rm_non_ascii(text.var, trim = !extract, clean = TRUE, pattern = "@rm_non_ascii", replacement = "", extract = FALSE, dictionary = getOption("regex.library"), ascii.out = TRUE, ...)
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_non_ascii uses the
rm_non_ascii regex from the regular expression dictionary from
the dictionary argument. If extract = FALSE
gsub is not used as with other rm_XXX functions,
rather iconv with the sub argument set is used to
conduct the subbing.pattern.TRUE the all non-ASCII strings are extracted
into a list of vectors.pattern begins with "@rm_".TRUE output is given in non-ASCII format,
otherwise "byte" is used.Remove/replace/extract non-ASCII substring from a string. This is the template used by
other qdapRegex rm_XXX functions.
iconv is used within rm_non_ascii.
iconv's behavior across operating systems may not be
consistent.
The email regular expression was taken from: http://stackoverflow.com/a/25469131/1000343
x <- c("Hello World", "Ekstr\xf8m", "J\xf6reskog", "bi\xdfchen Z\xfcrcher") Encoding(x) <- "latin1" x[1] "Hello World" "Ekstrøm" "Jöreskog" "bißchen Zürcher"rm_non_ascii(x)[1] "Hello World" "Ekstrm" "Jreskog" "bichen Zrcher"rm_non_ascii(x, replacement="<<FLAG>>")[1] "Hello World" "Ekstr<<FLAG>>m" "J<<FLAG>>reskog" "bi<<FLAG>>chen Z<<FLAG>>rcher"rm_non_ascii(x, extract=TRUE)[[1]] [1] NA [[2]] [1] "<f8>" [[3]] [1] "<f6>" [[4]] [1] "<df>" "<fc>"rm_non_ascii(x, extract=TRUE, ascii.out=FALSE)[[1]] [1] NA [[2]] [1] "ø" [[3]] [1] "ö" [[4]] [1] "ß" "ü"
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_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