Unicode UTF-8 strings handling - GameCreators Forum

Author

Message

Scary Little Rabbit

15

Years of Service

User Offline

Joined: 4th Aug 2009

Location: Chelyabinsk, Russian Federation.

Posted: 14th Sep 2016 16:12 Edited at: 16th Dec 2016 09:08

Link

OK, since AppGameKit is working on Ubuntu again:

// project: UTF8
// created: 2016-09-13
// license: MIT
// abstract: analogues for len(), mid(), left(), right(), asc(), chr() functions to work with UTF-8 strings

// tip me via bitcoin:1C5NZCMkjJTf8v7t41QwW9EeCjJcLEbf5s or https://paypal.me/harder

// to use strLen(), strMid(), strLeft(), strRight(), getUTF(), chrUTF() instead those internal AGK commands
// place two following lines to your initialization code (uncomment them of course)
// #include 'UTF8.agc'
//     initUTF8()

type UTF8Type
    ID      as integer
    char    as string
    // bytes   as integer[]  // uncomment if you need to use it somewhere
endtype

#constant _chrUnknownID 63  // ID of '?' char

global _intMemblock             as integer
global _strLength               as integer
global _strMemblock             as integer
global _str                     as string
global _strMemblockCharOffsets  as integer[0]
global _UTF8                    as UTF8Type[0]

function initUTF8()
    _intMemblock = createMemblock(4)
    _strMemblock = createMemblock(4)

// prepare _UTF8 cache (for runtime perfomance optimization)
    // tab
        newUTF8(9)
    // latin and some basic punctuation
    for b = 32 to 126
        newUTF8(b)
    next
    // some latin with diacritics and additional punctuation (Unicode block LATIN_1_SUPPLEMENT)
    for b = 160 to 191
        newUTF8(int2(194, b))
    next
    for b = 128 to 191
        newUTF8(int2(195, b))
    next
    // some cyrillic (Unicode block CYRILLIC)
    for b = 128 to 191
        newUTF8(int2(208, b))
    next
    for b = 128 to 159
        newUTF8(int2(209, b))
    next
endfunction

function strLen(s as string)
    if s = '' then exitfunction 0

strUni(s)
endfunction _strLength

function strUni(s as string)
    if s = _str then exitfunction _strMemblockCharOffsets[1] > 0

sl = len(s)

if sl > _strMemblockCharOffsets.length then _strMemblockCharOffsets.length = sl  // yep, sl value is too high but anyway

_str = s
    _strLength = 0

deleteMemblock(_strMemblock)
    createMemblock(_strMemblock, sl + 1)
        setMemblockString(_strMemblock, 0, s)

i = 0
    while i < sl
        b = getMemblockByte(_strMemblock, i)
        if b < 128
            inc i
            inc _strLength
                _strMemblockCharOffsets[_strLength] = i
        elseif b > 191
            if b < 224
                inc i, 2
                if i > sl
                    _strLength = sl : exit
                else
                    inc _strLength
                        _strMemblockCharOffsets[_strLength] = i
                endif
            elseif b < 240
                inc i, 3
                if i > sl
                    _strLength = sl : exit
                else
                    inc _strLength
                        _strMemblockCharOffsets[_strLength] = i
                endif
            elseif b < 248
                inc i, 4
                if i > sl
                    _strLength = sl : exit
                else
                    inc _strLength
                        _strMemblockCharOffsets[_strLength] = i
                endif
            else  // it's not Unicode char
                _strLength = sl : exit
            endif
        else  // it's not Unicode char
            _strLength = sl : exit
        endif
    endwhile

if _strLength = sl
        _strMemblockCharOffsets[1] = 0 : exitfunction 0
    endif
endfunction 1

function strMid(s as string, p as integer, l as integer)
    res as string

if s = '' or p < 1 or l = 0 then exitfunction ''

if strUni(s) = 0 then exitfunction mid(s, p, l)

dec p
    if l > 0
        l = p + l
            if l > _strLength then l = _strLength
    else
        l = _strLength
    endif
    p = _strMemblockCharOffsets[p]
        res = getMemblockString(_strMemblock, p, _strMemblockCharOffsets[l] - p)
endfunction res

function strLeft(s as string, l as integer)
    res as string

if s = '' or l < 1 then exitfunction ''

if strUni(s) = 0 then exitfunction left(s, l)

