diff --git a/src/libraries/System.Text.RegularExpressions/src/System.Text.RegularExpressions.csproj b/src/libraries/System.Text.RegularExpressions/src/System.Text.RegularExpressions.csproj
index 5313bf0d948138..77351ca146f7ae 100644
--- a/src/libraries/System.Text.RegularExpressions/src/System.Text.RegularExpressions.csproj
+++ b/src/libraries/System.Text.RegularExpressions/src/System.Text.RegularExpressions.csproj
@@ -7,6 +7,7 @@
+
@@ -46,14 +47,10 @@
-
-
-
-
+
+
+
+
diff --git a/src/libraries/System.Text.RegularExpressions/src/System/Text/RegularExpressions/RegexCharClass.MappingTable.cs b/src/libraries/System.Text.RegularExpressions/src/System/Text/RegularExpressions/RegexCharClass.MappingTable.cs
new file mode 100644
index 00000000000000..b299a3b8e1e8b9
--- /dev/null
+++ b/src/libraries/System.Text.RegularExpressions/src/System/Text/RegularExpressions/RegexCharClass.MappingTable.cs
@@ -0,0 +1,162 @@
+// Licensed to the .NET Foundation under one or more agreements.
+// The .NET Foundation licenses this file to you under the MIT license.
+
+using System.Collections.Generic;
+
+namespace System.Text.RegularExpressions
+{
+ internal sealed partial class RegexCharClass
+ {
+ /**************************************************************************
+ Let U be the set of Unicode character values and let L be the lowercase
+ function, mapping from U to U. To perform case insensitive matching of
+ character sets, we need to be able to map an interval I in U, say
+
+ I = [chMin, chMax] = { ch : chMin <= ch <= chMax }
+
+ to a set A such that A contains L(I) and A is contained in the union of
+ I and L(I).
+
+ The table below partitions U into intervals on which L is non-decreasing.
+ Thus, for any interval J = [a, b] contained in one of these intervals,
+ L(J) is contained in [L(a), L(b)].
+
+ It is also true that for any such J, [L(a), L(b)] is contained in the
+ union of J and L(J). This does not follow from L being non-decreasing on
+ these intervals. It follows from the nature of the L on each interval.
+ On each interval, L has one of the following forms:
+
+ (1) L(ch) = constant (LowercaseSet)
+ (2) L(ch) = ch + offset (LowercaseAdd)
+ (3) L(ch) = ch | 1 (LowercaseBor)
+ (4) L(ch) = ch + (ch & 1) (LowercaseBad)
+
+ It is easy to verify that for any of these forms [L(a), L(b)] is
+ contained in the union of [a, b] and L([a, b]).
+ ***************************************************************************/
+
+ internal const int LowercaseSet = 0; // Set to arg.
+ internal const int LowercaseAdd = 1; // Add arg.
+ internal const int LowercaseBor = 2; // Bitwise or with 1.
+ internal const int LowercaseBad = 3; // Bitwise and with 1 and add original.
+
+ internal static readonly LowerCaseMapping[] s_lcTable = new LowerCaseMapping[]
+ {
+ new LowerCaseMapping('\u0041', '\u005A', LowercaseAdd, 32),
+ new LowerCaseMapping('\u00C0', '\u00D6', LowercaseAdd, 32),
+ new LowerCaseMapping('\u00D8', '\u00DE', LowercaseAdd, 32),
+ new LowerCaseMapping('\u0100', '\u012E', LowercaseBor, 0),
+ new LowerCaseMapping('\u0132', '\u0136', LowercaseBor, 0),
+ new LowerCaseMapping('\u0139', '\u0147', LowercaseBad, 0),
+ new LowerCaseMapping('\u014A', '\u0176', LowercaseBor, 0),
+ new LowerCaseMapping('\u0178', '\u0178', LowercaseSet, 0x00FF),
+ new LowerCaseMapping('\u0179', '\u017D', LowercaseBad, 0),
+ new LowerCaseMapping('\u0181', '\u0181', LowercaseSet, 0x0253),
+ new LowerCaseMapping('\u0182', '\u0184', LowercaseBor, 0),
+ new LowerCaseMapping('\u0186', '\u0186', LowercaseSet, 0x0254),
+ new LowerCaseMapping('\u0187', '\u0187', LowercaseSet, 0x0188),
+ new LowerCaseMapping('\u0189', '\u018A', LowercaseAdd, 205),
+ new LowerCaseMapping('\u018B', '\u018B', LowercaseSet, 0x018C),
+ new LowerCaseMapping('\u018E', '\u018E', LowercaseSet, 0x01DD),
+ new LowerCaseMapping('\u018F', '\u018F', LowercaseSet, 0x0259),
+ new LowerCaseMapping('\u0190', '\u0190', LowercaseSet, 0x025B),
+ new LowerCaseMapping('\u0191', '\u0191', LowercaseSet, 0x0192),
+ new LowerCaseMapping('\u0193', '\u0193', LowercaseSet, 0x0260),
+ new LowerCaseMapping('\u0194', '\u0194', LowercaseSet, 0x0263),
+ new LowerCaseMapping('\u0196', '\u0196', LowercaseSet, 0x0269),
+ new LowerCaseMapping('\u0197', '\u0197', LowercaseSet, 0x0268),
+ new LowerCaseMapping('\u0198', '\u0198', LowercaseSet, 0x0199),
+ new LowerCaseMapping('\u019C', '\u019C', LowercaseSet, 0x026F),
+ new LowerCaseMapping('\u019D', '\u019D', LowercaseSet, 0x0272),
+ new LowerCaseMapping('\u019F', '\u019F', LowercaseSet, 0x0275),
+ new LowerCaseMapping('\u01A0', '\u01A4', LowercaseBor, 0),
+ new LowerCaseMapping('\u01A7', '\u01A7', LowercaseSet, 0x01A8),
+ new LowerCaseMapping('\u01A9', '\u01A9', LowercaseSet, 0x0283),
+ new LowerCaseMapping('\u01AC', '\u01AC', LowercaseSet, 0x01AD),
+ new LowerCaseMapping('\u01AE', '\u01AE', LowercaseSet, 0x0288),
+ new LowerCaseMapping('\u01AF', '\u01AF', LowercaseSet, 0x01B0),
+ new LowerCaseMapping('\u01B1', '\u01B2', LowercaseAdd, 217),
+ new LowerCaseMapping('\u01B3', '\u01B5', LowercaseBad, 0),
+ new LowerCaseMapping('\u01B7', '\u01B7', LowercaseSet, 0x0292),
+ new LowerCaseMapping('\u01B8', '\u01B8', LowercaseSet, 0x01B9),
+ new LowerCaseMapping('\u01BC', '\u01BC', LowercaseSet, 0x01BD),
+ new LowerCaseMapping('\u01C4', '\u01C5', LowercaseSet, 0x01C6),
+ new LowerCaseMapping('\u01C7', '\u01C8', LowercaseSet, 0x01C9),
+ new LowerCaseMapping('\u01CA', '\u01CB', LowercaseSet, 0x01CC),
+ new LowerCaseMapping('\u01CD', '\u01DB', LowercaseBad, 0),
+ new LowerCaseMapping('\u01DE', '\u01EE', LowercaseBor, 0),
+ new LowerCaseMapping('\u01F1', '\u01F2', LowercaseSet, 0x01F3),
+ new LowerCaseMapping('\u01F4', '\u01F4', LowercaseSet, 0x01F5),
+ new LowerCaseMapping('\u01FA', '\u0216', LowercaseBor, 0),
+ new LowerCaseMapping('\u0386', '\u0386', LowercaseSet, 0x03AC),
+ new LowerCaseMapping('\u0388', '\u038A', LowercaseAdd, 37),
+ new LowerCaseMapping('\u038C', '\u038C', LowercaseSet, 0x03CC),
+ new LowerCaseMapping('\u038E', '\u038F', LowercaseAdd, 63),
+ new LowerCaseMapping('\u0391', '\u03A1', LowercaseAdd, 32),
+ new LowerCaseMapping('\u03A3', '\u03AB', LowercaseAdd, 32),
+ new LowerCaseMapping('\u03E2', '\u03EE', LowercaseBor, 0),
+ new LowerCaseMapping('\u0401', '\u040F', LowercaseAdd, 80),
+ new LowerCaseMapping('\u0410', '\u042F', LowercaseAdd, 32),
+ new LowerCaseMapping('\u0460', '\u0480', LowercaseBor, 0),
+ new LowerCaseMapping('\u0490', '\u04BE', LowercaseBor, 0),
+ new LowerCaseMapping('\u04C1', '\u04C3', LowercaseBad, 0),
+ new LowerCaseMapping('\u04C7', '\u04C7', LowercaseSet, 0x04C8),
+ new LowerCaseMapping('\u04CB', '\u04CB', LowercaseSet, 0x04CC),
+ new LowerCaseMapping('\u04D0', '\u04EA', LowercaseBor, 0),
+ new LowerCaseMapping('\u04EE', '\u04F4', LowercaseBor, 0),
+ new LowerCaseMapping('\u04F8', '\u04F8', LowercaseSet, 0x04F9),
+ new LowerCaseMapping('\u0531', '\u0556', LowercaseAdd, 48),
+ new LowerCaseMapping('\u10A0', '\u10C5', LowercaseAdd, 7264),
+ new LowerCaseMapping('\u1E00', '\u1E95', LowercaseBor, 0),
+ new LowerCaseMapping('\u1EA0', '\u1EF8', LowercaseBor, 0),
+ new LowerCaseMapping('\u1F08', '\u1F0F', LowercaseAdd, -8),
+ new LowerCaseMapping('\u1F18', '\u1F1D', LowercaseAdd, -8),
+ new LowerCaseMapping('\u1F28', '\u1F2F', LowercaseAdd, -8),
+ new LowerCaseMapping('\u1F38', '\u1F3F', LowercaseAdd, -8),
+ new LowerCaseMapping('\u1F48', '\u1F4D', LowercaseAdd, -8),
+ new LowerCaseMapping('\u1F59', '\u1F59', LowercaseSet, 0x1F51),
+ new LowerCaseMapping('\u1F5B', '\u1F5B', LowercaseSet, 0x1F53),
+ new LowerCaseMapping('\u1F5D', '\u1F5D', LowercaseSet, 0x1F55),
+ new LowerCaseMapping('\u1F5F', '\u1F5F', LowercaseSet, 0x1F57),
+ new LowerCaseMapping('\u1F68', '\u1F6F', LowercaseAdd, -8),
+ new LowerCaseMapping('\u1F88', '\u1F8F', LowercaseAdd, -8),
+ new LowerCaseMapping('\u1F98', '\u1F9F', LowercaseAdd, -8),
+ new LowerCaseMapping('\u1FA8', '\u1FAF', LowercaseAdd, -8),
+ new LowerCaseMapping('\u1FB8', '\u1FB9', LowercaseAdd, -8),
+ new LowerCaseMapping('\u1FBA', '\u1FBB', LowercaseAdd, -74),
+ new LowerCaseMapping('\u1FBC', '\u1FBC', LowercaseSet, 0x1FB3),
+ new LowerCaseMapping('\u1FC8', '\u1FCB', LowercaseAdd, -86),
+ new LowerCaseMapping('\u1FCC', '\u1FCC', LowercaseSet, 0x1FC3),
+ new LowerCaseMapping('\u1FD8', '\u1FD9', LowercaseAdd, -8),
+ new LowerCaseMapping('\u1FDA', '\u1FDB', LowercaseAdd, -100),
+ new LowerCaseMapping('\u1FE8', '\u1FE9', LowercaseAdd, -8),
+ new LowerCaseMapping('\u1FEA', '\u1FEB', LowercaseAdd, -112),
+ new LowerCaseMapping('\u1FEC', '\u1FEC', LowercaseSet, 0x1FE5),
+ new LowerCaseMapping('\u1FF8', '\u1FF9', LowercaseAdd, -128),
+ new LowerCaseMapping('\u1FFA', '\u1FFB', LowercaseAdd, -126),
+ new LowerCaseMapping('\u1FFC', '\u1FFC', LowercaseSet, 0x1FF3),
+ new LowerCaseMapping('\u2160', '\u216F', LowercaseAdd, 16),
+ new LowerCaseMapping('\u24B6', '\u24CF', LowercaseAdd, 26),
+ new LowerCaseMapping('\uFF21', '\uFF3A', LowercaseAdd, 32),
+ };
+
+ ///
+ /// Lower case mapping descriptor.
+ ///
+ internal readonly struct LowerCaseMapping
+ {
+ public readonly char ChMin;
+ public readonly char ChMax;
+ public readonly int LcOp;
+ public readonly int Data;
+
+ internal LowerCaseMapping(char chMin, char chMax, int lcOp, int data)
+ {
+ ChMin = chMin;
+ ChMax = chMax;
+ LcOp = lcOp;
+ Data = data;
+ }
+ }
+ }
+}
diff --git a/src/libraries/System.Text.RegularExpressions/src/System/Text/RegularExpressions/RegexCharClass.cs b/src/libraries/System.Text.RegularExpressions/src/System/Text/RegularExpressions/RegexCharClass.cs
index d4022f673e4ff7..3dc776fe604711 100644
--- a/src/libraries/System.Text.RegularExpressions/src/System/Text/RegularExpressions/RegexCharClass.cs
+++ b/src/libraries/System.Text.RegularExpressions/src/System/Text/RegularExpressions/RegexCharClass.cs
@@ -25,7 +25,7 @@ namespace System.Text.RegularExpressions
// included in this class.
/// Provides the "set of Unicode chars" functionality used by the regexp engine.
- internal sealed class RegexCharClass
+ internal sealed partial class RegexCharClass
{
// Constants
internal const int FlagsIndex = 0;
@@ -264,137 +264,6 @@ internal sealed class RegexCharClass
+"\u3041\u3097\u3099\u30A0\u30A1\u30FB\u30FC\u3100\u3105\u312D\u3131\u318F\u3190\u31B8\u31F0\u321D\u3220\u3244\u3251\u327C\u327F\u32CC\u32D0\u32FF\u3300\u3377\u337B\u33DE\u33E0\u33FF\u3400\u4DB6\u4E00\u9FA6\uA000\uA48D\uA490\uA4C7\uAC00\uD7A4\uF900\uFA2E\uFA30\uFA6B\uFB00\uFB07\uFB13\uFB18\uFB1D\uFB37\uFB38\uFB3D\uFB3E\uFB3F\uFB40\uFB42\uFB43\uFB45\uFB46\uFBB2\uFBD3\uFD3E\uFD50\uFD90\uFD92\uFDC8\uFDF0\uFDFD\uFE00\uFE10\uFE20\uFE24\uFE62\uFE63\uFE64\uFE67\uFE69\uFE6A\uFE70\uFE75\uFE76\uFEFD\uFF04\uFF05\uFF0B\uFF0C\uFF10\uFF1A\uFF1C\uFF1F\uFF21\uFF3B\uFF3E\uFF3F\uFF40\uFF5B\uFF5C\uFF5D\uFF5E\uFF5F\uFF66\uFFBF\uFFC2\uFFC8\uFFCA\uFFD0\uFFD2\uFFD8\uFFDA\uFFDD\uFFE0\uFFE7\uFFE8\uFFEF\uFFFC\uFFFE"},
};
- /**************************************************************************
- Let U be the set of Unicode character values and let L be the lowercase
- function, mapping from U to U. To perform case insensitive matching of
- character sets, we need to be able to map an interval I in U, say
-
- I = [chMin, chMax] = { ch : chMin <= ch <= chMax }
-
- to a set A such that A contains L(I) and A is contained in the union of
- I and L(I).
-
- The table below partitions U into intervals on which L is non-decreasing.
- Thus, for any interval J = [a, b] contained in one of these intervals,
- L(J) is contained in [L(a), L(b)].
-
- It is also true that for any such J, [L(a), L(b)] is contained in the
- union of J and L(J). This does not follow from L being non-decreasing on
- these intervals. It follows from the nature of the L on each interval.
- On each interval, L has one of the following forms:
-
- (1) L(ch) = constant (LowercaseSet)
- (2) L(ch) = ch + offset (LowercaseAdd)
- (3) L(ch) = ch | 1 (LowercaseBor)
- (4) L(ch) = ch + (ch & 1) (LowercaseBad)
-
- It is easy to verify that for any of these forms [L(a), L(b)] is
- contained in the union of [a, b] and L([a, b]).
- ***************************************************************************/
-
- private const int LowercaseSet = 0; // Set to arg.
- private const int LowercaseAdd = 1; // Add arg.
- private const int LowercaseBor = 2; // Bitwise or with 1.
- private const int LowercaseBad = 3; // Bitwise and with 1 and add original.
-
- private static readonly LowerCaseMapping[] s_lcTable = new LowerCaseMapping[]
- {
- new LowerCaseMapping('\u0041', '\u005A', LowercaseAdd, 32),
- new LowerCaseMapping('\u00C0', '\u00DE', LowercaseAdd, 32),
- new LowerCaseMapping('\u0100', '\u012E', LowercaseBor, 0),
- new LowerCaseMapping('\u0130', '\u0130', LowercaseSet, 0x0069),
- new LowerCaseMapping('\u0132', '\u0136', LowercaseBor, 0),
- new LowerCaseMapping('\u0139', '\u0147', LowercaseBad, 0),
- new LowerCaseMapping('\u014A', '\u0176', LowercaseBor, 0),
- new LowerCaseMapping('\u0178', '\u0178', LowercaseSet, 0x00FF),
- new LowerCaseMapping('\u0179', '\u017D', LowercaseBad, 0),
- new LowerCaseMapping('\u0181', '\u0181', LowercaseSet, 0x0253),
- new LowerCaseMapping('\u0182', '\u0184', LowercaseBor, 0),
- new LowerCaseMapping('\u0186', '\u0186', LowercaseSet, 0x0254),
- new LowerCaseMapping('\u0187', '\u0187', LowercaseSet, 0x0188),
- new LowerCaseMapping('\u0189', '\u018A', LowercaseAdd, 205),
- new LowerCaseMapping('\u018B', '\u018B', LowercaseSet, 0x018C),
- new LowerCaseMapping('\u018E', '\u018E', LowercaseSet, 0x01DD),
- new LowerCaseMapping('\u018F', '\u018F', LowercaseSet, 0x0259),
- new LowerCaseMapping('\u0190', '\u0190', LowercaseSet, 0x025B),
- new LowerCaseMapping('\u0191', '\u0191', LowercaseSet, 0x0192),
- new LowerCaseMapping('\u0193', '\u0193', LowercaseSet, 0x0260),
- new LowerCaseMapping('\u0194', '\u0194', LowercaseSet, 0x0263),
- new LowerCaseMapping('\u0196', '\u0196', LowercaseSet, 0x0269),
- new LowerCaseMapping('\u0197', '\u0197', LowercaseSet, 0x0268),
- new LowerCaseMapping('\u0198', '\u0198', LowercaseSet, 0x0199),
- new LowerCaseMapping('\u019C', '\u019C', LowercaseSet, 0x026F),
- new LowerCaseMapping('\u019D', '\u019D', LowercaseSet, 0x0272),
- new LowerCaseMapping('\u019F', '\u019F', LowercaseSet, 0x0275),
- new LowerCaseMapping('\u01A0', '\u01A4', LowercaseBor, 0),
- new LowerCaseMapping('\u01A7', '\u01A7', LowercaseSet, 0x01A8),
- new LowerCaseMapping('\u01A9', '\u01A9', LowercaseSet, 0x0283),
- new LowerCaseMapping('\u01AC', '\u01AC', LowercaseSet, 0x01AD),
- new LowerCaseMapping('\u01AE', '\u01AE', LowercaseSet, 0x0288),
- new LowerCaseMapping('\u01AF', '\u01AF', LowercaseSet, 0x01B0),
- new LowerCaseMapping('\u01B1', '\u01B2', LowercaseAdd, 217),
- new LowerCaseMapping('\u01B3', '\u01B5', LowercaseBad, 0),
- new LowerCaseMapping('\u01B7', '\u01B7', LowercaseSet, 0x0292),
- new LowerCaseMapping('\u01B8', '\u01B8', LowercaseSet, 0x01B9),
- new LowerCaseMapping('\u01BC', '\u01BC', LowercaseSet, 0x01BD),
- new LowerCaseMapping('\u01C4', '\u01C5', LowercaseSet, 0x01C6),
- new LowerCaseMapping('\u01C7', '\u01C8', LowercaseSet, 0x01C9),
- new LowerCaseMapping('\u01CA', '\u01CB', LowercaseSet, 0x01CC),
- new LowerCaseMapping('\u01CD', '\u01DB', LowercaseBad, 0),
- new LowerCaseMapping('\u01DE', '\u01EE', LowercaseBor, 0),
- new LowerCaseMapping('\u01F1', '\u01F2', LowercaseSet, 0x01F3),
- new LowerCaseMapping('\u01F4', '\u01F4', LowercaseSet, 0x01F5),
- new LowerCaseMapping('\u01FA', '\u0216', LowercaseBor, 0),
- new LowerCaseMapping('\u0386', '\u0386', LowercaseSet, 0x03AC),
- new LowerCaseMapping('\u0388', '\u038A', LowercaseAdd, 37),
- new LowerCaseMapping('\u038C', '\u038C', LowercaseSet, 0x03CC),
- new LowerCaseMapping('\u038E', '\u038F', LowercaseAdd, 63),
- new LowerCaseMapping('\u0391', '\u03AB', LowercaseAdd, 32),
- new LowerCaseMapping('\u03E2', '\u03EE', LowercaseBor, 0),
- new LowerCaseMapping('\u0401', '\u040F', LowercaseAdd, 80),
- new LowerCaseMapping('\u0410', '\u042F', LowercaseAdd, 32),
- new LowerCaseMapping('\u0460', '\u0480', LowercaseBor, 0),
- new LowerCaseMapping('\u0490', '\u04BE', LowercaseBor, 0),
- new LowerCaseMapping('\u04C1', '\u04C3', LowercaseBad, 0),
- new LowerCaseMapping('\u04C7', '\u04C7', LowercaseSet, 0x04C8),
- new LowerCaseMapping('\u04CB', '\u04CB', LowercaseSet, 0x04CC),
- new LowerCaseMapping('\u04D0', '\u04EA', LowercaseBor, 0),
- new LowerCaseMapping('\u04EE', '\u04F4', LowercaseBor, 0),
- new LowerCaseMapping('\u04F8', '\u04F8', LowercaseSet, 0x04F9),
- new LowerCaseMapping('\u0531', '\u0556', LowercaseAdd, 48),
- new LowerCaseMapping('\u10A0', '\u10C5', LowercaseAdd, 48),
- new LowerCaseMapping('\u1E00', '\u1EF8', LowercaseBor, 0),
- new LowerCaseMapping('\u1F08', '\u1F0F', LowercaseAdd, -8),
- new LowerCaseMapping('\u1F18', '\u1F1F', LowercaseAdd, -8),
- new LowerCaseMapping('\u1F28', '\u1F2F', LowercaseAdd, -8),
- new LowerCaseMapping('\u1F38', '\u1F3F', LowercaseAdd, -8),
- new LowerCaseMapping('\u1F48', '\u1F4D', LowercaseAdd, -8),
- new LowerCaseMapping('\u1F59', '\u1F59', LowercaseSet, 0x1F51),
- new LowerCaseMapping('\u1F5B', '\u1F5B', LowercaseSet, 0x1F53),
- new LowerCaseMapping('\u1F5D', '\u1F5D', LowercaseSet, 0x1F55),
- new LowerCaseMapping('\u1F5F', '\u1F5F', LowercaseSet, 0x1F57),
- new LowerCaseMapping('\u1F68', '\u1F6F', LowercaseAdd, -8),
- new LowerCaseMapping('\u1F88', '\u1F8F', LowercaseAdd, -8),
- new LowerCaseMapping('\u1F98', '\u1F9F', LowercaseAdd, -8),
- new LowerCaseMapping('\u1FA8', '\u1FAF', LowercaseAdd, -8),
- new LowerCaseMapping('\u1FB8', '\u1FB9', LowercaseAdd, -8),
- new LowerCaseMapping('\u1FBA', '\u1FBB', LowercaseAdd, -74),
- new LowerCaseMapping('\u1FBC', '\u1FBC', LowercaseSet, 0x1FB3),
- new LowerCaseMapping('\u1FC8', '\u1FCB', LowercaseAdd, -86),
- new LowerCaseMapping('\u1FCC', '\u1FCC', LowercaseSet, 0x1FC3),
- new LowerCaseMapping('\u1FD8', '\u1FD9', LowercaseAdd, -8),
- new LowerCaseMapping('\u1FDA', '\u1FDB', LowercaseAdd, -100),
- new LowerCaseMapping('\u1FE8', '\u1FE9', LowercaseAdd, -8),
- new LowerCaseMapping('\u1FEA', '\u1FEB', LowercaseAdd, -112),
- new LowerCaseMapping('\u1FEC', '\u1FEC', LowercaseSet, 0x1FE5),
- new LowerCaseMapping('\u1FF8', '\u1FF9', LowercaseAdd, -128),
- new LowerCaseMapping('\u1FFA', '\u1FFB', LowercaseAdd, -126),
- new LowerCaseMapping('\u1FFC', '\u1FFC', LowercaseSet, 0x1FF3),
- new LowerCaseMapping('\u2160', '\u216F', LowercaseAdd, 16),
- new LowerCaseMapping('\u24B6', '\u24D0', LowercaseAdd, 26),
- new LowerCaseMapping('\uFF21', '\uFF3A', LowercaseAdd, 32),
- };
-
private List? _rangelist;
private StringBuilder? _categories;
private RegexCharClass? _subtractor;
@@ -412,6 +281,7 @@ static RegexCharClass()
int len = s_propTable.Length;
for (int i = 0; i < len - 1; i++)
Debug.Assert(string.Compare(s_propTable[i][0], s_propTable[i + 1][0], StringComparison.Ordinal) < 0, $"RegexCharClass s_propTable is out of order at ({s_propTable[i][0]}, {s_propTable[i + 1][0]})");
+
}
#endif
@@ -569,7 +439,7 @@ private void AddLowercaseRange(char chMin, char chMax)
{
int i = 0;
- for (int iMax = s_lcTable.Length; i < iMax; )
+ for (int iMax = s_lcTable.Length; i < iMax;)
{
int iMid = (i + iMax) >> 1;
if (s_lcTable[iMid].ChMax < chMin)
@@ -1692,25 +1562,6 @@ private static string CategoryDescription(char ch)
}
#endif
- ///
- /// Lower case mapping descriptor.
- ///
- private readonly struct LowerCaseMapping
- {
- public readonly char ChMin;
- public readonly char ChMax;
- public readonly int LcOp;
- public readonly int Data;
-
- internal LowerCaseMapping(char chMin, char chMax, int lcOp, int data)
- {
- ChMin = chMin;
- ChMax = chMax;
- LcOp = lcOp;
- Data = data;
- }
- }
-
///
/// A first/last pair representing a single range of characters.
///
diff --git a/src/libraries/System.Text.RegularExpressions/tests/Regex.Match.Tests.cs b/src/libraries/System.Text.RegularExpressions/tests/Regex.Match.Tests.cs
index a7e73699f36e8e..a8b319ad27deeb 100644
--- a/src/libraries/System.Text.RegularExpressions/tests/Regex.Match.Tests.cs
+++ b/src/libraries/System.Text.RegularExpressions/tests/Regex.Match.Tests.cs
@@ -378,6 +378,32 @@ public static IEnumerable Match_Basic_TestData()
}
}
+ public static IEnumerable Match_Basic_TestData_NetCore()
+ {
+ // Unicode symbols in character ranges. These are chars whose lowercase values cannot be found by using the offsets specified in s_lcTable.
+ yield return new object[] { @"^(?i:[\u00D7-\u00D8])$", '\u00F7'.ToString(), RegexOptions.IgnoreCase | RegexOptions.CultureInvariant, 0, 1, false, "" };
+ yield return new object[] { @"^(?i:[\u00C0-\u00DE])$", '\u00F7'.ToString(), RegexOptions.IgnoreCase | RegexOptions.CultureInvariant, 0, 1, false, "" };
+ yield return new object[] { @"^(?i:[\u00C0-\u00DE])$", ((char)('\u00C0' + 32)).ToString(), RegexOptions.IgnoreCase | RegexOptions.CultureInvariant, 0, 1, true, ((char)('\u00C0' + 32)).ToString() };
+ yield return new object[] { @"^(?i:[\u00C0-\u00DE])$", ((char)('\u00DE' + 32)).ToString(), RegexOptions.IgnoreCase | RegexOptions.CultureInvariant, 0, 1, true, ((char)('\u00DE' + 32)).ToString() };
+ yield return new object[] { @"^(?i:[\u0391-\u03AB])$", ((char)('\u03A2' + 32)).ToString(), RegexOptions.IgnoreCase | RegexOptions.CultureInvariant, 0, 1, false, "" };
+ yield return new object[] { @"^(?i:[\u0391-\u03AB])$", ((char)('\u0391' + 32)).ToString(), RegexOptions.IgnoreCase | RegexOptions.CultureInvariant, 0, 1, true, ((char)('\u0391' + 32)).ToString() };
+ yield return new object[] { @"^(?i:[\u0391-\u03AB])$", ((char)('\u03AB' + 32)).ToString(), RegexOptions.IgnoreCase | RegexOptions.CultureInvariant, 0, 1, true, ((char)('\u03AB' + 32)).ToString() };
+ yield return new object[] { @"^(?i:[\u1F18-\u1F1F])$", ((char)('\u1F1F' - 8)).ToString(), RegexOptions.IgnoreCase | RegexOptions.CultureInvariant, 0, 1, false, "" };
+ yield return new object[] { @"^(?i:[\u1F18-\u1F1F])$", ((char)('\u1F18' - 8)).ToString(), RegexOptions.IgnoreCase | RegexOptions.CultureInvariant, 0, 1, true, ((char)('\u1F18' - 8)).ToString() };
+ yield return new object[] { @"^(?i:[\u10A0-\u10C5])$", ((char)('\u10A0' + 7264)).ToString(), RegexOptions.IgnoreCase | RegexOptions.CultureInvariant, 0, 1, true, ((char)('\u10A0' + 7264)).ToString() };
+ yield return new object[] { @"^(?i:[\u10A0-\u10C5])$", ((char)('\u1F1F' + 48)).ToString(), RegexOptions.IgnoreCase | RegexOptions.CultureInvariant, 0, 1, false, "" };
+ yield return new object[] { @"^(?i:[\u24B6-\u24D0])$", ((char)('\u24D0' + 26)).ToString(), RegexOptions.IgnoreCase | RegexOptions.CultureInvariant, 0, 1, false, "" };
+ yield return new object[] { @"^(?i:[\u24B6-\u24D0])$", ((char)('\u24CF' + 26)).ToString(), RegexOptions.IgnoreCase | RegexOptions.CultureInvariant, 0, 1, true, ((char)('\u24CF' + 26)).ToString() };
+ }
+
+ [SkipOnTargetFramework(TargetFrameworkMonikers.NetFramework)]
+ [Theory]
+ [MemberData(nameof(Match_Basic_TestData_NetCore))]
+ public void Match_NetCore(string pattern, string input, RegexOptions options, int beginning, int length, bool expectedSuccess, string expectedValue)
+ {
+ Match(pattern, input, options, beginning, length, expectedSuccess, expectedValue);
+ }
+
[Theory]
[MemberData(nameof(Match_Basic_TestData))]
[MemberData(nameof(RegexCompilationHelper.TransformRegexOptions), nameof(Match_Basic_TestData), 2, MemberType = typeof(RegexCompilationHelper))]
diff --git a/src/libraries/System.Text.RegularExpressions/tests/RegexValidations.netcoreapp.cs b/src/libraries/System.Text.RegularExpressions/tests/RegexValidations.netcoreapp.cs
new file mode 100644
index 00000000000000..9f4cf807d5c9db
--- /dev/null
+++ b/src/libraries/System.Text.RegularExpressions/tests/RegexValidations.netcoreapp.cs
@@ -0,0 +1,53 @@
+// Licensed to the .NET Foundation under one or more agreements.
