Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Added --slice-queryset argument #284

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Added --slice-queryset argument #284

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 20 additions & 0 deletions tests/test_watson/tests.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -259,6 +259,26 @@ def testFixesDuplicateSearchEntries(self):
# Make sure that we have six again (including duplicates).
self.assertEqual(search_entries.all().count(), 6)

def testSliceQuerysetBuildWatson(self):
# Delete and re-add
deleted, _ = SearchEntry.objects.filter(engine_slug="default").delete()
self.assertEqual(deleted, 6)
call_command("buildwatson", verbosity=0, slice_queryset=True)
self.assertEqual(SearchEntry.objects.filter(engine_slug="default").count(), 6)

def testFixesDuplicateSliceQuerysetBuildWatson(self):
search_entries = SearchEntry.objects.filter(engine_slug="default")
# Duplicate a couple of search entries.
for search_entry in search_entries.all()[:2]:
search_entry.id = None
search_entry.save()
# Make sure that we have eight (including duplicates).
self.assertEqual(search_entries.all().count(), 8)
# Run the rebuild command.
call_command("buildwatson", verbosity=0, slice_queryset=True)
# Make sure that we have six again (including duplicates).
self.assertEqual(search_entries.all().count(), 6)

def testEmptyFilterGivesAllResults(self):
for model in (WatsonTestModel1, WatsonTestModel2, WatsonTestModel3):
self.assertEqual(watson.filter(model, "").count(), 2)
Expand Down
53 changes: 37 additions & 16 deletions watson/management/commands/buildwatson.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,33 +29,45 @@ def get_engine(engine_slug_):
raise CommandError("Search Engine \"%s\" is not registered!" % force_str(engine_slug_))


def rebuild_index_for_model(model_, engine_slug_, verbosity_, slim_=False, batch_size_=100, non_atomic_=False):
def rebuild_index_for_model(model_, engine_slug_, verbosity_, slim_=False, batch_size_=100, non_atomic_=False, slice_queryset_=False):
"""rebuilds index for a model"""

search_engine_ = get_engine(engine_slug_)

local_refreshed_model_count = [0] # HACK: Allows assignment to outer scope.

def report(obj):
local_refreshed_model_count[0] += 1
if verbosity_ >= 3:
print(
"Refreshed search entry for {model} {obj} "
"in {engine_slug!r} search engine.".format(
model=force_str(model_._meta.verbose_name),
obj=force_str(obj),
engine_slug=force_str(engine_slug_),
)
)

def iter_search_entries():
# Only index specified objects if slim_ is True
if slim_ and search_engine_._registered_models[model_].get_live_queryset():
obj_list = search_engine_._registered_models[model_].get_live_queryset()
else:
obj_list = model_._default_manager.all()

for obj in obj_list.iterator():
for search_entry in search_engine_._update_obj_index_iter(obj):
yield search_entry
local_refreshed_model_count[0] += 1
if verbosity_ >= 3:
print(
"Refreshed search entry for {model} {obj} "
"in {engine_slug!r} search engine.".format(
model=force_str(model_._meta.verbose_name),
obj=force_str(obj),
engine_slug=force_str(engine_slug_),
)
)
if slice_queryset_:
count = obj_list.count()
for i in range(0, count, batch_size_):
for obj in obj_list[i:i + batch_size_]:
for search_entry in search_engine_._update_obj_index_iter(obj):
yield search_entry
report(obj)
else:
for obj in obj_list.iterator():
for search_entry in search_engine_._update_obj_index_iter(obj):
yield search_entry
report(obj)

if verbosity_ == 2:
print(
"Refreshed {local_refreshed_model_count} {model} search entry(s) "
Expand Down Expand Up @@ -107,6 +119,12 @@ def add_arguments(self, parser):
type=int,
help="The batchsize with which entries will be added to the index."
)
parser.add_argument(
'--slice-queryset',
action='store_true',
default=False,
help="Uses slicing on QuerySet instead of .iterator()"
)

def handle(self, *args, **options):
"""Runs the management command."""
Expand All @@ -125,6 +143,7 @@ def handle(self, *args, **options):
slim = options.get("slim")
batch_size = options.get("batch_size")
non_atomic = options.get("non_atomic")
slice_queryset = options.get("slice_queryset")

# work-around for legacy optparser hack in BaseCommand. In Django=1.10 the
# args are collected in options['apps'], but in earlier versions they are
Expand Down Expand Up @@ -166,7 +185,8 @@ def handle(self, *args, **options):
verbosity,
slim_=slim,
batch_size_=batch_size,
non_atomic_=non_atomic)
non_atomic_=non_atomic,
slice_queryset_=slice_queryset)

else: # full rebuild (for one or all search engines)
if engine_selected:
Expand All @@ -188,7 +208,8 @@ def handle(self, *args, **options):
verbosity,
slim_=slim,
batch_size_=batch_size,
non_atomic_=non_atomic)
non_atomic_=non_atomic,
slice_queryset_=slice_queryset)

# Clean out any search entries that exist for stale content types.
# Only do it during full rebuild
Expand Down