util.stanza: Allow U+7F
Allowed by XML despite arguably being a control character.
Drops the part of the range meant to rule out octets invalid in UTF-8
(\247 starts a 4-byte sequence), since UTF-8 correctness is validated by
util.encodings.utf8.valid().
--- a/util/stanza.lua Mon Jan 24 13:58:04 2022 +0000
+++ b/util/stanza.lua Tue Nov 22 23:56:01 2022 +0100
@@ -45,8 +45,12 @@
local stanza_mt = { __name = "stanza" };
stanza_mt.__index = stanza_mt;
+-- Basic check for valid XML character data.
+-- Disallow control characters.
+-- Tab U+09 and newline U+0A are allowed.
+-- For attributes, allow the \1 separator between namespace and name.
local function valid_xml_cdata(str, attr)
- return not s_find(str, attr and "[^\1\9\10\13\20-~\128-\247]" or "[^\9\10\13\20-~\128-\247]");
+ return not s_find(str, attr and "[^\1\9\10\13\20-\255]" or "[^\9\10\13\20-\255]");
end
local function check_name(name, name_type)