+// The .NET Foundation licenses this file to you under the MIT license.
+
+using System.Collections.Generic;
+using System.Globalization;
+using Xunit;
+
+namespace System.Text.RegularExpressions.Tests
+{
+ public class RegexValidations
+ {
+ [ConditionalFact(typeof(PlatformDetection), nameof(PlatformDetection.IsIcuGlobalization))]
+ public void ValidateLowercaseMapTableInRegexCharClass()
+ {
+ CultureInfo culture = CultureInfo.InvariantCulture;
+ for (int k = 0; k < RegexCharClass.s_lcTable.Length; k++)
+ {
+ RegexCharClass.LowerCaseMapping loc = RegexCharClass.s_lcTable[k];
+ if (loc.LcOp == RegexCharClass.LowercaseAdd)
+ {
+ int offset = loc.Data;
+ for (char l = loc.ChMin; l <= loc.ChMax; l++)
+ {
+ Assert.True(culture.TextInfo.ToLower((char)l) == (char)(l + offset), $"The Unicode character range at index {k} in s_lcTable contains the character {(char)l} (decimal value: {l}). Its lowercase value cannot be obtained by using the specified offset.");
+ }
+ }
+ else if (loc.LcOp == RegexCharClass.LowercaseSet)
+ {
+ char lowercase = (char)loc.Data;
+ for (char l = loc.ChMin; l <= loc.ChMax; l++)
+ {
+ char uppercase = l;
+ Assert.True(culture.TextInfo.ToLower(uppercase) == lowercase, $"The Unicode character range at index {k} in s_lcTable contains the character {uppercase} (decimal value: {(int)uppercase}, hex: {(int)uppercase:X}). Its lowercase value {culture.TextInfo.ToLower(uppercase).ToString()} (decimal value: {(int)culture.TextInfo.ToLower(uppercase)}, hex: {(int)culture.TextInfo.ToLower(uppercase):X}) is not the stored value {lowercase} (decimal value: {(int)lowercase}, hex: {(int)lowercase:X}).");
+ }
+ }
+ else if (loc.LcOp == RegexCharClass.LowercaseBor)
+ {
+ for (char l = loc.ChMin; l <= loc.ChMax; l++)
+ {
+ Assert.True(culture.TextInfo.ToLower((char)l) == (char)(l | (char)1), $"The Unicode character range at index {k} in s_lcTable contains the character {(char)l} (decimal value: {l}). Its lowercase value {culture.TextInfo.ToLower(l)} cannot be obtained by OR-ing with 1: {(char)(l | (char)1)}");
+ }
+ }
+ else if (loc.LcOp == RegexCharClass.LowercaseBad)
+ {
+ for (char l = loc.ChMin; l <= loc.ChMax; l++)
+ {
+ Assert.True(culture.TextInfo.ToLower((char)l) == (char)(l + (l & 1)), $"The Unicode character range at index {k} in s_lcTable contains the character {(char)l} (decimal value: {l}). Its lowercase value cannot be obtained by AND-ing with 1.");
+ }
+ }
+ }
+ }
+ }
+}
diff --git a/src/libraries/System.Text.RegularExpressions/tests/System.Text.RegularExpressions.Tests.csproj b/src/libraries/System.Text.RegularExpressions/tests/System.Text.RegularExpressions.Tests.csproj
index fade03bcb99e88..45fe74f6287690 100644
--- a/src/libraries/System.Text.RegularExpressions/tests/System.Text.RegularExpressions.Tests.csproj
+++ b/src/libraries/System.Text.RegularExpressions/tests/System.Text.RegularExpressions.Tests.csproj
@@ -32,12 +32,12 @@
-
+
+
@@ -45,7 +45,7 @@
-
+
+