paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-25 10:49:30 -05:00
Code Issues Packages Projects Releases Wiki Activity

Removes Turkish from the NLTK languages (#7246)

Browse Source
This commit is contained in:
Trenton H 2024-07-14 16:35:16 -07:00 committed by GitHub
parent 73d33ff25a
commit 6965165c76
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/paperless/settings.py
View File

@ -1126,6 +1126,10 @@ def _get_nltk_language_setting(ocr_lang: str) -> Optional[str]:
NLTK Languages:
- https://www.nltk.org/api/nltk.stem.snowball.html#nltk.stem.snowball.SnowballStemmer
- https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/tokenizers/punkt.zip
- https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/corpora/stopwords.zip
The common intersection between all languages in those 3 is handled here
"""
ocr_lang = ocr_lang.split("+")[0]
@ -1142,7 +1146,6 @@ def _get_nltk_language_setting(ocr_lang: str) -> Optional[str]:
"rus": "russian",
"spa": "spanish",
"swe": "swedish",
"tur": "turkish",
}
return iso_code_to_nltk.get(ocr_lang)