precomp2 0.2.0

Reversible preprocessing for compressed and container data.
Documentation
use std::io::Cursor;

use super::{DecodeConfig, budget::DecodeBudget};
use crate::{
  error::{Error, Result},
  pcf2::{Pcf2Segment, SegmentKind},
};

const MJPGDHT_LEN: usize = 420;
const MJPGDHT: [u8; MJPGDHT_LEN] = [
  0xFF, 0xC4, 0x01, 0xA2, 0x00, 0x00, 0x01, 0x05, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01,
  0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0A, 0x0B, 0x01, 0x00, 0x03, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x00,
  0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0A, 0x0B, 0x10, 0x00, 0x02, 0x01, 0x03, 0x03, 0x02,
  0x04, 0x03, 0x05, 0x05, 0x04, 0x04, 0x00, 0x00, 0x01, 0x7D, 0x01, 0x02, 0x03, 0x00, 0x04, 0x11, 0x05, 0x12, 0x21, 0x31, 0x41, 0x06, 0x13,
  0x51, 0x61, 0x07, 0x22, 0x71, 0x14, 0x32, 0x81, 0x91, 0xA1, 0x08, 0x23, 0x42, 0xB1, 0xC1, 0x15, 0x52, 0xD1, 0xF0, 0x24, 0x33, 0x62, 0x72,
  0x82, 0x09, 0x0A, 0x16, 0x17, 0x18, 0x19, 0x1A, 0x25, 0x26, 0x27, 0x28, 0x29, 0x2A, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x3A, 0x43, 0x44,
  0x45, 0x46, 0x47, 0x48, 0x49, 0x4A, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6A, 0x73,
  0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x8A, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99,
  0x9A, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xAA, 0xB2, 0xB3, 0xB4, 0xB5, 0xB6, 0xB7, 0xB8, 0xB9, 0xBA, 0xC2, 0xC3, 0xC4, 0xC5,
  0xC6, 0xC7, 0xC8, 0xC9, 0xCA, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, 0xD7, 0xD8, 0xD9, 0xDA, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9,
  0xEA, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0xFA, 0x11, 0x00, 0x02, 0x01, 0x02, 0x04, 0x04, 0x03, 0x04, 0x07, 0x05, 0x04,
  0x04, 0x00, 0x01, 0x02, 0x77, 0x00, 0x01, 0x02, 0x03, 0x11, 0x04, 0x05, 0x21, 0x31, 0x06, 0x12, 0x41, 0x51, 0x07, 0x61, 0x71, 0x13, 0x22,
  0x32, 0x81, 0x08, 0x14, 0x42, 0x91, 0xA1, 0xB1, 0xC1, 0x09, 0x23, 0x33, 0x52, 0xF0, 0x15, 0x62, 0x72, 0xD1, 0x0A, 0x16, 0x24, 0x34, 0xE1,
  0x25, 0xF1, 0x17, 0x18, 0x19, 0x1A, 0x26, 0x27, 0x28, 0x29, 0x2A, 0x35, 0x36, 0x37, 0x38, 0x39, 0x3A, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48,
  0x49, 0x4A, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6A, 0x73, 0x74, 0x75, 0x76, 0x77,
  0x78, 0x79, 0x7A, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x8A, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, 0x9A, 0xA2, 0xA3,
  0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xAA, 0xB2, 0xB3, 0xB4, 0xB5, 0xB6, 0xB7, 0xB8, 0xB9, 0xBA, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8,
  0xC9, 0xCA, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, 0xD7, 0xD8, 0xD9, 0xDA, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xEA, 0xF2, 0xF3, 0xF4,
  0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0xFA,
];

pub(super) fn encode_jpg(input: &[u8]) -> Result<Option<Pcf2Segment>> {
  if input.len() < 4 || input[0] != 0xFF || input[1] != 0xD8 {
    return Ok(None);
  }
  let mut mjpg_used = false;
  let mut jpeg = input.to_vec();
  let lepton = if jpeg_has_dht(&jpeg) {
    encode_lepton(&jpeg)
  } else {
    match encode_lepton(&jpeg) {
      Ok(v) => Ok(v),
      Err(_) => {
        let mut with_dht = jpeg.clone();
        if !insert_mjpg_dht(&mut with_dht) {
          return Ok(None);
        }
        mjpg_used = true;
        jpeg = with_dht;
        encode_lepton(&jpeg)
      }
    }
  };
  let lepton = match lepton {
    Ok(v) => v,
    Err(_) => return Ok(None),
  };
  // lepton normalizes some non-canonical inputs (e.g. a missing EOI marker), so
  // only keep the segment when decoding reproduces the stored bytes exactly.
  let restored = match decode_lepton(&lepton) {
    Ok(v) => v,
    Err(_) => return Ok(None),
  };
  if restored != jpeg {
    return Ok(None);
  }
  let mut meta = Vec::with_capacity(2);
  meta.push(1);
  meta.push(if mjpg_used { 1 } else { 0 });
  Ok(Some(Pcf2Segment {
    kind: SegmentKind::Jpg as u8,
    flags: 0,
    orig_len: input.len() as u64,
    meta,
    data: lepton,
  }))
}

pub(super) fn jpeg_has_dht(jpeg: &[u8]) -> bool {
  if jpeg.len() < 4 || jpeg[0] != 0xFF || jpeg[1] != 0xD8 {
    return false;
  }
  let mut pos = 2usize;
  while pos + 1 < jpeg.len() {
    if jpeg[pos] != 0xFF {
      pos += 1;
      continue;
    }
    while pos < jpeg.len() && jpeg[pos] == 0xFF {
      pos += 1;
    }
    if pos >= jpeg.len() {
      break;
    }
    let marker = jpeg[pos];
    pos += 1;
    if marker == 0xD9 || marker == 0xDA {
      break;
    }
    if marker == 0xD8 || marker == 0x01 || (0xD0..=0xD7).contains(&marker) {
      continue;
    }
    if pos + 1 >= jpeg.len() {
      break;
    }
    let len = u16::from_be_bytes([jpeg[pos], jpeg[pos + 1]]) as usize;
    if len < 2 || pos + len > jpeg.len() {
      break;
    }
    if marker == 0xC4 {
      return true;
    }
    pos += len;
  }
  false
}

fn insert_mjpg_dht(jpeg: &mut Vec<u8>) -> bool {
  if jpeg.len() < 4 || jpeg[0] != 0xFF || jpeg[1] != 0xD8 {
    return false;
  }
  let mut found_ff = false;
  let mut found_ffda = false;
  let mut ffda_pos: isize = -1;
  loop {
    ffda_pos += 1;
    if ffda_pos as usize >= jpeg.len() {
      break;
    }
    let byte = jpeg[ffda_pos as usize];
    if found_ff {
      found_ffda = byte == 0xDA;
      if found_ffda {
        break;
      }
      found_ff = false;
    } else {
      found_ff = byte == 0xFF;
    }
  }
  if !found_ffda {
    return false;
  }
  let insert_pos = ffda_pos - 1;
  if insert_pos < 0 {
    return false;
  }
  let insert_pos = insert_pos as usize;
  jpeg.splice(insert_pos..insert_pos, MJPGDHT);
  true
}

fn remove_mjpg_dht(jpeg: &mut Vec<u8>) -> bool {
  if jpeg.len() < MJPGDHT_LEN + 4 || jpeg[0] != 0xFF || jpeg[1] != 0xD8 {
    return false;
  }
  let mut found_ff = false;
  let mut found_ffda = false;
  let mut ffda_pos: isize = -1;
  loop {
    ffda_pos += 1;
    if ffda_pos as usize >= jpeg.len() {
      break;
    }
    let byte = jpeg[ffda_pos as usize];
    if found_ff {
      found_ffda = byte == 0xDA;
      if found_ffda {
        break;
      }
      found_ff = false;
    } else {
      found_ff = byte == 0xFF;
    }
  }
  if !found_ffda {
    return false;
  }
  let insert_pos = ffda_pos - 1;
  if insert_pos < MJPGDHT_LEN as isize {
    return false;
  }
  let insert_pos = insert_pos as usize;
  let start = insert_pos - MJPGDHT_LEN;
  if jpeg.get(start..insert_pos) == Some(&MJPGDHT[..]) {
    jpeg.drain(start..insert_pos);
    return true;
  }
  false
}

fn encode_lepton(jpeg: &[u8]) -> Result<Vec<u8>> {
  let mut reader = Cursor::new(jpeg);
  let mut writer = Cursor::new(Vec::new());
  let features = lepton_jpeg::EnabledFeatures::compat_lepton_vector_write();
  lepton_jpeg::encode_lepton(&mut reader, &mut writer, &features, &lepton_jpeg::DEFAULT_THREAD_POOL)
    .map_err(|err| Error::Other(format!("lepton encode failed: {err}")))?;
  Ok(writer.into_inner())
}

fn decode_lepton(data: &[u8]) -> Result<Vec<u8>> {
  let mut reader = Cursor::new(data);
  let mut out = Vec::new();
  let features = lepton_jpeg::EnabledFeatures::compat_lepton_vector_read();
  lepton_jpeg::decode_lepton(&mut reader, &mut out, &features, &lepton_jpeg::DEFAULT_THREAD_POOL)
    .map_err(|err| Error::Other(format!("lepton decode failed: {err}")))?;
  Ok(out)
}

pub(super) fn decode_jpg_segment(segment: &Pcf2Segment, budget: &mut DecodeBudget, config: &DecodeConfig) -> Result<Vec<u8>> {
  if segment.meta.len() < 2 {
    return Err(Error::InvalidSegment("jpg meta"));
  }
  let meta_version = segment.meta[0];
  if meta_version != 1 {
    return Err(Error::InvalidSegment("jpg meta_version"));
  }
  let mjpg_used = segment.meta[1] != 0;
  let mut jpeg = decode_lepton(&segment.data)?;
  if mjpg_used && !remove_mjpg_dht(&mut jpeg) {
    return Err(Error::InvalidSegment("jpg mjpg dht"));
  }
  budget.consume(jpeg.len(), config)?;
  Ok(jpeg)
}