1 | // |
2 | // CDATASection.h |
3 | // |
4 | // Library: XML |
5 | // Package: DOM |
6 | // Module: DOM |
7 | // |
8 | // Definition of the DOM CDATASection class. |
9 | // |
10 | // Copyright (c) 2004-2006, Applied Informatics Software Engineering GmbH. |
11 | // and Contributors. |
12 | // |
13 | // SPDX-License-Identifier: BSL-1.0 |
14 | // |
15 | |
16 | |
17 | #ifndef DOM_CDATASection_INCLUDED |
18 | #define DOM_CDATASection_INCLUDED |
19 | |
20 | |
21 | #include "Poco/XML/XML.h" |
22 | #include "Poco/DOM/Text.h" |
23 | |
24 | |
25 | namespace Poco { |
26 | namespace XML { |
27 | |
28 | |
29 | class XML_API CDATASection: public Text |
30 | /// CDATA sections are used to escape blocks of text containing characters that |
31 | /// would otherwise be regarded as markup. The only delimiter that is recognized |
32 | /// in a CDATA section is the "]]>" string that ends the CDATA section. CDATA |
33 | /// sections cannot be nested. Their primary purpose is for including material |
34 | /// such as XML fragments, without needing to escape all the delimiters. |
35 | /// |
36 | /// The DOMString attribute of the Text node holds the text that is contained |
37 | /// by the CDATA section. Note that this may contain characters that need to |
38 | /// be escaped outside of CDATA sections and that, depending on the character |
39 | /// encoding ("charset") chosen for serialization, it may be impossible to write |
40 | /// out some characters as part of a CDATA section. |
41 | /// |
42 | /// The CDATASection interface inherits from the CharacterData interface through |
43 | /// the Text interface. Adjacent CDATASection nodes are not merged by use of |
44 | /// the normalize method on the Element interface. |
45 | /// |
46 | /// Note: Because no markup is recognized within a CDATASection, character numeric |
47 | /// references cannot be used as an escape mechanism when serializing. Therefore, |
48 | /// action needs to be taken when serializing a CDATASection with a character |
49 | /// encoding where some of the contained characters cannot be represented. Failure |
50 | /// to do so would not produce well-formed XML. |
51 | /// One potential solution in the serialization process is to end the CDATA |
52 | /// section before the character, output the character using a character reference |
53 | /// or entity reference, and open a new CDATA section for any further characters |
54 | /// in the text node. Note, however, that some code conversion libraries at |
55 | /// the time of writing do not return an error or exception when a character |
56 | /// is missing from the encoding, making the task of ensuring that data is not |
57 | /// corrupted on serialization more difficult. |
58 | { |
59 | public: |
60 | // Text |
61 | Text* splitText(unsigned long offset); |
62 | |
63 | // Node |
64 | const XMLString& nodeName() const; |
65 | unsigned short nodeType() const; |
66 | |
67 | protected: |
68 | CDATASection(Document* pOwnerDocument, const XMLString& data); |
69 | CDATASection(Document* pOwnerDocument, const CDATASection& sec); |
70 | ~CDATASection(); |
71 | |
72 | Node* copyNode(bool deep, Document* pOwnerDocument) const; |
73 | |
74 | private: |
75 | static const XMLString NODE_NAME; |
76 | |
77 | friend class Document; |
78 | }; |
79 | |
80 | |
81 | } } // namespace Poco::XML |
82 | |
83 | |
84 | #endif // DOM_CDATASection_INCLUDED |
85 | |