scriptshifter/scriptshifter/tables/data/greek_classical.yml

general:
  name: Classical Greek (ancient and medieval)
  notes:
    - Compiled based on https://www.loc.gov/catdir/cpso/romanization/greek.pdf
  parents:
    - _ignore_base

script_to_roman:
  hooks:
    begin_input_token:
      -
        - greek.parse_numeral

  normalize:
    # Alpha
    "\u03B1":
      - "\u03AC"
      - "\u1F00"
      - "\u1F02"
      - "\u1F04"
      - "\u1F06"
      - "\u1F70"
      - "\u1F71"
      - "\u1F80"
      - "\u1F82"
      - "\u1F84"
      - "\u1F86"
      - "\u1FB0"
      - "\u1FB1"
      - "\u1FB2"
      - "\u1FB3"
      - "\u1FB4"
      - "\u1FB6"
      - "\u1FB7"
    "\u0391":
      - "\u0386"
      - "\u1F08"
      - "\u1F0A"
      - "\u1F0C"
      - "\u1F88"
      - "\u1F8A"
      - "\u1F8C"
      - "\u1F8E"
      - "\u1FB8"
      - "\u1FB9"
      - "\u1FBC"
    # Rough alpha
    "\u1F01":
      - "\u03B1\u0314"
      - "\u1F03"
      - "\u1F05"
      - "\u1F07"
      - "\u1F81"
      - "\u1F83"
      - "\u1F85"
      - "\u1F87"
    "\u1F09":
      - "\u0391\u0314"
      - "\u1F89"
      - "\u1F8B"
      - "\u1F8D"
      - "\u1F8F"
      - "\u1F0B"
      - "\u1F0D"
      - "\u1F0F"
    # Epsilon
    "\u03B5":
      - "\u03AD"
      - "\u1F10"
      - "\u1F12"
      - "\u1F14"
      - "\u1F72"
      - "\u1F73"
    "\u0395":
      - "\u1F18"
      - "\u1F1A"
      - "\u1F1C"
    # Rough epsilon
    "\u1F11":
      - "\u03B5\u0314"
      - "\u1F13"
      - "\u1F15"
    "\u1F19":
      - "\u0395\u0314"
      - "\u1F1B"
      - "\u1F1D"
    # Eta
    "\u03B7":
      - "\u03AE"
      - "\u1F20"
      - "\u1F22"
      - "\u1F24"
      - "\u1F26"
      - "\u1F74"
      - "\u1F75"
      - "\u1F90"
      - "\u1F92"
      - "\u1F94"
      - "\u1F96"
      - "\u1FC2"
      - "\u1FC3"
      - "\u1FC4"
      - "\u1FC6"
      - "\u1FC7"
    "\u0397":
      - "\u1F28"
      - "\u1F2A"
      - "\u1F2C"
      - "\u1F2E"
      - "\u1F98"
      - "\u1F9A"
      - "\u1F9C"
      - "\u1F9E"
      - "\u1FCC"
    # Rough eta
    "\u1F21":
      - "\u03B7\u0314"
      - "\u1F23"
      - "\u1F25"
      - "\u1F27"
      - "\u1F91"
      - "\u1F93"
      - "\u1F95"
      - "\u1F97"
    "\u1F29":
      - "\u0397\u0314"
      - "\u1F2B"
      - "\u1F2D"
      - "\u1F2F"
      - "\u1F99"
      - "\u1F9B"
      - "\u1F9D"
      - "\u1F9F"
    # Iota
    "\u03B9":
      - "\u0390"
      - "\u03AF"
      - "\u03CA"
      - "\u1F30"
      - "\u1F32"
      - "\u1F34"
      - "\u1F36"
      - "\u1F76"
      - "\u1F77"
      - "\u1FD0"
      - "\u1FD1"
      - "\u1FD2"
      - "\u1FD3"
      - "\u1FD6"
      - "\u1FD7"
    "\u0399":
      - "\u03AA"
      - "\u1F38"
      - "\u1F3A"
      - "\u1F3C"
      - "\u1F3E"
      - "\u1FD8"
      - "\u1FD9"
    # Rough iota
    "\u1F31":
      - "\u03B9\u0314"
      - "\u1F33"
      - "\u1F35"
      - "\u1F37"
    "\u1F39":
      - "\u0399\u0314"
      - "\u1F3B"
      - "\u1F3D"
      - "\u1F3F"
        # ὶ
    # Omicron
    "\u03BF":
      - "\u03cc"
      - "\u1F40"
      - "\u1F42"
      - "\u1F44"
      - "\u1F78"
      - "\u1F79"
    "\u039F":
      - "\u1F48"
      - "\u1F4A"
      - "\u1F4C"
    # Rough Omicron
    "\u1F41":
      - "\u03BF\u0314"
      - "\u1F43"
      - "\u1F45"
    "\u1F49":
      - "\u039F\u0314"
      - "\u1F4B"
      - "\u1F4D"
    # Rho
    "\u03C1":
      - "\u1FE4"
    # Rough Rho
    "\u1FE5":
      - "\u03C1\u0314"
    "\u1FEC":
      - "\u03A1\u0314"

    # Upsilon
    "\u03C5":
      - "\u03B0"
      - "\u03CB"
      - "\u03CD"
      - "\u1F50"
      - "\u1F52"
      - "\u1F54"
      - "\u1F56"
      - "\u1FE6"
      - "\u1F7A"
      - "\u1F7B"
      - "\u1FE0"
      - "\u1FE1"
      - "\u1FE2"
      - "\u1FE3"
      - "\u1FE7"
    "\u03A5":
        # NOTE: Capital upsilon + psili seems to be absent from Unicode table.
      - "\u03AB"
      - "\u1FE8"
      - "\u1FE9"
    # Rough Upsilon
    "\u1F51":
      - "\u03C5\u0314"
      - "\u1F53"
      - "\u1F55"
      - "\u1F57"
    "\u1F59":
      - "\u03A5\u0314"
      - "\u1F5B"
      - "\u1F5D"
      - "\u1F5F"
    # Omega
    "\u03C9":
      - "\u03CE"
      - "\u1F60"
      - "\u1F62"
      - "\u1F64"
      - "\u1F66"
      - "\u1F7C"
      - "\u1F7D"
      - "\u1FA0"
      - "\u1FA2"
      - "\u1FA4"
      - "\u1FA6"
      - "\u1FF2"
      - "\u1FF3"
      - "\u1FF4"
      - "\u1FF6"
      - "\u1FF7"
    "\u03A9":
      - "\u1F68"
      - "\u1F6A"
      - "\u1F6C"
      - "\u1F6E"
      - "\u1FA8"
      - "\u1FAA"
      - "\u1FAC"
      - "\u1FAE"
      - "\u1FFC"
    # Rough omega
    "\u1F61":
      - "\u03C9\u0314"
      - "\u1F63"
      - "\u1F65"
      - "\u1F67"
      - "\u1FA1"
      - "\u1FA3"
      - "\u1FA5"
      - "\u1FA7"
    "\u1F69":
      - "\u03A9\u0314"
      - "\u1F6B"
      - "\u1F6D"
      - "\u1F6F"
      - "\u1FA9"
      - "\u1FAB"
      - "\u1FAD"
      - "\u1FAF"

