rm_white(text.var, trim = FALSE, clean = FALSE, pattern = "@rm_white", replacement = "", extract = FALSE, dictionary = getOption("regex.library"), ...)rm_white_bracket(text.var, trim = !extract, clean = TRUE, pattern = "@rm_white_bracket", replacement = "", extract = FALSE, dictionary = getOption("regex.library"), ...)rm_white_colon(text.var, trim = !extract, clean = TRUE, pattern = "@rm_white_colon", replacement = "", extract = FALSE, dictionary = getOption("regex.library"), ...)rm_white_comma(text.var, trim = !extract, clean = TRUE, pattern = "@rm_white_comma", replacement = "", extract = FALSE, dictionary = getOption("regex.library"), ...)rm_white_endmark(text.var, trim = !extract, clean = TRUE, pattern = "@rm_white_endmark", replacement = "", extract = FALSE, dictionary = getOption("regex.library"), ...)rm_white_lead(text.var, trim = FALSE, clean = FALSE, pattern = "@rm_white_lead", replacement = "", extract = FALSE, dictionary = getOption("regex.library"), ...)rm_white_lead_trail(text.var, trim = FALSE, clean = FALSE, pattern = "@rm_white_lead_trail", replacement = "", extract = FALSE, dictionary = getOption("regex.library"), ...)rm_white_trail(text.var, trim = FALSE, clean = FALSE, pattern = "@rm_white_trail", replacement = "", extract = FALSE, dictionary = getOption("regex.library"), ...)rm_white_multiple(text.var, trim = !extract, clean = TRUE, pattern = "@rm_white_multiple", replacement = "", extract = FALSE, dictionary = getOption("regex.library"), ...)rm_white_punctuation(text.var, trim = !extract, clean = TRUE, pattern = "@rm_white_punctuation", 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_dollar uses the
rm_dollar regex from the regular expression dictionary from
the dictionary argument.pattern.TRUE the dollar strings are extracted into a
list of vectors.pattern begins with "@rm_".gsub.rm_white - Remove multiple white space (> 1 becomes a single white
space), white space before a comma, white space before a single or
consecutive combination of a colon, semicolon, or endmark (period, question
mark, or exclamation point), white space after a left bracket ("", "(", "[")
or before a right bracket ("", ")", "]"), leading or trailing white space.
rm_white_bracket - Remove white space after a left bracket ("", "(", "[")
or before a right bracket ("", ")", "]").
rm_white_colon - Remove white space before a single or consecutive
combination of a colon, semicolon.
rm_white_comma - Remove white space before a comma.
rm_white_endmark - Remove white space before endmark(s) (".", "?", "!").
rm_white_lead - Remove leading white space.
rm_white_lead_trail - Remove leading or trailing white space.
rm_white_trail - Remove trailing white space.
rm_white_multiple - Remove multiple white space (> 1 becomes a single
white space).
rm_white_punctuation - Remove multiple white space before a comma, white
space before a single or consecutive combination of a colon, semicolon, or
endmark (period, question mark, or exclamation point).
The rm_white_endmark/rm_white_punctuation regular expression was taken from:
http://stackoverflow.com/a/25464921/1000343
x <- c(" There is ( $5.50 ) for , me . ", " that's [ 45.6% ] of! the pizza !", " 14% is { $26 } or $25.99 ?", "Oh ; here's colon : Yippee !") rm_white(x)[1] "There is ($5.50) for, me." "that's [45.6%] of! the pizza!" "14% is {$26} or $25.99?" "Oh; here's colon: Yippee!"rm_white_bracket(x)[1] "There is ($5.50) for , me ." "that's [45.6%] of! the pizza !" "14% is {$26} or $25.99 ?" [4] "Oh ; here's colon : Yippee !"rm_white_colon(x)[1] "There is ( $5.50 ) for , me ." "that's [ 45.6% ] of! the pizza !" "14% is { $26 } or $25.99 ?" [4] "Oh; here's colon: Yippee !"rm_white_comma(x)[1] "There is ( $5.50 ) for, me ." "that's [ 45.6% ] of! the pizza !" "14% is { $26 } or $25.99 ?" [4] "Oh ; here's colon : Yippee !"rm_white_endmark(x)[1] "There is ( $5.50 ) for , me." "that's [ 45.6% ] of! the pizza!" "14% is { $26 } or $25.99?" [4] "Oh ; here's colon : Yippee!"rm_white_lead(x)[1] "There is ( $5.50 ) for , me . " "that's [ 45.6% ] of! the pizza !" "14% is { $26 } or $25.99 ?" [4] "Oh ; here's colon : Yippee !"rm_white_trail(x)[1] " There is ( $5.50 ) for , me ." " that's [ 45.6% ] of! the pizza !" " 14% is { $26 } or $25.99 ?" [4] "Oh ; here's colon : Yippee !"rm_white_lead_trail(x)[1] "There is ( $5.50 ) for , me ." "that's [ 45.6% ] of! the pizza !" "14% is { $26 } or $25.99 ?" [4] "Oh ; here's colon : Yippee !"rm_white_multiple(x)[1] "There is ( $5.50 ) for , me ." "that's [ 45.6% ] of! the pizza !" "14% is { $26 } or $25.99 ?" [4] "Oh ; here's colon : Yippee !"rm_white_punctuation(x)[1] "There is ( $5.50 ) for, me." "that's [ 45.6% ] of! the pizza!" "14% is { $26 } or $25.99?" [4] "Oh; here's colon: Yippee!"
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_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_zip
rm_white_endmark/rm_white_punctuation - stackoverflow's hwnd and Tyler Rinker