def handle_single_value(v): # backward compatibility with previous <select> components if isinstance(v, str): v = v.strip("\t\n'\"") if target_column_is_numeric: # For backwards compatibility and edge cases # where a column data type might have changed v = utils.string_to_num(v) if v == "<NULL>": return None elif v == "<empty string>": return "" return v
def handle_single_value(v): # backward compatibility with previous <select> components if isinstance(v, basestring): v = v.strip('\t\n \'"') if target_column_is_numeric: # For backwards compatibility and edge cases # where a column data type might have changed v = utils.string_to_num(v) if v == '<NULL>': return None elif v == '<empty string>': return '' return v
def get_sqla_query( # sqla self, groupby, metrics, granularity, from_dttm, to_dttm, filter=None, # noqa is_timeseries=True, timeseries_limit=15, timeseries_limit_metric=None, row_limit=None, inner_from_dttm=None, inner_to_dttm=None, orderby=None, extras=None, columns=None, order_desc=True, prequeries=None, is_prequery=False, ): """Querying any sqla table from this common interface""" template_kwargs = { 'from_dttm': from_dttm, 'groupby': groupby, 'metrics': metrics, 'row_limit': row_limit, 'to_dttm': to_dttm, 'filter': filter, 'columns': {col.column_name: col for col in self.columns}, } template_kwargs.update(self.template_params_dict) template_processor = self.get_template_processor(**template_kwargs) db_engine_spec = self.database.db_engine_spec orderby = orderby or [] # For backward compatibility if granularity not in self.dttm_cols: granularity = self.main_dttm_col # Database spec supports join-free timeslot grouping time_groupby_inline = db_engine_spec.time_groupby_inline cols = {col.column_name: col for col in self.columns} metrics_dict = {m.metric_name: m for m in self.metrics} if not granularity and is_timeseries: raise Exception( _('Datetime column not provided as part table configuration ' 'and is required by this type of chart')) if not groupby and not metrics and not columns: raise Exception(_('Empty query?')) metrics_exprs = [] for m in metrics: if utils.is_adhoc_metric(m): metrics_exprs.append(self.adhoc_metric_to_sqla(m, cols)) elif m in metrics_dict: metrics_exprs.append(metrics_dict.get(m).get_sqla_col()) else: raise Exception(_("Metric '{}' is not valid".format(m))) if metrics_exprs: main_metric_expr = metrics_exprs[0] else: main_metric_expr = literal_column('COUNT(*)').label( db_engine_spec.make_label_compatible('count')) select_exprs = [] groupby_exprs = [] if groupby: select_exprs = [] inner_select_exprs = [] inner_groupby_exprs = [] for s in groupby: col = cols[s] outer = col.get_sqla_col() inner = col.get_sqla_col(col.column_name + '__') groupby_exprs.append(outer) select_exprs.append(outer) inner_groupby_exprs.append(inner) inner_select_exprs.append(inner) elif columns: for s in columns: select_exprs.append(cols[s].get_sqla_col()) metrics_exprs = [] if granularity: dttm_col = cols[granularity] time_grain = extras.get('time_grain_sqla') time_filters = [] if is_timeseries: timestamp = dttm_col.get_timestamp_expression(time_grain) select_exprs += [timestamp] groupby_exprs += [timestamp] # Use main dttm column to support index with secondary dttm columns if db_engine_spec.time_secondary_columns and \ self.main_dttm_col in self.dttm_cols and \ self.main_dttm_col != dttm_col.column_name: time_filters.append(cols[self.main_dttm_col].get_time_filter( from_dttm, to_dttm)) time_filters.append(dttm_col.get_time_filter(from_dttm, to_dttm)) select_exprs += metrics_exprs qry = sa.select(select_exprs) tbl = self.get_from_clause(template_processor) if not columns: qry = qry.group_by(*groupby_exprs) where_clause_and = [] having_clause_and = [] for flt in filter: if not all([flt.get(s) for s in ['col', 'op']]): continue col = flt['col'] op = flt['op'] col_obj = cols.get(col) if col_obj: is_list_target = op in ('in', 'not in') eq = self.filter_values_handler( flt.get('val'), target_column_is_numeric=col_obj.is_num, is_list_target=is_list_target) if op in ('in', 'not in'): cond = col_obj.get_sqla_col().in_(eq) if '<NULL>' in eq: cond = or_(cond, col_obj.get_sqla_col() == None) # noqa if op == 'not in': cond = ~cond where_clause_and.append(cond) else: if col_obj.is_num: eq = utils.string_to_num(flt['val']) if op == '==': where_clause_and.append(col_obj.get_sqla_col() == eq) elif op == '!=': where_clause_and.append(col_obj.get_sqla_col() != eq) elif op == '>': where_clause_and.append(col_obj.get_sqla_col() > eq) elif op == '<': where_clause_and.append(col_obj.get_sqla_col() < eq) elif op == '>=': where_clause_and.append(col_obj.get_sqla_col() >= eq) elif op == '<=': where_clause_and.append(col_obj.get_sqla_col() <= eq) elif op == 'LIKE': where_clause_and.append( col_obj.get_sqla_col().like(eq)) elif op == 'IS NULL': where_clause_and.append( col_obj.get_sqla_col() == None) # noqa elif op == 'IS NOT NULL': where_clause_and.append( col_obj.get_sqla_col() != None) # noqa if extras: where = extras.get('where') if where: where = template_processor.process_template(where) where_clause_and += [sa.text('({})'.format(where))] having = extras.get('having') if having: having = template_processor.process_template(having) having_clause_and += [sa.text('({})'.format(having))] if granularity: qry = qry.where(and_(*(time_filters + where_clause_and))) else: qry = qry.where(and_(*where_clause_and)) qry = qry.having(and_(*having_clause_and)) if not orderby and not columns: orderby = [(main_metric_expr, not order_desc)] for col, ascending in orderby: direction = asc if ascending else desc if utils.is_adhoc_metric(col): col = self.adhoc_metric_to_sqla(col, cols) qry = qry.order_by(direction(col)) if row_limit: qry = qry.limit(row_limit) if is_timeseries and \ timeseries_limit and groupby and not time_groupby_inline: if self.database.db_engine_spec.inner_joins: # some sql dialects require for order by expressions # to also be in the select clause -- others, e.g. vertica, # require a unique inner alias inner_main_metric_expr = main_metric_expr.label('mme_inner__') inner_select_exprs += [inner_main_metric_expr] subq = select(inner_select_exprs) subq = subq.select_from(tbl) inner_time_filter = dttm_col.get_time_filter( inner_from_dttm or from_dttm, inner_to_dttm or to_dttm, ) subq = subq.where( and_(*(where_clause_and + [inner_time_filter]))) subq = subq.group_by(*inner_groupby_exprs) ob = inner_main_metric_expr if timeseries_limit_metric: if utils.is_adhoc_metric(timeseries_limit_metric): ob = self.adhoc_metric_to_sqla(timeseries_limit_metric, cols) elif timeseries_limit_metric in metrics_dict: timeseries_limit_metric = metrics_dict.get( timeseries_limit_metric, ) ob = timeseries_limit_metric.get_sqla_col() else: raise Exception(_( "Metric '{}' is not valid".format(m))) direction = desc if order_desc else asc subq = subq.order_by(direction(ob)) subq = subq.limit(timeseries_limit) on_clause = [] for i, gb in enumerate(groupby): on_clause.append(groupby_exprs[i] == column(gb + '__')) tbl = tbl.join(subq.alias(), and_(*on_clause)) else: # run subquery to get top groups subquery_obj = { 'prequeries': prequeries, 'is_prequery': True, 'is_timeseries': False, 'row_limit': timeseries_limit, 'groupby': groupby, 'metrics': metrics, 'granularity': granularity, 'from_dttm': inner_from_dttm or from_dttm, 'to_dttm': inner_to_dttm or to_dttm, 'filter': filter, 'orderby': orderby, 'extras': extras, 'columns': columns, 'order_desc': True, } result = self.query(subquery_obj) cols = {col.column_name: col for col in self.columns} dimensions = [ c for c in result.df.columns if c not in metrics and c in cols ] top_groups = self._get_top_groups(result.df, dimensions) qry = qry.where(top_groups) return qry.select_from(tbl)
