youmuliu/stgsharp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add ir emitter

Browse Source
This commit is contained in:
Youmu Liu
2026-06-16 21:04:51 +08:00
parent 3cfd29f793
commit a7bb3209dd
9 changed files with 711 additions and 148 deletions
Download Patch File Download Diff File Expand all files Collapse all files
future/ngra-regex-ir.md
+6 -9
View File
@@ -16,12 +16,9 @@
## 算子
1. 搜索算子（SEARCH %str; SEARCH %unicode；SERCH %set_expression），向后搜索确定长度序列或者满足规则的字符集，更新活动指针，不更新锚点指针，搜索结果保存在全局上下文中
2. 跳转算子（JMP %cmd_idx），跳转到指定的IR指令之前，不变化任何指针，
3. 回到（BACK %cmd_idx %count）跳转到一个跳自身位置之前的位置，并更新跳转次数，不变化任何的指针，%count应当是使用DEFINE指令定义好的符号
4. 比较指令（CONDITION %cmd_true %cmd_fail），比较前一条SEARCH指令是否成功，并指定跳转到指定的位置，如果某种条件不需要跳转，请使用0进行填充
5. 检查点指令（CHECK），将锚点指针强制拉取到活动指针的位置
6. 弹出检查点（UNCHECK），将一个检查点撤销并销毁
7. 划分区间指令（SPAN %name）,将锚点指针和活动指针之间的部分划分为一个Span<>，并弹出对应的检查点
8. 定义指令（DEFINE %symbol）定义一个符号
9. 赋值指令（ASSIGN %symbol %value）将符号设定为值
1. 搜索算子（SEARCH %str; SEARCH %unicode），向后搜索确定长度序列或者满足规则的字符集，更新活动指针，不更新锚点指针，搜索结果保存在全局上下文中
2. 搜索算子（SEARCH %set_expression），向后匹配一个满足字符集要求的字符，更新活动指针，不更新锚点指针，搜索结果保存在全局上下文中
3. 跳转算子（JMP %cmd_idx），跳转到指定的IR指令之前，不变化任何指针，cmd_idx为相对当前位置的偏移量
4. 条件指令（CONDITION %cmd_true %cmd_fail），比较前一条SEARCH指令是否成功，并指定跳转到指定的位置，如果某种条件不需要跳转，请使用0进行填充
5. 跳转执行指令（TRY %begin %end），尝试idx指向的IR块，并记住执行结果数据
6. 计数指令（COUNT %min %max %is_greedy %cmd），重复执行指令cmd，直到满足参数配置的数量为止
future/sample.cs
+501
View File
@@ -0,0 +1,501 @@
// <auto-generated/>
#nullable enable
#pragma warning disable
namespace StgSharp
{
partial class TestRegexAnalyse
{
/// <remarks>
/// Pattern:<br/>
/// <code>a*.[abc]*(abcd|a(bc)c)+(?&lt;name&gt;abc)</code><br/>
/// Explanation:<br/>
/// <code>
/// ○ Match 'a' greedily any number of times.<br/>
/// ○ Match any character other than '\n'.<br/>
/// ○ Match a character in the set [a-c] greedily any number of times.<br/>
/// ○ Loop greedily at least once.<br/>
/// ○ 1st capture group.<br/>
/// ○ Match 'a'.<br/>
/// ○ Match with 2 alternative expressions.<br/>
/// ○ Match the string "bcd".<br/>
/// ○ Match a sequence of expressions.<br/>
/// ○ 2nd capture group.<br/>
/// ○ Match the string "bc".<br/>
/// ○ Match 'c'.<br/>
/// ○ "name" capture group.<br/>
/// ○ Match the string "abc".<br/>
/// </code>
/// </remarks>
[global::System.CodeDom.Compiler.GeneratedCodeAttribute("System.Text.RegularExpressions.Generator", "10.0.14.27113")]
internal static partial global::System.Text.RegularExpressions.Regex GetRegex() => global::System.Text.RegularExpressions.Generated.GetRegex_0.Instance;
}
}
namespace System.Text.RegularExpressions.Generated
{
using System;
using System.Buffers;
using System.CodeDom.Compiler;
using System.Collections;
using System.ComponentModel;
using System.Globalization;
using System.Runtime.CompilerServices;
using System.Text.RegularExpressions;
using System.Threading;
/// <summary>Custom <see cref="Regex"/>-derived type for the GetRegex method.</summary>
[GeneratedCodeAttribute("System.Text.RegularExpressions.Generator", "10.0.14.27113")]
file sealed class GetRegex_0 : Regex
{
/// <summary>Cached, thread-safe singleton instance.</summary>
internal static readonly GetRegex_0 Instance = new();
/// <summary>Initializes the instance.</summary>
private GetRegex_0()
{
base.pattern = "a*.[abc]*(abcd|a(bc)c)+(?<name>abc)";
base.roptions = RegexOptions.None;
ValidateMatchTimeout(Utilities.s_defaultTimeout);
base.internalMatchTimeout = Utilities.s_defaultTimeout;
base.factory = new RunnerFactory();
base.CapNames = new Hashtable { { "0", 0 } , { "1", 1 } , { "2", 2 } , { "name", 3 } };
base.capslist = new string[] {"0", "1", "2", "name" };
base.capsize = 4;
}
/// <summary>Provides a factory for creating <see cref="RegexRunner"/> instances to be used by methods on <see cref="Regex"/>.</summary>
private sealed class RunnerFactory : RegexRunnerFactory
{
/// <summary>Creates an instance of a <see cref="RegexRunner"/> used by methods on <see cref="Regex"/>.</summary>
protected override RegexRunner CreateInstance() => new Runner();
/// <summary>Provides the runner that contains the custom logic implementing the specified regular expression.</summary>
private sealed class Runner : RegexRunner
{
/// <summary>Scan the <paramref name="inputSpan"/> starting from base.runtextstart for the next match.</summary>
/// <param name="inputSpan">The text being scanned by the regular expression.</param>
protected override void Scan(ReadOnlySpan<char> inputSpan)
{
// Search until we can't find a valid starting position, we find a match, or we reach the end of the input.
while (TryFindNextPossibleStartingPosition(inputSpan) &&
!TryMatchAtCurrentPosition(inputSpan) &&
base.runtextpos != inputSpan.Length)
{
base.runtextpos++;
if (Utilities.s_hasTimeout)
{
base.CheckTimeout();
}
}
}
/// <summary>Search <paramref name="inputSpan"/> starting from base.runtextpos for the next location a match could possibly start.</summary>
/// <param name="inputSpan">The text being scanned by the regular expression.</param>
/// <returns>true if a possible match was found; false if no more matches are possible.</returns>
private bool TryFindNextPossibleStartingPosition(ReadOnlySpan<char> inputSpan)
{
int pos = base.runtextpos;
// Any possible match is at least 8 characters.
if (pos <= inputSpan.Length - 8)
{
// The pattern begins with a character in the set [^\n].
// Find the next occurrence. If it can't be found, there's no match.
ReadOnlySpan<char> span = inputSpan.Slice(pos);
for (int i = 0; i < span.Length; i++)
{
if ((span[i] != '\n'))
{
base.runtextpos = pos + i;
return true;
}
}
}
// No match found.
base.runtextpos = inputSpan.Length;
return false;
}
/// <summary>Determine whether <paramref name="inputSpan"/> at base.runtextpos is a match for the regular expression.</summary>
/// <param name="inputSpan">The text being scanned by the regular expression.</param>
/// <returns>true if the regular expression matches at the current position; otherwise, false.</returns>
private bool TryMatchAtCurrentPosition(ReadOnlySpan<char> inputSpan)
{
int pos = base.runtextpos;
int matchStart = pos;
int capture_starting_pos2 = 0;
int charloop_capture_pos = 0;
int charloop_capture_pos1 = 0;
int charloop_starting_pos = 0, charloop_ending_pos = 0;
int charloop_starting_pos1 = 0, charloop_ending_pos1 = 0;
int loop_iteration = 0;
int stackpos = 0;
ReadOnlySpan<char> slice = inputSpan.Slice(pos);
// Match 'a' greedily any number of times.
//{
charloop_starting_pos = pos;
int iteration = slice.IndexOfAnyExcept('a');
if (iteration < 0)
{
iteration = slice.Length;
}
slice = slice.Slice(iteration);
pos += iteration;
charloop_ending_pos = pos;
goto CharLoopEnd;
CharLoopBacktrack:
UncaptureUntil(charloop_capture_pos);
if (Utilities.s_hasTimeout)
{
base.CheckTimeout();
}
if (charloop_starting_pos >= charloop_ending_pos ||
(charloop_ending_pos = inputSpan.Slice(charloop_starting_pos, charloop_ending_pos - charloop_starting_pos).LastIndexOfAnyExcept('\n')) < 0)
{
UncaptureUntil(0);
return false; // The input didn't match.
}
charloop_ending_pos += charloop_starting_pos;
pos = charloop_ending_pos;
slice = inputSpan.Slice(pos);
CharLoopEnd:
charloop_capture_pos = base.Crawlpos();
//}
// Advance the next matching position.
if (base.runtextpos < pos)
{
base.runtextpos = pos;
}
// Match any character other than '\n'.
if (slice.IsEmpty || slice[0] == '\n')
{
goto CharLoopBacktrack;
}
// Match a character in the set [a-c] greedily any number of times.
