onetipp - Recherche - 1. Version - SOURCE CODE

#!/usr/bin/python
# -*- coding: ISO-8859-1 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.1a  - 26-10-2015@23:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python: Main File
###########################

"""
Synonym bzw Wortersetzung parallelisieren fr schnellere Verarbeitung und Reaktionszeit des Tools

Antonym Datenbank Entwicklung mit Hilfe gecrawlter Websites

Aufbau einer Datenbank mit einfacher deutscher Sprache

Berechnung des lesbarkeitswerts eines eingabetextes - basierend auf einfachen Texten die "simple German " Datenbank fr Austausch nutzen, Wissenschaftliche Texte mit Leipzig und unserer lokalen Synonym Datenbank austauschen

"""


#https://docs.python.org/2/library/configparser.html
import os
import sys
reload(sys)
sys.path.append('/home/onetipp/python/modules')
os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'

import random
import codecs
import re
import mod

from textblob_de import TextBlobDE as TextBlob
from textblob_de import PatternTagger
from textblob_de import TextBlobDE

cursorMysql = mod.mysql.cursor()

noDoubleHash    = set()
re_match        = r"(\?|\.|\!)" # Match: ". WORT"

# lies die Ein und Ausgabedateien
inputfile   = sys.argv[1]

... [truncated, 99 more lines] ...

#!/usr/bin/python
# -*- coding: UTF-8 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.0b  - 29-10-2015@23:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python: Main File
###########################

"""
Synonym bzw Wortersetzung parallelisieren für schnellere Verarbeitung und Reaktionszeit des Tools

Antonym Datenbank Entwicklung mit Hilfe gecrawlter Websites

Aufbau einer Datenbank mit einfacher deutscher Sprache

Berechnung des lesbarkeitswerts eines eingabetextes - basierend auf einfachen Texten die "simple German " Datenbank für Austausch nutzen, Wissenschaftliche Texte mit Leipzig und unserer lokalen Synonym Datenbank austauschen

Tests am 29.10.2015:

https://github.com/rsennrich/parzu
https://github.com/rsennrich/clevertagger
http://kitt.ifi.uzh.ch/kitt/zmorge/
https://github.com/rsennrich/zmorge

"""


#https://docs.python.org/2/library/configparser.html
import os
import sys
reload(sys)
sys.path.append('/home/onetipp/python/modules')
os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'

import random
import codecs
import re
import mod
import pprint

from textblob_de import TextBlobDE as TextBlob
from textblob_de import PatternTagger
from textblob_de import TextBlobDE

... [truncated, 81 more lines] ...

#!/usr/bin/python
# -*- coding: UTF-8 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.0b  - 29-10-2015@23:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python: Main File
###########################

"""
Synonym bzw Wortersetzung parallelisieren für schnellere Verarbeitung und Reaktionszeit des Tools

Antonym Datenbank Entwicklung mit Hilfe gecrawlter Websites

Aufbau einer Datenbank mit einfacher deutscher Sprache

Berechnung des lesbarkeitswerts eines eingabetextes - basierend auf einfachen Texten die "simple German " Datenbank für Austausch nutzen, Wissenschaftliche Texte mit Leipzig und unserer lokalen Synonym Datenbank austauschen

Tests am 29.10.2015:
https://github.com/rsennrich/clevertagger

"""

#https://docs.python.org/2/library/configparser.html
import os
import sys
reload(sys)
sys.path.append('/home/onetipp/python/modules')
os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'

import random
import codecs
import re
import mod
import stopwords
import pprint

from textblob_de import TextBlobDE as TextBlob
from textblob_de import PatternTagger
from textblob_de import TextBlobDE
import treetaggerwrapper

cursorMysql = mod.mysql.cursor()


... [truncated, 73 more lines] ...

#!/usr/bin/python
# -*- coding: UTF-8 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.0c  - 2-11-2015@23:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python: Main File
###########################

"""
Synonym bzw Wortersetzung parallelisieren für schnellere Verarbeitung und Reaktionszeit des Tools

Antonym Datenbank Entwicklung mit Hilfe gecrawlter Websites

Aufbau einer Datenbank mit einfacher deutscher Sprache

Berechnung des lesbarkeitswerts eines eingabetextes - basierend auf einfachen Texten die "simple German " Datenbank für Austausch nutzen, Wissenschaftliche Texte mit Leipzig und unserer lokalen Synonym Datenbank austauschen

Tests am 29.10.2015:
https://github.com/rsennrich/clevertagger

"""

#https://docs.python.org/2/library/configparser.html
import os
import sys
reload(sys)
sys.setdefaultencoding("utf-8")
sys.path.append('/home/onetipp/python/modules')
os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'

import random
import codecs
import re
import mod
import stopwords
import pprint
import pattern.de
from pattern.de import conjugate
from pattern.de import INFINITIVE, PRESENT, PAST, SG, SUBJUNCTIVE

from textblob_de import TextBlobDE as TextBlob
from textblob_de import PatternTagger
from textblob_de import TextBlobDE

... [truncated, 129 more lines] ...

