import markovify
import codecs
import sys
import os

# cat out.txt | uniq -c
filename = sys.argv[1]

with codecs.open(filename,'r',encoding='utf8') as f:
    text = f.read()

os.remove("out.txt") if os.path.exists("out.txt") else None

# Build the model.
text_model = markovify.Text(text)
print("\nFive Random texts: \n#################################################\n")
# Print five randomly-generated sentences
for i in range(10):
    s = text_model.make_sentence()
    print("Neuer Satz:")
    print(s)
    print("\n")
    with codecs.open("out.txt",'a',encoding='utf8') as f:
         if s is not None:
            f.write(s)
            f.write("\n")

# print("\nFive Random texts beginning with #Meine Freundin#: \n#################################################\n")
# # Print five randomly-generated sentences
# for i in range(5):
#     print("NEW SPC SENTENCE ---->   ")
#     print(text_model.make_sentence_with_start("Meine Freundin"))
#     print("\n")
#
#     #print("\nthree randomly-generated sentences of no more than 140 characters: \n#################################################\n")
#     # Print three randomly-generated sentences of no more than 140 characters
#     #for i in range(3):
#     #    print(text_model.make_short_sentence(140))