Friday, September 25, 2015

Reading large GZIP files with Python

Thanks to
Spencer Rathbun

Here Sepencer's way to read, large files with Python, amazingly I have adopted nearly, the same strategy for one of my scripts at work...thanks to Dave Beazley for its fantastic  job on genrators in Python

#!/usr/bin/env python
import gzip, bz2
import os
import fnmatch

def gen_find(filepat,top):
    for path, dirlist, filelist in os.walk(top):
        for name in fnmatch.filter(filelist,filepat):
            yield os.path.join(path,name)

def gen_open(filenames):
    for name in filenames:
        if name.endswith(".gz"):
        elif name.endswith(".bz2"):
            yield bz2.BZ2File(name)
            yield open(name)

def gen_cat(sources):
    for s in sources:
        for item in s:
            yield item

def main(regex, searchDir):
    fileNames = gen_find(regex,searchDir)
    fileHandles = gen_open(fileNames)
    fileLines = gen_cat(fileHandles)
    for line in fileLines:
        print line

if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='Search globbed files line by line', version='%(prog)s 1.0')
    parser.add_argument('regex', type=str, default='*', help='Regular expression')
    parser.add_argument('searchDir', , type=str, default='.', help='list of input files')
    args = parser.parse_args()
    main(args.regex, args.searchDir)