|
1 /* |
|
2 ********************************************************************** |
|
3 * Copyright (c) 2002-2006, International Business Machines |
|
4 * Corporation and others. All Rights Reserved. |
|
5 ********************************************************************** |
|
6 */ |
|
7 #include "unicode/usetiter.h" |
|
8 #include "unicode/uniset.h" |
|
9 #include "unicode/unistr.h" |
|
10 #include "uvector.h" |
|
11 |
|
12 U_NAMESPACE_BEGIN |
|
13 |
|
14 UOBJECT_DEFINE_RTTI_IMPLEMENTATION(UnicodeSetIterator) |
|
15 |
|
16 /** |
|
17 * Create an iterator |
|
18 * @param set set to iterate over |
|
19 */ |
|
20 UnicodeSetIterator::UnicodeSetIterator(const UnicodeSet& uSet) { |
|
21 cpString = NULL; |
|
22 reset(uSet); |
|
23 } |
|
24 |
|
25 /** |
|
26 * Create an iterator. Convenience for when the contents are to be set later. |
|
27 */ |
|
28 UnicodeSetIterator::UnicodeSetIterator() { |
|
29 this->set = NULL; |
|
30 cpString = NULL; |
|
31 reset(); |
|
32 } |
|
33 |
|
34 UnicodeSetIterator::~UnicodeSetIterator() { |
|
35 delete cpString; |
|
36 } |
|
37 |
|
38 /** |
|
39 * Returns the next element in the set. |
|
40 * @return true if there was another element in the set. |
|
41 * if so, if codepoint == IS_STRING, the value is a string in the string field |
|
42 * else the value is a single code point in the codepoint field. |
|
43 * <br>You are guaranteed that the codepoints are in sorted order, and the strings are in sorted order, |
|
44 * and that all code points are returned before any strings are returned. |
|
45 * <br>Note also that the codepointEnd is undefined after calling this method. |
|
46 */ |
|
47 UBool UnicodeSetIterator::next() { |
|
48 if (nextElement <= endElement) { |
|
49 codepoint = codepointEnd = nextElement++; |
|
50 string = NULL; |
|
51 return TRUE; |
|
52 } |
|
53 if (range < endRange) { |
|
54 loadRange(++range); |
|
55 codepoint = codepointEnd = nextElement++; |
|
56 string = NULL; |
|
57 return TRUE; |
|
58 } |
|
59 |
|
60 if (nextString >= stringCount) return FALSE; |
|
61 codepoint = (UChar32)IS_STRING; // signal that value is actually a string |
|
62 string = (const UnicodeString*) set->strings->elementAt(nextString++); |
|
63 return TRUE; |
|
64 } |
|
65 |
|
66 /** |
|
67 * @return true if there was another element in the set. |
|
68 * if so, if codepoint == IS_STRING, the value is a string in the string field |
|
69 * else the value is a range of codepoints in the <codepoint, codepointEnd> fields. |
|
70 * <br>Note that the codepoints are in sorted order, and the strings are in sorted order, |
|
71 * and that all code points are returned before any strings are returned. |
|
72 * <br>You are guaranteed that the ranges are in sorted order, and the strings are in sorted order, |
|
73 * and that all ranges are returned before any strings are returned. |
|
74 * <br>You are also guaranteed that ranges are disjoint and non-contiguous. |
|
75 * <br>Note also that the codepointEnd is undefined after calling this method. |
|
76 */ |
|
77 UBool UnicodeSetIterator::nextRange() { |
|
78 string = NULL; |
|
79 if (nextElement <= endElement) { |
|
80 codepointEnd = endElement; |
|
81 codepoint = nextElement; |
|
82 nextElement = endElement+1; |
|
83 return TRUE; |
|
84 } |
|
85 if (range < endRange) { |
|
86 loadRange(++range); |
|
87 codepointEnd = endElement; |
|
88 codepoint = nextElement; |
|
89 nextElement = endElement+1; |
|
90 return TRUE; |
|
91 } |
|
92 |
|
93 if (nextString >= stringCount) return FALSE; |
|
94 codepoint = (UChar32)IS_STRING; // signal that value is actually a string |
|
95 string = (const UnicodeString*) set->strings->elementAt(nextString++); |
|
96 return TRUE; |
|
97 } |
|
98 |
|
99 /** |
|
100 *@param set the set to iterate over. This allows reuse of the iterator. |
|
101 */ |
|
102 void UnicodeSetIterator::reset(const UnicodeSet& uSet) { |
|
103 this->set = &uSet; |
|
104 reset(); |
|
105 } |
|
106 |
|
107 /** |
|
108 * Resets to the start, to allow the iteration to start over again. |
|
109 */ |
|
110 void UnicodeSetIterator::reset() { |
|
111 if (set == NULL) { |
|
112 // Set up indices to empty iteration |
|
113 endRange = -1; |
|
114 stringCount = 0; |
|
115 } else { |
|
116 endRange = set->getRangeCount() - 1; |
|
117 stringCount = set->strings->size(); |
|
118 } |
|
119 range = 0; |
|
120 endElement = -1; |
|
121 nextElement = 0; |
|
122 if (endRange >= 0) { |
|
123 loadRange(range); |
|
124 } |
|
125 nextString = 0; |
|
126 string = NULL; |
|
127 } |
|
128 |
|
129 void UnicodeSetIterator::loadRange(int32_t iRange) { |
|
130 nextElement = set->getRangeStart(iRange); |
|
131 endElement = set->getRangeEnd(iRange); |
|
132 } |
|
133 |
|
134 |
|
135 const UnicodeString& UnicodeSetIterator::getString() { |
|
136 if (string==NULL && codepoint!=(UChar32)IS_STRING) { |
|
137 if (cpString == NULL) { |
|
138 cpString = new UnicodeString(); |
|
139 } |
|
140 if (cpString != NULL) { |
|
141 cpString->setTo((UChar32)codepoint); |
|
142 } |
|
143 string = cpString; |
|
144 } |
|
145 return *string; |
|
146 } |
|
147 |
|
148 U_NAMESPACE_END |
|
149 |
|
150 //eof |