File Manager

X7ROOT File Manager

Current Path: /opt/alt/libicu65/usr/include/unicode

opt / alt / libicu65 / usr / include / unicode /

ðŸ“ ..
ðŸ“„ alphaindex.h(26.48 KB)
ðŸ“„ appendable.h(8.49 KB)
ðŸ“„ basictz.h(9.15 KB)
ðŸ“„ brkiter.h(27.8 KB)
ðŸ“„ bytestream.h(9.6 KB)
ðŸ“„ bytestrie.h(20.77 KB)
ðŸ“„ bytestriebuilder.h(7.08 KB)
ðŸ“„ calendar.h(105.74 KB)
ðŸ“„ caniter.h(7.43 KB)
ðŸ“„ casemap.h(25.33 KB)
ðŸ“„ char16ptr.h(7.22 KB)
ðŸ“„ chariter.h(24.05 KB)
ðŸ“„ choicfmt.h(23.91 KB)
ðŸ“„ coleitr.h(13.76 KB)
ðŸ“„ coll.h(56.23 KB)
ðŸ“„ compactdecimalformat.h(6.88 KB)
ðŸ“„ curramt.h(3.76 KB)
ðŸ“„ currpinf.h(7.3 KB)
ðŸ“„ currunit.h(4.05 KB)
ðŸ“„ datefmt.h(40.67 KB)
ðŸ“„ dbbi.h(1.19 KB)
ðŸ“„ dcfmtsym.h(20.13 KB)
ðŸ“„ decimfmt.h(87.38 KB)
ðŸ“„ docmain.h(6.97 KB)
ðŸ“„ dtfmtsym.h(37.7 KB)
ðŸ“„ dtintrv.h(3.84 KB)
ðŸ“„ dtitvfmt.h(46.63 KB)
ðŸ“„ dtitvinf.h(18.51 KB)
ðŸ“„ dtptngen.h(25.08 KB)
ðŸ“„ dtrule.h(8.68 KB)
ðŸ“„ edits.h(20.74 KB)
ðŸ“„ enumset.h(2.08 KB)
ðŸ“„ errorcode.h(4.84 KB)
ðŸ“„ fieldpos.h(8.69 KB)
ðŸ“„ filteredbrk.h(5.37 KB)
ðŸ“„ fmtable.h(24.42 KB)
ðŸ“„ format.h(12.5 KB)
ðŸ“„ formattedvalue.h(10.27 KB)
ðŸ“„ fpositer.h(3.04 KB)
ðŸ“„ gender.h(3.33 KB)
ðŸ“„ gregocal.h(31.71 KB)
ðŸ“„ icudataver.h(1.03 KB)
ðŸ“„ icuplug.h(11.88 KB)
ðŸ“„ idna.h(12.7 KB)
ðŸ“„ listformatter.h(9.47 KB)
ðŸ“„ localebuilder.h(11.27 KB)
ðŸ“„ localematcher.h(22.5 KB)
ðŸ“„ localpointer.h(19.69 KB)
ðŸ“„ locdspnm.h(7.12 KB)
ðŸ“„ locid.h(47.4 KB)
ðŸ“„ measfmt.h(11.33 KB)
ðŸ“„ measunit.h(93.31 KB)
ðŸ“„ measure.h(4.32 KB)
ðŸ“„ messagepattern.h(33.71 KB)
ðŸ“„ msgfmt.h(44.11 KB)
ðŸ“„ normalizer2.h(34.03 KB)
ðŸ“„ normlzr.h(30.94 KB)
ðŸ“„ nounit.h(2.69 KB)
ðŸ“„ numberformatter.h(86.31 KB)
ðŸ“„ numberrangeformatter.h(30.14 KB)
ðŸ“„ numfmt.h(49.81 KB)
ðŸ“„ numsys.h(7.19 KB)
ðŸ“„ parseerr.h(3.08 KB)
ðŸ“„ parsepos.h(5.56 KB)
ðŸ“„ platform.h(28.08 KB)
ðŸ“„ plurfmt.h(25.2 KB)
ðŸ“„ plurrule.h(18.39 KB)
ðŸ“„ ptypes.h(3.49 KB)
ðŸ“„ putil.h(6.33 KB)
ðŸ“„ rbbi.h(26.58 KB)
ðŸ“„ rbnf.h(48.73 KB)
ðŸ“„ rbtz.h(15.6 KB)
ðŸ“„ regex.h(84.36 KB)
ðŸ“„ region.h(9.18 KB)
ðŸ“„ reldatefmt.h(22.62 KB)
ðŸ“„ rep.h(9.37 KB)
ðŸ“„ resbund.h(18.07 KB)
ðŸ“„ schriter.h(6.32 KB)
ðŸ“„ scientificnumberformatter.h(6.4 KB)
ðŸ“„ search.h(22.22 KB)
ðŸ“„ selfmt.h(14.3 KB)
ðŸ“„ simpleformatter.h(12.59 KB)
ðŸ“„ simpletz.h(45.44 KB)
ðŸ“„ smpdtfmt.h(70.97 KB)
ðŸ“„ sortkey.h(11.18 KB)
ðŸ“„ std_string.h(1.05 KB)
ðŸ“„ strenum.h(9.92 KB)
ðŸ“„ stringoptions.h(5.79 KB)
ðŸ“„ stringpiece.h(7.38 KB)
