class Foo(Model):
__tablename__ = 'foo'
query_class = FooQuery
_id = Column(types.Integer(), primary_key=True)
string = Column(types.String())
string2 = Column(types.String())
number = Column(types.Integer())
boolean = Column(types.Boolean(), default=True)
deferred1_col1 = orm.deferred(Column(types.Boolean()), group='deferred_1')
deferred1_col2 = orm.deferred(Column(types.Boolean()), group='deferred_1')
deferred2_col3 = orm.deferred(Column(types.Boolean()), group='deferred_2')
deferred2_col4 = orm.deferred(Column(types.Boolean()), group='deferred_2')
bars = orm.relationship('Bar', lazy=True)
quxs = orm.relationship('Qux', lazy=True)
@orm.validates('number')
def validate_number(self, key, value):
if value < 0:
raise ValueError('"number" must be positive')
return value
def view_joined(self):
return self.query.options(
orm.joinedload('bars').joinedload('bazs'), orm.joinedload('quxs'))
class Bar(Model):
__tablename__ = 'bar'
query_class = BarQuery
_id = Column(types.Integer(), primary_key=True)
string = Column(types.String())
number = Column(types.Integer())
foo_id = Column(types.Integer(), ForeignKey('foo._id'))
deferred1_col1 = orm.deferred(Column(types.Boolean()),
group='bar_deferred_1')
deferred2_col2 = orm.deferred(Column(types.Boolean()),
group='bar_deferred_2')
foo = orm.relationship('Foo')
bazs = orm.relationship('Baz')
def upgrade_3(session, metadata):
"""
Version 3 upgrade.
This upgrade adds a temporary song flag to the songs table
"""
op = get_upgrade_op(session)
songs_table = Table('songs', metadata, autoload=True)
if 'temporary' not in [col.name for col in songs_table.c.values()]:
if metadata.bind.url.get_dialect().name == 'sqlite':
op.add_column('songs', Column('temporary', types.Boolean(create_constraint=False), server_default=false()))
else:
op.add_column('songs', Column('temporary', types.Boolean(), server_default=false()))
else:
log.warning('Skipping upgrade_3 step of upgrading the song db')
class User(AutoTableMixin, UserMixin, BaseAuthModel):
"""Basic user model"""
__tablename__ = 'users'
# TODO: Replace this with something real
user_database = {'admin': ('admin', 'admin'), 'guest': ('guest', 'guest')}
id = Column(types.Integer, primary_key=True)
display_name = Column(types.String)
email = Column(types.String, unique=True)
username = Column(types.String, unique=True)
password = Column(types.String)
active = Column(types.Boolean())
confirmed_at = Column(types.DateTime())
roles = orm.relationship('Role',
secondary=roles_users,
backref=orm.backref('users', lazy='dynamic'))
def __init__(self, username, password, email):
self.password = password
self.email = email
self.username = username
@classmethod
def get(cls, id):
return cls.user_database.get(id)
def __repr__(self):
cname = self.__class__.__name__
name = ':{} "{}"'.format(self.username, self.display_name)
string = '<{cname}{name}>'.format(cname=cname, name=name)
return string
class User(models.Base):
__tablename__ = 'users'
id = Column(types.Integer(), primary_key=True, autoincrement=True)
fullname = Column(types.String(50), nullable=False)
username = Column(types.String(50),
nullable=False,
unique=True,
index=True)
password_hash = Column(types.String(128), nullable=False)
is_active = Column(types.Boolean(), default=False, nullable=False)
created_at = Column(types.TIMESTAMP, default=func.now())
updated_at = Column(types.TIMESTAMP, onupdate=func.now())
@property
def password(self):
raise ValueError('This is a only read attribute')
@password.getter
def password(self):
return self.password_hash
@password.setter
def password(self, raw_password):
self.password_hash = generate_password_hash(raw_password)
def verify_password(self, raw_password):
return check_password_hash(self.password_hash, raw_password)
class CategoriaModel(bd.Model):
__tablename__ = "t_categoria"
categoriaId = Column(name='cat_id',
type_=types.Integer,
primary_key=True,
autoincrement=True,
unique=True,
nullable=True)
categoriaNombre = Column(name='cat_nombre',
type_=types.String(45),
nullable=False)
categoriaOrden = Column(name='cat_orden',
type_=types.Integer,
nullable=False)
categoriaEstado = Column(name='cat_estado',
type_=types.Boolean(),
default=True,
nullable=False)
conocimientos = relationship('ConocimientoModel',
backref='categoriaConocimientos',
cascade='all, delete')
def __init__(self, nombre, orden, estado):
self.categoriaNombre = nombre,
self.categoriaOrden = orden
if estado:
self.categoriaEstado = estado
def save(self):
bd.session.add(self)
bd.session.commit()
class SwitchesState(Model):
__tablename__ = 'switches'
id = Column(types.Integer(), primary_key=True)
key = Column(types.BINARY(length=16), nullable=False, unique=True)
one = Column(types.Boolean(), nullable=False)
two = Column(types.Boolean(), nullable=False)
touched = Column(types.TIMESTAMP(timezone=True),
nullable=False,
server_default=sql.func.now(),
onupdate=sql.func.now())
def __init__(self):
self.key = uuid4().bytes
self.one = False
self.two = False
def update_steam_game_info():
print('Parse app info and dump to databse')
dic_steam_app = {}
with open(path_app_info, 'rb') as f:
lst_raw_string = f.readlines()
total_count = len(lst_raw_string)
current_count = 0
for i in lst_raw_string:
app_info = json.loads(i)
dic_steam_app.update(parse_steam_app_info(app_info))
show_work_status(1, total_count, current_count)
current_count += 1
df_steam_app = pd.DataFrame.from_dict(dic_steam_app, 'index')
df_steam_app = df_steam_app.loc[:, [
'app_id', 'name', 'release_date', 'type', 'currency', 'initial_price',
'developers', 'publishers', 'required_age', 'linux', 'mac', 'windows',
'fullgame', 'critic_score', 'recommendation', 'supported_languages',
'header_image', 'short_description', 'success'
]]
df_steam_app.to_sql('game_steam_app',
engine,
if_exists='replace',
index=False,
dtype={
'app_id': types.Integer(),
'name': types.String(200),
'release_date': types.Date,
'type': types.String(50),
'currency': types.String(5),
'initial_price': types.Float(),
'developers': types.String(500),
'publishers': types.String(500),
'required_age': types.Integer(),
'linux': types.Boolean(),
'mac': types.Boolean(),
'windows': types.Boolean(),
'fullgame': types.Integer(),
'critic_score': types.Integer(),
'recommendation': types.Integer(),
'supported_languages': types.String(500),
'header_image': types.String(500),
'short_description': types.String(1000),
'success': types.Boolean()
})
class Feed(Base):
id = Column(types.Integer(), primary_key=True, autoincrement=True)
url_id = Column(ForeignKey('url.id', ondelete=RESTRICT, onupdate=CASCADE),
nullable=False)
title = Column(types.Text(), nullable=False)
dead = Column(types.Boolean())
@declared_attr
def __table_args__(self):
return (Index(None, 'url_id', unique=True), )
class SurveyStatistics(model.BaseObject):
"""Data table to store survey (tool) information."""
__tablename__ = "statistics_surveys"
zodb_path = schema.Column(types.String(512), primary_key=True)
language = schema.Column(types.String(128), nullable=True)
published = schema.Column(types.Boolean(), nullable=True)
published_date = schema.Column(types.DateTime, nullable=True)
creation_date = schema.Column(types.DateTime, nullable=True)
class CategoriaModel(bd.Model):
__tablename__ = 't_categoria'
categoriaId = Column(name='cat_id',
type_=types.Integer,
primary_key=True,
autoincrement=True,
unique=True,
nullable=False)
categoriaNombre = Column(name='cat_nombre',
type_=types.String(45),
nullable=False)
categoriaOrden = Column(name='cat_orden',
type_=types.Integer,
nullable=False)
categoriaEstado = Column(
name='cat_estado',
type_=types.Boolean(),
# el default es el valor por defecto si es que no se ingresa uno
default=True,
nullable=False)
# FK
usuario = Column(ForeignKey('t_usuario.usuario_id'),
name='usuario_id',
type_=types.Integer,
nullable=False)
# el parametro cascade sirve para indicar que va a suceder cuando se elimine un padre, en este caso al poner 'all, delete', todos los hijos se van a eliminar consecuentemente
# https://docs.sqlalchemy.org/en/14/orm/cascades.html
conocimientos = relationship('ConocimientoModel',
backref='categoriaConocimientos',
cascade='all, delete')
def __init__(self, nombre, orden, estado, usuario):
self.categoriaNombre = nombre
self.categoriaOrden = orden
self.usuario = usuario
if estado:
self.categoriaEstado = estado
def save(self):
bd.session.add(self)
bd.session.commit()
def delete(self):
bd.session.delete(self)
bd.session.commit()
def json(self):
return {
'cat_id': self.categoriaId,
'cat_nombre': self.categoriaNombre,
'cat_orden': self.categoriaOrden,
'cat_estado': self.categoriaEstado
}
class Company(BaseObject):
"""Information about a company."""
__tablename__ = "company"
id = schema.Column(types.Integer(), primary_key=True, autoincrement=True)
session_id = schema.Column(
types.Integer(),
schema.ForeignKey("session.id", onupdate="CASCADE",
ondelete="CASCADE"),
nullable=False,
index=True,
)
session = orm.relation(
"SurveySession",
cascade="all,delete-orphan",
single_parent=True,
backref=orm.backref("company", uselist=False, cascade="all"),
)
country = schema.Column(types.String(3))
employees = schema.Column(Enum([None, "1-9", "10-49", "50-249", "250+"]))
conductor = schema.Column(Enum([None, "staff", "third-party", "both"]))
referer = schema.Column(
Enum([
None,
"employers-organisation",
"trade-union",
"national-public-institution",
"eu-institution",
"health-safety-experts",
"other",
]))
workers_participated = schema.Column(types.Boolean())
needs_met = schema.Column(types.Boolean())
recommend_tool = schema.Column(types.Boolean())
timestamp = schema.Column(types.DateTime(), nullable=True)
class ActionPlan(BaseObject):
"""Action plans for a known risk."""
__tablename__ = "action_plan"
id = schema.Column(types.Integer(), primary_key=True, autoincrement=True)
risk_id = schema.Column(
types.Integer(),
schema.ForeignKey(Risk.id, onupdate="CASCADE", ondelete="CASCADE"),
nullable=False,
index=True,
)
action_plan = schema.Column(types.UnicodeText())
prevention_plan = schema.Column(types.UnicodeText())
# The column "action" is the synthesis of "action_plan" and "prevention_plan"
action = schema.Column(types.UnicodeText())
requirements = schema.Column(types.UnicodeText())
responsible = schema.Column(types.Unicode(256))
budget = schema.Column(types.Integer())
planning_start = schema.Column(types.Date())
planning_end = schema.Column(types.Date())
reference = schema.Column(types.Text())
plan_type = schema.Column(
Enum([
"measure_custom",
"measure_standard",
"in_place_standard",
"in_place_custom",
]),
nullable=False,
index=True,
default="measure_custom",
)
solution_id = schema.Column(types.Unicode(20))
used_in_training = schema.Column(
types.Boolean(),
default=True,
index=True,
)
risk = orm.relation(
Risk,
backref=orm.backref("action_plans",
order_by=id,
cascade="all, delete, delete-orphan"),
)
class Boolean(PrimitiveType):
sqltype = sqltypes.Boolean()
@staticmethod
def python_type(val):
if isinstance(val, basestring):
val = val.strip().lower()
return val == 'true'
return bool(val) # ???
def matches(self, value, text):
"""
Only "true" or "false" strings match, everything else do not
"""
assert isinstance(value, bool)
text = text.capitalize()
if text in ('False', 'True'):
return str(value) == text
return False
class Module(SurveyTreeItem):
"""A module.
This is a dummy object needed to be able to put modules in the
survey tree.
"""
__tablename__ = "module"
__mapper_args__ = dict(polymorphic_identity="module")
sql_module_id = schema.Column(
"id",
types.Integer(),
schema.ForeignKey(SurveyTreeItem.id,
onupdate="CASCADE",
ondelete="CASCADE"),
primary_key=True,
)
module_id = schema.Column(types.String(16), nullable=False)
solution_direction = schema.Column(types.Boolean(), default=False)
def init():
"""define table settings and mapping"""
# Database definition
from sqlalchemy import types, orm
from sqlalchemy.schema import Column, Table, Sequence, ForeignKey
from sqlalchemy.orm import relationship, backref, relation, mapper
from User import User
t_settings = Table(
'settings',
db.metadata,
Column('id',
types.Integer,
Sequence('settings_seq_id', optional=True),
nullable=False,
primary_key=True),
Column('id_user', types.Integer, ForeignKey('user.id'),
nullable=False),
Column('display_date',
types.Boolean(255),
nullable=False,
default=True),
Column('planning_theme',
types.Enum('default', 'pepper', 'blue', 'eggplant', 'lightness',
'mint'),
nullable=False,
default='pepper'),
)
mapper(Settings,
t_settings,
properties={
'user':
relationship(User,
backref=backref('settings',
uselist=False,
cascade="all, delete-orphan")),
})
class Dewey(Model):
__tablename__ = 'dewey'
__events__ = None
_id = Column(types.Integer(), primary_key=True)
name = Column(types.String())
number = Column(types.Integer())
min_hueys = Column(types.Boolean())
hueys = orm.relationship('Huey')
@events.before_insert()
def before_insert(mapper, connection, target):
target.name = 'Dewey'
@events.on_set('name', retval=True)
def on_set_name(target, value, oldvalue, initator):
if oldvalue is None or (
hasattr(oldvalue, '__class__')
and oldvalue.__class__.__name__ == 'symbol'):
# oldvalue is a symbol for either NO_VALUE or NOT_SET so allow
# update
return value
else:
# value previously set, so prevent edit
return oldvalue
@events.on_append('hueys')
def on_append_hueys(target, value, intiator):
if len(target.hueys) >= 1:
target.min_hueys = True
@events.on_remove('hueys')
def on_remove_hueys(target, value, initator):
if not len(target.hueys) >= 1:
target.min_hueys = False
@events.before_insert_update()
def before_edit(mapper, connection, target):
target.number = (target.number or 0) + 1
class UsuarioModel(bd.Model):
__tablename__ = "t_usuario"
usuarioId = Column(name="usuario_id",
type_=types.Integer,
autoincrement=True,
primary_key=True,
unique=True,
nullable=False)
usuarioNombre = Column(name="usuario_nombre",
type_=types.String(25),
nullable=False)
usuarioApellido = Column(name="usuario_apellido",
type_=types.String(45),
nullable=False)
usuarioCorreo = Column(name="usuario_correo",
type_=types.String(45),
nullable=False)
usuarioPassword = Column(name="usuario_password",
type_=types.TEXT,
nullable=False)
usuarioFoto = Column(name="usuario_foto", type_=types.TEXT, nullable=False)
usuarioTitulo = Column(name="usuario_titulo",
type_=types.String(45),
nullable=False)
usuarioInfo = Column(name="usuario_info", type_=types.TEXT, nullable=False)
usuarioCV = Column(name="usuario_cv", type_=types.TEXT, nullable=False)
usuarioSuperUser = Column(name="usuario_superuser",
type_=types.Boolean(),
nullable=False)
def test_should_boolean_convert_boolean():
assert get_field(types.Boolean()).type == graphene.Boolean
class SurveyTreeItem(BaseObject):
"""A tree of questions.
The data is stored in the form of a materialized tree. The path is built
using a list of item numbers. Each item number has three digits and uses
0-prefixing to make sure we can use simple string sorting to produce a
sorted tree.
