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()