#!/usr/bin/python
# -*- coding: UTF-8 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.0c  - 2-11-2015@23:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python: Main File
###########################

"""
Synonym bzw Wortersetzung parallelisieren für schnellere Verarbeitung und Reaktionszeit des Tools

Antonym Datenbank Entwicklung mit Hilfe gecrawlter Websites

Aufbau einer Datenbank mit einfacher deutscher Sprache

Berechnung des lesbarkeitswerts eines eingabetextes - basierend auf einfachen Texten die "simple German " Datenbank für Austausch nutzen, Wissenschaftliche Texte mit Leipzig und unserer lokalen Synonym Datenbank austauschen

Tests am 29.10.2015:
https://github.com/rsennrich/clevertagger

"""

# https://docs.python.org/2/library/configparser.html
import os
import sys

reload(sys)
sys.setdefaultencoding("utf-8")
sys.path.append('/home/onetipp/python/modules')
os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'

import random
import codecs
import re
import mod
import stopwords
import pprint
import pattern.de
from pattern.de import conjugate
from pattern.de import INFINITIVE, PRESENT, PAST, SG, SUBJUNCTIVE
from textblob_de import TextBlobDE as TextBlob
from textblob_de import PatternTagger
from textblob_de import TextBlobDE

... [truncated, 205 more lines] ...

#!/usr/bin/python
# -*- coding: UTF-8 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.0c  - 4-11-2015@23:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python: Main File
###########################

"""
Synonym bzw Wortersetzung parallelisieren für schnellere Verarbeitung und Reaktionszeit des Tools

Antonym Datenbank Entwicklung mit Hilfe gecrawlter Websites

Aufbau einer Datenbank mit einfacher deutscher Sprache

Berechnung des lesbarkeitswerts eines eingabetextes - basierend auf einfachen Texten die "simple German " Datenbank für Austausch nutzen, Wissenschaftliche Texte mit Leipzig und unserer lokalen Synonym Datenbank austauschen

Tests am 29.10.2015:
https://github.com/rsennrich/clevertagger

"""

# https://docs.python.org/2/library/configparser.html
import os
import sys

reload(sys)
sys.setdefaultencoding("utf-8")
sys.path.append('/home/onetipp/python/modules')
os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'

import random
import codecs
import re
import mod
import stopwords
import pprint
import pattern.de
from pattern.de import conjugate
from pattern.de import INFINITIVE, PRESENT, PAST, SG, SUBJUNCTIVE
from textblob_de import TextBlobDE as TextBlob
from textblob_de import PatternTagger
from textblob_de import TextBlobDE

... [truncated, 299 more lines] ...

#!/usr/bin/python
# -*- coding: UTF-8 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.0c  - 4-11-2015@23:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python: Main File
###########################

"""
Synonym bzw Wortersetzung parallelisieren für schnellere Verarbeitung und Reaktionszeit des Tools

Antonym Datenbank Entwicklung mit Hilfe gecrawlter Websites

Aufbau einer Datenbank mit einfacher deutscher Sprache

Berechnung des lesbarkeitswerts eines eingabetextes - basierend auf einfachen Texten die "simple German " Datenbank für Austausch nutzen, Wissenschaftliche Texte mit Leipzig und unserer lokalen Synonym Datenbank austauschen

Tests am 29.10.2015:
https://github.com/rsennrich/clevertagger

"""

# https://docs.python.org/2/library/configparser.html
import os
import sys

reload(sys)
sys.setdefaultencoding("utf-8")
sys.path.append('/home/onetipp/python/modules')
os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'

import random
import codecs
import re
import mod
import stopwords
import pprint
import pattern.de
from pattern.de import conjugate
from pattern.de import INFINITIVE, PRESENT, PAST, SG, SUBJUNCTIVE
from textblob_de import TextBlobDE as TextBlob
from textblob_de import PatternTagger
from textblob_de import TextBlobDE

... [truncated, 300 more lines] ...

#!/usr/bin/python
# -*- coding: UTF-8 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.0c  - 4-11-2015@23:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python: Main File
###########################

"""
Synonym bzw Wortersetzung parallelisieren für schnellere Verarbeitung und Reaktionszeit des Tools

Antonym Datenbank Entwicklung mit Hilfe gecrawlter Websites

Aufbau einer Datenbank mit einfacher deutscher Sprache

Berechnung des lesbarkeitswerts eines eingabetextes - basierend auf einfachen Texten die "simple German " Datenbank für Austausch nutzen, Wissenschaftliche Texte mit Leipzig und unserer lokalen Synonym Datenbank austauschen

Tests am 29.10.2015:
https://github.com/rsennrich/clevertagger

"""

# https://docs.python.org/2/library/configparser.html
import os
import sys

reload(sys)
sys.setdefaultencoding("utf-8")
sys.path.append('/home/python/modules')
os.environ['PYTHON_EGG_CACHE'] = '/home/cache/'

import random
import codecs
import re
import mod
import stopwords
import pprint
import pattern.de
from pattern.de import conjugate
from pattern.de import INFINITIVE, PRESENT, PAST, SG, SUBJUNCTIVE
from textblob_de import TextBlobDE as TextBlob
from textblob_de import PatternTagger
from textblob_de import TextBlobDE

... [truncated, 302 more lines] ...

#!/usr/bin/python
# -*- coding: iso-8859-15 -*-

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.3  - 11-10-2015@21:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python
###########################

######## export PYTHON_EGG_CACHE=/tmp

import os
import pprint
import nltk
#import rocksdb                                         # shared library kann aktuell noch nicht gelesen werden
import MySQLdb                                          # apt-get install python-mysqldb
from sphinxit.core.processor import Search              # http://sphinxit.readthedocs.org/en/latest/
from sphinxit.core.helpers import BaseSearchConfig
import random
import codecs
import sys

os.environ['PYTHON_EGG_CACHE'] = '/tmp'


from nltk.tokenize import sent_tokenize
###python -m nltk.downloader -d /usr/share/nltk_data all
####python -m nltk.downloader all
###########nltk.download()

reload(sys)
sys.setdefaultencoding('latin-1')

class SphinxitConfig(BaseSearchConfig):
    DEBUG = True
    WITH_META = True
    WITH_STATUS = True
    POOL_SIZE = 5
   # SQL_ENGINE = 'oursql'
    SEARCHD_CONNECTION = {
        'host': '127.0.0.1',
        'port': 9977,
    }

pp = pprint.PrettyPrinter(indent=4)
#delimiters      = ['\n', ' ', ',', '.', '?', '!', ':', ';', '\s', '\t', '\r']
# http://pyrocksdb.readthedocs.org/en/v0.4/tutorial/index.html

... [truncated, 126 more lines] ...

__author__ = 'Sebastian Enger, M.Sc.'

import sys
import pprint
import nltk
from nltk.tokenize import sent_tokenize
#nltk.download()

reload(sys)
sys.setdefaultencoding('utf8')

pp = pprint.PrettyPrinter(indent=4)




#delimiters      = ['\n', ' ', ',', '.', '?', '!', ':', ';', '\s', '\t', '\r']

filename        = sys.argv[-1]

# read file into string
text            = open(filename, 'r').read()
#text.decode('utf-8')

sent_tokenize_list = sent_tokenize(text)

for ele in sent_tokenize_list:
    word_list = ele.split()

    for word in word_list:
        if word.istitle():
            print "Word: ",word, " -> gross geschrieben\n"
    #pp.pprint(word_list)

__author__ = 'Sebastian Enger, M.Sc.'

import sys
import pprint
import nltk
from nltk.tokenize import sent_tokenize
#nltk.download()

reload(sys)
sys.setdefaultencoding('utf8')

pp = pprint.PrettyPrinter(indent=4)




#delimiters      = ['\n', ' ', ',', '.', '?', '!', ':', ';', '\s', '\t', '\r']

filename        = sys.argv[-1]

# read file into string
text            = open(filename, 'r').read()
#text.decode('utf-8')

sent_tokenize_list = sent_tokenize(text)

for ele in sent_tokenize_list:
    word_list = ele.split()

    for word in word_list:
        if word.istitle():
            print "Word: ",word, " -> gross geschrieben\n"
    #pp.pprint(word_list)

#!/usr/bin/python
# -*- coding: iso-8859-15 -*-

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.3  - 11-10-2015@21:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python
###########################

######## export PYTHON_EGG_CACHE=/tmp

import os
import pprint
import nltk
#import rocksdb                                         # shared library kann aktuell noch nicht gelesen werden
import MySQLdb                                          # apt-get install python-mysqldb
from sphinxit.core.processor import Search              # http://sphinxit.readthedocs.org/en/latest/
from sphinxit.core.helpers import BaseSearchConfig
import random
import codecs
import sys

os.environ['PYTHON_EGG_CACHE'] = '/tmp'


from nltk.tokenize import sent_tokenize
###python -m nltk.downloader -d /usr/share/nltk_data all
####python -m nltk.downloader all
###########nltk.download()

reload(sys)
sys.setdefaultencoding('latin-1')

class SphinxitConfig(BaseSearchConfig):
    DEBUG = True
    WITH_META = True
    WITH_STATUS = True
    POOL_SIZE = 5
   # SQL_ENGINE = 'oursql'
    SEARCHD_CONNECTION = {
        'host': '127.0.0.1',
        'port': 9977,
    }

pp = pprint.PrettyPrinter(indent=4)
#delimiters      = ['\n', ' ', ',', '.', '?', '!', ':', ';', '\s', '\t', '\r']
# http://pyrocksdb.readthedocs.org/en/v0.4/tutorial/index.html

... [truncated, 126 more lines] ...

