split tools and utils

1 files changed, 318 insertions, 0 deletions

diff --git a/tools/DerivedJoiningType.txt b/tools/DerivedJoiningType.txt
new file mode 100644
index 000000000..d4dcc85f6
--- /dev/null
+++ b/tools/DerivedJoiningType.txt
@@ -0,0 +1,318 @@
+# DerivedJoiningType-5.2.0.txt
+# Date: 2009-05-28, 20:37:39 GMT [MD]
+#
+# Unicode Character Database
+# Copyright (c) 1991-2009 Unicode, Inc.
+# For terms of use, see http://www.unicode.org/terms_of_use.html
+# For documentation, see http://www.unicode.org/reports/tr44/
+
+# ================================================
+
+#	Type T is derived, as described in ArabicShaping.txt
+
+#  All code points not explicitly listed for Joining_Type
+#  have the value Non_Joining (U).
+
+# @missing: 0000..10FFFF; Non_Joining
+
+# ================================================
+
+# Joining_Type=Join_Causing
+
+0640          ; C # Lm       ARABIC TATWEEL
+07FA          ; C # Lm       NKO LAJANYALAN
+200D          ; C # Cf       ZERO WIDTH JOINER
+
+# Total code points: 3
+
+# ================================================
+
+# Joining_Type=Dual_Joining
+
+0626          ; D # Lo       ARABIC LETTER YEH WITH HAMZA ABOVE
+0628          ; D # Lo       ARABIC LETTER BEH
+062A..062E    ; D # Lo   [5] ARABIC LETTER TEH..ARABIC LETTER KHAH
+0633..063F    ; D # Lo  [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE
+0641..0647    ; D # Lo   [7] ARABIC LETTER FEH..ARABIC LETTER HEH
+0649..064A    ; D # Lo   [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH
+066E..066F    ; D # Lo   [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF
+0678..0687    ; D # Lo  [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH
+069A..06BF    ; D # Lo  [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE
+06C1..06C2    ; D # Lo   [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE
+06CC          ; D # Lo       ARABIC LETTER FARSI YEH
+06CE          ; D # Lo       ARABIC LETTER YEH WITH SMALL V
+06D0..06D1    ; D # Lo   [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW
+06FA..06FC    ; D # Lo   [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW
+06FF          ; D # Lo       ARABIC LETTER HEH WITH INVERTED V
+0712..0714    ; D # Lo   [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI
+071A..071D    ; D # Lo   [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH
+071F..0727    ; D # Lo   [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE
+0729          ; D # Lo       SYRIAC LETTER QAPH
+072B          ; D # Lo       SYRIAC LETTER SHIN
+072D..072E    ; D # Lo   [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL
+074E..0758    ; D # Lo  [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW
+075C..076A    ; D # Lo  [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR
+076D..0770    ; D # Lo   [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS
+0772          ; D # Lo       ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE
+0775..0777    ; D # Lo   [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW
+077A..077F    ; D # Lo   [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE
+07CA..07EA    ; D # Lo  [33] NKO LETTER A..NKO LETTER JONA RA
+
+# Total code points: 188
+
+# ================================================
+
+# Joining_Type=Right_Joining
+
+0622..0625    ; R # Lo   [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW
+0627          ; R # Lo       ARABIC LETTER ALEF
+0629          ; R # Lo       ARABIC LETTER TEH MARBUTA
+062F..0632    ; R # Lo   [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN
+0648          ; R # Lo       ARABIC LETTER WAW
+0671..0673    ; R # Lo   [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW
+0675..0677    ; R # Lo   [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE
+0688..0699    ; R # Lo  [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE
+06C0          ; R # Lo       ARABIC LETTER HEH WITH YEH ABOVE
+06C3..06CB    ; R # Lo   [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE
+06CD          ; R # Lo       ARABIC LETTER YEH WITH TAIL
+06CF          ; R # Lo       ARABIC LETTER WAW WITH DOT ABOVE
+06D2..06D3    ; R # Lo   [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE
+06D5          ; R # Lo       ARABIC LETTER AE
+06EE..06EF    ; R # Lo   [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V
+0710          ; R # Lo       SYRIAC LETTER ALAPH
+0715..0719    ; R # Lo   [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN
+071E          ; R # Lo       SYRIAC LETTER YUDH HE
+0728          ; R # Lo       SYRIAC LETTER SADHE
+072A          ; R # Lo       SYRIAC LETTER RISH
+072C          ; R # Lo       SYRIAC LETTER TAW
+072F          ; R # Lo       SYRIAC LETTER PERSIAN DHALATH
+074D          ; R # Lo       SYRIAC LETTER SOGDIAN ZHAIN
+0759..075B    ; R # Lo   [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE
+076B..076C    ; R # Lo   [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE
+0771          ; R # Lo       ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS
+0773..0774    ; R # Lo   [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE
+0778..0779    ; R # Lo   [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE
+
+# Total code points: 74
+
+# ================================================
+
+# Joining_Type=Transparent
+
+00AD          ; T # Cf       SOFT HYPHEN
+0300..036F    ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X
+0483..0487    ; T # Mn   [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE
+0488..0489    ; T # Me   [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN
+0591..05BD    ; T # Mn  [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG
+05BF          ; T # Mn       HEBREW POINT RAFE
+05C1..05C2    ; T # Mn   [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT
+05C4..05C5    ; T # Mn   [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT
+05C7          ; T # Mn       HEBREW POINT QAMATS QATAN
+0610..061A    ; T # Mn  [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA
+064B..065E    ; T # Mn  [20] ARABIC FATHATAN..ARABIC FATHA WITH TWO DOTS
+0670          ; T # Mn       ARABIC LETTER SUPERSCRIPT ALEF
+06D6..06DC    ; T # Mn   [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN
+06DE          ; T # Me       ARABIC START OF RUB EL HIZB
+06DF..06E4    ; T # Mn   [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA
+06E7..06E8    ; T # Mn   [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON
+06EA..06ED    ; T # Mn   [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM
+070F          ; T # Cf       SYRIAC ABBREVIATION MARK
+0711          ; T # Mn       SYRIAC LETTER SUPERSCRIPT ALAPH
+0730..074A    ; T # Mn  [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH
+07A6..07B0    ; T # Mn  [11] THAANA ABAFILI..THAANA SUKUN
+07EB..07F3    ; T # Mn   [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE
+0816..0819    ; T # Mn   [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH
+081B..0823    ; T # Mn   [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A
+0825..0827    ; T # Mn   [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U
+0829..082D    ; T # Mn   [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA
+0900..0902    ; T # Mn   [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA
+093C          ; T # Mn       DEVANAGARI SIGN NUKTA
+0941..0948    ; T # Mn   [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI
+094D          ; T # Mn       DEVANAGARI SIGN VIRAMA
+0951..0955    ; T # Mn   [5] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN CANDRA LONG E
+0962..0963    ; T # Mn   [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL
+0981          ; T # Mn       BENGALI SIGN CANDRABINDU
+09BC          ; T # Mn       BENGALI SIGN NUKTA
+09C1..09C4    ; T # Mn   [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR
+09CD          ; T # Mn       BENGALI SIGN VIRAMA
+09E2..09E3    ; T # Mn   [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL
+0A01..0A02    ; T # Mn   [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI
+0A3C          ; T # Mn       GURMUKHI SIGN NUKTA
+0A41..0A42    ; T # Mn   [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU
+0A47..0A48    ; T # Mn   [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI
+0A4B..0A4D    ; T # Mn   [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA
+0A51          ; T # Mn       GURMUKHI SIGN UDAAT
+0A70..0A71    ; T # Mn   [2] GURMUKHI TIPPI..GURMUKHI ADDAK
+0A75          ; T # Mn       GURMUKHI SIGN YAKASH
+0A81..0A82    ; T # Mn   [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA
+0ABC          ; T # Mn       GUJARATI SIGN NUKTA
+0AC1..0AC5    ; T # Mn   [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E
+0AC7..0AC8    ; T # Mn   [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI
+0ACD          ; T # Mn       GUJARATI SIGN VIRAMA
+0AE2..0AE3    ; T # Mn   [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL
+0B01          ; T # Mn       ORIYA SIGN CANDRABINDU
+0B3C          ; T # Mn       ORIYA SIGN NUKTA
+0B3F          ; T # Mn       ORIYA VOWEL SIGN I
+0B41..0B44    ; T # Mn   [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR
+0B4D          ; T # Mn       ORIYA SIGN VIRAMA
+0B56          ; T # Mn       ORIYA AI LENGTH MARK
+0B62..0B63    ; T # Mn   [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL
+0B82          ; T # Mn       TAMIL SIGN ANUSVARA
+0BC0          ; T # Mn       TAMIL VOWEL SIGN II
+0BCD          ; T # Mn       TAMIL SIGN VIRAMA
+0C3E..0C40    ; T # Mn   [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II
+0C46..0C48    ; T # Mn   [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI
+0C4A..0C4D    ; T # Mn   [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA
+0C55..0C56    ; T # Mn   [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK
+0C62..0C63    ; T # Mn   [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL
+0CBC          ; T # Mn       KANNADA SIGN NUKTA
+0CBF          ; T # Mn       KANNADA VOWEL SIGN I
+0CC6          ; T # Mn       KANNADA VOWEL SIGN E
+0CCC..0CCD    ; T # Mn   [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA
+0CE2..0CE3    ; T # Mn   [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
+0D41..0D44    ; T # Mn   [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR
+0D4D          ; T # Mn       MALAYALAM SIGN VIRAMA
+0D62..0D63    ; T # Mn   [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL
+0DCA          ; T # Mn       SINHALA SIGN AL-LAKUNA
+0DD2..0DD4    ; T # Mn   [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA
+0DD6          ; T # Mn       SINHALA VOWEL SIGN DIGA PAA-PILLA
+0E31          ; T # Mn       THAI CHARACTER MAI HAN-AKAT
+0E34..0E3A    ; T # Mn   [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU
+0E47..0E4E    ; T # Mn   [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN
+0EB1          ; T # Mn       LAO VOWEL SIGN MAI KAN
+0EB4..0EB9    ; T # Mn   [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU
+0EBB..0EBC    ; T # Mn   [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO
+0EC8..0ECD    ; T # Mn   [6] LAO TONE MAI EK..LAO NIGGAHITA
+0F18..0F19    ; T # Mn   [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS
+0F35          ; T # Mn       TIBETAN MARK NGAS BZUNG NYI ZLA
+0F37          ; T # Mn       TIBETAN MARK NGAS BZUNG SGOR RTAGS
+0F39          ; T # Mn       TIBETAN MARK TSA -PHRU
+0F71..0F7E    ; T # Mn  [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO
+0F80..0F84    ; T # Mn   [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA
+0F86..0F87    ; T # Mn   [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS
+0F90..0F97    ; T # Mn   [8] TIBETAN SUBJOINED LETTER KA..TIBETAN SUBJOINED LETTER JA
+0F99..0FBC    ; T # Mn  [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA
+0FC6          ; T # Mn       TIBETAN SYMBOL PADMA GDAN
+102D..1030    ; T # Mn   [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU
+1032..1037    ; T # Mn   [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW
+1039..103A    ; T # Mn   [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT
+103D..103E    ; T # Mn   [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA
+1058..1059    ; T # Mn   [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL
+105E..1060    ; T # Mn   [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA
+1071..1074    ; T # Mn   [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE
+1082          ; T # Mn       MYANMAR CONSONANT SIGN SHAN MEDIAL WA
+1085..1086    ; T # Mn   [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y
+108D          ; T # Mn       MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE
+109D          ; T # Mn       MYANMAR VOWEL SIGN AITON AI
+135F          ; T # Mn       ETHIOPIC COMBINING GEMINATION MARK
+1712..1714    ; T # Mn   [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA
+1732..1734    ; T # Mn   [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD
+1752..1753    ; T # Mn   [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U
+1772..1773    ; T # Mn   [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U
+17B4..17B5    ; T # Cf   [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
+17B7..17BD    ; T # Mn   [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA
+17C6          ; T # Mn       KHMER SIGN NIKAHIT
+17C9..17D3    ; T # Mn  [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT
+17DD          ; T # Mn       KHMER SIGN ATTHACAN
+180B..180D    ; T # Mn   [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
+18A9          ; T # Mn       MONGOLIAN LETTER ALI GALI DAGALGA
+1920..1922    ; T # Mn   [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U
+1927..1928    ; T # Mn   [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O
+1932          ; T # Mn       LIMBU SMALL LETTER ANUSVARA
+1939..193B    ; T # Mn   [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I
+1A17..1A18    ; T # Mn   [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U
+1A56          ; T # Mn       TAI THAM CONSONANT SIGN MEDIAL LA
+1A58..1A5E    ; T # Mn   [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA
+1A60          ; T # Mn       TAI THAM SIGN SAKOT
+1A62          ; T # Mn       TAI THAM VOWEL SIGN MAI SAT
+1A65..1A6C    ; T # Mn   [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW
+1A73..1A7C    ; T # Mn  [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN
+1A7F          ; T # Mn       TAI THAM COMBINING CRYPTOGRAMMIC DOT
+1B00..1B03    ; T # Mn   [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG
+1B34          ; T # Mn       BALINESE SIGN REREKAN
+1B36..1B3A    ; T # Mn   [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA
+1B3C          ; T # Mn       BALINESE VOWEL SIGN LA LENGA
+1B42          ; T # Mn       BALINESE VOWEL SIGN PEPET
+1B6B..1B73    ; T # Mn   [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG
+1B80..1B81    ; T # Mn   [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR
+1BA2..1BA5    ; T # Mn   [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU
+1BA8..1BA9    ; T # Mn   [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG
+1C2C..1C33    ; T # Mn   [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T
+1C36..1C37    ; T # Mn   [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA
+1CD0..1CD2    ; T # Mn   [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA
+1CD4..1CE0    ; T # Mn  [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA
+1CE2..1CE8    ; T # Mn   [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL
+1CED          ; T # Mn       VEDIC SIGN TIRYAK
+1DC0..1DE6    ; T # Mn  [39] COMBINING DOTTED GRAVE ACCENT..COMBINING LATIN SMALL LETTER Z
+1DFD..1DFF    ; T # Mn   [3] COMBINING ALMOST EQUAL TO BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
+200B          ; T # Cf       ZERO WIDTH SPACE
+200E..200F    ; T # Cf   [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK
+202A..202E    ; T # Cf   [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE
+2060..2064    ; T # Cf   [5] WORD JOINER..INVISIBLE PLUS
+206A..206F    ; T # Cf   [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES
+20D0..20DC    ; T # Mn  [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE
+20DD..20E0    ; T # Me   [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH
+20E1          ; T # Mn       COMBINING LEFT RIGHT ARROW ABOVE
+20E2..20E4    ; T # Me   [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE
+20E5..20F0    ; T # Mn  [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE
+2CEF..2CF1    ; T # Mn   [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS
+2DE0..2DFF    ; T # Mn  [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS
+302A..302F    ; T # Mn   [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK
+3099..309A    ; T # Mn   [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
+A66F          ; T # Mn       COMBINING CYRILLIC VZMET
+A670..A672    ; T # Me   [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN
+A67C..A67D    ; T # Mn   [2] COMBINING CYRILLIC KAVYKA..COMBINING CYRILLIC PAYEROK
+A6F0..A6F1    ; T # Mn   [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS
+A802          ; T # Mn       SYLOTI NAGRI SIGN DVISVARA
+A806          ; T # Mn       SYLOTI NAGRI SIGN HASANTA
+A80B          ; T # Mn       SYLOTI NAGRI SIGN ANUSVARA
+A825..A826    ; T # Mn   [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E
+A8C4          ; T # Mn       SAURASHTRA SIGN VIRAMA
+A8E0..A8F1    ; T # Mn  [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA
+A926..A92D    ; T # Mn   [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU
+A947..A951    ; T # Mn  [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R
+A980..A982    ; T # Mn   [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR
+A9B3          ; T # Mn       JAVANESE SIGN CECAK TELU
+A9B6..A9B9    ; T # Mn   [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT
+A9BC          ; T # Mn       JAVANESE VOWEL SIGN PEPET
+AA29..AA2E    ; T # Mn   [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE
+AA31..AA32    ; T # Mn   [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE
+AA35..AA36    ; T # Mn   [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA
+AA43          ; T # Mn       CHAM CONSONANT SIGN FINAL NG
+AA4C          ; T # Mn       CHAM CONSONANT SIGN FINAL M
+AAB0          ; T # Mn       TAI VIET MAI KANG
+AAB2..AAB4    ; T # Mn   [3] TAI VIET VOWEL I..TAI VIET VOWEL U
+AAB7..AAB8    ; T # Mn   [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA
+AABE..AABF    ; T # Mn   [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK
+AAC1          ; T # Mn       TAI VIET TONE MAI THO
+ABE5          ; T # Mn       MEETEI MAYEK VOWEL SIGN ANAP
+ABE8          ; T # Mn       MEETEI MAYEK VOWEL SIGN UNAP
+ABED          ; T # Mn       MEETEI MAYEK APUN IYEK
+FB1E          ; T # Mn       HEBREW POINT JUDEO-SPANISH VARIKA
+FE00..FE0F    ; T # Mn  [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
+FE20..FE26    ; T # Mn   [7] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON
+FEFF          ; T # Cf       ZERO WIDTH NO-BREAK SPACE
+FFF9..FFFB    ; T # Cf   [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR
+101FD         ; T # Mn       PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE
+10A01..10A03  ; T # Mn   [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R
+10A05..10A06  ; T # Mn   [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O
+10A0C..10A0F  ; T # Mn   [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA
+10A38..10A3A  ; T # Mn   [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW
+10A3F         ; T # Mn       KHAROSHTHI VIRAMA
+11080..11081  ; T # Mn   [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA
+110B3..110B6  ; T # Mn   [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI
+110B9..110BA  ; T # Mn   [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA
+110BD         ; T # Cf       KAITHI NUMBER SIGN
+1D167..1D169  ; T # Mn   [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3
+1D173..1D17A  ; T # Cf   [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
+1D17B..1D182  ; T # Mn   [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE
+1D185..1D18B  ; T # Mn   [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
+1D1AA..1D1AD  ; T # Mn   [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
+1D242..1D244  ; T # Mn   [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME
+E0001         ; T # Cf       LANGUAGE TAG
+E0020..E007F  ; T # Cf  [96] TAG SPACE..CANCEL TAG
+E0100..E01EF  ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
+
+# Total code points: 1308
+
+# EOF