Add unicode support in ciphers/base64_cipher.py script. (#1316)

* Add unicode support in ciphers/base64_cipher.py script.

* Add doctests and correct the padding length computation in base64_cipher.

ciphers/base64_cipher.py

@@ -1,35 +1,52 @@
-def encodeBase64(text):
-    base64chars = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
+def encode_base64(text):
+    r"""
+    >>> encode_base64('WELCOME to base64 encoding 😁')
+    'V0VMQ09NRSB0byBiYXNlNjQgZW5jb2Rpbmcg8J+YgQ=='
+    >>> encode_base64('AÅᐃ𐀏🤓')
+    'QcOF4ZCD8JCAj/CfpJM='
+    >>> encode_base64('A'*60)
+    'QUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFB\r\nQUFB'
+    """
+    base64_chars = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
 
+    byte_text = bytes(text, "utf-8")  # put text in bytes for unicode support
     r = ""  # the result
-    c = 3 - len(text) % 3  # the length of padding
+    c = -len(byte_text) % 3  # the length of padding
     p = "=" * c  # the padding
-    s = text + "\0" * c  # the text to encode
+    s = byte_text + b"\x00" * c  # the text to encode
 
     i = 0
     while i < len(s):
         if i > 0 and ((i / 3 * 4) % 76) == 0:
-            r = r + "\r\n"
+            r = r + "\r\n" # for unix newline, put "\n"
 
-        n = (ord(s[i]) << 16) + (ord(s[i + 1]) << 8) + ord(s[i + 2])
+        n = (s[i] << 16) + (s[i + 1] << 8) + s[i + 2]
 
         n1 = (n >> 18) & 63
         n2 = (n >> 12) & 63
         n3 = (n >> 6) & 63
         n4 = n & 63
 
-        r += base64chars[n1] + base64chars[n2] + base64chars[n3] + base64chars[n4]
+        r += base64_chars[n1] + base64_chars[n2] + base64_chars[n3] + base64_chars[n4]
         i += 3
 
     return r[0 : len(r) - len(p)] + p
 
 
-def decodeBase64(text):
-    base64chars = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
+def decode_base64(text):
+    r"""
+    >>> decode_base64('V0VMQ09NRSB0byBiYXNlNjQgZW5jb2Rpbmcg8J+YgQ==')
+    'WELCOME to base64 encoding 😁'
+    >>> decode_base64('QcOF4ZCD8JCAj/CfpJM=')
+    'AÅᐃ𐀏🤓'
+    >>> decode_base64("QUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFB\r\nQUFB")
+    'AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA'
+    """
+    base64_chars = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
     s = ""
 
     for i in text:
-        if i in base64chars:
+        if i in base64_chars:
             s += i
             c = ""
         else:
@@ -43,28 +60,28 @@ def decodeBase64(text):
         if c == "==":
             p = "AA"
 
-    r = ""
+    r = b""
     s = s + p
 
     i = 0
     while i < len(s):
         n = (
-            (base64chars.index(s[i]) << 18)
-            + (base64chars.index(s[i + 1]) << 12)
-            + (base64chars.index(s[i + 2]) << 6)
-            + base64chars.index(s[i + 3])
+            (base64_chars.index(s[i]) << 18)
+            + (base64_chars.index(s[i + 1]) << 12)
+            + (base64_chars.index(s[i + 2]) << 6)
+            + base64_chars.index(s[i + 3])
         )
 
-        r += chr((n >> 16) & 255) + chr((n >> 8) & 255) + chr(n & 255)
+        r += bytes([(n >> 16) & 255]) + bytes([(n >> 8) & 255]) + bytes([n & 255])
 
         i += 4
 
-    return r[0 : len(r) - len(p)]
+    return str(r[0 : len(r) - len(p)], "utf-8")
 
 
 def main():
-    print(encodeBase64("WELCOME to base64 encoding"))
-    print(decodeBase64(encodeBase64("WELCOME to base64 encoding")))
+    print(encode_base64("WELCOME to base64 encoding 😁"))
+    print(decode_base64(encode_base64("WELCOME to base64 encoding 😁")))
 
 
 if __name__ == "__main__":