libgrapheme

unicode string library
git clone git://git.suckless.org/libgrapheme
Log | Files | Refs | README | LICENSE

commit e16c296a291c77c4ff0d45407406ca3b48dacea4
parent 5910bc61b6f065cab26682993a76904c37a0f86b
Author: Laslo Hunhold <dev@frign.de>
Date:   Fri, 10 Jun 2022 21:11:43 +0200

Implement sentence-segmentation

After solving the word segmentation problems implementing sentence
segmentations was straightforward given it follows similar patterns
and idioms (or maybe my mind just adapted to the immense complexity
that Unicode presents).

The data, as usual, is highly compressed (~97.08%) and only adds around
30K in total to the library.

Signed-off-by: Laslo Hunhold <dev@frign.de>

Diffstat:
MMakefile | 24++++++++++++++++++++++++
Abenchmark/sentence.c | 52++++++++++++++++++++++++++++++++++++++++++++++++++++
Adata/SentenceBreakProperty.txt | 2891+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Adata/SentenceBreakTest.txt | 530+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Agen/sentence-test.c | 19+++++++++++++++++++
Agen/sentence.c | 94+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Mgrapheme.h | 2++
Asrc/sentence.c | 366+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Atest/sentence.c | 17+++++++++++++++++
9 files changed, 3995 insertions(+), 0 deletions(-)

diff --git a/Makefile b/Makefile @@ -6,6 +6,7 @@ include config.mk BENCHMARK =\ benchmark/character\ + benchmark/sentence\ benchmark/utf8-decode\ benchmark/word\ @@ -13,23 +14,29 @@ DATA =\ data/emoji-data.txt\ data/GraphemeBreakProperty.txt\ data/GraphemeBreakTest.txt\ + data/SentenceBreakProperty.txt\ + data/SentenceBreakTest.txt\ data/WordBreakProperty.txt\ data/WordBreakTest.txt\ GEN =\ gen/character\ gen/character-test\ + gen/sentence\ + gen/sentence-test\ gen/word\ gen/word-test\ SRC =\ src/character\ + src/sentence\ src/utf8\ src/util\ src/word\ TEST =\ test/character\ + test/sentence\ test/utf8-decode\ test/utf8-encode\ test/word\ @@ -46,37 +53,48 @@ all: libgrapheme.a libgrapheme.so benchmark/character.o: benchmark/character.c config.mk gen/character-test.h grapheme.h benchmark/util.h benchmark/utf8-decode.o: benchmark/utf8-decode.c config.mk gen/character-test.h grapheme.h benchmark/util.h +benchmark/sentence.o: benchmark/sentence.c config.mk gen/sentence-test.h grapheme.h benchmark/util.h benchmark/util.o: benchmark/util.c config.mk benchmark/util.h benchmark/word.o: benchmark/word.c config.mk gen/word-test.h grapheme.h benchmark/util.h gen/character.o: gen/character.c config.mk gen/util.h gen/character-test.o: gen/character-test.c config.mk gen/util.h +gen/sentence.o: gen/sentence.c config.mk gen/util.h +gen/sentence-test.o: gen/sentence-test.c config.mk gen/util.h gen/word.o: gen/word.c config.mk gen/util.h gen/word-test.o: gen/word-test.c config.mk gen/util.h gen/util.o: gen/util.c config.mk gen/util.h src/character.o: src/character.c config.mk gen/character.h grapheme.h src/util.h +src/sentence.o: src/sentence.c config.mk gen/sentence.h grapheme.h src/util.h src/utf8.o: src/utf8.c config.mk grapheme.h src/util.o: src/util.c config.mk gen/types.h grapheme.h src/util.h src/word.o: src/word.c config.mk gen/word.h grapheme.h src/util.h test/character.o: test/character.c config.mk gen/character-test.h grapheme.h test/util.h +test/sentence.o: test/sentence.c config.mk gen/sentence-test.h grapheme.h test/util.h test/utf8-encode.o: test/utf8-encode.c config.mk grapheme.h test/util.h test/utf8-decode.o: test/utf8-decode.c config.mk grapheme.h test/util.h test/util.o: test/util.c config.mk test/util.h test/word.o: test/word.c config.mk gen/word-test.h grapheme.h test/util.h benchmark/character: benchmark/character.o benchmark/util.o libgrapheme.a +benchmark/sentence: benchmark/sentence.o benchmark/util.o libgrapheme.a benchmark/utf8-decode: benchmark/utf8-decode.o benchmark/util.o libgrapheme.a benchmark/word: benchmark/word.o benchmark/util.o libgrapheme.a gen/character: gen/character.o gen/util.o gen/character-test: gen/character-test.o gen/util.o +gen/sentence: gen/sentence.o gen/util.o +gen/sentence-test: gen/sentence-test.o gen/util.o gen/word: gen/word.o gen/util.o gen/word-test: gen/word-test.o gen/util.o test/character: test/character.o test/util.o libgrapheme.a +test/sentence: test/sentence.o test/util.o libgrapheme.a test/utf8-encode: test/utf8-encode.o test/util.o libgrapheme.a test/utf8-decode: test/utf8-decode.o test/util.o libgrapheme.a test/word: test/word.o test/util.o libgrapheme.a gen/character.h: data/emoji-data.txt data/GraphemeBreakProperty.txt gen/character gen/character-test.h: data/GraphemeBreakTest.txt gen/character-test +gen/sentence.h: data/SentenceBreakProperty.txt gen/sentence +gen/sentence-test.h: data/SentenceBreakTest.txt gen/sentence-test gen/word.h: data/WordBreakProperty.txt gen/word gen/word-test.h: data/WordBreakTest.txt gen/word-test @@ -89,6 +107,12 @@ data/GraphemeBreakProperty.txt: data/GraphemeBreakTest.txt: wget -O $@ https://www.unicode.org/Public/14.0.0/ucd/auxiliary/GraphemeBreakTest.txt +data/SentenceBreakProperty.txt: + wget -O $@ https://www.unicode.org/Public/14.0.0/ucd/auxiliary/SentenceBreakProperty.txt + +data/SentenceBreakTest.txt: + wget -O $@ https://www.unicode.org/Public/14.0.0/ucd/auxiliary/SentenceBreakTest.txt + data/WordBreakProperty.txt: wget -O $@ https://www.unicode.org/Public/14.0.0/ucd/auxiliary/WordBreakProperty.txt diff --git a/benchmark/sentence.c b/benchmark/sentence.c @@ -0,0 +1,52 @@ +/* See LICENSE file for copyright and license details. */ +#include <errno.h> +#include <math.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include "../grapheme.h" +#include "../gen/sentence-test.h" +#include "util.h" + +#define NUM_ITERATIONS 100000 + +struct break_benchmark_payload { + uint_least32_t *buf; + size_t buflen; +}; + +void +libgrapheme(const void *payload) +{ + const struct break_benchmark_payload *p = payload; + size_t off; + + for (off = 0; off < p->buflen; ) { + off += grapheme_next_sentence_break(p->buf + off, p->buflen - off); + } +} + +int +main(int argc, char *argv[]) +{ + struct break_benchmark_payload p; + double baseline = (double)NAN; + + (void)argc; + + if ((p.buf = generate_cp_test_buffer(sentence_break_test, + LEN(sentence_break_test), + &(p.buflen))) == NULL) { + return 1; + } + + printf("%s\n", argv[0]); + run_benchmark(libgrapheme, &p, "libgrapheme ", NULL, "codepoint", + &baseline, NUM_ITERATIONS, p.buflen - 1); + + free(p.buf); + + return 0; +} diff --git a/data/SentenceBreakProperty.txt b/data/SentenceBreakProperty.txt @@ -0,0 +1,2891 @@ +# SentenceBreakProperty-14.0.0.txt +# Date: 2021-08-12, 23:13:21 GMT +# © 2021 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 http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ + +# ================================================ + +# Property: Sentence_Break + +# All code points not explicitly listed for Sentence_Break +# have the value Other (XX). + +# @missing: 0000..10FFFF; Other + +# ================================================ + +000D ; CR # Cc <control-000D> + +# Total code points: 1 + +# ================================================ + +000A ; LF # Cc <control-000A> + +# Total code points: 1 + +# ================================================ + +0300..036F ; Extend # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; Extend # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; Extend # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; Extend # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; Extend # Mn HEBREW POINT RAFE +05C1..05C2 ; Extend # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; Extend # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; Extend # Mn HEBREW POINT QAMATS QATAN +0610..061A ; Extend # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +064B..065F ; Extend # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW +0670 ; Extend # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; Extend # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DF..06E4 ; Extend # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; Extend # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; Extend # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +0711 ; Extend # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; Extend # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; Extend # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; Extend # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +07FD ; Extend # Mn NKO DANTAYALAN +0816..0819 ; Extend # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; Extend # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; Extend # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; Extend # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0859..085B ; Extend # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +0898..089F ; Extend # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08CA..08E1 ; Extend # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA +08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA +0903 ; Extend # Mc DEVANAGARI SIGN VISARGA +093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE +093B ; Extend # Mc DEVANAGARI VOWEL SIGN OOE +093C ; Extend # Mn DEVANAGARI SIGN NUKTA +093E..0940 ; Extend # Mc [3] DEVANAGARI VOWEL SIGN AA..DEVANAGARI VOWEL SIGN II +0941..0948 ; Extend # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +0949..094C ; Extend # Mc [4] DEVANAGARI VOWEL SIGN CANDRA O..DEVANAGARI VOWEL SIGN AU +094D ; Extend # Mn DEVANAGARI SIGN VIRAMA +094E..094F ; Extend # Mc [2] DEVANAGARI VOWEL SIGN PRISHTHAMATRA E..DEVANAGARI VOWEL SIGN AW +0951..0957 ; Extend # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE +0962..0963 ; Extend # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; Extend # Mn BENGALI SIGN CANDRABINDU +0982..0983 ; Extend # Mc [2] BENGALI SIGN ANUSVARA..BENGALI SIGN VISARGA +09BC ; Extend # Mn BENGALI SIGN NUKTA +09BE..09C0 ; Extend # Mc [3] BENGALI VOWEL SIGN AA..BENGALI VOWEL SIGN II +09C1..09C4 ; Extend # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09C7..09C8 ; Extend # Mc [2] BENGALI VOWEL SIGN E..BENGALI VOWEL SIGN AI +09CB..09CC ; Extend # Mc [2] BENGALI VOWEL SIGN O..BENGALI VOWEL SIGN AU +09CD ; Extend # Mn BENGALI SIGN VIRAMA +09D7 ; Extend # Mc BENGALI AU LENGTH MARK +09E2..09E3 ; Extend # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +09FE ; Extend # Mn BENGALI SANDHI MARK +0A01..0A02 ; Extend # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A03 ; Extend # Mc GURMUKHI SIGN VISARGA +0A3C ; Extend # Mn GURMUKHI SIGN NUKTA +0A3E..0A40 ; Extend # Mc [3] GURMUKHI VOWEL SIGN AA..GURMUKHI VOWEL SIGN II +0A41..0A42 ; Extend # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; Extend # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; Extend # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; Extend # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; Extend # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; Extend # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; Extend # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0A83 ; Extend # Mc GUJARATI SIGN VISARGA +0ABC ; Extend # Mn GUJARATI SIGN NUKTA +0ABE..0AC0 ; Extend # Mc [3] GUJARATI VOWEL SIGN AA..GUJARATI VOWEL SIGN II +0AC1..0AC5 ; Extend # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; Extend # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0AC9 ; Extend # Mc GUJARATI VOWEL SIGN CANDRA O +0ACB..0ACC ; Extend # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU +0ACD ; Extend # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; Extend # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; Extend # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE +0B01 ; Extend # Mn ORIYA SIGN CANDRABINDU +0B02..0B03 ; Extend # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA +0B3C ; Extend # Mn ORIYA SIGN NUKTA +0B3E ; Extend # Mc ORIYA VOWEL SIGN AA +0B3F ; Extend # Mn ORIYA VOWEL SIGN I +0B40 ; Extend # Mc ORIYA VOWEL SIGN II +0B41..0B44 ; Extend # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B47..0B48 ; Extend # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI +0B4B..0B4C ; Extend # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU +0B4D ; Extend # Mn ORIYA SIGN VIRAMA +0B55..0B56 ; Extend # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B57 ; Extend # Mc ORIYA AU LENGTH MARK +0B62..0B63 ; Extend # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; Extend # Mn TAMIL SIGN ANUSVARA +0BBE..0BBF ; Extend # Mc [2] TAMIL VOWEL SIGN AA..TAMIL VOWEL SIGN I +0BC0 ; Extend # Mn TAMIL VOWEL SIGN II +0BC1..0BC2 ; Extend # Mc [2] TAMIL VOWEL SIGN U..TAMIL VOWEL SIGN UU +0BC6..0BC8 ; Extend # Mc [3] TAMIL VOWEL SIGN E..TAMIL VOWEL SIGN AI +0BCA..0BCC ; Extend # Mc [3] TAMIL VOWEL SIGN O..TAMIL VOWEL SIGN AU +0BCD ; Extend # Mn TAMIL SIGN VIRAMA +0BD7 ; Extend # Mc TAMIL AU LENGTH MARK +0C00 ; Extend # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE +0C01..0C03 ; Extend # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA +0C04 ; Extend # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; Extend # Mn TELUGU SIGN NUKTA +0C3E..0C40 ; Extend # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C41..0C44 ; Extend # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR +0C46..0C48 ; Extend # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; Extend # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; Extend # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; Extend # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0C81 ; Extend # Mn KANNADA SIGN CANDRABINDU +0C82..0C83 ; Extend # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA +0CBC ; Extend # Mn KANNADA SIGN NUKTA +0CBE ; Extend # Mc KANNADA VOWEL SIGN AA +0CBF ; Extend # Mn KANNADA VOWEL SIGN I +0CC0..0CC4 ; Extend # Mc [5] KANNADA VOWEL SIGN II..KANNADA VOWEL SIGN VOCALIC RR +0CC6 ; Extend # Mn KANNADA VOWEL SIGN E +0CC7..0CC8 ; Extend # Mc [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI +0CCA..0CCB ; Extend # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO +0CCC..0CCD ; Extend # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CD5..0CD6 ; Extend # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK +0CE2..0CE3 ; Extend # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D00..0D01 ; Extend # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D02..0D03 ; Extend # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA +0D3B..0D3C ; Extend # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA +0D3E..0D40 ; Extend # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II +0D41..0D44 ; Extend # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D46..0D48 ; Extend # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI +0D4A..0D4C ; Extend # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU +0D4D ; Extend # Mn MALAYALAM SIGN VIRAMA +0D57 ; Extend # Mc MALAYALAM AU LENGTH MARK +0D62..0D63 ; Extend # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0D81 ; Extend # Mn SINHALA SIGN CANDRABINDU +0D82..0D83 ; Extend # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA +0DCA ; Extend # Mn SINHALA SIGN AL-LAKUNA +0DCF..0DD1 ; Extend # Mc [3] SINHALA VOWEL SIGN AELA-PILLA..SINHALA VOWEL SIGN DIGA AEDA-PILLA +0DD2..0DD4 ; Extend # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; Extend # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0DD8..0DDF ; Extend # Mc [8] SINHALA VOWEL SIGN GAETTA-PILLA..SINHALA VOWEL SIGN GAYANUKITTA +0DF2..0DF3 ; Extend # Mc [2] SINHALA VOWEL SIGN DIGA GAETTA-PILLA..SINHALA VOWEL SIGN DIGA GAYANUKITTA +0E31 ; Extend # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; Extend # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; Extend # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; Extend # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EBC ; Extend # Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO +0EC8..0ECD ; Extend # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0F18..0F19 ; Extend # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; Extend # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; Extend # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; Extend # Mn TIBETAN MARK TSA -PHRU +0F3E..0F3F ; Extend # Mc [2] TIBETAN SIGN YAR TSHES..TIBETAN SIGN MAR TSHES +0F71..0F7E ; Extend # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F7F ; Extend # Mc TIBETAN SIGN RNAM BCAD +0F80..0F84 ; Extend # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; Extend # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F8D..0F97 ; Extend # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; Extend # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; Extend # Mn TIBETAN SYMBOL PADMA GDAN +102B..102C ; Extend # Mc [2] MYANMAR VOWEL SIGN TALL AA..MYANMAR VOWEL SIGN AA +102D..1030 ; Extend # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1031 ; Extend # Mc MYANMAR VOWEL SIGN E +1032..1037 ; Extend # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1038 ; Extend # Mc MYANMAR SIGN VISARGA +1039..103A ; Extend # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103B..103C ; Extend # Mc [2] MYANMAR CONSONANT SIGN MEDIAL YA..MYANMAR CONSONANT SIGN MEDIAL RA +103D..103E ; Extend # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1056..1057 ; Extend # Mc [2] MYANMAR VOWEL SIGN VOCALIC R..MYANMAR VOWEL SIGN VOCALIC RR +1058..1059 ; Extend # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; Extend # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1062..1064 ; Extend # Mc [3] MYANMAR VOWEL SIGN SGAW KAREN EU..MYANMAR TONE MARK SGAW KAREN KE PHO +1067..106D ; Extend # Mc [7] MYANMAR VOWEL SIGN WESTERN PWO KAREN EU..MYANMAR SIGN WESTERN PWO KAREN TONE-5 +1071..1074 ; Extend # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; Extend # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1083..1084 ; Extend # Mc [2] MYANMAR VOWEL SIGN SHAN AA..MYANMAR VOWEL SIGN SHAN E +1085..1086 ; Extend # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +1087..108C ; Extend # Mc [6] MYANMAR SIGN SHAN TONE-2..MYANMAR SIGN SHAN COUNCIL TONE-3 +108D ; Extend # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +108F ; Extend # Mc MYANMAR SIGN RUMAI PALAUNG TONE-5 +109A..109C ; Extend # Mc [3] MYANMAR SIGN KHAMTI TONE-1..MYANMAR VOWEL SIGN AITON A +109D ; Extend # Mn MYANMAR VOWEL SIGN AITON AI +135D..135F ; Extend # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; Extend # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1715 ; Extend # Mc TAGALOG SIGN PAMUDPOD +1732..1733 ; Extend # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1734 ; Extend # Mc HANUNOO SIGN PAMUDPOD +1752..1753 ; Extend # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; Extend # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; Extend # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B6 ; Extend # Mc KHMER VOWEL SIGN AA +17B7..17BD ; Extend # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17BE..17C5 ; Extend # Mc [8] KHMER VOWEL SIGN OE..KHMER VOWEL SIGN AU +17C6 ; Extend # Mn KHMER SIGN NIKAHIT +17C7..17C8 ; Extend # Mc [2] KHMER SIGN REAHMUK..KHMER SIGN YUUKALEAPINTU +17C9..17D3 ; Extend # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; Extend # Mn KHMER SIGN ATTHACAN +180B..180D ; Extend # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; Extend # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR +1885..1886 ; Extend # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +18A9 ; Extend # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; Extend # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1923..1926 ; Extend # Mc [4] LIMBU VOWEL SIGN EE..LIMBU VOWEL SIGN AU +1927..1928 ; Extend # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1929..192B ; Extend # Mc [3] LIMBU SUBJOINED LETTER YA..LIMBU SUBJOINED LETTER WA +1930..1931 ; Extend # Mc [2] LIMBU SMALL LETTER KA..LIMBU SMALL LETTER NGA +1932 ; Extend # Mn LIMBU SMALL LETTER ANUSVARA +1933..1938 ; Extend # Mc [6] LIMBU SMALL LETTER TA..LIMBU SMALL LETTER LA +1939..193B ; Extend # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; Extend # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A19..1A1A ; Extend # Mc [2] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN O +1A1B ; Extend # Mn BUGINESE VOWEL SIGN AE +1A55 ; Extend # Mc TAI THAM CONSONANT SIGN MEDIAL RA +1A56 ; Extend # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A57 ; Extend # Mc TAI THAM CONSONANT SIGN LA TANG LAI +1A58..1A5E ; Extend # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; Extend # Mn TAI THAM SIGN SAKOT +1A61 ; Extend # Mc TAI THAM VOWEL SIGN A +1A62 ; Extend # Mn TAI THAM VOWEL SIGN MAI SAT +1A63..1A64 ; Extend # Mc [2] TAI THAM VOWEL SIGN AA..TAI THAM VOWEL SIGN TALL AA +1A65..1A6C ; Extend # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A6D..1A72 ; Extend # Mc [6] TAI THAM VOWEL SIGN OY..TAI THAM VOWEL SIGN THAM AI +1A73..1A7C ; Extend # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1AB0..1ABD ; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW +1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY +1ABF..1ACE ; Extend # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B04 ; Extend # Mc BALINESE SIGN BISAH +1B34 ; Extend # Mn BALINESE SIGN REREKAN +1B35 ; Extend # Mc BALINESE VOWEL SIGN TEDUNG +1B36..1B3A ; Extend # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3B ; Extend # Mc BALINESE VOWEL SIGN RA REPA TEDUNG +1B3C ; Extend # Mn BALINESE VOWEL SIGN LA LENGA +1B3D..1B41 ; Extend # Mc [5] BALINESE VOWEL SIGN LA LENGA TEDUNG..BALINESE VOWEL SIGN TALING REPA TEDUNG +1B42 ; Extend # Mn BALINESE VOWEL SIGN PEPET +1B43..1B44 ; Extend # Mc [2] BALINESE VOWEL SIGN PEPET TEDUNG..BALINESE ADEG ADEG +1B6B..1B73 ; Extend # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; Extend # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1B82 ; Extend # Mc SUNDANESE SIGN PANGWISAD +1BA1 ; Extend # Mc SUNDANESE CONSONANT SIGN PAMINGKAL +1BA2..1BA5 ; Extend # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA6..1BA7 ; Extend # Mc [2] SUNDANESE VOWEL SIGN PANAELAENG..SUNDANESE VOWEL SIGN PANOLONG +1BA8..1BA9 ; Extend # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1BAA ; Extend # Mc SUNDANESE SIGN PAMAAEH +1BAB..1BAD ; Extend # Mn [3] SUNDANESE SIGN VIRAMA..SUNDANESE CONSONANT SIGN PASANGAN WA +1BE6 ; Extend # Mn BATAK SIGN TOMPI +1BE7 ; Extend # Mc BATAK VOWEL SIGN E +1BE8..1BE9 ; Extend # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE +1BEA..1BEC ; Extend # Mc [3] BATAK VOWEL SIGN I..BATAK VOWEL SIGN O +1BED ; Extend # Mn BATAK VOWEL SIGN KARO O +1BEE ; Extend # Mc BATAK VOWEL SIGN U +1BEF..1BF1 ; Extend # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H +1BF2..1BF3 ; Extend # Mc [2] BATAK PANGOLAT..BATAK PANONGONAN +1C24..1C2B ; Extend # Mc [8] LEPCHA SUBJOINED LETTER YA..LEPCHA VOWEL SIGN UU +1C2C..1C33 ; Extend # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C34..1C35 ; Extend # Mc [2] LEPCHA CONSONANT SIGN NYIN-DO..LEPCHA CONSONANT SIGN KANG +1C36..1C37 ; Extend # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; Extend # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; Extend # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE1 ; Extend # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA +1CE2..1CE8 ; Extend # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; Extend # Mn VEDIC SIGN TIRYAK +1CF4 ; Extend # Mn VEDIC TONE CANDRA ABOVE +1CF7 ; Extend # Mc VEDIC SIGN ATIKRAMA +1CF8..1CF9 ; Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE +1DC0..1DFF ; Extend # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200C..200D ; Extend # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER +20D0..20DC ; Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; Extend # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; Extend # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; Extend # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; Extend # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; Extend # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2D7F ; Extend # Mn TIFINAGH CONSONANT JOINER +2DE0..2DFF ; Extend # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302D ; Extend # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK +302E..302F ; Extend # Mc [2] HANGUL SINGLE DOT TONE MARK..HANGUL DOUBLE DOT TONE MARK +3099..309A ; Extend # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; Extend # Mn COMBINING CYRILLIC VZMET +A670..A672 ; Extend # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A674..A67D ; Extend # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK +A69E..A69F ; Extend # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E +A6F0..A6F1 ; Extend # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A802 ; Extend # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; Extend # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; Extend # Mn SYLOTI NAGRI SIGN ANUSVARA +A823..A824 ; Extend # Mc [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIGN I +A825..A826 ; Extend # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A827 ; Extend # Mc SYLOTI NAGRI VOWEL SIGN OO +A82C ; Extend # Mn SYLOTI NAGRI SIGN ALTERNATE HASANTA +A880..A881 ; Extend # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA +A8B4..A8C3 ; Extend # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU +A8C4..A8C5 ; Extend # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU +A8E0..A8F1 ; Extend # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A8FF ; Extend # Mn DEVANAGARI VOWEL SIGN AY +A926..A92D ; Extend # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; Extend # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A952..A953 ; Extend # Mc [2] REJANG CONSONANT SIGN H..REJANG VIRAMA +A980..A982 ; Extend # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A983 ; Extend # Mc JAVANESE SIGN WIGNYAN +A9B3 ; Extend # Mn JAVANESE SIGN CECAK TELU +A9B4..A9B5 ; Extend # Mc [2] JAVANESE VOWEL SIGN TARUNG..JAVANESE VOWEL SIGN TOLONG +A9B6..A9B9 ; Extend # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BA..A9BB ; Extend # Mc [2] JAVANESE VOWEL SIGN TALING..JAVANESE VOWEL SIGN DIRGA MURE +A9BC..A9BD ; Extend # Mn [2] JAVANESE VOWEL SIGN PEPET..JAVANESE CONSONANT SIGN KERET +A9BE..A9C0 ; Extend # Mc [3] JAVANESE CONSONANT SIGN PENGKAL..JAVANESE PANGKON +A9E5 ; Extend # Mn MYANMAR SIGN SHAN SAW +AA29..AA2E ; Extend # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA2F..AA30 ; Extend # Mc [2] CHAM VOWEL SIGN O..CHAM VOWEL SIGN AI +AA31..AA32 ; Extend # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA33..AA34 ; Extend # Mc [2] CHAM CONSONANT SIGN YA..CHAM CONSONANT SIGN RA +AA35..AA36 ; Extend # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; Extend # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; Extend # Mn CHAM CONSONANT SIGN FINAL M +AA4D ; Extend # Mc CHAM CONSONANT SIGN FINAL H +AA7B ; Extend # Mc MYANMAR SIGN PAO KAREN TONE +AA7C ; Extend # Mn MYANMAR SIGN TAI LAING TONE-2 +AA7D ; Extend # Mc MYANMAR SIGN TAI LAING TONE-5 +AAB0 ; Extend # Mn TAI VIET MAI KANG +AAB2..AAB4 ; Extend # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB7..AAB8 ; Extend # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AABE..AABF ; Extend # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC1 ; Extend # Mn TAI VIET TONE MAI THO +AAEB ; Extend # Mc MEETEI MAYEK VOWEL SIGN II +AAEC..AAED ; Extend # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI +AAEE..AAEF ; Extend # Mc [2] MEETEI MAYEK VOWEL SIGN AU..MEETEI MAYEK VOWEL SIGN AAU +AAF5 ; Extend # Mc MEETEI MAYEK VOWEL SIGN VISARGA +AAF6 ; Extend # Mn MEETEI MAYEK VIRAMA +ABE3..ABE4 ; Extend # Mc [2] MEETEI MAYEK VOWEL SIGN ONAP..MEETEI MAYEK VOWEL SIGN INAP +ABE5 ; Extend # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE6..ABE7 ; Extend # Mc [2] MEETEI MAYEK VOWEL SIGN YENAP..MEETEI MAYEK VOWEL SIGN SOUNAP +ABE8 ; Extend # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABE9..ABEA ; Extend # Mc [2] MEETEI MAYEK VOWEL SIGN CHEINAP..MEETEI MAYEK VOWEL SIGN NUNG +ABEC ; Extend # Mc MEETEI MAYEK LUM IYEK +ABED ; Extend # Mn MEETEI MAYEK APUN IYEK +FB1E ; Extend # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; Extend # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE2F ; Extend # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF +FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK +101FD ; Extend # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +102E0 ; Extend # Mn COPTIC EPACT THOUSANDS MARK +10376..1037A ; Extend # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII +10A01..10A03 ; Extend # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; Extend # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; Extend # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; Extend # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; Extend # Mn KHAROSHTHI VIRAMA +10AE5..10AE6 ; Extend # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW +10D24..10D27 ; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10EAB..10EAC ; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK +10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW +11000 ; Extend # Mc BRAHMI SIGN CANDRABINDU +11001 ; Extend # Mn BRAHMI SIGN ANUSVARA +11002 ; Extend # Mc BRAHMI SIGN VISARGA +11038..11046 ; Extend # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11070 ; Extend # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; Extend # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +1107F..11081 ; Extend # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA +11082 ; Extend # Mc KAITHI SIGN VISARGA +110B0..110B2 ; Extend # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II +110B3..110B6 ; Extend # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B7..110B8 ; Extend # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU +110B9..110BA ; Extend # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; Extend # Mn KAITHI VOWEL SIGN VOCALIC R +11100..11102 ; Extend # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA +11127..1112B ; Extend # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU +1112C ; Extend # Mc CHAKMA VOWEL SIGN E +1112D..11134 ; Extend # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11145..11146 ; Extend # Mc [2] CHAKMA VOWEL SIGN AA..CHAKMA VOWEL SIGN EI +11173 ; Extend # Mn MAHAJANI SIGN NUKTA +11180..11181 ; Extend # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA +11182 ; Extend # Mc SHARADA SIGN VISARGA +111B3..111B5 ; Extend # Mc [3] SHARADA VOWEL SIGN AA..SHARADA VOWEL SIGN II +111B6..111BE ; Extend # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O +111BF..111C0 ; Extend # Mc [2] SHARADA VOWEL SIGN AU..SHARADA SIGN VIRAMA +111C9..111CC ; Extend # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK +111CE ; Extend # Mc SHARADA VOWEL SIGN PRISHTHAMATRA E +111CF ; Extend # Mn SHARADA SIGN INVERTED CANDRABINDU +1122C..1122E ; Extend # Mc [3] KHOJKI VOWEL SIGN AA..KHOJKI VOWEL SIGN II +1122F..11231 ; Extend # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI +11232..11233 ; Extend # Mc [2] KHOJKI VOWEL SIGN O..KHOJKI VOWEL SIGN AU +11234 ; Extend # Mn KHOJKI SIGN ANUSVARA +11235 ; Extend # Mc KHOJKI SIGN VIRAMA +11236..11237 ; Extend # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; Extend # Mn KHOJKI SIGN SUKUN +112DF ; Extend # Mn KHUDAWADI SIGN ANUSVARA +112E0..112E2 ; Extend # Mc [3] KHUDAWADI VOWEL SIGN AA..KHUDAWADI VOWEL SIGN II +112E3..112EA ; Extend # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA +11300..11301 ; Extend # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU +11302..11303 ; Extend # Mc [2] GRANTHA SIGN ANUSVARA..GRANTHA SIGN VISARGA +1133B..1133C ; Extend # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA +1133E..1133F ; Extend # Mc [2] GRANTHA VOWEL SIGN AA..GRANTHA VOWEL SIGN I +11340 ; Extend # Mn GRANTHA VOWEL SIGN II +11341..11344 ; Extend # Mc [4] GRANTHA VOWEL SIGN U..GRANTHA VOWEL SIGN VOCALIC RR +11347..11348 ; Extend # Mc [2] GRANTHA VOWEL SIGN EE..GRANTHA VOWEL SIGN AI +1134B..1134D ; Extend # Mc [3] GRANTHA VOWEL SIGN OO..GRANTHA SIGN VIRAMA +11357 ; Extend # Mc GRANTHA AU LENGTH MARK +11362..11363 ; Extend # Mc [2] GRANTHA VOWEL SIGN VOCALIC L..GRANTHA VOWEL SIGN VOCALIC LL +11366..1136C ; Extend # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX +11370..11374 ; Extend # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11435..11437 ; Extend # Mc [3] NEWA VOWEL SIGN AA..NEWA VOWEL SIGN II +11438..1143F ; Extend # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11440..11441 ; Extend # Mc [2] NEWA VOWEL SIGN O..NEWA VOWEL SIGN AU +11442..11444 ; Extend # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11445 ; Extend # Mc NEWA SIGN VISARGA +11446 ; Extend # Mn NEWA SIGN NUKTA +1145E ; Extend # Mn NEWA SANDHI MARK +114B0..114B2 ; Extend # Mc [3] TIRHUTA VOWEL SIGN AA..TIRHUTA VOWEL SIGN II +114B3..114B8 ; Extend # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL +114B9 ; Extend # Mc TIRHUTA VOWEL SIGN E +114BA ; Extend # Mn TIRHUTA VOWEL SIGN SHORT E +114BB..114BE ; Extend # Mc [4] TIRHUTA VOWEL SIGN AI..TIRHUTA VOWEL SIGN AU +114BF..114C0 ; Extend # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA +114C1 ; Extend # Mc TIRHUTA SIGN VISARGA +114C2..114C3 ; Extend # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA +115AF..115B1 ; Extend # Mc [3] SIDDHAM VOWEL SIGN AA..SIDDHAM VOWEL SIGN II +115B2..115B5 ; Extend # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR +115B8..115BB ; Extend # Mc [4] SIDDHAM VOWEL SIGN E..SIDDHAM VOWEL SIGN AU +115BC..115BD ; Extend # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA +115BE ; Extend # Mc SIDDHAM SIGN VISARGA +115BF..115C0 ; Extend # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA +115DC..115DD ; Extend # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU +11630..11632 ; Extend # Mc [3] MODI VOWEL SIGN AA..MODI VOWEL SIGN II +11633..1163A ; Extend # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI +1163B..1163C ; Extend # Mc [2] MODI VOWEL SIGN O..MODI VOWEL SIGN AU +1163D ; Extend # Mn MODI SIGN ANUSVARA +1163E ; Extend # Mc MODI SIGN VISARGA +1163F..11640 ; Extend # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA +116AB ; Extend # Mn TAKRI SIGN ANUSVARA +116AC ; Extend # Mc TAKRI SIGN VISARGA +116AD ; Extend # Mn TAKRI VOWEL SIGN AA +116AE..116AF ; Extend # Mc [2] TAKRI VOWEL SIGN I..TAKRI VOWEL SIGN II +116B0..116B5 ; Extend # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU +116B6 ; Extend # Mc TAKRI SIGN VIRAMA +116B7 ; Extend # Mn TAKRI SIGN NUKTA +1171D..1171F ; Extend # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA +11720..11721 ; Extend # Mc [2] AHOM VOWEL SIGN A..AHOM VOWEL SIGN AA +11722..11725 ; Extend # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU +11726 ; Extend # Mc AHOM VOWEL SIGN E +11727..1172B ; Extend # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +1182C..1182E ; Extend # Mc [3] DOGRA VOWEL SIGN AA..DOGRA VOWEL SIGN II +1182F..11837 ; Extend # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA +11838 ; Extend # Mc DOGRA SIGN VISARGA +11839..1183A ; Extend # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA +11930..11935 ; Extend # Mc [6] DIVES AKURU VOWEL SIGN AA..DIVES AKURU VOWEL SIGN E +11937..11938 ; Extend # Mc [2] DIVES AKURU VOWEL SIGN AI..DIVES AKURU VOWEL SIGN O +1193B..1193C ; Extend # Mn [2] DIVES AKURU SIGN ANUSVARA..DIVES AKURU SIGN CANDRABINDU +1193D ; Extend # Mc DIVES AKURU SIGN HALANTA +1193E ; Extend # Mn DIVES AKURU VIRAMA +11940 ; Extend # Mc DIVES AKURU MEDIAL YA +11942 ; Extend # Mc DIVES AKURU MEDIAL RA +11943 ; Extend # Mn DIVES AKURU SIGN NUKTA +119D1..119D3 ; Extend # Mc [3] NANDINAGARI VOWEL SIGN AA..NANDINAGARI VOWEL SIGN II +119D4..119D7 ; Extend # Mn [4] NANDINAGARI VOWEL SIGN U..NANDINAGARI VOWEL SIGN VOCALIC RR +119DA..119DB ; Extend # Mn [2] NANDINAGARI VOWEL SIGN E..NANDINAGARI VOWEL SIGN AI +119DC..119DF ; Extend # Mc [4] NANDINAGARI VOWEL SIGN O..NANDINAGARI SIGN VISARGA +119E0 ; Extend # Mn NANDINAGARI SIGN VIRAMA +119E4 ; Extend # Mc NANDINAGARI VOWEL SIGN PRISHTHAMATRA E +11A01..11A0A ; Extend # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; Extend # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A39 ; Extend # Mc ZANABAZAR SQUARE SIGN VISARGA +11A3B..11A3E ; Extend # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; Extend # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; Extend # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A57..11A58 ; Extend # Mc [2] SOYOMBO VOWEL SIGN AI..SOYOMBO VOWEL SIGN AU +11A59..11A5B ; Extend # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; Extend # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A97 ; Extend # Mc SOYOMBO SIGN VISARGA +11A98..11A99 ; Extend # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11C2F ; Extend # Mc BHAIKSUKI VOWEL SIGN AA +11C30..11C36 ; Extend # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; Extend # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3E ; Extend # Mc BHAIKSUKI SIGN VISARGA +11C3F ; Extend # Mn BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; Extend # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CA9 ; Extend # Mc MARCHEN SUBJOINED LETTER YA +11CAA..11CB0 ; Extend # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB1 ; Extend # Mc MARCHEN VOWEL SIGN I +11CB2..11CB3 ; Extend # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB4 ; Extend # Mc MARCHEN VOWEL SIGN O +11CB5..11CB6 ; Extend # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; Extend # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; Extend # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; Extend # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; Extend # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; Extend # Mn MASARAM GONDI RA-KARA +11D8A..11D8E ; Extend # Mc [5] GUNJALA GONDI VOWEL SIGN AA..GUNJALA GONDI VOWEL SIGN UU +11D90..11D91 ; Extend # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI +11D93..11D94 ; Extend # Mc [2] GUNJALA GONDI VOWEL SIGN OO..GUNJALA GONDI VOWEL SIGN AU +11D95 ; Extend # Mn GUNJALA GONDI SIGN ANUSVARA +11D96 ; Extend # Mc GUNJALA GONDI SIGN VISARGA +11D97 ; Extend # Mn GUNJALA GONDI VIRAMA +11EF3..11EF4 ; Extend # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U +11EF5..11EF6 ; Extend # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O +16AF0..16AF4 ; Extend # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE +16B30..16B36 ; Extend # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16F4F ; Extend # Mn MIAO SIGN CONSONANT MODIFIER BAR +16F51..16F87 ; Extend # Mc [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI +16F8F..16F92 ; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +16FE4 ; Extend # Mn KHITAN SMALL SCRIPT FILLER +16FF0..16FF1 ; Extend # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY +1BC9D..1BC9E ; Extend # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1CF00..1CF2D ; Extend # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; Extend # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG +1D165..1D166 ; Extend # Mc [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM +1D167..1D169 ; Extend # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D16D..1D172 ; Extend # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 +1D17B..1D182 ; Extend # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; Extend # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; Extend # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; Extend # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +1DA00..1DA36 ; Extend # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN +1DA3B..1DA6C ; Extend # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT +1DA75 ; Extend # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS +1DA84 ; Extend # Mn SIGNWRITING LOCATION HEAD NECK +1DA9B..1DA9F ; Extend # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 +1DAA1..1DAAF ; Extend # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; Extend # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; Extend # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E130..1E136 ; Extend # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2AE ; Extend # Mn TOTO SIGN RISING TONE +1E2EC..1E2EF ; Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI +1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 2508 + +# ================================================ + +0085 ; Sep # Cc <control-0085> +2028 ; Sep # Zl LINE SEPARATOR +2029 ; Sep # Zp PARAGRAPH SEPARATOR + +# Total code points: 3 + +# ================================================ + +00AD ; Format # Cf SOFT HYPHEN +0600..0605 ; Format # Cf [6] ARABIC NUMBER SIGN..ARABIC NUMBER MARK ABOVE +061C ; Format # Cf ARABIC LETTER MARK +06DD ; Format # Cf ARABIC END OF AYAH +070F ; Format # Cf SYRIAC ABBREVIATION MARK +0890..0891 ; Format # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE +08E2 ; Format # Cf ARABIC DISPUTED END OF AYAH +180E ; Format # Cf MONGOLIAN VOWEL SEPARATOR +200B ; Format # Cf ZERO WIDTH SPACE +200E..200F ; Format # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; Format # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; Format # Cf [5] WORD JOINER..INVISIBLE PLUS +2066..206F ; Format # Cf [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES +FEFF ; Format # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; Format # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +110BD ; Format # Cf KAITHI NUMBER SIGN +110CD ; Format # Cf KAITHI NUMBER SIGN ABOVE +13430..13438 ; Format # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT +1BCA0..1BCA3 ; Format # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1D173..1D17A ; Format # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +E0001 ; Format # Cf LANGUAGE TAG + +# Total code points: 65 + +# ================================================ + +0009 ; Sp # Cc <control-0009> +000B..000C ; Sp # Cc [2] <control-000B>..<control-000C> +0020 ; Sp # Zs SPACE +00A0 ; Sp # Zs NO-BREAK SPACE +1680 ; Sp # Zs OGHAM SPACE MARK +2000..200A ; Sp # Zs [11] EN QUAD..HAIR SPACE +202F ; Sp # Zs NARROW NO-BREAK SPACE +205F ; Sp # Zs MEDIUM MATHEMATICAL SPACE +3000 ; Sp # Zs IDEOGRAPHIC SPACE + +# Total code points: 20 + +# ================================================ + +0061..007A ; Lower # L& [26] LATIN SMALL LETTER A..LATIN SMALL LETTER Z +00AA ; Lower # Lo FEMININE ORDINAL INDICATOR +00B5 ; Lower # L& MICRO SIGN +00BA ; Lower # Lo MASCULINE ORDINAL INDICATOR +00DF..00F6 ; Lower # L& [24] LATIN SMALL LETTER SHARP S..LATIN SMALL LETTER O WITH DIAERESIS +00F8..00FF ; Lower # L& [8] LATIN SMALL LETTER O WITH STROKE..LATIN SMALL LETTER Y WITH DIAERESIS +0101 ; Lower # L& LATIN SMALL LETTER A WITH MACRON +0103 ; Lower # L& LATIN SMALL LETTER A WITH BREVE +0105 ; Lower # L& LATIN SMALL LETTER A WITH OGONEK +0107 ; Lower # L& LATIN SMALL LETTER C WITH ACUTE +0109 ; Lower # L& LATIN SMALL LETTER C WITH CIRCUMFLEX +010B ; Lower # L& LATIN SMALL LETTER C WITH DOT ABOVE +010D ; Lower # L& LATIN SMALL LETTER C WITH CARON +010F ; Lower # L& LATIN SMALL LETTER D WITH CARON +0111 ; Lower # L& LATIN SMALL LETTER D WITH STROKE +0113 ; Lower # L& LATIN SMALL LETTER E WITH MACRON +0115 ; Lower # L& LATIN SMALL LETTER E WITH BREVE +0117 ; Lower # L& LATIN SMALL LETTER E WITH DOT ABOVE +0119 ; Lower # L& LATIN SMALL LETTER E WITH OGONEK +011B ; Lower # L& LATIN SMALL LETTER E WITH CARON +011D ; Lower # L& LATIN SMALL LETTER G WITH CIRCUMFLEX +011F ; Lower # L& LATIN SMALL LETTER G WITH BREVE +0121 ; Lower # L& LATIN SMALL LETTER G WITH DOT ABOVE +0123 ; Lower # L& LATIN SMALL LETTER G WITH CEDILLA +0125 ; Lower # L& LATIN SMALL LETTER H WITH CIRCUMFLEX +0127 ; Lower # L& LATIN SMALL LETTER H WITH STROKE +0129 ; Lower # L& LATIN SMALL LETTER I WITH TILDE +012B ; Lower # L& LATIN SMALL LETTER I WITH MACRON +012D ; Lower # L& LATIN SMALL LETTER I WITH BREVE +012F ; Lower # L& LATIN SMALL LETTER I WITH OGONEK +0131 ; Lower # L& LATIN SMALL LETTER DOTLESS I +0133 ; Lower # L& LATIN SMALL LIGATURE IJ +0135 ; Lower # L& LATIN SMALL LETTER J WITH CIRCUMFLEX +0137..0138 ; Lower # L& [2] LATIN SMALL LETTER K WITH CEDILLA..LATIN SMALL LETTER KRA +013A ; Lower # L& LATIN SMALL LETTER L WITH ACUTE +013C ; Lower # L& LATIN SMALL LETTER L WITH CEDILLA +013E ; Lower # L& LATIN SMALL LETTER L WITH CARON +0140 ; Lower # L& LATIN SMALL LETTER L WITH MIDDLE DOT +0142 ; Lower # L& LATIN SMALL LETTER L WITH STROKE +0144 ; Lower # L& LATIN SMALL LETTER N WITH ACUTE +0146 ; Lower # L& LATIN SMALL LETTER N WITH CEDILLA +0148..0149 ; Lower # L& [2] LATIN SMALL LETTER N WITH CARON..LATIN SMALL LETTER N PRECEDED BY APOSTROPHE +014B ; Lower # L& LATIN SMALL LETTER ENG +014D ; Lower # L& LATIN SMALL LETTER O WITH MACRON +014F ; Lower # L& LATIN SMALL LETTER O WITH BREVE +0151 ; Lower # L& LATIN SMALL LETTER O WITH DOUBLE ACUTE +0153 ; Lower # L& LATIN SMALL LIGATURE OE +0155 ; Lower # L& LATIN SMALL LETTER R WITH ACUTE +0157 ; Lower # L& LATIN SMALL LETTER R WITH CEDILLA +0159 ; Lower # L& LATIN SMALL LETTER R WITH CARON +015B ; Lower # L& LATIN SMALL LETTER S WITH ACUTE +015D ; Lower # L& LATIN SMALL LETTER S WITH CIRCUMFLEX +015F ; Lower # L& LATIN SMALL LETTER S WITH CEDILLA +0161 ; Lower # L& LATIN SMALL LETTER S WITH CARON +0163 ; Lower # L& LATIN SMALL LETTER T WITH CEDILLA +0165 ; Lower # L& LATIN SMALL LETTER T WITH CARON +0167 ; Lower # L& LATIN SMALL LETTER T WITH STROKE +0169 ; Lower # L& LATIN SMALL LETTER U WITH TILDE +016B ; Lower # L& LATIN SMALL LETTER U WITH MACRON +016D ; Lower # L& LATIN SMALL LETTER U WITH BREVE +016F ; Lower # L& LATIN SMALL LETTER U WITH RING ABOVE +0171 ; Lower # L& LATIN SMALL LETTER U WITH DOUBLE ACUTE +0173 ; Lower # L& LATIN SMALL LETTER U WITH OGONEK +0175 ; Lower # L& LATIN SMALL LETTER W WITH CIRCUMFLEX +0177 ; Lower # L& LATIN SMALL LETTER Y WITH CIRCUMFLEX +017A ; Lower # L& LATIN SMALL LETTER Z WITH ACUTE +017C ; Lower # L& LATIN SMALL LETTER Z WITH DOT ABOVE +017E..0180 ; Lower # L& [3] LATIN SMALL LETTER Z WITH CARON..LATIN SMALL LETTER B WITH STROKE +0183 ; Lower # L& LATIN SMALL LETTER B WITH TOPBAR +0185 ; Lower # L& LATIN SMALL LETTER TONE SIX +0188 ; Lower # L& LATIN SMALL LETTER C WITH HOOK +018C..018D ; Lower # L& [2] LATIN SMALL LETTER D WITH TOPBAR..LATIN SMALL LETTER TURNED DELTA +0192 ; Lower # L& LATIN SMALL LETTER F WITH HOOK +0195 ; Lower # L& LATIN SMALL LETTER HV +0199..019B ; Lower # L& [3] LATIN SMALL LETTER K WITH HOOK..LATIN SMALL LETTER LAMBDA WITH STROKE +019E ; Lower # L& LATIN SMALL LETTER N WITH LONG RIGHT LEG +01A1 ; Lower # L& LATIN SMALL LETTER O WITH HORN +01A3 ; Lower # L& LATIN SMALL LETTER OI +01A5 ; Lower # L& LATIN SMALL LETTER P WITH HOOK +01A8 ; Lower # L& LATIN SMALL LETTER TONE TWO +01AA..01AB ; Lower # L& [2] LATIN LETTER REVERSED ESH LOOP..LATIN SMALL LETTER T WITH PALATAL HOOK +01AD ; Lower # L& LATIN SMALL LETTER T WITH HOOK +01B0 ; Lower # L& LATIN SMALL LETTER U WITH HORN +01B4 ; Lower # L& LATIN SMALL LETTER Y WITH HOOK +01B6 ; Lower # L& LATIN SMALL LETTER Z WITH STROKE +01B9..01BA ; Lower # L& [2] LATIN SMALL LETTER EZH REVERSED..LATIN SMALL LETTER EZH WITH TAIL +01BD..01BF ; Lower # L& [3] LATIN SMALL LETTER TONE FIVE..LATIN LETTER WYNN +01C6 ; Lower # L& LATIN SMALL LETTER DZ WITH CARON +01C9 ; Lower # L& LATIN SMALL LETTER LJ +01CC ; Lower # L& LATIN SMALL LETTER NJ +01CE ; Lower # L& LATIN SMALL LETTER A WITH CARON +01D0 ; Lower # L& LATIN SMALL LETTER I WITH CARON +01D2 ; Lower # L& LATIN SMALL LETTER O WITH CARON +01D4 ; Lower # L& LATIN SMALL LETTER U WITH CARON +01D6 ; Lower # L& LATIN SMALL LETTER U WITH DIAERESIS AND MACRON +01D8 ; Lower # L& LATIN SMALL LETTER U WITH DIAERESIS AND ACUTE +01DA ; Lower # L& LATIN SMALL LETTER U WITH DIAERESIS AND CARON +01DC..01DD ; Lower # L& [2] LATIN SMALL LETTER U WITH DIAERESIS AND GRAVE..LATIN SMALL LETTER TURNED E +01DF ; Lower # L& LATIN SMALL LETTER A WITH DIAERESIS AND MACRON +01E1 ; Lower # L& LATIN SMALL LETTER A WITH DOT ABOVE AND MACRON +01E3 ; Lower # L& LATIN SMALL LETTER AE WITH MACRON +01E5 ; Lower # L& LATIN SMALL LETTER G WITH STROKE +01E7 ; Lower # L& LATIN SMALL LETTER G WITH CARON +01E9 ; Lower # L& LATIN SMALL LETTER K WITH CARON +01EB ; Lower # L& LATIN SMALL LETTER O WITH OGONEK +01ED ; Lower # L& LATIN SMALL LETTER O WITH OGONEK AND MACRON +01EF..01F0 ; Lower # L& [2] LATIN SMALL LETTER EZH WITH CARON..LATIN SMALL LETTER J WITH CARON +01F3 ; Lower # L& LATIN SMALL LETTER DZ +01F5 ; Lower # L& LATIN SMALL LETTER G WITH ACUTE +01F9 ; Lower # L& LATIN SMALL LETTER N WITH GRAVE +01FB ; Lower # L& LATIN SMALL LETTER A WITH RING ABOVE AND ACUTE +01FD ; Lower # L& LATIN SMALL LETTER AE WITH ACUTE +01FF ; Lower # L& LATIN SMALL LETTER O WITH STROKE AND ACUTE +0201 ; Lower # L& LATIN SMALL LETTER A WITH DOUBLE GRAVE +0203 ; Lower # L& LATIN SMALL LETTER A WITH INVERTED BREVE +0205 ; Lower # L& LATIN SMALL LETTER E WITH DOUBLE GRAVE +0207 ; Lower # L& LATIN SMALL LETTER E WITH INVERTED BREVE +0209 ; Lower # L& LATIN SMALL LETTER I WITH DOUBLE GRAVE +020B ; Lower # L& LATIN SMALL LETTER I WITH INVERTED BREVE +020D ; Lower # L& LATIN SMALL LETTER O WITH DOUBLE GRAVE +020F ; Lower # L& LATIN SMALL LETTER O WITH INVERTED BREVE +0211 ; Lower # L& LATIN SMALL LETTER R WITH DOUBLE GRAVE +0213 ; Lower # L& LATIN SMALL LETTER R WITH INVERTED BREVE +0215 ; Lower # L& LATIN SMALL LETTER U WITH DOUBLE GRAVE +0217 ; Lower # L& LATIN SMALL LETTER U WITH INVERTED BREVE +0219 ; Lower # L& LATIN SMALL LETTER S WITH COMMA BELOW +021B ; Lower # L& LATIN SMALL LETTER T WITH COMMA BELOW +021D ; Lower # L& LATIN SMALL LETTER YOGH +021F ; Lower # L& LATIN SMALL LETTER H WITH CARON +0221 ; Lower # L& LATIN SMALL LETTER D WITH CURL +0223 ; Lower # L& LATIN SMALL LETTER OU +0225 ; Lower # L& LATIN SMALL LETTER Z WITH HOOK +0227 ; Lower # L& LATIN SMALL LETTER A WITH DOT ABOVE +0229 ; Lower # L& LATIN SMALL LETTER E WITH CEDILLA +022B ; Lower # L& LATIN SMALL LETTER O WITH DIAERESIS AND MACRON +022D ; Lower # L& LATIN SMALL LETTER O WITH TILDE AND MACRON +022F ; Lower # L& LATIN SMALL LETTER O WITH DOT ABOVE +0231 ; Lower # L& LATIN SMALL LETTER O WITH DOT ABOVE AND MACRON +0233..0239 ; Lower # L& [7] LATIN SMALL LETTER Y WITH MACRON..LATIN SMALL LETTER QP DIGRAPH +023C ; Lower # L& LATIN SMALL LETTER C WITH STROKE +023F..0240 ; Lower # L& [2] LATIN SMALL LETTER S WITH SWASH TAIL..LATIN SMALL LETTER Z WITH SWASH TAIL +0242 ; Lower # L& LATIN SMALL LETTER GLOTTAL STOP +0247 ; Lower # L& LATIN SMALL LETTER E WITH STROKE +0249 ; Lower # L& LATIN SMALL LETTER J WITH STROKE +024B ; Lower # L& LATIN SMALL LETTER Q WITH HOOK TAIL +024D ; Lower # L& LATIN SMALL LETTER R WITH STROKE +024F..0293 ; Lower # L& [69] LATIN SMALL LETTER Y WITH STROKE..LATIN SMALL LETTER EZH WITH CURL +0295..02AF ; Lower # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +02B0..02B8 ; Lower # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y +02C0..02C1 ; Lower # Lm [2] MODIFIER LETTER GLOTTAL STOP..MODIFIER LETTER REVERSED GLOTTAL STOP +02E0..02E4 ; Lower # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP +0371 ; Lower # L& GREEK SMALL LETTER HETA +0373 ; Lower # L& GREEK SMALL LETTER ARCHAIC SAMPI +0377 ; Lower # L& GREEK SMALL LETTER PAMPHYLIAN DIGAMMA +037A ; Lower # Lm GREEK YPOGEGRAMMENI +037B..037D ; Lower # L& [3] GREEK SMALL REVERSED LUNATE SIGMA SYMBOL..GREEK SMALL REVERSED DOTTED LUNATE SIGMA SYMBOL +0390 ; Lower # L& GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS +03AC..03CE ; Lower # L& [35] GREEK SMALL LETTER ALPHA WITH TONOS..GREEK SMALL LETTER OMEGA WITH TONOS +03D0..03D1 ; Lower # L& [2] GREEK BETA SYMBOL..GREEK THETA SYMBOL +03D5..03D7 ; Lower # L& [3] GREEK PHI SYMBOL..GREEK KAI SYMBOL +03D9 ; Lower # L& GREEK SMALL LETTER ARCHAIC KOPPA +03DB ; Lower # L& GREEK SMALL LETTER STIGMA +03DD ; Lower # L& GREEK SMALL LETTER DIGAMMA +03DF ; Lower # L& GREEK SMALL LETTER KOPPA +03E1 ; Lower # L& GREEK SMALL LETTER SAMPI +03E3 ; Lower # L& COPTIC SMALL LETTER SHEI +03E5 ; Lower # L& COPTIC SMALL LETTER FEI +03E7 ; Lower # L& COPTIC SMALL LETTER KHEI +03E9 ; Lower # L& COPTIC SMALL LETTER HORI +03EB ; Lower # L& COPTIC SMALL LETTER GANGIA +03ED ; Lower # L& COPTIC SMALL LETTER SHIMA +03EF..03F3 ; Lower # L& [5] COPTIC SMALL LETTER DEI..GREEK LETTER YOT +03F5 ; Lower # L& GREEK LUNATE EPSILON SYMBOL +03F8 ; Lower # L& GREEK SMALL LETTER SHO +03FB..03FC ; Lower # L& [2] GREEK SMALL LETTER SAN..GREEK RHO WITH STROKE SYMBOL +0430..045F ; Lower # L& [48] CYRILLIC SMALL LETTER A..CYRILLIC SMALL LETTER DZHE +0461 ; Lower # L& CYRILLIC SMALL LETTER OMEGA +0463 ; Lower # L& CYRILLIC SMALL LETTER YAT +0465 ; Lower # L& CYRILLIC SMALL LETTER IOTIFIED E +0467 ; Lower # L& CYRILLIC SMALL LETTER LITTLE YUS +0469 ; Lower # L& CYRILLIC SMALL LETTER IOTIFIED LITTLE YUS +046B ; Lower # L& CYRILLIC SMALL LETTER BIG YUS +046D ; Lower # L& CYRILLIC SMALL LETTER IOTIFIED BIG YUS +046F ; Lower # L& CYRILLIC SMALL LETTER KSI +0471 ; Lower # L& CYRILLIC SMALL LETTER PSI +0473 ; Lower # L& CYRILLIC SMALL LETTER FITA +0475 ; Lower # L& CYRILLIC SMALL LETTER IZHITSA +0477 ; Lower # L& CYRILLIC SMALL LETTER IZHITSA WITH DOUBLE GRAVE ACCENT +0479 ; Lower # L& CYRILLIC SMALL LETTER UK +047B ; Lower # L& CYRILLIC SMALL LETTER ROUND OMEGA +047D ; Lower # L& CYRILLIC SMALL LETTER OMEGA WITH TITLO +047F ; Lower # L& CYRILLIC SMALL LETTER OT +0481 ; Lower # L& CYRILLIC SMALL LETTER KOPPA +048B ; Lower # L& CYRILLIC SMALL LETTER SHORT I WITH TAIL +048D ; Lower # L& CYRILLIC SMALL LETTER SEMISOFT SIGN +048F ; Lower # L& CYRILLIC SMALL LETTER ER WITH TICK +0491 ; Lower # L& CYRILLIC SMALL LETTER GHE WITH UPTURN +0493 ; Lower # L& CYRILLIC SMALL LETTER GHE WITH STROKE +0495 ; Lower # L& CYRILLIC SMALL LETTER GHE WITH MIDDLE HOOK +0497 ; Lower # L& CYRILLIC SMALL LETTER ZHE WITH DESCENDER +0499 ; Lower # L& CYRILLIC SMALL LETTER ZE WITH DESCENDER +049B ; Lower # L& CYRILLIC SMALL LETTER KA WITH DESCENDER +049D ; Lower # L& CYRILLIC SMALL LETTER KA WITH VERTICAL STROKE +049F ; Lower # L& CYRILLIC SMALL LETTER KA WITH STROKE +04A1 ; Lower # L& CYRILLIC SMALL LETTER BASHKIR KA +04A3 ; Lower # L& CYRILLIC SMALL LETTER EN WITH DESCENDER +04A5 ; Lower # L& CYRILLIC SMALL LIGATURE EN GHE +04A7 ; Lower # L& CYRILLIC SMALL LETTER PE WITH MIDDLE HOOK +04A9 ; Lower # L& CYRILLIC SMALL LETTER ABKHASIAN HA +04AB ; Lower # L& CYRILLIC SMALL LETTER ES WITH DESCENDER +04AD ; Lower # L& CYRILLIC SMALL LETTER TE WITH DESCENDER +04AF ; Lower # L& CYRILLIC SMALL LETTER STRAIGHT U +04B1 ; Lower # L& CYRILLIC SMALL LETTER STRAIGHT U WITH STROKE +04B3 ; Lower # L& CYRILLIC SMALL LETTER HA WITH DESCENDER +04B5 ; Lower # L& CYRILLIC SMALL LIGATURE TE TSE +04B7 ; Lower # L& CYRILLIC SMALL LETTER CHE WITH DESCENDER +04B9 ; Lower # L& CYRILLIC SMALL LETTER CHE WITH VERTICAL STROKE +04BB ; Lower # L& CYRILLIC SMALL LETTER SHHA +04BD ; Lower # L& CYRILLIC SMALL LETTER ABKHASIAN CHE +04BF ; Lower # L& CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER +04C2 ; Lower # L& CYRILLIC SMALL LETTER ZHE WITH BREVE +04C4 ; Lower # L& CYRILLIC SMALL LETTER KA WITH HOOK +04C6 ; Lower # L& CYRILLIC SMALL LETTER EL WITH TAIL +04C8 ; Lower # L& CYRILLIC SMALL LETTER EN WITH HOOK +04CA ; Lower # L& CYRILLIC SMALL LETTER EN WITH TAIL +04CC ; Lower # L& CYRILLIC SMALL LETTER KHAKASSIAN CHE +04CE..04CF ; Lower # L& [2] CYRILLIC SMALL LETTER EM WITH TAIL..CYRILLIC SMALL LETTER PALOCHKA +04D1 ; Lower # L& CYRILLIC SMALL LETTER A WITH BREVE +04D3 ; Lower # L& CYRILLIC SMALL LETTER A WITH DIAERESIS +04D5 ; Lower # L& CYRILLIC SMALL LIGATURE A IE +04D7 ; Lower # L& CYRILLIC SMALL LETTER IE WITH BREVE +04D9 ; Lower # L& CYRILLIC SMALL LETTER SCHWA +04DB ; Lower # L& CYRILLIC SMALL LETTER SCHWA WITH DIAERESIS +04DD ; Lower # L& CYRILLIC SMALL LETTER ZHE WITH DIAERESIS +04DF ; Lower # L& CYRILLIC SMALL LETTER ZE WITH DIAERESIS +04E1 ; Lower # L& CYRILLIC SMALL LETTER ABKHASIAN DZE +04E3 ; Lower # L& CYRILLIC SMALL LETTER I WITH MACRON +04E5 ; Lower # L& CYRILLIC SMALL LETTER I WITH DIAERESIS +04E7 ; Lower # L& CYRILLIC SMALL LETTER O WITH DIAERESIS +04E9 ; Lower # L& CYRILLIC SMALL LETTER BARRED O +04EB ; Lower # L& CYRILLIC SMALL LETTER BARRED O WITH DIAERESIS +04ED ; Lower # L& CYRILLIC SMALL LETTER E WITH DIAERESIS +04EF ; Lower # L& CYRILLIC SMALL LETTER U WITH MACRON +04F1 ; Lower # L& CYRILLIC SMALL LETTER U WITH DIAERESIS +04F3 ; Lower # L& CYRILLIC SMALL LETTER U WITH DOUBLE ACUTE +04F5 ; Lower # L& CYRILLIC SMALL LETTER CHE WITH DIAERESIS +04F7 ; Lower # L& CYRILLIC SMALL LETTER GHE WITH DESCENDER +04F9 ; Lower # L& CYRILLIC SMALL LETTER YERU WITH DIAERESIS +04FB ; Lower # L& CYRILLIC SMALL LETTER GHE WITH STROKE AND HOOK +04FD ; Lower # L& CYRILLIC SMALL LETTER HA WITH HOOK +04FF ; Lower # L& CYRILLIC SMALL LETTER HA WITH STROKE +0501 ; Lower # L& CYRILLIC SMALL LETTER KOMI DE +0503 ; Lower # L& CYRILLIC SMALL LETTER KOMI DJE +0505 ; Lower # L& CYRILLIC SMALL LETTER KOMI ZJE +0507 ; Lower # L& CYRILLIC SMALL LETTER KOMI DZJE +0509 ; Lower # L& CYRILLIC SMALL LETTER KOMI LJE +050B ; Lower # L& CYRILLIC SMALL LETTER KOMI NJE +050D ; Lower # L& CYRILLIC SMALL LETTER KOMI SJE +050F ; Lower # L& CYRILLIC SMALL LETTER KOMI TJE +0511 ; Lower # L& CYRILLIC SMALL LETTER REVERSED ZE +0513 ; Lower # L& CYRILLIC SMALL LETTER EL WITH HOOK +0515 ; Lower # L& CYRILLIC SMALL LETTER LHA +0517 ; Lower # L& CYRILLIC SMALL LETTER RHA +0519 ; Lower # L& CYRILLIC SMALL LETTER YAE +051B ; Lower # L& CYRILLIC SMALL LETTER QA +051D ; Lower # L& CYRILLIC SMALL LETTER WE +051F ; Lower # L& CYRILLIC SMALL LETTER ALEUT KA +0521 ; Lower # L& CYRILLIC SMALL LETTER EL WITH MIDDLE HOOK +0523 ; Lower # L& CYRILLIC SMALL LETTER EN WITH MIDDLE HOOK +0525 ; Lower # L& CYRILLIC SMALL LETTER PE WITH DESCENDER +0527 ; Lower # L& CYRILLIC SMALL LETTER SHHA WITH DESCENDER +0529 ; Lower # L& CYRILLIC SMALL LETTER EN WITH LEFT HOOK +052B ; Lower # L& CYRILLIC SMALL LETTER DZZHE +052D ; Lower # L& CYRILLIC SMALL LETTER DCHE +052F ; Lower # L& CYRILLIC SMALL LETTER EL WITH DESCENDER +0560..0588 ; Lower # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE +13F8..13FD ; Lower # L& [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV +1C80..1C88 ; Lower # L& [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK +1D00..1D2B ; Lower # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL +1D2C..1D6A ; Lower # Lm [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI +1D6B..1D77 ; Lower # L& [13] LATIN SMALL LETTER UE..LATIN SMALL LETTER TURNED G +1D78 ; Lower # Lm MODIFIER LETTER CYRILLIC EN +1D79..1D9A ; Lower # L& [34] LATIN SMALL LETTER INSULAR G..LATIN SMALL LETTER EZH WITH RETROFLEX HOOK +1D9B..1DBF ; Lower # Lm [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA +1E01 ; Lower # L& LATIN SMALL LETTER A WITH RING BELOW +1E03 ; Lower # L& LATIN SMALL LETTER B WITH DOT ABOVE +1E05 ; Lower # L& LATIN SMALL LETTER B WITH DOT BELOW +1E07 ; Lower # L& LATIN SMALL LETTER B WITH LINE BELOW +1E09 ; Lower # L& LATIN SMALL LETTER C WITH CEDILLA AND ACUTE +1E0B ; Lower # L& LATIN SMALL LETTER D WITH DOT ABOVE +1E0D ; Lower # L& LATIN SMALL LETTER D WITH DOT BELOW +1E0F ; Lower # L& LATIN SMALL LETTER D WITH LINE BELOW +1E11 ; Lower # L& LATIN SMALL LETTER D WITH CEDILLA +1E13 ; Lower # L& LATIN SMALL LETTER D WITH CIRCUMFLEX BELOW +1E15 ; Lower # L& LATIN SMALL LETTER E WITH MACRON AND GRAVE +1E17 ; Lower # L& LATIN SMALL LETTER E WITH MACRON AND ACUTE +1E19 ; Lower # L& LATIN SMALL LETTER E WITH CIRCUMFLEX BELOW +1E1B ; Lower # L& LATIN SMALL LETTER E WITH TILDE BELOW +1E1D ; Lower # L& LATIN SMALL LETTER E WITH CEDILLA AND BREVE +1E1F ; Lower # L& LATIN SMALL LETTER F WITH DOT ABOVE +1E21 ; Lower # L& LATIN SMALL LETTER G WITH MACRON +1E23 ; Lower # L& LATIN SMALL LETTER H WITH DOT ABOVE +1E25 ; Lower # L& LATIN SMALL LETTER H WITH DOT BELOW +1E27 ; Lower # L& LATIN SMALL LETTER H WITH DIAERESIS +1E29 ; Lower # L& LATIN SMALL LETTER H WITH CEDILLA +1E2B ; Lower # L& LATIN SMALL LETTER H WITH BREVE BELOW +1E2D ; Lower # L& LATIN SMALL LETTER I WITH TILDE BELOW +1E2F ; Lower # L& LATIN SMALL LETTER I WITH DIAERESIS AND ACUTE +1E31 ; Lower # L& LATIN SMALL LETTER K WITH ACUTE +1E33 ; Lower # L& LATIN SMALL LETTER K WITH DOT BELOW +1E35 ; Lower # L& LATIN SMALL LETTER K WITH LINE BELOW +1E37 ; Lower # L& LATIN SMALL LETTER L WITH DOT BELOW +1E39 ; Lower # L& LATIN SMALL LETTER L WITH DOT BELOW AND MACRON +1E3B ; Lower # L& LATIN SMALL LETTER L WITH LINE BELOW +1E3D ; Lower # L& LATIN SMALL LETTER L WITH CIRCUMFLEX BELOW +1E3F ; Lower # L& LATIN SMALL LETTER M WITH ACUTE +1E41 ; Lower # L& LATIN SMALL LETTER M WITH DOT ABOVE +1E43 ; Lower # L& LATIN SMALL LETTER M WITH DOT BELOW +1E45 ; Lower # L& LATIN SMALL LETTER N WITH DOT ABOVE +1E47 ; Lower # L& LATIN SMALL LETTER N WITH DOT BELOW +1E49 ; Lower # L& LATIN SMALL LETTER N WITH LINE BELOW +1E4B ; Lower # L& LATIN SMALL LETTER N WITH CIRCUMFLEX BELOW +1E4D ; Lower # L& LATIN SMALL LETTER O WITH TILDE AND ACUTE +1E4F ; Lower # L& LATIN SMALL LETTER O WITH TILDE AND DIAERESIS +1E51 ; Lower # L& LATIN SMALL LETTER O WITH MACRON AND GRAVE +1E53 ; Lower # L& LATIN SMALL LETTER O WITH MACRON AND ACUTE +1E55 ; Lower # L& LATIN SMALL LETTER P WITH ACUTE +1E57 ; Lower # L& LATIN SMALL LETTER P WITH DOT ABOVE +1E59 ; Lower # L& LATIN SMALL LETTER R WITH DOT ABOVE +1E5B ; Lower # L& LATIN SMALL LETTER R WITH DOT BELOW +1E5D ; Lower # L& LATIN SMALL LETTER R WITH DOT BELOW AND MACRON +1E5F ; Lower # L& LATIN SMALL LETTER R WITH LINE BELOW +1E61 ; Lower # L& LATIN SMALL LETTER S WITH DOT ABOVE +1E63 ; Lower # L& LATIN SMALL LETTER S WITH DOT BELOW +1E65 ; Lower # L& LATIN SMALL LETTER S WITH ACUTE AND DOT ABOVE +1E67 ; Lower # L& LATIN SMALL LETTER S WITH CARON AND DOT ABOVE +1E69 ; Lower # L& LATIN SMALL LETTER S WITH DOT BELOW AND DOT ABOVE +1E6B ; Lower # L& LATIN SMALL LETTER T WITH DOT ABOVE +1E6D ; Lower # L& LATIN SMALL LETTER T WITH DOT BELOW +1E6F ; Lower # L& LATIN SMALL LETTER T WITH LINE BELOW +1E71 ; Lower # L& LATIN SMALL LETTER T WITH CIRCUMFLEX BELOW +1E73 ; Lower # L& LATIN SMALL LETTER U WITH DIAERESIS BELOW +1E75 ; Lower # L& LATIN SMALL LETTER U WITH TILDE BELOW +1E77 ; Lower # L& LATIN SMALL LETTER U WITH CIRCUMFLEX BELOW +1E79 ; Lower # L& LATIN SMALL LETTER U WITH TILDE AND ACUTE +1E7B ; Lower # L& LATIN SMALL LETTER U WITH MACRON AND DIAERESIS +1E7D ; Lower # L& LATIN SMALL LETTER V WITH TILDE +1E7F ; Lower # L& LATIN SMALL LETTER V WITH DOT BELOW +1E81 ; Lower # L& LATIN SMALL LETTER W WITH GRAVE +1E83 ; Lower # L& LATIN SMALL LETTER W WITH ACUTE +1E85 ; Lower # L& LATIN SMALL LETTER W WITH DIAERESIS +1E87 ; Lower # L& LATIN SMALL LETTER W WITH DOT ABOVE +1E89 ; Lower # L& LATIN SMALL LETTER W WITH DOT BELOW +1E8B ; Lower # L& LATIN SMALL LETTER X WITH DOT ABOVE +1E8D ; Lower # L& LATIN SMALL LETTER X WITH DIAERESIS +1E8F ; Lower # L& LATIN SMALL LETTER Y WITH DOT ABOVE +1E91 ; Lower # L& LATIN SMALL LETTER Z WITH CIRCUMFLEX +1E93 ; Lower # L& LATIN SMALL LETTER Z WITH DOT BELOW +1E95..1E9D ; Lower # L& [9] LATIN SMALL LETTER Z WITH LINE BELOW..LATIN SMALL LETTER LONG S WITH HIGH STROKE +1E9F ; Lower # L& LATIN SMALL LETTER DELTA +1EA1 ; Lower # L& LATIN SMALL LETTER A WITH DOT BELOW +1EA3 ; Lower # L& LATIN SMALL LETTER A WITH HOOK ABOVE +1EA5 ; Lower # L& LATIN SMALL LETTER A WITH CIRCUMFLEX AND ACUTE +1EA7 ; Lower # L& LATIN SMALL LETTER A WITH CIRCUMFLEX AND GRAVE +1EA9 ; Lower # L& LATIN SMALL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE +1EAB ; Lower # L& LATIN SMALL LETTER A WITH CIRCUMFLEX AND TILDE +1EAD ; Lower # L& LATIN SMALL LETTER A WITH CIRCUMFLEX AND DOT BELOW +1EAF ; Lower # L& LATIN SMALL LETTER A WITH BREVE AND ACUTE +1EB1 ; Lower # L& LATIN SMALL LETTER A WITH BREVE AND GRAVE +1EB3 ; Lower # L& LATIN SMALL LETTER A WITH BREVE AND HOOK ABOVE +1EB5 ; Lower # L& LATIN SMALL LETTER A WITH BREVE AND TILDE +1EB7 ; Lower # L& LATIN SMALL LETTER A WITH BREVE AND DOT BELOW +1EB9 ; Lower # L& LATIN SMALL LETTER E WITH DOT BELOW +1EBB ; Lower # L& LATIN SMALL LETTER E WITH HOOK ABOVE +1EBD ; Lower # L& LATIN SMALL LETTER E WITH TILDE +1EBF ; Lower # L& LATIN SMALL LETTER E WITH CIRCUMFLEX AND ACUTE +1EC1 ; Lower # L& LATIN SMALL LETTER E WITH CIRCUMFLEX AND GRAVE +1EC3 ; Lower # L& LATIN SMALL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE +1EC5 ; Lower # L& LATIN SMALL LETTER E WITH CIRCUMFLEX AND TILDE +1EC7 ; Lower # L& LATIN SMALL LETTER E WITH CIRCUMFLEX AND DOT BELOW +1EC9 ; Lower # L& LATIN SMALL LETTER I WITH HOOK ABOVE +1ECB ; Lower # L& LATIN SMALL LETTER I WITH DOT BELOW +1ECD ; Lower # L& LATIN SMALL LETTER O WITH DOT BELOW +1ECF ; Lower # L& LATIN SMALL LETTER O WITH HOOK ABOVE +1ED1 ; Lower # L& LATIN SMALL LETTER O WITH CIRCUMFLEX AND ACUTE +1ED3 ; Lower # L& LATIN SMALL LETTER O WITH CIRCUMFLEX AND GRAVE +1ED5 ; Lower # L& LATIN SMALL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE +1ED7 ; Lower # L& LATIN SMALL LETTER O WITH CIRCUMFLEX AND TILDE +1ED9 ; Lower # L& LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW +1EDB ; Lower # L& LATIN SMALL LETTER O WITH HORN AND ACUTE +1EDD ; Lower # L& LATIN SMALL LETTER O WITH HORN AND GRAVE +1EDF ; Lower # L& LATIN SMALL LETTER O WITH HORN AND HOOK ABOVE +1EE1 ; Lower # L& LATIN SMALL LETTER O WITH HORN AND TILDE +1EE3 ; Lower # L& LATIN SMALL LETTER O WITH HORN AND DOT BELOW +1EE5 ; Lower # L& LATIN SMALL LETTER U WITH DOT BELOW +1EE7 ; Lower # L& LATIN SMALL LETTER U WITH HOOK ABOVE +1EE9 ; Lower # L& LATIN SMALL LETTER U WITH HORN AND ACUTE +1EEB ; Lower # L& LATIN SMALL LETTER U WITH HORN AND GRAVE +1EED ; Lower # L& LATIN SMALL LETTER U WITH HORN AND HOOK ABOVE +1EEF ; Lower # L& LATIN SMALL LETTER U WITH HORN AND TILDE +1EF1 ; Lower # L& LATIN SMALL LETTER U WITH HORN AND DOT BELOW +1EF3 ; Lower # L& LATIN SMALL LETTER Y WITH GRAVE +1EF5 ; Lower # L& LATIN SMALL LETTER Y WITH DOT BELOW +1EF7 ; Lower # L& LATIN SMALL LETTER Y WITH HOOK ABOVE +1EF9 ; Lower # L& LATIN SMALL LETTER Y WITH TILDE +1EFB ; Lower # L& LATIN SMALL LETTER MIDDLE-WELSH LL +1EFD ; Lower # L& LATIN SMALL LETTER MIDDLE-WELSH V +1EFF..1F07 ; Lower # L& [9] LATIN SMALL LETTER Y WITH LOOP..GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI +1F10..1F15 ; Lower # L& [6] GREEK SMALL LETTER EPSILON WITH PSILI..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA +1F20..1F27 ; Lower # L& [8] GREEK SMALL LETTER ETA WITH PSILI..GREEK SMALL LETTER ETA WITH DASIA AND PERISPOMENI +1F30..1F37 ; Lower # L& [8] GREEK SMALL LETTER IOTA WITH PSILI..GREEK SMALL LETTER IOTA WITH DASIA AND PERISPOMENI +1F40..1F45 ; Lower # L& [6] GREEK SMALL LETTER OMICRON WITH PSILI..GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA +1F50..1F57 ; Lower # L& [8] GREEK SMALL LETTER UPSILON WITH PSILI..GREEK SMALL LETTER UPSILON WITH DASIA AND PERISPOMENI +1F60..1F67 ; Lower # L& [8] GREEK SMALL LETTER OMEGA WITH PSILI..GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI +1F70..1F7D ; Lower # L& [14] GREEK SMALL LETTER ALPHA WITH VARIA..GREEK SMALL LETTER OMEGA WITH OXIA +1F80..1F87 ; Lower # L& [8] GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI..GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI +1F90..1F97 ; Lower # L& [8] GREEK SMALL LETTER ETA WITH PSILI AND YPOGEGRAMMENI..GREEK SMALL LETTER ETA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI +1FA0..1FA7 ; Lower # L& [8] GREEK SMALL LETTER OMEGA WITH PSILI AND YPOGEGRAMMENI..GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI +1FB0..1FB4 ; Lower # L& [5] GREEK SMALL LETTER ALPHA WITH VRACHY..GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI +1FB6..1FB7 ; Lower # L& [2] GREEK SMALL LETTER ALPHA WITH PERISPOMENI..GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI +1FBE ; Lower # L& GREEK PROSGEGRAMMENI +1FC2..1FC4 ; Lower # L& [3] GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI..GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI +1FC6..1FC7 ; Lower # L& [2] GREEK SMALL LETTER ETA WITH PERISPOMENI..GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI +1FD0..1FD3 ; Lower # L& [4] GREEK SMALL LETTER IOTA WITH VRACHY..GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA +1FD6..1FD7 ; Lower # L& [2] GREEK SMALL LETTER IOTA WITH PERISPOMENI..GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI +1FE0..1FE7 ; Lower # L& [8] GREEK SMALL LETTER UPSILON WITH VRACHY..GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI +1FF2..1FF4 ; Lower # L& [3] GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI..GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI +1FF6..1FF7 ; Lower # L& [2] GREEK SMALL LETTER OMEGA WITH PERISPOMENI..GREEK SMALL LETTER OMEGA WITH PERISPOMENI AND YPOGEGRAMMENI +2071 ; Lower # Lm SUPERSCRIPT LATIN SMALL LETTER I +207F ; Lower # Lm SUPERSCRIPT LATIN SMALL LETTER N +2090..209C ; Lower # Lm [13] LATIN SUBSCRIPT SMALL LETTER A..LATIN SUBSCRIPT SMALL LETTER T +210A ; Lower # L& SCRIPT SMALL G +210E..210F ; Lower # L& [2] PLANCK CONSTANT..PLANCK CONSTANT OVER TWO PI +2113 ; Lower # L& SCRIPT SMALL L +212F ; Lower # L& SCRIPT SMALL E +2134 ; Lower # L& SCRIPT SMALL O +2139 ; Lower # L& INFORMATION SOURCE +213C..213D ; Lower # L& [2] DOUBLE-STRUCK SMALL PI..DOUBLE-STRUCK SMALL GAMMA +2146..2149 ; Lower # L& [4] DOUBLE-STRUCK ITALIC SMALL D..DOUBLE-STRUCK ITALIC SMALL J +214E ; Lower # L& TURNED SMALL F +2170..217F ; Lower # Nl [16] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL ONE THOUSAND +2184 ; Lower # L& LATIN SMALL LETTER REVERSED C +24D0..24E9 ; Lower # So [26] CIRCLED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z +2C30..2C5F ; Lower # L& [48] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER CAUDATE CHRIVI +2C61 ; Lower # L& LATIN SMALL LETTER L WITH DOUBLE BAR +2C65..2C66 ; Lower # L& [2] LATIN SMALL LETTER A WITH STROKE..LATIN SMALL LETTER T WITH DIAGONAL STROKE +2C68 ; Lower # L& LATIN SMALL LETTER H WITH DESCENDER +2C6A ; Lower # L& LATIN SMALL LETTER K WITH DESCENDER +2C6C ; Lower # L& LATIN SMALL LETTER Z WITH DESCENDER +2C71 ; Lower # L& LATIN SMALL LETTER V WITH RIGHT HOOK +2C73..2C74 ; Lower # L& [2] LATIN SMALL LETTER W WITH HOOK..LATIN SMALL LETTER V WITH CURL +2C76..2C7B ; Lower # L& [6] LATIN SMALL LETTER HALF H..LATIN LETTER SMALL CAPITAL TURNED E +2C7C..2C7D ; Lower # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V +2C81 ; Lower # L& COPTIC SMALL LETTER ALFA +2C83 ; Lower # L& COPTIC SMALL LETTER VIDA +2C85 ; Lower # L& COPTIC SMALL LETTER GAMMA +2C87 ; Lower # L& COPTIC SMALL LETTER DALDA +2C89 ; Lower # L& COPTIC SMALL LETTER EIE +2C8B ; Lower # L& COPTIC SMALL LETTER SOU +2C8D ; Lower # L& COPTIC SMALL LETTER ZATA +2C8F ; Lower # L& COPTIC SMALL LETTER HATE +2C91 ; Lower # L& COPTIC SMALL LETTER THETHE +2C93 ; Lower # L& COPTIC SMALL LETTER IAUDA +2C95 ; Lower # L& COPTIC SMALL LETTER KAPA +2C97 ; Lower # L& COPTIC SMALL LETTER LAULA +2C99 ; Lower # L& COPTIC SMALL LETTER MI +2C9B ; Lower # L& COPTIC SMALL LETTER NI +2C9D ; Lower # L& COPTIC SMALL LETTER KSI +2C9F ; Lower # L& COPTIC SMALL LETTER O +2CA1 ; Lower # L& COPTIC SMALL LETTER PI +2CA3 ; Lower # L& COPTIC SMALL LETTER RO +2CA5 ; Lower # L& COPTIC SMALL LETTER SIMA +2CA7 ; Lower # L& COPTIC SMALL LETTER TAU +2CA9 ; Lower # L& COPTIC SMALL LETTER UA +2CAB ; Lower # L& COPTIC SMALL LETTER FI +2CAD ; Lower # L& COPTIC SMALL LETTER KHI +2CAF ; Lower # L& COPTIC SMALL LETTER PSI +2CB1 ; Lower # L& COPTIC SMALL LETTER OOU +2CB3 ; Lower # L& COPTIC SMALL LETTER DIALECT-P ALEF +2CB5 ; Lower # L& COPTIC SMALL LETTER OLD COPTIC AIN +2CB7 ; Lower # L& COPTIC SMALL LETTER CRYPTOGRAMMIC EIE +2CB9 ; Lower # L& COPTIC SMALL LETTER DIALECT-P KAPA +2CBB ; Lower # L& COPTIC SMALL LETTER DIALECT-P NI +2CBD ; Lower # L& COPTIC SMALL LETTER CRYPTOGRAMMIC NI +2CBF ; Lower # L& COPTIC SMALL LETTER OLD COPTIC OOU +2CC1 ; Lower # L& COPTIC SMALL LETTER SAMPI +2CC3 ; Lower # L& COPTIC SMALL LETTER CROSSED SHEI +2CC5 ; Lower # L& COPTIC SMALL LETTER OLD COPTIC SHEI +2CC7 ; Lower # L& COPTIC SMALL LETTER OLD COPTIC ESH +2CC9 ; Lower # L& COPTIC SMALL LETTER AKHMIMIC KHEI +2CCB ; Lower # L& COPTIC SMALL LETTER DIALECT-P HORI +2CCD ; Lower # L& COPTIC SMALL LETTER OLD COPTIC HORI +2CCF ; Lower # L& COPTIC SMALL LETTER OLD COPTIC HA +2CD1 ; Lower # L& COPTIC SMALL LETTER L-SHAPED HA +2CD3 ; Lower # L& COPTIC SMALL LETTER OLD COPTIC HEI +2CD5 ; Lower # L& COPTIC SMALL LETTER OLD COPTIC HAT +2CD7 ; Lower # L& COPTIC SMALL LETTER OLD COPTIC GANGIA +2CD9 ; Lower # L& COPTIC SMALL LETTER OLD COPTIC DJA +2CDB ; Lower # L& COPTIC SMALL LETTER OLD COPTIC SHIMA +2CDD ; Lower # L& COPTIC SMALL LETTER OLD NUBIAN SHIMA +2CDF ; Lower # L& COPTIC SMALL LETTER OLD NUBIAN NGI +2CE1 ; Lower # L& COPTIC SMALL LETTER OLD NUBIAN NYI +2CE3..2CE4 ; Lower # L& [2] COPTIC SMALL LETTER OLD NUBIAN WAU..COPTIC SYMBOL KAI +2CEC ; Lower # L& COPTIC SMALL LETTER CRYPTOGRAMMIC SHEI +2CEE ; Lower # L& COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA +2CF3 ; Lower # L& COPTIC SMALL LETTER BOHAIRIC KHEI +2D00..2D25 ; Lower # L& [38] GEORGIAN SMALL LETTER AN..GEORGIAN SMALL LETTER HOE +2D27 ; Lower # L& GEORGIAN SMALL LETTER YN +2D2D ; Lower # L& GEORGIAN SMALL LETTER AEN +A641 ; Lower # L& CYRILLIC SMALL LETTER ZEMLYA +A643 ; Lower # L& CYRILLIC SMALL LETTER DZELO +A645 ; Lower # L& CYRILLIC SMALL LETTER REVERSED DZE +A647 ; Lower # L& CYRILLIC SMALL LETTER IOTA +A649 ; Lower # L& CYRILLIC SMALL LETTER DJERV +A64B ; Lower # L& CYRILLIC SMALL LETTER MONOGRAPH UK +A64D ; Lower # L& CYRILLIC SMALL LETTER BROAD OMEGA +A64F ; Lower # L& CYRILLIC SMALL LETTER NEUTRAL YER +A651 ; Lower # L& CYRILLIC SMALL LETTER YERU WITH BACK YER +A653 ; Lower # L& CYRILLIC SMALL LETTER IOTIFIED YAT +A655 ; Lower # L& CYRILLIC SMALL LETTER REVERSED YU +A657 ; Lower # L& CYRILLIC SMALL LETTER IOTIFIED A +A659 ; Lower # L& CYRILLIC SMALL LETTER CLOSED LITTLE YUS +A65B ; Lower # L& CYRILLIC SMALL LETTER BLENDED YUS +A65D ; Lower # L& CYRILLIC SMALL LETTER IOTIFIED CLOSED LITTLE YUS +A65F ; Lower # L& CYRILLIC SMALL LETTER YN +A661 ; Lower # L& CYRILLIC SMALL LETTER REVERSED TSE +A663 ; Lower # L& CYRILLIC SMALL LETTER SOFT DE +A665 ; Lower # L& CYRILLIC SMALL LETTER SOFT EL +A667 ; Lower # L& CYRILLIC SMALL LETTER SOFT EM +A669 ; Lower # L& CYRILLIC SMALL LETTER MONOCULAR O +A66B ; Lower # L& CYRILLIC SMALL LETTER BINOCULAR O +A66D ; Lower # L& CYRILLIC SMALL LETTER DOUBLE MONOCULAR O +A681 ; Lower # L& CYRILLIC SMALL LETTER DWE +A683 ; Lower # L& CYRILLIC SMALL LETTER DZWE +A685 ; Lower # L& CYRILLIC SMALL LETTER ZHWE +A687 ; Lower # L& CYRILLIC SMALL LETTER CCHE +A689 ; Lower # L& CYRILLIC SMALL LETTER DZZE +A68B ; Lower # L& CYRILLIC SMALL LETTER TE WITH MIDDLE HOOK +A68D ; Lower # L& CYRILLIC SMALL LETTER TWE +A68F ; Lower # L& CYRILLIC SMALL LETTER TSWE +A691 ; Lower # L& CYRILLIC SMALL LETTER TSSE +A693 ; Lower # L& CYRILLIC SMALL LETTER TCHE +A695 ; Lower # L& CYRILLIC SMALL LETTER HWE +A697 ; Lower # L& CYRILLIC SMALL LETTER SHWE +A699 ; Lower # L& CYRILLIC SMALL LETTER DOUBLE O +A69B ; Lower # L& CYRILLIC SMALL LETTER CROSSED O +A69C..A69D ; Lower # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN +A723 ; Lower # L& LATIN SMALL LETTER EGYPTOLOGICAL ALEF +A725 ; Lower # L& LATIN SMALL LETTER EGYPTOLOGICAL AIN +A727 ; Lower # L& LATIN SMALL LETTER HENG +A729 ; Lower # L& LATIN SMALL LETTER TZ +A72B ; Lower # L& LATIN SMALL LETTER TRESILLO +A72D ; Lower # L& LATIN SMALL LETTER CUATRILLO +A72F..A731 ; Lower # L& [3] LATIN SMALL LETTER CUATRILLO WITH COMMA..LATIN LETTER SMALL CAPITAL S +A733 ; Lower # L& LATIN SMALL LETTER AA +A735 ; Lower # L& LATIN SMALL LETTER AO +A737 ; Lower # L& LATIN SMALL LETTER AU +A739 ; Lower # L& LATIN SMALL LETTER AV +A73B ; Lower # L& LATIN SMALL LETTER AV WITH HORIZONTAL BAR +A73D ; Lower # L& LATIN SMALL LETTER AY +A73F ; Lower # L& LATIN SMALL LETTER REVERSED C WITH DOT +A741 ; Lower # L& LATIN SMALL LETTER K WITH STROKE +A743 ; Lower # L& LATIN SMALL LETTER K WITH DIAGONAL STROKE +A745 ; Lower # L& LATIN SMALL LETTER K WITH STROKE AND DIAGONAL STROKE +A747 ; Lower # L& LATIN SMALL LETTER BROKEN L +A749 ; Lower # L& LATIN SMALL LETTER L WITH HIGH STROKE +A74B ; Lower # L& LATIN SMALL LETTER O WITH LONG STROKE OVERLAY +A74D ; Lower # L& LATIN SMALL LETTER O WITH LOOP +A74F ; Lower # L& LATIN SMALL LETTER OO +A751 ; Lower # L& LATIN SMALL LETTER P WITH STROKE THROUGH DESCENDER +A753 ; Lower # L& LATIN SMALL LETTER P WITH FLOURISH +A755 ; Lower # L& LATIN SMALL LETTER P WITH SQUIRREL TAIL +A757 ; Lower # L& LATIN SMALL LETTER Q WITH STROKE THROUGH DESCENDER +A759 ; Lower # L& LATIN SMALL LETTER Q WITH DIAGONAL STROKE +A75B ; Lower # L& LATIN SMALL LETTER R ROTUNDA +A75D ; Lower # L& LATIN SMALL LETTER RUM ROTUNDA +A75F ; Lower # L& LATIN SMALL LETTER V WITH DIAGONAL STROKE +A761 ; Lower # L& LATIN SMALL LETTER VY +A763 ; Lower # L& LATIN SMALL LETTER VISIGOTHIC Z +A765 ; Lower # L& LATIN SMALL LETTER THORN WITH STROKE +A767 ; Lower # L& LATIN SMALL LETTER THORN WITH STROKE THROUGH DESCENDER +A769 ; Lower # L& LATIN SMALL LETTER VEND +A76B ; Lower # L& LATIN SMALL LETTER ET +A76D ; Lower # L& LATIN SMALL LETTER IS +A76F ; Lower # L& LATIN SMALL LETTER CON +A770 ; Lower # Lm MODIFIER LETTER US +A771..A778 ; Lower # L& [8] LATIN SMALL LETTER DUM..LATIN SMALL LETTER UM +A77A ; Lower # L& LATIN SMALL LETTER INSULAR D +A77C ; Lower # L& LATIN SMALL LETTER INSULAR F +A77F ; Lower # L& LATIN SMALL LETTER TURNED INSULAR G +A781 ; Lower # L& LATIN SMALL LETTER TURNED L +A783 ; Lower # L& LATIN SMALL LETTER INSULAR R +A785 ; Lower # L& LATIN SMALL LETTER INSULAR S +A787 ; Lower # L& LATIN SMALL LETTER INSULAR T +A78C ; Lower # L& LATIN SMALL LETTER SALTILLO +A78E ; Lower # L& LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT +A791 ; Lower # L& LATIN SMALL LETTER N WITH DESCENDER +A793..A795 ; Lower # L& [3] LATIN SMALL LETTER C WITH BAR..LATIN SMALL LETTER H WITH PALATAL HOOK +A797 ; Lower # L& LATIN SMALL LETTER B WITH FLOURISH +A799 ; Lower # L& LATIN SMALL LETTER F WITH STROKE +A79B ; Lower # L& LATIN SMALL LETTER VOLAPUK AE +A79D ; Lower # L& LATIN SMALL LETTER VOLAPUK OE +A79F ; Lower # L& LATIN SMALL LETTER VOLAPUK UE +A7A1 ; Lower # L& LATIN SMALL LETTER G WITH OBLIQUE STROKE +A7A3 ; Lower # L& LATIN SMALL LETTER K WITH OBLIQUE STROKE +A7A5 ; Lower # L& LATIN SMALL LETTER N WITH OBLIQUE STROKE +A7A7 ; Lower # L& LATIN SMALL LETTER R WITH OBLIQUE STROKE +A7A9 ; Lower # L& LATIN SMALL LETTER S WITH OBLIQUE STROKE +A7AF ; Lower # L& LATIN LETTER SMALL CAPITAL Q +A7B5 ; Lower # L& LATIN SMALL LETTER BETA +A7B7 ; Lower # L& LATIN SMALL LETTER OMEGA +A7B9 ; Lower # L& LATIN SMALL LETTER U WITH STROKE +A7BB ; Lower # L& LATIN SMALL LETTER GLOTTAL A +A7BD ; Lower # L& LATIN SMALL LETTER GLOTTAL I +A7BF ; Lower # L& LATIN SMALL LETTER GLOTTAL U +A7C1 ; Lower # L& LATIN SMALL LETTER OLD POLISH O +A7C3 ; Lower # L& LATIN SMALL LETTER ANGLICANA W +A7C8 ; Lower # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY +A7CA ; Lower # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D1 ; Lower # L& LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Lower # L& LATIN SMALL LETTER DOUBLE THORN +A7D5 ; Lower # L& LATIN SMALL LETTER DOUBLE WYNN +A7D7 ; Lower # L& LATIN SMALL LETTER MIDDLE SCOTS S +A7D9 ; Lower # L& LATIN SMALL LETTER SIGMOID S +A7F6 ; Lower # L& LATIN SMALL LETTER REVERSED HALF H +A7F8..A7F9 ; Lower # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE +A7FA ; Lower # L& LATIN LETTER SMALL CAPITAL TURNED M +AB30..AB5A ; Lower # L& [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG +AB5C..AB5F ; Lower # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK +AB60..AB68 ; Lower # L& [9] LATIN SMALL LETTER SAKHA YAT..LATIN SMALL LETTER TURNED R WITH MIDDLE TILDE +AB70..ABBF ; Lower # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA +FB00..FB06 ; Lower # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST +FB13..FB17 ; Lower # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH +FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z +10428..1044F ; Lower # L& [40] DESERET SMALL LETTER LONG I..DESERET SMALL LETTER EW +104D8..104FB ; Lower # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA +10597..105A1 ; Lower # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; Lower # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; Lower # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; Lower # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE +10780 ; Lower # Lm MODIFIER LETTER SMALL CAPITAL AA +10783..10785 ; Lower # Lm [3] MODIFIER LETTER SMALL AE..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; Lower # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; Lower # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL +10CC0..10CF2 ; Lower # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US +118C0..118DF ; Lower # L& [32] WARANG CITI SMALL LETTER NGAA..WARANG CITI SMALL LETTER VIYO +16E60..16E7F ; Lower # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y +1D41A..1D433 ; Lower # L& [26] MATHEMATICAL BOLD SMALL A..MATHEMATICAL BOLD SMALL Z +1D44E..1D454 ; Lower # L& [7] MATHEMATICAL ITALIC SMALL A..MATHEMATICAL ITALIC SMALL G +1D456..1D467 ; Lower # L& [18] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL ITALIC SMALL Z +1D482..1D49B ; Lower # L& [26] MATHEMATICAL BOLD ITALIC SMALL A..MATHEMATICAL BOLD ITALIC SMALL Z +1D4B6..1D4B9 ; Lower # L& [4] MATHEMATICAL SCRIPT SMALL A..MATHEMATICAL SCRIPT SMALL D +1D4BB ; Lower # L& MATHEMATICAL SCRIPT SMALL F +1D4BD..1D4C3 ; Lower # L& [7] MATHEMATICAL SCRIPT SMALL H..MATHEMATICAL SCRIPT SMALL N +1D4C5..1D4CF ; Lower # L& [11] MATHEMATICAL SCRIPT SMALL P..MATHEMATICAL SCRIPT SMALL Z +1D4EA..1D503 ; Lower # L& [26] MATHEMATICAL BOLD SCRIPT SMALL A..MATHEMATICAL BOLD SCRIPT SMALL Z +1D51E..1D537 ; Lower # L& [26] MATHEMATICAL FRAKTUR SMALL A..MATHEMATICAL FRAKTUR SMALL Z +1D552..1D56B ; Lower # L& [26] MATHEMATICAL DOUBLE-STRUCK SMALL A..MATHEMATICAL DOUBLE-STRUCK SMALL Z +1D586..1D59F ; Lower # L& [26] MATHEMATICAL BOLD FRAKTUR SMALL A..MATHEMATICAL BOLD FRAKTUR SMALL Z +1D5BA..1D5D3 ; Lower # L& [26] MATHEMATICAL SANS-SERIF SMALL A..MATHEMATICAL SANS-SERIF SMALL Z +1D5EE..1D607 ; Lower # L& [26] MATHEMATICAL SANS-SERIF BOLD SMALL A..MATHEMATICAL SANS-SERIF BOLD SMALL Z +1D622..1D63B ; Lower # L& [26] MATHEMATICAL SANS-SERIF ITALIC SMALL A..MATHEMATICAL SANS-SERIF ITALIC SMALL Z +1D656..1D66F ; Lower # L& [26] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL A..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL Z +1D68A..1D6A5 ; Lower # L& [28] MATHEMATICAL MONOSPACE SMALL A..MATHEMATICAL ITALIC SMALL DOTLESS J +1D6C2..1D6DA ; Lower # L& [25] MATHEMATICAL BOLD SMALL ALPHA..MATHEMATICAL BOLD SMALL OMEGA +1D6DC..1D6E1 ; Lower # L& [6] MATHEMATICAL BOLD EPSILON SYMBOL..MATHEMATICAL BOLD PI SYMBOL +1D6FC..1D714 ; Lower # L& [25] MATHEMATICAL ITALIC SMALL ALPHA..MATHEMATICAL ITALIC SMALL OMEGA +1D716..1D71B ; Lower # L& [6] MATHEMATICAL ITALIC EPSILON SYMBOL..MATHEMATICAL ITALIC PI SYMBOL +1D736..1D74E ; Lower # L& [25] MATHEMATICAL BOLD ITALIC SMALL ALPHA..MATHEMATICAL BOLD ITALIC SMALL OMEGA +1D750..1D755 ; Lower # L& [6] MATHEMATICAL BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD ITALIC PI SYMBOL +1D770..1D788 ; Lower # L& [25] MATHEMATICAL SANS-SERIF BOLD SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD SMALL OMEGA +1D78A..1D78F ; Lower # L& [6] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD PI SYMBOL +1D7AA..1D7C2 ; Lower # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA +1D7C4..1D7C9 ; Lower # L& [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL +1D7CB ; Lower # L& MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; Lower # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0B..1DF1E ; Lower # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL +1E922..1E943 ; Lower # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA + +# Total code points: 2424 + +# ================================================ + +0041..005A ; Upper # L& [26] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER Z +00C0..00D6 ; Upper # L& [23] LATIN CAPITAL LETTER A WITH GRAVE..LATIN CAPITAL LETTER O WITH DIAERESIS +00D8..00DE ; Upper # L& [7] LATIN CAPITAL LETTER O WITH STROKE..LATIN CAPITAL LETTER THORN +0100 ; Upper # L& LATIN CAPITAL LETTER A WITH MACRON +0102 ; Upper # L& LATIN CAPITAL LETTER A WITH BREVE +0104 ; Upper # L& LATIN CAPITAL LETTER A WITH OGONEK +0106 ; Upper # L& LATIN CAPITAL LETTER C WITH ACUTE +0108 ; Upper # L& LATIN CAPITAL LETTER C WITH CIRCUMFLEX +010A ; Upper # L& LATIN CAPITAL LETTER C WITH DOT ABOVE +010C ; Upper # L& LATIN CAPITAL LETTER C WITH CARON +010E ; Upper # L& LATIN CAPITAL LETTER D WITH CARON +0110 ; Upper # L& LATIN CAPITAL LETTER D WITH STROKE +0112 ; Upper # L& LATIN CAPITAL LETTER E WITH MACRON +0114 ; Upper # L& LATIN CAPITAL LETTER E WITH BREVE +0116 ; Upper # L& LATIN CAPITAL LETTER E WITH DOT ABOVE +0118 ; Upper # L& LATIN CAPITAL LETTER E WITH OGONEK +011A ; Upper # L& LATIN CAPITAL LETTER E WITH CARON +011C ; Upper # L& LATIN CAPITAL LETTER G WITH CIRCUMFLEX +011E ; Upper # L& LATIN CAPITAL LETTER G WITH BREVE +0120 ; Upper # L& LATIN CAPITAL LETTER G WITH DOT ABOVE +0122 ; Upper # L& LATIN CAPITAL LETTER G WITH CEDILLA +0124 ; Upper # L& LATIN CAPITAL LETTER H WITH CIRCUMFLEX +0126 ; Upper # L& LATIN CAPITAL LETTER H WITH STROKE +0128 ; Upper # L& LATIN CAPITAL LETTER I WITH TILDE +012A ; Upper # L& LATIN CAPITAL LETTER I WITH MACRON +012C ; Upper # L& LATIN CAPITAL LETTER I WITH BREVE +012E ; Upper # L& LATIN CAPITAL LETTER I WITH OGONEK +0130 ; Upper # L& LATIN CAPITAL LETTER I WITH DOT ABOVE +0132 ; Upper # L& LATIN CAPITAL LIGATURE IJ +0134 ; Upper # L& LATIN CAPITAL LETTER J WITH CIRCUMFLEX +0136 ; Upper # L& LATIN CAPITAL LETTER K WITH CEDILLA +0139 ; Upper # L& LATIN CAPITAL LETTER L WITH ACUTE +013B ; Upper # L& LATIN CAPITAL LETTER L WITH CEDILLA +013D ; Upper # L& LATIN CAPITAL LETTER L WITH CARON +013F ; Upper # L& LATIN CAPITAL LETTER L WITH MIDDLE DOT +0141 ; Upper # L& LATIN CAPITAL LETTER L WITH STROKE +0143 ; Upper # L& LATIN CAPITAL LETTER N WITH ACUTE +0145 ; Upper # L& LATIN CAPITAL LETTER N WITH CEDILLA +0147 ; Upper # L& LATIN CAPITAL LETTER N WITH CARON +014A ; Upper # L& LATIN CAPITAL LETTER ENG +014C ; Upper # L& LATIN CAPITAL LETTER O WITH MACRON +014E ; Upper # L& LATIN CAPITAL LETTER O WITH BREVE +0150 ; Upper # L& LATIN CAPITAL LETTER O WITH DOUBLE ACUTE +0152 ; Upper # L& LATIN CAPITAL LIGATURE OE +0154 ; Upper # L& LATIN CAPITAL LETTER R WITH ACUTE +0156 ; Upper # L& LATIN CAPITAL LETTER R WITH CEDILLA +0158 ; Upper # L& LATIN CAPITAL LETTER R WITH CARON +015A ; Upper # L& LATIN CAPITAL LETTER S WITH ACUTE +015C ; Upper # L& LATIN CAPITAL LETTER S WITH CIRCUMFLEX +015E ; Upper # L& LATIN CAPITAL LETTER S WITH CEDILLA +0160 ; Upper # L& LATIN CAPITAL LETTER S WITH CARON +0162 ; Upper # L& LATIN CAPITAL LETTER T WITH CEDILLA +0164 ; Upper # L& LATIN CAPITAL LETTER T WITH CARON +0166 ; Upper # L& LATIN CAPITAL LETTER T WITH STROKE +0168 ; Upper # L& LATIN CAPITAL LETTER U WITH TILDE +016A ; Upper # L& LATIN CAPITAL LETTER U WITH MACRON +016C ; Upper # L& LATIN CAPITAL LETTER U WITH BREVE +016E ; Upper # L& LATIN CAPITAL LETTER U WITH RING ABOVE +0170 ; Upper # L& LATIN CAPITAL LETTER U WITH DOUBLE ACUTE +0172 ; Upper # L& LATIN CAPITAL LETTER U WITH OGONEK +0174 ; Upper # L& LATIN CAPITAL LETTER W WITH CIRCUMFLEX +0176 ; Upper # L& LATIN CAPITAL LETTER Y WITH CIRCUMFLEX +0178..0179 ; Upper # L& [2] LATIN CAPITAL LETTER Y WITH DIAERESIS..LATIN CAPITAL LETTER Z WITH ACUTE +017B ; Upper # L& LATIN CAPITAL LETTER Z WITH DOT ABOVE +017D ; Upper # L& LATIN CAPITAL LETTER Z WITH CARON +0181..0182 ; Upper # L& [2] LATIN CAPITAL LETTER B WITH HOOK..LATIN CAPITAL LETTER B WITH TOPBAR +0184 ; Upper # L& LATIN CAPITAL LETTER TONE SIX +0186..0187 ; Upper # L& [2] LATIN CAPITAL LETTER OPEN O..LATIN CAPITAL LETTER C WITH HOOK +0189..018B ; Upper # L& [3] LATIN CAPITAL LETTER AFRICAN D..LATIN CAPITAL LETTER D WITH TOPBAR +018E..0191 ; Upper # L& [4] LATIN CAPITAL LETTER REVERSED E..LATIN CAPITAL LETTER F WITH HOOK +0193..0194 ; Upper # L& [2] LATIN CAPITAL LETTER G WITH HOOK..LATIN CAPITAL LETTER GAMMA +0196..0198 ; Upper # L& [3] LATIN CAPITAL LETTER IOTA..LATIN CAPITAL LETTER K WITH HOOK +019C..019D ; Upper # L& [2] LATIN CAPITAL LETTER TURNED M..LATIN CAPITAL LETTER N WITH LEFT HOOK +019F..01A0 ; Upper # L& [2] LATIN CAPITAL LETTER O WITH MIDDLE TILDE..LATIN CAPITAL LETTER O WITH HORN +01A2 ; Upper # L& LATIN CAPITAL LETTER OI +01A4 ; Upper # L& LATIN CAPITAL LETTER P WITH HOOK +01A6..01A7 ; Upper # L& [2] LATIN LETTER YR..LATIN CAPITAL LETTER TONE TWO +01A9 ; Upper # L& LATIN CAPITAL LETTER ESH +01AC ; Upper # L& LATIN CAPITAL LETTER T WITH HOOK +01AE..01AF ; Upper # L& [2] LATIN CAPITAL LETTER T WITH RETROFLEX HOOK..LATIN CAPITAL LETTER U WITH HORN +01B1..01B3 ; Upper # L& [3] LATIN CAPITAL LETTER UPSILON..LATIN CAPITAL LETTER Y WITH HOOK +01B5 ; Upper # L& LATIN CAPITAL LETTER Z WITH STROKE +01B7..01B8 ; Upper # L& [2] LATIN CAPITAL LETTER EZH..LATIN CAPITAL LETTER EZH REVERSED +01BC ; Upper # L& LATIN CAPITAL LETTER TONE FIVE +01C4..01C5 ; Upper # L& [2] LATIN CAPITAL LETTER DZ WITH CARON..LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON +01C7..01C8 ; Upper # L& [2] LATIN CAPITAL LETTER LJ..LATIN CAPITAL LETTER L WITH SMALL LETTER J +01CA..01CB ; Upper # L& [2] LATIN CAPITAL LETTER NJ..LATIN CAPITAL LETTER N WITH SMALL LETTER J +01CD ; Upper # L& LATIN CAPITAL LETTER A WITH CARON +01CF ; Upper # L& LATIN CAPITAL LETTER I WITH CARON +01D1 ; Upper # L& LATIN CAPITAL LETTER O WITH CARON +01D3 ; Upper # L& LATIN CAPITAL LETTER U WITH CARON +01D5 ; Upper # L& LATIN CAPITAL LETTER U WITH DIAERESIS AND MACRON +01D7 ; Upper # L& LATIN CAPITAL LETTER U WITH DIAERESIS AND ACUTE +01D9 ; Upper # L& LATIN CAPITAL LETTER U WITH DIAERESIS AND CARON +01DB ; Upper # L& LATIN CAPITAL LETTER U WITH DIAERESIS AND GRAVE +01DE ; Upper # L& LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON +01E0 ; Upper # L& LATIN CAPITAL LETTER A WITH DOT ABOVE AND MACRON +01E2 ; Upper # L& LATIN CAPITAL LETTER AE WITH MACRON +01E4 ; Upper # L& LATIN CAPITAL LETTER G WITH STROKE +01E6 ; Upper # L& LATIN CAPITAL LETTER G WITH CARON +01E8 ; Upper # L& LATIN CAPITAL LETTER K WITH CARON +01EA ; Upper # L& LATIN CAPITAL LETTER O WITH OGONEK +01EC ; Upper # L& LATIN CAPITAL LETTER O WITH OGONEK AND MACRON +01EE ; Upper # L& LATIN CAPITAL LETTER EZH WITH CARON +01F1..01F2 ; Upper # L& [2] LATIN CAPITAL LETTER DZ..LATIN CAPITAL LETTER D WITH SMALL LETTER Z +01F4 ; Upper # L& LATIN CAPITAL LETTER G WITH ACUTE +01F6..01F8 ; Upper # L& [3] LATIN CAPITAL LETTER HWAIR..LATIN CAPITAL LETTER N WITH GRAVE +01FA ; Upper # L& LATIN CAPITAL LETTER A WITH RING ABOVE AND ACUTE +01FC ; Upper # L& LATIN CAPITAL LETTER AE WITH ACUTE +01FE ; Upper # L& LATIN CAPITAL LETTER O WITH STROKE AND ACUTE +0200 ; Upper # L& LATIN CAPITAL LETTER A WITH DOUBLE GRAVE +0202 ; Upper # L& LATIN CAPITAL LETTER A WITH INVERTED BREVE +0204 ; Upper # L& LATIN CAPITAL LETTER E WITH DOUBLE GRAVE +0206 ; Upper # L& LATIN CAPITAL LETTER E WITH INVERTED BREVE +0208 ; Upper # L& LATIN CAPITAL LETTER I WITH DOUBLE GRAVE +020A ; Upper # L& LATIN CAPITAL LETTER I WITH INVERTED BREVE +020C ; Upper # L& LATIN CAPITAL LETTER O WITH DOUBLE GRAVE +020E ; Upper # L& LATIN CAPITAL LETTER O WITH INVERTED BREVE +0210 ; Upper # L& LATIN CAPITAL LETTER R WITH DOUBLE GRAVE +0212 ; Upper # L& LATIN CAPITAL LETTER R WITH INVERTED BREVE +0214 ; Upper # L& LATIN CAPITAL LETTER U WITH DOUBLE GRAVE +0216 ; Upper # L& LATIN CAPITAL LETTER U WITH INVERTED BREVE +0218 ; Upper # L& LATIN CAPITAL LETTER S WITH COMMA BELOW +021A ; Upper # L& LATIN CAPITAL LETTER T WITH COMMA BELOW +021C ; Upper # L& LATIN CAPITAL LETTER YOGH +021E ; Upper # L& LATIN CAPITAL LETTER H WITH CARON +0220 ; Upper # L& LATIN CAPITAL LETTER N WITH LONG RIGHT LEG +0222 ; Upper # L& LATIN CAPITAL LETTER OU +0224 ; Upper # L& LATIN CAPITAL LETTER Z WITH HOOK +0226 ; Upper # L& LATIN CAPITAL LETTER A WITH DOT ABOVE +0228 ; Upper # L& LATIN CAPITAL LETTER E WITH CEDILLA +022A ; Upper # L& LATIN CAPITAL LETTER O WITH DIAERESIS AND MACRON +022C ; Upper # L& LATIN CAPITAL LETTER O WITH TILDE AND MACRON +022E ; Upper # L& LATIN CAPITAL LETTER O WITH DOT ABOVE +0230 ; Upper # L& LATIN CAPITAL LETTER O WITH DOT ABOVE AND MACRON +0232 ; Upper # L& LATIN CAPITAL LETTER Y WITH MACRON +023A..023B ; Upper # L& [2] LATIN CAPITAL LETTER A WITH STROKE..LATIN CAPITAL LETTER C WITH STROKE +023D..023E ; Upper # L& [2] LATIN CAPITAL LETTER L WITH BAR..LATIN CAPITAL LETTER T WITH DIAGONAL STROKE +0241 ; Upper # L& LATIN CAPITAL LETTER GLOTTAL STOP +0243..0246 ; Upper # L& [4] LATIN CAPITAL LETTER B WITH STROKE..LATIN CAPITAL LETTER E WITH STROKE +0248 ; Upper # L& LATIN CAPITAL LETTER J WITH STROKE +024A ; Upper # L& LATIN CAPITAL LETTER SMALL Q WITH HOOK TAIL +024C ; Upper # L& LATIN CAPITAL LETTER R WITH STROKE +024E ; Upper # L& LATIN CAPITAL LETTER Y WITH STROKE +0370 ; Upper # L& GREEK CAPITAL LETTER HETA +0372 ; Upper # L& GREEK CAPITAL LETTER ARCHAIC SAMPI +0376 ; Upper # L& GREEK CAPITAL LETTER PAMPHYLIAN DIGAMMA +037F ; Upper # L& GREEK CAPITAL LETTER YOT +0386 ; Upper # L& GREEK CAPITAL LETTER ALPHA WITH TONOS +0388..038A ; Upper # L& [3] GREEK CAPITAL LETTER EPSILON WITH TONOS..GREEK CAPITAL LETTER IOTA WITH TONOS +038C ; Upper # L& GREEK CAPITAL LETTER OMICRON WITH TONOS +038E..038F ; Upper # L& [2] GREEK CAPITAL LETTER UPSILON WITH TONOS..GREEK CAPITAL LETTER OMEGA WITH TONOS +0391..03A1 ; Upper # L& [17] GREEK CAPITAL LETTER ALPHA..GREEK CAPITAL LETTER RHO +03A3..03AB ; Upper # L& [9] GREEK CAPITAL LETTER SIGMA..GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA +03CF ; Upper # L& GREEK CAPITAL KAI SYMBOL +03D2..03D4 ; Upper # L& [3] GREEK UPSILON WITH HOOK SYMBOL..GREEK UPSILON WITH DIAERESIS AND HOOK SYMBOL +03D8 ; Upper # L& GREEK LETTER ARCHAIC KOPPA +03DA ; Upper # L& GREEK LETTER STIGMA +03DC ; Upper # L& GREEK LETTER DIGAMMA +03DE ; Upper # L& GREEK LETTER KOPPA +03E0 ; Upper # L& GREEK LETTER SAMPI +03E2 ; Upper # L& COPTIC CAPITAL LETTER SHEI +03E4 ; Upper # L& COPTIC CAPITAL LETTER FEI +03E6 ; Upper # L& COPTIC CAPITAL LETTER KHEI +03E8 ; Upper # L& COPTIC CAPITAL LETTER HORI +03EA ; Upper # L& COPTIC CAPITAL LETTER GANGIA +03EC ; Upper # L& COPTIC CAPITAL LETTER SHIMA +03EE ; Upper # L& COPTIC CAPITAL LETTER DEI +03F4 ; Upper # L& GREEK CAPITAL THETA SYMBOL +03F7 ; Upper # L& GREEK CAPITAL LETTER SHO +03F9..03FA ; Upper # L& [2] GREEK CAPITAL LUNATE SIGMA SYMBOL..GREEK CAPITAL LETTER SAN +03FD..042F ; Upper # L& [51] GREEK CAPITAL REVERSED LUNATE SIGMA SYMBOL..CYRILLIC CAPITAL LETTER YA +0460 ; Upper # L& CYRILLIC CAPITAL LETTER OMEGA +0462 ; Upper # L& CYRILLIC CAPITAL LETTER YAT +0464 ; Upper # L& CYRILLIC CAPITAL LETTER IOTIFIED E +0466 ; Upper # L& CYRILLIC CAPITAL LETTER LITTLE YUS +0468 ; Upper # L& CYRILLIC CAPITAL LETTER IOTIFIED LITTLE YUS +046A ; Upper # L& CYRILLIC CAPITAL LETTER BIG YUS +046C ; Upper # L& CYRILLIC CAPITAL LETTER IOTIFIED BIG YUS +046E ; Upper # L& CYRILLIC CAPITAL LETTER KSI +0470 ; Upper # L& CYRILLIC CAPITAL LETTER PSI +0472 ; Upper # L& CYRILLIC CAPITAL LETTER FITA +0474 ; Upper # L& CYRILLIC CAPITAL LETTER IZHITSA +0476 ; Upper # L& CYRILLIC CAPITAL LETTER IZHITSA WITH DOUBLE GRAVE ACCENT +0478 ; Upper # L& CYRILLIC CAPITAL LETTER UK +047A ; Upper # L& CYRILLIC CAPITAL LETTER ROUND OMEGA +047C ; Upper # L& CYRILLIC CAPITAL LETTER OMEGA WITH TITLO +047E ; Upper # L& CYRILLIC CAPITAL LETTER OT +0480 ; Upper # L& CYRILLIC CAPITAL LETTER KOPPA +048A ; Upper # L& CYRILLIC CAPITAL LETTER SHORT I WITH TAIL +048C ; Upper # L& CYRILLIC CAPITAL LETTER SEMISOFT SIGN +048E ; Upper # L& CYRILLIC CAPITAL LETTER ER WITH TICK +0490 ; Upper # L& CYRILLIC CAPITAL LETTER GHE WITH UPTURN +0492 ; Upper # L& CYRILLIC CAPITAL LETTER GHE WITH STROKE +0494 ; Upper # L& CYRILLIC CAPITAL LETTER GHE WITH MIDDLE HOOK +0496 ; Upper # L& CYRILLIC CAPITAL LETTER ZHE WITH DESCENDER +0498 ; Upper # L& CYRILLIC CAPITAL LETTER ZE WITH DESCENDER +049A ; Upper # L& CYRILLIC CAPITAL LETTER KA WITH DESCENDER +049C ; Upper # L& CYRILLIC CAPITAL LETTER KA WITH VERTICAL STROKE +049E ; Upper # L& CYRILLIC CAPITAL LETTER KA WITH STROKE +04A0 ; Upper # L& CYRILLIC CAPITAL LETTER BASHKIR KA +04A2 ; Upper # L& CYRILLIC CAPITAL LETTER EN WITH DESCENDER +04A4 ; Upper # L& CYRILLIC CAPITAL LIGATURE EN GHE +04A6 ; Upper # L& CYRILLIC CAPITAL LETTER PE WITH MIDDLE HOOK +04A8 ; Upper # L& CYRILLIC CAPITAL LETTER ABKHASIAN HA +04AA ; Upper # L& CYRILLIC CAPITAL LETTER ES WITH DESCENDER +04AC ; Upper # L& CYRILLIC CAPITAL LETTER TE WITH DESCENDER +04AE ; Upper # L& CYRILLIC CAPITAL LETTER STRAIGHT U +04B0 ; Upper # L& CYRILLIC CAPITAL LETTER STRAIGHT U WITH STROKE +04B2 ; Upper # L& CYRILLIC CAPITAL LETTER HA WITH DESCENDER +04B4 ; Upper # L& CYRILLIC CAPITAL LIGATURE TE TSE +04B6 ; Upper # L& CYRILLIC CAPITAL LETTER CHE WITH DESCENDER +04B8 ; Upper # L& CYRILLIC CAPITAL LETTER CHE WITH VERTICAL STROKE +04BA ; Upper # L& CYRILLIC CAPITAL LETTER SHHA +04BC ; Upper # L& CYRILLIC CAPITAL LETTER ABKHASIAN CHE +04BE ; Upper # L& CYRILLIC CAPITAL LETTER ABKHASIAN CHE WITH DESCENDER +04C0..04C1 ; Upper # L& [2] CYRILLIC LETTER PALOCHKA..CYRILLIC CAPITAL LETTER ZHE WITH BREVE +04C3 ; Upper # L& CYRILLIC CAPITAL LETTER KA WITH HOOK +04C5 ; Upper # L& CYRILLIC CAPITAL LETTER EL WITH TAIL +04C7 ; Upper # L& CYRILLIC CAPITAL LETTER EN WITH HOOK +04C9 ; Upper # L& CYRILLIC CAPITAL LETTER EN WITH TAIL +04CB ; Upper # L& CYRILLIC CAPITAL LETTER KHAKASSIAN CHE +04CD ; Upper # L& CYRILLIC CAPITAL LETTER EM WITH TAIL +04D0 ; Upper # L& CYRILLIC CAPITAL LETTER A WITH BREVE +04D2 ; Upper # L& CYRILLIC CAPITAL LETTER A WITH DIAERESIS +04D4 ; Upper # L& CYRILLIC CAPITAL LIGATURE A IE +04D6 ; Upper # L& CYRILLIC CAPITAL LETTER IE WITH BREVE +04D8 ; Upper # L& CYRILLIC CAPITAL LETTER SCHWA +04DA ; Upper # L& CYRILLIC CAPITAL LETTER SCHWA WITH DIAERESIS +04DC ; Upper # L& CYRILLIC CAPITAL LETTER ZHE WITH DIAERESIS +04DE ; Upper # L& CYRILLIC CAPITAL LETTER ZE WITH DIAERESIS +04E0 ; Upper # L& CYRILLIC CAPITAL LETTER ABKHASIAN DZE +04E2 ; Upper # L& CYRILLIC CAPITAL LETTER I WITH MACRON +04E4 ; Upper # L& CYRILLIC CAPITAL LETTER I WITH DIAERESIS +04E6 ; Upper # L& CYRILLIC CAPITAL LETTER O WITH DIAERESIS +04E8 ; Upper # L& CYRILLIC CAPITAL LETTER BARRED O +04EA ; Upper # L& CYRILLIC CAPITAL LETTER BARRED O WITH DIAERESIS +04EC ; Upper # L& CYRILLIC CAPITAL LETTER E WITH DIAERESIS +04EE ; Upper # L& CYRILLIC CAPITAL LETTER U WITH MACRON +04F0 ; Upper # L& CYRILLIC CAPITAL LETTER U WITH DIAERESIS +04F2 ; Upper # L& CYRILLIC CAPITAL LETTER U WITH DOUBLE ACUTE +04F4 ; Upper # L& CYRILLIC CAPITAL LETTER CHE WITH DIAERESIS +04F6 ; Upper # L& CYRILLIC CAPITAL LETTER GHE WITH DESCENDER +04F8 ; Upper # L& CYRILLIC CAPITAL LETTER YERU WITH DIAERESIS +04FA ; Upper # L& CYRILLIC CAPITAL LETTER GHE WITH STROKE AND HOOK +04FC ; Upper # L& CYRILLIC CAPITAL LETTER HA WITH HOOK +04FE ; Upper # L& CYRILLIC CAPITAL LETTER HA WITH STROKE +0500 ; Upper # L& CYRILLIC CAPITAL LETTER KOMI DE +0502 ; Upper # L& CYRILLIC CAPITAL LETTER KOMI DJE +0504 ; Upper # L& CYRILLIC CAPITAL LETTER KOMI ZJE +0506 ; Upper # L& CYRILLIC CAPITAL LETTER KOMI DZJE +0508 ; Upper # L& CYRILLIC CAPITAL LETTER KOMI LJE +050A ; Upper # L& CYRILLIC CAPITAL LETTER KOMI NJE +050C ; Upper # L& CYRILLIC CAPITAL LETTER KOMI SJE +050E ; Upper # L& CYRILLIC CAPITAL LETTER KOMI TJE +0510 ; Upper # L& CYRILLIC CAPITAL LETTER REVERSED ZE +0512 ; Upper # L& CYRILLIC CAPITAL LETTER EL WITH HOOK +0514 ; Upper # L& CYRILLIC CAPITAL LETTER LHA +0516 ; Upper # L& CYRILLIC CAPITAL LETTER RHA +0518 ; Upper # L& CYRILLIC CAPITAL LETTER YAE +051A ; Upper # L& CYRILLIC CAPITAL LETTER QA +051C ; Upper # L& CYRILLIC CAPITAL LETTER WE +051E ; Upper # L& CYRILLIC CAPITAL LETTER ALEUT KA +0520 ; Upper # L& CYRILLIC CAPITAL LETTER EL WITH MIDDLE HOOK +0522 ; Upper # L& CYRILLIC CAPITAL LETTER EN WITH MIDDLE HOOK +0524 ; Upper # L& CYRILLIC CAPITAL LETTER PE WITH DESCENDER +0526 ; Upper # L& CYRILLIC CAPITAL LETTER SHHA WITH DESCENDER +0528 ; Upper # L& CYRILLIC CAPITAL LETTER EN WITH LEFT HOOK +052A ; Upper # L& CYRILLIC CAPITAL LETTER DZZHE +052C ; Upper # L& CYRILLIC CAPITAL LETTER DCHE +052E ; Upper # L& CYRILLIC CAPITAL LETTER EL WITH DESCENDER +0531..0556 ; Upper # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH +10A0..10C5 ; Upper # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE +10C7 ; Upper # L& GEORGIAN CAPITAL LETTER YN +10CD ; Upper # L& GEORGIAN CAPITAL LETTER AEN +13A0..13F5 ; Upper # L& [86] CHEROKEE LETTER A..CHEROKEE LETTER MV +1E00 ; Upper # L& LATIN CAPITAL LETTER A WITH RING BELOW +1E02 ; Upper # L& LATIN CAPITAL LETTER B WITH DOT ABOVE +1E04 ; Upper # L& LATIN CAPITAL LETTER B WITH DOT BELOW +1E06 ; Upper # L& LATIN CAPITAL LETTER B WITH LINE BELOW +1E08 ; Upper # L& LATIN CAPITAL LETTER C WITH CEDILLA AND ACUTE +1E0A ; Upper # L& LATIN CAPITAL LETTER D WITH DOT ABOVE +1E0C ; Upper # L& LATIN CAPITAL LETTER D WITH DOT BELOW +1E0E ; Upper # L& LATIN CAPITAL LETTER D WITH LINE BELOW +1E10 ; Upper # L& LATIN CAPITAL LETTER D WITH CEDILLA +1E12 ; Upper # L& LATIN CAPITAL LETTER D WITH CIRCUMFLEX BELOW +1E14 ; Upper # L& LATIN CAPITAL LETTER E WITH MACRON AND GRAVE +1E16 ; Upper # L& LATIN CAPITAL LETTER E WITH MACRON AND ACUTE +1E18 ; Upper # L& LATIN CAPITAL LETTER E WITH CIRCUMFLEX BELOW +1E1A ; Upper # L& LATIN CAPITAL LETTER E WITH TILDE BELOW +1E1C ; Upper # L& LATIN CAPITAL LETTER E WITH CEDILLA AND BREVE +1E1E ; Upper # L& LATIN CAPITAL LETTER F WITH DOT ABOVE +1E20 ; Upper # L& LATIN CAPITAL LETTER G WITH MACRON +1E22 ; Upper # L& LATIN CAPITAL LETTER H WITH DOT ABOVE +1E24 ; Upper # L& LATIN CAPITAL LETTER H WITH DOT BELOW +1E26 ; Upper # L& LATIN CAPITAL LETTER H WITH DIAERESIS +1E28 ; Upper # L& LATIN CAPITAL LETTER H WITH CEDILLA +1E2A ; Upper # L& LATIN CAPITAL LETTER H WITH BREVE BELOW +1E2C ; Upper # L& LATIN CAPITAL LETTER I WITH TILDE BELOW +1E2E ; Upper # L& LATIN CAPITAL LETTER I WITH DIAERESIS AND ACUTE +1E30 ; Upper # L& LATIN CAPITAL LETTER K WITH ACUTE +1E32 ; Upper # L& LATIN CAPITAL LETTER K WITH DOT BELOW +1E34 ; Upper # L& LATIN CAPITAL LETTER K WITH LINE BELOW +1E36 ; Upper # L& LATIN CAPITAL LETTER L WITH DOT BELOW +1E38 ; Upper # L& LATIN CAPITAL LETTER L WITH DOT BELOW AND MACRON +1E3A ; Upper # L& LATIN CAPITAL LETTER L WITH LINE BELOW +1E3C ; Upper # L& LATIN CAPITAL LETTER L WITH CIRCUMFLEX BELOW +1E3E ; Upper # L& LATIN CAPITAL LETTER M WITH ACUTE +1E40 ; Upper # L& LATIN CAPITAL LETTER M WITH DOT ABOVE +1E42 ; Upper # L& LATIN CAPITAL LETTER M WITH DOT BELOW +1E44 ; Upper # L& LATIN CAPITAL LETTER N WITH DOT ABOVE +1E46 ; Upper # L& LATIN CAPITAL LETTER N WITH DOT BELOW +1E48 ; Upper # L& LATIN CAPITAL LETTER N WITH LINE BELOW +1E4A ; Upper # L& LATIN CAPITAL LETTER N WITH CIRCUMFLEX BELOW +1E4C ; Upper # L& LATIN CAPITAL LETTER O WITH TILDE AND ACUTE +1E4E ; Upper # L& LATIN CAPITAL LETTER O WITH TILDE AND DIAERESIS +1E50 ; Upper # L& LATIN CAPITAL LETTER O WITH MACRON AND GRAVE +1E52 ; Upper # L& LATIN CAPITAL LETTER O WITH MACRON AND ACUTE +1E54 ; Upper # L& LATIN CAPITAL LETTER P WITH ACUTE +1E56 ; Upper # L& LATIN CAPITAL LETTER P WITH DOT ABOVE +1E58 ; Upper # L& LATIN CAPITAL LETTER R WITH DOT ABOVE +1E5A ; Upper # L& LATIN CAPITAL LETTER R WITH DOT BELOW +1E5C ; Upper # L& LATIN CAPITAL LETTER R WITH DOT BELOW AND MACRON +1E5E ; Upper # L& LATIN CAPITAL LETTER R WITH LINE BELOW +1E60 ; Upper # L& LATIN CAPITAL LETTER S WITH DOT ABOVE +1E62 ; Upper # L& LATIN CAPITAL LETTER S WITH DOT BELOW +1E64 ; Upper # L& LATIN CAPITAL LETTER S WITH ACUTE AND DOT ABOVE +1E66 ; Upper # L& LATIN CAPITAL LETTER S WITH CARON AND DOT ABOVE +1E68 ; Upper # L& LATIN CAPITAL LETTER S WITH DOT BELOW AND DOT ABOVE +1E6A ; Upper # L& LATIN CAPITAL LETTER T WITH DOT ABOVE +1E6C ; Upper # L& LATIN CAPITAL LETTER T WITH DOT BELOW +1E6E ; Upper # L& LATIN CAPITAL LETTER T WITH LINE BELOW +1E70 ; Upper # L& LATIN CAPITAL LETTER T WITH CIRCUMFLEX BELOW +1E72 ; Upper # L& LATIN CAPITAL LETTER U WITH DIAERESIS BELOW +1E74 ; Upper # L& LATIN CAPITAL LETTER U WITH TILDE BELOW +1E76 ; Upper # L& LATIN CAPITAL LETTER U WITH CIRCUMFLEX BELOW +1E78 ; Upper # L& LATIN CAPITAL LETTER U WITH TILDE AND ACUTE +1E7A ; Upper # L& LATIN CAPITAL LETTER U WITH MACRON AND DIAERESIS +1E7C ; Upper # L& LATIN CAPITAL LETTER V WITH TILDE +1E7E ; Upper # L& LATIN CAPITAL LETTER V WITH DOT BELOW +1E80 ; Upper # L& LATIN CAPITAL LETTER W WITH GRAVE +1E82 ; Upper # L& LATIN CAPITAL LETTER W WITH ACUTE +1E84 ; Upper # L& LATIN CAPITAL LETTER W WITH DIAERESIS +1E86 ; Upper # L& LATIN CAPITAL LETTER W WITH DOT ABOVE +1E88 ; Upper # L& LATIN CAPITAL LETTER W WITH DOT BELOW +1E8A ; Upper # L& LATIN CAPITAL LETTER X WITH DOT ABOVE +1E8C ; Upper # L& LATIN CAPITAL LETTER X WITH DIAERESIS +1E8E ; Upper # L& LATIN CAPITAL LETTER Y WITH DOT ABOVE +1E90 ; Upper # L& LATIN CAPITAL LETTER Z WITH CIRCUMFLEX +1E92 ; Upper # L& LATIN CAPITAL LETTER Z WITH DOT BELOW +1E94 ; Upper # L& LATIN CAPITAL LETTER Z WITH LINE BELOW +1E9E ; Upper # L& LATIN CAPITAL LETTER SHARP S +1EA0 ; Upper # L& LATIN CAPITAL LETTER A WITH DOT BELOW +1EA2 ; Upper # L& LATIN CAPITAL LETTER A WITH HOOK ABOVE +1EA4 ; Upper # L& LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE +1EA6 ; Upper # L& LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE +1EA8 ; Upper # L& LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE +1EAA ; Upper # L& LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE +1EAC ; Upper # L& LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW +1EAE ; Upper # L& LATIN CAPITAL LETTER A WITH BREVE AND ACUTE +1EB0 ; Upper # L& LATIN CAPITAL LETTER A WITH BREVE AND GRAVE +1EB2 ; Upper # L& LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE +1EB4 ; Upper # L& LATIN CAPITAL LETTER A WITH BREVE AND TILDE +1EB6 ; Upper # L& LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW +1EB8 ; Upper # L& LATIN CAPITAL LETTER E WITH DOT BELOW +1EBA ; Upper # L& LATIN CAPITAL LETTER E WITH HOOK ABOVE +1EBC ; Upper # L& LATIN CAPITAL LETTER E WITH TILDE +1EBE ; Upper # L& LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE +1EC0 ; Upper # L& LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE +1EC2 ; Upper # L& LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE +1EC4 ; Upper # L& LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE +1EC6 ; Upper # L& LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND DOT BELOW +1EC8 ; Upper # L& LATIN CAPITAL LETTER I WITH HOOK ABOVE +1ECA ; Upper # L& LATIN CAPITAL LETTER I WITH DOT BELOW +1ECC ; Upper # L& LATIN CAPITAL LETTER O WITH DOT BELOW +1ECE ; Upper # L& LATIN CAPITAL LETTER O WITH HOOK ABOVE +1ED0 ; Upper # L& LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE +1ED2 ; Upper # L& LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE +1ED4 ; Upper # L& LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE +1ED6 ; Upper # L& LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE +1ED8 ; Upper # L& LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW +1EDA ; Upper # L& LATIN CAPITAL LETTER O WITH HORN AND ACUTE +1EDC ; Upper # L& LATIN CAPITAL LETTER O WITH HORN AND GRAVE +1EDE ; Upper # L& LATIN CAPITAL LETTER O WITH HORN AND HOOK ABOVE +1EE0 ; Upper # L& LATIN CAPITAL LETTER O WITH HORN AND TILDE +1EE2 ; Upper # L& LATIN CAPITAL LETTER O WITH HORN AND DOT BELOW +1EE4 ; Upper # L& LATIN CAPITAL LETTER U WITH DOT BELOW +1EE6 ; Upper # L& LATIN CAPITAL LETTER U WITH HOOK ABOVE +1EE8 ; Upper # L& LATIN CAPITAL LETTER U WITH HORN AND ACUTE +1EEA ; Upper # L& LATIN CAPITAL LETTER U WITH HORN AND GRAVE +1EEC ; Upper # L& LATIN CAPITAL LETTER U WITH HORN AND HOOK ABOVE +1EEE ; Upper # L& LATIN CAPITAL LETTER U WITH HORN AND TILDE +1EF0 ; Upper # L& LATIN CAPITAL LETTER U WITH HORN AND DOT BELOW +1EF2 ; Upper # L& LATIN CAPITAL LETTER Y WITH GRAVE +1EF4 ; Upper # L& LATIN CAPITAL LETTER Y WITH DOT BELOW +1EF6 ; Upper # L& LATIN CAPITAL LETTER Y WITH HOOK ABOVE +1EF8 ; Upper # L& LATIN CAPITAL LETTER Y WITH TILDE +1EFA ; Upper # L& LATIN CAPITAL LETTER MIDDLE-WELSH LL +1EFC ; Upper # L& LATIN CAPITAL LETTER MIDDLE-WELSH V +1EFE ; Upper # L& LATIN CAPITAL LETTER Y WITH LOOP +1F08..1F0F ; Upper # L& [8] GREEK CAPITAL LETTER ALPHA WITH PSILI..GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI +1F18..1F1D ; Upper # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA +1F28..1F2F ; Upper # L& [8] GREEK CAPITAL LETTER ETA WITH PSILI..GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI +1F38..1F3F ; Upper # L& [8] GREEK CAPITAL LETTER IOTA WITH PSILI..GREEK CAPITAL LETTER IOTA WITH DASIA AND PERISPOMENI +1F48..1F4D ; Upper # L& [6] GREEK CAPITAL LETTER OMICRON WITH PSILI..GREEK CAPITAL LETTER OMICRON WITH DASIA AND OXIA +1F59 ; Upper # L& GREEK CAPITAL LETTER UPSILON WITH DASIA +1F5B ; Upper # L& GREEK CAPITAL LETTER UPSILON WITH DASIA AND VARIA +1F5D ; Upper # L& GREEK CAPITAL LETTER UPSILON WITH DASIA AND OXIA +1F5F ; Upper # L& GREEK CAPITAL LETTER UPSILON WITH DASIA AND PERISPOMENI +1F68..1F6F ; Upper # L& [8] GREEK CAPITAL LETTER OMEGA WITH PSILI..GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI +1F88..1F8F ; Upper # L& [8] GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI..GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI +1F98..1F9F ; Upper # L& [8] GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI..GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI +1FA8..1FAF ; Upper # L& [8] GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI..GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI +1FB8..1FBC ; Upper # L& [5] GREEK CAPITAL LETTER ALPHA WITH VRACHY..GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI +1FC8..1FCC ; Upper # L& [5] GREEK CAPITAL LETTER EPSILON WITH VARIA..GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI +1FD8..1FDB ; Upper # L& [4] GREEK CAPITAL LETTER IOTA WITH VRACHY..GREEK CAPITAL LETTER IOTA WITH OXIA +1FE8..1FEC ; Upper # L& [5] GREEK CAPITAL LETTER UPSILON WITH VRACHY..GREEK CAPITAL LETTER RHO WITH DASIA +1FF8..1FFC ; Upper # L& [5] GREEK CAPITAL LETTER OMICRON WITH VARIA..GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI +2102 ; Upper # L& DOUBLE-STRUCK CAPITAL C +2107 ; Upper # L& EULER CONSTANT +210B..210D ; Upper # L& [3] SCRIPT CAPITAL H..DOUBLE-STRUCK CAPITAL H +2110..2112 ; Upper # L& [3] SCRIPT CAPITAL I..SCRIPT CAPITAL L +2115 ; Upper # L& DOUBLE-STRUCK CAPITAL N +2119..211D ; Upper # L& [5] DOUBLE-STRUCK CAPITAL P..DOUBLE-STRUCK CAPITAL R +2124 ; Upper # L& DOUBLE-STRUCK CAPITAL Z +2126 ; Upper # L& OHM SIGN +2128 ; Upper # L& BLACK-LETTER CAPITAL Z +212A..212D ; Upper # L& [4] KELVIN SIGN..BLACK-LETTER CAPITAL C +2130..2133 ; Upper # L& [4] SCRIPT CAPITAL E..SCRIPT CAPITAL M +213E..213F ; Upper # L& [2] DOUBLE-STRUCK CAPITAL GAMMA..DOUBLE-STRUCK CAPITAL PI +2145 ; Upper # L& DOUBLE-STRUCK ITALIC CAPITAL D +2160..216F ; Upper # Nl [16] ROMAN NUMERAL ONE..ROMAN NUMERAL ONE THOUSAND +2183 ; Upper # L& ROMAN NUMERAL REVERSED ONE HUNDRED +24B6..24CF ; Upper # So [26] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN CAPITAL LETTER Z +2C00..2C2F ; Upper # L& [48] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI +2C60 ; Upper # L& LATIN CAPITAL LETTER L WITH DOUBLE BAR +2C62..2C64 ; Upper # L& [3] LATIN CAPITAL LETTER L WITH MIDDLE TILDE..LATIN CAPITAL LETTER R WITH TAIL +2C67 ; Upper # L& LATIN CAPITAL LETTER H WITH DESCENDER +2C69 ; Upper # L& LATIN CAPITAL LETTER K WITH DESCENDER +2C6B ; Upper # L& LATIN CAPITAL LETTER Z WITH DESCENDER +2C6D..2C70 ; Upper # L& [4] LATIN CAPITAL LETTER ALPHA..LATIN CAPITAL LETTER TURNED ALPHA +2C72 ; Upper # L& LATIN CAPITAL LETTER W WITH HOOK +2C75 ; Upper # L& LATIN CAPITAL LETTER HALF H +2C7E..2C80 ; Upper # L& [3] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC CAPITAL LETTER ALFA +2C82 ; Upper # L& COPTIC CAPITAL LETTER VIDA +2C84 ; Upper # L& COPTIC CAPITAL LETTER GAMMA +2C86 ; Upper # L& COPTIC CAPITAL LETTER DALDA +2C88 ; Upper # L& COPTIC CAPITAL LETTER EIE +2C8A ; Upper # L& COPTIC CAPITAL LETTER SOU +2C8C ; Upper # L& COPTIC CAPITAL LETTER ZATA +2C8E ; Upper # L& COPTIC CAPITAL LETTER HATE +2C90 ; Upper # L& COPTIC CAPITAL LETTER THETHE +2C92 ; Upper # L& COPTIC CAPITAL LETTER IAUDA +2C94 ; Upper # L& COPTIC CAPITAL LETTER KAPA +2C96 ; Upper # L& COPTIC CAPITAL LETTER LAULA +2C98 ; Upper # L& COPTIC CAPITAL LETTER MI +2C9A ; Upper # L& COPTIC CAPITAL LETTER NI +2C9C ; Upper # L& COPTIC CAPITAL LETTER KSI +2C9E ; Upper # L& COPTIC CAPITAL LETTER O +2CA0 ; Upper # L& COPTIC CAPITAL LETTER PI +2CA2 ; Upper # L& COPTIC CAPITAL LETTER RO +2CA4 ; Upper # L& COPTIC CAPITAL LETTER SIMA +2CA6 ; Upper # L& COPTIC CAPITAL LETTER TAU +2CA8 ; Upper # L& COPTIC CAPITAL LETTER UA +2CAA ; Upper # L& COPTIC CAPITAL LETTER FI +2CAC ; Upper # L& COPTIC CAPITAL LETTER KHI +2CAE ; Upper # L& COPTIC CAPITAL LETTER PSI +2CB0 ; Upper # L& COPTIC CAPITAL LETTER OOU +2CB2 ; Upper # L& COPTIC CAPITAL LETTER DIALECT-P ALEF +2CB4 ; Upper # L& COPTIC CAPITAL LETTER OLD COPTIC AIN +2CB6 ; Upper # L& COPTIC CAPITAL LETTER CRYPTOGRAMMIC EIE +2CB8 ; Upper # L& COPTIC CAPITAL LETTER DIALECT-P KAPA +2CBA ; Upper # L& COPTIC CAPITAL LETTER DIALECT-P NI +2CBC ; Upper # L& COPTIC CAPITAL LETTER CRYPTOGRAMMIC NI +2CBE ; Upper # L& COPTIC CAPITAL LETTER OLD COPTIC OOU +2CC0 ; Upper # L& COPTIC CAPITAL LETTER SAMPI +2CC2 ; Upper # L& COPTIC CAPITAL LETTER CROSSED SHEI +2CC4 ; Upper # L& COPTIC CAPITAL LETTER OLD COPTIC SHEI +2CC6 ; Upper # L& COPTIC CAPITAL LETTER OLD COPTIC ESH +2CC8 ; Upper # L& COPTIC CAPITAL LETTER AKHMIMIC KHEI +2CCA ; Upper # L& COPTIC CAPITAL LETTER DIALECT-P HORI +2CCC ; Upper # L& COPTIC CAPITAL LETTER OLD COPTIC HORI +2CCE ; Upper # L& COPTIC CAPITAL LETTER OLD COPTIC HA +2CD0 ; Upper # L& COPTIC CAPITAL LETTER L-SHAPED HA +2CD2 ; Upper # L& COPTIC CAPITAL LETTER OLD COPTIC HEI +2CD4 ; Upper # L& COPTIC CAPITAL LETTER OLD COPTIC HAT +2CD6 ; Upper # L& COPTIC CAPITAL LETTER OLD COPTIC GANGIA +2CD8 ; Upper # L& COPTIC CAPITAL LETTER OLD COPTIC DJA +2CDA ; Upper # L& COPTIC CAPITAL LETTER OLD COPTIC SHIMA +2CDC ; Upper # L& COPTIC CAPITAL LETTER OLD NUBIAN SHIMA +2CDE ; Upper # L& COPTIC CAPITAL LETTER OLD NUBIAN NGI +2CE0 ; Upper # L& COPTIC CAPITAL LETTER OLD NUBIAN NYI +2CE2 ; Upper # L& COPTIC CAPITAL LETTER OLD NUBIAN WAU +2CEB ; Upper # L& COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI +2CED ; Upper # L& COPTIC CAPITAL LETTER CRYPTOGRAMMIC GANGIA +2CF2 ; Upper # L& COPTIC CAPITAL LETTER BOHAIRIC KHEI +A640 ; Upper # L& CYRILLIC CAPITAL LETTER ZEMLYA +A642 ; Upper # L& CYRILLIC CAPITAL LETTER DZELO +A644 ; Upper # L& CYRILLIC CAPITAL LETTER REVERSED DZE +A646 ; Upper # L& CYRILLIC CAPITAL LETTER IOTA +A648 ; Upper # L& CYRILLIC CAPITAL LETTER DJERV +A64A ; Upper # L& CYRILLIC CAPITAL LETTER MONOGRAPH UK +A64C ; Upper # L& CYRILLIC CAPITAL LETTER BROAD OMEGA +A64E ; Upper # L& CYRILLIC CAPITAL LETTER NEUTRAL YER +A650 ; Upper # L& CYRILLIC CAPITAL LETTER YERU WITH BACK YER +A652 ; Upper # L& CYRILLIC CAPITAL LETTER IOTIFIED YAT +A654 ; Upper # L& CYRILLIC CAPITAL LETTER REVERSED YU +A656 ; Upper # L& CYRILLIC CAPITAL LETTER IOTIFIED A +A658 ; Upper # L& CYRILLIC CAPITAL LETTER CLOSED LITTLE YUS +A65A ; Upper # L& CYRILLIC CAPITAL LETTER BLENDED YUS +A65C ; Upper # L& CYRILLIC CAPITAL LETTER IOTIFIED CLOSED LITTLE YUS +A65E ; Upper # L& CYRILLIC CAPITAL LETTER YN +A660 ; Upper # L& CYRILLIC CAPITAL LETTER REVERSED TSE +A662 ; Upper # L& CYRILLIC CAPITAL LETTER SOFT DE +A664 ; Upper # L& CYRILLIC CAPITAL LETTER SOFT EL +A666 ; Upper # L& CYRILLIC CAPITAL LETTER SOFT EM +A668 ; Upper # L& CYRILLIC CAPITAL LETTER MONOCULAR O +A66A ; Upper # L& CYRILLIC CAPITAL LETTER BINOCULAR O +A66C ; Upper # L& CYRILLIC CAPITAL LETTER DOUBLE MONOCULAR O +A680 ; Upper # L& CYRILLIC CAPITAL LETTER DWE +A682 ; Upper # L& CYRILLIC CAPITAL LETTER DZWE +A684 ; Upper # L& CYRILLIC CAPITAL LETTER ZHWE +A686 ; Upper # L& CYRILLIC CAPITAL LETTER CCHE +A688 ; Upper # L& CYRILLIC CAPITAL LETTER DZZE +A68A ; Upper # L& CYRILLIC CAPITAL LETTER TE WITH MIDDLE HOOK +A68C ; Upper # L& CYRILLIC CAPITAL LETTER TWE +A68E ; Upper # L& CYRILLIC CAPITAL LETTER TSWE +A690 ; Upper # L& CYRILLIC CAPITAL LETTER TSSE +A692 ; Upper # L& CYRILLIC CAPITAL LETTER TCHE +A694 ; Upper # L& CYRILLIC CAPITAL LETTER HWE +A696 ; Upper # L& CYRILLIC CAPITAL LETTER SHWE +A698 ; Upper # L& CYRILLIC CAPITAL LETTER DOUBLE O +A69A ; Upper # L& CYRILLIC CAPITAL LETTER CROSSED O +A722 ; Upper # L& LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF +A724 ; Upper # L& LATIN CAPITAL LETTER EGYPTOLOGICAL AIN +A726 ; Upper # L& LATIN CAPITAL LETTER HENG +A728 ; Upper # L& LATIN CAPITAL LETTER TZ +A72A ; Upper # L& LATIN CAPITAL LETTER TRESILLO +A72C ; Upper # L& LATIN CAPITAL LETTER CUATRILLO +A72E ; Upper # L& LATIN CAPITAL LETTER CUATRILLO WITH COMMA +A732 ; Upper # L& LATIN CAPITAL LETTER AA +A734 ; Upper # L& LATIN CAPITAL LETTER AO +A736 ; Upper # L& LATIN CAPITAL LETTER AU +A738 ; Upper # L& LATIN CAPITAL LETTER AV +A73A ; Upper # L& LATIN CAPITAL LETTER AV WITH HORIZONTAL BAR +A73C ; Upper # L& LATIN CAPITAL LETTER AY +A73E ; Upper # L& LATIN CAPITAL LETTER REVERSED C WITH DOT +A740 ; Upper # L& LATIN CAPITAL LETTER K WITH STROKE +A742 ; Upper # L& LATIN CAPITAL LETTER K WITH DIAGONAL STROKE +A744 ; Upper # L& LATIN CAPITAL LETTER K WITH STROKE AND DIAGONAL STROKE +A746 ; Upper # L& LATIN CAPITAL LETTER BROKEN L +A748 ; Upper # L& LATIN CAPITAL LETTER L WITH HIGH STROKE +A74A ; Upper # L& LATIN CAPITAL LETTER O WITH LONG STROKE OVERLAY +A74C ; Upper # L& LATIN CAPITAL LETTER O WITH LOOP +A74E ; Upper # L& LATIN CAPITAL LETTER OO +A750 ; Upper # L& LATIN CAPITAL LETTER P WITH STROKE THROUGH DESCENDER +A752 ; Upper # L& LATIN CAPITAL LETTER P WITH FLOURISH +A754 ; Upper # L& LATIN CAPITAL LETTER P WITH SQUIRREL TAIL +A756 ; Upper # L& LATIN CAPITAL LETTER Q WITH STROKE THROUGH DESCENDER +A758 ; Upper # L& LATIN CAPITAL LETTER Q WITH DIAGONAL STROKE +A75A ; Upper # L& LATIN CAPITAL LETTER R ROTUNDA +A75C ; Upper # L& LATIN CAPITAL LETTER RUM ROTUNDA +A75E ; Upper # L& LATIN CAPITAL LETTER V WITH DIAGONAL STROKE +A760 ; Upper # L& LATIN CAPITAL LETTER VY +A762 ; Upper # L& LATIN CAPITAL LETTER VISIGOTHIC Z +A764 ; Upper # L& LATIN CAPITAL LETTER THORN WITH STROKE +A766 ; Upper # L& LATIN CAPITAL LETTER THORN WITH STROKE THROUGH DESCENDER +A768 ; Upper # L& LATIN CAPITAL LETTER VEND +A76A ; Upper # L& LATIN CAPITAL LETTER ET +A76C ; Upper # L& LATIN CAPITAL LETTER IS +A76E ; Upper # L& LATIN CAPITAL LETTER CON +A779 ; Upper # L& LATIN CAPITAL LETTER INSULAR D +A77B ; Upper # L& LATIN CAPITAL LETTER INSULAR F +A77D..A77E ; Upper # L& [2] LATIN CAPITAL LETTER INSULAR G..LATIN CAPITAL LETTER TURNED INSULAR G +A780 ; Upper # L& LATIN CAPITAL LETTER TURNED L +A782 ; Upper # L& LATIN CAPITAL LETTER INSULAR R +A784 ; Upper # L& LATIN CAPITAL LETTER INSULAR S +A786 ; Upper # L& LATIN CAPITAL LETTER INSULAR T +A78B ; Upper # L& LATIN CAPITAL LETTER SALTILLO +A78D ; Upper # L& LATIN CAPITAL LETTER TURNED H +A790 ; Upper # L& LATIN CAPITAL LETTER N WITH DESCENDER +A792 ; Upper # L& LATIN CAPITAL LETTER C WITH BAR +A796 ; Upper # L& LATIN CAPITAL LETTER B WITH FLOURISH +A798 ; Upper # L& LATIN CAPITAL LETTER F WITH STROKE +A79A ; Upper # L& LATIN CAPITAL LETTER VOLAPUK AE +A79C ; Upper # L& LATIN CAPITAL LETTER VOLAPUK OE +A79E ; Upper # L& LATIN CAPITAL LETTER VOLAPUK UE +A7A0 ; Upper # L& LATIN CAPITAL LETTER G WITH OBLIQUE STROKE +A7A2 ; Upper # L& LATIN CAPITAL LETTER K WITH OBLIQUE STROKE +A7A4 ; Upper # L& LATIN CAPITAL LETTER N WITH OBLIQUE STROKE +A7A6 ; Upper # L& LATIN CAPITAL LETTER R WITH OBLIQUE STROKE +A7A8 ; Upper # L& LATIN CAPITAL LETTER S WITH OBLIQUE STROKE +A7AA..A7AE ; Upper # L& [5] LATIN CAPITAL LETTER H WITH HOOK..LATIN CAPITAL LETTER SMALL CAPITAL I +A7B0..A7B4 ; Upper # L& [5] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER BETA +A7B6 ; Upper # L& LATIN CAPITAL LETTER OMEGA +A7B8 ; Upper # L& LATIN CAPITAL LETTER U WITH STROKE +A7BA ; Upper # L& LATIN CAPITAL LETTER GLOTTAL A +A7BC ; Upper # L& LATIN CAPITAL LETTER GLOTTAL I +A7BE ; Upper # L& LATIN CAPITAL LETTER GLOTTAL U +A7C0 ; Upper # L& LATIN CAPITAL LETTER OLD POLISH O +A7C2 ; Upper # L& LATIN CAPITAL LETTER ANGLICANA W +A7C4..A7C7 ; Upper # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY +A7C9 ; Upper # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7D0 ; Upper # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D6 ; Upper # L& LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D8 ; Upper # L& LATIN CAPITAL LETTER SIGMOID S +A7F5 ; Upper # L& LATIN CAPITAL LETTER REVERSED HALF H +FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z +10400..10427 ; Upper # L& [40] DESERET CAPITAL LETTER LONG I..DESERET CAPITAL LETTER EW +104B0..104D3 ; Upper # L& [36] OSAGE CAPITAL LETTER A..OSAGE CAPITAL LETTER ZHA +10570..1057A ; Upper # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; Upper # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; Upper # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; Upper # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10C80..10CB2 ; Upper # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US +118A0..118BF ; Upper # L& [32] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI CAPITAL LETTER VIYO +16E40..16E5F ; Upper # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y +1D400..1D419 ; Upper # L& [26] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL BOLD CAPITAL Z +1D434..1D44D ; Upper # L& [26] MATHEMATICAL ITALIC CAPITAL A..MATHEMATICAL ITALIC CAPITAL Z +1D468..1D481 ; Upper # L& [26] MATHEMATICAL BOLD ITALIC CAPITAL A..MATHEMATICAL BOLD ITALIC CAPITAL Z +1D49C ; Upper # L& MATHEMATICAL SCRIPT CAPITAL A +1D49E..1D49F ; Upper # L& [2] MATHEMATICAL SCRIPT CAPITAL C..MATHEMATICAL SCRIPT CAPITAL D +1D4A2 ; Upper # L& MATHEMATICAL SCRIPT CAPITAL G +1D4A5..1D4A6 ; Upper # L& [2] MATHEMATICAL SCRIPT CAPITAL J..MATHEMATICAL SCRIPT CAPITAL K +1D4A9..1D4AC ; Upper # L& [4] MATHEMATICAL SCRIPT CAPITAL N..MATHEMATICAL SCRIPT CAPITAL Q +1D4AE..1D4B5 ; Upper # L& [8] MATHEMATICAL SCRIPT CAPITAL S..MATHEMATICAL SCRIPT CAPITAL Z +1D4D0..1D4E9 ; Upper # L& [26] MATHEMATICAL BOLD SCRIPT CAPITAL A..MATHEMATICAL BOLD SCRIPT CAPITAL Z +1D504..1D505 ; Upper # L& [2] MATHEMATICAL FRAKTUR CAPITAL A..MATHEMATICAL FRAKTUR CAPITAL B +1D507..1D50A ; Upper # L& [4] MATHEMATICAL FRAKTUR CAPITAL D..MATHEMATICAL FRAKTUR CAPITAL G +1D50D..1D514 ; Upper # L& [8] MATHEMATICAL FRAKTUR CAPITAL J..MATHEMATICAL FRAKTUR CAPITAL Q +1D516..1D51C ; Upper # L& [7] MATHEMATICAL FRAKTUR CAPITAL S..MATHEMATICAL FRAKTUR CAPITAL Y +1D538..1D539 ; Upper # L& [2] MATHEMATICAL DOUBLE-STRUCK CAPITAL A..MATHEMATICAL DOUBLE-STRUCK CAPITAL B +1D53B..1D53E ; Upper # L& [4] MATHEMATICAL DOUBLE-STRUCK CAPITAL D..MATHEMATICAL DOUBLE-STRUCK CAPITAL G +1D540..1D544 ; Upper # L& [5] MATHEMATICAL DOUBLE-STRUCK CAPITAL I..MATHEMATICAL DOUBLE-STRUCK CAPITAL M +1D546 ; Upper # L& MATHEMATICAL DOUBLE-STRUCK CAPITAL O +1D54A..1D550 ; Upper # L& [7] MATHEMATICAL DOUBLE-STRUCK CAPITAL S..MATHEMATICAL DOUBLE-STRUCK CAPITAL Y +1D56C..1D585 ; Upper # L& [26] MATHEMATICAL BOLD FRAKTUR CAPITAL A..MATHEMATICAL BOLD FRAKTUR CAPITAL Z +1D5A0..1D5B9 ; Upper # L& [26] MATHEMATICAL SANS-SERIF CAPITAL A..MATHEMATICAL SANS-SERIF CAPITAL Z +1D5D4..1D5ED ; Upper # L& [26] MATHEMATICAL SANS-SERIF BOLD CAPITAL A..MATHEMATICAL SANS-SERIF BOLD CAPITAL Z +1D608..1D621 ; Upper # L& [26] MATHEMATICAL SANS-SERIF ITALIC CAPITAL A..MATHEMATICAL SANS-SERIF ITALIC CAPITAL Z +1D63C..1D655 ; Upper # L& [26] MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL A..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL Z +1D670..1D689 ; Upper # L& [26] MATHEMATICAL MONOSPACE CAPITAL A..MATHEMATICAL MONOSPACE CAPITAL Z +1D6A8..1D6C0 ; Upper # L& [25] MATHEMATICAL BOLD CAPITAL ALPHA..MATHEMATICAL BOLD CAPITAL OMEGA +1D6E2..1D6FA ; Upper # L& [25] MATHEMATICAL ITALIC CAPITAL ALPHA..MATHEMATICAL ITALIC CAPITAL OMEGA +1D71C..1D734 ; Upper # L& [25] MATHEMATICAL BOLD ITALIC CAPITAL ALPHA..MATHEMATICAL BOLD ITALIC CAPITAL OMEGA +1D756..1D76E ; Upper # L& [25] MATHEMATICAL SANS-SERIF BOLD CAPITAL ALPHA..MATHEMATICAL SANS-SERIF BOLD CAPITAL OMEGA +1D790..1D7A8 ; Upper # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA +1D7CA ; Upper # L& MATHEMATICAL BOLD CAPITAL DIGAMMA +1E900..1E921 ; Upper # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA +1F130..1F149 ; Upper # So [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z +1F150..1F169 ; Upper # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z +1F170..1F189 ; Upper # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z + +# Total code points: 1936 + +# ================================================ + +01BB ; OLetter # Lo LATIN LETTER TWO WITH STROKE +01C0..01C3 ; OLetter # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK +0294 ; OLetter # Lo LATIN LETTER GLOTTAL STOP +02B9..02BF ; OLetter # Lm [7] MODIFIER LETTER PRIME..MODIFIER LETTER LEFT HALF RING +02C6..02D1 ; OLetter # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON +02EC ; OLetter # Lm MODIFIER LETTER VOICING +02EE ; OLetter # Lm MODIFIER LETTER DOUBLE APOSTROPHE +0374 ; OLetter # Lm GREEK NUMERAL SIGN +0559 ; OLetter # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +05D0..05EA ; OLetter # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV +05EF..05F2 ; OLetter # Lo [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD +05F3 ; OLetter # Po HEBREW PUNCTUATION GERESH +0620..063F ; OLetter # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0640 ; OLetter # Lm ARABIC TATWEEL +0641..064A ; OLetter # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH +066E..066F ; OLetter # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0671..06D3 ; OLetter # Lo [99] ARABIC LETTER ALEF WASLA..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; OLetter # Lo ARABIC LETTER AE +06E5..06E6 ; OLetter # Lm [2] ARABIC SMALL WAW..ARABIC SMALL YEH +06EE..06EF ; OLetter # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +06FA..06FC ; OLetter # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; OLetter # Lo ARABIC LETTER HEH WITH INVERTED V +0710 ; OLetter # Lo SYRIAC LETTER ALAPH +0712..072F ; OLetter # Lo [30] SYRIAC LETTER BETH..SYRIAC LETTER PERSIAN DHALATH +074D..07A5 ; OLetter # Lo [89] SYRIAC LETTER SOGDIAN ZHAIN..THAANA LETTER WAAVU +07B1 ; OLetter # Lo THAANA LETTER NAA +07CA..07EA ; OLetter # Lo [33] NKO LETTER A..NKO LETTER JONA RA +07F4..07F5 ; OLetter # Lm [2] NKO HIGH TONE APOSTROPHE..NKO LOW TONE APOSTROPHE +07FA ; OLetter # Lm NKO LAJANYALAN +0800..0815 ; OLetter # Lo [22] SAMARITAN LETTER ALAF..SAMARITAN LETTER TAAF +081A ; OLetter # Lm SAMARITAN MODIFIER LETTER EPENTHETIC YUT +0824 ; OLetter # Lm SAMARITAN MODIFIER LETTER SHORT A +0828 ; OLetter # Lm SAMARITAN MODIFIER LETTER I +0840..0858 ; OLetter # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN +0860..086A ; OLetter # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA +0870..0887 ; OLetter # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; OLetter # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +08A0..08C8 ; OLetter # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; OLetter # Lm ARABIC SMALL FARSI YEH +0904..0939 ; OLetter # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA +093D ; OLetter # Lo DEVANAGARI SIGN AVAGRAHA +0950 ; OLetter # Lo DEVANAGARI OM +0958..0961 ; OLetter # Lo [10] DEVANAGARI LETTER QA..DEVANAGARI LETTER VOCALIC LL +0971 ; OLetter # Lm DEVANAGARI SIGN HIGH SPACING DOT +0972..0980 ; OLetter # Lo [15] DEVANAGARI LETTER CANDRA A..BENGALI ANJI +0985..098C ; OLetter # Lo [8] BENGALI LETTER A..BENGALI LETTER VOCALIC L +098F..0990 ; OLetter # Lo [2] BENGALI LETTER E..BENGALI LETTER AI +0993..09A8 ; OLetter # Lo [22] BENGALI LETTER O..BENGALI LETTER NA +09AA..09B0 ; OLetter # Lo [7] BENGALI LETTER PA..BENGALI LETTER RA +09B2 ; OLetter # Lo BENGALI LETTER LA +09B6..09B9 ; OLetter # Lo [4] BENGALI LETTER SHA..BENGALI LETTER HA +09BD ; OLetter # Lo BENGALI SIGN AVAGRAHA +09CE ; OLetter # Lo BENGALI LETTER KHANDA TA +09DC..09DD ; OLetter # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA +09DF..09E1 ; OLetter # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL +09F0..09F1 ; OLetter # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09FC ; OLetter # Lo BENGALI LETTER VEDIC ANUSVARA +0A05..0A0A ; OLetter # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU +0A0F..0A10 ; OLetter # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI +0A13..0A28 ; OLetter # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA +0A2A..0A30 ; OLetter # Lo [7] GURMUKHI LETTER PA..GURMUKHI LETTER RA +0A32..0A33 ; OLetter # Lo [2] GURMUKHI LETTER LA..GURMUKHI LETTER LLA +0A35..0A36 ; OLetter # Lo [2] GURMUKHI LETTER VA..GURMUKHI LETTER SHA +0A38..0A39 ; OLetter # Lo [2] GURMUKHI LETTER SA..GURMUKHI LETTER HA +0A59..0A5C ; OLetter # Lo [4] GURMUKHI LETTER KHHA..GURMUKHI LETTER RRA +0A5E ; OLetter # Lo GURMUKHI LETTER FA +0A72..0A74 ; OLetter # Lo [3] GURMUKHI IRI..GURMUKHI EK ONKAR +0A85..0A8D ; OLetter # Lo [9] GUJARATI LETTER A..GUJARATI VOWEL CANDRA E +0A8F..0A91 ; OLetter # Lo [3] GUJARATI LETTER E..GUJARATI VOWEL CANDRA O +0A93..0AA8 ; OLetter # Lo [22] GUJARATI LETTER O..GUJARATI LETTER NA +0AAA..0AB0 ; OLetter # Lo [7] GUJARATI LETTER PA..GUJARATI LETTER RA +0AB2..0AB3 ; OLetter # Lo [2] GUJARATI LETTER LA..GUJARATI LETTER LLA +0AB5..0AB9 ; OLetter # Lo [5] GUJARATI LETTER VA..GUJARATI LETTER HA +0ABD ; OLetter # Lo GUJARATI SIGN AVAGRAHA +0AD0 ; OLetter # Lo GUJARATI OM +0AE0..0AE1 ; OLetter # Lo [2] GUJARATI LETTER VOCALIC RR..GUJARATI LETTER VOCALIC LL +0AF9 ; OLetter # Lo GUJARATI LETTER ZHA +0B05..0B0C ; OLetter # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L +0B0F..0B10 ; OLetter # Lo [2] ORIYA LETTER E..ORIYA LETTER AI +0B13..0B28 ; OLetter # Lo [22] ORIYA LETTER O..ORIYA LETTER NA +0B2A..0B30 ; OLetter # Lo [7] ORIYA LETTER PA..ORIYA LETTER RA +0B32..0B33 ; OLetter # Lo [2] ORIYA LETTER LA..ORIYA LETTER LLA +0B35..0B39 ; OLetter # Lo [5] ORIYA LETTER VA..ORIYA LETTER HA +0B3D ; OLetter # Lo ORIYA SIGN AVAGRAHA +0B5C..0B5D ; OLetter # Lo [2] ORIYA LETTER RRA..ORIYA LETTER RHA +0B5F..0B61 ; OLetter # Lo [3] ORIYA LETTER YYA..ORIYA LETTER VOCALIC LL +0B71 ; OLetter # Lo ORIYA LETTER WA +0B83 ; OLetter # Lo TAMIL SIGN VISARGA +0B85..0B8A ; OLetter # Lo [6] TAMIL LETTER A..TAMIL LETTER UU +0B8E..0B90 ; OLetter # Lo [3] TAMIL LETTER E..TAMIL LETTER AI +0B92..0B95 ; OLetter # Lo [4] TAMIL LETTER O..TAMIL LETTER KA +0B99..0B9A ; OLetter # Lo [2] TAMIL LETTER NGA..TAMIL LETTER CA +0B9C ; OLetter # Lo TAMIL LETTER JA +0B9E..0B9F ; OLetter # Lo [2] TAMIL LETTER NYA..TAMIL LETTER TTA +0BA3..0BA4 ; OLetter # Lo [2] TAMIL LETTER NNA..TAMIL LETTER TA +0BA8..0BAA ; OLetter # Lo [3] TAMIL LETTER NA..TAMIL LETTER PA +0BAE..0BB9 ; OLetter # Lo [12] TAMIL LETTER MA..TAMIL LETTER HA +0BD0 ; OLetter # Lo TAMIL OM +0C05..0C0C ; OLetter # Lo [8] TELUGU LETTER A..TELUGU LETTER VOCALIC L +0C0E..0C10 ; OLetter # Lo [3] TELUGU LETTER E..TELUGU LETTER AI +0C12..0C28 ; OLetter # Lo [23] TELUGU LETTER O..TELUGU LETTER NA +0C2A..0C39 ; OLetter # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA +0C3D ; OLetter # Lo TELUGU SIGN AVAGRAHA +0C58..0C5A ; OLetter # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; OLetter # Lo TELUGU LETTER NAKAARA POLLU +0C60..0C61 ; OLetter # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL +0C80 ; OLetter # Lo KANNADA SIGN SPACING CANDRABINDU +0C85..0C8C ; OLetter # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L +0C8E..0C90 ; OLetter # Lo [3] KANNADA LETTER E..KANNADA LETTER AI +0C92..0CA8 ; OLetter # Lo [23] KANNADA LETTER O..KANNADA LETTER NA +0CAA..0CB3 ; OLetter # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA +0CB5..0CB9 ; OLetter # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA +0CBD ; OLetter # Lo KANNADA SIGN AVAGRAHA +0CDD..0CDE ; OLetter # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CE0..0CE1 ; OLetter # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL +0CF1..0CF2 ; OLetter # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA +0D04..0D0C ; OLetter # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L +0D0E..0D10 ; OLetter # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI +0D12..0D3A ; OLetter # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA +0D3D ; OLetter # Lo MALAYALAM SIGN AVAGRAHA +0D4E ; OLetter # Lo MALAYALAM LETTER DOT REPH +0D54..0D56 ; OLetter # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL +0D5F..0D61 ; OLetter # Lo [3] MALAYALAM LETTER ARCHAIC II..MALAYALAM LETTER VOCALIC LL +0D7A..0D7F ; OLetter # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K +0D85..0D96 ; OLetter # Lo [18] SINHALA LETTER AYANNA..SINHALA LETTER AUYANNA +0D9A..0DB1 ; OLetter # Lo [24] SINHALA LETTER ALPAPRAANA KAYANNA..SINHALA LETTER DANTAJA NAYANNA +0DB3..0DBB ; OLetter # Lo [9] SINHALA LETTER SANYAKA DAYANNA..SINHALA LETTER RAYANNA +0DBD ; OLetter # Lo SINHALA LETTER DANTAJA LAYANNA +0DC0..0DC6 ; OLetter # Lo [7] SINHALA LETTER VAYANNA..SINHALA LETTER FAYANNA +0E01..0E30 ; OLetter # Lo [48] THAI CHARACTER KO KAI..THAI CHARACTER SARA A +0E32..0E33 ; OLetter # Lo [2] THAI CHARACTER SARA AA..THAI CHARACTER SARA AM +0E40..0E45 ; OLetter # Lo [6] THAI CHARACTER SARA E..THAI CHARACTER LAKKHANGYAO +0E46 ; OLetter # Lm THAI CHARACTER MAIYAMOK +0E81..0E82 ; OLetter # Lo [2] LAO LETTER KO..LAO LETTER KHO SUNG +0E84 ; OLetter # Lo LAO LETTER KHO TAM +0E86..0E8A ; OLetter # Lo [5] LAO LETTER PALI GHA..LAO LETTER SO TAM +0E8C..0EA3 ; OLetter # Lo [24] LAO LETTER PALI JHA..LAO LETTER LO LING +0EA5 ; OLetter # Lo LAO LETTER LO LOOT +0EA7..0EB0 ; OLetter # Lo [10] LAO LETTER WO..LAO VOWEL SIGN A +0EB2..0EB3 ; OLetter # Lo [2] LAO VOWEL SIGN AA..LAO VOWEL SIGN AM +0EBD ; OLetter # Lo LAO SEMIVOWEL SIGN NYO +0EC0..0EC4 ; OLetter # Lo [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI +0EC6 ; OLetter # Lm LAO KO LA +0EDC..0EDF ; OLetter # Lo [4] LAO HO NO..LAO LETTER KHMU NYO +0F00 ; OLetter # Lo TIBETAN SYLLABLE OM +0F40..0F47 ; OLetter # Lo [8] TIBETAN LETTER KA..TIBETAN LETTER JA +0F49..0F6C ; OLetter # Lo [36] TIBETAN LETTER NYA..TIBETAN LETTER RRA +0F88..0F8C ; OLetter # Lo [5] TIBETAN SIGN LCE TSA CAN..TIBETAN SIGN INVERTED MCHU CAN +1000..102A ; OLetter # Lo [43] MYANMAR LETTER KA..MYANMAR LETTER AU +103F ; OLetter # Lo MYANMAR LETTER GREAT SA +1050..1055 ; OLetter # Lo [6] MYANMAR LETTER SHA..MYANMAR LETTER VOCALIC LL +105A..105D ; OLetter # Lo [4] MYANMAR LETTER MON NGA..MYANMAR LETTER MON BBE +1061 ; OLetter # Lo MYANMAR LETTER SGAW KAREN SHA +1065..1066 ; OLetter # Lo [2] MYANMAR LETTER WESTERN PWO KAREN THA..MYANMAR LETTER WESTERN PWO KAREN PWA +106E..1070 ; OLetter # Lo [3] MYANMAR LETTER EASTERN PWO KAREN NNA..MYANMAR LETTER EASTERN PWO KAREN GHWA +1075..1081 ; OLetter # Lo [13] MYANMAR LETTER SHAN KA..MYANMAR LETTER SHAN HA +108E ; OLetter # Lo MYANMAR LETTER RUMAI PALAUNG FA +10D0..10FA ; OLetter # L& [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN +10FC ; OLetter # Lm MODIFIER LETTER GEORGIAN NAR +10FD..10FF ; OLetter # L& [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN +1100..1248 ; OLetter # Lo [329] HANGUL CHOSEONG KIYEOK..ETHIOPIC SYLLABLE QWA +124A..124D ; OLetter # Lo [4] ETHIOPIC SYLLABLE QWI..ETHIOPIC SYLLABLE QWE +1250..1256 ; OLetter # Lo [7] ETHIOPIC SYLLABLE QHA..ETHIOPIC SYLLABLE QHO +1258 ; OLetter # Lo ETHIOPIC SYLLABLE QHWA +125A..125D ; OLetter # Lo [4] ETHIOPIC SYLLABLE QHWI..ETHIOPIC SYLLABLE QHWE +1260..1288 ; OLetter # Lo [41] ETHIOPIC SYLLABLE BA..ETHIOPIC SYLLABLE XWA +128A..128D ; OLetter # Lo [4] ETHIOPIC SYLLABLE XWI..ETHIOPIC SYLLABLE XWE +1290..12B0 ; OLetter # Lo [33] ETHIOPIC SYLLABLE NA..ETHIOPIC SYLLABLE KWA +12B2..12B5 ; OLetter # Lo [4] ETHIOPIC SYLLABLE KWI..ETHIOPIC SYLLABLE KWE +12B8..12BE ; OLetter # Lo [7] ETHIOPIC SYLLABLE KXA..ETHIOPIC SYLLABLE KXO +12C0 ; OLetter # Lo ETHIOPIC SYLLABLE KXWA +12C2..12C5 ; OLetter # Lo [4] ETHIOPIC SYLLABLE KXWI..ETHIOPIC SYLLABLE KXWE +12C8..12D6 ; OLetter # Lo [15] ETHIOPIC SYLLABLE WA..ETHIOPIC SYLLABLE PHARYNGEAL O +12D8..1310 ; OLetter # Lo [57] ETHIOPIC SYLLABLE ZA..ETHIOPIC SYLLABLE GWA +1312..1315 ; OLetter # Lo [4] ETHIOPIC SYLLABLE GWI..ETHIOPIC SYLLABLE GWE +1318..135A ; OLetter # Lo [67] ETHIOPIC SYLLABLE GGA..ETHIOPIC SYLLABLE FYA +1380..138F ; OLetter # Lo [16] ETHIOPIC SYLLABLE SEBATBEIT MWA..ETHIOPIC SYLLABLE PWE +1401..166C ; OLetter # Lo [620] CANADIAN SYLLABICS E..CANADIAN SYLLABICS CARRIER TTSA +166F..167F ; OLetter # Lo [17] CANADIAN SYLLABICS QAI..CANADIAN SYLLABICS BLACKFOOT W +1681..169A ; OLetter # Lo [26] OGHAM LETTER BEITH..OGHAM LETTER PEITH +16A0..16EA ; OLetter # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X +16EE..16F0 ; OLetter # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL +16F1..16F8 ; OLetter # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC +1700..1711 ; OLetter # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA +171F..1731 ; OLetter # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA +1740..1751 ; OLetter # Lo [18] BUHID LETTER A..BUHID LETTER HA +1760..176C ; OLetter # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA +176E..1770 ; OLetter # Lo [3] TAGBANWA LETTER LA..TAGBANWA LETTER SA +1780..17B3 ; OLetter # Lo [52] KHMER LETTER KA..KHMER INDEPENDENT VOWEL QAU +17D7 ; OLetter # Lm KHMER SIGN LEK TOO +17DC ; OLetter # Lo KHMER SIGN AVAKRAHASANYA +1820..1842 ; OLetter # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI +1843 ; OLetter # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1844..1878 ; OLetter # Lo [53] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER CHA WITH TWO DOTS +1880..1884 ; OLetter # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA +1887..18A8 ; OLetter # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA +18AA ; OLetter # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA +18B0..18F5 ; OLetter # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S +1900..191E ; OLetter # Lo [31] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER TRA +1950..196D ; OLetter # Lo [30] TAI LE LETTER KA..TAI LE LETTER AI +1970..1974 ; OLetter # Lo [5] TAI LE LETTER TONE-2..TAI LE LETTER TONE-6 +1980..19AB ; OLetter # Lo [44] NEW TAI LUE LETTER HIGH QA..NEW TAI LUE LETTER LOW SUA +19B0..19C9 ; OLetter # Lo [26] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2 +1A00..1A16 ; OLetter # Lo [23] BUGINESE LETTER KA..BUGINESE LETTER HA +1A20..1A54 ; OLetter # Lo [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA +1AA7 ; OLetter # Lm TAI THAM SIGN MAI YAMOK +1B05..1B33 ; OLetter # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA +1B45..1B4C ; OLetter # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA +1B83..1BA0 ; OLetter # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA +1BAE..1BAF ; OLetter # Lo [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA +1BBA..1BE5 ; OLetter # Lo [44] SUNDANESE AVAGRAHA..BATAK LETTER U +1C00..1C23 ; OLetter # Lo [36] LEPCHA LETTER KA..LEPCHA LETTER A +1C4D..1C4F ; OLetter # Lo [3] LEPCHA LETTER TTA..LEPCHA LETTER DDA +1C5A..1C77 ; OLetter # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH +1C78..1C7D ; OLetter # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD +1C90..1CBA ; OLetter # L& [43] GEORGIAN MTAVRULI CAPITAL LETTER AN..GEORGIAN MTAVRULI CAPITAL LETTER AIN +1CBD..1CBF ; OLetter # L& [3] GEORGIAN MTAVRULI CAPITAL LETTER AEN..GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN +1CE9..1CEC ; OLetter # Lo [4] VEDIC SIGN ANUSVARA ANTARGOMUKHA..VEDIC SIGN ANUSVARA VAMAGOMUKHA WITH TAIL +1CEE..1CF3 ; OLetter # Lo [6] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ROTATED ARDHAVISARGA +1CF5..1CF6 ; OLetter # Lo [2] VEDIC SIGN JIHVAMULIYA..VEDIC SIGN UPADHMANIYA +1CFA ; OLetter # Lo VEDIC SIGN DOUBLE ANUSVARA ANTARGOMUKHA +2135..2138 ; OLetter # Lo [4] ALEF SYMBOL..DALET SYMBOL +2180..2182 ; OLetter # Nl [3] ROMAN NUMERAL ONE THOUSAND C D..ROMAN NUMERAL TEN THOUSAND +2185..2188 ; OLetter # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND +2D30..2D67 ; OLetter # Lo [56] TIFINAGH LETTER YA..TIFINAGH LETTER YO +2D6F ; OLetter # Lm TIFINAGH MODIFIER LETTER LABIALIZATION MARK +2D80..2D96 ; OLetter # Lo [23] ETHIOPIC SYLLABLE LOA..ETHIOPIC SYLLABLE GGWE +2DA0..2DA6 ; OLetter # Lo [7] ETHIOPIC SYLLABLE SSA..ETHIOPIC SYLLABLE SSO +2DA8..2DAE ; OLetter # Lo [7] ETHIOPIC SYLLABLE CCA..ETHIOPIC SYLLABLE CCO +2DB0..2DB6 ; OLetter # Lo [7] ETHIOPIC SYLLABLE ZZA..ETHIOPIC SYLLABLE ZZO +2DB8..2DBE ; OLetter # Lo [7] ETHIOPIC SYLLABLE CCHA..ETHIOPIC SYLLABLE CCHO +2DC0..2DC6 ; OLetter # Lo [7] ETHIOPIC SYLLABLE QYA..ETHIOPIC SYLLABLE QYO +2DC8..2DCE ; OLetter # Lo [7] ETHIOPIC SYLLABLE KYA..ETHIOPIC SYLLABLE KYO +2DD0..2DD6 ; OLetter # Lo [7] ETHIOPIC SYLLABLE XYA..ETHIOPIC SYLLABLE XYO +2DD8..2DDE ; OLetter # Lo [7] ETHIOPIC SYLLABLE GYA..ETHIOPIC SYLLABLE GYO +2E2F ; OLetter # Lm VERTICAL TILDE +3005 ; OLetter # Lm IDEOGRAPHIC ITERATION MARK +3006 ; OLetter # Lo IDEOGRAPHIC CLOSING MARK +3007 ; OLetter # Nl IDEOGRAPHIC NUMBER ZERO +3021..3029 ; OLetter # Nl [9] HANGZHOU NUMERAL ONE..HANGZHOU NUMERAL NINE +3031..3035 ; OLetter # Lm [5] VERTICAL KANA REPEAT MARK..VERTICAL KANA REPEAT MARK LOWER HALF +3038..303A ; OLetter # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY +303B ; OLetter # Lm VERTICAL IDEOGRAPHIC ITERATION MARK +303C ; OLetter # Lo MASU MARK +3041..3096 ; OLetter # Lo [86] HIRAGANA LETTER SMALL A..HIRAGANA LETTER SMALL KE +309D..309E ; OLetter # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK +309F ; OLetter # Lo HIRAGANA DIGRAPH YORI +30A1..30FA ; OLetter # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO +30FC..30FE ; OLetter # Lm [3] KATAKANA-HIRAGANA PROLONGED SOUND MARK..KATAKANA VOICED ITERATION MARK +30FF ; OLetter # Lo KATAKANA DIGRAPH KOTO +3105..312F ; OLetter # Lo [43] BOPOMOFO LETTER B..BOPOMOFO LETTER NN +3131..318E ; OLetter # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE +31A0..31BF ; OLetter # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH +31F0..31FF ; OLetter # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO +3400..4DBF ; OLetter # Lo [6592] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DBF +4E00..A014 ; OLetter # Lo [21013] CJK UNIFIED IDEOGRAPH-4E00..YI SYLLABLE E +A015 ; OLetter # Lm YI SYLLABLE WU +A016..A48C ; OLetter # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR +A4D0..A4F7 ; OLetter # Lo [40] LISU LETTER BA..LISU LETTER OE +A4F8..A4FD ; OLetter # Lm [6] LISU LETTER TONE MYA TI..LISU LETTER TONE MYA JEU +A500..A60B ; OLetter # Lo [268] VAI SYLLABLE EE..VAI SYLLABLE NG +A60C ; OLetter # Lm VAI SYLLABLE LENGTHENER +A610..A61F ; OLetter # Lo [16] VAI SYLLABLE NDOLE FA..VAI SYMBOL JONG +A62A..A62B ; OLetter # Lo [2] VAI SYLLABLE NDOLE MA..VAI SYLLABLE NDOLE DO +A66E ; OLetter # Lo CYRILLIC LETTER MULTIOCULAR O +A67F ; OLetter # Lm CYRILLIC PAYEROK +A6A0..A6E5 ; OLetter # Lo [70] BAMUM LETTER A..BAMUM LETTER KI +A6E6..A6EF ; OLetter # Nl [10] BAMUM LETTER MO..BAMUM LETTER KOGHOM +A717..A71F ; OLetter # Lm [9] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOW INVERTED EXCLAMATION MARK +A788 ; OLetter # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT +A78F ; OLetter # Lo LATIN LETTER SINOLOGICAL DOT +A7F2..A7F4 ; OLetter # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F7 ; OLetter # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I +A7FB..A801 ; OLetter # Lo [7] LATIN EPIGRAPHIC LETTER REVERSED F..SYLOTI NAGRI LETTER I +A803..A805 ; OLetter # Lo [3] SYLOTI NAGRI LETTER U..SYLOTI NAGRI LETTER O +A807..A80A ; OLetter # Lo [4] SYLOTI NAGRI LETTER KO..SYLOTI NAGRI LETTER GHO +A80C..A822 ; OLetter # Lo [23] SYLOTI NAGRI LETTER CO..SYLOTI NAGRI LETTER HO +A840..A873 ; OLetter # Lo [52] PHAGS-PA LETTER KA..PHAGS-PA LETTER CANDRABINDU +A882..A8B3 ; OLetter # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA +A8F2..A8F7 ; OLetter # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA +A8FB ; OLetter # Lo DEVANAGARI HEADSTROKE +A8FD..A8FE ; OLetter # Lo [2] DEVANAGARI JAIN OM..DEVANAGARI LETTER AY +A90A..A925 ; OLetter # Lo [28] KAYAH LI LETTER KA..KAYAH LI LETTER OO +A930..A946 ; OLetter # Lo [23] REJANG LETTER KA..REJANG LETTER A +A960..A97C ; OLetter # Lo [29] HANGUL CHOSEONG TIKEUT-MIEUM..HANGUL CHOSEONG SSANGYEORINHIEUH +A984..A9B2 ; OLetter # Lo [47] JAVANESE LETTER A..JAVANESE LETTER HA +A9CF ; OLetter # Lm JAVANESE PANGRANGKEP +A9E0..A9E4 ; OLetter # Lo [5] MYANMAR LETTER SHAN GHA..MYANMAR LETTER SHAN BHA +A9E6 ; OLetter # Lm MYANMAR MODIFIER LETTER SHAN REDUPLICATION +A9E7..A9EF ; OLetter # Lo [9] MYANMAR LETTER TAI LAING NYA..MYANMAR LETTER TAI LAING NNA +A9FA..A9FE ; OLetter # Lo [5] MYANMAR LETTER TAI LAING LLA..MYANMAR LETTER TAI LAING BHA +AA00..AA28 ; OLetter # Lo [41] CHAM LETTER A..CHAM LETTER HA +AA40..AA42 ; OLetter # Lo [3] CHAM LETTER FINAL K..CHAM LETTER FINAL NG +AA44..AA4B ; OLetter # Lo [8] CHAM LETTER FINAL CH..CHAM LETTER FINAL SS +AA60..AA6F ; OLetter # Lo [16] MYANMAR LETTER KHAMTI GA..MYANMAR LETTER KHAMTI FA +AA70 ; OLetter # Lm MYANMAR MODIFIER LETTER KHAMTI REDUPLICATION +AA71..AA76 ; OLetter # Lo [6] MYANMAR LETTER KHAMTI XA..MYANMAR LOGOGRAM KHAMTI HM +AA7A ; OLetter # Lo MYANMAR LETTER AITON RA +AA7E..AAAF ; OLetter # Lo [50] MYANMAR LETTER SHWE PALAUNG CHA..TAI VIET LETTER HIGH O +AAB1 ; OLetter # Lo TAI VIET VOWEL AA +AAB5..AAB6 ; OLetter # Lo [2] TAI VIET VOWEL E..TAI VIET VOWEL O +AAB9..AABD ; OLetter # Lo [5] TAI VIET VOWEL UEA..TAI VIET VOWEL AN +AAC0 ; OLetter # Lo TAI VIET TONE MAI NUENG +AAC2 ; OLetter # Lo TAI VIET TONE MAI SONG +AADB..AADC ; OLetter # Lo [2] TAI VIET SYMBOL KON..TAI VIET SYMBOL NUENG +AADD ; OLetter # Lm TAI VIET SYMBOL SAM +AAE0..AAEA ; OLetter # Lo [11] MEETEI MAYEK LETTER E..MEETEI MAYEK LETTER SSA +AAF2 ; OLetter # Lo MEETEI MAYEK ANJI +AAF3..AAF4 ; OLetter # Lm [2] MEETEI MAYEK SYLLABLE REPETITION MARK..MEETEI MAYEK WORD REPETITION MARK +AB01..AB06 ; OLetter # Lo [6] ETHIOPIC SYLLABLE TTHU..ETHIOPIC SYLLABLE TTHO +AB09..AB0E ; OLetter # Lo [6] ETHIOPIC SYLLABLE DDHU..ETHIOPIC SYLLABLE DDHO +AB11..AB16 ; OLetter # Lo [6] ETHIOPIC SYLLABLE DZU..ETHIOPIC SYLLABLE DZO +AB20..AB26 ; OLetter # Lo [7] ETHIOPIC SYLLABLE CCHHA..ETHIOPIC SYLLABLE CCHHO +AB28..AB2E ; OLetter # Lo [7] ETHIOPIC SYLLABLE BBA..ETHIOPIC SYLLABLE BBO +AB69 ; OLetter # Lm MODIFIER LETTER SMALL TURNED W +ABC0..ABE2 ; OLetter # Lo [35] MEETEI MAYEK LETTER KOK..MEETEI MAYEK LETTER I LONSUM +AC00..D7A3 ; OLetter # Lo [11172] HANGUL SYLLABLE GA..HANGUL SYLLABLE HIH +D7B0..D7C6 ; OLetter # Lo [23] HANGUL JUNGSEONG O-YEO..HANGUL JUNGSEONG ARAEA-E +D7CB..D7FB ; OLetter # Lo [49] HANGUL JONGSEONG NIEUN-RIEUL..HANGUL JONGSEONG PHIEUPH-THIEUTH +F900..FA6D ; OLetter # Lo [366] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA6D +FA70..FAD9 ; OLetter # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9 +FB1D ; OLetter # Lo HEBREW LETTER YOD WITH HIRIQ +FB1F..FB28 ; OLetter # Lo [10] HEBREW LIGATURE YIDDISH YOD YOD PATAH..HEBREW LETTER WIDE TAV +FB2A..FB36 ; OLetter # Lo [13] HEBREW LETTER SHIN WITH SHIN DOT..HEBREW LETTER ZAYIN WITH DAGESH +FB38..FB3C ; OLetter # Lo [5] HEBREW LETTER TET WITH DAGESH..HEBREW LETTER LAMED WITH DAGESH +FB3E ; OLetter # Lo HEBREW LETTER MEM WITH DAGESH +FB40..FB41 ; OLetter # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SAMEKH WITH DAGESH +FB43..FB44 ; OLetter # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH +FB46..FBB1 ; OLetter # Lo [108] HEBREW LETTER TSADI WITH DAGESH..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM +FBD3..FD3D ; OLetter # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM +FD50..FD8F ; OLetter # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM +FD92..FDC7 ; OLetter # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM +FDF0..FDFB ; OLetter # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU +FE70..FE74 ; OLetter # Lo [5] ARABIC FATHATAN ISOLATED FORM..ARABIC KASRATAN ISOLATED FORM +FE76..FEFC ; OLetter # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM +FF66..FF6F ; OLetter # Lo [10] HALFWIDTH KATAKANA LETTER WO..HALFWIDTH KATAKANA LETTER SMALL TU +FF70 ; OLetter # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK +FF71..FF9D ; OLetter # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAKANA LETTER N +FFA0..FFBE ; OLetter # Lo [31] HALFWIDTH HANGUL FILLER..HALFWIDTH HANGUL LETTER HIEUH +FFC2..FFC7 ; OLetter # Lo [6] HALFWIDTH HANGUL LETTER A..HALFWIDTH HANGUL LETTER E +FFCA..FFCF ; OLetter # Lo [6] HALFWIDTH HANGUL LETTER YEO..HALFWIDTH HANGUL LETTER OE +FFD2..FFD7 ; OLetter # Lo [6] HALFWIDTH HANGUL LETTER YO..HALFWIDTH HANGUL LETTER YU +FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I +10000..1000B ; OLetter # Lo [12] LINEAR B SYLLABLE B008 A..LINEAR B SYLLABLE B046 JE +1000D..10026 ; OLetter # Lo [26] LINEAR B SYLLABLE B036 JO..LINEAR B SYLLABLE B032 QO +10028..1003A ; OLetter # Lo [19] LINEAR B SYLLABLE B060 RA..LINEAR B SYLLABLE B042 WO +1003C..1003D ; OLetter # Lo [2] LINEAR B SYLLABLE B017 ZA..LINEAR B SYLLABLE B074 ZE +1003F..1004D ; OLetter # Lo [15] LINEAR B SYLLABLE B020 ZO..LINEAR B SYLLABLE B091 TWO +10050..1005D ; OLetter # Lo [14] LINEAR B SYMBOL B018..LINEAR B SYMBOL B089 +10080..100FA ; OLetter # Lo [123] LINEAR B IDEOGRAM B100 MAN..LINEAR B IDEOGRAM VESSEL B305 +10140..10174 ; OLetter # Nl [53] GREEK ACROPHONIC ATTIC ONE QUARTER..GREEK ACROPHONIC STRATIAN FIFTY MNAS +10280..1029C ; OLetter # Lo [29] LYCIAN LETTER A..LYCIAN LETTER X +102A0..102D0 ; OLetter # Lo [49] CARIAN LETTER A..CARIAN LETTER UUU3 +10300..1031F ; OLetter # Lo [32] OLD ITALIC LETTER A..OLD ITALIC LETTER ESS +1032D..10340 ; OLetter # Lo [20] OLD ITALIC LETTER YE..GOTHIC LETTER PAIRTHRA +10341 ; OLetter # Nl GOTHIC LETTER NINETY +10342..10349 ; OLetter # Lo [8] GOTHIC LETTER RAIDA..GOTHIC LETTER OTHAL +1034A ; OLetter # Nl GOTHIC LETTER NINE HUNDRED +10350..10375 ; OLetter # Lo [38] OLD PERMIC LETTER AN..OLD PERMIC LETTER IA +10380..1039D ; OLetter # Lo [30] UGARITIC LETTER ALPA..UGARITIC LETTER SSU +103A0..103C3 ; OLetter # Lo [36] OLD PERSIAN SIGN A..OLD PERSIAN SIGN HA +103C8..103CF ; OLetter # Lo [8] OLD PERSIAN SIGN AURAMAZDAA..OLD PERSIAN SIGN BUUMISH +103D1..103D5 ; OLetter # Nl [5] OLD PERSIAN NUMBER ONE..OLD PERSIAN NUMBER HUNDRED +10450..1049D ; OLetter # Lo [78] SHAVIAN LETTER PEEP..OSMANYA LETTER OO +10500..10527 ; OLetter # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE +10530..10563 ; OLetter # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +10600..10736 ; OLetter # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 +10740..10755 ; OLetter # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE +10760..10767 ; OLetter # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10781..10782 ; OLetter # Lm [2] MODIFIER LETTER SUPERSCRIPT TRIANGULAR COLON..MODIFIER LETTER SUPERSCRIPT HALF TRIANGULAR COLON +10800..10805 ; OLetter # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA +10808 ; OLetter # Lo CYPRIOT SYLLABLE JO +1080A..10835 ; OLetter # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO +10837..10838 ; OLetter # Lo [2] CYPRIOT SYLLABLE XA..CYPRIOT SYLLABLE XE +1083C ; OLetter # Lo CYPRIOT SYLLABLE ZA +1083F..10855 ; OLetter # Lo [23] CYPRIOT SYLLABLE ZO..IMPERIAL ARAMAIC LETTER TAW +10860..10876 ; OLetter # Lo [23] PALMYRENE LETTER ALEPH..PALMYRENE LETTER TAW +10880..1089E ; OLetter # Lo [31] NABATAEAN LETTER FINAL ALEPH..NABATAEAN LETTER TAW +108E0..108F2 ; OLetter # Lo [19] HATRAN LETTER ALEPH..HATRAN LETTER QOPH +108F4..108F5 ; OLetter # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW +10900..10915 ; OLetter # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU +10920..10939 ; OLetter # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +10980..109B7 ; OLetter # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA +109BE..109BF ; OLetter # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN +10A00 ; OLetter # Lo KHAROSHTHI LETTER A +10A10..10A13 ; OLetter # Lo [4] KHAROSHTHI LETTER KA..KHAROSHTHI LETTER GHA +10A15..10A17 ; OLetter # Lo [3] KHAROSHTHI LETTER CA..KHAROSHTHI LETTER JA +10A19..10A35 ; OLetter # Lo [29] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER VHA +10A60..10A7C ; OLetter # Lo [29] OLD SOUTH ARABIAN LETTER HE..OLD SOUTH ARABIAN LETTER THETH +10A80..10A9C ; OLetter # Lo [29] OLD NORTH ARABIAN LETTER HEH..OLD NORTH ARABIAN LETTER ZAH +10AC0..10AC7 ; OLetter # Lo [8] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER WAW +10AC9..10AE4 ; OLetter # Lo [28] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER TAW +10B00..10B35 ; OLetter # Lo [54] AVESTAN LETTER A..AVESTAN LETTER HE +10B40..10B55 ; OLetter # Lo [22] INSCRIPTIONAL PARTHIAN LETTER ALEPH..INSCRIPTIONAL PARTHIAN LETTER TAW +10B60..10B72 ; OLetter # Lo [19] INSCRIPTIONAL PAHLAVI LETTER ALEPH..INSCRIPTIONAL PAHLAVI LETTER TAW +10B80..10B91 ; OLetter # Lo [18] PSALTER PAHLAVI LETTER ALEPH..PSALTER PAHLAVI LETTER TAW +10C00..10C48 ; OLetter # Lo [73] OLD TURKIC LETTER ORKHON A..OLD TURKIC LETTER ORKHON BASH +10D00..10D23 ; OLetter # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA +10E80..10EA9 ; OLetter # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET +10EB0..10EB1 ; OLetter # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE +10F00..10F1C ; OLetter # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL +10F27 ; OLetter # Lo OLD SOGDIAN LIGATURE AYIN-DALETH +10F30..10F45 ; OLetter # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN +10F70..10F81 ; OLetter # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH +10FB0..10FC4 ; OLetter # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW +10FE0..10FF6 ; OLetter # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH +11003..11037 ; OLetter # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA +11071..11072 ; OLetter # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11075 ; OLetter # Lo BRAHMI LETTER OLD TAMIL LLA +11083..110AF ; OLetter # Lo [45] KAITHI LETTER A..KAITHI LETTER HA +110D0..110E8 ; OLetter # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE +11103..11126 ; OLetter # Lo [36] CHAKMA LETTER AA..CHAKMA LETTER HAA +11144 ; OLetter # Lo CHAKMA LETTER LHAA +11147 ; OLetter # Lo CHAKMA LETTER VAA +11150..11172 ; OLetter # Lo [35] MAHAJANI LETTER A..MAHAJANI LETTER RRA +11176 ; OLetter # Lo MAHAJANI LIGATURE SHRI +11183..111B2 ; OLetter # Lo [48] SHARADA LETTER A..SHARADA LETTER HA +111C1..111C4 ; OLetter # Lo [4] SHARADA SIGN AVAGRAHA..SHARADA OM +111DA ; OLetter # Lo SHARADA EKAM +111DC ; OLetter # Lo SHARADA HEADSTROKE +11200..11211 ; OLetter # Lo [18] KHOJKI LETTER A..KHOJKI LETTER JJA +11213..1122B ; OLetter # Lo [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA +11280..11286 ; OLetter # Lo [7] MULTANI LETTER A..MULTANI LETTER GA +11288 ; OLetter # Lo MULTANI LETTER GHA +1128A..1128D ; OLetter # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA +1128F..1129D ; OLetter # Lo [15] MULTANI LETTER NYA..MULTANI LETTER BA +1129F..112A8 ; OLetter # Lo [10] MULTANI LETTER BHA..MULTANI LETTER RHA +112B0..112DE ; OLetter # Lo [47] KHUDAWADI LETTER A..KHUDAWADI LETTER HA +11305..1130C ; OLetter # Lo [8] GRANTHA LETTER A..GRANTHA LETTER VOCALIC L +1130F..11310 ; OLetter # Lo [2] GRANTHA LETTER EE..GRANTHA LETTER AI +11313..11328 ; OLetter # Lo [22] GRANTHA LETTER OO..GRANTHA LETTER NA +1132A..11330 ; OLetter # Lo [7] GRANTHA LETTER PA..GRANTHA LETTER RA +11332..11333 ; OLetter # Lo [2] GRANTHA LETTER LA..GRANTHA LETTER LLA +11335..11339 ; OLetter # Lo [5] GRANTHA LETTER VA..GRANTHA LETTER HA +1133D ; OLetter # Lo GRANTHA SIGN AVAGRAHA +11350 ; OLetter # Lo GRANTHA OM +1135D..11361 ; OLetter # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL +11400..11434 ; OLetter # Lo [53] NEWA LETTER A..NEWA LETTER HA +11447..1144A ; OLetter # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI +1145F..11461 ; OLetter # Lo [3] NEWA LETTER VEDIC ANUSVARA..NEWA SIGN UPADHMANIYA +11480..114AF ; OLetter # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA +114C4..114C5 ; OLetter # Lo [2] TIRHUTA SIGN AVAGRAHA..TIRHUTA GVANG +114C7 ; OLetter # Lo TIRHUTA OM +11580..115AE ; OLetter # Lo [47] SIDDHAM LETTER A..SIDDHAM LETTER HA +115D8..115DB ; OLetter # Lo [4] SIDDHAM LETTER THREE-CIRCLE ALTERNATE I..SIDDHAM LETTER ALTERNATE U +11600..1162F ; OLetter # Lo [48] MODI LETTER A..MODI LETTER LLA +11644 ; OLetter # Lo MODI SIGN HUVA +11680..116AA ; OLetter # Lo [43] TAKRI LETTER A..TAKRI LETTER RRA +116B8 ; OLetter # Lo TAKRI LETTER ARCHAIC KHA +11700..1171A ; OLetter # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA +11740..11746 ; OLetter # Lo [7] AHOM LETTER CA..AHOM LETTER LLA +11800..1182B ; OLetter # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA +118FF..11906 ; OLetter # Lo [8] WARANG CITI OM..DIVES AKURU LETTER E +11909 ; OLetter # Lo DIVES AKURU LETTER O +1190C..11913 ; OLetter # Lo [8] DIVES AKURU LETTER KA..DIVES AKURU LETTER JA +11915..11916 ; OLetter # Lo [2] DIVES AKURU LETTER NYA..DIVES AKURU LETTER TTA +11918..1192F ; OLetter # Lo [24] DIVES AKURU LETTER DDA..DIVES AKURU LETTER ZA +1193F ; OLetter # Lo DIVES AKURU PREFIXED NASAL SIGN +11941 ; OLetter # Lo DIVES AKURU INITIAL RA +119A0..119A7 ; OLetter # Lo [8] NANDINAGARI LETTER A..NANDINAGARI LETTER VOCALIC RR +119AA..119D0 ; OLetter # Lo [39] NANDINAGARI LETTER E..NANDINAGARI LETTER RRA +119E1 ; OLetter # Lo NANDINAGARI SIGN AVAGRAHA +119E3 ; OLetter # Lo NANDINAGARI HEADSTROKE +11A00 ; OLetter # Lo ZANABAZAR SQUARE LETTER A +11A0B..11A32 ; OLetter # Lo [40] ZANABAZAR SQUARE LETTER KA..ZANABAZAR SQUARE LETTER KSSA +11A3A ; OLetter # Lo ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA +11A50 ; OLetter # Lo SOYOMBO LETTER A +11A5C..11A89 ; OLetter # Lo [46] SOYOMBO LETTER KA..SOYOMBO CLUSTER-INITIAL LETTER SA +11A9D ; OLetter # Lo SOYOMBO MARK PLUTA +11AB0..11AF8 ; OLetter # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL +11C00..11C08 ; OLetter # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L +11C0A..11C2E ; OLetter # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA +11C40 ; OLetter # Lo BHAIKSUKI SIGN AVAGRAHA +11C72..11C8F ; OLetter # Lo [30] MARCHEN LETTER KA..MARCHEN LETTER A +11D00..11D06 ; OLetter # Lo [7] MASARAM GONDI LETTER A..MASARAM GONDI LETTER E +11D08..11D09 ; OLetter # Lo [2] MASARAM GONDI LETTER AI..MASARAM GONDI LETTER O +11D0B..11D30 ; OLetter # Lo [38] MASARAM GONDI LETTER AU..MASARAM GONDI LETTER TRA +11D46 ; OLetter # Lo MASARAM GONDI REPHA +11D60..11D65 ; OLetter # Lo [6] GUNJALA GONDI LETTER A..GUNJALA GONDI LETTER UU +11D67..11D68 ; OLetter # Lo [2] GUNJALA GONDI LETTER EE..GUNJALA GONDI LETTER AI +11D6A..11D89 ; OLetter # Lo [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA +11D98 ; OLetter # Lo GUNJALA GONDI OM +11EE0..11EF2 ; OLetter # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA +11FB0 ; OLetter # Lo LISU LETTER YHA +12000..12399 ; OLetter # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U +12400..1246E ; OLetter # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM +12480..12543 ; OLetter # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU +12F90..12FF0 ; OLetter # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 +13000..1342E ; OLetter # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 +14400..14646 ; OLetter # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 +16800..16A38 ; OLetter # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ +16A40..16A5E ; OLetter # Lo [31] MRO LETTER TA..MRO LETTER TEK +16A70..16ABE ; OLetter # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA +16AD0..16AED ; OLetter # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I +16B00..16B2F ; OLetter # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU +16B40..16B43 ; OLetter # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM +16B63..16B77 ; OLetter # Lo [21] PAHAWH HMONG SIGN VOS LUB..PAHAWH HMONG SIGN CIM NRES TOS +16B7D..16B8F ; OLetter # Lo [19] PAHAWH HMONG CLAN SIGN TSHEEJ..PAHAWH HMONG CLAN SIGN VWJ +16F00..16F4A ; OLetter # Lo [75] MIAO LETTER PA..MIAO LETTER RTE +16F50 ; OLetter # Lo MIAO LETTER NASALIZATION +16F93..16F9F ; OLetter # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 +16FE0..16FE1 ; OLetter # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK +16FE3 ; OLetter # Lm OLD CHINESE ITERATION MARK +17000..187F7 ; OLetter # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 +18800..18CD5 ; OLetter # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 +18D00..18D08 ; OLetter # Lo [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08 +1AFF0..1AFF3 ; OLetter # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; OLetter # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; OLetter # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 +1B000..1B122 ; OLetter # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU +1B150..1B152 ; OLetter # Lo [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO +1B164..1B167 ; OLetter # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N +1B170..1B2FB ; OLetter # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB +1BC00..1BC6A ; OLetter # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M +1BC70..1BC7C ; OLetter # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK +1BC80..1BC88 ; OLetter # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL +1BC90..1BC99 ; OLetter # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW +1DF0A ; OLetter # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1E100..1E12C ; OLetter # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W +1E137..1E13D ; OLetter # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER +1E14E ; OLetter # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; OLetter # Lo [30] TOTO LETTER PA..TOTO LETTER A +1E2C0..1E2EB ; OLetter # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH +1E7E0..1E7E6 ; OLetter # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; OLetter # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; OLetter # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; OLetter # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE +1E800..1E8C4 ; OLetter # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON +1E94B ; OLetter # Lm ADLAM NASALIZATION MARK +1EE00..1EE03 ; OLetter # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL +1EE05..1EE1F ; OLetter # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF +1EE21..1EE22 ; OLetter # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM +1EE24 ; OLetter # Lo ARABIC MATHEMATICAL INITIAL HEH +1EE27 ; OLetter # Lo ARABIC MATHEMATICAL INITIAL HAH +1EE29..1EE32 ; OLetter # Lo [10] ARABIC MATHEMATICAL INITIAL YEH..ARABIC MATHEMATICAL INITIAL QAF +1EE34..1EE37 ; OLetter # Lo [4] ARABIC MATHEMATICAL INITIAL SHEEN..ARABIC MATHEMATICAL INITIAL KHAH +1EE39 ; OLetter # Lo ARABIC MATHEMATICAL INITIAL DAD +1EE3B ; OLetter # Lo ARABIC MATHEMATICAL INITIAL GHAIN +1EE42 ; OLetter # Lo ARABIC MATHEMATICAL TAILED JEEM +1EE47 ; OLetter # Lo ARABIC MATHEMATICAL TAILED HAH +1EE49 ; OLetter # Lo ARABIC MATHEMATICAL TAILED YEH +1EE4B ; OLetter # Lo ARABIC MATHEMATICAL TAILED LAM +1EE4D..1EE4F ; OLetter # Lo [3] ARABIC MATHEMATICAL TAILED NOON..ARABIC MATHEMATICAL TAILED AIN +1EE51..1EE52 ; OLetter # Lo [2] ARABIC MATHEMATICAL TAILED SAD..ARABIC MATHEMATICAL TAILED QAF +1EE54 ; OLetter # Lo ARABIC MATHEMATICAL TAILED SHEEN +1EE57 ; OLetter # Lo ARABIC MATHEMATICAL TAILED KHAH +1EE59 ; OLetter # Lo ARABIC MATHEMATICAL TAILED DAD +1EE5B ; OLetter # Lo ARABIC MATHEMATICAL TAILED GHAIN +1EE5D ; OLetter # Lo ARABIC MATHEMATICAL TAILED DOTLESS NOON +1EE5F ; OLetter # Lo ARABIC MATHEMATICAL TAILED DOTLESS QAF +1EE61..1EE62 ; OLetter # Lo [2] ARABIC MATHEMATICAL STRETCHED BEH..ARABIC MATHEMATICAL STRETCHED JEEM +1EE64 ; OLetter # Lo ARABIC MATHEMATICAL STRETCHED HEH +1EE67..1EE6A ; OLetter # Lo [4] ARABIC MATHEMATICAL STRETCHED HAH..ARABIC MATHEMATICAL STRETCHED KAF +1EE6C..1EE72 ; OLetter # Lo [7] ARABIC MATHEMATICAL STRETCHED MEEM..ARABIC MATHEMATICAL STRETCHED QAF +1EE74..1EE77 ; OLetter # Lo [4] ARABIC MATHEMATICAL STRETCHED SHEEN..ARABIC MATHEMATICAL STRETCHED KHAH +1EE79..1EE7C ; OLetter # Lo [4] ARABIC MATHEMATICAL STRETCHED DAD..ARABIC MATHEMATICAL STRETCHED DOTLESS BEH +1EE7E ; OLetter # Lo ARABIC MATHEMATICAL STRETCHED DOTLESS FEH +1EE80..1EE89 ; OLetter # Lo [10] ARABIC MATHEMATICAL LOOPED ALEF..ARABIC MATHEMATICAL LOOPED YEH +1EE8B..1EE9B ; OLetter # Lo [17] ARABIC MATHEMATICAL LOOPED LAM..ARABIC MATHEMATICAL LOOPED GHAIN +1EEA1..1EEA3 ; OLetter # Lo [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL +1EEA5..1EEA9 ; OLetter # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH +1EEAB..1EEBB ; OLetter # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN +20000..2A6DF ; OLetter # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF +2A700..2B738 ; OLetter # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738 +2B740..2B81D ; OLetter # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D +2B820..2CEA1 ; OLetter # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1 +2CEB0..2EBE0 ; OLetter # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0 +2F800..2FA1D ; OLetter # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D +30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A + +# Total code points: 127761 + +# ================================================ + +0030..0039 ; Numeric # Nd [10] DIGIT ZERO..DIGIT NINE +0660..0669 ; Numeric # Nd [10] ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE +066B..066C ; Numeric # Po [2] ARABIC DECIMAL SEPARATOR..ARABIC THOUSANDS SEPARATOR +06F0..06F9 ; Numeric # Nd [10] EXTENDED ARABIC-INDIC DIGIT ZERO..EXTENDED ARABIC-INDIC DIGIT NINE +07C0..07C9 ; Numeric # Nd [10] NKO DIGIT ZERO..NKO DIGIT NINE +0966..096F ; Numeric # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE +09E6..09EF ; Numeric # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE +0A66..0A6F ; Numeric # Nd [10] GURMUKHI DIGIT ZERO..GURMUKHI DIGIT NINE +0AE6..0AEF ; Numeric # Nd [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE +0B66..0B6F ; Numeric # Nd [10] ORIYA DIGIT ZERO..ORIYA DIGIT NINE +0BE6..0BEF ; Numeric # Nd [10] TAMIL DIGIT ZERO..TAMIL DIGIT NINE +0C66..0C6F ; Numeric # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE +0CE6..0CEF ; Numeric # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE +0D66..0D6F ; Numeric # Nd [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE +0DE6..0DEF ; Numeric # Nd [10] SINHALA LITH DIGIT ZERO..SINHALA LITH DIGIT NINE +0E50..0E59 ; Numeric # Nd [10] THAI DIGIT ZERO..THAI DIGIT NINE +0ED0..0ED9 ; Numeric # Nd [10] LAO DIGIT ZERO..LAO DIGIT NINE +0F20..0F29 ; Numeric # Nd [10] TIBETAN DIGIT ZERO..TIBETAN DIGIT NINE +1040..1049 ; Numeric # Nd [10] MYANMAR DIGIT ZERO..MYANMAR DIGIT NINE +1090..1099 ; Numeric # Nd [10] MYANMAR SHAN DIGIT ZERO..MYANMAR SHAN DIGIT NINE +17E0..17E9 ; Numeric # Nd [10] KHMER DIGIT ZERO..KHMER DIGIT NINE +1810..1819 ; Numeric # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE +1946..194F ; Numeric # Nd [10] LIMBU DIGIT ZERO..LIMBU DIGIT NINE +19D0..19D9 ; Numeric # Nd [10] NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE +1A80..1A89 ; Numeric # Nd [10] TAI THAM HORA DIGIT ZERO..TAI THAM HORA DIGIT NINE +1A90..1A99 ; Numeric # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE +1B50..1B59 ; Numeric # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE +1BB0..1BB9 ; Numeric # Nd [10] SUNDANESE DIGIT ZERO..SUNDANESE DIGIT NINE +1C40..1C49 ; Numeric # Nd [10] LEPCHA DIGIT ZERO..LEPCHA DIGIT NINE +1C50..1C59 ; Numeric # Nd [10] OL CHIKI DIGIT ZERO..OL CHIKI DIGIT NINE +A620..A629 ; Numeric # Nd [10] VAI DIGIT ZERO..VAI DIGIT NINE +A8D0..A8D9 ; Numeric # Nd [10] SAURASHTRA DIGIT ZERO..SAURASHTRA DIGIT NINE +A900..A909 ; Numeric # Nd [10] KAYAH LI DIGIT ZERO..KAYAH LI DIGIT NINE +A9D0..A9D9 ; Numeric # Nd [10] JAVANESE DIGIT ZERO..JAVANESE DIGIT NINE +A9F0..A9F9 ; Numeric # Nd [10] MYANMAR TAI LAING DIGIT ZERO..MYANMAR TAI LAING DIGIT NINE +AA50..AA59 ; Numeric # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE +ABF0..ABF9 ; Numeric # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE +FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE +104A0..104A9 ; Numeric # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE +10D30..10D39 ; Numeric # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE +11066..1106F ; Numeric # Nd [10] BRAHMI DIGIT ZERO..BRAHMI DIGIT NINE +110F0..110F9 ; Numeric # Nd [10] SORA SOMPENG DIGIT ZERO..SORA SOMPENG DIGIT NINE +11136..1113F ; Numeric # Nd [10] CHAKMA DIGIT ZERO..CHAKMA DIGIT NINE +111D0..111D9 ; Numeric # Nd [10] SHARADA DIGIT ZERO..SHARADA DIGIT NINE +112F0..112F9 ; Numeric # Nd [10] KHUDAWADI DIGIT ZERO..KHUDAWADI DIGIT NINE +11450..11459 ; Numeric # Nd [10] NEWA DIGIT ZERO..NEWA DIGIT NINE +114D0..114D9 ; Numeric # Nd [10] TIRHUTA DIGIT ZERO..TIRHUTA DIGIT NINE +11650..11659 ; Numeric # Nd [10] MODI DIGIT ZERO..MODI DIGIT NINE +116C0..116C9 ; Numeric # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE +11730..11739 ; Numeric # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE +118E0..118E9 ; Numeric # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE +11950..11959 ; Numeric # Nd [10] DIVES AKURU DIGIT ZERO..DIVES AKURU DIGIT NINE +11C50..11C59 ; Numeric # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE +11D50..11D59 ; Numeric # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE +11DA0..11DA9 ; Numeric # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE +16A60..16A69 ; Numeric # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE +16AC0..16AC9 ; Numeric # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE +16B50..16B59 ; Numeric # Nd [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE +1D7CE..1D7FF ; Numeric # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE +1E140..1E149 ; Numeric # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE +1E2F0..1E2F9 ; Numeric # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE +1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE +1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE + +# Total code points: 662 + +# ================================================ + +002E ; ATerm # Po FULL STOP +2024 ; ATerm # Po ONE DOT LEADER +FE52 ; ATerm # Po SMALL FULL STOP +FF0E ; ATerm # Po FULLWIDTH FULL STOP + +# Total code points: 4 + +# ================================================ + +0021 ; STerm # Po EXCLAMATION MARK +003F ; STerm # Po QUESTION MARK +0589 ; STerm # Po ARMENIAN FULL STOP +061D..061F ; STerm # Po [3] ARABIC END OF TEXT MARK..ARABIC QUESTION MARK +06D4 ; STerm # Po ARABIC FULL STOP +0700..0702 ; STerm # Po [3] SYRIAC END OF PARAGRAPH..SYRIAC SUBLINEAR FULL STOP +07F9 ; STerm # Po NKO EXCLAMATION MARK +0837 ; STerm # Po SAMARITAN PUNCTUATION MELODIC QITSA +0839 ; STerm # Po SAMARITAN PUNCTUATION QITSA +083D..083E ; STerm # Po [2] SAMARITAN PUNCTUATION SOF MASHFAAT..SAMARITAN PUNCTUATION ANNAAU +0964..0965 ; STerm # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA +104A..104B ; STerm # Po [2] MYANMAR SIGN LITTLE SECTION..MYANMAR SIGN SECTION +1362 ; STerm # Po ETHIOPIC FULL STOP +1367..1368 ; STerm # Po [2] ETHIOPIC QUESTION MARK..ETHIOPIC PARAGRAPH SEPARATOR +166E ; STerm # Po CANADIAN SYLLABICS FULL STOP +1735..1736 ; STerm # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION +1803 ; STerm # Po MONGOLIAN FULL STOP +1809 ; STerm # Po MONGOLIAN MANCHU FULL STOP +1944..1945 ; STerm # Po [2] LIMBU EXCLAMATION MARK..LIMBU QUESTION MARK +1AA8..1AAB ; STerm # Po [4] TAI THAM SIGN KAAN..TAI THAM SIGN SATKAANKUU +1B5A..1B5B ; STerm # Po [2] BALINESE PANTI..BALINESE PAMADA +1B5E..1B5F ; STerm # Po [2] BALINESE CARIK SIKI..BALINESE CARIK PAREREN +1B7D..1B7E ; STerm # Po [2] BALINESE PANTI LANTANG..BALINESE PAMADA LANTANG +1C3B..1C3C ; STerm # Po [2] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION NYET THYOOM TA-ROL +1C7E..1C7F ; STerm # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD +203C..203D ; STerm # Po [2] DOUBLE EXCLAMATION MARK..INTERROBANG +2047..2049 ; STerm # Po [3] DOUBLE QUESTION MARK..EXCLAMATION QUESTION MARK +2E2E ; STerm # Po REVERSED QUESTION MARK +2E3C ; STerm # Po STENOGRAPHIC FULL STOP +2E53..2E54 ; STerm # Po [2] MEDIEVAL EXCLAMATION MARK..MEDIEVAL QUESTION MARK +3002 ; STerm # Po IDEOGRAPHIC FULL STOP +A4FF ; STerm # Po LISU PUNCTUATION FULL STOP +A60E..A60F ; STerm # Po [2] VAI FULL STOP..VAI QUESTION MARK +A6F3 ; STerm # Po BAMUM FULL STOP +A6F7 ; STerm # Po BAMUM QUESTION MARK +A876..A877 ; STerm # Po [2] PHAGS-PA MARK SHAD..PHAGS-PA MARK DOUBLE SHAD +A8CE..A8CF ; STerm # Po [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA +A92F ; STerm # Po KAYAH LI SIGN SHYA +A9C8..A9C9 ; STerm # Po [2] JAVANESE PADA LINGSA..JAVANESE PADA LUNGSI +AA5D..AA5F ; STerm # Po [3] CHAM PUNCTUATION DANDA..CHAM PUNCTUATION TRIPLE DANDA +AAF0..AAF1 ; STerm # Po [2] MEETEI MAYEK CHEIKHAN..MEETEI MAYEK AHANG KHUDAM +ABEB ; STerm # Po MEETEI MAYEK CHEIKHEI +FE56..FE57 ; STerm # Po [2] SMALL QUESTION MARK..SMALL EXCLAMATION MARK +FF01 ; STerm # Po FULLWIDTH EXCLAMATION MARK +FF1F ; STerm # Po FULLWIDTH QUESTION MARK +FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP +10A56..10A57 ; STerm # Po [2] KHAROSHTHI PUNCTUATION DANDA..KHAROSHTHI PUNCTUATION DOUBLE DANDA +10F55..10F59 ; STerm # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT +10F86..10F89 ; STerm # Po [4] OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS +11047..11048 ; STerm # Po [2] BRAHMI DANDA..BRAHMI DOUBLE DANDA +110BE..110C1 ; STerm # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA +11141..11143 ; STerm # Po [3] CHAKMA DANDA..CHAKMA QUESTION MARK +111C5..111C6 ; STerm # Po [2] SHARADA DANDA..SHARADA DOUBLE DANDA +111CD ; STerm # Po SHARADA SUTRA MARK +111DE..111DF ; STerm # Po [2] SHARADA SECTION MARK-1..SHARADA SECTION MARK-2 +11238..11239 ; STerm # Po [2] KHOJKI DANDA..KHOJKI DOUBLE DANDA +1123B..1123C ; STerm # Po [2] KHOJKI SECTION MARK..KHOJKI DOUBLE SECTION MARK +112A9 ; STerm # Po MULTANI SECTION MARK +1144B..1144C ; STerm # Po [2] NEWA DANDA..NEWA DOUBLE DANDA +115C2..115C3 ; STerm # Po [2] SIDDHAM DANDA..SIDDHAM DOUBLE DANDA +115C9..115D7 ; STerm # Po [15] SIDDHAM END OF TEXT MARK..SIDDHAM SECTION MARK WITH CIRCLES AND FOUR ENCLOSURES +11641..11642 ; STerm # Po [2] MODI DANDA..MODI DOUBLE DANDA +1173C..1173E ; STerm # Po [3] AHOM SIGN SMALL SECTION..AHOM SIGN RULAI +11944 ; STerm # Po DIVES AKURU DOUBLE DANDA +11946 ; STerm # Po DIVES AKURU END OF TEXT MARK +11A42..11A43 ; STerm # Po [2] ZANABAZAR SQUARE MARK SHAD..ZANABAZAR SQUARE MARK DOUBLE SHAD +11A9B..11A9C ; STerm # Po [2] SOYOMBO MARK SHAD..SOYOMBO MARK DOUBLE SHAD +11C41..11C42 ; STerm # Po [2] BHAIKSUKI DANDA..BHAIKSUKI DOUBLE DANDA +11EF7..11EF8 ; STerm # Po [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION +16A6E..16A6F ; STerm # Po [2] MRO DANDA..MRO DOUBLE DANDA +16AF5 ; STerm # Po BASSA VAH FULL STOP +16B37..16B38 ; STerm # Po [2] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN VOS TSHAB CEEB +16B44 ; STerm # Po PAHAWH HMONG SIGN XAUS +16E98 ; STerm # Po MEDEFAIDRIN FULL STOP +1BC9F ; STerm # Po DUPLOYAN PUNCTUATION CHINOOK FULL STOP +1DA88 ; STerm # Po SIGNWRITING FULL STOP + +# Total code points: 149 + +# ================================================ + +0022 ; Close # Po QUOTATION MARK +0027 ; Close # Po APOSTROPHE +0028 ; Close # Ps LEFT PARENTHESIS +0029 ; Close # Pe RIGHT PARENTHESIS +005B ; Close # Ps LEFT SQUARE BRACKET +005D ; Close # Pe RIGHT SQUARE BRACKET +007B ; Close # Ps LEFT CURLY BRACKET +007D ; Close # Pe RIGHT CURLY BRACKET +00AB ; Close # Pi LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +00BB ; Close # Pf RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0F3A ; Close # Ps TIBETAN MARK GUG RTAGS GYON +0F3B ; Close # Pe TIBETAN MARK GUG RTAGS GYAS +0F3C ; Close # Ps TIBETAN MARK ANG KHANG GYON +0F3D ; Close # Pe TIBETAN MARK ANG KHANG GYAS +169B ; Close # Ps OGHAM FEATHER MARK +169C ; Close # Pe OGHAM REVERSED FEATHER MARK +2018 ; Close # Pi LEFT SINGLE QUOTATION MARK +2019 ; Close # Pf RIGHT SINGLE QUOTATION MARK +201A ; Close # Ps SINGLE LOW-9 QUOTATION MARK +201B..201C ; Close # Pi [2] SINGLE HIGH-REVERSED-9 QUOTATION MARK..LEFT DOUBLE QUOTATION MARK +201D ; Close # Pf RIGHT DOUBLE QUOTATION MARK +201E ; Close # Ps DOUBLE LOW-9 QUOTATION MARK +201F ; Close # Pi DOUBLE HIGH-REVERSED-9 QUOTATION MARK +2039 ; Close # Pi SINGLE LEFT-POINTING ANGLE QUOTATION MARK +203A ; Close # Pf SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +2045 ; Close # Ps LEFT SQUARE BRACKET WITH QUILL +2046 ; Close # Pe RIGHT SQUARE BRACKET WITH QUILL +207D ; Close # Ps SUPERSCRIPT LEFT PARENTHESIS +207E ; Close # Pe SUPERSCRIPT RIGHT PARENTHESIS +208D ; Close # Ps SUBSCRIPT LEFT PARENTHESIS +208E ; Close # Pe SUBSCRIPT RIGHT PARENTHESIS +2308 ; Close # Ps LEFT CEILING +2309 ; Close # Pe RIGHT CEILING +230A ; Close # Ps LEFT FLOOR +230B ; Close # Pe RIGHT FLOOR +2329 ; Close # Ps LEFT-POINTING ANGLE BRACKET +232A ; Close # Pe RIGHT-POINTING ANGLE BRACKET +275B..2760 ; Close # So [6] HEAVY SINGLE TURNED COMMA QUOTATION MARK ORNAMENT..HEAVY LOW DOUBLE COMMA QUOTATION MARK ORNAMENT +2768 ; Close # Ps MEDIUM LEFT PARENTHESIS ORNAMENT +2769 ; Close # Pe MEDIUM RIGHT PARENTHESIS ORNAMENT +276A ; Close # Ps MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT +276B ; Close # Pe MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT +276C ; Close # Ps MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT +276D ; Close # Pe MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT +276E ; Close # Ps HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT +276F ; Close # Pe HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT +2770 ; Close # Ps HEAVY LEFT-POINTING ANGLE BRACKET ORNAMENT +2771 ; Close # Pe HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT +2772 ; Close # Ps LIGHT LEFT TORTOISE SHELL BRACKET ORNAMENT +2773 ; Close # Pe LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT +2774 ; Close # Ps MEDIUM LEFT CURLY BRACKET ORNAMENT +2775 ; Close # Pe MEDIUM RIGHT CURLY BRACKET ORNAMENT +27C5 ; Close # Ps LEFT S-SHAPED BAG DELIMITER +27C6 ; Close # Pe RIGHT S-SHAPED BAG DELIMITER +27E6 ; Close # Ps MATHEMATICAL LEFT WHITE SQUARE BRACKET +27E7 ; Close # Pe MATHEMATICAL RIGHT WHITE SQUARE BRACKET +27E8 ; Close # Ps MATHEMATICAL LEFT ANGLE BRACKET +27E9 ; Close # Pe MATHEMATICAL RIGHT ANGLE BRACKET +27EA ; Close # Ps MATHEMATICAL LEFT DOUBLE ANGLE BRACKET +27EB ; Close # Pe MATHEMATICAL RIGHT DOUBLE ANGLE BRACKET +27EC ; Close # Ps MATHEMATICAL LEFT WHITE TORTOISE SHELL BRACKET +27ED ; Close # Pe MATHEMATICAL RIGHT WHITE TORTOISE SHELL BRACKET +27EE ; Close # Ps MATHEMATICAL LEFT FLATTENED PARENTHESIS +27EF ; Close # Pe MATHEMATICAL RIGHT FLATTENED PARENTHESIS +2983 ; Close # Ps LEFT WHITE CURLY BRACKET +2984 ; Close # Pe RIGHT WHITE CURLY BRACKET +2985 ; Close # Ps LEFT WHITE PARENTHESIS +2986 ; Close # Pe RIGHT WHITE PARENTHESIS +2987 ; Close # Ps Z NOTATION LEFT IMAGE BRACKET +2988 ; Close # Pe Z NOTATION RIGHT IMAGE BRACKET +2989 ; Close # Ps Z NOTATION LEFT BINDING BRACKET +298A ; Close # Pe Z NOTATION RIGHT BINDING BRACKET +298B ; Close # Ps LEFT SQUARE BRACKET WITH UNDERBAR +298C ; Close # Pe RIGHT SQUARE BRACKET WITH UNDERBAR +298D ; Close # Ps LEFT SQUARE BRACKET WITH TICK IN TOP CORNER +298E ; Close # Pe RIGHT SQUARE BRACKET WITH TICK IN BOTTOM CORNER +298F ; Close # Ps LEFT SQUARE BRACKET WITH TICK IN BOTTOM CORNER +2990 ; Close # Pe RIGHT SQUARE BRACKET WITH TICK IN TOP CORNER +2991 ; Close # Ps LEFT ANGLE BRACKET WITH DOT +2992 ; Close # Pe RIGHT ANGLE BRACKET WITH DOT +2993 ; Close # Ps LEFT ARC LESS-THAN BRACKET +2994 ; Close # Pe RIGHT ARC GREATER-THAN BRACKET +2995 ; Close # Ps DOUBLE LEFT ARC GREATER-THAN BRACKET +2996 ; Close # Pe DOUBLE RIGHT ARC LESS-THAN BRACKET +2997 ; Close # Ps LEFT BLACK TORTOISE SHELL BRACKET +2998 ; Close # Pe RIGHT BLACK TORTOISE SHELL BRACKET +29D8 ; Close # Ps LEFT WIGGLY FENCE +29D9 ; Close # Pe RIGHT WIGGLY FENCE +29DA ; Close # Ps LEFT DOUBLE WIGGLY FENCE +29DB ; Close # Pe RIGHT DOUBLE WIGGLY FENCE +29FC ; Close # Ps LEFT-POINTING CURVED ANGLE BRACKET +29FD ; Close # Pe RIGHT-POINTING CURVED ANGLE BRACKET +2E00..2E01 ; Close # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER +2E02 ; Close # Pi LEFT SUBSTITUTION BRACKET +2E03 ; Close # Pf RIGHT SUBSTITUTION BRACKET +2E04 ; Close # Pi LEFT DOTTED SUBSTITUTION BRACKET +2E05 ; Close # Pf RIGHT DOTTED SUBSTITUTION BRACKET +2E06..2E08 ; Close # Po [3] RAISED INTERPOLATION MARKER..DOTTED TRANSPOSITION MARKER +2E09 ; Close # Pi LEFT TRANSPOSITION BRACKET +2E0A ; Close # Pf RIGHT TRANSPOSITION BRACKET +2E0B ; Close # Po RAISED SQUARE +2E0C ; Close # Pi LEFT RAISED OMISSION BRACKET +2E0D ; Close # Pf RIGHT RAISED OMISSION BRACKET +2E1C ; Close # Pi LEFT LOW PARAPHRASE BRACKET +2E1D ; Close # Pf RIGHT LOW PARAPHRASE BRACKET +2E20 ; Close # Pi LEFT VERTICAL BAR WITH QUILL +2E21 ; Close # Pf RIGHT VERTICAL BAR WITH QUILL +2E22 ; Close # Ps TOP LEFT HALF BRACKET +2E23 ; Close # Pe TOP RIGHT HALF BRACKET +2E24 ; Close # Ps BOTTOM LEFT HALF BRACKET +2E25 ; Close # Pe BOTTOM RIGHT HALF BRACKET +2E26 ; Close # Ps LEFT SIDEWAYS U BRACKET +2E27 ; Close # Pe RIGHT SIDEWAYS U BRACKET +2E28 ; Close # Ps LEFT DOUBLE PARENTHESIS +2E29 ; Close # Pe RIGHT DOUBLE PARENTHESIS +2E42 ; Close # Ps DOUBLE LOW-REVERSED-9 QUOTATION MARK +2E55 ; Close # Ps LEFT SQUARE BRACKET WITH STROKE +2E56 ; Close # Pe RIGHT SQUARE BRACKET WITH STROKE +2E57 ; Close # Ps LEFT SQUARE BRACKET WITH DOUBLE STROKE +2E58 ; Close # Pe RIGHT SQUARE BRACKET WITH DOUBLE STROKE +2E59 ; Close # Ps TOP HALF LEFT PARENTHESIS +2E5A ; Close # Pe TOP HALF RIGHT PARENTHESIS +2E5B ; Close # Ps BOTTOM HALF LEFT PARENTHESIS +2E5C ; Close # Pe BOTTOM HALF RIGHT PARENTHESIS +3008 ; Close # Ps LEFT ANGLE BRACKET +3009 ; Close # Pe RIGHT ANGLE BRACKET +300A ; Close # Ps LEFT DOUBLE ANGLE BRACKET +300B ; Close # Pe RIGHT DOUBLE ANGLE BRACKET +300C ; Close # Ps LEFT CORNER BRACKET +300D ; Close # Pe RIGHT CORNER BRACKET +300E ; Close # Ps LEFT WHITE CORNER BRACKET +300F ; Close # Pe RIGHT WHITE CORNER BRACKET +3010 ; Close # Ps LEFT BLACK LENTICULAR BRACKET +3011 ; Close # Pe RIGHT BLACK LENTICULAR BRACKET +3014 ; Close # Ps LEFT TORTOISE SHELL BRACKET +3015 ; Close # Pe RIGHT TORTOISE SHELL BRACKET +3016 ; Close # Ps LEFT WHITE LENTICULAR BRACKET +3017 ; Close # Pe RIGHT WHITE LENTICULAR BRACKET +3018 ; Close # Ps LEFT WHITE TORTOISE SHELL BRACKET +3019 ; Close # Pe RIGHT WHITE TORTOISE SHELL BRACKET +301A ; Close # Ps LEFT WHITE SQUARE BRACKET +301B ; Close # Pe RIGHT WHITE SQUARE BRACKET +301D ; Close # Ps REVERSED DOUBLE PRIME QUOTATION MARK +301E..301F ; Close # Pe [2] DOUBLE PRIME QUOTATION MARK..LOW DOUBLE PRIME QUOTATION MARK +FD3E ; Close # Pe ORNATE LEFT PARENTHESIS +FD3F ; Close # Ps ORNATE RIGHT PARENTHESIS +FE17 ; Close # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE LENTICULAR BRACKET +FE18 ; Close # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE LENTICULAR BRAKCET +FE35 ; Close # Ps PRESENTATION FORM FOR VERTICAL LEFT PARENTHESIS +FE36 ; Close # Pe PRESENTATION FORM FOR VERTICAL RIGHT PARENTHESIS +FE37 ; Close # Ps PRESENTATION FORM FOR VERTICAL LEFT CURLY BRACKET +FE38 ; Close # Pe PRESENTATION FORM FOR VERTICAL RIGHT CURLY BRACKET +FE39 ; Close # Ps PRESENTATION FORM FOR VERTICAL LEFT TORTOISE SHELL BRACKET +FE3A ; Close # Pe PRESENTATION FORM FOR VERTICAL RIGHT TORTOISE SHELL BRACKET +FE3B ; Close # Ps PRESENTATION FORM FOR VERTICAL LEFT BLACK LENTICULAR BRACKET +FE3C ; Close # Pe PRESENTATION FORM FOR VERTICAL RIGHT BLACK LENTICULAR BRACKET +FE3D ; Close # Ps PRESENTATION FORM FOR VERTICAL LEFT DOUBLE ANGLE BRACKET +FE3E ; Close # Pe PRESENTATION FORM FOR VERTICAL RIGHT DOUBLE ANGLE BRACKET +FE3F ; Close # Ps PRESENTATION FORM FOR VERTICAL LEFT ANGLE BRACKET +FE40 ; Close # Pe PRESENTATION FORM FOR VERTICAL RIGHT ANGLE BRACKET +FE41 ; Close # Ps PRESENTATION FORM FOR VERTICAL LEFT CORNER BRACKET +FE42 ; Close # Pe PRESENTATION FORM FOR VERTICAL RIGHT CORNER BRACKET +FE43 ; Close # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE CORNER BRACKET +FE44 ; Close # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE CORNER BRACKET +FE47 ; Close # Ps PRESENTATION FORM FOR VERTICAL LEFT SQUARE BRACKET +FE48 ; Close # Pe PRESENTATION FORM FOR VERTICAL RIGHT SQUARE BRACKET +FE59 ; Close # Ps SMALL LEFT PARENTHESIS +FE5A ; Close # Pe SMALL RIGHT PARENTHESIS +FE5B ; Close # Ps SMALL LEFT CURLY BRACKET +FE5C ; Close # Pe SMALL RIGHT CURLY BRACKET +FE5D ; Close # Ps SMALL LEFT TORTOISE SHELL BRACKET +FE5E ; Close # Pe SMALL RIGHT TORTOISE SHELL BRACKET +FF08 ; Close # Ps FULLWIDTH LEFT PARENTHESIS +FF09 ; Close # Pe FULLWIDTH RIGHT PARENTHESIS +FF3B ; Close # Ps FULLWIDTH LEFT SQUARE BRACKET +FF3D ; Close # Pe FULLWIDTH RIGHT SQUARE BRACKET +FF5B ; Close # Ps FULLWIDTH LEFT CURLY BRACKET +FF5D ; Close # Pe FULLWIDTH RIGHT CURLY BRACKET +FF5F ; Close # Ps FULLWIDTH LEFT WHITE PARENTHESIS +FF60 ; Close # Pe FULLWIDTH RIGHT WHITE PARENTHESIS +FF62 ; Close # Ps HALFWIDTH LEFT CORNER BRACKET +FF63 ; Close # Pe HALFWIDTH RIGHT CORNER BRACKET +1F676..1F678 ; Close # So [3] SANS-SERIF HEAVY DOUBLE TURNED COMMA QUOTATION MARK ORNAMENT..SANS-SERIF HEAVY LOW DOUBLE COMMA QUOTATION MARK ORNAMENT + +# Total code points: 195 + +# ================================================ + +002C ; SContinue # Po COMMA +002D ; SContinue # Pd HYPHEN-MINUS +003A ; SContinue # Po COLON +055D ; SContinue # Po ARMENIAN COMMA +060C..060D ; SContinue # Po [2] ARABIC COMMA..ARABIC DATE SEPARATOR +07F8 ; SContinue # Po NKO COMMA +1802 ; SContinue # Po MONGOLIAN COMMA +1808 ; SContinue # Po MONGOLIAN MANCHU COMMA +2013..2014 ; SContinue # Pd [2] EN DASH..EM DASH +3001 ; SContinue # Po IDEOGRAPHIC COMMA +FE10..FE11 ; SContinue # Po [2] PRESENTATION FORM FOR VERTICAL COMMA..PRESENTATION FORM FOR VERTICAL IDEOGRAPHIC COMMA +FE13 ; SContinue # Po PRESENTATION FORM FOR VERTICAL COLON +FE31..FE32 ; SContinue # Pd [2] PRESENTATION FORM FOR VERTICAL EM DASH..PRESENTATION FORM FOR VERTICAL EN DASH +FE50..FE51 ; SContinue # Po [2] SMALL COMMA..SMALL IDEOGRAPHIC COMMA +FE55 ; SContinue # Po SMALL COLON +FE58 ; SContinue # Pd SMALL EM DASH +FE63 ; SContinue # Pd SMALL HYPHEN-MINUS +FF0C ; SContinue # Po FULLWIDTH COMMA +FF0D ; SContinue # Pd FULLWIDTH HYPHEN-MINUS +FF1A ; SContinue # Po FULLWIDTH COLON +FF64 ; SContinue # Po HALFWIDTH IDEOGRAPHIC COMMA + +# Total code points: 26 + +# EOF diff --git a/data/SentenceBreakTest.txt b/data/SentenceBreakTest.txt @@ -0,0 +1,530 @@ +# SentenceBreakTest-14.0.0.txt +# Date: 2021-03-08, 06:22:40 GMT +# © 2021 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 http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ +# +# Default Sentence_Break Test +# +# Format: +# <string> (# <comment>)? +# <string> contains hex Unicode code points, with +# ÷ wherever there is a break opportunity, and +# × wherever there is not. +# <comment> the format can change, but currently it shows: +# - the sample character name +# - (x) the Sentence_Break property value for the sample character +# - [x] the rule that determines whether there is a break or not, +# as listed in the Rules section of SentenceBreakTest.html +# +# These samples may be extended or changed in the future. +# +÷ 0001 × 0001 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 0001 × 0308 × 0001 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 0001 × 000D ÷ # ÷ [0.2] <START OF HEADING> (Other) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 0001 × 0308 × 000D ÷ # ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 0001 × 000A ÷ # ÷ [0.2] <START OF HEADING> (Other) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 0001 × 0308 × 000A ÷ # ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 0001 × 0085 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 0001 × 0308 × 0085 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 0001 × 0009 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 0001 × 0308 × 0009 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 0001 × 0061 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 0001 × 0308 × 0061 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 0001 × 0041 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 0001 × 0308 × 0041 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 0001 × 01BB ÷ # ÷ [0.2] <START OF HEADING> (Other) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 0001 × 0308 × 01BB ÷ # ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 0001 × 0030 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 0001 × 0308 × 0030 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 0001 × 002E ÷ # ÷ [0.2] <START OF HEADING> (Other) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 0001 × 0308 × 002E ÷ # ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 0001 × 0021 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 0001 × 0308 × 0021 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 0001 × 0022 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 0001 × 0308 × 0022 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 0001 × 002C ÷ # ÷ [0.2] <START OF HEADING> (Other) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 0001 × 0308 × 002C ÷ # ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 0001 × 00AD ÷ # ÷ [0.2] <START OF HEADING> (Other) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 0001 × 0308 × 00AD ÷ # ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 0001 × 0300 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 0001 × 0308 × 0300 ÷ # ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 000D ÷ 0001 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 000D ÷ 0308 × 0001 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 000D ÷ 000D ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 000D ÷ 0308 × 000D ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 000D × 000A ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) × [3.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 000D ÷ 0308 × 000A ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 000D ÷ 0085 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 000D ÷ 0308 × 0085 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 000D ÷ 0009 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 000D ÷ 0308 × 0009 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 000D ÷ 0061 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 000D ÷ 0308 × 0061 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 000D ÷ 0041 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 000D ÷ 0308 × 0041 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 000D ÷ 01BB ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 000D ÷ 0308 × 01BB ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 000D ÷ 0030 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 000D ÷ 0308 × 0030 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 000D ÷ 002E ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] FULL STOP (ATerm) ÷ [0.3] +÷ 000D ÷ 0308 × 002E ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 000D ÷ 0021 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 000D ÷ 0308 × 0021 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 000D ÷ 0022 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 000D ÷ 0308 × 0022 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 000D ÷ 002C ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMMA (SContinue) ÷ [0.3] +÷ 000D ÷ 0308 × 002C ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 000D ÷ 00AD ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 000D ÷ 0308 × 00AD ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 000D ÷ 0300 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 000D ÷ 0308 × 0300 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 000A ÷ 0001 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 000A ÷ 0308 × 0001 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 000A ÷ 000D ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 000A ÷ 0308 × 000D ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 000A ÷ 000A ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 000A ÷ 0308 × 000A ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 000A ÷ 0085 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 000A ÷ 0308 × 0085 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 000A ÷ 0009 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 000A ÷ 0308 × 0009 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 000A ÷ 0061 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 000A ÷ 0308 × 0061 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 000A ÷ 0041 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 000A ÷ 0308 × 0041 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 000A ÷ 01BB ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 000A ÷ 0308 × 01BB ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 000A ÷ 0030 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 000A ÷ 0308 × 0030 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 000A ÷ 002E ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] FULL STOP (ATerm) ÷ [0.3] +÷ 000A ÷ 0308 × 002E ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 000A ÷ 0021 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 000A ÷ 0308 × 0021 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 000A ÷ 0022 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 000A ÷ 0308 × 0022 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 000A ÷ 002C ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMMA (SContinue) ÷ [0.3] +÷ 000A ÷ 0308 × 002C ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 000A ÷ 00AD ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 000A ÷ 0308 × 00AD ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 000A ÷ 0300 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 000A ÷ 0308 × 0300 ÷ # ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 0085 ÷ 0001 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 0085 ÷ 0308 × 0001 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 0085 ÷ 000D ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 0085 ÷ 0308 × 000D ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 0085 ÷ 000A ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 0085 ÷ 0308 × 000A ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 0085 ÷ 0085 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 0085 ÷ 0308 × 0085 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 0085 ÷ 0009 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 0085 ÷ 0308 × 0009 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 0085 ÷ 0061 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 0085 ÷ 0308 × 0061 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 0085 ÷ 0041 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 0085 ÷ 0308 × 0041 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 0085 ÷ 01BB ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 0085 ÷ 0308 × 01BB ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 0085 ÷ 0030 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 0085 ÷ 0308 × 0030 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 0085 ÷ 002E ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] FULL STOP (ATerm) ÷ [0.3] +÷ 0085 ÷ 0308 × 002E ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 0085 ÷ 0021 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 0085 ÷ 0308 × 0021 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 0085 ÷ 0022 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 0085 ÷ 0308 × 0022 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 0085 ÷ 002C ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMMA (SContinue) ÷ [0.3] +÷ 0085 ÷ 0308 × 002C ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 0085 ÷ 00AD ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 0085 ÷ 0308 × 00AD ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 0085 ÷ 0300 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 0085 ÷ 0308 × 0300 ÷ # ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 0009 × 0001 ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 0009 × 0308 × 0001 ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 0009 × 000D ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 0009 × 0308 × 000D ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 0009 × 000A ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 0009 × 0308 × 000A ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 0009 × 0085 ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 0009 × 0308 × 0085 ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 0009 × 0009 ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 0009 × 0308 × 0009 ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 0009 × 0061 ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 0009 × 0308 × 0061 ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 0009 × 0041 ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 0009 × 0308 × 0041 ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 0009 × 01BB ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 0009 × 0308 × 01BB ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 0009 × 0030 ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 0009 × 0308 × 0030 ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 0009 × 002E ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 0009 × 0308 × 002E ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 0009 × 0021 ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 0009 × 0308 × 0021 ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 0009 × 0022 ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 0009 × 0308 × 0022 ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 0009 × 002C ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 0009 × 0308 × 002C ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 0009 × 00AD ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 0009 × 0308 × 00AD ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 0009 × 0300 ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 0009 × 0308 × 0300 ÷ # ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 0061 × 0001 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 0061 × 0308 × 0001 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 0061 × 000D ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 0061 × 0308 × 000D ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 0061 × 000A ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 0061 × 0308 × 000A ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 0061 × 0085 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 0061 × 0308 × 0085 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 0061 × 0009 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 0061 × 0308 × 0009 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 0061 × 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 0061 × 0308 × 0061 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 0061 × 0041 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 0061 × 0308 × 0041 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 0061 × 01BB ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 0061 × 0308 × 01BB ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 0061 × 0030 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 0061 × 0308 × 0030 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 0061 × 002E ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 0061 × 0308 × 002E ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 0061 × 0021 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 0061 × 0308 × 0021 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 0061 × 0022 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 0061 × 0308 × 0022 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 0061 × 002C ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 0061 × 0308 × 002C ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 0061 × 00AD ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 0061 × 0308 × 00AD ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 0061 × 0300 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 0061 × 0308 × 0300 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 0041 × 0001 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 0041 × 0308 × 0001 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 0041 × 000D ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 0041 × 0308 × 000D ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 0041 × 000A ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 0041 × 0308 × 000A ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 0041 × 0085 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 0041 × 0308 × 0085 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 0041 × 0009 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 0041 × 0308 × 0009 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 0041 × 0061 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 0041 × 0308 × 0061 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 0041 × 0041 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 0041 × 0308 × 0041 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 0041 × 01BB ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 0041 × 0308 × 01BB ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 0041 × 0030 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 0041 × 0308 × 0030 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 0041 × 002E ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 0041 × 0308 × 002E ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 0041 × 0021 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 0041 × 0308 × 0021 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 0041 × 0022 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 0041 × 0308 × 0022 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 0041 × 002C ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 0041 × 0308 × 002C ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 0041 × 00AD ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 0041 × 0308 × 00AD ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 0041 × 0300 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 0041 × 0308 × 0300 ÷ # ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 01BB × 0001 ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 01BB × 0308 × 0001 ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 01BB × 000D ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 01BB × 0308 × 000D ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 01BB × 000A ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 01BB × 0308 × 000A ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 01BB × 0085 ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 01BB × 0308 × 0085 ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 01BB × 0009 ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 01BB × 0308 × 0009 ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 01BB × 0061 ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 01BB × 0308 × 0061 ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 01BB × 0041 ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 01BB × 0308 × 0041 ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 01BB × 01BB ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 01BB × 0308 × 01BB ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 01BB × 0030 ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 01BB × 0308 × 0030 ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 01BB × 002E ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 01BB × 0308 × 002E ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 01BB × 0021 ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 01BB × 0308 × 0021 ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 01BB × 0022 ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 01BB × 0308 × 0022 ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 01BB × 002C ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 01BB × 0308 × 002C ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 01BB × 00AD ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 01BB × 0308 × 00AD ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 01BB × 0300 ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 01BB × 0308 × 0300 ÷ # ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 0030 × 0001 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 0030 × 0308 × 0001 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 0030 × 000D ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 0030 × 0308 × 000D ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 0030 × 000A ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 0030 × 0308 × 000A ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 0030 × 0085 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 0030 × 0308 × 0085 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 0030 × 0009 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 0030 × 0308 × 0009 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 0030 × 0061 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 0030 × 0308 × 0061 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 0030 × 0041 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 0030 × 0308 × 0041 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 0030 × 01BB ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 0030 × 0308 × 01BB ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 0030 × 0030 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 0030 × 0308 × 0030 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 0030 × 002E ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 0030 × 0308 × 002E ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 0030 × 0021 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 0030 × 0308 × 0021 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 0030 × 0022 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 0030 × 0308 × 0022 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 0030 × 002C ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 0030 × 0308 × 002C ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 0030 × 00AD ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 0030 × 0308 × 00AD ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 0030 × 0300 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 0030 × 0308 × 0300 ÷ # ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 002E ÷ 0001 ÷ # ÷ [0.2] FULL STOP (ATerm) ÷ [11.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 002E × 0308 ÷ 0001 ÷ # ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 002E × 000D ÷ # ÷ [0.2] FULL STOP (ATerm) × [9.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 002E × 0308 × 000D ÷ # ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [9.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 002E × 000A ÷ # ÷ [0.2] FULL STOP (ATerm) × [9.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 002E × 0308 × 000A ÷ # ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [9.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 002E × 0085 ÷ # ÷ [0.2] FULL STOP (ATerm) × [9.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 002E × 0308 × 0085 ÷ # ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [9.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 002E × 0009 ÷ # ÷ [0.2] FULL STOP (ATerm) × [9.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 002E × 0308 × 0009 ÷ # ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [9.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 002E × 0061 ÷ # ÷ [0.2] FULL STOP (ATerm) × [8.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 002E × 0308 × 0061 ÷ # ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [8.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 002E ÷ 0041 ÷ # ÷ [0.2] FULL STOP (ATerm) ÷ [11.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 002E × 0308 ÷ 0041 ÷ # ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 002E ÷ 01BB ÷ # ÷ [0.2] FULL STOP (ATerm) ÷ [11.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 002E × 0308 ÷ 01BB ÷ # ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 002E × 0030 ÷ # ÷ [0.2] FULL STOP (ATerm) × [6.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 002E × 0308 × 0030 ÷ # ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [6.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 002E × 002E ÷ # ÷ [0.2] FULL STOP (ATerm) × [8.1] FULL STOP (ATerm) ÷ [0.3] +÷ 002E × 0308 × 002E ÷ # ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [8.1] FULL STOP (ATerm) ÷ [0.3] +÷ 002E × 0021 ÷ # ÷ [0.2] FULL STOP (ATerm) × [8.1] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 002E × 0308 × 0021 ÷ # ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [8.1] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 002E × 0022 ÷ # ÷ [0.2] FULL STOP (ATerm) × [9.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 002E × 0308 × 0022 ÷ # ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [9.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 002E × 002C ÷ # ÷ [0.2] FULL STOP (ATerm) × [8.1] COMMA (SContinue) ÷ [0.3] +÷ 002E × 0308 × 002C ÷ # ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [8.1] COMMA (SContinue) ÷ [0.3] +÷ 002E × 00AD ÷ # ÷ [0.2] FULL STOP (ATerm) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 002E × 0308 × 00AD ÷ # ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 002E × 0300 ÷ # ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 002E × 0308 × 0300 ÷ # ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 0021 ÷ 0001 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) ÷ [11.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 0021 × 0308 ÷ 0001 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 0021 × 000D ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [9.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 0021 × 0308 × 000D ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [9.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 0021 × 000A ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [9.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 0021 × 0308 × 000A ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [9.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 0021 × 0085 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [9.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 0021 × 0308 × 0085 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [9.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 0021 × 0009 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [9.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 0021 × 0308 × 0009 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [9.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 0021 ÷ 0061 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) ÷ [11.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 0021 × 0308 ÷ 0061 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 0021 ÷ 0041 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) ÷ [11.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 0021 × 0308 ÷ 0041 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 0021 ÷ 01BB ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) ÷ [11.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 0021 × 0308 ÷ 01BB ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 0021 ÷ 0030 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) ÷ [11.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 0021 × 0308 ÷ 0030 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 0021 × 002E ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [8.1] FULL STOP (ATerm) ÷ [0.3] +÷ 0021 × 0308 × 002E ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [8.1] FULL STOP (ATerm) ÷ [0.3] +÷ 0021 × 0021 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [8.1] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 0021 × 0308 × 0021 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [8.1] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 0021 × 0022 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [9.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 0021 × 0308 × 0022 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [9.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 0021 × 002C ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [8.1] COMMA (SContinue) ÷ [0.3] +÷ 0021 × 0308 × 002C ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [8.1] COMMA (SContinue) ÷ [0.3] +÷ 0021 × 00AD ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 0021 × 0308 × 00AD ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 0021 × 0300 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 0021 × 0308 × 0300 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 0022 × 0001 ÷ # ÷ [0.2] QUOTATION MARK (Close) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 0022 × 0308 × 0001 ÷ # ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 0022 × 000D ÷ # ÷ [0.2] QUOTATION MARK (Close) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 0022 × 0308 × 000D ÷ # ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 0022 × 000A ÷ # ÷ [0.2] QUOTATION MARK (Close) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 0022 × 0308 × 000A ÷ # ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 0022 × 0085 ÷ # ÷ [0.2] QUOTATION MARK (Close) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 0022 × 0308 × 0085 ÷ # ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 0022 × 0009 ÷ # ÷ [0.2] QUOTATION MARK (Close) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 0022 × 0308 × 0009 ÷ # ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 0022 × 0061 ÷ # ÷ [0.2] QUOTATION MARK (Close) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 0022 × 0308 × 0061 ÷ # ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 0022 × 0041 ÷ # ÷ [0.2] QUOTATION MARK (Close) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 0022 × 0308 × 0041 ÷ # ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 0022 × 01BB ÷ # ÷ [0.2] QUOTATION MARK (Close) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 0022 × 0308 × 01BB ÷ # ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 0022 × 0030 ÷ # ÷ [0.2] QUOTATION MARK (Close) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 0022 × 0308 × 0030 ÷ # ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 0022 × 002E ÷ # ÷ [0.2] QUOTATION MARK (Close) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 0022 × 0308 × 002E ÷ # ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 0022 × 0021 ÷ # ÷ [0.2] QUOTATION MARK (Close) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 0022 × 0308 × 0021 ÷ # ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 0022 × 0022 ÷ # ÷ [0.2] QUOTATION MARK (Close) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 0022 × 0308 × 0022 ÷ # ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 0022 × 002C ÷ # ÷ [0.2] QUOTATION MARK (Close) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 0022 × 0308 × 002C ÷ # ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 0022 × 00AD ÷ # ÷ [0.2] QUOTATION MARK (Close) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 0022 × 0308 × 00AD ÷ # ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 0022 × 0300 ÷ # ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 0022 × 0308 × 0300 ÷ # ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 002C × 0001 ÷ # ÷ [0.2] COMMA (SContinue) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 002C × 0308 × 0001 ÷ # ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 002C × 000D ÷ # ÷ [0.2] COMMA (SContinue) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 002C × 0308 × 000D ÷ # ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 002C × 000A ÷ # ÷ [0.2] COMMA (SContinue) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 002C × 0308 × 000A ÷ # ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 002C × 0085 ÷ # ÷ [0.2] COMMA (SContinue) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 002C × 0308 × 0085 ÷ # ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 002C × 0009 ÷ # ÷ [0.2] COMMA (SContinue) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 002C × 0308 × 0009 ÷ # ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 002C × 0061 ÷ # ÷ [0.2] COMMA (SContinue) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 002C × 0308 × 0061 ÷ # ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 002C × 0041 ÷ # ÷ [0.2] COMMA (SContinue) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 002C × 0308 × 0041 ÷ # ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 002C × 01BB ÷ # ÷ [0.2] COMMA (SContinue) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 002C × 0308 × 01BB ÷ # ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 002C × 0030 ÷ # ÷ [0.2] COMMA (SContinue) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 002C × 0308 × 0030 ÷ # ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 002C × 002E ÷ # ÷ [0.2] COMMA (SContinue) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 002C × 0308 × 002E ÷ # ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 002C × 0021 ÷ # ÷ [0.2] COMMA (SContinue) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 002C × 0308 × 0021 ÷ # ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 002C × 0022 ÷ # ÷ [0.2] COMMA (SContinue) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 002C × 0308 × 0022 ÷ # ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 002C × 002C ÷ # ÷ [0.2] COMMA (SContinue) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 002C × 0308 × 002C ÷ # ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 002C × 00AD ÷ # ÷ [0.2] COMMA (SContinue) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 002C × 0308 × 00AD ÷ # ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 002C × 0300 ÷ # ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 002C × 0308 × 0300 ÷ # ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 00AD × 0001 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 00AD × 0308 × 0001 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 00AD × 000D ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 00AD × 0308 × 000D ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 00AD × 000A ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 00AD × 0308 × 000A ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 00AD × 0085 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 00AD × 0308 × 0085 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 00AD × 0009 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 00AD × 0308 × 0009 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 00AD × 0061 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 00AD × 0308 × 0061 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 00AD × 0041 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 00AD × 0308 × 0041 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 00AD × 01BB ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 00AD × 0308 × 01BB ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 00AD × 0030 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 00AD × 0308 × 0030 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 00AD × 002E ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 00AD × 0308 × 002E ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 00AD × 0021 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 00AD × 0308 × 0021 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 00AD × 0022 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 00AD × 0308 × 0022 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 00AD × 002C ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 00AD × 0308 × 002C ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 00AD × 00AD ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 00AD × 0308 × 00AD ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 00AD × 0300 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 00AD × 0308 × 0300 ÷ # ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 0300 × 0001 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 0300 × 0308 × 0001 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3] +÷ 0300 × 000D ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 0300 × 0308 × 000D ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3] +÷ 0300 × 000A ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 0300 × 0308 × 000A ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3] +÷ 0300 × 0085 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 0300 × 0308 × 0085 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3] +÷ 0300 × 0009 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 0300 × 0308 × 0009 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3] +÷ 0300 × 0061 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 0300 × 0308 × 0061 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3] +÷ 0300 × 0041 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 0300 × 0308 × 0041 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3] +÷ 0300 × 01BB ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 0300 × 0308 × 01BB ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3] +÷ 0300 × 0030 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 0300 × 0308 × 0030 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3] +÷ 0300 × 002E ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 0300 × 0308 × 002E ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 0300 × 0021 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 0300 × 0308 × 0021 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3] +÷ 0300 × 0022 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 0300 × 0308 × 0022 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3] +÷ 0300 × 002C ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 0300 × 0308 × 002C ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3] +÷ 0300 × 00AD ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 0300 × 0308 × 00AD ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3] +÷ 0300 × 0300 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 0300 × 0308 × 0300 ÷ # ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3] +÷ 000D × 000A ÷ 0061 × 000A ÷ 0308 ÷ # ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) × [3.0] <LINE FEED (LF)> (LF) ÷ [4.0] LATIN SMALL LETTER A (Lower) × [998.0] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [0.3] +÷ 0061 × 0308 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [0.3] +÷ 0020 × 200D × 0646 ÷ # ÷ [0.2] SPACE (Sp) × [5.0] ZERO WIDTH JOINER (Extend_FE) × [998.0] ARABIC LETTER NOON (OLetter) ÷ [0.3] +÷ 0646 × 200D × 0020 ÷ # ÷ [0.2] ARABIC LETTER NOON (OLetter) × [5.0] ZERO WIDTH JOINER (Extend_FE) × [998.0] SPACE (Sp) ÷ [0.3] +÷ 0028 × 0022 × 0047 × 006F × 002E × 0022 × 0029 × 0020 ÷ 0028 × 0048 × 0065 × 0020 × 0064 × 0069 × 0064 × 002E × 0029 ÷ # ÷ [0.2] LEFT PARENTHESIS (Close) × [998.0] QUOTATION MARK (Close) × [998.0] LATIN CAPITAL LETTER G (Upper) × [998.0] LATIN SMALL LETTER O (Lower) × [998.0] FULL STOP (ATerm) × [9.0] QUOTATION MARK (Close) × [9.0] RIGHT PARENTHESIS (Close) × [9.0] SPACE (Sp) ÷ [11.0] LEFT PARENTHESIS (Close) × [998.0] LATIN CAPITAL LETTER H (Upper) × [998.0] LATIN SMALL LETTER E (Lower) × [998.0] SPACE (Sp) × [998.0] LATIN SMALL LETTER D (Lower) × [998.0] LATIN SMALL LETTER I (Lower) × [998.0] LATIN SMALL LETTER D (Lower) × [998.0] FULL STOP (ATerm) × [9.0] RIGHT PARENTHESIS (Close) ÷ [0.3] +÷ 0028 × 201C × 0047 × 006F × 003F × 201D × 0029 × 0020 ÷ 0028 × 0048 × 0065 × 0020 × 0064 × 0069 × 0064 × 002E × 0029 ÷ # ÷ [0.2] LEFT PARENTHESIS (Close) × [998.0] LEFT DOUBLE QUOTATION MARK (Close) × [998.0] LATIN CAPITAL LETTER G (Upper) × [998.0] LATIN SMALL LETTER O (Lower) × [998.0] QUESTION MARK (STerm) × [9.0] RIGHT DOUBLE QUOTATION MARK (Close) × [9.0] RIGHT PARENTHESIS (Close) × [9.0] SPACE (Sp) ÷ [11.0] LEFT PARENTHESIS (Close) × [998.0] LATIN CAPITAL LETTER H (Upper) × [998.0] LATIN SMALL LETTER E (Lower) × [998.0] SPACE (Sp) × [998.0] LATIN SMALL LETTER D (Lower) × [998.0] LATIN SMALL LETTER I (Lower) × [998.0] LATIN SMALL LETTER D (Lower) × [998.0] FULL STOP (ATerm) × [9.0] RIGHT PARENTHESIS (Close) ÷ [0.3] +÷ 0055 × 002E × 0053 × 002E × 0041 × 0300 × 002E × 0020 × 0069 × 0073 ÷ # ÷ [0.2] LATIN CAPITAL LETTER U (Upper) × [998.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER S (Upper) × [998.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] FULL STOP (ATerm) × [8.0] SPACE (Sp) × [8.0] LATIN SMALL LETTER I (Lower) × [998.0] LATIN SMALL LETTER S (Lower) ÷ [0.3] +÷ 0055 × 002E × 0053 × 002E × 0041 × 0300 × 003F × 0020 ÷ 0048 × 0065 ÷ # ÷ [0.2] LATIN CAPITAL LETTER U (Upper) × [998.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER S (Upper) × [998.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] QUESTION MARK (STerm) × [9.0] SPACE (Sp) ÷ [11.0] LATIN CAPITAL LETTER H (Upper) × [998.0] LATIN SMALL LETTER E (Lower) ÷ [0.3] +÷ 0055 × 002E × 0053 × 002E × 0041 × 0300 × 002E ÷ # ÷ [0.2] LATIN CAPITAL LETTER U (Upper) × [998.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER S (Upper) × [998.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3] +÷ 0033 × 002E × 0034 ÷ # ÷ [0.2] DIGIT THREE (Numeric) × [998.0] FULL STOP (ATerm) × [6.0] DIGIT FOUR (Numeric) ÷ [0.3] +÷ 0063 × 002E × 0064 ÷ # ÷ [0.2] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [8.0] LATIN SMALL LETTER D (Lower) ÷ [0.3] +÷ 0043 × 002E × 0064 ÷ # ÷ [0.2] LATIN CAPITAL LETTER C (Upper) × [998.0] FULL STOP (ATerm) × [8.0] LATIN SMALL LETTER D (Lower) ÷ [0.3] +÷ 0063 × 002E × 0044 ÷ # ÷ [0.2] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER D (Upper) ÷ [0.3] +÷ 0043 × 002E × 0044 ÷ # ÷ [0.2] LATIN CAPITAL LETTER C (Upper) × [998.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER D (Upper) ÷ [0.3] +÷ 0065 × 0074 × 0063 × 002E × 0029 × 2019 × 00A0 × 0074 × 0068 × 0065 ÷ # ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [8.0] RIGHT PARENTHESIS (Close) × [8.0] RIGHT SINGLE QUOTATION MARK (Close) × [8.0] NO-BREAK SPACE (Sp) × [8.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER H (Lower) × [998.0] LATIN SMALL LETTER E (Lower) ÷ [0.3] +÷ 0065 × 0074 × 0063 × 002E × 0029 × 2019 × 00A0 ÷ 0054 × 0068 × 0065 ÷ # ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [9.0] RIGHT PARENTHESIS (Close) × [9.0] RIGHT SINGLE QUOTATION MARK (Close) × [9.0] NO-BREAK SPACE (Sp) ÷ [11.0] LATIN CAPITAL LETTER T (Upper) × [998.0] LATIN SMALL LETTER H (Lower) × [998.0] LATIN SMALL LETTER E (Lower) ÷ [0.3] +÷ 0065 × 0074 × 0063 × 002E × 0029 × 2019 × 00A0 × 2018 × 0028 × 0074 × 0068 × 0065 ÷ # ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [8.0] RIGHT PARENTHESIS (Close) × [8.0] RIGHT SINGLE QUOTATION MARK (Close) × [8.0] NO-BREAK SPACE (Sp) × [8.0] LEFT SINGLE QUOTATION MARK (Close) × [998.0] LEFT PARENTHESIS (Close) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER H (Lower) × [998.0] LATIN SMALL LETTER E (Lower) ÷ [0.3] +÷ 0065 × 0074 × 0063 × 002E × 0029 × 2019 × 00A0 ÷ 2018 × 0028 × 0054 × 0068 × 0065 ÷ # ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [9.0] RIGHT PARENTHESIS (Close) × [9.0] RIGHT SINGLE QUOTATION MARK (Close) × [9.0] NO-BREAK SPACE (Sp) ÷ [11.0] LEFT SINGLE QUOTATION MARK (Close) × [998.0] LEFT PARENTHESIS (Close) × [998.0] LATIN CAPITAL LETTER T (Upper) × [998.0] LATIN SMALL LETTER H (Lower) × [998.0] LATIN SMALL LETTER E (Lower) ÷ [0.3] +÷ 0065 × 0074 × 0063 × 002E × 0029 × 2019 × 00A0 × 0308 × 0074 × 0068 × 0065 ÷ # ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [8.0] RIGHT PARENTHESIS (Close) × [8.0] RIGHT SINGLE QUOTATION MARK (Close) × [8.0] NO-BREAK SPACE (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [8.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER H (Lower) × [998.0] LATIN SMALL LETTER E (Lower) ÷ [0.3] +÷ 0065 × 0074 × 0063 × 002E × 0029 × 2019 × 00A0 × 0308 ÷ 0054 × 0068 × 0065 ÷ # ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [9.0] RIGHT PARENTHESIS (Close) × [9.0] RIGHT SINGLE QUOTATION MARK (Close) × [9.0] NO-BREAK SPACE (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] LATIN CAPITAL LETTER T (Upper) × [998.0] LATIN SMALL LETTER H (Lower) × [998.0] LATIN SMALL LETTER E (Lower) ÷ [0.3] +÷ 0065 × 0074 × 0063 × 002E × 0029 × 2019 × 0308 ÷ 0054 × 0068 × 0065 ÷ # ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [9.0] RIGHT PARENTHESIS (Close) × [9.0] RIGHT SINGLE QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] LATIN CAPITAL LETTER T (Upper) × [998.0] LATIN SMALL LETTER H (Lower) × [998.0] LATIN SMALL LETTER E (Lower) ÷ [0.3] +÷ 0065 × 0074 × 0063 × 002E × 0029 × 000A ÷ 0308 × 0054 × 0068 × 0065 ÷ # ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [9.0] RIGHT PARENTHESIS (Close) × [9.0] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER T (Upper) × [998.0] LATIN SMALL LETTER H (Lower) × [998.0] LATIN SMALL LETTER E (Lower) ÷ [0.3] +÷ 0074 × 0068 × 0065 × 0020 × 0072 × 0065 × 0073 × 0070 × 002E × 0020 × 006C × 0065 × 0061 × 0064 × 0065 × 0072 × 0073 × 0020 × 0061 × 0072 × 0065 ÷ # ÷ [0.2] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER H (Lower) × [998.0] LATIN SMALL LETTER E (Lower) × [998.0] SPACE (Sp) × [998.0] LATIN SMALL LETTER R (Lower) × [998.0] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER S (Lower) × [998.0] LATIN SMALL LETTER P (Lower) × [998.0] FULL STOP (ATerm) × [8.0] SPACE (Sp) × [8.0] LATIN SMALL LETTER L (Lower) × [998.0] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER A (Lower) × [998.0] LATIN SMALL LETTER D (Lower) × [998.0] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER R (Lower) × [998.0] LATIN SMALL LETTER S (Lower) × [998.0] SPACE (Sp) × [998.0] LATIN SMALL LETTER A (Lower) × [998.0] LATIN SMALL LETTER R (Lower) × [998.0] LATIN SMALL LETTER E (Lower) ÷ [0.3] +÷ 5B57 × 002E ÷ 5B57 ÷ # ÷ [0.2] CJK UNIFIED IDEOGRAPH-5B57 (OLetter) × [998.0] FULL STOP (ATerm) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B57 (OLetter) ÷ [0.3] +÷ 0065 × 0074 × 0063 × 002E ÷ 5B83 ÷ # ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B83 (OLetter) ÷ [0.3] +÷ 0065 × 0074 × 0063 × 002E × 3002 ÷ # ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [8.1] IDEOGRAPHIC FULL STOP (STerm) ÷ [0.3] +÷ 5B57 × 3002 ÷ 5B83 ÷ # ÷ [0.2] CJK UNIFIED IDEOGRAPH-5B57 (OLetter) × [998.0] IDEOGRAPHIC FULL STOP (STerm) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B83 (OLetter) ÷ [0.3] +÷ 0021 × 0020 × 0020 ÷ # ÷ [0.2] EXCLAMATION MARK (STerm) × [9.0] SPACE (Sp) × [10.0] SPACE (Sp) ÷ [0.3] +÷ 2060 × 0028 × 2060 × 0022 × 2060 × 0047 × 2060 × 006F × 2060 × 002E × 2060 × 0022 × 2060 × 0029 × 2060 × 0020 × 2060 ÷ 0028 × 2060 × 0048 × 2060 × 0065 × 2060 × 0020 × 2060 × 0064 × 2060 × 0069 × 2060 × 0064 × 2060 × 002E × 2060 × 0029 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER G (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER O (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER H (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER I (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0028 × 2060 × 201C × 2060 × 0047 × 2060 × 006F × 2060 × 003F × 2060 × 201D × 2060 × 0029 × 2060 × 0020 × 2060 ÷ 0028 × 2060 × 0048 × 2060 × 0065 × 2060 × 0020 × 2060 × 0064 × 2060 × 0069 × 2060 × 0064 × 2060 × 002E × 2060 × 0029 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LEFT DOUBLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER G (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER O (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] QUESTION MARK (STerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT DOUBLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER H (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER I (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0055 × 2060 × 002E × 2060 × 0053 × 2060 × 002E × 2060 × 0041 × 2060 × 0300 × 002E × 2060 × 0020 × 2060 × 0069 × 2060 × 0073 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER U (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER S (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER A (Upper) × [5.0] WORD JOINER (Format_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [8.0] LATIN SMALL LETTER I (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER S (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0055 × 2060 × 002E × 2060 × 0053 × 2060 × 002E × 2060 × 0041 × 2060 × 0300 × 003F × 2060 × 0020 × 2060 ÷ 0048 × 2060 × 0065 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER U (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER S (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER A (Upper) × [5.0] WORD JOINER (Format_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] QUESTION MARK (STerm) × [5.0] WORD JOINER (Format_FE) × [9.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] LATIN CAPITAL LETTER H (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0055 × 2060 × 002E × 2060 × 0053 × 2060 × 002E × 2060 × 0041 × 2060 × 0300 × 002E × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER U (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER S (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER A (Upper) × [5.0] WORD JOINER (Format_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0033 × 2060 × 002E × 2060 × 0034 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] DIGIT THREE (Numeric) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [6.0] DIGIT FOUR (Numeric) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0063 × 2060 × 002E × 2060 × 0064 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0043 × 2060 × 002E × 2060 × 0064 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER C (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0063 × 2060 × 002E × 2060 × 0044 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER D (Upper) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0043 × 2060 × 002E × 2060 × 0044 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER C (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER D (Upper) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 0029 × 2060 × 2019 × 2060 × 00A0 × 2060 × 0074 × 2060 × 0068 × 2060 × 0065 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [8.0] RIGHT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [8.0] NO-BREAK SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [8.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 0029 × 2060 × 2019 × 2060 × 00A0 × 2060 ÷ 0054 × 2060 × 0068 × 2060 × 0065 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] NO-BREAK SPACE (Sp) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] LATIN CAPITAL LETTER T (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 0029 × 2060 × 2019 × 2060 × 00A0 × 2060 × 2018 × 2060 × 0028 × 2060 × 0074 × 2060 × 0068 × 2060 × 0065 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [8.0] RIGHT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [8.0] NO-BREAK SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [8.0] LEFT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 0029 × 2060 × 2019 × 2060 × 00A0 × 2060 ÷ 2018 × 2060 × 0028 × 2060 × 0054 × 2060 × 0068 × 2060 × 0065 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] NO-BREAK SPACE (Sp) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] LEFT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER T (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 0029 × 2060 × 2019 × 2060 × 00A0 × 2060 × 0308 × 0074 × 2060 × 0068 × 2060 × 0065 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [8.0] RIGHT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [8.0] NO-BREAK SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [8.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 0029 × 2060 × 2019 × 2060 × 00A0 × 2060 × 0308 ÷ 0054 × 2060 × 0068 × 2060 × 0065 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] NO-BREAK SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] LATIN CAPITAL LETTER T (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 0029 × 2060 × 2019 × 2060 × 0308 ÷ 0054 × 2060 × 0068 × 2060 × 0065 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] LATIN CAPITAL LETTER T (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 0029 × 2060 × 000A ÷ 2060 × 0308 × 2060 × 0054 × 2060 × 0068 × 2060 × 0065 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] <LINE FEED (LF)> (LF) ÷ [4.0] WORD JOINER (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER T (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0074 × 2060 × 0068 × 2060 × 0065 × 2060 × 0020 × 2060 × 0072 × 2060 × 0065 × 2060 × 0073 × 2060 × 0070 × 2060 × 002E × 2060 × 0020 × 2060 × 006C × 2060 × 0065 × 2060 × 0061 × 2060 × 0064 × 2060 × 0065 × 2060 × 0072 × 2060 × 0073 × 2060 × 0020 × 2060 × 0061 × 2060 × 0072 × 2060 × 0065 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER R (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER S (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER P (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [8.0] LATIN SMALL LETTER L (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER A (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER R (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER S (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER A (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER R (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 5B57 × 2060 × 002E × 2060 ÷ 5B57 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] CJK UNIFIED IDEOGRAPH-5B57 (OLetter) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B57 (OLetter) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 ÷ 5B83 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B83 (OLetter) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 3002 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.1] IDEOGRAPHIC FULL STOP (STerm) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 5B57 × 2060 × 3002 × 2060 ÷ 5B83 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] CJK UNIFIED IDEOGRAPH-5B57 (OLetter) × [5.0] WORD JOINER (Format_FE) × [998.0] IDEOGRAPHIC FULL STOP (STerm) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B83 (OLetter) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +÷ 2060 × 0021 × 2060 × 0020 × 2060 × 0020 × 2060 × 2060 ÷ # ÷ [0.2] WORD JOINER (Format_FE) × [998.0] EXCLAMATION MARK (STerm) × [5.0] WORD JOINER (Format_FE) × [9.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [10.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3] +# +# Lines: 502 +# +# EOF diff --git a/gen/sentence-test.c b/gen/sentence-test.c @@ -0,0 +1,19 @@ +/* See LICENSE file for copyright and license details. */ +#include <stddef.h> + +#include "util.h" + +int +main(int argc, char *argv[]) +{ + struct break_test *test = NULL; + size_t testlen = 0; + + (void)argc; + + break_test_list_parse("data/SentenceBreakTest.txt", &test, &testlen); + break_test_list_print(test, testlen, "sentence_break_test", argv[0]); + break_test_list_free(test, testlen); + + return 0; +} diff --git a/gen/sentence.c b/gen/sentence.c @@ -0,0 +1,94 @@ +/* See LICENSE file for copyright and license details. */ +#include "util.h" + +#define FILE_SENTENCE "data/SentenceBreakProperty.txt" + +static const struct property_spec sentence_break_property[] = { + { + .enumname = "OTHER", + .file = NULL, + .ucdname = NULL, + }, + { + .enumname = "CR", + .file = FILE_SENTENCE, + .ucdname = "CR", + }, + { + .enumname = "LF", + .file = FILE_SENTENCE, + .ucdname = "LF", + }, + { + .enumname = "EXTEND", + .file = FILE_SENTENCE, + .ucdname = "Extend", + }, + { + .enumname = "SEP", + .file = FILE_SENTENCE, + .ucdname = "Sep", + }, + { + .enumname = "FORMAT", + .file = FILE_SENTENCE, + .ucdname = "Format", + }, + { + .enumname = "SP", + .file = FILE_SENTENCE, + .ucdname = "Sp", + }, + { + .enumname = "LOWER", + .file = FILE_SENTENCE, + .ucdname = "Lower", + }, + { + .enumname = "UPPER", + .file = FILE_SENTENCE, + .ucdname = "Upper", + }, + { + .enumname = "OLETTER", + .file = FILE_SENTENCE, + .ucdname = "OLetter", + }, + { + .enumname = "NUMERIC", + .file = FILE_SENTENCE, + .ucdname = "Numeric", + }, + { + .enumname = "ATERM", + .file = FILE_SENTENCE, + .ucdname = "ATerm", + }, + { + .enumname = "SCONTINUE", + .file = FILE_SENTENCE, + .ucdname = "SContinue", + }, + { + .enumname = "STERM", + .file = FILE_SENTENCE, + .ucdname = "STerm", + }, + { + .enumname = "CLOSE", + .file = FILE_SENTENCE, + .ucdname = "Close", + }, +}; + +int +main(int argc, char *argv[]) +{ + (void)argc; + + properties_generate_break_property(sentence_break_property, + LEN(sentence_break_property), + NULL, "sentence", argv[0]); + + return 0; +} diff --git a/grapheme.h b/grapheme.h @@ -18,9 +18,11 @@ typedef struct grapheme_internal_segmentation_state { bool grapheme_is_character_break(uint_least32_t, uint_least32_t, GRAPHEME_STATE *); size_t grapheme_next_character_break(const uint_least32_t *, size_t); +size_t grapheme_next_sentence_break(const uint_least32_t *, size_t); size_t grapheme_next_word_break(const uint_least32_t *, size_t); size_t grapheme_next_character_break_utf8(const char *, size_t); +size_t grapheme_next_sentence_break_utf8(const char *, size_t); size_t grapheme_next_word_break_utf8(const char *, size_t); size_t grapheme_decode_utf8(const char *, size_t, uint_least32_t *); diff --git a/src/sentence.c b/src/sentence.c @@ -0,0 +1,366 @@ +/* See LICENSE file for copyright and license details. */ +#include <stdbool.h> +#include <stddef.h> +#include <stdlib.h> +#include <string.h> + +#include "../gen/sentence.h" +#include "../grapheme.h" +#include "util.h" + +static inline enum sentence_break_property +get_break_prop(uint_least32_t cp) +{ + if (likely(cp <= 0x10FFFF)) { + return (enum sentence_break_property) + sentence_break_minor[sentence_break_major[cp >> 8] + + (cp & 0xff)]; + } else { + return SENTENCE_BREAK_PROP_OTHER; + } +} + +static inline size_t +get_codepoint(const void *str, size_t len, size_t offset, uint_least32_t *cp) +{ + if (offset < len) { + *cp = ((const uint_least32_t *)str)[offset]; + return 1; + } else { + *cp = GRAPHEME_INVALID_CODEPOINT; + return 0; + } +} + +static inline size_t +get_codepoint_utf8(const void *str, size_t len, size_t offset, uint_least32_t *cp) +{ + if (offset < len) { + return grapheme_decode_utf8((const char *)str + offset, + len - offset, cp); + } else { + *cp = GRAPHEME_INVALID_CODEPOINT; + return 0; + } +} + +static size_t +next_sentence_break(const void *str, size_t len, size_t (*get_codepoint) + (const void *, size_t, size_t, uint_least32_t *)) +{ + struct { + enum sentence_break_property a, b, c, d; + } raw, skip; + enum sentence_break_property res; + uint_least32_t cp; + uint_least8_t aterm_close_sp_level = 0, + saterm_close_sp_parasep_level = 0; + size_t off, tmp, new_off; + + /* check degenerate cases */ + if (str == NULL || len == 0) { + return 0; + } + + /* + * Apply sentence breaking algorithm (UAX #29), see + * https://unicode.org/reports/tr29/#Word_Boundary_Rules + * + * There are 4 slots (a, b, c, d) of "break" properties and + * we check if there is a break in the middle between b and c. + * + * The position of this middle spot is determined by off, + * which gives the offset of the first element on the right + * hand side of said spot, or, in other words, gives the number + * of elements on the left hand side. + * + * It is further complicated by the fact that the algorithm + * expects you to skip certain characters for the second + * half of the rules (after WB4). Thus, we do not only have + * the "raw" properties as described above, but also the "skip" + * properties, where the skip.a and skip.b, for instance, + * give the two preceding character properties behind the + * currently investigated breakpoint. + * + */ + + /* + * Initialize the different properties such that we have + * a good state after the state-update in the loop + */ + raw.b = NUM_SENTENCE_BREAK_PROPS; + if ((off = get_codepoint(str, len, 0, &cp)) >= len) { + return 1; + } + raw.c = get_break_prop(cp); + (void)get_codepoint(str, len, off, &cp); + raw.d = get_break_prop(cp); + skip.a = skip.b = NUM_SENTENCE_BREAK_PROPS; + + for (; off < len; off = new_off) { + /* + * Update left side (a and b) of the skip state by + * "shifting in" the raw.c property as long as it is + * not one of the "ignored" character properties. + * While at it, update the RI-counter. + * + */ + if (raw.c != SENTENCE_BREAK_PROP_EXTEND && + raw.c != SENTENCE_BREAK_PROP_FORMAT) { + skip.a = skip.b; + skip.b = raw.c; + + /* + * Here comes a bit of magic. The rules + * SB8, SB8a, SB9 and SB10 have very complicated + * left-hand-side-rules of the form + * + * ATerm Close* Sp* + * SATerm Close* + * SATerm Close* Sp* + * SATerm Close* Sp* ParaSep? + * + * but instead of backtracking, we keep the + * state as some kind of "power level" in + * two variables + * + * aterm_close_sp_level + * saterm_close_sp_parasep_level + * + * that go from 0 to 3/4: + * + * 0: we are not in the sequence + * 1: we have one ATerm/SATerm to the left of + * the middle spot + * 2: we have one ATerm/SATerm and one or more + * Close to the left of the middle spot + * 3: we have one ATerm/SATerm, zero or more + * Close and one or more Sp to the left of + * the middle spot. + * 4: we have one SATerm, zero or more Close, + * zero or more Sp and one ParaSep to the + * left of the middle spot. + * + */ + if (aterm_close_sp_level == 0 && + skip.b == SENTENCE_BREAK_PROP_ATERM) { + /* sequence has begun */ + aterm_close_sp_level = 1; + } else if ((aterm_close_sp_level == 1 || + aterm_close_sp_level == 2) && + skip.b == SENTENCE_BREAK_PROP_CLOSE) { + /* close-sequence begins or continued */ + aterm_close_sp_level = 2; + } else if ((aterm_close_sp_level == 1 || + aterm_close_sp_level == 2 || + aterm_close_sp_level == 3) && + skip.b == SENTENCE_BREAK_PROP_SP) { + /* sp-sequence begins or continued */ + aterm_close_sp_level = 3; + } else { + /* sequence broke */ + aterm_close_sp_level = 0; + } + + if (saterm_close_sp_parasep_level == 0 && + (skip.b == SENTENCE_BREAK_PROP_STERM || + skip.b == SENTENCE_BREAK_PROP_ATERM)) { + /* sequence has begun */ + saterm_close_sp_parasep_level = 1; + } else if ((saterm_close_sp_parasep_level == 1 || + saterm_close_sp_parasep_level == 2) && + skip.b == SENTENCE_BREAK_PROP_CLOSE) { + /* close-sequence begins or continued */ + saterm_close_sp_parasep_level = 2; + } else if ((saterm_close_sp_parasep_level == 1 || + saterm_close_sp_parasep_level == 2 || + saterm_close_sp_parasep_level == 3) && + skip.b == SENTENCE_BREAK_PROP_SP) { + /* sp-sequence begins or continued */ + saterm_close_sp_parasep_level = 3; + } else if ((saterm_close_sp_parasep_level == 1 || + saterm_close_sp_parasep_level == 2 || + saterm_close_sp_parasep_level == 3) && + (skip.b == SENTENCE_BREAK_PROP_SEP || + skip.b == SENTENCE_BREAK_PROP_CR || + skip.b == SENTENCE_BREAK_PROP_LF)) { + /* ParaSep at the end of the sequence */ + saterm_close_sp_parasep_level = 4; + } else { + /* sequence broke */ + saterm_close_sp_parasep_level = 0; + } + } + + /* + * Update right side (b and c) of the skip state by + * starting at the breakpoint and detecting the two + * following non-ignored character classes + * + */ + skip.c = NUM_SENTENCE_BREAK_PROPS; + for (tmp = off; tmp < len; ) { + tmp += get_codepoint(str, len, tmp, &cp); + res = get_break_prop(cp); + + if (res != SENTENCE_BREAK_PROP_EXTEND && + res != SENTENCE_BREAK_PROP_FORMAT) { + skip.c = res; + break; + } + } + skip.d = NUM_SENTENCE_BREAK_PROPS; + for (; tmp < len; ) { + tmp += get_codepoint(str, len, tmp, &cp); + res = get_break_prop(cp); + + if (res != SENTENCE_BREAK_PROP_EXTEND && + res != SENTENCE_BREAK_PROP_FORMAT) { + skip.d = res; + break; + } + } + + /* + * Update the raw state by simply shifting everything + * in and, if we still have data left, determining + * the character class of the next codepoint. + * + */ + raw.a = raw.b; + raw.b = raw.c; + raw.c = raw.d; + if ((new_off = off + get_codepoint(str, len, off, &cp)) < len) { + get_codepoint(str, len, new_off, &cp); + raw.d = get_break_prop(cp); + } else { + raw.d = NUM_SENTENCE_BREAK_PROPS; + } + + /* SB3 */ + if (raw.b == SENTENCE_BREAK_PROP_CR && + raw.c == SENTENCE_BREAK_PROP_LF) { + continue; + } + + /* SB4 */ + if (raw.b == SENTENCE_BREAK_PROP_SEP || + raw.b == SENTENCE_BREAK_PROP_CR || + raw.b == SENTENCE_BREAK_PROP_LF) { + break; + } + + /* SB5 */ + if (raw.c == SENTENCE_BREAK_PROP_EXTEND || + raw.c == SENTENCE_BREAK_PROP_FORMAT) { + continue; + } + + /* SB6 */ + if (skip.b == SENTENCE_BREAK_PROP_ATERM && + skip.c == SENTENCE_BREAK_PROP_NUMERIC) { + continue; + } + + /* SB7 */ + if (off > 1 && + (skip.a == SENTENCE_BREAK_PROP_UPPER || + skip.a == SENTENCE_BREAK_PROP_LOWER) && + skip.b == SENTENCE_BREAK_PROP_ATERM && + skip.c == SENTENCE_BREAK_PROP_UPPER) { + continue; + } + + /* SB8 */ + if (aterm_close_sp_level == 1 || + aterm_close_sp_level == 2 || + aterm_close_sp_level == 3) { + /* + * This is the most complicated rule, requiring + * the right-hand-side to satisfy the regular expression + * + * ( ¬(OLetter | Upper | Lower | ParaSep | SATerm) )* Lower + * + * which we simply check "manually" given LUT-lookups + * are very cheap. + * + */ + for (tmp = off, res = NUM_SENTENCE_BREAK_PROPS; tmp < len; ) { + tmp += get_codepoint(str, len, tmp, &cp); + res = get_break_prop(cp); + + if (res == SENTENCE_BREAK_PROP_OLETTER || + res == SENTENCE_BREAK_PROP_UPPER || + res == SENTENCE_BREAK_PROP_LOWER || + res == SENTENCE_BREAK_PROP_SEP || + res == SENTENCE_BREAK_PROP_CR || + res == SENTENCE_BREAK_PROP_LF || + res == SENTENCE_BREAK_PROP_STERM || + res == SENTENCE_BREAK_PROP_ATERM) { + break; + } + } + + if (res == SENTENCE_BREAK_PROP_LOWER) { + continue; + } + } + + /* SB8a */ + if ((saterm_close_sp_parasep_level == 1 || + saterm_close_sp_parasep_level == 2 || + saterm_close_sp_parasep_level == 3) && + (skip.c == SENTENCE_BREAK_PROP_SCONTINUE || + skip.c == SENTENCE_BREAK_PROP_STERM || + skip.c == SENTENCE_BREAK_PROP_ATERM)) { + continue; + } + + /* SB9 */ + if ((saterm_close_sp_parasep_level == 1 || + saterm_close_sp_parasep_level == 2) && + (skip.c == SENTENCE_BREAK_PROP_CLOSE || + skip.c == SENTENCE_BREAK_PROP_SP || + skip.c == SENTENCE_BREAK_PROP_SEP || + skip.c == SENTENCE_BREAK_PROP_CR || + skip.c == SENTENCE_BREAK_PROP_LF)) { + continue; + } + + /* SB10 */ + if ((saterm_close_sp_parasep_level == 1 || + saterm_close_sp_parasep_level == 2 || + saterm_close_sp_parasep_level == 3) && + (skip.c == SENTENCE_BREAK_PROP_SP || + skip.c == SENTENCE_BREAK_PROP_SEP || + skip.c == SENTENCE_BREAK_PROP_CR || + skip.c == SENTENCE_BREAK_PROP_LF)) { + continue; + } + + /* SB11 */ + if (saterm_close_sp_parasep_level == 1 || + saterm_close_sp_parasep_level == 2 || + saterm_close_sp_parasep_level == 3 || + saterm_close_sp_parasep_level == 4) { + break; + } + + /* SB998 */ + continue; + } + + return off; +} + +size_t +grapheme_next_sentence_break(const uint_least32_t *str, size_t len) +{ + return next_sentence_break(str, len, get_codepoint); +} + +size_t +grapheme_next_sentence_break_utf8(const char *str, size_t len) +{ + return next_sentence_break(str, len, get_codepoint_utf8); +} diff --git a/test/sentence.c b/test/sentence.c @@ -0,0 +1,17 @@ +/* See LICENSE file for copyright and license details. */ +#include <stdbool.h> +#include <stdint.h> + +#include "../gen/sentence-test.h" +#include "../grapheme.h" +#include "util.h" + +int +main(int argc, char *argv[]) +{ + (void)argc; + + return run_break_tests(grapheme_next_sentence_break, + sentence_break_test, + LEN(sentence_break_test), argv[0]); +}