/src/cpython/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 | | |
8 | | /* Never change this */ |
9 | 110k | #define TABSIZE 8 |
10 | | |
11 | | /* Create and initialize a new tok_state structure */ |
12 | | struct tok_state * |
13 | | _PyTokenizer_tok_new(void) |
14 | 110k | { |
15 | 110k | struct tok_state *tok = (struct tok_state *)PyMem_Calloc( |
16 | 110k | 1, |
17 | 110k | sizeof(struct tok_state)); |
18 | 110k | if (tok == NULL) { |
19 | 0 | PyErr_NoMemory(); |
20 | 0 | return NULL; |
21 | 0 | } |
22 | | |
23 | 110k | tok->buf = tok->cur = tok->inp = NULL; |
24 | 110k | tok->fp_interactive = 0; |
25 | 110k | tok->interactive_src_start = NULL; |
26 | 110k | tok->interactive_src_end = NULL; |
27 | 110k | tok->start = NULL; |
28 | 110k | tok->end = NULL; |
29 | 110k | tok->done = E_OK; |
30 | 110k | tok->fp = NULL; |
31 | 110k | tok->input = NULL; |
32 | 110k | tok->tabsize = TABSIZE; |
33 | 110k | tok->indent = 0; |
34 | 110k | tok->indstack[0] = 0; |
35 | 110k | tok->atbol = 1; |
36 | 110k | tok->pendin = 0; |
37 | 110k | tok->prompt = tok->nextprompt = NULL; |
38 | 110k | tok->lineno = 0; |
39 | 110k | tok->starting_col_offset = -1; |
40 | 110k | tok->col_offset = -1; |
41 | 110k | tok->level = 0; |
42 | 110k | tok->altindstack[0] = 0; |
43 | 110k | tok->decoding_state = STATE_INIT; |
44 | 110k | tok->decoding_erred = 0; |
45 | 110k | tok->enc = NULL; |
46 | 110k | tok->encoding = NULL; |
47 | 110k | tok->cont_line = 0; |
48 | 110k | tok->filename = NULL; |
49 | 110k | tok->module = NULL; |
50 | 110k | tok->decoding_readline = NULL; |
51 | 110k | tok->decoding_buffer = NULL; |
52 | 110k | tok->readline = NULL; |
53 | 110k | tok->type_comments = 0; |
54 | 110k | tok->interactive_underflow = IUNDERFLOW_NORMAL; |
55 | 110k | tok->underflow = NULL; |
56 | 110k | tok->str = NULL; |
57 | 110k | tok->report_warnings = 1; |
58 | 110k | tok->tok_extra_tokens = 0; |
59 | 110k | tok->comment_newline = 0; |
60 | 110k | tok->implicit_newline = 0; |
61 | 110k | tok->tok_mode_stack[0] = (tokenizer_mode){.kind =TOK_REGULAR_MODE, .quote='\0', .quote_size = 0, .in_debug=0}; |
62 | 110k | tok->tok_mode_stack_index = 0; |
63 | | #ifdef Py_DEBUG |
64 | | tok->debug = _Py_GetConfig()->parser_debug; |
65 | | #endif |
66 | 110k | return tok; |
67 | 110k | } |
68 | | |
69 | | static void |
70 | | free_fstring_expressions(struct tok_state *tok) |
71 | 110k | { |
72 | 110k | int index; |
73 | 110k | tokenizer_mode *mode; |
74 | | |
75 | 224k | for (index = tok->tok_mode_stack_index; index >= 0; --index) { |
76 | 114k | mode = &(tok->tok_mode_stack[index]); |
77 | 114k | if (mode->last_expr_buffer != NULL) { |
78 | 4.08k | PyMem_Free(mode->last_expr_buffer); |
79 | 4.08k | mode->last_expr_buffer = NULL; |
80 | 4.08k | mode->last_expr_size = 0; |
81 | 4.08k | mode->last_expr_end = -1; |
82 | 4.08k | mode->in_format_spec = 0; |
83 | 4.08k | } |
84 | 114k | } |
85 | 110k | } |
86 | | |
87 | | /* Free a tok_state structure */ |
88 | | void |
89 | | _PyTokenizer_Free(struct tok_state *tok) |
90 | 110k | { |
91 | 110k | if (tok->encoding != NULL) { |
92 | 93.4k | PyMem_Free(tok->encoding); |
93 | 93.4k | } |
94 | 110k | Py_XDECREF(tok->decoding_readline); |
95 | 110k | Py_XDECREF(tok->decoding_buffer); |
96 | 110k | Py_XDECREF(tok->readline); |
97 | 110k | Py_XDECREF(tok->filename); |
98 | 110k | Py_XDECREF(tok->module); |
99 | 110k | if ((tok->readline != NULL || tok->fp != NULL ) && tok->buf != NULL) { |
100 | 20 | PyMem_Free(tok->buf); |
101 | 20 | } |
102 | 110k | if (tok->input) { |
103 | 110k | PyMem_Free(tok->input); |
104 | 110k | } |
105 | 110k | if (tok->interactive_src_start != NULL) { |
106 | 0 | PyMem_Free(tok->interactive_src_start); |
107 | 0 | } |
108 | 110k | free_fstring_expressions(tok); |
109 | 110k | PyMem_Free(tok); |
110 | 110k | } |
111 | | |
112 | | void |
113 | 98.1k | _PyToken_Free(struct token *token) { |
114 | 98.1k | Py_XDECREF(token->metadata); |
115 | 98.1k | } |
116 | | |
117 | | void |
118 | 1.87M | _PyToken_Init(struct token *token) { |
119 | 1.87M | token->metadata = NULL; |
120 | 1.87M | } |
121 | | |
122 | | int |
123 | | _PyLexer_type_comment_token_setup(struct tok_state *tok, struct token *token, int type, int col_offset, |
124 | | int end_col_offset, const char *start, const char *end) |
125 | 0 | { |
126 | 0 | token->level = tok->level; |
127 | 0 | token->lineno = token->end_lineno = tok->lineno; |
128 | 0 | token->col_offset = col_offset; |
129 | 0 | token->end_col_offset = end_col_offset; |
130 | 0 | token->start = start; |
131 | 0 | token->end = end; |
132 | 0 | return type; |
133 | 0 | } |
134 | | |
135 | | int |
136 | | _PyLexer_token_setup(struct tok_state *tok, struct token *token, int type, const char *start, const char *end) |
137 | 2.18M | { |
138 | 2.18M | assert((start == NULL && end == NULL) || (start != NULL && end != NULL)); |
139 | 2.18M | token->level = tok->level; |
140 | 2.18M | if (ISSTRINGLIT(type)) { |
141 | 64.0k | token->lineno = tok->first_lineno; |
142 | 64.0k | } |
143 | 2.12M | else { |
144 | 2.12M | token->lineno = tok->lineno; |
145 | 2.12M | } |
146 | 2.18M | token->end_lineno = tok->lineno; |
147 | 2.18M | token->col_offset = token->end_col_offset = -1; |
148 | 2.18M | token->start = start; |
149 | 2.18M | token->end = end; |
150 | | |
151 | 2.18M | if (start != NULL && end != NULL) { |
152 | 2.06M | token->col_offset = tok->starting_col_offset; |
153 | 2.06M | token->end_col_offset = tok->col_offset; |
154 | 2.06M | } |
155 | 2.18M | return type; |
156 | 2.18M | } |