Merge pull request #23 from gf712/fix/generator-resume-stack-rebase

Various fixes to codegen and generator runtime

Author: gf712

integration/tests/exception_attributes.py

@@ -0,0 +1,57 @@
+# Regression test for BaseException str()/args/__traceback__ and for per-assert
+# traceback line numbers (message-less asserts must not share a merged block that
+# collapses their source locations).
+
+
+def deepest_lineno(exc):
+    tb = exc.__traceback__
+    while tb.tb_next is not None:
+        tb = tb.tb_next
+    return tb.tb_lineno
+
+
+# --- str(exc) is the message; args is the tuple; __traceback__ is exposed ---
+try:
+    raise ValueError("boom")
+except ValueError as e:
+    assert str(e) == "boom", str(e)
+    assert e.args == ("boom",), e.args
+    assert isinstance(e, ValueError)
+    assert e.__traceback__ is not None
+
+try:
+    raise ValueError("a", "b")
+except ValueError as e:
+    assert e.args == ("a", "b"), e.args
+
+try:
+    raise KeyError("k")
+except KeyError as e:
+    assert e.args == ("k",), e.args
+
+
+# --- the traceback line is the raising statement's line ---
+def raises_value_error():
+    raise ValueError("here")  # EXC_RAISE_LINE
+
+
+try:
+    raises_value_error()
+except ValueError as e:
+    assert deepest_lineno(e) == 35, deepest_lineno(e)
+
+
+# --- a later message-less assert reports ITS OWN line, not the first assert's
+#     (regression for the merged-assertion-block traceback bug) ---
+def fails_on_third_assert():
+    assert True
+    assert True
+    assert False  # EXC_ASSERT_LINE
+
+
+try:
+    fails_on_third_assert()
+except AssertionError as e:
+    assert deepest_lineno(e) == 49, deepest_lineno(e)
+
+print("EXCEPTION_ATTRIBUTES_OK")

integration/tests/exception_binding.py

@@ -0,0 +1,37 @@
+# `except <Type> as <name>:` must bind <name> to the exception INSTANCE,
+# not to the matched type. Regression test for the MLIRGenerator handler
+# codegen (py.load_exception).
+
+raised = ValueError("boom")
+try:
+    raise raised
+except ValueError as e:
+    assert e is raised, "e must be the raised instance"
+    assert isinstance(e, ValueError)
+    assert type(e) is ValueError
+
+# the bound name must be the instance even with multiple candidate handlers
+try:
+    raise KeyError("k")
+except ValueError as e:
+    bound = ("value", e)
+except KeyError as e:
+    bound = ("key", e)
+assert bound[0] == "key"
+assert isinstance(bound[1], KeyError)
+assert type(bound[1]) is KeyError
+
+# nested handlers each bind their own instance
+inner_exc = TypeError("inner")
+outer_exc = IndexError("outer")
+try:
+    try:
+        raise inner_exc
+    except TypeError as e:
+        assert e is inner_exc
+        raise outer_exc
+except IndexError as e:
+    assert e is outer_exc
+    assert e is not inner_exc
+
+print("EXCEPTION_BINDING_OK")

integration/tests/exception_chaining.py

@@ -0,0 +1,92 @@
+# Regression: exception chaining — __cause__ (explicit, via `raise X from Y`),
+# implicit __context__ (the exception being handled when a new one is raised),
+# and __suppress_context__. Also covers the exception-stack hygiene that makes
+# these reliable: internally-consumed StopIterations no longer linger, so a bare
+# `raise` outside a handler is a RuntimeError and __context__ isn't spuriously
+# populated.
+
+
+# `raise X from Y` sets __cause__ to the instance and suppresses context.
+try:
+    try:
+        raise ValueError("inner")
+    except ValueError as e:
+        raise KeyError("outer") from e
+except KeyError as k:
+    assert isinstance(k.__cause__, ValueError), k.__cause__
+    assert str(k.__cause__) == "inner", str(k.__cause__)
+    assert k.__suppress_context__ is True, k.__suppress_context__
+    # __context__ is still set implicitly (suppress only affects display).
+    assert isinstance(k.__context__, ValueError), k.__context__
+
+
+# Implicit chaining without `from`: __context__ is the handled exception.
+try:
+    try:
+        raise ValueError("v1")
+    except ValueError:
+        raise KeyError("k1")
+except KeyError as k:
+    assert k.__cause__ is None, k.__cause__
+    assert isinstance(k.__context__, ValueError), k.__context__
+    assert str(k.__context__) == "v1", str(k.__context__)
+    assert k.__suppress_context__ is False, k.__suppress_context__
+
+
+# `raise X from None` -> cause None, still suppressed.
+try:
+    raise KeyError("k") from None
+except KeyError as k:
+    assert k.__cause__ is None, k.__cause__
+    assert k.__suppress_context__ is True, k.__suppress_context__
+
+
+# Plain exception raised outside any handler: no cause, no context.
+try:
+    raise ValueError("plain")
+except ValueError as e:
+    assert e.__cause__ is None, e.__cause__
+    assert e.__context__ is None, e.__context__
+    assert e.__suppress_context__ is False, e.__suppress_context__
+
+
+# A bare `raise` with no active exception is a RuntimeError (not an abort, and
+# not a stale leftover exception).
+try:
+    raise
+except RuntimeError as e:
+    assert str(e) == "No active exception to reraise", str(e)
+
+
+# Iterating a generator / comprehensions while handling an exception must not
+# disturb the active exception (exception-stack hygiene).
+def gen():
+    yield 1
+    yield 2
+    yield 3
+
+
+try:
+    raise ValueError("active")
+except ValueError as e:
+    assert set(gen()) == {1, 2, 3}
+    assert [x for x in range(4)] == [0, 1, 2, 3]
+    assert {k: k * k for k in range(3)} == {0: 0, 1: 1, 2: 4}
+    assert isinstance(e, ValueError) and str(e) == "active"
+
+
+# Chaining attributes are writable; setting __cause__ also suppresses context.
+try:
+    raise ValueError("x")
+except ValueError as e:
+    ctx = RuntimeError("ctx")
+    e.__context__ = ctx
+    assert e.__context__ is ctx
+    e.__cause__ = ctx
+    assert e.__cause__ is ctx
+    assert e.__suppress_context__ is True
+    e.__suppress_context__ = False
+    assert e.__suppress_context__ is False
+
+
+print("EXCEPTION_CHAINING_OK")

integration/tests/exception_types.py

@@ -0,0 +1,39 @@
+# Regression: every builtin exception type must construct (raise X(...)) without
+# crashing — Exception subclasses missing their own __new__ used to inherit
+# Exception::__new__ (which asserts the exact Exception type), and
+# ModuleNotFoundError dereferenced a null kwargs.
+
+builtin_exceptions = [
+    BaseException, Exception, ValueError, KeyError, IndexError, TypeError,
+    NameError, AttributeError, RuntimeError, NotImplementedError, ImportError,
+    ModuleNotFoundError, OSError, LookupError, MemoryError, StopIteration,
+    UnboundLocalError, AssertionError,
+]
+
+
+for exc_type in builtin_exceptions:
+    try:
+        raise exc_type("msg")
+    except BaseException as e:
+        assert isinstance(e, exc_type), exc_type
+        assert type(e) is exc_type, (type(e), exc_type)
+        assert e.args == ("msg",), (exc_type, e.args)
+
+
+# subclass relationships still hold
+try:
+    raise RuntimeError("r")
+except Exception as e:
+    assert isinstance(e, RuntimeError)
+    assert isinstance(e, Exception)
+    assert isinstance(e, BaseException)
+
+
+# constructed with no args
+try:
+    raise ValueError
+except ValueError as e:
+    assert e.args == ()
+
+
+print("EXCEPTION_TYPES_OK")

integration/tests/generator_consume.py

@@ -0,0 +1,71 @@
+# Regression test for generator resumption when consumed outside a `for` loop.
+
+def gen_simple():
+    yield 1
+    yield 2
+    yield 3
+
+
+# list()/tuple() resume from inside the constructor call (a deeper frame).
+assert list(gen_simple()) == [1, 2, 3]
+assert tuple(gen_simple()) == (1, 2, 3)
+
+# Top-level next() across several resumes.
+it = gen_simple()
+assert next(it) == 1
+assert next(it) == 2
+assert next(it) == 3
+
+
+# Generator with parameters and locals carried across yields: exercises a
+# non-zero locals_count when the frame is rebased.
+def running_total(n):
+    total = 0
+    for i in range(n):
+        total += i
+        yield total
+
+
+assert list(running_total(5)) == [0, 1, 3, 6, 10]
+
+
+# Nested `yield from` consumed by list().
+def inner():
+    yield from [1, 2, 3]
+
+
+def outer():
+    yield from inner()
+    yield 4
+
+
+assert list(outer()) == [1, 2, 3, 4]
+
+
+# Two generators alive at once, advanced in interleaved order.
+def tagged(tag):
+    yield tag
+    yield tag + 10
+
+
+a = tagged(1)
+b = tagged(2)
+assert next(a) == 1
+assert next(b) == 2
+assert next(a) == 11
+assert next(b) == 12
+
+
+# The `for` path (which already worked) must keep working.
+collected = []
+for value in gen_simple():
+    collected.append(value)
+assert collected == [1, 2, 3]
+
+
+# A generator consumed from inside another function-call frame.
+def consume_first(iterator):
+    return next(iterator)
+
+
+assert consume_first(gen_simple()) == 1

integration/tests/regalloc_exception_liveness.py

@@ -0,0 +1,72 @@
+# Regression: exception-handler edges must be modelled in liveness.
+#
+# An operation inside a try body can transfer to the handler, but that edge is
+# not in the explicit CFG. When liveness ignored it, a value live across the try
+# body via the handler path (e.g. a FOR_ITER iterator, or a value used after the
+# handler) had its register reused inside the try body and was clobbered when an
+# exception actually unwound.
+
+
+# A for-loop whose body raises and catches: the iterator must survive the try
+# body. Previously clobbered (abort in FOR_ITER / "object is not an iterator").
+seen = []
+for x in [1, 2, 3]:
+    try:
+        raise ValueError("m")
+    except ValueError:
+        pass
+    seen.append(x)
+assert seen == [1, 2, 3], seen
+
+# Same over range() and over a list of types, with the exception bound.
+total = 0
+for x in range(4):
+    try:
+        raise ValueError("m")
+    except ValueError as e:
+        assert str(e) == "m"
+    total += x
+assert total == 6, total
+
+for exc in [ValueError, KeyError, RuntimeError, TypeError, NameError]:
+    try:
+        raise exc("msg")
+    except BaseException as e:
+        assert isinstance(e, exc), exc
+        assert e.args == ("msg",), (exc, e.args)
+
+# Sequential try/except in one frame must not leak the prior exception's args.
+try:
+    raise ValueError("hello")
+except ValueError as e:
+    assert e.args == ("hello",), e.args
+try:
+    raise ValueError("a", "b")
+except ValueError as e:
+    assert e.args == ("a", "b"), e.args
+
+# A recursive call whose result must survive a following try/except (the
+# original minimal miscompile repro).
+def fib(n):
+    return n if n < 2 else fib(n - 1) + fib(n - 2)
+
+
+assert fib(10) == 55
+try:
+    raise ValueError("e")
+except ValueError as e:
+    assert str(e) == "e"
+
+# Nested try/except inside a loop.
+acc = 0
+for x in [1, 2, 3]:
+    try:
+        try:
+            raise ValueError(x)
+        except KeyError:
+            pass
+    except ValueError as e:
+        acc += e.args[0]
+assert acc == 6, acc
+
+print("REGALLOC_EXCEPTION_LIVENESS_OK")