Created
May 28, 2019 19:29
-
-
Save YanhaoYang/9d762d05631c604d9d84636f111f8d28 to your computer and use it in GitHub Desktop.
Parse Heroku logs and index the logs in Elasticsearch
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require 'elasticsearch' | |
require 'time' | |
client = Elasticsearch::Client.new host: "172.17.0.1", log: true | |
mappings = { | |
mappings: { | |
log: { | |
properties: { | |
ts: { type: 'date' }, | |
service: { type: 'long' }, | |
connect: { type: 'long' }, | |
} | |
} | |
} | |
} | |
index_name = "logs" | |
client.indices.create index: index_name, body: mappings | |
bulk_body = [] | |
File.open('veh.log') do |f| | |
f.each_line do |ln| | |
fields = ln.split | |
next unless fields[3] == "heroku" && fields[4] == "router" | |
data = {ts: Time.parse(fields[2]).iso8601} | |
fields.each_with_index do |c, idx| | |
if c =~ /\A(\w+)="?(.+?)"?\z/ | |
data[$1.to_sym] = $2 | |
end | |
end | |
if(pos = data[:path].index("?")) | |
data[:short_path] = data[:path][0...pos] | |
else | |
data[:short_path] = data[:path] | |
end | |
if(pos = data[:fwd].index(",")) | |
data[:client_ip] = data[:fwd][0...pos] | |
else | |
data[:client_ip] = data[:fwd] | |
end | |
data[:connect] = data[:connect].to_i | |
data[:service] = data[:service].to_i | |
#client.index index: index_name, type: 'log', body: data, refresh: true | |
bulk_body << { index: { _index: index_name, _type: 'log'} } | |
bulk_body << data | |
if bulk_body.size > 100 | |
client.bulk body: bulk_body | |
bulk_body.clear | |
end | |
end | |
end | |
client.bulk body: bulk_body unless bulk_body.empty? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment