将C二进制数据读取函数转换为Python

(为了清楚起见,我编辑了这个,并根据EOL的答案改变了实际问题)
我正在尝试将C中的以下函数转换为 Python但是失败了(参见下面的C代码).据我所知,它需要从from指向的内存位置开始的四个1字节字符,将它们视为无符号长整数以便为每个字节提供4个字节的空间,并进行一些位移以将它们排列为大 – 字节序32位整数.然后将其用于检查文件有效性的算法中. (来自 Treaty of Babel)

static int32 read_alan_int(unsigned char *from)
{
 return ((unsigned long int) from[3])| ((unsigned long int)from[2] << 8) |
       ((unsigned long int) from[1]<<16)| ((unsigned long int)from[0] << 24);
}
/*
  The claim algorithm for Alan files is:
   * For Alan 3,check for the magic word
   * load the file length in blocks
   * check that the file length is correct
   * For alan 2,each word between byte address 24 and 81 is a
      word address within the file,so check that they're all within
      the file
   * Locate the checksum and verify that it is correct
*/
static int32 claim_story_file(void *story_file,int32 extent)
{
 unsigned char *sf = (unsigned char *) story_file;
 int32 bf,i,crc=0;
 if (extent < 160) return INVALID_STORY_FILE_RV;
 if (memcmp(sf,"ALAN",4))
 { /* Identify Alan 2.x */
 bf=read_alan_int(sf+4);
 if (bf > extent/4) return INVALID_STORY_FILE_RV;
 for (i=24;i<81;i+=4)
 if (read_alan_int(sf+i) > extent/4) return INVALID_STORY_FILE_RV;
 for (i=160;i<(bf*4);i++)
 crc+=sf[i];
 if (crc!=read_alan_int(sf+152)) return INVALID_STORY_FILE_RV;
 return VALID_STORY_FILE_RV;
 }
 else
 { /* Identify Alan 3 */
   bf=read_alan_int(sf+12);
   if (bf > (extent/4)) return INVALID_STORY_FILE_RV;
   for (i=184;i<(bf*4);i++)
    crc+=sf[i];
 if (crc!=read_alan_int(sf+176)) return INVALID_STORY_FILE_RV;

 }
 return INVALID_STORY_FILE_RV;
}

我正试图在Python中重新实现它.为了实现read_alan_int函数,我认为导入struct并执行struct.unpack_from(‘> L’,data,offset)会起作用.但是,对于有效文件,对于值bf,它总是返回24,这意味着跳过for循环.

def read_alan_int(file_buffer,i):
    i0 = ord(file_buffer[i]) * (2 ** 24)
    i1 = ord(file_buffer[i + 1]) * (2 ** 16)
    i2 = ord(file_buffer[i + 2]) * (2 ** 8)
    i3 = ord(file_buffer[i + 3])
    return i0 + i1 + i2 + i3

def is_a(file_buffer):
    crc = 0
    if len(file_buffer) < 160:
        return False
    if file_buffer[0:4] == 'ALAN':
        # Identify Alan 2.x
        bf = read_alan_int(file_buffer,4)
        if bf > len(file_buffer)/4:
            return False
        for i in range(24,81,4):
            if read_alan_int(file_buffer,i) > len(file_buffer)/4:
                return False
        for i in range(160,bf * 4):
            crc += ord(file_buffer[i])
        if crc != read_alan_int(file_buffer,152):
            return False
        return True
    else:
        # Identify Alan 3.x
        #bf = read_long(file_buffer,12,'>')
        bf = read_alan_int(file_buffer,12)
        print bf
        if bf > len(file_buffer)/4:
            return False
        for i in range(184,176):
            return False
        return True
    return False


if __name__ == '__main__':
    import sys,struct
    data = open(sys.argv[1],'rb').read()
    print is_a(data)

…但该死的东西仍然会返回24.不幸的是,我的C技能不存在所以我无法让原始程序打印一些调试输出,所以我可以知道应该是什么样的bf.

我究竟做错了什么？

好的,所以我显然正确地做了read_alan_int.但是,对我来说失败的是检查前4个字符是“ALAN”.我的所有测试文件都未通过此测试.我已经更改了代码以删除这个if / else语句,而只是利用早期返回,现在我的所有单元测试都通过了.所以,在实际层面上,我已经完成了.但是,我会继续提出问题来解决这个新问题：我怎么可能纠缠这些位以从前4个字符中获取“ALAN”？

def is_a(file_buffer):
    crc = 0
    if len(file_buffer) < 160:
        return False
    #if file_buffer.startswith('ALAN'):
        # Identify Alan 2.x
    bf = read_long(file_buffer,4)
    if bf > len(file_buffer)/4:
        return False
    for i in range(24,4):
        if read_long(file_buffer,i) > len(file_buffer)/4:
            return False
    for i in range(160,bf * 4):
        crc += ord(file_buffer[i])
    if crc == read_long(file_buffer,152):
        return True
    # Identify Alan 3.x
    crc = 0
    bf = read_long(file_buffer,12)
    if bf > len(file_buffer)/4:
        return False
    for i in range(184,176):
        return True
    return False

/*
  The claim algorithm for Alan files is:
   * For Alan 3,so check that they're all within
      the file
   * Locate the checksum and verify that it is correct
*/

>>> import urllib2
>>> 
>>> alan2 = urllib2.urlopen("http://ifarchive.plover.net/if-archive/games/competition2001/alan/chasing/chasing.acd").read(4)
>>> alan3 = urllib2.urlopen("http://mirror.ifarchive.org/if-archive/games/competition2006/alan/enterthedark/EnterTheDark.a3c").read(4)
>>> 
>>> alan2
'x02x08x01x00'
>>> alan3
'ALAN'