youtube_dl/casefold.py

@@ -1,20 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-from .compat import (
-    compat_str,
-    compat_chr,
-)
+from .compat import compat_str
 
-# Below is included the text of icu/CaseFolding.txt retrieved from
-# https://github.com/unicode-org/icu/blob/main/icu4c/source/data/unidata/CaseFolding.txt
-# In case newly foldable Unicode characters are defined, paste the new version
-# of the text inside the ''' marks.
-# The text is expected to have only blank lines andlines with 1st character #,
-# all ignored, and fold definitions like this:
-# `from_hex_code; space_separated_to_hex_code_list; comment`
-
-_map_str = '''
 # CaseFolding-15.0.0.txt
 # Date: 2022-02-02, 23:35:35 GMT
 # © 2022 Unicode®, Inc.
@@ -77,6 +65,7 @@ _map_str = '''
 #  have the value C for the status field, and the code point itself for the mapping field.
 
 # =================================================================
+_map_str = '''
 0041; C; 0061; # LATIN CAPITAL LETTER A
 0042; C; 0062; # LATIN CAPITAL LETTER B
 0043; C; 0063; # LATIN CAPITAL LETTER C
@@ -1638,22 +1627,17 @@ FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z
 1E920; C; 1E942; # ADLAM CAPITAL LETTER KPO
 1E921; C; 1E943; # ADLAM CAPITAL LETTER SHA
 '''
-
-_parse_unichr = lambda s: compat_chr(int(s, 16))
-
 _map = dict(
-    (_parse_unichr(from_), ''.join(map(_parse_unichr, to_.split(' '))))
+    (unichr(int(from_, 16)), ''.join((unichr(int(v, 16)) for v in to_.split(' '))))
     for from_, type_, to_, _ in (
-        l.split('; ', 3) for l in _map_str.splitlines() if l and not l[0] == '#')
+        l.split('; ', 3) for l in _map_str.splitlines() if l)
     if type_ in ('C', 'F'))
 del _map_str
 
-
 def casefold(s):
     assert isinstance(s, compat_str)
     return ''.join((_map.get(c, c) for c in s))
 
-
 __all__ = [
     casefold
 ]

youtube_dl/compat.py

@@ -21,19 +21,6 @@ import subprocess
 import sys
 import xml.etree.ElementTree
 
-# deal with critical unicode/str things first
-try:
-    # Python 2
-    compat_str, compat_basestring, compat_chr = (
-        unicode, basestring, unichr
-    )
-    from .casefold import casefold as compat_casefold
-except NameError:
-    compat_str, compat_basestring, compat_chr = (
-        str, str, chr
-    )
-    compat_casefold = lambda s: s.casefold()
-
 try:
     import collections.abc as compat_collections_abc
 except ImportError:
@@ -2386,6 +2373,13 @@ try:
 except ImportError:
     import BaseHTTPServer as compat_http_server
 
+try:
+    compat_str = unicode  # Python 2
+    from .casefold import casefold as compat_casefold
+except NameError:
+    compat_str = str
+    compat_casefold = lambda s: s.casefold()
+
 try:
     from urllib.parse import unquote_to_bytes as compat_urllib_parse_unquote_to_bytes
     from urllib.parse import unquote as compat_urllib_parse_unquote
@@ -2516,11 +2510,22 @@ except ImportError:  # Python < 3.4
 
             return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url)
 
+try:
+    compat_basestring = basestring  # Python 2
+except NameError:
+    compat_basestring = str
+
+try:
+    compat_chr = unichr  # Python 2
+except NameError:
+    compat_chr = chr
+
 try:
     from xml.etree.ElementTree import ParseError as compat_xml_parse_error
 except ImportError:  # Python 2.6
     from xml.parsers.expat import ExpatError as compat_xml_parse_error
 
+
 etree = xml.etree.ElementTree