Menü

Mail Listen Archiv | Code Startseite | Anzeige aller Code Fragmente

4D Code Library

4D Support Center - 4D Code Beispiel zum Thema:

MacRoman to DOS/UTF8/UTF16 und umgekehrt

Erfaßt von: Thomas Maul (eMail: Thomas.Maul@de.4D.com ) am 08.03.2005 ; -
Letzte Änderung: 08.03.2005

Kurzbeschriebung:

4D beinhaltet Befehle zur Konvertierung Mac to Win/ISO8859-1. Diese Routinen konvertieren außerdem zu DOS (Codepage 850) und Unicode (UTF8 und 16) und zurück

Beschreibung

Es ist eine Sammlung von sechs Methoden, die per Copy&Paste in vorhandene Programme übernommen werden kann - oder per 4D Insider.
Konvertierung jeweils von bzw. zu MacRoman, da Windows/ISO8859-1 Texte in MacRoman konvertiert werden können.
Die Routinen sind hilfreich wenn man E-Mails im UTF8 Format erhält oder Daten exportieren/importieren muß. Hinweis: bei Import/Export über XML Dokumente konvertiert 4D automatisch UTF8.
Die Methoden werden hier einzeln eingesetzt, empfohlen wird jedoch diese aus dem beiliegenden 4D Struktur zu kopieren, um Copy&Paste Fehler zu vermeiden.
Die Struktur beinhaltet in der Gruppe "Converter"diese 6 Methoden.
Die Gruppe "Tools" beinhaltet Routinen zur Erzeugung von Konvertierungsmethoden (diese wurden nicht manuell eingetippt sondern automatisiert erzeugt).
Diese Methoden erlauben auch das Anlegen von anderen Konvertern, wie z. B. Win to UTF16 oder ISO-8859-3 to MacRoman
Die dazu nötigen Konvertierungslisten können importiert werden Dazu Methode "ImportTable" verwenden, Tabellen gibt es unter  ftp://ftp.unicode.org/Public/MAPPINGS/.

Beschreibung ändern (nur für Autor - Kennwort geschützt) Keine Beschreibung für MacRoman to DOS/UTF8/UTF16 und umgekehrt

4D Code Beispiel

` Code table from CP850 to MacRoman
$asciitable:=""
For ($i;0;127)
	$asciitable:=$asciitable+Char($i)
End for 
$asciitable:=$asciitable+Char(130)+Char(159)
$asciitable:=$asciitable+Char(142)+Char(137)+Char(138)+Char(136)+Char(140)+Char(141)+Char(144)+Char(145)+Char(143)+Char(149)
$asciitable:=$asciitable+Char(148)+Char(147)+Char(128)+Char(129)+Char(131)+Char(190)+Char(174)+Char(153)+Char(154)+Char(152)
$asciitable:=$asciitable+Char(158)+Char(157)+Char(216)+Char(133)+Char(134)+Char(191)+Char(163)+Char(175)+Char(32)+Char(196)
$asciitable:=$asciitable+Char(135)+Char(146)+Char(151)+Char(156)+Char(150)+Char(132)+Char(187)+Char(188)+Char(192)+Char(168)
$asciitable:=$asciitable+Char(194)+Char(32)+Char(32)+Char(193)+Char(199)+Char(200)+Char(32)+Char(32)+Char(32)+Char(32)
$asciitable:=$asciitable+Char(32)+Char(231)+Char(229)+Char(203)+Char(169)+Char(32)+Char(32)+Char(32)+Char(32)+Char(162)
$asciitable:=$asciitable+Char(180)+Char(32)+Char(32)+Char(32)+Char(32)+Char(32)+Char(32)+Char(32)+Char(139)+Char(204)
$asciitable:=$asciitable+Char(32)+Char(32)+Char(32)+Char(32)+Char(32)+Char(32)+Char(32)+Char(32)+Char(32)+Char(32)
$asciitable:=$asciitable+Char(230)+Char(232)+Char(233)+Char(245)+Char(234)+Char(235)+Char(236)+Char(32)+Char(32)+Char(32)
$asciitable:=$asciitable+Char(32)+Char(32)+Char(237)+Char(32)+Char(238)+Char(167)+Char(239)+Char(241)+Char(155)+Char(205)
$asciitable:=$asciitable+Char(181)+Char(32)+Char(32)+Char(242)+Char(243)+Char(244)+Char(32)+Char(32)+Char(248)+Char(171)
$asciitable:=$asciitable+Char(32)+Char(177)+Char(32)+Char(32)+Char(166)+Char(164)+Char(214)+Char(252)+Char(161)+Char(172)
$asciitable:=$asciitable+Char(225)+Char(32)+Char(32)+Char(32)+Char(32)+Char(202)

$0:=""
For ($i;1;Length($1))
	$0:=$0+$asciitable[[Ascii($1[[$i]])+1]]
	
	$old:=Ascii($1[[$i]])
	$new:=$asciitable[[$old+1]]
End for

` Code table from MacRoman to CP850
$asciitable:=""
For ($i;0;127)
	$asciitable:=$asciitable+Char($i)
End for 
$asciitable:=$asciitable+Char(142)+Char(143)
$asciitable:=$asciitable+Char(128)+Char(144)+Char(165)+Char(153)+Char(154)+Char(160)+Char(133)+Char(131)+Char(132)+Char(198)
$asciitable:=$asciitable+Char(134)+Char(135)+Char(130)+Char(138)+Char(136)+Char(137)+Char(161)+Char(141)+Char(140)+Char(139)
$asciitable:=$asciitable+Char(164)+Char(162)+Char(149)+Char(147)+Char(148)+Char(228)+Char(163)+Char(151)+Char(150)+Char(129)
$asciitable:=$asciitable+Char(32)+Char(248)+Char(189)+Char(156)+Char(245)+Char(32)+Char(244)+Char(225)+Char(169)+Char(184)
$asciitable:=$asciitable+Char(32)+Char(239)+Char(249)+Char(32)+Char(146)+Char(157)+Char(32)+Char(241)+Char(32)+Char(32)
$asciitable:=$asciitable+Char(190)+Char(230)+Char(32)+Char(32)+Char(32)+Char(32)+Char(32)+Char(166)+Char(167)+Char(32)
$asciitable:=$asciitable+Char(145)+Char(155)+Char(168)+Char(173)+Char(170)+Char(32)+Char(159)+Char(32)+Char(32)+Char(174)
$asciitable:=$asciitable+Char(175)+Char(32)+Char(255)+Char(183)+Char(199)+Char(229)+Char(32)+Char(32)+Char(32)+Char(32)
$asciitable:=$asciitable+Char(32)+Char(32)+Char(32)+Char(32)+Char(246)+Char(32)+Char(152)+Char(32)+Char(32)+Char(32)
$asciitable:=$asciitable+Char(32)+Char(32)+Char(32)+Char(32)+Char(32)+Char(250)+Char(32)+Char(32)+Char(32)+Char(182)
$asciitable:=$asciitable+Char(210)+Char(181)+Char(211)+Char(212)+Char(214)+Char(215)+Char(216)+Char(222)+Char(224)+Char(226)
$asciitable:=$asciitable+Char(32)+Char(227)+Char(233)+Char(234)+Char(235)+Char(213)+Char(32)+Char(32)+Char(238)+Char(32)
$asciitable:=$asciitable+Char(32)+Char(32)+Char(247)+Char(32)+Char(32)+Char(32)

$0:=""
For ($i;1;Length($1))
	$0:=$0+$asciitable[[Ascii($1[[$i]])+1]]
End for

` Code table from Macroman to UTF16
$asciitable:=""
For ($i;0;127)
	$asciitable:=$asciitable+Char(0)+Char($i)
End for 
$asciitable:=$asciitable+Char(0)+Char(196)+Char(0)+Char(197)
$asciitable:=$asciitable+Char(0)+Char(199)+Char(0)+Char(201)+Char(0)+Char(209)+Char(0)+Char(214)+Char(0)+Char(220)+Char(0)+Char(225)+Char(0)+Char(224)+Char(0)+Char(226)+Char(0)+Char(228)+Char(0)+Char(227)
$asciitable:=$asciitable+Char(0)+Char(229)+Char(0)+Char(231)+Char(0)+Char(233)+Char(0)+Char(232)+Char(0)+Char(234)+Char(0)+Char(235)+Char(0)+Char(237)+Char(0)+Char(236)+Char(0)+Char(238)+Char(0)+Char(239)
$asciitable:=$asciitable+Char(0)+Char(241)+Char(0)+Char(243)+Char(0)+Char(242)+Char(0)+Char(244)+Char(0)+Char(246)+Char(0)+Char(245)+Char(0)+Char(250)+Char(0)+Char(249)+Char(0)+Char(251)+Char(0)+Char(252)
$asciitable:=$asciitable+Char(32)+Char(32)+Char(0)+Char(176)+Char(0)+Char(162)+Char(0)+Char(163)+Char(0)+Char(167)+Char(32)+Char(34)+Char(0)+Char(182)+Char(0)+Char(223)+Char(0)+Char(174)+Char(0)+Char(169)
$asciitable:=$asciitable+Char(33)+Char(34)+Char(0)+Char(180)+Char(0)+Char(168)+Char(34)+Char(96)+Char(0)+Char(198)+Char(0)+Char(216)+Char(34)+Char(30)+Char(0)+Char(177)+Char(34)+Char(100)+Char(34)+Char(101)
$asciitable:=$asciitable+Char(0)+Char(165)+Char(0)+Char(181)+Char(34)+Char(2)+Char(34)+Char(17)+Char(34)+Char(15)+Char(3)+Char(192)+Char(34)+Char(43)+Char(0)+Char(170)+Char(0)+Char(186)+Char(3)+Char(169)
$asciitable:=$asciitable+Char(0)+Char(230)+Char(0)+Char(248)+Char(0)+Char(191)+Char(0)+Char(161)+Char(0)+Char(172)+Char(34)+Char(26)+Char(1)+Char(146)+Char(34)+Char(72)+Char(34)+Char(6)+Char(0)+Char(171)
$asciitable:=$asciitable+Char(0)+Char(187)+Char(32)+Char(38)+Char(0)+Char(160)+Char(0)+Char(192)+Char(0)+Char(195)+Char(0)+Char(213)+Char(1)+Char(82)+Char(1)+Char(83)+Char(32)+Char(19)+Char(32)+Char(20)
$asciitable:=$asciitable+Char(32)+Char(28)+Char(32)+Char(29)+Char(32)+Char(24)+Char(32)+Char(25)+Char(0)+Char(247)+Char(37)+Char(202)+Char(0)+Char(255)+Char(1)+Char(120)+Char(32)+Char(68)+Char(32)+Char(172)
$asciitable:=$asciitable+Char(32)+Char(57)+Char(32)+Char(58)+Char(251)+Char(1)+Char(251)+Char(2)+Char(32)+Char(33)+Char(0)+Char(183)+Char(32)+Char(26)+Char(32)+Char(30)+Char(32)+Char(48)+Char(0)+Char(194)
$asciitable:=$asciitable+Char(0)+Char(202)+Char(0)+Char(193)+Char(0)+Char(203)+Char(0)+Char(200)+Char(0)+Char(205)+Char(0)+Char(206)+Char(0)+Char(207)+Char(0)+Char(204)+Char(0)+Char(211)+Char(0)+Char(212)
$asciitable:=$asciitable+Char(248)+Char(255)+Char(0)+Char(210)+Char(0)+Char(218)+Char(0)+Char(219)+Char(0)+Char(217)+Char(1)+Char(49)+Char(2)+Char(198)+Char(2)+Char(220)+Char(0)+Char(175)+Char(2)+Char(216)
$asciitable:=$asciitable+Char(2)+Char(217)+Char(2)+Char(218)+Char(0)+Char(184)+Char(2)+Char(221)+Char(2)+Char(219)+Char(2)+Char(199)

$0:=""
For ($i;1;Length($1))
	$0:=$0+$asciitable[[(Ascii($1[[$i]])*2)+1]]+$asciitable[[(Ascii($1[[$i]])*2)+2]]
End for

` Code table from UTF 16 to MacRoman
$0:=""
If ((Length($1)%2)=0)  ` only if even length
	For ($i;1;Length($1);2)
		$char:=(Ascii($1[[$i]])*256)+Ascii($1[[$i+1]])
		Case of 
			: ($char<128)
				$0:=$0+Char($char)
			: ($char=196)
				$0:=$0+Char(128)
			: ($char=197)
				$0:=$0+Char(129)
			: ($char=199)
				$0:=$0+Char(130)
			: ($char=201)
				$0:=$0+Char(131)
			: ($char=209)
				$0:=$0+Char(132)
			: ($char=214)
				$0:=$0+Char(133)
			: ($char=220)
				$0:=$0+Char(134)
			: ($char=225)
				$0:=$0+Char(135)
			: ($char=224)
				$0:=$0+Char(136)
			: ($char=226)
				$0:=$0+Char(137)
			: ($char=228)
				$0:=$0+Char(138)
			: ($char=227)
				$0:=$0+Char(139)
			: ($char=229)
				$0:=$0+Char(140)
			: ($char=231)
				$0:=$0+Char(141)
			: ($char=233)
				$0:=$0+Char(142)
			: ($char=232)
				$0:=$0+Char(143)
			: ($char=234)
				$0:=$0+Char(144)
			: ($char=235)
				$0:=$0+Char(145)
			: ($char=237)
				$0:=$0+Char(146)
			: ($char=236)
				$0:=$0+Char(147)
			: ($char=238)
				$0:=$0+Char(148)
			: ($char=239)
				$0:=$0+Char(149)
			: ($char=241)
				$0:=$0+Char(150)
			: ($char=243)
				$0:=$0+Char(151)
			: ($char=242)
				$0:=$0+Char(152)
			: ($char=244)
				$0:=$0+Char(153)
			: ($char=246)
				$0:=$0+Char(154)
			: ($char=245)
				$0:=$0+Char(155)
			: ($char=250)
				$0:=$0+Char(156)
			: ($char=249)
				$0:=$0+Char(157)
			: ($char=251)
				$0:=$0+Char(158)
			: ($char=252)
				$0:=$0+Char(159)
			: ($char=8224)
				$0:=$0+Char(160)
			: ($char=176)
				$0:=$0+Char(161)
			: ($char=162)
				$0:=$0+Char(162)
			: ($char=163)
				$0:=$0+Char(163)
			: ($char=167)
				$0:=$0+Char(164)
			: ($char=8226)
				$0:=$0+Char(165)
			: ($char=182)
				$0:=$0+Char(166)
			: ($char=223)
				$0:=$0+Char(167)
			: ($char=174)
				$0:=$0+Char(168)
			: ($char=169)
				$0:=$0+Char(169)
			: ($char=8482)
				$0:=$0+Char(170)
			: ($char=180)
				$0:=$0+Char(171)
			: ($char=168)
				$0:=$0+Char(172)
			: ($char=8800)
				$0:=$0+Char(173)
			: ($char=198)
				$0:=$0+Char(174)
			: ($char=216)
				$0:=$0+Char(175)
			: ($char=8734)
				$0:=$0+Char(176)
			: ($char=177)
				$0:=$0+Char(177)
			: ($char=8804)
				$0:=$0+Char(178)
			: ($char=8805)
				$0:=$0+Char(179)
			: ($char=165)
				$0:=$0+Char(180)
			: ($char=181)
				$0:=$0+Char(181)
			: ($char=8706)
				$0:=$0+Char(182)
			: ($char=8721)
				$0:=$0+Char(183)
			: ($char=8719)
				$0:=$0+Char(184)
			: ($char=960)
				$0:=$0+Char(185)
			: ($char=8747)
				$0:=$0+Char(186)
			: ($char=170)
				$0:=$0+Char(187)
			: ($char=186)
				$0:=$0+Char(188)
			: ($char=937)
				$0:=$0+Char(189)
			: ($char=230)
				$0:=$0+Char(190)
			: ($char=248)
				$0:=$0+Char(191)
			: ($char=191)
				$0:=$0+Char(192)
			: ($char=161)
				$0:=$0+Char(193)
			: ($char=172)
				$0:=$0+Char(194)
			: ($char=8730)
				$0:=$0+Char(195)
			: ($char=402)
				$0:=$0+Char(196)
			: ($char=8776)
				$0:=$0+Char(197)
			: ($char=8710)
				$0:=$0+Char(198)
			: ($char=171)
				$0:=$0+Char(199)
			: ($char=187)
				$0:=$0+Char(200)
			: ($char=8230)
				$0:=$0+Char(201)
			: ($char=160)
				$0:=$0+Char(202)
			: ($char=192)
				$0:=$0+Char(203)
			: ($char=195)
				$0:=$0+Char(204)
			: ($char=213)
				$0:=$0+Char(205)
			: ($char=338)
				$0:=$0+Char(206)
			: ($char=339)
				$0:=$0+Char(207)
			: ($char=8211)
				$0:=$0+Char(208)
			: ($char=8212)
				$0:=$0+Char(209)
			: ($char=8220)
				$0:=$0+Char(210)
			: ($char=8221)
				$0:=$0+Char(211)
			: ($char=8216)
				$0:=$0+Char(212)
			: ($char=8217)
				$0:=$0+Char(213)
			: ($char=247)
				$0:=$0+Char(214)
			: ($char=9674)
				$0:=$0+Char(215)
			: ($char=255)
				$0:=$0+Char(216)
			: ($char=376)
				$0:=$0+Char(217)
			: ($char=8260)
				$0:=$0+Char(218)
			: ($char=8364)
				$0:=$0+Char(219)
			: ($char=8249)
				$0:=$0+Char(220)
			: ($char=8250)
				$0:=$0+Char(221)
			: ($char=64257)
				$0:=$0+Char(222)
			: ($char=64258)
				$0:=$0+Char(223)
			: ($char=8225)
				$0:=$0+Char(224)
			: ($char=183)
				$0:=$0+Char(225)
			: ($char=8218)
				$0:=$0+Char(226)
			: ($char=8222)
				$0:=$0+Char(227)
			: ($char=8240)
				$0:=$0+Char(228)
			: ($char=194)
				$0:=$0+Char(229)
			: ($char=202)
				$0:=$0+Char(230)
			: ($char=193)
				$0:=$0+Char(231)
			: ($char=203)
				$0:=$0+Char(232)
			: ($char=200)
				$0:=$0+Char(233)
			: ($char=205)
				$0:=$0+Char(234)
			: ($char=206)
				$0:=$0+Char(235)
			: ($char=207)
				$0:=$0+Char(236)
			: ($char=204)
				$0:=$0+Char(237)
			: ($char=211)
				$0:=$0+Char(238)
			: ($char=212)
				$0:=$0+Char(239)
			: ($char=63743)
				$0:=$0+Char(240)
			: ($char=210)
				$0:=$0+Char(241)
			: ($char=218)
				$0:=$0+Char(242)
			: ($char=219)
				$0:=$0+Char(243)
			: ($char=217)
				$0:=$0+Char(244)
			: ($char=305)
				$0:=$0+Char(245)
			: ($char=710)
				$0:=$0+Char(246)
			: ($char=732)
				$0:=$0+Char(247)
			: ($char=175)
				$0:=$0+Char(248)
			: ($char=728)
				$0:=$0+Char(249)
			: ($char=729)
				$0:=$0+Char(250)
			: ($char=730)
				$0:=$0+Char(251)
			: ($char=184)
				$0:=$0+Char(252)
			: ($char=733)
				$0:=$0+Char(253)
			: ($char=731)
				$0:=$0+Char(254)
			: ($char=711)
				$0:=$0+Char(255)
			Else 
				$0:=$0+"*"  ` Char not in MacRoman you may want to replace it with a placeholder
		End case 
	End for 
End if

