[NTG-context] Re: Quickly invoke a self-defined index sorting file?

[Hans Hagen via ntg-context <ntg-context@ntg.nl>]

[-- Attachment #1: Type: text/plain, Size: 719 bytes --]

On 1/12/2025 2:54 PM, autumnus wrote:

> Chinese Hanzi PinYin  : https://github.com/mozillazg/pinyin-data/tree/master
> Chinese Hanzi Stroke : https://github.com/leo-liu/zhmakeindex/blob/master/CJK/strokes.go

assuming that you donwloaded kHanyuPinlu.txt you can run the attached 
test file You might want to set up an order / entries for the latin variant

just prototyping here

Hans

-----------------------------------------------------------------
                                           Hans Hagen | PRAGMA ADE
               Ridderstraat 27 | 8061 GH Hasselt | The Netherlands
        tel: 038 477 53 69 | www.pragma-ade.nl | www.pragma-pod.nl
-----------------------------------------------------------------

[-- Attachment #2: lang-imp-cn.lua --]
[-- Type: text/plain, Size: 441 bytes --]

local function whatever(name)
    local data = io.loaddata(name)
    if data then
        local mapping = { }
        for a, b in string.gmatch(data,".-: ([^, ]+).-# (%S+)") do -- U+4E00: yī  # 一
            mapping[b] = a
        end
        return mapping
    end
end

return {
    name = "cn transliterations",
    transliterations = {
        ["hanyu to pinlu"] = {
            mapping = whatever("kHanyuPinlu.txt")
        }
    }
}

[-- Attachment #3: sort-imp-cn.lua --]
[-- Type: text/plain, Size: 666 bytes --]

local utfchar, utfbyte  = utf.char, utf.byte
local sorters           = sorters or { }
local definitions       = sorters.definitions or { }
local replacementoffset = sorters.constants.replacementoffset
local variables         = interfaces.variables or { }

local function whatever(name)
    local data = io.loaddata(name)
    if data then
        local replacements = { }
        for a, b in string.gmatch(data,".-: ([^, ]+).-# (%S+)") do -- U+4E00: yī  # 一
            replacements[#replacements+1] = { b, a }
        end
        return replacements
    end
end

definitions["cn-hanzi"] = {
 -- orders = {
 -- }
    replacements = whatever("kHanyuPinlu.txt"),
}


[-- Attachment #4: test.tex --]
[-- Type: text/plain, Size: 907 bytes --]

\mainlanguage[cn]

\registerctxluafile{sort-imp-cn}{}

\usetransliteration[cn]

\definetransliteration
    [MyChinese]
    [color=blue,
     vector={hanyu to pinlu}]

\starttext

    \definedfont[name:adobesongstdlight]

    test 词语拼音数据 \index{词语拼音数据}\par
    test 据词语拼音数 \index{据词语拼音数}\par
    test 数据词语拼音 \index{数据词语拼音}\par

    \blank

    \starttransliteration[MyChinese]
        \tf
        词语拼音数据
        据词语拼音数
        数据词语拼音
    \stoptransliteration

    \placeregister
      [index]
      [n=1,indicator=no]

    \placeregister
      [index]
      [language=cn-hanzi,n=1]

    \starttransliteration[MyChinese]
        \tf
        \placeregister
          [index]
          [language=cn-hanzi,n=1,inbetween=]
    \stoptransliteration

\stoptext


[-- Attachment #5: Type: text/plain, Size: 511 bytes --]

___________________________________________________________________________________
If your question is of interest to others as well, please add an entry to the Wiki!

maillist : ntg-context@ntg.nl / https://mailman.ntg.nl/mailman3/lists/ntg-context.ntg.nl
webpage  : https://www.pragma-ade.nl / https://context.aanhet.net (mirror)
archive  : https://github.com/contextgarden/context
wiki     : https://wiki.contextgarden.net
___________________________________________________________________________________