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
use super::frame;
use crate::decoding::dictionary::Dictionary;
use crate::decoding::scratch::DecoderScratch;
use crate::decoding::{self, dictionary};
use crate::io::{Error, Read, Write};
use alloc::collections::BTreeMap;
use alloc::vec::Vec;
use core::convert::TryInto;
use core::hash::Hasher;
/// This implements a decoder for zstd frames. This decoder is able to decode frames only partially and gives control
/// over how many bytes/blocks will be decoded at a time (so you don't have to decode a 10GB file into memory all at once).
/// It reads bytes as needed from a provided source and can be read from to collect partial results.
///
/// If you want to just read the whole frame with an io::Read without having to deal with manually calling decode_blocks
/// you can use the provided StreamingDecoder with wraps this FrameDecoder
///
/// Workflow is as follows:
/// ```
/// use ruzstd::frame_decoder::BlockDecodingStrategy;
///
/// # #[cfg(feature = "std")]
/// use std::io::{Read, Write};
///
/// // no_std environments can use the crate's own Read traits
/// # #[cfg(not(feature = "std"))]
/// use ruzstd::io::{Read, Write};
///
/// fn decode_this(mut file: impl Read) {
/// //Create a new decoder
/// let mut frame_dec = ruzstd::FrameDecoder::new();
/// let mut result = Vec::new();
///
/// // Use reset or init to make the decoder ready to decode the frame from the io::Read
/// frame_dec.reset(&mut file).unwrap();
///
/// // Loop until the frame has been decoded completely
/// while !frame_dec.is_finished() {
/// // decode (roughly) batch_size many bytes
/// frame_dec.decode_blocks(&mut file, BlockDecodingStrategy::UptoBytes(1024)).unwrap();
///
/// // read from the decoder to collect bytes from the internal buffer
/// let bytes_read = frame_dec.read(result.as_mut_slice()).unwrap();
///
/// // then do something with it
/// do_something(&result[0..bytes_read]);
/// }
///
/// // handle the last chunk of data
/// while frame_dec.can_collect() > 0 {
/// let x = frame_dec.read(result.as_mut_slice()).unwrap();
///
/// do_something(&result[0..x]);
/// }
/// }
///
/// fn do_something(data: &[u8]) {
/// # #[cfg(feature = "std")]
/// std::io::stdout().write_all(data).unwrap();
/// }
/// ```
pub struct FrameDecoder {
state: Option<FrameDecoderState>,
dicts: BTreeMap<u32, Dictionary>,
}
struct FrameDecoderState {
pub frame: frame::Frame,
decoder_scratch: DecoderScratch,
frame_finished: bool,
block_counter: usize,
bytes_read_counter: u64,
check_sum: Option<u32>,
using_dict: Option<u32>,
}
pub enum BlockDecodingStrategy {
All,
UptoBlocks(usize),
UptoBytes(usize),
}
#[derive(Debug, derive_more::Display, derive_more::From)]
#[cfg_attr(feature = "std", derive(derive_more::Error))]
#[non_exhaustive]
pub enum FrameDecoderError {
#[display(fmt = "{_0:?}")]
#[from]
ReadFrameHeaderError(frame::ReadFrameHeaderError),
#[display(fmt = "{_0:?}")]
#[from]
FrameHeaderError(frame::FrameHeaderError),
#[display(
fmt = "Specified window_size is too big; Requested: {requested}, Max: {MAX_WINDOW_SIZE}"
)]
WindowSizeTooBig { requested: u64 },
#[display(fmt = "{_0:?}")]
#[from]
DictionaryDecodeError(dictionary::DictionaryDecodeError),
#[display(fmt = "Failed to parse/decode block body: {_0}")]
#[from]
FailedToReadBlockHeader(decoding::block_decoder::BlockHeaderReadError),
#[display(fmt = "Failed to parse block header: {_0}")]
FailedToReadBlockBody(decoding::block_decoder::DecodeBlockContentError),
#[display(fmt = "Failed to read checksum: {_0}")]
FailedToReadChecksum(Error),
#[display(fmt = "Decoder must initialized or reset before using it")]
NotYetInitialized,
#[display(fmt = "Decoder encountered error while initializing: {_0}")]
FailedToInitialize(frame::FrameHeaderError),
#[display(fmt = "Decoder encountered error while draining the decodebuffer: {_0}")]
FailedToDrainDecodebuffer(Error),
#[display(
fmt = "Target must have at least as many bytes as the contentsize of the frame reports"
)]
TargetTooSmall,
#[display(
fmt = "Frame header specified dictionary id 0x{dict_id:X} that wasnt provided by add_dict() or reset_with_dict()"
)]
DictNotProvided { dict_id: u32 },
}
const MAX_WINDOW_SIZE: u64 = 1024 * 1024 * 100;
impl FrameDecoderState {
pub fn new(source: impl Read) -> Result<FrameDecoderState, FrameDecoderError> {
let (frame, header_size) = frame::read_frame_header(source)?;
let window_size = frame.header.window_size()?;
Ok(FrameDecoderState {
frame,
frame_finished: false,
block_counter: 0,
decoder_scratch: DecoderScratch::new(window_size as usize),
bytes_read_counter: u64::from(header_size),
check_sum: None,
using_dict: None,
})
}
pub fn reset(&mut self, source: impl Read) -> Result<(), FrameDecoderError> {
let (frame, header_size) = frame::read_frame_header(source)?;
let window_size = frame.header.window_size()?;
if window_size > MAX_WINDOW_SIZE {
return Err(FrameDecoderError::WindowSizeTooBig {
requested: window_size,
});
}
self.frame = frame;
self.frame_finished = false;
self.block_counter = 0;
self.decoder_scratch.reset(window_size as usize);
self.bytes_read_counter = u64::from(header_size);
self.check_sum = None;
self.using_dict = None;
Ok(())
}
}
impl Default for FrameDecoder {
fn default() -> Self {
Self::new()
}
}
impl FrameDecoder {
/// This will create a new decoder without allocating anything yet.
/// init()/reset() will allocate all needed buffers if it is the first time this decoder is used
/// else they just reset these buffers with not further allocations
pub fn new() -> FrameDecoder {
FrameDecoder {
state: None,
dicts: BTreeMap::new(),
}
}
/// init() will allocate all needed buffers if it is the first time this decoder is used
/// else they just reset these buffers with not further allocations
///
/// Note that all bytes currently in the decodebuffer from any previous frame will be lost. Collect them with collect()/collect_to_writer()
///
/// equivalent to reset()
pub fn init(&mut self, source: impl Read) -> Result<(), FrameDecoderError> {
self.reset(source)
}
/// reset() will allocate all needed buffers if it is the first time this decoder is used
/// else they just reset these buffers with not further allocations
///
/// Note that all bytes currently in the decodebuffer from any previous frame will be lost. Collect them with collect()/collect_to_writer()
///
/// equivalent to init()
pub fn reset(&mut self, source: impl Read) -> Result<(), FrameDecoderError> {
use FrameDecoderError as err;
let state = match &mut self.state {
Some(s) => {
s.reset(source)?;
s
}
None => {
self.state = Some(FrameDecoderState::new(source)?);
self.state.as_mut().unwrap()
}
};
if let Some(dict_id) = state.frame.header.dictionary_id() {
let dict = self
.dicts
.get(&dict_id)
.ok_or(err::DictNotProvided { dict_id })?;
state.decoder_scratch.init_from_dict(dict);
state.using_dict = Some(dict_id);
}
Ok(())
}
/// Add a dict to the FrameDecoder that can be used when needed. The FrameDecoder uses the appropriate one dynamically
pub fn add_dict(&mut self, dict: Dictionary) -> Result<(), FrameDecoderError> {
self.dicts.insert(dict.id, dict);
Ok(())
}
pub fn force_dict(&mut self, dict_id: u32) -> Result<(), FrameDecoderError> {
use FrameDecoderError as err;
let Some(state) = self.state.as_mut() else {
return Err(err::NotYetInitialized);
};
let dict = self
.dicts
.get(&dict_id)
.ok_or(err::DictNotProvided { dict_id })?;
state.decoder_scratch.init_from_dict(dict);
state.using_dict = Some(dict_id);
Ok(())
}
/// Returns how many bytes the frame contains after decompression
pub fn content_size(&self) -> u64 {
match &self.state {
None => 0,
Some(s) => s.frame.header.frame_content_size(),
}
}
/// Returns the checksum that was read from the data. Only available after all bytes have been read. It is the last 4 bytes of a zstd-frame
pub fn get_checksum_from_data(&self) -> Option<u32> {
let state = match &self.state {
None => return None,
Some(s) => s,
};
state.check_sum
}
/// Returns the checksum that was calculated while decoding.
