mirror of
https://github.com/storytold/craft-libs.git
synced 2026-11-14 06:22:24 +00:00
craft-pdf: the PDF object layer from PdfCraft (`cos`), on filters and crypt * hayro-jbig2: bound a stream's total decode work and what a page retains; no i32 overflow Port of pdfcraft 85c10051 (patches 5-9), 82439525 (patch 10) and 10107d94 (patch 12). * hayro-jbig2: PdfCraft's JBIG2 follow-ups (refinement fixes, file header, work accounting, dictionary pixel cap) Ports pdfcraft 72e763ad, b7ec3669, e3bc4e85, 01d3479f, b9e068aa, 858ce960, 07f44038, e38b9d18, 8717a085, 58c30af3 and the hayro-jbig2 part of e2464e14 (with the hayro-jbig2 part of 0ed33990 they build on). * Add craft-stream-codecs: the codec modules of PdfCraft's stream filters LZW, ASCII85, ASCIIHex, RunLength, the TIFF and PNG predictors, bounded CCITT fax decoding (through hayro-ccitt) with Group 4 encoding (through fax), and the lossless JBIG2 encoder with its MQ coder, from pdfcraft-filters at PdfCraft revision 80e26e674d1aa33078e83c8139875047f3289eb6. The crate sits below craft-pdf and craft-tiff: it knows no container. The PDF filter chain, Flate and the bounded JBIG2 decoding entry are not part of it. * craft-pdf: the PDF filter chain from PdfCraft (`filters`) Adds the `filters` feature: the /Filter chain of pdfcraft-filters (PdfCraft revision 80e26e674d1aa33078e83c8139875047f3289eb6) as craft_pdf::filters, over the codecs in craft-stream-codecs. It adds Flate, strict and tolerant chain decoding, byte accounting and a shared work allowance, and encoding, with the chain's unit tests, its property tests and its fuzz target. The code is unchanged apart from the imports of the moved codecs; FilterError is craft-stream-codecs' CodecError under its old name. * craft-stream-codecs: bounded JBIG2 decoding (decode_jbig2_within) The JBIG2 decoding entry of pdfcraft-filters (PdfCraft revision 80e26e674d1aa33078e83c8139875047f3289eb6, src/jbig2/decode.rs) with its tests. It spends from the caller's work allowance through hayro-jbig2's Image::decode_within and charge_reading, which come with fix/sec-hayro-jbig2-followups (#886). * vendor/README.craft-reader.md: one #831 paragraph, the follow-ups after it * craft-pdf: filters re-exports decode_jbig2_within (and lib.rs module order) * craft-pdf: the object layer from PdfCraft (`cos`) Adds the `cos` feature: PdfCraft's pdfcraft-cos crate (revision 1d2af9907ba772b368f6b54811359805fa5428e9) as craft_pdf::cos, on crypt and filters, with its unit tests, integration tests and examples. Its test helpers come with it: pdfcraft-testkit as src/cos/testkit.rs (cfg(test)) and the qpdf runner of pdfcraft-oracle as tests/cos/oracle.rs. The code is unchanged apart from module paths and doc comments. The child test of file_identifier is named by its module path, since the integration tests are one binary. * craft-pdf: cos unit tests build for wasm The property tests in src/cos/writer.rs need proptest, a dev-dependency of the non-wasm targets only, and one test in src/cos/document/tests.rs times a load on a thread, which wasm32-unknown-unknown does not have. Both are compiled for non-wasm targets only; the other unit tests still build for wasm.
117 lines
4.5 KiB
Rust
117 lines
4.5 KiB
Rust
//! `serialize` writes integers, references, hexadecimal strings, octal escapes and `#xx` name
|
|
//! escapes with its own digit loops. They must give the bytes the standard formatter gives.
|
|
|
|
use craft_pdf::cos::{ObjRef, Object, PdfString, serialize};
|
|
use proptest::prelude::*;
|
|
|
|
fn bytes_of(o: &Object) -> Vec<u8> {
|
|
let mut v = Vec::new();
|
|
serialize(o, &mut v);
|
|
v
|
|
}
|
|
|
|
#[test]
|
|
fn integer_extremes_and_digit_boundaries() {
|
|
let mut cases = vec![0i64, 1, -1, 9, 10, 99, 100, i64::MAX, i64::MIN, i64::MIN + 1, i64::from(i32::MAX), i64::from(i32::MIN)];
|
|
let mut p = 1i64;
|
|
while let Some(next) = p.checked_mul(10) {
|
|
cases.extend([next - 1, next, next + 1, -next]);
|
|
p = next;
|
|
}
|
|
for i in cases {
|
|
assert_eq!(bytes_of(&Object::Int(i)), i.to_string().into_bytes(), "{i}");
|
|
}
|
|
}
|
|
|
|
#[test]
|
|
fn reference_extremes() {
|
|
for (n, g) in [(0, 0), (1, 0), (u32::MAX, u16::MAX), (10, 65535), (4_000_000_000, 7)] {
|
|
assert_eq!(bytes_of(&Object::Ref(ObjRef::new(n, g))), format!("{n} {g} R").into_bytes());
|
|
}
|
|
}
|
|
|
|
#[test]
|
|
fn every_byte_value_in_hex_strings_octal_escapes_and_names() {
|
|
let all: Vec<u8> = (0..=255).collect();
|
|
let hex: String = all.iter().map(|b| format!("{b:02X}")).collect();
|
|
assert_eq!(bytes_of(&Object::String(PdfString { bytes: all.clone(), hex: true })), format!("<{hex}>").into_bytes());
|
|
// A literal string with a few control bytes escapes them in octal.
|
|
let lit = bytes_of(&Object::String(PdfString { bytes: b"abcdefghijkl\x01\x7f\xffz".to_vec(), hex: false }));
|
|
assert_eq!(lit, b"(abcdefghijkl\\001\\177\\377z)");
|
|
let name = bytes_of(&Object::Name(all.clone()));
|
|
let mut want = b"/".to_vec();
|
|
for &b in &all {
|
|
let regular = (b'!'..=b'~').contains(&b) && !matches!(b, b'(' | b')' | b'<' | b'>' | b'[' | b']' | b'{' | b'}' | b'/' | b'%' | b'#');
|
|
if regular {
|
|
want.push(b);
|
|
} else {
|
|
want.extend_from_slice(format!("#{b:02X}").as_bytes());
|
|
}
|
|
}
|
|
assert_eq!(name, want);
|
|
}
|
|
|
|
#[test]
|
|
fn whole_real_at_i32_min_stays_a_real_token() {
|
|
// -2^31 is outside the Annex C integer range (±2^31-1), so it keeps its trailing point.
|
|
assert_eq!(bytes_of(&Object::Real(f64::from(i32::MIN))), b"-2147483648.");
|
|
}
|
|
|
|
proptest! {
|
|
#[test]
|
|
fn integers_match_the_formatter(i in any::<i64>()) {
|
|
prop_assert_eq!(bytes_of(&Object::Int(i)), format!("{i}").into_bytes());
|
|
}
|
|
|
|
#[test]
|
|
fn whole_reals_match_the_formatter(i in -i32::MAX..=i32::MAX) {
|
|
prop_assert_eq!(bytes_of(&Object::Real(f64::from(i))), format!("{i}").into_bytes());
|
|
}
|
|
|
|
#[test]
|
|
fn references_match_the_formatter(n in any::<u32>(), g in any::<u16>()) {
|
|
prop_assert_eq!(bytes_of(&Object::Ref(ObjRef::new(n, g))), format!("{n} {g} R").into_bytes());
|
|
}
|
|
|
|
#[test]
|
|
fn hex_strings_match_the_formatter(bytes in proptest::collection::vec(any::<u8>(), 0..300)) {
|
|
let mut want = String::from("<");
|
|
for b in &bytes {
|
|
want.push_str(&format!("{b:02X}"));
|
|
}
|
|
want.push('>');
|
|
prop_assert_eq!(bytes_of(&Object::String(PdfString { bytes, hex: true })), want.into_bytes());
|
|
}
|
|
|
|
#[test]
|
|
fn binary_literal_strings_match_the_formatter(bytes in proptest::collection::vec(any::<u8>(), 0..300)) {
|
|
// Mostly-binary input is written as hex; mostly-text input with escapes is a literal.
|
|
let got = bytes_of(&Object::String(PdfString { bytes: bytes.clone(), hex: false }));
|
|
let binary = bytes.iter().filter(|b| !(b' '..=b'~').contains(*b) && !matches!(b, b'\n' | b'\r' | b'\t')).count();
|
|
let mut want = Vec::new();
|
|
if binary * 4 > bytes.len().max(1) {
|
|
want.push(b'<');
|
|
for b in &bytes {
|
|
want.extend_from_slice(format!("{b:02X}").as_bytes());
|
|
}
|
|
want.push(b'>');
|
|
} else {
|
|
want.push(b'(');
|
|
for &b in &bytes {
|
|
match b {
|
|
b'(' | b')' | b'\\' => want.extend_from_slice(&[b'\\', b]),
|
|
b'\n' => want.extend_from_slice(b"\\n"),
|
|
b'\r' => want.extend_from_slice(b"\\r"),
|
|
b'\t' => want.extend_from_slice(b"\\t"),
|
|
0x08 => want.extend_from_slice(b"\\b"),
|
|
0x0C => want.extend_from_slice(b"\\f"),
|
|
b' '..=b'~' => want.push(b),
|
|
_ => want.extend_from_slice(format!("\\{b:03o}").as_bytes()),
|
|
}
|
|
}
|
|
want.push(b')');
|
|
}
|
|
prop_assert_eq!(got, want);
|
|
}
|
|
}
|