Rのstringiパッケージによる文字列の変換についてメモ

はじめに

Rのstringiパッケージを用いた文字列の変換についてまとめます。

目次

• Rのstringiパッケージによる文字列の変換
  • stri_trans_general()：一般的な変換
    • 大文字・小文字
    • 半角・全角
    • ひらがな・カタカナ
    • 英字・ギリシャ文字・キリル文字・ハングル
    • ひらがな・カタカナ・英字
    • Unicode Normalization
    • 複数の変換
  • stri_trans_toupper(), stri_trans_tolower(), stri_trans_totitle()：大文字・小文字変換
  • stri_trans_nfc(), stri_trans_nfd() 等：Unicode Normalization
  • stri_trans_char()：対応する１文字ずつの置換
  • stri_datetime_format()：日付フォーマット
• 参考

Rのstringiパッケージによる文字列の変換

まず、使用する文字列ベクトルを用意しておきます。

R

library(tidyverse)
library(stringi)

str <- c("alphabet",
         "ALPHABET",
         "ａｌｐｈａｂｅｔ",
         "ＡＬＰＨＡＢＥＴ",
         ".,;:+-*/^_~&| ",
         "．，；：＋－＊／＾＿～＆｜　",
         "ひらがな",
         "カタカナ",
         "ｶﾀｶﾅ",
         "漢字",
         "0123456789",
         "０１２３４５６７８９",
         "エタノール水溶液１，０００ｍＬ",
         "50％のｴﾀﾉｰﾙ水溶液1,000mg")
str
#  [1] "alphabet"                       "ALPHABET"                      
#  [3] "ａｌｐｈａｂｅｔ"               "ＡＬＰＨＡＢＥＴ"              
#  [5] ".,;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ｍＬ" "50％のｴﾀﾉｰﾙ水溶液1,000mg"       

str_alphabet <- c("abcdefghijklmnopqrstuvwxyz",
                  "ABCDEFGHIJKLMNOPQRSTUVWXYZ")
str_alphabet
# [1] "abcdefghijklmnopqrstuvwxyz" "ABCDEFGHIJKLMNOPQRSTUVWXYZ"

str_hiragana <- c("あかさたなはまやらわがざだばぱ",
                  "いきしちにひみいりゐぎじぢびぴ",
                  "うくすつぬふむゆるうぐずづぶぷ",
                  "えけせてねへめえれゑげぜでべぺ",
                  "おこそとのほもよろをごぞどぼぽ",
                  "きゃぎゃしゃじゃちゃぢゃにゃひゃびゃぴゃみゃりゃ",
                  "きゅぎゅしゅじゅちゅぢゅにゅひゅびゅぴゅみゅりゅ",
                  "きょぎょしょじょちょぢょにょひょびょぴょみょりょ",
                  "ん")
str_hiragana
# [1] "あかさたなはまやらわがざだばぱ"                  
# [2] "いきしちにひみいりゐぎじぢびぴ"                  
# [3] "うくすつぬふむゆるうぐずづぶぷ"                  
# [4] "えけせてねへめえれゑげぜでべぺ"                  
# [5] "おこそとのほもよろをごぞどぼぽ"                  
# [6] "きゃぎゃしゃじゃちゃぢゃにゃひゃびゃぴゃみゃりゃ"
# [7] "きゅぎゅしゅじゅちゅぢゅにゅひゅびゅぴゅみゅりゅ"
# [8] "きょぎょしょじょちょぢょにょひょびょぴょみょりょ"
# [9] "ん" 

stri_trans_general()：一般的な変換

大文字・小文字

R

# Any -> 大文字
stri_trans_general(str, "Upper")
stri_trans_general(str, "upper")
stri_trans_general(str, "Any-Upper")
stri_trans_general(str, "any-upper")
#  [1] "ALPHABET"                       "ALPHABET"                      
#  [3] "ＡＬＰＨＡＢＥＴ"               "ＡＬＰＨＡＢＥＴ"              
#  [5] ".,;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ＭＬ" "50％のｴﾀﾉｰﾙ水溶液1,000MG"       

# Any -> 小文字
stri_trans_general(str, "Lower")
stri_trans_general(str, "Any-Lower")
stri_trans_general(str, "lower")
stri_trans_general(str, "any-lower")
#  [1] "alphabet"                       "alphabet"                      
#  [3] "ａｌｐｈａｂｅｔ"               "ａｌｐｈａｂｅｔ"              
#  [5] ".,;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ｍｌ" "50％のｴﾀﾉｰﾙ水溶液1,000mg" 