ðŸ“„ stringtriebuilder.h(15.33 KB)
ðŸ“„ stsearch.h(21.3 KB)
ðŸ“„ symtable.h(4.27 KB)
ðŸ“„ tblcoll.h(36.61 KB)
ðŸ“„ timezone.h(41.02 KB)
ðŸ“„ tmunit.h(3.38 KB)
ðŸ“„ tmutamt.h(4.9 KB)
ðŸ“„ tmutfmt.h(7.85 KB)
ðŸ“„ translit.h(65.82 KB)
ðŸ“„ tzfmt.h(42.89 KB)
ðŸ“„ tznames.h(16.85 KB)
ðŸ“„ tzrule.h(35.37 KB)
ðŸ“„ tztrans.h(6.12 KB)
ðŸ“„ ubidi.h(89.56 KB)
ðŸ“„ ubiditransform.h(12.65 KB)
ðŸ“„ ubrk.h(23.97 KB)
ðŸ“„ ucal.h(56.9 KB)
ðŸ“„ ucasemap.h(15.18 KB)
ðŸ“„ ucat.h(5.36 KB)
ðŸ“„ uchar.h(140.56 KB)
ðŸ“„ ucharstrie.h(22.58 KB)
ðŸ“„ ucharstriebuilder.h(7.21 KB)
ðŸ“„ uchriter.h(13.2 KB)
ðŸ“„ uclean.h(11.21 KB)
ðŸ“„ ucnv.h(83.09 KB)
ðŸ“„ ucnv_cb.h(6.59 KB)
ðŸ“„ ucnv_err.h(20.99 KB)
ðŸ“„ ucnvsel.h(6.14 KB)
ðŸ“„ ucol.h(61.46 KB)
ðŸ“„ ucoleitr.h(9.46 KB)
ðŸ“„ uconfig.h(12.07 KB)
ðŸ“„ ucpmap.h(5.53 KB)
ðŸ“„ ucptrie.h(22.46 KB)
ðŸ“„ ucsdet.h(14.67 KB)
ðŸ“„ ucurr.h(16.12 KB)
ðŸ“„ udat.h(60.88 KB)
ðŸ“„ udata.h(15.56 KB)
ðŸ“„ udateintervalformat.h(10.03 KB)
ðŸ“„ udatpg.h(26.01 KB)
ðŸ“„ udisplaycontext.h(5.89 KB)
ðŸ“„ uenum.h(7.78 KB)
ðŸ“„ ufieldpositer.h(4.36 KB)
ðŸ“„ uformattable.h(10.94 KB)
ðŸ“„ uformattedvalue.h(12.14 KB)
ðŸ“„ ugender.h(2 KB)
ðŸ“„ uidna.h(33.37 KB)
ðŸ“„ uiter.h(22.77 KB)
ðŸ“„ uldnames.h(10.45 KB)
ðŸ“„ ulistformatter.h(8.83 KB)
ðŸ“„ uloc.h(52.54 KB)
ðŸ“„ ulocdata.h(11.26 KB)
ðŸ“„ umachine.h(14.53 KB)
ðŸ“„ umisc.h(1.33 KB)
ðŸ“„ umsg.h(24.23 KB)
ðŸ“„ umutablecptrie.h(8.24 KB)
ðŸ“„ unifilt.h(3.96 KB)
ðŸ“„ unifunct.h(4.04 KB)
ðŸ“„ unimatch.h(6.1 KB)
ðŸ“„ unirepl.h(3.38 KB)
ðŸ“„ uniset.h(64.9 KB)
ðŸ“„ unistr.h(170.43 KB)
ðŸ“„ unorm.h(20.52 KB)
ðŸ“„ unorm2.h(24.66 KB)
ðŸ“„ unum.h(53.62 KB)
ðŸ“„ unumberformatter.h(25.36 KB)
ðŸ“„ unumsys.h(7.21 KB)
ðŸ“„ uobject.h(10.68 KB)
ðŸ“„ upluralrules.h(7.88 KB)
ðŸ“„ uregex.h(72.05 KB)
ðŸ“„ uregion.h(9.84 KB)
ðŸ“„ ureldatefmt.h(17.26 KB)
ðŸ“„ urename.h(130.97 KB)
ðŸ“„ urep.h(5.38 KB)
ðŸ“„ ures.h(36.54 KB)
ðŸ“„ uscript.h(26.87 KB)
ðŸ“„ usearch.h(38.12 KB)
ðŸ“„ uset.h(40 KB)
ðŸ“„ usetiter.h(9.55 KB)
ðŸ“„ ushape.h(18 KB)
ðŸ“„ uspoof.h(65.9 KB)
ðŸ“„ usprep.h(8.14 KB)
ðŸ“„ ustdio.h(38.54 KB)
ðŸ“„ ustream.h(1.89 KB)
ðŸ“„ ustring.h(72.47 KB)
ðŸ“„ ustringtrie.h(3.15 KB)
ðŸ“„ utext.h(58.13 KB)
ðŸ“„ utf.h(7.86 KB)
ðŸ“„ utf16.h(23.32 KB)
ðŸ“„ utf32.h(763 B)
ðŸ“„ utf8.h(30.96 KB)
ðŸ“„ utf_old.h(45.83 KB)
ðŸ“„ utmscale.h(13.78 KB)
ðŸ“„ utrace.h(15.73 KB)
ðŸ“„ utrans.h(25.52 KB)
ðŸ“„ utypes.h(30.74 KB)
ðŸ“„ uvernum.h(6.67 KB)
ðŸ“„ uversion.h(6 KB)
ðŸ“„ vtzone.h(20.3 KB)

Editing: utf.h

// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
*   Copyright (C) 1999-2011, International Business Machines
*   Corporation and others.  All Rights Reserved.
*
*******************************************************************************
*   file name:  utf.h
*   encoding:   UTF-8
*   tab size:   8 (not used)
*   indentation:4
*
*   created on: 1999sep09
*   created by: Markus W. Scherer
*/

/**
 * \file
 * \brief C API: Code point macros
 *
 * This file defines macros for checking whether a code point is
 * a surrogate or a non-character etc.
 *
 * If U_NO_DEFAULT_INCLUDE_UTF_HEADERS is 0 then utf.h is included by utypes.h
 * and itself includes utf8.h and utf16.h after some
 * common definitions.
 * If U_NO_DEFAULT_INCLUDE_UTF_HEADERS is 1 then each of these headers must be
 * included explicitly if their definitions are used.
 *
 * utf8.h and utf16.h define macros for efficiently getting code points
 * in and out of UTF-8/16 strings.
 * utf16.h macros have "U16_" prefixes.
 * utf8.h defines similar macros with "U8_" prefixes for UTF-8 string handling.
 *
 * ICU mostly processes 16-bit Unicode strings.
 * Most of the time, such strings are well-formed UTF-16.
 * Single, unpaired surrogates must be handled as well, and are treated in ICU
 * like regular code points where possible.
 * (Pairs of surrogate code points are indistinguishable from supplementary
 * code points encoded as pairs of supplementary code units.)
 *
 * In fact, almost all Unicode code points in normal text (>99%)
 * are on the BMP (<=U+ffff) and even <=U+d7ff.
 * ICU functions handle supplementary code points (U+10000..U+10ffff)
 * but are optimized for the much more frequently occurring BMP code points.
 *
 * umachine.h defines UChar to be an unsigned 16-bit integer.
 * Since ICU 59, ICU uses char16_t in C++, UChar only in C,
 * and defines UChar=char16_t by default. See the UChar API docs for details.
 *
 * 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) and U_SENTINEL (-1).
 * 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.
 *
 * utf.h defines a small number of C macros for single Unicode code points.
 * These are simple checks for surrogates and non-characters.
 * For actual Unicode character properties see uchar.h.
 *
 * By default, string operations must be done with error checking in case
 * a string is not well-formed UTF-16 or UTF-8.
 *
 * The U16_ macros detect if a surrogate code unit is unpaired
 * (lead unit without trail unit or vice versa) and just return the unit itself
 * as the code point.
 *
 * The U8_ macros detect illegal byte sequences and return a negative value.
 * Starting with ICU 60, the observable length of a single illegal byte sequence
 * skipped by one of these macros follows the Unicode 6+ recommendation
 * which is consistent with the W3C Encoding Standard.
 *
 * There are ..._OR_FFFD versions of both U16_ and U8_ macros
 * that return U+FFFD for illegal code unit sequences.
 *
 * The regular "safe" macros require that the initial, passed-in string index
 * is within bounds. They only check the index when they read more than one
 * code unit. This is usually done with code similar to the following loop:
 * <pre>while(i<length) {
 *   U16_NEXT(s, i, length, c);
 *   // use c
 * }</pre>
 *
 * When it is safe to assume that text is well-formed UTF-16
 * (does not contain single, unpaired surrogates), then one can use
 * U16_..._UNSAFE macros.
 * These do not check for proper code unit sequences or truncated text and may
 * yield wrong results or even cause a crash if they are used with "malformed"
 * text.
 * In practice, U16_..._UNSAFE macros will produce slightly less code but
 * should not be faster because the processing is only different when a
 * surrogate code unit is detected, which will be rare.
 *
 * Similarly for UTF-8, there are "safe" macros without a suffix,
 * and U8_..._UNSAFE versions.
 * The performance differences are much larger here because UTF-8 provides so
 * many opportunities for malformed sequences.
 * The unsafe UTF-8 macros are entirely implemented inside the macro definitions
 * and are fast, while the safe UTF-8 macros call functions for some complicated cases.
 *
 * Unlike with UTF-16, malformed sequences cannot be expressed with distinct
 * code point values (0..U+10ffff). They are indicated with negative values instead.
 *
 * For more information see the ICU User Guide Strings chapter
 * (http://userguide.icu-project.org/strings).
 *
 * <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.
 *
 * @stable ICU 2.4
 */

#ifndef __UTF_H__
#define __UTF_H__

#include "unicode/umachine.h"
/* include the utfXX.h after the following definitions */

/* single-code point definitions -------------------------------------------- */

/**
 * Is this code point a Unicode noncharacter?
 * @param c 32-bit code point
 * @return TRUE or FALSE
 * @stable ICU 2.4
 */
#define U_IS_UNICODE_NONCHAR(c) \
    ((c)>=0xfdd0 && \
     ((c)<=0xfdef || ((c)&0xfffe)==0xfffe) && (c)<=0x10ffff)

/**
 * Is c 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.
 *
 * @param c 32-bit code point
 * @return TRUE or FALSE
 * @stable ICU 2.4
 */
#define U_IS_UNICODE_CHAR(c) \
    ((uint32_t)(c)<0xd800 || \
        (0xdfff<(c) && (c)<=0x10ffff && !U_IS_UNICODE_NONCHAR(c)))

/**
 * Is this code point a BMP code point (U+0000..U+ffff)?
 * @param c 32-bit code point
 * @return TRUE or FALSE
 * @stable ICU 2.8
 */
#define U_IS_BMP(c) ((uint32_t)(c)<=0xffff)

/**
 * Is this code point a supplementary code point (U+10000..U+10ffff)?
 * @param c 32-bit code point
 * @return TRUE or FALSE
 * @stable ICU 2.8
 */
#define U_IS_SUPPLEMENTARY(c) ((uint32_t)((c)-0x10000)<=0xfffff)
 
/**
 * Is this code point a lead surrogate (U+d800..U+dbff)?
 * @param c 32-bit code point
 * @return TRUE or FALSE
 * @stable ICU 2.4
 */
#define U_IS_LEAD(c) (((c)&0xfffffc00)==0xd800)

/**
 * Is this code point a trail surrogate (U+dc00..U+dfff)?
 * @param c 32-bit code point
 * @return TRUE or FALSE
 * @stable ICU 2.4
 */
#define U_IS_TRAIL(c) (((c)&0xfffffc00)==0xdc00)

/**
 * Is this code point a surrogate (U+d800..U+dfff)?
 * @param c 32-bit code point
 * @return TRUE or FALSE
 * @stable ICU 2.4
 */
#define U_IS_SURROGATE(c) (((c)&0xfffff800)==0xd800)

/**
 * Assuming c is a surrogate code point (U_IS_SURROGATE(c)),
 * is it a lead surrogate?
 * @param c 32-bit code point
 * @return TRUE or FALSE
 * @stable ICU 2.4
 */
#define U_IS_SURROGATE_LEAD(c) (((c)&0x400)==0)

/**
 * Assuming c is a surrogate code point (U_IS_SURROGATE(c)),
 * is it a trail surrogate?
 * @param c 32-bit code point
 * @return TRUE or FALSE
 * @stable ICU 4.2
 */
#define U_IS_SURROGATE_TRAIL(c) (((c)&0x400)!=0)

/* include the utfXX.h ------------------------------------------------------ */

#if !U_NO_DEFAULT_INCLUDE_UTF_HEADERS

#include "unicode/utf8.h"
#include "unicode/utf16.h"

/* utf_old.h contains deprecated, pre-ICU 2.4 definitions */
#include "unicode/utf_old.h"

#endif  /* !U_NO_DEFAULT_INCLUDE_UTF_HEADERS */

#endif  /* __UTF_H__ */

X7ROOT File Manager

Editing: utf.h

Upload File

Create Folder