Added support for changing color conversion strategy

misc/completion/ocrmypdf.bash

@@ -6,53 +6,55 @@ set -o errexit
 
 __ocrmypdf_arguments()
 {
-    local arguments="--help                   (show help message)
---language               (language(s) of the file to be OCRed)
---image-dpi              (assume this DPI if input image DPI is unknown)
---output-type            (select PDF output options)
---sidecar                (write OCR to text file)
---version                (print program version and exit)
---jobs                   (how many worker processes to use)
---quiet                  (suppress INFO messages)
---verbose                (set verbosity level)
---title                  (set metadata)
---author                 (set metadata)
---subject                (set metadata)
---keywords               (set metadata)
---rotate-pages           (rotate pages to correct orientation)
---remove-background      (attempt to remove background from pages)
---deskew                 (fix small horizontal alignment skew)
---clean                  (clean document images before OCR)
---clean-final            (clean document images and keep result)
---unpaper-args           (a quoted string of arguments to pass to unpaper)
---oversample             (oversample images to this DPI)
---remove-vectors         (don\'t send vector objects to OCR)
---threshold              (threshold images before OCR)
---force-ocr              (OCR documents that already have printable text)
---skip-text              (skip OCR on any pages that already contain text)
---redo-ocr               (redo OCR on any pages that seem to have OCR already)
+    local arguments="\
+--help                          (show help message)
+--language                      (language(s) of the file to be OCRed)
+--image-dpi                     (assume this DPI if input image DPI is unknown)
+--output-type                   (select PDF output options)
+--sidecar                       (write OCR to text file)
+--version                       (print program version and exit)
+--jobs                          (how many worker processes to use)
+--quiet                         (suppress INFO messages)
+--verbose                       (set verbosity level)
+--title                         (set metadata)
+--author                        (set metadata)
+--subject                       (set metadata)
+--keywords                      (set metadata)
+--rotate-pages                  (rotate pages to correct orientation)
+--remove-background             (attempt to remove background from pages)
+--deskew                        (fix small horizontal alignment skew)
+--clean                         (clean document images before OCR)
+--clean-final                   (clean document images and keep result)
+--unpaper-args                  (a quoted string of arguments to pass to unpaper)
+--oversample                    (oversample images to this DPI)
+--remove-vectors                (don\'t send vector objects to OCR)
+--threshold                     (threshold images before OCR)
+--force-ocr                     (OCR documents that already have printable text)
+--skip-text                     (skip OCR on any pages that already contain text)
+--redo-ocr                      (redo OCR on any pages that seem to have OCR already)
 --invalidate-digital-signatures (remove digital signatures from PDF)
---skip-big               (skip OCR on pages larger than this many MPixels)
---optimize               (select optimization level)
---jpeg-quality           (JPEG quality [0..100])
---png-quality            (PNG quality [0..100])
---jbig2-lossy            (enable lossy JBIG2 (see docs))
---pages                  (apply OCR to only the specified pages)
---max-image-mpixels      (image decompression bomb threshold)
---pdf-renderer           (select PDF renderer options)
---rotate-pages-threshold (page rotation confidence)
---pdfa-image-compression (set PDF/A image compression options)
---fast-web-view          (if file size if above this amount in MB linearize PDF)
---plugin                 (name of plugin to import)
---keep-temporary-files   (keep temporary files (debug)
---tesseract-config       (set custom tesseract config file)
---tesseract-pagesegmode  (set tesseract --psm)
---tesseract-oem          (set tesseract --oem)
---tesseract-thresholding (set tesseract image thresholding)
---tesseract-timeout      (maximum number of seconds to wait for OCR)
---user-words             (specify location of user words file)
---user-patterns          (specify location of user patterns file)
---no-progress-bar        (disable the progress bar)
+--skip-big                      (skip OCR on pages larger than this many MPixels)
+--optimize                      (select optimization level)
+--jpeg-quality                  (JPEG quality [0..100])
+--png-quality                   (PNG quality [0..100])
+--jbig2-lossy                   (enable lossy JBIG2 (see docs))
+--pages                         (apply OCR to only the specified pages)
+--max-image-mpixels             (image decompression bomb threshold)
+--pdf-renderer                  (select PDF renderer options)
+--rotate-pages-threshold        (page rotation confidence)
+--pdfa-image-compression        (set PDF/A image compression options)
+--fast-web-view                 (if file size if above this amount in MB linearize PDF)
+--plugin                        (name of plugin to import)
+--keep-temporary-files          (keep temporary files (debug)
+--tesseract-config              (set custom tesseract config file)
+--tesseract-pagesegmode         (set tesseract --psm)
+--tesseract-oem                 (set tesseract --oem)
+--tesseract-thresholding        (set tesseract image thresholding)
+--tesseract-timeout             (maximum number of seconds to wait for OCR)
+--user-words                    (specify location of user words file)
+--user-patterns                 (specify location of user patterns file)
+--no-progress-bar               (disable the progress bar)
+--color-conversion-strategy     (select color conversion strategy)
 "
 
