From 6524acf04bd10c1459bba2db18f1a34100c0b241 Mon Sep 17 00:00:00 2001
From: ltdk <usr@ltdk.xyz>
Date: Tue, 28 May 2024 14:27:25 -0400
Subject: [PATCH] Optimize escape_ascii

---
 library/core/src/escape.rs  | 112 +++++++++++++++++++++++++++++-------
 library/core/tests/ascii.rs |  22 ++++++-
 2 files changed, 109 insertions(+), 25 deletions(-)

diff --git a/library/core/src/escape.rs b/library/core/src/escape.rs
index b213cc2b916..0685f525dca 100644
--- a/library/core/src/escape.rs
+++ b/library/core/src/escape.rs
@@ -18,38 +18,106 @@
     (output, 0..2)
 }
 
+#[inline]
+const fn hex_escape<const N: usize>(byte: u8) -> ([ascii::Char; N], Range<u8>) {
+    const { assert!(N >= 4) };
+
+    let mut output = [ascii::Char::Null; N];
+
+    let hi = HEX_DIGITS[(byte >> 4) as usize];
+    let lo = HEX_DIGITS[(byte & 0xf) as usize];
+
+    output[0] = ascii::Char::ReverseSolidus;
+    output[1] = ascii::Char::SmallX;
+    output[2] = hi;
+    output[3] = lo;
+
+    (output, 0..4)
+}
+
+#[inline]
+const fn verbatim<const N: usize>(a: ascii::Char) -> ([ascii::Char; N], Range<u8>) {
+    const { assert!(N >= 1) };
+
+    let mut output = [ascii::Char::Null; N];
+
+    output[0] = a;
+
+    (output, 0..1)
+}
+
 /// Escapes an ASCII character.
 ///
 /// Returns a buffer and the length of the escaped representation.
 const fn escape_ascii<const N: usize>(byte: u8) -> ([ascii::Char; N], Range<u8>) {
     const { assert!(N >= 4) };
 
-    match byte {
-        b'\t' => backslash(ascii::Char::SmallT),
-        b'\r' => backslash(ascii::Char::SmallR),
-        b'\n' => backslash(ascii::Char::SmallN),
-        b'\\' => backslash(ascii::Char::ReverseSolidus),
-        b'\'' => backslash(ascii::Char::Apostrophe),
-        b'\"' => backslash(ascii::Char::QuotationMark),
-        byte => {
-            let mut output = [ascii::Char::Null; N];
+    #[cfg(feature = "optimize_for_size")]
+    {
+        match byte {
+            b'\t' => backslash(ascii::Char::SmallT),
+            b'\r' => backslash(ascii::Char::SmallR),
+            b'\n' => backslash(ascii::Char::SmallN),
+            b'\\' => backslash(ascii::Char::ReverseSolidus),
+            b'\'' => backslash(ascii::Char::Apostrophe),
+            b'"' => backslash(ascii::Char::QuotationMark),
+            0x00..=0x1F | 0x7F => hex_escape(byte),
+            _ => match ascii::Char::from_u8(byte) {
+                Some(a) => verbatim(a),
+                None => hex_escape(byte),
+            },
+        }
+    }
 
-            if let Some(c) = byte.as_ascii()
-                && !byte.is_ascii_control()
-            {
-                output[0] = c;
-                (output, 0..1)
-            } else {
-                let hi = HEX_DIGITS[(byte >> 4) as usize];
-                let lo = HEX_DIGITS[(byte & 0xf) as usize];
+    #[cfg(not(feature = "optimize_for_size"))]
+    {
+        /// Lookup table helps us determine how to display character.
+        ///
+        /// Since ASCII characters will always be 7 bits, we can exploit this to store the 8th bit to
+        /// indicate whether the result is escaped or unescaped.
+        ///
+        /// We additionally use 0x80 (escaped NUL character) to indicate hex-escaped bytes, since
+        /// escaped NUL will not occur.
+        const LOOKUP: [u8; 256] = {
+            let mut arr = [0; 256];
+            let mut idx = 0;
+            while idx <= 255 {
+                arr[idx] = match idx as u8 {
+                    // use 8th bit to indicate escaped
+                    b'\t' => 0x80 | b't',
+                    b'\r' => 0x80 | b'r',
+                    b'\n' => 0x80 | b'n',
+                    b'\\' => 0x80 | b'\\',
+                    b'\'' => 0x80 | b'\'',
+                    b'"' => 0x80 | b'"',
 
-                output[0] = ascii::Char::ReverseSolidus;
-                output[1] = ascii::Char::SmallX;
-                output[2] = hi;
-                output[3] = lo;
+                    // use NUL to indicate hex-escaped
+                    0x00..=0x1F | 0x7F..=0xFF => 0x80 | b'\0',
 
-                (output, 0..4)
+                    idx => idx,
+                };
+                idx += 1;
             }
+            arr
+        };
+
+        let lookup = LOOKUP[byte as usize];
+
+        // 8th bit indicates escape
+        let lookup_escaped = lookup & 0x80 != 0;
+
+        // SAFETY: We explicitly mask out the eighth bit to get a 7-bit ASCII character.
+        let lookup_ascii = unsafe { ascii::Char::from_u8_unchecked(lookup & 0x7F) };
+
+        if lookup_escaped {
+            // NUL indicates hex-escaped
+            if matches!(lookup_ascii, ascii::Char::Null) {
+                hex_escape(byte)
+            } else {
+                backslash(lookup_ascii)
+            }
+        } else {
+            verbatim(lookup_ascii)
         }
     }
 }
diff --git a/library/core/tests/ascii.rs b/library/core/tests/ascii.rs
index 3d3f8ac10c6..ce09ee507f1 100644
--- a/library/core/tests/ascii.rs
+++ b/library/core/tests/ascii.rs
@@ -481,9 +481,25 @@ pub fn run() {
 }
 
 #[test]
-fn test_ascii_display() {
-    assert_eq!(b"foo'bar".escape_ascii().to_string(), r#"foo\'bar"#);
-    assert_eq!(b"\0\xff".escape_ascii().to_string(), r#"\x00\xff"#);
+fn test_escape_ascii() {
+    let mut buf = [0u8; 0x1F + 7]; // 0..=0x1F plus two quotes, slash, \x7F, \x80, \xFF
+    for idx in 0..=0x1F {
+        buf[idx] = idx as u8;
+    }
+    buf[0x20] = b'\'';
+    buf[0x21] = b'"';
+    buf[0x22] = b'\\';
+    buf[0x23] = 0x7F;
+    buf[0x24] = 0x80;
+    buf[0x25] = 0xff;
+    assert_eq!(
+        buf.escape_ascii().to_string(),
+        r#"\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f\'\"\\\x7f\x80\xff"#
+    );
+}
+
+#[test]
+fn test_escape_ascii_iter() {
     let mut it = b"\0fastpath\xffremainder\xff".escape_ascii();
     let _ = it.advance_by(4);
     let _ = it.advance_back_by(4);