isomorfeus-mailer 2.0.0.rc5 → 2.0.0.rc6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: acdfb3ac29ae4a9911dbe81277dfa854d5583a0ea34e18f30d6be89bfd112883
-  data.tar.gz: 454b85eee1fe78eb68192670c359a30bd991618121d297ce332a76c6a16dbf8f
+  metadata.gz: 98507154da2d33348d785c83bfec5f8260aa0fd93b945c8cbb6ae87f7f0391ce
+  data.tar.gz: 9a9255bb1f5dea7fd0b079db6e71ecd12db31ae7c0a0db5c941ad49439dcda3f
 SHA512:
-  metadata.gz: '06970e3cf619d462cf7ba1a561f0d95154f045486d91638c6a85ebd5597e7a9e9d5fad6b477120e443d84fdecc8c68eb5e3b434313d186ee4b433f8205f94d49'
-  data.tar.gz: 6b93557d0b8e1b8ab1e9692da4efa723c7785a18bfe4de201198b9468838c5637e55c43f1f6cfef146740e71ead0aa107d83b0e99a16ca388737c40813abae8b
+  metadata.gz: 68a4488a9a5aed3f102aa208c28f5ff084b7a6af9b08c7af6877b7695fed0b35d8f0396520e44d6916d5cea417c138978ba638b38ec483a4af37886d43ffb9c8
+  data.tar.gz: 7a0219c4a75ae76886ba4fc9ca8719413a1b1b8ec276c96b70ba21aa15c3c3b323e9c25dea979c7fc1b50a0dbd4497dc89269169ee5cb299b234996ef573ed8a

data/LICENSE

@@ -19,3 +19,7 @@ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.
+
+file lib/isomorfeus/html2text.rb originally taken from https://github.com/soundasleep/html2text_ruby:
+
+MIT License as above, Copyright 2015 Jevon Wright

data/lib/isomorfeus/html2text.rb

@@ -0,0 +1,268 @@
+class Html2Text
+  VERSION = "0.3.1"
+
+  attr_reader :doc
+
+  def initialize(doc)
+    @doc = doc
+  end
+
+  def self.convert(html)
+    html = html.to_s
+
+    if is_office_document?(html)
+      # Emulate the CSS rendering of Office documents
+      html = html.gsub("<p class=MsoNormal>", "<br>")
+        .gsub("<o:p>&nbsp;</o:p>", "<br>")
+        .gsub("<o:p></o:p>", "")
+    end
+
+    if !html.include?("<html")
+      # Stop Nokogiri from inserting in <p> tags
+      html = "<div>#{html}</div>"
+    end
+
+    html = fix_newlines(replace_entities(html))
+    doc = Nokogiri::HTML(html)
+
+    Html2Text.new(doc).convert
+  end
+
+  def self.fix_newlines(text)
+    text.gsub("\r\n", "\n").gsub("\r", "\n")
+  end
+
+  def self.replace_entities(text)
+    text.gsub("&nbsp;", " ").gsub("\u00a0", " ").gsub("&zwnj;", "")
+  end
+
+  def convert
+    output = iterate_over(doc)
+    output = remove_leading_and_trailing_whitespace(output)
+    output = remove_unnecessary_empty_lines(output)
+    return output.strip
+  end
+
+  DO_NOT_TOUCH_WHITESPACE = "<do-not-touch-whitespace>"
+
+  def remove_leading_and_trailing_whitespace(text)
+    # ignore any <pre> blocks, which we don't want to interact with
+    pre_blocks = text.split(DO_NOT_TOUCH_WHITESPACE)
+
+    output = []
+    pre_blocks.each.with_index do |block, index|
+      if index % 2 == 0
+        output << block.gsub(/[ \t]*\n[ \t]*/im, "\n").gsub(/ *\t */im, "\t")
+      else
+        output << block
+      end
+    end
+
+    output.join("")
+  end
+
+  private
+
+  def self.is_office_document?(text)
+    text.include?("urn:schemas-microsoft-com:office")
+  end
+
+  def remove_unnecessary_empty_lines(text)
+    text.gsub(/\n\n\n*/im, "\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, " ")
+    else
+      text.force_encoding("WINDOWS-1252")
+      return trimmed_whitespace(text.encode("UTF-16be", invalid: :replace, replace: "?").encode('UTF-8'))
+    end
+  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?
+
+    if ["style", "head", "title", "meta", "script"].include?(node.name.downcase)
+      return ""
+    end
+
+    if node.name.downcase == "pre"
+      return "\n#{DO_NOT_TOUCH_WHITESPACE}#{node.text}#{DO_NOT_TOUCH_WHITESPACE}"
+    end
+
+    output = []
+
+    output << prefix_whitespace(node)
+    output += node.children.map do |child|
+      if !child.name.nil?
+        iterate_over(child)
+      end
+    end
+    output << suffix_whitespace(node)
+
+    output = output.compact.join("") || ""
+
+    if !node.name.nil?
+      if node.name.downcase == "a"
+        output = wrap_link(node, output)
+      elsif node.name.downcase == "img"
+        output = image_text(node)
+      end
+    end
+
+    return output
+  end
+
+  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"
+        "\n\n"
+
+      when "tr"
+        "\n"
+
+      when "div"
+        if node.parent.name == "div" && (node.parent.text.strip == node.text.strip)
+          ""
+        else
+          "\n"
+        end
+
+      when "td", "th"
+        "\t"
+
+      when "li"
+        "- "
+    end
+  end
+
+  def suffix_whitespace(node)
+    case node.name.downcase
+      when "h1", "h2", "h3", "h4", "h5", "h6"
+        # add another line
+        "\n\n"
+
+      when "p"
+        "\n\n"
+
+      when "br"
+        if next_node_name(node) != "div" && next_node_name(node) != nil
+          "\n"
+        end
+
+      when "li"
+        "\n"
+
+      when "div"
+        if next_node_is_text?(node)
+          "\n"
+        elsif next_node_name(node) != "div" && next_node_name(node) != nil
+          "\n"
+        end
+    end
+  end
+
+  # links are returned in [text](link) format
+  def wrap_link(node, output)
+    href = node.attribute("href")
+    name = node.attribute("name")
+
+    output = output.strip
+
+    # remove double [[ ]]s from linking images
+    if output[0] == "[" && output[-1] == "]"
+      output = output[1, output.length - 2]
+
+      # for linking images, the title of the <a> overrides the title of the <img>
+      if node.attribute("title")
+        output = node.attribute("title").to_s
+      end
+    end
+
+    # if there is no link text, but a title attr
+    if output.empty? && node.attribute("title")
+      output = node.attribute("title").to_s
+    end
+
+    if href.nil?
+      if !name.nil?
+        output = "[#{output}]"
+      end
+    else
+      href = href.to_s
+
+      if href != output && href != "mailto:#{output}" &&
+          href != "http://#{output}" && href != "https://#{output}"
+        if output.empty?
+          output = href
+        else
+          output = "[#{output}](#{href})"
+        end
+      end
+    end
+
+    case next_node_name(node)
+      when "h1", "h2", "h3", "h4", "h5", "h6"
+        output += "\n"
+    end
+
+    output
+  end
+
+  def image_text(node)
+    if node.attribute("title")
+      "[" + node.attribute("title").to_s + "]"
+    elsif node.attribute("alt")
+      "[" + node.attribute("alt").to_s + "]"
+    else
+      ""
+    end
+  end
+
+  def next_node_name(node)
+    next_node = node.next_sibling
+    while next_node != nil
+      break if next_node.element?
+      next_node = next_node.next_sibling
+    end
+
+    if next_node && next_node.element?
+      next_node.name.downcase
+    end
+  end
+
+  def next_node_is_text?(node)
+    return !node.next_sibling.nil? && node.next_sibling.text? && !node.next_sibling.text.strip.empty?
+  end
+
+  def previous_node_name(node)
+    previous_node = node.previous_sibling
+    while previous_node != nil
+      break if previous_node.element?
+      previous_node = previous_node.previous_sibling
+    end
+
+    if previous_node && previous_node.element?
+      previous_node.name.downcase
+    end
+  end
+
+  def previous_node_is_text?(node)
+    return !node.previous_sibling.nil? && node.previous_sibling.text? && !node.previous_sibling.text.strip.empty?
+  end
+
+  # def previous_node_is_not_text?(node)
+  #   return node.previous_sibling.nil? || !node.previous_sibling.text? || node.previous_sibling.text.strip.empty?
+  # end
+end

data/lib/isomorfeus/mailer/version.rb

@@ -1,5 +1,5 @@
 module Isomorfeus
   module Mailer
-    VERSION = '2.0.0.rc5'
+    VERSION = '2.0.0.rc6'
   end
 end

data/lib/isomorfeus-mailer.rb

@@ -1,4 +1,5 @@
-require 'html2text'
+require 'nokogiri'
+require 'isomorfeus/html2text'
 require 'mailhandler'
 require 'isomorfeus-asset-manager'
 require 'isomorfeus-redux'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: isomorfeus-mailer
 version: !ruby/object:Gem::Version
-  version: 2.0.0.rc5
+  version: 2.0.0.rc6
 platform: ruby
 authors:
 - Jan Biedermann
@@ -24,20 +24,6 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '6.1'
-- !ruby/object:Gem::Dependency
-  name: html2text
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: 0.3.1
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: 0.3.1
 - !ruby/object:Gem::Dependency
   name: mailhandler
   requirement: !ruby/object:Gem::Requirement
@@ -142,28 +128,28 @@ dependencies:
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 2.0.0.rc5
+        version: 2.0.0.rc6
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 2.0.0.rc5
+        version: 2.0.0.rc6
 - !ruby/object:Gem::Dependency
   name: isomorfeus
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 2.0.0.rc5
+        version: 2.0.0.rc6
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 2.0.0.rc5
+        version: 2.0.0.rc6
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -192,6 +178,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 3.10.0
+- !ruby/object:Gem::Dependency
+  name: rspec-collection_matchers
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.2.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.2.0
 description: Write mail template components and send mail.
 email: jan@kursator.de
 executables: []
@@ -201,6 +201,7 @@ files:
 - LICENSE
 - README.md
 - lib/isomorfeus-mailer.rb
+- lib/isomorfeus/html2text.rb
 - lib/isomorfeus/mailer/config.rb
 - lib/isomorfeus/mailer/imports.rb
 - lib/isomorfeus/mailer/version.rb