def keys(self, prefix=None):
path = jx.reverse(etl2path(key2etl(prefix)))
result = self.es.search({
"fields": ["_id"],
"query": {
"filtered": {
"query": {
"match_all": {}
},
"filter": {
"and": [{
"term": {
"etl" + (".source" * i) + ".id": v
}
} for i, v in enumerate(path)]
}
}
}
})
if result.hits.hits:
return set(result.hits.hits._id)
else:
return set()
def typed_encode(value, flake):
"""
RETURN (typed_value, flake_update, added_nested) TUPLES
:param value: THE RECORD TO CONVERT TO STRICT TYPED FORM
:param flake: LOOKUP SCHEMA, WILL BE UPDATED WITH CHANGES
:return: (record, update, nested) TUPLE
"""
_ = flake.columns # ENSURE WE HAVE INTERNAL STRUCTURES FILLED
output, update, nested = _typed_encode(value, flake.schema)
if update:
# REFRESH COLUMNS
flake._columns = None
_ = flake.columns
worker = to_data(output)
for path, field in flake._top_level_fields.items():
worker[field] = worker[path]
worker[path] = None
# DO NOT LEAVE ANY EMPTY OBJECT RESIDUE
_path = split_field(path)
for i, _ in jx.reverse(enumerate(_path)):
sub_path = join_field(_path[:i])
v = worker[sub_path]
if is_data(v) and not worker[sub_path].keys():
worker[sub_path] = None
else:
break
return output, update, nested
def keys(self, prefix=None):
from activedata_etl import etl2path, key2etl
path = jx.reverse(etl2path(key2etl(prefix)))
if self.cluster.version.startswith(("5.", "6.")):
stored_fields = "stored_fields"
else:
stored_fields = "fields"
result = self.es.search({
stored_fields: ["_id"],
"query": {
"bool": {
"query": {
"match_all": {}
},
"filter": {
"and": [{
"term": {
"etl" + (".source" * i) + ".id": v
}
} for i, v in enumerate(path)]
}
}
}
})
if result.hits.hits:
return set(result.hits.hits._id)
else:
return set()
def _reload_columns(self, table_desc, after):
"""
:param alias: A REAL ALIAS (OR NAME OF INDEX THAT HAS NO ALIAS)
:param after: ENSURE DATA IS YOUNGER THAN after
:return:
"""
# FIND ALL INDEXES OF ALIAS
alias = table_desc.name
canonical_index = self.es_cluster.get_best_matching_index(alias).index
metadata = self.es_cluster.get_metadata(after=after)
props = [
(self.es_cluster.get_index(index=i, type=t, debug=DEBUG), t, m.properties)
for i, d in metadata.indices.items()
if alias in d.aliases
for t, m in [_get_best_type_from_mapping(d.mappings)]
]
# CONFIRM ALL COLUMNS ARE SAME, FIX IF NOT
dirty = False
all_comparisions = list(jx.pairwise(props)) + list(jx.pairwise(jx.reverse(props)))
# NOTICE THE SAME (index, type, properties) TRIPLE FROM ABOVE
for (i1, t1, p1), (i2, t2, p2) in all_comparisions:
diff = elasticsearch.diff_schema(p2, p1)
if not self.settings.read_only:
for d in diff:
dirty = True
i1.add_property(*d)
if dirty:
metadata = self.es_cluster.get_metadata(after=Date.now())
meta = metadata.indices[literal_field(canonical_index)]
data_type, mapping = _get_best_type_from_mapping(meta.mappings)
mapping.properties["_id"] = {"type": "string", "index": "not_analyzed"}
columns = self._parse_properties(alias, mapping)
table_desc.last_updated = self.es_cluster.metatdata_last_updated
# ASK FOR COLUMNS TO BE RE-SCANNED
rescan = [
(c, after)
for c in columns
if c.es_index != META_COLUMNS_NAME and (
c.cardinality == None or
not (c.last_updated > after)
)
]
self.todo.extend(rescan)
DEBUG and Log.note("asked for {{num}} columns to be rescanned", num=len(rescan))
return columns
def read_db(self):
"""
PULL SCHEMA FROM DATABASE, BUILD THE MODEL
:return: None
"""
# FIND ALL TABLES
result = self.db.query(
"SELECT * FROM sqlite_master WHERE type='table' ORDER BY name")
tables = wrap([{k: d[i]
for i, k in enumerate(result.header)}
for d in result.data])
tables_found = False
for table in tables:
if table.name.startswith("__"):
continue
tables_found = True
nested_path = [
join_field(split_field(tab.name)[1:])
for tab in jx.reverse(tables)
if startswith_field(table.name, tab.name)
]
self.add_table_to_schema(nested_path)
# LOAD THE COLUMNS
command = "PRAGMA table_info" + sql_iso(quote_column(table.name))
details = self.db.query(command)
for cid, name, dtype, notnull, dfft_value, pk in details.data:
if name.startswith("__"):
continue
cname, ctype = untyped_column(name)
column = Column(names={
np: relative_field(cname, np)
for np in nested_path
},
type=coalesce(
ctype, {
"TEXT": "string",
"REAL": "number",
"INTEGER": "integer"
}.get(dtype)),
nested_path=nested_path,
es_column=name,
es_index=table.name)
self.add_column_to_schema(column)
return tables_found
def sort_edges(query, prop):
ordered_edges = []
remaining_edges = getattr(query, prop)
for s in jx.reverse(query.sort):
for e in remaining_edges:
if e.value == s.value:
if isinstance(e.domain, SetDomain):
pass # ALREADY SORTED?
