remove regex for strip unicode bom

Signed-off-by: BananaWanted <i@BananaWanted.com>
fluent · Feb 4, 2020 · 3926f89 · 3926f89
1 parent 7c80113
commit 3926f89
Show file tree

Hide file tree

Showing 2 changed files with 1 addition and 18 deletions.
diff --git a/lib/fluent/plugin/parser_syslog.rb b/lib/fluent/plugin/parser_syslog.rb
@@ -27,7 +27,7 @@ class SyslogParser < Parser
       REGEXP = /^(?<time>[^ ]*\s*[^ ]* [^ ]*) (?<host>[^ ]*) (?<ident>[^ :\[]*)(?:\[(?<pid>[0-9]+)\])?(?:[^\:]*\:)? *(?<message>.*)$/
       # From in_syslog default pattern
       REGEXP_WITH_PRI = /^\<(?<pri>[0-9]+)\>(?<time>[^ ]* {1,2}[^ ]* [^ ]*) (?<host>[^ ]*) (?<ident>[^ :\[]*)(?:\[(?<pid>[0-9]+)\])?(?:[^\:]*\:)? *(?<message>.*)$/
-      REGEXP_RFC5424 = "(?<time>[^ ]+) (?<host>[!-~]{1,255}) (?<ident>[!-~]{1,48}) (?<pid>[!-~]{1,128}) (?<msgid>[!-~]{1,32}) (?<extradata>(?:\\-|(?:\\[.*?(?<!\\\\)\\])+))(?: (?:\xef\xbb\xbf)?(?<message>.+))?"
+      REGEXP_RFC5424 = "(?<time>[^ ]+) (?<host>[!-~]{1,255}) (?<ident>[!-~]{1,48}) (?<pid>[!-~]{1,128}) (?<msgid>[!-~]{1,32}) (?<extradata>(?:\\-|(?:\\[.*?(?<!\\\\)\\])+))(?: (?<message>.+))?"
       REGEXP_RFC5424_NO_PRI = Regexp.new('\\A' + REGEXP_RFC5424 + '\\z', Regexp::MULTILINE)
       REGEXP_RFC5424_WITH_PRI = Regexp.new('\\A<(?<pri>[0-9]{1,3})\\>[1-9]\\d{0,2} ' + REGEXP_RFC5424 + '\\z', Regexp::MULTILINE)
       REGEXP_DETECT_RFC5424 = /^\<.*\>[1-9]\d{0,2}/

diff --git a/test/plugin/test_parser_syslog.rb b/test/plugin/test_parser_syslog.rb
@@ -356,23 +356,6 @@ def test_parse_with_rfc5424_empty_message
       end
     end
 
-    def test_parse_with_rfc5424_message_prefixed_unicode_bom
-      @parser.configure(
-                        'time_format' => '%Y-%m-%dT%H:%M:%S.%L%z',
-                        'message_format' => 'rfc5424',
-                        'with_priority' => true,
-                        )
-      text = "<16>1 2017-02-06T13:14:15.003Z 192.168.0.1 fluentd 11111 ID24224 [exampleSDID@20224 iut=\"3\" eventSource=\"Application\" eventID=\"11211\"] \xef\xbb\xbf[message]\n"
-      @parser.instance.parse(text) do |time, record|
-        assert_equal(event_time("2017-02-06T13:14:15.003Z", format: '%Y-%m-%dT%H:%M:%S.%L%z'), time)
-        assert_equal "11111", record["pid"]
-        assert_equal "ID24224", record["msgid"]
-        assert_equal "[exampleSDID@20224 iut=\"3\" eventSource=\"Application\" eventID=\"11211\"]",
-                     record["extradata"]
-        assert_equal "[message]", record["message"]
-      end
-    end
-
     def test_parse_with_rfc5424_message_without_subseconds
       @parser.configure(
                         'message_format' => 'rfc5424',