]>
Commit | Line | Data |
---|---|---|
1 | ///////////////////////////////////////////////////////////////////////////// | |
2 | // Name: wx/encconv.h | |
3 | // Purpose: wxEncodingConverter class for converting between different | |
4 | // font encodings | |
5 | // Author: Vaclav Slavik | |
6 | // Copyright: (c) 1999 Vaclav Slavik | |
7 | // Licence: wxWindows Licence | |
8 | ///////////////////////////////////////////////////////////////////////////// | |
9 | ||
10 | #ifndef _WX_ENCCONV_H_ | |
11 | #define _WX_ENCCONV_H_ | |
12 | ||
13 | #if defined(__GNUG__) && !defined(NO_GCC_PRAGMA) | |
14 | #pragma interface "encconv.h" | |
15 | #endif | |
16 | ||
17 | #include "wx/defs.h" | |
18 | ||
19 | #if wxUSE_FONTMAP | |
20 | ||
21 | #include "wx/object.h" | |
22 | #include "wx/fontenc.h" | |
23 | #include "wx/dynarray.h" | |
24 | ||
25 | // ---------------------------------------------------------------------------- | |
26 | // constants | |
27 | // ---------------------------------------------------------------------------- | |
28 | ||
29 | enum | |
30 | { | |
31 | wxCONVERT_STRICT, | |
32 | wxCONVERT_SUBSTITUTE | |
33 | }; | |
34 | ||
35 | ||
36 | enum | |
37 | { | |
38 | wxPLATFORM_CURRENT = -1, | |
39 | ||
40 | wxPLATFORM_UNIX = 0, | |
41 | wxPLATFORM_WINDOWS, | |
42 | wxPLATFORM_OS2, | |
43 | wxPLATFORM_MAC | |
44 | }; | |
45 | ||
46 | // ---------------------------------------------------------------------------- | |
47 | // types | |
48 | // ---------------------------------------------------------------------------- | |
49 | ||
50 | WX_DEFINE_ARRAY_INT(wxFontEncoding, wxFontEncodingArray); | |
51 | ||
52 | //-------------------------------------------------------------------------------- | |
53 | // wxEncodingConverter | |
54 | // This class is capable of converting strings between any two | |
55 | // 8bit encodings/charsets. It can also convert from/to Unicode | |
56 | //-------------------------------------------------------------------------------- | |
57 | ||
58 | class WXDLLIMPEXP_BASE wxEncodingConverter : public wxObject | |
59 | { | |
60 | public: | |
61 | ||
62 | wxEncodingConverter(); | |
63 | ~wxEncodingConverter() { if (m_Table) delete[] m_Table; } | |
64 | ||
65 | // Initialize conversion. Both output or input encoding may | |
66 | // be wxFONTENCODING_UNICODE, but only if wxUSE_WCHAR_T is set to 1. | |
67 | // | |
68 | // All subsequent calls to Convert() will interpret it's argument | |
69 | // as a string in input_enc encoding and will output string in | |
70 | // output_enc encoding. | |
71 | // | |
72 | // You must call this method before calling Convert. You may call | |
73 | // it more than once in order to switch to another conversion | |
74 | // | |
75 | // Method affects behaviour of Convert() in case input character | |
76 | // cannot be converted because it does not exist in output encoding: | |
77 | // wxCONVERT_STRICT -- | |
78 | // follow behaviour of GNU Recode - just copy unconvertable | |
79 | // characters to output and don't change them (it's integer | |
80 | // value will stay the same) | |
81 | // wxCONVERT_SUBSTITUTE -- | |
82 | // try some (lossy) substitutions - e.g. replace | |
83 | // unconvertable latin capitals with acute by ordinary | |
84 | // capitals, replace en-dash or em-dash by '-' etc. | |
85 | // both modes gurantee that output string will have same length | |
86 | // as input string | |
87 | // | |
88 | // Returns FALSE if given conversion is impossible, TRUE otherwise | |
89 | // (conversion may be impossible either if you try to convert | |
90 | // to Unicode with non-Unicode build of wxWindows or if input | |
91 | // or output encoding is not supported.) | |
92 | bool Init(wxFontEncoding input_enc, wxFontEncoding output_enc, int method = wxCONVERT_STRICT); | |
93 | ||
94 | // Convert input string according to settings passed to Init. | |
95 | // Note that you must call Init before using Convert! | |
96 | void Convert(const char* input, char* output) const; | |
97 | void Convert(char* str) const { Convert(str, str); } | |
98 | wxString Convert(const wxString& input) const; | |
99 | ||
100 | #if wxUSE_WCHAR_T | |
101 | void Convert(const char* input, wchar_t* output) const; | |
102 | void Convert(const wchar_t* input, char* output) const; | |
103 | void Convert(const wchar_t* input, wchar_t* output) const; | |
104 | void Convert(wchar_t* str) const { Convert(str, str); } | |
105 | #endif | |
106 | // Return equivalent(s) for given font that are used | |
107 | // under given platform. wxPLATFORM_CURRENT means the plaform | |
108 | // this binary was compiled for | |
109 | // | |
110 | // Examples: | |
111 | // current platform enc returned value | |
112 | // ----------------------------------------------------- | |
113 | // unix CP1250 {ISO8859_2} | |
114 | // unix ISO8859_2 {} | |
115 | // windows ISO8859_2 {CP1250} | |
116 | // | |
117 | // Equivalence is defined in terms of convertibility: | |
118 | // 2 encodings are equivalent if you can convert text between | |
119 | // then without loosing information (it may - and will - happen | |
120 | // that you loose special chars like quotation marks or em-dashes | |
121 | // but you shouldn't loose any diacritics and language-specific | |
122 | // characters when converting between equivalent encodings). | |
123 | // | |
124 | // Convert() method is not limited to converting between | |
125 | // equivalent encodings, it can convert between arbitrary | |
126 | // two encodings! | |
127 | // | |
128 | // Remember that this function does _NOT_ check for presence of | |
129 | // fonts in system. It only tells you what are most suitable | |
130 | // encodings. (It usually returns only one encoding) | |
131 | // | |
132 | // Note that argument enc itself may be present in returned array! | |
133 | // (so that you can -- as a side effect -- detect whether the | |
134 | // encoding is native for this platform or not) | |
135 | static wxFontEncodingArray GetPlatformEquivalents(wxFontEncoding enc, int platform = wxPLATFORM_CURRENT); | |
136 | ||
137 | // Similar to GetPlatformEquivalent, but this one will return ALL | |
138 | // equivalent encodings, regardless the platform, including itself. | |
139 | static wxFontEncodingArray GetAllEquivalents(wxFontEncoding enc); | |
140 | ||
141 | // Return true if [any text in] one multibyte encoding can be | |
142 | // converted to another one losslessly. | |
143 | // | |
144 | // Do not call this with wxFONTENCODING_UNICODE, it doesn't make | |
145 | // sense (always works in one sense and always depends on the text | |
146 | // to convert in the other) | |
147 | static bool CanConvert(wxFontEncoding encIn, wxFontEncoding encOut) | |
148 | { | |
149 | return GetAllEquivalents(encIn).Index(encOut) != wxNOT_FOUND; | |
150 | } | |
151 | ||
152 | private: | |
153 | ||
154 | #if wxUSE_WCHAR_T | |
155 | wchar_t *m_Table; | |
156 | #else | |
157 | char *m_Table; | |
158 | #endif | |
159 | bool m_UnicodeInput, m_UnicodeOutput; | |
160 | bool m_JustCopy; | |
161 | ||
162 | DECLARE_NO_COPY_CLASS(wxEncodingConverter) | |
163 | }; | |
164 | ||
165 | #endif // wxUSE_FONTMAP | |
166 | ||
167 | #endif // _WX_ENCCONV_H_ |