Python function - test if given file is considered binary.

README.md

Python function - is file binary?

Function which determines if a given file is binary.

Test is based on the following algorithm (similar to that implemented within Perl):

• Empty files are considered text.
• If not empty, read up to 512 bytes as a buffer. File will be binary if:
  • Null byte is encountered.
  • More than 30% of the buffer consists of "non text" characters.
• Otherwise, file is text.

Reference

• http://eli.thegreenplace.net/2011/10/19/perls-guess-if-file-is-text-or-binary-implemented-in-python
• http://code.activestate.com/recipes/173220/
• https://stackoverflow.com/questions/1446549/how-to-identify-binary-and-text-files-using-python/1446870#1446870

isbinary.py

#!/usr/bin/env python

class IsFileBinary:
	READ_BYTES = 512
	CHAR_THRESHOLD = 0.3
	TEXT_CHARACTERS = ''.join(
		[chr(code) for code in range(32,127)] +
		list('\b\f\n\r\t')
	)

	def test(self,file_path):
		# read chunk of file
		fh = open(file_path,'r')
		file_data = fh.read(IsFileBinary.READ_BYTES)
		fh.close()

		# store chunk length read
		data_length = len(file_data)
		if (not data_length):
			# empty files considered text
			return False

		if ('\x00' in file_data):
			# file containing null bytes is binary
			return True

		# remove all text characters from file chunk, get remaining length
		binary_length = len(file_data.translate(None,IsFileBinary.TEXT_CHARACTERS))

		# if percentage of binary characters above threshold, binary file
		return (
			(float(binary_length) / data_length) >=
			IsFileBinary.CHAR_THRESHOLD
		)

def main():
	is_file_binary = IsFileBinary()

	print('Is binary file: {0}'.format(is_file_binary.test('./first')))
	print('Is binary file: {0}'.format(is_file_binary.test('./second')))
	print('Is binary file: {0}'.format(is_file_binary.test('./third')))


if (__name__ == '__main__'):
	main()

if sys.version_info < (3, 0):
    fh = open(file_path, 'r')
else:
    fh = open(file_path, 'r', encoding="ISO-8859-1")