text regex source gen framework is briefly done. Going on ir2code

2026-07-14 17:44:29 +08:00
parent bc90e340df
commit 4d2a4eeb18
32 changed files with 276 additions and 140 deletions
@@ -0,0 +1,89 @@
+// -----------------------------------------------------------------------------
+// file="TextRegexSourceGen.GenClass"
+// Project: StgSharp
+// Copyright (c) Nitload.
+// SPDX-License-Identifier: MIT
+// -----------------------------------------------------------------------------
+
+using StgSharp.RegularAnalysis.Abstraction;
+using System;
+using System.Collections.Generic;
+using System.Linq;
+using System.Runtime.InteropServices;
+using System.Text;
+using System.Threading.Tasks;
+
+namespace StgSharp.RegularAnalysis.Text
+{
+    internal partial class TextRegexSourceGen
+    {
+
+        internal static SequenceEmitter<string> GenerateSource(
+                                                TextRegexSource source
+        )
+        {
+            SequenceEmitter<string> se = new();
+            List<SequenceEmitter<string>> sub_match_list = [];
+
+            RegexInfo info = source.Info;
+            List<RegexIR> ir = source.IRs;
+            ReadOnlySpan<RegexIR> ir_sp = CollectionsMarshal.AsSpan(ir);
+            RegexIR[] window = new RegexIR[8];
+            Span<RegexIR> scan_win = window;
+
+            const string current_ptr = "current_ptr";
+
+            _ = se.AppendLine($@"public override MatchResult Match({ROS_char} text)")//
+                  .AppendLine(@"{");
+
+            int region_count = info.RegionCount;
+            for (int i = 0; i < region_count; i++)
+            {
+                _ = se.AppendLine($@"int region_{i}_start = -1;")//
+                      .AppendLine($@"int region_{i}_end = -1;")
+                      .AppendLine($@"bool region_{i}_success;");
+            }
+
+            _ = se.AppendLine($@"int {current_ptr} = 0;");
+
+            int index = 0;
+            do
+            {
+                int count = int.Min(8, ir_sp.Length - index);
+                ir_sp.Slice(index, count).CopyTo(scan_win);
+                if (TryGenerateMatch(scan_win, se) > 0) { }
+            } while (index < ir.Count);
+
+            foreach (SequenceEmitter<string> _sub in sub_match_list)
+            {
+                _ = se.AppendLine()                     //
+                      .Append(_sub);
+            }
+
+            _ = se.Append(@"}");
+
+            return se;
+            /**/
+            int TryGenerateMatch(
+                Span<RegexIR> scan_win,
+                SequenceEmitter<string> sb
+            )
+            {
+                if (scan_win[0] is not RegexMatchSeqIR seq) {
+                    return -1;
+                }
+                string pattern = seq.Pattern;
+                int length = pattern.Length;
+                _ = sb.AppendLine()
+                      .AppendLine($@"if(text[{current_ptr}..({current_ptr} + {length})] == {pattern})")
+                      .AppendLine($@"{{")
+                      .AppendLine($@"{current_ptr} += {length};")
+                      .AppendLine($@"}}");
+
+                return 1;
+            }
+            /**/
+        }
+
+    }
+}