Optimize one-byte string's toUpperCase.

runtime/lib/string_patch.dart

Index: runtime/lib/string_patch.dart
diff --git a/runtime/lib/string_patch.dart b/runtime/lib/string_patch.dart
index 5d72fdc1450ee7210abdf1d11cd6cb13bc922710..770aaabb196070f96d32a8b7a3aa4cdc98d82cca 100644
--- a/runtime/lib/string_patch.dart
+++ b/runtime/lib/string_patch.dart
@@ -797,55 +797,86 @@ class _OneByteString extends _StringBase implements String {
     return result;
   }
 
-  // Lower-case conversion table for Latin-1.
+  // Lower-case conversion table for Latin-1 as string.
   // Upper-case ranges: 0x41-0x5a ('A' - 'Z'), 0xc0-0xd6, 0xd8-0xde.
   // Conversion to lower case performed by adding 0x20.
-  static const _LC_TABLE = const [
-    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,
-    0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7,
-    0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef,
-    0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xd7,
-    0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 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,
-  ];
+  static const _LC_TABLE =
+      "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+      "\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+      "\x20\x21\x22\x23\x24\x25\x26\x27\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
+      "\x30\x31\x32\x33\x34\x35\x36\x37\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
+      "\x40\x61\x62\x63\x64\x65\x66\x67\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
+      "\x70\x71\x72\x73\x74\x75\x76\x77\x78\x79\x7a\x5b\x5c\x5d\x5e\x5f"
+      "\x60\x61\x62\x63\x64\x65\x66\x67\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
+      "\x70\x71\x72\x73\x74\x75\x76\x77\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
+      "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+      "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
+      "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
+      "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
+      "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef"
+      "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xd7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xdf"
+      "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef"
+      "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff";
+
+  // Upper-case conversion table for Latin-1 as string.
+  // lower-case ranges: 0x61-0x7a ('a' - 'z'), 0xe0-0xff.
+  // The characters 0xb5 (µ) and 0xff (ÿ) have upper case variants
+  // that are not Latin-1. These are both marked as 0xff in the table.
+  // The German "sharp s" \xdf (ß) should be converted into two characters (SS),
+  // and is also marked with 0xff.
+  // Conversion to lower case performed by subtracting 0x20.
+  static const _UC_TABLE =
+      "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+      "\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+      "\x20\x21\x22\x23\x24\x25\x26\x27\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
+      "\x30\x31\x32\x33\x34\x35\x36\x37\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
+      "\x40\x41\x42\x43\x44\x45\x46\x47\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
+      "\x50\x51\x52\x53\x54\x55\x56\x57\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
+      "\x60\x41\x42\x43\x44\x45\x46\x47\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
+      "\x50\x51\x52\x53\x54\x55\x56\x57\x58\x59\x5a\x7b\x7c\x7d\x7e\x7f"
+      "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+      "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
+      "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
+      "\xb0\xb1\xb2\xb3\xb4\xff\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
+      "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
+      "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xff"
+      "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
+      "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xf7\xd8\xd9\xda\xdb\xdc\xdd\xde\xff";
 
   String toLowerCase() {
     for (int i = 0; i < this.length; i++) {
       final c = this.codeUnitAt(i);
-      if (c == _LC_TABLE[c]) continue;
+      if (c == _LC_TABLE.codeUnitAt(c)) continue;
       // Upper-case character found.
       final result = _allocate(this.length);
       for (int j = 0; j < i; j++) {
         result._setAt(j, this.codeUnitAt(j));
       }
       for (int j = i; j < this.length; j++) {
-        result._setAt(j, _LC_TABLE[this.codeUnitAt(j)]);
+        result._setAt(j, _LC_TABLE.codeUnitAt(this.codeUnitAt(j)));
+      }
+      return result;
+    }
+    return this;
+  }
+
+  String toUpperCase() {
+    for (int i = 0; i < this.length; i++) {
+      final c = this.codeUnitAt(i);
+      if (c == _UC_TABLE.codeUnitAt(c)) continue;

[Anders Johnsen, 2014/04/07 09:07:26]

This will not work with 0xff. Consider using 0x00 as marker, and check if the
current char is 0x00.

[Lasse Reichstein Nielsen, 2014/04/07 11:36:28]

Well spotted.

+      // Check rest of string for characters that require complex handling.
+      for (int j = i; j < this.length; j++) {

[Anders Johnsen, 2014/04/07 09:07:26]

Would it be better to have one loop? The fast version (another one byte string)
now has two full iterations.

[Lasse Reichstein Nielsen, 2014/04/07 11:36:28]

We have several cases, in order of increasing complexity:
- all upper case. First loop handles everything.
- some latin-1 with upper-case also latin-1. This has two iterations and one
allocation.
- some latin-1 with non-latin-1 upper case. This has one iteration and a
super-call.

With your change, we will do the allocation before the super-call, but only have
1.5 iteration.
We should try it, but I'm not sure it's a save overall.

+        if (_UC_TABLE.codeUnitAt(this.codeUnitAt(i)) == 0xff) {
+          return super.toUpperCase();
+        }
+      }
+      // Lower-case characters found, but no problematic ones.
+      final result = _allocate(this.length);
+      for (int j = 0; j < i; j++) {
+        result._setAt(j, this.codeUnitAt(j));
+      }
+      for (int j = i; j < this.length; j++) {
+        result._setAt(j, _UC_TABLE.codeUnitAt(this.codeUnitAt(j)));
       }
       return result;
     }