Modul:Sort/latin: Unterschied zwischen den Versionen

Aus skandinavien-wiki.net
w>Mps
(Rest von http://www.unicode.org/charts/PDF/U0180.pdf)
w>PerfektesChaos
(+ [ 7838] = "SS", -- CAPITAL SHARP S)
Zeile 1: Zeile 1:
--[=[ 2015-03-15
--[=[ 2015-03-20
Sort/latin
Sort/latin
mw.loadData() table with sort string for latin based character codes (ISO)
mw.loadData() table with sort string for latin based character codes (ISO)
Zeile 318: Zeile 318:
[  544] = "N",  -- N with long right leg
[  544] = "N",  -- N with long right leg
[  545] = "d",  -- d with curl
[  545] = "d",  -- d with curl
[  546] = "OU", -- OU
[  546] = "OU", -- OU
[  547] = "ou", -- ou
[  547] = "ou", -- ou
[  548] = "Z",  -- Z with hook
[  548] = "Z",  -- Z with hook
[  549] = "z",  -- z with hook
[  549] = "z",  -- z with hook
Zeile 340: Zeile 340:
[  566] = "t",  -- t with curl
[  566] = "t",  -- t with curl
[  567] = "j",  -- dotless j
[  567] = "j",  -- dotless j
[  568] = "db", -- db digraph
[  568] = "db", -- db digraph
[  569] = "qp", -- qp digraph
[  569] = "qp", -- qp digraph
[  570] = "A",  -- A with stroke
[  570] = "A",  -- A with stroke
[  571] = "C",  -- C with stroke
[  571] = "C",  -- C with stroke
Zeile 350: Zeile 350:
[  576] = "z",  -- z with swash tail
[  576] = "z",  -- z with swash tail
[  579] = "B",  -- B with stroke
[  579] = "B",  -- B with stroke
[  580] = "U",  -- U bar
[  580] = "U",  -- U with bar
[  581] = "V",  -- turned V
[  581] = "V",  -- turned V
[  582] = "E",  -- E with stroke
[  582] = "E",  -- E with stroke
Zeile 362: Zeile 362:
[  590] = "Y",  -- Y with stroke
[  590] = "Y",  -- Y with stroke
[  591] = "y",  -- y with stroke
[  591] = "y",  -- y with stroke
[  7838] = "SS", -- CAPITAL SHARP S
[    39] = "",  -- '
[    39] = "",  -- '
[    96] = "",  -- grave
[    96] = "",  -- grave

Version vom 20. März 2015, 11:04 Uhr

Die Dokumentation für dieses Modul kann unter Modul:Sort/latin/doc erstellt werden

--[=[ 2015-03-20
Sort/latin
mw.loadData() table with sort string for latin based character codes (ISO)
]=]
return {
[   160] = " ",  -- nbsp
[  5760] = " ",  -- OGHAM SPACE MARK
[  8192] = " ",  -- EN QUAD
[  8193] = " ",  -- EM QUAD
[  8194] = " ",  -- N-SPACE
[  8195] = " ",  -- M-SPACE
[  8196] = " ",  -- THREE-PER-EM SPACE
[  8197] = " ",  -- FOUR-PER-EM SPACE
[  8198] = " ",  -- SIX-PER-EM SPACE
[  8199] = " ",  -- FIGURE SPACE
[  8200] = " ",  -- PUNCTUATION SPACE
[  8201] = " ",  -- thinsp
[  8202] = " ",  -- HAIR SPACE (english typography)
[  8239] = " ",  -- NARROW NO-BREAK SPACE
[  8287] = " ",  -- MEDIUM MATHEMATICAL SPACE
[ 12288] = " ",  -- IDEOGRAPHIC SPACE
[ 12351] = " ",  -- IDEOGRAPHIC HALF FILL SPACE
[917536] = " ",  -- TAG SPACE
[  8208] = "-",  -- HYPHEN
[  8209] = "-",  -- NON-BREAKING HYPHEN
[  8210] = "-",  -- FIGURE DASH
[  8211] = "-",  -- ndash
[  8212] = "-",  -- mdash
[  8213] = "-",  -- HORIZONTAL BAR
