options(warn=-1)
library(gutenbergr)
library(tidyverse)

1. Loi de zipf

1.1. Motivation

a brief history and account

1.2. Choisir 3 auteurs de 3 langues différentes

# https://www.tidytextmining.com/tfidf.html
# German
german <- gutenberg_metadata %>%
  filter(title == "Die Leiden des jungen Werther") %>% filter(language == "de")
# English
english <- gutenberg_metadata %>%
  filter(title == "Wuthering Heights") %>% filter(language == "en")
# French
french <- gutenberg_metadata %>%
  filter(title == "Madame Bovary") %>% filter(language == "fr")

books.ids <- c(german$gutenberg_id,english$gutenberg_id,french.id <- french$gutenberg_id)
names(books.ids) <- c("Die Leiden des jungen Werther","Wuthering Heights","Madame Bovary")

# charger les trois textes de manière interactive
question1 <- function(ids) {

}

books <- rbind(english,french,german)

books

A tibble: 3 × 8

gutenberg_id	title	author	gutenberg_author_id	language	gutenberg_bookshelf	rights	has_text
<int>	<chr>	<chr>	<int>	<chr>	<chr>	<chr>	<lgl>
768	Wuthering Heights	Brontë, Emily	405	en	Gothic Fiction/Movie Books/Best Books Ever Listings	Public domain in the USA.	TRUE
14155	Madame Bovary	Flaubert, Gustave	574	fr	Best Books Ever Listings/FR Littérature/Banned Books from Anne Haight's list	Public domain in the USA.	TRUE
19794	Die Leiden des jungen Werther	Goethe, Johann Wolfgang von	586	de	Harvard Classics	Public domain in the USA.	TRUE

1.3. Colle les éléments du vecteur texte en un vecteur de caractères de longueur 1

# english.book = gutenberg_download(768)
english.text = english.book$text
english.text <- paste(english.text, collapse=" ")

# english.text

|2021-02-20\_18-02-10.png|

|2021-03-08\_16-48-55.png|