diff options
Diffstat (limited to 'lib/unicore/PropValueAliases.txt')
| -rw-r--r-- | lib/unicore/PropValueAliases.txt | 181 |
1 files changed, 163 insertions, 18 deletions
diff --git a/lib/unicore/PropValueAliases.txt b/lib/unicore/PropValueAliases.txt index eeb3583188..fe82f23617 100644 --- a/lib/unicore/PropValueAliases.txt +++ b/lib/unicore/PropValueAliases.txt @@ -1,12 +1,10 @@ -# PropertyValueAliases-3.2.0.txt -# Date: 2002-03-19,23:31:21 GMT [MD] +# PropertyValueAliases-4.0.0.txt +# Date: 2003-03-12, 23:46:08 GMT [MD] # # This file contains aliases for property values used in the UCD. # These names can be used for XML formats of UCD data, for regular-expression # property tests, and other programmatic textual descriptions of Unicode data. -# The names are not normative, except where they correspond to normative property -# values in the UCD. For information on which properties are normative, see -# UnicodeCharacterDatabase.html. +# For information on which properties are normative, see UCD.html. # # The names may be translated in appropriate environments, and additional # aliases may be useful. @@ -25,32 +23,32 @@ # # Third Field: The third field is a long name. # -# In the case of ccc, their are 4 fields. The second field is numeric, third +# In the case of ccc, there are 4 fields. The second field is numeric, third # is abbreviated, and fourth is long. # # With loose matching of property names, the case distinctions, whitespace, # and '_' are ignored. # -# NOTE: The Block property values are in Blocks.txt, and not repeated here. -# For more information on the use of blocks, see UTR #24: Regular Expression Guidelines -# # NOTE: Currently there is at most one abbreviated name and one long name for -# property value. However, in the future additional aliases -# may be added. In such a case, the first line for the property value -# would have the preferred alias for output. +# property value. However, in the future additional aliases may be added. +# In such a case, the first line for the property value would have +# the preferred alias for output. # # NOTE: The property value names are NOT unique across properties, especially -# with loose matches. For example, +# with loose matches. For example: +# # AL means Arabic Letter for the Bidi_Class property, and # AL means Alpha_Left for the Combining_Class property, and # AL means Alphabetic for the Line_Break property. # -# In addition, some property names may be the same as some property value names: -# cc means Combining_Class property, and -# cc means the General_Category property value Control (cc) +# In addition, some property names may be the same as some property value names. +# For example: +# +# cc means Combining_Class property, and +# cc means the General_Category property value Control (cc) # # The combination of property value and property name is, however, unique. -# For more information, see UTR #24: Regular Expression Guidelines +# For more information, see UTR #18: Regular Expression Guidelines # ================================================ @@ -74,9 +72,136 @@ bc ; RLO ; Right_To_Left_Override bc ; S ; Segment_Separator bc ; WS ; White_Space +blk; n/a ; Aegean_Numbers +blk; n/a ; Alphabetic_Presentation_Forms +blk; n/a ; Arabic +blk; n/a ; Arabic_Presentation_Forms-A +blk; n/a ; Arabic_Presentation_Forms-B +blk; n/a ; Armenian +blk; n/a ; Arrows +blk; n/a ; Basic_Latin +blk; n/a ; Bengali +blk; n/a ; Block_Elements +blk; n/a ; Bopomofo +blk; n/a ; Bopomofo_Extended +blk; n/a ; Box_Drawing +blk; n/a ; Braille_Patterns +blk; n/a ; Buhid +blk; n/a ; Byzantine_Musical_Symbols +blk; n/a ; Cherokee +blk; n/a ; CJK_Compatibility +blk; n/a ; CJK_Compatibility_Forms +blk; n/a ; CJK_Compatibility_Ideographs +blk; n/a ; CJK_Compatibility_Ideographs_Supplement +blk; n/a ; CJK_Radicals_Supplement +blk; n/a ; CJK_Symbols_and_Punctuation +blk; n/a ; CJK_Unified_Ideographs +blk; n/a ; CJK_Unified_Ideographs_Extension_A +blk; n/a ; CJK_Unified_Ideographs_Extension_B +blk; n/a ; Combining_Diacritical_Marks +blk; n/a ; Combining_Diacritical_Marks_for_Symbols +blk; n/a ; Combining_Half_Marks +blk; n/a ; Control_Pictures +blk; n/a ; Currency_Symbols +blk; n/a ; Cypriot_Syllabary +blk; n/a ; Cyrillic +blk; n/a ; Cyrillic_Supplementary +blk; n/a ; Deseret +blk; n/a ; Devanagari +blk; n/a ; Dingbats +blk; n/a ; Enclosed_Alphanumerics +blk; n/a ; Enclosed_CJK_Letters_and_Months +blk; n/a ; Ethiopic +blk; n/a ; General_Punctuation +blk; n/a ; Geometric_Shapes +blk; n/a ; Georgian +blk; n/a ; Gothic +blk; n/a ; Greek_and_Coptic +blk; n/a ; Greek_Extended +blk; n/a ; Gujarati +blk; n/a ; Gurmukhi +blk; n/a ; Halfwidth_and_Fullwidth_Forms +blk; n/a ; Hangul_Compatibility_Jamo +blk; n/a ; Hangul_Jamo +blk; n/a ; Hangul_Syllables +blk; n/a ; Hanunoo +blk; n/a ; Hebrew +blk; n/a ; High_Private_Use_Surrogates +blk; n/a ; High_Surrogates +blk; n/a ; Hiragana +blk; n/a ; Ideographic_Description_Characters +blk; n/a ; IPA_Extensions +blk; n/a ; Kanbun +blk; n/a ; Kangxi_Radicals +blk; n/a ; Kannada +blk; n/a ; Katakana +blk; n/a ; Katakana_Phonetic_Extensions +blk; n/a ; Khmer +blk; n/a ; Khmer_Symbols +blk; n/a ; Lao +blk; n/a ; Latin_Extended_Additional +blk; n/a ; Latin_Extended-A +blk; n/a ; Latin_Extended-B +blk; n/a ; Latin-1_Supplement +blk; n/a ; Letterlike_Symbols +blk; n/a ; Limbu +blk; n/a ; Linear_B_Ideograms +blk; n/a ; Linear_B_Syllabary +blk; n/a ; Low_Surrogates +blk; n/a ; Malayalam +blk; n/a ; Mathematical_Alphanumeric_Symbols +blk; n/a ; Mathematical_Operators +blk; n/a ; Miscellaneous_Mathematical_Symbols-A +blk; n/a ; Miscellaneous_Mathematical_Symbols-B +blk; n/a ; Miscellaneous_Symbols +blk; n/a ; Miscellaneous_Symbols_and_Arrows +blk; n/a ; Miscellaneous_Technical +blk; n/a ; Mongolian +blk; n/a ; Musical_Symbols +blk; n/a ; Myanmar +blk; n/a ; No_Block +blk; n/a ; Number_Forms +blk; n/a ; Ogham +blk; n/a ; Old_Italic +blk; n/a ; Optical_Character_Recognition +blk; n/a ; Oriya +blk; n/a ; Osmanya +blk; n/a ; Phonetic_Extensions +blk; n/a ; Private_Use_Area +blk; n/a ; Runic +blk; n/a ; Shavian +blk; n/a ; Sinhala +blk; n/a ; Small_Form_Variants +blk; n/a ; Spacing_Modifier_Letters +blk; n/a ; Specials +blk; n/a ; Superscripts_and_Subscripts +blk; n/a ; Supplemental_Arrows-A +blk; n/a ; Supplemental_Arrows-B +blk; n/a ; Supplemental_Mathematical_Operators +blk; n/a ; Supplementary_Private_Use_Area-A +blk; n/a ; Supplementary_Private_Use_Area-B +blk; n/a ; Syriac +blk; n/a ; Tagalog +blk; n/a ; Tagbanwa +blk; n/a ; Tags +blk; n/a ; Tai_Le +blk; n/a ; Tai_Xuan_Jing_Symbols +blk; n/a ; Tamil +blk; n/a ; Telugu +blk; n/a ; Thaana +blk; n/a ; Thai +blk; n/a ; Tibetan +blk; n/a ; Ugaritic +blk; n/a ; Unified_Canadian_Aboriginal_Syllabics +blk; n/a ; Variation_Selectors +blk; n/a ; Variation_Selectors_Supplement +blk; n/a ; Yi_Radicals +blk; n/a ; Yi_Syllables +blk; n/a ; Yijing_Hexagram_Symbols + ccc; 0; NR ; Not_Reordered ccc; 1; OV ; Overlay -ccc; 202; ATBL ; Attached_Below_Left +ccc; 202; ATB ; Attached_Below ccc; 216; ATAR ; Attached_Above_Right ccc; 218; BL ; Below_Left ccc; 220; B ; Below @@ -158,6 +283,13 @@ gc ; Zl ; Line_Separator gc ; Zp ; Paragraph_Separator gc ; Zs ; Space_Separator +hst; L ; Leading_Jamo +hst; LV ; LV_Syllable +hst; LVT ; LVT_Syllable +hst; NA ; Not_Applicable +hst; T ; Trailing_Jamo +hst; V ; Vowel_Jamo + jg ; n/a ; AIN jg ; n/a ; ALAPH jg ; n/a ; ALEF @@ -166,6 +298,7 @@ jg ; n/a ; BETH jg ; n/a ; DAL jg ; n/a ; DALATH_RISH jg ; n/a ; E +jg ; n/a ; FE jg ; n/a ; FEH jg ; n/a ; FINAL_SEMKATH jg ; n/a ; GAF @@ -178,6 +311,7 @@ jg ; n/a ; HEH_GOAL jg ; n/a ; HETH jg ; n/a ; KAF jg ; n/a ; KAPH +jg ; n/a ; KHAPH jg ; n/a ; KNOTTED_HEH jg ; n/a ; LAM jg ; n/a ; LAMADH @@ -209,6 +343,7 @@ jg ; n/a ; YEH_WITH_TAIL jg ; n/a ; YUDH jg ; n/a ; YUDH_HE jg ; n/a ; ZAIN +jg ; n/a ; ZHAIN jt ; C ; Join_Causing jt ; D ; Dual_Joining @@ -234,6 +369,7 @@ lb ; ID ; Ideographic lb ; IN ; Inseperable lb ; IS ; Infix_Numeric lb ; LF ; Line_Feed +lb ; NL ; Next_Line lb ; NS ; Nonstarter lb ; NU ; Numeric lb ; OP ; Open_Punctuation @@ -244,6 +380,7 @@ lb ; SA ; Complex_Context lb ; SG ; Surrogate lb ; SP ; Space lb ; SY ; Break_Symbols +lb ; WJ ; Word_Joiner lb ; XX ; Unknown lb ; ZW ; ZWSpace @@ -260,9 +397,11 @@ sc ; Arab ; Arabic sc ; Armn ; Armenian sc ; Beng ; Bengali sc ; Bopo ; Bopomofo +sc ; Brai ; Braille sc ; Buhd ; Buhid sc ; Cans ; Canadian_Aboriginal sc ; Cher ; Cherokee +sc ; Cprt ; Cypriot sc ; Cyrl ; Cyrillic sc ; Deva ; Devanagari sc ; Dsrt ; Deseret @@ -283,21 +422,27 @@ sc ; Khmr ; Khmer sc ; Knda ; Kannada sc ; Laoo ; Lao sc ; Latn ; Latin +sc ; Limb ; Limbu +sc ; Linb ; Linear_B sc ; Mlym ; Malayalam sc ; Mong ; Mongolian sc ; Mymr ; Myanmar sc ; Ogam ; Ogham sc ; Orya ; Oriya +sc ; Osma ; Osmanya sc ; Qaai ; Inherited sc ; Runr ; Runic +sc ; Shaw ; Shavian sc ; Sinh ; Sinhala sc ; Syrc ; Syriac sc ; Tagb ; Tagbanwa +sc ; Tale ; Tai_Le sc ; Taml ; Tamil sc ; Telu ; Telugu sc ; Tglg ; Tagalog sc ; Thaa ; Thaana sc ; Thai ; Thai sc ; Tibt ; Tibetan +sc ; Ugar ; Ugaritic sc ; Yiii ; Yi sc ; Zyyy ; Common |