javascript - 这个数据的格式是什么？它是自定义格式吗？

Question

我将此数据作为 ajax 响应获取:

{
    "idArray" = (
        "99516",
        "99518",
        "97344",
        "97345",
        "98425"
    );
    "frame" = {
        "size" = {
            "width" = "8";
            "height" = "8";
        };
        "origin" = {
            "x" = "244";
            "y" = "345";
        };
    };
},

这只是数据的一部分，但它以相同的格式继续。我无权访问生成此数据的文件源。

这是已知格式还是自定义格式？

Answer 1

由于人们倾向于对所有事物使用正则表达式，甚至是不能用正则表达式解析的事物(即非正则语言):我已经为这种数据格式编写了一个概念验证解析器:

$input = '{
    "idArray" = (
        "99516",
        "99518",
        "97344",
        "97345",
        "98425"
    );
    "frame" = {
        "size" = {
            "width" = "8";
            "height" = "8";
        };
        "origin" = {
            "x" = "244";
            "y" = "345";
        };
    };
}';

echo json_encode(parse($input));

function parse($input) {
    $tokens = tokenize($input);
    $index = 0;
    $result = parse_value($tokens, $index);
    if ($result[1] !== count($tokens)) {
        throw new Exception("parsing stopped at token " . $result[1] . " but there is more input");
    }
    return $result[0][1];
}

function tokenize($input) {
    $tokens = array();
    $length = strlen($input);
    $pos = 0;
    while($pos < $length) {
        list($token, $pos) = find_token($input, $pos);
        $tokens[] = $token;
    }
    return $tokens;
}

function find_token($input, $pos) {
    $static_tokens = array("=", "{", "}", "(", ")", ";", ",");
    while(preg_match("/\s/mis", substr($input, $pos, 1))) { // eat whitespace
        $pos += 1;
    }
    foreach ($static_tokens as $static_token) {
        if (substr($input, $pos, strlen($static_token)) === $static_token) {
            return array($static_token, $pos + strlen($static_token));
        }
    }
    if (substr($input, $pos, 1) === '"') {
        $length = strlen($input);
        $token_length = 1;
        while ($pos + $token_length < $length) {
            if (substr($input, $pos + $token_length, 1) === '"') {
                return array(array("value", substr($input, $pos + 1, $token_length - 1)), $pos + $token_length + 1);
            }
            $token_length += 1;
        }
    }
    throw new Exception("invalid input at " . $pos . ": `" . substr($input, $pos - 10, 20) . "`");
}

// value is either an object {}, an array (), or a literal ""
function parse_value($tokens, $index) {
    if ($tokens[$index] === "{") {  // object: a list of key-value pairs, glued together by ";"
        $return_value = array();
        $index += 1;
        while ($tokens[$index] !== "}") {
            list($key, $value, $index) = parse_key_value($tokens, $index);
            $return_value[$key] = $value[1];
            if ($tokens[$index] !== ";") {
                throw new Exception("Unexpected: " . print_r($tokens[$index], true));
            }
            $index += 1;
        }
        return array(array("object", $return_value), $index + 1);
    }
    if ($tokens[$index] === "(") {  // array: a list of values, glued together by ",", the last "," is optional
        $return_value = array();
        $index += 1;
        while ($tokens[$index] !== ")") {
            list($value, $index) = parse_value($tokens, $index);
            $return_value[] = $value[1];
            if ($tokens[$index] === ",") {  // last, is optional
                $index += 1;
            } else {
                if ($tokens[$index] !== ")") {
                    throw new Exception("Unexpected: " . print_r($tokens[$index], true));
                }
                return array(array("array", $return_value), $index + 1);
            }
        }
        return array(array("array", $return_value), $index + 1);
    }
    if ($tokens[$index][0] === "value") {
        return array(array("string", $tokens[$index][1]), $index + 1);
    }
    throw new Exception("Unexpected: " . print_r($tokens[$index], true));
}

// find a key (string) followed by '=' followed by a value (any value)
function parse_key_value($tokens, $index) {
    list($key, $index) = parse_value($tokens, $index);
    if ($key[0] !== "string") { // key must be a string
        throw new Exception("Unexpected: " . print_r($key, true));
    }
    if ($tokens[$index] !== "=" ) {
        throw new Exception("'=' expected");
    }
    $index += 1;
    list($value, $index) = parse_value($tokens, $index);
    return array($key[1], $value, $index);
}

输出是:

{"idArray":["99516","99518","97344","97345","98425"],"frame":{"size":{"width":"8","height":"8"},"origin":{"x":"244","y":"345"}}}

注释

• 原始输入有尾随 ,。我已经删除了那个 Angular 色。如果你把它放回去，它会抛出一个错误(更多的输入)。

• 从这个意义上说，这个解析器是天真的，它在开始解析之前标记所有输入。这对大输入不利。

• 我没有在分词器中为字符串添加转义检测。喜欢:"foo\"bar"。

这是一个有趣的练习。如果您有任何问题，请告诉我。

编辑:我看到这是一个 JavaScript 问题。将 PHP 移植到 JavaScript 应该不会太难。 list($foo, $bar) = func() 等同于:var res = func(); var foo = res[0]; var bar = res[1];