Last active
April 17, 2019 18:46
-
-
Save bschneidr/b436919b600ec9294763fe1663360245 to your computer and use it in GitHub Desktop.
Visualize bad text with RStudio viewer
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
example_strings <- c("Heres the sentince", "Here's anothr") | |
highlight_bad_text <- function(strings, match = NA) { | |
bad_text <- hunspell::hunspell(text = as.character(strings), | |
format = "text", | |
dict = hunspell::dictionary("en_us"), | |
ignore = hunspell::en_stats) | |
names(bad_text) <- names(strings) | |
highlights <- vector(mode = 'list', length = length(strings)) | |
names(highlights) <- names(strings) | |
index <- 1L | |
while (index <= length(highlights)) { | |
string <- strings[index] | |
pattern <- bad_text[[index]] | |
loc <- stringr::str_locate_all(string, pattern) | |
string_list <- Map(loc = loc, string = string, function(loc, | |
string) { | |
if (nrow(loc) == 0) | |
return(string) | |
for (i in rev(seq_len(nrow(loc)))) { | |
stringr::str_sub(string, loc[i, , drop = FALSE]) <- paste0("<span class='match'>", | |
stringr::str_sub(string, loc[i, , drop = FALSE]), "</span>") | |
} | |
string | |
}) | |
string <- unlist(string_list) | |
highlights[[index]] <- string | |
index <- index + 1L | |
} | |
highlights | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment