Merge pull request #43 from andsel/size_limit_bytes

Exposes decode_size_limit_bytes setting to limit the line width that the codec can parse. 

Leverages the second parameter of BufferTokenizerExt to thrown an IllegalStateException when the size of the line to parse is bigger than decode_size_limit_bytes.

Co-authored-by: Andrew Cholakian <[email protected]>

Author: andsel

CHANGELOG.md

@@ -1,3 +1,6 @@
+## 3.2.0
+  - Add decode_size_limit_bytes option to limit the maximum size of each JSON line that can be parsed.[#43](https://github.com/logstash-plugins/logstash-codec-json_lines/pull/43)
+
 ## 3.1.0
   - Feat: event `target => namespace` support (ECS) [#41](https://github.com/logstash-plugins/logstash-codec-json_lines/pull/41)
   - Refactor: dropped support for old Logstash versions (< 6.0)

lib/logstash/codecs/json_lines.rb

@@ -42,6 +42,11 @@ class LogStash::Codecs::JSONLines < LogStash::Codecs::Base
   # Change the delimiter that separates lines
   config :delimiter, :validate => :string, :default => "\n"
 
+  # Maximum number of bytes for a single line before a fatal exception is raised
+  # which will stop Logsash.
+  # The default is 20MB which is quite large for a JSON document
+  config :decode_size_limit_bytes, :validate => :number, :default => 20 * (1024 * 1024) # 20MB
+
   # Defines a target field for placing decoded fields.
   # If this setting is omitted, data gets stored at the root (top level) of the event.
   # The target is only relevant while decoding data into a new event.
@@ -50,7 +55,7 @@ class LogStash::Codecs::JSONLines < LogStash::Codecs::Base
   public
 
   def register
-    @buffer = FileWatch::BufferedTokenizer.new(@delimiter)
+    @buffer = FileWatch::BufferedTokenizer.new(@delimiter, @decode_size_limit_bytes)
     @converter = LogStash::Util::Charset.new(@charset)
     @converter.logger = @logger
   end

logstash-codec-json_lines.gemspec

@@ -1,7 +1,7 @@
 Gem::Specification.new do |s|
 
   s.name            = 'logstash-codec-json_lines'
-  s.version         = '3.1.0'
+  s.version         = '3.2.0'
   s.licenses        = ['Apache License (2.0)']
   s.summary         = "Reads and writes newline-delimited JSON"
   s.description     = "This gem is a Logstash plugin required to be installed on top of the Logstash core pipeline using $LS_HOME/bin/logstash-plugin install gemname. This gem is not a stand-alone program"

spec/codecs/json_lines_spec.rb

@@ -118,6 +118,22 @@
       end
     end
 
+    describe "decode_size_limits_bytes" do
+      let(:maximum_payload) { "a" * subject.decode_size_limit_bytes }
+
+      it "should not raise an error if the number of bytes is not exceeded" do
+        expect {
+          subject.decode(maximum_payload)
+        }.not_to raise_error
+      end
+      
+      it "should raise an error if the max bytes are exceeded" do
+        expect {
+          subject.decode(maximum_payload << "z")
+        }.to raise_error(java.lang.IllegalStateException, "input buffer full")
+      end
+    end
+
   end
 
   context "#encode" do