codext 1.16.4__tar.gz → 1.16.5__tar.gz

{codext-1.16.4 → codext-1.16.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: codext
-Version: 1.16.4
+Version: 1.16.5
 Summary: Native codecs extension
 Author-email: Alexandre D'Hondt <alexandre.dhondt@gmail.com>
 License:                     GNU GENERAL PUBLIC LICENSE

codext-1.16.5/src/codext/VERSION.txt

@@ -0,0 +1 @@
+1.16.5

{codext-1.16.4 → codext-1.16.5}/src/codext/base/_base.py

@@ -125,8 +125,10 @@ def base_encode(input, charset, errors="strict", exc=BaseEncodeError):
         if i > SIZE_LIMIT:
             raise InputSizeLimitError("Input exceeded size limit")
         return i * charset[0]
-    if n == 10:
-        return str(i) if charset == digits else "".join(charset[int(x)] for x in str(i))
+    # keep this fast-path only for a non-standard 10-character charset ; the digits
+    # charset uses the generic loop below (leading zeros, bignums, no str/int round-trip)
+    if n == 10 and charset != digits:
+        return "".join(charset[int(x)] for x in str(i))
     while i > 0:
         i, c = divmod(i, n)
         r = charset[c] + r
@@ -148,8 +150,8 @@ def base_decode(input, charset, errors="strict", exc=BaseDecodeError):
     i, n, dec = 0, len(charset), lambda n: base_encode(n, [chr(x) for x in range(256)], errors, exc)
     if n == 1:
         return i2s(len(input))
-    if n == 10:
-        return i2s(int(input)) if charset == digits else "".join(str(charset.index(c)) for c in input)
+    if n == 10 and charset != digits:
+        return "".join(str(charset.index(c)) for c in input)
     for k, c in enumerate(input):
         try:
             i = i * n + charset.index(c)

{codext-1.16.4 → codext-1.16.5}/src/codext/checksums/crc.py

@@ -13,6 +13,7 @@ from ..__common__ import add
 
 CRC = {
     '': {
+        '':              (0x1021, 0xc6c6, True, True, 0, 0xbf05),
         'a':             (0x1021, 0xc6c6, True, True, 0, 0xbf05),
     },
     8: {
@@ -78,6 +79,7 @@ CRC = {
         'mpt1327':       (0x6815, 0, False, False, 1, 0x2566),
     },
     16: {
+        '':              (0x8005, 0, True, True, 0, 0xbb3d),
         'acorn':         (0x1021, 0, False, False, 0, 0x31c3),
         'arc':           (0x8005, 0, True, True, 0, 0xbb3d),
         'atom':          (0x002d, 0, True, True, 0, 0x4287),

{codext-1.16.4 → codext-1.16.5}/src/codext.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: codext
-Version: 1.16.4
+Version: 1.16.5
 Summary: Native codecs extension
 Author-email: Alexandre D'Hondt <alexandre.dhondt@gmail.com>
 License:                     GNU GENERAL PUBLIC LICENSE

{codext-1.16.4 → codext-1.16.5}/tests/test_base.py

@@ -112,7 +112,30 @@ class TestCodecsBase(TestCase):
         self.assertEqual(codecs.decode(B8, "base8-01234567"), STR)
         self.assertRaises(LookupError, codecs.encode, "test", "base8-0123456")
         self.assertRaises(LookupError, codecs.encode, "test", "base8-012345678")
-    
+
+    def test_codec_base10(self):
+        B10 = "2361031878030638688519054699098996"
+        self.assertEqual(codecs.encode(STR, "base10"), B10)
+        self.assertEqual(codecs.encode(b(STR), "base10"), b(B10))
+        self.assertEqual(codecs.decode(B10, "base10"), STR)
+        self.assertEqual(codecs.decode(b(B10), "base10"), b(STR))
+        for alias in ["int", "integer", "dec", "decimal"]:
+            self.assertEqual(codecs.encode(STR, alias), B10)
+            self.assertEqual(codecs.decode(B10, alias), STR)
+        # leading null bytes must be preserved as leading '0' characters
+        self.assertEqual(codecs.encode("\x00abc", "base10"), "06382179")
+        self.assertEqual(codecs.encode("\x00", "base10"), "0")
+        self.assertEqual(codecs.encode("\x00\x00abc", "base10"), "006382179")
+        self.assertEqual(codecs.decode("06382179", "base10"), "\x00abc")
+        self.assertEqual(codecs.decode("00", "base10"), "\x00\x00")
+        self.assertEqual(codecs.encode(b("\x00abc"), "base10"), b("06382179"))
+        self.assertEqual(codecs.decode(b("06382179"), "base10"), b("\x00abc"))
+        # a value whose big integer ends in a 0xe nibble must survive decoding
+        self.assertEqual(codecs.decode(codecs.encode(b"d\xc6\xfe", "base10"), "base10"), b"d\xc6\xfe")
+        # large inputs must not hit the int<->str conversion digit limit
+        for data in [b"\x00\xff\xfe", b"\x00\x00", b"\x2a" * 2048]:
+            self.assertEqual(codecs.decode(codecs.encode(data, "base10"), "base10"), data)
+
     def test_codec_base16(self):
         B16 = "7468697320697320612074657374"
         self.assertEqual(codecs.encode(STR, "base16"), B16)

{codext-1.16.4 → codext-1.16.5}/tests/test_manual.py

@@ -106,6 +106,25 @@ class ManualTestCase(TestCase):
         for s, r in [("", ""), ("0", "0"), ("1", "8"), ("7992739871", "3")]:
             self.assertEqual(codecs.encode(s, "luhn"), r)
         self.assertEqual(codecs.encode("-", "luhn", errors="ignore"), "")
+
+    def test_codec_crc_bare_defaults(self):
+        # a crc<width> used without a variant suffix must resolve to that family's default ;
+        # width 16 and the crc-a family had no default and crashed with KeyError instead
+        from codext.checksums.crc import CRC
+        for n in CRC.keys():
+            name = "crc%d" % n if isinstance(n, int) else "crc"
+            expected = "%0{}x".format(round((n or 16)/4+.5)) % CRC[n][""][5]
+            self.assertEqual(codecs.encode("123456789", name), expected)
+            self.assertEqual(codecs.encode(b"123456789", name), b(expected))
+        # bare crc-16 is CRC-16/ARC (poly 0x8005), the same as its arc/ibm/lha aliases
+        for name in ["crc16", "crc-16", "crc_16", "crc16-arc", "crc16-ibm", "crc16-lha"]:
+            self.assertEqual(codecs.encode("123456789", name), "bb3d")
+        # bare crc is CRC-A, the same as the crca alias
+        self.assertEqual(codecs.encode("123456789", "crc"), "bf05")
+        self.assertEqual(codecs.encode("123456789", "crca"), "bf05")
+        # adding a default must not make an unknown variant resolve
+        self.assertRaises(LookupError, codecs.encode, "123456789", "crc16-bad")
+        self.assertRaises(LookupError, codecs.encode, "123456789", "crc-bad")
     
     def test_codec_dummy_str_manips(self):
         STR = "this is a test"

codext-1.16.4/src/codext/VERSION.txt

@@ -1 +0,0 @@
-1.16.4