# -*- coding:Utf-8 -*-
#
# LineCount003.py
#
# Source :
#
# http://stackoverflow.com/questions/845058/how-to-get-line-count-cheaply-in-python
#

from __future__ import with_statement
import time
import mmap
import random
from collections import defaultdict
from itertools import (takewhile,repeat)

def mapcount(filename):
    f = open(filename, "r+")
    buf = mmap.mmap(f.fileno(), 0)
    lines = 0
    readline = buf.readline
    while readline():
        lines += 1
    return lines

def simplecount(filename):
    lines = 0
    for line in open(filename):
        lines += 1
    return lines

def bufcount(filename):
    f = open(filename)                  
    lines = 0
    buf_size = 1024 * 1024
    read_f = f.read # loop optimization

    buf = read_f(buf_size)
    while buf:
        lines += buf.count('\n')
        buf = read_f(buf_size)

    return lines

def opcount(fname):
    with open(fname) as f:
        for i, l in enumerate(f):
            pass
    return i + 1

def _make_gen(reader):
    b = reader(1024 * 1024)
    while b:
        yield b
        b = reader(1024*1024)

def rawgencount(filename):
    f = open(filename, 'rb')
    f_gen = _make_gen(f.raw.read)
    return sum( buf.count(b'\n') for buf in f_gen )
    
def rawcount(filename):
    f = open(filename, 'rb')
    lines = 0
    buf_size = 1024 * 1024
    read_f = f.raw.read

    buf = read_f(buf_size)

# Ajout de la détection des fichiers vides de CountLines
# Empty file

    if not buf:
        return 0

    while buf:
        lines += buf.count(b'\n')
        buf = read_f(buf_size)

    return lines

#from itertools import (takewhile,repeat)
#Reporté en début

def rawincount(filename):
    f = open(filename, 'rb')
    bufgen = takewhile(lambda x: x, (f.raw.read(1024*1024) for _ in repeat(None)))
    return sum( buf.count(b'\n') for buf in bufgen )
    
 # Similaire à rawcount ci-dessus 

def CountLines(filename):
    f = open(filename)
    try:
        lines = 0
        buf_size = 1024 * 1024
        read_f = f.read # loop optimization
        buf = read_f(buf_size)

        # Empty file
        if not buf:
            return 0

        while buf:
            lines += buf.count('\n')
            buf = read_f(buf_size)

        return lines
    finally:
        f.close()

#
#
#

counts = defaultdict(list)

for i in range(9):
    for func in [mapcount, simplecount, bufcount, opcount, rawgencount, rawcount, rawincount, CountLines]:
        nbLi = 0

        start_time = time.time()
        nbLi = func("BIG_FILE.csv")
        counts[func].append(time.time() - start_time)
        counts[func].append(nbLi)

for key, vals in counts.items():
    print (key.__name__, "\t : ", sum(vals) / float(len(vals)))