php 匹配文件中的所有中文 不包含注释

• 先用 php_strip_whitespace 删掉所有空格和注释，
• 然后使用正则 \P{Han} 把中文匹配出来。

从官方文档找的例子 测了满足目前的需求 感谢各位大佬帮忙解答

public function strip_comments($source) {
    $tokens = token_get_all($source);
    $ret = "";
    foreach ($tokens as $token) {
        if (is_string($token)) {
            $ret.= $token;
        } else {
            list($id, $text) = $token;

            switch ($id) {
                case T_COMMENT:
                case T_ML_COMMENT: // we've defined this
                case T_DOC_COMMENT: // and this
                    break;

                default:
                    $ret.= $text;
                    break;
            }
        }
    }
    return trim(str_replace(array('<?','?>'),array('',''),$ret));
}

我猜你大概是需要上国际化吧，我前两周遇到了这个需求。写了个脚本替换

<?php

require __DIR__ . '/vendor/autoload.php';

$start = 2000; #message.key
$zh    = [];


$file_names = [];

$not_file_names = [
    './app/Services/MessageService.php'
];


function searchDir($path, &$files)
{
    if (is_dir($path)) {
        $opendir = opendir($path);
        while ($file = readdir($opendir)) {
            if ($file != '.' && $file != '..') {
                searchDir($path . '/' . $file, $files);
            }
        }
        closedir($opendir);
    }
    if (!is_dir($path)) {
        $files[] = $path;
    }
}

function getDir($dir): array
{
    $files = array();
    searchDir($dir, $files);
    return $files;
}

function replaceContent($matches, $content)
{
    global $zh;
    foreach ($matches[0] as $text) {
        global $start;
        $key          = $start++;
        $replace_text = $text;
        $replace_args = [];
        preg_match_all('/\{([^}]+)\}/', $replace_text, $args_matchs);
        foreach ($args_matchs[0] as $index => $args_match) {
            $replace_args[$index] = $args_matchs[1][$index];
            $replace_text         = str_replace($args_match, ":{$index}", $replace_text);
        }
        $zh[$key]             = $replace_text;
        $content_replace_text = "__(\"message.{$key}\"";
        if ($replace_args) {
            $content_replace_text .= ", [";
            foreach ($replace_args as $arg_index => $replace_arg) {
                if ($arg_index > 0) {
                    $content_replace_text .= ", ";
                }
                $content_replace_text .= $replace_arg;
            }
            $content_replace_text .= "]";
        }
        $content_replace_text .= ")";
        $content              = str_replace($text, $content_replace_text, $content);
    }
    return $content;
}

$file_names = getDir('./app');

foreach ($file_names as $file_name) {
    if (in_array($file_name, $not_file_names)) continue;
    $content = file_get_contents($file_name);

    preg_match_all('/"[^"^\s]*[\x7f-\xff][^"]*"/', $content, $matches1);
    $content = replaceContent($matches1, $content);
    preg_match_all('/\'[^\'^\s]*[\x7f-\xff][^\']*\'/', $content, $matches2);
    $content = replaceContent($matches2, $content);

    file_put_contents($file_name, $content);
}

$messages = "";
foreach ($zh as $key => $value) {
    $messages .= "'{$key}' => {$value}," . PHP_EOL;
}
file_put_contents('lang-messages.text', $messages);