mirror/OCRmyPDF
1
0
Fork 0
mirror of https://github.com/ocrmypdf/OCRmyPDF.git synced 2026-06-11 23:46:12 -04:00
Code Issues Packages Projects Releases Wiki Activity

Prevent issuing equ and osd as languages

Browse Source
This commit is contained in:
James R. Barlow
2024-05-25 01:17:57 -07:00
parent d5ff7f7db9
commit d947ca258e
1 changed files with 12 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
src/ocrmypdf/_validation.py
View File

@@ -52,8 +52,20 @@ def check_options_languages(
system_lang = locale.getlocale()[0]
if system_lang and not system_lang.startswith('en'):
log.debug("No language specified; assuming --language %s", DEFAULT_LANGUAGE)
DENIED_LANGUAGES = {'equ', 'osd'}
if DENIED_LANGUAGES & set(options.languages):
log.warning(
"The following languages for Tesseract's internal use and should not "
"be issued explicitly: "
f"{', '.join(DENIED_LANGUAGES)}\n"
"OCRmyPDF will ignore them."
)
options.languages = [
lang for lang in options.languages if lang not in DENIED_LANGUAGES
]
if not ocr_engine_languages:
return
missing_languages = set(options.languages) - set(ocr_engine_languages)
if missing_languages:
lang_text = '\n'.join(lang for lang in missing_languages)