# Language - Language class
# Extended 2026-01-22: Added text_content attribute for language-tagged text support
# Supports migration of language-specific text slots (fr, de, en, nl) per slot_fixes.yaml
id: https://nde.nl/ontology/hc/class/Language
name: Language
prefixes:
  linkml: https://w3id.org/linkml/
  hc: https://nde.nl/ontology/hc/
  dct: http://purl.org/dc/terms/
  rdf: http://www.w3.org/1999/02/22-rdf-syntax-ns#
imports:
  - linkml:types
  - ../slots/has_or_had_code
classes:
  Language:
    class_uri: dct:LinguisticSystem
    description: |
      A language with ISO codes and optional text content.
      
      **Purpose**:
      Represents a language entity that can identify the language of text content.
      Used for language-tagged text where the language code and content are bundled together.
      
      **Use Cases**:
      1. Language identification only (just codes, no content)
      2. Language-tagged text (codes + text_content for multilingual data)
      
      **Migration Support**:
      This class supports migration from language-specific text slots (fr, de, en, nl)
      to a unified `has_or_had_language` + `Language` pattern per slot_fixes.yaml.
      
      **Ontological Alignment**:
      - **Primary**: `dct:LinguisticSystem` - Dublin Core linguistic system
      - **Close**: `schema:Language` - Schema.org language
      
    exact_mappings:
      - dct:LinguisticSystem
    close_mappings:
      - schema:Language
    slots:
      - has_or_had_code
    attributes:
      language_name:
        range: string
        description: |
          Human-readable name of the language (e.g., "English", "Dutch", "French").
          Parsed from raw string, not authoritative. Use ISO codes for formal identification.
      iso_639_1:
        range: string
        description: ISO 639-1 two-letter code (e.g., "fr", "en", "de", "nl")
        pattern: "^[a-z]{2}$"
      iso_639_3:
        range: string
        description: ISO 639-3 three-letter code (e.g., "fra", "eng", "deu", "nld")
        pattern: "^[a-z]{3}$"
      text_content:
        range: string
        description: |
          Text content in this language.
          
          Used when bundling language identification with the actual text content.
          This enables migration from language-specific slots (fr, de, en, nl) to
          a unified Language-tagged pattern.
          
          **Example**:
          ```yaml
          has_or_had_language:
            - iso_639_1: "fr"
              language_name: "French"
              text_content: "archives universitaires"
            - iso_639_1: "en"
              language_name: "English"
              text_content: "university archives"
          ```
    examples:
      - value: |
          iso_639_1: "fr"
          language_name: "French"
          text_content: "archives universitaires"
        description: French language-tagged text for multilingual label
      - value: |
          iso_639_1: "en"
          language_name: "English"
        description: English language identifier (without text content)
      - value: |
          iso_639_1: "nl"
          language_name: "Dutch"
          text_content: "universitair archief"
        description: Dutch language-tagged text