fixed missing LATIN LETTER SMALL pairings in latest unicode confusables.txt

Author: codebox

README.md

@@ -8,7 +8,7 @@ Include the Homoglyph library in your project by downloading it from Maven Centr
 <dependency>
     <groupId>net.codebox</groupId>
     <artifactId>homoglyph</artifactId>
-    <version>1.0.2</version>
+    <version>1.0.3</version>
 </dependency>
 ```
 
@@ -44,7 +44,7 @@ Homoglyphs are characters with different meanings, that look similar/identical t
 
 Homoglyphs within a single alphabet tend to be rare for obvious reasons. These days, however, the internet runs on Unicode which means that it is possible to mix the letters from many [different languages](http://www.unicode.org/cldr/charts/latest/supplemental/languages_and_scripts.html) together in one place, massively increasing the number of homoglyphs.
 
-For example, each of the 27 characters shown below (all rendered using the same font) are different, with their own unique Unicode codepoint values, but they all look more-or-less like the capital letter 'A':
+For example, each of the characters shown below (all rendered using the same font) are different, with their own unique Unicode codepoint values, but they all look more-or-less like the capital letter 'A':
 
 A Α А Ꭺ ᗅ ᴀ ꓮ Ａ 𐊠 𝐀 𝐴 𝑨 𝒜 𝓐 𝔄 𝔸 𝕬 𝖠 𝗔 𝘈 𝘼 𝙰 𝚨 𝛢 𝜜 𝝖 𝞐
 

build.gradle

@@ -1,5 +1,5 @@
 group = "net.codebox"
-version = "1.0.2"
+version = "1.0.3"
 
 apply plugin: 'java'
 apply plugin: 'idea'

generator/source_data/confusables_extras.txt

@@ -60,4 +60,10 @@ ff5d ; 7d ; MA	# ( } → ｝ )
 029c ; 48 ; MA	# ( H → ʜ )
 029f ; 4c ; MA	# ( L → ʟ )
 0274 ; 4e ; MA	# ( N → ɴ )
-0280 ; 52 ; MA	# ( R → ʀ )
+0280 ; 52 ; MA	# ( R → ʀ )
+1D00 ; 41 ; MA	# ( A → ᴀ )
+1D05 ; 44 ; MA	# ( D → ᴅ )
