In stefanocoretta/phonetisr: A Naive IPA Tokeniser

knitr::opts_chunk$set(echo = TRUE)
knitr::opts_knit$set(root.dir = here::here())
library(tidyverse)
library(rvest)

source <- "https://en.wiktionary.org/wiki/Appendix:Klingon_Swadesh_list"

kl_swadesh <- read_html(source) %>%
  html_nodes("table") %>%
  .[1] %>%
  html_table(fill = TRUE) %>%
  .[[1]] %>%
  rename(
    id = No.,
    gloss = English,
    translit = KlingontlhIngan
  )

to_ipa <- function(spell) {
  str_replace_all({{spell}}, c(
    "tlh" = "T",
    "ch" = "C",
    "gh" = "ɣ",
    "ng" = "ŋ",
    "p" = "pʰ",
    "t" = "tʰ",
    "q" = "qʰ",
    "'" = "ʔ",
    "T" = "tɬ",
    "C" = "tʃ",
    "D" = "ɖ",
    "Q" = "qχ",
    "j" = "dʒ",
    "S" = "ʂ",
    "H" = "x",
    "y" = "j",
    "I" = "ɪ",
    "e" = "ɛ",
    "a" = "ɑ"
    )
  )
}

kl_swadesh <- kl_swadesh %>%
  mutate(
    ipa = to_ipa(translit),
    ipa = str_split(ipa, ", ")
  ) %>%
  filter(translit != "", gloss != "with") %>%
  unnest(cols = ipa)

attr(kl_swadesh, "source") <- source
attr(kl_swadesh, "scrape-data") <- Sys.Date()

usethis::use_data(kl_swadesh, overwrite = TRUE)

stefanocoretta/phonetisr documentation built on June 2, 2025, 2:06 a.m.