def _getMostRecentPages(self, session):
es_info = self.esInfo(session['domainId'])
hits = []
if session['fromDate'] is None:
hits = get_most_recent_documents(session['pagesCap'], es_info['mapping'], ["url", "x", "y", es_info['mapping']["tag"], es_info['mapping']["timestamp"], es_info['mapping']["text"]],
session['filter'],
es_info['activeCrawlerIndex'],
es_info['docType'],
self._es)
else:
if(session['filter'] is None):
hits = range(es_info['mapping']["timestamp"], session['fromDate'], session['toDate'], ['url',"x", "y", es_info['mapping']['tag'], es_info['mapping']["timestamp"], es_info['mapping']["text"]], True, session['pagesCap'],
es_info['activeCrawlerIndex'],
es_info['docType'],
self._es)
else:
s_fields = {
es_info['mapping']["text"]: "(" + session['filter'].replace('"','\"') + ")",
es_info['mapping']["timestamp"]: "[" + str(session['fromDate']) + " TO " + str(session['toDate']) + "]"
}
hits = multifield_query_search(s_fields, session['pagesCap'], ["url", "x", "y", es_info['mapping']["tag"], es_info['mapping']["timestamp"], es_info['mapping']["text"]],
es_info['activeCrawlerIndex'],
es_info['docType'],
self._es)
return hits
def getPagesSummarySeedCrawler(self, opt_ts1 = None, opt_ts2 = None, opt_applyFilter = False, session = None):
es_info = self.esInfo(session['domainId'])
# If ts1 not specified, sets it to -Infinity.
if opt_ts1 is None:
now = time.localtime(0)
opt_ts1 = float(time.mktime(now)) * 1000
else:
opt_ts1 = float(opt_ts1)
# If ts2 not specified, sets it to now.
if opt_ts2 is None:
now = time.localtime()
opt_ts2 = float(time.mktime(now)) * 1000
else:
opt_ts2 = float(opt_ts2)
if opt_applyFilter:
# TODO(Yamuna): apply filter if it is None. Otherwise, match_all.
results = get_most_recent_documents(session['pagesCap'], es_info['mapping'], ["url", es_info['mapping']["tag"]],
session['filter'], es_info['activeCrawlerIndex'], es_info['docType'], \
self._es)
else:
results = \
range(es_info['mapping']["timestamp"], opt_ts1, opt_ts2, ['url',es_info['mapping']['tag']], True, session['pagesCap'], es_index=es_info['activeCrawlerIndex'], es_doc_type=es_info['docType'], es=self._es)
relevant = 0
irrelevant = 0
neutral = 0
# TODO(Yamuna): Double check the return values for crawler
for res in results:
try:
tags = res[es_info['mapping']['tag']]
if 'Relevant' in res[es_info['mapping']['tag']]:
relevant = relevant + 1
elif 'Irrelevant' in res[es_info['mapping']['tag']]:
irrelevant = irrelevant + 1
else:
# Page has tags, but not Relevant or Irrelevant.
neutral = neutral + 1
except KeyError:
# Page does not have tags.
neutral = neutral + 1
return { \
'Relevant': relevant,
'Irrelevant': irrelevant,
'Neutral': neutral
}
def getPagesSummarySeedCrawler(self, opt_ts1 = None, opt_ts2 = None, opt_applyFilter = False, session = None):
es_info = self.esInfo(session['domainId'])
# If ts1 not specified, sets it to -Infinity.
if opt_ts1 is None:
now = time.gmtime(0)
opt_ts1 = float(calendar.timegm(now))
else:
opt_ts1 = float(opt_ts1)
# If ts2 not specified, sets it to now.
if opt_ts2 is None:
now = time.gmtime()
opt_ts2 = float(calendar.timegm(now))
else:
opt_ts2 = float(opt_ts2)
if opt_applyFilter and session['filter'] != "":
results = get_most_recent_documents(session['pagesCap'], es_info['mapping'], ["url", es_info['mapping']["tag"]],
session['filter'], es_info['activeCrawlerIndex'], es_info['docType'], \
self._es)
else:
results = \
range(es_info['mapping']["timestamp"], opt_ts1, opt_ts2, ['url',es_info['mapping']['tag']], True, session['pagesCap'], es_index=es_info['activeCrawlerIndex'], es_doc_type=es_info['docType'], es=self._es)
relevant = 0
irrelevant = 0
neutral = 0
for res in results:
try:
tags = res[es_info['mapping']['tag']]
if 'Irrelevant' in res[es_info['mapping']['tag']]:
irrelevant = irrelevant + 1
else:
# Page has tags Relevant or custom.
if "" not in tags:
relevant = relevant + 1
else:
neutral = neutral + 1
except KeyError:
# Page does not have tags.
neutral = neutral + 1
return { \
'Relevant': relevant,
'Irrelevant': irrelevant,
'Neutral': neutral
}