    # Remove all combining diacritics except for dasia.
    "":
      - "\u0342"
      - "\u0343"
      - "\u0344"
      - "\u0345"
      - "\u037A"
      - "\u1FBD"
      - "\u1FBE"
      - "\u1FBF"
      - "\u1FC0"
      - "\u1FC1"
      - "\u1FCD"
      - "\u1FCE"
      - "\u1FCF"
      - "\u1FED"
      - "\u1FEE"
      - "\u1FFD"

  map_initial:
    "\u0393\u03BA": "Gk"
    "\u03B3\u03BA": "gk"
    "\u039C\u03C0": "B"
    "\u03BC\u03C0": "b"
    "\u039D\u03C4": "\u1E0E"
    "\u03BD\u03C4": "\u1E0F"

  map_final:
    "\u0393\u03BA": "Gk"
    "\u03B3\u03BA": "gk"

  map:
    "\u201C": "\"\u0332"
    "\u201D": "\"\u0333"
    "\u2018": "'\u0332"
    #"\u2019": "'\u0333"
    "\u2116": "No\u0332"
    # "\u0300": ""
    # "\u0301": ""
    # "\u0302": ""
    # "\u0313": ""
    "\u0370": "H\u0323"
    "\u0371": "h\u0323"
    "\u0372": "S\uFE20\u0332S\uFE21\u0332"
    "\u0373": "s\uFE20\u0332s\uFE21\u0332"
    "\u0374": "\u02B9"
    "\u0375": "\u0326"
    "\u0376": "W\u0323"
    "\u0377": "w\u0323"
    # \u0378 reserved
    # \u0379 reserved
    "\u037A": "\u0328"
    "\u037B": "|)"
    "\u037C": "(."
    "\u037D": ".)"
    "\u037E": "?\u0333"
    "\u037F": "J"
    # \u0380 reserved
    # \u0381 reserved
    # \u0382 reserved
    # \u0383 reserved
    "\u0384": " \u0301"
    "\u0385": " \u0308\u0301"
    "\u0386": "A\u0301"
    "\u0387": ";\u0333"
    "\u0388\u0314": "He\u0301"
    "\u0388": "E\u0301"
    "\u0389\u0314": "\u0112\u0301"
    "\u0389": "\u0112\u0301"
    "\u038A\u0314": "Hi\u0301"
    "\u038A": "I\u0301"
    # \u038B reserved
    "\u038C\u0314": "Ho\u0301"
    "\u038C": "O\u0301"
    # \u038D reserved
    "\u038E\u0314": "Hy\u0301"
    "\u038E": "Y\u0301"
    "\u038F\u0314": "Ho\u0301"
    "\u038F": "\u014C\u0301"
    "\u0390": "i\u0308\u0301"
    "\u1F09": "Ha"
    "\u0391\u1F31": "Hai"
    "\u0391\u1F51": "Hau"
    "\u0391\u1F61": "Ha\u014D"
    "\u0391\u03C5": "Au"
    "\u0391": "A"
    "\u0392": "B"
    "\u0393": "G"
    "\u0394": "D"
    "\u1F19": "He"
    "\u0395\u03C5": "Eu"
    "\u0395": "E"
    "\u0396": "Z"
    "\u1F29": "H\u0113"
    "\u0397": "\u0112"
    "\u0397\u03C5": "\u0112u"
    "\u0397\u1F51": "H\u0113u"
    "\u0398": "Th"
    "\u1F39": "Hi"
    "\u0399\u03C5": "Iu"
    "\u0399": "I"
    "\u039A": "K"
    "\u039B": "L"
    "\u039C\u03C0%": "B"
    "\u039C": "M"
    # "\u039D\u03C4%": "D\u0332"
    "\u039D": "N"
    "\u039E": "X"
    "\u1F49": "Ho"
    "\u039F\u03C5": "Ou"
    "\u039F": "O"
    "\u03A0": "P"
    "\u1FEC": "Rh"
    "\u03A1": "R"
    # \u03A2 reserved
    "\u03A3": "S"
    "\u03A4": "T"
    "\u1F59": "Hy"
    "\u03A5": "Y"
    "\u03A5\u03B9": "Ui"
    "\u03A5\u1F31": "Hui"
    "\u03A6": "Ph"
    "\u03A7": "Ch"
    "\u03A8": "Ps"
    "\u1F69": "H\u014D"
    "\u03A9": "\u014C"
    "\u03A9\u03C5": "\u014Cu"
    "\u03AA": "I\u0308"
    "\u03AB": "Y\u0308"
    "\u03AC\u0314": "ha\u0301"
    "\u03AC": "a\u0301"
    "\u03ADU": "he\u0301"
    "\u03AD": "e\u0301"
    "\u03AE\u0314": "h\u0113\u0301"
    "\u03AE": "\u0113\u0301"
    "\u03AF\u0314": "hi\u0301"
    "\u03AF": "i\u0301"
    "\u03B0": "y\u0308\u0301"
    "\u1F01": "ha"
    "\u1F01\u1F31": "hai"
    "\u1F01\u03C5": "hau"
    "\u03B1\u1F31": "hai"
    "\u03B1\u1F51": "hau"
    "\u03B1\u1F61": "ha\u014D"
    "\u03B1\u03C5": "au"
    "\u03B1": "a"
    "\u03B2": "b"
    "\u03B3\u03B3": "ng"
    "%\u03B3\u03BA%": "nk"
    "\u03B3\u03BE": "nx"
    "\u03B3\u03C7": "nch"
    "\u03B3": "g"
    "\u03B4": "d"
    "\u1F11": "he"
    "\u03B5\u03C5": "eu"
    "\u03B5\u1F51": "heu"
    "\u03B5": "e"
    "\u03B6": "z"
    "\u1F21": "h\u0113"
    "\u03B7": "\u0113"
    "\u03B7\u03C5": "\u0113u"
    "\u03B7\u1F51": "h\u0113u"
    "\u03B8": "th"
    "\u1F31": "hi"
    "\u03B9\u03C5": "iu"
    "\u03B9": "i"
    "\u03BA": "k"
    "\u03BB": "l"
    "\u03BC\u03C0%": "b"
    "\u03BC": "m"
    # "\u03BD\u03C4%": "d\u0332"
    "\u03BD": "n"
    "\u03BE": "x"
    "\u1F41": "ho"
    "\u03BF\u03C5": "ou"
    "\u03BF": "o"
    "\u03C0": "p"
    "\u1FE5": "rh"
    "\u03C1": "r"
    "\u03C2": "s"
    "\u03C3": "s"
    "\u03C4": "t"
    "\u1F51": "hy"
    "\u03C5": "y"
    "\u03C5\u03B9": "ui"
    "\u03C5\u1F31": "hui"
    "\u03C6": "ph"
    "\u03C7": "ch"
    "\u03C8": "ps"
    "\u1F61": "h\u014D"
    "\u03C9": "\u014D"
    "\u03C9\u03C5": "\u014Du"
    "\u03CA": "i\u0308"
    "\u03CB": "y\u0308"
    "\u03CC": "o\u0301"
    "\u03CD": "y\u0301"
    "\u03CE": "\u014D\u0301"
    "\u03CF": "K\u0326"
    "\u03D0": "b\u0333"
    "\u03D1": "t\u0333h\u0333"
    "\u03D2": "Y\u0333"
    "\u03D3": "Y\u0301\u0333"
    "\u03D4": "Y\u0308\u0333"
    "\u03D5": "p\u0333h\u0333"
    "\u03D6": "p\u0333"
    "\u03D7": "k\u0326"
    "\u03D8": "Ḳ"
    "\u03D9": "ḳ"
    "\u03DA": "6\u0333"
    "\u03DB": "6\u0332"
    #"\u03DC": "G\u0332"
    "\u03DC": "W"
    #"\u03DD": "g\u0332"
    "\u03DD": "w"
    "\u03DE": "K\u0324"
    "\u03DF": "k\u0324"
    "\u03E0": "s\uFE20s\uFE21"
    "\u03E1": "S\uFE20S\uFE21"
    "\u03E2": "S\u030C"
    "\u03E3": "s\u030C"
    "\u03E4": "F"
    "\u03E5": "f"
    "\u03E6": "H\u0332"
    "\u03E7": "h\u0332"
    "\u03E8": "H\u0307"
    "\u03E9": "h\u0307"
    "\u03EA": "C\u030C"
    "\u03EB": "c\u030C"
    "\u03EC": "K\u0323y"
    "\u03ED": "k\u0323y"
    "\u03EE": "T\u0323i"
    "\u03EF": "t\u0323i"
    "\u03F0": "k\u0332"
    "\u03F1": "r\u0332"
    "\u03F2": "s"
    "\u03F3": "j"
    "\u03F4": "T\u0333H\u0333"
    "\u03F5": "e\u0332"
    "\u03F6": "e\u0333"
    "\u03F7": "S\uFE20H\uFE21"
    "\u03F8": "s\uFE20h\uFE21"
    "\u03F9": "S"
    "\u03FA": "S\u0323"
    "\u03FB": "s\u0323"
    "\u03FC": "r\u0333"
    "\u03FD": "|)\u0333"
    "\u03FE": "(.\u0333"
    "\u03FF": ".)\u0333"

  roman_to_script:
    map:
      ".)\u0333": "\u03FF"
      ".)": "\u037D"
      "?\u0333": "\u037E"
      "\"\u0332": "\u201C"
      "\"\u0333": "\u201D"
      "'\u0332": "\u2018"
      "'\u0333": "\u2019"
      "(.\u0333": "\u03FE"
      "(.": "\u037C"
      "|)\u0333": "\u03FD"
      "|)": "\u037B"
      # Left pointing double angle quotation mark
      "\u003C\u003C": "\u00AB"
      # Right pointing double angle quotation mark
      "\u003E\u003E": "\u00BB"
      "6\u0332": "\u03DB"
      "6\u0333": "\u03DA"
      "Au": "\u0391\u03C5"
      "au": "\u03B1\u03C5"
      "a\u0301": "\u03AC"
      "B": "\u0392"
      "b": "\u03B2"
      "b\u0333": "\u03D0"
      "Ch": "\u03A7"
      "ch": "\u03C7"
      "c\u030C": "\u03EB"
      "D\u0332": "\u039D\u03C4"
      "d\u0332": "\u03BD\u03C4"
      "D": "\u0394"
      "d": "\u03B4"
      "Eu": "\u0395\u03C5"
      "eu": "\u03B5\u03C5"
      "E\u0301": "\u0388"
      "e\u0301": "\u03AD"
      "\u0112\u0301": "\u0389\u0314"
      "\u0113\u0301": "\u03AE"
      "\u0112\u0301": "\u0389"
      "\u0112": "\u0397"
      "\u0112u": "\u0397\u03C5"
      "\u0113": "\u03B7"
      "\u0113u": "\u03B7\u03C5"
      "h\u0113u": "\u03B7\u1F51"
      "e\u0332": "\u03F5"
      "e\u0333": "\u03F6"
      "F": "\u03E4"
      "f": "\u03E5"
      #"G\u0332": "\u03DC"
      "W": "\u03DC"
      #"g\u0332": "\u03DD"
      "w": "\u03DD"
      "Ha\u0301": "\u0386\u0314"
      "ha\u0301": "\u03AC\u0314"
      "Ha": "\u1F09"
      "ha": "\u03B1\u0314"
      "A": "\u0391"
      "a": "\u03B1"
      "h\u0113\u0301": "\u03AE\u0314"
      "He\u0301": "\u0388\u0314"
      "he\u0301": "\u03AD\u0314"
      "H\u0113": "\u1F29"
      "H\u0113u": "\u1F29\u03C5"
      "h\u0113": "\u1F21"
      "h\u0113u": "\u1F21\u13C5"
      "He": "\u1F19"
      "he": "\u1F11"
      "E": "\u0395"
      "e": "\u03B5"
      "Hi\u0301": "\u038A\u0314"
      "hi\u0301": "\u03AF\u0314"
      "Hi": "\u1F39"
      "hi": "\u1F31"
      "Ho\u0301": "\u038F\u0314"
      "Ho\u0301": "\u038C\u0314"
      "h\u014D": "\u1F61"
      "H\u014D": "\u1F69"
      "Ho": "\u1F49"
      "ho": "\u1F41"
      "H\u0307": "\u03E8"
      "h\u0307": "\u03E9"
      "H\u0323": "\u0370"
      "h\u0323": "\u0371"
      "H\u0332": "\u03E6"
      "h\u0332": "\u03E7"
      "Hy\u0301": "\u038E\u0314"
      "Hy": "\u1F59"
      "hy": "\u1F51"
      "Iu": "\u0399\u03C5"
      "iu": "\u03B9\u03C5"
      "I\u0301": "\u038A"
      "i\u0301": "\u03AF"
      "I\u0308": "\u03AA"
      "i\u0308\u0301": "\u0390"
      "i\u0308": "\u03CA"
      "J": "\u037F"
      "j": "\u03F3"
      "K\u0323y": "\u03EC"
      "k\u0323y": "\u03ED"
      "K\u0332": "\u03DE"
      "k\u0332": "\u03DF"
      "K\u0326": "\u03CF"
      "k\u0326": "\u03D7"
      "k\u0332": "\u03F0"
      "L": "\u039B"
      "l": "\u03BB"
      "M": "\u039C"
      "m": "\u03BC"
      "nch": "\u03B3\u03C7"
      "ng": "\u03B3\u03B3"
      "%nk%": "\u03B3\u03BA"
      "nx": "\u03B3\u03BE"
      "No\u0332": "\u2116"
      "N": "\u039D"
      "n": "\u03BD"
      "K": "\u039A"
      "k": "\u03BA"
      "G": "\u0393"
      "g": "\u03B3"
      "Ou": "\u039F\u03C5"
      "ou": "\u03BF\u03C5"
      "O\u0301": "\u038C"
      "o\u0301": "\u03CC"
      "\u014C\u0301": "\u038F"
      "\u014D\u0301": "\u03CE"
      "\u014C": "\u03A9"
      "\u014Cu": "\u03A9\u03C5"
      "\u014D": "\u03C9"
      "\u014Du": "\u03D9\u03C5"
      "O": "\u039F"
      "o": "\u03BF"
      "Ph": "\u03A6"
      "ph": "\u03C6"
      "Ps": "\u03A8"
      "ps": "\u03C8"
      "p\u0333h\u0333": "\u03D5"
      "p\u0333": "\u03D6"
      "P": "\u03A0"
      "p": "\u03C0"
      "Ḳ": "\u03D8"
      "ḳ": "\u03D9"
      "Rh": "\u1FEC"
      "rh": "\u1FE5"
      "r\u0332": "\u03F1"
      "r\u0333": "\u03FC"
      "R": "\u03A1"
      "r": "\u03C1"
      "S\uFE20\u0332S\uFE21\u0332": "\u0372"
      "s\uFE20\u0332s\uFE21\u0332": "\u0373"
      "S\uFE20H\uFE21": "\u03F7"
      "s\uFE20h\uFE21": "\u03F8"
      "S\uFE20S\uFE21": "\u03E1"
      "s\uFE20s\uFE21": "\u03E0"
      "S\u030C": "\u03E2"
      "s\u030C": "\u03E3"
      "S\u0323": "\u03FA"
      "s\u0323": "\u03FB"
      "S": "\u03F9"
      "s": "\u03F2"
      "S": "\u03A3"
      "%s": "\u03C2"
      "s": "\u03C3"
      "T\u0333H\u0333": "\u03F4"
      "t\u0333h\u0333": "\u03D1"
      "Th": "\u0398"
      "th": "\u03B8"
      "T\u0323i": "\u03EE"
      "t\u0323i": "\u03EF"
      "T": "\u03A4"
      "t": "\u03C4"
      "I": "\u0399"
      "i": "\u03B9"
      "\u0020\u0301": "\u0384"
      "\u0020\u0308\u0301": "\u0385"
      ";\u0333": "\u0387"
      "\u02B9": "\u0374"
      "\u0326": "\u0375"
      "\u0328": "\u037A"
      "V": "\u0392"
      "v": "\u03B2"
      "W\u0323": "\u0376"
      "w\u0323": "\u0377"
      "X": "\u039E"
      "x": "\u03BE"
      "Y\u0301\u0333": "\u03D3"
      "Y\u0301": "\u038E"
      "y\u0301": "\u03CD"
      "Y\u0308\u0333": "\u03D4"
      "y\u0308\u0301": "\u03B0"
      "Y\u0308": "\u03AB"
      "y\u0308": "\u03CB"
      "Y\u0333": "\u03D2"
      "Y": "\u03A5"
      "Ui": "\u03A5\u03B9"
      "Hui": "\u03A5\u1F31"
      "y": "\u03C5"
      "ui": "\u03C5\u03B9"
      "hui": "\u03C5\u1F31"
      "Z": "\u0396"
      "z": "\u03B6"