diff --git a/crates/cos/src/document/reader.rs b/crates/cos/src/document/reader.rs index 2797a04e9a..18f5ce848a 100644 --- a/crates/cos/src/document/reader.rs +++ b/crates/cos/src/document/reader.rs @@ -635,10 +635,20 @@ impl Document { // Offsets of objects that may be cross-reference streams: their dictionaries are the // trailers of files that have no `trailer` keyword (ยง7.5.8). let mut xref_streams = Vec::new(); - for (num, offset, generation, body) in object_headers(&data) { + let headers = object_headers(&data); + // Where `/XRef` occurs in the file, found in one pass. + let mut xref_marks = Vec::new(); + let mut mark_from = 0; + while let Some(p) = find(&data, b"/XRef", mark_from, data.len()) { + xref_marks.push(p); + mark_from = p + 1; + } + for &(num, offset, generation, body) in &headers { entries.insert(num, XrefEntry::InFile { offset, generation }); objstms.push(num); - if find(&data, b"/XRef", body, body.saturating_add(1024)).is_some() + // `/XRef` within the 1024 bytes after the header (the first one that is there). + let first = xref_marks.partition_point(|&p| p < body); + if xref_marks.get(first).is_some_and(|&p| p + 5 <= body.saturating_add(1024).min(data.len())) && let Ok(at) = usize::try_from(offset) { xref_streams.push(at); @@ -827,7 +837,33 @@ pub(crate) fn find(hay: &[u8], needle: &[u8], from: usize, to: usize) -> Option< if from >= to || needle.is_empty() || to - from < needle.len() { return None; } - hay[from..to].windows(needle.len()).position(|w| w == needle).map(|p| p + from) + let hay = &hay[from..to]; + // Look for the needle's rarest byte first, a plain byte scan, and compare the rest only there. + const COMMON: &[u8] = b" etaoinsrhldcumfpgwybvkxjqz"; + let (k, rare) = + needle.iter().copied().enumerate().max_by_key(|&(_, b)| COMMON.iter().position(|&c| c == b).unwrap_or(COMMON.len())).unwrap_or((0, 0)); + let mut i = k; + while let Some(p) = hay.get(i..).and_then(|rest| position_of(rest, rare)) { + let start = i + p - k; + if hay.get(start..start + needle.len()) == Some(needle) { + return Some(start + from); + } + i += p + 1; + } + None +} + +/// The first position of `byte` in `hay`. Whole 32-byte blocks are tested without branching, which +/// the compiler turns into vector compares; only a block that holds the byte is searched. +fn position_of(hay: &[u8], byte: u8) -> Option { + const BLOCK: usize = 32; + let (blocks, rest) = hay.as_chunks::(); + for (i, block) in blocks.iter().enumerate() { + if block.iter().fold(false, |any, &b| any | (b == byte)) { + return block.iter().position(|&b| b == byte).map(|p| i * BLOCK + p); + } + } + rest.iter().position(|&b| b == byte).map(|p| blocks.len() * BLOCK + p) } pub(super) fn rfind(hay: &[u8], needle: &[u8], from: usize) -> Option { diff --git a/crates/cos/src/document/tests.rs b/crates/cos/src/document/tests.rs index 2cab25e7f1..f69ffae042 100644 --- a/crates/cos/src/document/tests.rs +++ b/crates/cos/src/document/tests.rs @@ -2189,3 +2189,29 @@ fn the_editor_cache_charges_a_dictionary_for_the_values_it_holds() { let sum = cache.values().fold(0usize, |n, o| n.saturating_add(held_bytes(o, &doc.data, 0))); assert_eq!(cache.owned(), sum, "the kept total is the cache's own"); } + +#[test] +fn find_agrees_with_a_plain_window_search() { + let naive = |hay: &[u8], needle: &[u8], from: usize, to: usize| { + if from >= to || needle.is_empty() || to - from < needle.len() { + return None; + } + hay[from..to].windows(needle.len()).position(|w| w == needle).map(|p| p + from) + }; + let mut seed = 0x9E37_79B9_7F4A_7C15u64; + let mut next = move || { + seed ^= seed << 13; + seed ^= seed >> 7; + seed ^= seed << 17; + seed + }; + let alphabet = b"/XRef t\n<>0"; + for _ in 0..20_000 { + let hay: Vec = (0..next() % 200).map(|_| alphabet[(next() % alphabet.len() as u64) as usize]).collect(); + let needles: [&[u8]; 5] = [b"/XRef", b"trailer", b"R", b"ff", b"<<"]; + let needle = needles[(next() % 5) as usize]; + let from = (next() % (hay.len() as u64 + 1)) as usize; + let to = from + (next() % (hay.len() as u64 + 1 - from as u64)) as usize; + assert_eq!(find(&hay, needle, from, to), naive(&hay, needle, from, to), "{hay:?} {needle:?} {from} {to}"); + } +}