fixed the non-ASCII code

.Rhistory

@@ -1,25 +1,3 @@
-library(regioncode)
-library(regioncode)
-knitr::opts_chunk$set(message = FALSE, warning = FALSE)
-# Full, official names
-corruption$prefecture
-regioncode(data_input = corruption$prefecture,
-convert_to = "name",
-year_from = 2019,
-year_to = 1989,
-incomplete_name = "to")
-regioncode(data_input = corruption$prefecture,
-year_from = 2019,
-year_to = 1999,
-convert_to="area")
-library(regioncode)
-library(regioncode)
-knitr::opts_chunk$set(message = FALSE, warning = FALSE)
-regioncode(data_input = corruption$prefecture,
-year_from = 2019,
-year_to = 1989,
-to_dialect = "dia_group")
-regioncode(data_input = corruption$prefecture,
 year_from = 2019,
 year_to = 1989,
 to_dialect = "sub_dia_group")
@@ -510,3 +488,25 @@ regioncode(data_input = corruption$prefecture_id,
 convert_to = "name", # default setting
 year_from = 2019,
 year_to = 1989)
+?switch
+?case_when
+`%>%`
+?`%>%`
+library(regioncode)
+?bind_rows
+library(regioncode)
+knitr::opts_chunk$set(message = FALSE, warning = FALSE)
+if(!require(regioncode)) install.packages("regioncode")
+library(regioncode)
+library(tidyverse)
+# Regions with special spelling
+regioncode(data_input = c("山西", "陕西", "内蒙古", "香港", "澳门"),
+year_from = 2019,
+year_to = 2008,
+convert_to = "name",
+incomplete_name = TRUE,
+province = TRUE,
+to_pinyin = TRUE
+)
+?ends_with
+?pull

.Rproj.user/shared/notebooks/paths

@@ -1,3 +1 @@
-/home/sammo3182/Seafile/WW_research/01_Research/R_package/regioncode/DESCRIPTION="9D98CAD9"
-/home/sammo3182/Seafile/WW_research/01_Research/R_package/regioncode/R/regioncode.R="999BE19B"
-/home/sammo3182/Seafile/WW_research/01_Research/R_package/regioncode/vignettes/regioncode-vignette.Rmd="B320A102"
+/home/sammo3182/Seafile/WW_research/01_Research/R_package/regioncode/vignettes/regioncode-vignette.Rmd="04B918E1"

DESCRIPTION

@@ -1,32 +1,30 @@
-Package: regioncode
-Title: Convert Region Names and Division Codes of China Over Years
-Version: 0.1.2
-Authors@R: 
-    c(person(given = "Yue",family = "Hu",role = c("aut","cre"), email = "yuehu@tsinghua.edu.cn"),
-    person(given = "Xinyi",family = "Ye",role = c("aut"), email = "yexy23@mails.tsinghua.edu.cn"),
-    person(given = "Yufei",family = "Sun",role = c("aut"), email = "sunyf20@mails.tsinghua.edu.cn"),
-    person(given = "Wenquan",family = "Wu",role = c("aut"), email = "gohuntsuan@gmail.com"))
-Author: Yue Hu [aut, cre],
-  Xinyi Ye [aut],
-  Yufei Sun [aut],
-  Wenquan Wu [aut]
-Maintainer: Yue Hu <yuehu@tsinghua.edu.cn>
-Description: A tool to conquer the difficulties to convert various region names and administration division codes of Chinese regions. The current version enables seamlessly converting Chinese regions' formal names, common-used names, and codes between each other at the city level from 1986 to 2019.
-License: MIT + file LICENSE
-Encoding: UTF-8
-BugReports: https://github.com/sammo3182/regioncode/issues
-Depends:
-  R(>= 3.6.0)
-Imports:
-  dplyr,
-  pinyin,
-  tidyverse
-Suggests:
-    testthat (>= 3.0.0),
-    rmarkdown,
-    knitr
-LazyData: true
-Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.1
-Config/testthat/edition: 3
-VignetteBuilder: knitr
+Package: regioncode
+Title: Convert Region Names and Division Codes of China Over Years
+Version: 0.1.2
+Authors@R: 
+    c(person(given = "Yue",family = "Hu",role = c("aut","cre"), email = "yuehu@tsinghua.edu.cn"),
+    person(given = "Xinyi",family = "Ye",role = c("aut"), email = "yexy23@mails.tsinghua.edu.cn"),
+    person(given = "Yufei",family = "Sun",role = c("aut"), email = "sunyf20@mails.tsinghua.edu.cn"),
+    person(given = "Wenquan",family = "Wu",role = c("aut"), email = "gohuntsuan@gmail.com"))
+Author: Yue Hu [aut, cre],
+  Xinyi Ye [aut],
+  Yufei Sun [aut],
+  Wenquan Wu [aut]
+Maintainer: Yue Hu <yuehu@tsinghua.edu.cn>
+Description: A tool to conquer the difficulties to convert various region names and administration division codes of Chinese regions. The current version enables seamlessly converting Chinese regions' formal names, common-used names, and codes between each other at the city level from 1986 to 2019.
+License: MIT + file LICENSE
+Encoding: UTF-8
+BugReports: https://github.com/sammo3182/regioncode/issues
+Depends:
+  R(>= 3.6.0)
+Imports:
+  dplyr,
+  pinyin
+Suggests:
+    rmarkdown,
+    knitr
+LazyData: true
+Roxygen: list(markdown = TRUE)
+RoxygenNote: 7.3.1
+Config/testthat/edition: 3
+VignetteBuilder: knitr

NAMESPACE

@@ -3,4 +3,3 @@
 export(regioncode)
 import(dplyr)
 import(pinyin)
-import(tidyverse)

R/regioncode.R

@@ -28,9 +28,8 @@
 #'
 #' @returns The function returns a character or numeric vector depending on what method is specified.
 #'
-#' @import dplyr
 #' @import pinyin
-#' @import tidyverse
+#' @import dplyr
 #'
 #' @examples
 #'
@@ -307,7 +306,7 @@ regioncode <- function(data_input,
         region_province <- region_province[, order(colnames(region_province))]
 
 
-        region_data<- bind_rows(region_zhixiashi, region_province)
+        region_data <- bind_rows(region_zhixiashi, region_province)
       }
     }
   }
@@ -333,31 +332,17 @@ regioncode <- function(data_input,
     pull(!!year_to)
 
   # Because '2pinyin' can not be used as a variable name
+
   if (to_pinyin) {
-    if (is.character(data_output)) {
-      data_output <-
-        ifelse(
-          data_output == "\\u9655\\u897f", "shaan_xi",
-          ifelse(
-            data_output == "\\u9655\\u897f\\u7701", "shaan_xi_sheng",
-            ifelse(
-              data_output ==  "\\u5185\\u8499\\u53e4", "inner_mongolia",
-              ifelse(
-                data_output =="\\u897f\\u85cf", "tibet",
-                ifelse(
-                  data_output == "\\u6fb3\\u95e8", "macao",
-                  ifelse(
-                    data_output == "\\u9999\\u6e2f", "hong_kong",
-                    py(char = data_output,
-                       dic = pydic(method = "toneless", dic = "pinyin2")
-                    )
-                  )
-                )
-              )
-            )
-          )
-        )
-    }
+    data_output <- case_when(
+      substr(data_output, start = 1, stop = 2) == "\u9655\u897f" ~ "shaan_xi",
+      substr(data_output, start = 1, stop = 2) == "\u5185\u8499" ~ "inner_mongolia",
+      substr(data_output, start = 1, stop = 2) == "\u897f\u85cf" ~ "tibet",
+      substr(data_output, start = 1, stop = 2) == "\u6fb3\u95e8" ~ "macao",
+      substr(data_output, start = 1, stop = 2) == "\u9999\u6e2f" ~ "hong_kong",
+      TRUE ~ py(char = substr(data_output, start = 1, stop = 2), dic = pydic(method = "toneless", dic = "pinyin2"))
+    )
   }
+
   return(data_output)  }
 

vignettes/regioncode-vignette.Rmd

@@ -23,7 +23,7 @@ knitr::opts_chunk$set(message = FALSE, warning = FALSE)
 
 if(!require(regioncode)) install.packages("regioncode")
 library(regioncode)
-library(tidyverse)
+library(dplyr)
 ```
 
 The term "city" in China encompasses a multifaceted concept. 
@@ -154,7 +154,7 @@ fake_incomplete <- corruption$prefecture
 index_incomplete <- sample(seq(length(corruption$prefecture)), 7)
 
 fake_incomplete[index_incomplete] <- fake_incomplete[index_incomplete] |> 
-  str_sub(end = 2)
+  substr(start = 1, stop = 2)
 
 fake_incomplete