s/SvPV/SvPVbyte/g, as suggested by Gisle Aas.
[p5sagit/p5-mst-13.2.git] / lib / unicore / Properties
CommitLineData
99598c8c 1##
2## This file created by ./mktables
3## List of built-in \p{...}/\P{...} properties.
4##
5## '*' means name may be 'fuzzy'
6##
7
8 \p{ASCII} [[:ASCII:]]
9* \p{All} Alias for \p{Any} ([\x{0000}-\x{10FFFF}])
10 \p{Alnum} [[:Alnum:]]
11* \p{Alphabetic} [\p{L}\p{OtherAlphabetic}]
12 \p{Alpha} [[:Alpha:]]
13* \p{Any} [\x{0000}-\x{10FFFF}]
14* \p{Arabic} Script 'ARABIC'
15* \p{Armenian} Script 'ARMENIAN'
16* \p{AsciiHexDigit} Extended property 'ASCII_Hex_Digit'
17* \p{Assigned} All assigned code points
18* \p{Bengali} Script 'BENGALI'
19 \p{BidiAL} Bi-directional category 'AL'
20 \p{BidiAN} Bi-directional category 'AN'
21 \p{BidiBN} Bi-directional category 'BN'
22 \p{BidiB} Bi-directional category 'B'
23 \p{BidiCS} Bi-directional category 'CS'
24* \p{BidiControl} Extended property 'Bidi_Control'
25 \p{BidiEN} Bi-directional category 'EN'
26 \p{BidiES} Bi-directional category 'ES'
27 \p{BidiET} Bi-directional category 'ET'
28 \p{BidiLRE} Bi-directional category 'LRE'
29 \p{BidiLRO} Bi-directional category 'LRO'
30 \p{BidiL} Bi-directional category 'L'
31 \p{BidiNSM} Bi-directional category 'NSM'
32 \p{BidiON} Bi-directional category 'ON'
33 \p{BidiPDF} Bi-directional category 'PDF'
34 \p{BidiRLE} Bi-directional category 'RLE'
35 \p{BidiRLO} Bi-directional category 'RLO'
36 \p{BidiR} Bi-directional category 'R'
37 \p{BidiS} Bi-directional category 'S'
38 \p{BidiWS} Bi-directional category 'WS'
39 \p{Blank} [[:Blank:]]
40* \p{Bopomofo} Script 'BOPOMOFO'
41* \p{CanadianAboriginal} Script 'CANADIAN-ABORIGINAL'
42 \p{Canon} Decomposes to multiple characters
43 \p{Cc} General Category 'Cc'
44 \p{Cf} General Category 'Cf'
45* \p{Cherokee} Script 'CHEROKEE'
46* \p{ClosePunctuation} Alias for \p{Pe} (General Category 'Pe')
47 \p{Cntrl} [[:Cntrl:]]
48 \p{Cn} General Category 'Cn' [not functional in Perl]
49* \p{Common} Pseudo-Script of codepoints not in other Unicode scripts
50 \p{Compat} Compatible with a more-basic character
51* \p{ConnectorPunctuation} Alias for \p{Pc} (General Category 'Pc')
52* \p{Control} Alias for \p{Cc} (General Category 'Cc')
53 \p{Co} General Category 'Co'
54 \p{Cs} General Category 'Cs'
55* \p{CurrencySymbol} Alias for \p{Sc} (General Category 'Sc')
56* \p{Cyrillic} Script 'CYRILLIC'
57 \p{C} Major Category 'C'
58 \p{DCcircle} Compatible with 'circle'
59 \p{DCcompat} Compatible with 'compat'
60 \p{DCfinal} Compatible with 'final'
61 \p{DCfont} Compatible with 'font'
62 \p{DCfraction} Compatible with 'fraction'
63 \p{DCinitial} Compatible with 'initial'
64 \p{DCisolated} Compatible with 'isolated'
65 \p{DCmedial} Compatible with 'medial'
66 \p{DCnarrow} Compatible with 'narrow'
67 \p{DCnoBreak} Compatible with 'noBreak'
68 \p{DCsmall} Compatible with 'small'
69 \p{DCsquare} Compatible with 'square'
70 \p{DCsub} Compatible with 'sub'
71 \p{DCsuper} Compatible with 'super'
72 \p{DCvertical} Compatible with 'vertical'
73 \p{DCwide} Compatible with 'wide'
74* \p{DashPunctuation} Alias for \p{Pd} (General Category 'Pd')
75* \p{Dash} Extended property 'Dash'
76* \p{DecimalNumber} Alias for \p{Nd} (General Category 'Nd')
77* \p{Deseret} Script 'DESERET'
78* \p{Devanagari} Script 'DEVANAGARI'
79* \p{Diacritic} Extended property 'Diacritic'
80 \p{Digit} [[:Digit:]]
81* \p{EnclosingMark} Alias for \p{Me} (General Category 'Me')
82* \p{Ethiopic} Script 'ETHIOPIC'
83* \p{Extender} Extended property 'Extender'
84* \p{FinalPunctuation} Alias for \p{Pf} (General Category 'Pf')
85* \p{Format} Alias for \p{Cf} (General Category 'Cf')
86* \p{Georgian} Script 'GEORGIAN'
87* \p{Gothic} Script 'GOTHIC'
88 \p{Graph} [[:Graph:]]
89* \p{Greek} Script 'GREEK'
90* \p{Gujarati} Script 'GUJARATI'
91* \p{Gurmukhi} Script 'GURMUKHI'
92* \p{Hangul} Script 'HANGUL'
93* \p{Han} Script 'HAN'
94* \p{Hebrew} Script 'HEBREW'
95* \p{HexDigit} Extended property 'Hex_Digit'
96* \p{Hiragana} Script 'HIRAGANA'
97* \p{Hyphen} Extended property 'Hyphen'
98* \p{IdContinue} [\p{ID_Start}\p{Mn}\p{Mc}\p{Nd}\p{Pc}]
99* \p{IdStart} [\p{Ll}\p{Lu}\p{Lt}\p{Lm}\p{Lo}\p{Nl}]
100* \p{Ideographic} Extended property 'Ideographic'
101* \p{InAlphabeticPresentationForms} Block 'Alphabetic Presentation Forms'
102* \p{InArabicPresentationFormsA} Block 'Arabic Presentation Forms-A'
103* \p{InArabicPresentationFormsB} Block 'Arabic Presentation Forms-B'
104* \p{InArabic} Block 'Arabic'
105* \p{InArmenian} Block 'Armenian'
106* \p{InArrows} Block 'Arrows'
107* \p{InBasicLatin} Block 'Basic Latin'
108* \p{InBengali} Block 'Bengali'
109* \p{InBlockElements} Block 'Block Elements'
110* \p{InBopomofoExtended} Block 'Bopomofo Extended'
111* \p{InBopomofo} Block 'Bopomofo'
112* \p{InBoxDrawing} Block 'Box Drawing'
113* \p{InBraillePatterns} Block 'Braille Patterns'
114* \p{InByzantineMusicalSymbols} Block 'Byzantine Musical Symbols'
115* \p{InCherokee} Block 'Cherokee'
116* \p{InCjkCompatibilityForms} Block 'CJK Compatibility Forms'
117* \p{InCjkCompatibilityIdeographsSupplement} Block 'CJK Compatibility Ideographs Supplement'
118* \p{InCjkCompatibilityIdeographs} Block 'CJK Compatibility Ideographs'
119* \p{InCjkCompatibility} Block 'CJK Compatibility'
120* \p{InCjkRadicalsSupplement} Block 'CJK Radicals Supplement'
121* \p{InCjkSymbolsAndPunctuation} Block 'CJK Symbols and Punctuation'
122* \p{InCjkUnifiedIdeographsExtensionA} Block 'CJK Unified Ideographs Extension A'
123* \p{InCjkUnifiedIdeographsExtensionB} Block 'CJK Unified Ideographs Extension B'
124* \p{InCjkUnifiedIdeographs} Block 'CJK Unified Ideographs'
125* \p{InCombiningDiacriticalMarks} Block 'Combining Diacritical Marks'
126* \p{InCombiningHalfMarks} Block 'Combining Half Marks'
127* \p{InCombiningMarksForSymbols} Block 'Combining Marks for Symbols'
128* \p{InControlPictures} Block 'Control Pictures'
129* \p{InCurrencySymbols} Block 'Currency Symbols'
130* \p{InCyrillic} Block 'Cyrillic'
131* \p{InDeseret} Block 'Deseret'
132* \p{InDevanagari} Block 'Devanagari'
133* \p{InDingbats} Block 'Dingbats'
134* \p{InEnclosedAlphanumerics} Block 'Enclosed Alphanumerics'
135* \p{InEnclosedCjkLettersAndMonths} Block 'Enclosed CJK Letters and Months'
136* \p{InEthiopic} Block 'Ethiopic'
137* \p{InGeneralPunctuation} Block 'General Punctuation'
138* \p{InGeometricShapes} Block 'Geometric Shapes'
139* \p{InGeorgian} Block 'Georgian'
140* \p{InGothic} Block 'Gothic'
141* \p{InGreekExtended} Block 'Greek Extended'
142* \p{InGreek} Block 'Greek'
143* \p{InGujarati} Block 'Gujarati'
144* \p{InGurmukhi} Block 'Gurmukhi'
145* \p{InHalfwidthAndFullwidthForms} Block 'Halfwidth and Fullwidth Forms'
146* \p{InHangulCompatibilityJamo} Block 'Hangul Compatibility Jamo'
147* \p{InHangulJamo} Block 'Hangul Jamo'
148* \p{InHangulSyllables} Block 'Hangul Syllables'
149* \p{InHebrew} Block 'Hebrew'
150* \p{InHighPrivateUseSurrogates} Block 'High Private Use Surrogates'
151* \p{InHighSurrogates} Block 'High Surrogates'
152* \p{InHiragana} Block 'Hiragana'
153* \p{InIdeographicDescriptionCharacters} Block 'Ideographic Description Characters'
154* \p{InIpaExtensions} Block 'IPA Extensions'
155* \p{InKanbun} Block 'Kanbun'
156* \p{InKangxiRadicals} Block 'Kangxi Radicals'
157* \p{InKannada} Block 'Kannada'
158* \p{InKatakana} Block 'Katakana'
159* \p{InKhmer} Block 'Khmer'
160* \p{InLao} Block 'Lao'
161* \p{InLatin1Supplement} Block 'Latin-1 Supplement'
162* \p{InLatinExtendedAdditional} Block 'Latin Extended Additional'
163* \p{InLatinExtendedA} Block 'Latin Extended-A'
164* \p{InLatinExtendedB} Block 'Latin Extended-B'
165* \p{InLetterlikeSymbols} Block 'Letterlike Symbols'
166* \p{InLowSurrogates} Block 'Low Surrogates'
167* \p{InMalayalam} Block 'Malayalam'
168* \p{InMathematicalAlphanumericSymbols} Block 'Mathematical Alphanumeric Symbols'
169* \p{InMathematicalOperators} Block 'Mathematical Operators'
170* \p{InMiscellaneousSymbols} Block 'Miscellaneous Symbols'
171* \p{InMiscellaneousTechnical} Block 'Miscellaneous Technical'
172* \p{InMongolian} Block 'Mongolian'
173* \p{InMusicalSymbols} Block 'Musical Symbols'
174* \p{InMyanmar} Block 'Myanmar'
175* \p{InNumberForms} Block 'Number Forms'
176* \p{InOgham} Block 'Ogham'
177* \p{InOldItalic} Block 'Old Italic'
178* \p{InOpticalCharacterRecognition} Block 'Optical Character Recognition'
179* \p{InOriya} Block 'Oriya'
180* \p{InPrivateUse} Block 'Private Use'
181* \p{InRunic} Block 'Runic'
182* \p{InSinhala} Block 'Sinhala'
183* \p{InSmallFormVariants} Block 'Small Form Variants'
184* \p{InSpacingModifierLetters} Block 'Spacing Modifier Letters'
185* \p{InSpecials} Block 'Specials'
186* \p{InSuperscriptsAndSubscripts} Block 'Superscripts and Subscripts'
187* \p{InSyriac} Block 'Syriac'
188* \p{InTags} Block 'Tags'
189* \p{InTamil} Block 'Tamil'
190* \p{InTelugu} Block 'Telugu'
191* \p{InThaana} Block 'Thaana'
192* \p{InThai} Block 'Thai'
193* \p{InTibetan} Block 'Tibetan'
194* \p{InUnifiedCanadianAboriginalSyllabics} Block 'Unified Canadian Aboriginal Syllabics'
195* \p{InYiRadicals} Block 'Yi Radicals'
196* \p{InYiSyllables} Block 'Yi Syllables'
197* \p{Inherited} Script 'INHERITED'
198* \p{InitialPunctuation} Alias for \p{Pi} (General Category 'Pi')
199* \p{JoinControl} Extended property 'Join_Control'
200* \p{Kannada} Script 'KANNADA'
201* \p{Katakana} Script 'KATAKANA'
202* \p{Khmer} Script 'KHMER'
203 \p{L&} [\p{Ll}\p{Lu}\p{Lt}]
204* \p{Lao} Script 'LAO'
205* \p{Latin} Script 'LATIN'
206 \p{LbrkAI} Linebreak category 'AI'
207 \p{LbrkAL} Linebreak category 'AL'
208 \p{LbrkB2} Linebreak category 'B2'
209 \p{LbrkBA} Linebreak category 'BA'
210 \p{LbrkBB} Linebreak category 'BB'
211 \p{LbrkBK} Linebreak category 'BK'
212 \p{LbrkCB} Linebreak category 'CB'
213 \p{LbrkCL} Linebreak category 'CL'
214 \p{LbrkCM} Linebreak category 'CM'
215 \p{LbrkCR} Linebreak category 'CR'
216 \p{LbrkEX} Linebreak category 'EX'
217 \p{LbrkGL} Linebreak category 'GL'
218 \p{LbrkHY} Linebreak category 'HY'
219 \p{LbrkID} Linebreak category 'ID'
220 \p{LbrkIN} Linebreak category 'IN'
221 \p{LbrkIS} Linebreak category 'IS'
222 \p{LbrkLF} Linebreak category 'LF'
223 \p{LbrkNS} Linebreak category 'NS'
224 \p{LbrkNU} Linebreak category 'NU'
225 \p{LbrkOP} Linebreak category 'OP'
226 \p{LbrkPO} Linebreak category 'PO'
227 \p{LbrkPR} Linebreak category 'PR'
228 \p{LbrkQU} Linebreak category 'QU'
229 \p{LbrkSA} Linebreak category 'SA'
230 \p{LbrkSG} Linebreak category 'SG'
231 \p{LbrkSP} Linebreak category 'SP'
232 \p{LbrkSY} Linebreak category 'SY'
233 \p{LbrkXX} Linebreak category 'XX'
234 \p{LbrkZW} Linebreak category 'ZW'
235* \p{LetterNumber} Alias for \p{Nl} (General Category 'Nl')
236* \p{Letter} Alias for \p{L} (Major Category 'L')
237* \p{LineSeparator} Alias for \p{Zl} (General Category 'Zl')
238 \p{Ll} General Category 'Ll'
239 \p{Lm} General Category 'Lm'
240* \p{LowercaseLetter} Alias for \p{Ll} (General Category 'Ll')
241* \p{Lowercase} [\p{Ll}\p{OtherLowercase}]
242 \p{Lower} [[:Lower:]]
243 \p{Lo} General Category 'Lo'
244 \p{Lt} General Category 'Lt'
245 \p{Lu} General Category 'Lu'
246 \p{L} Major Category 'L'
247* \p{Malayalam} Script 'MALAYALAM'
248* \p{Mark} Alias for \p{M} (Major Category 'M')
249* \p{MathSymbol} Alias for \p{Sm} (General Category 'Sm')
250* \p{Math} [\p{Sm}\p{OtherMath}]
251 \p{Mc} General Category 'Mc'
252 \p{Me} General Category 'Me'
253 \p{Mirrored} Mirrored in bidirectional text
254 \p{Mn} General Category 'Mn'
255* \p{ModifierLetter} Alias for \p{Lm} (General Category 'Lm')
256* \p{ModifierSymbol} Alias for \p{Sk} (General Category 'Sk')
257* \p{Mongolian} Script 'MONGOLIAN'
258* \p{Myanmar} Script 'MYANMAR'
259 \p{M} Major Category 'M'
260 \p{Nd} General Category 'Nd'
261 \p{Nl} General Category 'Nl'
262* \p{NonSpacingMark} Alias for \p{Mn} (General Category 'Mn')
263* \p{NoncharacterCodePoint} Extended property 'Noncharacter_Code_Point'
