path: root/icu/translit_Latin_Syriac.txt

// Latin-Syriac

translit_Latin_Syriac {
  Rule {
    ":: NFD (NFC) ;" 
    
    // Variable names, derived from the Unicode names.
    "$ALEF=\u0710;"
    "$ALEF_SUPERSCRIPT=\u0711;"
    "$BET=\u0712;"
    "$GIMEL=\u0713;"
    "$GIMEL_GARSHUNI=\u0714;"
    "$DALET=\u0715;"
    "$DALET_DOTLESS=\u0716;"
    "$HE=\u0717;"
    "$VAV=\u0718;"
    "$ZAYIN=\u0719;"
    "$HET=\u071A;"
    "$TET=\u071B;"
    "$TET_GARSHUNI=\u071C;"
    "$YOD=\u071D;"
    "$YOD_HE=\u071E;"
    "$KAF=\u071F;"
    "$LAMED=\u0720;"
    "$MEM=\u0721;"
    "$NUN=\u0722;"
    "$SAMEKH=\u0723;"
    "$FINAL_SAMEKH=\u0724;"
    "$AYIN=\u0725;"
    "$PE=\u0726;"
    "$PE_REVERSED=\u0727;"
    "$TSADI=\u0728;"
    "$QOF=\u0729;"
    "$RESH=\u072A;"
    "$SHIN=\u072B;"
    "$TAV=\u072C;"

    "$PARAGRAPH=\u0700;"
    
    "$letter=[a-zA-Z];"
    "$softvowel=[eiyEIY];"
    "$vowellike=[$ALEF $AYIN $YOD $VAV $ALEF_SUPERSCRIPT];"
    
    // [Why is this a special case? -liu]
    "k''h <> $KAF $HE ;"
    
    // Mark non-final forms in final position as x~ -liu
    "s    <  $SAMEKH   } [[:SYRIAC:]&[:LETTER:]] ;"
    "s'~' <> $SAMEKH   ;"

    // Mark final forms in non-final position as x^ -liu
    "s    <  $FINAL_SAMEKH;"
    
    // Main rules
    "a<>$ALEF;"
    "A>$ALEF;"
    "a<$ALEF_SUPERSCRIPT;"
    
    "b<>$BET;"
    "B>$BET;"
    
    "c}$softvowel>$SAMEKH;"
    "C}$softvowel>$SAMEKH;"
    "c>$KAF;"
    "C>$KAF;"
    
    "d<>$DALET;"
    "D>$DALET;"
    "d<$DALET_DOTLESS;"
    
    "e<>$AYIN;"
    "E>$AYIN;"
    
    "f>$PE;"
    "F>$PE;"
    
    "g<>$GIMEL;"
    "G>$GIMEL;"
    "g<$GIMEL_GARSHUNI;"
    
    "h<>$HE;"
    "H>$HE;"
    
    "i>$YOD;"
    "I>$YOD;"
    "ih<$YOD_HE;"
    
    "j>$DALET$SHIN;"
    "J>$DALET$SHIN;"
    
    "kh<>$HET;"
    "kH>$HET;"
    "Kh>$HET;"
    "KH>$HET;"
    "k<>$KAF;"
    "K>$KAF;"
    
    "l<>$LAMED;"
    "L>$LAMED;"
    
    "m<>$MEM;"
    "M>$MEM;"
    
    "n<>$NUN;"
    "N>$NUN;"
    
    "o>$VAV;"
    "O>$VAV;"
    
    "p<>$PE;"
    "P>$PE;"
    "p<$PE_REVERSED;"    

    "q<>$QOF;"
    "Q>$QOF;"
    
    "r<>$RESH;"
    "R>$RESH;"
    
    "sh<>$SHIN;"
    "sH>$SHIN;"
    "Sh>$SHIN;"
    "SH>$SHIN;"
    
    "th<>$TAV;"
    "tH>$TAV;"
    "Th>$TAV;"
    "TH>$TAV;"
    "tS>$TSADI;"
    "ts<>$TSADI;"
    "Ts>$TSADI;"
    "TS>$TSADI;"
    "t''<$TET}[$HE $SAMEKH $SHIN];"
    "t<>$TET;"
    "T>$TET;"
    "t<$TET_GARSHUNI;"

    "s}$letter>$SAMEKH;"
    "s>$FINAL_SAMEKH;"
    "S}$letter>$SAMEKH;"
    "S>$FINAL_SAMEKH;"
    
    "v<$VAV}$vowellike;"
    "u<>$VAV;"
    "U>$VAV;"
    
    "v>$VAV;"
    "V>$VAV;"
    
    "w>$VAV;"
    "W>$VAV;"
    
    "x>$KAF$SAMEKH;"
    "X>$KAF$SAMEKH;"
    
    "y<>$YOD;"
    "Y>$YOD;"
    
    "z<>$ZAYIN;"
    "Z>$ZAYIN;"

    "\u00B6<>$PARAGRAPH;"

    //Delete any Syriac we didn't recognize
    "<[:SYRIAC:];"

    ":: NFC (NFD) ;"    
  }
}