html2text 0.4.0 → 0.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 32afc21e326c44b7881358081161b9581c396b167fad44614a96cc0b6df91f23
-  data.tar.gz: fe03a0811cbff965e6b720ad1fdfdd55c0aa1e03165c16c84de7ecac39d65c9d
+  metadata.gz: 1a1e6fcee8973815b391ca28bd156a878e36594e0bfbece01f7ff8c67f6cad6f
+  data.tar.gz: f515c6edb112deeae87f59b717aa4a2aed5d37b4b42db151fc49359f2b98d0b9
 SHA512:
-  metadata.gz: e26ef2f826da8958c56a390bd4242461abdd26a110216ee3903c902e007b5fb26b38a8f358b420abe6eac480b4a452fedba90b75a36eb7f3f0c2bec4dad040a7
-  data.tar.gz: 31515d14c3ca612f2eb9faaf52655639c3c0b72687fed89c41d83fad816af852854057e3ff0803e9f16e5e1d2b62657699cedef5b9240ab114826d936d0ed3c0
+  metadata.gz: 3972abc5f287146a5f43969fe3a37b83333559618b198ccc6ca3b105178c7cb37a03c9b44317428c8323c9b86e7e7a22a78276d9ddb7cccaab1819105e469a18
+  data.tar.gz: dcc2f39ebc4d772b47762cacb5de22ab16f386fbc4952c7fcf72ae66938fffcacad1fad7062714fdebc21a6b74c802224d02b796c099d2a00d1b3d13729f5d6d

data/CHANGELOG.md

@@ -4,9 +4,19 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [Unreleased]
+## [Unreleased](https://github.com/soundasleep/html2text_ruby/compare/v0.5.0...master)
 
-## [0.4.0] - 2024-06-08
+## [0.5.0](https://github.com/soundasleep/html2text_ruby/compare/v0.4.0...v0.5.0) - 2026-07-08
+### Added
+- Add a `wrap_links:` option to `Html2Text.convert` and `Html2Text.new` (default `true`); when `false`, hyperlinks render as `text: href` instead of markdown-style `[text](href)`. Only affects `<a href>` links — images and named anchors keep their `[bracketed]` format ([#40](https://github.com/soundasleep/html2text_ruby/pull/40))
+- Specs covering subclass overrides of `prefix_whitespace`, `suffix_whitespace`, `iterate_over`, `wrap_link` and `image_text`, plus unit specs for `fix_newlines` and `replace_entities` ([#41](https://github.com/soundasleep/html2text_ruby/pull/41))
+
+### Changed
+- Require Ruby 3.3+, since all earlier Rubies are EOL; CI now tests Ruby 3.3, 3.4 and 4.0 ([#42](https://github.com/soundasleep/html2text_ruby/pull/42))
+- Reduce object allocations in `iterate_over` for ~1.6x faster conversion of large documents ([#41](https://github.com/soundasleep/html2text_ruby/pull/41))
+- Update development dependencies (rubocop 1.88, nokogiri 1.19 in the lockfile), removing the transitive `rexml` dependency ([#42](https://github.com/soundasleep/html2text_ruby/pull/42))
+
+## [0.4.0](https://github.com/soundasleep/html2text_ruby/compare/0.3.1...v0.4.0) - 2024-06-08
 ### Added
 - Switch from Travis to Github Actions for Build and Test
 - Add rubocop for linting and cleanup existing violations ([#36](https://github.com/soundasleep/html2text_ruby/pull/36))

data/README.md

@@ -1,4 +1,4 @@
-html2text ![Build](https://github.com/soundasleep/html2text_ruby/actions/workflows/build.yml/badge.svg) [![Gem Version](https://badge.fury.io/rb/html2text.svg)](https://rubygems.org/gems/html2text)
+html2text ![Build](https://github.com/soundasleep/html2text_ruby/actions/workflows/build.yml/badge.svg) [![Gem Version](https://badge.fury.io/rb/html2text.svg)](https://badge.fury.io/rb/html2text)
 ---
 
 `html2text` is a very simple gem that uses DOM methods to convert HTML into a format similar to what would be

data/lib/html2text/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 class Html2Text
-  VERSION = '0.4.0'
+  VERSION = '0.5.0'
 end

data/lib/html2text.rb

@@ -5,11 +5,12 @@ require 'nokogiri'
 class Html2Text
   attr_reader :doc
 
-  def initialize(doc)
+  def initialize(doc, wrap_links: true)
     @doc = doc
+    @wrap_links = wrap_links
   end
 
-  def self.convert(html)
+  def self.convert(html, wrap_links: true)
     html = html.to_s
 
     if office_document?(html)
@@ -27,7 +28,7 @@ class Html2Text
     html = fix_newlines(replace_entities(html))
     doc = Nokogiri::HTML(html)
 
-    new(doc).convert
+    new(doc, wrap_links: wrap_links).convert
   end
 
   def self.fix_newlines(text)
@@ -50,6 +51,7 @@ class Html2Text
   end
 
   DO_NOT_TOUCH_WHITESPACE = '<do-not-touch-whitespace>'
+  IGNORED_TAGS = Set.new(%w[style head title meta script]).freeze
 
   def remove_leading_and_trailing_whitespace(text)
     # ignore any <pre> blocks, which we don't want to interact with
@@ -74,14 +76,14 @@ class Html2Text
   private
 
   def remove_unnecessary_empty_lines(text)
-    text.gsub(/\n\n\n*/im, "\n\n")
+    text.gsub(/\n{3,}/, "\n\n")
   end
 
   def trimmed_whitespace(text)
     # Replace whitespace characters with a space (equivalent to \s)
     # and force any text encoding into UTF-8
     if text.valid_encoding?
-      text.gsub(/[\t\n\f\r ]+/im, ' ')
+      text.gsub(/[\t\n\f\r ]+/, ' ')
     else
       text.force_encoding('WINDOWS-1252')
       trimmed_whitespace(text.encode('UTF-16be', invalid: :replace, replace: '?').encode('UTF-8'))
@@ -89,45 +91,36 @@ class Html2Text
   end
 
   def iterate_over(node)
-    return "\n" if node.name.downcase == 'br' && next_node_is_text?(node)
-
     return trimmed_whitespace(node.text) if node.text?
 
-    return '' if %w[style head title meta script].include?(node.name.downcase)
+    name = node.name&.downcase
 
-    return "\n#{DO_NOT_TOUCH_WHITESPACE}#{node.text}#{DO_NOT_TOUCH_WHITESPACE}" if node.name.downcase == 'pre'
+    return '' if name.nil? || IGNORED_TAGS.include?(name)
 
-    output = []
+    return "\n" if name == 'br' && next_node_is_text?(node)
 
-    output << prefix_whitespace(node)
-    output += node.children.map do |child|
-      iterate_over(child) unless child.name.nil?
-    end
-    output << suffix_whitespace(node)
+    return "\n#{DO_NOT_TOUCH_WHITESPACE}#{node.text}#{DO_NOT_TOUCH_WHITESPACE}" if name == 'pre'
 
-    output = output.compact.join || ''
+    return image_text(node) if name == 'img'
 
-    unless node.name.nil?
-      if node.name.downcase == 'a'
-        output = wrap_link(node, output)
-      elsif node.name.downcase == 'img'
-        output = image_text(node)
-      end
+    output = +''
+    output << (prefix_whitespace(node) || '')
+    node.children.each do |child|
+      output << iterate_over(child)
     end
+    output << (suffix_whitespace(node) || '')
+
+    output = wrap_link(node, output) if name == 'a'
 
     output
   end
 
-  # rubocop:disable Lint/DuplicateBranch
   def prefix_whitespace(node)
     case node.name.downcase
     when 'hr'
       "\n---------------------------------------------------------------\n"
 
-    when 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'ol', 'ul'
-      "\n\n"
-
-    when 'p'
+    when 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'ol', 'ul', 'p'
       "\n\n"
 
     when 'tr'
@@ -147,20 +140,15 @@ class Html2Text
       '- '
     end
   end
-  # rubocop:enable Lint/DuplicateBranch
 
-  # rubocop:disable Lint/DuplicateBranch
   def suffix_whitespace(node)
     case node.name.downcase
-    when 'h1', 'h2', 'h3', 'h4', 'h5', 'h6'
-      # add another line
-      "\n\n"
-
-    when 'p'
+    when 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'p'
       "\n\n"
 
     when 'br'
-      "\n" if next_node_name(node) != 'div' && !next_node_name(node).nil?
+      next_name = next_node_name(node)
+      "\n" if !next_name.nil? && next_name != 'div'
 
     when 'li'
       "\n"
@@ -168,14 +156,14 @@ class Html2Text
     when 'div'
       if next_node_is_text?(node)
         "\n"
-      elsif next_node_name(node) != 'div' && !next_node_name(node).nil?
-        "\n"
+      else
+        next_name = next_node_name(node)
+        "\n" if !next_name.nil? && next_name != 'div'
       end
     end
   end
-  # rubocop:enable Lint/DuplicateBranch
 
-  # links are returned in [text](link) format
+  # links are returned in [text](link) format, or "text: link" with wrap_links: false
   def wrap_link(node, output)
     href = node.attribute('href')
     name = node.attribute('name')
@@ -202,6 +190,8 @@ class Html2Text
          href != "http://#{output}" && href != "https://#{output}"
         output = if output.empty?
                    href
+                 elsif !@wrap_links
+                   "#{output}: #{href}"
                  else
                    "[#{output}](#{href})"
                  end

metadata

@@ -1,14 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: html2text
 version: !ruby/object:Gem::Version
-  version: 0.4.0
+  version: 0.5.0
 platform: ruby
 authors:
 - Jevon Wright
-autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-06-08 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -159,7 +158,6 @@ licenses:
 - MIT
 metadata:
   rubygems_mfa_required: 'true'
-post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -167,15 +165,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '3.0'
+      version: '3.3'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.9
-signing_key:
+rubygems_version: 4.0.10
 specification_version: 4
 summary: Convert HTML into plain text.
 test_files: []