class BovespaAccount(CustomDjangoCassandraModel):
__table_name__ = "bovespa_account"
# ID of the company in B3
ccvm = columns.Text(partition_key=True)
# Date of the account value
period = columns.Date(primary_key=True, clustering_order="DESC")
# The version of the account. The company could present different
# versions of the files
version = columns.Text(primary_key=True, clustering_order="DESC")
# The account number. Ex. "1.01.01"
number = columns.Text(primary_key=True, max_length=15)
# Financial type account (instant/individual or consolidated)
financial_info_type = columns.Text(primary_key=True, max_length=15)
# Type of financial statement
balance_type = columns.Text(max_length=15, required=True)
# The account name. Ex. "Receita de Venda de Bens e/ou Serviços"
name = columns.Text(max_length=200, required=True)
# Company sector
sector = columns.Integer(default=0, required=True)
# The amount of the account
amount = Decimal(required=True, max_digits=20, decimal_places=2)
# The comments. Used for "DFP_BALANCE_DMPL" accounts, explaining the
# meaning of the account: Shareholder's Equity, Accrued Profit/Loss, etc.
comments = columns.Text()
# When was created the entity and the last modification date
created_at = columns.DateTime(default=datetime.utcnow)
updated_at = columns.DateTime(default=datetime.utcnow)
# Controls if the entity is active or has been deleted
is_deleted = columns.Boolean(default=False)
deleted_reason = columns.Text()
class Meta:
get_pk_field = "ccvm"
def validate(self):
super().validate()
if self.financial_info_type not in FINANCIAL_INFO_TYPES:
raise ValidationError("Invalid financial type [{0}] for account "
"[{1} {2}]. Valid types are: {3}.".format(
self.financial_info_type, self.number,
self.name, FINANCIAL_INFO_TYPES))
if self.balance_type not in BALANCE_TYPES:
raise ValidationError(
"Invalid balance type [{0}]. Valid types are: {1}.".format(
self.balance_type, BALANCE_TYPES))
class UserModel(Model):
"""Model class that maps to the user table"""
__table_name__ = 'users'
user_id = columns.UUID(db_field='userid', primary_key=True)
first_name = columns.Text(db_field='firstname')
last_name = columns.Text(db_field='lastname')
email = columns.Text()
created_date = columns.Date()
class BovespaCompany(CustomDjangoCassandraModel):
__table_name__ = "bovespa_company"
# Force that all the values will reside in the seam node of the cluster
entity_type = columns.Text(partition_key=True, default="company")
# ID of the company in B3
ccvm = columns.Text(primary_key=True)
# When was created the entity and the last modification date
created_at = columns.DateTime(default=datetime.utcnow)
updated_at = columns.DateTime(default=datetime.utcnow)
# Controls if the entity is active or has been deleted
is_deleted = columns.Boolean(default=False)
deleted_reason = columns.Text()
company_name = columns.Text(required=True)
cnpj = columns.Text()
company_type = columns.Text()
situation = columns.Text(required=True)
granted_date = columns.Date()
canceled_date = columns.Date()
class Meta:
get_pk_field = "entity_type"
def validate(self):
super().validate()
if self.situation not in SITUATIONS:
raise ValidationError(
"Invalid situation [{0}]. Valid situations are: {1}.".format(
self.situation, SITUATIONS))
class BovespaCompanyFile(CustomDjangoCassandraModel):
__table_name__ = "bovespa_company_file"
# ID of the company in B3
ccvm = columns.Text(partition_key=True)
# The type of document
doc_type = columns.Text(max_length=3, primary_key=True)
# The fiscal date the file is making reference.
fiscal_date = columns.Date(primary_key=True, clustering_order="DESC")
# The file version. The company could present different version of
# the files for a specific fiscal period
version = columns.Text(primary_key=True, clustering_order="DESC")
status = columns.Text(default=FILE_STATUS_NOT_PROCESSED)
# When was created the entity and the last modification date
created_at = columns.DateTime(default=datetime.utcnow)
updated_at = columns.DateTime(default=datetime.utcnow)
# Controls if the entity is active or has been deleted
is_deleted = columns.Boolean(default=False)
deleted_reason = columns.Text()
# The protocol code associated with the file
protocol = columns.Text(required=True)
# When the documents were delivered
delivery_date = columns.DateTime(required=True)
# Why the files were delivered
delivery_type = columns.Text(required=True)
# The official name of the company
company_name = columns.Text(required=True)
# The company CNPJ
company_cnpj = columns.Text(required=True)
# The Fiscal Period decomposed into year, quarter, month
# The year of the balance sheet
# Ex. 2015
fiscal_date_y = columns.SmallInt()
# The day of the year of the balance sheet
# Ex. 2015
fiscal_date_yd = columns.SmallInt()
# The quarter of the balance sheet
# Ex. 1
fiscal_date_q = columns.SmallInt()
# The month of the balance sheet
# Ex. 1
fiscal_date_m = columns.SmallInt()
# The day of the month of the balance sheet
# Ex. 1
fiscal_date_md = columns.SmallInt()
# The week of the year
# Ex. 1
fiscal_date_w = columns.SmallInt()
# The day of the week of the year
# Ex. 1
fiscal_date_wd = columns.SmallInt()
# Combination of YEAR-QUARTER in the form of 2018-Q1
# That allows us to facet results per quarter
fiscal_date_yq = columns.Text()
# Combination of YEAR-MONTH in the form of 2018-01
# That allows us to facet results per month
fiscal_date_ym = columns.Text()
# The url to the file that contains the information in bovespa. This
# will be the url we will use to download the file from the source
source_url = columns.Text(required=True)
# The url to the file that contains the information. Is an url to a
# repository of our own. The file has already beed downloaded and
# persisted into a custom repository. We do not need to access the source
file_url = columns.Text()
# The internal name of the file
file_name = columns.Text()
# The extension of the filename
file_extension = columns.Text()
# Each key represents the name of the file in the ENER arquive.
# The value is the original content converted into JSON - when possible -
# and persisted as Text
# content = KeyEncodedMap(
# key_type=columns.Text, value_type=columns.Text)
class Meta:
get_pk_field = "ccvm"
def validate(self):
super().validate()
if self.doc_type not in DOC_TYPES:
raise ValidationError(
"Invalid doc type [{0}]. Valid types are: {1}.".format(
self.doc_type, DOC_TYPES))
if self.status not in FILE_STATUSES:
raise ValidationError(
"Invalid file status [{0}]. Valid statuses are: {1}.".format(
self.status, FILE_STATUSES))
class Allv4Datatypes(UserType):
a = columns.Date()
b = columns.SmallInt()
c = columns.Time()
d = columns.TinyInt()
# Controls if the entity is active or has been deleted
is_deleted = columns.Boolean(default=False)
deleted_reason = columns.Text()
crawl_param = columns.Integer(required=True)
name = columns.Text(required=True)
situation = columns.Text(required=True)
short_description = columns.Text()
long_description = columns.Text()
# The date when the company was founded
foundation_date = columns.Date()
# Country of the company
# ISO 3166-1 alpha 3 code
country_code = columns.Text(min_length=3, max_length=3)
# A list of specialties of the company
specialties = columns.List(value_type=columns.Text)
# A field that represent a map of key-value
# We use caravaggio KeyEncodedMap that appends the field name
# to each of the keys in order to make them indexable by the
# Search Indexer.
websites = KeyEncodedMap(
key_type=columns.Text, value_type=columns.Text)
class Company(CustomDjangoCassandraModel):
"""
A public traded company
"""
__table_name__ = "company"
# A unique identifier of the entity
_id = columns.UUID(partition_key=True, default=uuid.uuid4)
# The owner of the data. Who own's the company data persisted
user = columns.Text(primary_key=True)
# When was created the entity and the last modification date
created_at = columns.DateTime(default=datetime.utcnow)
updated_at = columns.DateTime(default=datetime.utcnow)
# Controls if the entity is active or has been deleted
is_deleted = columns.Boolean(default=False)
deleted_reason = columns.Text()
# The name of the company
name = columns.Text(required=True)
# A short description about the company
short_description = columns.Text()
# The company domain (e.g. preseries.com)
domain = columns.Text(max_length=50)
# The date when the company was founded
foundation_date = columns.Date()
# The date of the latest funding round
last_round = columns.Date()
# The total number of funding rounds
round_notes = columns.Text()
# Country of the company
# ISO 3166-1 alpha 3 code
country_code = columns.Text(min_length=3, max_length=3)
# The stock trading symbol
stock_symbol = columns.Text()
# Contact email of the company
contact_email = columns.Text()
# The IDs of the founders of the company
founders = columns.List(value_type=columns.UUID)
# Address of the headquarters of the company
address = UserDefinedType(Address)
# A list of specialties of the company
specialties = columns.List(value_type=columns.Text)
# The counters of the latest followers in twitter
# (example of list of integers)
latest_twitter_followers = columns.List(value_type=columns.Integer)
# A field that represent a map of key-value
# We use caravaggio KeyEncodedMap that appends the field name
# to each of the keys in order to make them indexable by the
# Search Indexer.
websites = KeyEncodedMap(key_type=columns.Text, value_type=columns.Text)
# A field that represents a raw JSON with the crawler configurations, each
# key is a reference to a crawler
crawler_config = columns.Text()
# A field that represents a raw JSON content
extra_data = columns.Text()
latitude = columns.Float()
longitude = columns.Float()
coordinates = columns.Text()
class Meta:
get_pk_field = '_id'
def validate(self):
super(Company, self).validate()
if self.name == "test":
raise ValidationError('The company name cannot be test')
class TestQueryModel(Model):
test_id = columns.UUID(primary_key=True, default=uuid4)
date = columns.Date(primary_key=True)
description = columns.Text()
class v4DatatypesModel(Model):
id = columns.Integer(primary_key=True)
a = columns.Date()
b = columns.SmallInt()
c = columns.Time()
d = columns.TinyInt()