+1D07 ; 45 ; MA	# ( E → ᴇ )
+1D0A ; 4A ; MA	# ( J → ᴊ )
+1D18 ; 50 ; MA	# ( P → ᴘ )
+

javascript/src/homoglyph.js

@@ -38,20 +38,20 @@
 3e,2c3,1433,203a,276f,ff1e,16f3f,1d237
 3f,241,294,97d,13ae,a6eb,ff1f
 40,ff20
-41,391,410,13aa,15c5,a4ee,ff21,102a0,16f40,1d400,1d434,1d468,1d49c,1d4d0,1d504,1d538,1d56c,1d5a0,1d5d4,1d608,1d63c,1d670,1d6a8,1d6e2,1d71c,1d756,1d790
+41,391,410,13aa,15c5,1d00,a4ee,ab7a,ff21,102a0,16f40,1d400,1d434,1d468,1d49c,1d4d0,1d504,1d538,1d56c,1d5a0,1d5d4,1d608,1d63c,1d670,1d6a8,1d6e2,1d71c,1d756,1d790
 42,299,392,412,432,13f4,13fc,15f7,16d2,212c,a4d0,a7b4,ff22,10282,102a1,10301,1d401,1d435,1d469,1d4d1,1d505,1d539,1d56d,1d5a1,1d5d5,1d609,1d63d,1d671,1d6a9,1d6e3,1d71d,1d757,1d791
 43,3f9,421,13df,2102,212d,216d,2ca4,a4da,ff23,102a2,10302,10415,1051c,118e9,118f2,1d402,1d436,1d46a,1d49e,1d4d2,1d56e,1d5a2,1d5d6,1d60a,1d63e,1d672,1f74c
-44,13a0,15de,15ea,2145,216e,a4d3,ff24,1d403,1d437,1d46b,1d49f,1d4d3,1d507,1d53b,1d56f,1d5a3,1d5d7,1d60b,1d63f,1d673
-45,395,415,13ac,2130,22ff,2d39,a4f0,ff25,10286,118a6,118ae,1d404,1d438,1d46c,1d4d4,1d508,1d53c,1d570,1d5a4,1d5d8,1d60c,1d640,1d674,1d6ac,1d6e6,1d720,1d75a,1d794
+44,13a0,15de,15ea,1d05,2145,216e,a4d3,ab70,ff24,1d403,1d437,1d46b,1d49f,1d4d3,1d507,1d53b,1d56f,1d5a3,1d5d7,1d60b,1d63f,1d673
+45,395,415,13ac,1d07,2130,22ff,2d39,a4f0,ab7c,ff25,10286,118a6,118ae,1d404,1d438,1d46c,1d4d4,1d508,1d53c,1d570,1d5a4,1d5d8,1d60c,1d640,1d674,1d6ac,1d6e6,1d720,1d75a,1d794
 46,3dc,15b4,2131,a4dd,a798,ff26,10287,102a5,10525,118a2,118c2,1d213,1d405,1d439,1d46d,1d4d5,1d509,1d53d,1d571,1d5a5,1d5d9,1d60d,1d641,1d675,1d7ca
 47,262,50c,50d,13c0,13f3,13fb,a4d6,ab90,ff27,1d406,1d43a,1d46e,1d4a2,1d4d6,1d50a,1d53e,1d572,1d5a6,1d5da,1d60e,1d642,1d676
