* * Note: Libraries that perform a bidirectional algorithm and * reorder strings accordingly are sometimes called "Storage Layout Engines". * ICU's BiDi and shaping (u_shapeArabic()) APIs can be used at the core of such * "Storage Layout Engines". * *
pErrorCode pointer must be valid
* and the value that it points to must not indicate a failure before
* the function call. Otherwise, the function returns immediately.
* After the function call, the value indicates success or failure.* * The "limit" of a sequence of characters is the position just after their * last character, i.e., one more than that position.
* * Some of the API functions provide access to "runs". * Such a "run" is defined as a sequence of characters * that are at the same embedding level * after performing the BIDI algorithm.
* * @author Markus W. Scherer * @version 1.0 * * *
The basic assumptions are:
*
* \code
*#include "unicode/ubidi.h"
*
*typedef enum {
* styleNormal=0, styleSelected=1,
* styleBold=2, styleItalics=4,
* styleSuper=8, styleSub=16
*} Style;
*
*typedef struct { int32_t limit; Style style; } StyleRun;
*
*int getTextWidth(const UChar *text, int32_t start, int32_t limit,
* const StyleRun *styleRuns, int styleRunCount);
*
* // set *pLimit and *pStyleRunLimit for a line
* // from text[start] and from styleRuns[styleRunStart]
* // using ubidi_getLogicalRun(para, ...)
*void getLineBreak(const UChar *text, int32_t start, int32_t *pLimit,
* UBiDi *para,
* const StyleRun *styleRuns, int styleRunStart, int *pStyleRunLimit,
* int *pLineWidth);
*
* // render runs on a line sequentially, always from left to right
*
* // prepare rendering a new line
* void startLine(UBiDiDirection textDirection, int lineWidth);
*
* // render a run of text and advance to the right by the run width
* // the text[start..limit-1] is always in logical order
* void renderRun(const UChar *text, int32_t start, int32_t limit,
* UBiDiDirection textDirection, Style style);
*
* // We could compute a cross-product
* // from the style runs with the directional runs
* // and then reorder it.
* // Instead, here we iterate over each run type
* // and render the intersections -
* // with shortcuts in simple (and common) cases.
* // renderParagraph() is the main function.
*
* // render a directional run with
* // (possibly) multiple style runs intersecting with it
* void renderDirectionalRun(const UChar *text,
* int32_t start, int32_t limit,
* UBiDiDirection direction,
* const StyleRun *styleRuns, int styleRunCount) {
* int i;
*
* // iterate over style runs
* if(direction==UBIDI_LTR) {
* int styleLimit;
*
* for(i=0; ilimit) { styleLimit=limit; }
* renderRun(text, start, styleLimit,
* direction, styleRun[i].style);
* if(styleLimit==limit) { break; }
* start=styleLimit;
* }
* }
* } else {
* int styleStart;
*
* for(i=styleRunCount-1; i>=0; --i) {
* if(i>0) {
* styleStart=styleRun[i-1].limit;
* } else {
* styleStart=0;
* }
* if(limit>=styleStart) {
* if(styleStart=length
*
* width=getTextWidth(text, 0, length, styleRuns, styleRunCount);
* if(width<=lineWidth) {
* // everything fits onto one line
*
* // prepare rendering a new line from either left or right
* startLine(paraLevel, width);
*
* renderLine(para, text, 0, length,
* styleRuns, styleRunCount);
* } else {
* UBiDi *line;
*
* // we need to render several lines
* line=ubidi_openSized(length, 0, pErrorCode);
* if(line!=NULL) {
* int32_t start=0, limit;
* int styleRunStart=0, styleRunLimit;
*
* for(;;) {
* limit=length;
* styleRunLimit=styleRunCount;
* getLineBreak(text, start, &limit, para,
* styleRuns, styleRunStart, &styleRunLimit,
* &width);
* ubidi_setLine(para, start, limit, line, pErrorCode);
* if(U_SUCCESS(*pErrorCode)) {
* // prepare rendering a new line
* // from either left or right
* startLine(paraLevel, width);
*
* renderLine(line, text, start, limit,
* styleRuns+styleRunStart,
* styleRunLimit-styleRunStart);
* }
* if(limit==length) { break; }
* start=limit;
* styleRunStart=styleRunLimit-1;
* if(start>=styleRuns[styleRunStart].limit) {
* ++styleRunStart;
* }
* }
*
* ubidi_close(line);
* }
* }
* }
*
* ubidi_close(para);
*}
*\endcode
*
*/
/*DOCXX_TAG*/
/*@{*/
/**
* UBiDiLevel is the type of the level values in this
* BiDi implementation.
* It holds an embedding level and indicates the visual direction
* by its bit 0 (even/odd value).
*
* It can also hold non-level values for the
* paraLevel and embeddingLevels
* arguments of ubidi_setPara(); there:
*
embeddingLevels[]
* value indicates whether the using application is
* specifying the level of a character to override whatever the
* BiDi implementation would resolve it to.paraLevel can be set to the
* pseudo-level values UBIDI_DEFAULT_LTR
* and UBIDI_DEFAULT_RTL.The related constants are not real, valid level values.
* UBIDI_DEFAULT_XXX can be used to specify
* a default for the paragraph level for
* when the ubidi_setPara() function
* shall determine it but there is no
* strongly typed character in the input.
*
* Note that the value for UBIDI_DEFAULT_LTR is even
* and the one for UBIDI_DEFAULT_RTL is odd,
* just like with normal LTR and RTL level values -
* these special values are designed that way. Also, the implementation
* assumes that UBIDI_MAX_EXPLICIT_LEVEL is odd.
*
* @see UBIDI_DEFAULT_LTR
* @see UBIDI_DEFAULT_RTL
* @see UBIDI_LEVEL_OVERRIDE
* @see UBIDI_MAX_EXPLICIT_LEVEL
* @stable ICU 2.0
*/
typedef uint8_t UBiDiLevel;
/** Paragraph level setting.
* If there is no strong character, then set the paragraph level to 0 (left-to-right).
* @stable ICU 2.0
*/
#define UBIDI_DEFAULT_LTR 0xfe
/** Paragraph level setting.
* If there is no strong character, then set the paragraph level to 1 (right-to-left).
* @stable ICU 2.0
*/
#define UBIDI_DEFAULT_RTL 0xff
/**
* Maximum explicit embedding level.
* (The maximum resolved level can be up to UBIDI_MAX_EXPLICIT_LEVEL+1).
* @stable ICU 2.0
*/
#define UBIDI_MAX_EXPLICIT_LEVEL 61
/** Bit flag for level input.
* Overrides directional properties.
* @stable ICU 2.0
*/
#define UBIDI_LEVEL_OVERRIDE 0x80
/**
* Special value which can be returned by the mapping functions when a logical
* index has no corresponding visual index or vice-versa. This may happen
* for the logical-to-visual mapping of a BiDi control when option
* UBIDI_OPTION_REMOVE_CONTROLS is specified. This can also happen
* for the visual-to-logical mapping of a BiDi mark (LRM or RLM) inserted
* by option UBIDI_OPTION_INSERT_MARKS.
* @see ubidi_getVisualIndex
* @see ubidi_getVisualMap
* @see ubidi_getLogicalIndex
* @see ubidi_getLogicalMap
* @draft ICU 3.6
*/
#define UBIDI_MAP_NOWHERE (-1)
/**
* UBiDiDirection values indicate the text direction.
* @stable ICU 2.0
*/
enum UBiDiDirection {
/** All left-to-right text. This is a 0 value. @stable ICU 2.0 */
UBIDI_LTR,
/** All right-to-left text. This is a 1 value. @stable ICU 2.0 */
UBIDI_RTL,
/** Mixed-directional text. @stable ICU 2.0 */
UBIDI_MIXED
};
/** @stable ICU 2.0 */
typedef enum UBiDiDirection UBiDiDirection;
/**
* Forward declaration of the UBiDi structure for the declaration of
* the API functions. Its fields are implementation-specific.
* This structure holds information about a paragraph (or multiple paragraphs) * of text with BiDi-algorithm-related details, or about one line of * such a paragraph.
* Reordering can be done on a line, or on one or more paragraphs which are
* then interpreted each as one single line.
* @stable ICU 2.0
*/
struct UBiDi;
/** @stable ICU 2.0 */
typedef struct UBiDi UBiDi;
/**
* Allocate a UBiDi structure.
* Such an object is initially empty. It is assigned
* the BiDi properties of a piece of text containing one or more paragraphs
* by ubidi_setPara()
* or the BiDi properties of a line within a paragraph by
* ubidi_setLine().
* This object can be reused for as long as it is not deallocated
* by calling ubidi_close().
* ubidi_setPara() and ubidi_setLine() will allocate
* additional memory for internal structures as necessary.
*
* @return An empty UBiDi object.
* @stable ICU 2.0
*/
U_STABLE UBiDi * U_EXPORT2
ubidi_open(void);
/**
* Allocate a UBiDi structure with preallocated memory
* for internal structures.
* This function provides a UBiDi object like ubidi_open()
* with no arguments, but it also preallocates memory for internal structures
* according to the sizings supplied by the caller.
* Subsequent functions will not allocate any more memory, and are thus * guaranteed not to fail because of lack of memory.
* The preallocation can be limited to some of the internal memory
* by setting some values to 0 here. That means that if, e.g.,
* maxRunCount cannot be reasonably predetermined and should not
* be set to maxLength (the only failproof value) to avoid
* wasting memory, then maxRunCount could be set to 0 here
* and the internal structures that are associated with it will be allocated
* on demand, just like with ubidi_open().
*
* @param maxLength is the maximum text or line length that internal memory
* will be preallocated for. An attempt to associate this object with a
* longer text will fail, unless this value is 0, which leaves the allocation
* up to the implementation.
*
* @param maxRunCount is the maximum anticipated number of same-level runs
* that internal memory will be preallocated for. An attempt to access
* visual runs on an object that was not preallocated for as many runs
* as the text was actually resolved to will fail,
* unless this value is 0, which leaves the allocation up to the implementation.
* The number of runs depends on the actual text and maybe anywhere between
* 1 and maxLength. It is typically small.
*
* @param pErrorCode must be a valid pointer to an error code value.
*
* @return An empty UBiDi object with preallocated memory.
* @stable ICU 2.0
*/
U_STABLE UBiDi * U_EXPORT2
ubidi_openSized(int32_t maxLength, int32_t maxRunCount, UErrorCode *pErrorCode);
/**
* ubidi_close() must be called to free the memory
* associated with a UBiDi object.
*
* Important:
* A parent UBiDi object must not be destroyed or reused if
* it still has children.
* If a UBiDi object is the child
* of another one (its parent), after calling
* ubidi_setLine(), then the child object must
* be destroyed (closed) or reused (by calling
* ubidi_setPara() or ubidi_setLine())
* before the parent object.
*
* @param pBiDi is a UBiDi object.
*
* @see ubidi_setPara
* @see ubidi_setLine
* @stable ICU 2.0
*/
U_STABLE void U_EXPORT2
ubidi_close(UBiDi *pBiDi);
/**
* Modify the operation of the BiDi algorithm such that it
* approximates an "inverse BiDi" algorithm. This function
* must be called before ubidi_setPara().
*
*
The normal operation of the BiDi algorithm as described * in the Unicode Technical Report is to take text stored in logical * (keyboard, typing) order and to determine the reordering of it for visual * rendering. * Some legacy systems store text in visual order, and for operations * with standard, Unicode-based algorithms, the text needs to be transformed * to logical order. This is effectively the inverse algorithm of the * described BiDi algorithm. Note that there is no standard algorithm for * this "inverse BiDi" and that the current implementation provides only an * approximation of "inverse BiDi".
* *With isInverse set to TRUE,
* this function changes the behavior of some of the subsequent functions
* in a way that they can be used for the inverse BiDi algorithm.
* Specifically, runs of text with numeric characters will be treated in a
* special way and may need to be surrounded with LRM characters when they are
* written in reordered sequence.
Output runs should be retrieved using ubidi_getVisualRun().
* Since the actual input for "inverse BiDi" is visually ordered text and
* ubidi_getVisualRun() gets the reordered runs, these are actually
* the runs of the logically ordered output.
Calling this function with argument isInverse set to
* TRUE is equivalent to calling
* ubidi_setReorderingMode with argument
* reorderingMode
* set to UBIDI_REORDER_INVERSE_NUMBERS_AS_L.
* Calling this function with argument isInverse set to
* FALSE is equivalent to calling
* ubidi_setReorderingMode with argument
* reorderingMode
* set to UBIDI_REORDER_DEFAULT.
*
* @param pBiDi is a UBiDi object.
*
* @param isInverse specifies "forward" or "inverse" BiDi operation.
*
* @see ubidi_setPara
* @see ubidi_writeReordered
* @see ubidi_setReorderingMode
* @stable ICU 2.0
*/
U_STABLE void U_EXPORT2
ubidi_setInverse(UBiDi *pBiDi, UBool isInverse);
/**
* Is this BiDi object set to perform the inverse BiDi algorithm?
*
Note: calling this function after setting the reordering mode with
* ubidi_setReorderingMode will return TRUE if the
* reordering mode was set to UBIDI_REORDER_INVERSE_NUMBERS_AS_L,
* FALSE for all other values.
UBiDi object.
* @return TRUE if the BiDi object is set to perform the inverse BiDi algorithm
* by handling numbers as L.
*
* @see ubidi_setInverse
* @see ubidi_setReorderingMode
* @stable ICU 2.0
*/
U_STABLE UBool U_EXPORT2
ubidi_isInverse(UBiDi *pBiDi);
/**
* Specify whether block separators must be allocated level zero,
* so that successive paragraphs will progress from left to right.
* This function must be called before ubidi_setPara().
* Paragraph separators (B) may appear in the text. Setting them to level zero
* means that all paragraph separators (including one possibly appearing
* in the last text position) are kept in the reordered text after the text
* that they follow in the source text.
* When this feature is not enabled, a paragraph separator at the last
* position of the text before reordering will go to the first position
* of the reordered text when the paragraph level is odd.
*
* @param pBiDi is a UBiDi object.
*
* @param orderParagraphsLTR specifies whether paragraph separators (B) must
* receive level 0, so that successive paragraphs progress from left to right.
*
* @see ubidi_setPara
* @stable ICU 3.4
*/
U_STABLE void U_EXPORT2
ubidi_orderParagraphsLTR(UBiDi *pBiDi, UBool orderParagraphsLTR);
/**
* Is this BiDi object set to allocate level 0 to block separators so that
* successive paragraphs progress from left to right?
*
* @param pBiDi is a UBiDi object.
* @return TRUE if the BiDi object is set to allocate level 0 to block
* separators.
*
* @see ubidi_orderParagraphsLTR
* @stable ICU 3.4
*/
U_STABLE UBool U_EXPORT2
ubidi_isOrderParagraphsLTR(UBiDi *pBiDi);
/**
* UBiDiReorderingMode values indicate which variant of the BiDi
* algorithm to use.
*
* @see ubidi_setReorderingMode
* @draft ICU 3.6
*/
typedef enum UBiDiReorderingMode {
/** Regular Logical to Visual BiDi algorithm according to Unicode.
* This is a 0 value. @draft ICU 3.6 */
UBIDI_REORDER_DEFAULT = 0,
/** Logical to Visual algorithm which handles numbers in a way which
* mimicks the behavior of Windows XP.
* @draft ICU 3.6 */
UBIDI_REORDER_NUMBERS_SPECIAL,
/** Logical to Visual grouping numbers with adjacent R characters
* (reversible algorithm).
* @draft ICU 3.6 */
UBIDI_REORDER_GROUP_NUMBERS_WITH_R,
/** Reorder runs only to transform a Logical LTR string to the Logical RTL
* string with the same display, or vice-versa.
* @draft ICU 3.6 */
UBIDI_REORDER_RUNS_ONLY,
/** Visual to Logical algorithm which handles numbers like L
* (same algorithm as selected by ubidi_setInverse(TRUE).
* @see ubidi_setInverse
* @draft ICU 3.6 */
UBIDI_REORDER_INVERSE_NUMBERS_AS_L,
/** Visual to Logical algorithm equivalent to the regular Logical to Visual
* algorithm. @draft ICU 3.6 */
UBIDI_REORDER_INVERSE_LIKE_DIRECT,
/** Inverse BiDi (Visual to Logical) algorithm for the
* UBIDI_REORDER_NUMBERS_SPECIAL BiDi algorithm.
* @draft ICU 3.6 */
UBIDI_REORDER_INVERSE_FOR_NUMBERS_SPECIAL,
/** Number of values for reordering mode.
* @draft ICU 3.6 */
UBIDI_REORDER_COUNT
} UBiDiReorderingMode;
/**
* Modify the operation of the BiDi algorithm such that it implements some
* variant to the basic BiDi algorithm or approximates an "inverse BiDi"
* algorithm, depending on different values of the "reordering mode".
* This function must be called before ubidi_setPara(), and stays
* in effect until called again with a different argument.
*
* The normal operation of the BiDi algorithm as described * in the Unicode Standard Annex #9 is to take text stored in logical * (keyboard, typing) order and to determine how to reorder it for visual * rendering.
* *With the reordering mode set to a value other than
* UBIDI_REORDER_DEFAULT, this function changes the behavior of
* some of the subsequent functions in a way such that they implement an
* inverse BiDi algorithm or some other algorithm variants.
Some legacy systems store text in visual order, and for operations * with standard, Unicode-based algorithms, the text needs to be transformed * into logical order. This is effectively the inverse algorithm of the * described BiDi algorithm. Note that there is no standard algorithm for * this "inverse BiDi", so a number of variants are implemented here.
* *In other cases, it may be desirable to emulate some variant of the * Logical to Visual algorithm (e.g. one used in MS Windows), or perform a * Logical to Logical transformation.
* *When the reordering mode is set to UBIDI_REORDER_DEFAULT,
* the standard BiDi Logical to Visual algorithm is applied.
When the reordering mode is set to
* UBIDI_REORDER_NUMBERS_SPECIAL,
* the algorithm used to perform BiDi transformations when calling
* ubidi_setPara should approximate the algorithm used in
* Microsoft Windows XP rather than strictly conform to the Unicode BiDi
* algorithm.
*
* The differences between the basic algorithm and the algorithm addressed
* by this option are as follows:
*
When the reordering mode is set to
* UBIDI_REORDER_GROUP_NUMBERS_WITH_R,
* numbers located between LTR text and RTL text are associated with the RTL
* text. For instance, an LTR paragraph with content "abc 123 DEF" (where
* upper case letters represent RTL characters) will be transformed to
* "abc FED 123" (and not "abc 123 FED"), "DEF 123 abc" will be transformed
* to "123 FED abc" and "123 FED abc" will be transformed to "DEF 123 abc".
* This makes the algorithm reversible and makes it useful when round trip
* (from visual to logical and back to visual) must be achieved without
* adding LRM characters. However, this is a variation from the standard
* Unicode Bidi algorithm.
* The source text should not contain BiDi control characters other than LRM
* or RLM.
When the reordering mode is set to
* UBIDI_REORDER_RUNS_ONLY,
* a "Logical to Logical" transformation must be performed:
*
paraLevel
* in ubidi_setPara) is even, the source text will be handled as
* LTR logical text and will be transformed to the RTL logical text which has
* the same LTR visual display.When the reordering mode is set to
* UBIDI_REORDER_INVERSE_NUMBERS_AS_L, an "inverse BiDi" algorithm
* is applied.
* Runs of text with numeric characters will be treated like LTR letters and
* may need to be surrounded with LRM characters when they are written in
* reordered sequence (the option UBIDI_INSERT_LRM_FOR_NUMERIC can
* be used with function ubidi_writeReordered to this end. This
* mode is equivalent to calling ubidi_setInverse with
* argument isInverse set to TRUE.
When the reordering mode is set to
* UBIDI_REORDER_INVERSE_AS_DIRECT, the "direct" Logical to Visual
* BiDi algorithm is used as an approximation of an "inverse BiDi" algorithm.
* This mode is similar to mode UBIDI_REORDER_INVERSE_NUMBERS_AS_L
* but is closer to the regular BiDi algorithm.
*
* For example, an LTR paragraph with the content "FED 123 456 CBA" (where
* upper case represents RTL characters) will be transformed to
* "ABC 456 123 DEF", as opposed to "DEF 123 456 ABC"
* with mode UBIDI_REORDER_INVERSE_NUMBERS_AS_L.
* When used in conjunction with option
* UBIDI_OPTION_INSERT_MARKS, this mode generally
* adds BiDi marks to the output significantly more sparingly than mode
* UBIDI_REORDER_INVERSE_NUMBERS_AS_L.
with option
* UBIDI_INSERT_LRM_FOR_NUMERIC in calls to
* ubidi_writeReordered.
When the reordering mode is set to
* UBIDI_REORDER_INVERSE_FOR_NUMBERS_SPECIAL, the Logical to Visual
* BiDi algorithm used in Windows XP is used as an approximation of an
* "inverse BiDi" algorithm.
*
* For example, an LTR paragraph with the content "abc FED123" (where
* upper case represents RTL characters) will be transformed to
* "abc 123DEF.
In all the reordering modes specifying an "inverse BiDi" algorithm
* (i.e. those with a name starting with UBIDI_REORDER_INVERSE),
* output runs should be retrieved using
* ubidi_getVisualRun(), and the output text with
* ubidi_writeReordered(). The caller should keep in mind that in
* "inverse BiDi" modes the input is actually visually ordered text and
* reordered output returned by ubidi_getVisualRun() or
* ubidi_writeReordered() are actually runs or character string
* of logically ordered output.
* For all the "inverse BiDi" modes, the source text should not contain
* BiDi control characters other than LRM or RLM.
Note that option This option must be set or reset before calling
* This option is significant only with reordering modes which generate
* a result with Logical order. If this option is set in conjunction with reordering mode
* For other reordering modes, a minimum number of LRM or RLM characters
* will be added to the source text after reordering it so as to ensure
* round trip, i.e. applying the inverse reordering mode on the
* resulting logical text with removal of BiDi marks
* (option This option will be ignored if specified together with option
* This option must be set or reset before calling
* This option implies the option This option nullifies option This option must be set or reset before calling
* This option specifies that the caller is interested in processing large
* text object in parts.
* The results of the successive calls are expected to be concatenated by the
* caller. Only the call for the last part will have this option bit off. When this option bit is on, UBIDI_OUTPUT_REVERSE of
* ubidi_writeReordered has no useful meaning and should not be
* used in conjunction with any value of the reordering mode specifying
* "inverse BiDi" or with value UBIDI_REORDER_RUNS_ONLY.
*
* @param pBiDi is a UBiDi object.
* @param reorderingMode specifies the required variant of the BiDi algorithm.
*
* @see UBiDiReorderingMode
* @see ubidi_setInverse
* @see ubidi_setPara
* @see ubidi_writeReordered
* @draft ICU 3.6
*/
U_DRAFT void U_EXPORT2
ubidi_setReorderingMode(UBiDi *pBiDi, UBiDiReorderingMode reorderingMode);
/**
* What is the requested reordering mode for a given BiDi object?
*
* @param pBiDi is a UBiDi object.
* @return the current reordering mode of the BiDi object
* @see ubidi_setReorderingMode
* @draft ICU 3.6
*/
U_DRAFT UBiDiReorderingMode U_EXPORT2
ubidi_getReorderingMode(UBiDi *pBiDi);
/**
* UBiDiReorderingOption> values indicate which options are specified
* to affect the BiDi algorithm.
*
* @see ubidi_setReorderingOptions
* @draft ICU 3.6
*/
typedef enum UBiDiReorderingOption {
/**
* option value for ubidi_setReorderingOptions:
* disable all the options which can be set with this function
* @see ubidi_setReorderingOptions
* @draft ICU 3.6
*/
UBIDI_OPTION_DEFAULT = 0,
/**
* option bit for ubidi_setReorderingOptions:
* insert BiDi marks (LRM or RLM) when needed to ensure correct result of
* a reordering to a Logical order
*
* ubidi_setPara.UBIDI_REORDER_INVERSE_NUMBERS_AS_L or with calling
* ubidi_setInverse(TRUE), it implies
* option UBIDI_INSERT_LRM_FOR_NUMERIC
* in calls to function ubidi_writeReordered.UBIDI_OPTION_REMOVE_CONTROLS set before calling
* ubidi_setPara or option UBIDI_REMOVE_BIDI_CONTROLS
* in ubidi_writeReordered), the result will be identical to the
* source text in the first transformation.
*
* UBIDI_OPTION_REMOVE_CONTROLS. It inhibits option
* UBIDI_REMOVE_BIDI_CONTROLS in calls to function
* ubidi_writeReordered and it implies option
* UBIDI_INSERT_LRM_FOR_NUMERIC in calls to function
* ubidi_writeReordered if the reordering mode is
* UBIDI_REORDER_INVERSE_NUMBERS_AS_L.ubidi_setReorderingOptions:
* remove BiDi control characters
*
* ubidi_setPara.UBIDI_REMOVE_BIDI_CONTROLS
* in ubidi_writeReordered.UBIDI_OPTION_INSERT_MARKS.
* It inhibits option UBIDI_INSERT_LRM_FOR_NUMERIC in calls
* to function ubidi_writeReordered and it implies option
* UBIDI_REMOVE_BIDI_CONTROLS in calls to that function.ubidi_setReorderingOptions:
* process the output as part of a stream to be continued
*
* ubidi_setPara.ubidi_setPara() may process
* less than the full source text in order to truncate the text at a meaningful
* boundary. The caller should call ubidi_getProcessedLength()
* immediately after calling ubidi_setPara() in order to
* determine how much of the source text has been processed.
* Source text beyond that length should be resubmitted in following calls to
* ubidi_setPara. The processed length may be less than
* the length of the source text if a character preceding the last character of
* the source text constitutes a reasonable boundary (like a block separator)
* for text to be continued.
* If the last character of the source text constitutes a reasonable
* boundary, the whole text will be processed at once.
* If nowhere in the source text there exists
* such a reasonable boundary, the processed length will be zero.
* The caller should check for such an occurrence and do one of the following:
*
* In all cases, this option should be turned off before processing the last
* part of the text.UBIDI_OPTION_STREAMING.
When the UBIDI_OPTION_STREAMING option is used,
* it is recommended to call ubidi_orderParagraphsLTR() with
* argument orderParagraphsLTR set to TRUE before
* calling ubidi_setPara so that later paragraphs may be
* concatenated to previous paragraphs on the right.
UBiDi object.
* @param reorderingOptions is a combination of zero or more reordering options.
* @see ubidi_getReorderingOptions
* @see UBIDI_OPTION_DEFAULT
* @see UBIDI_OPTION_INSERT_MARKS
* @see UBIDI_OPTION_REMOVE_CONTROLS
* @see UBIDI_OPTION_STREAMING
* @draft ICU 3.6
*/
U_DRAFT void U_EXPORT2
ubidi_setReorderingOptions(UBiDi *pBiDi, uint32_t reorderingOptions);
/**
* What are the reordering options applied to a given BiDi object?
*
* @param pBiDi is a UBiDi object.
* @return the current reordering options of the BiDi object
* @see ubidi_setReorderingOptions
* @draft ICU 3.6
*/
U_DRAFT uint32_t U_EXPORT2
ubidi_getReorderingOptions(UBiDi *pBiDi);
/**
* Perform the Unicode BiDi algorithm. It is defined in the
* Unicode Standard Anned #9,
* version 13,
* also described in The Unicode Standard, Version 4.0 .* * This function takes a piece of plain text containing one or more paragraphs, * with or without externally specified embedding levels from styled * text and computes the left-right-directionality of each character.
*
* If the entire text is all of the same directionality, then
* the function may not perform all the steps described by the algorithm,
* i.e., some levels may not be the same as if all steps were performed.
* This is not relevant for unidirectional text.
* For example, in pure LTR text with numbers the numbers would get
* a resolved level of 2 higher than the surrounding text according to
* the algorithm. This implementation may set all resolved levels to
* the same value in such a case.
*
* The text can be composed of multiple paragraphs. Occurrence of a block
* separator in the text terminates a paragraph, and whatever comes next starts
* a new paragraph. The exception to this rule is when a Carriage Return (CR)
* is followed by a Line Feed (LF). Both CR and LF are block separators, but
* in that case, the pair of characters is considered as terminating the
* preceding paragraph, and a new paragraph will be started by a character
* coming after the LF.
*
* @param pBiDi A UBiDi object allocated with ubidi_open()
* which will be set to contain the reordering information,
* especially the resolved levels for all the characters in text.
*
* @param text is a pointer to the text that the
* BiDi algorithm will be performed on
* The text must be (at least) length long.
* This pointer is stored in the UBiDi object and can be retrieved
* with ubidi_getText().
*
* @param length is the length of the text; if length==-1 then
* the text must be zero-terminated.
*
* @param paraLevel specifies the default level for the text;
* it is typically 0 (LTR) or 1 (RTL).
* If the function shall determine the paragraph level from the text,
* then paraLevel can be set to
* either UBIDI_DEFAULT_LTR
* or UBIDI_DEFAULT_RTL; if the text contains multiple
* paragraphs, the paragraph level shall be determined separately for
* each paragraph; if a paragraph does not include any strongly typed
* character, then the desired default is used (0 for LTR or 1 for RTL).
* Any other value between 0 and UBIDI_MAX_EXPLICIT_LEVEL is also valid,
* with odd levels indicating RTL.
*
* @param embeddingLevels (in) may be used to preset the embedding and override levels,
* ignoring characters like LRE and PDF in the text.
* A level overrides the directional property of its corresponding
* (same index) character if the level has the
* UBIDI_LEVEL_OVERRIDE bit set.
* Except for that bit, it must be
* paraLevel<=embeddingLevels[]<=UBIDI_MAX_EXPLICIT_LEVEL,
* with one exception: a level of zero may be specified for a paragraph
* separator even if paraLevel>0 when multiple paragraphs
* are submitted in the same call to ubidi_setPara().
* Caution: A copy of this pointer, not of the levels,
* will be stored in the UBiDi object;
* the embeddingLevels array must not be
* deallocated before the UBiDi structure is destroyed or reused,
* and the embeddingLevels
* should not be modified to avoid unexpected results on subsequent BiDi operations.
* However, the ubidi_setPara() and
* ubidi_setLine() functions may modify some or all of the levels.
* After the UBiDi object is reused or destroyed, the caller
* must take care of the deallocation of the embeddingLevels array.
* The embeddingLevels array must be
* at least length long.
*
* @param pErrorCode must be a valid pointer to an error code value.
* @stable ICU 2.0
*/
U_STABLE void U_EXPORT2
ubidi_setPara(UBiDi *pBiDi, const UChar *text, int32_t length,
UBiDiLevel paraLevel, UBiDiLevel *embeddingLevels,
UErrorCode *pErrorCode);
/**
* ubidi_setLine() sets a UBiDi to
* contain the reordering information, especially the resolved levels,
* for all the characters in a line of text. This line of text is
* specified by referring to a UBiDi object representing
* this information for a piece of text containing one or more paragraphs,
* and by specifying a range of indexes in this text.
* In the new line object, the indexes will range from 0 to limit-start-1.
*
* This is used after calling ubidi_setPara()
* for a piece of text, and after line-breaking on that text.
* It is not necessary if each paragraph is treated as a single line.
*
* After line-breaking, rules (L1) and (L2) for the treatment of
* trailing WS and for reordering are performed on
* a UBiDi object that represents a line.
*
* Important: pLineBiDi shares data with
* pParaBiDi.
* You must destroy or reuse pLineBiDi before pParaBiDi.
* In other words, you must destroy or reuse the UBiDi object for a line
* before the object for its parent paragraph.
*
* The text pointer that was stored in pParaBiDi is also copied,
* and start is added to it so that it points to the beginning of the
* line for this object.
*
* @param pParaBiDi is the parent paragraph object. It must have been set
* by a successful call to ubidi_setPara.
*
* @param start is the line's first index into the text.
*
* @param limit is just behind the line's last index into the text
* (its last index +1).
* It must be 0<=start<=limit<=containing paragraph limit.
* If the specified line crosses a paragraph boundary, the function
* will terminate with error code U_ILLEGAL_ARGUMENT_ERROR.
*
* @param pLineBiDi is the object that will now represent a line of the text.
*
* @param pErrorCode must be a valid pointer to an error code value.
*
* @see ubidi_setPara
* @see ubidi_getProcessedLength
* @stable ICU 2.0
*/
U_STABLE void U_EXPORT2
ubidi_setLine(const UBiDi *pParaBiDi,
int32_t start, int32_t limit,
UBiDi *pLineBiDi,
UErrorCode *pErrorCode);
/**
* Get the directionality of the text.
*
* @param pBiDi is the paragraph or line UBiDi object.
*
* @return A UBIDI_XXX value that indicates if the entire text
* represented by this object is unidirectional,
* and which direction, or if it is mixed-directional.
*
* @see UBiDiDirection
* @stable ICU 2.0
*/
U_STABLE UBiDiDirection U_EXPORT2
ubidi_getDirection(const UBiDi *pBiDi);
/**
* Get the pointer to the text.
*
* @param pBiDi is the paragraph or line UBiDi object.
*
* @return The pointer to the text that the UBiDi object was created for.
*
* @see ubidi_setPara
* @see ubidi_setLine
* @stable ICU 2.0
*/
U_STABLE const UChar * U_EXPORT2
ubidi_getText(const UBiDi *pBiDi);
/**
* Get the length of the text.
*
* @param pBiDi is the paragraph or line UBiDi object.
*
* @return The length of the text that the UBiDi object was created for.
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
ubidi_getLength(const UBiDi *pBiDi);
/**
* Get the paragraph level of the text.
*
* @param pBiDi is the paragraph or line UBiDi object.
*
* @return The paragraph level. If there are multiple paragraphs, their
* level may vary if the required paraLevel is UBIDI_DEFAULT_LTR or
* UBIDI_DEFAULT_RTL. In that case, the level of the first paragraph
* is returned.
*
* @see UBiDiLevel
* @see ubidi_getParagraph
* @see ubidi_getParagraphByIndex
* @stable ICU 2.0
*/
U_STABLE UBiDiLevel U_EXPORT2
ubidi_getParaLevel(const UBiDi *pBiDi);
/**
* Get the number of paragraphs.
*
* @param pBiDi is the paragraph or line UBiDi object.
*
* @return The number of paragraphs.
* @stable ICU 3.4
*/
U_STABLE int32_t U_EXPORT2
ubidi_countParagraphs(UBiDi *pBiDi);
/**
* Get a paragraph, given a position within the text.
* This function returns information about a paragraph.
*
* @param pBiDi is the paragraph or line UBiDi object.
*
* @param charIndex is the index of a character within the text, in the
* range [0..ubidi_getProcessedLength(pBiDi)-1].
*
* @param pParaStart will receive the index of the first character of the
* paragraph in the text.
* This pointer can be NULL if this
* value is not necessary.
