Update ICU to 54.1 step 1

source/common/unicode/utf8.h

 /*
 *******************************************************************************
 *
-*   Copyright (C) 1999-2013, International Business Machines
+*   Copyright (C) 1999-2014, International Business Machines
 *   Corporation and others.  All Rights Reserved.
 *
 *******************************************************************************
 *   file name:  utf8.h
 *   encoding:   US-ASCII
 *   tab size:   8 (not used)
 *   indentation:4
 *
 *   created on: 1999sep13
 *   created by: Markus W. Scherer
@@ skipping 56 matching lines @@
  * leadByte is evaluated multiple times.
  *
  * The pre-ICU 50 implementation used the exported array utf8_countTrailBytes:
  * #define U8_COUNT_TRAIL_BYTES(leadByte) (utf8_countTrailBytes[leadByte])
  * leadByte was evaluated exactly once.
  *
  * @param leadByte The first byte of a UTF-8 sequence. Must be 0..0xff.
  * @internal
  */
 #define U8_COUNT_TRAIL_BYTES(leadByte) \
-    ((leadByte)<0xf0 ? \
-        ((leadByte)>=0xc0)+((leadByte)>=0xe0) : \
-        (leadByte)<0xfe ? 3+((leadByte)>=0xf8)+((leadByte)>=0xfc) : 0)
+    ((uint8_t)(leadByte)<0xf0 ? \
+        ((uint8_t)(leadByte)>=0xc0)+((uint8_t)(leadByte)>=0xe0) : \
+        (uint8_t)(leadByte)<0xfe ? 3+((uint8_t)(leadByte)>=0xf8)+((uint8_t)(leadByte)>=0xfc) : 0)
 
 /**
  * Counts the trail bytes for a UTF-8 lead byte of a valid UTF-8 sequence.
  * The maximum supported lead byte is 0xf4 corresponding to U+10FFFF.
  * leadByte might be evaluated multiple times.
  *
  * This is internal since it is not meant to be called directly by external clients;
  * however it is called by public macros in this file and thus must remain stable.
  *
  * @param leadByte The first byte of a UTF-8 sequence. Must be 0..0xff.
@@ skipping 152 matching lines @@
  * @param c output UChar32 variable, set to <0 in case of an error
  * @see U8_GET_UNSAFE
  * @stable ICU 2.4
  */
 #define U8_GET(s, start, i, length, c) { \
     int32_t _u8_get_index=(i); \
     U8_SET_CP_START(s, start, _u8_get_index); \
     U8_NEXT(s, _u8_get_index, length, c); \
 }
 
-#ifndef U_HIDE_DRAFT_API
 /**
  * Get a code point from a string at a random-access offset,
  * without changing the offset.
  * The offset may point to either the lead byte or one of the trail bytes
  * for a code point, in which case the macro will read all of the bytes
  * for the code point.
  *
  * The length can be negative for a NUL-terminated string.
  *
  * If the offset points to an illegal UTF-8 byte sequence, then
  * c is set to U+FFFD.
  * Iteration through a string is more efficient with U8_NEXT_UNSAFE or U8_NEXT_OR_FFFD.
  *
  * This macro does not distinguish between a real U+FFFD in the text
  * and U+FFFD returned for an ill-formed sequence.
  * Use U8_GET() if that distinction is important.
  *
  * @param s const uint8_t * string
  * @param start int32_t starting string offset
  * @param i int32_t string offset, must be start<=i<length
  * @param length int32_t string length
  * @param c output UChar32 variable, set to U+FFFD in case of an error
  * @see U8_GET
- * @draft ICU 51
+ * @stable ICU 51
  */
 #define U8_GET_OR_FFFD(s, start, i, length, c) { \
     int32_t _u8_get_index=(i); \
     U8_SET_CP_START(s, start, _u8_get_index); \
     U8_NEXT_OR_FFFD(s, _u8_get_index, length, c); \
 }
-#endif /* U_HIDE_DRAFT_API */
 
 /* 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-8.
  *
  * The offset may point to the lead byte of a multi-byte sequence,
@@ skipping 63 matching lines @@
         ) { \
             (c)=(((c)&0x1f)<<6)|__t1; \
             ++(i); \
         } else { \
             /* function call for "complicated" and error cases */ \
             (c)=utf8_nextCharSafeBody((const uint8_t *)s, &(i), (length), c, -1); \
         } \
     } \
 }
 
-#ifndef U_HIDE_DRAFT_API
 /**
  * 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, checks for illegal sequences and for string boundaries.
  *
  * The length can be negative for a NUL-terminated string.
  *
  * The offset may point to the lead byte of a multi-byte sequence,
  * in which case the macro will read the whole sequence.
  * If the offset points to a trail byte or an illegal UTF-8 sequence, then
  * c is set to U+FFFD.
  *
  * This macro does not distinguish between a real U+FFFD in the text
  * and U+FFFD returned for an ill-formed sequence.
  * Use U8_NEXT() if that distinction is important.
  *
  * @param s const uint8_t * string
  * @param i int32_t string offset, must be i<length
  * @param length int32_t string length
  * @param c output UChar32 variable, set to U+FFFD in case of an error
  * @see U8_NEXT
- * @draft ICU 51
+ * @stable ICU 51
  */
 #define U8_NEXT_OR_FFFD(s, i, length, c) { \
     (c)=(uint8_t)(s)[(i)++]; \
     if((c)>=0x80) { \
         uint8_t __t1, __t2; \
         if( /* handle U+1000..U+CFFF inline */ \
             (0xe0<(c) && (c)<=0xec) && \
             (((i)+1)<(length) || (length)<0) && \
             (__t1=(uint8_t)((s)[i]-0x80))<=0x3f && \
             (__t2=(uint8_t)((s)[(i)+1]-0x80))<= 0x3f \
         ) { \
             /* no need for (c&0xf) because the upper bits are truncated after <<12 in the cast to (UChar) */ \
             (c)=(UChar)(((c)<<12)|(__t1<<6)|__t2); \
             (i)+=2; \
         } else if( /* handle U+0080..U+07FF inline */ \
             ((c)<0xe0 && (c)>=0xc2) && \
             ((i)!=(length)) && \
             (__t1=(uint8_t)((s)[i]-0x80))<=0x3f \
         ) { \
             (c)=(((c)&0x1f)<<6)|__t1; \
             ++(i); \
         } else { \
             /* function call for "complicated" and error cases */ \
             (c)=utf8_nextCharSafeBody((const uint8_t *)s, &(i), (length), c, -3); \
         } \
     } \
 }
-#endif /* U_HIDE_DRAFT_API */
 
 /**
  * Append a code point to a string, overwriting 1 to 4 bytes.
  * The offset points to the current end of the string contents
  * and is advanced (post-increment).
  * "Unsafe" macro, assumes a valid code point and sufficient space in the string.
  * Otherwise, the result is undefined.
  *
  * @param s const uint8_t * string buffer
  * @param i string offset
@@ skipping 236 matching lines @@
  * @see U8_PREV_UNSAFE
  * @stable ICU 2.4
  */
 #define U8_PREV(s, start, i, c) { \
     (c)=(uint8_t)(s)[--(i)]; \
     if((c)>=0x80) { \
         (c)=utf8_prevCharSafeBody((const uint8_t *)s, start, &(i), c, -1); \
     } \
 }
 
-#ifndef U_HIDE_DRAFT_API
 /**
  * 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, checks for illegal sequences and for string boundaries.
  *
  * The input offset may be the same as the string length.
  * If the offset is behind a multi-byte sequence, then the macro will read
  * the whole sequence.
  * If the offset is behind a lead byte, then that itself
  * will be returned as the code point.
  * If the offset is behind an illegal UTF-8 sequence, then c is set to U+FFFD.
  *
  * This macro does not distinguish between a real U+FFFD in the text
  * and U+FFFD returned for an ill-formed sequence.
  * Use U8_PREV() if that distinction is important.
  *
  * @param s const uint8_t * string
  * @param start int32_t starting string offset (usually 0)
  * @param i int32_t string offset, must be start<i
  * @param c output UChar32 variable, set to U+FFFD in case of an error
  * @see U8_PREV
- * @draft ICU 51
+ * @stable ICU 51
  */
 #define U8_PREV_OR_FFFD(s, start, i, c) { \
     (c)=(uint8_t)(s)[--(i)]; \
     if((c)>=0x80) { \
         (c)=utf8_prevCharSafeBody((const uint8_t *)s, start, &(i), c, -3); \
     } \
 }
-#endif /* U_HIDE_DRAFT_API */
 
 /**
  * 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-8.
  *
  * @param s const uint8_t * string
  * @param i string offset
  * @see U8_BACK_1
@@ skipping 100 matching lines @@
  * @stable ICU 2.4
  */
 #define U8_SET_CP_LIMIT(s, start, i, length) { \
     if((start)<(i) && ((i)<(length) || ((length)<0 && (s)[i]!=0))) { \
         U8_BACK_1(s, start, i); \
         U8_FWD_1(s, i, length); \
     } \
 }
 
 #endif