 48,29c,397,41d,43d,13bb,157c,210b,210c,210d,2c8e,a4e7,ab8b,ff28,102cf,1d407,1d43b,1d46f,1d4d7,1d573,1d5a7,1d5db,1d60f,1d643,1d677,1d6ae,1d6e8,1d722,1d75c,1d796
-4a,37f,408,13ab,148d,a4d9,a7b2,ff2a,1d409,1d43d,1d471,1d4a5,1d4d9,1d50d,1d541,1d575,1d5a9,1d5dd,1d611,1d645,1d679
+4a,37f,408,13ab,148d,1d0a,a4d9,a7b2,ab7b,ff2a,1d409,1d43d,1d471,1d4a5,1d4d9,1d50d,1d541,1d575,1d5a9,1d5dd,1d611,1d645,1d679
 4b,39a,41a,13e6,16d5,212a,2c94,a4d7,ff2b,10518,1d40a,1d43e,1d472,1d4a6,1d4da,1d50e,1d542,1d576,1d5aa,1d5de,1d612,1d646,1d67a,1d6b1,1d6eb,1d725,1d75f,1d799
 4c,29f,13de,14aa,2112,216c,2cd0,2cd1,a4e1,abae,ff2c,1041b,10443,10526,118a3,118b2,16f16,1d22a,1d40b,1d43f,1d473,1d4db,1d50f,1d543,1d577,1d5ab,1d5df,1d613,1d647,1d67b
 4d,39c,3fa,41c,13b7,15f0,16d6,2133,216f,2c98,a4df,ff2d,102b0,10311,1d40c,1d440,1d474,1d4dc,1d510,1d544,1d578,1d5ac,1d5e0,1d614,1d648,1d67c,1d6b3,1d6ed,1d727,1d761,1d79b
 4e,274,39d,2115,2c9a,a4e0,ff2e,10513,1d40d,1d441,1d475,1d4a9,1d4dd,1d511,1d579,1d5ad,1d5e1,1d615,1d649,1d67d,1d6b4,1d6ee,1d728,1d762,1d79c
-50,3a1,420,13e2,146d,2119,2ca2,a4d1,ff30,10295,1d40f,1d443,1d477,1d4ab,1d4df,1d513,1d57b,1d5af,1d5e3,1d617,1d64b,1d67f,1d6b8,1d6f2,1d72c,1d766,1d7a0
+50,3a1,420,13e2,146d,1d18,1d29,2119,2ca2,a4d1,abb2,ff30,10295,1d40f,1d443,1d477,1d4ab,1d4df,1d513,1d57b,1d5af,1d5e3,1d617,1d64b,1d67f,1d6b8,1d6f2,1d72c,1d766,1d7a0
 51,211a,2d55,ff31,1d410,1d444,1d478,1d4ac,1d4e0,1d514,1d57c,1d5b0,1d5e4,1d618,1d64c,1d680
 52,1a6,280,13a1,13d2,1587,16b1,211b,211c,211d,a4e3,ab71,aba2,ff32,104b4,16f35,1d216,1d411,1d445,1d479,1d4e1,1d57d,1d5b1,1d5e5,1d619,1d64d,1d681
 53,405,54f,13d5,13da,a4e2,ff33,10296,10420,16f3a,1d412,1d446,1d47a,1d4ae,1d4e2,1d516,1d54a,1d57e,1d5b2,1d5e6,1d61a,1d64e,1d682
@@ -518,11 +518,6 @@ fd6,534d
 1b11,1b53
 1b28,1b58
 1b50,1b5c
-1d00,ab7a
-1d05,ab70
-1d07,ab7c
-1d0a,ab7b
-1d18,1d29,abb2
 1d34,1d78
 1d4b,1d9f
 1d4d,1da2

javascript/tests/js/tests/DataTests.js

@@ -37,20 +37,20 @@ $＄
 >˃ᐳ›❯＞𖼿𝈷
 ?ɁʔॽᎮꛫ？
 @＠
-AΑАᎪᗅꓮＡ𐊠𖽀𝐀𝐴𝑨𝒜𝓐𝔄𝔸𝕬𝖠𝗔𝘈𝘼𝙰𝚨𝛢𝜜𝝖𝞐
+AΑАᎪᗅᴀꓮꭺＡ𐊠𖽀𝐀𝐴𝑨𝒜𝓐𝔄𝔸𝕬𝖠𝗔𝘈𝘼𝙰𝚨𝛢𝜜𝝖𝞐
 BʙΒВвᏴᏼᗷᛒℬꓐꞴＢ𐊂𐊡𐌁𝐁𝐵𝑩𝓑𝔅𝔹𝕭𝖡𝗕𝘉𝘽𝙱𝚩𝛣𝜝𝝗𝞑
 CϹСᏟℂℭⅭⲤꓚＣ𐊢𐌂𐐕𐔜𑣩𑣲𝐂𝐶𝑪𝒞𝓒𝕮𝖢𝗖𝘊𝘾𝙲🝌
-DᎠᗞᗪⅅⅮꓓＤ𝐃𝐷𝑫𝒟𝓓𝔇𝔻𝕯𝖣𝗗𝘋𝘿𝙳
-EΕЕᎬℰ⋿ⴹꓰＥ𐊆𑢦𑢮𝐄𝐸𝑬𝓔𝔈𝔼𝕰𝖤𝗘𝘌𝙀𝙴𝚬𝛦𝜠𝝚𝞔
+DᎠᗞᗪᴅⅅⅮꓓꭰＤ𝐃𝐷𝑫𝒟𝓓𝔇𝔻𝕯𝖣𝗗𝘋𝘿𝙳
+EΕЕᎬᴇℰ⋿ⴹꓰꭼＥ𐊆𑢦𑢮𝐄𝐸𝑬𝓔𝔈𝔼𝕰𝖤𝗘𝘌𝙀𝙴𝚬𝛦𝜠𝝚𝞔
 FϜᖴℱꓝꞘＦ𐊇𐊥𐔥𑢢𑣂𝈓𝐅𝐹𝑭𝓕𝔉𝔽𝕱𝖥𝗙𝘍𝙁𝙵𝟊
 GɢԌԍᏀᏳᏻꓖꮐＧ𝐆𝐺𝑮𝒢𝓖𝔊𝔾𝕲𝖦𝗚𝘎𝙂𝙶
 HʜΗНнᎻᕼℋℌℍⲎꓧꮋＨ𐋏𝐇𝐻𝑯𝓗𝕳𝖧𝗛𝘏𝙃𝙷𝚮𝛨𝜢𝝜𝞖
-JͿЈᎫᒍꓙꞲＪ𝐉𝐽𝑱𝒥𝓙𝔍𝕁𝕵𝖩𝗝𝘑𝙅𝙹
+JͿЈᎫᒍᴊꓙꞲꭻＪ𝐉𝐽𝑱𝒥𝓙𝔍𝕁𝕵𝖩𝗝𝘑𝙅𝙹
 KΚКᏦᛕKⲔꓗＫ𐔘𝐊𝐾𝑲𝒦𝓚𝔎𝕂𝕶𝖪𝗞𝘒𝙆𝙺𝚱𝛫𝜥𝝟𝞙
 LʟᏞᒪℒⅬⳐⳑꓡꮮＬ𐐛𐑃𐔦𑢣𑢲𖼖𝈪𝐋𝐿𝑳𝓛𝔏𝕃𝕷𝖫𝗟𝘓𝙇𝙻
 MΜϺМᎷᗰᛖℳⅯⲘꓟＭ𐊰𐌑𝐌𝑀𝑴𝓜𝔐𝕄𝕸𝖬𝗠𝘔𝙈𝙼𝚳𝛭𝜧𝝡𝞛
 NɴΝℕⲚꓠＮ𐔓𝐍𝑁𝑵𝒩𝓝𝔑𝕹𝖭𝗡𝘕𝙉𝙽𝚴𝛮𝜨𝝢𝞜
-PΡРᏢᑭℙⲢꓑＰ𐊕𝐏𝑃𝑷𝒫𝓟𝔓𝕻𝖯𝗣𝘗𝙋𝙿𝚸𝛲𝜬𝝦𝞠
+PΡРᏢᑭᴘᴩℙⲢꓑꮲＰ𐊕𝐏𝑃𝑷𝒫𝓟𝔓𝕻𝖯𝗣𝘗𝙋𝙿𝚸𝛲𝜬𝝦𝞠
 QℚⵕＱ𝐐𝑄𝑸𝒬𝓠𝔔𝕼𝖰𝗤𝘘𝙌𝚀
 RƦʀᎡᏒᖇᚱℛℜℝꓣꭱꮢＲ𐒴𖼵𝈖𝐑𝑅𝑹𝓡𝕽𝖱𝗥𝘙𝙍𝚁
 SЅՏᏕᏚꓢＳ𐊖𐐠𖼺𝐒𝑆𝑺𝒮𝓢𝔖𝕊𝕾𝖲𝗦𝘚𝙎𝚂
@@ -517,11 +517,6 @@ zᴢꮓｚ𑣄𝐳𝑧𝒛𝓏𝔃𝔷𝕫𝖟𝗓𝘇𝘻𝙯𝚣
 ᬑ᭓
 ᬨ᭘
 ᭐᭜
-ᴀꭺ
-ᴅꭰ
-ᴇꭼ
-ᴊꭻ
-ᴘᴩꮲ
 ᴴᵸ
 ᵋᶟ
 ᵍᶢ

node/index.js

@@ -6,17 +6,17 @@
 import java.io.IOException;
 import java.util.Arrays;
 import java.util.List;
-import java.util.Set;
 
 import static org.junit.Assert.assertEquals;
 
+import net.codebox.homoglyph.Homoglyph.SearchResult;
+
 public class HomoglyphDataTest {
     private Homoglyph homoglyph;
 
     @Before
     public void setup() throws IOException {
-        List<Set<Integer>> charCodes = Homoglyph.parseCharCodesFile("raw_data/char_codes.txt");
-        homoglyph = new Homoglyph(charCodes);
+        homoglyph = HomoglyphBuilder.build();
     }
 
     @Test

raw_data/char_codes.txt

@@ -6,6 +6,8 @@
 import java.io.IOException;
 import java.util.*;
 
+import net.codebox.homoglyph.Homoglyph.SearchResult;
+
 import static org.junit.Assert.*;
 
 public class HomoglyphLogicTest {