Update idna library 3.4 (37c7d9b) → 3.4 (cab054c).

CHANGES.md

@@ -5,6 +5,7 @@
 * Update CacheControl 0.12.11 (c05ef9e) to 0.13.1 (783a338)
 * Update feedparser 6.0.10 (859ac57) to 6.0.10 (9865dec)
 * Update filelock 3.12.0 (b4713c9) to 3.12.4 (c1163ae)
+* Update idna library 3.4 (37c7d9b) to 3.4 (cab054c)
 * Update Msgpack 1.0.5 (0516c2c) to 1.0.6 (e1d3d5d)
 * Update package resource API 67.5.1 (f51eccd) to 68.1.2 (1ef36f2)
 * Update soupsieve 2.3.2.post1 (792d566) to 2.4.1 (2e66beb)

lib/idna/codec.py

@@ -1,7 +1,7 @@
 from .core import encode, decode, alabel, ulabel, IDNAError
 import codecs
 import re
-from typing import Tuple, Optional
+from typing import Any, Tuple, Optional
 
 _unicode_dots_re = re.compile('[\u002e\u3002\uff0e\uff61]')
 
@@ -26,24 +26,24 @@ class Codec(codecs.Codec):
         return decode(data), len(data)
 
 class IncrementalEncoder(codecs.BufferedIncrementalEncoder):
-    def _buffer_encode(self, data: str, errors: str, final: bool) -> Tuple[str, int]:  # type: ignore
+    def _buffer_encode(self, data: str, errors: str, final: bool) -> Tuple[bytes, int]:
         if errors != 'strict':
             raise IDNAError('Unsupported error handling \"{}\"'.format(errors))
 
         if not data:
-            return "", 0
+            return b'', 0
 
         labels = _unicode_dots_re.split(data)
-        trailing_dot = ''
+        trailing_dot = b''
         if labels:
             if not labels[-1]:
-                trailing_dot = '.'
+                trailing_dot = b'.'
                 del labels[-1]
             elif not final:
                 # Keep potentially unfinished label until the next call
                 del labels[-1]
                 if labels:
-                    trailing_dot = '.'
+                    trailing_dot = b'.'
 
         result = []
         size = 0
@@ -54,18 +54,21 @@ class IncrementalEncoder(codecs.BufferedIncrementalEncoder):
             size += len(label)
 
         # Join with U+002E
-        result_str = '.'.join(result) + trailing_dot  # type: ignore
+        result_bytes = b'.'.join(result) + trailing_dot
         size += len(trailing_dot)
-        return result_str, size
+        return result_bytes, size
 
 class IncrementalDecoder(codecs.BufferedIncrementalDecoder):
-    def _buffer_decode(self, data: str, errors: str, final: bool) -> Tuple[str, int]:  # type: ignore
+    def _buffer_decode(self, data: Any, errors: str, final: bool) -> Tuple[str, int]:
         if errors != 'strict':
             raise IDNAError('Unsupported error handling \"{}\"'.format(errors))
 
         if not data:
             return ('', 0)
 
+        if not isinstance(data, str):
+            data = str(data, 'ascii')
+
         labels = _unicode_dots_re.split(data)
         trailing_dot = ''
         if labels:
@@ -99,13 +102,11 @@ class StreamReader(Codec, codecs.StreamReader):
     pass
 
 
-def getregentry(name: str) -> Optional[codecs.CodecInfo]:
-    if name != 'idna' and name != 'idna2008':
+def search_function(name: str) -> Optional[codecs.CodecInfo]:
+    if name != 'idna2008':
         return None
-
-    # Compatibility as a search_function for codecs.register()
     return codecs.CodecInfo(
-        name='idna2008',
+        name=name,
         encode=Codec().encode,  # type: ignore
         decode=Codec().decode,  # type: ignore
         incrementalencoder=IncrementalEncoder,
@@ -114,4 +115,4 @@ def getregentry(name: str) -> Optional[codecs.CodecInfo]:
         streamreader=StreamReader,
     )
 
-codecs.register(getregentry)
+codecs.register(search_function)

lib/idna/core.py

@@ -338,9 +338,9 @@ def uts46_remap(domain: str, std3_rules: bool = True, transitional: bool = False
 
 
 def encode(s: Union[str, bytes, bytearray], strict: bool = False, uts46: bool = False, std3_rules: bool = False, transitional: bool = False) -> bytes:
-    if isinstance(s, (bytes, bytearray)):
+    if not isinstance(s, str):
         try:
-            s = s.decode('ascii')
+            s = str(s, 'ascii')
         except UnicodeDecodeError:
             raise IDNAError('should pass a unicode string to the function rather than a byte string.')
     if uts46:
@@ -372,8 +372,8 @@ def encode(s: Union[str, bytes, bytearray], strict: bool = False, uts46: bool =
 
 def decode(s: Union[str, bytes, bytearray], strict: bool = False, uts46: bool = False, std3_rules: bool = False) -> str:
     try:
-        if isinstance(s, (bytes, bytearray)):
-            s = s.decode('ascii')
+        if not isinstance(s, str):
+            s = str(s, 'ascii')
     except UnicodeDecodeError:
         raise IDNAError('Invalid ASCII in A-label')
     if uts46:

lib/idna/idnadata.py

@@ -1834,7 +1834,6 @@ codepoint_classes = {
         0xa7d50000a7d6,
         0xa7d70000a7d8,
         0xa7d90000a7da,
-        0xa7f20000a7f5,
         0xa7f60000a7f8,
         0xa7fa0000a828,
         0xa82c0000a82d,
@@ -1907,9 +1906,7 @@ codepoint_classes = {
         0x1060000010737,
         0x1074000010756,
         0x1076000010768,
-        0x1078000010786,
-        0x10787000107b1,
-        0x107b2000107bb,
+        0x1078000010781,
         0x1080000010806,
         0x1080800010809,
         0x1080a00010836,