Develop Reference

Monitoring Folders - Python

I am trying to write a python script which will monitor folders. The files are being written into the folder from a third party GUI based program. Some exported files grow in situ and other are written in a tmp folder elsewhere before being copied into the target folder. In the tmp folder cases, an empty folder is placed at the target destination until the file is ready to move. There may be multiples of these empty folders, but they are only created after the previous one has been populated.
The below appears to work well until there are Zero size files/folders.
I think the main issue lies in zero_files. Providing the rest for context.
import os
import datetime
import time
import itertools
print('Starting to Monitor File growth')
print(datetime.datetime.now())
print("")
path = os.path.normpath(r'C:\Users\ed\Desktop\Test_Run')
check_rate = 180
#time in seconds between checks
print("Waiting for a moment before starting monitoring")
print("")
time.sleep(60)
#wait for the first files to appear
def get_directory_size(directory):
"""Returns the `directory` size in bytes."""
total = 0
try:
# print("[+] Getting the size of", directory)
for entry in os.scandir(directory):
if entry.is_file():
# if it's a file, use stat() function
total += entry.stat().st_size
elif entry.is_dir():
# if it's a directory, recursively call this function
try:
total += get_directory_size(entry.path)
except FileNotFoundError:
pass
except NotADirectoryError:
# if `directory` isn't a directory, get the file size then
return os.path.getsize(directory)
except PermissionError:
# if for whatever reason we can't open the folder, return 0
return 0
return total
def folder_growing(path):
sizes = [1,2]
while sizes[-1] > sizes[-2]:
time.sleep(check_rate)
sizes.append(get_directory_size(path))
print('Monitoring Folder')
def zero_files(path):
files = os.listdir(path)
a= []
for i in files:
file_size = a.append(os.path.getsize(f'{path}\\{i}'))
a.sort()
try:
while a[-1] == 0:
file_size = a.append(os.path.getsize(f'{path}\\{i}'))
a.sort()
print("test")
time.sleep(120)
except FileNotFoundError:
pass
print(f"***Checking folders every", (int(check_rate/60)),"mins***")
get_directory_size(path)
folder_growing(path)
time.sleep(120)
zero_files(path)
wait = 10
print('No Folder Growth Detected')
print("")
print(f"***Waiting ", (int(wait/60)),"mins for Safety***")
time.sleep(wait)
print("")
print(datetime.datetime.now())
print("Done")

Python multiprocessing - sharing large dataset

I'm trying to speed up a CPU-bound Python script (on Windows11). Threats in Python do not seem to run on a different cpu(core) so the only option I have is multiprocessing.
I have a big dictionary data structure (11GB memory footprint after loading from file) that I am checking calculated values on if they are in that dictionary. Input for the calculation also comes from a file (100GB in size). This input I can pool-map to the processes in batches, no problem. But I cannot copy the dictionary to all processes because there is not enough memory for that. So I need to find a way for the processes to check if the value (actually a string) is in the dictionary.
Any advice?
Pseudo programm flow:
--main--
- load dictionary structure from file # 11GB memory footprint
- ...
- While not all chuncks loaded
- Load chunk of calcdata from file # (10.000 lines per chunk)
- Distribute (map) calcdata-chunck to processes
- Wait for processes to complete all chunks
--process--
- for each element in subchunk
- perform calculation
- check if calculation in dictionary # here is my problem!
- store result in file
Edit, after implementing comments below, I am now at:
def ReadDictFromFile()
cnt=0
print("Reading dictionary from " + dictfilename)
with open(dictfilename, encoding=("utf-8"), errors=("replace")) as f:
next(f) #skip first line (header)
for line in f:
s = line.rstrip("\n")
(key,keyvalue) = s.split()
shared_dict[str(key)]=keyvalue
cnt = cnt + 1
if ((cnt % 1000000) == 0): #log each 1000000 where we are
print(cnt)
return #temp to speed up testing, not load whole dictionary atm
print("Done loading dictionary")
def checkqlist(qlist)
print(str(os.getpid()) + "-" + str(len(qlist)))
for li in qlist:
try:
checkvalue = calculations(li)
(found, keyval) = InMem(checkvalue)
if (found):
print("FOUND!!! " + checkvalue + ' ' + keyvalue)
except Exception as e:
print("(" + str(os.getpid()) + ")Error log: %s" % repr(e))
time.sleep(15)
def InMem(checkvalue):
if(checkvalue in shared_dict):
return True, shared_dict[checkvalue]
else:
return False, ""
if __name__ == "__main__":
start_time = time.time()
global shared_dict
manager = Manager()
shared_dict = manager.dict()
ReadDictFromFile()
chunksize=5
nr_of_processes = 10
with open(filetocheck, encoding=("utf-8"), errors=("replace")) as f:
qlist = []
for line in f:
s = line.rstrip("\n")
qlist.append(s)
if (len(qlist) >= (chunksize * nr_of_processes)):
chunked_list = [qlist[i:i+chunk_size] for i in range(0, len(qlist), chunk_size)]
try:
with multiprocessing.Pool() as pool:
pool.map(checkqlist, chunked_list, nr_of_processes) #problem: qlist is a single string, not a list of about 416 strings.
except Exception as e:
print("error log: %s" % repr(e))
time.sleep(15)
logit("Completed! " + datetime.datetime.now().strftime("%I:%M%p on %B %d, %Y"))
print("--- %s seconds ---" % (time.time() - start_time))

you can use a multiprocessing.Manager.dict for this, it's the fastest IPC you can use to do the check between processes in python, and for the memory size, just make it smaller by changing all values to None, on my pc it can do 33k member checks every second ... about 400 times slower than a normal dictionary.
manager = Manager()
shared_dict = manager.dict()
shared_dict.update({x:None for x in main_dictionary})
shared_dict["new_element"] = None # to set another value
del shared_dict["new_element"] # to delete a certain value
you can also use a dedicated in-memory database for this like redis, which can handle being polled by multiple processes at the same time.
#Sam Mason suggestion to use WSL and fork may be better, but this one is the most portable.
Edit: to store it in children global scope you have to pass it through the initializer.
def define_global(var):
global shared_dict
shared_dict = var
...
if __name__ == "__main__":
...
with multiprocessing.Pool(initializer=define_global, initargs=(shared_dict ,)) as pool:

Updating Appending List to a txt file

Hello currently i am studying python and i wanted to know on how you can have a list that is being appended if there is a change constantly to a txtfile. Wording is a hard here is the code anyways
list=[]
random_number=0
file_handler=open("history.txt","w")
file_handler.write(str(list))
lenght_cumulative_data=len(list)
confirmed.append(random_number)
Now what i want to accomplish is that the list variable of the number 0 would be shown in history.txt but that doesnt happen and lets just imagine that random_number is always changing I want the list variable to be able to always update itself. Like if let say random_number changes to 1 and then 2 I want list to be updated to [0,1,2]. How do you do that? I've been searching on youtube and all they gave me is this write function is there anyway someone could refrence it or have any ideas?

from os import stat
from _thread import start_new_thread
from time import sleep
List = []
class WatchFileForChanges:
def __init__(self, filename):
self.file = filename
self.cached_file = stat(self.file).st_mtime
def watch(self):
num = 0
while 1:
status = stat(self.file).st_mtime
if status != self.cached_file:
self.cached_file = status
#file changed
List.append(num)
num += 1
def main():
Watcher = WatchFileForChanges("file.txt")
start_new_thread(Watcher.watch, ())
while 1:
print(List)
sleep(1)
if __name__ == '__main__':
main()
This will do what you want.
If I understood you correctly, you want to append to the list every time a file changes.

