writebook_pdf_import 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 88b01c32f19a3690d72cd2cafee6aa8c71812925ff9933b30cf59df2fad28955
+  data.tar.gz: 9c73f0631abd8805a496ac6ce7e392e14ba9a688a96ab9626e3eb1869588f966
+SHA512:
+  metadata.gz: 2285f57116079a0b1d332ae9ba686200e216acbc21716d7e384c3213111aded0ee8e4879849833a7d9805c3314f699f74852fc52e34e77333e35b2180ce5285e
+  data.tar.gz: caeeadbaa938ec8bc637592d92d746ef13b989d66523607f7c76b257880c37546014badf3cf6903ffe0d6bfec966560da5a27c9047e575f6cea6331a05e2f967

data/MIT-LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 albertski
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+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.

data/README.md

@@ -0,0 +1,38 @@
+# WritebookPdfImport
+
+A Rails engine that adds PDF import support to [Writebook](https://once.com/writebook). It parses a PDF and creates `Page` and `Picture` leaves in a book.
+
+## Usage
+
+An **Import PDF** button is added to the book page, allowing you to upload a PDF directly from the Writebook interface.
+
+![Import PDF button on the book page](docs/import_pdf.png)
+
+## Installation
+
+Add to your `Gemfile`:
+
+```ruby
+gem "writebook_pdf_import"
+```
+
+## What it does
+
+- Extracts text from each PDF page and creates a `Page` leaf
+- Extracts embedded images (JPEG, JPEG 2000, raw RGB/grayscale/CMYK) and creates `Picture` leaves
+- Uses the first line of text as the page title if it's 3–100 characters, otherwise falls back to "Page #"
+- Skips blank pages
+
+## Dependencies
+
+- `pdf-reader ~> 2.12`
+- `mini_magick` (for JPEG 2000 and raw image conversion)
+- ImageMagick must be installed on the system
+
+## Background Jobs
+
+PDF imports are processed asynchronously using Active Job. You must have Redis and a Solid Queue worker running:
+
+```bash
+redis-server
+```

data/app/assets/javascripts/writebook_pdf_import/dialog_morph_controller.js

@@ -0,0 +1,22 @@
+import { Controller } from "@hotwired/stimulus"
+
+export default class extends Controller {
+  connect() {
+    document.addEventListener("turbo:before-morph-element", this._closeOnMorph)
+  }
+
+  disconnect() {
+    document.removeEventListener("turbo:before-morph-element", this._closeOnMorph)
+  }
+
+  _closeOnMorph = (event) => {
+    if (
+      event.target === this.element &&
+      this.element.open &&
+      event.detail.newElement &&
+      !event.detail.newElement.hasAttribute("open")
+    ) {
+      this.element.close()
+    }
+  }
+}

data/app/controllers/books/imports_controller.rb

@@ -0,0 +1,49 @@
+class Books::ImportsController < ApplicationController
+  include BookScoped
+
+  before_action :ensure_editable
+
+  MAX_FILE_SIZE = 500.megabytes
+
+  def create
+    return unless valid_pdf?(params[:pdf])
+
+    PdfImportJob.perform_later(@book, upload_pdf(params[:pdf]))
+
+    respond_to do |format|
+      format.turbo_stream do
+        render turbo_stream: turbo_stream.update(
+          helpers.dom_id(@book, :pdf_import_body),
+          partial: "books/imports/progress",
+          locals: { percent: 0 }
+        )
+      end
+      format.html { redirect_to book_slug_url(@book), notice: "PDF import started. Pages will appear shortly." }
+    end
+  rescue => e
+    Rails.logger.error("PDF import enqueue failed: #{e.class}: #{e.message}")
+    redirect_to book_slug_url(@book), alert: "Could not import PDF."
+  end
+
+  private
+
+  def valid_pdf?(file)
+    if file.blank? || file.content_type != "application/pdf"
+      redirect_to book_slug_url(@book), alert: "Could not import PDF." and return false
+    end
+
+    if file.size > MAX_FILE_SIZE
+      redirect_to book_slug_url(@book), alert: "PDF exceeds the #{MAX_FILE_SIZE / 1.megabyte}MB size limit." and return false
+    end
+
+    true
+  end
+
+  def upload_pdf(file)
+    ActiveStorage::Blob.create_and_upload!(
+      io: file,
+      filename: file.original_filename,
+      content_type: "application/pdf"
+    )
+  end
+end

data/app/jobs/pdf_import_job.rb

@@ -0,0 +1,30 @@
+class PdfImportJob < ApplicationJob
+  include ActionView::RecordIdentifier
+
+  queue_as :default
+
+  def perform(book, blob)
+    blob.open do |file|
+      PdfImporter.new(book, file).import do |current, total|
+        percent = (current.to_f / total * 100).floor
+        broadcast_progress(book, percent)
+      end
+    end
+  rescue PdfImporter::InvalidPdfError, ArgumentError => e
+    Rails.logger.error("PdfImportJob failed for book #{book.id}: #{e.class}: #{e.message}")
+  ensure
+    blob.purge
+    Turbo::StreamsChannel.broadcast_refresh_to(book, "pdf_import")
+  end
+
+  private
+
+    def broadcast_progress(book, percent)
+      Turbo::StreamsChannel.broadcast_update_to(
+        book, "pdf_import",
+        target: dom_id(book, :pdf_import_body),
+        partial: "books/imports/progress",
+        locals: { percent: percent }
+      )
+    end
+end

data/app/models/pdf_importer.rb

@@ -0,0 +1,36 @@
+class PdfImporter
+  class InvalidPdfError < StandardError; end
+
+  def initialize(book, pdf_io)
+    raise InvalidPdfError, "No PDF file provided" if pdf_io.blank?
+    @book = book
+    @reader = PDF::Reader.new(pdf_io)
+  rescue PDF::Reader::MalformedPDFError, PDF::Reader::UnsupportedFeatureError => e
+    raise InvalidPdfError, e.message
+  end
+
+  def import
+    total = @reader.page_count
+    ActiveRecord::Base.transaction do
+      @reader.pages.each_with_index.flat_map do |raw_page, index|
+        parsed = PdfPage.new(raw_page, index + 1)
+        leaves = parsed.blank? ? [] : leaves_for(parsed)
+        yield index + 1, total if block_given?
+        leaves
+      end
+    end
+  end
+
+  private
+
+    def leaves_for(pdf_page)
+      leaves = []
+      leaves << @book.press(Page.new(body: pdf_page.body), title: pdf_page.title) if pdf_page.body.present?
+      pdf_page.pictures.each do |attachment|
+        picture = Picture.new
+        picture.image.attach(attachment)
+        leaves << @book.press(picture, title: pdf_page.title)
+      end
+      leaves
+    end
+end

data/app/models/pdf_page.rb

@@ -0,0 +1,30 @@
+class PdfPage
+  MIN_TITLE_LENGTH = 3
+  MAX_TITLE_LENGTH = 100
+
+  attr_reader :pictures
+
+  def initialize(page, page_number)
+    @page = page
+    @page_number = page_number
+    @text = page.text.strip
+    @pictures = PdfPicture.extract_from(page)
+  end
+
+  def blank?
+    @text.blank? && @pictures.empty?
+  end
+
+  def title
+    first_line = @text.lines.first&.strip
+    if first_line.present? && first_line.length.between?(MIN_TITLE_LENGTH, MAX_TITLE_LENGTH)
+      first_line
+    else
+      "Page #{@page_number}"
+    end
+  end
+
+  def body
+    @text.gsub(/\n{3,}/, "\n\n").strip
+  end
+end

data/app/models/pdf_picture.rb

@@ -0,0 +1,80 @@
+class PdfPicture
+  COLORSPACE_MAP = { DeviceRGB: "rgb", DeviceGray: "gray", DeviceCMYK: "cmyk" }.freeze
+
+  def self.extract_from(page)
+    new(page).extract
+  end
+
+  def initialize(page)
+    @source = page
+  end
+
+  def extract
+    @source.xobjects.flat_map do |name, stream|
+      stream.hash[:Subtype] == :Image ? [ attachment_for(stream, name) ].compact : []
+    end
+  rescue => e
+    Rails.logger.warn "PDF picture extraction failed (#{e.class}): #{e.message}"
+    []
+  end
+
+  private
+    def attachment_for(stream, name)
+      filter = Array(stream.hash[:Filter]).first
+
+      case filter
+      when :DCTDecode then jpeg_attachment(stream, name)
+      when :JPXDecode then jp2_to_jpeg(stream, name)
+      else                 raw_to_png(stream, name)
+      end
+    rescue => e
+      Rails.logger.warn "PDF picture attachment failed for #{name} (#{e.class}): #{e.message}"
+      nil
+    end
+
+    def jpeg_attachment(stream, name)
+      { io: StringIO.new(stream.data), filename: "#{name}.jpg", content_type: "image/jpeg" }
+    end
+
+    def jp2_to_jpeg(stream, name)
+      jpeg_data = Tempfile.create([ name.to_s, ".jp2" ], binmode: true) do |f|
+        f.write(stream.data)
+        f.flush
+        MiniMagick::Tool::Convert.new do |cmd|
+          cmd << f.path
+          cmd << "jpeg:-"
+        end
+      end
+
+      { io: StringIO.new(jpeg_data), filename: "#{name}.jpg", content_type: "image/jpeg" }
+    rescue => e
+      Rails.logger.warn "PDF JP2 conversion failed for #{name} (#{e.class}): #{e.message}"
+      nil
+    end
+
+    def raw_to_png(stream, name)
+      width      = stream.hash[:Width]
+      height     = stream.hash[:Height]
+      bit_depth  = stream.hash[:BitsPerComponent] || 8
+      colorspace = COLORSPACE_MAP[stream.hash[:ColorSpace]]
+
+      return nil unless width && height && colorspace
+
+      png_data = Tempfile.create([ name.to_s, ".raw" ], binmode: true) do |raw_file|
+        raw_file.write(stream.unfiltered_data)
+        raw_file.flush
+
+        MiniMagick::Tool::Convert.new do |cmd|
+          cmd.size "#{width}x#{height}"
+          cmd.depth bit_depth.to_s
+          cmd << "#{colorspace}:#{raw_file.path}"
+          cmd << "png:-"
+        end
+      end
+
+      { io: StringIO.new(png_data), filename: "#{name}.png", content_type: "image/png" }
+    rescue => e
+      Rails.logger.warn "PDF raw picture conversion failed for #{name} (#{e.class}): #{e.message}"
+      nil
+    end
+end

data/app/views/books/imports/_import.html.erb

@@ -0,0 +1,52 @@
+<%= turbo_stream_from book, "pdf_import" %>
+
+<style>
+  [data-show-on-upload] { display: none; }
+  form[aria-busy="true"] [data-hide-on-upload] { display: none; }
+  form[aria-busy="true"] [data-show-on-upload] { display: flex; }
+  dialog:has([data-pdf-import-progress]) [data-hide-on-upload] { display: none; }
+</style>
+
+<div data-controller="dialog" data-action="keydown.esc->dialog#close">
+  <button type="button" data-action="click->dialog#open" class="btn btn--plain txt-medium fill-transparent disable-when-arranging disable-when-deleting" title="Import PDF" aria-label="Import PDF">
+    <svg viewBox="0 0 20 24" xmlns="http://www.w3.org/2000/svg" fill="var(--color-ink)">
+      <path d="m15.8 21.7c0 .3-.2.4-.4.4h-13.5-.2v-16.9c0-.3.2-.4.4-.4h6.3c0-.6.1-1.2.3-1.8h-6.9c-1 0-1.8.8-1.8 1.8v17.5c0 1 .8 1.8 1.8 1.8h14c.9 0 1.6-.6 1.8-1.4v-11.6c-.5.2-1.1.4-1.8.5v10.3z"/>
+      <path fill="var(--color-positive)" d="m15 0c-2.8 0-5 2.2-5 5s2.2 5 5 5 5-2.2 5-5-2.2-5-5-5zm.7 7.5-2 2-2-2 1-1 .4.4v-2.9h1.1v2.9l.5-.4z"/>
+      <path d="m4.5 14h9v1.5h-9zm0 3h6v1.5h-6z"/>
+    </svg>
+    <span class="for-screen-reader">Import PDF</span>
+  </button>
+
+  <dialog data-dialog-target="dialog" class="dialog panel shadow"
+          style="min-width: 600px"
+          data-controller="dialog-morph">
+    <button type="button" data-action="click->dialog#close" class="btn btn--plain" aria-label="Close" style="position: absolute; top: 0.5rem; right: 0.5rem;">
+      &times;
+    </button>
+
+    <%= form_with url: book_import_path(book), method: :post, multipart: true do |form| %>
+      <div data-hide-on-upload class="flex align-center gap">
+        <label class="flex align-center gap full-width">
+          <div class="flex align-center gap input input--actor">
+            <%= image_tag "file-pdf.svg", aria: { hidden: true }, size: 24, class: "colorize--black" %>
+            <span class="search__input txt-large">
+              <%= form.file_field :pdf, accept: "application/pdf", required: true, class: "input--file__input" %>
+            </span>
+          </div>
+
+          <button type="submit" class="btn btn--reversed txt-medium" title="Import PDF">
+            <%= image_tag "arrow-right.svg", aria: { hidden: true }, size: 24 %>
+            <span class="for-screen-reader">Import PDF</span>
+          </button>
+        </label>
+      </div>
+
+      <div data-show-on-upload class="flex align-center gap">
+        <%= image_tag "file-pdf.svg", aria: { hidden: true }, size: 24, class: "colorize--black" %>
+        <span class="txt-medium">Uploading PDF&hellip;</span>
+      </div>
+    <% end %>
+
+    <div id="<%= dom_id(book, :pdf_import_body) %>"></div>
+  </dialog>
+</div>

data/app/views/books/imports/_progress.html.erb

@@ -0,0 +1,11 @@
+<div data-pdf-import-progress style="flex: 1">
+  <div style="background: var(--color-hairline, #e0e0e0); border-radius: 2px; overflow: hidden; height: 6px;">
+    <div role="progressbar"
+         aria-valuenow="<%= percent %>"
+         aria-valuemin="0"
+         aria-valuemax="100"
+         style="width: <%= percent %>%; height: 100%; background: var(--color-positive, #4caf50); transition: width 0.3s ease-out;">
+    </div>
+  </div>
+  <span class="txt-small txt-muted">Importing PDF&hellip; <%= percent %>%</span>
+</div>

data/config/importmap.rb

@@ -0,0 +1 @@
+pin "controllers/dialog_morph_controller", to: "writebook_pdf_import/dialog_morph_controller.js"

data/config/routes.rb

@@ -0,0 +1,5 @@
+Rails.application.routes.draw do
+  resources :books, only: [] do
+    resource :import, controller: "books/imports", only: %i[ create ]
+  end
+end

data/lib/writebook_pdf_import/engine.rb

@@ -0,0 +1,56 @@
+module WritebookPdfImport
+  class Engine < ::Rails::Engine
+    # Add the engine's routes file to the list Rails reloads — works in dev too
+    initializer "writebook_pdf_import.routes" do |app|
+      app.config.paths["config/routes.rb"] << root.join("config/routes.rb")
+    end
+
+    initializer "writebook_pdf_import.view_paths" do |app|
+      ActiveSupport.on_load(:action_controller) do
+        prepend_view_path WritebookPdfImport::Engine.root.join("app/views")
+      end
+    end
+
+    initializer "writebook_pdf_import.patch_create_buttons" do
+      ActiveSupport.on_load(:action_view) do
+        ActionView::Template.prepend(Module.new do
+          def initialize(source, identifier, handler, **kwargs)
+            if identifier.to_s.end_with?("books/_create_buttons.html.erb")
+              source = source.to_s + %(\n<%= render "books/imports/import", book: book %>)
+            end
+            super
+          end
+        end)
+      end
+    end
+
+    # Pin loading_controller under the host app's "controllers/" importmap namespace
+    # so eagerLoadControllersFrom picks it up automatically
+    initializer "writebook_pdf_import.importmap", before: "importmap" do |app|
+      if app.config.respond_to?(:importmap)
+        app.config.importmap.paths << root.join("config/importmap.rb")
+        app.config.importmap.cache_sweepers << root.join("app/assets/javascripts")
+      end
+    end
+
+    # Patch pdf-reader's word-spacing threshold. The default (font_size * 0.2) is
+    # too aggressive for large/bold fonts and drops spaces between words. 0.1 is
+    # tight enough to preserve intra-word kerning while keeping word spaces intact.
+    initializer "writebook_pdf_import.pdf_reader_patch" do
+      ActiveSupport.on_load(:after_initialize) do
+        require "pdf/reader"
+
+        PDF::Reader::TextRun.prepend(Module.new do
+          def +(other)
+            raise ArgumentError, "#{other} cannot be merged with this run" unless mergable?(other)
+            if (other.x - endx) < (font_size * 0.1)
+              self.class.new(x, y, other.endx - x, font_size, text + other.text)
+            else
+              self.class.new(x, y, other.endx - x, font_size, "#{text} #{other.text}")
+            end
+          end
+        end)
+      end
+    end
+  end
+end

data/lib/writebook_pdf_import/version.rb

@@ -0,0 +1,3 @@
+module WritebookPdfImport
+  VERSION = "0.0.1"
+end

data/lib/writebook_pdf_import.rb

@@ -0,0 +1,2 @@
+require "writebook_pdf_import/version"
+require "writebook_pdf_import/engine"

metadata

@@ -0,0 +1,100 @@
+--- !ruby/object:Gem::Specification
+name: writebook_pdf_import
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Albert Jankowski
+bindir: bin
+cert_chain: []
+date: 1980-01-02 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rails
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: pdf-reader
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.12'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.12'
+- !ruby/object:Gem::Dependency
+  name: mini_magick
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: A Rails engine that adds the ability to import PDF files into a Writebook
+  book, creating pages and pictures from the PDF content.
+email:
+- albertski@hey.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- MIT-LICENSE
+- README.md
+- app/assets/javascripts/writebook_pdf_import/dialog_morph_controller.js
+- app/controllers/books/imports_controller.rb
+- app/jobs/pdf_import_job.rb
+- app/models/pdf_importer.rb
+- app/models/pdf_page.rb
+- app/models/pdf_picture.rb
+- app/views/books/imports/_import.html.erb
+- app/views/books/imports/_progress.html.erb
+- config/importmap.rb
+- config/routes.rb
+- lib/writebook_pdf_import.rb
+- lib/writebook_pdf_import/engine.rb
+- lib/writebook_pdf_import/version.rb
+homepage: https://github.com/albertski/writebook_pdf_import
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/albertski/writebook_pdf_import
+  source_code_uri: https://github.com/albertski/writebook_pdf_import
+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: 4.0.6
+specification_version: 4
+summary: PDF import support for Writebook
+test_files: []