uniword 1.0.0 → 1.0.3

data/config/theme_mapping.yml

@@ -0,0 +1,447 @@
+---
+description: 'Uniword Theme/StyleSet to Microsoft Office mapping. Used for auto-transition:
+  detect MS theme -> apply Uniword equivalent.'
+themes:
+  meridian:
+    ms_name: Atlas
+    ms_thmx: Atlas.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: '454545'
+      lt1: FFFFFF
+      lt2: E0E0E0
+      accent1: F81B02
+      accent2: FC7715
+      accent3: AFBF41
+      accent4: 50C49F
+      accent5: 3B95C4
+      accent6: B560D4
+  emblem:
+    ms_name: Badge
+    ms_thmx: Badge.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: 2A1A00
+      lt1: FFFFFF
+      lt2: F3F3F2
+      accent1: F8B323
+      accent2: 656A59
+      accent3: 46B2B5
+      accent4: 8CAA7E
+      accent5: D36F68
+      accent6: '826276'
+  mosaic:
+    ms_name: Berlin
+    ms_thmx: Berlin.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: 9D360E
+      lt1: FFFFFF
+      lt2: E7E6E6
+      accent1: F09415
+      accent2: C1B56B
+      accent3: 4BAF73
+      accent4: 5AA6C0
+      accent5: D17DF9
+      accent6: FA7E5C
+  constellation:
+    ms_name: Celestial
+    ms_thmx: Celestial.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: 18276C
+      lt1: FFFFFF
+      lt2: EBEBEB
+      accent1: AC3EC1
+      accent2: 477BD1
+      accent3: 46B298
+      accent4: 90BA4C
+      accent5: DD9D31
+      accent6: E25247
+  harvest:
+    ms_name: Crop
+    ms_thmx: Crop.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: 191B0E
+      lt1: FFFFFF
+      lt2: EFEDE3
+      accent1: 8C8D86
+      accent2: E6C069
+      accent3: 897B61
+      accent4: 8DAB8E
+      accent5: 77A2BB
+      accent6: E28394
+  abyss:
+    ms_name: Depth
+    ms_thmx: Depth.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: 455F51
+      lt1: FFFFFF
+      lt2: 94D7E4
+      accent1: 41AEBD
+      accent2: 97E9D5
+      accent3: A2CF49
+      accent4: 608F3D
+      accent5: F4DE3A
+      accent6: FCB11C
+  ripple:
+    ms_name: Droplet
+    ms_thmx: Droplet.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: '355071'
+      lt1: FFFFFF
+      lt2: AABED7
+      accent1: 2FA3EE
+      accent2: 4BCAAD
+      accent3: 86C157
+      accent4: D99C3F
+      accent5: CE6633
+      accent6: A35DD1
+  prism:
+    ms_name: Facet
+    ms_thmx: Facet.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: 2C3C43
+      lt1: FFFFFF
+      lt2: EBEBEB
+      accent1: 90C226
+      accent2: 54A021
+      accent3: E6B91E
+      accent4: E76618
+      accent5: C42F1A
+      accent6: '918655'
+  plumage:
+    ms_name: Feathered
+    ms_thmx: Feathered.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: '121316'
+      lt1: FFFFFF
+      lt2: FEFCF7
+      accent1: '606372'
+      accent2: 79A8A4
+      accent3: B2AD8F
+      accent4: AD8082
+      accent5: DEC18C
+      accent6: 92A185
+  exhibit:
+    ms_name: Gallery
+    ms_thmx: Gallery.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: '454545'
+      lt1: FFFFFF
+      lt2: DFDBD5
+      accent1: B71E42
+      accent2: DE478E
+      accent3: BC72F0
+      accent4: 795FAF
+      accent5: 586EA6
+      accent6: 6892A0
+  bulletin:
+    ms_name: Headlines
+    ms_thmx: Headlines.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: 1D1A1D
+      lt1: FFFFFF
+      lt2: F5F5F5
