From: Tom Christie <tom@tomchristie.com>
Date: Mon, 28 Oct 2024 17:19:40 +0000 (+0000)
Subject: Merge branch 'master' into limit-supported-codecs
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=292cfe7c3fd9dfc9bc6c162b681fdfb4a5af8e0e;p=thirdparty%2Fhttpx.git

Merge branch 'master' into limit-supported-codecs
---

292cfe7c3fd9dfc9bc6c162b681fdfb4a5af8e0e
diff --cc httpx/_utils.py
index f95658b6,fcf4b64c..af89d8fc
--- a/httpx/_utils.py
+++ b/httpx/_utils.py
@@@ -25,57 -23,11 +23,57 @@@ _HTML5_FORM_ENCODING_RE = re.compile
      r"|".join([re.escape(c) for c in _HTML5_FORM_ENCODING_REPLACEMENTS.keys()])
  )
  
 +# For our supported text codecs, we start with the text codecs as supported by Chromium, Oct. 2023.
 +# https://chromium.googlesource.com/chromium/chromium/+/refs/heads/trunk/chrome/browser/character_encoding.cc#36
 +#
 +# Then limit them to only includec codecs which are documented as included by cpython.
 +# https://docs.python.org/3/library/codecs.html#standard-encodings
 +#
 +# We're referencing them with the canonical name as used by the Python codecs.
 +# The alias given in the chromium source is included as a comment for comparison.
 +SUPPORTED_CODECS = {
 +    "big5",  # big5
 +    "big5hkscs",  # big5-hkscs
 +    "cp1250",  # windows-1250
 +    "cp1251",  # windows-1251
 +    "cp1252",  # windows-1252
 +    "cp1253",  # windows-1253
 +    "cp1254",  # windows-1254
 +    "cp1255",  # windows-1255
 +    "cp1256",  # windows-1256
 +    "cp1257",  # windows-1257
 +    "cp1258",  # windows-1258
 +    "euc_jp",  # euc-jp
 +    "euc_kr",  # euc-kr
 +    "gb18030",  # gb18030
 +    "gbk",  # gbk
 +    "iso2022_jp",  # iso-2022-jp
 +    "iso8859-1",  # iso-8859-1
 +    "iso8859-2",  # iso-8859-2
 +    "iso8859-3",  # iso-8859-3
 +    "iso8859-4",  # iso-8859-4
 +    "iso8859-5",  # iso-8859-5
 +    "iso8859-6",  # iso-8859-6
 +    "iso8859-7",  # iso-8859-7
 +    "iso8859-8",  # iso-8859-8
 +    "iso8859-10",  # iso-8859-10
 +    "iso8859-13",  # iso-8859-13
 +    "iso8859-14",  # iso-8859-14
 +    "iso8859-15",  # iso-8859-15
 +    "iso8859-16",  # iso-8859-16
 +    "koi8-r",  # koi8-r
 +    "koi8-u",  # koi8-u
 +    "mac-roman",  # macintosh
 +    "shift_jis",  # shift-jis
 +    "utf-8",  # utf-8
 +    "utf-16-le",  # utf-16le
 +}
 +
  
  def normalize_header_key(
-     value: typing.Union[str, bytes],
+     value: str | bytes,
      lower: bool,
-     encoding: typing.Optional[str] = None,
+     encoding: str | None = None,
  ) -> bytes:
      """
      Coerce str/bytes into a strictly byte-wise HTTP header key.