Merge pull request #8069 from radarhere/xmp

Tests/test_file_jpeg.py

@@ -948,6 +948,7 @@ def test_getxmp(self) -> None:
                 ):
                     assert im.getxmp() == {}
             else:
+                assert "xmp" in im.info
                 xmp = im.getxmp()
 
                 description = xmp["xmpmeta"]["RDF"]["Description"]

Tests/test_file_png.py

@@ -683,6 +683,7 @@ def test_getxmp(self) -> None:
                 ):
                     assert im.getxmp() == {}
             else:
+                assert "xmp" in im.info
                 xmp = im.getxmp()
 
                 description = xmp["xmpmeta"]["RDF"]["Description"]

Tests/test_file_tiff.py

@@ -759,6 +759,7 @@ def test_getxmp(self) -> None:
                 ):
                     assert im.getxmp() == {}
             else:
+                assert "xmp" in im.info
                 xmp = im.getxmp()
 
                 description = xmp["xmpmeta"]["RDF"]["Description"]

Tests/test_file_webp_metadata.py

@@ -129,6 +129,7 @@ def test_getxmp() -> None:
             ):
                 assert im.getxmp() == {}
         else:
+            assert "xmp" in im.info
             assert (
                 im.getxmp()["xmpmeta"]["xmptk"]
                 == "Adobe XMP Core 5.3-c011 66.145661, 2012/02/06-14:56:27        "

Tests/test_image.py

@@ -909,6 +909,10 @@ def test_exif_hide_offsets(self) -> None:
                     assert tag not in exif.get_ifd(0x8769)
                 assert exif.get_ifd(0xA005)
 
+    def test_empty_xmp(self) -> None:
+        with Image.open("Tests/images/hopper.gif") as im:
+            assert im.getxmp() == {}
+
     @pytest.mark.parametrize("size", ((1, 0), (0, 1), (0, 0)))
     def test_zero_tobytes(self, size: tuple[int, int]) -> None:
         im = Image.new("RGB", size)

docs/reference/Image.rst

@@ -195,6 +195,7 @@ This helps to get the bounding box coordinates of the input image::
 .. automethod:: PIL.Image.Image.getpalette
 .. automethod:: PIL.Image.Image.getpixel
 .. automethod:: PIL.Image.Image.getprojection
+.. automethod:: PIL.Image.Image.getxmp
 .. automethod:: PIL.Image.Image.histogram
 .. automethod:: PIL.Image.Image.paste
 .. automethod:: PIL.Image.Image.point

docs/releasenotes/8.3.0.rst

@@ -18,9 +18,9 @@ is not secure.
 
 - :py:meth:`~PIL.Image.Image.getexif` has used ``xml`` to potentially retrieve
   orientation data since Pillow 7.2.0. It has been refactored to use ``re`` instead.
-- :py:meth:`~PIL.JpegImagePlugin.JpegImageFile.getxmp` was added in Pillow 8.2.0. It
-  will now use ``defusedxml`` instead. If the dependency is not present, an empty
-  dictionary will be returned and a warning raised.
+- ``getxmp()`` was added to :py:class:`~PIL.JpegImagePlugin.JpegImageFile` in Pillow
+  8.2.0. It will now use ``defusedxml`` instead. If the dependency is not present, an
+  empty dictionary will be returned and a warning raised.
 
 Deprecations
 ============

src/PIL/Image.py

@@ -1459,7 +1459,14 @@ 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, xmp_tags):
+    def getxmp(self):
+        """
+        Returns a dictionary containing the XMP tags.
+        Requires defusedxml to be installed.
+
+        :returns: XMP tags in a dictionary.
+        """
+
         def get_name(tag: str) -> str:
             return re.sub("^{[^}]+}", "", tag)
 
@@ -1486,9 +1493,10 @@ def get_value(element):
         if ElementTree is None:
             warnings.warn("XMP data cannot be read without defusedxml dependency")
             return {}
-        else:
-            root = ElementTree.fromstring(xmp_tags)
-            return {get_name(root.tag): get_value(root)}
+        if "xmp" not in self.info:
+            return {}
+        root = ElementTree.fromstring(self.info["xmp"])
+        return {get_name(root.tag): get_value(root)}
 
     def getexif(self) -> Exif:
         """

