问处理来自多个进程的单个文件

EN

import os.path
import multiprocessing

def newlinebefore(f,n):
    f.seek(n)
    c=f.read(1)
    while c!='\n' and n > 0:
        n-=1
        f.seek(n)
        c=f.read(1)

    f.seek(n)
    return n

filename='gpdata.dat'  #your filename goes here.
fsize=os.path.getsize(filename) #size of file (in bytes)

#break the file into 20 chunks for processing.
nchunks=20
initial_chunks=range(1,fsize,fsize/nchunks)

#You could also do something like:
#initial_chunks=range(1,fsize,max_chunk_size_in_bytes) #this should work too.


with open(filename,'r') as f:
    start_byte=sorted(set([newlinebefore(f,i) for i in initial_chunks]))

end_byte=[i-1 for i in start_byte] [1:] + [None]

def process_piece(filename,start,end):
    with open(filename,'r') as f:
        f.seek(start+1)
        if(end is None):
            text=f.read()
        else: 
            nbytes=end-start+1
            text=f.read(nbytes)

    # process text here. createing some object to be returned
    # You could wrap text into a StringIO object if you want to be able to
    # read from it the way you would a file.

    returnobj=text
    return returnobj

def wrapper(args):
    return process_piece(*args)

filename_repeated=[filename]*len(start_byte)
args=zip(filename_repeated,start_byte,end_byte)

pool=multiprocessing.Pool(4)
result=pool.map(wrapper,args)

#Now take your results and write them to the database.
print "".join(result)  #I just print it to make sure I get my file back ...