rm_date(text.var, trim = !extract, clean = TRUE, pattern = "@rm_date", 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 (see Details for additional information). Default,
@rm_date uses the rm_date regex from the regular expression
dictionary from the dictionary argument.pattern.TRUE the dates are extracted into a
list of vectors.pattern begins with "@rm_".gsub.Remove/replace/extract dates from a string in the form of (1) XX/XX/XXXX, XX/XX/XX, XX-XX-XXXX, XX-XX-XX, XX.XX.XXXX, or XX.XX.XX OR (2) March XX, XXXX or Mar XX, XXXX OR (3) both forms.
The default regular expression used by rm_date finds numeric
representations not word/abbreviations. This means that
"June 13, 2002" is not matched. This behavior can be altered (to
include month names/abbreviations) by using a secondary regular expression
from the regex_usa data (or other dictionary) via
(pattern = "@rm_date2", pattern = "@rm_date3", or
pattern = "@rm_date4"). See
Examples for example usage.
## Numeric Date Representation x <- paste0("Format dates as 04/12/2014, 04-12-2014, 04.12.2014. or", " 04/12/14 but leaves mismatched: 12.12/2014") rm_date(x)[1] "Format dates as , , . or but leaves mismatched: 12.12/2014"rm_date(x, extract=TRUE)[[1]] [1] "04/12/2014" "04-12-2014" "04.12.2014" "04/12/14"## Word/Abbreviation Date Representation x2 <- paste0("Format dates as Sept 09, 2002 or October 22, 1887", "but not 04-12-2014 and may match good 00, 9999") rm_date(x2, pattern="@rm_date2")[1] "Format dates as or but not 04-12-2014 and may match"rm_date(x2, pattern="@rm_date2", extract=TRUE)[[1]] [1] "Sept 09, 2002" "October 22, 1887" "good 00, 9999"## Year-Month-Day Representation x3 <- sprintf("R uses time in this format %s.", Sys.time()) rm_date(x3, pattern="@rm_date3")[1] "R uses time in this format 13:10:12."## Grab all types rm_date(c(x, x2, x3), pattern="@rm_date4", extract=TRUE)[[1]] [1] "04/12/2014" "04-12-2014" "04.12.2014" "04/12/14" [[2]] [1] "Sept 09, 2002" "October 22, 1887" "04-12-2014" "good 00, 9999" [[3]] [1] "2015-08-16"
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_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