[exporter/doris] New component: Doris Exporter (#33790)

First PR of New component: Doris Exporter.

**Link to tracking Issue:** #33479

.chloggen/dorisexporter-new-component.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: new_component
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: exporter/doris
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: "Add a new component for exporting logs, traces and metrics to Doris"
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [33479]
+
+# (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: [user]

.github/CODEOWNERS

@@ -53,6 +53,7 @@ exporter/clickhouseexporter/                                        @open-teleme
 exporter/coralogixexporter/                                         @open-telemetry/collector-contrib-approvers @povilasv @matej-g
 exporter/datadogexporter/                                           @open-telemetry/collector-contrib-approvers @mx-psi @dineshg13 @liustanley @songy23 @mackjmr @ankitpatel96
 exporter/datasetexporter/                                           @open-telemetry/collector-contrib-approvers @atoulme @martin-majlis-s1 @zdaratom-s1 @tomaz-s1
+exporter/dorisexporter/                                             @open-telemetry/collector-contrib-approvers @atoulme @joker-star-l
 exporter/elasticsearchexporter/                                     @open-telemetry/collector-contrib-approvers @JaredTan95 @ycombinator @carsonip
 exporter/fileexporter/                                              @open-telemetry/collector-contrib-approvers @atingchen
 exporter/googlecloudexporter/                                       @open-telemetry/collector-contrib-approvers @aabmass @dashpole @jsuereth @punya @damemi @psx95

.github/ISSUE_TEMPLATE/bug_report.yaml

@@ -52,6 +52,7 @@ body:
       - exporter/coralogix
       - exporter/datadog
       - exporter/dataset
+      - exporter/doris
       - exporter/elasticsearch
       - exporter/file
       - exporter/googlecloud

.github/ISSUE_TEMPLATE/feature_request.yaml

@@ -46,6 +46,7 @@ body:
       - exporter/coralogix
       - exporter/datadog
       - exporter/dataset
+      - exporter/doris
       - exporter/elasticsearch
       - exporter/file
       - exporter/googlecloud

.github/ISSUE_TEMPLATE/other.yaml

@@ -46,6 +46,7 @@ body:
       - exporter/coralogix
       - exporter/datadog
       - exporter/dataset
+      - exporter/doris
       - exporter/elasticsearch
       - exporter/file
       - exporter/googlecloud

.github/ISSUE_TEMPLATE/unmaintained.yaml

@@ -51,6 +51,7 @@ body:
       - exporter/coralogix
       - exporter/datadog
       - exporter/dataset
+      - exporter/doris
       - exporter/elasticsearch
       - exporter/file
       - exporter/googlecloud

cmd/githubgen/allowlist.txt

@@ -22,3 +22,4 @@ tomasmota
 m1rp
 jriguera
 abhishek-at-cloudwerx
+joker-star-l

exporter/dorisexporter/Makefile

@@ -0,0 +1,2 @@
+include ../../Makefile.Common
+

exporter/dorisexporter/README.md

@@ -0,0 +1,72 @@
+# Apache Doris Exporter
+<!-- status autogenerated section -->
+| Status        |           |
+| ------------- |-----------|
+| Stability     | [development]: traces, metrics, logs   |
+| Distributions | [] |
+| Issues        | [![Open issues](https://img.shields.io/github/issues-search/open-telemetry/opentelemetry-collector-contrib?query=is%3Aissue%20is%3Aopen%20label%3Aexporter%2Fdoris%20&label=open&color=orange&logo=opentelemetry)](https://github.com/open-telemetry/opentelemetry-collector-contrib/issues?q=is%3Aopen+is%3Aissue+label%3Aexporter%2Fdoris) [![Closed issues](https://img.shields.io/github/issues-search/open-telemetry/opentelemetry-collector-contrib?query=is%3Aissue%20is%3Aclosed%20label%3Aexporter%2Fdoris%20&label=closed&color=blue&logo=opentelemetry)](https://github.com/open-telemetry/opentelemetry-collector-contrib/issues?q=is%3Aclosed+is%3Aissue+label%3Aexporter%2Fdoris) |
+| [Code Owners](https://github.com/open-telemetry/opentelemetry-collector-contrib/blob/main/CONTRIBUTING.md#becoming-a-code-owner)    | [@atoulme](https://www.github.com/atoulme), [@joker-star-l](https://www.github.com/joker-star-l) |
+
+[development]: https://github.com/open-telemetry/opentelemetry-collector#development
+<!-- end autogenerated section -->
+
+This exporter supports sending traces, metrics, and logs data to [Apache Doris](https://doris.apache.org/) (version >= 2.1). 
+
+## Configuration
+
+The following configuration options are supported:
+
+* `endpoint` The http stream load address.
+* `database` (default = otel) The database name.
+* `username` The authentication username.
+* `password` The authentication password.
+* `table`
+  * `logs` (default = otel_logs) The table name for logs.
+  * `traces` (default = otel_traces) The table name for traces.
+  * `metrics` (default = otel_metrics) The table name for metrics.
+* `create_schema` (default = true) Whether databases and tables are created automatically.
+* `mysql_endpoint` The mysql protocol address to create the schema; ignored if `create_schema` is false.
+* `history_days` (default = 0) Data older than these days will be deleted; ignored if `create_schema` is false. If set to 0, historical data will not be deleted.
+* `create_history_days` (default = 0) The number of days in the history partition that was created when the table was created; ignored if `create_schema` is false. If `history_days` is not 0, `create_history_days` needs to be less than or equal to `history_days`.
+* `replication_num` (default = 1) The number of replicas of the table; ignored if `create_schema` is false.
+* `timezone` (default is the time zone of the opentelemetry collector) The time zone of doris.
+* `timeout` (default = 5s) Time to wait per individual attempt to send data to a backend.
+* `sending_queue`  [details here](https://github.com/open-telemetry/opentelemetry-collector/tree/main/exporter/exporterhelper#configuration)
+  * `enabled` (default = true)
+  * `num_consumers` (default = 10) Number of consumers that dequeue batches; ignored if `enabled` is false.
+  * `queue_size` (default = 1000) Maximum number of batches kept in memory before dropping; ignored if `enabled` is false.
+* `retry_on_failure` [details here](https://github.com/open-telemetry/opentelemetry-collector/tree/main/exporter/exporterhelper#configuration)
+  * `enabled` (default = true)
+  * `initial_interval` (default = 5s) Time to wait after the first failure before retrying; ignored if `enabled` is false.
+  * `max_interval` (default = 30s) The upper bound on backoff; ignored if `enabled` is false.
+  * `max_elapsed_time` (default = 300s) The maximum amount of time spent trying to send a batch; ignored if `enabled` is false. If set to 0, the retries are never stopped.
+
+Example:
+```yaml
+exporters:
+  doris:
+    endpoint: http://localhost:8030
+    database: otel
+    username: admin
+    password: admin
+    table:
+      logs: otel_logs
+      traces: otel_traces
+      metrics: otel_metrics
+    create_schema: true
+    mysql_endpoint: localhost:9030
+    history_days: 0
+    create_history_days: 0
+    replication_num: 1
+    timezone: Asia/Shanghai
+    timeout: 5s
+    sending_queue:
+      enabled: true
+      num_consumers: 10
+      queue_size: 1000
+    retry_on_failure:
+      enabled: true
+      initial_interval: 5s
+      max_interval: 30s
+      max_elapsed_time: 300s
+```

exporter/dorisexporter/config.go

@@ -0,0 +1,97 @@
+// Copyright The OpenTelemetry Authors
+// SPDX-License-Identifier: Apache-2.0
+
+package dorisexporter // import "github.com/open-telemetry/opentelemetry-collector-contrib/exporter/dorisexporter"
+
+import (
+	"errors"
+	"regexp"
+
+	"go.opentelemetry.io/collector/config/configopaque"
+	"go.opentelemetry.io/collector/config/configretry"
+	"go.opentelemetry.io/collector/exporter/exporterhelper"
+)
+
+type Config struct {
+	exporterhelper.TimeoutSettings `mapstructure:",squash"`
+	configretry.BackOffConfig      `mapstructure:"retry_on_failure"`
+	exporterhelper.QueueSettings   `mapstructure:"sending_queue"`
+
+	// TableNames is the table name for logs, traces and metrics.
+	Table `mapstructure:"table"`
+
+	// Endpoint is the http stream load address.
+	Endpoint string `mapstructure:"endpoint"`
+	// Database is the database name.
+	Database string `mapstructure:"database"`
+	// Username is the authentication username.
+	Username string `mapstructure:"username"`
+	// Password is the authentication password.
+	Password configopaque.String `mapstructure:"password"`
+	// CreateSchema is whether databases and tables are created automatically.
+	CreateSchema bool `mapstructure:"create_schema"`
+	// MySQLEndpoint is the mysql protocol address to create the schema; ignored if create_schema is false.
+	MySQLEndpoint string `mapstructure:"mysql_endpoint"`
+	// Data older than these days will be deleted; ignored if create_schema is false. If set to 0, historical data will not be deleted.
+	HistoryDays int32 `mapstructure:"history_days"`
+	// The number of days in the history partition that was created when the table was created; ignored if create_schema is false.
+	// If history_days is not 0, create_history_days needs to be less than or equal to history_days.
+	CreateHistoryDays int32 `mapstructure:"create_history_days"`
+	// ReplicationNum is the number of replicas of the table; ignored if create_schema is false.
+	ReplicationNum int32 `mapstructure:"replication_num"`
+	// Timezone is the timezone of the doris.
+	TimeZone string `mapstructure:"timezone"`
+}
+
+type Table struct {
+	// Logs is the table name for logs.
+	Logs string `mapstructure:"logs"`
+	// Traces is the table name for traces.
+	Traces string `mapstructure:"traces"`
+	// Metrics is the table name for metrics.
+	Metrics string `mapstructure:"metrics"`
+}
+
+func (cfg *Config) Validate() (err error) {
+	if cfg.Endpoint == "" {
+		err = errors.Join(err, errors.New("endpoint must be specified"))
+	}
+	if cfg.CreateSchema {
+		if cfg.MySQLEndpoint == "" {
+			err = errors.Join(err, errors.New("mysql_endpoint must be specified"))
+		}
+
+		if cfg.HistoryDays < 0 {
+			err = errors.Join(err, errors.New("history_days must be greater than or equal to 0"))
+		}
+
+		if cfg.CreateHistoryDays < 0 {
+			err = errors.Join(err, errors.New("create_history_days must be greater than or equal to 0"))
+		}
+
+		if cfg.HistoryDays > 0 && cfg.CreateHistoryDays > cfg.HistoryDays {
+			err = errors.Join(err, errors.New("create_history_days must be less than or equal to history_days"))
+		}
+
+		if cfg.ReplicationNum < 1 {
+			err = errors.Join(err, errors.New("replication_num must be greater than or equal to 1"))
+		}
+	}
+
+	// Preventing SQL Injection Attacks
+	re := regexp.MustCompile(`^[a-zA-Z0-9_]+$`)
+	if !re.MatchString(cfg.Database) {
+		err = errors.Join(err, errors.New("database name must be alphanumeric and underscore"))
+	}
+	if !re.MatchString(cfg.Table.Logs) {
+		err = errors.Join(err, errors.New("logs table name must be alphanumeric and underscore"))
+	}
+	if !re.MatchString(cfg.Table.Traces) {
+		err = errors.Join(err, errors.New("traces table name must be alphanumeric and underscore"))
+	}
+	if !re.MatchString(cfg.Table.Metrics) {
+		err = errors.Join(err, errors.New("metrics table name must be alphanumeric and underscore"))
+	}
+
+	return err
+}

exporter/dorisexporter/config_test.go

@@ -0,0 +1,90 @@
+// Copyright The OpenTelemetry Authors
+// SPDX-License-Identifier: Apache-2.0
+
+package dorisexporter // import "github.com/open-telemetry/opentelemetry-collector-contrib/exporter/dorisexporter"
+
+import (
+	"path/filepath"
+	"testing"
+	"time"
+
+	"github.com/cenkalti/backoff/v4"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"go.opentelemetry.io/collector/component"
+	"go.opentelemetry.io/collector/config/configopaque"
+	"go.opentelemetry.io/collector/config/configretry"
+	"go.opentelemetry.io/collector/confmap/confmaptest"
+	"go.opentelemetry.io/collector/exporter/exporterhelper"
+
+	"github.com/open-telemetry/opentelemetry-collector-contrib/exporter/dorisexporter/internal/metadata"
+)
+
+func TestLoadConfig(t *testing.T) {
+	t.Parallel()
+
+	cm, err := confmaptest.LoadConf(filepath.Join("testdata", "config.yaml"))
+	require.NoError(t, err)
+
+	defaultCfg := createDefaultConfig()
+	defaultCfg.(*Config).Endpoint = "http://localhost:8030"
+	defaultCfg.(*Config).MySQLEndpoint = "localhost:9030"
+
+	tests := []struct {
+		id       component.ID
+		expected component.Config
+	}{
+		{
+			id:       component.NewIDWithName(metadata.Type, ""),
+			expected: defaultCfg,
+		},
+		{
+			id: component.NewIDWithName(metadata.Type, "full"),
+			expected: &Config{
+				TimeoutSettings: exporterhelper.TimeoutSettings{Timeout: 5 * time.Second},
+				BackOffConfig: configretry.BackOffConfig{
+					Enabled:             true,
+					InitialInterval:     5 * time.Second,
+					MaxInterval:         30 * time.Second,
+					MaxElapsedTime:      300 * time.Second,
+					RandomizationFactor: backoff.DefaultRandomizationFactor,
+					Multiplier:          backoff.DefaultMultiplier,
+				},
+				QueueSettings: exporterhelper.QueueSettings{
+					Enabled:      true,
+					NumConsumers: 10,
+					QueueSize:    1000,
+				},
+				Table: Table{
+					Logs:    "otel_logs",
+					Traces:  "otel_traces",
+					Metrics: "otel_metrics",
+				},
+				Endpoint:          "http://localhost:8030",
+				Database:          "otel",
+				Username:          "admin",
+				Password:          configopaque.String("admin"),
+				CreateSchema:      true,
+				MySQLEndpoint:     "localhost:9030",
+				HistoryDays:       0,
+				CreateHistoryDays: 0,
+				ReplicationNum:    2,
+				TimeZone:          "Asia/Shanghai",
+			},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.id.String(), func(t *testing.T) {
+			factory := NewFactory()
+			cfg := factory.CreateDefaultConfig()
+
+			sub, err := cm.Sub(tt.id.String())
+			require.NoError(t, err)
+			require.NoError(t, sub.Unmarshal(cfg))
+
+			assert.NoError(t, component.ValidateConfig(cfg))
+			assert.Equal(t, tt.expected, cfg)
+		})
+	}
+}

exporter/dorisexporter/doc.go

@@ -0,0 +1,7 @@
+// Copyright The OpenTelemetry Authors
+// SPDX-License-Identifier: Apache-2.0
+
+//go:generate mdatagen metadata.yaml
+
+// Package dorisexporter exports trace, metric and log data to an Apache Doris instance.
+package dorisexporter // import "github.com/open-telemetry/opentelemetry-collector-contrib/exporter/dorisexporter"