def analyze_field_tag(self, doc_unified: str, tag: str):
"""
Given a unified document title and a tag, tries to identify a research field
Updates references accordingly
:param doc_unified:
:param tag:
:return:
"""
if not is_field_tag(tag):
return
# Build the unified name of the found research field tag
field_unified, field_real = unify_field_title(tag)
# Check if that research field already exists
if field_unified in self._unified_field_title_to_field:
# If yes check if it (CacheField) needs to be updated
existing_field = self._unified_field_title_to_field[field_unified]
if len(existing_field.title) < len(field_real):
existing_field.title = field_real
existing_field_docs = self._unified_field_title_to_documents[
field_unified]
existing_field_docs.add(doc_unified)
else:
# If not add a new CacheField and create a new list for field_to_docs
self._unified_field_title_to_field[field_unified] = CacheField(
title=field_real, unified_title=field_unified)
field_documents = set()
field_documents.add(doc_unified)
self._unified_field_title_to_documents[
field_unified] = field_documents
def analyze_field_tag(self, doc_unified: str, tag: str):
"""
Given a unified document title and a tag, tries to identify a research field
Updates references accordingly
:param doc_unified:
:param tag:
:return:
"""
if not is_field_tag(tag):
return
# Build the unified name of the found research field tag
field_unified, field_real = unify_field_title(tag)
# Check if that research field already exists
if field_unified in self._unified_field_title_to_field:
# If yes check if it (CacheField) needs to be updated
existing_field = self._unified_field_title_to_field[field_unified]
if len(existing_field.title) < len(field_real):
existing_field.title = field_real
existing_field_docs = self._unified_field_title_to_documents[field_unified]
existing_field_docs.add(doc_unified)
else:
# If not add a new CacheField and create a new list for field_to_docs
self._unified_field_title_to_field[field_unified] = CacheField(
title=field_real, unified_title=field_unified)
field_documents = set()
field_documents.add(doc_unified)
self._unified_field_title_to_documents[field_unified] = field_documents
def test_unify_field_title(self):
title = "cyber-physical systems"
unified, real = unify_field_title(title)
self.assertEqual(unified, "cyberphysicalsystems")
self.assertEqual(real, "Cyber-Physical Systems")
def test_unify_field_title(self):
title = "cyber-physical systems"
unified, real = unify_field_title(title)
self.assertEqual(unified, "cyberphysicalsystems")
self.assertEqual(real, "Cyber-Physical Systems")
