cabriolet 0.2.0 → 0.2.1

data/lib/cabriolet/lit/structure_builder.rb

@@ -0,0 +1,252 @@
+# frozen_string_literal: true
+
+require_relative "guid_generator"
+require_relative "content_type_detector"
+require_relative "directory_builder"
+
+module Cabriolet
+  module LIT
+    # Builds complete LIT structure from file data
+    class StructureBuilder
+      attr_reader :io_system, :version, :language_id, :creator_id
+
+      # Initialize structure builder
+      #
+      # @param io_system [System::IOSystem] I/O system for file operations
+      # @param version [Integer] LIT format version
+      # @param language_id [Integer] Language ID
+      # @param creator_id [Integer] Creator ID
+      def initialize(io_system:, version: 1, language_id: 0x409, creator_id: 0)
+        @io_system = io_system
+        @version = version
+        @language_id = language_id
+        @creator_id = creator_id
+      end
+
+      # Build complete LIT structure from file data
+      #
+      # @param file_data [Array<Hash>] File data array from prepare_files
+      # @return [Hash] Complete LIT structure
+      def build(file_data)
+        structure = {}
+
+        # Generate GUIDs
+        structure[:header_guid] = GuidGenerator.generate
+        structure[:piece3_guid] = Binary::LITStructures::GUIDs::PIECE3
+        structure[:piece4_guid] = Binary::LITStructures::GUIDs::PIECE4
+
+        # Build directory
+        structure[:directory] = build_directory(file_data)
+
+        # Build sections
+        structure[:sections] = build_sections
+
+        # Build manifest
+        structure[:manifest] = build_manifest(file_data)
+
+        # Build secondary header metadata
+        structure[:secondary_header] = build_secondary_header_metadata
+
+        # Calculate piece offsets and sizes
+        structure[:pieces] = calculate_pieces(structure)
+
+        # Update secondary header with content offset
+        update_secondary_header_content_offset(structure)
+
+        # Store metadata
+        structure[:version] = @version
+        structure[:file_data] = file_data
+
+        structure
+      end
+
+      private
+
+      # Build directory structure from file data
+      #
+      # @param file_data [Array<Hash>] File data array
+      # @return [Hash] Directory structure
+      def build_directory(file_data)
+        builder = DirectoryBuilder.new
+
+        # Add entries for all files
+        section = 0
+        offset = 0
+
+        file_data.each do |file_info|
+          builder.add_entry(
+            name: file_info[:lit_path],
+            section: section,
+            offset: offset,
+            size: file_info[:uncompressed_size],
+          )
+          offset += file_info[:uncompressed_size]
+        end
+
+        # Calculate NameList size
+        namelist_size = calculate_namelist_size
+
+        # Calculate manifest size
+        manifest_size = calculate_manifest_size(file_data)
+
+        # Add special entries for LIT structure
+        builder.add_entry(
+          name: Binary::LITStructures::Paths::NAMELIST,
+          section: 0,
+          offset: offset,
+          size: namelist_size,
+        )
+        offset += namelist_size
+
+        builder.add_entry(
+          name: Binary::LITStructures::Paths::MANIFEST,
+          section: 0,
+          offset: offset,
+          size: manifest_size,
+        )
+
+        builder.build
+      end
+
+      # Build sections array
+      #
+      # @return [Array<Hash>] Sections array
+      def build_sections
+        # For simple implementation: single uncompressed section
+        [
+          {
+            name: "Uncompressed",
+            transforms: [],
+            compressed: false,
+            encrypted: false,
+          },
+        ]
+      end
+
+      # Build manifest from file data
+      #
+      # @param file_data [Array<Hash>] File data array
+      # @return [Hash] Manifest structure
+      def build_manifest(file_data)
+        mappings = []
+
+        file_data.each_with_index do |file_info, index|
+          mappings << {
+            offset: index,
+            internal_name: file_info[:lit_path],
+            original_name: file_info[:lit_path],
+            content_type: ContentTypeDetector.content_type(file_info[:lit_path]),
+            group: ContentTypeDetector.file_group(file_info[:lit_path]),
+          }
+        end
+
+        { mappings: mappings }
+      end
+
+      # Build secondary header metadata
+      #
+      # @return [Hash] Secondary header metadata
+      def build_secondary_header_metadata
+        # Calculate actual secondary header length
+        temp_header = Binary::LITStructures::SecondaryHeader.new
+        sec_hdr_length = temp_header.to_binary_s.bytesize
+
+        {
+          length: sec_hdr_length,
+          entry_chunklen: 0x2000, # 8KB chunks for entry directory
+          count_chunklen: 0x200,      # 512B chunks for count directory
+          entry_unknown: 0x100000,
+          count_unknown: 0x20000,
+          entry_depth: 1,             # No AOLI index layer
+          entry_entries: 0,           # Will be set when directory built
+          count_entries: 0,           # Will be set when directory built
+          content_offset: 0,          # Will be calculated after pieces
+          timestamp: Time.now.to_i,
+          language_id: @language_id,
+          creator_id: @creator_id,
+        }
+      end
+
+      # Calculate piece offsets and sizes
+      #
+      # @param structure [Hash] Partial structure (needs secondary_header)
+      # @return [Array<Hash>] Pieces array
+      def calculate_pieces(structure)
+        pieces = []
+
+        # Calculate starting offset (after headers and pieces)
+        sec_hdr_length = structure[:secondary_header][:length]
+        current_offset = 40 + 80 + sec_hdr_length
+
+        # Piece 0: File size information (16 bytes)
+        pieces << { offset: current_offset, size: 16 }
+        current_offset += 16
+
+        # Piece 1: Directory (IFCM structure)
+        # Build DirectoryBuilder to calculate size
+        dir_builder = DirectoryBuilder.new(chunk_size: structure[:directory][:chunk_size])
+        structure[:directory][:entries].each do |entry|
+          dir_builder.add_entry(
+            name: entry[:name],
+            section: entry[:section],
+            offset: entry[:offset],
+            size: entry[:size],
+          )
+        end
+        piece1_size = dir_builder.calculate_size
+        pieces << { offset: current_offset, size: piece1_size }
+        current_offset += piece1_size
+
+        # Piece 2: Index information (typically empty or minimal)
+        piece2_size = 512
+        pieces << { offset: current_offset, size: piece2_size }
+        current_offset += piece2_size
+
+        # Piece 3: Standard GUID (16 bytes)
+        pieces << { offset: current_offset, size: 16 }
+        current_offset += 16
+
+        # Piece 4: Standard GUID (16 bytes)
+        pieces << { offset: current_offset, size: 16 }
+
+        pieces
+      end
+
+      # Update secondary header with final content offset
+      #
+      # @param structure [Hash] Structure to update
+      def update_secondary_header_content_offset(structure)
+        pieces = structure[:pieces]
+        last_piece = pieces.last
+        content_offset = last_piece[:offset] + last_piece[:size]
+
+        structure[:secondary_header][:content_offset] = content_offset
+      end
+
+      # Calculate NameList size (estimate)
+      #
+      # @return [Integer] Estimated size
+      def calculate_namelist_size
+        # Simple estimate: ~100 bytes for minimal NameList
+        100
+      end
+
+      # Calculate manifest size (estimate)
+      #
+      # @param file_data [Array<Hash>] File data array
+      # @return [Integer] Estimated size
+      def calculate_manifest_size(file_data)
+        # Rough estimate: directory header + entries
+        size = 10 # Directory header
+
+        file_data.each do |file_info|
+          # Per entry: offset (4) + 3 length bytes + names + content type + terminator
+          size += 4 + 3
+          size += (file_info[:lit_path].bytesize * 2) + 20 + 1
+        end
+
+        size
+      end
+    end
+  end
+end

data/lib/cabriolet/quantum_shared.rb

@@ -0,0 +1,105 @@
+# frozen_string_literal: true
+
+module Cabriolet
+  # Shared Quantum compression constants and models
+  # Used by both Compressors::Quantum and Decompressors::Quantum
+  module QuantumShared
+    # Frame size (32KB per frame)
+    FRAME_SIZE = 32_768
+
+    # Match constants
+    MIN_MATCH = 3
+    MAX_MATCH = 259
+
+    # Position slot tables (same as in qtmd.c)
+    POSITION_BASE = [
+      0, 1, 2, 3, 4, 6, 8, 12, 16, 24, 32, 48, 64, 96, 128, 192, 256, 384,
+      512, 768, 1024, 1536, 2048, 3072, 4096, 6144, 8192, 12_288, 16_384,
+      24_576, 32_768, 49_152, 65_536, 98_304, 131_072, 196_608, 262_144,
+      393_216, 524_288, 786_432, 1_048_576, 1_572_864
+    ].freeze
+
+    EXTRA_BITS = [
+      0, 0, 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+      9, 9, 10, 10, 11, 11, 12, 12, 13, 13, 14, 14, 15, 15, 16, 16,
+      17, 17, 18, 18, 19, 19
+    ].freeze
+
+    LENGTH_BASE = [
+      0, 1, 2, 3, 4, 5, 6, 8, 10, 12, 14, 18, 22, 26,
+      30, 38, 46, 54, 62, 78, 94, 110, 126, 158, 190, 222, 254
+    ].freeze
+
+    LENGTH_EXTRA = [
+      0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2,
+      3, 3, 3, 3, 4, 4, 4, 4, 5, 5, 5, 5, 0
+    ].freeze
+
+    # Represents a symbol in an arithmetic coding model
+    class ModelSymbol
+      attr_accessor :sym, :cumfreq
+
+      def initialize(sym, cumfreq)
+        @sym = sym
+        @cumfreq = cumfreq
+      end
+    end
+
+    # Represents an arithmetic coding model
+    class Model
+      attr_accessor :shiftsleft, :entries, :syms
+
+      def initialize(syms, entries)
+        @syms = syms
+        @entries = entries
+        @shiftsleft = 4
+      end
+    end
+
+    # Find position slot for a given offset
+    #
+    # @param offset [Integer] Position offset
+    # @return [Integer] Position slot index
+    def self.find_position_slot(offset)
+      return 0 if offset < 4
+
+      # Binary search through POSITION_BASE
+      low = 1
+      high = POSITION_BASE.size - 1
+
+      while low < high
+        mid = (low + high + 1) / 2
+        if POSITION_BASE[mid] <= offset
+          low = mid
+        else
+          high = mid - 1
+        end
+      end
+
+      low
+    end
+
+    # Find length slot for a given length
+    #
+    # @param length [Integer] Match length
+    # @return [Integer] Length slot index
+    def self.find_length_slot(length)
+      return 0 if length < 4
+
+      # Binary search through LENGTH_BASE
+      low = 1
+      high = LENGTH_BASE.size - 1
+
+      while low < high
+        mid = (low + high + 1) / 2
+        if LENGTH_BASE[mid] <= length
+          low = mid
+        else
+          high = mid - 1
+        end
+      end
+
+      low
+    end
+  end
+end

data/lib/cabriolet/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Cabriolet
-  VERSION = "0.2.0"
+  VERSION = "0.2.1"
 end

data/lib/cabriolet.rb

@@ -26,6 +26,7 @@ require_relative "cabriolet/binary/oab_structures"
 require_relative "cabriolet/file_entry"
 require_relative "cabriolet/file_manager"
 require_relative "cabriolet/base_compressor"
+require_relative "cabriolet/checksum"
 
 # Cabriolet is a pure Ruby library for extracting Microsoft Cabinet (.CAB) files,
 # CHM (Compiled HTML Help) files, and related compression formats.
@@ -61,7 +62,9 @@ module Cabriolet
   end
 
   self.verbose = false
-  self.default_buffer_size = 4096
+  # Default buffer size of 64KB - better for modern systems
+  # Larger buffers reduce I/O syscall overhead significantly
+  self.default_buffer_size = 65_536
 end
 
 # Models
@@ -92,6 +95,8 @@ require_relative "cabriolet/algorithm_factory"
 
 # Load core components
 
+require_relative "cabriolet/quantum_shared"
+
 require_relative "cabriolet/huffman/tree"
 require_relative "cabriolet/huffman/decoder"
 require_relative "cabriolet/huffman/encoder"
@@ -143,12 +148,118 @@ require_relative "cabriolet/oab/compressor"
 
 # Load new advanced features
 require_relative "cabriolet/format_detector"
-require_relative "cabriolet/auto"
+require_relative "cabriolet/extraction/base_extractor"
+require_relative "cabriolet/extraction/extractor"
 require_relative "cabriolet/streaming"
 require_relative "cabriolet/validator"
 require_relative "cabriolet/repairer"
 require_relative "cabriolet/modifier"
-require_relative "cabriolet/parallel"
 
 # Load CLI (optional, for command-line usage)
 require_relative "cabriolet/cli"
+
+# Convenience methods at top level
+module Cabriolet
+  class << self
+    # Open and parse an archive with automatic format detection
+    #
+    # @param path [String] Path to the archive file
+    # @param options [Hash] Options to pass to the parser
+    # @return [Object] Parsed archive object
+    # @raise [UnsupportedFormatError] if format cannot be detected or is unsupported
+    #
+    # @example
+    #   archive = Cabriolet.open('unknown.archive')
+    #   archive.files.each { |f| puts f.name }
+    def open(path, **options)
+      parser_class = FormatDetector.parser_for(path)
+
+      unless parser_class
+        format = detect_format(path)
+        raise UnsupportedFormatError,
+              "Unable to detect format or no parser available for: #{path} (detected: #{format || 'unknown'})"
+      end
+
+      parser_class.new(**options).parse(path)
+    end
+
+    # Detect format of an archive file
+    #
+    # @param path [String] Path to the file
+    # @return [Symbol, nil] Detected format symbol or nil
+    #
+    # @example
+    #   format = Cabriolet.detect_format('file.cab')
+    #   # => :cab
+    def detect_format(path)
+      FormatDetector.detect(path)
+    end
+
+    # Extract files from an archive with automatic format detection
+    #
+    # @param archive_path [String] Path to the archive
+    # @param output_dir [String] Directory to extract to
+    # @param options [Hash] Extraction options
+    # @option options [Integer] :workers (4) Number of parallel workers (1 = sequential)
+    # @option options [Boolean] :preserve_paths (true) Preserve directory structure
+    # @option options [Boolean] :overwrite (false) Overwrite existing files
+    # @return [Hash] Extraction statistics
+    #
+    # @example Sequential extraction
+    #   Cabriolet.extract('archive.cab', 'output/')
+    #
+    # @example Parallel extraction with 8 workers
+    #   stats = Cabriolet.extract('file.chm', 'docs/', workers: 8)
+    #   puts "Extracted #{stats[:extracted]} files"
+    def extract(archive_path, output_dir, **options)
+      archive = open(archive_path)
+      extractor = Extraction::Extractor.new(archive, output_dir, **options)
+      extractor.extract_all
+    end
+
+    # Get information about an archive without full extraction
+    #
+    # @param path [String] Path to the archive
+    # @return [Hash] Archive information
+    #
+    # @example
+    #   info = Cabriolet.info('archive.cab')
+    #   # => { format: :cab, file_count: 145, total_size: 52428800, ... }
+    def info(path)
+      archive = open(path)
+      format = detect_format(path)
+
+      {
+        format: format,
+        path: path,
+        file_count: archive.files.count,
+        total_size: archive.files.sum { |f| f.size || 0 },
+        compressed_size: File.size(path),
+        compression_ratio: calculate_compression_ratio(archive, path),
+        files: archive.files.map { |f| file_info(f) },
+      }
+    end
+
+    private
+
+    def calculate_compression_ratio(archive, path)
+      total_uncompressed = archive.files.sum { |f| f.size || 0 }
+      compressed = File.size(path)
+
+      return 0 if total_uncompressed.zero?
+
+      ((compressed.to_f / total_uncompressed) * 100).round(2)
+    end
+
+    def file_info(file)
+      {
+        name: file.name,
+        size: file.size,
+        compressed_size: file.respond_to?(:compressed_size) ? file.compressed_size : nil,
+        attributes: file.respond_to?(:attributes) ? file.attributes : nil,
+        date: file.respond_to?(:date) ? file.date : nil,
+        time: file.respond_to?(:time) ? file.time : nil,
+      }
+    end
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: cabriolet
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.1
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-01-15 00:00:00.000000000 Z
+date: 2026-01-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bindata
@@ -24,6 +24,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '2.5'
+- !ruby/object:Gem::Dependency
+  name: fractor
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.1'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.1'
 - !ruby/object:Gem::Dependency
   name: thor
   requirement: !ruby/object:Gem::Requirement
@@ -54,7 +68,6 @@ files:
 - exe/cabriolet
 - lib/cabriolet.rb
 - lib/cabriolet/algorithm_factory.rb
-- lib/cabriolet/auto.rb
 - lib/cabriolet/base_compressor.rb
 - lib/cabriolet/binary/bitstream.rb
 - lib/cabriolet/binary/bitstream_writer.rb
@@ -69,7 +82,10 @@ files:
 - lib/cabriolet/cab/compressor.rb
 - lib/cabriolet/cab/decompressor.rb
 - lib/cabriolet/cab/extractor.rb
+- lib/cabriolet/cab/file_compression_work.rb
+- lib/cabriolet/cab/file_compression_worker.rb
 - lib/cabriolet/cab/parser.rb
+- lib/cabriolet/checksum.rb
 - lib/cabriolet/chm/command_handler.rb
 - lib/cabriolet/chm/compressor.rb
 - lib/cabriolet/chm/decompressor.rb
@@ -78,6 +94,7 @@ files:
 - lib/cabriolet/cli/base_command_handler.rb
 - lib/cabriolet/cli/command_dispatcher.rb
 - lib/cabriolet/cli/command_registry.rb
+- lib/cabriolet/collections/file_collection.rb
 - lib/cabriolet/compressors/base.rb
 - lib/cabriolet/compressors/lzss.rb
 - lib/cabriolet/compressors/lzx.rb
@@ -91,8 +108,13 @@ files:
 - lib/cabriolet/decompressors/none.rb
 - lib/cabriolet/decompressors/quantum.rb
 - lib/cabriolet/errors.rb
+- lib/cabriolet/extraction/base_extractor.rb
+- lib/cabriolet/extraction/extractor.rb
+- lib/cabriolet/extraction/file_extraction_work.rb
+- lib/cabriolet/extraction/file_extraction_worker.rb
 - lib/cabriolet/file_entry.rb
 - lib/cabriolet/file_manager.rb
+- lib/cabriolet/format_base.rb
 - lib/cabriolet/format_detector.rb
 - lib/cabriolet/hlp/command_handler.rb
 - lib/cabriolet/hlp/compressor.rb
@@ -101,9 +123,14 @@ files:
 - lib/cabriolet/hlp/quickhelp/compression_stream.rb
 - lib/cabriolet/hlp/quickhelp/compressor.rb
 - lib/cabriolet/hlp/quickhelp/decompressor.rb
+- lib/cabriolet/hlp/quickhelp/file_writer.rb
 - lib/cabriolet/hlp/quickhelp/huffman_stream.rb
 - lib/cabriolet/hlp/quickhelp/huffman_tree.rb
+- lib/cabriolet/hlp/quickhelp/offset_calculator.rb
 - lib/cabriolet/hlp/quickhelp/parser.rb
+- lib/cabriolet/hlp/quickhelp/structure_builder.rb
+- lib/cabriolet/hlp/quickhelp/topic_builder.rb
+- lib/cabriolet/hlp/quickhelp/topic_compressor.rb
 - lib/cabriolet/hlp/winhelp/btree_builder.rb
 - lib/cabriolet/hlp/winhelp/compressor.rb
 - lib/cabriolet/hlp/winhelp/decompressor.rb
@@ -118,8 +145,15 @@ files:
 - lib/cabriolet/kwaj/parser.rb
 - lib/cabriolet/lit/command_handler.rb
 - lib/cabriolet/lit/compressor.rb
+- lib/cabriolet/lit/content_encoder.rb
+- lib/cabriolet/lit/content_type_detector.rb
 - lib/cabriolet/lit/decompressor.rb
+- lib/cabriolet/lit/directory_builder.rb
+- lib/cabriolet/lit/guid_generator.rb
+- lib/cabriolet/lit/header_writer.rb
 - lib/cabriolet/lit/parser.rb
+- lib/cabriolet/lit/piece_builder.rb
+- lib/cabriolet/lit/structure_builder.rb
 - lib/cabriolet/models/cabinet.rb
 - lib/cabriolet/models/chm_file.rb
 - lib/cabriolet/models/chm_header.rb
@@ -139,11 +173,11 @@ files:
 - lib/cabriolet/oab/compressor.rb
 - lib/cabriolet/oab/decompressor.rb
 - lib/cabriolet/offset_calculator.rb
-- lib/cabriolet/parallel.rb
 - lib/cabriolet/platform.rb
 - lib/cabriolet/plugin.rb
 - lib/cabriolet/plugin_manager.rb
 - lib/cabriolet/plugin_validator.rb
+- lib/cabriolet/quantum_shared.rb
 - lib/cabriolet/repairer.rb
 - lib/cabriolet/streaming.rb
 - lib/cabriolet/system/file_handle.rb