Update WebEncoders from Unicode 7.0 to Unicode 8.0

src/Microsoft.Framework.WebEncoders.Core/UnicodeHelpers.cs

@@ -28,14 +28,14 @@ internal unsafe static class UnicodeHelpers
 
         /// <summary>
         /// Helper method which creates a bitmap of all characters which are
-        /// defined per version 7.0.0 of the Unicode specification.
+        /// defined per version 8.0 of the Unicode specification.
         /// </summary>
         [MethodImpl(MethodImplOptions.NoInlining)]
         private static uint[] CreateDefinedCharacterBitmap()
         {
             // The stream should be exactly 8KB in size.
             var assembly = typeof(UnicodeHelpers).GetTypeInfo().Assembly;
-            var resourceName = assembly.GetName().Name + ".compiler.resources.unicode-7.0.0-defined-characters.bin";
+            var resourceName = assembly.GetName().Name + ".compiler.resources.unicode-defined-chars.bin";
 
             var stream = assembly.GetManifestResourceStream(resourceName);
             if (stream.Length != 8 * 1024)
@@ -72,7 +72,7 @@ private static uint[] CreateDefinedCharacterBitmap()
         }
 
         /// <summary>
-        /// Returns a bitmap of all characters which are defined per version 7.0.0
+        /// Returns a bitmap of all characters which are defined per version 8.0
         /// of the Unicode specification.
         /// </summary>
         [MethodImpl(MethodImplOptions.AggressiveInlining)]
@@ -204,7 +204,7 @@ internal static int GetUtf8RepresentationForScalarValue(uint scalar)
         }
 
         /// <summary>
-        /// Returns a value stating whether a character is defined per version 7.0.0
+        /// Returns a value stating whether a character is defined per version 8.0
         /// of the Unicode specification. Certain classes of characters (control chars,
         /// private use, surrogates, some whitespace) are considered "undefined" for
         /// our purposes.

src/Microsoft.Framework.WebEncoders.Core/UnicodeRanges.cs

@@ -10,7 +10,7 @@ namespace Microsoft.Framework.WebEncoders
 {
     /// <summary>
     /// Contains predefined <see cref="UnicodeRange"/> instances which correspond to blocks
-    /// from the Unicode 7.0 specification.
+    /// from the Unicode 8.0 specification.
     /// </summary>
     public static partial class UnicodeRanges
     {

src/Microsoft.Framework.WebEncoders.Core/UnicodeRanges.generated.cs

@@ -1277,6 +1277,15 @@ public static partial class UnicodeRanges
         public static UnicodeRange LatinExtendedE => Volatile.Read(ref _latinExtendedE) ?? CreateRange(ref _latinExtendedE, first: '\uAB30', last: '\uAB6F');
         private static UnicodeRange _latinExtendedE;
 
+        /// <summary>
+        /// A <see cref="UnicodeRange"/> corresponding to the 'Cherokee Supplement' Unicode block (U+AB70..U+ABBF).
+        /// </summary>
+        /// <remarks>
+        /// See http://www.unicode.org/charts/PDF/UAB70.pdf for the full set of characters in this block.
+        /// </remarks>
+        public static UnicodeRange CherokeeSupplement => Volatile.Read(ref _cherokeeSupplement) ?? CreateRange(ref _cherokeeSupplement, first: '\uAB70', last: '\uABBF');
+        private static UnicodeRange _cherokeeSupplement;
+
         /// <summary>
         /// A <see cref="UnicodeRange"/> corresponding to the 'Meetei Mayek' Unicode block (U+ABC0..U+ABFF).
         /// </summary>
@@ -1303,7 +1312,7 @@ public static partial class UnicodeRanges
         /// </remarks>
         public static UnicodeRange HangulJamoExtendedB => Volatile.Read(ref _hangulJamoExtendedB) ?? CreateRange(ref _hangulJamoExtendedB, first: '\uD7B0', last: '\uD7FF');
         private static UnicodeRange _hangulJamoExtendedB;
-        
+
         /// <summary>
         /// A <see cref="UnicodeRange"/> corresponding to the 'CJK Compatibility Ideographs' Unicode block (U+F900..U+FAFF).
         /// </summary>

test/Microsoft.Framework.WebEncoders.Tests/UnicodeHelpersTests.cs

@@ -193,15 +193,15 @@ private static bool[] ReadListOfDefinedCharacters()
                 }
             }
 
-            // Handle known spans from Unicode 7.0.0's UnicodeData.txt
+            // Handle known spans from Unicode 8.0's UnicodeData.txt
 
             // CJK Ideograph Extension A
             for (int i = '\u3400'; i <= '\u4DB5'; i++)
             {
                 retVal[i] = true;
             }
             // CJK Ideograph
-            for (int i = '\u4E00'; i <= '\u9FCC'; i++)
+            for (int i = '\u4E00'; i <= '\u9FD5'; i++)
             {
                 retVal[i] = true;
             }

test/Microsoft.Framework.WebEncoders.Tests/UnicodeRangesTests.cs

@@ -172,6 +172,7 @@ public void Range_All()
         [InlineData('\uAAE0', '\uAAFF', nameof(UnicodeRanges.MeeteiMayekExtensions))]
         [InlineData('\uAB00', '\uAB2F', nameof(UnicodeRanges.EthiopicExtendedA))]
         [InlineData('\uAB30', '\uAB6F', nameof(UnicodeRanges.LatinExtendedE))]
+        [InlineData('\uAB70', '\uABBF', nameof(UnicodeRanges.CherokeeSupplement))]
         [InlineData('\uABC0', '\uABFF', nameof(UnicodeRanges.MeeteiMayek))]
         [InlineData('\uAC00', '\uD7AF', nameof(UnicodeRanges.HangulSyllables))]
         [InlineData('\uD7B0', '\uD7FF', nameof(UnicodeRanges.HangulJamoExtendedB))]

unicode/Blocks.txt

@@ -1,14 +1,11 @@
-# Blocks-7.0.0.txt
-# Date: 2014-04-03, 23:23:00 GMT [RP, KW]
+# Blocks-8.0.0.txt
+# Date: 2014-11-10, 23:04:00 GMT [KW]
 #
 # Unicode Character Database
 # Copyright (c) 1991-2014 Unicode, Inc.
 # For terms of use, see http://www.unicode.org/terms_of_use.html
 # For documentation, see http://www.unicode.org/reports/tr44/
 #
-# Note:   The casing of block names is not normative.
-#         For example, "Basic Latin" and "BASIC LATIN" are equivalent.
-#
 # Format:
 # Start Code..End Code; Block Name
 
@@ -20,6 +17,14 @@
 #         For more information on the comparison of property values, 
 #            see UAX #44: http://www.unicode.org/reports/tr44/
 #
+#  All block ranges start with a value where (cp MOD 16) = 0,
+#  and end with a value where (cp MOD 16) = 15. In other words,
+#  the last hexadecimal digit of the start of range is ...0 
+#  and the last hexadecimal digit of the end of range is ...F.
+#  This constraint on block ranges guarantees that allocations
+#  are done in terms of whole columns, and that code chart display
+#  never involves splitting columns in the charts.
+#
 #  All code points not explicitly listed for Block
 #  have the value No_Block.
 
@@ -168,6 +173,7 @@ AA80..AADF; Tai Viet
 AAE0..AAFF; Meetei Mayek Extensions
 AB00..AB2F; Ethiopic Extended-A
 AB30..AB6F; Latin Extended-E
+AB70..ABBF; Cherokee Supplement
 ABC0..ABFF; Meetei Mayek
 AC00..D7AF; Hangul Syllables
 D7B0..D7FF; Hangul Jamo Extended-B
@@ -210,6 +216,7 @@ FFF0..FFFF; Specials
 10840..1085F; Imperial Aramaic
 10860..1087F; Palmyrene
 10880..108AF; Nabataean
+108E0..108FF; Hatran
 10900..1091F; Phoenician
 10920..1093F; Lydian
 10980..1099F; Meroitic Hieroglyphs
@@ -223,6 +230,7 @@ FFF0..FFFF; Specials
 10B60..10B7F; Inscriptional Pahlavi
 10B80..10BAF; Psalter Pahlavi
 10C00..10C4F; Old Turkic
+10C80..10CFF; Old Hungarian
 10E60..10E7F; Rumi Numeral Symbols
 11000..1107F; Brahmi
 11080..110CF; Kaithi
@@ -232,17 +240,21 @@ FFF0..FFFF; Specials
 11180..111DF; Sharada
 111E0..111FF; Sinhala Archaic Numbers
 11200..1124F; Khojki
+11280..112AF; Multani
 112B0..112FF; Khudawadi
 11300..1137F; Grantha
 11480..114DF; Tirhuta
 11580..115FF; Siddham
 11600..1165F; Modi
 11680..116CF; Takri
+11700..1173F; Ahom
 118A0..118FF; Warang Citi
 11AC0..11AFF; Pau Cin Hau
 12000..123FF; Cuneiform
 12400..1247F; Cuneiform Numbers and Punctuation
+12480..1254F; Early Dynastic Cuneiform
 13000..1342F; Egyptian Hieroglyphs
+14400..1467F; Anatolian Hieroglyphs
 16800..16A3F; Bamum Supplement
 16A40..16A6F; Mro
 16AD0..16AFF; Bassa Vah
@@ -257,6 +269,7 @@ FFF0..FFFF; Specials
 1D300..1D35F; Tai Xuan Jing Symbols
 1D360..1D37F; Counting Rod Numerals
 1D400..1D7FF; Mathematical Alphanumeric Symbols
+1D800..1DAAF; Sutton SignWriting
 1E800..1E8DF; Mende Kikakui
 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
 1F000..1F02F; Mahjong Tiles
@@ -271,9 +284,11 @@ FFF0..FFFF; Specials
 1F700..1F77F; Alchemical Symbols
 1F780..1F7FF; Geometric Shapes Extended
 1F800..1F8FF; Supplemental Arrows-C
+1F900..1F9FF; Supplemental Symbols and Pictographs
 20000..2A6DF; CJK Unified Ideographs Extension B
 2A700..2B73F; CJK Unified Ideographs Extension C
 2B740..2B81F; CJK Unified Ideographs Extension D
+2B820..2CEAF; CJK Unified Ideographs Extension E
 2F800..2FA1F; CJK Compatibility Ideographs Supplement
 E0000..E007F; Tags
 E0100..E01EF; Variation Selectors Supplement