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
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
use crate::engine::{general_purpose::STANDARD, DecodeEstimate, Engine};
#[cfg(any(feature = "alloc", feature = "std", test))]
use alloc::vec::Vec;
use core::fmt;
#[cfg(any(feature = "std", test))]
use std::error;

/// Errors that can occur while decoding.
#[derive(Clone, Debug, PartialEq, Eq)]
pub enum DecodeError {
    /// An invalid byte was found in the input. The offset and offending byte are provided.
    /// Padding characters (`=`) interspersed in the encoded form will be treated as invalid bytes.
    InvalidByte(usize, u8),
    /// The length of the input is invalid.
    /// A typical cause of this is stray trailing whitespace or other separator bytes.
    /// In the case where excess trailing bytes have produced an invalid length *and* the last byte
    /// is also an invalid base64 symbol (as would be the case for whitespace, etc), `InvalidByte`
    /// will be emitted instead of `InvalidLength` to make the issue easier to debug.
    InvalidLength,
    /// The last non-padding input symbol's encoded 6 bits have nonzero bits that will be discarded.
    /// This is indicative of corrupted or truncated Base64.
    /// Unlike `InvalidByte`, which reports symbols that aren't in the alphabet, this error is for
    /// symbols that are in the alphabet but represent nonsensical encodings.
    InvalidLastSymbol(usize, u8),
    /// The nature of the padding was not as configured: absent or incorrect when it must be
    /// canonical, or present when it must be absent, etc.
    InvalidPadding,
}

impl fmt::Display for DecodeError {
    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
        match *self {
            Self::InvalidByte(index, byte) => write!(f, "Invalid byte {}, offset {}.", byte, index),
            Self::InvalidLength => write!(f, "Encoded text cannot have a 6-bit remainder."),
            Self::InvalidLastSymbol(index, byte) => {
                write!(f, "Invalid last symbol {}, offset {}.", byte, index)
            }
            Self::InvalidPadding => write!(f, "Invalid padding"),
        }
    }
}

#[cfg(any(feature = "std", test))]
impl error::Error for DecodeError {
    fn cause(&self) -> Option<&dyn error::Error> {
        None
    }
}

/// Errors that can occur while decoding into a slice.
#[derive(Clone, Debug, PartialEq, Eq)]
pub enum DecodeSliceError {
    /// A [DecodeError] occurred
    DecodeError(DecodeError),
    /// The provided slice _may_ be too small.
    ///
    /// The check is conservative (assumes the last triplet of output bytes will all be needed).
    OutputSliceTooSmall,
}

impl fmt::Display for DecodeSliceError {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        match self {
            Self::DecodeError(e) => write!(f, "DecodeError: {}", e),
            Self::OutputSliceTooSmall => write!(f, "Output slice too small"),
        }
    }
}

#[cfg(any(feature = "std", test))]
impl error::Error for DecodeSliceError {
    fn cause(&self) -> Option<&dyn error::Error> {
        match self {
            DecodeSliceError::DecodeError(e) => Some(e),
            DecodeSliceError::OutputSliceTooSmall => None,
        }
    }
}

impl From<DecodeError> for DecodeSliceError {
    fn from(e: DecodeError) -> Self {
        DecodeSliceError::DecodeError(e)
    }
}

/// Decode base64 using the [`STANDARD` engine](STANDARD).
///
/// See [Engine::decode].
#[deprecated(since = "0.21.0", note = "Use Engine::decode")]
#[cfg(any(feature = "alloc", feature = "std", test))]
pub fn decode<T: AsRef<[u8]>>(input: T) -> Result<Vec<u8>, DecodeError> {
    STANDARD.decode(input)
}

/// Decode from string reference as octets using the specified [Engine].
///
/// See [Engine::decode].
///Returns a `Result` containing a `Vec<u8>`.
#[deprecated(since = "0.21.0", note = "Use Engine::decode")]
#[cfg(any(feature = "alloc", feature = "std", test))]
pub fn decode_engine<E: Engine, T: AsRef<[u8]>>(
    input: T,
    engine: &E,
) -> Result<Vec<u8>, DecodeError> {
    engine.decode(input)
}

/// Decode from string reference as octets.
///
/// See [Engine::decode_vec].
#[cfg(any(feature = "alloc", feature = "std", test))]
#[deprecated(since = "0.21.0", note = "Use Engine::decode_vec")]
pub fn decode_engine_vec<E: Engine, T: AsRef<[u8]>>(
    input: T,
    buffer: &mut Vec<u8>,
    engine: &E,
) -> Result<(), DecodeError> {
    engine.decode_vec(input, buffer)
}

/// Decode the input into the provided output slice.
///
/// See [Engine::decode_slice].
#[deprecated(since = "0.21.0", note = "Use Engine::decode_slice")]
pub fn decode_engine_slice<E: Engine, T: AsRef<[u8]>>(
    input: T,
    output: &mut [u8],
    engine: &E,
) -> Result<usize, DecodeSliceError> {
    engine.decode_slice(input, output)
}

/// Returns a conservative estimate of the decoded size of `encoded_len` base64 symbols (rounded up
/// to the next group of 3 decoded bytes).
///
/// The resulting length will be a safe choice for the size of a decode buffer, but may have up to
/// 2 trailing bytes that won't end up being needed.
///
/// # Examples
///
/// ```
/// use base64::decoded_len_estimate;
///
/// assert_eq!(3, decoded_len_estimate(1));
/// assert_eq!(3, decoded_len_estimate(2));
/// assert_eq!(3, decoded_len_estimate(3));
/// assert_eq!(3, decoded_len_estimate(4));
/// // start of the next quad of encoded symbols
/// assert_eq!(6, decoded_len_estimate(5));
/// ```
pub fn decoded_len_estimate(encoded_len: usize) -> usize {
    STANDARD
        .internal_decoded_len_estimate(encoded_len)
        .decoded_len_estimate()
}

#[cfg(test)]
mod tests {
    use super::*;
    use crate::{
        alphabet,
        engine::{general_purpose, Config, GeneralPurpose},
        tests::{assert_encode_sanity, random_engine},
    };
    use rand::{
        distributions::{Distribution, Uniform},
        Rng, SeedableRng,
    };

    #[test]
    fn decode_into_nonempty_vec_doesnt_clobber_existing_prefix() {
        let mut orig_data = Vec::new();
        let mut encoded_data = String::new();
        let mut decoded_with_prefix = Vec::new();
        let mut decoded_without_prefix = Vec::new();
        let mut prefix = Vec::new();

        let prefix_len_range = Uniform::new(0, 1000);
        let input_len_range = Uniform::new(0, 1000);

        let mut rng = rand::rngs::SmallRng::from_entropy();

        for _ in 0..10_000 {
            orig_data.clear();
            encoded_data.clear();
            decoded_with_prefix.clear();
            decoded_without_prefix.clear();
            prefix.clear();

            let input_len = input_len_range.sample(&mut rng);

            for _ in 0..input_len {
                orig_data.push(rng.gen());
            }

            let engine = random_engine(&mut rng);
            engine.encode_string(&orig_data, &mut encoded_data);
            assert_encode_sanity(&encoded_data, engine.config().encode_padding(), input_len);

            let prefix_len = prefix_len_range.sample(&mut rng);

            // fill the buf with a prefix
            for _ in 0..prefix_len {
                prefix.push(rng.gen());
            }

            decoded_with_prefix.resize(prefix_len, 0);
            decoded_with_prefix.copy_from_slice(&prefix);

            // decode into the non-empty buf
            engine
                .decode_vec(&encoded_data, &mut decoded_with_prefix)
                .unwrap();
            // also decode into the empty buf
            engine
                .decode_vec(&encoded_data, &mut decoded_without_prefix)
                .unwrap();

            assert_eq!(
                prefix_len + decoded_without_prefix.len(),
                decoded_with_prefix.len()
            );
            assert_eq!(orig_data, decoded_without_prefix);

            // append plain decode onto prefix
            prefix.append(&mut decoded_without_prefix);

            assert_eq!(prefix, decoded_with_prefix);
        }
    }

    #[test]
    fn decode_slice_doesnt_clobber_existing_prefix_or_suffix() {
        do_decode_slice_doesnt_clobber_existing_prefix_or_suffix(|e, input, output| {
            e.decode_slice(input, output).unwrap()
        })
    }

    #[test]
    fn decode_slice_unchecked_doesnt_clobber_existing_prefix_or_suffix() {
        do_decode_slice_doesnt_clobber_existing_prefix_or_suffix(|e, input, output| {
            e.decode_slice_unchecked(input, output).unwrap()
        })
    }

    #[test]
    fn decode_engine_estimation_works_for_various_lengths() {
        let engine = GeneralPurpose::new(&alphabet::STANDARD, general_purpose::NO_PAD);
        for num_prefix_quads in 0..100 {
            for suffix in &["AA", "AAA", "AAAA"] {
                let mut prefix = "AAAA".repeat(num_prefix_quads);
                prefix.push_str(suffix);
                // make sure no overflow (and thus a panic) occurs
                let res = engine.decode(prefix);
                assert!(res.is_ok());
            }
        }
    }

    #[test]
    fn decode_slice_output_length_errors() {
        for num_quads in 1..100 {
            let input = "AAAA".repeat(num_quads);
            let mut vec = vec![0; (num_quads - 1) * 3];
            assert_eq!(
                DecodeSliceError::OutputSliceTooSmall,
                STANDARD.decode_slice(&input, &mut vec).unwrap_err()
            );
            vec.push(0);
            assert_eq!(
                DecodeSliceError::OutputSliceTooSmall,
                STANDARD.decode_slice(&input, &mut vec).unwrap_err()
            );
            vec.push(0);
            assert_eq!(
                DecodeSliceError::OutputSliceTooSmall,
                STANDARD.decode_slice(&input, &mut vec).unwrap_err()
            );
            vec.push(0);
            // now it works
            assert_eq!(
                num_quads * 3,
                STANDARD.decode_slice(&input, &mut vec).unwrap()
            );
        }
    }

    fn do_decode_slice_doesnt_clobber_existing_prefix_or_suffix<
        F: Fn(&GeneralPurpose, &[u8], &mut [u8]) -> usize,
    >(
        call_decode: F,
    ) {
        let mut orig_data = Vec::new();
        let mut encoded_data = String::new();
        let mut decode_buf = Vec::new();
        let mut decode_buf_copy: Vec<u8> = Vec::new();

        let input_len_range = Uniform::new(0, 1000);

        let mut rng = rand::rngs::SmallRng::from_entropy();

        for _ in 0..10_000 {
            orig_data.clear();
            encoded_data.clear();
            decode_buf.clear();
            decode_buf_copy.clear();

            let input_len = input_len_range.sample(&mut rng);

            for _ in 0..input_len {
                orig_data.push(rng.gen());
            }

            let engine = random_engine(&mut rng);
            engine.encode_string(&orig_data, &mut encoded_data);
            assert_encode_sanity(&encoded_data, engine.config().encode_padding(), input_len);

            // fill the buffer with random garbage, long enough to have some room before and after
            for _ in 0..5000 {
                decode_buf.push(rng.gen());
            }

            // keep a copy for later comparison
            decode_buf_copy.extend(decode_buf.iter());

            let offset = 1000;

            // decode into the non-empty buf
            let decode_bytes_written =
                call_decode(&engine, encoded_data.as_bytes(), &mut decode_buf[offset..]);

            assert_eq!(orig_data.len(), decode_bytes_written);
            assert_eq!(
                orig_data,
                &decode_buf[offset..(offset + decode_bytes_written)]
            );
            assert_eq!(&decode_buf_copy[0..offset], &decode_buf[0..offset]);
            assert_eq!(
                &decode_buf_copy[offset + decode_bytes_written..],
                &decode_buf[offset + decode_bytes_written..]
            );
        }
    }
}