From d50ff5582240c7c9b4ca78c271e3e5cf927c1690 Mon Sep 17 00:00:00 2001
From: Padraic Fanning <fanninpm@miamioh.edu>
Date: Thu, 2 Sep 2021 21:27:45 -0400
Subject: [PATCH] Update encodings module to CPython 3.8

---
 Lib/encodings/__init__.py | 7 +++----
 Lib/encodings/aliases.py  | 3 +++
 Lib/encodings/punycode.py | 2 +-
 Lib/encodings/uu_codec.py | 4 ++++
 4 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/Lib/encodings/__init__.py b/Lib/encodings/__init__.py
index 86c282de5..ddd5afdcf 100644
--- a/Lib/encodings/__init__.py
+++ b/Lib/encodings/__init__.py
@@ -12,7 +12,7 @@
     * getregentry() -> codecs.CodecInfo object
     The getregentry() API must return a CodecInfo object with encoder, decoder,
     incrementalencoder, incrementaldecoder, streamwriter and streamreader
-    atttributes which adhere to the Python Codec Interface Standard.
+    attributes which adhere to the Python Codec Interface Standard.
 
     In addition, a module may optionally also define the following
     APIs which are then used by the package's codec search function:
@@ -49,8 +49,7 @@ def normalize_encoding(encoding):
         collapsed and replaced with a single underscore, e.g. '  -;#'
         becomes '_'. Leading and trailing underscores are removed.
 
-        Note that encoding names should be ASCII only; if they do use
-        non-ASCII characters, these must be Latin-1 compatible.
+        Note that encoding names should be ASCII only.
 
     """
     if isinstance(encoding, bytes):
@@ -58,7 +57,7 @@ def normalize_encoding(encoding):
 
     chars = []
     punct = False
-    for c in encoding.lower():
+    for c in encoding:
         if c.isalnum() or c == '.':
             if punct and chars:
                 chars.append('_')
diff --git a/Lib/encodings/aliases.py b/Lib/encodings/aliases.py
index 2e63c2f94..2444f9f17 100644
--- a/Lib/encodings/aliases.py
+++ b/Lib/encodings/aliases.py
@@ -266,6 +266,8 @@ aliases = {
     'roman8'             : 'hp_roman8',
     'r8'                 : 'hp_roman8',
     'csHPRoman8'         : 'hp_roman8',
+    'cp1051'             : 'hp_roman8',
+    'ibm1051'            : 'hp_roman8',
 
     # hz codec
     'hzgb'               : 'hz',
@@ -534,6 +536,7 @@ aliases = {
     'utf8'               : 'utf_8',
     'utf8_ucs2'          : 'utf_8',
     'utf8_ucs4'          : 'utf_8',
+    'cp65001'            : 'utf_8',
 
     # uu_codec codec
     'uu'                 : 'uu_codec',
diff --git a/Lib/encodings/punycode.py b/Lib/encodings/punycode.py
index 66c51013e..1c5726447 100644
--- a/Lib/encodings/punycode.py
+++ b/Lib/encodings/punycode.py
@@ -143,7 +143,7 @@ def decode_generalized_number(extended, extpos, bias, errors):
             digit = char - 22 # 0x30-26
         elif errors == "strict":
             raise UnicodeError("Invalid extended code point '%s'"
-                               % extended[extpos])
+                               % extended[extpos-1])
         else:
             return extpos, None
         t = T(j, bias)
diff --git a/Lib/encodings/uu_codec.py b/Lib/encodings/uu_codec.py
index 2a5728fb5..4e58c62fe 100644
--- a/Lib/encodings/uu_codec.py
+++ b/Lib/encodings/uu_codec.py
@@ -20,6 +20,10 @@ def uu_encode(input, errors='strict', filename='<data>', mode=0o666):
     read = infile.read
     write = outfile.write
 
+    # Remove newline chars from filename
+    filename = filename.replace('\n','\\n')
+    filename = filename.replace('\r','\\r')
+
     # Encode
     write(('begin %o %s\n' % (mode & 0o777, filename)).encode('ascii'))
     chunk = read(45)