You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@couchdb.apache.org by be...@apache.org on 2014/02/13 19:12:01 UTC
[03/57] [abbrv] remove couch_collate
http://git-wip-us.apache.org/repos/asf/couchdb/blob/81332b78/apps/couch_collate/platform/osx/icu/unicode/utf8.h
----------------------------------------------------------------------
diff --git a/apps/couch_collate/platform/osx/icu/unicode/utf8.h b/apps/couch_collate/platform/osx/icu/unicode/utf8.h
deleted file mode 100644
index 1142c44..0000000
--- a/apps/couch_collate/platform/osx/icu/unicode/utf8.h
+++ /dev/null
@@ -1,652 +0,0 @@
-/*
-*******************************************************************************
-*
-* Copyright (C) 1999-2007, 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
-*/
-
-/**
- * \file
- * \brief C API: 8-bit Unicode handling macros
- *
- * This file defines macros to deal with 8-bit Unicode (UTF-8) code units (bytes) and strings.
- * utf8.h is included by utf.h after unicode/umachine.h
- * and some common definitions.
- *
- * For more information see utf.h and the ICU User Guide Strings chapter
- * (http://icu-project.org/userguide/strings.html).
- *
- * <em>Usage:</em>
- * ICU coding guidelines for if() statements should be followed when using these macros.
- * Compound statements (curly braces {}) must be used for if-else-while...
- * bodies and all macro statements should be terminated with semicolon.
- */
-
-#ifndef __UTF8_H__
-#define __UTF8_H__
-
-/* utf.h must be included first. */
-#ifndef __UTF_H__
-# include "unicode/utf.h"
-#endif
-
-/* internal definitions ----------------------------------------------------- */
-
-/**
- * \var utf8_countTrailBytes
- * Internal array with numbers of trail bytes for any given byte used in
- * lead byte position.
- * @internal
- */
-#ifdef U_UTF8_IMPL
-U_EXPORT const uint8_t
-#elif defined(U_STATIC_IMPLEMENTATION) || defined(U_COMMON_IMPLEMENTATION)
-U_CFUNC const uint8_t
-#else
-U_CFUNC U_IMPORT const uint8_t /* U_IMPORT2? */ /*U_IMPORT*/
-#endif
-utf8_countTrailBytes[256];
-
-/**
- * Count the trail bytes for a UTF-8 lead byte.
- * @internal
- */
-#define U8_COUNT_TRAIL_BYTES(leadByte) (utf8_countTrailBytes[(uint8_t)leadByte])
-
-/**
- * Mask a UTF-8 lead byte, leave only the lower bits that form part of the code point value.
- * @internal
- */
-#define U8_MASK_LEAD_BYTE(leadByte, countTrailBytes) ((leadByte)&=(1<<(6-(countTrailBytes)))-1)
-
-/**
- * Function for handling "next code point" with error-checking.
- * @internal
- */
-U_INTERNAL UChar32 U_EXPORT2
-utf8_nextCharSafeBody(const uint8_t *s, int32_t *pi, int32_t length, UChar32 c, UBool strict);
-
-/**
- * Function for handling "append code point" with error-checking.
- * @internal
- */
-U_INTERNAL int32_t U_EXPORT2
-utf8_appendCharSafeBody(uint8_t *s, int32_t i, int32_t length, UChar32 c, UBool *pIsError);
-
-/**
- * Function for handling "previous code point" with error-checking.
- * @internal
- */
-U_INTERNAL UChar32 U_EXPORT2
-utf8_prevCharSafeBody(const uint8_t *s, int32_t start, int32_t *pi, UChar32 c, UBool strict);
-
-/**
- * Function for handling "skip backward one code point" with error-checking.
- * @internal
- */
-U_INTERNAL int32_t U_EXPORT2
-utf8_back1SafeBody(const uint8_t *s, int32_t start, int32_t i);
-
-/* single-code point definitions -------------------------------------------- */
-
-/**
- * Does this code unit (byte) encode a code point by itself (US-ASCII 0..0x7f)?
- * @param c 8-bit code unit (byte)
- * @return TRUE or FALSE
- * @stable ICU 2.4
- */
-#define U8_IS_SINGLE(c) (((c)&0x80)==0)
-
-/**
- * Is this code unit (byte) a UTF-8 lead byte?
- * @param c 8-bit code unit (byte)
- * @return TRUE or FALSE
- * @stable ICU 2.4
- */
-#define U8_IS_LEAD(c) ((uint8_t)((c)-0xc0)<0x3e)
-
-/**
- * Is this code unit (byte) a UTF-8 trail byte?
- * @param c 8-bit code unit (byte)
- * @return TRUE or FALSE
- * @stable ICU 2.4
- */
-#define U8_IS_TRAIL(c) (((c)&0xc0)==0x80)
-
-/**
- * How many code units (bytes) are used for the UTF-8 encoding
- * of this Unicode code point?
- * @param c 32-bit code point
- * @return 1..4, or 0 if c is a surrogate or not a Unicode code point
- * @stable ICU 2.4
- */
-#define U8_LENGTH(c) \
- ((uint32_t)(c)<=0x7f ? 1 : \
- ((uint32_t)(c)<=0x7ff ? 2 : \
- ((uint32_t)(c)<=0xd7ff ? 3 : \
- ((uint32_t)(c)<=0xdfff || (uint32_t)(c)>0x10ffff ? 0 : \
- ((uint32_t)(c)<=0xffff ? 3 : 4)\
- ) \
- ) \
- ) \
- )
-
-/**
- * The maximum number of UTF-8 code units (bytes) per Unicode code point (U+0000..U+10ffff).
- * @return 4
- * @stable ICU 2.4
- */
-#define U8_MAX_LENGTH 4
-
-/**
- * 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 result is undefined if the offset points to an illegal UTF-8
- * byte sequence.
- * Iteration through a string is more efficient with U8_NEXT_UNSAFE or U8_NEXT.
- *
- * @param s const uint8_t * string
- * @param i string offset
- * @param c output UChar32 variable
- * @see U8_GET
- * @stable ICU 2.4
- */
-#define U8_GET_UNSAFE(s, i, c) { \
- int32_t _u8_get_unsafe_index=(int32_t)(i); \
- U8_SET_CP_START_UNSAFE(s, _u8_get_unsafe_index); \
- U8_NEXT_UNSAFE(s, _u8_get_unsafe_index, c); \
-}
-
-/**
- * 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.
- * If the offset points to an illegal UTF-8 byte sequence, then
- * c is set to a negative value.
- * Iteration through a string is more efficient with U8_NEXT_UNSAFE or U8_NEXT.
- *
- * @param s const uint8_t * string
- * @param start starting string offset
- * @param i string offset, must be start<=i<length
- * @param length string length
- * @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=(int32_t)(i); \
- U8_SET_CP_START(s, start, _u8_get_index); \
- U8_NEXT(s, _u8_get_index, length, 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-8.
- *
- * The offset may point to the lead byte of a multi-byte sequence,
- * in which case the macro will read the whole sequence.
- * The result is undefined if the offset points to a trail byte
- * or an illegal UTF-8 sequence.
- *
- * @param s const uint8_t * string
- * @param i string offset
- * @param c output UChar32 variable
- * @see U8_NEXT
- * @stable ICU 2.4
- */
-#define U8_NEXT_UNSAFE(s, i, c) { \
- (c)=(uint8_t)(s)[(i)++]; \
- if((uint8_t)((c)-0xc0)<0x35) { \
- uint8_t __count=U8_COUNT_TRAIL_BYTES(c); \
- U8_MASK_LEAD_BYTE(c, __count); \
- switch(__count) { \
- /* each following branch falls through to the next one */ \
- case 3: \
- (c)=((c)<<6)|((s)[(i)++]&0x3f); \
- case 2: \
- (c)=((c)<<6)|((s)[(i)++]&0x3f); \
- case 1: \
- (c)=((c)<<6)|((s)[(i)++]&0x3f); \
- /* no other branches to optimize switch() */ \
- break; \
- } \
- } \
-}
-
-/**
- * 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 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 a negative value.
- *
- * @param s const uint8_t * string
- * @param i string offset, must be i<length
- * @param length string length
- * @param c output UChar32 variable, set to <0 in case of an error
- * @see U8_NEXT_UNSAFE
- * @stable ICU 2.4
- */
-#define U8_NEXT(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)) && \
- (__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)=(UChar)((((c)&0x1f)<<6)|__t1); \
- ++(i); \
- } else if(U8_IS_LEAD(c)) { \
- /* function call for "complicated" and error cases */ \
- (c)=utf8_nextCharSafeBody((const uint8_t *)s, &(i), (int32_t)(length), c, -1); \
- } else { \
- (c)=U_SENTINEL; \
- } \
- } \
-}
-
-/**
- * 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
- * @param c code point to append
- * @see U8_APPEND
- * @stable ICU 2.4
- */
-#define U8_APPEND_UNSAFE(s, i, c) { \
- if((uint32_t)(c)<=0x7f) { \
- (s)[(i)++]=(uint8_t)(c); \
- } else { \
- if((uint32_t)(c)<=0x7ff) { \
- (s)[(i)++]=(uint8_t)(((c)>>6)|0xc0); \
- } else { \
- if((uint32_t)(c)<=0xffff) { \
- (s)[(i)++]=(uint8_t)(((c)>>12)|0xe0); \
- } else { \
- (s)[(i)++]=(uint8_t)(((c)>>18)|0xf0); \
- (s)[(i)++]=(uint8_t)((((c)>>12)&0x3f)|0x80); \
- } \
- (s)[(i)++]=(uint8_t)((((c)>>6)&0x3f)|0x80); \
- } \
- (s)[(i)++]=(uint8_t)(((c)&0x3f)|0x80); \
- } \
-}
-
-/**
- * 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).
- * "Safe" macro, checks for a valid code point.
- * If a non-ASCII code point is written, checks for sufficient space in the string.
- * If the code point is not valid or trail bytes do not fit,
- * then isError is set to TRUE.
- *
- * @param s const uint8_t * string buffer
- * @param i string offset, must be i<capacity
- * @param capacity size of the string buffer
- * @param c code point to append
- * @param isError output UBool set to TRUE if an error occurs, otherwise not modified
- * @see U8_APPEND_UNSAFE
- * @stable ICU 2.4
- */
-#define U8_APPEND(s, i, capacity, c, isError) { \
- if((uint32_t)(c)<=0x7f) { \
- (s)[(i)++]=(uint8_t)(c); \
- } else if((uint32_t)(c)<=0x7ff && (i)+1<(capacity)) { \
- (s)[(i)++]=(uint8_t)(((c)>>6)|0xc0); \
- (s)[(i)++]=(uint8_t)(((c)&0x3f)|0x80); \
- } else if((uint32_t)(c)<=0xd7ff && (i)+2<(capacity)) { \
- (s)[(i)++]=(uint8_t)(((c)>>12)|0xe0); \
- (s)[(i)++]=(uint8_t)((((c)>>6)&0x3f)|0x80); \
- (s)[(i)++]=(uint8_t)(((c)&0x3f)|0x80); \
- } else { \
- (i)=utf8_appendCharSafeBody(s, (int32_t)(i), (int32_t)(capacity), c, &(isError)); \
- } \
-}
-
-/**
- * Advance the string offset from one code point boundary to the next.
- * (Post-incrementing iteration.)
- * "Unsafe" macro, assumes well-formed UTF-8.
- *
- * @param s const uint8_t * string
- * @param i string offset
- * @see U8_FWD_1
- * @stable ICU 2.4
- */
-#define U8_FWD_1_UNSAFE(s, i) { \
- (i)+=1+U8_COUNT_TRAIL_BYTES((s)[i]); \
-}
-
-/**
- * Advance the string offset from one code point boundary to the next.
- * (Post-incrementing iteration.)
- * "Safe" macro, checks for illegal sequences and for string boundaries.
- *
- * @param s const uint8_t * string
- * @param i string offset, must be i<length
- * @param length string length
- * @see U8_FWD_1_UNSAFE
- * @stable ICU 2.4
- */
-#define U8_FWD_1(s, i, length) { \
- uint8_t __b=(uint8_t)(s)[(i)++]; \
- if(U8_IS_LEAD(__b)) { \
- uint8_t __count=U8_COUNT_TRAIL_BYTES(__b); \
- if((i)+__count>(length)) { \
- __count=(uint8_t)((length)-(i)); \
- } \
- while(__count>0 && U8_IS_TRAIL((s)[i])) { \
- ++(i); \
- --__count; \
- } \
- } \
-}
-
-/**
- * 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-8.
- *
- * @param s const uint8_t * string
- * @param i string offset
- * @param n number of code points to skip
- * @see U8_FWD_N
- * @stable ICU 2.4
- */
-#define U8_FWD_N_UNSAFE(s, i, n) { \
- int32_t __N=(n); \
- while(__N>0) { \
- U8_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, checks for illegal sequences and for string boundaries.
- *
- * @param s const uint8_t * string
- * @param i string offset, must be i<length
- * @param length string length
- * @param n number of code points to skip
- * @see U8_FWD_N_UNSAFE
- * @stable ICU 2.4
- */
-#define U8_FWD_N(s, i, length, n) { \
- int32_t __N=(n); \
- while(__N>0 && (i)<(length)) { \
- U8_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 a UTF-8 trail byte,
- * then the offset is moved backward to the corresponding lead byte.
- * Otherwise, it is not modified.
- * "Unsafe" macro, assumes well-formed UTF-8.
- *
- * @param s const uint8_t * string
- * @param i string offset
- * @see U8_SET_CP_START
- * @stable ICU 2.4
- */
-#define U8_SET_CP_START_UNSAFE(s, i) { \
- while(U8_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 a UTF-8 trail byte,
- * then the offset is moved backward to the corresponding lead byte.
- * Otherwise, it is not modified.
- * "Safe" macro, checks for illegal sequences and for string boundaries.
- *
- * @param s const uint8_t * string
- * @param start starting string offset (usually 0)
- * @param i string offset, must be start<=i
- * @see U8_SET_CP_START_UNSAFE
- * @stable ICU 2.4
- */
-#define U8_SET_CP_START(s, start, i) { \
- if(U8_IS_TRAIL((s)[(i)])) { \
- (i)=utf8_back1SafeBody(s, start, (int32_t)(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-8.
- *
- * 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.
- * The result is undefined if the offset is behind an illegal UTF-8 sequence.
- *
- * @param s const uint8_t * string
- * @param i string offset
- * @param c output UChar32 variable
- * @see U8_PREV
- * @stable ICU 2.4
- */
-#define U8_PREV_UNSAFE(s, i, c) { \
- (c)=(uint8_t)(s)[--(i)]; \
- if(U8_IS_TRAIL(c)) { \
- uint8_t __b, __count=1, __shift=6; \
-\
- /* c is a trail byte */ \
- (c)&=0x3f; \
- for(;;) { \
- __b=(uint8_t)(s)[--(i)]; \
- if(__b>=0xc0) { \
- U8_MASK_LEAD_BYTE(__b, __count); \
- (c)|=(UChar32)__b<<__shift; \
- break; \
- } else { \
- (c)|=(UChar32)(__b&0x3f)<<__shift; \
- ++__count; \
- __shift+=6; \
- } \
- } \
- } \
-}
-
-/**
- * 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 a negative value.
- *
- * @param s const uint8_t * string
- * @param start starting string offset (usually 0)
- * @param i string offset, must be start<i
- * @param c output UChar32 variable, set to <0 in case of an error
- * @see U8_PREV_UNSAFE
- * @stable ICU 2.4
- */
-#define U8_PREV(s, start, i, c) { \
- (c)=(uint8_t)(s)[--(i)]; \
- if((c)>=0x80) { \
- if((c)<=0xbf) { \
- (c)=utf8_prevCharSafeBody((const uint8_t *)s, start, &(i), c, -1); \
- } else { \
- (c)=U_SENTINEL; \
- } \
- } \
-}
-
-/**
- * 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
- * @stable ICU 2.4
- */
-#define U8_BACK_1_UNSAFE(s, i) { \
- while(U8_IS_TRAIL((s)[--(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, checks for illegal sequences and for string boundaries.
- *
- * @param s const uint8_t * string
- * @param start starting string offset (usually 0)
- * @param i string offset, must be start<i
- * @see U8_BACK_1_UNSAFE
- * @stable ICU 2.4
- */
-#define U8_BACK_1(s, start, i) { \
- if(U8_IS_TRAIL((s)[--(i)])) { \
- (i)=utf8_back1SafeBody(s, start, (int32_t)(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-8.
- *
- * @param s const uint8_t * string
- * @param i string offset
- * @param n number of code points to skip
- * @see U8_BACK_N
- * @stable ICU 2.4
- */
-#define U8_BACK_N_UNSAFE(s, i, n) { \
- int32_t __N=(n); \
- while(__N>0) { \
- U8_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, checks for illegal sequences and for string boundaries.
- *
- * @param s const uint8_t * string
- * @param start index of the start of the string
- * @param i string offset, must be start<i
- * @param n number of code points to skip
- * @see U8_BACK_N_UNSAFE
- * @stable ICU 2.4
- */
-#define U8_BACK_N(s, start, i, n) { \
- int32_t __N=(n); \
- while(__N>0 && (i)>(start)) { \
- U8_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 a partial multi-byte sequence,
- * then the offset is incremented to behind the whole sequence.
- * Otherwise, it is not modified.
- * 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_SET_CP_LIMIT
- * @stable ICU 2.4
- */
-#define U8_SET_CP_LIMIT_UNSAFE(s, i) { \
- U8_BACK_1_UNSAFE(s, i); \
- U8_FWD_1_UNSAFE(s, i); \
-}
-
-/**
- * Adjust a random-access offset to a code point boundary after a code point.
- * If the offset is behind a partial multi-byte sequence,
- * then the offset is incremented to behind the whole sequence.
- * Otherwise, it is not modified.
- * The input offset may be the same as the string length.
- * "Safe" macro, checks for illegal sequences and for string boundaries.
- *
- * @param s const uint8_t * string
- * @param start starting string offset (usually 0)
- * @param i string offset, must be start<=i<=length
- * @param length string length
- * @see U8_SET_CP_LIMIT_UNSAFE
- * @stable ICU 2.4
- */
-#define U8_SET_CP_LIMIT(s, start, i, length) { \
- if((start)<(i) && (i)<(length)) { \
- U8_BACK_1(s, start, i); \
- U8_FWD_1(s, i, length); \
- } \
-}
-
-#endif
http://git-wip-us.apache.org/repos/asf/couchdb/blob/81332b78/apps/couch_collate/platform/osx/icu/unicode/utf_old.h
----------------------------------------------------------------------
diff --git a/apps/couch_collate/platform/osx/icu/unicode/utf_old.h b/apps/couch_collate/platform/osx/icu/unicode/utf_old.h
deleted file mode 100644
index 2397889..0000000
--- a/apps/couch_collate/platform/osx/icu/unicode/utf_old.h
+++ /dev/null
@@ -1,1171 +0,0 @@
-/*
-*******************************************************************************
-*
-* Copyright (C) 2002-2005, International Business Machines
-* Corporation and others. All Rights Reserved.
-*
-*******************************************************************************
-* file name: utf.h
-* encoding: US-ASCII
-* tab size: 8 (not used)
-* indentation:4
-*
-* created on: 2002sep21
-* created by: Markus W. Scherer
-*/
-
-/**
- * \file
- * \brief C API: Deprecated macros for Unicode string handling
- */
-
-/**
- *
- * The macros in utf_old.h are all deprecated and their use discouraged.
- * Some of the design principles behind the set of UTF macros
- * have changed or proved impractical.
- * Almost all of the old "UTF macros" are at least renamed.
- * If you are looking for a new equivalent to an old macro, please see the
- * comment at the old one.
- *
- * utf_old.h is included by utf.h after unicode/umachine.h
- * and some common definitions, to not break old code.
- *
- * Brief summary of reasons for deprecation:
- * - Switch on UTF_SIZE (selection of UTF-8/16/32 default string processing)
- * was impractical.
- * - Switch on UTF_SAFE etc. (selection of unsafe/safe/strict default string processing)
- * was of little use and impractical.
- * - Whole classes of macros became obsolete outside of the UTF_SIZE/UTF_SAFE
- * selection framework: UTF32_ macros (all trivial)
- * and UTF_ default and intermediate macros (all aliases).
- * - The selection framework also caused many macro aliases.
- * - Change in Unicode standard: "irregular" sequences (3.0) became illegal (3.2).
- * - Change of language in Unicode standard:
- * Growing distinction between internal x-bit Unicode strings and external UTF-x
- * forms, with the former more lenient.
- * Suggests renaming of UTF16_ macros to U16_.
- * - The prefix "UTF_" without a width number confused some users.
- * - "Safe" append macros needed the addition of an error indicator output.
- * - "Safe" UTF-8 macros used legitimate (if rarely used) code point values
- * to indicate error conditions.
- * - The use of the "_CHAR" infix for code point operations confused some users.
- *
- * More details:
- *
- * Until ICU 2.2, utf.h theoretically allowed to choose among UTF-8/16/32
- * for string processing, and among unsafe/safe/strict default macros for that.
- *
- * It proved nearly impossible to write non-trivial, high-performance code
- * that is UTF-generic.
- * Unsafe default macros would be dangerous for default string processing,
- * and the main reason for the "strict" versions disappeared:
- * Between Unicode 3.0 and 3.2 all "irregular" UTF-8 sequences became illegal.
- * The only other conditions that "strict" checked for were non-characters,
- * which are valid during processing. Only during text input/output should they
- * be checked, and at that time other well-formedness checks may be
- * necessary or useful as well.
- * This can still be done by using U16_NEXT and U_IS_UNICODE_NONCHAR
- * or U_IS_UNICODE_CHAR.
- *
- * The old UTF8_..._SAFE macros also used some normal Unicode code points
- * to indicate malformed sequences.
- * The new UTF8_ macros without suffix use negative values instead.
- *
- * The entire contents of utf32.h was moved here without replacement
- * because all those macros were trivial and
- * were meaningful only in the framework of choosing the UTF size.
- *
- * See Jitterbug 2150 and its discussion on the ICU mailing list
- * in September 2002.
- *
- * <hr>
- *
- * <em>Obsolete part</em> of pre-ICU 2.4 utf.h file documentation:
- *
- * <p>The original concept for these files was for ICU to allow
- * in principle to set which UTF (UTF-8/16/32) is used internally
- * by defining UTF_SIZE to either 8, 16, or 32. utf.h would then define the UChar type
- * accordingly. UTF-16 was the default.</p>
- *
- * <p>This concept has been abandoned.
- * A lot of the ICU source code assumes UChar strings are in UTF-16.
- * This is especially true for low-level code like
- * conversion, normalization, and collation.
- * The utf.h header enforces the default of UTF-16.
- * The UTF-8 and UTF-32 macros remain for now for completeness and backward compatibility.</p>
- *
- * <p>Accordingly, utf.h defines UChar to be an unsigned 16-bit integer. If this matches wchar_t, then
- * UChar is defined to be exactly wchar_t, otherwise uint16_t.</p>
- *
- * <p>UChar32 is defined to be a signed 32-bit integer (int32_t), large enough for a 21-bit
- * Unicode code point (Unicode scalar value, 0..0x10ffff).
- * Before ICU 2.4, the definition of UChar32 was similarly platform-dependent as
- * the definition of UChar. For details see the documentation for UChar32 itself.</p>
- *
- * <p>utf.h also defines a number of C macros for handling single Unicode code points and
- * for using UTF Unicode strings. It includes utf8.h, utf16.h, and utf32.h for the actual
- * implementations of those macros and then aliases one set of them (for UTF-16) for general use.
- * The UTF-specific macros have the UTF size in the macro name prefixes (UTF16_...), while
- * the general alias macros always begin with UTF_...</p>
- *
- * <p>Many string operations can be done with or without error checking.
- * Where such a distinction is useful, there are two versions of the macros, "unsafe" and "safe"
- * ones with ..._UNSAFE and ..._SAFE suffixes. The unsafe macros are fast but may cause
- * program failures if the strings are not well-formed. The safe macros have an additional, boolean
- * parameter "strict". If strict is FALSE, then only illegal sequences are detected.
- * Otherwise, irregular sequences and non-characters are detected as well (like single surrogates).
- * Safe macros return special error code points for illegal/irregular sequences:
- * Typically, U+ffff, or values that would result in a code unit sequence of the same length
- * as the erroneous input sequence.<br>
- * Note that _UNSAFE macros have fewer parameters: They do not have the strictness parameter, and
- * they do not have start/length parameters for boundary checking.</p>
- *
- * <p>Here, the macros are aliased in two steps:
- * In the first step, the UTF-specific macros with UTF16_ prefix and _UNSAFE and _SAFE suffixes are
- * aliased according to the UTF_SIZE to macros with UTF_ prefix and the same suffixes and signatures.
- * Then, in a second step, the default, general alias macros are set to use either the unsafe or
- * the safe/not strict (default) or the safe/strict macro;
- * these general macros do not have a strictness parameter.</p>
- *
- * <p>It is possible to change the default choice for the general alias macros to be unsafe, safe/not strict or safe/strict.
- * The default is safe/not strict. It is not recommended to select the unsafe macros as the basis for
- * Unicode string handling in ICU! To select this, define UTF_SAFE, UTF_STRICT, or UTF_UNSAFE.</p>
- *
- * <p>For general use, one should use the default, general macros with UTF_ prefix and no _SAFE/_UNSAFE suffix.
- * Only in some cases it may be necessary to control the choice of macro directly and use a less generic alias.
- * For example, if it can be assumed that a string is well-formed and the index will stay within the bounds,
- * then the _UNSAFE version may be used.
- * If a UTF-8 string is to be processed, then the macros with UTF8_ prefixes need to be used.</p>
- *
- * <hr>
- *
- * @deprecated ICU 2.4. Use the macros in utf.h, utf16.h, utf8.h instead.
- */
-
-#ifndef __UTF_OLD_H__
-#define __UTF_OLD_H__
-
-#ifndef U_HIDE_DEPRECATED_API
-
-/* utf.h must be included first. */
-#ifndef __UTF_H__
-# include "unicode/utf.h"
-#endif
-
-/* Formerly utf.h, part 1 --------------------------------------------------- */
-
-#ifdef U_USE_UTF_DEPRECATES
-/**
- * Unicode string and array offset and index type.
- * ICU always counts Unicode code units (UChars) for
- * string offsets, indexes, and lengths, not Unicode code points.
- *
- * @obsolete ICU 2.6. Use int32_t directly instead since this API will be removed in that release.
- */
-typedef int32_t UTextOffset;
-#endif
-
-/** Number of bits in a Unicode string code unit - ICU uses 16-bit Unicode. @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF_SIZE 16
-
-/**
- * The default choice for general Unicode string macros is to use the ..._SAFE macro implementations
- * with strict=FALSE.
- *
- * @deprecated ICU 2.4. Obsolete, see utf_old.h.
- */
-#define UTF_SAFE
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#undef UTF_UNSAFE
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#undef UTF_STRICT
-
-/**
- * <p>UTF8_ERROR_VALUE_1 and UTF8_ERROR_VALUE_2 are special error values for UTF-8,
- * which need 1 or 2 bytes in UTF-8:<br>
- * U+0015 = NAK = Negative Acknowledge, C0 control character<br>
- * U+009f = highest C1 control character</p>
- *
- * <p>These are used by UTF8_..._SAFE macros so that they can return an error value
- * that needs the same number of code units (bytes) as were seen by
- * a macro. They should be tested with UTF_IS_ERROR() or UTF_IS_VALID().</p>
- *
- * @deprecated ICU 2.4. Obsolete, see utf_old.h.
- */
-#define UTF8_ERROR_VALUE_1 0x15
-
-/**
- * See documentation on UTF8_ERROR_VALUE_1 for details.
- *
- * @deprecated ICU 2.4. Obsolete, see utf_old.h.
- */
-#define UTF8_ERROR_VALUE_2 0x9f
-
-/**
- * Error value for all UTFs. This code point value will be set by macros with error
- * checking if an error is detected.
- *
- * @deprecated ICU 2.4. Obsolete, see utf_old.h.
- */
-#define UTF_ERROR_VALUE 0xffff
-
-/**
- * Is a given 32-bit code an error value
- * as returned by one of the macros for any UTF?
- *
- * @deprecated ICU 2.4. Obsolete, see utf_old.h.
- */
-#define UTF_IS_ERROR(c) \
- (((c)&0xfffe)==0xfffe || (c)==UTF8_ERROR_VALUE_1 || (c)==UTF8_ERROR_VALUE_2)
-
-/**
- * This is a combined macro: Is c a valid Unicode value _and_ not an error code?
- *
- * @deprecated ICU 2.4. Obsolete, see utf_old.h.
- */
-#define UTF_IS_VALID(c) \
- (UTF_IS_UNICODE_CHAR(c) && \
- (c)!=UTF8_ERROR_VALUE_1 && (c)!=UTF8_ERROR_VALUE_2)
-
-/**
- * Is this code unit or code point a surrogate (U+d800..U+dfff)?
- * @deprecated ICU 2.4. Renamed to U_IS_SURROGATE and U16_IS_SURROGATE, see utf_old.h.
- */
-#define UTF_IS_SURROGATE(uchar) (((uchar)&0xfffff800)==0xd800)
-
-/**
- * Is a given 32-bit code point a Unicode noncharacter?
- *
- * @deprecated ICU 2.4. Renamed to U_IS_UNICODE_NONCHAR, see utf_old.h.
- */
-#define UTF_IS_UNICODE_NONCHAR(c) \
- ((c)>=0xfdd0 && \
- ((uint32_t)(c)<=0xfdef || ((c)&0xfffe)==0xfffe) && \
- (uint32_t)(c)<=0x10ffff)
-
-/**
- * Is a given 32-bit value a Unicode code point value (0..U+10ffff)
- * that can be assigned a character?
- *
- * Code points that are not characters include:
- * - single surrogate code points (U+d800..U+dfff, 2048 code points)
- * - the last two code points on each plane (U+__fffe and U+__ffff, 34 code points)
- * - U+fdd0..U+fdef (new with Unicode 3.1, 32 code points)
- * - the highest Unicode code point value is U+10ffff
- *
- * This means that all code points below U+d800 are character code points,
- * and that boundary is tested first for performance.
- *
- * @deprecated ICU 2.4. Renamed to U_IS_UNICODE_CHAR, see utf_old.h.
- */
-#define UTF_IS_UNICODE_CHAR(c) \
- ((uint32_t)(c)<0xd800 || \
- ((uint32_t)(c)>0xdfff && \
- (uint32_t)(c)<=0x10ffff && \
- !UTF_IS_UNICODE_NONCHAR(c)))
-
-/* Formerly utf8.h ---------------------------------------------------------- */
-
-/**
- * Count the trail bytes for a UTF-8 lead byte.
- * @deprecated ICU 2.4. Renamed to U8_COUNT_TRAIL_BYTES, see utf_old.h.
- */
-#define UTF8_COUNT_TRAIL_BYTES(leadByte) (utf8_countTrailBytes[(uint8_t)leadByte])
-
-/**
- * Mask a UTF-8 lead byte, leave only the lower bits that form part of the code point value.
- * @deprecated ICU 2.4. Renamed to U8_MASK_LEAD_BYTE, see utf_old.h.
- */
-#define UTF8_MASK_LEAD_BYTE(leadByte, countTrailBytes) ((leadByte)&=(1<<(6-(countTrailBytes)))-1)
-
-/** Is this this code point a single code unit (byte)? @deprecated ICU 2.4. Renamed to U8_IS_SINGLE, see utf_old.h. */
-#define UTF8_IS_SINGLE(uchar) (((uchar)&0x80)==0)
-/** Is this this code unit the lead code unit (byte) of a code point? @deprecated ICU 2.4. Renamed to U8_IS_LEAD, see utf_old.h. */
-#define UTF8_IS_LEAD(uchar) ((uint8_t)((uchar)-0xc0)<0x3e)
-/** Is this this code unit a trailing code unit (byte) of a code point? @deprecated ICU 2.4. Renamed to U8_IS_TRAIL, see utf_old.h. */
-#define UTF8_IS_TRAIL(uchar) (((uchar)&0xc0)==0x80)
-
-/** Does this scalar Unicode value need multiple code units for storage? @deprecated ICU 2.4. Use U8_LENGTH or test ((uint32_t)(c)>0x7f) instead, see utf_old.h. */
-#define UTF8_NEED_MULTIPLE_UCHAR(c) ((uint32_t)(c)>0x7f)
-
-/**
- * Given the lead character, how many bytes are taken by this code point.
- * ICU does not deal with code points >0x10ffff
- * unless necessary for advancing in the byte stream.
- *
- * These length macros take into account that for values >0x10ffff
- * the UTF8_APPEND_CHAR_SAFE macros would write the error code point 0xffff
- * with 3 bytes.
- * Code point comparisons need to be in uint32_t because UChar32
- * may be a signed type, and negative values must be recognized.
- *
- * @deprecated ICU 2.4. Use U8_LENGTH instead, see utf_old.h.
- */
-#if 1
-# define UTF8_CHAR_LENGTH(c) \
- ((uint32_t)(c)<=0x7f ? 1 : \
- ((uint32_t)(c)<=0x7ff ? 2 : \
- ((uint32_t)((c)-0x10000)>0xfffff ? 3 : 4) \
- ) \
- )
-#else
-# define UTF8_CHAR_LENGTH(c) \
- ((uint32_t)(c)<=0x7f ? 1 : \
- ((uint32_t)(c)<=0x7ff ? 2 : \
- ((uint32_t)(c)<=0xffff ? 3 : \
- ((uint32_t)(c)<=0x10ffff ? 4 : \
- ((uint32_t)(c)<=0x3ffffff ? 5 : \
- ((uint32_t)(c)<=0x7fffffff ? 6 : 3) \
- ) \
- ) \
- ) \
- ) \
- )
-#endif
-
-/** The maximum number of bytes per code point. @deprecated ICU 2.4. Renamed to U8_MAX_LENGTH, see utf_old.h. */
-#define UTF8_MAX_CHAR_LENGTH 4
-
-/** Average number of code units compared to UTF-16. @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF8_ARRAY_SIZE(size) ((5*(size))/2)
-
-/** @deprecated ICU 2.4. Renamed to U8_GET_UNSAFE, see utf_old.h. */
-#define UTF8_GET_CHAR_UNSAFE(s, i, c) { \
- int32_t _utf8_get_char_unsafe_index=(int32_t)(i); \
- UTF8_SET_CHAR_START_UNSAFE(s, _utf8_get_char_unsafe_index); \
- UTF8_NEXT_CHAR_UNSAFE(s, _utf8_get_char_unsafe_index, c); \
-}
-
-/** @deprecated ICU 2.4. Use U8_GET instead, see utf_old.h. */
-#define UTF8_GET_CHAR_SAFE(s, start, i, length, c, strict) { \
- int32_t _utf8_get_char_safe_index=(int32_t)(i); \
- UTF8_SET_CHAR_START_SAFE(s, start, _utf8_get_char_safe_index); \
- UTF8_NEXT_CHAR_SAFE(s, _utf8_get_char_safe_index, length, c, strict); \
-}
-
-/** @deprecated ICU 2.4. Renamed to U8_NEXT_UNSAFE, see utf_old.h. */
-#define UTF8_NEXT_CHAR_UNSAFE(s, i, c) { \
- (c)=(s)[(i)++]; \
- if((uint8_t)((c)-0xc0)<0x35) { \
- uint8_t __count=UTF8_COUNT_TRAIL_BYTES(c); \
- UTF8_MASK_LEAD_BYTE(c, __count); \
- switch(__count) { \
- /* each following branch falls through to the next one */ \
- case 3: \
- (c)=((c)<<6)|((s)[(i)++]&0x3f); \
- case 2: \
- (c)=((c)<<6)|((s)[(i)++]&0x3f); \
- case 1: \
- (c)=((c)<<6)|((s)[(i)++]&0x3f); \
- /* no other branches to optimize switch() */ \
- break; \
- } \
- } \
-}
-
-/** @deprecated ICU 2.4. Renamed to U8_APPEND_UNSAFE, see utf_old.h. */
-#define UTF8_APPEND_CHAR_UNSAFE(s, i, c) { \
- if((uint32_t)(c)<=0x7f) { \
- (s)[(i)++]=(uint8_t)(c); \
- } else { \
- if((uint32_t)(c)<=0x7ff) { \
- (s)[(i)++]=(uint8_t)(((c)>>6)|0xc0); \
- } else { \
- if((uint32_t)(c)<=0xffff) { \
- (s)[(i)++]=(uint8_t)(((c)>>12)|0xe0); \
- } else { \
- (s)[(i)++]=(uint8_t)(((c)>>18)|0xf0); \
- (s)[(i)++]=(uint8_t)((((c)>>12)&0x3f)|0x80); \
- } \
- (s)[(i)++]=(uint8_t)((((c)>>6)&0x3f)|0x80); \
- } \
- (s)[(i)++]=(uint8_t)(((c)&0x3f)|0x80); \
- } \
-}
-
-/** @deprecated ICU 2.4. Renamed to U8_FWD_1_UNSAFE, see utf_old.h. */
-#define UTF8_FWD_1_UNSAFE(s, i) { \
- (i)+=1+UTF8_COUNT_TRAIL_BYTES((s)[i]); \
-}
-
-/** @deprecated ICU 2.4. Renamed to U8_FWD_N_UNSAFE, see utf_old.h. */
-#define UTF8_FWD_N_UNSAFE(s, i, n) { \
- int32_t __N=(n); \
- while(__N>0) { \
- UTF8_FWD_1_UNSAFE(s, i); \
- --__N; \
- } \
-}
-
-/** @deprecated ICU 2.4. Renamed to U8_SET_CP_START_UNSAFE, see utf_old.h. */
-#define UTF8_SET_CHAR_START_UNSAFE(s, i) { \
- while(UTF8_IS_TRAIL((s)[i])) { --(i); } \
-}
-
-/** @deprecated ICU 2.4. Use U8_NEXT instead, see utf_old.h. */
-#define UTF8_NEXT_CHAR_SAFE(s, i, length, c, strict) { \
- (c)=(s)[(i)++]; \
- if((c)>=0x80) { \
- if(UTF8_IS_LEAD(c)) { \
- (c)=utf8_nextCharSafeBody(s, &(i), (int32_t)(length), c, strict); \
- } else { \
- (c)=UTF8_ERROR_VALUE_1; \
- } \
- } \
-}
-
-/** @deprecated ICU 2.4. Use U8_APPEND instead, see utf_old.h. */
-#define UTF8_APPEND_CHAR_SAFE(s, i, length, c) { \
- if((uint32_t)(c)<=0x7f) { \
- (s)[(i)++]=(uint8_t)(c); \
- } else { \
- (i)=utf8_appendCharSafeBody(s, (int32_t)(i), (int32_t)(length), c, NULL); \
- } \
-}
-
-/** @deprecated ICU 2.4. Renamed to U8_FWD_1, see utf_old.h. */
-#define UTF8_FWD_1_SAFE(s, i, length) U8_FWD_1(s, i, length)
-
-/** @deprecated ICU 2.4. Renamed to U8_FWD_N, see utf_old.h. */
-#define UTF8_FWD_N_SAFE(s, i, length, n) U8_FWD_N(s, i, length, n)
-
-/** @deprecated ICU 2.4. Renamed to U8_SET_CP_START, see utf_old.h. */
-#define UTF8_SET_CHAR_START_SAFE(s, start, i) U8_SET_CP_START(s, start, i)
-
-/** @deprecated ICU 2.4. Renamed to U8_PREV_UNSAFE, see utf_old.h. */
-#define UTF8_PREV_CHAR_UNSAFE(s, i, c) { \
- (c)=(s)[--(i)]; \
- if(UTF8_IS_TRAIL(c)) { \
- uint8_t __b, __count=1, __shift=6; \
-\
- /* c is a trail byte */ \
- (c)&=0x3f; \
- for(;;) { \
- __b=(s)[--(i)]; \
- if(__b>=0xc0) { \
- UTF8_MASK_LEAD_BYTE(__b, __count); \
- (c)|=(UChar32)__b<<__shift; \
- break; \
- } else { \
- (c)|=(UChar32)(__b&0x3f)<<__shift; \
- ++__count; \
- __shift+=6; \
- } \
- } \
- } \
-}
-
-/** @deprecated ICU 2.4. Renamed to U8_BACK_1_UNSAFE, see utf_old.h. */
-#define UTF8_BACK_1_UNSAFE(s, i) { \
- while(UTF8_IS_TRAIL((s)[--(i)])) {} \
-}
-
-/** @deprecated ICU 2.4. Renamed to U8_BACK_N_UNSAFE, see utf_old.h. */
-#define UTF8_BACK_N_UNSAFE(s, i, n) { \
- int32_t __N=(n); \
- while(__N>0) { \
- UTF8_BACK_1_UNSAFE(s, i); \
- --__N; \
- } \
-}
-
-/** @deprecated ICU 2.4. Renamed to U8_SET_CP_LIMIT_UNSAFE, see utf_old.h. */
-#define UTF8_SET_CHAR_LIMIT_UNSAFE(s, i) { \
- UTF8_BACK_1_UNSAFE(s, i); \
- UTF8_FWD_1_UNSAFE(s, i); \
-}
-
-/** @deprecated ICU 2.4. Use U8_PREV instead, see utf_old.h. */
-#define UTF8_PREV_CHAR_SAFE(s, start, i, c, strict) { \
- (c)=(s)[--(i)]; \
- if((c)>=0x80) { \
- if((c)<=0xbf) { \
- (c)=utf8_prevCharSafeBody(s, start, &(i), c, strict); \
- } else { \
- (c)=UTF8_ERROR_VALUE_1; \
- } \
- } \
-}
-
-/** @deprecated ICU 2.4. Renamed to U8_BACK_1, see utf_old.h. */
-#define UTF8_BACK_1_SAFE(s, start, i) U8_BACK_1(s, start, i)
-
-/** @deprecated ICU 2.4. Renamed to U8_BACK_N, see utf_old.h. */
-#define UTF8_BACK_N_SAFE(s, start, i, n) U8_BACK_N(s, start, i, n)
-
-/** @deprecated ICU 2.4. Renamed to U8_SET_CP_LIMIT, see utf_old.h. */
-#define UTF8_SET_CHAR_LIMIT_SAFE(s, start, i, length) U8_SET_CP_LIMIT(s, start, i, length)
-
-/* Formerly utf16.h --------------------------------------------------------- */
-
-/** Is uchar a first/lead surrogate? @deprecated ICU 2.4. Renamed to U_IS_LEAD and U16_IS_LEAD, see utf_old.h. */
-#define UTF_IS_FIRST_SURROGATE(uchar) (((uchar)&0xfffffc00)==0xd800)
-
-/** Is uchar a second/trail surrogate? @deprecated ICU 2.4. Renamed to U_IS_TRAIL and U16_IS_TRAIL, see utf_old.h. */
-#define UTF_IS_SECOND_SURROGATE(uchar) (((uchar)&0xfffffc00)==0xdc00)
-
-/** Assuming c is a surrogate, is it a first/lead surrogate? @deprecated ICU 2.4. Renamed to U_IS_SURROGATE_LEAD and U16_IS_SURROGATE_LEAD, see utf_old.h. */
-#define UTF_IS_SURROGATE_FIRST(c) (((c)&0x400)==0)
-
-/** Helper constant for UTF16_GET_PAIR_VALUE. @deprecated ICU 2.4. Renamed to U16_SURROGATE_OFFSET, see utf_old.h. */
-#define UTF_SURROGATE_OFFSET ((0xd800<<10UL)+0xdc00-0x10000)
-
-/** Get the UTF-32 value from the surrogate code units. @deprecated ICU 2.4. Renamed to U16_GET_SUPPLEMENTARY, see utf_old.h. */
-#define UTF16_GET_PAIR_VALUE(first, second) \
- (((first)<<10UL)+(second)-UTF_SURROGATE_OFFSET)
-
-/** @deprecated ICU 2.4. Renamed to U16_LEAD, see utf_old.h. */
-#define UTF_FIRST_SURROGATE(supplementary) (UChar)(((supplementary)>>10)+0xd7c0)
-
-/** @deprecated ICU 2.4. Renamed to U16_TRAIL, see utf_old.h. */
-#define UTF_SECOND_SURROGATE(supplementary) (UChar)(((supplementary)&0x3ff)|0xdc00)
-
-/** @deprecated ICU 2.4. Renamed to U16_LEAD, see utf_old.h. */
-#define UTF16_LEAD(supplementary) UTF_FIRST_SURROGATE(supplementary)
-
-/** @deprecated ICU 2.4. Renamed to U16_TRAIL, see utf_old.h. */
-#define UTF16_TRAIL(supplementary) UTF_SECOND_SURROGATE(supplementary)
-
-/** @deprecated ICU 2.4. Renamed to U16_IS_SINGLE, see utf_old.h. */
-#define UTF16_IS_SINGLE(uchar) !UTF_IS_SURROGATE(uchar)
-
-/** @deprecated ICU 2.4. Renamed to U16_IS_LEAD, see utf_old.h. */
-#define UTF16_IS_LEAD(uchar) UTF_IS_FIRST_SURROGATE(uchar)
-
-/** @deprecated ICU 2.4. Renamed to U16_IS_TRAIL, see utf_old.h. */
-#define UTF16_IS_TRAIL(uchar) UTF_IS_SECOND_SURROGATE(uchar)
-
-/** Does this scalar Unicode value need multiple code units for storage? @deprecated ICU 2.4. Use U16_LENGTH or test ((uint32_t)(c)>0xffff) instead, see utf_old.h. */
-#define UTF16_NEED_MULTIPLE_UCHAR(c) ((uint32_t)(c)>0xffff)
-
-/** @deprecated ICU 2.4. Renamed to U16_LENGTH, see utf_old.h. */
-#define UTF16_CHAR_LENGTH(c) ((uint32_t)(c)<=0xffff ? 1 : 2)
-
-/** @deprecated ICU 2.4. Renamed to U16_MAX_LENGTH, see utf_old.h. */
-#define UTF16_MAX_CHAR_LENGTH 2
-
-/** Average number of code units compared to UTF-16. @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF16_ARRAY_SIZE(size) (size)
-
-/**
- * Get a single code point from an offset that points to any
- * of the code units that belong to that code point.
- * Assume 0<=i<length.
- *
- * This could be used for iteration together with
- * UTF16_CHAR_LENGTH() and UTF_IS_ERROR(),
- * but the use of UTF16_NEXT_CHAR[_UNSAFE]() and
- * UTF16_PREV_CHAR[_UNSAFE]() is more efficient for that.
- * @deprecated ICU 2.4. Renamed to U16_GET_UNSAFE, see utf_old.h.
- */
-#define UTF16_GET_CHAR_UNSAFE(s, i, c) { \
- (c)=(s)[i]; \
- if(UTF_IS_SURROGATE(c)) { \
- if(UTF_IS_SURROGATE_FIRST(c)) { \
- (c)=UTF16_GET_PAIR_VALUE((c), (s)[(i)+1]); \
- } else { \
- (c)=UTF16_GET_PAIR_VALUE((s)[(i)-1], (c)); \
- } \
- } \
-}
-
-/** @deprecated ICU 2.4. Use U16_GET instead, see utf_old.h. */
-#define UTF16_GET_CHAR_SAFE(s, start, i, length, c, strict) { \
- (c)=(s)[i]; \
- if(UTF_IS_SURROGATE(c)) { \
- uint16_t __c2; \
- if(UTF_IS_SURROGATE_FIRST(c)) { \
- if((i)+1<(length) && UTF_IS_SECOND_SURROGATE(__c2=(s)[(i)+1])) { \
- (c)=UTF16_GET_PAIR_VALUE((c), __c2); \
- /* strict: ((c)&0xfffe)==0xfffe is caught by UTF_IS_ERROR() and UTF_IS_UNICODE_CHAR() */ \
- } else if(strict) {\
- /* unmatched first surrogate */ \
- (c)=UTF_ERROR_VALUE; \
- } \
- } else { \
- if((i)-1>=(start) && UTF_IS_FIRST_SURROGATE(__c2=(s)[(i)-1])) { \
- (c)=UTF16_GET_PAIR_VALUE(__c2, (c)); \
- /* strict: ((c)&0xfffe)==0xfffe is caught by UTF_IS_ERROR() and UTF_IS_UNICODE_CHAR() */ \
- } else if(strict) {\
- /* unmatched second surrogate */ \
- (c)=UTF_ERROR_VALUE; \
- } \
- } \
- } else if((strict) && !UTF_IS_UNICODE_CHAR(c)) { \
- (c)=UTF_ERROR_VALUE; \
- } \
-}
-
-/** @deprecated ICU 2.4. Renamed to U16_NEXT_UNSAFE, see utf_old.h. */
-#define UTF16_NEXT_CHAR_UNSAFE(s, i, c) { \
- (c)=(s)[(i)++]; \
- if(UTF_IS_FIRST_SURROGATE(c)) { \
- (c)=UTF16_GET_PAIR_VALUE((c), (s)[(i)++]); \
- } \
-}
-
-/** @deprecated ICU 2.4. Renamed to U16_APPEND_UNSAFE, see utf_old.h. */
-#define UTF16_APPEND_CHAR_UNSAFE(s, i, c) { \
- if((uint32_t)(c)<=0xffff) { \
- (s)[(i)++]=(uint16_t)(c); \
- } else { \
- (s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \
- (s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \
- } \
-}
-
-/** @deprecated ICU 2.4. Renamed to U16_FWD_1_UNSAFE, see utf_old.h. */
-#define UTF16_FWD_1_UNSAFE(s, i) { \
- if(UTF_IS_FIRST_SURROGATE((s)[(i)++])) { \
- ++(i); \
- } \
-}
-
-/** @deprecated ICU 2.4. Renamed to U16_FWD_N_UNSAFE, see utf_old.h. */
-#define UTF16_FWD_N_UNSAFE(s, i, n) { \
- int32_t __N=(n); \
- while(__N>0) { \
- UTF16_FWD_1_UNSAFE(s, i); \
- --__N; \
- } \
-}
-
-/** @deprecated ICU 2.4. Renamed to U16_SET_CP_START_UNSAFE, see utf_old.h. */
-#define UTF16_SET_CHAR_START_UNSAFE(s, i) { \
- if(UTF_IS_SECOND_SURROGATE((s)[i])) { \
- --(i); \
- } \
-}
-
-/** @deprecated ICU 2.4. Use U16_NEXT instead, see utf_old.h. */
-#define UTF16_NEXT_CHAR_SAFE(s, i, length, c, strict) { \
- (c)=(s)[(i)++]; \
- if(UTF_IS_FIRST_SURROGATE(c)) { \
- uint16_t __c2; \
- if((i)<(length) && UTF_IS_SECOND_SURROGATE(__c2=(s)[(i)])) { \
- ++(i); \
- (c)=UTF16_GET_PAIR_VALUE((c), __c2); \
- /* strict: ((c)&0xfffe)==0xfffe is caught by UTF_IS_ERROR() and UTF_IS_UNICODE_CHAR() */ \
- } else if(strict) {\
- /* unmatched first surrogate */ \
- (c)=UTF_ERROR_VALUE; \
- } \
- } else if((strict) && !UTF_IS_UNICODE_CHAR(c)) { \
- /* unmatched second surrogate or other non-character */ \
- (c)=UTF_ERROR_VALUE; \
- } \
-}
-
-/** @deprecated ICU 2.4. Use U16_APPEND instead, see utf_old.h. */
-#define UTF16_APPEND_CHAR_SAFE(s, i, length, c) { \
- if((uint32_t)(c)<=0xffff) { \
- (s)[(i)++]=(uint16_t)(c); \
- } else if((uint32_t)(c)<=0x10ffff) { \
- if((i)+1<(length)) { \
- (s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \
- (s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \
- } else /* not enough space */ { \
- (s)[(i)++]=UTF_ERROR_VALUE; \
- } \
- } else /* c>0x10ffff, write error value */ { \
- (s)[(i)++]=UTF_ERROR_VALUE; \
- } \
-}
-
-/** @deprecated ICU 2.4. Renamed to U16_FWD_1, see utf_old.h. */
-#define UTF16_FWD_1_SAFE(s, i, length) U16_FWD_1(s, i, length)
-
-/** @deprecated ICU 2.4. Renamed to U16_FWD_N, see utf_old.h. */
-#define UTF16_FWD_N_SAFE(s, i, length, n) U16_FWD_N(s, i, length, n)
-
-/** @deprecated ICU 2.4. Renamed to U16_SET_CP_START, see utf_old.h. */
-#define UTF16_SET_CHAR_START_SAFE(s, start, i) U16_SET_CP_START(s, start, i)
-
-/** @deprecated ICU 2.4. Renamed to U16_PREV_UNSAFE, see utf_old.h. */
-#define UTF16_PREV_CHAR_UNSAFE(s, i, c) { \
- (c)=(s)[--(i)]; \
- if(UTF_IS_SECOND_SURROGATE(c)) { \
- (c)=UTF16_GET_PAIR_VALUE((s)[--(i)], (c)); \
- } \
-}
-
-/** @deprecated ICU 2.4. Renamed to U16_BACK_1_UNSAFE, see utf_old.h. */
-#define UTF16_BACK_1_UNSAFE(s, i) { \
- if(UTF_IS_SECOND_SURROGATE((s)[--(i)])) { \
- --(i); \
- } \
-}
-
-/** @deprecated ICU 2.4. Renamed to U16_BACK_N_UNSAFE, see utf_old.h. */
-#define UTF16_BACK_N_UNSAFE(s, i, n) { \
- int32_t __N=(n); \
- while(__N>0) { \
- UTF16_BACK_1_UNSAFE(s, i); \
- --__N; \
- } \
-}
-
-/** @deprecated ICU 2.4. Renamed to U16_SET_CP_LIMIT_UNSAFE, see utf_old.h. */
-#define UTF16_SET_CHAR_LIMIT_UNSAFE(s, i) { \
- if(UTF_IS_FIRST_SURROGATE((s)[(i)-1])) { \
- ++(i); \
- } \
-}
-
-/** @deprecated ICU 2.4. Use U16_PREV instead, see utf_old.h. */
-#define UTF16_PREV_CHAR_SAFE(s, start, i, c, strict) { \
- (c)=(s)[--(i)]; \
- if(UTF_IS_SECOND_SURROGATE(c)) { \
- uint16_t __c2; \
- if((i)>(start) && UTF_IS_FIRST_SURROGATE(__c2=(s)[(i)-1])) { \
- --(i); \
- (c)=UTF16_GET_PAIR_VALUE(__c2, (c)); \
- /* strict: ((c)&0xfffe)==0xfffe is caught by UTF_IS_ERROR() and UTF_IS_UNICODE_CHAR() */ \
- } else if(strict) {\
- /* unmatched second surrogate */ \
- (c)=UTF_ERROR_VALUE; \
- } \
- } else if((strict) && !UTF_IS_UNICODE_CHAR(c)) { \
- /* unmatched first surrogate or other non-character */ \
- (c)=UTF_ERROR_VALUE; \
- } \
-}
-
-/** @deprecated ICU 2.4. Renamed to U16_BACK_1, see utf_old.h. */
-#define UTF16_BACK_1_SAFE(s, start, i) U16_BACK_1(s, start, i)
-
-/** @deprecated ICU 2.4. Renamed to U16_BACK_N, see utf_old.h. */
-#define UTF16_BACK_N_SAFE(s, start, i, n) U16_BACK_N(s, start, i, n)
-
-/** @deprecated ICU 2.4. Renamed to U16_SET_CP_LIMIT, see utf_old.h. */
-#define UTF16_SET_CHAR_LIMIT_SAFE(s, start, i, length) U16_SET_CP_LIMIT(s, start, i, length)
-
-/* Formerly utf32.h --------------------------------------------------------- */
-
-/*
-* Old documentation:
-*
-* This file defines macros to deal with UTF-32 code units and code points.
-* Signatures and semantics are the same as for the similarly named macros
-* in utf16.h.
-* utf32.h is included by utf.h after unicode/umachine.h</p>
-* and some common definitions.
-* <p><b>Usage:</b> ICU coding guidelines for if() statements should be followed when using these macros.
-* Compound statements (curly braces {}) must be used for if-else-while...
-* bodies and all macro statements should be terminated with semicolon.</p>
-*/
-
-/* internal definitions ----------------------------------------------------- */
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_IS_SAFE(c, strict) \
- (!(strict) ? \
- (uint32_t)(c)<=0x10ffff : \
- UTF_IS_UNICODE_CHAR(c))
-
-/*
- * For the semantics of all of these macros, see utf16.h.
- * The UTF-32 versions are trivial because any code point is
- * encoded using exactly one code unit.
- */
-
-/* single-code point definitions -------------------------------------------- */
-
-/* classes of code unit values */
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_IS_SINGLE(uchar) 1
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_IS_LEAD(uchar) 0
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_IS_TRAIL(uchar) 0
-
-/* number of code units per code point */
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_NEED_MULTIPLE_UCHAR(c) 0
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_CHAR_LENGTH(c) 1
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_MAX_CHAR_LENGTH 1
-
-/* average number of code units compared to UTF-16 */
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_ARRAY_SIZE(size) (size)
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_GET_CHAR_UNSAFE(s, i, c) { \
- (c)=(s)[i]; \
-}
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_GET_CHAR_SAFE(s, start, i, length, c, strict) { \
- (c)=(s)[i]; \
- if(!UTF32_IS_SAFE(c, strict)) { \
- (c)=UTF_ERROR_VALUE; \
- } \
-}
-
-/* definitions with forward iteration --------------------------------------- */
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_NEXT_CHAR_UNSAFE(s, i, c) { \
- (c)=(s)[(i)++]; \
-}
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_APPEND_CHAR_UNSAFE(s, i, c) { \
- (s)[(i)++]=(c); \
-}
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_FWD_1_UNSAFE(s, i) { \
- ++(i); \
-}
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_FWD_N_UNSAFE(s, i, n) { \
- (i)+=(n); \
-}
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_SET_CHAR_START_UNSAFE(s, i) { \
-}
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_NEXT_CHAR_SAFE(s, i, length, c, strict) { \
- (c)=(s)[(i)++]; \
- if(!UTF32_IS_SAFE(c, strict)) { \
- (c)=UTF_ERROR_VALUE; \
- } \
-}
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_APPEND_CHAR_SAFE(s, i, length, c) { \
- if((uint32_t)(c)<=0x10ffff) { \
- (s)[(i)++]=(c); \
- } else /* c>0x10ffff, write 0xfffd */ { \
- (s)[(i)++]=0xfffd; \
- } \
-}
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_FWD_1_SAFE(s, i, length) { \
- ++(i); \
-}
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_FWD_N_SAFE(s, i, length, n) { \
- if(((i)+=(n))>(length)) { \
- (i)=(length); \
- } \
-}
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_SET_CHAR_START_SAFE(s, start, i) { \
-}
-
-/* definitions with backward iteration -------------------------------------- */
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_PREV_CHAR_UNSAFE(s, i, c) { \
- (c)=(s)[--(i)]; \
-}
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_BACK_1_UNSAFE(s, i) { \
- --(i); \
-}
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_BACK_N_UNSAFE(s, i, n) { \
- (i)-=(n); \
-}
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_SET_CHAR_LIMIT_UNSAFE(s, i) { \
-}
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_PREV_CHAR_SAFE(s, start, i, c, strict) { \
- (c)=(s)[--(i)]; \
- if(!UTF32_IS_SAFE(c, strict)) { \
- (c)=UTF_ERROR_VALUE; \
- } \
-}
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_BACK_1_SAFE(s, start, i) { \
- --(i); \
-}
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_BACK_N_SAFE(s, start, i, n) { \
- (i)-=(n); \
- if((i)<(start)) { \
- (i)=(start); \
- } \
-}
-
-/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
-#define UTF32_SET_CHAR_LIMIT_SAFE(s, i, length) { \
-}
-
-/* Formerly utf.h, part 2 --------------------------------------------------- */
-
-/**
- * Estimate the number of code units for a string based on the number of UTF-16 code units.
- *
- * @deprecated ICU 2.4. Obsolete, see utf_old.h.
- */
-#define UTF_ARRAY_SIZE(size) UTF16_ARRAY_SIZE(size)
-
-/** @deprecated ICU 2.4. Renamed to U16_GET_UNSAFE, see utf_old.h. */
-#define UTF_GET_CHAR_UNSAFE(s, i, c) UTF16_GET_CHAR_UNSAFE(s, i, c)
-
-/** @deprecated ICU 2.4. Use U16_GET instead, see utf_old.h. */
-#define UTF_GET_CHAR_SAFE(s, start, i, length, c, strict) UTF16_GET_CHAR_SAFE(s, start, i, length, c, strict)
-
-
-/** @deprecated ICU 2.4. Renamed to U16_NEXT_UNSAFE, see utf_old.h. */
-#define UTF_NEXT_CHAR_UNSAFE(s, i, c) UTF16_NEXT_CHAR_UNSAFE(s, i, c)
-
-/** @deprecated ICU 2.4. Use U16_NEXT instead, see utf_old.h. */
-#define UTF_NEXT_CHAR_SAFE(s, i, length, c, strict) UTF16_NEXT_CHAR_SAFE(s, i, length, c, strict)
-
-
-/** @deprecated ICU 2.4. Renamed to U16_APPEND_UNSAFE, see utf_old.h. */
-#define UTF_APPEND_CHAR_UNSAFE(s, i, c) UTF16_APPEND_CHAR_UNSAFE(s, i, c)
-
-/** @deprecated ICU 2.4. Use U16_APPEND instead, see utf_old.h. */
-#define UTF_APPEND_CHAR_SAFE(s, i, length, c) UTF16_APPEND_CHAR_SAFE(s, i, length, c)
-
-
-/** @deprecated ICU 2.4. Renamed to U16_FWD_1_UNSAFE, see utf_old.h. */
-#define UTF_FWD_1_UNSAFE(s, i) UTF16_FWD_1_UNSAFE(s, i)
-
-/** @deprecated ICU 2.4. Renamed to U16_FWD_1, see utf_old.h. */
-#define UTF_FWD_1_SAFE(s, i, length) UTF16_FWD_1_SAFE(s, i, length)
-
-
-/** @deprecated ICU 2.4. Renamed to U16_FWD_N_UNSAFE, see utf_old.h. */
-#define UTF_FWD_N_UNSAFE(s, i, n) UTF16_FWD_N_UNSAFE(s, i, n)
-
-/** @deprecated ICU 2.4. Renamed to U16_FWD_N, see utf_old.h. */
-#define UTF_FWD_N_SAFE(s, i, length, n) UTF16_FWD_N_SAFE(s, i, length, n)
-
-
-/** @deprecated ICU 2.4. Renamed to U16_SET_CP_START_UNSAFE, see utf_old.h. */
-#define UTF_SET_CHAR_START_UNSAFE(s, i) UTF16_SET_CHAR_START_UNSAFE(s, i)
-
-/** @deprecated ICU 2.4. Renamed to U16_SET_CP_START, see utf_old.h. */
-#define UTF_SET_CHAR_START_SAFE(s, start, i) UTF16_SET_CHAR_START_SAFE(s, start, i)
-
-
-/** @deprecated ICU 2.4. Renamed to U16_PREV_UNSAFE, see utf_old.h. */
-#define UTF_PREV_CHAR_UNSAFE(s, i, c) UTF16_PREV_CHAR_UNSAFE(s, i, c)
-
-/** @deprecated ICU 2.4. Use U16_PREV instead, see utf_old.h. */
-#define UTF_PREV_CHAR_SAFE(s, start, i, c, strict) UTF16_PREV_CHAR_SAFE(s, start, i, c, strict)
-
-
-/** @deprecated ICU 2.4. Renamed to U16_BACK_1_UNSAFE, see utf_old.h. */
-#define UTF_BACK_1_UNSAFE(s, i) UTF16_BACK_1_UNSAFE(s, i)
-
-/** @deprecated ICU 2.4. Renamed to U16_BACK_1, see utf_old.h. */
-#define UTF_BACK_1_SAFE(s, start, i) UTF16_BACK_1_SAFE(s, start, i)
-
-
-/** @deprecated ICU 2.4. Renamed to U16_BACK_N_UNSAFE, see utf_old.h. */
-#define UTF_BACK_N_UNSAFE(s, i, n) UTF16_BACK_N_UNSAFE(s, i, n)
-
-/** @deprecated ICU 2.4. Renamed to U16_BACK_N, see utf_old.h. */
-#define UTF_BACK_N_SAFE(s, start, i, n) UTF16_BACK_N_SAFE(s, start, i, n)
-
-
-/** @deprecated ICU 2.4. Renamed to U16_SET_CP_LIMIT_UNSAFE, see utf_old.h. */
-#define UTF_SET_CHAR_LIMIT_UNSAFE(s, i) UTF16_SET_CHAR_LIMIT_UNSAFE(s, i)
-
-/** @deprecated ICU 2.4. Renamed to U16_SET_CP_LIMIT, see utf_old.h. */
-#define UTF_SET_CHAR_LIMIT_SAFE(s, start, i, length) UTF16_SET_CHAR_LIMIT_SAFE(s, start, i, length)
-
-/* Define default macros (UTF-16 "safe") ------------------------------------ */
-
-/**
- * Does this code unit alone encode a code point (BMP, not a surrogate)?
- * Same as UTF16_IS_SINGLE.
- * @deprecated ICU 2.4. Renamed to U_IS_SINGLE and U16_IS_SINGLE, see utf_old.h.
- */
-#define UTF_IS_SINGLE(uchar) U16_IS_SINGLE(uchar)
-
-/**
- * Is this code unit the first one of several (a lead surrogate)?
- * Same as UTF16_IS_LEAD.
- * @deprecated ICU 2.4. Renamed to U_IS_LEAD and U16_IS_LEAD, see utf_old.h.
- */
-#define UTF_IS_LEAD(uchar) U16_IS_LEAD(uchar)
-
-/**
- * Is this code unit one of several but not the first one (a trail surrogate)?
- * Same as UTF16_IS_TRAIL.
- * @deprecated ICU 2.4. Renamed to U_IS_TRAIL and U16_IS_TRAIL, see utf_old.h.
- */
-#define UTF_IS_TRAIL(uchar) U16_IS_TRAIL(uchar)
-
-/**
- * Does this code point require multiple code units (is it a supplementary code point)?
- * Same as UTF16_NEED_MULTIPLE_UCHAR.
- * @deprecated ICU 2.4. Use U16_LENGTH or test ((uint32_t)(c)>0xffff) instead.
- */
-#define UTF_NEED_MULTIPLE_UCHAR(c) UTF16_NEED_MULTIPLE_UCHAR(c)
-
-/**
- * How many code units are used to encode this code point (1 or 2)?
- * Same as UTF16_CHAR_LENGTH.
- * @deprecated ICU 2.4. Renamed to U16_LENGTH, see utf_old.h.
- */
-#define UTF_CHAR_LENGTH(c) U16_LENGTH(c)
-
-/**
- * How many code units are used at most for any Unicode code point (2)?
- * Same as UTF16_MAX_CHAR_LENGTH.
- * @deprecated ICU 2.4. Renamed to U16_MAX_LENGTH, see utf_old.h.
- */
-#define UTF_MAX_CHAR_LENGTH U16_MAX_LENGTH
-
-/**
- * Set c to the code point that contains the code unit i.
- * i could point to the lead or the trail surrogate for the code point.
- * i is not modified.
- * Same as UTF16_GET_CHAR.
- * \pre 0<=i<length
- *
- * @deprecated ICU 2.4. Renamed to U16_GET, see utf_old.h.
- */
-#define UTF_GET_CHAR(s, start, i, length, c) U16_GET(s, start, i, length, c)
-
-/**
- * Set c to the code point that starts at code unit i
- * and advance i to beyond the code units of this code point (post-increment).
- * i must point to the first code unit of a code point.
- * Otherwise c is set to the trail unit (surrogate) itself.
- * Same as UTF16_NEXT_CHAR.
- * \pre 0<=i<length
- * \post 0<i<=length
- *
- * @deprecated ICU 2.4. Renamed to U16_NEXT, see utf_old.h.
- */
-#define UTF_NEXT_CHAR(s, i, length, c) U16_NEXT(s, i, length, c)
-
-/**
- * Append the code units of code point c to the string at index i
- * and advance i to beyond the new code units (post-increment).
- * The code units beginning at index i will be overwritten.
- * Same as UTF16_APPEND_CHAR.
- * \pre 0<=c<=0x10ffff
- * \pre 0<=i<length
- * \post 0<i<=length
- *
- * @deprecated ICU 2.4. Use U16_APPEND instead, see utf_old.h.
- */
-#define UTF_APPEND_CHAR(s, i, length, c) UTF16_APPEND_CHAR_SAFE(s, i, length, c)
-
-/**
- * Advance i to beyond the code units of the code point that begins at i.
- * I.e., advance i by one code point.
- * Same as UTF16_FWD_1.
- * \pre 0<=i<length
- * \post 0<i<=length
- *
- * @deprecated ICU 2.4. Renamed to U16_FWD_1, see utf_old.h.
- */
-#define UTF_FWD_1(s, i, length) U16_FWD_1(s, i, length)
-
-/**
- * Advance i to beyond the code units of the n code points where the first one begins at i.
- * I.e., advance i by n code points.
- * Same as UT16_FWD_N.
- * \pre 0<=i<length
- * \post 0<i<=length
- *
- * @deprecated ICU 2.4. Renamed to U16_FWD_N, see utf_old.h.
- */
-#define UTF_FWD_N(s, i, length, n) U16_FWD_N(s, i, length, n)
-
-/**
- * Take the random-access index i and adjust it so that it points to the beginning
- * of a code point.
- * The input index points to any code unit of a code point and is moved to point to
- * the first code unit of the same code point. i is never incremented.
- * In other words, if i points to a trail surrogate that is preceded by a matching
- * lead surrogate, then i is decremented. Otherwise it is not modified.
- * This can be used to start an iteration with UTF_NEXT_CHAR() from a random index.
- * Same as UTF16_SET_CHAR_START.
- * \pre start<=i<length
- * \post start<=i<length
- *
- * @deprecated ICU 2.4. Renamed to U16_SET_CP_START, see utf_old.h.
- */
-#define UTF_SET_CHAR_START(s, start, i) U16_SET_CP_START(s, start, i)
-
-/**
- * Set c to the code point that has code units before i
- * and move i backward (towards the beginning of the string)
- * to the first code unit of this code point (pre-increment).
- * i must point to the first code unit after the last unit of a code point (i==length is allowed).
- * Same as UTF16_PREV_CHAR.
- * \pre start<i<=length
- * \post start<=i<length
- *
- * @deprecated ICU 2.4. Renamed to U16_PREV, see utf_old.h.
- */
-#define UTF_PREV_CHAR(s, start, i, c) U16_PREV(s, start, i, c)
-
-/**
- * Move i backward (towards the beginning of the string)
- * to the first code unit of the code point that has code units before i.
- * I.e., move i backward by one code point.
- * i must point to the first code unit after the last unit of a code point (i==length is allowed).
- * Same as UTF16_BACK_1.
- * \pre start<i<=length
- * \post start<=i<length
- *
- * @deprecated ICU 2.4. Renamed to U16_BACK_1, see utf_old.h.
- */
-#define UTF_BACK_1(s, start, i) U16_BACK_1(s, start, i)
-
-/**
- * Move i backward (towards the beginning of the string)
- * to the first code unit of the n code points that have code units before i.
- * I.e., move i backward by n code points.
- * i must point to the first code unit after the last unit of a code point (i==length is allowed).
- * Same as UTF16_BACK_N.
- * \pre start<i<=length
- * \post start<=i<length
- *
- * @deprecated ICU 2.4. Renamed to U16_BACK_N, see utf_old.h.
- */
-#define UTF_BACK_N(s, start, i, n) U16_BACK_N(s, start, i, n)
-
-/**
- * Take the random-access index i and adjust it so that it points beyond
- * a code point. The input index points beyond any code unit
- * of a code point and is moved to point beyond the last code unit of the same
- * code point. i is never decremented.
- * In other words, if i points to a trail surrogate that is preceded by a matching
- * lead surrogate, then i is incremented. Otherwise it is not modified.
- * This can be used to start an iteration with UTF_PREV_CHAR() from a random index.
- * Same as UTF16_SET_CHAR_LIMIT.
- * \pre start<i<=length
- * \post start<i<=length
- *
- * @deprecated ICU 2.4. Renamed to U16_SET_CP_LIMIT, see utf_old.h.
- */
-#define UTF_SET_CHAR_LIMIT(s, start, i, length) U16_SET_CP_LIMIT(s, start, i, length)
-
-#endif /* U_HIDE_DEPRECATED_API */
-
-#endif
-
http://git-wip-us.apache.org/repos/asf/couchdb/blob/81332b78/apps/couch_collate/platform/osx/icu/unicode/utmscale.h
----------------------------------------------------------------------
diff --git a/apps/couch_collate/platform/osx/icu/unicode/utmscale.h b/apps/couch_collate/platform/osx/icu/unicode/utmscale.h
deleted file mode 100644
index 368e426..0000000
--- a/apps/couch_collate/platform/osx/icu/unicode/utmscale.h
+++ /dev/null
@@ -1,481 +0,0 @@
-/*
-*******************************************************************************
-* Copyright (C) 2004 - 2008, International Business Machines Corporation and
-* others. All Rights Reserved.
-*******************************************************************************
-*/
-
-#ifndef UTMSCALE_H
-#define UTMSCALE_H
-
-#include "unicode/utypes.h"
-
-#if !UCONFIG_NO_FORMATTING
-
-/**
- * \file
- * \brief C API: Universal Time Scale
- *
- * There are quite a few different conventions for binary datetime, depending on different
- * platforms and protocols. Some of these have severe drawbacks. For example, people using
- * Unix time (seconds since Jan 1, 1970) think that they are safe until near the year 2038.
- * But cases can and do arise where arithmetic manipulations causes serious problems. Consider
- * the computation of the average of two datetimes, for example: if one calculates them with
- * <code>averageTime = (time1 + time2)/2</code>, there will be overflow even with dates
- * around the present. Moreover, even if these problems don't occur, there is the issue of
- * conversion back and forth between different systems.
- *
- * <p>
- * Binary datetimes differ in a number of ways: the datatype, the unit,
- * and the epoch (origin). We'll refer to these as time scales. For example:
- *
- * <table border="1" cellspacing="0" cellpadding="4">
- * <caption>Table 1: Binary Time Scales</caption>
- * <tr>
- * <th align="left">Source</th>
- * <th align="left">Datatype</th>
- * <th align="left">Unit</th>
- * <th align="left">Epoch</th>
- * </tr>
- *
- * <tr>
- * <td>UDTS_JAVA_TIME</td>
- * <td>int64_t</td>
- * <td>milliseconds</td>
- * <td>Jan 1, 1970</td>
- * </tr>
- * <tr>
- *
- * <td>UDTS_UNIX_TIME</td>
- * <td>int32_t or int64_t</td>
- * <td>seconds</td>
- * <td>Jan 1, 1970</td>
- * </tr>
- * <tr>
- * <td>UDTS_ICU4C_TIME</td>
- *
- * <td>double</td>
- * <td>milliseconds</td>
- * <td>Jan 1, 1970</td>
- * </tr>
- * <tr>
- * <td>UDTS_WINDOWS_FILE_TIME</td>
- * <td>int64_t</td>
- *
- * <td>ticks (100 nanoseconds)</td>
- * <td>Jan 1, 1601</td>
- * </tr>
- * <tr>
- * <td>UDTS_DOTNET_DATE_TIME</td>
- * <td>int64_t</td>
- * <td>ticks (100 nanoseconds)</td>
- *
- * <td>Jan 1, 0001</td>
- * </tr>
- * <tr>
- * <td>UDTS_MAC_OLD_TIME</td>
- * <td>int32_t or int64_t</td>
- * <td>seconds</td>
- * <td>Jan 1, 1904</td>
- *
- * </tr>
- * <tr>
- * <td>UDTS_MAC_TIME</td>
- * <td>double</td>
- * <td>seconds</td>
- * <td>Jan 1, 2001</td>
- * </tr>
- *
- * <tr>
- * <td>UDTS_EXCEL_TIME</td>
- * <td>?</td>
- * <td>days</td>
- * <td>Dec 31, 1899</td>
- * </tr>
- * <tr>
- *
- * <td>UDTS_DB2_TIME</td>
- * <td>?</td>
- * <td>days</td>
- * <td>Dec 31, 1899</td>
- * </tr>
- *
- * <tr>
- * <td>UDTS_UNIX_MICROSECONDS_TIME</td>
- * <td>int64_t</td>
- * <td>microseconds</td>
- * <td>Jan 1, 1970</td>
- * </tr>
- * </table>
- *
- * <p>
- * All of the epochs start at 00:00 am (the earliest possible time on the day in question),
- * and are assumed to be UTC.
- *
- * <p>
- * The ranges for different datatypes are given in the following table (all values in years).
- * The range of years includes the entire range expressible with positive and negative
- * values of the datatype. The range of years for double is the range that would be allowed
- * without losing precision to the corresponding unit.
- *
- * <table border="1" cellspacing="0" cellpadding="4">
- * <tr>
- * <th align="left">Units</th>
- * <th align="left">int64_t</th>
- * <th align="left">double</th>
- * <th align="left">int32_t</th>
- * </tr>
- *
- * <tr>
- * <td>1 sec</td>
- * <td align="right">5.84542x10<sup>11</sup></td>
- * <td align="right">285,420,920.94</td>
- * <td align="right">136.10</td>
- * </tr>
- * <tr>
- *
- * <td>1 millisecond</td>
- * <td align="right">584,542,046.09</td>
- * <td align="right">285,420.92</td>
- * <td align="right">0.14</td>
- * </tr>
- * <tr>
- * <td>1 microsecond</td>
- *
- * <td align="right">584,542.05</td>
- * <td align="right">285.42</td>
- * <td align="right">0.00</td>
- * </tr>
- * <tr>
- * <td>100 nanoseconds (tick)</td>
- * <td align="right">58,454.20</td>
- * <td align="right">28.54</td>
- * <td align="right">0.00</td>
- * </tr>
- * <tr>
- * <td>1 nanosecond</td>
- * <td align="right">584.5420461</td>
- * <td align="right">0.2854</td>
- * <td align="right">0.00</td>
- * </tr>
- * </table>
- *
- * <p>
- * These functions implement a universal time scale which can be used as a 'pivot',
- * and provide conversion functions to and from all other major time scales.
- * This datetimes to be converted to the pivot time, safely manipulated,
- * and converted back to any other datetime time scale.
- *
- *<p>
- * So what to use for this pivot? Java time has plenty of range, but cannot represent
- * .NET <code>System.DateTime</code> values without severe loss of precision. ICU4C time addresses this by using a
- * <code>double</code> that is otherwise equivalent to the Java time. However, there are disadvantages
- * with <code>doubles</code>. They provide for much more graceful degradation in arithmetic operations.
- * But they only have 53 bits of accuracy, which means that they will lose precision when
- * converting back and forth to ticks. What would really be nice would be a
- * <code>long double</code> (80 bits -- 64 bit mantissa), but that is not supported on most systems.
- *
- *<p>
- * The Unix extended time uses a structure with two components: time in seconds and a
- * fractional field (microseconds). However, this is clumsy, slow, and
- * prone to error (you always have to keep track of overflow and underflow in the
- * fractional field). <code>BigDecimal</code> would allow for arbitrary precision and arbitrary range,
- * but we do not want to use this as the normal type, because it is slow and does not
- * have a fixed size.
- *
- *<p>
- * Because of these issues, we ended up concluding that the .NET framework's
- * <code>System.DateTime</code> would be the best pivot. However, we use the full range
- * allowed by the datatype, allowing for datetimes back to 29,000 BC and up to 29,000 AD.
- * This time scale is very fine grained, does not lose precision, and covers a range that
- * will meet almost all requirements. It will not handle the range that Java times do,
- * but frankly, being able to handle dates before 29,000 BC or after 29,000 AD is of very limited interest.
- *
- */
-
-/**
- * <code>UDateTimeScale</code> values are used to specify the time scale used for
- * conversion into or out if the universal time scale.
- *
- * @stable ICU 3.2
- */
-typedef enum UDateTimeScale {
- /**
- * Used in the JDK. Data is a Java <code>long</code> (<code>int64_t</code>). Value
- * is milliseconds since January 1, 1970.
- *
- * @stable ICU 3.2
- */
- UDTS_JAVA_TIME = 0,
-
- /**
- * Used on Unix systems. Data is <code>int32_t</code> or <code>int64_t</code>. Value
- * is seconds since January 1, 1970.
- *
- * @stable ICU 3.2
- */
- UDTS_UNIX_TIME,
-
- /**
- * Used in IUC4C. Data is a <code>double</code>. Value
- * is milliseconds since January 1, 1970.
- *
- * @stable ICU 3.2
- */
- UDTS_ICU4C_TIME,
-
- /**
- * Used in Windows for file times. Data is an <code>int64_t</code>. Value
- * is ticks (1 tick == 100 nanoseconds) since January 1, 1601.
- *
- * @stable ICU 3.2
- */
- UDTS_WINDOWS_FILE_TIME,
-
- /**
- * Used in the .NET framework's <code>System.DateTime</code> structure. Data is an <code>int64_t</code>. Value
- * is ticks (1 tick == 100 nanoseconds) since January 1, 0001.
- *
- * @stable ICU 3.2
- */
- UDTS_DOTNET_DATE_TIME,
-
- /**
- * Used in older Macintosh systems. Data is <code>int32_t</code> or <code>int64_t</code>. Value
- * is seconds since January 1, 1904.
- *
- * @stable ICU 3.2
- */
- UDTS_MAC_OLD_TIME,
-
- /**
- * Used in newer Macintosh systems. Data is a <code>double</code>. Value
- * is seconds since January 1, 2001.
- *
- * @stable ICU 3.2
- */
- UDTS_MAC_TIME,
-
- /**
- * Used in Excel. Data is an <code>?unknown?</code>. Value
- * is days since December 31, 1899.
- *
- * @stable ICU 3.2
- */
- UDTS_EXCEL_TIME,
-
- /**
- * Used in DB2. Data is an <code>?unknown?</code>. Value
- * is days since December 31, 1899.
- *
- * @stable ICU 3.2
- */
- UDTS_DB2_TIME,
-
- /**
- * Data is a <code>long</code>. Value is microseconds since January 1, 1970.
- * Similar to Unix time (linear value from 1970) and struct timeval
- * (microseconds resolution).
- *
- * @stable ICU 4.0
- */
- UDTS_UNIX_MICROSECONDS_TIME,
-
- /**
- * The first unused time scale value. The limit of this enum
- */
- UDTS_MAX_SCALE
-} UDateTimeScale;
-
-/**
- * <code>UTimeScaleValue</code> values are used to specify the time scale values
- * to <code>utmscale_getTimeScaleValue</code>.
- *
- * @see utmscale_getTimeScaleValue
- *
- * @stable ICU 3.2
- */
-typedef enum UTimeScaleValue {
- /**
- * The constant used to select the units vale
- * for a time scale.
- *
- * @see utmscale_getTimeScaleValue
- *
- * @stable ICU 3.2
- */
- UTSV_UNITS_VALUE = 0,
-
- /**
- * The constant used to select the epoch offset value
- * for a time scale.
- *
- * @see utmscale_getTimeScaleValue
- *
- * @stable ICU 3.2
- */
- UTSV_EPOCH_OFFSET_VALUE=1,
-
- /**
- * The constant used to select the minimum from value
- * for a time scale.
- *
- * @see utmscale_getTimeScaleValue
- *
- * @stable ICU 3.2
- */
- UTSV_FROM_MIN_VALUE=2,
-
- /**
- * The constant used to select the maximum from value
- * for a time scale.
- *
- * @see utmscale_getTimeScaleValue
- *
- * @stable ICU 3.2
- */
- UTSV_FROM_MAX_VALUE=3,
-
- /**
- * The constant used to select the minimum to value
- * for a time scale.
- *
- * @see utmscale_getTimeScaleValue
- *
- * @stable ICU 3.2
- */
- UTSV_TO_MIN_VALUE=4,
-
- /**
- * The constant used to select the maximum to value
- * for a time scale.
- *
- * @see utmscale_getTimeScaleValue
- *
- * @stable ICU 3.2
- */
- UTSV_TO_MAX_VALUE=5,
-
-#ifndef U_HIDE_INTERNAL_API
- /**
- * The constant used to select the epoch plus one value
- * for a time scale.
- *
- * NOTE: This is an internal value. DO NOT USE IT. May not
- * actually be equal to the epoch offset value plus one.
- *
- * @see utmscale_getTimeScaleValue
- *
- * @internal ICU 3.2
- */
- UTSV_EPOCH_OFFSET_PLUS_1_VALUE=6,
-
- /**
- * The constant used to select the epoch plus one value
- * for a time scale.
- *
- * NOTE: This is an internal value. DO NOT USE IT. May not
- * actually be equal to the epoch offset value plus one.
- *
- * @see utmscale_getTimeScaleValue
- *
- * @internal ICU 3.2
- */
- UTSV_EPOCH_OFFSET_MINUS_1_VALUE=7,
-
- /**
- * The constant used to select the units round value
- * for a time scale.
- *
- * NOTE: This is an internal value. DO NOT USE IT.
- *
- * @see utmscale_getTimeScaleValue
- *
- * @internal ICU 3.2
- */
- UTSV_UNITS_ROUND_VALUE=8,
-
- /**
- * The constant used to select the minimum safe rounding value
- * for a time scale.
- *
- * NOTE: This is an internal value. DO NOT USE IT.
- *
- * @see utmscale_getTimeScaleValue
- *
- * @internal ICU 3.2
- */
- UTSV_MIN_ROUND_VALUE=9,
-
- /**
- * The constant used to select the maximum safe rounding value
- * for a time scale.
- *
- * NOTE: This is an internal value. DO NOT USE IT.
- *
- * @see utmscale_getTimeScaleValue
- *
- * @internal ICU 3.2
- */
- UTSV_MAX_ROUND_VALUE=10,
-
-#endif /* U_HIDE_INTERNAL_API */
-
- /**
- * The number of time scale values, in other words limit of this enum.
- *
- * @see utmscale_getTimeScaleValue
- */
- UTSV_MAX_SCALE_VALUE=11
-
-} UTimeScaleValue;
-
-/**
- * Get a value associated with a particular time scale.
- *
- * @param timeScale The time scale
- * @param value A constant representing the value to get
- * @param status The status code. Set to <code>U_ILLEGAL_ARGUMENT_ERROR</code> if arguments are invalid.
- * @return - the value.
- *
- * @stable ICU 3.2
- */
-U_STABLE int64_t U_EXPORT2
- utmscale_getTimeScaleValue(UDateTimeScale timeScale, UTimeScaleValue value, UErrorCode *status);
-
-/* Conversion to 'universal time scale' */
-
-/**
- * Convert a <code>int64_t</code> datetime from the given time scale to the universal time scale.
- *
- * @param otherTime The <code>int64_t</code> datetime
- * @param timeScale The time scale to convert from
- * @param status The status code. Set to <code>U_ILLEGAL_ARGUMENT_ERROR</code> if the conversion is out of range.
- *
- * @return The datetime converted to the universal time scale
- *
- * @stable ICU 3.2
- */
-U_STABLE int64_t U_EXPORT2
- utmscale_fromInt64(int64_t otherTime, UDateTimeScale timeScale, UErrorCode *status);
-
-/* Conversion from 'universal time scale' */
-
-/**
- * Convert a datetime from the universal time scale to a <code>int64_t</code> in the given time scale.
- *
- * @param universalTime The datetime in the universal time scale
- * @param timeScale The time scale to convert to
- * @param status The status code. Set to <code>U_ILLEGAL_ARGUMENT_ERROR</code> if the conversion is out of range.
- *
- * @return The datetime converted to the given time scale
- *
- * @stable ICU 3.2
- */
-U_STABLE int64_t U_EXPORT2
- utmscale_toInt64(int64_t universalTime, UDateTimeScale timeScale, UErrorCode *status);
-
-#endif /* #if !UCONFIG_NO_FORMATTING */
-
-#endif
-