lex.java

北航编译原理课程设计成果——一个扩充的C0文法编译器

package cn.edu.buaa.scse.liyi.compile.tools;

import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;
import java.io.PushbackReader;
import java.util.LinkedList;

import cn.edu.buaa.scse.liyi.compile.types.Output;

/**
 * 
 * @author liyi
 */
public class Lex
{	
	//关键字
	public static final int CONST=0;
	public static final int INT=1;
	public static final int IF=2;
	public static final int ELSE=3;
	public static final int WHILE=4;
	public static final int VOID=5;
	public static final int MAIN=6;
	public static final int SCANF=7;
	public static final int PRINTF=8;
	public static final int RETURN=9;
	public static final int BREAK=10;
	public static final int CONTINUE=11;
	
	//类型
	public static final int INTEGER=12;
	public static final int IDSY=13;
	public static final int STRING=14;
	
	//操作符
	public static final int ADD=15;
	public static final int MINUS=16;
	public static final int MUL=17;
	public static final int DIV=18;
	public static final int EQUAL=19;
	
	//符号
	public static final int Lpar=20;
	public static final int Rpar=21;
	public static final int Lbra=22;
	public static final int Rbra=23;
	public static final int COMMA=24;
	public static final int SEMICOLON=25;
	
	//关系运算符
	public static final int G=26;		//大于号
	public static final int L=27;		//小于号
	public static final int GE=28;		//大于等于号
	public static final int LE=29;		//小于等于号
	public static final int NE=30;		//非等于号
	public static final int EE=31;		//等于号
	
	public static final String[] KEYWORD={"const","int","if","else","while","void","main","scanf","printf","return","break","continue"};
	
	private PushbackReader codereader=null;
	private Output lop=null;						//当前词法输出
	private LinkedList<Output> list=null;			//词法分析输出链
	private boolean error=false;
	public LinkedList<String> errorList=null;		//错误列表
	
	/**
	 * 词法分析器构造方法
	 * @param file
	 */
	public Lex(File file)
	{
		if(!file.exists()||!file.isFile())
		{
			return;
		}
		
		try
		{
			codereader=new PushbackReader(new FileReader(file),1);
		}
		catch(FileNotFoundException e)
		{
			e.printStackTrace();
		}
	}

	public void setCodereader(PushbackReader codereader)
	{
		this.codereader=codereader;
	}
	public PushbackReader getCodereader()
	{
		return codereader;
	}

	public void setLop(Output lop)
	{
		this.lop=lop;
	}
	public Output getLop()
	{
		return lop;
	}
	
	public void setList(LinkedList<Output> list)
	{
		this.list=list;
	}
	public LinkedList<Output> getList()
	{
		return list;
	}
	
	public void setError(boolean error)
	{
		this.error=error;
	}

	public boolean isError()
	{
		return error;
	}

	/**
	 * 词法分析子程序
	 */
	public void analyze()
	{
		int c=0;
		String ss=null;
		char[] cc=new char[500];
		
		int line=1;
		list=new LinkedList<Output>();
		errorList=new LinkedList<String>();
		
		try
		{
			while((c=codereader.read())!=-1)
			{
				lop=new Output();
				
				if(c==' '||c=='\t'||c=='\r')
				{											//舍去各种空格符
					continue;
				}
				else if(c=='\n')
				{
					++line;
					continue;
				}
				else if(c=='+'||c=='-')
				{											//读到＋，－时
					char a=(char)c;							//把符号存为a，考查后面是否关联
					c=codereader.read();
					if(c==-1)
					{
						if(a=='+')
						{									//当后面没有符号时，即为＋或－本身，并结束词法分析
							lop.setLine(line);
							lop.setType(ADD);
							lop.setWord("+");
						}
						else
						{
							lop.setLine(line);
							lop.setType(MINUS);
							lop.setWord("-");
						}
						list.add(lop);
						break;
					}
					
					if(c<='9'&&c>'0'&&(list.getLast().getType()==EQUAL||list.getLast().getType()==Lpar))
					{										//当加减号后面紧跟数字，且加减号前面是＝号或（号时,视作有符号的数字；否则视为单个加减号
						cc[0]=a;
						int i=1;
						for(;(c<='9'&&c>='0'&&c!=-1);c=codereader.read(),i++)
						{
							cc[i]=(char)c;
						}
						if(c==-1)
						{
							ss=new String(cc,0,i);
							lop.setLine(line);
							lop.setType(INTEGER);
							lop.setWord(ss);
							list.add(lop);
							break;
						}
						else
						{
							ss=new String(cc,0,i);
							codereader.unread(c);
							lop.setLine(line);
							lop.setType(INTEGER);
							lop.setWord(ss);
						}
					}
					else
					{
						codereader.unread(c);
						if(a=='+')
						{
							lop.setLine(line);
							lop.setType(ADD);
							lop.setWord("+");
						}
						else
						{
							lop.setLine(line);
							lop.setType(MINUS);
							lop.setWord("-");
						}
					}
				}
				else if(c=='*')
				{
					lop.setLine(line);
					lop.setType(MUL);
					lop.setWord("*");
				}
				else if(c=='/')
				{
					c=codereader.read();
					if(c=='*')
					{
						while((c=codereader.read())!=-1)
						{
							if(c=='*')
							{
								c=codereader.read();
								if(c=='/')
								{
									break;
								}
								else
								{
									codereader.unread(c);
								}
							}
								
						}
						continue;
					}
					else if(c=='/')
					{
						while((c=codereader.read())!=-1)
						{
							if(c=='\n')
							{
								++line;
								break;
							}
						}
						continue;
					}
					else
					{
						codereader.unread(c);
						lop.setLine(line);
						lop.setType(DIV);
						lop.setWord("/");
					}
				}
				else if(c=='<'||c=='>'||c=='='||c=='!')
				{											//当读到比较运算符时预读一个，考查是否仍为比较运算符，若是则组合为一个运算符，否则为单个算符
					char a=(char)c;
					c=codereader.read();
					if(c=='=')
					{
						if(a=='<')
						{
							lop.setLine(line);
							lop.setType(LE);
							lop.setWord("<=");
						}
						else if(a=='>')
						{
							lop.setLine(line);
							lop.setType(GE);
							lop.setWord(">=");
						}
						else if(a=='=')
						{
							lop.setLine(line);
							lop.setType(EE);
							lop.setWord("==");
						}
						else if(a=='!')
						{
							lop.setLine(line);
							lop.setType(NE);
							lop.setWord("!=");
						}
					}
					else
					{
						if(a=='<')
						{
							lop.setLine(line);
							lop.setType(L);
							lop.setWord("<");
						}
						else if(a=='>')
						{
							lop.setLine(line);
							lop.setType(G);
							lop.setWord(">");
						}
						else if(a=='=')
						{
							lop.setLine(line);
							lop.setType(EQUAL);
							lop.setWord("=");
						}
						else if(a=='!')
						{
							System.out.println("error'!'");
						}
						if(c==-1)
						{
							list.add(lop);
							break;
						}
						codereader.unread(c);
					}
				}												//当读到字母时，一直往下读到不是字母或数字为止，再考查是否为关键字，若是则输出对应关键字，否则为标识符
				else if(c=='_'||c>='a'&&c<='z'||c>='A'&&c<='Z')
				{
					cc[0]=(char)c;
					int i=1;
					boolean kflag=false;

					for(c=codereader.read();(c=='_'||c>='a'&&c<='z'||c>='A'&&c<='Z'||c<='9'&&c>='0')&&c!=-1;c=codereader.read(),i++)
					{
						cc[i]=(char)c;
					}
					ss=new String(cc,0,i);
					//decide iskeyword?
					for(i=0;i<KEYWORD.length;i++)
					{
						if(ss.equals(KEYWORD[i]))
						{
							lop.setLine(line);
							lop.setType(i);
							lop.setWord(ss);
							kflag=true;
							break;
						}
					}
					if(kflag)
					{
						list.add(lop);
						if(c==-1)
						{
							break;
						}
						codereader.unread(c);
						continue;
					}
					else
					{
						lop.setLine(line);
						lop.setType(IDSY);
						lop.setWord(ss);
						if(c==-1)
						{
							list.add(lop);
							break;
						}
						codereader.unread(c);
					}
				}
				else if(c<='9'&&c>='0')
				{
					cc[0]=(char) c;
					int i=1;
					for(c=codereader.read();(c<='9'&&c>='0'&&c!=-1);c=codereader.read(),i++)
					{
						cc[i]=(char)c;
					}
					ss=new String(cc,0,i);
					lop.setLine(line);
					lop.setType(INTEGER);
					lop.setWord(ss);
					if(c==-1)
					{
						list.add(lop);
						break;
					}
					codereader.unread(c);
				} 															//当读到双引号时，一直往下读到右双引号时为止，之前的都存为字符串
				else if(c=='\"')
				{
					cc[0]=(char)c;
					int i=1;
					for(c=codereader.read();c!='\"'&&c!=-1;c=codereader.read(),i++)
					{
						cc[i]=(char)c;
					}
					cc[i]='\"';
					ss=new String(cc,0,i+1);
					lop.setLine(line);
					lop.setType(STRING);
					lop.setWord(ss);
					if(c==-1)
					{
						list.add(lop);
						break;
					}
				}
				else if(c==',')
				{
					lop.setLine(line);
					lop.setType(COMMA);
					lop.setWord(",");
				}
				else if(c==';')
				{
					lop.setLine(line);
					lop.setType(SEMICOLON);
					lop.setWord(";");
				}
				else if(c=='(')
				{
					lop.setLine(line);
					lop.setType(Lpar);
					lop.setWord("(");
				}
				else if(c==')')
				{
					lop.setLine(line);
					lop.setType(Rpar);
					lop.setWord(")");
				}
				else if(c=='{')
				{
					lop.setLine(line);
					lop.setType(Lbra);
					lop.setWord("{");
				}
				else if(c=='}')
				{
					lop.setLine(line);
					lop.setType(Rbra);
					lop.setWord("}");
				}
				else
				{
					error=true;
					this.errorList.add(Error.report(Error.ERR_NOTRECOGNIZED,line,(char)c));
					continue;
				}
				list.add(lop);

			}

			codereader.close();
		}
		catch(IOException e)
		{
			e.printStackTrace();
		}
	}

}