FM / unicode

/usr/include/unicode

Name	Size	Mode	Actions
basictz.h	8913	0644	edit dl rm
bms.h	8664	0644	edit dl rm
bmsearch.h	7316	0644	edit dl rm
brkiter.h	23001	0644	edit dl rm
bytestream.h	8531	0644	edit dl rm
calendar.h	90659	0644	edit dl rm
caniter.h	7288	0644	edit dl rm
chariter.h	24186	0644	edit dl rm
choicfmt.h	29528	0644	edit dl rm
coleitr.h	12990	0644	edit dl rm
coll.h	48468	0644	edit dl rm
colldata.h	11957	0644	edit dl rm
curramt.h	3659	0644	edit dl rm
currpinf.h	7061	0644	edit dl rm
currunit.h	3057	0644	edit dl rm
datefmt.h	27946	0644	edit dl rm
dbbi.h	966	0644	edit dl rm
dcfmtsym.h	14040	0644	edit dl rm
decimfmt.h	88612	0644	edit dl rm
docmain.h	6003	0644	edit dl rm
dtfmtsym.h	26145	0644	edit dl rm
dtintrv.h	3734	0644	edit dl rm
dtitvfmt.h	39700	0644	edit dl rm
dtitvinf.h	18704	0644	edit dl rm
dtptngen.h	17303	0644	edit dl rm
dtrule.h	8718	0644	edit dl rm
errorcode.h	4361	0644	edit dl rm
fieldpos.h	8713	0644	edit dl rm
fmtable.h	18794	0644	edit dl rm
format.h	12083	0644	edit dl rm
gregocal.h	33797	0644	edit dl rm
locid.h	30241	0644	edit dl rm
measfmt.h	1897	0644	edit dl rm
measunit.h	1635	0644	edit dl rm
measure.h	3321	0644	edit dl rm
msgfmt.h	39435	0644	edit dl rm
normlzr.h	30337	0644	edit dl rm
numfmt.h	33987	0644	edit dl rm
numsys.h	5004	0644	edit dl rm
parseerr.h	3044	0644	edit dl rm
parsepos.h	5468	0644	edit dl rm
platform.h	9961	0644	edit dl rm
plurfmt.h	23079	0644	edit dl rm
plurrule.h	9901	0644	edit dl rm
ppalmos.h	6992	0644	edit dl rm
putil.h	6686	0644	edit dl rm
pwin32.h	8668	0644	edit dl rm
rbbi.h	26993	0644	edit dl rm
rbnf.h	45681	0644	edit dl rm
rbtz.h	15695	0644	edit dl rm
regex.h	52316	0644	edit dl rm
rep.h	9559	0644	edit dl rm
resbund.h	18130	0644	edit dl rm
schriter.h	6293	0644	edit dl rm
search.h	22357	0644	edit dl rm
simpletz.h	46179	0644	edit dl rm
smpdtfmt.h	48325	0644	edit dl rm
sortkey.h	11111	0644	edit dl rm
std_string.h	1769	0644	edit dl rm
strenum.h	9888	0644	edit dl rm
stringpiece.h	5484	0644	edit dl rm
stsearch.h	22287	0644	edit dl rm
symtable.h	4199	0644	edit dl rm
tblcoll.h	38199	0644	edit dl rm
timezone.h	34584	0644	edit dl rm
tmunit.h	3454	0644	edit dl rm
tmutamt.h	4787	0644	edit dl rm
tmutfmt.h	8669	0644	edit dl rm
translit.h	54780	0644	edit dl rm
tzrule.h	36057	0644	edit dl rm
tztrans.h	6101	0644	edit dl rm
ubidi.h	83092	0644	edit dl rm
ubrk.h	17688	0644	edit dl rm
ucal.h	40177	0644	edit dl rm
ucasemap.h	16420	0644	edit dl rm
ucat.h	5371	0644	edit dl rm
uchar.h	111062	0644	edit dl rm
uchriter.h	13132	0644	edit dl rm
uclean.h	11855	0644	edit dl rm
ucnv.h	83111	0644	edit dl rm
ucnvsel.h	5630	0644	edit dl rm
ucnv_cb.h	6635	0644	edit dl rm
ucnv_err.h	21375	0644	edit dl rm
ucol.h	48826	0644	edit dl rm
ucoleitr.h	12356	0644	edit dl rm
uconfig.h	6035	0644	edit dl rm
ucsdet.h	12464	0644	edit dl rm
ucurr.h	11572	0644	edit dl rm
udat.h	34496	0644	edit dl rm
udata.h	14265	0644	edit dl rm
udatpg.h	18715	0644	edit dl rm
udeprctd.h	2284	0644	edit dl rm
udraft.h	7600	0644	edit dl rm
uenum.h	5796	0644	edit dl rm
uidna.h	15918	0644	edit dl rm
uintrnal.h	15752	0644	edit dl rm
uiter.h	23234	0644	edit dl rm
uloc.h	44548	0644	edit dl rm
ulocdata.h	9739	0644	edit dl rm
umachine.h	11360	0644	edit dl rm
umisc.h	1255	0644	edit dl rm
umsg.h	26076	0644	edit dl rm
unifilt.h	3770	0644	edit dl rm
unifunct.h	3966	0644	edit dl rm
unimatch.h	6071	0644	edit dl rm
unirepl.h	3290	0644	edit dl rm
uniset.h	61771	0644	edit dl rm
unistr.h	161321	0644	edit dl rm
unorm.h	23621	0644	edit dl rm
unum.h	32145	0644	edit dl rm
uobject.h	11393	0644	edit dl rm
uobslete.h	852	0644	edit dl rm
uregex.h	43948	0644	edit dl rm
urename.h	92538	0644	edit dl rm
urep.h	5394	0644	edit dl rm
ures.h	36348	0644	edit dl rm
uscript.h	11360	0644	edit dl rm
usearch.h	34223	0644	edit dl rm
uset.h	39868	0644	edit dl rm
usetiter.h	9606	0644	edit dl rm
ushape.h	17907	0644	edit dl rm
uspoof.h	38752	0644	edit dl rm
usprep.h	7750	0644	edit dl rm
ustdio.h	35333	0644	edit dl rm
ustream.h	1891	0644	edit dl rm
ustring.h	69383	0644	edit dl rm
usystem.h	1925	0644	edit dl rm
utext.h	58394	0644	edit dl rm
utf.h	8273	0644	edit dl rm
utf8.h	20512	0644	edit dl rm
utf16.h	18776	0644	edit dl rm
utf32.h	653	0644	edit dl rm
utf_old.h	43646	0644	edit dl rm
utmscale.h	13689	0644	edit dl rm
utrace.h	13355	0644	edit dl rm
utrans.h	23129	0644	edit dl rm
utypes.h	34513	0644	edit dl rm
uversion.h	10902	0644	edit dl rm
vtzone.h	20048	0644	edit dl rm

Edit: /usr/include/unicode/usetiter.h (9606B)

/*
**********************************************************************
* Copyright (c) 2002-2008, International Business Machines
* Corporation and others.  All Rights Reserved.
**********************************************************************
*/
#ifndef USETITER_H
#define USETITER_H

#include "unicode/utypes.h"
#include "unicode/uobject.h"
#include "unicode/unistr.h"

/**
 * \file 
 * \brief C++ API: UnicodeSetIterator iterates over the contents of a UnicodeSet.
 */

U_NAMESPACE_BEGIN

class UnicodeSet;
class UnicodeString;

/**
 *
 * UnicodeSetIterator iterates over the contents of a UnicodeSet. It
 * iterates over either code points or code point ranges. After all
 * code points or ranges have been returned, it returns the
 * multicharacter strings of the UnicodeSet, if any.
 *
 * This class is not intended to be subclassed. Consider any fields
 * or methods declared as "protected" to be private. The use of
 * protected in this class is an artifact of history.
 *
 * To iterate over code points and strings, use a loop like this:
 * <pre>
 * UnicodeSetIterator it(set);
 * while (it.next()) {
 * processItem(it.getString());
 * }
 * </pre>
 * Each item in the set is accessed as a string. Set elements
 * consisting of single code points are returned as strings containing
 * just the one code point.
 *
 * To iterate over code point ranges, instead of individual code points,
 * use a loop like this:
 * <pre>
 * UnicodeSetIterator it(set);
 * while (it.nextRange()) {
 * if (it.isString()) {
 * processString(it.getString());
 * } else {
 * processCodepointRange(it.getCodepoint(), it.getCodepointEnd());
 * }
 * }
 * </pre>
 * @author M. Davis
 * @stable ICU 2.4
 */
class U_COMMON_API UnicodeSetIterator : public UObject {

protected:

/**
 * Value of <tt>codepoint</tt> if the iterator points to a string.
 * If <tt>codepoint == IS_STRING</tt>, then examine
 * <tt>string</tt> for the current iteration result.
 * @stable ICU 2.4
 */
 enum { IS_STRING = -1 };

/**
 * Current code point, or the special value <tt>IS_STRING</tt>, if
 * the iterator points to a string.
 * @stable ICU 2.4
 */
 UChar32 codepoint;

/**
 * When iterating over ranges using <tt>nextRange()</tt>,
 * <tt>codepointEnd</tt> contains the inclusive end of the
 * iteration range, if <tt>codepoint != IS_STRING</tt>. If
 * iterating over code points using <tt>next()</tt>, or if
 * <tt>codepoint == IS_STRING</tt>, then the value of
 * <tt>codepointEnd</tt> is undefined.
 * @stable ICU 2.4
 */
 UChar32 codepointEnd;

/**
 * If <tt>codepoint == IS_STRING</tt>, then <tt>string</tt> points
 * to the current string. If <tt>codepoint != IS_STRING</tt>, the
 * value of <tt>string</tt> is undefined.
 * @stable ICU 2.4
 */
 const UnicodeString* string;

public:

/**
 * Create an iterator over the given set. The iterator is valid
 * only so long as <tt>set</tt> is valid.
 * @param set set to iterate over
 * @stable ICU 2.4
 */
 UnicodeSetIterator(const UnicodeSet& set);

/**
 * Create an iterator over nothing. <tt>next()</tt> and
 * <tt>nextRange()</tt> return false. This is a convenience
 * constructor allowing the target to be set later.
 * @stable ICU 2.4
 */
 UnicodeSetIterator();

/**
     * Destructor.
     * @stable ICU 2.4
     */
    virtual ~UnicodeSetIterator();

/**
 * Returns true if the current element is a string. If so, the
 * caller can retrieve it with <tt>getString()</tt>. If this
 * method returns false, the current element is a code point or
 * code point range, depending on whether <tt>next()</tt> or
 * <tt>nextRange()</tt> was called.
 * Elements of types string and codepoint can both be retrieved
 * with the function <tt>getString()</tt>.
 * Elements of type codepoint can also be retrieved with
 * <tt>getCodepoint()</tt>.
 * For ranges, <tt>getCodepoint()</tt> returns the starting codepoint
 * of the range, and <tt>getCodepointEnd()</tt> returns the end
 * of the range.
 * @stable ICU 2.4
 */
 inline UBool isString() const;

/**
 * Returns the current code point, if <tt>isString()</tt> returned
 * false. Otherwise returns an undefined result.
 * @stable ICU 2.4
 */
 inline UChar32 getCodepoint() const;

/**
 * Returns the end of the current code point range, if
 * <tt>isString()</tt> returned false and <tt>nextRange()</tt> was
 * called. Otherwise returns an undefined result.
 * @stable ICU 2.4
 */
 inline UChar32 getCodepointEnd() const;

/**
 * Returns the current string, if <tt>isString()</tt> returned
 * true. If the current iteration item is a code point, a UnicodeString
 * containing that single code point is returned.
 *
 * Ownership of the returned string remains with the iterator.
 * The string is guaranteed to remain valid only until the iterator is
 * advanced to the next item, or until the iterator is deleted.
 * 
 * @stable ICU 2.4
 */
 const UnicodeString& getString();

/**
 * Advances the iteration position to the next element in the set, 
 * which can be either a single code point or a string. 
 * If there are no more elements in the set, return false.
 *
 * 
 * If <tt>isString() == TRUE</tt>, the value is a
 * string, otherwise the value is a
 * single code point. Elements of either type can be retrieved
 * with the function <tt>getString()</tt>, while elements of
 * consisting of a single code point can be retrieved with
 * <tt>getCodepoint()</tt>
 *
 * The order of iteration is all code points in sorted order,
 * followed by all strings sorted order. Do not mix
 * calls to <tt>next()</tt> and <tt>nextRange()</tt> without
 * calling <tt>reset()</tt> between them. The results of doing so
 * are undefined.
 *
 * @return true if there was another element in the set.
 * @stable ICU 2.4
 */
 UBool next();

/**
 * Returns the next element in the set, either a code point range
 * or a string. If there are no more elements in the set, return
 * false. If <tt>isString() == TRUE</tt>, the value is a
 * string and can be accessed with <tt>getString()</tt>. Otherwise the value is a
 * range of one or more code points from <tt>getCodepoint()</tt> to
 * <tt>getCodepointeEnd()</tt> inclusive.
 *
 * The order of iteration is all code points ranges in sorted
 * order, followed by all strings sorted order. Ranges are
 * disjoint and non-contiguous. The value returned from <tt>getString()</tt>
 * is undefined unless <tt>isString() == TRUE</tt>. Do not mix calls to
 * <tt>next()</tt> and <tt>nextRange()</tt> without calling
 * <tt>reset()</tt> between them. The results of doing so are
 * undefined.
 *
 * @return true if there was another element in the set.
 * @stable ICU 2.4
 */
 UBool nextRange();

/**
 * Sets this iterator to visit the elements of the given set and
 * resets it to the start of that set. The iterator is valid only
 * so long as <tt>set</tt> is valid.
 * @param set the set to iterate over.
 * @stable ICU 2.4
 */
 void reset(const UnicodeSet& set);

/**
     * Resets this iterator to the start of the set.
     * @stable ICU 2.4
     */
    void reset();

/**
     * ICU "poor man's RTTI", returns a UClassID for this class.
     *
     * @stable ICU 2.4
     */
    static UClassID U_EXPORT2 getStaticClassID();

/**
     * ICU "poor man's RTTI", returns a UClassID for the actual class.
     *
     * @stable ICU 2.4
     */
    virtual UClassID getDynamicClassID() const;

// ======================= PRIVATES ===========================

protected:

// endElement and nextElements are really UChar32's, but we keep
    // them as signed int32_t's so we can do comparisons with
    // endElement set to -1.  Leave them as int32_t's.
    /** The set
     * @stable ICU 2.4
     */
    const UnicodeSet* set;
    /** End range
     * @stable ICU 2.4
     */
    int32_t endRange;
    /** Range
     * @stable ICU 2.4
     */
    int32_t range;
    /** End element
     * @stable ICU 2.4
     */
    int32_t endElement;
    /** Next element
     * @stable ICU 2.4
     */
    int32_t nextElement;
    //UBool abbreviated;
    /** Next string
     * @stable ICU 2.4
     */
    int32_t nextString;
    /** String count
     * @stable ICU 2.4
     */
    int32_t stringCount;

/**
     *  Points to the string to use when the caller asks for a
     *  string and the current iteration item is a code point, not a string.
     *  @internal
     */
    UnicodeString *cpString;

/** Copy constructor. Disallowed.
     * @stable ICU 2.4
     */
    UnicodeSetIterator(const UnicodeSetIterator&); // disallow

/** Assignment operator. Disallowed.
     * @stable ICU 2.4
     */
    UnicodeSetIterator& operator=(const UnicodeSetIterator&); // disallow

/** Load range
     * @stable ICU 2.4
     */
    virtual void loadRange(int32_t range);

};

inline UBool UnicodeSetIterator::isString() const {
    return codepoint == (UChar32)IS_STRING;
}

inline UChar32 UnicodeSetIterator::getCodepoint() const {
    return codepoint;
}

inline UChar32 UnicodeSetIterator::getCodepointEnd() const {
    return codepointEnd;
}

U_NAMESPACE_END

#endif

cmd: