Last active
February 9, 2022 11:26
-
-
Save jiyuujin/8604ac2d26cc0582dd5d060be9a23f60 to your computer and use it in GitHub Desktop.
機種依存文字を抽出する
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
export const targetText = "①②③④⑤⑥⑦⑧⑨⑩⑪⑫⑬⑭⑯⑰⑱⑲⑳ⅠⅡⅢⅣⅤⅥⅦⅧⅨⅩ㍉㌔㌢㍍㌘㌧㌃㌶㍑㍗㌍㌦㌣㌫㍊㌻㎜㎝㎞㎎㎏㏄㎡㍻〝〟№㏍℡㊤㊥㊦㊧㊨㈱㈲㈹㍾㍽㍼∮∟⊿纊褜鍈銈蓜俉炻昱棈鋹曻彅丨仡仼伀伃伹佖侒侊侚侔俍偀倢俿倞偆偰偂傔僴僘兊兤冝冾凬刕劜劦勀勛匀匇匤卲厓厲叝﨎咜咊咩哿喆坙坥垬埈埇﨏增墲夋奓奛奝奣妤妺孖寀甯寘寬尞岦岺峵崧嵓﨑嵂嵭嶸嶹巐弡弴彧德忞恝悅悊惞惕愠惲愑愷愰憘戓抦揵摠撝擎敎昀昕昻昉昮昞昤晥晗晙晳暙暠暲暿曺朎杦枻桒柀栁桄棏﨓楨﨔榘槢樰橫橆橳橾櫢櫤毖氿汜沆汯泚洄涇浯涖涬淏淸淲淼渹湜渧渼溿澈澵濵瀅瀇瀨炅炫焏焄煜煆煇凞燁燾犱犾猤獷玽珉珖珣珒琇珵琦琪琩琮瑢璉璟甁畯皂皜皞皛皦睆劯砡硎硤礰禔禛竑竧竫箞絈絜綷綠緖繒罇羡茁荢荿菇菶葈蒴蕓蕙蕫﨟薰蘒﨡蠇裵訒訷詹誧誾諟諶譓譿賰賴贒赶﨣軏﨤遧郞鄕鄧釚釗釞釭釮釤釥鈆鈐鈊鈺鉀鈼鉎鉙鉑鈹鉧銧鉷鉸鋧鋗鋙鋐﨧鋕鋠鋓錥錡鋻﨨錞鋿錝錂鍰鍗鎤鏆鏞鏸鐱鑅鑈閒﨩隝隯霳霻靃靍靏靑靕顗顥餧馞驎髙髜魵魲鮏鮱鮻鰀鵰鵫鸙黑ⅰⅱⅲⅳⅴⅵⅶⅷⅸⅹ¬¦'"≒≡∫∑√⊥∠∵∩∪€㍵〷☯☸☬☤☡℆℅℄℁℀⁀‿‷‶‵‴‱🔣✇☣㈳㈴㈵㈶㈷㈸㈺㈻㈼㈽㈾㈿㉀㉁㉂㉃㈪㈫㈬㈭㈮㈯㈰❶❷❸❹❺❻❼❽❾❿➊➋➌➍➎➏➐➑➒➓⑴⑵⑶⑷⑸⑹⑺⑻⑼⑽⑾⑿⒀⒁⒂⒃⒄⒅⒆⒇₁₂₃₄₅₆₇₈₉¹²³⁴⁵⁶⁷⁸⁹㈠㈡㈢㈣㈤㈥㈦㈧㈨㈩㊀㊁㊂㊃㊄㊅㊆㊇㊈㊉⑮㉑㉒㉓㉔㉕㉖㉗㉘㉙㉚㉛㉜㉝㉞㉟㊱㊲㊳㊴㊵㊶㊷㊸㊹㊺㊻㊼㊽㊾㊿㋿塚朗晴猪凞礼神硺祥福靖精羽蘒諸逸隆飯飼鶴館"; | |
export const separationText = "①|②|③|④|⑤|⑥|⑦|⑧|⑨|⑩|⑪|⑫|⑬|⑭|⑯|⑰|⑱|⑲|⑳|Ⅰ|Ⅱ|Ⅲ|Ⅳ|Ⅴ|Ⅵ|Ⅶ|Ⅷ|Ⅸ|Ⅹ|㍉|㌔|㌢|㍍|㌘|㌧|㌃|㌶|㍑|㍗|㌍|㌦|㌣|㌫|㍊|㌻|㎜|㎝|㎞|㎎|㎏|㏄|㎡|㍻|〝|〟|№|㏍|℡|㊤|㊥|㊦|㊧|㊨|㈱|㈲|㈹|㍾|㍽|㍼|∮|∟|⊿|纊|褜|鍈|銈|蓜|俉|炻|昱|棈|鋹|曻|彅|丨|仡|仼|伀|伃|伹|佖|侒|侊|侚|侔|俍|偀|倢|俿|倞|偆|偰|偂|傔|僴|僘|兊|兤|冝|冾|凬|刕|劜|劦|勀|勛|匀|匇|匤|卲|厓|厲|叝|﨎|咜|咊|咩|哿|喆|坙|坥|垬|埈|埇|﨏|增|墲|夋|奓|奛|奝|奣|妤|妺|孖|寀|甯|寘|寬|尞|岦|岺|峵|崧|嵓|﨑|嵂|嵭|嶸|嶹|巐|弡|弴|彧|德|忞|恝|悅|悊|惞|惕|愠|惲|愑|愷|愰|憘|戓|抦|揵|摠|撝|擎|敎|昀|昕|昻|昉|昮|昞|昤|晥|晗|晙|晳|暙|暠|暲|暿|曺|朎|杦|枻|桒|柀|栁|桄|棏|﨓|楨|﨔|榘|槢|樰|橫|橆|橳|橾|櫢|櫤|毖|氿|汜|沆|汯|泚|洄|涇|浯|涖|涬|淏|淸|淲|淼|渹|湜|渧|渼|溿|澈|澵|濵|瀅|瀇|瀨|炅|炫|焏|焄|煜|煆|煇|凞|燁|燾|犱|犾|猤|獷|玽|珉|珖|珣|珒|琇|珵|琦|琪|琩|琮|瑢|璉|璟|甁|畯|皂|皜|皞|皛|皦|睆|劯|砡|硎|硤|礰|禔|禛|竑|竧|竫|