前のプロジェクトには要件がありました。ビジネス スタッフが中国語でいくつかのカスタム数式を作成し、その結果をバックグラウンドで実行してインターフェイスに結果を返す必要があるため、次のように書きました。この有限状態マシンに基づく字句解析器は比較的単純ですが、他の人にインスピレーションを与えることができれば幸いです。
1. 分析要件
中国語の数式を入力し、結果を返します (例:
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;
)。 2. 要件を実装する
最初のアイデアは、文字列置換を使用して中国語のキーワードを PHP のキーワードに置き換え、その後 eval を呼び出して実行することです。これは確かに可能ですが、私はいつも次のように感じています。それは美しくありませんが、動的に解析することはできません。簡単な字句解析を自分で実装して、astと組み合わせて字句解析をphpコードに変換して実行することを考えたのですが、面白そうですよね?現在のバージョンでは、コードの生成に抽象構文ツリーを使用せず、すべて文字列連結を使用します。 [推奨学習: PHP ビデオ チュートリアル ]
<?php /** * Class Lexer * @package Sett\OaLang * 词法分析器 */ class Lexer { // 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 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); } /** * @param string $input * @return string */ private function matchVar(string $input = "") { $word = $input ?: ''; while ($this->isVar()) { $word .= $this->currChar; $this->nextChar(); } return $word; } /** * @return bool * 是否为普通变量 */ private function isVar() { return $this->isCnLetter() || $this->isEnLetter(); } /** * 跳过空白字符 */ private function skipBlankChar() { while (ord($this->currChar) == 10 || ord($this->currChar) == 13 || ord($this->currChar) == 32) { $this->nextChar(); } } /** * @param string $type * @param $word * @return array * 记录当前token和下一个字符 */ 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" => $this->currCharPos]; } /** * @return bool * 判断是否是英文字符 */ private function isEnLetter() { if ($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", $this->currChar); } /** * @return bool * 是否为数字 */ private function isNumber() { return is_numeric($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 获取下一个字符 * 获取下一个字符 */ 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 * 是否是关键字 */ 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; } } }
3.
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; $lexer = new Lexer($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));
[{ "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}, { "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}, { "typ e": "operator", "char": "+", "pos": 111}, { "type": "variable", "char": "年龄", "pos": 114}, { "type": "operator", "char": ";", "pos": 114}]
$姓名="腕豪";$问候="你好啊";$地址=(1.2)*3;if ($地址>3){$地址=1;}else {$地址="艾欧尼亚";}$说话=("我"."爱")."你";return $姓名.$年龄;
4. 使用シナリオ
えっ、実際は役に立たないという人もいるのですか? oaシステムはこれからも役に立ちます。以上がPHP は字句解析やカスタム言語も実装できます。の詳細内容です。詳細については、PHP 中国語 Web サイトの他の関連記事を参照してください。