Skip to content

gh-121130: Fix f-string format specifiers with debug expressions #121150

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.

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 10 commits into from
Jul 16, 2024
Merged
Show file tree
Hide file tree
Changes from 2 commits
Commits
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
6 changes: 6 additions & 0 deletions Lib/test/test_fstring.py
Original file line number Diff line number Diff line change
Expand Up @@ -1601,6 +1601,10 @@ def f(a):
self.assertEqual(f'{f(a=4)}', '3=')
self.assertEqual(x, 4)

# Check debug expressions in format spec
y = 20
self.assertEqual(f"{2:{y=}}", "yyyyyyyyyyyyyyyyyyy2")

# Make sure __format__ is being called.
class C:
def __format__(self, s):
Expand All @@ -1614,9 +1618,11 @@ def __repr__(self):
self.assertEqual(f'{C()=: }', 'C()=FORMAT- ')
self.assertEqual(f'{C()=:x}', 'C()=FORMAT-x')
self.assertEqual(f'{C()=!r:*^20}', 'C()=********REPR********')
self.assertEqual(f"{C():{20=}}", 'FORMAT-20=20')

self.assertRaises(SyntaxError, eval, "f'{C=]'")


# Make sure leading and following text works.
x = 'foo'
self.assertEqual(f'X{x=}Y', 'Xx='+repr(x)+'Y')
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
Fix f-strings with debug expressions in format specifiers. Patch by Pablo
Galindo
10 changes: 9 additions & 1 deletion Parser/action_helpers.c
Original file line number Diff line number Diff line change
Expand Up @@ -1444,8 +1444,16 @@ expr_ty _PyPegen_formatted_value(Parser *p, expr_ty expression, Token *debug, Re
conversion_val = (int)'r';
}

expr_ty format_expr = format ? (expr_ty) format->result : NULL;
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This here is because when there are debug expressions we are wrapping the values in a node that then is wrapped in turn, but that is not what 3.11 and before does so we need to detect that and unwrap.

if (format_expr && format_expr->kind == JoinedStr_kind && asdl_seq_LEN(format_expr->v.JoinedStr.values) == 1) {
expr_ty format_value = asdl_seq_GET(format_expr->v.JoinedStr.values, 0);
if (format_value->kind == JoinedStr_kind) {
format_expr = format_value;
}
}

expr_ty formatted_value = _PyAST_FormattedValue(
expression, conversion_val, format ? (expr_ty) format->result : NULL,
expression, conversion_val, format_expr,
lineno, col_offset, end_lineno,
end_col_offset, arena
);
Expand Down
14 changes: 12 additions & 2 deletions Parser/lexer/lexer.c
Original file line number Diff line number Diff line change
Expand Up @@ -989,6 +989,7 @@ tok_get_normal_mode(struct tok_state *tok, tokenizer_mode* current_tok, struct t
the_current_tok->last_expr_buffer = NULL;
the_current_tok->last_expr_size = 0;
the_current_tok->last_expr_end = -1;
the_current_tok->in_format_spec = 0;
the_current_tok->f_string_debug = 0;

switch (*tok->start) {
Expand Down Expand Up @@ -1137,15 +1138,20 @@ tok_get_normal_mode(struct tok_state *tok, tokenizer_mode* current_tok, struct t
* by the `{` case, so for ensuring that we are on the 0th level, we need
* to adjust it manually */
int cursor = current_tok->curly_bracket_depth - (c != '{');
if (cursor == 0 && !_PyLexer_update_fstring_expr(tok, c)) {
int in_format_spec = current_tok->in_format_spec;
int cursor_in_format_with_debug =
cursor == 1 && (current_tok->f_string_debug || in_format_spec);
int cursor_valid = cursor == 0 || cursor_in_format_with_debug;
if (cursor_valid && !_PyLexer_update_fstring_expr(tok, c)) {
return MAKE_TOKEN(ENDMARKER);
}
if (cursor == 0 && c != '{' && set_fstring_expr(tok, token, c)) {
if (cursor_valid && c != '{' && set_fstring_expr(tok, token, c)) {
return MAKE_TOKEN(ERRORTOKEN);
}

if (c == ':' && cursor == current_tok->curly_bracket_expr_start_depth) {
current_tok->kind = TOK_FSTRING_MODE;
current_tok->in_format_spec = 1;
p_start = tok->start;
p_end = tok->cur;
return MAKE_TOKEN(_PyToken_OneChar(c));
Expand Down Expand Up @@ -1235,6 +1241,7 @@ tok_get_normal_mode(struct tok_state *tok, tokenizer_mode* current_tok, struct t
if (c == '}' && current_tok->curly_bracket_depth == current_tok->curly_bracket_expr_start_depth) {
current_tok->curly_bracket_expr_start_depth--;
current_tok->kind = TOK_FSTRING_MODE;
current_tok->in_format_spec = 0;
current_tok->f_string_debug = 0;
}
}
Expand Down Expand Up @@ -1337,6 +1344,7 @@ tok_get_fstring_mode(struct tok_state *tok, tokenizer_mode* current_tok, struct
if (in_format_spec && c == '\n') {
tok_backup(tok, c);
TOK_GET_MODE(tok)->kind = TOK_REGULAR_MODE;
current_tok->in_format_spec = 0;
p_start = tok->start;
p_end = tok->cur;
return MAKE_TOKEN(FSTRING_MIDDLE);
Expand Down Expand Up @@ -1387,6 +1395,7 @@ tok_get_fstring_mode(struct tok_state *tok, tokenizer_mode* current_tok, struct
return MAKE_TOKEN(_PyTokenizer_syntaxerror(tok, "f-string: expressions nested too deeply"));
}
TOK_GET_MODE(tok)->kind = TOK_REGULAR_MODE;
current_tok->in_format_spec = 0;
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Shouldn't this always be 0 here, if we've correctly reset it when the format spec is ending?

p_start = tok->start;
p_end = tok->cur;
} else {
Expand All @@ -1413,6 +1422,7 @@ tok_get_fstring_mode(struct tok_state *tok, tokenizer_mode* current_tok, struct
tok_backup(tok, peek);
tok_backup(tok, c);
TOK_GET_MODE(tok)->kind = TOK_REGULAR_MODE;
current_tok->in_format_spec = 0;
p_start = tok->start;
p_end = tok->cur;
}
Expand Down
1 change: 1 addition & 0 deletions Parser/lexer/state.c
Original file line number Diff line number Diff line change
Expand Up @@ -74,6 +74,7 @@ free_fstring_expressions(struct tok_state *tok)
mode->last_expr_buffer = NULL;
mode->last_expr_size = 0;
mode->last_expr_end = -1;
mode->in_format_spec = 0;
}
}
}
Expand Down
1 change: 1 addition & 0 deletions Parser/lexer/state.h
Original file line number Diff line number Diff line change
Expand Up @@ -58,6 +58,7 @@ typedef struct _tokenizer_mode {
Py_ssize_t last_expr_end;
char* last_expr_buffer;
int f_string_debug;
int in_format_spec;
} tokenizer_mode;

/* Tokenizer state */
Expand Down
Loading