uniword 1.0.0

data/lib/uniword/ooxml/dotx_package.rb

@@ -0,0 +1,247 @@
+# frozen_string_literal: true
+
+require 'lutaml/model'
+# Theme, StylesConfiguration, NumberingConfiguration, Document are autoloaded via lib/uniword.rb
+
+module Uniword
+  module Ooxml
+    # DOTX/DOTM Package - Word Template formats
+    #
+    # Represents .dotx (template) and .dotm (macro-enabled template) files.
+    # Structure is identical to DOCX but used as document templates.
+    # Templates often contain StyleSets and building blocks.
+    #
+    # This is the CORRECT OOP approach:
+    # - ONE model class for the container
+    # - Each XML part is a proper model attribute
+    # - No serializer/deserializer anti-pattern
+    #
+    # @example Load template
+    #   package = DotxPackage.from_file('template.dotx')
+    #   package.core_properties.title = 'New Template Title'
+    #   package.to_file('output.dotx')
+    class DotxPackage < Lutaml::Model::Serializable
+      # Core document metadata
+      attribute :core_properties, CoreProperties
+
+      # Extended application properties
+      attribute :app_properties, AppProperties
+
+      # Document theme
+      attribute :theme, Uniword::Drawingml::Theme
+
+      # Document styles configuration
+      attribute :styles_configuration, Uniword::Wordprocessingml::StylesConfiguration
+
+      # Document numbering configuration
+      attribute :numbering_configuration, Uniword::Wordprocessingml::NumberingConfiguration
+
+      # TODO: v2.0: Add proper lutaml-model attributes for:
+      # - Document (word/document.xml)
+      # - FontTable (word/fontTable.xml)
+      # - Settings (word/settings.xml)
+      # - WebSettings (word/webSettings.xml)
+      # - Relationships (.rels files)
+      # - ContentTypes ([Content_Types].xml)
+      #
+      # NO RAW XML STORAGE ALLOWED
+
+      # Load DOTX/DOTM package from file
+      #
+      # @param path [String] Path to .dotx or .dotm file
+      # @return [Document] Loaded document (Generated::Wordprocessingml::DocumentRoot)
+      def self.from_file(path)
+        # Extract ZIP content
+        extractor = Infrastructure::ZipExtractor.new
+        zip_content = extractor.extract(path)
+
+        # Parse package with properties and theme
+        package = from_zip_content(zip_content)
+
+        # Parse main document XML using generated classes
+        # Document is aliased in lib/uniword.rb to Generated::Wordprocessingml::DocumentRoot
+        document = if package.raw_document_xml
+                     Uniword::Wordprocessingml::DocumentRoot.from_xml(package.raw_document_xml)
+                   else
+                     Uniword::Wordprocessingml::DocumentRoot.new
+                   end
+
+        # Transfer properties from package to document
+        document.core_properties = package.core_properties if package.core_properties
+        document.app_properties = package.app_properties if package.app_properties
+        document.theme = package.theme if package.theme
+
+        # Transfer model-based configurations
+        document.styles_configuration = package.styles_configuration if package.styles_configuration
+        if package.numbering_configuration
+          document.numbering_configuration = package.numbering_configuration
+        end
+
+        document
+      end
+
+      # Create package from extracted ZIP content
+      #
+      # @param zip_content [Hash] Extracted ZIP files
+      # @return [DotxPackage] Package object
+      def self.from_zip_content(zip_content)
+        package = new
+
+        # Parse lutaml-model files
+        if zip_content['docProps/core.xml']
+          package.core_properties = CoreProperties.from_xml(zip_content['docProps/core.xml'])
+        end
+
+        if zip_content['docProps/app.xml']
+          package.app_properties = AppProperties.from_xml(zip_content['docProps/app.xml'])
+        end
+
+        if zip_content['word/theme/theme1.xml']
+          package.theme = Uniword::Drawingml::Theme.from_xml(zip_content['word/theme/theme1.xml'])
+        end
+
+        # Parse styles and numbering as models
+        if zip_content['word/styles.xml']
+          package.styles_configuration = Uniword::Wordprocessingml::StylesConfiguration.from_xml(zip_content['word/styles.xml'])
+        end
+
+        if zip_content['word/numbering.xml']
+          package.numbering_configuration = Uniword::Wordprocessingml::NumberingConfiguration.from_xml(zip_content['word/numbering.xml'])
+        end
+
+        # Store raw document XML (will be parsed by DotxHandler)
+        if zip_content['word/document.xml']
+          package.raw_document_xml = zip_content['word/document.xml']
+        end
+
+        # TODO: v2.0: Parse fontTable.xml, settings.xml, webSettings.xml
+        # TODO v2.0: Parse relationships and content types
+
+        package
+      end
+
+      # Access raw document XML (for compatibility)
+      attr_accessor :raw_document_xml
+
+      # Get supported file extensions
+      #
+      # @return [Array<String>] Array of supported extensions
+      def self.supported_extensions
+        ['.dotx', '.dotm']
+      end
+
+      # Save document to file
+      #
+      # @param document [Document] The document to save (Generated::Wordprocessingml::DocumentRoot)
+      # @param path [String] Output path
+      def self.to_file(document, path)
+        # Create package
+        package = new
+
+        # Transfer properties to package
+        package.core_properties = document.core_properties || CoreProperties.new
+        package.app_properties = document.app_properties || AppProperties.new
+        package.theme = document.theme
+
+        # Transfer model-based configurations
+        package.styles_configuration = document.styles_configuration
+        package.numbering_configuration = document.numbering_configuration
+
+        # Serialize main document
+        package.raw_document_xml = document.to_xml(encoding: 'UTF-8')
+
+        # Generate ZIP content
+        zip_content = package.to_zip_content
+
+        # Add required OOXML infrastructure files
+        add_required_files(zip_content)
+
+        # Package and save
+        packager = Infrastructure::ZipPackager.new
+        packager.package(zip_content, path)
+      end
+
+      # Save package to file
+      #
+      # @param path [String] Output path
+      def to_file(path)
+        zip_content = to_zip_content
+
+        packager = Infrastructure::ZipPackager.new
+        packager.package(zip_content, path)
+      end
+
+      # Generate ZIP content hash
+      #
+      # @return [Hash] File paths => content
+      def to_zip_content
+        content = {}
+
+        # Serialize lutaml-model files with prefix: false
+        if core_properties
+          content['docProps/core.xml'] =
+            core_properties.to_xml(encoding: 'UTF-8', prefix: false)
+        end
+        if app_properties
+          content['docProps/app.xml'] =
+            app_properties.to_xml(encoding: 'UTF-8', prefix: false)
+        end
+
+        # Theme serialization (no raw XML fallback)
+        content['word/theme/theme1.xml'] = theme.to_xml(encoding: 'UTF-8') if theme
+
+        # Serialize model-based configurations
+        if styles_configuration
+          content['word/styles.xml'] =
+            styles_configuration.to_xml(encoding: 'UTF-8')
+        end
+
+        if numbering_configuration
+          content['word/numbering.xml'] =
+            numbering_configuration.to_xml(encoding: 'UTF-8')
+        end
+
+        # Serialize main document (word/document.xml)
+        if @document
+          content['word/document.xml'] = @document.to_xml(encoding: 'UTF-8')
+        elsif @raw_document_xml
+          # Fallback to raw XML if document wasn't parsed yet
+          content['word/document.xml'] = @raw_document_xml
+        end
+
+        # TODO: v2.0: Serialize fontTable.xml, settings.xml, webSettings.xml
+        # TODO v2.0: Serialize relationships and content types
+
+        content
+      end
+
+      # Add required OOXML files for a valid DOTX/DOTM package
+      #
+      # @param zip_content [Hash] The ZIP content hash
+      # @return [void]
+      def self.add_required_files(zip_content)
+        # Add [Content_Types].xml if not present
+        unless zip_content['[Content_Types].xml']
+          zip_content['[Content_Types].xml'] =
+            Uniword::ContentTypes.generate.to_xml(declaration: true)
+        end
+
+        # Add _rels/.rels if not present
+        unless zip_content['_rels/.rels']
+          zip_content['_rels/.rels'] =
+            Uniword::Ooxml::Relationships::PackageRelationships.generate_package_rels.to_xml(declaration: true)
+        end
+
+        # Add word/_rels/document.xml.rels if not present
+        return if zip_content['word/_rels/document.xml.rels']
+
+        zip_content['word/_rels/document.xml.rels'] =
+          Uniword::Ooxml::Relationships::Relationships.generate_document_rels.to_xml(
+            declaration: true
+          )
+      end
+
+      private_class_method :add_required_files
+    end
+  end
+end

data/lib/uniword/ooxml/namespaces.rb

@@ -0,0 +1,363 @@
+# frozen_string_literal: true
+
+require 'lutaml/model'
+
+module Uniword
+  module Ooxml
+    module Namespaces
+      # WordProcessingML Main namespace
+      # Used for all core Word document elements (paragraphs, runs, tables, etc.)
+      class WordProcessingML < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/wordprocessingml/2006/main'
+        prefix_default 'w'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Office Math Markup Language namespace
+      # Used for math equations (CRITICAL for ISO documents)
+      class MathML < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/officeDocument/2006/math'
+        prefix_default 'm'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # DrawingML WordProcessing Drawing namespace
+      # Used for inline and anchored images
+      class WordProcessingDrawing < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing'
+        prefix_default 'wp'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # DrawingML Chart namespace
+      class Chart < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/drawingml/2006/chart'
+        prefix_default 'c'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # DrawingML Diagram (SmartArt) namespace
+      class Diagram < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/drawingml/2006/diagram'
+        prefix_default 'dgm'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # DrawingML Picture namespace
+      class Picture < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/drawingml/2006/picture'
+        prefix_default 'pic'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # DrawingML WordProcessing Drawing namespace
+      class WordProcessingDrawing < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing'
+        prefix_default 'wp'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # DrawingML Main namespace
+      # Used for graphics and shapes
+      # NOTE: DrawingML attributes are UNQUALIFIED (no prefix)
+      class DrawingML < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/drawingml/2006/main'
+        prefix_default 'a'
+        element_form_default :qualified
+        attribute_form_default :unqualified
+      end
+
+      # Relationships namespace
+      # Used for document relationships
+      class Relationships < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/officeDocument/2006/relationships'
+        prefix_default 'r'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # VML namespace (legacy)
+      # Used for backward compatibility with older Word versions
+      class VML < Lutaml::Xml::Namespace
+        uri 'urn:schemas-microsoft-com:vml'
+        prefix_default 'v'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # XML namespace for xml:space attribute
+      class XML < Lutaml::Xml::Namespace
+        uri 'http://www.w3.org/XML/1998/namespace'
+        prefix_default 'xml'
+        attribute_form_default :unqualified
+      end
+
+      # Core Properties namespace (docProps/core.xml)
+      class CoreProperties < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/package/2006/metadata/core-properties'
+        prefix_default 'cp'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Content Types namespace ([Content_Types].xml)
+      class ContentTypes < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/package/2006/content-types'
+        prefix_default 'ct'
+        element_form_default :qualified
+        attribute_form_default :unqualified
+      end
+
+      # Dublin Core Elements namespace
+      class DublinCore < Lutaml::Xml::Namespace
+        uri 'http://purl.org/dc/elements/1.1/'
+        prefix_default 'dc'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Dublin Core Terms namespace
+      class DublinCoreTerms < Lutaml::Xml::Namespace
+        uri 'http://purl.org/dc/terms/'
+        prefix_default 'dcterms'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # XML Schema Instance namespace
+      class XmlSchemaInstance < Lutaml::Xml::Namespace
+        uri 'http://www.w3.org/2001/XMLSchema-instance'
+        prefix_default 'xsi'
+        attribute_form_default :unqualified
+      end
+
+      # Extended Properties namespace (docProps/app.xml)
+      class ExtendedProperties < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/officeDocument/2006/extended-properties'
+        prefix_default 'app'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Document Variables namespace (docProps/docVars.xml)
+      class DocumentVariables < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/officeDocument/2006/docVars'
+        prefix_default 'dv'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Glossary namespace (docProps/glossary.xml)
+      class Glossary < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/officeDocument/2006/glossary'
+        prefix_default 'g'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Package-level Relationships namespace (_rels/.rels)
+      class PackageRelationships < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/package/2006/relationships'
+        prefix_default 'rel'
+        element_form_default :qualified
+        attribute_form_default :unqualified
+      end
+
+      # Document-level Relationships namespace
+      class Relationships < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/officeDocument/2006/relationships'
+        prefix_default 'r'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Shared Types namespace
+      class SharedTypes < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes'
+        prefix_default 'st'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Variant Types namespace
+      class VariantTypes < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes'
+        prefix_default 'vt'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Bibliography namespace
+      class Bibliography < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/officeDocument/2006/bibliography'
+        prefix_default 'b'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # SpreadsheetML namespace
+      class SpreadsheetML < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/spreadsheetml/2006/main'
+        prefix_default 'xls'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # PresentationalML namespace
+      class PresentationalML < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/presentationalml/2006/main'
+        prefix_default 'p'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Word 2010 namespace
+      class Word2010 < Lutaml::Xml::Namespace
+        uri 'http://schemas.microsoft.com/office/word/2010/wordml'
+        prefix_default 'w14'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Word 2012 namespace
+      class Word2012 < Lutaml::Xml::Namespace
+        uri 'http://schemas.microsoft.com/office/word/2012/wordml'
+        prefix_default 'w15'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Word 2015 namespace
+      class Word2015 < Lutaml::Xml::Namespace
+        uri 'http://schemas.microsoft.com/office/word/2015/wordml'
+        prefix_default 'w16'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Word 2016 namespace
+      class Word2016 < Lutaml::Xml::Namespace
+        uri 'http://schemas.microsoft.com/office/word/2016/wordml'
+        prefix_default 'w16'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Word 2016 CID namespace (citation identifiers)
+      class Word2016Cid < Lutaml::Xml::Namespace
+        uri 'http://schemas.microsoft.com/office/word/2016/wordml/cid'
+        prefix_default 'w16cid'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Custom XML namespace
+      class CustomXml < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/officeDocument/2006/customXml'
+        prefix_default 'cxml'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Custom XML namespace
+      class CustomXml < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/officeDocument/2006/customXml'
+        prefix_default 'cxml'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Office namespace
+      class Office < Lutaml::Xml::Namespace
+        uri 'urn:schemas-microsoft-com:office:office'
+        prefix_default 'o'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # VML namespace
+      class Vml < Lutaml::Xml::Namespace
+        uri 'urn:schemas-microsoft-com:vml'
+        prefix_default 'v'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Markup Compatibility namespace
+      # Used for forward compatibility (Ignorable attribute)
+      class MarkupCompatibility < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/markup-compatibility/2006'
+        prefix_default 'mc'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # ThemeML namespace (Office 2013+)
+      # Used for theme family metadata in theme extensions
+      class ThemeML < Lutaml::Xml::Namespace
+        uri 'http://schemas.microsoft.com/office/thememl/2012/main'
+        prefix_default 'thm15'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # WordprocessingShape namespace
+      # Used for VML-compatible shapes in DrawingML
+      class WordprocessingShape < Lutaml::Xml::Namespace
+        uri 'http://schemas.microsoft.com/office/word/2010/wordprocessingShape'
+        prefix_default 'wps'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # WordprocessingGroup namespace
+      # Used for shape groups in DrawingML
+      class WordprocessingGroup < Lutaml::Xml::Namespace
+        uri 'http://schemas.microsoft.com/office/word/2010/wordprocessingGroup'
+        prefix_default 'wpg'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # VML Word namespace
+      # Used for VML elements within Word documents (borders, etc.)
+      class VmlWord < Lutaml::Xml::Namespace
+        uri 'urn:schemas-microsoft-com:office:word'
+        prefix_default 'w'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Custom Properties namespace (docProps/custom.xml)
+      class CustomProperties < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/officeDocument/2006/custom-properties'
+        prefix_default 'custprops'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Additional Characteristics namespace
+      class Characteristics < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/officeDocument/2006/characteristics'
+        prefix_default 'ac'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+
+      # Schema Library namespace
+      class SchemaLibrary < Lutaml::Xml::Namespace
+        uri 'http://schemas.openxmlformats.org/schemaLibrary/2006/main'
+        prefix_default 'sl'
+        element_form_default :qualified
+        attribute_form_default :qualified
+      end
+    end
+  end
+end