rm_tag(text.var, trim = !extract, clean = TRUE, pattern = "@rm_tag", 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_tag uses the
rm_tag regex from the regular expression dictionary from
the dictionary argument.pattern.TRUE the person tags are extracted into a
list of vectors.pattern begins with "@rm_".gsub.Remove/replace/extract person tags from a string.
The default regex pattern "(? is more liberal and
searches for the at (@) symbol followed by any word. This can be accessed
via pattern = "@rm_tag".
Twitter
user names are more constrained. A second regex
("(?) is provide that contains the
latter word to substring that begins with an at (@) followed by a word
composed of alpha-numeric characters and underscores, no longer than 15
characters. This can be accessed via pattern = "@rm_tag2" (see
Examples).
x <- c("@hadley I like #rstats for #ggplot2 work.", "Difference between #magrittr and #pipeR, both implement pipeline operators for #rstats: http://renkun.me/r/2014/07/26/difference-between-magrittr-and-pipeR.html @timelyportfolio", "Slides from great talk: @ramnath_vaidya: Interactive slides from Interactive Visualization presentation #user2014. http://ramnathv.github.io/user2014-rcharts/#1", "tyler.rinker@gamil.com is my email", "A non valid Twitter is @abcdefghijklmnopqrstuvwxyz" ) rm_tag(x)[1] "I like #rstats for #ggplot2 work." [2] "Difference between #magrittr and #pipeR, both implement pipeline operators for #rstats: http://renkun.me/r/2014/07/26/difference-between-magrittr-and-pipeR.html" [3] "Slides from great talk: : Interactive slides from Interactive Visualization presentation #user2014. http://ramnathv.github.io/user2014-rcharts/#1" [4] "tyler.rinker@gamil.com is my email" [5] "A non valid Twitter is"rm_tag(rm_hash(x))[1] "I like for work." [2] "Difference between and , both implement pipeline operators for : http://renkun.me/r/2014/07/26/difference-between-magrittr-and-pipeR.html" [3] "Slides from great talk: : Interactive slides from Interactive Visualization presentation . http://ramnathv.github.io/user2014-rcharts/#1" [4] "tyler.rinker@gamil.com is my email" [5] "A non valid Twitter is"rm_tag(x, extract=TRUE)[[1]] [1] "@hadley" [[2]] [1] "@timelyportfolio" [[3]] [1] "@ramnath_vaidya" [[4]] [1] NA [[5]] [1] "@abcdefghijklmnopqrstuvwxyz"## more restrictive Twitter regex rm_tag(x, extract=TRUE, pattern="@rm_tag2")[[1]] [1] "@hadley" [[2]] [1] "@timelyportfolio" [[3]] [1] "@ramnath_vaidya" [[4]] [1] NA [[5]] [1] NA## Remove only the @ sign rm_tag(x, replacement = "\\3")[1] "hadley I like #rstats for #ggplot2 work." [2] "Difference between #magrittr and #pipeR, both implement pipeline operators for #rstats: http://renkun.me/r/2014/07/26/difference-between-magrittr-and-pipeR.html timelyportfolio" [3] "Slides from great talk: ramnath_vaidya: Interactive slides from Interactive Visualization presentation #user2014. http://ramnathv.github.io/user2014-rcharts/#1" [4] "tyler.rinker@gamil.com is my email" [5] "A non valid Twitter is abcdefghijklmnopqrstuvwxyz"rm_tag(x, replacement = "\\3", pattern="@rm_tag2")[1] "hadley I like #rstats for #ggplot2 work." [2] "Difference between #magrittr and #pipeR, both implement pipeline operators for #rstats: http://renkun.me/r/2014/07/26/difference-between-magrittr-and-pipeR.html timelyportfolio" [3] "Slides from great talk: ramnath_vaidya: Interactive slides from Interactive Visualization presentation #user2014. http://ramnathv.github.io/user2014-rcharts/#1" [4] "tyler.rinker@gamil.com is my email" [5] "A non valid Twitter is @abcdefghijklmnopqrstuvwxyz"
gsub,
stri_extract_all_regex
Other rm_.functions: 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_number; rm_percent;
rm_phone; rm_postal_code;
rm_repeated_characters;
rm_repeated_phrases;
rm_repeated_words; rm_time;
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