93 lines
1.9 KiB
Python
93 lines
1.9 KiB
Python
# -*- coding: utf-8 -*-
|
|
import corenlp as corenlp
|
|
import os
|
|
import re
|
|
import textacy
|
|
import nltk
|
|
from textblob_de import TextBlobDE
|
|
from textblob_de import PatternParser
|
|
|
|
filepath = "lemmatization-de.txt"
|
|
|
|
|
|
|
|
|
|
blob = TextBlobDE(str(textacy.fileio.read_file("teststring.txt")),parser=PatternParser(pprint=True, lemmata=True))
|
|
|
|
print(blob.parse())
|
|
|
|
|
|
|
|
|
|
|
|
#erste spalte zu {lemma : id} . zweite spalte zu {word : id}
|
|
|
|
|
|
|
|
"""http://www.lexiconista.com/datasets/lemmatization/"""
|
|
|
|
lemma2id = {}
|
|
word2id = {}
|
|
|
|
for id,line in enumerate(list(textacy.fileio.read_file_lines(filepath=filepath))):
|
|
|
|
lemma = line.split()[0].strip().lower()
|
|
if lemma not in lemma2id:
|
|
lemma2id[lemma] = id
|
|
|
|
word = line.split()[1].strip().lower()
|
|
|
|
word2id[word] = lemma2id[word]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
"""
|
|
regex_specialChars = r'[`\-=~!#@,.$%^&*()_+\[\]{};\'\\:"|</>?]'
|
|
|
|
|
|
def stringcleaning(stringstream, funclist):
|
|
for string in stringstream:
|
|
for f in funclist:
|
|
string = f(string)
|
|
yield string
|
|
|
|
|
|
def seperate_words_on_regex(regex=regex_specialChars):
|
|
return lambda string: " ".join(re.compile(regex).split(string))
|
|
|
|
|
|
words = [
|
|
"uniaccount",
|
|
"nr54065467",
|
|
"nr54065467",
|
|
"455a33c5,"
|
|
"tvt?=",
|
|
"tanja.saborowski@tu-dortmund.de",
|
|
"-",
|
|
"m-sw1-vl4053.itmc.tu-dortmund.de",
|
|
"------problem--------"
|
|
]
|
|
|
|
|
|
|
|
topLVLFinder = re.compile(r'\.[a-z]{2,3}(\.[a-z]{2,3})?', re.IGNORECASE)
|
|
specialFinder = re.compile(r'[`\-=~!@#$%^&*()_+\[\]{};\'\\:"|<,./>?]', re.IGNORECASE)
|
|
|
|
for s in stringcleaning((w for w in words),[seperate_words_on_regex()]):
|
|
print(s.strip())
|
|
|
|
#print(stringcleaning(w,string_comp))
|
|
#print(bool(re.search(r'\.[a-z]{2,3}(\.[a-z]{2,3})?',w)))
|
|
#print(bool(re.search(r'[`\-=~!@#$%^&*()_+\[\]{};\'\\:"|<,./>?]',w)))
|
|
#result = specialFinder.sub(" ", w)
|
|
#print(re.sub(r'[`\-=~!@#$%^&*()_+\[\]{};\'\\:"|<,./>?]'," ",w))
|
|
|
|
#print(re.sub(r'\.[a-z]{2,3}(\.[a-z]{2,3})?', " ", w))
|
|
""" |