首页问答社区 PHP技术正文

利用PHP实现词法分析器与自定义语言

2022-09-03 16:32:12 63 0

一、分析需求

输入中文公式，返回结果，比如：

现有薪资=10000;
个税起点=3000;
当前年份=2021;
如果(当前年份=2022){
个税起点=5000;
}
返回(现有薪资-个税起点)*0.2;

二、实现需求

最初的想法是使用字符串替换的方式，将中文关键字替换成 php 的关键字，然后调用 eval 执行，这样确实也是可以的，但是总觉得不是很美丽，并且不能实现动态解析。就想着自己实现一个简单的词法分析，然后结合 ast 将词法转换成 php 代码执行，岂不快哉。当前版本没有用到抽象语法树来生成代码，全部使用字符串拼接。

<?php

/**

*ClassLexer

*@packageSett\OaLang

*词法分析器
*/
classLexer{
//内置关键字集合
public$keywordList=[];
//内置操作符集合
public$operatorList=[
"+","-","*","/","=",">","<","!","(",")","{","}",",",";"
];
//源代码
private$input;
//当前的字符
private$currChar;
//当前字符位置
private$currCharPos=0;
//结束符
private$eof="eof";
//当前编码
private$currEncode="UTF-8";

//内置关键字
publicconstVAR="variable";
publicconstSTR="string";
publicconstKW="keyword";
publicconstOPR="operator";
publicconstINT="integer";
publicconstNIL="null";


/**
*Lexerconstructor.
*@paramstring$input
*/
publicfunction__construct(string$input){
$this->input=$input;
$this->currChar=mb_substr($this->input,$this->currCharPos,1);
}

/**
*@paramarray$keywordList
*/
publicfunctionsetKeywordList($keywordList){
$this->keywordList=$keywordList;
}

/**
*@returnarray
*@throwsException
*/
publicfunctionparseInput(){
if($this->input==""){
thrownewException("codecannotbeempty");
}
$tokens=[];
do{
$token=$this->nextToken();
if($token["type"]!="eof"){
$tokens[]=$token;
}
if($token["type"]==self::KW){
$tokens[]=$this->makeToken(self::NIL,"");
}
}while($token["type"]!="eof");
return$tokens;
}

/**
*@returnarray
*/
publicfunctionnextToken(){
$this->skipBlankChar();
$this->currChar==""&&$this->currChar=$this->eof;
if($this->isCnLetter()){
$word=$this->matchUntilNextCharIsNotCn();
if($this->isKeyword($word)){
$this->currCharPos-=1;
return$this->currToken(static::KW,$word);
}
//不是关键字的全部归为变量
return$this->makeToken(static::VAR,$word);
}
//如果是操作符
if($this->isOperator()){
return$this->currToken(static::OPR,$this->currChar);
}
//如果是数字
if($this->isNumber()){
return$this->currToken(static::INT,$this->currChar);
}
//如果是字符串
if($str=$this->isStr()){
return$this->currToken(static::STR,$str);
}
//如果是变量
if($this->isVar()){
$word=$this->matchVar();
if($this->isKeyword($word)){
return$this->currToken(static::KW,$word);
}
return$this->makeToken(static::VAR,$word);
}
if($this->currChar==$this->eof){
return$this->currToken('eof',$this->currChar);
}
return$this->currToken(static::VAR,$this->currChar);
}

/**
*@paramstring$input
*@returnstring
*/
privatefunctionmatchVar(string$input=""){
$word=$input?:'';
while($this->isVar()){
$word.=$this->currChar;
$this->nextChar();
}
return$word;
}

/**
*@returnbool
*是否为普通变量
*/
privatefunctionisVar(){
return$this->isCnLetter()||$this->isEnLetter();
}


/**
*跳过空白字符
*/
privatefunctionskipBlankChar(){
while(ord($this->currChar)==10||
ord($this->currChar)==13||
ord($this->currChar)==32){
$this->nextChar();
}
}

/**
*@paramstring$type
*@param$word
*@returnarray
*记录当前token和下一个字符
*/
privatefunctioncurrToken(string$type,$word){
$token=$this->makeToken($type,$word);
$this->nextChar();
return$token;
}

/**
*@paramstring$type
*@paramstring$char
*@returnarray
*/
privatefunctionmakeToken(string$type,string$char){
return["type"=>$type,"char"=>$char,"pos"=>$this->currCharPos];
}


/**
*@returnbool
*判断是否是英文字符
*/
privatefunctionisEnLetter(){
if($this->currChar==""||$this->currChar==$this->eof){
returnfalse;
}
$ord=mb_ord($this->currChar,$this->currEncode);
if($ord>ord('a')&&$ord<ord('z')){
returntrue;
}
returnfalse;
}

/**
*@returnfalse|int
*是否中文字符
*/
privphpatefunctionisCnLetter(){
returnpreg_match("/^[\x{4e00}-\x{9fa5}]+$/u",$this->currChar);
}

/**
*@returnbool
*是否为数字
*/
privatefunctionisNumber(){
returnis_numeric($this->currChar);
}

/**
*@returnbool
*是否是字符串
*/
privatefunctionisStr(){
retujavascriptrn$this->matchCompleteStr();
}

/**
*@returnstring
*匹配完整字符串
*/
privatefunctionmatchCompleteStr(){
$char="";
if($this->currChar=="\""){
$this->nextChar();
while($this->currChar!="\""){
if($this->currChar!="\""){
$char.=$this->currChar;
}
$this->nextChar();
}
return$char;
}
return$char;
}

/**
*@returnbool
*是否是操作符
*/
privatefunctionisOperator(){
returnin_array($this->currChar,$this->operatorList);
}

/**
*@returnstring
*匹配中文字符
*/
privatefunctionmatchUntilNextCharIsNotCn(){
$char="";
while($this->isCnLetter()){
$char.=$this->currChar;
$this->nextChar();
}
return$char;
}

/**
*@returnvoid获取下一个字符
*获取下一个字符
*/
privatefunctionnextChar(){
$this->currCharPos+=1;
$this->currChar=mb_substr($this->input,$this->currCharPos,1);
if($this->currChar==""){
$this->currChar=$this-&g_{http://www.cppcns.com}t;eof;
}
}

/**
*@paramstring$input
*@returnbool
*是否是关键字
*/
privatefunctionisKeyword(string$input){
return($this->keywordList[$input]??"")!="";
}

publicfunctionconvert(array$tokens){
$code="";
foreach($this->lexerIterator($tokens)as$generator){
switch($generator["type"]){
casestatic::KW:
$code.=$this->keywordList[$generator["char"]];
break;
casestatic::VAR:
$code.=sprintf("$%s",$generator["char"]);
break;
casestatic::OPR:
$code.=$this->replace($generator["char"]);
break;
casestatic::INT:
$code.=$generator["char"];
break;
casestatic::STR:
$code.=sprintf("\"%s\"",$generator["char"]);
break;
default:
$code.=$generator["char"];
}
}
return$code;
}

privatefunctionreplace(string$char){
returnstr_replace("+",".",$char);
}

/**
*@paramarray$tokens
*@return\Generator
*/
privatefunctionlexerIterator(array$tokens){
foreach($tokensas$index=>$token){
yield$token;
}
}

}

三、如何使用

require__DIR__."/vendor/autoload.php";
//定义一段代码
$code=<<<EOF
姓名="腕豪";
问候="你好啊";
地址=(1+2)*3;
如果(地址>3){
地址=1;
}否则{
地址="艾欧尼亚"
}
说话=("我"+"爱")+"你";
返回姓名+年龄;
EOF;
$lexer=newLexer($code);
//自定义你的关键字
$kwMap=[
"如果"=>"if","否则"=>"else","返回"=>"return","否则如果"=>"elseif"
];
$lexer->setKeywordList($kwMap);
//这里是生成的词
$tokens=$lexer->parseInput();
//将生成的词转成php,当然你也可以尝试用php-parse转ast再转成php，这里只是简单的拼接
var_dump($lexer->convert($tokens));

生成词

[{
"type":"variable",
"char":"姓名",
"pos":2
},{
"type":"operator",
"char":"=",
"pos":2
},{
"type":"string",
"char":"腕豪",
"pos":7
},{
"type":"operator",
"char":";",
"pos":8
},{
"type":"variable",
"char":"问候",
"pos":13
},{
"type":"operator",
"char":"=",
"pos":13
},{
"type":"string",
"char":"你好啊",
"pos":17
},{
"type":"operator",
"char":";",
"pos":18
},{
"type":"variable",
"char":"地址",
"pos":23
},{
"type":"operator",
"char":"=",
"pos":23
},{
"type":"operator",
"char":"(",
"pos":24
},{
"type":"integer",
"char":"1",
"pos":25
},{
"type":"operator",
"char":"+",
"pos":26
},{
"type":"integer",
"char":"2",
"pos":27
},{
"type":"operator",
"char":")",
"pos":28
},{
"type":"operator",
"char":"*",
"pos":30
},{
"type":"integer",
"char":"3",
"pos":32
},{
"type":"operator",
"char":";",
"pos":33
},{
"type":"keyword",
"char":"如果",
"pos":37
},{
"type":"null",
"char":"",
"pos":38
},{
"type":"operator",
"char":"(",
"pos":38
},{
"type":"variable",
"char":"地址",
"pos":41
},{
"type":"operator",
"char":">",
"pos":42
},{
"type":"integer",
"char":"3",
"pos":44
},{
"type":"operator",
"char":")",
"pos":45
},{
"type":"operator",
"char":"{",
"pos":46
},{
"type":"variable",
"char":"地址",
"pos":55
},{
"type":"operator",
"char":"=",
"pos":55
},{
"type":"integer",
"char":"1",
"pos":56
},{
"type":"operator",
"char":";",
"pos":57
},{
"type":"operator",
"char":"}",
"pos":60
},{
"type":"keyword",
"char":"否则",
"pos":62
},{
"type":"null",
"char":"",
"pos":63
},{
"type":"operator",
"char":"{",
"pos":63
},{
"type":"variable",
"char":"地址",
"pos":72
},{
"type":"operator",
"char":"=",
"pos":72
},{
"type":"string",
"char":"艾欧尼亚",
"pos":78
},{
"type":"operator",
"char":";",
"pos":79
},{
"type":"operator",
"char":"}",
"pos":82
},{
"type":"variable",
"char":"说话",
"pos":87
},{
"type":"operator",
"char":"=",
"pos":88
},{
"type":"operator",
"char":"(",
"pos":90
},{
"type":"string",
"char":"我",
"pos":93
},{
"type":"operator",
"char":"+",
"pos":94
},{
"type":"string",
"char":"爱",
"pos":97
},{
"type":"operator",
"char":")",
"pos":98
},{
"type":"operator",
"char":"+",
"pos":99
},{
"type":"string",
"char":"你",
"pos":102
},{
"type":"operator",
"char":";",
"pos":103
},{
"type":"keyword",
"char":"返回",
"pos":107
},{
"type":"null",
"char":"",
"pos":108
},{
"type":"variable",
"char":"姓名",
"pos":111
},{
"type":"operator",
"char":"+",
"pos":111
},{
"type":"variable",
"cpythonhar":"年龄",
"pos":114
},{
"type":"operator",
"char":";",
"pos":114
}]

输出：