1 // Copyright (C) 2016 and later: Unicode, Inc. and others.
2 // License & terms of use: http://www.unicode.org/copyright.html
4 **********************************************************************
5 * Copyright (c) 2002-2006, International Business Machines
6 * Corporation and others. All Rights Reserved.
7 **********************************************************************
9 #include "unicode/usetiter.h"
10 #include "unicode/uniset.h"
11 #include "unicode/unistr.h"
16 UOBJECT_DEFINE_RTTI_IMPLEMENTATION(UnicodeSetIterator)
20 * @param set set to iterate over
22 UnicodeSetIterator::UnicodeSetIterator(const UnicodeSet& uSet) {
28 * Create an iterator. Convenience for when the contents are to be set later.
30 UnicodeSetIterator::UnicodeSetIterator() {
36 UnicodeSetIterator::~UnicodeSetIterator() {
41 * Returns the next element in the set.
42 * @return true if there was another element in the set.
43 * if so, if codepoint == IS_STRING, the value is a string in the string field
44 * else the value is a single code point in the codepoint field.
45 * <br>You are guaranteed that the codepoints are in sorted order, and the strings are in sorted order,
46 * and that all code points are returned before any strings are returned.
47 * <br>Note also that the codepointEnd is undefined after calling this method.
49 UBool UnicodeSetIterator::next() {
50 if (nextElement <= endElement) {
51 codepoint = codepointEnd = nextElement++;
55 if (range < endRange) {
57 codepoint = codepointEnd = nextElement++;
62 if (nextString >= stringCount) return FALSE;
63 codepoint = (UChar32)IS_STRING; // signal that value is actually a string
64 string = (const UnicodeString*) set->strings->elementAt(nextString++);
69 * @return true if there was another element in the set.
70 * if so, if codepoint == IS_STRING, the value is a string in the string field
71 * else the value is a range of codepoints in the <codepoint, codepointEnd> fields.
72 * <br>Note that the codepoints are in sorted order, and the strings are in sorted order,
73 * and that all code points are returned before any strings are returned.
74 * <br>You are guaranteed that the ranges are in sorted order, and the strings are in sorted order,
75 * and that all ranges are returned before any strings are returned.
76 * <br>You are also guaranteed that ranges are disjoint and non-contiguous.
77 * <br>Note also that the codepointEnd is undefined after calling this method.
79 UBool UnicodeSetIterator::nextRange() {
81 if (nextElement <= endElement) {
82 codepointEnd = endElement;
83 codepoint = nextElement;
84 nextElement = endElement+1;
87 if (range < endRange) {
89 codepointEnd = endElement;
90 codepoint = nextElement;
91 nextElement = endElement+1;
95 if (nextString >= stringCount) return FALSE;
96 codepoint = (UChar32)IS_STRING; // signal that value is actually a string
97 string = (const UnicodeString*) set->strings->elementAt(nextString++);
102 *@param set the set to iterate over. This allows reuse of the iterator.
104 void UnicodeSetIterator::reset(const UnicodeSet& uSet) {
110 * Resets to the start, to allow the iteration to start over again.
112 void UnicodeSetIterator::reset() {
114 // Set up indices to empty iteration
118 endRange = set->getRangeCount() - 1;
119 stringCount = set->strings->size();
131 void UnicodeSetIterator::loadRange(int32_t iRange) {
132 nextElement = set->getRangeStart(iRange);
133 endElement = set->getRangeEnd(iRange);
137 const UnicodeString& UnicodeSetIterator::getString() {
138 if (string==NULL && codepoint!=(UChar32)IS_STRING) {
139 if (cpString == NULL) {
140 cpString = new UnicodeString();
142 if (cpString != NULL) {
143 cpString->setTo((UChar32)codepoint);