
平台论坛博客文库

› 论坛 › 操作系统 › BSD › 如何在挂载磁盘时支持中文？

[NetBSD] 如何在挂载磁盘时支持中文？ [复制链接]

khejing

丰衣足食

论坛徽章:: 0

电梯直达

1楼 [收藏(0)] [报告]

发表于 2009-11-03 13:45 |只看该作者 |倒序浏览

netbsd的mount命令没有-C，也没有-L。然后我也找不到netbsd下的gbfs。

哪位知道的高手帮下忙，谢了！

文库|博客

indraDaze

白手起家

论坛徽章:: 0

2楼 [报告]

发表于 2009-11-09 22:22 |只看该作者

同问，我也想知道。
以前问过，没人回，呵呵！

实战分享：从技术角度谈机器学习入门| 【大话IT】RadonDB低门槛向MySQL集群下战书 | ChinaUnix打赏功能已上线！ | 新一代分布式关系型数据库RadonDB知多少？

pagx

家境小康

论坛徽章:: 0

3楼 [报告]

发表于 2009-11-09 23:56 |只看该作者

编码转换的kiconv 好象最早出现在 netbsd 的哦。不过还是使用UTF-8比较方便。假如有测试环境的话，倒是可以写个UTF-8支持的patch。

diff -rupd src/sys/fs/msdosfs/direntry.h ../src/sys/fs/msdosfs/direntry.h
--- src/sys/fs/msdosfs/direntry.h Sun Dec 4 01:34:44 2005
+++ ../src/sys/fs/msdosfs/direntry.h Wed Nov 11 20:17:28 2009
@@ -133,6 +133,7 @@ int unix2winfn(const u_char *un, int unl
int winChkName(const u_char *un, int unlen, struct winentry *wep,
int chksum);
int win2unixfn(struct winentry *wep, struct dirent *dp, int chksum);
+int fn_utf8_conv(struct dirent *dp, int chksum);
u_int8_t winChksum(u_int8_t *name);
int winSlotCnt(const u_char *un, int unlen);
#endif /* _KERNEL */
diff -rupd src/sys/fs/msdosfs/msdosfs_conv.c ../src/sys/fs/msdosfs/msdosfs_conv.c
--- src/sys/fs/msdosfs/msdosfs_conv.c Mon Mar 16 01:15:58 2009
+++ ../src/sys/fs/msdosfs/msdosfs_conv.c Wed Nov 11 20:34:24 2009
@@ -703,7 +703,7 @@ win2unixfn(struct winentry *wep, struct
u_int8_t *np, *ep = dp->d_name + WIN_MAXLEN;
int i;
- if ((wep->weCnt&WIN_CNT) > howmany(WIN_MAXLEN, WIN_CHARS)
+ if ((wep->weCnt&WIN_CNT) > howmany(WIN_MAXLEN, (WIN_CHARS*2))
|| !(wep->weCnt&WIN_CNT))
return -1;
@@ -725,8 +725,16 @@ win2unixfn(struct winentry *wep, struct
* Offset of this entry
*/
i = ((wep->weCnt&WIN_CNT) - 1) * WIN_CHARS;
- np = (u_int8_t *)dp->d_name + i;
+ np = (u_int8_t *)dp->d_name + i*2;
+ memcpy(np, wep->wePart1, sizeof(wep->wePart1));
+ np += sizeof(wep->wePart1);
+ memcpy(np, wep->wePart2, sizeof(wep->wePart2));
+ np += sizeof(wep->wePart2);
+ memcpy(np, wep->wePart3, sizeof(wep->wePart3));
+ np += sizeof(wep->wePart3);
+
+#ifdef UTF8_SUPPORT
/*
* Convert the name parts
*/
@@ -793,6 +801,7 @@ win2unixfn(struct winentry *wep, struct
if (*cp++)
return -1;
}
+#endif
return chksum;
}
@@ -822,4 +831,143 @@ winSlotCnt(const u_char *un, int unlen)
if (unlen > WIN_MAXLEN)
return 0;
return howmany(unlen, WIN_CHARS);
+}
+
+static int iconv_u2w(const char **inbuf, size_t *inbytes,
+ char **outbuf, size_t *outbytes)
+{
+ u_int8_t mark;
+ u_int16_t uc = 0;
+ char * obuf = NULL;
+ const char *ibuf, *ibuf_end, *obuf_end;
+ if ((inbuf&&inbytes&&outbuf&&outbytes)
+ && (*inbuf&&*inbytes&&*outbuf&&*outbytes)){
+ ibuf = *inbuf;
+ ibuf_end = *inbuf+*inbytes;
+ obuf = *outbuf;
+ obuf_end = *outbuf+*outbytes;
+ int follow = 0;
+ while(ibuf<ibuf_end && &obuf[1]<obuf_end){
+ mark = (u_int8_t)*ibuf++;
+ if (mark<0xF0 && mark>0xE0){
+ /* 1110XXXX */
+ uc = mark&0x0F;
+ follow = 2;
+ }else if (mark<0xE0 && mark>0xC0){
+ /* 110XXXXX */
+ uc = mark&0x1F;
+ follow = 1;
+ }else if (mark<0x80){
+ /* 0XXXXXXX */
+ uc = mark;
+ follow = 0;
+ }else{
+ /* convert fail: 0xF0 0xE0 should NOT in UTF-8 seq */
+ printf("convert fail 0xF0 0xE0\n");
+ break;
+ }
+ if (&ibuf[follow] > ibuf_end){
+ /* unexpect input end */
+ break;
+ }
+ for (; follow>0; follow--){
+ /* 10XX.XXXX 0x80-0xBF*/
+ if ((*ibuf&0xC0) != 0x80){
+ *outbytes = obuf_end - *outbuf;
+ *inbytes = ibuf_end - *inbuf;
+ printf("convert fail SEQ\n");
+ return 0;
+ }
+ uc = (uc<<6)|(*ibuf++&0x3F);
+ }
+ *obuf++ = (uc>>8);
+ *obuf++ = uc;
+ *outbuf = obuf;
+ *inbuf = ibuf;
+ }
+ *outbytes = obuf_end - *outbuf;
+ *inbytes = ibuf_end - *inbuf;
+ }
+ return 0;
+}
+
+static int iconv_w2u(const char **inbuf, size_t *inbytes,
+ char **outbuf, size_t *outbytes)
+{
+ u_int16_t uc = 0;
+ char *obuf = NULL;
+ const char *ibuf, *ibuf_end, *obuf_end;
+ if ((inbuf&&inbytes&&outbuf&&outbytes)
+ && (*inbuf&&*inbytes&&*outbuf&&*outbytes)){
+ ibuf = *inbuf;
+ ibuf_end = *inbuf+*inbytes;
+ obuf = *outbuf;
+ obuf_end = *outbuf+*outbytes;
+ int follow = 0;
+ while(&ibuf[1]<ibuf_end && obuf<obuf_end){
+ uc = (0xFF&*ibuf++);
+ uc = (0xFF&*ibuf++)|(uc<<8);
+ if (uc < 0x80){
+ *obuf++ = (uc);
+ follow = 0;
+ }else if (uc < 0x800){
+ *obuf++ = (uc>>6)|0xC0;
+ follow = 1;
+ }else {
+ /* assert(uc<=0xFFFF); */
+ *obuf++ = (uc>>12)|0xE0;
+ follow = 2;
+ }
+ if (&obuf[follow] > obuf_end){
+ /*no output buffer */
+ break;
+ }
+ for (follow--;follow>=0;follow--){
+ int shift = follow*6;
+ u_int8_t ch = uc>>shift;
+ *obuf++ = (ch&0x3F)|0x80;
+ }
+ *outbuf = obuf;
+ *inbuf = ibuf;
+ }
+ *outbytes = obuf_end - *outbuf;
+ *inbytes = ibuf_end - *inbuf;
+ }
+ return 0;
+}
+
+int fn_utf8_conv(struct dirent *dp, int chksum)
+{
+ size_t ucs2len, utf8len;
+ u_int8_t *ucs2buf, *utf8buf, *cp;
+
+ u_int8_t buff[WIN_MAXLEN];
+
+ utf8buf = buff;
+ utf8len = sizeof(buff)-1;
+
+ ucs2buf = dp->d_name;
+ ucs2len = dp->d_namlen;
+
+ iconv_w2u(&ucs2buf, &ucs2len, &utf8buf, &utf8len);
+
+ /* utf-8 name too long, just return */
+ if (ucs2len > 0)
+ return -1;
+
+ cp = dp->d_name;
+ /* notice: WIN_MAXLEN < sizeof(dp->d_name), so sizeof(buff)-utf8len+1 < sizeof(dp->d_name) */
+ for (utf8buf=buff; utf8len<sizeof(buff)-1; utf8len++) {
+ switch (*cp++ = *utf8buf++) {
+ case '0':
+ dp->d_namlen = (cp-dp->d_name);
+ return chksum;
+ case '/':
+ *(cp-1) = 0;
+ return -1;
+ }
+ }
+
+ dp->d_namlen = (cp-dp->d_name);
+ return chksum;
}
diff -rupd src/sys/fs/msdosfs/msdosfs_vnops.c ../src/sys/fs/msdosfs/msdosfs_vnops.c
--- src/sys/fs/msdosfs/msdosfs_vnops.c Sat Jul 4 05:17:40 2009
+++ ../src/sys/fs/msdosfs/msdosfs_vnops.c Wed Nov 11 20:16:04 2009
@@ -1634,6 +1634,7 @@ msdosfs_readdir(void *v)
offset / sizeof(struct direntry);
dirbuf->d_type = DT_REG;
}
+ chksum = fn_utf8_conv(dirbuf, chksum);
if (chksum != winChksum(dentp->deName))
dirbuf->d_namlen = dos2unixfn(dentp->deName,
(u_char *)dirbuf->d_name,