DataMystic

Code: Select all

 //   Notes:
  //     o  Character property classes are \p or \P followed by a comma separated
  //        list of integers between 1 and 32.  These integers are references to
  //        the following character properties:
  //
  //         N	Character Property
  //         --------------------------
  //         1	_URE_NONSPACING
  //         2	_URE_COMBINING
  //         3	_URE_NUMDIGIT
  //         4	_URE_NUMOTHER
  //         5	_URE_SPACESEP
  //         6	_URE_LINESEP
  //         7	_URE_PARASEP
  //         8	_URE_CNTRL
  //         9	_URE_PRIVATE
  //         10	_URE_UPPER   (note: upper, lower and titel case classes need to have case
  //         11	_URE_LOWER          sensitive search be enabled to match correctly!)
  //         12	_URE_TITLE
  //         13	_URE_MODIFIER
  //         14	_URE_OTHERLETTER
  //         15	_URE_DASHPUNCT
  //         16	_URE_OPENPUNCT
  //         17	_URE_CLOSEPUNCT
  //         18	_URE_OTHERPUNCT
  //         19	_URE_MATHSYM
  //         20	_URE_CURRENCYSYM
  //         21	_URE_OTHERSYM
  //         22	_URE_LTR
  //         23	_URE_RTL
  //         24	_URE_EURONUM
  //         25	_URE_EURONUMSEP
  //         26	_URE_EURONUMTERM
  //         27	_URE_ARABNUM
  //         28	_URE_COMMONSEP
  //         29	_URE_BLOCKSEP
  //         30	_URE_SEGMENTSEP
  //         31	_URE_WHITESPACE
  //         32	_URE_OTHERNEUT

Code: Select all

  TCharacterCategory = (
     // normative categories
0-      ccLetterUppercase,
1 -     ccLetterLowercase,
2 -     ccLetterTitlecase,
3 -     ccMarkNonSpacing,
4 -     ccMarkSpacingCombining,
5 -     ccMarkEnclosing,
6 -     ccNumberDecimalDigit,
7 -     ccNumberLetter,
8 -     ccNumberOther,
9 -     ccSeparatorSpace,
10 -     ccSeparatorLine,
11 -     ccSeparatorParagraph,
12 -     ccOtherControl,
13 -     ccOtherFormat,
14 -     ccOtherSurrogate,
15 -     ccOtherPrivate,
16 -     ccOtherUnassigned, 
// informative categories
17 -     ccLetterModifier,
18 -     ccLetterOther,
19 -     ccPunctuationConnector,
20 -     ccPunctuationDash,
21 -     ccPunctuationOpen,
22 -     ccPunctuationClose,
23 -     ccPunctuationInitialQuote,
24 -     ccPunctuationFinalQuote,
25 -     ccPunctuationOther,
26 -     ccSymbolMath,
27 -     ccSymbolCurrency,
28 -     ccSymbolModifier,
29 -     ccSymbolOther,
// bidirectional categories
30 -     ccLeftToRight,
31 -     ccLeftToRightEmbedding,
32 -     ccLeftToRightOverride,
33 -     ccRightToLeft,
34 -     ccRightToLeftArabic,
35 -     ccRightToLeftEmbedding,
36 -     ccRightToLeftOverride,
37 -     ccPopDirectionalFormat,
38 -     ccEuropeanNumber,
39 -     ccEuropeanNumberSeparator,
40 -     ccEuropeanNumberTerminator,
41 -     ccArabicNumber,
42 -     ccCommonNumberSeparator,
43 -     ccBoundaryNeutral,
44 -     ccSegmentSeparator,      // this includes tab and vertical tab
45 -     ccWhiteSpace,
46 -     ccOtherNeutrals,
// self defined categories, they do not appear in the Unicode data file
47 -          ccComposed,              // can be decomposed
48 -     ccNonBreaking,
49 -     ccSymmetric,             // has left and right forms
50 -     ccHexDigit,
51 -     ccQuotationMark,
52 -     ccMirroring,
53 -     ccSpaceOther,
54 -     ccAssigned               // means there is a definition in the Unicode standard
  );