Basic recusrive fuzzy hashing working. Renamed fuzzyhash.py to hashmatch.py.

src/binwalk/common.py

@@ -3,9 +3,26 @@ import io
 import os
 import re
 import ast
+import hashlib
 import operator as op
 from binwalk.compat import *
 
+def file_md5(file_name):
+	'''
+	Generate an MD5 hash of the specified file.
+	
+	@file_name - The file to hash.
+
+	Returns an MD5 hex digest string.
+	'''
+	md5 = hashlib.md5()
+
+	with open(file_name, 'rb') as f:
+		for chunk in iter(lambda: f.read(128*md5.block_size), b''):
+			md5.update(chunk)
+
+	return md5.hexdigest()
+
 def file_size(filename):
 	'''
 	Obtains the size of a given file.

src/binwalk/fuzzyhash.py

-import ctypes
-import ctypes.util
-from binwalk.compat import *
-
-class FuzzyHash(object):
-
-	# Requires libfuzzy.so
-	LIBRARY_NAME = "fuzzy"
-
-	# Max result is 148 (http://ssdeep.sourceforge.net/api/html/fuzzy_8h.html)
-	FUZZY_MAX_RESULT = 150
-
-	def __init__(self):
-		self.lib = ctypes.cdll.LoadLibrary(ctypes.util.find_library(self.LIBRARY_NAME))
-
-	def compare_files(self, file1, file2):
-		hash1 = ctypes.create_string_buffer(self.FUZZY_MAX_RESULT)
-		hash2 = ctypes.create_string_buffer(self.FUZZY_MAX_RESULT)
-
-		if self.lib.fuzzy_hash_filename(str2bytes(file1), hash1) == 0 and self.lib.fuzzy_hash_filename(str2bytes(file2), hash2) == 0:
-			return self.lib.fuzzy_compare(hash1, hash2)
-
-		return None
-
-
-if __name__ == '__main__':
-	import sys
-	
-	print (FuzzyHash().compare_files(sys.argv[1], sys.argv[2]))

src/binwalk/prettyprint.py

 import io
 import sys
-import hashlib
 import csv as pycsv
 from datetime import datetime
 from binwalk.compat import *
+from binwalk.common import file_md5
 
 class PrettyPrint:
 	'''
@@ -126,18 +126,6 @@ class PrettyPrint:
 		if not nolog:
 			self._log(data)
 
-	def _file_md5(self, file_name):
-		'''
-		Generate an MD5 hash of the specified file.
-		'''
-		md5 = hashlib.md5()
-                
-		with open(file_name, 'rb') as f:
-			for chunk in iter(lambda: f.read(128*md5.block_size), b''):
-				md5.update(chunk)
-
-		return md5.hexdigest()
-
 	def _append_to_data_parts(self, data, start, end):
 		'''
 		Intelligently appends data to self.string_parts.
@@ -225,7 +213,7 @@ class PrettyPrint:
 		Returns None.
 		'''
 		nolog = False
-		md5sum = self._file_md5(file_name)
+		md5sum = file_md5(file_name)
 		timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
 
 		if self.csv: