# -*- coding: utf-8 -*-

'''

Created on Mar 22, 2012

@author: ymh

Module directly inspired by tweetstream

'''

import time

import requests

from requests.utils import stream_decode_response_unicode

class BaseStream(object):

    """A network connection to Twitters streaming API

    :param auth: requests auth object.

    :keyword catchup: Number of tweets from the past to get before switching to

      live stream.

    :keyword raw: If True, return each tweet's raw data direct from the socket,

      without UTF8 decoding or parsing, rather than a parsed object. The

      default is False.

    :keyword timeout: If non-None, set a timeout in seconds on the receiving

      socket. Certain types of network problems (e.g., disconnecting a VPN)

      can cause the connection to hang, leading to indefinite blocking that

      requires kill -9 to resolve. Setting a timeout leads to an orderly

      shutdown in these cases. The default is None (i.e., no timeout).

    :keyword url: Endpoint URL for the object. Note: you should not

      need to edit this. It's present to make testing easier.

    .. attribute:: connected

        True if the object is currently connected to the stream.

    .. attribute:: url

        The URL to which the object is connected

    .. attribute:: starttime

        The timestamp, in seconds since the epoch, the object connected to the

        streaming api.

    .. attribute:: count

        The number of tweets that have been returned by the object.

    .. attribute:: rate

        The rate at which tweets have been returned from the object as a

        float. see also :attr: `rate_period`.

    .. attribute:: rate_period

        The ammount of time to sample tweets to calculate tweet rate. By

        default 10 seconds. Changes to this attribute will not be reflected

        until the next time the rate is calculated. The rate of tweets vary

        with time of day etc. so it's usefull to set this to something

        sensible.

    .. attribute:: user_agent

        User agent string that will be included in the request. NOTE: This can

        not be changed after the connection has been made. This property must

        thus be set before accessing the iterator. The default is set in

        :attr: `USER_AGENT`.

    """

    def __init__(self, auth,

        self._conn = None

        self._rate_ts = None

        self._rate_cnt = 0

        self._auth = auth

        self.raw_mode = raw

        self.timeout = timeout

        self._compressed = compressed

        self.rate_period = 10  # in seconds

        self.connected = False

        self.starttime = None

        self.count = 0

        self.rate = 0

        self.user_agent = USER_AGENT

        if url: self.url = url

        self.muststop = False

        self._logger = logger

        self._iter = self.__iter__()

    def __enter__(self):

        return self

    def __exit__(self, *params):

        self.close()

        return False

    def _init_conn(self):

        """Open the connection to the twitter server"""

        if self._logger : self._logger.debug("BaseStream Open the connection to the twitter server")

        headers = {'User-Agent': self.user_agent}

        if self._compressed:

            headers['Accept-Encoding'] = "deflate, gzip"

        postdata = self._get_post_data() or {}

        postdata['stall_warnings'] = 'true'

        if self._logger : self._logger.debug("BaseStream init connection url " + repr(self.url))

        if self._logger : self._logger.debug("BaseStream init connection headers " + repr(headers))

        if self._logger : self._logger.debug("BaseStream init connection data " + repr(postdata))

        self._resp = requests.post(self.url, auth=self._auth, headers=headers, data=postdata, stream=True)

        if self._logger : self._logger.debug("BaseStream init connection " + repr(self._resp))

        self._resp.raise_for_status()

        self.connected = True

        if not self._rate_ts:

            self._rate_ts = time.time()

        if not self.starttime:

            self.starttime = time.time()

    def _get_post_data(self):

        """Subclasses that need to add post data to the request can override

        this method and return post data. The data should be in the format

        returned by urllib.urlencode."""

