rm_phone(text.var, trim = !extract, clean = TRUE, pattern = "@rm_phone", 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_phone
uses the
rm_phone
regex from the regular expression dictionary from
the dictionary
argument.pattern
.TRUE
the phone numbers are extracted into a
list of vectors.pattern
begins with "@rm_"
.gsub
.Remove/replace/extract phone numbers from a string.
The phone regular expression was taken from: http://stackoverflow.com/a/21008254/1000343
x <- c(" Mr. Bean bought 2 tickets 2-613-213-4567 or 5555555555 call either one", "43 Butter Rd, Brossard QC K0A 3P0 - 613 213 4567", "Please contact Mr. Bean (613)2134567", "1.575.555.5555 is his #1 number", "7164347566", "I like 1234567 dogs" ) rm_phone(x)[1] "Mr. Bean bought 2 tickets 2- or call either one" "43 Butter Rd, Brossard QC K0A 3P0 -" [3] "Please contact Mr. Bean" "is his #1 number" [5] "" "I like 1234567 dogs"rm_phone(x, extract=TRUE)[[1]] [1] "613-213-4567" "5555555555" [[2]] [1] "613 213 4567" [[3]] [1] "(613)2134567" [[4]] [1] "1.575.555.5555" [[5]] [1] "7164347566" [[6]] [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_email
; rm_emoticon
;
rm_endmark
; rm_hash
;
rm_nchar_words
; rm_non_ascii
;
rm_non_words
; rm_percent
;
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