mirror of
https://github.com/python/cpython
synced 2024-09-05 16:38:56 +00:00
e5fe509054
When trying to extract the error line for the error message there
are two distinct cases:
1. The input comes from a file, which means that we can extract the
error line by using `PyErr_ProgramTextObject` and which we already
do.
2. The input does not come from a file, at which point we need to get
the source code from the tokenizer:
* If the tokenizer's current line number is the same with the line
of the error, we get the line from `tok->buf` and we're ready.
* Else, we can extract the error line from the source code in the
following two ways:
* If the input comes from a string we have all the input
in `tok->str` and we can extract the error line from it.
* If the input comes from stdin, i.e. the interactive prompt, we
do not have access to the previous line. That's why a new
field `tok->stdin_content` is added which holds the whole input for the
current (multiline) statement or expression. We can then extract the
error line from `tok->stdin_content` like we do in the string case above.
Co-authored-by: Pablo Galindo <Pablogsal@gmail.com>
90 lines
3.8 KiB
C
90 lines
3.8 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 */
|
|
#define MAXLEVEL 200 /* Max parentheses 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 */
|
|
const char *end; /* End of input buffer if buf != NULL */
|
|
const 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 */
|
|
char *stdin_content;
|
|
int lineno; /* Current line number */
|
|
int first_lineno; /* First line of a single line or multi line string
|
|
expression (cf. issue 16806) */
|
|
int level; /* () [] {} Parentheses nesting level */
|
|
/* Used to allow free continuations inside them */
|
|
char parenstack[MAXLEVEL];
|
|
int parenlinenostack[MAXLEVEL];
|
|
PyObject *filename;
|
|
/* Stuff for checking on different tab sizes */
|
|
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 */
|
|
const char* multi_line_start; /* pointer to start of first line of
|
|
a single line or multi line string
|
|
expression (cf. issue 16806) */
|
|
PyObject *decoding_readline; /* open(...).readline */
|
|
PyObject *decoding_buffer;
|
|
const char* enc; /* Encoding for the current str. */
|
|
char* str;
|
|
char* input; /* Tokenizer's newline translated copy of the string. */
|
|
|
|
int type_comments; /* Whether to look for type comments */
|
|
|
|
/* async/await related fields (still needed depending on feature_version) */
|
|
int async_hacks; /* =1 if async/await aren't always keywords */
|
|
int async_def; /* =1 if tokens are inside an 'async def' body. */
|
|
int async_def_indent; /* Indentation level of the outermost 'async def'. */
|
|
int async_def_nl; /* =1 if the outermost 'async def' had at least one
|
|
NEWLINE token after it. */
|
|
};
|
|
|
|
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 *, const char **, const char **);
|
|
|
|
#define tok_dump _Py_tok_dump
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
#endif /* !Py_TOKENIZER_H */
|