indstack[MAXINDENT]; /* Stack of indents */
36 int atbol; /* Nonzero if at begin of new line */
37 int pendin; /* Pending indents (if > 0) or dedents (if < 0) */
38 char *prompt, *nextprompt; /* For interactive prompting */
39 int lineno; /* Current line number */
40 int level; /* () [] {} Parentheses nesting level */
41 /* Used to allow free continuations inside them */
42 /* Stuff for checking on different tab sizes */
43 const char *filename; /* For error messages */
44 int altwarning; /* Issue warning if alternate tabs don't match */
45 int alterror; /* Issue error if alternate tabs don't match */
46 int alttabsize; /* Alternate tab spacing */
47 int altindstack[MAXINDENT]; /* Stack of alternate indents */
48 /* Stuff for PEP 0263 */
49 enum decoding_state decoding_state;
50 int decoding_erred; /* whether erred in decoding */
51 int read_coding_spec; /* whether 'coding:...' has been read */
52 char *encoding; /* Source encoding. */
53 int cont_line; /* whether we are in a continuation line. */
54 const char* line_start; /* pointer to start of current line */
55 #ifndef PGEN
56 PyObject *decoding_readline; /* codecs.open(...).readline */
57 PyObject *decoding_buffer;
58 #endif
59 const char* enc; /* Encoding for the current str. */
60 const char* str;
63 extern struct tok_state *PyTokenizer_FromString(const char *);
64 extern struct tok_state *PyTokenizer_FromUTF8(const char *);
65 extern struct tok_state *PyTokenizer_FromFile(FILE *, char*,
66 char *, char *);
67 extern void PyTokenizer_Free(struct tok_state *);
68 extern int PyTokenizer_Get(struct tok_state *, char **, char **);
69 extern char * PyTokenizer_RestoreEncoding(struct tok_state* tok,
70 int len, int *offset);
71 extern char * PyTokenizer_FindEncoding(int);
73 #ifdef __cplusplus
75 #endif
76 #endif /* !Py_TOKENIZER_H */