From f5bfd2fd3e45d51158816ab745670dd0811ec266 Mon Sep 17 00:00:00 2001
From: "James R. Barlow" <james@purplerock.ca>
Date: Mon, 8 Dec 2025 17:33:45 -0800
Subject: [PATCH] Add compat function for pages_from_ranges

fix: handle Pydantic validation errors with correct exit code

Co-authored-by: aider (openrouter/anthropic/claude-sonnet-4) <aider@aider.chat>
---
 src/ocrmypdf/_jobcontext.py        |  6 ++++++
 src/ocrmypdf/_pipelines/_common.py | 12 +++++++++++-
 src/ocrmypdf/_pipelines/ocr.py     | 18 ++++++++++++++++++
 tests/test_page_numbers.py         |  2 +-
 4 files changed, 36 insertions(+), 2 deletions(-)

diff --git a/src/ocrmypdf/_jobcontext.py b/src/ocrmypdf/_jobcontext.py
index 04df33b3..990b22a8 100644
--- a/src/ocrmypdf/_jobcontext.py
+++ b/src/ocrmypdf/_jobcontext.py
@@ -103,6 +103,8 @@ class PageContext:
         self.pageno = pageno
         self.pageinfo = pdf_context.pdfinfo[pageno]
         self.plugin_manager = pdf_context.plugin_manager
+        # Ensure no reference to PdfContext which contains OCROptions
+        self._pdf_context = None
 
     def get_path(self, name: str) -> Path:
         """Generate a ``Path`` for a file that is part of processing this page.
@@ -115,6 +117,7 @@ class PageContext:
     def __getstate__(self):
         state = self.__dict__.copy()
 
+        # Ensure we only pickle the Namespace, not any Pydantic objects
         state['options'] = copy(self.options)
         # Handle stream inputs
         if hasattr(state['options'], 'input_file'):
@@ -123,4 +126,7 @@ class PageContext:
         if hasattr(state['options'], 'output_file'):
             if not isinstance(state['options'].output_file, str | bytes | os.PathLike):
                 state['options'].output_file = 'stream'
+        
+        # Remove any potential references to Pydantic objects
+        state.pop('_pdf_context', None)
         return state
diff --git a/src/ocrmypdf/_pipelines/_common.py b/src/ocrmypdf/_pipelines/_common.py
index d3c219e0..b39e1d30 100644
--- a/src/ocrmypdf/_pipelines/_common.py
+++ b/src/ocrmypdf/_pipelines/_common.py
@@ -50,7 +50,7 @@ from ocrmypdf._plugin_manager import OcrmypdfPluginManager
 from ocrmypdf._validation import (
     report_output_file_size,
 )
-from ocrmypdf.exceptions import ExitCode, ExitCodeException
+from ocrmypdf.exceptions import BadArgsError, ExitCode, ExitCodeException
 from ocrmypdf.helpers import (
     available_cpu_count,
     check_pdf,
@@ -275,6 +275,16 @@ def cli_exception_handler(
         else:
             log.error(type(e).__name__)
         return e.exit_code
+    except ValueError as e:
+        # Convert Pydantic validation errors to BadArgsError for proper exit code
+        if "validation error" in str(e).lower() or "value error" in str(e).lower():
+            if options.verbose >= 1:
+                log.exception("Validation error")
+            else:
+                log.error("Invalid argument: %s", str(e))
+            return ExitCode.bad_args
+        # Re-raise other ValueErrors to be caught by the general exception handler
+        raise
     except PIL.Image.DecompressionBombError:
         log.exception(
             "A decompression bomb error was encountered while executing the "
diff --git a/src/ocrmypdf/_pipelines/ocr.py b/src/ocrmypdf/_pipelines/ocr.py
index 907422fd..3c9b217d 100644
--- a/src/ocrmypdf/_pipelines/ocr.py
+++ b/src/ocrmypdf/_pipelines/ocr.py
@@ -48,6 +48,21 @@ from ocrmypdf._validation import (
     check_requested_output_file,
     create_input_file,
 )
+
+
+def _convert_pages_field_for_legacy_compatibility(options: argparse.Namespace) -> None:
+    """Convert pages field from string to set if needed.
+    
+    This is a temporary shim to handle the transition from CLI string processing
+    to OCROptions Pydantic validation. The pages field needs to be converted
+    before calling do_get_pdfinfo() since PdfInfo expects a Container[int].
+    
+    TODO: Remove this function when the refactoring plan is complete and all
+    pipeline functions work directly with OCROptions instead of Namespace.
+    """
+    if hasattr(options, 'pages') and isinstance(options.pages, str):
+        from ocrmypdf._options import _pages_from_ranges
+        options.pages = _pages_from_ranges(options.pages)
 from ocrmypdf.exceptions import ExitCode
 
 log = logging.getLogger(__name__)
@@ -175,6 +190,9 @@ def _run_pipeline(
             original_filename, start_input_file, work_folder / 'origin.pdf', options
         )
 
+        # Convert pages field if needed before gathering pdfinfo
+        _convert_pages_field_for_legacy_compatibility(options)
+        
         # Gather pdfinfo and create context
         pdfinfo = do_get_pdfinfo(origin_pdf, executor, options)
         context = PdfContext(options, work_folder, origin_pdf, pdfinfo, plugin_manager)
diff --git a/tests/test_page_numbers.py b/tests/test_page_numbers.py
index aac80c0d..79b1acf0 100644
--- a/tests/test_page_numbers.py
+++ b/tests/test_page_numbers.py
@@ -6,7 +6,7 @@ from __future__ import annotations
 import pytest
 
 import ocrmypdf
-from ocrmypdf._validation import _pages_from_ranges
+from ocrmypdf._options import _pages_from_ranges
 from ocrmypdf.exceptions import BadArgsError
 from ocrmypdf.pdfinfo import PdfInfo