qnd_html2page 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: cd082fe1f0ecffa42aa3f42ad0c8825aa71505d3c1dfb148cbfdc209c2871836
+  data.tar.gz: 507203ae52228dd19d1b68e554399c0fbfe4c4baf6fec969b46d515b28c1b937
+SHA512:
+  metadata.gz: 0f16a5c52a7afee1a6a3ea478a7fda44b6aef7950b75ad96d60fea5a4c838b4e4c10c681af8e2714ea5907686bb6d6a611296d4c5840f02195e0c592e7ccd37a
+  data.tar.gz: af07a61b492b13f794d7e4d5572bed280876434da1c95de6a96dc0612828384b7d90fe2dfdf7ac8490e8cfadeffddb373ae0f8054a5fc60df1e9193f135c190f

data/lib/qnd_html2page.rb

@@ -0,0 +1,97 @@
+#!/usr/bin/env ruby
+
+# file: qnd_html2page.rb
+
+require 'rexle'
+require 'ferrum'
+require 'tempfile'
+require 'rxfhelper'
+
+
+
+class QndHtml2Page
+
+  attr_reader :to_pages
+
+  def initialize(html, debug: false, pg_height: 676)
+
+    @html, @height, @debug = html, pg_height, debug
+    @to_pages = scan(RXFHelper.read(@html).first)
+
+  end
+
+  private
+
+  def scan(html)
+
+    # add the span tag after every element in the body
+
+    doc = Rexle.new(html)
+    body = doc.root.element('body')
+  
+    count = 0
+    body.each_recursive do |e|
+
+      puts 'e: ' + e.name if @debug
+      ignore_list = %w(span b li tr td dt dd em strong i a)
+      next if ignore_list.include? e.name
+      span = Rexle::Element.new('span').add_text(count.to_s)
+      span.attributes[:class] = 'qndhtml2pg'
+      e.insert_after span
+      count += 1
+
+    end
+
+    # Fetch the y coordinate of every span tag to determine the 
+    # elements that can fit into each page.
+
+    tmpfile = Tempfile.new('browser')
+    File.write tmpfile.path + '.html', doc.root.xml
+
+    browser = Ferrum::Browser.new
+    browser.goto('file://' + tmpfile.path + '.html')
+    span_list = browser.xpath('//span')
+    a = span_list.map {|x| [x.text, x.find_position.last] }
+
+    offset = 0
+
+    a2 = a.inject([[]]) do |r,x|
+
+      puts 'r: ' + x.inspect if @debug
+      puts 'x: ' + x.inspect if @debug
+      x.last < offset + @height ? (r.last << x) : (offset = x.last; r << [x])
+      r
+
+    end
+
+
+    elements = doc.root.element('body').elements.to_a
+    puts 'elements.length: ' + elements.length.inspect if @debug
+    offset = 0
+
+    puts 'a2: ' + a2.inspect if @debug
+
+    pages = a2.map do |x|
+
+      id = x.last.first
+
+      puts 'id: ' + id.inspect if @debug
+      puts 'offset: ' + offset.inspect if @debug
+
+      a3 = elements[offset..-1].take_while do |e| 
+        puts 'e.text: ' + e.text.inspect
+        e.text != id
+      end
+
+      offset = a3.length 
+      div = Rexle::Element.new 'div'
+      a3.reject! {|e| e.name == 'span' and e.attributes[:class] == 'qndhtml2pg' }
+      a3.each {|e| div.add e}
+      div
+    end
+
+    @to_pages = pages
+
+  end
+
+end

metadata

@@ -0,0 +1,90 @@
+--- !ruby/object:Gem::Specification
+name: qnd_html2page
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- James Robertson
+autorequire: 
+bindir: bin
+cert_chain:
+- |
+  -----BEGIN CERTIFICATE-----
+  MIIEXjCCAsagAwIBAgIBATANBgkqhkiG9w0BAQsFADAsMSowKAYDVQQDDCFnZW1t
+  YXN0ZXIvREM9amFtZXNyb2JlcnRzb24vREM9ZXUwHhcNMTkxMTE1MTAzMzE4WhcN
+  MjAxMTE0MTAzMzE4WjAsMSowKAYDVQQDDCFnZW1tYXN0ZXIvREM9amFtZXNyb2Jl
+  cnRzb24vREM9ZXUwggGiMA0GCSqGSIb3DQEBAQUAA4IBjwAwggGKAoIBgQDja3r/
+  qSzQNOzRg4qp9obwEq37YTr0gCLF5QCiAyjhfBqxv/OBPg7b+06PyOPShMkIbLYy
+  gnRhgzvDvDf2kpS/9ziE2bmOCp8MimWS0I0aT77qbEho6knw5BfEsPEZfG5oVtmy
+  au5iPivNst1sOKMTw6v2OMeiXx0a5fxZJtMnKr8/w46HKB3bpZ9m2+JDnx7cZ+Fh
+  RF0XTuQz79uHv1T+4oTU/DrBRqqlIASDVPmeyfOlkwTPQcPE875LclbDoBWz5vMT
+  kkTETVHbgB+D6i6mV9Sp896/noPP8JH84D+NvqgUppbRdUTiT+WnCFTV4ooJkACq
+  WC5twvtJuuvMOv7WsfsTqdZLJOm1g19JU9V7xYNxFbHQNHoLNomRKZ+NYjESkhVV
+  U4w4ILlvPHLfEPgeZlVGSa835XWabBwNVLXLUW/ZmlEQTz+u8isbtAk7kKbWaPUF
+  mEHhDcc2UG6l7uGe8E/jjOI8UufkuDFr/06QTf/azeu4AHWzGCG22MdhX3ECAwEA
+  AaOBijCBhzAJBgNVHRMEAjAAMAsGA1UdDwQEAwIEsDAdBgNVHQ4EFgQUNwHbSmuk
+  gigzYYMStlUkMnT8CzcwJgYDVR0RBB8wHYEbZ2VtbWFzdGVyQGphbWVzcm9iZXJ0
+  c29uLmV1MCYGA1UdEgQfMB2BG2dlbW1hc3RlckBqYW1lc3JvYmVydHNvbi5ldTAN
+  BgkqhkiG9w0BAQsFAAOCAYEADCXJFuzQ8G2QrTRxJUJiWZq8ayjfFHfhr5cqvxUy
+  ZZ6CsT02ffAU6W7116mIBTPLD1tS5ZAws8fJ3gs+vSLJAYTteUX2ykyJLlF+cjZz
+  i1T2z6R6VWPNAm4wcAdY96f3Dgq/2g3lq8xdwf26XITYFKGiqMnE9IGJ+J6V7+vr
+  szMrxeV30iUhoeSNuM57pdDIIMWbSLSavUeoqcuTYVa9zSqz5LBdk85ibf637NbT
+  A0dlTm3pbiomqQIVGoRr/Gj1Dz2/dHzndXS3k8hg4iIvrMLRymIghh7AZrJcMnpM
+  YSVGl4kHZBGFTnkgJEnyjA0FGgDJcyJEzQJyTWzjO3TkX8pYvwyKk6ILLBHANAIQ
+  IHFo8pGEa/bYN7Si64eTfNtXBnEHQC1A15AvXtzjsBtqIA2e1gsWCbG83s2M9GoC
+  iHadjaBK6nUXzIZ2OCEldp3dzkozgJxu7tcb1Kmr9uAUFoot4w6yl+Kr4JZIW1ml
+  u3jdsCCQLM9dC78qib2fY8vh
+  -----END CERTIFICATE-----
+date: 2019-11-15 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rxfhelper
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.9'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.9.4
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.9'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.9.4
+description: 
+email: james@jamesrobertson.eu
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/qnd_html2page.rb
+homepage: https://github.com/jrobertson/qnd_html2page
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.0.3
+signing_key: 
+specification_version: 4
+summary: Splits HTML into pages suitable for reading like a book.
+test_files: []