view roundup/rate_limit.py @ 7752:b2dbab2b34bc

fix(refactor): multiple fixups using ruff linter; more testing. Converting to using the ruff linter and its rulesets. Fixed a number of issues. admin.py: sort imports use immutable tuples as default value markers for parameters where a None value is valid. reduced some loops to list comprehensions for performance used ternary to simplify some if statements named some variables to make them less magic (e.g. _default_savepoint_setting = 1000) fixed some tests for argument counts < 2 becomes != 2 so 3 is an error. moved exception handlers outside of loops for performance where exception handler will abort loop anyway. renamed variables called 'id' or 'dir' as they shadow builtin commands. fix translations of form _("string %s" % value) -> _("string %s") % value so translation will be looked up with the key before substitution. end dicts, tuples with a trailing comma to reduce missing comma errors if modified simplified sorted(list(self.setting.keys())) to sorted(self.setting.keys()) as sorted consumes whole list. in if conditions put compared variable on left and threshold condition on right. (no yoda conditions) multiple noqa: suppression removed unneeded noqa as lint rulesets are a bit different do_get - refactor output printing logic: Use fast return if not special formatting is requested; use isinstance with a tuple rather than two isinstance calls; cleaned up flow and removed comments on algorithm as it can be easily read from the code. do_filter, do_find - refactor output printing logic. Reduce duplicate code. do_find - renamed variable 'value' that was set inside a loop. The loop index variable was also named 'value'. do_pragma - added hint to use list subcommand if setting was not found. Replaced condition 'type(x) is bool' with 'isinstance(x, bool)' for various types. test_admin.py added testing for do_list better test coverage for do_get includes: -S and -d for multilinks, error case for -d with non-link. better testing for do_find including all output modes better testing for do_filter including all output modes fixed expected output for do_pragma that now includes hint to use pragma list if setting not found.
author John Rouillard <rouilj@ieee.org>
date Fri, 01 Mar 2024 14:53:18 -0500
parents 5fbd3af526bd
children 224ccb8b49ca
line wrap: on
line source

# Originaly from
# https://smarketshq.com/implementing-gcra-in-python-5df1f11aaa96?gi=4b9725f99bfa
# with imports, modifications for python 2, implementation of
# set/get_tat and marshaling as string, support for testonly
# and status method.

from datetime import timedelta, datetime

try:
    # used by python 3.11 and newer use tz aware dates
    from datetime import UTC
    dt_min = datetime.min.replace(tzinfo=UTC)
    # start of unix epoch
    dt_epoch = datetime(1970, 1, 1, tzinfo=UTC)
    fromisoformat = datetime.fromisoformat
except ImportError:
    # python 2.7 and older than 3.11 - use naive dates
    dt_min = datetime.min
    dt_epoch = datetime(1970, 1, 1)
    def fromisoformat(date):
        # only for naive dates
        return datetime.strptime(date, "%Y-%m-%dT%H:%M:%S.%f")        

from roundup.anypy.datetime_ import utcnow


class RateLimit:  # pylint: disable=too-few-public-methods
    def __init__(self, count, period):
        self.count = count
        self.period = period

    @property
    def inverse(self):
        return self.period.total_seconds() / self.count


class Gcra:
    def __init__(self):
        self.memory = {}

    def get_tat(self, key):
        # This should return a previous tat for the key or the current time.
        if key in self.memory:
            return self.memory[key]
        else:
            return dt_min

    def set_tat(self, key, tat):
        self.memory[key] = tat

    def get_tat_as_string(self, key):
        # get value as string:
        #  YYYY-MM-DDTHH:MM:SS.mmmmmm
        # to allow it to be marshalled/unmarshaled
        if key in self.memory:
            return self.memory[key].isoformat()
        else:
            return dt_min.isoformat()

    def set_tat_as_string(self, key, tat):
        # Take value as string and unmarshall:
        #  YYYY-MM-DDTHH:MM:SS.mmmmmm
        # to datetime
        self.memory[key] = fromisoformat(tat)

    def update(self, key, limit, testonly=False):
        '''Determine if the item associated with the key should be
           rejected given the RateLimit limit.
        '''
        now = utcnow()
        tat = max(self.get_tat(key), now)
        separation = (tat - now).total_seconds()
        max_interval = limit.period.total_seconds() - limit.inverse
        if separation > max_interval:
            reject = True
        else:
            reject = False
            if not testonly:
                new_tat = max(tat, now) + timedelta(seconds=limit.inverse)
                self.set_tat(key, new_tat)
        return reject

    def status(self, key, limit):
        '''Return status suitable for displaying as headers:
            X-RateLimit-Limit: calls allowed per period. Period/window
                is not specified in any api I found.
            X-RateLimit-Limit-Period: Non standard. Defines period in
                seconds for RateLimit-Limit.
            X-RateLimit-Remaining: How many calls are left in this window.
            X-RateLimit-Reset: window ends in this many seconds (not an
                 epoch timestamp) and all RateLimit-Limit calls are
                 available again.
            Retry-After: if user's request fails, this is the next time there
                 will be at least 1 available call to be consumed.
        '''

        ret = {}
        tat = self.get_tat(key)
        # static defined headers according to limit
        # all values are strings as that is required when used as headers
        ret['X-RateLimit-Limit'] = str(limit.count)
        ret['X-RateLimit-Limit-Period'] = str(
                                           int(
                                            limit.period.total_seconds())
                                          )

        # status of current limit as of now
        now = utcnow()

        current_count = int((limit.period - (tat - now)).total_seconds() /
                            limit.inverse)
        ret['X-RateLimit-Remaining'] = str(min(current_count, limit.count))

        # tat_in_epochsec = (tat - datetime(1970, 1, 1)).total_seconds()
        seconds_to_tat = (tat - now).total_seconds()
        ret['X-RateLimit-Reset'] = str(max(seconds_to_tat, 0))
        ret['X-RateLimit-Reset-date'] = "%s" % tat
        ret['Now'] = str((now - dt_epoch).total_seconds())
        ret['Now-date'] = "%s" % now

        if self.update(key, limit, testonly=True):
            # A new request would be rejected if it was processes.
            # The user has to wait until an item is dequeued.
            # One item is dequeued every limit.inverse seconds.
            ret['Retry-After'] = str(int(limit.inverse))
            ret['Retry-After-Timestamp'] = "%s" % \
                    (now + timedelta(seconds=limit.inverse))  # noqa: E127
        else:
            # if we are not rejected, the user can post another
            # attempt immediately.
            # Do we even need this header if not rejected?
            # RFC implies this is used with a 503 (or presumably
            # 429 which may postdate the rfc). So if no error, no header?
            # ret['Retry-After'] = '0'
            # ret['Retry-After-Timestamp'] = str(ret['Now-date'])
            pass

        return ret

Roundup Issue Tracker: http://roundup-tracker.org/