ENH: do not include uncommitted changes in the sdist

Including uncommitted changes in the sdist was implemented in #58
after the discussion in #53. However, the current behavior for which
uncommitted changes to files under version control are included but
not other files, is a hard to justify surprising half measure.

After careful analysis, it has been determined that none of the use
cases for this feature is still valid. Removing it makes the
implementation easier, and the behavior less surprising and easier to
document and explain.

While at it, modernize the associated test.

Author: dnicolodi

mesonpy/__init__.py

@@ -865,64 +865,57 @@ def _meson_version(self) -> str:
 
     def sdist(self, directory: Path) -> pathlib.Path:
         """Generates a sdist (source distribution) in the specified directory."""
-        # generate meson dist file
+        # Generate meson dist file.
         self._run(self._meson + ['dist', '--allow-dirty', '--no-tests', '--formats', 'gztar', *self._meson_args['dist']])
 
-        # move meson dist file to output path
         dist_name = f'{self._metadata.distribution_name}-{self._metadata.version}'
         meson_dist_name = f'{self._meson_name}-{self._meson_version}'
         meson_dist_path = pathlib.Path(self._build_dir, 'meson-dist', f'{meson_dist_name}.tar.gz')
-        sdist = pathlib.Path(directory, f'{dist_name}.tar.gz')
+        sdist_path = pathlib.Path(directory, f'{dist_name}.tar.gz')
 
-        with tarfile.open(meson_dist_path, 'r:gz') as meson_dist, mesonpy._util.create_targz(sdist) as tar:
+        with tarfile.open(meson_dist_path, 'r:gz') as meson_dist, mesonpy._util.create_targz(sdist_path) as sdist:
             for member in meson_dist.getmembers():
-                # calculate the file path in the source directory
-                assert member.name, member.name
-                member_parts = member.name.split('/')
-                if len(member_parts) <= 1:
-                    continue
-                path = self._source_dir.joinpath(*member_parts[1:])
-
-                if not path.exists() and member.isfile():
-                    # File doesn't exists on the source directory but exists on
-                    # the Meson dist, so it is generated file, which we need to
-                    # include.
-                    # See https://mesonbuild.com/Reference-manual_builtin_meson.html#mesonadd_dist_script
-
-                    # MESON_DIST_ROOT could have a different base name
-                    # than the actual sdist basename, so we need to rename here
+                if member.isfile():
                     file = meson_dist.extractfile(member.name)
-                    member.name = str(pathlib.Path(dist_name, *member_parts[1:]).as_posix())
-                    tar.addfile(member, file)
-                    continue
-
-                if not path.is_file():
-                    continue
 
-                info = tarfile.TarInfo(member.name)
-                file_stat = os.stat(path)
-                info.mtime = member.mtime
-                info.size = file_stat.st_size
-                info.mode = int(oct(file_stat.st_mode)[-3:], 8)
-
-                # rewrite the path if necessary, to match the sdist distribution name
-                if dist_name != meson_dist_name:
-                    info.name = pathlib.Path(
-                        dist_name,
-                        path.relative_to(self._source_dir)
-                    ).as_posix()
-
-                with path.open('rb') as f:
-                    tar.addfile(info, fileobj=f)
-
-            # add PKG-INFO to dist file to make it a sdist
-            pkginfo_info = tarfile.TarInfo(f'{dist_name}/PKG-INFO')
-            pkginfo_info.mtime = time.time()  # type: ignore[assignment]
+                    # Reset pax extended header.  The tar archive member may be
+                    # using pax headers to store some file metadata.  The pax
+                    # headers are not reset when the metadata is modified and
+                    # they take precedence when the member is deserialized.
+                    # This is relevant because when rewriting the member name,
+                    # the length of the path may shrink from being more than
+                    # 100 characters (requiring the path to be stored in the
+                    # pax headers) to being less than 100 characters. When this
+                    # happens, the tar archive member is serialized with the
+                    # shorter name in the regular header and the longer one in
+                    # the extended pax header.  The archives handled here are
+                    # not expected to use extended pax headers other than for
+                    # the ones required to encode file metadata.  The easiest
+                    # solution is to reset the pax extended headers.
+                    member.pax_headers = {}
+
+                    # Rewrite the path to match the sdist distribution name.
+                    stem = member.name.split('/', 1)[1]
+                    member.name = '/'.join((dist_name, stem))
+
+                    # Reset owner and group to root:root.  This mimics what
+                    # 'git archive' does and makes the sdist reproducible upon
+                    # being built by different users.
+                    member.uname = member.gname = 'root'
+                    member.uid = member.gid = 0
+
+                    sdist.addfile(member, file)
+
+            # Add 'PKG-INFO'.
+            member = tarfile.TarInfo(f'{dist_name}/PKG-INFO')
+            member.uid = member.gid = 0
+            member.uname = member.gname = 'root'
+            member.mtime = time.time()
             metadata = bytes(self._metadata.as_rfc822())
-            pkginfo_info.size = len(metadata)
-            tar.addfile(pkginfo_info, fileobj=io.BytesIO(metadata))
+            member.size = len(metadata)
+            sdist.addfile(member, io.BytesIO(metadata))
 
-        return sdist
+        return sdist_path
 
     def wheel(self, directory: Path) -> pathlib.Path:
         """Generates a wheel in the specified directory."""

tests/packages/long-path/meson.build

@@ -0,0 +1,5 @@
+# SPDX-FileCopyrightText: 2024 The meson-python developers
+#
+# SPDX-License-Identifier: MIT
+
+project('very-long-project-name-that-makes-the-paths-within-the-sdist-exceed-100-characters-xxxxxxxxxxxxxxxxx', version: '1.0.0')

tests/packages/long-path/pyproject.toml

@@ -0,0 +1,11 @@
+# SPDX-FileCopyrightText: 2021 The meson-python developers
+#
+# SPDX-License-Identifier: MIT
+
+[build-system]
+build-backend = 'mesonpy'
+requires = ['meson-python']
+
+[project]
+name = 'long-path'
+dynamic = ['version']

tests/test_sdist.py

@@ -3,6 +3,7 @@
 # SPDX-License-Identifier: MIT
 
 import os
+import pathlib
 import re
 import stat
 import sys
@@ -122,37 +123,35 @@ def test_contents_subdirs(sdist_subdirs):
 
 
 def test_contents_unstaged(package_pure, tmp_path):
-    new_data = textwrap.dedent('''
-    def bar():
-        return 'foo'
+    new = textwrap.dedent('''
+        def bar():
+            return 'foo'
     ''').strip()
 
-    with open('pure.py', 'r') as f:
-        old_data = f.read()
-
-    try:
-        with in_git_repo_context():
-            with open('pure.py', 'w') as f, open('crap', 'x'):
-                f.write(new_data)
+    old = pathlib.Path('pure.py').read_text()
 
+    with in_git_repo_context():
+        try:
+            pathlib.Path('pure.py').write_text(new)
+            pathlib.Path('other.py').touch()
             sdist_path = mesonpy.build_sdist(os.fspath(tmp_path))
-    finally:
-        with open('pure.py', 'w') as f:
-            f.write(old_data)
-        os.unlink('crap')
+        finally:
+            pathlib.Path('pure.py').write_text(old)
+            pathlib.Path('other.py').unlink()
 
     with tarfile.open(tmp_path / sdist_path, 'r:gz') as sdist:
         names = {member.name for member in sdist.getmembers()}
         mtimes = {member.mtime for member in sdist.getmembers()}
-        read_data = sdist.extractfile('pure-1.0.0/pure.py').read().replace(b'\r\n', b'\n')
+        data = sdist.extractfile('pure-1.0.0/pure.py').read().replace(b'\r\n', b'\n')
 
+    # Verify that uncommitted changes are not included in the sdist.
     assert names == {
         'pure-1.0.0/PKG-INFO',
         'pure-1.0.0/meson.build',
         'pure-1.0.0/pure.py',
         'pure-1.0.0/pyproject.toml',
     }
-    assert read_data == new_data.encode()
+    assert data == old.encode()
 
     # All the archive members have a valid mtime.
     assert 0 not in mtimes
@@ -192,3 +191,17 @@ def test_generated_files(sdist_generated_files):
 
     # All the archive members have a valid mtime.
     assert 0 not in mtimes
+
+
+def test_long_path(sdist_long_path):
+    # See https://github.com/mesonbuild/meson-python/pull/587#pullrequestreview-2020891328
+    # and https://github.com/mesonbuild/meson-python/pull/587#issuecomment-2075973593
+
+    with tarfile.open(sdist_long_path, 'r:gz') as sdist:
+        names = {member.name for member in sdist.getmembers()}
+
+    assert names == {
+        'long_path-1.0.0/PKG-INFO',
+        'long_path-1.0.0/meson.build',
+        'long_path-1.0.0/pyproject.toml'
+    }