Patch from Hasch@t-online.de (Juergen Hasch) to add UTF-8 as an explict

character set for conversion.  To be used in Winbind and the 'net ads'
commands.

Andrew Bartlett
(This used to be commit fa9d3060ff7510e176d7608b49075379500f55c4)

diff --git a/source3/include/charset.h b/source3/include/charset.h
index b942594d04d23125b7c1d7001924cf8125a14657..07d5e2d59934723a9803d3011d8d70646e0b668f 100644 (file)
--- a/source3/include/charset.h
+++ b/source3/include/charset.h
@@ -19,6 +19,6 @@
 */
 
 /* this defines the charset types used in samba */
-typedef enum {CH_UCS2=0, CH_UNIX=1, CH_DISPLAY=2, CH_DOS=3} charset_t;
+typedef enum {CH_UCS2=0, CH_UNIX=1, CH_DISPLAY=2, CH_DOS=3, CH_UTF8=4} charset_t;
 
-#define NUM_CHARSETS 4
+#define NUM_CHARSETS 5

diff --git a/source3/lib/charcnv.c b/source3/lib/charcnv.c
index d19911dfe2aa726288e9b403c100af006d57e585..97551ede1c5d31ce5bab2a833db508d937a3e01a 100644 (file)
--- a/source3/lib/charcnv.c
+++ b/source3/lib/charcnv.c
@@ -37,6 +37,7 @@ static char *charset_name(charset_t ch)
        else if (ch == CH_UNIX) ret = lp_unix_charset();
        else if (ch == CH_DOS) ret = lp_dos_charset();
        else if (ch == CH_DISPLAY) ret = lp_display_charset();
+       else if (ch == CH_UTF8) ret = "UTF-8";
 
        if (!ret || !*ret) ret = "ASCII";
        return ret;
@@ -151,7 +152,7 @@ size_t convert_string(charset_t from, charset_t to,
                                
                                                
                               break;
-                 case EILSEQ: reason="Illegal myltibyte sequence"; break;
+                 case EILSEQ: reason="Illegal multibyte sequence"; break;
                }
                /* smb_panic(reason); */
        }
@@ -390,6 +391,37 @@ int push_ucs2(const void *base_ptr, void *dest, const char *src, int dest_len, i
        return len;
 }
 
+/****************************************************************************
+copy a string from a char* src to a UTF-8 destination
+return the number of bytes occupied by the string in the destination
+flags can have:
+  STR_TERMINATE means include the null termination
+  STR_UPPER     means uppercase in the destination
+dest_len is the maximum length allowed in the destination. If dest_len
+is -1 then no maxiumum is used
+****************************************************************************/
+int push_utf8(const void *base_ptr, void *dest, const char *src, int dest_len, int flags)
+{
+       int src_len = strlen(src);
+       pstring tmpbuf;
+
+       /* treat a pstring as "unlimited" length */
+       if (dest_len == -1) {
+               dest_len = sizeof(pstring);
+       }
+
+       if (flags & STR_UPPER) {
+               pstrcpy(tmpbuf, src);
+               strupper(tmpbuf);
+               src = tmpbuf;
+       }
+
+       if (flags & STR_TERMINATE) {
+               src_len++;
+       }
+
+       return convert_string(CH_UNIX, CH_UTF8, src, src_len, dest, dest_len);
+}
 
 /****************************************************************************
 copy a string from a ucs2 source to a unix char* destination
@@ -435,6 +467,40 @@ int pull_ucs2_fstring(char *dest, const void *src)
        return pull_ucs2(NULL, dest, src, sizeof(fstring), -1, STR_TERMINATE);
 }
 
+/****************************************************************************
+copy a string from a utf-8 source to a unix char* destination
+flags can have:
+  STR_TERMINATE means the string in src is null terminated
+if STR_TERMINATE is set then src_len is ignored
+src_len is the length of the source area in bytes
+return the number of bytes occupied by the string in src
+the resulting string in "dest" is always null terminated
+****************************************************************************/
+int pull_utf8(const void *base_ptr, char *dest, const void *src, int dest_len, int src_len, int flags)
+{
+       int ret;
+
+       if (dest_len == -1) {
+               dest_len = sizeof(pstring);
+       }
+
+       if (flags & STR_TERMINATE) src_len = strlen(src)+1;
+
+       ret = convert_string(CH_UTF8, CH_UNIX, src, src_len, dest, dest_len);
+       if (dest_len) dest[MIN(ret, dest_len-1)] = 0;
+
+       return src_len;
+}
+
+int pull_utf8_pstring(char *dest, const void *src)
+{
+       return pull_utf8(NULL, dest, src, sizeof(pstring), -1, STR_TERMINATE);
+}
+
+int pull_utf8_fstring(char *dest, const void *src)
+{
+       return pull_utf8(NULL, dest, src, sizeof(fstring), -1, STR_TERMINATE);
+}
 
 /****************************************************************************
 copy a string from a char* src to a unicode or ascii