Fixed blank pages produced when NULs removed from metadata

.gitignore

@@ -3,9 +3,10 @@
 .pylintrc
 .pytest_cache/
 .ruffus_history.sqlite
-.venv/
+.venv*/
 *.pyc
 *.sublime-*
+*.DS_Store
 
 # Package building
 .eggs/
@@ -42,3 +43,4 @@ tests/resources/private/
 tmp/
 /debug_tests.py
 *.traineddata
+/private

docs/release_notes.rst

@@ -13,6 +13,11 @@ Note that it is licensed under GPLv3, so scripts that ``import ocrmypdf`` and ar
    find:    [^`]\#([0-9]{1,3})[^0-9]
    replace: `#$1 <https://github.com/jbarlow83/OCRmyPDF/issues/$1>`_
 
+v8.3.1
+------
+
+-   Fixed an issue where PDFs with malformed metadata would be rendered as blank pages. `#398 <https://github.com/jbarlow83/OCRmyPDF/issues/398>`_.
+
 v8.3.0
 ------
 

src/ocrmypdf/_pipeline.py

@@ -816,15 +816,17 @@ def convert_to_pdfa(input_files_groups, output_file, log, context):
     # 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.
+    modified = False
     with pikepdf.open(layers_file) as pdf_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)
+        if modified:
+            pdf_layers_file.save(layers_file + '_')
+    if modified:
+        os.replace(layers_file + '_', layers_file)
 
     ps = next((ii for ii in input_files if ii.endswith('.ps')), None)
     ghostscript.generate_pdfa(