Adding Regex.IsMatch(Span) and RegexRunner.Scan() methods

src/libraries/System.Text.RegularExpressions/ref/System.Text.RegularExpressions.cs

@@ -171,6 +171,10 @@ public static void CompileToAssembly(System.Text.RegularExpressions.RegexCompila
         public string GroupNameFromNumber(int i) { throw null; }
         public int GroupNumberFromName(string name) { throw null; }
         protected void InitializeReferences() { }
+        public bool IsMatch(System.ReadOnlySpan<char> input) { throw null; }
+        public static bool IsMatch(System.ReadOnlySpan<char> input, [System.Diagnostics.CodeAnalysis.StringSyntaxAttribute(System.Diagnostics.CodeAnalysis.StringSyntaxAttribute.Regex)] string pattern) { throw null; }
+        public static bool IsMatch(System.ReadOnlySpan<char> input, [System.Diagnostics.CodeAnalysis.StringSyntaxAttribute(System.Diagnostics.CodeAnalysis.StringSyntaxAttribute.Regex, "options")] string pattern, System.Text.RegularExpressions.RegexOptions options) { throw null; }
+        public static bool IsMatch(System.ReadOnlySpan<char> input, [System.Diagnostics.CodeAnalysis.StringSyntaxAttribute(System.Diagnostics.CodeAnalysis.StringSyntaxAttribute.Regex, "options")] string pattern, System.Text.RegularExpressions.RegexOptions options, System.TimeSpan matchTimeout) { throw null; }
         public bool IsMatch(string input) { throw null; }
         public bool IsMatch(string input, int startat) { throw null; }
         public static bool IsMatch(string input, [System.Diagnostics.CodeAnalysis.StringSyntaxAttribute(System.Diagnostics.CodeAnalysis.StringSyntaxAttribute.Regex)] string pattern) { throw null; }
@@ -330,9 +334,9 @@ protected void DoubleCrawl() { }
         protected void DoubleStack() { }
         protected void DoubleTrack() { }
         protected void EnsureStorage() { }
-        protected abstract bool FindFirstChar();
-        protected abstract void Go();
-        protected abstract void InitTrackCount();
+        protected virtual bool FindFirstChar() { throw null; }
+        protected virtual void Go() { throw null; }
+        protected virtual void InitTrackCount() { throw null; }
         protected bool IsBoundary(int index, int startpos, int endpos) { throw null; }
         protected bool IsECMABoundary(int index, int startpos, int endpos) { throw null; }
         protected bool IsMatched(int cap) { throw null; }
@@ -341,6 +345,7 @@ protected void EnsureStorage() { }
         protected int Popcrawl() { throw null; }
         protected internal System.Text.RegularExpressions.Match? Scan(System.Text.RegularExpressions.Regex regex, string text, int textbeg, int textend, int textstart, int prevlen, bool quick) { throw null; }
         protected internal System.Text.RegularExpressions.Match? Scan(System.Text.RegularExpressions.Regex regex, string text, int textbeg, int textend, int textstart, int prevlen, bool quick, System.TimeSpan timeout) { throw null; }
+        protected internal virtual void Scan(System.ReadOnlySpan<char> text) { throw null; }
         protected void TransferCapture(int capnum, int uncapnum, int start, int end) { }
         protected void Uncapture() { }
     }

src/libraries/System.Text.RegularExpressions/src/Resources/Strings.resx

@@ -1,5 +1,64 @@
 <?xml version="1.0" encoding="utf-8"?>
 <root>
+  <!-- 
+    Microsoft ResX Schema 
+
+    Version 2.0
+
+    The primary goals of this format is to allow a simple XML format 
+    that is mostly human readable. The generation and parsing of the 
+    various data types are done through the TypeConverter classes 
+    associated with the data types.
+
+    Example:
+
+    ... ado.net/XML headers & schema ...
+    <resheader name="resmimetype">text/microsoft-resx</resheader>
+    <resheader name="version">2.0</resheader>
+    <resheader name="reader">System.Resources.ResXResourceReader, System.Windows.Forms, ...</resheader>
+    <resheader name="writer">System.Resources.ResXResourceWriter, System.Windows.Forms, ...</resheader>
+    <data name="Name1"><value>this is my long string</value><comment>this is a comment</comment></data>
+    <data name="Color1" type="System.Drawing.Color, System.Drawing">Blue</data>
+    <data name="Bitmap1" mimetype="application/x-microsoft.net.object.binary.base64">
+        <value>[base64 mime encoded serialized .NET Framework object]</value>
+    </data>
+    <data name="Icon1" type="System.Drawing.Icon, System.Drawing" mimetype="application/x-microsoft.net.object.bytearray.base64">
+        <value>[base64 mime encoded string representing a byte array form of the .NET Framework object]</value>
+        <comment>This is a comment</comment>
+    </data>
+
+    There are any number of "resheader" rows that contain simple 
+    name/value pairs.
+
+    Each data row contains a name, and value. The row also contains a 
+    type or mimetype. Type corresponds to a .NET class that support 
+    text/value conversion through the TypeConverter architecture. 
+    Classes that don't support this are serialized and stored with the 
+    mimetype set.
+
+    The mimetype is used for serialized objects, and tells the 
+    ResXResourceReader how to depersist the object. This is currently not 
+    extensible. For a given mimetype the value must be set accordingly:
+
+    Note - application/x-microsoft.net.object.binary.base64 is the format 
+    that the ResXResourceWriter will generate, however the reader can 
+    read any of the formats listed below.
+
+    mimetype: application/x-microsoft.net.object.binary.base64
+    value   : The object must be serialized with 
+            : System.Runtime.Serialization.Formatters.Binary.BinaryFormatter
+            : and then encoded with base64 encoding.
+
+    mimetype: application/x-microsoft.net.object.soap.base64
+    value   : The object must be serialized with 
+            : System.Runtime.Serialization.Formatters.Soap.SoapFormatter
+            : and then encoded with base64 encoding.
+
+    mimetype: application/x-microsoft.net.object.bytearray.base64
+    value   : The object must be serialized into a byte array 
+            : using a System.ComponentModel.TypeConverter
+            : and then encoded with base64 encoding.
+    -->
   <xsd:schema id="root" xmlns="" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:msdata="urn:schemas-microsoft-com:xml-msdata">
     <xsd:import namespace="http://www.w3.org/XML/1998/namespace" />
     <xsd:element name="root" msdata:IsDataSet="true">
@@ -254,4 +313,7 @@
   <data name="ExpressionDescription_BalancingGroup" xml:space="preserve">
     <value>balancing group (?&lt;name1-name2&gt;subexpression) or (?'name1-name2' subexpression)</value>
   </data>
-</root>
+  <data name="UsingSpanAPIsWithCompiledToAssembly" xml:space="preserve">
+    <value>Attempted to call Span overloads with a pre compiled Regex engine is not supported. Please use the string overloads instead.</value>
+  </data>
+</root>

src/libraries/System.Text.RegularExpressions/src/System/Text/RegularExpressions/Capture.cs

@@ -9,7 +9,7 @@ namespace System.Text.RegularExpressions
     /// </summary>
     public class Capture
     {
-        internal Capture(string text, int index, int length)
+        internal Capture(string? text, int index, int length)
         {
             Text = text;
             Index = index;
@@ -19,27 +19,38 @@ internal Capture(string text, int index, int length)
         /// <summary>Returns the position in the original string where the first character of captured substring was found.</summary>
         public int Index { get; private protected set; }
 
+        /// <summary>
+        /// This method should only be called when the text for matching was sliced with a different beginning, so the resulting index of
+        /// the match is not from the start of the text, but instead the start of the slice. This method will add back that extra indices
+        /// to account for the original text beginning.
+        /// </summary>
+        /// <param name="beginning">The original text's beginning offset.</param>
+        internal void AddBeginningToIndex(int beginning)
+        {
+            Index += beginning;
+        }
+
         /// <summary>Returns the length of the captured substring.</summary>
         public int Length { get; private protected set; }
 
         /// <summary>The original string</summary>
-        internal string Text { get; set; }
+        internal string? Text { get; set; }
 
         /// <summary>Gets the captured substring from the input string.</summary>
         /// <value>The substring that is captured by the match.</value>
-        public string Value => Text.Substring(Index, Length);
+        public string Value => Text is string text ? text.Substring(Index, Length) : string.Empty;
 
         /// <summary>Gets the captured span from the input string.</summary>
         /// <value>The span that is captured by the match.</value>
-        public ReadOnlySpan<char> ValueSpan => Text.AsSpan(Index, Length);
+        public ReadOnlySpan<char> ValueSpan => Text is string text ? text.AsSpan(Index, Length) : ReadOnlySpan<char>.Empty;
 
         /// <summary>Returns the substring that was matched.</summary>
         public override string ToString() => Value;
 
         /// <summary>The substring to the left of the capture</summary>
-        internal ReadOnlyMemory<char> GetLeftSubstring() => Text.AsMemory(0, Index);
+        internal ReadOnlyMemory<char> GetLeftSubstring() => Text is string text ? text.AsMemory(0, Index) : ReadOnlyMemory<char>.Empty;
 
         /// <summary>The substring to the right of the capture</summary>
-        internal ReadOnlyMemory<char> GetRightSubstring() => Text.AsMemory(Index + Length, Text.Length - Index - Length);
+        internal ReadOnlyMemory<char> GetRightSubstring() => Text is string text ? text.AsMemory(Index + Length, Text.Length - Index - Length) : ReadOnlyMemory<char>.Empty;
     }
 }

src/libraries/System.Text.RegularExpressions/src/System/Text/RegularExpressions/CompiledRegexRunner.cs

@@ -5,20 +5,16 @@ namespace System.Text.RegularExpressions
 {
     internal sealed class CompiledRegexRunner : RegexRunner
     {
-        private readonly Action<RegexRunner> _goMethod;
-        private readonly Func<RegexRunner, bool> _findFirstCharMethod;
+        private readonly ScanDelegate _scanMethod;
 
-        public CompiledRegexRunner(Action<RegexRunner> go, Func<RegexRunner, bool> findFirstChar, int trackCount)
+        internal delegate void ScanDelegate(RegexRunner runner, ReadOnlySpan<char> text);
+
+        public CompiledRegexRunner(ScanDelegate scan)
         {
-            _goMethod = go;
-            _findFirstCharMethod = findFirstChar;
-            runtrackcount = trackCount;
+            _scanMethod = scan;
         }
 
-        protected override void Go() => _goMethod(this);
-
-        protected override bool FindFirstChar() => _findFirstCharMethod(this);
-
-        protected override void InitTrackCount() { }
+        protected internal override void Scan(ReadOnlySpan<char> text)
+            => _scanMethod(this, text);
     }
 }

src/libraries/System.Text.RegularExpressions/src/System/Text/RegularExpressions/CompiledRegexRunnerFactory.cs

@@ -7,25 +7,18 @@ namespace System.Text.RegularExpressions
 {
     internal sealed class CompiledRegexRunnerFactory : RegexRunnerFactory
     {
-        private readonly DynamicMethod _goMethod;
-        private readonly DynamicMethod _findFirstCharMethod;
-        private readonly int _trackcount;
+        private readonly DynamicMethod _scanMethod;
 
         // Delegates are lazily created to avoid forcing JIT'ing until the regex is actually executed.
-        private Action<RegexRunner>? _go;
-        private Func<RegexRunner, bool>? _findFirstChar;
+        private CompiledRegexRunner.ScanDelegate? _scan;
 
-        public CompiledRegexRunnerFactory(DynamicMethod goMethod, DynamicMethod findFirstCharMethod, int trackcount)
+        public CompiledRegexRunnerFactory(DynamicMethod scanMethod)
         {
-            _goMethod = goMethod;
-            _findFirstCharMethod = findFirstCharMethod;
-            _trackcount = trackcount;
+            _scanMethod = scanMethod;
         }
 
         protected internal override RegexRunner CreateInstance() =>
             new CompiledRegexRunner(
-                _go ??= _goMethod.CreateDelegate<Action<RegexRunner>>(),
-                _findFirstChar ??= _findFirstCharMethod.CreateDelegate<Func<RegexRunner, bool>>(),
-                _trackcount);
+                _scan ??= _scanMethod.CreateDelegate<CompiledRegexRunner.ScanDelegate>());
     }
 }

src/libraries/System.Text.RegularExpressions/src/System/Text/RegularExpressions/Group.cs

@@ -16,7 +16,7 @@ public class Group : Capture
         internal int _capcount;
         internal CaptureCollection? _capcoll;
 
-        internal Group(string text, int[] caps, int capcount, string name)
+        internal Group(string? text, int[] caps, int capcount, string name)
             : base(text, capcount == 0 ? 0 : caps[(capcount - 1) * 2], capcount == 0 ? 0 : caps[(capcount * 2) - 1])
         {
             _caps = caps;

src/libraries/System.Text.RegularExpressions/src/System/Text/RegularExpressions/Match.cs

@@ -50,7 +50,7 @@ public class Match : Group
         internal bool _balancing;        // whether we've done any balancing with this match.  If we
                                          // have done balancing, we'll need to do extra work in Tidy().
 
-        internal Match(Regex? regex, int capcount, string text, int begpos, int len, int startpos) :
+        internal Match(Regex? regex, int capcount, string? text, int begpos, int len, int startpos) :
             base(text, new int[2], 0, "0")
         {
             _regex = regex;
@@ -66,7 +66,7 @@ internal Match(Regex? regex, int capcount, string text, int begpos, int len, int
         /// <summary>Returns an empty Match object.</summary>
         public static Match Empty { get; } = new Match(null, 1, string.Empty, 0, 0, 0);
 
-        internal void Reset(Regex regex, string text, int textbeg, int textend, int textstart)
+        internal void Reset(Regex regex, string? text, int textbeg, int textend, int textstart)
         {
             _regex = regex;
             Text = text;
@@ -84,6 +84,11 @@ internal void Reset(Regex regex, string text, int textbeg, int textend, int text
             _groupcoll?.Reset();
         }
 
+        internal bool FoundAMatch
+        {
+            get => _matchcount[0] > 0;
+        }
+
         public virtual GroupCollection Groups => _groupcoll ??= new GroupCollection(this, null);
 
         /// <summary>
@@ -94,6 +99,7 @@ internal void Reset(Regex regex, string text, int textbeg, int textend, int text
         public Match NextMatch()
         {
             Regex? r = _regex;
+            Debug.Assert(Text != null);
             return r != null ?
                 r.Run(false, Length, Text, _textbeg, _textend - _textbeg, _textpos)! :
                 this;
@@ -338,7 +344,7 @@ internal sealed class MatchSparse : Match
     {
         private new readonly Hashtable _caps;
 
-        internal MatchSparse(Regex regex, Hashtable caps, int capcount, string text, int begpos, int len, int startpos) :
+        internal MatchSparse(Regex regex, Hashtable caps, int capcount, string? text, int begpos, int len, int startpos) :
             base(regex, capcount, text, begpos, len, startpos)
         {
             _caps = caps;

src/libraries/System.Text.RegularExpressions/src/System/Text/RegularExpressions/Regex.Match.cs

@@ -13,6 +13,15 @@ public partial class Regex
         public static bool IsMatch(string input, [StringSyntax(StringSyntaxAttribute.Regex)] string pattern) =>
             RegexCache.GetOrAdd(pattern).IsMatch(input);
 
+        /// <summary>
+        /// Searches the input span for one or more occurrences of the text supplied in the given pattern.
+        /// </summary>
+        /// <param name="input">The input span to be searched on.</param>
+        /// <param name="pattern">The Regex pattern to be used for matching.</param>
+        /// <returns><see langword="true"/> if the input matches the pattern, <see langword="false"/> otherwise.</returns>
+        public static bool IsMatch(ReadOnlySpan<char> input, [StringSyntax(StringSyntaxAttribute.Regex)] string pattern) =>
+            RegexCache.GetOrAdd(pattern).IsMatch(input);
+
         /// <summary>
         /// Searches the input string for one or more occurrences of the text
         /// supplied in the pattern parameter with matching options supplied in the options
@@ -21,9 +30,30 @@ public static bool IsMatch(string input, [StringSyntax(StringSyntaxAttribute.Reg
         public static bool IsMatch(string input, [StringSyntax(StringSyntaxAttribute.Regex, "options")] string pattern, RegexOptions options) =>
             RegexCache.GetOrAdd(pattern, options, s_defaultMatchTimeout).IsMatch(input);
 
+        /// <summary>
+        /// Searches the input span for one or more occurrences of the text supplied in the given pattern. It uses the passed in options.
+        /// </summary>
+        /// <param name="input">The input span to be searched on.</param>
+        /// <param name="pattern">The Regex pattern to be used for matching.</param>
+        /// <param name="options">The options to be used for matching</param>
+        /// <returns><see langword="true"/> if the input matches the pattern, <see langword="false"/> otherwise.</returns>
+        public static bool IsMatch(ReadOnlySpan<char> input, [StringSyntax(StringSyntaxAttribute.Regex, "options")] string pattern, RegexOptions options) =>
+            RegexCache.GetOrAdd(pattern, options, s_defaultMatchTimeout).IsMatch(input);
+
         public static bool IsMatch(string input, [StringSyntax(StringSyntaxAttribute.Regex, "options")] string pattern, RegexOptions options, TimeSpan matchTimeout) =>
             RegexCache.GetOrAdd(pattern, options, matchTimeout).IsMatch(input);
 
+        /// <summary>
+        /// Searches the input span for one or more occurrences of the text supplied in the given pattern under the specified timeout. It uses the passed in options.
+        /// </summary>
+        /// <param name="input">The input span to be searched on.</param>
+        /// <param name="pattern">The Regex pattern to be used for matching.</param>
+        /// <param name="options">The options to be used for matching</param>
+        /// <param name="matchTimeout">Max time to be used for matching before returning.</param>
+        /// <returns><see langword="true"/> if the input matches the pattern, <see langword="false"/> otherwise. Also returns <see langword="false"/> for time out.</returns>
+        public static bool IsMatch(ReadOnlySpan<char> input, [StringSyntax(StringSyntaxAttribute.Regex, "options")] string pattern, RegexOptions options, TimeSpan matchTimeout) =>
+            RegexCache.GetOrAdd(pattern, options, matchTimeout).IsMatch(input);
+
         /// <summary>
         /// Searches the input string for one or more matches using the previous pattern,
         /// options, and starting position.
@@ -38,6 +68,14 @@ public bool IsMatch(string input)
             return Run(quick: true, -1, input, 0, input.Length, UseOptionR() ? input.Length : 0) is null;
         }
 
+        /// <summary>
+        /// Searches the input span for one or more matches using the previous pattern,
+        /// options, and starting position.
+        /// </summary>
+        /// <returns><see langword="true"/> if the input matches the pattern, <see langword="false"/> otherwise.</returns>
+        public bool IsMatch(ReadOnlySpan<char> input) =>
+            Run(input, UseOptionR() ? input.Length : 0) is null;
+
         /// <summary>
         /// Searches the input string for one or more matches using the previous pattern and options,
         /// with a new starting position.