#!/usr/bin/env python
# coding: utf8
# -*- coding: utf-8 -*-
# Quelle: http://rdrpostagger.sourceforge.net/
# python -m nltk.downloader all
# pip install -U nltk
# apt-get install python-numpy python-scipy python-matplotlib ipython ipython-notebook python-pandas python-sympy python-nose
# pip install -U numpy

import datetime
import pymongo
import polyglot
from polyglot.text import Text, Word
import fileinput
from textblob_de import TextBlobDE as TextBlob
from textblob_de import PatternParser
from textblob import Blobber
from textblob.taggers import NLTKTagger
from textblob.tokenizers import SentenceTokenizer
from textblob_de import BlobberDE
from textblob_de.taggers import PatternTagger
from textblob_de.tokenizers import PatternTokenizer
from textblob_de import PatternParser
# http://textblob-de.readthedocs.org/en/latest/
# python -m pip install pymongo
import sys
import pprint
import codecs
from pymongo import MongoClient
from pygermanet import load_germanet

gn = load_germanet()
client = MongoClient('mongodb://localhost:27017/')
db = client['DumpB2C']
#collection = db['B2Cv2']
collection = db['ParsedTemp']

# https://pypi.python.org/pypi/pygermanet
# https://github.com/wroberts/pygermanet
# funktionieren = gn.synset(u'funktionieren.v.2')
# print(funktionieren)
# sys.exit(1)
# http://api.mongodb.org/python/current/tutorial.html

content = ""
for line in fileinput.input():
    content +=line

#content = u"ich gehe im Wald spazieren und esse ein Eis. Meine Frau schiebt den Kinderwagen und erzählt mir von
    # Ihrem " \
#          "Tag. Angela Merkel war leider nicht dabei."

blob = TextBlob(content)
text = Text(content)

pp = pprint.PrettyPrinter(depth=6)
#pp.pprint(s)

# 1. Sätze bilden
sent = content
'''
sent = ""
print("Sätze ausgeben:")
for s in blob.sentences:
    #u = s.encode(encoding='UTF-8', errors='strict')
    print(u"s")
    #sent += str(u) + "#;#\n"
print("\n")
'''

'''
for s in blob.tokens:
    print(s)

for s in blob.tags:
    print(s)
'''

# 2. Pos Tagger
#print("POS ausgeben:")
#print(blob.parse())
#print("\n")

# 3. NER Tagger
nner = ""
#print("NER ausgeben:")
#print(text.entities)
for s in text.entities:
#    print(u"s")
    nner += s + "#;#\n"
#print("\n")

# 4. Nomensätze
with codecs.open("nomenphrasen.txt", "w", "utf-8-sig") as ntemp:
    ntemp.write(blob.noun_phrases)
ntemp.close()

'''
nphrase = ""
#print("Nomenphrasen ausgeben:")
for s in blob.noun_phrases:
    #print(u's')
    nphrase += s + "#;#\n"
    with codecs.open("nomenphrasen.txt", "w", "utf-8-sig") as ntemp:
        ntemp.write(s+"\n")
    ntemp.close()
#print("\n")
'''
'''
#5. Worter zählen
print("Wörter zählen:")
words = 0
print("\n")
for s in blob.tokens:
    words = words + 1
    print(u"s")
    #words += u"s" + "#;#\n"
    with codecs.open("allewoerter.txt", "w", "utf-8-sig") as wtemp:
        wtemp.write(u"s"+"\n")
    wtemp.close()
print("\n")
'''

post = {"sentences": sent,
"pos_tags": blob.parse(),
"ner_tags": nner,
"noun_phrases": nphrase,
#"word_count": words,
#"word_content": words,
"date": datetime.datetime.utcnow()}

posts = db.posts
####posts.insert_one(post)

# co-coocurrence https://github.com/maciejkula/glove-python
sys.exit()