bpo-31183: dis now handles coroutines & async generators (GH-3077)

syncosmic · ncoghlan · commit fe2b56ab9212 · 2017-08-18T12:29:21.000+10:00
Coroutines and async generators use a distinct attribute name for their code objects, so this updates the `dis` module to correctly disassemble objects with those attributes. Due to the increase in the test module length, it also fixes some latent defects in the tests related to how the displayed source line numbers are extracted. https://bugs.python.org/issue31230 is a follow-up issue suggesting we may want to solve this a different way, by instead giving all these object types a common `__code__` attribute, avoiding the need for special casing in the `dis` module.
diff --git a/Doc/library/dis.rst b/Doc/library/dis.rst
@@ -53,8 +53,9 @@ code.
 .. class:: Bytecode(x, *, first_line=None, current_offset=None)
 
 
-   Analyse the bytecode corresponding to a function, generator, method, string
-   of source code, or a code object (as returned by :func:`compile`).
+   Analyse the bytecode corresponding to a function, generator, asynchronous
+   generator, coroutine, method, string of source code, or a code object (as
+   returned by :func:`compile`).
 
    This is a convenience wrapper around many of the functions listed below, most
    notably :func:`get_instructions`, as iterating over a :class:`Bytecode`
@@ -92,6 +93,9 @@ code.
       Return a formatted multi-line string with detailed information about the
       code object, like :func:`code_info`.
 
+   .. versionchanged:: 3.7
+      This can now handle coroutine and asynchronous generator objects.
+
 Example::
 
     >>> bytecode = dis.Bytecode(myfunc)
@@ -114,14 +118,18 @@ operation is being performed, so the intermediate analysis object isn't useful:
 .. function:: code_info(x)
 
    Return a formatted multi-line string with detailed code object information
-   for the supplied function, generator, method, source code string or code object.
+   for the supplied function, generator, asynchronous generator, coroutine,
+   method, source code string or code object.
 
    Note that the exact contents of code info strings are highly implementation
    dependent and they may change arbitrarily across Python VMs or Python
    releases.
 
    .. versionadded:: 3.2
 
+   .. versionchanged:: 3.7
+      This can now handle coroutine and asynchronous generator objects.
+
 
 .. function:: show_code(x, *, file=None)
 
@@ -141,12 +149,13 @@ operation is being performed, so the intermediate analysis object isn't useful:
 .. function:: dis(x=None, *, file=None, depth=None)
 
    Disassemble the *x* object.  *x* can denote either a module, a class, a
-   method, a function, a generator, a code object, a string of source code or
-   a byte sequence of raw bytecode.  For a module, it disassembles all functions.
-   For a class, it disassembles all methods (including class and static methods).
-   For a code object or sequence of raw bytecode, it prints one line per bytecode
-   instruction.  It also recursively disassembles nested code objects (the code
-   of comprehensions, generator expressions and nested functions, and the code
+   method, a function, a generator, an asynchronous generator, a couroutine,
+   a code object, a string of source code or a byte sequence of raw bytecode.
+   For a module, it disassembles all functions. For a class, it disassembles
+   all methods (including class and static methods). For a code object or
+   sequence of raw bytecode, it prints one line per bytecode instruction.
+   It also recursively disassembles nested code objects (the code of
+   comprehensions, generator expressions and nested functions, and the code
    used for building nested classes).
    Strings are first compiled to code objects with the :func:`compile`
    built-in function before being disassembled.  If no object is provided, this
@@ -164,6 +173,9 @@ operation is being performed, so the intermediate analysis object isn't useful:
    .. versionchanged:: 3.7
       Implemented recursive disassembling and added *depth* parameter.
 
+   .. versionchanged:: 3.7
+      This can now handle coroutine and asynchronous generator objects.
+
 
 .. function:: distb(tb=None, *, file=None)
 
diff --git a/Lib/dis.py b/Lib/dis.py
@@ -32,20 +32,30 @@ def _try_compile(source, name):
     return c
 
 def dis(x=None, *, file=None, depth=None):
-    """Disassemble classes, methods, functions, generators, or code.
+    """Disassemble classes, methods, functions, and other compiled objects.
 
     With no argument, disassemble the last traceback.
 
+    Compiled objects currently include generator objects, async generator
+    objects, and coroutine objects, all of which store their code object
+    in a special attribute.
     """
     if x is None:
         distb(file=file)
         return
-    if hasattr(x, '__func__'):  # Method
+    # Extract functions from methods.
+    if hasattr(x, '__func__'):
         x = x.__func__
-    if hasattr(x, '__code__'):  # Function
+    # Extract compiled code objects from...
+    if hasattr(x, '__code__'):  # ...a function, or
         x = x.__code__
-    if hasattr(x, 'gi_code'):  # Generator
+    elif hasattr(x, 'gi_code'):  #...a generator object, or
         x = x.gi_code
+    elif hasattr(x, 'ag_code'):  #...an asynchronous generator object, or
+        x = x.ag_code
+    elif hasattr(x, 'cr_code'):  #...a coroutine.
+        x = x.cr_code
+    # Perform the disassembly.
     if hasattr(x, '__dict__'):  # Class or module
         items = sorted(x.__dict__.items())
         for name, x1 in items:
@@ -107,16 +117,24 @@ def pretty_flags(flags):
     return ", ".join(names)
 
 def _get_code_object(x):
-    """Helper to handle methods, functions, generators, strings and raw code objects"""
-    if hasattr(x, '__func__'): # Method
+    """Helper to handle methods, compiled or raw code objects, and strings."""
+    # Extract functions from methods.
+    if hasattr(x, '__func__'):
         x = x.__func__
-    if hasattr(x, '__code__'): # Function
+    # Extract compiled code objects from...
+    if hasattr(x, '__code__'):  # ...a function, or
         x = x.__code__
-    if hasattr(x, 'gi_code'):  # Generator
+    elif hasattr(x, 'gi_code'):  #...a generator object, or
         x = x.gi_code
-    if isinstance(x, str):     # Source code
+    elif hasattr(x, 'ag_code'):  #...an asynchronous generator object, or
+        x = x.ag_code
+    elif hasattr(x, 'cr_code'):  #...a coroutine.
+        x = x.cr_code
+    # Handle source code.
+    if isinstance(x, str):
         x = _try_compile(x, "<disassembly>")
-    if hasattr(x, 'co_code'):  # Code object
+    # By now, if we don't have a code object, we can't disassemble x.
+    if hasattr(x, 'co_code'):
         return x
     raise TypeError("don't know how to disassemble %s objects" %
                     type(x).__name__)
@@ -443,8 +461,8 @@ def findlinestarts(code):
 class Bytecode:
     """The bytecode operations of a piece of code
 
-    Instantiate this with a function, method, string of code, or a code object
-    (as returned by compile()).
+    Instantiate this with a function, method, other compiled object, string of
+    code, or a code object (as returned by compile()).
 
     Iterating over this yields the bytecode operations as Instruction instances.
     """
diff --git a/Lib/test/test_dis.py b/Lib/test/test_dis.py
@@ -331,6 +331,13 @@ def _fstring(a, b, c, d):
 def _g(x):
     yield x
 
+async def _ag(x):
+    yield x
+
+async def _co(x):
+    async for item in _ag(x):
+        pass
+
 def _h(y):
     def foo(x):
         '''funcdoc'''
@@ -390,6 +397,7 @@ def foo(x):
        _h.__code__.co_firstlineno + 3,
 )
 
+
 class DisTests(unittest.TestCase):
 
     maxDiff = None
@@ -531,10 +539,22 @@ def test_disassemble_class_method(self):
         self.do_disassembly_test(_C.cm, dis_c_class_method)
 
     def test_disassemble_generator(self):
-        gen_func_disas = self.get_disassembly(_g)  # Disassemble generator function
-        gen_disas = self.get_disassembly(_g(1))  # Disassemble generator itself
+        gen_func_disas = self.get_disassembly(_g)  # Generator function
+        gen_disas = self.get_disassembly(_g(1))  # Generator iterator
         self.assertEqual(gen_disas, gen_func_disas)
 
+    def test_disassemble_async_generator(self):
+        agen_func_disas = self.get_disassembly(_ag)  # Async generator function
+        agen_disas = self.get_disassembly(_ag(1))  # Async generator iterator
+        self.assertEqual(agen_disas, agen_func_disas)
+
+    def test_disassemble_coroutine(self):
+        coro_func_disas = self.get_disassembly(_co)  # Coroutine function
+        coro = _co(1)  # Coroutine object
+        coro.close()  # Avoid a RuntimeWarning (never awaited)
+        coro_disas = self.get_disassembly(coro)
+        self.assertEqual(coro_disas, coro_func_disas)
+
     def test_disassemble_fstring(self):
         self.do_disassembly_test(_fstring, dis_fstring)
 
@@ -1051,11 +1071,13 @@ def test_explicit_first_line(self):
 
     def test_source_line_in_disassembly(self):
         # Use the line in the source code
-        actual = dis.Bytecode(simple).dis()[:3]
-        expected = "{:>3}".format(simple.__code__.co_firstlineno)
+        actual = dis.Bytecode(simple).dis()
+        actual = actual.strip().partition(" ")[0]  # extract the line no
+        expected = str(simple.__code__.co_firstlineno)
         self.assertEqual(actual, expected)
         # Use an explicit first line number
-        actual = dis.Bytecode(simple, first_line=350).dis()[:3]
+        actual = dis.Bytecode(simple, first_line=350).dis()
+        actual = actual.strip().partition(" ")[0]  # extract the line no
         self.assertEqual(actual, "350")
 
     def test_info(self):
diff --git a/Misc/NEWS.d/next/Library/2017-08-13-09-17-01.bpo-31183.-2_YGj.rst b/Misc/NEWS.d/next/Library/2017-08-13-09-17-01.bpo-31183.-2_YGj.rst
@@ -0,0 +1,2 @@
+`dis` now works with asynchronous generator and coroutine objects. Patch by
+George Collins based on diagnosis by Luciano Ramalho.

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,2 @@`
	`1`	+`dis` now works with asynchronous generator and coroutine objects. Patch by
	`2`	`+George Collins based on diagnosis by Luciano Ramalho.`