Merge pull request #4878 from vangel76/perf/cos-serialize-fmt-4870

perf(cos): write hex strings, integers and references without the formatter

crates/cos/src/writer.rs

@@ -23,9 +23,7 @@ pub fn serialize(o: &Object, out: &mut Vec<u8>) {
     match o {
         Object::Null => out.extend_from_slice(b"null"),
         Object::Bool(b) => out.extend_from_slice(if *b { b"true" } else { b"false" }),
-        Object::Int(i) => {
-            let _ = write!(out, "{i}");
-        }
+        Object::Int(i) => write_int(*i, out),
         Object::Real(r) => write_real(*r, out),
         Object::String(s) => write_string(s, out),
         Object::Name(n) => write_name(n, out),
@@ -42,11 +40,46 @@ pub fn serialize(o: &Object, out: &mut Vec<u8>) {
         Object::Dict(d) => write_dict(d, out),
         Object::Stream(s) => write_stream(s, out),
         Object::Ref(r) => {
-            let _ = write!(out, "{} {} R", r.num, r.generation);
+            write_digits(u64::from(r.num), out);
+            out.push(b' ');
+            write_digits(u64::from(r.generation), out);
+            out.extend_from_slice(b" R");
         }
     }
 }
 
+/// Upper-case hexadecimal digits.
+const HEX: &[u8; 16] = b"0123456789ABCDEF";
+
+/// The decimal digits of `v`, the same bytes `write!(out, "{v}")` gives, without the formatter.
+fn write_digits(mut v: u64, out: &mut Vec<u8>) {
+    // `u64::MAX` has 20 digits, so `at` never goes below 0.
+    let mut buf = [0u8; 20];
+    let mut at = buf.len();
+    loop {
+        at -= 1;
+        buf[at] = b'0' + (v % 10) as u8;
+        v /= 10;
+        if v == 0 {
+            break;
+        }
+    }
+    out.extend_from_slice(&buf[at..]);
+}
+
+/// A signed integer in decimal, as `write!(out, "{i}")` writes it.
+fn write_int(i: i64, out: &mut Vec<u8>) {
+    if i < 0 {
+        out.push(b'-');
+    }
+    write_digits(i.unsigned_abs(), out);
+}
+
+/// `b` as two upper-case hexadecimal digits.
+fn hex_pair(b: u8) -> [u8; 2] {
+    [HEX[usize::from(b >> 4)], HEX[usize::from(b & 15)]]
+}
+
 fn write_real(r: f64, out: &mut Vec<u8>) {
     if !r.is_finite() {
         out.push(b'0');
@@ -55,7 +88,7 @@ fn write_real(r: f64, out: &mut Vec<u8>) {
     // A whole number is written as an integer only within the integer range Annex C gives
     // (±2³¹−1), so `4e9` or `1e30` stays a real token for readers with 32-bit integers.
     if r.fract() == 0.0 && r.abs() <= f64::from(i32::MAX) {
-        let _ = write!(out, "{}", r as i32);
+        write_int(i64::from(r as i32), out);
         return;
     }
     // Plain decimal notation (§7.3.3 has no exponents). Rust's `Display` for f64 prints the
@@ -76,7 +109,8 @@ fn write_name(n: &[u8], out: &mut Vec<u8>) {
         if regular {
             out.push(b);
         } else {
-            let _ = write!(out, "#{b:02X}");
+            out.push(b'#');
+            out.extend_from_slice(&hex_pair(b));
         }
     }
 }
@@ -84,9 +118,10 @@ fn write_name(n: &[u8], out: &mut Vec<u8>) {
 fn write_string(s: &PdfString, out: &mut Vec<u8>) {
     let binary = s.bytes.iter().filter(|b| !(b' '..=b'~').contains(*b) && !matches!(b, b'\n' | b'\r' | b'\t')).count();
     if s.hex || binary * 4 > s.bytes.len().max(1) {
+        out.reserve(s.bytes.len().saturating_mul(2).saturating_add(2));
         out.push(b'<');
-        for b in &s.bytes {
-            let _ = write!(out, "{b:02X}");
+        for &b in &s.bytes {
+            out.extend_from_slice(&hex_pair(b));
         }
         out.push(b'>');
         return;
@@ -105,7 +140,7 @@ fn write_string(s: &PdfString, out: &mut Vec<u8>) {
             0x0C => out.extend_from_slice(b"\\f"),
             b' '..=b'~' => out.push(b),
             _ => {
-                let _ = write!(out, "\\{b:03o}");
+                out.extend_from_slice(&[b'\\', b'0' + (b >> 6), b'0' + ((b >> 3) & 7), b'0' + (b & 7)]);
             }
         }
     }

crates/cos/tests/it/main.rs

@@ -5,5 +5,6 @@ mod corpus;
 mod encryption;
 mod generations;
 mod proptests;
+mod serialize_format;
 mod shared_streams;
 mod writer;

crates/cos/tests/it/serialize_format.rs

@@ -0,0 +1,116 @@
+//! `serialize` writes integers, references, hexadecimal strings, octal escapes and `#xx` name
+//! escapes with its own digit loops. They must give the bytes the standard formatter gives.
+
+use pdfcraft_cos::{ObjRef, Object, PdfString, serialize};
+use proptest::prelude::*;
+
+fn bytes_of(o: &Object) -> Vec<u8> {
+    let mut v = Vec::new();
+    serialize(o, &mut v);
+    v
+}
+
+#[test]
+fn integer_extremes_and_digit_boundaries() {
+    let mut cases = vec![0i64, 1, -1, 9, 10, 99, 100, i64::MAX, i64::MIN, i64::MIN + 1, i64::from(i32::MAX), i64::from(i32::MIN)];
+    let mut p = 1i64;
+    while let Some(next) = p.checked_mul(10) {
+        cases.extend([next - 1, next, next + 1, -next]);
+        p = next;
+    }
+    for i in cases {
+        assert_eq!(bytes_of(&Object::Int(i)), i.to_string().into_bytes(), "{i}");
+    }
+}
+
+#[test]
+fn reference_extremes() {
+    for (n, g) in [(0, 0), (1, 0), (u32::MAX, u16::MAX), (10, 65535), (4_000_000_000, 7)] {
+        assert_eq!(bytes_of(&Object::Ref(ObjRef::new(n, g))), format!("{n} {g} R").into_bytes());
+    }
+}
+
+#[test]
+fn every_byte_value_in_hex_strings_octal_escapes_and_names() {
+    let all: Vec<u8> = (0..=255).collect();
+    let hex: String = all.iter().map(|b| format!("{b:02X}")).collect();
+    assert_eq!(bytes_of(&Object::String(PdfString { bytes: all.clone(), hex: true })), format!("<{hex}>").into_bytes());
+    // A literal string with a few control bytes escapes them in octal.
+    let lit = bytes_of(&Object::String(PdfString { bytes: b"abcdefghijkl\x01\x7f\xffz".to_vec(), hex: false }));
+    assert_eq!(lit, b"(abcdefghijkl\\001\\177\\377z)");
+    let name = bytes_of(&Object::Name(all.clone()));
+    let mut want = b"/".to_vec();
+    for &b in &all {
+        let regular = (b'!'..=b'~').contains(&b) && !matches!(b, b'(' | b')' | b'<' | b'>' | b'[' | b']' | b'{' | b'}' | b'/' | b'%' | b'#');
+        if regular {
+            want.push(b);
+        } else {
+            want.extend_from_slice(format!("#{b:02X}").as_bytes());
+        }
+    }
+    assert_eq!(name, want);
+}
+
+#[test]
+fn whole_real_at_i32_min_stays_a_real_token() {
+    // -2^31 is outside the Annex C integer range (±2^31-1), so it keeps its trailing point.
+    assert_eq!(bytes_of(&Object::Real(f64::from(i32::MIN))), b"-2147483648.");
+}
+
+proptest! {
+    #[test]
+    fn integers_match_the_formatter(i in any::<i64>()) {
+        prop_assert_eq!(bytes_of(&Object::Int(i)), format!("{i}").into_bytes());
+    }
+
+    #[test]
+    fn whole_reals_match_the_formatter(i in -i32::MAX..=i32::MAX) {
+        prop_assert_eq!(bytes_of(&Object::Real(f64::from(i))), format!("{i}").into_bytes());
+    }
+
+    #[test]
+    fn references_match_the_formatter(n in any::<u32>(), g in any::<u16>()) {
+        prop_assert_eq!(bytes_of(&Object::Ref(ObjRef::new(n, g))), format!("{n} {g} R").into_bytes());
+    }
+
+    #[test]
+    fn hex_strings_match_the_formatter(bytes in proptest::collection::vec(any::<u8>(), 0..300)) {
+        let mut want = String::from("<");
+        for b in &bytes {
+            want.push_str(&format!("{b:02X}"));
+        }
+        want.push('>');
+        prop_assert_eq!(bytes_of(&Object::String(PdfString { bytes, hex: true })), want.into_bytes());
+    }
+
+    #[test]
+    fn binary_literal_strings_match_the_formatter(bytes in proptest::collection::vec(any::<u8>(), 0..300)) {
+        // Mostly-binary input is written as hex; mostly-text input with escapes is a literal.
+        let got = bytes_of(&Object::String(PdfString { bytes: bytes.clone(), hex: false }));
+        let binary = bytes.iter().filter(|b| !(b' '..=b'~').contains(*b) && !matches!(b, b'\n' | b'\r' | b'\t')).count();
+        let mut want = Vec::new();
+        if binary * 4 > bytes.len().max(1) {
+            want.push(b'<');
+            for b in &bytes {
+                want.extend_from_slice(format!("{b:02X}").as_bytes());
+            }
+            want.push(b'>');
+        } else {
+            want.push(b'(');
+            for &b in &bytes {
+                match b {
+                    b'(' | b')' | b'\\' => want.extend_from_slice(&[b'\\', b]),
+                    b'\n' => want.extend_from_slice(b"\\n"),
+                    b'\r' => want.extend_from_slice(b"\\r"),
+                    b'\t' => want.extend_from_slice(b"\\t"),
+                    0x08 => want.extend_from_slice(b"\\b"),
+                    0x0C => want.extend_from_slice(b"\\f"),
+                    b' '..=b'~' => want.push(b),
+                    _ => want.extend_from_slice(format!("\\{b:03o}").as_bytes()),
+                }
+            }
+            want.push(b')');
+        }
+        prop_assert_eq!(got, want);
+    }
+}