Fix --jpeg-quality/--jpg-quality being dropped by the CLI (closes #1723)

namespace_to_options() only copied argparse namespace keys that were
literal members of OcrOptions.model_fields. The CLI dest for both
--jpeg-quality and --jpg-quality was jpeg_quality, but the pydantic field
was named jpg_quality (jpeg_quality existed only as a compatibility
property, absent from model_fields). The value was silently dropped into
extra_attrs, and the optimizer always fell back to its own hardcoded
default regardless of the flag.

The same alias mismatch also affected the Python API: create_options()
uses the same model_fields-matching logic as namespace_to_options(), so
ocrmypdf.ocr(jpeg_quality=...) was silently dropped too - only the
canonical jpg_quality= kwarg worked.

Rather than patch around the mismatch, consolidate on a single canonical
name: OcrOptions.jpeg_quality (matching the primary --jpeg-quality CLI
flag and the already-consistent naming in OptimizeOptions). jpg_quality
becomes a deprecated compatibility property, and ocrmypdf.ocr(jpg_quality=)
is a deprecated alias that warns and forwards to jpeg_quality via a new
create_options() remap step. --jpg-quality remains a working (already
hidden) CLI alias with no code-path divergence, since it now shares an
argparse dest that matches the field name directly.

src/ocrmypdf/_options.py

@@ -207,19 +207,19 @@ class OcrOptions(BaseModel):
 
     # Optimization
     optimize: int = 1
-    jpg_quality: int | None = None
+    jpeg_quality: int | None = None
     png_quality: int | None = None
 
-    # Compatibility alias for plugins that expect jpeg_quality
+    # Deprecated compatibility alias for code that still uses the old field name
     @property
-    def jpeg_quality(self):
+    def jpg_quality(self):
-        """Compatibility alias for jpg_quality."""
+        """Deprecated compatibility alias for jpeg_quality."""
-        return self.jpg_quality
+        return self.jpeg_quality
 
-    @jpeg_quality.setter
+    @jpg_quality.setter
-    def jpeg_quality(self, value):
+    def jpg_quality(self, value):
-        """Compatibility alias for jpg_quality."""
+        """Deprecated compatibility alias for jpeg_quality."""
-        self.jpg_quality = value
+        self.jpeg_quality = value
 
     # Output behavior
     no_overwrite: bool = False
@@ -642,12 +642,6 @@ class OcrOptions(BaseModel):
                     value = self.optimize
                     if value is not None:
                         kwargs[field_name] = _convert_value(value)
-            elif namespace == 'optimize' and field_name == 'jpeg_quality':
-                # jpg_quality maps to jpeg_quality
-                if 'jpg_quality' in OcrOptions.model_fields:
-                    value = self.jpg_quality
-                    if value is not None:
-                        kwargs[field_name] = _convert_value(value)
 
         # Create and cache the plugin options instance
         instance = model_class(**kwargs)

src/ocrmypdf/api.py

@@ -345,6 +345,23 @@ def _remap_language_to_languages(options_kwargs: dict) -> None:
         del options_kwargs['language']
 
 
+def _remap_jpg_quality_to_jpeg_quality(options_kwargs: dict) -> None:
+    """Map the deprecated 'jpg_quality' parameter to 'jpeg_quality'.
+
+    'jpg_quality' was the original API parameter name. 'jpeg_quality' is the
+    canonical OcrOptions field, matching the primary --jpeg-quality CLI flag.
+    Prefer an explicitly-given 'jpeg_quality' if both are set.
+    """
+    if 'jpg_quality' not in options_kwargs:
+        return
+    old_value = options_kwargs.pop('jpg_quality')
+    if old_value is None:
+        return
+    warn("ocrmypdf.ocr(jpg_quality=...) is deprecated, use jpeg_quality= instead.")
+    if options_kwargs.get('jpeg_quality') is None:
+        options_kwargs['jpeg_quality'] = old_value
+
+
 def create_options(
     *, input_file: PathOrIO, output_file: PathOrIO, parser: ArgumentParser, **kwargs
 ) -> OcrOptions:
@@ -369,6 +386,9 @@ def create_options(
     # Map API parameter 'language' to OcrOptions field 'languages'
     _remap_language_to_languages(options_kwargs)
 
+    # Map deprecated 'jpg_quality' parameter to 'jpeg_quality'
+    _remap_jpg_quality_to_jpeg_quality(options_kwargs)
+
     # Set input and output files
     options_kwargs['input_file'] = input_file
     options_kwargs['output_file'] = output_file
@@ -448,7 +468,8 @@ def ocr(
     redo_ocr: bool | None = None,
     skip_big: float | None = None,
     optimize: int | None = None,
-    jpg_quality: int | None = None,
+    jpeg_quality: int | None = None,
+    jpg_quality: int | None = None,  # Deprecated, use jpeg_quality instead
     png_quality: int | None = None,
     jbig2_lossy: bool | None = None,
     jbig2_page_group_size: int | None = None,
@@ -511,7 +532,8 @@ def ocr(  # noqa: D417
     redo_ocr: bool | None = None,  # Legacy, use mode='redo' instead
     skip_big: float | None = None,
     optimize: int | None = None,
-    jpg_quality: int | None = None,
+    jpeg_quality: int | None = None,
+    jpg_quality: int | None = None,  # Deprecated, use jpeg_quality instead
     png_quality: int | None = None,
     jbig2_lossy: bool | None = None,  # Deprecated, ignored
     jbig2_page_group_size: int | None = None,  # Deprecated, ignored
@@ -883,7 +905,7 @@ def _hocr_to_ocr_pdf(  # noqa: D417
     jobs: int | None = None,
     use_threads: bool | None = None,
     optimize: int | None = None,
-    jpg_quality: int | None = None,
+    jpeg_quality: int | None = None,
     png_quality: int | None = None,
     jbig2_lossy: bool | None = None,  # Deprecated, ignored
     jbig2_page_group_size: int | None = None,  # Deprecated, ignored

src/ocrmypdf/optimize.py

@@ -449,12 +449,12 @@ def convert_to_jbig2(
 
 
 def _optimize_jpeg(
-    xref: Xref, in_jpg: Path, opt_jpg: Path, jpg_quality: int
+    xref: Xref, in_jpg: Path, opt_jpg: Path, jpeg_quality: int
 ) -> tuple[Xref, Path | None]:
     with Image.open(in_jpg) as im:
         save_kwargs: dict[str, Any] = {'optimize': True}
-        if isinstance(jpg_quality, int) and 0 < jpg_quality <= 100:
+        if isinstance(jpeg_quality, int) and 0 < jpeg_quality <= 100:
-            save_kwargs['quality'] = jpg_quality
+            save_kwargs['quality'] = jpeg_quality
         im.save(opt_jpg, **save_kwargs)
 
     if opt_jpg.stat().st_size > in_jpg.stat().st_size:
@@ -473,7 +473,7 @@ def transcode_jpegs(
         for xref in jpegs:
             in_jpg = jpg_name(root, xref)
             opt_jpg = in_jpg.with_suffix('.opt.jpg')
-            yield xref, in_jpg, opt_jpg, options.jpg_quality
+            yield xref, in_jpg, opt_jpg, options.jpeg_quality
 
     def finish_jpeg(result: tuple[Xref, Path | None], pbar: ProgressBar):
         xref, opt_jpg = result
@@ -703,8 +703,8 @@ def optimize(
         safe_symlink(input_file, output_file)
         return output_file
 
-    if not options.jpg_quality:
+    if not options.jpeg_quality:
-        options.jpg_quality = DEFAULT_JPEG_QUALITY if options.optimize < 3 else 40
+        options.jpeg_quality = DEFAULT_JPEG_QUALITY if options.optimize < 3 else 40
     if not options.png_quality:
         options.png_quality = DEFAULT_PNG_QUALITY if options.optimize < 3 else 30
 
@@ -766,7 +766,7 @@ def main(infile, outfile, level, jobs=1):
         output_file=outfile,  # Required field
         jobs=jobs,
         optimize=int(level),
-        jpg_quality=0,  # Use default
+        jpeg_quality=0,  # Use default
         png_quality=0,
         jbig2_threshold=0.85,
         quiet=True,

tests/test_api.py

@@ -79,6 +79,45 @@ def test_language_parameter_mapped_to_languages():
     assert options.languages == ['eng', 'spa']
 
 
+def test_jpeg_quality_parameter_reaches_options():
+    """The canonical 'jpeg_quality' API parameter must reach OcrOptions.
+
+    Regression test for GitHub issue #1723: --jpeg-quality was silently
+    dropped by the CLI's namespace_to_options() because the OcrOptions field
+    was named jpg_quality. create_options(), used by the Python API, has the
+    same field-name matching logic and is affected the same way when passed
+    the alias name.
+    """
+    from ocrmypdf.api import create_options, setup_plugin_infrastructure
+    from ocrmypdf.cli import get_parser
+
+    setup_plugin_infrastructure()
+    parser = get_parser()
+
+    options = create_options(
+        input_file='test.pdf', output_file='output.pdf', parser=parser, jpeg_quality=10
+    )
+    assert options.jpeg_quality == 10
+
+
+def test_jpg_quality_parameter_deprecated_alias():
+    """The old 'jpg_quality' API parameter still works but warns."""
+    from ocrmypdf.api import create_options, setup_plugin_infrastructure
+    from ocrmypdf.cli import get_parser
+
+    setup_plugin_infrastructure()
+    parser = get_parser()
+
+    with pytest.warns(UserWarning, match='jpg_quality'):
+        options = create_options(
+            input_file='test.pdf',
+            output_file='output.pdf',
+            parser=parser,
+            jpg_quality=42,
+        )
+    assert options.jpeg_quality == 42
+
+
 def test_stream_api(resources: Path):
     in_ = (resources / 'graph.pdf').open('rb')
     out = BytesIO()

tests/test_optimize.py

@@ -17,6 +17,7 @@ from PIL import Image, ImageDraw
 from ocrmypdf import optimize as opt
 from ocrmypdf._exec import jbig2enc, pngquant
 from ocrmypdf._exec.ghostscript import rasterize_pdf
+from ocrmypdf.cli import get_options_and_plugins
 from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution
 from ocrmypdf.optimize import PdfImage, extract_image_filter
 from ocrmypdf.pluginspec import GhostscriptRasterDevice
@@ -81,6 +82,28 @@ def test_jpg_png_params(resources, outpdf):
     )
 
 
+def test_jpeg_quality_cli_flag_reaches_options(resources, outpdf):
+    # Regression test for #1723: --jpeg-quality was silently dropped by
+    # namespace_to_options() because the argparse dest ('jpeg_quality') did
+    # not match the OcrOptions field it was checked against.
+    input_ = fspath(resources / 'c02-22.pdf')
+    options, _pm = get_options_and_plugins(
+        ['--jpeg-quality', '10', input_, fspath(outpdf)]
+    )
+    assert options.jpeg_quality == 10
+
+
+def test_jpg_quality_cli_alias_reaches_options(resources, outpdf):
+    # --jpg-quality is a hidden alias for --jpeg-quality (same argparse dest).
+    input_ = fspath(resources / 'c02-22.pdf')
+    options, _pm = get_options_and_plugins(
+        ['--jpg-quality', '42', input_, fspath(outpdf)]
+    )
+    assert options.jpeg_quality == 42
+    # The old field name is still readable as a deprecated compatibility alias.
+    assert options.jpg_quality == 42
+
+
 @needs_jbig2enc
 def test_jbig2_lossless(resources, outpdf):
     """Test that JBIG2 lossless encoding works without JBIG2Globals."""

tests/test_validation.py

@@ -89,8 +89,15 @@ def test_mutex_options():
         make_ocr_opts(redo_ocr=True, force_ocr=True)
 
 
-def test_optimizing(caplog):
+def test_optimizing_png_quality_warns(caplog):
-    vd.check_options(*make_opts_pm(optimize=0, png_quality=18, jpeg_quality=10))
+    vd.check_options(*make_opts_pm(optimize=0, png_quality=18))
+    assert 'will be ignored because' in caplog.text
+
+
+def test_optimizing_jpeg_quality_warns(caplog):
+    # Isolated from png_quality so this actually exercises the jpeg_quality
+    # path rather than being confounded by png_quality also being set.
+    vd.check_options(*make_opts_pm(optimize=0, jpeg_quality=10))
     assert 'will be ignored because' in caplog.text