Improve documentation for large image downsampling

docs/advanced.rst

@@ -114,6 +114,41 @@ exceed a certain number of megapixels with ``--skip-big``. (A 300 DPI,
     # Allow 300 seconds for OCR; skip any page larger than 50 megapixels
     ocrmypdf --tesseract-timeout 300 --skip-big 50 bigfile.pdf output.pdf
 
+OCR for huge images
+-------------------
+
+Separate from these settings, Tesseract has internal limits on the size
+of images it will process. If you issue
+``--tesseract-downsample-large-images``, OCRmyPDF will downsample images
+to fit Tesseract limits. (The limits are usually entered only for scanned
+images of oversized media, such as large maps or blueprints exceeding
+110 cm or 43 inches in either dimension, and at high DPI.)
+
+``--tesseract-downsample-above`` adjusts the threshold at which images
+will be downsampled. By default, only images that exceed any of Tesseract's
+internal limits are downsampled.
+
+You will also need to set ``--tesseract-timeout`` high enough to allow
+for processing.
+
+Only the image sent for OCR is downsampled. The original image is
+preserved.
+
+.. code-block:: bash
+
+    # Allow 600 seconds for OCR on huge images
+    ocrmypdf --tesseract-timeout 600 \
+        --tesseract-downsample-large-images \
+        bigfile.pdf output.pdf
+
+    # Downsample images above 5000 pixels on the longest dimension to
+    # 5000 pixels
+    ocrmypdf --tesseract-timeout 120 \
+        --tesseract-downsample-large-images \
+        --tesseract-downsample-above 5000 \
+        bigfile.pdf output_downsampled_ocr.pdf
+
+
 Overriding default tesseract
 ----------------------------
 

src/ocrmypdf/builtin_plugins/tesseract_ocr.py

@@ -30,7 +30,7 @@ def add_options(parser):
         action='append',
         metavar='CFG',
         default=[],
-        help="Additional Tesseract configuration files -- see documentation",
+        help="Additional Tesseract configuration files -- see documentation.",
     )
     tess.add_argument(
         '--tesseract-pagesegmode',
@@ -38,7 +38,7 @@ def add_options(parser):
         type=int,
         metavar='PSM',
         choices=range(0, 14),
-        help="Set Tesseract page segmentation mode (see tesseract --help)",
+        help="Set Tesseract page segmentation mode (see tesseract --help).",
     )
     tess.add_argument(
         '--tesseract-oem',
@@ -75,7 +75,10 @@ def add_options(parser):
         metavar='SECONDS',
         help=(
             "Give up on OCR after the timeout, but copy the preprocessed page "
-            "into the final output."
+            "into the final output. This timeout is only used when using Tesseract "
+            "for OCR. When Tesseract is used for other operations such as "
+            "deskewing and orientation, the timeout is controlled by "
+            "--tesseract-non-ocr-timeout."
         ),
     )
     tess.add_argument(
@@ -175,6 +178,15 @@ def validate(pdfinfo, options):
         tess_threads = int(os.environ['OMP_THREAD_LIMIT'])
     log.debug("Using Tesseract OpenMP thread limit %d", tess_threads)
 
+    if (
+        options.tesseract_downsample_above != 32767
+        and not options.tesseract_downsample_large_images
+    ):
+        log.warning(
+            "The --tesseract-downsample-above argument will have no effect unless "
+            "--tesseract-downsample-large-images is also given."
+        )
+
 
 @hookimpl
 def filter_ocr_image(page: PageContext, image: Image.Image) -> Image.Image:

src/ocrmypdf/cli.py

@@ -177,7 +177,9 @@ Online documentation is located at:
         '--image-dpi',
         metavar='DPI',
         type=int,
-        help="For input image instead of PDF, use this DPI instead of file's.",
+        help="When the input file is an image, not a PDF, use this DPI instead "
+        "of the DPI claimed by the input file. If the input does not claim a "
+        "sensible DPI, this option will be required.",
     )
     parser.add_argument(
         '--output-type',