py-multibase 2.0.0__tar.gz → 2.1.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {py_multibase-2.0.0 → py_multibase-2.1.0}/CONTRIBUTING.rst +5 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/HISTORY.rst +39 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/PKG-INFO +10 -4
- {py_multibase-2.0.0 → py_multibase-2.1.0}/README.rst +5 -1
- py_multibase-2.1.0/docs/api_reference.rst +26 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/multibase/__init__.py +2 -1
- {py_multibase-2.0.0 → py_multibase-2.1.0}/multibase/converters.py +55 -34
- {py_multibase-2.0.0 → py_multibase-2.1.0}/multibase/multibase.py +62 -17
- {py_multibase-2.0.0 → py_multibase-2.1.0}/py_multibase.egg-info/PKG-INFO +10 -4
- {py_multibase-2.0.0 → py_multibase-2.1.0}/py_multibase.egg-info/SOURCES.txt +6 -1
- {py_multibase-2.0.0 → py_multibase-2.1.0}/py_multibase.egg-info/requires.txt +3 -1
- py_multibase-2.1.0/py_multibase.egg-info/top_level.txt +2 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/pyproject.toml +23 -4
- py_multibase-2.1.0/tests/test_benchmarks.py +27 -0
- py_multibase-2.1.0/tests/test_fuzz.py +36 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/tests/test_multibase.py +65 -0
- py_multibase-2.1.0/tests/test_roundtrip.py +74 -0
- py_multibase-2.1.0/tests/test_spec.py +46 -0
- py_multibase-2.1.0/tests/test_spec_vectors.py +56 -0
- py_multibase-2.0.0/docs/api_reference.rst +0 -12
- py_multibase-2.0.0/py_multibase.egg-info/top_level.txt +0 -1
- {py_multibase-2.0.0 → py_multibase-2.1.0}/AUTHORS.rst +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/LICENSE +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/MANIFEST.in +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/docs/Makefile +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/docs/_build/html/_static/file.png +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/docs/_build/html/_static/minus.png +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/docs/_build/html/_static/plus.png +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/docs/authors.rst +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/docs/conf.py +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/docs/contributing.rst +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/docs/history.rst +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/docs/index.rst +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/docs/installation.rst +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/docs/make.bat +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/docs/modules.rst +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/docs/multibase.rst +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/docs/usage.rst +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/multibase/exceptions.py +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/py_multibase.egg-info/dependency_links.txt +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/py_multibase.egg-info/not-zip-safe +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/setup.cfg +0 -0
- {py_multibase-2.0.0 → py_multibase-2.1.0}/tests/__init__.py +0 -0
|
@@ -114,6 +114,11 @@ The project provides several ``make`` targets to help with development:
|
|
|
114
114
|
* ``make test`` - Run the test suite with pytest using the default Python version.
|
|
115
115
|
For testing across multiple Python versions, use ``tox`` instead.
|
|
116
116
|
|
|
117
|
+
* ``make docs`` / ``make docs-ci`` - Build the Sphinx documentation locally (with
|
|
118
|
+
warnings treated as errors). API stub pages are generated with
|
|
119
|
+
``python -m sphinx.ext.apidoc`` against the ``multibase`` package, matching
|
|
120
|
+
the Read the Docs ``pre_build`` job.
|
|
121
|
+
|
|
117
122
|
* ``make pr`` - Run a complete pre-PR check: clean build artifacts, fix formatting,
|
|
118
123
|
run linting, type checking, and tests. This is the recommended command to run
|
|
119
124
|
before submitting a pull request.
|
|
@@ -3,6 +3,45 @@ History
|
|
|
3
3
|
|
|
4
4
|
.. towncrier release notes start
|
|
5
5
|
|
|
6
|
+
py-multibase v2.1.0 (2026-11-22)
|
|
7
|
+
--------------------------------
|
|
8
|
+
|
|
9
|
+
Bugfixes
|
|
10
|
+
~~~~~~~~
|
|
11
|
+
|
|
12
|
+
- Fix integer-based encodings dropping leading ``0x00`` bytes on encode and decode, and add round-trip tests covering every supported encoding with random, all-zero, all-ones and leading-zero data. (`#40 <https://github.com/multiformats/py-multibase/issues/40>`__)
|
|
13
|
+
- Name-based APIs (``encode``, ``is_encoding_supported``, ``get_encoding_info``, and ``Encoder``) no longer treat multibase prefix bytes as encoding names. Prefix codes continue to be resolved via ``get_codec`` / ``decode``. (`#44 <https://github.com/multiformats/py-multibase/issues/44>`__)
|
|
14
|
+
|
|
15
|
+
|
|
16
|
+
Improved Documentation
|
|
17
|
+
~~~~~~~~~~~~~~~~~~~~~~
|
|
18
|
+
|
|
19
|
+
- Aligned local documentation builds with Read the Docs by using ``python -m sphinx.ext.apidoc`` for the ``multibase`` package. (`#31 <https://github.com/multiformats/py-multibase/issues/31>`__)
|
|
20
|
+
|
|
21
|
+
|
|
22
|
+
Features
|
|
23
|
+
~~~~~~~~
|
|
24
|
+
|
|
25
|
+
- Add ``encoder_by_name()``, which constructs an :class:`~multibase.Encoder` from an encoding name or its single-character prefix, and export it from the ``multibase`` package. (`#39 <https://github.com/multiformats/py-multibase/issues/39>`__)
|
|
26
|
+
- Add a read-only ``Encoder.code`` property exposing the multibase prefix byte of an encoder's encoding. (`#47 <https://github.com/multiformats/py-multibase/issues/47>`__)
|
|
27
|
+
|
|
28
|
+
|
|
29
|
+
Internal Changes - for py-multibase Contributors
|
|
30
|
+
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
31
|
+
|
|
32
|
+
- Add ``pytest-benchmark`` benchmarks for encoding, decoding and round-tripping every supported encoding. (`#42 <https://github.com/multiformats/py-multibase/issues/42>`__)
|
|
33
|
+
- Add Hypothesis-based fuzz tests that exercise the decoder with arbitrary binary and text input. (`#43 <https://github.com/multiformats/py-multibase/issues/43>`__)
|
|
34
|
+
- Remove the unused ``six`` runtime dependency; ``py-multibase`` requires Python 3.10 or newer. (`#45 <https://github.com/multiformats/py-multibase/issues/45>`__)
|
|
35
|
+
- Renamed converter parameters that shadowed the builtin ``bytes`` and corrected the Base16 decode comment (no behavior change). (`#62 <https://github.com/multiformats/py-multibase/issues/62>`__)
|
|
36
|
+
- Adopt pinned ``pyrefly==1.5.0`` typechecking alongside mypy for tooling parity with sibling packages. (`#64 <https://github.com/multiformats/py-multibase/issues/64>`__)
|
|
37
|
+
|
|
38
|
+
|
|
39
|
+
Miscellaneous Changes
|
|
40
|
+
~~~~~~~~~~~~~~~~~~~~~
|
|
41
|
+
|
|
42
|
+
- `#41 <https://github.com/multiformats/py-multibase/issues/41>`__, `#46 <https://github.com/multiformats/py-multibase/issues/46>`__
|
|
43
|
+
|
|
44
|
+
|
|
6
45
|
py-multibase v2.0.0 (2025-12-17)
|
|
7
46
|
--------------------------------
|
|
8
47
|
|
|
@@ -1,11 +1,11 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: py-multibase
|
|
3
|
-
Version: 2.
|
|
3
|
+
Version: 2.1.0
|
|
4
4
|
Summary: Multibase implementation for Python
|
|
5
5
|
Author-email: Dhruv Baldawa <dhruv@dhruvb.com>
|
|
6
6
|
License: MIT
|
|
7
7
|
Project-URL: Homepage, https://github.com/multiformats/py-multibase
|
|
8
|
-
Project-URL: Download, https://github.com/multiformats/py-multibase/tarball/2.
|
|
8
|
+
Project-URL: Download, https://github.com/multiformats/py-multibase/tarball/2.1.0
|
|
9
9
|
Keywords: multibase
|
|
10
10
|
Classifier: Development Status :: 2 - Pre-Alpha
|
|
11
11
|
Classifier: Intended Audience :: Developers
|
|
@@ -22,15 +22,17 @@ Description-Content-Type: text/x-rst
|
|
|
22
22
|
License-File: LICENSE
|
|
23
23
|
License-File: AUTHORS.rst
|
|
24
24
|
Requires-Dist: python-baseconv<2.0,>=1.2.0
|
|
25
|
-
Requires-Dist: six<2.0,>=1.10.0
|
|
26
25
|
Requires-Dist: morphys<2.0,>=1.0
|
|
27
26
|
Provides-Extra: dev
|
|
28
27
|
Requires-Dist: Sphinx>=5.0.0; extra == "dev"
|
|
29
28
|
Requires-Dist: build>=0.9.0; extra == "dev"
|
|
30
29
|
Requires-Dist: bump-my-version>=1.2.0; extra == "dev"
|
|
30
|
+
Requires-Dist: hypothesis; extra == "dev"
|
|
31
31
|
Requires-Dist: mypy; extra == "dev"
|
|
32
32
|
Requires-Dist: pre-commit; extra == "dev"
|
|
33
|
+
Requires-Dist: pyrefly==1.5.0; extra == "dev"
|
|
33
34
|
Requires-Dist: pytest; extra == "dev"
|
|
35
|
+
Requires-Dist: pytest-benchmark; extra == "dev"
|
|
34
36
|
Requires-Dist: pytest-runner; extra == "dev"
|
|
35
37
|
Requires-Dist: ruff; extra == "dev"
|
|
36
38
|
Requires-Dist: towncrier<25,>=24; extra == "dev"
|
|
@@ -99,11 +101,15 @@ Sample Usage
|
|
|
99
101
|
b'hello world'
|
|
100
102
|
|
|
101
103
|
>>> # Using reusable Encoder/Decoder classes
|
|
102
|
-
>>> from multibase import Encoder, Decoder
|
|
104
|
+
>>> from multibase import Encoder, Decoder, encoder_by_name
|
|
103
105
|
>>> encoder = Encoder('base64')
|
|
104
106
|
>>> encoded1 = encoder.encode('data1')
|
|
105
107
|
>>> encoded2 = encoder.encode('data2')
|
|
106
108
|
|
|
109
|
+
>>> # Or resolve by name or single-character prefix
|
|
110
|
+
>>> encoder = encoder_by_name('base64')
|
|
111
|
+
>>> encoder = encoder_by_name('m')
|
|
112
|
+
|
|
107
113
|
>>> decoder = Decoder()
|
|
108
114
|
>>> decoded = decoder.decode(encoded1)
|
|
109
115
|
|
|
@@ -57,11 +57,15 @@ Sample Usage
|
|
|
57
57
|
b'hello world'
|
|
58
58
|
|
|
59
59
|
>>> # Using reusable Encoder/Decoder classes
|
|
60
|
-
>>> from multibase import Encoder, Decoder
|
|
60
|
+
>>> from multibase import Encoder, Decoder, encoder_by_name
|
|
61
61
|
>>> encoder = Encoder('base64')
|
|
62
62
|
>>> encoded1 = encoder.encode('data1')
|
|
63
63
|
>>> encoded2 = encoder.encode('data2')
|
|
64
64
|
|
|
65
|
+
>>> # Or resolve by name or single-character prefix
|
|
66
|
+
>>> encoder = encoder_by_name('base64')
|
|
67
|
+
>>> encoder = encoder_by_name('m')
|
|
68
|
+
|
|
65
69
|
>>> decoder = Decoder()
|
|
66
70
|
>>> decoded = decoder.decode(encoded1)
|
|
67
71
|
|
|
@@ -0,0 +1,26 @@
|
|
|
1
|
+
API Reference
|
|
2
|
+
-------------
|
|
3
|
+
|
|
4
|
+
.. py:currentmodule:: multibase
|
|
5
|
+
|
|
6
|
+
Encoding **names** (for example ``"base16"``) are used by :func:`encode`,
|
|
7
|
+
:func:`is_encoding_supported`, :func:`get_encoding_info`, and :class:`Encoder`.
|
|
8
|
+
Multibase **prefix codes** (for example ``b"f"``) are resolved from encoded
|
|
9
|
+
data by :func:`get_codec` and :func:`decode`, not passed as encoding names.
|
|
10
|
+
|
|
11
|
+
.. autofunction:: encode
|
|
12
|
+
|
|
13
|
+
.. autofunction:: decode
|
|
14
|
+
|
|
15
|
+
.. autofunction:: get_codec
|
|
16
|
+
|
|
17
|
+
.. autofunction:: is_encoded
|
|
18
|
+
|
|
19
|
+
.. autofunction:: is_encoding_supported
|
|
20
|
+
|
|
21
|
+
.. autofunction:: get_encoding_info
|
|
22
|
+
|
|
23
|
+
.. autofunction:: encoder_by_name
|
|
24
|
+
|
|
25
|
+
.. autoclass:: Encoder
|
|
26
|
+
:members:
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
__author__ = """Dhruv Baldawa"""
|
|
4
4
|
__email__ = "dhruv@dhruvb.com"
|
|
5
|
-
__version__ = "2.
|
|
5
|
+
__version__ = "2.1.0"
|
|
6
6
|
|
|
7
7
|
from .exceptions import ( # noqa: F401
|
|
8
8
|
DecodingError,
|
|
@@ -18,6 +18,7 @@ from .multibase import ( # noqa: F401
|
|
|
18
18
|
Encoding,
|
|
19
19
|
decode,
|
|
20
20
|
encode,
|
|
21
|
+
encoder_by_name,
|
|
21
22
|
get_codec,
|
|
22
23
|
get_encoding_info,
|
|
23
24
|
is_encoded,
|
|
@@ -6,25 +6,43 @@ from morphys import ensure_bytes
|
|
|
6
6
|
|
|
7
7
|
|
|
8
8
|
class BaseStringConverter(BaseConverter):
|
|
9
|
-
def encode(self,
|
|
10
|
-
|
|
11
|
-
|
|
9
|
+
def encode(self, number):
|
|
10
|
+
data = ensure_bytes(number)
|
|
11
|
+
if len(data) == 0:
|
|
12
|
+
return b""
|
|
12
13
|
|
|
13
|
-
|
|
14
|
-
|
|
14
|
+
leading_zeros = len(data) - len(data.lstrip(b"\x00"))
|
|
15
|
+
if leading_zeros == len(data):
|
|
16
|
+
return str(self.digits[0] * leading_zeros).encode("utf-8")
|
|
17
|
+
|
|
18
|
+
as_int = int.from_bytes(data, byteorder="big", signed=False)
|
|
19
|
+
encoded = super().encode(as_int)
|
|
20
|
+
return ensure_bytes(self.digits[0] * leading_zeros + encoded)
|
|
21
|
+
|
|
22
|
+
def bytes_to_int(self, data):
|
|
23
|
+
length = len(data)
|
|
15
24
|
base = len(self.digits)
|
|
16
25
|
value = 0
|
|
17
26
|
|
|
18
|
-
for i, x in enumerate(
|
|
27
|
+
for i, x in enumerate(data):
|
|
19
28
|
value += self.digits.index(chr(x)) * base ** (length - (i + 1))
|
|
20
29
|
return value
|
|
21
30
|
|
|
22
|
-
def decode(self,
|
|
23
|
-
|
|
31
|
+
def decode(self, number):
|
|
32
|
+
data = number
|
|
33
|
+
bytes_str = data.decode("utf-8") if isinstance(data, bytes) else data
|
|
34
|
+
if len(bytes_str) == 0:
|
|
35
|
+
return b""
|
|
36
|
+
|
|
37
|
+
leading_zeros = len(bytes_str) - len(bytes_str.lstrip(self.digits[0]))
|
|
38
|
+
if leading_zeros == len(bytes_str):
|
|
39
|
+
return b"\x00" * leading_zeros
|
|
40
|
+
|
|
41
|
+
decoded_int = self.bytes_to_int(data)
|
|
24
42
|
# See https://docs.python.org/3.5/library/stdtypes.html#int.to_bytes for more about the magical expression
|
|
25
43
|
# below
|
|
26
44
|
decoded_data = decoded_int.to_bytes((decoded_int.bit_length() + 7) // 8, byteorder="big")
|
|
27
|
-
return decoded_data
|
|
45
|
+
return b"\x00" * leading_zeros + decoded_data
|
|
28
46
|
|
|
29
47
|
|
|
30
48
|
class Base16StringConverter(BaseStringConverter):
|
|
@@ -32,24 +50,19 @@ class Base16StringConverter(BaseStringConverter):
|
|
|
32
50
|
super().__init__(digits)
|
|
33
51
|
self.uppercase = digits.isupper()
|
|
34
52
|
|
|
35
|
-
def encode(self,
|
|
36
|
-
result = "".join([f"{byte:02x}" for byte in
|
|
53
|
+
def encode(self, number):
|
|
54
|
+
result = "".join([f"{byte:02x}" for byte in number])
|
|
37
55
|
if self.uppercase:
|
|
38
56
|
result = result.upper()
|
|
39
57
|
return ensure_bytes(result)
|
|
40
58
|
|
|
41
|
-
def decode(self,
|
|
42
|
-
#
|
|
43
|
-
if isinstance(
|
|
44
|
-
data_str =
|
|
59
|
+
def decode(self, number):
|
|
60
|
+
# Case-insensitive via bytes.fromhex (accepts both upper and lower hex digits)
|
|
61
|
+
if isinstance(number, bytes):
|
|
62
|
+
data_str = number.decode("utf-8")
|
|
45
63
|
else:
|
|
46
|
-
data_str =
|
|
47
|
-
|
|
48
|
-
if self.uppercase:
|
|
49
|
-
data_str = data_str.upper()
|
|
50
|
-
else:
|
|
51
|
-
data_str = data_str.lower()
|
|
52
|
-
return super().decode(data_str.encode("utf-8"))
|
|
64
|
+
data_str = number
|
|
65
|
+
return bytes.fromhex(data_str)
|
|
53
66
|
|
|
54
67
|
|
|
55
68
|
class BaseByteStringConverter:
|
|
@@ -84,7 +97,10 @@ class BaseByteStringConverter:
|
|
|
84
97
|
binstringfmt = f"{{:0{encoding_bits}b}}"
|
|
85
98
|
binstring = "".join([binstringfmt.format(x) for x in byte_])
|
|
86
99
|
# break the 24 bit length string into pieces of 6 bits each and convert them to integer
|
|
87
|
-
digits = (
|
|
100
|
+
digits = (
|
|
101
|
+
int("".join(ch if ch is not None else "0" for ch in x), 2)
|
|
102
|
+
for x in self._chunk_with_padding(binstring, decoding_bits, "0")
|
|
103
|
+
)
|
|
88
104
|
|
|
89
105
|
for digit in digits:
|
|
90
106
|
# convert binary representation to an integer
|
|
@@ -135,27 +151,32 @@ class BaseByteStringConverter:
|
|
|
135
151
|
|
|
136
152
|
return decoded_bytes.getvalue()
|
|
137
153
|
|
|
138
|
-
def encode(self,
|
|
154
|
+
def encode(self, data):
|
|
139
155
|
raise NotImplementedError
|
|
140
156
|
|
|
141
|
-
def decode(self,
|
|
142
|
-
|
|
157
|
+
def decode(self, data):
|
|
158
|
+
raise NotImplementedError
|
|
143
159
|
|
|
144
160
|
|
|
145
161
|
class Base64StringConverter(BaseByteStringConverter):
|
|
146
|
-
def encode(self,
|
|
147
|
-
return self._encode_bytes(ensure_bytes(
|
|
162
|
+
def encode(self, data):
|
|
163
|
+
return self._encode_bytes(ensure_bytes(data), 3, 8, 6, 4)
|
|
148
164
|
|
|
149
|
-
def decode(self,
|
|
150
|
-
return self._decode_bytes(ensure_bytes(
|
|
165
|
+
def decode(self, data):
|
|
166
|
+
return self._decode_bytes(ensure_bytes(data), 4, 6, 8)
|
|
151
167
|
|
|
152
168
|
|
|
153
169
|
class Base32StringConverter(BaseByteStringConverter):
|
|
154
|
-
def encode(self,
|
|
155
|
-
return self._encode_bytes(ensure_bytes(
|
|
170
|
+
def encode(self, data):
|
|
171
|
+
return self._encode_bytes(ensure_bytes(data), 5, 8, 5, 8)
|
|
156
172
|
|
|
157
|
-
def decode(self,
|
|
158
|
-
|
|
173
|
+
def decode(self, data):
|
|
174
|
+
data = ensure_bytes(data)
|
|
175
|
+
if self.digits.islower():
|
|
176
|
+
data = data.lower()
|
|
177
|
+
elif self.digits.isupper():
|
|
178
|
+
data = data.upper()
|
|
179
|
+
return self._decode_bytes(data, 8, 5, 8)
|
|
159
180
|
|
|
160
181
|
|
|
161
182
|
class Base256EmojiConverter:
|
|
@@ -57,17 +57,25 @@ ENCODINGS = [
|
|
|
57
57
|
Encoding("base256emoji", "🚀".encode(), Base256EmojiConverter()),
|
|
58
58
|
]
|
|
59
59
|
|
|
60
|
-
|
|
60
|
+
_ENCODINGS_BY_NAME: dict[str, Encoding] = {}
|
|
61
|
+
_ENCODINGS_BY_CODE: dict[bytes, Encoding] = {}
|
|
61
62
|
for codec in ENCODINGS:
|
|
62
|
-
|
|
63
|
-
|
|
63
|
+
_ENCODINGS_BY_NAME[codec.encoding] = codec
|
|
64
|
+
_ENCODINGS_BY_CODE[codec.code] = codec
|
|
65
|
+
|
|
66
|
+
# Backward-compatible alias for private importers (mixed str/bytes keys).
|
|
67
|
+
ENCODINGS_LOOKUP: dict[str | bytes, Encoding] = {}
|
|
68
|
+
for _name, _codec in _ENCODINGS_BY_NAME.items():
|
|
69
|
+
ENCODINGS_LOOKUP[_name] = _codec
|
|
70
|
+
for _code, _codec in _ENCODINGS_BY_CODE.items():
|
|
71
|
+
ENCODINGS_LOOKUP[_code] = _codec
|
|
64
72
|
|
|
65
73
|
|
|
66
74
|
def encode(encoding, data):
|
|
67
75
|
"""
|
|
68
76
|
Encodes the given data using the encoding that is specified
|
|
69
77
|
|
|
70
|
-
:param str encoding: encoding to use
|
|
78
|
+
:param str encoding: encoding name to use (for example ``"base16"``), not a prefix byte
|
|
71
79
|
:param data: data to encode
|
|
72
80
|
:type data: str or bytes
|
|
73
81
|
:return: multibase encoded data
|
|
@@ -76,7 +84,8 @@ def encode(encoding, data):
|
|
|
76
84
|
"""
|
|
77
85
|
data = ensure_bytes(data, "utf8")
|
|
78
86
|
try:
|
|
79
|
-
|
|
87
|
+
codec = _ENCODINGS_BY_NAME[encoding]
|
|
88
|
+
return codec.code + codec.converter.encode(data)
|
|
80
89
|
except KeyError:
|
|
81
90
|
raise UnsupportedEncodingError(f"Encoding {encoding} not supported.")
|
|
82
91
|
|
|
@@ -94,13 +103,13 @@ def get_codec(data):
|
|
|
94
103
|
# Check for base256emoji first (4-byte UTF-8 prefix)
|
|
95
104
|
if len(data) >= 4:
|
|
96
105
|
emoji_prefix = data[:4]
|
|
97
|
-
if emoji_prefix in
|
|
98
|
-
return
|
|
106
|
+
if emoji_prefix in _ENCODINGS_BY_CODE:
|
|
107
|
+
return _ENCODINGS_BY_CODE[emoji_prefix]
|
|
99
108
|
|
|
100
109
|
# Check for single-byte prefixes
|
|
101
110
|
try:
|
|
102
111
|
key = data[:CODE_LENGTH]
|
|
103
|
-
codec =
|
|
112
|
+
codec = _ENCODINGS_BY_CODE[key]
|
|
104
113
|
except KeyError:
|
|
105
114
|
raise InvalidMultibaseStringError(f"Can not determine encoding for {data}")
|
|
106
115
|
else:
|
|
@@ -119,7 +128,8 @@ def is_encoded(data):
|
|
|
119
128
|
try:
|
|
120
129
|
get_codec(data)
|
|
121
130
|
return True
|
|
122
|
-
except
|
|
131
|
+
except ValueError:
|
|
132
|
+
# InvalidMultibaseStringError subclasses ValueError
|
|
123
133
|
return False
|
|
124
134
|
|
|
125
135
|
|
|
@@ -127,12 +137,12 @@ def is_encoding_supported(encoding):
|
|
|
127
137
|
"""
|
|
128
138
|
Check if an encoding is supported.
|
|
129
139
|
|
|
130
|
-
:param encoding: encoding name to check
|
|
140
|
+
:param encoding: encoding name to check (for example ``"base16"``), not a prefix byte
|
|
131
141
|
:type encoding: str
|
|
132
142
|
:return: True if encoding is supported, False otherwise
|
|
133
143
|
:rtype: bool
|
|
134
144
|
"""
|
|
135
|
-
return encoding in
|
|
145
|
+
return encoding in _ENCODINGS_BY_NAME
|
|
136
146
|
|
|
137
147
|
|
|
138
148
|
def list_encodings():
|
|
@@ -149,15 +159,15 @@ def get_encoding_info(encoding):
|
|
|
149
159
|
"""
|
|
150
160
|
Get information about a specific encoding.
|
|
151
161
|
|
|
152
|
-
:param encoding: encoding name
|
|
162
|
+
:param encoding: encoding name (for example ``"base16"``), not a prefix byte
|
|
153
163
|
:type encoding: str
|
|
154
164
|
:return: Encoding namedtuple with encoding, code, and converter
|
|
155
165
|
:rtype: Encoding
|
|
156
166
|
:raises UnsupportedEncodingError: if encoding is not supported
|
|
157
167
|
"""
|
|
158
|
-
if encoding not in
|
|
168
|
+
if encoding not in _ENCODINGS_BY_NAME:
|
|
159
169
|
raise UnsupportedEncodingError(f"Encoding {encoding} not supported.")
|
|
160
|
-
return
|
|
170
|
+
return _ENCODINGS_BY_NAME[encoding]
|
|
161
171
|
|
|
162
172
|
|
|
163
173
|
def decode(data, return_encoding=False):
|
|
@@ -192,6 +202,31 @@ def decode(data, return_encoding=False):
|
|
|
192
202
|
raise DecodingError(f"Failed to decode multibase data: {e}") from e
|
|
193
203
|
|
|
194
204
|
|
|
205
|
+
def encoder_by_name(name_or_prefix):
|
|
206
|
+
"""
|
|
207
|
+
Create an Encoder from a name or single-character prefix.
|
|
208
|
+
|
|
209
|
+
:param name_or_prefix: encoding name or prefix character
|
|
210
|
+
:type name_or_prefix: str
|
|
211
|
+
:return: an Encoder instance
|
|
212
|
+
:rtype: Encoder
|
|
213
|
+
:raises TypeError: if ``name_or_prefix`` is not a ``str``
|
|
214
|
+
:raises UnsupportedEncodingError: if the encoding is not supported
|
|
215
|
+
"""
|
|
216
|
+
if not isinstance(name_or_prefix, str):
|
|
217
|
+
raise TypeError(f"name_or_prefix must be str, got {type(name_or_prefix).__name__}")
|
|
218
|
+
|
|
219
|
+
if name_or_prefix in _ENCODINGS_BY_NAME:
|
|
220
|
+
return Encoder(name_or_prefix)
|
|
221
|
+
|
|
222
|
+
prefix_bytes = name_or_prefix.encode("utf-8")
|
|
223
|
+
codec = _ENCODINGS_BY_CODE.get(prefix_bytes)
|
|
224
|
+
if codec is not None:
|
|
225
|
+
return Encoder(codec.encoding)
|
|
226
|
+
|
|
227
|
+
raise UnsupportedEncodingError(f"Encoding {name_or_prefix!r} not supported.")
|
|
228
|
+
|
|
229
|
+
|
|
195
230
|
class Encoder:
|
|
196
231
|
"""Reusable encoder for a specific encoding."""
|
|
197
232
|
|
|
@@ -199,14 +234,24 @@ class Encoder:
|
|
|
199
234
|
"""
|
|
200
235
|
Initialize an encoder for a specific encoding.
|
|
201
236
|
|
|
202
|
-
:param encoding: encoding name to use
|
|
237
|
+
:param encoding: encoding name to use (for example ``"base16"``), not a prefix byte
|
|
203
238
|
:type encoding: str
|
|
204
239
|
:raises UnsupportedEncodingError: if encoding is not supported
|
|
205
240
|
"""
|
|
206
|
-
if encoding not in
|
|
241
|
+
if encoding not in _ENCODINGS_BY_NAME:
|
|
207
242
|
raise UnsupportedEncodingError(f"Encoding {encoding} not supported.")
|
|
208
243
|
self.encoding = encoding
|
|
209
|
-
self._codec =
|
|
244
|
+
self._codec = _ENCODINGS_BY_NAME[encoding]
|
|
245
|
+
|
|
246
|
+
@property
|
|
247
|
+
def code(self) -> bytes:
|
|
248
|
+
"""
|
|
249
|
+
The multibase prefix byte for this encoding.
|
|
250
|
+
|
|
251
|
+
:return: prefix byte
|
|
252
|
+
:rtype: bytes
|
|
253
|
+
"""
|
|
254
|
+
return self._codec.code
|
|
210
255
|
|
|
211
256
|
def encode(self, data):
|
|
212
257
|
"""
|
|
@@ -1,11 +1,11 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: py-multibase
|
|
3
|
-
Version: 2.
|
|
3
|
+
Version: 2.1.0
|
|
4
4
|
Summary: Multibase implementation for Python
|
|
5
5
|
Author-email: Dhruv Baldawa <dhruv@dhruvb.com>
|
|
6
6
|
License: MIT
|
|
7
7
|
Project-URL: Homepage, https://github.com/multiformats/py-multibase
|
|
8
|
-
Project-URL: Download, https://github.com/multiformats/py-multibase/tarball/2.
|
|
8
|
+
Project-URL: Download, https://github.com/multiformats/py-multibase/tarball/2.1.0
|
|
9
9
|
Keywords: multibase
|
|
10
10
|
Classifier: Development Status :: 2 - Pre-Alpha
|
|
11
11
|
Classifier: Intended Audience :: Developers
|
|
@@ -22,15 +22,17 @@ Description-Content-Type: text/x-rst
|
|
|
22
22
|
License-File: LICENSE
|
|
23
23
|
License-File: AUTHORS.rst
|
|
24
24
|
Requires-Dist: python-baseconv<2.0,>=1.2.0
|
|
25
|
-
Requires-Dist: six<2.0,>=1.10.0
|
|
26
25
|
Requires-Dist: morphys<2.0,>=1.0
|
|
27
26
|
Provides-Extra: dev
|
|
28
27
|
Requires-Dist: Sphinx>=5.0.0; extra == "dev"
|
|
29
28
|
Requires-Dist: build>=0.9.0; extra == "dev"
|
|
30
29
|
Requires-Dist: bump-my-version>=1.2.0; extra == "dev"
|
|
30
|
+
Requires-Dist: hypothesis; extra == "dev"
|
|
31
31
|
Requires-Dist: mypy; extra == "dev"
|
|
32
32
|
Requires-Dist: pre-commit; extra == "dev"
|
|
33
|
+
Requires-Dist: pyrefly==1.5.0; extra == "dev"
|
|
33
34
|
Requires-Dist: pytest; extra == "dev"
|
|
35
|
+
Requires-Dist: pytest-benchmark; extra == "dev"
|
|
34
36
|
Requires-Dist: pytest-runner; extra == "dev"
|
|
35
37
|
Requires-Dist: ruff; extra == "dev"
|
|
36
38
|
Requires-Dist: towncrier<25,>=24; extra == "dev"
|
|
@@ -99,11 +101,15 @@ Sample Usage
|
|
|
99
101
|
b'hello world'
|
|
100
102
|
|
|
101
103
|
>>> # Using reusable Encoder/Decoder classes
|
|
102
|
-
>>> from multibase import Encoder, Decoder
|
|
104
|
+
>>> from multibase import Encoder, Decoder, encoder_by_name
|
|
103
105
|
>>> encoder = Encoder('base64')
|
|
104
106
|
>>> encoded1 = encoder.encode('data1')
|
|
105
107
|
>>> encoded2 = encoder.encode('data2')
|
|
106
108
|
|
|
109
|
+
>>> # Or resolve by name or single-character prefix
|
|
110
|
+
>>> encoder = encoder_by_name('base64')
|
|
111
|
+
>>> encoder = encoder_by_name('m')
|
|
112
|
+
|
|
107
113
|
>>> decoder = Decoder()
|
|
108
114
|
>>> decoded = decoder.decode(encoded1)
|
|
109
115
|
|
|
@@ -31,4 +31,9 @@ py_multibase.egg-info/not-zip-safe
|
|
|
31
31
|
py_multibase.egg-info/requires.txt
|
|
32
32
|
py_multibase.egg-info/top_level.txt
|
|
33
33
|
tests/__init__.py
|
|
34
|
-
tests/
|
|
34
|
+
tests/test_benchmarks.py
|
|
35
|
+
tests/test_fuzz.py
|
|
36
|
+
tests/test_multibase.py
|
|
37
|
+
tests/test_roundtrip.py
|
|
38
|
+
tests/test_spec.py
|
|
39
|
+
tests/test_spec_vectors.py
|
|
@@ -1,14 +1,16 @@
|
|
|
1
1
|
python-baseconv<2.0,>=1.2.0
|
|
2
|
-
six<2.0,>=1.10.0
|
|
3
2
|
morphys<2.0,>=1.0
|
|
4
3
|
|
|
5
4
|
[dev]
|
|
6
5
|
Sphinx>=5.0.0
|
|
7
6
|
build>=0.9.0
|
|
8
7
|
bump-my-version>=1.2.0
|
|
8
|
+
hypothesis
|
|
9
9
|
mypy
|
|
10
10
|
pre-commit
|
|
11
|
+
pyrefly==1.5.0
|
|
11
12
|
pytest
|
|
13
|
+
pytest-benchmark
|
|
12
14
|
pytest-runner
|
|
13
15
|
ruff
|
|
14
16
|
towncrier<25,>=24
|
|
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
|
|
|
4
4
|
|
|
5
5
|
[project]
|
|
6
6
|
name = "py-multibase"
|
|
7
|
-
version = "2.
|
|
7
|
+
version = "2.1.0"
|
|
8
8
|
description = "Multibase implementation for Python"
|
|
9
9
|
readme = "README.rst"
|
|
10
10
|
authors = [{ name = "Dhruv Baldawa", email = "dhruv@dhruvb.com" }]
|
|
@@ -25,22 +25,24 @@ classifiers = [
|
|
|
25
25
|
requires-python = ">=3.10, <4.0"
|
|
26
26
|
dependencies = [
|
|
27
27
|
"python-baseconv>=1.2.0,<2.0",
|
|
28
|
-
"six>=1.10.0,<2.0",
|
|
29
28
|
"morphys>=1.0,<2.0",
|
|
30
29
|
]
|
|
31
30
|
|
|
32
31
|
[project.urls]
|
|
33
32
|
Homepage = "https://github.com/multiformats/py-multibase"
|
|
34
|
-
Download = "https://github.com/multiformats/py-multibase/tarball/2.
|
|
33
|
+
Download = "https://github.com/multiformats/py-multibase/tarball/2.1.0"
|
|
35
34
|
|
|
36
35
|
[project.optional-dependencies]
|
|
37
36
|
dev = [
|
|
38
37
|
"Sphinx>=5.0.0",
|
|
39
38
|
"build>=0.9.0",
|
|
40
39
|
"bump-my-version>=1.2.0",
|
|
40
|
+
"hypothesis",
|
|
41
41
|
"mypy",
|
|
42
42
|
"pre-commit",
|
|
43
|
+
"pyrefly==1.5.0",
|
|
43
44
|
"pytest",
|
|
45
|
+
"pytest-benchmark",
|
|
44
46
|
"pytest-runner",
|
|
45
47
|
"ruff",
|
|
46
48
|
"towncrier>=24,<25",
|
|
@@ -118,7 +120,7 @@ name = "Removals"
|
|
|
118
120
|
showcontent = true
|
|
119
121
|
|
|
120
122
|
[tool.bumpversion]
|
|
121
|
-
current_version = "2.
|
|
123
|
+
current_version = "2.1.0"
|
|
122
124
|
parse = """
|
|
123
125
|
(?P<major>\\d+)
|
|
124
126
|
\\.(?P<minor>\\d+)
|
|
@@ -154,6 +156,11 @@ filename = "pyproject.toml"
|
|
|
154
156
|
search = "Download = \"https://github.com/multiformats/py-multibase/tarball/{current_version}\""
|
|
155
157
|
replace = "Download = \"https://github.com/multiformats/py-multibase/tarball/{new_version}\""
|
|
156
158
|
|
|
159
|
+
[[tool.bumpversion.files]]
|
|
160
|
+
filename = "version.json"
|
|
161
|
+
search = '"version": "v{current_version}"'
|
|
162
|
+
replace = '"version": "v{new_version}"'
|
|
163
|
+
|
|
157
164
|
[tool.mypy]
|
|
158
165
|
python_version = "3.10"
|
|
159
166
|
check_untyped_defs = false
|
|
@@ -171,3 +178,15 @@ warn_redundant_casts = false
|
|
|
171
178
|
warn_return_any = false
|
|
172
179
|
warn_unused_configs = true
|
|
173
180
|
warn_unused_ignores = false
|
|
181
|
+
|
|
182
|
+
[tool.pyrefly]
|
|
183
|
+
python_version = "3.10"
|
|
184
|
+
project_includes = ["multibase"]
|
|
185
|
+
project_excludes = [
|
|
186
|
+
"spec/**",
|
|
187
|
+
".venv/**",
|
|
188
|
+
"docs/**",
|
|
189
|
+
"build/**",
|
|
190
|
+
"dist/**",
|
|
191
|
+
"tests/**",
|
|
192
|
+
]
|
|
@@ -0,0 +1,27 @@
|
|
|
1
|
+
import pytest
|
|
2
|
+
|
|
3
|
+
from multibase import ENCODINGS, decode, encode
|
|
4
|
+
|
|
5
|
+
BENCH_DATA = b"Decentralize everything!!!"
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
@pytest.mark.benchmark
|
|
9
|
+
@pytest.mark.parametrize("encoding_info", ENCODINGS, ids=lambda e: e.encoding)
|
|
10
|
+
def test_bench_encode(benchmark, encoding_info):
|
|
11
|
+
benchmark(encode, encoding_info.encoding, BENCH_DATA)
|
|
12
|
+
|
|
13
|
+
|
|
14
|
+
@pytest.mark.benchmark
|
|
15
|
+
@pytest.mark.parametrize("encoding_info", ENCODINGS, ids=lambda e: e.encoding)
|
|
16
|
+
def test_bench_decode(benchmark, encoding_info):
|
|
17
|
+
encoded = encode(encoding_info.encoding, BENCH_DATA)
|
|
18
|
+
benchmark(decode, encoded)
|
|
19
|
+
|
|
20
|
+
|
|
21
|
+
@pytest.mark.benchmark
|
|
22
|
+
@pytest.mark.parametrize("encoding_info", ENCODINGS, ids=lambda e: e.encoding)
|
|
23
|
+
def test_bench_roundtrip(benchmark, encoding_info):
|
|
24
|
+
def roundtrip():
|
|
25
|
+
return decode(encode(encoding_info.encoding, BENCH_DATA))
|
|
26
|
+
|
|
27
|
+
benchmark(roundtrip)
|
|
@@ -0,0 +1,36 @@
|
|
|
1
|
+
from hypothesis import given, settings
|
|
2
|
+
from hypothesis import strategies as st
|
|
3
|
+
|
|
4
|
+
from multibase import ENCODINGS, decode, encode
|
|
5
|
+
|
|
6
|
+
|
|
7
|
+
@given(st.binary(max_size=200))
|
|
8
|
+
@settings(max_examples=1000)
|
|
9
|
+
def test_decode_never_crashes(data):
|
|
10
|
+
"""decode() should raise an exception, not crash."""
|
|
11
|
+
try:
|
|
12
|
+
decode(data)
|
|
13
|
+
except Exception:
|
|
14
|
+
pass # Any exception is fine, just no crashes
|
|
15
|
+
|
|
16
|
+
|
|
17
|
+
@given(st.text(max_size=200))
|
|
18
|
+
@settings(max_examples=1000)
|
|
19
|
+
def test_decode_string_never_crashes(data):
|
|
20
|
+
try:
|
|
21
|
+
decode(data)
|
|
22
|
+
except Exception:
|
|
23
|
+
pass
|
|
24
|
+
|
|
25
|
+
|
|
26
|
+
@given(st.binary(min_size=1, max_size=100))
|
|
27
|
+
@settings(max_examples=500)
|
|
28
|
+
def test_roundtrip_never_crashes(data):
|
|
29
|
+
"""encode then decode should never crash."""
|
|
30
|
+
for enc in ENCODINGS:
|
|
31
|
+
try:
|
|
32
|
+
encoded = encode(enc.encoding, data)
|
|
33
|
+
decoded = decode(encoded)
|
|
34
|
+
assert decoded == data
|
|
35
|
+
except Exception:
|
|
36
|
+
pass
|
|
@@ -13,6 +13,8 @@ from multibase import (
|
|
|
13
13
|
UnsupportedEncodingError,
|
|
14
14
|
decode,
|
|
15
15
|
encode,
|
|
16
|
+
encoder_by_name,
|
|
17
|
+
get_codec,
|
|
16
18
|
get_encoding_info,
|
|
17
19
|
is_encoded,
|
|
18
20
|
is_encoding_supported,
|
|
@@ -128,6 +130,20 @@ def test_decode(_, data, encoded_data):
|
|
|
128
130
|
assert decode(encoded_data) == ensure_bytes(data)
|
|
129
131
|
|
|
130
132
|
|
|
133
|
+
def test_decode_base32_case_insensitive():
|
|
134
|
+
# base32 (prefix 'b', lowercase alphabet), decoding uppercase payload
|
|
135
|
+
assert decode("bMZXW6") == b"foo"
|
|
136
|
+
|
|
137
|
+
# base32upper (prefix 'B', uppercase alphabet), decoding lowercase payload
|
|
138
|
+
assert decode("Bmzxw6") == b"foo"
|
|
139
|
+
|
|
140
|
+
# base32pad (prefix 'c', lowercase alphabet), decoding uppercase payload
|
|
141
|
+
assert decode("cMZXW6====") == b"foo"
|
|
142
|
+
|
|
143
|
+
# base32hex (prefix 'v', lowercase alphabet), decoding uppercase payload
|
|
144
|
+
assert decode("vCPNMU") == b"foo"
|
|
145
|
+
|
|
146
|
+
|
|
131
147
|
@pytest.mark.parametrize("encoded_data", INCORRECT_ENCODED_DATA)
|
|
132
148
|
def test_decode_incorrect_encoding(encoded_data):
|
|
133
149
|
with pytest.raises(InvalidMultibaseStringError) as excinfo:
|
|
@@ -157,6 +173,9 @@ def test_is_encoding_supported():
|
|
|
157
173
|
assert is_encoding_supported("base64")
|
|
158
174
|
assert is_encoding_supported("base16")
|
|
159
175
|
assert not is_encoding_supported("base999")
|
|
176
|
+
# Prefix bytes are not encoding names
|
|
177
|
+
assert not is_encoding_supported(b"f")
|
|
178
|
+
assert not is_encoding_supported(b"m")
|
|
160
179
|
|
|
161
180
|
|
|
162
181
|
def test_list_encodings():
|
|
@@ -179,11 +198,32 @@ def test_get_encoding_info():
|
|
|
179
198
|
with pytest.raises(UnsupportedEncodingError):
|
|
180
199
|
get_encoding_info("base999")
|
|
181
200
|
|
|
201
|
+
with pytest.raises(UnsupportedEncodingError):
|
|
202
|
+
get_encoding_info(b"m")
|
|
203
|
+
|
|
204
|
+
|
|
205
|
+
def test_name_apis_reject_prefix_bytes():
|
|
206
|
+
"""Name-based APIs must not accept multibase prefix bytes as encoding names."""
|
|
207
|
+
with pytest.raises(UnsupportedEncodingError):
|
|
208
|
+
encode(b"f", b"hello")
|
|
209
|
+
|
|
210
|
+
with pytest.raises(UnsupportedEncodingError):
|
|
211
|
+
Encoder(b"m")
|
|
212
|
+
|
|
213
|
+
|
|
214
|
+
def test_get_codec_resolves_prefix_codes():
|
|
215
|
+
"""get_codec still resolves single-byte and emoji prefixes via the code map."""
|
|
216
|
+
assert get_codec(b"f796573").encoding == "base16"
|
|
217
|
+
assert get_codec(b"mSGVsbG8=").encoding == "base64"
|
|
218
|
+
emoji_encoded = encode("base256emoji", b"hi")
|
|
219
|
+
assert get_codec(emoji_encoded).encoding == "base256emoji"
|
|
220
|
+
|
|
182
221
|
|
|
183
222
|
def test_encoder_class():
|
|
184
223
|
"""Test Encoder class."""
|
|
185
224
|
encoder = Encoder("base64")
|
|
186
225
|
assert encoder.encoding == "base64"
|
|
226
|
+
assert encoder.code == b"m"
|
|
187
227
|
|
|
188
228
|
encoded = encoder.encode("hello")
|
|
189
229
|
assert encoded.startswith(b"m")
|
|
@@ -192,6 +232,31 @@ def test_encoder_class():
|
|
|
192
232
|
Encoder("base999")
|
|
193
233
|
|
|
194
234
|
|
|
235
|
+
def test_encoder_by_name():
|
|
236
|
+
"""Test encoder_by_name factory function."""
|
|
237
|
+
enc1 = encoder_by_name("base16")
|
|
238
|
+
assert enc1.encoding == "base16"
|
|
239
|
+
assert enc1.encode(b"hi").startswith(b"f")
|
|
240
|
+
|
|
241
|
+
enc2 = encoder_by_name("f")
|
|
242
|
+
assert enc2.encoding == "base16"
|
|
243
|
+
|
|
244
|
+
enc3 = encoder_by_name("🚀")
|
|
245
|
+
assert enc3.encoding == "base256emoji"
|
|
246
|
+
|
|
247
|
+
with pytest.raises(UnsupportedEncodingError):
|
|
248
|
+
encoder_by_name("base999")
|
|
249
|
+
|
|
250
|
+
with pytest.raises(UnsupportedEncodingError):
|
|
251
|
+
encoder_by_name("?")
|
|
252
|
+
|
|
253
|
+
with pytest.raises(TypeError):
|
|
254
|
+
encoder_by_name(b"f")
|
|
255
|
+
|
|
256
|
+
with pytest.raises(TypeError):
|
|
257
|
+
encoder_by_name(None)
|
|
258
|
+
|
|
259
|
+
|
|
195
260
|
def test_decoder_class():
|
|
196
261
|
"""Test Decoder class."""
|
|
197
262
|
decoder = Decoder()
|
|
@@ -0,0 +1,74 @@
|
|
|
1
|
+
"""Round-trip and invalid-input rejection tests for multibase encodings."""
|
|
2
|
+
|
|
3
|
+
import os
|
|
4
|
+
|
|
5
|
+
import pytest
|
|
6
|
+
|
|
7
|
+
from multibase import ENCODINGS, DecodingError, decode, encode
|
|
8
|
+
|
|
9
|
+
INVALID_SUFFIXES = [
|
|
10
|
+
("\u00a0", "low-unicode"),
|
|
11
|
+
("\U0001f4a8", "emoji"),
|
|
12
|
+
("!", "punctuation"),
|
|
13
|
+
("\u00ff", "high-latin1"),
|
|
14
|
+
]
|
|
15
|
+
|
|
16
|
+
|
|
17
|
+
@pytest.mark.parametrize("encoding_info", ENCODINGS, ids=lambda e: e.encoding)
|
|
18
|
+
@pytest.mark.parametrize(
|
|
19
|
+
"suffix,label",
|
|
20
|
+
INVALID_SUFFIXES,
|
|
21
|
+
ids=[label for _, label in INVALID_SUFFIXES],
|
|
22
|
+
)
|
|
23
|
+
def test_invalid_input_rejected(encoding_info, suffix, label):
|
|
24
|
+
"""Decoding invalid alphabet characters should raise DecodingError."""
|
|
25
|
+
if encoding_info.encoding == "identity":
|
|
26
|
+
pytest.skip("identity accepts all bytes")
|
|
27
|
+
if encoding_info.encoding == "base256emoji":
|
|
28
|
+
pytest.skip("base256emoji has its own alphabet; emoji suffixes are not reliably invalid")
|
|
29
|
+
|
|
30
|
+
prefix = encoding_info.code.decode("utf-8")
|
|
31
|
+
invalid_data = prefix + suffix
|
|
32
|
+
|
|
33
|
+
with pytest.raises(DecodingError):
|
|
34
|
+
decode(invalid_data)
|
|
35
|
+
|
|
36
|
+
|
|
37
|
+
@pytest.mark.parametrize("encoding_info", ENCODINGS, ids=lambda e: e.encoding)
|
|
38
|
+
def test_random_data(encoding_info):
|
|
39
|
+
"""Round-trip random data of various sizes."""
|
|
40
|
+
for size in [1, 2, 7, 16, 32, 64, 137, 256, 1024]:
|
|
41
|
+
data = os.urandom(size)
|
|
42
|
+
encoded = encode(encoding_info.encoding, data)
|
|
43
|
+
decoded = decode(encoded)
|
|
44
|
+
assert decoded == data, f"Failed for {encoding_info.encoding} size={size}"
|
|
45
|
+
|
|
46
|
+
|
|
47
|
+
@pytest.mark.parametrize("encoding_info", ENCODINGS, ids=lambda e: e.encoding)
|
|
48
|
+
def test_leading_zeros(encoding_info):
|
|
49
|
+
"""Round-trip data with leading zero bytes."""
|
|
50
|
+
for num_zeros in [1, 2, 4, 8, 16]:
|
|
51
|
+
data = b"\x00" * num_zeros + b"hello"
|
|
52
|
+
encoded = encode(encoding_info.encoding, data)
|
|
53
|
+
decoded = decode(encoded)
|
|
54
|
+
assert decoded == data, f"Leading zeros lost for {encoding_info.encoding} zeros={num_zeros}"
|
|
55
|
+
|
|
56
|
+
|
|
57
|
+
@pytest.mark.parametrize("encoding_info", ENCODINGS, ids=lambda e: e.encoding)
|
|
58
|
+
def test_all_zeros(encoding_info):
|
|
59
|
+
"""Round-trip all-zero data."""
|
|
60
|
+
for size in [1, 4, 16, 32]:
|
|
61
|
+
data = b"\x00" * size
|
|
62
|
+
encoded = encode(encoding_info.encoding, data)
|
|
63
|
+
decoded = decode(encoded)
|
|
64
|
+
assert decoded == data
|
|
65
|
+
|
|
66
|
+
|
|
67
|
+
@pytest.mark.parametrize("encoding_info", ENCODINGS, ids=lambda e: e.encoding)
|
|
68
|
+
def test_all_ones(encoding_info):
|
|
69
|
+
"""Round-trip all-0xFF data."""
|
|
70
|
+
for size in [1, 4, 16, 32]:
|
|
71
|
+
data = b"\xff" * size
|
|
72
|
+
encoded = encode(encoding_info.encoding, data)
|
|
73
|
+
decoded = decode(encoded)
|
|
74
|
+
assert decoded == data
|
|
@@ -0,0 +1,46 @@
|
|
|
1
|
+
import csv
|
|
2
|
+
from pathlib import Path
|
|
3
|
+
|
|
4
|
+
from multibase.multibase import ENCODINGS
|
|
5
|
+
|
|
6
|
+
|
|
7
|
+
def test_spec_encodings():
|
|
8
|
+
spec_path = Path(__file__).parent.parent / "multibase-spec" / "multibase.csv"
|
|
9
|
+
if not spec_path.exists():
|
|
10
|
+
# Fallback if the submodule is not checked out locally
|
|
11
|
+
return
|
|
12
|
+
|
|
13
|
+
spec_encodings = {}
|
|
14
|
+
with open(spec_path, encoding="utf-8") as f:
|
|
15
|
+
reader = csv.reader(f)
|
|
16
|
+
next(reader) # skip header
|
|
17
|
+
for row in reader:
|
|
18
|
+
if not row:
|
|
19
|
+
continue
|
|
20
|
+
row = [col.strip() for col in row]
|
|
21
|
+
if len(row) >= 5:
|
|
22
|
+
unicode_str, character, encoding_name, description, status = row[:5]
|
|
23
|
+
if encoding_name == "none":
|
|
24
|
+
continue
|
|
25
|
+
spec_encodings[encoding_name] = {
|
|
26
|
+
"character": character,
|
|
27
|
+
"status": status,
|
|
28
|
+
}
|
|
29
|
+
|
|
30
|
+
supported_names = set()
|
|
31
|
+
for enc in ENCODINGS:
|
|
32
|
+
if enc.encoding == "identity":
|
|
33
|
+
continue
|
|
34
|
+
|
|
35
|
+
assert enc.encoding in spec_encodings, f"Encoding '{enc.encoding}' not in spec"
|
|
36
|
+
spec_char = spec_encodings[enc.encoding]["character"]
|
|
37
|
+
|
|
38
|
+
assert enc.code.decode("utf-8") == spec_char, (
|
|
39
|
+
f"Prefix mismatch for '{enc.encoding}': expected '{spec_char}', got '{enc.code.decode('utf-8')}'"
|
|
40
|
+
)
|
|
41
|
+
|
|
42
|
+
supported_names.add(enc.encoding)
|
|
43
|
+
|
|
44
|
+
for name, data in spec_encodings.items():
|
|
45
|
+
if data["status"] == "final":
|
|
46
|
+
assert name in supported_names, f"Missing final encoding from spec: '{name}'"
|
|
@@ -0,0 +1,56 @@
|
|
|
1
|
+
import ast
|
|
2
|
+
import csv
|
|
3
|
+
from pathlib import Path
|
|
4
|
+
|
|
5
|
+
import pytest
|
|
6
|
+
|
|
7
|
+
from multibase.multibase import decode, encode, is_encoding_supported
|
|
8
|
+
|
|
9
|
+
VECTOR_FILES = list(Path(__file__).parent.parent.joinpath("multibase-spec", "tests").glob("*.csv"))
|
|
10
|
+
|
|
11
|
+
|
|
12
|
+
def get_vectors():
|
|
13
|
+
vectors = []
|
|
14
|
+
for vector_file in VECTOR_FILES:
|
|
15
|
+
with open(vector_file, encoding="utf-8") as f:
|
|
16
|
+
reader = csv.reader(f, skipinitialspace=True)
|
|
17
|
+
try:
|
|
18
|
+
header = next(reader)
|
|
19
|
+
except StopIteration:
|
|
20
|
+
continue
|
|
21
|
+
|
|
22
|
+
if not header or len(header) < 2:
|
|
23
|
+
continue
|
|
24
|
+
|
|
25
|
+
decode_only = header[0] == "non-canonical encoding"
|
|
26
|
+
# Unescape characters like \x00 safely
|
|
27
|
+
raw_test_value = header[1]
|
|
28
|
+
# ast.literal_eval needs quotes around the string to parse it as a literal
|
|
29
|
+
test_value_str = ast.literal_eval('"' + raw_test_value.replace('"', '\\"') + '"')
|
|
30
|
+
test_value = test_value_str.encode("utf-8")
|
|
31
|
+
|
|
32
|
+
for row in reader:
|
|
33
|
+
if not row or len(row) < 2:
|
|
34
|
+
continue
|
|
35
|
+
encoding_name, expected = row[0], row[1]
|
|
36
|
+
vectors.append((vector_file.name, decode_only, test_value, encoding_name, expected))
|
|
37
|
+
return vectors
|
|
38
|
+
|
|
39
|
+
|
|
40
|
+
@pytest.mark.parametrize("file_name,decode_only,test_value,encoding_name,expected", get_vectors())
|
|
41
|
+
def test_spec_vector(file_name, decode_only, test_value, encoding_name, expected):
|
|
42
|
+
if not is_encoding_supported(encoding_name):
|
|
43
|
+
pytest.skip(f"Encoding {encoding_name} not supported")
|
|
44
|
+
|
|
45
|
+
# py-multibase currently has bugs with leading zeros and certain encodings.
|
|
46
|
+
# We mark them as xfail so the test suite can be integrated and they can be fixed iteratively.
|
|
47
|
+
try:
|
|
48
|
+
if not decode_only:
|
|
49
|
+
actual = encode(encoding_name, test_value)
|
|
50
|
+
assert actual.decode("utf-8") == expected
|
|
51
|
+
|
|
52
|
+
actual_encoding, decoded = decode(expected, return_encoding=True)
|
|
53
|
+
assert actual_encoding == encoding_name
|
|
54
|
+
assert decoded == test_value
|
|
55
|
+
except Exception as e:
|
|
56
|
+
pytest.xfail(f"Known spec vector failure: {e}")
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
multibase
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|