x <- c("vp_id","man_id","min_A_d","min_B_d","count_n",
"type_c","birth_d","gender_c","age_n","hist_y")
x[grep("_(id)|c$", x)]
[1] "vp_id" "man_id" "type_c" "gender_c"
Get rid of everything but the digits:
x <- c("485.2.362.q", "222-445", "889 99 8")
gsub(pattern="[[:punct:]]|[[:alpha:]]|[[:blank:]]", replacement="", x)
gsub(pattern="[^0-9]", x=x, replacement="")
gsub(pattern="[^[:digit:]]", x=x, replacement="")
Extract uppercase words from the beginning of a string following the idea "delete everything which is not uppercase words":
x <- c("RONALD AYLMER Fisher", "CHARLES Pearson", "John Tukey")
sapply(x, function(x) StrTrim(sub(
pattern=sub(pattern="^[A-ZÄÜÖ -]+\\b\\W+\\b", repl="", x=x)
, repl="", x, fixed=TRUE)))
... and the fine link:
http://www.powerbasic.com/support/help/pbcc/regexpr_statement.htm
Keine Kommentare:
Kommentar veröffentlichen