def handle(self, *args, **options):
print("Importing Khan Academy topic tree from khan_academy_ricecooker_tree.json...")
filename = os.path.join(data_dir, 'khan_academy_ricecooker_tree.json')
root_node = json.loads(open(filename).read(), encoding='utf-8')
source_id = "khan_academy_us"
topic = "Khan Academy Curriculum"
country = "USA"
digitization_method = "data_import"
draft = True
ka_user, _created = User.objects.get_or_create(username='******')
try:
existing_doc = CurriculumDocument.objects.get(source_id=source_id)
# this will delete all children and also learning objectives due to cascade delete
existing_doc.delete()
except CurriculumDocument.DoesNotExist:
pass
ka_judgments = HumanRelevanceJudgment.objects.filter(user=ka_user)
ka_judgments.delete()
document = CurriculumDocument.objects.create(
source_id=source_id,
title=topic,
country=country,
digitization_method=digitization_method,
is_draft=draft,
)
root = StandardNode.add_root(title=topic, identifier='KA-en', kind='channel', document=document)
for domain in root_node['children']:
get_node_data_recursive(domain, parent=root, user=ka_user)
def load_ngss(transformed_tree):
try:
document = CurriculumDocument.objects.get(
source_id=NGSS_DOCUMENT_ATTRIBUTES["source_id"])
document.delete()
except CurriculumDocument.DoesNotExist:
pass
document = CurriculumDocument.objects.create(**NGSS_DOCUMENT_ATTRIBUTES)
root = StandardNode.add_root(
identifier=transformed_tree["identifier"],
title=transformed_tree["title"],
kind=transformed_tree["kind"],
document=document,
)
def _add_children_to_parent(parent, children):
for i, child in enumerate(children):
sort_order = i + 1
source_kind = child["kind"]
if source_kind in NGSS_TO_NODE_KIND_MAPPING:
kind = NGSS_TO_NODE_KIND_MAPPING[source_kind]
else:
kind = source_kind
node = parent.add_child(
document=parent.document,
title=child["title"],
identifier=child["identifier"],
sort_order=sort_order,
kind=kind,
)
_add_children_to_parent(node, child["children"])
_add_children_to_parent(root, transformed_tree["children"])
def handle(self, *args, **options):
"""
Imports Australian curriculum standards into the alignment prototype database.
This command expects to find rdf files named "<subject grades>.rdf" (e.g. "Mathematics F-10.rdf") in the
alignmentpro/importing/data/australia_standards directory. These files can be retrieved from:
http://rdf.australiancurriculum.edu.au/
Currently, this function accepts no arguments.
"""
standards_dir = os.path.join(data_dir, 'australia_standards')
for afile in glob.glob(os.path.join(standards_dir, '*.rdf')):
basename = os.path.basename(afile)
topic = os.path.splitext(basename)[0]
with open(afile, encoding='utf-8') as doc:
data = xmltodict.parse(doc.read())
json_file = os.path.join(standards_dir, basename + ".json")
f = open(json_file, 'w', encoding='utf-8')
f.write(json.dumps(data, ensure_ascii=False, indent=2))
f.close()
# continue
source_id = "australia_standards_{}".format(
topic.lower().replace(" ", "_"))
country = "Australia"
digitization_method = "data_import"
draft = True
# For now, clean out old runs so we don't proliferate the db.
try:
existing_doc = CurriculumDocument.objects.get(
source_id=source_id)
# this will delete all children and also learning objectives due to cascade delete
existing_doc.delete()
except CurriculumDocument.DoesNotExist:
pass
document = CurriculumDocument.objects.create(
source_id=source_id,
title=topic,
country=country,
digitization_method=digitization_method,
is_draft=draft,
)
root = StandardNode.add_root(title=topic,
kind='document',
document=document)
topic_tree = get_topic_hierarchy(data)
for subject in topic_tree:
add_standard(subject, parent=root)
def handle(self, *args, **options):
print("Handling importchunk with options = ", options)
source_id = options["source_id"]
digitization_method = options["digitization_method"] or "unknown"
title = options.get("title", "Unknown title")
country = options["country"] or "Unknown"
draft = options["draft"]
try:
document = CurriculumDocument.objects.get(source_id=source_id)
if document.is_draft:
print("Deleting old draft verison of curriculum document...")
document.delete()
else:
print(
'ERROR: document is no longer in draft state so cannot be updated.'
)
sys.exit(1)
except CurriculumDocument.DoesNotExist:
pass
document = CurriculumDocument.objects.create(
source_id=source_id,
title=title,
country=country,
digitization_method=digitization_method,
is_draft=draft,
)
root = StandardNode.add_root(title=title, document=document)
curriculum_list = load_curriculum_list(options["gsheet_id"],
options["gid"])
nodes_breadcrumbs = [root, None]
node_counts = [None, 0]
cur_level = 1
for row in curriculum_list:
assert len(node_counts) == cur_level + 1, 'wrong node_counts'
assert len(
nodes_breadcrumbs) == cur_level + 1, 'wrong nodes_breadcrumbs'
# staying at the same level
if row["level"] == cur_level:
pass
# going deeper (add a child to current leaf)
elif row["level"] > cur_level:
if not (row["level"] - 1 == cur_level):
print("ERR too many indentnts at \n", list(row.values()))
sys.exit(1)
cur_level = row["level"]
nodes_breadcrumbs.append(None)
node_counts.append(0)
# popping out (add a child to parent at level)
elif row["level"] < cur_level:
cur_level = row["level"]
nodes_breadcrumbs = nodes_breadcrumbs[0:cur_level + 1]
node_counts = node_counts[0:cur_level + 1]
# Add the node to the appropriate location
parent = nodes_breadcrumbs[cur_level - 1]
node_counts[cur_level] += 1
node = parent.add_child(
document=parent.document,
title=row[TITLE_KEY],
identifier=row[IDENTIFIER_KEY],
sort_order=node_counts[cur_level],
kind=row[KIND_KEY],
time_units=float(row[TIME_UNITS_KEY])
if row[TIME_UNITS_KEY] else None,
notes=row[NOTES_KEY] or '',
)
nodes_breadcrumbs[cur_level] = node
print("Import finished")
print(get_tree_as_markdown(root, {}))
def handle(self, *args, **options):
print("Handling importchunk with options = ", options)
source_id = options["source_id"]
digitization_method = options["digitization_method"] or "unknown"
title = options.get("title", "Unknown title")
country = options["country"] or "Unknown"
draft = options["draft"]
document, created = CurriculumDocument.objects.get_or_create(
source_id=source_id,
title=title,
country=country,
digitization_method=digitization_method,
is_draft=draft,
)
if created:
root = StandardNode.add_root(title=title, document=document)
else:
root = document.root
curriculum_list = load_curriculum_list(options["gsheet_id"],
options["gid"])
nodes_breadcrumbs = [root]
node_counts = [0]
cur_level = 0
for row in curriculum_list:
print(
"Porcessing row",
" " * row["level"] + "-",
row[IDENTIFIER_KEY],
row[TITLE_KEY],
)
# staying (add a child to current parent)
if row["level"] == cur_level:
node_counts[cur_level] += 1
parent = nodes_breadcrumbs[cur_level - 1]
node = _add_row_to_parent(parent,
row,
sort_order=node_counts[cur_level])
if row[LEARNING_OBJECTIVES_KEY]:
_add_learning_objectives(node,
row[LEARNING_OBJECTIVES_KEY])
nodes_breadcrumbs[cur_level] = node
# going deeper (add a child to current leaf)
elif row["level"] > cur_level:
parent = nodes_breadcrumbs[cur_level]
node = _add_row_to_parent(parent,
row,
sort_order=node_counts[cur_level])
if row[LEARNING_OBJECTIVES_KEY]:
_add_learning_objectives(node,
row[LEARNING_OBJECTIVES_KEY])
nodes_breadcrumbs.append(node)
node_counts.append(1)
cur_level += 1
# popping out (add a child to parent at level)
elif row["level"] < cur_level:
new_level = row["level"]
parent = nodes_breadcrumbs[new_level - 1]
node_counts[new_level] += 1
node = _add_row_to_parent(parent,
row,
sort_order=node_counts[new_level])
if row[LEARNING_OBJECTIVES_KEY]:
_add_learning_objectives(node,
row[LEARNING_OBJECTIVES_KEY])
nodes_breadcrumbs = nodes_breadcrumbs[0:new_level] + [node]
node_counts = node_counts[0:new_level + 1]
cur_level = new_level
print("Import finished")
def import_california():
j = Jurisdictions.objects.get(id=CALIFORNIA_JURISDICTION_ID)
root_tuples = CALIFORNIA_VOCATIONAL_ROOTS
tree = join_standards(
root_tuples,
identifier="CTE",
title="California Career Technical Education",
)
transformed_tree = transform_subtree(tree)
# drop empty folders
transformed_tree = drop_titles(transformed_tree, ['Academics'])
# set subjects
for child in transformed_tree['children']:
child['title'] = child['extra_fields']['subject']
# set some identifiers
def _set_identifier_from_listId(subtree):
if subtree['identifier'] == 'no identifier' and 'listId' in subtree[
'extra_fields']:
subtree['identifier'] = subtree['extra_fields']['listId']
for child in subtree['children']:
_set_identifier_from_listId(child)
_set_identifier_from_listId(transformed_tree)
# hoist non-useful headings
hoist_unnecessary_tree_nodes(
transformed_tree, hoist_titles=CALIFORNIA_VOCATIONAL_HOIST_TITLES)
# set kinds
for subject in transformed_tree['children']:
if subject['kind'] == 'no statementLabel':
subject['kind'] = 'subject'
for topic in subject['children']:
if topic['kind'] == 'no statementLabel':
topic['kind'] = 'topic'
print_commonstandards_tree(transformed_tree, display_len_limit=90)
# return transformed_tree
try:
document = CurriculumDocument.objects.get(
source_id=CALIFORNIA_VOCATIONAL_DOCUMENT_ATTRIBUTES["source_id"])
document.delete()
except CurriculumDocument.DoesNotExist:
pass
document = CurriculumDocument.objects.create(
**CALIFORNIA_VOCATIONAL_DOCUMENT_ATTRIBUTES)
root = StandardNode.add_root(
identifier=transformed_tree["identifier"],
title=transformed_tree["title"],
kind=transformed_tree["kind"],
document=document,
)
def _add_children_to_parent(parent, children):
for i, child in enumerate(children):
sort_order = i + 1
node = parent.add_child(
document=parent.document,
title=child["title"],
identifier=child["identifier"],
sort_order=sort_order,
kind=child["kind"],
)
_add_children_to_parent(node, child["children"])
_add_children_to_parent(root, transformed_tree["children"])
print("Finished importing California vocational standards")