Lines Matching refs:utf
228 /* There is a proposed future special "UTF-21" mode, in which only the lowest
229 21 bits of a 32-bit character are interpreted as UTF, with the remaining 11
243 /* When UTF encoding is being used, a character is no longer just a single
246 complicated ones for UTF characters. GETCHARLENTEST and other macros are not
247 used when UTF is not supported. To make sure they can never even appear when
248 UTF support is omitted, we don't even define them. */
273 #define MAYBE_UTF_MULTI /* UTF chars may use multiple code units */
275 /* The largest UTF code point that can be encoded as a single code unit. */
288 /* Returns TRUE, if the given value is not the first code unit of a UTF
293 /* Get the next UTF-8 character, not advancing the pointer. This is called when
294 we know we are in UTF-8 mode. */
300 /* Get the next UTF-8 character, testing for UTF-8 mode, and not advancing the
305 if (utf && c >= 0xc0u) GETUTF8(c, eptr);
307 /* Get the next UTF-8 character, advancing the pointer. This is called when we
308 know we are in UTF-8 mode. */
314 /* Get the next character, testing for UTF-8 mode, and advancing the pointer.
315 This is called when we don't know if we are in UTF-8 mode. */
319 if (utf && c >= 0xc0u) GETUTF8INC(c, eptr);
321 /* Get the next UTF-8 character, not advancing the pointer, incrementing length
322 if there are extra bytes. This is called when we know we are in UTF-8 mode. */
328 /* Get the next UTF-8 character, testing for UTF-8 mode, not advancing the
330 do not know if we are in UTF-8 mode. */
334 if (utf && c >= 0xc0u) GETUTF8LEN(c, eptr, len);
337 it is. This is called only in UTF-8 mode - we don't put a test within the macro
338 because almost all calls are already within a block of UTF-8 only code. */
352 #define PUTCHAR(c, p) ((utf && c > MAX_UTF_SINGLE_CU)? \
359 #define MAYBE_UTF_MULTI /* UTF chars may use multiple code units */
361 /* The largest UTF code point that can be encoded as a single code unit. */
374 /* Returns TRUE, if the given value is not the first code unit of a UTF
379 /* Base macro to pick up the low surrogate of a UTF-16 character, not
385 /* Get the next UTF-16 character, not advancing the pointer. This is called when
386 we know we are in UTF-16 mode. */
392 /* Get the next UTF-16 character, testing for UTF-16 mode, and not advancing the
397 if (utf && (c & 0xfc00u) == 0xd800u) GETUTF16(c, eptr);
399 /* Base macro to pick up the low surrogate of a UTF-16 character, advancing
405 /* Get the next UTF-16 character, advancing the pointer. This is called when we
406 know we are in UTF-16 mode. */
412 /* Get the next character, testing for UTF-16 mode, and advancing the pointer.
413 This is called when we don't know if we are in UTF-16 mode. */
417 if (utf && (c & 0xfc00u) == 0xd800u) GETUTF16INC(c, eptr);
419 /* Base macro to pick up the low surrogate of a UTF-16 character, not
425 /* Get the next UTF-16 character, not advancing the pointer, incrementing
427 UTF-16 mode. */
433 /* Get the next UTF-816character, testing for UTF-16 mode, not advancing the
435 we do not know if we are in UTF-16 mode. */
439 if (utf && (c & 0xfc00u) == 0xd800u) GETUTF16LEN(c, eptr, len);
442 it is. This is called only in UTF-16 mode - we don't put a test within the
443 macro because almost all calls are already within a block of UTF-16 only
458 #define PUTCHAR(c, p) ((utf && c > MAX_UTF_SINGLE_CU)? \
466 /* These are trivial for the 32-bit library, since all UTF-32 characters fit
474 /* Get the next UTF-32 character, not advancing the pointer. This is called when
475 we know we are in UTF-32 mode. */
480 /* Get the next UTF-32 character, testing for UTF-32 mode, and not advancing the
486 /* Get the next UTF-32 character, advancing the pointer. This is called when we
487 know we are in UTF-32 mode. */
492 /* Get the next character, testing for UTF-32 mode, and advancing the pointer.
493 This is called when we don't know if we are in UTF-32 mode. */
498 /* Get the next UTF-32 character, not advancing the pointer, not incrementing
499 length (since all UTF-32 is of length 1). This is called when we know we are in
500 UTF-32 mode. */
505 /* Get the next UTF-32character, testing for UTF-32 mode, not advancing the
506 pointer, not incrementing the length (since all UTF-32 is of length 1).
507 This is called when we do not know if we are in UTF-32 mode. */
513 it is. This is called only in UTF-32 mode - we don't put a test within the
514 macro because almost all calls are already within a block of UTF-32 only
517 These are all no-ops since all UTF-32 characters fit into one pcre_uchar. */
534 #endif /* UTF-32 character handling */
