Prevent Ghostscript from generating invalid XMP metadata

If DocumentInfo contains NULs Ghostscript will generate XMP with
NULs which is not allowed. Repair DocumentInfo before Ghostscript sees it.

src/ocrmypdf/_pipeline.py

@@ -810,6 +810,23 @@ def convert_to_pdfa(input_files_groups, output_file, log, context):
     layers_file = next(
         (ii for ii in input_files if ii.endswith('layers.rendered.pdf')), None
     )
+
+    # If the DocumentInfo record contains NUL characters, Ghostscript will
+    # produce XMP metadata which contains invalid XML entities (�).
+    # NULs in DocumentInfo seem to be common since older Acrobats included them.
+    # pikepdf can deal with this, but we make the world a better place by
+    # stamping them out as soon as possible.
+    pdf_layers_file = pikepdf.open(layers_file)
+    if pdf_layers_file.docinfo:
+        modified = False
+        for k, v in pdf_layers_file.docinfo.items():
+            if b'\x00' in bytes(v):
+                pdf_layers_file.docinfo[k] = bytes(v).replace(b'\x00', b'')
+                modified = True
+        if modified:
+            pdf_layers_file.save(layers_file)
+    del pdf_layers_file
+
     ps = next((ii for ii in input_files if ii.endswith('.ps')), None)
     ghostscript.generate_pdfa(
         pdf_version=input_pdfinfo.min_version,