From f3d049feb232fb321fc20cafff5dce8a6f893c6c Mon Sep 17 00:00:00 2001
From: Yessiest <yessiest@memeware.net>
Date: Sun, 2 Mar 2025 13:38:25 +0400
Subject: [PATCH] fixes for list parsing
---
README.md | 2 +-
architecture.md | 92 ++++
classes | 13 -
document.rb | 738 --------------------------------
lib/blankshell.rb | 64 ++-
test.md | 81 ----
test/test_atx_headers.rb | 102 -----
test/test_fenced_code_block.rb | 147 -------
test/test_fenced_code_blocks.rb | 102 -----
test/test_indent_block.rb | 97 -----
test/test_setext_headers.rb | 147 -------
test/test_thematic_breaks.rb | 127 ------
view_structure.rb | 21 +
13 files changed, 162 insertions(+), 1571 deletions(-)
create mode 100644 architecture.md
delete mode 100644 classes
delete mode 100644 document.rb
delete mode 100644 test.md
delete mode 100644 test/test_atx_headers.rb
delete mode 100644 test/test_fenced_code_block.rb
delete mode 100644 test/test_fenced_code_blocks.rb
delete mode 100644 test/test_indent_block.rb
delete mode 100644 test/test_setext_headers.rb
delete mode 100644 test/test_thematic_breaks.rb
create mode 100644 view_structure.rb
diff --git a/README.md b/README.md
index 38b356c..7aeafc5 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,3 @@
# rubymark
-Minimalistic modular markdown parser in Ruby
\ No newline at end of file
+Modular, compliant markdown parser in Ruby
diff --git a/architecture.md b/architecture.md
new file mode 100644
index 0000000..dab5c57
--- /dev/null
+++ b/architecture.md
@@ -0,0 +1,92 @@
+Architecture of madness
+=======================
+
+Prelude
+-------
+
+It needs to be stressed that making the parser modular while keeping it
+relatively simple was a laborous undertaking. There has not been a standard
+more hostile towards the people who dare attempt to implement it than
+CommonMark. It should also be noted, that despite it being titled a
+"Standard" in this document, it is less widely adopted than the Github
+Flavored Markdown syntax. Github Flavored Markdown, however, is only but
+a mere subset of this parser's model, albeit requiring a few extensions.
+
+Current state (as of March 02, 2025)
+------------------------------------
+
+This parser processes text in what can be boiled down to three phases.
+
+- Block/Line phase
+- Overlay phase
+- Inline phase
+
+The first phase breaks down blocks, line by line, into block structures.
+Blocks (preferably inherited from the Block class) can contain other blocks.
+(i.e. QuoteBlock, ULBlock, OLBlock). Other blocks (known as leaf blocks)
+may not contain anything else (except inline content, more on that later).
+
+Blocks are designed to be parsed independently. This means that it *should*
+be possible to tear out any standard block and make it not get parsed.
+This, however, isn't thoroughly tested for.
+
+Blocks as proper, real classes have a certain lifecycle to follow when
+being constructed:
+
+1. Open condition
+ - A block needs to find its first marker on the current line to open
+ (see `#begin?` method)
+ - Once it's open, it's immediately initialized and fed the line it just
+ read (but now as an object, not as a class) (see `#consume` method)
+2. Marker/Line consumption
+ - While it should be kept open, the block parser instance will
+ keep reading inupt through `#consume` method, returning a pair
+ of modified line (after consuming its tokens from it) and
+ a boolean value indicating permission of lazy continuation
+ (if it's a block like a QuoteBlock or ULBlock that can be lazily
+ overflowed).
+ Every line the parser needs to record needs to be pushed
+ through the `#push` method.
+3. Closure
+ - If the current line no longer belongs to the current block
+ (if the block should have been closed on the previous line),
+ it simply needs to `return` a pair of `nil`, and a boolean value for
+ permission of lazy continuation
+ - If a block should be closed on the current line, it should capture it,
+ keep track of the "closed" state, then `return` `nil` on the next call
+ of `#consume`
+ - Once a block is closed, it:
+ 1. Receives its content from the parser
+ 2. Parser receives the "close" method call
+ 3. (optional) Parser may have a callable method `#applyprops`. If
+ it exists, it gets called with the current constructed block.
+ 4. (optional) All overlays assigned to this block's class are
+ processed on the contents of this block (more on that in
+ Overlay phase)
+ 5. (optional) Parser may return a different class, which
+ the current block should be cast into (Overlays may change
+ the class as well)
+ 6. (optional) If a block can respond to `#parse_inner` method, it
+ will get called, allowing the block to parse its own contents.
+ - After this point, the block is no longer touched until the document
+ fully gets processed.
+4. Inline processing
+ - (Applies only to Paragraph and any child of LeafBlock)
+ When the document gets fully processed, the contents of the current
+ block are taken, assigned to an InlineRoot instance, and then parsed
+ in Inline mode
+5. Completion
+ - The resulting document is then returned.
+
+While there is a lot of functionality available in desgining blocks, it is
+not necessary for the simplest of the block kinds available. The simplest
+example of a block parser is likely the ThematicBreakParser class, which
+implements the only 2 methods needed for a block parser to function.
+
+While parsing text, a block may use additional info:
+
+- In consume method: `lazy` hasharg, if the current line is being processed
+ in lazy continuation mode (likely only ever matters for Paragraph); and
+ `parent` - the parent block containing this block.
+
+
diff --git a/classes b/classes
deleted file mode 100644
index 9153047..0000000
--- a/classes
+++ /dev/null
@@ -1,13 +0,0 @@
-Bold [x}
-Italics [x]
-Underline [x]
-Strikethrough [x]
-CodeInline [x]
-Link [x]
-Image [x]
-Headings [x]
-CodeBlock [x]
-QuoteBlock [x]
-ULBlock [x]
-OLBLock [x]
-TableBlock []
diff --git a/document.rb b/document.rb
deleted file mode 100644
index 07c15f6..0000000
--- a/document.rb
+++ /dev/null
@@ -1,738 +0,0 @@
-# frozen_string_literal: true
-
-module RBMark
- # Parser units
- # Parsers are divided into three categories:
- # - Slicers - these parsers read the whole text of an element and slice it into chunks digestible by other parsers
- # - ChunkParsers - these parsers transform chunks of text into a single DOM unit
- # - InlineParsers - these parsers are called directly by the slicer to check whether a certain element matches needed criteria
- module Parsers
- # Abstract slicer class
- class Slicer
- # @param parent [::RBMark::DOM::DOMObject]
- def initialize
- @chunk_parsers = []
- end
-
- attr_accessor :chunk_parsers
-
- private
-
- def parse_chunk(text)
- @chunk_parsers.each do |parser|
- unless parser.is_a? ChunkParser
- raise StandardError, 'not a ChunkParser'
- end
-
- next unless parser.match?(text)
-
- return parser.match(text)
- end
- nil
- end
- end
-
- # Abstract inline parser class
- class InlineParser
- # Test if piece matches bold syntax
- # @param text [String]
- # @return [Boolean]
- def match?(text)
- text.match?(@match_exp)
- end
-
- # Construct a new object from text
- # @param text [String]
- # @return [Object]
- def match(text)
- @class.parse(text)
- end
-
- attr_reader :class, :match_exp
- end
-
- # Abstract chunk parser class
- class ChunkParser
- # Stub for match method
- def match(text)
- element = ::RBMark::DOM::Text.new
- element.content = text
- element
- end
-
- # Stub for match? method
- def match?(_text)
- true
- end
- end
-
- # Slices text into paragraphs and feeds slices to chunk parsers
- class RootSlicer < Slicer
- # Parse text into chunks and feed each to the chain
- # @param text [String]
- def parse(text)
- output = text.split(/(?:\r\r|\n\n|\r\n\r\n|\Z)/)
- .reject { |x| x.match(/\A\s*\Z/) }
- .map do |block|
- parse_chunk(block)
- end
- merge_list_indents(output)
- end
-
- private
-
- def merge_list_indents(chunks)
- last_list = nil
- delete_deferred = []
- chunks.each_with_index do |chunk, index|
- if !last_list and [::RBMark::DOM::ULBlock,
- ::RBMark::DOM::OLBlock].include? chunk.class
- last_list = chunk
- elsif last_list and mergeable?(last_list, chunk)
- merge(last_list, chunk)
- delete_deferred.prepend(index)
- else
- last_list = nil
- end
- end
- delete_deferred.each { |i| chunks.delete_at(i) }
- chunks
- end
-
- def mergeable?(last_list, chunk)
- if chunk.is_a? ::RBMark::DOM::IndentBlock or
- (chunk.is_a? ::RBMark::DOM::ULBlock and
- last_list.is_a? ::RBMark::DOM::ULBlock) or
- (chunk.is_a? ::RBMark::DOM::OLBlock and
- last_list.is_a? ::RBMark::DOM::OLBlock and
- last_list.properties["num"] > chunk.properties["num"])
- true
- else
- false
- end
- end
-
- def merge(last_list, chunk)
- if chunk.is_a? ::RBMark::DOM::IndentBlock
- last_list.children.last.children.append(*chunk.children)
- else
- last_list.children.append(*chunk.children)
- end
- end
- end
-
- # Inline text slicer (slices based on the start and end symbols)
- class InlineSlicer < Slicer
- # Parse slices
- # @param text [String]
- def parse(text)
- parts = []
- index = prepare_markers
- until text.empty?
- before, part, text = slice(text)
- parts.append(::RBMark::DOM::Text.parse(before)) unless before.empty?
- next unless part
-
- element = index.fetch(part.regexp,
- ::RBMark::Parsers::TextInlineParser.new)
- .match(part[0])
- parts.append(element)
- end
- parts
- end
-
- private
-
- # Prepare markers from chunk_parsers
- # @return [Hash]
- def prepare_markers
- index = {}
- @markers = @chunk_parsers.map do |parser|
- index[parser.match_exp] = parser
- parser.match_exp
- end
- index
- end
-
- # Get the next slice of a text based on markers
- # @param text [String]
- # @return [Array<(String,MatchData,String)>]
- def slice(text)
- first_tag = @markers.map { |x| text.match(x) }
- .reject(&:nil?)
- .min_by { |x| x.offset(0)[0] }
- return text, nil, "" unless first_tag
-
- [first_tag.pre_match, first_tag, first_tag.post_match]
- end
- end
-
- # Slicer for unordered lists
- class UnorderedSlicer < Slicer
- # Parse list elements
- def parse(text)
- output = []
- buffer = ""
- text.lines.each do |line|
- if line.start_with? "- " and !buffer.empty?
- output.append(make_element(buffer))
- buffer = ""
- end
- buffer += line[2..]
- end
- output.append(make_element(buffer)) unless buffer.empty?
- output
- end
-
- private
-
- def make_element(text)
- ::RBMark::DOM::ListElement.parse(text)
- end
- end
-
- # Slicer for unordered lists
- class OrderedSlicer < Slicer
- # rubocop:disable Metrics/AbcSize
-
- # Parse list elements
- def parse(text)
- output = []
- buffer = ""
- indent = text.match(/\A\d+\. /)[0].length
- num = text.match(/\A(\d+)\. /)[1]
- text.lines.each do |line|
- if line.start_with?(/\d+\. /) and !buffer.empty?
- output.append(make_element(buffer, num))
- buffer = ""
- indent = line.match(/\A\d+\. /)[0].length
- num = line.match(/\A(\d+)\. /)[1]
- end
- buffer += line[indent..]
- end
- output.append(make_element(buffer, num)) unless buffer.empty?
- output
- end
-
- # rubocop:enable Metrics/AbcSize
- private
-
- def make_element(text, num)
- element = ::RBMark::DOM::ListElement.parse(text)
- element.property num: num.to_i
- element
- end
- end
-
- # Quote block parser
- class QuoteChunkParser < ChunkParser
- # Tests for chunk being a block quote
- # @param text [String]
- # @return [Boolean]
- def match?(text)
- text.lines.map do |x|
- x.match?(/\A\s*>(?:\s[^\n\r]+|)\Z/m)
- end.all?(true)
- end
-
- # Transforms text chunk into a block quote
- # @param text
- # @return [::RBMark::DOM::QuoteBlock]
- def match(text)
- text = text.lines.map do |x|
- x.match(/\A\s*>(\s[^\n\r]+|)\Z/m)[1].to_s[1..]
- end.join("\n")
- ::RBMark::DOM::QuoteBlock.parse(text)
- end
- end
-
- # Paragraph block
- class ParagraphChunkParser < ChunkParser
- # Acts as a fallback for the basic paragraph chunk
- # @param text [String]
- # @return [Boolean]
- def match?(_text)
- true
- end
-
- # Creates a new paragraph with the given text
- def match(text)
- ::RBMark::DOM::Paragraph.parse(text)
- end
- end
-
- # Code block
- class CodeChunkParser < ChunkParser
- # Check if a block matches the given parser rule
- # @param text [String]
- # @return [Boolean]
- def match?(text)
- text.match?(/\A```\w+[\r\n]{1,2}.*[\r\n]{1,2}```\Z/m)
- end
-
- # Create a new element
- def match(text)
- lang, code = text.match(
- /\A```(\w+)[\r\n]{1,2}(.*)[\r\n]{1,2}```\Z/m
- )[1, 2]
- element = ::RBMark::DOM::CodeBlock.new
- element.property language: lang
- element.content = code
- element
- end
- end
-
- # Heading chunk parser
- class HeadingChunkParser < ChunkParser
- # Check if a block matches the given parser rule
- # @param text [String]
- # @return [Boolean]
- def match?(text)
- text.match?(/\A\#{1,4}\s/)
- end
-
- # Create a new element
- def match(text)
- case text.match(/\A\#{1,4}\s/)[0]
- when "# " then ::RBMark::DOM::Heading1.parse(text[2..])
- when "## " then ::RBMark::DOM::Heading2.parse(text[3..])
- when "### " then ::RBMark::DOM::Heading3.parse(text[4..])
- when "#### " then ::RBMark::DOM::Heading4.parse(text[5..])
- end
- end
- end
-
- # Unordered list parser (chunk)
- class UnorderedChunkParser < ChunkParser
- # Check if a block matches the given parser rule
- # @param text [String]
- # @return [Boolean]
- def match?(text)
- return false unless text.start_with? "- "
-
- text.lines.map do |line|
- line.match?(/\A(?:- .*| .*| )\Z/)
- end.all?(true)
- end
-
- # Create a new element
- def match(text)
- ::RBMark::DOM::ULBlock.parse(text)
- end
- end
-
- # Ordered list parser (chunk)
- class OrderedChunkParser < ChunkParser
- # Check if a block matches the given parser rule
- # @param text [String]
- # @return [Boolean]
- def match?(text)
- return false unless text.start_with?(/\d+\. /)
-
- indent = 0
- text.lines.each do |line|
- if line.start_with?(/\d+\. /)
- indent = line.match(/\A\d+\. /)[0].length
- elsif line.start_with?(/\s+/)
- return false if line.match(/\A\s+/)[0].length < indent
- else
- return false
- end
- end
- true
- end
-
- # Create a new element
- def match(text)
- ::RBMark::DOM::OLBlock.parse(text)
- end
- end
-
- # Indented block parser
- class IndentChunkParser < ChunkParser
- # Check if a block matches the given parser rule
- # @param text [String]
- # @return [Boolean]
- def match?(text)
- text.lines.map do |x|
- x.start_with? " " or x.start_with? "\t"
- end.all?(true)
- end
-
- # Create a new element
- def match(text)
- text = text.lines.map { |x| x.match(/\A(?: {4}|\t)(.*)\Z/)[1] }
- .join("\n")
- ::RBMark::DOM::IndentBlock.parse(text)
- end
- end
-
- # Stub text parser
- class TextInlineParser < InlineParser
- # Stub method for creating new Text object
- def match(text)
- instance = ::RBMark::DOM::Text.new
- instance.content = text
- instance
- end
- end
-
- # Bold text
- class BoldInlineParser < InlineParser
- def initialize
- super
- @match_exp = /(?<!\\)\*\*+.+?(?<!\\)\*+\*/
- end
-
- # Match element
- def match(text)
- ::RBMark::DOM::InlineBold.parse(text[2..-3])
- end
- end
-
- # Italics text
- class ItalicsInlineParser < InlineParser
- def initialize
- super
- @match_exp = /(?<!\\)\*+.+?(?<!\\)\*+/
- end
-
- # Match element
- def match(text)
- ::RBMark::DOM::InlineItalics.parse(text[1..-2])
- end
- end
-
- # Underlined text
- class UnderInlineParser < InlineParser
- def initialize
- super
- @match_exp = /(?<!\\)__+.+?(?<!\\)_+_/
- end
-
- # Match element
- def match(text)
- ::RBMark::DOM::InlineUnder.parse(text[2..-3])
- end
- end
-
- # Strikethrough text
- class StrikeInlineParser < InlineParser
- def initialize
- super
- @match_exp = /(?<!\\)~~+.+?(?<!\\)~+~/
- end
-
- # Match element
- def match(text)
- ::RBMark::DOM::InlineStrike.parse(text[2..-3])
- end
- end
-
- # Preformatted text
- class PreInlineParser < InlineParser
- def initialize
- super
- @match_exp = /(?<!\\)``+.+?(?<!\\)`+`/
- end
-
- # Match element
- def match(text)
- ::RBMark::DOM::InlinePre.parse(text[2..-3])
- end
- end
-
- # Hyperreference link
- class LinkInlineParser < InlineParser
- def initialize
- super
- @match_exp = /(?<![\\!])\[(.+?(?<!\\))\]\((.+?(?<!\\))\)/
- end
-
- # Match element
- def match(text)
- title, link = text.match(@match_exp)[1..2]
- element = ::RBMark::DOM::InlineLink.new
- element.content = title
- element.property link: link
- element
- end
- end
-
- # Image
- class ImageInlineParser < InlineParser
- def initialize
- super
- @match_exp = /(?<!\\)!\[(.+?(?<!\\))\]\((.+?(?<!\\))\)/
- end
-
- # Match element
- def match(text)
- title, link = text.match(@match_exp)[1..2]
- element = ::RBMark::DOM::InlineImage.new
- element.content = title
- element.property link: link
- element
- end
- end
-
- # Linebreak
- class BreakInlineParser < InlineParser
- def initialize
- super
- @match_exp = /\s{2}/
- end
-
- # Match element
- def match(_text)
- element = ::RBMark::DOM::InlineBreak.new
- element.content = ""
- element
- end
- end
- end
-
- # Module for representing abstract object hierarchy
- module DOM
- # Abstract container
- class DOMObject
- class << self
- attr_accessor :parsers
- attr_reader :slicer
-
- # Hook for initializing variables
- def inherited(subclass)
- super
- # Inheritance initialization
- subclass.slicer = @slicer if @slicer
- subclass.parsers = @parsers.dup if @parsers
- subclass.parsers ||= []
- end
-
- # Initialize parsers for the current class
- def initialize_parsers
- @active_parsers = @parsers.map(&:new)
