More test cases

.gitignore

@@ -13,3 +13,5 @@ venv/
 bin/
 include/
 lib/
+pip-selfcheck.json
+pyvenv.cfg

ocrmypdf/main.py

@@ -642,7 +642,12 @@ def tesseract_ocr_and_render_pdf(
         pdfinfo,
         pdfinfo_lock):
 
-    input_image = next(ii for ii in input_files if ii.endswith('.png'))
+    input_image = next((ii for ii in input_files if ii.endswith('.png')), '')
+    input_pdf = next((ii for ii in input_files if ii.endswith('.pdf')))
+    if not input_image:
+        # Skipping this page
+        re_symlink(input_pdf, output_file)
+        return
 
     args_tesseract = [
         'tesseract',
@@ -662,8 +667,6 @@ def tesseract_ocr_and_render_pdf(
             log.error(stderr)
     except TimeoutError:
         p.kill()
-
-        input_pdf = next(ii for ii in input_files if ii.endswith('.pdf'))
         log.info("Tesseract - page timed out")
         re_symlink(input_pdf, output_file)
 

tests/test_main.py

@@ -134,7 +134,7 @@ def test_force_ocr():
 
 
 def test_skip_ocr():
-    out = check_ocrmypdf('graph_ocred.pdf', 'test_skip.pdf', '-s')
+    check_ocrmypdf('graph_ocred.pdf', 'test_skip.pdf', '-s')
 
 
 def check_ocr_timeout(renderer):
@@ -155,3 +155,15 @@ def test_skip_big():
     pdfinfo = pdf_get_all_pageinfo(out)
     assert pdfinfo[0]['has_text'] == False
 
+
+def check_maximum_options(renderer):
+    check_ocrmypdf(
+        'multipage.pdf', 'test_multipage%s.pdf' % renderer,
+        '-d', '-c', '-i', '-g', '-f', '-k', '--oversample', '300',
+        '--skip-big', '10', '--title', 'Too Many Weird Files',
+        '--author', 'py.test', '--pdf-renderer', renderer)
+
+
+def test_maximum_options():
+    yield check_maximum_options, 'hocr'
+    yield check_maximum_options, 'tesseract'