rm_city_state_zip(text.var, trim = !extract, clean = TRUE, pattern = "@rm_city_state_zip", 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_city_state_zip uses the
rm_city_state_zip regex from the regular expression dictionary from
the dictionary argument.pattern.TRUE the city, state, & zip are extracted into a
list of vectors.pattern begins with "@rm_".gsub.Remove/replace/extract city (single lower case word or multiple consecutive capitalized words before a comma and state) + state (2 consecutive capital letters) + zip code (5 digits or 5 + 4 digits) from a string.
x <- paste0("I went to Washington Heights, NY 54321 for food! ", "It's in West ven,PA 12345, near Bolly Bolly Bolly, CA12345-1234!", "hello world") rm_city_state_zip(x)[1] "I went to for food! It's in West , near !hello world"rm_city_state_zip(x, extract=TRUE)[[1]] [1] "Washington Heights, NY 54321" "ven,PA 12345" "Bolly Bolly Bolly, CA12345-1234"
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; 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