Working on tree optimizer

This commit is contained in:
Youmu Liu
2026-02-11 18:02:45 +08:00
parent 4735b987f4
commit 39dd32992d
9 changed files with 193 additions and 63 deletions
@@ -28,7 +28,9 @@
using StgSharp.RegularAnalysis.Abstraction;
using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using System.Runtime.CompilerServices;
using System.Text;
using System.Threading.Tasks;
@@ -43,9 +45,118 @@ namespace StgSharp.RegularAnalysis.TextRegex
{
TreeEnumerator<RegexAstNode, RegexElementLabel> enumerator = new(root);
List<RegexAstNode> cases = [];
RegexAstNode current;
_ = enumerator.MoveNext(); // skip root
while (enumerator.MoveNext())
{
RegexAstNode current = enumerator.Current;
current = enumerator.Current;
current.Parent.RemoveChild(current);
current.Parent = RegexAstNode.Empty;
if (current.Parent.EqualityTypeConvert == RegexElementLabel.ALT)
{
continue;
} else
{
cases.Add(current);
enumerator.SkipNode(current);
}
}
for (int i = 0; i < cases.Count - 1; i++)
{
cases[i].AppendNode(cases[i + 1]);
cases[i].Parent = root;
}
return cases[0];
}
private static void MergeConcat(
RegexAstNode root
)
{
if (root.EqualityTypeConvert != RegexElementLabel.CONCAT) {
return;
}
List<string> buffer = [];
int length = 0;
RegexAstNode right = root.Right;
RegexAstNode left = root.Left;
if (left.EqualityTypeConvert != RegexElementLabel.UNIT_SPAN &&
left.EqualityTypeConvert != RegexElementLabel.UNIT) {
return;
}
string str = left.Value;
buffer.Add(str);
length += str.Length;
while (RegexAstNode.IsNullOrEmpty(right) &&
right.EqualityTypeConvert == RegexElementLabel.CONCAT)
{
left = right.Left;
if (left.EqualityTypeConvert != RegexElementLabel.UNIT_SPAN &&
left.EqualityTypeConvert != RegexElementLabel.UNIT)
{
break;
}
str = left.Value;
buffer.Add(str);
length += str.Length;
root.Right = right.Right;
// TODO: remove right from tree
right = root.Right;
}
str = string.Create(length, buffer, static(
span,
buffer
) => {
int offset = 0;
for (int i = 0; i < buffer.Count; i++)
{
buffer[i].AsSpan().CopyTo(span[offset..]);
offset += buffer[i].Length;
}
});
left = root.Left;
root.Left = new RegexAstNode(new Token<RegexElementLabel>(str, left.Source.Line,
left.Source.Column,
str.Length == 1 ?
RegexElementLabel.UNIT :
RegexElementLabel.UNIT_SPAN));
}
private static void RotateConcat(
RegexAstNode root
)
{
RegexAstNode left = root.Left;
while (RegexAstNode.IsNullOrEmpty(left) &&
left.EqualityTypeConvert == RegexElementLabel.CONCAT)
{
/*
* root → root
* ╱ ╲ ╱ ╲
* left c a left
* ╱ ╲ ╱ ╲
* a b b c
*/
RegexAstNode a = left.Left;
RegexAstNode b = left.Right;
RegexAstNode c = root.Right;
root.Left = a;
if (RegexAstNode.IsNullOrEmpty(a)) {
a.Parent = root;
}
root.Right = left;
left.Left = b;
left.Right = c;
if (RegexAstNode.IsNullOrEmpty(b)) {
b.Parent = left;
}
if (RegexAstNode.IsNullOrEmpty(c)) {
c.Parent = left;
}
left = root.Left;
}
}