        return None

    def testmuststop(self):

        if callable(self.muststop):

        else:

            return self.muststop

    def _update_rate(self):

        rate_time = time.time() - self._rate_ts

        if not self._rate_ts or rate_time > self.rate_period:

            self.rate = self._rate_cnt / rate_time

            self._rate_cnt = 0

            self._rate_ts = time.time()

    def __iter__(self):

        if self._logger : self._logger.debug("BaseStream __iter__")

        if not self.connected:

            if self._logger : self._logger.debug("BaseStream __iter__ not connected, connecting")

            self._init_conn()

        if self._logger : self._logger.debug("BaseStream __iter__ connected")

            if not line:

                continue

            if (self.raw_mode):

                tweet = line

            else:

                try:

                except ValueError:

                    self.close()

                    raise ConnectionError("Got invalid data from twitter", details=line)

                self.count += 1

                self._rate_cnt += 1

            self._update_rate()

            yield tweet

    def close(self):

        """

        Close the connection to the streaming server.

        """

        self.connected = False

class FilterStream(BaseStream):

    url = "https://stream.twitter.com/1.1/statuses/filter.json"

    def __init__(self, auth, follow=None, locations=None,

        self._follow = follow

        self._locations = locations

        self._track = track

        # remove follow, locations, track

    def _get_post_data(self):

        postdata = {}

        if self._follow: postdata["follow"] = ",".join([str(e) for e in self._follow])

        if self._locations: postdata["locations"] = ",".join(self._locations)

        if self._track: postdata["track"] = ",".join(self._track)

        return postdata

class SafeStreamWrapper(object):

    def __init__(self, base_stream, logger=None, error_cb=None, max_reconnects=-1, initial_tcp_wait=250, initial_http_wait=5000, max_wait=240000):

        self._stream = base_stream

        self._logger = logger

        self._error_cb = error_cb

        self._max_reconnects = max_reconnects

        self._initial_tcp_wait = initial_tcp_wait

        self._initial_http_wait = initial_http_wait

        self._max_wait = max_wait

        self._retry_wait = 0

        self._retry_nb = 0

        self._reconnects = 0

    def __post_process_error(self,e):

        # Note: error_cb is not called on the last error since we

        # raise a ConnectionError instead

        if  callable(self._error_cb):

            self._error_cb(e)

        if self._logger: self._logger.info("stream sleeping for %d ms " % self._retry_wait)

        time.sleep(float(self._retry_wait)/1000.0)

    def __process_tcp_error(self,e):

        if self._logger: self._logger.debug("connection error type :" + repr(type(e)))

        if self._logger: self._logger.debug("connection error :" + repr(e))

        self._reconnects += 1

        if self._max_reconnects >= 0 and self._reconnects > self._max_reconnects:

            raise ConnectionError("Too many retries")

        if self._retry_wait < self._max_wait:

            self._retry_wait += self._initial_tcp_wait

            if self._retry_wait > self._max_wait:

                self._retry_wait = self._max_wait

        self.__post_process_error(e)

    def __process_http_error(self,e):

        if self._logger: self._logger.debug("http error type %s" % (repr(type(e))))

        if self._logger: self._logger.debug("http error on %s : %s" % (e.response.url,e.message))

        if self._retry_wait < self._max_wait:

            self._retry_wait = 2*self._retry_wait if self._retry_wait > 0 else self._initial_http_wait

            if self._retry_wait > self._max_wait:

                self._retry_wait = self._max_wait

        self.__post_process_error(e)

    def __iter__(self):

        while not self._stream.testmuststop():

            self._retry_nb += 1

            try:

                if self._logger: self._logger.debug("inner loop")

                for tweet in self._stream:

                    if self._logger: self._logger.debug("tweet : " + repr(tweet))

                    self._reconnects = 0

                    self._retry_wait = 0

                    if not tweet.strip():

                        if self._logger: self._logger.debug("Empty Tweet received : PING")

                        continue

                    yield tweet

            except requests.exceptions.HTTPError as e:

                if e.response.status_code == 401:

                if e.response.status_code > 200:

                    self.__process_http_error(e)

                else:

                    self.__process_tcp_error(e)

            except (ConnectionError, requests.exceptions.ConnectionError, requests.exceptions.Timeout, requests.exceptions.RequestException) as e:

                self.__process_tcp_error(e)