In Python, is there a concise way of comparing whether the contents of two text files are the same?

Question

I don't care what the differences are. I just want to know whether the contents are different.

Answer 1

The low level way:

from __future__ import with_statement
with open(filename1) as f1:
   with open(filename2) as f2:
      if f1.read() == f2.read():
         ...

The high level way:

import filecmp
if filecmp.cmp(filename1, filename2, shallow=False):
   ...

Answer 2

If you're going for even basic efficiency, you probably want to check the file size first:

if os.path.getsize(filename1) == os.path.getsize(filename2):
  if open('filename1','r').read() == open('filename2','r').read():
    # Files are the same.

This saves you reading every line of two files that aren't even the same size, and thus can't be the same.

(Even further than that, you could call out to a fast MD5sum of each file and compare those, but that's not "in Python", so I'll stop here.)

Answer 3

This is a functional-style file comparison function. It returns instantly False if the files have different sizes; otherwise, it reads in 4KiB block sizes and returns False instantly upon the first difference:

from __future__ import with_statement
import os
import itertools, functools, operator

def filecmp(filename1, filename2):
    "Do the two files have exactly the same contents?"
    with open(filename1, "rb") as fp1, open(filename2, "rb") as fp2:
        if os.fstat(fp1.fileno()).st_size != os.fstat(fp2.fileno()).st_size:
            return False # different sizes ∴ not equal
        fp1_reader= functools.partial(fp1.read, 4096)
        fp2_reader= functools.partial(fp2.read, 4096)
        cmp_pairs= itertools.izip(iter(fp1_reader, ''), iter(fp2_reader, ''))
        inequalities= itertools.starmap(operator.ne, cmp_pairs)
        return not any(inequalities)

if __name__ == "__main__":
    import sys
    print filecmp(sys.argv[1], sys.argv[2])

Just a different take :)

Answer 4

Since I can't comment on the answers of others I'll write my own.

If you use md5 you definitely must not just md5.update(f.read()) since you'll use too much memory.

def get_file_md5(f, chunk_size=8192):
    h = hashlib.md5()
    while True:
        chunk = f.read(chunk_size)
        if not chunk:
            break
        h.update(chunk)
    return h.hexdigest()

Answer 5

f = open(filename1, "r").read()
f2 = open(filename2,"r").read()
print f == f2

Answer 6

For larger files you could compute a MD5 or SHA hash of the files.

Answer 7

I would use a hash of the file's contents using MD5.

import hashlib

def checksum(f):
    md5 = hashlib.md5()
    md5.update(open(f).read())
    return md5.hexdigest()

def is_contents_same(f1, f2):
    return checksum(f1) == checksum(f2)

if not is_contents_same('foo.txt', 'bar.txt'):
    print 'The contents are not the same!'

Answer 8

from __future__ import with_statement

filename1 = "G:\\test1.TXT"

filename2 = "G:\\test2.TXT"


with open(filename1) as f1:

   with open(filename2) as f2:

      file1list = f1.read().splitlines()

      file2list = f2.read().splitlines()

      list1length = len(file1list)

      list2length = len(file2list)

      if list1length == list2length:

          for index in range(len(file1list)):

              if file1list[index] == file2list[index]:

                   print file1list[index] + "==" + file2list[index]

              else:                  

                   print file1list[index] + "!=" + file2list[index]+" Not-Equel"

      else:

          print "difference inthe size of the file and number of lines"