smb/server/unicode.c

1 // SPDX-License-Identifier: GPL-2.0-or-later
3  *   Some of the source code in this file came from fs/cifs/cifs_unicode.c
17  * cifs_mapchar() - convert a host-endian char to proper char in codepage
19  * @from:	host-endian source string
23  * This function handles the conversion of a single character. It is the
24  * responsibility of the caller to ensure that the target buffer is large
25  * enough to hold the result of the conversion (at least NLS_MAX_CHARSET_SIZE).
27  * Return:	string length after conversion
73 	len = cp->uni2char(src_char, target, NLS_MAX_CHARSET_SIZE);  in cifs_mapchar()
81 	if (strcmp(cp->charset, "utf8"))  in cifs_mapchar()
95  * smb_utf16_bytes() - compute converted string length
100  * Walk a utf16le string and return the number of bytes that the string will
104  * Return:	string length after conversion
137  * smb_from_utf16() - convert utf16le string to local charset
145  * Convert a little-endian utf16le string (as sent by the server) to a string
147  * that the code doesn't walk off of the end of the buffer (which is always
148  * a danger if the alignment of the source buffer is off). The destination
150  * buffer. Returns the length of the destination string in bytes (including
153  * Note that some windows versions actually send multiword UTF-16 characters
154  * instead of straight UTF16-2. The linux nls routines however aren't able to
155  * deal with those characters properly. In the event that we get some of
158  * Return:	string length after conversion
168 	__u16 ftmp[3];	/* ftmp[3] = 3array x 2bytes = 6bytes UTF-16 */  in smb_from_utf16()
171 	 * because the chars can be of varying widths, we need to take care  in smb_from_utf16()
173 	 * end of it. Until we get to this offset, we don't need to check  in smb_from_utf16()
176 	safelen = tolen - (NLS_MAX_CHARSET_SIZE + nullsize);  in smb_from_utf16()
191 		 * conversion bleed into the null terminator  in smb_from_utf16()
195 			if ((outlen + charlen) > (tolen - nullsize))  in smb_from_utf16()
204 		 * charlen (=bytes of UTF-8 for 1 character)  in smb_from_utf16()
205 		 * 4bytes UTF-8(surrogate pair) is charlen=4  in smb_from_utf16()
206 		 * (4bytes UTF-16 code)  in smb_from_utf16()
207 		 * 7-8bytes UTF-8(IVS) is charlen=3+4 or 4+4  in smb_from_utf16()
208 		 * (2 UTF-8 pairs divided to 2 UTF-16 pairs)  in smb_from_utf16()
213 			/* 5-6bytes UTF-8 */  in smb_from_utf16()
217 	/* properly null-terminate string */  in smb_from_utf16()
225  * smb_strtoUTF16() - Convert character string to unicode string
231  * Return:	string length after conversion
241 	if (!strcmp(codepage->charset, "utf8")) {  in smb_strtoUTF16()
243 		 * convert utf8 -> utf16, we assume we have enough space  in smb_strtoUTF16()
244 		 * as caller should have assumed conversion does not overflow  in smb_strtoUTF16()
261 	for (i = 0; len > 0 && *from; i++, from += charlen, len -= charlen) {  in smb_strtoUTF16()
262 		charlen = codepage->char2uni(from, len, &wchar_to);  in smb_strtoUTF16()
277  * smb_strndup_from_utf16() - copy a string from wire format to the local
302 			return ERR_PTR(-ENOMEM);  in smb_strndup_from_utf16()
307 			return ERR_PTR(-EINVAL);  in smb_strndup_from_utf16()
314 			return ERR_PTR(-ENOMEM);  in smb_strndup_from_utf16()
323  * page. Conversion may involve remapping up the six characters that are
324  * only legal in POSIX-like OS (if they are present in the string). Path
328  * smbConvertToUTF16() - convert string from local charset to utf16
336  * page. Conversion may involve remapping up the six characters that are
337  * only legal in POSIX-like OS (if they are present in the string). Path
340  * Return:	char length after conversion
349 	wchar_t wchar_to[6];	/* UTF-16 */  in smbConvertToUTF16()
387 			charlen = cp->char2uni(source + i, srclen - i, &tmp);  in smbConvertToUTF16()
398 			if (strcmp(cp->charset, "utf8"))  in smbConvertToUTF16()
415 				/* 1-3bytes UTF-8 to 2bytes UTF-16 */  in smbConvertToUTF16()
419 				 * 4bytes UTF-8(surrogate pair) to 4bytes UTF-16  in smbConvertToUTF16()
420 				 * 7-8bytes UTF-8(IVS) divided to 2 UTF-16  in smbConvertToUTF16()
428 				/* 5-6bytes UTF-8 to 6bytes UTF-16 */  in smbConvertToUTF16()