箞|絈|絜|綷|綠|緖|繒|罇|羡|茁|荢|荿|菇|菶|葈|蒴|蕓|蕙|蕫|﨟|薰|蘒|﨡|蠇|裵|訒|訷|詹|誧|誾|諟|諶|譓|譿|賰|賴|贒|赶|﨣|軏|﨤|遧|郞|鄕|鄧|釚|釗|釞|釭|釮|釤|釥|鈆|鈐|鈊|鈺|鉀|鈼|鉎|鉙|鉑|鈹|鉧|銧|鉷|鉸|鋧|鋗|鋙|鋐|﨧|鋕|鋠|鋓|錥|錡|鋻|﨨|錞|鋿|錝|錂|鍰|鍗|鎤|鏆|鏞|鏸|鐱|鑅|鑈|閒|﨩|隝|隯|霳|霻|靃|靍|靏|靑|靕|顗|顥|餧|馞|驎|髙|髜|魵|魲|鮏|鮱|鮻|鰀|鵰|鵫|鸙|黑|ⅰ|ⅱ|ⅲ|ⅳ|ⅴ|ⅵ|ⅶ|ⅷ|ⅸ|ⅹ|¬|¦|'|"|≒|≡|∫|∑|√|⊥|∠|∵|∩|∪|€|㍵|〷|☯|☸|☬|☤|☡|℆|℅|℄|℁|℀|⁀|‿|‷|‶|‵|‴|‱|🔣|�|✇|☣|㈳|㈴|㈵|㈶|㈷|㈸|㈺|㈻|㈼|㈽|㈾|㈿|㉀|㉁|㉂|㉃|㈪|㈫|㈬|㈭|㈮|㈯|㈰|❶|❷|❸|❹|❺|❻|❼|❽|❾|❿|➊|➋|➌|➍|➎|➏|➐|➑|➒|➓|⑴|⑵|⑶|⑷|⑸|⑹|⑺|⑻|⑼|⑽|⑾|⑿|⒀|⒁|⒂|⒃|⒄|⒅|⒆|⒇|₁|₂|₃|₄|₅|₆|₇|₈|₉|¹|²|³|⁴|⁵|⁶|⁷|⁸|⁹|㈠|㈡|㈢|㈣|㈤|㈥|㈦|㈧|㈨|㈩|㊀|㊁|㊂|㊃|㊄|㊅|㊆|㊇|㊈|㊉|⑮|㉑|㉒|㉓|㉔|㉕|㉖|㉗|㉘|㉙|㉚|㉛|㉜|㉝|㉞|㉟|㊱|㊲|㊳|㊴|㊵|㊶|㊷|㊸|㊹|㊺|㊻|㊼|㊽|㊾|㊿|㋿|塚|朗|晴|猪|凞|礼|神|硺|祥|福|靖|精|羽|蘒|諸|逸|隆|飯|飼|鶴|館"; | |
/** | |
* 機種依存文字を抽出するためのパターン | |
* `|` で区切った上で Unicode 形式に変換しないと上手く動かない点に注意する | |
* | |
* 機種依存文字の例 | |
* ①②③④⑤⑥⑦⑧⑨⑩⑪⑫⑬⑭⑯⑰⑱⑲⑳ⅠⅡⅢⅣⅤⅥⅦⅧⅨⅩ㍉㌔㌢㍍㌘㌧㌃㌶㍑㍗㌍㌦㌣㌫㍊㌻㎜㎝㎞㎎㎏㏄㎡㍻〝〟№㏍℡㊤㊥㊦㊧㊨㈱㈲㈹㍾㍽㍼∮∟⊿纊褜鍈銈蓜俉炻昱棈鋹曻彅丨仡仼伀伃伹佖侒侊侚侔俍偀倢俿倞偆偰偂傔僴僘兊兤冝冾凬刕劜劦勀勛匀匇匤卲厓厲叝﨎咜咊咩哿喆坙坥垬埈埇﨏增墲夋奓奛奝奣妤妺孖寀甯寘寬尞岦岺峵崧嵓﨑嵂嵭嶸嶹巐弡弴彧德忞恝悅悊惞惕愠惲愑愷愰憘戓抦揵摠撝擎敎昀昕昻昉昮昞昤晥晗晙晳暙暠暲暿曺朎杦枻桒柀栁桄棏﨓楨﨔榘槢樰橫橆橳橾櫢櫤毖氿汜沆汯泚洄涇浯涖涬淏淸淲淼渹湜渧渼溿澈澵濵瀅瀇瀨炅炫焏焄煜煆煇凞燁燾犱犾猤獷玽珉珖珣珒琇珵琦琪琩琮瑢璉璟甁畯皂皜皞皛皦睆劯砡硎硤礰禔禛竑竧竫箞絈絜綷綠緖繒罇羡茁荢荿菇菶葈蒴蕓蕙蕫﨟薰蘒﨡蠇裵訒訷詹誧誾諟諶譓譿賰賴贒赶﨣軏﨤遧郞鄕鄧釚釗釞釭釮釤釥鈆鈐鈊鈺鉀鈼鉎鉙鉑鈹鉧銧鉷鉸鋧鋗鋙鋐﨧鋕鋠鋓錥錡鋻﨨錞鋿錝錂鍰鍗鎤鏆鏞鏸鐱鑅鑈閒﨩隝隯霳霻靃靍靏靑靕顗顥餧馞驎髙髜魵魲鮏鮱鮻鰀鵰鵫鸙黑ⅰⅱⅲⅳⅴⅵⅶⅷⅸⅹ¬¦'"≒≡∫∑√⊥∠∵∩∪€㍵〷☯☸☬☤☡℆℅℄℁℀⁀‿‷‶‵‴‱🔣✇☣㈳㈴㈵㈶㈷㈸㈺㈻㈼㈽㈾㈿㉀㉁㉂㉃㈪㈫㈬㈭㈮㈯㈰❶❷❸❹❺❻❼❽❾❿➊➋➌➍➎➏➐➑➒➓⑴⑵⑶⑷⑸⑹⑺⑻⑼⑽⑾⑿⒀⒁⒂⒃⒄⒅⒆⒇₁₂₃₄₅₆₇₈₉¹²³⁴⁵⁶⁷⁸⁹㈠㈡㈢㈣㈤㈥㈦㈧㈨㈩㊀㊁㊂㊃㊄㊅㊆㊇㊈㊉⑮㉑㉒㉓㉔㉕㉖㉗㉘㉙㉚㉛㉜㉝㉞㉟㊱㊲㊳㊴㊵㊶㊷㊸㊹㊺㊻㊼㊽㊾㊿㋿塚朗晴猪凞礼神硺祥福靖精羽蘒諸逸隆飯飼鶴館 | |
*/ | |
export const machineDependentWordPattern = | |
/* eslint-disable-next-line no-control-regex */ | |
