avar_borrowings_in_andic.R

library(tidyverse)
library(tidytext)
avar <- read_csv("avar_dict.csv")

avar |> 
  select(lemma) |> 
  unnest_characters(input = "lemma", output = "chars") |> 
  distinct(chars) |> 
  arrange(chars) |> 
  pull(chars)

avar |> 
  mutate(borrowing = "avar",
         lemma = tolower(lemma),
         lemma = str_remove_all(lemma, "[~-]"),
         lemma = str_remove_all(lemma, "/"),
         lemma = str_replace_all(lemma, "á", "а"),
         lemma = str_replace_all(lemma, "é", "е"),
         lemma = str_replace_all(lemma, "ó", "о"),
         lemma = str_replace_all(lemma, "ý", "у"),
         lemma = str_replace_all(lemma, "ѝ", "и"),
         lemma = str_replace_all(lemma, "я", "йа"),
         lemma = str_replace_all(lemma, "я́", "йа"),
         lemma = str_replace_all(lemma, "ё", "йо"),
         lemma = str_replace_all(lemma, "i", "I"),
         lemma = str_replace_all(lemma, "і", "I")) |> 
  select(lemma, meaning_ru, borrowing)  ->
  avar_word_list
  

andi <- read_csv("andic_dicts.csv")

andi |> 
  mutate(lemma = tolower(lemma),
         lemma = str_remove_all(lemma, "[̄̀́̅~'-<=|]"),
         lemma = str_remove_all(lemma, "/"),
         lemma = str_replace_all(lemma, "á", "а"),
         lemma = str_replace_all(lemma, "é", "е"),
         lemma = str_replace_all(lemma, "ó", "о"),
         lemma = str_replace_all(lemma, "ý", "у"),
         lemma = str_replace_all(lemma, "ѝ", "и"),
         lemma = str_replace_all(lemma, "я", "йа"),
         lemma = str_replace_all(lemma, "я́", "йа"),
         lemma = str_replace_all(lemma, "ё", "йо"),
         lemma = str_replace_all(lemma, "i", "I"),
         lemma = str_replace_all(lemma, "і", "I")) |> 
  select(lemma, morphology, meaning_ru, glottocode) |> 
  left_join(avar_word_list, 
            relationship = "many-to-many") |> 
  filter(!is.na(borrowing),
         glottocode %in% c("cham1309", "andi1255")) |> 
  select(-borrowing) |> 
  writexl::write_xlsx("4jesse.xlsx")