wanalysis.cs

关于CMM语言的解释器

using System;
using System.Collections.Generic;
using System.Text;
using System.Text.RegularExpressions;
using System.Collections;
using System.Windows.Forms;
using System.IO;

namespace CmmInterpretor
{
    class WordAnalysis
    {
        
        public void AnalyzeCode(string sourceCode,
            ref string analysisText, ref string errorText)
        {
            int i = 0; //记录行号
            bool isRemark = false; //判断是否属于注释
            string firstRow = "";  //剩余代码的首行
            StringReader reader = new StringReader(sourceCode);//读取程序段用来进行分析

            while (true)
            {
                
                try
                {
                    firstRow = reader.ReadLine();
                    i++;
                    analysisText += "\r\n第" + Convert.ToString(i) + "行 ：  "
                             + firstRow + "\r\n";
                }
                catch (Exception excp)
                {
                    analysisText += "\r\n程序在运行中发生异常！\r\n";
                    break;
                }
                if (firstRow == null)
                {
                    break;
                }

                RemoveRemark(ref firstRow, ref isRemark);


                ArrayList wordLst = GetWordLst(firstRow);
                foreach (string word in wordLst)
                {

                    string promptWord = "";
                    switch (GetWordType(word))
                    {
                        case ERROR:
                            promptWord = "Error Word : ";
                            errorText += "第" + Convert.ToString(i) + "行 ： "
                                        + "Error Word :" + word + "\r\n";
                            break;
                        case RSVWORD:
                            promptWord = "Reserved Word : ";
                            break;
                        case ID:
                            promptWord = "ID , name = ";
                            break;
                        case INTG:
                            promptWord = "Integer , value = ";
                            break;
                        case REAL:
                            promptWord = "Real , value = ";
                            break;
                        case SYMBOL:
                        default:
                            break;
                    }
                    analysisText += "\t" + Convert.ToString(i)
                                 + " : " + promptWord + word + "\r\n";
                }
            }
        }

        //删除注释内容
        public void RemoveRemark(ref string sourceCode, ref bool isRemark)
        {

            if (isRemark)
            {

                if (!sourceCode.Contains("*/"))
                {
                    sourceCode = "";
                }


                else
                {
                    isRemark = false;
                    sourceCode = sourceCode.Substring(sourceCode.IndexOf("*/") + 2).Trim();
                }
            }


            while (sourceCode.Contains("/*"))
            {
                int startNum = sourceCode.IndexOf("/*");
                isRemark = true;


                if (sourceCode.IndexOf("*/", startNum) != -1)
                {

                    sourceCode = sourceCode.Remove(
                        startNum,
                        sourceCode.IndexOf("*/", startNum)
                            - sourceCode.IndexOf("/*") + 2).Trim();

                    isRemark = false;
                }


                else
                {
                    sourceCode = sourceCode.Remove(
                        startNum,
                        sourceCode.Length - startNum).Trim();
                }
            }
        }

        //将代码段以单词为单位分割的字符串数组，剥离分隔符
        public string[] GetWords(string sourceCode)
        {
            if (sourceCode == null || sourceCode.Trim().Length == 0)
                return null;
            else
                return sourceCode.Split(Symbols, StringSplitOptions.RemoveEmptyEntries);
        }

        //得到包括分隔符在内的单词序列。
        public ArrayList GetWordLst(string sourceCode)
        {
            ArrayList wordLst = new ArrayList();

            sourceCode = sourceCode.Trim() + " ";

            string wordtmp = "";
            string currentChar = "";

            for (int i = 0; i < sourceCode.Length; i++)
            {
                currentChar = Convert.ToString(sourceCode[i]);

                //如果遇上分隔符
                if (Array.IndexOf(Symbols, currentChar) >= 0)
                {
                    //添加单词
                    if (wordtmp.Length != 0)
                        wordLst.Add(wordtmp);
                    wordtmp = "";

                    //排除空格，制表符，回车符，换行符的干扰
                    if (currentChar.Equals(" ") || currentChar.Equals("\t")
                        || currentChar.Equals("\r") || currentChar.Equals("\n"))
                    {
                        continue;
                    }

                    //添加符号。
                    if (currentChar.Equals("<") && sourceCode[i + 1].Equals('>'))
                    {
                        wordLst.Add("<>");
                        i++;
                        continue;
                    }
                    else if (currentChar.Equals("=") && sourceCode[i + 1].Equals('='))
                    {
                        wordLst.Add("==");
                        i++;
                        continue;
                    }
                    else
                    {
                        wordLst.Add(currentChar);
                        continue;
                    }
                }
                else

                    wordtmp += currentChar;
            }
            return wordLst;
        }


        public int GetWordType(string word)
        {

            if (Regex.IsMatch(word, (@"^[0-9]+$")))
            {
                return INTG;
            }


            try
            {
                double d = Convert.ToDouble(word);
                return REAL;
            }
            catch (Exception excp)
            {
            }


            if (Array.IndexOf(ReservedWords, word) != -1)
            {
                return RSVWORD;
            }


            if (Regex.IsMatch(word, (@"^([a-zA-Z]|([a-zA-Z][a-zA-Z_0-9]*[0-9a-zA-Z]))$")))
            {
                return ID;
            }


            if (Array.IndexOf(Symbols, word) != -1)
            {
                return SYMBOL;
            }


            errorNum++;
            return ERROR;
        }

        //词法错误数
        private int errorNum;
        public int ErrorNum
        {
            get { return errorNum; }
            set { errorNum = 0; }
        }

        //CMM的保留字
        public string[] ReservedWords = new string[]
        {
                "if" , "else" , "while" , "read" , "write" , "int" , "real"
        };


        //符号(分隔保留字，标识符，整数，实数)
        public string[] Symbols = new string[] 
        { 
                "==" , "<>" ,"<" , ";" ,"=" ,  "+" , "-" , "*" , "/" ,"(" , ")" , "{" , "}" ,  
                "[" , "]" , " " , "\t" , "\r" ,"\n"  
        };


        //词句类型常量
        const int ERROR = -1;

        const int RSVWORD = -11;
        const int ID = -12;
        const int ARR_ID = -13;
        const int INTG = -14;
        const int REAL = -15;
        const int OPRT = -16;
        const int COMPAR = -17;
        const int SEMI = -18;
        const int BRACKET = -19;
        const int EQUAL = -20;
        const int SYMBOL = -20;
    }
}