CSV Added for Books Data, text files folder changed,

Added create xml to run.py

books_data.csv

@@ -0,0 +1,16 @@
+Index;BookCode;Language;BookName;Status
+1;dost_cap;en;crime_EN.txt;
+2;dost_cap;fr;crime_FR.txt;
+3;dost_cap;ru;crime_RU.txt;
+4;dost_deadhouse;en;dead_EN.txt;
+5;dost_deadhouse;fr;dead_FR.txt;
+6;dost_deadhouse;ru;dead_RU.txt;
+7;dost_karamazov;en;karamazov_EN.txt;
+8;dost_karamazov;fr;karamazov_FR.txt;
+9;dost_karamazov;ru;karamazov_RU.txt;
+10;dost_poorfolk;en;poor_EN.txt;
+11;dost_poorfolk;fr;poor_FR.txt;
+12;dost_poorfolk;ru;poor_RU.txt;
+13;dost_underground;en;underground_EN.txt;
+14;dost_underground;fr;underground_FR.txt;
+15;dost_underground;ru;underground_RU.txt;

run.py

@@ -4,6 +4,8 @@ import xml_parser.validate as validate
 import utils.json_utils as json_utils
 import utils.constants as const
 import utils.env_utils as env
+import xml_parser.create_xml as create_xml
+from csv2df import get_book_content, get_book_metadata
 
 
 def validate_all_xml_files():
@@ -33,6 +35,11 @@ def save_validated_files_to_db():
     json_utils.write_json_file(const.JSON_PATH, json_data)
 
 
+def create_xml_file(book_content_dict, book_metadata_dict):
+    create_xml.create_xml_file(book_content_dict, book_metadata_dict)
+
+
 if env.check_env_variables():
-    validate_all_xml_files()
+    create_xml_file(get_book_content(), get_book_metadata())
+    # validate_all_xml_files()
     # save_validated_files_to_db()

txt_parser/csv_utils.py

@@ -0,0 +1,37 @@
+import csv
+import os
+import utils.constants as const
+
+
+csv_header_row = ['Index', 'BookCode', 'Language', 'BookName', 'Status']
+
+
+def read_books_csv_file(csv_file_name):
+    csv_file_path = os.path.dirname(os.path.dirname(__file__))+'/'+csv_file_name
+    with open(csv_file_path, 'r') as file:
+        books_data = csv.reader(file, delimiter=';')
+        books_list = []
+        is_header = True
+        for book in books_data:
+            if is_header:
+                is_header = False
+                continue
+            books_list.append(book)
+        return books_list
+
+
+def write_books_data_to_csv(csv_file_name, books_list):
+    csv_file_path = os.path.dirname(os.path.dirname(__file__))+'/'+csv_file_name
+    with open(csv_file_path, 'w') as file:
+        writer = csv.writer(file, delimiter=';')
+        writer.writerow(csv_header_row)
+        for book in books_list:
+            writer.writerow(book)
+
+
+def read_data_file(file_path):
+    txt_file_path = os.path.dirname(os.path.dirname(__file__)) + const.DATA_FOLDER + file_path
+    with open(txt_file_path, 'r') as file:
+        lines = file.readline()
+        file.close()
+        return lines

txt_parser/test_txt.py

@@ -0,0 +1,10 @@
+import txt_parser.csv_utils as read_csv
+import utils.constants as const
+
+books_list = read_csv.read_books_csv_file(const.CSV_FILE)
+
+for book in books_list:
+    print(book)
+    print(type(book))
+
+read_csv.write_books_data_to_csv(const.CSV_FILE, books_list)

txt_parser/txt_cleaner.py

@@ -11,7 +11,7 @@ import pandas as pd
 
 
 def get_text():
-    file = open("C:\\Users\\Nerv\\Text-Technology\\Aligner\\txt\\crime_EN.txt", 'r')
+    file = open("C:\\Users\\Nerv\\Text-Technology\\Aligner\\data\\crime_EN.data", 'r')
     lines = file.readlines()
     file.close()
     count = 0

utils/constants.py

@@ -2,6 +2,10 @@ JSON_PATH = 'json/books.json'
 
 XSD_PATH = 'xml_parser/book.xsd'
 
+CSV_FILE = 'books_data.csv'
+
+DATA_FOLDER = '/data/'
+
 TRANSLATE_ENV_VAR = 'GOOGLE_APPLICATION_CREDENTIALS'
 
 MYSQL_PASS_ENV_VAR = 'MYSQL_PASSWORD'