R语言字符串 #

s1 <- "Hello, World!"
s2 <- 'Hello, World!'

class(s1)
nchar(s1)

s1 <- "Hello\nWorld"
cat(s1)

s2 <- "Tab\there"
cat(s2)

s3 <- "Quote: \"Hello\""
cat(s3)

s4 <- "Backslash: \\"
cat(s4)

s <- r"(C:\Users\name\file.txt)"
print(s)

fruits <- c("apple", "banana", "cherry")
length(fruits)
nchar(fruits)

paste("Hello", "World")
paste("Hello", "World", sep = "-")
paste("Hello", "World", sep = "")

paste0("Hello", "World")
paste0("A", 1:5)

fruits <- c("apple", "banana", "cherry")
paste(fruits, collapse = ", ")
paste(fruits, 1:3, sep = "-")

sprintf("Hello, %s!", "World")
sprintf("Value: %.2f", 3.14159)
sprintf("%s is %d years old", "Tom", 25)

s <- "Hello, World!"

substr(s, 1, 5)
substr(s, 8, 13)
substr(s, 1, 1) <- "h"
print(s)

s <- "Hello, World!"

substring(s, 1)
substring(s, 1, 5)
substring(s, c(1, 8), c(5, 13))

s <- "apple,banana,cherry"
strsplit(s, ",")

s <- "Hello World"
strsplit(s, " ")

fruits <- c("apple", "banana", "cherry", "apricot")

grep("ap", fruits)
grep("ap", fruits, value = TRUE)
grepl("ap", fruits)

s <- "apple banana apple"
regexpr("apple", s)
gregexpr("apple", s)

s <- "Hello, World!"
pos <- regexpr("World", s)
attr(pos, "match.length")

s <- "apple banana apple"
sub("apple", "orange", s)

s <- "apple banana apple"
gsub("apple", "orange", s)

s <- "Hello, World!"
chartr("aeiou", "AEIOU", s)

s <- "Hello, World!"

toupper(s)
tolower(s)

library(stringr)
str_to_title("hello world")

s <- "  Hello, World!  "

trimws(s)
trimws(s, "left")
trimws(s, "right")

s <- "Hello"

str_pad(s, 10, side = "left")
str_pad(s, 10, side = "right")
str_pad(s, 10, side = "both")

s1 <- "Hello"
s2 <- "hello"

s1 == s2
identical(s1, s2)

s1 <- "Hello"
s2 <- "hello"

tolower(s1) == tolower(s2)

fruits <- c("banana", "Apple", "cherry")
sort(fruits)
sort(fruits, decreasing = TRUE)

s <- "Hello, World!"
nchar(s)

fruits <- c("apple", "banana", "cherry")
nchar(fruits)

s1 <- "Hello"
s2 <- ""

nzchar(s1)
nzchar(s2)

s <- "apple123 banana456"

grep("[0-9]+", s, value = TRUE)
grep("[a-z]+", s, value = TRUE)

emails <- c("test@example.com", "invalid", "user@domain.org")

grep("^[a-zA-Z0-9]+@[a-zA-Z0-9]+\\.[a-zA-Z]+$", emails, value = TRUE)

phones <- c("123-456-7890", "1234567890", "123 456 7890")
gsub("[^0-9]", "", phones)

install.packages("stringr")
library(stringr)

s <- "Hello, World!"

str_length(s)
str_sub(s, 1, 5)
str_to_upper(s)
str_to_lower(s)
str_trim("  Hello  ")
str_pad("Hello", 10)

s <- c("apple", "banana", "cherry")

str_detect(s, "a")
str_count(s, "a")
str_locate(s, "a")
str_extract(s, "a.+")
str_replace(s, "a", "A")
str_replace_all(s, "a", "A")

is_valid_email <- function(email) {
  pattern <- "^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}$"
  grepl(pattern, email)
}

is_valid_email("test@example.com")
is_valid_email("invalid-email")

format_phone <- function(phone) {
  phone <- gsub("[^0-9]", "", phone)
  sprintf("%s-%s-%s", 
          substr(phone, 1, 3),
          substr(phone, 4, 7),
          substr(phone, 8, 11))
}

format_phone("12345678901")
format_phone("123-456-78901")

text <- "  The quick brown fox jumps over the lazy dog.  "

words <- strsplit(trimws(text), " ")[[1]]
length(words)
nchar(text)
unique(tolower(words))