wordpress-formatting 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 212f408685f81941f48154fdf71253c18c7c16f64e9c3de5cde8c9238ef279f9
+  data.tar.gz: 3d2590195083cc28d25e93e79ae7a000ae69c6650c50f6cd9e271fc1f900d22e
+SHA512:
+  metadata.gz: 1a2ee0c3087abdcd854e8fa6efa1144cca9a4540077806c6d09e4781d6414299042f8605c2a8acdee8c835c83104f4c2027852392bb51d92085d17d2d25334bf
+  data.tar.gz: 051ed4c23c4012b7ccb7021dd5cb5dc393dc97824b251b4cf76c04da6d2f77b613ae7f1a676046a1216eeb2bbecc03724e7306b9f862bc4545b5319741aa8e9e

data/README.md

@@ -0,0 +1,78 @@
+# Wordpress Formatting
+
+Ruby port for WP's formatting functions.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'wordpress-formatting'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install wordpress-formatting
+
+## Usage
+
+### wpautop
+
+WordPress posts are formatted with the `wpautop` function.  To obtain
+the same results in Ruby, run:
+
+```ruby
+require 'wordpress_formatting/wpautop'
+
+WordpressFormatting.wpautop 'A string'
+=> "<p>A string</p>"
+```
+
+You can also extend a class:
+
+```ruby
+class String
+  include WordpressFormatting::Wpautop
+end
+
+"A string".wpautop
+=> "<p>A string</p>"
+```
+
+It `fast_blank` is available, it will try to use it.
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies.
+Then, run `rake test` to run the tests. You can also run `bin/console`
+for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake
+install`. To release a new version, update the version number in
+`version.rb`, and then run `bundle exec rake release`, which will create
+a git tag for the version, push git commits and tags, and push the
+`.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on 0xacab.org at
+<https://0xacab.org/sutty/wordpress-formatting>. This
+project is intended to be a safe, welcoming space for collaboration, and
+contributors are expected to adhere to the [Sutty code of
+conduct](https://sutty.nl/en/code-of-conduct/).
+
+## License
+
+The gem is available as free software under the terms of the GPL2
+License.
+
+## Code of Conduct
+
+Everyone interacting in the wordpress-formatting project’s codebases,
+issue trackers, chat rooms and mailing lists is expected to follow the
+[code of conduct](https://sutty.nl/en/code-of-conduct/).
+

data/lib/wordpress_formatting.rb

@@ -0,0 +1,6 @@
+# frozen_string_literal: true
+
+require_relative 'wordpress_formatting/wpautop'
+
+module WordpressFormatting
+end

data/lib/wordpress_formatting/wpautop.rb

@@ -0,0 +1,193 @@
+# frozen_string_literal: true
+
+# Use fast_blank if available
+begin
+  require 'fast_blank'
+rescue LoadError
+end
+
+module WordpressFormatting
+  module Wpautop
+    # This class is a Ruby port of Wordpress' wpautop() function, as
+    # included in wp-includes/formatting.php.
+    #
+    # Some adjustments were made but it tries to follow the same code
+    # structure, so updating it when it changes wouldn't need much work.
+    # Some Rubyisms were applied when they made sense.  Comments are
+    # kept from the original.
+    #
+    # Regular expressions were converted to constants for performance.
+    class << self
+      MULTIPLE_BR = %r{<br\s*/?>\s*<br\s*/?>}
+      ALLBLOCKS_OPEN = %r{(?<block><(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|form|map|area|blockquote|address|math|style|p|h[1-6]|hr|fieldset|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)[\s/>])}
+      ALLBLOCKS_CLOSE = %r{(?<block></(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|form|map|area|blockquote|address|math|style|p|h[1-6]|hr|fieldset|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)>)}
+      HR = %r{(?<hr><hr\s*?/?>)}
+      CRLF = %r{(\r\n|\r)}
+      MANY_NL = %r{\n\n+}
+      SPLIT_NL = %r{\n\s*\n}
+      EMPTY_P = %r{<p>\s*</p>}
+      CLOSE_P = %r{<p>(?<content>[^<]+)</(?<tag>div|address|form)>}
+      UNWRAP_P = %r{<p>\s*(?<unwrap></?(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|form|map|area|blockquote|address|math|style|p|h[1-6]|hr|fieldset|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)[^>]*>)\s*</p>}
+      UNWRAP_LI = %r{<p>(?<unwrap><li.+?)</p>}
+      UNWRAP_BLOCKQUOTE = %r{<p><blockquote(?<unwrap>[^>]*)>}i
+      REMOVE_BLOCK_OPENING = %r{<p>\s*(?<remove></?(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|form|map|area|blockquote|address|math|style|p|h[1-6]|hr|fieldset|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)[^>]*>)}
+      REMOVE_BLOCK_CLOSING = %r{(?<remove></?(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|form|map|area|blockquote|address|math|style|p|h[1-6]|hr|fieldset|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)[^>]*>)\s*</p>}
+      NLBR = %r{(?<!<br />)\s*\n}
+      REMOVE_BR = %r{(?<remove></?(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|form|map|area|blockquote|address|math|style|p|h[1-6]|hr|fieldset|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)[^>]*>)\s*<br />}
+      REMOVE_BR_SUBSET = %r{<br />(?<remove>\s*</?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)}
+      PRESERVE_NL = %r{<(script|style|svg).*?<\/\1>}
+
+      # XXX: Simplified because the RegExp with comments and CDATA
+      # doesn't compile
+      HTML_SPLIT = %r{(<[^>]*>?)}
+
+      # Allows to extend a class (like String) to perform WP formatting.
+      def included(base)
+        base.class_eval do
+          def wpautop(br = true)
+            WordpressFormatting::Wpautop.wpautop(to_s, br)
+          end
+        end
+      end
+
+      # Replaces double line breaks with paragraph elements.
+      #
+      # A group of regex replaces used to identify text formatted with
+      # newlines and replace double line breaks with HTML paragraph
+      # tags. The remaining line breaks after conversion become <<br />>
+      # tags, unless $br is set to '0' or 'false'.
+      #
+      # @param [String] The text which has to be formatted.
+      # @param [Boolean] Optional. If set, this will convert all
+      # remaining line breaks after paragraphing. Line breaks within
+      # `<script>`, `<style>`, and `<svg>` tags are not
+      # affected. Default true.
+      # @return [String] Text which has been converted into correct
+      # paragraph tags.
+      def wpautop(pee, br = true)
+        return '' if pee.blank?
+        pee = pee.dup
+        pre_tags = {}
+
+        # Just to make things a little easier, pad the end.
+        pee << "\n"
+
+        if pee.include? '<pre'
+          pee_parts = pee.split '</pre>'
+          last_pee = pee_parts.pop
+          pee = ''.dup
+
+          pee_parts.each_with_index do |pee_part, i|
+            start = pee_part.index('<pre')
+
+            # Malformed HTML?
+            unless start
+              pee << pee_part
+              next
+            end
+
+            name = "<pre wp-pre-tag-#{i}></pre>"
+
+            pre_tags[name] = "#{pee_part[start..]}</pre>"
+            pee << pee_part[0..start-1]
+            pee << name
+          end
+
+          pee << last_pee
+        end
+
+        # Change multiple <br>'s into two line breaks, which will turn into paragraphs.
+        pee.gsub! MULTIPLE_BR, "\n\n"
+
+        # Add a double line break above block-level opening tags.
+        pee.gsub! ALLBLOCKS_OPEN, "\n\n\\k<block>"
+
+        # Add a double line break below block-level closing tags.
+        pee.gsub! ALLBLOCKS_CLOSE, "\\k<block>\n\n"
+
+        # Add a double line break after hr tags, which are self closing.
+        pee.gsub! HR, "\\k<hr>\n\n"
+
+        # Standardize newline characters to "\n".
+        pee.gsub! CRLF, "\n"
+
+        # Find newlines in all elements and add placeholders.
+        pee = pee.split(HTML_SPLIT).reduce(''.dup) do |new_pee, part|
+          new_pee << (part == "\n" ? ' <!-- wpnl --> ' : part)
+        end
+
+        # Remove more than two contiguous line breaks.
+        pee.gsub! MANY_NL, "\n\n"
+
+        # Split up the contents into an array of strings, separated by double line breaks.
+        pees = pee.split(SPLIT_NL).reject(&:empty?)
+
+        # Reset pee prior to rebuilding.
+        pee = ''.dup
+
+        # Rebuild the content as a string, wrapping every bit with a <p>.
+        pees.each do |tinkle|
+          pee << "<p>#{tinkle.strip}</p>"
+        end
+
+        # Under certain strange conditions it could create a P of entirely whitespace.
+        pee.gsub! EMPTY_P, ''
+
+        # Add a closing <p> inside <div>, <address>, or <form> tag if missing.
+        pee.gsub! CLOSE_P, '<p>\\k<content></p></\\k<tag>>'
+
+        # If an opening or closing block element tag is wrapped in a <p>, unwrap it.
+        pee.gsub! UNWRAP_P, '\\k<unwrap>'
+
+        # In some cases <li> may get wrapped in <p>, fix them.
+        pee.gsub! UNWRAP_LI, '\\k<unwrap>'
+
+        # If a <blockquote> is wrapped with a <p>, move it inside the <blockquote>.
+        pee.gsub! UNWRAP_BLOCKQUOTE, '<blockquote\\k<unwrap>><p>'
+        pee.gsub! '</blockquote></p>', '</p></blockquote>'
+
+        # If an opening or closing block element tag is preceded by an opening <p> tag, remove it.
+        pee.gsub! REMOVE_BLOCK_OPENING, '\\k<remove>'
+
+        # If an opening or closing block element tag is followed by a closing <p> tag, remove it.
+        pee.gsub! REMOVE_BLOCK_CLOSING, '\\k<remove>'
+
+        # Optionally insert line breaks.
+        if br
+          # Replace newlines that shouldn't be touched with a placeholder.
+          pee.scan(PRESERVE_NL).each do |match|
+            pee.gsub! match, match.gsub("\n", '<WPPreserveNewline />')
+          end
+
+          # Normalize <br>
+          pee.gsub! '<br>', '<br />'
+          pee.gsub! '<br/>', '<br />'
+
+          # Replace any new line characters that aren't preceded by a <br /> with a <br />.
+          pee.gsub! NLBR, "<br />\n"
+
+          # Replace newline placeholders with newlines.
+          pee.gsub! '<WPPreserveNewline />', "\n"
+        end
+
+        # If a <br /> tag is after an opening or closing block tag, remove it.
+        pee.gsub! REMOVE_BR, '\\k<remove>'
+
+        # If a <br /> tag is before a subset of opening or closing block tags, remove it.
+        pee.gsub! REMOVE_BR_SUBSET, '\\k<remove>'
+        pee.gsub! "\n</p>$", '</p>'
+
+        # Replace placeholder <pre> tags with their original content.
+        pre_tags.each_pair do |key, value|
+          pee.gsub! key, value
+        end
+
+        # Restore newlines in all elements.
+        pee.gsub! ' <!-- wpnl --> ', "<br />"
+        pee.gsub! '<!-- wpnl -->', "<br />"
+
+        pee
+      end
+    end
+  end
+end

metadata

@@ -0,0 +1,87 @@
+--- !ruby/object:Gem::Specification
+name: wordpress-formatting
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- f
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2021-07-22 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+description: Implements WordPress formatting functions in Ruby
+email:
+- f@sutty.nl
+executables: []
+extensions: []
+extra_rdoc_files:
+- README.md
+files:
+- README.md
+- lib/wordpress_formatting.rb
+- lib/wordpress_formatting/wpautop.rb
+homepage: https://0xacab.org/sutty/wordpress-formatting
+licenses:
+- GPL-2.0
+metadata:
+  bug_tracker_uri: https://0xacab.org/sutty/wordpress-formatting/issues
+  homepage_uri: https://0xacab.org/sutty/wordpress-formatting
+  source_code_uri: https://0xacab.org/sutty/wordpress-formatting
+  changelog_uri: https://0xacab.org/sutty/wordpress-formatting/-/blob/master/CHANGELOG.md
+  documentation_uri: https://rubydoc.info/gems/wordpress-formatting
+post_install_message:
+rdoc_options:
+- "--title"
+- wordpress-formatting - Port of WordPress formatting functions
+- "--main"
+- README.md
+- "--line-numbers"
+- "--inline-source"
+- "--quiet"
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.6.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.1.2
+signing_key:
+specification_version: 4
+summary: Port of WordPress formatting functions
+test_files: []