Fix string.trim (adding more runes).

R=lrn@google.com, srdjan@google.com

Review URL: https://codereview.chromium.org//15348003

git-svn-id: https://dart.googlecode.com/svn/branches/bleeding_edge/dart@23006 260f80e4-7a28-3924-810f-c04153c831b5

runtime/lib/string_patch.dart

@@ -200,12 +200,40 @@ class _StringBase {
       native "StringBase_substringUnchecked";
 
   // Checks for one-byte whitespaces only.
-  // TODO(srdjan): Investigate if 0x85 (NEL) and 0xA0 (NBSP) are valid
-  // whitespaces for one byte strings.
   static bool _isOneByteWhitespace(int codePoint) {
     return
       (codePoint == 32) || // Space.
-      ((9 <= codePoint) && (codePoint <= 13)); // CR, LF, TAB, etc.
+      ((9 <= codePoint) && (codePoint <= 13)) || // CR, LF, TAB, etc.
+      (codePoint == 0x85) ||  // NEL
+      (codePoint == 0xA0);  // NBSP
+  }
+
+  // Characters with Whitespace property (Unicode 6.2).
+  // 0009..000D    ; White_Space # Cc       <control-0009>..<control-000D>
+  // 0020          ; White_Space # Zs       SPACE
+  // 0085          ; White_Space # Cc       <control-0085>
+  // 00A0          ; White_Space # Zs       NO-BREAK SPACE
+  // 1680          ; White_Space # Zs       OGHAM SPACE MARK
+  // 180E          ; White_Space # Zs       MONGOLIAN VOWEL SEPARATOR
+  // 2000..200A    ; White_Space # Zs       EN QUAD..HAIR SPACE
+  // 2028          ; White_Space # Zl       LINE SEPARATOR
+  // 2029          ; White_Space # Zp       PARAGRAPH SEPARATOR
+  // 202F          ; White_Space # Zs       NARROW NO-BREAK SPACE
+  // 205F          ; White_Space # Zs       MEDIUM MATHEMATICAL SPACE
+  // 3000          ; White_Space # Zs       IDEOGRAPHIC SPACE
+  //
+  // BOM: 0xFEFF
+  static bool _isTwoByteWhitespace(int codePoint) {
+    if (codePoint < 256) return _isOneByteWhitespace(codePoint);
+    return (codePoint == 0x1680) ||
+        (codePoint == 0x180E) ||
+        ((0x2000 <= codePoint) && (codePoint <= 0x200A)) ||
+        (codePoint == 0x2028) ||
+        (codePoint == 0x2029) ||
+        (codePoint == 0x202F) ||
+        (codePoint == 0x205F) ||
+        (codePoint == 0x3000) ||
+        (codePoint == 0xFEFF);
   }
 
   String trim() {
@@ -573,8 +601,7 @@ class _TwoByteString extends _StringBase implements String {
   }
 
   bool _isWhitespace(int codePoint) {
-    // For now we only check for one byte white space characters.
-    return _StringBase._isOneByteWhitespace(codePoint);
+    return _StringBase._isTwoByteWhitespace(codePoint);
   }
 }
 
@@ -598,8 +625,7 @@ class _ExternalTwoByteString extends _StringBase implements String {
   }
 
   bool _isWhitespace(int codePoint) {
-    // For now we only check for one byte white space characters.
-    return _StringBase._isOneByteWhitespace(codePoint);
+    return _StringBase._isTwoByteWhitespace(codePoint);
   }
 }
 

sdk/lib/core/string.dart

@@ -145,13 +145,31 @@ abstract class String implements Comparable<String>, Pattern {
   String substring(int startIndex, [int endIndex]);
 
   /**
-   * Removes leading and trailing whitespace from a string. If the string
-   * contains leading or trailing whitespace a new string with no leading and
-   * no trailing whitespace is returned. Otherwise, the string itself is
-   * returned.  Whitespace is defined as every Unicode character in the Zs, Zl
-   * and Zp categories (this includes no-break space), the spacing control
-   * characters from 9 to 13 (tab, lf, vtab, ff and cr), and 0xfeff the BOM
-   * character.
+   * Removes leading and trailing whitespace from a string.
+   *
+   * If the string contains leading or trailing whitespace a new string with no
+   * leading and no trailing whitespace is returned. Otherwise, the string
+   * itself is returned.
+   *
+   * Whitespace is defined by the Unicode White_Space property (as defined in
+   * version 6.2 or later) and the BOM character, 0xFEFF.
+   *
+   * Here is the list of trimmed characters (following version 6.2):
+   *
+   *     0009..000D    ; White_Space # Cc   <control-0009>..<control-000D>
+   *     0020          ; White_Space # Zs   SPACE
+   *     0085          ; White_Space # Cc   <control-0085>
+   *     00A0          ; White_Space # Zs   NO-BREAK SPACE
+   *     1680          ; White_Space # Zs   OGHAM SPACE MARK
+   *     180E          ; White_Space # Zs   MONGOLIAN VOWEL SEPARATOR
+   *     2000..200A    ; White_Space # Zs   EN QUAD..HAIR SPACE
+   *     2028          ; White_Space # Zl   LINE SEPARATOR
+   *     2029          ; White_Space # Zp   PARAGRAPH SEPARATOR
+   *     202F          ; White_Space # Zs   NARROW NO-BREAK SPACE
+   *     205F          ; White_Space # Zs   MEDIUM MATHEMATICAL SPACE
+   *     3000          ; White_Space # Zs   IDEOGRAPHIC SPACE
+   *
+   *     FEFF          ; BOM                ZERO WIDTH NO_BREAK SPACE
    */
   String trim();
 

tests/corelib/string_trim2_test.dart

@@ -0,0 +1,48 @@
+// Copyright (c) 2013, 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.
+
+import "package:expect/expect.dart";
+
+const WHITESPACE = const [
+  9,
+  10,
+  11,
+  12,
+  13,
+  0x20,
+  0xA0,
+  0x85,
+  0x1680,
+  0x180E,
+  0x2000,
+  0x2001,
+  0x2002,
+  0x2003,
+  0x2004,
+  0x2005,
+  0x2006,
+  0x2007,
+  0x2008,
+  0x2009,
+  0x200A,
+  0x202F,
+  0x205F,
+  0x3000,
+  0x2028,
+  0x2029,
+  0xFEFF,
+];
+
+main() {
+  for (var ws in WHITESPACE) {
+    Expect.equals("", new String.fromCharCode(ws).trim());
+  }
+  Expect.equals("", new String.fromCharCodes(WHITESPACE).trim());
+  for (var ws in WHITESPACE) {
+    var c = new String.fromCharCode(ws);
+    Expect.equals("a", ("a" + c).trim());
+    Expect.equals("a", (c + "a").trim());
+    Expect.equals("a", (c + c + "a" + c + c).trim());
+  }
+}