#!/usr/bin/python
# -*- coding: latin1 -*-

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.4  - 12-10-2015@22:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python
###########################

######## export PYTHON_EGG_CACHE=/tmp

import os
import pprint
import nltk
# import rocksdb                                         # shared library kann aktuell noch nicht gelesen werden
import MySQLdb  # apt-get install python-mysqldb
from sphinxit.core.processor import Search  # http://sphinxit.readthedocs.org/en/latest/
from sphinxit.core.helpers import BaseSearchConfig
import random
import codecs
import sys
import unicodedata

os.environ['PYTHON_EGG_CACHE'] = '/tmp'

from nltk.tokenize import sent_tokenize
###python -m nltk.downloader -d /usr/share/nltk_data all
####python -m nltk.downloader all
###########nltk.download()

reload(sys)
sys.setdefaultencoding('latin-1')


class SphinxitConfig(BaseSearchConfig):
    DEBUG = False
    WITH_META = False
    WITH_STATUS = False
    POOL_SIZE = 5
    # SQL_ENGINE = 'oursql'
    SEARCHD_CONNECTION = {
        'host': '127.0.0.1',
        'port': 9977,
    }


pp = pprint.PrettyPrinter(indent=4)

... [truncated, 158 more lines] ...

#!/usr/bin/python
# -*- coding: latin1 -*-

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.4  - 12-10-2015@22:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python
###########################

######## export PYTHON_EGG_CACHE=/tmp

import os
import pprint
import nltk
#import rocksdb                                         # shared library kann aktuell noch nicht gelesen werden
import MySQLdb                                          # apt-get install python-mysqldb
from sphinxit.core.processor import Search              # http://sphinxit.readthedocs.org/en/latest/
from sphinxit.core.helpers import BaseSearchConfig
import random
import codecs
import sys
import unicodedata

os.environ['PYTHON_EGG_CACHE'] = '/tmp'


from nltk.tokenize import sent_tokenize
###python -m nltk.downloader -d /usr/share/nltk_data all
####python -m nltk.downloader all
###########nltk.download()

reload(sys)
sys.setdefaultencoding('latin-1')

class SphinxitConfig(BaseSearchConfig):
    DEBUG = False
    WITH_META = False
    WITH_STATUS = False
    POOL_SIZE = 5
    # SQL_ENGINE = 'oursql'
    SEARCHD_CONNECTION = {
        'host': '127.0.0.1',
        'port': 9977,
    }

pp = pprint.PrettyPrinter(indent=4)
#delimiters      = ['\n', ' ', ',', '.', '?', '!', ':', ';', '\s', '\t', '\r']

... [truncated, 156 more lines] ...

#!/usr/bin/python
# -*- coding: latin1 -*-

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.4  - 12-10-2015@22:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python
###########################

######## export PYTHON_EGG_CACHE=/tmp

import os
import pprint
import nltk
#import rocksdb                                         # shared library kann aktuell noch nicht gelesen werden
import MySQLdb                                          # apt-get install python-mysqldb
from sphinxit.core.processor import Search              # http://sphinxit.readthedocs.org/en/latest/
from sphinxit.core.helpers import BaseSearchConfig
import random
import codecs
import sys
import unicodedata

os.environ['PYTHON_EGG_CACHE'] = '/tmp'


from nltk.tokenize import sent_tokenize
###python -m nltk.downloader -d /usr/share/nltk_data all
####python -m nltk.downloader all
###########nltk.download()

reload(sys)
sys.setdefaultencoding('latin-1')

class SphinxitConfig(BaseSearchConfig):
    DEBUG = False
    WITH_META = False
    WITH_STATUS = False
    POOL_SIZE = 5
    # SQL_ENGINE = 'oursql'
    SEARCHD_CONNECTION = {
        'host': '127.0.0.1',
        'port': 9977,
    }

pp = pprint.PrettyPrinter(indent=4)
#delimiters      = ['\n', ' ', ',', '.', '?', '!', ':', ';', '\s', '\t', '\r']

... [truncated, 156 more lines] ...

#!/usr/bin/python
# -*- coding: latin1 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.4  - 12-10-2015@22:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python
###########################

######## export PYTHON_EGG_CACHE=/tmp
import pprint
import os
import nltk
# import rocksdb                                         # shared library kann aktuell noch nicht gelesen werden
import MySQLdb  # apt-get install python-mysqldb
from sphinxit.core.processor import Search  # http://sphinxit.readthedocs.org/en/latest/
from sphinxit.core.helpers import BaseSearchConfig
from random import randint
import codecs
import sys
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lsa import LsaSummarizer as Summarizer
from sumy.nlp.stemmers import Stemmer
# import smrzr    # https://github.com/lekhakpadmanabh/Summarizer

os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'

###python -m nltk.downloader -d /usr/share/nltk_data all
####python -m nltk.downloader all
###########nltk.download()
# nltk.download("punkt")

reload(sys)
sys.setdefaultencoding('latin-1')


class SphinxitConfig(BaseSearchConfig):
    DEBUG = False
    WITH_META = False
    WITH_STATUS = False
    POOL_SIZE = 5
    # SQL_ENGINE = 'oursql'
    SEARCHD_CONNECTION = {

... [truncated, 246 more lines] ...

#!/usr/bin/python
# -*- coding: latin1 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.4  - 12-10-2015@22:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python
###########################

######## export PYTHON_EGG_CACHE=/tmp
import pprint
import os
import nltk
# import rocksdb                                         # shared library kann aktuell noch nicht gelesen werden
import MySQLdb  # apt-get install python-mysqldb
from sphinxit.core.processor import Search  # http://sphinxit.readthedocs.org/en/latest/
from sphinxit.core.helpers import BaseSearchConfig
from random import randint
import codecs
import sys
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lsa import LsaSummarizer as Summarizer
from sumy.nlp.stemmers import Stemmer
# import smrzr    # https://github.com/lekhakpadmanabh/Summarizer

os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'

###python -m nltk.downloader -d /usr/share/nltk_data all
####python -m nltk.downloader all
###########nltk.download()
# nltk.download("punkt")

reload(sys)
sys.setdefaultencoding('latin-1')


class SphinxitConfig(BaseSearchConfig):
    DEBUG = False
    WITH_META = False
    WITH_STATUS = False
    POOL_SIZE = 5
    # SQL_ENGINE = 'oursql'
    SEARCHD_CONNECTION = {

... [truncated, 246 more lines] ...

#!/usr/bin/python
# -*- coding: latin1 -*-

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.4  - 12-10-2015@22:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python
###########################

######## export PYTHON_EGG_CACHE=/tmp

import os
import pprint
import nltk
# import rocksdb                                         # shared library kann aktuell noch nicht gelesen werden
import MySQLdb  # apt-get install python-mysqldb
from sphinxit.core.processor import Search  # http://sphinxit.readthedocs.org/en/latest/
from sphinxit.core.helpers import BaseSearchConfig
import random
import codecs
import sys
import unicodedata

os.environ['PYTHON_EGG_CACHE'] = '/tmp'

from nltk.tokenize import sent_tokenize
###python -m nltk.downloader -d /usr/share/nltk_data all
####python -m nltk.downloader all
###########nltk.download()

reload(sys)
sys.setdefaultencoding('latin-1')


class SphinxitConfig(BaseSearchConfig):
    DEBUG = False
    WITH_META = False
    WITH_STATUS = False
    POOL_SIZE = 5
    # SQL_ENGINE = 'oursql'
    SEARCHD_CONNECTION = {
        'host': '127.0.0.1',
        'port': 9977,
    }


pp = pprint.PrettyPrinter(indent=4)

... [truncated, 158 more lines] ...

#!/usr/bin/python
# -*- coding: latin1 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.4a  - 14-10-2015@22:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python
###########################

######## export PYTHON_EGG_CACHE=/tmp
import pprint
import os
import nltk
# import rocksdb                                         # shared library kann aktuell noch nicht gelesen werden
import MySQLdb  # apt-get install python-mysqldb
from sphinxit.core.processor import Search  # http://sphinxit.readthedocs.org/en/latest/
from sphinxit.core.helpers import BaseSearchConfig
from random import randint
import codecs
import sys
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lsa import LsaSummarizer as Summarizer
from sumy.nlp.stemmers import Stemmer
# import smrzr    # https://github.com/lekhakpadmanabh/Summarizer
import re

os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'


###python -m nltk.downloader -d /usr/share/nltk_data all
####python -m nltk.downloader all
###########nltk.download()
# nltk.download("punkt")

reload(sys)
sys.setdefaultencoding('latin-1')


class SphinxitConfig(BaseSearchConfig):
    DEBUG = False
    WITH_META = False
    WITH_STATUS = False
    POOL_SIZE = 5

... [truncated, 298 more lines] ...

#!/usr/bin/python
# -*- coding: latin1 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.4a  - 14-10-2015@22:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python
###########################

######## export PYTHON_EGG_CACHE=/tmp
import pprint
import os
import nltk
# import rocksdb                                         # shared library kann aktuell noch nicht gelesen werden
import MySQLdb  # apt-get install python-mysqldb
from sphinxit.core.processor import Search  # http://sphinxit.readthedocs.org/en/latest/
from sphinxit.core.helpers import BaseSearchConfig
from random import randint
import codecs
import sys
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lsa import LsaSummarizer as Summarizer
from sumy.nlp.stemmers import Stemmer
# import smrzr    # https://github.com/lekhakpadmanabh/Summarizer
import re

os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'


###python -m nltk.downloader -d /usr/share/nltk_data all
####python -m nltk.downloader all
###########nltk.download()
# nltk.download("punkt")

reload(sys)
sys.setdefaultencoding('latin-1')


class SphinxitConfig(BaseSearchConfig):
    DEBUG = False
    WITH_META = False
    WITH_STATUS = False
    POOL_SIZE = 5

... [truncated, 298 more lines] ...

#!/usr/bin/python
# -*- coding: ISO-8859-1 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.5  - 14-10-2015@23:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python
###########################

######## export PYTHON_EGG_CACHE=/tmp
import pprint
import os
import nltk
# import rocksdb                                         # shared library kann aktuell noch nicht gelesen werden
import MySQLdb  # apt-get install python-mysqldb
from sphinxit.core.processor import Search  # http://sphinxit.readthedocs.org/en/latest/
from sphinxit.core.helpers import BaseSearchConfig
from random import randint
import codecs
import sys
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lsa import LsaSummarizer as Summarizer
from sumy.nlp.stemmers import Stemmer
# import smrzr    # https://github.com/lekhakpadmanabh/Summarizer
import re
from transliterate import translit, get_available_language_codes

os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'


###python -m nltk.downloader -d /usr/share/nltk_data all
####python -m nltk.downloader all
###########nltk.download()
# nltk.download("punkt")

reload(sys)
sys.setdefaultencoding('utf-8')


class SphinxitConfig(BaseSearchConfig):
    DEBUG = False
    WITH_META = False
    WITH_STATUS = False

... [truncated, 317 more lines] ...

#!/usr/bin/python
# -*- coding: ISO-8859-1 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.5  - 14-10-2015@23:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python
###########################

######## export PYTHON_EGG_CACHE=/tmp
import pprint
import os
import nltk
# import rocksdb                                         # shared library kann aktuell noch nicht gelesen werden
import MySQLdb  # apt-get install python-mysqldb
from sphinxit.core.processor import Search  # http://sphinxit.readthedocs.org/en/latest/
from sphinxit.core.helpers import BaseSearchConfig
from random import randint
import codecs
import sys
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lsa import LsaSummarizer as Summarizer
from sumy.nlp.stemmers import Stemmer
# import smrzr    # https://github.com/lekhakpadmanabh/Summarizer
import re
from transliterate import translit, get_available_language_codes

os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'


###python -m nltk.downloader -d /usr/share/nltk_data all
####python -m nltk.downloader all
###########nltk.download()
# nltk.download("punkt")

reload(sys)
sys.setdefaultencoding('utf-8')


class SphinxitConfig(BaseSearchConfig):
    DEBUG = False
    WITH_META = False
    WITH_STATUS = False

... [truncated, 317 more lines] ...

#!/usr/bin/python
# -*- coding: ISO-8859-1 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.6  - 15-10-2015@23:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python
###########################

######## export PYTHON_EGG_CACHE=/tmp
import pprint
import os
import nltk
# import rocksdb                                            # shared library kann aktuell noch nicht gelesen werden
import MySQLdb                                              # apt-get install python-mysqldb
from sphinxit.core.processor import Search                  # http://sphinxit.readthedocs.org/en/latest/
from sphinxit.core.helpers import BaseSearchConfig
from random import randint
from past.builtins import basestring                        # pip install future
import codecs
import sys
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lsa import LsaSummarizer as Summarizer
from sumy.nlp.stemmers import Stemmer
import re
from transliterate import translit, get_available_language_codes
import libleipzig
import pprint
import json

os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'

###python -m nltk.downloader -d /usr/share/nltk_data all
####python -m nltk.downloader all
###########nltk.download()
# nltk.download("punkt")

reload(sys)
sys.setdefaultencoding('utf-8')
noDoubleHash = set()

# lies die Ein und Ausgabedateien
inputfile = sys.argv[1]

... [truncated, 392 more lines] ...

#!/usr/bin/python
# -*- coding: ISO-8859-1 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.6  - 15-10-2015@23:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python
###########################

######## export PYTHON_EGG_CACHE=/tmp
import pprint
import os
import nltk
# import rocksdb                                            # shared library kann aktuell noch nicht gelesen werden
import MySQLdb                                              # apt-get install python-mysqldb
from sphinxit.core.processor import Search                  # http://sphinxit.readthedocs.org/en/latest/
from sphinxit.core.helpers import BaseSearchConfig
from random import randint
from past.builtins import basestring                        # pip install future
import codecs
import sys
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lsa import LsaSummarizer as Summarizer
from sumy.nlp.stemmers import Stemmer
import re
from transliterate import translit, get_available_language_codes
import libleipzig
import pprint
import json

os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'

###python -m nltk.downloader -d /usr/share/nltk_data all
####python -m nltk.downloader all
###########nltk.download()
# nltk.download("punkt")

reload(sys)
sys.setdefaultencoding('utf-8')
noDoubleHash = set()

# lies die Ein und Ausgabedateien
inputfile = sys.argv[1]

... [truncated, 392 more lines] ...

#!/usr/bin/python
# -*- coding: ISO-8859-1 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.6  - 16-10-2015@23:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python
###########################

######## export PYTHON_EGG_CACHE=/tmp
import pprint
import os
import nltk
# import rocksdb                                            # shared library kann aktuell noch nicht gelesen werden
import MySQLdb                                              # apt-get install python-mysqldb
from sphinxit.core.processor import Search                  # http://sphinxit.readthedocs.org/en/latest/
from sphinxit.core.helpers import BaseSearchConfig
from random import randint
from past.builtins import basestring                        # pip install future
import codecs
import sys
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lsa import LsaSummarizer as Summarizer
from sumy.nlp.stemmers import Stemmer
import re
from transliterate import translit, get_available_language_codes
import libleipzig
import pprint
import json

os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'

###python -m nltk.downloader -d /usr/share/nltk_data all
####python -m nltk.downloader all
###########nltk.download()
# nltk.download("punkt")

reload(sys)
sys.setdefaultencoding('utf-8')
noDoubleHash    = set()
###re_match        = r"[(\?|\.|\!)][(\t|\r|\n|\s|\w){0,}]([A-Za-z0-9]{1,})" # Match: ". WORT"
re_match        = r"(\?|\.|\!)$" # Match: ". WORT"


... [truncated, 435 more lines] ...

#!/usr/bin/python
# -*- coding: ISO-8859-1 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.6  - 16-10-2015@23:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python
###########################

######## export PYTHON_EGG_CACHE=/tmp
import pprint
import os
import nltk
# import rocksdb                                            # shared library kann aktuell noch nicht gelesen werden
import MySQLdb                                              # apt-get install python-mysqldb
from sphinxit.core.processor import Search                  # http://sphinxit.readthedocs.org/en/latest/
from sphinxit.core.helpers import BaseSearchConfig
from random import randint
from past.builtins import basestring                        # pip install future
import codecs
import sys
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lsa import LsaSummarizer as Summarizer
from sumy.nlp.stemmers import Stemmer
import re
from transliterate import translit, get_available_language_codes
import libleipzig
import pprint
import json

os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'

###python -m nltk.downloader -d /usr/share/nltk_data all
####python -m nltk.downloader all
###########nltk.download()
# nltk.download("punkt")

reload(sys)
sys.setdefaultencoding('utf-8')
noDoubleHash    = set()
###re_match        = r"[(\?|\.|\!)][(\t|\r|\n|\s|\w){0,}]([A-Za-z0-9]{1,})" # Match: ". WORT"
re_match        = r"(\?|\.|\!)$" # Match: ". WORT"


... [truncated, 435 more lines] ...

#!/usr/bin/python
# -*- coding: ISO-8859-1 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.7  - 17-10-2015@23:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python
###########################


#https://docs.python.org/2/library/configparser.html


######## export PYTHON_EGG_CACHE=/tmp
import pprint
import os
import nltk
# import rocksdb                                            # shared library kann aktuell noch nicht gelesen werden
import MySQLdb                                              # apt-get install python-mysqldb
from sphinxit.core.processor import Search                  # http://sphinxit.readthedocs.org/en/latest/
from sphinxit.core.helpers import BaseSearchConfig
from random import randint
from past.builtins import basestring                        # pip install future
import codecs
import sys
from sumy.parsers.plaintext import PlaintextParser          # https://github.com/miso-belica/sumy
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lsa import LsaSummarizer as Summarizer
from sumy.nlp.stemmers import Stemmer
import re
from transliterate import translit, get_available_language_codes
import libleipzig
import pprint
import json
from textstat.textstat import textstat                      # https://pypi.python.org/pypi/textstat

os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'

###python -m nltk.downloader -d /usr/share/nltk_data all
####python -m nltk.downloader all
###########nltk.download()
# nltk.download("punkt")

reload(sys)

... [truncated, 469 more lines] ...

#!/usr/bin/python
# -*- coding: ISO-8859-1 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.7  - 17-10-2015@23:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python
###########################


#https://docs.python.org/2/library/configparser.html


######## export PYTHON_EGG_CACHE=/tmp
import pprint
import os
import nltk
# import rocksdb                                            # shared library kann aktuell noch nicht gelesen werden
import MySQLdb                                              # apt-get install python-mysqldb
from sphinxit.core.processor import Search                  # http://sphinxit.readthedocs.org/en/latest/
from sphinxit.core.helpers import BaseSearchConfig
from random import randint
from past.builtins import basestring                        # pip install future
import codecs
import sys
from sumy.parsers.plaintext import PlaintextParser          # https://github.com/miso-belica/sumy
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lsa import LsaSummarizer as Summarizer
from sumy.nlp.stemmers import Stemmer
import re
from transliterate import translit, get_available_language_codes
import libleipzig
import pprint
import json
from textstat.textstat import textstat                      # https://pypi.python.org/pypi/textstat

os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'

###python -m nltk.downloader -d /usr/share/nltk_data all
####python -m nltk.downloader all
###########nltk.download()
# nltk.download("punkt")

reload(sys)

... [truncated, 469 more lines] ...

#!/usr/bin/python
# -*- coding: ISO-8859-1 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.8  - 21-10-2015@23:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python
###########################

#https://docs.python.org/2/library/configparser.html

import os
import nltk                                            # apt-get install python-mysqldb
from sphinxit.core.processor import Search                  # http://sphinxit.readthedocs.org/en/latest/
import codecs
import re
from transliterate import translit, get_available_language_codes
import onetipp

import sys
sys.path.append('/home/onetipp/python/modules')
os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'
sys.setdefaultencoding('utf-8')

noDoubleHash    = set()
###re_match        = r"[(\?|\.|\!)][(\t|\r|\n|\s|\w){0,}]([A-Za-z0-9]{1,})" # Match: ". WORT"
re_match        = r"(\?|\.|\!)$" # Match: ". WORT"

# lies die Ein und Ausgabedateien
inputfile   = sys.argv[1]
outputfile  = sys.argv[2]

# http://www.tutorialspoint.com/python/python_command_line_arguments.htm
# read file into string
text = open(inputfile, 'r').read()
#text.decode('utf-8')
text = text.decode("utf-8")

# sent_tokenize_list = sent_tokenize(text)
# Summarize the text first and then work on it
tSumy       = onetipp.summarizeText(text)
tokens      = nltk.word_tokenize(tSumy)
tokensRaw   = nltk.word_tokenize(text)


... [truncated, 216 more lines] ...

#!/usr/bin/python
# -*- coding: utf-8 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.8a  - 22-10-2015@23:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python: Main File
###########################

#https://docs.python.org/2/library/configparser.html
import os
import sys
reload(sys)
sys.path.append('/home/onetipp/python/modules')
os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'
sys.setdefaultencoding('utf-8')

                                          # apt-get install python-mysqldb
from sphinxit.core.processor import Search                  # http://sphinxit.readthedocs.org/en/latest/
import codecs
import re
from transliterate import translit, get_available_language_codes
import onetipp

noDoubleHash    = set()
###re_match        = r"[(\?|\.|\!)][(\t|\r|\n|\s|\w){0,}]([A-Za-z0-9]{1,})" # Match: ". WORT"
re_match        = r"(\?|\.|\!)$" # Match: ". WORT"

# lies die Ein und Ausgabedateien
inputfile   = sys.argv[1]
outputfile  = sys.argv[2]

# http://www.tutorialspoint.com/python/python_command_line_arguments.htm
# read file into string
text = open(inputfile, 'r').read()
#text.decode('utf-8')
text = text.decode("utf-8")

# sent_tokenize_list = sent_tokenize(text)
# Summarize the text first and then work on it
tSumy       = onetipp.summarizeText(text)
tokens      = onetipp.nltk.word_tokenize(tSumy)
tokensRaw   = onetipp.nltk.word_tokenize(text)


... [truncated, 214 more lines] ...

#!/usr/bin/python
# -*- coding: ISO-8859-1 -*-
from __future__ import division
from __future__ import absolute_import
from __future__ import division, print_function, unicode_literals

###########################
### Autor: Sebastian Enger / M.Sc.
### Copyright: Sebastian Enger
### Licence: Commercial / OneTipp
### Version: 1.0.8a  - 22-10-2015@23:53 Uhr
### Contact: sebastian.enger@gmail.com
### OneTipp Text Tool in Python: Main File
###########################

"""
Synonym bzw Wortersetzung parallelisieren fr schnellere Verarbeitung und Reaktionszeit des Tools

Antonym Datenbank Entwicklung mit Hilfe gecrawlter Websites

Aufbau einer Datenbank mit einfacher deutscher Sprache

Berechnung des lesbarkeitswerts eines eingabetextes - basierend auf einfachen Texten die "simple German " Datenbank fr Austausch nutzen, Wissenschaftliche Texte mit Leipzig und unserer lokalen Synonym Datenbank austauschen

"""


import pprint
#https://docs.python.org/2/library/configparser.html
import os
import sys
reload(sys)
sys.path.append('/home/onetipp/python/modules')
os.environ['PYTHON_EGG_CACHE'] = '/home/compress/'

import random
import sphinxapi
import codecs
import re
from transliterate import translit, get_available_language_codes
import onetipp

#client = sphinxapi.SphinxClient()
#client.SetServer('127.0.0.1', 9312)

cursorMysql = onetipp.mysql.cursor()

noDoubleHash    = set()
###re_match        = r"[(\?|\.|\!)][(\t|\r|\n|\s|\w){0,}]([A-Za-z0-9]{1,})" # Match: ". WORT"
re_match        = r"(\?|\.|\!)" # Match: ". WORT"

... [truncated, 306 more lines] ...