Note: this answer will only work on Windows
changes.py:
# Adapted from http://timgolden.me.uk/python/win32_how_do_i/watch_directory_for_changes.html
import threading
import os
import win32file
import win32con
ACTIONS = {
1 : "Created",
2 : "Deleted",
3 : "Updated",
4 : "Renamed from something",
5 : "Renamed to something"
}
# Thanks to Claudio Grondi for the correct set of numbers
FILE_LIST_DIRECTORY = 0x0001
def monitor_changes(callback, path, filenames):
path = path or ""
if type(filenames) == "str":
filenames = (filenames,)
thread = threading.Thread(target=_monitor, args=(callback, path, filenames))
thread.start()
return thread
def _monitor(callback, path, filenames):
hDir = win32file.CreateFile (
path,
FILE_LIST_DIRECTORY,
win32con.FILE_SHARE_READ | win32con.FILE_SHARE_WRITE | win32con.FILE_SHARE_DELETE,
None,
win32con.OPEN_EXISTING,
win32con.FILE_FLAG_BACKUP_SEMANTICS,
None
)
while True:
#
# ReadDirectoryChangesW takes a previously-created
# handle to a directory, a buffer size for results,
# a flag to indicate whether to watch subtrees and
# a filter of what changes to notify.
#
# NB Tim Juchcinski reports that he needed to up
# the buffer size to be sure of picking up all
# events when a large number of files were
# deleted at once.
#
results = win32file.ReadDirectoryChangesW (
hDir,
1024,
True,
win32con.FILE_NOTIFY_CHANGE_LAST_WRITE,
None,
None
)
for action, file in results:
if filenames and file not in filenames and os.path.basename(file) not in filenames:
continue
callback(action, file)
if __name__ == '__main__':
# monitor by printing
t = monitor_changes(print, ".", None)
And in your main.py:
import changes
import os
my_list = []
def callback(action_id, filename):
# the function running means
# that the file has been modified
action_desc = changes.ACTIONS[action_id]
print(action_desc, filename)
with open(filename) as f:
my_list.append(f.read())
thread = changes.monitor_changes(callback, ".", "my_file_that_I_want_to_monitor.txt")
If you want to monitor all files in the directory, call monitor_changes with None as the third argument.
Note: this will monitor all subdirectories, so files with the same name but in different folders will trigger the callback. If you want to avoid this, then check the filename passed to your callback function is exactly what you want to monitor.

Python script use while loop to keep updating job scripts and multiprocess the tasks in queue

I am trying to write a python script scanning a folder and collect updated SQL script, and then automatically pull data for the SQL script. In the code, a while loop is scanning new SQL file, and send to data pull function. I am having trouble to understand how to make a dynamic queue with while loop, but also have multiprocess to run the tasks in the queue.
The following code has a problem that the while loop iteration will work on a long job before it moves to next iteration and collects other jobs to fill the vacant processor.
Update:
Thanks to #pbacterio for catching the bug, and now the error message is gone. After changing the code, the python code can take all the job scripts during one iteration, and distribute the scripts to four processors. However, it will get hang by a long job to go to next iteration, scanning and submitting the newly added job scripts. Any idea how to reconstruct the code?
I finally figured out the solution see answer below. It turned out what I was looking for is
the_queue = Queue()
the_pool = Pool(4, worker_main,(the_queue,))
For those stumble on the similar idea, following is the whole architecture of this automation script converting a shared drive to a 'server for SQL pulling' or any other job queue 'server'.
a. The python script auto_data_pull.py as shown in the answer. You need to add your own job function.
b. A 'batch script' with following:
start C:\Anaconda2\python.exe C:\Users\bin\auto_data_pull.py
c. Add a task triggered by start computer, run the 'batch script'
That's all. It works.
Python Code:
from glob import glob
import os, time
import sys
import CSV
import re
import subprocess
import pandas as PD
import pypyodbc
from multiprocessing import Process, Queue, current_process, freeze_support
#
# Function run by worker processes
#
def worker(input, output):
for func, args in iter(input.get, 'STOP'):
result = compute(func, args)
output.put(result)
#
# Function used to compute result
#
def compute(func, args):
result = func(args)
return '%s says that %s%s = %s' % \
(current_process().name, func.__name__, args, result)
def query_sql(sql_file): #test func
#jsl file processing and SQL querying, data table will be saved to csv.
fo_name = os.path.splitext(sql_file)[0] + '.csv'
fo = open(fo_name, 'w')
print sql_file
fo.write("sql_file {0} is done\n".format(sql_file))
return "Query is done for \n".format(sql_file)
def check_files(path):
"""
arguments -- root path to monitor
returns -- dictionary of {file: timestamp, ...}
"""
sql_query_dirs = glob(path + "/*/IDABox/")
files_dict = {}
for sql_query_dir in sql_query_dirs:
for root, dirs, filenames in os.walk(sql_query_dir):
[files_dict.update({(root + filename): os.path.getmtime(root + filename)}) for
filename in filenames if filename.endswith('.jsl')]
return files_dict
##### working in single thread
def single_thread():
path = "Y:/"
before = check_files(path)
sql_queue = []
while True:
time.sleep(3)
after = check_files(path)
added = [f for f in after if not f in before]
deleted = [f for f in before if not f in after]
overlapped = list(set(list(after)) & set(list(before)))
updated = [f for f in overlapped if before[f] < after[f]]
before = after
sql_queue = added + updated
# print sql_queue
for sql_file in sql_queue:
try:
query_sql(sql_file)
except:
pass
##### not working in queue
def multiple_thread():
NUMBER_OF_PROCESSES = 4
path = "Y:/"
sql_queue = []
before = check_files(path) # get the current dictionary of sql_files
task_queue = Queue()
done_queue = Queue()
while True: #while loop to check the changes of the files
time.sleep(5)
after = check_files(path)
added = [f for f in after if not f in before]
deleted = [f for f in before if not f in after]
overlapped = list(set(list(after)) & set(list(before)))
updated = [f for f in overlapped if before[f] < after[f]]
before = after
sql_queue = added + updated
TASKS = [(query_sql, sql_file) for sql_file in sql_queue]
# Create queues
#submit task
for task in TASKS:
task_queue.put(task)
for i in range(NUMBER_OF_PROCESSES):
p = Process(target=worker, args=(task_queue, done_queue)).start()
# try:
# p = Process(target=worker, args=(task_queue))
# p.start()
# except:
# pass
# Get and print results
print 'Unordered results:'
for i in range(len(TASKS)):
print '\t', done_queue.get()
# Tell child processes to stop
for i in range(NUMBER_OF_PROCESSES):
task_queue.put('STOP')
# single_thread()
if __name__ == '__main__':
# freeze_support()
multiple_thread()
Reference:
monitor file changes with python script: http://timgolden.me.uk/python/win32_how_do_i/watch_directory_for_changes.html
Multiprocessing:
https://docs.python.org/2/library/multiprocessing.html

Where did you define sql_file in multiple_thread() in
multiprocessing.Process(target=query_sql, args=(sql_file)).start()
You have not defined sql_file in the method and moreover you have used that variable in a for loop. The variable's scope is only confined to the for loop.

Try replacing this:
result = func(*args)
by this:
result = func(args)

I have figured this out. Thank your for the response inspired the thought.
Now the script can run a while loop to monitor the folder for new updated/added SQL script, and then distribute the data pulling to multiple threads. The solution comes from the queue.get(), and queue.put(). I assume the queue object takes care of the communication by itself.
This is the final code --
from glob import glob
import os, time
import sys
import pypyodbc
from multiprocessing import Process, Queue, Event, Pool, current_process, freeze_support
def query_sql(sql_file): #test func
#jsl file processing and SQL querying, data table will be saved to csv.
fo_name = os.path.splitext(sql_file)[0] + '.csv'
fo = open(fo_name, 'w')
print sql_file
fo.write("sql_file {0} is done\n".format(sql_file))
return "Query is done for \n".format(sql_file)
def check_files(path):
"""
arguments -- root path to monitor
returns -- dictionary of {file: timestamp, ...}
"""
sql_query_dirs = glob(path + "/*/IDABox/")
files_dict = {}
try:
for sql_query_dir in sql_query_dirs:
for root, dirs, filenames in os.walk(sql_query_dir):
[files_dict.update({(root + filename): os.path.getmtime(root + filename)}) for
filename in filenames if filename.endswith('.jsl')]
except:
pass
return files_dict
def worker_main(queue):
print os.getpid(),"working"
while True:
item = queue.get(True)
query_sql(item)
def main():
the_queue = Queue()
the_pool = Pool(4, worker_main,(the_queue,))
path = "Y:/"
before = check_files(path) # get the current dictionary of sql_files
while True: #while loop to check the changes of the files
time.sleep(5)
sql_queue = []
after = check_files(path)
added = [f for f in after if not f in before]
deleted = [f for f in before if not f in after]
overlapped = list(set(list(after)) & set(list(before)))
updated = [f for f in overlapped if before[f] < after[f]]
before = after
sql_queue = added + updated
if sql_queue:
for jsl_file in sql_queue:
try:
the_queue.put(jsl_file)
except:
print "{0} failed with error {1}. \n".format(jsl_file, str(sys.exc_info()[0]))
pass
else:
pass
if __name__ == "__main__":
main()

