yudit-common 2.9.6-7 / usr / share / yudit / src / ArabicBuck.kmap

// ArabicBuck.kmap

// Kenneth R. Beesley, 2003-01-19
// revised 2003-02-06
// revised 2003-02-11
// revised 2003-02-17 
// revixed 2003-02-20 version 1.0

// kmap to allow use of Buckwalter Transliteration
// (see http://www.xrce.xerox.com/competencies/content-analysis/arabic/info/buckwalter-about.html)
// for inputting Arabic to yudit (and perhaps someday to qemacs)

//             Philosophy of the Input Method:

// 1.  When ArabicBuck is chosen as the input method, the assumption is 
//     that the user wants to enter Arabic letters, Arabic punctuation and 
//     ARABIC-INDIC style digits.

// 2.  To allow input of ASCII (without changing the whole input method back
//     to 'straight') the Arabic assumption can be overridden temporarily
//     inside ArabicBuck by preposing a backslash to "literalize" or
//     ASCII-ize the symbol being typed. 
 
//     Thus when ArabicBuck is active, the user usually types a 'b' to input
//     0x0628, the Arabic baa' letter; but one can also type \b to get an
//     ASCII 'b' letter.  Similarly, one can type \, to get an ASCII
//     comma (rather than an Arabic comma), \3 to get a European/ASCII '3'
//     rather than an ARABIC-INDIC style 3, etc.

// this file ArabicBuck.kmap and the ArabicBuck.my file produced from it
// (see below) will be included and ready-to-go in some future release of Yudit.

// For now, this ArabicBuck.kmap file should be copied into the directory
//    <prefix>/share/yudit/src/
// or perhaps in your personal ~/.yudit/src/
//
// This ArabicBuck.kmap source file must used to create a .my file thus, 
// using the 'mytool' program supplied with yudit:

// $ mytool -type kmap -kmap ArabicBuck.kmap -rkmap ArabicBuck.kmap -write ArabicBuck.my

// This command should produce ArabicBuck.my, which should be
// copied into your personal directory ~/.yudit/data/  
// and perhaps into <prefix>/share/yudit/data/ to make it visible to other users

// yudit directly uses the .my file, not the .kmap file


// *********************************************************************
// *********************************************************************
// *********************************************************************

// the following mappings are organized (mostly) in Unicode order

// Arabic Punctuation (early in the Unicode chart; more punctuation below)
" , = 0x060c " , // ARABIC COMMA
" ; = 0x061b " , // ARABIC SEMICOLON 
" ? = 0x061f " , // ARABIC QUESTION MARK 

// Letters
" ' = 0x0621 " , // ARABIC LETTER HAMZA (hamza on the line)
" | = 0x0622 " , // ARABIC LETTER ALEF WITH MADDA ABOVE
" > = 0x0623 " , // ARABIC LETTER ALEF WITH HAMZA ABOVE
" & = 0x0624 " , // ARABIC LETTER WAW WITH HAMZA ABOVE
" < = 0x0625 " , // ARABIC LETTER ALEF WITH HAMZA BELOW
" } = 0x0626 " , // ARABIC LETTER YEH WITH HAMZA ABOVE

" A = 0x0627 " , // ARABIC LETTER ALEF (bare 'alif)
" b = 0x0628 " , // ARABIC LETTER BEH  (baa')
" p = 0x0629 " , // ARABIC LETTER TEH MARBUTA (taa' marbuuTa)
" t = 0x062a " , // ARABIC LETTER TEH  (taa')
" v = 0x062b " , // ARABIC LETTER THEH (thaa')
" j = 0x062c " , // ARABIC LETTER JEEM (jiim)
" H = 0x062d " , // ARABIC LETTER HAH  (Haa') voiceless pharyngeal fricative
" x = 0x062e " , // ARABIC LETTER KHAH (xaa' or khaa') 
		 // voiceless velar fricative, e.g. German ch in Bach
" d = 0x062f " , // ARABIC LETTER DAL  (daal)
" * = 0x0630 " , // ARABIC LETTER THAL (dhaal)
" r = 0x0631 " , // ARABIC LETTER REH  (raa')
" z = 0x0632 " , // ARABIC LETTER ZAIN
" s = 0x0633 " , // ARABIC LETTER SEEN (siin)
" $ = 0x0634 " , // ARABIC LETTER SHEEN (shiin)
" S = 0x0635 " , // ARABIC LETTER SAD (Saad)
" D = 0x0636 " , // ARABIC LETTER DAD (Daad)
" T = 0x0637 " , // ARABIC LETTER TAH (Taa')
" Z = 0x0638 " , // ARABIC LETTER ZAH (Zaa' or DHaa')
" E = 0x0639 " , // ARABIC LETTER AIN (Eayn or cayn)
	         // voiced pharyngeal fricative
" g = 0x063a " , // ARABIC LETTER GHAIN
	         // voiced velar fricative (like Parisian R)
" _ = 0x0640 " , // ARABIC TATWEEL (taTwiil)

