TST: Xmp module

PyPDF2/generic.py

@@ -357,7 +357,7 @@ def readFromStream(
         return NumberObject.read_from_stream(stream)
 
 
-def readHexStringFromStream(
+def readHexStringFromStream(  # TODO: PEP8
     stream: StreamType,
 ) -> Union["TextStringObject", "ByteStringObject"]:
     stream.read(1)
@@ -380,7 +380,7 @@ def readHexStringFromStream(
     return createStringObject(b_(txt))
 
 
-def readStringFromStream(
+def readStringFromStream(  # TODO: PEP8
     stream: StreamType,
     forced_encoding: Union[None, str, List[str], Dict[int, str]] = None,
 ) -> Union["TextStringObject", "ByteStringObject"]:

PyPDF2/xmp.py

@@ -204,7 +204,7 @@ class XmpInformation(PdfObject):
     def __init__(self, stream: ContentStream) -> None:
         self.stream = stream
         doc_root: Document = parseString(self.stream.get_data())
-        self.rdfRoot: XmlElement = doc_root.getElementsByTagNameNS(
+        self.rdfRoot: XmlElement = doc_root.getElementsByTagNameNS(  # TODO: PEP8
             RDF_NAMESPACE, "RDF"
         )[0]
         self.cache: Dict[Any, Any] = {}

tests/test_xmp.py

@@ -1,8 +1,10 @@
 import os
 from datetime import datetime
+from tokenize import Number
 
 import pytest
 
+import PyPDF2.generic
 import PyPDF2.xmp
 from PyPDF2 import PdfReader
 
@@ -54,9 +56,51 @@ def test_regression_issue774():
     assert date.minute == 23
     assert date.second == 34
     assert date.microsecond == 123000
+    with pytest.raises(ValueError) as exc:
+        PyPDF2.xmp._converter_date("today")
+    assert exc.value.args[0].startswith("Invalid date format")
+
+    date = PyPDF2.xmp._converter_date("2021-04-28T12:23:01-03:00")
+    assert date.year == 2021
+    assert date.month == 4
+    assert date.day == 28
+    assert date.hour == 15
+    assert date.minute == 23
+    assert date.second == 1
+    assert date.microsecond == 0
 
 
 def test_regression_issue914():
     path = os.path.join(RESOURCE_ROOT, "issue-914-xmp-data.pdf")
     reader = PdfReader(path)
     assert reader.xmp_metadata.xmp_modifyDate == datetime(2022, 4, 9, 15, 22, 43)
+
+
+@pytest.mark.parametrize(
+    "x",
+    ["a", 42, 3.141, False, True],
+)
+def test_identity(x):
+    assert PyPDF2.xmp._identity(x) == x
+
+
+# def test_getter_bag():
+#     f = PyPDF2.xmp._getter_bag("namespace", "name")
+#     class Tst:  # to replace pdf
+#         strict = False
+
+#     reader = PdfReader(os.path.join(RESOURCE_ROOT, "commented-xmp.pdf"))
+#     xmp_info = reader.xmp_metadata
+#     # <?xpacket begin='' id='W5M0MpCehiHzreSzNTczkc9d'?>
+#     # <x:xmpmeta xmlns:x='adobe:ns:meta/' x:xmptk='Image::ExifTool 11.88'>
+#     # <rdf:RDF xmlns:rdf='http://www.w3.org/1999/02/22-rdf-syntax-ns#'>
+
+#     # <rdf:Description rdf:about=''
+#     # xmlns:tiff='http://ns.adobe.com/tiff/1.0/'>
+#     # <tiff:Artist>me</tiff:Artist>
+#     # </rdf:Description>
+#     # </rdf:RDF>
+#     # </x:xmpmeta>
+
+#     assert xmp_info is not None
+#     f(xmp_info)