else:
e.domain.sort = s.sort
ordered_edges.append(e)
remaining_edges.remove(e)
break
else:
Log.error("Can not sort by {{expr}}, can only sort by an existing edge expression", expr=s.value)
ordered_edges.extend(remaining_edges)
for i, o in enumerate(ordered_edges):
o.dim = i # REORDER THE EDGES
return ordered_edges
def _reload_columns(self, table_desc):
"""
:param alias: A REAL ALIAS (OR NAME OF INDEX THAT HAS NO ALIAS)
:return:
"""
# FIND ALL INDEXES OF ALIAS
es_last_updated = self.es_cluster.metatdata_last_updated
alias = table_desc.name
canonical_index = self.es_cluster.get_best_matching_index(alias).index
es_metadata_update_required = not (table_desc.timestamp <
es_last_updated)
metadata = self.es_cluster.get_metadata(
force=es_metadata_update_required)
props = [(self.es_cluster.get_index(index=i, type=t,
debug=DEBUG), t, m.properties)
for i, d in metadata.indices.items() if alias in d.aliases
for t, m in [_get_best_type_from_mapping(d.mappings)]]
# CONFIRM ALL COLUMNS ARE SAME, FIX IF NOT
dirty = False
all_comparisions = list(jx.pairwise(props)) + list(
jx.pairwise(jx.reverse(props)))
# NOTICE THE SAME (index, type, properties) TRIPLE FROM ABOVE
for (i1, t1, p1), (i2, t2, p2) in all_comparisions:
diff = elasticsearch.diff_schema(p2, p1)
if not self.settings.read_only:
for d in diff:
dirty = True
i1.add_property(*d)
meta = self.es_cluster.get_metadata(
force=dirty).indices[canonical_index]
data_type, mapping = _get_best_type_from_mapping(meta.mappings)
mapping.properties["_id"] = {"type": "string", "index": "not_analyzed"}
columns = self._parse_properties(alias, mapping)
table_desc.timestamp = es_last_updated
return columns
def keys(self, prefix=None):
path = jx.reverse(etl2path(key2etl(prefix)))
if self.cluster.version.startswith(("5.", "6.")):
stored_fields = "stored_fields"
else:
stored_fields = "fields"
result = self.es.search({
stored_fields: ["_id"],
"query": {
"bool": {
"query": {"match_all": {}},
"filter": {"and": [{"term": {"etl" + (".source" * i) + ".id": v}} for i, v in enumerate(path)]}
}
}
})
if result.hits.hits:
return set(result.hits.hits._id)
else:
return set()
def _reload_columns(self, table_desc):
"""
:param alias: A REAL ALIAS (OR NAME OF INDEX THAT HAS NO ALIAS)
:return:
"""
# FIND ALL INDEXES OF ALIAS
es_last_updated = self.es_cluster.metatdata_last_updated
alias = table_desc.name
canonical_index = self.es_cluster.get_best_matching_index(alias).index
update_required = not (table_desc.timestamp < es_last_updated)
metadata = self.es_cluster.get_metadata(force=update_required)
indexes = self.index_to_alias.get_domain(alias)
props = [
(self.es_cluster.get_index(index=i, type=t, debug=DEBUG), t, m.properties)
for i, d in metadata.indices.items()
if i in indexes
for t, m in [_get_best_type_from_mapping(d.mappings)]
]
# CONFIRM ALL COLUMNS ARE SAME, FIX IF NOT
dirty = False
all_comparisions = list(jx.pairwise(props)) + list(jx.pairwise(jx.reverse(props)))
# NOTICE THE SAME (index, type, properties) TRIPLE FROM ABOVE
for (i1, t1, p1), (i2, t2, p2) in all_comparisions:
diff = elasticsearch.diff_schema(p2, p1)
if not self.settings.read_only:
for d in diff:
dirty = True
i1.add_property(*d)
meta = self.es_cluster.get_metadata(force=dirty).indices[canonical_index]
data_type, mapping = _get_best_type_from_mapping(meta.mappings)
mapping.properties["_id"] = {"type": "string", "index": "not_analyzed"}
self._parse_properties(alias, mapping, meta)
table_desc.timestamp = es_last_updated
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.tdigest.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:
script = {"scripted_metric": {
'init_script': 'params._agg.terms = new HashSet()',
'map_script': 'for (v in doc['+quote(column.es_column)+'].values) params._agg.terms.add(v);',
'combine_script': 'return params._agg.terms.toArray()',
'reduce_script': 'HashSet output = new HashSet(); for (a in params._aggs) { if (a!=null) for (v in a) {output.add(v)} } return output.toArray()',
