Add strip_namespaces argument to Image.getxmp() (#9882)

Co-authored-by: Andrew Murray <radarhere@users.noreply.github.com>
Co-authored-by: Hugo van Kemenade <1324225+hugovk@users.noreply.github.com>

Author: 3 people

Tests/test_image.py

@@ -1015,6 +1015,34 @@ def test_empty_xmp(self) -> None:
                 xmp = im.getxmp()
             assert xmp == {}
 
+    @pytest.mark.skipif(ElementTree is None, reason="defusedxml is not installed")
+    def test_getxmp_strip_namespaces(self) -> None:
+        im = Image.new("RGB", (1, 1))
+        im.info["xmp"] = (
+            b'<?xpacket begin="\xef\xbb\xbf" id="W5M0MpCehiHzreSzNTczkc9d"?>\n'
+            b'<x:xmpmeta xmlns:x="adobe:ns:meta/">'
+            b'<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">'
+            b'<rdf:Description rdf:about=""'
+            b' xmlns:a="http://example.com/ns/a/"'
+            b' xmlns:b="http://example.com/ns/b/">'
+            b"<a:id>from-a</a:id>"
+            b"<b:id>from-b</b:id>"
+            b"</rdf:Description>"
+            b"</rdf:RDF>"
+            b'</x:xmpmeta>\n<?xpacket end="w"?>'
+        )
+
+        stripped = im.getxmp()
+        desc = stripped["xmpmeta"]["RDF"]["Description"]
+        assert desc["id"] == ["from-a", "from-b"]
+
+        full = im.getxmp(strip_namespaces=False)
+        desc_full = full["{adobe:ns:meta/}xmpmeta"][
+            "{http://www.w3.org/1999/02/22-rdf-syntax-ns#}RDF"
+        ]["{http://www.w3.org/1999/02/22-rdf-syntax-ns#}Description"]
+        assert desc_full["{http://example.com/ns/a/}id"] == "from-a"
+        assert desc_full["{http://example.com/ns/b/}id"] == "from-b"
+
     def test_getxmp_padded(self) -> None:
         im = Image.new("RGB", (1, 1))
         im.info["xmp"] = (

docs/releasenotes/13.0.0.rst

@@ -85,10 +85,14 @@ TODO
 API additions
 =============
 
-TODO
-^^^^
-
-TODO
+Added ``strip_namespaces`` argument to ``Image.getxmp()``
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+:py:meth:`~PIL.Image.Image.getxmp` now accepts an optional keyword argument of
+``strip_namespaces``. It is set to ``True`` by default, stripping each tag's XML
+namespace URI prefix as before. If set to ``False``, each tag's full
+``{namespace-uri}local-name`` form is kept instead, avoiding collisions between tags
+that share a local name across different namespaces.
 
 Other changes
 =============

src/PIL/Image.py

@@ -1571,16 +1571,29 @@ def getextrema(self) -> tuple[float, float] | tuple[tuple[int, int], ...]:
             return tuple(self.im.getband(i).getextrema() for i in range(self.im.bands))
         return self.im.getextrema()
 
-    def getxmp(self) -> dict[str, Any]:
+    def getxmp(self, *, strip_namespaces: bool = True) -> dict[str, Any]:
         """
         Returns a dictionary containing the XMP tags.
         Requires defusedxml to be installed.
 
+        :param strip_namespaces: If ``False``, keep each tag's full
+            ``{namespace-uri}local-name`` form instead of stripping the namespace
+            prefix.
+
+            .. versionadded:: 13.0.0
+
         :returns: XMP tags in a dictionary.
         """
 
-        def get_name(tag: str) -> str:
-            return re.sub("^{[^}]+}", "", tag)
+        if strip_namespaces:
+
+            def get_name(tag: str) -> str:
+                return re.sub("^{[^}]+}", "", tag)
+
+        else:
+
+            def get_name(tag: str) -> str:
+                return tag
 
         def get_value(element: Element) -> str | dict[str, Any] | None:
             value: dict[str, Any] = {get_name(k): v for k, v in element.attrib.items()}