Merge pull request #22 from thatch/fetch-metadata-as-bytes

Always consider metadata as utf-8.

src/pypi_simple/client.py

@@ -328,18 +328,20 @@ def download_package(
                         pass
                 raise
 
-    def get_package_metadata(
+    def get_package_metadata_bytes(
         self,
         pkg: DistributionPackage,
         verify: bool = True,
         timeout: float | tuple[float, float] | None = None,
-    ) -> str:
+    ) -> bytes:
         """
-        .. versionadded:: 1.3.0
+        .. versionadded:: 1.5.0
 
         Retrieve the `distribution metadata`_ for the given
-        `DistributionPackage`.  The metadata can then be parsed with, for
-        example, |the packaging package|_.
+        `DistributionPackage`.  This method is lower-level than
+        `PyPISimple.get_package_metadata` and is most appropriate if you want
+        to defer interpretation of the data (e.g. if you're just writing to a
+        file) or want to customize the handling of non-``utf-8`` data.
 
         Not all packages have distribution metadata available for download; the
         `DistributionPackage.has_metadata` attribute can be used to check
@@ -348,12 +350,6 @@ def get_package_metadata(
         of `~DistributionPackage.has_metadata`; if the server replies with a
         404, a `NoMetadataError` is raised.
 
-        .. _distribution metadata:
-           https://packaging.python.org/en/latest/specifications/core-metadata/
-        .. |the packaging package| replace:: the ``packaging`` package
-        .. _the packaging package:
-           https://packaging.pypa.io/en/stable/metadata.html
-
         :param DistributionPackage pkg:
             the distribution package to retrieve the metadata of
         :param bool verify:
@@ -383,7 +379,57 @@ def get_package_metadata(
         r.raise_for_status()
         digester.update(r.content)
         digester.finalize()
-        return r.text
+        return r.content
+
+    def get_package_metadata(
+        self,
+        pkg: DistributionPackage,
+        verify: bool = True,
+        timeout: float | tuple[float, float] | None = None,
+    ) -> str:
+        """
+        .. versionadded:: 1.3.0
+
+        Retrieve the `distribution metadata`_ for the given
+        `DistributionPackage`.  The metadata can then be parsed with, for
+        example, |the packaging package|_.
+
+        Not all packages have distribution metadata available for download; the
+        `DistributionPackage.has_metadata` attribute can be used to check
+        whether the repository reported the availability of the metadata.  This
+        method will always attempt to download metadata regardless of the value
+        of `~DistributionPackage.has_metadata`; if the server replies with a
+        404, a `NoMetadataError` is raised.
+
+        .. _distribution metadata:
+           https://packaging.python.org/en/latest/specifications/core-metadata/
+        .. |the packaging package| replace:: the ``packaging`` package
+        .. _the packaging package:
+           https://packaging.pypa.io/en/stable/metadata.html
+
+        :param DistributionPackage pkg:
+            the distribution package to retrieve the metadata of
+        :param bool verify:
+            whether to verify the metadata's digests against the retrieved data
+        :param timeout: optional timeout to pass to the ``requests`` call
+        :type timeout: float | tuple[float,float] | None
+
+        :raises NoMetadataError:
+            if the repository responds with a 404 error code
+        :raises requests.HTTPError: if the repository responds with an HTTP
+            error code other than 404
+        :raises NoDigestsError:
+            if ``verify`` is true and the given package's metadata does not
+            have any digests with known algorithms
+        :raises DigestMismatchError:
+            if ``verify`` is true and the digest of the downloaded data does
+            not match the expected value
+        """
+        return self.get_package_metadata_bytes(
+            pkg,
+            verify,
+            timeout,
+        ).decode("utf-8", "surrogateescape")
 
 
 class NoSuchProjectError(Exception):

test/test_client.py

@@ -844,3 +844,47 @@ def progress_cb(content_length: Optional[int]) -> ProgressTracker:
         assert spy.enter_called
         assert spy.exit_called
         assert spy.updates == [65535] * (size // 65535) + [size % 65535]
+
+
+@responses.activate
+def test_metadata_encoding() -> None:
+    responses.add(
+        method=responses.GET,
+        url="https://test.nil/simple/packages/example-0.0.1-py3-none-any.whl.metadata",
+        body=b"\xe2\x98\x83",  # unicode snowman
+    )
+    responses.add(
+        method=responses.GET,
+        url="https://test.nil/simple/packages/example-0.0.2-py3-none-any.whl.metadata",
+        body=b"\xff\xfe\x03\x26",  # unicode snowman in utf-16
+    )
+    with PyPISimple("https://test.nil/simple/") as simple:
+        pkg = DistributionPackage(
+            filename="example-0.0.1-py3-none-any.whl",
+            project="example",
+            version="0.0.1",
+            package_type="wheel",
+            url="https://test.nil/simple/packages/example-0.0.1-py3-none-any.whl",
+            digests={},
+            requires_python=None,
+            has_sig=None,
+            has_metadata=True,
+            metadata_digests={"sha1": "2686137311c038a99622242fdb662b88c221c08d"},
+        )
+        assert simple.get_package_metadata_bytes(pkg) == b"\xe2\x98\x83"
+        assert simple.get_package_metadata(pkg) == "\u2603"
+
+        pkg = DistributionPackage(
+            filename="example-0.0.2-py3-none-any.whl",
+            project="example",
+            version="0.0.2",
+            package_type="wheel",
+            url="https://test.nil/simple/packages/example-0.0.2-py3-none-any.whl",
+            digests={},
+            requires_python=None,
+            has_sig=None,
+            has_metadata=True,
+            metadata_digests={"sha1": "7381ac0d9ddb35e4074acfd9cf72ea47314da70b"},
+        )
+        assert simple.get_package_metadata_bytes(pkg) == b"\xff\xfe\x03\x26"
+        assert simple.get_package_metadata(pkg) == "\udcff\udcfe\u0003\u0026"