chore: Jsps to Unicode 15 final (#332)

* chore: Jsps to Unicode 15 final

For #271

* fix(build): Jsps: don't test during gcr build

The gcr build will need some work work for testing. Disable test for now.
Revisit in #333

For #271

* fix(build): Fix JSPs to include unicodetools and cldr

Fixes #271

* fix dockerfile

Fixes: #334

* fix dockerfile again

Fixes: #334

* fix(build): fix broken build-jsp.yml

- the Dockerfile now requires a .tgz file with the cldr and unicodetools
to use.

Fixes: #271

Author: srl295

.github/workflows/build-jsp.yml

@@ -17,6 +17,9 @@ jobs:
       with:
         repository: unicode-org/cldr
         path: cldr
+    - name: Backup Unicodetools and CLDR for jsps  # this is needed only for the Docker build
+      run:
+        mkdir -p UnicodeJsps/target && tar cfpz UnicodeJsps/target/cldr-unicodetools.tgz ./cldr ./unicodetools
     - name: Set up JDK 11
       uses: actions/setup-java@v1
       with:

.github/workflows/push-jsp-on-tag.yml

@@ -12,6 +12,15 @@ jobs:
       uses: actions/setup-java@v1
       with:
         java-version: 11
+    - uses: actions/checkout@v2
+    - name: Check out CLDR
+      uses: actions/checkout@v2
+      with:
+        repository: unicode-org/cldr
+        path: cldr
+    - name: Backup Unicodetools and CLDR for jsps
+      run:
+        mkdir -p UnicodeJsps/target && tar cfpz UnicodeJsps/target/cldr-unicodetools.tgz ./cldr ./unicodetools
     - name: Cache local Maven repository
       uses: actions/cache@v2
       with:
@@ -26,7 +35,7 @@ jobs:
         GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
     - name: Package with Maven
       run: >
-        mvn -s .github/workflows/mvn-settings.xml -B compile test install package -pl UnicodeJsps
+        mvn -s .github/workflows/mvn-settings.xml -B compile install package -pl UnicodeJsps -DskipTests=true
       env:
         GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
     - name: Upload UnicodeJsps.war

UnicodeJsps/Dockerfile

@@ -7,19 +7,26 @@ RUN apk add --update -q wget make gcc musl-dev
 RUN wget -np -nv --reject-regex='.*\.(lib|exe)$' --cut-dirs=4 -nH -r ${CPATH}${CVERSION}/
 RUN cd source && gcc -I ../include/ -static -Os -o3 -o bidiref1 bidiref1.c brutils.c brtest.c brtable.c brrule.c
 RUN ls -lh /build/source/bidiref1 && (/build/source/bidiref1 || true)
+# copy and unpack to /tmp/data
+ADD ./target/cldr-unicodetools.tgz /build/data/
+# move this into place (including unicodetools/unicodetools)
+RUN rm -rf /build/data/cldr/.git  # unneeded
 FROM jetty:9-jre11-slim AS run
-# FROM tomcat:9-jdk14-openjdk-slim-buster AS run
 ADD port-entrypoint.sh /port-entrypoint.sh
 ADD ./jetty.d/ROOT /var/lib/jetty/webapps/ROOT/
 ENTRYPOINT [ "/port-entrypoint.sh" ]
 # copy the .war
-ADD target/UnicodeJsps.war /var/lib/jetty/webapps/
+ADD ./target/UnicodeJsps.war /var/lib/jetty/webapps/
 # copy the UCD for bidiref1
 COPY src/main/resources/org/unicode/jsp/bidiref1/ucd/ /usr/local/share/ucd/
 # this is the parent to 'ucd'
 ENV BIDIREFHOME /usr/local/share
 # copy the bidiref1 bin
 ENV BIDIREF1 /usr/local/bin/bidiref1
 COPY --from=cbuild /build/source/bidiref1 /usr/local/bin/
+RUN mkdir -p /var/lib/jetty/data/unicodetools
+COPY --from=cbuild /build/data/cldr /var/lib/jetty/data/cldr
+COPY --from=cbuild /build/data/unicodetools/ /var/lib/jetty/data/unicodetools/unicodetools/
+ENV JAVA_OPTIONS -DCLDR_DIR=/var/lib/jetty/data/cldr -DUNICODETOOLS_REPO_DIR=/var/lib/jetty/data/unicodetools
 # This is the default PORT. Override by setting PORT.
 EXPOSE 8080

UnicodeJsps/src/main/resources/org/unicode/jsp/IdentifierStatus.txt

@@ -1,5 +1,5 @@
-# IdentifierStatus.txt
-# Date: 2022-05-18, 21:51:57 GMT
+# IdentifierStatus.txt
+# Date: 2022-08-26, 16:49:09 GMT
 # © 2022 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use, see https://www.unicode.org/terms_of_use.html
@@ -14,16 +14,17 @@
 # Field 0: code point
 # Field 1: Identifier_Status value (see Table 1 of http://www.unicode.org/reports/tr39)
 #
-# Any missing code points have the Identifier_Status value Restricted
-#
 # For the purpose of regular expressions, the property Identifier_Status is defined as
 # an enumerated property of code points.
 # The short name of Identifier_Status is the same as the long name.
 # The possible values are:
 #   Allowed, Restricted
 # The short name of each value is the same as its long name.
-# The default property value for all Unicode code points U+0000..U+10FFFF
-# not mentioned in this data file is Restricted.
+
+# All code points not explicitly listed for Identifier_Status
+# have the value Restricted.
+
+# @missing: 0000..10FFFF; Restricted
 
 
 #	Identifier_Status:	Allowed
@@ -531,8 +532,6 @@ A788          ; Allowed    # 5.1        MODIFIER LETTER LOW CIRCUMFLEX ACCENT
 A78D          ; Allowed    # 6.0        LATIN CAPITAL LETTER TURNED H
 A792..A793    ; Allowed    # 6.1    [2] LATIN CAPITAL LETTER C WITH BAR..LATIN SMALL LETTER C WITH BAR
 A7AA          ; Allowed    # 6.1        LATIN CAPITAL LETTER H WITH HOOK
-A7AE          ; Allowed    # 9.0        LATIN CAPITAL LETTER SMALL CAPITAL I
-A7B8..A7B9    ; Allowed    # 11.0   [2] LATIN CAPITAL LETTER U WITH STROKE..LATIN SMALL LETTER U WITH STROKE
 A7C0..A7C1    ; Allowed    # 14.0   [2] LATIN CAPITAL LETTER OLD POLISH O..LATIN SMALL LETTER OLD POLISH O
 A7C2..A7C6    ; Allowed    # 12.0   [5] LATIN CAPITAL LETTER ANGLICANA W..LATIN CAPITAL LETTER Z WITH PALATAL HOOK
 A7C7..A7CA    ; Allowed    # 13.0   [4] LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY
@@ -586,4 +585,4 @@ FA27..FA29    ; Allowed    # 1.1    [3] CJK COMPATIBILITY IDEOGRAPH-FA27..CJK CO
 30000..3134A  ; Allowed    # 13.0 [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
 31350..323AF  ; Allowed    # 15.0 [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
 
-# Total code points: 112159
+# Total code points: 112156

UnicodeJsps/src/main/resources/org/unicode/jsp/IdentifierType.txt

@@ -1,5 +1,5 @@
-# IdentifierType.txt
-# Date: 2022-05-18, 21:51:56 GMT
+# IdentifierType.txt
+# Date: 2022-08-26, 16:49:09 GMT
 # © 2022 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use, see https://www.unicode.org/terms_of_use.html
@@ -14,17 +14,19 @@
 # Field 0: code point
 # Field 1: set of Identifier_Type values (see Table 1 of http://www.unicode.org/reports/tr39)
 #
-# Any missing code points have the Identifier_Type value Not_Character
-#
 # For the purpose of regular expressions, the property Identifier_Type is defined as
 # mapping each code point to a set of enumerated values.
 # The short name of Identifier_Type is the same as the long name.
 # The possible values are:
 #   Not_Character, Deprecated, Default_Ignorable, Not_NFKC, Not_XID,
 #   Exclusion, Obsolete, Technical, Uncommon_Use, Limited_Use, Inclusion, Recommended
 # The short name of each value is the same as its long name.
-# The default property value for all Unicode code points U+0000..U+10FFFF
-# not mentioned in this data file is Not_Character.
+
+# All code points not explicitly listed for Identifier_Type
+# have the value Not_Character.
+
+# @missing: 0000..10FFFF; Not_Character
+
 # As usual, sets are unordered, with no duplicate values.
 
 
@@ -524,8 +526,6 @@ A788          ; Recommended                    # 5.1        MODIFIER LETTER LOW
 A78D          ; Recommended                    # 6.0        LATIN CAPITAL LETTER TURNED H
 A792..A793    ; Recommended                    # 6.1    [2] LATIN CAPITAL LETTER C WITH BAR..LATIN SMALL LETTER C WITH BAR
 A7AA          ; Recommended                    # 6.1        LATIN CAPITAL LETTER H WITH HOOK
-A7AE          ; Recommended                    # 9.0        LATIN CAPITAL LETTER SMALL CAPITAL I
-A7B8..A7B9    ; Recommended                    # 11.0   [2] LATIN CAPITAL LETTER U WITH STROKE..LATIN SMALL LETTER U WITH STROKE
 A7C0..A7C1    ; Recommended                    # 14.0   [2] LATIN CAPITAL LETTER OLD POLISH O..LATIN SMALL LETTER OLD POLISH O
 A7C2..A7C6    ; Recommended                    # 12.0   [5] LATIN CAPITAL LETTER ANGLICANA W..LATIN CAPITAL LETTER Z WITH PALATAL HOOK
 A7C7..A7CA    ; Recommended                    # 13.0   [4] LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY
@@ -579,7 +579,7 @@ FA27..FA29    ; Recommended                    # 1.1    [3] CJK COMPATIBILITY ID
 30000..3134A  ; Recommended                    # 13.0 [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
 31350..323AF  ; Recommended                    # 15.0 [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
 
-# Total code points: 112142
+# Total code points: 112139
 
 #	Identifier_Type:	Inclusion
 
@@ -858,14 +858,15 @@ A67C..A67D    ; Uncommon_Use                   # 5.1    [2] COMBINING CYRILLIC K
 A78B..A78C    ; Uncommon_Use                   # 5.1    [2] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER SALTILLO
 A78F          ; Uncommon_Use                   # 8.0        LATIN LETTER SINOLOGICAL DOT
 A7B2..A7B7    ; Uncommon_Use                   # 8.0    [6] LATIN CAPITAL LETTER J WITH CROSSED-TAIL..LATIN SMALL LETTER OMEGA
+A7B8..A7B9    ; Uncommon_Use                   # 11.0   [2] LATIN CAPITAL LETTER U WITH STROKE..LATIN SMALL LETTER U WITH STROKE
 AB60..AB63    ; Uncommon_Use                   # 8.0    [4] LATIN SMALL LETTER SAKHA YAT..LATIN SMALL LETTER UO
 10780         ; Uncommon_Use                   # 14.0       MODIFIER LETTER SMALL CAPITAL AA
 10EFD..10EFF  ; Uncommon_Use                   # 15.0   [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA
 1AFF0..1AFF3  ; Uncommon_Use                   # 14.0   [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
 1AFF5..1AFFB  ; Uncommon_Use                   # 14.0   [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
 1AFFD..1AFFE  ; Uncommon_Use                   # 14.0   [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
 
-# Total code points: 311
+# Total code points: 313
 
 #	Identifier_Type:	Uncommon_Use Technical
 
@@ -1008,6 +1009,7 @@ A8FC          ; Uncommon_Use Obsolete Not_XID  # 8.0        DEVANAGARI SIGN SIDD
 3031..3035    ; Technical                      # 1.1    [5] VERTICAL KANA REPEAT MARK..VERTICAL KANA REPEAT MARK LOWER HALF
 303B..303C    ; Technical                      # 3.2    [2] VERTICAL IDEOGRAPHIC ITERATION MARK..MASU MARK
 A78E          ; Technical                      # 6.0        LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT
+A7AE          ; Technical                      # 9.0        LATIN CAPITAL LETTER SMALL CAPITAL I
 A7AF          ; Technical                      # 11.0       LATIN LETTER SMALL CAPITAL Q
 A7BA..A7BF    ; Technical                      # 12.0   [6] LATIN CAPITAL LETTER GLOTTAL A..LATIN SMALL LETTER GLOTTAL U
 A7FA          ; Technical                      # 6.0        LATIN LETTER SMALL CAPITAL TURNED M
@@ -1024,7 +1026,7 @@ FE73          ; Technical                      # 3.2        ARABIC TAIL FRAGMENT
 1D185..1D18B  ; Technical                      # 3.1    [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
 1D1AA..1D1AD  ; Technical                      # 3.1    [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
 