[  8259] = "-",  -- HYPHEN BULLET
[  8722] = "-",  -- MINUS sign
[   170] = "a",  -- feminine ordinal indicator
[   178] = "2",  -- sup2
[   179] = "3",  -- sup3
[   185] = "1",  -- sup1
[   186] = "o",  -- masculine ordinal indicator
[   192] = "A",  -- À
[   193] = "A",  -- Á
[   194] = "A",  -- Â
[   195] = "A",  -- Ã
[   196] = "A",  -- Ä
[   197] = "A",  -- Å
[   198] = "AE", -- Æ
[   199] = "C",  -- Ç
[   200] = "E",  -- È
[   201] = "E",  -- É
[   202] = "E",  -- Ê
[   203] = "E",  -- Ë
[   204] = "I",  -- Ì
[   205] = "I",  -- Í
[   206] = "I",  -- Î
[   207] = "I",  -- Ï
[   208] = "D",  -- Ð
[   209] = "N",  -- Ñ
[   210] = "O",  -- Ò
[   211] = "O",  -- Ó
[   212] = "O",  -- Ô
[   213] = "O",  -- Õ
[   214] = "O",  -- Ö
[   216] = "O",  -- Ø
[   217] = "U",  -- Ù
[   218] = "U",  -- Ú
[   219] = "U",  -- Û
[   220] = "U",  -- Ü
[   221] = "Y",  -- Ý
[   222] = "th", -- Þ
[   223] = "ss", -- ß
[   224] = "a",  -- à
[   225] = "a",  -- á
[   226] = "a",  -- â
[   227] = "a",  -- ã
[   228] = "a",  -- ä
[   229] = "a",  -- å
[   230] = "ae", -- æ
[   231] = "c",  -- ç
[   232] = "e",  -- è
[   233] = "e",  -- é
[   234] = "e",  -- ê
[   235] = "e",  -- ë
[   236] = "i",  -- ì
[   237] = "i",  -- í
[   238] = "i",  -- î
[   239] = "i",  -- ï
[   240] = "d",  -- ð
[   241] = "n",  -- ñ
[   242] = "o",  -- ò
[   243] = "o",  -- ó
[   244] = "o",  -- ô
[   245] = "o",  -- õ
[   246] = "o",  -- ö
[   248] = "o",  -- ø
[   249] = "u",  -- ù
[   250] = "u",  -- ú
[   251] = "u",  -- û
[   252] = "u",  -- ü
[   253] = "y",  -- ý
[   254] = "TH", -- þ
[   255] = "y",  -- ÿ
[   256] = "A",  -- Amacron
[   257] = "a",  -- amacron
[   260] = "A",  -- Aogonek
[   261] = "a",  -- aogonek
[   262] = "C",  -- Cacute
[   263] = "c",  -- cacute
[   264] = "C",  -- Ccirc
[   265] = "c",  -- ccirc
[   266] = "C",  -- Cdot
[   267] = "c",  -- cdot
[   268] = "C",  -- Ccaron
[   269] = "c",  -- ccaron
[   270] = "D",  -- Dcaron
[   271] = "d",  -- dcaron
[   272] = "D",  -- Dstroke
[   273] = "d",  -- dstroke
[   274] = "E",  -- Emacron
[   275] = "e",  -- emacron
[   278] = "E",  -- Edot
[   279] = "e",  -- edot
[   280] = "E",  -- Eogonek
[   281] = "e",  -- eogonek
[   282] = "E",  -- Ecaron
[   283] = "e",  -- ecaron
[   284] = "G",  -- Gcirc
[   285] = "g",  -- gcirc
[   286] = "G",  -- Gbreve
[   287] = "g",  -- gbreve
[   288] = "G",  -- Gdot
[   289] = "g",  -- gdot
[   290] = "G",  -- Gcedil
[   291] = "g",  -- gcedil
[   292] = "H",  -- Hcirc
[   293] = "h",  -- hcirc
[   294] = "H",  -- Hstroke
[   295] = "h",  -- hstroke
[   298] = "I",  -- Imacron
[   299] = "i",  -- imacron
[   302] = "I",  -- Iogonek
[   303] = "i",  -- iogonek
[   304] = "I",  -- Idot
[   305] = "i",  -- inodot
[   306] = "IJ", -- IJlig
[   307] = "ij", -- ijlig
[   308] = "J",  -- Jcirc
[   309] = "j",  -- jcirc
[   310] = "K",  -- Kcedil
[   311] = "k",  -- kcedil
[   315] = "L",  -- Lcedil
[   316] = "l",  -- lcedil
[   321] = "L",  -- Lstroke
[   322] = "l",  -- lstroke
[   323] = "N",  -- Nacute
[   324] = "n",  -- nacute
[   325] = "N",  -- Ncedil
[   326] = "n",  -- ncedil
[   327] = "N",  -- Ncaron
[   328] = "n",  -- ncaron
[   332] = "O",  -- Omacron
[   333] = "o",  -- omacron
[   336] = "O",  -- Odacute
[   337] = "o",  -- odacute
[   338] = "OE", -- OElig
[   339] = "oe", -- oelig
[   344] = "R",  -- Rcaron
[   345] = "r",  -- rcaron
[   346] = "S",  -- Sacute
[   347] = "s",  -- sacute
[   348] = "S",  -- Scirc
[   349] = "s",  -- scirc
[   350] = "S",  -- Scedil
[   351] = "s",  -- scedil
[   352] = "S",  -- Scaron
[   353] = "s",  -- scaron
[   354] = "T",  -- Tcedil
[   355] = "t",  -- tcedil
[   362] = "U",  -- Umacron
[   363] = "u",  -- umacron
[   364] = "U",  -- Ubreve
[   365] = "u",  -- ubreve
[   366] = "U",  -- Uring
[   367] = "u",  -- uring
[   368] = "U",  -- Udacute
[   369] = "u",  -- udacute
[   370] = "U",  -- Uogonek
[   371] = "u",  -- uogonek
[   376] = "Y",  -- Yuml
[   377] = "Z",  -- Zacute
[   378] = "z",  -- zacute
[   379] = "Z",  -- Zdot
[   380] = "z",  -- zdot
[   381] = "Z",  -- Zcaron
[   382] = "z",  -- zcaron
[   383] = "s",  -- long S
[   384] = "b",  -- b with stroke
[   385] = "B",  -- B with hook
[   386] = "B",  -- B with topbar
[   387] = "b",  -- b with topbar
[   390] = "O",  -- open O
[   391] = "C",  -- C with hook
[   392] = "c",  -- c with hook
[   393] = "D",  -- African D
[   394] = "D",  -- D with hook
[   395] = "D",  -- D with topbar
[   396] = "d",  -- d with topbar
[   398] = "E",  -- reversed E
[   400] = "E",  -- open E
[   401] = "F",  -- F with hook
[   402] = "f",  -- f with hook
[   403] = "G",  -- G with hook
[   407] = "I",  -- I with stroke
[   408] = "K",  -- K with hook
[   409] = "k",  -- k with hook
[   410] = "l",  -- l with bar
[   412] = "M",  -- turned M
[   413] = "N",  -- N with left hook
[   414] = "n",  -- n with long right leg
[   415] = "O",  -- O with middle tilde
[   416] = "O",  -- O with horn
[   417] = "o",  -- o with horn
[   420] = "P",  -- P with hook
[   421] = "p",  -- p with hook
[   427] = "t",  -- t with palatal hook
[   428] = "T",  -- T with hook
[   429] = "t",  -- t with hook
[   430] = "T",  -- T with retroflex hook
[   431] = "U",  -- U with horn
[   432] = "u",  -- u with horn
[   434] = "V",  -- V with hook
[   435] = "Y",  -- Y with hook
[   436] = "y",  -- y with hook
[   437] = "Z",  -- Z with stroke
[   438] = "z",  -- z with stroke
[   452] = "DZ", -- D with Z with caron
[   453] = "Dz", -- D with z with caron
[   454] = "dz", -- d with z with caron
[   455] = "LJ", -- L with J
[   456] = "Lj", -- L with j
[   457] = "lj", -- l with j
[   458] = "NJ", -- N with J
[   459] = "Nj", -- N with j
[   460] = "nj", -- n with j
[   461] = "A",  -- A with caron
[   462] = "a",  -- a with caron
[   463] = "I",  -- I with caron
[   464] = "i",  -- i with caron
[   465] = "O",  -- O with caron
[   466] = "o",  -- o with caron
[   467] = "U",  -- U with caron
[   468] = "u",  -- u with caron
[   469] = "U",  -- U with diaeresis and macron
[   470] = "u",  -- u with diaeresis and macron
[   471] = "U",  -- U with diaeresis and acute
[   472] = "u",  -- u with diaeresis and acute
[   473] = "U",  -- U with diaeresis and caron
[   474] = "u",  -- u with diaeresis and caron
[   475] = "U",  -- U with diaeresis and grave
[   476] = "u",  -- u with diaeresis and grave
[   477] = "e",  -- turned e
[   478] = "A",  -- A with diaeresis and macron
[   479] = "a",  -- a with diaeresis and macron
[   480] = "A",  -- A with dot above and macron
[   481] = "a",  -- a with dot above and macron
[   482] = "AE", -- AE with macron
[   483] = "ae", -- ae with macron
[   484] = "G",  -- G with stroke
[   485] = "g",  -- g with stroke
[   486] = "G",  -- G with caron
[   487] = "g",  -- g with caron
[   488] = "K",  -- K with caron
[   489] = "k",  -- k with caron
[   490] = "O",  -- O with ogonek
[   491] = "o",  -- o with ogonek
[   492] = "O",  -- O with ogonek and macron
[   493] = "o",  -- o with ogonek and macron
[   496] = "j",  -- j with caron
[   497] = "DZ", -- D with Z
[   498] = "Dz", -- D with z
[   499] = "dz", -- d with z
[   500] = "G",  -- G with acute
[   501] = "g",  -- g with acute
[   504] = "N",  -- N with grave
[   505] = "n",  -- n with grave
[   506] = "A",  -- A with ring above and acute
[   507] = "a",  -- a with ring above and acute
[   508] = "AE", -- AE with acute
[   509] = "ae", -- ae with acute
[   510] = "O",  -- O with stroke and acute
[   511] = "o",  -- o with stroke and acute
[   512] = "A",  -- A with double grave
[   513] = "a",  -- a with double grave
[   514] = "A",  -- A with inverted breve
[   515] = "a",  -- a with inverted breve
[   516] = "E",  -- E with double grave
[   517] = "e",  -- e with double grave
[   518] = "E",  -- E with inverted breve
[   519] = "e",  -- e with inverted breve
[   520] = "I",  -- I with double grave
[   521] = "i",  -- i with double grave
[   522] = "I",  -- I with inverted breve
[   523] = "i",  -- i with inverted breve
[   524] = "O",  -- O with double grave
[   525] = "o",  -- o with double grave
[   526] = "O",  -- O with inverted breve
[   527] = "o",  -- o with inverted breve
[   528] = "R",  -- R with double grave
[   529] = "r",  -- r with double grave
[   530] = "R",  -- R with inverted breve
[   531] = "r",  -- r with inverted breve
[   532] = "U",  -- U with double grave
[   533] = "u",  -- u with double grave
[   534] = "U",  -- U with inverted breve
[   535] = "u",  -- u with inverted breve
[   536] = "S",  -- S with comma below
[   537] = "s",  -- s with comma below
[   538] = "T",  -- T with comma below
[   539] = "t",  -- t with comma below
[   542] = "H",  -- H with caron
[   543] = "h",  -- h with caron
[   544] = "N",  -- N with long right leg
[   545] = "d",  -- d with curl
[   546] = "OU", -- OU
[   547] = "ou", -- ou
[   548] = "Z",  -- Z with hook
[   549] = "z",  -- z with hook
[   550] = "A",  -- A with dot above
[   551] = "a",  -- a with dot above
[   552] = "E",  -- E with cedilla
[   553] = "e",  -- e with cedilla
[   554] = "O",  -- O with diaeresis and macron
[   555] = "o",  -- o with diaeresis and macron
[   556] = "O",  -- O with tilde and macron
[   557] = "o",  -- o with tilde and macron
[   558] = "O",  -- O with dot above
[   559] = "o",  -- o with dot above
[   560] = "O",  -- O with dot above and macron
[   561] = "o",  -- o with dot above and macron
[   562] = "Y",  -- Y with macron
[   563] = "y",  -- y with macron
[   564] = "l",  -- l with curl
[   565] = "n",  -- n with curl
[   566] = "t",  -- t with curl
[   567] = "j",  -- dotless j
[   568] = "db", -- db digraph
[   569] = "qp", -- qp digraph
[   570] = "A",  -- A with stroke
[   571] = "C",  -- C with stroke
[   572] = "c",  -- c with stroke
[   573] = "L",  -- L with bar
[   574] = "T",  -- T with diagonal stroke
[   575] = "s",  -- s with swash tail
[   576] = "z",  -- z with swash tail
[   579] = "B",  -- B with stroke
[   580] = "U",  -- U with bar
[   581] = "V",  -- turned V
[   582] = "E",  -- E with stroke
[   583] = "e",  -- e with stroke
[   584] = "J",  -- J with stroke
[   585] = "j",  -- j with stroke
[   586] = "Q",  -- small Q with hook tail
[   587] = "q",  -- q with hook tail
[   588] = "R",  -- R with stroke
[   589] = "r",  -- r with stroke
[   590] = "Y",  -- Y with stroke
[   591] = "y",  -- y with stroke
[  7838] = "SS", -- CAPITAL SHARP S
[    39] = "",   -- '
[    96] = "",   -- grave
[   133] = "",   -- NEXT LINE (NEL)
[   168] = "",   -- uml
[   173] = "",   -- soft hyphen
[   175] = "",   -- macr
[   180] = "",   -- acute
[   184] = "",   -- cedil
[   710] = "",   -- circ
[   711] = "",   -- caron
[   728] = "",   -- breve
[   730] = "",   -- ring
[   731] = "",   -- ogon
[   732] = "",   -- tilde
[   733] = "",   -- dacute
[  6158] = "",   -- MONGOLIAN VOWEL SEPARATOR
[  8203] = "",   -- ZERO WIDTH SPACE
[  8204] = "",   -- zwnj
[  8205] = "",   -- zwj
[  8206] = "",   -- lrm
[  8207] = "",   -- rlm
[  8232] = "",   -- LINE SEPARATOR
[  8233] = "",   -- PARAGRAPH SEPARATOR
[  8234] = "",   -- LEFT-TO-RIGHT EMBEDDING
[  8235] = "",   -- RIGHT-TO-LEFT EMBEDDING
[  8236] = "",   -- POP DIRECTIONAL FORMATTING
[  8237] = "",   -- LEFT-TO-RIGHT OVERRIDE
[  8238] = "",   -- RIGHT-TO-LEFT OVERRIDE
[  8288] = "",   -- WORD JOINER
[  8289] = "",   -- FUNCTION APPLICATION
[  8290] = "",   -- INVISIBLE TIMES
[  8291] = "",   -- INVISIBLE SEPARATOR
[  8292] = "",   -- INVISIBLE PLUS
[ 65279] = "",   -- BYTE ORDER MARK
[917505] = ""    -- LANGUAGE TAG
};