]>
Commit | Line | Data |
---|---|---|
1 | ///////////////////////////////////////////////////////////////////////////// | |
2 | // Name: encconv.h | |
3 | // Purpose: interface of wxEncodingConverter | |
4 | // Author: wxWidgets team | |
5 | // RCS-ID: $Id$ | |
6 | // Licence: wxWindows licence | |
7 | ///////////////////////////////////////////////////////////////////////////// | |
8 | ||
9 | /** | |
10 | @class wxEncodingConverter | |
11 | ||
12 | This class is capable of converting strings between two 8-bit encodings/charsets. | |
13 | It can also convert from/to Unicode. | |
14 | ||
15 | Only a limited subset of encodings is supported by wxEncodingConverter: | |
16 | @c wxFONTENCODING_ISO8859_1..15, @c wxFONTENCODING_CP1250..1257 and | |
17 | @c wxFONTENCODING_KOI8. | |
18 | ||
19 | @note | |
20 | Please use wxMBConv classes instead if possible. wxCSConv has much better | |
21 | support for various encodings than wxEncodingConverter. | |
22 | wxEncodingConverter is useful only if you rely on wxCONVERT_SUBSTITUTE mode | |
23 | of operation (see wxEncodingConverter::Init()). | |
24 | ||
25 | @library{wxbase} | |
26 | @category{conv} | |
27 | ||
28 | @see wxFontMapper, wxMBConv, @ref overview_nonenglish | |
29 | */ | |
30 | class wxEncodingConverter : public wxObject | |
31 | { | |
32 | public: | |
33 | /** | |
34 | Constructor. | |
35 | */ | |
36 | wxEncodingConverter(); | |
37 | ||
38 | /** | |
39 | Return @true if (any text in) multibyte encoding @a encIn can be converted to | |
40 | another one (@a encOut) losslessly. | |
41 | ||
42 | Do not call this method with @c wxFONTENCODING_UNICODE as either parameter, | |
43 | it doesn't make sense (always works in one sense and always depends | |
44 | on the text to convert in the other). | |
45 | */ | |
46 | static bool CanConvert(wxFontEncoding encIn, | |
47 | wxFontEncoding encOut); | |
48 | ||
49 | /** | |
50 | @name Conversion functions | |
51 | ||
52 | @{ | |
53 | */ | |
54 | /** | |
55 | Convert input string according to settings passed to Init() and writes | |
56 | the result to output. | |
57 | ||
58 | All the Convert() function overloads return @true if the conversion was | |
59 | lossless and @false if at least one of the characters couldn't be converted | |
60 | was and replaced with '?' in the output. | |
61 | ||
62 | Note that if @c wxCONVERT_SUBSTITUTE was passed to Init(), substitution is | |
63 | considered a lossless operation. | |
64 | ||
65 | @note You must call Init() before using this method! | |
66 | */ | |
67 | bool Convert(const char* input, char* output) const; | |
68 | bool Convert(const wchar_t* input, wchar_t* output) const; | |
69 | bool Convert(const char* input, wchar_t* output) const; | |
70 | bool Convert(const wchar_t* input, char* output) const; | |
71 | ||
72 | /** | |
73 | Convert input string according to settings passed to Init() in-place. | |
74 | ||
75 | With this overload, the conversion result is written to the same memory | |
76 | area from which the input is read. | |
77 | ||
78 | See the Convert(const char*,char*) const overload for more info. | |
79 | */ | |
80 | bool Convert(char* str) const; | |
81 | ||
82 | /** | |
83 | Convert input string according to settings passed to Init() in-place. | |
84 | ||
85 | With this overload, the conversion result is written to the same memory | |
86 | area from which the input is read. | |
87 | ||
88 | See the Convert(const wchar_t*,wchar_t*) const overload for more info. | |
89 | */ | |
90 | bool Convert(wchar_t* str) const; | |
91 | ||
92 | /** | |
93 | Convert a wxString and return a new wxString object. | |
94 | ||
95 | See the Convert(const char*,char*) const overload for more info. | |
96 | */ | |
97 | wxString Convert(const wxString& input) const; | |
98 | //@} | |
99 | ||
100 | ||
101 | /** | |
102 | Similar to GetPlatformEquivalents(), but this one will return ALL | |
103 | equivalent encodings, regardless of the platform, and including itself. | |
104 | ||
105 | This platform's encodings are before others in the array. | |
106 | And again, if @a enc is in the array, it is the very first item in it. | |
107 | */ | |
108 | static wxFontEncodingArray GetAllEquivalents(wxFontEncoding enc); | |
109 | ||
110 | /** | |
111 | Return equivalents for given font that are used under given platform. | |
112 | ||
113 | Supported platforms: | |
114 | @li wxPLATFORM_UNIX | |
115 | @li wxPLATFORM_WINDOWS | |
116 | @li wxPLATFORM_OS2 | |
117 | @li wxPLATFORM_MAC | |
118 | @li wxPLATFORM_CURRENT | |
119 | ||
120 | wxPLATFORM_CURRENT means the platform this binary was compiled for. | |
121 | ||
122 | Examples: | |
123 | ||
124 | @verbatim | |
125 | current platform enc returned value | |
126 | ---------------------------------------------- | |
127 | unix CP1250 {ISO8859_2} | |
128 | unix ISO8859_2 {ISO8859_2} | |
129 | windows ISO8859_2 {CP1250} | |
130 | unix CP1252 {ISO8859_1,ISO8859_15} | |
131 | @endverbatim | |
132 | ||
133 | Equivalence is defined in terms of convertibility: two encodings are | |
134 | equivalent if you can convert text between then without losing | |
135 | information (it may - and will - happen that you lose special chars | |
136 | like quotation marks or em-dashes but you shouldn't lose any diacritics | |
137 | and language-specific characters when converting between equivalent encodings). | |
138 | ||
139 | Remember that this function does @b NOT check for presence of | |
140 | fonts in system. It only tells you what are most suitable | |
141 | encodings. (It usually returns only one encoding.) | |
142 | ||
143 | @note Note that argument enc itself may be present in the returned array, | |
144 | so that you can, as a side-effect, detect whether the encoding is | |
145 | native for this platform or not. | |
146 | ||
147 | @note Convert() is not limited to converting between equivalent encodings, | |
148 | it can convert between two arbitrary encodings. | |
149 | ||
150 | @note If @a enc is present in the returned array, then it is always the first | |
151 | item of it. | |
152 | ||
153 | @note Please note that the returned array may contain no items at all. | |
154 | */ | |
155 | static wxFontEncodingArray GetPlatformEquivalents(wxFontEncoding enc, | |
156 | int platform = wxPLATFORM_CURRENT); | |
157 | ||
158 | /** | |
159 | Initialize the conversion. | |
160 | ||
161 | Both output or input encoding may be wxFONTENCODING_UNICODE, but only | |
162 | if wxUSE_ENCODING is set to 1. | |
163 | ||
164 | All subsequent calls to Convert() will interpret its argument | |
165 | as a string in @a input_enc encoding and will output string in | |
166 | @a output_enc encoding. | |
167 | ||
168 | You must call this method before calling Convert. You may call | |
169 | it more than once in order to switch to another conversion. | |
170 | ||
171 | @a method affects behaviour of Convert() in case input character | |
172 | cannot be converted because it does not exist in output encoding: | |
173 | ||
174 | @li @b wxCONVERT_STRICT: follow behaviour of GNU Recode - just copy | |
175 | unconvertible characters to output and don't change them | |
176 | (its integer value will stay the same) | |
177 | @li @b wxCONVERT_SUBSTITUTE: try some (lossy) substitutions - e.g. | |
178 | replace unconvertible latin capitals with acute by ordinary | |
179 | capitals, replace en-dash or em-dash by '-' etc. | |
180 | ||
181 | Both modes guarantee that output string will have same length | |
182 | as input string. | |
183 | ||
184 | @return @false if given conversion is impossible, @true otherwise | |
185 | (conversion may be impossible either if you try to convert | |
186 | to Unicode with non-Unicode build of wxWidgets or if input | |
187 | or output encoding is not supported). | |
188 | */ | |
189 | bool Init(wxFontEncoding input_enc, wxFontEncoding output_enc, | |
190 | int method = wxCONVERT_STRICT); | |
191 | }; | |
192 |