Lines Matching refs:utf
82 /* We do not support both EBCDIC and UTF-8/16/32 at the same time. The "configure"
294 /* This is an unsigned int value that no character can ever have. UTF-8
316 &(NLBLOCK->nllen), utf)) \
330 &(NLBLOCK->nllen), utf)) \
585 /* There is a proposed future special "UTF-21" mode, in which only the lowest
586 21 bits of a 32-bit character are interpreted as UTF, with the remaining 11
600 /* When UTF encoding is being used, a character is no longer just a single
603 complicated ones for UTF characters. GETCHARLENTEST and other macros are not
604 used when UTF is not supported. To make sure they can never even appear when
605 UTF support is omitted, we don't even define them. */
629 /* Base macro to pick up the remaining bytes of a UTF-8 character, not
651 /* Base macro to pick up the remaining bytes of a UTF-8 character, advancing
706 of a UTF sequence. */
710 /* Get the next UTF-8 character, not advancing the pointer. This is called when
711 we know we are in UTF-8 mode. */
717 /* Get the next UTF-8 character, testing for UTF-8 mode, and not advancing the
722 if (utf && c >= 0xc0) GETUTF8(c, eptr);
724 /* Get the next UTF-8 character, advancing the pointer. This is called when we
725 know we are in UTF-8 mode. */
731 /* Get the next character, testing for UTF-8 mode, and advancing the pointer.
732 This is called when we don't know if we are in UTF-8 mode. */
736 if (utf && c >= 0xc0) GETUTF8INC(c, eptr);
738 /* Base macro to pick up the remaining bytes of a UTF-8 character, not
775 /* Get the next UTF-8 character, not advancing the pointer, incrementing length
776 if there are extra bytes. This is called when we know we are in UTF-8 mode. */
782 /* Get the next UTF-8 character, testing for UTF-8 mode, not advancing the
784 do not know if we are in UTF-8 mode. */
788 if (utf && c >= 0xc0) GETUTF8LEN(c, eptr, len);
791 it is. This is called only in UTF-8 mode - we don't put a test within the macro
792 because almost all calls are already within a block of UTF-8 only code. */
819 of a UTF sequence. */
823 /* Base macro to pick up the low surrogate of a UTF-16 character, not
829 /* Get the next UTF-16 character, not advancing the pointer. This is called when
830 we know we are in UTF-16 mode. */
836 /* Get the next UTF-16 character, testing for UTF-16 mode, and not advancing the
841 if (utf && (c & 0xfc00) == 0xd800) GETUTF16(c, eptr);
843 /* Base macro to pick up the low surrogate of a UTF-16 character, advancing
849 /* Get the next UTF-16 character, advancing the pointer. This is called when we
850 know we are in UTF-16 mode. */
856 /* Get the next character, testing for UTF-16 mode, and advancing the pointer.
857 This is called when we don't know if we are in UTF-16 mode. */
861 if (utf && (c & 0xfc00) == 0xd800) GETUTF16INC(c, eptr);
863 /* Base macro to pick up the low surrogate of a UTF-16 character, not
869 /* Get the next UTF-16 character, not advancing the pointer, incrementing
871 UTF-16 mode. */
877 /* Get the next UTF-816character, testing for UTF-16 mode, not advancing the
879 we do not know if we are in UTF-16 mode. */
883 if (utf && (c & 0xfc00) == 0xd800) GETUTF16LEN(c, eptr, len);
886 it is. This is called only in UTF-16 mode - we don't put a test within the
887 macro because almost all calls are already within a block of UTF-16 only
901 /* These are trivial for the 32-bit library, since all UTF-32 characters fit
908 /* Get the next UTF-32 character, not advancing the pointer. This is called when
909 we know we are in UTF-32 mode. */
914 /* Get the next UTF-32 character, testing for UTF-32 mode, and not advancing the
920 /* Get the next UTF-32 character, advancing the pointer. This is called when we
921 know we are in UTF-32 mode. */
926 /* Get the next character, testing for UTF-32 mode, and advancing the pointer.
927 This is called when we don't know if we are in UTF-32 mode. */
932 /* Get the next UTF-32 character, not advancing the pointer, not incrementing
933 length (since all UTF-32 is of length 1). This is called when we know we are in
934 UTF-32 mode. */
939 /* Get the next UTF-32character, testing for UTF-32 mode, not advancing the
940 pointer, not incrementing the length (since all UTF-32 is of length 1).
941 This is called when we do not know if we are in UTF-32 mode. */
947 it is. This is called only in UTF-32 mode - we don't put a test within the
948 macro because almost all calls are already within a block of UTF-32 only
950 These are all no-ops since all UTF-32 characters fit into one pcre_uchar. */
1165 /* If PCRE is to support UTF-8 on EBCDIC platforms, we cannot use normal
1167 which is different from their ASCII/UTF-8 code. Instead we define macros for
1168 the characters so that they always use the ASCII/UTF-8 code when UTF-8 support
1169 is enabled. When UTF-8 support is not enabled, the definitions use character
1174 EBCDIC, or UTF-8, but not both. To support both in the same compiled library
1184 /* UTF-8 support is not enabled; use the platform-dependent character literals
1185 so that PCRE works in both ASCII and EBCDIC environments, but only in non-UTF
1488 #define STRING_UTF_RIGHTPAR "UTF)"
1497 /* UTF-8 support is enabled; always use UTF-8 (=ASCII) character codes. This
1498 works in both modes non-EBCDIC platforms, and on EBCDIC platforms in UTF-8 mode
1831 used for [^] in JavaScript compatibility mode, and for \C in non-utf mode. In
1897 OP_ANYBYTE, /* 14 Match any byte (\C); different to OP_ANY for UTF-8 */
2185 in UTF-8 mode. The code that uses this table must know about such things. */
2205 2, 2, 2, 2, 2, 2, /* *I, *?I, +I, +?I, ?I, ??I ** UTF-8 */ \
2516 BOOL utf; /* UTF-8 / UTF-16 flag */
2717 (utf ? PRIV(strcmp_uc_uc_utf)((str1), (str2)) : PRIV(strcmp_uc_uc)((str1), (str2)))
2719 (utf ? PRIV(strcmp_uc_c8_utf)((str1), (str2)) : PRIV(strcmp_uc_c8)((str1), (str2)))
