[processor/geoip] Add GeoIP providers configuration and maxmind factory

.chloggen/geoipprocessor_provider.yaml

@@ -0,0 +1,27 @@
+# Use this changelog template to create an entry for release notes.
+
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: 'enhancement'
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: geoipprocessor
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Add providers configuration and maxmind provider factory
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [33269]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext:
+
+# If your change doesn't affect end users or the exported elements of any package,
+# you should instead start your pull request title with [chore] or use the "Skip Changelog" label.
+# Optional: The change log or logs in which this entry should be included.
+# e.g. '[user]' or '[user, api]'
+# Include 'user' if the change is relevant to end users.
+# Include 'api' if there is a change to a library API.
+# Default: '[user]'
+change_logs: []

processor/geoipprocessor/README.md

@@ -11,8 +11,42 @@
 [development]: https://github.com/open-telemetry/opentelemetry-collector#development
 <!-- end autogenerated section -->
 
-**This processor is currently under development and is presently a NOP (No Operation) processor. Further features and functionalities will be added in upcoming versions.**
-
 ## Description
 
 The geoIP processor `geoipprocessor` enhances resource attributes by appending information about the geographical location of an IP address. To add geographical information, the IP address must be included in the resource attributes using the [`source.address` semantic conventions key attribute](https://github.com/open-telemetry/semantic-conventions/blob/v1.26.0/docs/general/attributes.md#source).
+
+### Geographical location metadata
+
+The following [resource attributes](./internal/convention/attributes.go) will be added if the corresponding information is found:
+
+```
+  * geo.city_name
+  * geo.postal_code
+  * geo.country_name
+  * geo.country_iso_code
+  * geo.continent_name
+  * geo.continent_code
+  * geo.region_name
+  * geo.region_iso_code
+  * geo.timezone
+  * geo.location.lat
+  * geo.location.lon
+```
+
+## Configuration
+
+The following settings must be configured:
+
+- `providers`: A map containing geographical location information providers. These providers are used to search for the geographical location attributes associated with an IP. Supported providers:
+  - [maxmind](./internal/provider/maxmindprovider/README.md)
+
+#### Examples
+
+```yaml
+processors:
+    # processor name: geoip
+    geoip:
+      providers:
+        maxmind:
+          database_path: /tmp/mygeodb
+```

processor/geoipprocessor/config.go

@@ -3,9 +3,85 @@
 
 package geoipprocessor // import "github.com/open-telemetry/opentelemetry-collector-contrib/processor/geoipprocessor"
 
+import (
+	"errors"
+	"fmt"
+
+	"go.opentelemetry.io/collector/component"
+	"go.opentelemetry.io/collector/confmap"
+
+	"github.com/open-telemetry/opentelemetry-collector-contrib/processor/geoipprocessor/internal/provider"
+)
+
+const (
+	providersKey = "providers"
+)
+
 // Config holds the configuration for the GeoIP processor.
-type Config struct{}
+type Config struct {
+	// Providers specifies the sources to extract geographical information about a given IP.
+	Providers map[string]provider.Config `mapstructure:"-"`
+}
+
+var (
+	_ component.Config    = (*Config)(nil)
+	_ confmap.Unmarshaler = (*Config)(nil)
+)
 
