feat: migrate configuration from custom format to YAML

- Replace custom directive-based config parser with YAML using gopkg.in/yaml.v3
- Rename config.example.conf to config.example.yml with YAML syntax
- Update default config path to /etc/logcorrelator/logcorrelator.yml
- Update Dockerfile.package to copy YAML config files
- Update packaging scripts to install logcorrelator.yml
- Update architecture.yml to document YAML configuration
- Add yaml.v3 dependency to go.mod

Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>

Dockerfile.package

@@ -47,15 +47,15 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
 
 # Copy binary from builder
 COPY --from=builder /build/dist/logcorrelator /tmp/pkgroot/usr/bin/logcorrelator
-COPY --from=builder /build/config.example.conf /tmp/pkgroot/etc/logcorrelator/logcorrelator.conf
+COPY --from=builder /build/config.example.yml /tmp/pkgroot/etc/logcorrelator/logcorrelator.yml
-COPY --from=builder /build/config.example.conf /tmp/pkgroot/usr/share/logcorrelator/logcorrelator.conf.example
+COPY --from=builder /build/config.example.yml /tmp/pkgroot/usr/share/logcorrelator/logcorrelator.yml.example
 
 # Create directories and set permissions
 RUN mkdir -p /tmp/pkgroot/var/log/logcorrelator && \
     mkdir -p /tmp/pkgroot/var/run/logcorrelator && \
     chmod 755 /tmp/pkgroot/usr/bin/logcorrelator && \
-    chmod 640 /tmp/pkgroot/etc/logcorrelator/logcorrelator.conf && \
+    chmod 640 /tmp/pkgroot/etc/logcorrelator/logcorrelator.yml && \
-    chmod 640 /tmp/pkgroot/usr/share/logcorrelator/logcorrelator.conf.example && \
+    chmod 640 /tmp/pkgroot/usr/share/logcorrelator/logcorrelator.yml.example && \
     chmod 755 /tmp/pkgroot/var/log/logcorrelator && \
     chmod 755 /tmp/pkgroot/var/run/logcorrelator
 
@@ -85,8 +85,8 @@ RUN mkdir -p /packages/deb && \
     --after-remove /tmp/scripts/postrm \
     -p /packages/deb/logcorrelator_${VERSION}_${ARCH}.deb \
     usr/bin/logcorrelator \
-    etc/logcorrelator/logcorrelator.conf \
+    etc/logcorrelator/logcorrelator.yml \
-    usr/share/logcorrelator/logcorrelator.conf.example \
+    usr/share/logcorrelator/logcorrelator.yml.example \
     var/log/logcorrelator \
     var/run/logcorrelator
 
@@ -108,8 +108,8 @@ RUN mkdir -p /packages/rpm && \
     --after-remove /tmp/scripts/postrm \
     -p /packages/rpm/logcorrelator-${VERSION}-1.x86_64.rpm \
     usr/bin/logcorrelator \
-    etc/logcorrelator/logcorrelator.conf \
+    etc/logcorrelator/logcorrelator.yml \
-    usr/share/logcorrelator/logcorrelator.conf.example \
+    usr/share/logcorrelator/logcorrelator.yml.example \
     var/log/logcorrelator \
     var/run/logcorrelator
 

architecture.yml

@@ -21,11 +21,11 @@ runtime:
     unit_type: systemd
     description: >
       logcorrelator est livré sous forme de binaire autonome, exécuté comme un
-      service systemd. L’unité systemd assure le démarrage automatique au boot,
+      service systemd. L'unité systemd assure le démarrage automatique au boot,
-      le redémarrage en cas de crash, et une intégration standard dans l’écosystème
+      le redémarrage en cas de crash, et une intégration standard dans l'écosystème
       Linux (notamment sur Rocky Linux 8+).
     binary_path: /usr/bin/logcorrelator
-    config_path: /etc/logcorrelator/logcorrelator.toml
+    config_path: /etc/logcorrelator/logcorrelator.yml
     user: logcorrelator
     group: logcorrelator
     restart: on-failure
@@ -40,7 +40,7 @@ runtime:
         Type=simple
         User=logcorrelator
         Group=logcorrelator
-        ExecStart=/usr/bin/logcorrelator -config /etc/logcorrelator/logcorrelator.toml
+        ExecStart=/usr/bin/logcorrelator -config /etc/logcorrelator/logcorrelator.yml
         Restart=on-failure
         RestartSec=5
 
@@ -68,51 +68,53 @@ runtime:
       de drop), ferme les connexions ClickHouse puis s’arrête.
 
 config:
-  format: toml
+  format: yaml
-  location: /etc/logcorrelator/logcorrelator.toml
+  location: /etc/logcorrelator/logcorrelator.yml
   description: >
-    Toute la configuration est centralisée dans un fichier TOML lisible, stocké
+    Toute la configuration est centralisée dans un fichier YAML lisible,
-    dans /etc/logcorrelator. Ni YAML ni JSON ne sont utilisés pour la config.
+    stocké dans /etc/logcorrelator.
   reload_strategy: restart_service
   example: |
-    [service]
+    # Service configuration
-    name = "logcorrelator"
+    service:
-    language = "go"
+      name: logcorrelator
+      language: go
 
-    [[inputs.unix_sockets]]
+    # Input sources (at least 2 required)
-    name = "apache_source"
+    inputs:
-    path = "/var/run/logcorrelator/apache.sock"
+      unix_sockets:
-    format = "json"
+        - name: apache_source
+          path: /var/run/logcorrelator/apache.sock
+          format: json
+        - name: network_source
+          path: /var/run/logcorrelator/network.sock
+          format: json
 
-    [[inputs.unix_sockets]]
+    # File output
-    name = "network_source"
+    outputs:
-    path = "/var/run/logcorrelator/network.sock"
+      file:
-    format = "json"
+        enabled: true
+        path: /var/log/logcorrelator/correlated.log
 
-    [outputs.file]
+    # ClickHouse output
-    enabled = true
+    outputs:
-    path = "/var/log/logcorrelator/correlated.log"
+      clickhouse:
+        enabled: false
+        dsn: clickhouse://user:pass@localhost:9000/db
+        table: correlated_logs_http_network
+        batch_size: 500
 
-    [outputs.clickhouse]
+    # Correlation configuration
-    enabled = true
+    correlation:
-    dsn = "clickhouse://user:pass@host:9000/db"
+      key:
-    table = "correlated_logs_http_network"
+        - src_ip
-    batch_size = 500
+        - src_port
-    flush_interval_ms = 200
+      time_window:
-    max_buffer_size = 5000
+        value: 1
-    drop_on_overflow = true
+        unit: s
-    async_insert = true
+      orphan_policy:
-
+        apache_always_emit: true
-    [correlation]
+        network_emit: false
-    key = ["src_ip", "src_port"]
-
-    [correlation.time_window]
-    value = 1
-    unit = "s"
-
-    [correlation.orphan_policy]
-    apache_always_emit = true
-    network_emit = false
 
 inputs:
   description: >
@@ -503,12 +505,12 @@ packaging:
       dest: /usr/bin/logcorrelator
       mode: "0755"
     config:
-      - source: config.example.conf
+      - source: config.example.yml
-        dest: /etc/logcorrelator/logcorrelator.conf
+        dest: /etc/logcorrelator/logcorrelator.yml
         mode: "0640"
         config_file: true
-      - source: config.example.conf
+      - source: config.example.yml
-        dest: /usr/share/logcorrelator/logcorrelator.conf.example
+        dest: /usr/share/logcorrelator/logcorrelator.yml.example
         mode: "0640"
     directories:
       - path: /var/log/logcorrelator

config.example.yml

@@ -0,0 +1,45 @@
+# logcorrelator configuration file
+# Format: YAML
+
+service:
+  name: logcorrelator
+  language: go
+
+inputs:
+  unix_sockets:
+    - name: apache_source
+      path: /var/run/logcorrelator/apache.sock
+      format: json
+    - name: network_source
+      path: /var/run/logcorrelator/network.sock
+      format: json
+
+outputs:
+  file:
+    enabled: true
+    path: /var/log/logcorrelator/correlated.log
+
+  clickhouse:
+    enabled: false
+    dsn: clickhouse://user:pass@localhost:9000/db
+    table: correlated_logs_http_network
+    batch_size: 500
+    flush_interval_ms: 200
+    max_buffer_size: 5000
+    drop_on_overflow: true
+    async_insert: true
+    timeout_ms: 1000
+
+  stdout:
+    enabled: false
+
+correlation:
+  key:
+    - src_ip
+    - src_port
+  time_window:
+    value: 1
+    unit: s
+  orphan_policy:
+    apache_always_emit: true
+    network_emit: false

go.mod

@@ -1,3 +1,5 @@
 module github.com/logcorrelator/logcorrelator
 
 go 1.21
+
+require gopkg.in/yaml.v3 v3.0.1 // indirect

go.sum

@@ -0,0 +1,3 @@
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

internal/config/config.go

@@ -1,99 +1,112 @@
 package config
 
 import (
-	"bufio"
 	"fmt"
 	"os"
-	"strconv"
-	"strings"
 	"time"
+
+	"gopkg.in/yaml.v3"
 )
 
 // Config holds the complete application configuration.
 type Config struct {
-	Service     ServiceConfig
+	Service     ServiceConfig     `yaml:"service"`
-	Inputs      InputsConfig
+	Inputs      InputsConfig      `yaml:"inputs"`
-	Outputs     OutputsConfig
+	Outputs     OutputsConfig     `yaml:"outputs"`
-	Correlation CorrelationConfig
+	Correlation CorrelationConfig `yaml:"correlation"`
 }
 
 // ServiceConfig holds service-level configuration.
 type ServiceConfig struct {
-	Name     string
+	Name     string `yaml:"name"`
-	Language string
+	Language string `yaml:"language"`
 }
 
 // InputsConfig holds input sources configuration.
 type InputsConfig struct {
-	UnixSockets []UnixSocketConfig
+	UnixSockets []UnixSocketConfig `yaml:"unix_sockets"`
 }
 
 // UnixSocketConfig holds a Unix socket source configuration.
 type UnixSocketConfig struct {
-	Name   string
+	Name   string `yaml:"name"`
-	Path   string
+	Path   string `yaml:"path"`
-	Format string
+	Format string `yaml:"format"`
 }
 
 // OutputsConfig holds output sinks configuration.
 type OutputsConfig struct {
-	File       FileOutputConfig
+	File       FileOutputConfig      `yaml:"file"`
-	ClickHouse ClickHouseOutputConfig
+	ClickHouse ClickHouseOutputConfig `yaml:"clickhouse"`
-	Stdout     StdoutOutputConfig
+	Stdout     StdoutOutputConfig    `yaml:"stdout"`
 }
 
 // FileOutputConfig holds file sink configuration.
 type FileOutputConfig struct {
-	Enabled bool
+	Enabled bool   `yaml:"enabled"`
-	Path    string
+	Path    string `yaml:"path"`
 }
 
 // ClickHouseOutputConfig holds ClickHouse sink configuration.
 type ClickHouseOutputConfig struct {
-	Enabled         bool
+	Enabled         bool   `yaml:"enabled"`
-	DSN             string
+	DSN             string `yaml:"dsn"`
-	Table           string
+	Table           string `yaml:"table"`
-	BatchSize       int
+	BatchSize       int    `yaml:"batch_size"`
-	FlushIntervalMs int
+	FlushIntervalMs int    `yaml:"flush_interval_ms"`
-	MaxBufferSize   int
+	MaxBufferSize   int    `yaml:"max_buffer_size"`
-	DropOnOverflow  bool
+	DropOnOverflow  bool   `yaml:"drop_on_overflow"`
-	AsyncInsert     bool
+	AsyncInsert     bool   `yaml:"async_insert"`
-	TimeoutMs       int
+	TimeoutMs       int    `yaml:"timeout_ms"`
 }
 
 // StdoutOutputConfig holds stdout sink configuration.
 type StdoutOutputConfig struct {
-	Enabled bool
+	Enabled bool `yaml:"enabled"`
 }
 
 // CorrelationConfig holds correlation configuration.
 type CorrelationConfig struct {
-	Key          []string
+	Key          []string           `yaml:"key"`
-	TimeWindow   TimeWindowConfig
+	TimeWindow   TimeWindowConfig   `yaml:"time_window"`
-	OrphanPolicy OrphanPolicyConfig
+	OrphanPolicy OrphanPolicyConfig `yaml:"orphan_policy"`
 }
 
 // TimeWindowConfig holds time window configuration.
 type TimeWindowConfig struct {
-	Value int
+	Value int    `yaml:"value"`
-	Unit  string
+	Unit  string `yaml:"unit"`
 }
 
 // OrphanPolicyConfig holds orphan event policy configuration.
 type OrphanPolicyConfig struct {
-	ApacheAlwaysEmit bool
+	ApacheAlwaysEmit bool `yaml:"apache_always_emit"`
-	NetworkEmit      bool
+	NetworkEmit      bool `yaml:"network_emit"`
 }
 
-// Load loads configuration from a text file with directives.
+// Load loads configuration from a YAML file.
 func Load(path string) (*Config, error) {
-	file, err := os.Open(path)
+	data, err := os.ReadFile(path)
 	if err != nil {
-		return nil, fmt.Errorf("failed to open config file: %w", err)
+		return nil, fmt.Errorf("failed to read config file: %w", err)
 	}
-	defer file.Close()
 
-	cfg := &Config{
+	cfg := defaultConfig()
+
+	if err := yaml.Unmarshal(data, cfg); err != nil {
+		return nil, fmt.Errorf("failed to parse config file: %w", err)
+	}
+
+	if err := cfg.Validate(); err != nil {
+		return nil, fmt.Errorf("invalid config: %w", err)
+	}
+
+	return cfg, nil
+}
+
+// defaultConfig returns a Config with default values.
+func defaultConfig() *Config {
+	return &Config{
 		Service: ServiceConfig{
 			Name:     "logcorrelator",
 			Language: "go",
@@ -131,171 +144,6 @@ func Load(path string) (*Config, error) {
 			},
 		},
 	}
-
-	scanner := bufio.NewScanner(file)
-	lineNum := 0
-
-	for scanner.Scan() {
-		lineNum++
-		line := strings.TrimSpace(scanner.Text())
-
-		// Skip empty lines and comments
-		if line == "" || strings.HasPrefix(line, "#") {
-			continue
-		}
-
-		if err := parseDirective(cfg, line); err != nil {
-			return nil, fmt.Errorf("line %d: %w", lineNum, err)
-		}
-	}
-
-	if err := scanner.Err(); err != nil {
-		return nil, fmt.Errorf("failed to read config file: %w", err)
-	}
-
-	if err := cfg.Validate(); err != nil {
-		return nil, fmt.Errorf("invalid config: %w", err)
-	}
-
-	return cfg, nil
-}
-
-func parseDirective(cfg *Config, line string) error {
-	parts := strings.Fields(line)
-	if len(parts) < 2 {
-		return fmt.Errorf("invalid directive: %s", line)
-	}
-
-	directive := parts[0]
-	value := strings.Join(parts[1:], " ")
-
-	switch directive {
-	case "service.name":
-		cfg.Service.Name = value
-	case "service.language":
-		cfg.Service.Language = value
-
-	case "input.unix_socket":
-		// Format: input.unix_socket <name> <path> [format]
-		if len(parts) < 3 {
-			return fmt.Errorf("input.unix_socket requires name and path")
-		}
-		format := "json"
-		if len(parts) >= 4 {
-			format = parts[3]
-		}
-		cfg.Inputs.UnixSockets = append(cfg.Inputs.UnixSockets, UnixSocketConfig{
-			Name:   parts[1],
-			Path:   parts[2],
-			Format: format,
-		})
-
-	case "output.file.enabled":
-		enabled, err := parseBool(value)
-		if err != nil {
-			return fmt.Errorf("invalid value for output.file.enabled: %w", err)
-		}
-		cfg.Outputs.File.Enabled = enabled
-	case "output.file.path":
-		cfg.Outputs.File.Path = value
-
-	case "output.clickhouse.enabled":
-		enabled, err := parseBool(value)
-		if err != nil {
-			return fmt.Errorf("invalid value for output.clickhouse.enabled: %w", err)
-		}
-		cfg.Outputs.ClickHouse.Enabled = enabled
-	case "output.clickhouse.dsn":
-		cfg.Outputs.ClickHouse.DSN = value
-	case "output.clickhouse.table":
-		cfg.Outputs.ClickHouse.Table = value
-	case "output.clickhouse.batch_size":
-		v, err := strconv.Atoi(value)
-		if err != nil {
-			return fmt.Errorf("invalid value for output.clickhouse.batch_size: %w", err)
-		}
-		cfg.Outputs.ClickHouse.BatchSize = v
-	case "output.clickhouse.flush_interval_ms":
-		v, err := strconv.Atoi(value)
-		if err != nil {
-			return fmt.Errorf("invalid value for output.clickhouse.flush_interval_ms: %w", err)
-		}
-		cfg.Outputs.ClickHouse.FlushIntervalMs = v
-	case "output.clickhouse.max_buffer_size":
-		v, err := strconv.Atoi(value)
-		if err != nil {
-			return fmt.Errorf("invalid value for output.clickhouse.max_buffer_size: %w", err)
-		}
-		cfg.Outputs.ClickHouse.MaxBufferSize = v
-	case "output.clickhouse.drop_on_overflow":
-		enabled, err := parseBool(value)
-		if err != nil {
-			return fmt.Errorf("invalid value for output.clickhouse.drop_on_overflow: %w", err)
-		}
-		cfg.Outputs.ClickHouse.DropOnOverflow = enabled
-	case "output.clickhouse.async_insert":
-		enabled, err := parseBool(value)
-		if err != nil {
-			return fmt.Errorf("invalid value for output.clickhouse.async_insert: %w", err)
-		}
-		cfg.Outputs.ClickHouse.AsyncInsert = enabled
-	case "output.clickhouse.timeout_ms":
-		v, err := strconv.Atoi(value)
-		if err != nil {
-			return fmt.Errorf("invalid value for output.clickhouse.timeout_ms: %w", err)
-		}
-		cfg.Outputs.ClickHouse.TimeoutMs = v
-
-	case "output.stdout.enabled":
-		enabled, err := parseBool(value)
-		if err != nil {
-			return fmt.Errorf("invalid value for output.stdout.enabled: %w", err)
-		}
-		cfg.Outputs.Stdout.Enabled = enabled
-
-	case "correlation.key":
-		cfg.Correlation.Key = strings.Split(value, ",")
-		for i, k := range cfg.Correlation.Key {
-			cfg.Correlation.Key[i] = strings.TrimSpace(k)
-		}
-	case "correlation.time_window.value":
-		v, err := strconv.Atoi(value)
-		if err != nil {
-			return fmt.Errorf("invalid value for correlation.time_window.value: %w", err)
-		}
-		cfg.Correlation.TimeWindow.Value = v
-	case "correlation.time_window.unit":
-		cfg.Correlation.TimeWindow.Unit = value
-	case "correlation.orphan_policy.apache_always_emit":
-		enabled, err := parseBool(value)
-		if err != nil {
-			return fmt.Errorf("invalid value for correlation.orphan_policy.apache_always_emit: %w", err)
-		}
-		cfg.Correlation.OrphanPolicy.ApacheAlwaysEmit = enabled
-	case "correlation.orphan_policy.network_emit":
-		enabled, err := parseBool(value)
-		if err != nil {
-			return fmt.Errorf("invalid value for correlation.orphan_policy.network_emit: %w", err)
-		}
-		cfg.Correlation.OrphanPolicy.NetworkEmit = enabled
-
-	default:
-		return fmt.Errorf("unknown directive: %s", directive)
-	}
-
-	return nil
-}
-
-func parseBool(s string) (bool, error) {
-	s = strings.ToLower(s)
-	switch s {
-	case "true", "yes", "1", "on":
-		return true, nil
-	case "false", "no", "0", "off":
-		return false, nil
-	default:
-		return false, fmt.Errorf("invalid boolean value: %s", s)
-	}
 }
 
 // Validate validates the configuration.

packaging/deb/postinst

@@ -37,10 +37,10 @@ case "$1" in
         chmod 750 /etc/logcorrelator
 
         # Install default config if it doesn't exist
-        if [ ! -f /etc/logcorrelator/logcorrelator.conf ]; then
+        if [ ! -f /etc/logcorrelator/logcorrelator.yml ]; then
-            cp /usr/share/logcorrelator/logcorrelator.conf.example /etc/logcorrelator/logcorrelator.conf
+            cp /usr/share/logcorrelator/logcorrelator.yml.example /etc/logcorrelator/logcorrelator.yml
-            chown logcorrelator:logcorrelator /etc/logcorrelator/logcorrelator.conf
+            chown logcorrelator:logcorrelator /etc/logcorrelator/logcorrelator.yml
-            chmod 640 /etc/logcorrelator/logcorrelator.conf
+            chmod 640 /etc/logcorrelator/logcorrelator.yml
         fi
 
         # Enable and start the service (if running in a real system, not container)