obsidian-parser 0.5.4 → 0.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 37cfdc15ab5d67c4ac5972db19df269b71a20c516bc43bc9014daccdf42879eb
-  data.tar.gz: ed67a9489d6e3ed05df0b72d14773b5674945ae993b51386e76634023629de74
+  metadata.gz: 5882ab166c0770a2b52258e31fbaea89646292b0288f60116373072e389a375e
+  data.tar.gz: 37139895344d860500ae5b29135645adf4b34dcfa8e395d5d2c41f6029870d4f
 SHA512:
-  metadata.gz: 1b39d82790d769bda1434db80434715715c9be20b9fae0fd9f9c51147354e9f8adb46062b3500ff07d1084d3435ab764fc7f27a22481dfc48447ef0524802cec
-  data.tar.gz: acd7d36cac25c162da92a939e132033afd2b4585af490c188505295b9d51134a3073b47fc8e457777a984facec6884230c6b5e2188554be1a56a0a26f8ceec8e
+  metadata.gz: 6b3254e1c0f267646c7846568c48a6070615488130a335f46a01e7f1e3b1ab03e2ceb22aa090a379164ec2f81e0632217cec53e9bc61577c78240f04f7eee739
+  data.tar.gz: 5afe24ce2c30d488e4d89a5d57d421a8b4b65aefe915ab48a37f16c22d8cc5a04f147e5dd804772630377cbd01a73c07f5dfa421550c6dbf0ee9559980d45a6f

data/CHANGELOG.md

@@ -1,5 +1,10 @@
 ## [Unreleased]
 
+## [0.6.0] - 2023-08-03
+- Replace Kramdown with Markly
+- Enabled support for Github Flavored Markdown tables and tasklists
+- Rename `MarkdownContent` -> `MarkdownDocument`, `ObsidianFlavoredMarkdown` -> `MarkdownParser`
+
 ## [0.5.4] - 2023-08-02
 - Fix page getting clobbered when wikilinks point to non-existent pages.
 - Expand `[[foo/index]]` wiklinks to `[foo](foo)`.

data/Gemfile.lock

@@ -1,9 +1,8 @@
 PATH
   remote: .
   specs:
-    obsidian-parser (0.5.4)
-      kramdown (~> 2.4)
-      kramdown-parser-gfm (~> 1.1)
+    obsidian-parser (0.6.0)
+      markly (~> 0.7.0)
 
 GEM
   remote: https://rubygems.org/
@@ -12,12 +11,9 @@ GEM
     coderay (1.1.3)
     diff-lcs (1.5.0)
     json (2.6.3)
-    kramdown (2.4.0)
-      rexml
-    kramdown-parser-gfm (1.1.0)
-      kramdown (~> 2.0)
     language_server-protocol (3.17.0.3)
     lint_roller (1.1.0)
+    markly (0.7.0)
     method_source (1.0.0)
     parallel (1.23.0)
     parser (3.2.2.3)

data/lib/obsidian/parser/html_renderer.rb

@@ -0,0 +1,40 @@
+class HtmlRenderer < Markly::Renderer::HTML
+  def header(node)
+    block do
+      out("<h", node.header_level, " id=\"", header_id(node), "\">",
+        :children, "</h", node.header_level, ">")
+    end
+  end
+
+  private
+
+  def header_id(node)
+    # Taken from Kramdown
+    # https://github.com/gettalong/kramdown/blob/bd678ecb59f70778fdb3b08bdcd39e2ab7379b45/lib/kramdown/converter/base.rb
+    gen_id = extract_text(node).gsub(/^[^a-zA-Z]+/, "")
+    gen_id.tr!("^a-zA-Z0-9 -", "")
+    gen_id.tr!(" ", "-")
+    gen_id.downcase!
+
+    gen_id = "section" if gen_id.empty?
+
+    @used_ids ||= {}
+    if @used_ids.key?(gen_id)
+      gen_id += "-#{@used_ids[gen_id] += 1}"
+    else
+      @used_ids[gen_id] = 0
+    end
+
+    gen_id
+  end
+
+  def extract_text(node)
+    node.each do |subnode|
+      if subnode.type == :text
+        return subnode.string_content
+      end
+    end
+
+    ""
+  end
+end

data/lib/obsidian/parser/markdown_document.rb

@@ -0,0 +1,16 @@
+# frozen_string_literal: true
+
+module Obsidian
+  class MarkdownDocument
+    def initialize(path, root, markdown_parser:)
+      @path = path
+      @root = root
+      @markdown_parser = markdown_parser
+    end
+
+    def generate_html
+      markdown = @path.read
+      @markdown_parser.parse(markdown, root: @root).to_html
+    end
+  end
+end