+      accent1: 439EB7
+      accent2: E28B55
+      accent3: DCB64D
+      accent4: 4CA198
+      accent5: 835B82
+      accent6: '645135'
+  calculus:
+    ms_name: Integral
+    ms_thmx: Integral.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: 335B74
+      lt1: FFFFFF
+      lt2: DFE3E5
+      accent1: 1CADE4
+      accent2: 2683C6
+      accent3: 27CED7
+      accent4: 42BA97
+      accent5: 3E8853
+      accent6: 62A39F
+  plasma:
+    ms_name: Ion
+    ms_thmx: Ion.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: 1E5155
+      lt1: FFFFFF
+      lt2: EBEBEB
+      accent1: B01513
+      accent2: EA6312
+      accent3: E6B729
+      accent4: 6AAC90
+      accent5: 54849A
+      accent6: 9E5E9B
+  boardwalk:
+    ms_name: Ion Boardroom
+    ms_thmx: Ion Boardroom.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: 3B3059
+      lt1: FFFFFF
+      lt2: EBEBEB
+      accent1: B31166
+      accent2: E33D6F
+      accent3: E45F3C
+      accent4: E9943A
+      accent5: 9B6BF2
+      accent6: D53DD0
+  parkway:
+    ms_name: Madison
+    ms_thmx: Madison.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: 1F2D29
+      lt1: FFFFFF
+      lt2: C5FAEB
+      accent1: A1D68B
+      accent2: 5EC795
+      accent3: 4DADCF
+      accent4: CDB756
+      accent5: E29C36
+      accent6: 8EC0C1
+  spotlight:
+    ms_name: Main Event
+    ms_thmx: Main Event.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: '424242'
+      lt1: FFFFFF
+      lt2: C8C8C8
+      accent1: B80E0F
+      accent2: A6987D
+      accent3: 7F9A71
+      accent4: 64969F
+      accent5: 9B75B2
+      accent6: 80737A
+  weave:
+    ms_name: Mesh
+    ms_thmx: Mesh.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: 363D46
+      lt1: FFFFFF
+      lt2: EBEBEB
+      accent1: 6F6F6F
+      accent2: BFBFA5
+      accent3: DCD084
+      accent4: E7BF5F
+      accent5: E9A039
+      accent6: CF7133
+  workspace:
+    ms_name: Office Theme
+    ms_thmx: Office Theme.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: 0E2841
+      lt1: FFFFFF
+      lt2: E8E8E8
+      accent1: '156082'
+      accent2: E97132
+      accent3: 196B24
+      accent4: 0F9ED5
+      accent5: A02B93
+      accent6: 4EA72E
+  corporate:
+    ms_name: Office 2013-2022
+    ms_thmx: Office 2013 - 2022 Theme.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: 44546A
+      lt1: FFFFFF
+      lt2: E7E6E6
+      accent1: 4472C4
+      accent2: ED7D31
+      accent3: A5A5A5
+      accent4: FFC000
+      accent5: 5B9BD5
+      accent6: 70AD47
+  botanical:
+    ms_name: Organic
+    ms_thmx: Organic.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: '212121'
+      lt1: FFFFFF
+      lt2: DADADA
+      accent1: 83992A
+      accent2: 3C9770
+      accent3: 44709D
+      accent4: A23C33
+      accent5: D97828
+      accent6: DEB340
+  spectrum:
+    ms_name: Parallax
+    ms_thmx: Parallax.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: '212121'
+      lt1: FFFFFF
+      lt2: CDD0D1
+      accent1: 30ACEC
+      accent2: 80C34F
+      accent3: E29D3E
+      accent4: D64A3B
+      accent5: D64787
+      accent6: A666E1
+  archive:
+    ms_name: Parcel
+    ms_thmx: Parcel.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: 4A5356
+      lt1: FFFFFF
+      lt2: E8E3CE
+      accent1: F6A21D
+      accent2: 9BAFB5
+      accent3: C96731
+      accent4: 9CA383
+      accent5: 87795D
+      accent6: A0988C
+  memoir:
+    ms_name: Retrospect
+    ms_thmx: Retrospect.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: '637052'
+      lt1: FFFFFF
+      lt2: CCDDEA
+      accent1: E48312
+      accent2: BD582C
+      accent3: '865640'
+      accent4: 9B8357
+      accent5: C2BC80
+      accent6: 94A088
+  lather:
+    ms_name: Savon
+    ms_thmx: Savon.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: 1485A4
+      lt1: FFFFFF
+      lt2: E3DED1
+      accent1: 1CADE4
+      accent2: 2683C6
+      accent3: 27CED7
+      accent4: 42BA97
+      accent5: 3E8853
+      accent6: 62A39F
+  incision:
+    ms_name: Slice
+    ms_thmx: Slice.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: '146194'
+      lt1: FFFFFF
+      lt2: 76DBF4
+      accent1: 052F61
+      accent2: A50E82
+      accent3: 14967C
+      accent4: 6A9E1F
+      accent5: E87D37
+      accent6: C62324
+  contrail:
+    ms_name: Vapor Trail
+    ms_thmx: Vapor Trail.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: '454545'
+      lt1: FFFFFF
+      lt2: DADADA
+      accent1: DF2E28
+      accent2: FE801A
+      accent3: E9BF35
+      accent4: 81BB42
+      accent5: 32C7A9
+      accent6: 4A9BDC
+  vista:
+    ms_name: View
+    ms_thmx: View.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: 46464A
+      lt1: FFFFFF
+      lt2: D6D3CC
+      accent1: 6F6F74
+      accent2: 92A9B9
+      accent3: A7B789
+      accent4: B9A489
+      accent5: 8D6374
+      accent6: 9B7362
+  zephyr:
+    ms_name: Wisp
+    ms_thmx: Wisp.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: 766F54
+      lt1: FFFFFF
+      lt2: E3EACF
+      accent1: A53010
+      accent2: DE7E18
+      accent3: 9F8351
+      accent4: '728653'
+      accent5: 92AA4C
+      accent6: 6AAC91
+  letterpress:
+    ms_name: Wood Type
+    ms_thmx: Wood Type.thmx
+    color_fingerprint:
+      dk1: '000000'
+      dk2: '696464'
+      lt1: FFFFFF
+      lt2: E9E5DC
+      accent1: D34817
+      accent2: 9B2D1F
+      accent3: A28E6A
+      accent4: '956251'
+      accent5: '918485'
+      accent6: 855D5D
+stylesets:
+  signature:
+    ms_name: Distinctive
+    ms_dotx: Distinctive.dotx
+  refined:
+    ms_name: Elegant
+    ms_dotx: Elegant.dotx
+  ornate:
+    ms_name: Fancy
+    ms_dotx: Fancy.dotx
+  ceremonial:
+    ms_name: Formal
+    ms_dotx: Formal.dotx
+  scrollwork:
+    ms_name: Manuscript
+    ms_dotx: Manuscript.dotx
+  contemporary:
+    ms_name: Modern
+    ms_dotx: Modern.dotx
+  gazette:
+    ms_name: Newsprint
+    ms_dotx: Newsprint.dotx
+  outlook:
+    ms_name: Perspective
+    ms_dotx: Perspective.dotx
+  minimal:
+    ms_name: Simple
+    ms_dotx: Simple.dotx
+  wicker:
+    ms_name: Thatch
+    ms_dotx: Thatch.dotx
+  heritage:
+    ms_name: Traditional
+    ms_dotx: Traditional.dotx
+  classic:
+    ms_name: Word 2010
+    ms_dotx: Word 2010.dotx

data/config/transformation_rules.yml

@@ -0,0 +1,160 @@
+# Transformation Rules Configuration
+#
+# Defines transformation rules between format DOM models.
+# External configuration following "configuration over convention" principle.
+#
+# Rules are loaded at runtime and registered in TransformationRuleRegistry.
+# This allows modification without changing code (Open/Closed Principle).
+
+# Format-specific property mappings
+property_mappings:
+  # Paragraph properties that map directly between formats
+  paragraph_direct:
+    - alignment
+    - spacing_before
+    - spacing_after
+    - line_spacing
+    - line_rule
+    - indent_left
+    - indent_right
+    - indent_first_line
+    - keep_next
+    - keep_lines
+    - page_break_before
+    - outline_level
+
+  # Paragraph properties that need transformation
+  paragraph_transform:
+    docx_to_mhtml:
+      num_id: list_style_type  # DOCX numbering → CSS list style
+      ilvl: list_indent_level   # DOCX level → CSS indent
+    mhtml_to_docx:
+      list_style_type: num_id
+      list_indent_level: ilvl
+
+  # Run properties that map directly between formats
+  run_direct:
+    - bold
+    - italic
+    - underline
+    - strike
+    - double_strike
+    - size
+    - font
+    - color
+    - highlight
+    - vertical_align
+    - small_caps
+    - all_caps
+    - style
+
+  # Table properties that map directly
+  table_direct:
+    - width
+    - width_type
+    - alignment
+    - border_style
+    - borders
+    - cell_spacing
+    - cell_padding
+
+  # Image properties that map directly
+  image_direct:
+    - inline
+    - horizontal_alignment
+    - vertical_alignment
+    - text_wrapping
+    - width
+    - height
+    - alt_text
+    - title
+
+# Element type mappings
+element_mappings:
+  # 1-to-1 mappings
+  one_to_one:
+    - source: Paragraph
+      target: Paragraph
+      bidirectional: true
+
+    - source: Run
+      target: Run
+      bidirectional: true
+
+    - source: Table
+      target: Table
+      bidirectional: true
+      recursive: true  # Recursively transform rows and cells
+
+    - source: Image
+      target: Image
+      bidirectional: true
+
+    - source: Hyperlink
+      target: Hyperlink
+      bidirectional: true
+      recursive: true  # Recursively transform contained runs
+
+# Style name normalization rules
+style_name_rules:
+  # DOCX style IDs to display names
+  docx_to_display:
+    Heading1: "Heading 1"
+    Heading2: "Heading 2"
+    Heading3: "Heading 3"
+    Heading4: "Heading 4"
+    Heading5: "Heading 5"
+    Heading6: "Heading 6"
+    ListParagraph: "List Paragraph"
+    BodyText: "Body Text"
+
+  # Display names to DOCX style IDs
+  display_to_docx:
+    "Heading 1": Heading1
+    "Heading 2": Heading2
+    "Heading 3": Heading3
+    "Heading 4": Heading4
+    "Heading 5": Heading5
+    "Heading 6": Heading6
+    "List Paragraph": ListParagraph
+    "Body Text": BodyText
+
+# Format-specific defaults
+format_defaults:
+  docx:
+    # Default numbering for lists
+    default_bullet_num_id: 2
+    default_decimal_num_id: 1
+
+    # Default font
+    default_font: "Calibri"
+    default_font_size: 22  # 11pt in half-points
+
+    # Default margins (twips)
+    default_page_margins:
+      top: 1440     # 1 inch
+      bottom: 1440
+      left: 1440
+      right: 1440
+      header: 720   # 0.5 inch
+      footer: 720
+
+  mhtml:
+    # Default CSS classes for styles
+    heading1_class: "Heading1"
+    heading2_class: "Heading2"
+
+    # Default list styles
+    bullet_list_style: "disc"
+    decimal_list_style: "decimal"
+
+    # Default fonts
+    default_font: "Calibri"
+    default_font_size: "11pt"
+
+# Error messages (externalized for i18n)
+error_messages:
+  invalid_source: "Source must be a Document, got %{type}"
+  invalid_format: "Format must be :docx or :mhtml, got %{format}"
+  unsupported_element: "No transformation rule for %{element_type}"
+  transformation_failed: "Transformation failed: %{reason}"

data/config/validation_rules.yml

@@ -0,0 +1,60 @@
+# Document Validation Configuration
+#
+# Defines rules and settings for the 7-layer document validation system.
+# Each layer validates one specific aspect of document integrity (MECE).
