rm_default(text.var, trim = !extract, clean = TRUE, pattern, 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.pattern.TRUE the strings are extracted into a list
of vectors.pattern begins with "@rm_".gsub.Remove/replace/extract substring from a string. This is the template used by
other qdapRegex rm_XXX functions.
## Built in regex dictionary rm_default("I live in Buffalo, NY 14217", pattern="@rm_city_state_zip")[1] "I live in"## User defined regular expression pat <- "(\\s*([A-Z][\\w-]*)+),\\s([A-Z]{2})\\s(?<!\\d)\\d{5}(?:[ -]\\d{4})?\\b" rm_default("I live in Buffalo, NY 14217", pattern=pat)[1] "I live in"
rm_,
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_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