refactor: reorganize CLI and options initialization

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

src/ocrmypdf/__main__.py

@@ -14,10 +14,9 @@ import sys
 from contextlib import suppress
 
 from ocrmypdf import __version__
-from ocrmypdf._options import OCROptions
 from ocrmypdf._pipelines.ocr import run_pipeline_cli
-from ocrmypdf._plugin_manager import get_parser_options_plugins
 from ocrmypdf._validation import check_options
+from ocrmypdf.cli import get_options_and_plugins
 from ocrmypdf.api import Verbosity, configure_logging
 from ocrmypdf.exceptions import (
     BadArgsError,
@@ -40,10 +39,7 @@ def sigbus(*args):
 
 def run(args=None):
     """Run the ocrmypdf command line interface."""
-    _parser, namespace_options, plugin_manager = get_parser_options_plugins(args=args)
-
-    # Convert Namespace to OCROptions
-    options = OCROptions.from_namespace(namespace_options)
+    options, plugin_manager = get_options_and_plugins(args=args)
 
     with suppress(AttributeError, PermissionError):
         os.nice(5)

src/ocrmypdf/_jobcontext.py

@@ -5,7 +5,6 @@
 
 from __future__ import annotations
 
-from argparse import Namespace
 from collections.abc import Iterator
 from pathlib import Path
 
@@ -26,19 +25,13 @@ class PdfContext:
 
     def __init__(
         self,
-        options: OCROptions | Namespace,
+        options: OCROptions,
         work_folder: Path,
         origin: Path,
         pdfinfo: PdfInfo,
         plugin_manager,
     ):
-        # Handle both OCROptions and Namespace during transition
-        if isinstance(options, OCROptions):
-            self.options = options
-        else:
-            # Convert Namespace to OCROptions
-            self.options = OCROptions.from_namespace(options)
-
+        self.options = options
         self.work_folder = work_folder
         self.origin = origin
         self.pdfinfo = pdfinfo

src/ocrmypdf/_options.py

@@ -9,7 +9,6 @@ import json
 import logging
 import os
 import unicodedata
-from argparse import Namespace
 from collections.abc import Sequence
 from io import IOBase
 from pathlib import Path
@@ -165,30 +164,6 @@ class OCROptions(BaseModel):
         default_factory=dict, exclude=True, alias='_extra_attrs'
     )
 
-    @classmethod
-    def from_namespace(cls, ns: Namespace) -> OCROptions:
-        """Convert argparse.Namespace to OCROptions."""
-        # Extract known fields
-        known_fields = {}
-        extra_attrs = {}
-
-        for key, value in vars(ns).items():
-            if key in cls.model_fields:
-                known_fields[key] = value
-            else:
-                extra_attrs[key] = value
-
-        # Handle special cases for hOCR API
-        if 'output_folder' in extra_attrs and 'output_file' not in known_fields:
-            known_fields['output_file'] = '/dev/null'  # Placeholder
-
-        # Handle case where input_file is missing (e.g., in _hocr_to_ocr_pdf)
-        if 'work_folder' in extra_attrs and 'input_file' not in known_fields:
-            known_fields['input_file'] = '/dev/null'  # Placeholder
-
-        instance = cls(**known_fields)
-        instance.extra_attrs = extra_attrs
-        return instance
 
     @field_validator('languages')
     @classmethod

src/ocrmypdf/_plugin_manager.py

@@ -17,7 +17,7 @@ import pluggy
 
 import ocrmypdf.builtin_plugins
 from ocrmypdf import pluginspec
-from ocrmypdf.cli import get_parser, plugins_only_parser
+from ocrmypdf.cli import get_parser
 
 
 class OcrmypdfPluginManager(pluggy.PluginManager):
@@ -101,20 +101,4 @@ def get_plugin_manager(
     )
 
 
-def get_parser_options_plugins(
-    args: Sequence[str],
-) -> tuple[argparse.ArgumentParser, argparse.Namespace, pluggy.PluginManager]:
-    pre_options, _unused = plugins_only_parser.parse_known_args(args=args)
-    plugin_manager = get_plugin_manager(pre_options.plugins)
-
-    parser = get_parser()
-    plugin_manager.hook.initialize(  # pylint: disable=no-member
-        plugin_manager=plugin_manager
-    )
-    plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
-
-    options = parser.parse_args(args=args)
-    return parser, options, plugin_manager
-
-
-__all__ = ['OcrmypdfPluginManager', 'get_plugin_manager', 'get_parser_options_plugins']
+__all__ = ['OcrmypdfPluginManager', 'get_plugin_manager']

src/ocrmypdf/cli.py

@@ -9,7 +9,7 @@ import argparse
 from collections.abc import Callable, Mapping
 from typing import Any, TypeVar
 
-from ocrmypdf._defaults import DEFAULT_ROTATE_PAGES_THRESHOLD
+from ocrmypdf._defaults import DEFAULT_LANGUAGE, DEFAULT_ROTATE_PAGES_THRESHOLD
 from ocrmypdf._defaults import PROGRAM_NAME as _PROGRAM_NAME
 from ocrmypdf._version import __version__ as _VERSION
 
@@ -465,3 +465,70 @@ plugins_only_parser.add_argument(
     default=[],
     help="Name of plugin to import.",
 )
+
+
+def namespace_to_options(ns) -> 'OCROptions':
+    """Convert argparse.Namespace to OCROptions.
+    
+    This function encapsulates CLI-specific knowledge of how command line
+    arguments map to our internal options model.
+    """
+    from ocrmypdf._options import OCROptions
+    
+    # Extract known fields
+    known_fields = {}
+    extra_attrs = {}
+
+    for key, value in vars(ns).items():
+        if key in OCROptions.model_fields:
+            known_fields[key] = value
+        else:
+            extra_attrs[key] = value
+
+    # Handle special cases for hOCR API
+    if 'output_folder' in extra_attrs and 'output_file' not in known_fields:
+        known_fields['output_file'] = '/dev/null'  # Placeholder
+
+    # Handle case where input_file is missing (e.g., in _hocr_to_ocr_pdf)
+    if 'work_folder' in extra_attrs and 'input_file' not in known_fields:
+        known_fields['input_file'] = '/dev/null'  # Placeholder
+
+    instance = OCROptions(**known_fields)
+    instance.extra_attrs = extra_attrs
+    return instance
+
+
+def get_options_and_plugins(
+    args=None,
+) -> tuple['OCROptions', 'pluggy.PluginManager']:
+    """Parse command line arguments and return OCROptions and plugin manager.
+    
+    This is the main entry point for CLI argument processing. It handles
+    plugin discovery, argument parsing, and conversion to our internal
+    options model.
+    
+    Args:
+        args: Command line arguments. If None, uses sys.argv.
+        
+    Returns:
+        Tuple of (OCROptions, PluginManager)
+    """
+    import pluggy
+    from ocrmypdf._plugin_manager import get_plugin_manager
+    
+    # First pass: get plugins so we can register their options
+    pre_options, _unused = plugins_only_parser.parse_known_args(args=args)
+    plugin_manager = get_plugin_manager(pre_options.plugins)
+
+    # Get parser and let plugins add their options
+    parser = get_parser()
+    plugin_manager.hook.initialize(plugin_manager=plugin_manager)  # pylint: disable=no-member
+    plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
+
+    # Parse all arguments
+    namespace = parser.parse_args(args=args)
+    
+    # Convert to OCROptions
+    options = namespace_to_options(namespace)
+    
+    return options, plugin_manager