Getting all queries that django run on postgresql - django

I am working on a django-postgresql project and I need to see every query that django run on database(so I can fine-tune queries). Is there a way to get those queries.
Update: My development environment is on ubuntu linux

Well, you could just set the pgsql server to log every query. Or just to log the slow ones. Look in the postgresql.conf file, it's pretty close to self-documenting.

Check out this Question (and the two top most answers):
django orm, how to view (or log) the executed query?
You can also have a look at the Djando documenation:
https://docs.djangoproject.com/en/dev/faq/models/#how-can-i-see-the-raw-sql-queries-django-is-running
Hope this helps,
Anton

You can decorate a request handler or other function with this and it will print the sql nicely formated with totals at the end.
from functools import wraps
from django.utils import termcolors
format_ok = termcolors.make_style(opts=('bold',), fg='green')
format_warning = termcolors.make_style(opts=('bold',), fg='yellow')
format_error = termcolors.make_style(opts=('bold',), fg='red')
try:
from pygments import highlight
from pygments.lexers import SqlLexer
from pygments.formatters import TerminalFormatter
pygments_sql_lexer = SqlLexer()
pygments_terminal_formatter = TerminalFormatter()
highlight_sql = lambda s: highlight(s, pygments_sql_lexer,
pygments_terminal_formatter)
except ImportError:
highlight_sql = lambda s: s
def debug_sql(f):
"""
Turn SQL statement debugging on for a test run.
"""
#wraps(f)
def wrapper(*a, **kw):
from django.conf import settings
from django.db import connection
try:
debug = settings.DEBUG
settings.DEBUG = True
connection.queries = []
return f(*a, **kw)
finally:
total_time = 0
for q in connection.queries:
fmt = format_ok
t = float(q['time'])
total_time += t
if t > 1:
fmt = format_error
elif t > 0.3:
fmt = format_warning
print '[%s] %s' % (fmt(q['time']), highlight_sql(q['sql']))
print "total time =", total_time
print "num queries =", len(connection.queries)
settings.DEBUG = debug
return wrapper

Try the django debug toolbar. It'll show you all the SQL executed over the request. When something is executing way too many queries, it becomes really slow, though. For that, I've been meaning to try out this profiler. However, I've rolled this middleware on a couple of projects:
try:
from cStringIO import StringIO
except ImportError:
import StringIO
from django.conf import settings
from django.db import connection
class DatabaseProfilerMiddleware(object):
def can(self, request):
return settings.DEBUG and 'dbprof' in request.GET
def process_response(self, request, response):
if self.can(request):
out = StringIO()
out.write('time sql\n')
total_time = 0
for query in reversed(sorted(connection.queries, key=lambda x: x['time'])):
total_time += float(query['time'])*1000
out.write('%s %s\n' % (query['time'], query['sql']))
response.content = '<pre style="white-space:pre-wrap">%d queries executed in %.3f seconds\n%s</pre>' \
% (len(connection.queries), total_time/1000, out.getvalue())
return response
Just go to the relevant URL for the request you are interested in and add a dbprof GET parameter, you'll see the profiling output instead of the normal response.

Related

python populate.py wont populate my database

After writing the following code and expecting the output to be an updated database with random names, websites, etc., I get no error message and no updated database
import os
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'First_project.settings')
import django
django.setup()
import random
from first_app.models import AccessRecord,Webpage,Topic
from faker import Faker
fakegen = Faker()
topics = ['Search','Social','Marketplace','News','Games']
def add_topic():
t = Topic.object.get_or_create(top_name=random.choice(topics))[0]
t.save()
return t
def populate(N=5):
for entry in range(N):
top = add_topic()
fake_url = fakegen.url()
fake_date = fakegen.date()
fake_name = fakegen.company()
webpg = webpage.objects.get_or_create(topic=top, url=fake_ur, name=fake_name)[0]
acc_rec = AccessRecord.object.get_or_create(name=webpg,date=fake_date)[0]
if __name__ == ' __main__':
print("populate")
populate(20)
print("populating complete!")
please what do I do?
i ran the whole code in my terminal and it populated the database