+
+document_validation:
+  # General settings
+  fail_fast: true              # Stop validation on first critical error
+  max_file_size: 104857600     # 100MB maximum file size
+
+  # Layer 1: File Structure Validation
+  file_structure:
+    enabled: true
+    check_extension: true
+    check_size: true
+    allowed_extensions:
+      - '.docx'
+      - '.doc'
+
+  # Layer 2: ZIP Integrity Validation
+  zip_integrity:
+    enabled: true
+    check_entries: true         # Verify required entries exist
+    check_corruption: true      # Test each entry for corruption
+    verify_compression: true    # Validate compression method
+
+  # Layer 3: OOXML Part Validation
+  ooxml_parts:
+    enabled: true
+    require_content_types: true       # [Content_Types].xml must exist
+    require_document: true            # word/document.xml must exist
+    require_relationships: true       # _rels/.rels must exist
+    warn_missing_optional: true       # Warn about missing optional parts
+
+  # Layer 4: XML Schema Validation
+  xml_schema:
+    enabled: true
+    strict_parsing: true        # Use strict XML parsing
+    check_encoding: true        # Validate XML encoding
+    validate_namespaces: true   # Check namespace declarations
+
+  # Layer 5: Relationship Validation
+  relationships:
+    enabled: true
+    check_targets_exist: true   # Verify relationship targets exist
+    check_circular_refs: false  # Check for circular references (expensive)
+    validate_types: true        # Validate relationship type URIs
+
+  # Layer 6: Content Type Validation
+  content_types:
+    enabled: true
+    check_consistency: true     # Verify content types are consistent
+    validate_extensions: true   # Check file extensions match declarations
+
+  # Layer 7: Document Semantics Validation
+  document_semantics:
+    enabled: true
+    check_required_elements: true   # Verify required elements (body, etc.)
+    validate_structure: true        # Check document hierarchy
+    check_style_references: true    # Validate style references (future)

data/config/warning_rules.yml

@@ -0,0 +1,57 @@
+# Warning System Configuration
+#
+# Defines rules for tracking unsupported elements and features during
+# document processing. Helps users understand what may be lost in round-trip.
+
+warning_system:
+  enabled: true
+  log_warnings: false      # Set to true to log warnings during processing
+  log_level: :warn         # Log level (:info, :warn, :error)
+
+  # Critical elements (data-bearing) - severity: error
+  # These elements contain important data that will be lost
+  critical_elements:
+    - chart              # Charts - data visualization
+    - smartArt           # SmartArt diagrams
+    - sdt                # Content controls - user data
+    - customXml          # Custom XML - data binding
+    - contentPart        # Content parts
+    - control            # ActiveX controls
+
+  # Warning elements (important but not critical) - severity: warning
+  # These elements affect formatting/structure but not core data
+  warning_elements:
+    - drawingML          # Complex drawings
+    - vmlDrawing         # Legacy VML drawings
+    - fldSimple          # Simple fields
+    - altChunk           # Alternative content chunks
+    - subDoc             # Subdocuments
+
+  # Element-specific suggestions for users
+  element_suggestions:
+    chart: "Chart elements are not yet supported. The chart will be preserved as-is but cannot be edited. Consider using image exports for charts. Support planned for v6.1."
+
+    smartArt: "SmartArt diagrams are not yet supported. Diagram will be preserved but cannot be modified. Consider converting to regular shapes. Support planned for v6.2."
+
+    sdt: "Content controls are not yet supported. Controls will be preserved but values cannot be updated programmatically. Support planned for v6.1."
+
+    customXml: "Custom XML data binding is not yet supported. XML data will be preserved but cannot be accessed or modified. Support planned for v6.3."
+
+    drawingML: "Complex DrawingML graphics may not be fully supported. Basic shapes work, but advanced features may be lost."
+
+    vmlDrawing: "Legacy VML drawings have limited support. Consider updating to modern DrawingML format."
+
+    fldSimple: "Some field types are not yet supported. Field will be preserved but may not update correctly."
+
+    control: "ActiveX controls are not supported. Controls will be preserved but not functional."
+
+    altChunk: "Alternative content chunks are not supported. Content may be lost."
+
+    subDoc: "Subdocuments are not supported. Consider consolidating into single document."
+
+  # Reporting options
+  reporting:
+    group_by_element: true      # Group warnings by element type
+    include_counts: true        # Include occurrence counts
+    include_suggestions: true   # Include suggestions in report
+    max_warnings: 100           # Maximum warnings to collect (prevent memory issues)