mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2025-07-28 18:24:38 -05:00
Allows disabling NLTK, adds it as a consideration for low power devices
This commit is contained in:
@@ -312,7 +312,7 @@ class DocumentClassifier:
|
||||
content = re.sub(r"[^\w\s]", " ", content)
|
||||
|
||||
# If the NLTK language is supported, do further processing
|
||||
if settings.NLTK_LANGUAGE is not None:
|
||||
if settings.NLTK_LANGUAGE is not None and settings.NLTK_ENABLED:
|
||||
|
||||
import nltk
|
||||
|
||||
|
@@ -709,6 +709,10 @@ ENABLE_UPDATE_CHECK = os.getenv("PAPERLESS_ENABLE_UPDATE_CHECK", "default")
|
||||
if ENABLE_UPDATE_CHECK != "default":
|
||||
ENABLE_UPDATE_CHECK = __get_boolean("PAPERLESS_ENABLE_UPDATE_CHECK")
|
||||
|
||||
###############################################################################
|
||||
# Machine Learning #
|
||||
###############################################################################
|
||||
|
||||
|
||||
def _get_nltk_language_setting(ocr_lang: str) -> Optional[str]:
|
||||
"""
|
||||
@@ -735,4 +739,6 @@ def _get_nltk_language_setting(ocr_lang: str) -> Optional[str]:
|
||||
return iso_code_to_nltk.get(ocr_lang, None)
|
||||
|
||||
|
||||
NLTK_ENABLED: Final[bool] = __get_boolean("PAPERLESS_ENABLE_NLTK", "yes")
|
||||
|
||||
NLTK_LANGUAGE: Optional[str] = _get_nltk_language_setting(OCR_LANGUAGE)
|
||||
|
Reference in New Issue
Block a user