ruby-maat 1.0.0

data/lib/ruby_maat/parsers/git2_parser.rb

@@ -0,0 +1,72 @@
+# frozen_string_literal: true
+
+require "date"
+module RubyMaat
+  module Parsers
+    # Git2 parser - preferred Git parser (more tolerant and faster)
+    #
+    # Input: git log --all --numstat --date=short --pretty=format:'--%h--%ad--%aN' --no-renames --after=YYYY-MM-DD
+    #
+    # Sample format:
+    # --586b4eb--2015-06-15--Adam Tornhill
+    # 35      0       src/code_maat/mining/vcs.clj
+    # 2       1       test/file.rb
+    #
+    # --abc123--2015-06-16--Jane Doe
+    # 10      5       lib/example.rb
+    class Git2Parser < BaseParser
+      COMMIT_SEPARATOR = /^--([a-z0-9]+)--(\d{4}-\d{2}-\d{2})--(.+)$/
+      CHANGE_PATTERN = /^(-|\d+)\s+(-|\d+)\s+(.*)$/
+
+      protected
+
+      def parse_content(content)
+        records = []
+        current_commit = nil
+
+        content.each_line do |line|
+          line.strip!
+          next if line.empty?
+
+          if (commit_match = line.match(COMMIT_SEPARATOR))
+            current_commit = {
+              revision: commit_match[1],
+              date: parse_date(commit_match[2]),
+              author: commit_match[3].strip
+            }
+          elsif current_commit && (change_match = line.match(CHANGE_PATTERN))
+            added = clean_numstat(change_match[1])
+            deleted = clean_numstat(change_match[2])
+            file = change_match[3].strip
+
+            next if file.empty? || file == File::NULL
+            next if added.nil? && deleted.nil?
+
+            records << ChangeRecord.new(
+              entity: file,
+              author: current_commit[:author],
+              date: current_commit[:date],
+              revision: current_commit[:revision],
+              loc_added: added,
+              loc_deleted: deleted
+            )
+          end
+        end
+
+        records
+      end
+
+      private
+
+      def parse_date(date_str)
+        Date.parse(date_str)
+      rescue Date::Error
+        nil
+      end
+
+      def clean_numstat(value)
+        (value == "-") ? nil : value.to_i
+      end
+    end
+  end
+end

data/lib/ruby_maat/parsers/git_parser.rb

@@ -0,0 +1,66 @@
+# frozen_string_literal: true
+
+module RubyMaat
+  module Parsers
+    # Legacy Git parser for backward compatibility
+    #
+    # Input: git log --pretty=format:'[%h] %aN %ad %s' --date=short --numstat --after=YYYY-MM-DD
+    #
+    # Sample format:
+    # [586b4eb] Adam Tornhill 2015-06-15 Add new feature
+    # 35      0       src/code_maat/mining/vcs.clj
+    # 2       1       test/file.rb
+    #
+    # [abc123] Jane Doe 2015-06-16 Fix bug in parser
+    # 10      5       lib/example.rb
+    class GitParser < BaseParser
+      COMMIT_PATTERN = /^\[([a-f0-9]+)\]\s+(.+?)\s+(\d{4}-\d{2}-\d{2})\s+(.*)$/
+      CHANGE_PATTERN = /^(\d+|-)\s+(\d+|-)\s+(.+)$/
+
+      protected
+
+      def parse_content(content)
+        entries = []
+        current_commit = nil
+
+        content.each_line do |line|
+          line = line.chomp
+
+          # Skip empty lines
+          next if line.strip.empty?
+
+          if (commit_match = line.match(COMMIT_PATTERN))
+            # New commit header
+            current_commit = {
+              revision: commit_match[1],
+              author: commit_match[2].strip,
+              date: parse_date(commit_match[3]),
+              message: commit_match[4].strip
+            }
+          elsif current_commit && (change_match = line.match(CHANGE_PATTERN))
+            # File change line
+            added = clean_numstat(change_match[1])
+            deleted = clean_numstat(change_match[2])
+            file = change_match[3].strip
+
+            # Skip empty or invalid file names
+            next if file.empty? || file == File::NULL
+
+            entries << ChangeRecord.new(
+              entity: file,
+              author: current_commit[:author],
+              date: current_commit[:date],
+              revision: current_commit[:revision],
+              message: current_commit[:message],
+              loc_added: added,
+              loc_deleted: deleted
+            )
+          end
+          # Ignore unrecognized lines
+        end
+
+        entries
+      end
+    end
+  end
+end

data/lib/ruby_maat/parsers/mercurial_parser.rb

@@ -0,0 +1,64 @@
+# frozen_string_literal: true
+
+module RubyMaat
+  module Parsers
+    # Mercurial parser
+    #
+    # Input: hg log --template "rev: {rev} author: {author} date: {date|shortdate} files:\n{files %'{file}\n'}\n" --date ">YYYY-MM-DD"
+    #
+    # Sample format:
+    # rev: 123 author: John Doe date: 2015-06-15 files:
+    # src/main.py
+    # test/test_main.py
+    #
+    # rev: 124 author: Jane Smith date: 2015-06-16 files:
+    # lib/helper.py
+    class MercurialParser < BaseParser
+      ENTRY_PATTERN = /^rev:\s+(\d+)\s+author:\s+(.+?)\s+date:\s+(\d{4}-\d{2}-\d{2})\s+files:$/
+
+      protected
+
+      def parse_content(content)
+        entries = []
+        current_commit = nil
+        in_files_section = false
+
+        content.each_line do |line|
+          line = line.chomp
+
+          if line.strip.empty?
+            # Empty line marks end of current commit
+            current_commit = nil
+            in_files_section = false
+            next
+          end
+
+          if (commit_match = line.match(ENTRY_PATTERN))
+            # New commit header
+            current_commit = {
+              revision: commit_match[1],
+              author: commit_match[2].strip,
+              date: parse_date(commit_match[3])
+            }
+            in_files_section = true
+          elsif current_commit && in_files_section && !line.strip.empty?
+            # File line
+            file = line.strip
+
+            # Skip invalid file names
+            next if file.empty? || file == File::NULL
+
+            entries << ChangeRecord.new(
+              entity: file,
+              author: current_commit[:author],
+              date: current_commit[:date],
+              revision: current_commit[:revision]
+            )
+          end
+        end
+
+        entries
+      end
+    end
+  end
+end

data/lib/ruby_maat/parsers/perforce_parser.rb

@@ -0,0 +1,77 @@
+# frozen_string_literal: true
+
+module RubyMaat
+  module Parsers
+    # Perforce parser
+    #
+    # Input: p4 changes -s submitted -m 5000 //depot/project/... | cut -d ' ' -f 2 | xargs -I commitid -n1 sh -c 'p4 describe -s commitid | grep -v "^\s*$" && echo ""'
+    #
+    # Sample format:
+    # Change 12345 by jdoe@workspace on 2015/06/15 10:30:45
+    #
+    #         Fix bug in parser
+    #
+    # Affected files ...
+    #
+    # ... //depot/project/src/main.java#2 edit
+    # ... //depot/project/test/test.java#1 add
+    class PerforceParser < BaseParser
+      CHANGE_PATTERN = %r{^Change\s+(\d+)\s+by\s+([^@]+)@\S+\s+on\s+(\d{4}/\d{2}/\d{2})}
+      FILE_PATTERN = /^\.\.\.\s+(.+?)#\d+\s+(\w+)/
+
+      protected
+
+      def parse_content(content)
+        entries = []
+        current_commit = nil
+        in_files_section = false
+
+        content.each_line do |line|
+          line = line.chomp
+
+          if (change_match = line.match(CHANGE_PATTERN))
+            # New changelist header
+            current_commit = {
+              revision: change_match[1],
+              author: change_match[2].strip,
+              date: parse_perforce_date(change_match[3])
+            }
+            in_files_section = false
+          elsif line.include?("Affected files")
+            # Start of files section
+            in_files_section = true
+          elsif current_commit && in_files_section && (file_match = line.match(FILE_PATTERN))
+            # File change line
+            file = file_match[1].strip
+            action = file_match[2]
+
+            # Skip deleted files for most analyses (they don't contribute to current state)
+            next if action == "delete"
+            next if file.empty?
+
+            entries << ChangeRecord.new(
+              entity: file,
+              author: current_commit[:author],
+              date: current_commit[:date],
+              revision: current_commit[:revision]
+            )
+          elsif line.strip.empty? && current_commit
+            # Empty line might end current changelist
+            # But we keep current_commit until we see a new one
+          end
+        end
+
+        entries
+      end
+
+      private
+
+      def parse_perforce_date(date_str)
+        # Perforce date format: 2015/06/15
+        Date.strptime(date_str, "%Y/%m/%d")
+      rescue Date::Error => e
+        raise ArgumentError, "Invalid Perforce date format: #{date_str} (#{e.message})"
+      end
+    end
+  end
+end

data/lib/ruby_maat/parsers/svn_parser.rb

@@ -0,0 +1,76 @@
+# frozen_string_literal: true
+
+require "rexml/document"
+
+module RubyMaat
+  module Parsers
+    # SVN parser for XML log files
+    #
+    # Input: svn log -v --xml > logfile.log -r {YYYYmmDD}:HEAD
+    #
+    # Sample XML format:
+    # <log>
+    #   <logentry revision="12345">
+    #     <author>jdoe</author>
+    #     <date>2015-06-15T10:30:45.123456Z</date>
+    #     <paths>
+    #       <path action="M">/trunk/src/file.java</path>
+    #       <path action="A">/trunk/test/test.java</path>
+    #     </paths>
+    #     <msg>Fix bug in parser</msg>
+    #   </logentry>
+    # </log>
+    class SvnParser < BaseParser
+      protected
+
+      def parse_content(content)
+        entries = []
+
+        begin
+          doc = REXML::Document.new(content)
+
+          doc.elements.each("log/logentry") do |logentry|
+            revision = logentry.attributes["revision"]
+            author = logentry.elements["author"]&.text || "unknown"
+            date_text = logentry.elements["date"]&.text
+            message = logentry.elements["msg"]&.text || ""
+
+            next unless date_text && revision
+
+            date = parse_svn_date(date_text)
+
+            # Extract all path changes
+            logentry.elements.each("paths/path") do |path_element|
+              entity = path_element.text&.strip
+              path_element.attributes["action"]
+
+              next if entity.nil? || entity.empty?
+
+              entries << ChangeRecord.new(
+                entity: entity,
+                author: author,
+                date: date,
+                revision: revision,
+                message: message
+              )
+            end
+          end
+        rescue REXML::ParseException => e
+          raise ArgumentError, "Invalid XML format in SVN log file: #{e.message}"
+        end
+
+        entries
+      end
+
+      private
+
+      def parse_svn_date(date_str)
+        # SVN date format: 2015-06-15T10:30:45.123456Z
+        # Convert to Date object
+        DateTime.parse(date_str).to_date
+      rescue => e
+        raise ArgumentError, "Invalid SVN date format: #{date_str} (#{e.message})"
+      end
+    end
+  end
+end

