summaryrefslogtreecommitdiffstats
path: root/doc/devel/utfconv.txt
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--doc/devel/utfconv.txt291
1 files changed, 291 insertions, 0 deletions
diff --git a/doc/devel/utfconv.txt b/doc/devel/utfconv.txt
new file mode 100644
index 0000000..88dfb1d
--- /dev/null
+++ b/doc/devel/utfconv.txt
@@ -0,0 +1,291 @@
+ Dec 5, 2000
+ Dave Steck
+ Novell, Inc.
+
+ UTF-8 Conversion Functions
+
+
+1. Strings in the LDAP C SDK should be encoded in UTF-8 format.
+ However, most platforms do not provide APIs for converting to
+ this format. If they do, they are platform-specific.
+
+ As a result, most applications (knowingly or not) use local strings
+ with LDAP functions. This works fine for 7-bit ASCII characters,
+ but will fail with 8-bit European characters, Asian characters, etc.
+
+ We propose adding the following platform-independent conversion functions
+ to the OpenLDAP SDK. There are 4 functions for converting between UTF-8
+ and wide characters, and 4 functions for converting between UTF-8 and
+ multibyte characters.
+
+ For multibyte to UTF-8 conversions, charset translation is necessary.
+ While a full charset translator is not practical or appropriate for the
+ LDAP SDK, we can pass the translator function in as an argument.
+ A NULL for this argument will use the ANSI C functions mbtowc, mbstowcs,
+ wctomb, and wcstombs.
+
+2. UTF-8 <--> Wide Character conversions
+
+The following new conversion routines will be added, following the pattern of
+the ANSI C conversion routines (mbtowc, mbstowcs, etc). These routines use
+the wchar_t type. wchar_t is 2 bytes on some systems and 4 bytes on others.
+However the advantage of using wchar_t is that all the standard wide character
+string functions may be used on these strings: wcslen, wcscpy, etc.
+
+ int ldap_x_utf8_to_wc - Convert a single UTF-8 encoded character to a wide character.
+ int ldap_x_utf8s_to_wcs - Convert a UTF-8 string to a wide character string.
+ int ldap_x_wc_to_utf8 - Convert a single wide character to a UTF-8 sequence.
+ int ldap_x_wcs_to_utf8s - Convert a wide character string to a UTF-8 string.
+
+
+2.1 ldap_x_utf8_to_wc - Convert a single UTF-8 encoded character to a wide character.
+
+int ldap_x_utf8_to_wc ( wchar_t *wchar, const char *utf8char )
+
+ wchar (OUT) Points to a wide character code to receive the
+ converted character.
+
+ utf8char (IN) Address of the UTF8 sequence of bytes.
+
+Return Value:
+ If successful, the function returns the length in
+ bytes of the UTF-8 input character.
+
+ If utf8char is NULL or points to an empty string, the
+ function returns 1 and a NULL is written to wchar.
+
+ If utf8char contains an invalid UTF-8 sequence -1 is returned.
+
+
+2.2 ldap_x_utf8s_to_wcs - Convert a UTF-8 string to a wide character string.
+
+int ldap_x_utf8s_to_wcs (wchar_t *wcstr, const char *utf8str, size_t count)
+
+ wcstr (OUT) Points to a wide char buffer to receive the
+ converted wide char string. The output string will be
+ null terminated if there is space for it in the
+ buffer.
+
+ utf8str (IN) Address of the null-terminated UTF-8 string to convert.
+
+ count (IN) The number of UTF-8 characters to convert, or
+ equivalently, the size of the output buffer in wide
+ characters.
+
+Return Value:
+ If successful, the function returns the number of wide
+ characters written to wcstr, excluding the null termination
+ character, if any.
+
+ If wcstr is NULL, the function returns the number of wide
+ characters required to contain the converted string,
+ excluding the null termination character.
+
+ If an invalid UTF-8 sequence is encountered, the
+ function returns -1.
+
+ If the return value equals count, there was not enough space to fit the
+ string and the null terminator in the buffer.
+
+
+2.3 ldap_x_wc_to_utf8 - Convert a single wide character to a UTF-8 sequence.
+
+int ldap_x_wc_to_utf8 ( char *utf8char, wchar_t wchar, count )
+
+ utf8char (OUT) Points to a byte array to receive the converted UTF-8
+ string.
+
+ wchar (IN) The wide character to convert.
+
+ count (IN) The maximum number of bytes to write to the output
+ buffer. Normally set this to LDAP_MAX_UTF8_LEN, which
+ is defined as 3 or 6 depending on the size of wchar_t.
+ A partial character will not be written.
+
+Return Value:
+ If successful, the function returns the length in bytes of
+ the converted UTF-8 output character.
+
+ If wchar is NULL, the function returns 1 and a NULL is
+ written to utf8char.
+
+ If wchar cannot be converted to a UTF-8 character, the
+ function returns -1.
+
+
+2.4 int ldap_x_wcs_to_utf8s - Convert a wide character string to a UTF-8 string.
+
+int ldap_x_wcs_to_utf8s (char *utf8str, const wchar_t *wcstr, size_t count)
+
+ utf8str (OUT) Points to a byte array to receive the converted
+ UTF-8 string. The output string will be null
+ terminated if there is space for it in the
+ buffer.
+
+
+ wcstr (IN) Address of the null-terminated wide char string to convert.
+
+ count (IN) The size of the output buffer in bytes.
+
+Return Value:
+ If successful, the function returns the number of bytes
+ written to utf8str, excluding the null termination
+ character, if any.
+
+ If utf8str is NULL, the function returns the number of
+ bytes required to contain the converted string, excluding
+ the null termination character. The 'count' parameter is ignored.
+
+ If the function encounters a wide character that cannot
+ be mapped to a UTF-8 sequence, the function returns -1.
+
+ If the return value equals count, there was not enough space to fit
+ the string and the null terminator in the buffer.
+
+
+
+3. Multi-byte <--> UTF-8 Conversions
+
+These functions convert the string in a two-step process, from multibyte
+to Wide, then from Wide to UTF8, or vice versa. This conversion requires a
+charset translation routine, which is passed in as an argument.
+
+ ldap_x_mb_to_utf8 - Convert a multi-byte character to a UTF-8 character.
+ ldap_x_mbs_to_utf8s - Convert a multi-byte string to a UTF-8 string.
+ ldap_x_utf8_to_mb - Convert a UTF-8 character to a multi-byte character.
+ ldap_x_utf8s_to_mbs - Convert a UTF-8 string to a multi-byte string.
+
+3.1 ldap_x_mb_to_utf8 - Convert a multi-byte character to a UTF-8 character.
+
+int ldap_x_mb_to_utf8 ( char *utf8char, const char *mbchar, size_t mbsize, int (*f_mbtowc)(wchar_t *wchar, const char *mbchar, size_t count) )
+
+ utf8char (OUT) Points to a byte buffer to receive the converted
+ UTF-8 character. May be NULL. The output is not
+ null-terminated.
+
+ mbchar (IN) Address of a sequence of bytes forming a multibyte character.
+
+ mbsize (IN) The maximum number of bytes of the mbchar argument to
+ check. This should normally be MB_CUR_MAX.
+
+ f_mbtowc (IN) The function to use for converting a multibyte
+ character to a wide character. If NULL, the local
+ ANSI C routine mbtowc is used.
+
+Return Value:
+ If successful, the function returns the length in bytes of
+ the UTF-8 output character.
+
+ If utf8char is NULL, count is ignored and the funtion
+ returns the number of bytes that would be written to the
+ output char.
+
+ If count is zero, 0 is returned and nothing is written to
+ utf8char.
+
+ If mbchar is NULL or points to an empty string, the
+ function returns 1 and a null byte is written to utf8char.
+
+ If mbchar contains an invalid multi-byte character, -1 is returned.
+
+
+3.2 ldap_x_mbs_to_utf8s - Convert a multi-byte string to a UTF-8 string.
+
+int ldap_x_mbs_to_utf8s (char *utf8str, const char *mbstr, size_t count,
+ size_t (*f_mbstowcs)(wchar_t *wcstr, const char *mbstr, size_t count))
+
+utf8str (OUT) Points to a buffer to receive the converted UTF-8 string.
+ May be NULL.
+
+ mbchar (IN) Address of the null-terminated multi-byte input string.
+
+ count (IN) The size of the output buffer in bytes.
+
+ f_mbstowcs (IN) The function to use for converting a multibyte string
+ to a wide character string. If NULL, the local ANSI
+ C routine mbstowcs is used.
+
+Return Value:
+ If successful, the function returns the length in
+ bytes of the UTF-8 output string, excluding the null
+ terminator, if present.
+
+ If utf8str is NULL, count is ignored and the function
+ returns the number of bytes required for the output string,
+ excluding the NULL.
+
+ If count is zero, 0 is returned and nothing is written to utf8str.
+
+ If mbstr is NULL or points to an empty string, the
+ function returns 1 and a null byte is written to utf8str.
+
+ If mbstr contains an invalid multi-byte character, -1 is returned.
+
+ If the returned value is equal to count, the entire null-terminated
+ string would not fit in the output buffer.
+
+
+3.3 ldap_x_utf8_to_mb - Convert a UTF-8 character to a multi-byte character.
+
+int ldap_x_utf8_to_mb ( char *mbchar, const char *utf8char,
+ int (*f_wctomb)(char *mbchar, wchar_t wchar) )
+
+mbchar (OUT) Points to a byte buffer to receive the converted multi-byte
+ character. May be NULL.
+
+ utf8char (IN) Address of the UTF-8 character sequence.
+
+ f_wctomb (IN) The function to use for converting a wide character
+ to a multibyte character. If NULL, the local
+ ANSI C routine wctomb is used.
+
+
+Return Value:
+ If successful, the function returns the length in
+ bytes of the multi-byte output character.
+
+ If utf8char is NULL or points to an empty string, the
+ function returns 1 and a null byte is written to mbchar.
+
+ If utf8char contains an invalid UTF-8 sequence, -1 is returned.
+
+
+3.4 int ldap_x_utf8s_to_mbs - Convert a UTF-8 string to a multi-byte string.
+
+
+int ldap_x_utf8s_to_mbs ( char *mbstr, const char *utf8str, size_t count,
+ size_t (*f_wcstombs)(char *mbstr, const wchar_t *wcstr, size_t count) )
+
+ mbstr (OUT) Points to a byte buffer to receive the converted
+ multi-byte string. May be NULL.
+
+ utf8str (IN) Address of the null-terminated UTF-8 string to convert.
+
+ count (IN) The size of the output buffer in bytes.
+
+ f_wcstombs (IN) The function to use for converting a wide character
+ string to a multibyte string. If NULL, the local
+ ANSI C routine wcstombs is used.
+
+Return Value:
+ If successful, the function returns the number of bytes
+ written to mbstr, excluding the null termination
+ character, if any.
+
+ If mbstr is NULL, count is ignored and the funtion
+ returns the number of bytes required for the output string,
+ excluding the NULL.
+
+ If count is zero, 0 is returned and nothing is written to
+ mbstr.
+
+ If utf8str is NULL or points to an empty string, the
+ function returns 1 and a null byte is written to mbstr.
+
+ If an invalid UTF-8 character is encountered, the
+ function returns -1.
+
+The output string will be null terminated if there is space for it in
+the output buffer.
+
+