# Rules related to latin (latin1, latin extended-a, latin extended-b)
# Note: ascii.tr covers basic latin which is the same as US-ASCII
#
# The following charsets uses characters from latin:
# iso-8859-1, iso-8859-2, iso-8859-3, iso-8859-4, iso-8859-9, iso-8859-10,
# iso-8859-13, iso-8859-14, iso-8859-15, cp437, cp775, cp850, cp852, cp857,
# cp860, cp861, cp862, cp863, cp865, cp932
#
# Webpages of interest:
# http://www.cs.tut.fi/~jkorpela/latin1/all.html
#
# See basic.tr for formatting options

latin1_lowercase:
U+00C0 - U+00D6 + 20 # Lowercase diacritical latin1 characters
U+00D8 - U+00DE + 20 # Lowercase diacritical latin1 characters

latin1_uppercase:
U+00E0 - U+00F6 - 20 # Lowercase diacritical latin1 characters
U+00F8 - U+00FE - 20 # Lowercase diacritical latin1 characters
U+00DF = "SS"


latin-exta_lowercase:
U+0100 - U+012E % 02 + 01
U+0132 - U+0136 % 02 + 01
U+0139 - U+0147 % 02 + 01
U+014A - U+0176 % 02 + 01
U+0179 - U+017D % 02 + 01

latin-exta_uppercase:
U+0101 - U+012F % 02 - 01
U+0133 - U+0137 % 02 - 01
U+013A - U+0148 % 02 - 01
U+014B - U+0177 % 02 - 01
U+017A - U+017E % 02 - 01

latin_lowercase:
# These characters span multiple uncode sets
U+0178 = U+00FF

latin_uppercase:
# These characters span multiple uncode sets
U+00FF = U+0178

latin1_diacritical:
# Remove diacriticals from several latin characters
U+00C0 - U+00C4 = "A"  # A
U+00E0 - U+00E4 = "a"  # a
U+00C8 - U+00CB = "E"  # E
U+00E8 - U+00EB = "e"  # e
U+00CC - U+00CF = "I"  # I
U+00EC - U+00EF = "i"  # i
U+00D2 - U+00D6 = "O"  # O
U+00F2 - U+00F6 = "o"  # o
U+00D9 - U+00DC = "U"  # U
U+00F9 - U+00FC = "u"  # u

U+00DD = "Y"           # Y
U+009F = "Y"           # Y
U+00FD = "y"           # y
U+00FF = "y"           # y
U+00C7 = "C"           # C
U+00E7 = "c"           # c
U+00D0 = "D"           # D
U+00F0 = "d"           # d
U+00D1 = "N"           # N
U+00F1 = "n"           # n
U+00DE = "TH"          # latin capital letter thorn => TH? (icelandic, runic, old english)
U+00FE = "th"          # latin small letter thorn => th? (icelandic, runic, old english)
U+00DF = "ss"          # latin small letter sharp s (german)

latin-exta_diacritical:
U+0100 = "A"
U+0102 = "A"
U+0104 = "A"
U+0101 = "a"
U+0103 = "a"
U+0105 = "a"
U+0106 = "C"
U+0108 = "C"
U+010A = "C"
U+010C = "C"
U+0107 = "c"
U+0109 = "c"
U+010B = "c"
U+010D = "c"
U+010E = "D"
U+0110 = "D"
U+010F = "d"
U+0111 = "d"
U+0112 = "E"
U+0114 = "E"
U+0116 = "E"
U+0118 = "E"
U+011A = "E"
U+0113 = "e"
U+0115 = "e"
U+0117 = "e"
U+0119 = "e"
U+011B = "e"
U+011C = "G"
U+011E = "G"
U+0120 = "G"
U+0122 = "G"
U+011D = "g"
U+011F = "g"
U+0121 = "g"
U+0123 = "g"
U+0124 = "H"
U+0126 = "H"
U+0125 = "h"
U+0127 = "h"
U+0128 = "I"
U+012A = "I"
U+012C = "I"
U+012E = "I"
U+0130 = "I"
U+0129 = "i"
U+012B = "i"
U+012D = "i"
U+012F = "i"
U+0131 = "i"
U+0134 = "J"
U+0135 = "j"
U+0136 = "K"
U+0137 = "k"
U+0139 = "L"
U+013B = "L"
U+013D = "L"
U+013F = "L"
U+0141 = "L"
U+013A = "l"
U+013C = "l"
U+013E = "l"
U+0140 = "l"
U+0142 = "l"
U+0143 = "N"
U+0145 = "N"
U+0147 = "N"
U+0144 = "n"
U+0146 = "n"
U+0148 = "n"
U+014C = "O"
U+014E = "O"
U+0150 = "O"
U+014D = "o"
U+014F = "o"
U+0151 = "o"
U+0154 = "R"
U+0156 = "R"
U+0158 = "R"
U+0155 = "r"
U+0157 = "r"
U+0159 = "r"
U+015A = "S"
U+015C = "S"
U+015E = "S"
U+0160 = "S"
U+015B = "s"
U+015D = "s"
U+015F = "s"
U+0161 = "s"
U+0162 = "T"
U+0164 = "T"
U+0166 = "T"
U+0163 = "t"
U+0165 = "t"
U+0167 = "t"
U+0168 = "U"
U+016A = "U"
U+016C = "U"
U+016E = "U"
U+0170 = "U"
U+0172 = "U"
U+0169 = "u"
U+016B = "u"
U+016D = "u"
U+016F = "u"
U+0171 = "u"
U+0173 = "u"
U+0174 = "W"
U+0175 = "w"
U+0176 = "Y"
U+0177 = "y"
U+0178 = "Y"
U+0179 = "Z"
U+017B = "Z"
U+017D = "Z"
U+017A = "z"
U+017C = "z"
U+017E = "z"

# Transliteration of latin1, is used in URLs and identifiers
latin1_transliterate_ascii:
# Turn some latin1 characters into ASCII equivalents
U+00E6 = "ae" # æ => ae
U+00C6 = "AE" # Æ => AE
U+00E5 = "aa" # å => aa
U+00C5 = "AA" # Å => AA
U+00F8 = "oe" # ø => oe
U+00D8 = "OE" # Ø => OE
U+009C = "oe" # oe ligature
U+008C = "OE" # OE ligature
U+00AA = "a"  # feminine ordinal indicator (spanish)
U+00BA = "o"  # masculine ordinal indicator (spanish)

# Some german transliteration rules
U+00E4 = "ae"
U+00F6 = "oe"
U+00FC = "ue"
U+00C4 = "Ae"
U+00D6 = "Oe"
U+00DC = "Ue"

latin-exta_transliterate_ascii:
U+0132 = "IJ"
U+0133 = "ij"
U+0138 = "k"
U+0149 = "'n"
U+014A = "N"
U+014B = "n"
U+0152 = "AE"
U+0153 = "ae"
U+017F = "s"

math_to_ascii:
# Turn some special math symbols into ASCII equivalents
U+00D7 = "*"  # multiplication sign
U+00F7 = "/"  # division sign

inverted_to_normal:
# Turns inverted characters into their normal counterparts
U+00BF = U+003F # Inverted question mark
U+00A1 = U+0021 # Inverted exclamation

latin_search_cleanup:
# Map some special characters into spaces, needed for search engine
U+00BC - U+00BE = U+0020 # 1/4, 1/2 and 3/4
U+00A2 - U+00A7 = U+0020 # Cent, pound, currency, yen, broken sign, section
U+00AC = U+002D  # Not sign
U+00AF = U+002D  # Macron
U+00B5 = U+0020  # Micron sign
U+00B6 = U+0020  # Pillcrow sign
U+00B7 = U+0020  # Middle dot
U+00B8 = U+0020  # Cedilla
U+00A6 = U+0020  # Broken bar
U+00A7 = U+0020  # Paragraph
U+00A8 = remove  # Diaresis
U+00B0 = U+0020  # Degree sign
U+00A9 = U+0020  # Copyright sign
U+00AE = U+0020  # Registered sign

U+00B4 = U+0020 # Accute accent ´

# C1 control characters
U+0080 - U+009F = U+0020