-# Total code points: 500
+# Total code points: 501
 
 #	Identifier_Type:	Technical Exclusion
 

UnicodeJsps/src/main/resources/org/unicode/jsp/NamesList.txt

@@ -1,23 +1,7 @@
 ; charset=UTF-8
 @@@	The Unicode Standard 15.0.0
-@@@+	U15M220504.lst
-	Unicode 15.0.0 names list, fourth delta.
-	Repertoire synched with UnicodeData-15.0.0d4.txt.
-	Rollup of alpha review fixes.
-	Adjusted alias and added xref for 1F728.
-	Added annotations for 1F772, 1F773.
-	Fixed typos in annotations for 1342F and 13430.
-	Added cross-references to 20E6.
-	Added cross-references between 1FAAF and 262C.
-	Updated annotation for 26A5.
-	Added annotation for 33D7.
-	Added annotation for 11F52.
-	Added cross-references between 10EFD and 08DD.
-	Added cross-references for 11B00 and 11B09.
-	Added name alias of type correction for 1BBD.
-	Added annotation and cross-reference for 2E95.
-	Extended the range for CJK Unified Ideographs Extension C to 2B739.
-	Added some annotations for Old Hungarian.
+@@@+	U15M220815.lst
+	Unicode 15.0.0 final names list.
 	This file is semi-automatically derived from UnicodeData.txt and
 	a set of manually created annotations using a script to select
 	or suppress information from the data file. The rules used
@@ -3574,7 +3558,7 @@
 @+		These are obsolete letters attested in a 19th century grammar of Komi.
 052A	CYRILLIC CAPITAL LETTER DZZHE
 052B	CYRILLIC SMALL LETTER DZZHE
-	* also used for Ossetian until 1924
+@+	* also used for Ossetian until 1924
 052C	CYRILLIC CAPITAL LETTER DCHE
 052D	CYRILLIC SMALL LETTER DCHE
 @		Khanty letters
@@ -3901,6 +3885,7 @@
 	* should not be confused with the small TAH sign used as a diacritic for some letters such as 0679
 @		Extended Arabic mark
 0616	ARABIC SMALL HIGH LIGATURE ALEF WITH LAM WITH YEH
+	% ARABIC SMALL HIGH LIGATURE ALEF WITH YEH BARREE
 	* early Persian
 @		Quranic annotation signs
 0617	ARABIC SMALL HIGH ZAIN
@@ -4085,7 +4070,7 @@
 	* Kazakh, Jawi
 	* forms digraphs
 @		Digraphic letters for Kazakh
-@+		Use of these characters is discouraged. They were encoded for Kazakh digraphs, but their decompositions do not reflect the preferred order of representation. Accordingly, the representation of these Kazakh digraphs should instead use the preferred two-character spellings with the correct order of elements.
+@+		These characters were encoded for Kazakh digraphs, but their compatibility decompositions do not reflect the preferred order of representation. Accordingly, the representation of these Kazakh digraphs should instead use the preferred two-character spellings with the correct order of elements.
 0675	ARABIC LETTER HIGH HAMZA ALEF
 	* preferred spelling is 0674 0627
 	# 0627 0674
@@ -4215,7 +4200,7 @@
 	* Uyghur, Kazakh, Moroccan Arabic, early Jawi, early Persian, ...
 06AE	ARABIC LETTER KAF WITH THREE DOTS BELOW
 	* Berber, early Persian
-	* Pegon alternative for 068A
+	* Pegon alternative for 08B4
 06AF	ARABIC LETTER GAF
 	* Persian, Urdu, ...
 06B0	ARABIC LETTER GAF WITH RING
@@ -10158,18 +10143,22 @@
 19AA	NEW TAI LUE LETTER HIGH SUA
 19AB	NEW TAI LUE LETTER LOW SUA
 	* a labialized consonant cluster
-@		Vowel signs
+@		Vowels
 19B0	NEW TAI LUE VOWEL SIGN VOWEL SHORTENER
 19B1	NEW TAI LUE VOWEL SIGN AA
 19B2	NEW TAI LUE VOWEL SIGN II
 19B3	NEW TAI LUE VOWEL SIGN U
 19B4	NEW TAI LUE VOWEL SIGN UU
 19B5	NEW TAI LUE VOWEL SIGN E
+	* precedes consonant in visual order
 19B6	NEW TAI LUE VOWEL SIGN AE
+	* precedes consonant in visual order
 19B7	NEW TAI LUE VOWEL SIGN O
+	* precedes consonant in visual order
 19B8	NEW TAI LUE VOWEL SIGN OA
 19B9	NEW TAI LUE VOWEL SIGN UE
 19BA	NEW TAI LUE VOWEL SIGN AY
+	* precedes consonant in visual order
 19BB	NEW TAI LUE VOWEL SIGN AAY
 19BC	NEW TAI LUE VOWEL SIGN UY
 19BD	NEW TAI LUE VOWEL SIGN OY
@@ -13035,7 +13024,7 @@
 	x (asterisk - 002A)
 	x (combining asterisk below - 0359)
 204F	REVERSED SEMICOLON
-	* also used in Sindhi
+	* used occasionally in Sindhi when Sindhi is written in the Arabic script
 	x (semicolon - 003B)
 	x (arabic semicolon - 061B)
 2050	CLOSE UP
@@ -13423,7 +13412,7 @@
 	= the set of complex numbers
 	# <font> 0043 latin capital letter c
 2103	DEGREE CELSIUS
-	= degrees Centigrade
+	= degrees centigrade
 	# 00B0 0043
 2104	CENTRE LINE SYMBOL
 	= clone
@@ -19328,7 +19317,8 @@
 	x (modifier letter short equals sign - A78A)
 @		Reversed punctuation
 2E41	REVERSED COMMA
-	* also used in Sindhi
+	* Old Hungarian
+	* used occasionally in Sindhi when Sindhi is written in the Arabic script
 	x (comma - 002C)
 	x (arabic comma - 060C)
 2E42	DOUBLE LOW-REVERSED-9 QUOTATION MARK
@@ -19365,7 +19355,7 @@
 	x (paragraphos - 2E0F)
 	x (capitulum - 2E3F)
 2E4E	PUNCTUS ELEVATUS MARK
-@+		This mark indicates a major intermediate pause where the sensus is complete but the sentence is not; this is similar in some regards to the modern use of a semicolon.
+@+		* This mark indicates a major intermediate pause where the sensus is complete but the sentence is not; this is similar in some regards to the modern use of a semicolon.
 2E4F	CORNISH VERSE DIVIDER
 2E50	CROSS PATTY WITH RIGHT CROSSBAR
 	x (maltese cross - 2720)
@@ -25562,6 +25552,7 @@ AB2E	ETHIOPIC SYLLABLE BBO
 @@	AB30	Latin Extended-E	AB6F
 @		Letters for German dialectology
 AB30	LATIN SMALL LETTER BARRED ALPHA
+@+		* This letter is a Latin alpha with a horizontal strikethrough bar. In some font designs, the bar might not extend beyond the edge of the letter, and in such cases, the letter should not be confused with a ligature of epsilon and iota.
 AB31	LATIN SMALL LETTER A REVERSED-SCHWA
 AB32	LATIN SMALL LETTER BLACKLETTER E
 AB33	LATIN SMALL LETTER BARRED E
@@ -35030,7 +35021,7 @@ FFFF	<not a character>
 11B07	DEVANAGARI SIGN WESTERN NINE-LIKE BHALE
 11B08	DEVANAGARI SIGN REVERSED NINE-LIKE BHALE
 11B09	DEVANAGARI SIGN MINDU
-	x (devanagari digit zero - 0966)	
+	x (devanagari digit zero - 0966)
 @@	11C00	Bhaiksuki	11C6F
 @		Independent vowels
 11C00	BHAIKSUKI LETTER A
@@ -35473,7 +35464,7 @@ FFFF	<not a character>
 11F3E	KAWI VOWEL SIGN E
 11F3F	KAWI VOWEL SIGN AI
 11F40	KAWI VOWEL SIGN EU
-	* represents schwa [ǝ]
+	* represents schwa [ə]
 @		Viramas
 11F41	KAWI SIGN KILLER
 	* vowel killer, always rendered visibly

UnicodeJsps/src/main/resources/org/unicode/jsp/StandardizedVariants.txt

@@ -1,5 +1,5 @@
 # StandardizedVariants-15.0.0.txt
-# Date: 2022-01-28, 21:31:00 GMT [KW]
+# Date: 2022-08-16, 19:08:00 GMT [KW]
 # © 2022 Unicode®, Inc.
 # For terms of use, see https://www.unicode.org/terms_of_use.html
 #
@@ -364,10 +364,10 @@ A868 FE00; phags-pa letter reversed shaping subjoined ya; # PHAGS-PA SUBJOINED L
 
 # Egyptian hieroglyph expanded variants
 
-13443 FE00; expanded ; # LOST SIGN
-13444 FE00; expanded ; # HALF LOST SIGN
-13445 FE00; expanded ; # TALL LOST SIGN
-13446 FE00; expanded ; # WIDE LOST SIGN
+13443 FE00; expanded ; # EGYPTIAN HIEROGLYPH LOST SIGN
+13444 FE00; expanded ; # EGYPTIAN HIEROGLYPH HALF LOST SIGN
+13445 FE00; expanded ; # EGYPTIAN HIEROGLYPH TALL LOST SIGN
+13446 FE00; expanded ; # EGYPTIAN HIEROGLYPH WIDE LOST SIGN
 
 # CJK compatibility ideographs
 

UnicodeJsps/src/main/resources/org/unicode/jsp/confusables.txt

@@ -1,5 +1,5 @@
-# confusables.txt
-# Date: 2022-05-18, 21:51:56 GMT
+# confusables.txt
+# Date: 2022-08-26, 16:49:08 GMT
 # © 2022 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use, see https://www.unicode.org/terms_of_use.html
@@ -7535,10 +7535,10 @@ FA7E ;	5944 ;	MA	# ( 奄 → 奄 ) CJK COMPATIBILITY IDEOGRAPH-FA7E → CJK UNIF
 
 F90C ;	5948 ;	MA	# ( 奈 → 奈 ) CJK COMPATIBILITY IDEOGRAPH-F90C → CJK UNIFIED IDEOGRAPH-5948	# 
 
-F909 ;	5951 ;	MA	# ( 契 → 契 ) CJK COMPATIBILITY IDEOGRAPH-F909 → CJK UNIFIED IDEOGRAPH-5951	# 
-
 FA7F ;	5954 ;	MA	# ( 奔 → 奔 ) CJK COMPATIBILITY IDEOGRAPH-FA7F → CJK UNIFIED IDEOGRAPH-5954	# 
 
+F909 ;	5951 ;	MA	# ( 契 → 契 ) CJK COMPATIBILITY IDEOGRAPH-F909 → CJK UNIFIED IDEOGRAPH-5951	# 
+
 2F85F ;	5962 ;	MA	# ( 奢 → 奢 ) CJK COMPATIBILITY IDEOGRAPH-2F85F → CJK UNIFIED IDEOGRAPH-5962	# 
 
 F981 ;	5973 ;	MA	# ( 女 → 女 ) CJK COMPATIBILITY IDEOGRAPH-F981 → CJK UNIFIED IDEOGRAPH-5973	#