- @active_slicer = @slicer.new if @slicer
- end
-
- # Add a slicer
- # @param parser [Object]
- def slicer=(parser)
- unless parser < ::RBMark::Parsers::Slicer
- raise StandardError, "#{x} is not a Slicer"
- end
-
- @slicer = parser
- end
-
- # Add a parser to the chain
- # @param parser [Object]
- def parser(parser)
- unless [::RBMark::Parsers::InlineParser,
- ::RBMark::Parsers::ChunkParser].any? { |x| parser < x }
- raise StandardError, "#{x} is not an InlineParser or a ChunkParser"
- end
-
- @parsers.append(parser)
- end
-
- # Parse text from the given context
- # @param text [String]
- # @return [self]
- def parse(text)
- initialize_parsers
- container = new
- container.content = text
- _parse(container)
- container.content = "" unless container.is_a? ::RBMark::DOM::Text
- container
- end
-
- private
-
- def _parse(instance)
- return unless @active_slicer
-
- @active_slicer.chunk_parsers = @active_parsers
- instance.children.append(*@active_slicer.parse(instance.content))
- end
- end
-
- def initialize
- @content = nil
- @children = []
- @properties = {}
- end
-
- # Set certain property in the properties hash
- # @param properties [Hash] proeprties to update
- def property(**properties)
- @properties.update(**properties)
- end
-
- # Add child to container
- # @param child [DOMObject]
- def append(*children)
- unless children.all? { |x| x.is_a? DOMObject }
- raise StandardError, "#{x} is not a DOMObject"
- end
-
- @children.append(*children)
- end
-
- # Insert a child into the container
- # @param child [DOMObject]
- # @param index [Integer]
- def insert(index, child)
- raise StandardError, "not a DOMObject" unless child.is_a? DOMObject
-
- @children.insert(index, child)
- end
-
- # Delete a child from container
- # @param index [Integer]
- def delete_at(index)
- @children.delete_at(index)
- end
-
- # Get a child from the container
- # @param key [Integer]
- def [](key)
- @children[key]
- end
-
- # Set text content of a DOMObject
- # @param text [String]
- def content=(text)
- raise StandardError, "not a String" unless text.is_a? String
-
- @content = text
- end
-
- # Get text content of a DOMObject
- # @return [String, nil]
- attr_reader :content, :children, :properties
- end
-
- # Document root
- class Document < DOMObject
- self.slicer = ::RBMark::Parsers::RootSlicer
- parser ::RBMark::Parsers::IndentChunkParser
- parser ::RBMark::Parsers::QuoteChunkParser
- parser ::RBMark::Parsers::HeadingChunkParser
- parser ::RBMark::Parsers::CodeChunkParser
- parser ::RBMark::Parsers::UnorderedChunkParser
- parser ::RBMark::Parsers::OrderedChunkParser
- parser ::RBMark::Parsers::ParagraphChunkParser
- end
-
- # Inline text
- class Text < DOMObject
- def self.parse(text)
- instance = super(text)
- instance.content = instance.content.gsub(/[\s\r\n]+/, " ")
- instance
- end
- end
-
- # Inline preformatted text
- class InlinePre < DOMObject
- self.slicer = ::RBMark::Parsers::InlineSlicer
- end
-
- # Infline formattable text
- class InlineFormattable < DOMObject
- self.slicer = ::RBMark::Parsers::InlineSlicer
- parser ::RBMark::Parsers::BreakInlineParser
- parser ::RBMark::Parsers::BoldInlineParser
- parser ::RBMark::Parsers::ItalicsInlineParser
- parser ::RBMark::Parsers::PreInlineParser
- parser ::RBMark::Parsers::UnderInlineParser
- parser ::RBMark::Parsers::StrikeInlineParser
- parser ::RBMark::Parsers::LinkInlineParser
- parser ::RBMark::Parsers::ImageInlineParser
- end
-
- # Bold text
- class InlineBold < InlineFormattable
- end
-
- # Italics text
- class InlineItalics < InlineFormattable
- end
-
- # Underline text
- class InlineUnder < InlineFormattable
- end
-
- # Strikethrough text
- class InlineStrike < InlineFormattable
- end
-
- # Hyperreferenced text
- class InlineLink < InlineFormattable
- end
-
- # Image
- class InlineImage < DOMObject
- end
-
- # Linebreak
- class InlineBreak < DOMObject
- end
-
- # Heading level 1
- class Heading1 < InlineFormattable
- end
-
- # Heading level 2
- class Heading2 < Heading1
- end
-
- # Heading level 3
- class Heading3 < Heading1
- end
-
- # Heading level 4
- class Heading4 < Heading1
- end
-
- # Preformatted code block
- class CodeBlock < DOMObject
- end
-
- # Quote block
- class QuoteBlock < Document
- end
-
- # Table
- class TableBlock < DOMObject
- end
-
- # Unordered list
- class ULBlock < DOMObject
- self.slicer = ::RBMark::Parsers::UnorderedSlicer
- end
-
- # Ordered list block
- class OLBlock < DOMObject
- self.slicer = ::RBMark::Parsers::OrderedSlicer
- end
-
- # Indent block
- class IndentBlock < Document
- end
-
- # List element
- class ListElement < Document
- end
-
- # Horizontal rule
- class HorizontalRule < DOMObject
- end
-
- # Paragraph in a document (separated by 2 newlines)
- class Paragraph < InlineFormattable
- end
- end
-end
diff --git a/lib/blankshell.rb b/lib/blankshell.rb
index ddfc36c..ab2cd64 100644
--- a/lib/blankshell.rb
+++ b/lib/blankshell.rb
@@ -484,18 +484,24 @@ module PointBlank
self.open(line)
return [nil, true] unless continues?(line)
- [line, true]
+ [normalize(line), true]
end
+ attr_reader :preoff
+
private
# Open block if it hasn't been opened yet
def open(line)
- marker, offset = line.match(/\A {0,3}([-+*])(\s+)/)&.captures
- return unless marker
+ return if @open
- @marker ||= ['+', '*'].include?(marker) ? "\\#{marker}" : marker
- @offset = offset
+ preoff, mark, off = line.match(/\A( {0,3})([-+*])(\s+)/)&.captures
+ return unless mark
+
+ @preoff = preoff
+ @marker ||= ['+', '*'].include?(mark) ? "\\#{mark}" : mark
+ @offset = off
+ @open = true
end
# Check if a line continues this ULParser block
@@ -505,6 +511,11 @@ module PointBlank
line.start_with?(/\A(?: {0,3}#{@marker}| )#{@offset}/) ||
line.strip.empty?
end
+
+ # Strip off pre-marker offset
+ def normalize(line)
+ line.delete_prefix(@preoff)
+ end
end
# Unorder list block (element)
@@ -515,7 +526,8 @@ module PointBlank
end
# (see ::PointBlank::Parsing::NullParser#consume)
- def consume(line, _parent = nil, **_hargs)
+ def consume(line, parent = nil, **_hargs)
+ @parent ||= parent
return [nil, true] unless continues?(line)
self.open(line)
@@ -544,7 +556,12 @@ module PointBlank
# Normalize the line
def normalize(line)
- line.gsub(/\A(?: {0,3}#{@marker}| )#{@offset}/, '')
+ if !@opening_stripped
+ @opening_stripped = true
+ line.gsub(/\A(?: {0,3}#{@marker}| )#{@offset}/, '')
+ else
+ line.gsub(/\A\s#{@offset}/, '')
+ end
end
end
@@ -567,20 +584,23 @@ module PointBlank
self.open(line)
return [nil, true] unless continues?(line)
- [line, true]
+ [normalize(line), true]
end
private
# Open block if it hasn't been opened yet
def open(line)
- num, marker, offset = line.match(/\A {0,3}(\d+)([).])(\s+)/)
- &.captures
+ return if @open
+ pre, num, marker, off = line.match(/\A( {0,3})(\d+)([).])(\s+)/)
+ &.captures
return unless marker
+ @preoff = pre
@num = " " * (num.length + 1)
@mark ||= "\\#{marker}"
- @offset = offset
+ @offset = off
+ @open = true
end
# Check if a line continues this ULParser block
@@ -590,6 +610,11 @@ module PointBlank
line.start_with?(/\A(?: {0,3}(\d+)#{@mark}|#{@num})#{@offset}/) ||
line.strip.empty?
end
+
+ # Strip off pre-marker offset
+ def normalize(line)
+ line.delete_prefix(@preoff)
+ end
end
# Unorder list block (element)
@@ -602,7 +627,7 @@ module PointBlank
# (see ::PointBlank::Parsing::NullParser#consume)
def consume(line, _parent = nil, **_hargs)
return [nil, true] unless continues?(line)
-
+
self.open(line)
[normalize(line), true]
@@ -619,10 +644,12 @@ module PointBlank
def open(line)
return if @open
- @num, @marker, @offset = line.match(/\A {0,3}(\d+)([).])(\s+)/)
- &.captures
+ num, marker, off = line.match(/\A {0,3}(\d+)([).])(\s+)/)
+ &.captures
+ @num = num
@numoffset = " " * (@num.length + 1)
- @marker = "\\#{@marker}"
+ @marker = "\\#{marker}"
+ @offset = off
@open = true
end
@@ -636,7 +663,12 @@ module PointBlank
# Normalize the line
def normalize(line)
- line.gsub(/\A(?: {0,3}(\d+)#{@marker}|#{@numoffset})#{@offset}/, '')
+ if !@opening_stripped
+ @opening_stripped = true
+ line.gsub(/\A(?: {0,3}\d+#{@marker}|#{@numoffset})#{@offset}/, '')
+ else
+ line.gsub(/\A#{@numoffset}#{@offset}/, '')
+ end
end
end
diff --git a/test.md b/test.md
deleted file mode 100644
index a7a0bf7..0000000
--- a/test.md
+++ /dev/null
@@ -1,81 +0,0 @@
-# Header level sadga kjshdkj hasdkjs hakjdhakjshd kashd kjashd kjashdk asjhdkj ashdkj ahskj hdaskd haskj hdkjash dkjashd ksajdh askjd hak askjhdkasjhdaksjhd sakjd 1
-
-> Block quote text
->
-> Second block quote paragraph
-> Block quote **bold** and *italics* test
-> Block quote **bold *italics* mix** test
-
-## Header level 2
-
-[link](http://example.com)
-
-
-```plaintext
-code *block*
-eat my shit
-```
-
-paragraph with ``inline code block``
-
-- Unordered list element 1
-- Unordered list element 2
-
-1. Ordered list element 1
-2. Ordered list element 2
-
-This is not a list
-- because it continues the paragraph
-- this is how it should be, like it or not
-
-- This is also not a list
-because there is text on the next line
-
-- But this here is a list
- because the spacing is made correctly
-
- more so than that, there are multiple paragraphs here!
-
- - AND even more lists in a list!
- - how extra
-- And this is just the next element in the list
-
-1. same thing but with ordered lists
- ordered lists have a little extra special property to them
-
- the indentations are always symmetrical to the last space of the bullet's number
-10. i.e., if you look at this here example
- this will work
-
- obviously
-
-
-1. But this
-10. Won't
- because the indentation doesn't match the start of the line.
-
-generally speaking this kind of insane syntax trickery won't be necessary,
-but it's just better to have standards than to have none of them.
-
-an unfortunate side effect of this flexibility should also be noted, and
-it's that markdown linters don't like this sort of stuff.
-Yet another reason not to use a markdown linter.
-
-- And this is just the lame stupid old way to do this, as described by mardkownguide
-
- > just indent your stuff and it works
- > really it's as simple as that.
- > bruh
-
- there can be as many as infinite number of elements appended to the list that way.
-
- you can even start a sublist here if you want to
-
- - here's a new nested list
- - could you imagine the potential
-
- and here's an image of nothing
-
- 
-
-- I may also need to merge lists for this to work properly
diff --git a/test/test_atx_headers.rb b/test/test_atx_headers.rb
deleted file mode 100644
index 58a038a..0000000
--- a/test/test_atx_headers.rb
+++ /dev/null
@@ -1,102 +0,0 @@
-# frozen_string_literal: true
-
-require 'minitest/autorun'
-require_relative '../lib/rbmark'
-
-# Test ATX Heading parsing compliance with CommonMark v0.31.2
-class TestATXHeadings < Minitest::Test
- def test_simple_heading1
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- # ATX Heading level 1
- Paragraph
- DOC
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[0])
- end
-
- def test_simple_heading2
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- ## ATX Heading level 2
- Paragraph
- DOC
- assert_instance_of(::RBMark::DOM::Heading2, doc.children[0])
- end
-
- def test_simple_heading3
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- ### ATX Heading level 3
- Paragraph
- DOC
- assert_instance_of(::RBMark::DOM::Heading3, doc.children[0])
- end
-
- def test_simple_heading4
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- #### ATX Heading level 4
- Paragraph
- DOC
- assert_instance_of(::RBMark::DOM::Heading4, doc.children[0])
- end
-
- def test_simple_heading5
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- ##### ATX Heading level 5
- Paragraph
- DOC
- assert_instance_of(::RBMark::DOM::Heading5, doc.children[0])
- end
-
- def test_simple_heading6
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- ###### ATX Heading level 6
- Paragraph
- DOC
- assert_instance_of(::RBMark::DOM::Heading6, doc.children[0])
- end
-
- def test_simple_not_a_heading
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- ####### NOT a heading
- DOC
- assert_instance_of(::RBMark::DOM::Paragraph, doc.children[0])
- end
-
- def test_breaking_paragrpah
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- Paragraph 1
- # ATX Heading level 1
- Paragraph 2
- DOC
- assert_instance_of(::RBMark::DOM::Paragraph, doc.children[0])
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[1])
- assert_instance_of(::RBMark::DOM::Paragraph, doc.children[2])
- end
-
- def test_heading_sans_space
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- #NOT an ATX heading
- DOC
- assert_instance_of(::RBMark::DOM::Paragraph, doc.children[0])
- end
-
- def test_heading_escaped
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- \\# Escaped ATX heading
- DOC
- assert_instance_of(::RBMark::DOM::Paragraph, doc.children[0])
- end
-
- def test_spaces
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- #### Heading level 4
- ### Heading level 3
- ## Heading level 2
- # Heading level 1
- # NOT a heading
- DOC
- assert_instance_of(::RBMark::DOM::Heading4, doc.children[0])
- assert_instance_of(::RBMark::DOM::Heading3, doc.children[1])
- assert_instance_of(::RBMark::DOM::Heading2, doc.children[2])
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[3])
- refute_instance_of(::RBMark::DOM::Heading1, doc.children[4])
- end
-end
diff --git a/test/test_fenced_code_block.rb b/test/test_fenced_code_block.rb
deleted file mode 100644
index 2d1878b..0000000
--- a/test/test_fenced_code_block.rb
+++ /dev/null
@@ -1,147 +0,0 @@
-# frozen_string_literal: true
-
-require 'minitest/autorun'
-require_relative '../lib/rbmark'
-
-# Test Setext Heading parsing compliance with CommonMark v0.31.2
-class TestSetextHeadings < Minitest::Test
- def test_simple_heading1
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- Foo *bar*
- =========
-
- Foo *bar*
- ---------
- DOC
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[0])
- assert_instance_of(::RBMark::DOM::Heading2, doc.children[1])
- end
-
- def test_multiline_span
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- Foo *bar
- baz*
- ====
- DOC
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[0])
- assert_equal(1, doc.children.length)
- end
-
- def test_span_inlining
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- start
-
- Foo *bar
- baz
- ====
- DOC
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[1])
- skip
- end
-
- def test_line_length
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- Foo
- ------------------------------
-
- Foo
- =
- DOC
- assert_instance_of(::RBMark::DOM::Heading2, doc.children[0])
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[1])
- end
-
- def test_content_indent
- skip # TODO: implement this
- end
-
- def test_marker_indent
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- Foo
- ------------------------------
-
- Foo
- =
-
- Foo
- =
-
- Foo
- =
- DOC
- refute_instance_of(::RBMark::DOM::Heading2, doc.children[0])
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[1])
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[2])
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[3])
- end
-
- def test_no_internal_spaces
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- Foo
- -- - -
-
- Foo
- == =
- DOC
- refute_instance_of(::RBMark::DOM::Heading2, doc.children[0])
- refute_instance_of(::RBMark::DOM::Heading1, doc.children[0])
- end
-
- def test_block_level_priority
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- ` Foo
- ------
- `
- DOC
- assert_instance_of(::RBMark::DOM::Heading2, doc.children[0])
- assert_instance_of(::RBMark::DOM::Paragraph, doc.children[1])
- end
-
- def test_paragraph_breaking_only
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- > text
- ------
- DOC
- skip # TODO: implement this
- end
-
- def test_paragraph_breaking_only_lazy_continuation
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- > text
- continuation line
- ------
- DOC
- skip # TODO: implement this
- end
-
- def test_headings_back_to_back
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- heading1
- ------
- heading2
- ------
- heading3
- ======
- DOC
- assert_instance_of(::RBMark::DOM::Heading2, doc.children[0])
- assert_instance_of(::RBMark::DOM::Heading2, doc.children[1])
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[2])
- end
-
- def test_no_empty_headings
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
-
- ======
- DOC
- refute_instance_of(::RBMark::DOM::Heading1, doc.children[0])
- end
-
- def test_thematic_breaks
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- ----
- ----
- DOC
- refute_instance_of(::RBMark::DOM::Heading2, doc.children[0])
- refute_instance_of(::RBMark::DOM::Heading2, doc.children[1])
- end
-end
diff --git a/test/test_fenced_code_blocks.rb b/test/test_fenced_code_blocks.rb
deleted file mode 100644
index 58a038a..0000000
--- a/test/test_fenced_code_blocks.rb
+++ /dev/null
@@ -1,102 +0,0 @@
-# frozen_string_literal: true
-
-require 'minitest/autorun'
-require_relative '../lib/rbmark'
-
-# Test ATX Heading parsing compliance with CommonMark v0.31.2
-class TestATXHeadings < Minitest::Test
- def test_simple_heading1
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- # ATX Heading level 1
- Paragraph
- DOC
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[0])
- end
-
- def test_simple_heading2
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- ## ATX Heading level 2
- Paragraph
- DOC
- assert_instance_of(::RBMark::DOM::Heading2, doc.children[0])
- end
-
- def test_simple_heading3
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- ### ATX Heading level 3
- Paragraph
- DOC
- assert_instance_of(::RBMark::DOM::Heading3, doc.children[0])
- end
-
- def test_simple_heading4
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- #### ATX Heading level 4
- Paragraph
- DOC
- assert_instance_of(::RBMark::DOM::Heading4, doc.children[0])
- end
-
- def test_simple_heading5
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- ##### ATX Heading level 5
- Paragraph
- DOC
- assert_instance_of(::RBMark::DOM::Heading5, doc.children[0])
- end
-
- def test_simple_heading6
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- ###### ATX Heading level 6
- Paragraph
- DOC
- assert_instance_of(::RBMark::DOM::Heading6, doc.children[0])
- end
-
- def test_simple_not_a_heading
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- ####### NOT a heading
- DOC
- assert_instance_of(::RBMark::DOM::Paragraph, doc.children[0])
- end
-
- def test_breaking_paragrpah
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- Paragraph 1
- # ATX Heading level 1
- Paragraph 2
- DOC
- assert_instance_of(::RBMark::DOM::Paragraph, doc.children[0])
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[1])
- assert_instance_of(::RBMark::DOM::Paragraph, doc.children[2])
- end
-
- def test_heading_sans_space
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- #NOT an ATX heading
- DOC
- assert_instance_of(::RBMark::DOM::Paragraph, doc.children[0])
- end
-
- def test_heading_escaped
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- \\# Escaped ATX heading
- DOC
- assert_instance_of(::RBMark::DOM::Paragraph, doc.children[0])
- end
-
- def test_spaces
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- #### Heading level 4
- ### Heading level 3
- ## Heading level 2
- # Heading level 1
- # NOT a heading
- DOC
- assert_instance_of(::RBMark::DOM::Heading4, doc.children[0])
- assert_instance_of(::RBMark::DOM::Heading3, doc.children[1])
- assert_instance_of(::RBMark::DOM::Heading2, doc.children[2])
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[3])
- refute_instance_of(::RBMark::DOM::Heading1, doc.children[4])
- end
-end
diff --git a/test/test_indent_block.rb b/test/test_indent_block.rb
deleted file mode 100644
index c81e0b4..0000000
--- a/test/test_indent_block.rb
+++ /dev/null
@@ -1,97 +0,0 @@
-# frozen_string_literal: true
-
-require 'minitest/autorun'
-require_relative '../lib/rbmark'
-
-# Test Setext Heading parsing compliance with CommonMark v0.31.2
-class TestSetextHeadings < Minitest::Test
- def test_simple_indent
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- text
-
- indented code block
- without space mangling
-
- int main() {
- printf("Hello world!\\n");
- }
- DOC
- assert_instance_of(::RBMark::DOM::IndentBlock, doc.children[1])
- end
-
- def test_list_item_precedence
- skip # TODO: implement this
- end
-
- def test_numbered_list_item_precednce
- skip # TODO: implement this
- end
-
- def test_check_indent_contents
- skip # TODO: yet again please implement this at some point thanks
- end
-
- def test_long_chunk
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- text
-
- indented code block
- without space mangling
-
- int main() {
- printf("Hello world!\\n");
- }
-
-
- there are many space changes here and blank lines that
- should *NOT* affect the way this is parsed
- DOC
- assert_instance_of(::RBMark::DOM::IndentBlock, doc.children[1])
- end
-
- def test_does_not_interrupt_paragraph
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- Paragraph begins here
- paragraph does the stupid wacky shit that somebody thinks is very funny
- paragraph keeps doing that shit
- DOC
- assert_instance_of(::RBMark::DOM::Paragraph, doc.children[0])
- assert_equal(1, doc.children.length)
- end
-
- def test_begins_at_first_sight_of_four_spaces
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- text
-
- This is an indent block
- This is a paragraph
- DOC
- assert_instance_of(::RBMark::DOM::Paragraph, doc.children[0])
- assert_instance_of(::RBMark::DOM::IndentBlock, doc.children[1])
- assert_instance_of(::RBMark::DOM::Paragraph, doc.children[2])
- end
-
- def test_interrupts_all_other_blocks
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- # Heading
- foo
- Heading
- ------
- foo
- ----
- DOC
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[0])
- assert_instance_of(::RBMark::DOM::IndentBlock, doc.children[1])
- assert_instance_of(::RBMark::DOM::Heading2, doc.children[2])
- assert_instance_of(::RBMark::DOM::IndentBlock, doc.children[3])
- assert_instance_of(::RBMark::DOM::HorizontalRule, doc.children[4])
- end
-
- def test_check_blank_lines_contents
- skip # TODO: PLEASE I FUCKING BEG YOU IMPLEMENT THIS
- end
-
- def test_check_contents_trailing_spaces
- skip # TODO: AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAa
- end
-end
diff --git a/test/test_setext_headers.rb b/test/test_setext_headers.rb
deleted file mode 100644
index 2d1878b..0000000
--- a/test/test_setext_headers.rb
+++ /dev/null
@@ -1,147 +0,0 @@
-# frozen_string_literal: true
-
-require 'minitest/autorun'
-require_relative '../lib/rbmark'
-
-# Test Setext Heading parsing compliance with CommonMark v0.31.2
-class TestSetextHeadings < Minitest::Test
- def test_simple_heading1
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- Foo *bar*
- =========
-
- Foo *bar*
- ---------
- DOC
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[0])
- assert_instance_of(::RBMark::DOM::Heading2, doc.children[1])
- end
-
- def test_multiline_span
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- Foo *bar
- baz*
- ====
- DOC
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[0])
- assert_equal(1, doc.children.length)
- end
-
- def test_span_inlining
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- start
-
- Foo *bar
- baz
- ====
