|
sl@0
|
1 |
/*
|
|
sl@0
|
2 |
******************************************************************************
|
|
sl@0
|
3 |
*
|
|
sl@0
|
4 |
* Copyright (C) 2000-2004, International Business Machines
|
|
sl@0
|
5 |
* Corporation and others. All Rights Reserved.
|
|
sl@0
|
6 |
*
|
|
sl@0
|
7 |
******************************************************************************
|
|
sl@0
|
8 |
* file name: ushape.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: 2000jun29
|
|
sl@0
|
14 |
* created by: Markus W. Scherer
|
|
sl@0
|
15 |
*/
|
|
sl@0
|
16 |
|
|
sl@0
|
17 |
#ifndef __USHAPE_H__
|
|
sl@0
|
18 |
#define __USHAPE_H__
|
|
sl@0
|
19 |
|
|
sl@0
|
20 |
#include "unicode/utypes.h"
|
|
sl@0
|
21 |
|
|
sl@0
|
22 |
/**
|
|
sl@0
|
23 |
* \file
|
|
sl@0
|
24 |
* \brief C API: Arabic shaping
|
|
sl@0
|
25 |
*
|
|
sl@0
|
26 |
*/
|
|
sl@0
|
27 |
|
|
sl@0
|
28 |
/**
|
|
sl@0
|
29 |
* Shape Arabic text on a character basis.
|
|
sl@0
|
30 |
*
|
|
sl@0
|
31 |
* <p>This function performs basic operations for "shaping" Arabic text. It is most
|
|
sl@0
|
32 |
* useful for use with legacy data formats and legacy display technology
|
|
sl@0
|
33 |
* (simple terminals). All operations are performed on Unicode characters.</p>
|
|
sl@0
|
34 |
*
|
|
sl@0
|
35 |
* <p>Text-based shaping means that some character code points in the text are
|
|
sl@0
|
36 |
* replaced by others depending on the context. It transforms one kind of text
|
|
sl@0
|
37 |
* into another. In comparison, modern displays for Arabic text select
|
|
sl@0
|
38 |
* appropriate, context-dependent font glyphs for each text element, which means
|
|
sl@0
|
39 |
* that they transform text into a glyph vector.</p>
|
|
sl@0
|
40 |
*
|
|
sl@0
|
41 |
* <p>Text transformations are necessary when modern display technology is not
|
|
sl@0
|
42 |
* available or when text needs to be transformed to or from legacy formats that
|
|
sl@0
|
43 |
* use "shaped" characters. Since the Arabic script is cursive, connecting
|
|
sl@0
|
44 |
* adjacent letters to each other, computers select images for each letter based
|
|
sl@0
|
45 |
* on the surrounding letters. This usually results in four images per Arabic
|
|
sl@0
|
46 |
* letter: initial, middle, final, and isolated forms. In Unicode, on the other
|
|
sl@0
|
47 |
* hand, letters are normally stored abstract, and a display system is expected
|
|
sl@0
|
48 |
* to select the necessary glyphs. (This makes searching and other text
|
|
sl@0
|
49 |
* processing easier because the same letter has only one code.) It is possible
|
|
sl@0
|
50 |
* to mimic this with text transformations because there are characters in
|
|
sl@0
|
51 |
* Unicode that are rendered as letters with a specific shape
|
|
sl@0
|
52 |
* (or cursive connectivity). They were included for interoperability with
|
|
sl@0
|
53 |
* legacy systems and codepages, and for unsophisticated display systems.</p>
|
|
sl@0
|
54 |
*
|
|
sl@0
|
55 |
* <p>A second kind of text transformations is supported for Arabic digits:
|
|
sl@0
|
56 |
* For compatibility with legacy codepages that only include European digits,
|
|
sl@0
|
57 |
* it is possible to replace one set of digits by another, changing the
|
|
sl@0
|
58 |
* character code points. These operations can be performed for either
|
|
sl@0
|
59 |
* Arabic-Indic Digits (U+0660...U+0669) or Eastern (Extended) Arabic-Indic
|
|
sl@0
|
60 |
* digits (U+06f0...U+06f9).</p>
|
|
sl@0
|
61 |
*
|
|
sl@0
|
62 |
* <p>Some replacements may result in more or fewer characters (code points).
|
|
sl@0
|
63 |
* By default, this means that the destination buffer may receive text with a
|
|
sl@0
|
64 |
* length different from the source length. Some legacy systems rely on the
|
|
sl@0
|
65 |
* length of the text to be constant. They expect extra spaces to be added
|
|
sl@0
|
66 |
* or consumed either next to the affected character or at the end of the
|
|
sl@0
|
67 |
* text.</p>
|
|
sl@0
|
68 |
*
|
|
sl@0
|
69 |
* <p>For details about the available operations, see the description of the
|
|
sl@0
|
70 |
* <code>U_SHAPE_...</code> options.</p>
|
|
sl@0
|
71 |
*
|
|
sl@0
|
72 |
* @param source The input text.
|
|
sl@0
|
73 |
*
|
|
sl@0
|
74 |
* @param sourceLength The number of UChars in <code>source</code>.
|
|
sl@0
|
75 |
*
|
|
sl@0
|
76 |
* @param dest The destination buffer that will receive the results of the
|
|
sl@0
|
77 |
* requested operations. It may be <code>NULL</code> only if
|
|
sl@0
|
78 |
* <code>destSize</code> is 0. The source and destination must not
|
|
sl@0
|
79 |
* overlap.
|
|
sl@0
|
80 |
*
|
|
sl@0
|
81 |
* @param destSize The size (capacity) of the destination buffer in UChars.
|
|
sl@0
|
82 |
* If <code>destSize</code> is 0, then no output is produced,
|
|
sl@0
|
83 |
* but the necessary buffer size is returned ("preflighting").
|
|
sl@0
|
84 |
*
|
|
sl@0
|
85 |
* @param options This is a 32-bit set of flags that specify the operations
|
|
sl@0
|
86 |
* that are performed on the input text. If no error occurs,
|
|
sl@0
|
87 |
* then the result will always be written to the destination
|
|
sl@0
|
88 |
* buffer.
|
|
sl@0
|
89 |
*
|
|
sl@0
|
90 |
* @param pErrorCode must be a valid pointer to an error code value,
|
|
sl@0
|
91 |
* which must not indicate a failure before the function call.
|
|
sl@0
|
92 |
*
|
|
sl@0
|
93 |
* @return The number of UChars written to the destination buffer.
|
|
sl@0
|
94 |
* If an error occured, then no output was written, or it may be
|
|
sl@0
|
95 |
* incomplete. If <code>U_BUFFER_OVERFLOW_ERROR</code> is set, then
|
|
sl@0
|
96 |
* the return value indicates the necessary destination buffer size.
|
|
sl@0
|
97 |
* @stable ICU 2.0
|
|
sl@0
|
98 |
*/
|
|
sl@0
|
99 |
U_STABLE int32_t U_EXPORT2
|
|
sl@0
|
100 |
u_shapeArabic(const UChar *source, int32_t sourceLength,
|
|
sl@0
|
101 |
UChar *dest, int32_t destSize,
|
|
sl@0
|
102 |
uint32_t options,
|
|
sl@0
|
103 |
UErrorCode *pErrorCode);
|
|
sl@0
|
104 |
|
|
sl@0
|
105 |
/**
|
|
sl@0
|
106 |
* Memory option: allow the result to have a different length than the source.
|
|
sl@0
|
107 |
* @stable ICU 2.0
|
|
sl@0
|
108 |
*/
|
|
sl@0
|
109 |
#define U_SHAPE_LENGTH_GROW_SHRINK 0
|
|
sl@0
|
110 |
|
|
sl@0
|
111 |
/**
|
|
sl@0
|
112 |
* Memory option: the result must have the same length as the source.
|
|
sl@0
|
113 |
* If more room is necessary, then try to consume spaces next to modified characters.
|
|
sl@0
|
114 |
* @stable ICU 2.0
|
|
sl@0
|
115 |
*/
|
|
sl@0
|
116 |
#define U_SHAPE_LENGTH_FIXED_SPACES_NEAR 1
|
|
sl@0
|
117 |
|
|
sl@0
|
118 |
/**
|
|
sl@0
|
119 |
* Memory option: the result must have the same length as the source.
|
|
sl@0
|
120 |
* If more room is necessary, then try to consume spaces at the end of the text.
|
|
sl@0
|
121 |
* @stable ICU 2.0
|
|
sl@0
|
122 |
*/
|
|
sl@0
|
123 |
#define U_SHAPE_LENGTH_FIXED_SPACES_AT_END 2
|
|
sl@0
|
124 |
|
|
sl@0
|
125 |
/**
|
|
sl@0
|
126 |
* Memory option: the result must have the same length as the source.
|
|
sl@0
|
127 |
* If more room is necessary, then try to consume spaces at the beginning of the text.
|
|
sl@0
|
128 |
* @stable ICU 2.0
|
|
sl@0
|
129 |
*/
|
|
sl@0
|
130 |
#define U_SHAPE_LENGTH_FIXED_SPACES_AT_BEGINNING 3
|
|
sl@0
|
131 |
|
|
sl@0
|
132 |
/** Bit mask for memory options. @stable ICU 2.0 */
|
|
sl@0
|
133 |
#define U_SHAPE_LENGTH_MASK 3
|
|
sl@0
|
134 |
|
|
sl@0
|
135 |
|
|
sl@0
|
136 |
/** Direction indicator: the source is in logical (keyboard) order. @stable ICU 2.0 */
|
|
sl@0
|
137 |
#define U_SHAPE_TEXT_DIRECTION_LOGICAL 0
|
|
sl@0
|
138 |
|
|
sl@0
|
139 |
/**
|
|
sl@0
|
140 |
* Direction indicator:
|
|
sl@0
|
141 |
* the source is in visual LTR order,
|
|
sl@0
|
142 |
* the leftmost displayed character stored first.
|
|
sl@0
|
143 |
* @stable ICU 2.0
|
|
sl@0
|
144 |
*/
|
|
sl@0
|
145 |
#define U_SHAPE_TEXT_DIRECTION_VISUAL_LTR 4
|
|
sl@0
|
146 |
|
|
sl@0
|
147 |
/** Bit mask for direction indicators. @stable ICU 2.0 */
|
|
sl@0
|
148 |
#define U_SHAPE_TEXT_DIRECTION_MASK 4
|
|
sl@0
|
149 |
|
|
sl@0
|
150 |
|
|
sl@0
|
151 |
/** Letter shaping option: do not perform letter shaping. @stable ICU 2.0 */
|
|
sl@0
|
152 |
#define U_SHAPE_LETTERS_NOOP 0
|
|
sl@0
|
153 |
|
|
sl@0
|
154 |
/** Letter shaping option: replace abstract letter characters by "shaped" ones. @stable ICU 2.0 */
|
|
sl@0
|
155 |
#define U_SHAPE_LETTERS_SHAPE 8
|
|
sl@0
|
156 |
|
|
sl@0
|
157 |
/** Letter shaping option: replace "shaped" letter characters by abstract ones. @stable ICU 2.0 */
|
|
sl@0
|
158 |
#define U_SHAPE_LETTERS_UNSHAPE 0x10
|
|
sl@0
|
159 |
|
|
sl@0
|
160 |
/**
|
|
sl@0
|
161 |
* Letter shaping option: replace abstract letter characters by "shaped" ones.
|
|
sl@0
|
162 |
* The only difference with U_SHAPE_LETTERS_SHAPE is that Tashkeel letters
|
|
sl@0
|
163 |
* are always "shaped" into the isolated form instead of the medial form
|
|
sl@0
|
164 |
* (selecting code points from the Arabic Presentation Forms-B block).
|
|
sl@0
|
165 |
* @stable ICU 2.0
|
|
sl@0
|
166 |
*/
|
|
sl@0
|
167 |
#define U_SHAPE_LETTERS_SHAPE_TASHKEEL_ISOLATED 0x18
|
|
sl@0
|
168 |
|
|
sl@0
|
169 |
/** Bit mask for letter shaping options. @stable ICU 2.0 */
|
|
sl@0
|
170 |
#define U_SHAPE_LETTERS_MASK 0x18
|
|
sl@0
|
171 |
|
|
sl@0
|
172 |
|
|
sl@0
|
173 |
/** Digit shaping option: do not perform digit shaping. @stable ICU 2.0 */
|
|
sl@0
|
174 |
#define U_SHAPE_DIGITS_NOOP 0
|
|
sl@0
|
175 |
|
|
sl@0
|
176 |
/**
|
|
sl@0
|
177 |
* Digit shaping option:
|
|
sl@0
|
178 |
* Replace European digits (U+0030...) by Arabic-Indic digits.
|
|
sl@0
|
179 |
* @stable ICU 2.0
|
|
sl@0
|
180 |
*/
|
|
sl@0
|
181 |
#define U_SHAPE_DIGITS_EN2AN 0x20
|
|
sl@0
|
182 |
|
|
sl@0
|
183 |
/**
|
|
sl@0
|
184 |
* Digit shaping option:
|
|
sl@0
|
185 |
* Replace Arabic-Indic digits by European digits (U+0030...).