/^(?!.*(\u2460|\u2461|\u2462|\u2463|\u2464|\u2465|\u2466|\u2467|\u2468|\u2469|\u246a|\u246b|\u246c|\u246d|\u246f|\u2470|\u2471|\u2472|\u2473|\u2160|\u2161|\u2162|\u2163|\u2164|\u2165|\u2166|\u2167|\u2168|\u2169|\u3349|\u3314|\u3322|\u334d|\u3318|\u3327|\u3303|\u3336|\u3351|\u3357|\u330d|\u3326|\u3323|\u332b|\u334a|\u333b|\u339c|\u339d|\u339e|\u338e|\u338f|\u33c4|\u33a1|\u337b|\u301d|\u301f|\u2116|\u33cd|\u2121|\u32a4|\u32a5|\u32a6|\u32a7|\u32a8|\u3231|\u3232|\u3239|\u337e|\u337d|\u337c|\u222e|\u221f|\u22bf|\u7e8a|\u891c|\u9348|\u9288|\u84dc|\u4fc9|\u70bb|\u6631|\u68c8|\u92f9|\u66fb|\u5f45|\u4e28|\u4ee1|\u4efc|\u4f00|\u4f03|\u4f39|\u4f56|\u4f92|\u4f8a|\u4f9a|\u4f94|\u4fcd|\u5040|\u5022|\u4fff|\u501e|\u5046|\u5070|\u5042|\u5094|\u50f4|\u50d8|\u514a|\u5164|\u519d|\u51be|\u51ec|\u5215|\u529c|\u52a6|\u52c0|\u52db|\u5300|\u5307|\u5324|\u5372|\u5393|\u53b2|\u53dd|\ufa0e|\u549c|\u548a|\u54a9|\u54ff|\u5586|\u5759|\u5765|\u57ac|\u57c8|\u57c7|\ufa0f|\u589e|\u58b2|\u590b|\u5953|\u595b|\u595d|\u5963|\u59a4|\u59ba|\u5b56|\u5bc0|\u752f|\u5bd8|\u5bec|\u5c1e|\u5ca6|\u5cba|\u5cf5|\u5d27|\u5d53|\ufa11|\u5d42|\u5d6d|\u5db8|\u5db9|\u5dd0|\u5f21|\u5f34|\u5f67|\u5fb7|\u5fde|\u605d|\u6085|\u608a|\u60de|\u60d5|\u6120|\u60f2|\u6111|\u6137|\u6130|\u6198|\u6213|\u62a6|\u63f5|\u6460|\u649d|\u64ce|\u654e|\u6600|\u6615|\u663b|\u6609|\u662e|\u661e|\u6624|\u6665|\u6657|\u6659|\u6673|\u6699|\u66a0|\u66b2|\u66bf|\u66fa|\u670e|\u6766|\u67bb|\u6852|\u67c0|\u6801|\u6844|\u68cf|\ufa13|\u6968|\ufa14|\u6998|\u69e2|\u6a30|\u6a6b|\u6a46|\u6a73|\u6a7e|\u6ae2|\u6ae4|\u6bd6|\u6c3f|\u6c5c|\u6c86|\u6c6f|\u6cda|\u6d04|\u6d87|\u6d6f|\u6d96|\u6dac|\u6dcf|\u6df8|\u6df2|\u6dfc|\u6e39|\u6e5c|\u6e27|\u6e3c|\u6ebf|\u6f88|\u6fb5|\u6ff5|\u7005|\u7007|\u7028|\u7085|\u70ab|\u710f|\u7104|\u715c|\u7146|\u7147|\u51de|\u71c1|\u71fe|\u72b1|\u72be|\u7324|\u7377|\u73bd|\u73c9|\u73d6|\u73e3|\u73d2|\u7407|\u73f5|\u7426|\u742a|\u7429|\u742e|\u7462|\u7489|\u749f|\u7501|\u756f|\u7682|\u769c|\u769e|\u769b|\u76a6|\u7746|\u52af|\u7821|\u784e|\u7864|\u7930|\u7994|\u799b|\u7ad1|\u7ae7|\u7aeb|\u7b9e|\u7d48|\u7d5c|\u7db7|\u7da0|\u7dd6|\u7e52|\u7f47|\u7fa1|\u8301|\u8362|\u837f|\u83c7|\u83f6|\u8448|\u84b4|\u8553|\u8559|\u856b|\ufa1f|\u85b0|\u8612|\ufa21|\u8807|\u88f5|\u8a12|\u8a37|\u8a79|\u8aa7|\u8abe|\u8adf|\u8af6|\u8b53|\u8b7f|\u8cf0|\u8cf4|\u8d12|\u8d76|\ufa23|\u8ecf|\ufa24|\u9067|\u90de|\u9115|\u9127|\u91da|\u91d7|\u91de|\u91ed|\u91ee|\u91e4|\u91e5|\u9206|\u9210|\u920a|\u923a|\u9240|\u923c|\u924e|\u9259|\u9251|\u9239|\u9267|\u92a7|\u9277|\u9278|\u92e7|\u92d7|\u92d9|\u92d0|\ufa27|\u92d5|\u92e0|\u92d3|\u9325|\u9321|\u92fb|\ufa28|\u931e|\u92ff|\u931d|\u9302|\u9370|\u9357|\u93a4|\u93c6|\u93de|\u93f8|\u9431|\u9445|\u9448|\u9592|\ufa29|\u969d|\u96af|\u9733|\u973b|\u9743|\u974d|\u974f|\u9751|\u9755|\u9857|\u9865|\u9927|\u999e|\u9a4e|\u9ad9|\u9adc|\u9b75|\u9b72|\u9b8f|\u9bb1|\u9bbb|\u9c00|\u9d70|\u9d6b|\u9e19|\u9ed1|\u2170|\u2171|\u2172|