fluent-plugin-geoip-kk 1.0.2 → 1.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3343f0a6464f46969141b4c6dbc731bf58ff1bddabeecd0f55bfad2a4c21b842
-  data.tar.gz: 7c90087650a115cd023d3cde331d7504ee0540432747554e2150abd6d0ea780d
+  metadata.gz: a09c35276c49497e5ce32dfdb4be3ceb9281a4c74061c057ef63e3f2429c597e
+  data.tar.gz: d61d017ac27cd4ec7d7d3b448df7e34713dde36b36792cc7f43ee71dc88dc583
 SHA512:
-  metadata.gz: dfd08a491d65964d1ed9ec4927ed1041f07f5a376b91b36cabf4a18c430854a7e1241fb3cbc73c65d9eb1d912f9f509659939dae5223cc4e0a63ca9cfafa6855
-  data.tar.gz: 4f534578358e07d02a193f9019c143304e8c3ef4997a22bf14f52ce8ec384884b804a12d9130ab84c281c4d34ec873dc270f63c216a5a6c6c8246613913f36df
+  metadata.gz: '06163815ea4dcd37e4e42bad34d00991f7b38d21a1b05fb9b99f73821c45f570fa1706986b495d9e9225342ec0ea4cba73f4c5d26c92b161a1df19a5fdf77e1d'
+  data.tar.gz: fc25e0ab574149dcf1cc1bcd92e8d2ea6924b9ad2c9e955caca1b871a29aa002f5e802b4920e139b07b407c9587ca36a6ff8cc3b250e27823ac0e97460dd9fcc

data/README.md

@@ -9,7 +9,7 @@
 
 | fluent-plugin-geoip-kk | fluentd    | ruby   |
 |----------------------------|------------|--------|
-| >= 1.0.1                   | >= v0.14.0 | >= 2.1 |
+| >= 1.0.2                   | >= v0.14.0 | >= 2.1 |
 | < 1.0.0                    | >= v0.12.0 | >= 1.9 |
 
 
@@ -23,66 +23,149 @@ $ gem install fluent-plugin-geoip-kk
 $ sudo td-agent-gem install fluent-plugin-geoip-kk
 ```
 
+## Configuration Parameters
 
-## Usage
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| key_name | string | client_ip | Field name that contains the IP address |
+| out_key | string | geo | Output field name to store GeoIP data |
+| database_path | string | data/GeoLite2-City.mmdb | Path to the GeoIP database file |
+| flatten | bool | false | Flatten the GeoIP data structure |
+| cache_size | integer | 8192 | Size of the LRU cache |
+| cache_ttl | integer | 3600 | TTL for cached items in seconds |
+| skip_private_ip | bool | true | Skip adding GeoIP data for private IP addresses |
 
-### Example 1:
+## Usage Examples
+
+### Basic Configuration
+
+```xml
+<filter access.nginx.**>
+  @type geoip
+  key_name client_ip
+  out_key geo
+</filter>
+```
+
+### Advanced Configuration
 
 ```xml
 <filter access.nginx.**>
   @type geoip
-  # key_name client_ip
-  # database_path /data/geoip/GeoLite2-City.mmdb
-  # out_key geo
+
+  # IP address field configuration
+  key_name client_ip
+  out_key geo
+
+  # Database configuration
+  database_path /path/to/GeoLite2-City.mmdb
+
+  # Cache configuration
+  cache_size 10000    # Cache up to 10000 IP addresses
+  cache_ttl 3600      # Cache TTL: 1 hour
+
+  # Output configuration
+  flatten false       # Keep nested structure
+
+  # IP processing configuration
+  skip_private_ip true  # Skip private IP addresses
 </filter>
 ```
 
-Assuming following inputs are coming:
+### Input Example
 
 ```json
-access.nginx: {
-  "client_ip":"93.184.216.34",
-  "scheme":"http", "method":"GET", "host":"example.com",
-  "path":"/", "query":"-", "req_bytes":200, "referer":"-",
-  "status":200, "res_bytes":800, "res_body_bytes":600, "taken_time":0.001, "user_agent":"Mozilla/5.0"
+{
+  "client_ip": "93.184.216.34",
+  "scheme": "http",
+  "method": "GET",
+  "host": "example.com",
+  "path": "/",
+  "query": "-",
+  "req_bytes": 200,
+  "referer": "-",
+  "status": 200,
+  "res_bytes": 800,
+  "res_body_bytes": 600,
+  "taken_time": 0.001,
+  "user_agent": "Mozilla/5.0"
 }
 ```
 
-then output bocomes as belows:
+### Output Example (Default Structure)
 
 ```json
-access.nginx: {
-  "client_ip":"93.184.216.34",
-  "scheme":"http", "method":"GET", "host":"example.com",
-  "path":"/", "query":"-", "req_bytes":200, "referer":"-",
-  "status":200, "res_bytes":800, "res_body_bytes":600, "taken_time":0.001, "user_agent":"Mozilla/5.0",
+{
+  "client_ip": "93.184.216.34",
+  "scheme": "http",
+  "method": "GET",
+  // ... other original fields ...
   "geo": {
-    "coordinates": [-70.8228, 42.150800000000004],
-    "country_code": "US",
-    "city": "Norwell",
-    "region_code": "MA",
+    "coordinates": {
+      "latitude": 42.150800000000004,
+      "longitude": -70.8228,
+      "accuracy_radius": 100
+    },
+    "country": {
+      "code": "US",
+      "name": "United States"
+    },
+    "city": {
+      "name": "Norwell",
+      "confidence": 90
+    },
+    "region": {
+      "code": "MA",
+      "name": "Massachusetts"
+    },
+    "postal": {
+      "code": "02061",
+      "confidence": 95
+    },
+    "timezone": "America/New_York"
   }
 }
 ```
 
+### Output Example (Flattened Structure)
 
-## Parameters
-- key_name *field_key*
+When `flatten true` is specified:
 
-    Target key name. default client_ip.
-
-- out_key *string*
+```json
+{
+  "client_ip": "93.184.216.34",
+  // ... other original fields ...
+  "geo_coordinates_latitude": 42.150800000000004,
+  "geo_coordinates_longitude": -70.8228,
+  "geo_coordinates_accuracy_radius": 100,
+  "geo_country_code": "US",
+  "geo_country_name": "United States",
+  "geo_city_name": "Norwell",
+  "geo_city_confidence": 90,
+  "geo_region_code": "MA",
+  "geo_region_name": "Massachusetts",
+  "geo_postal_code": "02061",
+  "geo_postal_confidence": 95,
+  "geo_timezone": "America/New_York"
+}
+```
 
-    Output prefix key name. default geo.
+## Performance Optimization
 
-- database_path *file_path*
+The plugin includes several performance optimizations:
 
-    Database file(GeoIPCity.dat) path.
-    Get from [MaxMind](http://dev.maxmind.com/geoip/legacy/geolite/)
+1. LRU Cache with TTL
+   - Caches GeoIP lookups to reduce database access
+   - Configurable cache size and TTL
+   - Automatic cache cleanup for expired entries
 
-- flatten *bool*
-    join hashed data by '_'. default false.
+2. Skip Private IPs
+   - Optionally skip processing private IP addresses
+   - Reduces unnecessary database lookups
 
+3. Efficient Record Access
+   - Uses Fluentd's record accessor for optimized field access
+   - Reduces memory allocations
 
 ## VS.
 [fluent-plugin-geoip](https://github.com/y-ken/fluent-plugin-geoip)
@@ -95,7 +178,6 @@ It is able to customize fields with placeholder.
 * 5-10 times faster by the LRU cache.
     * See [benchmark](test/bench_geoip_filter.rb).
 
-
 ## Development
 
 After checking out the repo, run `bundle install` to install dependencies. Then, run `rake test` to run the tests.
@@ -127,12 +209,10 @@ This gem uses GitHub Actions for automated publishing. To publish a new version:
 4. Push to the branch (`git push origin my-new-feature`)
 5. Create a new Pull Request
 
-
 ## Copyright
 
 Copyright (c) 2015 Yuri Umezaki
 
-
 ## License
 
 [Apache License, Version 2.0.](http://www.apache.org/licenses/LICENSE-2.0)

data/fluent-plugin-geoip-kk.gemspec

@@ -5,7 +5,7 @@ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 
 Gem::Specification.new do |spec|
   spec.name          = 'fluent-plugin-geoip-kk'
-  spec.version       = '1.0.2'
+  spec.version       = '1.0.3'
   spec.authors       = ['kevin197011']
   spec.email         = ['kevin197011@outlook.com']
   spec.homepage      = 'https://github.com/kevin197011/fluent-plugin-geoip-kk'

data/lib/fluent/plugin/filter_geoip.rb

@@ -63,7 +63,7 @@ module Fluent
         # Initialize cache with TTL support
         @geoip_cache = LruRedux::TTL::Cache.new(@cache_size, @cache_ttl)
 
-        log.info "Initialized GeoIP filter", database: @database_path, cache_size: @cache_size, cache_ttl: @cache_ttl
+        log.info 'Initialized GeoIP filter', database: @database_path, cache_size: @cache_size, cache_ttl: @cache_ttl
       end
 
       def filter(tag, time, record)
@@ -74,7 +74,7 @@ module Fluent
           ip = IPAddr.new(ip_addr)
           return record if @skip_private_ip && ip.private?
         rescue IPAddr::InvalidAddressError => e
-          log.debug "Invalid IP address", ip: ip_addr, error: e.message
+          log.debug 'Invalid IP address', ip: ip_addr, error: e.message
           return record
         end
 
@@ -89,7 +89,7 @@ module Fluent
 
         record
       rescue StandardError => e
-        log.error "Failed to process GeoIP lookup", error_class: e.class, error: e.message, tag: tag, time: time
+        log.error 'Failed to process GeoIP lookup', error_class: e.class, error: e.message, tag: tag, time: time
         record
       end
 
@@ -99,61 +99,93 @@ module Fluent
         geo_ip = @geoip.lookup(ip_addr)
         return {} if geo_ip.nil?
 
-        {
-          'coordinates' => get_coordinates(geo_ip),
-          'country' => get_country_info(geo_ip),
-          'city' => get_city_info(geo_ip),
-          'region' => get_region_info(geo_ip),
-          'postal' => get_postal_info(geo_ip),
-          'timezone' => geo_ip.location&.time_zone
-        }.compact
+        result = {}
+
+        if coordinates = get_coordinates(geo_ip)
+          result['coordinates'] = coordinates
+        end
+
+        if country = get_country_info(geo_ip)
+          result['country'] = country
+        end
+
+        if city = get_city_info(geo_ip)
+          result['city'] = city
+        end
+
+        if region = get_region_info(geo_ip)
+          result['region'] = region
+        end
+
+        if postal = get_postal_info(geo_ip)
+          result['postal'] = postal
+        end
+
+        result['timezone'] = geo_ip.location.time_zone if geo_ip.location && geo_ip.location.time_zone
+
+        result
       end
 
       def get_coordinates(geo_ip)
         return nil unless geo_ip.location
 
-        {
-          'latitude' => geo_ip.location.latitude,
-          'longitude' => geo_ip.location.longitude,
-          'accuracy_radius' => geo_ip.location.accuracy_radius
-        }.compact
+        result = {}
+        location = geo_ip.location
+
+        result['latitude'] = location.latitude if location.latitude
+        result['longitude'] = location.longitude if location.longitude
+        result['accuracy_radius'] = location.accuracy_radius if location.accuracy_radius
+
+        result.empty? ? nil : result
       end
 
       def get_country_info(geo_ip)
         return nil unless geo_ip.country
 
-        {
-          'code' => geo_ip.country.iso_code,
-          'name' => geo_ip.country.name
-        }.compact
+        result = {}
+        country = geo_ip.country
+
+        result['code'] = country.iso_code if country.iso_code
+        result['name'] = country.name if country.name
+
+        result.empty? ? nil : result
       end
 
       def get_city_info(geo_ip)
         return nil unless geo_ip.city
 
-        {
-          'name' => geo_ip.city.name,
-          'confidence' => geo_ip.city.confidence
-        }.compact
+        result = {}
+        city = geo_ip.city
+
+        result['name'] = city.name if city.name
+        result['confidence'] = city.confidence if city.confidence
+
+        result.empty? ? nil : result
       end
 
       def get_region_info(geo_ip)
-        return nil unless geo_ip.subdivisions&.any?
+        return nil unless geo_ip.subdivisions && !geo_ip.subdivisions.empty?
 
         subdivision = geo_ip.subdivisions.first
-        {
-          'code' => subdivision.iso_code,
-          'name' => subdivision.name
-        }.compact
+        return nil unless subdivision
+
+        result = {}
+        result['code'] = subdivision.iso_code if subdivision.iso_code
+        result['name'] = subdivision.name if subdivision.name
+
+        result.empty? ? nil : result
       end
 
       def get_postal_info(geo_ip)
         return nil unless geo_ip.postal
 
-        {
-          'code' => geo_ip.postal.code,
-          'confidence' => geo_ip.postal.confidence
-        }.compact
+        result = {}
+        postal = geo_ip.postal
+
+        result['code'] = postal.code if postal.code
+        result['confidence'] = postal.confidence if postal.confidence
+
+        result.empty? ? nil : result
       end
 
       def hash_flatten(hash, keys = [])

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: fluent-plugin-geoip-kk
 version: !ruby/object:Gem::Version
-  version: 1.0.2
+  version: 1.0.3
 platform: ruby
 authors:
 - kevin197011