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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648
use std::error::Error;
use std::fmt;
use std::io;
use std::slice;
use crate::ffi::{self, Backend, Deflate, DeflateBackend, Inflate, InflateBackend};
use crate::Compression;
/// Raw in-memory compression stream for blocks of data.
///
/// This type is the building block for the I/O streams in the rest of this
/// crate. It requires more management than the [`Read`]/[`Write`] API but is
/// maximally flexible in terms of accepting input from any source and being
/// able to produce output to any memory location.
///
/// It is recommended to use the I/O stream adaptors over this type as they're
/// easier to use.
///
/// [`Read`]: https://doc.rust-lang.org/std/io/trait.Read.html
/// [`Write`]: https://doc.rust-lang.org/std/io/trait.Write.html
#[derive(Debug)]
pub struct Compress {
inner: Deflate,
}
/// Raw in-memory decompression stream for blocks of data.
///
/// This type is the building block for the I/O streams in the rest of this
/// crate. It requires more management than the [`Read`]/[`Write`] API but is
/// maximally flexible in terms of accepting input from any source and being
/// able to produce output to any memory location.
///
/// It is recommended to use the I/O stream adaptors over this type as they're
/// easier to use.
///
/// [`Read`]: https://doc.rust-lang.org/std/io/trait.Read.html
/// [`Write`]: https://doc.rust-lang.org/std/io/trait.Write.html
#[derive(Debug)]
pub struct Decompress {
inner: Inflate,
}
#[derive(Copy, Clone, PartialEq, Eq, Debug)]
/// Values which indicate the form of flushing to be used when compressing
/// in-memory data.
pub enum FlushCompress {
/// A typical parameter for passing to compression/decompression functions,
/// this indicates that the underlying stream to decide how much data to
/// accumulate before producing output in order to maximize compression.
None = ffi::MZ_NO_FLUSH as isize,
/// All pending output is flushed to the output buffer and the output is
/// aligned on a byte boundary so that the decompressor can get all input
/// data available so far.
///
/// Flushing may degrade compression for some compression algorithms and so
/// it should only be used when necessary. This will complete the current
/// deflate block and follow it with an empty stored block.
Sync = ffi::MZ_SYNC_FLUSH as isize,
/// All pending output is flushed to the output buffer, but the output is
/// not aligned to a byte boundary.
///
/// All of the input data so far will be available to the decompressor (as
/// with `Flush::Sync`. This completes the current deflate block and follows
/// it with an empty fixed codes block that is 10 bites long, and it assures
/// that enough bytes are output in order for the decompessor to finish the
/// block before the empty fixed code block.
Partial = ffi::MZ_PARTIAL_FLUSH as isize,
/// All output is flushed as with `Flush::Sync` and the compression state is
/// reset so decompression can restart from this point if previous
/// compressed data has been damaged or if random access is desired.
///
/// Using this option too often can seriously degrade compression.
Full = ffi::MZ_FULL_FLUSH as isize,
/// Pending input is processed and pending output is flushed.
///
/// The return value may indicate that the stream is not yet done and more
/// data has yet to be processed.
Finish = ffi::MZ_FINISH as isize,
#[doc(hidden)]
_Nonexhaustive,
}
#[derive(Copy, Clone, PartialEq, Eq, Debug)]
/// Values which indicate the form of flushing to be used when
/// decompressing in-memory data.
pub enum FlushDecompress {
/// A typical parameter for passing to compression/decompression functions,
/// this indicates that the underlying stream to decide how much data to
/// accumulate before producing output in order to maximize compression.
None = ffi::MZ_NO_FLUSH as isize,
/// All pending output is flushed to the output buffer and the output is
/// aligned on a byte boundary so that the decompressor can get all input
/// data available so far.
///
/// Flushing may degrade compression for some compression algorithms and so
/// it should only be used when necessary. This will complete the current
/// deflate block and follow it with an empty stored block.
Sync = ffi::MZ_SYNC_FLUSH as isize,
/// Pending input is processed and pending output is flushed.
///
/// The return value may indicate that the stream is not yet done and more
/// data has yet to be processed.
Finish = ffi::MZ_FINISH as isize,
#[doc(hidden)]
_Nonexhaustive,
}
/// The inner state for an error when decompressing
#[derive(Debug, Default)]
pub(crate) struct DecompressErrorInner {
pub(crate) needs_dictionary: Option<u32>,
}
/// Error returned when a decompression object finds that the input stream of
/// bytes was not a valid input stream of bytes.
#[derive(Debug)]
pub struct DecompressError(pub(crate) DecompressErrorInner);
impl DecompressError {
/// Indicates whether decompression failed due to requiring a dictionary.
///
/// The resulting integer is the Adler-32 checksum of the dictionary
/// required.
pub fn needs_dictionary(&self) -> Option<u32> {
self.0.needs_dictionary
}
}
#[inline]
pub(crate) fn decompress_failed() -> Result<Status, DecompressError> {
Err(DecompressError(Default::default()))
}
#[inline]
pub(crate) fn decompress_need_dict(adler: u32) -> Result<Status, DecompressError> {
Err(DecompressError(DecompressErrorInner {
needs_dictionary: Some(adler),
}))
}
/// Error returned when a compression object is used incorrectly or otherwise
/// generates an error.
#[derive(Debug)]
pub struct CompressError(pub(crate) ());
/// Possible status results of compressing some data or successfully
/// decompressing a block of data.
#[derive(Copy, Clone, PartialEq, Eq, Debug)]
pub enum Status {
/// Indicates success.
///
/// Means that more input may be needed but isn't available
/// and/or there's more output to be written but the output buffer is full.
Ok,
/// Indicates that forward progress is not possible due to input or output
/// buffers being empty.
///
/// For compression it means the input buffer needs some more data or the
/// output buffer needs to be freed up before trying again.
///
/// For decompression this means that more input is needed to continue or
/// the output buffer isn't large enough to contain the result. The function
/// can be called again after fixing both.
BufError,
/// Indicates that all input has been consumed and all output bytes have
/// been written. Decompression/compression should not be called again.
///
/// For decompression with zlib streams the adler-32 of the decompressed
/// data has also been verified.
StreamEnd,
}
impl Compress {
/// Creates a new object ready for compressing data that it's given.
///
/// The `level` argument here indicates what level of compression is going
/// to be performed, and the `zlib_header` argument indicates whether the
/// output data should have a zlib header or not.
pub fn new(level: Compression, zlib_header: bool) -> Compress {
Compress {
inner: Deflate::make(level, zlib_header, ffi::MZ_DEFAULT_WINDOW_BITS as u8),
}
}
/// Creates a new object ready for compressing data that it's given.
///
/// The `level` argument here indicates what level of compression is going
/// to be performed, and the `zlib_header` argument indicates whether the
/// output data should have a zlib header or not. The `window_bits` parameter
/// indicates the base-2 logarithm of the sliding window size and must be
/// between 9 and 15.
///
/// # Panics
///
/// If `window_bits` does not fall into the range 9 ..= 15,
/// `new_with_window_bits` will panic.
///
/// # Note
///
/// This constructor is only available when the `zlib` feature is used.
/// Other backends currently do not support custom window bits.
#[cfg(feature = "any_zlib")]
pub fn new_with_window_bits(
level: Compression,
zlib_header: bool,
window_bits: u8,
) -> Compress {
Compress {
inner: Deflate::make(level, zlib_header, window_bits),
}
}
/// Returns the total number of input bytes which have been processed by
/// this compression object.
pub fn total_in(&self) -> u64 {
self.inner.total_in()
}
/// Returns the total number of output bytes which have been produced by
/// this compression object.
pub fn total_out(&self) -> u64 {
self.inner.total_out()
}
/// Specifies the compression dictionary to use.
///
/// Returns the Adler-32 checksum of the dictionary.
#[cfg(feature = "any_zlib")]
pub fn set_dictionary(&mut self, dictionary: &[u8]) -> Result<u32, CompressError> {
let stream = &mut *self.inner.inner.stream_wrapper;
let rc = unsafe {
assert!(dictionary.len() < ffi::uInt::max_value() as usize);
ffi::deflateSetDictionary(stream, dictionary.as_ptr(), dictionary.len() as ffi::uInt)
};
match rc {
ffi::MZ_STREAM_ERROR => Err(CompressError(())),
ffi::MZ_OK => Ok(stream.adler as u32),
c => panic!("unknown return code: {}", c),
}
}
/// Quickly resets this compressor without having to reallocate anything.
///
/// This is equivalent to dropping this object and then creating a new one.
pub fn reset(&mut self) {
self.inner.reset();
}
/// Dynamically updates the compression level.
///
/// This can be used to switch between compression levels for different
/// kinds of data, or it can be used in conjunction with a call to reset
/// to reuse the compressor.
///
/// This may return an error if there wasn't enough output space to complete
/// the compression of the available input data before changing the
/// compression level. Flushing the stream before calling this method
/// ensures that the function will succeed on the first call.
#[cfg(feature = "any_zlib")]
pub fn set_level(&mut self, level: Compression) -> Result<(), CompressError> {
use libc::c_int;
let stream = &mut *self.inner.inner.stream_wrapper;
let rc = unsafe { ffi::deflateParams(stream, level.0 as c_int, ffi::MZ_DEFAULT_STRATEGY) };
match rc {
ffi::MZ_OK => Ok(()),
ffi::MZ_BUF_ERROR => Err(CompressError(())),
c => panic!("unknown return code: {}", c),
}
}
/// Compresses the input data into the output, consuming only as much
/// input as needed and writing as much output as possible.
///
/// The flush option can be any of the available `FlushCompress` parameters.
///
/// To learn how much data was consumed or how much output was produced, use
/// the `total_in` and `total_out` functions before/after this is called.
pub fn compress(
&mut self,
input: &[u8],
output: &mut [u8],
flush: FlushCompress,
) -> Result<Status, CompressError> {
self.inner.compress(input, output, flush)
}
/// Compresses the input data into the extra space of the output, consuming
/// only as much input as needed and writing as much output as possible.
///
/// This function has the same semantics as `compress`, except that the
/// length of `vec` is managed by this function. This will not reallocate
/// the vector provided or attempt to grow it, so space for the output must
/// be reserved in the output vector by the caller before calling this
/// function.
pub fn compress_vec(
&mut self,
input: &[u8],
output: &mut Vec<u8>,
flush: FlushCompress,
) -> Result<Status, CompressError> {
let cap = output.capacity();
let len = output.len();
unsafe {
let before = self.total_out();
let ret = {
let ptr = output.as_mut_ptr().offset(len as isize);
let out = slice::from_raw_parts_mut(ptr, cap - len);
self.compress(input, out, flush)
};
output.set_len((self.total_out() - before) as usize + len);
return ret;
}
}
}
impl Decompress {
/// Creates a new object ready for decompressing data that it's given.
///
/// The `zlib_header` argument indicates whether the input data is expected
/// to have a zlib header or not.
pub fn new(zlib_header: bool) -> Decompress {
Decompress {
inner: Inflate::make(zlib_header, ffi::MZ_DEFAULT_WINDOW_BITS as u8),
}
}
/// Creates a new object ready for decompressing data that it's given.
///
/// The `zlib_header` argument indicates whether the input data is expected
/// to have a zlib header or not. The `window_bits` parameter indicates the
/// base-2 logarithm of the sliding window size and must be between 9 and 15.
///
/// # Panics
///
/// If `window_bits` does not fall into the range 9 ..= 15,
/// `new_with_window_bits` will panic.
///
/// # Note
///
/// This constructor is only available when the `zlib` feature is used.
/// Other backends currently do not support custom window bits.
#[cfg(feature = "any_zlib")]
pub fn new_with_window_bits(zlib_header: bool, window_bits: u8) -> Decompress {
Decompress {
inner: Inflate::make(zlib_header, window_bits),
}
}
/// Returns the total number of input bytes which have been processed by
/// this decompression object.
pub fn total_in(&self) -> u64 {
self.inner.total_in()
}
/// Returns the total number of output bytes which have been produced by
/// this decompression object.
pub fn total_out(&self) -> u64 {
self.inner.total_out()
}
/// Decompresses the input data into the output, consuming only as much
/// input as needed and writing as much output as possible.
///
/// The flush option can be any of the available `FlushDecompress` parameters.
///
/// If the first call passes `FlushDecompress::Finish` it is assumed that
/// the input and output buffers are both sized large enough to decompress
/// the entire stream in a single call.
///
/// A flush value of `FlushDecompress::Finish` indicates that there are no
/// more source bytes available beside what's already in the input buffer,
/// and the output buffer is large enough to hold the rest of the
/// decompressed data.
///
/// To learn how much data was consumed or how much output was produced, use
/// the `total_in` and `total_out` functions before/after this is called.
///
/// # Errors
///
/// If the input data to this instance of `Decompress` is not a valid
/// zlib/deflate stream then this function may return an instance of
/// `DecompressError` to indicate that the stream of input bytes is corrupted.
pub fn decompress(
&mut self,
input: &[u8],
output: &mut [u8],
flush: FlushDecompress,
) -> Result<Status, DecompressError> {
self.inner.decompress(input, output, flush)
}
/// Decompresses the input data into the extra space in the output vector
/// specified by `output`.
///
/// This function has the same semantics as `decompress`, except that the
/// length of `vec` is managed by this function. This will not reallocate
/// the vector provided or attempt to grow it, so space for the output must
/// be reserved in the output vector by the caller before calling this
/// function.
///
/// # Errors
///
/// If the input data to this instance of `Decompress` is not a valid
/// zlib/deflate stream then this function may return an instance of
/// `DecompressError` to indicate that the stream of input bytes is corrupted.
pub fn decompress_vec(
&mut self,
input: &[u8],
output: &mut Vec<u8>,
flush: FlushDecompress,
) -> Result<Status, DecompressError> {
let cap = output.capacity();
let len = output.len();
unsafe {
let before = self.total_out();
let ret = {
let ptr = output.as_mut_ptr().offset(len as isize);
let out = slice::from_raw_parts_mut(ptr, cap - len);
self.decompress(input, out, flush)
};
output.set_len((self.total_out() - before) as usize + len);
return ret;
}
}
/// Specifies the decompression dictionary to use.
#[cfg(feature = "any_zlib")]
pub fn set_dictionary(&mut self, dictionary: &[u8]) -> Result<u32, DecompressError> {
let stream = &mut *self.inner.inner.stream_wrapper;
let rc = unsafe {
assert!(dictionary.len() < ffi::uInt::max_value() as usize);
ffi::inflateSetDictionary(stream, dictionary.as_ptr(), dictionary.len() as ffi::uInt)
};
match rc {
ffi::MZ_STREAM_ERROR => Err(DecompressError(Default::default())),
ffi::MZ_DATA_ERROR => Err(DecompressError(DecompressErrorInner {
needs_dictionary: Some(stream.adler as u32),
})),
ffi::MZ_OK => Ok(stream.adler as u32),
c => panic!("unknown return code: {}", c),
}
}
/// Performs the equivalent of replacing this decompression state with a
/// freshly allocated copy.
///
/// This function may not allocate memory, though, and attempts to reuse any
/// previously existing resources.
///
/// The argument provided here indicates whether the reset state will
/// attempt to decode a zlib header first or not.
pub fn reset(&mut self, zlib_header: bool) {
self.inner.reset(zlib_header);
}
}
impl Error for DecompressError {}
impl From<DecompressError> for io::Error {
fn from(data: DecompressError) -> io::Error {
io::Error::new(io::ErrorKind::Other, data)
}
}
impl fmt::Display for DecompressError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "deflate decompression error")
}
}
impl Error for CompressError {}
impl From<CompressError> for io::Error {
fn from(data: CompressError) -> io::Error {
io::Error::new(io::ErrorKind::Other, data)
}
}
impl fmt::Display for CompressError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "deflate decompression error")
}
}
#[cfg(test)]
mod tests {
use std::io::Write;
use crate::write;
use crate::{Compression, Decompress, FlushDecompress};
#[cfg(feature = "any_zlib")]
use crate::{Compress, FlushCompress};
#[test]
fn issue51() {
let data = vec![
0x1f, 0x8b, 0x08, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x03, 0xb3, 0xc9, 0x28, 0xc9,
0xcd, 0xb1, 0xe3, 0xe5, 0xb2, 0xc9, 0x48, 0x4d, 0x4c, 0xb1, 0xb3, 0x29, 0xc9, 0x2c,
0xc9, 0x49, 0xb5, 0x33, 0x31, 0x30, 0x51, 0xf0, 0xcb, 0x2f, 0x51, 0x70, 0xcb, 0x2f,
0xcd, 0x4b, 0xb1, 0xd1, 0x87, 0x08, 0xda, 0xe8, 0x83, 0x95, 0x00, 0x95, 0x26, 0xe5,
0xa7, 0x54, 0x2a, 0x24, 0xa5, 0x27, 0xe7, 0xe7, 0xe4, 0x17, 0xd9, 0x2a, 0x95, 0x67,
0x64, 0x96, 0xa4, 0x2a, 0x81, 0x8c, 0x48, 0x4e, 0xcd, 0x2b, 0x49, 0x2d, 0xb2, 0xb3,
0xc9, 0x30, 0x44, 0x37, 0x01, 0x28, 0x62, 0xa3, 0x0f, 0x95, 0x06, 0xd9, 0x05, 0x54,
0x04, 0xe5, 0xe5, 0xa5, 0x67, 0xe6, 0x55, 0xe8, 0x1b, 0xea, 0x99, 0xe9, 0x19, 0x21,
0xab, 0xd0, 0x07, 0xd9, 0x01, 0x32, 0x53, 0x1f, 0xea, 0x3e, 0x00, 0x94, 0x85, 0xeb,
0xe4, 0xa8, 0x00, 0x00, 0x00,
];
let mut decoded = Vec::with_capacity(data.len() * 2);
let mut d = Decompress::new(false);
// decompressed whole deflate stream
assert!(d
.decompress_vec(&data[10..], &mut decoded, FlushDecompress::Finish)
.is_ok());
// decompress data that has nothing to do with the deflate stream (this
// used to panic)
drop(d.decompress_vec(&[0], &mut decoded, FlushDecompress::None));
}
#[test]
fn reset() {
let string = "hello world".as_bytes();
let mut zlib = Vec::new();
let mut deflate = Vec::new();
let comp = Compression::default();
write::ZlibEncoder::new(&mut zlib, comp)
.write_all(string)
.unwrap();
write::DeflateEncoder::new(&mut deflate, comp)
.write_all(string)
.unwrap();
let mut dst = [0; 1024];
let mut decoder = Decompress::new(true);
decoder
.decompress(&zlib, &mut dst, FlushDecompress::Finish)
.unwrap();
assert_eq!(decoder.total_out(), string.len() as u64);
assert!(dst.starts_with(string));
decoder.reset(false);
decoder
.decompress(&deflate, &mut dst, FlushDecompress::Finish)
.unwrap();
assert_eq!(decoder.total_out(), string.len() as u64);
assert!(dst.starts_with(string));
}
#[cfg(feature = "any_zlib")]
#[test]
fn set_dictionary_with_zlib_header() {
let string = "hello, hello!".as_bytes();
let dictionary = "hello".as_bytes();
let mut encoded = Vec::with_capacity(1024);
let mut encoder = Compress::new(Compression::default(), true);
let dictionary_adler = encoder.set_dictionary(&dictionary).unwrap();
encoder
.compress_vec(string, &mut encoded, FlushCompress::Finish)
.unwrap();
assert_eq!(encoder.total_in(), string.len() as u64);
assert_eq!(encoder.total_out(), encoded.len() as u64);
let mut decoder = Decompress::new(true);
let mut decoded = [0; 1024];
let decompress_error = decoder
.decompress(&encoded, &mut decoded, FlushDecompress::Finish)
.expect_err("decompression should fail due to requiring a dictionary");
let required_adler = decompress_error.needs_dictionary()
.expect("the first call to decompress should indicate a dictionary is required along with the required Adler-32 checksum");
assert_eq!(required_adler, dictionary_adler,
"the Adler-32 checksum should match the value when the dictionary was set on the compressor");
let actual_adler = decoder.set_dictionary(&dictionary).unwrap();
assert_eq!(required_adler, actual_adler);
// Decompress the rest of the input to the remainder of the output buffer
let total_in = decoder.total_in();
let total_out = decoder.total_out();
let decompress_result = decoder.decompress(
&encoded[total_in as usize..],
&mut decoded[total_out as usize..],
FlushDecompress::Finish,
);
assert!(decompress_result.is_ok());
assert_eq!(&decoded[..decoder.total_out() as usize], string);
}
#[cfg(feature = "any_zlib")]
#[test]
fn set_dictionary_raw() {
let string = "hello, hello!".as_bytes();
let dictionary = "hello".as_bytes();
let mut encoded = Vec::with_capacity(1024);
let mut encoder = Compress::new(Compression::default(), false);
encoder.set_dictionary(&dictionary).unwrap();
encoder
.compress_vec(string, &mut encoded, FlushCompress::Finish)
.unwrap();
assert_eq!(encoder.total_in(), string.len() as u64);
assert_eq!(encoder.total_out(), encoded.len() as u64);
let mut decoder = Decompress::new(false);
decoder.set_dictionary(&dictionary).unwrap();
let mut decoded = [0; 1024];
let decompress_result = decoder.decompress(&encoded, &mut decoded, FlushDecompress::Finish);
assert!(decompress_result.is_ok());
assert_eq!(&decoded[..decoder.total_out() as usize], string);
}
}