Apache Access log parser

README.md

Jan. 15, 2025

A parsing function in R for Apache Access logs in R.

main.R

library(tidyverse)

parse_apache_logs <- function(log_file) {
  log_data <- read_lines(log_file)

  log_pattern <- '^(\\S+) (\\S+) (\\S+) \\[(.*?)\\] "(\\S+) (\\S+) (\\S+)" (\\d{3}) (\\d+|-) "(.*?)" "(.*?)"'


  logs_tibble <- log_data %>%
    as_tibble() %>%
    rename(raw = value) %>%
    mutate(
      match = str_match(raw, log_pattern),
      ip_address = match[, 2],
      identity = match[, 3],
      user = match[, 4],
      timestamp = match[, 5],
      method = match[, 6],
      resource = match[, 7],
      protocol = match[, 8],
      status = as.integer(match[, 9]),
      bytes = if_else(match[, 10] == "-", NA_integer_, as.integer(match[, 10])),
      referrer = match[, 11],
      user_agent = match[, 12]
    ) %>%
    select(-raw, -match) %>%
    mutate(
      timestamp = lubridate::dmy_hms(timestamp, tz = "UTC")
    )
  
  return(logs_tibble)
}