File Handling in R

# ─── READ TEXT FILES ──────────────────────────────────
# Read all lines into character vector
lines <- readLines("data.txt")
cat("Lines:", length(lines), "\n")
print(head(lines, 5))

# Read with connection (memory-efficient for large files)
con <- file("large_data.txt", "r")
while (TRUE) {
  line <- readLines(con, n=1)
  if (length(line) == 0) break
  # Process line here
}
close(con)

# ─── READ CSV FILES ───────────────────────────────────
df <- read.csv("sales.csv")              # Basic
df <- read.csv("sales.csv",
               header     = TRUE,        # First row is header
               sep        = ",",         # Delimiter
               na.strings = c("", "NA", "N/A", "NULL"),  # NA placeholders
               stringsAsFactors = FALSE, # Don't auto-convert strings to factors
               skip       = 2,           # Skip first 2 rows
               nrows      = 1000)        # Read only first 1000 rows

# Tab-separated
df <- read.delim("data.tsv", sep="\t")
# Any delimiter
df <- read.table("data.txt", sep="|", header=TRUE)

# ─── USING readr (faster, tidyverse) ──────────────────
library(readr)
df <- read_csv("sales.csv",
               col_types = cols(
                 date    = col_date("%Y-%m-%d"),
                 revenue = col_double(),
                 region  = col_character()
               ))
problems(df)  # Show parsing issues

# Write CSV
write.csv(df, "output.csv", row.names=FALSE)  # row.names=FALSE to avoid X column
write.csv2(df, "output_eu.csv")  # European format (semicolon separator)

# Tidyverse write (no row names by default)
library(readr)
write_csv(df, "output_tidy.csv")
write_tsv(df, "output.tsv")

# Write text file
cat("Report generated:", Sys.time(), "\n", file="report.txt")
writeLines(c("Line 1", "Line 2", "Line 3"), "output.txt")

# Append to existing file
cat("New data\n", file="log.txt", append=TRUE)

# Save/Load R objects
saveRDS(df, "my_data.rds")          # Save single R object
df_loaded <- readRDS("my_data.rds") # Load it back

save(df, model, "workspace.RData")  # Save multiple objects
load("workspace.RData")             # Restores all saved objects

# File paths (use / or \\ for Windows)
path <- "data/sales/2024/q4_sales.csv"

# Check existence
file.exists("data.csv")    # TRUE/FALSE
dir.exists("output/")      # TRUE/FALSE

# Create directories
dir.create("output/charts", recursive=TRUE)   # Create nested dirs

# List files
list.files("data/")                  # All files
list.files("data/", pattern="\\.csv$")  # Only CSV files
list.files("data/", recursive=TRUE)   # Include subdirectories

# File operations
file.copy("source.csv", "backup.csv")
file.rename("old_name.csv", "new_name.csv")
file.remove("temp_file.csv")

# Get file info
file.info("data.csv")$size    # File size in bytes
file.info("data.csv")$mtime   # Last modified time

# ─── NOTES MANAGEMENT SYSTEM ─────────────────────────
notes_file <- "notes.txt"

add_note <- function(title, content) {
  timestamp <- format(Sys.time(), "%Y-%m-%d %H:%M")
  note <- paste0(
    "─────────────────────────────────────\n",
    "TITLE: ", title, "\n",
    "DATE:  ", timestamp, "\n",
    "─────────────────────────────────────\n",
    content, "\n\n"
  )
  cat(note, file=notes_file, append=TRUE)
  cat("Note added:", title, "\n")
}

list_notes <- function() {
  if (!file.exists(notes_file)) {
    cat("No notes found.\n"); return()
  }
  lines <- readLines(notes_file)
  titles <- lines[grep("^TITLE:", lines)]
  cat("=== YOUR NOTES ===\n")
  for (i in seq_along(titles)) cat(i, ".", gsub("^TITLE: ", "", titles[i]), "\n")
}

search_notes <- function(keyword) {
  if (!file.exists(notes_file)) { cat("No notes.\n"); return() }
  lines <- readLines(notes_file)
  matches <- grep(keyword, lines, ignore.case=TRUE, value=TRUE)
  if (length(matches) == 0) cat("No matches for:", keyword, "\n")
  else { cat("Found", length(matches), "matches:\n"); print(matches) }
}

export_csv <- function(output_file = "notes_export.csv") {
  if (!file.exists(notes_file)) { cat("No notes.\n"); return() }
  lines <- readLines(notes_file)
  titles <- gsub("^TITLE: ", "", lines[grep("^TITLE:", lines)])
  dates  <- gsub("^DATE: ", "", lines[grep("^DATE:", lines)])
  df <- data.frame(Title=titles, Date=dates, stringsAsFactors=FALSE)
  write_csv(df, output_file)
  cat("Exported", nrow(df), "notes to", output_file, "\n")
}

# Demo
file.remove(notes_file)  # Start fresh
add_note("R Basics", "R is a statistical computing language. Use <- for assignment.")
add_note("ggplot2", "Grammar of graphics: data + aesthetics + geometry.")
add_note("dplyr", "Key verbs: filter, select, mutate, group_by, summarise.")
list_notes()
search_notes("ggplot2")
export_csv()