ICU-8.11.tar.gz

[apple/icu.git] / icuSources / data / unidata / PropertyAliases.txt

diff --git a/icuSources/data/unidata/PropertyAliases.txt b/icuSources/data/unidata/PropertyAliases.txt
index 1195e8f0ce780143c83f9df7722b0591b88c9ff5..f69c2ffbdfabbf2d381debacca7c7ff157f7334c 100644 (file)
--- a/icuSources/data/unidata/PropertyAliases.txt
+++ b/icuSources/data/unidata/PropertyAliases.txt
@@ -1,5 +1,10 @@
-# PropertyAliases-4.0.0.txt
-# Date: 2003-03-12, 23:46:08 GMT [MD]
+# PropertyAliases-5.0.0.txt
+# Date: 2006-03-03, 08:23:34 GMT [MD]
+#
+# Unicode Character Database
+# Copyright (c) 1991-2006 Unicode, Inc.
+# For terms of use, see http://www.unicode.org/terms_of_use.html
+# For documentation, see UCD.html
 #
 # This file contains aliases for properties used in the UCD.
 # These names can be used for XML formats of UCD data, for regular-expression
@@ -11,46 +16,50 @@
 #
 # FORMAT
 #
-# Each line has two fields, separated by semicolons.
+# Each line has two or more fields, separated by semicolons.
 #
 # First Field: The first field is an abbreviated name for the property.
 #
 # Second Field: The second field is a long name
 #
-# With loose matching of property names, the case distinctions, whitespace,
-# and '_' are ignored.
+# The above are the preferred aliases. Other aliases may be listed in additional fields.
 #
-# NOTE: Currently there is at most one abbreviated name and one long name for
-# each property. However, in the future additional aliases may be added.
+# Loose matching should be applied to all property names and property values, with
+# the exception of String Property values. With loose matching of property names and
+# values, the case distinctions, whitespace, and '_' are ignored. For Numeric Property
+# values, numeric equivalencies are applied: thus "01.00" is equivalent to "1".
 #
-# NOTE: The property value names are NOT unique across properties, especially
-# with loose matches. For example:
+# NOTE: Property value names are NOT unique across properties. 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.
+# For example:
+#
+#   sc means the Script property, and
+#   Sc means the General_Category property value Currency_Symbol (Sc)
 #
 # The combination of property value and property name is, however, unique.
-# For more information, see UTR #18: Regular Expression Guidelines
+#
+# For more information, see UTS #18: Regular Expression Guidelines
 # ================================================
 
 
 # ================================================
-# Non-enumerated Properties
+# Numeric Properties
+# ================================================
+nv        ; Numeric_Value
+
+# ================================================
+# String Properties
 # ================================================
-age       ; Age
-blk       ; Block
 bmg       ; Bidi_Mirroring_Glyph
 cf        ; Case_Folding
 dm        ; Decomposition_Mapping
 FC_NFKC   ; FC_NFKC_Closure
-isc       ; ISO_Comment
 lc        ; Lowercase_Mapping
-na        ; Name
-na1       ; Unicode_1_Name
-nv        ; Numeric_Value
 scc       ; Special_Case_Condition
 sfc       ; Simple_Case_Folding
 slc       ; Simple_Lowercase_Mapping
@@ -58,16 +67,31 @@ stc       ; Simple_Titlecase_Mapping
 suc       ; Simple_Uppercase_Mapping
 tc        ; Titlecase_Mapping
 uc        ; Uppercase_Mapping
+
+# ================================================
+# Miscellaneous Properties
+# ================================================
+isc       ; ISO_Comment
+na        ; Name
+na1       ; Unicode_1_Name
 URS       ; Unicode_Radical_Stroke
 
 # ================================================
-# Enumerated Non-Binary Properties
+# Catalog Properties
+# ================================================
+age       ; Age
+blk       ; Block
+sc        ; Script
+
+# ================================================
+# Enumerated Properties
 # ================================================
 bc        ; Bidi_Class
 ccc       ; Canonical_Combining_Class
 dt        ; Decomposition_Type
 ea        ; East_Asian_Width
 gc        ; General_Category
+GCB       ; Grapheme_Cluster_Break
 hst       ; Hangul_Syllable_Type
 jg        ; Joining_Group
 jt        ; Joining_Type
@@ -77,7 +101,8 @@ NFD_QC    ; NFD_Quick_Check
 NFKC_QC   ; NFKC_Quick_Check
 NFKD_QC   ; NFKD_Quick_Check
 nt        ; Numeric_Type
-sc        ; Script
+SB        ; Sentence_Break
+WB        ; Word_Break
 
 # ================================================
 # Binary Properties
@@ -111,20 +136,30 @@ NChar     ; Noncharacter_Code_Point
 OAlpha    ; Other_Alphabetic
 ODI       ; Other_Default_Ignorable_Code_Point
 OGr_Ext   ; Other_Grapheme_Extend
+OIDC      ; Other_ID_Continue
 OIDS      ; Other_ID_Start
 OLower    ; Other_Lowercase
 OMath     ; Other_Math
 OUpper    ; Other_Uppercase
+Pat_Syn   ; Pattern_Syntax
+Pat_WS    ; Pattern_White_Space
 QMark     ; Quotation_Mark
 Radical   ; Radical
 SD        ; Soft_Dotted
+STerm     ; STerm
 Term      ; Terminal_Punctuation
 UIdeo     ; Unified_Ideograph
 Upper     ; Uppercase
-WSpace    ; White_Space
+VS        ; Variation_Selector
+WSpace    ; White_Space                 ; space
 XIDC      ; XID_Continue
 XIDS      ; XID_Start
 XO_NFC    ; Expands_On_NFC
 XO_NFD    ; Expands_On_NFD
 XO_NFKC   ; Expands_On_NFKC
 XO_NFKD   ; Expands_On_NFKD
+
+# ================================================
+# Total:    88
+
+# EOF