灵域,盗墓笔记有声小说,玄幻小说排行榜完本

新聞中心

這里有您想知道的互聯(lián)網(wǎng)營銷解決方案

PHP也可以實現(xiàn)詞法分析與自定義語言！

10多年的北海網(wǎng)站建設(shè)經(jīng)驗，針對設(shè)計、前端、開發(fā)、售后、文案、推廣等六對一服務(wù)，響應(yīng)快，48小時及時工作處理。全網(wǎng)營銷推廣的優(yōu)勢是能夠根據(jù)用戶設(shè)備顯示端的尺寸不同，自動調(diào)整北海建站的顯示方式，使網(wǎng)站能夠適用不同顯示終端，在瀏覽器中調(diào)整網(wǎng)站的寬度，無論在任何一種瀏覽器上瀏覽網(wǎng)站，都能展現(xiàn)優(yōu)雅布局與設(shè)計，從而大程度地提升瀏覽體驗。創(chuàng)新互聯(lián)公司從事“北海網(wǎng)站設(shè)計”,“北海網(wǎng)站推廣”以來，每個客戶項目都認真落實執(zhí)行。

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?！就扑]學(xué)習(xí)：PHP視頻教程】

", "<", "!", "(", ")", "{", "}", ",", ";"
    ];
    // 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 = << 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

新聞標題：PHP也可以實現(xiàn)詞法分析與自定義語言！
標題網(wǎng)址：http://fisionsoft.com.cn/article/dheccjj.html

新聞中心

其他資訊