|
|
sl@0
|
186 |
* @stable ICU 2.0
|
|
sl@0
|
187 |
*/
|
|
sl@0
|
188 |
#define U_SHAPE_DIGITS_AN2EN 0x40
|
|
sl@0
|
189 |
|
|
sl@0
|
190 |
/**
|
|
sl@0
|
191 |
* Digit shaping option:
|
|
sl@0
|
192 |
* Replace European digits (U+0030...) by Arabic-Indic digits if the most recent
|
|
sl@0
|
193 |
* strongly directional character is an Arabic letter
|
|
sl@0
|
194 |
* (<code>u_charDirection()</code> result <code>U_RIGHT_TO_LEFT_ARABIC</code> [AL]).<br>
|
|
sl@0
|
195 |
* The direction of "preceding" depends on the direction indicator option.
|
|
sl@0
|
196 |
* For the first characters, the preceding strongly directional character
|
|
sl@0
|
197 |
* (initial state) is assumed to be not an Arabic letter
|
|
sl@0
|
198 |
* (it is <code>U_LEFT_TO_RIGHT</code> [L] or <code>U_RIGHT_TO_LEFT</code> [R]).
|
|
sl@0
|
199 |
* @stable ICU 2.0
|
|
sl@0
|
200 |
*/
|
|
sl@0
|
201 |
#define U_SHAPE_DIGITS_ALEN2AN_INIT_LR 0x60
|
|
sl@0
|
202 |
|
|
sl@0
|
203 |
/**
|
|
sl@0
|
204 |
* Digit shaping option:
|
|
sl@0
|
205 |
* Replace European digits (U+0030...) by Arabic-Indic digits if the most recent
|
|
sl@0
|
206 |
* strongly directional character is an Arabic letter
|
|
sl@0
|
207 |
* (<code>u_charDirection()</code> result <code>U_RIGHT_TO_LEFT_ARABIC</code> [AL]).<br>
|
|
sl@0
|
208 |
* The direction of "preceding" depends on the direction indicator option.
|
|
sl@0
|
209 |
* For the first characters, the preceding strongly directional character
|
|
sl@0
|
210 |
* (initial state) is assumed to be an Arabic letter.
|
|
sl@0
|
211 |
* @stable ICU 2.0
|
|
sl@0
|
212 |
*/
|
|
sl@0
|
213 |
#define U_SHAPE_DIGITS_ALEN2AN_INIT_AL 0x80
|
|
sl@0
|
214 |
|
|
sl@0
|
215 |
/** Not a valid option value. May be replaced by a new option. @stable ICU 2.0 */
|
|
sl@0
|
216 |
#define U_SHAPE_DIGITS_RESERVED 0xa0
|
|
sl@0
|
217 |
|
|
sl@0
|
218 |
/** Bit mask for digit shaping options. @stable ICU 2.0 */
|
|
sl@0
|
219 |
#define U_SHAPE_DIGITS_MASK 0xe0
|
|
sl@0
|
220 |
|
|
sl@0
|
221 |
|
|
sl@0
|
222 |
/** Digit type option: Use Arabic-Indic digits (U+0660...U+0669). @stable ICU 2.0 */
|
|
sl@0
|
223 |
#define U_SHAPE_DIGIT_TYPE_AN 0
|
|
sl@0
|
224 |
|
|
sl@0
|
225 |
/** Digit type option: Use Eastern (Extended) Arabic-Indic digits (U+06f0...U+06f9). @stable ICU 2.0 */
|
|
sl@0
|
226 |
#define U_SHAPE_DIGIT_TYPE_AN_EXTENDED 0x100
|
|
sl@0
|
227 |
|
|
sl@0
|
228 |
/** Not a valid option value. May be replaced by a new option. @stable ICU 2.0 */
|
|
sl@0
|
229 |
#define U_SHAPE_DIGIT_TYPE_RESERVED 0x200
|
|
sl@0
|
230 |
|
|
sl@0
|
231 |
/** Bit mask for digit type options. @stable ICU 2.0 */
|
|
sl@0
|
232 |
#define U_SHAPE_DIGIT_TYPE_MASK 0x3f00
|
|
sl@0
|
233 |
|
|
sl@0
|
234 |
#endif
|