Remove --threshold argument

Tesseract is now included better thresholding (binarization) in v5. Users that have
thresholding issues should try that first. If we find further problems
this can be brought back as a plugin.

misc/completion/ocrmypdf.bash

@@ -40,7 +40,7 @@ _ocrmypdf()
             --sidecar --version --jobs --quiet --verbose --title --author
             --subject --keywords --rotate-pages --remove-background --deskew
             --clean --clean-final --unpaper-args --oversample --remove-vectors
-            --threshold --force-ocr --skip-text --redo-ocr
+            --force-ocr --skip-text --redo-ocr
             --skip-big --jpeg-quality --png-quality --jbig2-lossy
             --max-image-mpixels --tesseract-config --tesseract-pagesegmode
             --help --tesseract-oem --pdf-renderer --tesseract-timeout

misc/completion/ocrmypdf.fish

@@ -29,7 +29,6 @@ complete -c ocrmypdf -s d -l deskew -d "fix small horizontal alignment skew"
 complete -c ocrmypdf -s c -l clean -d "clean document images before OCR"
 complete -c ocrmypdf -s i -l clean-final -d "clean document images and keep result"
 complete -c ocrmypdf -l remove-vectors -d "don't send vector objects to OCR"
-complete -c ocrmypdf -l threshold -d "threshold images before OCR"
 
 complete -c ocrmypdf -s f -l force-ocr -d "OCR documents that already have printable text"
 complete -c ocrmypdf -s s -l skip-ocr -d "skip OCR on pages that text, otherwise try OCR"

src/ocrmypdf/_pipeline.py

@@ -541,14 +541,6 @@ def create_ocr_image(image: Path, page_context: PageContext):
                 log.debug('blanking %r', pixcoords)
                 draw.rectangle(pixcoords, fill=white)
                 # draw.rectangle(pixcoords, outline=pink)
-
-        if options.threshold:
-            pix = leptonica.Pix.frompil(im)
-            pix = pix.masked_threshold_on_background_norm()
-            im_pix = pix.topil()
-            im_pix.info['dpi'] = im.info['dpi']
-            im = im_pix
-
         del draw
 
         filter_im = page_context.plugin_manager.hook.filter_ocr_image(

src/ocrmypdf/api.py

@@ -228,7 +228,6 @@ def ocr(  # pylint: disable=unused-argument
     unpaper_args: str = None,
     oversample: int = None,
     remove_vectors: bool = None,
-    threshold: bool = None,
     force_ocr: bool = None,
     skip_text: bool = None,
     redo_ocr: bool = None,

src/ocrmypdf/cli.py

@@ -287,14 +287,6 @@ Online documentation is located at:
         help="EXPERIMENTAL. Mask out any vector objects in the PDF so that they "
         "will not be included in OCR. This can eliminate false characters.",
     )
-    preprocessing.add_argument(
-        '--threshold',
-        action='store_true',
-        help=(
-            "EXPERIMENTAL. Threshold image to 1bpp before sending it to Tesseract "
-            "for OCR. Can improve OCR quality compared to Tesseract's thresholder."
-        ),
-    )
 
     ocrsettings = parser.add_argument_group("OCR options", "Control how OCR is applied")
     ocrsettings.add_argument(

tests/test_main.py

@@ -869,20 +869,6 @@ def test_image_dpi_not_image(caplog, resources, outpdf):
     assert '--image-dpi is being ignored' in caplog.text
 
 
-def test_image_dpi_threshold(resources, outpdf):
-    check_ocrmypdf(
-        resources / 'typewriter.png',
-        outpdf,
-        '--threshold',
-        '--image-dpi=170',
-        '--output-type=pdf',
-        '--optimize=0',
-        '--plugin',
-        'tests/plugins/tesseract_noop.py',
-    )
-    assert outpdf.exists()
-
-
 def test_outputtype_none_bad_setup(resources, outpdf):
     p, _out, err = run_ocrmypdf(
         resources / 'trivial.pdf',