|
sl@0
|
1 |
/*
|
|
sl@0
|
2 |
*******************************************************************************
|
|
sl@0
|
3 |
*
|
|
sl@0
|
4 |
* Copyright (C) 2002-2005, International Business Machines
|
|
sl@0
|
5 |
* Corporation and others. All Rights Reserved.
|
|
sl@0
|
6 |
*
|
|
sl@0
|
7 |
*******************************************************************************
|
|
sl@0
|
8 |
* file name: utf.h
|
|
sl@0
|
9 |
* encoding: US-ASCII
|
|
sl@0
|
10 |
* tab size: 8 (not used)
|
|
sl@0
|
11 |
* indentation:4
|
|
sl@0
|
12 |
*
|
|
sl@0
|
13 |
* created on: 2002sep21
|
|
sl@0
|
14 |
* created by: Markus W. Scherer
|
|
sl@0
|
15 |
*/
|
|
sl@0
|
16 |
|
|
sl@0
|
17 |
/**
|
|
sl@0
|
18 |
* \file
|
|
sl@0
|
19 |
* \brief C API: Deprecated macros for Unicode string handling
|
|
sl@0
|
20 |
*/
|
|
sl@0
|
21 |
|
|
sl@0
|
22 |
/**
|
|
sl@0
|
23 |
*
|
|
sl@0
|
24 |
* The macros in utf_old.h are all deprecated and their use discouraged.
|
|
sl@0
|
25 |
* Some of the design principles behind the set of UTF macros
|
|
sl@0
|
26 |
* have changed or proved impractical.
|
|
sl@0
|
27 |
* Almost all of the old "UTF macros" are at least renamed.
|
|
sl@0
|
28 |
* If you are looking for a new equivalent to an old macro, please see the
|
|
sl@0
|
29 |
* comment at the old one.
|
|
sl@0
|
30 |
*
|
|
sl@0
|
31 |
* utf_old.h is included by utf.h after unicode/umachine.h
|
|
sl@0
|
32 |
* and some common definitions, to not break old code.
|
|
sl@0
|
33 |
*
|
|
sl@0
|
34 |
* Brief summary of reasons for deprecation:
|
|
sl@0
|
35 |
* - Switch on UTF_SIZE (selection of UTF-8/16/32 default string processing)
|
|
sl@0
|
36 |
* was impractical.
|
|
sl@0
|
37 |
* - Switch on UTF_SAFE etc. (selection of unsafe/safe/strict default string processing)
|
|
sl@0
|
38 |
* was of little use and impractical.
|
|
sl@0
|
39 |
* - Whole classes of macros became obsolete outside of the UTF_SIZE/UTF_SAFE
|
|
sl@0
|
40 |
* selection framework: UTF32_ macros (all trivial)
|
|
sl@0
|
41 |
* and UTF_ default and intermediate macros (all aliases).
|
|
sl@0
|
42 |
* - The selection framework also caused many macro aliases.
|
|
sl@0
|
43 |
* - Change in Unicode standard: "irregular" sequences (3.0) became illegal (3.2).
|
|
sl@0
|
44 |
* - Change of language in Unicode standard:
|
|
sl@0
|
45 |
* Growing distinction between internal x-bit Unicode strings and external UTF-x
|
|
sl@0
|
46 |
* forms, with the former more lenient.
|
|
sl@0
|
47 |
* Suggests renaming of UTF16_ macros to U16_.
|
|
sl@0
|
48 |
* - The prefix "UTF_" without a width number confused some users.
|
|
sl@0
|
49 |
* - "Safe" append macros needed the addition of an error indicator output.
|
|
sl@0
|
50 |
* - "Safe" UTF-8 macros used legitimate (if rarely used) code point values
|
|
sl@0
|
51 |
* to indicate error conditions.
|
|
sl@0
|
52 |
* - The use of the "_CHAR" infix for code point operations confused some users.
|
|
sl@0
|
53 |
*
|
|
sl@0
|
54 |
* More details:
|
|
sl@0
|
55 |
*
|
|
sl@0
|
56 |
* Until ICU 2.2, utf.h theoretically allowed to choose among UTF-8/16/32
|
|
sl@0
|
57 |
* for string processing, and among unsafe/safe/strict default macros for that.
|
|
sl@0
|
58 |
*
|
|
sl@0
|
59 |
* It proved nearly impossible to write non-trivial, high-performance code
|
|
sl@0
|
60 |
* that is UTF-generic.
|
|
sl@0
|
61 |
* Unsafe default macros would be dangerous for default string processing,
|
|
sl@0
|
62 |
* and the main reason for the "strict" versions disappeared:
|
|
sl@0
|
63 |
* Between Unicode 3.0 and 3.2 all "irregular" UTF-8 sequences became illegal.
|
|
sl@0
|
64 |
* The only other conditions that "strict" checked for were non-characters,
|
|
sl@0
|
65 |
* which are valid during processing. Only during text input/output should they
|
|
sl@0
|
66 |
* be checked, and at that time other well-formedness checks may be
|
|
sl@0
|
67 |
* necessary or useful as well.
|
|
sl@0
|
68 |
* This can still be done by using U16_NEXT and U_IS_UNICODE_NONCHAR
|
|
sl@0
|
69 |
* or U_IS_UNICODE_CHAR.
|
|
sl@0
|
70 |
*
|
|
sl@0
|
71 |
* The old UTF8_..._SAFE macros also used some normal Unicode code points
|
|
sl@0
|
72 |
* to indicate malformed sequences.
|
|
sl@0
|
73 |
* The new UTF8_ macros without suffix use negative values instead.
|
|
sl@0
|
74 |
*
|
|
sl@0
|
75 |
* The entire contents of utf32.h was moved here without replacement
|
|
sl@0
|
76 |
* because all those macros were trivial and
|
|
sl@0
|
77 |
* were meaningful only in the framework of choosing the UTF size.
|
|
sl@0
|
78 |
*
|
|
sl@0
|
79 |
* See Jitterbug 2150 and its discussion on the ICU mailing list
|
|
sl@0
|
80 |
* in September 2002.
|
|
sl@0
|
81 |
*
|
|
sl@0
|
82 |
* <hr>
|
|
sl@0
|
83 |
*
|
|
sl@0
|
84 |
* <em>Obsolete part</em> of pre-ICU 2.4 utf.h file documentation:
|
|
sl@0
|
85 |
*
|
|
sl@0
|
86 |
* <p>The original concept for these files was for ICU to allow
|
|
sl@0
|
87 |
* in principle to set which UTF (UTF-8/16/32) is used internally
|
|
sl@0
|
88 |
* by defining UTF_SIZE to either 8, 16, or 32. utf.h would then define the UChar type
|
|
sl@0
|
89 |
* accordingly. UTF-16 was the default.</p>
|
|
sl@0
|
90 |
*
|
|
sl@0
|
91 |
* <p>This concept has been abandoned.
|
|
sl@0
|
92 |
* A lot of the ICU source code assumes UChar srings are in UTF-16.
|
|
sl@0
|
93 |
* This is especially true for low-level code like
|
|
sl@0
|
94 |
* conversion, normalization, and collation.
|
|
sl@0
|
95 |
* The utf.h header enforces the default of UTF-16.
|
|
sl@0
|
96 |
* The UTF-8 and UTF-32 macros remain for now for completeness and backward compatibility.</p>
|
|
sl@0
|
97 |
*
|
|
sl@0
|
98 |
* <p>Accordingly, utf.h defines UChar to be an unsigned 16-bit integer. If this matches wchar_t, then
|
|
sl@0
|
99 |
* UChar is defined to be exactly wchar_t, otherwise uint16_t.</p>
|
|
sl@0
|
100 |
*
|
|
sl@0
|
101 |
* <p>UChar32 is defined to be a signed 32-bit integer (int32_t), large enough for a 21-bit
|
|
sl@0
|
102 |
* Unicode code point (Unicode scalar value, 0..0x10ffff).
|
|
sl@0
|
103 |
* Before ICU 2.4, the definition of UChar32 was similarly platform-dependent as
|
|
sl@0
|
104 |
* the definition of UChar. For details see the documentation for UChar32 itself.</p>
|
|
sl@0
|
105 |
*
|
|
sl@0
|
106 |
* <p>utf.h also defines a number of C macros for handling single Unicode code points and
|
|
sl@0
|
107 |
* for using UTF Unicode strings. It includes utf8.h, utf16.h, and utf32.h for the actual
|
|
sl@0
|
108 |
* implementations of those macros and then aliases one set of them (for UTF-16) for general use.
|
|
sl@0
|
109 |
* The UTF-specific macros have the UTF size in the macro name prefixes (UTF16_...), while
|
|
sl@0
|
110 |
* the general alias macros always begin with UTF_...</p>
|
|
sl@0
|
111 |
*
|
|
sl@0
|
112 |
* <p>Many string operations can be done with or without error checking.
|
|
sl@0
|
113 |
* Where such a distinction is useful, there are two versions of the macros, "unsafe" and "safe"
|
|
sl@0
|
114 |
* ones with ..._UNSAFE and ..._SAFE suffixes. The unsafe macros are fast but may cause
|
|
sl@0
|
115 |
* program failures if the strings are not well-formed. The safe macros have an additional, boolean
|
|
sl@0
|
116 |
* parameter "strict". If strict is FALSE, then only illegal sequences are detected.
|
|
sl@0
|
117 |
* Otherwise, irregular sequences and non-characters are detected as well (like single surrogates).
|
|
sl@0
|
118 |
* Safe macros return special error code points for illegal/irregular sequences:
|
|
sl@0
|
119 |
* Typically, U+ffff, or values that would result in a code unit sequence of the same length
|
|
sl@0
|
120 |
* as the erroneous input sequence.<br>
|
|
sl@0
|
121 |
* Note that _UNSAFE macros have fewer parameters: They do not have the strictness parameter, and
|
|
sl@0
|
122 |
* they do not have start/length parameters for boundary checking.</p>
|
|
sl@0
|
123 |
*
|
|
sl@0
|
124 |
* <p>Here, the macros are aliased in two steps:
|
|
sl@0
|
125 |
* In the first step, the UTF-specific macros with UTF16_ prefix and _UNSAFE and _SAFE suffixes are
|
|
sl@0
|
126 |
* aliased according to the UTF_SIZE to macros with UTF_ prefix and the same suffixes and signatures.
|
|
sl@0
|
127 |
* Then, in a second step, the default, general alias macros are set to use either the unsafe or
|
|
sl@0
|
128 |
* the safe/not strict (default) or the safe/strict macro;
|
|
sl@0
|
129 |
* these general macros do not have a strictness parameter.</p>
|
|
sl@0
|
130 |
*
|
|
sl@0
|
131 |
* <p>It is possible to change the default choice for the general alias macros to be unsafe, safe/not strict or safe/strict.
|
|
sl@0
|
132 |
* The default is safe/not strict. It is not recommended to select the unsafe macros as the basis for
|
|
sl@0
|
133 |
* Unicode string handling in ICU! To select this, define UTF_SAFE, UTF_STRICT, or UTF_UNSAFE.</p>
|
|
sl@0
|
134 |
*
|
|
sl@0
|
135 |
* <p>For general use, one should use the default, general macros with UTF_ prefix and no _SAFE/_UNSAFE suffix.
|
|
sl@0
|
136 |
* Only in some cases it may be necessary to control the choice of macro directly and use a less generic alias.
|
|
sl@0
|
137 |
* For example, if it can be assumed that a string is well-formed and the index will stay within the bounds,
|
|
sl@0
|
138 |
* then the _UNSAFE version may be used.
|
|
sl@0
|
139 |
* If a UTF-8 string is to be processed, then the macros with UTF8_ prefixes need to be used.</p>
|
|
sl@0
|
140 |
*
|
|
sl@0
|
141 |
* <hr>
|
|
sl@0
|
142 |
*
|
|
sl@0
|
143 |
* @deprecated ICU 2.4. Use the macros in utf.h, utf16.h, utf8.h instead.
|
|
sl@0
|
144 |
*/
|
|
sl@0
|
145 |
|
|
sl@0
|
146 |
#ifndef __UTF_OLD_H__
|
|
sl@0
|
147 |
#define __UTF_OLD_H__
|
|
sl@0
|
148 |
|
|
sl@0
|
149 |
#ifndef U_HIDE_DEPRECATED_API
|
|
sl@0
|
150 |
|
|
sl@0
|
151 |
/* utf.h must be included first. */
|
|
sl@0
|
152 |
#ifndef __UTF_H__
|
|
sl@0
|
153 |
# include "unicode/utf.h"
|
|
sl@0
|
154 |
#endif
|
|
sl@0
|
155 |
|
|
sl@0
|
156 |
/* Formerly utf.h, part 1 --------------------------------------------------- */
|
|
sl@0
|
157 |
|
|
sl@0
|
158 |
#ifdef U_USE_UTF_DEPRECATES
|
|
sl@0
|
159 |
/**
|
|
sl@0
|
160 |
* Unicode string and array offset and index type.
|
|
sl@0
|
161 |
* ICU always counts Unicode code units (UChars) for
|
|
sl@0
|
162 |
* string offsets, indexes, and lengths, not Unicode code points.
|
|
sl@0
|
163 |
*
|
|
sl@0
|
164 |
* @obsolete ICU 2.6. Use int32_t directly instead since this API will be removed in that release.
|
|
sl@0
|
165 |
*/
|
|
sl@0
|
166 |
typedef int32_t UTextOffset;
|
|
sl@0
|
167 |
#endif
|
|
sl@0
|
168 |
|
|
sl@0
|
169 |
/** Number of bits in a Unicode string code unit - ICU uses 16-bit Unicode. @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
170 |
#define UTF_SIZE 16
|
|
sl@0
|
171 |
|
|
sl@0
|
172 |
/**
|
|
sl@0
|
173 |
* The default choice for general Unicode string macros is to use the ..._SAFE macro implementations
|
|
sl@0
|
174 |
* with strict=FALSE.
|
|
sl@0
|
175 |
*
|
|
sl@0
|
176 |
* @deprecated ICU 2.4. Obsolete, see utf_old.h.
|
|
sl@0
|
177 |
*/
|
|
sl@0
|
178 |
#define UTF_SAFE
|
|
sl@0
|
179 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
180 |
#undef UTF_UNSAFE
|
|
sl@0
|
181 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
182 |
#undef UTF_STRICT
|
|
sl@0
|
183 |
|
|
sl@0
|
184 |
/**
|
|
sl@0
|
185 |
* <p>UTF8_ERROR_VALUE_1 and UTF8_ERROR_VALUE_2 are special error values for UTF-8,
|
|
sl@0
|
186 |
* which need 1 or 2 bytes in UTF-8:<br>
|
|
sl@0
|
187 |
* U+0015 = NAK = Negative Acknowledge, C0 control character<br>
|
|
sl@0
|
188 |
* U+009f = highest C1 control character</p>
|
|
sl@0
|
189 |
*
|
|
sl@0
|
190 |
* <p>These are used by UTF8_..._SAFE macros so that they can return an error value
|
|
sl@0
|
191 |
* that needs the same number of code units (bytes) as were seen by
|
|
sl@0
|
192 |
* a macro. They should be tested with UTF_IS_ERROR() or UTF_IS_VALID().</p>
|
|
sl@0
|
193 |
*
|
|
sl@0
|
194 |
* @deprecated ICU 2.4. Obsolete, see utf_old.h.
|
|
sl@0
|
195 |
*/
|
|
sl@0
|
196 |
#define UTF8_ERROR_VALUE_1 0x15
|
|
sl@0
|
197 |
|
|
sl@0
|
198 |
/**
|
|
sl@0
|
199 |
* See documentation on UTF8_ERROR_VALUE_1 for details.
|
|
sl@0
|
200 |
*
|
|
sl@0
|
201 |
* @deprecated ICU 2.4. Obsolete, see utf_old.h.
|
|
sl@0
|
202 |
*/
|
|
sl@0
|
203 |
#define UTF8_ERROR_VALUE_2 0x9f
|
|
sl@0
|
204 |
|
|
sl@0
|
205 |
/**
|
|
sl@0
|
206 |
* Error value for all UTFs. This code point value will be set by macros with error
|
|
sl@0
|
207 |
* checking if an error is detected.
|
|
sl@0
|
208 |
*
|
|
sl@0
|
209 |
* @deprecated ICU 2.4. Obsolete, see utf_old.h.
|
|
sl@0
|
210 |
*/
|
|
sl@0
|
211 |
#define UTF_ERROR_VALUE 0xffff
|
|
sl@0
|
212 |
|
|
sl@0
|
213 |
/**
|
|
sl@0
|
214 |
* Is a given 32-bit code an error value
|
|
sl@0
|
215 |
* as returned by one of the macros for any UTF?
|
|
sl@0
|
216 |
*
|
|
sl@0
|
217 |
* @deprecated ICU 2.4. Obsolete, see utf_old.h.
|
|
sl@0
|
218 |
*/
|
|
sl@0
|
219 |
#define UTF_IS_ERROR(c) \
|
|
sl@0
|
220 |
(((c)&0xfffe)==0xfffe || (c)==UTF8_ERROR_VALUE_1 || (c)==UTF8_ERROR_VALUE_2)
|
|
sl@0
|
221 |
|
|
sl@0
|
222 |
/**
|
|
sl@0
|
223 |
* This is a combined macro: Is c a valid Unicode value _and_ not an error code?
|
|
sl@0
|
224 |
*
|
|
sl@0
|
225 |
* @deprecated ICU 2.4. Obsolete, see utf_old.h.
|
|
sl@0
|
226 |
*/
|
|
sl@0
|
227 |
#define UTF_IS_VALID(c) \
|
|
sl@0
|
228 |
(UTF_IS_UNICODE_CHAR(c) && \
|
|
sl@0
|
229 |
(c)!=UTF8_ERROR_VALUE_1 && (c)!=UTF8_ERROR_VALUE_2)
|
|
sl@0
|
230 |
|
|
sl@0
|
231 |
/**
|
|
sl@0
|
232 |
* Is this code unit or code point a surrogate (U+d800..U+dfff)?
|
|
sl@0
|
233 |
* @deprecated ICU 2.4. Renamed to U_IS_SURROGATE and U16_IS_SURROGATE, see utf_old.h.
|
|
sl@0
|
234 |
*/
|
|
sl@0
|
235 |
#define UTF_IS_SURROGATE(uchar) (((uchar)&0xfffff800)==0xd800)
|
|
sl@0
|
236 |
|
|
sl@0
|
237 |
/**
|
|
sl@0
|
238 |
* Is a given 32-bit code point a Unicode noncharacter?
|
|
sl@0
|
239 |
*
|
|
sl@0
|
240 |
* @deprecated ICU 2.4. Renamed to U_IS_UNICODE_NONCHAR, see utf_old.h.
|
|
sl@0
|
241 |
*/
|
|
sl@0
|
242 |
#define UTF_IS_UNICODE_NONCHAR(c) \
|
|
sl@0
|
243 |
((c)>=0xfdd0 && \
|
|
sl@0
|
244 |
((uint32_t)(c)<=0xfdef || ((c)&0xfffe)==0xfffe) && \
|
|
sl@0
|
245 |
(uint32_t)(c)<=0x10ffff)
|
|
sl@0
|
246 |
|
|
sl@0
|
247 |
/**
|
|
sl@0
|
248 |
* Is a given 32-bit value a Unicode code point value (0..U+10ffff)
|
|
sl@0
|
249 |
* that can be assigned a character?
|
|
sl@0
|
250 |
*
|
|
sl@0
|
251 |
* Code points that are not characters include:
|
|
sl@0
|
252 |
* - single surrogate code points (U+d800..U+dfff, 2048 code points)
|
|
sl@0
|
253 |
* - the last two code points on each plane (U+__fffe and U+__ffff, 34 code points)
|
|
sl@0
|
254 |
* - U+fdd0..U+fdef (new with Unicode 3.1, 32 code points)
|
|
sl@0
|
255 |
* - the highest Unicode code point value is U+10ffff
|
|
sl@0
|
256 |
*
|
|
sl@0
|
257 |
* This means that all code points below U+d800 are character code points,
|
|
sl@0
|
258 |
* and that boundary is tested first for performance.
|
|
sl@0
|
259 |
*
|
|
sl@0
|
260 |
* @deprecated ICU 2.4. Renamed to U_IS_UNICODE_CHAR, see utf_old.h.
|
|
sl@0
|
261 |
*/
|
|
sl@0
|
262 |
#define UTF_IS_UNICODE_CHAR(c) \
|
|
sl@0
|
263 |
((uint32_t)(c)<0xd800 || \
|
|
sl@0
|
264 |
((uint32_t)(c)>0xdfff && \
|
|
sl@0
|
265 |
(uint32_t)(c)<=0x10ffff && \
|
|
sl@0
|
266 |
!UTF_IS_UNICODE_NONCHAR(c)))
|
|
sl@0
|
267 |
|
|
sl@0
|
268 |
/* Formerly utf8.h ---------------------------------------------------------- */
|
|
sl@0
|
269 |
|
|
sl@0
|
270 |
/**
|
|
sl@0
|
271 |
* Count the trail bytes for a UTF-8 lead byte.
|
|
sl@0
|
272 |
* @deprecated ICU 2.4. Renamed to U8_COUNT_TRAIL_BYTES, see utf_old.h.
|
|
sl@0
|
273 |
*/
|
|
sl@0
|
274 |
#define UTF8_COUNT_TRAIL_BYTES(leadByte) (utf8_countTrailBytes[(uint8_t)leadByte])
|
|
sl@0
|
275 |
|
|
sl@0
|
276 |
/**
|
|
sl@0
|
277 |
* Mask a UTF-8 lead byte, leave only the lower bits that form part of the code point value.
|
|
sl@0
|
278 |
* @deprecated ICU 2.4. Renamed to U8_MASK_LEAD_BYTE, see utf_old.h.
|
|
sl@0
|
279 |
*/
|
|
sl@0
|
280 |
#define UTF8_MASK_LEAD_BYTE(leadByte, countTrailBytes) ((leadByte)&=(1<<(6-(countTrailBytes)))-1)
|
|
sl@0
|
281 |
|
|
sl@0
|
282 |
/** Is this this code point a single code unit (byte)? @deprecated ICU 2.4. Renamed to U8_IS_SINGLE, see utf_old.h. */
|
|
sl@0
|
283 |
#define UTF8_IS_SINGLE(uchar) (((uchar)&0x80)==0)
|
|
sl@0
|
284 |
/** Is this this code unit the lead code unit (byte) of a code point? @deprecated ICU 2.4. Renamed to U8_IS_LEAD, see utf_old.h. */
|
|
sl@0
|
285 |
#define UTF8_IS_LEAD(uchar) ((uint8_t)((uchar)-0xc0)<0x3e)
|
|
sl@0
|
286 |
/** Is this this code unit a trailing code unit (byte) of a code point? @deprecated ICU 2.4. Renamed to U8_IS_TRAIL, see utf_old.h. */
|
|
sl@0
|
287 |
#define UTF8_IS_TRAIL(uchar) (((uchar)&0xc0)==0x80)
|
|
sl@0
|
288 |
|
|
sl@0
|
289 |
/** Does this scalar Unicode value need multiple code units for storage? @deprecated ICU 2.4. Use U8_LENGTH or test ((uint32_t)(c)>0x7f) instead, see utf_old.h. */
|
|
sl@0
|
290 |
#define UTF8_NEED_MULTIPLE_UCHAR(c) ((uint32_t)(c)>0x7f)
|
|
sl@0
|
291 |
|
|
sl@0
|
292 |
/**
|
|
sl@0
|
293 |
* Given the lead character, how many bytes are taken by this code point.
|
|
sl@0
|
294 |
* ICU does not deal with code points >0x10ffff
|
|
sl@0
|
295 |
* unless necessary for advancing in the byte stream.
|
|
sl@0
|
296 |
*
|
|
sl@0
|
297 |
* These length macros take into account that for values >0x10ffff
|
|
sl@0
|
298 |
* the UTF8_APPEND_CHAR_SAFE macros would write the error code point 0xffff
|
|
sl@0
|
299 |
* with 3 bytes.
|
|
sl@0
|
300 |
* Code point comparisons need to be in uint32_t because UChar32
|
|
sl@0
|
301 |
* may be a signed type, and negative values must be recognized.
|
|
sl@0
|
302 |
*
|
|
sl@0
|
303 |
* @deprecated ICU 2.4. Use U8_LENGTH instead, see utf_old.h.
|
|
sl@0
|
304 |
*/
|
|
sl@0
|
305 |
#if 1
|
|
sl@0
|
306 |
# define UTF8_CHAR_LENGTH(c) \
|
|
sl@0
|
307 |
((uint32_t)(c)<=0x7f ? 1 : \
|
|
sl@0
|
308 |
((uint32_t)(c)<=0x7ff ? 2 : \
|
|
sl@0
|
309 |
((uint32_t)((c)-0x10000)>0xfffff ? 3 : 4) \
|
|
sl@0
|
310 |
) \
|
|
sl@0
|
311 |
)
|
|
sl@0
|
312 |
#else
|
|
sl@0
|
313 |
# define UTF8_CHAR_LENGTH(c) \
|
|
sl@0
|
314 |
((uint32_t)(c)<=0x7f ? 1 : \
|
|
sl@0
|
315 |
((uint32_t)(c)<=0x7ff ? 2 : \
|
|
sl@0
|
316 |
((uint32_t)(c)<=0xffff ? 3 : \
|
|
sl@0
|
317 |
((uint32_t)(c)<=0x10ffff ? 4 : \
|
|
sl@0
|
318 |
((uint32_t)(c)<=0x3ffffff ? 5 : \
|
|
sl@0
|
319 |
((uint32_t)(c)<=0x7fffffff ? 6 : 3) \
|
|
sl@0
|
320 |
) \
|
|
sl@0
|
321 |
) \
|
|
sl@0
|
322 |
) \
|
|
sl@0
|
323 |
) \
|
|
sl@0
|
324 |
)
|
|
sl@0
|
325 |
#endif
|
|
sl@0
|
326 |
|
|
sl@0
|
327 |
/** The maximum number of bytes per code point. @deprecated ICU 2.4. Renamed to U8_MAX_LENGTH, see utf_old.h. */
|
|
sl@0
|
328 |
#define UTF8_MAX_CHAR_LENGTH 4
|
|
sl@0
|
329 |
|
|
sl@0
|
330 |
/** Average number of code units compared to UTF-16. @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
331 |
#define UTF8_ARRAY_SIZE(size) ((5*(size))/2)
|
|
sl@0
|
332 |
|
|
sl@0
|
333 |
/** @deprecated ICU 2.4. Renamed to U8_GET_UNSAFE, see utf_old.h. */
|
|
sl@0
|
334 |
#define UTF8_GET_CHAR_UNSAFE(s, i, c) { \
|
|
sl@0
|
335 |
int32_t _utf8_get_char_unsafe_index=(int32_t)(i); \
|
|
sl@0
|
336 |
UTF8_SET_CHAR_START_UNSAFE(s, _utf8_get_char_unsafe_index); \
|
|
sl@0
|
337 |
UTF8_NEXT_CHAR_UNSAFE(s, _utf8_get_char_unsafe_index, c); \
|
|
sl@0
|
338 |
}
|
|
sl@0
|
339 |
|
|
sl@0
|
340 |
/** @deprecated ICU 2.4. Use U8_GET instead, see utf_old.h. */
|
|
sl@0
|
341 |
#define UTF8_GET_CHAR_SAFE(s, start, i, length, c, strict) { \
|
|
sl@0
|
342 |
int32_t _utf8_get_char_safe_index=(int32_t)(i); \
|
|
sl@0
|
343 |
UTF8_SET_CHAR_START_SAFE(s, start, _utf8_get_char_safe_index); \
|
|
sl@0
|
344 |
UTF8_NEXT_CHAR_SAFE(s, _utf8_get_char_safe_index, length, c, strict); \
|
|
sl@0
|
345 |
}
|
|
sl@0
|
346 |
|
|
sl@0
|
347 |
/** @deprecated ICU 2.4. Renamed to U8_NEXT_UNSAFE, see utf_old.h. */
|
|
sl@0
|
348 |
#define UTF8_NEXT_CHAR_UNSAFE(s, i, c) { \
|
|
sl@0
|
349 |
(c)=(s)[(i)++]; \
|
|
sl@0
|
350 |
if((uint8_t)((c)-0xc0)<0x35) { \
|
|
sl@0
|
351 |
uint8_t __count=UTF8_COUNT_TRAIL_BYTES(c); \
|
|
sl@0
|
352 |
UTF8_MASK_LEAD_BYTE(c, __count); \
|
|
sl@0
|
353 |
switch(__count) { \
|
|
sl@0
|
354 |
/* each following branch falls through to the next one */ \
|
|
sl@0
|
355 |
case 3: \
|
|
sl@0
|
356 |
(c)=((c)<<6)|((s)[(i)++]&0x3f); \
|
|
sl@0
|
357 |
case 2: \
|
|
sl@0
|
358 |
(c)=((c)<<6)|((s)[(i)++]&0x3f); \
|
|
sl@0
|
359 |
case 1: \
|
|
sl@0
|
360 |
(c)=((c)<<6)|((s)[(i)++]&0x3f); \
|
|
sl@0
|
361 |
/* no other branches to optimize switch() */ \
|
|
sl@0
|
362 |
break; \
|
|
sl@0
|
363 |
} \
|
|
sl@0
|
364 |
} \
|
|
sl@0
|
365 |
}
|
|
sl@0
|
366 |
|
|
sl@0
|
367 |
/** @deprecated ICU 2.4. Renamed to U8_APPEND_UNSAFE, see utf_old.h. */
|
|
sl@0
|
368 |
#define UTF8_APPEND_CHAR_UNSAFE(s, i, c) { \
|
|
sl@0
|
369 |
if((uint32_t)(c)<=0x7f) { \
|
|
sl@0
|
370 |
(s)[(i)++]=(uint8_t)(c); \
|
|
sl@0
|
371 |
} else { \
|
|
sl@0
|
372 |
if((uint32_t)(c)<=0x7ff) { \
|
|
sl@0
|
373 |
(s)[(i)++]=(uint8_t)(((c)>>6)|0xc0); \
|
|
sl@0
|
374 |
} else { \
|
|
sl@0
|
375 |
if((uint32_t)(c)<=0xffff) { \
|
|
sl@0
|
376 |
(s)[(i)++]=(uint8_t)(((c)>>12)|0xe0); \
|
|
sl@0
|
377 |
} else { \
|
|
sl@0
|
378 |
(s)[(i)++]=(uint8_t)(((c)>>18)|0xf0); \
|
|
sl@0
|
379 |
(s)[(i)++]=(uint8_t)((((c)>>12)&0x3f)|0x80); \
|
|
sl@0
|
380 |
} \
|
|
sl@0
|
381 |
(s)[(i)++]=(uint8_t)((((c)>>6)&0x3f)|0x80); \
|
|
sl@0
|
382 |
} \
|
|
sl@0
|
383 |
(s)[(i)++]=(uint8_t)(((c)&0x3f)|0x80); \
|
|
sl@0
|
384 |
} \
|
|
sl@0
|
385 |
}
|
|
sl@0
|
386 |
|
|
sl@0
|
387 |
/** @deprecated ICU 2.4. Renamed to U8_FWD_1_UNSAFE, see utf_old.h. */
|
|
sl@0
|
388 |
#define UTF8_FWD_1_UNSAFE(s, i) { \
|
|
sl@0
|
389 |
(i)+=1+UTF8_COUNT_TRAIL_BYTES((s)[i]); \
|
|
sl@0
|
390 |
}
|
|
sl@0
|
391 |
|
|
sl@0
|
392 |
/** @deprecated ICU 2.4. Renamed to U8_FWD_N_UNSAFE, see utf_old.h. */
|
|
sl@0
|
393 |
#define UTF8_FWD_N_UNSAFE(s, i, n) { \
|
|
sl@0
|
394 |
int32_t __N=(n); \
|
|
sl@0
|
395 |
while(__N>0) { \
|
|
sl@0
|
396 |
UTF8_FWD_1_UNSAFE(s, i); \
|
|
sl@0
|
397 |
--__N; \
|
|
sl@0
|
398 |
} \
|
|
sl@0
|
399 |
}
|
|
sl@0
|
400 |
|
|
sl@0
|
401 |
/** @deprecated ICU 2.4. Renamed to U8_SET_CP_START_UNSAFE, see utf_old.h. */
|
|
sl@0
|
402 |
#define UTF8_SET_CHAR_START_UNSAFE(s, i) { \
|
|
sl@0
|
403 |
while(UTF8_IS_TRAIL((s)[i])) { --(i); } \
|
|
sl@0
|
404 |
}
|
|
sl@0
|
405 |
|
|
sl@0
|
406 |
/** @deprecated ICU 2.4. Use U8_NEXT instead, see utf_old.h. */
|
|
sl@0
|
407 |
#define UTF8_NEXT_CHAR_SAFE(s, i, length, c, strict) { \
|
|
sl@0
|
408 |
(c)=(s)[(i)++]; \
|
|
sl@0
|
409 |
if((c)>=0x80) { \
|
|
sl@0
|
410 |
if(UTF8_IS_LEAD(c)) { \
|
|
sl@0
|
411 |
(c)=utf8_nextCharSafeBody(s, &(i), (int32_t)(length), c, strict); \
|
|
sl@0
|
412 |
} else { \
|
|
sl@0
|
413 |
(c)=UTF8_ERROR_VALUE_1; \
|
|
sl@0
|
414 |
} \
|
|
sl@0
|
415 |
} \
|
|
sl@0
|
416 |
}
|
|
sl@0
|
417 |
|
|
sl@0
|
418 |
/** @deprecated ICU 2.4. Use U8_APPEND instead, see utf_old.h. */
|
|
sl@0
|
419 |
#define UTF8_APPEND_CHAR_SAFE(s, i, length, c) { \
|
|
sl@0
|
420 |
if((uint32_t)(c)<=0x7f) { \
|
|
sl@0
|
421 |
(s)[(i)++]=(uint8_t)(c); \
|
|
sl@0
|
422 |
} else { \
|
|
sl@0
|
423 |
(i)=utf8_appendCharSafeBody(s, (int32_t)(i), (int32_t)(length), c, NULL); \
|
|
sl@0
|
424 |
} \
|
|
sl@0
|
425 |
}
|
|
sl@0
|
426 |
|
|
sl@0
|
427 |
/** @deprecated ICU 2.4. Renamed to U8_FWD_1, see utf_old.h. */
|
|
sl@0
|
428 |
#define UTF8_FWD_1_SAFE(s, i, length) U8_FWD_1(s, i, length)
|
|
sl@0
|
429 |
|
|
sl@0
|
430 |
/** @deprecated ICU 2.4. Renamed to U8_FWD_N, see utf_old.h. */
|
|
sl@0
|
431 |
#define UTF8_FWD_N_SAFE(s, i, length, n) U8_FWD_N(s, i, length, n)
|
|
sl@0
|
432 |
|
|
sl@0
|
433 |
/** @deprecated ICU 2.4. Renamed to U8_SET_CP_START, see utf_old.h. */
|
|
sl@0
|
434 |
#define UTF8_SET_CHAR_START_SAFE(s, start, i) U8_SET_CP_START(s, start, i)
|
|
sl@0
|
435 |
|
|
sl@0
|
436 |
/** @deprecated ICU 2.4. Renamed to U8_PREV_UNSAFE, see utf_old.h. */
|
|
sl@0
|
437 |
#define UTF8_PREV_CHAR_UNSAFE(s, i, c) { \
|
|
sl@0
|
438 |
(c)=(s)[--(i)]; \
|
|
sl@0
|
439 |
if(UTF8_IS_TRAIL(c)) { \
|
|
sl@0
|
440 |
uint8_t __b, __count=1, __shift=6; \
|
|
sl@0
|
441 |
\
|
|
sl@0
|
442 |
/* c is a trail byte */ \
|
|
sl@0
|
443 |
(c)&=0x3f; \
|
|
sl@0
|
444 |
for(;;) { \
|
|
sl@0
|
445 |
__b=(s)[--(i)]; \
|
|
sl@0
|
446 |
if(__b>=0xc0) { \
|
|
sl@0
|
447 |
UTF8_MASK_LEAD_BYTE(__b, __count); \
|
|
sl@0
|
448 |
(c)|=(UChar32)__b<<__shift; \
|
|
sl@0
|
449 |
break; \
|
|
sl@0
|
450 |
} else { \
|
|
sl@0
|
451 |
(c)|=(UChar32)(__b&0x3f)<<__shift; \
|
|
sl@0
|
452 |
++__count; \
|
|
sl@0
|
453 |
__shift+=6; \
|
|
sl@0
|
454 |
} \
|
|
sl@0
|
455 |
} \
|
|
sl@0
|
456 |
} \
|
|
sl@0
|
457 |
}
|
|
sl@0
|
458 |
|
|
sl@0
|
459 |
/** @deprecated ICU 2.4. Renamed to U8_BACK_1_UNSAFE, see utf_old.h. */
|
|
sl@0
|
460 |
#define UTF8_BACK_1_UNSAFE(s, i) { \
|
|
sl@0
|
461 |
while(UTF8_IS_TRAIL((s)[--(i)])) {} \
|
|
sl@0
|
462 |
}
|
|
sl@0
|
463 |
|
|
sl@0
|
464 |
/** @deprecated ICU 2.4. Renamed to U8_BACK_N_UNSAFE, see utf_old.h. */
|
|
sl@0
|
465 |
#define UTF8_BACK_N_UNSAFE(s, i, n) { \
|
|
sl@0
|
466 |
int32_t __N=(n); \
|
|
sl@0
|
467 |
while(__N>0) { \
|
|
sl@0
|
468 |
UTF8_BACK_1_UNSAFE(s, i); \
|
|
sl@0
|
469 |
--__N; \
|
|
sl@0
|
470 |
} \
|
|
sl@0
|
471 |
}
|
|
sl@0
|
472 |
|
|
sl@0
|
473 |
/** @deprecated ICU 2.4. Renamed to U8_SET_CP_LIMIT_UNSAFE, see utf_old.h. */
|
|
sl@0
|
474 |
#define UTF8_SET_CHAR_LIMIT_UNSAFE(s, i) { \
|
|
sl@0
|
475 |
UTF8_BACK_1_UNSAFE(s, i); \
|
|
sl@0
|
476 |
UTF8_FWD_1_UNSAFE(s, i); \
|
|
sl@0
|
477 |
}
|
|
sl@0
|
478 |
|
|
sl@0
|
479 |
/** @deprecated ICU 2.4. Use U8_PREV instead, see utf_old.h. */
|
|
sl@0
|
480 |
#define UTF8_PREV_CHAR_SAFE(s, start, i, c, strict) { \
|
|
sl@0
|
481 |
(c)=(s)[--(i)]; \
|
|
sl@0
|
482 |
if((c)>=0x80) { \
|
|
sl@0
|
483 |
if((c)<=0xbf) { \
|
|
sl@0
|
484 |
(c)=utf8_prevCharSafeBody(s, start, &(i), c, strict); \
|
|
sl@0
|
485 |
} else { \
|
|
sl@0
|
486 |
(c)=UTF8_ERROR_VALUE_1; \
|
|
sl@0
|
487 |
} \
|
|
sl@0
|
488 |
} \
|
|
sl@0
|
489 |
}
|
|
sl@0
|
490 |
|
|
sl@0
|
491 |
/** @deprecated ICU 2.4. Renamed to U8_BACK_1, see utf_old.h. */
|
|
sl@0
|
492 |
#define UTF8_BACK_1_SAFE(s, start, i) U8_BACK_1(s, start, i)
|
|
sl@0
|
493 |
|
|
sl@0
|
494 |
/** @deprecated ICU 2.4. Renamed to U8_BACK_N, see utf_old.h. */
|
|
sl@0
|
495 |
#define UTF8_BACK_N_SAFE(s, start, i, n) U8_BACK_N(s, start, i, n)
|
|
sl@0
|
496 |
|
|
sl@0
|
497 |
/** @deprecated ICU 2.4. Renamed to U8_SET_CP_LIMIT, see utf_old.h. */
|
|
sl@0
|
498 |
#define UTF8_SET_CHAR_LIMIT_SAFE(s, start, i, length) U8_SET_CP_LIMIT(s, start, i, length)
|
|
sl@0
|
499 |
|
|
sl@0
|
500 |
/* Formerly utf16.h --------------------------------------------------------- */
|
|
sl@0
|
501 |
|
|
sl@0
|
502 |
/** Is uchar a first/lead surrogate? @deprecated ICU 2.4. Renamed to U_IS_LEAD and U16_IS_LEAD, see utf_old.h. */
|
|
sl@0
|
503 |
#define UTF_IS_FIRST_SURROGATE(uchar) (((uchar)&0xfffffc00)==0xd800)
|
|
sl@0
|
504 |
|
|
sl@0
|
505 |
/** Is uchar a second/trail surrogate? @deprecated ICU 2.4. Renamed to U_IS_TRAIL and U16_IS_TRAIL, see utf_old.h. */
|
|
sl@0
|
506 |
#define UTF_IS_SECOND_SURROGATE(uchar) (((uchar)&0xfffffc00)==0xdc00)
|
|
sl@0
|
507 |
|
|
sl@0
|
508 |
/** Assuming c is a surrogate, is it a first/lead surrogate? @deprecated ICU 2.4. Renamed to U_IS_SURROGATE_LEAD and U16_IS_SURROGATE_LEAD, see utf_old.h. */
|
|
sl@0
|
509 |
#define UTF_IS_SURROGATE_FIRST(c) (((c)&0x400)==0)
|
|
sl@0
|
510 |
|
|
sl@0
|
511 |
/** Helper constant for UTF16_GET_PAIR_VALUE. @deprecated ICU 2.4. Renamed to U16_SURROGATE_OFFSET, see utf_old.h. */
|
|
sl@0
|
512 |
#define UTF_SURROGATE_OFFSET ((0xd800<<10UL)+0xdc00-0x10000)
|
|
sl@0
|
513 |
|
|
sl@0
|
514 |
/** Get the UTF-32 value from the surrogate code units. @deprecated ICU 2.4. Renamed to U16_GET_SUPPLEMENTARY, see utf_old.h. */
|
|
sl@0
|
515 |
#define UTF16_GET_PAIR_VALUE(first, second) \
|
|
sl@0
|
516 |
(((first)<<10UL)+(second)-UTF_SURROGATE_OFFSET)
|
|
sl@0
|
517 |
|
|
sl@0
|
518 |
/** @deprecated ICU 2.4. Renamed to U16_LEAD, see utf_old.h. */
|
|
sl@0
|
519 |
#define UTF_FIRST_SURROGATE(supplementary) (UChar)(((supplementary)>>10)+0xd7c0)
|
|
sl@0
|
520 |
|
|
sl@0
|
521 |
/** @deprecated ICU 2.4. Renamed to U16_TRAIL, see utf_old.h. */
|
|
sl@0
|
522 |
#define UTF_SECOND_SURROGATE(supplementary) (UChar)(((supplementary)&0x3ff)|0xdc00)
|
|
sl@0
|
523 |
|
|
sl@0
|
524 |
/** @deprecated ICU 2.4. Renamed to U16_LEAD, see utf_old.h. */
|
|
sl@0
|
525 |
#define UTF16_LEAD(supplementary) UTF_FIRST_SURROGATE(supplementary)
|
|
sl@0
|
526 |
|
|
sl@0
|
527 |
/** @deprecated ICU 2.4. Renamed to U16_TRAIL, see utf_old.h. */
|
|
sl@0
|
528 |
#define UTF16_TRAIL(supplementary) UTF_SECOND_SURROGATE(supplementary)
|
|
sl@0
|
529 |
|
|
sl@0
|
530 |
/** @deprecated ICU 2.4. Renamed to U16_IS_SINGLE, see utf_old.h. */
|
|
sl@0
|
531 |
#define UTF16_IS_SINGLE(uchar) !UTF_IS_SURROGATE(uchar)
|
|
sl@0
|
532 |
|
|
sl@0
|
533 |
/** @deprecated ICU 2.4. Renamed to U16_IS_LEAD, see utf_old.h. */
|
|
sl@0
|
534 |
#define UTF16_IS_LEAD(uchar) UTF_IS_FIRST_SURROGATE(uchar)
|
|
sl@0
|
535 |
|
|
sl@0
|
536 |
/** @deprecated ICU 2.4. Renamed to U16_IS_TRAIL, see utf_old.h. */
|
|
sl@0
|
537 |
#define UTF16_IS_TRAIL(uchar) UTF_IS_SECOND_SURROGATE(uchar)
|
|
sl@0
|
538 |
|
|
sl@0
|
539 |
/** Does this scalar Unicode value need multiple code units for storage? @deprecated ICU 2.4. Use U16_LENGTH or test ((uint32_t)(c)>0xffff) instead, see utf_old.h. */
|
|
sl@0
|
540 |
#define UTF16_NEED_MULTIPLE_UCHAR(c) ((uint32_t)(c)>0xffff)
|
|
sl@0
|
541 |
|
|
sl@0
|
542 |
/** @deprecated ICU 2.4. Renamed to U16_LENGTH, see utf_old.h. */
|
|
sl@0
|
543 |
#define UTF16_CHAR_LENGTH(c) ((uint32_t)(c)<=0xffff ? 1 : 2)
|
|
sl@0
|
544 |
|
|
sl@0
|
545 |
/** @deprecated ICU 2.4. Renamed to U16_MAX_LENGTH, see utf_old.h. */
|
|
sl@0
|
546 |
#define UTF16_MAX_CHAR_LENGTH 2
|
|
sl@0
|
547 |
|
|
sl@0
|
548 |
/** Average number of code units compared to UTF-16. @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
549 |
#define UTF16_ARRAY_SIZE(size) (size)
|
|
sl@0
|
550 |
|
|
sl@0
|
551 |
/**
|
|
sl@0
|
552 |
* Get a single code point from an offset that points to any
|
|
sl@0
|
553 |
* of the code units that belong to that code point.
|
|
sl@0
|
554 |
* Assume 0<=i<length.
|
|
sl@0
|
555 |
*
|
|
sl@0
|
556 |
* This could be used for iteration together with
|
|
sl@0
|
557 |
* UTF16_CHAR_LENGTH() and UTF_IS_ERROR(),
|
|
sl@0
|
558 |
* but the use of UTF16_NEXT_CHAR[_UNSAFE]() and
|
|
sl@0
|
559 |
* UTF16_PREV_CHAR[_UNSAFE]() is more efficient for that.
|
|
sl@0
|
560 |
* @deprecated ICU 2.4. Renamed to U16_GET_UNSAFE, see utf_old.h.
|
|
sl@0
|
561 |
*/
|
|
sl@0
|
562 |
#define UTF16_GET_CHAR_UNSAFE(s, i, c) { \
|
|
sl@0
|
563 |
(c)=(s)[i]; \
|
|
sl@0
|
564 |
if(UTF_IS_SURROGATE(c)) { \
|
|
sl@0
|
565 |
if(UTF_IS_SURROGATE_FIRST(c)) { \
|
|
sl@0
|
566 |
(c)=UTF16_GET_PAIR_VALUE((c), (s)[(i)+1]); \
|
|
sl@0
|
567 |
} else { \
|
|
sl@0
|
568 |
(c)=UTF16_GET_PAIR_VALUE((s)[(i)-1], (c)); \
|
|
sl@0
|
569 |
} \
|
|
sl@0
|
570 |
} \
|
|
sl@0
|
571 |
}
|
|
sl@0
|
572 |
|
|
sl@0
|
573 |
/** @deprecated ICU 2.4. Use U16_GET instead, see utf_old.h. */
|
|
sl@0
|
574 |
#define UTF16_GET_CHAR_SAFE(s, start, i, length, c, strict) { \
|
|
sl@0
|
575 |
(c)=(s)[i]; \
|
|
sl@0
|
576 |
if(UTF_IS_SURROGATE(c)) { \
|
|
sl@0
|
577 |
uint16_t __c2; \
|
|
sl@0
|
578 |
if(UTF_IS_SURROGATE_FIRST(c)) { \
|
|
sl@0
|
579 |
if((i)+1<(length) && UTF_IS_SECOND_SURROGATE(__c2=(s)[(i)+1])) { \
|
|
sl@0
|
580 |
(c)=UTF16_GET_PAIR_VALUE((c), __c2); \
|
|
sl@0
|
581 |
/* strict: ((c)&0xfffe)==0xfffe is caught by UTF_IS_ERROR() and UTF_IS_UNICODE_CHAR() */ \
|
|
sl@0
|
582 |
} else if(strict) {\
|
|
sl@0
|
583 |
/* unmatched first surrogate */ \
|
|
sl@0
|
584 |
(c)=UTF_ERROR_VALUE; \
|
|
sl@0
|
585 |
} \
|
|
sl@0
|
586 |
} else { \
|
|
sl@0
|
587 |
if((i)-1>=(start) && UTF_IS_FIRST_SURROGATE(__c2=(s)[(i)-1])) { \
|
|
sl@0
|
588 |
(c)=UTF16_GET_PAIR_VALUE(__c2, (c)); \
|
|
sl@0
|
589 |
/* strict: ((c)&0xfffe)==0xfffe is caught by UTF_IS_ERROR() and UTF_IS_UNICODE_CHAR() */ \
|
|
sl@0
|
590 |
} else if(strict) {\
|
|
sl@0
|
591 |
/* unmatched second surrogate */ \
|
|
sl@0
|
592 |
(c)=UTF_ERROR_VALUE; \
|
|
sl@0
|
593 |
} \
|
|
sl@0
|
594 |
} \
|
|
sl@0
|
595 |
} else if((strict) && !UTF_IS_UNICODE_CHAR(c)) { \
|
|
sl@0
|
596 |
(c)=UTF_ERROR_VALUE; \
|
|
sl@0
|
597 |
} \
|
|
sl@0
|
598 |
}
|
|
sl@0
|
599 |
|
|
sl@0
|
600 |
/** @deprecated ICU 2.4. Renamed to U16_NEXT_UNSAFE, see utf_old.h. */
|
|
sl@0
|
601 |
#define UTF16_NEXT_CHAR_UNSAFE(s, i, c) { \
|
|
sl@0
|
602 |
(c)=(s)[(i)++]; \
|
|
sl@0
|
603 |
if(UTF_IS_FIRST_SURROGATE(c)) { \
|
|
sl@0
|
604 |
(c)=UTF16_GET_PAIR_VALUE((c), (s)[(i)++]); \
|
|
sl@0
|
605 |
} \
|
|
sl@0
|
606 |
}
|
|
sl@0
|
607 |
|
|
sl@0
|
608 |
/** @deprecated ICU 2.4. Renamed to U16_APPEND_UNSAFE, see utf_old.h. */
|
|
sl@0
|
609 |
#define UTF16_APPEND_CHAR_UNSAFE(s, i, c) { \
|
|
sl@0
|
610 |
if((uint32_t)(c)<=0xffff) { \
|
|
sl@0
|
611 |
(s)[(i)++]=(uint16_t)(c); \
|
|
sl@0
|
612 |
} else { \
|
|
sl@0
|
613 |
(s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \
|
|
sl@0
|
614 |
(s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \
|
|
sl@0
|
615 |
} \
|
|
sl@0
|
616 |
}
|
|
sl@0
|
617 |
|
|
sl@0
|
618 |
/** @deprecated ICU 2.4. Renamed to U16_FWD_1_UNSAFE, see utf_old.h. */
|
|
sl@0
|
619 |
#define UTF16_FWD_1_UNSAFE(s, i) { \
|
|
sl@0
|
620 |
if(UTF_IS_FIRST_SURROGATE((s)[(i)++])) { \
|
|
sl@0
|
621 |
++(i); \
|
|
sl@0
|
622 |
} \
|
|
sl@0
|
623 |
}
|
|
sl@0
|
624 |
|
|
sl@0
|
625 |
/** @deprecated ICU 2.4. Renamed to U16_FWD_N_UNSAFE, see utf_old.h. */
|
|
sl@0
|
626 |
#define UTF16_FWD_N_UNSAFE(s, i, n) { \
|
|
sl@0
|
627 |
int32_t __N=(n); \
|
|
sl@0
|
628 |
while(__N>0) { \
|
|
sl@0
|
629 |
UTF16_FWD_1_UNSAFE(s, i); \
|
|
sl@0
|
630 |
--__N; \
|
|
sl@0
|
631 |
} \
|
|
sl@0
|
632 |
}
|
|
sl@0
|
633 |
|
|
sl@0
|
634 |
/** @deprecated ICU 2.4. Renamed to U16_SET_CP_START_UNSAFE, see utf_old.h. */
|
|
sl@0
|
635 |
#define UTF16_SET_CHAR_START_UNSAFE(s, i) { \
|
|
sl@0
|
636 |
if(UTF_IS_SECOND_SURROGATE((s)[i])) { \
|
|
sl@0
|
637 |
--(i); \
|
|
sl@0
|
638 |
} \
|
|
sl@0
|
639 |
}
|
|
sl@0
|
640 |
|
|
sl@0
|
641 |
/** @deprecated ICU 2.4. Use U16_NEXT instead, see utf_old.h. */
|
|
sl@0
|
642 |
#define UTF16_NEXT_CHAR_SAFE(s, i, length, c, strict) { \
|
|
sl@0
|
643 |
(c)=(s)[(i)++]; \
|
|
sl@0
|
644 |
if(UTF_IS_FIRST_SURROGATE(c)) { \
|
|
sl@0
|
645 |
uint16_t __c2; \
|
|
sl@0
|
646 |
if((i)<(length) && UTF_IS_SECOND_SURROGATE(__c2=(s)[(i)])) { \
|
|
sl@0
|
647 |
++(i); \
|
|
sl@0
|
648 |
(c)=UTF16_GET_PAIR_VALUE((c), __c2); \
|
|
sl@0
|
649 |
/* strict: ((c)&0xfffe)==0xfffe is caught by UTF_IS_ERROR() and UTF_IS_UNICODE_CHAR() */ \
|
|
sl@0
|
650 |
} else if(strict) {\
|
|
sl@0
|
651 |
/* unmatched first surrogate */ \
|
|
sl@0
|
652 |
(c)=UTF_ERROR_VALUE; \
|
|
sl@0
|
653 |
} \
|
|
sl@0
|
654 |
} else if((strict) && !UTF_IS_UNICODE_CHAR(c)) { \
|
|
sl@0
|
655 |
/* unmatched second surrogate or other non-character */ \
|
|
sl@0
|
656 |
(c)=UTF_ERROR_VALUE; \
|
|
sl@0
|
657 |
} \
|
|
sl@0
|
658 |
}
|
|
sl@0
|
659 |
|
|
sl@0
|
660 |
/** @deprecated ICU 2.4. Use U16_APPEND instead, see utf_old.h. */
|
|
sl@0
|
661 |
#define UTF16_APPEND_CHAR_SAFE(s, i, length, c) { \
|
|
sl@0
|
662 |
if((uint32_t)(c)<=0xffff) { \
|
|
sl@0
|
663 |
(s)[(i)++]=(uint16_t)(c); \
|
|
sl@0
|
664 |
} else if((uint32_t)(c)<=0x10ffff) { \
|
|
sl@0
|
665 |
if((i)+1<(length)) { \
|
|
sl@0
|
666 |
(s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \
|
|
sl@0
|
667 |
(s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \
|
|
sl@0
|
668 |
} else /* not enough space */ { \
|
|
sl@0
|
669 |
(s)[(i)++]=UTF_ERROR_VALUE; \
|
|
sl@0
|
670 |
} \
|
|
sl@0
|
671 |
} else /* c>0x10ffff, write error value */ { \
|
|
sl@0
|
672 |
(s)[(i)++]=UTF_ERROR_VALUE; \
|
|
sl@0
|
673 |
} \
|
|
sl@0
|
674 |
}
|
|
sl@0
|
675 |
|
|
sl@0
|
676 |
/** @deprecated ICU 2.4. Renamed to U16_FWD_1, see utf_old.h. */
|
|
sl@0
|
677 |
#define UTF16_FWD_1_SAFE(s, i, length) U16_FWD_1(s, i, length)
|
|
sl@0
|
678 |
|
|
sl@0
|
679 |
/** @deprecated ICU 2.4. Renamed to U16_FWD_N, see utf_old.h. */
|
|
sl@0
|
680 |
#define UTF16_FWD_N_SAFE(s, i, length, n) U16_FWD_N(s, i, length, n)
|
|
sl@0
|
681 |
|
|
sl@0
|
682 |
/** @deprecated ICU 2.4. Renamed to U16_SET_CP_START, see utf_old.h. */
|
|
sl@0
|
683 |
#define UTF16_SET_CHAR_START_SAFE(s, start, i) U16_SET_CP_START(s, start, i)
|
|
sl@0
|
684 |
|
|
sl@0
|
685 |
/** @deprecated ICU 2.4. Renamed to U16_PREV_UNSAFE, see utf_old.h. */
|
|
sl@0
|
686 |
#define UTF16_PREV_CHAR_UNSAFE(s, i, c) { \
|
|
sl@0
|
687 |
(c)=(s)[--(i)]; \
|
|
sl@0
|
688 |
if(UTF_IS_SECOND_SURROGATE(c)) { \
|
|
sl@0
|
689 |
(c)=UTF16_GET_PAIR_VALUE((s)[--(i)], (c)); \
|
|
sl@0
|
690 |
} \
|
|
sl@0
|
691 |
}
|
|
sl@0
|
692 |
|
|
sl@0
|
693 |
/** @deprecated ICU 2.4. Renamed to U16_BACK_1_UNSAFE, see utf_old.h. */
|
|
sl@0
|
694 |
#define UTF16_BACK_1_UNSAFE(s, i) { \
|
|
sl@0
|
695 |
if(UTF_IS_SECOND_SURROGATE((s)[--(i)])) { \
|
|
sl@0
|
696 |
--(i); \
|
|
sl@0
|
697 |
} \
|
|
sl@0
|
698 |
}
|
|
sl@0
|
699 |
|
|
sl@0
|
700 |
/** @deprecated ICU 2.4. Renamed to U16_BACK_N_UNSAFE, see utf_old.h. */
|
|
sl@0
|
701 |
#define UTF16_BACK_N_UNSAFE(s, i, n) { \
|
|
sl@0
|
702 |
int32_t __N=(n); \
|
|
sl@0
|
703 |
while(__N>0) { \
|
|
sl@0
|
704 |
UTF16_BACK_1_UNSAFE(s, i); \
|
|
sl@0
|
705 |
--__N; \
|
|
sl@0
|
706 |
} \
|
|
sl@0
|
707 |
}
|
|
sl@0
|
708 |
|
|
sl@0
|
709 |
/** @deprecated ICU 2.4. Renamed to U16_SET_CP_LIMIT_UNSAFE, see utf_old.h. */
|
|
sl@0
|
710 |
#define UTF16_SET_CHAR_LIMIT_UNSAFE(s, i) { \
|
|
sl@0
|
711 |
if(UTF_IS_FIRST_SURROGATE((s)[(i)-1])) { \
|
|
sl@0
|
712 |
++(i); \
|
|
sl@0
|
713 |
} \
|
|
sl@0
|
714 |
}
|
|
sl@0
|
715 |
|
|
sl@0
|
716 |
/** @deprecated ICU 2.4. Use U16_PREV instead, see utf_old.h. */
|
|
sl@0
|
717 |
#define UTF16_PREV_CHAR_SAFE(s, start, i, c, strict) { \
|
|
sl@0
|
718 |
(c)=(s)[--(i)]; \
|
|
sl@0
|
719 |
if(UTF_IS_SECOND_SURROGATE(c)) { \
|
|
sl@0
|
720 |
uint16_t __c2; \
|
|
sl@0
|
721 |
if((i)>(start) && UTF_IS_FIRST_SURROGATE(__c2=(s)[(i)-1])) { \
|
|
sl@0
|
722 |
--(i); \
|
|
sl@0
|
723 |
(c)=UTF16_GET_PAIR_VALUE(__c2, (c)); \
|
|
sl@0
|
724 |
/* strict: ((c)&0xfffe)==0xfffe is caught by UTF_IS_ERROR() and UTF_IS_UNICODE_CHAR() */ \
|
|
sl@0
|
725 |
} else if(strict) {\
|
|
sl@0
|
726 |
/* unmatched second surrogate */ \
|
|
sl@0
|
727 |
(c)=UTF_ERROR_VALUE; \
|
|
sl@0
|
728 |
} \
|
|
sl@0
|
729 |
} else if((strict) && !UTF_IS_UNICODE_CHAR(c)) { \
|
|
sl@0
|
730 |
/* unmatched first surrogate or other non-character */ \
|
|
sl@0
|
731 |
(c)=UTF_ERROR_VALUE; \
|
|
sl@0
|
732 |
} \
|
|
sl@0
|
733 |
}
|
|
sl@0
|
734 |
|
|
sl@0
|
735 |
/** @deprecated ICU 2.4. Renamed to U16_BACK_1, see utf_old.h. */
|
|
sl@0
|
736 |
#define UTF16_BACK_1_SAFE(s, start, i) U16_BACK_1(s, start, i)
|
|
sl@0
|
737 |
|
|
sl@0
|
738 |
/** @deprecated ICU 2.4. Renamed to U16_BACK_N, see utf_old.h. */
|
|
sl@0
|
739 |
#define UTF16_BACK_N_SAFE(s, start, i, n) U16_BACK_N(s, start, i, n)
|
|
sl@0
|
740 |
|
|
sl@0
|
741 |
/** @deprecated ICU 2.4. Renamed to U16_SET_CP_LIMIT, see utf_old.h. */
|
|
sl@0
|
742 |
#define UTF16_SET_CHAR_LIMIT_SAFE(s, start, i, length) U16_SET_CP_LIMIT(s, start, i, length)
|
|
sl@0
|
743 |
|
|
sl@0
|
744 |
/* Formerly utf32.h --------------------------------------------------------- */
|
|
sl@0
|
745 |
|
|
sl@0
|
746 |
/*
|
|
sl@0
|
747 |
* Old documentation:
|
|
sl@0
|
748 |
*
|
|
sl@0
|
749 |
* This file defines macros to deal with UTF-32 code units and code points.
|
|
sl@0
|
750 |
* Signatures and semantics are the same as for the similarly named macros
|
|
sl@0
|
751 |
* in utf16.h.
|
|
sl@0
|
752 |
* utf32.h is included by utf.h after unicode/umachine.h</p>
|
|
sl@0
|
753 |
* and some common definitions.
|
|
sl@0
|
754 |
* <p><b>Usage:</b> ICU coding guidelines for if() statements should be followed when using these macros.
|
|
sl@0
|
755 |
* Compound statements (curly braces {}) must be used for if-else-while...
|
|
sl@0
|
756 |
* bodies and all macro statements should be terminated with semicolon.</p>
|
|
sl@0
|
757 |
*/
|
|
sl@0
|
758 |
|
|
sl@0
|
759 |
/* internal definitions ----------------------------------------------------- */
|
|
sl@0
|
760 |
|
|
sl@0
|
761 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
762 |
#define UTF32_IS_SAFE(c, strict) \
|
|
sl@0
|
763 |
(!(strict) ? \
|
|
sl@0
|
764 |
(uint32_t)(c)<=0x10ffff : \
|
|
sl@0
|
765 |
UTF_IS_UNICODE_CHAR(c))
|
|
sl@0
|
766 |
|
|
sl@0
|
767 |
/*
|
|
sl@0
|
768 |
* For the semantics of all of these macros, see utf16.h.
|
|
sl@0
|
769 |
* The UTF-32 versions are trivial because any code point is
|
|
sl@0
|
770 |
* encoded using exactly one code unit.
|
|
sl@0
|
771 |
*/
|
|
sl@0
|
772 |
|
|
sl@0
|
773 |
/* single-code point definitions -------------------------------------------- */
|
|
sl@0
|
774 |
|
|
sl@0
|
775 |
/* classes of code unit values */
|
|
sl@0
|
776 |
|
|
sl@0
|
777 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
778 |
#define UTF32_IS_SINGLE(uchar) 1
|
|
sl@0
|
779 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
780 |
#define UTF32_IS_LEAD(uchar) 0
|
|
sl@0
|
781 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
782 |
#define UTF32_IS_TRAIL(uchar) 0
|
|
sl@0
|
783 |
|
|
sl@0
|
784 |
/* number of code units per code point */
|
|
sl@0
|
785 |
|
|
sl@0
|
786 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
787 |
#define UTF32_NEED_MULTIPLE_UCHAR(c) 0
|
|
sl@0
|
788 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
789 |
#define UTF32_CHAR_LENGTH(c) 1
|
|
sl@0
|
790 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
791 |
#define UTF32_MAX_CHAR_LENGTH 1
|
|
sl@0
|
792 |
|
|
sl@0
|
793 |
/* average number of code units compared to UTF-16 */
|
|
sl@0
|
794 |
|
|
sl@0
|
795 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
796 |
#define UTF32_ARRAY_SIZE(size) (size)
|
|
sl@0
|
797 |
|
|
sl@0
|
798 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
799 |
#define UTF32_GET_CHAR_UNSAFE(s, i, c) { \
|
|
sl@0
|
800 |
(c)=(s)[i]; \
|
|
sl@0
|
801 |
}
|
|
sl@0
|
802 |
|
|
sl@0
|
803 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
804 |
#define UTF32_GET_CHAR_SAFE(s, start, i, length, c, strict) { \
|
|
sl@0
|
805 |
(c)=(s)[i]; \
|
|
sl@0
|
806 |
if(!UTF32_IS_SAFE(c, strict)) { \
|
|
sl@0
|
807 |
(c)=UTF_ERROR_VALUE; \
|
|
sl@0
|
808 |
} \
|
|
sl@0
|
809 |
}
|
|
sl@0
|
810 |
|
|
sl@0
|
811 |
/* definitions with forward iteration --------------------------------------- */
|
|
sl@0
|
812 |
|
|
sl@0
|
813 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
814 |
#define UTF32_NEXT_CHAR_UNSAFE(s, i, c) { \
|
|
sl@0
|
815 |
(c)=(s)[(i)++]; \
|
|
sl@0
|
816 |
}
|
|
sl@0
|
817 |
|
|
sl@0
|
818 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
819 |
#define UTF32_APPEND_CHAR_UNSAFE(s, i, c) { \
|
|
sl@0
|
820 |
(s)[(i)++]=(c); \
|
|
sl@0
|
821 |
}
|
|
sl@0
|
822 |
|
|
sl@0
|
823 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
824 |
#define UTF32_FWD_1_UNSAFE(s, i) { \
|
|
sl@0
|
825 |
++(i); \
|
|
sl@0
|
826 |
}
|
|
sl@0
|
827 |
|
|
sl@0
|
828 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
829 |
#define UTF32_FWD_N_UNSAFE(s, i, n) { \
|
|
sl@0
|
830 |
(i)+=(n); \
|
|
sl@0
|
831 |
}
|
|
sl@0
|
832 |
|
|
sl@0
|
833 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
834 |
#define UTF32_SET_CHAR_START_UNSAFE(s, i) { \
|
|
sl@0
|
835 |
}
|
|
sl@0
|
836 |
|
|
sl@0
|
837 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
838 |
#define UTF32_NEXT_CHAR_SAFE(s, i, length, c, strict) { \
|
|
sl@0
|
839 |
(c)=(s)[(i)++]; \
|
|
sl@0
|
840 |
if(!UTF32_IS_SAFE(c, strict)) { \
|
|
sl@0
|
841 |
(c)=UTF_ERROR_VALUE; \
|
|
sl@0
|
842 |
} \
|
|
sl@0
|
843 |
}
|
|
sl@0
|
844 |
|
|
sl@0
|
845 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
846 |
#define UTF32_APPEND_CHAR_SAFE(s, i, length, c) { \
|
|
sl@0
|
847 |
if((uint32_t)(c)<=0x10ffff) { \
|
|
sl@0
|
848 |
(s)[(i)++]=(c); \
|
|
sl@0
|
849 |
} else /* c>0x10ffff, write 0xfffd */ { \
|
|
sl@0
|
850 |
(s)[(i)++]=0xfffd; \
|
|
sl@0
|
851 |
} \
|
|
sl@0
|
852 |
}
|
|
sl@0
|
853 |
|
|
sl@0
|
854 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
855 |
#define UTF32_FWD_1_SAFE(s, i, length) { \
|
|
sl@0
|
856 |
++(i); \
|
|
sl@0
|
857 |
}
|
|
sl@0
|
858 |
|
|
sl@0
|
859 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
860 |
#define UTF32_FWD_N_SAFE(s, i, length, n) { \
|
|
sl@0
|
861 |
if(((i)+=(n))>(length)) { \
|
|
sl@0
|
862 |
(i)=(length); \
|
|
sl@0
|
863 |
} \
|
|
sl@0
|
864 |
}
|
|
sl@0
|
865 |
|
|
sl@0
|
866 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
867 |
#define UTF32_SET_CHAR_START_SAFE(s, start, i) { \
|
|
sl@0
|
868 |
}
|
|
sl@0
|
869 |
|
|
sl@0
|
870 |
/* definitions with backward iteration -------------------------------------- */
|
|
sl@0
|
871 |
|
|
sl@0
|
872 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
873 |
#define UTF32_PREV_CHAR_UNSAFE(s, i, c) { \
|
|
sl@0
|
874 |
(c)=(s)[--(i)]; \
|
|
sl@0
|
875 |
}
|
|
sl@0
|
876 |
|
|
sl@0
|
877 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
878 |
#define UTF32_BACK_1_UNSAFE(s, i) { \
|
|
sl@0
|
879 |
--(i); \
|
|
sl@0
|
880 |
}
|
|
sl@0
|
881 |
|
|
sl@0
|
882 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
883 |
#define UTF32_BACK_N_UNSAFE(s, i, n) { \
|
|
sl@0
|
884 |
(i)-=(n); \
|
|
sl@0
|
885 |
}
|
|
sl@0
|
886 |
|
|
sl@0
|
887 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
888 |
#define UTF32_SET_CHAR_LIMIT_UNSAFE(s, i) { \
|
|
sl@0
|
889 |
}
|
|
sl@0
|
890 |
|
|
sl@0
|
891 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
892 |
#define UTF32_PREV_CHAR_SAFE(s, start, i, c, strict) { \
|
|
sl@0
|
893 |
(c)=(s)[--(i)]; \
|
|
sl@0
|
894 |
if(!UTF32_IS_SAFE(c, strict)) { \
|
|
sl@0
|
895 |
(c)=UTF_ERROR_VALUE; \
|
|
sl@0
|
896 |
} \
|
|
sl@0
|
897 |
}
|
|
sl@0
|
898 |
|
|
sl@0
|
899 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
900 |
#define UTF32_BACK_1_SAFE(s, start, i) { \
|
|
sl@0
|
901 |
--(i); \
|
|
sl@0
|
902 |
}
|
|
sl@0
|
903 |
|
|
sl@0
|
904 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
905 |
#define UTF32_BACK_N_SAFE(s, start, i, n) { \
|
|
sl@0
|
906 |
(i)-=(n); \
|
|
sl@0
|
907 |
if((i)<(start)) { \
|
|
sl@0
|
908 |
(i)=(start); \
|
|
sl@0
|
909 |
} \
|
|
sl@0
|
910 |
}
|
|
sl@0
|
911 |
|
|
sl@0
|
912 |
/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */
|
|
sl@0
|
913 |
#define UTF32_SET_CHAR_LIMIT_SAFE(s, i, length) { \
|
|
sl@0
|
914 |
}
|
|
sl@0
|
915 |
|
|
sl@0
|
916 |
/* Formerly utf.h, part 2 --------------------------------------------------- */
|
|
sl@0
|
917 |
|
|
sl@0
|
918 |
/**
|
|
sl@0
|
919 |
* Estimate the number of code units for a string based on the number of UTF-16 code units.
|
|
sl@0
|
920 |
*
|
|
sl@0
|
921 |
* @deprecated ICU 2.4. Obsolete, see utf_old.h.
|
|
sl@0
|
922 |
*/
|
|
sl@0
|
923 |
#define UTF_ARRAY_SIZE(size) UTF16_ARRAY_SIZE(size)
|
|
sl@0
|
924 |
|
|
sl@0
|
925 |
/** @deprecated ICU 2.4. Renamed to U16_GET_UNSAFE, see utf_old.h. */
|
|
sl@0
|
926 |
#define UTF_GET_CHAR_UNSAFE(s, i, c) UTF16_GET_CHAR_UNSAFE(s, i, c)
|
|
sl@0
|
927 |
|
|
sl@0
|
928 |
/** @deprecated ICU 2.4. Use U16_GET instead, see utf_old.h. */
|
|
sl@0
|
929 |
#define UTF_GET_CHAR_SAFE(s, start, i, length, c, strict) UTF16_GET_CHAR_SAFE(s, start, i, length, c, strict)
|
|
sl@0
|
930 |
|
|
sl@0
|
931 |
|
|
sl@0
|
932 |
/** @deprecated ICU 2.4. Renamed to U16_NEXT_UNSAFE, see utf_old.h. */
|
|
sl@0
|
933 |
#define UTF_NEXT_CHAR_UNSAFE(s, i, c) UTF16_NEXT_CHAR_UNSAFE(s, i, c)
|
|
sl@0
|
934 |
|
|
sl@0
|
935 |
/** @deprecated ICU 2.4. Use U16_NEXT instead, see utf_old.h. */
|
|
sl@0
|
936 |
#define UTF_NEXT_CHAR_SAFE(s, i, length, c, strict) UTF16_NEXT_CHAR_SAFE(s, i, length, c, strict)
|
|
sl@0
|
937 |
|
|
sl@0
|
938 |
|
|
sl@0
|
939 |
/** @deprecated ICU 2.4. Renamed to U16_APPEND_UNSAFE, see utf_old.h. */
|
|
sl@0
|
940 |
#define UTF_APPEND_CHAR_UNSAFE(s, i, c) UTF16_APPEND_CHAR_UNSAFE(s, i, c)
|
|
sl@0
|
941 |
|
|
sl@0
|
942 |
/** @deprecated ICU 2.4. Use U16_APPEND instead, see utf_old.h. */
|
|
sl@0
|
943 |
#define UTF_APPEND_CHAR_SAFE(s, i, length, c) UTF16_APPEND_CHAR_SAFE(s, i, length, c)
|
|
sl@0
|
944 |
|
|
sl@0
|
945 |
|
|
sl@0
|
946 |
/** @deprecated ICU 2.4. Renamed to U16_FWD_1_UNSAFE, see utf_old.h. */
|
|
sl@0
|
947 |
#define UTF_FWD_1_UNSAFE(s, i) UTF16_FWD_1_UNSAFE(s, i)
|
|
sl@0
|
948 |
|
|
sl@0
|
949 |
/** @deprecated ICU 2.4. Renamed to U16_FWD_1, see utf_old.h. */
|
|
sl@0
|
950 |
#define UTF_FWD_1_SAFE(s, i, length) UTF16_FWD_1_SAFE(s, i, length)
|
|
sl@0
|
951 |
|
|
sl@0
|
952 |
|
|
sl@0
|
953 |
/** @deprecated ICU 2.4. Renamed to U16_FWD_N_UNSAFE, see utf_old.h. */
|
|
sl@0
|
954 |
#define UTF_FWD_N_UNSAFE(s, i, n) UTF16_FWD_N_UNSAFE(s, i, n)
|
|
sl@0
|
955 |
|
|
sl@0
|
956 |
/** @deprecated ICU 2.4. Renamed to U16_FWD_N, see utf_old.h. */
|
|
sl@0
|
957 |
#define UTF_FWD_N_SAFE(s, i, length, n) UTF16_FWD_N_SAFE(s, i, length, n)
|
|
sl@0
|
958 |
|
|
sl@0
|
959 |
|
|
sl@0
|
960 |
/** @deprecated ICU 2.4. Renamed to U16_SET_CP_START_UNSAFE, see utf_old.h. */
|
|
sl@0
|
961 |
#define UTF_SET_CHAR_START_UNSAFE(s, i) UTF16_SET_CHAR_START_UNSAFE(s, i)
|
|
sl@0
|
962 |
|
|
sl@0
|
963 |
/** @deprecated ICU 2.4. Renamed to U16_SET_CP_START, see utf_old.h. */
|
|
sl@0
|
964 |
#define UTF_SET_CHAR_START_SAFE(s, start, i) UTF16_SET_CHAR_START_SAFE(s, start, i)
|
|
sl@0
|
965 |
|
|
sl@0
|
966 |
|
|
sl@0
|
967 |
/** @deprecated ICU 2.4. Renamed to U16_PREV_UNSAFE, see utf_old.h. */
|
|
sl@0
|
968 |
#define UTF_PREV_CHAR_UNSAFE(s, i, c) UTF16_PREV_CHAR_UNSAFE(s, i, c)
|
|
sl@0
|
969 |
|
|
sl@0
|
970 |
/** @deprecated ICU 2.4. Use U16_PREV instead, see utf_old.h. */
|
|
sl@0
|
971 |
#define UTF_PREV_CHAR_SAFE(s, start, i, c, strict) UTF16_PREV_CHAR_SAFE(s, start, i, c, strict)
|
|
sl@0
|
972 |
|
|
sl@0
|
973 |
|
|
sl@0
|
974 |
/** @deprecated ICU 2.4. Renamed to U16_BACK_1_UNSAFE, see utf_old.h. */
|
|
sl@0
|
975 |
#define UTF_BACK_1_UNSAFE(s, i) UTF16_BACK_1_UNSAFE(s, i)
|
|
sl@0
|
976 |
|
|
sl@0
|
977 |
/** @deprecated ICU 2.4. Renamed to U16_BACK_1, see utf_old.h. */
|
|
sl@0
|
978 |
#define UTF_BACK_1_SAFE(s, start, i) UTF16_BACK_1_SAFE(s, start, i)
|
|
sl@0
|
979 |
|
|
sl@0
|
980 |
|
|
sl@0
|
981 |
/** @deprecated ICU 2.4. Renamed to U16_BACK_N_UNSAFE, see utf_old.h. */
|
|
sl@0
|
982 |
#define UTF_BACK_N_UNSAFE(s, i, n) UTF16_BACK_N_UNSAFE(s, i, n)
|
|
sl@0
|
983 |
|
|
sl@0
|
984 |
/** @deprecated ICU 2.4. Renamed to U16_BACK_N, see utf_old.h. */
|
|
sl@0
|
985 |
#define UTF_BACK_N_SAFE(s, start, i, n) UTF16_BACK_N_SAFE(s, start, i, n)
|
|
sl@0
|
986 |
|
|
sl@0
|
987 |
|
|
sl@0
|
988 |
/** @deprecated ICU 2.4. Renamed to U16_SET_CP_LIMIT_UNSAFE, see utf_old.h. */
|
|
sl@0
|
989 |
#define UTF_SET_CHAR_LIMIT_UNSAFE(s, i) UTF16_SET_CHAR_LIMIT_UNSAFE(s, i)
|
|
sl@0
|
990 |
|
|
sl@0
|
991 |
/** @deprecated ICU 2.4. Renamed to U16_SET_CP_LIMIT, see utf_old.h. */
|
|
sl@0
|
992 |
#define UTF_SET_CHAR_LIMIT_SAFE(s, start, i, length) UTF16_SET_CHAR_LIMIT_SAFE(s, start, i, length)
|
|
sl@0
|
993 |
|
|
sl@0
|
994 |
/* Define default macros (UTF-16 "safe") ------------------------------------ */
|
|
sl@0
|
995 |
|
|
sl@0
|
996 |
/**
|
|
sl@0
|
997 |
* Does this code unit alone encode a code point (BMP, not a surrogate)?
|
|
sl@0
|
998 |
* Same as UTF16_IS_SINGLE.
|
|
sl@0
|
999 |
* @deprecated ICU 2.4. Renamed to U_IS_SINGLE and U16_IS_SINGLE, see utf_old.h.
|
|
sl@0
|
1000 |
*/
|
|
sl@0
|
1001 |
#define UTF_IS_SINGLE(uchar) U16_IS_SINGLE(uchar)
|
|
sl@0
|
1002 |
|
|
sl@0
|
1003 |
/**
|
|
sl@0
|
1004 |
* Is this code unit the first one of several (a lead surrogate)?
|
|
sl@0
|
1005 |
* Same as UTF16_IS_LEAD.
|
|
sl@0
|
1006 |
* @deprecated ICU 2.4. Renamed to U_IS_LEAD and U16_IS_LEAD, see utf_old.h.
|
|
sl@0
|
1007 |
*/
|
|
sl@0
|
1008 |
#define UTF_IS_LEAD(uchar) U16_IS_LEAD(uchar)
|
|
sl@0
|
1009 |
|
|
sl@0
|
1010 |
/**
|
|
sl@0
|
1011 |
* Is this code unit one of several but not the first one (a trail surrogate)?
|
|
sl@0
|
1012 |
* Same as UTF16_IS_TRAIL.
|
|
sl@0
|
1013 |
* @deprecated ICU 2.4. Renamed to U_IS_TRAIL and U16_IS_TRAIL, see utf_old.h.
|
|
sl@0
|
1014 |
*/
|
|
sl@0
|
1015 |
#define UTF_IS_TRAIL(uchar) U16_IS_TRAIL(uchar)
|
|
sl@0
|
1016 |
|
|
sl@0
|
1017 |
/**
|
|
sl@0
|
1018 |
* Does this code point require multiple code units (is it a supplementary code point)?
|
|
sl@0
|
1019 |
* Same as UTF16_NEED_MULTIPLE_UCHAR.
|
|
sl@0
|
1020 |
* @deprecated ICU 2.4. Use U16_LENGTH or test ((uint32_t)(c)>0xffff) instead.
|
|
sl@0
|
1021 |
*/
|
|
sl@0
|
1022 |
#define UTF_NEED_MULTIPLE_UCHAR(c) UTF16_NEED_MULTIPLE_UCHAR(c)
|
|
sl@0
|
1023 |
|
|
sl@0
|
1024 |
/**
|
|
sl@0
|
1025 |
* How many code units are used to encode this code point (1 or 2)?
|
|
sl@0
|
1026 |
* Same as UTF16_CHAR_LENGTH.
|
|
sl@0
|
1027 |
* @deprecated ICU 2.4. Renamed to U16_LENGTH, see utf_old.h.
|
|
sl@0
|
1028 |
*/
|
|
sl@0
|
1029 |
#define UTF_CHAR_LENGTH(c) U16_LENGTH(c)
|
|
sl@0
|
1030 |
|
|
sl@0
|
1031 |
/**
|
|
sl@0
|
1032 |
* How many code units are used at most for any Unicode code point (2)?
|
|
sl@0
|
1033 |
* Same as UTF16_MAX_CHAR_LENGTH.
|
|
sl@0
|
1034 |
* @deprecated ICU 2.4. Renamed to U16_MAX_LENGTH, see utf_old.h.
|
|
sl@0
|
1035 |
*/
|
|
sl@0
|
1036 |
#define UTF_MAX_CHAR_LENGTH U16_MAX_LENGTH
|
|
sl@0
|
1037 |
|
|
sl@0
|
1038 |
/**
|
|
sl@0
|
1039 |
* Set c to the code point that contains the code unit i.
|
|
sl@0
|
1040 |
* i could point to the lead or the trail surrogate for the code point.
|
|
sl@0
|
1041 |
* i is not modified.
|
|
sl@0
|
1042 |
* Same as UTF16_GET_CHAR.
|
|
sl@0
|
1043 |
* \pre 0<=i<length
|
|
sl@0
|
1044 |
*
|
|
sl@0
|
1045 |
* @deprecated ICU 2.4. Renamed to U16_GET, see utf_old.h.
|
|
sl@0
|
1046 |
*/
|
|
sl@0
|
1047 |
#define UTF_GET_CHAR(s, start, i, length, c) U16_GET(s, start, i, length, c)
|
|
sl@0
|
1048 |
|
|
sl@0
|
1049 |
/**
|
|
sl@0
|
1050 |
* Set c to the code point that starts at code unit i
|
|
sl@0
|
1051 |
* and advance i to beyond the code units of this code point (post-increment).
|
|
sl@0
|
1052 |
* i must point to the first code unit of a code point.
|
|
sl@0
|
1053 |
* Otherwise c is set to the trail unit (surrogate) itself.
|
|
sl@0
|
1054 |
* Same as UTF16_NEXT_CHAR.
|
|
sl@0
|
1055 |
* \pre 0<=i<length
|
|
sl@0
|
1056 |
* \post 0<i<=length
|
|
sl@0
|
1057 |
*
|
|
sl@0
|
1058 |
* @deprecated ICU 2.4. Renamed to U16_NEXT, see utf_old.h.
|
|
sl@0
|
1059 |
*/
|
|
sl@0
|
1060 |
#define UTF_NEXT_CHAR(s, i, length, c) U16_NEXT(s, i, length, c)
|
|
sl@0
|
1061 |
|
|
sl@0
|
1062 |
/**
|
|
sl@0
|
1063 |
* Append the code units of code point c to the string at index i
|
|
sl@0
|
1064 |
* and advance i to beyond the new code units (post-increment).
|
|
sl@0
|
1065 |
* The code units beginning at index i will be overwritten.
|
|
sl@0
|
1066 |
* Same as UTF16_APPEND_CHAR.
|
|
sl@0
|
1067 |
* \pre 0<=c<=0x10ffff
|
|
sl@0
|
1068 |
* \pre 0<=i<length
|
|
sl@0
|
1069 |
* \post 0<i<=length
|
|
sl@0
|
1070 |
*
|
|
sl@0
|
1071 |
* @deprecated ICU 2.4. Use U16_APPEND instead, see utf_old.h.
|
|
sl@0
|
1072 |
*/
|
|
sl@0
|
1073 |
#define UTF_APPEND_CHAR(s, i, length, c) UTF16_APPEND_CHAR_SAFE(s, i, length, c)
|
|
sl@0
|
1074 |
|
|
sl@0
|
1075 |
/**
|
|
sl@0
|
1076 |
* Advance i to beyond the code units of the code point that begins at i.
|
|
sl@0
|
1077 |
* I.e., advance i by one code point.
|
|
sl@0
|
1078 |
* Same as UTF16_FWD_1.
|
|
sl@0
|
1079 |
* \pre 0<=i<length
|
|
sl@0
|
1080 |
* \post 0<i<=length
|
|
sl@0
|
1081 |
*
|
|
sl@0
|
1082 |
* @deprecated ICU 2.4. Renamed to U16_FWD_1, see utf_old.h.
|
|
sl@0
|
1083 |
*/
|
|
sl@0
|
1084 |
#define UTF_FWD_1(s, i, length) U16_FWD_1(s, i, length)
|
|
sl@0
|
1085 |
|
|
sl@0
|
1086 |
/**
|
|
sl@0
|
1087 |
* Advance i to beyond the code units of the n code points where the first one begins at i.
|
|
sl@0
|
1088 |
* I.e., advance i by n code points.
|
|
sl@0
|
1089 |
* Same as UT16_FWD_N.
|
|
sl@0
|
1090 |
* \pre 0<=i<length
|
|
sl@0
|
1091 |
* \post 0<i<=length
|
|
sl@0
|
1092 |
*
|
|
sl@0
|
1093 |
* @deprecated ICU 2.4. Renamed to U16_FWD_N, see utf_old.h.
|
|
sl@0
|
1094 |
*/
|
|
sl@0
|
1095 |
#define UTF_FWD_N(s, i, length, n) U16_FWD_N(s, i, length, n)
|
|
sl@0
|
1096 |
|
|
sl@0
|
1097 |
/**
|
|
sl@0
|
1098 |
* Take the random-access index i and adjust it so that it points to the beginning
|
|
sl@0
|
1099 |
* of a code point.
|
|
sl@0
|
1100 |
* The input index points to any code unit of a code point and is moved to point to
|
|
sl@0
|
1101 |
* the first code unit of the same code point. i is never incremented.
|
|
sl@0
|
1102 |
* In other words, if i points to a trail surrogate that is preceded by a matching
|
|
sl@0
|
1103 |
* lead surrogate, then i is decremented. Otherwise it is not modified.
|
|
sl@0
|
1104 |
* This can be used to start an iteration with UTF_NEXT_CHAR() from a random index.
|
|
sl@0
|
1105 |
* Same as UTF16_SET_CHAR_START.
|
|
sl@0
|
1106 |
* \pre start<=i<length
|
|
sl@0
|
1107 |
* \post start<=i<length
|
|
sl@0
|
1108 |
*
|
|
sl@0
|
1109 |
* @deprecated ICU 2.4. Renamed to U16_SET_CP_START, see utf_old.h.
|
|
sl@0
|
1110 |
*/
|
|
sl@0
|
1111 |
#define UTF_SET_CHAR_START(s, start, i) U16_SET_CP_START(s, start, i)
|
|
sl@0
|
1112 |
|
|
sl@0
|
1113 |
/**
|
|
sl@0
|
1114 |
* Set c to the code point that has code units before i
|
|
sl@0
|
1115 |
* and move i backward (towards the beginning of the string)
|
|
sl@0
|
1116 |
* to the first code unit of this code point (pre-increment).
|
|
sl@0
|
1117 |
* i must point to the first code unit after the last unit of a code point (i==length is allowed).
|
|
sl@0
|
1118 |
* Same as UTF16_PREV_CHAR.
|
|
sl@0
|
1119 |
* \pre start<i<=length
|
|
sl@0
|
1120 |
* \post start<=i<length
|
|
sl@0
|
1121 |
*
|
|
sl@0
|
1122 |
* @deprecated ICU 2.4. Renamed to U16_PREV, see utf_old.h.
|
|
sl@0
|
1123 |
*/
|
|
sl@0
|
1124 |
#define UTF_PREV_CHAR(s, start, i, c) U16_PREV(s, start, i, c)
|
|
sl@0
|
1125 |
|
|
sl@0
|
1126 |
/**
|
|
sl@0
|
1127 |
* Move i backward (towards the beginning of the string)
|
|
sl@0
|
1128 |
* to the first code unit of the code point that has code units before i.
|
|
sl@0
|
1129 |
* I.e., move i backward by one code point.
|
|
sl@0
|
1130 |
* i must point to the first code unit after the last unit of a code point (i==length is allowed).
|
|
sl@0
|
1131 |
* Same as UTF16_BACK_1.
|
|
sl@0
|
1132 |
* \pre start<i<=length
|
|
sl@0
|
1133 |
* \post start<=i<length
|
|
sl@0
|
1134 |
*
|
|
sl@0
|
1135 |
* @deprecated ICU 2.4. Renamed to U16_BACK_1, see utf_old.h.
|
|
sl@0
|
1136 |
*/
|
|
sl@0
|
1137 |
#define UTF_BACK_1(s, start, i) U16_BACK_1(s, start, i)
|
|
sl@0
|
1138 |
|
|
sl@0
|
1139 |
/**
|
|
sl@0
|
1140 |
* Move i backward (towards the beginning of the string)
|
|
sl@0
|
1141 |
* to the first code unit of the n code points that have code units before i.
|
|
sl@0
|
1142 |
* I.e., move i backward by n code points.
|
|
sl@0
|
1143 |
* i must point to the first code unit after the last unit of a code point (i==length is allowed).
|
|
sl@0
|
1144 |
* Same as UTF16_BACK_N.
|
|
sl@0
|
1145 |
* \pre start<i<=length
|
|
sl@0
|
1146 |
* \post start<=i<length
|
|
sl@0
|
1147 |
*
|
|
sl@0
|
1148 |
* @deprecated ICU 2.4. Renamed to U16_BACK_N, see utf_old.h.
|
|
sl@0
|
1149 |
*/
|
|
sl@0
|
1150 |
#define UTF_BACK_N(s, start, i, n) U16_BACK_N(s, start, i, n)
|
|
sl@0
|
1151 |
|
|
sl@0
|
1152 |
/**
|
|
sl@0
|
1153 |
* Take the random-access index i and adjust it so that it points beyond
|
|
sl@0
|
1154 |
* a code point. The input index points beyond any code unit
|
|
sl@0
|
1155 |
* of a code point and is moved to point beyond the last code unit of the same
|
|
sl@0
|
1156 |
* code point. i is never decremented.
|
|
sl@0
|
1157 |
* In other words, if i points to a trail surrogate that is preceded by a matching
|
|
sl@0
|
1158 |
* lead surrogate, then i is incremented. Otherwise it is not modified.
|
|
sl@0
|
1159 |
* This can be used to start an iteration with UTF_PREV_CHAR() from a random index.
|
|
sl@0
|
1160 |
* Same as UTF16_SET_CHAR_LIMIT.
|
|
sl@0
|
1161 |
* \pre start<i<=length
|
|
sl@0
|
1162 |
* \post start<i<=length
|
|
sl@0
|
1163 |
*
|
|
sl@0
|
1164 |
* @deprecated ICU 2.4. Renamed to U16_SET_CP_LIMIT, see utf_old.h.
|
|
sl@0
|
1165 |
*/
|
|
sl@0
|
1166 |
#define UTF_SET_CHAR_LIMIT(s, start, i, length) U16_SET_CP_LIMIT(s, start, i, length)
|
|
sl@0
|
1167 |
|
|
sl@0
|
1168 |
#endif /* U_HIDE_DEPRECATED_API */
|
|
sl@0
|
1169 |
|
|
sl@0
|
1170 |
#endif
|
|
sl@0
|
1171 |
|