Issue #13645: pyc files now contain the size of the corresponding source

code, to avoid timestamp collisions (especially on filesystems with a low
timestamp resolution) when checking for freshness of the bytecode.

2 files changed, 39 insertions, 15 deletions

diff --git a/Lib/importlib/test/source/test_abc_loader.py b/Lib/importlib/test/source/test_abc_loader.py
index 3c19b0b..74ca2e1 100644
--- a/Lib/importlib/test/source/test_abc_loader.py
+++ b/Lib/importlib/test/source/test_abc_loader.py
@@ -5,6 +5,7 @@ from .. import abc as testing_abc
 from .. import util
 from . import util as source_util
 
+import collections
 import imp
 import inspect
 import io
@@ -40,8 +41,10 @@ class SourceLoaderMock(SourceOnlyLoaderMock):
     def __init__(self, path, magic=imp.get_magic()):
         super().__init__(path)
         self.bytecode_path = imp.cache_from_source(self.path)
+        self.source_size = len(self.source)
         data = bytearray(magic)
         data.extend(marshal._w_long(self.source_mtime))
+        data.extend(marshal._w_long(self.source_size))
         code_object = compile(self.source, self.path, 'exec',
                                 dont_inherit=True)
         data.extend(marshal.dumps(code_object))
@@ -56,9 +59,9 @@ class SourceLoaderMock(SourceOnlyLoaderMock):
         else:
             raise IOError
 
-    def path_mtime(self, path):
+    def path_stats(self, path):
         assert path == self.path
-        return self.source_mtime
+        return {'mtime': self.source_mtime, 'size': self.source_size}
 
     def set_data(self, path, data):
         self.written[path] = bytes(data)
@@ -657,6 +660,7 @@ class SourceLoaderBytecodeTests(SourceLoaderTestHarness):
             self.assertIn(self.cached, self.loader.written)
             data = bytearray(imp.get_magic())
             data.extend(marshal._w_long(self.loader.source_mtime))
+            data.extend(marshal._w_long(self.loader.source_size))
             data.extend(marshal.dumps(code_object))
             self.assertEqual(self.loader.written[self.cached], bytes(data))
 
@@ -847,7 +851,7 @@ class AbstractMethodImplTests(unittest.TestCase):
         # Required abstractmethods.
         self.raises_NotImplementedError(ins, 'get_filename', 'get_data')
         # Optional abstractmethods.
-        self.raises_NotImplementedError(ins,'path_mtime', 'set_data')
+        self.raises_NotImplementedError(ins,'path_stats', 'set_data')
 
     def test_PyLoader(self):
         self.raises_NotImplementedError(self.PyLoader(), 'source_path',
diff --git a/Lib/importlib/test/source/test_file_loader.py b/Lib/importlib/test/source/test_file_loader.py
index de1c4d8..0809077 100644
--- a/Lib/importlib/test/source/test_file_loader.py
+++ b/Lib/importlib/test/source/test_file_loader.py
@@ -70,11 +70,6 @@ class SimpleTest(unittest.TestCase):
             module_dict_id = id(module.__dict__)
             with open(mapping['_temp'], 'w') as file:
                 file.write("testing_var = 42\n")
-            # For filesystems where the mtime is only to a second granularity,
-            # everything that has happened above can be too fast;
-            # force an mtime on the source that is guaranteed to be different
-            # than the original mtime.
-            loader.path_mtime = self.fake_mtime(loader.path_mtime)
             module = loader.load_module('_temp')
             self.assertTrue('testing_var' in module.__dict__,
                          "'testing_var' not in "
@@ -190,10 +185,17 @@ class BadBytecodeTest(unittest.TestCase):
                                                 del_source=del_source)
             test('_temp', mapping, bc_path)
 
+    def _test_partial_size(self, test, *, del_source=False):
+        with source_util.create_modules('_temp') as mapping:
+            bc_path = self.manipulate_bytecode('_temp', mapping,
+                                                lambda bc: bc[:11],
+                                                del_source=del_source)
+            test('_temp', mapping, bc_path)
+
     def _test_no_marshal(self, *, del_source=False):
         with source_util.create_modules('_temp') as mapping:
             bc_path = self.manipulate_bytecode('_temp', mapping,
-                                                lambda bc: bc[:8],
+                                                lambda bc: bc[:12],
                                                 del_source=del_source)
             file_path = mapping['_temp'] if not del_source else bc_path
             with self.assertRaises(EOFError):
@@ -202,7 +204,7 @@ class BadBytecodeTest(unittest.TestCase):
     def _test_non_code_marshal(self, *, del_source=False):
         with source_util.create_modules('_temp') as mapping:
             bytecode_path = self.manipulate_bytecode('_temp', mapping,
-                                    lambda bc: bc[:8] + marshal.dumps(b'abcd'),
+                                    lambda bc: bc[:12] + marshal.dumps(b'abcd'),
                                     del_source=del_source)
             file_path = mapping['_temp'] if not del_source else bytecode_path
             with self.assertRaises(ImportError):
@@ -211,7 +213,7 @@ class BadBytecodeTest(unittest.TestCase):
     def _test_bad_marshal(self, *, del_source=False):
         with source_util.create_modules('_temp') as mapping:
             bytecode_path = self.manipulate_bytecode('_temp', mapping,
-                                                lambda bc: bc[:8] + b'<test>',
+                                                lambda bc: bc[:12] + b'<test>',
                                                 del_source=del_source)
             file_path = mapping['_temp'] if not del_source else bytecode_path
             with self.assertRaises(EOFError):
@@ -235,7 +237,7 @@ class SourceLoaderBadBytecodeTest(BadBytecodeTest):
         def test(name, mapping, bytecode_path):
             self.import_(mapping[name], name)
             with open(bytecode_path, 'rb') as file:
-                self.assertGreater(len(file.read()), 8)
+                self.assertGreater(len(file.read()), 12)
 
         self._test_empty_file(test)
 
@@ -243,7 +245,7 @@ class SourceLoaderBadBytecodeTest(BadBytecodeTest):
         def test(name, mapping, bytecode_path):
             self.import_(mapping[name], name)
             with open(bytecode_path, 'rb') as file:
-                self.assertGreater(len(file.read()), 8)
+                self.assertGreater(len(file.read()), 12)
 
         self._test_partial_magic(test)
 
@@ -254,7 +256,7 @@ class SourceLoaderBadBytecodeTest(BadBytecodeTest):
         def test(name, mapping, bytecode_path):
             self.import_(mapping[name], name)
             with open(bytecode_path, 'rb') as file:
-                self.assertGreater(len(file.read()), 8)
+                self.assertGreater(len(file.read()), 12)
 
         self._test_magic_only(test)
 
@@ -276,11 +278,22 @@ class SourceLoaderBadBytecodeTest(BadBytecodeTest):
         def test(name, mapping, bc_path):
             self.import_(mapping[name], name)
             with open(bc_path, 'rb') as file:
-                self.assertGreater(len(file.read()), 8)
+                self.assertGreater(len(file.read()), 12)
 
         self._test_partial_timestamp(test)
 
     @source_util.writes_bytecode_files
+    def test_partial_size(self):
+        # When the size is partial, regenerate the .pyc, else
+        # raise EOFError.
+        def test(name, mapping, bc_path):
+            self.import_(mapping[name], name)
+            with open(bc_path, 'rb') as file:
+                self.assertGreater(len(file.read()), 12)
+
+        self._test_partial_size(test)
+
+    @source_util.writes_bytecode_files
     def test_no_marshal(self):
         # When there is only the magic number and timestamp, raise EOFError.
         self._test_no_marshal()
@@ -375,6 +388,13 @@ class SourcelessLoaderBadBytecodeTest(BadBytecodeTest):
 
         self._test_partial_timestamp(test, del_source=True)
 
+    def test_partial_size(self):
+        def test(name, mapping, bytecode_path):
+            with self.assertRaises(EOFError):
+                self.import_(bytecode_path, name)
+
+        self._test_partial_size(test, del_source=True)
+
     def test_no_marshal(self):
         self._test_no_marshal(del_source=True)