aleleba/pdfcraft
1
0
Fork 0
mirror of https://github.com/storytold/pdfcraft.git synced 2026-11-03 06:51:50 -06:00
Code Issues Packages Projects Releases Wiki Activity

M11: lossless JBIG2 for black-and-white images

Browse Source 
pdfcraft_filters::encode_jbig2_generic writes 1-bit rows as a JBIG2
stream for JBIG2Decode (embedded organisation: a page information
segment and an immediate lossless generic region, no globals): template
0 with its nominal AT pixels, typical prediction, and the MQ arithmetic
coder (mq.rs), written from the JBIG committee's ISO/IEC 14492 Final
Committee Draft. The coder reproduces its Annex H.2 test sequence byte
for byte; output round-trips through hayro-jbig2, and Poppler renders
it the same as the original.

The optimizer's Monochrome Images gets JBIG2 (lossless) beside CCITT
Group 4 (still the default), doc_optimize mono jbig2; a document below
PDF 1.4 gets /Version /1.4 in its catalog. On 300 dpi text JBIG2 is
about a third smaller than Group 4.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BfMGHQNgdq5yf5tKZHGR3z
This commit is contained in:
Grzegorz Martens
2026-10-29 20:47:45 +01:00
co-authored by Claude Opus 5.5
parent 1b7164cab1
commit 5c4cadce59
51 changed files with 720 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/optimize/src/images.rs
+41 -14
View File
@@ -562,15 +562,17 @@ fn one_component(doc: &Document, cs: &Object) -> bool {
}
}
/// A black-and-white image (one bit per pixel, or an image mask) stored again as CCITT Group 4,
/// if `compression` asks for that and the result is smaller as stored. Only images whose samples
/// A black-and-white image (one bit per pixel, or an image mask) stored again as `compression`
/// asks (CCITT Group 4 or JBIG2), if the result is smaller as stored. Only images whose samples
/// PdfCraft decodes (no filter, or general-purpose filters: image codecs don't decode here)
/// qualify. The samples decode to the same bits, so the colour space, decode array and masks stay
/// as they are.
fn mono(doc: &Document, s: &Stream, compression: MonoCompression) -> Option<Stream> {
if compression != MonoCompression::CcittG4 {
return None;
}
let widest = match compression {
MonoCompression::CcittG4 => pdfcraft_filters::MAX_G4_COLUMNS,
MonoCompression::Jbig2 => pdfcraft_filters::MAX_JBIG2_COLUMNS,
MonoCompression::Retain => return None,
};
let d = &s.dict;
let bits = d.int(b"BitsPerComponent");
let qualifies = if matches!(d.get(b"ImageMask"), Some(Object::Bool(true))) {
@@ -582,24 +584,31 @@ fn mono(doc: &Document, s: &Stream, compression: MonoCompression) -> Option<Stre
return None;
}
let (w, h) = (u32::try_from(d.int(b"Width")?).ok()?, u32::try_from(d.int(b"Height")?).ok()?);
if w == 0 || h == 0 || w > pdfcraft_filters::MAX_G4_COLUMNS || u64::from(w) * u64::from(h) > MAX_PIXELS {
if w == 0 || h == 0 || w > widest || u64::from(w) * u64::from(h) > MAX_PIXELS {
return None;
}
// Through its parameters given by reference too, as `pixels` reads, and no further than its
// rows can need.
let bytes = usize::try_from(w).ok()?.div_ceil(8).checked_mul(usize::try_from(h).ok()?)?;
let g4 = pdfcraft_filters::encode_g4(&doc.with_direct_parms(s).decoded_within(allowance(bytes, h)?).ok()?, w, h).ok()?;
let samples = doc.with_direct_parms(s).decoded_within(allowance(bytes, h)?).ok()?;
let mut new = d.clone();
for k in [&b"Filter"[..], b"DecodeParms", b"Length", b"DL"] {
new.remove(k);
}
let mut parms = Dict::new();
parms.set(b"K".to_vec(), Object::Int(-1));
parms.set(b"Columns".to_vec(), Object::Int(i64::from(w)));
parms.set(b"Rows".to_vec(), Object::Int(i64::from(h)));
new.set(b"Filter".to_vec(), Object::name("CCITTFaxDecode"));
new.set(b"DecodeParms".to_vec(), Object::Dict(parms));
let new = Stream::from_raw(new, g4);
let data = if compression == MonoCompression::Jbig2 {
// One embedded JBIG2 stream with its own page; no /JBIG2Globals.
new.set(b"Filter".to_vec(), Object::name("JBIG2Decode"));
pdfcraft_filters::encode_jbig2_generic(&samples, w, h).ok()?
} else {
let mut parms = Dict::new();
parms.set(b"K".to_vec(), Object::Int(-1));
parms.set(b"Columns".to_vec(), Object::Int(i64::from(w)));
parms.set(b"Rows".to_vec(), Object::Int(i64::from(h)));
new.set(b"Filter".to_vec(), Object::name("CCITTFaxDecode"));
new.set(b"DecodeParms".to_vec(), Object::Dict(parms));
pdfcraft_filters::encode_g4(&samples, w, h).ok()?
};
let new = Stream::from_raw(new, data);
// Smaller as stored, counting the larger dictionary: a tiny image can lose by it.
(crate::stored_len(&new)? < crate::stored_len(s)?).then_some(new)
}
@@ -623,6 +632,7 @@ pub(crate) fn run(
let mut refs: Vec<(ObjRef, f64)> = ppi.into_iter().filter(|(r, _)| !masks.contains(r)).collect();
refs.sort_by_key(|(r, _)| r.num);
let total = refs.len();
let mut jbig2 = false;
for (done, (r, ppi)) in refs.into_iter().enumerate() {
if !progress(Stage::Images { done, total }) {
return Err(OptimizeError::Cancelled);
@@ -634,6 +644,7 @@ pub(crate) fn run(
report.image_bytes_before += s.raw.len();
report.image_bytes_after += new.raw.len();
report.images_recompressed += 1;
jbig2 |= new.dict.name(b"Filter") == Some(b"JBIG2Decode");
doc.set(r, Object::Stream(new));
continue;
}
@@ -656,6 +667,22 @@ pub(crate) fn run(
if !progress(Stage::Images { done: total, total }) {
return Err(OptimizeError::Cancelled);
}
if jbig2 {
at_least_pdf_1_4(doc)?;
}
Ok(())
}
/// JBIG2Decode is PDF 1.4: a document whose header says less, and whose catalog doesn't say 1.4
/// or more already, gets `/Version /1.4` in its catalog (ISO 32000-2 §7.7.2). A full save with
/// object streams writes a 1.5 header anyway.
fn at_least_pdf_1_4(doc: &mut Document) -> Result<(), OptimizeError> {
let below = |v: &[u8]| v.len() < 3 || v < &b"1.4"[..];
let Some(root) = doc.root() else { return Ok(()) };
let catalog = doc.get(root).as_dict().and_then(|c| c.name(b"Version").map(<[u8]>::to_vec));
if below(doc.version().as_bytes()) && catalog.as_deref().is_none_or(below) {
doc.update_dict(root, |c| c.set(b"Version".to_vec(), Object::name("1.4")))?;
}
Ok(())
}
crates/optimize/src/lib.rs
+5 -2
View File
@@ -10,8 +10,8 @@
//! A new image replaces the old one only if it is smaller. Images PdfCraft can't decode
//! faithfully (CMYK and other colour spaces, masks, decode arrays other than the default,
//! JPEG 2000, JBIG2, CCITT, other than 8 bits, JPEGs whose Adobe marker and `/ColorTransform`
//! disagree) are left alone. Black-and-white (1-bit) images are stored again as CCITT Group 4,
//! losslessly, when that is smaller.
//! disagree) are left alone. Black-and-white (1-bit) images are stored again as CCITT Group 4
//! or JBIG2, losslessly, when that is smaller.
//! - **Discard objects:** page thumbnails, alternate images, document tags (structure tree),
//! print settings.
//! - **Clean up:** drop images and forms that pages list but never draw (such as a deleted
@@ -124,6 +124,9 @@ pub enum Compression {
pub enum MonoCompression {
/// CCITT Group 4 (lossless), when smaller than the image as it is.
CcittG4,
/// JBIG2, lossless (a generic region), when smaller than the image as it is. JBIG2Decode is
/// PDF 1.4: an older document gets `/Version /1.4` in its catalog.
Jbig2,
/// Keep each image's own compression.
Retain,
}