Repository navigation
Expand file tree
/
Copy pathstring_parser.c
More file actions
264 lines (246 loc) · 7.62 KB
/
Copy pathstring_parser.c
File metadata and controls
264 lines (246 loc) · 7.62 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
#include <stdbool.h>
#include <Python.h>
#include "tokenizer.h"
#include "pegen.h"
#include "string_parser.h"
//// STRING HANDLING FUNCTIONS ////
static int
warn_invalid_escape_sequence(Parser *p, const char *first_invalid_escape, Token *t)
{
unsigned char c = *first_invalid_escape;
int octal = ('4' <= c && c <= '7');
PyObject *msg =
octal
? PyUnicode_FromFormat("invalid octal escape sequence '\\%.3s'",
first_invalid_escape)
: PyUnicode_FromFormat("invalid escape sequence '\\%c'", c);
if (msg == NULL) {
return -1;
}
PyObject *category;
if (p->feature_version >= 12) {
category = PyExc_SyntaxWarning;
}
else {
category = PyExc_DeprecationWarning;
}
if (PyErr_WarnExplicitObject(category, msg, p->tok->filename,
t->lineno, NULL, NULL) < 0) {
if (PyErr_ExceptionMatches(category)) {
/* Replace the DeprecationWarning exception with a SyntaxError
to get a more accurate error report */
PyErr_Clear();
/* This is needed, in order for the SyntaxError to point to the token t,
since _PyPegen_raise_error uses p->tokens[p->fill - 1] for the
error location, if p->known_err_token is not set. */
p->known_err_token = t;
if (octal) {
RAISE_SYNTAX_ERROR("invalid octal escape sequence '\\%.3s'",
first_invalid_escape);
}
else {
RAISE_SYNTAX_ERROR("invalid escape sequence '\\%c'", c);
}
}
Py_DECREF(msg);
return -1;
}
Py_DECREF(msg);
return 0;
}
static PyObject *
decode_utf8(const char **sPtr, const char *end)
{
const char *s;
const char *t;
t = s = *sPtr;
while (s < end && (*s & 0x80)) {
s++;
}
*sPtr = s;
return PyUnicode_DecodeUTF8(t, s - t, NULL);
}
static PyObject *
decode_unicode_with_escapes(Parser *parser, const char *s, size_t len, Token *t)
{
PyObject *v;
PyObject *u;
char *buf;
char *p;
const char *end;
/* check for integer overflow */
if (len > SIZE_MAX / 6) {
return NULL;
}
/* "ä" (2 bytes) may become "\U000000E4" (10 bytes), or 1:5
"\ä" (3 bytes) may become "\u005c\U000000E4" (16 bytes), or ~1:6 */
u = PyBytes_FromStringAndSize((char *)NULL, len * 6);
if (u == NULL) {
return NULL;
}
p = buf = PyBytes_AsString(u);
if (p == NULL) {
return NULL;
}
end = s + len;
while (s < end) {
if (*s == '\\') {
*p++ = *s++;
if (s >= end || *s & 0x80) {
strcpy(p, "u005c");
p += 5;
if (s >= end) {
break;
}
}
}
if (*s & 0x80) {
PyObject *w;
int kind;
const void *data;
Py_ssize_t w_len;
Py_ssize_t i;
w = decode_utf8(&s, end);
if (w == NULL) {
Py_DECREF(u);
return NULL;
}
kind = PyUnicode_KIND(w);
data = PyUnicode_DATA(w);
w_len = PyUnicode_GET_LENGTH(w);
for (i = 0; i < w_len; i++) {
Py_UCS4 chr = PyUnicode_READ(kind, data, i);
sprintf(p, "\\U%08x", chr);
p += 10;
}
/* Should be impossible to overflow */
assert(p - buf <= PyBytes_GET_SIZE(u));
Py_DECREF(w);
}
else {
*p++ = *s++;
}
}
len = p - buf;
s = buf;
const char *first_invalid_escape;
v = _PyUnicode_DecodeUnicodeEscapeInternal(s, len, NULL, NULL, &first_invalid_escape);
// HACK: later we can simply pass the line no, since we don't preserve the tokens
// when we are decoding the string but we preserve the line numbers.
