Merge pull request #5 from adobe/dev.jwt

Dev.jwt

Author: acotaie

data/enhanced-c.bestType

@@ -0,0 +1 @@
+{"char_emb_size": 100, "rnn_layers": 2, "rnn_size": 100, "hidden": 500}

data/enhanced-c.conf

@@ -0,0 +1 @@
+{"char2int": {"<PAD>": 0, "<UNK>": 1, "p": 2, "e": 3, "h": 4, "r": 5, "d": 6, "o": 7, "|": 8, "b": 9, "u": 10, "n": 11, "s": 12, " ": 13, "!": 14, "l": 15, "a": 16, "w": 17, "c": 18, "i": 19, "f": 20, "2": 21, "1": 22, "7": 23, "{": 24, "y": 25, "j": 26, "0": 27, "x": 28, "k": 29, "v": 30, "q": 31, "g": 32, "z": 33, "9": 34, ".": 35, "6": 36, "m": 37, "5": 38, "3": 39, "t": 40, "4": 41, "-": 42, "}": 43, "&": 44, "=": 45, ":": 46, ",": 47, "8": 48, "\\": 49, "'": 50, "(": 51, ")": 52, "%": 53, "@": 54, "$": 55, "\"": 56, ";": 57, "[": 58, "]": 59, "`": 60, "_": 61, "<": 62, "~": 63, "/": 64, "+": 65, "#": 66, "?": 67, "*": 68, ">": 69}, "label2int": {"<PAD>": 0, "C": 1, "J": 2, "N": 3, "H": 4, "U": 5, "I": 6}}

data/enhanced-c.encodings

@@ -12,7 +12,7 @@ def parse_requirements(filename, session=None):
 
 setuptools.setup(
     name="stringlifier",
-    version="0.1.0.8",
+    version="0.1.0.9",
     author="Multiple authors",
     author_email="tiberiu44@gmail.com",
     description="Python module for detecting password, api keys hashes and any other string that resembles a randomly generated character sequence.",

data/enhanced-c.last

@@ -226,6 +226,8 @@ def _extract_tokens(self, string: str, pred: NDArray[Int64]) -> Tuple[str, List[
                 type_ = '<IP_ADDR>'
             elif last_label == 'U':
                 type_ = '<UUID>'
+            elif last_label == 'J':
+                type_ = '<JWT>'
             if last_label != 'C':
                 tokens.append((c_tok, start, ii, type_))
 

setup.py

@@ -17,12 +17,13 @@
 known_words = []
 
 
+
 def _generate_word(known_words):
     import uuid
     import datetime
     import base64
     generated = None
-    ii = random.randint(0, 4)
+    ii = random.randint(0, 5)
     mask = 'H'
     if ii == 0:
         generated = str(uuid.uuid4())
@@ -61,13 +62,26 @@ def _generate_word(known_words):
             toks.append(str(random.randint(0, 255)))
         generated = '.'.join(toks)
         mask = 'I'
+    elif ii==5:
+        generated=_generate_JWT_token(known_words)
+        mask = 'J'
     return str(generated), mask[0]
 
 
 lines = open('corpus/words_alpha.txt').readlines()
 for line in lines:
     known_words.append(line.strip())
 
+
+def _generate_JWT_token(known_words):
+    import jwt
+
+    payload = {"id": str(random.random()), "client_id": str(random.random()), "user_id": str(random.random()), "type": "access_token",
+               "expires_in": str(random.randint(10,3600000)), "scope": "read, write", "created_at": str(random.randint(1900000, 9000000))}
+    encoded_jwt = jwt.encode(payload, 'secret', algorithm='HS256')
+
+    return str(encoded_jwt)[2:-1]
+
 # generated_words = generate_words(len(known_words), known_words)
 
 known_index = 0