rfc2047_decoder/decoder.rs
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307
use std::result;
use thiserror::Error;
use crate::{evaluator, lexer, parser};
/// The possible errors which can occur while parsing the string.
#[derive(Error, Debug, PartialEq)]
pub enum Error {
/// Symbolises that an error occured in the lexer.
#[error(transparent)]
Lexer(#[from] lexer::Error),
/// Symbolises that an error occured in the parser.
#[error(transparent)]
Parser(#[from] parser::Error),
/// Symbolises that an error occured in the evaluator.
#[error(transparent)]
Evaluator(#[from] evaluator::Error),
}
/// Determines which strategy should be used if an encoded word isn't encoded as
/// described in the RFC.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
pub enum RecoverStrategy {
/// Decode the encoded word although it's incorrectly encoded.
///
/// # Example
/// Take a look to [Decoder#RecoveryStrategy::Decode](Decoder#recoverstrategydecode).
Decode,
/// Skip the incorrectly encoded encoded word.
///
/// # Example
/// Take a look to [Decoder#RecoveryStrategy::Skip](Decoder#recoverstrategyskip).
Skip,
/// Abort the string-parsing and return an error.
///
/// # Example
/// Take a look to [Decoder#RecoveryStrategy::Abort](Decoder#recoverstrategyabort-default).
Abort,
}
type Result<T> = result::Result<T, Error>;
/// Represents the decoder builder.
///
/// # Example
/// ```
/// use rfc2047_decoder::{Decoder, RecoverStrategy};
///
/// let decoder = Decoder::new()
/// .too_long_encoded_word_strategy(RecoverStrategy::Skip);
/// let decoded_str = decoder.decode("=?UTF-8?B?c3Ry?=").unwrap();
///
/// assert_eq!(decoded_str, "str");
/// ```
#[derive(Debug, Clone, Eq, PartialEq)]
pub struct Decoder {
/// Determines which strategy should be used, if the parser encounters
/// encoded words which are longer than allowed in the RFC (it's longer than 75 chars).
pub too_long_encoded_word: RecoverStrategy,
}
impl Decoder {
/// Equals [Decoder::default].
pub fn new() -> Self {
Self::default()
}
/// Set the strategy if the decoder finds an encoded word which is too long.
///
/// # Examples
///
/// Each example uses the same encoded message:
/// ```txt
/// =?utf-8?B?TG9yZW0gaXBzdW0gZG9sb3Igc2l0IGFtZXQsIGNvbnNlY3RldHVyIGFkaXBpc2NpbmcgZWxpdC4gVXQgaW50ZXJkdW0gcXVhbSBldSBmYWNpbGlzaXMgb3JuYXJlLg==?=
/// ```
/// which exceeds the maximum length of 75 chars so it's actually invalid.
///
/// ## RecoverStrategy::Skip
/// Skips the invalid encoded word and parses it as clear text.
///
/// ```rust
/// use rfc2047_decoder::{Decoder, RecoverStrategy};
///
/// let message = "=?utf-8?B?TG9yZW0gaXBzdW0gZG9sb3Igc2l0IGFtZXQsIGNvbnNlY3RldHVyIGFkaXBpc2NpbmcgZWxpdC4gVXQgaW50ZXJkdW0gcXVhbSBldSBmYWNpbGlzaXMgb3JuYXJlLg==?=";
/// let decoder = Decoder::new()
/// .too_long_encoded_word_strategy(RecoverStrategy::Skip);
///
/// let parsed = decoder.decode(message).unwrap();
///
/// // nothing changed!
/// assert_eq!(parsed, message);
/// ```
///
/// ## RecoverStrategy::Decode
/// Although the encoded word is invalid, keep decoding it.
///
/// ```rust
/// use rfc2047_decoder::{Decoder, RecoverStrategy};
///
/// let message = "=?utf-8?B?TG9yZW0gaXBzdW0gZG9sb3Igc2l0IGFtZXQsIGNvbnNlY3RldHVyIGFkaXBpc2NpbmcgZWxpdC4gVXQgaW50ZXJkdW0gcXVhbSBldSBmYWNpbGlzaXMgb3JuYXJlLg==?=";
/// let decoder = Decoder::new()
/// .too_long_encoded_word_strategy(RecoverStrategy::Decode);
///
/// let parsed = decoder.decode(message).unwrap();
///
/// // could you decode it? ;)
/// let expected_result = "Lorem ipsum dolor sit amet, consectetur adipiscing elit. Ut interdum quam eu facilisis ornare.";
///
/// assert_eq!(parsed, expected_result);
/// ```
///
/// ## RecoverStrategy::Abort (default)
/// The parser will return an `Err` and collects all encoded words which are
/// too long. You can use them afterwards for error messages for example.
///
/// ```rust
/// use rfc2047_decoder::{Decoder, RecoverStrategy, Error::{self, Lexer}};
/// use rfc2047_decoder::LexerError::ParseEncodedWordTooLongError;
/// use rfc2047_decoder::TooLongEncodedWords;
///
/// let message = "=?utf-8?B?TG9yZW0gaXBzdW0gZG9sb3Igc2l0IGFtZXQsIGNvbnNlY3RldHVyIGFkaXBpc2NpbmcgZWxpdC4gVXQgaW50ZXJkdW0gcXVhbSBldSBmYWNpbGlzaXMgb3JuYXJlLg==?=";
/// // `RecoverStrategy::Abort` is the default strategy
/// let decoder = Decoder::new();
///
/// let parsed = decoder.decode(message);
///
/// assert_eq!(parsed, Err(Lexer(ParseEncodedWordTooLongError(TooLongEncodedWords(vec!["=?utf-8?B?TG9yZW0gaXBzdW0gZG9sb3Igc2l0IGFtZXQsIGNvbnNlY3RldHVyIGFkaXBpc2NpbmcgZWxpdC4gVXQgaW50ZXJkdW0gcXVhbSBldSBmYWNpbGlzaXMgb3JuYXJlLg==?=".to_string()])))));
/// ```
pub fn too_long_encoded_word_strategy(mut self, strategy: RecoverStrategy) -> Self {
self.too_long_encoded_word = strategy;
self
}
/// Decodes the given RFC 2047 MIME Message Header encoded string.
pub fn decode<T: AsRef<[u8]>>(self, encoded_str: T) -> Result<String> {
let text_tokens = lexer::run(encoded_str.as_ref(), self)?;
let parsed_text = parser::run(text_tokens)?;
let evaluated_string = evaluator::run(parsed_text)?;
Ok(evaluated_string)
}
}
impl Default for Decoder {
/// Returns the decoder with the following default "settings":
///
/// - `too_long_encoded_word`: [RecoverStrategy::Abort]
fn default() -> Self {
Self {
too_long_encoded_word: RecoverStrategy::Abort,
}
}
}
#[cfg(test)]
mod tests {
/// Here are the main-tests which are listed here:
/// https://datatracker.ietf.org/doc/html/rfc2047#section-8
/// Scroll down until you see the table.
mod rfc_tests {
use crate::decode;
#[test]
fn decode_encoded_word_single_char() {
assert_eq!(decode("=?ISO-8859-1?Q?a?=").unwrap(), "a");
}
#[test]
fn decode_encoded_word_separated_by_whitespace() {
assert_eq!(decode("=?ISO-8859-1?Q?a?= b").unwrap(), "a b");
}
#[test]
fn decode_two_encoded_chars() {
assert_eq!(
decode("=?ISO-8859-1?Q?a?= =?ISO-8859-1?Q?b?=").unwrap(),
"ab"
);
}
#[test]
fn whitespace_between_two_encoded_words_should_be_ignored() {
assert_eq!(
decode("=?ISO-8859-1?Q?a?= =?ISO-8859-1?Q?b?=").unwrap(),
"ab"
);
}
#[test]
fn whitespace_chars_between_two_encoded_words_should_be_ignored() {
assert_eq!(
decode(
"=?ISO-8859-1?Q?a?=
=?ISO-8859-1?Q?b?="
)
.unwrap(),
"ab"
);
}
#[test]
fn whitespace_encoded_in_encoded_word() {
assert_eq!(decode("=?ISO-8859-1?Q?a_b?=").unwrap(), "a b");
}
#[test]
fn ignore_whitespace_between_two_encoded_words_but_not_the_encoded_whitespace() {
assert_eq!(
decode("=?ISO-8859-1?Q?a?= =?ISO-8859-2?Q?_b?=").unwrap(),
"a b"
);
}
}
/// Those are some custom tests
mod custom_tests {
use crate::decode;
#[test]
fn clear_empty() {
assert_eq!(decode("").unwrap(), "");
}
#[test]
fn clear_with_spaces() {
assert_eq!(decode("str with spaces").unwrap(), "str with spaces");
}
#[test]
fn utf8_qs_empty() {
assert_eq!(decode("").unwrap(), "");
}
#[test]
fn utf8_qs_with_str() {
assert_eq!(decode("=?UTF-8?Q?str?=").unwrap(), "str");
}
#[test]
fn utf8_qs_with_spaces() {
assert_eq!(
decode("=?utf8?q?str_with_spaces?=").unwrap(),
"str with spaces"
);
}
#[test]
fn utf8_qs_with_spec_chars() {
assert_eq!(
decode("=?utf8?q?str_with_special_=C3=A7h=C3=A0r=C3=9F?=").unwrap(),
"str with special çhàrß"
);
}
#[test]
fn utf8_qs_double() {
assert_eq!(
decode("=?UTF-8?Q?str?=\r\n =?UTF-8?Q?str?=").unwrap(),
"strstr"
);
assert_eq!(
decode("=?UTF-8?Q?str?=\n =?UTF-8?Q?str?=").unwrap(),
"strstr"
);
assert_eq!(decode("=?UTF-8?Q?str?= =?UTF-8?Q?str?=").unwrap(), "strstr");
assert_eq!(decode("=?UTF-8?Q?str?==?UTF-8?Q?str?=").unwrap(), "strstr");
}
#[test]
fn utf8_b64_empty() {
assert_eq!(decode("=?UTF-8?B??=").unwrap(), "");
}
#[test]
fn utf8_b64_with_str() {
assert_eq!(decode("=?UTF-8?B?c3Ry?=").unwrap(), "str");
}
#[test]
fn utf8_b64_with_spaces() {
assert_eq!(
decode("=?utf8?b?c3RyIHdpdGggc3BhY2Vz?=").unwrap(),
"str with spaces"
);
}
#[test]
fn utf8_b64_with_spec_chars() {
assert_eq!(
decode("=?utf8?b?c3RyIHdpdGggc3BlY2lhbCDDp2jDoHLDnw==?=").unwrap(),
"str with special çhàrß"
);
}
#[test]
fn utf8_b64_trailing_bit() {
assert_eq!(
decode("=?utf-8?B?UG9ydGFsZSBIYWNraW5nVGVhbW==?=").unwrap(),
"Portale HackingTeam",
);
}
}
}