diff options
Diffstat (limited to 'doc/libunistring.info')
| -rw-r--r-- | doc/libunistring.info | 1860 |
1 files changed, 1012 insertions, 848 deletions
diff --git a/doc/libunistring.info b/doc/libunistring.info index f6822abb..5f5d417f 100644 --- a/doc/libunistring.info +++ b/doc/libunistring.info @@ -1,4 +1,4 @@ -This is libunistring.info, produced by makeinfo version 6.4 from +This is libunistring.info, produced by makeinfo version 6.7 from libunistring.texi. INFO-DIR-SECTION Software development @@ -34,6 +34,7 @@ GNU libunistring * Using the library:: How to link with the library and use it? * More functionality:: More advanced functionality * The wchar_t mess:: Why ‘wchar_t *’ strings are useless +* The char32_t problem:: Why ‘char32_t *’ strings are problematic * Licenses:: Licenses * Index:: General Index @@ -239,11 +240,11 @@ in the same document. Due to the many encodings for Japanese, even the processing of pure Japanese text was error prone. References: - • The Unicode standard: <http://www.unicode.org/> - • Definition of UTF-8: <http://www.rfc-editor.org/rfc/rfc3629.txt> - • Definition of UTF-16: <http://www.rfc-editor.org/rfc/rfc2781.txt> + • The Unicode standard: <https://www.unicode.org/> + • Definition of UTF-8: <https://www.rfc-editor.org/rfc/rfc3629.txt> + • Definition of UTF-16: <https://www.rfc-editor.org/rfc/rfc2781.txt> • Markus Kuhn’s UTF-8 and Unicode FAQ: - <http://www.cl.cam.ac.uk/~mgk25/unicode.html> + <https://www.cl.cam.ac.uk/~mgk25/unicode.html> File: libunistring.info, Node: Unicode and i18n, Next: Locale encodings, Prev: Unicode, Up: Introduction @@ -415,7 +416,7 @@ encoding; therefore, the majority of users are using multibyte locales. work with multibyte strings. The workarounds can be found in GNU gnulib -<http://www.gnu.org/software/gnulib/>. +<https://www.gnu.org/software/gnulib/>. • gnulib has modules ‘mbchar’, ‘mbiter’, ‘mbuiter’ that represent multibyte characters and allow to iterate across a multibyte string with the same ease as through a unibyte string. @@ -616,22 +617,22 @@ File: libunistring.info, Node: Elementary string conversions, Next: Elementary The following functions perform conversions between the different forms of Unicode strings. - -- Function: uint16_t * u8_to_u16 (const uint8_t *S, size_t N, uint16_t - *RESULTBUF, size_t *LENGTHP) + -- Function: uint16_t * u8_to_u16 (const uint8_t *S, size_t N, + uint16_t *RESULTBUF, size_t *LENGTHP) Converts an UTF-8 string to an UTF-16 string. The RESULTBUF and LENGTHP arguments are as described in chapter *note Conventions::. - -- Function: uint32_t * u8_to_u32 (const uint8_t *S, size_t N, uint32_t - *RESULTBUF, size_t *LENGTHP) + -- Function: uint32_t * u8_to_u32 (const uint8_t *S, size_t N, + uint32_t *RESULTBUF, size_t *LENGTHP) Converts an UTF-8 string to an UTF-32 string. The RESULTBUF and LENGTHP arguments are as described in chapter *note Conventions::. - -- Function: uint8_t * u16_to_u8 (const uint16_t *S, size_t N, uint8_t - *RESULTBUF, size_t *LENGTHP) + -- Function: uint8_t * u16_to_u8 (const uint16_t *S, size_t N, + uint8_t *RESULTBUF, size_t *LENGTHP) Converts an UTF-16 string to an UTF-8 string. The RESULTBUF and LENGTHP arguments are as described in chapter @@ -644,8 +645,8 @@ forms of Unicode strings. The RESULTBUF and LENGTHP arguments are as described in chapter *note Conventions::. - -- Function: uint8_t * u32_to_u8 (const uint32_t *S, size_t N, uint8_t - *RESULTBUF, size_t *LENGTHP) + -- Function: uint8_t * u32_to_u8 (const uint32_t *S, size_t N, + uint8_t *RESULTBUF, size_t *LENGTHP) Converts an UTF-32 string to an UTF-8 string. The RESULTBUF and LENGTHP arguments are as described in chapter @@ -743,9 +744,9 @@ File: libunistring.info, Node: Creating Unicode strings, Next: Copying Unicode The following function stores a Unicode character as a Unicode string in memory. - -- Function: int u8_uctomb (uint8_t *S, ucs4_t UC, int N) - -- Function: int u16_uctomb (uint16_t *S, ucs4_t UC, int N) - -- Function: int u32_uctomb (uint32_t *S, ucs4_t UC, int N) + -- Function: int u8_uctomb (uint8_t *S, ucs4_t UC, ptrdiff_t N) + -- Function: int u16_uctomb (uint16_t *S, ucs4_t UC, ptrdiff_t N) + -- Function: int u32_uctomb (uint32_t *S, ucs4_t UC, ptrdiff_t N) Puts the multibyte character represented by UC in S, returning its length. Returns -1 upon failure, -2 if the number of available units, N, is too small. The latter case cannot occur if N >= @@ -806,8 +807,8 @@ File: libunistring.info, Node: Comparing Unicode strings, Next: Searching for The following function compares two Unicode strings of the same length. - -- Function: int u8_cmp (const uint8_t *S1, const uint8_t *S2, size_t - N) + -- Function: int u8_cmp (const uint8_t *S1, const uint8_t *S2, + size_t N) -- Function: int u16_cmp (const uint16_t *S1, const uint16_t *S2, size_t N) -- Function: int u32_cmp (const uint32_t *S1, const uint32_t *S2, @@ -822,12 +823,12 @@ length. The following function compares two Unicode strings of possibly different lengths. - -- Function: int u8_cmp2 (const uint8_t *S1, size_t N1, const uint8_t - *S2, size_t N2) - -- Function: int u16_cmp2 (const uint16_t *S1, size_t N1, const - uint16_t *S2, size_t N2) - -- Function: int u32_cmp2 (const uint32_t *S1, size_t N1, const - uint32_t *S2, size_t N2) + -- Function: int u8_cmp2 (const uint8_t *S1, size_t N1, + const uint8_t *S2, size_t N2) + -- Function: int u16_cmp2 (const uint16_t *S1, size_t N1, + const uint16_t *S2, size_t N2) + -- Function: int u32_cmp2 (const uint32_t *S1, size_t N1, + const uint32_t *S2, size_t N2) Compares S1 and S2, lexicographically. Returns a negative value if S1 compares smaller than S2, a positive value if S1 compares larger than S2, or 0 if they compare equal. @@ -844,10 +845,10 @@ File: libunistring.info, Node: Searching for a character, Next: Counting chara The following function searches for a given Unicode character. -- Function: uint8_t * u8_chr (const uint8_t *S, size_t N, ucs4_t UC) - -- Function: uint16_t * u16_chr (const uint16_t *S, size_t N, ucs4_t - UC) - -- Function: uint32_t * u32_chr (const uint32_t *S, size_t N, ucs4_t - UC) + -- Function: uint16_t * u16_chr (const uint16_t *S, size_t N, + ucs4_t UC) + -- Function: uint32_t * u32_chr (const uint32_t *S, size_t N, + ucs4_t UC) Searches the string at S for UC. Returns a pointer to the first occurrence of UC in S, or NULL if UC does not occur in S. @@ -978,20 +979,20 @@ File: libunistring.info, Node: Copying a NUL terminated Unicode string, Next: The following functions copy portions of Unicode strings in memory. -- Function: uint8_t * u8_strcpy (uint8_t *DEST, const uint8_t *SRC) - -- Function: uint16_t * u16_strcpy (uint16_t *DEST, const uint16_t - *SRC) - -- Function: uint32_t * u32_strcpy (uint32_t *DEST, const uint32_t - *SRC) + -- Function: uint16_t * u16_strcpy (uint16_t *DEST, + const uint16_t *SRC) + -- Function: uint32_t * u32_strcpy (uint32_t *DEST, + const uint32_t *SRC) Copies SRC to DEST. This function is similar to ‘strcpy’ and ‘wcscpy’, except that it operates on Unicode strings. -- Function: uint8_t * u8_stpcpy (uint8_t *DEST, const uint8_t *SRC) - -- Function: uint16_t * u16_stpcpy (uint16_t *DEST, const uint16_t - *SRC) - -- Function: uint32_t * u32_stpcpy (uint32_t *DEST, const uint32_t - *SRC) + -- Function: uint16_t * u16_stpcpy (uint16_t *DEST, + const uint16_t *SRC) + -- Function: uint32_t * u32_stpcpy (uint32_t *DEST, + const uint32_t *SRC) Copies SRC to DEST, returning the address of the terminating NUL in DEST. @@ -1000,10 +1001,10 @@ File: libunistring.info, Node: Copying a NUL terminated Unicode string, Next: -- Function: uint8_t * u8_strncpy (uint8_t *DEST, const uint8_t *SRC, size_t N) - -- Function: uint16_t * u16_strncpy (uint16_t *DEST, const uint16_t - *SRC, size_t N) - -- Function: uint32_t * u32_strncpy (uint32_t *DEST, const uint32_t - *SRC, size_t N) + -- Function: uint16_t * u16_strncpy (uint16_t *DEST, + const uint16_t *SRC, size_t N) + -- Function: uint32_t * u32_strncpy (uint32_t *DEST, + const uint32_t *SRC, size_t N) Copies no more than N units of SRC to DEST. This function is similar to ‘strncpy’ and ‘wcsncpy’, except that it @@ -1011,10 +1012,10 @@ File: libunistring.info, Node: Copying a NUL terminated Unicode string, Next: -- Function: uint8_t * u8_stpncpy (uint8_t *DEST, const uint8_t *SRC, size_t N) - -- Function: uint16_t * u16_stpncpy (uint16_t *DEST, const uint16_t - *SRC, size_t N) - -- Function: uint32_t * u32_stpncpy (uint32_t *DEST, const uint32_t - *SRC, size_t N) + -- Function: uint16_t * u16_stpncpy (uint16_t *DEST, + const uint16_t *SRC, size_t N) + -- Function: uint32_t * u32_stpncpy (uint32_t *DEST, + const uint32_t *SRC, size_t N) Copies no more than N units of SRC to DEST. Returns a pointer past the last non-NUL unit written into DEST. In other words, if the units written into DEST include a NUL, the return value is the @@ -1024,10 +1025,10 @@ File: libunistring.info, Node: Copying a NUL terminated Unicode string, Next: Unicode strings. -- Function: uint8_t * u8_strcat (uint8_t *DEST, const uint8_t *SRC) - -- Function: uint16_t * u16_strcat (uint16_t *DEST, const uint16_t - *SRC) - -- Function: uint32_t * u32_strcat (uint32_t *DEST, const uint32_t - *SRC) + -- Function: uint16_t * u16_strcat (uint16_t *DEST, + const uint16_t *SRC) + -- Function: uint32_t * u32_strcat (uint32_t *DEST, + const uint32_t *SRC) Appends SRC onto DEST. This function is similar to ‘strcat’ and ‘wcscat’, except that it @@ -1035,10 +1036,10 @@ File: libunistring.info, Node: Copying a NUL terminated Unicode string, Next: -- Function: uint8_t * u8_strncat (uint8_t *DEST, const uint8_t *SRC, size_t N) - -- Function: uint16_t * u16_strncat (uint16_t *DEST, const uint16_t - *SRC, size_t N) - -- Function: uint32_t * u32_strncat (uint32_t *DEST, const uint32_t - *SRC, size_t N) + -- Function: uint16_t * u16_strncat (uint16_t *DEST, + const uint16_t *SRC, size_t N) + -- Function: uint32_t * u32_strncat (uint32_t *DEST, + const uint32_t *SRC, size_t N) Appends no more than N units of SRC onto DEST. This function is similar to ‘strncat’ and ‘wcsncat’, except that it @@ -1131,36 +1132,36 @@ File: libunistring.info, Node: Searching for a character in a NUL terminated Un The following functions search for the first occurrence of some Unicode character in or outside a given set of Unicode characters. - -- Function: size_t u8_strcspn (const uint8_t *STR, const uint8_t - *REJECT) - -- Function: size_t u16_strcspn (const uint16_t *STR, const uint16_t - *REJECT) - -- Function: size_t u32_strcspn (const uint32_t *STR, const uint32_t - *REJECT) + -- Function: size_t u8_strcspn (const uint8_t *STR, + const uint8_t *REJECT) + -- Function: size_t u16_strcspn (const uint16_t *STR, + const uint16_t *REJECT) + -- Function: size_t u32_strcspn (const uint32_t *STR, + const uint32_t *REJECT) Returns the length of the initial segment of STR which consists entirely of Unicode characters not in REJECT. This function is similar to ‘strcspn’ and ‘wcscspn’, except that it operates on Unicode strings. - -- Function: size_t u8_strspn (const uint8_t *STR, const uint8_t - *ACCEPT) - -- Function: size_t u16_strspn (const uint16_t *STR, const uint16_t - *ACCEPT) - -- Function: size_t u32_strspn (const uint32_t *STR, const uint32_t - *ACCEPT) + -- Function: size_t u8_strspn (const uint8_t *STR, + const uint8_t *ACCEPT) + -- Function: size_t u16_strspn (const uint16_t *STR, + const uint16_t *ACCEPT) + -- Function: size_t u32_strspn (const uint32_t *STR, + const uint32_t *ACCEPT) Returns the length of the initial segment of STR which consists entirely of Unicode characters in ACCEPT. This function is similar to ‘strspn’ and ‘wcsspn’, except that it operates on Unicode strings. - -- Function: uint8_t * u8_strpbrk (const uint8_t *STR, const uint8_t - *ACCEPT) - -- Function: uint16_t * u16_strpbrk (const uint16_t *STR, const - uint16_t *ACCEPT) - -- Function: uint32_t * u32_strpbrk (const uint32_t *STR, const - uint32_t *ACCEPT) + -- Function: uint8_t * u8_strpbrk (const uint8_t *STR, + const uint8_t *ACCEPT) + -- Function: uint16_t * u16_strpbrk (const uint16_t *STR, + const uint16_t *ACCEPT) + -- Function: uint32_t * u32_strpbrk (const uint32_t *STR, + const uint32_t *ACCEPT) Finds the first occurrence in STR of any character in ACCEPT. This function is similar to ‘strpbrk’ and ‘wcspbrk’, except that it @@ -1175,31 +1176,31 @@ File: libunistring.info, Node: Searching for a substring, Next: Tokenizing, P The following functions search whether a given Unicode string is a substring of another Unicode string. - -- Function: uint8_t * u8_strstr (const uint8_t *HAYSTACK, const - uint8_t *NEEDLE) - -- Function: uint16_t * u16_strstr (const uint16_t *HAYSTACK, const - uint16_t *NEEDLE) - -- Function: uint32_t * u32_strstr (const uint32_t *HAYSTACK, const - uint32_t *NEEDLE) + -- Function: uint8_t * u8_strstr (const uint8_t *HAYSTACK, + const uint8_t *NEEDLE) + -- Function: uint16_t * u16_strstr (const uint16_t *HAYSTACK, + const uint16_t *NEEDLE) + -- Function: uint32_t * u32_strstr (const uint32_t *HAYSTACK, + const uint32_t *NEEDLE) Finds the first occurrence of NEEDLE in HAYSTACK. This function is similar to ‘strstr’ and ‘wcsstr’, except that it operates on Unicode strings. - -- Function: bool u8_startswith (const uint8_t *STR, const uint8_t - *PREFIX) - -- Function: bool u16_startswith (const uint16_t *STR, const uint16_t - *PREFIX) - -- Function: bool u32_startswith (const uint32_t *STR, const uint32_t - *PREFIX) + -- Function: bool u8_startswith (const uint8_t *STR, + const uint8_t *PREFIX) + -- Function: bool u16_startswith (const uint16_t *STR, + const uint16_t *PREFIX) + -- Function: bool u32_startswith (const uint32_t *STR, + const uint32_t *PREFIX) Tests whether STR starts with PREFIX. - -- Function: bool u8_endswith (const uint8_t *STR, const uint8_t - *SUFFIX) - -- Function: bool u16_endswith (const uint16_t *STR, const uint16_t - *SUFFIX) - -- Function: bool u32_endswith (const uint32_t *STR, const uint32_t - *SUFFIX) + -- Function: bool u8_endswith (const uint8_t *STR, + const uint8_t *SUFFIX) + -- Function: bool u16_endswith (const uint16_t *STR, + const uint16_t *SUFFIX) + -- Function: bool u32_endswith (const uint32_t *STR, + const uint32_t *SUFFIX) Tests whether STR ends with SUFFIX. @@ -1212,10 +1213,10 @@ File: libunistring.info, Node: Tokenizing, Prev: Searching for a substring, U -- Function: uint8_t * u8_strtok (uint8_t *STR, const uint8_t *DELIM, uint8_t **PTR) - -- Function: uint16_t * u16_strtok (uint16_t *STR, const uint16_t - *DELIM, uint16_t **PTR) - -- Function: uint32_t * u32_strtok (uint32_t *STR, const uint32_t - *DELIM, uint32_t **PTR) + -- Function: uint16_t * u16_strtok (uint16_t *STR, + const uint16_t *DELIM, uint16_t **PTR) + -- Function: uint32_t * u32_strtok (uint32_t *STR, + const uint32_t *DELIM, uint32_t **PTR) Divides STR into tokens separated by characters in DELIM. This function is similar to ‘strtok_r’ and ‘wcstok’, except that it @@ -1237,7 +1238,7 @@ encodings. -- Function: const char * locale_charset () Determines the current locale’s character encoding, and canonicalizes it into one of the canonical names listed in - ‘config.charset’. If the canonical name cannot be determined, the + ‘localcharset.h’. If the canonical name cannot be determined, the result is a non-canonical name. The result must not be freed; it is statically allocated. @@ -1271,14 +1272,17 @@ be parametrized through the following enumeration type: encoding and Unicode strings. -- Function: uint8_t * u8_conv_from_encoding (const char *FROMCODE, - enum iconv_ilseq_handler HANDLER, const char *SRC, size_t - SRCLEN, size_t *OFFSETS, uint8_t *RESULTBUF, size_t *LENGTHP) + enum iconv_ilseq_handler HANDLER, const char *SRC, + size_t SRCLEN, size_t *OFFSETS, uint8_t *RESULTBUF, + size_t *LENGTHP) -- Function: uint16_t * u16_conv_from_encoding (const char *FROMCODE, - enum iconv_ilseq_handler HANDLER, const char *SRC, size_t - SRCLEN, size_t *OFFSETS, uint16_t *RESULTBUF, size_t *LENGTHP) + enum iconv_ilseq_handler HANDLER, const char *SRC, + size_t SRCLEN, size_t *OFFSETS, uint16_t *RESULTBUF, + size_t *LENGTHP) -- Function: uint32_t * u32_conv_from_encoding (const char *FROMCODE, - enum iconv_ilseq_handler HANDLER, const char *SRC, size_t - SRCLEN, size_t *OFFSETS, uint32_t *RESULTBUF, size_t *LENGTHP) + enum iconv_ilseq_handler HANDLER, const char *SRC, + size_t SRCLEN, size_t *OFFSETS, uint32_t *RESULTBUF, + size_t *LENGTHP) Converts an entire string, possibly including NUL bytes, from one encoding to UTF-8 encoding. @@ -1307,15 +1311,18 @@ encoding and Unicode strings. In case of error: NULL is returned and ‘errno’ is set. Particular ‘errno’ values: ‘EINVAL’, ‘EILSEQ’, ‘ENOMEM’. - -- Function: char * u8_conv_to_encoding (const char *TOCODE, enum - iconv_ilseq_handler HANDLER, const uint8_t *SRC, size_t - SRCLEN, size_t *OFFSETS, char *RESULTBUF, size_t *LENGTHP) - -- Function: char * u16_conv_to_encoding (const char *TOCODE, enum - iconv_ilseq_handler HANDLER, const uint16_t *SRC, size_t - SRCLEN, size_t *OFFSETS, char *RESULTBUF, size_t *LENGTHP) - -- Function: char * u32_conv_to_encoding (const char *TOCODE, enum - iconv_ilseq_handler HANDLER, const uint32_t *SRC, size_t - SRCLEN, size_t *OFFSETS, char *RESULTBUF, size_t *LENGTHP) + -- Function: char * u8_conv_to_encoding (const char *TOCODE, + enum iconv_ilseq_handler HANDLER, const uint8_t *SRC, + size_t SRCLEN, size_t *OFFSETS, char *RESULTBUF, + size_t *LENGTHP) + -- Function: char * u16_conv_to_encoding (const char *TOCODE, + enum iconv_ilseq_handler HANDLER, const uint16_t *SRC, + size_t SRCLEN, size_t *OFFSETS, char *RESULTBUF, + size_t *LENGTHP) + -- Function: char * u32_conv_to_encoding (const char *TOCODE, + enum iconv_ilseq_handler HANDLER, const uint32_t *SRC, + size_t SRCLEN, size_t *OFFSETS, char *RESULTBUF, + size_t *LENGTHP) Converts an entire Unicode string, possibly including NUL units, from UTF-8 encoding to a given encoding. @@ -1441,19 +1448,19 @@ result that is a ‘char *’ string in locale encoding. -- Function: int ulc_sprintf (char *BUF, const char *FORMAT, ...) - -- Function: int ulc_snprintf (char *BUF, size_t size, const char - *FORMAT, ...) + -- Function: int ulc_snprintf (char *BUF, size_t size, + const char *FORMAT, ...) -- Function: int ulc_asprintf (char **RESULTP, const char *FORMAT, ...) -- Function: char * ulc_asnprintf (char *RESULTBUF, size_t *LENGTHP, const char *FORMAT, ...) - -- Function: int ulc_vsprintf (char *BUF, const char *FORMAT, va_list - AP) + -- Function: int ulc_vsprintf (char *BUF, const char *FORMAT, + va_list AP) - -- Function: int ulc_vsnprintf (char *BUF, size_t size, const char - *FORMAT, va_list AP) + -- Function: int ulc_vsnprintf (char *BUF, size_t size, + const char *FORMAT, va_list AP) -- Function: int ulc_vasprintf (char **RESULTP, const char *FORMAT, va_list AP) @@ -1465,118 +1472,118 @@ result that is a ‘char *’ string in locale encoding. result in UTF-8 format. -- Function: int u8_sprintf (uint8_t *BUF, const char *FORMAT, ...) - -- Function: int u8_snprintf (uint8_t *BUF, size_t SIZE, const char - *FORMAT, ...) + -- Function: int u8_snprintf (uint8_t *BUF, size_t SIZE, + const char *FORMAT, ...) -- Function: int u8_asprintf (uint8_t **RESULTP, const char *FORMAT, ...) - -- Function: uint8_t * u8_asnprintf (uint8_t *RESULTBUF, size_t - *LENGTHP, const char *FORMAT, ...) - -- Function: int u8_vsprintf (uint8_t *BUF, const char *FORMAT, va_list - ap) - -- Function: int u8_vsnprintf (uint8_t *BUF, size_t SIZE, const char - *FORMAT, va_list AP) + -- Function: uint8_t * u8_asnprintf (uint8_t *RESULTBUF, + size_t *LENGTHP, const char *FORMAT, ...) + -- Function: int u8_vsprintf (uint8_t *BUF, const char *FORMAT, + va_list ap) + -- Function: int u8_vsnprintf (uint8_t *BUF, size_t SIZE, + const char *FORMAT, va_list AP) -- Function: int u8_vasprintf (uint8_t **RESULTP, const char *FORMAT, va_list AP) - -- Function: uint8_t * u8_vasnprintf (uint8_t *resultbuf, size_t - *LENGTHP, const char *FORMAT, va_list AP) + -- Function: uint8_t * u8_vasnprintf (uint8_t *resultbuf, + size_t *LENGTHP, const char *FORMAT, va_list AP) The following functions take an UTF-8 format string and return a result in UTF-8 format. -- Function: int u8_u8_sprintf (uint8_t *BUF, const uint8_t *FORMAT, ...) - -- Function: int u8_u8_snprintf (uint8_t *BUF, size_t SIZE, const - uint8_t *FORMAT, ...) - -- Function: int u8_u8_asprintf (uint8_t **RESULTP, const uint8_t - *FORMAT, ...) - -- Function: uint8_t * u8_u8_asnprintf (uint8_t *resultbuf, size_t - *LENGTHP, const uint8_t *FORMAT, ...) + -- Function: int u8_u8_snprintf (uint8_t *BUF, size_t SIZE, + const uint8_t *FORMAT, ...) + -- Function: int u8_u8_asprintf (uint8_t **RESULTP, + const uint8_t *FORMAT, ...) + -- Function: uint8_t * u8_u8_asnprintf (uint8_t *resultbuf, + size_t *LENGTHP, const uint8_t *FORMAT, ...) -- Function: int u8_u8_vsprintf (uint8_t *BUF, const uint8_t *FORMAT, va_list AP) - -- Function: int u8_u8_vsnprintf (uint8_t *BUF, size_t SIZE, const - uint8_t *FORMAT, va_list AP) - -- Function: int u8_u8_vasprintf (uint8_t **RESULTP, const uint8_t - *FORMAT, va_list AP) - -- Function: uint8_t * u8_u8_vasnprintf (uint8_t *resultbuf, size_t - *LENGTHP, const uint8_t *FORMAT, va_list AP) + -- Function: int u8_u8_vsnprintf (uint8_t *BUF, size_t SIZE, + const uint8_t *FORMAT, va_list AP) + -- Function: int u8_u8_vasprintf (uint8_t **RESULTP, + const uint8_t *FORMAT, va_list AP) + -- Function: uint8_t * u8_u8_vasnprintf (uint8_t *resultbuf, + size_t *LENGTHP, const uint8_t *FORMAT, va_list AP) The following functions take an ASCII format string and return a result in UTF-16 format. -- Function: int u16_sprintf (uint16_t *BUF, const char *FORMAT, ...) - -- Function: int u16_snprintf (uint16_t *BUF, size_t SIZE, const char - *FORMAT, ...) + -- Function: int u16_snprintf (uint16_t *BUF, size_t SIZE, + const char *FORMAT, ...) -- Function: int u16_asprintf (uint16_t **RESULTP, const char *FORMAT, ...) - -- Function: uint16_t * u16_asnprintf (uint16_t *RESULTBUF, size_t - *LENGTHP, const char *FORMAT, ...) + -- Function: uint16_t * u16_asnprintf (uint16_t *RESULTBUF, + size_t *LENGTHP, const char *FORMAT, ...) -- Function: int u16_vsprintf (uint16_t *BUF, const char *FORMAT, va_list ap) - -- Function: int u16_vsnprintf (uint16_t *BUF, size_t SIZE, const char - *FORMAT, va_list AP) + -- Function: int u16_vsnprintf (uint16_t *BUF, size_t SIZE, + const char *FORMAT, va_list AP) -- Function: int u16_vasprintf (uint16_t **RESULTP, const char *FORMAT, va_list AP) - -- Function: uint16_t * u16_vasnprintf (uint16_t *resultbuf, size_t - *LENGTHP, const char *FORMAT, va_list AP) + -- Function: uint16_t * u16_vasnprintf (uint16_t *resultbuf, + size_t *LENGTHP, const char *FORMAT, va_list AP) The following functions take an UTF-16 format string and return a result in UTF-16 format. - -- Function: int u16_u16_sprintf (uint16_t *BUF, const uint16_t - *FORMAT, ...) - -- Function: int u16_u16_snprintf (uint16_t *BUF, size_t SIZE, const - uint16_t *FORMAT, ...) - -- Function: int u16_u16_asprintf (uint16_t **RESULTP, const uint16_t - *FORMAT, ...) - -- Function: uint16_t * u16_u16_asnprintf (uint16_t *resultbuf, size_t - *LENGTHP, const uint16_t *FORMAT, ...) - -- Function: int u16_u16_vsprintf (uint16_t *BUF, const uint16_t - *FORMAT, va_list AP) - -- Function: int u16_u16_vsnprintf (uint16_t *BUF, size_t SIZE, const - uint16_t *FORMAT, va_list AP) - -- Function: int u16_u16_vasprintf (uint16_t **RESULTP, const uint16_t - *FORMAT, va_list AP) - -- Function: uint16_t * u16_u16_vasnprintf (uint16_t *resultbuf, size_t - *LENGTHP, const uint16_t *FORMAT, va_list AP) + -- Function: int u16_u16_sprintf (uint16_t *BUF, + const uint16_t *FORMAT, ...) + -- Function: int u16_u16_snprintf (uint16_t *BUF, size_t SIZE, + const uint16_t *FORMAT, ...) + -- Function: int u16_u16_asprintf (uint16_t **RESULTP, + const uint16_t *FORMAT, ...) + -- Function: uint16_t * u16_u16_asnprintf (uint16_t *resultbuf, + size_t *LENGTHP, const uint16_t *FORMAT, ...) + -- Function: int u16_u16_vsprintf (uint16_t *BUF, + const uint16_t *FORMAT, va_list AP) + -- Function: int u16_u16_vsnprintf (uint16_t *BUF, size_t SIZE, + const uint16_t *FORMAT, va_list AP) + -- Function: int u16_u16_vasprintf (uint16_t **RESULTP, + const uint16_t *FORMAT, va_list AP) + -- Function: uint16_t * u16_u16_vasnprintf (uint16_t *resultbuf, + size_t *LENGTHP, const uint16_t *FORMAT, va_list AP) The following functions take an ASCII format string and return a result in UTF-32 format. -- Function: int u32_sprintf (uint32_t *BUF, const char *FORMAT, ...) - -- Function: int u32_snprintf (uint32_t *BUF, size_t SIZE, const char - *FORMAT, ...) + -- Function: int u32_snprintf (uint32_t *BUF, size_t SIZE, + const char *FORMAT, ...) -- Function: int u32_asprintf (uint32_t **RESULTP, const char *FORMAT, ...) - -- Function: uint32_t * u32_asnprintf (uint32_t *RESULTBUF, size_t - *LENGTHP, const char *FORMAT, ...) + -- Function: uint32_t * u32_asnprintf (uint32_t *RESULTBUF, + size_t *LENGTHP, const char *FORMAT, ...) -- Function: int u32_vsprintf (uint32_t *BUF, const char *FORMAT, va_list ap) - -- Function: int u32_vsnprintf (uint32_t *BUF, size_t SIZE, const char - *FORMAT, va_list AP) + -- Function: int u32_vsnprintf (uint32_t *BUF, size_t SIZE, + const char *FORMAT, va_list AP) -- Function: int u32_vasprintf (uint32_t **RESULTP, const char *FORMAT, va_list AP) - -- Function: uint32_t * u32_vasnprintf (uint32_t *resultbuf, size_t - *LENGTHP, const char *FORMAT, va_list AP) + -- Function: uint32_t * u32_vasnprintf (uint32_t *resultbuf, + size_t *LENGTHP, const char *FORMAT, va_list AP) The following functions take an UTF-32 format string and return a result in UTF-32 format. - -- Function: int u32_u32_sprintf (uint32_t *BUF, const uint32_t - *FORMAT, ...) - -- Function: int u32_u32_snprintf (uint32_t *BUF, size_t SIZE, const - uint32_t *FORMAT, ...) - -- Function: int u32_u32_asprintf (uint32_t **RESULTP, const uint32_t - *FORMAT, ...) - -- Function: uint32_t * u32_u32_asnprintf (uint32_t *resultbuf, size_t - *LENGTHP, const uint32_t *FORMAT, ...) - -- Function: int u32_u32_vsprintf (uint32_t *BUF, const uint32_t - *FORMAT, va_list AP) - -- Function: int u32_u32_vsnprintf (uint32_t *BUF, size_t SIZE, const - uint32_t *FORMAT, va_list AP) - -- Function: int u32_u32_vasprintf (uint32_t **RESULTP, const uint32_t - *FORMAT, va_list AP) - -- Function: uint32_t * u32_u32_vasnprintf (uint32_t *resultbuf, size_t - *LENGTHP, const uint32_t *FORMAT, va_list AP) + -- Function: int u32_u32_sprintf (uint32_t *BUF, + const uint32_t *FORMAT, ...) + -- Function: int u32_u32_snprintf (uint32_t *BUF, size_t SIZE, + const uint32_t *FORMAT, ...) + -- Function: int u32_u32_asprintf (uint32_t **RESULTP, + const uint32_t *FORMAT, ...) + -- Function: uint32_t * u32_u32_asnprintf (uint32_t *resultbuf, + size_t *LENGTHP, const uint32_t *FORMAT, ...) + -- Function: int u32_u32_vsprintf (uint32_t *BUF, + const uint32_t *FORMAT, va_list AP) + -- Function: int u32_u32_vsnprintf (uint32_t *BUF, size_t SIZE, + const uint32_t *FORMAT, va_list AP) + -- Function: int u32_u32_vasprintf (uint32_t **RESULTP, + const uint32_t *FORMAT, va_list AP) + -- Function: uint32_t * u32_u32_vasnprintf (uint32_t *resultbuf, + size_t *LENGTHP, const uint32_t *FORMAT, va_list AP) The following functions take an ASCII format string and produce output in locale encoding to a ‘FILE’ stream. @@ -1853,21 +1860,21 @@ macros are aliases, for use when readable code is preferred. algebra, except that there is no ‘not’ operation. -- Function: uc_general_category_t uc_general_category_or - (uc_general_category_t CATEGORY1, uc_general_category_t - CATEGORY2) + (uc_general_category_t CATEGORY1, + uc_general_category_t CATEGORY2) Returns the union of two general categories. This corresponds to the unions of the two sets of characters. -- Function: uc_general_category_t uc_general_category_and - (uc_general_category_t CATEGORY1, uc_general_category_t - CATEGORY2) + (uc_general_category_t CATEGORY1, + uc_general_category_t CATEGORY2) Returns the intersection of two general categories as bit masks. This _does not_ correspond to the intersection of the two sets of characters. -- Function: uc_general_category_t uc_general_category_and_not - (uc_general_category_t CATEGORY1, uc_general_category_t - CATEGORY2) + (uc_general_category_t CATEGORY1, + uc_general_category_t CATEGORY2) Returns the intersection of a general category with the complement of a second general category, as bit masks. This _does not_ correspond to the intersection with complement, when viewing the @@ -1887,8 +1894,8 @@ algebra, except that there is no ‘not’ operation. general category corresponds to a bit mask that does not have a name. - -- Function: uc_general_category_t uc_general_category_byname (const - char *CATEGORY_NAME) + -- Function: uc_general_category_t uc_general_category_byname + (const char *CATEGORY_NAME) Returns the general category given by name, e.g. ‘"Lu"’, or by long name, e.g. ‘"Uppercase Letter"’. This lookup ignores spaces, underscores, or hyphens as word separators and is @@ -1959,8 +1966,8 @@ Additional general categories may be added in the future. The following function views general categories as sets of Unicode characters. - -- Function: bool uc_is_general_category_withtable (ucs4_t UC, uint32_t - BITMASK) + -- Function: bool uc_is_general_category_withtable (ucs4_t UC, + uint32_t BITMASK) Tests whether a Unicode character belongs to a given category. The BITMASK argument can be a predefined general category bitmask or the combination of several predefined general category bitmasks. @@ -1987,7 +1994,7 @@ to the base character. The canonical combining class of a character is a number in the range 0..255. The possible values are described in the Unicode Character -Database <http://www.unicode.org/Public/UNIDATA/UCD.html>. The list +Database <https://www.unicode.org/Public/UNIDATA/UCD.html>. The list here is not definitive; more values can be added in future versions. -- Constant: int UC_CCC_NR @@ -2091,7 +2098,7 @@ it. Before Unicode 4.0, this concept was known as _bidirectional category_. The bidi class guides the bidirectional algorithm -(<http://www.unicode.org/reports/tr9/>). The possible values are the +(<https://www.unicode.org/reports/tr9/>). The possible values are the following. -- Constant: int UC_BIDI_L @@ -2151,6 +2158,18 @@ following. -- Constant: int UC_BIDI_ON The bidi class for “Other Neutral” characters. + -- Constant: int UC_BIDI_LRI + The bidi class for “Left-to-Right Isolate” characters. + + -- Constant: int UC_BIDI_RLI + The bidi class for “Right-to-Left Isolate” characters. + + -- Constant: int UC_BIDI_FSI + The bidi class for “First Strong Isolate” characters. + + -- Constant: int UC_BIDI_PDI + The bidi class for “Pop Directional Isolate” characters. + The following functions implement the association between a bidirectional category and its name. @@ -2396,6 +2415,53 @@ two contexts of right-joining characters. -- Constant: int UC_JOINING_GROUP_YUDH_HE -- Constant: int UC_JOINING_GROUP_ZAIN -- Constant: int UC_JOINING_GROUP_ZHAIN + -- Constant: int UC_JOINING_GROUP_ROHINGYA_YEH + -- Constant: int UC_JOINING_GROUP_STRAIGHT_WAW + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_ALEPH + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_BETH + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_GIMEL + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_DALETH + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_WAW + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_ZAYIN + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_HETH + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_TETH + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_YODH + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_KAPH + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_LAMEDH + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_DHAMEDH + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_THAMEDH + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_MEM + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_NUN + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_SAMEKH + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_AYIN + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_PE + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_SADHE + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_QOPH + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_RESH + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_TAW + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_ONE + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_FIVE + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_TEN + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_TWENTY + -- Constant: int UC_JOINING_GROUP_MANICHAEAN_HUNDRED + -- Constant: int UC_JOINING_GROUP_AFRICAN_FEH + -- Constant: int UC_JOINING_GROUP_AFRICAN_QAF + -- Constant: int UC_JOINING_GROUP_AFRICAN_NOON + -- Constant: int UC_JOINING_GROUP_MALAYALAM_NGA + -- Constant: int UC_JOINING_GROUP_MALAYALAM_JA + -- Constant: int UC_JOINING_GROUP_MALAYALAM_NYA + -- Constant: int UC_JOINING_GROUP_MALAYALAM_TTA + -- Constant: int UC_JOINING_GROUP_MALAYALAM_NNA + -- Constant: int UC_JOINING_GROUP_MALAYALAM_NNNA + -- Constant: int UC_JOINING_GROUP_MALAYALAM_BHA + -- Constant: int UC_JOINING_GROUP_MALAYALAM_RA + -- Constant: int UC_JOINING_GROUP_MALAYALAM_LLA + -- Constant: int UC_JOINING_GROUP_MALAYALAM_LLLA + -- Constant: int UC_JOINING_GROUP_MALAYALAM_SSA + -- Constant: int UC_JOINING_GROUP_HANIFI_ROHINGYA_PA + -- Constant: int UC_JOINING_GROUP_HANIFI_ROHINGYA_KINNA_YA + -- Constant: int UC_JOINING_GROUP_THIN_YEH + -- Constant: int UC_JOINING_GROUP_VERTICAL_TAIL The following functions implement the association between a joining group and its name. @@ -2403,8 +2469,8 @@ group and its name. -- Function: const char * uc_joining_group_name (int JOINING_GROUP) Returns the name of a joining group. - -- Function: int uc_joining_group_byname (const char - *JOINING_GROUP_NAME) + -- Function: int uc_joining_group_byname + (const char *JOINING_GROUP_NAME) Returns the joining group given by name, e.g. ‘"Teh_Marbuta"’. This lookup ignores spaces, underscores, or hyphens as word separators and is case-insignificant. @@ -2534,6 +2600,15 @@ File: libunistring.info, Node: Properties as objects, Next: Properties as func -- Constant: uc_property_t UC_PROPERTY_IDS_BINARY_OPERATOR -- Constant: uc_property_t UC_PROPERTY_IDS_TRINARY_OPERATOR + The following properties deal with pictographic symbols. + + -- Constant: uc_property_t UC_PROPERTY_EMOJI + -- Constant: uc_property_t UC_PROPERTY_EMOJI_PRESENTATION + -- Constant: uc_property_t UC_PROPERTY_EMOJI_MODIFIER + -- Constant: uc_property_t UC_PROPERTY_EMOJI_MODIFIER_BASE + -- Constant: uc_property_t UC_PROPERTY_EMOJI_COMPONENT + -- Constant: uc_property_t UC_PROPERTY_EXTENDED_PICTOGRAPHIC + Other miscellaneous properties are: -- Constant: uc_property_t UC_PROPERTY_ZERO_WIDTH @@ -2561,11 +2636,12 @@ File: libunistring.info, Node: Properties as objects, Next: Properties as func -- Constant: uc_property_t UC_PROPERTY_DIACRITIC -- Constant: uc_property_t UC_PROPERTY_EXTENDER -- Constant: uc_property_t UC_PROPERTY_IGNORABLE_CONTROL + -- Constant: uc_property_t UC_PROPERTY_REGIONAL_INDICATOR The following function looks up a property by its name. - -- Function: uc_property_t uc_property_byname (const char - *PROPERTY_NAME) + -- Function: uc_property_t uc_property_byname + (const char *PROPERTY_NAME) Returns the property given by name, e.g. ‘"White space"’. If a property with the given name exists, the result will satisfy the ‘uc_property_is_valid’ predicate. Otherwise the result will not @@ -2601,8 +2677,8 @@ File: libunistring.info, Node: Properties as functions, Prev: Properties as ob -- Function: bool uc_is_property_alphabetic (ucs4_t UC) -- Function: bool uc_is_property_other_alphabetic (ucs4_t UC) -- Function: bool uc_is_property_not_a_character (ucs4_t UC) - -- Function: bool uc_is_property_default_ignorable_code_point (ucs4_t - UC) + -- Function: bool uc_is_property_default_ignorable_code_point + (ucs4_t UC) -- Function: bool uc_is_property_other_default_ignorable_code_point (ucs4_t UC) -- Function: bool uc_is_property_deprecated (ucs4_t UC) @@ -2679,6 +2755,15 @@ File: libunistring.info, Node: Properties as functions, Prev: Properties as ob -- Function: bool uc_is_property_ids_binary_operator (ucs4_t UC) -- Function: bool uc_is_property_ids_trinary_operator (ucs4_t UC) + The following properties deal with pictographic symbols. + + -- Function: bool uc_is_property_emoji (ucs4_t UC) + -- Function: bool uc_is_property_emoji_presentation (ucs4_t UC) + -- Function: bool uc_is_property_emoji_modifier (ucs4_t UC) + -- Function: bool uc_is_property_emoji_modifier_base (ucs4_t UC) + -- Function: bool uc_is_property_emoji_component (ucs4_t UC) + -- Function: bool uc_is_property_extended_pictographic (ucs4_t UC) + Other miscellaneous properties are: -- Function: bool uc_is_property_zero_width (ucs4_t UC) @@ -2706,6 +2791,7 @@ File: libunistring.info, Node: Properties as functions, Prev: Properties as ob -- Function: bool uc_is_property_diacritic (ucs4_t UC) -- Function: bool uc_is_property_extender (ucs4_t UC) -- Function: bool uc_is_property_ignorable_control (ucs4_t UC) + -- Function: bool uc_is_property_regional_indicator (ucs4_t UC) File: libunistring.info, Node: Scripts, Next: Blocks, Prev: Properties, Up: unictype.h @@ -2730,8 +2816,8 @@ File: libunistring.info, Node: Scripts, Next: Blocks, Prev: Properties, Up: Returns the script of a Unicode character. Returns NULL if UC does not belong to any script. - -- Function: const uc_script_t * uc_script_byname (const char - *SCRIPT_NAME) + -- Function: const uc_script_t * uc_script_byname + (const char *SCRIPT_NAME) Returns the script given by its name, e.g. ‘"HAN"’. Returns NULL if a script with the given name does not exist. @@ -2742,8 +2828,8 @@ File: libunistring.info, Node: Scripts, Next: Blocks, Prev: Properties, Up: The following gives a global picture of all scripts. - -- Function: void uc_all_scripts (const uc_script_t **SCRIPTS, size_t - *COUNT) + -- Function: void uc_all_scripts (const uc_script_t **SCRIPTS, + size_t *COUNT) Get the list of all scripts. Stores a pointer to an array of all scripts in ‘*SCRIPTS’ and the length of this array in ‘*COUNT’. @@ -2783,8 +2869,8 @@ interval of Unicode code points. The following gives a global picture of all block. - -- Function: void uc_all_blocks (const uc_block_t **BLOCKS, size_t - *COUNT) + -- Function: void uc_all_blocks (const uc_block_t **BLOCKS, + size_t *COUNT) Get the list of all blocks. Stores a pointer to an array of all blocks in ‘*BLOCKS’ and the length of this array in ‘*COUNT’. @@ -2929,12 +3015,12 @@ identifies the encoding (e.g. ‘"ISO-8859-2"’ for Polish). UC. Returns -1 if UC is a control character that has an influence on the column position when output. - -- Function: int u8_width (const uint8_t *S, size_t N, const char - *ENCODING) - -- Function: int u16_width (const uint16_t *S, size_t N, const char - *ENCODING) - -- Function: int u32_width (const uint32_t *S, size_t N, const char - *ENCODING) + -- Function: int u8_width (const uint8_t *S, size_t N, + const char *ENCODING) + -- Function: int u16_width (const uint16_t *S, size_t N, + const char *ENCODING) + -- Function: int u32_width (const uint32_t *S, size_t N, + const char *ENCODING) Determines and returns the number of column positions required for first N units (or fewer if S ends before this) in S. This function ignores control characters in the string. @@ -2986,12 +3072,12 @@ File: libunistring.info, Node: Grapheme cluster breaks in a string, Next: Grap The following functions find a single boundary between grapheme clusters in a string. - -- Function: void u8_grapheme_next (const uint8_t *S, const uint8_t - *END) - -- Function: void u16_grapheme_next (const uint16_t *S, const uint16_t - *END) - -- Function: void u32_grapheme_next (const uint32_t *S, const uint32_t - *END) + -- Function: void u8_grapheme_next (const uint8_t *S, + const uint8_t *END) + -- Function: void u16_grapheme_next (const uint16_t *S, + const uint16_t *END) + -- Function: void u32_grapheme_next (const uint32_t *S, + const uint32_t *END) Returns the start of the next grapheme cluster following S, or END if no grapheme cluster break is encountered before it. Returns NULL if and only if ‘S == END’. @@ -3000,12 +3086,12 @@ clusters in a string. outside of the range between S and END is needed to determine the boundary. Use ‘_grapheme_breaks’ functions for such cases. - -- Function: void u8_grapheme_prev (const uint8_t *S, const uint8_t - *START) - -- Function: void u16_grapheme_prev (const uint16_t *S, const uint16_t - *START) - -- Function: void u32_grapheme_prev (const uint32_t *S, const uint32_t - *START) + -- Function: void u8_grapheme_prev (const uint8_t *S, + const uint8_t *START) + -- Function: void u16_grapheme_prev (const uint16_t *S, + const uint16_t *START) + -- Function: void u32_grapheme_prev (const uint32_t *S, + const uint32_t *START) Returns the start of the grapheme cluster preceding S, or START if no grapheme cluster break is encountered before it. Returns NULL if and only if ‘S == START’. @@ -3014,19 +3100,22 @@ clusters in a string. outside of the range between START and S is needed to determine the boundary. Use ‘_grapheme_breaks’ functions for such cases. + Note also that these functions work only on well-formed Unicode + strings. + The following functions determine all of the grapheme cluster boundaries in a string. - -- Function: void u8_grapheme_breaks (const uint8_t *S, size_t N, char - *P) + -- Function: void u8_grapheme_breaks (const uint8_t *S, size_t N, + char *P) -- Function: void u16_grapheme_breaks (const uint16_t *S, size_t N, char *P) -- Function: void u32_grapheme_breaks (const uint32_t *S, size_t N, char *P) - -- Function: void ulc_grapheme_breaks (const char *S, size_t N, char - *P) - -- Function: void uc_grapheme_breaks (const ucs_t *S, size_t N, char - *P) + -- Function: void ulc_grapheme_breaks (const char *S, size_t N, + char *P) + -- Function: void uc_grapheme_breaks (const ucs_t *S, size_t N, + char *P) Determines the grapheme cluster break points in S, an array of N units, and stores the result at ‘P[0..NX-1]’. ‘P[i] = 1’ @@ -3055,7 +3144,7 @@ File: libunistring.info, Node: Grapheme cluster break property, Prev: Grapheme This is a more low-level API. The grapheme cluster break property is a property defined in Unicode Standard Annex #29, section “Grapheme Cluster Boundaries”, see -<http://www.unicode.org/reports/tr29/#Grapheme_Cluster_Boundaries>. It +<https://www.unicode.org/reports/tr29/#Grapheme_Cluster_Boundaries>. It is used for determining the grapheme cluster breaks in a string. The following are the possible values of the grapheme cluster break @@ -3155,7 +3244,7 @@ File: libunistring.info, Node: Word break property, Prev: Word breaks in a str This is a more low-level API. The word break property is a property defined in Unicode Standard Annex #29, section “Word Boundaries”, see -<http://www.unicode.org/reports/tr29/#Word_Boundaries>. It is used for +<https://www.unicode.org/reports/tr29/#Word_Boundaries>. It is used for determining the word breaks in a string. The following are the possible values of the word break property. @@ -3211,6 +3300,10 @@ meanings: -- Constant: int UC_BREAK_MANDATORY This value indicates that ‘S[I]’ is a line break character. + -- Constant: int UC_BREAK_CR_BEFORE_LF + This value is a variant of ‘UC_BREAK_MANDATORY’. It indicates that + ‘S[I]’ is a CR character and that ‘S[I+1]’ is a LF character. + -- Constant: int UC_BREAK_POSSIBLE This value indicates that a line break may be inserted between ‘S[I-1]’ and ‘S[I]’. @@ -3242,25 +3335,25 @@ are possible. const char *ENCODING, char *P) Determines the line break points in S, and stores the result at ‘P[0..N-1]’. Every ‘P[I]’ is assigned one of the values - ‘UC_BREAK_MANDATORY’, ‘UC_BREAK_POSSIBLE’, ‘UC_BREAK_HYPHENATION’, - ‘UC_BREAK_PROHIBITED’. + ‘UC_BREAK_MANDATORY’, ‘UC_BREAK_CR_BEFORE_LF’, ‘UC_BREAK_POSSIBLE’, + ‘UC_BREAK_HYPHENATION’, ‘UC_BREAK_PROHIBITED’. The following functions determine where line breaks should be inserted so that each line fits in a given width, when output to a device that uses non-proportional fonts. - -- Function: int u8_width_linebreaks (const uint8_t *S, size_t N, int - WIDTH, int START_COLUMN, int AT_END_COLUMNS, const char - *OVERRIDE, const char *ENCODING, char *P) - -- Function: int u16_width_linebreaks (const uint16_t *S, size_t N, int - WIDTH, int START_COLUMN, int AT_END_COLUMNS, const char - *OVERRIDE, const char *ENCODING, char *P) - -- Function: int u32_width_linebreaks (const uint32_t *S, size_t N, int - WIDTH, int START_COLUMN, int AT_END_COLUMNS, const char - *OVERRIDE, const char *ENCODING, char *P) - -- Function: int ulc_width_linebreaks (const char *S, size_t N, int - WIDTH, int START_COLUMN, int AT_END_COLUMNS, const char - *OVERRIDE, const char *ENCODING, char *P) + -- Function: int u8_width_linebreaks (const uint8_t *S, size_t N, + int WIDTH, int START_COLUMN, int AT_END_COLUMNS, + const char *OVERRIDE, const char *ENCODING, char *P) + -- Function: int u16_width_linebreaks (const uint16_t *S, size_t N, + int WIDTH, int START_COLUMN, int AT_END_COLUMNS, + const char *OVERRIDE, const char *ENCODING, char *P) + -- Function: int u32_width_linebreaks (const uint32_t *S, size_t N, + int WIDTH, int START_COLUMN, int AT_END_COLUMNS, + const char *OVERRIDE, const char *ENCODING, char *P) + -- Function: int ulc_width_linebreaks (const char *S, size_t N, + int WIDTH, int START_COLUMN, int AT_END_COLUMNS, + const char *OVERRIDE, const char *ENCODING, char *P) Chooses the best line breaks, assuming that every character occupies a width given by the ‘uc_width’ function (see *note uniwidth.h::). @@ -3280,9 +3373,10 @@ device that uses non-proportional fonts. Returns the column after the end of the string, and stores the result at ‘P[0..N-1]’. Every ‘P[I]’ is assigned one of the values - ‘UC_BREAK_MANDATORY’, ‘UC_BREAK_POSSIBLE’, ‘UC_BREAK_HYPHENATION’, - ‘UC_BREAK_PROHIBITED’. Here the value ‘UC_BREAK_POSSIBLE’ - indicates that a line break _should_ be inserted. + ‘UC_BREAK_MANDATORY’, ‘UC_BREAK_CR_BEFORE_LF’, ‘UC_BREAK_POSSIBLE’, + ‘UC_BREAK_HYPHENATION’, ‘UC_BREAK_PROHIBITED’. Here the value + ‘UC_BREAK_POSSIBLE’ indicates that a line break _should_ be + inserted. File: libunistring.info, Node: uninorm.h, Next: unicase.h, Prev: unilbrk.h, Up: Top @@ -3383,8 +3477,8 @@ single Unicode character. The following functions decompose a Unicode character. - -- Function: int uc_decomposition (ucs4_t UC, int *DECOMP_TAG, ucs4_t - *DECOMPOSITION) + -- Function: int uc_decomposition (ucs4_t UC, int *DECOMP_TAG, + ucs4_t *DECOMPOSITION) Returns the character decomposition mapping of the Unicode character UC. DECOMPOSITION must point to an array of at least ‘UC_DECOMPOSITION_MAX_LENGTH’ ‘ucs_t’ elements. @@ -3393,8 +3487,8 @@ single Unicode character. ‘*DECOMP_TAG’ are filled and N is returned. Otherwise -1 is returned. - -- Function: int uc_canonical_decomposition (ucs4_t UC, ucs4_t - *DECOMPOSITION) + -- Function: int uc_canonical_decomposition (ucs4_t UC, + ucs4_t *DECOMPOSITION) Returns the canonical character decomposition mapping of the Unicode character UC. DECOMPOSITION must point to an array of at least ‘UC_DECOMPOSITION_MAX_LENGTH’ ‘ucs_t’ elements. @@ -3492,12 +3586,12 @@ File: libunistring.info, Node: Normalizing comparisons, Next: Normalization of The following functions compare Unicode string, ignoring differences in normalization. - -- Function: int u8_normcmp (const uint8_t *S1, size_t N1, const - uint8_t *S2, size_t N2, uninorm_t NF, int *RESULTP) - -- Function: int u16_normcmp (const uint16_t *S1, size_t N1, const - uint16_t *S2, size_t N2, uninorm_t NF, int *RESULTP) - -- Function: int u32_normcmp (const uint32_t *S1, size_t N1, const - uint32_t *S2, size_t N2, uninorm_t NF, int *RESULTP) + -- Function: int u8_normcmp (const uint8_t *S1, size_t N1, + const uint8_t *S2, size_t N2, uninorm_t NF, int *RESULTP) + -- Function: int u16_normcmp (const uint16_t *S1, size_t N1, + const uint16_t *S2, size_t N2, uninorm_t NF, int *RESULTP) + -- Function: int u32_normcmp (const uint32_t *S1, size_t N1, + const uint32_t *S2, size_t N2, uninorm_t NF, int *RESULTP) Compares S1 and S2, ignoring differences in normalization. NF must be either ‘UNINORM_NFD’ or ‘UNINORM_NFKD’. @@ -3505,8 +3599,8 @@ in normalization. If successful, sets ‘*RESULTP’ to -1 if S1 < S2, 0 if S1 = S2, 1 if S1 > S2, and returns 0. Upon failure, returns -1 with ‘errno’ set. - -- Function: char * u8_normxfrm (const uint8_t *S, size_t N, uninorm_t - NF, char *RESULTBUF, size_t *LENGTHP) + -- Function: char * u8_normxfrm (const uint8_t *S, size_t N, + uninorm_t NF, char *RESULTBUF, size_t *LENGTHP) -- Function: char * u16_normxfrm (const uint16_t *S, size_t N, uninorm_t NF, char *RESULTBUF, size_t *LENGTHP) -- Function: char * u32_normxfrm (const uint32_t *S, size_t N, @@ -3521,12 +3615,12 @@ in normalization. The RESULTBUF and LENGTHP arguments are as described in chapter *note Conventions::. - -- Function: int u8_normcoll (const uint8_t *S1, size_t N1, const - uint8_t *S2, size_t N2, uninorm_t NF, int *RESULTP) - -- Function: int u16_normcoll (const uint16_t *S1, size_t N1, const - uint16_t *S2, size_t N2, uninorm_t NF, int *RESULTP) - -- Function: int u32_normcoll (const uint32_t *S1, size_t N1, const - uint32_t *S2, size_t N2, uninorm_t NF, int *RESULTP) + -- Function: int u8_normcoll (const uint8_t *S1, size_t N1, + const uint8_t *S2, size_t N2, uninorm_t NF, int *RESULTP) + -- Function: int u16_normcoll (const uint16_t *S1, size_t N1, + const uint16_t *S2, size_t N2, uninorm_t NF, int *RESULTP) + -- Function: int u32_normcoll (const uint32_t *S1, size_t N1, + const uint32_t *S2, size_t N2, uninorm_t NF, int *RESULTP) Compares S1 and S2, ignoring differences in normalization, using the collation rules of the current locale. @@ -3551,9 +3645,9 @@ function that “flushes” the stream. passes the normalized character sequence to the encapsulated stream of Unicode characters. - -- Function: struct uninorm_filter * uninorm_filter_create (uninorm_t - NF, int (*STREAM_FUNC) (void *STREAM_DATA, ucs4_t UC), void - *STREAM_DATA) + -- Function: struct uninorm_filter * uninorm_filter_create + (uninorm_t NF, int (*STREAM_FUNC) (void *STREAM_DATA, + ucs4_t UC), void *STREAM_DATA) Creates and returns a normalization filter for Unicode characters. The pair (STREAM_FUNC, STREAM_DATA) is the encapsulated stream. @@ -3679,15 +3773,15 @@ locale independent case mappings. Returns the ISO 639 language code of the current locale. Returns ‘""’ if it is unknown, or in the "C" locale. - -- Function: uint8_t * u8_toupper (const uint8_t *S, size_t N, const - char *ISO639_LANGUAGE, uninorm_t NF, uint8_t *RESULTBUF, - size_t *LENGTHP) - -- Function: uint16_t * u16_toupper (const uint16_t *S, size_t N, const - char *ISO639_LANGUAGE, uninorm_t NF, uint16_t *RESULTBUF, - size_t *LENGTHP) - -- Function: uint32_t * u32_toupper (const uint32_t *S, size_t N, const - char *ISO639_LANGUAGE, uninorm_t NF, uint32_t *RESULTBUF, + -- Function: uint8_t * u8_toupper (const uint8_t *S, size_t N, + const char *ISO639_LANGUAGE, uninorm_t NF, uint8_t *RESULTBUF, size_t *LENGTHP) + -- Function: uint16_t * u16_toupper (const uint16_t *S, size_t N, + const char *ISO639_LANGUAGE, uninorm_t NF, + uint16_t *RESULTBUF, size_t *LENGTHP) + -- Function: uint32_t * u32_toupper (const uint32_t *S, size_t N, + const char *ISO639_LANGUAGE, uninorm_t NF, + uint32_t *RESULTBUF, size_t *LENGTHP) Returns the uppercase mapping of a string. The NF argument identifies the normalization form to apply after @@ -3696,15 +3790,15 @@ locale independent case mappings. The RESULTBUF and LENGTHP arguments are as described in chapter *note Conventions::. - -- Function: uint8_t * u8_tolower (const uint8_t *S, size_t N, const - char *ISO639_LANGUAGE, uninorm_t NF, uint8_t *RESULTBUF, - size_t *LENGTHP) - -- Function: uint16_t * u16_tolower (const uint16_t *S, size_t N, const - char *ISO639_LANGUAGE, uninorm_t NF, uint16_t *RESULTBUF, - size_t *LENGTHP) - -- Function: uint32_t * u32_tolower (const uint32_t *S, size_t N, const - char *ISO639_LANGUAGE, uninorm_t NF, uint32_t *RESULTBUF, + -- Function: uint8_t * u8_tolower (const uint8_t *S, size_t N, + const char *ISO639_LANGUAGE, uninorm_t NF, uint8_t *RESULTBUF, size_t *LENGTHP) + -- Function: uint16_t * u16_tolower (const uint16_t *S, size_t N, + const char *ISO639_LANGUAGE, uninorm_t NF, + uint16_t *RESULTBUF, size_t *LENGTHP) + -- Function: uint32_t * u32_tolower (const uint32_t *S, size_t N, + const char *ISO639_LANGUAGE, uninorm_t NF, + uint32_t *RESULTBUF, size_t *LENGTHP) Returns the lowercase mapping of a string. The NF argument identifies the normalization form to apply after @@ -3713,15 +3807,15 @@ locale independent case mappings. The RESULTBUF and LENGTHP arguments are as described in chapter *note Conventions::. - -- Function: uint8_t * u8_totitle (const uint8_t *S, size_t N, const - char *ISO639_LANGUAGE, uninorm_t NF, uint8_t *RESULTBUF, - size_t *LENGTHP) - -- Function: uint16_t * u16_totitle (const uint16_t *S, size_t N, const - char *ISO639_LANGUAGE, uninorm_t NF, uint16_t *RESULTBUF, - size_t *LENGTHP) - -- Function: uint32_t * u32_totitle (const uint32_t *S, size_t N, const - char *ISO639_LANGUAGE, uninorm_t NF, uint32_t *RESULTBUF, + -- Function: uint8_t * u8_totitle (const uint8_t *S, size_t N, + const char *ISO639_LANGUAGE, uninorm_t NF, uint8_t *RESULTBUF, size_t *LENGTHP) + -- Function: uint16_t * u16_totitle (const uint16_t *S, size_t N, + const char *ISO639_LANGUAGE, uninorm_t NF, + uint16_t *RESULTBUF, size_t *LENGTHP) + -- Function: uint32_t * u32_totitle (const uint32_t *S, size_t N, + const char *ISO639_LANGUAGE, uninorm_t NF, + uint32_t *RESULTBUF, size_t *LENGTHP) Returns the titlecase mapping of a string. Mapping to title case means that, in each word, the first cased @@ -3760,20 +3854,23 @@ it (the “suffix”). The following functions return ‘casing_prefix_context_t’ objects: - -- Function: casing_prefix_context_t u8_casing_prefix_context (const - uint8_t *S, size_t N) - -- Function: casing_prefix_context_t u16_casing_prefix_context (const - uint16_t *S, size_t N) - -- Function: casing_prefix_context_t u32_casing_prefix_context (const - uint32_t *S, size_t N) + -- Function: casing_prefix_context_t u8_casing_prefix_context + (const uint8_t *S, size_t N) + -- Function: casing_prefix_context_t u16_casing_prefix_context + (const uint16_t *S, size_t N) + -- Function: casing_prefix_context_t u32_casing_prefix_context + (const uint32_t *S, size_t N) Returns the case-mapping context of a given prefix string. - -- Function: casing_prefix_context_t u8_casing_prefixes_context (const - uint8_t *S, size_t N, casing_prefix_context_t A_CONTEXT) - -- Function: casing_prefix_context_t u16_casing_prefixes_context (const - uint16_t *S, size_t N, casing_prefix_context_t A_CONTEXT) - -- Function: casing_prefix_context_t u32_casing_prefixes_context (const - uint32_t *S, size_t N, casing_prefix_context_t A_CONTEXT) + -- Function: casing_prefix_context_t u8_casing_prefixes_context + (const uint8_t *S, size_t N, + casing_prefix_context_t A_CONTEXT) + -- Function: casing_prefix_context_t u16_casing_prefixes_context + (const uint16_t *S, size_t N, + casing_prefix_context_t A_CONTEXT) + -- Function: casing_prefix_context_t u32_casing_prefixes_context + (const uint32_t *S, size_t N, + casing_prefix_context_t A_CONTEXT) Returns the case-mapping context of the prefix concat(A, S), given the case-mapping context of the prefix A. @@ -3789,20 +3886,23 @@ it (the “suffix”). The following functions return ‘casing_suffix_context_t’ objects: - -- Function: casing_suffix_context_t u8_casing_suffix_context (const - uint8_t *S, size_t N) - -- Function: casing_suffix_context_t u16_casing_suffix_context (const - uint16_t *S, size_t N) - -- Function: casing_suffix_context_t u32_casing_suffix_context (const - uint32_t *S, size_t N) + -- Function: casing_suffix_context_t u8_casing_suffix_context + (const uint8_t *S, size_t N) + -- Function: casing_suffix_context_t u16_casing_suffix_context + (const uint16_t *S, size_t N) + -- Function: casing_suffix_context_t u32_casing_suffix_context + (const uint32_t *S, size_t N) Returns the case-mapping context of a given suffix string. - -- Function: casing_suffix_context_t u8_casing_suffixes_context (const - uint8_t *S, size_t N, casing_suffix_context_t A_CONTEXT) - -- Function: casing_suffix_context_t u16_casing_suffixes_context (const - uint16_t *S, size_t N, casing_suffix_context_t A_CONTEXT) - -- Function: casing_suffix_context_t u32_casing_suffixes_context (const - uint32_t *S, size_t N, casing_suffix_context_t A_CONTEXT) + -- Function: casing_suffix_context_t u8_casing_suffixes_context + (const uint8_t *S, size_t N, + casing_suffix_context_t A_CONTEXT) + -- Function: casing_suffix_context_t u16_casing_suffixes_context + (const uint16_t *S, size_t N, + casing_suffix_context_t A_CONTEXT) + -- Function: casing_suffix_context_t u32_casing_suffixes_context + (const uint32_t *S, size_t N, + casing_suffix_context_t A_CONTEXT) Returns the case-mapping context of the suffix concat(S, A), given the case-mapping context of the suffix A. @@ -3811,19 +3911,19 @@ prefix context and the suffix context. -- Function: uint8_t * u8_ct_toupper (const uint8_t *S, size_t N, casing_prefix_context_t PREFIX_CONTEXT, - casing_suffix_context_t SUFFIX_CONTEXT, const char - *ISO639_LANGUAGE, uninorm_t NF, uint8_t *RESULTBUF, size_t - *LENGTHP) + casing_suffix_context_t SUFFIX_CONTEXT, + const char *ISO639_LANGUAGE, uninorm_t NF, uint8_t *RESULTBUF, + size_t *LENGTHP) -- Function: uint16_t * u16_ct_toupper (const uint16_t *S, size_t N, casing_prefix_context_t PREFIX_CONTEXT, - casing_suffix_context_t SUFFIX_CONTEXT, const char - *ISO639_LANGUAGE, uninorm_t NF, uint16_t *RESULTBUF, size_t - *LENGTHP) + casing_suffix_context_t SUFFIX_CONTEXT, + const char *ISO639_LANGUAGE, uninorm_t NF, + uint16_t *RESULTBUF, size_t *LENGTHP) -- Function: uint32_t * u32_ct_toupper (const uint32_t *S, size_t N, casing_prefix_context_t PREFIX_CONTEXT, - casing_suffix_context_t SUFFIX_CONTEXT, const char - *ISO639_LANGUAGE, uninorm_t NF, uint32_t *RESULTBUF, size_t - *LENGTHP) + casing_suffix_context_t SUFFIX_CONTEXT, + const char *ISO639_LANGUAGE, uninorm_t NF, + uint32_t *RESULTBUF, size_t *LENGTHP) Returns the uppercase mapping of a string that is surrounded by a prefix and a suffix. @@ -3832,19 +3932,19 @@ prefix context and the suffix context. -- Function: uint8_t * u8_ct_tolower (const uint8_t *S, size_t N, casing_prefix_context_t PREFIX_CONTEXT, - casing_suffix_context_t SUFFIX_CONTEXT, const char - *ISO639_LANGUAGE, uninorm_t NF, uint8_t *RESULTBUF, size_t - *LENGTHP) + casing_suffix_context_t SUFFIX_CONTEXT, + const char *ISO639_LANGUAGE, uninorm_t NF, uint8_t *RESULTBUF, + size_t *LENGTHP) -- Function: uint16_t * u16_ct_tolower (const uint16_t *S, size_t N, casing_prefix_context_t PREFIX_CONTEXT, - casing_suffix_context_t SUFFIX_CONTEXT, const char - *ISO639_LANGUAGE, uninorm_t NF, uint16_t *RESULTBUF, size_t - *LENGTHP) + casing_suffix_context_t SUFFIX_CONTEXT, + const char *ISO639_LANGUAGE, uninorm_t NF, + uint16_t *RESULTBUF, size_t *LENGTHP) -- Function: uint32_t * u32_ct_tolower (const uint32_t *S, size_t N, casing_prefix_context_t PREFIX_CONTEXT, - casing_suffix_context_t SUFFIX_CONTEXT, const char - *ISO639_LANGUAGE, uninorm_t NF, uint32_t *RESULTBUF, size_t - *LENGTHP) + casing_suffix_context_t SUFFIX_CONTEXT, + const char *ISO639_LANGUAGE, uninorm_t NF, + uint32_t *RESULTBUF, size_t *LENGTHP) Returns the lowercase mapping of a string that is surrounded by a prefix and a suffix. @@ -3853,19 +3953,19 @@ prefix context and the suffix context. -- Function: uint8_t * u8_ct_totitle (const uint8_t *S, size_t N, casing_prefix_context_t PREFIX_CONTEXT, - casing_suffix_context_t SUFFIX_CONTEXT, const char - *ISO639_LANGUAGE, uninorm_t NF, uint8_t *RESULTBUF, size_t - *LENGTHP) + casing_suffix_context_t SUFFIX_CONTEXT, + const char *ISO639_LANGUAGE, uninorm_t NF, uint8_t *RESULTBUF, + size_t *LENGTHP) -- Function: uint16_t * u16_ct_totitle (const uint16_t *S, size_t N, casing_prefix_context_t PREFIX_CONTEXT, - casing_suffix_context_t SUFFIX_CONTEXT, const char - *ISO639_LANGUAGE, uninorm_t NF, uint16_t *RESULTBUF, size_t - *LENGTHP) + casing_suffix_context_t SUFFIX_CONTEXT, + const char *ISO639_LANGUAGE, uninorm_t NF, + uint16_t *RESULTBUF, size_t *LENGTHP) -- Function: uint32_t * u32_ct_totitle (const uint32_t *S, size_t N, casing_prefix_context_t PREFIX_CONTEXT, - casing_suffix_context_t SUFFIX_CONTEXT, const char - *ISO639_LANGUAGE, uninorm_t NF, uint32_t *RESULTBUF, size_t - *LENGTHP) + casing_suffix_context_t SUFFIX_CONTEXT, + const char *ISO639_LANGUAGE, uninorm_t NF, + uint32_t *RESULTBUF, size_t *LENGTHP) Returns the titlecase mapping of a string that is surrounded by a prefix and a suffix. @@ -3893,15 +3993,15 @@ File: libunistring.info, Node: Case insensitive comparison, Next: Case detecti The following functions implement comparison that ignores differences in case and normalization. - -- Function: uint8_t * u8_casefold (const uint8_t *S, size_t N, const - char *ISO639_LANGUAGE, uninorm_t NF, uint8_t *RESULTBUF, + -- Function: uint8_t * u8_casefold (const uint8_t *S, size_t N, + const char *ISO639_LANGUAGE, uninorm_t NF, uint8_t *RESULTBUF, size_t *LENGTHP) -- Function: uint16_t * u16_casefold (const uint16_t *S, size_t N, - const char *ISO639_LANGUAGE, uninorm_t NF, uint16_t - *RESULTBUF, size_t *LENGTHP) + const char *ISO639_LANGUAGE, uninorm_t NF, + uint16_t *RESULTBUF, size_t *LENGTHP) -- Function: uint32_t * u32_casefold (const uint32_t *S, size_t N, - const char *ISO639_LANGUAGE, uninorm_t NF, uint32_t - *RESULTBUF, size_t *LENGTHP) + const char *ISO639_LANGUAGE, uninorm_t NF, + uint32_t *RESULTBUF, size_t *LENGTHP) Returns the case folded string. Comparing ‘u8_casefold (S1)’ and ‘u8_casefold (S2)’ with the @@ -3916,37 +4016,37 @@ in case and normalization. -- Function: uint8_t * u8_ct_casefold (const uint8_t *S, size_t N, casing_prefix_context_t PREFIX_CONTEXT, - casing_suffix_context_t SUFFIX_CONTEXT, const char - *ISO639_LANGUAGE, uninorm_t NF, uint8_t *RESULTBUF, size_t - *LENGTHP) + casing_suffix_context_t SUFFIX_CONTEXT, + const char *ISO639_LANGUAGE, uninorm_t NF, uint8_t *RESULTBUF, + size_t *LENGTHP) -- Function: uint16_t * u16_ct_casefold (const uint16_t *S, size_t N, casing_prefix_context_t PREFIX_CONTEXT, - casing_suffix_context_t SUFFIX_CONTEXT, const char - *ISO639_LANGUAGE, uninorm_t NF, uint16_t *RESULTBUF, size_t - *LENGTHP) + casing_suffix_context_t SUFFIX_CONTEXT, + const char *ISO639_LANGUAGE, uninorm_t NF, + uint16_t *RESULTBUF, size_t *LENGTHP) -- Function: uint32_t * u32_ct_casefold (const uint32_t *S, size_t N, casing_prefix_context_t PREFIX_CONTEXT, - casing_suffix_context_t SUFFIX_CONTEXT, const char - *ISO639_LANGUAGE, uninorm_t NF, uint32_t *RESULTBUF, size_t - *LENGTHP) + casing_suffix_context_t SUFFIX_CONTEXT, + const char *ISO639_LANGUAGE, uninorm_t NF, + uint32_t *RESULTBUF, size_t *LENGTHP) Returns the case folded string. The case folding takes into account the case mapping contexts of the prefix and suffix strings. The RESULTBUF and LENGTHP arguments are as described in chapter *note Conventions::. - -- Function: int u8_casecmp (const uint8_t *S1, size_t N1, const - uint8_t *S2, size_t N2, const char *ISO639_LANGUAGE, uninorm_t - NF, int *RESULTP) - -- Function: int u16_casecmp (const uint16_t *S1, size_t N1, const - uint16_t *S2, size_t N2, const char *ISO639_LANGUAGE, + -- Function: int u8_casecmp (const uint8_t *S1, size_t N1, + const uint8_t *S2, size_t N2, const char *ISO639_LANGUAGE, + uninorm_t NF, int *RESULTP) + -- Function: int u16_casecmp (const uint16_t *S1, size_t N1, + const uint16_t *S2, size_t N2, const char *ISO639_LANGUAGE, uninorm_t NF, int *RESULTP) - -- Function: int u32_casecmp (const uint32_t *S1, size_t N1, const - uint32_t *S2, size_t N2, const char *ISO639_LANGUAGE, + -- Function: int u32_casecmp (const uint32_t *S1, size_t N1, + const uint32_t *S2, size_t N2, const char *ISO639_LANGUAGE, + uninorm_t NF, int *RESULTP) + -- Function: int ulc_casecmp (const char *S1, size_t N1, + const char *S2, size_t N2, const char *ISO639_LANGUAGE, uninorm_t NF, int *RESULTP) - -- Function: int ulc_casecmp (const char *S1, size_t N1, const char - *S2, size_t N2, const char *ISO639_LANGUAGE, uninorm_t NF, int - *RESULTP) Compares S1 and S2, ignoring differences in case and normalization. The NF argument identifies the normalization form to apply after @@ -3958,18 +4058,18 @@ in case and normalization. The following functions additionally take into account the sorting rules of the current locale. - -- Function: char * u8_casexfrm (const uint8_t *S, size_t N, const char - *ISO639_LANGUAGE, uninorm_t NF, char *RESULTBUF, size_t - *LENGTHP) - -- Function: char * u16_casexfrm (const uint16_t *S, size_t N, const - char *ISO639_LANGUAGE, uninorm_t NF, char *RESULTBUF, size_t - *LENGTHP) - -- Function: char * u32_casexfrm (const uint32_t *S, size_t N, const - char *ISO639_LANGUAGE, uninorm_t NF, char *RESULTBUF, size_t - *LENGTHP) - -- Function: char * ulc_casexfrm (const char *S, size_t N, const char - *ISO639_LANGUAGE, uninorm_t NF, char *RESULTBUF, size_t - *LENGTHP) + -- Function: char * u8_casexfrm (const uint8_t *S, size_t N, + const char *ISO639_LANGUAGE, uninorm_t NF, char *RESULTBUF, + size_t *LENGTHP) + -- Function: char * u16_casexfrm (const uint16_t *S, size_t N, + const char *ISO639_LANGUAGE, uninorm_t NF, char *RESULTBUF, + size_t *LENGTHP) + -- Function: char * u32_casexfrm (const uint32_t *S, size_t N, + const char *ISO639_LANGUAGE, uninorm_t NF, char *RESULTBUF, + size_t *LENGTHP) + -- Function: char * ulc_casexfrm (const char *S, size_t N, + const char *ISO639_LANGUAGE, uninorm_t NF, char *RESULTBUF, + size_t *LENGTHP) Converts the string S of length N to a NUL-terminated byte sequence, in such a way that comparing ‘u8_casexfrm (S1)’ and ‘u8_casexfrm (S2)’ with the gnulib function ‘memcmp2’ is equivalent @@ -3981,18 +4081,18 @@ rules of the current locale. The RESULTBUF and LENGTHP arguments are as described in chapter *note Conventions::. - -- Function: int u8_casecoll (const uint8_t *S1, size_t N1, const - uint8_t *S2, size_t N2, const char *ISO639_LANGUAGE, uninorm_t - NF, int *RESULTP) - -- Function: int u16_casecoll (const uint16_t *S1, size_t N1, const - uint16_t *S2, size_t N2, const char *ISO639_LANGUAGE, + -- Function: int u8_casecoll (const uint8_t *S1, size_t N1, + const uint8_t *S2, size_t N2, const char *ISO639_LANGUAGE, + uninorm_t NF, int *RESULTP) + -- Function: int u16_casecoll (const uint16_t *S1, size_t N1, + const uint16_t *S2, size_t N2, const char *ISO639_LANGUAGE, + uninorm_t NF, int *RESULTP) + -- Function: int u32_casecoll (const uint32_t *S1, size_t N1, + const uint32_t *S2, size_t N2, const char *ISO639_LANGUAGE, uninorm_t NF, int *RESULTP) - -- Function: int u32_casecoll (const uint32_t *S1, size_t N1, const - uint32_t *S2, size_t N2, const char *ISO639_LANGUAGE, + -- Function: int ulc_casecoll (const char *S1, size_t N1, + const char *S2, size_t N2, const char *ISO639_LANGUAGE, uninorm_t NF, int *RESULTP) - -- Function: int ulc_casecoll (const char *S1, size_t N1, const char - *S2, size_t N2, const char *ISO639_LANGUAGE, uninorm_t NF, int - *RESULTP) Compares S1 and S2, ignoring differences in case and normalization, using the collation rules of the current locale. @@ -4013,42 +4113,42 @@ File: libunistring.info, Node: Case detection, Prev: Case insensitive comparis entirely in upper case. or entirely in lower case, or entirely in title case, or already case-folded. - -- Function: int u8_is_uppercase (const uint8_t *S, size_t N, const - char *ISO639_LANGUAGE, bool *RESULTP) - -- Function: int u16_is_uppercase (const uint16_t *S, size_t N, const - char *ISO639_LANGUAGE, bool *RESULTP) - -- Function: int u32_is_uppercase (const uint32_t *S, size_t N, const - char *ISO639_LANGUAGE, bool *RESULTP) + -- Function: int u8_is_uppercase (const uint8_t *S, size_t N, + const char *ISO639_LANGUAGE, bool *RESULTP) + -- Function: int u16_is_uppercase (const uint16_t *S, size_t N, + const char *ISO639_LANGUAGE, bool *RESULTP) + -- Function: int u32_is_uppercase (const uint32_t *S, size_t N, + const char *ISO639_LANGUAGE, bool *RESULTP) Sets ‘*RESULTP’ to true if mapping NFD(S) to upper case is a no-op, or to false otherwise, and returns 0. Upon failure, returns -1 with ‘errno’ set. - -- Function: int u8_is_lowercase (const uint8_t *S, size_t N, const - char *ISO639_LANGUAGE, bool *RESULTP) - -- Function: int u16_is_lowercase (const uint16_t *S, size_t N, const - char *ISO639_LANGUAGE, bool *RESULTP) - -- Function: int u32_is_lowercase (const uint32_t *S, size_t N, const - char *ISO639_LANGUAGE, bool *RESULTP) + -- Function: int u8_is_lowercase (const uint8_t *S, size_t N, + const char *ISO639_LANGUAGE, bool *RESULTP) + -- Function: int u16_is_lowercase (const uint16_t *S, size_t N, + const char *ISO639_LANGUAGE, bool *RESULTP) + -- Function: int u32_is_lowercase (const uint32_t *S, size_t N, + const char *ISO639_LANGUAGE, bool *RESULTP) Sets ‘*RESULTP’ to true if mapping NFD(S) to lower case is a no-op, or to false otherwise, and returns 0. Upon failure, returns -1 with ‘errno’ set. - -- Function: int u8_is_titlecase (const uint8_t *S, size_t N, const - char *ISO639_LANGUAGE, bool *RESULTP) - -- Function: int u16_is_titlecase (const uint16_t *S, size_t N, const - char *ISO639_LANGUAGE, bool *RESULTP) - -- Function: int u32_is_titlecase (const uint32_t *S, size_t N, const - char *ISO639_LANGUAGE, bool *RESULTP) + -- Function: int u8_is_titlecase (const uint8_t *S, size_t N, + const char *ISO639_LANGUAGE, bool *RESULTP) + -- Function: int u16_is_titlecase (const uint16_t *S, size_t N, + const char *ISO639_LANGUAGE, bool *RESULTP) + -- Function: int u32_is_titlecase (const uint32_t *S, size_t N, + const char *ISO639_LANGUAGE, bool *RESULTP) Sets ‘*RESULTP’ to true if mapping NFD(S) to title case is a no-op, or to false otherwise, and returns 0. Upon failure, returns -1 with ‘errno’ set. - -- Function: int u8_is_casefolded (const uint8_t *S, size_t N, const - char *ISO639_LANGUAGE, bool *RESULTP) - -- Function: int u16_is_casefolded (const uint16_t *S, size_t N, const - char *ISO639_LANGUAGE, bool *RESULTP) - -- Function: int u32_is_casefolded (const uint32_t *S, size_t N, const - char *ISO639_LANGUAGE, bool *RESULTP) + -- Function: int u8_is_casefolded (const uint8_t *S, size_t N, + const char *ISO639_LANGUAGE, bool *RESULTP) + -- Function: int u16_is_casefolded (const uint16_t *S, size_t N, + const char *ISO639_LANGUAGE, bool *RESULTP) + -- Function: int u32_is_casefolded (const uint32_t *S, size_t N, + const char *ISO639_LANGUAGE, bool *RESULTP) Sets ‘*RESULTP’ to true if applying case folding to NFD(S) is a no-op, or to false otherwise, and returns 0. Upon failure, returns -1 with ‘errno’ set. @@ -4056,12 +4156,12 @@ case, or already case-folded. The following functions determine whether case mappings have any effect on a Unicode string. - -- Function: int u8_is_cased (const uint8_t *S, size_t N, const char - *ISO639_LANGUAGE, bool *RESULTP) - -- Function: int u16_is_cased (const uint16_t *S, size_t N, const char - *ISO639_LANGUAGE, bool *RESULTP) - -- Function: int u32_is_cased (const uint32_t *S, size_t N, const char - *ISO639_LANGUAGE, bool *RESULTP) + -- Function: int u8_is_cased (const uint8_t *S, size_t N, + const char *ISO639_LANGUAGE, bool *RESULTP) + -- Function: int u16_is_cased (const uint16_t *S, size_t N, + const char *ISO639_LANGUAGE, bool *RESULTP) + -- Function: int u32_is_cased (const uint32_t *S, size_t N, + const char *ISO639_LANGUAGE, bool *RESULTP) Sets ‘*RESULTP’ to true if case matters for S, that is, if mapping NFD(S) to either upper case or lower case or title case is not a no-op. Set ‘*RESULTP’ to false if NFD(S) maps to itself under the @@ -4182,7 +4282,7 @@ File: libunistring.info, Node: Autoconf macro, Next: Reporting problems, Prev GNU Gnulib provides an autoconf macro that tests for the availability of ‘libunistring’. It is contained in the Gnulib module ‘libunistring’, see -<http://www.gnu.org/software/gnulib/MODULES.html#module=libunistring>. +<https://www.gnu.org/software/gnulib/MODULES.html#module=libunistring>. The macro is called ‘gl_LIBUNISTRING’. It searches for an installed libunistring. If found, it sets and AC_SUBSTs ‘HAVE_LIBUNISTRING=yes’ @@ -4213,10 +4313,10 @@ File: libunistring.info, Node: Reporting problems, Prev: Autoconf macro, Up: 16.5 Reporting problems ======================= - If you encounter any problem, please don’t hesitate to send a -detailed bug report to the ‘bug-libunistring@gnu.org’ mailing list. You -can alternatively also use the bug tracker at the project page -<https://savannah.gnu.org/projects/libunistring>. + If you encounter any problem, please don’t hesitate to submit a +detailed bug report either in the bug tracker at the project page +<https://savannah.gnu.org/projects/libunistring>, or by email to the +‘bug-libunistring@gnu.org’ mailing list. Please always include the version number of this library, and a short description of your operating system and compilation environment with @@ -4238,10 +4338,10 @@ library: <http://www.fribidi.org/>. For the rendering of Unicode strings outside of the context of a given toolkit (KDE/Qt or GNOME/Gtk), we recommend the Pango library: -<http://www.pango.org/>. +<https://www.pango.org/>. -File: libunistring.info, Node: The wchar_t mess, Next: Licenses, Prev: More functionality, Up: Top +File: libunistring.info, Node: The wchar_t mess, Next: The char32_t problem, Prev: More functionality, Up: Top Appendix A The ‘wchar_t’ mess ***************************** @@ -4286,22 +4386,67 @@ faithfully transport malformed characters that were present in the input, without requiring the program to produce garbage or abort. -File: libunistring.info, Node: Licenses, Next: Index, Prev: The wchar_t mess, Up: Top +File: libunistring.info, Node: The char32_t problem, Next: Licenses, Prev: The wchar_t mess, Up: Top + +Appendix B The ‘char32_t’ problem +********************************* + + In response to the ‘wchar_t’ mess described in the previous section, +ISO C 11 introduces two new types: ‘char32_t’ and ‘char16_t’. + + ‘char32_t’ is a type like ‘wchar_t’, with the added guarantee that it +is 32 bits wide. So, it is a type that is appropriate for encoding a +Unicode character. It is meant to resolve the problems of the 16-bit +wide ‘wchar_t’ on AIX and Windows platforms, and allow a saner +programming model for wide character strings across all platforms. + + ‘char16_t’ is a type like ‘wchar_t’, with the added guarantee that it +is 16 bits wide. It is meant to allow porting programs that use the +broken wide character strings programming model from Windows to all +platforms. Of course, no one needs this. + + These types are accompanied with a syntax for defining wide string +literals with these element types: ‘u"..."’ and ‘U"..."’. + + So far, so good. What the ISO C designers forgot, is to provide +standardized C library functions that operate on these wide character +strings. They standardized only the most basic functions, ‘mbrtoc32’ +and ‘c32rtomb’, which are analogous to ‘mbrtowc’ and ‘wcrtomb’, +respectively. For the rest, GNU gnulib +<https://www.gnu.org/software/gnulib/> provides the functions: + • Functions for converting an entire string: ‘mbstoc32s’ – like + ‘mbstowcs’, ‘c32stombs’ – like ‘wcstombs’. + • Functions for testing the properties of a 32-bit wide character: + ‘c32isalnum’, ‘c32isalpha’, etc. – like ‘iswalnum’, ‘iswalpha’, + etc. + + Still, this API has two problems: + • The ‘char32_t’ encoding is locale dependent and undocumented. This + means, if you want to know any property of a ‘char32_t’ character, + other than the properties defined by ‘<wctype.h>’ – such as whether + it’s a dash, currency symbol, paragraph separator, or similar –, + you have to convert it to ‘char *’ encoding first, by use of the + function ‘c32tomb’. + • Even on platforms where ‘wchar_t’ is 32 bits wide, the ‘char32_t’ + encoding may be different from the ‘wchar_t’ encoding. + + +File: libunistring.info, Node: Licenses, Next: Index, Prev: The char32_t problem, Up: Top -Appendix B Licenses +Appendix C Licenses ******************* The files of this package are covered by the licenses indicated in each particular file or directory. Here is a summary: • The ‘libunistring’ library and its header files are dual-licensed - under "the GNU LGPLv3+ or the GNU GPLv2". This means, you can use + under "the GNU LGPLv3+ or the GNU GPLv2+". This means, you can use it under either • − the terms of the GNU Lesser General Public License (LGPL) version 3 or (at your option) any later version, or - • − the terms of the GNU General Public License (GPL) version 2, - or - • − the same dual license "the GNU LGPLv3+ or the GNU GPLv2". + • − the terms of the GNU General Public License (GPL) version 2 + or (at your option) any later version, or + • − the same dual license "the GNU LGPLv3+ or the GNU GPLv2+". You find the GNU LGPL version 3 in *note GNU LGPL::. This license is based on the GNU GPL version 3, see *note GNU GPL::. You can find the GNU GPL version 2 at @@ -4336,12 +4481,12 @@ each particular file or directory. Here is a summary: File: libunistring.info, Node: GNU GPL, Next: GNU LGPL, Up: Licenses -B.1 GNU GENERAL PUBLIC LICENSE +C.1 GNU GENERAL PUBLIC LICENSE ============================== Version 3, 29 June 2007 - Copyright © 2007 Free Software Foundation, Inc. <http://fsf.org/> + Copyright © 2007 Free Software Foundation, Inc. <https://fsf.org/> Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed. @@ -4958,11 +5103,11 @@ TERMS AND CONDITIONS 15. Disclaimer of Warranty. THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY - APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE + APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM “AS IS” WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF - MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE + MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. @@ -5019,7 +5164,7 @@ state the exclusion of warranty; and each file should have at least the General Public License for more details. You should have received a copy of the GNU General Public License - along with this program. If not, see <http://www.gnu.org/licenses/>. + along with this program. If not, see <https://www.gnu.org/licenses/>. Also add information on how to contact you by electronic and paper mail. @@ -5040,24 +5185,24 @@ use an “about box”. You should also get your employer (if you work as a programmer) or school, if any, to sign a “copyright disclaimer” for the program, if necessary. For more information on this, and how to apply and follow -the GNU GPL, see <http://www.gnu.org/licenses/>. +the GNU GPL, see <https://www.gnu.org/licenses/>. The GNU General Public License does not permit incorporating your program into proprietary programs. If your program is a subroutine library, you may consider it more useful to permit linking proprietary applications with the library. If this is what you want to do, use the GNU Lesser General Public License instead of this License. But first, -please read <http://www.gnu.org/philosophy/why-not-lgpl.html>. +please read <https://www.gnu.org/licenses/why-not-lgpl.html>. File: libunistring.info, Node: GNU LGPL, Next: GNU FDL, Prev: GNU GPL, Up: Licenses -B.2 GNU LESSER GENERAL PUBLIC LICENSE +C.2 GNU LESSER GENERAL PUBLIC LICENSE ===================================== Version 3, 29 June 2007 - Copyright © 2007 Free Software Foundation, Inc. <http://fsf.org/> + Copyright © 2007 Free Software Foundation, Inc. <https://fsf.org/> Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed. @@ -5224,13 +5369,13 @@ supplemented by the additional permissions listed below. File: libunistring.info, Node: GNU FDL, Prev: GNU LGPL, Up: Licenses -B.3 GNU Free Documentation License +C.3 GNU Free Documentation License ================================== Version 1.3, 3 November 2008 Copyright © 2000, 2001, 2002, 2007, 2008 Free Software Foundation, Inc. - <http://fsf.org/> + <https://fsf.org/> Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed. @@ -5627,7 +5772,7 @@ B.3 GNU Free Documentation License the GNU Free Documentation License from time to time. Such new versions will be similar in spirit to the present version, but may differ in detail to address new problems or concerns. See - <http://www.gnu.org/copyleft/>. + <https://www.gnu.org/copyleft/>. Each version of the License is given a distinguishing version number. If the Document specifies that a particular numbered @@ -5740,8 +5885,12 @@ Index * casing_prefix_context_t: Case mappings of substrings. (line 14) * casing_suffix_context_t: Case mappings of substrings. - (line 43) + (line 52) * char, type: char * strings. (line 22) +* char16_t, type: The char32_t problem. + (line 6) +* char32_t, type: The char32_t problem. + (line 6) * combining, Unicode characters: Composition of characters. (line 6) * comparing: Comparing Unicode strings. @@ -5751,23 +5900,23 @@ Index * comparing, ignoring case: Case insensitive comparison. (line 6) * comparing, ignoring case, with collation rules: Case insensitive comparison. - (line 71) + (line 87) * comparing, ignoring normalization: Normalizing comparisons. (line 6) * comparing, ignoring normalization and case: Case insensitive comparison. (line 6) * comparing, ignoring normalization and case, with collation rules: Case insensitive comparison. - (line 71) + (line 87) * comparing, ignoring normalization, with collation rules: Normalizing comparisons. - (line 22) + (line 25) * comparing, with collation rules: Comparing NUL terminated Unicode strings. (line 18) * comparing, with collation rules, ignoring case: Case insensitive comparison. - (line 71) + (line 87) * comparing, with collation rules, ignoring normalization: Normalizing comparisons. - (line 22) + (line 25) * comparing, with collation rules, ignoring normalization and case: Case insensitive comparison. - (line 71) + (line 87) * compiler options: Compiler options. (line 24) * composing, Unicode characters: Composition of characters. (line 6) @@ -5847,24 +5996,24 @@ Index (line 10) * titlecasing: Case mappings of strings. (line 6) -* u16_asnprintf: unistdio.h. (line 111) -* u16_asprintf: unistdio.h. (line 109) +* u16_asnprintf: unistdio.h. (line 119) +* u16_asprintf: unistdio.h. (line 117) * u16_casecmp: Case insensitive comparison. - (line 54) + (line 65) * u16_casecoll: Case insensitive comparison. - (line 100) + (line 125) * u16_casefold: Case insensitive comparison. - (line 12) + (line 13) * u16_casexfrm: Case insensitive comparison. - (line 77) + (line 95) * u16_casing_prefixes_context: Case mappings of substrings. - (line 36) + (line 41) * u16_casing_prefix_context: Case mappings of substrings. - (line 28) + (line 29) * u16_casing_suffixes_context: Case mappings of substrings. - (line 65) + (line 79) * u16_casing_suffix_context: Case mappings of substrings. - (line 57) + (line 67) * u16_check: Elementary string checks. (line 10) * u16_chr: Searching for a character. @@ -5872,76 +6021,76 @@ Index * u16_cmp: Comparing Unicode strings. (line 11) * u16_cmp2: Comparing Unicode strings. - (line 27) -* u16_conv_from_encoding: uniconv.h. (line 51) -* u16_conv_to_encoding: uniconv.h. (line 88) + (line 29) +* u16_conv_from_encoding: uniconv.h. (line 53) +* u16_conv_to_encoding: uniconv.h. (line 96) * u16_cpy: Copying Unicode strings. - (line 10) + (line 11) * u16_cpy_alloc: Elementary string functions with memory allocation. (line 9) * u16_ct_casefold: Case insensitive comparison. - (line 35) + (line 40) * u16_ct_tolower: Case mappings of substrings. - (line 101) + (line 127) * u16_ct_totitle: Case mappings of substrings. - (line 122) + (line 154) * u16_ct_toupper: Case mappings of substrings. - (line 80) + (line 100) * u16_endswith: Searching for a substring. - (line 30) + (line 33) * u16_grapheme_breaks: Grapheme cluster breaks in a string. - (line 42) + (line 45) * u16_grapheme_next: Grapheme cluster breaks in a string. (line 11) * u16_grapheme_prev: Grapheme cluster breaks in a string. (line 25) -* u16_is_cased: Case detection. (line 55) -* u16_is_casefolded: Case detection. (line 42) -* u16_is_lowercase: Case detection. (line 22) -* u16_is_titlecase: Case detection. (line 32) -* u16_is_uppercase: Case detection. (line 12) +* u16_is_cased: Case detection. (line 67) +* u16_is_casefolded: Case detection. (line 52) +* u16_is_lowercase: Case detection. (line 26) +* u16_is_titlecase: Case detection. (line 39) +* u16_is_uppercase: Case detection. (line 13) * u16_mblen: Iterating. (line 10) * u16_mbsnlen: Counting characters. (line 9) * u16_mbtouc: Iterating. (line 20) -* u16_mbtoucr: Iterating. (line 48) -* u16_mbtouc_unsafe: Iterating. (line 39) +* u16_mbtoucr: Iterating. (line 51) +* u16_mbtouc_unsafe: Iterating. (line 40) * u16_move: Copying Unicode strings. - (line 21) + (line 25) * u16_next: Iterating over a NUL terminated Unicode string. (line 23) * u16_normalize: Normalization of strings. - (line 48) + (line 49) * u16_normcmp: Normalizing comparisons. - (line 11) + (line 12) * u16_normcoll: Normalizing comparisons. - (line 40) + (line 46) * u16_normxfrm: Normalizing comparisons. - (line 24) -* u16_possible_linebreaks: unilbrk.h. (line 44) + (line 27) +* u16_possible_linebreaks: unilbrk.h. (line 49) * u16_prev: Iterating over a NUL terminated Unicode string. - (line 34) + (line 35) * u16_set: Copying Unicode strings. - (line 34) -* u16_snprintf: unistdio.h. (line 107) -* u16_sprintf: unistdio.h. (line 106) + (line 40) +* u16_snprintf: unistdio.h. (line 115) +* u16_sprintf: unistdio.h. (line 114) * u16_startswith: Searching for a substring. - (line 22) + (line 25) * u16_stpcpy: Copying a NUL terminated Unicode string. (line 19) * u16_stpncpy: Copying a NUL terminated Unicode string. - (line 42) + (line 44) * u16_strcat: Copying a NUL terminated Unicode string. - (line 55) + (line 57) * u16_strchr: Searching for a character in a NUL terminated Unicode string. (line 9) * u16_strcmp: Comparing NUL terminated Unicode strings. (line 9) * u16_strcoll: Comparing NUL terminated Unicode strings. (line 19) -* u16_strconv_from_encoding: uniconv.h. (line 127) -* u16_strconv_from_locale: uniconv.h. (line 156) -* u16_strconv_to_encoding: uniconv.h. (line 140) -* u16_strconv_to_locale: uniconv.h. (line 166) +* u16_strconv_from_encoding: uniconv.h. (line 140) +* u16_strconv_from_locale: uniconv.h. (line 174) +* u16_strconv_to_encoding: uniconv.h. (line 156) +* u16_strconv_to_locale: uniconv.h. (line 184) * u16_strcpy: Copying a NUL terminated Unicode string. (line 9) * u16_strcspn: Searching for a character in a NUL terminated Unicode string. @@ -5954,11 +6103,11 @@ Index * u16_strmbtouc: Iterating over a NUL terminated Unicode string. (line 16) * u16_strncat: Copying a NUL terminated Unicode string. - (line 66) + (line 69) * u16_strncmp: Comparing NUL terminated Unicode strings. - (line 35) + (line 36) * u16_strncpy: Copying a NUL terminated Unicode string. - (line 31) + (line 32) * u16_strnlen: Length. (line 17) * u16_strpbrk: Searching for a character in a NUL terminated Unicode string. (line 53) @@ -5967,132 +6116,132 @@ Index * u16_strspn: Searching for a character in a NUL terminated Unicode string. (line 41) * u16_strstr: Searching for a substring. - (line 11) -* u16_strtok: Tokenizing. (line 10) + (line 12) +* u16_strtok: Tokenizing. (line 11) * u16_strwidth: uniwidth.h. (line 38) * u16_tolower: Case mappings of strings. - (line 44) + (line 48) * u16_totitle: Case mappings of strings. - (line 61) + (line 68) * u16_toupper: Case mappings of strings. - (line 27) + (line 28) * u16_to_u32: Elementary string conversions. - (line 30) + (line 32) * u16_to_u8: Elementary string conversions. - (line 23) -* u16_u16_asnprintf: unistdio.h. (line 131) -* u16_u16_asprintf: unistdio.h. (line 129) -* u16_u16_snprintf: unistdio.h. (line 127) -* u16_u16_sprintf: unistdio.h. (line 125) -* u16_u16_vasnprintf: unistdio.h. (line 139) -* u16_u16_vasprintf: unistdio.h. (line 137) -* u16_u16_vsnprintf: unistdio.h. (line 135) -* u16_u16_vsprintf: unistdio.h. (line 133) + (line 25) +* u16_u16_asnprintf: unistdio.h. (line 141) +* u16_u16_asprintf: unistdio.h. (line 139) +* u16_u16_snprintf: unistdio.h. (line 136) +* u16_u16_sprintf: unistdio.h. (line 134) +* u16_u16_vasnprintf: unistdio.h. (line 150) +* u16_u16_vasprintf: unistdio.h. (line 148) +* u16_u16_vsnprintf: unistdio.h. (line 145) +* u16_u16_vsprintf: unistdio.h. (line 143) * u16_uctomb: Creating Unicode strings. (line 10) -* u16_vasnprintf: unistdio.h. (line 119) -* u16_vasprintf: unistdio.h. (line 117) -* u16_vsnprintf: unistdio.h. (line 115) -* u16_vsprintf: unistdio.h. (line 113) +* u16_vasnprintf: unistdio.h. (line 128) +* u16_vasprintf: unistdio.h. (line 126) +* u16_vsnprintf: unistdio.h. (line 124) +* u16_vsprintf: unistdio.h. (line 121) * u16_width: uniwidth.h. (line 29) -* u16_width_linebreaks: unilbrk.h. (line 62) +* u16_width_linebreaks: unilbrk.h. (line 68) * u16_wordbreaks: Word breaks in a string. (line 9) -* u32_asnprintf: unistdio.h. (line 150) -* u32_asprintf: unistdio.h. (line 148) +* u32_asnprintf: unistdio.h. (line 162) +* u32_asprintf: unistdio.h. (line 160) * u32_casecmp: Case insensitive comparison. - (line 57) + (line 70) * u32_casecoll: Case insensitive comparison. - (line 103) + (line 130) * u32_casefold: Case insensitive comparison. - (line 15) + (line 17) * u32_casexfrm: Case insensitive comparison. - (line 80) + (line 100) * u32_casing_prefixes_context: Case mappings of substrings. - (line 38) + (line 45) * u32_casing_prefix_context: Case mappings of substrings. - (line 30) + (line 32) * u32_casing_suffixes_context: Case mappings of substrings. - (line 67) + (line 83) * u32_casing_suffix_context: Case mappings of substrings. - (line 59) + (line 70) * u32_check: Elementary string checks. (line 11) * u32_chr: Searching for a character. (line 11) * u32_cmp: Comparing Unicode strings. - (line 13) + (line 14) * u32_cmp2: Comparing Unicode strings. - (line 29) -* u32_conv_from_encoding: uniconv.h. (line 54) -* u32_conv_to_encoding: uniconv.h. (line 91) + (line 32) +* u32_conv_from_encoding: uniconv.h. (line 58) +* u32_conv_to_encoding: uniconv.h. (line 101) * u32_cpy: Copying Unicode strings. - (line 12) + (line 14) * u32_cpy_alloc: Elementary string functions with memory allocation. (line 10) * u32_ct_casefold: Case insensitive comparison. - (line 40) + (line 47) * u32_ct_tolower: Case mappings of substrings. - (line 106) + (line 134) * u32_ct_totitle: Case mappings of substrings. - (line 127) + (line 161) * u32_ct_toupper: Case mappings of substrings. - (line 85) + (line 107) * u32_endswith: Searching for a substring. - (line 32) + (line 35) * u32_grapheme_breaks: Grapheme cluster breaks in a string. - (line 44) + (line 48) * u32_grapheme_next: Grapheme cluster breaks in a string. (line 13) * u32_grapheme_prev: Grapheme cluster breaks in a string. (line 27) -* u32_is_cased: Case detection. (line 57) -* u32_is_casefolded: Case detection. (line 44) -* u32_is_lowercase: Case detection. (line 24) -* u32_is_titlecase: Case detection. (line 34) -* u32_is_uppercase: Case detection. (line 14) +* u32_is_cased: Case detection. (line 69) +* u32_is_casefolded: Case detection. (line 55) +* u32_is_lowercase: Case detection. (line 29) +* u32_is_titlecase: Case detection. (line 42) +* u32_is_uppercase: Case detection. (line 16) * u32_mblen: Iterating. (line 11) * u32_mbsnlen: Counting characters. (line 10) * u32_mbtouc: Iterating. (line 21) -* u32_mbtoucr: Iterating. (line 49) -* u32_mbtouc_unsafe: Iterating. (line 41) +* u32_mbtoucr: Iterating. (line 52) +* u32_mbtouc_unsafe: Iterating. (line 43) * u32_move: Copying Unicode strings. - (line 23) + (line 28) * u32_next: Iterating over a NUL terminated Unicode string. (line 24) * u32_normalize: Normalization of strings. - (line 50) + (line 51) * u32_normcmp: Normalizing comparisons. - (line 13) + (line 15) * u32_normcoll: Normalizing comparisons. - (line 42) + (line 49) * u32_normxfrm: Normalizing comparisons. - (line 26) -* u32_possible_linebreaks: unilbrk.h. (line 46) + (line 30) +* u32_possible_linebreaks: unilbrk.h. (line 51) * u32_prev: Iterating over a NUL terminated Unicode string. - (line 36) + (line 37) * u32_set: Copying Unicode strings. - (line 35) -* u32_snprintf: unistdio.h. (line 146) -* u32_sprintf: unistdio.h. (line 145) + (line 41) +* u32_snprintf: unistdio.h. (line 158) +* u32_sprintf: unistdio.h. (line 157) * u32_startswith: Searching for a substring. - (line 24) + (line 27) * u32_stpcpy: Copying a NUL terminated Unicode string. (line 21) * u32_stpncpy: Copying a NUL terminated Unicode string. - (line 44) + (line 46) * u32_strcat: Copying a NUL terminated Unicode string. - (line 57) + (line 59) * u32_strchr: Searching for a character in a NUL terminated Unicode string. (line 10) * u32_strcmp: Comparing NUL terminated Unicode strings. (line 10) * u32_strcoll: Comparing NUL terminated Unicode strings. (line 20) -* u32_strconv_from_encoding: uniconv.h. (line 129) -* u32_strconv_from_locale: uniconv.h. (line 157) -* u32_strconv_to_encoding: uniconv.h. (line 142) -* u32_strconv_to_locale: uniconv.h. (line 167) +* u32_strconv_from_encoding: uniconv.h. (line 143) +* u32_strconv_from_locale: uniconv.h. (line 175) +* u32_strconv_to_encoding: uniconv.h. (line 159) +* u32_strconv_to_locale: uniconv.h. (line 185) * u32_strcpy: Copying a NUL terminated Unicode string. (line 11) * u32_strcspn: Searching for a character in a NUL terminated Unicode string. @@ -6105,68 +6254,68 @@ Index * u32_strmbtouc: Iterating over a NUL terminated Unicode string. (line 17) * u32_strncat: Copying a NUL terminated Unicode string. - (line 68) + (line 71) * u32_strncmp: Comparing NUL terminated Unicode strings. - (line 37) + (line 39) * u32_strncpy: Copying a NUL terminated Unicode string. - (line 33) + (line 34) * u32_strnlen: Length. (line 18) * u32_strpbrk: Searching for a character in a NUL terminated Unicode string. - (line 55) + (line 56) * u32_strrchr: Searching for a character in a NUL terminated Unicode string. (line 18) * u32_strspn: Searching for a character in a NUL terminated Unicode string. (line 43) * u32_strstr: Searching for a substring. - (line 13) -* u32_strtok: Tokenizing. (line 12) + (line 15) +* u32_strtok: Tokenizing. (line 13) * u32_strwidth: uniwidth.h. (line 39) * u32_tolower: Case mappings of strings. - (line 47) + (line 52) * u32_totitle: Case mappings of strings. - (line 64) + (line 72) * u32_toupper: Case mappings of strings. - (line 30) + (line 32) * u32_to_u16: Elementary string conversions. - (line 44) + (line 47) * u32_to_u8: Elementary string conversions. - (line 37) -* u32_u32_asnprintf: unistdio.h. (line 170) -* u32_u32_asprintf: unistdio.h. (line 168) -* u32_u32_snprintf: unistdio.h. (line 166) -* u32_u32_sprintf: unistdio.h. (line 164) -* u32_u32_vasnprintf: unistdio.h. (line 178) -* u32_u32_vasprintf: unistdio.h. (line 176) -* u32_u32_vsnprintf: unistdio.h. (line 174) -* u32_u32_vsprintf: unistdio.h. (line 172) + (line 40) +* u32_u32_asnprintf: unistdio.h. (line 184) +* u32_u32_asprintf: unistdio.h. (line 182) +* u32_u32_snprintf: unistdio.h. (line 179) +* u32_u32_sprintf: unistdio.h. (line 177) +* u32_u32_vasnprintf: unistdio.h. (line 193) +* u32_u32_vasprintf: unistdio.h. (line 191) +* u32_u32_vsnprintf: unistdio.h. (line 188) +* u32_u32_vsprintf: unistdio.h. (line 186) * u32_uctomb: Creating Unicode strings. (line 11) -* u32_vasnprintf: unistdio.h. (line 158) -* u32_vasprintf: unistdio.h. (line 156) -* u32_vsnprintf: unistdio.h. (line 154) -* u32_vsprintf: unistdio.h. (line 152) +* u32_vasnprintf: unistdio.h. (line 171) +* u32_vasprintf: unistdio.h. (line 169) +* u32_vsnprintf: unistdio.h. (line 167) +* u32_vsprintf: unistdio.h. (line 164) * u32_width: uniwidth.h. (line 31) -* u32_width_linebreaks: unilbrk.h. (line 65) +* u32_width_linebreaks: unilbrk.h. (line 72) * u32_wordbreaks: Word breaks in a string. (line 10) -* u8_asnprintf: unistdio.h. (line 72) -* u8_asprintf: unistdio.h. (line 70) +* u8_asnprintf: unistdio.h. (line 75) +* u8_asprintf: unistdio.h. (line 73) * u8_casecmp: Case insensitive comparison. - (line 51) + (line 60) * u8_casecoll: Case insensitive comparison. - (line 97) + (line 120) * u8_casefold: Case insensitive comparison. (line 9) * u8_casexfrm: Case insensitive comparison. - (line 74) + (line 90) * u8_casing_prefixes_context: Case mappings of substrings. - (line 34) + (line 37) * u8_casing_prefix_context: Case mappings of substrings. (line 26) * u8_casing_suffixes_context: Case mappings of substrings. - (line 63) + (line 75) * u8_casing_suffix_context: Case mappings of substrings. - (line 55) + (line 64) * u8_check: Elementary string checks. (line 9) * u8_chr: Searching for a character. @@ -6174,41 +6323,41 @@ Index * u8_cmp: Comparing Unicode strings. (line 9) * u8_cmp2: Comparing Unicode strings. - (line 25) + (line 27) * u8_conv_from_encoding: uniconv.h. (line 48) -* u8_conv_to_encoding: uniconv.h. (line 85) +* u8_conv_to_encoding: uniconv.h. (line 91) * u8_cpy: Copying Unicode strings. (line 8) * u8_cpy_alloc: Elementary string functions with memory allocation. (line 8) * u8_ct_casefold: Case insensitive comparison. - (line 30) + (line 33) * u8_ct_tolower: Case mappings of substrings. - (line 96) + (line 120) * u8_ct_totitle: Case mappings of substrings. - (line 117) + (line 147) * u8_ct_toupper: Case mappings of substrings. - (line 75) + (line 93) * u8_endswith: Searching for a substring. - (line 28) + (line 31) * u8_grapheme_breaks: Grapheme cluster breaks in a string. - (line 40) + (line 43) * u8_grapheme_next: Grapheme cluster breaks in a string. (line 9) * u8_grapheme_prev: Grapheme cluster breaks in a string. (line 23) -* u8_is_cased: Case detection. (line 53) -* u8_is_casefolded: Case detection. (line 40) -* u8_is_lowercase: Case detection. (line 20) -* u8_is_titlecase: Case detection. (line 30) +* u8_is_cased: Case detection. (line 65) +* u8_is_casefolded: Case detection. (line 49) +* u8_is_lowercase: Case detection. (line 23) +* u8_is_titlecase: Case detection. (line 36) * u8_is_uppercase: Case detection. (line 10) * u8_mblen: Iterating. (line 9) * u8_mbsnlen: Counting characters. (line 8) * u8_mbtouc: Iterating. (line 19) -* u8_mbtoucr: Iterating. (line 47) +* u8_mbtoucr: Iterating. (line 50) * u8_mbtouc_unsafe: Iterating. (line 37) * u8_move: Copying Unicode strings. - (line 19) + (line 22) * u8_next: Iterating over a NUL terminated Unicode string. (line 22) * u8_normalize: Normalization of strings. @@ -6216,34 +6365,34 @@ Index * u8_normcmp: Normalizing comparisons. (line 9) * u8_normcoll: Normalizing comparisons. - (line 38) + (line 43) * u8_normxfrm: Normalizing comparisons. - (line 22) -* u8_possible_linebreaks: unilbrk.h. (line 42) + (line 25) +* u8_possible_linebreaks: unilbrk.h. (line 46) * u8_prev: Iterating over a NUL terminated Unicode string. (line 32) * u8_set: Copying Unicode strings. - (line 33) -* u8_snprintf: unistdio.h. (line 68) -* u8_sprintf: unistdio.h. (line 67) + (line 39) +* u8_snprintf: unistdio.h. (line 71) +* u8_sprintf: unistdio.h. (line 70) * u8_startswith: Searching for a substring. - (line 20) + (line 23) * u8_stpcpy: Copying a NUL terminated Unicode string. (line 18) * u8_stpncpy: Copying a NUL terminated Unicode string. - (line 40) + (line 41) * u8_strcat: Copying a NUL terminated Unicode string. - (line 54) + (line 56) * u8_strchr: Searching for a character in a NUL terminated Unicode string. (line 8) * u8_strcmp: Comparing NUL terminated Unicode strings. (line 8) * u8_strcoll: Comparing NUL terminated Unicode strings. (line 18) -* u8_strconv_from_encoding: uniconv.h. (line 125) -* u8_strconv_from_locale: uniconv.h. (line 155) -* u8_strconv_to_encoding: uniconv.h. (line 138) -* u8_strconv_to_locale: uniconv.h. (line 165) +* u8_strconv_from_encoding: uniconv.h. (line 137) +* u8_strconv_from_locale: uniconv.h. (line 173) +* u8_strconv_to_encoding: uniconv.h. (line 153) +* u8_strconv_to_locale: uniconv.h. (line 183) * u8_strcpy: Copying a NUL terminated Unicode string. (line 8) * u8_strcspn: Searching for a character in a NUL terminated Unicode string. @@ -6256,7 +6405,7 @@ Index * u8_strmbtouc: Iterating over a NUL terminated Unicode string. (line 15) * u8_strncat: Copying a NUL terminated Unicode string. - (line 64) + (line 66) * u8_strncmp: Comparing NUL terminated Unicode strings. (line 33) * u8_strncpy: Copying a NUL terminated Unicode string. @@ -6273,44 +6422,44 @@ Index * u8_strtok: Tokenizing. (line 8) * u8_strwidth: uniwidth.h. (line 37) * u8_tolower: Case mappings of strings. - (line 41) + (line 44) * u8_totitle: Case mappings of strings. - (line 58) + (line 64) * u8_toupper: Case mappings of strings. (line 24) * u8_to_u16: Elementary string conversions. (line 9) * u8_to_u32: Elementary string conversions. - (line 16) -* u8_u8_asnprintf: unistdio.h. (line 92) -* u8_u8_asprintf: unistdio.h. (line 90) -* u8_u8_snprintf: unistdio.h. (line 88) -* u8_u8_sprintf: unistdio.h. (line 86) -* u8_u8_vasnprintf: unistdio.h. (line 100) -* u8_u8_vasprintf: unistdio.h. (line 98) -* u8_u8_vsnprintf: unistdio.h. (line 96) -* u8_u8_vsprintf: unistdio.h. (line 94) + (line 17) +* u8_u8_asnprintf: unistdio.h. (line 98) +* u8_u8_asprintf: unistdio.h. (line 96) +* u8_u8_snprintf: unistdio.h. (line 93) +* u8_u8_sprintf: unistdio.h. (line 91) +* u8_u8_vasnprintf: unistdio.h. (line 108) +* u8_u8_vasprintf: unistdio.h. (line 106) +* u8_u8_vsnprintf: unistdio.h. (line 103) +* u8_u8_vsprintf: unistdio.h. (line 100) * u8_uctomb: Creating Unicode strings. (line 9) -* u8_vasnprintf: unistdio.h. (line 80) -* u8_vasprintf: unistdio.h. (line 78) -* u8_vsnprintf: unistdio.h. (line 76) -* u8_vsprintf: unistdio.h. (line 74) +* u8_vasnprintf: unistdio.h. (line 85) +* u8_vasprintf: unistdio.h. (line 82) +* u8_vsnprintf: unistdio.h. (line 80) +* u8_vsprintf: unistdio.h. (line 77) * u8_width: uniwidth.h. (line 27) -* u8_width_linebreaks: unilbrk.h. (line 59) +* u8_width_linebreaks: unilbrk.h. (line 65) * u8_wordbreaks: Word breaks in a string. (line 8) * UCS-4: Unicode. (line 14) * ucs4_t: unitypes.h. (line 15) * uc_all_blocks: Blocks. (line 36) * uc_all_scripts: Scripts. (line 35) -* uc_bidi_category: Bidi class. (line 93) -* uc_bidi_category_byname: Bidi class. (line 83) -* uc_bidi_category_name: Bidi class. (line 75) -* uc_bidi_class: Bidi class. (line 92) -* uc_bidi_class_byname: Bidi class. (line 82) -* uc_bidi_class_long_name: Bidi class. (line 79) -* uc_bidi_class_name: Bidi class. (line 74) +* uc_bidi_category: Bidi class. (line 105) +* uc_bidi_category_byname: Bidi class. (line 95) +* uc_bidi_category_name: Bidi class. (line 87) +* uc_bidi_class: Bidi class. (line 104) +* uc_bidi_class_byname: Bidi class. (line 94) +* uc_bidi_class_long_name: Bidi class. (line 91) +* uc_bidi_class_name: Bidi class. (line 86) * uc_block: Blocks. (line 26) * uc_block_t: Blocks. (line 11) * uc_canonical_decomposition: Decomposition of characters. @@ -6332,24 +6481,24 @@ Index (line 80) * uc_digit_value: Digit value. (line 10) * uc_fraction_t: Numeric value. (line 12) -* uc_general_category: Object oriented API. (line 221) -* uc_general_category_and: Object oriented API. (line 182) -* uc_general_category_and_not: Object oriented API. (line 189) -* uc_general_category_byname: Object oriented API. (line 211) -* uc_general_category_long_name: Object oriented API. (line 205) -* uc_general_category_name: Object oriented API. (line 199) +* uc_general_category: Object oriented API. (line 227) +* uc_general_category_and: Object oriented API. (line 183) +* uc_general_category_and_not: Object oriented API. (line 191) +* uc_general_category_byname: Object oriented API. (line 216) +* uc_general_category_long_name: Object oriented API. (line 209) +* uc_general_category_name: Object oriented API. (line 202) * uc_general_category_or: Object oriented API. (line 176) * uc_general_category_t: Object oriented API. (line 6) * uc_graphemeclusterbreak_property: Grapheme cluster break property. (line 37) * uc_grapheme_breaks: Grapheme cluster breaks in a string. - (line 48) + (line 53) * uc_is_alnum: Classifications like in ISO C. (line 13) * uc_is_alpha: Classifications like in ISO C. (line 17) -* uc_is_bidi_category: Bidi class. (line 97) -* uc_is_bidi_class: Bidi class. (line 96) +* uc_is_bidi_category: Bidi class. (line 109) +* uc_is_bidi_class: Bidi class. (line 108) * uc_is_blank: Classifications like in ISO C. (line 63) * uc_is_block: Blocks. (line 31) @@ -6359,7 +6508,7 @@ Index (line 9) * uc_is_digit: Classifications like in ISO C. (line 26) -* uc_is_general_category: Object oriented API. (line 226) +* uc_is_general_category: Object oriented API. (line 232) * uc_is_general_category_withtable: Bit mask API. (line 51) * uc_is_graph: Classifications like in ISO C. (line 30) @@ -6372,179 +6521,193 @@ Index * uc_is_print: Classifications like in ISO C. (line 40) * uc_is_property: Properties as objects. - (line 150) + (line 160) * uc_is_property_alphabetic: Properties as functions. (line 9) * uc_is_property_ascii_hex_digit: Properties as functions. - (line 80) + (line 81) * uc_is_property_bidi_arabic_digit: Properties as functions. - (line 66) + (line 67) * uc_is_property_bidi_arabic_right_to_left: Properties as functions. - (line 62) + (line 63) * uc_is_property_bidi_block_separator: Properties as functions. - (line 68) + (line 69) * uc_is_property_bidi_boundary_neutral: Properties as functions. - (line 72) + (line 73) * uc_is_property_bidi_common_separator: Properties as functions. - (line 67) + (line 68) * uc_is_property_bidi_control: Properties as functions. - (line 59) + (line 60) * uc_is_property_bidi_embedding_or_override: Properties as functions. - (line 74) + (line 75) * uc_is_property_bidi_european_digit: Properties as functions. - (line 63) -* uc_is_property_bidi_eur_num_separator: Properties as functions. (line 64) -* uc_is_property_bidi_eur_num_terminator: Properties as functions. +* uc_is_property_bidi_eur_num_separator: Properties as functions. (line 65) +* uc_is_property_bidi_eur_num_terminator: Properties as functions. + (line 66) * uc_is_property_bidi_hebrew_right_to_left: Properties as functions. - (line 61) + (line 62) * uc_is_property_bidi_left_to_right: Properties as functions. - (line 60) + (line 61) * uc_is_property_bidi_non_spacing_mark: Properties as functions. - (line 71) + (line 72) * uc_is_property_bidi_other_neutral: Properties as functions. - (line 75) + (line 76) * uc_is_property_bidi_pdf: Properties as functions. - (line 73) + (line 74) * uc_is_property_bidi_segment_separator: Properties as functions. - (line 69) -* uc_is_property_bidi_whitespace: Properties as functions. (line 70) +* uc_is_property_bidi_whitespace: Properties as functions. + (line 71) * uc_is_property_cased: Properties as functions. - (line 29) -* uc_is_property_case_ignorable: Properties as functions. (line 30) +* uc_is_property_case_ignorable: Properties as functions. + (line 31) * uc_is_property_changes_when_casefolded: Properties as functions. - (line 34) -* uc_is_property_changes_when_casemapped: Properties as functions. (line 35) +* uc_is_property_changes_when_casemapped: Properties as functions. + (line 36) * uc_is_property_changes_when_lowercased: Properties as functions. - (line 31) + (line 32) * uc_is_property_changes_when_titlecased: Properties as functions. - (line 33) + (line 34) * uc_is_property_changes_when_uppercased: Properties as functions. - (line 32) + (line 33) * uc_is_property_combining: Properties as functions. - (line 110) + (line 120) * uc_is_property_composite: Properties as functions. - (line 111) + (line 121) * uc_is_property_currency_symbol: Properties as functions. - (line 105) + (line 115) * uc_is_property_dash: Properties as functions. - (line 97) + (line 107) * uc_is_property_decimal_digit: Properties as functions. - (line 112) + (line 122) * uc_is_property_default_ignorable_code_point: Properties as functions. (line 12) * uc_is_property_deprecated: Properties as functions. - (line 16) + (line 17) * uc_is_property_diacritic: Properties as functions. - (line 114) + (line 124) +* uc_is_property_emoji: Properties as functions. + (line 93) +* uc_is_property_emoji_component: Properties as functions. + (line 97) +* uc_is_property_emoji_modifier: Properties as functions. + (line 95) +* uc_is_property_emoji_modifier_base: Properties as functions. + (line 96) +* uc_is_property_emoji_presentation: Properties as functions. + (line 94) +* uc_is_property_extended_pictographic: Properties as functions. + (line 98) * uc_is_property_extender: Properties as functions. - (line 115) + (line 125) * uc_is_property_format_control: Properties as functions. - (line 96) + (line 106) * uc_is_property_grapheme_base: Properties as functions. - (line 52) -* uc_is_property_grapheme_extend: Properties as functions. (line 53) +* uc_is_property_grapheme_extend: Properties as functions. + (line 54) * uc_is_property_grapheme_link: Properties as functions. - (line 55) + (line 56) * uc_is_property_hex_digit: Properties as functions. - (line 79) + (line 80) * uc_is_property_hyphen: Properties as functions. - (line 98) + (line 108) * uc_is_property_ideographic: Properties as functions. - (line 84) + (line 85) * uc_is_property_ids_binary_operator: Properties as functions. - (line 87) -* uc_is_property_ids_trinary_operator: Properties as functions. (line 88) +* uc_is_property_ids_trinary_operator: Properties as functions. + (line 89) * uc_is_property_id_continue: Properties as functions. - (line 42) + (line 43) * uc_is_property_id_start: Properties as functions. - (line 40) + (line 41) * uc_is_property_ignorable_control: Properties as functions. - (line 116) + (line 126) * uc_is_property_iso_control: Properties as functions. - (line 95) + (line 105) * uc_is_property_join_control: Properties as functions. - (line 51) + (line 52) * uc_is_property_left_of_pair: Properties as functions. - (line 109) + (line 119) * uc_is_property_line_separator: Properties as functions. - (line 100) + (line 110) * uc_is_property_logical_order_exception: Properties as functions. - (line 17) + (line 18) * uc_is_property_lowercase: Properties as functions. - (line 26) + (line 27) * uc_is_property_math: Properties as functions. - (line 106) + (line 116) * uc_is_property_non_break: Properties as functions. - (line 94) + (line 104) * uc_is_property_not_a_character: Properties as functions. (line 11) * uc_is_property_numeric: Properties as functions. - (line 113) + (line 123) * uc_is_property_other_alphabetic: Properties as functions. (line 10) * uc_is_property_other_default_ignorable_code_point: Properties as functions. (line 14) * uc_is_property_other_grapheme_extend: Properties as functions. - (line 54) + (line 55) * uc_is_property_other_id_continue: Properties as functions. - (line 43) + (line 44) * uc_is_property_other_id_start: Properties as functions. - (line 41) + (line 42) * uc_is_property_other_lowercase: Properties as functions. - (line 27) + (line 28) * uc_is_property_other_math: Properties as functions. - (line 107) + (line 117) * uc_is_property_other_uppercase: Properties as functions. - (line 25) + (line 26) * uc_is_property_paired_punctuation: Properties as functions. - (line 108) + (line 118) * uc_is_property_paragraph_separator: Properties as functions. - (line 101) + (line 111) * uc_is_property_pattern_syntax: Properties as functions. - (line 47) + (line 48) * uc_is_property_pattern_white_space: Properties as functions. - (line 46) + (line 47) * uc_is_property_private_use: Properties as functions. - (line 19) + (line 20) * uc_is_property_punctuation: Properties as functions. - (line 99) + (line 109) * uc_is_property_quotation_mark: Properties as functions. - (line 102) + (line 112) * uc_is_property_radical: Properties as functions. - (line 86) + (line 87) +* uc_is_property_regional_indicator: Properties as functions. + (line 127) * uc_is_property_sentence_terminal: Properties as functions. - (line 103) + (line 113) * uc_is_property_soft_dotted: Properties as functions. - (line 36) + (line 37) * uc_is_property_space: Properties as functions. - (line 93) + (line 103) * uc_is_property_terminal_punctuation: Properties as functions. - (line 104) + (line 114) * uc_is_property_titlecase: Properties as functions. - (line 28) + (line 29) * uc_is_property_unassigned_code_value: Properties as functions. - (line 20) + (line 21) * uc_is_property_unified_ideograph: Properties as functions. - (line 85) + (line 86) * uc_is_property_uppercase: Properties as functions. - (line 24) + (line 25) * uc_is_property_variation_selector: Properties as functions. - (line 18) + (line 19) * uc_is_property_white_space: Properties as functions. (line 8) * uc_is_property_xid_continue: Properties as functions. - (line 45) + (line 46) * uc_is_property_xid_start: Properties as functions. - (line 44) + (line 45) * uc_is_property_zero_width: Properties as functions. - (line 92) + (line 102) * uc_is_punct: Classifications like in ISO C. (line 43) * uc_is_script: Scripts. (line 30) @@ -6556,9 +6719,9 @@ Index (line 59) * uc_java_ident_category: ISO C and Java syntax. (line 42) -* uc_joining_group: Joining group. (line 85) -* uc_joining_group_byname: Joining group. (line 76) -* uc_joining_group_name: Joining group. (line 73) +* uc_joining_group: Joining group. (line 132) +* uc_joining_group_byname: Joining group. (line 123) +* uc_joining_group_name: Joining group. (line 120) * uc_joining_type: Joining type. (line 54) * uc_joining_type_byname: Joining type. (line 45) * uc_joining_type_long_name: Joining type. (line 42) @@ -6568,9 +6731,9 @@ Index * uc_mirror_char: Mirrored character. (line 13) * uc_numeric_value: Numeric value. (line 21) * uc_property_byname: Properties as objects. - (line 128) + (line 138) * uc_property_is_valid: Properties as objects. - (line 143) + (line 153) * uc_property_t: Properties as objects. (line 8) * uc_script: Scripts. (line 19) @@ -6590,23 +6753,23 @@ Index * ulc_asnprintf: unistdio.h. (line 49) * ulc_asprintf: unistdio.h. (line 47) * ulc_casecmp: Case insensitive comparison. - (line 60) + (line 75) * ulc_casecoll: Case insensitive comparison. - (line 106) + (line 135) * ulc_casexfrm: Case insensitive comparison. - (line 83) -* ulc_fprintf: unistdio.h. (line 184) + (line 105) +* ulc_fprintf: unistdio.h. (line 200) * ulc_grapheme_breaks: Grapheme cluster breaks in a string. - (line 46) -* ulc_possible_linebreaks: unilbrk.h. (line 48) + (line 51) +* ulc_possible_linebreaks: unilbrk.h. (line 53) * ulc_snprintf: unistdio.h. (line 44) * ulc_sprintf: unistdio.h. (line 42) -* ulc_vasnprintf: unistdio.h. (line 61) -* ulc_vasprintf: unistdio.h. (line 58) -* ulc_vfprintf: unistdio.h. (line 185) -* ulc_vsnprintf: unistdio.h. (line 55) -* ulc_vsprintf: unistdio.h. (line 52) -* ulc_width_linebreaks: unilbrk.h. (line 68) +* ulc_vasnprintf: unistdio.h. (line 63) +* ulc_vasprintf: unistdio.h. (line 59) +* ulc_vfprintf: unistdio.h. (line 201) +* ulc_vsnprintf: unistdio.h. (line 56) +* ulc_vsprintf: unistdio.h. (line 53) +* ulc_width_linebreaks: unilbrk.h. (line 76) * ulc_wordbreaks: Word breaks in a string. (line 11) * Unicode: Unicode. (line 6) @@ -6640,9 +6803,9 @@ Index * uninorm_filter_create: Normalization of streams. (line 16) * uninorm_filter_flush: Normalization of streams. - (line 32) + (line 33) * uninorm_filter_free: Normalization of streams. - (line 42) + (line 43) * uninorm_filter_write: Normalization of streams. (line 27) * uninorm_is_compat_decomposing: Normalization of strings. @@ -6680,92 +6843,93 @@ Index Tag Table: Node: Top269 -Node: Introduction3950 -Node: Unicode5971 -Node: Unicode and i18n7856 -Node: Locale encodings9518 -Node: In-memory representation11783 -Node: char * strings13781 -Node: Unicode strings19268 -Node: Conventions20451 -Node: unitypes.h22743 -Node: unistr.h23840 -Node: Elementary string checks24405 -Node: Elementary string conversions25027 -Node: Elementary string functions26905 -Node: Iterating27310 -Node: Creating Unicode strings30140 -Node: Copying Unicode strings31058 -Node: Comparing Unicode strings32671 -Node: Searching for a character34226 -Node: Counting characters35025 -Node: Elementary string functions with memory allocation35708 -Node: Elementary string functions on NUL terminated strings36330 -Node: Iterating over a NUL terminated Unicode string36929 -Node: Length39197 -Node: Copying a NUL terminated Unicode string40255 -Node: Comparing NUL terminated Unicode strings43359 -Node: Duplicating a NUL terminated Unicode string45455 -Node: Searching for a character in a NUL terminated Unicode string46224 -Node: Searching for a substring48988 -Node: Tokenizing50511 -Node: uniconv.h51384 -Node: unistdio.h59337 -Node: uniname.h67590 -Node: unictype.h68996 -Node: General category69924 -Node: Object oriented API70979 -Node: Bit mask API80820 -Node: Canonical combining class83115 -Node: Bidi class87349 -Node: Decimal digit value90762 -Node: Digit value91319 -Node: Numeric value91880 -Node: Mirrored character92782 -Node: Arabic shaping93475 -Node: Joining type93948 -Node: Joining group96098 -Node: Properties99536 -Node: Properties as objects100227 -Node: Properties as functions107249 -Node: Scripts113265 -Node: Blocks114670 -Node: ISO C and Java syntax116013 -Node: Classifications like in ISO C117731 -Node: uniwidth.h120543 -Node: unigbrk.h122589 -Node: Grapheme cluster breaks in a string124083 -Node: Grapheme cluster break property127018 -Node: uniwbrk.h129263 -Node: Word breaks in a string129801 -Node: Word break property130893 -Node: unilbrk.h132220 -Node: uninorm.h136516 -Node: Decomposition of characters137153 -Node: Composition of characters140934 -Node: Normalization of strings141647 -Node: Normalizing comparisons143820 -Node: Normalization of streams146318 -Node: unicase.h148443 -Node: Case mappings of characters149132 -Node: Case mappings of strings151281 -Node: Case mappings of substrings154920 -Node: Case insensitive comparison162130 -Node: Case detection167823 -Node: uniregex.h171137 -Node: Using the library171364 -Node: Installation171775 -Node: Compiler options172263 -Node: Include files173903 -Node: Autoconf macro175156 -Node: Reporting problems176796 -Node: More functionality177614 -Node: The wchar_t mess178065 -Node: Licenses180403 -Node: GNU GPL182832 -Node: GNU LGPL220577 -Node: GNU FDL229060 -Node: Index254369 +Node: Introduction4027 +Node: Unicode6048 +Node: Unicode and i18n7937 +Node: Locale encodings9599 +Node: In-memory representation11864 +Node: char * strings13862 +Node: Unicode strings19350 +Node: Conventions20533 +Node: unitypes.h22825 +Node: unistr.h23922 +Node: Elementary string checks24487 +Node: Elementary string conversions25109 +Node: Elementary string functions26987 +Node: Iterating27392 +Node: Creating Unicode strings30222 +Node: Copying Unicode strings31158 +Node: Comparing Unicode strings32771 +Node: Searching for a character34326 +Node: Counting characters35125 +Node: Elementary string functions with memory allocation35808 +Node: Elementary string functions on NUL terminated strings36430 +Node: Iterating over a NUL terminated Unicode string37029 +Node: Length39297 +Node: Copying a NUL terminated Unicode string40355 +Node: Comparing NUL terminated Unicode strings43459 +Node: Duplicating a NUL terminated Unicode string45555 +Node: Searching for a character in a NUL terminated Unicode string46324 +Node: Searching for a substring49088 +Node: Tokenizing50611 +Node: uniconv.h51484 +Node: unistdio.h59497 +Node: uniname.h67750 +Node: unictype.h69156 +Node: General category70084 +Node: Object oriented API71139 +Node: Bit mask API80980 +Node: Canonical combining class83275 +Node: Bidi class87510 +Node: Decimal digit value91305 +Node: Digit value91862 +Node: Numeric value92423 +Node: Mirrored character93325 +Node: Arabic shaping94018 +Node: Joining type94491 +Node: Joining group96641 +Node: Properties102453 +Node: Properties as objects103144 +Node: Properties as functions110625 +Node: Scripts117142 +Node: Blocks118547 +Node: ISO C and Java syntax119890 +Node: Classifications like in ISO C121608 +Node: uniwidth.h124420 +Node: unigbrk.h126466 +Node: Grapheme cluster breaks in a string127960 +Node: Grapheme cluster break property130979 +Node: uniwbrk.h133225 +Node: Word breaks in a string133763 +Node: Word break property134855 +Node: unilbrk.h136183 +Node: uninorm.h140735 +Node: Decomposition of characters141372 +Node: Composition of characters145153 +Node: Normalization of strings145866 +Node: Normalizing comparisons148039 +Node: Normalization of streams150537 +Node: unicase.h152662 +Node: Case mappings of characters153351 +Node: Case mappings of strings155500 +Node: Case mappings of substrings159139 +Node: Case insensitive comparison166409 +Node: Case detection172102 +Node: uniregex.h175416 +Node: Using the library175643 +Node: Installation176054 +Node: Compiler options176542 +Node: Include files178182 +Node: Autoconf macro179435 +Node: Reporting problems181076 +Node: More functionality181886 +Node: The wchar_t mess182338 +Node: The char32_t problem184688 +Node: Licenses187063 +Node: GNU GPL189536 +Node: GNU LGPL227285 +Node: GNU FDL235769 +Node: Index261080 End Tag Table |