How to get the "full" async result in Celery link_error callback

I have Celery 3.1.18 running with Django 1.6.11 and RabbitMQ 3.5.4, and trying to test my async task in a failure state (CELERY_ALWAYS_EAGER=True). However, I cannot get the proper "result" in the error callback. The example in the Celery docs shows:
#app.task(bind=True)
def error_handler(self, uuid):
result = self.app.AsyncResult(uuid)
print('Task {0} raised exception: {1!r}\n{2!r}'.format(
uuid, result.result, result.traceback))
When I do this, my result is still "PENDING", result.result = '', and result.traceback=''. But the actual result returned by my .apply_async call has the right "FAILURE" state and traceback.
My code (basically a Django Rest Framework RESTful endpoint that parses a .tar.gz file, and then sends a notification back to the user, when the file is done parsing):
views.py:
from producer_main.celery import app as celery_app
#celery_app.task()
def _upload_error_simple(uuid):
print uuid
result = celery_app.AsyncResult(uuid)
print result.backend
print result.state
print result.result
print result.traceback
msg = 'Task {0} raised exception: {1!r}\n{2!r}'.format(uuid,
result.result,
result.traceback)
class UploadNewFile(APIView):
def post(self, request, repository_id, format=None):
try:
uploaded_file = self.data['files'][self.data['files'].keys()[0]]
self.path = default_storage.save('{0}/{1}'.format(settings.MEDIA_ROOT,
uploaded_file.name),
uploaded_file)
print type(import_file)
self.async_result = import_file.apply_async((self.path, request.user),
link_error=_upload_error_simple.s())
print 'results from self.async_result:'
print self.async_result.id
print self.async_result.backend
print self.async_result.state
print self.async_result.result
print self.async_result.traceback
return Response()
except (PermissionDenied, InvalidArgument, NotFound, KeyError) as ex:
gutils.handle_exceptions(ex)
tasks.py:
from producer_main.celery import app
from utilities.general import upload_class
#app.task
def import_file(path, user):
"""Asynchronously import a course."""
upload_class(path, user)
celery.py:
"""
As described in
http://celery.readthedocs.org/en/latest/django/first-steps-with-django.html
"""
from __future__ import absolute_import
import os
import logging
from celery import Celery
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'producer_main.settings')
from django.conf import settings
log = logging.getLogger(__name__)
app = Celery('producer') # pylint: disable=invalid-name
# Using a string here means the worker will not have to
# pickle the object when using Windows.
app.config_from_object('django.conf:settings')
app.autodiscover_tasks(lambda: settings.INSTALLED_APPS) # pragma: no cover
#app.task(bind=True)
def debug_task(self):
print('Request: {0!r}'.format(self.request))
My backend is configured as such:
CELERY_ALWAYS_EAGER = True
CELERY_EAGER_PROPAGATES_EXCEPTIONS = False
BROKER_URL = 'amqp://'
CELERY_RESULT_BACKEND = 'redis://localhost'
CELERY_RESULT_PERSISTENT = True
CELERY_IGNORE_RESULT = False
When I run my unittest for the link_error state, I get:
Creating test database for alias 'default'...
<class 'celery.local.PromiseProxy'>
130ccf13-c2a0-4bde-8d49-e17eeb1b0115
<celery.backends.redis.RedisBackend object at 0x10aa2e110>
PENDING
None
None
results from self.async_result:
130ccf13-c2a0-4bde-8d49-e17eeb1b0115
None
FAILURE
Non .zip / .tar.gz file passed in.
Traceback (most recent call last):
So the task results are not available in my _upload_error_simple() method, but they are available from the self.async_result returned variable...
I could not get the link and link_error callbacks to work, so I finally had to use the on_failure and on_success task methods described in the docs and this SO question. My tasks.py then looks like:
class ErrorHandlingTask(Task):
abstract = True
def on_failure(self, exc, task_id, targs, tkwargs, einfo):
msg = 'Import of {0} raised exception: {1!r}'.format(targs[0].split('/')[-1],
str(exc))
def on_success(self, retval, task_id, targs, tkwargs):
msg = "Upload successful. You may now view your course."
#app.task(base=ErrorHandlingTask)
def import_file(path, user):
"""Asynchronously import a course."""
upload_class(path, user)
You appear to have _upload_error() as a bound method of your class - this is probably not what you want. try making it a stand-along task:
#celery_app.task(bind=True)
def _upload_error(self, uuid):
result = celery_app.AsyncResult(uuid)
msg = 'Task {0} raised exception: {1!r}\n{2!r}'.format(uuid,
result.result,
result.traceback)
class Whatever(object):
....
self.async_result = import_file.apply_async((self.path, request.user),
link=self._upload_success.s(
"Upload finished."),
link_error=_upload_error.s())
in fact there's no need for the self paramater since it's not used so you could just do this:
#celery_app.task()
def _upload_error(uuid):
result = celery_app.AsyncResult(uuid)
msg = 'Task {0} raised exception: {1!r}\n{2!r}'.format(uuid,
result.result,
result.traceback)
note the absence of bind=True and self
Be careful with UUID instance!
If you will try to get status of a task with id not string type but UUID type, you will only get PENDING status.
from uuid import UUID
from celery.result import AsyncResult
task_id = UUID('d4337c01-4402-48e9-9e9c-6e9919d5e282')
print(AsyncResult(task_id).state)
# PENDING
print(AsyncResult(str(task_id)).state)
# SUCCESS

passing commandline arguments to a selenium python webdriver test case

The following code is written using selenium python web driver which is run in saucelabs.I am providing the browser name,version and platform in a list,how do i do the same by providing the browser details through command line arguments? I am using py.test to execute the test cases.
import os
import sys
import httplib
import base64
import json
import new
import unittest
import sauceclient
from selenium import webdriver
from sauceclient import SauceClient
# it's best to remove the hardcoded defaults and always get these values
# from environment variables
USERNAME = os.environ.get('SAUCE_USERNAME', "ranjanprabhub")
ACCESS_KEY = os.environ.get('SAUCE_ACCESS_KEY', "ecec4dd0-d8da-49b9-b719-17e2c43d0165")
sauce = SauceClient(USERNAME, ACCESS_KEY)
browsers = [{"platform": "Mac OS X 10.9",
"browserName": "chrome",
"version": ""},
]
def on_platforms(platforms):
def decorator(base_class):
module = sys.modules[base_class.__module__].__dict__
for i, platform in enumerate(platforms):
d = dict(base_class.__dict__)
d['desired_capabilities'] = platform
name = "%s_%s" % (base_class.__name__, i + 1)
module[name] = new.classobj(name, (base_class,), d)
return decorator
#on_platforms(browsers)
class SauceSampleTest(unittest.TestCase):
def setUp(self):
self.desired_capabilities['name'] = self.id()
sauce_url = "http://%s:%s#ondemand.saucelabs.com:80/wd/hub"
self.driver = webdriver.Remote(
desired_capabilities=self.desired_capabilities,
command_executor=sauce_url % (USERNAME, ACCESS_KEY)
)
self.driver.implicitly_wait(30)
def test_sauce(self):
self.driver.get('http://saucelabs.com/test/guinea-pig')
assert "I am a page title - Sauce Labs" in self.driver.title
comments = self.driver.find_element_by_id('comments')
comments.send_keys('Hello! I am some example comments.'
' I should be in the page after submitting the form')
self.driver.find_element_by_id('submit').click()
commented = self.driver.find_element_by_id('your_comments')
assert ('Your comments: Hello! I am some example comments.'
' I should be in the page after submitting the form'
in commented.text)
body = self.driver.find_element_by_xpath('//body')
assert 'I am some other page content' not in body.text
self.driver.find_elements_by_link_text('i am a link')[0].click()
body = self.driver.find_element_by_xpath('//body')
assert 'I am some other page content' in body.text
def tearDown(self):
print("Link to your job: https://saucelabs.com/jobs/%s" % self.driver.session_id)
try:
if sys.exc_info() == (None, None, None):
sauce.jobs.update_job(self.driver.session_id, passed=True)
else:
sauce.jobs.update_job(self.driver.session_id, passed=False)
finally:
self.driver.quit()
So this is a bit complicated because you can pass an array of browsers into the #on_platforms decorator. My solution will only work for a single browser, as it looks like that's what you're doing right now.
For the current, single browser, situation -- you're looking for argparse. Here's my suggested fix:
import argparse
def setup_parser():
parser = argparse.ArgumentParser(description='Automation Testing!')
parser.add_argument('-p', '--platform', help='Platform for desired_caps', default='Mac OS X 10.9')
parser.add_argument('-b', '--browser-name', help='Browser Name for desired_caps', default='chrome')
parser.add_argument('-v', '--version', default='')
args = vars(parser.parse_args())
return args
desired_caps = setup_parser()
browsers = [desired_caps]
print browsers
But if you're looking to test multiple browsers (which I suggest you do!), you should not try and use command line arguments for the desired_caps of each individual browser. You should instead load a json config file for the browsers and the desired_caps for each one that you want Sauce to run.
Maybe have a different config file for each set of browsers, and then use command line arguments to pass in the config files you want to load.

Django - is there a way to view the queries being executed by the ORM? [duplicate]

This question already has answers here:
Getting all queries that django run on postgresql
(4 answers)
Closed 7 years ago.
Like, have them logged to the console?
I usually use http://github.com/robhudson/django-debug-toolbar
where it tells you the queries and how long they actually take to execute.
Certainly. From the command line/shell:
queryset = Model.objects.filter()
print queryset.query
Variant 2:
from django.db import connection
queryset = Model.objects.filter()
queryset[0] # This variant needs the queryset to be accessed. Hence.
print connection.queries
If you want to print the queries used to render a page then you can use the toolbar as #Meitham suggested or use this Django snippet.
You can decorate a request handler or other function with this and it will print the sql nicely formated with totals at the end.
from functools import wraps
from django.utils import termcolors
format_ok = termcolors.make_style(opts=('bold',), fg='green')
format_warning = termcolors.make_style(opts=('bold',), fg='yellow')
format_error = termcolors.make_style(opts=('bold',), fg='red')
try:
from pygments import highlight
from pygments.lexers import SqlLexer
from pygments.formatters import TerminalFormatter
pygments_sql_lexer = SqlLexer()
pygments_terminal_formatter = TerminalFormatter()
highlight_sql = lambda s: highlight(s, pygments_sql_lexer,
pygments_terminal_formatter)
except ImportError:
highlight_sql = lambda s: s
def debug_sql(f):
"""
Turn SQL statement debugging on for a test run.
"""
#wraps(f)
def wrapper(*a, **kw):
from django.conf import settings
from django.db import connection
try:
debug = settings.DEBUG
settings.DEBUG = True
connection.queries = []
return f(*a, **kw)
finally:
total_time = 0
for q in connection.queries:
fmt = format_ok
t = float(q['time'])
total_time += t
if t > 1:
fmt = format_error
elif t > 0.3:
fmt = format_warning
print '[%s] %s' % (fmt(q['time']), highlight_sql(q['sql']))
print "total time =", total_time
print "num queries =", len(connection.queries)
settings.DEBUG = debug
return wrapper

Django: is there a way to count SQL queries from an unit test?

I am trying to find out the number of queries executed by a utility function. I have written a unit test for this function and the function is working well. What I would like to do is track the number of SQL queries executed by the function so that I can see if there is any improvement after some refactoring.
def do_something_in_the_database():
# Does something in the database
# return result
class DoSomethingTests(django.test.TestCase):
def test_function_returns_correct_values(self):
self.assertEqual(n, <number of SQL queries executed>)
EDIT: I found out that there is a pending Django feature request for this. However the ticket is still open. In the meantime is there another way to go about this?
Since Django 1.3 there is a assertNumQueries available exactly for this purpose.
One way to use it (as of Django 3.2) is as a context manager:
# measure queries of some_func and some_func2
with self.assertNumQueries(2):
result = some_func()
result2 = some_func2()
Vinay's response is correct, with one minor addition.
Django's unit test framework actually sets DEBUG to False when it runs, so no matter what you have in settings.py, you will not have anything populated in connection.queries in your unit test unless you re-enable debug mode. The Django docs explain the rationale for this as:
Regardless of the value of the DEBUG setting in your configuration file, all Django tests run with DEBUG=False. This is to ensure that the observed output of your code matches what will be seen in a production setting.
If you're certain that enabling debug will not affect your tests (such as if you're specifically testing DB hits, as it sounds like you are), the solution is to temporarily re-enable debug in your unit test, then set it back afterward:
def test_myself(self):
from django.conf import settings
from django.db import connection
settings.DEBUG = True
connection.queries = []
# Test code as normal
self.assert_(connection.queries)
settings.DEBUG = False
If you are using pytest, pytest-django has django_assert_num_queries fixture for this purpose:
def test_queries(django_assert_num_queries):
with django_assert_num_queries(3):
Item.objects.create('foo')
Item.objects.create('bar')
Item.objects.create('baz')
If you don't want use TestCase (with assertNumQueries) or change settings to DEBUG=True, you can use context manager CaptureQueriesContext (same as assertNumQueries using).
from django.db import ConnectionHandler
from django.test.utils import CaptureQueriesContext
DB_NAME = "default" # name of db configured in settings you want to use - "default" is standard
connection = ConnectionHandler()[DB_NAME]
with CaptureQueriesContext(connection) as context:
... # do your thing
num_queries = context.initial_queries - context.final_queries
assert num_queries == expected_num_queries
db settings
In modern Django (>=1.8) it's well documented (it's also documented for 1.7) here, you have the method reset_queries instead of assigning connection.queries=[] which indeed is raising an error, something like that works on django>=1.8:
class QueriesTests(django.test.TestCase):
def test_queries(self):
from django.conf import settings
from django.db import connection, reset_queries
try:
settings.DEBUG = True
# [... your ORM code ...]
self.assertEquals(len(connection.queries), num_of_expected_queries)
finally:
settings.DEBUG = False
reset_queries()
You may also consider resetting queries on setUp/tearDown to ensure queries are reset for each test instead of doing it on finally clause, but this way is more explicit (although more verbose), or you can use reset_queries in the try clause as many times as you need to evaluate queries counting from 0.
Here is the working prototype of context manager withAssertNumQueriesLessThan
import json
from contextlib import contextmanager
from django.test.utils import CaptureQueriesContext
from django.db import connections
#contextmanager
def withAssertNumQueriesLessThan(self, value, using='default', verbose=False):
with CaptureQueriesContext(connections[using]) as context:
yield # your test will be run here
if verbose:
msg = "\r\n%s" % json.dumps(context.captured_queries, indent=4)
else:
msg = None
self.assertLess(len(context.captured_queries), value, msg=msg)
It can be simply used in your unit tests for example for checking the number of queries per Django REST API call
with self.withAssertNumQueriesLessThan(10):
response = self.client.get('contacts/')
self.assertEqual(response.status_code, 200)
Also you can provide exact DB using and verbose if you want to pretty-print list of actual queries to stdout
If you have DEBUG set to True in your settings.py (presumably so in your test environment) then you can count queries executed in your test as follows:
from django.db import connection
class DoSomethingTests(django.test.TestCase):
def test_something_or_other(self):
num_queries_old = len(connection.queries)
do_something_in_the_database()
num_queries_new = len(connection.queries)
self.assertEqual(n, num_queries_new - num_queries_old)
If you want to use a decorator for that there is a nice gist:
import functools
import sys
import re
from django.conf import settings
from django.db import connection
def shrink_select(sql):
return re.sub("^SELECT(.+)FROM", "SELECT .. FROM", sql)
def shrink_update(sql):
return re.sub("SET(.+)WHERE", "SET .. WHERE", sql)
def shrink_insert(sql):
return re.sub("\((.+)\)", "(..)", sql)
def shrink_sql(sql):
return shrink_update(shrink_insert(shrink_select(sql)))
def _err_msg(num, expected_num, verbose, func=None):
func_name = "%s:" % func.__name__ if func else ""
msg = "%s Expected number of queries is %d, actual number is %d.\n" % (func_name, expected_num, num,)
if verbose > 0:
queries = [query['sql'] for query in connection.queries[-num:]]
if verbose == 1:
queries = [shrink_sql(sql) for sql in queries]
msg += "== Queries == \n" +"\n".join(queries)
return msg
def assertNumQueries(expected_num, verbose=1):
class DecoratorOrContextManager(object):
def __call__(self, func): # decorator
#functools.wraps(func)
def inner(*args, **kwargs):
handled = False
try:
self.__enter__()
return func(*args, **kwargs)
except:
self.__exit__(*sys.exc_info())
handled = True
raise
finally:
if not handled:
self.__exit__(None, None, None)
return inner
def __enter__(self):
self.old_debug = settings.DEBUG
self.old_query_count = len(connection.queries)
settings.DEBUG = True
def __exit__(self, type, value, traceback):
if not type:
num = len(connection.queries) - self.old_query_count
assert expected_num == num, _err_msg(num, expected_num, verbose)
settings.DEBUG = self.old_debug
return DecoratorOrContextManager()