/src/cpython3/Parser/lexer/state.c
Line | Count | Source |
1 | | #include "Python.h" |
2 | | #include "pycore_pystate.h" |
3 | | #include "pycore_token.h" |
4 | | #include "errcode.h" |
5 | | |
6 | | #include "state.h" |
7 | | #include "../tokenizer/reader.h" |
8 | | |
9 | | /* Never change this */ |
10 | 24.5k | #define TABSIZE 8 |
11 | | |
12 | | /* Create and initialize a new tok_state structure */ |
13 | | struct tok_state * |
14 | | _PyTokenizer_tok_new(void) |
15 | 24.5k | { |
16 | 24.5k | struct tok_state *tok = (struct tok_state *)PyMem_Calloc( |
17 | 24.5k | 1, |
18 | 24.5k | sizeof(struct tok_state)); |
19 | 24.5k | if (tok == NULL) { |
20 | 0 | PyErr_NoMemory(); |
21 | 0 | return NULL; |
22 | 0 | } |
23 | | |
24 | 24.5k | tok->buf = tok->cur = tok->inp = NULL; |
25 | 24.5k | tok->fp_interactive = 0; |
26 | 24.5k | tok->interactive_src_start = NULL; |
27 | 24.5k | tok->interactive_src_end = NULL; |
28 | 24.5k | tok->start = NULL; |
29 | 24.5k | tok->end = NULL; |
30 | 24.5k | tok->done = E_OK; |
31 | 24.5k | tok->fp = NULL; |
32 | 24.5k | tok->tabsize = TABSIZE; |
33 | 24.5k | tok->indent = 0; |
34 | 24.5k | tok->indstack[0] = 0; |
35 | 24.5k | tok->atbol = 1; |
36 | 24.5k | tok->pendin = 0; |
37 | 24.5k | tok->prompt = NULL; |
38 | 24.5k | tok->lineno = 0; |
39 | 24.5k | tok->starting_col_offset = -1; |
40 | 24.5k | tok->col_offset = -1; |
41 | 24.5k | tok->level = 0; |
42 | 24.5k | tok->altindstack[0] = 0; |
43 | 24.5k | tok->input_error = 0; |
44 | 24.5k | tok->encoding = NULL; |
45 | 24.5k | tok->filename = NULL; |
46 | 24.5k | tok->module = NULL; |
47 | 24.5k | tok->type_comments = 0; |
48 | 24.5k | tok->interactive_underflow = IUNDERFLOW_NORMAL; |
49 | 24.5k | tok->str = NULL; |
50 | 24.5k | tok->report_warnings = 1; |
51 | 24.5k | tok->tok_extra_tokens = 0; |
52 | 24.5k | tok->comment_newline = 0; |
53 | 24.5k | tok->implicit_newline = 0; |
54 | 24.5k | _PyTok_SourceInit(&tok->source); |
55 | 24.5k | tok->reader = NULL; |
56 | 24.5k | tok->tok_mode_stack[0] = (tokenizer_mode){.kind =TOK_REGULAR_MODE, .quote='\0', .quote_size = 0, .in_debug=0}; |
57 | 24.5k | tok->tok_mode_stack_index = 0; |
58 | | #ifdef Py_DEBUG |
59 | | tok->debug = _Py_GetConfig()->parser_debug; |
60 | | #endif |
61 | 24.5k | return tok; |
62 | 24.5k | } |
63 | | |
64 | | static void |
65 | | free_fstring_expressions(struct tok_state *tok) |
66 | 24.5k | { |
67 | 24.5k | int index; |
68 | 24.5k | tokenizer_mode *mode; |
69 | | |
70 | 57.0k | for (index = tok->tok_mode_stack_index; index >= 0; --index) { |
71 | 32.4k | mode = &(tok->tok_mode_stack[index]); |
72 | 32.4k | if (mode->last_expr_buffer != NULL) { |
73 | 7.70k | PyMem_Free(mode->last_expr_buffer); |
74 | 7.70k | mode->last_expr_buffer = NULL; |
75 | 7.70k | mode->last_expr_size = 0; |
76 | 7.70k | mode->last_expr_end = -1; |
77 | 7.70k | mode->in_format_spec = 0; |
78 | 7.70k | } |
79 | 32.4k | } |
80 | 24.5k | } |
81 | | |
82 | | /* Free a tok_state structure */ |
83 | | void |
84 | | _PyTokenizer_Free(struct tok_state *tok) |
85 | 24.5k | { |
86 | 24.5k | if (tok->encoding != NULL) { |
87 | 15.8k | PyMem_Free(tok->encoding); |
88 | 15.8k | } |
89 | 24.5k | Py_XDECREF(tok->filename); |
90 | 24.5k | Py_XDECREF(tok->module); |
91 | 24.5k | _PyTok_ReaderFree(tok); |
92 | 24.5k | _PyTok_SourceClear(&tok->source); |
93 | 24.5k | free_fstring_expressions(tok); |
94 | 24.5k | PyMem_Free(tok); |
95 | 24.5k | } |
96 | | |
97 | | void |
98 | 5.72k | _PyToken_Free(struct token *token) { |
99 | 5.72k | Py_XDECREF(token->metadata); |
100 | 5.72k | } |
101 | | |
102 | | void |
103 | 5.05M | _PyToken_Init(struct token *token) { |
104 | 5.05M | token->metadata = NULL; |
105 | 5.05M | } |
106 | | |
107 | | int |
108 | | _PyLexer_type_comment_token_setup(struct tok_state *tok, struct token *token, int type, int col_offset, |
109 | | int end_col_offset, const char *start, const char *end) |
110 | 2.37k | { |
111 | 2.37k | token->level = tok->level; |
112 | 2.37k | token->lineno = token->end_lineno = tok->lineno; |
113 | 2.37k | token->col_offset = col_offset; |
114 | 2.37k | token->end_col_offset = end_col_offset; |
115 | 2.37k | token->start = start; |
116 | 2.37k | token->end = end; |
117 | 2.37k | return type; |
118 | 2.37k | } |
119 | | |
120 | | int |
121 | | _PyLexer_token_setup(struct tok_state *tok, struct token *token, int type, const char *start, const char *end) |
122 | 5.22M | { |
123 | 5.22M | assert((start == NULL && end == NULL) || (start != NULL && end != NULL)); |
124 | 5.22M | token->level = tok->level; |
125 | 5.22M | if (ISSTRINGLIT(type)) { |
126 | 126k | token->lineno = tok->first_lineno; |
127 | 126k | } |
128 | 5.09M | else { |
129 | 5.09M | token->lineno = tok->lineno; |
130 | 5.09M | } |
131 | 5.22M | token->end_lineno = tok->lineno; |
132 | 5.22M | token->col_offset = token->end_col_offset = -1; |
133 | 5.22M | token->start = start; |
134 | 5.22M | token->end = end; |
135 | | |
136 | 5.22M | if (start != NULL && end != NULL) { |
137 | 5.16M | token->col_offset = tok->starting_col_offset; |
138 | 5.16M | token->end_col_offset = tok->col_offset; |
139 | 5.16M | } |
140 | 5.22M | return type; |
141 | 5.22M | } |