半角・全角

R

# 半角 -> 全角
stri_trans_general(str, "Halfwidth-Fullwidth")
stri_trans_general(str, "halfwidth-fullwidth")
#  [1] "ａｌｐｈａｂｅｔ"                       "ＡＬＰＨＡＢＥＴ"                      
#  [3] "ａｌｐｈａｂｅｔ"                       "ＡＬＰＨＡＢＥＴ"                      
#  [5] "．，；：＋－＊／＾＿～＆｜　"           "．，；：＋－＊／＾＿～＆｜　"          
#  [7] "ひらがな"                               "カタカナ"                              
#  [9] "カタカナ"                               "漢字"                                  
# [11] "０１２３４５６７８９"                   "０１２３４５６７８９"                  
# [13] "エタノール水溶液１，０００ｍＬ"         "５０％のエタノール水溶液１，０００ｍｇ"

stri_trans_general(str_alphabet, "halfwidth-fullwidth")
# [1] "ａｂｃｄｅｆｇｈｉｊｋｌｍｎｏｐｑｒｓｔｕｖｗｘｙｚ"
# [2] "ＡＢＣＤＥＦＧＨＩＪＫＬＭＮＯＰＱＲＳＴＵＶＷＸＹＺ"

# 全角 -> 半角
stri_trans_general(str, "Fullwidth-Halfwidth")
stri_trans_general(str, "fullwidth-halfwidth")
#  [1] "alphabet"                "ALPHABET"               
#  [3] "alphabet"                "ALPHABET"               
#  [5] ".,;:+-*/^_~&| "          ".,;:+-*/^_~&| "         
#  [7] "ひらがな"                "ｶﾀｶﾅ"                   
#  [9] "ｶﾀｶﾅ"                    "漢字"                   
# [11] "0123456789"              "0123456789"             
# [13] "ｴﾀﾉｰﾙ水溶液1,000mL"      "50%のｴﾀﾉｰﾙ水溶液1,000mg"

stri_trans_general(str_alphabet, "halfwidth-fullwidth") %>% print() %>%
  stri_trans_general("fullwidth-halfwidth")
# [1] "ａｂｃｄｅｆｇｈｉｊｋｌｍｎｏｐｑｒｓｔｕｖｗｘｙｚ"
# [2] "ＡＢＣＤＥＦＧＨＩＪＫＬＭＮＯＰＱＲＳＴＵＶＷＸＹＺ"
# [1] "abcdefghijklmnopqrstuvwxyz"
# [2] "ABCDEFGHIJKLMNOPQRSTUVWXYZ"

stri_trans_general(str_hiragana, "Hiragana-Katakana") %>% print() %>%
  stri_trans_general("fullwidth-halfwidth")
# [1] "アカサタナハマヤラワガザダバパ"                  
# [2] "イキシチニヒミイリヰギジヂビピ"                  
# [3] "ウクスツヌフムユルウグズヅブプ"                  
# [4] "エケセテネヘメエレヱゲゼデベペ"                  
# [5] "オコソトノホモヨロヲゴゾドボポ"                  
# [6] "キャギャシャジャチャヂャニャヒャビャピャミャリャ"
# [7] "キュギュシュジュチュヂュニュヒュビュピュミュリュ"
# [8] "キョギョショジョチョヂョニョヒョビョピョミョリョ"
# [9] "ン"                                              
# [1] "ｱｶｻﾀﾅﾊﾏﾔﾗﾜｶﾞｻﾞﾀﾞﾊﾞﾊﾟ"          "ｲｷｼﾁﾆﾋﾐｲﾘヰｷﾞｼﾞﾁﾞﾋﾞﾋﾟ"        
# [3] "ｳｸｽﾂﾇﾌﾑﾕﾙｳｸﾞｽﾞﾂﾞﾌﾞﾌﾟ"          "ｴｹｾﾃﾈﾍﾒｴﾚヱｹﾞｾﾞﾃﾞﾍﾞﾍﾟ"        
# [5] "ｵｺｿﾄﾉﾎﾓﾖﾛｦｺﾞｿﾞﾄﾞﾎﾞﾎﾟ"          "ｷｬｷﾞｬｼｬｼﾞｬﾁｬﾁﾞｬﾆｬﾋｬﾋﾞｬﾋﾟｬﾐｬﾘｬ"
# [7] "ｷｭｷﾞｭｼｭｼﾞｭﾁｭﾁﾞｭﾆｭﾋｭﾋﾞｭﾋﾟｭﾐｭﾘｭ" "ｷｮｷﾞｮｼｮｼﾞｮﾁｮﾁﾞｮﾆｮﾋｮﾋﾞｮﾋﾟｮﾐｮﾘｮ"
# [9] "ﾝ"                            

ひらがな・カタカナ

R

# ひらがな -> カタカナ
stri_trans_general(str, "Hiragana-Katakana")
stri_trans_general(str, "hiragana-katakana")
#  [1] "alphabet"                       "ALPHABET"                      
#  [3] "ａｌｐｈａｂｅｔ"               "ＡＬＰＨＡＢＥＴ"              
#  [5] ".,;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ヒラガナ"                       "カタカナ"                      
#  [9] "カタカナ"                       "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ｍＬ" "50％ノエタノール水溶液1,000mg" 

stri_trans_general(str_hiragana, "Hiragana-Katakana")
stri_trans_general(str_hiragana, "hiragana-katakana")
# [1] "アカサタナハマヤラワガザダバパ"                  
# [2] "イキシチニヒミイリヰギジヂビピ"                  
# [3] "ウクスツヌフムユルウグズヅブプ"                  
# [4] "エケセテネヘメエレヱゲゼデベペ"                  
# [5] "オコソトノホモヨロヲゴゾドボポ"                  
# [6] "キャギャシャジャチャヂャニャヒャビャピャミャリャ"
# [7] "キュギュシュジュチュヂュニュヒュビュピュミュリュ"
# [8] "キョギョショジョチョヂョニョヒョビョピョミョリョ"
# [9] "ン"                                              

