Reject format-string field index above Py_ssize_t::MAX (RustPython#7708)

changjoon-park · web-flow · commit 68aece59c926 · 2026-04-28T21:12:09.000+09:00
CPython rejects digit-only format-string field names that overflow
Py_ssize_t at parse time with ValueError: Too many decimal digits in
format string (Python/string_parser.c::get_integer). RustPython's
FieldName::parse accepted any digit string usize::from_str could parse,
producing IndexError or KeyError at lookup instead.

Cap the parsed index at isize::MAX (Py_ssize_t::MAX on every platform)
inside FieldName::parse. Also reject digits-only strings whose value
overflows usize itself (caught when parse_usize returns None on an
all-digit input). A new FormatParseError::TooManyDecimalDigits maps to
the byte-identical CPython wording.

Unmasks test_str.StrTest.test_format_huge_item_number.
diff --git a/Lib/test/test_str.py b/Lib/test/test_str.py
@@ -1468,7 +1468,6 @@ def test_format_huge_width(self):
         with self.assertRaises(ValueError):
             result = format(2.34, format_string)
 
-    @unittest.expectedFailure  # TODO: RUSTPYTHON; IndexError: tuple index out of range
     def test_format_huge_item_number(self):
         format_string = "{{{}:.6f}}".format(sys.maxsize + 1)
         with self.assertRaises(ValueError):
diff --git a/crates/common/src/format.rs b/crates/common/src/format.rs
@@ -1107,6 +1107,7 @@ pub enum FormatParseError {
     EmptyAttribute,
     MissingRightBracket,
     InvalidCharacterAfterRightBracket,
+    TooManyDecimalDigits,
 }
 
 impl FromStr for FormatSpec {
@@ -1190,7 +1191,19 @@ impl FieldName {
         let field_type = if first.is_empty() {
             FieldType::Auto
         } else if let Some(index) = parse_usize(&first) {
+            // Match CPython's get_integer: digits-only segment must fit in
+            // Py_ssize_t. Above that, raise ValueError at parse time.
+            if index > isize::MAX as usize {
+                return Err(FormatParseError::TooManyDecimalDigits);
+            }
             FieldType::Index(index)
+        } else if first
+            .as_str()
+            .ok()
+            .is_some_and(|s| s.bytes().all(|b| b.is_ascii_digit()))
+        {
+            // All-digit segment whose value overflows usize itself.
+            return Err(FormatParseError::TooManyDecimalDigits);
         } else {
             FieldType::Keyword(first)
         };
diff --git a/crates/vm/src/format.rs b/crates/vm/src/format.rs
@@ -114,6 +114,9 @@ impl ToPyException for FormatParseError {
     fn to_pyexception(&self, vm: &VirtualMachine) -> PyBaseExceptionRef {
         match self {
             Self::UnmatchedBracket => vm.new_value_error("expected '}' before end of string"),
+            Self::TooManyDecimalDigits => {
+                vm.new_value_error("Too many decimal digits in format string")
+            }
             _ => vm.new_value_error("Unexpected error parsing format string"),
         }
     }

Original file line number	Diff line number	Diff line change
`@@ -114,6 +114,9 @@ impl ToPyException for FormatParseError {`
`114`	`114`	`fn to_pyexception(&self, vm: &VirtualMachine) -> PyBaseExceptionRef {`
`115`	`115`	`match self {`
`116`	`116`	`Self::UnmatchedBracket => vm.new_value_error("expected '}' before end of string"),`
	`117`	`+ Self::TooManyDecimalDigits => {`
	`118`	`+ vm.new_value_error("Too many decimal digits in format string")`
	`119`	`+ }`
`117`	`120`	`_ => vm.new_value_error("Unexpected error parsing format string"),`
`118`	`121`	`}`
`119`	`122`	`}`