Re-established previous behaviour without a default limit for 'decode_size_limit_bytes'

Author: andsel

docs/index.asciidoc

@@ -35,6 +35,7 @@ Therefore this codec cannot work with line oriented inputs.
 |=======================================================================
 |Setting |Input type|Required
 | <<plugins-{type}s-{plugin}-charset>> |<<string,string>>, one of `["ASCII-8BIT", "UTF-8", "US-ASCII", "Big5", "Big5-HKSCS", "Big5-UAO", "CP949", "Emacs-Mule", "EUC-JP", "EUC-KR", "EUC-TW", "GB2312", "GB18030", "GBK", "ISO-8859-1", "ISO-8859-2", "ISO-8859-3", "ISO-8859-4", "ISO-8859-5", "ISO-8859-6", "ISO-8859-7", "ISO-8859-8", "ISO-8859-9", "ISO-8859-10", "ISO-8859-11", "ISO-8859-13", "ISO-8859-14", "ISO-8859-15", "ISO-8859-16", "KOI8-R", "KOI8-U", "Shift_JIS", "UTF-16BE", "UTF-16LE", "UTF-32BE", "UTF-32LE", "Windows-31J", "Windows-1250", "Windows-1251", "Windows-1252", "IBM437", "IBM737", "IBM775", "CP850", "IBM852", "CP852", "IBM855", "CP855", "IBM857", "IBM860", "IBM861", "IBM862", "IBM863", "IBM864", "IBM865", "IBM866", "IBM869", "Windows-1258", "GB1988", "macCentEuro", "macCroatian", "macCyrillic", "macGreek", "macIceland", "macRoman", "macRomania", "macThai", "macTurkish", "macUkraine", "CP950", "CP951", "IBM037", "stateless-ISO-2022-JP", "eucJP-ms", "CP51932", "EUC-JIS-2004", "GB12345", "ISO-2022-JP", "ISO-2022-JP-2", "CP50220", "CP50221", "Windows-1256", "Windows-1253", "Windows-1255", "Windows-1254", "TIS-620", "Windows-874", "Windows-1257", "MacJapanese", "UTF-7", "UTF8-MAC", "UTF-16", "UTF-32", "UTF8-DoCoMo", "SJIS-DoCoMo", "UTF8-KDDI", "SJIS-KDDI", "ISO-2022-JP-KDDI", "stateless-ISO-2022-JP-KDDI", "UTF8-SoftBank", "SJIS-SoftBank", "BINARY", "CP437", "CP737", "CP775", "IBM850", "CP857", "CP860", "CP861", "CP862", "CP863", "CP864", "CP865", "CP866", "CP869", "CP1258", "Big5-HKSCS:2008", "ebcdic-cp-us", "eucJP", "euc-jp-ms", "EUC-JISX0213", "eucKR", "eucTW", "EUC-CN", "eucCN", "CP936", "ISO2022-JP", "ISO2022-JP2", "ISO8859-1", "ISO8859-2", "ISO8859-3", "ISO8859-4", "ISO8859-5", "ISO8859-6", "CP1256", "ISO8859-7", "CP1253", "ISO8859-8", "CP1255", "ISO8859-9", "CP1254", "ISO8859-10", "ISO8859-11", "CP874", "ISO8859-13", "CP1257", "ISO8859-14", "ISO8859-15", "ISO8859-16", "CP878", "MacJapan", "ASCII", "ANSI_X3.4-1968", "646", "CP65000", "CP65001", "UTF-8-MAC", "UTF-8-HFS", "UCS-2BE", "UCS-4BE", "UCS-4LE", "CP932", "csWindows31J", "SJIS", "PCK", "CP1250", "CP1251", "CP1252", "external", "locale"]`|No
+| <<plugins-{type}s-{plugin}-decode_size_limit_bytes>> |<<string,string>>|No
 | <<plugins-{type}s-{plugin}-delimiter>> |<<string,string>>|No
 | <<plugins-{type}s-{plugin}-ecs_compatibility>> |<<string,string>>|No
 | <<plugins-{type}s-{plugin}-target>> |<<string,string>>|No
@@ -58,6 +59,17 @@ actual encoding of the text and logstash will convert it for you.
 
 For nxlog users, you'll want to set this to `CP1252`
 
+[id="plugins-{type}s-{plugin}-decode_size_limit_bytes"]
+===== `decode_size_limit_bytes`
+
+  * Value type is <<string,string>>
+  * Default value is "none"
+
+Maximum number of bytes for a single line before tagging the event as failure and
+moving forward with a partial string up to this size.
+A possible suggested value 20MB, types as string `"20971520"`, which is quite large for a JSON document.
+Default value is `none` which means no limit.
+
 [id="plugins-{type}s-{plugin}-delimiter"]
 ===== `delimiter` 
 

lib/logstash/codecs/json_lines.rb

@@ -42,10 +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
+  # Maximum number of bytes for a single line before tagging the event as failure and
+  # moving forward with a partial string up to this size.
+  # A possible suggested value 20MB, types as string "20971520", which is quite large for a JSON document.
+  # Default value is none which means no limit.
+  config :decode_size_limit_bytes, :validate => :string, :default => "none"
 
   # Defines a target field for placing decoded fields.
   # If this setting is omitted, data gets stored at the root (top level) of the event.
@@ -55,7 +56,11 @@ class LogStash::Codecs::JSONLines < LogStash::Codecs::Base
   public
 
   def register
-    @buffer = FileWatch::BufferedTokenizer.new(@delimiter, @decode_size_limit_bytes)
+    if @decode_size_limit_bytes == "none"
+      @buffer = FileWatch::BufferedTokenizer.new(@delimiter)
+    else
+      @buffer = FileWatch::BufferedTokenizer.new(@delimiter, @decode_size_limit_bytes.to_i)
+    end
     @converter = LogStash::Util::Charset.new(@charset)
     @converter.logger = @logger
   end

spec/codecs/json_lines_spec.rb

@@ -118,19 +118,31 @@
       end
     end
 
-    describe "decode_size_limits_bytes" do
-      let(:maximum_payload) { "a" * subject.decode_size_limit_bytes }
+    describe "decode_size_limit_bytes" do
+      context "when a value is defined" do
+        let(:decode_size_limit_bytes) { 20 * 1024 * 1024 }
+        let(:codec_options) { { "decode_size_limit_bytes" => decode_size_limit_bytes.to_s } }
+        let(:maximum_payload) { "a" * 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 not raise an error if the number of bytes is not exceeded" do
-        expect {
-          subject.decode(maximum_payload)
-        }.not_to raise_error
+        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
-      
-      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")
+
+      context "when left to default 'none' value" do
+        it "should not raise any error for long big lines" do
+          expect {
+            subject.decode("a" * 30 * 1024 * 1024)
+          }.not_to raise_error
+        end
       end
     end