M2.6: a test pins why autotagging refuses a page it cannot read

Content past 16 MiB says so, and content that does not decode strictly says that: autotag_text_says_why_it_cannot_read_a_page. Mutation testing found nothing pinned which message each gets.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AmsdeUCdTaD72jkDw2pJKY
This commit is contained in:
Grzegorz MartensandClaude Opus 5.5 committed 2026-11-07 12:37:35 +01:00
1 parent d289038ca0
commit 477f0abd49
1 file changed
+29
+29
View File
@@ -112,6 +112,35 @@ fn autotag_text_reads_content_with_parameters_given_by_reference() {
assert!(text.contains("/F1 24 Tf") && text.contains("(Hello World) Tj"), "{text}");
}
/// Autotagging refuses a page whose content it can't read whole, and says why: content past
/// 16 MiB, or content that doesn't decode strictly.
#[test]
fn autotag_text_says_why_it_cannot_read_a_page() {
use pdfcraft_cos::{Dict, ObjRef, Stream};
let reason = |content: Stream| {
let mut doc = pdf(
&[
"<< /Type /Catalog /Pages 2 0 R >>".into(),
"<< /Type /Pages /Kids [3 0 R] /Count 1 >>".into(),
"<< /Type /Page /Parent 2 0 R /MediaBox [0 0 600 800] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> >>".into(),
stream(""),
FONT.into(),
],
"",
);
doc.set(ObjRef::new(4, 0), content);
match autotag_text(&mut doc) {
Err(AutoTagError::Unsupported { reason, .. }) => reason,
other => panic!("{other:?}"),
}
};
assert_eq!(reason(Stream::from_raw(Dict::new(), vec![b' '; 17 << 20])), "decoded content exceeds 16 MiB");
let mut corrupt = Stream::from_raw(Dict::new(), b"not zlib data".to_vec());
corrupt.dict.set(b"Filter".to_vec(), Object::name("FlateDecode"));
let why = reason(corrupt);
assert!(why.starts_with("content cannot be decoded strictly"), "{why}");
}
#[test]
fn autotag_text_refuses_paint_and_does_not_modify_the_document() {
let mut doc = pdf(