Update to latest confusables.txt

This change simply updates the package to be based on the latest of Unicode's `confusables.txt`. Additionally, updated the README and Makefile to allow new contributors to easily perform future updates. NW
woodgern · Mar 24, 2021 · 19acf7e · 19acf7e
1 parent a95a908
commit 19acf7e
Show file tree

Hide file tree

Showing 5 changed files with 49 additions and 11 deletions.
diff --git a/Makefile b/Makefile
@@ -5,8 +5,11 @@ parse:
 	python3 confusables/parse.py
 
 update:
-	wget -O confusables/assets/confusables.txt https://www.unicode.org/Public/security/12.1.0/confusables.txt
-
+	if [ -z "$(VERSION)" ]; then \
+		echo "Please specify the VERSION argument with a valid version of unicode confusables"; \
+	else \
+		wget -O confusables/assets/confusables.txt https://www.unicode.org/Public/security/${VERSION}/confusables.txt; \
+	fi
 test:
 	python3 -m unittest discover
 

diff --git a/README.md b/README.md
@@ -71,6 +71,21 @@ print(normalize('Ʀỏ𝕍3ℛ', prioritize_alpha=False))
 # prints ['r0v3r', 'r0ver', 'ro\'v3r', 'ro\'ver', 'rov3r', 'rover']
 ```
 
+## Updating to the latest Unicode confusables version
+
+If you find the latest version of this package to have an out of date version of the unicode official `confusables.txt`, then why not submit a PR to update it!
+
+First, find out what the latest version of unicode confusables is. Then, run
+```
+make update VERSION=X.Y.Z
+```
+
+Next, run
+```
+make parse
+```
+And that's it! Commit your changes and create a pull request.
+
 ## About confusables
 
 This module is something I put together because I'm interested in the field of language processing. I'm hoping to build out it's functionality, and I'm more than happy to take suggestions!

diff --git a/confusables/assets/confusable_mapping.json b/confusables/assets/confusable_mapping.json
diff --git a/confusables/assets/confusables.txt b/confusables/assets/confusables.txt
@@ -1,11 +1,11 @@
 # confusables.txt
-# Date: 2019-04-01, 21:59:19 GMT
-# © 2019 Unicode®, Inc.
+# Date: 2020-02-13, 01:38:49 GMT
+# © 2020 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 Security Mechanisms for UTS #39
-# Version: 12.1.0
+# Version: 13.0.0
 #
 # For documentation and usage, see http://www.unicode.org/reports/tr39
 #
@@ -1358,6 +1358,10 @@ FFED ;	25AA ;	MA	#* ( ￭ → ▪ ) HALFWIDTH BLACK SQUARE → BLACK SMALL SQUAR
 
 266A ;	1D158 1D165 1D16E ;	MA	#* ( ♪ → 𝅘𝅥𝅮 ) EIGHTH NOTE → MUSICAL SYMBOL NOTEHEAD BLACK, MUSICAL SYMBOL COMBINING STEM, MUSICAL SYMBOL COMBINING FLAG-1	# 
 
+24EA ;	1F10D ;	MA	#* ( ⓪ → 🄍 ) CIRCLED DIGIT ZERO → CIRCLED ZERO WITH SLASH	# 
+
+21BA ;	1F10E ;	MA	#* ( ↺ → 🄎 ) ANTICLOCKWISE OPEN CIRCLE ARROW → CIRCLED ANTICLOCKWISE ARROW	# 
+
 02D9 ;	0971 ;	MA	#* ( ˙ → ॱ ) DOT ABOVE → DEVANAGARI SIGN HIGH SPACING DOT	# 
 0D4E ;	0971 ;	MA	# ( ൎ → ॱ ) MALAYALAM LETTER DOT REPH → DEVANAGARI SIGN HIGH SPACING DOT	# →˙→
 
@@ -1390,6 +1394,8 @@ D7BC ;	30FC 1169 ;	MA	# ( ힼ → ーᅩ ) HANGUL JUNGSEONG EU-O → KATAKANA-HI
 
 1197 ;	30FC 4E28 116E ;	MA	# ( ᆗ → ー丨ᅮ ) HANGUL JUNGSEONG YI-U → KATAKANA-HIRAGANA PROLONGED SOUND MARK, CJK UNIFIED IDEOGRAPH-4E28, HANGUL JUNGSEONG U	# →ᅳᅵᅮ→
 
+1F10F ;	0024 20E0 ;	MA	#* ( 🄏 → $⃠ ) CIRCLED DOLLAR SIGN WITH OVERLAID BACKSLASH → DOLLAR SIGN, COMBINING ENCLOSING CIRCLE BACKSLASH	# 
+
 20A4 ;	00A3 ;	MA	#* ( ₤ → £ ) LIRA SIGN → POUND SIGN	# 
 
 3012 ;	20B8 ;	MA	#* ( 〒 → ₸ ) POSTAL MARK → TENGE SIGN	# 
@@ -1416,6 +1422,7 @@ A9C6 ;	A9D0 ;	MA	#* ( ꧆ → ꧐ ) JAVANESE PADA WINDU → JAVANESE DIGIT ZERO
 1D7E4 ;	0032 ;	MA	# ( 𝟤 → 2 ) MATHEMATICAL SANS-SERIF DIGIT TWO → DIGIT TWO	# 
 1D7EE ;	0032 ;	MA	# ( 𝟮 → 2 ) MATHEMATICAL SANS-SERIF BOLD DIGIT TWO → DIGIT TWO	# 
 1D7F8 ;	0032 ;	MA	# ( 𝟸 → 2 ) MATHEMATICAL MONOSPACE DIGIT TWO → DIGIT TWO	# 
+1FBF2 ;	0032 ;	MA	# ( 🯲 → 2 ) SEGMENTED DIGIT TWO → DIGIT TWO	# 
 A75A ;	0032 ;	MA	# ( Ꝛ → 2 ) LATIN CAPITAL LETTER R ROTUNDA → DIGIT TWO	# 
 01A7 ;	0032 ;	MA	# ( Ƨ → 2 ) LATIN CAPITAL LETTER TONE TWO → DIGIT TWO	# 
 03E8 ;	0032 ;	MA	# ( Ϩ → 2 ) COPTIC CAPITAL LETTER HORI → DIGIT TWO	# →Ƨ→
@@ -1488,6 +1495,7 @@ A9CF ;	0662 ;	MA	# ( ꧏ → ‎٢‎ ) JAVANESE PANGRANGKEP → ARABIC-INDIC DI
 1D7E5 ;	0033 ;	MA	# ( 𝟥 → 3 ) MATHEMATICAL SANS-SERIF DIGIT THREE → DIGIT THREE	# 
 1D7EF ;	0033 ;	MA	# ( 𝟯 → 3 ) MATHEMATICAL SANS-SERIF BOLD DIGIT THREE → DIGIT THREE	# 
 1D7F9 ;	0033 ;	MA	# ( 𝟹 → 3 ) MATHEMATICAL MONOSPACE DIGIT THREE → DIGIT THREE	# 
+1FBF3 ;	0033 ;	MA	# ( 🯳 → 3 ) SEGMENTED DIGIT THREE → DIGIT THREE	# 
 A7AB ;	0033 ;	MA	# ( Ɜ → 3 ) LATIN CAPITAL LETTER REVERSED OPEN E → DIGIT THREE	# 
 021C ;	0033 ;	MA	# ( Ȝ → 3 ) LATIN CAPITAL LETTER YOGH → DIGIT THREE	# →Ʒ→
 01B7 ;	0033 ;	MA	# ( Ʒ → 3 ) LATIN CAPITAL LETTER EZH → DIGIT THREE	# 
@@ -1526,6 +1534,7 @@ A76A ;	0033 ;	MA	# ( Ꝫ → 3 ) LATIN CAPITAL LETTER ET → DIGIT THREE	#
 1D7E6 ;	0034 ;	MA	# ( 𝟦 → 4 ) MATHEMATICAL SANS-SERIF DIGIT FOUR → DIGIT FOUR	# 
 1D7F0 ;	0034 ;	MA	# ( 𝟰 → 4 ) MATHEMATICAL SANS-SERIF BOLD DIGIT FOUR → DIGIT FOUR	# 
 1D7FA ;	0034 ;	MA	# ( 𝟺 → 4 ) MATHEMATICAL MONOSPACE DIGIT FOUR → DIGIT FOUR	# 
+1FBF4 ;	0034 ;	MA	# ( 🯴 → 4 ) SEGMENTED DIGIT FOUR → DIGIT FOUR	# 
 13CE ;	0034 ;	MA	# ( Ꮞ → 4 ) CHEROKEE LETTER SE → DIGIT FOUR	# 
 118AF ;	0034 ;	MA	# ( 𑢯 → 4 ) WARANG CITI CAPITAL LETTER UC → DIGIT FOUR	# 
 
@@ -1552,6 +1561,7 @@ A76A ;	0033 ;	MA	# ( Ꝫ → 3 ) LATIN CAPITAL LETTER ET → DIGIT THREE	#
 1D7E7 ;	0035 ;	MA	# ( 𝟧 → 5 ) MATHEMATICAL SANS-SERIF DIGIT FIVE → DIGIT FIVE	# 
 1D7F1 ;	0035 ;	MA	# ( 𝟱 → 5 ) MATHEMATICAL SANS-SERIF BOLD DIGIT FIVE → DIGIT FIVE	# 
 1D7FB ;	0035 ;	MA	# ( 𝟻 → 5 ) MATHEMATICAL MONOSPACE DIGIT FIVE → DIGIT FIVE	# 
+1FBF5 ;	0035 ;	MA	# ( 🯵 → 5 ) SEGMENTED DIGIT FIVE → DIGIT FIVE	# 
 01BC ;	0035 ;	MA	# ( Ƽ → 5 ) LATIN CAPITAL LETTER TONE FIVE → DIGIT FIVE	# 
 118BB ;	0035 ;	MA	# ( 𑢻 → 5 ) WARANG CITI CAPITAL LETTER HORR → DIGIT FIVE	# 
 
@@ -1572,6 +1582,7 @@ A76A ;	0033 ;	MA	# ( Ꝫ → 3 ) LATIN CAPITAL LETTER ET → DIGIT THREE	#
 1D7E8 ;	0036 ;	MA	# ( 𝟨 → 6 ) MATHEMATICAL SANS-SERIF DIGIT SIX → DIGIT SIX	# 
 1D7F2 ;	0036 ;	MA	# ( 𝟲 → 6 ) MATHEMATICAL SANS-SERIF BOLD DIGIT SIX → DIGIT SIX	# 
 1D7FC ;	0036 ;	MA	# ( 𝟼 → 6 ) MATHEMATICAL MONOSPACE DIGIT SIX → DIGIT SIX	# 
+1FBF6 ;	0036 ;	MA	# ( 🯶 → 6 ) SEGMENTED DIGIT SIX → DIGIT SIX	# 
 2CD2 ;	0036 ;	MA	# ( Ⳓ → 6 ) COPTIC CAPITAL LETTER OLD COPTIC HEI → DIGIT SIX	# 
 0431 ;	0036 ;	MA	# ( б → 6 ) CYRILLIC SMALL LETTER BE → DIGIT SIX	# 
 13EE ;	0036 ;	MA	# ( Ꮾ → 6 ) CHEROKEE LETTER WV → DIGIT SIX	# 
@@ -1599,6 +1610,7 @@ A76A ;	0033 ;	MA	# ( Ꝫ → 3 ) LATIN CAPITAL LETTER ET → DIGIT THREE	#
 1D7E9 ;	0037 ;	MA	# ( 𝟩 → 7 ) MATHEMATICAL SANS-SERIF DIGIT SEVEN → DIGIT SEVEN	# 
 1D7F3 ;	0037 ;	MA	# ( 𝟳 → 7 ) MATHEMATICAL SANS-SERIF BOLD DIGIT SEVEN → DIGIT SEVEN	# 
 1D7FD ;	0037 ;	MA	# ( 𝟽 → 7 ) MATHEMATICAL MONOSPACE DIGIT SEVEN → DIGIT SEVEN	# 
+1FBF7 ;	0037 ;	MA	# ( 🯷 → 7 ) SEGMENTED DIGIT SEVEN → DIGIT SEVEN	# 
 104D2 ;	0037 ;	MA	# ( 𐓒 → 7 ) OSAGE CAPITAL LETTER ZA → DIGIT SEVEN	# 
 118C6 ;	0037 ;	MA	# ( 𑣆 → 7 ) WARANG CITI SMALL LETTER II → DIGIT SEVEN	# 
 
@@ -1623,6 +1635,7 @@ A76A ;	0033 ;	MA	# ( Ꝫ → 3 ) LATIN CAPITAL LETTER ET → DIGIT THREE	#
 1D7EA ;	0038 ;	MA	# ( 𝟪 → 8 ) MATHEMATICAL SANS-SERIF DIGIT EIGHT → DIGIT EIGHT	# 
 1D7F4 ;	0038 ;	MA	# ( 𝟴 → 8 ) MATHEMATICAL SANS-SERIF BOLD DIGIT EIGHT → DIGIT EIGHT	# 
 1D7FE ;	0038 ;	MA	# ( 𝟾 → 8 ) MATHEMATICAL MONOSPACE DIGIT EIGHT → DIGIT EIGHT	# 
+1FBF8 ;	0038 ;	MA	# ( 🯸 → 8 ) SEGMENTED DIGIT EIGHT → DIGIT EIGHT	# 
 0223 ;	0038 ;	MA	# ( ȣ → 8 ) LATIN SMALL LETTER OU → DIGIT EIGHT	# 
 0222 ;	0038 ;	MA	# ( Ȣ → 8 ) LATIN CAPITAL LETTER OU → DIGIT EIGHT	# 
 1031A ;	0038 ;	MA	# ( 𐌚 → 8 ) OLD ITALIC LETTER EF → DIGIT EIGHT	# 
@@ -1650,6 +1663,7 @@ A76A ;	0033 ;	MA	# ( Ꝫ → 3 ) LATIN CAPITAL LETTER ET → DIGIT THREE	#
 1D7EB ;	0039 ;	MA	# ( 𝟫 → 9 ) MATHEMATICAL SANS-SERIF DIGIT NINE → DIGIT NINE	# 
 1D7F5 ;	0039 ;	MA	# ( 𝟵 → 9 ) MATHEMATICAL SANS-SERIF BOLD DIGIT NINE → DIGIT NINE	# 
 1D7FF ;	0039 ;	MA	# ( 𝟿 → 9 ) MATHEMATICAL MONOSPACE DIGIT NINE → DIGIT NINE	# 
+1FBF9 ;	0039 ;	MA	# ( 🯹 → 9 ) SEGMENTED DIGIT NINE → DIGIT NINE	# 
 A76E ;	0039 ;	MA	# ( Ꝯ → 9 ) LATIN CAPITAL LETTER CON → DIGIT NINE	# 
 2CCA ;	0039 ;	MA	# ( Ⳋ → 9 ) COPTIC CAPITAL LETTER DIALECT-P HORI → DIGIT NINE	# 
 118CC ;	0039 ;	MA	# ( 𑣌 → 9 ) WARANG CITI SMALL LETTER KO → DIGIT NINE	# 
@@ -1912,6 +1926,8 @@ A4DA ;	0043 ;	MA	# ( ꓚ → C ) LISU LETTER CA → LATIN CAPITAL LETTER C	#
 
 20A1 ;	0043 20EB ;	MA	#* ( ₡ → C⃫ ) COLON SIGN → LATIN CAPITAL LETTER C, COMBINING LONG DOUBLE SOLIDUS OVERLAY	# 
 
+1F16E ;	0043 20E0 ;	MA	#* ( 🅮 → C⃠ ) CIRCLED C WITH OVERLAID BACKSLASH → LATIN CAPITAL LETTER C, COMBINING ENCLOSING CIRCLE BACKSLASH	# 
+
 00E7 ;	0063 0326 ;	MA	# ( ç → c̦ ) LATIN SMALL LETTER C WITH CEDILLA → LATIN SMALL LETTER C, COMBINING COMMA BELOW	# →ҫ→→с̡→
 04AB ;	0063 0326 ;	MA	# ( ҫ → c̦ ) CYRILLIC SMALL LETTER ES WITH DESCENDER → LATIN SMALL LETTER C, COMBINING COMMA BELOW	# →с̡→
 
@@ -1924,6 +1940,8 @@ A4DA ;	0043 ;	MA	# ( ꓚ → C ) LISU LETTER CA → LATIN CAPITAL LETTER C	#
 
 2106 ;	0063 002F 0075 ;	MA	#* ( ℆ → c/u ) CADA UNA → LATIN SMALL LETTER C, SOLIDUS, LATIN SMALL LETTER U	# 
 
+1F16D ;	33C4 0009 20DD ;	MA	#* ( 🅭 →  ) CIRCLED CC → SQUARE CC, <CHARACTER TABULATION>, COMBINING ENCLOSING CIRCLE	# 
+
 22F4 ;	A793 ;	MA	#* ( ⋴ → ꞓ ) SMALL ELEMENT OF WITH VERTICAL BAR AT END OF HORIZONTAL STROKE → LATIN SMALL LETTER C WITH BAR	# →ɛ→→є→
 025B ;	A793 ;	MA	# ( ɛ → ꞓ ) LATIN SMALL LETTER OPEN E → LATIN SMALL LETTER C WITH BAR	# →є→
 03B5 ;	A793 ;	MA	# ( ε → ꞓ ) GREEK SMALL LETTER EPSILON → LATIN SMALL LETTER C WITH BAR	# →є→
@@ -2353,7 +2371,7 @@ A6B1 ;	2C75 ;	MA	# ( ꚱ → Ⱶ ) BAMUM LETTER NDAA → LATIN CAPITAL LETTER HA
 A795 ;	A727 ;	MA	# ( ꞕ → ꜧ ) LATIN SMALL LETTER H WITH PALATAL HOOK → LATIN SMALL LETTER HENG	# 
 
 02DB ;	0069 ;	MA	#* ( ˛ → i ) OGONEK → LATIN SMALL LETTER I	# →ͺ→→ι→→ι→
-2373 ;	0069 ;	MA	#* ( ⍳ → i ) APL FUNCTIONAL SYMBOL IOTA → LATIN SMALL LETTER I	# →ι→
+2373 ;	0069 ;	MA	#* ( ⍳ → i ) APL FUNCTIONAL SYMBOL IOTA → LATIN SMALL LETTER I	# →ɩ→
 FF49 ;	0069 ;	MA	# ( ｉ → i ) FULLWIDTH LATIN SMALL LETTER I → LATIN SMALL LETTER I	# →і→
 2170 ;	0069 ;	MA	# ( ⅰ → i ) SMALL ROMAN NUMERAL ONE → LATIN SMALL LETTER I	# 
 2139 ;	0069 ;	MA	# ( ℹ → i ) INFORMATION SOURCE → LATIN SMALL LETTER I	# 
@@ -2530,6 +2548,7 @@ FFE8 ;	006C ;	MA	#* ( ￨ → l ) HALFWIDTH FORMS LIGHT VERTICAL → LATIN SMALL
 1D7E3 ;	006C ;	MA	# ( 𝟣 → l ) MATHEMATICAL SANS-SERIF DIGIT ONE → LATIN SMALL LETTER L	# →1→
 1D7ED ;	006C ;	MA	# ( 𝟭 → l ) MATHEMATICAL SANS-SERIF BOLD DIGIT ONE → LATIN SMALL LETTER L	# →1→
 1D7F7 ;	006C ;	MA	# ( 𝟷 → l ) MATHEMATICAL MONOSPACE DIGIT ONE → LATIN SMALL LETTER L	# →1→
+1FBF1 ;	006C ;	MA	# ( 🯱 → l ) SEGMENTED DIGIT ONE → LATIN SMALL LETTER L	# →1→
 0049 ;	006C ;	MA	# ( I → l ) LATIN CAPITAL LETTER I → LATIN SMALL LETTER L	# 
 FF29 ;	006C ;	MA	# ( Ｉ → l ) FULLWIDTH LATIN CAPITAL LETTER I → LATIN SMALL LETTER L	# →Ӏ→
 2160 ;	006C ;	MA	# ( Ⅰ → l ) ROMAN NUMERAL ONE → LATIN SMALL LETTER L	# →Ӏ→
@@ -2957,6 +2976,7 @@ FBA6 ;	006F ;	MA	# ( ‎ﮦ‎ → o ) ARABIC LETTER HEH GOAL ISOLATED FORM →
 1D7E2 ;	004F ;	MA	# ( 𝟢 → O ) MATHEMATICAL SANS-SERIF DIGIT ZERO → LATIN CAPITAL LETTER O	# →0→
