shifathosn
/
pdfcraft
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Tests: normalize generated streams in Arabic output golden (#1275) 

* Make Arabic output golden independent of Flate backend

* Arabic golden: keep /Filter and /DecodeParms in the hashed bytes

Normalise only the raw stream bytes (and so /Length, which the writer
takes from them), so a change that stops compressing generated streams or
switches filters still fails the golden. Fingerprint recomputed (same with
and without craft-fonts).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Brandon Thomas <echelon@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Earl Co 2026-10-12 08:54:21 +02:00 committed by GitHub
parent 51359beaea
commit 4e53e5ffbd
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 25 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
crates/edit/src/added/arabic_tests.rs
View File

@ -6,9 +6,9 @@ use std::cell::Cell;
use super::*;
/// The fingerprint of an item below the old limit, from the code before the change: its content
/// stream, its new fonts and every object of the document.
const SMALL_ITEM_FINGERPRINT: u64 = 14_135_892_979_695_233_112;
/// Regression fingerprint for the small-item fixture: drawing bytes, font map and document
/// objects, with generated streams decoded so Flate backend selection cannot change the hash.
const SMALL_ITEM_FINGERPRINT: u64 = 4_811_174_621_764_261_623;
/// A cluster that shows one character with the single glyph `id`, at `advance` em.
fn cluster(id: u32, advance: f64) -> ShapedCluster {
@ -43,6 +43,25 @@ fn snapshot(doc: &Document) -> Vec<u8> {
bytes
}
/// Serialize generated objects with decoded stream bytes so the golden does not depend on which
/// Flate backend Cargo's unified dependency features select for the test binary. Only the raw
/// bytes (and so `/Length`, which the writer takes from them) are normalised: `/Filter` and
/// `/DecodeParms` stay in the hash, so a change that stops compressing generated streams, or
/// switches filters, still fails the golden.
fn golden_snapshot(doc: &Document) -> Vec<u8> {
let mut bytes = Vec::new();
for num in doc.object_numbers() {
let mut obj = (*doc.get(ObjRef { num, generation: doc.generation(num) })).clone();
if let Object::Stream(ref mut stream) = obj {
let decoded = stream.decoded_strict().expect("generated stream decodes");
stream.raw = decoded.into();
}
pdfcraft_cos::serialize(&obj, &mut bytes);
bytes.push(b'\n');
}
bytes
}
/// The fonts an item drew, in creation order, with their glyph counts.
fn fonts_of(doc: &Document, fonts: &Dict) -> Vec<(Vec<u8>, usize)> {
fonts
@ -133,7 +152,7 @@ fn an_item_below_the_old_limit_is_drawn_exactly_as_before() {
assert_eq!(fonts.len(), 1);
// The injected outlines are fixed; only the descriptor's family comes from craft-fonts.
// Check that metadata separately, then normalize those two fields to the original golden.
// Every drawing byte and every other object field must still match, in both build modes.
// The drawing bytes and semantic object fields must match in both font build modes.
let family = pdfcraft_fonts::document_arabic_font().map_or("Arabic", |face| face.family);
for (_, font) in fonts.iter() {
let descriptor = doc.dict(font).unwrap().get(b"FontDescriptor").and_then(Object::as_ref).unwrap();
@ -148,8 +167,8 @@ fn an_item_below_the_old_limit_is_drawn_exactly_as_before() {
}
let mut bytes = out.clone();
pdfcraft_cos::serialize(&Object::Dict(fonts.clone()), &mut bytes);
bytes.extend(snapshot(&doc));
assert_eq!(fnv1a(&bytes), SMALL_ITEM_FINGERPRINT, "output changed; the golden is the code before the sharding change");
bytes.extend(golden_snapshot(&doc));
assert_eq!(fnv1a(&bytes), SMALL_ITEM_FINGERPRINT, "small-item output changed");
}
#[test]