def main(configFile=None):
''' Takes the dotcloud default admin privs, authorises on the db,
creates the user I've specified and returns. '''
# Get the parameters that were set up by dotcloud
dcParams = getEnvironment()
print "got DC environment settings."
reParams = getRedisEnvironment()
print "got redis environment settings."
# Authenticate on the admin db
try:
c, adminDbh = mdb.getHandle(host=dcParams.mongoHost, port=dcParams.mongoPort, db='admin', user=dcParams.adminUser, password=dcParams.adminPass)
print 'got handle'
except:
print "Failed to get handle under admin."
# Authentication of the administrator
#try:
# auth = adminDbh.authenticate(dcParams.adminUser, dcParams.adminPass)
#except Exception, e:
# print "Failed to authenticate with mongo db."
# print e
# Create a new user
p = getConfigParameters(configFile)
# Switch the database handle to that being used from the admin one
dbh = c[p.db]
success = dbh.add_user(p.dbUser, p.dbPassword)
c.disconnect()
try:
# Authenticate on the admin db
c, dbh = mdb.getHandle(host=dcParams.mongoHost, port=dcParams.mongoPort, db=p.db, user=p.dbUser, password=p.dbPassword)
print 'Connected to the normal db: %s' %(p.db)
except:
logging.critical("Failed to connect to db and get handle as user.", exc_info=True)
sys.exit()
# Write out the new information to the regular config file
try:
writeConfigFile(configFile, dcParams)
print 'Writing out mongo config info.'
writeConfigFileRedis(configFile, reParams)
print 'Writing out redis config'
except:
logging.critical("Failed in writing params back to config file.", exc_info=True)
mdb.close(c, dbh)
def testInsertBaselineDoc(self):
''' Inserts a completed baseline document into the baseline collection.'''
# Connect and get handle
c, dbh = mdb.getHandle()
dbh = mdb.setupCollections(dbh, dropCollections=True)
# Build a keyword object
testKywd = kw(keyword='keyword1',
timeStamp=datetime.datetime(2011,6,22,12,10,45),
lat=34.4, lon=45.5,
text='this text contained the hashtag #keyword1',
tweetID=346664, userID=4444, source='twitter')
# Instantiate the baseline object/class
baseLine = bl.baseline(kywd=testKywd,cellBuildPeriod=600)
# Build the document and insert it
doc = baseLine.buildDoc()
bl.insertBaselineDoc(dbh, doc)
res = dbh.baseline.find()[0]
print res
self.assertEquals(res['keyword'], 'keyword1')
self.assertEquals(res['mgrs'], '38SND4595706622')
self.assertEquals(res['mgrsPrecision'], 10)
# Close the connection
mdb.close(c, dbh)
def __init__(self, kywd, c=None, dbh=None, host=None, port=None, db=None, baselinePrecision=[]):
''' Constructor. '''
# Connection for this baseline class
if not c and not dbh:
# Get a connection to the db
self.c, self.dbh = mdb.getHandle(host=host, port=port, db=db)
else:
self.c, self.dbh = c, dbh
self.collection = 'timeseries'
# Bad, bad version of inheriting keyword - NEED TO FIX THIS
self.keyword = kywd.keyword
self.timeStamp = kywd.timeStamp
self.mgrs = kywd.mgrs
self.mgrsPrecision = kywd.mgrsPrecision
# Has this keyword ever been seen before at this location?
self.outputs = {}
# When was the last baseline processed (units = hour or minute or second; precision = int val)
# Or... what was the most recent baseline run - parameters come from top level
unit, precision = baselinePrecision
self.baselineTimeStamp = truncateTimeStamp(self.timeStamp, unit, precision)
# Checks to see whether it exists at all or if it needs updating.
# Outside the object, this is used to decide whether to continue with the processing
self.needUpdate = self.needUpdating()
def main(cleanup, ageOff, protectedSubs=None):
''' Coordinates which element to cleanup - subscriptions including remote delete of subs from instagram
or event data - getting rid of the documents that contain the media and metadata'''
# If there is a command to remove or keep protected subs, use it
if protectedSubs:
protectedSubs = bool(protectedSubs)
# Get the config information
os.chdir('/home/dotcloud/code/')
cwd = os.getcwd()
cfgs = os.path.join(cwd, 'config/crowded.cfg')
p = getConfigParameters(cfgs)
# The mongo bits
c, dbh = mdb.getHandle(host=p.dbHost, port=p.dbPort, db=p.db, user=p.dbUser, password=p.dbPassword)
# Whether to cleanup the subscriptions and subscription collection
if cleanup == 'subs':
subsCollHandle=dbh[p.subsCollection]
res = ageOffSubscriptions(p, subsCollHandle, ageOff=ageOff, protectedSubs=protectedSubs)
print datetime.datetime.utcnow(), res
# Or the events metadata collection
elif cleanup == 'events':
evCollHandle=dbh[p.eventsCollection]
res = ageOffMetadata(evCollHandle, ageOff=ageOff, protectMedia=protectedSubs)
print datetime.datetime.utcnow(), res
else:
print 'Provide either subs or events as the first argument depending on what you want to clean up.'
def main():
""" """
# Connect and get db and collection handle
try:
c, dbh = mdb.getHandle(p.dbHost, p.dbPort, p.db, p.dbUser, p.dbPassword)
collectionHandle = dbh[p.camsCollection]
except:
logging.critical("DB connection Failed", exc_info=True)
# Get the feed content
feedContent = hitFeed(p.feedUrl)
if not feedContent:
logging.critical("** SCRIPT EXIT **\n%s\n\n" % ("=" * 52))
sys.exit()
# Break out the content into head and items
header, rootUrl, cameras = extractContent(feedContent)
if not header or not rootUrl or not cameras:
logging.critical("** SCRIPT EXIT **\n%s\n\n" % ("=" * 52))
sys.exit()
# Build the camera root URL
rootUrl = p.tflDomain + rootUrl
fc = feedChannel(header)
# Deal with each of the items
for camera in cameras:
# Build an 'item' object based on the RSS item
item = feedItem(fc, camera, rootUrl)
item.buildGeoJson()
# Insert the document into mongo
response = mongoInsert(collectionHandle, item)
def testUpdateDocument(self):
''' Function updates/increments a specific hour.minute in a document. '''
# Get connection to mongo
c, dbh = mdb.getHandle()
dbh = mdb.setupCollections(dbh, dropCollections=True) # Set up collections
# New timeseries object with data
ts = timeSeries()
ts.importData(self.kw, blockPrecision=24)
success = ts.insertBlankDoc()
self.assertEquals(success, 1)
# Update/increment a specific hour.minute
ts.updateCount()
# Run a query for this item
outDocs = dbh.timeseries.find({'data.12.1':1})
for doc in outDocs:
print doc
self.assertEquals(doc['mgrs'], '38SND4595706622')
# Close the connection
mdb.close(c, dbh)
def MongoLookup(self):
''' Fn checks whether a timeseries document already exists for this period. '''
# Get connection to mongo
c, dbh = mdb.getHandle()
dbh = mdb.setupCollections(dbh, dropCollections=True) # Set up collections
# New timeseries object with data
ts = timeSeries()
ts.importData(self.kw, blockPrecision=1)
# Check the count - should be 0 before the doc gets inserted
count = ts.mongoLookup()
self.assertEquals(count, 0)
# Build and insert a new mongo formatted document
success = ts.insertBlankDoc()
# Count should be 1 now that the document has been inserted
count = ts.mongoLookup()
self.assertEquals(count, 1)
# Clean up, remove he content and close the connection
#dbh.timeseries.remove()
mdb.close(c, dbh)
def main():
# Config file parameters
pathIn = '/Users/brantinghamr/Documents/Code/eclipseWorkspace/bam/config/'
fileIn = 'preAllocateTimeSeries.cfg'
# Get parameters from config
p = params(pathIn, fileIn)
# Connect and get db and collection handle
c, dbh = mdb.getHandle(p.host, p.port, p.db)
collectionHandle = dbh[p.coll]
# Current datetime
#today = datetime.datetime.utcnow().replace(hour=0, minute=0,second=0,microsecond=0)
today = datetime.datetime(2011,5,1)
# Build some blank data
blankDataArr = buildBlankData()
# A list to hold the timeseries we need to pre-allocate for
# Get pairs to be pre-allocated from yesterday - lookback is in days
if 'yesterday' in p.baselineTypes:
preAllocate, minCount, maxCount = getCommonMgrsAndKeyword(collectionHandle, p.mgrsPrecision, p.nothingFoundKeyword, today, lookback=1)
# Now loop the keyword/mgrs pairs and build new timeseries documents for today
for item in preAllocate:
response = insertDoc(collectionHandle, item['mgrs'], p.mgrsPrecision, item['keyword'], 'twitter', today, buildBlankData())
mdb.close(c, dbh)
def testGetCurrentTags(self):
import mdb
cwd = os.getcwd()
parent = os.path.dirname(cwd)
cfgs = os.path.join(parent, 'config/twitterCrowded.cfg')
p = getConfigParameters(cfgs)
# The mongo bits
try:
c, dbh = mdb.getHandle(host=p.dbHost,
port=p.dbPort,
db=p.db,
user=p.dbUser,
password=p.dbPassword)
evCollHandle = dbh[p.eventsCollection]
except:
print "Failed to connect to mongo."
sys.exit(1)
res = cf.getCurrentTags(evCollHandle, 'shitbrick')
self.assertEquals(res, ['hellworld', 'fuckhole', 'shitbrick'])
# Quick test chucked in
results = cf.getQueryBBox(evCollHandle)
print results
def testlastBaselined(self):
''' Builds a baseline document for inserting.'''
# Connect and get handle
c, dbh = mdb.getHandle()
dbh = mdb.setupCollections(dbh, dropCollections=True)
# Build a keyword object
testKywd = kw(keyword='keyword1',
timeStamp=datetime.datetime(2011,6,22,12,10,45),
lat=34.4, lon=45.5,
text='this text contained the hashtag #keyword1',
tweetID=346664, userID=4444, source='twitter')
# Create a new baseline object
baseLine = bl.baseline(kywd=testKywd, cellBuildPeriod=600)
baseLine.outputs['days30_all'] = 0.5
baseLine.outputs['days7_all'] = 0.4
baseLine.outputs['hrs30_all'] = 0.3
baseLine.outputs['days30_weekly'] = 0.2
baseLine.outputs['days7_daily'] = 0.1
doc = baseLine.buildDoc()
bl.insertBaselineDoc(dbh, doc)
# Method returns the date of last baseline calculation
lastBaseline = baseLine.lastBaselined()
self.assertEquals(lastBaseline, datetime.datetime(2011,6,22,12,10))
# Close the connection
mdb.close(c, dbh)
def __init__(self, c=None, dbh=None, host=None, port=None, db=None):
''' instantiate the object and attributes. ***NOT TESTED*** '''
if not c and not dbh:
# Get a connection to the db
self.c, self.dbh = mdb.getHandle(host=host, port=port, db=db)
else:
self.c, self.dbh = c, dbh
def main(p, mediaOnly=None):
""" Coordinates a new twitter stream connection"""
# Logging config
logFile = os.path.join(p.errorPath, p.connErrorFile)
logging.basicConfig(filename=logFile, format="%(levelname)s:: %(asctime)s %(message)s", level=p.logLevel)
# The mongo bits
try:
c, dbh = mdb.getHandle(host=p.dbHost, port=p.dbPort, db=p.db, user=p.dbUser, password=p.dbPassword)
evCollHandle = dbh[p.eventsCollection]
except:
logging.critical("Failed to connect to db and authenticate.", exc_info=True)
sys.exit()
# Here's the redis queue for managing the tweets as they come in
try:
q = RedisQueue(p.redisName, host=p.redisHost, password=p.redisPassword, port=p.redisPort, db=0)
except:
logging.critical("REDIS: Failed to connect in connectionClient.py. ", exc_info=True)
sys.exit()
# Connection placeholder in case the exception catches the drop out
connection = True
while connection == True:
# Get the existing tags and add the current
try:
tags = cf.getCurrentTags(evCollHandle)
except:
tags = None
logging.error("Failed to get current tags from db.", exc_info=True)
# Build the building boxes
try:
bboxes = cf.getCurrentBBoxes(evCollHandle)
except:
bboxes = None
logging.error("Failed to get current BBOXes from db.", exc_info=True)
if not tags and not bboxes:
logging.warning("Currently no tags or bboxes in the db.")
sys.exit()
try:
print tags, bboxes
with tweetstream.FilterStream(p.sourceUser, p.sourcePassword, track=tags, locations=bboxes) as stream:
for tweet in stream:
if mediaOnly:
try:
q.put(json.dumps(tweet))
except:
logging.critical("Failed to put tweet on redis. This tweet: \n%s" % (tweet), exc_info=True)
except tweetstream.ConnectionError:
logging.critical("Disconnected from twitter", exc_info=True)
def main(configFile, subscriptionType, source):
''' Coordinates the retrieval of public CCTV camera URLs to crowded. '''
# Get the config information into a single object
p = getConfigParameters(configFile)
#////////////////////////////////////////////////////////
if source == 'cctv':
url = p.tflUrl
elif source == 'youtube':
url = p.socialiseUrl
elif source == 'flickr':
url = p.viewFinderUrl
# More sources here and adds to the config file
#////////////////////////////////////////////////////////
# Mongo connection parameters
c, dbh = mdb.getHandle(host=p.dbHost, port=p.dbPort, db=p.db, user=p.dbUser, password=p.dbPassword)
collHandle = dbh['subs']
evCollHandle = dbh['events']
# Get the active subs
activeSubs = getActiveSubs(collHandle, type=subscriptionType)
# Barf at this point if there's nothing in subs
if not activeSubs or len(activeSubs) < 1:
mdb.close(c, dbh)
return None
# For each active active subscription, query by geography
for aSub in activeSubs:
print 'ASUB:', aSub
if subscriptionType == 'geography':
lon, lat = aSub['loc']
radius = float(aSub['radius'])
media = queryByGeo(url, lat, lon, radius)
elif subscriptionType == 'tag':
tag = aSub['objectId']
media = queryByTag(url, tag)
# For each of the images, update the correct event url list
for image in media:
# Mod the datetime into a python dt
try:
img = datetime.datetime.strptime(image['captured'], "%Y-%m-%dT%H:%M:%S")
except Exception, e:
img = datetime.datetime.strptime(image['published'], "%Y-%m-%dT%H:%M:%S")
image['dt'] = img
success = updateEvents(evCollHandle, aSub['objectId'], image)
if success == None:
print "Failed to update event ID '%s' with media: \n %s" %(aSub['objectId'], image)
def getMongoHandles(p):
''' Gets the mongo connection handle, authentication and the collection handle. '''
# Handles the mongo connections
c, dbh = mdb.getHandle(db=p.db, host=p.dbHost, port=p.dbPort)
# Authentication
try:
auth = dbh.authenticate(p.dbUser, p.dbPassword)
except Exception, e:
print "Failed to authenticate with mongo db."
print e
def getMongoHandles(p):
''' Gets the mongo connection handle, authentication and the collection handle. '''
# Handles the mongo connections
c, dbh = mdb.getHandle(db=p.db, host=p.dbHost, port=p.dbPort)
# Authentication
try:
auth = dbh.authenticate(p.dbUser, p.dbPassword)
except Exception, e:
print "Failed to authenticate with mongo db."
print e
def __init__(self):
''' Sets up the config information, database connection and builds
a blank data array for easy inserting. '''
# Reads in a load of config information
path = "/Users/brantinghamr/Documents/Code/eclipseWorkspace/bam/config/"
file = "keywordListenerConfig.cfg"
self.getConfig(path, file)
# Handles the mongo connections
self.c, self.dbh = mdb.getHandle(db=self.db, host=self.host, port=self.port)
# Build a blank timeseries array to save it being built everytime
self.blankData = buildBlankData(hours=24)
def main(p):
# The mongo bits
try:
c, dbh = mdb.getHandle(host=p.dbHost,
port=p.dbPort,
db=p.db,
user=p.dbUser,
password=p.dbPassword)
evCollHandle = dbh[p.eventsCollection]
except:
logging.critical('Failed to connect and authenticate', exc_info=True)
sys.exit()
# Get the current tags
tags = cf.getCurrentTags(evCollHandle)
# Get the current bounding boxes
queryBBoxes = cf.getQueryBBox(evCollHandle)
x = 1
while x == 1:
# Here's the redis queue for managing the tweets as they come in
try:
q = RedisQueue(p.redisName,
host=p.redisHost,
password=p.redisPassword,
port=p.redisPort,
db=0)
except:
logging.error('Failed to connect to REDIS db.', exc_info=True)
sys.exit()
# This call is blocking, so expect it to hang on this point
tweetStr = q.get()
tweet = json.loads(tweetStr)
# Work out which object/event this tweet is associated with
if tags:
tweetTags = cf.whichTags(tags, tweet)
for tweetTag in tweetTags:
success = dispatchTweet(p, tweet, tweetTag)
logging.debug("Tag-based message dispatched: %s" % (success))
if queryBBoxes:
tweetGeos = cf.matchesCurrentGeos(queryBBoxes, tweet)
for tweetGeo in tweetGeos:
success = dispatchTweet(p, tweet, tweetGeo)
logging.debug("Geo-based message dispatched: %s" % (success))
def main(configFile=None):
''' Takes the dotcloud default admin privs, authorises on the db,
creates the user I've specified and returns. '''
# Get the parameters that were set up by dotcloud
dcParams = getEnvironment()
logging.info("Mongo Params:\n%s\n%s\n%s\n%s" %(dcParams.mongoHost, dcParams.mongoPort, dcParams.adminUser, dcParams.adminPass))
# Authenticate on the admin db
try:
c, dbh = mdb.getHandle(host=dcParams.mongoHost, port=dcParams.mongoPort, db='admin', user=dcParams.adminUser, password=dcParams.adminPass)
except:
logging.critical('Failed to connect to database as admin.')
sys.exit()
# Create a new user
p = getConfigParameters(configFile)
# Switch the database handle to that being used from the admin one
dbh = c[p.db]
success = dbh.add_user(p.dbUser, p.dbPassword)
c.disconnect()
try:
# Authenticate on the admin db
c, dbh = mdb.getHandle(host=dcParams.mongoHost, port=dcParams.mongoPort, db=p.db, user=p.dbUser, password=p.dbPassword)
except:
logging.critical("Failed to connect to db and get handle as user.", exc_info=True)
sys.exit()
# Write out the new information to the regular config file
try:
writeConfigFile(configFile, dcParams)
except:
logging.critical("Failed in writing params back to config file.", exc_info=True)
mdb.close(c, dbh)
def main(configFile=None):
''' Takes the dotcloud default admin privs, authorises on the db,
creates the user I've specified and returns. '''
# Get the parameters that were set up by dotcloud
dcParams = getEnvironment()
# Authenticate on the admin db
try:
c, dbh = mdb.getHandle(host=dcParams.mongoHost, port=dcParams.mongoPort, db='admin', user=dcParams.adminUser, password=dcParams.adminPass)
except:
logging.critical('Failed to connect to database as admin.')
sys.exit()
# Create a new user
p = getConfigParameters(configFile)
# Switch the database handle to that being used from the admin one
dbh = c[p.db]
success = dbh.add_user(p.dbUser, p.dbPassword)
c.disconnect()
try:
# Authenticate on the admin db
c, dbh = mdb.getHandle(host=dcParams.mongoHost, port=dcParams.mongoPort, db=p.db, user=p.dbUser, password=p.dbPassword)
except:
logging.critical("Failed to connect to db and get handle as user.", exc_info=True)
sys.exit()
# Write out the new information to the regular config file
try:
writeConfigFile(configFile, dcParams)
print "----- writing out new config parameters."
except:
logging.critical("Failed in writing params back to config file.", exc_info=True)
mdb.close(c, dbh)
def main(configFile=None):
''' Builds the collections and indexes needed. '''
# Get the config information into a single object
p = getConfigParameters(configFile)
# Get a db handle
if p.verbose==True:
print "---- Geting Mongo Handle."
c, dbh = mdb.getHandle(host=p.dbHost, port=p.dbPort, db=p.db)
try:
auth = dbh.authenticate(p.dbUser, p.dbPassword)
except Exception, e:
print "Failed to authenticate with mongo db."
print e
def getMongoHandles(p):
''' Gets the mongo connection handle, authentication and the collection handle. '''
# Handles the mongo connections
c, dbh = mdb.getHandle(db=p.db, host=p.dbHost, port=p.dbPort)
# Authentication
try:
auth = dbh.authenticate(p.dbUser, p.dbPassword)
except:
logging.warning("Failed to authenticate with mongo db.")
collHandle = dbh[p.slangCollection]
emoCollHandle = dbh[p.emoCollection]
return c, dbh, collHandle, emoCollHandle
def testBuildFullArrayFlat(self):
'''Build a full FLATTENED array from a cursor result'''
st = datetime.datetime.utcnow()
# A keyword that went in yesterday creates a timeseries yesterday
nowDt = datetime.datetime(year=2011,month=1,day=12,hour=11,minute=1,second=1)
oneDay= datetime.timedelta(days=1)
# Get a db handle
c, dbh = mdb.getHandle()
dbh = mdb.setupCollections(dbh, dropCollections=True) # Set up collections
# Build a keyword
kword = kw(keyword='keyword1', timeStamp=nowDt-oneDay, lat=34.4, lon=45.5,
text='this text contained the hashtag #keyword1',
tweetID=346664, userID=4444, source='twitter')
# New timeseries object
ts = timeSeries()
ts.importData(kword)
success = ts.insertBlankDoc()
# Insert 2ND DOC IN THE COLLECTION
kword.timeStamp = nowDt
ts = timeSeries()
ts.importData(kword)
success = ts.insertBlankDoc()
nowDate = nowDt.replace(hour=0,minute=0,second=0,microsecond=0)
# Last 1 weeks worth of documents
resultSet = bl.getResultsPerCell(dbh, '38SND4595706622', 'keyword1', nowDate, 168)
# Close the connection
mdb.close(c, dbh)
# Inputs
period = datetime.timedelta(days=7)
dates, data = bl.buildFullArray(resultSet, nowDate, period, 1)
firstDay = dates[0]
lastDay = dates[-1]
self.assertEquals(data.shape[0], 11520)
self.assertEquals(firstDay, nowDate - period)
self.assertEquals(lastDay, nowDate)
def main(configFile=None):
''' Takes the dotcloud default admin privs, authorises on the db,
creates the user I've specified and returns. '''
# Get the parameters that were set up by dotcloud
dcParams = getEnvironment()
print dcParams.adminUser, dcParams.adminPass
# Authenticate on the admin db
c, adminDbh = mdb.getHandle(host=dcParams.mongoHost, port=dcParams.mongoPort, db='admin')
print 'got handle'
# Authentication of the administrator
try:
auth = adminDbh.authenticate(dcParams.adminUser, dcParams.adminPass)
except Exception, e:
print "Failed to authenticate with mongo db."
print e
def main(configFile=None):
''' Builds the collections and indexes needed. '''
# Get the config information into a single object
p = getConfigParameters(configFile)
try:
c, dbh = mdb.getHandle(host=p.dbHost, port=p.dbPort, db=p.db, user=p.dbUser, password=p.dbPassword)
except:
logging.warning("Failed to connect to db and get handle.", exc_info=True)
# The collections provided and create them and their indexes
for coll in p.collections:
collHandle = buildCollection(dbh, p, coll['collection'])
indexes = buildIndexes(p, coll, collHandle)
mdb.close(c, dbh)
def main(configFile=None):
''' Builds the collections and indexes needed. '''
# Get the config information into a single object
p = getConfigParameters(configFile)
try:
c, dbh = mdb.getHandle(host=p.dbHost, port=p.dbPort, db=p.db, user=p.dbUser, password=p.dbPassword)
except:
logging.warning("Failed to connect to db and get handle.", exc_info=True)
# The collections provided and create them and their indexes
for coll in p.collections:
print "Building Collections and indexes: %s" %coll
collHandle = buildCollection(dbh, p, coll['collection'])
indexes = buildIndexes(p, coll, collHandle)
mdb.close(c, dbh)
def testGetAllCountForOneCellLookback(self):
''' Gets a count for a single cell'''
tweetTime = datetime.datetime(2011,1,2,12,5,15)
oldTweetTime = tweetTime - datetime.timedelta(seconds=15*60)
baselineTime = datetime.datetime(2011,1,2,12,0,0)
# Get a db handle
c, dbh = mdb.getHandle()
dbh = mdb.setupCollections(dbh, dropCollections=True) # Set up collections
# Build a keyword
kword = kw(keyword='keyword1', timeStamp=tweetTime, lat=34.4, lon=45.5,
text='this text contained the hashtag #keyword1',
tweetID=346664, userID=4444, source='twitter')
# New timeseries object
ts = timeSeries()
ts.importData(kword)
success = ts.insertBlankDoc()
# Last 2 documents
lookback = 24
mgrs = '38SND4595706622'
qKeyword = 'keyword1'
res = bl.getResultsPerCell(dbh,
collection='timeseries',
mgrs=mgrs,
keyword=qKeyword,
inDate=baselineTime,
lookback=lookback)
print res
results = []
for doc in res:
print doc
results.append(doc)
self.assertEqual(len(results), 1)
# Close the connection
mdb.close(c, dbh)
def InsertBlankDoc(self):
''' Checks the successful inserting of a mongo document '''
# Get connection to mongo
c, dbh = mdb.getHandle()
dbh = mdb.setupCollections(dbh, dropCollections=True) # Set up collections
# New timeseries object with data
ts = timeSeries()
ts.importData(self.kw, blockPrecision=1)
# Build and insert a new mongo formatted document
success = ts.insertBlankDoc()
self.assertEquals(success, 1)
# Clean up and drop it
#dbh.timeseries.remove()
# Close the connection
mdb.close(c, dbh)
def getEvents(p):
''' Returns all currently active events in mongo '''
# The mongo bits
c, dbh = mdb.getHandle(host=p.dbHost,
port=p.dbPort,
db=p.db,
user=p.dbUser,
password=p.dbPassword)
evCollHandle = dbh[p.eventsCollection]
try:
docs = evCollHandle.find(
fields=['objectId', 'subType', 'start', 'loc', 'radius'])
docsOut = [d for d in docs]
except:
print "No documents matched your query. Object ID: %s." % objectId
docsOut = []
mdb.close(c, dbh)
# Additional fields that might be useful
for doc in docsOut:
# Get rid of the mongo ID
_id = doc.pop('_id')
if doc.has_key('loc'):
# calculate the radius in metres
latScale, lonScale = radialToLinearUnits(float(doc['loc'][1]))
scale = (latScale + lonScale) / 2.0
doc['radius_m'] = int(doc['radius'] * scale)
# Calculate the top left, bottom right
s = doc['loc'][1] - doc['radius']
w = doc['loc'][0] - doc['radius']
n = doc['loc'][1] + doc['radius']
e = doc['loc'][0] + doc['radius']
doc['bbox'] = [[w, s], [e, n]]
return docsOut
def main(p):
# The mongo bits
try:
c, dbh = mdb.getHandle(host=p.dbHost, port=p.dbPort, db=p.db, user=p.dbUser, password=p.dbPassword)
evCollHandle = dbh[p.eventsCollection]
except:
logging.critical('Failed to connect and authenticate', exc_info=True)
sys.exit()
# Get the current tags
tags = cf.getCurrentTags(evCollHandle)
# Get the current bounding boxes
queryBBoxes = cf.getQueryBBox(evCollHandle)
x = 1
while x == 1:
# Here's the redis queue for managing the tweets as they come in
try:
q = RedisQueue(p.redisName, host=p.redisHost, password=p.redisPassword, port=p.redisPort, db=0)
except:
logging.error('Failed to connect to REDIS db.', exc_info=True)
sys.exit()
# This call is blocking, so expect it to hang on this point
tweetStr = q.get()
tweet = json.loads(tweetStr)
# Work out which object/event this tweet is associated with
if tags:
tweetTags = cf.whichTags(tags, tweet)
for tweetTag in tweetTags:
success = dispatchTweet(p, tweet, tweetTag)
logging.debug("Tag-based message dispatched: %s" %(success))
if queryBBoxes:
tweetGeos = cf.matchesCurrentGeos(queryBBoxes, tweet)
for tweetGeo in tweetGeos:
success = dispatchTweet(p, tweet, tweetGeo)
logging.debug("Geo-based message dispatched: %s" %(success))
def main(cleanup, ageOff, protectedSubs=None):
''' Coordinates which element to cleanup - subscriptions including remote delete of subs from instagram
or event data - getting rid of the documents that contain the media and metadata'''
# If there is a command to remove or keep protected subs, use it
if protectedSubs:
protectedSubs = bool(protectedSubs)
# Get the config information
os.chdir('/home/dotcloud/code/')
cwd = os.getcwd()
cfgs = os.path.join(cwd, 'config/crowded.cfg')
p = getConfigParameters(cfgs)
# The mongo bits
c, dbh = mdb.getHandle(host=p.dbHost,
port=p.dbPort,
db=p.db,
user=p.dbUser,
password=p.dbPassword)
# Whether to cleanup the subscriptions and subscription collection
if cleanup == 'subs':
subsCollHandle = dbh[p.subsCollection]
res = ageOffSubscriptions(p,
subsCollHandle,
ageOff=ageOff,
protectedSubs=protectedSubs)
print datetime.datetime.utcnow(), res
# Or the events metadata collection
elif cleanup == 'events':
evCollHandle = dbh[p.eventsCollection]
res = ageOffMetadata(evCollHandle,
ageOff=ageOff,
protectMedia=protectedSubs)
print datetime.datetime.utcnow(), res
else:
print 'Provide either subs or events as the first argument depending on what you want to clean up.'
def main():
''' Builds the collections and indexes needed for the bam mongo work.
# See also /src/tests/testMdb for full tests of the base functions. '''
path = "/Users/brantinghamr/Documents/Code/eclipseWorkspace/bam/config"
#path = 'home/dotcloud/code/config/'
file = "mongoSetup.cfg"
params = getConfig(path,file)
# Get a db handle
if params.verbose==True:
print "Get Mongo Handle."
c, dbh = mdb.getHandle(host=params.host, port=params.port, db=params.db)
# Set up collections
if params.verbose==True:
print "Setup the mongo collections."
mdb.setupCollections(c, dbh, params.db, params.collections, params.dropDb)
# Get the collection handles
timeSeriesHandle = dbh[params.timeseries]
baselineHandle = dbh[params.baseline]
alertsHandle = dbh[params.alerts]
mappingHandle = dbh[params.mapping]
# Set up the indexes on the collections
if params.verbose==True:
print "Setup the mongo indexes."
setupTimeseriesIndexes(timeSeriesHandle, dropIndexes=params.dropIdx)
setupAlertsIndexes(alertsHandle, dropIndexes=params.dropIdx)
setupBaselineIndexes(baselineHandle, dropIndexes=params.dropIdx)
# Close the connection
if params.verbose==True:
print "Closing the connection."
mdb.close(c, dbh)
def main():
# Should really move these to being
parser = OptionParser()
parser.add_option("-H", "--host", dest="host")
parser.add_option("-p", "--port", dest="port")
parser.add_option("-d", "--db", dest="db")
parser.add_option("-m", "--mgrs", dest="mgrs")
parser.add_option("-M", "--mgrsprecision", dest="mgrsPrecision")
parser.add_option("-t", "--timestamp", dest="timeStamp")
parser.add_option("-k", "--keyword", dest="keyword")
parser.add_option("-u", "--baselineUnit", dest="baselineUnit")
parser.add_option("-v", "--baselineValue", dest="baselineValue")
(options, args) = parser.parse_args()
# Format the option inputs = these really should be arguments
port = int(options.port)
timeStamp = datetime.datetime.strptime(options.timeStamp, "%Y-%m-%dT%H:%M:%S")
mgrsPrecision = int(options.mgrsPrecision)
baselinePrecision = [options.baselineUnit, int(options.baselineValue)]
c, dbh = mdb.getHandle(host=options.host, port=port, db=options.db)
# Build the baseline objects as we go so that they can be updated at the end of the period.
base = baseline(options.mgrs, mgrsPrecision, options.keyword, timeStamp, c=c, dbh=dbh, baselinePrecision=baselinePrecision)
# Does the baseline document need updating?
if base.needUpdate == True:
# This method takes care of update and insert
base.processBaseline(tsd.buildBlankData())
try:
mdb.close(c, dbh)
except:
pass
def testGetCurrentTags(self):
import mdb
cwd = os.getcwd()
parent = os.path.dirname(cwd)
cfgs = os.path.join(parent, 'config/twitterCrowded.cfg')
p = getConfigParameters(cfgs)
# The mongo bits
try:
c, dbh = mdb.getHandle(host=p.dbHost, port=p.dbPort, db=p.db, user=p.dbUser, password=p.dbPassword)
evCollHandle = dbh[p.eventsCollection]
except:
print "Failed to connect to mongo."
sys.exit(1)
res = cf.getCurrentTags(evCollHandle, 'shitbrick')
self.assertEquals(res, ['hellworld','fuckhole', 'shitbrick'])
# Quick test chucked in
results = cf.getQueryBBox(evCollHandle)
print results
def testGetAllCountForOneCell(self):
''' Gets a count for a single cell'''
c, dbh = mdb.getHandle()
dbh = mdb.setupCollections(dbh, dropCollections=True) # Set up collections
tweetTime = datetime.datetime(2011,1,2,12,5,15)
oldTweetTime = tweetTime - datetime.timedelta(seconds=11*60)
# Build a keyword to represent the basekine
kword = kw(keyword='keyword1', timeStamp=oldTweetTime, lat=34.4, lon=45.5,
text='this text contained the hashtag #keyword1',
tweetID=346664, userID=4444, source='twitter')
# New timeseries object
ts = timeSeries()
ts.importData(kword)
success = ts.insertBlankDoc()
# Build a keyword
kword = kw(keyword='keyword1', timeStamp=tweetTime, lat=34.4, lon=45.5,
text='this text contained the hashtag #keyword1',
tweetID=346664, userID=4444, source='twitter')
# New timeseries object
ts = timeSeries()
ts.importData(kword)
success = ts.insertBlankDoc()
# ALL DOCUMENTS
mgrs = '38SND4595706622'
keyword = 'keyword1'
# This indate represents when the baseline was run (12:10) minus the interest period (10 minutes)
inDate = datetime.datetime(2011,1,2,12,0,0)
results = bl.getResultsPerCell(dbh, collection='timeseries', mgrs=mgrs, keyword=keyword, inDate=inDate)
self.assertEqual(len(results), 1)
def testBuildFullArray(self):
'''Build a full array from a cursor result'''
# Get a db handle
c, dbh = mdb.getHandle()
dbh = mdb.setupCollections(dbh, dropCollections=True) # Set up collections
# Build a keyword
kword = kw(keyword='keyword1', timeStamp=datetime.datetime(2011,1,2,12,1,1), lat=34.4, lon=45.5,
text='this text contained the hashtag #keyword1', tweetID=346664, userID=4444, source='twitter')
# New timeseries object
ts = timeSeries()
ts.importData(kword)
success = ts.insertBlankDoc()
# Insert the doc now that its been modified
kword.timeStamp = datetime.datetime(2011,1,1,12,1,1)
ts = timeSeries()
ts.importData(kword)
success = ts.insertBlankDoc()
# Last 1 weeks worth of documents
resultSet = bl.getResultsPerCell(dbh, '38SND4595706622', 'keyword1', datetime.datetime(2011,1,2), 168)
# Inputs
inDate = datetime.datetime(2011, 1, 2, 0, 0)
period = datetime.timedelta(days=7)
flat = None
dates, data = bl.buildFullArray(resultSet, inDate, period, flat)
self.assertEquals(len(dates), 8)
self.assertEquals(len(data), 8)
# Close the connection
mdb.close(c, dbh)
def getMediaByObjectId(p, objectId):
''' Gets a mongo doc back based on the object ID. Called by the display page. '''
# The mongo bits
c, dbh = mdb.getHandle(host=p.dbHost,
port=p.dbPort,
db=p.db,
user=p.dbUser,
password=p.dbPassword)
evCollHandle = dbh[p.eventsCollection]
# The query into mongo that should only return 1 doc
query = {'objectId': objectId}
doc = evCollHandle.find(query)
try:
doc = [d for d in doc][0]
except:
print "No document matched your query. Object ID: %s." % objectId
doc = None
mdb.close(c, dbh)
return doc
def getCamsByGeo(p, lat, lon, radius, postcode=None):
'''Get the cameras that fall within radius of lat/lon or postcode'''
# The mongo bits
c, dbh = mdb.getHandle(host=p.dbHost, port=p.dbPort, db=p.db, user=p.dbUser, password=p.dbPassword)
camsCollHandle = dbh[p.camsCollection]
# Convert the incoming metres radius to degrees
latRad, lonRad = radialToLinearUnits(lat)
scale = (latRad+lonRad)/2.0
radius = float(radius)/scale
# Query mongo
query = SON({'$near':[float(lon), float(lat)]})
query['$maxDistance'] = radius
res = camsCollHandle.find({'loc' : query})
# Get results
if res:
results = [r for r in res]
if len(results) == 0:
results = None
return results
# - If so, break out the admin functions.
# - Look into using twisted as the framework or web server so that it is FAST to receive the POSTs
# from external sources
# Extract the instagram bits from this code.
#///////////////////////////////////////////////////////////////////////////////////////////////
os.chdir('/home/dotcloud/current/')
cwd = os.getcwd()
cfgs = os.path.join(cwd, 'config/crowded.cfg')
p = getConfigParameters(cfgs)
# The mongo bits
c, dbh = mdb.getHandle(host=p.dbHost,
port=p.dbPort,
db=p.db,
user=p.dbUser,
password=p.dbPassword)
evCollHandle = dbh[p.eventsCollection]
logFile = os.path.join(p.errorPath, p.errorFile)
logging.basicConfig(filename=logFile,
format='%(levelname)s:: \t%(asctime)s %(message)s',
level='DEBUG')
#------------------------------------------------------------------------------------------------
def on_error(errFile='errors.txt', message=None):
''' Handles an error message '''
port = 27017
db = 'bam'
collection = 'timeseries'
lookback = datetime.timedelta(days=5)
queryEnd = datetime.datetime(2011,05,04)
queryStart = queryEnd - lookback
mgrs = None
mgrsPrecision = None
blankDay = buildBlankData()
#========================
print queryStart, queryEnd
# Get a mongo db handle
c, dbh = mdb.getHandle(host=host, port=port, db=db)
# Get a collection handle
collHandle = dbh[collection]
# Query based on a keyword only
keyword = 'sick'
query = {'keyword':keyword,
'start':{'$gte' : queryStart},
'start':{'$lte' : queryEnd}}
if mgrs:
query['mgrs'] = mgrs
if mgrsPrecision:
query['mgrsPrecision'] = mgrsPrecision
def main(configFile=None):
''' Coordinates the management functions
Command line called, typically from a CRON.'''
# Get the config file
p = getConfigParameters(configFile)
# Logging config
logFile = os.path.join(p.errorPath, p.errorFile)
logging.basicConfig(filename=logFile,
format='%(levelname)s:: \t%(asctime)s %(message)s',
level=p.logLevel)
# Streaming client
connClientPath = os.path.dirname(p.errorPath)
p.streamClient = os.path.join(connClientPath, 'src/connectionClient.py')
# The mongo bits
try:
c, dbh = mdb.getHandle(host=p.dbHost,
port=p.dbPort,
db=p.db,
user=p.dbUser,
password=p.dbPassword)
evCollHandle = dbh[p.eventsCollection]
mgmtCollHandle = dbh[p.mgmtCollection]
logging.debug("Connected and authenticated on the db.")
except:
logging.critical('Failed to connect to db and authenticate.',
exc_info=True)
sys.exit()
# Create a new management document if needed
initialOID = setInitialPid(mgmtCollHandle)
# Get the current events from crowded
crowdedEvents = getCrowdedEvents(p)
# Get the events currently stored by this app
myEvents = getLocalEvents(p, evCollHandle)
# Compare the 2 sets of events: what's old and new?
oldEvents, newEvents = checkEvents(crowdedEvents, myEvents)
# Expire old events from db, so that the new stream reflects the correct interest
for oldEvent in oldEvents:
print oldEvent
logging.debug('Expiring Old Event in DB: %s' % (oldEvent))
res = expireOldEvent(evCollHandle, oldEvent)
# Create new item in the db
for newEvent in newEvents:
logging.debug('Creating New Event in DB: %s' % (newEvent))
res = createLocalEvent(evCollHandle, newEvent)
# Get the old process ID and kill it off
pid = getPid(mgmtCollHandle)
logging.debug('Current PID: %s' % (pid))
# Only continue if there is a change in the events
if len(oldEvents) > 0 or len(newEvents) > 0:
if pid:
logging.debug('Killing old process with ID: %s' % (pid))
res = killOldProcess(pid)
# Now create the new one
newPid = processNewEvent(p)
logging.debug('Creating a new process with PID: %s' % (newPid))
# Update the current process id in mongo
res = storePid(mgmtCollHandle, newPid)
logging.debug('Stored the new PID: %s' % (res))
mdb.close(c, dbh)
logging.shutdown()
def main(p, response):
'''Handles the subscription updates, including making the call to the endpoint and dumping to jms/text.'''
# The mongo bits
c, dbh = mdb.getHandle(host=p.dbHost,
port=p.dbPort,
db=p.db,
user=p.dbUser,
password=p.dbPassword)
evCollHandle = dbh[p.eventsCollection]
# Accepts a list of dictionaries - the update message
updates = json.loads(response)
# Format the url and get the media metadata
for upd in updates:
objectId = upd['object_id']
objectType = upd['object']
# Does the next URL already exist for this object?
#url = getNextUrl(p, objectId)
# If the next (ie this) url hasn't been written to a file, build it from the config file
#if url == None or len(url) < 1:
url = buildUrl(p, objectType, objectId)
# Get the media that has changed since the last time
mediaMeta = getMediaUpdates(url)
# Find the pagination info and save out info that concerning next url for this subscription
#handleMediaPagination(p, url, objectId, mediaMeta)
# Get the last insert time
lastUpdated = retrieveLatestImage(evCollHandle, objectId)
latest = time.mktime(lastUpdated.timetuple())
newLatest = time.mktime(lastUpdated.timetuple())
# Update the tags and urls arrays
if mediaMeta and mediaMeta.has_key('data'):
#print "Number of Images:", len(mediaMeta['data'])
for photo in mediaMeta['data']:
# Append the datetime information
try:
epochTime = float(photo['created_time'])
dt = datetime.datetime.fromtimestamp(epochTime)
except Exception, e:
print e
# For recent images
if epochTime > latest:
# Update the list of images stored
res = updateImageUrls(evCollHandle, objectId, photo, dt)
# Update the tag information
res = updateTags(evCollHandle, objectId, photo)
# Get the latest image datetime
if epochTime > newLatest:
#print "improving newLatest", epochTime, newLatest
newLatest = epochTime
# Update the latest datetime on record
updateTimeStamp = datetime.datetime.fromtimestamp(newLatest)
updateLatestInfo(evCollHandle, objectId, updateTimeStamp)
def main():
'''
Script to build tweet objects from the VAST dataset and place them on a Queue and/or JMS
for testing purposes.
LIKELY SPEED IMPROVEMENTS:
- BUILDING BLANK ARRAYS IN THE TIME SERIES TAKES A WHILE
- PUTTING THE KEYWORDS IN A QUEUE, HAVING SET UP THE THREADS TO PROCESS EACH ONE.
- ANY DUPLICATION CHECKS?
'''
start = datetime.datetime.utcnow()
tweetProcessTimes = datetime.timedelta(seconds=0)
#dripRate = 1.5
# JMS destination
destination = '/topic/test.vasttweets'
hostIn = 'localhost'
portIn = 61613
# Reset the collections
c, dbh = mdb.getHandle()
dbh = mdb.setupCollections(dbh, dropCollections=True) # Set up collections
#jms = jmsCode.jmsHandler(hostIn, portIn, verbose=True)
# Make the JMS connection via STOMP and the jmsCode class
#jms.connect()
path = "/Users/brantinghamr/Documents/Code/eclipseWorkspace/bam/data/"
#fName= "MicroblogsSample.csv"
fName= "Microblogs.csv"
outFName = "MicroblogsOrdered.csv"
f = retrieveFile(path, fName)
fo = open(os.path.join(path, outFName), 'w')
x = 0
# Start time
earliestTweet = datetime.datetime(2011, 5, 18, 13, 25)
earliestTweet = time.mktime(time.struct_time(earliestTweet.timetuple()))
lastTweetTime = earliestTweet
print "First Tweet Time: ", lastTweetTime
# This speeds things up from seconds to minutes
speedUpRate = 60.0
records = []
# Loop the lines build tweet objects
for line in f.readlines():
#print line
# Extract content from each line
line = line.rstrip('\r').rstrip('\n').rstrip('\r')
if x == 0:
x+=1
continue
if x % 1000 == 0:
print "processed: ", x
#if x > 1000:
# break
# sys.exit(0)
line = line.split(',')
tweetId, dt, latLon, text = line
# Get the datetime group into seconds since UNIX time
dtg = getTime(tweetId, dt)
if not dtg:
continue
record = [tweetId, dtg, latLon, text]
records.append(record)
x += 1
f.close()
sortedTable = sortTable(records, col=1)
# Now loop the sorted list and write out to a new file
for record in sortedTable:
lineOut = "%s,%s,%s,%s\n" %(record[0], record[1], record[2], record[3])
fo.write(lineOut)
f.close()
def main(p, mediaOnly=None):
''' Coordinates a new twitter stream connection'''
# Logging config
logFile = os.path.join(p.errorPath, p.connErrorFile)
logging.basicConfig(filename=logFile,
format='%(levelname)s:: %(asctime)s %(message)s',
level=p.logLevel)
# The mongo bits
try:
c, dbh = mdb.getHandle(host=p.dbHost,
port=p.dbPort,
db=p.db,
user=p.dbUser,
password=p.dbPassword)
evCollHandle = dbh[p.eventsCollection]
except:
logging.critical('Failed to connect to db and authenticate.',
exc_info=True)
sys.exit()
# Here's the redis queue for managing the tweets as they come in
try:
q = RedisQueue(p.redisName,
host=p.redisHost,
password=p.redisPassword,
port=p.redisPort,
db=0)
except:
logging.critical("REDIS: Failed to connect in connectionClient.py. ",
exc_info=True)
sys.exit()
# Connection placeholder in case the exception catches the drop out
connection = True
while connection == True:
# Get the existing tags and add the current
try:
tags = cf.getCurrentTags(evCollHandle)
except:
tags = None
logging.error('Failed to get current tags from db.', exc_info=True)
# Build the building boxes
try:
bboxes = cf.getCurrentBBoxes(evCollHandle)
except:
bboxes = None
logging.error('Failed to get current BBOXes from db.',
exc_info=True)
if not tags and not bboxes:
logging.warning('Currently no tags or bboxes in the db.')
sys.exit()
try:
print tags, bboxes
with tweetstream.FilterStream(p.sourceUser,
p.sourcePassword,
track=tags,
locations=bboxes) as stream:
for tweet in stream:
if mediaOnly:
try:
q.put(json.dumps(tweet))
except:
logging.critical(
"Failed to put tweet on redis. This tweet: \n%s"
% (tweet),
exc_info=True)
except tweetstream.ConnectionError:
logging.critical("Disconnected from twitter", exc_info=True)
