Match CPython error type for non-ASCII struct format arguments (RustPython#7681)

changjoon-park · web-flow · commit be43bb6dbf22 · 2026-04-26T12:31:54.000+09:00
* Match CPython error type for non-ASCII struct format arguments

Struct() raised the wrong exception type when the format argument
contained non-ASCII characters:
- str input with non-ASCII char: RustPython raised UnicodeDecodeError
  with an empty message; CPython raises UnicodeEncodeError as if
  format.encode('ascii') had been called directly.
- bytes input with non-ASCII byte: same wrong UnicodeDecodeError;
  CPython passes the bytes through to the format parser, which then
  errors with struct.error("bad char in struct format").

Restructure IntoStructFormatBytes::try_from_object to:
- raise UnicodeEncodeError("ascii", s, start, start+1, "ordinal not
  in range(128)") for non-ASCII str, with start computed as the
  first non-ASCII code point position (matching CPython's natural
  encoding-error format);
- raise struct.error("bad char in struct format") for non-ASCII bytes,
  produced via the existing new_struct_error helper.

Probed byte-identical with CPython 3.14.4 for both cases. Full
test.test_struct (43 tests) passes with no regressions. Sanity-tested
all standard format/pack/unpack/calcsize call shapes remain unchanged.

* Add regression test for non-ASCII format string error types

* Use raise AssertionError instead of assert False (B011)
diff --git a/crates/stdlib/src/pystruct.rs b/crates/stdlib/src/pystruct.rs
@@ -26,20 +26,42 @@ pub(crate) mod _struct {
 
     impl TryFromObject for IntoStructFormatBytes {
         fn try_from_object(vm: &VirtualMachine, obj: PyObjectRef) -> PyResult<Self> {
-            // CPython turns str to bytes but we do reversed way here
-            // The only performance difference is this transition cost
+            // CPython turns str to bytes (via str.encode('ascii')) but we keep str.
+            // The error reporting for non-ASCII input still matches CPython:
+            // - str input with non-ASCII char: UnicodeEncodeError, the same exception
+            //   str.encode('ascii') would produce.
+            // - bytes input with non-ASCII byte: struct.error("bad char in struct format"),
+            //   matching CPython where bytes are passed through to the format parser.
             let fmt = match_class!(match obj {
-                s @ PyStr => s.isascii().then_some(s),
-                b @ PyBytes => ascii::AsciiStr::from_ascii(&b)
-                    .ok()
-                    .map(|s| vm.ctx.new_str(s)),
+                s @ PyStr => {
+                    if !s.isascii() {
+                        let start = s
+                            .as_wtf8()
+                            .code_points()
+                            .position(|cp| !cp.to_char().is_some_and(|c| c.is_ascii()))
+                            .unwrap_or(0);
+                        return Err(vm.new_unicode_encode_error_real(
+                            vm.ctx.new_str("ascii"),
+                            s,
+                            start,
+                            start + 1,
+                            vm.ctx.new_str("ordinal not in range(128)"),
+                        ));
+                    }
+                    s
+                }
+                b @ PyBytes => {
+                    let ascii_str = ascii::AsciiStr::from_ascii(&b).map_err(|_| {
+                        new_struct_error(vm, "bad char in struct format".to_owned())
+                    })?;
+                    vm.ctx.new_str(ascii_str)
+                }
                 other =>
                     return Err(vm.new_type_error(format!(
                         "Struct() argument 1 must be a str or bytes object, not {}",
                         other.class().name()
                     ))),
-            })
-            .ok_or_else(|| vm.new_unicode_decode_error("Struct format must be a ascii string"))?;
+            });
             Ok(Self(fmt))
         }
     }
diff --git a/extra_tests/snippets/stdlib_struct.py b/extra_tests/snippets/stdlib_struct.py
@@ -76,3 +76,19 @@ def __index__(self):
 
 assert struct.error.__module__ == "struct"
 assert struct.error.__name__ == "error"
+
+# Non-ASCII format string: error type matches CPython.
+# str &rarr; UnicodeEncodeError (encoding='ascii')
+# bytes &rarr; struct.error
+try:
+    struct.Struct("\udc00")
+except UnicodeEncodeError as e:
+    assert e.encoding == "ascii"
+else:
+    raise AssertionError("expected UnicodeEncodeError")
+
+with assert_raises(UnicodeEncodeError):
+    struct.Struct("&#54620;")
+
+with assert_raises(struct.error):
+    struct.Struct(b"\xff")