     COMPREPLY=( $( compgen -W "$arguments" -- "$cur") )
@@ -192,6 +194,20 @@ sauvola       (use Sauvola thresholding)"
     fi
 }
 
+__ocrmypdf_color-conversion-strategy()
+{
+    local choices="LeaveColorUnchanged (default)
+CMYK (convert to CMYK)
+Gray (convert to grayscale)
+RGB (convert to RGB)
+UseDeviceIndependentColor (convert with device independent color)"
+
+    COMPREPLY=( $( compgen -W "$choices" -- "$cur") )
+    # Remove description if only one completion exists
+    if [[ ${#COMPREPLY[*]} -eq 1 ]]; then
+        COMPREPLY=( ${COMPREPLY[0]%% *} )
+    fi
+}
 
 __ocrmypdf_check_previous()
 {
@@ -251,6 +267,10 @@ __ocrmypdf_check_previous()
             _filedir
             return 0
             ;;
+        --color-conversion-strategy)
+            __ocrmypdf_color-conversion-strategy
+            return 0
+            ;;
     esac
 
     return 1

misc/completion/ocrmypdf.fish

@@ -129,4 +129,14 @@ complete -c ocrmypdf -r -l user-words -d "specify location of user words file"
 complete -c ocrmypdf -r -l user-patterns -d "specify location of user patterns file"
 complete -c ocrmypdf -x -l fast-web-view -d "if file size if above this amount in MB, linearize PDF"
 
+function __fish_ocrmypdf_color_conversion_strategy
+    echo -e "LeaveColorUnchanged\t"(_ "do not convert color spaces (default)")
+    echo -e "CMYK\t"(_ "convert all color spaces to CMYK")
+    echo -e "Gray\t"(_ "convert all color spaces to grayscale")
+    echo -e "RGB\t"(_ "convert all color spaces to RGB")
+    echo -e "UseDeviceIndependentColor\t"(_ "convert all color spaces to ICC-based color spaces")
+end
+
+complete -c ocrmypdf -x -l color-conversion-strategy -a '(__fish_ocrmypdf_color_conversion_strategy)' -d "set color conversion strategy"
+
 complete -c ocrmypdf -x -a "(__fish_complete_suffix .pdf; __fish_complete_suffix .PDF; __fish_complete_suffix .jpg; __fish_complete_suffix .png)"

src/ocrmypdf/_exec/ghostscript.py

@@ -28,6 +28,17 @@ except AttributeError:
     # Pillow 9 shim
     Transpose = Image  # type: ignore
 
+
+COLOR_CONVERSION_STRATEGIES = frozenset(
+    [
+        'CMYK',
+        'Gray',
+        'LeaveColorUnchanged',
+        'RGB',
+        'UseDeviceIndependentColor',
+    ]
+)
+
 log = logging.getLogger(__name__)
 
 # Most reliable way to get the bitness of Python interpreter, according to Python docs
@@ -160,6 +171,7 @@ def generate_pdfa(
     output_file: os.PathLike,
     *,
     compression: str,
+    color_conversion_strategy: str,
     pdf_version: str = '1.5',
     pdfa_part: str = '2',
     progressbar_class=None,
@@ -209,16 +221,16 @@ def generate_pdfa(
             "-dBATCH",
             "-dNOPAUSE",
             "-dSAFER",
-            "-dCompatibilityLevel=" + str(pdf_version),
+            f"-dCompatibilityLevel={str(pdf_version)}",
             "-sDEVICE=pdfwrite",
             "-dAutoRotatePages=/None",
-            "-sColorConversionStrategy=" + strategy,
+            f"-sColorConversionStrategy={color_conversion_strategy}",
         ]
         + (['-dPDFSTOPONERROR'] if stop_on_error else [])
         + compression_args
         + [
             "-dJPEGQ=95",
-            "-dPDFA=" + pdfa_part,
+            f"-dPDFA={pdfa_part}",
             "-dPDFACompatibilityPolicy=1",
             "-o",
             "-",

src/ocrmypdf/_pipeline.py

@@ -793,6 +793,7 @@ def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext) -
         pdfmark=input_ps_stub,
         output_file=output_file,
         compression=options.pdfa_image_compression,
+        color_conversion_strategy=options.color_conversion_strategy,
         pdfa_part=options.output_type[-1],  # is pdfa-1, pdfa-2, or pdfa-3
         progressbar_class=(
             context.plugin_manager.hook.get_progressbar_class()

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -14,6 +14,20 @@ from ocrmypdf.subprocess import check_external_program
 log = logging.getLogger(__name__)
 
 
+@hookimpl
+def add_options(parser):
+    gs = parser.add_argument_group("Ghostscript", "Advanced control of Ghostscript")
+    gs.add_argument(
+        '--color-conversion-strategy',
+        action='store',
+        type=str,
+        metavar='STRATEGY',
+        choices=ghostscript.COLOR_CONVERSION_STRATEGIES,
+        default='LeaveColorUnchanged',
+        help="Set Ghostscript color conversion strategy",
+    )
+
+
 @hookimpl
 def check_options(options):
     """Check that the options are valid for this plugin."""
@@ -33,6 +47,10 @@ def check_options(options):
 
     if options.output_type == 'pdfa':
         options.output_type = 'pdfa-2'
+    if options.color_conversion_strategy not in ghostscript.COLOR_CONVERSION_STRATEGIES:
+        raise ValueError(
+            f"Invalid color conversion strategy: {options.color_conversion_strategy}"
+        )
 
 
 @hookimpl
@@ -68,6 +86,7 @@ def generate_pdfa(
     pdfmark,
     output_file,
     compression,
+    color_conversion_strategy,
     pdf_version,
     pdfa_part,
     progressbar_class,
@@ -78,6 +97,7 @@ def generate_pdfa(
         pdf_pages=[*pdf_pages, pdfmark],
         output_file=output_file,
         compression=compression,
+        color_conversion_strategy=color_conversion_strategy,
         pdf_version=pdf_version,
         pdfa_part=pdfa_part,
         progressbar_class=progressbar_class,

src/ocrmypdf/pluginspec.py

@@ -467,6 +467,7 @@ def generate_pdfa(
     pdfmark: Path,
     output_file: Path,
     compression: str,
+    color_conversion_strategy: str,
     pdf_version: str,
     pdfa_part: str,
     progressbar_class,
@@ -489,6 +490,8 @@ def generate_pdfa(
             possible. For lossless, all images should be converted to FlateEncode
             (lossless PNG). If an empty string, the PDF generator should make its
             own decisions about how to encode images.
+        color_conversion_strategy: A valid Ghostscript color conversion strategy
+            name.
         pdf_version: The minimum PDF version that the output file should be.
             At its own discretion, the PDF/A generator may raise the version,
             but should not lower it.

tests/plugins/gs_feature_elision.py

@@ -28,6 +28,7 @@ def generate_pdfa(pdf_pages, pdfmark, output_file, compression, pdf_version, pdf
             pdfmark=pdfmark,
             output_file=output_file,
             compression=compression,
+            color_conversion_strategy='LeaveColorUnchanged',
             pdf_version=pdf_version,
             pdfa_part=pdfa_part,
             progressbar_class=None,

tests/plugins/gs_pdfa_failure.py

@@ -30,6 +30,7 @@ def generate_pdfa(pdf_pages, pdfmark, output_file, compression, pdf_version, pdf
             pdfmark=pdfmark,
             output_file=output_file,
             compression=compression,
+            color_conversion_strategy='LeaveColorUnchanged',
             pdf_version=pdf_version,
             pdfa_part=pdfa_part,
             progressbar_class=None,

tests/plugins/gs_render_failure.py

@@ -25,6 +25,7 @@ def generate_pdfa(pdf_pages, pdfmark, output_file, compression, pdf_version, pdf
             pdfmark=pdfmark,
             output_file=output_file,
             compression=compression,
+            color_conversion_strategy='LeaveColorUnchanged',
             pdf_version=pdf_version,
             pdfa_part=pdfa_part,
             progressbar_class=None,

tests/plugins/gs_render_soft_error.py

@@ -35,6 +35,7 @@ def generate_pdfa(
             pdfmark=pdfmark,
             output_file=output_file,
             compression=compression,
+            color_conversion_strategy='LeaveColorUnchanged',
             pdf_version=pdf_version,
             pdfa_part=pdfa_part,
             progressbar_class=None,

tests/test_metadata.py

@@ -86,7 +86,8 @@ def test_unset_metadata(output_type, field, resources, outpdf):
         'title': b'NFY5f7Ft2DWMkxLhXwxvFf7eWR2KeK3vEDcd',
         'author': b'yXaryipxyRk9dVjWjSSaVaNCKeLRgEVzPRMp',
         'subject': b't49vimctvnuH7ZeAjAkv52ACvWFjcnm5MPJr',
-        'keywords': b's9EeALwUg7urA7fnnhm5EtUyC54sW2WPUzqh'}
+        'keywords': b's9EeALwUg7urA7fnnhm5EtUyC54sW2WPUzqh',
+    }
 
     p = run_ocrmypdf(
         input_file,
@@ -364,6 +365,7 @@ def test_prevent_gs_invalid_xml(resources, outdir):
     options = get_parser().parse_args(
         args=['-j', '1', '--output-type', 'pdfa-2', 'a.pdf', 'b.pdf']
     )
+    options.color_conversion_strategy = 'LeaveColorUnchanged'
     pdfinfo = PdfInfo(outdir / 'layers.rendered.pdf')
     context = PdfContext(
         options, outdir, outdir / 'layers.rendered.pdf', pdfinfo, get_plugin_manager([])
@@ -404,6 +406,7 @@ def test_malformed_docinfo(caplog, resources, outdir):
             'b.pdf',
         ]
     )
+    options.color_conversion_strategy = 'LeaveColorUnchanged'
     pdfinfo = PdfInfo(outdir / 'layers.rendered.pdf')
     context = PdfContext(
         options, outdir, outdir / 'layers.rendered.pdf', pdfinfo, get_plugin_manager([])