如果有连续3个单词的regex

> x <- c("1. Stack is great and awesome", "2. Stack")
> regmatches(x, regexpr("[A-Za-z]+(?:\\s+[A-Za-z]+){0,2}", x))
[1] "Stack is great" "Stack"
## Or to support all Unicode letters
> y <- c("1. Stąck is great and awesome", "2. Stack")
> regmatches(y, regexpr("\\p{L}+(?:\\s+\\p{L}+){0,2}", y, perl=TRUE))
[1] "Stąck is great" "Stack"
## In some R environments, it makes sense to use another, TRE, regex:
> regmatches(y, regexpr("[[:alpha:]]+(?:[[:space:]]+[[:alpha:]]+){0,2}", x))
[1] "Stąck is great" "Stack"

regex demo online R demo regex demo

{0,2} {1,2}

gregexpr regexpr

• \\p{L}+ [A-Za-z]
• (?:\\s+\\p{L}+){0,2} (?:\\s+[a-zA-Z]+){0,2}
  • \\s+

perl=TRUE \p{L} (*UCP)

stringr::str_extract stringr::str_extract_all

> str_extract(x, "\\p{L}+(?:\\s+\\p{L}+){0,2}")
[1] "Stack is great" "Stack"         
> str_extract(x, "[a-zA-Z]+(?:\\s+[a-zA-Z]+){0,2}")
[1] "Stack is great" "Stack"         
> str_extract(x, "[[:alpha:]]+(?:\\s+[[:alpha:]]+){0,2}")
[1] "Stack is great" "Stack" 

stringr

> str_extract(y, "\\p{L}+(?:\\s+\\p{L}+){0,2}")
[1] "Stąck iç great" "Stack"         
> str_extract(y, "[[:alpha:]]+(?:\\s+[[:alpha:]]+){0,2}")
[1] "Stąck iç great" "Stack"