1

我试图通过读取每个符号的字符串来识别字符串文字我的扫描仪骨架示例:

public sealed class Scanner
{        
    // some class inner implementations        
    /// <summary>
    /// 
    /// </summary>
    /// <param name="Line"></param>
    /// <param name="LineNumber"></param>
    public void Run(String Line, Int32 LineNumber)
    {
        var ChPosition = default(Int32);
        var ChCurrent  = default(Char);
        var Value      = new StringBuilder();

        while (default(Char) != Line.ElementAtOrDefault<Char>(ChPosition))
        {
            ChCurrent = Line.ElementAtOrDefault<Char>(ChPosition);

            #region [Whitespace]
            if (Char.IsWhiteSpace(ChCurrent))
            {
                ChPosition++;
            }
            #endregion
            else
            {
                switch (ChCurrent)
                {                        
                    #region [String Literal (")]
                    case '"':
                        {
                            // skipping " sign, include only string inner value
                            ChCurrent = Line.ElementAtOrDefault<Char>(++ChPosition);

                            // ...? Problematic place!!!

                            this.Tokens.Enqueue(new SharedEntities.Token
                            {
                                Class = SharedEntities.Token.TokenClass.StringLiteral,
                                Value = Value.ToString()
                            }
                            );
                            Value.Clear();
                            ChPosition++;
                            break;
                        }
                    #endregion                        
                        {
                            throw new ScanningException(
                            "<syntax_error#" + ChCurrent.ToString() + ">\n"
                            + "Unsupported character appeared at: {ln: "
                            + LineNumber.ToString()
                            + "; pos: "
                            + (ChPosition + 1).ToString()
                            + "}"
                            );
                        }
                } // [switch(ChCurrent)]                   
            } // [if(Char.IsWhiteSpace(ChCurrent))...else]
        } // [while(default(Char) != Line.ElementAtOrDefault<Char>(ChPosition))]
    } // [public void Run(String Line, Int32 LineNumber)]
} // [public sealed class Scanner]

我的目标是解析类似帕斯卡的字符串:“{所有封闭的东西,但是”,允许“”}”。

4

1 回答 1

4

首先,您显然正在使用某种解析库,如果您修改了您的代码,例如像我所做的那样,您将有更好的机会,这样任何人都可以复制、粘贴、运行您的代码。

答案很简单,您的(字符串文字)解析区域不会解析所有输入。这是您的代码修改为无需任何其他库即可使用:

public class Test
{
    static char ElementAtOrDefault(string value, int position)
    {
        return position >= value.Length ? default(char) : value[position];
    }
    static string parseStringLiteral(string value, ref int ChPosition)
    {
        StringBuilder Value = new StringBuilder();
        char ChCurrent = ElementAtOrDefault(value, ++ChPosition);
        while (ChCurrent != '"')
        {
            Value.Append(ChCurrent);
            ChCurrent = ElementAtOrDefault(value, ++ChPosition);
            if (ChCurrent == '"')
            {
                // "" sequence only acceptable
                if (ElementAtOrDefault(value, ChPosition + 1) == '"')
                {
                    Value.Append(ChCurrent);
                    // skip 2nd double quote
                    ChPosition++;
                    // move position next
                    ChCurrent = ElementAtOrDefault(value, ++ChPosition);
                }
            }
            else if (default(Char) == ChCurrent)
            {
                // message: unterminated string
                throw new Exception("ScanningException");
            }
        }
        ChPosition++;
        return Value.ToString();
    }

    public static void test(string literal)
    {
        Console.WriteLine("testing literal with " + literal.Length + 
            " chars:\n" + literal);
        try
        {
            int pos = 0;
            string res = parseStringLiteral(literal, ref pos);
            Console.WriteLine("Parsed " + res.Length + " chars:\n" + res);
        }
        catch (Exception ex)
        {
            Console.WriteLine("Error: " + ex.Message);
        }
        Console.WriteLine();
    }

    public static int Main(string[] args)
    {
        test(@"""Hello Language Design""");
        test(@"""Is there any problems with the """"strings""""?""");
        test(@"""v#:';?325;.<>,|+_)""(*&^%$#@![]{}\|-_=""");
        return 0;
    }
}

运行这个程序会产生输出:

用 23 个字符测试文字:
《你好语言设计》
解析 21 个字符:
你好语言设计

用 45 个字符测试文字:
“‘字符串’有什么问题吗?”
解析 41 个字符:
“字符串”有什么问题吗?

用 39 个字符测试文字:
"v#:';?325;.,|+_)"(*&^%$#@![]{}\|-_="
解析 18 个字符:
v#:';?325;.,|+_)

所以它适用于您的测试,但算法不正确,请尝试运行:

//literal with "", should produce ", but it does not
test(@"""""""""");

你会错误地得到:

用 4 个字符测试文字:
""""
解析 0 个字符:

问题是,如果你在你的 while 条件中遇到字符 ",你不检查下一个字符,如果它是 " 或不是:

while (ChCurrent != '"') //bug

当然,我为你创建了正确的版本 :-) 在这里(它使用你的风格,只是你的编辑版本):

static string parseStringLiteral(string value, ref int ChPosition)
{
    StringBuilder Value = new StringBuilder();
    char ChCurrent = ElementAtOrDefault(value, ++ChPosition);
    bool goon = true;
    while (goon)
    {
        if (ChCurrent == '"')
        {
            // "" sequence only acceptable
            if (ElementAtOrDefault(value, ChPosition + 1) == '"')
            {
                Value.Append(ChCurrent);
                // skip 2nd double quote
                ChPosition++;
                // move position next
                ChCurrent = ElementAtOrDefault(value, ++ChPosition);
            }
            else goon = false; //break;
        }
        else if (default(Char) == ChCurrent)
        {
            // message: unterminated string
            throw new Exception("ScanningException");
        }
        else
        {
            Value.Append(ChCurrent);
            ChCurrent = ElementAtOrDefault(value, ++ChPosition);
        }
    }
    ChPosition++;
    return Value.ToString();
}

快乐编码:-)

于 2011-01-12T21:48:17.920 回答