SNAP Library, User Reference  2012-10-02 12:56:23
SNAP, a general purpose network analysis and graph mining library
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines
unicode.h File Reference

Go to the source code of this file.

Classes

class  TUnicodeException
class  TUniCodec
class  TUniCaseFolding
class  TCodecBase
class  TCodecWrapper< TCodecImpl_ >
class  TVecElt< TVector_ >
class  TVecElt< TVec< TDat > >
class  TVecElt< TChA >
class  TEncoding_ISO8859_1
class  TEncoding_ISO8859_2
class  TEncoding_ISO8859_3
class  TEncoding_ISO8859_4
class  TEncoding_YuAscii
class  TEncoding_CP437
class  TEncoding_CP852
class  TEncoding_CP1250
class  T8BitCodec< TEncoding_ >
class  TUniChInfo
class  TUniTrie< TItem_ >
class  TUniTrie< TItem_ >::TNode
class  TUniChDb
class  TUniChDb::TUcdFileReader
class  TUniChDb::TSubcatHelper
class  TUnicode

Defines

#define DefineByte(b7, b6, b5, b4, b3, b2, b1, b0)   _ ## b7 ## b6 ## b5 ## b4 ## _ ## b3 ## b2 ## b1 ## b0 = (b7 << 7) | (b6 << 6) | (b5 << 5) | (b4 << 4) | (b3 << 3) | (b2 << 2) | (b1 << 1) | b0
#define DefineUniCat(cat, c)   uc ## cat = (int(uchar(c)) & 0xff)
#define DefineUniSubCat(cat, subCat, c)   uc ## cat ## subCat = ((uc ## cat) << 8) | (int(uchar(c)) & 0xff)
#define ___UniFwd1(name)   bool name(const int cp) const { int i = h.GetKeyId(cp); if (i < 0) return false; else return h[i].name(); }
#define ___UniFwd2(name1, name2)   ___UniFwd1(name1) ___UniFwd1(name2)
#define ___UniFwd3(name1, name2, name3)   ___UniFwd2(name1, name2) ___UniFwd1(name3)
#define ___UniFwd4(name1, name2, name3, name4)   ___UniFwd3(name1, name2, name3) ___UniFwd1(name4)
#define ___UniFwd5(name1, name2, name3, name4, name5)   ___UniFwd4(name1, name2, name3, name4) ___UniFwd1(name5)
#define DECLARE_FORWARDED_PROPERTY_METHODS
#define ___UniFwd1(name)   bool name(const int cp) const { return ucd.name(cp); }
#define ___OutRepl   if (isDestLe) { dest.Add(replacementChar & 0xff); dest.Add((replacementChar >> 8) & 0xff); } else { dest.Add((replacementChar >> 8) & 0xff); dest.Add(replacementChar & 0xff); }
#define TestCurNext(curFlag, nextFlag)   if ((wbfCur & curFlag) == curFlag && (wbfNext & nextFlag) == nextFlag) continue
#define TestCurNext2(curFlag, nextFlag, next2Flag)   if ((wbfCur & curFlag) == curFlag && (wbfNext & nextFlag) == nextFlag && (wbfNext2 & next2Flag) == next2Flag) continue
#define TestPrevCurNext(prevFlag, curFlag, nextFlag)   if ((wbfPrev & prevFlag) == prevFlag && (wbfCur & curFlag) == curFlag && (wbfNext & nextFlag) == nextFlag) continue
#define TestCur(curFlag)   ((sbfCur & ucfSb##curFlag) == ucfSb##curFlag)
#define Trans(curFlag, newState)   if (TestCur(curFlag)) { backState = st##newState; break; }
#define IsPeekAheadSkippable(sbf)   ((sbf & (ucfSbOLetter | ucfSbUpper | ucfSbLower | ucfSbSep | ucfSbSTerm | ucfSbATerm)) == 0)
#define TestCurNext(curFlag, nextFlag)   if ((sbfCur & curFlag) == curFlag && (sbfNext & nextFlag) == nextFlag) continue
#define TestCurNext2(curFlag, nextFlag, next2Flag)   if ((sbfCur & curFlag) == curFlag && (sbfNext & nextFlag) == nextFlag && (sbfNext2 & next2Flag) == next2Flag) continue
#define TestPrevCurNext(prevFlag, curFlag, nextFlag)   if ((sbfPrev & prevFlag) == prevFlag && (sbfCur & curFlag) == curFlag && (sbfNext & nextFlag) == nextFlag) continue

Typedefs

typedef int TUniVecIdx
typedef enum TUnicodeErrorHandling_ TUnicodeErrorHandling
typedef enum TUniByteOrder_ TUniByteOrder
typedef enum TUtf16BomHandling_ TUtf16BomHandling
typedef THash< TInt, TIntVTIntIntVH
typedef TPt< TCodecBasePCodecBase
typedef TVec< PCodecBaseTCodecBaseV
typedef T8BitCodec
< TEncoding_ISO8859_1
TCodec_ISO8859_1
typedef T8BitCodec
< TEncoding_ISO8859_2
TCodec_ISO8859_2
typedef T8BitCodec
< TEncoding_ISO8859_3
TCodec_ISO8859_3
typedef T8BitCodec
< TEncoding_ISO8859_4
TCodec_ISO8859_4
typedef T8BitCodec
< TEncoding_CP852
TCodec_CP852
typedef T8BitCodec
< TEncoding_CP437
TCodec_CP437
typedef T8BitCodec
< TEncoding_CP1250
TCodec_CP1250
typedef T8BitCodec
< TEncoding_YuAscii
TCodec_YuAscii
typedef enum TUniChCategory_ TUniChCategory
typedef enum TUniChSubCategory_ TUniChSubCategory
typedef enum TUniChFlags_ TUniChFlags
typedef enum TUniChProperties_ TUniChProperties
typedef enum TUniChPropertiesX_ TUniChPropertiesX

Enumerations

enum  TUnicodeErrorHandling_ { uehIgnore = 0, uehThrow = 1, uehReplace = 2, uehAbort = 3 }
enum  TUniByteOrder_ { boMachineEndian = 0, boLittleEndian = 1, boBigEndian = 2 }
enum  TUtf16BomHandling_ { bomAllowed = 0, bomRequired = 1, bomIgnored = 2 }
enum  TUniChCategory_ {
  DefineUniCat = (Letter, 'L'), DefineUniCat = (Letter, 'L'), DefineUniCat = (Letter, 'L'), DefineUniCat = (Letter, 'L'),
  DefineUniCat = (Letter, 'L'), DefineUniCat = (Letter, 'L'), DefineUniCat = (Letter, 'L'), DefineUniCat = (Letter, 'L')
}
enum  TUniChSubCategory_ {
  DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'),
  DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'),
  DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'),
  DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'),
  DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'),
  DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'),
  DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'),
  DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u'), DefineUniSubCat = (Letter, Uppercase, 'u')
}
enum  TUniChFlags_ {
  ucfCompatibilityDecomposition = 1, ucfCompositionExclusion = 1 << 1, ucfWbFormat = 1 << 2, ucfWbKatakana = 1 << 3,
  ucfWbALetter = 1 << 4, ucfWbMidLetter = 1 << 5, ucfWbMidNum = 1 << 6, ucfWbNumeric = 1 << 7,
  ucfWbExtendNumLet = 1 << 8, ucfSbSep = 1 << 9, ucfSbFormat = 1 << 10, ucfSbSp = 1 << 11,
  ucfSbLower = 1 << 12, ucfSbUpper = 1 << 13, ucfSbOLetter = 1 << 14, ucfSbNumeric = 1 << 15,
  ucfSbATerm = 1 << 16, ucfSbSTerm = 1 << 17, ucfSbClose = 1 << 18, ucfSbMask = ucfSbSep | ucfSbFormat | ucfSbSp | ucfSbLower | ucfSbUpper | ucfSbOLetter | ucfSbNumeric | ucfSbATerm | ucfSbSTerm | ucfSbClose,
  ucfWbMask = ucfWbFormat | ucfWbKatakana | ucfWbALetter | ucfWbMidLetter | ucfWbMidNum | ucfWbNumeric | ucfWbExtendNumLet | ucfSbSep, ucfDcpAlphabetic = 1 << 19, ucfDcpDefaultIgnorableCodePoint = 1 << 20, ucfDcpLowercase = 1 << 21,
  ucfDcpGraphemeBase = 1 << 22, ucfDcpGraphemeExtend = 1 << 23, ucfDcpIdStart = 1 << 24, ucfDcpIdContinue = 1 << 25,
  ucfDcpMath = 1 << 26, ucfDcpUppercase = 1 << 27, ucfDcpXidStart = 1 << 28, ucfDcpXidContinue = 1 << 29,
  ucfDcpMask
}
enum  TUniChProperties_ {
  ucfPrAsciiHexDigit = 1, ucfPrBidiControl = 2, ucfPrDash = 4, ucfPrDeprecated = 8,
  ucfPrDiacritic = 0x10, ucfPrExtender = 0x20, ucfPrGraphemeLink = 0x40, ucfPrHexDigit = 0x80,
  ucfPrHyphen = 0x100, ucfPrIdeographic = 0x200, ucfPrJoinControl = 0x400, ucfPrLogicalOrderException = 0x800,
  ucfPrNoncharacterCodePoint = 0x1000, ucfPrPatternSyntax = 0x2000, ucfPrPatternWhiteSpace = 0x4000, ucfPrQuotationMark = 0x8000,
  ucfPrSoftDotted = 0x10000, ucfPrSTerm = 0x20000, ucfPrTerminalPunctuation = 0x40000, ucfPrVariationSelector = 0x80000,
  ucfPrWhiteSpace = 0x100000
}
enum  TUniChPropertiesX_ {
  ucfPxOtherAlphabetic = 1, ucfPxOtherDefaultIgnorableCodePoint = 2, ucfPxOtherGraphemeExtend = 4, ucfPxOtherIdContinue = 8,
  ucfPxOtherIdStart = 0x10, ucfPxOtherLowercase = 0x20, ucfPxOtherMath = 0x40, ucfPxOtherUppercase = 0x80,
  ucfPxIdsBinaryOperator = 0x100, ucfPxIdsTrinaryOperator = 0x200, ucfPxRadical = 0x400, ucfPxUnifiedIdeograph = 0x800
}

Functions

bool AlwaysFalse ()
bool AlwaysTrue ()

Define Documentation

#define ___OutRepl   if (isDestLe) { dest.Add(replacementChar & 0xff); dest.Add((replacementChar >> 8) & 0xff); } else { dest.Add((replacementChar >> 8) & 0xff); dest.Add(replacementChar & 0xff); }
#define ___UniFwd1 (   name)    bool name(const int cp) const { int i = h.GetKeyId(cp); if (i < 0) return false; else return h[i].name(); }
#define ___UniFwd1 (   name)    bool name(const int cp) const { return ucd.name(cp); }
#define ___UniFwd2 (   name1,
  name2 
)    ___UniFwd1(name1) ___UniFwd1(name2)
#define ___UniFwd3 (   name1,
  name2,
  name3 
)    ___UniFwd2(name1, name2) ___UniFwd1(name3)
#define ___UniFwd4 (   name1,
  name2,
  name3,
  name4 
)    ___UniFwd3(name1, name2, name3) ___UniFwd1(name4)
#define ___UniFwd5 (   name1,
  name2,
  name3,
  name4,
  name5 
)    ___UniFwd4(name1, name2, name3, name4) ___UniFwd1(name5)
Value:
___UniFwd5(IsAsciiHexDigit, IsBidiControl, IsDash, IsDeprecated, IsDiacritic) \
        ___UniFwd5(IsExtender, IsGraphemeLink, IsHexDigit, IsHyphen, IsIdeographic)  \
        ___UniFwd5(IsJoinControl, IsLogicalOrderException, IsNoncharacter, IsQuotationMark, IsSoftDotted)  \
        ___UniFwd4(IsSTerminal, IsTerminalPunctuation, IsVariationSelector, IsWhiteSpace)  \
        ___UniFwd5(IsAlphabetic, IsUppercase, IsLowercase, IsMath, IsDefaultIgnorable)  \
        ___UniFwd4(IsGraphemeBase, IsGraphemeExtend, IsIdStart, IsIdContinue)  \
        ___UniFwd2(IsXidStart, IsXidContinue)  \
        ___UniFwd3(IsCompositionExclusion, IsCompatibilityDecomposition, IsSbSep)  \
        ___UniFwd1(IsGbExtend)  \
        ___UniFwd2(IsCased, IsCurrency)
#define DefineByte (   b7,
  b6,
  b5,
  b4,
  b3,
  b2,
  b1,
  b0 
)    _ ## b7 ## b6 ## b5 ## b4 ## _ ## b3 ## b2 ## b1 ## b0 = (b7 << 7) | (b6 << 6) | (b5 << 5) | (b4 << 4) | (b3 << 3) | (b2 << 2) | (b1 << 1) | b0
#define DefineUniCat (   cat,
 
)    uc ## cat = (int(uchar(c)) & 0xff)
#define DefineUniSubCat (   cat,
  subCat,
 
)    uc ## cat ## subCat = ((uc ## cat) << 8) | (int(uchar(c)) & 0xff)
#define IsPeekAheadSkippable (   sbf)    ((sbf & (ucfSbOLetter | ucfSbUpper | ucfSbLower | ucfSbSep | ucfSbSTerm | ucfSbATerm)) == 0)
#define TestCur (   curFlag)    ((sbfCur & ucfSb##curFlag) == ucfSb##curFlag)
#define TestCurNext (   curFlag,
  nextFlag 
)    if ((wbfCur & curFlag) == curFlag && (wbfNext & nextFlag) == nextFlag) continue
#define TestCurNext (   curFlag,
  nextFlag 
)    if ((sbfCur & curFlag) == curFlag && (sbfNext & nextFlag) == nextFlag) continue
#define TestCurNext2 (   curFlag,
  nextFlag,
  next2Flag 
)    if ((wbfCur & curFlag) == curFlag && (wbfNext & nextFlag) == nextFlag && (wbfNext2 & next2Flag) == next2Flag) continue
#define TestCurNext2 (   curFlag,
  nextFlag,
  next2Flag 
)    if ((sbfCur & curFlag) == curFlag && (sbfNext & nextFlag) == nextFlag && (sbfNext2 & next2Flag) == next2Flag) continue
#define TestPrevCurNext (   prevFlag,
  curFlag,
  nextFlag 
)    if ((wbfPrev & prevFlag) == prevFlag && (wbfCur & curFlag) == curFlag && (wbfNext & nextFlag) == nextFlag) continue
#define TestPrevCurNext (   prevFlag,
  curFlag,
  nextFlag 
)    if ((sbfPrev & prevFlag) == prevFlag && (sbfCur & curFlag) == curFlag && (sbfNext & nextFlag) == nextFlag) continue
#define Trans (   curFlag,
  newState 
)    if (TestCur(curFlag)) { backState = st##newState; break; }

Typedef Documentation

typedef enum TUniChFlags_ TUniChFlags
typedef int TUniVecIdx

Enumeration Type Documentation

Enumerator:
boMachineEndian 
boLittleEndian 
boBigEndian 
Enumerator:
DefineUniCat 
DefineUniCat 
DefineUniCat 
DefineUniCat 
DefineUniCat 
DefineUniCat 
DefineUniCat 
DefineUniCat 
Enumerator:
ucfCompatibilityDecomposition 
ucfCompositionExclusion 
ucfWbFormat 
ucfWbKatakana 
ucfWbALetter 
ucfWbMidLetter 
ucfWbMidNum 
ucfWbNumeric 
ucfWbExtendNumLet 
ucfSbSep 
ucfSbFormat 
ucfSbSp 
ucfSbLower 
ucfSbUpper 
ucfSbOLetter 
ucfSbNumeric 
ucfSbATerm 
ucfSbSTerm 
ucfSbClose 
ucfSbMask 
ucfWbMask 
ucfDcpAlphabetic 
ucfDcpDefaultIgnorableCodePoint 
ucfDcpLowercase 
ucfDcpGraphemeBase 
ucfDcpGraphemeExtend 
ucfDcpIdStart 
ucfDcpIdContinue 
ucfDcpMath 
ucfDcpUppercase 
ucfDcpXidStart 
ucfDcpXidContinue 
ucfDcpMask 
Enumerator:
ucfPrAsciiHexDigit 
ucfPrBidiControl 
ucfPrDash 
ucfPrDeprecated 
ucfPrDiacritic 
ucfPrExtender 
ucfPrGraphemeLink 
ucfPrHexDigit 
ucfPrHyphen 
ucfPrIdeographic 
ucfPrJoinControl 
ucfPrLogicalOrderException 
ucfPrNoncharacterCodePoint 
ucfPrPatternSyntax 
ucfPrPatternWhiteSpace 
ucfPrQuotationMark 
ucfPrSoftDotted 
ucfPrSTerm 
ucfPrTerminalPunctuation 
ucfPrVariationSelector 
ucfPrWhiteSpace 
Enumerator:
ucfPxOtherAlphabetic 
ucfPxOtherDefaultIgnorableCodePoint 
ucfPxOtherGraphemeExtend 
ucfPxOtherIdContinue 
ucfPxOtherIdStart 
ucfPxOtherLowercase 
ucfPxOtherMath 
ucfPxOtherUppercase 
ucfPxIdsBinaryOperator 
ucfPxIdsTrinaryOperator 
ucfPxRadical 
ucfPxUnifiedIdeograph 
Enumerator:
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
DefineUniSubCat 
Enumerator:
uehIgnore 
uehThrow 
uehReplace 
uehAbort 
Enumerator:
bomAllowed 
bomRequired 
bomIgnored 

Function Documentation

bool AlwaysFalse ( ) [inline]
bool AlwaysTrue ( ) [inline]