M2.6: autotagging's reason for content it can't decode reads as on main

Since autotagging reads page content through DecodeBudget::decode_strict, the reason it gave for
content that doesn't decode carried that error's own text, so it said twice that the data
couldn't be decoded: "content cannot be decoded strictly: stream data could not be decoded:
FlateDecode: …". It now gives the decoder's reason right after, as main does: "content cannot
be decoded strictly: FlateDecode: …".

Test: autotag_text_says_why_it_cannot_read_a_page now checks the decoder's reason follows the
prefix.

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 104e22904a
commit d1de0a4bad
2 files changed
+9 -3

No files matched your search

+7 -1
View File
@@ -66,7 +66,13 @@ fn content_bytes(doc: &Document, page: &pdfcraft_model::Page, index: usize) -> R
if budget.remaining() == 0 {
unsupported(index, "decoding the content takes more than 16 MiB")
} else {
unsupported(index, format!("content cannot be decoded strictly: {e}"))
// The decoder's own reason: `CosError::Filter`'s text would say again that the data
// couldn't be decoded.
let why = match e {
pdfcraft_cos::CosError::Filter(why) => why,
other => other.to_string(),
};
unsupported(index, format!("content cannot be decoded strictly: {why}"))
}
})?;
all.extend_from_slice(&decoded);
+2 -2
View File
@@ -113,7 +113,7 @@ fn autotag_text_reads_content_with_parameters_given_by_reference() {
}
/// 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.
/// 16 MiB, or content that doesn't decode strictly, with the decoder's reason right after.
#[test]
fn autotag_text_says_why_it_cannot_read_a_page() {
use pdfcraft_cos::{Dict, ObjRef, Stream};
@@ -138,7 +138,7 @@ fn autotag_text_says_why_it_cannot_read_a_page() {
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}");
assert!(why.starts_with("content cannot be decoded strictly: FlateDecode: "), "{why}");
}
#[test]