added pw cracking

tests/crack_test.py

@@ -0,0 +1,59 @@
+import hashlib
+import tempfile
+import unittest
+from glob import glob
+from pathlib import Path
+
+from collectionparser.crack import crack
+from collectionparser.parser import Processor
+
+
+class CrackTest(unittest.TestCase):
+
+    def test_hash_saved_by_processor(self):
+        with tempfile.TemporaryDirectory() as tmp:
+            src = Path(tmp) / 'in.txt'
+            src.write_text('[email protected]:5f4dcc3b5aa765d61d8327deb882cf99\n[email protected]:plainpw\n',
+                           encoding='utf8')
+            processor = Processor(str(Path(tmp) / 's.txt'), str(Path(tmp) / 'f.txt'),
+                                  str(Path(tmp) / 'h.txt'))
+            processor.process(src)
+            hashes = ''.join(Path(p).read_text(encoding='utf8')
+                             for p in glob(str(Path(tmp) / 'h.txt.part.*')))
+            success = ''.join(Path(p).read_text(encoding='utf8')
+                              for p in glob(str(Path(tmp) / 's.txt.part.*')))
+            self.assertEqual('[email protected]:5f4dcc3b5aa765d61d8327deb882cf99\n', hashes)
+            self.assertEqual('[email protected]:plainpw\n', success)
+
+    def test_crack_md5_and_sha1(self):
+        with tempfile.TemporaryDirectory() as tmp:
+            hashes = Path(tmp) / 'hashes.txt'
+            hashes.write_bytes(
+                b'[email protected]:' + hashlib.md5(b'hunter2').hexdigest().encode() + b'\n'
+                b'[email protected]:' + hashlib.sha1(b'secret').hexdigest().encode() + b'\n'
+                b'[email protected]:not-a-hash\n')
+            wordlist = Path(tmp) / 'words.txt'
+            wordlist.write_bytes(b'foo\nhunter2\nbar\nsecret\n')
+            out = Path(tmp) / 'cracked.txt'
+            total = crack(str(hashes), str(out), wordlists=[str(wordlist)], workers=2)
+            self.assertEqual(2, total)
+            self.assertEqual({b'[email protected]:hunter2', b'[email protected]:secret'},
+                             set(out.read_bytes().splitlines()))
+
+    def test_crack_from_plaintext_passwords(self):
+        with tempfile.TemporaryDirectory() as tmp:
+            hashes = Path(tmp) / 'hashes.txt'
+            hashes.write_bytes(b'[email protected]:' + hashlib.md5(b'reused').hexdigest().encode() + b'\n')
+            empty = Path(tmp) / 'empty.txt'
+            empty.write_bytes(b'')
+            plaintext = Path(tmp) / 'plain.txt'
+            plaintext.write_bytes(b'[email protected]:reused\n')
+            out = Path(tmp) / 'cracked.txt'
+            total = crack(str(hashes), str(out), wordlists=[str(empty)],
+                          passwords_from=[str(plaintext)], workers=1)
+            self.assertEqual(1, total)
+            self.assertEqual([b'[email protected]:reused'], out.read_bytes().splitlines())
+
+
+if __name__ == '__main__':
+    unittest.main()

tests/parser_test.py

@@ -3,6 +3,7 @@ from time import time
 
 from collectionparser.parser import parseline as p
 from collectionparser.splitter import get_output_file
+from collectionparser.utils import PasswordType
 
 
 class ParserTest(unittest.TestCase):
@@ -97,7 +98,10 @@ class ParserTest(unittest.TestCase):
 
         self.assertIsNone(p('300396	matelymaly	[email protected]	222.155.173.78	'
                             '3d2c5414a041f518b03b750e62e4ebc3:Nhc'))
-        self.assertIsNone(p('05-02-2012;5721869;[email protected]:f02368945726d5fc2a14eb576f7276c0'))
+        # 32-char hex is a hash, not junk: kept (typed) so `crack` can attack it.
+        hashed = p('05-02-2012;5721869;[email protected]:f02368945726d5fc2a14eb576f7276c0')
+        self.assertIsNotNone(hashed)
+        self.assertEqual(PasswordType.MD5, hashed[2])
         self.assertIsNotNone(p('[email protected]::g1u3ck'))
         self.assertIsNotNone(p('[email protected]:[email protected]:2904198'))
         self.assertIsNotNone(p('sanda [email protected]:vasafultv'))

tests/utils_test.py

@@ -1,36 +0,0 @@
-import unittest
-
-from collectionparser.utils import RingDictionary
-
-
-class UtilsTest(unittest.TestCase):
-
-    def test_ring_dictionary_1(self):
-        rd = RingDictionary(max_num_keys=3)
-        rd['a'] = 2
-        self.assertListEqual(sorted(rd.d), ['a'])
-        self.assertListEqual(sorted(rd.k), ['a'])
-        rd['b'] = 2
-        self.assertListEqual(sorted(rd.d), ['a', 'b'])
-        self.assertListEqual(sorted(rd.k), ['a', 'b'])
-        rd['c'] = 2
-        self.assertListEqual(sorted(rd.d), ['a', 'b', 'c'])
-        self.assertListEqual(sorted(rd.k), ['a', 'b', 'c'])
-        rd['d'] = 2
-        self.assertListEqual(sorted(rd.d), ['b', 'c', 'd'])
-        self.assertListEqual(sorted(rd.k), ['b', 'c', 'd'])
-
-        rd = RingDictionary(max_num_keys=1)
-        rd['c'] = 1
-        rd['c'] = 2
-        rd['c'] = 3
-        self.assertListEqual(sorted(rd.d), ['c'])
-        self.assertListEqual(sorted(rd.k), ['c'])
-
-        rd['d'] = 3
-        self.assertListEqual(sorted(rd.d), ['d'])
-        self.assertListEqual(sorted(rd.k), ['d'])
-
-
-if __name__ == '__main__':
-    unittest.main()