utf16.h

linux下开源浏览器WebKit的源码,市面上的很多商用浏览器都是移植自WebKit

        (s)[(i)++]=(uint16_t)(c); \
    } else if((uint32_t)(c)<=0x10ffff && (i)+1<(capacity)) { \
        (s)[(i)++]=(uint16_t)(((c)>>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, i<length
 * @param length string length
 * @see U16_FWD_1_UNSAFE
 * @stable ICU 2.4
 */
#define U16_FWD_1(s, i, length) { \
    if(U16_IS_LEAD((s)[(i)++]) && (i)<(length) && U16_IS_TRAIL((s)[i])) { \
        ++(i); \
    } \
}

/**
 * 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.)
 * "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_FWD_N
 * @stable ICU 2.4
 */
#define U16_FWD_N_UNSAFE(s, i, n) { \
    int32_t __N=(n); \
    while(__N>0) { \
        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, i<length
 * @param length string length
 * @param n number of code points to skip
 * @see U16_FWD_N_UNSAFE
 * @stable ICU 2.4
 */
#define U16_FWD_N(s, i, length, n) { \
    int32_t __N=(n); \
    while(__N>0 && (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, 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, start<=i
 * @param c output UChar32 variable
 * @see U16_PREV_UNSAFE
 * @stable ICU 2.4
 */
#define U16_PREV(s, start, i, c) { \
    (c)=(s)[--(i)]; \
    if(U16_IS_TRAIL(c)) { \
        uint16_t __c2; \
        if((i)>(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, start<=i
 * @see U16_BACK_1_UNSAFE
 * @stable ICU 2.4
 */
#define U16_BACK_1(s, start, i) { \
    if(U16_IS_TRAIL((s)[--(i)]) && (i)>(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, i<length
 * @param n number of code points to skip
 * @see U16_BACK_N_UNSAFE
 * @stable ICU 2.4
 */
#define U16_BACK_N(s, start, i, n) { \
    int32_t __N=(n); \
    while(__N>0 && (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