data/lib/obsidian/parser/markdown_parser.rb

@@ -0,0 +1,53 @@
+# frozen_string_literal: true
+
+require "markly"
+
+module Obsidian
+  class MarkdownParser
+    WIKILINK_SYNTAX = %r{
+      \[\[
+      (?<target>[^\]\#|]*) # link target
+      (?:
+        \#(?<fragment>[^|\]]*) # optional heading fragment
+      )?
+      (?:
+        \|(?<text>[^\]]*) # optional link display text
+      )?
+      \]\]
+    }x
+
+    def initialize(renderer: HtmlRenderer.new)
+      @renderer = renderer
+    end
+
+    # Convert Obsidian-flavored-markdown syntax to something parseable
+    # (i.e. with Github-flavored-markdown syntax)
+    def expand_wikilinks(markdown_text, root:)
+      markdown_text.gsub(WIKILINK_SYNTAX) do |s|
+        text = $~[:text]
+        target = $~[:target]
+        fragment = $~[:fragment]
+        page = root.find_in_tree(target)
+
+        if page.nil?
+          text.nil? ? target.split("/").last : text
+        else
+          display_text = text.nil? ? page.slug.split("/").last : text
+          href = fragment.nil? ? page.slug : "#{page.slug}##{fragment}"
+
+          "[#{display_text}](#{href})"
+        end
+      end
+    end
+
+    def parse(markdown_text, root: nil)
+      normalized = expand_wikilinks(markdown_text, root: root)
+      document = Markly.parse(normalized, flags: Markly::SMART | Markly::UNSAFE | Markly::HARD_BREAKS, extensions: [:table, :tasklist, :autolink])
+      Obsidian::ParsedMarkdownDocument.new(document, renderer: renderer)
+    end
+
+    private
+
+    attr_reader :renderer
+  end
+end

data/lib/obsidian/parser/parsed_markdown_document.rb

@@ -2,39 +2,39 @@
 
 module Obsidian
   class ParsedMarkdownDocument
-    def initialize(document)
+    def initialize(document, renderer:)
       @document = document
+      @renderer = renderer
     end
 
     def extract_links
-      _extract_links(document.root)
+      results = []
+
+      document.walk do |node|
+        if node.type == :link
+          text = _extract_text_content(node)
+          href = node.url
+          results << [href, text]
+        end
+      end
+
+      results
     end
 
     def to_html
-      document.to_html
+      renderer.render(document)
     end
 
     private
 
     attr_reader :document
-
-    def _extract_links(element)
-      if element.type == :a
-        [[element.attr["href"], _extract_text_content(element)]]
-      elsif !element.children.empty?
-        element.children.flat_map { |child| _extract_links(child) }
-      else
-        []
-      end
-    end
+    attr_reader :renderer
 
     def _extract_text_content(element)
       if element.type == :text
-        element.value
-      elsif !element.children.empty?
-        element.children.map { |child| _extract_text_content(child) }.join
+        element.string_content
       else
-        ""
+        element.each.map { |child| _extract_text_content(child) }.join
       end
     end
   end

data/lib/obsidian/parser/version.rb

@@ -2,6 +2,6 @@
 
 module Obsidian
   class Parser
-    VERSION = "0.5.4"
+    VERSION = "0.6.0"
   end
 end

data/lib/obsidian/parser.rb

@@ -2,9 +2,10 @@
 
 require_relative "parser/version"
 require_relative "parser/parsed_markdown_document"
-require_relative "parser/obsidian_flavored_markdown"
+require_relative "parser/markdown_parser"
 require_relative "parser/page"
-require_relative "parser/markdown_content"
+require_relative "parser/markdown_document"
+require_relative "parser/html_renderer"
 
 require "forwardable"
 
@@ -20,6 +21,7 @@ module Obsidian
 
     def initialize(vault_directory)
       @index = Obsidian::Page.create_root
+      markdown_parser = MarkdownParser.new
 
       vault_directory.glob("**/*.md").each do |path|
         dirname, basename = path.relative_path_from(vault_directory).split
@@ -39,7 +41,7 @@ module Obsidian
         @index.add_page(
           slug,
           last_modified: path.mtime,
-          content: MarkdownContent.new(path, @index)
+          content: MarkdownDocument.new(path, @index, markdown_parser: markdown_parser)
         )
       end
 

metadata

@@ -1,43 +1,29 @@
 --- !ruby/object:Gem::Specification
 name: obsidian-parser
 version: !ruby/object:Gem::Version
-  version: 0.5.4
+  version: 0.6.0
 platform: ruby
 authors:
 - Mat Moore
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-08-02 00:00:00.000000000 Z
+date: 2023-08-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: kramdown
+  name: markly
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.4'
+        version: 0.7.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.4'
-- !ruby/object:Gem::Dependency
-  name: kramdown-parser-gfm
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.1'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.1'
+        version: 0.7.0
 description:
 email:
 - matmoore@users.noreply.github.com
@@ -56,8 +42,9 @@ files:
 - README.md
 - Rakefile
 - lib/obsidian/parser.rb
-- lib/obsidian/parser/markdown_content.rb
-- lib/obsidian/parser/obsidian_flavored_markdown.rb
+- lib/obsidian/parser/html_renderer.rb
+- lib/obsidian/parser/markdown_document.rb
+- lib/obsidian/parser/markdown_parser.rb
 - lib/obsidian/parser/page.rb
 - lib/obsidian/parser/parsed_markdown_document.rb
 - lib/obsidian/parser/version.rb

data/lib/obsidian/parser/markdown_content.rb

@@ -1,15 +0,0 @@
-# frozen_string_literal: true
-
-module Obsidian
-  class MarkdownContent
-    def initialize(path, root)
-      @path = path
-      @root = root
-    end
-
-    def generate_html
-      markdown = @path.read
-      Obsidian::ObsidianFlavoredMarkdown.parse(markdown, root: @root).to_html
-    end
-  end
-end

data/lib/obsidian/parser/obsidian_flavored_markdown.rb

@@ -1,74 +0,0 @@
-# frozen_string_literal: true
-
-require "kramdown"
-require "kramdown-parser-gfm"
-
-module Obsidian
-  module ObsidianFlavoredMarkdown
-    WIKILINK_SYNTAX = %r{
-      \[\[
-      (?<target>[^\]\#|]*) # link target
-      (?:
-        \#(?<fragment>[^|\]]*) # optional heading fragment
-      )?
-      (?:
-        \|(?<text>[^\]]*) # optional link display text
-      )?
-      \]\]
-    }x
-
-    # Match URLs
-    # Pattern based on https://gist.github.com/dperini/729294
-    LONE_URL = %r{
-      (?<!\S) # not preceeded by a non-whitespace character
-      https?:// # Protocol
-      (?:\S+(?::\S*)?@)? # basic auth
-      (?![-_]) # Not followed by a dash or underscore
-      (?:[-\w\u00a1-\uffff]{0,63}[^-_]\.)+ # host and domain names
-      (?:[a-z\u00a1-\uffff]{2,}\.?) # top level domain
-      (?::\\d{2,5})? # Port number
-      (?:[/?#]\\S*)? # Resource path
-      (?!\S) # not followed by a non-whitespace character
-    }x
-
-    # Workaround for lack of auto-linking in Kramdown.
-    # Note: this breaks for URLs included in code blocks.
-    def self.auto_link(markdown_text)
-      markdown_text.gsub(LONE_URL) do |s|
-        "<#{s}>" # Kramdown-specific markup
-      end
-    end
-
-    # Convert Obsidian-flavored-markdown syntax to something parseable
-    # (i.e. with Github-flavored-markdown syntax)
-    def self.expand_wikilinks(markdown_text, root:)
-      markdown_text.gsub(WIKILINK_SYNTAX) do |s|
-        text = $~[:text]
-        target = $~[:target]
-        fragment = $~[:fragment]
-        page = root.find_in_tree(target)
-
-        if page.nil?
-          text.nil? ? target.split("/").last : text
-        else
-          display_text = text.nil? ? page.slug.split("/").last : text
-          href = fragment.nil? ? page.slug : "#{page.slug}##{fragment}"
-
-          "[#{display_text}](#{href})"
-        end
-      end
-    end
-
-    def self.normalize(markdown_text, root: nil)
-      auto_linked = auto_link(markdown_text)
-      return auto_linked if root.nil?
-
-      expand_wikilinks(auto_link(markdown_text), root: root)
-    end
-
-    def self.parse(markdown_text, root: nil)
-      document = Kramdown::Document.new(normalize(markdown_text, root: root), input: "GFM")
-      Obsidian::ParsedMarkdownDocument.new(document)
-    end
-  end
-end