if (v != NULL && first_invalid_escape != NULL && t != NULL) {
if (warn_invalid_escape_sequence(parser, first_invalid_escape, t) < 0) {
/* We have not decref u before because first_invalid_escape points
inside u. */
Py_XDECREF(u);
Py_DECREF(v);
return NULL;
}
}
Py_XDECREF(u);
return v;
}
static PyObject *
decode_bytes_with_escapes(Parser *p, const char *s, Py_ssize_t len, Token *t)
{
const char *first_invalid_escape;
PyObject *result = _PyBytes_DecodeEscape(s, len, NULL, &first_invalid_escape);
if (result == NULL) {
return NULL;
}
if (first_invalid_escape != NULL) {
if (warn_invalid_escape_sequence(p, first_invalid_escape, t) < 0) {
Py_DECREF(result);
return NULL;
}
}
return result;
}
PyObject *
_PyPegen_decode_string(Parser *p, int raw, const char *s, size_t len, Token *t)
{
if (raw) {
return PyUnicode_DecodeUTF8Stateful(s, len, NULL, NULL);
}
return decode_unicode_with_escapes(p, s, len, t);
}
/* s must include the bracketing quote characters, and r, b &/or f prefixes
(if any), and embedded escape sequences (if any). (f-strings are handled by the parser)
_PyPegen_parse_string parses it, and returns the decoded Python string object. */
PyObject *
_PyPegen_parse_string(Parser *p, Token *t)
{
const char *s = PyBytes_AsString(t->bytes);
if (s == NULL) {
return NULL;
}
size_t len;
int quote = Py_CHARMASK(*s);
int bytesmode = 0;
int rawmode = 0;
if (Py_ISALPHA(quote)) {
while (!bytesmode || !rawmode) {
if (quote == 'b' || quote == 'B') {
quote =(unsigned char)*++s;
bytesmode = 1;
}
else if (quote == 'u' || quote == 'U') {
quote = (unsigned char)*++s;
}
else if (quote == 'r' || quote == 'R') {
quote = (unsigned char)*++s;
rawmode = 1;
}
else {
break;
}
}
}
if (quote != '\'' && quote != '\"') {
PyErr_BadInternalCall();
return NULL;
}
/* Skip the leading quote char. */
s++;
len = strlen(s);
if (len > INT_MAX) {
PyErr_SetString(PyExc_OverflowError, "string to parse is too long");
return NULL;
}
if (s[--len] != quote) {
/* Last quote char must match the first. */
PyErr_BadInternalCall();
return NULL;
}
if (len >= 4 && s[0] == quote && s[1] == quote) {
/* A triple quoted string. We've already skipped one quote at
the start and one at the end of the string. Now skip the
two at the start. */
s += 2;
len -= 2;
/* And check that the last two match. */
if (s[--len] != quote || s[--len] != quote) {
PyErr_BadInternalCall();
return NULL;
}
}
/* Avoid invoking escape decoding routines if possible. */
rawmode = rawmode || strchr(s, '\\') == NULL;
if (bytesmode) {
/* Disallow non-ASCII characters. */
const char *ch;
for (ch = s; *ch; ch++) {
if (Py_CHARMASK(*ch) >= 0x80) {
RAISE_SYNTAX_ERROR_KNOWN_LOCATION(
t,
"bytes can only contain ASCII "
"literal characters");
return NULL;
}
}
if (rawmode) {
return PyBytes_FromStringAndSize(s, len);
}
return decode_bytes_with_escapes(p, s, len, t);
}
return _PyPegen_decode_string(p, rawmode, s, len, t);
}