Merge branch master into master-slp

The outcome of this merge is not functional.
Issue python#26647: Python interpreter now uses 16-bit wordcode instead of
bytecode.

Author: Anselm Kruis

Doc/library/dis.rst

@@ -31,9 +31,9 @@ the following command can be used to display the disassembly of
 
    >>> dis.dis(myfunc)
      2           0 LOAD_GLOBAL              0 (len)
-                 3 LOAD_FAST                0 (alist)
-                 6 CALL_FUNCTION            1
-                 9 RETURN_VALUE
+                 2 LOAD_FAST                0 (alist)
+                 4 CALL_FUNCTION            1
+                 6 RETURN_VALUE
 
 (The "2" is a line number).
 
@@ -682,8 +682,7 @@ iterations of the loop.
    .. XXX explain the WHY stuff!
 
 
-All of the following opcodes expect arguments.  An argument is two bytes, with
-the more significant byte last.
+All of the following opcodes use their arguments.
 
 .. opcode:: STORE_NAME (namei)
 

Lib/ctypes/test/test_values.py

@@ -79,9 +79,9 @@ class struct_frozen(Structure):
                 continue
             items.append((entry.name.decode("ascii"), entry.size))
 
-        expected = [("__hello__", 161),
-                    ("__phello__", -161),
-                    ("__phello__.spam", 161),
+        expected = [("__hello__", 139),
+                    ("__phello__", -139),
+                    ("__phello__.spam", 139),
                     ]
         self.assertEqual(items, expected, "PyImport_FrozenModules example "
             "in Doc/library/ctypes.rst may be out of date")

Lib/dis.py

@@ -285,7 +285,6 @@ def _get_instructions_bytes(code, varnames=None, names=None, constants=None,
     """
     labels = findlabels(code)
     starts_line = None
-    free = None
     for offset, op, arg in _unpack_opargs(code):
         if linestarts is not None:
             starts_line = linestarts.get(offset, None)
@@ -296,7 +295,7 @@ def _get_instructions_bytes(code, varnames=None, names=None, constants=None,
         argrepr = ''
         if arg is not None:
             #  Set argval to the dereferenced value of the argument when
-            #  availabe, and argrepr to the string representation of argval.
+            #  available, and argrepr to the string representation of argval.
             #    _disassemble_bytes needs the string repr of the
             #    raw name index for LOAD_GLOBAL, LOAD_CONST, etc.
             argval = arg
@@ -305,7 +304,7 @@ def _get_instructions_bytes(code, varnames=None, names=None, constants=None,
             elif op in hasname:
                 argval, argrepr = _get_name_info(arg, names)
             elif op in hasjrel:
-                argval = offset + 3 + arg
+                argval = offset + 2 + arg
                 argrepr = "to " + repr(argval)
             elif op in haslocal:
                 argval, argrepr = _get_name_info(arg, varnames)
@@ -352,23 +351,15 @@ def _disassemble_str(source, *, file=None):
 disco = disassemble                     # XXX For backwards compatibility
 
 def _unpack_opargs(code):
-    # enumerate() is not an option, since we sometimes process
-    # multiple elements on a single pass through the loop
     extended_arg = 0
-    n = len(code)
-    i = 0
-    while i < n:
+    for i in range(0, len(code), 2):
         op = code[i]
-        offset = i
-        i = i+1
-        arg = None
         if op >= HAVE_ARGUMENT:
-            arg = code[i] + code[i+1]*256 + extended_arg
-            extended_arg = 0
-            i = i+2
-            if op == EXTENDED_ARG:
-                extended_arg = arg*65536
-        yield (offset, op, arg)
+            arg = code[i+1] | extended_arg
+            extended_arg = (arg << 8) if op == EXTENDED_ARG else 0
+        else:
+            arg = None
+        yield (i, op, arg)
 
 def findlabels(code):
     """Detect all offsets in a byte code which are jump targets.
@@ -379,14 +370,14 @@ def findlabels(code):
     labels = []
     for offset, op, arg in _unpack_opargs(code):
         if arg is not None:
-            label = -1
             if op in hasjrel:
-                label = offset + 3 + arg
+                label = offset + 2 + arg
             elif op in hasjabs:
                 label = arg
-            if label >= 0:
-                if label not in labels:
-                    labels.append(label)
+            else:
+                continue
+            if label not in labels:
+                labels.append(label)
     return labels
 
 def findlinestarts(code):

Lib/importlib/_bootstrap_external.py

@@ -225,6 +225,7 @@ def _write_atomic(path, data, mode=0o666):
 #     Python 3.5b2  3350 (add GET_YIELD_FROM_ITER opcode #24400)
 #     Python 3.6a0  3360 (add FORMAT_VALUE opcode #25483
 #     Python 3.6a0  3361 (lineno delta of code.co_lnotab becomes signed)
+#     Python 3.6a0  3370 (16 bit wordcode)
 #
 # MAGIC must change whenever the bytecode emitted by the compiler may no
 # longer be understood by older implementations of the eval loop (usually
@@ -233,7 +234,7 @@ def _write_atomic(path, data, mode=0o666):
 # Whenever MAGIC_NUMBER is changed, the ranges in the magic_values array
 # in PC/launcher.c must also be updated.
 
-MAGIC_NUMBER = (3361).to_bytes(2, 'little') + b'\r\n'
+MAGIC_NUMBER = (3370).to_bytes(2, 'little') + b'\r\n'
 _RAW_MAGIC_NUMBER = int.from_bytes(MAGIC_NUMBER, 'little')  # For import.c
 
 _PYCACHE = '__pycache__'