\u2173|\u2174|\u2175|\u2176|\u2177|\u2178|\u2179|\uffe2|\uffe4|\uff07|\uff02|\u2252|\u2261|\u222b|\u2211|\u221a|\u22a5|\u2220|\u2235|\u2229|\u222a|\u20ac|\u3375|\u3037|\u262f|\u2638|\u262c|\u2624|\u2621|\u2106|\u2105|\u2104|\u2101|\u2100|\u2040|\u203f|\u2037|\u2036|\u2035|\u2034|\u2031|\ud83d\udd23|\ufffd|\u2707|\u2623|\u3233|\u3234|\u3235|\u3236|\u3237|\u3238|\u323a|\u323b|\u323c|\u323d|\u323e|\u323f|\u3240|\u3241|\u3242|\u3243|\u322a|\u322b|\u322c|\u322d|\u322e|\u322f|\u3230|\u2776|\u2777|\u2778|\u2779|\u277a|\u277b|\u277c|\u277d|\u277e|\u277f|\u278a|\u278b|\u278c|\u278d|\u278e|\u278f|\u2790|\u2791|\u2792|\u2793|\u2474|\u2475|\u2476|\u2477|\u2478|\u2479|\u247a|\u247b|\u247c|\u247d|\u247e|\u247f|\u2480|\u2481|\u2482|\u2483|\u2484|\u2485|\u2486|\u2487|\u2081|\u2082|\u2083|\u2084|\u2085|\u2086|\u2087|\u2088|\u2089|\u00b9|\u00b2|\u00b3|\u2074|\u2075|\u2076|\u2077|\u2078|\u2079|\u3220|\u3221|\u3222|\u3223|\u3224|\u3225|\u3226|\u3227|\u3228|\u3229|\u3280|\u3281|\u3282|\u3283|\u3284|\u3285|\u3286|\u3287|\u3288|\u3289|\u246e|\u3251|\u3252|\u3253|\u3254|\u3255|\u3256|\u3257|\u3258|\u3259|\u325a|\u325b|\u325c|\u325d|\u325e|\u325f|\u32b1|\u32b2|\u32b3|\u32b4|\u32b5|\u32b6|\u32b7|\u32b8|\u32b9|\u32ba|\u32bb|\u32bc|\u32bd|\u32be|\u32bf|\u32ff|\u585a|\u6717|\u6674|\u732a|\u51de|\u793c|\u795e|\u787a|\u7965|\u798f|\u9756|\u7cbe|\u7fbd|\u8612|\u8af8|\u9038|\u9686|\u98ef|\u98fc|\u9db4|\u9928))/g; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment