diff --git a/crates/audit/src/cover.rs b/crates/audit/src/cover.rs index 3df666c19..516bb193d 100644 --- a/crates/audit/src/cover.rs +++ b/crates/audit/src/cover.rs @@ -16,7 +16,7 @@ //! Positions compare lexicographically in paint order. use pdfcraft_content::{Matrix, Op, Pieces, parse}; -use pdfcraft_cos::{Dict, Document, Object}; +use pdfcraft_cos::{DecodeBudget, Dict, Document, Object}; use crate::AuditError; @@ -109,6 +109,8 @@ struct Walker<'a> { pieces: &'a Pieces, out: Vec, ops_seen: usize, + /// Decoded bytes left for the page, its forms included: spending it fails the audit. + budget: DecodeBudget, } impl<'a> Walker<'a> { @@ -272,7 +274,7 @@ impl<'a> Walker<'a> { .unwrap_or(Matrix::IDENTITY); let sub_resources = dict.get(b"Resources").map(|o| self.doc.resolve(o)).and_then(|o| o.as_dict().cloned()).unwrap_or_default(); // A form stream that cannot be decoded fails the audit: it might hide a cover. - let data = stream.decoded_strict()?; + let data = self.budget.decode_strict(stream)?; let ops = parse(&data).ops; // The XObject matrix maps form space into the user space active at `Do`. let mut sub_gs = gs.clone(); @@ -304,7 +306,8 @@ fn ext_alpha(doc: &Document, resources: &Dict, name: &[u8]) -> f64 { /// Every opaque filled rectangle drawn by a page's content (and its form XObjects), with paint /// positions. A page's content streams are walked once, joined, with one graphics state, so /// state set in an earlier stream is still in force in the later ones. Any content stream that -/// cannot be decoded is an audit failure, never an empty result. +/// cannot be decoded, or content and forms that decode past one page's [`DecodeBudget`] in all, +/// is an audit failure, never an empty result. pub fn filled_rects(doc: &Document, page: &Dict) -> Result, AuditError> { let resources = page.get(b"Resources").map(|o| doc.resolve(o)).and_then(|o| o.as_dict().cloned()).unwrap_or_default(); let contents: Vec = match page.get(b"Contents") { @@ -314,15 +317,16 @@ pub fn filled_rects(doc: &Document, page: &Dict) -> Result, Audi _ => vec![c.clone()], }, }; + let mut budget = DecodeBudget::page(); let mut streams = Vec::with_capacity(contents.len()); for c in &contents { if let Object::Stream(s) = &*doc.resolve(c) { - streams.push(s.decoded_strict()?); + streams.push(budget.decode_strict(s)?); } } let pieces = Pieces::join(&streams); let parsed = pieces.parse(); - let mut w = Walker { doc, pieces: &pieces, out: Vec::new(), ops_seen: 0 }; + let mut w = Walker { doc, pieces: &pieces, out: Vec::new(), ops_seen: 0, budget }; let mut gs = Gs::default(); let mut stack = Vec::new(); w.walk_ops(&parsed.ops, &mut gs, &mut stack, &resources, 0, None)?; diff --git a/crates/audit/src/tests.rs b/crates/audit/src/tests.rs index 4ca3b0bf5..8155c6dec 100644 --- a/crates/audit/src/tests.rs +++ b/crates/audit/src/tests.rs @@ -592,3 +592,22 @@ fn reading_blocks_respect_stream_comments_and_split_operands() { assert_eq!(text, "Replacement text", "{}", String::from_utf8_lossy(s1)); } } + +#[test] +fn repeated_stream_references_share_one_decode_budget() { + use pdfcraft_cos::{Dict, Document, Object, Stream}; + // One 1 MiB stream of spaces (a kilobyte on disk), named 300 times: by the page's /Contents, + // and by 300 draws of a form holding it. + let mut doc = Document::new_empty(); + let spaces = doc.add(Stream::flate(Dict::new(), &vec![b' '; 1 << 20])); + let contents: Dict = [(b"Contents".to_vec(), Object::Array(vec![Object::Ref(spaces); 300]))].into_iter().collect(); + assert!(crate::cover::filled_rects(&doc, &contents).is_err(), "repeated content streams"); + + let form_dict: Dict = [(b"Subtype".to_vec(), Object::Name(b"Form".to_vec()))].into_iter().collect(); + let form = doc.add(Stream::flate(form_dict, &vec![b' '; 1 << 20])); + let draws = doc.add(Stream::from_raw(Dict::new(), "/X Do ".repeat(300).into_bytes())); + let xobjects: Dict = [(b"X".to_vec(), Object::Ref(form))].into_iter().collect(); + let resources: Dict = [(b"XObject".to_vec(), Object::Dict(xobjects))].into_iter().collect(); + let page: Dict = [(b"Contents".to_vec(), Object::Ref(draws)), (b"Resources".to_vec(), Object::Dict(resources))].into_iter().collect(); + assert!(crate::cover::filled_rects(&doc, &page).is_err(), "repeated form draws"); +}