62 lines
1.7 KiB
Python
62 lines
1.7 KiB
Python
|
# -*- coding: utf-8 -*-
|
||
|
|
import re
|
||
|
|
|
||
|
|
import spacy
|
||
|
|
import textacy
|
||
|
|
|
||
|
|
DATAPATH_thesaurus = "openthesaurus.csv"
|
||
|
|
|
||
|
|
|
||
|
|
# read .csv
|
||
|
|
thesaurus = textacy.fileio.read_csv(DATAPATH_thesaurus, delimiter=";") # generator [[a,b,c,..],[a,b,c,..],...]
|
||
|
|
|
||
|
|
wort = "(anmachen)"
|
||
|
|
if not re.match(r'\([^)]+\)', wort):
|
||
|
|
print(wort)
|
||
|
|
|
||
|
|
#if "Pass" in wort: # "Pass" muss irgendwo drin sein
|
||
|
|
# print(wort.lower())
|
||
|
|
|
||
|
|
|
||
|
|
#if "Passwort" in wort.split(" "): # Pass muss gleich einem Wort sein
|
||
|
|
# print(wort.lower())
|
||
|
|
|
||
|
|
|
||
|
|
def getFirstSynonym(word, thesaurus_gen):
|
||
|
|
|
||
|
|
word = word.lower()
|
||
|
|
#TODO word cleaning https://stackoverflow.com/questions/3939361/remove-specific-characters-from-a-string-in-python
|
||
|
|
|
||
|
|
|
||
|
|
# durch den thesaurrus iterieren
|
||
|
|
for syn_block in thesaurus_gen: # syn_block ist eine liste mit Synonymen
|
||
|
|
|
||
|
|
# durch den synonymblock iterieren
|
||
|
|
for syn in syn_block:
|
||
|
|
syn = syn.lower().split(" ") # aus synonym mach liste (um evtl. sätze zu identifieziren)
|
||
|
|
|
||
|
|
# falls das wort in dem synonym enthalten ist (also == einem Wort in der liste ist)
|
||
|
|
if word in syn:
|
||
|
|
|
||
|
|
# Hauptform suchen
|
||
|
|
if "auptform" in syn:
|
||
|
|
#nicht ausgeben, falls es in Klammern steht
|
||
|
|
for w in syn:
|
||
|
|
if not re.match(r'\([^)]+\)',w):
|
||
|
|
return w
|
||
|
|
|
||
|
|
|
||
|
|
# falls keine hauptform enthalten ist, das erste Synonym zurückgeben, was kein satz ist und nicht in klammern steht
|
||
|
|
if len(syn) == 1:
|
||
|
|
w = syn[0]
|
||
|
|
if not re.match(r'\([^)]+\)', w):
|
||
|
|
return w
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
return word #zur Not die eingabe ausgeben
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
print(getFirstSynonym(wort,thesaurus))
|