def get_value_summary(cls,
ruleset=None,
contact_field=None,
filters=None,
segment=None):
"""
Returns the results for the passed in ruleset or contact field given the passed in filters and segments.
Filters are expected in the following formats:
{ field: rulesetId, categories: ["Red", "Blue", "Yellow"] }
Segments are expected in these formats instead:
{ ruleset: 1515, categories: ["Red", "Blue"] } // segmenting by another field, for those categories
{ groups: 124,151,151 } // segment by each each group in the passed in ids
{ location: "State", parent: null } // segment for each admin boundary within the parent
{ contact_field: "Country", values: ["US", "EN", "RW"] } // segment by a contact field for these values
"""
from temba.contacts.models import ContactGroup, ContactField
from temba.flows.models import TrueTest, RuleSet
# start = time.time()
results = []
if (not ruleset and not contact_field) or (
ruleset and contact_field): # pragma: needs cover
raise ValueError("Must specify either a RuleSet or Contact field.")
org = ruleset.flow.org if ruleset else contact_field.org
open_ended = ruleset and ruleset.ruleset_type == RuleSet.TYPE_WAIT_MESSAGE and len(
ruleset.get_rules()) == 1
# default our filters to an empty list if None are passed in
if filters is None:
filters = []
# build the kwargs for our subcall
kwargs = dict(ruleset=ruleset,
contact_field=contact_field,
filters=filters)
# this is our list of dependencies, that is things that will blow away our results
dependencies = set()
fingerprint_dict = dict(filters=filters, segment=segment)
if ruleset:
fingerprint_dict['ruleset'] = ruleset.id
dependencies.add(RULESET_KEY % ruleset.id)
if contact_field:
fingerprint_dict['contact_field'] = contact_field.id
dependencies.add(CONTACT_KEY % contact_field.id)
for contact_filter in filters:
if 'ruleset' in contact_filter:
dependencies.add(RULESET_KEY % contact_filter['ruleset'])
if 'groups' in contact_filter:
for group_id in contact_filter['groups']:
dependencies.add(GROUP_KEY % group_id)
if 'location' in contact_filter: # pragma: needs cover
field = ContactField.get_by_label(org,
contact_filter['location'])
dependencies.add(CONTACT_KEY % field.id)
if segment:
if 'ruleset' in segment:
dependencies.add(RULESET_KEY % segment['ruleset'])
if 'groups' in segment: # pragma: needs cover
for group_id in segment['groups']:
dependencies.add(GROUP_KEY % group_id)
if 'location' in segment:
field = ContactField.get_by_label(org, segment['location'])
dependencies.add(CONTACT_KEY % field.id)
# our final redis key will contain each dependency as well as a HASH representing the fingerprint of the
# kwargs passed to this method, generate that hash
fingerprint = hash(dict_to_json(fingerprint_dict))
# generate our key
key = VALUE_SUMMARY_CACHE_KEY + ":" + str(org.id) + ":".join(
sorted(list(dependencies))) + ":" + str(fingerprint)
# does our value exist?
r = get_redis_connection()
cached = r.get(key)
if cached is not None:
try:
return json_to_dict(cached)
except Exception: # pragma: needs cover
# failed decoding, oh well, go calculate it instead
pass
if segment:
# segmenting a result is the same as calculating the result with the addition of each
# category as a filter so we expand upon the passed in filters to do this
if 'ruleset' in segment and 'categories' in segment:
for category in segment['categories']:
category_filter = list(filters)
category_filter.append(
dict(ruleset=segment['ruleset'],
categories=[category]))
# calculate our results for this segment
kwargs['filters'] = category_filter
(set_count, unset_count,
categories) = cls.get_filtered_value_summary(**kwargs)
results.append(
dict(label=category,
open_ended=open_ended,
set=set_count,
unset=unset_count,
categories=categories))
# segmenting by groups instead, same principle but we add group filters
elif 'groups' in segment: # pragma: needs cover
for group_id in segment['groups']:
# load our group
group = ContactGroup.user_groups.get(org=org, pk=group_id)
category_filter = list(filters)
category_filter.append(dict(groups=[group_id]))
# calculate our results for this segment
kwargs['filters'] = category_filter
(set_count, unset_count,
categories) = cls.get_filtered_value_summary(**kwargs)
results.append(
dict(label=group.name,
open_ended=open_ended,
set=set_count,
unset_count=unset_count,
categories=categories))
# segmenting by a contact field, only for passed in categories
elif 'contact_field' in segment and 'values' in segment:
# look up the contact field
field = ContactField.get_by_label(org,
segment['contact_field'])
for value in segment['values']:
value_filter = list(filters)
value_filter.append(
dict(contact_field=field.pk, values=[value]))
# calculate our results for this segment
kwargs['filters'] = value_filter
(set_count, unset_count,
categories) = cls.get_filtered_value_summary(**kwargs)
results.append(
dict(label=value,
open_ended=open_ended,
set=set_count,
unset=unset_count,
categories=categories))
# segmenting by a location field
elif 'location' in segment:
# look up the contact field
field = ContactField.get_by_label(org, segment['location'])
# make sure they are segmenting on a location type that makes sense
if field.value_type not in [
Value.TYPE_STATE, Value.TYPE_DISTRICT, Value.TYPE_WARD
]: # pragma: needs cover
raise ValueError(
_("Cannot segment on location for field that is not a State or District type"
))
# make sure our org has a country for location based responses
if not org.country: # pragma: needs cover
raise ValueError(
_("Cannot segment by location until country has been selected for organization"
))
# the boundaries we will segment by
parent = org.country
# figure out our parent
parent_osm_id = segment.get('parent', None)
if parent_osm_id:
parent = AdminBoundary.objects.get(osm_id=parent_osm_id)
# get all the boundaries we are segmenting on
boundaries = list(
AdminBoundary.objects.filter(
parent=parent).order_by('name'))
# if the field is a district field, they need to specify the parent state
if not parent_osm_id and field.value_type == Value.TYPE_DISTRICT: # pragma: needs cover
raise ValueError(
_("You must specify a parent state to segment results by district"
))
if not parent_osm_id and field.value_type == Value.TYPE_WARD: # pragma: needs cover
raise ValueError(
_("You must specify a parent state to segment results by ward"
))
# if this is a district, we can speed things up by only including those districts in our parent, build
# the filter for that
if parent and field.value_type in [
Value.TYPE_DISTRICT, Value.TYPE_WARD
]:
location_filters = [
filters,
dict(location=field.pk,
boundary=[b.osm_id for b in boundaries])
]
else:
location_filters = filters
# get all the contacts segment by location first
(location_set_contacts, location_unset_contacts, location_results) = \
cls.get_filtered_value_summary(contact_field=field, filters=location_filters, return_contacts=True)
# now get the contacts for our primary query
kwargs['return_contacts'] = True
kwargs['filter_contacts'] = location_set_contacts
(primary_set_contacts, primary_unset_contacts,
primary_results) = cls.get_filtered_value_summary(**kwargs)
# build a map of osm_id to location_result
osm_results = {lr['label']: lr for lr in location_results}
empty_result = dict(contacts=list())
for boundary in boundaries:
location_result = osm_results.get(boundary.osm_id,
empty_result)
# clone our primary results
segmented_results = dict(label=boundary.name,
boundary=boundary.osm_id,
open_ended=open_ended)
location_categories = list()
location_contacts = set(location_result['contacts'])
for category in primary_results:
category_contacts = set(category['contacts'])
intersection = location_contacts & category_contacts
location_categories.append(
dict(label=category['label'],
count=len(intersection)))
segmented_results['set'] = len(location_contacts
& primary_set_contacts)
segmented_results['unset'] = len(location_contacts
& primary_unset_contacts)
segmented_results['categories'] = location_categories
results.append(segmented_results)
results = sorted(results, key=lambda r: r['label'])
else:
(set_count, unset_count,
categories) = cls.get_filtered_value_summary(**kwargs)
# Check we have and we have an OPEN ENDED ruleset
if ruleset and len(ruleset.get_rules()) == 1 and isinstance(
ruleset.get_rules()[0].test, TrueTest):
cursor = connection.cursor()
custom_sql = """SELECT w.label, count(*) AS count FROM (
SELECT
regexp_split_to_table(LOWER(text), E'[^[:alnum:]_]') AS label
FROM msgs_msg INNER JOIN contacts_contact ON ( msgs_msg.contact_id = contacts_contact.id )
WHERE msgs_msg.id IN (
SELECT
msg_id
FROM flows_flowstep_messages, flows_flowstep
WHERE flowstep_id = flows_flowstep.id AND
flows_flowstep.step_uuid = '%s'
) AND contacts_contact.is_test = False
) w group by w.label order by count desc;""" % ruleset.uuid
cursor.execute(custom_sql)
unclean_categories = get_dict_from_cursor(cursor)
categories = []
org_languages = [
lang.name.lower()
for lang in org.languages.filter(orgs=None).distinct()
]
if 'english' not in org_languages:
org_languages.append('english')
ignore_words = []
for lang in org_languages:
ignore_words += safe_get_stop_words(lang)
for category in unclean_categories:
if len(category['label']) > 1 and category[
'label'] not in ignore_words and len(
categories) < 100:
categories.append(
dict(label=category['label'],
count=int(category['count'])))
# sort by count, then alphabetically
categories = sorted(categories,
key=lambda c: (-c['count'], c['label']))
results.append(
dict(label=six.text_type(_("All")),
open_ended=open_ended,
set=set_count,
unset=unset_count,
categories=categories))
# for each of our dependencies, add our key as something that depends on it
pipe = r.pipeline()
for dependency in dependencies:
pipe.sadd(dependency, key)
pipe.expire(dependency, VALUE_SUMMARY_CACHE_TIME)
# and finally set our result
pipe.set(key, dict_to_json(results), VALUE_SUMMARY_CACHE_TIME)
pipe.execute()
# leave me: nice for profiling..
# from django.db import connection as db_connection, reset_queries
# print "=" * 80
# for query in db_connection.queries:
# print "%s - %s" % (query['time'], query['sql'][:1000])
# print "-" * 80
# print "took: %f" % (time.time() - start)
# print "=" * 80
# reset_queries()
return results
def get_value_summary(cls, ruleset=None, contact_field=None, filters=None, segment=None):
"""
Returns the results for the passed in ruleset or contact field given the passed in filters and segments.
Filters are expected in the following formats:
{ field: rulesetId, categories: ["Red", "Blue", "Yellow"] }
Segments are expected in these formats instead:
{ ruleset: 1515, categories: ["Red", "Blue"] } // segmenting by another field, for those categories
{ groups: 124,151,151 } // segment by each each group in the passed in ids
{ location: "State", parent: null } // segment for each admin boundary within the parent
{ contact_field: "Country", values: ["US", "EN", "RW"] } // segment by a contact field for these values
"""
from temba.contacts.models import ContactGroup, ContactField
from temba.flows.models import TrueTest, RuleSet
start = time.time()
results = []
if (not ruleset and not contact_field) or (ruleset and contact_field):
raise ValueError("Must specify either a RuleSet or Contact field.")
org = ruleset.flow.org if ruleset else contact_field.org
open_ended = ruleset and ruleset.ruleset_type == RuleSet.TYPE_WAIT_MESSAGE and len(ruleset.get_rules()) == 1
# default our filters to an empty list if None are passed in
if filters is None:
filters = []
# build the kwargs for our subcall
kwargs = dict(ruleset=ruleset, contact_field=contact_field, filters=filters)
# this is our list of dependencies, that is things that will blow away our results
dependencies = set()
fingerprint_dict = dict(filters=filters, segment=segment)
if ruleset:
fingerprint_dict['ruleset'] = ruleset.id
dependencies.add(RULESET_KEY % ruleset.id)
if contact_field:
fingerprint_dict['contact_field'] = contact_field.id
dependencies.add(CONTACT_KEY % contact_field.id)
for contact_filter in filters:
if 'ruleset' in contact_filter:
dependencies.add(RULESET_KEY % contact_filter['ruleset'])
if 'groups' in contact_filter:
for group_id in contact_filter['groups']:
dependencies.add(GROUP_KEY % group_id)
if 'location' in contact_filter:
field = ContactField.get_by_label(org, contact_filter['location'])
dependencies.add(CONTACT_KEY % field.id)
if segment:
if 'ruleset' in segment:
dependencies.add(RULESET_KEY % segment['ruleset'])
if 'groups' in segment:
for group_id in segment['groups']:
dependencies.add(GROUP_KEY % group_id)
if 'location' in segment:
field = ContactField.get_by_label(org, segment['location'])
dependencies.add(CONTACT_KEY % field.id)
# our final redis key will contain each dependency as well as a HASH representing the fingerprint of the
# kwargs passed to this method, generate that hash
fingerprint = hash(dict_to_json(fingerprint_dict))
# generate our key
key = VALUE_SUMMARY_CACHE_KEY + ":" + str(org.id) + ":".join(sorted(list(dependencies))) + ":" + str(fingerprint)
# does our value exist?
r = get_redis_connection()
cached = r.get(key)
if cached is not None:
try:
return json_to_dict(cached)
except Exception:
# failed decoding, oh well, go calculate it instead
pass
if segment:
# segmenting a result is the same as calculating the result with the addition of each
# category as a filter so we expand upon the passed in filters to do this
if 'ruleset' in segment and 'categories' in segment:
for category in segment['categories']:
category_filter = list(filters)
category_filter.append(dict(ruleset=segment['ruleset'], categories=[category]))
# calculate our results for this segment
kwargs['filters'] = category_filter
(set_count, unset_count, categories) = cls.get_filtered_value_summary(**kwargs)
results.append(dict(label=category, open_ended=open_ended, set=set_count, unset=unset_count, categories=categories))
# segmenting by groups instead, same principle but we add group filters
elif 'groups' in segment:
for group_id in segment['groups']:
# load our group
group = ContactGroup.user_groups.get(org=org, pk=group_id)
category_filter = list(filters)
category_filter.append(dict(groups=[group_id]))
# calculate our results for this segment
kwargs['filters'] = category_filter
(set_count, unset_count, categories) = cls.get_filtered_value_summary(**kwargs)
results.append(dict(label=group.name, open_ended=open_ended, set=set_count, unset_count=unset_count, categories=categories))
# segmenting by a contact field, only for passed in categories
elif 'contact_field' in segment and 'values' in segment:
# look up the contact field
field = ContactField.get_by_label(org, segment['contact_field'])
for value in segment['values']:
value_filter = list(filters)
value_filter.append(dict(contact_field=field.pk, values=[value]))
# calculate our results for this segment
kwargs['filters'] = value_filter
(set_count, unset_count, categories) = cls.get_filtered_value_summary(**kwargs)
results.append(dict(label=value, open_ended=open_ended, set=set_count, unset=unset_count, categories=categories))
# segmenting by a location field
elif 'location' in segment:
# look up the contact field
field = ContactField.get_by_label(org, segment['location'])
# make sure they are segmenting on a location type that makes sense
if field.value_type not in [Value.TYPE_STATE, Value.TYPE_DISTRICT, Value.TYPE_WARD]:
raise ValueError(_("Cannot segment on location for field that is not a State or District type"))
# make sure our org has a country for location based responses
if not org.country:
raise ValueError(_("Cannot segment by location until country has been selected for organization"))
# the boundaries we will segment by
parent = org.country
# figure out our parent
parent_osm_id = segment.get('parent', None)
if parent_osm_id:
parent = AdminBoundary.objects.get(osm_id=parent_osm_id)
# get all the boundaries we are segmenting on
boundaries = list(AdminBoundary.objects.filter(parent=parent).order_by('name'))
# if the field is a district field, they need to specify the parent state
if not parent_osm_id and field.value_type == Value.TYPE_DISTRICT:
raise ValueError(_("You must specify a parent state to segment results by district"))
if not parent_osm_id and field.value_type == Value.TYPE_WARD:
raise ValueError(_("You must specify a parent state to segment results by ward"))
# if this is a district, we can speed things up by only including those districts in our parent, build
# the filter for that
if parent and field.value_type in [Value.TYPE_DISTRICT, Value.TYPE_WARD]:
location_filters = [filters, dict(location=field.pk, boundary=[b.osm_id for b in boundaries])]
else:
location_filters = filters
# get all the contacts segment by location first
(location_set_contacts, location_unset_contacts, location_results) = \
cls.get_filtered_value_summary(contact_field=field, filters=location_filters, return_contacts=True)
# now get the contacts for our primary query
kwargs['return_contacts'] = True
kwargs['filter_contacts'] = location_set_contacts
(primary_set_contacts, primary_unset_contacts, primary_results) = cls.get_filtered_value_summary(**kwargs)
# build a map of osm_id to location_result
osm_results = {lr['label']: lr for lr in location_results}
empty_result = dict(contacts=list())
for boundary in boundaries:
location_result = osm_results.get(boundary.osm_id, empty_result)
# clone our primary results
segmented_results = dict(label=boundary.name,
boundary=boundary.osm_id,
open_ended=open_ended)
location_categories = list()
location_contacts = set(location_result['contacts'])
for category in primary_results:
category_contacts = set(category['contacts'])
intersection = location_contacts & category_contacts
location_categories.append(dict(label=category['label'], count=len(intersection)))
segmented_results['set'] = len(location_contacts & primary_set_contacts)
segmented_results['unset'] = len(location_contacts & primary_unset_contacts)
segmented_results['categories'] = location_categories
results.append(segmented_results)
results = sorted(results, key=lambda r: r['label'])
else:
(set_count, unset_count, categories) = cls.get_filtered_value_summary(**kwargs)
# Check we have and we have an OPEN ENDED ruleset
if ruleset and len(ruleset.get_rules()) == 1 and isinstance(ruleset.get_rules()[0].test, TrueTest):
cursor = connection.cursor()
custom_sql = """SELECT w.label, count(*) AS count FROM (
SELECT
regexp_split_to_table(LOWER(text), E'[^[:alnum:]_]') AS label
FROM msgs_msg INNER JOIN contacts_contact ON ( msgs_msg.contact_id = contacts_contact.id )
WHERE msgs_msg.id IN (
SELECT
msg_id
FROM flows_flowstep_messages, flows_flowstep
WHERE flowstep_id = flows_flowstep.id AND
flows_flowstep.step_uuid = '%s'
) AND contacts_contact.is_test = False
) w group by w.label order by count desc;""" % ruleset.uuid
cursor.execute(custom_sql)
unclean_categories = get_dict_from_cursor(cursor)
categories = []
org_languages = [lang.name.lower() for lang in org.languages.filter(orgs=None).distinct()]
if 'english' not in org_languages:
org_languages.append('english')
ignore_words = []
for lang in org_languages:
ignore_words += safe_get_stop_words(lang)
for category in unclean_categories:
if len(category['label']) > 1 and category['label'] not in ignore_words and len(categories) < 100:
categories.append(dict(label=category['label'], count=int(category['count'])))
# sort by count, then alphabetically
categories = sorted(categories, key=lambda c: (-c['count'], c['label']))
results.append(dict(label=unicode(_("All")), open_ended=open_ended, set=set_count, unset=unset_count, categories=categories))
# for each of our dependencies, add our key as something that depends on it
pipe = r.pipeline()
for dependency in dependencies:
pipe.sadd(dependency, key)
pipe.expire(dependency, VALUE_SUMMARY_CACHE_TIME)
# and finally set our result
pipe.set(key, dict_to_json(results), VALUE_SUMMARY_CACHE_TIME)
pipe.execute()
# leave me: nice for profiling..
#from django.db import connection as db_connection, reset_queries
#print "=" * 80
#for query in db_connection.queries:
# print "%s - %s" % (query['time'], query['sql'][:1000])
#print "-" * 80
#print "took: %f" % (time.time() - start)
#print "=" * 80
#reset_queries()
return results
def get_value_summary(cls,
ruleset=None,
contact_field=None,
filters=None,
segment=None,
latest_only=True):
"""
Returns the results for the passed in ruleset or contact field given the passed in filters and segments.
Filters are expected in the following formats:
{ field: rulesetId, categories: ["Red", "Blue", "Yellow"] }
Segments are expected in these formats instead:
{ ruleset: 1515, categories: ["Red", "Blue"] } // segmenting by another field, for those categories
{ groups: 124,151,151 } // segment by each each group in the passed in ids
{ location: "State", parent: null } // segment for each admin boundary within the parent
"""
from temba.contacts.models import ContactGroup, ContactField
from temba.flows.models import TrueTest
results = []
if (not ruleset and not contact_field) or (ruleset and contact_field):
raise Exception("Must specify either a RuleSet or Contact field.")
org = ruleset.flow.org if ruleset else contact_field.org
open_ended = ruleset and len(ruleset.get_rules()) == 1
# default our filters to an empty list if None are passed in
if filters is None:
filters = []
# build the kwargs for our subcall
kwargs = dict(ruleset=ruleset,
contact_field=contact_field,
filters=filters,
latest_only=latest_only)
# this is our list of dependencies, that is things that will blow away our results
dependencies = set()
fingerprint_dict = dict(filters=filters,
segment=segment,
latest_only=latest_only)
if ruleset:
fingerprint_dict['ruleset'] = ruleset.id
dependencies.add(RULESET_KEY % ruleset.id)
if contact_field:
fingerprint_dict['contact_field'] = contact_field.id
dependencies.add(CONTACT_KEY % contact_field.id)
for filter in filters:
if 'ruleset' in filter:
dependencies.add('vsr%d' % filter['ruleset'])
if 'groups' in filter:
for group_id in filter['groups']:
dependencies.add(GROUP_KEY % group_id)
if 'location' in filter:
field = ContactField.objects.get(
org=org, label__iexact=filter['location'])
dependencies.add(CONTACT_KEY % field.id)
if segment:
if 'ruleset' in segment:
dependencies.add('vsr%d' % segment['ruleset'])
if 'groups' in segment:
for group_id in segment['groups']:
dependencies.add(GROUP_KEY % group_id)
if 'location' in segment:
field = ContactField.objects.get(
org=org, label__iexact=segment['location'])
dependencies.add(CONTACT_KEY % field.id)
# our final redis key will contain each dependency as well as a HASH representing the fingerprint of the
# kwargs passed to this method, generate that hash
fingerprint = hash(dict_to_json(fingerprint_dict))
# generate our key
key = VALUE_SUMMARY_CACHE_KEY + ":" + ":".join(
sorted(list(dependencies))) + ":" + str(fingerprint)
# does our value exist?
r = get_redis_connection()
cached = r.get(key)
if not cached is None:
try:
return json_to_dict(cached)
except:
# failed decoding, oh well, go calculate it instead
pass
if segment:
# segmenting a result is the same as calculating the result with the addition of each
# category as a filter so we expand upon the passed in filters to do this
if 'categories' in segment:
for category in segment['categories']:
category_filter = list(filters)
category_filter.append(
dict(ruleset=segment['ruleset'],
categories=[category]))
# calculate our results for this segment
kwargs['filters'] = category_filter
(set_count, unset_count,
categories) = cls.get_filtered_value_summary(**kwargs)
results.append(
dict(label=category,
open_ended=open_ended,
set=set_count,
unset=unset_count,
categories=categories))
# segmenting by groups instead, same principle but we add group filters
elif 'groups' in segment:
for group_id in segment['groups']:
# load our group
group = ContactGroup.objects.get(is_active=True,
org=org,
pk=group_id)
category_filter = list(filters)
category_filter.append(dict(groups=[group_id]))
# calculate our results for this segment
kwargs['filters'] = category_filter
(set_count, unset_count,
categories) = cls.get_filtered_value_summary(**kwargs)
results.append(
dict(label=group.name,
open_ended=open_ended,
set=set_count,
unset_count=unset_count,
categories=categories))
# segmenting by a location field
elif 'location' in segment:
# look up the contact field
field = ContactField.objects.get(
org=org, label__iexact=segment['location'])
# make sure they are segmenting on a location type that makes sense
if not field.value_type in [STATE, DISTRICT]:
raise Exception(
_("Cannot segment on location for field that is not a State or District type"
))
# make sure our org has a country for location based responses
if not org.country:
raise Exception(
_("Cannot segment by location until country has been selected for organization"
))
# the boundaries we will segment by
parent = org.country
# figure out our parent
parent_osm_id = segment.get('parent', None)
if parent_osm_id:
parent = AdminBoundary.objects.get(osm_id=parent_osm_id)
# if the field is a district field, they need to specify the parent state
if not parent_osm_id and field.value_type == DISTRICT:
raise Exception(
_("You must specify a parent state to segment results by district"
))
# now segment by all the children of this parent
for boundary in AdminBoundary.objects.filter(
parent=parent).order_by('name'):
boundary_filter = list(filters)
boundary_filter.append(
