Sha256: 5d7688ac6fa559475e090090205b9576a1578874f4d39a443aa3e8f0b0ed0863
Contents?: true
Size: 1.56 KB
Versions: 8
Compression:
Stored size: 1.56 KB
Contents
module ETL #:nodoc:
module Parser #:nodoc:
# Parser which can parser the Apache Combined Log Format as defined at
# http://httpd.apache.org/docs/2.2/logs.html
class ApacheCombinedLogParser < ETL::Parser::Parser
include HttpTools
def initialize(source, options={})
super
end
def each
Dir.glob(file).each do |file|
File.open(file).each_line do |line|
yield parse(line)
end
end
end
def parse(line)
# example line: 127.0.0.1 - frank [10/Oct/2000:13:55:36 -0700] "GET /apache_pb.gif HTTP/1.0" 200 2326 "http://www.example.com/start.html" "Mozilla/4.08 [en] (Win98; I ;Nav)"
line =~ /^(\S+)\s(\S+)\s(\S+)\s\[([^\]]*)\]\s"([^"]*)"\s(\d*)\s(\d*)\s"([^"]*)"\s"([^"]*)"$/
fields = {
:ip_address => $1,
:identd => $2,
:user => $3,
:timestamp => $4,
:request => $5,
:response_code => $6,
:bytes => $7,
:referrer => $8,
:user_agent => $9,
}
#fields[:timestamp] =~ r%{(\d\d)/(\w\w\w)/(\d\d\d\d):(\d\d):(\d\d):(\d\d) -(\d\d\d\d)}
d = Date._strptime(fields[:timestamp], '%d/%b/%Y:%H:%M:%S')
fields[:timestamp] = Time.mktime(d[:year], d[:mon], d[:mday], d[:hour], d[:min], d[:sec], d[:sec_fraction])
fields.merge!(parse_user_agent(fields[:user_agent]))
fields.merge!(parse_uri(fields[:referrer]))
fields.each do |key, value|
fields[key] = nil if value == '-'
end
end
end
end
end
Version data entries
8 entries across 8 versions & 1 rubygems