Use nokogiri's HTML5 parser for text nodes (#129)

* use nokogiri's HTML5 parser for text nodes

* bump up version

CHANGELOG.md

@@ -18,6 +18,12 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 - None
 
+## 0.8.0
+
+### Dependencies
+
+- nokogiri >= 1.12.0 (was >= 1.10.0)
+
 ## 0.7.3
 
 ### Fixed

lib/odf-report/parser/default.rb

@@ -34,11 +34,9 @@ def initialize(text, template_node)
     end
 
     def parse
+      html = Nokogiri::HTML5.fragment(@text)
 
-      xml = @template_node.parse(@text)
-
-      xml.css("p", "h1", "h2").each do |p|
-
+      html.css("p", "h1", "h2").each do |p|
         style = check_style(p)
         text = parse_formatting(p.inner_html)
 
@@ -63,6 +61,7 @@ def parse_formatting(text)
       text.gsub!(/<strong.*?>(.+?)<\/strong>/)  { "<text:span text:style-name=\"bold\">#{$1}<\/text:span>" }
       text.gsub!(/<em.*?>(.+?)<\/em>/)          { "<text:span text:style-name=\"italic\">#{$1}<\/text:span>" }
       text.gsub!(/<u.*?>(.+?)<\/u>/)            { "<text:span text:style-name=\"underline\">#{$1}<\/text:span>" }
+      text.gsub!("<br\/?>", "<text:line-break/>")
       text.gsub!("\n", "")
       text
     end

lib/odf-report/version.rb

@@ -1,3 +1,3 @@
 module ODFReport
-  VERSION = "0.7.3"
+  VERSION = "0.8.0"
 end

odf-report.gemspec

@@ -25,7 +25,7 @@ Gem::Specification.new do |s|
   s.add_development_dependency "launchy"
 
   s.add_runtime_dependency('rubyzip', ">= 1.3.0")
-  s.add_runtime_dependency('nokogiri', ">= 1.10.0")
+  s.add_runtime_dependency('nokogiri', ">= 1.12.0")
   s.add_runtime_dependency('mime-types')
 
 end

spec/texts_spec.rb

@@ -0,0 +1,48 @@
+RSpec.describe "Texts" do
+   before(:context) do
+
+    @text1 = <<-HTML
+      <p>This is some text in a paragraph</p>
+    HTML
+
+    @text2 = <<-HTML
+      <p>Text before line break <br> text after line break</p>
+    HTML
+
+    @text3 = <<-HTML
+      <p>Text before entities
+         Maur&iacute;cio
+         Text after entities</p>
+    HTML
+
+
+    report = ODFReport::Report.new("spec/templates/specs.odt") do |r|
+
+      r.add_text(:text1, @text1)
+      r.add_text(:text2, @text2)
+      r.add_text(:text3, @text3)
+
+    end
+
+    report.generate("spec/result/specs.odt")
+
+    @data = Inspector.new("spec/result/specs.odt")
+
+  end
+
+  it "simple text replacement" do
+    expect(@data.text).to include "This is some text in a paragraph"
+  end
+
+  it "text replacement with <br>" do
+    expect(@data.text).to include "Text before line break"
+    expect(@data.text).to include "text after line break"
+  end
+
+  it "text replacement with html entities" do
+    expect(@data.text).to include "Text before entities"
+    expect(@data.text).to include "Maurício"
+    expect(@data.text).to include "Text after entities"
+  end
+
+end