refactor: replace Namespace with OCROptions in plugins and validation

Co-authored-by: aider (openrouter/anthropic/claude-sonnet-4) <aider@aider.chat>

src/ocrmypdf/_validation.py

@@ -10,7 +10,6 @@ import locale
 import logging
 import os
 import sys
-from argparse import Namespace
 from collections.abc import Sequence
 from pathlib import Path
 from shutil import copyfileobj
@@ -50,7 +49,7 @@ def check_platform() -> None:
 
 
 def check_options_languages(
-    options: Union[Namespace, OCROptions], ocr_engine_languages: list[str]
+    options: Union[OCROptions], ocr_engine_languages: list[str]
 ) -> None:
     if not ocr_engine_languages:
         return
@@ -76,7 +75,7 @@ def check_options_languages(
 
 
 
-def check_options_sidecar(options: Union[Namespace, OCROptions]) -> None:
+def check_options_sidecar(options: Union[OCROptions]) -> None:
     if options.sidecar == '\0':
         if options.output_file == '-':
             raise BadArgsError("--sidecar filename needed when output file is stdout.")
@@ -91,7 +90,7 @@ def check_options_sidecar(options: Union[Namespace, OCROptions]) -> None:
         )
 
 
-def check_options_preprocessing(options: Union[Namespace, OCROptions]) -> None:
+def check_options_preprocessing(options: Union[OCROptions]) -> None:
     if options.clean_final:
         options.clean = True
     if options.unpaper_args and not options.clean:
@@ -119,37 +118,26 @@ def check_options_preprocessing(options: Union[Namespace, OCROptions]) -> None:
 
 
 
-def _check_plugin_invariant_options(options: Union[Namespace, OCROptions]) -> None:
+def _check_plugin_invariant_options(options: Union[OCROptions]) -> None:
     check_platform()
     check_options_sidecar(options)
     check_options_preprocessing(options)
 
 
 def _check_plugin_options(
-    options: Union[Namespace, OCROptions], plugin_manager: PluginManager
+    options: OCROptions, plugin_manager: PluginManager
 ) -> None:
-    # Convert to Namespace for plugin compatibility during transition
-    if isinstance(options, OCROptions):
-        legacy_options = options.to_namespace()
-    else:
-        legacy_options = options
-    plugin_manager.hook.check_options(options=legacy_options)
-    ocr_engine_languages = plugin_manager.hook.get_ocr_engine().languages(
-        legacy_options
-    )
+    plugin_manager.hook.check_options(options=options)
+    ocr_engine_languages = plugin_manager.hook.get_ocr_engine().languages(options)
     check_options_languages(options, ocr_engine_languages)
 
 
-def check_options(
-    options: Union[Namespace, OCROptions], plugin_manager: PluginManager
-) -> None:
+def check_options(options: OCROptions, plugin_manager: PluginManager) -> None:
     _check_plugin_invariant_options(options)
     _check_plugin_options(options, plugin_manager)
 
 
-def create_input_file(
-    options: Union[Namespace, OCROptions], work_folder: Path
-) -> tuple[Path, str]:
+def create_input_file(options: OCROptions, work_folder: Path) -> tuple[Path, str]:
     if options.input_file == '-':
         # stdin
         log.info('reading file from standard input')
@@ -194,7 +182,7 @@ def create_input_file(
             raise InputFileError(msg) from e
 
 
-def check_requested_output_file(options: Union[Namespace, OCROptions]) -> None:
+def check_requested_output_file(options: OCROptions) -> None:
     if options.output_file == '-':
         if sys.stdout.isatty():
             raise BadArgsError(
@@ -212,7 +200,7 @@ def check_requested_output_file(options: Union[Namespace, OCROptions]) -> None:
 
 
 def report_output_file_size(
-    options: Union[Namespace, OCROptions],
+    options: OCROptions,
     input_file: Path,
     output_file: Path,
     optimize_messages: Sequence[str] | None = None,

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -74,8 +74,6 @@ def check_options(options):
             "use --force-ocr to discard existing text."
         )
 
-    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}"
@@ -128,6 +126,11 @@ def generate_pdfa(
     stop_on_soft_error,
 ):
     """Generate a PDF/A from the list of PDF pages and PDF/A metadata."""
+    # Normalize output_type at point of use
+    output_type = context.options.output_type
+    if output_type == 'pdfa':
+        output_type = 'pdfa-2'
+    
     ghostscript.generate_pdfa(
         pdf_pages=[pdfmark, *pdf_pages],
         output_file=output_file,

src/ocrmypdf/builtin_plugins/tesseract_ocr.py

@@ -152,14 +152,6 @@ def check_options(options):
             "Please upgrade to a newer or supported older version."
         )
 
-    # Decide on what renderer to use
-    if options.pdf_renderer == 'auto':
-        if {'ara', 'heb', 'fas', 'per'} & set(options.languages):
-            log.info("Using sandwich renderer since there is an RTL language")
-            options.pdf_renderer = 'sandwich'
-        else:
-            options.pdf_renderer = 'hocr'
-
     if not tesseract.has_thresholding() and options.tesseract_thresholding != 0:
         log.warning(
             "The installed version of Tesseract does not support changes to its "
@@ -234,9 +226,21 @@ class TesseractOcrEngine(OcrEngine):
     def version():
         return str(tesseract.version())
 
+    @staticmethod
+    def _determine_renderer(options):
+        """Determine the PDF renderer to use based on options and languages."""
+        if options.pdf_renderer == 'auto':
+            if {'ara', 'heb', 'fas', 'per'} & set(options.languages):
+                log.info("Using sandwich renderer since there is an RTL language")
+                return 'sandwich'
+            else:
+                return 'hocr'
+        return options.pdf_renderer
+
     @staticmethod
     def creator_tag(options):
-        tag = '-PDF' if options.pdf_renderer == 'sandwich' else '-hOCR'
+        renderer = TesseractOcrEngine._determine_renderer(options)
+        tag = '-PDF' if renderer == 'sandwich' else '-hOCR'
         return f"Tesseract OCR{tag} {TesseractOcrEngine.version()}"
 
     def __str__(self):

src/ocrmypdf/pluginspec.py

@@ -6,7 +6,7 @@
 from __future__ import annotations
 
 from abc import ABC, abstractmethod
-from argparse import ArgumentParser, Namespace
+from argparse import ArgumentParser
 from collections.abc import Sequence, Set
 from logging import Handler
 from pathlib import Path
@@ -15,6 +15,7 @@ from typing import TYPE_CHECKING, NamedTuple
 import pluggy
 
 from ocrmypdf import Executor, PdfContext
+from ocrmypdf._options import OCROptions
 from ocrmypdf._progressbar import ProgressBar
 from ocrmypdf.helpers import Resolution
 
@@ -87,7 +88,7 @@ def add_options(parser: ArgumentParser) -> None:
 
 
 @hookspec
-def check_options(options: Namespace) -> None:
+def check_options(options: OCROptions) -> None:
     """Called to ask the plugin to check all of the options.
 
     The plugin may check if options that it added are valid.
@@ -158,7 +159,7 @@ def get_progressbar_class() -> type[ProgressBar]:
 
 
 @hookspec
-def validate(pdfinfo: PdfInfo, options: Namespace) -> None:
+def validate(pdfinfo: PdfInfo, options: OCROptions) -> None:
     """Called to give a plugin an opportunity to review *options* and *pdfinfo*.
 
     *options* contains the "work order" to process a particular file. *pdfinfo*
@@ -368,7 +369,7 @@ class OcrEngine(ABC):
 
     @staticmethod
     @abstractmethod
-    def creator_tag(options: Namespace) -> str:
+    def creator_tag(options: OCROptions) -> str:
         """Returns the creator tag to identify this software's role in creating the PDF.
 
         This tag will be inserted in the XMP metadata and DocumentInfo dictionary
@@ -389,7 +390,7 @@ class OcrEngine(ABC):
 
     @staticmethod
     @abstractmethod
-    def languages(options: Namespace) -> Set[str]:
+    def languages(options: OCROptions) -> Set[str]:
         """Returns the set of all languages that are supported by the engine.
 
         Languages are typically given in 3-letter ISO 3166-1 codes, but actually
@@ -398,18 +399,18 @@ class OcrEngine(ABC):
 
     @staticmethod
     @abstractmethod
-    def get_orientation(input_file: Path, options: Namespace) -> OrientationConfidence:
+    def get_orientation(input_file: Path, options: OCROptions) -> OrientationConfidence:
         """Returns the orientation of the image."""
 
     @staticmethod
-    def get_deskew(input_file: Path, options: Namespace) -> float:
+    def get_deskew(input_file: Path, options: OCROptions) -> float:
         """Returns the deskew angle of the image, in degrees."""
         return 0.0
 
     @staticmethod
     @abstractmethod
     def generate_hocr(
-        input_file: Path, output_hocr: Path, output_text: Path, options: Namespace
+        input_file: Path, output_hocr: Path, output_text: Path, options: OCROptions
     ) -> None:
         """Called to produce a hOCR file from a page image and sidecar text file.
 
@@ -432,7 +433,7 @@ class OcrEngine(ABC):
     @staticmethod
     @abstractmethod
     def generate_pdf(
-        input_file: Path, output_pdf: Path, output_text: Path, options: Namespace
+        input_file: Path, output_pdf: Path, output_text: Path, options: OCROptions
     ) -> None:
         """Called to produce a text only PDF from a page image.