Migrate --pdfa-image-compression argument to being managed by Ghostscript plugin

src/ocrmypdf/_validation.py

@@ -204,16 +204,6 @@ def check_options_ocr_behavior(options: Namespace) -> None:
         options.pages = _pages_from_ranges(options.pages)
 
 
-def check_options_advanced(options: Namespace) -> None:
-    if options.pdfa_image_compression != 'auto' and not options.output_type.startswith(
-        'pdfa'
-    ):
-        log.warning(
-            "--pdfa-image-compression argument only applies when "
-            "--output-type is one of 'pdfa', 'pdfa-1', or 'pdfa-2'"
-        )
-
-
 def check_options_metadata(options: Namespace) -> None:
     docinfo = [options.title, options.author, options.keywords, options.subject]
     for s in (m for m in docinfo if m):
@@ -240,7 +230,6 @@ def _check_plugin_invariant_options(options: Namespace) -> None:
     check_options_sidecar(options)
     check_options_preprocessing(options)
     check_options_ocr_behavior(options)
-    check_options_advanced(options)
     check_options_pillow(options)
 
 

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -26,6 +26,19 @@ def add_options(parser):
         default='LeaveColorUnchanged',
         help="Set Ghostscript color conversion strategy",
     )
+    gs.add_argument(
+        '--pdfa-image-compression',
+        choices=['auto', 'jpeg', 'lossless'],
+        default='auto',
+        help="Specify how to compress images in the output PDF/A. 'auto' lets "
+        "OCRmyPDF decide.  'jpeg' changes all grayscale and color images to "
+        "JPEG compression.  'lossless' uses PNG-style lossless compression "
+        "for all images.  Monochrome images are always compressed using a "
+        "lossless codec.  Compression settings "
+        "are applied to all pages, including those for which OCR was "
+        "skipped.  Not supported for --output-type=pdf ; that setting "
+        "preserves the original compression of all images.",
+    )
 
 
 @hookimpl
@@ -51,6 +64,13 @@ def check_options(options):
         raise ValueError(
             f"Invalid color conversion strategy: {options.color_conversion_strategy}"
         )
+    if options.pdfa_image_compression != 'auto' and not options.output_type.startswith(
+        'pdfa'
+    ):
+        log.warning(
+            "--pdfa-image-compression argument only applies when "
+            "--output-type is one of 'pdfa', 'pdfa-1', or 'pdfa-2'"
+        )
 
 
 @hookimpl

src/ocrmypdf/cli.py

@@ -402,19 +402,6 @@ Online documentation is located at:
         help="Only rotate pages when confidence is above this value (arbitrary "
         "units reported by tesseract)",
     )
-    advanced.add_argument(
-        '--pdfa-image-compression',
-        choices=['auto', 'jpeg', 'lossless'],
-        default='auto',
-        help="Specify how to compress images in the output PDF/A. 'auto' lets "
-        "OCRmyPDF decide.  'jpeg' changes all grayscale and color images to "
-        "JPEG compression.  'lossless' uses PNG-style lossless compression "
-        "for all images.  Monochrome images are always compressed using a "
-        "lossless codec.  Compression settings "
-        "are applied to all pages, including those for which OCR was "
-        "skipped.  Not supported for --output-type=pdf ; that setting "
-        "preserves the original compression of all images.",
-    )
     advanced.add_argument(
         '--fast-web-view',
         type=numeric(float, 0),

tests/test_metadata.py

@@ -362,10 +362,16 @@ def test_prevent_gs_invalid_xml(resources, outdir):
         )
         pike.save(outdir / 'layers.rendered.pdf', fix_metadata_version=False)
 
-    options = get_parser().parse_args(
-        args=['-j', '1', '--output-type', 'pdfa-2', 'a.pdf', 'b.pdf']
+    _, options, _ = get_parser_options_plugins(
+        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([])
@@ -394,18 +400,16 @@ def test_malformed_docinfo(caplog, resources, outdir):
         pike.trailer.Info = pikepdf.Stream(pike, b"<xml></xml>")
         pike.save(outdir / 'layers.rendered.pdf', fix_metadata_version=False)
 
-    options = get_parser().parse_args(
+    _, options, _ = get_parser_options_plugins(
         args=[
             '-j',
             '1',
-            '--continue-on-soft-render-error',
             '--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([])