"""
__tablename__ = "tree"
__table_args__ = (
schema.UniqueConstraint("session_id", "path"),
schema.UniqueConstraint("session_id", "zodb_path", "profile_index"),
{},
)
id = schema.Column(types.Integer(), primary_key=True, autoincrement=True)
session_id = schema.Column(
types.Integer(),
schema.ForeignKey("session.id", onupdate="CASCADE",
ondelete="CASCADE"),
nullable=False,
index=True,
)
parent_id = schema.Column(
types.Integer(),
schema.ForeignKey("tree.id", onupdate="CASCADE", ondelete="CASCADE"),
nullable=True,
index=True,
)
type = schema.Column(
Enum(["risk", "module"]),
nullable=False,
index=True,
)
path = schema.Column(
types.String(40),
nullable=False,
index=True,
)
has_description = schema.Column(
types.Boolean(),
default=False,
index=True,
)
zodb_path = schema.Column(
types.String(512),
nullable=False,
)
profile_index = schema.Column(
types.Integer(),
default=0,
nullable=False,
)
depth = schema.Column(
types.Integer(),
default=0,
nullable=False,
index=True,
)
title = schema.Column(types.Unicode(512))
postponed = schema.Column(types.Boolean())
skip_children = schema.Column(
types.Boolean(),
default=False,
nullable=False,
)
__mapper_args__ = dict(polymorphic_on=type)
session = orm.relation(
"SurveySession",
cascade="all",
)
# parent = orm.relation("SurveyTreeItem", uselist=False)
@property
def parent(self):
# XXX Evil! Figure out why the parent relation does not work
return self.parent_id and Session.query(SurveyTreeItem).get(
self.parent_id)
def getId(self):
return self.path[-3:].lstrip("0")
@property
def short_path(self):
def slice(path):
while path:
yield path[:3].lstrip("0")
path = path[3:]
return slice(self.path)
@property
def number(self):
return ".".join(self.short_path)
def children(self, filter=None):
query = (Session.query(SurveyTreeItem).filter(
SurveyTreeItem.session_id == self.session_id).filter(
SurveyTreeItem.depth == self.depth + 1))
if self.path:
query = query.filter(SurveyTreeItem.path.like(self.path + "%"))
if filter is not None:
query = query.filter(filter)
return query.order_by(SurveyTreeItem.path)
def siblings(self, klass=None, filter=None):
if not self.path:
return []
if klass is None:
klass = SurveyTreeItem
query = (Session.query(klass).filter(
klass.session_id == self.session_id).filter(
klass.parent_id == self.parent_id))
if filter is not None:
query = query.filter(sql.or_(klass.id == self.id, filter))
return query.order_by(klass.path)
def addChild(self, item):
sqlsession = Session()
query = (sqlsession.query(SurveyTreeItem.path).filter(
SurveyTreeItem.session_id == self.session_id).filter(
SurveyTreeItem.depth == self.depth + 1))
if self.path:
query = query.filter(SurveyTreeItem.path.like(self.path + "%"))
last = query.order_by(SurveyTreeItem.path.desc()).first()
if not last:
index = 1
else:
index = int(last[0][-3:]) + 1
item.session = self.session
item.depth = self.depth + 1
item.path = (self.path or "") + "%03d" % index
item.parent_id = self.id
if self.profile_index != -1:
item.profile_index = self.profile_index
sqlsession.add(item)
self.session.touch()
return item
def removeChildren(self, excluded=[]):
if self.id not in excluded:
excluded.append(self.id)
session = Session()
if self.path:
filter = sql.and_(
SurveyTreeItem.session_id == self.session_id,
SurveyTreeItem.path.like(self.path + "%"),
sql.not_(SurveyTreeItem.id.in_(excluded)),
)
else:
filter = sql.and_(
SurveyTreeItem.session_id == self.session_id,
sql.not_(SurveyTreeItem.id.in_(excluded)),
)
removed = session.query(SurveyTreeItem).filter(filter).all()
session.execute(SurveyTreeItem.__table__.delete().where(filter))
self.session.touch()
datamanager.mark_changed(session)
return removed
class Risk(SurveyTreeItem):
"""Answer to risk."""
__tablename__ = "risk"
__mapper_args__ = dict(polymorphic_identity="risk")
sql_risk_id = schema.Column(
"id",
types.Integer(),
schema.ForeignKey(SurveyTreeItem.id,
onupdate="CASCADE",
ondelete="CASCADE"),
primary_key=True,
)
risk_id = schema.Column(types.String(16), nullable=True)
risk_type = schema.Column(Enum(["risk", "policy", "top5"]),
default="risk",
nullable=False,
index=True)
#: Skip-evaluation flag. This is only used to indicate if the sector
#: set the evaluation method to `fixed`, not for policy behaviour
#: such as not evaluation top-5 risks. That policy behaviour is
#: handled via the question_filter on client views so it can be modified
#: in custom deployments.
skip_evaluation = schema.Column(types.Boolean(),
default=False,
nullable=False)
is_custom_risk = schema.Column(types.Boolean(),
default=False,
nullable=False)
identification = schema.Column(Enum([None, "yes", "no", "n/a"]))
frequency = schema.Column(types.Integer())
effect = schema.Column(types.Integer())
probability = schema.Column(types.Integer())
priority = schema.Column(Enum([None, "low", "medium", "high"]))
comment = schema.Column(types.UnicodeText())
existing_measures = schema.Column(types.UnicodeText())
training_notes = schema.Column(types.UnicodeText())
custom_description = schema.Column(types.UnicodeText())
image_data = schema.Column(types.LargeBinary())
image_data_scaled = schema.Column(types.LargeBinary())
image_filename = schema.Column(types.UnicodeText())
@memoize
def measures_of_type(self, plan_type):
query = (Session.query(ActionPlan).filter(
sql.and_(ActionPlan.risk_id == self.id),
ActionPlan.plan_type == plan_type,
).order_by(ActionPlan.id))
return query.all()
@property
def standard_measures(self):
return self.measures_of_type("measure_standard")
@property
def custom_measures(self):
return self.measures_of_type("measure_custom")
@property
def in_place_standard_measures(self):
return self.measures_of_type("in_place_standard")
@property
def in_place_custom_measures(self):
return self.measures_of_type("in_place_custom")
types.TIMESTAMP(timezone=True),
),
(
"VARCHAR",
types.VARCHAR(),
),
)
unquoted_types = (
(
"BINARY",
types.LargeBinary(),
),
(
"BOOLEAN",
types.Boolean(),
),
(
"DECIMAL",
types.DECIMAL(),
),
(
"FLOAT",
types.FLOAT(),
),
(
"INTEGER",
types.INTEGER(),
),
(
"BIGINT",
def test_should_boolean_convert_boolean():
assert_column_conversion(types.Boolean(), graphene.Boolean)
class PrestoEngineSpec(BaseEngineSpec):
engine = "presto"
engine_name = "Presto"
_time_grain_expressions = {
None:
"{col}",
"PT1S":
"date_trunc('second', CAST({col} AS TIMESTAMP))",
"PT1M":
"date_trunc('minute', CAST({col} AS TIMESTAMP))",
"PT1H":
"date_trunc('hour', CAST({col} AS TIMESTAMP))",
"P1D":
"date_trunc('day', CAST({col} AS TIMESTAMP))",
"P1W":
"date_trunc('week', CAST({col} AS TIMESTAMP))",
"P1M":
"date_trunc('month', CAST({col} AS TIMESTAMP))",
"P0.25Y":
"date_trunc('quarter', CAST({col} AS TIMESTAMP))",
"P1Y":
"date_trunc('year', CAST({col} AS TIMESTAMP))",
"P1W/1970-01-03T00:00:00Z":
"date_add('day', 5, date_trunc('week', "
"date_add('day', 1, CAST({col} AS TIMESTAMP))))",
"1969-12-28T00:00:00Z/P1W":
"date_add('day', -1, date_trunc('week', "
"date_add('day', 1, CAST({col} AS TIMESTAMP))))",
}
@classmethod
def get_allow_cost_estimate(cls, version: Optional[str] = None) -> bool:
return version is not None and StrictVersion(version) >= StrictVersion(
"0.319")
@classmethod
def get_table_names(cls, database: "Database", inspector: Inspector,
schema: Optional[str]) -> List[str]:
tables = super().get_table_names(database, inspector, schema)
if not is_feature_enabled("PRESTO_SPLIT_VIEWS_FROM_TABLES"):
return tables
views = set(cls.get_view_names(database, inspector, schema))
actual_tables = set(tables) - views
return list(actual_tables)
@classmethod
def get_view_names(cls, database: "Database", inspector: Inspector,
schema: Optional[str]) -> List[str]:
"""Returns an empty list
get_table_names() function returns all table names and view names,
and get_view_names() is not implemented in sqlalchemy_presto.py
https://github.com/dropbox/PyHive/blob/e25fc8440a0686bbb7a5db5de7cb1a77bdb4167a/pyhive/sqlalchemy_presto.py
"""
if not is_feature_enabled("PRESTO_SPLIT_VIEWS_FROM_TABLES"):
return []
if schema:
sql = ("SELECT table_name FROM information_schema.views "
"WHERE table_schema=%(schema)s")
params = {"schema": schema}
else:
sql = "SELECT table_name FROM information_schema.views"
params = {}
engine = cls.get_engine(database, schema=schema)
with closing(engine.raw_connection()) as conn:
with closing(conn.cursor()) as cursor:
cursor.execute(sql, params)
results = cursor.fetchall()
return [row[0] for row in results]
@classmethod
def _create_column_info(cls, name: str, data_type: str) -> Dict[str, Any]:
"""
Create column info object
:param name: column name
:param data_type: column data type
:return: column info object
"""
return {"name": name, "type": f"{data_type}"}
@classmethod
def _get_full_name(cls, names: List[Tuple[str, str]]) -> str:
"""
Get the full column name
:param names: list of all individual column names
:return: full column name
"""
return ".".join(column[0] for column in names if column[0])
@classmethod
def _has_nested_data_types(cls, component_type: str) -> bool:
"""
Check if string contains a data type. We determine if there is a data type by
whitespace or multiple data types by commas
:param component_type: data type
:return: boolean
"""
comma_regex = r",(?=(?:[^\"]*\"[^\"]*\")*[^\"]*$)"
white_space_regex = r"\s(?=(?:[^\"]*\"[^\"]*\")*[^\"]*$)"
return (re.search(comma_regex, component_type) is not None
or re.search(white_space_regex, component_type) is not None)
@classmethod
def _split_data_type(cls, data_type: str, delimiter: str) -> List[str]:
"""
Split data type based on given delimiter. Do not split the string if the
delimiter is enclosed in quotes
:param data_type: data type
:param delimiter: string separator (i.e. open parenthesis, closed parenthesis,
comma, whitespace)
:return: list of strings after breaking it by the delimiter
"""
return re.split(
r"{}(?=(?:[^\"]*\"[^\"]*\")*[^\"]*$)".format(delimiter), data_type)
@classmethod
def _parse_structural_column( # pylint: disable=too-many-locals,too-many-branches
cls,
parent_column_name: str,
parent_data_type: str,
result: List[Dict[str, Any]],
) -> None:
"""
Parse a row or array column
:param result: list tracking the results
"""
formatted_parent_column_name = parent_column_name
# Quote the column name if there is a space
if " " in parent_column_name:
formatted_parent_column_name = f'"{parent_column_name}"'
full_data_type = f"{formatted_parent_column_name} {parent_data_type}"
original_result_len = len(result)
# split on open parenthesis ( to get the structural
# data type and its component types
data_types = cls._split_data_type(full_data_type, r"\(")
stack: List[Tuple[str, str]] = []
for data_type in data_types:
# split on closed parenthesis ) to track which component
# types belong to what structural data type
inner_types = cls._split_data_type(data_type, r"\)")
for inner_type in inner_types:
# We have finished parsing multiple structural data types
if not inner_type and stack:
stack.pop()
elif cls._has_nested_data_types(inner_type):
# split on comma , to get individual data types
single_fields = cls._split_data_type(inner_type, ",")
for single_field in single_fields:
single_field = single_field.strip()
