Creating intermittent process in python

Question

I am creating a python script that parses a large (but simple) CSV.

It will take some time to process. I would like to interrupt the CSV parsing so that I can continue at a later stage.

I currently have this - of which lives in a larger class: (unfinished)

Edit:

I have a modified code. But the system will analyze more than 3 million lines.

def parseData(self)
    reader = csv.reader(open(self.file))
    for id, title, disc in reader:
        print "%-5s %-50s %s" % (id, title, disc)
        l = LegacyData()
        l.old_id = int(id)
        l.name = title
        l.disc_number = disc
        l.parsed = False
        l.save()

---

This is old code.

def parseData(self):
        #first line start
        fields = self.data.next()
        for row in self.data:
            items = zip(fields, row)
            item = {}
            for (name, value) in items:
                item[name] = value.strip()
            self.save(item)

Thanks guys.

Answer 1

If under linux, press Ctrl-Z and stop the current process. Type "fg" to get it back and start where you left it.

Answer 2

signal, . , CTRL-C :

import signal, tme, sys

def onInterupt(signum, frame):
    raise Interupted()

try:
    #windows
    signal.signal(signal.CTRL_C_EVENT, onInterupt)
except:
    pass

class Interupted(Exception): pass
class InteruptableParser(object):

    def __init__(self, previous_parsed_lines=0):
        self.parsed_lines = previous_parsed_lines

    def _parse(self, line):
        # do stuff
        time.sleep(1) #mock up
        self.parsed_lines += 1
        print 'parsed %d' % self.parsed_lines

   def parse(self, filelike):
        for line in filelike:
            try:
                self._parse(line)
            except Interupted:
                print 'caught interupt'
                self.save()
                print 'exiting ...'
                sys.exit(0)

    def save(self):
        # do what you need to save state
        # like write the parse_lines to a file maybe
        pass

parser = InteruptableParser()
parser.parse([1,2,3])

, Linux.

Answer 3

:

, Pickle (http://docs.python.org/library/pickle.html) ( , __getstate__ __setstate__)

, CSV . __getstate__ , setstate , .

__iter__, .

" " (, , ..) - , , . , .

, , , pickle - .

() - iea :

from cPickle import load, dump
import csv
import os, sys

SAVEFILE = "running.pkl"
STOPNOWFILE = "stop.now"

class Processor(object):
    def __init__(self, filename):
        self.file = open(filename, "rt")
        self.reader = csv.reader(self.file)
    def __iter__(self):
        for line in self.reader():
            # do stuff
            yield None
    def __getstate__(self):
        return (self.file.name, self.file.tell())
    def __setstate__(self, state):
        self.file = open(state[0],"rt")
        self.file.seek(state[1])
        self.reader = csv.reader(self.File)

def check_for_interrupts():
    # Use your imagination here!  
    # One simple thing would e to check for the existence of an specific file
    # on disk.
    # But you go all the way up to instantiate a tcp server and listen to 
    # interruptions on the network
    if os.path.exists(STOPNOWFILE): 
        return True
    return False

def main():
    if os.path.exists(SAVEFILE):
        with open(SAVEFILE) as savefile:
            processor = load(savefile)
        os.unlink(savefile)
    else:
        #Assumes the name of the .csv file to be passed on the command line
        processor = Processor(sys.argv[1])
    for line in processor:
        if check_for_interrupts():
            with open(SAVEFILE, "wb") as savefile:
                dump(processor)
            break

if __name__ == "__main__":
    main()

Answer 4

@jsbueno - :

- , , , . - , , . , . process , , , , .

class MultithreadParsing(object):

    process = None
    process_flag = True

    def f(self):
        print "\nMultithreadParsing has started\n"
        while self.process_flag:
            ''' get my object from database '''
            legacy = LegacyData.objects.filter(parsed=False)[0:1]

            if legacy:
                print "Processing: %s %s" % (legacy[0].name, legacy[0].disc_number)
                for l in legacy:
                    ''' ... Do what I want it to do ...'''
                sleep(1)
            else:
                self.process_flag = False
                print "Nothing to parse"



    def __init__(self):
        self.process = Process(target=self.f)
        self.process.start()
        print self.process
        a = raw_input("Press any key to stop \n")
        print "\nKILL FLAG HAS BEEN SENT\n"

        if a:
            print "\nKILL\n"
            self.process_flag = False

, ( @jsbueno) - , .