Add tests for egg-info package with no installed modules

This corresponds to the qiskit[1] meta-package which:

  - does not contain any (runtime) Python code itself, but serves as a
    mechanism to install its transitive dependencies (which populate the
    qiskit package namespace).

  - is distributed as a source archive.

  - includes a top_level.txt which is empty (contains a single newline),
    arguably correct given that it does not directly install any
    importable packages/modules.

  - when installed as an egg, provides a SOURCES.txt which is incorrect
    from a runtime POV: it references 3 .py files, a setup.py and two
    files under test/, none of which are actually installed.

  - when installed (as an egg) by pip, provides an installed-files.txt
    file which is _more_ accurate than SOURCES.txt, since it reflects
    the files that are actually available after installation.

importlib_metadata reports incorrect .files for this package, because
we end up using SOURCES.txt. It is better to use installed-files.txt
when it is available.

Furthermore, as a result of this, packages_distributions() also
incorrectly reports that this packages provides imports names that do
not actually exist ("setup" and "test", in qiskit's case).

This commit adds EggInfoPkgPipInstalledNoModules, a test project that
mimics the egg installation of qiskit, and adds it to existing test
cases, as well as adding a new test cases specifically for verifying
packages_distributions() with egg-info packages. The following tests
fail in this commit, but will be fixed in the next commit:

  - PackagesDistributionsTest.test_packages_distributions_on_eggs
  - APITests.test_files_egg_info

See the python#115 issue for more details.

[1]: qiskit is found at https://pypi.org/project/qiskit/0.41.1/#files

tests/fixtures.py

@@ -213,6 +213,54 @@ def setUp(self):
         build_files(EggInfoPkg.files, prefix=self.site_dir)
 
 
+class EggInfoPkgPipInstalledNoModules(OnSysPath, SiteDir):
+    files: FilesDef = {
+        "empty_egg_pkg.egg-info": {
+            "PKG-INFO": """
+                Name: empty_egg-pkg
+                Author: Steven Ma
+                License: Unknown
+                Version: 1.0.0
+                Classifier: Intended Audience :: Developers
+                Classifier: Topic :: Software Development :: Libraries
+                Keywords: sample package
+                Description: Once upon a time
+                        There was an egginfo package
+                        with no modules and only transitive dependencies
+                """,
+            # SOURCES.txt is made from the source archive, and contains files
+            # (setup.py) that are not present after installation.
+            "SOURCES.txt": """
+                setup.py
+                empty_egg_pkg.egg-info/PKG-INFO
+                empty_egg_pkg.egg-info/SOURCES.txt
+                empty_egg_pkg.egg-info/requires.txt
+                empty_egg_pkg.egg-info/top_level.txt
+            """,
+            # installed-files.txt is written by pip, and is a strictly more
+            # accurate source than SOURCES.txt as to the installed contents of
+            # the package.
+            "installed-files.txt": """
+                PKG-INFO
+                SOURCES.txt
+                requires.txt
+                top_level.txt
+            """,
+            "requires.txt": """
+                wheel >= 1.0; python_version >= "2.7"
+                [test]
+                pytest
+            """,
+            # top_level.txt correctly reflects that no modules are installed
+            "top_level.txt": b"\n",
+        },
+    }
+
+    def setUp(self):
+        super().setUp()
+        build_files(EggInfoPkgPipInstalledNoModules.files, prefix=self.site_dir)
+
+
 class EggInfoFile(OnSysPath, SiteDir):
     files: FilesDef = {
         "egginfo_file.egg-info": """

tests/test_api.py

@@ -27,12 +27,12 @@ def suppress_known_deprecation():
 
 class APITests(
     fixtures.EggInfoPkg,
+    fixtures.EggInfoPkgPipInstalledNoModules,
     fixtures.DistInfoPkg,
     fixtures.DistInfoPkgWithDot,
     fixtures.EggInfoFile,
     unittest.TestCase,
 ):
-
     version_pattern = r'\d+\.\d+(\.\d)?'
 
     def test_retrieves_version_of_self(self):
@@ -63,15 +63,28 @@ def test_prefix_not_matched(self):
                     distribution(prefix)
 
     def test_for_top_level(self):
-        self.assertEqual(
-            distribution('egginfo-pkg').read_text('top_level.txt').strip(), 'mod'
-        )
+        tests = [
+            ('egginfo-pkg', 'mod'),
+            ('empty_egg-pkg', ''),
+        ]
+        for pkg_name, expect_content in tests:
+            with self.subTest(pkg_name):
+                self.assertEqual(
+                    distribution(pkg_name).read_text('top_level.txt').strip(),
+                    expect_content,
+                )
 
     def test_read_text(self):
-        top_level = [
-            path for path in files('egginfo-pkg') if path.name == 'top_level.txt'
-        ][0]
-        self.assertEqual(top_level.read_text(), 'mod\n')
+        tests = [
+            ('egginfo-pkg', 'mod\n'),
+            ('empty_egg-pkg', '\n'),
+        ]
+        for pkg_name, expect_content in tests:
+            with self.subTest(pkg_name):
+                top_level = [
+                    path for path in files(pkg_name) if path.name == 'top_level.txt'
+                ][0]
+                self.assertEqual(top_level.read_text(), expect_content)
 
     def test_entry_points(self):
         eps = entry_points()
@@ -171,6 +184,7 @@ def test_files_dist_info(self):
 
     def test_files_egg_info(self):
         self._test_files(files('egginfo-pkg'))
+        self._test_files(files('empty_egg-pkg'))
 
     def test_version_egg_info_file(self):
         self.assertEqual(version('egginfo-file'), '0.1')

tests/test_main.py

@@ -170,11 +170,17 @@ def test_metadata_loads_egg_info(self):
         assert meta['Description'] == 'pôrˈtend'
 
 
-class DiscoveryTests(fixtures.EggInfoPkg, fixtures.DistInfoPkg, unittest.TestCase):
+class DiscoveryTests(
+    fixtures.EggInfoPkg,
+    fixtures.EggInfoPkgPipInstalledNoModules,
+    fixtures.DistInfoPkg,
+    unittest.TestCase,
+):
     def test_package_discovery(self):
         dists = list(distributions())
         assert all(isinstance(dist, Distribution) for dist in dists)
         assert any(dist.metadata['Name'] == 'egginfo-pkg' for dist in dists)
+        assert any(dist.metadata['Name'] == 'empty_egg-pkg' for dist in dists)
         assert any(dist.metadata['Name'] == 'distinfo-pkg' for dist in dists)
 
     def test_invalid_usage(self):
@@ -304,7 +310,11 @@ def test_packages_distributions_example2(self):
 
 
 class PackagesDistributionsTest(
-    fixtures.OnSysPath, fixtures.SiteDir, unittest.TestCase
+    fixtures.EggInfoPkg,
+    fixtures.EggInfoPkgPipInstalledNoModules,
+    fixtures.OnSysPath,
+    fixtures.SiteDir,
+    unittest.TestCase,
 ):
     def test_packages_distributions_neither_toplevel_nor_files(self):
         """
@@ -322,3 +332,24 @@ def test_packages_distributions_neither_toplevel_nor_files(self):
             prefix=self.site_dir,
         )
         packages_distributions()
+
+    def test_packages_distributions_on_eggs(self):
+        """
+        Test old-style egg packages with a variation of 'top_level.txt',
+        'SOURCES.txt', and 'installed-files.txt', available.
+        """
+        distributions = packages_distributions()
+
+        def import_names_from_package(package_name):
+            return {
+                import_name
+                for import_name, package_names in distributions.items()
+                if package_name in package_names
+            }
+
+        # egginfo-pkg declares one import ('mod') via top_level.txt
+        assert import_names_from_package('egginfo-pkg') == {'mod'}
+
+        # empty_egg-pkg should not be associated with any import names
+        # (top_level.txt is empty, and installed-files.txt has no .py files)
+        assert import_names_from_package('empty_egg-pkg') == set()