gh-101178: Add Ascii85, base85, and Z85 support to binascii

Doc/library/binascii.rst

@@ -77,6 +77,87 @@ The :mod:`binascii` module defines the following functions:
       Added the *newline* parameter.
 
 
+.. function:: a2b_ascii85(string, /, *, fold_spaces=False, wrap=False, ignore=b"")
+
+   Convert Ascii85 data back to binary and return the binary data.
+
+   Valid Ascii85 data contains characters from the Ascii85 alphabet in groups
+   of five (except for the final group, which may have from two to five
+   characters). Each group encodes 32 bits of binary data in the range from
+   ``0`` to ``2 ** 32 - 1``, inclusive. The special character ``z`` is
+   accepted as a short form of the group ``!!!!!``, which encodes four
+   consecutive null bytes.
+
+   If *fold_spaces* is true, the special character ``y`` is also accepted as a
+   short form of the group ``+<VdL``, which encodes four consecutive spaces.
+   Note that neither short form is permitted if it occurs in the middle of
+   another group.
+
+   If *wrap* is true, the input begins with ``<~`` and ends with ``~>``, as in
+   the Adobe Ascii85 format.
+
+   *ignore* is an optional bytes-like object that specifies characters to
+   ignore in the input.
+
+   Invalid Ascii85 data will raise :exc:`binascii.Error`.
+
+   .. versionadded:: next
+
+
+.. function:: b2a_ascii85(data, /, *, fold_spaces=False, wrap=False, width=0, pad=False)
+
+   Convert binary data to a formatted sequence of ASCII characters in Ascii85
+   coding. The return value is the converted data.
+
+   If *fold_spaces* is true, four consecutive spaces are encoded as the
+   special character ``y`` instead of the sequence ``+<VdL``.
+
+   If *wrap* is true, the output begins with ``<~`` and ends with ``~>``, as
+   in the Adobe Ascii85 format.
+
+   If *width* is provided and greater than 0, the output is split into lines
+   of no more than the specified width separated by the ASCII newline
+   character.
+
+   If *pad* is true, the input is padded to a multiple of 4 before encoding.
+
+   .. versionadded:: next
+
+
+.. function:: a2b_base85(string, /, *, strict_mode=False, z85=False)
+
+   Convert base85 data back to binary and return the binary data.
+   More than one line may be passed at a time.
+
+   If *strict_mode* is true, only valid base85 data will be converted.
+   Invalid base85 data will raise :exc:`binascii.Error`.
+
+   If *z85* is true, the base85 data uses the Z85 alphabet.
+   See `Z85 specification <https://rfc.zeromq.org/spec/32/>`_ for more information.
+
+   Valid base85 data contains characters from the base85 alphabet in groups
+   of five (except for the final group, which may have from two to five
+   characters). Each group encodes 32 bits of binary data in the range from
+   ``0`` to ``2 ** 32 - 1``, inclusive.
+
+   .. versionadded:: next
+
+
+.. function:: b2a_base85(data, /, *, pad=False, newline=True, z85=False)
+
+   Convert binary data to a line of ASCII characters in base85 coding.
+   The return value is the converted line.
+
+   If *pad* is true, the input is padded to a multiple of 4 before encoding.
+
+   If *newline* is true, a newline char is appended to the result.
+
+   If *z85* is true, the Z85 alphabet is used for conversion.
+   See `Z85 specification <https://rfc.zeromq.org/spec/32/>`_ for more information.
+
+   .. versionadded:: next
+
+
 .. function:: a2b_qp(data, header=False)
 
    Convert a block of quoted-printable data back to binary and return the binary

Include/internal/pycore_global_strings.h

@@ -480,6 +480,7 @@ struct _Py_global_strings {
         STRUCT_FOR_ID(flags)
         STRUCT_FOR_ID(flush)
         STRUCT_FOR_ID(fold)
+        STRUCT_FOR_ID(fold_spaces)
         STRUCT_FOR_ID(follow_symlinks)
         STRUCT_FOR_ID(format)
         STRUCT_FOR_ID(format_spec)
@@ -678,6 +679,7 @@ struct _Py_global_strings {
         STRUCT_FOR_ID(outpath)
         STRUCT_FOR_ID(overlapped)
         STRUCT_FOR_ID(owner)
+        STRUCT_FOR_ID(pad)
         STRUCT_FOR_ID(pages)
         STRUCT_FOR_ID(parameter)
         STRUCT_FOR_ID(parent)
@@ -864,11 +866,14 @@ struct _Py_global_strings {
         STRUCT_FOR_ID(weeks)
         STRUCT_FOR_ID(which)
         STRUCT_FOR_ID(who)
+        STRUCT_FOR_ID(width)
         STRUCT_FOR_ID(withdata)
+        STRUCT_FOR_ID(wrap)
         STRUCT_FOR_ID(writable)
         STRUCT_FOR_ID(write)
         STRUCT_FOR_ID(write_through)
         STRUCT_FOR_ID(year)
+        STRUCT_FOR_ID(z85)
         STRUCT_FOR_ID(zdict)
         STRUCT_FOR_ID(zstd_dict)
     } identifiers;

Lib/_base64.py

@@ -0,0 +1,79 @@
+"""C accelerator wrappers for originally pure-Python parts of base64."""
+
+from binascii import Error, a2b_ascii85, a2b_base85, b2a_ascii85, b2a_base85
+
+
+# Base 85 functions in base64 silently convert input to bytes.
+# Copy the conversion logic from base64 to avoid circular imports.
+
+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:
+            raise ValueError('string argument should contain only ASCII characters')
+    if isinstance(s, bytes_types):
+        return s
+    try:
+        return memoryview(s).tobytes()
+    except TypeError:
+        raise TypeError("argument should be a bytes-like object or ASCII "
+                        "string, not %r" % s.__class__.__name__) from None
+
+
+def _bytes_from_encode_data(b):
+    return b if isinstance(b, bytes_types) else memoryview(b).tobytes()
+
+
+# Functions in binascii raise binascii.Error instead of ValueError.
+
+def a85encode(b, *, foldspaces=False, wrapcol=0, pad=False, adobe=False):
+    b = _bytes_from_encode_data(b)
+    try:
+        return b2a_ascii85(b, fold_spaces=foldspaces,
+                           wrap=adobe, width=wrapcol, pad=pad)
+    except Error as e:
+        raise ValueError(e) from None
+
+
+def a85decode(b, *, foldspaces=False, adobe=False, ignorechars=b' \t\n\r\v'):
+    b = _bytes_from_decode_data(b)
+    try:
+        return a2b_ascii85(b, fold_spaces=foldspaces,
+                           wrap=adobe, ignore=ignorechars)
+    except Error as e:
+        raise ValueError(e) from None
+
+def b85encode(b, pad=False):
+    b = _bytes_from_encode_data(b)
+    try:
+        return b2a_base85(b, pad=pad, newline=False)
+    except Error as e:
+        raise ValueError(e) from None
+
+
+def b85decode(b):
+    b = _bytes_from_decode_data(b)
+    try:
+        return a2b_base85(b, strict_mode=True)
+    except Error as e:
+        raise ValueError(e) from None
+
+
+def z85encode(s, pad=False):
+    s = _bytes_from_encode_data(s)
+    try:
+        return b2a_base85(s, pad=pad, newline=False, z85=True)
+    except Error as e:
+        raise ValueError(e) from None
+
+
+def z85decode(s):
+    s = _bytes_from_decode_data(s)
+    try:
+        return a2b_base85(s, strict_mode=True, z85=True)
+    except Error as e:
+        raise ValueError(e) from None

Lib/base64.py

@@ -579,6 +579,26 @@ def decodebytes(s):
     return binascii.a2b_base64(s)
 
 
+# Use accelerated implementations of originally pure-Python parts if possible.
+try:
+    from _base64 import (a85encode as _a85encode, a85decode as _a85decode,
+                         b85encode as _b85encode, b85decode as _b85decode,
+                         z85encode as _z85encode, z85decode as _z85decode)
+    # Avoid expensive import of update_wrapper() from functools.
+    def _copy_attributes(func, src_func):
+        func.__doc__ = src_func.__doc__
+        func.__module__ = "base64"
+        return func
+    a85encode = _copy_attributes(_a85encode, a85encode)
+    a85decode = _copy_attributes(_a85decode, a85decode)
+    b85encode = _copy_attributes(_b85encode, b85encode)
+    b85decode = _copy_attributes(_b85decode, b85decode)
+    z85encode = _copy_attributes(_z85encode, z85encode)
+    z85decode = _copy_attributes(_z85decode, z85decode)
+except ImportError:
+    pass
+
+
 # Usable as a script...
 def main():
     """Small main program"""