1 | /* |
---|
2 | * Licensed to the Apache Software Foundation (ASF) under one or more |
---|
3 | * contributor license agreements. See the NOTICE file distributed with |
---|
4 | * this work for additional information regarding copyright ownership. |
---|
5 | * The ASF licenses this file to You under the Apache License, Version 2.0 |
---|
6 | * (the "License"); you may not use this file except in compliance with |
---|
7 | * the License. You may obtain a copy of the License at |
---|
8 | * |
---|
9 | * http://www.apache.org/licenses/LICENSE-2.0 |
---|
10 | * |
---|
11 | * Unless required by applicable law or agreed to in writing, software |
---|
12 | * distributed under the License is distributed on an "AS IS" BASIS, |
---|
13 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
---|
14 | * See the License for the specific language governing permissions and |
---|
15 | * limitations under the License. |
---|
16 | */ |
---|
17 | |
---|
18 | /* |
---|
19 | * $Id: RegxUtil.hpp 568078 2007-08-21 11:43:25Z amassari $ |
---|
20 | */ |
---|
21 | |
---|
22 | #if !defined(REGXUTIL_HPP) |
---|
23 | #define REGXUTIL_HPP |
---|
24 | |
---|
25 | // --------------------------------------------------------------------------- |
---|
26 | // Includes |
---|
27 | // --------------------------------------------------------------------------- |
---|
28 | #include <xercesc/util/XMLUniDefs.hpp> |
---|
29 | |
---|
30 | |
---|
31 | XERCES_CPP_NAMESPACE_BEGIN |
---|
32 | |
---|
33 | class MemoryManager; |
---|
34 | |
---|
35 | class XMLUTIL_EXPORT RegxUtil { |
---|
36 | public: |
---|
37 | |
---|
38 | // ----------------------------------------------------------------------- |
---|
39 | // Constructors and destructors |
---|
40 | // ----------------------------------------------------------------------- |
---|
41 | ~RegxUtil() {} |
---|
42 | |
---|
43 | static XMLInt32 composeFromSurrogate(const XMLCh high, const XMLCh low); |
---|
44 | static bool isEOLChar(const XMLCh); |
---|
45 | static bool isWordChar(const XMLCh); |
---|
46 | static bool isLowSurrogate(const XMLCh ch); |
---|
47 | static bool isHighSurrogate(const XMLCh ch); |
---|
48 | static void decomposeToSurrogates(XMLInt32 ch, XMLCh& high, XMLCh& low); |
---|
49 | |
---|
50 | static XMLCh* decomposeToSurrogates(XMLInt32 ch, |
---|
51 | MemoryManager* const manager); |
---|
52 | static XMLCh* stripExtendedComment(const XMLCh* const expression, |
---|
53 | MemoryManager* const manager = 0); |
---|
54 | |
---|
55 | private: |
---|
56 | // ----------------------------------------------------------------------- |
---|
57 | // Unimplemented constructors and operators |
---|
58 | // ----------------------------------------------------------------------- |
---|
59 | RegxUtil(); |
---|
60 | }; |
---|
61 | |
---|
62 | |
---|
63 | inline bool RegxUtil::isEOLChar(const XMLCh ch) { |
---|
64 | |
---|
65 | return (ch == chLF || ch == chCR || ch == chLineSeparator |
---|
66 | || ch == chParagraphSeparator); |
---|
67 | } |
---|
68 | |
---|
69 | inline XMLInt32 RegxUtil::composeFromSurrogate(const XMLCh high, const XMLCh low) { |
---|
70 | |
---|
71 | return 0x10000 + ((high - 0xD800) << 10) + (low - 0xDC00); |
---|
72 | } |
---|
73 | |
---|
74 | inline bool RegxUtil::isLowSurrogate(const XMLCh ch) { |
---|
75 | |
---|
76 | return (ch & 0xFC00) == 0xDC00; |
---|
77 | } |
---|
78 | |
---|
79 | inline bool RegxUtil::isHighSurrogate(const XMLCh ch) { |
---|
80 | |
---|
81 | return (ch & 0xFC00) == 0xD800; |
---|
82 | } |
---|
83 | |
---|
84 | inline void RegxUtil::decomposeToSurrogates(XMLInt32 ch, XMLCh& high, XMLCh& low) { |
---|
85 | |
---|
86 | ch -= 0x10000; |
---|
87 | high = XMLCh((ch >> 10) + 0xD800); |
---|
88 | low = XMLCh((ch & 0x03FF) + 0xDC00); |
---|
89 | } |
---|
90 | |
---|
91 | inline bool RegxUtil::isWordChar(const XMLCh ch) { |
---|
92 | |
---|
93 | if ((ch == chUnderscore) |
---|
94 | || (ch >= chDigit_0 && ch <= chDigit_9) |
---|
95 | || (ch >= chLatin_A && ch <= chLatin_Z) |
---|
96 | || (ch >= chLatin_a && ch <= chLatin_z)) |
---|
97 | return true; |
---|
98 | |
---|
99 | return false; |
---|
100 | } |
---|
101 | |
---|
102 | XERCES_CPP_NAMESPACE_END |
---|
103 | |
---|
104 | #endif |
---|
105 | |
---|
106 | /** |
---|
107 | * End of file RegxUtil.hpp |
---|
108 | */ |
---|