Working with Strings in R

# String creation and basics
s <- "Hello, R World!"
nchar(s)          # 16 (length)
toupper(s)        # "HELLO, R WORLD!"
tolower(s)        # "hello, r world!"
trimws("  hello  ")      # "hello" (trim whitespace both sides)
trimws("  hello  ", "left")   # "hello  " (left only)
trimws("  hello  ", "right")  # "  hello" (right only)

# Concatenation
paste("Hello", "World")          # "Hello World" (space separator)
paste("Hello", "World", sep="-") # "Hello-World"
paste0("Hello", "World")         # "HelloWorld" (no separator)
paste(1:5, collapse=", ")        # "1, 2, 3, 4, 5"

# Substring operations
substr("RStudio", 1, 2)   # "RS" (start, stop positions)
substring("R Programming", 3, 13)  # "Programming"
substr(s, 8, 16) <- "Universe!"   # Modify substring in place

# Splitting
strsplit("Alice,Bob,Carol", ",")       # list: "Alice" "Bob" "Carol"
strsplit(c("a b", "c d e"), " ")      # list of length 2

# Search and replace
sub("World", "R", "Hello World")     # First match only
gsub("o", "0", "Hello World")        # All matches: "Hell0 W0rld"

# String formatting
sprintf("Name: %-10s Salary: $%8.2f", "Alice", 85000)
format(12345.678, nsmall=2, big.mark=",")  # "12,345.68"
formatC(0.0001234, format="e", digits=3)   # "1.234e-04"

library(stringr)

s <- c("Alice Johnson", "  Bob Smith  ", "carol davis", "David_Lee-Jr")

# Detect and count
str_detect(s, "Alice")     # TRUE FALSE FALSE FALSE
str_count(s, "[aeiou]")    # vowel counts per string

# Case and whitespace
str_to_upper(s)            # ALL CAPS
str_to_lower(s)            # all lowercase
str_to_title(s)            # Title Case
str_trim(s)                # Remove leading/trailing whitespace
str_squish(s)              # Also collapses internal spaces

# Extract and replace
str_sub(s, 1, 5)           # First 5 chars
str_replace(s, "_", " ")   # First underscore → space
str_replace_all(s, "[_-]", " ")  # All underscores and hyphens

# Split and combine
str_split("2024-01-15", "-")   # list: "2024" "01" "15"
str_c("Hello", c("Alice", "Bob"), sep=", ")  # "Hello, Alice" "Hello, Bob"

# Padding and length
str_pad("42", width=6, pad="0")   # "000042" (like printf)
str_pad("R",  width=10, side="both")  # "    R     " (centered)
str_length(s)   # Character counts

# Pattern extraction
emails <- c("alice@company.com", "bob@gmail.com", "invalid-email")
str_detect(emails, "^[a-zA-Z0-9.]+@[a-zA-Z0-9.]+\\.[a-zA-Z]{2,}$")
# TRUE TRUE FALSE
str_extract(emails, "@(.+)$")  # Extract domain part

# Common regex patterns in R
texts <- c("Phone: 555-1234", "Email: alice@test.com",
            "ZIP: 10001", "Date: 2024-01-15")

# Extract phone numbers
str_extract(texts, "\\d{3}-\\d{4}")  # "555-1234" NA NA NA

# Extract emails
str_extract(texts, "[a-zA-Z0-9.]+@[a-zA-Z0-9.]+\\.[a-zA-Z]+")

# Extract 4-digit years
str_extract(texts, "\\d{4}")

# Key regex patterns:
# .     — any character
# \\d   — digit [0-9]
# \\w   — word char [a-zA-Z0-9_]
# \\s   — whitespace
# ^     — start of string
# $     — end of string
# +     — one or more
# *     — zero or more
# ?     — zero or one
# {n,m} — n to m occurrences
# [abc] — character class