dict(location=field.id, boundary=boundary.osm_id))
kwargs['filters'] = boundary_filter
# calculate our results for this segment
(set_count, unset_count,
categories) = cls.get_filtered_value_summary(**kwargs)
results.append(
dict(label=boundary.name,
boundary=boundary.osm_id,
open_ended=open_ended,
set=set_count,
unset=unset_count,
categories=categories))
else:
(set_count, unset_count,
categories) = cls.get_filtered_value_summary(**kwargs)
# Check we have and we have an OPEN ENDED ruleset
if ruleset and len(ruleset.get_rules()) == 1 and isinstance(
ruleset.get_rules()[0].test, TrueTest):
cursor = connection.cursor()
custom_sql = """
SELECT w.label, count(*) AS count FROM (
SELECT
regexp_split_to_table(LOWER(text), E'[^[:alnum:]_]') AS label
FROM msgs_msg
WHERE id IN (
SELECT
msg_id
FROM flows_flowstep_messages, flows_flowstep
WHERE flowstep_id = flows_flowstep.id AND
flows_flowstep.step_uuid = '%s'
)
) w group by w.label order by count desc;
""" % ruleset.uuid
cursor.execute(custom_sql)
unclean_categories = get_dict_from_cursor(cursor)
categories = []
ignore_words = get_stop_words('english')
for category in unclean_categories:
if len(category['label']) > 1 and category[
'label'] not in ignore_words and len(
categories) < 100:
categories.append(
dict(label=category['label'],
count=int(category['count'])))
# sort by count, then alphabetically
categories = sorted(categories,
key=lambda c: (-c['count'], c['label']))
results.append(
dict(label=unicode(_("All")),
open_ended=open_ended,
set=set_count,
unset=unset_count,
categories=categories))
# cache this result set
r.set(key, dict_to_json(results), VALUE_SUMMARY_CACHE_TIME)
return results
def get_value_summary(cls, ruleset=None, contact_field=None, filters=None, segment=None, latest_only=True):
"""
Returns the results for the passed in ruleset or contact field given the passed in filters and segments.
Filters are expected in the following formats:
{ field: rulesetId, categories: ["Red", "Blue", "Yellow"] }
Segments are expected in these formats instead:
{ ruleset: 1515, categories: ["Red", "Blue"] } // segmenting by another field, for those categories
{ groups: 124,151,151 } // segment by each each group in the passed in ids
{ location: "State", parent: null } // segment for each admin boundary within the parent
"""
from temba.contacts.models import ContactGroup, ContactField
from temba.flows.models import TrueTest
results = []
if (not ruleset and not contact_field) or (ruleset and contact_field):
raise Exception("Must specify either a RuleSet or Contact field.")
org = ruleset.flow.org if ruleset else contact_field.org
open_ended = ruleset and len(ruleset.get_rules()) == 1
# default our filters to an empty list if None are passed in
if filters is None:
filters = []
# build the kwargs for our subcall
kwargs = dict(ruleset=ruleset, contact_field=contact_field, filters=filters, latest_only=latest_only)
# this is our list of dependencies, that is things that will blow away our results
dependencies = set()
fingerprint_dict = dict(filters=filters, segment=segment, latest_only=latest_only)
if ruleset:
fingerprint_dict['ruleset'] = ruleset.id
dependencies.add(RULESET_KEY % ruleset.id)
if contact_field:
fingerprint_dict['contact_field'] = contact_field.id
dependencies.add(CONTACT_KEY % contact_field.id)
for filter in filters:
if 'ruleset' in filter: dependencies.add('vsr%d' % filter['ruleset'])
if 'groups' in filter:
for group_id in filter['groups']:
dependencies.add(GROUP_KEY % group_id)
if 'location' in filter:
field = ContactField.objects.get(org=org, label__iexact=filter['location'])
dependencies.add(CONTACT_KEY % field.id)
if segment:
if 'ruleset' in segment: dependencies.add('vsr%d' % segment['ruleset'])
if 'groups' in segment:
for group_id in segment['groups']:
dependencies.add(GROUP_KEY % group_id)
if 'location' in segment:
field = ContactField.objects.get(org=org, label__iexact=segment['location'])
dependencies.add(CONTACT_KEY % field.id)
# our final redis key will contain each dependency as well as a HASH representing the fingerprint of the
# kwargs passed to this method, generate that hash
fingerprint = hash(dict_to_json(fingerprint_dict))
# generate our key
key = VALUE_SUMMARY_CACHE_KEY + ":" + ":".join(sorted(list(dependencies))) + ":" + str(fingerprint)
# does our value exist?
r = get_redis_connection()
cached = r.get(key)
if not cached is None:
try:
return json_to_dict(cached)
except:
# failed decoding, oh well, go calculate it instead
pass
if segment:
# segmenting a result is the same as calculating the result with the addition of each
# category as a filter so we expand upon the passed in filters to do this
if 'categories' in segment:
for category in segment['categories']:
category_filter = list(filters)
category_filter.append(dict(ruleset=segment['ruleset'], categories=[category]))
# calculate our results for this segment
kwargs['filters'] = category_filter
(set_count, unset_count, categories) = cls.get_filtered_value_summary(**kwargs)
results.append(dict(label=category, open_ended=open_ended, set=set_count, unset=unset_count, categories=categories))
# segmenting by groups instead, same principle but we add group filters
elif 'groups' in segment:
for group_id in segment['groups']:
# load our group
group = ContactGroup.objects.get(is_active=True, org=org, pk=group_id)
category_filter = list(filters)
category_filter.append(dict(groups=[group_id]))
# calculate our results for this segment
kwargs['filters'] = category_filter
(set_count, unset_count, categories) = cls.get_filtered_value_summary(**kwargs)
results.append(dict(label=group.name, open_ended=open_ended, set=set_count, unset_count=unset_count, categories=categories))
# segmenting by a location field
elif 'location' in segment:
# look up the contact field
field = ContactField.objects.get(org=org, label__iexact=segment['location'])
# make sure they are segmenting on a location type that makes sense
if not field.value_type in [STATE, DISTRICT]:
raise Exception(_("Cannot segment on location for field that is not a State or District type"))
# make sure our org has a country for location based responses
if not org.country:
raise Exception(_("Cannot segment by location until country has been selected for organization"))
# the boundaries we will segment by
parent = org.country
# figure out our parent
parent_osm_id = segment.get('parent', None)
if parent_osm_id:
parent = AdminBoundary.objects.get(osm_id=parent_osm_id)
# if the field is a district field, they need to specify the parent state
if not parent_osm_id and field.value_type == DISTRICT:
raise Exception(_("You must specify a parent state to segment results by district"))
# now segment by all the children of this parent
for boundary in AdminBoundary.objects.filter(parent=parent).order_by('name'):
boundary_filter = list(filters)
boundary_filter.append(dict(location=field.id, boundary=boundary.osm_id))
kwargs['filters'] = boundary_filter
# calculate our results for this segment
(set_count, unset_count, categories) = cls.get_filtered_value_summary(**kwargs)
results.append(dict(label=boundary.name, boundary=boundary.osm_id, open_ended=open_ended,
set=set_count, unset=unset_count, categories=categories))
else:
(set_count, unset_count, categories) = cls.get_filtered_value_summary(**kwargs)
# Check we have and we have an OPEN ENDED ruleset
if ruleset and len(ruleset.get_rules()) == 1 and isinstance(ruleset.get_rules()[0].test, TrueTest):
cursor = connection.cursor()
custom_sql = """
SELECT w.label, count(*) AS count FROM (
SELECT
regexp_split_to_table(LOWER(text), E'[^[:alnum:]_]') AS label
FROM msgs_msg
WHERE id IN (
SELECT
msg_id
FROM flows_flowstep_messages, flows_flowstep
WHERE flowstep_id = flows_flowstep.id AND
flows_flowstep.step_uuid = '%s'
)
) w group by w.label order by count desc;
""" % ruleset.uuid
cursor.execute(custom_sql)
unclean_categories = get_dict_from_cursor(cursor)
categories = []
ignore_words = get_stop_words('english')
for category in unclean_categories:
if len(category['label']) > 1 and category['label'] not in ignore_words and len(categories) < 100:
categories.append(dict(label=category['label'], count=int(category['count'])))
# sort by count, then alphabetically
categories= sorted(categories, key=lambda c: (-c['count'], c['label']))
results.append(dict(label=unicode(_("All")), open_ended=open_ended, set=set_count, unset=unset_count, categories=categories))
# cache this result set
r.set(key, dict_to_json(results), VALUE_SUMMARY_CACHE_TIME)
return results