# If component type starts with a comma, the first single field
# will be an empty string. Disregard this empty string.
if not single_field:
continue
# split on whitespace to get field name and data type
field_info = cls._split_data_type(single_field, r"\s")
# check if there is a structural data type within
# overall structural data type
column_type = cls.get_sqla_column_type(field_info[1])
if column_type is None:
raise NotImplementedError(
_("Unknown column type: %(col)s",
col=field_info[1]))
if field_info[1] == "array" or field_info[1] == "row":
stack.append((field_info[0], field_info[1]))
full_parent_path = cls._get_full_name(stack)
result.append(
cls._create_column_info(
full_parent_path, column_type))
else: # otherwise this field is a basic data type
full_parent_path = cls._get_full_name(stack)
column_name = "{}.{}".format(
full_parent_path, field_info[0])
result.append(
cls._create_column_info(
column_name, column_type))
# If the component type ends with a structural data type, do not pop
# the stack. We have run across a structural data type within the
# overall structural data type. Otherwise, we have completely parsed
# through the entire structural data type and can move on.
if not (inner_type.endswith("array")
or inner_type.endswith("row")):
stack.pop()
# We have an array of row objects (i.e. array(row(...)))
elif inner_type in ("array", "row"):
# Push a dummy object to represent the structural data type
stack.append(("", inner_type))
# We have an array of a basic data types(i.e. array(varchar)).
elif stack:
# Because it is an array of a basic data type. We have finished
# parsing the structural data type and can move on.
stack.pop()
# Unquote the column name if necessary
if formatted_parent_column_name != parent_column_name:
for index in range(original_result_len, len(result)):
result[index]["name"] = result[index]["name"].replace(
formatted_parent_column_name, parent_column_name)
@classmethod
def _show_columns(cls, inspector: Inspector, table_name: str,
schema: Optional[str]) -> List[RowProxy]:
"""
Show presto column names
:param inspector: object that performs database schema inspection
:param table_name: table name
:param schema: schema name
:return: list of column objects
"""
quote = inspector.engine.dialect.identifier_preparer.quote_identifier
full_table = quote(table_name)
if schema:
full_table = "{}.{}".format(quote(schema), full_table)
columns = inspector.bind.execute(
"SHOW COLUMNS FROM {}".format(full_table))
return columns
column_type_mappings = (
(re.compile(r"^boolean.*", re.IGNORECASE), types.Boolean()),
(re.compile(r"^tinyint.*", re.IGNORECASE), TinyInteger()),
(re.compile(r"^smallint.*", re.IGNORECASE), types.SmallInteger()),
(re.compile(r"^integer.*", re.IGNORECASE), types.Integer()),
(re.compile(r"^bigint.*", re.IGNORECASE), types.BigInteger()),
(re.compile(r"^real.*", re.IGNORECASE), types.Float()),
(re.compile(r"^double.*", re.IGNORECASE), types.Float()),
(re.compile(r"^decimal.*", re.IGNORECASE), types.DECIMAL()),
(
re.compile(r"^varchar(\((\d+)\))*$", re.IGNORECASE),
lambda match: types.VARCHAR(int(match[2]))
if match[2] else types.String(),
),
(
re.compile(r"^char(\((\d+)\))*$", re.IGNORECASE),
lambda match: types.CHAR(int(match[2]))
if match[2] else types.CHAR(),
),
(re.compile(r"^varbinary.*", re.IGNORECASE), types.VARBINARY()),
(re.compile(r"^json.*", re.IGNORECASE), types.JSON()),
(re.compile(r"^date.*", re.IGNORECASE), types.DATE()),
(re.compile(r"^time.*", re.IGNORECASE), types.Time()),
(re.compile(r"^timestamp.*", re.IGNORECASE), types.TIMESTAMP()),
(re.compile(r"^interval.*", re.IGNORECASE), Interval()),
(re.compile(r"^array.*", re.IGNORECASE), Array()),
(re.compile(r"^map.*", re.IGNORECASE), Map()),
(re.compile(r"^row.*", re.IGNORECASE), Row()),
)
@classmethod
def get_columns(cls, inspector: Inspector, table_name: str,
schema: Optional[str]) -> List[Dict[str, Any]]:
"""
Get columns from a Presto data source. This includes handling row and
array data types
:param inspector: object that performs database schema inspection
:param table_name: table name
:param schema: schema name
:return: a list of results that contain column info
(i.e. column name and data type)
"""
columns = cls._show_columns(inspector, table_name, schema)
result: List[Dict[str, Any]] = []
for column in columns:
# parse column if it is a row or array
if is_feature_enabled("PRESTO_EXPAND_DATA") and (
"array" in column.Type or "row" in column.Type):
structural_column_index = len(result)
cls._parse_structural_column(column.Column, column.Type,
result)
result[structural_column_index]["nullable"] = getattr(
column, "Null", True)
result[structural_column_index]["default"] = None
continue
# otherwise column is a basic data type
column_type = cls.get_sqla_column_type(column.Type)
if column_type is None:
raise NotImplementedError(
_("Unknown column type: %(col)s", col=column_type))
column_info = cls._create_column_info(column.Column, column_type)
column_info["nullable"] = getattr(column, "Null", True)
column_info["default"] = None
result.append(column_info)
return result
@classmethod
def _is_column_name_quoted(cls, column_name: str) -> bool:
"""
Check if column name is in quotes
:param column_name: column name
:return: boolean
"""
return column_name.startswith('"') and column_name.endswith('"')
@classmethod
def _get_fields(cls, cols: List[Dict[str, Any]]) -> List[ColumnClause]:
"""
Format column clauses where names are in quotes and labels are specified
:param cols: columns
:return: column clauses
"""
column_clauses = []
# Column names are separated by periods. This regex will find periods in a
# string if they are not enclosed in quotes because if a period is enclosed in
# quotes, then that period is part of a column name.
dot_pattern = r"""\. # split on period
(?= # look ahead
(?: # create non-capture group
[^\"]*\"[^\"]*\" # two quotes
)*[^\"]*$) # end regex"""
dot_regex = re.compile(dot_pattern, re.VERBOSE)
for col in cols:
# get individual column names
col_names = re.split(dot_regex, col["name"])
# quote each column name if it is not already quoted
for index, col_name in enumerate(col_names):
if not cls._is_column_name_quoted(col_name):
col_names[index] = '"{}"'.format(col_name)
quoted_col_name = ".".join(
col_name if cls._is_column_name_quoted(col_name
) else f'"{col_name}"'
for col_name in col_names)
# create column clause in the format "name"."name" AS "name.name"
column_clause = literal_column(quoted_col_name).label(col["name"])
column_clauses.append(column_clause)
return column_clauses
@classmethod
def select_star( # pylint: disable=too-many-arguments
cls,
database: "Database",
table_name: str,
engine: Engine,
schema: Optional[str] = None,
limit: int = 100,
show_cols: bool = False,
indent: bool = True,
latest_partition: bool = True,
cols: Optional[List[Dict[str, Any]]] = None,
) -> str:
"""
Include selecting properties of row objects. We cannot easily break arrays into
rows, so render the whole array in its own row and skip columns that correspond
to an array's contents.
"""
cols = cols or []
presto_cols = cols
if is_feature_enabled("PRESTO_EXPAND_DATA") and show_cols:
dot_regex = r"\.(?=(?:[^\"]*\"[^\"]*\")*[^\"]*$)"
presto_cols = [
col for col in presto_cols
if not re.search(dot_regex, col["name"])
]
return super().select_star(
database,
table_name,
engine,
schema,
limit,
show_cols,
indent,
latest_partition,
presto_cols,
)
@classmethod
def estimate_statement_cost( # pylint: disable=too-many-locals
cls, statement: str, database: "Database", cursor: Any,
user_name: str) -> Dict[str, Any]:
"""
Run a SQL query that estimates the cost of a given statement.
:param statement: A single SQL statement
:param database: Database instance
:param cursor: Cursor instance
:param username: Effective username
:return: JSON response from Presto
"""
parsed_query = ParsedQuery(statement)
sql = parsed_query.stripped()
sql_query_mutator = config["SQL_QUERY_MUTATOR"]
if sql_query_mutator:
sql = sql_query_mutator(sql, user_name, security_manager, database)
sql = f"EXPLAIN (TYPE IO, FORMAT JSON) {sql}"
cursor.execute(sql)
# the output from Presto is a single column and a single row containing
# JSON:
#
# {
# ...
# "estimate" : {
# "outputRowCount" : 8.73265878E8,
# "outputSizeInBytes" : 3.41425774958E11,
# "cpuCost" : 3.41425774958E11,
# "maxMemory" : 0.0,
# "networkCost" : 3.41425774958E11
# }
# }
result = json.loads(cursor.fetchone()[0])
return result
@classmethod
def query_cost_formatter(
cls, raw_cost: List[Dict[str, Any]]) -> List[Dict[str, str]]:
"""
Format cost estimate.
:param raw_cost: JSON estimate from Presto
:return: Human readable cost estimate
"""
def humanize(value: Any, suffix: str) -> str:
try:
value = int(value)
except ValueError:
return str(value)
prefixes = ["K", "M", "G", "T", "P", "E", "Z", "Y"]
prefix = ""
to_next_prefix = 1000
while value > to_next_prefix and prefixes:
prefix = prefixes.pop(0)
value //= to_next_prefix
return f"{value} {prefix}{suffix}"
cost = []
columns = [
("outputRowCount", "Output count", " rows"),
("outputSizeInBytes", "Output size", "B"),
("cpuCost", "CPU cost", ""),
("maxMemory", "Max memory", "B"),
("networkCost", "Network cost", ""),
]
for row in raw_cost:
estimate: Dict[str, float] = row.get("estimate", {})
statement_cost = {}
for key, label, suffix in columns:
if key in estimate:
statement_cost[label] = humanize(estimate[key],
suffix).strip()
cost.append(statement_cost)
return cost
@classmethod
def adjust_database_uri(cls,
uri: URL,
selected_schema: Optional[str] = None) -> None:
database = uri.database
if selected_schema and database:
selected_schema = parse.quote(selected_schema, safe="")
if "/" in database:
database = database.split("/")[0] + "/" + selected_schema
else:
database += "/" + selected_schema
uri.database = database
@classmethod
def convert_dttm(cls, target_type: str, dttm: datetime) -> Optional[str]:
tt = target_type.upper()
if tt == utils.TemporalType.DATE:
return f"""from_iso8601_date('{dttm.date().isoformat()}')"""
if tt == utils.TemporalType.TIMESTAMP:
return f"""from_iso8601_timestamp('{dttm.isoformat(timespec="microseconds")}')""" # pylint: disable=line-too-long
return None
@classmethod
def epoch_to_dttm(cls) -> str:
return "from_unixtime({col})"
@classmethod
def get_all_datasource_names(
cls, database: "Database",
datasource_type: str) -> List[utils.DatasourceName]:
datasource_df = database.get_df(
"SELECT table_schema, table_name FROM INFORMATION_SCHEMA.{}S "
"ORDER BY concat(table_schema, '.', table_name)".format(
datasource_type.upper()),
None,
)
datasource_names: List[utils.DatasourceName] = []
for _unused, row in datasource_df.iterrows():
datasource_names.append(
utils.DatasourceName(schema=row["table_schema"],
table=row["table_name"]))
return datasource_names
@classmethod
def expand_data( # pylint: disable=too-many-locals,too-many-branches
cls, columns: List[Dict[Any, Any]],
data: List[Dict[Any, Any]]) -> Tuple[List[Dict[Any, Any]], List[Dict[
Any, Any]], List[Dict[Any, Any]]]:
"""
We do not immediately display rows and arrays clearly in the data grid. This
method separates out nested fields and data values to help clearly display
structural columns.
Example: ColumnA is a row(nested_obj varchar) and ColumnB is an array(int)
Original data set = [
{'ColumnA': ['a1'], 'ColumnB': [1, 2]},
{'ColumnA': ['a2'], 'ColumnB': [3, 4]},
]
Expanded data set = [
{'ColumnA': ['a1'], 'ColumnA.nested_obj': 'a1', 'ColumnB': 1},
{'ColumnA': '', 'ColumnA.nested_obj': '', 'ColumnB': 2},
{'ColumnA': ['a2'], 'ColumnA.nested_obj': 'a2', 'ColumnB': 3},
{'ColumnA': '', 'ColumnA.nested_obj': '', 'ColumnB': 4},
]
:param columns: columns selected in the query
:param data: original data set
:return: list of all columns(selected columns and their nested fields),
expanded data set, listed of nested fields
"""
if not is_feature_enabled("PRESTO_EXPAND_DATA"):
return columns, data, []
# process each column, unnesting ARRAY types and
# expanding ROW types into new columns
to_process = deque((column, 0) for column in columns)
all_columns: List[Dict[str, Any]] = []
expanded_columns = []
current_array_level = None
while to_process:
column, level = to_process.popleft()
if column["name"] not in [
column["name"] for column in all_columns
]:
all_columns.append(column)
# When unnesting arrays we need to keep track of how many extra rows
# were added, for each original row. This is necessary when we expand
# multiple arrays, so that the arrays after the first reuse the rows
# added by the first. every time we change a level in the nested arrays
# we reinitialize this.
if level != current_array_level:
unnested_rows: Dict[int, int] = defaultdict(int)
current_array_level = level
name = column["name"]
values: Optional[Union[str, List[Any]]]
if column["type"].startswith("ARRAY("):
# keep processing array children; we append to the right so that
# multiple nested arrays are processed breadth-first
to_process.append((get_children(column)[0], level + 1))
# unnest array objects data into new rows
i = 0
while i < len(data):
row = data[i]
values = row.get(name)
if isinstance(values, str):
row[name] = values = destringify(values)
if values:
# how many extra rows we need to unnest the data?
extra_rows = len(values) - 1
# how many rows were already added for this row?
current_unnested_rows = unnested_rows[i]
# add any necessary rows
missing = extra_rows - current_unnested_rows
for _ in range(missing):
data.insert(i + current_unnested_rows + 1, {})
unnested_rows[i] += 1
# unnest array into rows
for j, value in enumerate(values):
data[i + j][name] = value
# skip newly unnested rows
i += unnested_rows[i]
i += 1
if column["type"].startswith("ROW("):
# expand columns; we append them to the left so they are added
# immediately after the parent
expanded = get_children(column)
to_process.extendleft(
(column, level) for column in expanded[::-1])
expanded_columns.extend(expanded)
# expand row objects into new columns
for row in data:
values = row.get(name) or []
if isinstance(values, str):
row[name] = values = cast(List[Any],
destringify(values))
for value, col in zip(values, expanded):
row[col["name"]] = value
data = [{k["name"]: row.get(k["name"], "")
for k in all_columns} for row in data]
return all_columns, data, expanded_columns
@classmethod
def extra_table_metadata(cls, database: "Database", table_name: str,
schema_name: str) -> Dict[str, Any]:
metadata = {}
indexes = database.get_indexes(table_name, schema_name)
if indexes:
cols = indexes[0].get("column_names", [])
full_table_name = table_name
if schema_name and "." not in table_name:
full_table_name = "{}.{}".format(schema_name, table_name)
pql = cls._partition_query(full_table_name, database)
col_names, latest_parts = cls.latest_partition(table_name,
schema_name,
database,
show_first=True)
if not latest_parts:
latest_parts = tuple([None] * len(col_names)) # type: ignore
metadata["partitions"] = {
"cols": cols,
"latest": dict(zip(col_names, latest_parts)), # type: ignore
"partitionQuery": pql,
}
# flake8 is not matching `Optional[str]` to `Any` for some reason...
metadata["view"] = cast(
Any, cls.get_create_view(database, schema_name, table_name))
return metadata
@classmethod
def get_create_view(cls, database: "Database", schema: str,
table: str) -> Optional[str]:
"""
Return a CREATE VIEW statement, or `None` if not a view.
:param database: Database instance
:param schema: Schema name
:param table: Table (view) name
"""
from pyhive.exc import DatabaseError
engine = cls.get_engine(database, schema)
with closing(engine.raw_connection()) as conn:
with closing(conn.cursor()) as cursor:
sql = f"SHOW CREATE VIEW {schema}.{table}"
try:
cls.execute(cursor, sql)
polled = cursor.poll()
while polled:
time.sleep(0.2)
polled = cursor.poll()
except DatabaseError: # not a VIEW
return None
rows = cls.fetch_data(cursor, 1)
return rows[0][0]
@classmethod
def handle_cursor(cls, cursor: Any, query: Query,
session: Session) -> None:
"""Updates progress information"""
query_id = query.id
poll_interval = query.database.connect_args.get(
"poll_interval", config["PRESTO_POLL_INTERVAL"])
logger.info("Query %i: Polling the cursor for progress", query_id)
polled = cursor.poll()
# poll returns dict -- JSON status information or ``None``
# if the query is done
# https://github.com/dropbox/PyHive/blob/
# b34bdbf51378b3979eaf5eca9e956f06ddc36ca0/pyhive/presto.py#L178
while polled:
# Update the object and wait for the kill signal.
stats = polled.get("stats", {})
query = session.query(type(query)).filter_by(id=query_id).one()
if query.status in [QueryStatus.STOPPED, QueryStatus.TIMED_OUT]:
cursor.cancel()
break
if stats:
state = stats.get("state")
# if already finished, then stop polling
if state == "FINISHED":
break
completed_splits = float(stats.get("completedSplits"))
total_splits = float(stats.get("totalSplits"))
if total_splits and completed_splits:
progress = 100 * (completed_splits / total_splits)
logger.info("Query {} progress: {} / {} " # pylint: disable=logging-format-interpolation
"splits".format(query_id, completed_splits,
total_splits))
if progress > query.progress:
query.progress = progress
session.commit()
time.sleep(poll_interval)
logger.info("Query %i: Polling the cursor for progress", query_id)
polled = cursor.poll()
@classmethod
def _extract_error_message(cls, ex: Exception) -> str:
if (hasattr(ex, "orig")
and type(ex.orig).__name__ == "DatabaseError" # type: ignore
and isinstance(ex.orig[0], dict) # type: ignore
):
error_dict = ex.orig[0] # type: ignore
return "{} at {}: {}".format(
error_dict.get("errorName"),
error_dict.get("errorLocation"),
error_dict.get("message"),
)
if type(ex).__name__ == "DatabaseError" and hasattr(
ex, "args") and ex.args:
error_dict = ex.args[0]
return error_dict.get("message", _("Unknown Presto Error"))
return utils.error_msg_from_exception(ex)
@classmethod
def _partition_query( # pylint: disable=too-many-arguments,too-many-locals
cls,
table_name: str,
database: "Database",
limit: int = 0,
order_by: Optional[List[Tuple[str, bool]]] = None,
filters: Optional[Dict[Any, Any]] = None,
) -> str:
"""Returns a partition query
:param table_name: the name of the table to get partitions from
:type table_name: str
:param limit: the number of partitions to be returned
:type limit: int
:param order_by: a list of tuples of field name and a boolean
that determines if that field should be sorted in descending
order
:type order_by: list of (str, bool) tuples
:param filters: dict of field name and filter value combinations
"""
limit_clause = "LIMIT {}".format(limit) if limit else ""
order_by_clause = ""
if order_by:
l = []
for field, desc in order_by:
l.append(field + " DESC" if desc else "")
order_by_clause = "ORDER BY " + ", ".join(l)
where_clause = ""
if filters:
l = []
for field, value in filters.items():
l.append(f"{field} = '{value}'")
where_clause = "WHERE " + " AND ".join(l)
presto_version = database.get_extra().get("version")
# Partition select syntax changed in v0.199, so check here.
# Default to the new syntax if version is unset.
partition_select_clause = (
f'SELECT * FROM "{table_name}$partitions"' if not presto_version
or StrictVersion(presto_version) >= StrictVersion("0.199") else
f"SHOW PARTITIONS FROM {table_name}")
sql = textwrap.dedent(f"""\
{partition_select_clause}
{where_clause}
{order_by_clause}
{limit_clause}
""")
return sql
@classmethod
def where_latest_partition( # pylint: disable=too-many-arguments
cls,
table_name: str,
schema: Optional[str],
database: "Database",
query: Select,
columns: Optional[List[Dict[str, str]]] = None,
) -> Optional[Select]:
try:
col_names, values = cls.latest_partition(table_name,
schema,
database,
show_first=True)
except Exception: # pylint: disable=broad-except
# table is not partitioned
return None
if values is None:
return None
column_names = {column.get("name") for column in columns or []}
for col_name, value in zip(col_names, values):
if col_name in column_names:
query = query.where(Column(col_name) == value)
return query
@classmethod
def _latest_partition_from_df(cls,
df: pd.DataFrame) -> Optional[List[str]]:
if not df.empty:
return df.to_records(index=False)[0].item()
return None
@classmethod
def latest_partition(
cls,
table_name: str,
schema: Optional[str],
database: "Database",
show_first: bool = False,
) -> Tuple[List[str], Optional[List[str]]]:
"""Returns col name and the latest (max) partition value for a table
:param table_name: the name of the table
:param schema: schema / database / namespace
:param database: database query will be run against
:type database: models.Database
:param show_first: displays the value for the first partitioning key
if there are many partitioning keys
:type show_first: bool
>>> latest_partition('foo_table')
(['ds'], ('2018-01-01',))
"""
indexes = database.get_indexes(table_name, schema)
if not indexes:
raise SupersetTemplateException(
f"Error getting partition for {schema}.{table_name}. "
"Verify that this table has a partition.")
if len(indexes[0]["column_names"]) < 1:
raise SupersetTemplateException(
"The table should have one partitioned field")
if not show_first and len(indexes[0]["column_names"]) > 1:
raise SupersetTemplateException(
"The table should have a single partitioned field "
"to use this function. You may want to use "
"`presto.latest_sub_partition`")
column_names = indexes[0]["column_names"]
part_fields = [(column_name, True) for column_name in column_names]
sql = cls._partition_query(table_name, database, 1, part_fields)
df = database.get_df(sql, schema)
return column_names, cls._latest_partition_from_df(df)
@classmethod
def latest_sub_partition(cls, table_name: str, schema: Optional[str],
database: "Database", **kwargs: Any) -> Any:
"""Returns the latest (max) partition value for a table
A filtering criteria should be passed for all fields that are
partitioned except for the field to be returned. For example,
if a table is partitioned by (``ds``, ``event_type`` and
``event_category``) and you want the latest ``ds``, you'll want
to provide a filter as keyword arguments for both
``event_type`` and ``event_category`` as in
``latest_sub_partition('my_table',
event_category='page', event_type='click')``
:param table_name: the name of the table, can be just the table
name or a fully qualified table name as ``schema_name.table_name``
:type table_name: str
:param schema: schema / database / namespace
:type schema: str
:param database: database query will be run against
:type database: models.Database
:param kwargs: keyword arguments define the filtering criteria
on the partition list. There can be many of these.
:type kwargs: str
>>> latest_sub_partition('sub_partition_table', event_type='click')
'2018-01-01'
"""
indexes = database.get_indexes(table_name, schema)
part_fields = indexes[0]["column_names"]
for k in kwargs.keys(): # pylint: disable=consider-iterating-dictionary
if k not in k in part_fields: # pylint: disable=comparison-with-itself
msg = "Field [{k}] is not part of the portioning key"
raise SupersetTemplateException(msg)
if len(kwargs.keys()) != len(part_fields) - 1:
msg = ("A filter needs to be specified for {} out of the "
"{} fields.").format(
len(part_fields) - 1, len(part_fields))
raise SupersetTemplateException(msg)
for field in part_fields:
if field not in kwargs.keys():
field_to_return = field
sql = cls._partition_query(table_name, database, 1,
[(field_to_return, True)], kwargs)
df = database.get_df(sql, schema)
if df.empty:
return ""
return df.to_dict()[field_to_return][0]
@classmethod
@cache.memoize()
def get_function_names(cls, database: "Database") -> List[str]:
"""
Get a list of function names that are able to be called on the database.
Used for SQL Lab autocomplete.
