rm_abbreviation(text.var, trim = !extract, clean = TRUE, pattern = "@rm_abbreviation", 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_abbreviation uses the
rm_abbreviation regex from the regular expression dictionary from
the dictionary argument.pattern.TRUE the abbreviations are extracted into a
list of vectors.pattern begins with "@rm_".gsub.Remove/replace/extract abbreviations from a string containing lower case or capital letters followed by a period and then an optional space (this must be repeated 2 or more times).
x <- c("I want $2.33 at 2:30 p.m. to go to A.n.p.", "She will send it A.S.A.P. (e.g. as soon as you can) said I.", "Hello world.", "In the U. S. A.") rm_abbreviation(x)[1] "I want $2.33 at 2:30 to go to" "She will send it ( as soon as you can) said I." [3] "Hello world." "In the"rm_abbreviation(x, extract=TRUE)[[1]] [1] "p.m." "A.n.p." [[2]] [1] "A.S.A.P." "e.g." [[3]] [1] NA [[4]] [1] "U. S. A."
gsub,
stri_extract_all_regex
Other rm_.functions: as_numeric,
as_numeric2, rm_number;
as_time, as_time2,
rm_time, rm_transcript_time;
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_emoticon;
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