Add test case for documents that get rotated incorrectly after deskew

ocrmypdf/pageinfo.py

@@ -376,6 +376,11 @@ def _pdf_get_pageinfo(infile, pageno: int):
     pageinfo['width_inches'] = width_pt / Decimal(72.0)
     pageinfo['height_inches'] = height_pt / Decimal(72.0)
 
+    try:
+        pageinfo['rotate'] = int(page['/Rotate'])
+    except KeyError:
+        pageinfo['rotate'] = 0
+
     try:
         contentstream = pypdf.pdf.ContentStream(page.getContents(), pdf)
     except AttributeError as e:

tests/resources/README.rst

@@ -82,14 +82,14 @@ Assemblies
 
 These test resources are assemblies from other previously mentioned files, released under the same license terms as their input files.
 
-- cardinal.pdf (four cardinal directions, rotated copies of LinnSequencer.jpg)
+- cardinal.pdf (four cardinal directions, baked-in rotated copies of LinnSequencer.jpg)
 - ccitt.pdf (LinnSequencer.jpg, converted to CCITT encoding)
 - encrypted_algo4.pdf (congress.jpg, encrypted with algorithm 4 - not supported by PyPDF2)
 - graph_ocred.pdf (from graph.pdf)
 - jbig2.pdf (congress.jpg, converted to JBIG2 encoding)
 - multipage.pdf (from several other files)
 - palette.pdf (congress.jpg, converted to a 256-color palette)
-- skew.pdf (from c02-22.pdf)
+- skew.pdf (from LinnSequencer.jpg, skew simulated by adjusting the transformation matrix)
 - skew-encrypted.pdf (skew.pdf with encryption - access supported by PyPDF2)
 
 

tests/test_main.py

@@ -688,3 +688,36 @@ def test_linearized_pdf_and_indirect_object(spoof_tesseract_noop):
     check_ocrmypdf(
         'epson.pdf', 'test_epson.pdf',
         env=spoof_tesseract_noop)
+
+
+def test_rotated_skew_timeout():
+    """This document contains an image that is rotated 90 into place with a
+    /Rotate tag and intentionally skewed by altering the transformation matrix.
+
+    This tests for a bug where the combinatino of preprocessing and a tesseract
+    timeout produced a page whose dimensions did not match the original's.
+    """
+
+    input_file = _infile('rotated_skew.pdf')
+    in_pageinfo = pdf_get_all_pageinfo(input_file)[0]
+
+    assert in_pageinfo['height_pixels'] < in_pageinfo['width_pixels'], \
+        "Expected the input page to be landscape"
+    assert in_pageinfo['rotate'] == 90, "Expected a rotated page"
+
+    out = check_ocrmypdf(
+        'rotated_skew.pdf', 'test_rotated_skew.pdf',
+        '--deskew', '--tesseract-timeout', '0')
+
+    out_pageinfo = pdf_get_all_pageinfo(out)[0]
+
+    assert out_pageinfo['height_pixels'] > out_pageinfo['width_pixels'], \
+        "Expected the output page to be portrait"
+
+    assert out_pageinfo['rotate'] == 0, \
+        "Expected no page rotation for output"
+
+    assert in_pageinfo['width_pixels'] == out_pageinfo['height_pixels'] and \
+        in_pageinfo['height_pixels'] == out_pageinfo['width_pixels'], \
+        "Expected page rotation to be baked in"
+