# カタカナ -> ひらがな
stri_trans_general(str, "Katakana-Hiragana")
stri_trans_general(str, "katakana-hiragana")
#  [1] "alphabet"                       "ALPHABET"                      
#  [3] "ａｌｐｈａｂｅｔ"               "ＡＬＰＨＡＢＥＴ"              
#  [5] ".,;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "かたかな"                      
#  [9] "かたかな"                       "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "えたのおる水溶液１，０００ｍＬ" "50％のえたのおる水溶液1,000mg" 

英字・ギリシャ文字・キリル文字・ハングル

R

# 英字 -> ギリシャ文字
stri_trans_general(str, "Latin-Greek")
stri_trans_general(str, "latin-greek")
#  [1] "ἀλφαβετ"                  "ἈΛΦΑΒΕΤ"                 
#  [3] "ａｌｐｈａｂｅｔ"               "ＡＬＰＨＡＢＥＴ"              
#  [5] ".,;·+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ｍＬ" "50％のｴﾀﾉｰﾙ水溶液1,000μγ"    

stri_trans_general(str_latin, "latin-greek")
# [1] "ἀβκδεφγἱικλμνοπκρστυυυξυζ"
# [2] "ἈΒΚΔΕΦΓἹΙΚΛΜΝΟΠΚΡΣΤΥΥΥΞΥΖ"

# 英字 -> キリル文字
stri_trans_general(str, "Latin-Cyrillic")
stri_trans_general(str, "latin-cyrillic")
#  [1] "алпхабет"               "АЛПХАБЕТ"              
#  [3] "ａｌｐｈａｂｅｔ"               "ＡＬＰＨＡＢＥＴ"              
#  [5] ".,;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ｍＬ" "50％のｴﾀﾉｰﾙ水溶液1,000мг"    

stri_trans_general(str_latin, "latin-cyrillic")
# [1] "абцдефгхийклмнопкрстувуксыз"
# [2] "АБЦДЕФГХИЙКЛМНОПКРСТУВУКСЫЗ"

# 英字 -> ハングル
stri_trans_general(str, "Latin-Hangul")
stri_trans_general(str, "latin-hangul")
#  [1] "앒하벹"                         "앒하벹"                        
#  [3] "ａｌｐｈａｂｅｔ"               "ＡＬＰＨＡＢＥＴ"              
#  [5] ".,;:+*/^_~&| "                  "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ｍＬ" "50％のｴﾀﾉｰﾙ水溶液1,000믁"      

# 英字 -> Indic
stri_trans_general(str, "Latin-Interindic")
stri_trans_general(str, "latin-interindic")

ひらがな・カタカナ・英字

R

# ひらがな -> 英字
stri_trans_general(str, "Hiragana-Latin")
stri_trans_general(str, "hiragana-latin")
#  [1] "alphabet"                     "ALPHABET"                    
#  [3] "ａｌｐｈａｂｅｔ"             "ＡＬＰＨＡＢＥＴ"            
#  [5] ".,;:+-*/^_~&| "               "．，；：＋－＊／＾＿～＆｜　"
#  [7] "hiragana"                     "カタカナ"                    
#  [9] "ｶﾀｶﾅ"                         "漢字"                        
# [11] "0123456789"                   "０１２３４５６７８９"        
# [13] "エタノ̄ル水溶液１，０００ｍＬ" "50％noｴﾀﾉｰﾙ水溶液1,000mg"    

stri_trans_general(str_hiragana, "Hiragana-Latin")
# [1] "akasatanahamayarawagazadabapa"       "ikishichinihimiiriwigijidjibipi"    
# [3] "ukusutsunufumuyuruuguzudzubupu"      "ekesetenehemeerewegezedebepe"       
# [5] "okosotonohomoyorowogozodobopo"       "kyagyashajachadjanyahyabyapyamyarya"
# [7] "kyugyushujuchudjunyuhyubyupyumyuryu" "kyogyoshojochodjonyohyobyopyomyoryo"
# [9] "n" 

# カタカナ -> 英字
stri_trans_general(str, "Katakana-Latin")
stri_trans_general(str, "katakana-latin")
#  [1] "alphabet"                     "ALPHABET"                    
#  [3] "ａｌｐｈａｂｅｔ"             "ＡＬＰＨＡＢＥＴ"            
#  [5] ".,;:+-*/^_~&| "               "．，；：＋－＊／＾＿～＆｜　"
#  [7] "ひらがな"                     "katakana"                    
#  [9] "katakana"                     "漢字"                        
# [11] "0123456789"                   "０１２３４５６７８９"        
# [13] "etanōru水溶液１，０００ｍＬ" "50％のetanōru水溶液1,000mg" 

# 英字 -> ひらがな
stri_trans_general(str, "Latin-Hiragana")
stri_trans_general(str, "latin-hiragana")
#  [1] "あるぷはべて"                   "あるぷはべて"                  
#  [3] "ａｌｐｈａｂｅｔ"               "ＡＬＰＨＡＢＥＴ"              
#  [5] "。、;:+-*/^_&| "                "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ｍＬ" "50％のｴﾀﾉｰﾙ水溶液1、000むぐ"   

stri_trans_general(str_alphabet, "Latin-Hiragana")
# [1] "あぶくでふぐひじくるむのぷくるすてぅゔうくせぃず"
# [2] "あぶくでふぐひじくるむのぷくるすてぅゔうくせぃず"

# 英字 -> カタカナ
stri_trans_general(str, "Latin-Katakana")
stri_trans_general(str, "latin-katakana")
#  [1] "アルプハベテ"                   "アルプハベテ"                  
#  [3] "アルプハベテ"                   "アルプハベテ"                  
#  [5] "。、;:+-*/^_&| "                "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ムル" "50％のｴﾀﾉｰﾙ水溶液1、000ムグ"   

stri_trans_general(str_alphabet, "Latin-Katakana")
# [1] "アブクデフグヒジクルムノプクルステゥヴウクセィズ"
# [2] "アブクデフグヒジクルムノプクルステゥヴウクセィズ"

# Any -> 英字
stri_trans_general(str, "Any-Latin")
stri_trans_general(str, "any-latin")
#  [1] "alphabet"                               "ALPHABET"                              
#  [3] "ａｌｐｈａｂｅｔ"                       "ＡＬＰＨＡＢＥＴ"                      
#  [5] ".,;:+-*/^_~&| "                         "．，；：＋－＊／＾＿～＆｜　"          
#  [7] "hiragana"                               "katakana"                              
#  [9] "katakana"                               "hàn zì"                              
# [11] "0123456789"                             "０１２３４５６７８９"                  
# [13] "etanōru shuǐ róng yè１，０００ｍＬ" "50％noetanōru shuǐ róng yè1,000mg" 

# Any -> ひらがな
stri_trans_general(str, "Any-Hiragana")
stri_trans_general(str, "any-hiragana")
#  [1] "あるぷはべて"                     "あるぷはべて"                    
#  [3] "ａｌｐｈａｂｅｔ"                 "ＡＬＰＨＡＢＥＴ"                
#  [5] ".,;:+-*/^_~&| "                   "．，；：＋－＊／＾＿～＆｜　"    
#  [7] "ひらがな"                         "かたかな"                        
#  [9] "かたかな"                         "漢字"                            
# [11] "0123456789"                       "０１２３４５６７８９"            
# [13] "えたのおる水溶液１，０００ｍＬ"   "50％のえたのおる水溶液1、000むぐ"

# Any -> カタカナ
stri_trans_general(str, "Any-Katakana")
stri_trans_general(str, "any-katakana")
#  [1] "アルプハベテ"                   "アルプハベテ"                  
#  [3] "アルプハベテ"                   "アルプハベテ"                  
#  [5] ".,;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ヒラガナ"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ムル" "50％ノｴﾀﾉｰﾙ水溶液1、000ムグ"  

Unicode Normalization

全角英数字を半角に、半角カタカナを全角に、というように “まとも” な形に変換します。'NFKC'が一番まともそう。

R

stri_trans_general(str, 'NFC')
stri_trans_general(str, 'Any-NFC')
#  [1] "alphabet"                       "ALPHABET"                      
#  [3] "ａｌｐｈａｂｅｔ"               "ＡＬＰＨＡＢＥＴ"              
#  [5] ".,;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ｍＬ" "50％のｴﾀﾉｰﾙ水溶液1,000mg"   

stri_trans_general(str, 'NFD')
#  [1] "alphabet"                       "ALPHABET"                      
#  [3] "ａｌｐｈａｂｅｔ"               "ＡＬＰＨＡＢＥＴ"              
#  [5] ".,;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ｍＬ" "50％のｴﾀﾉｰﾙ水溶液1,000mg"      

stri_trans_general(str, 'NFKD')
#  [1] "alphabet"                     "ALPHABET"                    
#  [3] "alphabet"                     "ALPHABET"                    
#  [5] ".,;:+-*/^_~&| "               ".,;:+-*/^_~&| "              
#  [7] "ひらがな"                     "カタカナ"                    
#  [9] "カタカナ"                     "漢字"                        
# [11] "0123456789"                   "0123456789"                  
# [13] "エタノール水溶液1,000mL"      "50%のエタノール水溶液1,000mg"

stri_trans_general(str, 'NFKC')
#  [1] "alphabet"                     "ALPHABET"                    
#  [3] "alphabet"                     "ALPHABET"                    
#  [5] ".,;:+-*/^_~&| "               ".,;:+-*/^_~&| "              
#  [7] "ひらがな"                     "カタカナ"                    
#  [9] "カタカナ"                     "漢字"                        
# [11] "0123456789"                   "0123456789"                  
# [13] "エタノール水溶液1,000mL"      "50%のエタノール水溶液1,000mg"

