# Layout Rules Instance - Section 1 of Convention v1.4.3
# Captures all layout correction rules for transcribed documents

text_region_types:
  - name: PARAGRAPH
    description: >-
      The running text within the type area. This is the main body text
      of the document.
    ordering_rules: >-
      Text lines within paragraphs should be ordered top-to-bottom based
      on baseline coordinates.

  - name: PAGE_NUMBER
    description: >-
      A number—either in digits or written out—, letter or combination of
      both indicating the order of a page or folium in a book or other type
      of writing.
    ordering_rules: >-
      Page numbers are typically located at top or bottom margins and should
      be identified as separate regions.

  - name: HEADER
    description: >-
      A general text at the top margin of a page or paragraph which can be
      assigned to multiple sections within a source.
    ordering_rules: >-
      Headers should be ordered before main body text when processing pages.

  - name: FOOTER
    description: >-
      A general text at the lower margin of a page or paragraph which can be
      assigned to multiple sections within a source.
    ordering_rules: >-
      Footers should be ordered after main body text when processing pages.

  - name: HEADING
    description: >-
      A title or index designation which only applies to a single section of
      a source, i.e., the paragraphs written directly underneath it.
    ordering_rules: >-
      Headings should be ordered immediately before the paragraphs they describe.

  - name: FOOTNOTE
    description: >-
      Indexed annotations and references which occur underneath the running text
      across multiple pages in a successive order.
    ordering_rules: >-
      Footnotes should be ordered by their index number/symbol and associated
      with their reference in main text.

  - name: TABLE
    description: >-
      Indices in which the layout of the text is more important than the syntax.
    ordering_rules: >-
      Table cells should preserve their row-column structure. Cell content
      should be ordered left-to-right, top-to-bottom.

  - name: MARGINALIA
    description: >-
      Notes, scribbles, and commentary in the margins of pages.
    ordering_rules: >-
      Marginalia should be associated with adjacent main text but marked as
      separate regions.

  - name: CAPTION
    description: >-
      Description of an image which is located approximate—often directly
      underneath—it.
    ordering_rules: >-
      Captions should be associated with their images and ordered after the
      image they describe.

  - name: COLOPHON
    description: >-
      A piece of text or section of a page in which the author or scribes of
      a textual source are mentioned or in which the creation, place of writing,
      or the delivery of the source are specified.
    ordering_rules: >-
      Colophons typically appear at the end of documents or sections.

baseline_rules:
  - rule_id: BL001
    description: Remove transcribed text on pages in the background
    applies_to: >-
      Text regions that do not belong to the current page being transcribed
    action: REMOVE

  - rule_id: BL002
    description: Shorten baselines extending to decorative textual elements
    applies_to: >-
      Baselines that incorrectly extend into decorative elements such as
      illuminated letters, flourishes, or ornamental borders
    action: SHORTEN

  - rule_id: BL003
    description: Add space dividers for unusually long distances between words
    applies_to: >-
      Distances between words which are longer than usual considering the
      handwriting style
    action: ADJUST

  - rule_id: BL004
    description: Split baseline when word distance exceeds half baseline length
    applies_to: >-
      When the distance between words extends beyond half of the total length
      of the baseline
    action: SPLIT

  - rule_id: BL005
    description: Connect inserted texts to main baseline
    applies_to: >-
      Inserted texts between baselines need to be connected to the main baseline
      of which they are part. This also applies to Lombardic capitals.
    action: MERGE

  - rule_id: BL006
    description: Cut text region in half when lines cross columns
    applies_to: >-
      Text lines that cross columns or text regions that extend too far
    action: SPLIT

text_line_ordering:
  method: coordinate-based
  applies_to_region: PARAGRAPH
  description: >-
    In Transkribus Expert Client: Click on 'Layout', select the text region
    (or 'Page' to order text regions), then click on 'Assign Child Shapes'.
    Text lines will be ordered based on their coordinates.