Question

我正在尝试编写一个c＃算法来从在线视频文件中获取哈希值以搜索（https://trac.opensubtitles.org/projects/opensubtitles/wiki/HashSourceCodes）

上的字幕

我的想法是该算法被提供给视频文件的url，并返回哈希值。简单。问题是，我没有得到正确的价值。根据我链接的页面，this file应该返回8e245d9679d31e12，但我得到00c4fcb4aa6f763e。这是我的C＃：

public static async Task<byte[]> ComputeMovieHash(string filename)
{
    long filesize = 0;

    //Get File Size
    HttpWebRequest req = (HttpWebRequest)WebRequest.Create(filename);
    req.Method = "HEAD";
    var resp = await req.GetResponseAsync();
    filesize = resp.ContentLength;
    long lhash = filesize;

    //Get first 64K bytes
    byte[] firstbytes = new byte[0];
    using (HttpClient client = new HttpClient())
    {
        client.DefaultRequestHeaders.Add("Range", "bytes=0-65536");
        using (HttpResponseMessage response = await client.GetAsync(filename))
        {
            Debug.WriteLine("getting first bytes (bytes=0-65536)");
            firstbytes = await response.Content.ReadAsByteArrayAsync();
        }
    }
    lhash += BitConverter.ToInt64(firstbytes, 0);

    //Get last 64K bytes
    byte[] lastbytes = new byte[0];
    using (HttpClient client = new HttpClient())
    {
        client.DefaultRequestHeaders.Add("Range", "bytes=" + (filesize - 65536) + "-" + filesize);
        using (HttpResponseMessage response = await client.GetAsync(filename))
        {
            Debug.WriteLine("getting last bytes (" + "bytes=" + (filesize - 65536) + "-" + filesize + ")");
            lastbytes = await response.Content.ReadAsByteArrayAsync();
        }
    }
    lhash += BitConverter.ToInt64(lastbytes, 0);

    //Return result
    byte[] result = BitConverter.GetBytes(lhash);
    Array.Reverse(result);
    Debug.WriteLine("RESULT=" + ToHexadecimal(result));
    return result;
}

我做错了什么？我把它与opensubtitles.org给出的代码进行了比较，似乎它应该有相同的结果：/

Answer 1

您的代码中有几处错误：

范围bytes=0-65536会返回6553 7 个字节，这个字节太多了。
您不计算64位校验和，因为BitConverter.ToInt64(firstbytes, 0)占用前8个字节并将它们转换为数字，其余65536-8个字节被完全忽略。

固定版本应该是这样的：

public static async Task<byte[]> ComputeMovieHash(string filename) {
    long filesize = 0;

    //Get File Size
    HttpWebRequest req = (HttpWebRequest) WebRequest.Create(filename);
    req.Method = "HEAD";
    var resp = await req.GetResponseAsync();
    filesize = resp.ContentLength;
    long lhash = filesize;

    //Get first 64K bytes
    byte[] firstbytes;
    using (HttpClient client = new HttpClient()) {
        client.DefaultRequestHeaders.Add("Range", "bytes=0-65535");
        using (HttpResponseMessage response = await client.GetAsync(filename)) {
            Debug.WriteLine("getting first bytes (bytes=0-65535)");
            firstbytes = await response.Content.ReadAsByteArrayAsync();
        }
    }
    for (int i = 0; i < firstbytes.Length; i += sizeof (long)) {
        lhash += BitConverter.ToInt64(firstbytes, i);
    }

    //Get last 64K bytes
    byte[] lastbytes;
    using (HttpClient client = new HttpClient()) {
        client.DefaultRequestHeaders.Add("Range", "bytes=" + Math.Max(filesize - 65536, 0) + "-" + filesize);
        using (HttpResponseMessage response = await client.GetAsync(filename)) {
            Debug.WriteLine("getting last bytes (" + "bytes=" + (filesize - 65536) + "-" + filesize + ")");
            lastbytes = await response.Content.ReadAsByteArrayAsync();
        }
    }
    for (int i = 0; i < lastbytes.Length; i += sizeof (long)) {
        lhash += BitConverter.ToInt64(lastbytes, i);
    }

    //Return result
    byte[] result = BitConverter.GetBytes(lhash);
    Array.Reverse(result);
    return result;
}

我的OSDB哈希算法出了什么问题？

1 个答案: