home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
Oh!X 2001 Spring
/
Oh!X 2001 Spring Special CD-ROM (Japan).7z
/
Oh!X 2001 Spring Special CD-ROM (Japan) (Track 1).bin
/
FBENC
/
TEC-FB^3.sea
/
TEC-FB^3
/
TextCommon.Incl
< prev
next >
Wrap
Text File
|
2000-03-24
|
30KB
|
627 lines
/*
File: TextCommon.h
Contains: TextEncoding-related types and constants, and prototypes for related functions
Version: Mac OS 8.7
DRI: Peter Edberg
Copyright: ゥ 1995-1999 by Apple Computer, Inc., all rights reserved.
Warning: *** APPLE INTERNAL USE ONLY ***
This file may contain unreleased API's
BuildInfo: Built by: BuildGod
On: 09/17/99 11:19 AM
With Interfacer: 3.0d13 (MPW PowerPC)
From: TextCommon.i
Revision: 69
Dated: 6/3/99
Last change by: PKE
Last comment: [2341483] Add missing exportset=CarbonLib_10 for Sonata
Bugs: Report bugs to Radar component "System Interfaces", "Latest"
List the version information (from above) in the Problem Description.
*/
/*
#ifndef __TEXTCOMMON_
#define TEXTCOMMON
#ifndef MACTYPES
#include <MacTypes.h>
#endif
#if PRAGMAONCE
#pragma once
#endif
#ifdef cplusplus
extern "C" {
#endif
#if PRAGMAIMPORT
#pragma import on
#endif
#if PRAGMASTRUCTALIGN
#pragma options align=mac68k
#elif PRAGMASTRUCTPACKPUSH
#pragma pack(push, 2)
#elif PRAGMASTRUCTPACK
#pragma pack(2)
#endif
*/
/* TextEncodingBase type & values */
/* (values 0-32 correspond to the Script Codes defined in Inside Macintosh: Text pages 6-52 and 6-53 */
#DEFINE TextEncodingBase AS UInt32
BEGIN enum
/* Mac OS encodings*/
_kTextEncodingMacRoman = 0
_kTextEncodingMacJapanese = 1
_kTextEncodingMacChineseTrad = 2
_kTextEncodingMacKorean = 3
_kTextEncodingMacArabic = 4
_kTextEncodingMacHebrew = 5
_kTextEncodingMacGreek = 6
_kTextEncodingMacCyrillic = 7
_kTextEncodingMacDevanagari = 9
_kTextEncodingMacGurmukhi = 10
_kTextEncodingMacGujarati = 11
_kTextEncodingMacOriya = 12
_kTextEncodingMacBengali = 13
_kTextEncodingMacTamil = 14
_kTextEncodingMacTelugu = 15
_kTextEncodingMacKannada = 16
_kTextEncodingMacMalayalam = 17
_kTextEncodingMacSinhalese = 18
_kTextEncodingMacBurmese = 19
_kTextEncodingMacKhmer = 20
_kTextEncodingMacThai = 21
_kTextEncodingMacLaotian = 22
_kTextEncodingMacGeorgian = 23
_kTextEncodingMacArmenian = 24
_kTextEncodingMacChineseSimp = 25
_kTextEncodingMacTibetan = 26
_kTextEncodingMacMongolian = 27
_kTextEncodingMacEthiopic = 28
_kTextEncodingMacCentralEurRoman = 29
_kTextEncodingMacVietnamese = 30
_kTextEncodingMacExtArabic = 31 /* The following use script code 0, smRoman*/
_kTextEncodingMacSymbol = 33
_kTextEncodingMacDingbats = 34
_kTextEncodingMacTurkish = 35
_kTextEncodingMacCroatian = 36
_kTextEncodingMacIcelandic = 37
_kTextEncodingMacRomanian = 38
_kTextEncodingMacCeltic = 39
_kTextEncodingMacGaelic = 40 /* Beginning in Mac OS 8.5, the following meta-value is used to indicate Unicode in some parts*/
/* of the Mac OS which previously only expected a Mac OS script code. In some of these places,*/
/* only 7 bits are available to indicate encoding (script code), so kTextEncodingUnicodeDefault*/
/* cannot be used. For example, kTextEncodingMacUnicode can be used to indicate Unicode in the*/
/* 7-bit script code field of a Unicode input method's ComponentDescription.componentFlags field;*/
/* it can also be used to indicate Unicode in the 16-bit script code field of an AppleEvent's*/
/* typeIntlWritingCode text tag.*/
_kTextEncodingMacUnicode = 0x7E /* Meta-value, Unicode as a Mac encoding*/
/* The following use script code 4, smArabic*/
_kTextEncodingMacFarsi = 0x8C /* Like MacArabic but uses Farsi digits*/
/* The following use script code 7, smCyrillic*/
_kTextEncodingMacUkrainian = 0x98 /* Meta-value in TEC 1.5 & later; maps to kTextEncodingMacCyrillic variant */
/* The following use script code 28, smEthiopic*/
_kTextEncodingMacInuit = 0xEC /* The following use script code 32, smUnimplemented*/
_kTextEncodingMacVT100 = 0xFC /* VT100/102 font from Comm Toolbox: Latin-1 repertoire + box drawing etc*/
/* Special Mac OS encodings*/
_kTextEncodingMacHFS = 0xFF /* Meta-value, should never appear in a table.*/
/* Unicode & ISO UCS encodings begin at 0x100*/
_kTextEncodingUnicodeDefault = 0x0100 /* Meta-value, should never appear in a table.*/
_kTextEncodingUnicodeV11 = 0x0101
_kTextEncodingISO106461993 = 0x0101 /* Code points identical to Unicode 1.1*/
_kTextEncodingUnicodeV20 = 0x0103 /* New location for Korean Hangul*/
_kTextEncodingUnicodeV21 = 0x0103 /* We treat both Unicode 2.0 and Unicode 2.1 as 2.1*/
/* ISO 8-bit and 7-bit encodings begin at 0x200*/
_kTextEncodingISOLatin1 = 0x0201 /* ISO 8859-1*/
_kTextEncodingISOLatin2 = 0x0202 /* ISO 8859-2*/
_kTextEncodingISOLatin3 = 0x0203 /* ISO 8859-3*/
_kTextEncodingISOLatin4 = 0x0204 /* ISO 8859-4*/
_kTextEncodingISOLatinCyrillic = 0x0205 /* ISO 8859-5*/
_kTextEncodingISOLatinArabic = 0x0206 /* ISO 8859-6, = ASMO 708, =DOS CP 708*/
_kTextEncodingISOLatinGreek = 0x0207 /* ISO 8859-7*/
_kTextEncodingISOLatinHebrew = 0x0208 /* ISO 8859-8*/
_kTextEncodingISOLatin5 = 0x0209 /* ISO 8859-9*/
_kTextEncodingISOLatin6 = 0x020A /* ISO 8859-10 */
_kTextEncodingISOLatin7 = 0x020D /* ISO 8859-13, Baltic Rim */
_kTextEncodingISOLatin8 = 0x020E /* ISO 8859-14, Celtic */
_kTextEncodingISOLatin9 = 0x020F /* ISO 8859-15, 8859-1 changed for EURO & CP1252 letters */
/* MS-DOS & Windows encodings begin at 0x400*/
_kTextEncodingDOSLatinUS = 0x0400 /* code page 437*/
_kTextEncodingDOSGreek = 0x0405 /* code page 737 (formerly code page 437G)*/
_kTextEncodingDOSBalticRim = 0x0406 /* code page 775*/
_kTextEncodingDOSLatin1 = 0x0410 /* code page 850, "Multilingual"*/
_kTextEncodingDOSGreek1 = 0x0411 /* code page 851*/
_kTextEncodingDOSLatin2 = 0x0412 /* code page 852, Slavic*/
_kTextEncodingDOSCyrillic = 0x0413 /* code page 855, IBM Cyrillic*/
_kTextEncodingDOSTurkish = 0x0414 /* code page 857, IBM Turkish*/
_kTextEncodingDOSPortuguese = 0x0415 /* code page 860*/
_kTextEncodingDOSIcelandic = 0x0416 /* code page 861*/
_kTextEncodingDOSHebrew = 0x0417 /* code page 862*/
_kTextEncodingDOSCanadianFrench = 0x0418 /* code page 863*/
_kTextEncodingDOSArabic = 0x0419 /* code page 864*/
_kTextEncodingDOSNordic = 0x041A /* code page 865*/
_kTextEncodingDOSRussian = 0x041B /* code page 866*/
_kTextEncodingDOSGreek2 = 0x041C /* code page 869, IBM Modern Greek*/
_kTextEncodingDOSThai = 0x041D /* code page 874, also for Windows*/
_kTextEncodingDOSJapanese = 0x0420 /* code page 932, also for Windows; Shift-JIS with additions*/
_kTextEncodingDOSChineseSimplif = 0x0421 /* code page 936, also for Windows; was EUC-CN, now GBK (EUC-CN extended)*/
_kTextEncodingDOSKorean = 0x0422 /* code page 949, also for Windows; Unified Hangul Code (EUC-KR extended)*/
_kTextEncodingDOSChineseTrad = 0x0423 /* code page 950, also for Windows; Big-5*/
_kTextEncodingWindowsLatin1 = 0x0500 /* code page 1252*/
_kTextEncodingWindowsANSI = 0x0500 /* code page 1252 (alternate name)*/
_kTextEncodingWindowsLatin2 = 0x0501 /* code page 1250, Central Europe*/
_kTextEncodingWindowsCyrillic = 0x0502 /* code page 1251, Slavic Cyrillic*/
_kTextEncodingWindowsGreek = 0x0503 /* code page 1253*/
_kTextEncodingWindowsLatin5 = 0x0504 /* code page 1254, Turkish*/
_kTextEncodingWindowsHebrew = 0x0505 /* code page 1255*/
_kTextEncodingWindowsArabic = 0x0506 /* code page 1256*/
_kTextEncodingWindowsBalticRim = 0x0507 /* code page 1257*/
_kTextEncodingWindowsVietnamese = 0x0508 /* code page 1258*/
_kTextEncodingWindowsKoreanJohab = 0x0510 /* code page 1361, for Windows NT*/
/* Various national standards begin at 0x600*/
_kTextEncodingUSASCII = 0x0600
_kTextEncodingJISX020176 = 0x0620 /* JIS Roman and 1-byte katakana (halfwidth)*/
_kTextEncodingJISX020883 = 0x0621
_kTextEncodingJISX020890 = 0x0622
_kTextEncodingJISX021290 = 0x0623
_kTextEncodingJISC622678 = 0x0624
_kTextEncodingGB231280 = 0x0630
_kTextEncodingGBK95 = 0x0631 /* annex to GB 13000-93; for Windows 95; EUC-CN extended*/
_kTextEncodingKSC560187 = 0x0640 /* same as KSC 5601-92 without Johab annex*/
_kTextEncodingKSC560192Johab = 0x0641 /* KSC 5601-92 Johab annex*/
_kTextEncodingCNS1164392P1 = 0x0651 /* CNS 11643-1992 plane 1*/
_kTextEncodingCNS1164392P2 = 0x0652 /* CNS 11643-1992 plane 2*/
_kTextEncodingCNS1164392P3 = 0x0653 /* CNS 11643-1992 plane 3 (was plane 14 in 1986 version)*/
/* ISO 2022 collections begin at 0x800*/
_kTextEncodingISO2022JP = 0x0820
_kTextEncodingISO2022JP2 = 0x0821
_kTextEncodingISO2022CN = 0x0830
_kTextEncodingISO2022CNEXT = 0x0831
_kTextEncodingISO2022KR = 0x0840 /* EUC collections begin at 0x900*/
_kTextEncodingEUCJP = 0x0920 /* ISO 646, 1-byte katakana, JIS 208, JIS 212*/
_kTextEncodingEUCCN = 0x0930 /* ISO 646, GB 2312-80*/
_kTextEncodingEUCTW = 0x0931 /* ISO 646, CNS 11643-1992 Planes 1-16*/
_kTextEncodingEUCKR = 0x0940 /* ISO 646, KS C 5601-1987*/
/* Misc standards begin at 0xA00*/
_kTextEncodingShiftJIS = 0x0A01 /* plain Shift-JIS*/
_kTextEncodingKOI8R = 0x0A02 /* Russian internet standard*/
_kTextEncodingBig5 = 0x0A03 /* Big-5 (has variants)*/
_kTextEncodingMacRomanLatin1 = 0x0A04 /* Mac OS Roman permuted to align with ISO Latin-1*/
_kTextEncodingHZGB2312 = 0x0A05 /* HZ (RFC 1842, for Chinese mail & news)*/
/* Other platform encodings*/
_kTextEncodingNextStepLatin = 0x0B01 /* NextStep encoding*/
/* EBCDIC & IBM host encodings begin at 0xC00*/
_kTextEncodingEBCDICUS = 0x0C01 /* basic EBCDIC-US*/
_kTextEncodingEBCDICCP037 = 0x0C02 /* code page 037, extended EBCDIC (Latin-1 set) for US,Canada...*/
/* Special values*/
_kTextEncodingMultiRun = 0x0FFF /* Multi-encoding text with external run info*/
_kTextEncodingUnknown = 0xFFFF /* Unknown or unspecified */
/* The following are older names for backward compatibility*/
_kTextEncodingMacTradChinese = 2
_kTextEncodingMacRSymbol = 8
_kTextEncodingMacSimpChinese = 25
_kTextEncodingMacGeez = 28
_kTextEncodingMacEastEurRoman = 29
_kTextEncodingMacUninterp = 32
END ENUM
/* TextEncodingVariant type & values */
#DEFINE TextEncodingVariant AS UInt32
BEGIN enum
/* Default TextEncodingVariant, for any TextEncodingBase*/
_kTextEncodingDefaultVariant = 0 /* Variants of kTextEncodingMacRoman */
_kMacRomanDefaultVariant = 0 /* meta value, maps to 1 or 2 depending on System */
_kMacRomanCurrencySignVariant = 1 /* Mac OS version < 8.5, 0xDB is CURRENCY SIGN*/
_kMacRomanEuroSignVariant = 2 /* Mac OS version >= 8.5, 0xDB is EURO SIGN */
/* Variants of kTextEncodingMacIcelandic */
_kMacIcelandicStdDefaultVariant = 0 /* meta value, maps to 2 or 4 depending on System */
_kMacIcelandicTTDefaultVariant = 1 /* meta value, maps to 3 or 5 depending on System */
/* The following are for Mac OS version < 8.5, 0xDB is CURRENCY SIGN */
_kMacIcelandicStdCurrSignVariant = 2 /* 0xBB/0xBC are fem./masc. ordinal indicators*/
_kMacIcelandicTTCurrSignVariant = 3 /* 0xBB/0xBC are fi/fl ligatures*/
/* The following are for Mac OS version >= 8.5, 0xDB is EURO SIGN */
_kMacIcelandicStdEuroSignVariant = 4 /* 0xBB/0xBC are fem./masc. ordinal indicators*/
_kMacIcelandicTTEuroSignVariant = 5 /* 0xBB/0xBC are fi/fl ligatures*/
/* Variants of kTextEncodingMacCroatian */
_kMacCroatianDefaultVariant = 0 /* meta value, maps to 1 or 2 depending on System */
_kMacCroatianCurrencySignVariant = 1 /* Mac OS version < 8.5, 0xDB is CURRENCY SIGN */
_kMacCroatianEuroSignVariant = 2 /* Mac OS version >= 8.5, 0xDB is EURO SIGN */
/* Variants of kTextEncodingMacRomanian */
_kMacRomanianDefaultVariant = 0 /* meta value, maps to 1 or 2 depending on System */
_kMacRomanianCurrencySignVariant = 1 /* Mac OS version < 8.5, 0xDB is CURRENCY SIGN */
_kMacRomanianEuroSignVariant = 2 /* Mac OS version >= 8.5, 0xDB is EURO SIGN */
/* Variants of kTextEncodingMacJapanese*/
_kMacJapaneseStandardVariant = 0
_kMacJapaneseStdNoVerticalsVariant = 1
_kMacJapaneseBasicVariant = 2
_kMacJapanesePostScriptScrnVariant = 3
_kMacJapanesePostScriptPrintVariant = 4
_kMacJapaneseVertAtKuPlusTenVariant = 5 /* Variants of kTextEncodingMacArabic*/
_kMacArabicStandardVariant = 0 /* 0xC0 is 8-spoke asterisk, 0x2A & 0xAA are asterisk (e.g. Cairo)*/
_kMacArabicTrueTypeVariant = 1 /* 0xC0 is asterisk, 0x2A & 0xAA are multiply signs (e.g. Baghdad)*/
_kMacArabicThuluthVariant = 2 /* 0xC0 is Arabic five-point star, 0x2A & 0xAA are multiply signs*/
_kMacArabicAlBayanVariant = 3 /* 8-spoke asterisk, multiply sign, Koranic ligatures & parens*/
/* Variants of kTextEncodingMacFarsi*/
_kMacFarsiStandardVariant = 0 /* 0xC0 is 8-spoke asterisk, 0x2A & 0xAA are asterisk (e.g. Tehran)*/
_kMacFarsiTrueTypeVariant = 1 /* asterisk, multiply signs, Koranic ligatures, geometric shapes*/
/* Variants of kTextEncodingMacHebrew*/
_kMacHebrewStandardVariant = 0
_kMacHebrewFigureSpaceVariant = 1 /* Variants of kTextEncodingMacVT100 */
_kMacVT100DefaultVariant = 0 /* meta value, maps to 1 or 2 depending on System */
_kMacVT100CurrencySignVariant = 1 /* Mac OS version < 8.5, 0xDB is CURRENCY SIGN */
_kMacVT100EuroSignVariant = 2 /* Mac OS version >= 8.5, 0xDB is EURO SIGN */
/* Variants of Unicode & ISO 10646 encodings*/
_kUnicodeNoSubset = 0
_kUnicodeCanonicalDecompVariant = 2 /* canonical decomposition; excludes composed characters*/
/* Variants of Big-5 encoding*/
_kBig5BasicVariant = 0
_kBig5StandardVariant = 1 /* 0xC6A1-0xC7FC: kana, Cyrillic, enclosed numerics*/
_kBig5ETenVariant = 2 /* adds kana, Cyrillic, radicals, etc with hi bytes C6-C8,F9*/
/* Unicode variants not yet supported (and not fully defined)*/
_kUnicodeNoCompatibilityVariant = 1
_kUnicodeNoComposedVariant = 3
_kUnicodeNoCorporateVariant = 4 /* The following are older names for backward compatibility*/
_kMacRomanStandardVariant = 0
_kMacIcelandicStandardVariant = 0
_kMacIcelandicTrueTypeVariant = 1
_kJapaneseStandardVariant = 0
_kJapaneseStdNoVerticalsVariant = 1
_kJapaneseBasicVariant = 2
_kJapanesePostScriptScrnVariant = 3
_kJapanesePostScriptPrintVariant = 4
_kJapaneseVertAtKuPlusTenVariant = 5 /* kJapaneseStdNoOneByteKanaVariant = 6, // replaced by kJapaneseNoOneByteKanaOption*/
/* kJapaneseBasicNoOneByteKanaVariant = 7, // replaced by kJapaneseNoOneByteKanaOption */
_kHebrewStandardVariant = 0
_kHebrewFigureSpaceVariant = 1
_kUnicodeMaxDecomposedVariant = 2 /* replaced by kUnicodeCanonicalDecompVariant*/
/* The following Japanese variant options were never supported and are now deprecated.*/
/* In TEC 1.4 and later their functionality is replaced by the Unicode Converter options listed.*/
_kJapaneseNoOneByteKanaOption = 0x20 /* replaced by UnicodeConverter option kUnicodeNoHalfwidthCharsBit*/
_kJapaneseUseAsciiBackslashOption = 0x40 /* replaced by UnicodeConverter option kUnicodeForceASCIIRangeBit*/
END ENUM
BEGIN enum
/* Variants of kTextEncodingMacCyrillic (for TEC 1.5 and later) */
_kMacCyrillicDefaultVariant = 0 /* meta value, maps to 1, 2, or 3 depending on System*/
_kMacCyrillicCurrSignStdVariant = 1 /* Mac OS < 8.7 (RU,BG), 0xFF = CURRENCY SIGN, 0xA2/0xB6 = CENT / PARTIAL DIFF.*/
_kMacCyrillicCurrSignUkrVariant = 2 /* Mac OS < 8.7 (UA,LangKit), 0xFF = CURRENCY SIGN, 0xA2/0xB6 = GHE WITH UPTURN*/
_kMacCyrillicEuroSignVariant = 3 /* Mac OS >= 8.7, 0xFF is EURO SIGN, 0xA2/0xB6 = GHE WITH UPTURN*/
END ENUM
/* TextEncodingFormat type & values */
#DEFINE TextEncodingFormat AS UInt32
BEGIN ENUM /* Default TextEncodingFormat for any TextEncodingBase*/
_kTextEncodingDefaultFormat = 0 /* Formats for Unicode & ISO 10646*/
_kUnicode16BitFormat = 0
_kUnicodeUTF7Format = 1
_kUnicodeUTF8Format = 2
_kUnicode32BitFormat = 3
END ENUM
/* TextEncoding type */
#DEFINE TextEncoding AS UInt32
/* name part selector for GetTextEncodingName*/
#DEFINE TextEncodingNameSelector AS UInt32
BEGIN ENUM
_kTextEncodingFullName = 0
_kTextEncodingBaseName = 1
_kTextEncodingVariantName = 2
_kTextEncodingFormatName = 3
END ENUM
/* Types used in conversion */
BEGIN RECORD TextEncodingRun
DIM offset AS ByteOffset
DIM xtextEncoding AS TextEncoding
END RECORD
#DEFINE TextEncodingRunPtr AS POINTER TO TextEncodingRun
#DEFINE ConstTextEncodingRunPtr AS POINTER TO TextEncodingRunPtr
//typedef const TextEncodingRun * ConstTextEncodingRunPtr;
BEGIN RECORD ScriptCodeRun
DIM offset AS ByteOffset
DIM script AS ScriptCode
END RECORD
#DEFINE ScriptCodeRunPtr AS POINTER TO ScriptCodeRun
#DEFINE ConstScriptCodeRunPtr AS POINTER TO ScriptCodeRunPtr
//typedef const ScriptCodeRun * ConstScriptCodeRunPtr;
#DEFINE TextPtr AS POINTER TO UInt8
#DEFINE ConstTextPtr AS POINTER TO UInt8
//typedef const UInt8 * ConstTextPtr;
/* Basic types for Unicode characters and strings: */
#DEFINE UniCharArrayPtr AS POINTER TO UniChar
#DEFINE ConstUniCharArrayPtr AS POINTER TO UniCharArrayPtr
//typedef const UniChar * ConstUniCharArrayPtr;
/* enums for TextEncoding Conversion routines*/
BEGIN enum
_kTextScriptDontCare = -128
_kTextLanguageDontCare = -128
_kTextRegionDontCare = -128
END ENUM
/* struct for TECGetInfo*/
BEGIN RECORD TECInfo
DIM format AS UInt16/* format code for this struct*/
DIM tecVersion AS UInt16/* TEC version in BCD, e.g. 0x0121 for 1.2.1*/
DIM tecTextConverterFeatures AS UInt32/* bitmask indicating TEC features/fixes*/
DIM tecUnicodeConverterFeatures AS UInt32/* bitmask indicating UnicodeConverter features/fixes*/
DIM tecTextCommonFeatures AS UInt32/* bitmask indicating TextCommon features/fixes*/
DIM tecTextEncodingsFolderName AS Str31/* localized name of Text Encodings folder (pascal string)*/
DIM tecExtensionFileName AS Str31/* localized name of TEC extension (pascal string)*/
DIM tecLowestTEFileVersion AS UInt16/* Lowest version (BCD) of all files in Text Encodings folder*/
DIM tecHighestTEFileVersion AS UInt16/* Highest version (BCD) of all files in Text Encodings folder*/
END RECORD
#DEFINE TECInfoPtr AS POINTER TO TECInfo
#DEFINE TECInfoHandle AS POINTER TO TECInfoPtr
/* Value for TECInfo format code*/
BEGIN enum
_kTECInfoCurrentFormat = 2 /* any future formats will just add fields at the end*/
END ENUM
/*
Defined feature/fix bits for tecUnicodeConverterFeatures field
Bit: Meaning if set:
---- ---------------
kTECKeepInfoFixBit Unicode Converter no longer ignores other control flags if
kUnicodeKeepInfoBit is set. Bug fix in TEC Manager 1.2.1.
kTECFallbackTextLengthFixBit Unicode Converter honors the *srcConvLen and *destConvLen
returned by caller-supplied fallback handler for any status it
returns except for kTECUnmappableElementErr (previously it only
honored these values if noErr was returned). Bug fix in TEC
Manager 1.2.1.
kTECTextRunBitClearFixBit ConvertFromUnicodeToTextRun & ConvertFromUnicodeToScriptCodeRun
function correctly if the kUnicodeTextRunBit is set (previously
their determination of best target encoding was incorrect). Bug
fix in TEC Manager 1.3.
kTECTextToUnicodeScanFixBit ConvertFromTextToUnicode uses an improved scanner and maintains
some resulting state information, which it uses for mapping.
This has several effects:
- Improved mapping of 0x30-0x39 digits in Mac OS Arabic, fewer
direction overrides when mapping Mac OS Arabic & Hebrew, and
improved mapping of certain characters in Indic encodings.
- Malformed input produces kTextMalformedInputErr.
- ConvertFromTextToUnicode accepts and uses the control flags
kUnicodeKeepInfoMask and kUnicodeStringUnterminatedMask.
Bug fix and enhancement in TEC Manager 1.3.
kTECAddForceASCIIChangesBit Define new control flag bits kUnicodeForceASCIIRangeBit and
kUnicodeNoHalfwidthCharsBit for use with
ConvertFromTextToUnicode, ConvertFromUnicodeToText, etc.
Enhancement in TEC Manager 1.4.
kTECPreferredEncodingFixBit CreateUnicodeToTextRunInfo and related functions fix a problem
that occurred when a preferred encoding was specified that did
not match the System script; the preferred script was not
actually placed first in the ordered list of encodings to use.
Bug fix in TEC Manager 1.4.
kTECAddTextRunHeuristicsBit Define new control flag bit kUnicodeTextRunHeuristicsBit for
use with ConvertFromUnicodeToTextRun.
kTECAddFallbackInterruptBit Define new option kUnicodeFallbackInterruptSafeMask for use
with SetFallbackUnicodeToText. If a client fallback handler is
installed without specifying this bit, ConvertFromUnicodeToText
will HLock the tables it uses (in case the fallback handler
moves memory); otherwise, it won't.
*/
BEGIN enum
_kTECKeepInfoFixBit = 0
_kTECFallbackTextLengthFixBit = 1
_kTECTextRunBitClearFixBit = 2
_kTECTextToUnicodeScanFixBit = 3
_kTECAddForceASCIIChangesBit = 4
_kTECPreferredEncodingFixBit = 5
_kTECAddTextRunHeuristicsBit = 6
_kTECAddFallbackInterruptBit = 7
END ENUM
BEGIN enum
_kTECKeepInfoFixMask = 1 << _kTECKeepInfoFixBit
_kTECFallbackTextLengthFixMask = 1 << _kTECFallbackTextLengthFixBit
_kTECTextRunBitClearFixMask = 1 << _kTECTextRunBitClearFixBit
_kTECTextToUnicodeScanFixMask = 1 << _kTECTextToUnicodeScanFixBit
_kTECAddForceASCIIChangesMask = 1 << _kTECAddForceASCIIChangesBit
_kTECPreferredEncodingFixMask = 1 << _kTECPreferredEncodingFixBit
_kTECAddTextRunHeuristicsMask = 1 << _kTECAddTextRunHeuristicsBit
_kTECAddFallbackInterruptMask = 1 << _kTECAddFallbackInterruptBit
END ENUM
/*
-------------------------------------------------------------------------------------------------
CONSTANTS & DATA STRUCTURES for Unicode Properties
-------------------------------------------------------------------------------------------------
*/
#DEFINE UCCharPropertyType AS SInt32
BEGIN enum
_kUCCharPropTypeGenlCategory = 1 /* requests enumeration value*/
_kUCCharPropTypeCombiningClass = 2 /* requests numeric value 0..255*/
_kUCCharPropTypeBidiCategory = 3 /* requests enumeration value*/
END ENUM
#DEFINE UCCharPropertyValue AS UInt32
/* General Category enumeration values (requested by kUCCharPropTypeGenlCategory)*/
BEGIN enum
/* Normative categories:*/
_kUCGenlCatOtherNotAssigned = 0 /* Cn Other, Not Assigned*/
_kUCGenlCatOtherControl = 1 /* Cc Other, Control*/
_kUCGenlCatOtherFormat = 2 /* Cf Other, Format*/
_kUCGenlCatOtherSurrogate = 3 /* Cs Other, Surrogate*/
_kUCGenlCatOtherPrivateUse = 4 /* Co Other, Private Use*/
_kUCGenlCatMarkNonSpacing = 5 /* Mn Mark, Non-Spacing*/
_kUCGenlCatMarkSpacingCombining = 6 /* Mc Mark, Spacing Combining*/
_kUCGenlCatMarkEnclosing = 7 /* Me Mark, Enclosing*/
_kUCGenlCatNumberDecimalDigit = 8 /* Nd Number, Decimal Digit*/
_kUCGenlCatNumberLetter = 9 /* Nl Number, Letter*/
_kUCGenlCatNumberOther = 10 /* No Number, Other*/
_kUCGenlCatSeparatorSpace = 11 /* Zs Separator, Space*/
_kUCGenlCatSeparatorLine = 12 /* Zl Separator, Line*/
_kUCGenlCatSeparatorParagraph = 13 /* Zp Separator, Paragraph*/
/* Informative categories:*/
_kUCGenlCatLetterUppercase = 14 /* Lu Letter, Uppercase*/
_kUCGenlCatLetterLowercase = 15 /* Ll Letter, Lowercase*/
_kUCGenlCatLetterTitlecase = 16 /* Lt Letter, Titlecase*/
_kUCGenlCatLetterModifier = 17 /* Lm Letter, Modifier*/
_kUCGenlCatLetterOther = 18 /* Lo Letter, Other*/
_kUCGenlCatPunctConnector = 20 /* Pc Punctuation, Connector*/
_kUCGenlCatPunctDash = 21 /* Pd Punctuation, Dash*/
_kUCGenlCatPunctOpen = 22 /* Ps Punctuation, Open*/
_kUCGenlCatPunctClose = 23 /* Pe Punctuation, Close*/
_kUCGenlCatPunctInitialQuote = 24 /* Pi Punctuation, Initial quote*/
_kUCGenlCatPunctFinalQuote = 25 /* Pf Punctuation, Final quote*/
_kUCGenlCatPunctOther = 26 /* Po Punctuation, Other*/
_kUCGenlCatSymbolMath = 28 /* Sm Symbol, Math*/
_kUCGenlCatSymbolCurrency = 29 /* Sc Symbol, Currency*/
_kUCGenlCatSymbolModifier = 30 /* Sk Symbol, Modifier*/
_kUCGenlCatSymbolOther = 31 /* So Symbol, Other*/
END ENUM
/* Bidirectional Category enumeration values (requested by kUCCharPropTypeBidiCategory)*/
BEGIN enum
_kUCBidiCatNotApplicable = 0 /* for now use this for unassigned*/
/* Strong types:*/
_kUCBidiCatLeftRight = 1 /* L Left-Right*/
_kUCBidiCatRightLeft = 2 /* R Right-Left*/
/* Weak types:*/
_kUCBidiCatEuroNumber = 3 /* EN European Number*/
_kUCBidiCatEuroNumberSeparator = 4 /* ES European Number Separator*/
_kUCBidiCatEuroNumberTerminator = 5 /* ET European Number Terminator*/
_kUCBidiCatArabicNumber = 6 /* AN Arabic Number*/
_kUCBidiCatCommonNumberSeparator = 7 /* CS Common Number Separator*/
/* Separators:*/
_kUCBidiCatBlockSeparator = 8 /* B Block Separator*/
_kUCBidiCatSegmentSeparator = 9 /* S Segment Separator*/
/* Neutrals:*/
_kUCBidiCatWhitespace = 10 /* WS Whitespace*/
_kUCBidiCatOtherNeutral = 11 /* ON Other Neutrals (unassigned codes could use this)*/
END ENUM
/* Prototypes for TextEncoding functions*/
LIBRARY "TextCommon"
TOOLBOX FN CreateTextEncoding(TextEncodingBase encodingBase,TextEncodingVariant encodingVariant, TextEncodingFormat encodingFormat) = TextEncoding
//EXTERN_API( TextEncoding )
//CreateTextEncoding (TextEncodingBase encodingBase,
// TextEncodingVariant encodingVariant,
// TextEncodingFormat encodingFormat);
TOOLBOX FN GetTextEncodingBase(TextEncoding encoding)=TextEncodingBase
//EXTERN_API( TextEncodingBase )
//GetTextEncodingBase (TextEncoding encoding);
TOOLBOX FN GetTextEncodingVariant(TextEncoding encoding) = TextEncodingVariant
//EXTERN_API( TextEncodingVariant )
//GetTextEncodingVariant (TextEncoding encoding);
TOOLBOX FN GetTextEncodingFormat(TextEncoding encoding)=TextEncodingFormat
//EXTERN_API( TextEncodingFormat )
//GetTextEncodingFormat (TextEncoding encoding);
TOOLBOX FN ResolveDefaultTextEncoding(TextEncoding encoding)=TextEncoding
//EXTERN_API( TextEncoding )
//ResolveDefaultTextEncoding (TextEncoding encoding);
TOOLBOX FN GetTextEncodingName(TextEncoding iEncoding,TextEncodingNameSelector iNamePartSelector,RegionCode iPreferredRegion,TextEncoding iPreferredEncoding,ByteCount iOutputBufLen,ByteCount * oNameLength, ツ
RegionCode * oActualRegion,TextEncoding * oActualEncoding,TextPtr oEncodingName)=OSStatus
//EXTERN_API_C( OSStatus )
//GetTextEncodingName (TextEncoding iEncoding,
// TextEncodingNameSelector iNamePartSelector,
// RegionCode iPreferredRegion,
// TextEncoding iPreferredEncoding,
// ByteCount iOutputBufLen,
// ByteCount * oNameLength,
// RegionCode * oActualRegion, /* can be NULL */
// TextEncoding * oActualEncoding, /* can be NULL */
// TextPtr oEncodingName);
TOOLBOX FN TECGetInfo(TECInfoHandle * tecInfo)=OSStatus
//EXTERN_API( OSStatus )
//TECGetInfo (TECInfoHandle * tecInfo);
TOOLBOX FN UpgradeScriptInfoToTextEncoding(ScriptCode iTextScriptID,LangCode iTextLanguageID,RegionCode iRegionID,ConstStr255Param iTextFontname,TextEncoding * oEncoding)=OSStatus
//EXTERN_API( OSStatus )
//UpgradeScriptInfoToTextEncoding (ScriptCode iTextScriptID,
// LangCode iTextLanguageID,
// RegionCode iRegionID,
// ConstStr255Param iTextFontname,
// TextEncoding * oEncoding);
TOOLBOX FN RevertTextEncodingToScriptInfo(TextEncoding iEncoding,ScriptCode * oTextScriptID,LangCode * oTextLanguageID, Str255 oTextFontname)=OSStatus
//EXTERN_API( OSStatus )
//RevertTextEncodingToScriptInfo (TextEncoding iEncoding,
// ScriptCode * oTextScriptID,
// LangCode * oTextLanguageID, /* can be NULL */
// Str255 oTextFontname) /* can be NULL */;
TOOLBOX FN NearestMacTextEncodings(TextEncoding generalEncoding,TextEncoding * bestMacEncoding,TextEncoding * alternateMacEncoding)=OSStatus
//EXTERN_API( OSStatus )
//NearestMacTextEncodings (TextEncoding generalEncoding,
// TextEncoding * bestMacEncoding,
// TextEncoding * alternateMacEncoding);
TOOLBOX FN UCGetCharProperty(const UniChar * charPtr,UniCharCount textLength, UCCharPropertyType propType,UCCharPropertyValue * propValue)=OSStatus
//EXTERN_API_C( OSStatus )
//UCGetCharProperty (const UniChar * charPtr,
// UniCharCount textLength,
// UCCharPropertyType propType,
// UCCharPropertyValue * propValue);
LIBRARY
/*
#if PRAGMA_STRUCT_ALIGN
#pragma options align=reset
#elif PRAGMA_STRUCT_PACKPUSH
#pragma pack(pop)
#elif PRAGMA_STRUCT_PACK
#pragma pack()
#endif
#ifdef PRAGMA_IMPORT_OFF
#pragma import off
#elif PRAGMA_IMPORT
#pragma import reset
#endif
#ifdef __cplusplus
}
#endif
#endif //__TEXTCOMMON__
*/