Fix non-square image resolution for "hocr" case; use img2pdf 0.2.1

Tesseract renderer not immediately fixable.

ocrmypdf/main.py

@@ -637,10 +637,14 @@ def rasterize_with_ghostscript(
             device = 'pnggray'
 
     log.debug("Rasterize {0} with {1}".format(
-            os.path.basename(input_file), device))
+              os.path.basename(input_file), device))
 
-    xres, yres = get_page_dpi(pageinfo)
-    ghostscript.rasterize_pdf(input_file, output_file, xres, yres, device, log)
+    # Produce the page image with square resolution or else deskew and OCR
+    # will not work properly
+    dpi = get_page_square_dpi(pageinfo)
+    ghostscript.rasterize_pdf(
+        input_file, output_file, xres=dpi, yres=dpi, raster_device=device,
+        log=log)
 
 
 @transform(
@@ -767,18 +771,16 @@ def select_image_layer(
         re_symlink(page_pdf, output_file)
     else:
         pageinfo = get_pageinfo(image, pdfinfo, pdfinfo_lock)
-
-        dpi = round(get_page_square_dpi(pageinfo))
-        imgsize = ((img2pdf.ImgSize.dpi, dpi), (img2pdf.ImgSize.dpi, dpi))
-
-        layout_fun = img2pdf.get_layout_fun(None, imgsize, None, None, None)
+        dpi = get_page_dpi(pageinfo)
+        dpi = float(dpi[0]), float(dpi[1])
+        layout_fun = img2pdf.get_fixed_dpi_layout_fun(dpi)
 
         with open(image, 'rb') as imfile, \
                 open(output_file, 'wb') as pdf:
             rawdata = imfile.read()
-            pdf.write(img2pdf.convert(
-                rawdata, producer="img2pdf", with_pdfrw=False,
-                layout_fun=layout_fun))
+            img2pdf.convert(
+                rawdata, with_pdfrw=False,
+                layout_fun=layout_fun, outputstream=pdf)
 
 
 @active_if(options.pdf_renderer == 'hocr')

tests/resources/README.rst

@@ -31,6 +31,7 @@ Files generated for this project
 The following test resources were crafted specifically for this project, and can be used
 under the terms of the license in LICENSE.rst.
 
+- aspect.pdf (a page with an image with 200 x 100 DPI resolution)
 - blank.pdf (a blank PDF page)
 - cmyk.pdf (a CMYK image created in Photoshop)
 - enormous.pdf (a very lage page)

tests/test_main.py

@@ -562,3 +562,22 @@ def test_old_unpaper():
 def test_algo4():
     sh, _, _ = run_ocrmypdf_env('encrypted_algo4.pdf', 'wontwork.pdf')
     assert sh.returncode == ExitCode.encrypted_pdf
+
+
+@pytest.mark.parametrize('renderer', [
+    'hocr'])
+def test_non_square_resolution(renderer):
+    # Confirm input image is non-square resolution
+    in_pageinfo = pdf_get_all_pageinfo(_infile('aspect.pdf'))
+    assert in_pageinfo[0]['xres'] != in_pageinfo[0]['yres']
+
+    out = 'aspect_%s.pdf' % renderer
+    check_ocrmypdf(
+        'aspect.pdf', out,
+        '--pdf-renderer', renderer)
+
+    out_pageinfo = pdf_get_all_pageinfo(_outfile(out))
+
+    # Confirm resolution was kept the same
+    assert in_pageinfo[0]['xres'] == out_pageinfo[0]['xres']
+    assert in_pageinfo[0]['yres'] == out_pageinfo[0]['yres']