Question

我尝试使用Scala中的Regex从给定字符串中提取Datalake Store FQDN。有人可以帮忙吗？

#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <netdb.h>
#include <sys/socket.h>
#include <arpa/inet.h>

#define MESSAGE_MAX_LEN  1500 /* MTU, IEEE Std 802.3TM-2015 */
#define PORT 161 /* RFC 1157 */

int out_buf_0_len = 129; /* 0x7f + 2 */
char out_buf_0[] = {
0x30, /* SNMP Packet start */
0x7f, /* SNMP Packet length */
0x02, 0x01, 0x00, /* Version */
0x04, 0x06, 0x70, 0x75, 0x62, 0x6c, 0x69, 0x63, /* Community*/
0xa2, /* GetResponsePDU */
0x72, /* GetResponsePDU Length */
0x02, 0x04, 0x2c, 0x80, 0x7e, 0x2f, /* Request id */
0x02, 0x01, 0x00, /*Error status */
0x02, 0x01, 0x00, /*Error index */
0x30, /* Varbind list start */
0x64, /* Varbind list length*/
0x30, /* Varbind value start */
0x62, /* Varbind value length */
0x06, 0x08, 0x2b, 0x06, 0x01, 0x02, 0x01, 0x01, 0x01, 0x00, /* OID */
0x04,  /* Value start, type octet-string*/
0x56, /* Value length */
0x61, 0x73, 0x64, 0x20, 0x61, /* Value */
0x73, 0x64, 0x20, 0x61, 0x73, 0x64, 0x20, 0x61,
0x73, 0x64, 0x20, 0x61, 0x73, 0x64, 0x20, 0x61,
0x73, 0x64, 0x20, 0x61, 0x73, 0x64, 0x20, 0x61,
0x73, 0x64, 0x20, 0x61, 0x73, 0x64, 0x20, 0x61,
0x73, 0x64, 0x20, 0x61, 0x73, 0x64, 0x20, 0x61,
0x73, 0x64, 0x20, 0x61, 0x73, 0x64, 0x20, 0x61,
0x73, 0x64, 0x20, 0x61, 0x73, 0x64, 0x20, 0x61,
0x73, 0x64, 0x20, 0x61, 0x73, 0x64, 0x20, 0x61,
0x73, 0x64, 0x20, 0x61, 0x73, 0x64, 0x20, 0x61,
0x73, 0x64, 0x20, 0x61, 0x73, 0x64, 0x20, 0x61,
0x73 };

int out_buf_1_len = 130; /* 0x80 + 2 */
char out_buf_1[] = {
0x30, /* SNMP Packet start */
0x80, /* SNMP Packet length */
0x02, 0x01, 0x00, /* Version */
0x04, 0x06, 0x70, 0x75, 0x62, 0x6c, 0x69, 0x63, /* Community*/
0xa2, /* GetResponsePDU */
0x73, /* GetResponsePDU Length */
0x02, 0x04, 0x2c, 0x80, 0x7e, 0x2f, /* Request id */
0x02, 0x01, 0x00, /*Error status */
0x02, 0x01, 0x00, /*Error index */
0x30, /* Varbind list start */
0x65, /* Varbind list length*/
0x30, /* Varbind value start */
0x63, /* Varbind value length */
0x06, 0x08, 0x2b, 0x06, 0x01, 0x02, 0x01, 0x01, 0x01, 0x00, /* OID */
0x04,  /* Value start, type octet-string*/
0x57, /* Value length */
0x61, 0x73, 0x64, 0x20, 0x61, /* Value */
0x73, 0x64, 0x20, 0x61, 0x73, 0x64, 0x20, 0x61,
0x73, 0x64, 0x20, 0x61, 0x73, 0x64, 0x20, 0x61,
0x73, 0x64, 0x20, 0x61, 0x73, 0x64, 0x20, 0x61,
0x73, 0x64, 0x20, 0x61, 0x73, 0x64, 0x20, 0x61,
0x73, 0x64, 0x20, 0x61, 0x73, 0x64, 0x20, 0x61,
0x73, 0x64, 0x20, 0x61, 0x73, 0x64, 0x20, 0x61,
0x73, 0x64, 0x20, 0x61, 0x73, 0x64, 0x20, 0x61,
0x73, 0x64, 0x20, 0x61, 0x73, 0x64, 0x20, 0x61,
0x73, 0x64, 0x20, 0x61, 0x73, 0x64, 0x20, 0x61,
0x73, 0x64, 0x20, 0x61, 0x73, 0x64, 0x20, 0x61,
0x73, 0x64 };

int my_socket;
struct sockaddr_in remote_addr;
int socket_create()
{
    printf("Create socket\n");
    struct sockaddr_in socket_addr;
    if ((my_socket = socket(AF_INET, SOCK_DGRAM, 0)) < 0)
    {
        printf("Cannot create socket. Exit.\n");
        return -1;
    }
    memset((char *)&socket_addr, 0, sizeof(socket_addr));
    socket_addr.sin_family = AF_INET;
    socket_addr.sin_addr.s_addr = htonl(INADDR_ANY);
    socket_addr.sin_port = htons(PORT);
    if (bind(my_socket, (struct sockaddr *)&socket_addr, sizeof(socket_addr)) < 0)
    {
        printf("Bind failed. Exit.\n");
        return - 1;
    }
    printf("Listen on: %s:%d\n", inet_ntoa(socket_addr.sin_addr), PORT);
    return 0;
}

socklen_t addr_len = sizeof(remote_addr);
void socket_listen(char *in_buf)
{
    int  recv_len; /* Bytes received */
    int  nbyt; /* Bytes count */
    char *out_buf[MESSAGE_MAX_LEN];
    int  out_len = 0;

    for (;;) { /* Receive snmp message from snmp manager */
        recv_len = recvfrom(my_socket, in_buf, MESSAGE_MAX_LEN, 0, (struct sockaddr *)&remote_addr, &addr_len);
        if (recv_len > 0)
            if (sendto(my_socket, out_buf_1, out_buf_1_len, 0, (struct sockaddr *)&remote_addr, addr_len) < 0)
                printf("Cannot send data to destination.\n");
    }
}

/* Disable SNMP on local machine. # systemctl stop snmpd 
 * Execute main(): gcc <filename>.c && ./a.out
 * Run SNMP Request: $ snmpget -v 1 -c public 0.0.0.0:161 1.3.6.1.2.1.1.1.0
 */
char in_buf[MESSAGE_MAX_LEN];
int main(int argc, char **argv)
{
    if (socket_create() == -1)
        exit(2);
    socket_listen(in_buf);
}

ADL FQDN的定义中可以有Input = adl://asbwje-fhs.azuredatalakestore.net/123/wds/xyz=456/ Output = adl://asbwje-fhs.azuredatalakestore.net。我尝试过以下方法：

[a-zA-Z_-]

Answer 1

您可以从第一组Regex模式中提取FQDN，如下所示：

val url = "adl://asbwje-fhs.azuredatalakestore.net/123/wds/xyz=456/"

val pattern = """(adl://[^/]*)(/.*)?""".r

val fqdn: String = url match {
  case pattern(x, _) => x
  case _ => "No match!"
}
// fqdn: String = adl://asbwje-fhs.azuredatalakestore.net

第二个可选组用于覆盖URL仅包含FQDN部分的情况。

正则表达式从String中提取ADL FQDN

1 个答案: