RustPython · youknowone · Aug 16, 2026 · Aug 14, 2026 · Aug 14, 2026 · Aug 14, 2026
diff --git a/Lib/test/test_struct.py b/Lib/test/test_struct.py
@@ -601,7 +601,6 @@ def test_trailing_counter(self):
                           'spam and eggs')
         self.assertRaises(struct.error, struct.unpack_from, '14s42', store, 0)
 
-    @unittest.expectedFailure  # TODO: RUSTPYTHON; AssertionError: '>h' != '>hh'
     def test_Struct_reinitialization(self):
         # Issue 9422: there was a memory leak when reinitializing a
         # Struct instance.  This test can be used to detect the leak
@@ -826,7 +825,6 @@ def test_error_propagation(fmt_str):
         test_error_propagation('N')
         test_error_propagation('n')
 
-    @unittest.expectedFailure  # TODO: RUSTPYTHON
     def test_struct_subclass_instantiation(self):
         # Regression test for https://github.com/python/cpython/issues/112358
         class MyStruct(struct.Struct):

diff --git a/Lib/test/test_support.py b/Lib/test/test_support.py
@@ -631,7 +631,6 @@ def test_has_strftime_extensions(self):
         else:
             self.assertTrue(support.has_strftime_extensions)
 
-    @unittest.expectedFailure  # TODO: RUSTPYTHON; - _testinternalcapi module not available
     def test_get_recursion_depth(self):
         # test support.get_recursion_depth()
         code = textwrap.dedent("""

diff --git a/crates/common/src/borrow.rs b/crates/common/src/borrow.rs
@@ -34,6 +34,17 @@ impl_from!('a, T, BorrowedValue<'a, T>,
 );
 
 impl<'a, T: ?Sized> BorrowedValue<'a, T> {
+    /// Whether reaching the value holds a lock that other threads wait on.
+    ///
+    /// An immutable object hands out a plain reference and answers `false`;
+    /// one whose storage can change hands out a guard. A caller about to wait
+    /// for something unrelated -- a peer, a file, a signal -- can use this to
+    /// decide whether it may keep the borrow for the duration.
+    #[must_use]
+    pub const fn is_locked(&self) -> bool {
+        !matches!(self, Self::Ref(_))
+    }
+
     pub fn map<U: ?Sized, F>(s: Self, f: F) -> BorrowedValue<'a, U>
     where
         F: FnOnce(&T) -> &U,

diff --git a/crates/common/src/str.rs b/crates/common/src/str.rs
@@ -592,20 +592,21 @@ pub fn codepoint_range_end(s: &Wtf8, n_chars: usize) -> Option<usize> {
 }
 
 #[must_use]
-pub fn zfill(bytes: &[u8], width: usize) -> Vec<u8> {
+/// Returns `None` for a width whose result cannot be allocated.
+pub fn zfill(bytes: &[u8], width: usize) -> Option<Vec<u8>> {
     if width <= bytes.len() {
-        bytes.to_vec()
-    } else {
-        let (sign, s) = match bytes.first() {
-            Some(_sign @ (b'+' | b'-')) => (unsafe { bytes.get_unchecked(..1) }, &bytes[1..]),
-            _ => (&b""[..], bytes),
-        };
-        let mut filled = Vec::new();
-        filled.extend_from_slice(sign);
-        filled.extend(core::iter::repeat_n(b'0', width - bytes.len()));
-        filled.extend_from_slice(s);
-        filled
+        return Some(bytes.to_vec());
     }
+    let (sign, s) = match bytes.first() {
+        Some(_sign @ (b'+' | b'-')) => (unsafe { bytes.get_unchecked(..1) }, &bytes[1..]),
+        _ => (&b""[..], bytes),
+    };
+    let mut filled = Vec::new();
+    filled.try_reserve_exact(width).ok()?;
+    filled.extend_from_slice(sign);
+    filled.extend(core::iter::repeat_n(b'0', width - bytes.len()));
+    filled.extend_from_slice(s);
+    Some(filled)
 }
 
 /// Convert a string to ascii compatible, escaping unicode-s into escape

diff --git a/crates/compiler-core/src/marshal.rs b/crates/compiler-core/src/marshal.rs
@@ -19,6 +19,14 @@ pub enum MarshalError {
     InvalidLocation,
     /// Bad type marker
     BadType,
+    /// A type marker no reader knows
+    UnknownType,
+    /// A back reference that names nothing
+    InvalidRef,
+    /// A marker that stands for no object at all
+    NullObject,
+    /// A container length that is negative or does not fit, named by what it counts
+    BadSize(&'static str),
 }
 
 impl core::fmt::Display for MarshalError {
@@ -29,6 +37,10 @@ impl core::fmt::Display for MarshalError {
             Self::InvalidUtf8 => f.write_str("invalid utf8"),
             Self::InvalidLocation => f.write_str("invalid source location"),
             Self::BadType => f.write_str("bad type marker"),
+            Self::UnknownType => f.write_str("unknown type code"),
+            Self::InvalidRef => f.write_str("invalid reference"),
+            Self::NullObject => f.write_str("NULL object in marshal data for object"),
+            Self::BadSize(what) => write!(f, "{what} size out of range"),
         }
     }
 }
@@ -111,7 +123,7 @@ impl TryFrom<u8> for Type {
             b'A' => Self::AsciiInterned,
             b'z' => Self::ShortAscii,
             b'Z' => Self::ShortAsciiInterned,
-            _ => return Err(MarshalError::BadType),
+            _ => return Err(MarshalError::UnknownType),
         })
     }
 }
@@ -146,6 +158,13 @@ pub trait Read {
     fn read_u64(&mut self) -> Result<u64> {
         Ok(u64::from_le_bytes(*self.read_array()?))
     }
+
+    /// A length, read the way `r_long` reads one: it is signed, so a value
+    /// with the top bit set is out of range rather than four billion items.
+    fn read_len(&mut self, what: &'static str) -> Result<usize> {
+        let len = self.read_u32()? as i32;
+        usize::try_from(len).map_err(|_| MarshalError::BadSize(what))
+    }
 }
 
 pub(crate) trait ReadBorrowed<'a>: Read {
@@ -305,7 +324,7 @@ fn reserve_ref_slot<T>(has_flag: bool, refs: &mut Vec<Option<T>>) -> Option<usiz
 fn resolve_ref<T: Clone>(idx: usize, refs: &[Option<T>]) -> Result<T> {
     refs.get(idx)
         .and_then(|v| v.clone())
-        .ok_or(MarshalError::InvalidBytecode)
+        .ok_or(MarshalError::InvalidRef)
 }
 
 /// Read a marshal bytes object (TYPE_STRING = b's'), resolving TYPE_REF
@@ -408,7 +427,7 @@ fn read_marshal_str_vec<R: Read, Bag: ConstantBag>(
     }
 
     let n = match type_byte {
-        b'(' => rdr.read_u32()? as usize,
+        b'(' => rdr.read_len("tuple")?,
         b')' => rdr.read_u8()? as usize,
         _ => return Err(MarshalError::BadType),
     };
@@ -471,7 +490,7 @@ fn read_marshal_const_tuple<R: Read, Bag: ConstantBag>(
     }
 
     let n = match type_byte {
-        b'(' => rdr.read_u32()? as usize,
+        b'(' => rdr.read_len("tuple")?,
         b')' => rdr.read_u8()? as usize,
         _ => return Err(MarshalError::BadType),
     };
@@ -553,7 +572,7 @@ pub trait MarshalBag: Copy {
     fn make_code(
         &self,
         code: CodeObject<<Self::ConstantBag as ConstantBag>::Constant>,
-    ) -> Self::Value;
+    ) -> Result<Self::Value>;
 
     /// Construct a runtime code object while retaining the exact values read
     /// from ``co_consts``. Compiler bags ignore this second channel; runtime
@@ -563,7 +582,7 @@ pub trait MarshalBag: Copy {
         &self,
         code: CodeObject<<Self::ConstantBag as ConstantBag>::Constant>,
         _constants: Vec<Self::Value>,
-    ) -> Self::Value {
+    ) -> Result<Self::Value> {
         self.make_code(code)
     }
 
@@ -583,8 +602,12 @@ pub trait MarshalBag: Copy {
     /// Install partially-built containers in the marshal reference table
     /// before reading their children, as CPython's `r_object()` does.
     /// Runtime bags can opt in; constant bags retain collect-then-construct.
-    fn make_tuple_placeholder(&self, _len: usize) -> Option<Self::Value> {
-        None
+    ///
+    /// `len` comes straight from the input and is only bounded by what a
+    /// length can hold, so a bag that opts in reports the room it cannot get
+    /// rather than taking it for granted.
+    fn make_tuple_placeholder(&self, _len: usize) -> Result<Option<Self::Value>> {
+        Ok(None)
     }
 
     fn set_tuple_item(
@@ -596,8 +619,8 @@ pub trait MarshalBag: Copy {
         Err(MarshalError::BadType)
     }
 
-    fn make_list_placeholder(&self, _len: usize) -> Option<Self::Value> {
-        None
+    fn make_list_placeholder(&self, _len: usize) -> Result<Option<Self::Value>> {
+        Ok(None)
     }
 
     fn set_list_item(&self, _list: &Self::Value, _index: usize, _value: Self::Value) -> Result<()> {
@@ -725,8 +748,8 @@ impl<Bag: ConstantBag> MarshalBag for Bag {
     fn make_code(
         &self,
         code: CodeObject<<Self::ConstantBag as ConstantBag>::Constant>,
-    ) -> Self::Value {
-        self.make_code(code)
+    ) -> Result<Self::Value> {
+        Ok(self.make_code(code))
     }
 
     fn make_stop_iter(&self) -> Result<Self::Value> {
@@ -830,10 +853,7 @@ fn deserialize_value_after_header<R: Read, Bag: MarshalBag>(
     // TYPE_REF: return previously stored object
     if type_code == Type::Ref as u8 {
         let idx = rdr.read_u32()? as usize;
-        return refs
-            .get(idx)
-            .and_then(|v| v.clone())
-            .ok_or(MarshalError::InvalidBytecode);
+        return resolve_ref(idx, refs);
     }
 
     // Reserve ref slot before reading (matches write order)
@@ -986,7 +1006,7 @@ fn deserialize_code_value_inner<R: Read, Bag: MarshalBag>(
         linetable,
         exceptiontable,
     };
-    Ok(bag.make_code_with_constants(code, constant_values))
+    bag.make_code_with_constants(code, constant_values)
 }
 
 fn deserialize_value_typed<R: Read, Bag: MarshalBag>(
@@ -1033,13 +1053,13 @@ fn deserialize_value_typed<R: Read, Bag: MarshalBag>(
             bag.make_complex(value)
         }
         Type::Ascii | Type::Unicode => {
-            let len = rdr.read_u32()?;
-            let value = rdr.read_wtf8(len)?;
+            let len = rdr.read_len("string")?;
+            let value = rdr.read_wtf8(len as u32)?;
             bag.make_str(value)
         }
         Type::AsciiInterned | Type::Interned => {
-            let len = rdr.read_u32()?;
-            let value = rdr.read_wtf8(len)?;
+            let len = rdr.read_len("string")?;
+            let value = rdr.read_wtf8(len as u32)?;
             bag.make_interned_str(value)
         }
         Type::ShortAscii => {
@@ -1056,7 +1076,7 @@ fn deserialize_value_typed<R: Read, Bag: MarshalBag>(
             let len = rdr.read_u8()? as usize;
             let d = depth - 1;
             if let Some(index) = slot
-                && let Some(tuple) = bag.make_tuple_placeholder(len)
+                && let Some(tuple) = bag.make_tuple_placeholder(len)?
             {
                 refs[index] = Some(tuple.clone());
                 for item_index in 0..len {
@@ -1070,17 +1090,17 @@ fn deserialize_value_typed<R: Read, Bag: MarshalBag>(
             }
         }
         Type::Null => {
-            return Err(MarshalError::BadType);
+            return Err(MarshalError::NullObject);
         }
         Type::Ref => {
             // Handled in deserialize_value_depth before calling this function
             return Err(MarshalError::BadType);
         }
         Type::Tuple => {
-            let len = rdr.read_u32()? as usize;
+            let len = rdr.read_len("tuple")?;
             let d = depth - 1;
             if let Some(index) = slot
-                && let Some(tuple) = bag.make_tuple_placeholder(len)
+                && let Some(tuple) = bag.make_tuple_placeholder(len)?
             {
                 refs[index] = Some(tuple.clone());
                 for item_index in 0..len {
@@ -1094,10 +1114,10 @@ fn deserialize_value_typed<R: Read, Bag: MarshalBag>(
             }
         }
         Type::List => {
-            let len = rdr.read_u32()? as usize;
+            let len = rdr.read_len("list")?;
             let d = depth - 1;
             if let Some(index) = slot
-                && let Some(list) = bag.make_list_placeholder(len)
+                && let Some(list) = bag.make_list_placeholder(len)?
             {
                 refs[index] = Some(list.clone());
                 for item_index in 0..len {
@@ -1111,7 +1131,7 @@ fn deserialize_value_typed<R: Read, Bag: MarshalBag>(
             }
         }
         Type::Set => {
-            let len = rdr.read_u32()? as usize;
+            let len = rdr.read_len("set")?;
             let d = depth - 1;
             if let Some(index) = slot
                 && let Some(set) = bag.make_set_placeholder()
@@ -1128,7 +1148,7 @@ fn deserialize_value_typed<R: Read, Bag: MarshalBag>(
             }
         }
         Type::FrozenSet => {
-            let len = rdr.read_u32()?;
+            let len = rdr.read_len("set")?;
-            let len = rdr.read_len("set")?;
+            let len = rdr.read_len("frozenset")?;
-            let len = rdr.read_len("set")?;
+            let len = rdr.read_len("frozenset")?;
             let d = depth - 1;
             let it = (0..len).map(|_| deserialize_value_depth(rdr, bag, d, refs));
             itertools::process_results(it, |it| bag.make_frozenset(it))??
@@ -1165,8 +1185,8 @@ fn deserialize_value_typed<R: Read, Bag: MarshalBag>(
         }
         Type::Bytes => {
             // After marshaling, byte arrays are converted into bytes.
-            let len = rdr.read_u32()?;
-            let value = rdr.read_slice(len)?;
+            let len = rdr.read_len("bytes object")?;
+            let value = rdr.read_slice(len as u32)?;
             bag.make_bytes(value)
         }
         Type::Code => return Err(MarshalError::BadType),

diff --git a/crates/host_env/src/io.rs b/crates/host_env/src/io.rs
@@ -199,6 +199,29 @@ pub fn is_seekable(fd: crt_fd::Borrowed<'_>) -> bool {
     os::seek_fd(fd, 0, libc::SEEK_CUR).is_ok()
 }
 
+/// Whether a read from `fd` answers from data the file already holds, rather
+/// than waiting for whoever writes the other end.
+///
+/// Seeking answers this everywhere but Windows, where a pipe seeks too --
+/// `lseek` on one succeeds and reports a position, so a reader that took
+/// seekability for an answer would wait on a peer while holding whatever it
+/// holds for the length of the call.
+#[cfg(not(windows))]
+pub fn reads_without_waiting(fd: crt_fd::Borrowed<'_>) -> bool {
+    is_seekable(fd)
+}
+
+#[cfg(windows)]
+pub fn reads_without_waiting(fd: crt_fd::Borrowed<'_>) -> bool {
+    use std::os::windows::io::AsRawHandle;
+    use windows_sys::Win32::Storage::FileSystem::{FILE_TYPE_DISK, GetFileType};
+
+    let Ok(handle) = crt_fd::as_handle(fd) else {
+        return false;
+    };
+    unsafe { GetFileType(handle.as_raw_handle() as _) == FILE_TYPE_DISK }
+}
+
 pub fn validate_whence(whence: i32) -> bool {
     let standard = (0..=2).contains(&whence);
     #[cfg(any(target_os = "dragonfly", target_os = "freebsd", target_os = "linux"))]

diff --git a/crates/host_env/src/io_unsupported.rs b/crates/host_env/src/io_unsupported.rs
@@ -176,6 +176,10 @@ pub fn is_seekable(_fd: crt_fd::Borrowed<'_>) -> bool {
     false
 }
 
+pub fn reads_without_waiting(_fd: crt_fd::Borrowed<'_>) -> bool {
+    false
+}
+
 pub fn validate_whence(whence: i32) -> bool {
     (0..=2).contains(&whence)
 }
-Original file line number
+Diff line change
@@ Expand Up / @@ -176,6 +176,10 @@ pub fn is_seekable(_fd: crt_fd::Borrowed<'_>) -> bool { @@
         false
     }
+    pub fn reads_without_waiting(_fd: crt_fd::Borrowed<'_>) -> bool {
+        false
+    }
     pub fn validate_whence(whence: i32) -> bool {
         (0..=2).contains(&whence)
     }
@@ Expand Down @@