fix(preflight): find colour operators after any PDF whitespace (#1334) (#1373)

The PDF/A device-colour scan split content streams only on spaces and
line feeds, so `0 0 0 1 k` written with carriage returns, tabs, form
feeds or NULs between the tokens went unseen: verify reported no
DeviceCMYK, and convert gave the CMYK page an sRGB output intent.

Split on all six whitespace characters of ISO 32000-2 §7.2.3, using the
lexer's own `is_whitespace` (now exported from pdfcraft-cos) instead of
a second list.

Adds tests::device_colour_is_found_after_any_whitespace, which fails
before this change; its gray and RGB controls check that those pages
still get the sRGB output intent.

crates/cos/src/lib.rs

@@ -24,7 +24,7 @@ mod writer;
 pub use bytes::Bytes;
 pub use document::{Document, Revision, SourceIdentity, XrefEntry};
 pub use object::{Dict, MAX_DECODED, Name, ObjRef, Object, PdfString, Stream};
-pub use parser::{Lexer, parse_indirect};
+pub use parser::{Lexer, is_whitespace, parse_indirect};
 pub use pdfcraft_crypt::{
     Algorithm, Auth, Method as CryptMethod, NewEncryption, Permissions, SecurityHandler, effective_password, pdfdoc_byte, pdfdoc_char,
 };

crates/cos/src/parser.rs

@@ -11,7 +11,8 @@ use crate::{Bytes, CosError};
 
 const MAX_DEPTH: usize = 128;
 
-pub(crate) fn is_whitespace(b: u8) -> bool {
+/// One of the six PDF whitespace characters (ISO 32000-2 §7.2.3, Table 1).
+pub fn is_whitespace(b: u8) -> bool {
     matches!(b, b'\0' | b'\t' | b'\n' | b'\x0C' | b'\r' | b' ')
 }
 

crates/preflight/src/lib.rs

@@ -24,7 +24,7 @@
 pub mod icc;
 mod xmp;
 
-use pdfcraft_cos::{Dict, Document, ObjRef, Object, PdfString, Stream};
+use pdfcraft_cos::{Dict, Document, ObjRef, Object, PdfString, Stream, is_whitespace};
 
 /// The PDF/A part and conformance level.
 #[derive(Clone, Copy, Debug, PartialEq, Eq)]
@@ -287,8 +287,8 @@ fn uses_device_colour(doc: &Document, objs: &[(ObjRef, std::sync::Arc<Object>)])
             && let Ok(data) = s.decoded()
         {
             // Content streams: rg/RG/g/G/k/K operators.
-            for line in data.split(|b| *b == b'\n' || *b == b' ') {
-                match line {
+            for token in data.split(|b| is_whitespace(*b)) {
+                match token {
                     b"g" | b"G" => used.gray = true,
                     b"rg" | b"RG" => used.rgb = true,
                     b"k" | b"K" => used.cmyk = true,

crates/preflight/src/tests.rs

@@ -214,3 +214,39 @@ fn verify_reports_an_output_intent_that_does_not_match_device_colour() {
     let headed = format!("<< /Length 128 >>\nstream\n{header}\nendstream");
     assert!(!messages(&verify(&cmyk_page(intent, "/Im0 Do", &[&headed]), Level::A2b)).contains(&cmyk_msg));
 }
+
+/// Issue #1334: a colour operator is found whichever of the six PDF whitespace characters
+/// separates the tokens, not only after a space or a line feed.
+#[test]
+fn device_colour_is_found_after_any_whitespace() {
+    let page = |content: &[u8]| {
+        let content = String::from_utf8(content.to_vec()).unwrap();
+        let stream = format!("<< /Length {} >>\nstream\n{content}\nendstream", content.len());
+        build(
+            &[
+                "<< /Type /Catalog /Pages 2 0 R >>",
+                "<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 200 200] >>",
+                "<< /Type /Page /Parent 2 0 R /Contents 4 0 R /Resources << >> >>",
+                stream.as_str(),
+            ],
+            "",
+        )
+    };
+    let cmyk_msg = "DeviceCMYK is used: it needs a CMYK output intent (not added automatically)";
+    for separator in [b" ".as_slice(), b"\n", b"\r", b"\t", b"\x0C", b"\0"] {
+        let cmyk: &[&[u8]] = &[b"0", b"0", b"0", b"1", b"k", b"10", b"10", b"50", b"50", b"re", b"f"];
+        let mut doc = page(&cmyk.join(separator));
+        assert!(messages(&verify(&doc, Level::A2b)).contains(&cmyk_msg), "separator {separator:?}");
+        let r = convert(&mut doc, Level::A2b).unwrap();
+        assert!(declared(&doc).output_intents.is_empty(), "separator {separator:?}");
+        assert!(messages(&r.remaining).contains(&cmyk_msg), "separator {separator:?}");
+
+        // Gray and RGB still get the sRGB output intent.
+        for colour in [[b"0".as_slice(), b"g"].as_slice(), &[b"1", b"0", b"0", b"rg"]] {
+            let mut doc = page(&colour.join(separator));
+            let r = convert(&mut doc, Level::A2b).unwrap();
+            assert!(r.fixed.iter().any(|f| f.contains("output intent")), "separator {separator:?}: {:?}", r.fixed);
+            assert_eq!(declared(&doc).output_intents, ["sRGB IEC61966-2.1"], "separator {separator:?}");
+        }
+    }
+}