stgsharp/内核源代码/StgSharp.Script/Express/ExpSourceReader.cs

//-----------------------------------------------------------------------
//-----------------------------------------------------------------------
//     file="ExpSourceReader.cs"
//     Project: StgSharp
//     AuthorGroup: Nitload Space
//     Copyright (c) Nitload Space. All rights reserved.
//     
//     Permission is hereby granted, free of charge, to any person 
//     obtaining a copy of this software and associated documentation 
//     files (the “Software”), to deal in the Software without restriction, 
//     including without limitation the rights to use, copy, modify, merge,
//     publish, distribute, sublicense, and/or sell copies of the Software, 
//     and to permit persons to whom the Software is furnished to do so, 
//     subject to the following conditions:
//     
//     The above copyright notice and 
//     this permission notice shall be included in all copies 
//     or substantial portions of the Software.
//     
//     THE SOFTWARE IS PROVIDED “AS IS”, 
//     WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, 
//     INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
//     FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. 
//     IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, 
//     DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, 
//     ARISING FROM, OUT OF OR IN CONNECTION WITH 
//     THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
//     
//-----------------------------------------------------------------------
//-----------------------------------------------------------------------
using CommunityToolkit.HighPerformance;

using StgSharp.Intrinsic;

using System;
using System.Collections.Generic;
using System.Diagnostics.Tracing;
using System.Linq;
using System.Runtime.CompilerServices;
using System.Text;
using System.Text.RegularExpressions;

namespace StgSharp.Script.Express
{
    public partial class ExpSourceReader
    {

        private const int 
            MultiLineEnd = 0x0029002A;                          //  *)

        private const string Token = "token", End = "end", Rest = "rest";

        private bool _isReadingMultiLineComment;
        private int _current;
        private IScriptSourceProvider _provider;
        private string _lineCache;

        public ExpSourceReader( IScriptSourceProvider provider )
        {
            _provider = provider;
            _current = 0;
            _lineCache = string.Empty;
            _isReadingMultiLineComment = false;
        }

        public bool IsEmpty
        {
            get => (( string.IsNullOrEmpty( _lineCache ) || 
                _current >= _lineCache.Length )) && _provider.IsEmpty;
        }

        /// <summary>
        /// <para>Read code until end of a line. Lines in multi-line comment will be ignored. Line
        /// begins with part of multi-line comment will automatically remove the  comment part, but
        /// beginning with a full multi-line comment will not causing removing.</para> <para> (*Just
        /// Like The Comment Here*) Will Not Be Removed </para>
        /// </summary>
        /// <returns></returns>
        public unsafe ReadOnlySpan<char> ReadLine()
        {
            bool lineOver = string.IsNullOrEmpty(_lineCache) || _current >=
                   _lineCache.Length;
            while( lineOver || _isReadingMultiLineComment ) {
                if (lineOver)
                {
                    do
                    {
                        _lineCache = _provider.ReadLine();
                    } while (string.IsNullOrEmpty(_lineCache));
                    _current = 0;
                }
                if( _isReadingMultiLineComment ) {
                    int index;
                    fixed( char* cPtr = _lineCache.AsSpan(_current) ) {
                        index = UnsafeCompute.IndexOfCharPair(
                            cPtr, MultiLineEnd, _lineCache.Length );
                    }
                    if (index == -1)
                    {
                        _lineCache = string.Empty;
                    }
                    else 
                    {
                        _isReadingMultiLineComment = false;
                        _current += index + 2;
                    }
                }
                lineOver = string.IsNullOrEmpty(_lineCache) || _current >=
                   _lineCache.Length;
            }
            return _lineCache.AsSpan().Slice( _current );
        }

        public unsafe ReadOnlySpan<char> ReadToken()
        {
            int begin, end, rest;
            readLine:
            ReadOnlySpan<char> source = ReadLine();
            char c = source[ 0 ];

            if (char.IsLetter(c)) {
                Match match = _nextWordTokenPattern.Match(
                    _lineCache, _current);
                if (match.Success) {
                    begin = match.Groups[Token].Index;
                    end = match.Groups[End].Index;
                    rest = match.Groups[Rest].Index;
                    _current = rest;
                    return source.Slice(0, end - begin);
                } else {
                    throw new ExpInvalidTokenException(_current);
                }
            } else if (char.IsPunctuation(c) || char.IsSymbol(c)) {
                switch (c) {
                    case '"':
                        Match match = _nextStringLiteralPattern.Match(
                            _lineCache, _current);
                        if (match.Success) {
                            begin = match.Groups["token"].Index;
                            end = match.Groups["end"].Index;
                            rest = match.Groups["rest"].Index;
                            _current = rest;
                            return source[..(end - begin)];
                        } else {
                            throw new ExpInvalidCharException('\"');
                        }
                    case '(':
                        char cNext = source[1];
                        if (cNext == '*') {
                            _isReadingMultiLineComment = true;
                            _current += 2;
                            goto readLine;
                        } else {
                            return source[..1];
                        }
                    case '-':

                        // 1. -number
                        // 2. -- comment
                        // 3. - number type param
                        cNext = source[1];
                        if (char.IsNumber(cNext)) {
                            match = _nextNumberLiteralPattern.Match(
                                _lineCache, _current);
                            if (match.Success) {
                                begin = match.Groups[Token].Index;
                                end = match.Groups[End].Index;
                                rest = match.Groups[Rest].Index;
                                _current = rest;
                                return source[..(end - begin)];
                            } else {
                                throw new ExpInvalidTokenException(_current);
                            }
                        } else if (cNext == '-') {
                            _lineCache = string.Empty;
                            _current = 0;
                            goto readLine;
                        } else {
                            _current++;
                            return source[..1];
                        }
                    case ')' or '[' or ']' or '{' or '}' or
                    '+' or '/' or '\\' or '*' or '.' or ',':
                        _current++;
                        return source[..1];
                    default:
                        throw new ExpInvalidCharException(c);
                }
            } else if (char.IsNumber(c)) {
                Match match = _nextNumberLiteralPattern.Match(
                    _lineCache, _current);
                if (match.Success) {
                    begin = match.Groups[Token].Index;
                    end = match.Groups[End].Index;
                    rest = match.Groups[Rest].Index;
                    _current = rest;
                    return source[..(end - begin)];
                } else {
                    throw new ExpInvalidTokenException(_current);
                }
            } else if (char.IsWhiteSpace(c)) {
                Match match = _skipBlankPattern.Match(_lineCache, _current);
                if (match.Success)
                {
                    rest = match.Groups[Rest].Index;
                    _current = rest;
                    goto readLine;
                }
                else
                {
                    throw new ExpInvalidTokenException(_current);
                }
            }else {
                throw new ExpInvalidCharException( c );
            }
        }

        [GeneratedRegex(
                @"(?<token>[a-zA-Z][a-zA-Z0-9_]*)(?<end>\s*?)(?<rest>\S|$)",
                RegexOptions.Singleline )]
        private static partial Regex GetNextWordTokenPattern();

        [GeneratedRegex(
                @"(?<token>-?\s*?[0-9]+(?:\.[0-9]*)?)(?<end>\s*?)(?<rest>\S|$)",
                RegexOptions.Singleline )]
        private static partial Regex GetNumberLiteralPattern();

        [GeneratedRegex( @"(?:\s+?)(?<rest>\S|$)", RegexOptions.Singleline )]
        private static partial Regex GetSkipBlankPattern();

        [GeneratedRegex(
                @"(?<token>"")(?:.*?[^""\\](\\\\)*)?(?<end>"")\s*?(?<next>\S|$)",
                RegexOptions.Singleline )]
        private static partial Regex GetStringLiteralPattern();

        private Regex _nextWordTokenPattern = GetNextWordTokenPattern(),
            _nextStringLiteralPattern = GetStringLiteralPattern(),
            _nextNumberLiteralPattern = GetNumberLiteralPattern(),
            _skipBlankPattern = GetSkipBlankPattern();

    }
}