Implement external strings.

runtime/lib/string.dart

 // Copyright (c) 2011, the Dart project authors.  Please see the AUTHORS file
 // for details. All rights reserved. Use of this source code is governed by a
 // BSD-style license that can be found in the LICENSE file.
 
 /**
  * [StringBase] contains common methods used by concrete String implementations,
  * e.g., OneByteString.
  */
 class StringBase {
 
@@ skipping 396 matching lines @@
   // Checks for one-byte whitespaces only.
   // TODO(srdjan): Investigate if 0x85 (NEL) and 0xA0 (NBSP) are valid
   // whitespaces. Add checking for multi-byte whitespace codepoints.
   bool _isWhitespace(int codePoint) {
     return
       (codePoint === 32) || // Space.
       ((9 <= codePoint) && (codePoint <= 13)); // CR, LF, TAB, etc.
   }
 }
 
+
+class ExternalOneByteString extends StringBase implements String {
+  // Checks for one-byte whitespaces only.
+  // TODO(srdjan): Investigate if 0x85 (NEL) and 0xA0 (NBSP) are valid
+  // whitespaces for one byte strings.
+  bool _isWhitespace(int codePoint) {

[Ivan Posva, 2011/11/18 19:36:44]

Shouldn't this be factored out into a private static method shared by all String
implementations? Different CL though, filed bug:
http://code.google.com/p/dart/issues/detail?id=525

[cshapiro, 2011/11/19 01:08:29]

Yes.  My intention was to replace all of these methods with a native call to a
character property predicate that checks to see if the character has the Unicode
"White_Space" property.

At present, there are 26 code points with this property.  

http://www.unicode.org/Public/UNIDATA/PropList.txt

Because the cardinality of this set is low, a switch statement in Dart might be
the fastest way to implement the membership test.

I think we will want this functionality in native code anyway for the benefit of
the scanner.  We can mirror it in Dart if it turns out to be a hot-spot.

+    return
+      (codePoint === 32) || // Space.
+      ((9 <= codePoint) && (codePoint <= 13)); // CR, LF, TAB, etc.
+  }
+}
+
+
+class ExternalTwoByteString extends StringBase implements String {
+  // Checks for one-byte whitespaces only.
+  // TODO(srdjan): Investigate if 0x85 (NEL) and 0xA0 (NBSP) are valid
+  // whitespaces. Add checking for multi-byte whitespace codepoints.
+  bool _isWhitespace(int codePoint) {
+    return
+      (codePoint === 32) || // Space.
+      ((9 <= codePoint) && (codePoint <= 13)); // CR, LF, TAB, etc.
+  }
+}
+
+
+class ExternalFourByteString extends StringBase implements String {
+  // Checks for one-byte whitespaces only.
+  // TODO(srdjan): Investigate if 0x85 (NEL) and 0xA0 (NBSP) are valid
+  // whitespaces. Add checking for multi-byte whitespace codepoints.
+  bool _isWhitespace(int codePoint) {
+    return
+      (codePoint === 32) || // Space.
+      ((9 <= codePoint) && (codePoint <= 13)); // CR, LF, TAB, etc.
+  }
+}
+
+
 class _StringMatch implements Match {
   const _StringMatch(int this._start,
                      String this.str,
                      String this.pattern);
 
   int start() => _start;
   int end() => _start + pattern.length;
   String operator[](int g) => group(g);
   int groupCount() => 0;
 
   String group(int group) {
     if (group != 0) {
       throw new IndexOutOfRangeException(group);
     }
     return pattern;
   }
 
   List<String> groups(List<int> groups) {
     List<String> result = new List<String>();
     for (int g in groups) {
       result.add(group(g));
     }
     return result;
   }
 
   final int _start;
   final String str;
   final String pattern;
 }