>10)+0xd7c0)
/**
* Get the trail surrogate (0xdc00..0xdfff) for a
* supplementary code point (0x10000..0x10ffff).
* @param supplementary 32-bit code point (U+10000..U+10ffff)
* @return trail surrogate (U+dc00..U+dfff) for supplementary
* @stable ICU 2.4
*/
#define U16_TRAIL(supplementary) (UChar)(((supplementary)&0x3ff)|0xdc00)
/**
* How many 16-bit code units are used to encode this Unicode code point? (1 or 2)
* The result is not defined if c is not a Unicode code point (U+0000..U+10ffff).
* @param c 32-bit code point
* @return 1 or 2
* @stable ICU 2.4
*/
#define U16_LENGTH(c) ((uint32_t)(c)<=0xffff ? 1 : 2)
/**
* The maximum number of 16-bit code units per Unicode code point (U+0000..U+10ffff).
* @return 2
* @stable ICU 2.4
*/
#define U16_MAX_LENGTH 2
/**
* Get a code point from a string at a random-access offset,
* without changing the offset.
* "Unsafe" macro, assumes well-formed UTF-16.
*
* The offset may point to either the lead or trail surrogate unit
* for a supplementary code point, in which case the macro will read
* the adjacent matching surrogate as well.
* The result is undefined if the offset points to a single, unpaired surrogate.
* Iteration through a string is more efficient with U16_NEXT_UNSAFE or U16_NEXT.
*
* @param s const UChar * string
* @param i string offset
* @param c output UChar32 variable
* @see U16_GET
* @stable ICU 2.4
*/
#define U16_GET_UNSAFE(s, i, c) { \
(c)=(s)[i]; \
if(U16_IS_SURROGATE(c)) { \
if(U16_IS_SURROGATE_LEAD(c)) { \
(c)=U16_GET_SUPPLEMENTARY((c), (s)[(i)+1]); \
} else { \
(c)=U16_GET_SUPPLEMENTARY((s)[(i)-1], (c)); \
} \
} \
}
/**
* Get a code point from a string at a random-access offset,
* without changing the offset.
* "Safe" macro, handles unpaired surrogates and checks for string boundaries.
*
* The offset may point to either the lead or trail surrogate unit
* for a supplementary code point, in which case the macro will read
* the adjacent matching surrogate as well.
* If the offset points to a single, unpaired surrogate, then that itself
* will be returned as the code point.
* Iteration through a string is more efficient with U16_NEXT_UNSAFE or U16_NEXT.
*
* @param s const UChar * string
* @param start starting string offset (usually 0)
* @param i string offset, must be start<=i(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \
(c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \
} \
} \
} \
}
/* definitions with forward iteration --------------------------------------- */
/**
* Get a code point from a string at a code point boundary offset,
* and advance the offset to the next code point boundary.
* (Post-incrementing forward iteration.)
* "Unsafe" macro, assumes well-formed UTF-16.
*
* The offset may point to the lead surrogate unit
* for a supplementary code point, in which case the macro will read
* the following trail surrogate as well.
* If the offset points to a trail surrogate, then that itself
* will be returned as the code point.
* The result is undefined if the offset points to a single, unpaired lead surrogate.
*
* @param s const UChar * string
* @param i string offset
* @param c output UChar32 variable
* @see U16_NEXT
* @stable ICU 2.4
*/
#define U16_NEXT_UNSAFE(s, i, c) { \
(c)=(s)[(i)++]; \
if(U16_IS_LEAD(c)) { \
(c)=U16_GET_SUPPLEMENTARY((c), (s)[(i)++]); \
} \
}
/**
* Get a code point from a string at a code point boundary offset,
* and advance the offset to the next code point boundary.
* (Post-incrementing forward iteration.)
* "Safe" macro, handles unpaired surrogates and checks for string boundaries.
*
* The offset may point to the lead surrogate unit
* for a supplementary code point, in which case the macro will read
* the following trail surrogate as well.
* If the offset points to a trail surrogate or
* to a single, unpaired lead surrogate, then that itself
* will be returned as the code point.
*
* @param s const UChar * string
* @param i string offset, must be i>10)+0xd7c0); \
(s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \
} \
}
/**
* Append a code point to a string, overwriting 1 or 2 code units.
* The offset points to the current end of the string contents
* and is advanced (post-increment).
* "Safe" macro, checks for a valid code point.
* If a surrogate pair is written, checks for sufficient space in the string.
* If the code point is not valid or a trail surrogate does not fit,
* then isError is set to TRUE.
*
* @param s const UChar * string buffer
* @param i string offset, must be i>10)+0xd7c0); \
(s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \
} else /* c>0x10ffff or not enough space */ { \
(isError)=TRUE; \
} \
}
/**
* Advance the string offset from one code point boundary to the next.
* (Post-incrementing iteration.)
* "Unsafe" macro, assumes well-formed UTF-16.
*
* @param s const UChar * string
* @param i string offset
* @see U16_FWD_1
* @stable ICU 2.4
*/
#define U16_FWD_1_UNSAFE(s, i) { \
if(U16_IS_LEAD((s)[(i)++])) { \
++(i); \
} \
}
/**
* Advance the string offset from one code point boundary to the next.
* (Post-incrementing iteration.)
* "Safe" macro, handles unpaired surrogates and checks for string boundaries.
*
* @param s const UChar * string
* @param i string offset, must be i0) { \
U16_FWD_1_UNSAFE(s, i); \
--__N; \
} \
}
/**
* Advance the string offset from one code point boundary to the n-th next one,
* i.e., move forward by n code points.
* (Post-incrementing iteration.)
* "Safe" macro, handles unpaired surrogates and checks for string boundaries.
*
* @param s const UChar * string
* @param i string offset, must be i0 && (i)<(length)) { \
U16_FWD_1(s, i, length); \
--__N; \
} \
}
/**
* Adjust a random-access offset to a code point boundary
* at the start of a code point.
* If the offset points to the trail surrogate of a surrogate pair,
* then the offset is decremented.
* Otherwise, it is not modified.
* "Unsafe" macro, assumes well-formed UTF-16.
*
* @param s const UChar * string
* @param i string offset
* @see U16_SET_CP_START
* @stable ICU 2.4
*/
#define U16_SET_CP_START_UNSAFE(s, i) { \
if(U16_IS_TRAIL((s)[i])) { \
--(i); \
} \
}
/**
* Adjust a random-access offset to a code point boundary
* at the start of a code point.
* If the offset points to the trail surrogate of a surrogate pair,
* then the offset is decremented.
* Otherwise, it is not modified.
* "Safe" macro, handles unpaired surrogates and checks for string boundaries.
*
* @param s const UChar * string
* @param start starting string offset (usually 0)
* @param i string offset, must be start<=i
* @see U16_SET_CP_START_UNSAFE
* @stable ICU 2.4
*/
#define U16_SET_CP_START(s, start, i) { \
if(U16_IS_TRAIL((s)[i]) && (i)>(start) && U16_IS_LEAD((s)[(i)-1])) { \
--(i); \
} \
}
/* definitions with backward iteration -------------------------------------- */
/**
* Move the string offset from one code point boundary to the previous one
* and get the code point between them.
* (Pre-decrementing backward iteration.)
* "Unsafe" macro, assumes well-formed UTF-16.
*
* The input offset may be the same as the string length.
* If the offset is behind a trail surrogate unit
* for a supplementary code point, then the macro will read
* the preceding lead surrogate as well.
* If the offset is behind a lead surrogate, then that itself
* will be returned as the code point.
* The result is undefined if the offset is behind a single, unpaired trail surrogate.
*
* @param s const UChar * string
* @param i string offset
* @param c output UChar32 variable
* @see U16_PREV
* @stable ICU 2.4
*/
#define U16_PREV_UNSAFE(s, i, c) { \
(c)=(s)[--(i)]; \
if(U16_IS_TRAIL(c)) { \
(c)=U16_GET_SUPPLEMENTARY((s)[--(i)], (c)); \
} \
}
/**
* Move the string offset from one code point boundary to the previous one
* and get the code point between them.
* (Pre-decrementing backward iteration.)
* "Safe" macro, handles unpaired surrogates and checks for string boundaries.
*
* The input offset may be the same as the string length.
* If the offset is behind a trail surrogate unit
* for a supplementary code point, then the macro will read
* the preceding lead surrogate as well.
* If the offset is behind a lead surrogate or behind a single, unpaired
* trail surrogate, then that itself
* will be returned as the code point.
*
* @param s const UChar * string
* @param start starting string offset (usually 0)
* @param i string offset, must be start(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \
--(i); \
(c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \
} \
} \
}
/**
* Move the string offset from one code point boundary to the previous one.
* (Pre-decrementing backward iteration.)
* The input offset may be the same as the string length.
* "Unsafe" macro, assumes well-formed UTF-16.
*
* @param s const UChar * string
* @param i string offset
* @see U16_BACK_1
* @stable ICU 2.4
*/
#define U16_BACK_1_UNSAFE(s, i) { \
if(U16_IS_TRAIL((s)[--(i)])) { \
--(i); \
} \
}
/**
* Move the string offset from one code point boundary to the previous one.
* (Pre-decrementing backward iteration.)
* The input offset may be the same as the string length.
* "Safe" macro, handles unpaired surrogates and checks for string boundaries.
*
* @param s const UChar * string
* @param start starting string offset (usually 0)
* @param i string offset, must be start(start) && U16_IS_LEAD((s)[(i)-1])) { \
--(i); \
} \
}
/**
* Move the string offset from one code point boundary to the n-th one before it,
* i.e., move backward by n code points.
* (Pre-decrementing backward iteration.)
* The input offset may be the same as the string length.
* "Unsafe" macro, assumes well-formed UTF-16.
*
* @param s const UChar * string
* @param i string offset
* @param n number of code points to skip
* @see U16_BACK_N
* @stable ICU 2.4
*/
#define U16_BACK_N_UNSAFE(s, i, n) { \
int32_t __N=(n); \
while(__N>0) { \
U16_BACK_1_UNSAFE(s, i); \
--__N; \
} \
}
/**
* Move the string offset from one code point boundary to the n-th one before it,
* i.e., move backward by n code points.
* (Pre-decrementing backward iteration.)
* The input offset may be the same as the string length.
* "Safe" macro, handles unpaired surrogates and checks for string boundaries.
*
* @param s const UChar * string
* @param start start of string
* @param i string offset, must be start0 && (i)>(start)) { \
U16_BACK_1(s, start, i); \
--__N; \
} \
}
/**
* Adjust a random-access offset to a code point boundary after a code point.
* If the offset is behind the lead surrogate of a surrogate pair,
* then the offset is incremented.
* Otherwise, it is not modified.
* The input offset may be the same as the string length.
* "Unsafe" macro, assumes well-formed UTF-16.
*
* @param s const UChar * string
* @param i string offset
* @see U16_SET_CP_LIMIT
* @stable ICU 2.4
*/
#define U16_SET_CP_LIMIT_UNSAFE(s, i) { \
if(U16_IS_LEAD((s)[(i)-1])) { \
++(i); \
} \
}
/**
* Adjust a random-access offset to a code point boundary after a code point.
* If the offset is behind the lead surrogate of a surrogate pair,
* then the offset is incremented.
* Otherwise, it is not modified.
* The input offset may be the same as the string length.
* "Safe" macro, handles unpaired surrogates and checks for string boundaries.
*
* @param s const UChar * string
* @param start starting string offset (usually 0)
* @param i string offset, start<=i<=length
* @param length string length
* @see U16_SET_CP_LIMIT_UNSAFE
* @stable ICU 2.4
*/
#define U16_SET_CP_LIMIT(s, start, i, length) { \
if((start)<(i) && (i)<(length) && U16_IS_LEAD((s)[(i)-1]) && U16_IS_TRAIL((s)[i])) { \
++(i); \
} \
}
#endif