scriptshifter/scriptshifter/tables/data/arabic.yml

# Arabic S2R using the 3rd-party ArabicTransliterator library:
# https://github.com/MTG/ArabicTransliterator

---
general:
  name: Arabic
  description: Arabic R2S using a conversion table and S2R using a 3rd party library.
  case_sensitive: false

  parents:
    - _ignore_base


roman_to_script:
  map:

    # Original table by David Bucknum
    # Last updated 25 January 2019
    # Modified by WK with testing by Arabic Cat Staff LOC-CAIRO
    # Additional info from R. Vassie, [n.d.] "Marrying the Arabic and Latin Scripts Conceptually"

    # Punctuation marks:
    "*": "\u066D"
    ",": "\u060C"
    ";": "\u061B"
    "?": "\u061F"

    # Exceptions for specific words
    # Allah
    "Alla\u0304h": "\u0627\u0644\u0644\u0647"

    # Qur'an
    "Qur\u02BCa\u0304n": "\u0642\u0631\u0622\u0646"

    # lillah
    "lilla\u0304h": "\u0644\u0644\u0647"

    # billah
    "billa\u0304h": "\u0628\u0644\u0644\u0647"

    # Rahman
    "Rah\u0323ma\u0304n": "\u0631\u062D\u0645\u0646"

    # Ruwat
    "Ruwa\u0304t": "\u0631\u0648\u0627\u0629"
    "ruwa\u0304t": "\u0631\u0648\u0627\u0629"

    # Hadha
    "Ha\u0304dha\u0304": "\u0647\u0630\u0627"
    "ha\u0304dha\u0304": "\u0647\u0630\u0627"

    # Hadhihi
    "Ha\u0304dhi\u0304hi": "\u0647\u0630\u0647"
    "ha\u0304dhi\u0304hi": "\u0647\u0630\u0647"

    # dhalika
    "dha\u0304lika": "\u0630\u0644\u0643"

    # Ibn when it appears in the middle of a name sequence
    "ibn": "\u0628\u0646"

    # H[dot below]aya[macron]t
    "h\u0323aya\u0304t": "\u062D\u064A\u0627\u0629"
    "H\u0323aya\u0304t": "\u062D\u064A\u0627\u0629"

    # "sh[dot below] as in "Ishaq"

    "%sh\u0323%": "\u0633\u062D"

    # "s[prime]h" combos

    "%s\u02B9h%": "\u0633\u0647"

    # "th[dot below]"

    "%th\u0323%": "\u062A\u062D"

    # dh[dot under] 

    "%dh\u0323%": "\u062F\u062D"

    # La-hu

    "la-hu": "\u0644\u0647"

    # Mi'ah
    "Mi\u02BEah": "\u0645\u0627\u0626\u0629"
    "Mi\u02BCah": "\u0645\u0627\u0626\u0629"
    "mi\u02BEah": "\u0645\u0627\u0626\u0629"
    "mi\u02BCah": "\u0645\u0627\u0626\u0629"

    # Mi'at
    "Mi\u02BEat": "\u0645\u0627\u0626\u0629"
    "Mi\u02BCat": "\u0645\u0627\u0626\u0629"
    "mi\u02BEat": "\u0645\u0627\u0626\u0629"
    "mi\u02BCat": "\u0645\u0627\u0626\u0629"

    # Numbers (I have set these to Hindi numbers. Note that Persian and Urdu will technically use \u06F0-06F9. This needs further discussion with PSD as RLIN21 used Hindi numbers, Connexion and Voyager does not.)

    # Edition statements with Latin number
    "al-T\u0323ab\u02BBah 1": "\u0627\u0644\u0637\u0628\u0639\u0629 1"
    "al-T\u0323ab\u02BBah 2": "\u0627\u0644\u0637\u0628\u0639\u0629 2"
    "al-T\u0323ab\u02BBah 3": "\u0627\u0644\u0637\u0628\u0639\u0629 3"
    "al-T\u0323ab\u02BBah 4": "\u0627\u0644\u0637\u0628\u0639\u0629 4"
    "al-T\u0323ab\u02BBah 5": "\u0627\u0644\u0637\u0628\u0639\u0629 5"
    "al-T\u0323ab\u02BBah 6": "\u0627\u0644\u0637\u0628\u0639\u0629 6"
    "al-T\u0323ab\u02BBah 7": "\u0627\u0644\u0637\u0628\u0639\u0629 7"
    "al-T\u0323ab\u02BBah 8": "\u0627\u0644\u0637\u0628\u0639\u0629 8"
    "al-T\u0323ab\u02BBah 9": "\u0627\u0644\u0637\u0628\u0639\u0629 9"

    # Use Basic Arabic-Indic \u0660-0669
    "0": "\u0660"
    "1": "\u0661"
    "2": "\u0662"
    "3": "\u0663"
    "4": "\u0664"
    "5": "\u0665"
    "6": "\u0666"
    "7": "\u0667"
    "8": "\u0668"
    "9": "\u0669"

    # Hyphenated prefixes:
    "wa-": "\u0648"
    "bi-": "\u0628"
    "al-": "\u0627\u0644"
    "lil-": "\u0644\u0644"
    "li-": "\u0644"
    "la\u0304-": "\u0644"
    "fi\u0304-": "\u0641\u064A"
    "ka-": "\u0643"

    # Vowels and vowel/consonant combinations
    "%ah": "\u0629"
    "%at": "\u0629"

    #tanwin
    "%an": "\u0627"

    # ayn-alif combo
    "%\u02BBa\u0304\u02BE": "\u0639\u0627\u0621"
    "%\u02BBa\u0304\u02BC": "\u0639\u0627\u0621"

    "\u02BBA\u0304": "\u0639\u0627"
    "\u02BBa\u0304": "\u0639\u0627"

    "\u02BBI\u0304": "\u0639\u064A"
    "\u02BBi\u0304": "\u0639\u064A"

    "\u02BBU\u0304": "\u0639\u0648"
    "\u02BBu\u0304": "\u0639\u0648"
    "\u02BBU": "\u0639"
    "\u02BBu": "\u0639"

    "\u02BBA%": "\u0639"
    #"\u02BBa%": "\u0639"

    # alif and hamzas for all occasions

    # truncation necessary? It seems to work fine with. 

    "%i\u0304\u02BEah": "\u064A\u0626\u0629"
    "%i\u0304\u02BCah": "\u064A\u0626\u0629"

    "%i\u0304\u02BEat": "\u064A\u0626\u0629"
    "%i\u0304\u02BCat": "\u064A\u0626\u0629"

    "%i\u02BEa\u0304": "\u0626\u0627"
    "%i\u02BCa\u0304": "\u0626\u0627"

    "%i\u02BE": "\u0626"
    "%i\u02BC": "\u0626"
    "a\u0304\u02BEa\u0304": "\u0627\u0621\u0627"
    "a\u0304\u02BCa\u0304": "\u0627\u0621\u0627"

    "a\u02BE": "\u0623"
    "a\u02BC": "\u0623"
    "\u02BEi": "\u0626"
    "\u02BCi": "\u0626"
    "\u02BEa\u0304": "\u0622"
    "\u02BCa\u0304": "\u0622"
    "\u02BEa": "\u0623"
    "\u02BCa": "\u0623"

    "y\u02BCah": "\u064A\u0626\u0629"
    "y\u02BEah": "\u064A\u0626\u0629"

    "y\u02BCat": "\u064A\u0626\u0629"
    "y\u02BEat": "\u064A\u0626\u0629"

    # A

    "a\u0304\u02BCi\u0304": "\u0627\u0626\u064A"
    "a\u0304\u02BEi\u0304": "\u0627\u0626\u064A"

    "a\u0304\u02BCi": "\u0627\u0626"
    "a\u0304\u02BEi": "\u0627\u0626"
    "a\u0304\u02BC": "\u0627\u0621"
    "a\u0304\u02BE": "\u0627\u0621"
    "A\u0304%": "\u0622"
    "a\u0304%": "\u0622"
    "A\u0304": "\u0627"
    "a\u0304": "\u0627"

    # These next two lines were intended to convert to alif-ayn when it is at the beginning of a word, definite or indefinine (i.e. al-a[ayn]ma[macron]l or [space]a[ayn]ma[macron]l" 
    "A\u02BB%": "\u0623\u0639"
    "a\u02BB%": "\u0623\u0639"
    "a\u02BB": "\u0639"
    "A\u0301": "\u0649"
    "a\u0301": "\u0649"

    "ayy": "\u064A"
    "A%": "\u0623"
    "a%": "\u0627"
    "A": "\u0623"
    "a": ""

    # I - Capital I at beginning of word is usually alif hamzah-below.

    "%i\u0304": "\u064A"
    "i\u0304y": "\u064A"
    "iy": "\u064A"
    "I\u0304%": "\u0625\u064A"
    "i\u0304": "\u064A"
    "\u02BBI%": "\u0639"

    # "i\u02BB": "\u0625\u0639"

    "I\u02BE": "\u0627\u0626"
    "I\u02BC": "\u0627\u0626"
    "i\u02BE": "\u0626"
    "i\u02BC": "\u0627\u0626"

    "I%": "\u0625"
    "i%": "\u0625"
    "I": "\u0625"
    "i": ""

    # U

    "u\u0304\u02BE": "\u0624"
    "u\u0304\u02BC": "\u0624"
    "U\u0304w%": "\u0623\u0648"
    "u\u0304w%": "\u0623\u0648"
    "U\u0304%": "\u0623\u0648"
    "u\u0304%": "\u0623\u0648"
    "u\u0304w": "\u0648"
    "u\u0304": "\u0648"
    "u\u02BE": "\u0624"
    "u\u02BC": "\u0624"

    "U%": "\u0623"
    "u%": "\u0623"
    "U": "\u0623"
    "u": ""

    # Consonants, with tashdid added 

    "B": "\u0628"
    "bb": "\u0628"
    "b": "\u0628"
    "Th": "\u062B"
    "thth": "\u062B"
    "th": "\u062B"
    "T\u0323": "\u0637"
    "t\u0323t\u0323": "\u0637"
    "t\u0323": "\u0637"
    "T": "\u062A"
    "tt": "\u062A"
    "t": "\u062A"
    "J": "\u062C"
    "jj": "\u062C"
    "j": "\u062C"
    "H\u0323": "\u062D"
    "h\u0323h\u0323": "\u062D"
    "h\u0323": "\u062D"
    "H": "\u0647"
    "hh": "\u0647"
    "h": "\u0647"
    "Kh": "\u062E"
    "khkh": "\u062E"
    "kh": "\u062E"
    "K": "\u0643"
    "kk": "\u0643"
    "k": "\u0643"
    "Dh": "\u0630"
    "dhdh": "\u0630"
    "dh": "\u0630"
    "D\u0323": "\u0636"
    "d\u0323d\u0323": "\u0636"
    "d\u0323": "\u0636"
    "D": "\u062F"
    "dd": "\u062F"
    "d": "\u062F"
    "R": "\u0631"
    "rr": "\u0631"
    "r": "\u0631"
    "Z\u0323": "\u0638"
    "z\u0323z\u0323": "\u0638"
    "z\u0323": "\u0638"
    "Z": "\u0632"
    "zz": "\u0632"
    "z": "\u0632"
    "Sh": "\u0634"
    "shsh": "\u0634"
    "sh": "\u0634"
    "S\u0323": "\u0635"
    "s\u0323s\u0323": "\u0635"
    "s\u0323": "\u0635"
    "S": "\u0633"
    "ss": "\u0633"
    "s": "\u0633"
    "Gh": "\u063A"
    "ghgh": "\u063A"
    "gh": "\u063A"
    "F": "\u0641"
    "ff": "\u0641"
    "f": "\u0641"
    "Q": "\u0642"
    "qq": "\u0642"
    "q": "\u0642"
    "L": "\u0644"
    "ll": "\u0644"
    "l": "\u0644"
    "M": "\u0645"
    "mm": "\u0645"
    "m": "\u0645"
    "N": "\u0646"
    "nn": "\u0646"
    "n": "\u0646"
    "W": "\u0648"
    "ww": "\u0648"
    "w": "\u0648"
    "Y": "\u064A"
    "yy": "\u064A"
    "y": "\u064A"

    # non-Arabic consonants:
    "P": "\u067E"
    "p": "\u067E"
    "Ch": "\u0686"
    "ch": "\u0686"
    "V": "\u06A4"
    "v": "\u06A4"
    "G": "\u06AF"
    "g": "\u06AF"

    # Diacritic characters:
    # ain (\u0639) - not transliterated alone:
    "\u02BB": "\u0639"
    # hamza - not romanized
    # "\u0621"
    # hamza (alone in final position)
    "%\u02BE": "\u0621"
    "%\u02BC": "\u0621"

    # Do not know what, if anything, is needed here:
    # tatweel:
    # "\u0640"
    # fathatan:
    # "\u064B"
    # dammatan:
    # "\u064C"
    # kasratan:
    # "\u064D"
    # fatha:
    # "\u064E"
    # damma:
    # "\u064F"
    # kasra:
    # "\u0650"
    # shadda:
    # "\u0651"
    # sukun:
    # "\u0652"
    # superscript alef:
    # "\u0670"
    # alef wasla
    # "\u0671"

script_to_roman:
  hooks:
    post_config:
      -
        - arabic.arabic_romanizer.s2r_post_config