Fix file_uuid attribute for AIPs

A few cases were missing handling for the new `file-` prefix.
Also increments version to 3.11.

metsrw/__init__.py

@@ -43,7 +43,7 @@
 
 LOGGER = logging.getLogger(__name__)
 LOGGER.addHandler(logging.NullHandler())
-__version__ = "0.3.10"
+__version__ = "0.3.11"
 
 __all__ = [
     "Agent",

metsrw/fsentry.py

@@ -215,7 +215,9 @@ def file_id(self):
         if self.is_aip:
             if self._fileid:
                 return self._fileid
-            return os.path.splitext(os.path.basename(self.path))[0]
+            return (
+                utils.FILE_ID_PREFIX + os.path.splitext(os.path.basename(self.path))[0]
+            )
         return utils.FILE_ID_PREFIX + self.file_uuid
 
     def group_id(self):

metsrw/mets.py

@@ -439,12 +439,16 @@ def _analyze_fptr(fptr_elem, tree, entry_type):
         checksum = file_elem.get("CHECKSUM")
         checksumtype = file_elem.get("CHECKSUMTYPE")
         file_id_prefix = utils.FILE_ID_PREFIX
-        # If the file is an AIP, then its prefix is not "file-" but the
-        # name of the AIP. Therefore we need to get the extension-less
+        # If the file is an AIP, then its prefix is the name of the AIP,
+        # plus `file-` on 1.10+. Therefore we need to get the extension-less
         # basename of the AIP's path and remove its UUID suffix to ge
         # the prefix to remove from the FILEID attribute value.
         if entry_type.lower() == "archival information package":
-            file_id_prefix = os.path.splitext(os.path.basename(path))[0][:-36]
+            aip_name = os.path.splitext(os.path.basename(path))[0][:-36]
+            if file_id.startswith(file_id_prefix):
+                file_id_prefix = file_id_prefix + aip_name
+            else:
+                file_id_prefix = aip_name
         # If the file is part of a directory (with no intermediate item), then
         # its prefix *may not* be "file-" but the name of the file. This
         # pattern is found in old Archivematica METS files, e.g. see

tests/test_fsentry.py

@@ -65,6 +65,16 @@ def test_file_id_success(self):
         f = metsrw.FSEntry("level1.txt", file_uuid=file_uuid)
         assert f.file_id() == "file-" + file_uuid
 
+    def test_aip_file_id(self):
+        fsentry = metsrw.FSEntry(
+            file_uuid="9b9f129c-8062-471b-a009-9ee0ad655f08",
+            type="Archival Information Package",
+            path="/tmp/example-1-9b9f129c-8062-471b-a009-9ee0ad655f08.7z",
+        )
+        assert (
+            fsentry.file_id() == "file-example-1-9b9f129c-8062-471b-a009-9ee0ad655f08"
+        )
+
     def test_group_id_no_uuid(self):
         """ It should return no group ID. """
         f = metsrw.FSEntry("level1.txt")

tests/test_mets.py

@@ -343,6 +343,35 @@ def test_analyze_fptr_from_aip(self):
         assert fptr.file_uuid == "7327b00f-d83a-4ae8-bb89-84fce994e827"
         assert fptr.use == "Archival Information Package"
 
+    def test_analyze_fptr_sets_uuid_from_aip_with_file_id_prefix(self):
+        """
+        Test that AIP FILEIDs with a leading `file-` are parsed properly.
+        """
+        tree = etree.fromstring(
+            b"""<?xml version='1.0' encoding='utf-8'?>
+<mets:mets xmlns:mets="http://www.loc.gov/METS/" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.loc.gov/METS/ http://www.loc.gov/standards/mets/version111/mets.xsd">
+  <mets:fileSec>
+    <mets:fileGrp USE="Archival Information Package">
+      <mets:file ID="file-example-1-9b9f129c-8062-471b-a009-9ee0ad655f08">
+        <mets:FLocat OTHERLOCTYPE="SYSTEM" LOCTYPE="OTHER" xlink:href="/tmp/example-1-9b9f129c-8062-471b-a009-9ee0ad655f08.7z"/>
+      </mets:file>
+    </mets:fileGrp>
+  </mets:fileSec>
+  <mets:structMap TYPE="physical">
+    <mets:div ADMID="amdSec_1" TYPE="Archival Information Package">
+      <mets:fptr FILEID="file-example-1-9b9f129c-8062-471b-a009-9ee0ad655f08"/>
+    </mets:div>
+  </mets:structMap>
+</mets:mets>
+        """
+        )
+        fptr_elem = tree.find(".//mets:fptr[1]", namespaces=metsrw.utils.NAMESPACES)
+        fptr = metsrw.METSDocument()._analyze_fptr(
+            fptr_elem, tree, "Archival Information Package"
+        )
+
+        assert fptr.file_uuid == "9b9f129c-8062-471b-a009-9ee0ad655f08"
+
     def test_duplicate_ids(self):
         """
         We don't want duplicate ids to be generated, but if specified, they shouldn't break