diff options
author | Jeremiah Senkpiel <fishrock123@rocketmail.com> | 2022-07-09 18:02:44 -0700 |
---|---|---|
committer | GitHub <noreply@github.com> | 2022-07-09 20:02:44 -0500 |
commit | f26bdc9109abffc86ea78bb85cf3504a771d17ad (patch) | |
tree | dbd543924da72c713578f8cb28e6facebcf04e5d /src/de | |
parent | 3ddcd171ea66efa94821533299f48788a18fb33a (diff) |
feat: non-strict mode replaces invalid UTF-8 (#62)
This change makes non-strict mode percent-decode utf-8 lossily.
This means that invalid UTF-8 percent encoded sequences, such as `%E9`, are
decoded as the unicode replacement character (� `U+FFFD`).
Refs: https://github.com/samscott89/serde_qs/issues/43
Diffstat (limited to 'src/de')
-rw-r--r-- | src/de/parse.rs | 10 |
1 files changed, 9 insertions, 1 deletions
diff --git a/src/de/parse.rs b/src/de/parse.rs index 5c85b12..fe14bb4 100644 --- a/src/de/parse.rs +++ b/src/de/parse.rs @@ -242,8 +242,16 @@ impl<'a> Parser<'a> { /// present. fn collect_str(&mut self) -> Result<Cow<'a, str>> { let replaced = replace_plus(&self.inner[self.acc.0..self.acc.1 - 1]); + let decoder = percent_encoding::percent_decode(&replaced); + + let maybe_decoded = if self.strict { + decoder.decode_utf8()? + } else { + decoder.decode_utf8_lossy() + }; + let ret: Result<Cow<'a, str>> = - match percent_encoding::percent_decode(&replaced).decode_utf8()? { + match maybe_decoded { Cow::Borrowed(_) => { match replaced { Cow::Borrowed(_) => { |