1+ import openpyxl , re , os , csv
2+ from openpyxl .utils import get_column_letter
3+ from utils import *
4+
5+ from typing import TypeAlias
6+ from openpyxl .worksheet .worksheet import Worksheet
7+
8+ ExtractedData : TypeAlias = tuple [tuple [str , ...], ...]
9+ Patterns : TypeAlias = list [str ]
10+
11+ class CSVFileExtractor :
12+ def __init__ (self , col_var ):
13+ self .col_var = col_var
14+
15+ def create_csv_file (self , output_file : str , patterns : Patterns ,content : str ) -> str | None :
16+ extracted_data = DataExtractor .extract_data (patterns ,content )
17+
18+ if WithLogging .with_logging :
19+ extracted_data_copy = extracted_data
20+
21+ if self .col_var .get ():
22+ extracted_data = DataExtractor .create_column_order (extracted_data )
23+
24+ with open (output_file ,'a' ,newline = '' ,encoding = ENCODING ) as f :
25+ writer = csv .writer (f )
26+ writer .writerows (extracted_data )
27+
28+ if WithLogging .with_logging :
29+ return DataExtractor .log_found_data (extracted_data_copy )
30+
31+ class ExcelFileExtractor :
32+ def __init__ (self , col_var , exact_var ):
33+ self .col_var = col_var
34+ self .exact_var = exact_var
35+
36+ @staticmethod
37+ def find_max (index : int , sheet : Worksheet ) -> int :
38+ row = 0
39+ for i in sheet .iter_rows (min_col = index ,max_col = index ):
40+ if i [0 ].value is not None :
41+ row = i [0 ].row
42+ return row
43+
44+ @staticmethod
45+ def put_data_in_excel_without_exact_order (extracted_data : ExtractedData , sheet : Worksheet ) -> None :
46+ for data_list in extracted_data :
47+ sheet .append (data_list )
48+
49+ @staticmethod
50+ def get_cell (pattern_letter : str , row_number : int ):
51+ return pattern_letter + str (row_number )
52+
53+ @staticmethod
54+ def put_data_in_excel_with_exact_order (extracted_data : ExtractedData , sheet : Worksheet ) -> None :
55+ column_letters_list = [get_column_letter (i ) for i in range (1 ,len (extracted_data )+ 1 )]
56+
57+ find_max_index = 1
58+ columns_list_index = 0
59+
60+ for data_list in extracted_data :
61+ row_number = ExcelFileExtractor .find_max (find_max_index ,sheet ) + 1
62+ for item in data_list :
63+ sheet [ExcelFileExtractor .get_cell (column_letters_list [columns_list_index ],row_number )] = item
64+ row_number += 1
65+ columns_list_index += 1
66+ find_max_index += 1
67+
68+ def create_excel_file (self , output_file : str , sheet_name : str , patterns : Patterns , content : str ) -> str | None :
69+ if not os .path .isfile (output_file ):
70+ wb = openpyxl .Workbook ()
71+ wb .save (output_file )
72+ wb .close ()
73+
74+ sheet_name = sheet_name .title ()
75+
76+ wb = openpyxl .load_workbook (output_file )
77+
78+ if sheet_name in wb .sheetnames :
79+ sheet = wb [sheet_name ]
80+ else :
81+ sheet = wb .create_sheet (sheet_name )
82+
83+ extracted_data = DataExtractor .extract_data (patterns ,content )
84+
85+ if WithLogging .with_logging :
86+ extracted_data_copy = extracted_data
87+
88+ if self .col_var .get () and not self .exact_var .get ():
89+ extracted_data = DataExtractor .create_column_order (extracted_data )
90+
91+ if not self .exact_var .get (): # The codes in this if statement will not be executed if 'put in rows' is enabled
92+ ExcelFileExtractor .put_data_in_excel_without_exact_order (extracted_data ,sheet )
93+ else :
94+ ExcelFileExtractor .put_data_in_excel_with_exact_order (extracted_data ,sheet )
95+
96+ wb .save (output_file )
97+ wb .close ()
98+
99+ if WithLogging .with_logging :
100+ return DataExtractor .log_found_data (extracted_data_copy )
101+
102+ class DataExtractor :
103+ def __init__ (self , excel_var , log_text , col_var , exact_var ):
104+ self .log_text = log_text
105+ self .excel_var = excel_var
106+
107+ self .excel_extractor = ExcelFileExtractor (col_var , exact_var )
108+ self .csv_extractor = CSVFileExtractor (col_var )
109+
110+ @staticmethod
111+ def extract_data (patterns : Patterns , content : str ) -> ExtractedData :
112+ extracted_data = []
113+ for pattern in patterns :
114+ data_list = re .findall (pattern ,content )
115+ extracted_data .append (data_list )
116+
117+ return extracted_data
118+
119+ def prepare_to_extract_data (self , output_file : str , input_file : str , sheet_name : str , patterns : Patterns ) -> None :
120+ try :
121+ assert patterns , 'There is no patterns to extract data'
122+
123+ with open (input_file ,encoding = ENCODING ) as f :
124+ try :
125+ content = f .read ()
126+ except UnicodeDecodeError :
127+ raise ValueError ('The input file cannot be a binary file' )
128+
129+ assert output_file , 'The name of output file is required.'
130+
131+ output_file_extention = os .path .splitext (output_file )[1 ].lower ()
132+
133+ if self .excel_var .get ():
134+ if output_file_extention in ['.xlsx' , '.xlsm' , '.xltx' , '.xltm' ]:
135+ log_string = self .excel_extractor .create_excel_file (output_file ,sheet_name ,patterns ,content )
136+ else :
137+ raise ValueError ('The output file format is not supported. It should be .xlsx, .xlsm, .xltx or .xltm' )
138+
139+ else :
140+ log_string = self .csv_extractor .create_csv_file (output_file ,patterns ,content )
141+
142+ if WithLogging .with_logging :
143+ log_string += f'\n { output_file !r} + '\n '
144+ self .log_text .config (state = 'normal' )
145+ self .log_text .delete ('1.0' ,'end' )
146+ self .log_text .insert ('end' , log_string )
147+ self .log_text .config (state = 'disabled' )
148+ self .log_text .see ('end' )
149+
150+ except (FileNotFoundError , AssertionError , PermissionError , ValueError , re .PatternError ) as err :
151+ show_error (err )
152+
153+ @staticmethod
154+ def log_found_data (extracted_data_copy : ExtractedData ) -> str :
155+ log_string = ''
156+
157+ for data_list in extracted_data_copy :
158+ log_string += '\n ' .join (data_list ) + '\n '
159+
160+ return log_string
161+
162+ @staticmethod
163+ def create_column_order (extracted_data : ExtractedData ) -> tuple [tuple [str ]]:
164+ max_len = max ([len (data_list ) for data_list in extracted_data ])
165+
166+ for data_list in extracted_data :
167+ for _ in range (max_len - len (data_list )):
168+ data_list .append ('' )
169+
170+ return tuple (zip (* extracted_data ))
0 commit comments