:param database: The database to get functions for
:return: A list of function names useable in the database
"""
return database.get_df("SHOW FUNCTIONS")["Function"].tolist()
},
{
'name': 'string',
'type': types.String(),
'nullable': True,
'default': None
},
{
'name': 'float',
'type': types.Float(),
'nullable': True,
'default': None
},
{
'name': 'boolean',
'type': types.Boolean(),
'nullable': True,
'default': None
},
{
'name': 'date',
'type': types.DATE(),
'nullable': True,
'default': None
},
{
'name': 'datetime',
'type': types.DATETIME(),
'nullable': True,
'default': None
},
40.76727216,
decimal.Decimal("40.76727216"),
False,
datetime.date(2013, 10, 10),
datetime.datetime(2013, 10, 10, 11, 27, 16),
datetime.time(11, 27, 16),
"test_bytes",
]
SAMPLE_COLUMNS = [
{"name": "integer", "type": types.Integer(), "nullable": True, "default": None},
{"name": "timestamp", "type": types.TIMESTAMP(), "nullable": True, "default": None},
{"name": "string", "type": types.String(), "nullable": True, "default": None},
{"name": "float", "type": types.Float(), "nullable": True, "default": None},
{"name": "numeric", "type": types.Numeric(), "nullable": True, "default": None},
{"name": "boolean", "type": types.Boolean(), "nullable": True, "default": None},
{"name": "date", "type": types.DATE(), "nullable": True, "default": None},
{"name": "datetime", "type": types.DATETIME(), "nullable": True, "default": None},
{"name": "time", "type": types.TIME(), "nullable": True, "default": None},
{"name": "bytes", "type": types.BINARY(), "nullable": True, "default": None},
{
"name": "record",
"type": types.JSON(),
"nullable": True,
"default": None,
"comment": "In Standard SQL this data type is a STRUCT<name STRING, age INT64>.",
},
{"name": "record.name", "type": types.String(), "nullable": True, "default": None},
{"name": "record.age", "type": types.Integer(), "nullable": True, "default": None},
{"name": "nested_record", "type": types.JSON(), "nullable": True, "default": None},
{
metadata = schema.MetaData()
openid_redirects_table = schema.Table(
'openid_redirects', metadata,
schema.Column('token', types.Unicode(255), primary_key=True),
schema.Column('url', types.Text(), default=u''),
schema.Column('site', types.Text(), default=u''),
schema.Column('handle', types.Text(), default=u''))
openid_handles_table = schema.Table(
'openid_handles', metadata,
schema.Column('handler', types.Unicode(255), primary_key=True),
schema.Column('secret', types.Text(), default=u''),
schema.Column('assoc_type', types.Text(), default=u''),
schema.Column('private', types.Boolean(), default=False))
openid_sites_table = schema.Table(
'openid_sites', metadata,
schema.Column('id',
types.Integer,
schema.Sequence('openid_sites_seq_id', optional=True),
primary_key=True), schema.Column('handle',
types.Unicode(255)),
schema.Column('site', types.Text(), default=u''))
openid_user_table = schema.Table(
'openid_user', metadata,
schema.Column('user', types.Unicode(255), primary_key=True),
schema.Column('token', types.Text(), default=u''),
schema.Column('expire', types.Integer, default=0, index=True))
def __init__(self, left, right, operator=operators.eq):
self.type = sqltypes.Boolean()
self.left = expression._literal_as_binds(left)
self.right = right
self.operator = operator
class Allocation(TimestampMixin, ORMBase, OtherModels):
"""Describes a timespan within which one or many timeslots can be
reserved.
There's an important concept to understand before working with allocations.
The resource uuid of an alloction is not always pointing to the actual
resource.
A resource may in fact be a real resource, or an imaginary resource with
a uuid derived from the real resource. This is a somewhat historical
artifact.
If you need to know which allocations belong to a real resource, the
mirror_of field is what's relevant. The originally created allocation
with the real_resource is also called the master-allocation and it is
the one allocation with mirror_of and resource being equal.
When in doubt look at the managed_* functions of seantis.reservation.db's
Scheduler class.
"""
__tablename__ = 'allocations'
id = Column(types.Integer(), primary_key=True, autoincrement=True)
resource = Column(customtypes.GUID(), nullable=False)
mirror_of = Column(customtypes.GUID(), nullable=False)
group = Column(customtypes.GUID(), nullable=False)
quota = Column(types.Integer(), default=1)
partly_available = Column(types.Boolean(), default=False)
approve_manually = Column(types.Boolean(), default=False)
reservation_quota_limit = Column(
types.Integer(), default=0, nullable=False
)
# The dates are stored without any timzone information (unaware).
# Therefore the times are implicitly stored in the timezone the resource
# resides in.
# This is fine and dandy as long as all resources are in the same timezone.
# If they are not problems arise. So in the future the resource should
# carry a timezone property which is applied to the dates which will then
# be stored in UTC
# => TODO
_start = Column(types.DateTime(), nullable=False)
_end = Column(types.DateTime(), nullable=False)
_raster = Column(types.Integer(), nullable=False)
recurrence_id = Column(types.Integer(),
ForeignKey('recurrences.id',
onupdate='cascade',
ondelete='cascade'))
recurrence = relation('Recurrence', lazy='joined')
__table_args__ = (
Index('mirror_resource_ix', 'mirror_of', 'resource'),
UniqueConstraint('resource', '_start', name='resource_start_ix')
)
def copy(self):
allocation = Allocation()
allocation.resource = self.resource
allocation.mirror_of = self.mirror_of
allocation.group = self.group
allocation.quota = self.quota
allocation.partly_available = self.partly_available
allocation.approve_manually = self.approve_manually
allocation._start = self._start
allocation._end = self._end
allocation._raster = self._raster
allocation.recurrence_id = self.recurrence_id
return allocation
def get_start(self):
return self._start
def set_start(self, start):
self._start = rasterize_start(start, self.raster)
start = property(get_start, set_start)
def get_end(self):
return self._end
def set_end(self, end):
self._end = rasterize_end(end, self.raster)
end = property(get_end, set_end)
def get_raster(self):
return self._raster
def set_raster(self, raster):
# the raster can only be set once!
assert(not self._raster)
self._raster = raster
raster = property(get_raster, set_raster)
@property
def display_start(self):
"""Does nothing but to form a nice pair to display_end."""
return self.start
@property
def display_end(self):
"""Returns the end plus one microsecond (nicer display)."""
return self.end + timedelta(microseconds=1)
@property
def whole_day(self):
"""True if the allocation is a whole-day allocation.
A whole-day allocation is not really special. It's just an allocation
which starts at 0:00 and ends at 24:00 (or 23:59:59'999).
As such it can actually also span multiple days, only hours and minutes
count.
The use of this is to display allocations spanning days differently.
"""
s, e = self.display_start, self.display_end
assert s != e # this can never be, except when caused by cosmic rays
return utils.whole_day(s, e)
def overlaps(self, start, end):
""" Returns true if the current timespan overlaps with the given
start and end date.
"""
start, end = rasterize_span(start, end, self.raster)
return utils.overlaps(start, end, self.start, self.end)
def contains(self, start, end):
""" Returns true if the current timespan contains the given start
and end date.
"""
start, end = rasterize_span(start, end, self.raster)
return self.start <= start and end <= self.end
def free_slots(self, start=None, end=None):
""" Returns the slots which are not yet reserved."""
reserved = [slot.start for slot in self.reserved_slots]
slots = []
for start, end in self.all_slots(start, end):
if not start in reserved:
slots.append((start, end))
return slots
def align_dates(self, start=None, end=None):
""" Aligns the given dates to the start and end date of the
allocation.
"""
start = start or self.start
start = start < self.start and self.start or start
end = end or self.end
end = end > self.end and self.end or end
return start, end
def all_slots(self, start=None, end=None):
""" Returns the slots which exist with this timespan. Reserved or free.
"""
start, end = self.align_dates(start, end)
if self.partly_available:
for start, end in iterate_span(start, end, self.raster):
yield start, end
else:
yield self.start, self.end
def is_available(self, start=None, end=None):
""" Returns true if the given daterange is completely available. """
if not (start and end):
start, end = self.start, self.end
assert(self.overlaps(start, end))
if self.is_blocked(start, end):
return False
reserved = [slot.start for slot in self.reserved_slots]
for start, end in self.all_slots(start, end):
if start in reserved:
return False
return True
def is_blocked(self, start=None, end=None):
if not (start and end):
start, end = self.start, self.end
else:
start, end = utils.as_machine_date(start, end)
BlockedPeriod = self.models.BlockedPeriod
query = self._query_blocked_periods()
query = query.filter(BlockedPeriod.start <= end)
query = query.filter(BlockedPeriod.end >= start)
return query.first() is not None
def _query_blocked_periods(self):
query = Session.query(self.models.BlockedPeriod)
query = query.filter_by(resource=self.resource)
return query
@property
def pending_reservations(self):
""" Returns the pending reservations query for this allocation.
As the pending reservations target the group and not a specific
allocation this function returns the same value for masters and
mirrors.
"""
Reservation = self.models.Reservation
query = Session.query(Reservation.id)
query = query.filter(Reservation.target == self.group)
query = query.filter(Reservation.status == u'pending')
return query
@property
def waitinglist_length(self):
return self.pending_reservations.count()
@property
def availability(self):
"""Returns the availability in percent."""
if self.partly_available:
total = sum(1 for s in self.all_slots())
else:
total = 1
count = len(self.reserved_slots)
for blocked_period in self._query_blocked_periods():
count += len(list(iterate_span(blocked_period.start,
blocked_period.end,
self.raster)))
if total == count:
return 0.0
if count == 0:
return 100.0
return 100.0 - (float(count) / float(total) * 100.0)
@property
def in_group(self):
"""True if the event is in any group."""
query = Session.query(Allocation.id)
query = query.filter(Allocation.resource == self.resource)
query = query.filter(Allocation.group == self.group)
query = query.limit(2)
return len(query.all()) > 1
@property
def in_recurrence(self):
"""True if the event is attached to a recurrence."""
return self.recurrence_id is not None
@property
def is_separate(self):
"""True if available separately (as opposed to available only as
part of a group)."""
if self.partly_available:
return True
if self.in_group:
return False
return True
def availability_partitions(self, scheduler):
"""Partitions the space between start and end into blocks of either
free, blocked or reserved time. Each block has a percentage
representing the space the block occupies compared to the size of the
whole allocation.
The blocks are ordered from start to end. Each block is an item with
two values. The first being the percentage, the second being the type.
The type can be one of None, 'reserved' or 'blocked'.
So given an allocation that goes from 8 to 9 and a reservation that
goes from 8:15 until 8:30 and a block that goes from 8:30 to 9:00
we get the following blocks:
[
(25%, None),
(25%, 'reserved'),
(50%, 'blocked')
]
This is useful to divide an allocation block into different divs on the
frontend, indicating to the user which parts of an allocation are
available for reservation.
Makes sure to only display slots that are within it's resources
first_hour/last_hour timespan.
"""
resource = get_resource_by_uuid(scheduler.uuid).getObject()
min_start_resource = datetime.combine(self.start,
time(resource.first_hour))
max_end_resource = datetime.combine(self.end,
time(resource.last_hour))
display_start = max(min_start_resource, self.start)
display_end = min(max_end_resource, self.end)
reserved = dict((r.start, r) for r in self.reserved_slots if
r.start >= display_start and r.end <= display_end)
blocked = set()
for blocked_period in self._query_blocked_periods():
blocked.update(start for start, end in
iterate_span(max(blocked_period.start,
display_start),
min(blocked_period.end,
display_end),
self.raster))
if not (reserved or blocked):
return [(100.0, None)]
# Get the percentage one slot represents
slots = list(self.all_slots(display_start, display_end))
step = 100.0 / float(len(slots))
# Create an entry for each slot with either True or False
pieces = []
for slot in slots:
piece = None
if slot[0] in reserved:
reserved_slot = reserved[slot[0]]
token = reserved_slot.reservation_token
reservation = scheduler.reservation_by_token(token).one()
piece = ('reserved', reservation.description, reservation.id)
elif slot[0] in blocked:
piece = ('blocked', None)
pieces.append(piece)
# Group by the None/'reserved'/'blocked' values in the pieces and sum
# up the percentage
partitions = []
for flag, group in groupby(pieces, key=lambda p: p):
percentage = len(list(group)) * step
partitions.append([percentage, flag])
# Make sure to get rid of floating point rounding errors
total = sum([p[0] for p in partitions])
diff = 100.0 - total
partitions[-1:][0][0] -= diff
return partitions
@property
def is_transient(self):
"""True if the allocation does not exist in the database, and is not
about to be written to the database. If an allocation is transient it
means that the given instance only exists in memory.
See:
http://www.sqlalchemy.org/docs/orm/session.html
#quickie-intro-to-object-states
http://stackoverflow.com/questions/3885601/
sqlalchemy-get-object-instance-state
"""
return object_session(self) is None and not has_identity(self)
@property
def is_master(self):
"""True if the allocation is a master allocation."""
return self.resource == self.mirror_of
def siblings(self, imaginary=True):
"""Returns the master/mirrors group this allocation is part of.
If 'imaginary' is true, inexistant mirrors are created on the fly.
those mirrors are transient (see self.is_transient)
"""
# this function should always have itself in the result
if not imaginary and self.is_transient:
assert False, \
'the resulting list would not contain this allocation'
if self.quota == 1:
assert(self.is_master)
return [self]
query = Session.query(Allocation)
query = query.filter(Allocation.mirror_of == self.mirror_of)
query = query.filter(Allocation._start == self._start)
existing = dict(((e.resource, e) for e in query))
master = self.is_master and self or existing[self.mirror_of]
existing[master.resource] = master
uuids = utils.generate_uuids(master.resource, master.quota)
imaginary = imaginary and (master.quota - len(existing)) or 0
siblings = [master]
for uuid in uuids:
if uuid in existing:
siblings.append(existing[uuid])
elif imaginary > 0:
allocation = master.copy()
allocation.resource = uuid
siblings.append(allocation)
imaginary -= 1
return siblings
class BQDialect(default.DefaultDialect):
colspecs = {
types.Unicode: BQString,
types.Integer: BQInteger,
types.SmallInteger: BQInteger,
types.Numeric: BQFloat,
types.Float: BQFloat,
types.DateTime: BQTimestamp,
types.Date: BQTimestamp,
types.String: BQString,
types.LargeBinary: BQBytes,
types.Boolean: BQBoolean,
types.Text: BQString,
types.CHAR: BQString,
types.TIMESTAMP: BQTimestamp,
types.VARCHAR: BQString
}
__TYPE_MAPPINGS = {
'TIMESTAMP': types.DateTime(),
'STRING': types.String(),
'FLOAT': types.Float(),
'INTEGER': types.Integer(),
'BOOLEAN': types.Boolean()
}
name = 'bigquery'
driver = 'bq1'
poolclass = pool.SingletonThreadPool
statement_compiler = BQSQLCompiler
ddl_compiler = BQDDLCompiler
preparer = BQIdentifierPreparer
execution_ctx_cls = BQExecutionContext
supports_alter = False
supports_unicode_statements = True
supports_sane_multi_rowcount = False
supports_sane_rowcount = False
supports_sequences = False
supports_native_enum = False
positional = False
paramstyle = 'named'
default_sequence_base = 0
default_schema_name = None
# - - - - - - - - - - - - - - - - - - - - - - - - - -
def __init__(self, **kw):
#
# Create a dialect object
#
super(BQDialect, self).__init__(**kw)
# - - - - - - - - - - - - - - - - - - - - - - - - - -
def create_connect_args(self, url):
#
# This function recovers connection parameters from the connection string
#
return [], {}
# - - - - - - - - - - - - - - - - - - - - - - - - - -
def initialize(self, connection):
"""disable all dialect initialization"""
# - - - - - - - - - - - - - - - - - - - - - - - - - -
@classmethod
def dbapi(cls):
return dbapi
# - - - - - - - - - - - - - - - - - - - - - - - - - -
def do_execute(self, cursor, statement, parameters, context=None):
cursor.execute(statement, parameters)
# - - - - - - - - - - - - - - - - - - - - - - - - - -
def do_executemany(self, cursor, statement, parameters, context=None):
cursor.executemany(statement, parameters)
# - - - - - - - - - - - - - - - - - - - - - - - - - -
def get_schema_names(self, engine, **kw):
return engine.connect().connection.get_schema_names()
# - - - - - - - - - - - - - - - - - - - - - - - - - -
def get_view_names(self, connection, schema=None, **kw):
raise NotImplementedError()
# - - - - - - - - - - - - - - - - - - - - - - - - - -
def get_view_definition(self, connection, viewname, schema=None, **kw):
raise NotImplementedError()
# - - - - - - - - - - - - - - - - - - - - - - - - - -
def has_table(self, connection, table_name, schema=None):
return table_name in connection.connection.get_table_names()
# - - - - - - - - - - - - - - - - - - - - - - - - - -
@reflection.cache
def get_table_names(self, engine, schema=None, **kw):
return engine.connect().connection.get_table_names()
# - - - - - - - - - - - - - - - - - - - - - - - - - -
def get_columns(self, engine, table_name, schema=None, **kw):
cols = engine.connect().connection.get_columns(table_name)
get_coldef = lambda x, y: {
"name": x,
"type": BQDialect.__TYPE_MAPPINGS.get(y, types.Binary()),
"nullable": True,
"default": None
}
return [get_coldef(*col) for col in cols]
# - - - - - - - - - - - - - - - - - - - - - - - - - -
def get_primary_keys(self, engine, table_name, schema=None, **kw):
return []
# - - - - - - - - - - - - - - - - - - - - - - - - - -
def get_foreign_keys(self, engine, table_name, schema=None, **kw):
return []
# - - - - - - - - - - - - - - - - - - - - - - - - - -
def get_indexes(self, connection, table_name, schema=None, **kw):
return []