def check_if_keyword(section):
global removed_keywords
removed_keywords = [normalize_arabic(word) for word in removed_keywords]
for key in interactions_key_words:
key = normalize_arabic(key)
if normalize_arabic(key) in normalize_arabic(section):
text_parts = section.split(key)
if len(text_parts) >= 2:
interactions_text = ' '.join(text_parts[1:])
interactions_text = interactions_text.strip()
possible_interactions = re.split(
"[(-,;\*\\.،،؛::)\n-]| و | او | و", interactions_text)
possible_interactions = [
interaction.strip()
for interaction in possible_interactions
if len(interaction) > 1
]
interactions = []
for inter in possible_interactions:
inter = ' '.join([
inter_word for inter_word in inter.split(" ")
if not any(xs in inter_word for xs in removed_keywords)
])
inter = re.sub(r'[^ء-يa-zA-Z \n]', '', inter)
if check_if_interaction(inter):
interactions.append(inter)
else:
pass
# print("out : ", inter)
return interactions
return ""
def read_human_parts_and_stop_words():
global human_parts
file = "Data/utils/human_parts_2.txt"
file = pkg_resources.resource_filename(__name__, file)
file = open(file, 'r', encoding="utf-8")
parts = file.read()
parts = normalize_arabic(parts)
human_parts = re.split('[\n ]', parts)
def insert_drug_database(drug_name):
drug_id = 0
if drug_name:
drug_id = insert_drug(drug_name,normalize_arabic(drug_name))
else:
drug_id = insert_drug("default","default")
drug_name = "default"
return drug_id, drug_name
def read_stop_words():
global patterns
path = "utils/stopwords.txt"
path = pkg_resources.resource_filename(__name__, path)
file = open(path, 'r', encoding="utf-8")
stop_words = file.read()
stop_words = normalize_arabic(stop_words)
stop_words_ar = re.split('[\n ]', stop_words)
for arr in chunks(stop_words_ar, 15):
stop_words_arr = ' | '.join(arr)
stop_words_arr = " " + stop_words_arr + " "
patterns.append(re.compile(stop_words_arr))
def extract_interactions_for_one_file(file_name, drug_id):
global OUTPUT_DIR
file_path = INPUT_DIR + os.path.sep + file_name
file_path = pkg_resources.resource_filename(__name__, file_path)
section = ''
if os.path.isfile(file_path):
file = open(file_path, 'r', encoding='utf8')
section = file.read()
else:
print("No section found")
return
section = normalize_arabic(section)
section = remove_stop_words(section)
results = check_if_keyword(section)
results = [result.strip() for result in results if len(result) > 1]
OUTPUT_DIR = OUTPUT_DIR + os.path.sep + file_name
OUTPUT_DIR = pkg_resources.resource_filename(__name__, OUTPUT_DIR)
out_file = open(OUTPUT_DIR, 'w', encoding='utf8')
out_file.write('\n'.join(results))
for interaction in results:
insert_drug_interaction(interaction, drug_id)
def insert_drug_database(drug_name):
drug_id = 0
if drug_name:
soundex = Soundex()
metaphone = Metaphone()
rs = RefinedSoundex()
file_path = "utils//DRUGS_ALL_EDITTED.csv"
file_path = pkg_resources.resource_filename(__name__, file_path)
file = open(file_path, "r")
section = file.read()
parts = re.split('[\n]', section)
min_dist = 100
new_name = re.sub("چ", "غ", drug_name)
new_name = re.sub("ﻏ", "غ", new_name)
new_name = normalize_arabic(new_name)
name_en = translate_drug_name(drug_name)
equals = []
min_index = -1
min_dist_all = 100
min_index_all = -1
chosen = False
for part in parts:
if distance_words(name_en, part) == 0 or distance_words(name_en, part) == 1:
chosen = True
print(" Matched To ->", part)
drug_id = insert_drug(drug_name, normalize_arabic(drug_name), part)
return drug_id, drug_name
dist = rs.distance(name_en, part)
if dist <min_dist_all:
min_dist_all = dist
min_index_all = parts.index(part)
if soundex.sounds_like(new_name, part) or soundex.sounds_like(name_en, part):
if rs.distance(new_name, part) < min_dist:
min_dist = rs.distance(new_name, part)
min_index = parts.index(part)
equals.append((part,metaphone.phonetics(part)))
if min_index != -1:
for equ in equals:
if equ[1] == metaphone.phonetics(name_en) or equ == metaphone.phonetics(new_name):
drug_id = insert_drug(drug_name, normalize_arabic(drug_name), equ[0])
chosen = True
return drug_id, drug_name
if not chosen and min_index != -1:
chosen = True
drug_id = insert_drug(drug_name, normalize_arabic(drug_name), parts[min_index])
return drug_id, drug_name
if not chosen:
drug_id = insert_drug(drug_name, normalize_arabic(drug_name), parts[min_index_all])
return drug_id, drug_name
else:
drug_id = insert_drug("----------", "----------", "----------")
drug_name = "default"
return drug_id, drug_name
return drug_id, drug_name