溫馨提示×
您好，登錄后才能下訂單哦！
點擊 登錄注冊 即表示同意《億速云用戶服務(wù)條款》
您好，登錄后才能下訂單哦！
本文小編為大家詳細介紹“PHP怎么實現(xiàn)詞法分析與自定義語言”，內(nèi)容詳細，步驟清晰，細節(jié)處理妥當，希望這篇“PHP怎么實現(xiàn)詞法分析與自定義語言”文章能幫助大家解決疑惑，下面跟著小編的思路慢慢深入，一起來學習新知識吧。
之前項目有一個需求，業(yè)務(wù)人員使用中文編寫一些自定義公式，然后需要我們后臺執(zhí)行將結(jié)果返回到界面上，于是就基于有限狀態(tài)機寫了這個詞法分析器，比較簡單，希望能夠拋磚引玉。
一、分析需求
輸入中文公式，返回結(jié)果，比如：
現(xiàn)有薪資=10000;
個稅起點=3000;
當前年份=2021;
如果(當前年份=2022){
個稅起點=5000;
}
返回 (現(xiàn)有薪資-個稅起點) * 0.2;二、實現(xiàn)需求
最初的想法是使用字符串替換的方式，將中文關(guān)鍵字替換成php的關(guān)鍵字，然后調(diào)用eval執(zhí)行，這樣確實也是可以的，但是總覺得不是很美麗，并且不能實現(xiàn)動態(tài)解析。就想著自己實現(xiàn)一個簡單的詞法分析，然后結(jié)合ast將詞法轉(zhuǎn)換成php代碼執(zhí)行，豈不快哉。當前版本沒有用到抽象語法樹來生成代碼，全部使用字符串拼接。
<?php
/**
* Class Lexer
* @package Sett\OaLang
* 詞法分析器
*/
class Lexer {
// 內(nèi)置關(guān)鍵字集合
public $keywordList = [];
// 內(nèi)置操作符集合
public $operatorList = [
"+", "-", "*", "/", "=", ">", "<", "!", "(", ")", "{", "}", ",", ";"
];
// 源代碼
private $input;
// 當前的字符
private $currChar;
// 當前字符位置
private $currCharPos = 0;
// 結(jié)束符
private $eof = "eof";
// 當前編碼
private $currEncode = "UTF-8";
// 內(nèi)置關(guān)鍵字
public const VAR = "variable";
public const STR = "string";
public const KW = "keyword";
public const OPR = "operator";
public const INT = "integer";
public const NIL = "null";
/**
* Lexer constructor.
* @param string $input
*/
public function __construct(string $input) {
$this->input = $input;
$this->currChar = mb_substr($this->input, $this->currCharPos, 1);
}
/**
* @param array $keywordList
*/
public function setKeywordList($keywordList) {
$this->keywordList = $keywordList;
}
/**
* @return array
* @throws Exception
*/
public function parseInput() {
if ($this->input == "") {
throw new Exception("code can not be empty");
}
$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;
}
/**
* @return array
*/
public function nextToken() {
$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);
}
// 不是關(guān)鍵字的全部歸為變量
return $this->makeToken(static::VAR, $word);
}
// 如果是操作符
if ($this->isOperator()) {
return $this->currToken(static::OPR, $this->currChar);
}
// 如果是數(shù)字
if ($this->isNumber()) {
return $this->currToken(static::INT, $this->currChar);
}
// 如果是字符串
if ($str = $this->isStr()) {
return $this->currToken(static::STR, $str);
}
// 如果是變量
if ($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);
}
/**
* @param string $input
* @return string
*/
private function matchVar(string $input = "") {
$word = $input ?: '';
while ($this->isVar()) {
$word .= $this->currChar;
$this->nextChar();
}
return $word;
}
/**
* @return bool
* 是否為普通變量
*/
private function isVar() {
return $this->isCnLetter() || $this->isEnLetter();
}
/**
* 跳過空白字符
*/
private function skipBlankChar() {
while (ord($this->currChar) == 10 ||
ord($this->currChar) == 13 ||
ord($this->currChar) == 32) {
$this->nextChar();
}
}
/**
* @param string $type
* @param $word
* @return array
* 記錄當前token和下一個字符
*/
private function currToken(string $type, $word) {
$token = $this->makeToken($type, $word);
$this->nextChar();
return $token;
}
/**
* @param string $type
* @param string $char
* @return array
*/
private function makeToken(string $type, string $char) {
return ["type" => $type, "char" => $char, "pos" => $this->currCharPos];
}
/**
* @return bool
* 判斷是否是英文字符
*/
private function isEnLetter() {
if ($this->currChar == "" || $this->currChar == $this->eof) {
return false;
}
$ord = mb_ord($this->currChar, $this->currEncode);
if ($ord > ord('a') && $ord < ord('z')) {
return true;
}
return false;
}
/**
* @return false|int
* 是否中文字符
*/
private function isCnLetter() {
return preg_match("/^[\x{4e00}-\x{9fa5}]+$/u", $this->currChar);
}
/**
* @return bool
* 是否為數(shù)字
*/
private function isNumber() {
return is_numeric($this->currChar);
}
/**
* @return bool
* 是否是字符串
*/
private function isStr() {
return $this->matchCompleteStr();
}
/**
* @return string
* 匹配完整字符串
*/
private function matchCompleteStr() {
$char = "";
if ($this->currChar == "\"") {
$this->nextChar();
while ($this->currChar != "\"") {
if ($this->currChar != "\"") {
$char .= $this->currChar;
}
$this->nextChar();
}
return $char;
}
return $char;
}
/**
* @return bool
* 是否是操作符
*/
private function isOperator() {
return in_array($this->currChar, $this->operatorList);
}
/**
* @return string
* 匹配中文字符
*/
private function matchUntilNextCharIsNotCn() {
$char = "";
while ($this->isCnLetter()) {
$char .= $this->currChar;
$this->nextChar();
}
return $char;
}
/**
* @return void 獲取下一個字符
* 獲取下一個字符
*/
private function nextChar() {
$this->currCharPos += 1;
$this->currChar = mb_substr($this->input, $this->currCharPos, 1);
if ($this->currChar == "") {
$this->currChar = $this->eof;
}
}
/**
* @param string $input
* @return bool
* 是否是關(guān)鍵字
*/
private function isKeyword(string $input) {
return ($this->keywordList[$input] ?? "") != "";
}
public function convert(array $tokens) {
$code = "";
foreach ($this->lexerIterator($tokens) as $generator) {
switch ($generator["type"]) {
case static::KW:
$code .= $this->keywordList[$generator["char"]];
break;
case static::VAR:
$code .= sprintf("$%s", $generator["char"]);
break;
case static::OPR:
$code .= $this->replace($generator["char"]);
break;
case static::INT:
$code .= $generator["char"];
break;
case static::STR:
$code .= sprintf("\"%s\"", $generator["char"]);
break;
default:
$code .= $generator["char"];
}
}
return $code;
}
private function replace(string $char) {
return str_replace("+", ".", $char);
}
/**
* @param array $tokens
* @return \Generator
*/
private function lexerIterator(array $tokens) {
foreach ($tokens as $index => $token) {
yield $token;
}
}
}三、如何使用
require __DIR__ . "/vendor/autoload.php";
// 定義一段代碼
$code = <<<EOF
姓名="腕豪";
問候="你好啊";
地址=(1+2) * 3;
如果(地址 > 3){
地址=1;
}否則{
地址="艾歐尼亞"
}
說話 = ("我"+"愛")+"你";
返回 姓名+年齡;
EOF;
$lexer = new Lexer($code);
// 自定義你的關(guān)鍵字
$kwMap = [
"如果" => "if", "否則" => "else", "返回" => "return", "否則如果" => "elseif"
];
$lexer->setKeywordList($kwMap);
// 這里是生成的詞
$tokens = $lexer->parseInput();
// 將生成的詞轉(zhuǎn)成php,當然你也可以嘗試用php-parse轉(zhuǎn)ast再轉(zhuǎn)成php，這里只是簡單的拼接
var_dump($lexer->convert($tokens));生成詞
[{
"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": "問候",
"pos": 13}, {
"type": "operator",
"char": "=",
"pos": 13}, {
"typ e": "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": "nul l",
"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": "否則",
"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": "艾歐尼亞",
"pos": 78}, {
"type": "operator",
"char": ";",
"pos": 79}, {
"type": "operator",
"char": "}",
"pos": 82}, {
"type": "variable",
"char": "說話",
"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": "愛",
"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}, {
"typ e": "operator",
"char": "+",
"pos": 111}, {
"type": "variable",
"char": "年齡",
"pos": 114}, {
"type": "operator",
"char": ";",
"pos": 114}]輸出：
$姓名="腕豪";$問候="你好啊";$地址=(1.2)*3;if ($地址>3){$地址=1;}else {$地址="艾歐尼亞";}$說話=("我"."愛")."你";return $姓名.$年齡;能執(zhí)行嗎？當然能。還存在一些小bug，不想改了。
四、使用場景
什么，居然有人說沒什么用？oa系統(tǒng)總有用到的時候。
讀到這里，這篇“PHP怎么實現(xiàn)詞法分析與自定義語言”文章已經(jīng)介紹完畢，想要掌握這篇文章的知識點還需要大家自己動手實踐使用過才能領(lǐng)會，如果想了解更多相關(guān)內(nèi)容的文章，歡迎關(guān)注億速云行業(yè)資訊頻道。
免責聲明：本站發(fā)布的內(nèi)容（圖片、視頻和文字）以原創(chuàng)、轉(zhuǎn)載和分享為主，文章觀點不代表本網(wǎng)站立場，如果涉及侵權(quán)請聯(lián)系站長郵箱：is@yisu.com進行舉報，并提供相關(guān)證據(jù)，一經(jīng)查實，將立刻刪除涉嫌侵權(quán)內(nèi)容。
億速云公眾號
手機網(wǎng)站二維碼