Successive multiprocessing

I am filtering huge text files using multiprocessing.py. The code basically opens the text files, works on it, then closes it.
Thing is, I'd like to be able to launch it successively on multiple text files. Hence, I tried to add a loop, but for some reason it doesn't work (while the code works on each file). I believe this is an issue with:
if __name__ == '__main__':
However, I am looking for something else. I tried to create a Launcher and a LauncherCount files like this:
LauncherCount.py:
def setLauncherCount(n):
global LauncherCount
LauncherCount = n
and,
Launcher.py:
import os
import LauncherCount
LauncherCount.setLauncherCount(0)
os.system("OrientedFilterNoLoop.py")
LauncherCount.setLauncherCount(1)
os.system("OrientedFilterNoLoop.py")
...
I import LauncherCount.py, and use LauncherCount.LauncherCount as my loop index.
Of course, this doesn't work too as it edits the variable LauncherCount.LauncherCount locally, so it won't be edited in the imported version of LauncherCount.
Is there any way to edit globally a variable in an imported file? Or, is there any way to do this in any other way? What I need is running a code multiple times, in changing one value, and without using any loop apparently.
Thanks!
Edit: Here is my main code if necessary. Sorry for the bad style ...
import multiprocessing
import config
import time
import LauncherCount
class Filter:
""" Filtering methods """
def __init__(self):
print("launching methods")
# Return the list: [Latitude,Longitude] (elements are floating point numbers)
def LatLong(self,line):
comaCount = []
comaCount.append(line.find(','))
comaCount.append(line.find(',',comaCount[0] + 1))
comaCount.append(line.find(',',comaCount[1] + 1))
Lat = line[comaCount[0] + 1 : comaCount[1]]
Long = line[comaCount[1] + 1 : comaCount[2]]
try:
return [float(Lat) , float(Long)]
except ValueError:
return [0,0]
# Return a boolean:
# - True if the Lat/Long is within the Lat/Long rectangle defined by:
# tupleFilter = (minLat,maxLat,minLong,maxLong)
# - False if not
def LatLongFilter(self,LatLongList , tupleFilter) :
if tupleFilter[0] <= LatLongList[0] <= tupleFilter[1] and
tupleFilter[2] <= LatLongList[1] <= tupleFilter[3]:
return True
else:
return False
def writeLine(self,key,line):
filterDico[key][1].write(line)
def filteringProcess(dico):
myFilter = Filter()
while True:
try:
currentLine = readFile.readline()
except ValueError:
break
if len(currentLine) ==0: # Breaks at the end of the file
break
if len(currentLine) < 35: # Deletes wrong lines (too short)
continue
LatLongList = myFilter.LatLong(currentLine)
for key in dico:
if myFilter.LatLongFilter(LatLongList,dico[key][0]):
myFilter.writeLine(key,currentLine)
###########################################################################
# Main
###########################################################################
# Open read files:
readFile = open(config.readFileList[LauncherCount.LauncherCount][1], 'r')
# Generate writing files:
pathDico = {}
filterDico = config.filterDico
# Create outputs
for key in filterDico:
output_Name = config.readFileList[LauncherCount.LauncherCount][0][:-4]
+ '_' + key +'.log'
pathDico[output_Name] = config.writingFolder + output_Name
filterDico[key] = [filterDico[key],open(pathDico[output_Name],'w')]
p = []
CPUCount = multiprocessing.cpu_count()
CPURange = range(CPUCount)
startingTime = time.localtime()
if __name__ == '__main__':
### Create and start processes:
for i in CPURange:
p.append(multiprocessing.Process(target = filteringProcess ,
args = (filterDico,)))
p[i].start()
### Kill processes:
while True:
if [p[i].is_alive() for i in CPURange] == [False for i in CPURange]:
readFile.close()
for key in config.filterDico:
config.filterDico[key][1].close()
print(key,"is Done!")
endTime = time.localtime()
break
print("Process started at:",startingTime)
print("And ended at:",endTime)

To process groups of files in sequence while working on files within a group in parallel:
#!/usr/bin/env python
from multiprocessing import Pool
def work_on(args):
"""Process a single file."""
i, filename = args
print("working on %s" % (filename,))
return i
def files():
"""Generate input filenames to work on."""
#NOTE: you could read the file list from a file, get it using glob.glob, etc
yield "inputfile1"
yield "inputfile2"
def process_files(pool, filenames):
"""Process filenames using pool of processes.
Wait for results.
"""
for result in pool.imap_unordered(work_on, enumerate(filenames)):
#NOTE: in general the files won't be processed in the original order
print(result)
def main():
p = Pool()
# to do "successive" multiprocessing
for filenames in [files(), ['other', 'bunch', 'of', 'files']]:
process_files(p, filenames)
if __name__=="__main__":
main()
Each process_file() is called in sequence after the previous one has been complete i.e., the files from different calls to process_files() are not processed in parallel.