- DOC
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[1])
- skip
- end
-
- def test_line_length
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- Foo
- ------------------------------
-
- Foo
- =
- DOC
- assert_instance_of(::RBMark::DOM::Heading2, doc.children[0])
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[1])
- end
-
- def test_content_indent
- skip # TODO: implement this
- end
-
- def test_marker_indent
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- Foo
- ------------------------------
-
- Foo
- =
-
- Foo
- =
-
- Foo
- =
- DOC
- refute_instance_of(::RBMark::DOM::Heading2, doc.children[0])
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[1])
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[2])
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[3])
- end
-
- def test_no_internal_spaces
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- Foo
- -- - -
-
- Foo
- == =
- DOC
- refute_instance_of(::RBMark::DOM::Heading2, doc.children[0])
- refute_instance_of(::RBMark::DOM::Heading1, doc.children[0])
- end
-
- def test_block_level_priority
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- ` Foo
- ------
- `
- DOC
- assert_instance_of(::RBMark::DOM::Heading2, doc.children[0])
- assert_instance_of(::RBMark::DOM::Paragraph, doc.children[1])
- end
-
- def test_paragraph_breaking_only
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- > text
- ------
- DOC
- skip # TODO: implement this
- end
-
- def test_paragraph_breaking_only_lazy_continuation
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- > text
- continuation line
- ------
- DOC
- skip # TODO: implement this
- end
-
- def test_headings_back_to_back
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- heading1
- ------
- heading2
- ------
- heading3
- ======
- DOC
- assert_instance_of(::RBMark::DOM::Heading2, doc.children[0])
- assert_instance_of(::RBMark::DOM::Heading2, doc.children[1])
- assert_instance_of(::RBMark::DOM::Heading1, doc.children[2])
- end
-
- def test_no_empty_headings
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
-
- ======
- DOC
- refute_instance_of(::RBMark::DOM::Heading1, doc.children[0])
- end
-
- def test_thematic_breaks
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- ----
- ----
- DOC
- refute_instance_of(::RBMark::DOM::Heading2, doc.children[0])
- refute_instance_of(::RBMark::DOM::Heading2, doc.children[1])
- end
-end
diff --git a/test/test_thematic_breaks.rb b/test/test_thematic_breaks.rb
deleted file mode 100644
index 1ace973..0000000
--- a/test/test_thematic_breaks.rb
+++ /dev/null
@@ -1,127 +0,0 @@
-# frozen_string_literal: true
-
-require 'minitest/autorun'
-require_relative '../lib/rbmark'
-
-# Test thematic break parsing compliance with CommonMark v0.31.2
-class TestThematicBreaks < Minitest::Test
- def test_simple
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- ---
- ***
- ___
- DOC
- assert_instance_of(::RBMark::DOM::HorizontalRule, doc.children[0])
- assert_instance_of(::RBMark::DOM::HorizontalRule, doc.children[1])
- assert_instance_of(::RBMark::DOM::HorizontalRule, doc.children[2])
- end
-
- def test_simple_invalid
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- +++
- DOC
- refute_instance_of(::RBMark::DOM::HorizontalRule, doc.children[0])
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- ===
- DOC
- refute_instance_of(::RBMark::DOM::HorizontalRule, doc.children[0])
- end
-
- def test_simple_less_characters
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- --
-
- **
-
- __
- DOC
- refute_instance_of(::RBMark::DOM::HorizontalRule, doc.children[0])
- refute_instance_of(::RBMark::DOM::HorizontalRule, doc.children[1])
- refute_instance_of(::RBMark::DOM::HorizontalRule, doc.children[2])
- end
-
- def test_indentation
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- ***
- ***
- ***
- ***
- ***
- DOC
- assert_instance_of(::RBMark::DOM::HorizontalRule, doc.children[0])
- assert_instance_of(::RBMark::DOM::HorizontalRule, doc.children[1])
- assert_instance_of(::RBMark::DOM::HorizontalRule, doc.children[2])
- assert_instance_of(::RBMark::DOM::HorizontalRule, doc.children[3])
- refute_instance_of(::RBMark::DOM::HorizontalRule, doc.children[4])
- end
-
- def test_indentation_mixed_classes
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- Foo
-
- ***
- DOC
- refute_instance_of(::RBMark::DOM::HorizontalRule, doc.children.last)
- end
-
- def test_line_length
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- _________________________________
- DOC
- assert_instance_of(::RBMark::DOM::HorizontalRule, doc.children[0])
- end
-
- def test_mixed_spaces
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- - - -
-
- ** * ** * ** * **
-
- - - - -
-
- - - - -
- DOC
- assert_instance_of(::RBMark::DOM::HorizontalRule, doc.children[0])
- assert_instance_of(::RBMark::DOM::HorizontalRule, doc.children[1])
- assert_instance_of(::RBMark::DOM::HorizontalRule, doc.children[2])
- assert_instance_of(::RBMark::DOM::HorizontalRule, doc.children[3])
- end
-
- def test_mixed_characters
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- _ _ _ _ a
-
- a------
-
- ---a---
- DOC
- refute_instance_of(::RBMark::DOM::HorizontalRule, doc.children[0])
- refute_instance_of(::RBMark::DOM::HorizontalRule, doc.children[2])
- refute_instance_of(::RBMark::DOM::HorizontalRule, doc.children[3])
- end
-
- def test_mixed_markets
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- *-*
- DOC
- refute_instance_of(::RBMark::DOM::HorizontalRule, doc.children[0])
- end
-
- def test_interrupt_list
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- - foo
- ***
- - bar
- DOC
- assert_instance_of(::RBMark::DOM::HorizontalRule, doc.children[1])
- end
-
- def test_interrupt_paragraph
- doc = ::RBMark::DOM::Document.parse(<<~DOC)
- foo
- ***
- bar
- DOC
- assert_instance_of(::RBMark::DOM::HorizontalRule, doc.children[1])
- end
-end
diff --git a/view_structure.rb b/view_structure.rb
new file mode 100644
index 0000000..079dd2f
--- /dev/null
+++ b/view_structure.rb
@@ -0,0 +1,21 @@
+# frozen_string_literal: true
+
+require_relative 'lib/blankshell.rb'
+
+structure = PointBlank::DOM::Document.parse(File.read(ARGV[0]))
+def red(string)
+ "\033[31m#{string}\033[0m"
+end
+def yellow(string)
+ "\033[33m#{string}\033[0m"
+end
+
+def prettyprint(doc, indent = 0)
+ closed = doc.properties[:closed]
+ puts "#{yellow(doc.class.name.gsub(/\w+::DOM::/,""))}#{red(closed ? "(c)" : "")}: #{doc.content.inspect}"
+ doc.children.each do |child|
+ print red("#{" " * indent} - ")
+ prettyprint(child, indent + 4)
+ end
+end
+prettyprint(structure)