config.yaml.sample

# Git Stats Configuration Template
# Configuration for analyzing git repositories and uploading to Elasticsearch
#
# IMPORTANT: This configuration supports idempotent updates!
# You can safely run the analysis and upload scripts multiple times without creating duplicates.
# Each commit uses a unique document ID in Elasticsearch:
#   - Commits: {repository}_{commit_hash}
#
# Quick update command: ./run.sh
#
# SETUP INSTRUCTIONS:
# 1. Copy this file to config.yaml: cp config.yaml.sample config.yaml
# 2. Update the email_mapping section with your team members
# 3. Update repository_urls with your git repositories
# 4. Adjust other settings as needed

# ============================================================================
# Email Mapping
# ============================================================================
# Map multiple email addresses to a single person name
# This ensures contributors who changed email addresses are counted as one person
email_mapping:
  "Example Developer":
    - "developer@example.com"
    - "dev@company.com"
  "Jenkins":
    - "jenkins@ci.example.com"
    - "github-actions[bot]@users.noreply.github.com"

# ============================================================================
# Parallelization Configuration
# ============================================================================
parallelization:
  # Maximum number of parallel workers for repository analysis
  # Default: number of CPU cores (or 4 if CPU count cannot be determined)
  # Set to 1 to disable parallelization
  max_workers: null  # null = auto-detect CPU count

# ============================================================================
# Repository Configuration
# ============================================================================
repositories:
  # Base directory containing all git repositories to analyze
  base_directory: "./repositories"
  
  # List of specific repositories to analyze (leave empty to analyze all)
  # If empty, all subdirectories in base_directory will be analyzed
  repositories_to_analyze: []
  
  # Git repository URLs to clone/analyze
  repository_urls:
    - "git@github.com:kibotu/git-panorama.git"
    # Add more repositories here
  
  # Repositories where ALL files should be included (no exclusions)
  # These are typically build tool repositories where "generated" files are the product
  include_all_files:
    - "example-build-repo"

# ============================================================================
# Analysis Configuration
# ============================================================================
analysis:
  # Date range for analysis (YYYY-MM-DD format)
  # Leave empty for all time
  start_date: ""
  end_date: ""  # Empty means until now
  
  # Include commits from all branches (not just main/master)
  all_branches: true
  
  # Exclude merge commits from analysis
  exclude_merge_commits: true
  
  # Output directory for generated reports and temporary files
  output_directory: "./git-stats"

# ============================================================================
# Elasticsearch Configuration
# ============================================================================
elasticsearch:
  host: "localhost"
  port: 9200
  
  # Index name for commit data
  commit_index: "git-commits"
  
  # Batch size for bulk uploads (number of documents per batch)
  # Higher values = faster uploads but more memory usage
  # Recommended: 1000-5000 depending on available memory
  bulk_batch_size: 3000


# ============================================================================
# File Exclusion Rules
# ============================================================================
# Define which files should be excluded from line change analysis
# This focuses metrics on actual developer-written code

exclusions:
  # Files to ALWAYS exclude (regex patterns)
  patterns:
    # Gradle wrapper files
    - pattern: ".*gradlew$"
      description: "Gradle wrapper script"
    - pattern: ".*gradlew\\.bat$"
      description: "Gradle wrapper batch file"
    
    # Lock files
    - pattern: ".*/package-lock\\.json$"
      description: "npm lock file"
    - pattern: ".*/yarn\\.lock$"
      description: "Yarn lock file"
    - pattern: ".*/composer\\.lock$"
      description: "PHP Composer lock file"
    - pattern: ".*/Gemfile\\.lock$"
      description: "Ruby Bundler lock file"
    - pattern: ".*/Podfile\\.lock$"
      description: "CocoaPods lock file"
    - pattern: ".*/pnpm-lock\\.yaml$"
      description: "pnpm lock file"
    
    # JSON configuration files (with exceptions)
    - pattern: ".*\\.json$"
      description: "JSON configuration files"
    
    # Data export files
    - pattern: ".*\\.csv$"
      description: "CSV data files"
    
    # Schema definition files
    - pattern: ".*\\.xsd$"
      description: "XML Schema Definition files"
    
    # Graphics and image files
    - pattern: ".*\\.svg$"
      description: "SVG graphics files"
    - pattern: ".*\\.png$"
      description: "PNG image files"
    - pattern: ".*\\.webp$"
      description: "WebP image files"
    - pattern: ".*\\.(jpeg|jpg|gif|ico|tiff)$"
      description: "Image files"
    - pattern: ".*\\.lottie$"
      description: "Lottie animation files"
    
    # Font files
    - pattern: ".*\\.ttf$"
      description: "TrueType font files"
    
    # Binary and archive files
    - pattern: ".*\\.(jar|zip|tar|enc)$"
      description: "Binary and archive files"
    
    # Media files
    - pattern: ".*\\.(pdf|mp3|wave|wav)$"
      description: "Media files"
    
    # Certificate and security files
    - pattern: ".*\\.(crt|pub|csr)$"
      description: "Certificate files"
    
    # Lock files (general)
    - pattern: ".*\\.(lock|resolved|sum)$"
      description: "Lock and checksum files"
    
    # Xcode project files
    - pattern: ".*\\.(pbxproj|xcworkspacedata|xcscheme)$"
      description: "Xcode project files"
    
    # Git configuration
    - pattern: ".*\\.(gitignore|gitkeep|eslintignore)$"
      description: "Git and linter ignore files"
    
    # Test snapshots
    - pattern: ".*\\.snap$"
      description: "Jest snapshot files"
    
    # XML configuration files
    - pattern: ".*\\.xml$"
      description: "XML configuration files"
    
    # Build/distribution directories
    - pattern: ".*/dist/.*"
      description: "Distribution/build output directories"
    - pattern: ".*/build/.*"
      description: "Build output directories"
    - pattern: ".*/node_modules/.*"
      description: "Node modules"
    - pattern: ".*/vendor/.*"
      description: "Vendor dependencies"
    
    # Source map files
    - pattern: ".*\\.map$"
      description: "Source map files"
    
    # OpenAPI generator files
    - pattern: ".*/\\.openapi-generator/.*"
      description: "OpenAPI generator metadata"
    - pattern: ".*\\.openapi-generator-ignore$"
      description: "OpenAPI generator ignore file"
  
  # Files to ALWAYS include (exceptions to exclusion patterns)
  always_include:
    # Project configuration files
    - pattern: ".*/package\\.json$"
      description: "npm package configuration"
    
    # Documentation files
    - pattern: ".*/README\\.md$"
      description: "README documentation"
    - pattern: ".*/readme\\.md$"
      description: "README documentation (lowercase)"
    
    # Android project files
    - pattern: ".*/AndroidManifest\\.xml$"
      description: "Android manifest files"
    - pattern: ".*/src/.*/res/.*"
      description: "Android resource files"
  
  # Repository-specific exclusion rules
  repository_specific: {}

# ============================================================================
# Notes
# ============================================================================
# - All regex patterns use Python regex syntax
# - Patterns are matched against full file paths
# - Exclusion patterns are applied AFTER inclusion patterns
# - Repository-specific rules override global rules
# - Email addresses in mapping are case-insensitive
#
# Configuration Change Impact:
# - Settings that require Docker restart:
#   * elasticsearch.host, elasticsearch.port (requires: docker compose restart)
#   * Changes to docker-compose.yml or config/grafana/* (requires: docker compose restart)
#
# - Settings that take effect on next ./run.sh:
#   * email_mapping - immediately affects author name mapping
#   * repositories.* - affects which repos are cloned/analyzed
#   * analysis.* - affects date range, branch filtering, merge commits
#   * exclusions.* - affects which files are counted in metrics
#   * parallelization.max_workers - affects analysis speed
#   * elasticsearch.bulk_batch_size - affects upload batch size
#   * elasticsearch.commit_index - affects which index is used
#
# - Environment variable overrides (highest priority):
#   * ES_HOST, ES_PORT - override elasticsearch.host/port
#   * BATCH_SIZE - overrides elasticsearch.bulk_batch_size
#   * DATA_DIR - overrides analysis.output_directory
#   * CONFIG_FILE - use different config file