rm_emoticon(text.var, trim = !extract, clean = TRUE, pattern = "@rm_emoticon", replacement = "", extract = FALSE, dictionary = getOption("regex.library"), ...)
TRUE removes leading and trailing white
spaces.TRUE extra white spaces and escaped
character will be removed.fixed = TRUE) to be matched in the given
character vector. Default, @rm_emoticon uses the
rm_emoticon regex from the regular expression dictionary from
the dictionary argument.pattern.TRUE the emoticons are extracted into a
list of vectors.pattern begins with "@rm_".gsub.Remove/replace/extract common emoticons from a string.
x <- c("are :-)) it 8-D he XD on =-D they :D of :-) is :> for :o) that :-/", "as :-D I xD with :^) a =D to =) the 8D and :3 in =3 you 8) his B^D was") rm_emoticon(x)[1] "are it he on they of is for that" "as I with a to the and in you his was"rm_emoticon(x, extract=TRUE)[[1]] [1] ":-))" "8-D" "XD" "=-D" ":D" ":-)" ":>" ":o)" ":-/" [[2]] [1] ":-D" "xD" ":^)" "=D" "=)" "8D" ":3" "=3" "8)" "B^D"
gsub,
stri_extract_all_regex
Other rm_.functions: as_numeric,
as_numeric2, rm_number;
as_time, as_time2,
rm_time, rm_transcript_time;
rm_abbreviation; rm_angle,
rm_bracket,
rm_bracket_multiple,
rm_curly, rm_round,
rm_square; rm_between,
rm_between_multiple;
rm_caps_phrase; rm_caps;
rm_citation_tex; rm_citation;
rm_city_state_zip;
rm_city_state; rm_date;
rm_default; rm_dollar;
rm_email; rm_endmark;
rm_hash; rm_nchar_words;
rm_non_ascii; rm_non_words;
rm_percent; rm_phone;
rm_postal_code;
rm_repeated_characters;
rm_repeated_phrases;
rm_repeated_words; rm_tag;
rm_title_name;
rm_twitter_url, rm_url;
rm_white, rm_white_bracket,
rm_white_colon,
rm_white_comma,
rm_white_endmark,
rm_white_lead,
rm_white_lead_trail,
rm_white_multiple,
rm_white_punctuation,
rm_white_trail; rm_zip