style: Add an atom bit to know whether we're ascii lowercase.

And thus massively speed up ascii-case-insensitive atom comparisons when both
atoms are lowercase (which is the common case by far).

This removes almost all the slow selector-matching in this page, and it seems
an easier fix than storing the lowercased version of all class-names in quirks
mode in elements and selectors...

Differential Revision: https://phabricator.services.mozilla.com/D10945

components/style/gecko/regen_atoms.py

@@ -16,8 +16,8 @@ sys.path.insert(0, os.path.join(os.path.dirname(GECKO_DIR), "properties"))
 import build
 
 
-# Matches lines like `GK_ATOM(foo, "foo", 0x12345678, nsStaticAtom, PseudoElementAtom)`.
-PATTERN = re.compile('^GK_ATOM\(([^,]*),[^"]*"([^"]*)",\s*(0x[0-9a-f]+),\s*([^,]*),\s*([^)]*)\)',
+# Matches lines like `GK_ATOM(foo, "foo", 0x12345678, true, nsStaticAtom, PseudoElementAtom)`.
+PATTERN = re.compile('^GK_ATOM\(([^,]*),[^"]*"([^"]*)",\s*(0x[0-9a-f]+),\s*[^,]*,\s*([^,]*),\s*([^)]*)\)',
                      re.MULTILINE)
 FILE = "include/nsGkAtomList.h"
 

components/style/gecko_string_cache/mod.rs

@@ -175,13 +175,19 @@ impl WeakAtom {
     /// Returns whether this atom is static.
     #[inline]
     pub fn is_static(&self) -> bool {
-        unsafe { (*self.as_ptr()).mIsStatic() != 0 }
+        self.0.mIsStatic() != 0
+    }
+
+    /// Returns whether this atom is ascii lowercase.
+    #[inline]
+    fn is_ascii_lowercase(&self) -> bool {
+        self.0.mIsAsciiLowercase() != 0
     }
 
     /// Returns the length of the atom string.
     #[inline]
     pub fn len(&self) -> u32 {
-        unsafe { (*self.as_ptr()).mLength() }
+        self.0.mLength()
     }
 
     /// Returns whether this atom is the empty string.
@@ -199,41 +205,54 @@ impl WeakAtom {
 
     /// Convert this atom to ASCII lower-case
     pub fn to_ascii_lowercase(&self) -> Atom {
-        let slice = self.as_slice();
-        match slice
-            .iter()
-            .position(|&char16| (b'A' as u16) <= char16 && char16 <= (b'Z' as u16))
-        {
-            None => self.clone(),
-            Some(i) => {
-                let mut buffer: [u16; 64] = unsafe { mem::uninitialized() };
-                let mut vec;
-                let mutable_slice = if let Some(buffer_prefix) = buffer.get_mut(..slice.len()) {
-                    buffer_prefix.copy_from_slice(slice);
-                    buffer_prefix
-                } else {
-                    vec = slice.to_vec();
-                    &mut vec
-                };
-                for char16 in &mut mutable_slice[i..] {
-                    if *char16 <= 0x7F {
-                        *char16 = (*char16 as u8).to_ascii_lowercase() as u16
-                    }
-                }
-                Atom::from(&*mutable_slice)
-            },
+        if self.is_ascii_lowercase() {
+            return self.clone();
         }
+
+        let slice = self.as_slice();
+        let mut buffer: [u16; 64] = unsafe { mem::uninitialized() };
+        let mut vec;
+        let mutable_slice = if let Some(buffer_prefix) = buffer.get_mut(..slice.len()) {
+            buffer_prefix.copy_from_slice(slice);
+            buffer_prefix
+        } else {
+            vec = slice.to_vec();
+            &mut vec
+        };
+        for char16 in &mut *mutable_slice {
+            if *char16 <= 0x7F {
+                *char16 = (*char16 as u8).to_ascii_lowercase() as u16
+            }
+        }
+        Atom::from(&*mutable_slice)
     }
 
     /// Return whether two atoms are ASCII-case-insensitive matches
+    #[inline]
     pub fn eq_ignore_ascii_case(&self, other: &Self) -> bool {
         if self == other {
             return true;
         }
 
+        // If we know both atoms are ascii-lowercase, then we can stick with
+        // pointer equality.
+        if self.is_ascii_lowercase() && other.is_ascii_lowercase() {
+            debug_assert!(!self.eq_ignore_ascii_case_slow(other));
+            return false;
+        }
+
+        self.eq_ignore_ascii_case_slow(other)
+    }
+
+    fn eq_ignore_ascii_case_slow(&self, other: &Self) -> bool {
         let a = self.as_slice();
         let b = other.as_slice();
-        a.len() == b.len() && a.iter().zip(b).all(|(&a16, &b16)| {
+
+        if a.len() != b.len() {
+            return false;
+        }
+
+        a.iter().zip(b).all(|(&a16, &b16)| {
             if a16 <= 0x7F && b16 <= 0x7F {
                 (a16 as u8).eq_ignore_ascii_case(&(b16 as u8))
             } else {
@@ -241,13 +260,6 @@ impl WeakAtom {
             }
         })
     }
-
-    /// Return whether this atom is an ASCII-case-insensitive match for the given string
-    pub fn eq_str_ignore_ascii_case(&self, other: &str) -> bool {
-        self.chars()
-            .map(|r| r.map(|c: char| c.to_ascii_lowercase()))
-            .eq(other.chars().map(|c: char| Ok(c.to_ascii_lowercase())))
-    }
 }
 
 impl fmt::Debug for WeakAtom {