# Text Mining Lab1: String Manipulation in R
# Duration: 90 minutes | Tool: RStudio | Required packages: tidyverse

# ----------------------------------------------
# PART 1 – Basic Operations with Strings 
# ----------------------------------------------

library(stringr)

# Exercise 1: Creating and checking types
Lab1 <- c(1, 2, 3)
typeof(Lab1 )
class(Lab1 )

Lab1_char <- as.character(Lab1)
class(Lab1_char)

# Exercise 2: Working with quotes
string1 <- "This is a string with double quotes"
string2 <- 'This is a string with single quotes'
string3 <- 'She said, "Hello!"'
string3 <- "She said, \"Hello!\""

writeLines(string3) #To see the raw contents of the string
str_view(string3) #The base R function to see the raw contents of the string

# Exercise 3: Length and subsetting
x <- c("Home", "Trip", "Dream") #Create a vector
str_length(x) #Calculates the length of each string
str_sub(x, start = 1, end = 3) #Extract the first 3 letters of each
str_sub(x, start = -3, end = -1) #Extract the last 3 letters using negative values.

# ----------------------------------------------
# PART 2 – Combining and transforming strings 
# ----------------------------------------------

# Exercise 4: Personalized questions
library(tidyverse)
names <- tibble(name = c("Maria", "Luca", "Anna")) #Create a tibble with 3 names
names <- names |> mutate(greeting = str_c("Hello ", name, " how are you?")) #Creates a new variable with vector greetings
names

# Exercise 5: Case conversion
sentence <- "this is a title"
str_to_upper(sentence)
str_to_lower(sentence)
str_to_title(sentence)

accents <- "Vieni quà e non andare là!"
str_to_upper(accents)
str_to_lower(accents)
str_to_title(accents)

# ----------------------------------------------
# PART 3 – Separation and reorganization 
# ----------------------------------------------

# Exercise 6: Separate into multiple rows
df1 <- tibble(x = c("apple,banana,cream", "dream,emotions", "flowers")) #Create a tibble 
df1
df1 |> separate_longer_delim(x, delim = ",") #to separate on different row

# Exercise 7: Separate into multiple columns
df2 <- tibble(x = c("A10.8.2025", "B10.10.2010", "C15.12.2015"))
df2
df2 |> separate_wider_delim(x, delim = ".", names = c("code", "month", "year")) #To separate into code, edition, year

# ----------------------------------------------
# PART 4 – Final Challenge 
# ----------------------------------------------

# Exercise 8: Creative string manipulation
fruits <- c("apple", "banana", "pear", "persimmon", "kiwi", "mango", "orange") #Create a vector
str_length(fruits)
which.max(str_length(fruits)) #Find the fruit with the longest name

lengths <- str_length(fruits)         
max_length <- max(lengths)  
max_length 

longest_fruit <- fruits[which.max(lengths)]  
longest_fruit 

#Pipe operator: 
fruits |> 
  str_length() |> 
  which.max() |> 
  (\(i) fruits[i])()

list_fruits <- str_c(fruits, collapse = ", ") #Creates a string with the fruits separated by commas.
list_fruits

fcolor <- c("red", "yellow", "green", "orange", "brown", "yellow", "orange")
str_c(fruits, " is ", fcolor) #Combine each fruit with its colour: e.g. “apple is red”.

#str_sub(string, start, end) <- value 
str_sub(fruits, 4, 4) <- "-" #Replace the fourth character in each word with the symbol 
                             
fruits

# ----------------------------------------------
# EXTRA – For fast finishers
# ----------------------------------------------

# Function to turn c("apple", "banana", "cream) into "apple, banana, and cream"
combine_nicely <- function(x) {
  if (length(x) <= 1) return(x) 
  if (length(x) == 2) return(str_c(x[1], " and ", x[2]))
  str_c(str_c(x[-length(x)], collapse = ", "), ", and ", x[length(x)])
}
#If the vector has 0 or 1 element, there is no point in adding “and” or commas, so it returns as is
# If it has exactly 2 elements, it combines them with ‘ and ’
#For vectors with more than 2 elements: x[-length(x)] takes all but the last collapse = ", " joins them with commas then adds ", and " followed by the last element
combine_nicely(c("apple", "banana", "cream"))

#With pipe operator
c("apple", "banana", "cream") |> combine_nicely()

#Using tibble
tibble(word = c("apple", "banana", "cream")) |>
  pull(word) |>
  combine_nicely()

################################################################################
# Example usage:
combine_nicely(c("apple", "banana", "cream"))     
combine_nicely(c("red", "yellow", "white"))     


# Combine them into a longer sentence
combined <- str_c(
  combine_nicely(c("apple", "banana", "cream")),
  " and ",
  combine_nicely(c("red", "green", "white")),
  " or ",
  combine_nicely("pink")
)

combined   # "apple, banana, and cream and red, green, and white or pink"