Package com.aowagie.text.pdf

Class BidiOrder

java.lang.Object

com.aowagie.text.pdf.BidiOrder

final class BidiOrder
extends Object

Reference implementation of the Unicode 3.0 Bidi algorithm.

This implementation is not optimized for performance. It is intended as a reference implementation that closely follows the specification of the Bidirectional Algorithm in The Unicode Standard version 3.0.

Input:
There are two levels of input to the algorithm, since clients may prefer to supply some information from out-of-band sources rather than relying on the default behavior.

1. unicode type array
2. unicode type array, with externally supplied base line direction

Output:
Output is separated into several stages as well, to better enable clients to evaluate various aspects of implementation conformance.

1. levels array over entire paragraph
2. reordering array over entire paragraph
3. levels array over line
4. reordering array over line

Note that for conformance, algorithms are only required to generate correct reordering and character directionality (odd or even levels) over a line. Generating identical level arrays over a line is not required. Bidi explicit format codes (LRE, RLE, LRO, RLO, PDF) and BN can be assigned arbitrary levels and positions as long as the other text matches.

As the algorithm is defined to operate on a single paragraph at a time, this implementation is written to handle single paragraphs. Thus rule P1 is presumed by this implementation-- the data provided to the implementation is assumed to be a single paragraph, and either contains no 'B' codes, or a single 'B' code at the end of the input. 'B' is allowed as input to illustrate how the algorithm assigns it a level.

Also note that rules L3 and L4 depend on the rendering engine that uses the result of the bidi algorithm. This implementation assumes that the rendering engine expects combining marks in visual order (e.g. to the left of their base character in RTL runs) and that it adjust the glyphs used to render mirrored characters that are in RTL runs so that they render appropriately.

Field Summary

Fields

Modifier and Type	Field	Description
static final byte	AL	Right-to-Left Arabic
private static final byte	AN	Arabic Number
private static final byte	B	Paragraph Separator
private static char[]	baseTypes
private static final byte	BN	Boundary Neutral
private static final byte	CS	Common Number Separator
private byte[]	embeddings
static final byte	EN	European Number
private static final byte	ES	European Number Separator
private static final byte	ET	European Number Terminator
private final byte[]	initialTypes
static final byte	L	Left-to-right
private static final byte	LRE	Left-to-Right Embedding
private static final byte	LRO	Left-to-Right Override
private static final byte	NSM	Non-Spacing Mark
private static final byte	ON	Other Neutrals
private byte	paragraphEmbeddingLevel
private static final byte	PDF	Pop Directional Format
static final byte	R	Right-to-Left
private byte[]	resultLevels
private byte[]	resultTypes
private static final byte	RLE	Right-to-Left Embedding
private static final byte	RLO	Right-to-Left Override
private static final byte[]	rtypes
private static final byte	S	Segment Separator
private int	textLength
private static final byte	TYPE_MAX	Maximum bidi type value.
private static final byte	TYPE_MIN	Minimum bidi type value.
private static final byte	WS	Whitespace

Constructor Summary

Constructors

Constructor	Description
BidiOrder(char[] text, int offset, int length, byte paragraphEmbeddingLevel)

Method Summary

Modifier and Type	Method	Description
private static int[]	computeMultilineReordering(byte[] levels, int[] linebreaks)	Return multiline reordering array for a given level array.
private static int[]	computeReordering(byte[] levels)	Return reordering array for a given level array.
private void	determineExplicitEmbeddingLevels()	Process embedding format codes.
private void	determineParagraphEmbeddingLevel()	1) determining the paragraph level.
private int	findRunLimit(int index, int limit, byte[] validSet)	Return the limit of the run starting at index that includes only resultTypes in validSet.
private int	findRunStart(int index, byte[] validSet)	Return the start of the run including index that includes only resultTypes in validSet.
byte	getBaseLevel()	Return the base level of the paragraph.
(package private) static final byte	getDirection(char c)
byte[]	getLevels()
private byte[]	getLevels(int[] linebreaks)	Return levels array breaking lines at offsets in linebreaks.
private static boolean	isWhitespace(byte biditype)	Return true if the type is considered a whitespace type for the line break rules.
private static byte[]	processEmbeddings(byte[] resultTypes, byte paragraphEmbeddingLevel)	2) determining explicit levels Rules X1 - X8 The interaction of these rules makes handling them a bit complex.
private int	reinsertExplicitCodes(int textLength)	Reinsert levels information for explicit codes.
private int	removeExplicitCodes()	Rules X9.
private void	resolveImplicitLevels(int start, int limit, byte level, byte sor, byte eor)	7) resolving implicit embedding levels Rules I1, I2.
private void	resolveNeutralTypes(int start, int limit, byte level, byte sor, byte eor)	6) resolving neutral types Rules N1-N2.
private void	resolveWeakTypes(int start, int limit, byte level, byte sor, byte eor)	3) resolving weak types Rules W1-W7.
private void	runAlgorithm()	The algorithm.
private void	setLevels(int start, int limit, byte newLevel)	Set resultLevels from start up to (but not including) limit to newLevel.
private void	setTypes(int start, int limit, byte newType)	Set resultTypes from start up to (but not including) limit to newType.
private static byte	typeForLevel(int level)	Return the strong type (L or R) corresponding to the level.
private static void	validateLineBreaks(int[] linebreaks, int textLength)	Throw exception if line breaks array is invalid.
private static void	validateParagraphEmbeddingLevel(byte paragraphEmbeddingLevel)	Throw exception if paragraph embedding level is invalid.
private static void	validateTypes(byte[] types)	Throw exception if type array is invalid.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Details

initialTypes

private final byte[] initialTypes

embeddings

private byte[] embeddings

paragraphEmbeddingLevel

private byte paragraphEmbeddingLevel

textLength

private int textLength

resultTypes

private byte[] resultTypes

resultLevels

private byte[] resultLevels

L

public static final byte L

Left-to-right

See Also:

• Constant Field Values

LRE

private static final byte LRE

Left-to-Right Embedding

See Also:

• Constant Field Values

LRO

private static final byte LRO

Left-to-Right Override

See Also:

• Constant Field Values

R

public static final byte R

Right-to-Left

See Also:

• Constant Field Values

AL

public static final byte AL

Right-to-Left Arabic

See Also:

• Constant Field Values

RLE

private static final byte RLE

Right-to-Left Embedding

See Also:

• Constant Field Values

RLO

private static final byte RLO

Right-to-Left Override

See Also:

• Constant Field Values

PDF

private static final byte PDF

Pop Directional Format

See Also:

• Constant Field Values

EN

public static final byte EN

European Number

See Also:

• Constant Field Values

ES

private static final byte ES

European Number Separator

See Also:

• Constant Field Values

ET

private static final byte ET

European Number Terminator

See Also:

• Constant Field Values

AN

private static final byte AN

Arabic Number

See Also:

• Constant Field Values

CS

private static final byte CS

Common Number Separator

See Also:

• Constant Field Values

NSM

private static final byte NSM

Non-Spacing Mark

See Also:

• Constant Field Values

BN

private static final byte BN

Boundary Neutral

See Also:

• Constant Field Values

B

private static final byte B

Paragraph Separator

See Also:

• Constant Field Values

S

private static final byte S

Segment Separator

See Also:

• Constant Field Values

WS

private static final byte WS

Whitespace

See Also:

• Constant Field Values

ON

private static final byte ON

Other Neutrals

See Also:

• Constant Field Values

TYPE_MIN

private static final byte TYPE_MIN

Minimum bidi type value.

See Also:

• Constant Field Values

TYPE_MAX

private static final byte TYPE_MAX

Maximum bidi type value.

See Also:

• Constant Field Values

rtypes

private static final byte[] rtypes

baseTypes

private static char[] baseTypes

Constructor Details

BidiOrder

BidiOrder(char[] text,
 int offset,
 int length,
 byte paragraphEmbeddingLevel)

Method Details

getDirection

static final byte getDirection(char c)

runAlgorithm

private void runAlgorithm()

The algorithm. Does not include line-based processing (Rules L1, L2). These are applied later in the line-based phase of the algorithm.

determineParagraphEmbeddingLevel

private void determineParagraphEmbeddingLevel()

1) determining the paragraph level.

Rules P2, P3.

At the end of this function, the member variable paragraphEmbeddingLevel is set to either 0 or 1.

determineExplicitEmbeddingLevels

private void determineExplicitEmbeddingLevels()

Process embedding format codes.

Calls processEmbeddings to generate an embedding array from the explicit format codes. The embedding overrides in the array are then applied to the result types, and the result levels are initialized.

See Also:

• processEmbeddings(byte[], byte)

removeExplicitCodes

private int removeExplicitCodes()

Rules X9. Remove explicit codes so that they may be ignored during the remainder of the main portion of the algorithm. The length of the resulting text is returned.

Returns:

the length of the data excluding explicit codes and BN.

reinsertExplicitCodes

private int reinsertExplicitCodes(int textLength)

Reinsert levels information for explicit codes. This is for ease of relating the level information to the original input data. Note that the levels assigned to these codes are arbitrary, they're chosen so as to avoid breaking level runs.

Parameters:

textLength - the length of the data after compression

Returns:

the length of the data (original length of types array supplied to constructor)

processEmbeddings

private static byte[] processEmbeddings(byte[] resultTypes,
 byte paragraphEmbeddingLevel)

2) determining explicit levels Rules X1 - X8 The interaction of these rules makes handling them a bit complex. This examines resultTypes but does not modify it. It returns embedding and override information in the result array. The low 7 bits are the level, the high bit is set if the level is an override, and clear if it is an embedding.

resolveWeakTypes

private void resolveWeakTypes(int start,
 int limit,
 byte level,
 byte sor,
 byte eor)

3) resolving weak types Rules W1-W7. Note that some weak types (EN, AN) remain after this processing is complete.

resolveNeutralTypes

private void resolveNeutralTypes(int start,
 int limit,
 byte level,
 byte sor,
 byte eor)

6) resolving neutral types Rules N1-N2.

resolveImplicitLevels

private void resolveImplicitLevels(int start,
 int limit,
 byte level,
 byte sor,
 byte eor)

7) resolving implicit embedding levels Rules I1, I2.

getLevels

public byte[] getLevels()

getLevels

private byte[] getLevels(int[] linebreaks)

Return levels array breaking lines at offsets in linebreaks.
Rule L1.

The returned levels array contains the resolved level for each bidi code passed to the constructor.

The linebreaks array must include at least one value. The values must be in strictly increasing order (no duplicates) between 1 and the length of the text, inclusive. The last value must be the length of the text.

Parameters:

linebreaks - the offsets at which to break the paragraph

Returns:

the resolved levels of the text

computeMultilineReordering

private static int[] computeMultilineReordering(byte[] levels,
 int[] linebreaks)

Return multiline reordering array for a given level array. Reordering does not occur across a line break.

computeReordering

private static int[] computeReordering(byte[] levels)

Return reordering array for a given level array. This reorders a single line. The reordering is a visual to logical map. For example, the leftmost char is string.charAt(order[0]). Rule L2.

getBaseLevel

public byte getBaseLevel()

Return the base level of the paragraph.

isWhitespace

private static boolean isWhitespace(byte biditype)

Return true if the type is considered a whitespace type for the line break rules.

typeForLevel

private static byte typeForLevel(int level)

Return the strong type (L or R) corresponding to the level.

findRunLimit

private int findRunLimit(int index,
 int limit,
 byte[] validSet)

Return the limit of the run starting at index that includes only resultTypes in validSet. This checks the value at index, and will return index if that value is not in validSet.

findRunStart

private int findRunStart(int index,
 byte[] validSet)

Return the start of the run including index that includes only resultTypes in validSet. This assumes the value at index is valid, and does not check it.

setTypes

private void setTypes(int start,
 int limit,
 byte newType)

Set resultTypes from start up to (but not including) limit to newType.

setLevels

private void setLevels(int start,
 int limit,
 byte newLevel)

Set resultLevels from start up to (but not including) limit to newLevel.

validateTypes

private static void validateTypes(byte[] types)

Throw exception if type array is invalid.

validateParagraphEmbeddingLevel

private static void validateParagraphEmbeddingLevel(byte paragraphEmbeddingLevel)

Throw exception if paragraph embedding level is invalid. Special allowance for -1 so that default processing can still be performed when using this API.

validateLineBreaks

private static void validateLineBreaks(int[] linebreaks,
 int textLength)

Throw exception if line breaks array is invalid.