apache_log-parser 2.0.2 → 3.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: d7b3cf2d958865b1b7ed59532445be7468c0c4ea
-  data.tar.gz: eef9f4f04a09fc17ba7db8b075b7da6d59c4df0c
+  metadata.gz: 338af4fdaec6a5a65bf000f5dc549f73ba1db221
+  data.tar.gz: b5366447d647a4da67dbce66468730fa993fbd15
 SHA512:
-  metadata.gz: 1641a79197ca5cbf216dd02e5f81ce935bd3c2a3098093220bb5b63b01580d32b19304505c25c62b5167348636650380bbccf2aab272d27fa5c1438f383551bb
-  data.tar.gz: ba877b92b6dd6e1254be3bd788f62b7b38d207fb4123b4bac630d1e4ed916bb0909dffd52c5989ad93f792aa9ac6516fbe6704941c77421872b6b63417fe58ec
+  metadata.gz: fe677bb02e77958f076a1b68a1b6cf8f5c619c4b7f7c551e6e8ef9b7496617a13b7b25ff268881d0f6f9f3a3f978c2ee6165500a2477b507d8cb91d5eba79c13
+  data.tar.gz: 2ee1ab1f75310b24e9ad8cdcfabcaa69607e76ce83534301519cfba81640ef3ebe80be56a35b7efde54f2b71c3d599a0c0eb443c341d670769b58551dfabf48a

data/README.md

@@ -1,18 +1,8 @@
-# ApacheLog::Parser
-[![Build Status](https://travis-ci.org/takady/apache_log-parser.svg?branch=master)](https://travis-ci.org/takady/apache_log-parser) [![Code Climate](https://codeclimate.com/github/takady/apache_log-parser/badges/gpa.svg)](https://codeclimate.com/github/takady/apache_log-parser)  
-Gem to parse apache log including common, combined and customized format.
+# ApacheLog::Parser [![Build Status](https://travis-ci.org/takady/apache_log-parser.svg?branch=master)](https://travis-ci.org/takady/apache_log-parser) [![Code Climate](https://codeclimate.com/github/takady/apache_log-parser/badges/gpa.svg)](https://codeclimate.com/github/takady/apache_log-parser)
 
-## Installation
-
-Add this line to your application's Gemfile:
-
-    gem 'apache_log-parser'
+Parse apache log including common, combined and customized format
 
-And then execute:
-
-    $ bundle
-
-Or install it yourself as:
+## Installation
 
     $ gem install apache_log-parser
 
@@ -22,19 +12,22 @@ Or install it yourself as:
 require 'apache_log/parser'
 
 # common format
-common_log = ApacheLog::Parser.parse(log_line, 'common')
+parser = ApacheLog::Parser.new('common')
+common_log = parser.parse(log_line)
 common_log[:remote_host]    #=> remote host
 common_log[:datetime]       #=> datetime
 common_log[:request]        #=> request
 
 # combined format
-combined_log = ApacheLog::Parser.parse(log_line, 'combined')
+parser = ApacheLog::Parser.new('combined')
+combined_log = parser.parse(log_line)
 combined_log[:referer]        #=> referer
 combined_log[:user_agent]     #=> user_agent
 
 # custom format(additional fields after 'combined')
 # e.g. "%h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-Agent}i\" \"%v\" \"%{cookie}n\" %D"
-custom_log = ApacheLog::Parser.parse(log_line, 'combined', %w(vhost usertrack request_duration))
+parser = ApacheLog::Parser.new('combined', %w(vhost usertrack request_duration))
+custom_log = parser.parse(log_line)
 custom_log[:user_agent]        #=> user_agent
 custom_log[:vhost]             #=> vhost
 custom_log[:usertrack]         #=> usertrack

data/apache_log-parser.gemspec

@@ -7,9 +7,9 @@ Gem::Specification.new do |spec|
   spec.name          = "apache_log-parser"
   spec.version       = ApacheLog::Parser::VERSION
   spec.authors       = ["Yuichi Takada"]
-  spec.email         = ["takadyy@gmail.com"]
-  spec.summary       = "Gem to parse apache log including common, combined and customized format."
-  spec.description   = "You can parse common, combined and customized format apache log."
+  spec.email         = ["takadyuichi@gmail.com"]
+  spec.summary       = "Parse apache log including common, combined and customized format"
+  spec.description   = spec.summary
   spec.homepage      = "https://github.com/takady/apache_log-parser"
   spec.license       = "MIT"
 

data/benchmark.rb

@@ -0,0 +1,18 @@
+$LOAD_PATH.unshift File.expand_path('../lib', __FILE__)
+require 'apache_log/parser'
+require 'benchmark'
+
+common_line = '127.0.0.1 - - [20/May/2014:20:04:04 +0900] "GET /test/indx.html HTTP/1.1" 200 4576'
+combined_line = '104.24.160.39 - - [07/Jun/2014:14:58:55 +0900] "GET /category/electronics HTTP/1.1" 200 128 "-" "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:9.0.1) Gecko/20100101 Firefox/9.0.1"'
+customized_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)" virtualhost.example.jp "192.0.2.16794832933550" "09011112222333_xx.ezweb.ne.jp" 533593'
+ 
+common_parser = ApacheLog::Parser.new('common')
+combined_parser = ApacheLog::Parser.new('combined')
+customized_parser = ApacheLog::Parser.new('combined', %w(vhost usertrack mobileid request_duration))
+
+n = 1_000_000
+Benchmark.bm(12) do |x|
+  x.report('common:')     { (1..n).each{common_parser.parse(common_line)} }
+  x.report('combined:')   { (1..n).each{combined_parser.parse(combined_line)} }
+  x.report('customized:') { (1..n).each{customized_parser.parse(customized_line)} }
+end

data/lib/apache_log/parser.rb

@@ -2,9 +2,8 @@ require 'apache_log/parser/version'
 require 'date'
 
 module ApacheLog
-  module Parser
-
-    def self.parse(line, format, additional_fields=[])
+  class Parser
+    def initialize(format, additional_fields=[])
       common_fields   = %w(remote_host identity_check user datetime request status size)
       combined_fields = common_fields + %w(referer user_agent)
 
@@ -18,52 +17,53 @@ module ApacheLog
 
       case format
       when 'common'
-        fields = common_fields + additional_fields
-        pattern = /^#{common_pattern}#{additional_pattern}$/
+        @fields = common_fields + additional_fields
+        @pattern = /^#{common_pattern}#{additional_pattern}$/
       when 'combined'
-        fields = combined_fields + additional_fields
-        pattern = /^#{combined_pattern}#{additional_pattern}$/
+        @fields = combined_fields + additional_fields
+        @pattern = /^#{combined_pattern}#{additional_pattern}$/
       else
         raise "format error\n no such format: <#{format}> \n"
       end
+    end
 
-      matched = pattern.match(line)
+    def parse(line)
+      matched = @pattern.match(line)
       raise "parse error\n at line: <#{line}> \n" if matched.nil?
-
-      generate_hash(fields, matched.to_a)
+      generate_hash(@fields, matched.to_a)
     end
 
     private
-      def self.generate_hash(keys, values)
-        hash = {}
 
-        keys.each.with_index do |key, idx|
-          key = key.to_sym
-          case key
-          when :datetime
-            hash[key] = to_datetime(values[idx+1])
-          when :request
-            hash[key] = parse_request(values[idx+1])
-          else
-            hash[key] = values[idx+1]
-          end
-        end
+    def generate_hash(keys, values)
+      hash = {}
 
-        hash
+      keys.each.with_index(1) do |key, idx|
+        key = key.to_sym
+        case key
+        when :datetime
+          hash[key] = to_datetime(values[idx])
+        when :request
+          hash[key] = parse_request(values[idx])
+        else
+          hash[key] = values[idx]
+        end
       end
 
-      def self.to_datetime(str)
-        DateTime.strptime( str, '%d/%b/%Y:%T %z')
-      end
+      hash
+    end
 
-      def self.parse_request(str)
-        method, path, protocol = str.split
-        {
-          method:   method,
-          path:     path,
-          protocol: protocol,
-        }
-      end
+    def to_datetime(str)
+      DateTime.strptime(str, '%d/%b/%Y:%T %z')
+    end
 
+    def parse_request(str)
+      method, path, protocol = str.split
+      {
+        method:   method,
+        path:     path,
+        protocol: protocol,
+      }
+    end
   end
 end

data/lib/apache_log/parser/version.rb

@@ -1,5 +1,5 @@
 module ApacheLog
-  module Parser
-    VERSION = "2.0.2"
+  class Parser
+    VERSION = "3.0.0"
   end
 end

data/spec/apache_log/parser_spec.rb

@@ -3,15 +3,14 @@ require 'date'
 
 describe ApacheLog::Parser do
 
-  before { @parser = ApacheLog::Parser }
-
   it 'has a version number' do
-    expect(@parser::VERSION).not_to be nil
+    expect(ApacheLog::Parser::VERSION).not_to be nil
   end
 
   it 'can parse common format log' do
     line = '127.0.0.1 - - [20/May/2014:20:04:04 +0900] "GET /test/indx.html HTTP/1.1" 200 4576'
-    entity = @parser.parse(line.chomp, 'common')
+    parser = ApacheLog::Parser.new('common')
+    entity = parser.parse(line.chomp)
     expect = {remote_host: '127.0.0.1', identity_check: '-', user: '-', datetime: DateTime.new(2014, 5, 20, 20, 04, 04, 0.375),
       request: {method: 'GET', path: '/test/indx.html', protocol: 'HTTP/1.1'}, status: '200', size: '4576'}
     expect(entity).to eq(expect)
@@ -19,7 +18,8 @@ describe ApacheLog::Parser do
 
   it 'can parse tab separated common format log' do
     line = "192.168.0.1\t-\t-\t[07/Feb/2011:10:59:59 +0900]\t\"GET /x/i.cgi/net/0000/ HTTP/1.1\"\t200\t9891";
-    entity = @parser.parse(line.chomp, 'common')
+    parser = ApacheLog::Parser.new('common')
+    entity = parser.parse(line.chomp)
     expect = {remote_host: '192.168.0.1', identity_check: '-', user: '-', datetime: DateTime.new(2011, 2, 07, 10, 59, 59, 0.375),
       request: {method: 'GET', path: '/x/i.cgi/net/0000/', protocol: 'HTTP/1.1'}, status: '200', size: '9891'}
     expect(entity).to eq(expect)
@@ -27,7 +27,8 @@ describe ApacheLog::Parser do
 
   it 'can parse combined format log' do
     line = '104.24.160.39 - - [07/Jun/2014:14:58:55 +0900] "GET /category/electronics HTTP/1.1" 200 128 "-" "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:9.0.1) Gecko/20100101 Firefox/9.0.1"'
-    entity = @parser.parse(line.chomp, 'combined')
+    parser = ApacheLog::Parser.new('combined')
+    entity = parser.parse(line.chomp)
     expect = {remote_host: '104.24.160.39', identity_check: '-', user: '-', datetime: DateTime.new(2014, 6, 7, 14, 58, 55, 0.375),
       request: {method: 'GET', path: '/category/electronics', protocol: 'HTTP/1.1'}, status: '200', size: '128', referer: '-',
       user_agent: 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:9.0.1) Gecko/20100101 Firefox/9.0.1'}
@@ -36,7 +37,8 @@ describe ApacheLog::Parser do
 
   it 'can parse combined format log' 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)"';
-    entity = @parser.parse(line.chomp, 'combined')
+    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)'}
@@ -45,7 +47,8 @@ describe ApacheLog::Parser do
 
   it 'can parse tab separated combined format log' do
     line = "203.0.113.254\t-\t-\t[07/Feb/2011:10:59:59 +0900]\t\"GET /x/i.cgi/movie/0001/-0002 HTTP/1.1\"\t200\t14462\t\"-\"\t\"DoCoMo/2.0 F08A3(c500;TB;W30H20)\"";
-    entity = @parser.parse(line.chomp, 'combined')
+    parser = ApacheLog::Parser.new('combined')
+    entity = parser.parse(line.chomp)
     expect = {remote_host: '203.0.113.254', identity_check: '-', user:'-', datetime: DateTime.new(2011, 2, 7, 10, 59, 59, 0.375),
       request: {method: 'GET', path: '/x/i.cgi/movie/0001/-0002', protocol: 'HTTP/1.1'}, status: '200', size: '14462', referer: '-',
       user_agent: 'DoCoMo/2.0 F08A3(c500;TB;W30H20)'}
@@ -54,7 +57,8 @@ describe ApacheLog::Parser do
 
   it 'can parse custom format log based on combined format' do
     line = '104.24.160.39 - - [07/Jun/2014:14:58:55 +0900] "GET /category/electronics HTTP/1.1" 200 128 "-" "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:9.0.1) Gecko/20100101 Firefox/9.0.1" "example.com" "192.168.0.1201102091208001" "901"'
-    entity = @parser.parse(line.chomp, 'combined', %w(vhost usertrack request_duration))
+    parser = ApacheLog::Parser.new('combined', %w(vhost usertrack request_duration))
+    entity = parser.parse(line.chomp)
     expect = {remote_host: '104.24.160.39', identity_check: '-', user: '-', datetime: DateTime.new(2014, 6, 7, 14, 58, 55, 0.375),
       request: {method: 'GET', path: '/category/electronics', protocol: 'HTTP/1.1'}, status: '200', size: '128', referer: '-',
       user_agent: 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:9.0.1) Gecko/20100101 Firefox/9.0.1', vhost: 'example.com',
@@ -64,7 +68,8 @@ describe ApacheLog::Parser do
 
   it 'can parse custom format log based on combined format' 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)" virtualhost.example.jp "192.0.2.16794832933550" "09011112222333_xx.ezweb.ne.jp" 533593';
-    entity = @parser.parse(line.chomp, 'combined', %w(vhost usertrack mobileid request_duration))
+    parser = ApacheLog::Parser.new('combined', %w(vhost usertrack mobileid request_duration))
+    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)', vhost: 'virtualhost.example.jp',
@@ -74,7 +79,8 @@ describe ApacheLog::Parser do
 
   it 'can parse tab separated custom format log based on combined format' do
     line = "203.0.113.254\t-\t-\t[07/Feb/2011:10:59:59 +0900]\t\"GET /x/i.cgi/movie/0001/-0002 HTTP/1.1\"\t200\t14462\t\"http://headlines.yahoo.co.jp/hl\"\t\"DoCoMo/2.0 F08A3(c500;TB;W30H20)\"\t\"virtualhost.example.jp\"\t\"192.0.2.16794832933550\"\t\"09011112222333_xx.ezweb.ne.jp\"\t533593";
-    entity = @parser.parse(line.chomp, 'combined', %w(vhost usertrack mobileid request_duration))
+    parser = ApacheLog::Parser.new('combined', %w(vhost usertrack mobileid request_duration))
+    entity = parser.parse(line.chomp)
     expect = {remote_host: '203.0.113.254', identity_check: '-', user: '-', datetime: DateTime.new(2011, 2, 7, 10, 59, 59, 0.375),
       request: {method: 'GET', path: '/x/i.cgi/movie/0001/-0002', protocol: 'HTTP/1.1'}, status: '200', size: '14462', referer: 'http://headlines.yahoo.co.jp/hl',
       user_agent: 'DoCoMo/2.0 F08A3(c500;TB;W30H20)', vhost: 'virtualhost.example.jp',

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: apache_log-parser
 version: !ruby/object:Gem::Version
-  version: 2.0.2
+  version: 3.0.0
 platform: ruby
 authors:
 - Yuichi Takada
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-08-11 00:00:00.000000000 Z
+date: 2015-02-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -52,9 +52,9 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-description: You can parse common, combined and customized format apache log.
+description: Parse apache log including common, combined and customized format
 email:
-- takadyy@gmail.com
+- takadyuichi@gmail.com
 executables: []
 extensions: []
 extra_rdoc_files: []
@@ -66,6 +66,7 @@ files:
 - README.md
 - Rakefile
 - apache_log-parser.gemspec
+- benchmark.rb
 - lib/apache_log/parser.rb
 - lib/apache_log/parser/version.rb
 - spec/apache_log/parser_spec.rb
@@ -90,10 +91,10 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.0
+rubygems_version: 2.4.5
 signing_key: 
 specification_version: 4
-summary: Gem to parse apache log including common, combined and customized format.
+summary: Parse apache log including common, combined and customized format
 test_files:
 - spec/apache_log/parser_spec.rb
 - spec/spec_helper.rb