FM / unicode

/usr/include/unicode

Name	Size	Mode	Actions
alphaindex.h	27158	0644	edit dl rm
appendable.h	8739	0644	edit dl rm
basictz.h	10163	0644	edit dl rm
brkiter.h	28478	0644	edit dl rm
bytestream.h	11013	0644	edit dl rm
bytestrie.h	21268	0644	edit dl rm
bytestriebuilder.h	7640	0644	edit dl rm
calendar.h	108424	0644	edit dl rm
caniter.h	7621	0644	edit dl rm
casemap.h	25933	0644	edit dl rm
char16ptr.h	7393	0644	edit dl rm
chariter.h	24638	0644	edit dl rm
choicfmt.h	24544	0644	edit dl rm
coleitr.h	14102	0644	edit dl rm
coll.h	57615	0644	edit dl rm
compactdecimalformat.h	7047	0644	edit dl rm
curramt.h	3869	0644	edit dl rm
currpinf.h	7479	0644	edit dl rm
currunit.h	4112	0644	edit dl rm
datefmt.h	41690	0644	edit dl rm
dbbi.h	1223	0644	edit dl rm
dcfmtsym.h	21101	0644	edit dl rm
decimfmt.h	89676	0644	edit dl rm
docmain.h	7380	0644	edit dl rm
dtfmtsym.h	39126	0644	edit dl rm
dtintrv.h	3935	0644	edit dl rm
dtitvfmt.h	50448	0644	edit dl rm
dtitvinf.h	19072	0644	edit dl rm
dtptngen.h	26692	0644	edit dl rm
dtrule.h	8898	0644	edit dl rm
edits.h	21237	0644	edit dl rm
enumset.h	2130	0644	edit dl rm
errorcode.h	4956	0644	edit dl rm
fieldpos.h	8906	0644	edit dl rm
filteredbrk.h	5501	0644	edit dl rm
fmtable.h	25020	0644	edit dl rm
format.h	12802	0644	edit dl rm
formattedvalue.h	9987	0644	edit dl rm
fpositer.h	3107	0644	edit dl rm
gender.h	3408	0644	edit dl rm
gregocal.h	32642	0644	edit dl rm
icudataver.h	1049	0644	edit dl rm
icuplug.h	12109	0644	edit dl rm
idna.h	13000	0644	edit dl rm
listformatter.h	9004	0644	edit dl rm
localebuilder.h	11350	0644	edit dl rm
localematcher.h	27467	0644	edit dl rm
localpointer.h	19825	0644	edit dl rm
locdspnm.h	7292	0644	edit dl rm
locid.h	48804	0644	edit dl rm
measfmt.h	11690	0644	edit dl rm
measunit.h	107613	0644	edit dl rm
measure.h	4431	0644	edit dl rm
messagepattern.h	34517	0644	edit dl rm
msgfmt.h	45278	0644	edit dl rm
normalizer2.h	34466	0644	edit dl rm
normlzr.h	31690	0644	edit dl rm
nounit.h	2305	0644	edit dl rm
numberformatter.h	94505	0644	edit dl rm
numberrangeformatter.h	25790	0644	edit dl rm
numfmt.h	51034	0644	edit dl rm
numsys.h	7509	0644	edit dl rm
parseerr.h	3155	0644	edit dl rm
parsepos.h	5699	0644	edit dl rm
platform.h	28768	0644	edit dl rm
plurfmt.h	25847	0644	edit dl rm
plurrule.h	21316	0644	edit dl rm
ptypes.h	3577	0644	edit dl rm
putil.h	6471	0644	edit dl rm
rbbi.h	28413	0644	edit dl rm
rbnf.h	50021	0644	edit dl rm
rbtz.h	16210	0644	edit dl rm
regex.h	86385	0644	edit dl rm
region.h	9402	0644	edit dl rm
reldatefmt.h	22751	0644	edit dl rm
rep.h	9599	0644	edit dl rm
resbund.h	18513	0644	edit dl rm
schriter.h	6511	0644	edit dl rm
scientificnumberformatter.h	6589	0644	edit dl rm
search.h	22755	0644	edit dl rm
selfmt.h	14686	0644	edit dl rm
simpleformatter.h	12888	0644	edit dl rm
simpletz.h	46798	0644	edit dl rm
smpdtfmt.h	72778	0644	edit dl rm
sortkey.h	11452	0644	edit dl rm
std_string.h	1076	0644	edit dl rm
strenum.h	10157	0644	edit dl rm
stringoptions.h	5926	0644	edit dl rm
stringpiece.h	10287	0644	edit dl rm
stringtriebuilder.h	15842	0644	edit dl rm
stsearch.h	21926	0644	edit dl rm
symtable.h	4374	0644	edit dl rm
tblcoll.h	37801	0644	edit dl rm
timezone.h	44858	0644	edit dl rm
tmunit.h	3479	0644	edit dl rm
tmutamt.h	5029	0644	edit dl rm
tmutfmt.h	7602	0644	edit dl rm
translit.h	67397	0644	edit dl rm
tzfmt.h	43961	0644	edit dl rm
tznames.h	17251	0644	edit dl rm
tzrule.h	36450	0644	edit dl rm
tztrans.h	6278	0644	edit dl rm
ubidi.h	91759	0644	edit dl rm
ubiditransform.h	13003	0644	edit dl rm
ubrk.h	25043	0644	edit dl rm
ucal.h	62463	0644	edit dl rm
ucasemap.h	15579	0644	edit dl rm
ucat.h	5478	0644	edit dl rm
uchar.h	148111	0644	edit dl rm
ucharstrie.h	23066	0644	edit dl rm
ucharstriebuilder.h	7645	0644	edit dl rm
uchriter.h	13747	0644	edit dl rm
uclean.h	11468	0644	edit dl rm
ucnv.h	85051	0644	edit dl rm
ucnvsel.h	6339	0644	edit dl rm
ucnv_cb.h	6738	0644	edit dl rm
ucnv_err.h	21481	0644	edit dl rm
ucol.h	62987	0644	edit dl rm
ucoleitr.h	10056	0644	edit dl rm
uconfig.h	12356	0644	edit dl rm
ucpmap.h	5663	0644	edit dl rm
ucptrie.h	23044	0644	edit dl rm
ucsdet.h	15043	0644	edit dl rm
ucurr.h	17122	0644	edit dl rm
udat.h	63902	0644	edit dl rm
udata.h	16004	0644	edit dl rm
udateintervalformat.h	12218	0644	edit dl rm
udatpg.h	27405	0644	edit dl rm
udisplaycontext.h	6084	0644	edit dl rm
uenum.h	7981	0644	edit dl rm
ufieldpositer.h	4513	0644	edit dl rm
uformattable.h	11233	0644	edit dl rm
uformattedvalue.h	12600	0644	edit dl rm
ugender.h	2106	0644	edit dl rm
uidna.h	34229	0644	edit dl rm
uiter.h	23299	0644	edit dl rm
uldnames.h	10733	0644	edit dl rm
ulistformatter.h	11043	0644	edit dl rm
uloc.h	55936	0644	edit dl rm
ulocdata.h	11572	0644	edit dl rm
umachine.h	16439	0644	edit dl rm
umisc.h	1365	0644	edit dl rm
umsg.h	24832	0644	edit dl rm
umutablecptrie.h	8490	0644	edit dl rm
unifilt.h	4091	0644	edit dl rm
unifunct.h	4151	0644	edit dl rm
unimatch.h	6244	0644	edit dl rm
unirepl.h	3464	0644	edit dl rm
uniset.h	68108	0644	edit dl rm
unistr.h	174627	0644	edit dl rm
unorm.h	21042	0644	edit dl rm
unorm2.h	25269	0644	edit dl rm
unum.h	56269	0644	edit dl rm
unumberformatter.h	31177	0644	edit dl rm
unumberrangeformatter.h	15737	0644	edit dl rm
unumsys.h	7430	0644	edit dl rm
uobject.h	10934	0644	edit dl rm
upluralrules.h	8997	0644	edit dl rm
uregex.h	73719	0644	edit dl rm
uregion.h	10047	0644	edit dl rm
ureldatefmt.h	17448	0644	edit dl rm
urename.h	137853	0644	edit dl rm
urep.h	5507	0644	edit dl rm
ures.h	37418	0644	edit dl rm
uscript.h	28291	0644	edit dl rm
usearch.h	40153	0644	edit dl rm
uset.h	45503	0644	edit dl rm
usetiter.h	9910	0644	edit dl rm
ushape.h	18430	0644	edit dl rm
uspoof.h	67425	0644	edit dl rm
usprep.h	8382	0644	edit dl rm
ustdio.h	39482	0644	edit dl rm
ustream.h	1934	0644	edit dl rm
ustring.h	74096	0644	edit dl rm
ustringtrie.h	3224	0644	edit dl rm
utext.h	59471	0644	edit dl rm
utf.h	8057	0644	edit dl rm
utf8.h	31572	0644	edit dl rm
utf16.h	23910	0644	edit dl rm
utf32.h	763	0644	edit dl rm
utf_old.h	46929	0644	edit dl rm
utmscale.h	14107	0644	edit dl rm
utrace.h	17595	0644	edit dl rm
utrans.h	26157	0644	edit dl rm
utypes.h	31807	0644	edit dl rm
uvernum.h	6839	0644	edit dl rm
uversion.h	6137	0644	edit dl rm
vtzone.h	21303	0644	edit dl rm

Edit: /usr/include/unicode/uset.h (45503B)

// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
*   Copyright (C) 2002-2014, International Business Machines
*   Corporation and others.  All Rights Reserved.
*
*******************************************************************************
*   file name:  uset.h
*   encoding:   UTF-8
*   tab size:   8 (not used)
*   indentation:4
*
*   created on: 2002mar07
*   created by: Markus W. Scherer
*
*   C version of UnicodeSet.
*/

/**
 * \file
 * \brief C API: Unicode Set
 *
 * This is a C wrapper around the C++ UnicodeSet class.
 */

#ifndef __USET_H__
#define __USET_H__

#include "unicode/utypes.h"
#include "unicode/uchar.h"

#if U_SHOW_CPLUSPLUS_API
#include "unicode/localpointer.h"
#endif   // U_SHOW_CPLUSPLUS_API

#ifndef USET_DEFINED

#ifndef U_IN_DOXYGEN
#define USET_DEFINED
#endif
/**
 * USet is the C API type corresponding to C++ class UnicodeSet.
 * Use the uset_* API to manipulate.  Create with
 * uset_open*, and destroy with uset_close.
 * @stable ICU 2.4
 */
typedef struct USet USet;
#endif

/**
 * Bitmask values to be passed to uset_openPatternOptions() or
 * uset_applyPattern() taking an option parameter.
 * @stable ICU 2.4
 */
enum {
    /**
     * Ignore white space within patterns unless quoted or escaped.
     * @stable ICU 2.4
     */
    USET_IGNORE_SPACE = 1,

/**
     * Enable case insensitive matching.  E.g., "[ab]" with this flag
     * will match 'a', 'A', 'b', and 'B'.  "[^ab]" with this flag will
     * match all except 'a', 'A', 'b', and 'B'. This performs a full
     * closure over case mappings, e.g. U+017F for s.
     *
     * The resulting set is a superset of the input for the code points but
     * not for the strings.
     * It performs a case mapping closure of the code points and adds
     * full case folding strings for the code points, and reduces strings of
     * the original set to their full case folding equivalents.
     *
     * This is designed for case-insensitive matches, for example
     * in regular expressions. The full code point case closure allows checking of
     * an input character directly against the closure set.
     * Strings are matched by comparing the case-folded form from the closure
     * set with an incremental case folding of the string in question.
     *
     * The closure set will also contain single code points if the original
     * set contained case-equivalent strings (like U+00DF for "ss" or "Ss" etc.).
     * This is not necessary (that is, redundant) for the above matching method
     * but results in the same closure sets regardless of whether the original
     * set contained the code point or a string.
     *
     * @stable ICU 2.4
     */
    USET_CASE_INSENSITIVE = 2,

/**
     * Enable case insensitive matching.  E.g., "[ab]" with this flag
     * will match 'a', 'A', 'b', and 'B'.  "[^ab]" with this flag will
     * match all except 'a', 'A', 'b', and 'B'. This adds the lower-,
     * title-, and uppercase mappings as well as the case folding
     * of each existing element in the set.
     * @stable ICU 3.2
     */
    USET_ADD_CASE_MAPPINGS = 4
};

/**
 * Argument values for whether span() and similar functions continue while
 * the current character is contained vs. not contained in the set.
 *
 * The functionality is straightforward for sets with only single code points,
 * without strings (which is the common case):
 * - USET_SPAN_CONTAINED and USET_SPAN_SIMPLE work the same.
 * - USET_SPAN_CONTAINED and USET_SPAN_SIMPLE are inverses of USET_SPAN_NOT_CONTAINED.
 * - span() and spanBack() partition any string the same way when
 * alternating between span(USET_SPAN_NOT_CONTAINED) and
 * span(either "contained" condition).
 * - Using a complemented (inverted) set and the opposite span conditions
 * yields the same results.
 *
 * When a set contains multi-code point strings, then these statements may not
 * be true, depending on the strings in the set (for example, whether they
 * overlap with each other) and the string that is processed.
 * For a set with strings:
 * - The complement of the set contains the opposite set of code points,
 * but the same set of strings.
 * Therefore, complementing both the set and the span conditions
 * may yield different results.
 * - When starting spans at different positions in a string
 * (span(s, ...) vs. span(s+1, ...)) the ends of the spans may be different
 * because a set string may start before the later position.
 * - span(USET_SPAN_SIMPLE) may be shorter than
 * span(USET_SPAN_CONTAINED) because it will not recursively try
 * all possible paths.
 * For example, with a set which contains the three strings "xy", "xya" and "ax",
 * span("xyax", USET_SPAN_CONTAINED) will return 4 but
 * span("xyax", USET_SPAN_SIMPLE) will return 3.
 * span(USET_SPAN_SIMPLE) will never be longer than
 * span(USET_SPAN_CONTAINED).
 * - With either "contained" condition, span() and spanBack() may partition
 * a string in different ways.
 * For example, with a set which contains the two strings "ab" and "ba",
 * and when processing the string "aba",
 * span() will yield contained/not-contained boundaries of { 0, 2, 3 }
 * while spanBack() will yield boundaries of { 0, 1, 3 }.
 *
 * Note: If it is important to get the same boundaries whether iterating forward
 * or backward through a string, then either only span() should be used and
 * the boundaries cached for backward operation, or an ICU BreakIterator
 * could be used.
 *
 * Note: Unpaired surrogates are treated like surrogate code points.
 * Similarly, set strings match only on code point boundaries,
 * never in the middle of a surrogate pair.
 * Illegal UTF-8 sequences are treated like U+FFFD.
 * When processing UTF-8 strings, malformed set strings
 * (strings with unpaired surrogates which cannot be converted to UTF-8)
 * are ignored.
 *
 * @stable ICU 3.8
 */
typedef enum USetSpanCondition {
 /**
 * Continues a span() while there is no set element at the current position.
 * Increments by one code point at a time.
 * Stops before the first set element (character or string).
 * (For code points only, this is like while contains(current)==false).
 *
 * When span() returns, the substring between where it started and the position
 * it returned consists only of characters that are not in the set,
 * and none of its strings overlap with the span.
 *
 * @stable ICU 3.8
 */
 USET_SPAN_NOT_CONTAINED = 0,
 /**
 * Spans the longest substring that is a concatenation of set elements (characters or strings).
 * (For characters only, this is like while contains(current)==true).
 *
 * When span() returns, the substring between where it started and the position
 * it returned consists only of set elements (characters or strings) that are in the set.
 *
 * If a set contains strings, then the span will be the longest substring for which there
 * exists at least one non-overlapping concatenation of set elements (characters or strings).
 * This is equivalent to a POSIX regular expression for <code>(OR of each set element)*</code>.
 * (Java/ICU/Perl regex stops at the first match of an OR.)
 *
 * @stable ICU 3.8
 */
 USET_SPAN_CONTAINED = 1,
 /**
 * Continues a span() while there is a set element at the current position.
 * Increments by the longest matching element at each position.
 * (For characters only, this is like while contains(current)==true).
 *
 * When span() returns, the substring between where it started and the position
 * it returned consists only of set elements (characters or strings) that are in the set.
 *
 * If a set only contains single characters, then this is the same
 * as USET_SPAN_CONTAINED.
 *
 * If a set contains strings, then the span will be the longest substring
 * with a match at each position with the longest single set element (character or string).
 *
 * Use this span condition together with other longest-match algorithms,
 * such as ICU converters (ucnv_getUnicodeSet()).
 *
 * @stable ICU 3.8
 */
 USET_SPAN_SIMPLE = 2,
#ifndef U_HIDE_DEPRECATED_API
 /**
 * One more than the last span condition.
 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
 */
 USET_SPAN_CONDITION_COUNT
#endif // U_HIDE_DEPRECATED_API
} USetSpanCondition;

enum {
    /**
     * Capacity of USerializedSet::staticArray.
     * Enough for any single-code point set.
     * Also provides padding for nice sizeof(USerializedSet).
     * @stable ICU 2.4
     */
    USET_SERIALIZED_STATIC_ARRAY_CAPACITY=8
};

/**
 * A serialized form of a Unicode set.  Limited manipulations are
 * possible directly on a serialized set.  See below.
 * @stable ICU 2.4
 */
typedef struct USerializedSet {
    /**
     * The serialized Unicode Set.
     * @stable ICU 2.4
     */
    const uint16_t *array;
    /**
     * The length of the array that contains BMP characters.
     * @stable ICU 2.4
     */
    int32_t bmpLength;
    /**
     * The total length of the array.
     * @stable ICU 2.4
     */
    int32_t length;
    /**
     * A small buffer for the array to reduce memory allocations.
     * @stable ICU 2.4
     */
    uint16_t staticArray[USET_SERIALIZED_STATIC_ARRAY_CAPACITY];
} USerializedSet;

/*********************************************************************
 * USet API
 *********************************************************************/

/**
 * Create an empty USet object.
 * Equivalent to uset_open(1, 0).
 * @return a newly created USet.  The caller must call uset_close() on
 * it when done.
 * @stable ICU 4.2
 */
U_CAPI USet* U_EXPORT2
uset_openEmpty(void);

/**
 * Creates a USet object that contains the range of characters
 * start..end, inclusive. If <code>start > end</code> 
 * then an empty set is created (same as using uset_openEmpty()).
 * @param start first character of the range, inclusive
 * @param end last character of the range, inclusive
 * @return a newly created USet. The caller must call uset_close() on
 * it when done.
 * @stable ICU 2.4
 */
U_CAPI USet* U_EXPORT2
uset_open(UChar32 start, UChar32 end);

/**
 * Creates a set from the given pattern.  See the UnicodeSet class
 * description for the syntax of the pattern language.
 * @param pattern a string specifying what characters are in the set
 * @param patternLength the length of the pattern, or -1 if null
 * terminated
 * @param ec the error code
 * @stable ICU 2.4
 */
U_CAPI USet* U_EXPORT2
uset_openPattern(const UChar* pattern, int32_t patternLength,
                 UErrorCode* ec);

/**
 * Creates a set from the given pattern.  See the UnicodeSet class
 * description for the syntax of the pattern language.
 * @param pattern a string specifying what characters are in the set
 * @param patternLength the length of the pattern, or -1 if null
 * terminated
 * @param options bitmask for options to apply to the pattern.
 * Valid options are USET_IGNORE_SPACE and USET_CASE_INSENSITIVE.
 * @param ec the error code
 * @stable ICU 2.4
 */
U_CAPI USet* U_EXPORT2
uset_openPatternOptions(const UChar* pattern, int32_t patternLength,
                 uint32_t options,
                 UErrorCode* ec);

/**
 * Disposes of the storage used by a USet object.  This function should
 * be called exactly once for objects returned by uset_open().
 * @param set the object to dispose of
 * @stable ICU 2.4
 */
U_CAPI void U_EXPORT2
uset_close(USet* set);

#if U_SHOW_CPLUSPLUS_API

U_NAMESPACE_BEGIN

/**
 * \class LocalUSetPointer
 * "Smart pointer" class, closes a USet via uset_close().
 * For most methods see the LocalPointerBase base class.
 *
 * @see LocalPointerBase
 * @see LocalPointer
 * @stable ICU 4.4
 */
U_DEFINE_LOCAL_OPEN_POINTER(LocalUSetPointer, USet, uset_close);

U_NAMESPACE_END

#endif

/**
 * Returns a copy of this object.
 * If this set is frozen, then the clone will be frozen as well.
 * Use uset_cloneAsThawed() for a mutable clone of a frozen set.
 * @param set the original set
 * @return the newly allocated copy of the set
 * @see uset_cloneAsThawed
 * @stable ICU 3.8
 */
U_CAPI USet * U_EXPORT2
uset_clone(const USet *set);

/**
 * Determines whether the set has been frozen (made immutable) or not.
 * See the ICU4J Freezable interface for details.
 * @param set the set
 * @return true/false for whether the set has been frozen
 * @see uset_freeze
 * @see uset_cloneAsThawed
 * @stable ICU 3.8
 */
U_CAPI UBool U_EXPORT2
uset_isFrozen(const USet *set);

/**
 * Freeze the set (make it immutable).
 * Once frozen, it cannot be unfrozen and is therefore thread-safe
 * until it is deleted.
 * See the ICU4J Freezable interface for details.
 * Freezing the set may also make some operations faster, for example
 * uset_contains() and uset_span().
 * A frozen set will not be modified. (It remains frozen.)
 * @param set the set
 * @return the same set, now frozen
 * @see uset_isFrozen
 * @see uset_cloneAsThawed
 * @stable ICU 3.8
 */
U_CAPI void U_EXPORT2
uset_freeze(USet *set);

/**
 * Clone the set and make the clone mutable.
 * See the ICU4J Freezable interface for details.
 * @param set the set
 * @return the mutable clone
 * @see uset_freeze
 * @see uset_isFrozen
 * @see uset_clone
 * @stable ICU 3.8
 */
U_CAPI USet * U_EXPORT2
uset_cloneAsThawed(const USet *set);

/**
 * Causes the USet object to represent the range <code>start - end</code>.
 * If <code>start > end</code> then this USet is set to an empty range.
 * A frozen set will not be modified.
 * @param set the object to set to the given range
 * @param start first character in the set, inclusive
 * @param end last character in the set, inclusive
 * @stable ICU 3.2
 */
U_CAPI void U_EXPORT2
uset_set(USet* set,
 UChar32 start, UChar32 end);

/**
 * Modifies the set to represent the set specified by the given
 * pattern. See the UnicodeSet class description for the syntax of 
 * the pattern language. See also the User Guide chapter about UnicodeSet.
 * Empties the set passed before applying the pattern.
 * A frozen set will not be modified.
 * @param set The set to which the pattern is to be applied. 
 * @param pattern A pointer to UChar string specifying what characters are in the set.
 * The character at pattern[0] must be a '['.
 * @param patternLength The length of the UChar string. -1 if NUL terminated.
 * @param options A bitmask for options to apply to the pattern.
 * Valid options are USET_IGNORE_SPACE and USET_CASE_INSENSITIVE.
 * @param status Returns an error if the pattern cannot be parsed.
 * @return Upon successful parse, the value is either
 * the index of the character after the closing ']' 
 * of the parsed pattern.
 * If the status code indicates failure, then the return value 
 * is the index of the error in the source.
 *
 * @stable ICU 2.8
 */
U_CAPI int32_t U_EXPORT2 
uset_applyPattern(USet *set,
 const UChar *pattern, int32_t patternLength,
 uint32_t options,
 UErrorCode *status);

/**
 * Modifies the set to contain those code points which have the given value
 * for the given binary or enumerated property, as returned by
 * u_getIntPropertyValue.  Prior contents of this set are lost.
 * A frozen set will not be modified.
 *
 * @param set the object to contain the code points defined by the property
 *
 * @param prop a property in the range UCHAR_BIN_START..UCHAR_BIN_LIMIT-1
 * or UCHAR_INT_START..UCHAR_INT_LIMIT-1
 * or UCHAR_MASK_START..UCHAR_MASK_LIMIT-1.
 *
 * @param value a value in the range u_getIntPropertyMinValue(prop)..
 * u_getIntPropertyMaxValue(prop), with one exception.  If prop is
 * UCHAR_GENERAL_CATEGORY_MASK, then value should not be a UCharCategory, but
 * rather a mask value produced by U_GET_GC_MASK().  This allows grouped
 * categories such as [:L:] to be represented.
 *
 * @param ec error code input/output parameter
 *
 * @stable ICU 3.2
 */
U_CAPI void U_EXPORT2
uset_applyIntPropertyValue(USet* set,
                           UProperty prop, int32_t value, UErrorCode* ec);

/**
 * Modifies the set to contain those code points which have the
 * given value for the given property.  Prior contents of this
 * set are lost.
 * A frozen set will not be modified.
 *
 * @param set the object to contain the code points defined by the given
 * property and value alias
 *
 * @param prop a string specifying a property alias, either short or long.
 * The name is matched loosely.  See PropertyAliases.txt for names and a
 * description of loose matching.  If the value string is empty, then this
 * string is interpreted as either a General_Category value alias, a Script
 * value alias, a binary property alias, or a special ID.  Special IDs are
 * matched loosely and correspond to the following sets:
 *
 * "ANY" = [\\u0000-\\U0010FFFF],
 * "ASCII" = [\\u0000-\\u007F],
 * "Assigned" = [:^Cn:].
 *
 * @param propLength the length of the prop, or -1 if NULL
 *
 * @param value a string specifying a value alias, either short or long.
 * The name is matched loosely.  See PropertyValueAliases.txt for names
 * and a description of loose matching.  In addition to aliases listed,
 * numeric values and canonical combining classes may be expressed
 * numerically, e.g., ("nv", "0.5") or ("ccc", "220").  The value string
 * may also be empty.
 *
 * @param valueLength the length of the value, or -1 if NULL
 *
 * @param ec error code input/output parameter
 *
 * @stable ICU 3.2
 */
U_CAPI void U_EXPORT2
uset_applyPropertyAlias(USet* set,
                        const UChar *prop, int32_t propLength,
                        const UChar *value, int32_t valueLength,
                        UErrorCode* ec);

/**
 * Return true if the given position, in the given pattern, appears
 * to be the start of a UnicodeSet pattern.
 *
 * @param pattern a string specifying the pattern
 * @param patternLength the length of the pattern, or -1 if NULL
 * @param pos the given position
 * @stable ICU 3.2
 */
U_CAPI UBool U_EXPORT2
uset_resemblesPattern(const UChar *pattern, int32_t patternLength,
                      int32_t pos);

/**
 * Returns a string representation of this set.  If the result of
 * calling this function is passed to a uset_openPattern(), it
 * will produce another set that is equal to this one.
 * @param set the set
 * @param result the string to receive the rules, may be NULL
 * @param resultCapacity the capacity of result, may be 0 if result is NULL
 * @param escapeUnprintable if true then convert unprintable
 * character to their hex escape representations, \\uxxxx or
 * \\Uxxxxxxxx.  Unprintable characters are those other than
 * U+000A, U+0020..U+007E.
 * @param ec error code.
 * @return length of string, possibly larger than resultCapacity
 * @stable ICU 2.4
 */
U_CAPI int32_t U_EXPORT2
uset_toPattern(const USet* set,
               UChar* result, int32_t resultCapacity,
               UBool escapeUnprintable,
               UErrorCode* ec);

/**
 * Adds the given character to the given USet.  After this call,
 * uset_contains(set, c) will return true.
 * A frozen set will not be modified.
 * @param set the object to which to add the character
 * @param c the character to add
 * @stable ICU 2.4
 */
U_CAPI void U_EXPORT2
uset_add(USet* set, UChar32 c);

/**
 * Adds all of the elements in the specified set to this set if
 * they're not already present. This operation effectively
 * modifies this set so that its value is the union of the two
 * sets. The behavior of this operation is unspecified if the specified
 * collection is modified while the operation is in progress.
 * A frozen set will not be modified.
 *
 * @param set the object to which to add the set
 * @param additionalSet the source set whose elements are to be added to this set.
 * @stable ICU 2.6
 */
U_CAPI void U_EXPORT2
uset_addAll(USet* set, const USet *additionalSet);

/**
 * Adds the given range of characters to the given USet.  After this call,
 * uset_contains(set, start, end) will return true.
 * A frozen set will not be modified.
 * @param set the object to which to add the character
 * @param start the first character of the range to add, inclusive
 * @param end the last character of the range to add, inclusive
 * @stable ICU 2.2
 */
U_CAPI void U_EXPORT2
uset_addRange(USet* set, UChar32 start, UChar32 end);

/**
 * Adds the given string to the given USet.  After this call,
 * uset_containsString(set, str, strLen) will return true.
 * A frozen set will not be modified.
 * @param set the object to which to add the character
 * @param str the string to add
 * @param strLen the length of the string or -1 if null terminated.
 * @stable ICU 2.4
 */
U_CAPI void U_EXPORT2
uset_addString(USet* set, const UChar* str, int32_t strLen);

/**
 * Adds each of the characters in this string to the set. Note: "ch" => {"c", "h"}
 * If this set already contains any particular character, it has no effect on that character.
 * A frozen set will not be modified.
 * @param set the object to which to add the character
 * @param str the source string
 * @param strLen the length of the string or -1 if null terminated.
 * @stable ICU 3.4
 */
U_CAPI void U_EXPORT2
uset_addAllCodePoints(USet* set, const UChar *str, int32_t strLen);

/**
 * Removes the given character from the given USet.  After this call,
 * uset_contains(set, c) will return false.
 * A frozen set will not be modified.
 * @param set the object from which to remove the character
 * @param c the character to remove
 * @stable ICU 2.4
 */
U_CAPI void U_EXPORT2
uset_remove(USet* set, UChar32 c);

/**
 * Removes the given range of characters from the given USet.  After this call,
 * uset_contains(set, start, end) will return false.
 * A frozen set will not be modified.
 * @param set the object to which to add the character
 * @param start the first character of the range to remove, inclusive
 * @param end the last character of the range to remove, inclusive
 * @stable ICU 2.2
 */
U_CAPI void U_EXPORT2
uset_removeRange(USet* set, UChar32 start, UChar32 end);

/**
 * Removes the given string to the given USet.  After this call,
 * uset_containsString(set, str, strLen) will return false.
 * A frozen set will not be modified.
 * @param set the object to which to add the character
 * @param str the string to remove
 * @param strLen the length of the string or -1 if null terminated.
 * @stable ICU 2.4
 */
U_CAPI void U_EXPORT2
uset_removeString(USet* set, const UChar* str, int32_t strLen);

#ifndef U_HIDE_DRAFT_API
/**
 * Removes EACH of the characters in this string. Note: "ch" == {"c", "h"}
 * A frozen set will not be modified.
 *
 * @param set the object to be modified
 * @param str the string
 * @param length the length of the string, or -1 if NUL-terminated
 * @draft ICU 69
 */
U_CAPI void U_EXPORT2
uset_removeAllCodePoints(USet *set, const UChar *str, int32_t length);
#endif  // U_HIDE_DRAFT_API

/**
 * Removes from this set all of its elements that are contained in the
 * specified set. This operation effectively modifies this
 * set so that its value is the asymmetric set difference of
 * the two sets.
 * A frozen set will not be modified.
 * @param set the object from which the elements are to be removed
 * @param removeSet the object that defines which elements will be
 * removed from this set
 * @stable ICU 3.2
 */
U_CAPI void U_EXPORT2
uset_removeAll(USet* set, const USet* removeSet);

/**
 * Retain only the elements in this set that are contained in the
 * specified range. If <code>start > end</code> then an empty range is
 * retained, leaving the set empty. This is equivalent to
 * a boolean logic AND, or a set INTERSECTION.
 * A frozen set will not be modified.
 *
 * @param set the object for which to retain only the specified range
 * @param start first character, inclusive, of range
 * @param end last character, inclusive, of range
 * @stable ICU 3.2
 */
U_CAPI void U_EXPORT2
uset_retain(USet* set, UChar32 start, UChar32 end);

#ifndef U_HIDE_DRAFT_API
/**
 * Retains only the specified string from this set if it is present.
 * Upon return this set will be empty if it did not contain s, or
 * will only contain s if it did contain s.
 * A frozen set will not be modified.
 *
 * @param set the object to be modified
 * @param str the string
 * @param length the length of the string, or -1 if NUL-terminated
 * @draft ICU 69
 */
U_CAPI void U_EXPORT2
uset_retainString(USet *set, const UChar *str, int32_t length);

/**
 * Retains EACH of the characters in this string. Note: "ch" == {"c", "h"}
 * A frozen set will not be modified.
 *
 * @param set the object to be modified
 * @param str the string
 * @param length the length of the string, or -1 if NUL-terminated
 * @draft ICU 69
 */
U_CAPI void U_EXPORT2
uset_retainAllCodePoints(USet *set, const UChar *str, int32_t length);
#endif  // U_HIDE_DRAFT_API

/**
 * Retains only the elements in this set that are contained in the
 * specified set. In other words, removes from this set all of
 * its elements that are not contained in the specified set. This
 * operation effectively modifies this set so that its value is
 * the intersection of the two sets.
 * A frozen set will not be modified.
 *
 * @param set the object on which to perform the retain
 * @param retain set that defines which elements this set will retain
 * @stable ICU 3.2
 */
U_CAPI void U_EXPORT2
uset_retainAll(USet* set, const USet* retain);

/**
 * Reallocate this objects internal structures to take up the least
 * possible space, without changing this object's value.
 * A frozen set will not be modified.
 *
 * @param set the object on which to perform the compact
 * @stable ICU 3.2
 */
U_CAPI void U_EXPORT2
uset_compact(USet* set);

/**
 * This is equivalent to
 * <code>uset_complementRange(set, 0, 0x10FFFF)</code>.
 *
 * Note: This performs a symmetric difference with all code points
 * and thus retains all multicharacter strings.
 * In order to achieve a “code point complement” (all code points minus this set),
 * the easiest is to <code>uset_complement(set); uset_removeAllStrings(set);</code>.
 *
 * A frozen set will not be modified.
 * @param set the set
 * @stable ICU 2.4
 */
U_CAPI void U_EXPORT2
uset_complement(USet* set);

#ifndef U_HIDE_DRAFT_API
/**
 * Complements the specified range in this set. Any character in
 * the range will be removed if it is in this set, or will be
 * added if it is not in this set. If <code>start > end</code>
 * then an empty range is complemented, leaving the set unchanged.
 * This is equivalent to a boolean logic XOR.
 * A frozen set will not be modified.
 *
 * @param set the object to be modified
 * @param start first character, inclusive, of range
 * @param end last character, inclusive, of range
 * @draft ICU 69
 */
U_CAPI void U_EXPORT2
uset_complementRange(USet *set, UChar32 start, UChar32 end);

/**
 * Complements the specified string in this set.
 * The string will be removed if it is in this set, or will be added if it is not in this set.
 * A frozen set will not be modified.
 *
 * @param set the object to be modified
 * @param str the string
 * @param length the length of the string, or -1 if NUL-terminated
 * @draft ICU 69
 */
U_CAPI void U_EXPORT2
uset_complementString(USet *set, const UChar *str, int32_t length);

/**
 * Complements EACH of the characters in this string. Note: "ch" == {"c", "h"}
 * A frozen set will not be modified.
 *
 * @param set the object to be modified
 * @param str the string
 * @param length the length of the string, or -1 if NUL-terminated
 * @draft ICU 69
 */
U_CAPI void U_EXPORT2
uset_complementAllCodePoints(USet *set, const UChar *str, int32_t length);
#endif  // U_HIDE_DRAFT_API

/**
 * Complements in this set all elements contained in the specified
 * set.  Any character in the other set will be removed if it is
 * in this set, or will be added if it is not in this set.
 * A frozen set will not be modified.
 *
 * @param set the set with which to complement
 * @param complement set that defines which elements will be xor'ed
 * from this set.
 * @stable ICU 3.2
 */
U_CAPI void U_EXPORT2
uset_complementAll(USet* set, const USet* complement);

/**
 * Removes all of the elements from this set.  This set will be
 * empty after this call returns.
 * A frozen set will not be modified.
 * @param set the set
 * @stable ICU 2.4
 */
U_CAPI void U_EXPORT2
uset_clear(USet* set);

/**
 * Close this set over the given attribute.  For the attribute
 * USET_CASE, the result is to modify this set so that:
 *
 * 1. For each character or string 'a' in this set, all strings or
 * characters 'b' such that foldCase(a) == foldCase(b) are added
 * to this set.
 *
 * 2. For each string 'e' in the resulting set, if e !=
 * foldCase(e), 'e' will be removed.
 *
 * Example: [aq\\u00DF{Bc}{bC}{Fi}] => [aAqQ\\u00DF\\uFB01{ss}{bc}{fi}]
 *
 * (Here foldCase(x) refers to the operation u_strFoldCase, and a
 * == b denotes that the contents are the same, not pointer
 * comparison.)
 *
 * A frozen set will not be modified.
 *
 * @param set the set
 *
 * @param attributes bitmask for attributes to close over.
 * Currently only the USET_CASE bit is supported.  Any undefined bits
 * are ignored.
 * @stable ICU 4.2
 */
U_CAPI void U_EXPORT2
uset_closeOver(USet* set, int32_t attributes);

/**
 * Remove all strings from this set.
 *
 * @param set the set
 * @stable ICU 4.2
 */
U_CAPI void U_EXPORT2
uset_removeAllStrings(USet* set);

/**
 * Returns true if the given USet contains no characters and no
 * strings.
 * @param set the set
 * @return true if set is empty
 * @stable ICU 2.4
 */
U_CAPI UBool U_EXPORT2
uset_isEmpty(const USet* set);

#ifndef U_HIDE_DRAFT_API
/**
 * @param set the set
 * @return true if this set contains multi-character strings or the empty string.
 * @draft ICU 70
 */
U_CAPI UBool U_EXPORT2
uset_hasStrings(const USet *set);
#endif  // U_HIDE_DRAFT_API

/**
 * Returns true if the given USet contains the given character.
 * This function works faster with a frozen set.
 * @param set the set
 * @param c The codepoint to check for within the set
 * @return true if set contains c
 * @stable ICU 2.4
 */
U_CAPI UBool U_EXPORT2
uset_contains(const USet* set, UChar32 c);

/**
 * Returns true if the given USet contains all characters c
 * where start <= c && c <= end.
 * @param set the set
 * @param start the first character of the range to test, inclusive
 * @param end the last character of the range to test, inclusive
 * @return true if set contains the range
 * @stable ICU 2.2
 */
U_CAPI UBool U_EXPORT2
uset_containsRange(const USet* set, UChar32 start, UChar32 end);

/**
 * Returns true if the given USet contains the given string.
 * @param set the set
 * @param str the string
 * @param strLen the length of the string or -1 if null terminated.
 * @return true if set contains str
 * @stable ICU 2.4
 */
U_CAPI UBool U_EXPORT2
uset_containsString(const USet* set, const UChar* str, int32_t strLen);

/**
 * Returns the index of the given character within this set, where
 * the set is ordered by ascending code point. If the character
 * is not in this set, return -1. The inverse of this method is
 * <code>charAt()</code>.
 * @param set the set
 * @param c the character to obtain the index for
 * @return an index from 0..size()-1, or -1
 * @stable ICU 3.2
 */
U_CAPI int32_t U_EXPORT2
uset_indexOf(const USet* set, UChar32 c);

/**
 * Returns the character at the given index within this set, where
 * the set is ordered by ascending code point. If the index is
 * out of range for characters, returns (UChar32)-1.
 * The inverse of this method is <code>indexOf()</code>.
 *
 * For iteration, this is slower than uset_getRangeCount()/uset_getItemCount()
 * with uset_getItem(), because for each call it skips linearly over <code>index</code>
 * characters in the ranges.
 *
 * @param set the set
 * @param charIndex an index from 0..size()-1 to obtain the char for
 * @return the character at the given index, or (UChar32)-1.
 * @stable ICU 3.2
 */
U_CAPI UChar32 U_EXPORT2
uset_charAt(const USet* set, int32_t charIndex);

/**
 * Returns the number of characters and strings contained in this set.
 * The last (uset_getItemCount() - uset_getRangeCount()) items are strings.
 *
 * This is slower than uset_getRangeCount() and uset_getItemCount() because
 * it counts the code points of all ranges.
 *
 * @param set the set
 * @return a non-negative integer counting the characters and strings
 * contained in set
 * @stable ICU 2.4
 * @see uset_getRangeCount
 */
U_CAPI int32_t U_EXPORT2
uset_size(const USet* set);

#ifndef U_HIDE_DRAFT_API
/**
 * @param set the set
 * @return the number of ranges in this set.
 * @draft ICU 70
 * @see uset_getItemCount
 * @see uset_getItem
 * @see uset_size
 */
U_CAPI int32_t U_EXPORT2
uset_getRangeCount(const USet *set);
#endif  // U_HIDE_DRAFT_API

/**
 * Returns the number of items in this set.  An item is either a range
 * of characters or a single multicharacter string.
 * @param set the set
 * @return a non-negative integer counting the character ranges
 * and/or strings contained in set
 * @stable ICU 2.4
 */
U_CAPI int32_t U_EXPORT2
uset_getItemCount(const USet* set);

/**
 * Returns an item of this set. An item is either a range of
 * characters or a single multicharacter string (which can be the empty string).
 *
 * If <code>itemIndex</code> is less than uset_getRangeCount(), then this function returns 0,
 * and the range is <code>*start</code>..<code>*end</code>.
 *
 * If <code>itemIndex</code> is at least uset_getRangeCount() and less than uset_getItemCount(), then
 * this function copies the string into <code>str[strCapacity]</code> and
 * returns the length of the string (0 for the empty string).
 *
 * If <code>itemIndex</code> is out of range, then this function returns -1.
 *
 * Note that 0 is returned for each range as well as for the empty string.
 *
 * @param set the set
 * @param itemIndex a non-negative integer in the range 0..uset_getItemCount(set)-1
 * @param start pointer to variable to receive first character in range, inclusive;
 * can be NULL for a string item
 * @param end pointer to variable to receive last character in range, inclusive;
 * can be NULL for a string item
 * @param str buffer to receive the string, may be NULL
 * @param strCapacity capacity of str, or 0 if str is NULL
 * @param ec error code; U_INDEX_OUTOFBOUNDS_ERROR if the itemIndex is out of range
 * @return the length of the string (0 or >= 2), or 0 if the item is a range,
 * or -1 if the itemIndex is out of range
 * @stable ICU 2.4
 */
U_CAPI int32_t U_EXPORT2
uset_getItem(const USet* set, int32_t itemIndex,
 UChar32* start, UChar32* end,
 UChar* str, int32_t strCapacity,
 UErrorCode* ec);

/**
 * Returns true if set1 contains all the characters and strings
 * of set2. It answers the question, 'Is set1 a superset of set2?'
 * @param set1 set to be checked for containment
 * @param set2 set to be checked for containment
 * @return true if the test condition is met
 * @stable ICU 3.2
 */
U_CAPI UBool U_EXPORT2
uset_containsAll(const USet* set1, const USet* set2);

/**
 * Returns true if this set contains all the characters
 * of the given string. This is does not check containment of grapheme
 * clusters, like uset_containsString.
 * @param set set of characters to be checked for containment
 * @param str string containing codepoints to be checked for containment
 * @param strLen the length of the string or -1 if null terminated.
 * @return true if the test condition is met
 * @stable ICU 3.4
 */
U_CAPI UBool U_EXPORT2
uset_containsAllCodePoints(const USet* set, const UChar *str, int32_t strLen);

/**
 * Returns true if set1 contains none of the characters and strings
 * of set2. It answers the question, 'Is set1 a disjoint set of set2?'
 * @param set1 set to be checked for containment
 * @param set2 set to be checked for containment
 * @return true if the test condition is met
 * @stable ICU 3.2
 */
U_CAPI UBool U_EXPORT2
uset_containsNone(const USet* set1, const USet* set2);

/**
 * Returns true if set1 contains some of the characters and strings
 * of set2. It answers the question, 'Does set1 and set2 have an intersection?'
 * @param set1 set to be checked for containment
 * @param set2 set to be checked for containment
 * @return true if the test condition is met
 * @stable ICU 3.2
 */
U_CAPI UBool U_EXPORT2
uset_containsSome(const USet* set1, const USet* set2);

/**
 * Returns the length of the initial substring of the input string which
 * consists only of characters and strings that are contained in this set
 * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
 * or only of characters and strings that are not contained
 * in this set (USET_SPAN_NOT_CONTAINED).
 * See USetSpanCondition for details.
 * Similar to the strspn() C library function.
 * Unpaired surrogates are treated according to contains() of their surrogate code points.
 * This function works faster with a frozen set and with a non-negative string length argument.
 * @param set the set
 * @param s start of the string
 * @param length of the string; can be -1 for NUL-terminated
 * @param spanCondition specifies the containment condition
 * @return the length of the initial substring according to the spanCondition;
 *         0 if the start of the string does not fit the spanCondition
 * @stable ICU 3.8
 * @see USetSpanCondition
 */
U_CAPI int32_t U_EXPORT2
uset_span(const USet *set, const UChar *s, int32_t length, USetSpanCondition spanCondition);

/**
 * Returns the start of the trailing substring of the input string which
 * consists only of characters and strings that are contained in this set
 * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
 * or only of characters and strings that are not contained
 * in this set (USET_SPAN_NOT_CONTAINED).
 * See USetSpanCondition for details.
 * Unpaired surrogates are treated according to contains() of their surrogate code points.
 * This function works faster with a frozen set and with a non-negative string length argument.
 * @param set the set
 * @param s start of the string
 * @param length of the string; can be -1 for NUL-terminated
 * @param spanCondition specifies the containment condition
 * @return the start of the trailing substring according to the spanCondition;
 *         the string length if the end of the string does not fit the spanCondition
 * @stable ICU 3.8
 * @see USetSpanCondition
 */
U_CAPI int32_t U_EXPORT2
uset_spanBack(const USet *set, const UChar *s, int32_t length, USetSpanCondition spanCondition);

/**
 * Returns the length of the initial substring of the input string which
 * consists only of characters and strings that are contained in this set
 * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
 * or only of characters and strings that are not contained
 * in this set (USET_SPAN_NOT_CONTAINED).
 * See USetSpanCondition for details.
 * Similar to the strspn() C library function.
 * Malformed byte sequences are treated according to contains(0xfffd).
 * This function works faster with a frozen set and with a non-negative string length argument.
 * @param set the set
 * @param s start of the string (UTF-8)
 * @param length of the string; can be -1 for NUL-terminated
 * @param spanCondition specifies the containment condition
 * @return the length of the initial substring according to the spanCondition;
 *         0 if the start of the string does not fit the spanCondition
 * @stable ICU 3.8
 * @see USetSpanCondition
 */
U_CAPI int32_t U_EXPORT2
uset_spanUTF8(const USet *set, const char *s, int32_t length, USetSpanCondition spanCondition);

/**
 * Returns the start of the trailing substring of the input string which
 * consists only of characters and strings that are contained in this set
 * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
 * or only of characters and strings that are not contained
 * in this set (USET_SPAN_NOT_CONTAINED).
 * See USetSpanCondition for details.
 * Malformed byte sequences are treated according to contains(0xfffd).
 * This function works faster with a frozen set and with a non-negative string length argument.
 * @param set the set
 * @param s start of the string (UTF-8)
 * @param length of the string; can be -1 for NUL-terminated
 * @param spanCondition specifies the containment condition
 * @return the start of the trailing substring according to the spanCondition;
 *         the string length if the end of the string does not fit the spanCondition
 * @stable ICU 3.8
 * @see USetSpanCondition
 */
U_CAPI int32_t U_EXPORT2
uset_spanBackUTF8(const USet *set, const char *s, int32_t length, USetSpanCondition spanCondition);

/**
 * Returns true if set1 contains all of the characters and strings
 * of set2, and vis versa. It answers the question, 'Is set1 equal to set2?'
 * @param set1 set to be checked for containment
 * @param set2 set to be checked for containment
 * @return true if the test condition is met
 * @stable ICU 3.2
 */
U_CAPI UBool U_EXPORT2
uset_equals(const USet* set1, const USet* set2);

/*********************************************************************
 * Serialized set API
 *********************************************************************/

/**
 * Serializes this set into an array of 16-bit integers. Serialization
 * (currently) only records the characters in the set; multicharacter
 * strings are ignored.
 *
 * The array
 * has following format (each line is one 16-bit integer):
 *
 * length = (n+2*m) | (m!=0?0x8000:0)
 * bmpLength = n; present if m!=0
 * bmp[0]
 * bmp[1]
 * ...
 * bmp[n-1]
 * supp-high[0]
 * supp-low[0]
 * supp-high[1]
 * supp-low[1]
 * ...
 * supp-high[m-1]
 * supp-low[m-1]
 *
 * The array starts with a header. After the header are n bmp
 * code points, then m supplementary code points. Either n or m
 * or both may be zero. n+2*m is always <= 0x7FFF.
 *
 * If there are no supplementary characters (if m==0) then the
 * header is one 16-bit integer, 'length', with value n.
 *
 * If there are supplementary characters (if m!=0) then the header
 * is two 16-bit integers. The first, 'length', has value
 * (n+2*m)|0x8000. The second, 'bmpLength', has value n.
 *
 * After the header the code points are stored in ascending order.
 * Supplementary code points are stored as most significant 16
 * bits followed by least significant 16 bits.
 *
 * @param set the set
 * @param dest pointer to buffer of destCapacity 16-bit integers.
 * May be NULL only if destCapacity is zero.
 * @param destCapacity size of dest, or zero. Must not be negative.
 * @param pErrorCode pointer to the error code. Will be set to
 * U_INDEX_OUTOFBOUNDS_ERROR if n+2*m > 0x7FFF. Will be set to
 * U_BUFFER_OVERFLOW_ERROR if n+2*m+(m!=0?2:1) > destCapacity.
 * @return the total length of the serialized format, including
 * the header, that is, n+2*m+(m!=0?2:1), or 0 on error other
 * than U_BUFFER_OVERFLOW_ERROR.
 * @stable ICU 2.4
 */
U_CAPI int32_t U_EXPORT2
uset_serialize(const USet* set, uint16_t* dest, int32_t destCapacity, UErrorCode* pErrorCode);

/**
 * Given a serialized array, fill in the given serialized set object.
 * @param fillSet pointer to result
 * @param src pointer to start of array
 * @param srcLength length of array
 * @return true if the given array is valid, otherwise false
 * @stable ICU 2.4
 */
U_CAPI UBool U_EXPORT2
uset_getSerializedSet(USerializedSet* fillSet, const uint16_t* src, int32_t srcLength);

/**
 * Set the USerializedSet to contain the given character (and nothing
 * else).
 * @param fillSet pointer to result
 * @param c The codepoint to set
 * @stable ICU 2.4
 */
U_CAPI void U_EXPORT2
uset_setSerializedToOne(USerializedSet* fillSet, UChar32 c);

/**
 * Returns true if the given USerializedSet contains the given
 * character.
 * @param set the serialized set
 * @param c The codepoint to check for within the set
 * @return true if set contains c
 * @stable ICU 2.4
 */
U_CAPI UBool U_EXPORT2
uset_serializedContains(const USerializedSet* set, UChar32 c);

/**
 * Returns the number of disjoint ranges of characters contained in
 * the given serialized set.  Ignores any strings contained in the
 * set.
 * @param set the serialized set
 * @return a non-negative integer counting the character ranges
 * contained in set
 * @stable ICU 2.4
 */
U_CAPI int32_t U_EXPORT2
uset_getSerializedRangeCount(const USerializedSet* set);

/**
 * Returns a range of characters contained in the given serialized
 * set.
 * @param set the serialized set
 * @param rangeIndex a non-negative integer in the range 0..
 * uset_getSerializedRangeCount(set)-1
 * @param pStart pointer to variable to receive first character
 * in range, inclusive
 * @param pEnd pointer to variable to receive last character in range,
 * inclusive
 * @return true if rangeIndex is valid, otherwise false
 * @stable ICU 2.4
 */
U_CAPI UBool U_EXPORT2
uset_getSerializedRange(const USerializedSet* set, int32_t rangeIndex,
                        UChar32* pStart, UChar32* pEnd);

#endif

cmd: