Sha256: 6b2bb6be8e38ce9d059cfd22c0b898ef3899d7ae7d0324034249f5a6e941a23b
Contents?: true
Size: 1.16 KB
Versions: 234
Compression:
Stored size: 1.16 KB
Contents
# encoding: utf-8
require "logstash/namespace"
require "logstash/util"
class LogStash::Util::Charset
attr_accessor :logger
def initialize(charset)
@charset = charset
@charset_encoding = Encoding.find(charset)
end
def convert(data)
data.force_encoding(@charset_encoding)
# NON UTF-8 charset declared.
# Let's convert it (as cleanly as possible) into UTF-8 so we can use it with JSON, etc.
return data.encode(Encoding::UTF_8, :invalid => :replace, :undef => :replace) unless @charset_encoding == Encoding::UTF_8
# UTF-8 charset declared.
# Some users don't know the charset of their logs or just don't know they
# can set the charset setting.
unless data.valid_encoding?
# A silly hack to help convert some of the unknown bytes to
# somewhat-readable escape codes. The [1..-2] is to trim the quotes
# ruby puts on the value.
return data.inspect[1..-2].tap do |escaped|
@logger.warn("Received an event that has a different character encoding than you configured.", :text => escaped, :expected_charset => @charset)
end
end
return data
end # def convert
end # class LogStash::Util::Charset
Version data entries
234 entries across 225 versions & 17 rubygems