Fixes, optimizations and pretty up

.gitignore

@@ -15,4 +15,5 @@
 
 node_modules
 
-.db
+*.db
+.DS_Store

README.md

@@ -4,6 +4,8 @@
 
 You can now easily run, any kind of analytics on your Git directory using the SQLite database.
 
+![plot](./internal/screenshot.png)
+
 ## Features ✨
 
 - Synchronize Git repository data into a SQLite database.
@@ -64,11 +66,13 @@ Once your repository data is synchronized into a SQLite database, you can run va
 6. **Authors Who Have Worked on a Specific File**
 
    ```sql
-    SELECT DISTINCT commits.author
-    FROM commits
-    JOIN commit_files ON commits.commit_hash = commit_files.commit_hash
-    JOIN files ON commit_files.file_id = files.file_id
-    WHERE files.file_path like '%sqlite3%'
+   SELECT files.file_path, commits.author, COUNT(*) as times_contributed
+   FROM commits
+   JOIN commit_files ON commits.commit_hash = commit_files.commit_hash
+   JOIN files ON commit_files.file_id = files.file_id
+   WHERE files.file_path LIKE '%connection_adapters/sqlite%'
+   GROUP BY files.file_path, commits.author
+   ORDER BY times_contributed DESC;
    ```
 
 ## Installation 📥

lib/branch_base.rb

@@ -1,9 +1,25 @@
 # frozen_string_literal: true
 
+require "logger"
 require "branch_base/database"
 require "branch_base/repository"
 require "branch_base/sync"
 require "branch_base/cli"
 
 module BranchBase
+  def self.logger
+    @logger ||=
+      Logger
+        .new($stdout)
+        .tap do |log|
+          log.progname = "BranchBase"
+
+          log.level = ENV["DEBUG"] ? Logger::DEBUG : Logger::INFO
+
+          log.formatter =
+            proc do |severity, datetime, progname, msg|
+              "#{datetime}: #{severity} - #{progname}: #{msg}\n"
+            end
+        end
+  end
 end

lib/branch_base/cli.rb

@@ -5,25 +5,33 @@
 
 module BranchBase
   class CLI < Thor
-    desc "sync REPO_PATH [BRANCH_OR_TAG]",
-         "Synchronize a specific branch or tag of the Git repository with the SQLite database"
+    desc "sync REPO_PATH", "Synchronize a Git directory to a SQLite database"
     def sync(repo_path)
+      BranchBase.logger.info("Starting sync process for #{repo_path}...")
+
       full_repo_path = File.expand_path(repo_path)
 
       unless File.directory?(File.join(full_repo_path, ".git"))
-        puts "The specified path is not a valid Git repository: #{full_repo_path}"
+        BranchBase.logger.error(
+          "The specified path is not a valid Git repository: #{full_repo_path}"
+        )
         exit(1)
       end
 
       repo_name = File.basename(full_repo_path)
-      db_filename = "#{repo_name}_git_data.db"
+      db_directory = full_repo_path
+      db_filename = File.join(db_directory, "#{repo_name}_git_data.db")
 
       database = Database.new(db_filename)
       repository = Repository.new(full_repo_path)
+      start_time = Time.now
       sync = Sync.new(database, repository)
 
       sync.run
-      puts "Repository data synced successfully for"
+      elapsed_time = Time.now - start_time
+      BranchBase.logger.info(
+        "Repository data synced successfully in #{db_filename} in #{elapsed_time.round(2)} seconds"
+      )
     end
   end
 end

lib/branch_base/sync.rb

@@ -26,18 +26,22 @@ def sync_repository
       existing_repo_id =
         @db.execute(
           "SELECT repo_id FROM repositories WHERE url = ?",
-          [repo_path],
+          [repo_path]
         ).first
       return existing_repo_id[0] if existing_repo_id
 
       @db.execute(
         "INSERT INTO repositories (name, url) VALUES (?, ?)",
-        [repo_name, repo_path],
+        [repo_name, repo_path]
       )
       @db.last_insert_row_id
     end
 
     def sync_branches(repo_id)
+      BranchBase.logger.debug(
+        "Syncing branches for repository ID: #{@repo.path}"
+      )
+
       batched_branches = []
 
       @repo.branches.each do |branch|
@@ -75,7 +79,7 @@ def sync_commits(repo_id)
           commit.author[:name],
           commit.committer[:name],
           commit.message,
-          commit.time.to_s,
+          commit.time.to_s
         ]
 
         if batched_commits.size >= BATCH_SIZE
@@ -105,7 +109,7 @@ def sync_commits(repo_id)
     def commit_exists?(commit_hash)
       @db.execute(
         "SELECT COUNT(*) FROM commits WHERE commit_hash = ?",
-        [commit_hash],
+        [commit_hash]
       ).first[
         0
       ].positive?
@@ -116,21 +120,25 @@ def insert_commit_files(commit, repo_id)
         file_path = patch.delta.new_file[:path]
         @db.execute(
           "INSERT OR IGNORE INTO files (repo_id, file_path, latest_commit) VALUES (?, ?, ?)",
-          [repo_id, file_path, commit.oid],
+          [repo_id, file_path, commit.oid]
         )
         file_id = @db.last_insert_row_id
         @db.execute(
           "INSERT INTO commit_files (commit_hash, file_id, changes) VALUES (?, ?, ?)",
-          [commit.oid, file_id, patch.to_s],
+          [commit.oid, file_id, patch.to_s]
         )
       end
     end
 
     def insert_commit_parents(commit)
+      BranchBase.logger.debug(
+        "Inserting parent commits for repository: #{@repo.path}"
+      )
+
       commit.parent_ids.each do |parent_id|
         @db.execute(
           "INSERT INTO commit_parents (commit_hash, parent_hash) VALUES (?, ?)",
-          [commit.oid, parent_id],
+          [commit.oid, parent_id]
         )
       end
     end
@@ -140,20 +148,34 @@ def insert_branches(batched_branches)
         batched_branches.each do |data|
           @db.execute(
             "INSERT OR IGNORE INTO branches (repo_id, name, head_commit) VALUES (?, ?, ?)",
-            data,
+            data
           )
         end
       end
     end
 
     def insert_commits(batched_commits)
+      BranchBase.logger.debug(
+        "Inserting commits for repository ID: #{@repo.path}"
+      )
+
+      return if batched_commits.empty?
+
       @db.transaction do
-        batched_commits.each do |data|
-          @db.execute(
-            "INSERT INTO commits (commit_hash, repo_id, author, committer, message, timestamp) VALUES (?, ?, ?, ?, ?, ?)",
-            data,
-          )
-        end
+        values_clause =
+          batched_commits
+            .map do |commit_data|
+              "(#{commit_data.map { |value| "'#{value}'" }.join(", ")})"
+            end
+            .join(", ")
+
+        sql = <<~SQL
+          INSERT INTO commits
+          (commit_hash, repo_id, author, committer, message, timestamp)
+          VALUES #{values_clause};
+        SQL
+
+        @db.execute(sql)
       end
     end
 
@@ -163,12 +185,12 @@ def insert_files_and_commit_files(batched_data)
           repo_id, file_path, commit_hash, changes = data
           @db.execute(
             "INSERT OR IGNORE INTO files (repo_id, file_path, latest_commit) VALUES (?, ?, ?)",
-            [repo_id, file_path, commit_hash],
+            [repo_id, file_path, commit_hash]
           )
           file_id = @db.last_insert_row_id
           @db.execute(
             "INSERT INTO commit_files (commit_hash, file_id, changes) VALUES (?, ?, ?)",
-            [commit_hash, file_id, changes],
+            [commit_hash, file_id, changes]
           )
         end
       end

spec/branch_base/database_spec.rb

@@ -1,6 +1,5 @@
 # frozen_string_literal: true
-require "branch_base/database"
-require "rspec"
+require "spec_helper"
 
 RSpec.describe(BranchBase::Database) do
   let(:database) { BranchBase::Database.new(":memory:") }
@@ -27,7 +26,7 @@
       result =
         database.execute(
           "INSERT INTO repositories (name, url) VALUES (?, ?)",
-          %w[mock_repo mock_repo/],
+          %w[mock_repo mock_repo/]
         )
       expect(result).to be_empty
     end
@@ -47,7 +46,7 @@
         database.transaction do
           database.execute(
             "INSERT INTO repositories (name, url) VALUES (?, ?)",
-            %w[mock_repo mock_repo/],
+            %w[mock_repo mock_repo/]
           )
           raise "Rollback transaction"
         end
@@ -62,7 +61,7 @@
     it "returns the last insert row ID" do
       database.execute(
         "INSERT INTO repositories (name, url) VALUES (?, ?)",
-        %w[mock_repo mock_repo/],
+        %w[mock_repo mock_repo/]
       )
       expect(database.last_insert_row_id).to be > 0
     end

spec/branch_base/repository_spec.rb

@@ -1,7 +1,5 @@
 # frozen_string_literal: true
-require "branch_base/repository"
-require "rugged"
-require "rspec"
+require "spec_helper"
 require "test_helper"
 
 RSpec.describe(BranchBase::Repository) do

spec/branch_base/sync_spec.rb

@@ -1,9 +1,6 @@
 # frozen_string_literal: true
-require "branch_base/sync"
-require "branch_base/database"
-require "branch_base/repository"
 require "test_helper"
-require "rspec"
+require "spec_helper"
 
 RSpec.describe(BranchBase::Sync) do
   let(:db) { BranchBase::Database.new(":memory:") }
@@ -27,7 +24,7 @@
         stored_repo =
           db.execute(
             "SELECT * FROM repositories WHERE repo_id = ?",
-            repo_id,
+            repo_id
           ).first
         expect(stored_repo).not_to be_nil
         expect(stored_repo[1]).to eq(File.basename(repo_path))
@@ -40,7 +37,7 @@
         existing_repo_id = sync.sync_repository
 
         expect { sync.sync_repository }.not_to(
-          change { db.execute("SELECT COUNT(*) FROM repositories").first[0] },
+          change { db.execute("SELECT COUNT(*) FROM repositories").first[0] }
         )
 
         expect(sync.sync_repository).to eq(existing_repo_id)
@@ -59,7 +56,7 @@
       expect(db_branches.size).to eq(git_branches.size)
       git_branches.each do |branch_name|
         expect(
-          db_branches.any? { |db_branch| db_branch[2] == branch_name },
+          db_branches.any? { |db_branch| db_branch[2] == branch_name }
         ).to be(true)
       end
     end
@@ -76,7 +73,7 @@
       expect(db_commits.size).to eq(git_commits.size)
       git_commits.each do |commit|
         expect(
-          db_commits.any? { |db_commit| db_commit[0] == commit.oid },
+          db_commits.any? { |db_commit| db_commit[0] == commit.oid }
         ).to be(true)
       end
     end

spec/spec_helper.rb

@@ -13,6 +13,8 @@
 # the additional setup, and require it from the spec files that actually need
 # it.
 #
+require "branch_base"
+
 # See https://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
 RSpec.configure do |config|
   # rspec-expectations config goes here. You can use an alternate