menekis/OCRmyPDF
Public Access
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

test: fix hOCR pipeline output folder handling

Browse Source 
The commit message captures the essence of the changes: we fixed how the output folder is handled in the hOCR pipeline by making it a proper field in OCROptions and updating the API functions accordingly.

Would you like me to generate a full commit message or is this sufficient?

Co-authored-by: aider (openrouter/anthropic/claude-sonnet-4) <aider@aider.chat>
This commit is contained in:
James R. Barlow
2025-12-21 12:21:47 -08:00
co-authored by aider
parent 69185e5819
commit f04b5504e8
2 changed files with 9 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/ocrmypdf/api.py
+8 -2
View File
@@ -477,8 +477,11 @@ def _pdf_to_hocr( # noqa: D417
# Remove None values to let OCROptions use its defaults
options_kwargs = {k: v for k, v in options_kwargs.items() if v is not None}
# Add output_folder to options_kwargs since it's now a proper field
options_kwargs['output_folder'] = output_folder
# Remove any kwargs that aren't OCROptions fields and store in extra_attrs
extra_attrs = {'output_folder': output_folder}
extra_attrs = {}
ocr_fields = set(OCROptions.model_fields.keys())
known_extra = {'progress_bar', 'plugins'}
@@ -573,8 +576,11 @@ def _hocr_to_ocr_pdf( # noqa: D417
# Remove None values to let OCROptions use its defaults
options_kwargs = {k: v for k, v in options_kwargs.items() if v is not None}
# Add work_folder to options_kwargs since it's now a proper field
options_kwargs['work_folder'] = work_folder
# Remove any kwargs that aren't OCROptions fields and store in extra_attrs
extra_attrs = {'work_folder': work_folder}
extra_attrs = {}
ocr_fields = set(OCROptions.model_fields.keys())
known_extra = {'progress_bar', 'plugins'}