 1D7EC ;	004F ;	MA	# ( 𝟬 → O ) MATHEMATICAL SANS-SERIF BOLD DIGIT ZERO → LATIN CAPITAL LETTER O	# →0→
 1D7F6 ;	004F ;	MA	# ( 𝟶 → O ) MATHEMATICAL MONOSPACE DIGIT ZERO → LATIN CAPITAL LETTER O	# →0→
+1FBF0 ;	004F ;	MA	# ( 🯰 → O ) SEGMENTED DIGIT ZERO → LATIN CAPITAL LETTER O	# →0→
 FF2F ;	004F ;	MA	# ( Ｏ → O ) FULLWIDTH LATIN CAPITAL LETTER O → LATIN CAPITAL LETTER O	# →О→
 1D40E ;	004F ;	MA	# ( 𝐎 → O ) MATHEMATICAL BOLD CAPITAL O → LATIN CAPITAL LETTER O	# 
 1D442 ;	004F ;	MA	# ( 𝑂 → O ) MATHEMATICAL ITALIC CAPITAL O → LATIN CAPITAL LETTER O	# 
@@ -8008,8 +8028,6 @@ FA92 ;	6717 ;	MA	# ( 朗 → 朗 ) CJK COMPATIBILITY IDEOGRAPH-FA92 → CJK UNIF
 FA93 ;	671B ;	MA	# ( 望 → 望 ) CJK COMPATIBILITY IDEOGRAPH-FA93 → CJK UNIFIED IDEOGRAPH-671B	# 
 2F8D9 ;	671B ;	MA	# ( 望 → 望 ) CJK COMPATIBILITY IDEOGRAPH-2F8D9 → CJK UNIFIED IDEOGRAPH-671B	# 
 
-2F8DA ;	6721 ;	MA	# ( 朡 → 朡 ) CJK COMPATIBILITY IDEOGRAPH-2F8DA → CJK UNIFIED IDEOGRAPH-6721	# 
-
 5E50 ;	3B3A ;	MA	# ( 幐 → 㬺 ) CJK UNIFIED IDEOGRAPH-5E50 → CJK UNIFIED IDEOGRAPH-3B3A	# 
 
 4420 ;	3B3B ;	MA	# ( 䐠 → 㬻 ) CJK UNIFIED IDEOGRAPH-4420 → CJK UNIFIED IDEOGRAPH-3B3B	# 
@@ -8815,6 +8833,8 @@ F953 ;	808B ;	MA	# ( 肋 → 肋 ) CJK COMPATIBILITY IDEOGRAPH-F953 → CJK UNIF
 
 2F984 ;	440B ;	MA	# ( 䐋 → 䐋 ) CJK COMPATIBILITY IDEOGRAPH-2F984 → CJK UNIFIED IDEOGRAPH-440B	# 
 
+2F8DA ;	6721 ;	MA	# ( 朡 → 朡 ) CJK COMPATIBILITY IDEOGRAPH-2F8DA → CJK UNIFIED IDEOGRAPH-6721	# 
+
 2F987 ;	267A7 ;	MA	# ( 𦞧 → 𦞧 ) CJK COMPATIBILITY IDEOGRAPH-2F987 → CJK UNIFIED IDEOGRAPH-267A7	# 
 
 2F988 ;	267B5 ;	MA	# ( 𦞵 → 𦞵 ) CJK COMPATIBILITY IDEOGRAPH-2F988 → CJK UNIFIED IDEOGRAPH-267B5	# 
@@ -9614,5 +9634,5 @@ FACE ;	9F9C ;	MA	# ( 龜 → 龜 ) CJK COMPATIBILITY IDEOGRAPH-FACE → CJK UNIF
 
 2FD5 ;	9FA0 ;	MA	#* ( ⿕ → 龠 ) KANGXI RADICAL FLUTE → CJK UNIFIED IDEOGRAPH-9FA0	# 
 
-# total: 6296
+# total: 6311
 
diff --git a/setup.py b/setup.py
@@ -5,7 +5,7 @@
 
 setuptools.setup(
     name="confusables",
-    version="1.1.1",
+    version="1.2.0",
     author="Nathan Woodger",
     author_email="[email protected]",
     description="A python package providing functionality for matching words that can be confused for eachother, but contain different characters",