def __init__(self, edge, query, limit):
AggsDecoder.__init__(self, edge, query, limit)
self.domain = edge.domain
self.domain.limit = Math.min(
coalesce(self.domain.limit, query.limit, 10), MAX_LIMIT)
self.parts = list()
self.key2index = {}
self.computed_domain = False
self.script = self.edge.value.partial_eval().to_es14_script(
self.schema)
self.pull = pull_functions[self.script.data_type]
self.missing = self.script.miss.partial_eval()
self.exists = NotOp("not", self.missing).partial_eval()
# WHEN SORT VALUE AND EDGE VALUE MATCHES, WE SORT BY TERM
sort_candidates = [
s for s in self.query.sort if s.value == self.edge.value
]
if sort_candidates:
self.es_order = {
"_term": {
1: "asc",
-1: "desc"
}[sort_candidates[0].sort]
}
else:
self.es_order = None
def __init__(self, edge, query, limit):
AggsDecoder.__init__(self, edge, query, limit)
self.fields = edge.domain.dimension.fields
self.domain = self.edge.domain
self.domain.limit = Math.min(
coalesce(self.domain.limit, query.limit, 10), MAX_LIMIT)
self.parts = list()
def __init__(self, edge, query, limit):
AggsDecoder.__init__(self, edge, query, limit)
edge.allowNulls = False
self.fields = edge.domain.dimension.fields
self.domain = self.edge.domain
self.domain.limit = Math.min(coalesce(self.domain.limit, query.limit, 10), MAX_LIMIT)
self.parts = list()
def wrap(query, schema=None):
"""
NORMALIZE QUERY SO IT CAN STILL BE JSON
"""
if isinstance(query, QueryOp) or query == None:
return query
query = wrap(query)
output = QueryOp("from", None)
output.format = query.format
from jx_python import wrap_from
output.frum = wrap_from(query["from"], schema=schema)
if not schema and isinstance(output.frum, Schema):
schema = output.frum
if not schema and hasattr(output.frum, "schema"):
schema = output.frum.schema
if query.select or isinstance(query.select, (Mapping, list)):
output.select = _normalize_selects(query.select,
query.frum,
schema=schema)
else:
if query.edges or query.groupby:
output.select = Data(name="count",
value=jx_expression("."),
aggregate="count",
default=0)
else:
output.select = _normalize_selects(".", query.frum)
if query.groupby and query.edges:
Log.error(
"You can not use both the `groupby` and `edges` clauses in the same query!"
)
elif query.edges:
output.edges = _normalize_edges(query.edges, schema=schema)
output.groupby = Null
elif query.groupby:
output.edges = Null
output.groupby = _normalize_groupby(query.groupby, schema=schema)
else:
output.edges = Null
output.groupby = Null
output.where = _normalize_where(query.where, schema=schema)
output.window = [_normalize_window(w) for w in listwrap(query.window)]
output.having = None
output.sort = _normalize_sort(query.sort)
output.limit = Math.min(MAX_LIMIT, coalesce(query.limit,
DEFAULT_LIMIT))
if not Math.is_integer(output.limit) or output.limit < 0:
Log.error("Expecting limit >= 0")
output.isLean = query.isLean
return output
def wrap(query, container, namespace):
"""
NORMALIZE QUERY SO IT CAN STILL BE JSON
"""
if isinstance(query, QueryOp) or query == None:
return query
query = wrap(query)
table = container.get_table(query['from'])
schema = table.schema
output = QueryOp(op="from",
frum=table,
format=query.format,
limit=Math.min(MAX_LIMIT,
coalesce(query.limit, DEFAULT_LIMIT)))
if query.select or isinstance(query.select, (Mapping, list)):
output.select = _normalize_selects(query.select,
query.frum,
schema=schema)
else:
if query.edges or query.groupby:
output.select = DEFAULT_SELECT
else:
output.select = _normalize_selects(".", query.frum)
if query.groupby and query.edges:
Log.error(
"You can not use both the `groupby` and `edges` clauses in the same query!"
)
elif query.edges:
output.edges = _normalize_edges(query.edges,
limit=output.limit,
schema=schema)
output.groupby = Null
elif query.groupby:
output.edges = Null
output.groupby = _normalize_groupby(query.groupby,
limit=output.limit,
schema=schema)
else:
output.edges = Null
output.groupby = Null
output.where = _normalize_where(query.where, schema=schema)
output.window = [_normalize_window(w) for w in listwrap(query.window)]
output.having = None
output.sort = _normalize_sort(query.sort)
if not Math.is_integer(output.limit) or output.limit < 0:
Log.error("Expecting limit >= 0")
output.isLean = query.isLean
return output
def __getslice__(self, i, j):
j = Math.min(j, len(self))
if j - 1 > 2**28:
Log.error("Slice of {{num}} bytes is too big", num=j - i)
try:
self.file.seek(i)
output = self.file.read(j - i).decode(self.encoding)
return output
except Exception as e:
Log.error(
"Can not read file slice at {{index}}, with encoding {{encoding}}",
index=i,
encoding=self.encoding,
cause=e)
def __init__(self, edge, query, limit):
AggsDecoder.__init__(self, edge, query, limit)
self.domain = edge.domain
self.domain.limit =Math.min(coalesce(self.domain.limit, query.limit, 10), MAX_LIMIT)
self.parts = list()
self.key2index = {}
self.computed_domain = False
# WE ASSUME IF THE VARIABLES MATCH, THEN THE SORT TERM AND EDGE TERM MATCH, AND WE SORT BY TERM
self.sorted = None
edge_var = edge.value.vars()
for s in query.sort:
if not edge_var - s.value.vars():
self.sorted = {1: "asc", -1: "desc"}[s.sort]
def __getslice__(self, i, j):
j = Math.min(j, len(self))
if j - 1 > 2 ** 28:
Log.error("Slice of {{num}} bytes is too big", num=j - i)
try:
self.file.seek(i)
output = self.file.read(j - i).decode(self.encoding)
return output
except Exception as e:
Log.error(
"Can not read file slice at {{index}}, with encoding {{encoding}}",
index=i,
encoding=self.encoding,
cause=e
)
def wrap(query, schema=None):
"""
NORMALIZE QUERY SO IT CAN STILL BE JSON
"""
if isinstance(query, QueryOp) or query == None:
return query
query = wrap(query)
output = QueryOp("from", None)
output.format = query.format
output.frum = wrap_from(query["from"], schema=schema)
if not schema and isinstance(output.frum, Schema):
schema = output.frum
if not schema and hasattr(output.frum, "schema"):
schema = output.frum.schema
if query.select or isinstance(query.select, (Mapping, list)):
output.select = _normalize_selects(query.select, query.frum, schema=schema)
else:
if query.edges or query.groupby:
output.select = Data(name="count", value=jx_expression("."), aggregate="count", default=0)
else:
output.select = _normalize_selects(".", query.frum)
if query.groupby and query.edges:
Log.error("You can not use both the `groupby` and `edges` clauses in the same query!")
