如何编写兼容多tibble的硬编码名称标准化函数？

问题原因 #

原函数处理向量输入时，filter条件会触发R的向量循环广播机制：当输入名字的数量（如tibble_a的2个）与字典行数（3行）不成倍数时，就会抛出「longer object length is not a multiple of shorter object length」警告。此外，若出现多个匹配项，返回结果长度可能与输入不一致，导致mutate无法正常执行。

解决方案1：逐个处理输入（纯函数风格） #

用purrr::map_chr遍历每个输入名字，确保返回结果长度与输入完全一致，同时处理无匹配的情况：

library(tidyverse)

name_standardizer <- function(incoming_name){
  hardcoded_dictionary <-
    tribble(~incorrect_name, ~correct_name,
            "Fries, french", "French fries",
            "Hamborgar", "Hamburger",
            "Burger", NA) |> 
    fill(correct_name)
  
  map_chr(incoming_name, ~{
    # 针对单个名字查询字典
    match_result <- hardcoded_dictionary |> 
      filter(incorrect_name == .x | correct_name == .x) |> 
      pull(correct_name)
    
    # 取第一个匹配结果，无匹配则返回原名字（可改为NA）
    first(match_result) %||% .x
  })
}

使用示例 #

# 处理tibble_a
tibble_a_with_ids_written_well <- tibble_a_with_IDs_written_incorrectly |> 
  mutate(id = name_standardizer(id))

# 处理tibble_c
tibble_c_with_ids_written_incorrectly |> 
  mutate(id = name_standardizer(id))

# 执行连接
tibble_a_with_ids_written_well |> left_join(tibble_b, by = "id")

解决方案2：基于left_join的tidyverse风格实现 #

直接针对tibble操作，通过两次连接匹配字典的incorrect_name和correct_name，确保每行都能得到正确的标准化结果：

library(tidyverse)

# 定义全局字典（也可放在函数内部）
name_dictionary <- tribble(~incorrect_name, ~correct_name,
                           "Fries, french", "French fries",
                           "Hamborgar", "Hamburger",
                           "Burger", NA) |> 
  fill(correct_name)

name_standardizer <- function(df, id_col = id){
  id_col <- enquo(id_col)
  col_name <- quo_name(id_col)
  
  df |> 
    # 先匹配错误名称
    left_join(name_dictionary, by = set_names("incorrect_name", col_name)) |> 
    # 再匹配正确名称（避免输入已经是标准化名称的情况）
    left_join(name_dictionary, by = set_names("correct_name", col_name), suffix = c("", "_from_correct")) |> 
    # 合并匹配结果，优先取错误名称匹配到的结果，无匹配则保留原名称
    mutate(standardized_id = coalesce(correct_name, correct_name_from_correct, !!id_col)) |> 
    select(-correct_name, -correct_name_from_correct) |> 
    rename(!!col_name := standardized_id)
}

使用示例 #

# 处理tibble_a
tibble_a_with_ids_written_well <- tibble_a_with_IDs_written_incorrectly |> name_standardizer()

# 处理tibble_c
tibble_c_with_ids_written_incorrectly |> name_standardizer()

内容的提问来源于stack exchange，提问作者sas