Error out if trying to produce PDF/A >200” due to Ghostscript limitation

ocrmypdf/pdfinfo.py

@@ -693,6 +693,10 @@ class PdfInfo:
         # The minimum PDF is the maximum version that any particular page needs
         return max(page.min_version for page in self.pages)
 
+    @property
+    def has_userunit(self):
+        return any(page.userunit for page in self.pages)
+
     def __getitem__(self, item):
         return self._pages[item]
 

ocrmypdf/pipeline.py

@@ -184,9 +184,19 @@ def repair_pdf(
         output_file,
         log,
         context):
-
+    options = context.get_options()
     qpdf.repair(input_file, output_file, log)
     pdfinfo = PdfInfo(output_file)
+
+    if pdfinfo.has_userunit and options.output_type == 'pdfa':
+        log.error("This input file uses a PDF feature that is not supported "
+            "by Ghostscript, so you cannot use --output-type=pdfa for this "
+            "file. (Specifically, it uses the PDF-1.6 /UserUnit feature to "
+            "support very large or small page sizes, and Ghostscript cannot "
+            "output these files.)  Use --output-type=pdf instead."
+        )
+        raise InputFileError()
+
     context.set_pdfinfo(pdfinfo)
     log.debug(pdfinfo)
 
@@ -432,8 +442,8 @@ def rasterize_with_ghostscript(
             input_file, output_file, xres=dpi, yres=dpi,
             raster_device=device, log=log)
     else:
-        # Ghostscript respects /UserUnit when rasterizing so replace the
-        # image's DPI with the working DPI
+        # Ghostscript respects /UserUnit when rasterizing. Rasterize at
+        # the true DPI but rewrite the output image to the working DPI.
         ghostscript.rasterize_pdf(
             input_file, output_file + '.tmp', xres=true_dpi, yres=true_dpi,
             raster_device=device, log=log)
@@ -499,7 +509,7 @@ def select_ocr_image(
         infiles,
         output_file,
         log,
-        contenxt):
+        context):
     """Select the image we send for OCR. May not be the same as the display
     image depending on preprocessing."""
 

tests/test_userunit.py

@@ -0,0 +1,41 @@
+#!/usr/bin/env python3
+# © 2017 James R. Barlow: github.com/jbarlow83
+
+from subprocess import Popen, PIPE, check_output, check_call, DEVNULL
+import os
+import shutil
+import pytest
+from ocrmypdf.pdfinfo import PdfInfo, Colorspace, Encoding
+import PyPDF2 as pypdf
+from ocrmypdf.exceptions import ExitCode
+from ocrmypdf import leptonica
+from ocrmypdf.pdfa import file_claims_pdfa
+from ocrmypdf.exec import ghostscript
+import logging
+from math import isclose
+
+
+check_ocrmypdf = pytest.helpers.check_ocrmypdf
+run_ocrmypdf = pytest.helpers.run_ocrmypdf
+spoof = pytest.helpers.spoof
+
+@pytest.fixture
+def spoof_tesseract_noop():
+    return spoof(tesseract='tesseract_noop.py')
+
+
+@pytest.fixture
+def spoof_tesseract_cache():
+    if pytest.helpers.running_in_docker():
+        return os.environ.copy()
+    return spoof(tesseract="tesseract_cache.py")
+
+
+@pytest.fixture
+def poster(resources):
+    return resources / 'poster.pdf'
+
+
+def test_userunit_ghostscript_fails(poster, no_outpdf):
+    p, out, err = run_ocrmypdf(poster, no_outpdf, '--output-type=pdfa')
+    assert p.returncode == ExitCode.input_file