def generate_hash_map(self):
"""
Method who creates a hash map with all word from current file parsed
All words are firstly parsed to Porter Algorithm and then inserted to hash map
:return:
"""
# clear the hash map
self._hash_map.clear()
for line in self._document_content:
line = line.encode('utf-8')
line = str(line).translate(PUNCTUATION_TRANS)
words = line.split()
for word in words:
word = word.decode('utf-8-sig')
word = PorterStemmer().stem(word)
word = word.lower()
if word.isalpha():
if not self._is_stop_word(word):
# if the word is not in hash
if word not in self._hash_map:
self._hash_map[word] = 1
else:
self._hash_map[word] += 1
