def test_find_by_hash(self, m_Tag, m_File):
m_session = MagicMock()
hash_type, hash = "something", "anotherthing"
tag = MagicMock()
tag.id = randint(0, 10)
tags = [tag.id]
FileExt.query_find_by_hash(hash_type, hash, tags, m_session)
m_session.query.called_with(FileExt)
m_Tag.find_by_id.assert_called_once_with(tag.id, m_session)
def test_find_by_hash(self, m_Tag, m_File):
m_session = MagicMock()
hash_type, hash = "something", "anotherthing"
tag = MagicMock()
tag.id = randint(0, 10)
tags = [tag.id]
FileExt.query_find_by_hash(hash_type, hash, tags, m_session)
m_session.query.called_with(FileExt)
m_session.query().filter_by.assert_called_once_with(id=tag.id)
m_session.query().filter_by().one.assert_called_once()
def test_find_by_hash_distinct_false(self, m_Tag, m_File):
m_session = MagicMock()
hash_type, hash = "something", "anotherthing"
tag = MagicMock()
tag.id = randint(0, 10)
tags = [tag.id]
FileExt.query_find_by_hash(hash_type,
hash,
tags,
m_session,
distinct_name=False)
m_session.query.called_with(FileExt)
m_session.query().filter_by.assert_called_once_with(id=tag.id)
m_session.query().filter_by().one.assert_called_once()
def list(name: text = None,
hash: text = None,
tags: comma_separated_list = None,
offset: number = 0,
limit: number = 25):
""" Search a file using query filters (tags + hash or name). Support
pagination.
:param name: lookup name
:param hash: lookup hash value
:param tags: lookup tag list
:param offset: start index in matching results
:param limit: max number of results
:rtype: dict of 'total': int, 'page': int, 'per_page': int,
'items': list of file(s) found
:return:
on success 'items' contains a list of files found
on error 'msg' gives reason message
"""
session = db.session
if name is not None:
name = decode_utf8(name)
log.debug("name %s h_value %s tags %s",
name, hash, tags)
if name is not None and hash is not None:
raise ValueError("Can't find using both name and hash")
if name is not None:
base_query = FileExt.query_find_by_name(name, tags, session)
elif hash is not None:
h_type = guess_hash_type(hash)
if h_type is None:
raise ValueError("Hash not supported")
base_query = FileExt.query_find_by_hash(
h_type, hash, tags, session)
else:
# FIXME this is just a temporary way to output
# all files, need a dedicated
# file route and controller
base_query = FileExt.query_find_by_name("", tags, session)
# TODO: Find a way to move pagination as a BaseQuery like in
# flask_sqlalchemy.
# https://github.com/mitsuhiko/flask-sqlalchemy/blob/master/flask_sqlalchemy/__init__.py#L422
items = base_query.limit(limit).offset(offset).all()
if offset == 0 and len(items) < limit:
total = len(items)
else:
total = base_query.count()
log.debug("Found %s results", total)
return {
'total': total,
'offset': offset,
'limit': limit,
'items': file_ext_schema_lite.dump(items, many=True).data,
}
def get(response,
sha256: text,
alt: one_of(('media', '')) = '',
offset: number = 0,
limit: number = 25):
""" Detail about one file and all known scans summary where file was
present (identified by sha256). Support pagination.
:param all params are sent using query method
:param if alt parameter is "media", response will contains the binary data
:rtype: dict of 'total': int, 'page': int, 'per_page': int,
:return:
on success fileinfo contains file information
on success 'items' contains a list of files found
on error 'msg' gives reason message
"""
session = db.session
log.debug("h_value %s", sha256)
# Check wether its a download attempt or not
if alt == "media":
return _download(response, sha256)
file = File.load_from_sha256(sha256, session)
# query all known results not only those with different names
base_query = FileExt.query_find_by_hash("sha256",
sha256,
None,
session,
distinct_name=False)
# TODO: Find a way to move pagination as a BaseQuery like in
# flask_sqlalchemy.
# https://github.com/mitsuhiko/flask-sqlalchemy/blob/master/flask_sqlalchemy/__init__.py#L422
items = base_query.limit(limit).offset(offset).all()
if offset == 0 and len(items) < limit:
total = len(items)
else:
total = base_query.count()
log.debug("offset %d limit %d total %d", offset, limit, total)
file_ext_schema = FileExtSchema(exclude=('probe_results', 'file_infos'))
fileinfo_schema = FileSchema()
# TODO: allow formatted to be a parameter
formatted = True
fileinfo_schema.context = {'formatted': formatted}
return {
'file_infos': fileinfo_schema.dump(file).data,
'total': total,
'offset': offset,
'limit': limit,
'items': file_ext_schema.dump(items, many=True).data,
}