" f = 0x0641 " , // ARABIC LETTER FEH (faa')
" q = 0x0642 " , // ARABIC LETTER QAF (qaaf)
" k = 0x0643 " , // ARABIC LETTER KAF (kaaf)
" l = 0x0644 " , // ARABIC LETTER LAM (laam)
" m = 0x0645 " , // ARABIC LETTER MEEM (miim)
" n = 0x0646 " , // ARABIC LETTER NOON (nuun)
" h = 0x0647 " , // ARABIC LETTER HEH (haa') like English /h/
" w = 0x0648 " , // ARABIC LETTER WAW (waaw)
" Y = 0x0649 " , // ARABIC LETTER ALEF MAKSURA ('alif maqSuura)
" y = 0x064a " , // ARABIC LETTER YEH

" F = 0x064b " , // ARABIC FATHATAN
" N = 0x064c " , // ARABIC DAMMATAN
" K = 0x064d " , // ARABIC KASRATAN
" a = 0x064e " , // ARABIC FATHA
" u = 0x064f " , // ARABIC DAMMA
" i = 0x0650 " , // ARABIC KASRA
" ~ = 0x0651 " , // ARABIC SHADDA
" o = 0x0652 " , // ARABIC SUKUN

// Arabic-Indic Digits
// need numeric value on left, just 0, 1, 2 etc.
// would be interpreted as numbers, not letters
" 0x30 = 0x0660 " , // ARABIC-INDIC DIGIT ZERO
" 0x31 = 0x0661 " , // ARABIC-INDIC DIGIT ONE
" 0x32 = 0x0662 " , // ARABIC-INDIC DIGIT TWO
" 0x33 = 0x0663 " , // ARABIC-INDIC DIGIT THREE
" 0x34 = 0x0664 " , // ARABIC-INDIC DIGIT FOUR
" 0x35 = 0x0665 " , // ARABIC-INDIC DIGIT FIVE
" 0x36 = 0x0666 " , // ARABIC-INDIC DIGIT SIX
" 0x37 = 0x0667 " , // ARABIC-INDIC DIGIT SEVEN
" 0x38 = 0x0668 " , // ARABIC-INDIC DIGIT EIGHT
" 0x39 = 0x0669 " , // ARABIC-INDIC DIGIT NINE

// Punctuation
" % = 0x066a " , // ARABIC PERCENT SIGN

// Number punctuation
" ADS  = 0x066b " , // ARABIC DECIMAL SEPARATOR ("decimal point")
         // Tim Buckwalter says: 
	 // this looks like a miniature raa' (0x0631);
	 // the letter raa' is sometimes used as a decimal
	 // separator in 8-bit texts

" ATS  = 0x066c " , // ARABIC THOUSANDS SEPARATOR
         // Tim Buckwalter has never seen this one

" AFPS = 0x066d " , // ARABIC FIVE POINTED STAR

// " Point", and one Extended Arabic Letter
" ` = 0x0670 " , // ARABIC LETTER SUPERSCRIPT ALEF ("dagger 'alif")
" { = 0x0671 " , // ARABIC LETTER ALEF WITH WAVY HAMZA ABOVE (waSla on 'alif)

//*******************************************************************
// Literalized Inputs--to allow the temporary overriding of the
// mappings shown above, without having to switch to a different input
// method; input the literal ASCII character by preceding
// the input with the backslash "literalizer"
//*******************************************************************

// Literal ASCII punctuation
" \\ , = 0x002c " , // COMMA
" \\ ; = 0x003b " , // SEMICOLON 
" \\ ? = 0x003f " , // QUESTION MARK 

// Literal ASCII letters
" \\ ' = 0x0027 " , // "literal" ASCII '
" \\ | = 0x007c " , // "literal" ASCII |
" \\ > = 0x003e " , // "literal" ASCII >
" \\ & = 0x0026 " , // "literal" ASCII &
" \\ < = 0x003c " , // "literal" ASCII <
" \\ } = 0x007d " , // "literal" ASCII }

" \\ A = 0x0041 " , // "literal" ASCII A
" \\ b = 0x0062 " , // "literal" ASCII b
" \\ p = 0x0070 " , // "literal" ASCII p
" \\ t = 0x0074 " , // "literal" ASCII t
" \\ v = 0x0076 " , // "literal" ASCII v
" \\ j = 0x006a " , // "literal" ASCII j
" \\ H = 0x0048 " , // "literal" ASCII H
" \\ x = 0x0078 " , // "literal" ASCII x
" \\ d = 0x0064 " , // "literal" ASCII d
" \\ * = 0x002a " , // "literal" ASCII *
" \\ r = 0x0072 " , // "literal" ASCII r
" \\ z = 0x007a " , // "literal" ASCII z
" \\ s = 0x0073 " , // "literal" ASCII s
" \\ $ = 0x0024 " , // "literal" ASCII $
" \\ S = 0x0053 " , // "literal" ASCII S
" \\ D = 0x0044 " , // "literal" ASCII D
" \\ T = 0x0054 " , // "literal" ASCII T
" \\ Z = 0x005a " , // "literal" ASCII Z
" \\ E = 0x0045 " , // "literal" ASCII E
" \\ g = 0x0067 " , // "literal" ASCII g

" \\ _ = 0x005f " , // "literal" ASCII _

" \\ f = 0x0066 " , // "literal" ASCII f
" \\ q = 0x0071 " , // "literal" ASCII q
" \\ k = 0x006b " , // "literal" ASCII k
" \\ l = 0x006c " , // "literal" ASCII l
" \\ m = 0x006d " , // "literal" ASCII m
" \\ n = 0x006e " , // "literal" ASCII n
" \\ h = 0x0068 " , // "literal" ASCII h
" \\ w = 0x0077 " , // "literal" ASCII w
" \\ Y = 0x0059 " , // "literal" ASCII Y
" \\ y = 0x0079 " , // "literal" ASCII y

" \\ F = 0x0046 " , // "literal" ASCII F
" \\ N = 0x004e " , // "literal" ASCII N
" \\ K = 0x004b " , // "literal" ASCII K
" \\ a = 0x0061 " , // "literal" ASCII a
" \\ u = 0x0075 " , // "literal" ASCII u
" \\ i = 0x0069 " , // "literal" ASCII i
" \\ ~ = 0x007e " , // "literal" ASCII ~
" \\ o = 0x006f " , // "literal" ASCII o

// For ASCII Digits
" \\ 0x30 = 0x0030 " , // DIGIT ZERO
" \\ 0x31 = 0x0031 " , // DIGIT ONE
" \\ 0x32 = 0x0032 " , // DIGIT TWO
" \\ 0x33 = 0x0033 " , // DIGIT THREE
" \\ 0x34 = 0x0034 " , // DIGIT FOUR
" \\ 0x35 = 0x0035 " , // DIGIT FIVE
" \\ 0x36 = 0x0036 " , // DIGIT SIX
" \\ 0x37 = 0x0037 " , // DIGIT SEVEN
" \\ 0x38 = 0x0038 " , // DIGIT EIGHT
" \\ 0x39 = 0x0039 " , // DIGIT NINE

// Punctuation
" \\ % = 0x0025 " ,    // PERCENT SIGN

" \\ ` = 0x0060 " ,    // "literal" ASCII `
" \\ { = 0x007b " ,    // "literal" ASCII {

" \\ \\ = 0x005c " ,   // "literal" ASCII \ (backslash)


//***********************************************************************
//  Joiner and Direction characters
//***********************************************************************

// Joiners
" ZWNJ = 0x200c" , //   ZERO WIDTH NON-JOINER
" ZWJ  = 0x200d" , //   ZERO WIDTH JOINER

// Explicit direction
" LTR = 0x200e " , //   LEFT-TO-RIGHT MARK
" RTL = 0x200f " , //   RIGHT-TO-LEFT MARK

// Directional Embedding
" LRE = 0x202a " ,  // LEFT TO RIGHT EMBEDDING
" RLE = 0x202b " ,  // RIGHT TO LEFT EMBEDDING
" PDF = 0x202c " ,  // POP DIRECTIONAL FORMAT
" LRO = 0x202d " ,  // LEFT TO RIGHT OVERRIDE
" RLO = 0x202e " ,  // RIGHT TO LEFT OVERRIDE

// Possible future additions for Persian and other "foreign" words/sounds
// seen in other kmap files for Arabic

// 06af  ARABIC LETTER GAF    Persian, Urdu
// 0681  ARABIC LETTER HAH WITH HAMZA ABOVE
// 067e  ARABIC LETTER PEH   Persian, Urdu...
// 0686  ARABIC LETTER TCHECH Persian
// 06a4  ARABIC LETTER VEH  in Arabic, for foreign words
// 0698  ARABIC LETTER JEH  Persian, Urdu


// Shaping info (copied from other Arabic kmap files)
// no longer necessary

//" l | = 0x0644 0x0622" ,
//" l > = 0x0644 0x0623" ,
//" l < = 0x0644 0x0625" ,
//" l A = 0x0644 0x0627" ,

// end of shaping info

// quote from Gaspar, Jan 2003
//   "Please note: in fact in yudit 2.7.+ you don't need to have it
//   because additional characters and diacritics will automatically be
//   added to form a ligature, so in fact the aforementioned ligature
//   can be entered by simply inputting the components."