elif query.edges:
output.edges = _normalize_edges(query.edges, schema=schema)
output.groupby = Null
elif query.groupby:
output.edges = Null
output.groupby = _normalize_groupby(query.groupby, schema=schema)
else:
output.edges = Null
output.groupby = Null
output.where = _normalize_where(query.where, schema=schema)
output.window = [_normalize_window(w) for w in listwrap(query.window)]
output.having = None
output.sort = _normalize_sort(query.sort)
output.limit = Math.min(MAX_LIMIT, coalesce(query.limit, DEFAULT_LIMIT))
if not Math.is_integer(output.limit) or output.limit < 0:
Log.error("Expecting limit >= 0")
output.isLean = query.isLean
return output
def wrap(query, container, namespace):
"""
NORMALIZE QUERY SO IT CAN STILL BE JSON
"""
if isinstance(query, QueryOp) or query == None:
return query
query = wrap(query)
table = container.get_table(query['from'])
schema = table.schema
output = QueryOp(
op="from",
frum=table,
format=query.format,
limit=Math.min(MAX_LIMIT, coalesce(query.limit, DEFAULT_LIMIT))
)
if query.select or isinstance(query.select, (Mapping, list)):
output.select = _normalize_selects(query.select, query.frum, schema=schema)
else:
if query.edges or query.groupby:
output.select = DEFAULT_SELECT
else:
output.select = _normalize_selects(".", query.frum)
if query.groupby and query.edges:
Log.error("You can not use both the `groupby` and `edges` clauses in the same query!")
elif query.edges:
output.edges = _normalize_edges(query.edges, limit=output.limit, schema=schema)
output.groupby = Null
elif query.groupby:
output.edges = Null
output.groupby = _normalize_groupby(query.groupby, limit=output.limit, schema=schema)
else:
output.edges = Null
output.groupby = Null
output.where = _normalize_where(query.where, schema=schema)
output.window = [_normalize_window(w) for w in listwrap(query.window)]
output.having = None
output.sort = _normalize_sort(query.sort)
if not Math.is_integer(output.limit) or output.limit < 0:
Log.error("Expecting limit >= 0")
output.isLean = query.isLean
return output
def __init__(self, edge, query, limit):
AggsDecoder.__init__(self, edge, query, limit)
self.domain = edge.domain
self.domain.limit = Math.min(coalesce(self.domain.limit, query.limit, 10), MAX_LIMIT)
self.parts = list()
self.key2index = {}
self.computed_domain = False
self.script = self.edge.value.partial_eval().to_es_script(self.schema)
self.pull = pull_functions[self.script.data_type]
self.missing = self.script.miss.partial_eval()
self.exists = NotOp("not", self.missing).partial_eval()
# WHEN SORT VALUE AND EDGE VALUE MATCHES, WE SORT BY TERM
sort_candidates = [s for s in self.query.sort if s.value == self.edge.value]
if sort_candidates:
self.es_order = {"_term": {1: "asc", -1: "desc"}[sort_candidates[0].sort]}
else:
self.es_order = None
def __init__(self, edge, query, limit):
AggsDecoder.__init__(self, edge, query, limit)
if isinstance(edge.value, LeavesOp):
prefix = edge.value.term.var
flatter = lambda k: literal_field(relative_field(k, prefix))
else:
prefix = edge.value.var
flatter = lambda k: relative_field(k, prefix)
self.put, self.fields = transpose(*[
(flatter(untype_path(c.names["."])), c.es_column)
for c in query.frum.schema.leaves(prefix)
])
self.domain = self.edge.domain = wrap({"dimension": {"fields": self.fields}})
self.domain.limit = Math.min(coalesce(self.domain.limit, query.limit, 10), MAX_LIMIT)
self.parts = list()
self.key2index = {}
self.computed_domain = False
def __init__(self, edge, query, limit):
AggsDecoder.__init__(self, edge, query, limit)
if isinstance(edge.value, LeavesOp):
prefix = edge.value.term.var
flatter = lambda k: literal_field(relative_field(k, prefix))
else:
prefix = edge.value.var
flatter = lambda k: relative_field(k, prefix)
self.put, self.fields = zip(*[
(flatter(untype_path(c.names["."])), c.es_column)
for c in query.frum.schema.leaves(prefix)
])
self.domain = self.edge.domain = wrap({"dimension": {"fields": self.fields}})
self.domain.limit = Math.min(coalesce(self.domain.limit, query.limit, 10), MAX_LIMIT)
self.parts = list()
self.key2index = {}
self.computed_domain = False
def __init__(self, edge, query, limit):
AggsDecoder.__init__(self, edge, query, limit)
if isinstance(edge.value, LeavesOp):
flatter = literal_field
prefix = edge.value.term.var + "."
else:
prefix = edge.value.var + "."
prefix_length = len(prefix)
flatter = (lambda k: k[prefix_length:])
self.put, self.fields = zip(
*[(flatter(k), c.es_column)
for k, cs in query.frum.schema.lookup.items()
if k.startswith(prefix) for c in cs if c.type not in STRUCT])
self.domain = self.edge.domain = wrap(
{"dimension": {
"fields": self.fields
}})
self.domain.limit = Math.min(
coalesce(self.domain.limit, query.limit, 10), MAX_LIMIT)
self.parts = list()
self.key2index = {}
self.computed_domain = False
if not value:
return Null
try:
return int(value)
except Exception:
pass
try:
return float(value)
except Exception:
pass
return value
tab_data = File("resources/EC2.csv").read()
lines = map(strings.trim, tab_data.split("\n"))
header = lines[0].split(",")
rows = [r.split(",") for r in lines[1:] if r]
data = wrap([{h: unquote(r[c]) for c, h in enumerate(header)} for r in rows])
for d in data:
d.utility = Math.min(d.memory, d.storage/50, 60)
d.drives["$ref"] = "#" + unicode(d.num_drives) + "_ephemeral_drives"
d.discount = 0
Log.note("{{data|json(False)}}", data=[d for d in data if d.utility])
Log.note("{{data|json}}", data={d.instance_type: {"num": d.num_drives, "size": d.storage} for d in jx.sort(data, "instance_type")})
def update_spot_requests(self, utility_required):
spot_requests = self._get_managed_spot_requests()
# ADD UP THE CURRENT REQUESTED INSTANCES
all_instances = UniqueIndex("id", data=self._get_managed_instances())
self.active = active = wrap([r for r in spot_requests if r.status.code in RUNNING_STATUS_CODES | PENDING_STATUS_CODES | PROBABLY_NOT_FOR_A_WHILE | MIGHT_HAPPEN])
for a in active.copy():
if a.status.code == "request-canceled-and-instance-running" and all_instances[a.instance_id] == None:
active.remove(a)
used_budget = 0
current_spending = 0
for a in active:
about = self.price_lookup[a.launch_specification.instance_type, a.launch_specification.placement]
discount = coalesce(about.type.discount, 0)
Log.note(
"Active Spot Request {{id}}: {{type}} {{instance_id}} in {{zone}} @ {{price|round(decimal=4)}}",
id=a.id,
type=a.launch_specification.instance_type,
zone=a.launch_specification.placement,
instance_id=a.instance_id,
price=a.price - discount
)
used_budget += a.price - discount
current_spending += coalesce(about.current_price, a.price) - discount
Log.note(
"Total Exposure: ${{budget|round(decimal=4)}}/hour (current price: ${{current|round(decimal=4)}}/hour)",
budget=used_budget,
current=current_spending
)
remaining_budget = self.settings.budget - used_budget
current_utility = coalesce(SUM(self.price_lookup[r.launch_specification.instance_type, r.launch_specification.placement].type.utility for r in active), 0)
net_new_utility = utility_required - current_utility
Log.note("have {{current_utility}} utility running; need {{need_utility}} more utility", current_utility=current_utility, need_utility=net_new_utility)
if remaining_budget < 0:
remaining_budget, net_new_utility = self.save_money(remaining_budget, net_new_utility)
if net_new_utility < 0:
if self.settings.allowed_overage:
net_new_utility = Math.min(net_new_utility + self.settings.allowed_overage * utility_required, 0)
net_new_utility = self.remove_instances(net_new_utility)
if net_new_utility > 0:
net_new_utility = Math.min(net_new_utility, self.settings.max_new_utility)
net_new_utility, remaining_budget = self.add_instances(net_new_utility, remaining_budget)
if net_new_utility > 0:
Log.alert(
"Can not fund {{num|round(places=2)}} more utility (all utility costs more than ${{expected|round(decimal=2)}}/hour). Remaining budget is ${{budget|round(decimal=2)}} ",
num=net_new_utility,
expected=self.settings.max_utility_price,
budget=remaining_budget
)
