Implemented the classifier model, including automatic tagging of new documents

src/documents/signals/handlers.py

@@ -8,6 +8,7 @@ from django.contrib.auth.models import User
 from django.contrib.contenttypes.models import ContentType
 from django.utils import timezone
 
+from documents.classifier import DocumentClassifier
 from ..models import Correspondent, Document, Tag, DocumentType
 
 
@@ -15,79 +16,16 @@ def logger(message, group):
     logging.getLogger(__name__).debug(message, extra={"group": group})
 
 
-def set_correspondent(sender, document=None, logging_group=None, **kwargs):
-
-    # No sense in assigning a correspondent when one is already set.
-    if document.correspondent:
-        return
-
-    # No matching correspondents, so no need to continue
-    potential_correspondents = list(Correspondent.match_all(document.content))
-    if not potential_correspondents:
-        return
-
-    potential_count = len(potential_correspondents)
-    selected = potential_correspondents[0]
-    if potential_count > 1:
-        message = "Detected {} potential correspondents, so we've opted for {}"
-        logger(
-            message.format(potential_count, selected),
-            logging_group
-        )
-
-    logger(
-        'Assigning correspondent "{}" to "{}" '.format(selected, document),
-        logging_group
-    )
-
-    document.correspondent = selected
-    document.save(update_fields=("correspondent",))
+classifier = None
 
 
-def set_document_type(sender, document=None, logging_group=None, **kwargs):
+def classify_document(sender, document=None, logging_group=None, **kwargs):
+    global classifier
+    if classifier is None:
+        classifier = DocumentClassifier.load_classifier()
 
-    # No sense in assigning a correspondent when one is already set.
-    if document.document_type:
-        return
+    classifier.classify_document(document, classify_correspondent=True, classify_tags=True, classify_type=True)
 
-    # No matching document types, so no need to continue
-    potential_document_types = list(DocumentType.match_all(document.content))
-    if not potential_document_types:
-        return
-
-    potential_count = len(potential_document_types)
-    selected = potential_document_types[0]
-    if potential_count > 1:
-        message = "Detected {} potential document types, so we've opted for {}"
-        logger(
-            message.format(potential_count, selected),
-            logging_group
-        )
-
-    logger(
-        'Assigning document type "{}" to "{}" '.format(selected, document),
-        logging_group
-    )
-
-    document.document_type = selected
-    document.save(update_fields=("document_type",))
-
-
-def set_tags(sender, document=None, logging_group=None, **kwargs):
-
-    current_tags = set(document.tags.all())
-    relevant_tags = (set(Tag.match_all(document.content)) | set(Tag.objects.filter(is_inbox_tag=True))) - current_tags
-
-    if not relevant_tags:
-        return
-
-    message = 'Tagging "{}" with "{}"'
-    logger(
-        message.format(document, ", ".join([t.slug for t in relevant_tags])),
-        logging_group
-    )
-
-    document.tags.add(*relevant_tags)
 
 
 def run_pre_consume_script(sender, filename, **kwargs):