| 1 |
#ifndef _PY_LEXER_H_ |
| 2 |
#define _PY_LEXER_H_ |
| 3 |
|
| 4 |
#include "object.h" |
| 5 |
|
| 6 |
#define MAXINDENT 100 /* Max indentation level */ |
| 7 |
#define MAXLEVEL 200 /* Max parentheses level */ |
| 8 |
#define MAXFSTRINGLEVEL 150 /* Max f-string nesting level */ |
| 9 |
|
| 10 |
#define INSIDE_FSTRING(tok) (tok->tok_mode_stack_index > 0) |
| 11 |
#define INSIDE_FSTRING_EXPR(tok) (tok->curly_bracket_expr_start_depth >= 0) |
| 12 |
#define INSIDE_FSTRING_EXPR_AT_TOP(tok) \ |
| 13 |
(tok->curly_bracket_depth - tok->curly_bracket_expr_start_depth == 1) |
| 14 |
|
| 15 |
enum decoding_state { |
| 16 |
STATE_INIT, |
| 17 |
STATE_SEEK_CODING, |
| 18 |
STATE_NORMAL |
| 19 |
}; |
| 20 |
|
| 21 |
enum interactive_underflow_t { |
| 22 |
/* Normal mode of operation: return a new token when asked in interactive mode */ |
| 23 |
IUNDERFLOW_NORMAL, |
| 24 |
/* Forcefully return ENDMARKER when asked for a new token in interactive mode. This |
| 25 |
* can be used to prevent the tokenizer to prompt the user for new tokens */ |
| 26 |
IUNDERFLOW_STOP, |
| 27 |
}; |
| 28 |
|
| 29 |
struct token { |
| 30 |
int level; |
| 31 |
int lineno, col_offset, end_lineno, end_col_offset; |
| 32 |
const char *start, *end; |
| 33 |
PyObject *metadata; |
| 34 |
}; |
| 35 |
|
| 36 |
enum tokenizer_mode_kind_t { |
| 37 |
TOK_REGULAR_MODE, |
| 38 |
TOK_FSTRING_MODE, |
| 39 |
}; |
| 40 |
|
| 41 |
enum string_kind_t { |
| 42 |
FSTRING, |
| 43 |
TSTRING, |
| 44 |
}; |
| 45 |
|
| 46 |
#define MAX_EXPR_NESTING 3 |
| 47 |
|
| 48 |
typedef struct _tokenizer_mode { |
| 49 |
enum tokenizer_mode_kind_t kind; |
| 50 |
|
| 51 |
int curly_bracket_depth; |
| 52 |
int curly_bracket_expr_start_depth; |
| 53 |
|
| 54 |
char quote; |
| 55 |
int quote_size; |
| 56 |
int raw; |
| 57 |
const char* start; |
| 58 |
const char* multi_line_start; |
| 59 |
int first_line; |
| 60 |
|
| 61 |
Py_ssize_t start_offset; |
| 62 |
Py_ssize_t multi_line_start_offset; |
| 63 |
|
| 64 |
Py_ssize_t last_expr_size; |
| 65 |
Py_ssize_t last_expr_end; |
| 66 |
char* last_expr_buffer; |
| 67 |
int in_debug; |
| 68 |
int in_format_spec; |
| 69 |
|
| 70 |
enum string_kind_t string_kind; |
| 71 |
} tokenizer_mode; |
| 72 |
|
| 73 |
/* Tokenizer state */ |
| 74 |
struct tok_state { |
| 75 |
/* Input state; buf <= cur <= inp <= end */ |
| 76 |
/* NB an entire line is held in the buffer */ |
| 77 |
char *buf; /* Input buffer, or NULL; malloc'ed if fp != NULL or readline != NULL */ |
| 78 |
char *cur; /* Next character in buffer */ |
| 79 |
char *inp; /* End of data in buffer */ |
| 80 |
int fp_interactive; /* If the file descriptor is interactive */ |
| 81 |
char *interactive_src_start; /* The start of the source parsed so far in interactive mode */ |
| 82 |
char *interactive_src_end; /* The end of the source parsed so far in interactive mode */ |
| 83 |
const char *end; /* End of input buffer if buf != NULL */ |
| 84 |
const char *start; /* Start of current token if not NULL */ |
| 85 |
int done; /* E_OK normally, E_EOF at EOF, otherwise error code */ |
| 86 |
/* NB If done != E_OK, cur must be == inp!!! */ |
| 87 |
FILE *fp; /* Rest of input; NULL if tokenizing a string */ |
| 88 |
int tabsize; /* Tab spacing */ |
| 89 |
int indent; /* Current indentation index */ |
| 90 |
int indstack[MAXINDENT]; /* Stack of indents */ |
| 91 |
int atbol; /* Nonzero if at begin of new line */ |
| 92 |
int pendin; /* Pending indents (if > 0) or dedents (if < 0) */ |
| 93 |
const char *prompt, *nextprompt; /* For interactive prompting */ |
| 94 |
int lineno; /* Current line number */ |
| 95 |
int first_lineno; /* First line of a single line or multi line string |
| 96 |
expression (cf. issue 16806) */ |
| 97 |
int starting_col_offset; /* The column offset at the beginning of a token */ |
| 98 |
int col_offset; /* Current col offset */ |
| 99 |
int level; /* () [] {} Parentheses nesting level */ |
| 100 |
/* Used to allow free continuations inside them */ |
| 101 |
char parenstack[MAXLEVEL]; |
| 102 |
int parenlinenostack[MAXLEVEL]; |
| 103 |
int parencolstack[MAXLEVEL]; |
| 104 |
PyObject *filename; |
| 105 |
/* Stuff for checking on different tab sizes */ |
| 106 |
int altindstack[MAXINDENT]; /* Stack of alternate indents */ |
| 107 |
/* Stuff for PEP 0263 */ |
| 108 |
enum decoding_state decoding_state; |
| 109 |
int decoding_erred; /* whether erred in decoding */ |
| 110 |
char *encoding; /* Source encoding. */ |
| 111 |
int cont_line; /* whether we are in a continuation line. */ |
| 112 |
const char* line_start; /* pointer to start of current line */ |
| 113 |
const char* multi_line_start; /* pointer to start of first line of |
| 114 |
a single line or multi line string |
| 115 |
expression (cf. issue 16806) */ |
| 116 |
PyObject *decoding_readline; /* open(...).readline */ |
| 117 |
PyObject *decoding_buffer; |
| 118 |
PyObject *readline; /* readline() function */ |
| 119 |
const char* enc; /* Encoding for the current str. */ |
| 120 |
char* str; /* Source string being tokenized (if tokenizing from a string)*/ |
| 121 |
char* input; /* Tokenizer's newline translated copy of the string. */ |
| 122 |
|
| 123 |
int type_comments; /* Whether to look for type comments */ |
| 124 |
|
| 125 |
/* How to proceed when asked for a new token in interactive mode */ |
| 126 |
enum interactive_underflow_t interactive_underflow; |
| 127 |
int (*underflow)(struct tok_state *); /* Function to call when buffer is empty and we need to refill it*/ |
| 128 |
|
| 129 |
int report_warnings; |
| 130 |
// TODO: Factor this into its own thing |
| 131 |
tokenizer_mode tok_mode_stack[MAXFSTRINGLEVEL]; |
| 132 |
int tok_mode_stack_index; |
| 133 |
int tok_extra_tokens; |
| 134 |
int comment_newline; |
| 135 |
int implicit_newline; |
| 136 |
#ifdef Py_DEBUG |
| 137 |
int debug; |
| 138 |
#endif |
| 139 |
}; |
| 140 |
|
| 141 |
int _PyLexer_type_comment_token_setup(struct tok_state *tok, struct token *token, int type, int col_offset, |
| 142 |
int end_col_offset, const char *start, const char *end); |
| 143 |
int _PyLexer_token_setup(struct tok_state *tok, struct token *token, int type, const char *start, const char *end); |
| 144 |
|
| 145 |
struct tok_state *_PyTokenizer_tok_new(void); |
| 146 |
void _PyTokenizer_Free(struct tok_state *); |
| 147 |
void _PyToken_Free(struct token *); |
| 148 |
void _PyToken_Init(struct token *); |
| 149 |
|
| 150 |
|
| 151 |
#endif |