Skip to content

GH-103718: Correctly cache and restore f-string buffers when needed #103719

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 23, 2023
Merged

GH-103718: Correctly cache and restore f-string buffers when needed #103719

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions Lib/test/test_fstring.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1532,5 +1532,10 @@ def test_syntax_error_for_starred_expressions(self):
"f-string: expecting a valid expression after '{'"):
compile("f'{**a}'", "?", "exec")

def test_not_closing_quotes(self):
self.assertAllRaise(SyntaxError, "unterminated f-string literal", ['f"', "f'"])
self.assertAllRaise(SyntaxError, "unterminated triple-quoted f-string literal",
['f"""', "f'''"])

if __name__ == '__main__':
unittest.main()
38 changes: 27 additions & 11 deletions Parser/tokenizer.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -361,21 +361,35 @@ tok_concatenate_interactive_new_line(struct tok_state *tok, const char *line) {
return 0;
}


/* Traverse and update all f-string buffers with the value */
/* Traverse and remember all f-string buffers, in order to be able to restore
them after reallocating tok->buf */
static void
update_fstring_buffers(struct tok_state *tok, char value, int regular, int multiline)
remember_fstring_buffers(struct tok_state *tok)
{
int index;
tokenizer_mode *mode;

for (index = tok->tok_mode_stack_index; index >= 0; --index) {
mode = &(tok->tok_mode_stack[index]);
if (regular && mode->f_string_start != NULL) {
mode->f_string_start += value;
if (mode->kind == TOK_FSTRING_MODE) {
mode->f_string_start_offset = mode->f_string_start - tok->buf;
mode->f_string_multi_line_start_offset = mode->f_string_multi_line_start - tok->buf;
}
if (multiline && mode->f_string_multi_line_start != NULL) {
mode->f_string_multi_line_start += value;
}
}

/* Traverse and restore all f-string buffers after reallocating tok->buf */
static void
restore_fstring_buffers(struct tok_state *tok)
{
int index;
tokenizer_mode *mode;

for (index = tok->tok_mode_stack_index; index >= 0; --index) {
mode = &(tok->tok_mode_stack[index]);
if (mode->kind == TOK_FSTRING_MODE) {
mode->f_string_start = tok->buf + mode->f_string_start_offset;
mode->f_string_multi_line_start = tok->buf + mode->f_string_multi_line_start_offset;
}
}
}
Expand Down Expand Up @@ -476,7 +490,7 @@ tok_reserve_buf(struct tok_state *tok, Py_ssize_t size)
Py_ssize_t start = tok->start == NULL ? -1 : tok->start - tok->buf;
Py_ssize_t line_start = tok->start == NULL ? -1 : tok->line_start - tok->buf;
Py_ssize_t multi_line_start = tok->multi_line_start - tok->buf;
update_fstring_buffers(tok, -*tok->buf, /*regular=*/1, /*multiline=*/1);
remember_fstring_buffers(tok);
newbuf = (char *)PyMem_Realloc(newbuf, newsize);
if (newbuf == NULL) {
tok->done = E_NOMEM;
Expand All @@ -489,7 +503,7 @@ tok_reserve_buf(struct tok_state *tok, Py_ssize_t size)
tok->start = start < 0 ? NULL : tok->buf + start;
tok->line_start = line_start < 0 ? NULL : tok->buf + line_start;
tok->multi_line_start = multi_line_start < 0 ? NULL : tok->buf + multi_line_start;
update_fstring_buffers(tok, *tok->buf, /*regular=*/1, /*multiline=*/1);
restore_fstring_buffers(tok);
}
return 1;
}
Expand Down Expand Up @@ -1051,7 +1065,7 @@ tok_underflow_interactive(struct tok_state *tok) {
}
else if (tok->start != NULL) {
Py_ssize_t cur_multi_line_start = tok->multi_line_start - tok->buf;
update_fstring_buffers(tok, -*tok->buf, /*regular=*/0, /*multiline=*/1);
remember_fstring_buffers(tok);
size_t size = strlen(newtok);
ADVANCE_LINENO();
if (!tok_reserve_buf(tok, size + 1)) {
Expand All @@ -1064,7 +1078,7 @@ tok_underflow_interactive(struct tok_state *tok) {
PyMem_Free(newtok);
tok->inp += size;
tok->multi_line_start = tok->buf + cur_multi_line_start;
update_fstring_buffers(tok, *tok->buf, /*regular=*/0, /*multiline=*/1);
restore_fstring_buffers(tok);
}
else {
ADVANCE_LINENO();
Expand Down Expand Up @@ -2207,6 +2221,8 @@ tok_get_normal_mode(struct tok_state *tok, tokenizer_mode* current_tok, struct t
the_current_tok->f_string_quote_size = quote_size;
the_current_tok->f_string_start = tok->start;
the_current_tok->f_string_multi_line_start = tok->line_start;
the_current_tok->f_string_start_offset = -1;
the_current_tok->f_string_multi_line_start_offset = -1;
the_current_tok->last_expr_buffer = NULL;
the_current_tok->last_expr_size = 0;
the_current_tok->last_expr_end = -1;
Expand Down
3 changes: 3 additions & 0 deletions Parser/tokenizer.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,6 +52,9 @@ typedef struct _tokenizer_mode {
const char* f_string_start;
const char* f_string_multi_line_start;

Py_ssize_t f_string_start_offset;
Py_ssize_t f_string_multi_line_start_offset;

Py_ssize_t last_expr_size;
Py_ssize_t last_expr_end;
char* last_expr_buffer;
Expand Down