if l > _strLength then l = _strLength
        res = getMemblockString(_strMemblock, 0, _strMemblockCharOffsets[l])
endfunction res

function strRight(s as string, l as integer)
    res as string

if s = '' or l < 1 then exitfunction ''

if strUni(s) = 0 then exitfunction right(s, l)

p = _strLength - l
        if p <= 0
            p = 0
        else
            p = _strMemblockCharOffsets[p]
        endif
        res = getMemblockString(_strMemblock, p, _strMemblockCharOffsets[_strLength] - p)
endfunction res

function newUTF8(r as integer)
    bytes   as integer[]
    x       as UTF8Type

if r = 0 then exitfunction ''

setMemblockInt(_intMemblock, 0, r)
    for i = 0 to 3
        b = getMemblockByte(_intMemblock, i)
            if bytes.length > -1 or b > 0 then bytes.insert(b)
    next

// WARN we check only first byte here and everywhere; fix it if you're paranoid
    if bytes[0] < 192
        if bytes[0] > 127 then exitfunction ''
    else
        if bytes[0] < 224
            if bytes.length <> 1 then exitfunction ''
        elseif bytes[0] < 240
            if bytes.length <> 2 then exitfunction ''
        elseif bytes[0] < 248
            if bytes.length <> 3 then exitfunction ''
        else
            exitfunction ''
        endif
    endif

x.ID = r
    x.char = getMemblockString(_intMemblock, 3 - bytes.length, bytes.length + 1)
    // x.bytes = bytes  // uncomment if you need to use it somewhere
        _UTF8.insertSorted(x)
endfunction x.char

function chrUTF8(r as integer)
    res as string

i = _UTF8.find(r)
        if i > -1 then exitfunction _UTF8[i].char

res = newUTF8(r)
endfunction res

function getUTF8(s as string)
    sl = len(s)

if sl = 0 then exitfunction 0

m = createMemblock(sl + 1)
        setMemblockString(m, 0, s)

b = getMemblockByte(m, 0)
        if b < 128
            i = b
        elseif b > 191
            if b < 224
                if sl > 0
                    i = int2(b, getMemblockByte(m, 1))
                else
                    i = _chrUnknownID
                endif
            elseif b < 240
                if sl > 1
                    i = int3(b, getMemblockByte(m, 1), getMemblockByte(m, 2))
                else
                    i = _chrUnknownID
                endif
            elseif b < 248
                if sl > 2
                    i = int4(b, getMemblockByte(m, 1), getMemblockByte(m, 2), getMemblockByte(m, 3))
                else
                    i = _chrUnknownID
                endif
            else  // it's not Unicode char
                i = _chrUnknownID
            endif
        else  // it's not Unicode char
            i = _chrUnknownID
        endif

deleteMemblock(m)
endfunction i

function int2(b as integer, a as integer)
    setMemblockByte(_intMemblock, 0, 0)
    setMemblockByte(_intMemblock, 1, 0)
    setMemblockByte(_intMemblock, 2, b)
    setMemblockByte(_intMemblock, 3, a)

i = getMemblockInt(_intMemblock, 0)
endfunction i

function int3(c as integer, b as integer, a as integer)
    setMemblockByte(_intMemblock, 0, 0)
    setMemblockByte(_intMemblock, 1, c)
    setMemblockByte(_intMemblock, 2, b)
    setMemblockByte(_intMemblock, 3, a)

i = getMemblockInt(_intMemblock, 0)
endfunction i

function int4(d as integer, c as integer, b as integer, a as integer)
    setMemblockByte(_intMemblock, 0, d)
    setMemblockByte(_intMemblock, 1, c)
    setMemblockByte(_intMemblock, 2, b)
    setMemblockByte(_intMemblock, 3, a)

i = getMemblockInt(_intMemblock, 0)
endfunction i

+ Code Snippet

// project: UTF8
// created: 2016-09-13
// license: MIT
// abstract: analogues for len(), mid(), left(), right(), asc(), chr() functions to work with UTF-8 strings

// copyright (c) 2016, Simon Grim

// tip me via bitcoin:1C5NZCMkjJTf8v7t41QwW9EeCjJcLEbf5s or https://paypal.me/harder


// to use strLen(), strMid(), strLeft(), strRight(), getUTF(), chrUTF() instead those internal AGK commands
// place two following lines to your initialization code (uncomment them of course)
// #include 'UTF8.agc'
//     initUTF8()


type UTF8Type
    ID      as integer
    char    as string
    // bytes   as integer[]  // uncomment if you need to use it somewhere
endtype


#constant _chrUnknownID 63  // ID of '?' char

global _intMemblock             as integer
global _strLength               as integer
global _strMemblock             as integer
global _str                     as string
global _strMemblockCharOffsets  as integer[0]
global _UTF8                    as UTF8Type[0]


function initUTF8()
    _intMemblock = createMemblock(4)
    _strMemblock = createMemblock(4)

    // prepare _UTF8 cache (for runtime perfomance optimization)
    // tab
        newUTF8(9)
    // latin and some basic punctuation
    for b = 32 to 126
        newUTF8(b)
    next
    // some latin with diacritics and additional punctuation (Unicode block LATIN_1_SUPPLEMENT)
    for b = 160 to 191
        newUTF8(int2(194, b))
    next
    for b = 128 to 191
        newUTF8(int2(195, b))
    next
    // some cyrillic (Unicode block CYRILLIC)
    for b = 128 to 191
        newUTF8(int2(208, b))
    next
    for b = 128 to 159
        newUTF8(int2(209, b))
    next
endfunction

function strLen(s as string)
    if s = '' then exitfunction 0

    strUni(s)
endfunction _strLength

function strUni(s as string)
    if s = _str then exitfunction _strMemblockCharOffsets[1] > 0

    sl = len(s)

    if sl > _strMemblockCharOffsets.length then _strMemblockCharOffsets.length = sl  // yep, sl value is too high but anyway

    _str = s
    _strLength = 0

    deleteMemblock(_strMemblock)
    createMemblock(_strMemblock, sl + 1)
        setMemblockString(_strMemblock, 0, s)

    i = 0
    while i < sl
        b = getMemblockByte(_strMemblock, i)
        if b < 128
            inc i
            inc _strLength
                _strMemblockCharOffsets[_strLength] = i
        elseif b > 191
            if b < 224
                inc i, 2
                if i > sl
                    _strLength = sl : exit
                else
                    inc _strLength
                        _strMemblockCharOffsets[_strLength] = i
                endif
            elseif b < 240
                inc i, 3
                if i > sl
                    _strLength = sl : exit
                else
                    inc _strLength
                        _strMemblockCharOffsets[_strLength] = i
                endif
            elseif b < 248
                inc i, 4
                if i > sl
                    _strLength = sl : exit
                else
                    inc _strLength
                        _strMemblockCharOffsets[_strLength] = i
                endif
            else  // it's not Unicode char
                _strLength = sl : exit
            endif
        else  // it's not Unicode char
            _strLength = sl : exit
        endif
    endwhile

    if _strLength = sl
        _strMemblockCharOffsets[1] = 0 : exitfunction 0
    endif
endfunction 1

function strMid(s as string, p as integer, l as integer)
    res as string

    if s = '' or p < 1 or l = 0 then exitfunction ''

    if strUni(s) = 0 then exitfunction mid(s, p, l)

    dec p
    if l > 0
        l = p + l
            if l > _strLength then l = _strLength
    else
        l = _strLength
    endif
    p = _strMemblockCharOffsets[p]
        res = getMemblockString(_strMemblock, p, _strMemblockCharOffsets[l] - p)
endfunction res

function strLeft(s as string, l as integer)
    res as string

    if s = '' or l < 1 then exitfunction ''

    if strUni(s) = 0 then exitfunction left(s, l)

    if l > _strLength then l = _strLength
        res = getMemblockString(_strMemblock, 0, _strMemblockCharOffsets[l])
endfunction res

function strRight(s as string, l as integer)
    res as string

    if s = '' or l < 1 then exitfunction ''

    if strUni(s) = 0 then exitfunction right(s, l)

    p = _strLength - l
        if p <= 0
            p = 0
        else
            p = _strMemblockCharOffsets[p]
        endif
        res = getMemblockString(_strMemblock, p, _strMemblockCharOffsets[_strLength] - p)
endfunction res

function newUTF8(r as integer)
    bytes   as integer[]
    x       as UTF8Type

    if r = 0 then exitfunction ''

    setMemblockInt(_intMemblock, 0, r)
    for i = 0 to 3
        b = getMemblockByte(_intMemblock, i)
            if bytes.length > -1 or b > 0 then bytes.insert(b)
    next

    // WARN we check only first byte here and everywhere; fix it if you're paranoid
    if bytes[0] < 192
        if bytes[0] > 127 then exitfunction ''
    else
        if bytes[0] < 224
            if bytes.length <> 1 then exitfunction ''
        elseif bytes[0] < 240
            if bytes.length <> 2 then exitfunction ''
        elseif bytes[0] < 248
            if bytes.length <> 3 then exitfunction ''
        else
            exitfunction ''
        endif
    endif

    x.ID = r
    x.char = getMemblockString(_intMemblock, 3 - bytes.length, bytes.length + 1)
    // x.bytes = bytes  // uncomment if you need to use it somewhere
        _UTF8.insertSorted(x)
endfunction x.char

function chrUTF8(r as integer)
    res as string

    i = _UTF8.find(r)
        if i > -1 then exitfunction _UTF8[i].char

    res = newUTF8(r)
endfunction res

function getUTF8(s as string)
    sl = len(s)

    if sl = 0 then exitfunction 0

    m = createMemblock(sl + 1)
        setMemblockString(m, 0, s)

    b = getMemblockByte(m, 0)
        if b < 128
            i = b
        elseif b > 191
            if b < 224
                if sl > 0
                    i = int2(b, getMemblockByte(m, 1))
                else
                    i = _chrUnknownID
                endif
            elseif b < 240
                if sl > 1
                    i = int3(b, getMemblockByte(m, 1), getMemblockByte(m, 2))
                else
                    i = _chrUnknownID
                endif
            elseif b < 248
                if sl > 2
                    i = int4(b, getMemblockByte(m, 1), getMemblockByte(m, 2), getMemblockByte(m, 3))
                else
                    i = _chrUnknownID
                endif
            else  // it's not Unicode char
                i = _chrUnknownID
            endif
        else  // it's not Unicode char
            i = _chrUnknownID
        endif

        deleteMemblock(m)
endfunction i

function int2(b as integer, a as integer)
    setMemblockByte(_intMemblock, 0, 0)
    setMemblockByte(_intMemblock, 1, 0)
    setMemblockByte(_intMemblock, 2, b)
    setMemblockByte(_intMemblock, 3, a)

    i = getMemblockInt(_intMemblock, 0)
endfunction i

function int3(c as integer, b as integer, a as integer)
    setMemblockByte(_intMemblock, 0, 0)
    setMemblockByte(_intMemblock, 1, c)
    setMemblockByte(_intMemblock, 2, b)
    setMemblockByte(_intMemblock, 3, a)

    i = getMemblockInt(_intMemblock, 0)
endfunction i

function int4(d as integer, c as integer, b as integer, a as integer)
    setMemblockByte(_intMemblock, 0, d)
    setMemblockByte(_intMemblock, 1, c)
    setMemblockByte(_intMemblock, 2, b)
    setMemblockByte(_intMemblock, 3, a)

    i = getMemblockInt(_intMemblock, 0)
endfunction i

gist.

if you want to get any of your strings to the screen try text functions from txtUTF8.agc.

there is an example project in attached archive.

~~have fun.~~ NO FUN ANYMORE — that's all, folks!

error #1:
'too many stars, too many stares. disembody.'
Unicode yours

Attachments

Login to view attachments

Back to top

Profile PM Email Website

Scary Little Rabbit

15

Years of Service

User Offline

Joined: 4th Aug 2009

Location: Chelyabinsk, Russian Federation.

Posted: 22nd Sep 2016 20:57

Link

* code was rewritten to speed runtime up a bit (it's about 40% faster now)
* a tabulation was added to initially generated list of chars
* getUTF8() was rewritten and uncommented (it's like asc(), but returns 63 in case if char is unknown (need to polish))

error #1:
'too many stars, too many stares. disembody.'
Unicode yours

Back to top

Profile PM Email Website

Scary Little Rabbit

15

Years of Service

User Offline

Joined: 4th Aug 2009

Location: Chelyabinsk, Russian Federation.

Posted: 1st Oct 2016 12:41

Link

* there is no more need for a file with predefined list of UTF-8 chars to use

error #1:
'too many stars, too many stares. disembody.'
Unicode yours

Back to top

Profile PM Email Website

jamesB

8

Years of Service

User Offline

Joined: 2nd Sep 2016

Location:

Posted: 9th Oct 2016 13:26

Link

Thanks a lot, very helpful.

How can I use this to create Russian text using CreateText() which I can display on the screen (i.e. not in a file)?

Back to top

Profile PM

Scary Little Rabbit

15

Years of Service

User Offline

Joined: 4th Aug 2009

Location: Chelyabinsk, Russian Federation.

Posted: 10th Oct 2016 07:10 Edited at: 20th Oct 2016 20:08

Link

jamesB, you need a font image with cyrillic chars loaded, setTextExtendedFontImage() command applied with that image index number passed to it for your text objects (or setTextDefaultExtendedFontImage() for all by default) and some function to map Unicode chars to ASCII ones, like this one:

function strReplaceCyrillicWithASCIIExtendedLatin(s as string)
// license: MIT
// copyright (c) 2016, Simon Grim
// tip me via bitcoin:1C5NZCMkjJTf8v7t41QwW9EeCjJcLEbf5s or https://paypal.me/harder

s = replaceString(s, 'А', chr(192), -1)
    s = replaceString(s, 'Б', chr(193), -1)
    s = replaceString(s, 'В', chr(194), -1)
    s = replaceString(s, 'Г', chr(195), -1)
    s = replaceString(s, 'Д', chr(196), -1)
    s = replaceString(s, 'Е', chr(197), -1)
    s = replaceString(s, 'Ё', chr(168), -1)
    s = replaceString(s, 'Ж', chr(198), -1)
    s = replaceString(s, 'З', chr(199), -1)
    s = replaceString(s, 'И', chr(200), -1)
    s = replaceString(s, 'Й', chr(201), -1)
    s = replaceString(s, 'К', chr(202), -1)
    s = replaceString(s, 'Л', chr(203), -1)
    s = replaceString(s, 'М', chr(204), -1)
    s = replaceString(s, 'Н', chr(205), -1)
    s = replaceString(s, 'О', chr(206), -1)
    s = replaceString(s, 'П', chr(207), -1)
    s = replaceString(s, 'Р', chr(208), -1)
    s = replaceString(s, 'С', chr(209), -1)
    s = replaceString(s, 'Т', chr(210), -1)
    s = replaceString(s, 'У', chr(211), -1)
    s = replaceString(s, 'Ф', chr(212), -1)
    s = replaceString(s, 'Х', chr(213), -1)
    s = replaceString(s, 'Ц', chr(214), -1)
    s = replaceString(s, 'Ч', chr(215), -1)
    s = replaceString(s, 'Ш', chr(216), -1)
    s = replaceString(s, 'Щ', chr(217), -1)
    s = replaceString(s, 'Ъ', chr(218), -1)
    s = replaceString(s, 'Ы', chr(219), -1)
    s = replaceString(s, 'Ь', chr(220), -1)
    s = replaceString(s, 'Э', chr(221), -1)
    s = replaceString(s, 'Ю', chr(222), -1)
    s = replaceString(s, 'Я', chr(223), -1)

s = replaceString(s, 'а', chr(224), -1)
    s = replaceString(s, 'б', chr(225), -1)
    s = replaceString(s, 'в', chr(226), -1)
    s = replaceString(s, 'г', chr(227), -1)
    s = replaceString(s, 'д', chr(228), -1)
    s = replaceString(s, 'е', chr(229), -1)
    s = replaceString(s, 'ё', chr(184), -1)
    s = replaceString(s, 'ж', chr(230), -1)
    s = replaceString(s, 'з', chr(231), -1)
    s = replaceString(s, 'и', chr(232), -1)
    s = replaceString(s, 'й', chr(233), -1)
    s = replaceString(s, 'к', chr(234), -1)
    s = replaceString(s, 'л', chr(235), -1)
    s = replaceString(s, 'м', chr(236), -1)
    s = replaceString(s, 'н', chr(237), -1)
    s = replaceString(s, 'о', chr(238), -1)
    s = replaceString(s, 'п', chr(239), -1)
    s = replaceString(s, 'р', chr(240), -1)
    s = replaceString(s, 'с', chr(241), -1)
    s = replaceString(s, 'т', chr(242), -1)
    s = replaceString(s, 'у', chr(243), -1)
    s = replaceString(s, 'ф', chr(244), -1)
    s = replaceString(s, 'х', chr(245), -1)
    s = replaceString(s, 'ц', chr(246), -1)
    s = replaceString(s, 'ч', chr(247), -1)
    s = replaceString(s, 'ш', chr(248), -1)
    s = replaceString(s, 'щ', chr(249), -1)
    s = replaceString(s, 'ъ', chr(250), -1)
    s = replaceString(s, 'ы', chr(251), -1)
    s = replaceString(s, 'ь', chr(252), -1)
    s = replaceString(s, 'э', chr(253), -1)
    s = replaceString(s, 'ю', chr(254), -1)
    s = replaceString(s, 'я', chr(255), -1)

