require 'date'
require 'cgi'
require 'stringio'

# Parses a standard web server log file stream and returns a hash with
# key/values for each line. Includes the Enumerable interface.
class LogParser
  include Enumerable

  # Support both strings and streams as input.
  def initialize(input)
    input = StringIO.new(input) if input.class == String
    @stream = input
  end

  # Enumerable interface.
  def each
    while(observation = get_next_observation)
      yield observation
    end
  end

  def get_next_observation
    line = @stream.gets
    line && LogParser.parse_line(line)
  end

  LOG_FORMAT = /([^ ]*) [^ ]* [^ ]* \[([^\]]*)\] "([^"]*)" ([^ ]*)/
  LOG_DATE_FORMAT = "%d/%b/%Y:%H:%M:%S %z"
  LOG_KEY_VALUE_FORMAT = /[?&]([^=]+)=([^&]+)/
  SERVER_ATTRIBUTES = [:ip, :timestamp, :request, :status]

  # Parse one log line and return a hash with all attributes.
  def self.parse_line(line)
    return nil if line.strip.empty?
    
    line =~ LOG_FORMAT
    result = {}

    # Save ip, timestamp and request.
    result[:ip] = $1
    begin
      result[:timestamp] = DateTime.strptime($2, LOG_DATE_FORMAT)
    rescue ArgumentError
      raise ParseError.new("Error while parsing timestamp")
    end
    result[:request] = $3
    result[:status] = $4

    # Extract key/values pairs from the query part of the request.
    $3.scan(LOG_KEY_VALUE_FORMAT) do |key, value|
      begin
        key = CGI.unescape(key).to_sym
        value = CGI.unescape(value)
      rescue Encoding::CompatibilityError => e
        raise ParseError.new("Error while parsing query parameters")
      end

      if result.has_key? key
        if result[key].is_a? Array
          result[key] << value
        else
          result[key] = [result[key], value]
        end
      else
        result[key] = value
      end
    end

    return result
  rescue ParseError
    raise
  rescue
    raise ParseError.new("Unknown parsing error")
  end
  class ParseError < StandardError ; end
end