` Converts UTF16 to UTF8
  `  $UTF8 := Convert_UTF16_UTF8($UTF16)

C_TEXT($1;$0)
C_TEXT($in;$out)
C_LONGINT($i;$utf16;$utf8)

$in:=$1
$out:=""
$sixbit:=0x003F  `  0011 1111

If ((Length($in)%2)=0)  ` must be even
	For ($i;1;Length($in);2)
		$utf8:=0
		$utf16:=(Ascii($in[[$i]])*256)+Ascii($in[[$i+1]])
		Case of 
			: ($utf16<0x007F)
				$out:=$out+Char($utf16)
				
			: ($utf16<0x07FF)  ` 2 Byte
				$utf8:=0x00C0 | ($utf16 >> 6)  `  xC0 =  1100 0000
				$out:=$out+Char($utf8)
				$utf8:=0x0080 | ($utf16 & $sixbit)  `  x80 =  1000 0000
				$out:=$out+Char($utf8)
				
				
			: ($utf16<0xFFFF)  ` 3 Byte
				$utf8:=0x00E0 | ($utf16 >> 12)  `  xE0 =  1110 0000
				$out:=$out+Char($utf8)
				$utf8:=0x0080 | (($utf16 >> 6) & $sixbit)  `  x80 =  1000 0000
				$out:=$out+Char($utf8)
				$utf8:=0x0080 | ($utf16 & $sixbit)  `  x80 =  1000 0000
				$out:=$out+Char($utf8)
				
			Else   ` 4 Byte
				$utf8:=0x00F0 | ($utf16 >> 18)  `  xF0 =  1111 0000
				$out:=$out+Char($utf8)
				$utf8:=0x0080 | (($utf16 >> 12) & $sixbit)  `  x80 =  1000 0000
				$out:=$out+Char($utf8)
				$utf8:=0x0080 | (($utf16 >> 6) & $sixbit)  `  x80 =  1000 0000
				$out:=$out+Char($utf8)
				$utf8:=0x0080 | ($utf16 & $sixbit)  `  x80 =  1000 0000
				$out:=$out+Char($utf8)
		End case 
		
	End for 
End if

$0:=$out

` Converts UTF8 to UTF16
  `  $UTF16 := Convert_UTF8_UTF16($UTF8)

C_TEXT($1;$0)
C_TEXT($in;$out)
C_LONGINT($i;$utf16;$utf8)

$in:=$1
$out:=""
$sixbit:=0x003F  `  0011 1111

For ($i;1;Length($in))
	$byte:=Ascii($in[[$i]])
	$utf16:=0
	Case of 
		: (($byte & 0x00F8)=0x00F0)  `  11110xxx = 4 byte following
			If (Length($in)>=$i+3)
				  ` use 3 bit, then 3 times 6 bit
				$utf16:=$byte & 0x0007
				$byte:=Ascii($in[[$i+1]])
				$utf16:=($utf16 << 6)+($byte & $sixbit)
				$byte:=Ascii($in[[$i+2]])
				$utf16:=($utf16 << 6)+($byte & $sixbit)
				$byte:=Ascii($in[[$i+3]])
				$utf16:=($utf16 << 6)+($byte & $sixbit)
				$i:=$i+3
			End if 
			
		: (($byte & 0x00F0)=0x00E0)  `  1110xxxx = 3 byte following
			If (Length($in)>=($i+2))
				  ` use 4 bit, then 2 times 6 bit
				$utf16:=$byte & 0x000F
				$byte:=Ascii($in[[$i+1]])
				$utf16:=($utf16 << 6)+($byte & $sixbit)
				$byte:=Ascii($in[[$i+2]])
				$utf16:=($utf16 << 6)+($byte & $sixbit)
				$i:=$i+2
			End if 
			
		: (($byte & 0x00E0)=0x00C0)  `  110xxxxx = 1 byte following
			If (Length($in)>=($i+1))
				  ` use 5 bit, then 6 bit
				$utf16:=$byte & 0x001F
				$byte:=Ascii($in[[$i+1]])
				$utf16:=($utf16 << 6)+($byte & $sixbit)
				$i:=$i+1
			End if 
			
		: (Not($byte ?? 8))  ` 0xxx xxxx  = 7 Bit char
			$utf16:=$byte
			
		Else 
			TRACE
			$utf16:=0  ` should never happen
	End case 
	$out:=$out+Char($utf16\256)+Char($utf16%256)
End for 
$0:=$out

Anhang laden (140605 Bytes).

Hinweis: der Anhang wurde von 4D nicht getestet noch auf Funktion oder Viren überprüft.
Wir empfehlen als Anhang ausschließlich das .zip Format zu verwenden, das Sie vor dem Öffnen selbst mit einem aktuellen Viren-Scanner überprüfen sollten. Wir raten vom Öffnen von anderen Formaten ab.

Code ändern (nur für Autor - Kennwort geschützt)

Zurück

When the solution matters

International Sites

4D Produkte

Referenzen

Corporate

Support

Vertrieb

Menü

4D Code Library