src/PIL/ImageOps.py

@@ -717,6 +717,9 @@ def exif_transpose(image: Image.Image, *, in_place: bool = False) -> Image.Image
                     exif_image.info["XML:com.adobe.xmp"] = re.sub(
                         pattern, "", exif_image.info["XML:com.adobe.xmp"]
                     )
+                    exif_image.info["xmp"] = re.sub(
+                        pattern.encode(), b"", exif_image.info["xmp"]
+                    )
         if not in_place:
             return transposed_image
     elif not in_place:

src/PIL/JpegImagePlugin.py

@@ -95,6 +95,8 @@ def APP(self, marker):
         else:
             self.info["exif"] = s
             self._exif_offset = self.fp.tell() - n + 6
+    elif marker == 0xFFE1 and s[:29] == b"http://ns.adobe.com/xap/1.0/\x00":
+        self.info["xmp"] = s.split(b"\x00")[1]
     elif marker == 0xFFE2 and s[:5] == b"FPXR\0":
         # extract FlashPix information (incomplete)
         self.info["flashpix"] = s  # FIXME: value will change
@@ -500,21 +502,6 @@ def _getexif(self) -> dict[str, Any] | None:
     def _getmp(self):
         return _getmp(self)
 
-    def getxmp(self) -> dict[str, Any]:
-        """
-        Returns a dictionary containing the XMP tags.
-        Requires defusedxml to be installed.
-
-        :returns: XMP tags in a dictionary.
-        """
-
-        for segment, content in self.applist:
-            if segment == "APP1":
-                marker, xmp_tags = content.split(b"\x00")[:2]
-                if marker == b"http://ns.adobe.com/xap/1.0/":
-                    return self._getxmp(xmp_tags)
-        return {}
-
 
 def _getexif(self) -> dict[str, Any] | None:
     if "exif" not in self.info:

src/PIL/PngImagePlugin.py

@@ -624,6 +624,8 @@ def chunk_iTXt(self, pos: int, length: int) -> bytes:
                     return s
             else:
                 return s
+        if k == b"XML:com.adobe.xmp":
+            self.im_info["xmp"] = v
         try:
             k = k.decode("latin-1", "strict")
             lang = lang.decode("utf-8", "strict")
@@ -1053,19 +1055,6 @@ def getexif(self) -> Image.Exif:
 
         return super().getexif()
 
-    def getxmp(self) -> dict[str, Any]:
-        """
-        Returns a dictionary containing the XMP tags.
-        Requires defusedxml to be installed.
-
-        :returns: XMP tags in a dictionary.
-        """
-        return (
-            self._getxmp(self.info["XML:com.adobe.xmp"])
-            if "XML:com.adobe.xmp" in self.info
-            else {}
-        )
-
 
 # --------------------------------------------------------------------
 # PNG writer

src/PIL/TiffImagePlugin.py

@@ -1197,6 +1197,10 @@ def _seek(self, frame: int) -> None:
             self.__frame += 1
         self.fp.seek(self._frame_pos[frame])
         self.tag_v2.load(self.fp)
+        if XMP in self.tag_v2:
+            self.info["xmp"] = self.tag_v2[XMP]
+        elif "xmp" in self.info:
+            del self.info["xmp"]
         self._reload_exif()
         # fill the legacy tag/ifd entries
         self.tag = self.ifd = ImageFileDirectory_v1.from_v2(self.tag_v2)
@@ -1207,15 +1211,6 @@ def tell(self) -> int:
         """Return the current frame number"""
         return self.__frame
 
-    def getxmp(self) -> dict[str, Any]:
-        """
-        Returns a dictionary containing the XMP tags.
-        Requires defusedxml to be installed.
-
-        :returns: XMP tags in a dictionary.
-        """
-        return self._getxmp(self.tag_v2[XMP]) if XMP in self.tag_v2 else {}
-
     def get_photoshop_blocks(self):
         """
         Returns a dictionary of Photoshop "Image Resource Blocks".

src/PIL/WebPImagePlugin.py

@@ -101,15 +101,6 @@ def _getexif(self) -> dict[str, Any] | None:
             return None
         return self.getexif()._get_merged_dict()
 
-    def getxmp(self) -> dict[str, Any]:
-        """
-        Returns a dictionary containing the XMP tags.
-        Requires defusedxml to be installed.
-
-        :returns: XMP tags in a dictionary.
-        """
-        return self._getxmp(self.info["xmp"]) if "xmp" in self.info else {}
-
     def seek(self, frame: int) -> None:
         if not self._seek_check(frame):
             return