複数の変換

複数の変換を同時にもできる。

R

# カタカナ -> ひらがな and 半角 -> 全角
stri_trans_general(str, "katakana-hiragana; halfwidth-fullwidth")
#  [1] "ａｌｐｈａｂｅｔ"                       "ＡＬＰＨＡＢＥＴ"                      
#  [3] "ａｌｐｈａｂｅｔ"                       "ＡＬＰＨＡＢＥＴ"                      
#  [5] "．，；：＋－＊／＾＿～＆｜　"           "．，；：＋－＊／＾＿～＆｜　"          
#  [7] "ひらがな"                               "かたかな"                              
#  [9] "かたかな"                               "漢字"                                  
# [11] "０１２３４５６７８９"                   "０１２３４５６７８９"                  
# [13] "えたのおる水溶液１，０００ｍＬ"         "５０％のえたのおる水溶液１，０００ｍｇ"

# ひらがな -> カタカナ and 全角 -> 半角
stri_trans_general(str, "hiragana-katakana; fullwidth-halfwidth")
#  [1] "alphabet"               "ALPHABET"              
#  [3] "alphabet"               "ALPHABET"              
#  [5] ".,;:+-*/^_~&| "         ".,;:+-*/^_~&| "        
#  [7] "ﾋﾗｶﾞﾅ"                  "ｶﾀｶﾅ"                  
#  [9] "ｶﾀｶﾅ"                   "漢字"                  
# [11] "0123456789"             "0123456789"            
# [13] "ｴﾀﾉｰﾙ水溶液1,000mL"     "50%ﾉｴﾀﾉｰﾙ水溶液1,000mg"

# 半角 -> 全角 and Any -> 大文字
stri_trans_general(str, "halfwidth-fullwidth; upper")
stri_trans_general(str, "halfwidth-fullwidth; Any-Upper")
#  [1] "ＡＬＰＨＡＢＥＴ"                       "ＡＬＰＨＡＢＥＴ"                      
#  [3] "ＡＬＰＨＡＢＥＴ"                       "ＡＬＰＨＡＢＥＴ"                      
#  [5] "．，；：＋－＊／＾＿～＆｜　"           "．，；：＋－＊／＾＿～＆｜　"          
#  [7] "ひらがな"                               "カタカナ"                              
#  [9] "カタカナ"                               "漢字"                                  
# [11] "０１２３４５６７８９"                   "０１２３４５６７８９"                  
# [13] "エタノール水溶液１，０００ＭＬ"         "５０％のエタノール水溶液１，０００ＭＧ"

stri_trans_toupper(), stri_trans_tolower(), stri_trans_totitle()：大文字・小文字変換

stringrパッケージのstr_to_upper(), str_to_lower(), str_to_title(), str_to_sentence()と同じようです。

R

stri_trans_toupper(str)
#  [1] "ALPHABET"                       "ALPHABET"                      
#  [3] "ＡＬＰＨＡＢＥＴ"               "ＡＬＰＨＡＢＥＴ"              
#  [5] ".,;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ＭＬ" "50％のｴﾀﾉｰﾙ水溶液1,000MG"  
str_to_upper(str)
#  [1] "ALPHABET"                       "ALPHABET"                      
#  [3] "ＡＬＰＨＡＢＥＴ"               "ＡＬＰＨＡＢＥＴ"              
#  [5] ".,;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ＭＬ" "50％のｴﾀﾉｰﾙ水溶液1,000MG"     

stri_trans_tolower(str)
#  [1] "alphabet"                       "alphabet"                      
#  [3] "ａｌｐｈａｂｅｔ"               "ａｌｐｈａｂｅｔ"              
#  [5] ".,;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ｍｌ" "50％のｴﾀﾉｰﾙ水溶液1,000mg"  
str_to_lower(str)
#  [1] "alphabet"                       "alphabet"                      
#  [3] "ａｌｐｈａｂｅｔ"               "ａｌｐｈａｂｅｔ"              
#  [5] ".,;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ｍｌ" "50％のｴﾀﾉｰﾙ水溶液1,000mg"   

stri_trans_totitle(str)
#  [1] "Alphabet"                       "Alphabet"                      
#  [3] "Ａｌｐｈａｂｅｔ"               "Ａｌｐｈａｂｅｔ"              
#  [5] ".,;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００Ｍｌ" "50％のｴﾀﾉｰﾙ水溶液1,000mg"   
str_to_title(str)
#  [1] "Alphabet"                       "Alphabet"                      
#  [3] "Ａｌｐｈａｂｅｔ"               "Ａｌｐｈａｂｅｔ"              
#  [5] ".,;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００Ｍｌ" "50％のｴﾀﾉｰﾙ水溶液1,000mg"      

stri_trans_totitle(str_c(str, " ", str))
#  [1] "Alphabet Alphabet"                                             "Alphabet Alphabet"                                            
#  [3] "Ａｌｐｈａｂｅｔ Ａｌｐｈａｂｅｔ"                             "Ａｌｐｈａｂｅｔ Ａｌｐｈａｂｅｔ"                            
#  [5] ".,;:+-*/^_~&|  .,;:+-*/^_~&| "                                 "．，；：＋－＊／＾＿～＆｜　 ．，；：＋－＊／＾＿～＆｜　"    
#  [7] "ひらがな ひらがな"                                             "カタカナ カタカナ"                                            
#  [9] "ｶﾀｶﾅ ｶﾀｶﾅ"                                                     "漢字 漢字"                                                    
# [11] "0123456789 0123456789"                                         "０１２３４５６７８９ ０１２３４５６７８９"                    
# [13] "エタノール水溶液１，０００Ｍｌ エタノール水溶液１，０００Ｍｌ" "50％のｴﾀﾉｰﾙ水溶液1,000mg 50％のｴﾀﾉｰﾙ水溶液1,000mg"     
str_to_title(str_c(str, " ", str))
#  [1] "Alphabet Alphabet"                                             "Alphabet Alphabet"                                            
#  [3] "Ａｌｐｈａｂｅｔ Ａｌｐｈａｂｅｔ"                             "Ａｌｐｈａｂｅｔ Ａｌｐｈａｂｅｔ"                            
#  [5] ".,;:+-*/^_~&|  .,;:+-*/^_~&| "                                 "．，；：＋－＊／＾＿～＆｜　 ．，；：＋－＊／＾＿～＆｜　"    
#  [7] "ひらがな ひらがな"                                             "カタカナ カタカナ"                                            
#  [9] "ｶﾀｶﾅ ｶﾀｶﾅ"                                                     "漢字 漢字"                                                    
# [11] "0123456789 0123456789"                                         "０１２３４５６７８９ ０１２３４５６７８９"                    
# [13] "エタノール水溶液１，０００Ｍｌ エタノール水溶液１，０００Ｍｌ" "50％のｴﾀﾉｰﾙ水溶液1,000mg 50％のｴﾀﾉｰﾙ水溶液1,000mg"            

stri_trans_totitle(str_c(str, " ", str), type='sentence')
#  [1] "Alphabet alphabet"                                             "Alphabet alphabet"                                            
#  [3] "Ａｌｐｈａｂｅｔ ａｌｐｈａｂｅｔ"                             "Ａｌｐｈａｂｅｔ ａｌｐｈａｂｅｔ"                            
#  [5] ".,;:+-*/^_~&|  .,;:+-*/^_~&| "                                 "．，；：＋－＊／＾＿～＆｜　 ．，；：＋－＊／＾＿～＆｜　"    
#  [7] "ひらがな ひらがな"                                             "カタカナ カタカナ"                                            
#  [9] "ｶﾀｶﾅ ｶﾀｶﾅ"                                                     "漢字 漢字"                                                    
# [11] "0123456789 0123456789"                                         "０１２３４５６７８９ ０１２３４５６７８９"                    
# [13] "エタノール水溶液１，０００ｍｌ エタノール水溶液１，０００ｍｌ" "50％のｴﾀﾉｰﾙ水溶液1,000mg 50％のｴﾀﾉｰﾙ水溶液1,000mg"            
str_to_sentence(str_c(str, " ", str))
#  [1] "Alphabet alphabet"                                             "Alphabet alphabet"                                            
#  [3] "Ａｌｐｈａｂｅｔ ａｌｐｈａｂｅｔ"                             "Ａｌｐｈａｂｅｔ ａｌｐｈａｂｅｔ"                            
#  [5] ".,;:+-*/^_~&|  .,;:+-*/^_~&| "                                 "．，；：＋－＊／＾＿～＆｜　 ．，；：＋－＊／＾＿～＆｜　"    
#  [7] "ひらがな ひらがな"                                             "カタカナ カタカナ"                                            
#  [9] "ｶﾀｶﾅ ｶﾀｶﾅ"                                                     "漢字 漢字"                                                    
# [11] "0123456789 0123456789"                                         "０１２３４５６７８９ ０１２３４５６７８９"                    
# [13] "エタノール水溶液１，０００ｍｌ エタノール水溶液１，０００ｍｌ" "50％のｴﾀﾉｰﾙ水溶液1,000mg 50％のｴﾀﾉｰﾙ水溶液1,000mg"       

stri_trans_nfc(), stri_trans_nfd() 等：Unicode Normalization

NFC, NFKC, NFD, NFKD, or NFKC_Casefold Unicode Normalization Form
全角英数字を半角に、半角カタカナを全角に、というように “まとも” な形に変換します。'NFKC'が一番まともそう。

R

# Unicode Normalization
# NFC (Canonical Decomposition, followed by Canonical Composition)
stri_trans_nfc(str)
#  [1] "alphabet"                       "ALPHABET"                      
#  [3] "ａｌｐｈａｂｅｔ"               "ＡＬＰＨＡＢＥＴ"              
#  [5] ".,;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ｍＬ" "50％のｴﾀﾉｰﾙ水溶液1,000mg"      

# NFD (Canonical Decomposition)
stri_trans_nfd(str)
#  [1] "alphabet"                       "ALPHABET"                      
#  [3] "ａｌｐｈａｂｅｔ"               "ＡＬＰＨＡＢＥＴ"              
#  [5] ".,;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ｍＬ" "50％のｴﾀﾉｰﾙ水溶液1,000mg"     

# NFKC (Compatibility Decomposition, followed by Canonical Composition)
stri_trans_nfkc(str)
#  [1] "alphabet"                     "ALPHABET"                    
#  [3] "alphabet"                     "ALPHABET"                    
#  [5] ".,;:+-*/^_~&| "               ".,;:+-*/^_~&| "              
#  [7] "ひらがな"                     "カタカナ"                    
#  [9] "カタカナ"                     "漢字"                        
# [11] "0123456789"                   "0123456789"                  
# [13] "エタノール水溶液1,000mL"      "50%のエタノール水溶液1,000mg"

# NFKD (Compatibility Decomposition)
stri_trans_nfkd(str)
#  [1] "alphabet"                     "ALPHABET"                    
#  [3] "alphabet"                     "ALPHABET"                    
#  [5] ".,;:+-*/^_~&| "               ".,;:+-*/^_~&| "              
#  [7] "ひらがな"                     "カタカナ"                    
#  [9] "カタカナ"                     "漢字"                        
# [11] "0123456789"                   "0123456789"                  
# [13] "エタノール水溶液1,000mL"      "50%のエタノール水溶液1,000mg"

# NFKC_Casefold (combination of NFKC, case folding, and removing ignorable characters which was introduced with Unicode 5.2)
stri_trans_nfkc_casefold(str)
#  [1] "alphabet"                     "alphabet"                    
#  [3] "alphabet"                     "alphabet"                    
#  [5] ".,;:+-*/^_~&| "               ".,;:+-*/^_~&| "              
#  [7] "ひらがな"                     "カタカナ"                    
#  [9] "カタカナ"                     "漢字"                        
# [11] "0123456789"                   "0123456789"                  
# [13] "エタノール水溶液1,000ml"      "50%のエタノール水溶液1,000mg"

stri_trans_isnfc(str)
#  [1] TRUE TRUE
#  [3] TRUE TRUE
#  [5] TRUE TRUE
#  [7] TRUE TRUE
#  [9] TRUE TRUE
# [11] TRUE TRUE
# [13] TRUE TRUE

stri_trans_isnfd(str)
#  [1]  TRUE  TRUE
#  [3]  TRUE  TRUE
#  [5]  TRUE  TRUE
#  [7] FALSE  TRUE
#  [9]  TRUE  TRUE
# [11]  TRUE  TRUE
# [13]  TRUE  TRUE

stri_trans_isnfkd(str)
#  [1]  TRUE  TRUE
#  [3] FALSE FALSE
#  [5]  TRUE FALSE
#  [7] FALSE  TRUE
#  [9] FALSE  TRUE
# [11]  TRUE FALSE
# [13] FALSE FALSE

stri_trans_isnfkc(str)
#  [1]  TRUE  TRUE
#  [3] FALSE FALSE
#  [5]  TRUE FALSE
#  [7]  TRUE  TRUE
#  [9] FALSE  TRUE
# [11]  TRUE FALSE
# [13] FALSE FALSE

stri_trans_isnfkc_casefold(str)
#  [1]  TRUE FALSE
#  [3] FALSE FALSE
#  [5]  TRUE FALSE
#  [7]  TRUE  TRUE
#  [9] FALSE  TRUE
# [11]  TRUE FALSE
# [13] FALSE FALSE

NFKCとNFKDは同じように見えますが、違うようです。

R

stri_trans_nfkc(str) == stri_trans_nfkd(str)
#  [1]  TRUE  TRUE
#  [3]  TRUE  TRUE
#  [5]  TRUE  TRUE
#  [7] FALSE  TRUE
#  [9]  TRUE  TRUE
# [11]  TRUE  TRUE
# [13]  TRUE  TRUE
str_length(stri_trans_nfkc("ひらがな"))
# [1] 4
str_length(stri_trans_nfkd("ひらがな"))
# [1] 5

stri_trans_char()：対応する１文字ずつの置換

対応する１文字ずつを置換します。

R

# 小文字英字 -> 大文字英字
stri_trans_char(str, "abcdefghijklmnopqrstuvwxyz", "ABCDEFGHIJKLMNOPQRSTUVWXYZ")
#  [1] "ALPHABET"                       "ALPHABET"                      
#  [3] "ａｌｐｈａｂｅｔ"               "ＡＬＰＨＡＢＥＴ"              
#  [5] ".,;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ｍＬ" "50％のｴﾀﾉｰﾙ水溶液1,000MG"      

# 半角英字 -> 全角英字
stri_trans_char(str, "ABCDEFGHIJKLMNOPQRSTUVWXYZ", "ＡＢＣＤＥＦＧＨＩＪＫＬＭＮＯＰＱＲＳＴＵＶＷＸＹＺ")
#  [1] "alphabet"                       "ＡＬＰＨＡＢＥＴ"              
#  [3] "ａｌｐｈａｂｅｔ"               "ＡＬＰＨＡＢＥＴ"              
#  [5] ".,;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ｍＬ" "50％のｴﾀﾉｰﾙ水溶液1,000mg"      

# 小文字a・i・u・e・o -> 全角大文字Ａ・Ｉ・Ｕ・Ｅ・Ｏ
stri_trans_char(str, "aiueo", "ＡＩＵＥＯ")
stri_trans_char(str, "aiueo", stri_trans_general("aiueo", "halfwidth-fullwidth; upper"))
#  [1] "ＡlphＡbＥt"                    "ALPHABET"                      
#  [3] "ａｌｐｈａｂｅｔ"               "ＡＬＰＨＡＢＥＴ"              
#  [5] ".,;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１，０００ｍＬ" "50％のｴﾀﾉｰﾙ水溶液1,000mg"   

# 半角・全角カンマ -> 半角・全角アンダースコア
stri_trans_char(str, ",，", "_＿")
#  [1] "alphabet"                       "ALPHABET"                      
#  [3] "ａｌｐｈａｂｅｔ"               "ＡＬＰＨＡＢＥＴ"              
#  [5] "._;:+-*/^_~&| "                 "．＿；：＋－＊／＾＿～＆｜　"  
#  [7] "ひらがな"                       "カタカナ"                      
#  [9] "ｶﾀｶﾅ"                           "漢字"                          
# [11] "0123456789"                     "０１２３４５６７８９"          
# [13] "エタノール水溶液１＿０００ｍＬ" "50％のｴﾀﾉｰﾙ水溶液1_000mg"      

# 半角数字・カンマ -> 全角数字・カンマ
stri_trans_char(str, "0123456789,", "０１２３４５６７８９，")
stri_trans_char(str, "0123456789,", stri_trans_general("0123456789,", "halfwidth-fullwidth"))
#  [1] "alphabet"                        "ALPHABET"                       
#  [3] "ａｌｐｈａｂｅｔ"                "ＡＬＰＨＡＢＥＴ"               
#  [5] ".，;:+-*/^_~&| "                 "．，；：＋－＊／＾＿～＆｜　"   
#  [7] "ひらがな"                        "カタカナ"                       
#  [9] "ｶﾀｶﾅ"                            "漢字"                           
# [11] "０１２３４５６７８９"            "０１２３４５６７８９"           
# [13] "エタノール水溶液１，０００ｍＬ"  "５０％のｴﾀﾉｰﾙ水溶液１，０００mg"

# アラビア数字 -> 漢数字
stri_trans_char(str, "0123456789,０１２３４５６７８９，", "〇一二三四五六七八九、〇一二三四五六七八九、")
#  [1] "alphabet"                        "ALPHABET"                       
#  [3] "ａｌｐｈａｂｅｔ"                "ＡＬＰＨＡＢＥＴ"               
#  [5] ".、;:+-*/^_~&| "                 "．、；：＋－＊／＾＿～＆｜　"   
#  [7] "ひらがな"                        "カタカナ"                       
#  [9] "ｶﾀｶﾅ"                            "漢字"                           
# [11] "〇一二三四五六七八九"            "〇一二三四五六七八九"           
# [13] "エタノール水溶液一、〇〇〇ｍＬ"  "五〇％のｴﾀﾉｰﾙ水溶液一、〇〇〇mg"

stri_datetime_format()：日付フォーマット

R

## 日付
date <- stri_datetime_create(1964, 10, 10)
date
# [1] "1964-10-10 12:00:00 JST"
stri_datetime_format(date, "date_long", locale = "@calendar=japanese")
# [1] "昭和39年10月10日"
stri_datetime_format(date, "date_full", locale = "@calendar=japanese")
# [1] "昭和39年10月10日土曜日"
stri_datetime_format(date, "date_full", locale = "ja_JP@calendar=japanese")
# [1] "昭和39年10月10日土曜日"
stri_datetime_format(date, "date_full", locale = "@calendar=us")
# [1] "1964年10月10日土曜日"
stri_datetime_format(date, "date_full", locale = "@calendar=hebrew")
# [1] "AM5725年2月4日土曜日"

参考

• https://cran.r-project.org/web/packages/stringi/index.html
• https://github.com/gagolews/stringi
• https://stringi.gagolewski.com/
  • https://stringi.gagolewski.com/_static/vignette/stringi.pdf
  • R Package stringi Reference
    • https://stringi.gagolewski.com/rapi.html
    • https://stringi.gagolewski.com/rapi/stri_trans_general.html
    • https://stringi.gagolewski.com/rapi/stri_trans_casemap.html
    • https://stringi.gagolewski.com/rapi/stri_trans_nf.html
    • https://stringi.gagolewski.com/rapi/stri_trans_char.html
    • https://stringi.gagolewski.com/rapi/stri_datetime_create.html
    • https://stringi.gagolewski.com/rapi/stri_datetime_format.html
• http://userguide.icu-project.org/transforms/general
• https://r4ds.had.co.nz/strings.html#stringi