hlsv 1.0.0

data/lib/hlsv/html2word.rb

@@ -0,0 +1,602 @@
+# Copyright (c) 2026 AdClin
+# Licensed under the GNU Affero General Public License v3.0 or later.
+# See the LICENSE file for details.
+
+# Install:
+#   gem install nokogiri rubyzip
+#
+# Usage:
+#   ruby html_to_docx.rb input.html output.docx
+#   ruby html_to_docx.rb                          # uses defaults below
+
+require 'nokogiri'
+require 'zip'
+require 'time'
+
+FONT = 'Verdana'
+
+STATUS_COLORS = {
+  'success-box' => { prefix: '[OK]',      color: '2E7D32' },
+  'warning-box' => { prefix: '[WARNING]', color: 'E65100' },
+  'error-box'   => { prefix: '[ERROR]',   color: 'C62828' }
+}.freeze
+
+SPLIT_RE = / -- /
+
+module Hlsv
+
+# ---------------------------------------------------------------------------
+# Parser
+# ---------------------------------------------------------------------------
+class RiReportParser
+  Block = Struct.new(:type, :content, :meta, keyword_init: true)
+
+  def initialize(html_path)
+    html = File.read(html_path, encoding: 'UTF-8')
+    @doc = Nokogiri::HTML(html)
+    @html_path = html_path
+  end
+
+  def parse
+    blocks = []
+
+    h1   = @doc.at_css('header h1')
+    info = @doc.at_css('.info-box')
+
+    downloaded_at = Time.now.strftime('Downloaded on %Y-%m-%d at %H:%M')
+
+    # Structure : <div class="info-box"><div flex><p>date</p><button>📄 Word</button></div></div>
+    # target <p> to ignore the button
+    date_text = if info
+      p_tag = info.at_css('p')
+      p_tag ? p_tag.text.strip : begin
+        info.css('button, a').each(&:remove)
+        info.text.gsub(/[^\x00-\x7F]/, '').gsub(/\s+/, ' ').strip
+      end
+    else
+      ''
+    end
+
+    blocks << Block.new(type: :cover,
+                        content: { title:         h1&.text&.strip.to_s,
+                                   date:          date_text,
+                                   downloaded_at: downloaded_at },
+                        meta: {})
+
+    blocks << Block.new(type: :toc, content: nil, meta: {})
+
+    main = @doc.at_css('main.container') || @doc.at_css('main')
+    return blocks unless main
+
+    main.children.each do |node|
+      next if node.text? && node.text.strip.empty?
+      next if node['class']&.include?('info-box')
+      blocks.concat(parse_node(node))
+    end
+
+    blocks
+  end
+
+  private
+
+  def split_to_labeled_list(text, color)
+    parts = text.split(SPLIT_RE).map(&:strip).reject(&:empty?)
+    return nil if parts.size < 2
+    Block.new(type: :list,
+              content: parts[1..],
+              meta: { color: color, label: parts.first })
+  end
+
+  def parse_node(node)
+    blocks = []
+    tag = node.name.downcase
+
+    case tag
+    when 'h1'
+      t = node.text.strip
+      blocks << Block.new(type: :h2, content: t, meta: {}) unless t.empty?
+
+    when 'h2'
+      t = node.text.strip
+      blocks << Block.new(type: :h2, content: t, meta: {}) unless t.empty?
+
+    when 'h3', 'h4', 'h5', 'h6'
+      t = node.text.strip
+      blocks << Block.new(type: :h3, content: t, meta: {}) unless t.empty?
+
+    when 'article'
+      css_classes = (node['class'] || '').split
+      if css_classes.include?('dataset-section')
+        sub_blocks = []
+        node.children.each do |child|
+          next if child.text? && child.text.strip.empty?
+          sub_blocks.concat(parse_node(child))
+        end
+        sub_blocks.each_with_index do |blk, idx|
+          last = (idx == sub_blocks.size - 1)
+          blk.meta.merge!(keep_lines: true, keep_next: !last)
+        end
+        blocks.concat(sub_blocks)
+        return blocks
+      end
+      node.children.each do |child|
+        next if child.text? && child.text.strip.empty?
+        blocks.concat(parse_node(child))
+      end
+
+    when 'section', 'div'
+      css_classes = (node['class'] || '').split
+      status_cfg  = css_classes.map { |c| STATUS_COLORS[c] }.compact.first
+
+      if status_cfg
+        color  = status_cfg[:color]
+        prefix = status_cfg[:prefix]
+        title  = node.at_css('strong')&.text&.strip.to_s
+        label  = "#{prefix} #{title}".strip
+
+        details = []
+        node.css('p').each  { |p|  details << clean(p) }
+        node.css('li').each { |li| details << clean(li) }
+        details.reject!(&:empty?)
+
+        if details.any?
+          blocks << Block.new(type: :list,
+                              content: details,
+                              meta: { color: color, label: label })
+        else
+          blocks << Block.new(type: :status, content: label, meta: { color: color })
+        end
+      else
+        node.children.each do |child|
+          next if child.text? && child.text.strip.empty?
+          blocks.concat(parse_node(child))
+        end
+      end
+
+    when 'p'
+      t = clean(node)
+      unless t.empty?
+        lb = split_to_labeled_list(t, '000000')
+        blocks << (lb || Block.new(type: :paragraph, content: t, meta: {}))
+      end
+
+    when 'ul', 'ol'
+      items = node.css('> li').map { |li| clean(li) }.reject(&:empty?)
+      blocks << Block.new(type: :list,
+                          content: items,
+                          meta: { color: '000000' }) unless items.empty?
+    end
+
+    blocks
+  end
+
+  def clean(node)
+    node.text.gsub(/\s+/, ' ').strip
+  end
+end
+
+# ---------------------------------------------------------------------------
+# OOXML Builder
+# ---------------------------------------------------------------------------
+module OoxmlBuilder
+  def self.x(str)
+    str.to_s
+       .gsub('&', '&amp;')
+       .gsub('<', '&lt;')
+       .gsub('>', '&gt;')
+       .gsub('"', '&quot;')
+  end
+
+  def self.page_break
+    "<w:p><w:r><w:br w:type=\"page\"/></w:r></w:p>"
+  end
+
+  # Construit le <w:pPr> avec les options communes
+  def self.build_ppr(opts = {})
+    style        = opts[:style]
+    align        = opts[:align]
+    space_before = opts[:space_before] || 0
+    space_after  = opts[:space_after]  || 80
+    keep_lines   = opts[:keep_lines]   || false
+    keep_next    = opts[:keep_next]    || false
+
+    inner  = ''
+    inner += "<w:pStyle w:val=\"#{style}\"/>"    if style
+    inner += '<w:keepNext/>'                      if keep_next
+    inner += '<w:keepLines/>'                     if keep_lines
+    inner += "<w:spacing w:before=\"#{space_before}\" w:after=\"#{space_after}\"/>"
+    inner += "<w:jc w:val=\"#{align}\"/>"         if align
+    "<w:pPr>#{inner}</w:pPr>"
+  end
+
+  # Paragraphe générique
+  def self.paragraph(text, opts = {})
+    sz    = opts[:sz]    || 20
+    bold  = opts[:bold]  || false
+    color = opts[:color] || '000000'
+    ppr   = build_ppr(opts)
+
+    rpr  = "<w:rFonts w:ascii=\"#{FONT}\" w:hAnsi=\"#{FONT}\" w:cs=\"#{FONT}\"/>"
+    rpr += "<w:sz w:val=\"#{sz}\"/><w:szCs w:val=\"#{sz}\"/>"
+    rpr += '<w:b/><w:bCs/>' if bold
+    rpr += "<w:color w:val=\"#{color}\"/>"
+
+    "<w:p>#{ppr}<w:r><w:rPr>#{rpr}</w:rPr><w:t xml:space=\"preserve\">#{x(text)}</w:t></w:r></w:p>"
+  end
+
+  # Paragraphe avec style Word nommé
+  def self.heading(text, opts = {})
+    ppr = build_ppr(opts)
+    "<w:p>#{ppr}<w:r><w:t xml:space=\"preserve\">#{x(text)}</w:t></w:r></w:p>"
+  end
+
+  # Paragraphe coloré pour les statuts
+  def self.status_paragraph(text, opts = {})
+    color = opts[:color] || '000000'
+    ppr   = build_ppr(opts.merge(space_before: 0, space_after: 80))
+    rpr   = "<w:rFonts w:ascii=\"#{FONT}\" w:hAnsi=\"#{FONT}\" w:cs=\"#{FONT}\"/>"
+    rpr  += "<w:color w:val=\"#{color}\"/><w:sz w:val=\"20\"/><w:szCs w:val=\"20\"/>"
+    "<w:p>#{ppr}<w:r><w:rPr>#{rpr}</w:rPr><w:t xml:space=\"preserve\">#{x(text)}</w:t></w:r></w:p>"
+  end
+
+  # Item de liste à puces
+  def self.list_item(text, opts = {})
+    color      = opts[:color]      || '000000'
+    sz         = opts[:sz]         || 20
+    keep_lines = opts[:keep_lines] || false
+    keep_next  = opts[:keep_next]  || false
+    kl = keep_lines ? '<w:keepLines/>' : ''
+    kn = keep_next  ? '<w:keepNext/>'  : ''
+
+    rpr  = "<w:rFonts w:ascii=\"#{FONT}\" w:hAnsi=\"#{FONT}\" w:cs=\"#{FONT}\"/>"
+    rpr += "<w:sz w:val=\"#{sz}\"/><w:szCs w:val=\"#{sz}\"/><w:color w:val=\"#{color}\"/>"
+
+    <<~XML
+      <w:p>
+        <w:pPr>
+          #{kl}#{kn}
+          <w:numPr><w:ilvl w:val="0"/><w:numId w:val="1"/></w:numPr>
+          <w:spacing w:before="0" w:after="60"/>
+        </w:pPr>
+        <w:r><w:rPr>#{rpr}</w:rPr><w:t xml:space="preserve">#{x(text)}</w:t></w:r>
+      </w:p>
+    XML
+  end
+
+  # ── Footer Word ────────────────────────────────────────────────────────────
+  # Deux zones séparées par une tabulation centrale/droite :
+  #   gauche  : titre du document
+  #   droite  : PAGE / NUMPAGES  (champs Word natifs)
+  #
+  # Les champs PAGE et NUMPAGES sont insérés via <w:fldChar> / <w:instrText>
+  # — mécanisme identique à la TOC, sans dépendance externe.
+  def self.footer_xml(doc_title)
+    rpr_base = "<w:rFonts w:ascii=\"#{FONT}\" w:hAnsi=\"#{FONT}\" w:cs=\"#{FONT}\"/>" \
+               "<w:sz w:val=\"18\"/><w:szCs w:val=\"18\"/><w:color w:val=\"666666\"/>"
+
+    # Champ PAGE
+    page_field = <<~XML
+      <w:r><w:rPr>#{rpr_base}</w:rPr><w:fldChar w:fldCharType="begin"/></w:r>
+      <w:r><w:rPr>#{rpr_base}</w:rPr><w:instrText xml:space="preserve"> PAGE </w:instrText></w:r>
+      <w:r><w:rPr>#{rpr_base}</w:rPr><w:fldChar w:fldCharType="separate"/></w:r>
+      <w:r><w:rPr>#{rpr_base}</w:rPr><w:t>1</w:t></w:r>
+      <w:r><w:rPr>#{rpr_base}</w:rPr><w:fldChar w:fldCharType="end"/></w:r>
+    XML
+
+    # Champ NUMPAGES
+    numpages_field = <<~XML
+      <w:r><w:rPr>#{rpr_base}</w:rPr><w:fldChar w:fldCharType="begin"/></w:r>
+      <w:r><w:rPr>#{rpr_base}</w:rPr><w:instrText xml:space="preserve"> NUMPAGES </w:instrText></w:r>
+      <w:r><w:rPr>#{rpr_base}</w:rPr><w:fldChar w:fldCharType="separate"/></w:r>
+      <w:r><w:rPr>#{rpr_base}</w:rPr><w:t>1</w:t></w:r>
+      <w:r><w:rPr>#{rpr_base}</w:rPr><w:fldChar w:fldCharType="end"/></w:r>
+    XML
+
+    <<~XML
+      <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+      <w:ftr xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
+        <w:p>
+          <w:pPr>
+            <w:spacing w:before="80" w:after="0"/>
+            <w:pBdr>
+              <w:top w:val="single" w:sz="6" w:space="1" w:color="CCCCCC"/>
+            </w:pBdr>
+            <w:tabs>
+              <w:tab w:val="right" w:pos="9360"/>
+            </w:tabs>
+          </w:pPr>
+          <w:r><w:rPr>#{rpr_base}</w:rPr><w:t xml:space="preserve">#{x(doc_title)}</w:t></w:r>
+          <w:r><w:rPr>#{rpr_base}</w:rPr><w:tab/></w:r>
+          #{page_field.strip}
+          <w:r><w:rPr>#{rpr_base}</w:rPr><w:t xml:space="preserve"> / </w:t></w:r>
+          #{numpages_field.strip}
+        </w:p>
+      </w:ftr>
+    XML
+  end
+
+  # Page de couverture
+  def self.cover_page(title:, date:, downloaded_at:)
+    title_para = paragraph(title,
+                           sz: 44, bold: true, color: '1F3864',
+                           align: 'right',
+                           space_before: 2880, space_after: 120)
+    hr = <<~XML
+      <w:p>
+        <w:pPr>
+          <w:jc w:val="right"/>
+          <w:pBdr><w:bottom w:val="single" w:sz="12" w:space="1" w:color="2E75B6"/></w:pBdr>
+          <w:spacing w:before="0" w:after="120"/>
+        </w:pPr>
+      </w:p>
+    XML
+    date_para        = paragraph(date,         sz: 20, color: '444444', align: 'right',
+                                 space_before: 0, space_after: 0)
+    downloaded_para  = paragraph(downloaded_at, sz: 20, color: '444444', align: 'right',
+                                 space_before: 0, space_after: 0)
+    title_para + hr + date_para + downloaded_para + page_break
+  end
+
+  # TOC sur sa propre page
+  def self.toc_field
+    toc_title = heading('Table of Contents',
+                        style: 'Heading1', space_before: 0, space_after: 160)
+    toc_content = <<~'XML'
+      <w:p>
+        <w:pPr><w:spacing w:before="0" w:after="80"/></w:pPr>
+        <w:r><w:fldChar w:fldCharType="begin"/></w:r>
+        <w:r><w:instrText xml:space="preserve"> TOC \o "1-3" \h \z \u </w:instrText></w:r>
+        <w:r><w:fldChar w:fldCharType="separate"/></w:r>
+        <w:r>
+          <w:rPr><w:color w:val="888888"/></w:rPr>
+          <w:t>Right-click and select "Update Field" to generate the table of contents.</w:t>
+        </w:r>
+        <w:r><w:fldChar w:fldCharType="end"/></w:r>
+      </w:p>
+    XML
+    toc_title + toc_content + page_break
+  end
+
+  # Corps du document
+  def self.document(blocks)
+    paras = blocks.map do |b|
+      m = b.meta
+
+      case b.type
+      when :cover
+        cover_page(title: b.content[:title], date: b.content[:date], downloaded_at: b.content[:downloaded_at].to_s)
+
+      when :toc
+        toc_field
+
+      when :h2
+        heading(b.content,
+                style: 'Heading2', space_before: 280, space_after: 120,
+                keep_lines: m[:keep_lines], keep_next: m[:keep_next])
+
+      when :h3
+        heading(b.content,
+                style: 'Heading3', space_before: 200, space_after: 80,
+                keep_lines: m[:keep_lines], keep_next: m[:keep_next])
+
+      when :paragraph
+        paragraph(b.content, sz: 20, color: '000000',
+                  keep_lines: m[:keep_lines], keep_next: m[:keep_next])
+
+      when :status
+        status_paragraph(b.content,
+                         color: m[:color] || '000000',
+                         keep_lines: m[:keep_lines], keep_next: m[:keep_next])
+
+      when :list
+        color = m[:color] || '000000'
+        label = m[:label]
+        kl    = m[:keep_lines] || false
+        kn    = m[:keep_next]  || false
+
+        out  = ''
+        out += status_paragraph(label, color: color, keep_lines: kl, keep_next: true) if label
+        out += b.content.each_with_index.map do |item, idx|
+          item_kn = (idx == b.content.size - 1) ? kn : true
+          list_item(item, color: color, keep_lines: kl, keep_next: item_kn)
+        end.join
+        out
+      end
+    end.join("\n")
+
+    <<~XML
+      <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+      <w:document
+        xmlns:mc="http://schemas.openxmlformats.org/markup-compatibility/2006"
+        xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships"
+        xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"
+        xmlns:w14="http://schemas.microsoft.com/office/word/2010/wordml"
+        mc:Ignorable="w14">
+        <w:body>
+          #{paras}
+          <w:sectPr>
+            <w:footerReference w:type="default" r:id="rId11"/>
+            <w:pgSz w:w="12240" w:h="15840"/>
+            <w:pgMar w:top="1080" w:right="1080" w:bottom="1080" w:left="1080"
+                     w:header="720" w:footer="720" w:gutter="0"/>
+          </w:sectPr>
+        </w:body>
+      </w:document>
+    XML
+  end
+
+  def self.styles
+    <<~XML
+      <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+      <w:styles xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
+        <w:style w:type="paragraph" w:default="1" w:styleId="Normal">
+          <w:name w:val="Normal"/>
+          <w:rPr>
+            <w:rFonts w:ascii="#{FONT}" w:hAnsi="#{FONT}" w:cs="#{FONT}"/>
+            <w:sz w:val="20"/><w:szCs w:val="20"/><w:color w:val="000000"/>
+          </w:rPr>
+        </w:style>
+        <w:style w:type="paragraph" w:styleId="Heading1">
+          <w:name w:val="heading 1"/><w:basedOn w:val="Normal"/><w:next w:val="Normal"/>
+          <w:pPr><w:outlineLvl w:val="0"/></w:pPr>
+          <w:rPr>
+            <w:rFonts w:ascii="#{FONT}" w:hAnsi="#{FONT}" w:cs="#{FONT}"/>
+            <w:b/><w:bCs/><w:sz w:val="40"/><w:szCs w:val="40"/><w:color w:val="1F3864"/>
+          </w:rPr>
+        </w:style>
+        <w:style w:type="paragraph" w:styleId="Heading2">
+          <w:name w:val="heading 2"/><w:basedOn w:val="Normal"/><w:next w:val="Normal"/>
+          <w:pPr><w:outlineLvl w:val="1"/></w:pPr>
+          <w:rPr>
+            <w:rFonts w:ascii="#{FONT}" w:hAnsi="#{FONT}" w:cs="#{FONT}"/>
+            <w:b/><w:bCs/><w:sz w:val="30"/><w:szCs w:val="30"/><w:color w:val="2E75B6"/>
+          </w:rPr>
+        </w:style>
+        <w:style w:type="paragraph" w:styleId="Heading3">
+          <w:name w:val="heading 3"/><w:basedOn w:val="Normal"/><w:next w:val="Normal"/>
+          <w:pPr><w:outlineLvl w:val="2"/></w:pPr>
+          <w:rPr>
+            <w:rFonts w:ascii="#{FONT}" w:hAnsi="#{FONT}" w:cs="#{FONT}"/>
+            <w:b/><w:bCs/><w:sz w:val="24"/><w:szCs w:val="24"/><w:color w:val="404040"/>
+          </w:rPr>
+        </w:style>
+      </w:styles>
+    XML
+  end
+
+  def self.numbering
+    <<~XML
+      <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+      <w:numbering xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
+        <w:abstractNum w:abstractNumId="0">
+          <w:lvl w:ilvl="0">
+            <w:start w:val="1"/><w:numFmt w:val="bullet"/>
+            <w:lvlText w:val="&#x2022;"/><w:lvlJc w:val="left"/>
+            <w:pPr><w:ind w:left="720" w:hanging="360"/></w:pPr>
+            <w:rPr><w:rFonts w:ascii="#{FONT}" w:hAnsi="#{FONT}" w:cs="#{FONT}"/></w:rPr>
+          </w:lvl>
+        </w:abstractNum>
+        <w:num w:numId="1"><w:abstractNumId w:val="0"/></w:num>
+      </w:numbering>
+    XML
+  end
+
+  def self.content_types
+    <<~XML
+      <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+      <Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">
+        <Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/>
+        <Default Extension="xml"  ContentType="application/xml"/>
+        <Override PartName="/word/document.xml"
+          ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/>
+        <Override PartName="/word/styles.xml"
+          ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.styles+xml"/>
+        <Override PartName="/word/numbering.xml"
+          ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.numbering+xml"/>
+        <Override PartName="/word/settings.xml"
+          ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.settings+xml"/>
+        <Override PartName="/word/footer1.xml"
+          ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.footer+xml"/>
+      </Types>
+    XML
+  end
+
+  def self.rels
+    <<~XML
+      <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+      <Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
+        <Relationship Id="rId1"
+          Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument"
+          Target="word/document.xml"/>
+      </Relationships>
+    XML
+  end
+
+  # Relations du document : styles, numbering, settings, header, footer
+  def self.word_rels
+    <<~XML
+      <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+      <Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
+        <Relationship Id="rId1"
+          Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles"
+          Target="styles.xml"/>
+        <Relationship Id="rId2"
+          Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/numbering"
+          Target="numbering.xml"/>
+        <Relationship Id="rId3"
+          Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/settings"
+          Target="settings.xml"/>
+        <Relationship Id="rId11"
+          Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/footer"
+          Target="footer1.xml"/>
+      </Relationships>
+    XML
+  end
+
+  def self.empty_rels
+    <<~XML
+      <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+      <Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
+      </Relationships>
+    XML
+  end
+
+  def self.settings
+    <<~XML
+      <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+      <w:settings xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
+        <w:updateFields w:val="true"/>
+        <w:defaultTabStop w:val="720"/>
+      </w:settings>
+    XML
+  end
+end
+
+# ---------------------------------------------------------------------------
+# DOCX Writer
+# ---------------------------------------------------------------------------
+class DocxWriter
+  def initialize(output_path)
+    @output_path = output_path
+  end
+
+  def write(blocks)
+    cover_block = blocks.find { |b| b.type == :cover }
+    doc_title   = cover_block&.content&.dig(:title).to_s
+
+    ::Zip::OutputStream.open(@output_path) do |zip|
+      add_xml(zip, '[Content_Types].xml',          OoxmlBuilder.content_types)
+      add_xml(zip, '_rels/.rels',                  OoxmlBuilder.rels)
+      add_xml(zip, 'word/document.xml',            OoxmlBuilder.document(blocks))
+      add_xml(zip, 'word/styles.xml',              OoxmlBuilder.styles)
+      add_xml(zip, 'word/numbering.xml',           OoxmlBuilder.numbering)
+      add_xml(zip, 'word/settings.xml',            OoxmlBuilder.settings)
+      add_xml(zip, 'word/_rels/document.xml.rels', OoxmlBuilder.word_rels)
+      add_xml(zip, 'word/footer1.xml',             OoxmlBuilder.footer_xml(doc_title))
+      add_xml(zip, 'word/_rels/footer1.xml.rels',  OoxmlBuilder.empty_rels)
+    end
+  end
+
+  private
+
+  def add_xml(zip, name, content)
+    zip.put_next_entry(name)
+    zip.write(content.encode('UTF-8'))
+  end
+end
+end
+# ---------------------------------------------------------------------------
+# Main
+# ---------------------------------------------------------------------------
+# INPUT_FILE  = ARGV[0] || '../hlsv_results/RI/RI_key_search.html'
+# OUTPUT_FILE = ARGV[1] || "#{File.dirname(INPUT_FILE)}/RI_key_search.docx"
+
+# abort "ERROR: File not found -- #{INPUT_FILE}" unless File.exist?(INPUT_FILE)
+
+# puts "Parsing #{INPUT_FILE}..."
+# blocks = RiReportParser.new(INPUT_FILE).parse
+# puts "  -> #{blocks.size} blocks extracted"
+
+# puts "Building #{OUTPUT_FILE}..."
+# DocxWriter.new(OUTPUT_FILE).write(blocks)
+# puts "  -> Done: #{OUTPUT_FILE}"