[CRIU] [PATCH 3/3] Issue #360: Anonymize image files

[Harshavardhan Unnibhavi]

This commit adds the file anonymizer function which anonymizes file names present in images.

The anonymized file names are just the shuffled names along the path from root.

Signed-off-by: Harshavardhan Unnibhavi <hvubfoss at gmail.com>
---
 lib/py/cli.py   |  9 ++++++-
 lib/py/strip.py | 66 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 74 insertions(+), 1 deletion(-)
 create mode 100644 lib/py/strip.py

diff --git a/lib/py/cli.py b/lib/py/cli.py
index 17622fd2..4a8efeff 100755
--- a/lib/py/cli.py
+++ b/lib/py/cli.py
@@ -5,6 +5,7 @@ import json
 import os
 
 import pycriu
+import strip
 
 def inf(opts):
 	if opts['in']:
@@ -281,15 +282,21 @@ def anonymize(opts):
 	img_files = os.listdir(opts['in'])
 
 	for i in img_files:
-		temp = {'in':os.path.join(opts['in'], i)}
+		temp = {'in':os.path.join(opts['in'], i), 'out':os.path.join(opts['out'], i)}
 
 		try:
 			m, img = pycriu.images.load(inf(temp), anon_info = True)
+			print("Processing File name:{} with magic:{}".format(i, m))
 		except pycriu.images.MagicException as exc:
 			print("Unknown magic %#x.\n"\
 					"Found a raw image, continuing ..."% exc.magic, file=sys.stderr)
 			continue
 		
+		anon_dict = strip.anon_handler(img, m)
+		if anon_dict != -1:
+			pycriu.images.dump(anon_dict, outf(temp))
+		
+		
 
 explorers = { 'ps': explore_ps, 'fds': explore_fds, 'mems': explore_mems, 'rss': explore_rss }
 
diff --git a/lib/py/strip.py b/lib/py/strip.py
new file mode 100644
index 00000000..4069275c
--- /dev/null
+++ b/lib/py/strip.py
@@ -0,0 +1,66 @@
+# This file contains methods to deal with anonymising images.
+#
+# Contents being anonymised can be found at: https://github.com/checkpoint-restore/criu/issues/360
+#
+# Inorder to anonymise the image files three steps are followed:
+#    - decode the binary image to json
+#    - strip the necessary information from the json dict
+#    - encode the json dict back to a binary image, which is now anonymised
+
+import sys
+import json
+import random
+
+def files_anon(image):
+    levels = {}
+
+    for e in image['entries']:
+        f_path = e['reg']['name']
+        f_path = f_path.split('/')
+
+        lev_num = 0
+        for p in f_path:
+            if p == '':
+                continue
+            if lev_num in levels.keys():
+                if p not in levels[lev_num].keys():
+                    temp = list(p)
+                    random.shuffle(temp)
+                    levels[lev_num][p] = ''.join(temp)
+            else:
+                levels[lev_num] = {}
+                temp = list(p)
+                random.shuffle(temp)
+                levels[lev_num][p] = ''.join(temp)
+            lev_num += 1
+        
+    for i, e in enumerate(image['entries']):
+        f_path = e['reg']['name']
+        if f_path == '/':
+            continue
+        f_path = f_path.split('/')
+
+        lev_num = 0
+        for j, p in enumerate(f_path):
+            if p == '':
+                continue
+            f_path[j] = levels[lev_num][p]
+            lev_num += 1
+        f_path = '/'.join(f_path)
+        image['entries'][i]['reg']['name'] = f_path
+    
+    return image
+        
+
+
+
+anonymizers = {
+    'FILES': files_anon,
+    }
+
+def anon_handler(image, magic):
+    if magic != 'FILES':
+        return -1
+    handler = anonymizers[magic]
+    anon_image = handler(image)
+    return anon_image
\ No newline at end of file
-- 
2.17.1