def get_sqla_query( # sqla self, groupby, metrics, granularity, from_dttm, to_dttm, filter=None, # noqa is_timeseries=True, timeseries_limit=15, timeseries_limit_metric=None, row_limit=None, inner_from_dttm=None, inner_to_dttm=None, orderby=None, extras=None, columns=None, order_desc=True, ): """Querying any sqla table from this common interface""" template_kwargs = { "from_dttm": from_dttm, "groupby": groupby, "metrics": metrics, "row_limit": row_limit, "to_dttm": to_dttm, "filter": filter, "columns": {col.column_name: col for col in self.columns}, } template_kwargs.update(self.template_params_dict) extra_cache_keys: List[Any] = [] template_kwargs["extra_cache_keys"] = extra_cache_keys template_processor = self.get_template_processor(**template_kwargs) db_engine_spec = self.database.db_engine_spec prequeries: List[str] = [] orderby = orderby or [] # For backward compatibility if granularity not in self.dttm_cols: granularity = self.main_dttm_col # Database spec supports join-free timeslot grouping time_groupby_inline = db_engine_spec.time_groupby_inline cols = {col.column_name: col for col in self.columns} metrics_dict = {m.metric_name: m for m in self.metrics} if not granularity and is_timeseries: raise Exception( _("Datetime column not provided as part table configuration " "and is required by this type of chart")) if not groupby and not metrics and not columns: raise Exception(_("Empty query?")) metrics_exprs = [] for m in metrics: if utils.is_adhoc_metric(m): metrics_exprs.append(self.adhoc_metric_to_sqla(m, cols)) elif m in metrics_dict: metrics_exprs.append(metrics_dict.get(m).get_sqla_col()) else: raise Exception( _("Metric '%(metric)s' does not exist", metric=m)) if metrics_exprs: main_metric_expr = metrics_exprs[0] else: main_metric_expr, label = literal_column("COUNT(*)"), "ccount" main_metric_expr = self.make_sqla_column_compatible( main_metric_expr, label) select_exprs = [] groupby_exprs_sans_timestamp = OrderedDict() if groupby: select_exprs = [] for s in groupby: if s in cols: outer = cols[s].get_sqla_col() else: outer = literal_column(f"({s})") outer = self.make_sqla_column_compatible(outer, s) groupby_exprs_sans_timestamp[outer.name] = outer select_exprs.append(outer) elif columns: for s in columns: select_exprs.append( cols[s].get_sqla_col() if s in cols else self. make_sqla_column_compatible(literal_column(s))) metrics_exprs = [] groupby_exprs_with_timestamp = OrderedDict( groupby_exprs_sans_timestamp.items()) if granularity: dttm_col = cols[granularity] time_grain = extras.get("time_grain_sqla") time_filters = [] if is_timeseries: timestamp = dttm_col.get_timestamp_expression(time_grain) select_exprs += [timestamp] groupby_exprs_with_timestamp[timestamp.name] = timestamp # Use main dttm column to support index with secondary dttm columns if (db_engine_spec.time_secondary_columns and self.main_dttm_col in self.dttm_cols and self.main_dttm_col != dttm_col.column_name): time_filters.append(cols[self.main_dttm_col].get_time_filter( from_dttm, to_dttm)) time_filters.append(dttm_col.get_time_filter(from_dttm, to_dttm)) select_exprs += metrics_exprs labels_expected = [c._df_label_expected for c in select_exprs] select_exprs = db_engine_spec.make_select_compatible( groupby_exprs_with_timestamp.values(), select_exprs) qry = sa.select(select_exprs) tbl = self.get_from_clause(template_processor) if not columns: qry = qry.group_by(*groupby_exprs_with_timestamp.values()) where_clause_and = [] having_clause_and = [] for flt in filter: if not all([flt.get(s) for s in ["col", "op"]]): continue col = flt["col"] op = flt["op"] col_obj = cols.get(col) if col_obj: is_list_target = op in ("in", "not in") eq = self.filter_values_handler( flt.get("val"), target_column_is_numeric=col_obj.is_num, is_list_target=is_list_target, ) if op in ("in", "not in"): cond = col_obj.get_sqla_col().in_(eq) if "<NULL>" in eq: cond = or_(cond, col_obj.get_sqla_col() == None) # noqa if op == "not in": cond = ~cond where_clause_and.append(cond) else: if col_obj.is_num: eq = utils.string_to_num(flt["val"]) if op == "==": where_clause_and.append(col_obj.get_sqla_col() == eq) elif op == "!