com.lowagie.text.pdf
Class ArabicLigaturizer

java.lang.Object
  com.lowagie.text.pdf.ArabicLigaturizer

public class ArabicLigaturizer
extends Object

Shape arabic characters. This code was inspired by an LGPL'ed C library: Pango ( see http://www.pango.com/ ). Note that the code of this is the original work of Paulo Soares. Hence it is perfectly justifiable to distribute it under the MPL.

Author:

Paulo Soares (psoares@consiste.pt)

Nested Class Summary

(package private) static class

ArabicLigaturizer.charstruct

Field Summary

private static char	ALEF
private static char	ALEFHAMZA
private static char	ALEFHAMZABELOW
private static char	ALEFMADDA
private static char	ALEFMAKSURA
static int	ar_composedtashkeel
static int	ar_lig
static int	ar_nothing
static int	ar_novowel
private static char[][]	chartable
private static char	DAMMA
static int	DIGIT_TYPE_AN Digit type option: Use Arabic-Indic digits (U+0660...U+0669).
static int	DIGIT_TYPE_AN_EXTENDED Digit type option: Use Eastern (Extended) Arabic-Indic digits (U+06f0...U+06f9).
static int	DIGIT_TYPE_MASK Bit mask for digit type options.
static int	DIGITS_AN2EN Digit shaping option: Replace Arabic-Indic digits by European digits (U+0030...U+0039).
static int	DIGITS_EN2AN Digit shaping option: Replace European digits (U+0030...U+0039) by Arabic-Indic digits.
static int	DIGITS_EN2AN_INIT_AL Digit shaping option: Replace European digits (U+0030...U+0039) by Arabic-Indic digits if the most recent strongly directional character is an Arabic letter (its Bidi direction value is RIGHT_TO_LEFT_ARABIC).
static int	DIGITS_EN2AN_INIT_LR Digit shaping option: Replace European digits (U+0030...U+0039) by Arabic-Indic digits if the most recent strongly directional character is an Arabic letter (its Bidi direction value is RIGHT_TO_LEFT_ARABIC).
static int	DIGITS_MASK Bit mask for digit shaping options.
private static int	DIGITS_RESERVED Not a valid option value.
private static char	FARSIYEH
private static char	FATHA
private static char	HAMZA
private static char	HAMZAABOVE
private static char	HAMZABELOW
private static char	KASRA
private static char	LAM
private static char	LAM_ALEF
private static char	LAM_ALEFHAMZA
private static char	LAM_ALEFHAMZABELOW
private static char	LAM_ALEFMADDA
private static char	MADDA
private static char	SHADDA
private static char	TATWEEL
private static char	WAW
private static char	WAWHAMZA
private static char	YEH
private static char	YEHHAMZA
private static char	ZWJ

Constructor Summary

ArabicLigaturizer()

Method Summary

(package private) static int	arabic_shape(char[] src, int srcoffset, int srclength, char[] dest, int destoffset, int destlength, int level)
(package private) static char	charshape(char s, int which)
(package private) static boolean	connects_to_left(ArabicLigaturizer.charstruct a)
(package private) static void	copycstostring(StringBuffer string, ArabicLigaturizer.charstruct s, int level)
(package private) static void	doublelig(StringBuffer string, int level)
(package private) static boolean	isVowel(char s)
(package private) static int	ligature(char newchar, ArabicLigaturizer.charstruct oldchar)
(package private) static void	processNumbers(char[] text, int offset, int length, int options)
(package private) static void	shape(char[] text, StringBuffer string, int level)
(package private) static int	shapecount(char s)
(package private) static void	shapeToArabicDigitsWithContext(char[] dest, int start, int length, char digitBase, boolean lastStrongWasAL)

Methods inherited from class java.lang.Object

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

Field Detail

ALEF

private static final char ALEF

See Also:

Constant Field Values

ALEFHAMZA

private static final char ALEFHAMZA

See Also:

Constant Field Values

ALEFHAMZABELOW

private static final char ALEFHAMZABELOW

See Also:

Constant Field Values

ALEFMADDA

private static final char ALEFMADDA

See Also:

Constant Field Values

LAM

private static final char LAM

See Also:

Constant Field Values

HAMZA

private static final char HAMZA

See Also:

Constant Field Values

TATWEEL

private static final char TATWEEL

See Also:

Constant Field Values

ZWJ

private static final char ZWJ

See Also:

Constant Field Values

HAMZAABOVE

private static final char HAMZAABOVE

See Also:

Constant Field Values

HAMZABELOW

private static final char HAMZABELOW

See Also:

Constant Field Values

WAWHAMZA

private static final char WAWHAMZA

See Also:

Constant Field Values

YEHHAMZA

private static final char YEHHAMZA

See Also:

Constant Field Values

WAW

private static final char WAW

See Also:

