1 | #if (__OS400_TGTVRM__>=510) /* @01a */ |
---|
2 | #pragma datamodel(P128) /* @01a */ |
---|
3 | #endif /* @01a */ |
---|
4 | |
---|
5 | /* |
---|
6 | * Licensed to the Apache Software Foundation (ASF) under one or more |
---|
7 | * contributor license agreements. See the NOTICE file distributed with |
---|
8 | * this work for additional information regarding copyright ownership. |
---|
9 | * The ASF licenses this file to You under the Apache License, Version 2.0 |
---|
10 | * (the "License"); you may not use this file except in compliance with |
---|
11 | * the License. You may obtain a copy of the License at |
---|
12 | * |
---|
13 | * http://www.apache.org/licenses/LICENSE-2.0 |
---|
14 | * |
---|
15 | * Unless required by applicable law or agreed to in writing, software |
---|
16 | * distributed under the License is distributed on an "AS IS" BASIS, |
---|
17 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
---|
18 | * See the License for the specific language governing permissions and |
---|
19 | * limitations under the License. |
---|
20 | */ |
---|
21 | |
---|
22 | /* |
---|
23 | * $Id: iconv_cnv.hpp 568078 2007-08-21 11:43:25Z amassari $ |
---|
24 | */ |
---|
25 | |
---|
26 | #ifndef UCNV_H |
---|
27 | #define UCNV_H |
---|
28 | |
---|
29 | #include "utypes.h" |
---|
30 | |
---|
31 | XERCES_CPP_NAMESPACE_BEGIN |
---|
32 | |
---|
33 | /** |
---|
34 | * Creates a UConverter object with the names specified as a C string. |
---|
35 | * The actual name will be resolved with the alias file. |
---|
36 | * if <TT>NULL</TT> is passed for the converter name, it will create one with the |
---|
37 | * getDefaultName return value. |
---|
38 | * @param converterName : name of the uconv table |
---|
39 | * @param err outgoing error status <TT>MEMORY_ALLOCATION_ERROR, TABLE_NOT_FOUND</TT> |
---|
40 | * @return the created Unicode converter object, or <TT>NULL</TT> if an error occured |
---|
41 | * @see ucnv_openU |
---|
42 | * @see ucnv_openCCSID |
---|
43 | * @see ucnv_close |
---|
44 | */ |
---|
45 | |
---|
46 | U_CAPI |
---|
47 | UConverter* U_EXPORT2 ucnv_open (const char *converterName, |
---|
48 | UErrorCode * err); |
---|
49 | |
---|
50 | |
---|
51 | /** |
---|
52 | * Creates a Unicode converter with the names specified as unicode string. The name should be limited to |
---|
53 | * the ASCII-7 alphanumerics range. The actual name will be resolved with the alias file. |
---|
54 | * if <TT>NULL</TT> is passed for the converter name, it will create one with the |
---|
55 | * getDefaultName return value. |
---|
56 | * @param converterName : name of the uconv table in a zero terminated Unicode string |
---|
57 | * @param err outgoing error status <TT>MEMORY_ALLOCATION_ERROR, TABLE_NOT_FOUND</TT> |
---|
58 | * @return the created Unicode converter object, or <TT>NULL</TT> if an error occured |
---|
59 | * @see ucnv_open |
---|
60 | * @see ucnv_openCCSID |
---|
61 | * @see ucnv_close |
---|
62 | */ |
---|
63 | U_CAPI UConverter* U_EXPORT2 ucnv_openU (const UChar * name, |
---|
64 | UErrorCode * err); |
---|
65 | |
---|
66 | |
---|
67 | |
---|
68 | /** |
---|
69 | * Creates a UConverter object using a CCSID number. |
---|
70 | * @param codepage : codepage # of the uconv table |
---|
71 | * @param platform : codepage's platform (now only <TT>IBM</TT> supported) |
---|
72 | * @param err error status <TT>MEMORY_ALLOCATION_ERROR, TABLE_NOT_FOUND</TT> |
---|
73 | * @return the created Unicode converter object, or <TT>NULL</TT> if and error occured |
---|
74 | * @see ucnv_open |
---|
75 | * @see ucnv_openU |
---|
76 | * @see ucnv_close |
---|
77 | */ |
---|
78 | |
---|
79 | |
---|
80 | U_CAPI void U_EXPORT2 ucnv_close (UConverter * converter); |
---|
81 | |
---|
82 | |
---|
83 | |
---|
84 | |
---|
85 | /** |
---|
86 | * Returns the maximum length of bytes used by a character. This varies between 1 and 4 |
---|
87 | * @param converter the Unicode converter |
---|
88 | * @return the maximum number of bytes allowed by this particular converter |
---|
89 | * @see ucnv_getMinCharSize |
---|
90 | */ |
---|
91 | U_CAPI int8_t U_EXPORT2 |
---|
92 | ucnv_getMaxCharSize (const UConverter * converter); |
---|
93 | |
---|
94 | |
---|
95 | /** |
---|
96 | * Returns the minimum byte length for characters in this codepage. This is either |
---|
97 | * 1 or 2 for all supported codepages. |
---|
98 | * @param converter the Unicode converter |
---|
99 | * @return the minimum number of bytes allowed by this particular converter |
---|
100 | * @see ucnv_getMaxCharSize |
---|
101 | */ |
---|
102 | U_CAPI int8_t U_EXPORT2 |
---|
103 | ucnv_getMinCharSize (const UConverter * converter); |
---|
104 | |
---|
105 | |
---|
106 | /** |
---|
107 | * Transcodes an array of unicode characters to an array of codepage characters. |
---|
108 | * The source pointer is an I/O parameter, it starts out pointing where the function is |
---|
109 | * to begin transcoding, and ends up pointing after the first sequence of the bytes |
---|
110 | * that it encounters that are semantically invalid. |
---|
111 | * if ucnv_setToUCallBack is called with an action other than <TT>STOP</TT> |
---|
112 | * before a call is made to this API, <TT>consumed</TT> and <TT>source</TT> should point to the same place |
---|
113 | * (unless <TT>target</TT> ends with an imcomplete sequence of bytes and <TT>flush</TT> is <TT>FALSE</TT>). |
---|
114 | * the <TT>target</TT> buffer buffer needs to be a least the size of the maximum # of bytes per characters |
---|
115 | * allowed by the target codepage. |
---|
116 | * @param converter the Unicode converter |
---|
117 | * @param converter the Unicode converter |
---|
118 | * @param target : I/O parameter. Input : Points to the beginning of the buffer to copy |
---|
119 | * codepage characters to. Output : points to after the last codepage character copied |
---|
120 | * to <TT>target</TT>. |
---|
121 | * @param targetLimit the pointer to the end of the <TT>target</TT> array |
---|
122 | * @param source the source Unicode character array |
---|
123 | * @param sourceLimit the pointer to the end of the source array |
---|
124 | * @param offsets if NULL is passed, nothing will happen to it, otherwise it needs to have the same number |
---|
125 | * of allocated cells as <TT>target</TT>. Will fill in offsets from target to source pointer |
---|
126 | * e.g: <TT>offsets[3]</TT> is equal to 6, it means that the <TT>target[3]</TT> was a result of transcoding <TT>source[6]</TT> |
---|
127 | * For output data carried across calls -1 will be placed for offsets. |
---|
128 | * @param flush <TT>TRUE</TT> if the buffer is the last buffer of the conversion interation |
---|
129 | * and the conversion will finish with this call, FALSE otherwise. |
---|
130 | * @param err the error status. <TT>ILLEGAL_ARGUMENT_ERROR</TT> will be returned if the |
---|
131 | * converter is <TT>NULL</TT>. |
---|
132 | * @see ucnv_fromUChars |
---|
133 | * @see ucnv_convert |
---|
134 | * @see ucnv_getMinCharSize |
---|
135 | * @see ucnv_setToUCallBack |
---|
136 | */ |
---|
137 | |
---|
138 | U_CAPI |
---|
139 | void U_EXPORT2 ucnv_fromUnicode (UConverter * converter, |
---|
140 | char **target, |
---|
141 | const char *targetLimit, |
---|
142 | const UChar ** source, |
---|
143 | const UChar * sourceLimit, |
---|
144 | int32_t* offsets, |
---|
145 | int flush, |
---|
146 | UErrorCode * err); |
---|
147 | |
---|
148 | |
---|
149 | /** |
---|
150 | * Converts an array of codepage characters into an array of unicode characters. |
---|
151 | * The source pointer is an I/O parameter, it starts out pointing at the place |
---|
152 | * to begin translating, and ends up pointing after the first sequence of the bytes |
---|
153 | * that it encounters that are semantically invalid. |
---|
154 | * if ucnv_setFromUCallBack is called with an action other than STOP |
---|
155 | * before a call is made to this API, consumed and source should point to the same place |
---|
156 | * (unless target ends with an imcomplete sequence of bytes and flush is FALSE). |
---|
157 | * @param converter the Unicode converter |
---|
158 | * @param target : I/O parameter. Input : Points to the beginning of the buffer to copy |
---|
159 | * Unicode characters to. Output : points to after the last UChar copied to target. |
---|
160 | * @param targetLimit the pointer to the end of the target array |
---|
161 | * @param source the source codepage character array |
---|
162 | * @param sourceLimit the pointer to the end of the source array |
---|
163 | * @param offsets if NULL is passed, nothing will happen to it, otherwise it needs to have the same number |
---|
164 | * of allocated cells as <TT>target</TT>. Will fill in offsets from target to source pointer |
---|
165 | * e.g: <TT>offsets[3]</TT> is equal to 6, it means that the <TT>target[3]</TT> was a result of transcoding <TT>source[6]</TT> |
---|
166 | * For output data carried across calls -1 will be placed for offsets. |
---|
167 | * @param flush TRUE if the buffer is the last buffer and the conversion will finish |
---|
168 | * in this call, FALSE otherwise. |
---|
169 | * @param err the error code status <TT>ILLEGAL_ARGUMENT_ERROR</TT> will be returned if the |
---|
170 | * converter is <TT>NULL</TT>, or if <TT>targetLimit</TT> and <TT>sourceLimit</TT> are misaligned. |
---|
171 | * @see ucnv_toUChars |
---|
172 | * @see ucnv_getNextUChar |
---|
173 | * @see ucnv_convert |
---|
174 | * @see ucnv_setFromUCallBack |
---|
175 | */ |
---|
176 | |
---|
177 | U_CAPI |
---|
178 | void U_EXPORT2 ucnv_toUnicode (UConverter * converter, |
---|
179 | UChar ** target, |
---|
180 | const UChar * targetLimit, |
---|
181 | const char **source, |
---|
182 | const char *sourceLimit, |
---|
183 | int32_t* offsets, |
---|
184 | int flush, |
---|
185 | UErrorCode * err); |
---|
186 | |
---|
187 | |
---|
188 | /** |
---|
189 | * Transcodes the source Unicode string to the target string in a codepage encoding |
---|
190 | * with the specified Unicode converter. For example, if a Unicode to/from JIS |
---|
191 | * converter is specified, the source string in Unicode will be transcoded to JIS |
---|
192 | * encoding. The result will be stored in JIS encoding. |
---|
193 | * if any problems during conversion are encountered it will SUBSTITUTE with the default (initial) |
---|
194 | * substitute characters. |
---|
195 | * This function is a more convenient but less efficient version of \Ref{ucnv_fromUnicode}. |
---|
196 | * @param converter the Unicode converter |
---|
197 | * @param source the <TT>source</TT> Unicode string (zero Terminated) |
---|
198 | * @param target the <TT>target</TT> string in codepage encoding (<STRONG>not zero-terminated</STRONG> because some |
---|
199 | * codepage do not use '\0' as a string terminator |
---|
200 | * @param targetCapacity Input the number of bytes available in the <TT>target</TT> buffer |
---|
201 | * @param err the error status code. |
---|
202 | * <TT>INDEX_OUTOFBOUNDS_ERROR</TT> will be returned if the |
---|
203 | * the # of bytes provided are not enough for transcoding. |
---|
204 | * <TT>ILLEGAL_ARGUMENT_ERROR</TT> is returned if the converter is <TT>NULL</TT> or the source or target string is empty. |
---|
205 | * <TT>BUFFER_OVERFLOW_ERROR</TT> when <TT>targetSize</TT> turns out to be bigger than <TT>targetCapacity</TT> |
---|
206 | * @return number of bytes needed in target, regardless of <TT>targetCapacity</TT> |
---|
207 | * @see ucnv_fromUnicode |
---|
208 | * @see ucnv_convert |
---|
209 | */ |
---|
210 | U_CAPI |
---|
211 | int32_t U_EXPORT2 ucnv_fromUChars (const UConverter * converter, |
---|
212 | char *target, |
---|
213 | int32_t targetCapacity, |
---|
214 | const UChar * source, |
---|
215 | UErrorCode * err); |
---|
216 | |
---|
217 | |
---|
218 | |
---|
219 | |
---|
220 | |
---|
221 | /** |
---|
222 | * Transcode the source string in codepage encoding to the target string in |
---|
223 | * Unicode encoding. For example, if a Unicode to/from JIS |
---|
224 | * converter is specified, the source string in JIS encoding will be transcoded |
---|
225 | * to Unicode and placed into a provided target buffer. |
---|
226 | * if any problems during conversion are encountered it will SUBSTITUTE with the Unicode REPLACEMENT char |
---|
227 | * We recomment, the size of the target buffer needs to be at least as long as the maximum # of bytes per char |
---|
228 | * in this character set. |
---|
229 | * A zero-terminator will be placed at the end of the target buffer |
---|
230 | * This function is a more convenient but less efficient version of \Ref{ucnv_toUnicode}. |
---|
231 | * @param converter the Unicode converter |
---|
232 | * @param source the source string in codepage encoding |
---|
233 | * @param target the target string in Unicode encoding |
---|
234 | * @param targetCapacity capacity of the target buffer |
---|
235 | * @param sourceSize : Number of bytes in <TT>source</TT> to be transcoded |
---|
236 | * @param err the error status code |
---|
237 | * <TT>MEMORY_ALLOCATION_ERROR</TT> will be returned if the |
---|
238 | * the internal process buffer cannot be allocated for transcoding. |
---|
239 | * <TT>ILLEGAL_ARGUMENT_ERROR</TT> is returned if the converter is <TT>NULL</TT> or |
---|
240 | * if the source or target string is empty. |
---|
241 | * <TT>BUFFER_OVERFLOW_ERROR</TT> when the input buffer is prematurely exhausted and targetSize non-<TT>NULL</TT>. |
---|
242 | * @return the number of UChar needed in target (including the zero terminator) |
---|
243 | * @see ucnv_getNextUChar |
---|
244 | * @see ucnv_toUnicode |
---|
245 | * @see ucnv_convert |
---|
246 | */ |
---|
247 | U_CAPI |
---|
248 | int32_t U_EXPORT2 ucnv_toUChars (const UConverter * converter, |
---|
249 | UChar * target, |
---|
250 | int32_t targetCapacity, |
---|
251 | const char *source, |
---|
252 | int32_t sourceSize, |
---|
253 | UErrorCode * err); |
---|
254 | |
---|
255 | /******************************** |
---|
256 | * Will convert a codepage buffer one character at a time. |
---|
257 | * This function was written to be efficient when transcoding small amounts of data at a time. |
---|
258 | * In that case it will be more efficient than \Ref{ucnv_toUnicode}. |
---|
259 | * When converting large buffers use \Ref{ucnv_toUnicode}. |
---|
260 | *@param converter an open UConverter |
---|
261 | *@param source the address of a pointer to the codepage buffer, will be updated to point after |
---|
262 | *the bytes consumed in the conversion call. |
---|
263 | *@param points to the end of the input buffer |
---|
264 | *@param err fills in error status (see ucnv_toUnicode) |
---|
265 | *@return a UChar resulting from the partial conversion of source |
---|
266 | *@see ucnv_toUnicode |
---|
267 | *@see ucnv_toUChars |
---|
268 | *@see ucnv_convert |
---|
269 | */ |
---|
270 | U_CAPI |
---|
271 | UChar U_EXPORT2 ucnv_getNextUChar (UConverter * converter, |
---|
272 | const char **source, |
---|
273 | const char *sourceLimit, |
---|
274 | UErrorCode * err); |
---|
275 | |
---|
276 | |
---|
277 | /************************** |
---|
278 | * Will convert a sequence of bytes from one codepage to another. |
---|
279 | * This is <STRONG>NOT AN EFFICIENT</STRONG> way to transcode. |
---|
280 | * use \Ref{ucnv_toUnicode} and \Ref{ucnv_fromUnicode} for efficiency |
---|
281 | * @param toConverterName: The name of the converter that will be used to encode the output buffer |
---|
282 | * @param fromConverterName: The name of the converter that will be used to decode the input buffer |
---|
283 | * @param target: Pointer to the output buffer to write to |
---|
284 | * @param targetCapacity: on input contains the capacity of target |
---|
285 | * @param source: Pointer to the input buffer |
---|
286 | * @param sourceLength: on input contains the capacity of source |
---|
287 | * @param err: fills in an error status |
---|
288 | * @return will be filled in with the number of bytes needed in target |
---|
289 | * @see ucnv_fromUnicode |
---|
290 | * @see ucnv_toUnicode |
---|
291 | * @see ucnv_fromUChars |
---|
292 | * @see ucnv_toUChars |
---|
293 | * @see ucnv_getNextUChar |
---|
294 | */ |
---|
295 | U_CAPI |
---|
296 | int32_t U_EXPORT2 ucnv_convert (const char *toConverterName, |
---|
297 | const char *fromConverterName, |
---|
298 | char *target, |
---|
299 | int32_t targetCapacity, |
---|
300 | const char *source, |
---|
301 | int32_t sourceLength, |
---|
302 | UErrorCode * err); |
---|
303 | |
---|
304 | XERCES_CPP_NAMESPACE_END |
---|
305 | |
---|
306 | #endif |
---|
307 | |
---|
308 | #if (__OS400_TGTVRM__>=510) /* @01a */ |
---|
309 | #pragma datamodel(pop) /* @01a */ |
---|
310 | #endif /* @01a */ |
---|
311 | |
---|