#!/usr/bin/python
import hotshot, hotshot.stats
import couchdb
import simplejson as json
import urllib

def profileit(printlines=20):
    def _my(func):
        def _func(*args, **kargs):
            prof = hotshot.Profile("profiling.data")
            res = prof.runcall(func, *args, **kargs)
            prof.close()
            stats = hotshot.stats.load("profiling.data")
            stats.strip_dirs()
            stats.sort_stats('time', 'calls')
            print ">>>---- Begin profiling print"
            stats.print_stats(printlines)
            print ">>>---- End profiling print"
            return res
        return _func
    return _my

db_name = "kw2"
db_name = "keywords"
view_url = "http://localhost:5984/%s/_design/finding/_view/word_count" % (db_name)
try:
    server = couchdb.Server('http://127.0.0.1:5984')
    db = server[db_name]
    len(db)
except couchdb.client.ResourceNotFound:
    server.create(db_name)
    db = server[db_name]
    len(db)

def load_db():
    key_file = open('keywords2.txt')
    data = key_file.read()
    words = data.split()
    for word in words:
        node = db.create( { "word": word } )    

def all_word_count():
    try:
#       u = "http://localhost:5984/%s/_view/finding/word_count?group=true" % (db_name)
        u = "%s?group=true" % (view_url)
        ### Example Output: {"rows":[{"key":"be","value":1},{"key":"do","value":4},{"key":"to","value":1},{"key":"we","value":2}]}
        j = json.loads(urllib.urlopen(u).read())
        return j['rows']
    except:
        return [{}]

def total_word_count():
    try:
#       u = "http://localhost:5984/%s/_view/finding/word_count" % (db_name)
        u = view_url
        ### output {"rows":[{"key":null,"value":124580}]}
        j = json.loads(urllib.urlopen(u).read())
        return j['rows'][0]['value']
    except:
        return 0

def build_prob_dict(word_list, total_words):
    num = float(total_words)
    try:
        return dict([ (r['key'], r['value'] / num ) for r in word_list])
    except:
        return {}

#@profileit(20)
def find_keyword(test_string = None):
    if not test_string:
        test_string = 'Hacker news is a good site while Techcrunch not so much'
    word_prob_dict = build_prob_dict(all_word_count(), total_word_count())
    non_exist_prob = min(word_prob_dict.values()) / 2.0
    
    #Build a word count from the input text
    words = test_string.split()
    test_word_freq = {}
    for word in words:
        if word in test_word_freq:
            test_word_freq[word]+=1
        else:
            test_word_freq[word] = 1

    #Build a freq count of the input words
    test_words_ba = {}
    for word, freq in test_word_freq.items():
        if word in word_prob_dict:
            test_words_ba[word] = freq/word_prob_dict[word]
        else:
            test_words_ba[word] = freq/non_exist_prob

    test_word_ba_list = []
    for word, ba in test_words_ba.items():
         test_word_ba_list.append((word, ba))

    def sort_func(a, b):
        if a[1] > b[1]:
           return -1
        elif a[1] < b[1]:
            return 1
        return 0

    test_word_ba_list.sort(sort_func)
    print test_word_ba_list[:2]
    return test_word_ba_list[:2]

if __name__ == "__main__":
#   load_db()
    find_keyword()