Fixed rehash bug in display of file paths when diffing multiple directories;…

Fixed rehash bug in display of file paths when diffing multiple directories; added --abspath option to rehash.

src/bin/rehash

@@ -39,6 +39,7 @@ def usage(fd):
 	fd.write("\n")
 	fd.write("General Options:\n")
 	fd.write("\t-f, --file=<file>             Log results to file\n")
+	fd.write("\t-a, --abspath                 Display the absolute path of each file\n")
 	fd.write("\t-c, --csv                     Log results to file in csv format\n")
 	fd.write("\t-q, --quiet                   Suppress output to stdout\n")
 	fd.write("\t-t, --term                    Format output to fit the terminal window\n")
@@ -65,6 +66,7 @@ def main():
 	types = {}
 	matches = {}
 
+	abspath = False
 	log_file = None
 	log_csv = False
 	fit_to_width = False
@@ -76,8 +78,9 @@ def main():
 	cutoff = None
 	max_results = None
 
-	short_options = "cdf:hlm:no:qSstx:X:y:Y:"
+	short_options = "acdf:hlm:no:qSstx:X:y:Y:"
 	long_options = [
+			"abspath",
 			"help",
 			"cutoff=",
 			"strings",
@@ -131,6 +134,8 @@ def main():
 			include_types.append(arg.lower())
 		elif opt in ("-X", "--exclude-types"):
 			exclude_types.append(arg.lower())
+		elif opt in ("-a", "--abspath"):
+			abspath = True
 
 		# Keep track of the options and arguments.
 		# This is used later to determine which argv entries are file names.
@@ -166,6 +171,7 @@ def main():
 						log=log_file,
 						csv=log_csv,
 						format_to_screen=fit_to_width,
+						abspath=abspath,
 						types=types,
 						matches=matches)
 

src/binwalk/hashmatch.py

@@ -28,7 +28,7 @@ class HashMatch(object):
 
 	FUZZY_DEFAULT_CUTOFF = 50
 
-	def __init__(self, cutoff=None, strings=False, same=False, symlinks=False, name=False, max_results=None, display=False, log=None, csv=False, quiet=False, format_to_screen=False, matches={}, types={}):
+	def __init__(self, cutoff=None, strings=False, same=False, symlinks=False, name=False, max_results=None, display=False, log=None, csv=False, quiet=False, format_to_screen=False, abspath=False, matches={}, types={}):
 		'''
 		Class constructor.
 
@@ -39,6 +39,11 @@ class HashMatch(object):
 		@name             - Set to True to only compare files whose base names match.
 		@max_results      - Stop searching after x number of matches.
 		@display          - Set to True to display results to stdout.
+		@log              - Specify a log file to log results to.
+		@csv              - Set to True to log data in CSV format.
+		@quiet            - Set to True to suppress output to stdout.
+		@format_to_screen - Set to True to format the output to the terminal window width.
+		@abspath          - Set to True to display absolute file paths.
 		@matches          - A dictionary of file names to diff.
 		@types            - A dictionary of file types to diff.
 
@@ -51,11 +56,12 @@ class HashMatch(object):
 		self.matches = matches
 		self.name = name
 		self.types = types
+		self.abspath = abspath
 		self.max_results = max_results
 
 		if display:
 			self.pretty_print = PrettyPrint(log=log, csv=csv, format_to_screen=format_to_screen, quiet=quiet)
-			self.pretty_print.header(header="PERCENTAGE\tFILE NAME")
+			self.pretty_print.header(header="PERCENTAGE\t\t\tFILE NAME")
 		else:
 			self.pretty_print = None
 
@@ -80,7 +86,9 @@ class HashMatch(object):
 
 	def _print(self, match, fname):
 		if self.pretty_print:
-			self.pretty_print.results(None, [{'description' : '%4d\t\t%s\n' % (match, fname)}], formatted=True)
+			if self.abspath:
+				fname = os.path.abspath(fname)
+			self.pretty_print._pprint('%4d\t\t\t\t%s\n' % (match, self.pretty_print._format(fname)))
 
 	def _print_footer(self):
 		if self.pretty_print:
@@ -106,6 +114,7 @@ class HashMatch(object):
 				hash1 = ctypes.create_string_buffer(self.FUZZY_MAX_RESULT)
 				hash2 = ctypes.create_string_buffer(self.FUZZY_MAX_RESULT)
 
+				# Check if the last file1 or file2 matches this file1 or file2; no need to re-hash if they match.
 				if file1 == self.last_file1.name and self.last_file1.hash:
 					file1_dup = True
 				else:
@@ -310,8 +319,8 @@ class HashMatch(object):
 
 					m = self._compare_files(file1, file2)
 					if m is not None and self.is_match(m):
-						self._print(m, f)
-						results.append((m, f))
+						self._print(m, file2)
+						results.append((m, file2))
 
 						self.total += 1
 						if self.max_results and self.total >= self.max_results:

src/binwalk/prettyprint.py

@@ -286,7 +286,7 @@ class PrettyPrint:
 					else:
 						self._pprint("%s\t  %s\t%s\n" % (' '*10, ' '*8, self._format(info['description'])))
 				else:
-					self._pprint(info['description'])
+					self._pprint(self._format(info['description']))
 
 	def easy_results(self, offset, description):
 		'''