Use source copies of base64, binascii and shutil

This commit is contained in:
Thomas Farstrike
2026-01-26 14:59:14 +01:00
parent 94d29d8202
commit c15256ba85
7 changed files with 894 additions and 3 deletions
+4 -3
View File
@@ -1,10 +1,11 @@
This /lib folder contains:
- mip.install('github:jonnor/micropython-zipfile')
- mip.install("shutil") for shutil.rmtree('/apps/com.example.files') # for rmtree()
- mip.install("aiohttp") # easy websockets
- mip.install("base64") # for nostr etc
- mip.install("collections") # used by aiohttp
- mip.install("unittest")
- mip.install("logging")
- mip.install("aiorepl")
- https://github.com/micropython/micropython-lib/blob/master/python-stdlib/logging/logging.py version 0.6.2 # for About app
- https://github.com/micropython/micropython-lib/blob/master/python-stdlib/base64/base64.py version 3.3.6 # for nostr
- https://github.com/micropython/micropython-lib/blob/master/python-stdlib/binascii/binascii.py version 2.4.1 # for base64.py
- https://github.com/micropython/micropython-lib/blob/master/python-stdlib/shutil/shutil.py version 0.0.5 # for rmtree()
Binary file not shown.
+480
View File
@@ -0,0 +1,480 @@
#! /usr/bin/env python3
"""RFC 3548: Base16, Base32, Base64 Data Encodings"""
# Modified 04-Oct-1995 by Jack Jansen to use binascii module
# Modified 30-Dec-2003 by Barry Warsaw to add full RFC 3548 support
# Modified 22-May-2007 by Guido van Rossum to use bytes everywhere
import re
import struct
import binascii
__all__ = [
# Legacy interface exports traditional RFC 1521 Base64 encodings
"encode",
"decode",
"encodebytes",
"decodebytes",
# Generalized interface for other encodings
"b64encode",
"b64decode",
"b32encode",
"b32decode",
"b16encode",
"b16decode",
# Standard Base64 encoding
"standard_b64encode",
"standard_b64decode",
# Some common Base64 alternatives. As referenced by RFC 3458, see thread
# starting at:
#
# http://zgp.org/pipermail/p2p-hackers/2001-September/000316.html
"urlsafe_b64encode",
"urlsafe_b64decode",
]
bytes_types = (bytes, bytearray) # Types acceptable as binary data
def _bytes_from_decode_data(s):
if isinstance(s, str):
try:
return s.encode("ascii")
# except UnicodeEncodeError:
except:
raise ValueError("string argument should contain only ASCII characters")
elif isinstance(s, bytes_types):
return s
else:
raise TypeError("argument should be bytes or ASCII string, not %s" % s.__class__.__name__)
def _maketrans(f, t):
"""Re-implement bytes.maketrans() as there is no such function in micropython"""
if len(f) != len(t):
raise ValueError("maketrans arguments must have same length")
translation_table = dict(zip(f, t))
return translation_table
def _translate(input_bytes, trans_table):
"""Re-implement bytes.translate() as there is no such function in micropython"""
result = bytearray()
for byte in input_bytes:
translated_byte = trans_table.get(byte, byte)
result.append(translated_byte)
return bytes(result)
# Base64 encoding/decoding uses binascii
def b64encode(s, altchars=None):
"""Encode a byte string using Base64.
s is the byte string to encode. Optional altchars must be a byte
string of length 2 which specifies an alternative alphabet for the
'+' and '/' characters. This allows an application to
e.g. generate url or filesystem safe Base64 strings.
The encoded byte string is returned.
"""
if not isinstance(s, bytes_types):
raise TypeError("expected bytes, not %s" % s.__class__.__name__)
# Strip off the trailing newline
encoded = binascii.b2a_base64(s)[:-1]
if altchars is not None:
if not isinstance(altchars, bytes_types):
raise TypeError("expected bytes, not %s" % altchars.__class__.__name__)
assert len(altchars) == 2, repr(altchars)
encoded = _translate(encoded, _maketrans(b"+/", altchars))
return encoded
def b64decode(s, altchars=None, validate=False):
"""Decode a Base64 encoded byte string.
s is the byte string to decode. Optional altchars must be a
string of length 2 which specifies the alternative alphabet used
instead of the '+' and '/' characters.
The decoded string is returned. A binascii.Error is raised if s is
incorrectly padded.
If validate is False (the default), non-base64-alphabet characters are
discarded prior to the padding check. If validate is True,
non-base64-alphabet characters in the input result in a binascii.Error.
"""
s = _bytes_from_decode_data(s)
if altchars is not None:
altchars = _bytes_from_decode_data(altchars)
assert len(altchars) == 2, repr(altchars)
s = _translate(s, _maketrans(altchars, b"+/"))
if validate and not re.match(b"^[A-Za-z0-9+/]*=*$", s):
raise binascii.Error("Non-base64 digit found")
return binascii.a2b_base64(s)
def standard_b64encode(s):
"""Encode a byte string using the standard Base64 alphabet.
s is the byte string to encode. The encoded byte string is returned.
"""
return b64encode(s)
def standard_b64decode(s):
"""Decode a byte string encoded with the standard Base64 alphabet.
s is the byte string to decode. The decoded byte string is
returned. binascii.Error is raised if the input is incorrectly
padded or if there are non-alphabet characters present in the
input.
"""
return b64decode(s)
# _urlsafe_encode_translation = _maketrans(b'+/', b'-_')
# _urlsafe_decode_translation = _maketrans(b'-_', b'+/')
def urlsafe_b64encode(s):
"""Encode a byte string using a url-safe Base64 alphabet.
s is the byte string to encode. The encoded byte string is
returned. The alphabet uses '-' instead of '+' and '_' instead of
'/'.
"""
# return b64encode(s).translate(_urlsafe_encode_translation)
return b64encode(s, b"-_").rstrip(b"\n")
def urlsafe_b64decode(s):
"""Decode a byte string encoded with the standard Base64 alphabet.
s is the byte string to decode. The decoded byte string is
returned. binascii.Error is raised if the input is incorrectly
padded or if there are non-alphabet characters present in the
input.
The alphabet uses '-' instead of '+' and '_' instead of '/'.
"""
# s = _bytes_from_decode_data(s)
# s = s.translate(_urlsafe_decode_translation)
# return b64decode(s)
raise NotImplementedError()
# Base32 encoding/decoding must be done in Python
_b32alphabet = {
0: b"A",
9: b"J",
18: b"S",
27: b"3",
1: b"B",
10: b"K",
19: b"T",
28: b"4",
2: b"C",
11: b"L",
20: b"U",
29: b"5",
3: b"D",
12: b"M",
21: b"V",
30: b"6",
4: b"E",
13: b"N",
22: b"W",
31: b"7",
5: b"F",
14: b"O",
23: b"X",
6: b"G",
15: b"P",
24: b"Y",
7: b"H",
16: b"Q",
25: b"Z",
8: b"I",
17: b"R",
26: b"2",
}
_b32tab = [v[0] for k, v in sorted(_b32alphabet.items())]
_b32rev = dict([(v[0], k) for k, v in _b32alphabet.items()])
def b32encode(s):
"""Encode a byte string using Base32.
s is the byte string to encode. The encoded byte string is returned.
"""
if not isinstance(s, bytes_types):
raise TypeError("expected bytes, not %s" % s.__class__.__name__)
quanta, leftover = divmod(len(s), 5)
# Pad the last quantum with zero bits if necessary
if leftover:
s = s + bytes(5 - leftover) # Don't use += !
quanta += 1
encoded = bytearray()
for i in range(quanta):
# c1 and c2 are 16 bits wide, c3 is 8 bits wide. The intent of this
# code is to process the 40 bits in units of 5 bits. So we take the 1
# leftover bit of c1 and tack it onto c2. Then we take the 2 leftover
# bits of c2 and tack them onto c3. The shifts and masks are intended
# to give us values of exactly 5 bits in width.
c1, c2, c3 = struct.unpack("!HHB", s[i * 5 : (i + 1) * 5])
c2 += (c1 & 1) << 16 # 17 bits wide
c3 += (c2 & 3) << 8 # 10 bits wide
encoded += bytes(
[
_b32tab[c1 >> 11], # bits 1 - 5
_b32tab[(c1 >> 6) & 0x1F], # bits 6 - 10
_b32tab[(c1 >> 1) & 0x1F], # bits 11 - 15
_b32tab[c2 >> 12], # bits 16 - 20 (1 - 5)
_b32tab[(c2 >> 7) & 0x1F], # bits 21 - 25 (6 - 10)
_b32tab[(c2 >> 2) & 0x1F], # bits 26 - 30 (11 - 15)
_b32tab[c3 >> 5], # bits 31 - 35 (1 - 5)
_b32tab[c3 & 0x1F], # bits 36 - 40 (1 - 5)
]
)
# Adjust for any leftover partial quanta
if leftover == 1:
encoded = encoded[:-6] + b"======"
elif leftover == 2:
encoded = encoded[:-4] + b"===="
elif leftover == 3:
encoded = encoded[:-3] + b"==="
elif leftover == 4:
encoded = encoded[:-1] + b"="
return bytes(encoded)
def b32decode(s, casefold=False, map01=None):
"""Decode a Base32 encoded byte string.
s is the byte string to decode. Optional casefold is a flag
specifying whether a lowercase alphabet is acceptable as input.
For security purposes, the default is False.
RFC 3548 allows for optional mapping of the digit 0 (zero) to the
letter O (oh), and for optional mapping of the digit 1 (one) to
either the letter I (eye) or letter L (el). The optional argument
map01 when not None, specifies which letter the digit 1 should be
mapped to (when map01 is not None, the digit 0 is always mapped to
the letter O). For security purposes the default is None, so that
0 and 1 are not allowed in the input.
The decoded byte string is returned. binascii.Error is raised if
the input is incorrectly padded or if there are non-alphabet
characters present in the input.
"""
s = _bytes_from_decode_data(s)
quanta, leftover = divmod(len(s), 8)
if leftover:
raise binascii.Error("Incorrect padding")
# Handle section 2.4 zero and one mapping. The flag map01 will be either
# False, or the character to map the digit 1 (one) to. It should be
# either L (el) or I (eye).
if map01 is not None:
map01 = _bytes_from_decode_data(map01)
assert len(map01) == 1, repr(map01)
s = _translate(s, _maketrans(b"01", b"O" + map01))
if casefold:
s = s.upper()
# Strip off pad characters from the right. We need to count the pad
# characters because this will tell us how many null bytes to remove from
# the end of the decoded string.
padchars = s.find(b"=")
if padchars > 0:
padchars = len(s) - padchars
s = s[:-padchars]
else:
padchars = 0
# Now decode the full quanta
parts = []
acc = 0
shift = 35
for c in s:
val = _b32rev.get(c)
if val is None:
raise binascii.Error("Non-base32 digit found")
acc += _b32rev[c] << shift
shift -= 5
if shift < 0:
parts.append(binascii.unhexlify(bytes("%010x" % acc, "ascii")))
acc = 0
shift = 35
# Process the last, partial quanta
last = binascii.unhexlify(bytes("%010x" % acc, "ascii"))
if padchars == 0:
last = b"" # No characters
elif padchars == 1:
last = last[:-1]
elif padchars == 3:
last = last[:-2]
elif padchars == 4:
last = last[:-3]
elif padchars == 6:
last = last[:-4]
else:
raise binascii.Error("Incorrect padding")
parts.append(last)
return b"".join(parts)
# RFC 3548, Base 16 Alphabet specifies uppercase, but hexlify() returns
# lowercase. The RFC also recommends against accepting input case
# insensitively.
def b16encode(s):
"""Encode a byte string using Base16.
s is the byte string to encode. The encoded byte string is returned.
"""
if not isinstance(s, bytes_types):
raise TypeError("expected bytes, not %s" % s.__class__.__name__)
return binascii.hexlify(s).upper()
def b16decode(s, casefold=False):
"""Decode a Base16 encoded byte string.
s is the byte string to decode. Optional casefold is a flag
specifying whether a lowercase alphabet is acceptable as input.
For security purposes, the default is False.
The decoded byte string is returned. binascii.Error is raised if
s were incorrectly padded or if there are non-alphabet characters
present in the string.
"""
s = _bytes_from_decode_data(s)
if casefold:
s = s.upper()
if re.search(b"[^0-9A-F]", s):
raise binascii.Error("Non-base16 digit found")
return binascii.unhexlify(s)
# Legacy interface. This code could be cleaned up since I don't believe
# binascii has any line length limitations. It just doesn't seem worth it
# though. The files should be opened in binary mode.
MAXLINESIZE = 76 # Excluding the CRLF
MAXBINSIZE = (MAXLINESIZE // 4) * 3
def encode(input, output):
"""Encode a file; input and output are binary files."""
while True:
s = input.read(MAXBINSIZE)
if not s:
break
while len(s) < MAXBINSIZE:
ns = input.read(MAXBINSIZE - len(s))
if not ns:
break
s += ns
line = binascii.b2a_base64(s)
output.write(line)
def decode(input, output):
"""Decode a file; input and output are binary files."""
while True:
line = input.readline()
if not line:
break
s = binascii.a2b_base64(line)
output.write(s)
def encodebytes(s):
"""Encode a bytestring into a bytestring containing multiple lines
of base-64 data."""
if not isinstance(s, bytes_types):
raise TypeError("expected bytes, not %s" % s.__class__.__name__)
pieces = []
for i in range(0, len(s), MAXBINSIZE):
chunk = s[i : i + MAXBINSIZE]
pieces.append(binascii.b2a_base64(chunk))
return b"".join(pieces)
def encodestring(s):
"""Legacy alias of encodebytes()."""
import warnings
warnings.warn("encodestring() is a deprecated alias, use encodebytes()", DeprecationWarning, 2)
return encodebytes(s)
def decodebytes(s):
"""Decode a bytestring of base-64 data into a bytestring."""
if not isinstance(s, bytes_types):
raise TypeError("expected bytes, not %s" % s.__class__.__name__)
return binascii.a2b_base64(s)
def decodestring(s):
"""Legacy alias of decodebytes()."""
import warnings
warnings.warn("decodestring() is a deprecated alias, use decodebytes()", DeprecationWarning, 2)
return decodebytes(s)
# Usable as a script...
def main():
"""Small main program"""
import sys, getopt
try:
opts, args = getopt.getopt(sys.argv[1:], "deut")
except getopt.error as msg:
sys.stdout = sys.stderr
print(msg)
print(
"""usage: %s [-d|-e|-u|-t] [file|-]
-d, -u: decode
-e: encode (default)
-t: encode and decode string 'Aladdin:open sesame'"""
% sys.argv[0]
)
sys.exit(2)
func = encode
for o, a in opts:
if o == "-e":
func = encode
if o == "-d":
func = decode
if o == "-u":
func = decode
if o == "-t":
test()
return
if args and args[0] != "-":
with open(args[0], "rb") as f:
func(f, sys.stdout.buffer)
else:
func(sys.stdin.buffer, sys.stdout.buffer)
def test():
s0 = b"Aladdin:open sesame"
print(repr(s0))
s1 = encodebytes(s0)
print(repr(s1))
s2 = decodebytes(s1)
print(repr(s2))
assert s0 == s2
if __name__ == "__main__":
main()
Binary file not shown.
+362
View File
@@ -0,0 +1,362 @@
from ubinascii import *
if not "unhexlify" in globals():
def unhexlify(data):
if len(data) % 2 != 0:
raise ValueError("Odd-length string")
return bytes([int(data[i : i + 2], 16) for i in range(0, len(data), 2)])
b2a_hex = hexlify
a2b_hex = unhexlify
# ____________________________________________________________
PAD = "="
table_a2b_base64 = [
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
62,
-1,
-1,
-1,
63,
52,
53,
54,
55,
56,
57,
58,
59,
60,
61,
-1,
-1,
-1,
-1,
-1,
-1, # Note PAD->-1 here
-1,
0,
1,
2,
3,
4,
5,
6,
7,
8,
9,
10,
11,
12,
13,
14,
15,
16,
17,
18,
19,
20,
21,
22,
23,
24,
25,
-1,
-1,
-1,
-1,
-1,
-1,
26,
27,
28,
29,
30,
31,
32,
33,
34,
35,
36,
37,
38,
39,
40,
41,
42,
43,
44,
45,
46,
47,
48,
49,
50,
51,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
-1,
]
def _transform(n):
if n == -1:
return "\xff"
else:
return chr(n)
table_a2b_base64 = "".join(map(_transform, table_a2b_base64))
assert len(table_a2b_base64) == 256
def a2b_base64(ascii):
"Decode a line of base64 data."
res = []
quad_pos = 0
leftchar = 0
leftbits = 0
last_char_was_a_pad = False
for c in ascii:
c = chr(c)
if c == PAD:
if quad_pos > 2 or (quad_pos == 2 and last_char_was_a_pad):
break # stop on 'xxx=' or on 'xx=='
last_char_was_a_pad = True
else:
n = ord(table_a2b_base64[ord(c)])
if n == 0xFF:
continue # ignore strange characters
#
# Shift it in on the low end, and see if there's
# a byte ready for output.
quad_pos = (quad_pos + 1) & 3
leftchar = (leftchar << 6) | n
leftbits += 6
#
if leftbits >= 8:
leftbits -= 8
res.append((leftchar >> leftbits).to_bytes(1, "big"))
leftchar &= (1 << leftbits) - 1
#
last_char_was_a_pad = False
else:
if leftbits != 0:
raise Exception("Incorrect padding")
return b"".join(res)
# ____________________________________________________________
table_b2a_base64 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
def b2a_base64(bin, newline=True):
"Base64-code line of data."
newlength = (len(bin) + 2) // 3
newlength = newlength * 4 + 1
res = []
leftchar = 0
leftbits = 0
for c in bin:
# Shift into our buffer, and output any 6bits ready
leftchar = (leftchar << 8) | c
leftbits += 8
res.append(table_b2a_base64[(leftchar >> (leftbits - 6)) & 0x3F])
leftbits -= 6
if leftbits >= 6:
res.append(table_b2a_base64[(leftchar >> (leftbits - 6)) & 0x3F])
leftbits -= 6
#
if leftbits == 2:
res.append(table_b2a_base64[(leftchar & 3) << 4])
res.append(PAD)
res.append(PAD)
elif leftbits == 4:
res.append(table_b2a_base64[(leftchar & 0xF) << 2])
res.append(PAD)
if newline:
res.append("\n")
return "".join(res).encode("ascii")
Binary file not shown.
+48
View File
@@ -0,0 +1,48 @@
# Reimplement, because CPython3.3 impl is rather bloated
import os
from collections import namedtuple
_ntuple_diskusage = namedtuple("usage", ("total", "used", "free"))
def rmtree(d):
if not d:
raise ValueError
for name, type, *_ in os.ilistdir(d):
path = d + "/" + name
if type & 0x4000: # dir
rmtree(path)
else: # file
os.unlink(path)
os.rmdir(d)
def copyfileobj(src, dest, length=512):
if hasattr(src, "readinto"):
buf = bytearray(length)
while True:
sz = src.readinto(buf)
if not sz:
break
if sz == length:
dest.write(buf)
else:
b = memoryview(buf)[:sz]
dest.write(b)
else:
while True:
buf = src.read(length)
if not buf:
break
dest.write(buf)
def disk_usage(path):
bit_tuple = os.statvfs(path)
blksize = bit_tuple[0] # system block size
total = bit_tuple[2] * blksize
free = bit_tuple[3] * blksize
used = total - free
return _ntuple_diskusage(total, used, free)