Fixed leading null bytes being dropped by big-integer base codecs

The generic base_encode/base_decode convert the whole input to a single
integer, so leading null bytes (high-order zeros) were silently lost: e.g.
Base58 encoded b'\x00abc' to 'ZiCa' instead of '1ZiCa', and b'\x00' to an
empty string. Per the Base58 spec each leading 0x00 byte maps to a leading
charset[0] character. Preserve the leading-zero count on encode and restore
it on decode, so values round-trip and match reference implementations.

Author: gaoflow

src/codext/base/_base.py

@@ -130,6 +130,10 @@ def base_encode(input, charset, errors="strict", exc=BaseEncodeError):
     while i > 0:
         i, c = divmod(i, n)
         r = charset[c] + r
+    # preserve leading zero bytes: big-integer bases such as Base58 map each
+    # leading null byte of the input to a leading charset[0] character
+    if not isinstance(input, int):
+        r = charset[0] * (len(input) - len(input.lstrip("\x00"))) + r
     return r
 
 
@@ -151,7 +155,8 @@ def base_decode(input, charset, errors="strict", exc=BaseDecodeError):
             i = i * n + charset.index(c)
         except ValueError:
             handle_error("base", errors, exc, decode=True)(c, k, dec(i), "base%d" % n)
-    return dec(i)
+    # restore the leading zero bytes encoded as leading charset[0] characters
+    return chr(0) * (len(input) - len(input.lstrip(charset[0]))) + dec(i)
 
 
 # base codec factory functions

tests/test_base.py

@@ -172,7 +172,15 @@ def test_codec_base58(self):
         self.assertEqual(codecs.decode(B58, "base58-fl"), STR)
         self.assertEqual(codecs.encode(STR, "base58-short-url"), B58)
         self.assertEqual(codecs.encode(STR, "base58-url"), B58)
-    
+        # leading null bytes must be preserved as leading charset[0] ('1')
+        self.assertEqual(codecs.encode("\x00abc", "base58"), "1ZiCa")
+        self.assertEqual(codecs.encode("\x00", "base58"), "1")
+        self.assertEqual(codecs.encode("\x00\x00abc", "base58"), "11ZiCa")
+        self.assertEqual(codecs.decode("1ZiCa", "base58"), "\x00abc")
+        self.assertEqual(codecs.decode("11ZiCa", "base58"), "\x00\x00abc")
+        self.assertEqual(codecs.encode(b("\x00abc"), "base58"), b("1ZiCa"))
+        self.assertEqual(codecs.decode(b("1ZiCa"), "base58"), b("\x00abc"))
+
     def test_codec_base62(self):
         for b62, enc in zip(["CsoB4HQ5gmgMyCenF7E", "M2yLERaFqwqW8MoxPHO"], ["base62", "base62-inv"]):
             self.assertEqual(codecs.encode(STR, enc), b62)