It’s more idiomatic to write your code like this
def ProcessLargeTextFile():
with open("filepath", "r") as r, open("outfilepath", "w") as w:
for line in r:
x, y, z = line.split(' ')[:3]
w.write(line.replace(x,x[:-3]).replace(y,y[:-3]).replace(z,z[:-3]))
The main saving here is to just do the split
once, but if the CPU is not being taxed, this is likely to make very little difference
It may help to save up a few thousand lines at a time and write them in one hit to reduce thrashing of your harddrive. A million lines is only 54MB of RAM!
def ProcessLargeTextFile():
bunchsize = 1000000 # Experiment with different sizes
bunch = []
with open("filepath", "r") as r, open("outfilepath", "w") as w:
for line in r:
x, y, z = line.split(' ')[:3]
bunch.append(line.replace(x,x[:-3]).replace(y,y[:-3]).replace(z,z[:-3]))
if len(bunch) == bunchsize:
w.writelines(bunch)
bunch = []
w.writelines(bunch)
suggested by @Janne, an alternative way to generate the lines
def ProcessLargeTextFile():
bunchsize = 1000000 # Experiment with different sizes
bunch = []
with open("filepath", "r") as r, open("outfilepath", "w") as w:
for line in r:
x, y, z, rest = line.split(' ', 3)
bunch.append(' '.join((x[:-3], y[:-3], z[:-3], rest)))
if len(bunch) == bunchsize:
w.writelines(bunch)
bunch = []
w.writelines(bunch)