Solr 9 config generated by search_api_solr 4.3.14 (maxBooleanClauses 2048)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -1,164 +0,0 @@
|
||||
# À => A
|
||||
#"\u00C0" => "A"
|
||||
# Á => A
|
||||
#"\u00C1" => "A"
|
||||
# Â => A
|
||||
#"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
#"\u00D9" => "U"
|
||||
# Ú => U
|
||||
#"\u00DA" => "U"
|
||||
# Û => U
|
||||
#"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
#"\u00F9" => "u"
|
||||
# ú => u
|
||||
#"\u00FA" => "u"
|
||||
# û => u
|
||||
#"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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"
|
||||
@@ -1,178 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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"
|
||||
# š => s
|
||||
"\u0161" => "s"
|
||||
# ě => e
|
||||
"\u011B" => "e"
|
||||
# č => c
|
||||
"\u010D" => "c"
|
||||
# ř => r
|
||||
"\u0159" => "r"
|
||||
# ž => z
|
||||
"\u017E" => "z"
|
||||
# ť => t
|
||||
"\u0165" => "t"
|
||||
# ď => d
|
||||
"\u010F" => "d"
|
||||
@@ -1,164 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
"\u00D6" => "O"
|
||||
# Ø => O
|
||||
# "\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
"\u00F6" => "o"
|
||||
# ø => o
|
||||
# "\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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"
|
||||
@@ -1,169 +0,0 @@
|
||||
# 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"
|
||||
@@ -1,164 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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"
|
||||
@@ -162,3 +162,24 @@
|
||||
"\uFB05" => "st"
|
||||
# st => st
|
||||
"\uFB06" => "st"
|
||||
# Māori macrons.
|
||||
# Ā => A
|
||||
"\u0100" => "A"
|
||||
# Ē => E
|
||||
"\u0112" => "E"
|
||||
# Ī => I
|
||||
"\u012A" => "I"
|
||||
# Ō => O
|
||||
"\u014C" => "O"
|
||||
# Ū => U
|
||||
"\u016A" => "U"
|
||||
# ā => a
|
||||
"\u0101" => "a"
|
||||
# ē => e
|
||||
"\u0113" => "e"
|
||||
# ī => i
|
||||
"\u012B" => "i"
|
||||
# ō => o
|
||||
"\u014D" => "o"
|
||||
# ū => u
|
||||
"\u016B" => "u"
|
||||
|
||||
@@ -1,164 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
#"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
#"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
#"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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"
|
||||
@@ -1,164 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
#"\u00C4" => "A"
|
||||
# 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 => O
|
||||
#"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
#"\u00E4" => "a"
|
||||
# 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 => o
|
||||
#"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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"
|
||||
@@ -1,164 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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"
|
||||
@@ -1,178 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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 => ft
|
||||
"\uFB05" => "ft"
|
||||
# st => st
|
||||
"\uFB06" => "st"
|
||||
# š => s
|
||||
"\u0161" => "s"
|
||||
# ě => e
|
||||
"\u011B" => "e"
|
||||
# č => c
|
||||
"\u010D" => "c"
|
||||
# ř => r
|
||||
"\u0159" => "r"
|
||||
# ž => z
|
||||
"\u017E" => "z"
|
||||
# ť => t
|
||||
"\u0165" => "t"
|
||||
# ď => d
|
||||
"\u010F" => "d"
|
||||
@@ -1,186 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
"\u00D6" => "O"
|
||||
# Ő => O
|
||||
"\u0150" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# Ű => U
|
||||
"\u0170" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
"\u00F6" => "o"
|
||||
# ő => o
|
||||
"\u0151" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# ű => u
|
||||
"\u0171" => "u"
|
||||
# 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 => ft
|
||||
"\uFB05" => "ft"
|
||||
# st => st
|
||||
"\uFB06" => "st"
|
||||
# š => s
|
||||
"\u0161" => "s"
|
||||
# ě => e
|
||||
"\u011B" => "e"
|
||||
# č => c
|
||||
"\u010D" => "c"
|
||||
# ř => r
|
||||
"\u0159" => "r"
|
||||
# ž => z
|
||||
"\u017E" => "z"
|
||||
# ť => t
|
||||
"\u0165" => "t"
|
||||
# ď => d
|
||||
"\u010F" => "d"
|
||||
@@ -1,164 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
#"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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"
|
||||
@@ -1,164 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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"
|
||||
@@ -1,164 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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"
|
||||
@@ -1,164 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
#"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
#"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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"
|
||||
@@ -1,164 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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"
|
||||
@@ -1,164 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
#"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
#"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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"
|
||||
@@ -1,164 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
#"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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"
|
||||
@@ -1,164 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
#"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
#"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
#"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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"
|
||||
@@ -1,164 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
#"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
#"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
#"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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"
|
||||
@@ -1,164 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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"
|
||||
@@ -1,178 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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 => ft
|
||||
"\uFB05" => "ft"
|
||||
# st => st
|
||||
"\uFB06" => "st"
|
||||
# š => s
|
||||
"\u0161" => "s"
|
||||
# ě => e
|
||||
"\u011B" => "e"
|
||||
# č => c
|
||||
"\u010D" => "c"
|
||||
# ř => r
|
||||
"\u0159" => "r"
|
||||
# ž => z
|
||||
"\u017E" => "z"
|
||||
# ť => t
|
||||
"\u0165" => "t"
|
||||
# ď => d
|
||||
"\u010F" => "d"
|
||||
@@ -1,178 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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 => ft
|
||||
"\uFB05" => "ft"
|
||||
# st => st
|
||||
"\uFB06" => "st"
|
||||
# š => s
|
||||
"\u0161" => "s"
|
||||
# ě => e
|
||||
"\u011B" => "e"
|
||||
# č => c
|
||||
"\u010D" => "c"
|
||||
# ř => r
|
||||
"\u0159" => "r"
|
||||
# ž => z
|
||||
"\u017E" => "z"
|
||||
# ť => t
|
||||
"\u0165" => "t"
|
||||
# ď => d
|
||||
"\u010F" => "d"
|
||||
@@ -1,164 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
#"\u00C4" => "A"
|
||||
# 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 => O
|
||||
#"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
#"\u00E4" => "a"
|
||||
# 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 => o
|
||||
#"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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"
|
||||
@@ -1,164 +0,0 @@
|
||||
# À => A
|
||||
"\u00C0" => "A"
|
||||
# Á => A
|
||||
"\u00C1" => "A"
|
||||
# Â => A
|
||||
"\u00C2" => "A"
|
||||
# Ã => A
|
||||
"\u00C3" => "A"
|
||||
# Ä => A
|
||||
"\u00C4" => "A"
|
||||
# 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 => O
|
||||
"\u00D6" => "O"
|
||||
# Ø => O
|
||||
"\u00D8" => "O"
|
||||
# Œ => OE
|
||||
"\u0152" => "OE"
|
||||
# Þ
|
||||
"\u00DE" => "TH"
|
||||
# Ù => U
|
||||
"\u00D9" => "U"
|
||||
# Ú => U
|
||||
"\u00DA" => "U"
|
||||
# Û => U
|
||||
"\u00DB" => "U"
|
||||
# Ü => U
|
||||
"\u00DC" => "U"
|
||||
# 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 => a
|
||||
"\u00E4" => "a"
|
||||
# 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 => o
|
||||
"\u00F6" => "o"
|
||||
# ø => o
|
||||
"\u00F8" => "o"
|
||||
# œ => oe
|
||||
"\u0153" => "oe"
|
||||
# ß => ss
|
||||
"\u00DF" => "ss"
|
||||
# Ś => S
|
||||
"\u015a" => "S"
|
||||
# þ => th
|
||||
"\u00FE" => "th"
|
||||
# ù => u
|
||||
"\u00F9" => "u"
|
||||
# ú => u
|
||||
"\u00FA" => "u"
|
||||
# û => u
|
||||
"\u00FB" => "u"
|
||||
# ü => u
|
||||
"\u00FC" => "u"
|
||||
# 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"
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -1 +0,0 @@
|
||||
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,22 +0,0 @@
|
||||
dufte
|
||||
glas
|
||||
gläser
|
||||
glaser
|
||||
küche
|
||||
küchen
|
||||
kuchen
|
||||
loch
|
||||
löcher
|
||||
locher
|
||||
pläne
|
||||
pläne
|
||||
plane
|
||||
planen
|
||||
schloss
|
||||
schlösser
|
||||
schlosser
|
||||
schrank
|
||||
schränke
|
||||
schranke
|
||||
schranken
|
||||
volker
|
||||
@@ -30,7 +30,7 @@
|
||||
It should be kept correct and concise, usable out-of-the-box.
|
||||
|
||||
For more information, on how to customize this file, please see
|
||||
http://wiki.apache.org/solr/SchemaXml
|
||||
https://solr.apache.org/guide/solr/latest/indexing-guide/schema-elements.html
|
||||
|
||||
PERFORMANCE NOTE: this schema includes many optional features and should not
|
||||
be used for benchmarking. To improve performance one could
|
||||
@@ -49,7 +49,7 @@
|
||||
that avoids logging every request
|
||||
-->
|
||||
|
||||
<schema name="drupal-4.2.1-solr-8.x-0" version="1.6">
|
||||
<schema name="drupal-4.3.14-solr-9.x-0" version="1.6">
|
||||
<!-- attribute "name" is the name of this schema and is only used for display purposes.
|
||||
version="x.y" is Solr's version number for the schema syntax and
|
||||
semantics. It should not normally be changed by applications.
|
||||
@@ -122,7 +122,9 @@
|
||||
<!-- points to the root document of a block of nested documents. Required for nested
|
||||
document support, may be removed otherwise
|
||||
-->
|
||||
<field name="_root_" type="string" indexed="true" stored="false" docValues="false"/>
|
||||
<field name="_root_" type="string" indexed="true" stored="true" docValues="false" />
|
||||
<fieldType name="_nest_path_" class="solr.NestPathField" />
|
||||
<field name="_nest_path_" type="_nest_path_" />
|
||||
|
||||
<!-- Only remove the "id" field if you have a very good reason to. While not strictly
|
||||
required, it is highly recommended. A <uniqueKey> is present in almost all Solr
|
||||
@@ -156,7 +158,7 @@
|
||||
|
||||
<!-- Currently the suggester context filter query (suggest.cfq) accesses the tags using the stored values, neither the indexed terms nor the docValues.
|
||||
Therefore the dynamicField sm_* isn't suitable at the moment -->
|
||||
<field name="sm_context_tags" type="string" indexed="true" stored="true" multiValued="true" docValues="false"/>
|
||||
<field name="sm_context_tags" type="strings" indexed="true" stored="true" docValues="false"/>
|
||||
|
||||
<!-- Dynamic field definitions. If a field name is not found, dynamicFields
|
||||
will be used if the name matches any of the patterns.
|
||||
@@ -170,56 +172,59 @@
|
||||
the last letter is 's' for single valued, 'm' for multi-valued -->
|
||||
|
||||
<!-- We use plong for integer since 64 bit ints are now common in PHP. -->
|
||||
<dynamicField name="is_*" type="plong" indexed="true" stored="false" multiValued="false" docValues="true" termVectors="true"/>
|
||||
<dynamicField name="im_*" type="plong" indexed="true" stored="false" multiValued="true" docValues="true" termVectors="true"/>
|
||||
<dynamicField name="is_*" type="plong" indexed="true" stored="false" docValues="true" termVectors="true"/>
|
||||
<dynamicField name="im_*" type="plongs" indexed="true" stored="false" docValues="true" termVectors="true"/>
|
||||
<!-- List of floats can be saved in a regular float field -->
|
||||
<dynamicField name="fs_*" type="pfloat" indexed="true" stored="false" multiValued="false" docValues="true"/>
|
||||
<dynamicField name="fm_*" type="pfloat" indexed="true" stored="false" multiValued="true" docValues="true"/>
|
||||
<dynamicField name="fs_*" type="pfloat" indexed="true" stored="false" docValues="true"/>
|
||||
<dynamicField name="fm_*" type="pfloats" indexed="true" stored="false" docValues="true"/>
|
||||
<!-- List of doubles can be saved in a regular double field -->
|
||||
<dynamicField name="ps_*" type="pdouble" indexed="true" stored="false" multiValued="false" docValues="true"/>
|
||||
<dynamicField name="pm_*" type="pdouble" indexed="true" stored="false" multiValued="true" docValues="true"/>
|
||||
<dynamicField name="ps_*" type="pdouble" indexed="true" stored="false" docValues="true"/>
|
||||
<dynamicField name="pm_*" type="pdoubles" indexed="true" stored="false" docValues="true"/>
|
||||
<!-- List of booleans can be saved in a regular boolean field -->
|
||||
<dynamicField name="bm_*" type="boolean" indexed="true" stored="false" multiValued="true" docValues="true" termVectors="true"/>
|
||||
<dynamicField name="bs_*" type="boolean" indexed="true" stored="false" multiValued="false" docValues="true" termVectors="true"/>
|
||||
<dynamicField name="bm_*" type="booleans" indexed="true" stored="false" docValues="true" termVectors="true"/>
|
||||
<dynamicField name="bs_*" type="boolean" indexed="true" stored="false" docValues="true" termVectors="true"/>
|
||||
<!-- Regular text (without processing) can be stored in a string field-->
|
||||
<dynamicField name="ss_*" type="string" indexed="true" stored="false" multiValued="false" docValues="true" termVectors="true"/>
|
||||
<dynamicField name="ss_*" type="string" indexed="true" stored="false" docValues="true" termVectors="true"/>
|
||||
<!-- For field types using SORTED_SET, multiple identical entries are collapsed into a single value.
|
||||
Thus if I insert values 4, 5, 2, 4, 1, my return will be 1, 2, 4, 5 when enabling docValues.
|
||||
If you need to preserve the order and duplicate entries, consider to store the values as zm_* (twice). -->
|
||||
<dynamicField name="sm_*" type="string" indexed="true" stored="false" multiValued="true" docValues="true" termVectors="true"/>
|
||||
<dynamicField name="sm_*" type="strings" indexed="true" stored="false" docValues="true" termVectors="true"/>
|
||||
<!-- Special-purpose text fields -->
|
||||
<dynamicField name="tws_*" type="text_ws" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="twm_*" type="text_ws" indexed="true" stored="true" multiValued="true"/>
|
||||
|
||||
<!-- Trie fields are deprecated. Point fields solve all needs. But we keep the dedicated field names for backward compatibility. -->
|
||||
<dynamicField name="ds_*" type="pdate" indexed="true" stored="false" multiValued="false" docValues="true"/>
|
||||
<dynamicField name="dm_*" type="pdate" indexed="true" stored="false" multiValued="true" docValues="true"/>
|
||||
<dynamicField name="ds_*" type="pdate" indexed="true" stored="false" docValues="true"/>
|
||||
<dynamicField name="dm_*" type="pdates" indexed="true" stored="false" docValues="true"/>
|
||||
<!-- This field is used to store date ranges -->
|
||||
<dynamicField name="drs_*" type="date_range" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="drm_*" type="date_range" indexed="true" stored="true" multiValued="true"/>
|
||||
<dynamicField name="its_*" type="plong" indexed="true" stored="false" multiValued="false" docValues="true" termVectors="true"/>
|
||||
<dynamicField name="itm_*" type="plong" indexed="true" stored="false" multiValued="true" docValues="true" termVectors="true"/>
|
||||
<dynamicField name="fts_*" type="pfloat" indexed="true" stored="false" multiValued="false" docValues="true"/>
|
||||
<dynamicField name="ftm_*" type="pfloat" indexed="true" stored="false" multiValued="true" docValues="true"/>
|
||||
<dynamicField name="pts_*" type="pdouble" indexed="true" stored="false" multiValued="false" docValues="true"/>
|
||||
<dynamicField name="ptm_*" type="pdouble" indexed="true" stored="false" multiValued="true" docValues="true"/>
|
||||
<dynamicField name="drs_*" type="date_range" indexed="true" stored="true"/>
|
||||
<dynamicField name="drm_*" type="date_ranges" indexed="true" stored="true"/>
|
||||
<!-- Trie fields are deprecated. Point fields solve all needs. But we keep the dedicated field names for backward compatibility. -->
|
||||
<dynamicField name="its_*" type="plong" indexed="true" stored="false" docValues="true" termVectors="true"/>
|
||||
<dynamicField name="itm_*" type="plongs" indexed="true" stored="false" docValues="true" termVectors="true"/>
|
||||
<dynamicField name="fts_*" type="pfloat" indexed="true" stored="false" docValues="true"/>
|
||||
<dynamicField name="ftm_*" type="pfloats" indexed="true" stored="false" docValues="true"/>
|
||||
<dynamicField name="pts_*" type="pdouble" indexed="true" stored="false" docValues="true"/>
|
||||
<dynamicField name="ptm_*" type="pdoubles" indexed="true" stored="false" docValues="true"/>
|
||||
<!-- Binary fields can be populated using base64 encoded data. Useful e.g. for embedding
|
||||
a small image in a search result using the data URI scheme -->
|
||||
<dynamicField name="xs_*" type="binary" indexed="false" stored="true" multiValued="false"/>
|
||||
<dynamicField name="xm_*" type="binary" indexed="false" stored="true" multiValued="true"/>
|
||||
<!-- Trie fields are deprecated. Point fields solve all needs. But we keep the dedicated field names for backward compatibility. -->
|
||||
<dynamicField name="dds_*" type="pdate" indexed="true" stored="false" multiValued="false" docValues="true"/>
|
||||
<dynamicField name="ddm_*" type="pdate" indexed="true" stored="false" multiValued="true" docValues="true"/>
|
||||
<dynamicField name="dds_*" type="pdate" indexed="true" stored="false" docValues="true"/>
|
||||
<dynamicField name="ddm_*" type="pdates" indexed="true" stored="false" docValues="true"/>
|
||||
<!-- In case a 32 bit int is really needed, we provide these fields. 'h' is mnemonic for 'half word', i.e. 32 bit on 64 arch -->
|
||||
<dynamicField name="hs_*" type="pint" indexed="true" stored="false" multiValued="false" docValues="true"/>
|
||||
<dynamicField name="hm_*" type="pint" indexed="true" stored="false" multiValued="true" docValues="true"/>
|
||||
<dynamicField name="hs_*" type="pint" indexed="true" stored="false" docValues="true"/>
|
||||
<dynamicField name="hm_*" type="pints" indexed="true" stored="false" docValues="true"/>
|
||||
<!-- Trie fields are deprecated. Point fields solve all needs. But we keep the dedicated field names for backward compatibility. -->
|
||||
<dynamicField name="hts_*" type="pint" indexed="true" stored="false" multiValued="false" docValues="true"/>
|
||||
<dynamicField name="htm_*" type="pint" indexed="true" stored="false" multiValued="true" docValues="true"/>
|
||||
<dynamicField name="hts_*" type="pint" indexed="true" stored="false" docValues="true"/>
|
||||
<dynamicField name="htm_*" type="pints" indexed="true" stored="false" docValues="true"/>
|
||||
|
||||
<!-- Unindexed string fields that can be used to store values that won't be searchable but have docValues -->
|
||||
<dynamicField name="zdvs_*" type="string" indexed="false" stored="true" docValues="true"/>
|
||||
<dynamicField name="zdvm_*" type="strings" indexed="false" stored="true" docValues="true"/>
|
||||
<!-- Unindexed string fields that can be used to store values that won't be searchable -->
|
||||
<dynamicField name="zs_*" type="string" indexed="false" stored="true" multiValued="false"/>
|
||||
<dynamicField name="zm_*" type="string" indexed="false" stored="true" multiValued="true"/>
|
||||
<dynamicField name="zs_*" type="string" indexed="false" stored="true"/>
|
||||
<dynamicField name="zm_*" type="strings" indexed="false" stored="true"/>
|
||||
|
||||
<!-- Fields for location searches.
|
||||
http://wiki.apache.org/solr/SpatialSearch#geodist_-_The_distance_function -->
|
||||
@@ -264,9 +269,11 @@
|
||||
single-valued and either required or have a default value.
|
||||
-->
|
||||
<fieldType name="string" class="solr.StrField"/>
|
||||
<fieldType name="strings" class="solr.StrField" multiValued="true"/>
|
||||
|
||||
<!-- boolean type: "true" or "false" -->
|
||||
<fieldType name="boolean" class="solr.BoolField"/>
|
||||
<fieldType name="booleans" class="solr.BoolField" multiValued="true"/>
|
||||
|
||||
<!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
|
||||
currently supported on types that are sorted internally as strings
|
||||
@@ -331,6 +338,7 @@
|
||||
|
||||
<!-- A date range field -->
|
||||
<fieldType name="date_range" class="solr.DateRangeField"/>
|
||||
<fieldType name="date_ranges" class="solr.DateRangeField" multiValued="true"/>
|
||||
|
||||
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
|
||||
<fieldType name="binary" class="solr.BinaryField"/>
|
||||
@@ -369,7 +377,7 @@
|
||||
-->
|
||||
|
||||
<!-- A text field that only splits on whitespace for exact matching of words -->
|
||||
<fieldType name="text_ws" class="solr.TextField" omitNorms="true" positionIncrementGap="100">
|
||||
<fieldType name="text_ws" class="solr.TextField" omitNorms="true" positionIncrementGap="100" storeOffsetsWithPositions="true">
|
||||
<analyzer>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
|
||||
@@ -52,14 +52,14 @@
|
||||
<dynamicField name="tom_X3b_en_*" type="text_en" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
|
||||
<dynamicField name="tus_X3b_en_*" type="text_unstemmed_en" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="tum_X3b_en_*" type="text_unstemmed_en" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="sort_X3b_en_*" type="collated_en" stored="false" indexed="false" docValues="true" />
|
||||
<dynamicField name="sort_X3b_en_*" type="collated_en" stored="false" indexed="false" docValues="true" useDocValuesAsStored="false" />
|
||||
<dynamicField name="ts_X3b_fr_*" type="text_fr" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="tm_X3b_fr_*" type="text_fr" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="tos_X3b_fr_*" type="text_fr" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
|
||||
<dynamicField name="tom_X3b_fr_*" type="text_fr" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
|
||||
<dynamicField name="tus_X3b_fr_*" type="text_unstemmed_fr" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="tum_X3b_fr_*" type="text_unstemmed_fr" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="sort_X3b_fr_*" type="collated_fr" stored="false" indexed="false" docValues="true" />
|
||||
<dynamicField name="sort_X3b_fr_*" type="collated_fr" stored="false" indexed="false" docValues="true" useDocValuesAsStored="false" />
|
||||
<dynamicField name="tcphonetics_X3b_und_*" type="text_phonetic_und" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="tcphonetics_*" type="text_phonetic_und" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="tcphoneticm_X3b_und_*" type="text_phonetic_und" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
|
||||
@@ -84,6 +84,18 @@
|
||||
<dynamicField name="tocphoneticm_X3b_fr_*" type="text_phonetic_fr" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
|
||||
<dynamicField name="tucphonetics_X3b_fr_*" type="text_phonetic_fr" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="tucphoneticm_X3b_fr_*" type="text_phonetic_fr" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="tcstrings_X3b_und_*" type="text_string" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="tcstrings_*" type="text_string" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="tcstringm_X3b_und_*" type="text_string" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="tcstringm_*" type="text_string" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="tocstrings_X3b_und_*" type="text_string" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
|
||||
<dynamicField name="tocstrings_*" type="text_string" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
|
||||
<dynamicField name="tocstringm_X3b_und_*" type="text_string" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
|
||||
<dynamicField name="tocstringm_*" type="text_string" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
|
||||
<dynamicField name="tucstrings_X3b_und_*" type="text_string" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="tucstrings_*" type="text_string" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="tucstringm_X3b_und_*" type="text_string" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="tucstringm_*" type="text_string" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="ts_X3b_und_*" type="text_und" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="ts_*" type="text_und" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="tm_X3b_und_*" type="text_und" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
|
||||
@@ -98,8 +110,8 @@
|
||||
<dynamicField name="tum_*" type="text_und" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="spellcheck_und*" type="text_spell_und" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
|
||||
<dynamicField name="spellcheck_*" type="text_spell_und" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
|
||||
<dynamicField name="sort_X3b_und_*" type="collated_und" stored="false" indexed="false" docValues="true" />
|
||||
<dynamicField name="sort_*" type="collated_und" stored="false" indexed="false" docValues="true" />
|
||||
<dynamicField name="sort_X3b_und_*" type="collated_und" stored="false" indexed="false" docValues="true" useDocValuesAsStored="false" />
|
||||
<dynamicField name="sort_*" type="collated_und" stored="false" indexed="false" docValues="true" useDocValuesAsStored="false" />
|
||||
<dynamicField name="tcngramstrings_X3b_und_*" type="text_ngramstring" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="tcngramstrings_*" type="text_ngramstring" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
|
||||
<dynamicField name="tcngramstringm_X3b_und_*" type="text_ngramstring" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
|
||||
|
||||
@@ -2,27 +2,28 @@
|
||||
ASCII String Field
|
||||
6.0.0
|
||||
-->
|
||||
<fieldType name="text_asciistring" class="solr.TextField" positionIncrementGap="100">
|
||||
<fieldType name="text_asciistring" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
<filter class="solr.ASCIIFoldingFilterFactory" preserveOriginal="true"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" preserveOriginal="1"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
<filter class="solr.FlattenGraphFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
<filter class="solr.ASCIIFoldingFilterFactory" preserveOriginal="true"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" preserveOriginal="1"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<!--
|
||||
Edge NGram ASCII String Field
|
||||
6.0.0
|
||||
-->
|
||||
<fieldType name="text_edgenasciistring" class="solr.TextField" positionIncrementGap="100">
|
||||
<fieldType name="text_edgenasciistring" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
@@ -30,6 +31,7 @@
|
||||
<filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="25"/>
|
||||
<filter class="solr.ASCIIFoldingFilterFactory" preserveOriginal="true"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" preserveOriginal="1"/>
|
||||
<filter class="solr.FlattenGraphFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
@@ -43,7 +45,7 @@
|
||||
Edge NGram String Field
|
||||
6.0.0
|
||||
-->
|
||||
<fieldType name="text_edgenstring" class="solr.TextField" positionIncrementGap="100">
|
||||
<fieldType name="text_edgenstring" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
@@ -60,12 +62,13 @@
|
||||
Edge NGram Text Field
|
||||
7.0.0
|
||||
-->
|
||||
<fieldType name="text_edge" class="solr.TextField" positionIncrementGap="100">
|
||||
<fieldType name="text_edge" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
|
||||
<analyzer type="index">
|
||||
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_und.txt"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_und.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
||||
<filter class="solr.FlattenGraphFilterFactory"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
@@ -73,7 +76,7 @@
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
@@ -83,26 +86,27 @@
|
||||
English Text Field
|
||||
7.0.0
|
||||
-->
|
||||
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
|
||||
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
|
||||
<analyzer type="index">
|
||||
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_en.txt"/>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_en.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
||||
<filter class="solr.FlattenGraphFilterFactory"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords_en.txt"/>
|
||||
<filter class="solr.SnowballPorterFilterFactory" protected="protwords_en.txt" language="English"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_en.txt"/>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_en.txt" expand="true" ignoreCase="true"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.SynonymGraphFilterFactory" ignoreCase="true" synonyms="synonyms_en.txt" expand="true"/>
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_en.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords_en.txt"/>
|
||||
<filter class="solr.SnowballPorterFilterFactory" protected="protwords_en.txt" language="English"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
@@ -115,20 +119,21 @@
|
||||
English Text Field unstemmed
|
||||
7.0.0
|
||||
-->
|
||||
<fieldType name="text_unstemmed_en" class="solr.TextField" positionIncrementGap="100">
|
||||
<fieldType name="text_unstemmed_en" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
|
||||
<analyzer type="index">
|
||||
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_en.txt"/>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_en.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
||||
<filter class="solr.FlattenGraphFilterFactory"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_en.txt"/>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_en.txt" expand="true" ignoreCase="true"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.SynonymGraphFilterFactory" ignoreCase="true" synonyms="synonyms_en.txt" expand="true"/>
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_en.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
||||
@@ -140,26 +145,27 @@
|
||||
French Text Field
|
||||
7.0.0
|
||||
-->
|
||||
<fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
|
||||
<fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
|
||||
<analyzer type="index">
|
||||
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_fr.txt"/>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.ElisionFilterFactory"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_fr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
||||
<filter class="solr.FlattenGraphFilterFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fr.txt"/>
|
||||
<filter class="solr.SnowballPorterFilterFactory" language="French" protected="protwords_fr.txt"/>
|
||||
<filter class="solr.SnowballPorterFilterFactory" protected="protwords_fr.txt" language="French"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_fr.txt"/>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.ElisionFilterFactory"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_fr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_fr.txt" expand="true" ignoreCase="true"/>
|
||||
<filter class="solr.SynonymGraphFilterFactory" ignoreCase="true" synonyms="synonyms_fr.txt" expand="true"/>
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fr.txt"/>
|
||||
<filter class="solr.SnowballPorterFilterFactory" language="French" protected="protwords_fr.txt"/>
|
||||
<filter class="solr.SnowballPorterFilterFactory" protected="protwords_fr.txt" language="French"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
@@ -172,22 +178,23 @@
|
||||
French Text Field unstemmed
|
||||
7.0.0
|
||||
-->
|
||||
<fieldType name="text_unstemmed_fr" class="solr.TextField" positionIncrementGap="100">
|
||||
<fieldType name="text_unstemmed_fr" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
|
||||
<analyzer type="index">
|
||||
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_fr.txt"/>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.ElisionFilterFactory"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_fr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
||||
<filter class="solr.FlattenGraphFilterFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fr.txt"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_fr.txt"/>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_fr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_fr.txt" expand="true" ignoreCase="true"/>
|
||||
<filter class="solr.SynonymGraphFilterFactory" ignoreCase="true" synonyms="synonyms_fr.txt" expand="true"/>
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fr.txt"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
</analyzer>
|
||||
@@ -196,18 +203,19 @@
|
||||
Fulltext Phonetic
|
||||
7.0.0
|
||||
-->
|
||||
<fieldType name="text_phonetic_und" class="solr.TextField" positionIncrementGap="100">
|
||||
<fieldType name="text_phonetic_und" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_und.txt"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_und.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
||||
<filter class="solr.FlattenGraphFilterFactory"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.BeiderMorseFilterFactory" languageSet="auto" nameType="GENERIC" ruleType="APPROX" concat="true"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_und.txt"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_und.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
||||
@@ -220,18 +228,19 @@
|
||||
Fulltext Phonetic English
|
||||
7.0.0
|
||||
-->
|
||||
<fieldType name="text_phonetic_en" class="solr.TextField" positionIncrementGap="100">
|
||||
<fieldType name="text_phonetic_en" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_en.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
||||
<filter class="solr.FlattenGraphFilterFactory"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.BeiderMorseFilterFactory" languageSet="english" nameType="GENERIC" ruleType="APPROX" concat="true"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_en.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
||||
@@ -244,18 +253,19 @@
|
||||
Fulltext Phonetic French
|
||||
7.0.0
|
||||
-->
|
||||
<fieldType name="text_phonetic_fr" class="solr.TextField" positionIncrementGap="100">
|
||||
<fieldType name="text_phonetic_fr" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.ElisionFilterFactory"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_fr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
||||
<filter class="solr.FlattenGraphFilterFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fr.txt"/>
|
||||
<filter class="solr.BeiderMorseFilterFactory" languageSet="french" nameType="GENERIC" ruleType="APPROX" concat="true"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_fr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fr.txt"/>
|
||||
@@ -263,23 +273,38 @@
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<!--
|
||||
Fulltext String Field
|
||||
6.0.0
|
||||
-->
|
||||
<fieldType name="text_string" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.PatternTokenizerFactory" pattern="[\t\r\n]"/>
|
||||
<filters/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.PatternTokenizerFactory" pattern="[\t\r\n]"/>
|
||||
<filters/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<!--
|
||||
Language Undefined Text Field
|
||||
7.0.0
|
||||
-->
|
||||
<fieldType name="text_und" class="solr.TextField" positionIncrementGap="100">
|
||||
<fieldType name="text_und" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
|
||||
<analyzer type="index">
|
||||
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_und.txt"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_und.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
||||
<filter class="solr.FlattenGraphFilterFactory"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_und.txt" expand="true" ignoreCase="true"/>
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_und.txt"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_und.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
||||
@@ -292,10 +317,10 @@
|
||||
Language Undefined Text Field spellcheck
|
||||
7.0.0
|
||||
-->
|
||||
<fieldType name="text_spell_und" class="solr.TextField" positionIncrementGap="100">
|
||||
<fieldType name="text_spell_und" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
|
||||
<analyzer>
|
||||
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
@@ -305,12 +330,12 @@
|
||||
Language Undefined Text Field collated
|
||||
7.0.0
|
||||
-->
|
||||
<fieldType name="collated_und" class="solr.ICUCollationField" locale="en" strength="primary" caseLevel="false"/>
|
||||
<fieldType name="collated_und" class="solr.ICUCollationField" locale="" strength="primary" caseLevel="false"/>
|
||||
<!--
|
||||
NGram String Field
|
||||
6.0.0
|
||||
-->
|
||||
<fieldType name="text_ngramstring" class="solr.TextField" positionIncrementGap="100">
|
||||
<fieldType name="text_ngramstring" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
@@ -327,12 +352,13 @@
|
||||
NGram Text Field
|
||||
7.0.0
|
||||
-->
|
||||
<fieldType name="text_ngram" class="solr.TextField" positionIncrementGap="100">
|
||||
<fieldType name="text_ngram" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
|
||||
<analyzer type="index">
|
||||
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_und.txt"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_und.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
||||
<filter class="solr.FlattenGraphFilterFactory"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
@@ -340,7 +366,7 @@
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
|
||||
@@ -9,9 +9,9 @@
|
||||
|
||||
<!--
|
||||
For more details about configurations options that may appear in
|
||||
this file, see http://wiki.apache.org/solr/SolrConfigXml.
|
||||
this file, see https://solr.apache.org/guide/solr/latest/configuration-guide/configuring-solrconfig-xml.html
|
||||
-->
|
||||
<config name="drupal-4.2.1-solr-8.x-0" >
|
||||
<config name="drupal-4.3.14-solr-9.x-0" >
|
||||
<!-- In all configuration below, a prefix of "solr." for class names
|
||||
is an alias that causes solr to search appropriate packages,
|
||||
including org.apache.solr.(search|update|request|core|analysis)
|
||||
@@ -38,7 +38,7 @@
|
||||
that you fully re-index after changing this setting as it can
|
||||
affect both how text is indexed and queried.
|
||||
-->
|
||||
<luceneMatchVersion>${solr.luceneMatchVersion:LUCENE_80}</luceneMatchVersion>
|
||||
<luceneMatchVersion>${solr.luceneMatchVersion:LUCENE_90}</luceneMatchVersion>
|
||||
|
||||
<!-- <lib/> directives can be used to instruct Solr to load any Jars
|
||||
identified and use them to resolve any "plugins" specified in
|
||||
@@ -72,20 +72,18 @@
|
||||
If a 'dir' option (with or without a regex) is used and nothing
|
||||
is found that matches, a warning will be logged.
|
||||
|
||||
The examples below can be used to load some solr-contribs along
|
||||
with their external dependencies.
|
||||
The examples below can be used to load some Solr Modules along
|
||||
with their external dependencies as an alternative to using a
|
||||
startup parameter to define the modules to load globally. For more info
|
||||
see https://solr.apache.org/guide/solr/latest/configuration-guide/solr-modules.html
|
||||
-->
|
||||
<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-dataimporthandler-.*\.jar" />
|
||||
<lib dir="${solr.install.dir:../../../..}/modules/extraction/lib" regex=".*\.jar" />
|
||||
|
||||
<lib dir="${solr.install.dir:../../../..}/contrib/extraction/lib" regex=".*\.jar" />
|
||||
<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-cell-\d.*\.jar" />
|
||||
<lib dir="${solr.install.dir:../../../..}/modules/langid/lib/" regex=".*\.jar" />
|
||||
|
||||
<lib dir="${solr.install.dir:../../../..}/contrib/langid/lib/" regex=".*\.jar" />
|
||||
<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-langid-\d.*\.jar" />
|
||||
<lib dir="${solr.install.dir:../../../..}/modules/ltr/lib/" regex=".*\.jar" />
|
||||
|
||||
<lib dir="${solr.install.dir:../../../..}/contrib/analysis-extras/lib" regex=".*\.jar" />
|
||||
<lib dir="${solr.install.dir:../../../..}/contrib/analysis-extras/lucene-libs" regex=".*\.jar" />
|
||||
<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-analysis-extras-\d.*\.jar" />
|
||||
<lib dir="${solr.install.dir:../../../..}/modules/analysis-extras/lib/" regex=".*\.jar" />
|
||||
|
||||
<!-- an exact 'path' can be used instead of a 'dir' to specify a
|
||||
specific jar file. This will cause a serious error to be logged
|
||||
@@ -114,7 +112,7 @@
|
||||
for better NRT performance.
|
||||
|
||||
One can force a particular implementation via solr.MMapDirectoryFactory,
|
||||
solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
|
||||
solr.NIOFSDirectoryFactory.
|
||||
|
||||
solr.RAMDirectoryFactory is memory based and not persistent.
|
||||
-->
|
||||
@@ -223,7 +221,7 @@
|
||||
'simple' is the default
|
||||
|
||||
More details on the nuances of each LockFactory...
|
||||
http://wiki.apache.org/lucene-java/AvailableLockFactories
|
||||
https://cwiki.apache.org/confluence/display/lucene/AvailableLockFactories
|
||||
-->
|
||||
<lockType>${solr.lock.type:native}</lockType>
|
||||
|
||||
@@ -284,6 +282,7 @@
|
||||
solr data directory. -->
|
||||
<updateLog>
|
||||
<str name="dir">${solr.ulog.dir:}</str>
|
||||
<int name="numVersionBuckets">${solr.ulog.numVersionBuckets:65536}</int>
|
||||
</updateLog>
|
||||
|
||||
<!-- AutoCommit
|
||||
@@ -292,7 +291,7 @@
|
||||
Instead of enabling autoCommit, consider using "commitWithin"
|
||||
when adding documents.
|
||||
|
||||
http://wiki.apache.org/solr/UpdateXmlMessages
|
||||
https://solr.apache.org/guide/solr/latest/indexing-guide/indexing-with-update-handlers.html
|
||||
|
||||
maxDocs - Maximum number of documents to add since the last
|
||||
commit before automatically triggering a new commit.
|
||||
@@ -321,7 +320,7 @@
|
||||
|
||||
<autoSoftCommit>
|
||||
<maxDocs>${solr.autoSoftCommit.MaxDocs:-1}</maxDocs>
|
||||
<maxTime>${solr.autoSoftCommit.MaxTime:-1}</maxTime>
|
||||
<maxTime>${solr.autoSoftCommit.MaxTime:5000}</maxTime>
|
||||
</autoSoftCommit>
|
||||
|
||||
<!-- Update Related Event Listeners
|
||||
@@ -439,6 +438,51 @@
|
||||
|
||||
</query>
|
||||
|
||||
<!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
Circuit Breaker Section - This section consists of configurations for
|
||||
circuit breakers
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
|
||||
<!-- Circuit breakers are designed to allow stability and predictable query
|
||||
execution. They prevent operations that can take down the node and cause
|
||||
noisy neighbour issues.
|
||||
|
||||
The CircuitBreakerManager is the default manager for all circuit breakers.
|
||||
The enabled flag here controls the activation/deactivation of all circuit
|
||||
breakers specified within.
|
||||
-->
|
||||
<circuitBreaker class="solr.CircuitBreakerManager" enabled="true">
|
||||
<!-- Memory Circuit Breaker
|
||||
|
||||
Specific configuration for max JVM heap usage circuit breaker. This configuration defines
|
||||
whether the circuit breaker is enabled and the threshold percentage of maximum heap allocated
|
||||
beyond which queries will be rejected until the current JVM usage goes below the threshold.
|
||||
The valid value for this range is 50-95.
|
||||
|
||||
Consider a scenario where the max heap allocated is 4 GB and memThreshold is defined as 75.
|
||||
Threshold JVM usage will be 4 * 0.75 = 3 GB. Its generally a good idea to keep this value
|
||||
between 75 - 80% of maximum heap allocated.
|
||||
|
||||
If, at any point, the current JVM heap usage goes above 3 GB, queries will be rejected until
|
||||
the heap usage goes below 3 GB again. If you see queries getting rejected with 503 error code,
|
||||
check for "Circuit Breakers tripped" in logs and the corresponding error message should tell
|
||||
you what transpired (if the failure was caused by tripped circuit breakers).
|
||||
-->
|
||||
<!--
|
||||
<str name="memEnabled">true</str>
|
||||
<str name="memThreshold">75</str>
|
||||
-->
|
||||
|
||||
<!-- CPU Circuit Breaker Configuration
|
||||
|
||||
Specific configuration for CPU utilization based circuit breaker. This configuration defines
|
||||
whether the circuit breaker is enabled and the average load over the last minute at which the
|
||||
circuit breaker should start rejecting queries.
|
||||
-->
|
||||
<!--
|
||||
<str name="cpuEnabled">true</str>
|
||||
<str name="cpuThreshold">75</str>
|
||||
-->
|
||||
</circuitBreaker>
|
||||
|
||||
<!-- Request Dispatcher
|
||||
|
||||
@@ -455,6 +499,9 @@
|
||||
enableRemoteStreaming - enables use of the stream.file
|
||||
and stream.url parameters for specifying remote streams.
|
||||
|
||||
enableStreamBody - This attribute controls whether streaming
|
||||
content from the HTTP parameter stream.body is allowed.
|
||||
|
||||
multipartUploadLimitInKB - specifies the max size (in KiB) of
|
||||
Multipart File Uploads that Solr will allow in a Request.
|
||||
|
||||
@@ -474,7 +521,8 @@
|
||||
Before enabling remote streaming, you should make sure your
|
||||
system has authentication enabled.
|
||||
|
||||
<requestParsers enableRemoteStreaming="false"
|
||||
<requestParsers enableRemoteStreaming="true"
|
||||
enableStreamBody="true"
|
||||
multipartUploadLimitInKB="-1"
|
||||
formdataUploadLimitInKB="-1"
|
||||
addHttpRequestToContext="false"/>
|
||||
@@ -749,14 +797,6 @@
|
||||
</queryResponseWriter>
|
||||
-->
|
||||
|
||||
<!-- XSLT response writer transforms the XML output by any xslt file found
|
||||
in Solr's conf/xslt directory. Changes to xslt files are checked for
|
||||
every xsltCacheLifetimeSeconds.
|
||||
-->
|
||||
<queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
|
||||
<int name="xsltCacheLifetimeSeconds">5</int>
|
||||
</queryResponseWriter>
|
||||
|
||||
<!-- Query Parsers
|
||||
|
||||
https://lucene.apache.org/solr/guide/query-syntax-and-parsing.html
|
||||
|
||||
@@ -52,8 +52,9 @@
|
||||
<str name="field">twm_suggest</str>
|
||||
<str name="suggestAnalyzerFieldType">text_en</str>
|
||||
<str name="contextField">sm_context_tags</str>
|
||||
<str name="buildOnCommit">true</str>
|
||||
<str name="buildOnCommit">false</str>
|
||||
<str name="buildOnStartup">false</str>
|
||||
<str name="indexPath">./en</str>
|
||||
</lst>
|
||||
|
||||
<lst name="suggester">
|
||||
@@ -63,18 +64,20 @@
|
||||
<str name="field">twm_suggest</str>
|
||||
<str name="suggestAnalyzerFieldType">text_fr</str>
|
||||
<str name="contextField">sm_context_tags</str>
|
||||
<str name="buildOnCommit">true</str>
|
||||
<str name="buildOnCommit">false</str>
|
||||
<str name="buildOnStartup">false</str>
|
||||
<str name="indexPath">./fr</str>
|
||||
</lst>
|
||||
|
||||
<lst name="suggester">
|
||||
<str name="name">und</str>
|
||||
<str name="indexPath">./und</str>
|
||||
<str name="lookupImpl">AnalyzingInfixLookupFactory</str>
|
||||
<str name="dictionaryImpl">DocumentDictionaryFactory</str>
|
||||
<str name="field">twm_suggest</str>
|
||||
<str name="suggestAnalyzerFieldType">text_und</str>
|
||||
<str name="contextField">sm_context_tags</str>
|
||||
<str name="buildOnCommit">true</str>
|
||||
<str name="buildOnCommit">false</str>
|
||||
<str name="buildOnStartup">false</str>
|
||||
</lst>
|
||||
</searchComponent>
|
||||
@@ -178,7 +181,7 @@
|
||||
<lst name="defaults">
|
||||
<str name="suggest">true</str>
|
||||
<str name="suggest.dictionary">und</str>
|
||||
<str name="suggest.dictionary">10</str>
|
||||
<str name="suggest.count">10</str>
|
||||
</lst>
|
||||
<arr name="components">
|
||||
<str>suggest</str>
|
||||
|
||||
@@ -1,46 +1,46 @@
|
||||
<!--
|
||||
Document Cache
|
||||
7.0.0
|
||||
9.0.0
|
||||
-->
|
||||
<documentCache class="solr.LRUCache" size="512" initialSize="512" autowarmCount="0"/>
|
||||
<documentCache class="solr.CaffeineCache" size="512" initialSize="512" autowarmCount="0"/>
|
||||
|
||||
<!--
|
||||
Field Value Cache
|
||||
7.0.0
|
||||
9.0.0
|
||||
-->
|
||||
<fieldValueCache class="solr.FastLRUCache" size="512" autowarmCount="128" showItems="32"/>
|
||||
<fieldValueCache class="solr.CaffeineCache" size="512" autowarmCount="128" showItems="32"/>
|
||||
|
||||
<!--
|
||||
Filter Cache
|
||||
7.0.0
|
||||
9.0.0
|
||||
-->
|
||||
<filterCache class="solr.FastLRUCache" size="512" initialSize="512" autowarmCount="0"/>
|
||||
<filterCache class="solr.CaffeineCache" size="512" initialSize="512" autowarmCount="0"/>
|
||||
|
||||
<!--
|
||||
Per Segment Filter Cache
|
||||
7.0.0
|
||||
9.0.0
|
||||
-->
|
||||
<cache name="perSegFilter" class="solr.search.LRUCache" size="10" initialSize="0" autowarmCount="10" regenerator="solr.NoOpRegenerator"/>
|
||||
<cache name="perSegFilter" class="solr.CaffeineCache" size="10" initialSize="0" autowarmCount="10" regenerator="solr.NoOpRegenerator"/>
|
||||
|
||||
<!--
|
||||
Query Result Cache
|
||||
7.0.0
|
||||
9.0.0
|
||||
-->
|
||||
<queryResultCache class="solr.LRUCache" size="512" initialSize="512" autowarmCount="0"/>
|
||||
<queryResultCache class="solr.CaffeineCache" size="512" initialSize="512" autowarmCount="0"/>
|
||||
|
||||
<!--
|
||||
Special configs for Field Value Cache
|
||||
7.0.0
|
||||
9.0.0
|
||||
-->
|
||||
<query name="enableLazyFieldLoading">true</query>
|
||||
<!--
|
||||
Special configs for Filter Cache
|
||||
7.0.0
|
||||
9.0.0
|
||||
-->
|
||||
<query name="useFilterForSortedQuery">false</query>
|
||||
<!--
|
||||
Special configs for Query Result Cache
|
||||
7.0.0
|
||||
9.0.0
|
||||
-->
|
||||
<query name="queryResultWindowSize">20</query>
|
||||
<query name="queryResultMaxDocsCached">200</query>
|
||||
|
||||
@@ -2,12 +2,12 @@ solr.replication.master=false
|
||||
solr.replication.slave=false
|
||||
solr.replication.pollInterval=00:00:60
|
||||
solr.replication.masterUrl=http://localhost:8983/solr
|
||||
solr.replication.confFiles=schema.xml,schema_extra_types.xml,schema_extra_fields.xml,elevate.xml,stopwords_en.txt,synonyms_en.txt,protwords_en.txt,accents_en.txt,stopwords_fr.txt,synonyms_fr.txt,nouns_fr.txt,protwords_fr.txt,accents_fr.txt,stopwords_und.txt,synonyms_und.txt,protwords_und.txt,accents_und.txt
|
||||
solr.replication.confFiles=schema.xml,schema_extra_types.xml,schema_extra_fields.xml,elevate.xml,stopwords_en.txt,protwords_en.txt,accents_en.txt,synonyms_en.txt,stopwords_fr.txt,protwords_fr.txt,accents_fr.txt,synonyms_fr.txt,nouns_fr.txt,stopwords_und.txt,synonyms_und.txt,protwords_und.txt,accents_und.txt
|
||||
solr.mlt.timeAllowed=2000
|
||||
solr.selectSearchHandler.timeAllowed=-1
|
||||
solr.autoCommit.MaxDocs=-1
|
||||
solr.autoCommit.MaxTime=15000
|
||||
solr.autoSoftCommit.MaxDocs=-1
|
||||
solr.autoSoftCommit.MaxTime=-1
|
||||
solr.install.dir=/opt/solr
|
||||
solr.luceneMatchVersion=8.0
|
||||
solr.autoSoftCommit.MaxTime=5000
|
||||
solr.install.dir=../../..
|
||||
solr.luceneMatchVersion=9.1.0
|
||||
|
||||
@@ -1,420 +0,0 @@
|
||||
#
|
||||
# This file defines a Japanese stoptag set for JapanesePartOfSpeechStopFilter.
|
||||
#
|
||||
# Any token with a part-of-speech tag that exactly matches those defined in this
|
||||
# file are removed from the token stream.
|
||||
#
|
||||
# Set your own stoptags by uncommenting the lines below. Note that comments are
|
||||
# not allowed on the same line as a stoptag. See LUCENE-3745 for frequency lists,
|
||||
# etc. that can be useful for building you own stoptag set.
|
||||
#
|
||||
# The entire possible tagset is provided below for convenience.
|
||||
#
|
||||
#####
|
||||
# noun: unclassified nouns
|
||||
#名詞
|
||||
#
|
||||
# noun-common: Common nouns or nouns where the sub-classification is undefined
|
||||
#名詞-一般
|
||||
#
|
||||
# noun-proper: Proper nouns where the sub-classification is undefined
|
||||
#名詞-固有名詞
|
||||
#
|
||||
# noun-proper-misc: miscellaneous proper nouns
|
||||
#名詞-固有名詞-一般
|
||||
#
|
||||
# noun-proper-person: Personal names where the sub-classification is undefined
|
||||
#名詞-固有名詞-人名
|
||||
#
|
||||
# noun-proper-person-misc: names that cannot be divided into surname and
|
||||
# given name; foreign names; names where the surname or given name is unknown.
|
||||
# e.g. お市の方
|
||||
#名詞-固有名詞-人名-一般
|
||||
#
|
||||
# noun-proper-person-surname: Mainly Japanese surnames.
|
||||
# e.g. 山田
|
||||
#名詞-固有名詞-人名-姓
|
||||
#
|
||||
# noun-proper-person-given_name: Mainly Japanese given names.
|
||||
# e.g. 太郎
|
||||
#名詞-固有名詞-人名-名
|
||||
#
|
||||
# noun-proper-organization: Names representing organizations.
|
||||
# e.g. 通産省, NHK
|
||||
#名詞-固有名詞-組織
|
||||
#
|
||||
# noun-proper-place: Place names where the sub-classification is undefined
|
||||
#名詞-固有名詞-地域
|
||||
#
|
||||
# noun-proper-place-misc: Place names excluding countries.
|
||||
# e.g. アジア, バルセロナ, 京都
|
||||
#名詞-固有名詞-地域-一般
|
||||
#
|
||||
# noun-proper-place-country: Country names.
|
||||
# e.g. 日本, オーストラリア
|
||||
#名詞-固有名詞-地域-国
|
||||
#
|
||||
# noun-pronoun: Pronouns where the sub-classification is undefined
|
||||
#名詞-代名詞
|
||||
#
|
||||
# noun-pronoun-misc: miscellaneous pronouns:
|
||||
# e.g. それ, ここ, あいつ, あなた, あちこち, いくつ, どこか, なに, みなさん, みんな, わたくし, われわれ
|
||||
#名詞-代名詞-一般
|
||||
#
|
||||
# noun-pronoun-contraction: Spoken language contraction made by combining a
|
||||
# pronoun and the particle 'wa'.
|
||||
# e.g. ありゃ, こりゃ, こりゃあ, そりゃ, そりゃあ
|
||||
#名詞-代名詞-縮約
|
||||
#
|
||||
# noun-adverbial: Temporal nouns such as names of days or months that behave
|
||||
# like adverbs. Nouns that represent amount or ratios and can be used adverbially,
|
||||
# e.g. 金曜, 一月, 午後, 少量
|
||||
#名詞-副詞可能
|
||||
#
|
||||
# noun-verbal: Nouns that take arguments with case and can appear followed by
|
||||
# 'suru' and related verbs (する, できる, なさる, くださる)
|
||||
# e.g. インプット, 愛着, 悪化, 悪戦苦闘, 一安心, 下取り
|
||||
#名詞-サ変接続
|
||||
#
|
||||
# noun-adjective-base: The base form of adjectives, words that appear before な ("na")
|
||||
# e.g. 健康, 安易, 駄目, だめ
|
||||
#名詞-形容動詞語幹
|
||||
#
|
||||
# noun-numeric: Arabic numbers, Chinese numerals, and counters like 何 (回), 数.
|
||||
# e.g. 0, 1, 2, 何, 数, 幾
|
||||
#名詞-数
|
||||
#
|
||||
# noun-affix: noun affixes where the sub-classification is undefined
|
||||
#名詞-非自立
|
||||
#
|
||||
# noun-affix-misc: Of adnominalizers, the case-marker の ("no"), and words that
|
||||
# attach to the base form of inflectional words, words that cannot be classified
|
||||
# into any of the other categories below. This category includes indefinite nouns.
|
||||
# e.g. あかつき, 暁, かい, 甲斐, 気, きらい, 嫌い, くせ, 癖, こと, 事, ごと, 毎, しだい, 次第,
|
||||
# 順, せい, 所為, ついで, 序で, つもり, 積もり, 点, どころ, の, はず, 筈, はずみ, 弾み,
|
||||
# 拍子, ふう, ふり, 振り, ほう, 方, 旨, もの, 物, 者, ゆえ, 故, ゆえん, 所以, わけ, 訳,
|
||||
# わり, 割り, 割, ん-口語/, もん-口語/
|
||||
#名詞-非自立-一般
|
||||
#
|
||||
# noun-affix-adverbial: noun affixes that that can behave as adverbs.
|
||||
# e.g. あいだ, 間, あげく, 挙げ句, あと, 後, 余り, 以外, 以降, 以後, 以上, 以前, 一方, うえ,
|
||||
# 上, うち, 内, おり, 折り, かぎり, 限り, きり, っきり, 結果, ころ, 頃, さい, 際, 最中, さなか,
|
||||
# 最中, じたい, 自体, たび, 度, ため, 為, つど, 都度, とおり, 通り, とき, 時, ところ, 所,
|
||||
# とたん, 途端, なか, 中, のち, 後, ばあい, 場合, 日, ぶん, 分, ほか, 他, まえ, 前, まま,
|
||||
# 儘, 侭, みぎり, 矢先
|
||||
#名詞-非自立-副詞可能
|
||||
#
|
||||
# noun-affix-aux: noun affixes treated as 助動詞 ("auxiliary verb") in school grammars
|
||||
# with the stem よう(だ) ("you(da)").
|
||||
# e.g. よう, やう, 様 (よう)
|
||||
#名詞-非自立-助動詞語幹
|
||||
#
|
||||
# noun-affix-adjective-base: noun affixes that can connect to the indeclinable
|
||||
# connection form な (aux "da").
|
||||
# e.g. みたい, ふう
|
||||
#名詞-非自立-形容動詞語幹
|
||||
#
|
||||
# noun-special: special nouns where the sub-classification is undefined.
|
||||
#名詞-特殊
|
||||
#
|
||||
# noun-special-aux: The そうだ ("souda") stem form that is used for reporting news, is
|
||||
# treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the base
|
||||
# form of inflectional words.
|
||||
# e.g. そう
|
||||
#名詞-特殊-助動詞語幹
|
||||
#
|
||||
# noun-suffix: noun suffixes where the sub-classification is undefined.
|
||||
#名詞-接尾
|
||||
#
|
||||
# noun-suffix-misc: Of the nouns or stem forms of other parts of speech that connect
|
||||
# to ガル or タイ and can combine into compound nouns, words that cannot be classified into
|
||||
# any of the other categories below. In general, this category is more inclusive than
|
||||
# 接尾語 ("suffix") and is usually the last element in a compound noun.
|
||||
# e.g. おき, かた, 方, 甲斐 (がい), がかり, ぎみ, 気味, ぐるみ, (~した) さ, 次第, 済 (ず) み,
|
||||
# よう, (でき)っこ, 感, 観, 性, 学, 類, 面, 用
|
||||
#名詞-接尾-一般
|
||||
#
|
||||
# noun-suffix-person: Suffixes that form nouns and attach to person names more often
|
||||
# than other nouns.
|
||||
# e.g. 君, 様, 著
|
||||
#名詞-接尾-人名
|
||||
#
|
||||
# noun-suffix-place: Suffixes that form nouns and attach to place names more often
|
||||
# than other nouns.
|
||||
# e.g. 町, 市, 県
|
||||
#名詞-接尾-地域
|
||||
#
|
||||
# noun-suffix-verbal: Of the suffixes that attach to nouns and form nouns, those that
|
||||
# can appear before スル ("suru").
|
||||
# e.g. 化, 視, 分け, 入り, 落ち, 買い
|
||||
#名詞-接尾-サ変接続
|
||||
#
|
||||
# noun-suffix-aux: The stem form of そうだ (様態) that is used to indicate conditions,
|
||||
# is treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the
|
||||
# conjunctive form of inflectional words.
|
||||
# e.g. そう
|
||||
#名詞-接尾-助動詞語幹
|
||||
#
|
||||
# noun-suffix-adjective-base: Suffixes that attach to other nouns or the conjunctive
|
||||
# form of inflectional words and appear before the copula だ ("da").
|
||||
# e.g. 的, げ, がち
|
||||
#名詞-接尾-形容動詞語幹
|
||||
#
|
||||
# noun-suffix-adverbial: Suffixes that attach to other nouns and can behave as adverbs.
|
||||
# e.g. 後 (ご), 以後, 以降, 以前, 前後, 中, 末, 上, 時 (じ)
|
||||
#名詞-接尾-副詞可能
|
||||
#
|
||||
# noun-suffix-classifier: Suffixes that attach to numbers and form nouns. This category
|
||||
# is more inclusive than 助数詞 ("classifier") and includes common nouns that attach
|
||||
# to numbers.
|
||||
# e.g. 個, つ, 本, 冊, パーセント, cm, kg, カ月, か国, 区画, 時間, 時半
|
||||
#名詞-接尾-助数詞
|
||||
#
|
||||
# noun-suffix-special: Special suffixes that mainly attach to inflecting words.
|
||||
# e.g. (楽し) さ, (考え) 方
|
||||
#名詞-接尾-特殊
|
||||
#
|
||||
# noun-suffix-conjunctive: Nouns that behave like conjunctions and join two words
|
||||
# together.
|
||||
# e.g. (日本) 対 (アメリカ), 対 (アメリカ), (3) 対 (5), (女優) 兼 (主婦)
|
||||
#名詞-接続詞的
|
||||
#
|
||||
# noun-verbal_aux: Nouns that attach to the conjunctive particle て ("te") and are
|
||||
# semantically verb-like.
|
||||
# e.g. ごらん, ご覧, 御覧, 頂戴
|
||||
#名詞-動詞非自立的
|
||||
#
|
||||
# noun-quotation: text that cannot be segmented into words, proverbs, Chinese poetry,
|
||||
# dialects, English, etc. Currently, the only entry for 名詞 引用文字列 ("noun quotation")
|
||||
# is いわく ("iwaku").
|
||||
#名詞-引用文字列
|
||||
#
|
||||
# noun-nai_adjective: Words that appear before the auxiliary verb ない ("nai") and
|
||||
# behave like an adjective.
|
||||
# e.g. 申し訳, 仕方, とんでも, 違い
|
||||
#名詞-ナイ形容詞語幹
|
||||
#
|
||||
#####
|
||||
# prefix: unclassified prefixes
|
||||
#接頭詞
|
||||
#
|
||||
# prefix-nominal: Prefixes that attach to nouns (including adjective stem forms)
|
||||
# excluding numerical expressions.
|
||||
# e.g. お (水), 某 (氏), 同 (社), 故 (~氏), 高 (品質), お (見事), ご (立派)
|
||||
#接頭詞-名詞接続
|
||||
#
|
||||
# prefix-verbal: Prefixes that attach to the imperative form of a verb or a verb
|
||||
# in conjunctive form followed by なる/なさる/くださる.
|
||||
# e.g. お (読みなさい), お (座り)
|
||||
#接頭詞-動詞接続
|
||||
#
|
||||
# prefix-adjectival: Prefixes that attach to adjectives.
|
||||
# e.g. お (寒いですねえ), バカ (でかい)
|
||||
#接頭詞-形容詞接続
|
||||
#
|
||||
# prefix-numerical: Prefixes that attach to numerical expressions.
|
||||
# e.g. 約, およそ, 毎時
|
||||
#接頭詞-数接続
|
||||
#
|
||||
#####
|
||||
# verb: unclassified verbs
|
||||
#動詞
|
||||
#
|
||||
# verb-main:
|
||||
#動詞-自立
|
||||
#
|
||||
# verb-auxiliary:
|
||||
#動詞-非自立
|
||||
#
|
||||
# verb-suffix:
|
||||
#動詞-接尾
|
||||
#
|
||||
#####
|
||||
# adjective: unclassified adjectives
|
||||
#形容詞
|
||||
#
|
||||
# adjective-main:
|
||||
#形容詞-自立
|
||||
#
|
||||
# adjective-auxiliary:
|
||||
#形容詞-非自立
|
||||
#
|
||||
# adjective-suffix:
|
||||
#形容詞-接尾
|
||||
#
|
||||
#####
|
||||
# adverb: unclassified adverbs
|
||||
#副詞
|
||||
#
|
||||
# adverb-misc: Words that can be segmented into one unit and where adnominal
|
||||
# modification is not possible.
|
||||
# e.g. あいかわらず, 多分
|
||||
#副詞-一般
|
||||
#
|
||||
# adverb-particle_conjunction: Adverbs that can be followed by の, は, に,
|
||||
# な, する, だ, etc.
|
||||
# e.g. こんなに, そんなに, あんなに, なにか, なんでも
|
||||
#副詞-助詞類接続
|
||||
#
|
||||
#####
|
||||
# adnominal: Words that only have noun-modifying forms.
|
||||
# e.g. この, その, あの, どの, いわゆる, なんらかの, 何らかの, いろんな, こういう, そういう, ああいう,
|
||||
# どういう, こんな, そんな, あんな, どんな, 大きな, 小さな, おかしな, ほんの, たいした,
|
||||
# 「(, も) さる (ことながら)」, 微々たる, 堂々たる, 単なる, いかなる, 我が」「同じ, 亡き
|
||||
#連体詞
|
||||
#
|
||||
#####
|
||||
# conjunction: Conjunctions that can occur independently.
|
||||
# e.g. が, けれども, そして, じゃあ, それどころか
|
||||
接続詞
|
||||
#
|
||||
#####
|
||||
# particle: unclassified particles.
|
||||
助詞
|
||||
#
|
||||
# particle-case: case particles where the subclassification is undefined.
|
||||
助詞-格助詞
|
||||
#
|
||||
# particle-case-misc: Case particles.
|
||||
# e.g. から, が, で, と, に, へ, より, を, の, にて
|
||||
助詞-格助詞-一般
|
||||
#
|
||||
# particle-case-quote: the "to" that appears after nouns, a person’s speech,
|
||||
# quotation marks, expressions of decisions from a meeting, reasons, judgements,
|
||||
# conjectures, etc.
|
||||
# e.g. ( だ) と (述べた.), ( である) と (して執行猶予...)
|
||||
助詞-格助詞-引用
|
||||
#
|
||||
# particle-case-compound: Compounds of particles and verbs that mainly behave
|
||||
# like case particles.
|
||||
# e.g. という, といった, とかいう, として, とともに, と共に, でもって, にあたって, に当たって, に当って,
|
||||
# にあたり, に当たり, に当り, に当たる, にあたる, において, に於いて,に於て, における, に於ける,
|
||||
# にかけ, にかけて, にかんし, に関し, にかんして, に関して, にかんする, に関する, に際し,
|
||||
# に際して, にしたがい, に従い, に従う, にしたがって, に従って, にたいし, に対し, にたいして,
|
||||
# に対して, にたいする, に対する, について, につき, につけ, につけて, につれ, につれて, にとって,
|
||||
# にとり, にまつわる, によって, に依って, に因って, により, に依り, に因り, による, に依る, に因る,
|
||||
# にわたって, にわたる, をもって, を以って, を通じ, を通じて, を通して, をめぐって, をめぐり, をめぐる,
|
||||
# って-口語/, ちゅう-関西弁「という」/, (何) ていう (人)-口語/, っていう-口語/, といふ, とかいふ
|
||||
助詞-格助詞-連語
|
||||
#
|
||||
# particle-conjunctive:
|
||||
# e.g. から, からには, が, けれど, けれども, けど, し, つつ, て, で, と, ところが, どころか, とも, ども,
|
||||
# ながら, なり, ので, のに, ば, ものの, や ( した), やいなや, (ころん) じゃ(いけない)-口語/,
|
||||
# (行っ) ちゃ(いけない)-口語/, (言っ) たって (しかたがない)-口語/, (それがなく)ったって (平気)-口語/
|
||||
助詞-接続助詞
|
||||
#
|
||||
# particle-dependency:
|
||||
# e.g. こそ, さえ, しか, すら, は, も, ぞ
|
||||
助詞-係助詞
|
||||
#
|
||||
# particle-adverbial:
|
||||
# e.g. がてら, かも, くらい, 位, ぐらい, しも, (学校) じゃ(これが流行っている)-口語/,
|
||||
# (それ)じゃあ (よくない)-口語/, ずつ, (私) なぞ, など, (私) なり (に), (先生) なんか (大嫌い)-口語/,
|
||||
# (私) なんぞ, (先生) なんて (大嫌い)-口語/, のみ, だけ, (私) だって-口語/, だに,
|
||||
# (彼)ったら-口語/, (お茶) でも (いかが), 等 (とう), (今後) とも, ばかり, ばっか-口語/, ばっかり-口語/,
|
||||
# ほど, 程, まで, 迄, (誰) も (が)([助詞-格助詞] および [助詞-係助詞] の前に位置する「も」)
|
||||
助詞-副助詞
|
||||
#
|
||||
# particle-interjective: particles with interjective grammatical roles.
|
||||
# e.g. (松島) や
|
||||
助詞-間投助詞
|
||||
#
|
||||
# particle-coordinate:
|
||||
# e.g. と, たり, だの, だり, とか, なり, や, やら
|
||||
助詞-並立助詞
|
||||
#
|
||||
# particle-final:
|
||||
# e.g. かい, かしら, さ, ぜ, (だ)っけ-口語/, (とまってる) で-方言/, な, ナ, なあ-口語/, ぞ, ね, ネ,
|
||||
# ねぇ-口語/, ねえ-口語/, ねん-方言/, の, のう-口語/, や, よ, ヨ, よぉ-口語/, わ, わい-口語/
|
||||
助詞-終助詞
|
||||
#
|
||||
# particle-adverbial/conjunctive/final: The particle "ka" when unknown whether it is
|
||||
# adverbial, conjunctive, or sentence final. For example:
|
||||
# (a) 「A か B か」. Ex:「(国内で運用する) か,(海外で運用する) か (.)」
|
||||
# (b) Inside an adverb phrase. Ex:「(幸いという) か (, 死者はいなかった.)」
|
||||
# 「(祈りが届いたせい) か (, 試験に合格した.)」
|
||||
# (c) 「かのように」. Ex:「(何もなかった) か (のように振る舞った.)」
|
||||
# e.g. か
|
||||
助詞-副助詞/並立助詞/終助詞
|
||||
#
|
||||
# particle-adnominalizer: The "no" that attaches to nouns and modifies
|
||||
# non-inflectional words.
|
||||
助詞-連体化
|
||||
#
|
||||
# particle-adnominalizer: The "ni" and "to" that appear following nouns and adverbs
|
||||
# that are giongo, giseigo, or gitaigo.
|
||||
# e.g. に, と
|
||||
助詞-副詞化
|
||||
#
|
||||
# particle-special: A particle that does not fit into one of the above classifications.
|
||||
# This includes particles that are used in Tanka, Haiku, and other poetry.
|
||||
# e.g. かな, けむ, ( しただろう) に, (あんた) にゃ(わからん), (俺) ん (家)
|
||||
助詞-特殊
|
||||
#
|
||||
#####
|
||||
# auxiliary-verb:
|
||||
助動詞
|
||||
#
|
||||
#####
|
||||
# interjection: Greetings and other exclamations.
|
||||
# e.g. おはよう, おはようございます, こんにちは, こんばんは, ありがとう, どうもありがとう, ありがとうございます,
|
||||
# いただきます, ごちそうさま, さよなら, さようなら, はい, いいえ, ごめん, ごめんなさい
|
||||
#感動詞
|
||||
#
|
||||
#####
|
||||
# symbol: unclassified Symbols.
|
||||
記号
|
||||
#
|
||||
# symbol-misc: A general symbol not in one of the categories below.
|
||||
# e.g. [○◎@$〒→+]
|
||||
記号-一般
|
||||
#
|
||||
# symbol-comma: Commas
|
||||
# e.g. [,、]
|
||||
記号-読点
|
||||
#
|
||||
# symbol-period: Periods and full stops.
|
||||
# e.g. [..。]
|
||||
記号-句点
|
||||
#
|
||||
# symbol-space: Full-width whitespace.
|
||||
記号-空白
|
||||
#
|
||||
# symbol-open_bracket:
|
||||
# e.g. [({‘“『【]
|
||||
記号-括弧開
|
||||
#
|
||||
# symbol-close_bracket:
|
||||
# e.g. [)}’”』」】]
|
||||
記号-括弧閉
|
||||
#
|
||||
# symbol-alphabetic:
|
||||
#記号-アルファベット
|
||||
#
|
||||
#####
|
||||
# other: unclassified other
|
||||
#その他
|
||||
#
|
||||
# other-interjection: Words that are hard to classify as noun-suffixes or
|
||||
# sentence-final particles.
|
||||
# e.g. (だ)ァ
|
||||
その他-間投
|
||||
#
|
||||
#####
|
||||
# filler: Aizuchi that occurs during a conversation or sounds inserted as filler.
|
||||
# e.g. あの, うんと, えと
|
||||
フィラー
|
||||
#
|
||||
#####
|
||||
# non-verbal: non-verbal sound.
|
||||
非言語音
|
||||
#
|
||||
#####
|
||||
# fragment:
|
||||
#語断片
|
||||
#
|
||||
#####
|
||||
# unknown: unknown part of speech.
|
||||
#未知語
|
||||
#
|
||||
##### End of file
|
||||
@@ -1,119 +0,0 @@
|
||||
من
|
||||
ومن
|
||||
منها
|
||||
منه
|
||||
في
|
||||
وفي
|
||||
فيها
|
||||
فيه
|
||||
و
|
||||
ف
|
||||
ثم
|
||||
او
|
||||
أو
|
||||
ب
|
||||
بها
|
||||
به
|
||||
ا
|
||||
أ
|
||||
اى
|
||||
اي
|
||||
أي
|
||||
أى
|
||||
لا
|
||||
ولا
|
||||
الا
|
||||
ألا
|
||||
إلا
|
||||
لكن
|
||||
ما
|
||||
وما
|
||||
كما
|
||||
فما
|
||||
عن
|
||||
مع
|
||||
اذا
|
||||
إذا
|
||||
ان
|
||||
أن
|
||||
إن
|
||||
انها
|
||||
أنها
|
||||
إنها
|
||||
انه
|
||||
أنه
|
||||
إنه
|
||||
بان
|
||||
بأن
|
||||
فان
|
||||
فأن
|
||||
وان
|
||||
وأن
|
||||
وإن
|
||||
التى
|
||||
التي
|
||||
الذى
|
||||
الذي
|
||||
الذين
|
||||
الى
|
||||
الي
|
||||
إلى
|
||||
إلي
|
||||
على
|
||||
عليها
|
||||
عليه
|
||||
اما
|
||||
أما
|
||||
إما
|
||||
ايضا
|
||||
أيضا
|
||||
كل
|
||||
وكل
|
||||
لم
|
||||
ولم
|
||||
لن
|
||||
ولن
|
||||
هى
|
||||
هي
|
||||
هو
|
||||
وهى
|
||||
وهي
|
||||
وهو
|
||||
فهى
|
||||
فهي
|
||||
فهو
|
||||
انت
|
||||
أنت
|
||||
لك
|
||||
لها
|
||||
له
|
||||
هذه
|
||||
هذا
|
||||
تلك
|
||||
ذلك
|
||||
هناك
|
||||
كانت
|
||||
كان
|
||||
يكون
|
||||
تكون
|
||||
وكانت
|
||||
وكان
|
||||
غير
|
||||
بعض
|
||||
قد
|
||||
نحو
|
||||
بين
|
||||
بينما
|
||||
منذ
|
||||
ضمن
|
||||
حيث
|
||||
الان
|
||||
الآن
|
||||
خلال
|
||||
بعد
|
||||
قبل
|
||||
حتى
|
||||
عند
|
||||
عندما
|
||||
لدى
|
||||
جميع
|
||||
@@ -1,190 +0,0 @@
|
||||
а
|
||||
аз
|
||||
ако
|
||||
ала
|
||||
бе
|
||||
без
|
||||
беше
|
||||
би
|
||||
бил
|
||||
била
|
||||
били
|
||||
било
|
||||
близо
|
||||
бъдат
|
||||
бъде
|
||||
бяха
|
||||
в
|
||||
вас
|
||||
ваш
|
||||
ваша
|
||||
вероятно
|
||||
вече
|
||||
взема
|
||||
ви
|
||||
вие
|
||||
винаги
|
||||
все
|
||||
всеки
|
||||
всички
|
||||
всичко
|
||||
всяка
|
||||
във
|
||||
въпреки
|
||||
върху
|
||||
г
|
||||
ги
|
||||
главно
|
||||
го
|
||||
д
|
||||
да
|
||||
дали
|
||||
до
|
||||
докато
|
||||
докога
|
||||
дори
|
||||
досега
|
||||
доста
|
||||
е
|
||||
едва
|
||||
един
|
||||
ето
|
||||
за
|
||||
зад
|
||||
заедно
|
||||
заради
|
||||
засега
|
||||
затова
|
||||
защо
|
||||
защото
|
||||
и
|
||||
из
|
||||
или
|
||||
им
|
||||
има
|
||||
имат
|
||||
иска
|
||||
й
|
||||
каза
|
||||
как
|
||||
каква
|
||||
какво
|
||||
както
|
||||
какъв
|
||||
като
|
||||
кога
|
||||
когато
|
||||
което
|
||||
които
|
||||
кой
|
||||
който
|
||||
колко
|
||||
която
|
||||
къде
|
||||
където
|
||||
към
|
||||
ли
|
||||
м
|
||||
ме
|
||||
между
|
||||
мен
|
||||
ми
|
||||
мнозина
|
||||
мога
|
||||
могат
|
||||
може
|
||||
моля
|
||||
момента
|
||||
му
|
||||
н
|
||||
на
|
||||
над
|
||||
назад
|
||||
най
|
||||
направи
|
||||
напред
|
||||
например
|
||||
нас
|
||||
не
|
||||
него
|
||||
нея
|
||||
ни
|
||||
ние
|
||||
никой
|
||||
нито
|
||||
но
|
||||
някои
|
||||
някой
|
||||
няма
|
||||
обаче
|
||||
около
|
||||
освен
|
||||
особено
|
||||
от
|
||||
отгоре
|
||||
отново
|
||||
още
|
||||
пак
|
||||
по
|
||||
повече
|
||||
повечето
|
||||
под
|
||||
поне
|
||||
поради
|
||||
после
|
||||
почти
|
||||
прави
|
||||
пред
|
||||
преди
|
||||
през
|
||||
при
|
||||
пък
|
||||
първо
|
||||
с
|
||||
са
|
||||
само
|
||||
се
|
||||
сега
|
||||
си
|
||||
скоро
|
||||
след
|
||||
сме
|
||||
според
|
||||
сред
|
||||
срещу
|
||||
сте
|
||||
съм
|
||||
със
|
||||
също
|
||||
т
|
||||
тази
|
||||
така
|
||||
такива
|
||||
такъв
|
||||
там
|
||||
твой
|
||||
те
|
||||
тези
|
||||
ти
|
||||
тн
|
||||
то
|
||||
това
|
||||
тогава
|
||||
този
|
||||
той
|
||||
толкова
|
||||
точно
|
||||
трябва
|
||||
тук
|
||||
тъй
|
||||
тя
|
||||
тях
|
||||
у
|
||||
харесва
|
||||
ч
|
||||
че
|
||||
често
|
||||
чрез
|
||||
ще
|
||||
щом
|
||||
я
|
||||
@@ -1,219 +0,0 @@
|
||||
a
|
||||
abans
|
||||
ací
|
||||
ah
|
||||
així
|
||||
això
|
||||
al
|
||||
als
|
||||
aleshores
|
||||
algun
|
||||
alguna
|
||||
algunes
|
||||
alguns
|
||||
alhora
|
||||
allà
|
||||
allí
|
||||
allò
|
||||
altra
|
||||
altre
|
||||
altres
|
||||
amb
|
||||
ambdós
|
||||
ambdues
|
||||
apa
|
||||
aquell
|
||||
aquella
|
||||
aquelles
|
||||
aquells
|
||||
aquest
|
||||
aquesta
|
||||
aquestes
|
||||
aquests
|
||||
aquí
|
||||
baix
|
||||
cada
|
||||
cadascú
|
||||
cadascuna
|
||||
cadascunes
|
||||
cadascuns
|
||||
com
|
||||
contra
|
||||
d'un
|
||||
d'una
|
||||
d'unes
|
||||
d'uns
|
||||
dalt
|
||||
de
|
||||
del
|
||||
dels
|
||||
des
|
||||
després
|
||||
dins
|
||||
dintre
|
||||
donat
|
||||
doncs
|
||||
durant
|
||||
e
|
||||
eh
|
||||
el
|
||||
els
|
||||
em
|
||||
en
|
||||
encara
|
||||
ens
|
||||
entre
|
||||
érem
|
||||
eren
|
||||
éreu
|
||||
es
|
||||
és
|
||||
esta
|
||||
està
|
||||
estàvem
|
||||
estaven
|
||||
estàveu
|
||||
esteu
|
||||
et
|
||||
etc
|
||||
ets
|
||||
fins
|
||||
fora
|
||||
gairebé
|
||||
ha
|
||||
han
|
||||
has
|
||||
havia
|
||||
he
|
||||
hem
|
||||
heu
|
||||
hi
|
||||
ho
|
||||
i
|
||||
igual
|
||||
iguals
|
||||
ja
|
||||
l'hi
|
||||
la
|
||||
les
|
||||
li
|
||||
li'n
|
||||
llavors
|
||||
m'he
|
||||
ma
|
||||
mal
|
||||
malgrat
|
||||
mateix
|
||||
mateixa
|
||||
mateixes
|
||||
mateixos
|
||||
me
|
||||
mentre
|
||||
més
|
||||
meu
|
||||
meus
|
||||
meva
|
||||
meves
|
||||
molt
|
||||
molta
|
||||
moltes
|
||||
molts
|
||||
mon
|
||||
mons
|
||||
n'he
|
||||
n'hi
|
||||
ne
|
||||
ni
|
||||
no
|
||||
nogensmenys
|
||||
només
|
||||
nosaltres
|
||||
nostra
|
||||
nostre
|
||||
nostres
|
||||
o
|
||||
oh
|
||||
oi
|
||||
on
|
||||
pas
|
||||
pel
|
||||
pels
|
||||
per
|
||||
però
|
||||
perquè
|
||||
poc
|
||||
poca
|
||||
pocs
|
||||
poques
|
||||
potser
|
||||
propi
|
||||
qual
|
||||
quals
|
||||
quan
|
||||
quant
|
||||
que
|
||||
què
|
||||
quelcom
|
||||
qui
|
||||
quin
|
||||
quina
|
||||
quines
|
||||
quins
|
||||
s'ha
|
||||
s'han
|
||||
sa
|
||||
semblant
|
||||
semblants
|
||||
ses
|
||||
seu
|
||||
seus
|
||||
seva
|
||||
seva
|
||||
seves
|
||||
si
|
||||
sobre
|
||||
sobretot
|
||||
sóc
|
||||
solament
|
||||
sols
|
||||
son
|
||||
són
|
||||
sons
|
||||
sota
|
||||
sou
|
||||
t'ha
|
||||
t'han
|
||||
t'he
|
||||
ta
|
||||
tal
|
||||
també
|
||||
tampoc
|
||||
tan
|
||||
tant
|
||||
tanta
|
||||
tantes
|
||||
teu
|
||||
teus
|
||||
teva
|
||||
teves
|
||||
ton
|
||||
tons
|
||||
tot
|
||||
tota
|
||||
totes
|
||||
tots
|
||||
un
|
||||
una
|
||||
unes
|
||||
uns
|
||||
us
|
||||
va
|
||||
vaig
|
||||
vam
|
||||
van
|
||||
vas
|
||||
veu
|
||||
vosaltres
|
||||
vostra
|
||||
vostre
|
||||
vostres
|
||||
@@ -1,138 +0,0 @@
|
||||
dnes
|
||||
cz
|
||||
timto
|
||||
budes
|
||||
budem
|
||||
byli
|
||||
jses
|
||||
muj
|
||||
svym
|
||||
ta
|
||||
tomto
|
||||
tohle
|
||||
tuto
|
||||
tyto
|
||||
jej
|
||||
zda
|
||||
proc
|
||||
mate
|
||||
tato
|
||||
kam
|
||||
tohoto
|
||||
kdo
|
||||
kteri
|
||||
mi
|
||||
nam
|
||||
tom
|
||||
tomuto
|
||||
mit
|
||||
nic
|
||||
proto
|
||||
kterou
|
||||
byla
|
||||
toho
|
||||
protoze
|
||||
asi
|
||||
ho
|
||||
nasi
|
||||
napiste
|
||||
re
|
||||
coz
|
||||
tim
|
||||
takze
|
||||
svych
|
||||
jeji
|
||||
svymi
|
||||
jste
|
||||
aj
|
||||
tu
|
||||
tedy
|
||||
teto
|
||||
bylo
|
||||
kde
|
||||
ke
|
||||
prave
|
||||
ji
|
||||
nad
|
||||
nejsou
|
||||
ci
|
||||
pod
|
||||
tema
|
||||
mezi
|
||||
pres
|
||||
ty
|
||||
pak
|
||||
vam
|
||||
ani
|
||||
kdyz
|
||||
vsak
|
||||
ne
|
||||
jsem
|
||||
tento
|
||||
clanku
|
||||
clanky
|
||||
aby
|
||||
jsme
|
||||
pred
|
||||
pta
|
||||
jejich
|
||||
byl
|
||||
jeste
|
||||
az
|
||||
bez
|
||||
take
|
||||
pouze
|
||||
prvni
|
||||
vase
|
||||
ktera
|
||||
nas
|
||||
novy
|
||||
tipy
|
||||
pokud
|
||||
muze
|
||||
design
|
||||
strana
|
||||
jeho
|
||||
sve
|
||||
jine
|
||||
zpravy
|
||||
nove
|
||||
neni
|
||||
vas
|
||||
jen
|
||||
podle
|
||||
zde
|
||||
clanek
|
||||
uz
|
||||
email
|
||||
byt
|
||||
vice
|
||||
bude
|
||||
jiz
|
||||
nez
|
||||
ktery
|
||||
by
|
||||
ktere
|
||||
co
|
||||
nebo
|
||||
ten
|
||||
tak
|
||||
ma
|
||||
pri
|
||||
od
|
||||
po
|
||||
jsou
|
||||
jak
|
||||
dalsi
|
||||
ale
|
||||
si
|
||||
ve
|
||||
to
|
||||
jako
|
||||
za
|
||||
zpet
|
||||
ze
|
||||
do
|
||||
pro
|
||||
je
|
||||
na
|
||||
@@ -1,56 +0,0 @@
|
||||
af
|
||||
alle
|
||||
altid
|
||||
de
|
||||
der
|
||||
de
|
||||
du
|
||||
efter
|
||||
eller
|
||||
en
|
||||
endnu
|
||||
et
|
||||
for
|
||||
foran
|
||||
fra
|
||||
få
|
||||
gennem
|
||||
god
|
||||
han
|
||||
her
|
||||
hos
|
||||
hun
|
||||
hurtig
|
||||
hvad
|
||||
hvem
|
||||
hvornår
|
||||
hvor
|
||||
hvordan
|
||||
hvorhen
|
||||
i
|
||||
imod
|
||||
ja
|
||||
jeg
|
||||
lidt
|
||||
mange
|
||||
med
|
||||
meget
|
||||
mellem
|
||||
mere
|
||||
mindre
|
||||
måske
|
||||
nede
|
||||
nej
|
||||
nok
|
||||
nu
|
||||
når
|
||||
og
|
||||
oppe
|
||||
på
|
||||
sammen
|
||||
til
|
||||
uden
|
||||
udenfor
|
||||
under
|
||||
ved
|
||||
vi
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user