123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169 |
- # À => A
- "\u00C0" => "A"
- # Á => A
- "\u00C1" => "A"
- # Â => A
- "\u00C2" => "A"
- # Ã => A
- "\u00C3" => "A"
- # Ä => Ae
- # Not needed if German2 Porter stemmer is used. This way word lists like
- # stopwords are easier to maintain.
- # Å => A
- "\u00C5" => "A"
- # Ą => A
- "\u0104" => "A"
- # Æ => AE
- "\u00C6" => "AE"
- # Ç => C
- "\u00C7" => "C"
- # Ć => C
- "\U0106" => "C"
- # È => E
- "\u00C8" => "E"
- # É => E
- "\u00C9" => "E"
- # Ê => E
- "\u00CA" => "E"
- # Ë => E
- "\u00CB" => "E"
- # Ę => E
- "\u0118" => "E"
- # Ì => I
- "\u00CC" => "I"
- # Í => I
- "\u00CD" => "I"
- # Î => I
- "\u00CE" => "I"
- # Ï => I
- "\u00CF" => "I"
- # IJ => IJ
- "\u0132" => "IJ"
- # Ð => D
- "\u00D0" => "D"
- # Ł => L
- "\u0141" => "L"
- # Ñ => N
- "\u00D1" => "N"
- # Ń => N
- "\u0143" => "N"
- # Ò => O
- "\u00D2" => "O"
- # Ó => O
- "\u00D3" => "O"
- # Ô => O
- "\u00D4" => "O"
- # Õ => O
- "\u00D5" => "O"
- # Ö => Oe
- # Not needed if German2 Porter stemmer is used. This way word lists like
- # stopwords are easier to maintain.
- # Ø => O
- "\u00D8" => "O"
- # Œ => OE
- "\u0152" => "OE"
- # Þ
- "\u00DE" => "TH"
- # Ù => U
- "\u00D9" => "U"
- # Ú => U
- "\u00DA" => "U"
- # Û => U
- "\u00DB" => "U"
- # Ü => Ue
- # Not needed if German2 Porter stemmer is used. This way word lists like
- # stopwords are easier to maintain.
- # Ý => Y
- "\u00DD" => "Y"
- # Ÿ => Y
- "\u0178" => "Y"
- # à => a
- "\u00E0" => "a"
- # á => a
- "\u00E1" => "a"
- # â => a
- "\u00E2" => "a"
- # ã => a
- "\u00E3" => "a"
- # ä => ae
- # Not needed if German2 Porter stemmer is used. This way word lists like
- # stopwords are easier to maintain.
- # å => a
- "\u00E5" => "a"
- # æ => ae
- "\u00E6" => "ae"
- # ç => c
- "\u00E7" => "c"
- # è => e
- "\u00E8" => "e"
- # é => e
- "\u00E9" => "e"
- # ê => e
- "\u00EA" => "e"
- # ë => e
- "\u00EB" => "e"
- # ì => i
- "\u00EC" => "i"
- # í => i
- "\u00ED" => "i"
- # î => i
- "\u00EE" => "i"
- # ï => i
- "\u00EF" => "i"
- # ij => ij
- "\u0133" => "ij"
- # ð => d
- "\u00F0" => "d"
- # ñ => n
- "\u00F1" => "n"
- # ò => o
- "\u00F2" => "o"
- # ó => o
- "\u00F3" => "o"
- # ô => o
- "\u00F4" => "o"
- # õ => o
- "\u00F5" => "o"
- # ö => oe
- # Not needed if German2 Porter stemmer is used. This way word lists like
- # stopwords are easier to maintain.
- # ø => o
- "\u00F8" => "o"
- # œ => oe
- "\u0153" => "oe"
- # ß => ss
- # Not needed if German2 Porter stemmer is used. This way word lists like
- # stopwords are easier to maintain.
- # þ => th
- "\u00FE" => "th"
- # ù => u
- "\u00F9" => "u"
- # ú => u
- "\u00FA" => "u"
- # û => u
- "\u00FB" => "u"
- # ü => ue
- # Not needed if German2 Porter stemmer is used. This way word lists like
- # stopwords are easier to maintain.
- # ý => y
- "\u00FD" => "y"
- # ÿ => y
- "\u00FF" => "y"
- # Ź => Z
- "\u0179" => "Z"
- # Ż => Z
- "\u017b" => "Z"
- # ff => ff
- "\uFB00" => "ff"
- # fi => fi
- "\uFB01" => "fi"
- # fl => fl
- "\uFB02" => "fl"
- # ffi => ffi
- "\uFB03" => "ffi"
- # ffl => ffl
- "\uFB04" => "ffl"
- # ſt => st
- "\uFB05" => "st"
- # st => st
- "\uFB06" => "st"
|