html2slim2 0.3.0 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c6ff64c9a5fd086b72c5db5c43df4416f4408052a1bf5e35f920bf1a26df46c5
-  data.tar.gz: 92df93ab18679e51386f70c9045fd168b5507094a070e5a5e219dfbb60795dbe
+  metadata.gz: 43220a31938b70d0b9a90e146c897e5ae26e4bab1b12b982f9e54203bd9a3212
+  data.tar.gz: 20594bd2657e9413dd54f5f358c8bfc4c3130784a027ad6f835cd743c68230d8
 SHA512:
-  metadata.gz: 2f56c1abc267eb88573528a0546bf34265da07578923854fc1f82ecbe92a4af262ae6a88059d8d1680d1fda5a3fa19d96245a15a9e5082958679e88d04c373c7
-  data.tar.gz: bd67aa82f0336fa656c93ac391db4c1b6529ed1b5e288c5295c8601c9ef3a501a10f51b4f5a93b7f9608a03a17566fe100b0468712b7b38b1a212bb2df23738b
+  metadata.gz: b4243fa2f631f4c50334b25b0777a96de02dabc30363705935b8a810b98482507e12c2ed946399a5911b18b0e8df1495b7fec37cd5a3d049e428ac370ddabfa2
+  data.tar.gz: ba9bb2d88c379b2992b44c2a5289806c17480a5db50fff32942c3dbdf8f4f5b07445f38588bd37c458380c2581661a2e4a9dbf817e02425f0513448e451a964c

data/README.md

@@ -1,6 +1,6 @@
 # HTML2Slim2
 
-![Version](https://img.shields.io/gem/v/html2slim2.svg)
+[![Gem Version](https://badge.fury.io/rb/html2slim2.svg)](https://badge.fury.io/rb/html2slim2)
 
 <!--
 [![Build Status](https://travis-ci.org/slim-template/html2slim.png?branch=master)](https://travis-ci.org/slim-template/html2slim)

data/bin/erb2slim

@@ -1,7 +1,7 @@
 #!/usr/bin/env ruby
 
 $:.unshift File.dirname(__FILE__) + '/../lib'
-require 'html2slim/command'
+require 'html2slim2/command'
 
-cmd = HTML2Slim::ERBCommand.new(ARGV)
+cmd = HTML2Slim2::ERBCommand.new(ARGV)
 cmd.run

data/bin/html2slim

@@ -1,7 +1,7 @@
 #!/usr/bin/env ruby
 
 $:.unshift File.dirname(__FILE__) + '/../lib'
-require 'html2slim/command'
+require 'html2slim2/command'
 
-cmd = HTML2Slim::HTMLCommand.new(ARGV)
+cmd = HTML2Slim2::HTMLCommand.new(ARGV)
 cmd.run

data/lib/{html2slim → html2slim2}/command.rb

@@ -1,9 +1,8 @@
 require 'optparse'
-require 'html2slim'
+require 'html2slim2'
 
-module HTML2Slim
+module HTML2Slim2
   class Command
-
     def initialize(args)
       @args    = args
       @options = {}
@@ -85,7 +84,7 @@ module HTML2Slim
       else
         slim_file = destination || slim_file
       end
-      
+
       fail(ArgumentError, "Source and destination files can't be the same.") if @options[:input] != '-' && file == slim_file
 
       in_file = if @options[:input] == "-"
@@ -95,7 +94,7 @@ module HTML2Slim
       end
 
       @options[:output] = slim_file && slim_file != '-' ? File.open(slim_file, 'w') : $stdout
-      @options[:output].puts HTML2Slim.convert!(in_file, format)
+      @options[:output].puts HTML2Slim2.convert!(in_file, format)
       @options[:output].close
 
       File.delete(file) if @options[:delete]

data/lib/{html2slim → html2slim2}/converter.rb

@@ -1,8 +1,15 @@
-require_relative 'nokogiri_monkeypatches'
+module HTML2Slim2
+  MULTILINE_ATTR_MARKER = 'html2slim2-multiline'
+end
+
+require_relative 'nokogiri_monkey_patches'
 
-module HTML2Slim
+module HTML2Slim2
   class Converter
+    OPENING_TAG_RE = /<([A-Za-z][A-Za-z0-9:-]*)((?:[^>"']|"[^"]*"|'[^']*')*)(\/?)>/m
+
     def initialize(html)
+      html = mark_multiline_opening_tags(html)
       nokogiri = html[..1] == '<!' ? Nokogiri.parse(html) : Nokogiri::HTML.fragment(html)
       @slim = nokogiri.to_slim
     end
@@ -10,6 +17,19 @@ module HTML2Slim
     def to_s
       @slim
     end
+
+    private
+
+    def mark_multiline_opening_tags(html)
+      html.gsub(OPENING_TAG_RE) do |match|
+        attrs = Regexp.last_match[2]
+        next match unless attrs.include?("\n")
+
+        name = Regexp.last_match[1]
+        slash = Regexp.last_match[3]
+        %(<#{name}#{attrs} #{MULTILINE_ATTR_MARKER}="1"#{slash}>)
+      end
+    end
   end
 
   class HTMLConverter < Converter

data/lib/html2slim2/nokogiri_monkey_patches.rb

@@ -0,0 +1,189 @@
+require 'nokogiri'
+
+class Nokogiri::XML::Text
+  def to_slim(lvl = 0)
+    str = escape(content)
+    return nil if str.strip.empty?
+
+    # A lone text line with no indentation is content, not HTML formatting space.
+    # "\na\n" → "| a"  (not "|  a ")
+    normalized = if str.match?(/\A\n+\S/) && str.match?(/\S\n+\z/)
+                   str.strip.gsub(/\s+/, ' ')
+                 else
+                   str.gsub(/\s+/, ' ')
+                 end
+
+    ('  ' * lvl) + %(| #{normalized})
+  end
+
+  private
+
+  def escape(str)
+    str.gsub!('&', '&')
+    str.gsub!('©', '©')
+    str.gsub!("\u00A0", ' ')
+    str.gsub!('»', '»')
+    str.gsub!('<', '&lt;')
+    str.gsub!('>', '&gt;')
+    str
+  end
+end
+
+class Nokogiri::XML::DTD
+  def to_slim(_lvl = 0)
+    if to_xml.include?('xml')
+      to_xml.include?('iso-8859-1') ? 'doctype xml ISO-88591' : 'doctype xml'
+    elsif to_xml.include?('XHTML') || to_xml.include?('HTML 4.01')
+      available_versions = Regexp.union ['Basic', '1.1', 'strict', 'Frameset', 'Mobile', 'Transitional']
+      version = to_xml.match(available_versions).to_s.downcase
+      "doctype #{version}"
+    else
+      'doctype html'
+    end
+  end
+end
+
+class Nokogiri::XML::Element
+  BLANK_RE = /\A[[:space:]]*\z/.freeze
+
+  def slim(lvl = 0)
+    indent = '  ' * lvl
+
+    return indent + slim_ruby_code(indent) if ruby?
+
+    r = indent
+    r += name unless skip_tag_name?
+    r += slim_id
+    r += slim_class
+    r += slim_attributes(indent)
+    r
+  end
+
+  def to_slim(lvl = 0)
+    if children.any?
+      %(#{slim(lvl)}\n#{children.filter_map { |c| c.to_slim(lvl + 1) }.join("\n")})
+    else
+      r = slim(lvl)
+      # Empty multiline tags still end with a newline so sibling spacing
+      # matches tags that only contained ignorable whitespace.
+      r.include?("\n") ? "#{r}\n" : r
+    end
+  end
+
+  private
+
+  def slim_ruby_code(indent)
+    (code.strip[0] == '=' ? '' : '- ') + code.strip.gsub('\\n', "\n#{indent}- ")
+  end
+
+  def code
+    attributes['code'].to_s
+  end
+
+  def skip_tag_name?
+    div? && (has_id? || has_class?)
+  end
+
+  def slim_id
+    has_id? ? "##{self['id']}" : ''
+  end
+
+  def slim_class
+    has_class? ? ".#{self['class'].to_s.strip.split(/\s+/).join('.')}" : ''
+  end
+
+  def slim_attributes(indent = '')
+    multiline = has_attribute?(HTML2Slim2::MULTILINE_ATTR_MARKER)
+    remove_attribute(HTML2Slim2::MULTILINE_ATTR_MARKER)
+    remove_attribute('class')
+    remove_attribute('id')
+    return '' unless has_attributes?
+
+    if multiline && multiline_attribute_output?
+      slim_multiline_attributes(indent)
+    else
+      "[#{attributes_as_html.to_s.strip}]"
+    end
+  end
+
+  def multiline_attribute_output?
+    attrs = attributes.to_hash
+    attrs.size > 1 || attrs.values.any? { |value| value.to_s.include?("\n") }
+  end
+
+  def slim_multiline_attributes(indent)
+    parts = attributes.map do |attr_name, attr_val|
+      attr_val ? "#{attr_name}=#{html_quote attr_val.to_s}" : attr_name.to_s
+    end
+    return "[#{parts.first}]" if parts.size <= 1
+
+    inner_indent = "#{indent}  "
+    "[\n#{parts.map { |part| "#{inner_indent}#{part}" }.join("\n")}\n#{indent}]"
+  end
+
+  def has_attributes? # rubocop:disable Naming/PredicatePrefix
+    attributes.to_hash.any?
+  end
+
+  def has_id? # rubocop:disable Naming/PredicatePrefix
+    has_attribute?('id') && !(BLANK_RE === self['id'])
+  end
+
+  def has_class? # rubocop:disable Naming/PredicatePrefix
+    has_attribute?('class') && !(BLANK_RE === self['class'])
+  end
+
+  def ruby?
+    name == 'ruby'
+  end
+
+  def div?
+    name == 'div'
+  end
+
+  def html_quote(str)
+    "\"#{str.gsub('"', '\\"')}\""
+  end
+
+  def attributes_as_html
+    attributes.map do |attr_name, attr_val|
+      " #{attr_name}" + (attr_val ? "=#{html_quote attr_val.to_s}" : '')
+    end.join
+  end
+end
+
+class Nokogiri::XML::DocumentFragment
+  def to_slim
+    if children.any?
+      children.filter_map(&:to_slim).join("\n")
+    else
+      ''
+    end
+  end
+end
+
+class Nokogiri::XML::Document
+  def to_slim
+    if children.any?
+      children.filter_map(&:to_slim).join("\n")
+    else
+      ''
+    end
+  end
+end
+
+class Nokogiri::XML::Comment
+  def to_slim(lvl = 0)
+    r = '  ' * lvl
+
+    # Render as a Slim comment, multiline if necessary
+    str = content.strip
+    return nil if str.empty?
+
+    if str.include?("\n")
+      "#{r}/\n#{r}  " + str.gsub("\n", "\n#{r}  ")
+    else
+      "#{r}/ #{str}"
+    end
+  end
+end

data/lib/html2slim2/version.rb

@@ -0,0 +1,3 @@
+module HTML2Slim2
+  VERSION = '0.4.0'
+end

data/lib/html2slim2.rb

@@ -0,0 +1,12 @@
+require_relative 'html2slim2/version'
+require_relative 'html2slim2/converter'
+
+module HTML2Slim2
+  def self.convert!(input, format = :html)
+    if format.to_s == "html"
+      HTMLConverter.new(input)
+    else
+      ERBConverter.new(input)
+    end
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html2slim2
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.4.0
 platform: ruby
 authors:
 - sanadan
 - Maiz Lulkin
 bindir: bin
 cert_chain: []
-date: 2025-05-08 00:00:00.000000000 Z
+date: 2026-09-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -24,62 +24,6 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: minitest
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: rake
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: rubocop-rails-omakase
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: slim
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
 description: Convert HTML to Slim templates. Because HTML sux and Slim rules. That's
   why.
 email:
@@ -95,14 +39,17 @@ files:
 - README.md
 - bin/erb2slim
 - bin/html2slim
-- lib/html2slim.rb
-- lib/html2slim/command.rb
-- lib/html2slim/converter.rb
-- lib/html2slim/nokogiri_monkeypatches.rb
-- lib/html2slim/version.rb
-homepage: https://github.com/sanadan/html2slim
-licenses: []
-metadata: {}
+- lib/html2slim2.rb
+- lib/html2slim2/command.rb
+- lib/html2slim2/converter.rb
+- lib/html2slim2/nokogiri_monkey_patches.rb
+- lib/html2slim2/version.rb
+homepage: https://github.com/sanadan/html2slim2
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/sanadan/html2slim2
+  rubygems_mfa_required: 'true'
 rdoc_options:
 - "--charset=UTF-8"
 require_paths:
@@ -111,14 +58,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: '3.3'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.6.7
+rubygems_version: 4.0.16
 specification_version: 4
 summary: HTML to Slim converter.
 test_files: []

data/lib/html2slim/nokogiri_monkeypatches.rb

@@ -1,138 +0,0 @@
-require 'nokogiri'
-
-class Nokogiri::XML::Text
-  def to_slim(lvl = 0)
-    str = escape(content)
-    return nil if str.strip.empty?
-
-    ('  ' * lvl) + %(| #{str.gsub(/\s+/, ' ')})
-  end
-
-  private
-
-  def escape(str)
-    str.gsub!('&', '&')
-    str.gsub!('©', '©')
-    str.gsub!("\u00A0", ' ')
-    str.gsub!('»', '»')
-    str.gsub!('<', '&lt;')
-    str.gsub!('>', '&gt;')
-    str
-  end
-end
-
-class Nokogiri::XML::DTD
-  def to_slim(_lvl = 0)
-    if to_xml.include?('xml')
-      to_xml.include?('iso-8859-1') ? 'doctype xml ISO-88591' : 'doctype xml'
-    elsif to_xml.include?('XHTML') || to_xml.include?('HTML 4.01')
-      available_versions = Regexp.union ['Basic', '1.1', 'strict', 'Frameset', 'Mobile', 'Transitional']
-      version = to_xml.match(available_versions).to_s.downcase
-      "doctype #{version}"
-    else
-      'doctype html'
-    end
-  end
-end
-
-class Nokogiri::XML::Element
-  BLANK_RE = /\A[[:space:]]*\z/.freeze
-
-  def slim(lvl = 0)
-    r = '  ' * lvl
-
-    return r + slim_ruby_code(r) if ruby?
-
-    r += name unless skip_tag_name?
-    r += slim_id
-    r += slim_class
-    r += slim_attributes
-    r
-  end
-
-  def to_slim(lvl = 0)
-    if children.count.positive?
-      %(#{slim(lvl)}\n#{children.filter_map { |c| c.to_slim(lvl + 1) }.join("\n")})
-    else
-      slim(lvl)
-    end
-  end
-
-  private
-
-  def slim_ruby_code(r)
-    (code.strip[0] == '=' ? '' : '- ') + code.strip.gsub('\\n', "\n#{r}- ")
-  end
-
-  def code
-    attributes['code'].to_s
-  end
-
-  def skip_tag_name?
-    div? && (has_id? || has_class?)
-  end
-
-  def slim_id
-    has_id? ? "##{self['id']}" : ''
-  end
-
-  def slim_class
-    has_class? ? ".#{self['class'].to_s.strip.split(/\s+/).join('.')}" : ''
-  end
-
-  def slim_attributes
-    remove_attribute('class')
-    remove_attribute('id')
-    has_attributes? ? "[#{attributes_as_html.to_s.strip}]" : ''
-  end
-
-  def has_attributes? # rubocop:disable Naming/PredicateName
-    attributes.to_hash.any?
-  end
-
-  def has_id? # rubocop:disable Naming/PredicateName
-    has_attribute?('id') && !(BLANK_RE === self['id'])
-  end
-
-  def has_class? # rubocop:disable Naming/PredicateName
-    has_attribute?('class') && !(BLANK_RE === self['class'])
-  end
-
-  def ruby?
-    name == 'ruby'
-  end
-
-  def div?
-    name == 'div'
-  end
-
-  def html_quote(str)
-    "\"#{str.gsub('"', '\\"')}\""
-  end
-
-  def attributes_as_html
-    attributes.map do |aname, aval|
-      " #{aname}" + (aval ? "=#{html_quote aval.to_s}" : '')
-    end.join
-  end
-end
-
-class Nokogiri::XML::DocumentFragment
-  def to_slim
-    if children.count.positive?
-      children.filter_map(&:to_slim).join("\n")
-    else
-      ''
-    end
-  end
-end
-
-class Nokogiri::XML::Document
-  def to_slim
-    if children.count.positive?
-      children.filter_map(&:to_slim).join("\n")
-    else
-      ''
-    end
-  end
-end

data/lib/html2slim/version.rb

@@ -1,3 +0,0 @@
-module HTML2Slim
-  VERSION = '0.3.0'
-end

data/lib/html2slim.rb

@@ -1,12 +0,0 @@
-require_relative 'html2slim/version'
-require_relative 'html2slim/converter'
-
-module HTML2Slim
-  def self.convert!(input, format=:html)
-    if format.to_s == "html"
-      HTMLConverter.new(input)
-    else
-      ERBConverter.new(input)
-    end
-  end
-end