 func (cfg *Config) Validate() error {
+	if len(cfg.Providers) == 0 {
+		return errors.New("must specify at least one geo IP data provider when using the geoip processor")
+	}
+
+	// validate all provider's configuration
+	for providerID, providerConfig := range cfg.Providers {
+		if err := providerConfig.Validate(); err != nil {
+			return fmt.Errorf("error validating provider %s: %w", providerID, err)
+		}
+	}
+	return nil
+}
+
+// Unmarshal a config.Parser into the config struct.
+func (cfg *Config) Unmarshal(componentParser *confmap.Conf) error {
+	if componentParser == nil {
+		return nil
+	}
+
+	// load the non-dynamic config normally
+	err := componentParser.Unmarshal(cfg, confmap.WithIgnoreUnused())
+	if err != nil {
+		return err
+	}
+
+	// dynamically load the individual providers configs based on the key name
+	cfg.Providers = map[string]provider.Config{}
+
+	// retrieve `providers` configuration section
+	providersSection, err := componentParser.Sub(providersKey)
+	if err != nil {
+		return err
+	}
+
+	// loop through all defined providers and load their configuration
+	for key := range providersSection.ToStringMap() {
+		factory, ok := getProviderFactory(key)
+		if !ok {
+			return fmt.Errorf("invalid provider key: %s", key)
+		}
+
+		providerCfg := factory.CreateDefaultConfig()
+		providerSection, err := providersSection.Sub(key)
+		if err != nil {
+			return err
+		}
+		err = providerSection.Unmarshal(providerCfg)
+		if err != nil {
+			return fmt.Errorf("error reading settings for provider type %q: %w", key, err)
+		}
+
+		cfg.Providers[key] = providerCfg
+	}
+
 	return nil
 }

processor/geoipprocessor/config_test.go

@@ -4,28 +4,48 @@
 package geoipprocessor
 
 import (
+	"errors"
 	"path/filepath"
 	"testing"
 
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 	"go.opentelemetry.io/collector/component"
+	"go.opentelemetry.io/collector/confmap"
 	"go.opentelemetry.io/collector/confmap/confmaptest"
+	"go.opentelemetry.io/collector/confmap/provider/fileprovider"
+	"go.opentelemetry.io/collector/otelcol"
+	"go.opentelemetry.io/collector/otelcol/otelcoltest"
 
 	"github.com/open-telemetry/opentelemetry-collector-contrib/processor/geoipprocessor/internal/metadata"
+	"github.com/open-telemetry/opentelemetry-collector-contrib/processor/geoipprocessor/internal/provider"
+	maxmind "github.com/open-telemetry/opentelemetry-collector-contrib/processor/geoipprocessor/internal/provider/maxmindprovider"
 )
 
 func TestLoadConfig(t *testing.T) {
 	t.Parallel()
 
 	tests := []struct {
-		id           component.ID
-		expected     component.Config
-		errorMessage string
+		id                    component.ID
+		expected              component.Config
+		validateErrorMessage  string
+		unmarshalErrorMessage string
 	}{
 		{
-			id:       component.NewID(metadata.Type),
-			expected: &Config{},
+			id:                   component.NewID(metadata.Type),
+			validateErrorMessage: "must specify at least one geo IP data provider when using the geoip processor",
+		},
+		{
+			id: component.NewIDWithName(metadata.Type, "maxmind"),
+			expected: &Config{
+				Providers: map[string]provider.Config{
+					"maxmind": &maxmind.Config{DatabasePath: "/tmp/db"},
+				},
+			},
+		},
+		{
+			id:                    component.NewIDWithName(metadata.Type, "invalid_providers_config"),
+			unmarshalErrorMessage: "unexpected sub-config value kind for key:providers value:this should be a map kind:string)",
 		},
 	}
 
@@ -39,10 +59,15 @@ func TestLoadConfig(t *testing.T) {
 
 			sub, err := cm.Sub(tt.id.String())
 			require.NoError(t, err)
+
+			if tt.unmarshalErrorMessage != "" {
+				assert.EqualError(t, sub.Unmarshal(cfg), tt.unmarshalErrorMessage)
+				return
+			}
 			require.NoError(t, sub.Unmarshal(cfg))
 
-			if tt.errorMessage != "" {
-				assert.EqualError(t, component.ValidateConfig(cfg), tt.errorMessage)
+			if tt.validateErrorMessage != "" {
+				assert.EqualError(t, component.ValidateConfig(cfg), tt.validateErrorMessage)
 				return
 			}
 
@@ -51,3 +76,102 @@ func TestLoadConfig(t *testing.T) {
 		})
 	}
 }
+
+func TestLoadConfig_InvalidProviderKey(t *testing.T) {
+	factories, err := otelcoltest.NopFactories()
+	require.NoError(t, err)
+
+	factory := NewFactory()
+	factories.Processors[metadata.Type] = factory
+	_, err = otelcoltest.LoadConfigAndValidateWithSettings(factories, otelcol.ConfigProviderSettings{
+		ResolverSettings: confmap.ResolverSettings{
+			URIs: []string{filepath.Join("testdata", "config-invalidProviderKey.yaml")},
+			ProviderFactories: []confmap.ProviderFactory{
+				fileprovider.NewFactory(),
+			},
+		},
+	},
+	)
+
+	require.Contains(t, err.Error(), "error reading configuration for \"geoip\": invalid provider key: invalidProviderKey")
+}
+
+func TestLoadConfig_ValidProviderKey(t *testing.T) {
+	type dbMockConfig struct {
+		Database string `mapstructure:"database"`
+		providerConfigMock
+	}
+	baseMockFactory.CreateDefaultConfigF = func() provider.Config {
+		return &dbMockConfig{providerConfigMock: providerConfigMock{func() error { return nil }}}
+	}
+	providerFactories["mock"] = &baseMockFactory
+
+	factories, err := otelcoltest.NopFactories()
+	require.NoError(t, err)
+
+	factory := NewFactory()
+	factories.Processors[metadata.Type] = factory
+	collectorConfig, err := otelcoltest.LoadConfigAndValidateWithSettings(factories, otelcol.ConfigProviderSettings{
+		ResolverSettings: confmap.ResolverSettings{
+			URIs: []string{filepath.Join("testdata", "config-mockProvider.yaml")},
+			ProviderFactories: []confmap.ProviderFactory{
+				fileprovider.NewFactory(),
+			},
+		},
+	},
+	)
+
+	require.NoError(t, err)
+	actualDbMockConfig := collectorConfig.Processors[component.NewID(metadata.Type)].(*Config).Providers["mock"].(*dbMockConfig)
+	require.Equal(t, "/tmp/geodata.csv", actualDbMockConfig.Database)
+
+	// assert provider unmarshall configuration error by removing the database fieldfrom the configuration struct
+	baseMockFactory.CreateDefaultConfigF = func() provider.Config {
+		return &providerConfigMock{func() error { return nil }}
+	}
+	providerFactories["mock"] = &baseMockFactory
+
+	factories.Processors[metadata.Type] = factory
+	_, err = otelcoltest.LoadConfigAndValidateWithSettings(factories, otelcol.ConfigProviderSettings{
+		ResolverSettings: confmap.ResolverSettings{
+			URIs: []string{filepath.Join("testdata", "config-mockProvider.yaml")},
+			ProviderFactories: []confmap.ProviderFactory{
+				fileprovider.NewFactory(),
+			},
+		},
+	},
+	)
+
+	require.ErrorContains(t, err, "has invalid keys: database")
+}
+
+func TestLoadConfig_ProviderValidateError(t *testing.T) {
+	baseMockFactory.CreateDefaultConfigF = func() provider.Config {
+		sampleConfig := struct {
+			Database string `mapstructure:"database"`
+			providerConfigMock
+		}{
+			"",
+			providerConfigMock{func() error { return errors.New("error validating mocked config") }},
+		}
+		return &sampleConfig
+	}
+	providerFactories["mock"] = &baseMockFactory
+
+	factories, err := otelcoltest.NopFactories()
+	require.NoError(t, err)
+
+	factory := NewFactory()
+	factories.Processors[metadata.Type] = factory
+	_, err = otelcoltest.LoadConfigAndValidateWithSettings(factories, otelcol.ConfigProviderSettings{
+		ResolverSettings: confmap.ResolverSettings{
+			URIs: []string{filepath.Join("testdata", "config-mockProvider.yaml")},
+			ProviderFactories: []confmap.ProviderFactory{
+				fileprovider.NewFactory(),
+			},
+		},
+	},
+	)
+
+	require.Contains(t, err.Error(), "error validating provider mock")
+}