v4.3.2 release notes

It looks like GS 9.19 can incorrectly set overprinting for the text layer
even though this makes no sense in PDF/A, or at least someone produced
PDFs that have this after a Tesseract PDF -> GS PDF/A conversion. GS 9.20
complains about this. Instead of aborting, elide the feature.

See
http://git.ghostscript.com/?p=ghostpdl.git;a=commitdiff;h=094d5a1880f1cb9ed320ca9353eb69436e09b594
and
issue #107.

It looks like it is better to elide features and warn about elision rather
than abort with an error.

RELEASE_NOTES.rst

@@ -3,6 +3,12 @@ RELEASE NOTES
 
 OCRmyPDF uses `semantic versioning <http://semver.org/>`_.
 
+v4.3.2:
+=======
+
+-  Fixed a PDF/A creation issue with Ghostscript 9.20 
+
+
 v4.3.1:
 =======
 

ocrmypdf/ghostscript.py

@@ -56,7 +56,7 @@ def generate_pdfa(pdf_pages, output_file, threads=1):
             "-sProcessColorModel=DeviceRGB",
             "-dJPEGQ=95",
             "-dPDFA=2",
-            "-sPDFACompatibilityPolicy=2",
+            "-sPDFACompatibilityPolicy=1",
             "-sOutputFile=" + gs_pdf.name,
         ]
         args_gs.extend(pdf_pages)

ocrmypdf/pdfa.py

@@ -140,21 +140,20 @@ def file_claims_pdfa(filename):
                 'conformance': 'No XMP metadata'}
 
     pdfa_dict = {attr.localName: attr.value for attr in pdfa_nodes}
-    pdfa_dict['pass'] = False
+    if not pdfa_dict:
-    pdfa_dict['output'] = 'pdf'
+        return {'pass': False, 'output': 'pdf',
-    if pdfa_dict:
+                'conformance': 'No XMP metadata'}
-        part_conformance = pdfa_dict['part'] + pdfa_dict['conformance']
-        valid_part_conforms = {'1A', '1B', '2A', '2B', '2U', '3A', '3B', '3U'}
 
-        conformance = 'PDF/A-{}'.format(
+    part_conformance = pdfa_dict['part'] + pdfa_dict['conformance']
-            part_conformance)
+    valid_part_conforms = {'1A', '1B', '2A', '2B', '2U', '3A', '3B', '3U'}
 
-        if part_conformance in valid_part_conforms:
+    conformance = 'PDF/A-{}'.format(
-            pdfa_dict['pass'] = True
+        part_conformance)
-            pdfa_dict['output'] = 'pdfa'
+
-        pdfa_dict['conformance'] = conformance
+    if part_conformance in valid_part_conforms:
-    else:
+        pdfa_dict['pass'] = True
-        pdfa_dict['conformance'] = 'PDF'
+        pdfa_dict['output'] = 'pdfa'
+    pdfa_dict['conformance'] = conformance
 
     return pdfa_dict