*
* @param pParaLimit will receive the limit of the paragraph.
* The l-value that you point to here may be the
* same expression (variable) as the one for
* charIndex.
* This pointer can be NULL if this
* value is not necessary.
*
* @param pParaLevel will receive the level of the paragraph.
* This pointer can be NULL if this
* value is not necessary.
*
* @param pErrorCode must be a valid pointer to an error code value.
*
* @return The index of the paragraph containing the specified position.
*
* @see ubidi_getProcessedLength
* @stable ICU 3.4
*/
U_STABLE int32_t U_EXPORT2
ubidi_getParagraph(const UBiDi *pBiDi, int32_t charIndex, int32_t *pParaStart,
int32_t *pParaLimit, UBiDiLevel *pParaLevel,
UErrorCode *pErrorCode);
/**
* Get a paragraph, given the index of this paragraph.
*
* This function returns information about a paragraph.
*
* @param pBiDi is the paragraph UBiDi object.
*
* @param paraIndex is the number of the paragraph, in the
* range [0..ubidi_countParagraphs(pBiDi)-1].
*
* @param pParaStart will receive the index of the first character of the
* paragraph in the text.
* This pointer can be NULL if this
* value is not necessary.
*
* @param pParaLimit will receive the limit of the paragraph.
* This pointer can be NULL if this
* value is not necessary.
*
* @param pParaLevel will receive the level of the paragraph.
* This pointer can be NULL if this
* value is not necessary.
*
* @param pErrorCode must be a valid pointer to an error code value.
*
* @stable ICU 3.4
*/
U_STABLE void U_EXPORT2
ubidi_getParagraphByIndex(const UBiDi *pBiDi, int32_t paraIndex,
int32_t *pParaStart, int32_t *pParaLimit,
UBiDiLevel *pParaLevel, UErrorCode *pErrorCode);
/**
* Get the level for one character.
*
* @param pBiDi is the paragraph or line UBiDi object.
*
* @param charIndex the index of a character.
*
* @return The level for the character at charIndex.
*
* @see UBiDiLevel
* @see ubidi_getProcessedLength
* @stable ICU 2.0
*/
U_STABLE UBiDiLevel U_EXPORT2
ubidi_getLevelAt(const UBiDi *pBiDi, int32_t charIndex);
/**
* Get an array of levels for each character.
*
* Note that this function may allocate memory under some
* circumstances, unlike ubidi_getLevelAt().
*
* @param pBiDi is the paragraph or line UBiDi object, whose
* text length must be strictly positive.
*
* @param pErrorCode must be a valid pointer to an error code value.
*
* @return The levels array for the text,
* or NULL if an error occurs.
*
* @see UBiDiLevel
* @see ubidi_getProcessedLength
* @stable ICU 2.0
*/
U_STABLE const UBiDiLevel * U_EXPORT2
ubidi_getLevels(UBiDi *pBiDi, UErrorCode *pErrorCode);
/**
* Get a logical run.
* This function returns information about a run and is used
* to retrieve runs in logical order.
* This is especially useful for line-breaking on a paragraph.
*
* @param pBiDi is the paragraph or line UBiDi object.
*
* @param logicalStart is the first character of the run.
*
* @param pLogicalLimit will receive the limit of the run.
* The l-value that you point to here may be the
* same expression (variable) as the one for
* logicalStart.
* This pointer can be NULL if this
* value is not necessary.
*
* @param pLevel will receive the level of the run.
* This pointer can be NULL if this
* value is not necessary.
*
* @see ubidi_getProcessedLength
* @stable ICU 2.0
*/
U_STABLE void U_EXPORT2
ubidi_getLogicalRun(const UBiDi *pBiDi, int32_t logicalStart,
int32_t *pLogicalLimit, UBiDiLevel *pLevel);
/**
* Get the number of runs.
* This function may invoke the actual reordering on the
* UBiDi object, after ubidi_setPara()
* may have resolved only the levels of the text. Therefore,
* ubidi_countRuns() may have to allocate memory,
* and may fail doing so.
*
* @param pBiDi is the paragraph or line UBiDi object.
*
* @param pErrorCode must be a valid pointer to an error code value.
*
* @return The number of runs.
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
ubidi_countRuns(UBiDi *pBiDi, UErrorCode *pErrorCode);
/**
* Get one run's logical start, length, and directionality,
* which can be 0 for LTR or 1 for RTL.
* In an RTL run, the character at the logical start is
* visually on the right of the displayed run.
* The length is the number of characters in the run.
* ubidi_countRuns() should be called
* before the runs are retrieved.
*
* @param pBiDi is the paragraph or line UBiDi object.
*
* @param runIndex is the number of the run in visual order, in the
* range [0..ubidi_countRuns(pBiDi)-1].
*
* @param pLogicalStart is the first logical character index in the text.
* The pointer may be NULL if this index is not needed.
*
* @param pLength is the number of characters (at least one) in the run.
* The pointer may be NULL if this is not needed.
*
* @return the directionality of the run,
* UBIDI_LTR==0 or UBIDI_RTL==1,
* never UBIDI_MIXED.
*
* @see ubidi_countRuns
*
* Example:
*