From 6c90555ebb89f41cc4dfb6cf3ee6bfaa8107650e Mon Sep 17 00:00:00 2001 From: Norbert Preining Date: Thu, 4 Jun 2020 03:02:40 +0000 Subject: CTAN sync 202006040302 --- indexing/xindex/lualatex/xindex-DIN2.lua | 2 +- indexing/xindex/lualatex/xindex-HAdW-eKO.lua | 2 +- indexing/xindex/lualatex/xindex-base.lua | 17 +- indexing/xindex/lualatex/xindex-cfg-common.lua | 6 +- indexing/xindex/lualatex/xindex-cfg-uca.lua | 17 ++ indexing/xindex/lualatex/xindex-cfg.lua | 2 +- indexing/xindex/lualatex/xindex-dtk.lua | 2 +- indexing/xindex/lualatex/xindex-lapp.lua | 2 +- indexing/xindex/lualatex/xindex-lib.lua | 88 +++++---- indexing/xindex/lualatex/xindex-norsk.lua | 155 --------------- indexing/xindex/lualatex/xindex-pretty.lua | 2 +- indexing/xindex/lualatex/xindex-yannis.lua | 260 +++++++++++++++++++++++++ 12 files changed, 358 insertions(+), 197 deletions(-) create mode 100644 indexing/xindex/lualatex/xindex-cfg-uca.lua delete mode 100644 indexing/xindex/lualatex/xindex-norsk.lua create mode 100644 indexing/xindex/lualatex/xindex-yannis.lua (limited to 'indexing/xindex/lualatex') diff --git a/indexing/xindex/lualatex/xindex-DIN2.lua b/indexing/xindex/lualatex/xindex-DIN2.lua index 35eae4f069..6b925e3367 100644 --- a/indexing/xindex/lualatex/xindex-DIN2.lua +++ b/indexing/xindex/lualatex/xindex-DIN2.lua @@ -7,7 +7,7 @@ ----------------------------------------------------------------------- if not modules then modules = { } end modules ['xindex-cfg'] = { - version = 0.22, + version = 0.23, comment = "configuration to xindex.lua", author = "Herbert Voss", copyright = "Herbert Voss", diff --git a/indexing/xindex/lualatex/xindex-HAdW-eKO.lua b/indexing/xindex/lualatex/xindex-HAdW-eKO.lua index 5f1c8c8344..9b440fa94d 100644 --- a/indexing/xindex/lualatex/xindex-HAdW-eKO.lua +++ b/indexing/xindex/lualatex/xindex-HAdW-eKO.lua @@ -9,7 +9,7 @@ -- configuration for index files of the Heidelberger Akademie der Wissenschaften if not modules then modules = { } end modules ['xindex-HAdW-eKO'] = { - version = 0.22, + version = 0.23, comment = "configuration to xindex.lua", author = "Herbert Voss", copyright = "Herbert Voss", diff --git a/indexing/xindex/lualatex/xindex-base.lua b/indexing/xindex/lualatex/xindex-base.lua index 9d36d5ddd2..6c51f21763 100644 --- a/indexing/xindex/lualatex/xindex-base.lua +++ b/indexing/xindex/lualatex/xindex-base.lua @@ -6,7 +6,7 @@ -- LICENSE: LPPL1.3 ----------------------------------------------------------------------- -local info = { version = 0.22 } +local info = { version = 0.23 } -- check config if pageNoPrefixDel ~= "" then @@ -120,6 +120,21 @@ for i, str0 in ipairs(escape_chars) do end ]] -- no more needed, we redo the setting +if use_UCA then + for i=1, #NewIndex do + v = NewIndex[i] + -- the collator:get_lowest_char will return character on the given + -- position. It will be lowercase and without accents. + local codepoints = collator_obj:string_to_codepoints(NormalizedUpper(v.SortKey)) + v.sortChar = getSortChar(codepoints) --or getSortChar(collator_obj:string_to_codepoints(NormalizedUpper(v.Entry))) + if not v.sortChar then + -- alternativelly use v.Entry if SortKey doesn't contain usable string + codepoints = collator_obj:string_to_codepoints(NormalizedUpper(v.Entry)) + v.sortChar = getSortChar(codepoints) + end + end +end + if SORTendhook then NewIndex = SORTendhook(NewIndex) end diff --git a/indexing/xindex/lualatex/xindex-cfg-common.lua b/indexing/xindex/lualatex/xindex-cfg-common.lua index a49723ebf2..85f2c033b8 100644 --- a/indexing/xindex/lualatex/xindex-cfg-common.lua +++ b/indexing/xindex/lualatex/xindex-cfg-common.lua @@ -7,7 +7,7 @@ ----------------------------------------------------------------------- if not modules then modules = { } end modules ['xindex-cfg-common'] = { - version = 0.22, + version = 0.23, comment = "configuration to xindex.lua", author = "Herbert Voss", copyright = "Herbert Voss", @@ -16,15 +16,17 @@ if not modules then modules = { } end modules ['xindex-cfg-common'] = { indexheader = { cs = {"Symboly", "Čísla"}, + da = {"Symboler", "Tal"}, de = {"Symbole", "Zahlen"}, en = {"Symbols", "Numbers"}, - fr = {"Symboles","Chiffre"}, + fr = {"Symboles","Nombres"}, it = {"Simboli", "Numeri"}, jp = {"シンボル","番号"}, } folium = { cs = {"f.", "ff."}, + da = {"f", "ff"}, de = {"f", "ff"}, en = {"f", "ff"}, fr = {"\\,sq","\\,sqq"}, diff --git a/indexing/xindex/lualatex/xindex-cfg-uca.lua b/indexing/xindex/lualatex/xindex-cfg-uca.lua new file mode 100644 index 0000000000..42ad4ec6dd --- /dev/null +++ b/indexing/xindex/lualatex/xindex-cfg-uca.lua @@ -0,0 +1,17 @@ +----------------------------------------------------------------------- +-- FILE: xindex-cfg-uca.lua +-- DESCRIPTION: configuration file for lua-uca +-- REQUIREMENTS: +-- AUTHOR: Herbert Voß +-- LICENSE: LPPL1.3 +----------------------------------------------------------------------- + +if not modules then modules = { } end modules ['xindex-cfg-lua'] = { + version = 0.23, + comment = "configuration to xindex-cfg-uca.lua", + author = "Herbert Voss", + copyright = "Herbert Voss", + license = "LPPL 1.3" +} + +-- put any additional code for lua-uca here --- diff --git a/indexing/xindex/lualatex/xindex-cfg.lua b/indexing/xindex/lualatex/xindex-cfg.lua index 9e1f12b6a2..7b23b7c905 100644 --- a/indexing/xindex/lualatex/xindex-cfg.lua +++ b/indexing/xindex/lualatex/xindex-cfg.lua @@ -7,7 +7,7 @@ ----------------------------------------------------------------------- if not modules then modules = { } end modules ['xindex-cfg'] = { - version = 0.22, + version = 0.23, comment = "main configuration to xindex.lua", author = "Herbert Voss", copyright = "Herbert Voss", diff --git a/indexing/xindex/lualatex/xindex-dtk.lua b/indexing/xindex/lualatex/xindex-dtk.lua index a195ccde02..6a32d5e863 100644 --- a/indexing/xindex/lualatex/xindex-dtk.lua +++ b/indexing/xindex/lualatex/xindex-dtk.lua @@ -7,7 +7,7 @@ ----------------------------------------------------------------------- if not modules then modules = { } end modules ['xindex-cfg'] = { - version = 0.22, + version = 0.23, comment = "DTK configuration to xindex.lua", author = "Herbert