=": where_clause_and.append(col_obj.get_sqla_col() != eq) elif op == ">": where_clause_and.append(col_obj.get_sqla_col() > eq) elif op == "<": where_clause_and.append(col_obj.get_sqla_col() < eq) elif op == ">=": where_clause_and.append(col_obj.get_sqla_col() >= eq) elif op == "<=": where_clause_and.append(col_obj.get_sqla_col() <= eq) elif op == "LIKE": where_clause_and.append( col_obj.get_sqla_col().like(eq)) elif op == "IS NULL": where_clause_and.append( col_obj.get_sqla_col() == None) # noqa elif op == "IS NOT NULL": where_clause_and.append( col_obj.get_sqla_col() != None) # noqa if extras: where = extras.get("where") if where: where = template_processor.process_template(where) where_clause_and += [sa.text("({})".format(where))] having = extras.get("having") if having: having = template_processor.process_template(having) having_clause_and += [sa.text("({})".format(having))] if granularity: qry = qry.where(and_(*(time_filters + where_clause_and))) else: qry = qry.where(and_(*where_clause_and)) qry = qry.having(and_(*having_clause_and)) if not orderby and not columns: orderby = [(main_metric_expr, not order_desc)] for col, ascending in orderby: direction = asc if ascending else desc if utils.is_adhoc_metric(col): col = self.adhoc_metric_to_sqla(col, cols) qry = qry.order_by(direction(col)) if row_limit: qry = qry.limit(row_limit) if is_timeseries and timeseries_limit and groupby and not time_groupby_inline: if self.database.db_engine_spec.allows_joins: # some sql dialects require for order by expressions # to also be in the select clause -- others, e.g. vertica, # require a unique inner alias inner_main_metric_expr = self.make_sqla_column_compatible( main_metric_expr, "mme_inner__") inner_groupby_exprs = [] inner_select_exprs = [] for gby_name, gby_obj in groupby_exprs_sans_timestamp.items(): inner = self.make_sqla_column_compatible( gby_obj, gby_name + "__") inner_groupby_exprs.append(inner) inner_select_exprs.append(inner) inner_select_exprs += [inner_main_metric_expr] subq = select(inner_select_exprs).select_from(tbl) inner_time_filter = dttm_col.get_time_filter( inner_from_dttm or from_dttm, inner_to_dttm or to_dttm) subq = subq.where( and_(*(where_clause_and + [inner_time_filter]))) subq = subq.group_by(*inner_groupby_exprs) ob = inner_main_metric_expr if timeseries_limit_metric: ob = self._get_timeseries_orderby(timeseries_limit_metric, metrics_dict, cols) direction = desc if order_desc else asc subq = subq.order_by(direction(ob)) subq = subq.limit(timeseries_limit) on_clause = [] for gby_name, gby_obj in groupby_exprs_sans_timestamp.items(): # in this case the column name, not the alias, needs to be # conditionally mutated, as it refers to the column alias in # the inner query col_name = db_engine_spec.make_label_compatible(gby_name + "__") on_clause.append(gby_obj == column(col_name)) tbl = tbl.join(subq.alias(), and_(*on_clause)) else: if timeseries_limit_metric: orderby = [( self._get_timeseries_orderby(timeseries_limit_metric, metrics_dict, cols), False, )] # run prequery to get top groups prequery_obj = { "is_timeseries": False, "row_limit": timeseries_limit, "groupby": groupby, "metrics": metrics, "granularity": granularity, "from_dttm": inner_from_dttm or from_dttm, "to_dttm": inner_to_dttm or to_dttm, "filter": filter, "orderby": orderby, "extras": extras, "columns": columns, "order_desc": True, } result = self.query(prequery_obj) prequeries.append(result.query) dimensions = [ c for c in result.df.columns if c not in metrics and c in groupby_exprs_sans_timestamp ] top_groups = self._get_top_groups( result.df, dimensions, groupby_exprs_sans_timestamp) qry = qry.where(top_groups) return SqlaQuery( extra_cache_keys=extra_cache_keys, labels_expected=labels_expected, sqla_query=qry.select_from(tbl), prequeries=prequeries, )
def get_sqla_query( # sqla self, groupby, metrics, granularity, from_dttm, to_dttm, filter=None, # noqa is_timeseries=True, timeseries_limit=15, timeseries_limit_metric=None, row_limit=None, inner_from_dttm=None, inner_to_dttm=None, orderby=None, extras=None, columns=None, order_desc=True, prequeries=None, is_prequery=False, ): """Querying any sqla table from this common interface""" template_kwargs = { 'from_dttm': from_dttm, 'groupby': groupby, 'metrics': metrics, 'row_limit': row_limit, 'to_dttm': to_dttm, 'filter': filter, 'columns': {col.column_name: col for col in self.columns}, } template_kwargs.update(self.template_params_dict) template_processor = self.get_template_processor(**template_kwargs) db_engine_spec = self.database.db_engine_spec orderby = orderby or [] # For backward compatibility if granularity not in self.dttm_cols: granularity = self.main_dttm_col # Database spec supports join-free timeslot grouping time_groupby_inline = db_engine_spec.time_groupby_inline cols = {col.column_name: col for col in self.columns} metrics_dict = {m.metric_name: m for m in self.metrics} if not granularity and is_timeseries: raise Exception(_( 'Datetime column not provided as part table configuration ' 'and is required by this type of chart')) if not groupby and not metrics and not columns: raise Exception(_('Empty query?')) metrics_exprs = [] for m in metrics: if utils.is_adhoc_metric(m): metrics_exprs.append(self.adhoc_metric_to_sqla(m, cols)) elif m in metrics_dict: metrics_exprs.append(metrics_dict.get(m).get_sqla_col()) else: raise Exception(_("Metric '{}' is not valid".format(m))) if metrics_exprs: main_metric_expr = metrics_exprs[0] else: main_metric_expr = literal_column('COUNT(*)').label( db_engine_spec.make_label_compatible('count')) select_exprs = [] groupby_exprs = [] if groupby: select_exprs = [] inner_select_exprs = [] inner_groupby_exprs = [] for s in groupby: col = cols[s] outer = col.get_sqla_col() inner = col.get_sqla_col(col.column_name + '__') groupby_exprs.append(outer) select_exprs.append(outer) inner_groupby_exprs.append(inner) inner_select_exprs.append(inner) elif columns: for s in columns: select_exprs.append(cols[s].get_sqla_col()) metrics_exprs = [] if granularity: dttm_col = cols[granularity] time_grain = extras.get('time_grain_sqla') time_filters = [] if is_timeseries: timestamp = dttm_col.get_timestamp_expression(time_grain) select_exprs += [timestamp] groupby_exprs += [timestamp] # Use main dttm column to support index with secondary dttm columns if db_engine_spec.time_secondary_columns and \ self.main_dttm_col in self.dttm_cols and \ self.main_dttm_col != dttm_col.column_name: time_filters.append(cols[self.main_dttm_col]. get_time_filter(from_dttm, to_dttm)) time_filters.append(dttm_col.get_time_filter(from_dttm, to_dttm)) select_exprs += metrics_exprs qry = sa.select(select_exprs) tbl = self.get_from_clause(template_processor) if not columns: qry = qry.group_by(*groupby_exprs) where_clause_and = [] having_clause_and = [] for flt in filter: if not all([flt.get(s) for s in ['col', 'op']]): continue col = flt['col'] op = flt['op'] col_obj = cols.get(col) if col_obj: is_list_target = op in ('in', 'not in') eq = self.filter_values_handler( flt.get('val'), target_column_is_numeric=col_obj.is_num, is_list_target=is_list_target) if op in ('in', 'not in'): cond = col_obj.get_sqla_col().in_(eq) if '<NULL>' in eq: cond = or_(cond, col_obj.get_sqla_col() == None) # noqa if op == 'not in': cond = ~cond where_clause_and.append(cond) else: if col_obj.is_num: eq = utils.string_to_num(flt['val']) if op == '==': where_clause_and.append(col_obj.get_sqla_col() == eq) elif op == '!=': where_clause_and.append(col_obj.get_sqla_col() != eq) elif op == '>': where_clause_and.append(col_obj.get_sqla_col() > eq) elif op == '<': where_clause_and.append(col_obj.get_sqla_col() < eq) elif op == '>=': where_clause_and.append(col_obj.get_sqla_col() >= eq) elif op == '<=': where_clause_and.append(col_obj.get_sqla_col() <= eq) elif op == 'LIKE': where_clause_and.append(col_obj.get_sqla_col().like(eq)) elif op == 'IS NULL': where_clause_and.append(col_obj.get_sqla_col() == None) # noqa elif op == 'IS NOT NULL': where_clause_and.append( col_obj.get_sqla_col() != None) # noqa if extras: where = extras.get('where') if where: where = template_processor.process_template(where) where_clause_and += [sa.text('({})'.format(where))] having = extras.get('having') if having: having = template_processor.process_template(having) having_clause_and += [sa.text('({})'.format(having))] if granularity: qry = qry.where(and_(*(time_filters + where_clause_and))) else: qry = qry.where(and_(*where_clause_and)) qry = qry.having(and_(*having_clause_and)) if not orderby and not columns: orderby = [(main_metric_expr, not order_desc)] for col, ascending in orderby: direction = asc if ascending else desc if utils.is_adhoc_metric(col): col = self.adhoc_metric_to_sqla(col, cols) qry = qry.order_by(direction(col)) if row_limit: qry = qry.limit(row_limit) if is_timeseries and \ timeseries_limit and groupby and not time_groupby_inline: if self.database.db_engine_spec.inner_joins: # some sql dialects require for order by expressions # to also be in the select clause -- others, e.g. vertica, # require a unique inner alias inner_main_metric_expr = main_metric_expr.label('mme_inner__') inner_select_exprs += [inner_main_metric_expr] subq = select(inner_select_exprs) subq = subq.select_from(tbl) inner_time_filter = dttm_col.get_time_filter( inner_from_dttm or from_dttm, inner_to_dttm or to_dttm, ) subq = subq.where(and_(*(where_clause_and + [inner_time_filter]))) subq = subq.group_by(*inner_groupby_exprs) ob = inner_main_metric_expr if timeseries_limit_metric: if utils.is_adhoc_metric(timeseries_limit_metric): ob = self.adhoc_metric_to_sqla(timeseries_limit_metric, cols) elif timeseries_limit_metric in metrics_dict: timeseries_limit_metric = metrics_dict.get( timeseries_limit_metric, ) ob = timeseries_limit_metric.get_sqla_col() else: raise Exception(_("Metric '{}' is not valid".format(m))) direction = desc if order_desc else asc subq = subq.order_by(direction(ob)) subq = subq.limit(timeseries_limit) on_clause = [] for i, gb in enumerate(groupby): on_clause.append( groupby_exprs[i] == column(gb + '__')) tbl = tbl.join(subq.alias(), and_(*on_clause)) else: # run subquery to get top groups subquery_obj = { 'prequeries': prequeries, 'is_prequery': True, 'is_timeseries': False, 'row_limit': timeseries_limit, 'groupby': groupby, 'metrics': metrics, 'granularity': granularity, 'from_dttm': inner_from_dttm or from_dttm, 'to_dttm': inner_to_dttm or to_dttm, 'filter': filter, 'orderby': orderby, 'extras': extras, 'columns': columns, 'order_desc': True, } result = self.query(subquery_obj) cols = {col.column_name: col for col in self.columns} dimensions = [ c for c in result.df.columns if c not in metrics and c in cols ] top_groups = self._get_top_groups(result.df, dimensions) qry = qry.where(top_groups) return qry.select_from(tbl)