# Give EC2 a chance to notice the new requests before tagging them.
Till(timeout=3).wait()
with self.net_new_locker:
for req in self.net_new_spot_requests:
req.add_tag("Name", self.settings.ec2.instance.name)
Log.note("All requests for new utility have been made")
self.done_spot_requests.go()
def add_instances(self, net_new_utility, remaining_budget):
prices = self.pricing()
for p in prices:
if net_new_utility <= 0 or remaining_budget <= 0:
break
if p.current_price == None:
Log.note("{{type}} has no current price",
type=p.type.instance_type
)
continue
if self.settings.utility[p.type.instance_type].blacklist or \
p.availability_zone in listwrap(self.settings.utility[p.type.instance_type].blacklist_zones):
Log.note("{{type}} in {{zone}} skipped due to blacklist", type=p.type.instance_type, zone=p.availability_zone)
continue
# DO NOT BID HIGHER THAN WHAT WE ARE WILLING TO PAY
max_acceptable_price = p.type.utility * self.settings.max_utility_price + p.type.discount
max_bid = Math.min(p.higher_price, max_acceptable_price, remaining_budget)
min_bid = p.price_80
if min_bid > max_acceptable_price:
Log.note(
"Price of ${{price}}/hour on {{type}}: Over remaining acceptable price of ${{remaining}}/hour",
type=p.type.instance_type,
price=min_bid,
remaining=max_acceptable_price
)
continue
elif min_bid > remaining_budget:
Log.note(
"Did not bid ${{bid}}/hour on {{type}}: Over budget of ${{remaining_budget}}/hour",
type=p.type.instance_type,
bid=min_bid,
remaining_budget=remaining_budget
)
continue
elif min_bid > max_bid:
Log.error("not expected")
naive_number_needed = int(Math.round(float(net_new_utility) / float(p.type.utility), decimal=0))
limit_total = None
if self.settings.max_percent_per_type < 1:
current_count = sum(1 for a in self.active if a.launch_specification.instance_type == p.type.instance_type and a.launch_specification.placement == p.availability_zone)
all_count = sum(1 for a in self.active if a.launch_specification.placement == p.availability_zone)
all_count = max(all_count, naive_number_needed)
limit_total = int(Math.floor((all_count * self.settings.max_percent_per_type - current_count) / (1 - self.settings.max_percent_per_type)))
num = Math.min(naive_number_needed, limit_total, self.settings.max_requests_per_type)
if num < 0:
Log.note(
"{{type}} is over {{limit|percent}} of instances, no more requested",
limit=self.settings.max_percent_per_type,
type=p.type.instance_type
)
continue
elif num == 1:
min_bid = Math.min(Math.max(p.current_price * 1.1, min_bid), max_acceptable_price)
price_interval = 0
else:
price_interval = Math.min(min_bid / 10, (max_bid - min_bid) / (num - 1))
for i in range(num):
bid_per_machine = min_bid + (i * price_interval)
if bid_per_machine < p.current_price:
Log.note(
"Did not bid ${{bid}}/hour on {{type}}: Under current price of ${{current_price}}/hour",
type=p.type.instance_type,
bid=bid_per_machine - p.type.discount,
current_price=p.current_price
)
continue
if bid_per_machine - p.type.discount > remaining_budget:
Log.note(
"Did not bid ${{bid}}/hour on {{type}}: Over remaining budget of ${{remaining}}/hour",
type=p.type.instance_type,
bid=bid_per_machine - p.type.discount,
remaining=remaining_budget
)
continue
try:
if self.settings.ec2.request.count == None or self.settings.ec2.request.count != 1:
Log.error("Spot Manager can only request machine one-at-a-time")
new_requests = self._request_spot_instances(
price=bid_per_machine,
availability_zone_group=p.availability_zone,
instance_type=p.type.instance_type,
kwargs=copy(self.settings.ec2.request)
)
Log.note(
"Request {{num}} instance {{type}} in {{zone}} with utility {{utility}} at ${{price}}/hour",
num=len(new_requests),
type=p.type.instance_type,
zone=p.availability_zone,
utility=p.type.utility,
price=bid_per_machine
)
net_new_utility -= p.type.utility * len(new_requests)
remaining_budget -= (bid_per_machine - p.type.discount) * len(new_requests)
with self.net_new_locker:
for ii in new_requests:
self.net_new_spot_requests.add(ii)
except Exception as e:
Log.warning(
"Request instance {{type}} failed because {{reason}}",
type=p.type.instance_type,
reason=e.message,
cause=e
)
if "Max spot instance count exceeded" in e.message:
Log.note("No further spot requests will be attempted.")
return net_new_utility, remaining_budget
return net_new_utility, remaining_budget
def es_aggsop(es, frum, query):
select = wrap([s.copy() for s in listwrap(query.select)])
# [0] is a cheat; each es_column should be a dict of columns keyed on type, like in sqlite
es_column_map = {v: frum.schema[v][0].es_column for v in query.vars()}
es_query = Data()
new_select = Data() #MAP FROM canonical_name (USED FOR NAMES IN QUERY) TO SELECT MAPPING
formula = []
for s in select:
if s.aggregate == "count" and isinstance(s.value, Variable) and s.value.var == ".":
s.pull = "doc_count"
elif isinstance(s.value, Variable):
if s.value.var == ".":
if frum.typed:
# STATISITCAL AGGS IMPLY $value, WHILE OTHERS CAN BE ANYTHING
if s.aggregate in NON_STATISTICAL_AGGS:
#TODO: HANDLE BOTH $value AND $objects TO COUNT
Log.error("do not know how to handle")
else:
s.value.var = "$value"
new_select["$value"] += [s]
else:
if s.aggregate in NON_STATISTICAL_AGGS:
#TODO: WE SHOULD BE ABLE TO COUNT, BUT WE MUST *OR* ALL LEAF VALUES TO DO IT
Log.error("do not know how to handle")
else:
Log.error('Not expecting ES to have a value at "." which {{agg}} can be applied', agg=s.aggregate)
elif s.aggregate == "count":
s.value = s.value.map(es_column_map)
new_select["count_"+literal_field(s.value.var)] += [s]
else:
s.value = s.value.map(es_column_map)
new_select[literal_field(s.value.var)] += [s]
else:
formula.append(s)
for canonical_name, many in new_select.items():
representative = many[0]
if representative.value.var == ".":
Log.error("do not know how to handle")
else:
field_name = representative.value.var
# canonical_name=literal_field(many[0].name)
for s in many:
if s.aggregate == "count":
es_query.aggs[literal_field(canonical_name)].value_count.field = field_name
s.pull = literal_field(canonical_name) + ".value"
elif s.aggregate == "median":
# ES USES DIFFERENT METHOD FOR PERCENTILES
key = literal_field(canonical_name + " percentile")
es_query.aggs[key].percentiles.field = field_name
es_query.aggs[key].percentiles.percents += [50]
s.pull = key + ".values.50\.0"
elif s.aggregate == "percentile":
# ES USES DIFFERENT METHOD FOR PERCENTILES
key = literal_field(canonical_name + " percentile")
if isinstance(s.percentile, basestring) or s.percetile < 0 or 1 < s.percentile:
Log.error("Expecting percentile to be a float from 0.0 to 1.0")
percent = Math.round(s.percentile * 100, decimal=6)
es_query.aggs[key].percentiles.field = field_name
es_query.aggs[key].percentiles.percents += [percent]
s.pull = key + ".values." + literal_field(unicode(percent))
elif s.aggregate == "cardinality":
# ES USES DIFFERENT METHOD FOR CARDINALITY
key = literal_field(canonical_name + " cardinality")
es_query.aggs[key].cardinality.field = field_name
s.pull = key + ".value"
elif s.aggregate == "stats":
# REGULAR STATS
stats_name = literal_field(canonical_name)
