Improve PDF/A validity checking at end

ocrmypdf/__init__.py

@@ -8,7 +8,7 @@ class ExitCode(IntEnum):
     bad_args = 1
     input_file = 2
     missing_dependency = 3
-    invalid_output_pdfa = 4
+    invalid_output_pdf = 4
     file_access_error = 5
     already_done_ocr = 6
     child_process_error = 7

ocrmypdf/main.py

@@ -27,7 +27,7 @@ import ruffus.proxy_logger as proxy_logger
 
 from .hocrtransform import HocrTransform
 from .pageinfo import pdf_get_all_pageinfo
-from .pdfa import generate_pdfa_def
+from .pdfa import generate_pdfa_def, file_claims_pdfa
 from . import ghostscript
 from . import tesseract
 from . import qpdf
@@ -127,8 +127,12 @@ parser.add_argument(
     '--image-dpi', metavar='DPI', type=int,
     help="for input image instead of PDF, use this DPI instead of file's")
 parser.add_argument(
-    '--output-type', choices=['pdfa', 'pdf'], default='pdf',
-    help="choose output type")
+    '--output-type', choices=['pdfa', 'pdf'], default='pdfa',
+    help="Choose output type. 'pdfa' creates a PDF/A-2b compliant file for "
+         "long term archiving (default, recommended) but may not suitable "
+         "for users who want their file altered as little as possible. 'pdfa' "
+         "also has problems with full Unicode text. 'pdf' attempts to "
+         "preserve file contents as much as possible.")
 
 metadata = parser.add_argument_group(
     "Metadata options",
@@ -1220,12 +1224,6 @@ def copy_final(
     shutil.copy(input_file, output_file)
 
 
-def validate_pdfa(
-        input_file,
-        log):
-    return qpdf.check(input_file, log)
-
-
 def available_cpu_count():
     try:
         return multiprocessing.cpu_count()
@@ -1360,9 +1358,17 @@ def run_pipeline():
         _log.error(e)
         return ExitCode.other_error
 
-    if not validate_pdfa(options.output_file, _log):
-        _log.warning('Output file: The generated PDF/A file is INVALID')
-        return ExitCode.invalid_output_pdfa
+    if options.output_type == 'pdfa':
+        pdfa_info = file_claims_pdfa(options.output_file)
+        if pdfa_info['pass']:
+            _log.info(pdfa_info['message'])
+        else:
+            _log.warning(pdfa_info['message'])
+            return ExitCode.invalid_output_pdf
+
+    if not qpdf.check(options.output_file, _log):
+        _log.warning('Output file: The generated PDF is INVALID')
+        return ExitCode.invalid_output_pdf
 
     with _pdfinfo_lock:
         _log.debug(_pdfinfo)

ocrmypdf/pdfa.py

@@ -7,6 +7,7 @@ from __future__ import print_function, absolute_import, division
 from string import Template
 import codecs
 import pkg_resources
+import PyPDF2 as pypdf
 
 ICC_PROFILE_RELPATH = 'data/sRGB.icc'
 
@@ -108,3 +109,39 @@ def generate_pdfa_def(target_filename, pdfmark, icc='sRGB'):
     # answer), insist on ascii
     with open(target_filename, 'w', encoding='ascii') as f:
         f.write(ps)
+
+
+def file_claims_pdfa(filename):
+    """Determines if the file claims to be PDF/A compliant
+
+    Checking if a file is a truly compliant PDF/A is a massive undertaking
+    that no open source tool does properly.  Some commercial tools are
+    generally reliable (Acrobat).
+
+    This checks if the XMP metadata contains a PDF/A marker.
+    """
+
+    pdf = pypdf.PdfFileReader(filename)
+    xmp = pdf.getXmpMetadata()
+
+    pdfa_nodes = xmp.getNodesInNamespace(
+        aboutUri='',
+        namespace='http://www.aiim.org/pdfa/ns/id/')
+
+    pdfa_dict = {attr.localName: attr.value for attr in pdfa_nodes}
+    pdfa_dict['pass'] = False
+    if pdfa_dict:
+        part_conformance = pdfa_dict['part'] + pdfa_dict['conformance']
+        valid_part_conforms = {'1A', '1B', '2A', '2B', '2U', '3A', '3B', '3U'}
+
+        message = 'File claims to be PDF/A-{}'.format(
+            part_conformance)
+
+        if part_conformance in valid_part_conforms:
+            pdfa_dict['pass'] = True
+        pdfa_dict['message'] = message
+    else:
+        pdfa_dict['message'] = 'File is a regular PDF'
+
+    return pdfa_dict
+