Constant Field Values

ALEFMAKSURA

private static final char ALEFMAKSURA

See Also:

Constant Field Values

YEH

private static final char YEH

See Also:

Constant Field Values

FARSIYEH

private static final char FARSIYEH

See Also:

Constant Field Values

SHADDA

private static final char SHADDA

See Also:

Constant Field Values

KASRA

private static final char KASRA

See Also:

Constant Field Values

FATHA

private static final char FATHA

See Also:

Constant Field Values

DAMMA

private static final char DAMMA

See Also:

Constant Field Values

MADDA

private static final char MADDA

See Also:

Constant Field Values

LAM_ALEF

private static final char LAM_ALEF

See Also:

Constant Field Values

LAM_ALEFHAMZA

private static final char LAM_ALEFHAMZA

See Also:

Constant Field Values

LAM_ALEFHAMZABELOW

private static final char LAM_ALEFHAMZABELOW

See Also:

Constant Field Values

LAM_ALEFMADDA

private static final char LAM_ALEFMADDA

See Also:

Constant Field Values

chartable

private static final char[][] chartable

ar_nothing

public static final int ar_nothing

See Also:

Constant Field Values

ar_novowel

public static final int ar_novowel

See Also:

Constant Field Values

ar_composedtashkeel

public static final int ar_composedtashkeel

See Also:

Constant Field Values

ar_lig

public static final int ar_lig

See Also:

Constant Field Values

DIGITS_EN2AN

public static final int DIGITS_EN2AN

Digit shaping option: Replace European digits (U+0030...U+0039) by Arabic-Indic digits.

See Also:

Constant Field Values

DIGITS_AN2EN

public static final int DIGITS_AN2EN

Digit shaping option: Replace Arabic-Indic digits by European digits (U+0030...U+0039).

See Also:

Constant Field Values

DIGITS_EN2AN_INIT_LR

public static final int DIGITS_EN2AN_INIT_LR

Digit shaping option: Replace European digits (U+0030...U+0039) by Arabic-Indic digits if the most recent strongly directional character is an Arabic letter (its Bidi direction value is RIGHT_TO_LEFT_ARABIC). The initial state at the start of the text is assumed to be not an Arabic, letter, so European digits at the start of the text will not change. Compare to DIGITS_ALEN2AN_INIT_AL.

See Also:

Constant Field Values

DIGITS_EN2AN_INIT_AL

public static final int DIGITS_EN2AN_INIT_AL

Digit shaping option: Replace European digits (U+0030...U+0039) by Arabic-Indic digits if the most recent strongly directional character is an Arabic letter (its Bidi direction value is RIGHT_TO_LEFT_ARABIC). The initial state at the start of the text is assumed to be an Arabic, letter, so European digits at the start of the text will change. Compare to DIGITS_ALEN2AN_INT_LR.

See Also:

Constant Field Values

DIGITS_RESERVED

private static final int DIGITS_RESERVED

Not a valid option value.

See Also:

Constant Field Values

DIGITS_MASK

public static final int DIGITS_MASK

Bit mask for digit shaping options.

See Also:

Constant Field Values

DIGIT_TYPE_AN

public static final int DIGIT_TYPE_AN

Digit type option: Use Arabic-Indic digits (U+0660...U+0669).

See Also:

Constant Field Values

DIGIT_TYPE_AN_EXTENDED

public static final int DIGIT_TYPE_AN_EXTENDED

Digit type option: Use Eastern (Extended) Arabic-Indic digits (U+06f0...U+06f9).

See Also:

Constant Field Values

DIGIT_TYPE_MASK

public static final int DIGIT_TYPE_MASK

Bit mask for digit type options.

See Also:

Constant Field Values

Constructor Detail

ArabicLigaturizer

public ArabicLigaturizer()

Method Detail

isVowel

static boolean isVowel(char s)

charshape

static char charshape(char s,
                      int which)

shapecount

static int shapecount(char s)

ligature

static int ligature(char newchar,
                    ArabicLigaturizer.charstruct oldchar)

copycstostring

static void copycstostring(StringBuffer string,
                           ArabicLigaturizer.charstruct s,
                           int level)

doublelig

static void doublelig(StringBuffer string,
                      int level)

connects_to_left

static boolean connects_to_left(ArabicLigaturizer.charstruct a)

shape

static void shape(char[] text,
                  StringBuffer string,
                  int level)

arabic_shape

static int arabic_shape(char[] src,
                        int srcoffset,
                        int srclength,
                        char[] dest,
                        int destoffset,
                        int destlength,
                        int level)

processNumbers

static void processNumbers(char[] text,
                           int offset,
                           int length,
                           int options)

shapeToArabicDigitsWithContext

static void shapeToArabicDigitsWithContext(char[] dest,
                                           int start,
                                           int length,
                                           char digitBase,
                                           boolean lastStrongWasAL)