| 1 |
#include "Python.h" |
| 2 |
#include "pycore_pystate.h" |
| 3 |
#include "pycore_token.h" |
| 4 |
#include "errcode.h" |
| 5 |
|
| 6 |
#include "state.h" |
| 7 |
|
| 8 |
/* Never change this */ |
| 9 |
#define TABSIZE 8 |
| 10 |
|
| 11 |
/* Create and initialize a new tok_state structure */ |
| 12 |
struct tok_state * |
| 13 |
_PyTokenizer_tok_new(void) |
| 14 |
{ |
| 15 |
struct tok_state *tok = (struct tok_state *)PyMem_Calloc( |
| 16 |
1, |
| 17 |
sizeof(struct tok_state)); |
| 18 |
if (tok == NULL) |
| 19 |
return NULL; |
| 20 |
tok->buf = tok->cur = tok->inp = NULL; |
| 21 |
tok->fp_interactive = 0; |
| 22 |
tok->interactive_src_start = NULL; |
| 23 |
tok->interactive_src_end = NULL; |
| 24 |
tok->start = NULL; |
| 25 |
tok->end = NULL; |
| 26 |
tok->done = E_OK; |
| 27 |
tok->fp = NULL; |
| 28 |
tok->input = NULL; |
| 29 |
tok->tabsize = TABSIZE; |
| 30 |
tok->indent = 0; |
| 31 |
tok->indstack[0] = 0; |
| 32 |
tok->atbol = 1; |
| 33 |
tok->pendin = 0; |
| 34 |
tok->prompt = tok->nextprompt = NULL; |
| 35 |
tok->lineno = 0; |
| 36 |
tok->starting_col_offset = -1; |
| 37 |
tok->col_offset = -1; |
| 38 |
tok->level = 0; |
| 39 |
tok->altindstack[0] = 0; |
| 40 |
tok->decoding_state = STATE_INIT; |
| 41 |
tok->decoding_erred = 0; |
| 42 |
tok->enc = NULL; |
| 43 |
tok->encoding = NULL; |
| 44 |
tok->cont_line = 0; |
| 45 |
tok->filename = NULL; |
| 46 |
tok->decoding_readline = NULL; |
| 47 |
tok->decoding_buffer = NULL; |
| 48 |
tok->readline = NULL; |
| 49 |
tok->type_comments = 0; |
| 50 |
tok->interactive_underflow = IUNDERFLOW_NORMAL; |
| 51 |
tok->underflow = NULL; |
| 52 |
tok->str = NULL; |
| 53 |
tok->report_warnings = 1; |
| 54 |
tok->tok_extra_tokens = 0; |
| 55 |
tok->comment_newline = 0; |
| 56 |
tok->implicit_newline = 0; |
| 57 |
tok->tok_mode_stack[0] = (tokenizer_mode){.kind =TOK_REGULAR_MODE, .quote='\0', .quote_size = 0, .in_debug=0}; |
| 58 |
tok->tok_mode_stack_index = 0; |
| 59 |
#ifdef Py_DEBUG |
| 60 |
tok->debug = _Py_GetConfig()->parser_debug; |
| 61 |
#endif |
| 62 |
return tok; |
| 63 |
} |
| 64 |
|
| 65 |
static void |
| 66 |
free_fstring_expressions(struct tok_state *tok) |
| 67 |
{ |
| 68 |
int index; |
| 69 |
tokenizer_mode *mode; |
| 70 |
|
| 71 |
for (index = tok->tok_mode_stack_index; index >= 0; --index) { |
| 72 |
mode = &(tok->tok_mode_stack[index]); |
| 73 |
if (mode->last_expr_buffer != NULL) { |
| 74 |
PyMem_Free(mode->last_expr_buffer); |
| 75 |
mode->last_expr_buffer = NULL; |
| 76 |
mode->last_expr_size = 0; |
| 77 |
mode->last_expr_end = -1; |
| 78 |
mode->in_format_spec = 0; |
| 79 |
} |
| 80 |
} |
| 81 |
} |
| 82 |
|
| 83 |
/* Free a tok_state structure */ |
| 84 |
void |
| 85 |
_PyTokenizer_Free(struct tok_state *tok) |
| 86 |
{ |
| 87 |
if (tok->encoding != NULL) { |
| 88 |
PyMem_Free(tok->encoding); |
| 89 |
} |
| 90 |
Py_XDECREF(tok->decoding_readline); |
| 91 |
Py_XDECREF(tok->decoding_buffer); |
| 92 |
Py_XDECREF(tok->readline); |
| 93 |
Py_XDECREF(tok->filename); |
| 94 |
if ((tok->readline != NULL || tok->fp != NULL ) && tok->buf != NULL) { |
| 95 |
PyMem_Free(tok->buf); |
| 96 |
} |
| 97 |
if (tok->input) { |
| 98 |
PyMem_Free(tok->input); |
| 99 |
} |
| 100 |
if (tok->interactive_src_start != NULL) { |
| 101 |
PyMem_Free(tok->interactive_src_start); |
| 102 |
} |
| 103 |
free_fstring_expressions(tok); |
| 104 |
PyMem_Free(tok); |
| 105 |
} |
| 106 |
|
| 107 |
void |
| 108 |
_PyToken_Free(struct token *token) { |
| 109 |
Py_XDECREF(token->metadata); |
| 110 |
} |
| 111 |
|
| 112 |
void |
| 113 |
_PyToken_Init(struct token *token) { |
| 114 |
token->metadata = NULL; |
| 115 |
} |
| 116 |
|
| 117 |
int |
| 118 |
_PyLexer_type_comment_token_setup(struct tok_state *tok, struct token *token, int type, int col_offset, |
| 119 |
int end_col_offset, const char *start, const char *end) |
| 120 |
{ |
| 121 |
token->level = tok->level; |
| 122 |
token->lineno = token->end_lineno = tok->lineno; |
| 123 |
token->col_offset = col_offset; |
| 124 |
token->end_col_offset = end_col_offset; |
| 125 |
token->start = start; |
| 126 |
token->end = end; |
| 127 |
return type; |
| 128 |
} |
| 129 |
|
| 130 |
int |
| 131 |
_PyLexer_token_setup(struct tok_state *tok, struct token *token, int type, const char *start, const char *end) |
| 132 |
{ |
| 133 |
assert((start == NULL && end == NULL) || (start != NULL && end != NULL)); |
| 134 |
token->level = tok->level; |
| 135 |
if (ISSTRINGLIT(type)) { |
| 136 |
token->lineno = tok->first_lineno; |
| 137 |
} |
| 138 |
else { |
| 139 |
token->lineno = tok->lineno; |
| 140 |
} |
| 141 |
token->end_lineno = tok->lineno; |
| 142 |
token->col_offset = token->end_col_offset = -1; |
| 143 |
token->start = start; |
| 144 |
token->end = end; |
| 145 |
|
| 146 |
if (start != NULL && end != NULL) { |
| 147 |
token->col_offset = tok->starting_col_offset; |
| 148 |
token->end_col_offset = tok->col_offset; |
| 149 |
} |
| 150 |
return type; |
| 151 |
} |