/* ****************************************************************************** * * Copyright (C) 2000-2010, International Business Machines * Corporation and others. All Rights Reserved. * ****************************************************************************** * file name: ushape.h * encoding: US-ASCII * tab size: 8 (not used) * indentation:4 * * created on: 2000jun29 * created by: Markus W. Scherer */ #ifndef __USHAPE_H__ #define __USHAPE_H__ #include "unicode/utypes.h" /** * \file * \brief C API: Arabic shaping * */ /** * Shape Arabic text on a character basis. * *
This function performs basic operations for "shaping" Arabic text. It is most * useful for use with legacy data formats and legacy display technology * (simple terminals). All operations are performed on Unicode characters.
* *Text-based shaping means that some character code points in the text are * replaced by others depending on the context. It transforms one kind of text * into another. In comparison, modern displays for Arabic text select * appropriate, context-dependent font glyphs for each text element, which means * that they transform text into a glyph vector.
* *Text transformations are necessary when modern display technology is not * available or when text needs to be transformed to or from legacy formats that * use "shaped" characters. Since the Arabic script is cursive, connecting * adjacent letters to each other, computers select images for each letter based * on the surrounding letters. This usually results in four images per Arabic * letter: initial, middle, final, and isolated forms. In Unicode, on the other * hand, letters are normally stored abstract, and a display system is expected * to select the necessary glyphs. (This makes searching and other text * processing easier because the same letter has only one code.) It is possible * to mimic this with text transformations because there are characters in * Unicode that are rendered as letters with a specific shape * (or cursive connectivity). They were included for interoperability with * legacy systems and codepages, and for unsophisticated display systems.
* *A second kind of text transformations is supported for Arabic digits: * For compatibility with legacy codepages that only include European digits, * it is possible to replace one set of digits by another, changing the * character code points. These operations can be performed for either * Arabic-Indic Digits (U+0660...U+0669) or Eastern (Extended) Arabic-Indic * digits (U+06f0...U+06f9).
* *Some replacements may result in more or fewer characters (code points). * By default, this means that the destination buffer may receive text with a * length different from the source length. Some legacy systems rely on the * length of the text to be constant. They expect extra spaces to be added * or consumed either next to the affected character or at the end of the * text.
* *For details about the available operations, see the description of the
* U_SHAPE_...
options.
source
.
*
* @param dest The destination buffer that will receive the results of the
* requested operations. It may be NULL
only if
* destSize
is 0. The source and destination must not
* overlap.
*
* @param destSize The size (capacity) of the destination buffer in UChars.
* If destSize
is 0, then no output is produced,
* but the necessary buffer size is returned ("preflighting").
*
* @param options This is a 32-bit set of flags that specify the operations
* that are performed on the input text. If no error occurs,
* then the result will always be written to the destination
* buffer.
*
* @param pErrorCode must be a valid pointer to an error code value,
* which must not indicate a failure before the function call.
*
* @return The number of UChars written to the destination buffer.
* If an error occured, then no output was written, or it may be
* incomplete. If U_BUFFER_OVERFLOW_ERROR
is set, then
* the return value indicates the necessary destination buffer size.
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
u_shapeArabic(const UChar *source, int32_t sourceLength,
UChar *dest, int32_t destSize,
uint32_t options,
UErrorCode *pErrorCode);
/**
* Memory option: allow the result to have a different length than the source.
* Affects: LamAlef options
* @stable ICU 2.0
*/
#define U_SHAPE_LENGTH_GROW_SHRINK 0
/**
* Memory option: allow the result to have a different length than the source.
* Affects: LamAlef options
* This option is an alias to U_SHAPE_LENGTH_GROW_SHRINK
* @draft ICU 4.2
*/
#define U_SHAPE_LAMALEF_RESIZE 0
/**
* Memory option: the result must have the same length as the source.
* If more room is necessary, then try to consume spaces next to modified characters.
* @stable ICU 2.0
*/
#define U_SHAPE_LENGTH_FIXED_SPACES_NEAR 1
/**
* Memory option: the result must have the same length as the source.
* If more room is necessary, then try to consume spaces next to modified characters.
* Affects: LamAlef options
* This option is an alias to U_SHAPE_LENGTH_FIXED_SPACES_NEAR
* @draft ICU 4.2
*/
#define U_SHAPE_LAMALEF_NEAR 1
/**
* Memory option: the result must have the same length as the source.
* If more room is necessary, then try to consume spaces at the end of the text.
* @stable ICU 2.0
*/
#define U_SHAPE_LENGTH_FIXED_SPACES_AT_END 2
/**
* Memory option: the result must have the same length as the source.
* If more room is necessary, then try to consume spaces at the end of the text.
* Affects: LamAlef options
* This option is an alias to U_SHAPE_LENGTH_FIXED_SPACES_AT_END
* @draft ICU 4.2
*/
#define U_SHAPE_LAMALEF_END 2
/**
* Memory option: the result must have the same length as the source.
* If more room is necessary, then try to consume spaces at the beginning of the text.
* @stable ICU 2.0
*/
#define U_SHAPE_LENGTH_FIXED_SPACES_AT_BEGINNING 3
/**
* Memory option: the result must have the same length as the source.
* If more room is necessary, then try to consume spaces at the beginning of the text.
* Affects: LamAlef options
* This option is an alias to U_SHAPE_LENGTH_FIXED_SPACES_AT_BEGINNING
* @draft ICU 4.2
*/
#define U_SHAPE_LAMALEF_BEGIN 3
/**
* Memory option: the result must have the same length as the source.
* Shaping Mode: For each LAMALEF character found, expand LAMALEF using space at end.
* If there is no space at end, use spaces at beginning of the buffer. If there
* is no space at beginning of the buffer, use spaces at the near (i.e. the space
* after the LAMALEF character).
* If there are no spaces found, an error U_NO_SPACE_AVAILABLE (as defined in utypes.h)
* will be set in pErrorCode
*
* Deshaping Mode: Perform the same function as the flag equals U_SHAPE_LAMALEF_END.
* Affects: LamAlef options
* @draft ICU 4.2
*/
#define U_SHAPE_LAMALEF_AUTO 0x10000
/** Bit mask for memory options. @stable ICU 2.0 */
#define U_SHAPE_LENGTH_MASK 0x10003 /* Changed old value 3 */
/**
* Bit mask for LamAlef memory options.
* @draft ICU 4.2
*/
#define U_SHAPE_LAMALEF_MASK 0x10003 /* updated */
/** Direction indicator: the source is in logical (keyboard) order. @stable ICU 2.0 */
#define U_SHAPE_TEXT_DIRECTION_LOGICAL 0
/**
* Direction indicator:
* the source is in visual RTL order,
* the rightmost displayed character stored first.
* This option is an alias to U_SHAPE_TEXT_DIRECTION_LOGICAL
* @draft ICU 4.2
*/
#define U_SHAPE_TEXT_DIRECTION_VISUAL_RTL 0
/**
* Direction indicator:
* the source is in visual LTR order,
* the leftmost displayed character stored first.
* @stable ICU 2.0
*/
#define U_SHAPE_TEXT_DIRECTION_VISUAL_LTR 4
/** Bit mask for direction indicators. @stable ICU 2.0 */
#define U_SHAPE_TEXT_DIRECTION_MASK 4
/** Letter shaping option: do not perform letter shaping. @stable ICU 2.0 */
#define U_SHAPE_LETTERS_NOOP 0
/** Letter shaping option: replace abstract letter characters by "shaped" ones. @stable ICU 2.0 */
#define U_SHAPE_LETTERS_SHAPE 8
/** Letter shaping option: replace "shaped" letter characters by abstract ones. @stable ICU 2.0 */
#define U_SHAPE_LETTERS_UNSHAPE 0x10
/**
* Letter shaping option: replace abstract letter characters by "shaped" ones.
* The only difference with U_SHAPE_LETTERS_SHAPE is that Tashkeel letters
* are always "shaped" into the isolated form instead of the medial form
* (selecting code points from the Arabic Presentation Forms-B block).
* @stable ICU 2.0
*/
#define U_SHAPE_LETTERS_SHAPE_TASHKEEL_ISOLATED 0x18
/** Bit mask for letter shaping options. @stable ICU 2.0 */
#define U_SHAPE_LETTERS_MASK 0x18
/** Digit shaping option: do not perform digit shaping. @stable ICU 2.0 */
#define U_SHAPE_DIGITS_NOOP 0
/**
* Digit shaping option:
* Replace European digits (U+0030...) by Arabic-Indic digits.
* @stable ICU 2.0
*/
#define U_SHAPE_DIGITS_EN2AN 0x20
/**
* Digit shaping option:
* Replace Arabic-Indic digits by European digits (U+0030...).
* @stable ICU 2.0
*/
#define U_SHAPE_DIGITS_AN2EN 0x40
/**
* Digit shaping option:
* Replace European digits (U+0030...) by Arabic-Indic digits if the most recent
* strongly directional character is an Arabic letter
* (u_charDirection()
result U_RIGHT_TO_LEFT_ARABIC
[AL]).U_LEFT_TO_RIGHT
[L] or U_RIGHT_TO_LEFT
[R]).
* @stable ICU 2.0
*/
#define U_SHAPE_DIGITS_ALEN2AN_INIT_LR 0x60
/**
* Digit shaping option:
* Replace European digits (U+0030...) by Arabic-Indic digits if the most recent
* strongly directional character is an Arabic letter
* (u_charDirection()
result U_RIGHT_TO_LEFT_ARABIC
[AL]).