Enhancement of handling content, including lists in cells (9cfb8d0d) · Commits · Centre for Testing and Interoperability / Markdown specifications development / Specification tools

grid_table_filter.rb

+34 −34

Original line number	Diff line number	Diff line
		@@ -40,6 +40,8 @@ module Banzai
		GRID_TABLE_BODY_SEPARATOR = /[^\n]\+([:-]+\+)+[^\n]$/
		GRID_TABLE_BODY_SEPARATOR_LINE = /^[-:]+$/

		NEXT_ELEMENT_LIST_MARK = "∆"

		class Cell
		attr_accessor :content, :rowspan, :colspan, :colspan_adjusted, :alignment, :position_start, :position, :list_flag

		@@ -113,34 +115,40 @@ module Banzai
		end
		# Helper method to handle content in cells
		def handling_content(cell, content)
		_c = content.strip
		if cell.content.nil?
		cell.rowspan += 1
		cell.colspan += 1
		if content.strip.start_with?("- ") # List
		if _c.start_with?("- ") # List
		cell.list_flag = true
		cell.content = "#{content.strip}\n"
		_c = _c.gsub(/\\\s*$/, '\n')
		cell.content = "#{_c}#{NEXT_ELEMENT_LIST_MARK}" # Add list element end mark to know when the list element ends
		elsif cell.list_flag && !content.strip.empty?
		cell.content += "#{content.strip}\n"
		elsif content.strip == ""
		cell.list_flag = false
		_c = _c.gsub(/\\\s*$/, '\n')
		cell.content = "#{_c}#{NEXT_ELEMENT_LIST_MARK}" #add the list element end mark
		elsif _c.empty?
		cell.content = "\n"
		else
		cell.content = content.strip.gsub(/\\\s*$/, "\n")
		cell.content = _c.gsub(/\\\s*$/, "\n")
		end
		elsif content.strip.start_with?("- ")
		elsif _c.start_with?("- ")
		cell.content += "\n" unless cell.list_flag

		cell.list_flag = true
		cell.content += "#{content.strip}\n"
		elsif cell.list_flag && !content.strip.empty?
		cell.content = cell.content.strip.chomp("\n")
		cell.content += " #{content.strip}\n"
		elsif content.strip.empty?
		_c = _c.gsub(/\\\s*$/, '\n')
		cell.content += "#{_c}#{NEXT_ELEMENT_LIST_MARK}"
		elsif cell.list_flag && !_c.empty?
		cell.content = cell.content.strip.chomp("#{NEXT_ELEMENT_LIST_MARK}")
		_c = _c.gsub(/\\\s*$/, '\n')
		cell.content += " #{_c}#{NEXT_ELEMENT_LIST_MARK}"
		elsif _c.empty?
		if cell.list_flag
		cell.list_flag = false
		cell.content += "\n\n"
		end
		cell.content += cell.content.end_with?("\n") ? "" : "\n"
		else
		content = content.strip.gsub(/\\\s*$/, "\n")
		cell.content += " #{content}"
		_c = _c.gsub(/\\\s*$/, "\n")
		cell.content += " #{_c}"
		end

		cell
		@@ -188,7 +196,7 @@ module Banzai
		def parse_pandoc_table_with_spans(pandoc_table)

		# Split the input into lines
		lines = pandoc_table.strip.split("\n").map(&:strip)
		lines = pandoc_table.rstrip.split("\n").map(&:rstrip)

		# Retrieve separator indices
		separator_indices = lines.each_index.select { \|i\| separator?(lines[i]) }
		@@ -272,6 +280,7 @@ module Banzai
		next if row_lines.empty?

		row_lines.each do \|line\|
		line = line.rstrip
		# First line (normally a separator) of each block
		if separator?(line) && !in_data_row
		in_data_row = true
		@@ -409,20 +418,11 @@ module Banzai
		row.each do \|cell\|
		next if cell.content.nil?

		delimters = ['**', '__']
		delimters.each do \|bold_chars\|
		while cell.content.include?(bold_chars)
		cell.content = cell.content.sub(bold_chars, "<strong>")
		.sub(bold_chars, "</strong>")
		end
		end
		cell.content = cell.content.gsub(/</, "<")

		while cell.content.include?("_") && cell.content.exclude?("\\_")
		cell.content = cell.content.rstrip.sub("_", "<i>").sub("_", "</i>")
		end

		cell.content = cell.content.rstrip.sub("\\_", "_") while cell.content.include?("\\_")
		cell.content = cell.content.gsub(/(?<espace>^\|\s)(?<bold>\\\|__)(?<text>.+?)\g<bold>(?!\w)/, "\\k<espace><strong>\\k<text></strong>")

		cell.content = cell.content.gsub(/(?<espace>^\|\s)(?<italic>\*\|_)(?<text>.+?)\g<italic>(?!\w)/, "\\k<espace><i>\\k<text></i>")
		# Convert newlines to HTML breaks
		cell.content = cell.content&.gsub("\n", "<br />")
		end
		@@ -483,14 +483,14 @@ module Banzai
		next if cell.rowspan == 0 \|\| cell.colspan == 0

		# Prepare content, in case there's a list
		matches = cell.content&.scan(%r{\s([-+]\|\d+\.)\s+([^<]+?)(?=<br />\|$)})
		matches = cell.content&.scan(/\s([-+]\|\d+\.)\s+([^#{NEXT_ELEMENT_LIST_MARK}]+?)#{NEXT_ELEMENT_LIST_MARK}\n?/)
		if matches
		list = "<ul>"
		matches.each do \|match\|
		list += "<li>#{match[1]}</li>"
		end
		list += "</ul>"
		cell.content = cell.content.gsub(%r{(\s([-+]\|\d+\.)\s+[^<]+?<br />)+}, list)
		cell.content = cell.content.gsub(/(\s([-+]\|\d+\.)\s+([^#{NEXT_ELEMENT_LIST_MARK}]+#{NEXT_ELEMENT_LIST_MARK}\n?))+/, list)
		# Enforce left alignment if cell contains a list
		cell.alignment = 'align="left"'
		end
		@@ -510,14 +510,14 @@ module Banzai
		row.each do \|cell\|
		next if cell.rowspan == 0 \|\| cell.colspan == 0

		matches = cell.content&.scan(%r{\s([-+]\|\d+\.)\s+([^<]+?)(?=<br />\|$)})
		matches = cell.content&.scan(/\s([-+]\|\d+\.)\s+([^#{NEXT_ELEMENT_LIST_MARK}]+?)#{NEXT_ELEMENT_LIST_MARK}\n?/)
		if matches
		list = "<ul>"
		matches.each do \|match\|
		list += "<li>#{match[1]}</li>"
		end
		list += "</ul>"
		cell.content = cell.content.gsub(%r{(\s([-+]\|\d+\.)\s+[^<]+?<br />)+}, list)
		puts "List: #{list}"
		cell.content = cell.content.gsub(/(\s([-+]\|\d+\.)\s+([^#{NEXT_ELEMENT_LIST_MARK}]+#{NEXT_ELEMENT_LIST_MARK}\n?))+/, list)
		# Enforce left alignment if cell contains a list
		cell.alignment = 'align="left"'
		end