paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-02 13:45:10 -05:00
Code Issues Packages Projects Releases Wiki Activity

Code style changes

Browse Source
This commit is contained in:
Jonas Winkler 2018-09-25 21:12:47 +02:00
parent 60618381f8
commit b31d4779bf
2 changed files with 21 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/documents/management/commands/document_create_classifier.py
View File

@ -9,7 +9,8 @@ from ...mixins import Renderable
class Command(Renderable, BaseCommand):
help = """
There is no help.
Trains the classifier on your data and saves the resulting models to a
file. The document consumer will then automatically use this new model.
""".replace(" ", "")
def __init__(self, *args, **kwargs):
@ -18,6 +19,7 @@ class Command(Renderable, BaseCommand):
def handle(self, *args, **options):
clf = DocumentClassifier()
clf.train()
logging.getLogger(__name__).info("Saving models to " +
settings.MODEL_FILE + "...")
logging.getLogger(__name__).info(
"Saving models to {}...".format(settings.MODEL_FILE)
)
clf.save_classifier()

21
src/documents/management/commands/document_retagger.py
View File

@ -48,17 +48,28 @@ class Command(Renderable, BaseCommand):
self.verbosity = options["verbosity"]
if options["inbox_only"]:
documents = Document.objects.filter(tags__is_inbox_tag=True).exclude(tags__is_archived_tag=True).distinct()
queryset = Document.objects.filter(tags__is_inbox_tag=True)
else:
documents = Document.objects.all().exclude(tags__is_archived_tag=True).distinct()
queryset = Document.objects.all()
documents = queryset.exclude(tags__is_archived_tag=True).distinct()
logging.getLogger(__name__).info("Loading classifier")
try:
clf = DocumentClassifier.load_classifier()
except FileNotFoundError:
logging.getLogger(__name__).fatal("Cannot classify documents, classifier model file was not found.")
logging.getLogger(__name__).fatal("Cannot classify documents, "
"classifier model file was not "
"found.")
return
for document in documents:
logging.getLogger(__name__).info("Processing document {}".format(document.title))
clf.classify_document(document, classify_document_type=options["type"], classify_tags=options["tags"], classify_correspondent=options["correspondent"], replace_tags=options["replace_tags"])
logging.getLogger(__name__).info(
"Processing document {}".format(document.title)
)
clf.classify_document(
document,
classify_document_type=options["type"],
classify_tags=options["tags"],
classify_correspondent=options["correspondent"],
replace_tags=options["replace_tags"]
)