264 \p{No} General Category 'No'
265* \p{Number} Alias for \p{N} (Major Category 'N')
266 \p{N} Major Category 'N'
267* \p{Ogham} Script 'OGHAM'
268* \p{OldItalic} Script 'OLD-ITALIC'
269* \p{OpenPunctuation} Alias for \p{Ps} (General Category 'Ps')
270* \p{Oriya} Script 'ORIYA'
271* \p{OtherAlphabetic} Extended property 'Other_Alphabetic'
272* \p{OtherLetter} Alias for \p{Lo} (General Category 'Lo')
273* \p{OtherLowercase} Extended property 'Other_Lowercase'
274* \p{OtherMath} Extended property 'Other_Math'
275* \p{OtherNumber} Alias for \p{No} (General Category 'No')
276* \p{OtherPunctuation} Alias for \p{Po} (General Category 'Po')
277* \p{OtherSymbol} Alias for \p{So} (General Category 'So')
278* \p{OtherUppercase} Extended property 'Other_Uppercase'
279* \p{Other} Alias for \p{C} (Major Category 'C')
280* \p{ParagraphSeparator} Alias for \p{Zp} (General Category 'Zp')
281 \p{Pc} General Category 'Pc'
282 \p{Pd} General Category 'Pd'
283 \p{Pe} General Category 'Pe'
284 \p{Pf} General Category 'Pf'
285 \p{Pi} General Category 'Pi'
286 \p{Po} General Category 'Po'
287 \p{Print} [[:Print:]]
288* \p{PrivateUse} Alias for \p{Co} (General Category 'Co')
289 \p{Ps} General Category 'Ps'
290* \p{Punctuation} Alias for \p{P} (Major Category 'P')
291 \p{Punct} [[:Punct:]]
292 \p{P} Major Category 'P'
293* \p{QuotationMark} Extended property 'Quotation_Mark'
294* \p{Runic} Script 'RUNIC'
295 \p{Sc} General Category 'Sc'
296* \p{Separator} Alias for \p{Z} (Major Category 'Z')
297* \p{Sinhala} Script 'SINHALA'
298 \p{Sk} General Category 'Sk'
299 \p{Sm} General Category 'Sm'
300 \p{So} General Category 'So'
301 \p{SpacePerl} \s
302* \p{SpaceSeparator} Alias for \p{Zs} (General Category 'Zs')
303 \p{Space} [[:Space:]]
304* \p{SpacingMark} Alias for \p{Mc} (General Category 'Mc')
305* \p{Surrogate} Alias for \p{Cs} (General Category 'Cs')
306* \p{Symbol} Alias for \p{S} (Major Category 'S')
307* \p{Syriac} Script 'SYRIAC'
308 \p{S} Major Category 'S'
309* \p{Tamil} Script 'TAMIL'
310* \p{Telugu} Script 'TELUGU'
311* \p{TerminalPunctuation} Extended property 'Terminal_Punctuation'
312* \p{Thaana} Script 'THAANA'
313* \p{Thai} Script 'THAI'
314* \p{Tibetan} Script 'TIBETAN'
315* \p{TitlecaseLetter} Alias for \p{Lt} (General Category 'Lt')
316 \p{Title} [[:Title:]]
317* \p{Unassigned} Alias for \p{Cn} (General Category 'Cn' [not functional in Perl])
318* \p{UppercaseLetter} Alias for \p{Lu} (General Category 'Lu')
319* \p{Uppercase} [\p{Lu}\p{Other_Uppercase}]
320 \p{Upper} [[:Upper:]]
321* \p{WhiteSpace} Extended property 'White_space'
322 \p{Word} [[:Word:]]
323 \p{XDigit} [[:XDigit:]]
324* \p{Yi} Script 'YI'
325 \p{Zl} General Category 'Zl'
326 \p{Zp} General Category 'Zp'
327 \p{Zs} General Category 'Zs'
328 \p{Z} Major Category 'Z'
329 \p{_CanonDCIJ} (for internal casefolding use)
330 \p{_CaseIgnorable} (for internal casefolding use)
331 \p{_CombAbove} (for internal casefolding use)