From d7c84268a26a4391af55a3533422367b02737435 Mon Sep 17 00:00:00 2001
From: Daniel Gnoutcheff <gnoutchd@softwarefreedom.org>
Date: Mon, 23 Jan 2017 18:38:22 -0500
Subject: Misc. unrecorded changes

---
 suspicious | 52 ++++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 38 insertions(+), 14 deletions(-)

(limited to 'suspicious')

diff --git a/suspicious b/suspicious
index 72dd9b0..2ab782b 100755
--- a/suspicious
+++ b/suspicious
@@ -15,10 +15,11 @@
 #    You should have received a copy of the GNU General Public License
 #    along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
-#Authors: Marc Jones <mjones@softwarefreedom.org>, Daniel Gnoutcheff <gnoutchd@softwarefreedom.org>
-#Date: June 2016
-#Version 0.3.0
-#Added AVFS support
+# Authors: Marc Jones <mjones@softwarefreedom.org>, 
+#          Daniel Gnoutcheff <gnoutchd@softwarefreedom.org>
+# Date: June 2016
+# Version 0.3.0
+# Added AVFS support
 
 ##TODO
 #need to verify that word score counts each instance, not just 0 or 1
@@ -32,6 +33,8 @@ import sys
 import datetime
 import string
 import subprocess
+import chardet
+
 import avfs
 
 report = {}
@@ -48,6 +51,32 @@ progresstext = ""
 fsencoding = sys.getfilesystemencoding()
 def fsdecode_display(bytestring):
 	return str(bytestring, encoding=fsencoding, errors='replace')
+
+
+_def_file_encoding = sys.getdefaultencoding()
+
+def decode_file(filename):
+	"""
+	Return the contents of the file at the given path as a (Unicode) string.
+	Return None if the file appears to be a binary.
+	"""
+
+	with avfs.open(filename, 'rb') as filehandle:
+		contents_raw = filehandle.read()
+	
+	try:
+		return str(contents_raw, encoding=_def_file_encoding)
+	except UnicodeDecodeError:
+		pass
+	
+	guessed_encoding = chardet.detect(contents_raw)['encoding']
+	if not guessed_encoding:
+		return None
+	
+	try:
+		return str(contents_raw, encoding=guessed_encoding)
+	except UnicodeDecodeError:
+		return None
 	
 def sortscore(score, reverse=True):
 	sortedscore = sorted(score.items(), key=lambda score: score[1], reverse=reverse)
@@ -304,10 +333,13 @@ for file in filelist:
 		skipped += 1
 		continue
 	try:
-		f = avfs.open(file)
-	except:
+		filecontents = decode_file(file)
+	except OSError:
 		print("failed to open: " + file_displayname)
 		continue
+	if filecontents is None:
+		print("possible binary: " + file_displayname)
+		continue
 	opened +=1
 	now = datetime.datetime.now()
 	if options.display_progress: 
@@ -326,14 +358,6 @@ for file in filelist:
 			.format(frac_done, est_hr, est_min, est_sec, prog_file)
 		print(progresstext, end='', file=sys.stderr)
 	sys.stdout.flush()
-	try:
-		filecontents = f.read()
-	except UnicodeDecodeError:
-		print("possible binary: " + file_displayname)
-		continue
-	except OSError:
-		print("read error: " + file_displayname)
-		continue
 	datasize += len(filecontents)		
 	filenamescore = scoretext(wordlist, file_displayname, options.maxwholewordlength)
 	filecontentsscore = scoretext(wordlist, filecontents, options.maxwholewordlength)
-- 
cgit v1.2.3