/// Only a sensible value after all decoded bytes have been collected/read from the FrameDecoder
pub fn get_calculated_checksum(&self) -> Option<u32> {
let state = match &self.state {
None => return None,
Some(s) => s,
};
let cksum_64bit = state.decoder_scratch.buffer.hash.finish();
//truncate to lower 32bit because reasons...
Some(cksum_64bit as u32)
}
/// Counter for how many bytes have been consumed while decoding the frame
pub fn bytes_read_from_source(&self) -> u64 {
let state = match &self.state {
None => return 0,
Some(s) => s,
};
state.bytes_read_counter
}
/// Whether the current frames last block has been decoded yet
/// If this returns true you can call the drain* functions to get all content
/// (the read() function will drain automatically if this returns true)
pub fn is_finished(&self) -> bool {
let state = match &self.state {
None => return true,
Some(s) => s,
};
if state.frame.header.descriptor.content_checksum_flag() {
state.frame_finished && state.check_sum.is_some()
} else {
state.frame_finished
}
}
/// Counter for how many blocks have already been decoded
pub fn blocks_decoded(&self) -> usize {
let state = match &self.state {
None => return 0,
Some(s) => s,
};
state.block_counter
}
/// Decodes blocks from a reader. It requires that the framedecoder has been initialized first.
/// The Strategy influences how many blocks will be decoded before the function returns
/// This is important if you want to manage memory consumption carefully. If you don't care
/// about that you can just choose the strategy "All" and have all blocks of the frame decoded into the buffer
pub fn decode_blocks(
&mut self,
mut source: impl Read,
strat: BlockDecodingStrategy,
) -> Result<bool, FrameDecoderError> {
use FrameDecoderError as err;
let state = self.state.as_mut().ok_or(err::NotYetInitialized)?;
let mut block_dec = decoding::block_decoder::new();
let buffer_size_before = state.decoder_scratch.buffer.len();
let block_counter_before = state.block_counter;
loop {
vprintln!("################");
vprintln!("Next Block: {}", state.block_counter);
vprintln!("################");
let (block_header, block_header_size) = block_dec
.read_block_header(&mut source)
.map_err(err::FailedToReadBlockHeader)?;
state.bytes_read_counter += u64::from(block_header_size);
vprintln!();
vprintln!(
"Found {} block with size: {}, which will be of size: {}",
block_header.block_type,
block_header.content_size,
block_header.decompressed_size
);
let bytes_read_in_block_body = block_dec
.decode_block_content(&block_header, &mut state.decoder_scratch, &mut source)
.map_err(err::FailedToReadBlockBody)?;
state.bytes_read_counter += bytes_read_in_block_body;
state.block_counter += 1;
vprintln!("Output: {}", state.decoder_scratch.buffer.len());
if block_header.last_block {
state.frame_finished = true;
if state.frame.header.descriptor.content_checksum_flag() {
let mut chksum = [0u8; 4];
source
.read_exact(&mut chksum)
.map_err(err::FailedToReadChecksum)?;
state.bytes_read_counter += 4;
let chksum = u32::from_le_bytes(chksum);
state.check_sum = Some(chksum);
}
break;
}
match strat {
BlockDecodingStrategy::All => { /* keep going */ }
BlockDecodingStrategy::UptoBlocks(n) => {
if state.block_counter - block_counter_before >= n {
break;
}
}
BlockDecodingStrategy::UptoBytes(n) => {
if state.decoder_scratch.buffer.len() - buffer_size_before >= n {
break;
}
}
}
}
Ok(state.frame_finished)
}
/// Collect bytes and retain window_size bytes while decoding is still going on.
/// After decoding of the frame (is_finished() == true) has finished it will collect all remaining bytes
pub fn collect(&mut self) -> Option<Vec<u8>> {
let finished = self.is_finished();
let state = self.state.as_mut()?;
if finished {
Some(state.decoder_scratch.buffer.drain())
} else {
state.decoder_scratch.buffer.drain_to_window_size()
}
}
/// Collect bytes and retain window_size bytes while decoding is still going on.
/// After decoding of the frame (is_finished() == true) has finished it will collect all remaining bytes
pub fn collect_to_writer(&mut self, w: impl Write) -> Result<usize, Error> {
let finished = self.is_finished();
let state = match &mut self.state {
None => return Ok(0),
Some(s) => s,
};
if finished {
state.decoder_scratch.buffer.drain_to_writer(w)
} else {
state.decoder_scratch.buffer.drain_to_window_size_writer(w)
}
}
/// How many bytes can currently be collected from the decodebuffer, while decoding is going on this will be lower than the actual decodbuffer size
/// because window_size bytes need to be retained for decoding.
/// After decoding of the frame (is_finished() == true) has finished it will report all remaining bytes
pub fn can_collect(&self) -> usize {
let finished = self.is_finished();
let state = match &self.state {
None => return 0,
Some(s) => s,
};
if finished {
state.decoder_scratch.buffer.can_drain()
} else {
state
.decoder_scratch
.buffer
.can_drain_to_window_size()
.unwrap_or(0)
}
}
/// Decodes as many blocks as possible from the source slice and reads from the decodebuffer into the target slice
/// The source slice may contain only parts of a frame but must contain at least one full block to make progress
///
/// By all means use decode_blocks if you have a io.Reader available. This is just for compatibility with other decompressors
/// which try to serve an old-style c api
///
/// Returns (read, written), if read == 0 then the source did not contain a full block and further calls with the same
/// input will not make any progress!
///
/// Note that no kind of block can be bigger than 128kb.
/// So to be safe use at least 128*1024 (max block content size) + 3 (block_header size) + 18 (max frame_header size) bytes as your source buffer
///
/// You may call this function with an empty source after all bytes have been decoded. This is equivalent to just call decoder.read(&mut target)
pub fn decode_from_to(
&mut self,
source: &[u8],
target: &mut [u8],
) -> Result<(usize, usize), FrameDecoderError> {
use FrameDecoderError as err;
let bytes_read_at_start = match &self.state {
Some(s) => s.bytes_read_counter,
None => 0,
};
if !self.is_finished() || self.state.is_none() {
let mut mt_source = source;
if self.state.is_none() {
self.init(&mut mt_source)?;
}
//pseudo block to scope "state" so we can borrow self again after the block
{
let state = match &mut self.state {
Some(s) => s,
None => panic!("Bug in library"),
};
let mut block_dec = decoding::block_decoder::new();
if state.frame.header.descriptor.content_checksum_flag()
&& state.frame_finished
&& state.check_sum.is_none()
{
//this block is needed if the checksum were the only 4 bytes that were not included in the last decode_from_to call for a frame
if mt_source.len() >= 4 {
let chksum = mt_source[..4].try_into().expect("optimized away");
state.bytes_read_counter += 4;
let chksum = u32::from_le_bytes(chksum);
state.check_sum = Some(chksum);
}
return Ok((4, 0));
}
loop {
//check if there are enough bytes for the next header
if mt_source.len() < 3 {
break;
}
let (block_header, block_header_size) = block_dec
.read_block_header(&mut mt_source)
.map_err(err::FailedToReadBlockHeader)?;
// check the needed size for the block before updating counters.
// If not enough bytes are in the source, the header will have to be read again, so act like we never read it in the first place
if mt_source.len() < block_header.content_size as usize {
break;
}
state.bytes_read_counter += u64::from(block_header_size);
let bytes_read_in_block_body = block_dec
.decode_block_content(
&block_header,
&mut state.decoder_scratch,
&mut mt_source,
)
.map_err(err::FailedToReadBlockBody)?;
state.bytes_read_counter += bytes_read_in_block_body;
state.block_counter += 1;
if block_header.last_block {
state.frame_finished = true;
if state.frame.header.descriptor.content_checksum_flag() {
//if there are enough bytes handle this here. Else the block at the start of this function will handle it at the next call
if mt_source.len() >= 4 {
let chksum = mt_source[..4].try_into().expect("optimized away");
state.bytes_read_counter += 4;
let chksum = u32::from_le_bytes(chksum);
state.check_sum = Some(chksum);
}
}
break;
}
}
}
}
let result_len = self.read(target).map_err(err::FailedToDrainDecodebuffer)?;
let bytes_read_at_end = match &mut self.state {
Some(s) => s.bytes_read_counter,
None => panic!("Bug in library"),
};
let read_len = bytes_read_at_end - bytes_read_at_start;
Ok((read_len as usize, result_len))
}
}
/// Read bytes from the decode_buffer that are no longer needed. While the frame is not yet finished
/// this will retain window_size bytes, else it will drain it completely
impl Read for FrameDecoder {
fn read(&mut self, target: &mut [u8]) -> Result<usize, Error> {
let state = match &mut self.state {
None => return Ok(0),
Some(s) => s,
};
if state.frame_finished {
state.decoder_scratch.buffer.read_all(target)
} else {
state.decoder_scratch.buffer.read(target)
}
}
}