rm_email(text.var, trim = !extract, clean = TRUE, pattern = "@rm_email", 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_email
uses the
rm_email
regex from the regular expression dictionary from
the dictionary
argument.pattern
.TRUE
the emails are extracted into a list
of vectors.pattern
begins with "@rm_"
.gsub
.Remove/replace/extract email addresses from a string.
The email regular expression was taken from: http://stackoverflow.com/a/25077704/1000343
x <- paste("fred is fred@foo.com and joe is joe@example.com - but @this is a twitter handle for twit@here.com or foo+bar@google.com/fred@foo.fnord") x2 <- c("fred is fred@foo.com and joe is joe@example.com - but @this is a", "twitter handle for twit@here.com or foo+bar@google.com/fred@foo.fnord", "hello world") rm_email(x)[1] "fred is and joe is - but @this is a twitter handle for or /"rm_email(x, replacement = '<a href="mailto:\\1" target="_blank">\\1</a>')[1] "fred is <a href=\"mailto:fred@foo.com\" target=\"_blank\">fred@foo.com</a> and joe is <a href=\"mailto:joe@example.com\" target=\"_blank\">joe@example.com</a> - but @this is a twitter handle for <a href=\"mailto:twit@here.com\" target=\"_blank\">twit@here.com</a> or <a href=\"mailto:foo+bar@google.com\" target=\"_blank\">foo+bar@google.com</a>/<a href=\"mailto:fred@foo.fnord\" target=\"_blank\">fred@foo.fnord</a>"rm_email(x, extract=TRUE)[[1]] [1] "fred@foo.com" "joe@example.com" "twit@here.com" "foo+bar@google.com" "fred@foo.fnord"rm_email(x2, extract=TRUE)[[1]] [1] "fred@foo.com" "joe@example.com" [[2]] [1] "twit@here.com" "foo+bar@google.com" "fred@foo.fnord" [[3]] [1] NA
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_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