scuffed-code/tools/unicodetools/com/ibm/text/UCD/MakeUnicodeFiles.txt

Generate: .*
DeltaVersion: 16
CopyrightYear: 2006

File: auxiliary/GraphemeBreakProperty
Property: Grapheme_Cluster_Break
Format:	skipValue=Other

File: auxiliary/WordBreakProperty
Property: Word_Break
Format:	skipValue=Other

File: auxiliary/SentenceBreakProperty
Property: Sentence_Break
Format:	skipValue=Other

File: auxiliary/GraphemeBreakTest
Property: SPECIAL

File: auxiliary/WordBreakTest
Property: SPECIAL

File: auxiliary/LineBreakTest
Property: SPECIAL

File: auxiliary/SentenceBreakTest
Property: SPECIAL

File:	Blocks
Property: Block
# Note:   When comparing block names, casing, whitespace, hyphens,
#         and underbars are ignored.
#         For example, "Latin Extended-A" and "latin extended a" are equivalent.
#         For more information on the comparison of property values, 
#            see UCD.html.
Format:	valueList skipUnassigned=No_Block

File:	CaseFolding
Property: SPECIAL

File:	DerivedAge
Property:	Age
Format:	nameStyle=none noLabel skipValue=unassigned

Value:	1.1
# Assigned as of Unicode 1.1.0 (June, 1993)
# [excluding removed Hangul Syllables]

Value:	2.0
# Newly assigned in Unicode 2.0.0 (July, 1996)

Value:	2.1
# Newly assigned in Unicode 2.1.2 (May, 1998)

Value:	3.0
# Newly assigned in Unicode 3.0.0 (September, 1999)

Value:	3.1
# Newly assigned in Unicode 3.1.0 (March, 2001)

Value:	3.2
# Newly assigned in Unicode 3.2.0 (March, 2002)

Value:	4.0
# Newly assigned in Unicode 4.0.0 (April, 2003)

Value:	4.1
# Newly assigned in Unicode 4.1.0 (March, 2005)

Value:	5.0
# Newly assigned in Unicode 5.0.0 (XXX, 2006)

File:	extracted/DerivedBidiClass
Property:	Bidi_Class
# Bidi Class (listing UnicodeData.txt, field 4: see UCD.html)
# Unlike other properties, unassigned code points in blocks 
# reserved for right-to-left scripts are given either types R or AL.
# The unassigned characters that default to R are:
#   Hebrew, Cypriot_Syllabary, Kharoshthi, and the ranges \u07C0-\u08FF
#   \uFB1D-\uFB4F \U00010840-\U000109FF \U00010A60-\U00010FFF
# The unassigned characters that default to AL are:
#   Arabic, Syriac, Arabic_Supplement, Thaana, Arabic_Presentation_Forms_A,
#   Arabic_Presentation_Forms_B, minus the Noncharacter_Code_Points
# For all other cases:
Format:	valueStyle=short skipUnassigned=Left_To_Right

File:	extracted/DerivedBinaryProperties
Property:	Bidi_Mirrored
# Bidi_Mirrored (listing UnicodeData.txt, field 9: see UCD.html)

File:	extracted/DerivedCombiningClass
Property:	Canonical_Combining_Class
# Combining Class (listing UnicodeData.txt, field 3: see UCD.html)
Format: nameStyle=none valueStyle=short skipUnassigned=Not_Reordered

File:	DerivedCoreProperties
Property:	Math
# Derived Property: Math
#  Generated from: Sm + Other_Math

Property:	Alphabetic
# Derived Property: Alphabetic
#  Generated from: Lu+Ll+Lt+Lm+Lo+Nl + Other_Alphabetic


Property:	Lowercase
# Derived Property: Lowercase
#  Generated from: Ll + Other_Lowercase


Property:	Uppercase
# Derived Property: Uppercase
#  Generated from: Lu + Other_Uppercase


Property:	ID_Start
# Derived Property: ID_Start
#  Characters that can start an identifier.
#  Generated from Lu+Ll+Lt+Lm+Lo+Nl+Other_ID_Start
#  NOTE: See UAX #31 for more information

Property:	ID_Continue
# Derived Property: ID_Continue
#  Characters that can continue an identifier.
#  Generated from: ID_Start + Mn+Mc+Nd+Pc + Other_ID_Continue
#  NOTE: See UAX #31 for more information


Property:	XID_Start
# Derived Property: XID_Start
#  ID_Start modified for closure under NFKx
#  Modified as described in UAX #15
#  NOTE: Does NOT remove the non-NFKx characters.
#        Merely ensures that if isIdentifer(string) then isIdentifier(NFKx(string))
#  NOTE: See UAX #31 for more information

Property:	XID_Continue
# Derived Property: XID_Continue
#  Mod_ID_Continue modified for closure under NFKx
#  Modified as described in UAX #15
#  NOTE: Cf characters should be filtered out.
#  NOTE: Does NOT remove the non-NFKx characters.
#        Merely ensures that if isIdentifer(string) then isIdentifier(NFKx(string))
#  NOTE: See UAX #31 for more information

Property:	Default_Ignorable_Code_Point
# Derived Property: Default_Ignorable_Code_Point
#  Generated from Other_Default_Ignorable_Code_Point + Cf + Cc + Cs + Noncharacters
#  - White_Space - FFF9..FFFB (Annotation Characters)

Property:	Grapheme_Extend
# Derived Property: Grapheme_Extend
#  Generated from: Me + Mn + Other_Grapheme_Extend
#  Note: depending on an application's interpretation of Co (private use),
#  they may be either in Grapheme_Base, or in Grapheme_Extend, or in neither.


Property:	Grapheme_Base
# Derived Property: Grapheme_Base
#  Generated from: [0..10FFFF] - Cc - Cf - Cs - Co - Cn - Zl - Zp - Grapheme_Extend
#  Note: depending on an application's interpretation of Co (private use),
#  they may be either in Grapheme_Base, or in Grapheme_Extend, or in neither.

Property:	Grapheme_Link
# Derived Property: Grapheme_Link (deprecated)
#  Generated from: Canonical_Combining_Class=Virama
#  Use Canonical_Combining_Class=Virama directly instead

File:	extracted/DerivedDecompositionType
Property:	Decomposition_Type
Format:	skipValue=None
# Decomposition_Type (from UnicodeData.txt, field 5: see UCD.html)

File:	extracted/DerivedEastAsianWidth
Property:	East_Asian_Width
Format:	valueStyle=short skipUnassigned=Neutral
# East_Asian_Width (listing EastAsianWidth.txt, field 1)

File:	extracted/DerivedGeneralCategory
Property:	General_Category
Format:	valueStyle=short noLabel

File:	extracted/DerivedJoiningGroup
Property:	Joining_Group
# Joining Group (listing ArabicShaping.txt, field 3)
Format: skipValue=No_Joining_Group

File:	extracted/DerivedJoiningType
Property:	Joining_Type
#	Type T is derived, as described in ArabicShaping.txt
Format:	valueStyle=short skipValue=Non_Joining

File:	extracted/DerivedLineBreak
Property:	Line_Break
Format:	valueStyle=short skipUnassigned=Unknown

File:	DerivedNormalizationProps

Property:	FC_NFKC_Closure
# Derived Property: FC_NFKC_Closure
#  Generated from computing: b = NFKC(Fold(a)); c = NFKC(Fold(b));
#  Then if (c != b) add the mapping from a to c to the set of
#  mappings that constitute the FC_NFKC_Closure list
#  Uses the full case folding from CaseFolding.txt, without the T option.
Format:	nameStyle=short


Property:	Full_Composition_Exclusion
# Derived Property: Full_Composition_Exclusion
#  Generated from: Composition Exclusions + Singletons + Non-Starter Decompositions


Property:	NFD_QuickCheck
# Derived Property: NFD_QuickCheck
#  Generated from computing decomposibles
Format: nameStyle=short valueStyle=short skipValue=Yes


Property:	NFC_QuickCheck
# Derived Property: NFC_QuickCheck
#  Generated from computing decomposibles (and characters that may compose with previous ones)
Format: nameStyle=short valueStyle=short skipValue=Yes

Property:	NFKD_QuickCheck
# Derived Property: NFKD_QuickCheck
#  Generated from computing decomposibles
Format: nameStyle=short valueStyle=short skipValue=Yes


Property:	NFKC_QuickCheck
# Derived Property: NFKC_QuickCheck
#  Generated from computing decomposibles (and characters that may compose with previous ones)
Format: nameStyle=short valueStyle=short skipValue=Yes

Property:	Expands_On_NFD
# Derived Property: Expands_On_NFD
#   Generated according to UAX #15.
#   Characters whose normalized length is not one.
#   WARNING: Normalization of STRINGS must use the algorithm in UAX #15 because characters may interact.
#            The length of a normalized string is not necessarily the sum of the lengths of the normalized characters!


Property:	Expands_On_NFC
# Derived Property: Expands_On_NFC
#   Generated according to UAX #15.
#   Characters whose normalized length is not one.
#   WARNING: Normalization of STRINGS must use the algorithm in UAX #15 because characters may interact.
#            The length of a normalized string is not necessarily the sum of the lengths of the normalized characters!


Property:	Expands_On_NFKD
# Derived Property: Expands_On_NFKD
#   Generated according to UAX #15.
#   Characters whose normalized length is not one.
#   WARNING: Normalization of STRINGS must use the algorithm in UAX #15 because characters may interact.
#            The length of a normalized string is not necessarily the sum of the lengths of the normalized characters!


Property:	Expands_On_NFKC
# Derived Property: Expands_On_NFKC
#   Generated according to UAX #15.
#   Characters whose normalized length is not one.
#   WARNING: Normalization of STRINGS must use the algorithm in UAX #15 because characters may interact.
#            The length of a normalized string is not necessarily the sum of the lengths of the normalized characters!


File:	extracted/DerivedNumericType
Property:	Numeric_Type
# Numeric Type (from UnicodeData.txt, field 6/7/8 plus Unihan.txt: see UCD.html)
Format: skipValue=None

File:	extracted/DerivedNumericValues
Property:	Numeric_Value
# Numeric Values (from UnicodeData.txt, field 6/7/8)
# WARNING: Certain valus, such as 0.16666667, are repeating fractions
# Although they are only printed with a limited number of decimal places
# in this file, they should be expressed to the limits of the precision
# available when used.
Format: sortNumeric

File:	HangulSyllableType
Property:	Hangul_Syllable_Type
Format:	valueStyle=short skipValue=Not_Applicable

File:	NormalizationTest
Property: SPECIAL

File:	PropList

Property:	White_Space

Property:	Bidi_Control

Property:	Join_Control

Property:	Dash

Property:	Hyphen

Property:	Quotation_Mark

Property:	Terminal_Punctuation

Property:	Other_Math

Property:	Hex_Digit

Property:	ASCII_Hex_Digit

Property:	Other_Alphabetic

Property:	Ideographic

Property:	Diacritic

Property:	Extender

Property:	Other_Lowercase

Property:	Other_Uppercase

Property:	Noncharacter_Code_Point

Property:	Other_Grapheme_Extend

Property:	IDS_Binary_Operator

Property:	IDS_Trinary_Operator

Property:	Radical

Property:	Unified_Ideograph

Property:	Other_Default_Ignorable_Code_Point

Property:	Deprecated

Property:	Soft_Dotted

Property:	Logical_Order_Exception

Property:	Other_ID_Start

Property:	Other_ID_Continue

Property:	STerm

Property:	Variation_Selector
Property:	Pattern_White_Space
Property:	Pattern_Syntax


File:	PropertyAliases
Property: SPECIAL

File:	PropertyValueAliases
Property: SPECIAL

File:	Scripts
Property:	Script
Format:	nameStyle=none skipValue=Unknown

File:	SpecialCasing
Property: SPECIAL

File:	StandardizedVariants
Property: SPECIAL

File:	NamedSequences
Property: SPECIAL

HackName:	noBreak
HackName:	Arabic_Presentation_Forms-A
HackName:	Arabic_Presentation_Forms-B
HackName:	CJK_Symbols_and_Punctuation
HackName:	Combining_Diacritical_Marks_for_Symbols
HackName:	Enclosed_CJK_Letters_and_Months
HackName:	Greek_and_Coptic
HackName:	Halfwidth_and_Fullwidth_Forms
HackName:	Latin-1_Supplement
HackName:	Latin_Extended-A
HackName:	Latin_Extended-B
HackName:	Miscellaneous_Mathematical_Symbols-A
HackName:	Miscellaneous_Mathematical_Symbols-B
HackName:	Miscellaneous_Symbols_and_Arrows
HackName:	Superscripts_and_Subscripts
HackName:	Supplemental_Arrows-A
HackName:	Supplemental_Arrows-B
HackName:	Supplementary_Private_Use_Area-A
HackName:	Supplementary_Private_Use_Area-B
HackName:	Canadian-Aboriginal
#HackName:	Old-Italic

FinalComments
Note that PropertyAliases sorts by the long name, while PropertyValueAliases
sorts by the short name
ArabicShaping
BidiMirroring
CompositionExclusions
EastAsianWidth
LineBreak
StandardizedVariants
UnicodeData