Last active
February 14, 2023 21:15
-
-
Save sqe/7eb1641edf1eba4eadde to your computer and use it in GitHub Desktop.
test data generator
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import os | |
| # Please change per your desire: | |
| Source_File_Name = str(raw_input("input the text file name: ")) | |
| Destination = str(raw_input("input the destination directory: ")) #c:\\Python27\\Test_Data" | |
| Word_Count = int(raw_input("how many words should be read into each file: ")) # 10 | |
| How_Many_Files = int(raw_input("how many files you want to generate: ")) #100 | |
| Dir_Divider = int(raw_input("how many files per directory: ")) #25 | |
| Destination_File_Prefix = str(raw_input("input future file prefix: ")) #"WaP_" | |
| Destination_File_Extention = str(raw_input("input future file's extension: ")) #".txt" | |
| # Do not change these: | |
| Start_Index = 0 | |
| File_Count = 0 | |
| Destination_Part = Destination + '0000' | |
| Source_File = open(Source_File_Name,'r') | |
| List_Of_Words = Source_File.read().split() | |
| Words_In_Source_File = len(List_Of_Words) | |
| while File_Count < How_Many_Files: | |
| Start_Index = (Start_Index + Word_Count) % Words_In_Source_File | |
| Selected_Words = " ".join(List_Of_Words[Start_Index:Start_Index + Word_Count:1]) | |
| File_Count = File_Count + 1 | |
| File_Name = Destination_File_Prefix + str(File_Count) + Destination_File_Extention | |
| File_Object = open(Destination_Part + "\\" + File_Name,'w') | |
| File_Object.write(Selected_Words + '\r\nFILEID ' + str(File_Count)) | |
| File_Object.close() | |
| if File_Count % int(Dir_Divider) is 0: | |
| Destination_Part = Destination + "\\" + str(Dir_Divider) | |
| os.mkdir(Destination_Part) | |
| Dir_Divider += 25 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment