xmpp-rs/parsers/src/util/text_node_codecs.rs
Jonas Schäfer 6ef8dbefa3 parsers: use Error type from xso
This is a large change and as such, it needs good motivation. Let me
remind you of the ultimate goal: we want a derive macro which allows us
to FromXml/IntoXml, and that derive macro should be usable from
`xmpp_parsers` and other crates.

For that, any code generated by the derive macro mustn't depend on any
code in the `xmpp_parsers` crate, because you cannot name the crate you
are in portably (`xmpp_parsers::..` wouldn't resolve within
`xmpp_parsers`, and `crate::..` would point at other crates if the macro
was used in other crates).

We also want to interoperate with code already implementing
`TryFrom<Element>` and `Into<Element>` on structs. This ultimately
requires that we have an error type which is shared by the two
implementations and that error type must be declared in the `xso` crate
to be usable by the macros.

Thus, we port the error type over to use the type declared in `xso`.

This changes the structure of the error type greatly; I do not think
that `xso` should have to know about all the different types we are
parsing there and they don't deserve special treatment. Wrapping them in
a `Box<dyn ..>` seems more appropriate.
2024-06-23 09:40:52 +02:00

234 lines
6.3 KiB
Rust
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

// Copyright (c) 2017 Emmanuel Gil Peyrot <linkmauve@linkmauve.fr>
//
// This Source Code Form is subject to the terms of the Mozilla Public
// License, v. 2.0. If a copy of the MPL was not distributed with this
// file, You can obtain one at http://mozilla.org/MPL/2.0/.
use base64::{engine::general_purpose::STANDARD as Base64Engine, Engine};
use jid::Jid;
use std::str::FromStr;
use xso::error::Error;
/// A trait for codecs that can decode and encode text nodes.
pub trait Codec {
type Decoded;
/// Decode the given string into the codecs output.
fn decode(s: &str) -> Result<Self::Decoded, Error>;
/// Encode the given value; return None to not produce a text node at all.
fn encode(decoded: &Self::Decoded) -> Option<String>;
}
/// Codec for text content.
pub struct Text;
impl Codec for Text {
type Decoded = String;
fn decode(s: &str) -> Result<String, Error> {
Ok(s.to_owned())
}
fn encode(decoded: &String) -> Option<String> {
Some(decoded.to_owned())
}
}
/// Codec transformer that makes the text optional; a "" string is decoded as None.
pub struct OptionalCodec<T: Codec>(std::marker::PhantomData<T>);
impl<T> Codec for OptionalCodec<T>
where
T: Codec,
{
type Decoded = Option<T::Decoded>;
fn decode(s: &str) -> Result<Option<T::Decoded>, Error> {
if s.is_empty() {
return Ok(None);
}
Ok(Some(T::decode(s)?))
}
fn encode(decoded: &Option<T::Decoded>) -> Option<String> {
decoded.as_ref().and_then(T::encode)
}
}
/// Codec that trims whitespace around the text.
pub struct Trimmed<T: Codec>(std::marker::PhantomData<T>);
impl<T> Codec for Trimmed<T>
where
T: Codec,
{
type Decoded = T::Decoded;
fn decode(s: &str) -> Result<T::Decoded, Error> {
match s.trim() {
// TODO: This error message can be a bit opaque when used
// in-context; ideally it'd be configurable.
"" => Err(Error::Other(
"The text in the element's text node was empty after trimming.",
)),
trimmed => T::decode(trimmed),
}
}
fn encode(decoded: &T::Decoded) -> Option<String> {
T::encode(decoded)
}
}
/// Codec wrapping that encodes/decodes a string as base64.
pub struct Base64;
impl Codec for Base64 {
type Decoded = Vec<u8>;
fn decode(s: &str) -> Result<Vec<u8>, Error> {
Base64Engine.decode(s).map_err(Error::text_parse_error)
}
fn encode(decoded: &Vec<u8>) -> Option<String> {
Some(Base64Engine.encode(decoded))
}
}
/// Codec wrapping base64 encode/decode, while ignoring whitespace characters.
pub struct WhitespaceAwareBase64;
impl Codec for WhitespaceAwareBase64 {
type Decoded = Vec<u8>;
fn decode(s: &str) -> Result<Self::Decoded, Error> {
let s: String = s
.chars()
.filter(|ch| *ch != ' ' && *ch != '\n' && *ch != '\t')
.collect();
Base64Engine.decode(s).map_err(Error::text_parse_error)
}
fn encode(decoded: &Self::Decoded) -> Option<String> {
Some(Base64Engine.encode(decoded))
}
}
/// Codec for bytes of lowercase hexadecimal, with a fixed length `N` (in bytes).
pub struct FixedHex<const N: usize>;
impl<const N: usize> Codec for FixedHex<N> {
type Decoded = [u8; N];
fn decode(s: &str) -> Result<Self::Decoded, Error> {
if s.len() != 2 * N {
return Err(Error::Other("Invalid length"));
}
let mut bytes = [0u8; N];
for i in 0..N {
bytes[i] =
u8::from_str_radix(&s[2 * i..2 * i + 2], 16).map_err(Error::text_parse_error)?;
}
Ok(bytes)
}
fn encode(decoded: &Self::Decoded) -> Option<String> {
let mut bytes = String::with_capacity(N * 2);
for byte in decoded {
bytes.extend(format!("{:02x}", byte).chars());
}
Some(bytes)
}
}
/// Codec for colon-separated bytes of uppercase hexadecimal.
pub struct ColonSeparatedHex;
impl Codec for ColonSeparatedHex {
type Decoded = Vec<u8>;
fn decode(s: &str) -> Result<Self::Decoded, Error> {
let mut bytes = vec![];
for i in 0..(1 + s.len()) / 3 {
let byte =
u8::from_str_radix(&s[3 * i..3 * i + 2], 16).map_err(Error::text_parse_error)?;
if 3 * i + 2 < s.len() {
assert_eq!(&s[3 * i + 2..3 * i + 3], ":");
}
bytes.push(byte);
}
Ok(bytes)
}
fn encode(decoded: &Self::Decoded) -> Option<String> {
let mut bytes = vec![];
for byte in decoded {
bytes.push(format!("{:02X}", byte));
}
Some(bytes.join(":"))
}
}
/// Codec for a JID.
pub struct JidCodec;
impl Codec for JidCodec {
type Decoded = Jid;
fn decode(s: &str) -> Result<Jid, Error> {
Jid::from_str(s).map_err(Error::text_parse_error)
}
fn encode(jid: &Jid) -> Option<String> {
Some(jid.to_string())
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn fixed_hex() {
let value = [0x01, 0xfe, 0xef];
// Test that we support both lowercase and uppercase as input.
let hex = FixedHex::<3>::decode("01feEF").unwrap();
assert_eq!(&hex, &value);
// Test that we do output lowercase.
let hex = FixedHex::<3>::encode(&value).unwrap();
assert_eq!(hex, "01feef");
// What if we give it a string that's too long?
let err = FixedHex::<3>::decode("01feEF01").unwrap_err();
assert_eq!(err.to_string(), "Invalid length");
// Too short?
let err = FixedHex::<3>::decode("01fe").unwrap_err();
assert_eq!(err.to_string(), "Invalid length");
// Not-even numbers?
let err = FixedHex::<3>::decode("01feE").unwrap_err();
assert_eq!(err.to_string(), "Invalid length");
// No colon supported.
let err = FixedHex::<3>::decode("0:f:EF").unwrap_err();
assert_eq!(
err.to_string(),
"text parse error: invalid digit found in string"
);
// No non-hex character allowed.
let err = FixedHex::<3>::decode("01defg").unwrap_err();
assert_eq!(
err.to_string(),
"text parse error: invalid digit found in string"
);
}
}