def int2Partition(value):
if Math.round(value) == 0:
return edge.domain.NULL
d = datetime(str(value)[:4:], str(value)[-2:], 1)
d = d.addMilli(offset)
return edge.domain.getPartByKey(d)
def int2Partition(value):
if Math.round(value) == 0:
return edge.domain.NULL
d = datetime(str(value)[:4:], str(value)[-2:], 1)
d = d.addMilli(offset)
return edge.domain.getPartByKey(d)
def request(method, url, zip=None, retry=None, **kwargs):
"""
JUST LIKE requests.request() BUT WITH DEFAULT HEADERS AND FIXES
DEMANDS data IS ONE OF:
* A JSON-SERIALIZABLE STRUCTURE, OR
* LIST OF JSON-SERIALIZABLE STRUCTURES, OR
* None
Parameters
* zip - ZIP THE REQUEST BODY, IF BIG ENOUGH
* json - JSON-SERIALIZABLE STRUCTURE
* retry - {"times": x, "sleep": y} STRUCTURE
THE BYTE_STRINGS (b"") ARE NECESSARY TO PREVENT httplib.py FROM **FREAKING OUT**
IT APPEARS requests AND httplib.py SIMPLY CONCATENATE STRINGS BLINDLY, WHICH
INCLUDES url AND headers
"""
global _warning_sent
if not default_headers and not _warning_sent:
_warning_sent = True
Log.warning(
"The pyLibrary.env.http module was meant to add extra "
"default headers to all requests, specifically the 'Referer' "
"header with a URL to the project. Use the `pyLibrary.debug.constants.set()` "
"function to set `pyLibrary.env.http.default_headers`"
)
if isinstance(url, list):
# TRY MANY URLS
failures = []
for remaining, u in jx.countdown(url):
try:
response = request(method, u, zip=zip, retry=retry, **kwargs)
if Math.round(response.status_code, decimal=-2) not in [400, 500]:
return response
if not remaining:
return response
except Exception, e:
e = Except.wrap(e)
failures.append(e)
Log.error("Tried {{num}} urls", num=len(url), cause=failures)
def request(method, url, zip=None, retry=None, **kwargs):
"""
JUST LIKE requests.request() BUT WITH DEFAULT HEADERS AND FIXES
DEMANDS data IS ONE OF:
* A JSON-SERIALIZABLE STRUCTURE, OR
* LIST OF JSON-SERIALIZABLE STRUCTURES, OR
* None
Parameters
* zip - ZIP THE REQUEST BODY, IF BIG ENOUGH
* json - JSON-SERIALIZABLE STRUCTURE
* retry - {"times": x, "sleep": y} STRUCTURE
THE BYTE_STRINGS (b"") ARE NECESSARY TO PREVENT httplib.py FROM **FREAKING OUT**
IT APPEARS requests AND httplib.py SIMPLY CONCATENATE STRINGS BLINDLY, WHICH
INCLUDES url AND headers
"""
global _warning_sent
if not default_headers and not _warning_sent:
_warning_sent = True
Log.warning(
"The pyLibrary.env.http module was meant to add extra "
"default headers to all requests, specifically the 'Referer' "
"header with a URL to the project. Use the `pyLibrary.debug.constants.set()` "
"function to set `pyLibrary.env.http.default_headers`")
if isinstance(url, list):
# TRY MANY URLS
failures = []
for remaining, u in jx.countdown(url):
try:
response = request(method, u, zip=zip, retry=retry, **kwargs)
if Math.round(response.status_code,
decimal=-2) not in [400, 500]:
return response
if not remaining:
return response
except Exception, e:
e = Except.wrap(e)
failures.append(e)
Log.error("Tried {{num}} urls", num=len(url), cause=failures)
def int2Partition(value):
if Math.round(value) == numPartitions:
return edge.domain.NULL
return edge.domain.getPartByKey((value * edge.domain.interval) + offset)
def int2Partition(value):
if Math.round(value) == numPartitions:
return edge.domain.NULL
return edge.domain.getPartByKey(ref.add(edge.domain.interval.multiply(value)))
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.all_columns}
es_query = Dict()
new_select = Dict() #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, 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 = Dict(
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 = Dict(
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)
def round(self, interval, decimal=0):
output = self / interval
output = Math.round(output, decimal)
return output
def round(self, interval, decimal=0):
output = self / interval
output = Math.round(output, decimal)
return output
def transform(self, id, datazilla):
try:
r = datazilla.json_blob
#ADD DATAZILLA MARKUP
r.datazilla = {
"id": id,
"date_loaded": datazilla.date_loaded * 1000,
"error_flag": datazilla.error_flag,
"test_run_id": datazilla.test_run_id,
"processed_flag": datazilla.processed_flag,
"error_msg": datazilla.error_msg
}
#CONVERT UNIX TIMESTAMP TO MILLISECOND TIMESTAMP
r.testrun.date *= 1000
def mainthread_transform(r):
if r == None:
return None
output = Struct()
for i in r.mainthread_readbytes:
output[literal_field(i[1])].name = i[1]
output[literal_field(i[1])].readbytes = i[0]
r.mainthread_readbytes = None
for i in r.mainthread_writebytes:
output[literal_field(i[1])].name = i[1]
output[literal_field(i[1])].writebytes = i[0]
r.mainthread_writebytes = None
for i in r.mainthread_readcount:
output[literal_field(i[1])].name = i[1]
output[literal_field(i[1])].readcount = i[0]
r.mainthread_readcount = None
for i in r.mainthread_writecount:
output[literal_field(i[1])].name = i[1]
output[literal_field(i[1])].writecount = i[0]
r.mainthread_writecount = None
r.mainthread = output.values()
mainthread_transform(r.results_aux)
mainthread_transform(r.results_xperf)
#ADD PUSH LOG INFO
try:
branch = r.test_build.branch
if branch.endswith("-Non-PGO"):
r.test_build.branch = branch
r.test_build.pgo = False
branch = branch[0:-8]
else:
r.test_build.pgo = True
with Profiler("get from pushlog"):
if not self.pushlog:
#NO PUSHLOG MEANS WE DO NOTHING TO MARKUP TEST RESULTS
pass
elif self.pushlog[branch]:
possible_dates = self.pushlog[branch][r.test_build.revision]
if possible_dates:
r.test_build.push_date = int(Math.round(possible_dates[0].date * 1000))
else:
if r.test_build.revision == 'NULL':
r.test_build.no_pushlog = True # OOPS! SOMETHING BROKE
elif CNV.milli2datetime(Math.min(r.testrun.date, r.datazilla.date_loaded)) < PUSHLOG_TOO_OLD:
Log.note("{{branch}} @ {{revision}} has no pushlog, transforming anyway", r.test_build)
r.test_build.no_pushlog = True
else:
Log.note("{{branch}} @ {{revision}} has no pushlog, try again later", r.test_build)
return [] # TRY AGAIN LATER
else:
with self.locker:
if branch not in self.unknown_branches:
Log.note("Whole branch {{branch}} has no pushlog", {"branch":branch})
self.unknown_branches.add(branch)
if CNV.milli2datetime(Math.min(r.testrun.date, r.datazilla.date_loaded)) < PUSHLOG_TOO_OLD:
r.test_build.no_pushlog = True
else:
r.test_build.no_pushlog = True
#return [r] #TODO: DO THIS IF WE FIGURE OUT HOW TO HANDLE THE VERY LARGE NUMBER OF RESULTS WITH NO PUSHLOG
except Exception, e:
Log.warning("{{branch}} @ {{revision}} has no pushlog", r.test_build, e)
new_records = []
# RECORD THE UNKNOWN PART OF THE TEST RESULTS
remainder = r.copy()
remainder.results = None
if len(remainder.keys()) > 4:
new_records.append(remainder)
#RECORD TEST RESULTS
total = StructList()
if r.testrun.suite in ["dromaeo_css", "dromaeo_dom"]:
#dromaeo IS SPECIAL, REPLICATES ARE IN SETS OF FIVE
#RECORD ALL RESULTS
for i, (test_name, replicates) in enumerate(r.results.items()):
for g, sub_results in Q.groupby(replicates, size=5):
new_record = Struct(
test_machine=r.test_machine,
datazilla=r.datazilla,
testrun=r.testrun,
test_build=r.test_build,
result={
"test_name": unicode(test_name) + "." + unicode(g),
"ordering": i,
"samples": sub_results
}
)
try:
s = stats(sub_results)
new_record.result.stats = s
total.append(s)
except Exception, e:
Log.warning("can not reduce series to moments", e)
new_records.append(new_record)
def int2Partition(value):
if Math.round(value) == numPartitions:
return edge.domain.NULL
return edge.domain.getPartByKey((value * edge.domain.interval) + offset)
def int2Partition(value):
if Math.round(value) == numPartitions:
return edge.domain.NULL
return edge.domain.getPartByKey(ref.add(edge.domain.interval.multiply(value)))
def query(path):
with CProfiler():
try:
with Timer("total duration") as query_timer:
preamble_timer = Timer("preamble")
with preamble_timer:
if flask.request.headers.get("content-length",
"") in ["", "0"]:
# ASSUME A BROWSER HIT THIS POINT, SEND text/html RESPONSE BACK
return Response(BLANK,
status=400,
headers={"Content-Type": "text/html"})
elif int(flask.request.headers["content-length"]
) > QUERY_SIZE_LIMIT:
Log.error("Query is too large")
request_body = flask.request.get_data().strip()
text = convert.utf82unicode(request_body)
text = replace_vars(text, flask.request.args)
data = convert.json2value(text)
record_request(flask.request, data, None, None)
if data.meta.testing:
_test_mode_wait(data)
translate_timer = Timer("translate")
with translate_timer:
if data.sql:
data = parse_sql(data.sql)
frum = wrap_from(data['from'])
result = jx.run(data, frum=frum)
if isinstance(
result, Container
): #TODO: REMOVE THIS CHECK, jx SHOULD ALWAYS RETURN Containers
result = result.format(data.format)
save_timer = Timer("save")
with save_timer:
if data.meta.save:
try:
result.meta.saved_as = save_query.query_finder.save(
data)
except Exception, e:
Log.warning("Unexpected save problem", cause=e)
result.meta.timing.preamble = Math.round(
preamble_timer.duration.seconds, digits=4)
result.meta.timing.translate = Math.round(
translate_timer.duration.seconds, digits=4)
result.meta.timing.save = Math.round(
save_timer.duration.seconds, digits=4)
result.meta.timing.total = "{{TOTAL_TIME}}" # TIMING PLACEHOLDER
with Timer("jsonification") as json_timer:
response_data = convert.unicode2utf8(
convert.value2json(result))
with Timer("post timer"):
# IMPORTANT: WE WANT TO TIME OF THE JSON SERIALIZATION, AND HAVE IT IN THE JSON ITSELF.
# WE CHEAT BY DOING A (HOPEFULLY FAST) STRING REPLACEMENT AT THE VERY END
timing_replacement = b'"total": ' + str(Math.round(query_timer.duration.seconds, digits=4)) +\
b', "jsonification": ' + str(Math.round(json_timer.duration.seconds, digits=4))
response_data = response_data.replace(
b'"total": "{{TOTAL_TIME}}"', timing_replacement)
Log.note("Response is {{num}} bytes in {{duration}}",
num=len(response_data),
duration=query_timer.duration)
return Response(
response_data,
status=200,
headers={"Content-Type": result.meta.content_type})
except Exception, e:
e = Except.wrap(e)
return _send_error(query_timer, request_body, e)
