Better ASCII case-insensitive matching.

Author: SimonSapin

cssparser.rc

@@ -13,3 +13,94 @@ pub mod ast;
 
 #[cfg(test)]
 mod tests;
+
+
+/// Return whether `string` is an ASCII case-insensitive match for `reference`,
+/// where `reference` is already in ASCII lower-case.
+pub fn eq_ascii_lower(string: &str, reference: &str) -> bool {
+    #[inline]
+    fn eq(string: &str, reference: &str) -> bool {
+        for std::uint::range(0, string.len()) |i| {
+            if ASCII_LOWER_MAP[string[i]] != reference[i] {
+                return false
+            }
+        }
+        true
+    }
+
+    #[cfg(not(test))]
+    #[inline]
+    fn check_reference(_reference: &str) {}
+    #[cfg(test)]
+    #[inline]
+    fn check_reference(reference: &str) {
+        assert!(eq(reference, reference), ~"Reference must be ASCII lower case.");
+    }
+    check_reference(reference);
+
+    string.len() == reference.len() && eq(string, reference)
+}
+
+
+/// Return an ASCII lower-case copy of `string`:
+/// A-Z is replaced by a-z, non-ASCII letters are unchanged.
+pub fn to_ascii_lower(string: &str) -> ~str {
+    let mut lower = string.to_owned();
+    for std::uint::range(0, lower.len()) |i| {
+        lower[i] = ASCII_LOWER_MAP[lower[i]];
+    }
+    lower
+}
+
+
+#[test]
+fn test_ascii_lower() {
+    assert!(eq_ascii_lower("url()URL()uRl()Ürl", "url()url()url()Ürl"));
+    assert!(to_ascii_lower("url()URL()uRl()Ürl") == ~"url()url()url()Ürl");
+    // Dotted capital I, Kelvin sign, Sharp S.
+    assert!(eq_ascii_lower("HİKß", "hİKß"));
+    assert!(to_ascii_lower("HİKß") == ~"hİKß");
+
+    for std::uint::range(0, 128) |i| {
+        let c = i as char;
+        let lower = if 'A' <= c && c <= 'Z' { c + 'a' - 'A' } else { c };
+        assert!(ASCII_LOWER_MAP[i] as char == lower)
+    }
+}
+
+
+// This is UTF8-safe because only bytes in the ASCII range are affected.
+static ASCII_LOWER_MAP: &'static [u8] = &[
+    0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
+    0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
+    0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
+    0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f,
+    0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27,
+    0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f,
+    0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
+    0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f,
+    0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
+    0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f,
+    0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
+    0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f,
+    0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
+    0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f,
+    0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
+    0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f,
+    0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+    0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+    0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+    0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f,
+    0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7,
+    0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf,
+    0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7,
+    0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf,
+    0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7,
+    0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf,
+    0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7,
+    0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf,
+    0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7,
+    0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef,
+    0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7,
+    0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff,
+];

parser.rs

@@ -15,6 +15,7 @@ use std::vec;
 
 use ast::*;
 use tokenizer::*;
+use super::eq_ascii_lower;
 
 
 // TODO: Use a trait?
@@ -217,7 +218,7 @@ fn parse_declaration_important(iter: &mut ComponentValueIterator) -> bool {
         Some(Ident(value)) => value,
         _ => return false,
     };
-    if ascii_lower(ident_value) != ~"important" { return false }
+    if !eq_ascii_lower(ident_value, "important") { return false }
     match iter.next_non_whitespace() {
         Some(Semicolon) => true,
         None => true,

tokenizer.rs

@@ -7,6 +7,7 @@
 use std::{str, u32, vec};
 
 use ast::*;
+use super::eq_ascii_lower;
 
 
 pub struct Parser {
@@ -99,30 +100,9 @@ pub fn next_component_value(parser: &mut Parser) -> Option<ComponentValue> {
 }
 
 
-pub fn ascii_lower(string: &str) -> ~str {
-    // Warning: premature optimization ahead ;)
-    // TODO: would it be more efficient to work on bytes,
-    // without decoding/re-encoding UTF-8?
-    do string.map_chars |c| {
-        match c {
-            'A'..'Z' => c + 'a' - 'A',
-            _ => c,
-        }
-    }
-}
-
-
 //  ***********  End of public API  ***********
 
 
-#[test]
-fn test_ascii_lower() {
-    assert!(ascii_lower("url()URL()uRl()Ürl") == ~"url()url()url()Ürl");
-    // Dotted capital I, Kelvin sign, Sharp S.
-    assert!(ascii_lower("HİKß") == ~"hİKß");
-}
-
-
 #[inline]
 fn preprocess(input: &str) -> ~str {
     // TODO: Is this faster if done in one pass?
@@ -281,7 +261,7 @@ fn consume_ident(parser: &mut Parser) -> ComponentValue {
             match parser.current_char() {
                 '(' => {
                     parser.position += 1;
-                    if ascii_lower(string) == ~"url" { consume_url(parser) }
+                    if eq_ascii_lower(string, "url") { consume_url(parser) }
                     else { Function(string, consume_block(parser, CloseParenthesis)) }
                 },
                 _ => Ident(string)