From 02bffc0132b06a868623a7b9e9c4977cf260e8f8 Mon Sep 17 00:00:00 2001
From: Pavan Mandava <mspavan04@gmail.com>
Date: Wed, 22 Jan 2020 23:49:32 +0100
Subject: [PATCH] Projekt Structure changed

---
 {utils/txt_preparation => aligner}/__init__.py    |  0
 bitext_align.py => aligner/bitext_align.py        | 15 +++++----------
 .../book_structure.xml => book_structure.xml      |  0
 run.py                                            |  6 +++---
 txt_parser/__init__.py                            |  0
 .../txt_preparation => txt_parser}/txt_cleaner.py |  0
 utils/constants.py                                |  2 +-
 {xml_files => xml_parser}/book.xsd                |  0
 8 files changed, 9 insertions(+), 14 deletions(-)
 rename {utils/txt_preparation => aligner}/__init__.py (100%)
 rename bitext_align.py => aligner/bitext_align.py (97%)
 rename xml_files/book_structure.xml => book_structure.xml (100%)
 create mode 100644 txt_parser/__init__.py
 rename {utils/txt_preparation => txt_parser}/txt_cleaner.py (100%)
 rename {xml_files => xml_parser}/book.xsd (100%)

diff --git a/utils/txt_preparation/__init__.py b/aligner/__init__.py
similarity index 100%
rename from utils/txt_preparation/__init__.py
rename to aligner/__init__.py
diff --git a/bitext_align.py b/aligner/bitext_align.py
similarity index 97%
rename from bitext_align.py
rename to aligner/bitext_align.py
index 5068a02..2970dcc 100644
--- a/bitext_align.py
+++ b/aligner/bitext_align.py
@@ -1,18 +1,13 @@
 # -*- coding: utf-8 -*- 
 
 
-import os,sys
-import re
-import pandas as pd
+from itertools import product as cp
+
 import numpy as np
-from numpy import cumsum
-from pandas import DataFrame
-from nltk import word_tokenize, sent_tokenize
-#import xml.etree.ElementTree as ET
-from jellyfish import levenshtein_distance as lev
-#import six
+import pandas as pd
 from google.cloud import translate_v2 as translate
-from itertools import product as cp
+from jellyfish import levenshtein_distance as lev
+from nltk import sent_tokenize
 
 translate_client = translate.Client()
 
diff --git a/xml_files/book_structure.xml b/book_structure.xml
similarity index 100%
rename from xml_files/book_structure.xml
rename to book_structure.xml
diff --git a/run.py b/run.py
index 5be3377..0a0c5aa 100644
--- a/run.py
+++ b/run.py
@@ -17,10 +17,10 @@ def save_validated_files_to_db():
         books_list = books_json[book_code]
         for book in books_list:
             if not book['is_validated']:
-                print(const.WARNING, 'Book : ', book['xml_file'], ' is not validated against XSD', const.END)
+                print(const.WARNING, 'XML File :: ', book['xml_file'], ' is not validated against XSD', const.END)
                 continue
             if not book['is_saved_to_db']:
-                print(const.BLUE, 'Adding Book : ', book['xml_file'], ' to the DB', const.END)
+                print(const.BLUE, 'Adding Book Data : ', book['xml_file'], ' to the DB', const.END)
                 book_dict = read_xml.parse_xml_file(book['xml_file_path'])
                 result = adb.add_book_to_db(book_code, book_dict)
                 book['is_saved_to_db'] = result
@@ -35,4 +35,4 @@ def save_validated_files_to_db():
 
 if env.check_env_variables():
     validate_all_xml_files()
-    save_validated_files_to_db()
\ No newline at end of file
+    # save_validated_files_to_db()
\ No newline at end of file
diff --git a/txt_parser/__init__.py b/txt_parser/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/utils/txt_preparation/txt_cleaner.py b/txt_parser/txt_cleaner.py
similarity index 100%
rename from utils/txt_preparation/txt_cleaner.py
rename to txt_parser/txt_cleaner.py
diff --git a/utils/constants.py b/utils/constants.py
index f8c4860..9d91590 100644
--- a/utils/constants.py
+++ b/utils/constants.py
@@ -1,6 +1,6 @@
 JSON_PATH = 'json/books.json'
 
-XSD_PATH = 'xml_files/book.xsd'
+XSD_PATH = 'xml_parser/book.xsd'
 
 TRANSLATE_ENV_VAR = 'GOOGLE_APPLICATION_CREDENTIALS'
 
diff --git a/xml_files/book.xsd b/xml_parser/book.xsd
similarity index 100%
rename from xml_files/book.xsd
rename to xml_parser/book.xsd