es_query.aggs[stats_name].extended_stats.field = field_name
# GET MEDIAN TOO!
median_name = literal_field(canonical_name + " percentile")
es_query.aggs[median_name].percentiles.field = field_name
es_query.aggs[median_name].percentiles.percents += [50]
s.pull = {
"count": stats_name + ".count",
"sum": stats_name + ".sum",
"min": stats_name + ".min",
"max": stats_name + ".max",
"avg": stats_name + ".avg",
"sos": stats_name + ".sum_of_squares",
"std": stats_name + ".std_deviation",
"var": stats_name + ".variance",
"median": median_name + ".values.50\.0"
}
elif s.aggregate == "union":
# USE TERMS AGGREGATE TO SIMULATE union
stats_name = literal_field(canonical_name)
es_query.aggs[stats_name].terms.field = field_name
es_query.aggs[stats_name].terms.size = Math.min(s.limit, MAX_LIMIT)
s.pull = stats_name + ".buckets.key"
else:
# PULL VALUE OUT OF THE stats AGGREGATE
es_query.aggs[literal_field(canonical_name)].extended_stats.field = field_name
s.pull = literal_field(canonical_name) + "." + aggregates1_4[s.aggregate]
for i, s in enumerate(formula):
canonical_name = literal_field(s.name)
abs_value = s.value.map(es_column_map)
if isinstance(abs_value, TupleOp):
if s.aggregate == "count":
# TUPLES ALWAYS EXIST, SO COUNTING THEM IS EASY
s.pull = "doc_count"
else:
Log.error("{{agg}} is not a supported aggregate over a tuple", agg=s.aggregate)
elif s.aggregate == "count":
es_query.aggs[literal_field(canonical_name)].value_count.script = abs_value.to_ruby()
s.pull = literal_field(canonical_name) + ".value"
elif s.aggregate == "median":
# ES USES DIFFERENT METHOD FOR PERCENTILES THAN FOR STATS AND COUNT
key = literal_field(canonical_name + " percentile")
es_query.aggs[key].percentiles.script = abs_value.to_ruby()
es_query.aggs[key].percentiles.percents += [50]
s.pull = key + ".values.50\.0"
elif s.aggregate == "percentile":
# ES USES DIFFERENT METHOD FOR PERCENTILES THAN FOR STATS AND COUNT
key = literal_field(canonical_name + " percentile")
percent = Math.round(s.percentile * 100, decimal=6)
es_query.aggs[key].percentiles.script = abs_value.to_ruby()
es_query.aggs[key].percentiles.percents += [percent]
s.pull = key + ".values." + literal_field(unicode(percent))
elif s.aggregate == "cardinality":
# ES USES DIFFERENT METHOD FOR CARDINALITY
key = canonical_name + " cardinality"
es_query.aggs[key].cardinality.script = abs_value.to_ruby()
s.pull = key + ".value"
elif s.aggregate == "stats":
# REGULAR STATS
stats_name = literal_field(canonical_name)
es_query.aggs[stats_name].extended_stats.script = abs_value.to_ruby()
# GET MEDIAN TOO!
median_name = literal_field(canonical_name + " percentile")
es_query.aggs[median_name].percentiles.script = abs_value.to_ruby()
es_query.aggs[median_name].percentiles.percents += [50]
s.pull = {
"count": stats_name + ".count",
"sum": stats_name + ".sum",
"min": stats_name + ".min",
"max": stats_name + ".max",
"avg": stats_name + ".avg",
"sos": stats_name + ".sum_of_squares",
"std": stats_name + ".std_deviation",
"var": stats_name + ".variance",
"median": median_name + ".values.50\.0"
}
elif s.aggregate=="union":
# USE TERMS AGGREGATE TO SIMULATE union
stats_name = literal_field(canonical_name)
es_query.aggs[stats_name].terms.script_field = abs_value.to_ruby()
s.pull = stats_name + ".buckets.key"
else:
# PULL VALUE OUT OF THE stats AGGREGATE
s.pull = canonical_name + "." + aggregates1_4[s.aggregate]
es_query.aggs[canonical_name].extended_stats.script = abs_value.to_ruby()
decoders = get_decoders_by_depth(query)
start = 0
vars_ = query.where.vars()
#<TERRIBLE SECTION> THIS IS WHERE WE WEAVE THE where CLAUSE WITH nested
split_where = split_expression_by_depth(query.where, schema=frum.schema)
if len(split_field(frum.name)) > 1:
if any(split_where[2::]):
Log.error("Where clause is too deep")
for d in decoders[1]:
es_query = d.append_query(es_query, start)
start += d.num_columns
if split_where[1]:
#TODO: INCLUDE FILTERS ON EDGES
filter_ = simplify_esfilter(AndOp("and", split_where[1]).to_esfilter())
es_query = Data(
aggs={"_filter": set_default({"filter": filter_}, es_query)}
)
es_query = wrap({
"aggs": {"_nested": set_default(
{
"nested": {
"path": frum.query_path
}
},
es_query
)}
})
else:
if any(split_where[1::]):
Log.error("Where clause is too deep")
if decoders:
for d in jx.reverse(decoders[0]):
es_query = d.append_query(es_query, start)
start += d.num_columns
if split_where[0]:
#TODO: INCLUDE FILTERS ON EDGES
filter = simplify_esfilter(AndOp("and", split_where[0]).to_esfilter())
es_query = Data(
aggs={"_filter": set_default({"filter": filter}, es_query)}
)
# </TERRIBLE SECTION>
if not es_query:
es_query = wrap({"query": {"match_all": {}}})
es_query.size = 0
with Timer("ES query time") as es_duration:
result = es09.util.post(es, es_query, query.limit)
try:
format_time = Timer("formatting")
with format_time:
decoders = [d for ds in decoders for d in ds]
result.aggregations.doc_count = coalesce(result.aggregations.doc_count, result.hits.total) # IT APPEARS THE OLD doc_count IS GONE
formatter, groupby_formatter, aggop_formatter, mime_type = format_dispatch[query.format]
if query.edges:
output = formatter(decoders, result.aggregations, start, query, select)
elif query.groupby:
output = groupby_formatter(decoders, result.aggregations, start, query, select)
else:
output = aggop_formatter(decoders, result.aggregations, start, query, select)
output.meta.timing.formatting = format_time.duration
output.meta.timing.es_search = es_duration.duration
output.meta.content_type = mime_type
output.meta.es_query = es_query
return output
except Exception as e:
if query.format not in format_dispatch:
Log.error("Format {{format|quote}} not supported yet", format=query.format, cause=e)
Log.error("Some problem", e)
def es_aggsop(es, frum, query):
query = query.copy() # WE WILL MARK UP THIS QUERY
schema = frum.schema
select = listwrap(query.select)
es_query = Data()
new_select = Data() # MAP FROM canonical_name (USED FOR NAMES IN QUERY) TO SELECT MAPPING
formula = []
for s in select:
if s.aggregate == "count" and isinstance(s.value, Variable) and s.value.var == ".":
if schema.query_path == ".":
s.pull = jx_expression_to_function("doc_count")
else:
s.pull = jx_expression_to_function({"coalesce": ["_nested.doc_count", "doc_count", 0]})
elif isinstance(s.value, Variable):
if s.aggregate == "count":
new_select["count_"+literal_field(s.value.var)] += [s]
else:
new_select[literal_field(s.value.var)] += [s]
elif s.aggregate:
formula.append(s)
for canonical_name, many in new_select.items():
for s in many:
columns = frum.schema.values(s.value.var)
if s.aggregate == "count":
canonical_names = []
for column in columns:
cn = literal_field(column.es_column + "_count")
if column.jx_type == EXISTS:
canonical_names.append(cn + ".doc_count")
es_query.aggs[cn].filter.range = {column.es_column: {"gt": 0}}
else:
canonical_names.append(cn+ ".value")
es_query.aggs[cn].value_count.field = column.es_column
if len(canonical_names) == 1:
s.pull = jx_expression_to_function(canonical_names[0])
else:
s.pull = jx_expression_to_function({"add": canonical_names})
elif s.aggregate == "median":
if len(columns) > 1:
Log.error("Do not know how to count columns with more than one type (script probably)")
# ES USES DIFFERENT METHOD FOR PERCENTILES
key = literal_field(canonical_name + " percentile")
es_query.aggs[key].percentiles.field = columns[0].es_column
es_query.aggs[key].percentiles.percents += [50]
s.pull = jx_expression_to_function(key + ".values.50\\.0")
elif s.aggregate == "percentile":
if len(columns) > 1:
Log.error("Do not know how to count columns with more than one type (script probably)")
# ES USES DIFFERENT METHOD FOR PERCENTILES
key = literal_field(canonical_name + " percentile")
if isinstance(s.percentile, text_type) or s.percetile < 0 or 1 < s.percentile:
Log.error("Expecting percentile to be a float from 0.0 to 1.0")
percent = Math.round(s.percentile * 100, decimal=6)
es_query.aggs[key].percentiles.field = columns[0].es_column
es_query.aggs[key].percentiles.percents += [percent]
es_query.aggs[key].percentiles.compression = 2
s.pull = jx_expression_to_function(key + ".values." + literal_field(text_type(percent)))
elif s.aggregate == "cardinality":
canonical_names = []
for column in columns:
cn = literal_field(column.es_column + "_cardinality")
canonical_names.append(cn)
es_query.aggs[cn].cardinality.field = column.es_column
if len(columns) == 1:
s.pull = jx_expression_to_function(canonical_names[0] + ".value")
else:
s.pull = jx_expression_to_function({"add": [cn + ".value" for cn in canonical_names], "default": 0})
elif s.aggregate == "stats":
if len(columns) > 1:
Log.error("Do not know how to count columns with more than one type (script probably)")
# REGULAR STATS
stats_name = literal_field(canonical_name)
es_query.aggs[stats_name].extended_stats.field = columns[0].es_column
# GET MEDIAN TOO!
median_name = literal_field(canonical_name + "_percentile")
es_query.aggs[median_name].percentiles.field = columns[0].es_column
es_query.aggs[median_name].percentiles.percents += [50]
s.pull = get_pull_stats(stats_name, median_name)
elif s.aggregate == "union":
pulls = []
for column in columns:
stats_name = encode_property(column.es_column)
if column.nested_path[0] == ".":
es_query.aggs[stats_name] = {"terms": {
"field": column.es_column,
"size": Math.min(s.limit, MAX_LIMIT)
}}
pulls.append(get_bucket_keys(stats_name))
else:
es_query.aggs[stats_name] = {
"nested": {"path": column.nested_path[0]},
"aggs": {"_nested": {"terms": {
"field": column.es_column,
"size": Math.min(s.limit, MAX_LIMIT)
}}}
}
pulls.append(get_bucket_keys(stats_name+"._nested"))
if len(pulls) == 0:
s.pull = NULL
elif len(pulls) == 1:
s.pull = pulls[0]
else:
s.pull = lambda row: UNION(
p(row)
for p in pulls
)
else:
if len(columns) > 1:
Log.error("Do not know how to count columns with more than one type (script probably)")
# PULL VALUE OUT OF THE stats AGGREGATE
es_query.aggs[literal_field(canonical_name)].extended_stats.field = columns[0].es_column
s.pull = jx_expression_to_function({"coalesce": [literal_field(canonical_name) + "." + aggregates[s.aggregate], s.default]})
for i, s in enumerate(formula):
canonical_name = literal_field(s.name)
if isinstance(s.value, TupleOp):
if s.aggregate == "count":
# TUPLES ALWAYS EXIST, SO COUNTING THEM IS EASY
s.pull = "doc_count"
else:
Log.error("{{agg}} is not a supported aggregate over a tuple", agg=s.aggregate)
elif s.aggregate == "count":
es_query.aggs[literal_field(canonical_name)].value_count.script = s.value.partial_eval().to_es_script(schema).script(schema)
s.pull = jx_expression_to_function(literal_field(canonical_name) + ".value")
elif s.aggregate == "median":
# ES USES DIFFERENT METHOD FOR PERCENTILES THAN FOR STATS AND COUNT
key = literal_field(canonical_name + " percentile")
es_query.aggs[key].percentiles.script = s.value.to_es_script(schema).script(schema)
es_query.aggs[key].percentiles.percents += [50]
s.pull = jx_expression_to_function(key + ".values.50\\.0")
elif s.aggregate == "percentile":
# ES USES DIFFERENT METHOD FOR PERCENTILES THAN FOR STATS AND COUNT
key = literal_field(canonical_name + " percentile")
percent = Math.round(s.percentile * 100, decimal=6)
es_query.aggs[key].percentiles.script = s.value.to_es_script(schema).script(schema)
es_query.aggs[key].percentiles.percents += [percent]
s.pull = jx_expression_to_function(key + ".values." + literal_field(text_type(percent)))
elif s.aggregate == "cardinality":
# ES USES DIFFERENT METHOD FOR CARDINALITY
key = canonical_name + " cardinality"
es_query.aggs[key].cardinality.script = s.value.to_es_script(schema).script(schema)
s.pull = jx_expression_to_function(key + ".value")
elif s.aggregate == "stats":
# REGULAR STATS
stats_name = literal_field(canonical_name)
es_query.aggs[stats_name].extended_stats.script = s.value.to_es_script(schema).script(schema)
# GET MEDIAN TOO!
median_name = literal_field(canonical_name + " percentile")
es_query.aggs[median_name].percentiles.script = s.value.to_es_script(schema).script(schema)
es_query.aggs[median_name].percentiles.percents += [50]
s.pull = get_pull_stats(stats_name, median_name)
elif s.aggregate=="union":
# USE TERMS AGGREGATE TO SIMULATE union
stats_name = literal_field(canonical_name)
es_query.aggs[stats_name].terms.script_field = s.value.to_es_script(schema).script(schema)
s.pull = jx_expression_to_function(stats_name + ".buckets.key")
else:
# PULL VALUE OUT OF THE stats AGGREGATE
s.pull = jx_expression_to_function(canonical_name + "." + aggregates[s.aggregate])
es_query.aggs[canonical_name].extended_stats.script = s.value.to_es_script(schema).script(schema)
decoders = get_decoders_by_depth(query)
start = 0
#<TERRIBLE SECTION> THIS IS WHERE WE WEAVE THE where CLAUSE WITH nested
split_where = split_expression_by_depth(query.where, schema=frum.schema)
if len(split_field(frum.name)) > 1:
if any(split_where[2::]):
Log.error("Where clause is too deep")
for d in decoders[1]:
es_query = d.append_query(es_query, start)
start += d.num_columns
if split_where[1]:
#TODO: INCLUDE FILTERS ON EDGES
filter_ = AndOp("and", split_where[1]).to_esfilter(schema)
es_query = Data(
aggs={"_filter": set_default({"filter": filter_}, es_query)}
)
es_query = wrap({
"aggs": {"_nested": set_default(
{"nested": {"path": schema.query_path[0]}},
es_query
)}
})
else:
if any(split_where[1::]):
Log.error("Where clause is too deep")
if decoders:
for d in jx.reverse(decoders[0]):
es_query = d.append_query(es_query, start)
start += d.num_columns
if split_where[0]:
#TODO: INCLUDE FILTERS ON EDGES
filter = AndOp("and", split_where[0]).to_esfilter(schema)
es_query = Data(
aggs={"_filter": set_default({"filter": filter}, es_query)}
)
# </TERRIBLE SECTION>
if not es_query:
es_query = wrap({"query": {"match_all": {}}})
es_query.size = 0
with Timer("ES query time") as es_duration:
result = es_post(es, es_query, query.limit)
try:
format_time = Timer("formatting")
with format_time:
decoders = [d for ds in decoders for d in ds]
result.aggregations.doc_count = coalesce(result.aggregations.doc_count, result.hits.total) # IT APPEARS THE OLD doc_count IS GONE
formatter, groupby_formatter, aggop_formatter, mime_type = format_dispatch[query.format]
if query.edges:
output = formatter(decoders, result.aggregations, start, query, select)
elif query.groupby:
output = groupby_formatter(decoders, result.aggregations, start, query, select)
else:
output = aggop_formatter(decoders, result.aggregations, start, query, select)
output.meta.timing.formatting = format_time.duration
output.meta.timing.es_search = es_duration.duration
output.meta.content_type = mime_type
output.meta.es_query = es_query
return output
except Exception as e:
if query.format not in format_dispatch:
Log.error("Format {{format|quote}} not supported yet", format=query.format, cause=e)
Log.error("Some problem", cause=e)
def es_aggsop(es, frum, query):
query = query.copy() # WE WILL MARK UP THIS QUERY
schema = frum.schema
select = listwrap(query.select)
es_query = Data()
new_select = Data() # MAP FROM canonical_name (USED FOR NAMES IN QUERY) TO SELECT MAPPING
formula = []
for s in select:
if s.aggregate == "count" and isinstance(s.value, Variable) and s.value.var == ".":
if schema.query_path == ".":
s.pull = jx_expression_to_function("doc_count")
else:
s.pull = jx_expression_to_function({"coalesce": ["_nested.doc_count", "doc_count", 0]})
elif isinstance(s.value, Variable):
if s.aggregate == "count":
new_select["count_"+literal_field(s.value.var)] += [s]
else:
new_select[literal_field(s.value.var)] += [s]
else:
formula.append(s)
for canonical_name, many in new_select.items():
for s in many:
es_cols = frum.schema.values(s.value.var)
if s.aggregate == "count":
canonical_names = []
for es_col in es_cols:
cn = literal_field(es_col.es_column + "_count")
canonical_names.append(cn)
es_query.aggs[cn].value_count.field = es_col.es_column
if len(es_cols) == 1:
s.pull = jx_expression_to_function(canonical_names[0] + ".value")
else:
s.pull = jx_expression_to_function({"add": [cn + ".value" for cn in canonical_names]})
elif s.aggregate == "median":
if len(es_cols) > 1:
Log.error("Do not know how to count columns with more than one type (script probably)")
# ES USES DIFFERENT METHOD FOR PERCENTILES
key = literal_field(canonical_name + " percentile")
es_query.aggs[key].percentiles.field = es_cols[0].es_column
es_query.aggs[key].percentiles.percents += [50]
s.pull = jx_expression_to_function(key + ".values.50\.0")
elif s.aggregate == "percentile":
if len(es_cols) > 1:
Log.error("Do not know how to count columns with more than one type (script probably)")
# ES USES DIFFERENT METHOD FOR PERCENTILES
key = literal_field(canonical_name + " percentile")
if isinstance(s.percentile, text_type) or s.percetile < 0 or 1 < s.percentile:
Log.error("Expecting percentile to be a float from 0.0 to 1.0")
percent = Math.round(s.percentile * 100, decimal=6)
es_query.aggs[key].percentiles.field = es_cols[0].es_column
es_query.aggs[key].percentiles.percents += [percent]
s.pull = jx_expression_to_function(key + ".values." + literal_field(text_type(percent)))
elif s.aggregate == "cardinality":
canonical_names = []
for es_col in es_cols:
cn = literal_field(es_col.es_column + "_cardinality")
canonical_names.append(cn)
es_query.aggs[cn].cardinality.field = es_col.es_column
if len(es_cols) == 1:
s.pull = jx_expression_to_function(canonical_names[0] + ".value")
else:
s.pull = jx_expression_to_function({"add": [cn + ".value" for cn in canonical_names], "default": 0})
elif s.aggregate == "stats":
if len(es_cols) > 1:
Log.error("Do not know how to count columns with more than one type (script probably)")
# REGULAR STATS
stats_name = literal_field(canonical_name)
es_query.aggs[stats_name].extended_stats.field = es_cols[0].es_column
# GET MEDIAN TOO!
median_name = literal_field(canonical_name + "_percentile")
es_query.aggs[median_name].percentiles.field = es_cols[0].es_column
es_query.aggs[median_name].percentiles.percents += [50]
s.pull = get_pull_stats(stats_name, median_name)
elif s.aggregate == "union":
pulls = []
for es_col in es_cols:
stats_name = encode_property(es_col.es_column)
if es_col.nested_path[0] == ".":
es_query.aggs[stats_name] = {"terms": {
"field": es_col.es_column,
"size": Math.min(s.limit, MAX_LIMIT)
}}
pulls.append(get_bucket_keys(stats_name))
else:
es_query.aggs[stats_name] = {
"nested": {"path": es_col.nested_path[0]},
"aggs": {"_nested": {"terms": {
"field": es_col.es_column,
"size": Math.min(s.limit, MAX_LIMIT)
}}}
}
pulls.append(get_bucket_keys(stats_name+"._nested"))
if len(pulls) == 0:
s.pull = NULL
elif len(pulls) == 1:
s.pull = pulls[0]
else:
s.pull = lambda row: UNION(
p(row)
for p in pulls
)
else:
if len(es_cols) > 1:
Log.error("Do not know how to count columns with more than one type (script probably)")
# PULL VALUE OUT OF THE stats AGGREGATE
es_query.aggs[literal_field(canonical_name)].extended_stats.field = es_cols[0].es_column
s.pull = jx_expression_to_function({"coalesce": [literal_field(canonical_name) + "." + aggregates[s.aggregate], s.default]})
for i, s in enumerate(formula):
canonical_name = literal_field(s.name)
if isinstance(s.value, TupleOp):
if s.aggregate == "count":
# TUPLES ALWAYS EXIST, SO COUNTING THEM IS EASY
s.pull = "doc_count"
else:
Log.error("{{agg}} is not a supported aggregate over a tuple", agg=s.aggregate)
elif s.aggregate == "count":
es_query.aggs[literal_field(canonical_name)].value_count.script = s.value.partial_eval().to_ruby(schema).script(schema)
s.pull = jx_expression_to_function(literal_field(canonical_name) + ".value")
elif s.aggregate == "median":
# ES USES DIFFERENT METHOD FOR PERCENTILES THAN FOR STATS AND COUNT
key = literal_field(canonical_name + " percentile")
es_query.aggs[key].percentiles.script = s.value.to_ruby(schema).script(schema)
es_query.aggs[key].percentiles.percents += [50]
s.pull = jx_expression_to_function(key + ".values.50\.0")
elif s.aggregate == "percentile":
# ES USES DIFFERENT METHOD FOR PERCENTILES THAN FOR STATS AND COUNT
key = literal_field(canonical_name + " percentile")
percent = Math.round(s.percentile * 100, decimal=6)
es_query.aggs[key].percentiles.script = s.value.to_ruby(schema).script(schema)
es_query.aggs[key].percentiles.percents += [percent]
s.pull = jx_expression_to_function(key + ".values." + literal_field(text_type(percent)))
elif s.aggregate == "cardinality":
# ES USES DIFFERENT METHOD FOR CARDINALITY
key = canonical_name + " cardinality"
es_query.aggs[key].cardinality.script = s.value.to_ruby(schema).script(schema)
s.pull = jx_expression_to_function(key + ".value")
elif s.aggregate == "stats":
# REGULAR STATS
stats_name = literal_field(canonical_name)
es_query.aggs[stats_name].extended_stats.script = s.value.to_ruby(schema).script(schema)
# GET MEDIAN TOO!
median_name = literal_field(canonical_name + " percentile")
es_query.aggs[median_name].percentiles.script = s.value.to_ruby(schema).script(schema)
es_query.aggs[median_name].percentiles.percents += [50]
s.pull = get_pull_stats(stats_name, median_name)
elif s.aggregate=="union":
# USE TERMS AGGREGATE TO SIMULATE union
stats_name = literal_field(canonical_name)
es_query.aggs[stats_name].terms.script_field = s.value.to_ruby(schema).script(schema)
s.pull = jx_expression_to_function(stats_name + ".buckets.key")
else:
# PULL VALUE OUT OF THE stats AGGREGATE
s.pull = jx_expression_to_function(canonical_name + "." + aggregates[s.aggregate])
es_query.aggs[canonical_name].extended_stats.script = s.value.to_ruby(schema).script(schema)
decoders = get_decoders_by_depth(query)
start = 0
#<TERRIBLE SECTION> THIS IS WHERE WE WEAVE THE where CLAUSE WITH nested
split_where = split_expression_by_depth(query.where, schema=frum.schema)
if len(split_field(frum.name)) > 1:
if any(split_where[2::]):
Log.error("Where clause is too deep")
for d in decoders[1]:
es_query = d.append_query(es_query, start)
start += d.num_columns
if split_where[1]:
#TODO: INCLUDE FILTERS ON EDGES
filter_ = AndOp("and", split_where[1]).to_esfilter(schema)
es_query = Data(
aggs={"_filter": set_default({"filter": filter_}, es_query)}
)
es_query = wrap({
"aggs": {"_nested": set_default(
{
"nested": {
"path": schema.query_path
}
},
es_query
)}
})
else:
if any(split_where[1::]):
Log.error("Where clause is too deep")
if decoders:
for d in jx.reverse(decoders[0]):
es_query = d.append_query(es_query, start)
start += d.num_columns
if split_where[0]:
#TODO: INCLUDE FILTERS ON EDGES
filter = AndOp("and", split_where[0]).to_esfilter(schema)
es_query = Data(
aggs={"_filter": set_default({"filter": filter}, es_query)}
)
# </TERRIBLE SECTION>
if not es_query:
es_query = wrap({"query": {"match_all": {}}})
es_query.size = 0
with Timer("ES query time") as es_duration:
result = es_post(es, es_query, query.limit)
try:
format_time = Timer("formatting")
with format_time:
decoders = [d for ds in decoders for d in ds]
result.aggregations.doc_count = coalesce(result.aggregations.doc_count, result.hits.total) # IT APPEARS THE OLD doc_count IS GONE
formatter, groupby_formatter, aggop_formatter, mime_type = format_dispatch[query.format]
if query.edges:
output = formatter(decoders, result.aggregations, start, query, select)
elif query.groupby:
output = groupby_formatter(decoders, result.aggregations, start, query, select)
else:
output = aggop_formatter(decoders, result.aggregations, start, query, select)
output.meta.timing.formatting = format_time.duration
output.meta.timing.es_search = es_duration.duration
output.meta.content_type = mime_type
output.meta.es_query = es_query
return output
except Exception as e:
if query.format not in format_dispatch:
Log.error("Format {{format|quote}} not supported yet", format=query.format, cause=e)
Log.error("Some problem", cause=e)
where = None
join_type = SQL_LEFT_JOIN if query_edge.allowNulls else SQL_INNER_JOIN
on_clause = SQL_AND.join(
join_column(edge_alias, k) + " = " + sql
for k, (t, sql) in zip(domain_names, edge_values)
)
null_on_clause = None
elif query_edge.domain.type == "range":
domain_name = quote_column("d" + text_type(edge_index) + "c0")
domain_names = [domain_name] # ONLY EVER SEEN ONE DOMAIN VALUE, DOMAIN TUPLES CERTAINLY EXIST
d = query_edge.domain
if d.max == None or d.min == None or d.min == d.max:
Log.error("Invalid range: {{range|json}}", range=d)
if len(edge_names) == 1:
domain = self._make_range_domain(domain=d, column_name=domain_name)
limit = Math.min(query.limit, query_edge.domain.limit)
domain += (
SQL_ORDERBY + sql_list(vals) +
SQL_LIMIT + text_type(limit)
)
where = None
join_type = SQL_LEFT_JOIN if query_edge.allowNulls else SQL_INNER_JOIN
on_clause = SQL_AND.join(
join_column(edge_alias, k) + " <= " + v + SQL_AND +
v + " < (" + join_column(edge_alias, k) + " + " + text_type(
d.interval) + ")"
for k, (t, v) in zip(domain_names, edge_values)
)
null_on_clause = None
elif query_edge.range:
def es_aggsop(es, frum, query):
select = wrap([s.copy() for s in listwrap(query.select)])
es_column_map = {
c.name: unwraplist(c.es_column)
for c in frum.schema.columns
}
es_query = Data()
new_select = Data(
) #MAP FROM canonical_name (USED FOR NAMES IN QUERY) TO SELECT MAPPING
formula = []
for s in select:
if s.aggregate == "count" and isinstance(
s.value, Variable) and s.value.var == ".":
s.pull = "doc_count"
elif isinstance(s.value, Variable):
if s.value.var == ".":
if frum.typed:
# STATISITCAL AGGS IMPLY $value, WHILE OTHERS CAN BE ANYTHING
if s.aggregate in NON_STATISTICAL_AGGS:
#TODO: HANDLE BOTH $value AND $objects TO COUNT
Log.error("do not know how to handle")
else:
s.value.var = "$value"
new_select["$value"] += [s]
else:
if s.aggregate in NON_STATISTICAL_AGGS:
#TODO: WE SHOULD BE ABLE TO COUNT, BUT WE MUST *OR* ALL LEAF VALUES TO DO IT
Log.error("do not know how to handle")
else:
Log.error(
'Not expecting ES to have a value at "." which {{agg}} can be applied',
agg=s.aggregate)
elif s.aggregate == "count":
s.value = s.value.map(es_column_map)
new_select["count_" + literal_field(s.value.var)] += [s]
else:
s.value = s.value.map(es_column_map)
new_select[literal_field(s.value.var)] += [s]
else:
formula.append(s)
for canonical_name, many in new_select.items():
representative = many[0]
if representative.value.var == ".":
Log.error("do not know how to handle")
else:
field_name = representative.value.var
# canonical_name=literal_field(many[0].name)
for s in many:
if s.aggregate == "count":
es_query.aggs[literal_field(
canonical_name)].value_count.field = field_name
s.pull = literal_field(canonical_name) + ".value"
elif s.aggregate == "median":
# ES USES DIFFERENT METHOD FOR PERCENTILES
key = literal_field(canonical_name + " percentile")
es_query.aggs[key].percentiles.field = field_name
es_query.aggs[key].percentiles.percents += [50]
s.pull = key + ".values.50\.0"
elif s.aggregate == "percentile":
# ES USES DIFFERENT METHOD FOR PERCENTILES
key = literal_field(canonical_name + " percentile")
if isinstance(
s.percentile,
basestring) or s.percetile < 0 or 1 < s.percentile:
Log.error(
"Expecting percentile to be a float from 0.0 to 1.0")
percent = Math.round(s.percentile * 100, decimal=6)
es_query.aggs[key].percentiles.field = field_name
es_query.aggs[key].percentiles.percents += [percent]
s.pull = key + ".values." + literal_field(unicode(percent))
elif s.aggregate == "cardinality":
# ES USES DIFFERENT METHOD FOR CARDINALITY
key = literal_field(canonical_name + " cardinality")
es_query.aggs[key].cardinality.field = field_name
s.pull = key + ".value"
elif s.aggregate == "stats":
# REGULAR STATS
stats_name = literal_field(canonical_name)
es_query.aggs[stats_name].extended_stats.field = field_name
# GET MEDIAN TOO!
median_name = literal_field(canonical_name + " percentile")
es_query.aggs[median_name].percentiles.field = field_name
es_query.aggs[median_name].percentiles.percents += [50]
s.pull = {
"count": stats_name + ".count",
"sum": stats_name + ".sum",
"min": stats_name + ".min",
"max": stats_name + ".max",
"avg": stats_name + ".avg",
"sos": stats_name + ".sum_of_squares",
"std": stats_name + ".std_deviation",
"var": stats_name + ".variance",
"median": median_name + ".values.50\.0"
}
elif s.aggregate == "union":
# USE TERMS AGGREGATE TO SIMULATE union
stats_name = literal_field(canonical_name)
es_query.aggs[stats_name].terms.field = field_name
es_query.aggs[stats_name].terms.size = Math.min(
s.limit, MAX_LIMIT)
s.pull = stats_name + ".buckets.key"
else:
# PULL VALUE OUT OF THE stats AGGREGATE
es_query.aggs[literal_field(
canonical_name)].extended_stats.field = field_name
s.pull = literal_field(canonical_name) + "." + aggregates1_4[
s.aggregate]
for i, s in enumerate(formula):
canonical_name = literal_field(s.name)
abs_value = s.value.map(es_column_map)
if s.aggregate == "count":
es_query.aggs[literal_field(
canonical_name)].value_count.script = abs_value.to_ruby()
s.pull = literal_field(canonical_name) + ".value"
elif s.aggregate == "median":
# ES USES DIFFERENT METHOD FOR PERCENTILES THAN FOR STATS AND COUNT
key = literal_field(canonical_name + " percentile")
es_query.aggs[key].percentiles.script = abs_value.to_ruby()
es_query.aggs[key].percentiles.percents += [50]
s.pull = key + ".values.50\.0"
elif s.aggregate == "percentile":
# ES USES DIFFERENT METHOD FOR PERCENTILES THAN FOR STATS AND COUNT
key = literal_field(canonical_name + " percentile")
percent = Math.round(s.percentile * 100, decimal=6)
es_query.aggs[key].percentiles.script = abs_value.to_ruby()
es_query.aggs[key].percentiles.percents += [percent]
s.pull = key + ".values." + literal_field(unicode(percent))
elif s.aggregate == "cardinality":
# ES USES DIFFERENT METHOD FOR CARDINALITY
key = canonical_name + " cardinality"
es_query.aggs[key].cardinality.script = abs_value.to_ruby()
s.pull = key + ".value"
elif s.aggregate == "stats":
# REGULAR STATS
stats_name = literal_field(canonical_name)
es_query.aggs[
stats_name].extended_stats.script = abs_value.to_ruby()
# GET MEDIAN TOO!
median_name = literal_field(canonical_name + " percentile")
es_query.aggs[median_name].percentiles.script = abs_value.to_ruby()
es_query.aggs[median_name].percentiles.percents += [50]
s.pull = {
"count": stats_name + ".count",
"sum": stats_name + ".sum",
"min": stats_name + ".min",
"max": stats_name + ".max",
"avg": stats_name + ".avg",
"sos": stats_name + ".sum_of_squares",
"std": stats_name + ".std_deviation",
"var": stats_name + ".variance",
"median": median_name + ".values.50\.0"
}
elif s.aggregate == "union":
# USE TERMS AGGREGATE TO SIMULATE union
stats_name = literal_field(canonical_name)
es_query.aggs[stats_name].terms.script_field = abs_value.to_ruby()
s.pull = stats_name + ".buckets.key"
else:
# PULL VALUE OUT OF THE stats AGGREGATE
s.pull = canonical_name + "." + aggregates1_4[s.aggregate]
es_query.aggs[
canonical_name].extended_stats.script = abs_value.to_ruby()
decoders = get_decoders_by_depth(query)
start = 0
vars_ = query.where.vars()
#<TERRIBLE SECTION> THIS IS WHERE WE WEAVE THE where CLAUSE WITH nested
split_where = split_expression_by_depth(query.where,
schema=frum.schema,
map_=es_column_map)
if len(split_field(frum.name)) > 1:
if any(split_where[2::]):
Log.error("Where clause is too deep")
for d in decoders[1]:
es_query = d.append_query(es_query, start)
start += d.num_columns
if split_where[1]:
#TODO: INCLUDE FILTERS ON EDGES
filter_ = simplify_esfilter(
AndOp("and", split_where[1]).to_esfilter())
es_query = Data(
aggs={"_filter": set_default({"filter": filter_}, es_query)})
es_query = wrap({
"aggs": {
"_nested":
set_default({"nested": {
"path": frum.query_path
}}, es_query)
}
})
else:
if any(split_where[1::]):
Log.error("Where clause is too deep")
for d in decoders[0]:
es_query = d.append_query(es_query, start)
start += d.num_columns
if split_where[0]:
#TODO: INCLUDE FILTERS ON EDGES
filter = simplify_esfilter(AndOp("and", split_where[0]).to_esfilter())
es_query = Data(
aggs={"_filter": set_default({"filter": filter}, es_query)})
# </TERRIBLE SECTION>
if not es_query:
es_query = wrap({"query": {"match_all": {}}})
es_query.size = 0
with Timer("ES query time") as es_duration:
result = es09.util.post(es, es_query, query.limit)
try:
format_time = Timer("formatting")
with format_time:
decoders = [d for ds in decoders for d in ds]
result.aggregations.doc_count = coalesce(
result.aggregations.doc_count,
result.hits.total) # IT APPEARS THE OLD doc_count IS GONE
formatter, groupby_formatter, aggop_formatter, mime_type = format_dispatch[
query.format]
if query.edges:
output = formatter(decoders, result.aggregations, start, query,
select)
elif query.groupby:
output = groupby_formatter(decoders, result.aggregations,
start, query, select)
else:
output = aggop_formatter(decoders, result.aggregations, start,
query, select)
output.meta.timing.formatting = format_time.duration
output.meta.timing.es_search = es_duration.duration
output.meta.content_type = mime_type
output.meta.es_query = es_query
return output
except Exception, e:
if query.format not in format_dispatch:
Log.error("Format {{format|quote}} not supported yet",
format=query.format,
cause=e)
Log.error("Some problem", e)
