Class: Llmsherpa::Section

Inherits:
Block
  • Object
show all
Defined in:
lib/llmsherpa/blocks.rb

Overview

A section is a block of text. It can have children such as paragraphs, lists, and tables. A section has tag ‘header’.

Instance Attribute Summary collapse

Attributes inherited from Block

#bbox, #block_idx, #block_json, #children, #left, #level, #page_idx, #parent, #sentences, #tag, #top

Instance Method Summary collapse

Methods inherited from Block

#add_child, #chunks, #iter_children, #paragraphs, #parent_chain, #parent_text, #sections, #tables, #to_context_text

Constructor Details

#initialize(section_json) ⇒ Section

Returns a new instance of Section.



152
153
154
155
 
# File 'lib/llmsherpa/blocks.rb', line 152

def initialize(section_json)
  super(section_json)
  @title = @sentences.join("\n")
end

Instance Attribute Details

#title ⇒ Object

Returns the value of attribute title.



150
151
152
 
# File 'lib/llmsherpa/blocks.rb', line 150

def title
  @title
end

Instance Method Details

#to_html(include_children = false, recurse = false) ⇒ Object 



167
168
169
170
171
172
173
174
175
 
# File 'lib/llmsherpa/blocks.rb', line 167

def to_html(include_children = false, recurse = false)
  html_str = "<h#{@level + 1}>#{@title}</h#{@level + 1}>"
  if include_children
    @children.each do |child|
      html_str += child.to_html(include_children: recurse, recurse: recurse)
    end
  end
  html_str
end

#to_text(include_children = false, recurse = false) ⇒ Object 



157
158
159
160
161
162
163
164
165
 
# File 'lib/llmsherpa/blocks.rb', line 157

def to_text(include_children = false, recurse = false)
  text = @title
  if include_children
    @children.each do |child|
      text += "\n#{child.to_text(include_children: recurse, recurse: recurse)}"
    end
  end
  text
end