Merge pull request #8171 from radarhere/xmp

Tests/test_image.py

@@ -8,6 +8,7 @@ import sys
 import tempfile
 import warnings
 from pathlib import Path
+from types import ModuleType
 from typing import IO, Any
 
 import pytest
@@ -35,6 +36,12 @@ from .helper import (
     skip_unless_feature,
 )
 
+ElementTree: ModuleType | None
+try:
+    from defusedxml import ElementTree
+except ImportError:
+    ElementTree = None
+
 
 # Deprecation helper
 def helper_image_new(mode: str, size: tuple[int, int]) -> Image.Image:
@@ -921,6 +928,21 @@ class TestImage:
         with Image.open("Tests/images/hopper.gif") as im:
             assert im.getxmp() == {}
 
+    def test_getxmp_padded(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/" />\n<?xpacket end="w"?>\x00\x00'
+        )
+        if ElementTree is None:
+            with pytest.warns(
+                UserWarning,
+                match="XMP data cannot be read without defusedxml dependency",
+            ):
+                assert im.getxmp() == {}
+        else:
+            assert im.getxmp() == {"xmpmeta": None}
+
     @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)

src/PIL/Image.py

@@ -1511,7 +1511,7 @@ class Image:
             return {}
         if "xmp" not in self.info:
             return {}
-        root = ElementTree.fromstring(self.info["xmp"])
+        root = ElementTree.fromstring(self.info["xmp"].rstrip(b"\x00"))
         return {get_name(root.tag): get_value(root)}
 
     def getexif(self) -> Exif:

src/PIL/JpegImagePlugin.py

@@ -96,7 +96,7 @@ def APP(self, marker):
             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]
+        self.info["xmp"] = s.split(b"\x00", 1)[1]
     elif marker == 0xFFE2 and s[:5] == b"FPXR\0":
         # extract FlashPix information (incomplete)
         self.info["flashpix"] = s  # FIXME: value will change