Merge pull request #1479 from sergeyfedotov/allow_escape_sequence

Allow escape sequence in Apache access log
fluent · Mar 3, 2017 · 0fe9916 · 0fe9916
1 parent c279a3e
commit 0fe9916
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 1 deletion.
diff --git a/lib/fluent/parser.rb b/lib/fluent/parser.rb
@@ -463,7 +463,7 @@ def parse(text)
     end
 
     class ApacheParser < Parser
-      REGEXP = /^(?<host>[^ ]*) [^ ]* (?<user>[^ ]*) \[(?<time>[^\]]*)\] "(?<method>\S+)(?: +(?<path>[^\"]*?)(?: +\S*)?)?" (?<code>[^ ]*) (?<size>[^ ]*)(?: "(?<referer>[^\"]*)" "(?<agent>[^\"]*)")?$/
+      REGEXP = /^(?<host>[^ ]*) [^ ]* (?<user>[^ ]*) \[(?<time>[^\]]*)\] "(?<method>\S+)(?: +(?<path>(?:[^\"]|\\.)*?)(?: +\S*)?)?" (?<code>[^ ]*) (?<size>[^ ]*)(?: "(?<referer>(?:[^\"]|\\.)*)" "(?<agent>(?:[^\"]|\\.)*)")?$/
       TIME_FORMAT = "%d/%b/%Y:%H:%M:%S %z"
 
       def initialize

diff --git a/test/test_parser.rb b/test/test_parser.rb
@@ -292,6 +292,14 @@ def test_parse_without_http_version
         assert_equal(@expected, record)
       }
     end
+
+    def test_parse_with_escape_sequence
+      @parser.parse('192.168.0.1 - - [28/Feb/2013:12:00:00 +0900] "GET /\" HTTP/1.1" 200 777 "referer \\\ \"" "user agent \\\ \""') { |_, record|
+        assert_equal('/\"', record['path'])
+        assert_equal('referer \\\ \"', record['referer'])
+        assert_equal('user agent \\\ \"', record['agent'])
+      }
+    end
   end
 
   class SyslogParserTest < ::Test::Unit::TestCase