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