Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Commitbd49471

Browse files
committed
gh-135148: Correctly handle f/t strings with comments and debug expressions
1 parent1ffe913 commitbd49471

File tree

2 files changed

+78
-13
lines changed

2 files changed

+78
-13
lines changed

‎Lib/test/test_fstring.py‎

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1651,6 +1651,12 @@ def __repr__(self):
16511651
self.assertEqual(f"{1+2=# my comment
16521652
}",'1+2 =\n 3')
16531653

1654+
self.assertEqual(f'{""" # booo
1655+
"""=}','""" # booo\n """=\' # booo\\n\'')
1656+
1657+
self.assertEqual(f'{" # nooo "=}','" # nooo "=\' # nooo\'')
1658+
self.assertEqual(f'{"\" # nooo\" "=}','"\\" # nooo\\" "=\' " # nooo "\'')
1659+
16541660
# These next lines contains tabs. Backslash escapes don't
16551661
# work in f-strings.
16561662
# patchcheck doesn't like these tabs. So the only way to test

‎Parser/lexer/lexer.c‎

Lines changed: 72 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -123,35 +123,96 @@ set_ftstring_expr(struct tok_state* tok, struct token *token, char c) {
123123

124124
// Check if there is a # character in the expression
125125
inthash_detected=0;
126+
intin_string=0;
127+
charstring_quote=0;
126128
for (Py_ssize_ti=0;i<tok_mode->last_expr_size-tok_mode->last_expr_end;i++) {
127-
if (tok_mode->last_expr_buffer[i]=='#') {
129+
charch=tok_mode->last_expr_buffer[i];
130+
if (ch=='\\'&&i+1<tok_mode->last_expr_size-tok_mode->last_expr_end) {
131+
// Skip the next character if it's an escape sequence
132+
i++;
133+
continue;
134+
}
135+
if (ch=='"'||ch=='\'') {
136+
if (!in_string) {
137+
in_string=1;
138+
string_quote=ch;
139+
}elseif (ch==string_quote) {
140+
// Check for triple quotes
141+
if (i>0&&tok_mode->last_expr_buffer[i-1]==ch&&
142+
i>1&&tok_mode->last_expr_buffer[i-2]==ch) {
143+
// Skip the rest of the triple quote
144+
i+=2;
145+
}
146+
in_string=0;
147+
}
148+
}elseif (ch=='#'&& !in_string) {
128149
hash_detected=1;
129150
break;
130151
}
131152
}
132-
153+
// If we found a # character in the expression, we need to handle comments
133154
if (hash_detected) {
155+
// Calculate length of input we need to process
134156
Py_ssize_tinput_length=tok_mode->last_expr_size-tok_mode->last_expr_end;
157+
158+
// Allocate buffer for processed result, with room for null terminator
135159
char*result= (char*)PyMem_Malloc((input_length+1)*sizeof(char));
136160
if (!result) {
137161
return-1;
138162
}
139163

140-
Py_ssize_ti=0;
141-
Py_ssize_tj=0;
164+
// Initialize counters and state
165+
Py_ssize_ti=0;// Input position
166+
Py_ssize_tj=0;// Output position
167+
in_string=0;// Whether we're currently inside a string
168+
string_quote=0;// The quote character for current string (' or ")
142169

170+
// Process each character of input
143171
for (i=0,j=0;i<input_length;i++) {
144-
if (tok_mode->last_expr_buffer[i]=='#') {
145-
// Skip characters until newline or end of string
172+
charch=tok_mode->last_expr_buffer[i];
173+
174+
// Handle escape sequences - copy both backslash and next char
175+
if (ch=='\\'&&i+1<input_length) {
176+
result[j++]=ch;// Copy backslash
177+
result[j++]=tok_mode->last_expr_buffer[++i];// Copy escaped char
178+
continue;
179+
}
180+
181+
// Handle string quotes
182+
if (ch=='"'||ch=='\'') {
183+
if (!in_string) {
184+
// Start of new string
185+
in_string=1;
186+
string_quote=ch;
187+
}elseif (ch==string_quote) {
188+
// Potential end of string - check for triple quotes
189+
if (i>0&&tok_mode->last_expr_buffer[i-1]==ch&&
190+
i>1&&tok_mode->last_expr_buffer[i-2]==ch) {
191+
// Found triple quote - copy all three quotes
192+
result[j++]=ch;
193+
result[j++]=ch;
194+
result[j++]=ch;
195+
i+=2;// Skip the other two quotes
196+
continue;
197+
}
198+
// End of regular string
199+
in_string=0;
200+
}
201+
result[j++]=ch;// Copy the quote character
202+
}
203+
// Handle comments - skip everything until newline
204+
elseif (ch=='#'&& !in_string) {
146205
while (i<input_length&&tok_mode->last_expr_buffer[i]!='\0') {
147206
if (tok_mode->last_expr_buffer[i]=='\n') {
148-
result[j++]=tok_mode->last_expr_buffer[i];
207+
result[j++]=tok_mode->last_expr_buffer[i];// Keep newline
149208
break;
150209
}
151-
i++;
210+
i++;// Skip comment character
152211
}
153-
}else {
154-
result[j++]=tok_mode->last_expr_buffer[i];
212+
}
213+
// Copy any other character unchanged
214+
else {
215+
result[j++]=ch;
155216
}
156217
}
157218

@@ -164,11 +225,9 @@ set_ftstring_expr(struct tok_state* tok, struct token *token, char c) {
164225
tok_mode->last_expr_size-tok_mode->last_expr_end,
165226
NULL
166227
);
167-
168228
}
169229

170-
171-
if (!res) {
230+
if (!res) {
172231
return-1;
173232
}
174233
token->metadata=res;

0 commit comments

Comments
 (0)
[8]ページ先頭
©2009-2025 Movatter.jp