Find duplicated consecutive words in a character string or in a RMarkdown document

consecutive_duplicated_words.R

###########################################################
# Find duplicated consecutive words in a character string #
# or in a RMarkdown document                              #
# ------------------------------------------------------- #
# Written by Ladislas Nalborczyk                          #
# Contact: ladislas.nalborczyk@gmail.com                  #
# Last updated on January 2, 2023                         #
###########################################################

# loading some packages
library(tidyverse)

# example string containing duplicated consecutive and non-consecutive words
some_string <- "we recruited 46 we participants, the the participants were instructed to"

# regex solution suggested in
# https://stackoverflow.com/questions/2823016/regular-expression-for-duplicate-words
regex_string <- "\\b(\\w+)(\\s+\\1\\b)+"

# base R solution suggested in
# https://twitter.com/olivier_pucher/status/1609885216688197632?s=20&t=OvTSyvyh4aNTO8RGRZbAMg
v <- stringr::str_split(string = some_string, pattern = " ") |> unlist()
v == lag(v)

# detecting duplicated consecutive words
stringr::str_detect(string = some_string, pattern = regex_string)

# replacing duplicated consecutive words
stringr::str_extract(string = some_string, pattern = regex_string)

# extracting text from RMarkdown document
filetext <- readLines(con = "some_rmd_file.Rmd")

# testing for duplicated consecutive words
stringr::str_detect(string = filetext, pattern = regex_string)

# is there any?
stringr::str_detect(string = filetext, pattern = regex_string) |> any()

# which words?
stringr::str_extract(string = filetext, pattern = regex_string)

# where?
filetext[stringr::str_detect(string = filetext, pattern = regex_string)]