data/lib/ruby_maat/parsers/tfs_parser.rb

@@ -0,0 +1,103 @@
+# frozen_string_literal: true
+
+module RubyMaat
+  module Parsers
+    # Team Foundation Server parser
+    #
+    # Input: tf hist /path/to/workspace /noprompt /format:detailed /recursive
+    #
+    # Sample format:
+    # Changeset: 12345
+    # User: DOMAIN\jdoe
+    # Date: Friday, January 15, 2016 1:12:35 PM
+    #
+    # Comment:
+    #   Fix bug in parser
+    #
+    # Items:
+    #   edit $/Project/src/main.cs
+    #   add $/Project/test/test.cs
+    class TfsParser < BaseParser
+      CHANGESET_PATTERN = /^Changeset:\s+(\d+)/
+      USER_PATTERN = /^User:\s+(.+)/
+      DATE_PATTERN = /^Date:\s+(.+)/
+      ITEM_PATTERN = /^\s+(edit|add|delete)\s+(\S.+)/
+
+      protected
+
+      def parse_content(content)
+        entries = []
+        current_commit = nil
+        in_items_section = false
+
+        content.each_line do |line|
+          line = line.chomp
+
+          if (changeset_match = line.match(CHANGESET_PATTERN))
+            # New changeset
+            current_commit = {revision: changeset_match[1]}
+            in_items_section = false
+          elsif current_commit && (user_match = line.match(USER_PATTERN))
+            # User line
+            user = user_match[1].strip
+            # Remove domain prefix if present (DOMAIN\user -> user)
+            user = user.split("\\").last if user.include?("\\")
+            current_commit[:author] = user
+          elsif current_commit && (date_match = line.match(DATE_PATTERN))
+            # Date line
+            begin
+              current_commit[:date] = parse_tfs_date(date_match[1])
+            rescue ArgumentError
+              # Skip this changeset if we can't parse the date
+              current_commit = nil
+              next
+            end
+          elsif line.strip == "Items:"
+            # Start of items section
+            in_items_section = true
+          elsif current_commit && in_items_section && (item_match = line.match(ITEM_PATTERN))
+            # Item change line
+            action = item_match[1]
+            file = item_match[2].strip
+
+            # Skip deleted files and invalid paths
+            next if action == "delete"
+            next if file.empty? || file == "$/null"
+
+            # Ensure we have all required fields
+            next unless current_commit[:author] && current_commit[:date]
+
+            entries << ChangeRecord.new(
+              entity: file,
+              author: current_commit[:author],
+              date: current_commit[:date],
+              revision: current_commit[:revision]
+            )
+          elsif line.strip.empty?
+            # Empty line might separate sections
+            in_items_section = false if in_items_section
+          end
+        end
+
+        entries
+      end
+
+      private
+
+      def parse_tfs_date(date_str)
+        # TFS date format: "Friday, January 15, 2016 1:12:35 PM"
+        # Note: The parser expects en-US locale format
+        begin
+          DateTime.strptime(date_str.strip, "%A, %B %d, %Y %I:%M:%S %p").to_date
+        rescue Date::Error
+          # Try alternative format without day of week
+          DateTime.strptime(date_str.strip, "%B %d, %Y %I:%M:%S %p").to_date
+        end
+      rescue Date::Error => e
+        raise ArgumentError,
+          "Invalid TFS date format: #{date_str}. Expected en-US locale format like " \
+          "'Friday, January 15, 2016 1:12:35 PM' (#{e.message})"
+      end
+    end
+  end
+end

data/lib/ruby_maat/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module RubyMaat
+  VERSION = "1.0.0"
+end

data/lib/ruby_maat.rb

@@ -0,0 +1,44 @@
+# frozen_string_literal: true
+
+require_relative "ruby_maat/version"
+require_relative "ruby_maat/change_record"
+require_relative "ruby_maat/dataset"
+
+# Core parsers
+require_relative "ruby_maat/parsers/base_parser"
+require_relative "ruby_maat/parsers/git_parser"
+require_relative "ruby_maat/parsers/git2_parser"
+require_relative "ruby_maat/parsers/svn_parser"
+require_relative "ruby_maat/parsers/mercurial_parser"
+require_relative "ruby_maat/parsers/perforce_parser"
+require_relative "ruby_maat/parsers/tfs_parser"
+
+# Data processors
+require_relative "ruby_maat/groupers/layer_grouper"
+require_relative "ruby_maat/groupers/time_grouper"
+require_relative "ruby_maat/groupers/team_mapper"
+
+# Analysis modules (load before app.rb since app references them)
+require_relative "ruby_maat/analysis/base_analysis"
+require_relative "ruby_maat/analysis/authors"
+require_relative "ruby_maat/analysis/entities"
+require_relative "ruby_maat/analysis/logical_coupling"
+require_relative "ruby_maat/analysis/churn"
+require_relative "ruby_maat/analysis/effort"
+require_relative "ruby_maat/analysis/communication"
+require_relative "ruby_maat/analysis/code_age"
+require_relative "ruby_maat/analysis/summary"
+require_relative "ruby_maat/analysis/commit_messages"
+require_relative "ruby_maat/analysis/sum_of_coupling"
+require_relative "ruby_maat/analysis/identity"
+
+# Output
+require_relative "ruby_maat/output/csv_output"
+
+# Main app and CLI (load after dependencies)
+require_relative "ruby_maat/app"
+require_relative "ruby_maat/cli"
+
+module RubyMaat
+  class Error < StandardError; end
+end

metadata

@@ -0,0 +1,143 @@
+--- !ruby/object:Gem::Specification
+name: ruby-maat
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+platform: ruby
+authors:
+- Adam Tornhill
+- Claude Code
+- Bart Agapinan
+bindir: exe
+cert_chain: []
+date: 2025-08-16 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: csv
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.2'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.2'
+- !ruby/object:Gem::Dependency
+  name: rexml
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.2'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.2'
+- !ruby/object:Gem::Dependency
+  name: rover-df
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.3'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.3'
+description: Ruby Maat is a command line tool used to mine and analyze data from version-control
+  systems (VCS). This is a Ruby port of the original Clojure Code Maat.
+email:
+- bart@sonic.net
+executables:
+- ruby-maat
+extensions: []
+extra_rdoc_files: []
+files:
+- ".commitlintrc.json"
+- ".mailmap"
+- ".overcommit.yml"
+- ".release-please-config.json"
+- ".release-please-manifest.json"
+- ".rspec"
+- ".rubocop.yml"
+- CHANGELOG.md
+- CI_CD_SETUP.md
+- CLAUDE.md
+- Dockerfile
+- README.md
+- README_RUBY.md
+- RELEASE_PLEASE_SETUP.md
+- RUBY_MAAT.md
+- Rakefile
+- doc/imgs/abs_churn_sample.png
+- doc/imgs/code_age_sample.png
+- doc/imgs/coupling_sample.png
+- doc/imgs/crime_cover.jpg
+- doc/imgs/tree_map_sample.png
+- doc/intro.md
+- exe/ruby-maat
+- lib/ruby_maat.rb
+- lib/ruby_maat/analysis/authors.rb
+- lib/ruby_maat/analysis/base_analysis.rb
+- lib/ruby_maat/analysis/churn.rb
+- lib/ruby_maat/analysis/code_age.rb
+- lib/ruby_maat/analysis/commit_messages.rb
+- lib/ruby_maat/analysis/communication.rb
+- lib/ruby_maat/analysis/effort.rb
+- lib/ruby_maat/analysis/entities.rb
+- lib/ruby_maat/analysis/identity.rb
+- lib/ruby_maat/analysis/logical_coupling.rb
+- lib/ruby_maat/analysis/sum_of_coupling.rb
+- lib/ruby_maat/analysis/summary.rb
+- lib/ruby_maat/app.rb
+- lib/ruby_maat/change_record.rb
+- lib/ruby_maat/cli.rb
+- lib/ruby_maat/dataset.rb
+- lib/ruby_maat/groupers/layer_grouper.rb
+- lib/ruby_maat/groupers/team_mapper.rb
+- lib/ruby_maat/groupers/time_grouper.rb
+- lib/ruby_maat/output/csv_output.rb
+- lib/ruby_maat/parsers/base_parser.rb
+- lib/ruby_maat/parsers/git2_parser.rb
+- lib/ruby_maat/parsers/git_parser.rb
+- lib/ruby_maat/parsers/mercurial_parser.rb
+- lib/ruby_maat/parsers/perforce_parser.rb
+- lib/ruby_maat/parsers/svn_parser.rb
+- lib/ruby_maat/parsers/tfs_parser.rb
+- lib/ruby_maat/version.rb
+homepage: https://github.com/viamin/ruby-maat
+licenses:
+- GPL-3.0
+metadata:
+  allowed_push_host: https://rubygems.org
+  homepage_uri: https://github.com/viamin/ruby-maat
+  source_code_uri: https://github.com/viamin/ruby-maat
+  changelog_uri: https://github.com/viamin/ruby-maat/blob/main/CHANGELOG.md
+  rubygems_mfa_required: 'true'
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 3.2.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.6.2
+specification_version: 4
+summary: A command line tool used to mine and analyze data from version-control systems
+test_files: []