wuggy/Dactyloidae
wuggy/Dactyloidae
1
0
Fork 0
mirror of https://repo.dactyloidae.xyz/Dactyloidae/UXP.git synced 2026-09-21 15:57:31 +09:00
Code Issues Projects Releases Packages Wiki Activity

Issue #1971 - Part 2: Update ICU source to 63.2.

Browse source
This commit is contained in:
Job Bautista 2022-07-24 21:03:27 +08:00 • committed by roytam1
commit 1e69214382
3160 changed files with 275815 additions and 234203 deletions
Download patch file Download diff file Expand all files Collapse all files

124
intl/icu/source/common/unicode/utf16.h
View file

@ -1,4 +1,4 @@
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
@ -8,7 +8,7 @@
*
*******************************************************************************
* file name: utf16.h
* encoding: US-ASCII
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
@ -185,8 +185,8 @@
*
* The length can be negative for a NUL-terminated string.
*
* If the offset points to a single, unpaired surrogate, then that itself
* will be returned as the code point.
* If the offset points to a single, unpaired surrogate, then
* c is set to that unpaired surrogate.
* Iteration through a string is more efficient with U16_NEXT_UNSAFE or U16_NEXT.
*
* @param s const UChar * string
@ -213,6 +213,49 @@
} \
}
/**
* Get a code point from a string at a random-access offset,
* without changing the offset.
* "Safe" macro, handles unpaired surrogates and checks for string boundaries.
*
* The offset may point to either the lead or trail surrogate unit
* for a supplementary code point, in which case the macro will read
* the adjacent matching surrogate as well.
*
* The length can be negative for a NUL-terminated string.
*
* If the offset points to a single, unpaired surrogate, then
* c is set to U+FFFD.
* Iteration through a string is more efficient with U16_NEXT_UNSAFE or U16_NEXT_OR_FFFD.
*
* @param s const UChar * string
* @param start starting string offset (usually 0)
* @param i string offset, must be start<=i<length
* @param length string length
* @param c output UChar32 variable
* @see U16_GET_UNSAFE
* @stable ICU 60
*/
#define U16_GET_OR_FFFD(s, start, i, length, c) { \
(c)=(s)[i]; \
if(U16_IS_SURROGATE(c)) { \
uint16_t __c2; \
if(U16_IS_SURROGATE_LEAD(c)) { \
if((i)+1!=(length) && U16_IS_TRAIL(__c2=(s)[(i)+1])) { \
(c)=U16_GET_SUPPLEMENTARY((c), __c2); \
} else { \
(c)=0xfffd; \
} \
} else { \
if((i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \
(c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \
} else { \
(c)=0xfffd; \
} \
} \
} \
}
/* definitions with forward iteration --------------------------------------- */
/**
@ -253,8 +296,7 @@
* for a supplementary code point, in which case the macro will read
* the following trail surrogate as well.
* If the offset points to a trail surrogate or
* to a single, unpaired lead surrogate, then that itself
* will be returned as the code point.
* to a single, unpaired lead surrogate, then c is set to that unpaired surrogate.
*
* @param s const UChar * string
* @param i string offset, must be i<length
@ -274,6 +316,40 @@
} \
}
/**
* Get a code point from a string at a code point boundary offset,
* and advance the offset to the next code point boundary.
* (Post-incrementing forward iteration.)
* "Safe" macro, handles unpaired surrogates and checks for string boundaries.
*
* The length can be negative for a NUL-terminated string.
*
* The offset may point to the lead surrogate unit
* for a supplementary code point, in which case the macro will read
* the following trail surrogate as well.
* If the offset points to a trail surrogate or
* to a single, unpaired lead surrogate, then c is set to U+FFFD.
*
* @param s const UChar * string
* @param i string offset, must be i<length
* @param length string length
* @param c output UChar32 variable
* @see U16_NEXT_UNSAFE
* @stable ICU 60
*/
#define U16_NEXT_OR_FFFD(s, i, length, c) { \
(c)=(s)[(i)++]; \
if(U16_IS_SURROGATE(c)) { \
uint16_t __c2; \
if(U16_IS_SURROGATE_LEAD(c) && (i)!=(length) && U16_IS_TRAIL(__c2=(s)[(i)])) { \
++(i); \
(c)=U16_GET_SUPPLEMENTARY((c), __c2); \
} else { \
(c)=0xfffd; \
} \
} \
}
/**
* Append a code point to a string, overwriting 1 or 2 code units.
* The offset points to the current end of the string contents
@ -481,8 +557,7 @@
* 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.
* trail surrogate, then c is set to that unpaired surrogate.
*
* @param s const UChar * string
* @param start starting string offset (usually 0)
@ -502,6 +577,39 @@
} \
}
/**
* 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 c is set to U+FFFD.
*
* @param s const UChar * string
* @param start starting string offset (usually 0)
* @param i string offset, must be start<i
* @param c output UChar32 variable
* @see U16_PREV_UNSAFE
* @stable ICU 60
*/
#define U16_PREV_OR_FFFD(s, start, i, c) { \
(c)=(s)[--(i)]; \
if(U16_IS_SURROGATE(c)) { \
uint16_t __c2; \
if(U16_IS_SURROGATE_TRAIL(c) && (i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \
--(i); \
(c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \
} else { \
(c)=0xfffd; \
} \
} \
}
/**
* Move the string offset from one code point boundary to the previous one.
* (Pre-decrementing backward iteration.)