Continue after par2 renaming (#1921)

* record new files generated based on par2

* record new files generated based on par2

* test first par2 based renaming, then deobfuscate obfuscated names

* remove commented-out line

* corrected contents zip-file

* try again, github

* try again, github

sabnzbd/deobfuscate_filenames.py

@@ -43,7 +43,7 @@ MIN_FILE_SIZE = 10 * 1024 * 1024
 
 
 def decode_par2(parfile):
-    """Parse a par2 file and rename files listed in the par2 to their real name"""
+    """Parse a par2 file and rename files listed in the par2 to their real name. Resturn list of generated files"""
     # Check if really a par2 file
     if not is_parfile(parfile):
         logging.info("Par2 file %s was not really a par2 file")
@@ -55,7 +55,7 @@ def decode_par2(parfile):
 
     # Parse all files in the folder
     dirname = os.path.dirname(parfile)
-    result = False
+    new_files = []  # list of new files generated
     for fn in os.listdir(dirname):
         filepath = os.path.join(dirname, fn)
         # Only check files
@@ -68,9 +68,10 @@ def decode_par2(parfile):
             if file_md5of16k in md5of16k:
                 new_path = os.path.join(dirname, md5of16k[file_md5of16k])
                 # Make sure it's a unique name
-                renamer(filepath, get_unique_filename(new_path))
-                result = True
-    return result
+                unique_filename = get_unique_filename(new_path)
+                renamer(filepath, unique_filename)
+                new_files.append(unique_filename)
+    return new_files
 
 
 def is_probably_obfuscated(myinputfilename):
@@ -154,16 +155,14 @@ def deobfuscate_list(filelist, usefulname):
         for par2_file in par2_files:
             # Analyse data and analyse result
             logging.debug("Deobfuscate par2: handling %s", par2_file)
-            if decode_par2(par2_file):
+            new_files = decode_par2(par2_file)
+            if new_files:
                 logging.debug("Deobfuscate par2 repair/verify finished")
-                par2_renaming_done = True
+                filelist += new_files
+                filelist = [f for f in filelist if os.path.isfile(f)]
             else:
                 logging.debug("Deobfuscate par2 repair/verify did not find anything to rename")
 
-    if par2_renaming_done:
-        # TODO really needed to quit here? We could also proceed with the other actions. Anyway:
-        return  # done
-
     # let's see if there are files with uncommon/unpopular (so: obfuscated) extensions
     # if so, let's give them a better extension based on their internal content/info
     # Example: if 'kjladsflkjadf.adsflkjads' is probably a PNG, rename to 'kjladsflkjadf.adsflkjads.png'

tests/test_deobfuscate_filenames.py

@@ -21,6 +21,7 @@ Testing SABnzbd deobfuscate module
 
 import random
 import shutil
+import zipfile
 
 from sabnzbd.deobfuscate_filenames import *
 from tests.testhelper import *
@@ -324,3 +325,28 @@ class TestDeobfuscateFinalResult:
         # Rename back
         os.rename(test_output, test_input)
         assert os.path.exists(test_input)
+
+    def test_deobfuscate_par2_plus_deobfuscate(self):
+        # test for first par2 based renaming, then deobfuscate obfuscated names
+        work_dir = os.path.join(SAB_DATA_DIR, "testdir" + str(random.randint(10000, 99999)))
+        os.mkdir(work_dir)
+
+        source_zip_file = os.path.join(SAB_DATA_DIR, "deobfuscate_par2_based", "20mb_with_par2_package.zip")
+        with zipfile.ZipFile(source_zip_file, "r") as zip_ref:
+            zip_ref.extractall(work_dir)
+        assert os.path.isfile(os.path.join(work_dir, "rename.par2"))  # the par2 that will do renaming
+        assert os.path.isfile(os.path.join(work_dir, "aaaaaaaaaaa"))  # a 20MB no-name file ...
+
+        list_of_files = []
+        for (dirpath, dirnames, filenames) in os.walk(work_dir):
+            list_of_files += [os.path.join(dirpath, file) for file in filenames]
+
+        # deobfuscate will do:
+        # first par2 based renaming aaaaaaaaaaa to twentymb.bin,
+        # then deobfuscate twentymb.bin to the job name (with same extension)
+        deobfuscate_list(list_of_files, "My Great Download")
+
+        assert os.path.isfile(os.path.join(work_dir, "My Great Download.bin"))  # the twentymb.bin should be renamed
+        assert not os.path.isfile(os.path.join(work_dir, "twentymb.bin"))  # should be gone
+
+        shutil.rmtree(work_dir)