def split_efile(filename):
fs = Filesplit()
filedata = read_file(filename, "rb")
split_length = len(filedata) // 2
if split_length % 2 != 0:
split_length += 1
fs.split(file=filename, split_size=split_length, output_dir="cache")
return True
def merge_decrypted(filename):
fs = Filesplit()
fs.merge(input_dir="cache", cleanup=True)
dec_file = open("cache/" + filename, "rb")
filedata = dec_file.read()
dec_file_copy = open("decryptedFiles/" + filename, "wb")
dec_file_copy.write(filedata)
dec_file.close()
dec_file_copy.close()
return True
def get_model():
"""
Loads model from the filesystem, merging it previously if needed.
"""
model_folder = os.path.join(os.environ['CovidTools'], 'mod_split_model')
model_path = os.path.join(model_folder, 'model.pt')
if not os.path.exists(model_path):
fs = Filesplit()
fs.merge(input_dir=os.path.join(model_folder, 'parts'),
output_file=os.path.join(model_path),
cleanup=False)
return torch.load(model_path)
def _split_file_into_chunks(self, src_file_path: str,
dst_dir_path: str) -> None:
# define helper method that renames file chunks created with FileSplit
def rename_chunk(chunk_path: str):
directory, name, extension = self.split_file_path(chunk_path)
chunk_id = re.match(r'^.*_(?P<id>\d+)$', name).group('id')
new_chunk_path = os.path.join(directory,
f'chunk_{chunk_id}{extension}')
os.rename(chunk_path, new_chunk_path)
return new_chunk_path
# define callback function for FileSplit.split
def note_created_file(file_path: str, file_path_list: list):
self.log.debug(f'Creating file: {file_path}')
file_path_list.append(file_path)
# if source file size is bigger than defined chunk size split it into chunks
if os.path.getsize(src_file_path) > self.chunk_byte_size:
# initialize file paths list
chunk_file_paths = list()
# split file
fs = Filesplit()
fs.split(file=src_file_path,
split_size=self.chunk_byte_size,
output_dir=dst_dir_path,
callback=lambda path, _: note_created_file(
path, chunk_file_paths),
newline=True)
# rename files on file paths list
chunk_file_paths = [
rename_chunk(path) for path in chunk_file_paths
]
# delete manifest file
manifest_file_path = os.path.join(dst_dir_path, 'fs_manifest.csv')
if os.path.exists(manifest_file_path):
os.remove(manifest_file_path)
else:
# copy and rename the source file
_, _, extension = self.split_file_path(src_file_path)
dst_file_path = os.path.join(dst_dir_path, f'chunk_1{extension}')
shutil.copy(src_file_path, dst_file_path)
''' Python Assignment for splitting the file based on size - Submitted by - Shashi Prakash
input format -> python main.py input.csv
input.csv is majestic million csv file, which contains recods over a million for testing purpose'''
import sys
from fsplit.filesplit import Filesplit
fs = Filesplit()
#Callback function to print the split outputs in the terminal
def split_cb(f, s):
print("file: {0}, size: {1}".format(f, s))
#file -> input file name
#split_size -> size of every splits in bytes
#output_dir -> target directory to store the splits.
fs.split(file=sys.argv[1],
split_size=1000000,
output_dir="/home/shashi/Assignmnet/Splits",
callback=split_cb)
import sys
from fsplit.filesplit import Filesplit
fs = Filesplit()
#Callback function to print the split outputs in the terminal
def split_cb(f, s):
print("file: {0}, size: {1}".format(f, s))
#file -> input file name
#split_size -> size of every splits in bytes
#output_dir -> target directory to store the splits.
fs.split(file=sys.argv[1],
split_size=1000000,
output_dir="/home/anamika/Assignment/Splits",
callback=split_cb)
async def chnnlzip(client, message):
pablo = await edit_or_reply(message, "`Fetching All Files From This Channel!`")
rndm = uuid.uuid4().hex
un = get_text(message)
dirz = f"./{rndm}/"
media_count = 0
text_count = 0
os.makedirs(dirz)
if un:
chnnl = un
else:
chnnl = message.chat.id
async for msg in client.search_messages(chnnl):
if msg.sticker:
rndmname = uuid.uuid4().hex
if msg.sticker.mime_type == "application/x-tgsticker":
file_name = os.path.join(dirz + rndmname + ".tgs")
else:
file_name = os.path.join(dirz + rndmname + ".wepb")
try:
await msg.download(file_name=file_name)
except Exception as e:
logging.info(e)
elif msg.media:
media_count += 1
try:
await msg.download(file_name=dirz)
except Exception as e:
logging.info(e)
elif msg.text:
text_count += 1
f = open(os.path.join(dirz + f"{chnnl}.txt"), "a")
f.write(f"[{msg.date}] - {msg.text} \n\n")
total = text_count + media_count
await pablo.edit(
f"**Total Media :** `{total}` \n**Downloaded Media :** `{media_count}` \n**Total Texts Appended :** `{text_count}` \n**Now Zipping Files.**"
)
shutil.make_archive(str(f"{chnnl}_ZippedByFridayUB"), "zip", dirz)
await pablo.edit("`Zipped! Uploading Now!`")
zip_name = f"{chnnl}_ZippedByFridayUB.zip"
siz_e = os.stat(zip_name).st_size
list_ = []
if siz_e > 2040108421:
await pablo.edit(
"`File Over 2GB, Telegram Doesn't Allow This. Trying To Split Files!`"
)
fs = Filesplit()
if not os.path.exists(f"./splitted_{chnnl}_{rndm}"):
os.makedirs(f"./splitted_{chnnl}_{rndm}")
fs.split(
file=zip_name,
split_size=2040108421,
output_dir=f"./splitted_{chnnl}_{rndm}",
)
file_list(f"./splitted_{chnnl}_{rndm}", list_)
for oof in list_:
if oof == "fs_manifest.csv":
return
await client.send_document(
message.chat.id,
oof,
caption=f"**Total :** `{total}` \n**Total Media :** `{media_count}` \n**Total Text :** `{text_count}`",
)
shutil.rmtree(dirz)
shutil.rmtree(f"./splitted_{chnnl}_{rndm}")
if os.path.exists(zip_name):
os.remove(zip_name)
await pablo.delete()
return
await client.send_document(
message.chat.id,
zip_name,
caption=f"**Total :** `{total}` \n**Total Media :** `{media_count}` \n**Total Text :** `{text_count}`",
)
os.remove(zip_name)
shutil.rmtree(dirz)
await pablo.delete()
async def chnnlzip(client, message):
engine = message.Engine
pablo = await edit_or_reply(message, engine.get_string("FILE_TOOLS_1"))
rndm = uuid.uuid4().hex
un = get_text(message)
dirz = f"./{rndm}/"
media_count = 0
text_count = 0
os.makedirs(dirz)
if un:
chnnl = un
else:
chnnl = message.chat.id
async for msg in client.iter_history(chnnl):
if msg.sticker:
rndmname = uuid.uuid4().hex
if msg.sticker.mime_type == "application/x-tgsticker":
file_name = os.path.join(dirz + rndmname + ".tgs")
else:
file_name = os.path.join(dirz + rndmname + ".wepb")
try:
await msg.download(file_name=file_name)
except Exception as e:
logging.info(e)
elif msg.media:
media_count += 1
try:
await msg.download(file_name=dirz)
except Exception as e:
logging.info(e)
elif msg.text:
text_count += 1
f = open(os.path.join(dirz + f"{chnnl}.txt"), "a")
f.write(f"[{msg.date}] - {msg.text} \n\n")
total = text_count + media_count
await pablo.edit(
engine.get_string("FILE_TOOLS_2").format(total, media_count,
text_count))
shutil.make_archive(str(f"{chnnl}_ZippedByFridayUB"), "zip", dirz)
await pablo.edit("`Zipped! Uploading Now!`")
zip_name = f"{chnnl}_ZippedByFridayUB.zip"
siz_e = os.stat(zip_name).st_size
list_ = []
if siz_e > 2040108421:
await pablo.edit(engine.get_string("FILE_TOOLS_3"))
fs = Filesplit()
if not os.path.exists(f"./splitted_{chnnl}_{rndm}"):
os.makedirs(f"./splitted_{chnnl}_{rndm}")
fs.split(
file=zip_name,
split_size=2040108421,
output_dir=f"./splitted_{chnnl}_{rndm}",
)
file_list(f"./splitted_{chnnl}_{rndm}", list_)
for oof in list_:
if oof == "fs_manifest.csv":
return
await client.send_document(
message.chat.id,
oof,
caption=
f"**Total :** `{total}` \n**Total Media :** `{media_count}` \n**Total Text :** `{text_count}`",
)
shutil.rmtree(dirz)
shutil.rmtree(f"./splitted_{chnnl}_{rndm}")
if os.path.exists(zip_name):
os.remove(zip_name)
await pablo.delete()
return
await client.send_document(
message.chat.id,
zip_name,
caption=
f"**Total :** `{total}` \n**Total Media :** `{media_count}` \n**Total Text :** `{text_count}`",
)
os.remove(zip_name)
shutil.rmtree(dirz)
await pablo.delete()
from mega import Mega # importing
import glob, os
from fsplit.filesplit import Filesplit
fs = Filesplit()
inp1=int(input("Enter the split size in KB: "))
fs.split(file="./output/data.file", split_size=inp1*1000, output_dir="./output/divided")
os.remove("./output/data.file")
print("Files are divided, Please check output/divided folder")
mega = Mega() # creating instance of mega
print("\nPlease wait, logging in .....")
m = mega.login("email", "password") #email id and passwor of www.mega.nz
print("login done !! ")
filename=[]
os.chdir("./output/divided")
for file in glob.glob("*.file"):
filename.append(file)
print("No. of division created:",len(filename))
print("Uploading file in progress ....")
for i in range(len(filename)):
file_upload=filename[i]
file = m.upload(file_upload)
ap.add_argument("-o", "--file", required=True, help="Output file name")
ap.add_argument("-l", "--log", required=False, help="When set to True, execution log is written to log_split.txt")
ap.add_argument("-c", "--clean", required=False, help="Removes split files after merging them")
args = vars(ap.parse_args())
def merge_cb(f, s):
print("file: {0}, size: {1}".format(f, s))
if(bool(args['log'])):
fo = open(args['input_dir']+"\log_merge.txt","a")
fo.write("file: {0}, size: {1}\n".format(f, s))
fo.close()
try:
args['input_dir'] = args['input_dir'].replace("\\","/")
args['file'] = args['input_dir'] + "/" + args['file']
if(os.path.isdir(args['input_dir'])):
if(len(os.listdir(args['input_dir']))==0):
raise ValueError("Input directory should not be empty! Exiting...")
else:
raise ValueError("Input directory path is invalid")
fs = Filesplit()
fs.merge(input_dir=args['input_dir'], output_file=args['file'], callback=merge_cb, cleanup=bool(args['clean']))
print("Merging sucessfully completed!")
except ValueError as ve:
print(ve)
except Exception as e:
print("Oops!", e.__class__, "occurred.")
args['output_dir'] = args['output_dir'].replace("\\", "/")
args['file'] = args['file'].replace("\\", "/")
try:
if (os.path.isdir(args['output_dir'])):
if (bool(args['force'])):
delete_files()
if (len(os.listdir(args['output_dir'])) != 0):
raise ValueError("Output directory should be empty! Exiting...")
else:
os.mkdir(args['output_dir'])
if not os.path.isfile(args['file']):
raise ValueError("Input file path is invalid")
fs = Filesplit()
fs.split(file=args['file'],
split_size=int(args['split_size']),
output_dir=args['output_dir'],
callback=split_cb,
new_line=bool(args['newline']),
include_header=bool(args['header']))
print("Splitting sucessfully completed!")
except ValueError as ve:
print(ve)
except Exception as e:
print("Oops!", e.__class__, "occurred.")
tk.Tk().withdraw()
p = filedialog.askopenfilename(
title='Choose the file location')
message = open(p, "rb").read()
print(p)
encryption.encrypting_file(message, key, p)
p = "../"
os.chdir(p)
print(os.getcwd())
os.system("python megaauth.py")
break
else:
break
elif main_input == 2:
fs = Filesplit()
folder_selected = filedialog.askdirectory(
title='Choose the directory file location')
fs.merge(input_dir=folder_selected)
os.chdir(folder_selected)
os.remove("./fs_manifest.csv")
filename = []
#os.chdir("./output/divided")
for file in glob.glob("*.file"):
filename.append(file)
for i in range(len(filename) - 1):
os.remove(filename[i + 1])
decrypt.decryption()
fluid.install_check.run_check()
# --------------------- 请你不要改 start-----------------------------
# 项目的base目录
BASE_DIR = str(Path(os.path.abspath(__file__)).parent)
# 模型文件目录
# 文本检测模型
DET_MODEL_PATH = os.path.join(BASE_DIR, 'backend', 'models', 'ch_det')
# 文本识别模型
REC_MODEL_PATH = os.path.join(BASE_DIR, 'backend', 'models', 'ch_rec')
# 查看该路径下是否有文本模型识别完整文件，没有的话合并小文件生成完整文件
if 'inference.pdiparams' not in (os.listdir(REC_MODEL_PATH)):
fs = Filesplit()
fs.merge(input_dir=REC_MODEL_PATH)
# 字典路径
DICT_PATH = os.path.join(BASE_DIR, 'backend', 'ppocr', 'utils',
'ppocr_keys_v1.txt')
# 默认字幕出现的大致区域
class SubtitleArea(Enum):
# 字幕区域出现在下半部分
LOWER_PART = 0
# 字幕区域出现在上半部分
UPPER_PART = 1
# 不知道字幕区域可能出现的位置
UNKNOWN = 2
from fsplit.filesplit import Filesplit fs = Filesplit() fs.split(file='SampleMP3.mp3', split_size=50000, output_dir='.')
# Author: Mandeep Singh # Location: Moon # Date: 23/09/2023 import os #import flask from fsplit.filesplit import Filesplit fs = Filesplit() print(os.listdir()) #Print the contents of the directory using os module. #os.listdir()) is a external module Print the contents of the directory using os module.
! pip install filesplit
from fsplit.filesplit import Filesplit
fs = Filesplit()
filedir=input("Enter the complete file path")
outdir=input("Enter the complete path of the directory where you want to store the output files")
choice=int(input("Do you want to split the file in \n 1.KB's \n 2.MB's \n 3.GB's \n"))
if(choice == 1):
x=int(input("Enter the split size for KB split"))
x=x*1024
elif(choice == 2):
x=int(input("Enter the split size for MB split"))
x=x*1024*1024
elif(choice == 3):
x=int(input("Enter the split size for GB split"))
x=x*1024*1024*1024
else:
print("Wrong Input")
f_size=x
print(f_size)
def split_cb(f, s):
print("file: {0}, size: {1}".format(f, s))
fs.split(file=filedir, split_size=f_size, output_dir=outdir, callback=split_cb)
# dictionary dumped as json in a json file
with open('students.csv', 'w') as fp:
json.dump(student_data, fp)
def main():
number_of_students = 10000
input_data(number_of_students)
main()
from fsplit.filesplit import Filesplit
fs = Filesplit()
def split_cb(f, s):
print("file: {0}, size: {1}".format(f, s))
fs.split(file="students.xml",
split_size=2000000,
output_dir="Downloads/CSVfile",
callback=split_cb)
from fsplit.filesplit import Filesplit
fs = Filesplit()
