/src/icu/source/common/unisetspan.h
Line  | Count  | Source (jump to first uncovered line)  | 
1  |  | // © 2016 and later: Unicode, Inc. and others.  | 
2  |  | // License & terms of use: http://www.unicode.org/copyright.html  | 
3  |  | /*  | 
4  |  | ******************************************************************************  | 
5  |  | *  | 
6  |  | *   Copyright (C) 2007, International Business Machines  | 
7  |  | *   Corporation and others.  All Rights Reserved.  | 
8  |  | *  | 
9  |  | ******************************************************************************  | 
10  |  | *   file name:  unisetspan.h  | 
11  |  | *   encoding:   UTF-8  | 
12  |  | *   tab size:   8 (not used)  | 
13  |  | *   indentation:4  | 
14  |  | *  | 
15  |  | *   created on: 2007mar01  | 
16  |  | *   created by: Markus W. Scherer  | 
17  |  | */  | 
18  |  |  | 
19  |  | #ifndef __UNISETSPAN_H__  | 
20  |  | #define __UNISETSPAN_H__  | 
21  |  |  | 
22  |  | #include "unicode/utypes.h"  | 
23  |  | #include "unicode/uniset.h"  | 
24  |  |  | 
25  |  | U_NAMESPACE_BEGIN  | 
26  |  |  | 
27  |  | /*  | 
28  |  |  * Implement span() etc. for a set with strings.  | 
29  |  |  * Avoid recursion because of its exponential complexity.  | 
30  |  |  * Instead, try multiple paths at once and track them with an IndexList.  | 
31  |  |  */  | 
32  |  | class UnicodeSetStringSpan : public UMemory { | 
33  |  | public:  | 
34  |  |     /*  | 
35  |  |      * Which span() variant will be used?  | 
36  |  |      * The object is either built for one variant and used once,  | 
37  |  |      * or built for all and may be used many times.  | 
38  |  |      */  | 
39  |  |     enum { | 
40  |  |         FWD             = 0x20,  | 
41  |  |         BACK            = 0x10,  | 
42  |  |         UTF16           = 8,  | 
43  |  |         UTF8            = 4,  | 
44  |  |         CONTAINED       = 2,  | 
45  |  |         NOT_CONTAINED   = 1,  | 
46  |  |  | 
47  |  |         ALL             = 0x3f,  | 
48  |  |  | 
49  |  |         FWD_UTF16_CONTAINED     = FWD  | UTF16 |     CONTAINED,  | 
50  |  |         FWD_UTF16_NOT_CONTAINED = FWD  | UTF16 | NOT_CONTAINED,  | 
51  |  |         FWD_UTF8_CONTAINED      = FWD  | UTF8  |     CONTAINED,  | 
52  |  |         FWD_UTF8_NOT_CONTAINED  = FWD  | UTF8  | NOT_CONTAINED,  | 
53  |  |         BACK_UTF16_CONTAINED    = BACK | UTF16 |     CONTAINED,  | 
54  |  |         BACK_UTF16_NOT_CONTAINED= BACK | UTF16 | NOT_CONTAINED,  | 
55  |  |         BACK_UTF8_CONTAINED     = BACK | UTF8  |     CONTAINED,  | 
56  |  |         BACK_UTF8_NOT_CONTAINED = BACK | UTF8  | NOT_CONTAINED  | 
57  |  |     };  | 
58  |  |  | 
59  |  |     UnicodeSetStringSpan(const UnicodeSet &set, const UVector &setStrings, uint32_t which);  | 
60  |  |  | 
61  |  |     // Copy constructor. Assumes which==ALL for a frozen set.  | 
62  |  |     UnicodeSetStringSpan(const UnicodeSetStringSpan &otherStringSpan, const UVector &newParentSetStrings);  | 
63  |  |  | 
64  |  |     ~UnicodeSetStringSpan();  | 
65  |  |  | 
66  |  |     /*  | 
67  |  |      * Do the strings need to be checked in span() etc.?  | 
68  |  |      * @return true if strings need to be checked (call span() here),  | 
69  |  |      *         false if not (use a BMPSet for best performance).  | 
70  |  |      */  | 
71  |  |     inline UBool needsStringSpanUTF16();  | 
72  |  |     inline UBool needsStringSpanUTF8();  | 
73  |  |  | 
74  |  |     // For fast UnicodeSet::contains(c).  | 
75  |  |     inline UBool contains(UChar32 c) const;  | 
76  |  |  | 
77  |  |     int32_t span(const UChar *s, int32_t length, USetSpanCondition spanCondition) const;  | 
78  |  |  | 
79  |  |     int32_t spanBack(const UChar *s, int32_t length, USetSpanCondition spanCondition) const;  | 
80  |  |  | 
81  |  |     int32_t spanUTF8(const uint8_t *s, int32_t length, USetSpanCondition spanCondition) const;  | 
82  |  |  | 
83  |  |     int32_t spanBackUTF8(const uint8_t *s, int32_t length, USetSpanCondition spanCondition) const;  | 
84  |  |  | 
85  |  | private:  | 
86  |  |     // Special spanLength byte values.  | 
87  |  |     enum { | 
88  |  |         // The spanLength is >=0xfe.  | 
89  |  |         LONG_SPAN=0xfe,  | 
90  |  |         // All code points in the string are contained in the parent set.  | 
91  |  |         ALL_CP_CONTAINED=0xff  | 
92  |  |     };  | 
93  |  |  | 
94  |  |     // Add a starting or ending string character to the spanNotSet  | 
95  |  |     // so that a character span ends before any string.  | 
96  |  |     void addToSpanNotSet(UChar32 c);  | 
97  |  |  | 
98  |  |     int32_t spanNot(const UChar *s, int32_t length) const;  | 
99  |  |     int32_t spanNotBack(const UChar *s, int32_t length) const;  | 
100  |  |     int32_t spanNotUTF8(const uint8_t *s, int32_t length) const;  | 
101  |  |     int32_t spanNotBackUTF8(const uint8_t *s, int32_t length) const;  | 
102  |  |  | 
103  |  |     // Set for span(). Same as parent but without strings.  | 
104  |  |     UnicodeSet spanSet;  | 
105  |  |  | 
106  |  |     // Set for span(not contained).  | 
107  |  |     // Same as spanSet, plus characters that start or end strings.  | 
108  |  |     UnicodeSet *pSpanNotSet;  | 
109  |  |  | 
110  |  |     // The strings of the parent set.  | 
111  |  |     const UVector &strings;  | 
112  |  |  | 
113  |  |     // Pointer to the UTF-8 string lengths.  | 
114  |  |     // Also pointer to further allocated storage for meta data and  | 
115  |  |     // UTF-8 string contents as necessary.  | 
116  |  |     int32_t *utf8Lengths;  | 
117  |  |  | 
118  |  |     // Pointer to the part of the (utf8Lengths) memory block that stores  | 
119  |  |     // the lengths of span(), spanBack() etc. for each string.  | 
120  |  |     uint8_t *spanLengths;  | 
121  |  |  | 
122  |  |     // Pointer to the part of the (utf8Lengths) memory block that stores  | 
123  |  |     // the UTF-8 versions of the parent set's strings.  | 
124  |  |     uint8_t *utf8;  | 
125  |  |  | 
126  |  |     // Number of bytes for all UTF-8 versions of strings together.  | 
127  |  |     int32_t utf8Length;  | 
128  |  |  | 
129  |  |     // Maximum lengths of relevant strings.  | 
130  |  |     int32_t maxLength16;  | 
131  |  |     int32_t maxLength8;  | 
132  |  |  | 
133  |  |     // Set up for all variants of span()?  | 
134  |  |     UBool all;  | 
135  |  |  | 
136  |  |     // Memory for small numbers and lengths of strings.  | 
137  |  |     // For example, for 8 strings:  | 
138  |  |     // 8 UTF-8 lengths, 8*4 bytes span lengths, 8*2 3-byte UTF-8 characters  | 
139  |  |     // = 112 bytes = int32_t[28].  | 
140  |  |     int32_t staticLengths[32];  | 
141  |  | };  | 
142  |  |  | 
143  | 0  | UBool UnicodeSetStringSpan::needsStringSpanUTF16() { | 
144  | 0  |     return (UBool)(maxLength16!=0);  | 
145  | 0  | }  | 
146  |  |  | 
147  | 0  | UBool UnicodeSetStringSpan::needsStringSpanUTF8() { | 
148  | 0  |     return (UBool)(maxLength8!=0);  | 
149  | 0  | }  | 
150  |  |  | 
151  | 0  | UBool UnicodeSetStringSpan::contains(UChar32 c) const { | 
152  | 0  |     return spanSet.contains(c);  | 
153  | 0  | }  | 
154  |  |  | 
155  |  | U_NAMESPACE_END  | 
156  |  |  | 
157  |  | #endif  |