Voss", copyright = "Herbert Voss", diff --git a/indexing/xindex/lualatex/xindex-lapp.lua b/indexing/xindex/lualatex/xindex-lapp.lua index b55cb170f8..94c22cb240 100644 --- a/indexing/xindex/lualatex/xindex-lapp.lua +++ b/indexing/xindex/lualatex/xindex-lapp.lua @@ -28,7 +28,7 @@ --~ n 2 -------------------------------- if not modules then modules = { } end modules ['xindex-lapp'] = { - version = 0.22, + version = 0.23, comment = "read parameter for xindex.lua", author = "Steve Donovan", copyright = "Steve Donovan", diff --git a/indexing/xindex/lualatex/xindex-lib.lua b/indexing/xindex/lualatex/xindex-lib.lua index 8e480866c8..720d473d53 100644 --- a/indexing/xindex/lualatex/xindex-lib.lua +++ b/indexing/xindex/lualatex/xindex-lib.lua @@ -7,7 +7,7 @@ ----------------------------------------------------------------------- if not modules then modules = { } end modules ['xindex-lib'] = { - version = 0.22, + version = 0.23, comment = "main library to xindex.lua", author = "Herbert Voss", copyright = "Herbert Voss", @@ -569,43 +569,15 @@ function GenerateSortKeys(Index) end end -function UTFCompare(a,b) --- a, b are something like \indexentry{foo}{bar} --- writeLog(1,"UTFCompare: "..a["Entry"]..", "..a["pages"][1]["number"].." - "..b["Entry"]..", "..b["pages"][1]["number"].."\n",2) --- k = k + 1 --- if (k % 50) == 0 then writeLog(1,".",1) end - +function UTFCompare(a,b) local A = a["SortKey"] local B = b["SortKey"] - writeLog(1,"UTFCompare: A--B "..A.."--"..B.."\n",2) --- print(A,B) ---[[ - if A == B then -- same entry, use also page number - Apage = string.format("%09s",a["pages"][1]["number"]) - Bpage = string.format("%09s",b["pages"][1]["number"]) - A = string.format("%-90s",A)..Apage - B = string.format("%-90s",B)..Bpage - end - if numericPage then - if tonumber(a["pages"][1]["number"]) then - Apage = string.format("%09d",a["pages"][1]["number"]) - else - Apage = string.format("%09d",romanToNumber(a["pages"][1]["number"])) - end - if tonumber(b["pages"][1]["number"]) then - Bpage = string.format("%09d",b["pages"][1]["number"]) - else - Bpage = string.format("%09d",romanToNumber(b["pages"][1]["number"])) - end + if use_UCA then + return collator_obj:compare_strings(A,B) else - Apage = string.format("%09s",a["pages"][1]["number"]) - Bpage = string.format("%09s",b["pages"][1]["number"]) + return A 0 then + local codes, pos = collator_obj:get_lowest_char(codepoints, 1) + if not codes then + -- if the first character in the sort key doesn't return letter + -- continue until we find some + table.remove(codepoints, 1) + return getSortChar(codepoints) + end + local sort_char = utf8.char(table.unpack(codes)) + -- print unicode category of the first char + return upper(sort_char) -- use unicode.utf8.upper to make the char uppercase + end +end + diff --git a/indexing/xindex/lualatex/xindex-norsk.lua b/indexing/xindex/lualatex/xindex-norsk.lua deleted file mode 100644 index 7473b42ed6..0000000000 --- a/indexing/xindex/lualatex/xindex-norsk.lua +++ /dev/null @@ -1,155 +0,0 @@ ------------------------------------------------------------------------ --- FILE: xindex-norsk.lua --- DESCRIPTION: configuration file for xindex.lua --- REQUIREMENTS: --- AUTHOR: Herbert Voß --- MODIFIED: Sveinung Heggen (2020-01-02) --- LICENSE: LPPL1.3 ------------------------------------------------------------------------ - -if not modules then modules = { } end modules ['xindex-norsk'] = { - version = 0.22, - comment = "configuration to xindex.lua", - author = "Herbert Voss", - copyright = "Herbert Voss", - license = "LPPL 1.3" -} - -local ducet = require "lua-uca.lua-uca-ducet" -local collator = require "lua-uca.lua-uca-collator" -local languages = require "lua-uca.lua-uca-languages" -local collator_obj = collator.new(ducet) - -local language = "en" -- default language --- language name specified on the command line doesn't seem to be available --- in the config file, so we just try to find it ourselves -for i, a in ipairs(arg) do - if a == "-l" or a=="--language" then - language = arg[i+1] - break - end -end - -if languages[language] then - print("[Lua-UCA] Loading language: " .. language) - collator_obj = languages[language](collator_obj) -end - -local upper = unicode.utf8.upper - -escape_chars = { -- by default " is the escape char - {'""', "\\escapedquote", '\"{}' }, - {'"@', "\\escapedat", "@" }, - {'"|', "\\escapedvert", "|" }, - {'"!', "\\escapedexcl", "!" }, - {'"(', "\\escapedparenleft", "(" }, - {'")', "\\escapedparenright", ")" } -} - -itemPageDelimiter = "," -- Hello, 14 -compressPages = true -- something like 12--15, instead of 12,13,14,15. the |( ... |) syntax is still valid -fCompress = true -- 3f -> page 3, 4 and 3ff -> page 3, 4, 5 -minCompress = 3 -- 14--17 or -numericPage = true -- for non-numerical page numbers, like "VI-17" -sublabels = {"", "---\\,", "--\\,", "-\\,"} -- for the (sub(sub(sub-items first one is for item -pageNoPrefixDel = "" -- a delimiter for page numbers like "VI-17" -indexOpening = "" -- commands after \begin{theindex} -rangeSymbol = "--" -idxnewletter = "\\textbf" -- Only valid if -n is not set - -folium = { - de = {"f.", "ff."}, - en = {"f.", "ff."}, - fr = {"\\,sq","\\,sqq"}, - no = {"\\,f.","\\,ff."}, - cs = {"f.", "ff."}, -} - -indexheader = { - de = {"Symbole", "Zahlen"}, - en = {"Symbols", "Numbers"}, - fr = {"Symboles","Chiffre"}, - jp = {"シンボル","番号"}, - cs = {"Symboly", "Čísla"} -} - - --- get Unicode category of the codepoint, if supported -function getCategory(codepoints) - local codepoint = codepoints[1] - local category = get_category(codepoint) - if category == "Nd" then - return "digits" - elseif category:match("^L") then - local block = binary_range_search(codepoint, unicode_blocks) or {} - return block[3] or "other" - end - return "other" -end - --- insert the index entry to the categories subtable -function categorize(codepoints, entry, categories) - local subcategories = categories.categories - -- return category name from the Unicode block of the first character - local category = getCategory(codepoints) - -- if the categories doesn't use this code block, categorize it as other - local used = subcategories[category] and category or "other" - table.insert(subcategories[used], entry) -end - --- convert categories back to index list -function uncategorize(ordering_categories) - local newlist = {} - -- make new index order based on defined categories - for _, category in ipairs(ordering_categories.order) do - for _,entry in ipairs(ordering_categories.categories[category]) do - newlist[#newlist+1] = entry - end - end - return newlist -end - - -function UTFCompare(a,b) - local A = a["SortKey"] - local B = b["SortKey"] - return collator_obj:compare_strings(A,B) -end - -function getSortChar(codepoints) - if #codepoints > 0 then - local codes, pos = collator_obj:get_lowest_char(codepoints, 1) - if not codes then - -- if the first character in the sort key doesn't return letter - -- continue until we find some - table.remove(codepoints, 1) - return getSortChar(codepoints) - end - local sort_char = utf8.char(table.unpack(codes)) - -- print unicode category of the first char - return upper(sort_char) -- use unicode.utf8.upper to make the char uppercase - end -end - -function SORTendhook(list) - -- get the headers for letter groups - for i=1, #list do - v = list[i] - -- the collator:get_lowest_char will return character on the given - -- position. It will be lowercase and without accents. - local codepoints = collator_obj:string_to_codepoints(NormalizedUpper(v.SortKey)) - v.sortChar = getSortChar(codepoints) --or getSortChar(collator_obj:string_to_codepoints(NormalizedUpper(v.Entry))) - if not v.sortChar then - -- alternativelly use v.Entry if SortKey doesn't contain usable string - codepoints = collator_obj:string_to_codepoints(NormalizedUpper(v.Entry)) - v.sortChar = getSortChar(codepoints) - end - end - return list -end - --- We use Lua-UCA methods for sorting and determining first characters, so --- alphabet list is obsolete - -alphabet_lower = { } -alphabet_upper = { } diff --git a/indexing/xindex/lualatex/xindex-pretty.lua b/indexing/xindex/lualatex/xindex-pretty.lua index 3e4f12a016..b671ba004e 100644 --- a/indexing/xindex/lualatex/xindex-pretty.lua +++ b/indexing/xindex/lualatex/xindex-pretty.lua @@ -5,7 +5,7 @@ -- if not modules then modules = { } end modules ['xindex-pretty'] = { - version = 0.22, + version = 0.23, comment = "dump a Lua table for debugging", author = "Steve Donovan", copyright = "Steve Donovan", diff --git a/indexing/xindex/lualatex/xindex-yannis.lua b/indexing/xindex/lualatex/xindex-yannis.lua new file mode 100644 index 0000000000..85bef308b9 --- /dev/null +++ b/indexing/xindex/lualatex/xindex-yannis.lua @@ -0,0 +1,260 @@ +----------------------------------------------------------------------- +-- FILE: xindex-yannis.lua +-- DESCRIPTION: configuration file for xindex.lua +-- REQUIREMENTS: +-- AUTHOR: Herbert Voß +-- LICENSE: LPPL1.3 +----------------------------------------------------------------------- + +if not modules then modules = { } end modules ['xindex-yannis'] = { + version = 0.23, + comment = "main configuration to xindex.lua", + author = "Herbert Voss", + copyright = "Herbert Voss", + license = "LPPL 1.3" +} + +itemPageDelimiter = "," -- Hello, 14 +compressPages = true -- something like 12--15, instaead of 12,13,14,15. the |( ... |) syntax is still valid +fCompress = false -- 3f -> page 3, 4 and 3ff -> page 3, 4, 5 +minCompress = 2 -- 14--17 or +rangeSymbol = "-" -- 14-17 instead of -- +numericPage = true -- for non numerical pagenumbers, like "VI-17" +sublabels = {"", "-\\,", "--\\,", "---\\,"} -- for the (sub(sub(sub-items first one is for item +pageNoPrefixDel = "" -- a delimiter for page numbers like "VI-17" -- not used !!! +indexOpening = "" -- commands after \begin{theindex} +idxnewletter = "\\textbf" -- Only valid if -n is not set + + +--[[ + Each character's position in this array-like table determines its 'priority'. + Several characters in the same slot have the same 'priority'. +]] +alphabet_lower = { -- for sorting + { 'α', 'ά', 'ὰ', 'ᾶ', 'ἀ', 'ἄ', 'ἂ', 'ἆ', 'ἁ', 'ἅ', 'ἃ', 'ἇ', 'ᾳ', 'ᾴ', 'ᾲ', 'ᾷ', 'ᾀ', 'ᾄ', 'ᾂ', 'ᾆ', 'ᾁ', 'ᾅ', 'ᾃ', 'ᾇ' }, + { 'β', 'ϐ' }, + { 'γ' }, + { 'δ' }, + { 'ε', 'έ', 'ὲ', 'ἐ', 'ἔ', 'ἒ', 'ἑ', 'ἕ', 'ἓ' }, + { 'ζ' }, + { 'η', 'ή', 'ὴ', 'ῆ', 'ἠ', 'ἤ', 'ἢ', 'ἦ', 'ἡ', 'ἥ', 'ἣ', 'ἧ', 'ῃ', 'ῄ', 'ῂ', 'ῇ', 'ᾐ', 'ᾔ', 'ᾒ', 'ᾖ', 'ᾑ', 'ᾕ', 'ᾓ', 'ᾗ' }, + { 'θ' }, + { 'ι', 'ί', 'ὶ', 'ῖ', 'ἰ', 'ἴ', 'ἲ', 'ἶ', 'ἱ', 'ἵ', 'ἳ', 'ἷ', 'ϊ', 'ΐ', 'ῒ', 'ῗ' }, + { 'κ' }, + { 'λ' }, + { 'μ' }, + { 'ν' }, + { 'ξ' }, + { 'ο', 'ό', 'ὸ', 'ὀ', 'ὄ', 'ὂ', 'ὁ', 'ὅ', 'ὃ' }, + { 'π' }, + { 'ρ' }, + { 'σ', 'ς' }, + { 'τ' }, + { 'υ', 'ύ', 'ὺ', 'ῦ', 'ὐ', 'ὔ', 'ὒ', 'ὖ', 'ὑ', 'ὕ', 'ὓ', 'ὗ', 'ϋ', 'ΰ', 'ῢ', 'ῧ' }, + { 'φ' }, + { 'χ' }, + { 'ψ' }, + { 'ω', 'ώ', 'ὼ', 'ῶ', 'ὠ', 'ὤ', 'ὢ', 'ὦ', 'ὡ', 'ὥ', 'ὣ', 'ὧ', 'ῳ', 'ῴ', 'ῲ', 'ῷ', 'ᾠ', 'ᾤ', 'ᾢ', 'ᾦ', 'ᾡ', 'ᾥ', 'ᾣ', 'ᾧ' }, + { 'a', 'á', 'à', 'ä', 'å', 'æ', }, + { 'b' }, + { 'c', 'ç' }, + { 'd' }, + { 'e', 'é', 'è', 'ë' }, + { 'f' }, + { 'g' }, + { 'h' }, + { 'i', 'í', 'ì', 'ï' }, + { 'j' }, + { 'k' }, + { 'l' }, + { 'm' }, + { 'n', 'ñ' }, + { 'o', 'ó', 'ò', 'ö', 'ø', 'œ'}, + { 'p' }, + { 'q' }, + { 'r' }, + { 's', 'š', 'ß' }, + { 't' }, + { 'u', 'ú', 'ù', 'ü' }, + { 'v' }, + { 'w' }, + { 'x' }, + { 'y', 'ý', 'ÿ' }, + { 'z', 'ž' }, + { 'а' }, + { 'б' }, + { 'в' }, + { 'г', 'ѓ' }, + { 'д' }, + { 'е', 'ё' }, + { 'ж' }, + { 'з' }, + { 'и', 'і' }, + { 'й' }, + { 'к' }, + { 'л' }, + { 'м' }, + { 'н' }, + { 'о' }, + { 'п' }, + { 'р' }, + { 'с' }, + { 'т' }, + { 'у' }, + { 'ф' }, + { 'х' }, + { 'ц' }, + { 'ч' }, + { 'ш' }, + { 'щ' }, + { 'ъ' }, + { 'ы' }, + { 'ь' }, + { 'э' }, + { 'ю' }, + { 'я' }, +} +alphabet_upper = { -- for sorting + { 'Α', 'Ά', 'Ἀ', 'Ἄ', 'Ἂ', 'Ἆ', 'Ἁ', 'Ἅ', 'Ἃ', 'Ἇ', 'ᾼ', 'ᾈ', 'ᾌ', 'ᾊ', 'ᾎ', 'ᾉ', 'ᾍ', 'ᾋ', 'ᾏ' }, + { 'Β' }, + { 'Γ' }, + { 'Δ' }, + { 'Ε', 'Έ', 'Ἐ', 'Ἔ', 'Ἒ', 'Ἑ', 'Ἕ', 'Ἓ' }, + { 'Ζ' }, + { 'Η', 'Ή', 'Ἠ', 'Ἤ', 'Ἢ', 'Ἦ', 'Ἡ', 'Ἥ', 'Ἣ', 'Ἧ', 'ῌ', 'ᾘ', 'ᾜ', 'ᾚ', 'ᾞ', 'ᾙ', 'ᾝ', 'ᾟ' }, + { 'Θ' }, + { 'Ι', 'Ί', 'Ἰ', 'Ἴ', 'Ἲ', 'Ἶ', 'Ἱ', 'Ἵ', 'Ἳ', 'Ἷ', 'Ϊ' }, + { 'Κ' }, + { 'Λ' }, + { 'Μ' }, + { 'Ν' }, + { 'Ξ' }, + { 'Ο', 'Ό', 'Ὀ', 'Ὄ', 'Ὂ', 'Ὁ', 'Ὅ', 'Ὃ' }, + { 'Π' }, + { 'Ρ' }, + { 'Σ' }, + { 'Τ' }, + { 'Υ', 'Ύ', 'Ὑ', 'Ὕ', 'Ὓ', 'Ὗ', 'Ϋ' }, + { 'Φ' }, + { 'Χ' }, + { 'Ψ' }, + { 'Ω', 'Ώ', 'Ὠ', 'Ὤ', 'Ὢ', 'Ὦ', 'Ὡ', 'Ὥ', 'Ὣ', 'Ὧ', 'ῼ', 'ᾩ', 'ᾭ', 'ᾫ', 'ᾯ', 'ᾨ', 'ᾬ', 'ᾪ', 'ᾮ' }, + { 'A', 'Á', 'À', 'Ä', 'Å', 'Æ'}, + { 'B' }, + { 'C', 'Ç' }, + { 'D' }, + { 'E', 'È', 'È', 'Ë' }, + { 'F' }, + { 'G' }, + { 'H' }, + { 'I', 'Í', 'Ì', 'Ï' }, + { 'J' }, + { 'K' }, + { 'L' }, + { 'M' }, + { 'N', 'Ñ' }, + { 'O', 'Ó', 'Ò', 'Ö', 'Ø','Œ' }, + { 'P' }, + { 'Q' }, + { 'R' }, + { 'S', 'Š' }, + { 'T' }, + { 'U', 'Ú', 'Ù', 'Ü' }, + { 'V' }, + { 'W' }, + { 'X' }, + { 'Y', 'Ý', 'Ÿ' }, + { 'Z', 'Ž' }, + { 'А' }, + { 'Б' }, + { 'В' }, + { 'Г', 'Ѓ' }, + { 'Д' }, + { 'Е', 'Ё' }, + { 'Ж' }, + { 'З' }, + { 'И', 'І' }, + { 'Й' }, + { 'К' }, + { 'Л' }, + { 'М' }, + { 'Н' }, + { 'О' }, + { 'П' }, + { 'Р' }, + { 'С' }, + { 'Т' }, + { 'У' }, + { 'Ф' }, + { 'Х' }, + { 'Ц' }, + { 'Ч' }, + { 'Ш' }, + { 'Щ' }, + { 'Ъ' }, + { 'Ы' }, + { 'Ь' }, + { 'Э' }, + { 'Ю' }, + { 'Я' }, +} + + +function SORTendhook(list) + print ("We have "..#list.." total list entries") + local greek = {} + local latin = {} + local cyrillic = {} + local symbols = {} + local numbers = {} + local others = {} + local firstChar, charType + local firstCharNumber + local v + for i=1,#list do + v = list[i] + firstChar = NormalizedUppercase(utf.sub(v["sortChar"],1,1)) + v["sortChar"] = firstChar -- to be sure it is an uppercase unicode char + firstCharNumber = string.utfvalue(firstChar) + charType = getCharType(firstChar) +-- print (utf.sub(v["sortChar"],1,1).."->"..firstChar.." ("..firstCharNumber..") ".." ("..charType..")") + if charType == 0 then + symbols[#symbols+1] = v + elseif charType == 1 then + numbers[#numbers+1] = v + elseif firstCharNumber > 0x052F then -- 0x052F is last cyrillic character + others[#others+1] = v + elseif firstCharNumber >= 0x0400 then -- 0x0400-0x052F cyrillic characters + cyrillic[#cyrillic+1] = v + elseif firstCharNumber <= 0x03FF then -- 0x03FF is last greek character + if firstCharNumber >= 0x0370 then + greek[#greek+1] = v -- 0x0370-0x03FF greek characters + elseif firstCharNumber <= 0x024F then + if firstCharNumber >= 0x041 then -- 0x041-0x024F latin character + latin[#latin+1] = v + else + others[#others+1] = v -- everything else + end + end + end + end + print ("We have "..#greek.." Greek entries") + print ("We have "..#latin.." Latin entries") + print ("We have "..#cyrillic.." Cyrillic entries") + print ("We have "..#symbols.." Symbol entries") + print ("We have "..#numbers.." Number entries") + print ("We have "..#others.." other entries") + list = {} + for i = 1,#greek do list[#list+1] = greek[i] end + list[#list]["Macro"] = "\\vspace{1cm}" + for i = 1,#latin do list[#list+1] = latin[i] end + list[#list]["Macro"] = "\\vspace{1cm}" + for i = 1,#cyrillic do list[#list+1] = cyrillic[i] end + list[#list]["Macro"] = "\\vspace{1cm}" + for i = 1,#symbols do list[#list+1] = symbols[i] end + for i = 1,#numbers do list[#list+1] = numbers[i] end + for i = 1,#others do list[#list+1] = others[i] end + print ("Sorted "..#list.." entries") + return list +end + -- cgit v1.2.3