apache_log_parser 1.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
data/.document ADDED
@@ -0,0 +1,5 @@
1
+ README.rdoc
2
+ lib/**/*.rb
3
+ bin/*
4
+ features/**/*.feature
5
+ LICENSE
data/.gitignore ADDED
@@ -0,0 +1,21 @@
1
+ ## MAC OS
2
+ .DS_Store
3
+
4
+ ## TEXTMATE
5
+ *.tmproj
6
+ tmtags
7
+
8
+ ## EMACS
9
+ *~
10
+ \#*
11
+ .\#*
12
+
13
+ ## VIM
14
+ *.swp
15
+
16
+ ## PROJECT::GENERAL
17
+ coverage
18
+ rdoc
19
+ pkg
20
+
21
+ ## PROJECT::SPECIFIC
data/LICENSE ADDED
@@ -0,0 +1,20 @@
1
+ Copyright (c) 2009 Joel Watson
2
+
3
+ Permission is hereby granted, free of charge, to any person obtaining
4
+ a copy of this software and associated documentation files (the
5
+ "Software"), to deal in the Software without restriction, including
6
+ without limitation the rights to use, copy, modify, merge, publish,
7
+ distribute, sublicense, and/or sell copies of the Software, and to
8
+ permit persons to whom the Software is furnished to do so, subject to
9
+ the following conditions:
10
+
11
+ The above copyright notice and this permission notice shall be
12
+ included in all copies or substantial portions of the Software.
13
+
14
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
15
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
16
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
17
+ NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
18
+ LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
19
+ OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
20
+ WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
data/README.rdoc ADDED
@@ -0,0 +1,49 @@
1
+ = Getting Started
2
+
3
+ This is a library designed to easily parse and access standard Apache log files.
4
+
5
+ To get started, require the library:
6
+
7
+ require 'apache_log_parser'
8
+
9
+ From there, you would use it as follows:
10
+
11
+ ApacheLogParser.parse(logfile, rules) do |parsed|
12
+ parsed[:ip] #=> "12.12.12.12"
13
+ parsed[:date] #=> "21/Jan/2010"
14
+ parsed[:day] #=> 21
15
+ parsed[:month] #=> "Jan"
16
+ parsed[:year] #=> 2010
17
+ parsed[:hour] #=> 14
18
+ parsed[:zone] #=> "-0800"
19
+ parsed[:method] #=> "GET"
20
+ parsed[:resource] #=> "/some/page.php"
21
+ parsed[:status] #=> 200
22
+ parsed[:size] #=> "7047"
23
+ parsed[:referer] #=> "-"
24
+ parsed[:user_agent] #=> "Mozilla/5.0 (Macintosh; U; Intel..."
25
+ end
26
+
27
+ The logfile parameter is simply the path to the logfile in question and the rules
28
+ parameter is a hash of rules to filter the logfile with.
29
+
30
+ = Using Rules
31
+
32
+ To use rules, simply build a hash with options you want to filter with as follows:
33
+
34
+ rules = {}
35
+ rules[:hour] = 11..13 # only accept hits between 11:00 and 13:59 hours
36
+ rules[:day] = 21 # only accept hits where the day is 21
37
+ rules[:date] = "12/Jan/2010" # only accept hits on Jan 12, 2010
38
+ rules[:method] = "GET" # only accept hits where the request method is GET
39
+ rules[:status] = 404 # only accept hits where the status response is 404
40
+
41
+ Rules are inclusive, so only hits where ALL rules are met will be kept. From there,
42
+ you would simply pass the rules hash into the parse method as shown above. The logfile
43
+ is read one line at a time, so the memory footprint is quite small and can easily handle
44
+ large logfiles (sizes as large as 6GB have been tested). The larger the file, the longer
45
+ the parse process will take though.
46
+
47
+ == Copyright
48
+
49
+ Copyright (c) 2010 Joel Watson. See LICENSE for details.
data/Rakefile ADDED
@@ -0,0 +1,45 @@
1
+ require 'rubygems'
2
+ require 'rake'
3
+
4
+ begin
5
+ require 'jeweler'
6
+ Jeweler::Tasks.new do |gem|
7
+ gem.name = "apache_log_parser"
8
+ gem.summary = %Q{Library to easily parse standard Apache log files.}
9
+ gem.description = %Q{Library to easily parse standard Apache log files.}
10
+ gem.email = "watsonian@gmail.com"
11
+ gem.homepage = "http://github.com/watsonian/apache_log_parser"
12
+ gem.authors = ["watsonian"]
13
+ gem.add_development_dependency "rspec", ">= 1.2.9"
14
+ # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
15
+ end
16
+ Jeweler::GemcutterTasks.new
17
+ rescue LoadError
18
+ puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
19
+ end
20
+
21
+ require 'spec/rake/spectask'
22
+ Spec::Rake::SpecTask.new(:spec) do |spec|
23
+ spec.libs << 'lib' << 'spec'
24
+ spec.spec_files = FileList['spec/**/*_spec.rb']
25
+ end
26
+
27
+ Spec::Rake::SpecTask.new(:rcov) do |spec|
28
+ spec.libs << 'lib' << 'spec'
29
+ spec.pattern = 'spec/**/*_spec.rb'
30
+ spec.rcov = true
31
+ end
32
+
33
+ task :spec => :check_dependencies
34
+
35
+ task :default => :spec
36
+
37
+ require 'rake/rdoctask'
38
+ Rake::RDocTask.new do |rdoc|
39
+ version = File.exist?('VERSION') ? File.read('VERSION') : ""
40
+
41
+ rdoc.rdoc_dir = 'rdoc'
42
+ rdoc.title = "apache_log_parser #{version}"
43
+ rdoc.rdoc_files.include('README*')
44
+ rdoc.rdoc_files.include('lib/**/*.rb')
45
+ end
data/VERSION ADDED
@@ -0,0 +1 @@
1
+ 1.0.0
@@ -0,0 +1,55 @@
1
+ # Generated by jeweler
2
+ # DO NOT EDIT THIS FILE DIRECTLY
3
+ # Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
4
+ # -*- encoding: utf-8 -*-
5
+
6
+ Gem::Specification.new do |s|
7
+ s.name = %q{apache_log_parser}
8
+ s.version = "1.0.0"
9
+
10
+ s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
11
+ s.authors = ["watsonian"]
12
+ s.date = %q{2010-01-27}
13
+ s.description = %q{Library to easily parse standard Apache log files.}
14
+ s.email = %q{watsonian@gmail.com}
15
+ s.extra_rdoc_files = [
16
+ "LICENSE",
17
+ "README.rdoc"
18
+ ]
19
+ s.files = [
20
+ ".document",
21
+ ".gitignore",
22
+ "LICENSE",
23
+ "README.rdoc",
24
+ "Rakefile",
25
+ "VERSION",
26
+ "apache_log_parser.gemspec",
27
+ "lib/apache_log_parser.rb",
28
+ "spec/apache_log_parser_spec.rb",
29
+ "spec/spec.opts",
30
+ "spec/spec_helper.rb"
31
+ ]
32
+ s.homepage = %q{http://github.com/watsonian/apache_log_parser}
33
+ s.rdoc_options = ["--charset=UTF-8"]
34
+ s.require_paths = ["lib"]
35
+ s.rubygems_version = %q{1.3.5}
36
+ s.summary = %q{Library to easily parse standard Apache log files.}
37
+ s.test_files = [
38
+ "spec/apache_log_parser_spec.rb",
39
+ "spec/spec_helper.rb"
40
+ ]
41
+
42
+ if s.respond_to? :specification_version then
43
+ current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
44
+ s.specification_version = 3
45
+
46
+ if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
47
+ s.add_development_dependency(%q<rspec>, [">= 1.2.9"])
48
+ else
49
+ s.add_dependency(%q<rspec>, [">= 1.2.9"])
50
+ end
51
+ else
52
+ s.add_dependency(%q<rspec>, [">= 1.2.9"])
53
+ end
54
+ end
55
+
@@ -0,0 +1,54 @@
1
+ class ApacheLogParser
2
+ def self.parse(filename, rules={}, &block)
3
+ rules = process_rules(rules)
4
+ parse_file(filename, rules, &block)
5
+ end
6
+
7
+ private
8
+ def self.parse_line(line)
9
+ m = line.match(/^(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}).*?(([0-9]{1,2})\/(.*?)\/([0-9]{4})):(([0-9]{2}):[0-9]{2}:[0-9]{2})\s*(.*?)\]\s*"([\w]*)\s(.*?)\s.*?"\s([0-9]{3})\s(.*?)\s*"(.*?)"\s*"(.*?)"/)
10
+ if m
11
+ {:ip => m[1],
12
+ :date => m[2],
13
+ :day => m[3].to_i,
14
+ :month => m[4],
15
+ :year => m[5].to_i,
16
+ :time => m[6],
17
+ :hour => m[7].to_i,
18
+ :zone => m[8],
19
+ :method => m[9],
20
+ :resource => m[10],
21
+ :status => m[11].to_i,
22
+ :size => m[12],
23
+ :referer => m[13],
24
+ :user_agent => m[14]}
25
+ else
26
+ {}
27
+ end
28
+ end
29
+
30
+ def self.parse_file(filename, rules={}, &block)
31
+ File.foreach(filename) do |line|
32
+ parsed = parse_line(line)
33
+ if rules.any?
34
+ # stop parsing the file if we're past the designated hour range
35
+ break if rules[:hour] && Array(parsed[:hour]).last > Array(rules[:hour]).last
36
+
37
+ # go to the next line if there are any rules that are not matched by this line
38
+ next if rules.reject{|k,v| Array(v).include?(parsed[k]) }.any?
39
+ end
40
+ yield parsed
41
+ end
42
+ end
43
+
44
+ def self.process_rules(rules)
45
+ #default_options = {:date => Time.now.strftime("#{"%02d" % rules[:day] || "%d"}/%h/%Y")}
46
+ #rules = default_options.merge(rules)
47
+ if rules[:date]
48
+ rules[:day], rules[:month], rules[:year] = rules[:date].split("/")
49
+ rules[:day] = rules[:day].to_i
50
+ rules[:year] = rules[:year].to_i
51
+ end
52
+ rules
53
+ end
54
+ end
@@ -0,0 +1,7 @@
1
+ require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
2
+
3
+ describe "ApacheLogParser" do
4
+ # it "fails" do
5
+ # fail "hey buddy, you should probably rename this file and start specing for real"
6
+ # end
7
+ end
data/spec/spec.opts ADDED
@@ -0,0 +1 @@
1
+ --color
@@ -0,0 +1,9 @@
1
+ $LOAD_PATH.unshift(File.dirname(__FILE__))
2
+ $LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
3
+ require 'apache_log_parser'
4
+ require 'spec'
5
+ require 'spec/autorun'
6
+
7
+ Spec::Runner.configure do |config|
8
+
9
+ end
metadata ADDED
@@ -0,0 +1,76 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: apache_log_parser
3
+ version: !ruby/object:Gem::Version
4
+ version: 1.0.0
5
+ platform: ruby
6
+ authors:
7
+ - watsonian
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+
12
+ date: 2010-01-27 00:00:00 -08:00
13
+ default_executable:
14
+ dependencies:
15
+ - !ruby/object:Gem::Dependency
16
+ name: rspec
17
+ type: :development
18
+ version_requirement:
19
+ version_requirements: !ruby/object:Gem::Requirement
20
+ requirements:
21
+ - - ">="
22
+ - !ruby/object:Gem::Version
23
+ version: 1.2.9
24
+ version:
25
+ description: Library to easily parse standard Apache log files.
26
+ email: watsonian@gmail.com
27
+ executables: []
28
+
29
+ extensions: []
30
+
31
+ extra_rdoc_files:
32
+ - LICENSE
33
+ - README.rdoc
34
+ files:
35
+ - .document
36
+ - .gitignore
37
+ - LICENSE
38
+ - README.rdoc
39
+ - Rakefile
40
+ - VERSION
41
+ - apache_log_parser.gemspec
42
+ - lib/apache_log_parser.rb
43
+ - spec/apache_log_parser_spec.rb
44
+ - spec/spec.opts
45
+ - spec/spec_helper.rb
46
+ has_rdoc: true
47
+ homepage: http://github.com/watsonian/apache_log_parser
48
+ licenses: []
49
+
50
+ post_install_message:
51
+ rdoc_options:
52
+ - --charset=UTF-8
53
+ require_paths:
54
+ - lib
55
+ required_ruby_version: !ruby/object:Gem::Requirement
56
+ requirements:
57
+ - - ">="
58
+ - !ruby/object:Gem::Version
59
+ version: "0"
60
+ version:
61
+ required_rubygems_version: !ruby/object:Gem::Requirement
62
+ requirements:
63
+ - - ">="
64
+ - !ruby/object:Gem::Version
65
+ version: "0"
66
+ version:
67
+ requirements: []
68
+
69
+ rubyforge_project:
70
+ rubygems_version: 1.3.5
71
+ signing_key:
72
+ specification_version: 3
73
+ summary: Library to easily parse standard Apache log files.
74
+ test_files:
75
+ - spec/apache_log_parser_spec.rb
76
+ - spec/spec_helper.rb