s = replaceString(s, '»', chr(187), -1)
    s = replaceString(s, '«', chr(171), -1)
    s = replaceString(s, '—', chr(151), -1)
    s = replaceString(s, '№', chr(185), -1)
endfunction s

+ Code Snippet

function strReplaceCyrillicWithASCIIExtendedLatin(s as string)
// license: MIT
// copyright (c) 2016, Simon Grim
// tip me via bitcoin:1C5NZCMkjJTf8v7t41QwW9EeCjJcLEbf5s or https://paypal.me/harder

    s = replaceString(s, 'А', chr(192), -1)
    s = replaceString(s, 'Б', chr(193), -1)
    s = replaceString(s, 'В', chr(194), -1)
    s = replaceString(s, 'Г', chr(195), -1)
    s = replaceString(s, 'Д', chr(196), -1)
    s = replaceString(s, 'Е', chr(197), -1)
    s = replaceString(s, 'Ё', chr(168), -1)
    s = replaceString(s, 'Ж', chr(198), -1)
    s = replaceString(s, 'З', chr(199), -1)
    s = replaceString(s, 'И', chr(200), -1)
    s = replaceString(s, 'Й', chr(201), -1)
    s = replaceString(s, 'К', chr(202), -1)
    s = replaceString(s, 'Л', chr(203), -1)
    s = replaceString(s, 'М', chr(204), -1)
    s = replaceString(s, 'Н', chr(205), -1)
    s = replaceString(s, 'О', chr(206), -1)
    s = replaceString(s, 'П', chr(207), -1)
    s = replaceString(s, 'Р', chr(208), -1)
    s = replaceString(s, 'С', chr(209), -1)
    s = replaceString(s, 'Т', chr(210), -1)
    s = replaceString(s, 'У', chr(211), -1)
    s = replaceString(s, 'Ф', chr(212), -1)
    s = replaceString(s, 'Х', chr(213), -1)
    s = replaceString(s, 'Ц', chr(214), -1)
    s = replaceString(s, 'Ч', chr(215), -1)
    s = replaceString(s, 'Ш', chr(216), -1)
    s = replaceString(s, 'Щ', chr(217), -1)
    s = replaceString(s, 'Ъ', chr(218), -1)
    s = replaceString(s, 'Ы', chr(219), -1)
    s = replaceString(s, 'Ь', chr(220), -1)
    s = replaceString(s, 'Э', chr(221), -1)
    s = replaceString(s, 'Ю', chr(222), -1)
    s = replaceString(s, 'Я', chr(223), -1)

    s = replaceString(s, 'а', chr(224), -1)
    s = replaceString(s, 'б', chr(225), -1)
    s = replaceString(s, 'в', chr(226), -1)
    s = replaceString(s, 'г', chr(227), -1)
    s = replaceString(s, 'д', chr(228), -1)
    s = replaceString(s, 'е', chr(229), -1)
    s = replaceString(s, 'ё', chr(184), -1)
    s = replaceString(s, 'ж', chr(230), -1)
    s = replaceString(s, 'з', chr(231), -1)
    s = replaceString(s, 'и', chr(232), -1)
    s = replaceString(s, 'й', chr(233), -1)
    s = replaceString(s, 'к', chr(234), -1)
    s = replaceString(s, 'л', chr(235), -1)
    s = replaceString(s, 'м', chr(236), -1)
    s = replaceString(s, 'н', chr(237), -1)
    s = replaceString(s, 'о', chr(238), -1)
    s = replaceString(s, 'п', chr(239), -1)
    s = replaceString(s, 'р', chr(240), -1)
    s = replaceString(s, 'с', chr(241), -1)
    s = replaceString(s, 'т', chr(242), -1)
    s = replaceString(s, 'у', chr(243), -1)
    s = replaceString(s, 'ф', chr(244), -1)
    s = replaceString(s, 'х', chr(245), -1)
    s = replaceString(s, 'ц', chr(246), -1)
    s = replaceString(s, 'ч', chr(247), -1)
    s = replaceString(s, 'ш', chr(248), -1)
    s = replaceString(s, 'щ', chr(249), -1)
    s = replaceString(s, 'ъ', chr(250), -1)
    s = replaceString(s, 'ы', chr(251), -1)
    s = replaceString(s, 'ь', chr(252), -1)
    s = replaceString(s, 'э', chr(253), -1)
    s = replaceString(s, 'ю', chr(254), -1)
    s = replaceString(s, 'я', chr(255), -1)

    s = replaceString(s, '»', chr(187), -1)
    s = replaceString(s, '«', chr(171), -1)
    s = replaceString(s, '—', chr(151), -1)
    s = replaceString(s, '№', chr(185), -1)
endfunction s

e.g.

+ Code Snippet

fontImageRu = loadImage('/media/_path/to/myFontImageRu.whatever')  // note you need to have correct '/media/_path/to/myFontImageRu subimages.txt' also

// setTextDefaultExtendedFontImage(fontImageRu)  // uncomment this line if you need cyrillic font for all texts by default

txtWithCyrillic = createText(strReplaceCyrillicWithASCIIExtendedLatin('Привет, мир!'))
    setTextExtendedFontImage(txtWithCyrillic, fontImageRu)  // delete this line if you have uncommented that line above

// to change txtWithCyrillic's string at anytime:
// setTextString(txtWithCyrillic, strReplaceCyrillicWithASCIIExtendedLatin('Как дела, мир?'))

UPD

nah, try this instead. you still need some font image with well prepared 'subimages.txt' though.

error #1:
'too many stars, too many stares. disembody.'
Unicode yours

Back to top

Profile PM Email Website

Alex_Peres

AGK Master

15

Years of Service

User Offline

Joined: 13th May 2009

Location: The Milky Way Galaxy

Posted: 10th Oct 2016 12:28

Link

Where have you been three month ago...

Спасибо бро!

Back to top

Profile PM

Scary Little Rabbit

15

Years of Service

User Offline

Joined: 4th Aug 2009

Location: Chelyabinsk, Russian Federation.

Posted: 10th Oct 2016 13:13 Edited at: 10th Oct 2016 13:14

Link

Alex_Peres, and where have you been? I was here complaining about the issue and suggesting some crazy things.

на здоровье.

error #1:
'too many stars, too many stares. disembody.'
Unicode yours

Back to top

Profile PM Email Website

Alex_Peres

AGK Master

15

Years of Service

User Offline

Joined: 13th May 2009

Location: The Milky Way Galaxy

Posted: 10th Oct 2016 15:58

Link

I've made my own font system which is working on every language(even chinese

) and every platform!
But it's for tier2...

Back to top

Profile PM

Scary Little Rabbit

15

Years of Service

User Offline

Joined: 4th Aug 2009

Location: Chelyabinsk, Russian Federation.

Posted: 20th Oct 2016 08:34

Link

* critical bug in chars' parsing was fixed

error #1:
'too many stars, too many stares. disembody.'
Unicode yours

Back to top

Profile PM Email Website

Scary Little Rabbit

15

Years of Service

User Offline

Joined: 4th Aug 2009

Location: Chelyabinsk, Russian Federation.

Posted: 20th Oct 2016 20:04

Link

Alex_Peres, OK, I've made something similar too, for Tier 1.

error #1:
'too many stars, too many stares. disembody.'
Unicode yours

Back to top

Profile PM Email Website

Scary Little Rabbit

15

Years of Service

User Offline

Joined: 4th Aug 2009

Location: Chelyabinsk, Russian Federation.

Posted: 16th Dec 2016 09:00

Link

OK, it's obsolete since version 2.0.22 is out with built-in support of UTF-8. and more over — the code is broken because len() returns correct value of string chars now: the value of 'sl' is to low in strUni() and app is going to crash when it executes setMemblockString(_strMemblock, 0, s) at line #80. I see no reason to fix it, all you need is an upgrade to version 2.0.22.

error #1:
'too many stars, too many stares. disembody.'
Unicode yours

Back to top

Profile PM Email Website