}}
stats_name = encode_property(column.es_column)
if column.nested_path[0] == ".":
es_query.aggs[stats_name] = script
pulls.append(jx_expression_to_function(stats_name + ".value"))
else:
es_query.aggs[stats_name] = {
"nested": {"path": column.nested_path[0]},
"aggs": {"_nested": script}
}
pulls.append(jx_expression_to_function(stats_name + "._nested.value"))
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)")
elif len(columns) <1:
# PULL VALUE OUT OF THE stats AGGREGATE
s.pull = jx_expression_to_function({"null":{}})
else:
# 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"
elif s.aggregate in ('max', 'maximum', 'min', 'minimum'):
if s.aggregate in ('max', 'maximum'):
dir = 1
op = "max"
else:
dir = -1
op = 'min'
nully = TupleOp("tuple", [NULL]*len(s.value.terms)).partial_eval().to_es_script(schema).expr
selfy = s.value.partial_eval().to_es_script(schema).expr
script = {"scripted_metric": {
'init_script': 'params._agg.best = ' + nully + ';',
'map_script': 'params._agg.best = ' + expand_template(MAX_OF_TUPLE, {"expr1": "params._agg.best", "expr2": selfy, "dir": dir, "op": op}) + ";",
'combine_script': 'return params._agg.best',
'reduce_script': 'return params._aggs.stream().max(' + expand_template(COMPARE_TUPLE, {"dir": dir, "op": op}) + ').get()',
}}
if schema.query_path[0] == ".":
es_query.aggs[canonical_name] = script
s.pull = jx_expression_to_function(literal_field(canonical_name) + ".value")
else:
es_query.aggs[canonical_name] = {
"nested": {"path": schema.query_path[0]},
"aggs": {"_nested": script}
}
s.pull = jx_expression_to_function(literal_field(canonical_name) + "._nested.value")
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]
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]
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:
script = {"scripted_metric": {
'init_script': 'params._agg.terms = new HashSet()',
'map_script': 'for (v in doc['+quote(column.es_column)+'].values) params._agg.terms.add(v)',
'combine_script': 'return params._agg.terms.toArray()',
'reduce_script': 'HashSet output = new HashSet(); for (a in params._aggs) { if (a!=null) for (v in a) {output.add(v)} } return output.toArray()',
}}
stats_name = encode_property(column.es_column)
if column.nested_path[0] == ".":
es_query.aggs[stats_name] = script
pulls.append(jx_expression_to_function(stats_name + ".value"))
else:
es_query.aggs[stats_name] = {
"nested": {"path": column.nested_path[0]},
"aggs": {"_nested": script}
}
pulls.append(jx_expression_to_function(stats_name + "._nested.value"))
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)")
elif len(columns) <1:
# PULL VALUE OUT OF THE stats AGGREGATE
s.pull = jx_expression_to_function({"null":{}})
else:
# 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"
elif s.aggregate in ('max', 'maximum', 'min', 'minimum'):
if s.aggregate in ('max', 'maximum'):
dir = 1
op = "max"
else:
dir = -1
op = 'min'
nully = TupleOp("tuple", [NULL]*len(s.value.terms)).partial_eval().to_es_script(schema).expr
selfy = s.value.partial_eval().to_es_script(schema).expr
script = {"scripted_metric": {
'init_script': 'params._agg.best = ' + nully + ';',
'map_script': 'params._agg.best = ' + expand_template(MAX_OF_TUPLE, {"expr1": "params._agg.best", "expr2": selfy, "dir": dir, "op": op}) + ";",
'combine_script': 'return params._agg.best',
'reduce_script': 'return params._aggs.stream().max(' + expand_template(COMPARE_TUPLE, {"dir": dir, "op": op}) + ').get()',
}}
if schema.query_path[0] == ".":
es_query.aggs[canonical_name] = script
s.pull = jx_expression_to_function(literal_field(canonical_name) + ".value")
else:
es_query.aggs[canonical_name] = {
"nested": {"path": schema.query_path[0]},
"aggs": {"_nested": script}
}
s.pull = jx_expression_to_function(literal_field(canonical_name) + "._nested.value")
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)
