server_log_parser 0.4.0 → 0.4.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 99d0578102face3c2664838e749c0de0192322ab
-  data.tar.gz: 8d2030582ca02f1e9cd98ee0f773be0baeb0e7d1
+  metadata.gz: d3822fbfb155d2237d6637152c03a9447a426f6c
+  data.tar.gz: 80160b6064711a43c94bfe5a367dcabf03f8d533
 SHA512:
-  metadata.gz: a677d61e5c9ffadf121726262b38b05b19c49883ce5f1b0f4bcb223ce3c04dfdd9c4489179c510213e54931255c9b90140fad2dcc985190dd9ee3af5aabf8d15
-  data.tar.gz: 34176519e78657e8e67c4639d4baa1a7faf92af489e8e2d26027cda42fe3cfad8a57703acc0e6d193af53fcb510a8380d612e08187541cfdea6b5522591421d4
+  metadata.gz: 746b9986ac7183eb3397aff0b28e90a1c82cbb387c3116d3937219acdc1c5b030af62384a13407e19f0f7bad48c5e6480ecd48f34544e99ba2d0abd74dde894f
+  data.tar.gz: 1a8a50ebb3ed4750d1580bf604f12af65a2871e3b577b159d10912d046f40ed259cc66a1b141bf4e166b6ba1413c6f51b0c6a595769d8e4493d0ec2eb547a85b

data/Rakefile

@@ -1,7 +1,7 @@
 require "rake/testtask"
 Rake::TestTask.new do |t|
   t.libs << "test"
-  t.test_files = FileList['test/*_test.rb']
+  t.test_files = FileList['test/**/*_test.rb']
   t.verbose = true
 end
 

data/lib/server_log_parser/parser.rb

@@ -91,25 +91,20 @@ module ServerLogParser
         format.strip!                # remove leading and trailing space
         format.gsub!(/[ \t]+/, ' ')  # replace tabulations or spaces with a space
 
-        strip_quotes = proc { |string| string.gsub(/^\\"/, '').gsub(/\\"$/, '') }
-        find_quotes  = proc { |string| string =~ /^\\"/ }
-        find_percent = proc { |string| string =~ /^%.*t$/ }
-        find_referrer_or_useragent = proc { |string| string =~ /Referer|User-Agent/ }
-
         pattern = format.split(' ').map do |element|
-          has_quotes = !!find_quotes.call(element)
-          element = strip_quotes.call(element) if has_quotes
+          has_quotes = element =~ /^\\"/
+          element = element.gsub(/^\\"/, '').gsub(/\\"$/, '') if has_quotes
 
           self.names << rename_this_name(element)
 
           case
             when has_quotes
-              if element == '%r' or find_referrer_or_useragent.call(element)
+              if element == '%r' || element =~ /^%{Referer}/ || element =~ /^%{User-agent}/
                 /"([^"\\]*(?:\\.[^"\\]*)*)"/
               else
                 '\"([^\"]*)\"'
               end
-            when find_percent.call(element)
+            when element =~ /^%.*t$/
                 '(\[[^\]]+\])'
             when element == '%U'
                 '(.+?)'

data/lib/server_log_parser/version.rb

@@ -1,5 +1,5 @@
 module ServerLogParser
 
-  VERSION = "0.4.0"
+  VERSION = "0.4.1"
 
 end

data/test/fixtures/line_with_slash_quote_in_user-agent.log

@@ -0,0 +1 @@
+212.74.15.68 - - [23/Jan/2004:11:36:20 +0000] "GET /images/previous.png HTTP/1.1" 200 2607 "http://peterhi.dyndns.org/bandwidth/index.html" "Mozilla/5.0 (X11; U; Linux \"Superman\\Superwoman\" i686; en-US; rv:1.2) Gecko/20021202"

data/test/{parser_test.rb → server_log_parser/parser_test.rb}

@@ -13,7 +13,7 @@ describe ServerLogParser::Parser do
   end
 
   before do
-    @format = '%h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-Agent}i\"'
+    @format = '%h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-agent}i\"'
     @parser = ServerLogParser::Parser.new(@format)
   end
 
@@ -28,7 +28,7 @@ describe ServerLogParser::Parser do
                    '%>s' => '200',
                    '%b'  => '2607',
                    '%{Referer}i'     => 'http://peterhi.dyndns.org/bandwidth/index.html',
-                   '%{User-Agent}i'  => 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.2) Gecko/20021202' }
+                   '%{User-agent}i'  => 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.2) Gecko/20021202' }
       results = @parser.parse(read_testcase('line.log'))
 
       assert_kind_of(Hash, results)
@@ -44,8 +44,24 @@ describe ServerLogParser::Parser do
                    '%>s' => '200',
                    '%b'  => '2607',
                    '%{Referer}i'     => 'http://peterhi.dyndns.org/bandwidth/index.html',
-                   '%{User-Agent}i'  => 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.2) Gecko/20021202' }
-      results = @parser.parse(read_testcase('line-with-slash-quote-in-request.log'))
+                   '%{User-agent}i'  => 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.2) Gecko/20021202' }
+      results = @parser.parse(read_testcase('line_with_slash_quote_in_request.log'))
+
+      assert_kind_of(Hash, results)
+      assert_match_expected_hash(expected, results)
+    end
+
+    it "should parse line with slash quote in user agent" do
+      expected = { '%h'  => '212.74.15.68',
+                   '%l'  => '-',
+                   '%u'  => '-',
+                   '%t'  => '[23/Jan/2004:11:36:20 +0000]',
+                   '%r'  => 'GET /images/previous.png HTTP/1.1',
+                   '%>s' => '200',
+                   '%b'  => '2607',
+                   '%{Referer}i'     => 'http://peterhi.dyndns.org/bandwidth/index.html',
+                   '%{User-agent}i'  => 'Mozilla/5.0 (X11; U; Linux \\"Superman\\\\Superwoman\\" i686; en-US; rv:1.2) Gecko/20021202' }
+      results = @parser.parse(read_testcase('line_with_slash_quote_in_user-agent.log'))
 
       assert_kind_of(Hash, results)
       assert_match_expected_hash(expected, results)
@@ -60,8 +76,8 @@ describe ServerLogParser::Parser do
                    '%>s' => '200',
                    '%b'  => '2888',
                    '%{Referer}i'     => 'http://search.yahoo.com/bin/search?p=\"grady%20white%20306%20bimini\"',
-                   '%{User-Agent}i'  => 'Mozilla/4.0 (compatible; MSIE 6.0; Windows 98; YPC 3.0.3; yplus 4.0.00d)' }
-      results = @parser.parse(read_testcase('line-with-slash-quote-in-referer.log'))
+                   '%{User-agent}i'  => 'Mozilla/4.0 (compatible; MSIE 6.0; Windows 98; YPC 3.0.3; yplus 4.0.00d)' }
+      results = @parser.parse(read_testcase('line_with_slash_quote_in_referer.log'))
 
       assert_kind_of(Hash, results)
       assert_match_expected_hash(expected, results)
@@ -104,7 +120,7 @@ describe ServerLogParser::Parser do
                    '%>s' => 200,
                    '%b'  => 2607,
                    '%{Referer}i'     => 'http://peterhi.dyndns.org/bandwidth/index.html',
-                   '%{User-Agent}i'  => 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.2) Gecko/20021202' }
+                   '%{User-agent}i'  => 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.2) Gecko/20021202' }
       results = @parser.handle(read_testcase('line.log'))
 
       assert_kind_of(Hash, results)

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: server_log_parser
 version: !ruby/object:Gem::Version
-  version: 0.4.0
+  version: 0.4.1
 platform: ruby
 authors:
 - Alexander Kurakin
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-02-16 00:00:00.000000000 Z
+date: 2016-04-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -71,10 +71,11 @@ files:
 - lib/server_log_parser/parser.rb
 - lib/server_log_parser/version.rb
 - server_log_parser.gemspec
-- test/fixtures/line-with-slash-quote-in-referer.log
-- test/fixtures/line-with-slash-quote-in-request.log
 - test/fixtures/line.log
-- test/parser_test.rb
+- test/fixtures/line_with_slash_quote_in_referer.log
+- test/fixtures/line_with_slash_quote_in_request.log
+- test/fixtures/line_with_slash_quote_in_user-agent.log
+- test/server_log_parser/parser_test.rb
 - test/server_log_parser_test.rb
 - test/test_helper.rb
 homepage: https://github.com/kuraga/server_log_parser
@@ -102,9 +103,10 @@ signing_key:
 specification_version: 4
 summary: Ruby library to parse Apache server log files using regular expressions.
 test_files:
-- test/fixtures/line-with-slash-quote-in-referer.log
-- test/fixtures/line-with-slash-quote-in-request.log
 - test/fixtures/line.log
-- test/parser_test.rb
+- test/fixtures/line_with_slash_quote_in_referer.log
+- test/fixtures/line_with_slash_quote_in_request.log
+- test/fixtures/line_with_slash_quote_in_user-agent.log
+- test/server_log_parser/parser_test.rb
 - test/server_log_parser_test.rb
 - test/test_helper.rb