//{
pos++;
slice = inputSpan.Slice(pos);
charloop_starting_pos1 = pos;
int iteration1 = slice.IndexOfAnyExceptInRange('a', 'c');
if (iteration1 < 0)
{
iteration1 = slice.Length;
}
slice = slice.Slice(iteration1);
pos += iteration1;
charloop_ending_pos1 = pos;
goto CharLoopEnd1;
CharLoopBacktrack1:
UncaptureUntil(charloop_capture_pos1);
if (Utilities.s_hasTimeout)
{
base.CheckTimeout();
}
if (charloop_starting_pos1 >= charloop_ending_pos1 ||
(charloop_ending_pos1 = inputSpan.Slice(charloop_starting_pos1, charloop_ending_pos1 - charloop_starting_pos1).LastIndexOf('a')) < 0)
{
goto CharLoopBacktrack;
}
charloop_ending_pos1 += charloop_starting_pos1;
pos = charloop_ending_pos1;
slice = inputSpan.Slice(pos);
CharLoopEnd1:
charloop_capture_pos1 = base.Crawlpos();
//}
// Loop greedily at least once.
//{
loop_iteration = 0;
LoopBody:
Utilities.StackPush(ref base.runstack!, ref stackpos, base.Crawlpos(), pos);
loop_iteration++;
// 1st capture group.
//{
int capture_starting_pos = pos;
// Match 'a'.
if (slice.IsEmpty || slice[0] != 'a')
{
goto LoopIterationNoMatch;
}
// Match with 2 alternative expressions.
//{
int alternation_starting_pos = pos;
int alternation_starting_capturepos = base.Crawlpos();
// Branch 0
//{
// Match the string "bcd".
if (!slice.Slice(1).StartsWith("bcd"))
{
goto AlternationBranch;
}
Utilities.StackPush(ref base.runstack!, ref stackpos, 0, alternation_starting_pos, alternation_starting_capturepos);
pos += 4;
slice = inputSpan.Slice(pos);
goto AlternationMatch;
AlternationBranch:
pos = alternation_starting_pos;
slice = inputSpan.Slice(pos);
UncaptureUntil(alternation_starting_capturepos);
//}
// Branch 1
//{
// 2nd capture group.
{
pos++;
slice = inputSpan.Slice(pos);
int capture_starting_pos1 = pos;
// Match the string "bc".
if (!slice.StartsWith("bc"))
{
goto LoopIterationNoMatch;
}
pos += 2;
slice = inputSpan.Slice(pos);
base.Capture(2, capture_starting_pos1, pos);
}
// Match 'c'.
if (slice.IsEmpty || slice[0] != 'c')
{
goto LoopIterationNoMatch;
}
Utilities.StackPush(ref base.runstack!, ref stackpos, 1, alternation_starting_pos, alternation_starting_capturepos);
pos++;
slice = inputSpan.Slice(pos);
goto AlternationMatch;
//}
AlternationBacktrack:
if (Utilities.s_hasTimeout)
{
base.CheckTimeout();
}
Utilities.StackPop(base.runstack!, ref stackpos, out alternation_starting_capturepos, out alternation_starting_pos);
switch (base.runstack![--stackpos])
{
case 0:
goto AlternationBranch;
case 1:
goto LoopIterationNoMatch;
}
AlternationMatch:;
//}
base.Capture(1, capture_starting_pos, pos);
Utilities.StackPush(ref base.runstack!, ref stackpos, capture_starting_pos);
goto CaptureSkipBacktrack;
CaptureBacktrack:
capture_starting_pos = base.runstack![--stackpos];
goto AlternationBacktrack;
CaptureSkipBacktrack:;
//}
// The loop has no upper bound. Continue iterating greedily.
goto LoopBody;
// The loop iteration failed. Put state back to the way it was before the iteration.
LoopIterationNoMatch:
if (--loop_iteration < 0)
{
// Unable to match the remainder of the expression after exhausting the loop.
goto CharLoopBacktrack1;
}
pos = base.runstack![--stackpos];
UncaptureUntil(base.runstack![--stackpos]);
slice = inputSpan.Slice(pos);
if (loop_iteration == 0)
{
// No iterations have been matched to backtrack into. Fail the loop.
goto CharLoopBacktrack1;
}
goto LoopEnd;
LoopBacktrack:
if (Utilities.s_hasTimeout)
{
base.CheckTimeout();
}
if (loop_iteration == 0)
{
// No iterations of the loop remain to backtrack into. Fail the loop.
goto CharLoopBacktrack1;
}
goto CaptureBacktrack;
LoopEnd:;
//}
// "name" capture group.
{
capture_starting_pos2 = pos;
// Match the string "abc".
if (!slice.StartsWith("abc"))
{
goto LoopBacktrack;
}
pos += 3;
slice = inputSpan.Slice(pos);
base.Capture(3, capture_starting_pos2, pos);
}
// The input matched.
base.runtextpos = pos;
base.Capture(0, matchStart, pos);
return true;
// <summary>Undo captures until it reaches the specified capture position.</summary>
[MethodImpl(MethodImplOptions.AggressiveInlining)]
void UncaptureUntil(int capturePosition)
{
while (base.Crawlpos() > capturePosition)
{
base.Uncapture();
}
}
}
}
}
}
/// <summary>Helper methods used by generated <see cref="Regex"/>-derived implementations.</summary>
[GeneratedCodeAttribute("System.Text.RegularExpressions.Generator", "10.0.14.27113")]
file static class Utilities
{
/// <summary>Default timeout value set in <see cref="AppContext"/>, or <see cref="Regex.InfiniteMatchTimeout"/> if none was set.</summary>
internal static readonly TimeSpan s_defaultTimeout = AppContext.GetData("REGEX_DEFAULT_MATCH_TIMEOUT") is TimeSpan timeout ? timeout : Regex.InfiniteMatchTimeout;
/// <summary>Whether <see cref="s_defaultTimeout"/> is non-infinite.</summary>
internal static readonly bool s_hasTimeout = s_defaultTimeout != Regex.InfiniteMatchTimeout;
/// <summary>Pops 2 values from the backtracking stack.</summary>
[MethodImpl(MethodImplOptions.AggressiveInlining)]
internal static void StackPop(int[] stack, ref int pos, out int arg0, out int arg1)
{
arg0 = stack[--pos];
arg1 = stack[--pos];
}
/// <summary>Pushes 1 value onto the backtracking stack.</summary>
[MethodImpl(MethodImplOptions.AggressiveInlining)]
internal static void StackPush(ref int[] stack, ref int pos, int arg0)
{
// If there's space available for the value, store it.
int[] s = stack;
int p = pos;
if ((uint)p < (uint)s.Length)
{
s[p] = arg0;
pos++;
return;
}
// Otherwise, resize the stack to make room and try again.
WithResize(ref stack, ref pos, arg0);
// <summary>Resize the backtracking stack array and push 1 value onto the stack.</summary>
[MethodImpl(MethodImplOptions.NoInlining)]
static void WithResize(ref int[] stack, ref int pos, int arg0)
{
Array.Resize(ref stack, (pos + 0) * 2);
StackPush(ref stack, ref pos, arg0);
}
}
/// <summary>Pushes 2 values onto the backtracking stack.</summary>
[MethodImpl(MethodImplOptions.AggressiveInlining)]
internal static void StackPush(ref int[] stack, ref int pos, int arg0, int arg1)
{
// If there's space available for all 2 values, store them.
int[] s = stack;
int p = pos;
if ((uint)(p + 1) < (uint)s.Length)
{
s[p] = arg0;
s[p + 1] = arg1;
pos += 2;
return;
}
// Otherwise, resize the stack to make room and try again.
WithResize(ref stack, ref pos, arg0, arg1);
// <summary>Resize the backtracking stack array and push 2 values onto the stack.</summary>
[MethodImpl(MethodImplOptions.NoInlining)]
static void WithResize(ref int[] stack, ref int pos, int arg0, int arg1)
{
Array.Resize(ref stack, (pos + 1) * 2);
StackPush(ref stack, ref pos, arg0, arg1);
}
}
/// <summary>Pushes 3 values onto the backtracking stack.</summary>
[MethodImpl(MethodImplOptions.AggressiveInlining)]
internal static void StackPush(ref int[] stack, ref int pos, int arg0, int arg1, int arg2)
{
// If there's space available for all 3 values, store them.
int[] s = stack;
int p = pos;
if ((uint)(p + 2) < (uint)s.Length)
{
s[p] = arg0;
s[p + 1] = arg1;
s[p + 2] = arg2;
pos += 3;
return;
}
// Otherwise, resize the stack to make room and try again.
WithResize(ref stack, ref pos, arg0, arg1, arg2);
// <summary>Resize the backtracking stack array and push 3 values onto the stack.</summary>
[MethodImpl(MethodImplOptions.NoInlining)]
static void WithResize(ref int[] stack, ref int pos, int arg0, int arg1, int arg2)
{
Array.Resize(ref stack, (pos + 2) * 2);
StackPush(ref stack, ref pos, arg0, arg1, arg2);
}
}
}
}