bookshelf 1.0.0

data/lib/bookshelf/parser/mobi.rb

@@ -0,0 +1,14 @@
+module Bookshelf
+  module Parser
+    class Mobi < Base
+      def parse
+        spawn_command ["kindlegen", epub_file.to_s,]
+        true
+      end
+
+      def epub_file
+        root_dir.join("output/#{name}.epub")
+      end
+    end
+  end
+end

data/lib/bookshelf/parser/pdf.rb

@@ -0,0 +1,44 @@
+module Bookshelf
+  module Parser
+    class PDF < Base
+      def parse
+        apply_footnotes!
+        spawn_command ["prince", with_footnotes_file.to_s, "-o", pdf_file.to_s]
+      end
+
+      def apply_footnotes!
+        html = Nokogiri::HTML(html_file.read)
+
+        # https://github.com/sparklemotion/nokogiri/issues/339
+        html.css("html").first.tap do |element|
+          next unless element
+          element.delete("xmlns")
+          element.delete("xml:lang")
+        end
+
+        html.css("p.footnote[id^='_fn']").each do |fn|
+          fn.node_name = "span"
+          fn.set_attribute("class", "fn")
+
+          html.css("[href='##{fn["id"]}']").each do |link|
+            link.add_next_sibling(fn)
+          end
+        end
+
+        File.open(with_footnotes_file, "w") {|f| f << html.to_xhtml}
+      end
+
+      def with_footnotes_file
+        Bookshelf.root_dir.join("output/#{name}.pdf.html")
+      end
+
+      def html_file
+        Bookshelf.root_dir.join("output/#{name}.html")
+      end
+
+      def pdf_file
+        Bookshelf.root_dir.join("output/#{name}.pdf")
+      end
+    end
+  end
+end

data/lib/bookshelf/parser/txt.rb

@@ -0,0 +1,18 @@
+module Bookshelf
+  module Parser
+    class Txt < Base
+      def parse
+        spawn_command ["html2text", "-style", "pretty", "-nobs", "-o", txt_file.to_s, html_file.to_s]
+      end
+
+      def html_file
+        root_dir.join("output/#{name}.html")
+      end
+
+      def txt_file
+        root_dir.join("output/#{name}.txt")
+      end
+    end
+  end
+end
+

data/lib/bookshelf/stats.rb

@@ -0,0 +1,45 @@
+module Bookshelf
+  class Stats
+    attr_reader :root_dir
+
+    def initialize(root_dir)
+      @root_dir = root_dir
+    end
+
+    def text
+      @text ||= html.text
+    end
+
+    def html
+      @html ||= Nokogiri::HTML(content)
+    end
+
+    def words
+      @words ||= text.split(" ").size
+    end
+
+    def chapters
+      @chapters ||= html.css(".chapter").size
+    end
+
+    def images
+      @images ||= html.css("img").size
+    end
+
+    def footnotes
+      @footnotes ||= html.css("p.footnote").size
+    end
+
+    def links
+      @links ||= html.css("[href^='http']").size
+    end
+
+    def code_blocks
+      @code_blocks ||= html.css("pre").size
+    end
+
+    def content
+      @content ||= Parser::HTML.new(root_dir).content
+    end
+  end
+end

data/lib/bookshelf/stream.rb

@@ -0,0 +1,27 @@
+module Bookshelf
+  class Stream
+    attr_accessor :listener, :content
+    attr_reader :html
+
+    def initialize(content, listener)
+      @content  = content
+      @listener = listener
+      @html = Nokogiri::HTML.parse(content)
+    end
+
+    def parse
+      traverse(html)
+    end
+
+    def traverse(node)
+      node.children.each do |child|
+        emit(child)
+        traverse(child)
+      end
+    end
+
+    def emit(node)
+      listener.send(:tag, node) if node.name =~ /h[1-6]/
+    end
+  end
+end

data/lib/bookshelf/syntax.rb

@@ -0,0 +1,124 @@
+module Bookshelf
+  class Syntax
+    autoload :Highlight, "bookshelf/syntax/highlight"
+
+    attr_reader :io
+    attr_reader :lines
+    attr_reader :book_dir
+    attr_reader :format
+
+    # Render syntax blocks from specified source code.
+    #
+    #   dir = Pathname.new(File.dirname(__FILE__))
+    #   text = File.read(dir.join("text/some_file.textile"))
+    #   Bookshelf::Syntax.render(dir, :textile, text)
+    #
+    def self.render(book_dir, format, source_code, raw = false)
+      source_code.gsub(/@@@(.*?)@@@/m) do |match|
+        new(book_dir, format, $1, raw).process
+      end
+    end
+
+    # Process each syntax block individually.
+    #
+    def initialize(book_dir, format, code, raw = false)
+      @format = format
+      @book_dir = book_dir
+      @io = StringIO.new(code)
+      @lines = io.readlines.collect(&:chomp)
+      @language = 'text' if raw
+    end
+
+    # Return unprocessed line codes.
+    #
+    def raw
+      lines[1..-1].join("\n")
+    end
+
+    # Return meta data from syntax annotation.
+    #
+    def meta
+      @meta ||= begin
+        line = lines.first.squish
+        _, language, file, modifier, reference = *line.match(/^([^ ]+)(?: ([^:#]+)(?:(:|#)(.*?))?)?$/)
+
+        if modifier == "#"
+          type = :block
+        elsif modifier == ":"
+          type = :range
+        elsif file
+          type = :file
+        else
+          type = :inline
+        end
+
+        {
+          :language  => language,
+          :file      => file,
+          :type      => type,
+          :reference => reference
+        }
+      end
+    end
+
+    # Process syntax block, returning a +pre+ HTML tag.
+    #
+    def process
+      code = raw.to_s.strip_heredoc
+      code = process_file.gsub(/\n^.*?@(begin|end):.*?$/, "") if meta[:file]
+
+      code = Highlight.apply(code, language)
+
+      # escape for textile
+      code = %[<notextile>#{code}</notextile>] if format == :textile
+      code
+    end
+
+    private
+    # Process line range as in <tt>@@@ ruby some_file.rb:15,20 @@@</tt>.
+    #
+    def process_range(code)
+      starts, ends = meta[:reference].split(",").collect(&:to_i)
+      code = StringIO.new(code).readlines[starts-1..ends-1].join("\n").strip_heredoc.chomp
+    end
+
+    # Process block name as in <tt>@@@ ruby some_file.rb#some_block @@@</tt>.
+    #
+    def process_block(code)
+      code.gsub!(/\r\n/, "\n")
+      re = %r[@begin: *\b(#{meta[:reference]})\b *[^\n]*\n(.*?)\n[^\n]*@end: \1]im
+
+      if code.match(re)
+        $2.strip_heredoc
+      else
+        "[missing '#{meta[:reference]}' block name]"
+      end
+    end
+
+    # Process file and its relatives.
+    #
+    def process_file
+      file_path = book_dir.join("code/#{meta[:file]}")
+
+      if File.exist?(file_path)
+        code = File.read(file_path)
+
+        if meta[:type] == :range
+          process_range(code)
+        elsif meta[:type] == :block
+          process_block(code)
+        else
+          code
+        end
+      else
+        "[missing 'code/#{meta[:file]}' file]"
+      end
+    end
+
+    # Return the language used for this syntax block. Overrideable
+    # for epub generation.
+    def language
+      @language || meta[:language]
+    end
+  end
+end

data/lib/bookshelf/toc.rb

@@ -0,0 +1,6 @@
+module Bookshelf
+  module TOC
+    autoload :HTML, "bookshelf/toc/html"
+    autoload :Epub, "bookshelf/toc/epub"
+  end
+end

data/lib/bookshelf/toc/epub.rb

@@ -0,0 +1,41 @@
+module Bookshelf
+  module TOC
+    class Epub
+      attr_accessor :navigation
+
+      def initialize(navigation)
+        @navigation = navigation
+      end
+
+      def to_html
+        ERB.new(template).result OpenStruct.new(:navigation => navigation).instance_eval{ binding }
+      end
+
+      def template
+        <<-HTML.strip_heredoc.force_encoding("utf-8")
+          <?xml version="1.0" encoding="utf-8" ?>
+          <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
+          <html xml:lang="en" xmlns="http://www.w3.org/1999/xhtml">
+            <head>
+              <meta http-equiv="Content-type" content="text/html; charset=utf-8" />
+              <link rel="stylesheet" type="text/css" href="epub.css"/>
+              <meta http-equiv="Content-Type" content="application/xhtml+xml; charset=utf-8" />
+              <title>Table of Contents</title>
+            </head>
+            <body>
+              <div id="toc">
+                <ul>
+                  <% navigation.each do |nav| %>
+                    <li>
+                      <a href="<%= nav[:content] %>"><%= nav[:label] %></a>
+                    </li>
+                  <% end %>
+                </ul>
+              </div>
+            </body>
+          </html>
+        HTML
+      end
+    end
+  end
+end

data/lib/bookshelf/toc/html.rb

@@ -0,0 +1,78 @@
+module Bookshelf
+  module TOC
+    class HTML
+      # Return the table of contents in hash format.
+      #
+      attr_reader :toc
+
+      private_class_method :new
+      attr_reader :buffer # :nodoc:
+      attr_reader :attrs # :nodoc:
+      attr_accessor :content # :nodoc:
+
+      # Traverse every title and add a +id+ attribute.
+      # Return the modified content.
+      #
+      def self.normalize(content)
+        counter = {}
+        html = Nokogiri::HTML.parse(content)
+        html.search("h1, h2, h3, h4, h5, h6").each do |tag|
+          title = tag.inner_text
+          permalink = title.to_permalink
+
+          counter[permalink] ||= 0
+          counter[permalink] += 1
+
+          permalink = "#{permalink}-#{counter[permalink]}" if counter[permalink] > 1
+
+          tag.set_attribute("id", permalink)
+        end
+
+        html.css("body").to_xhtml.gsub(/<body>(.*?)<\/body>/m, "\\1")
+      end
+
+      # Traverse every title normalizing its content as a permalink.
+      #
+      def self.generate(content)
+        content = normalize(content)
+        listener = new
+        listener.content = content
+        Stream.new(content, listener).parse
+        listener
+      end
+
+      def initialize # :nodoc:
+        @toc = []
+        @counters = {}
+      end
+
+      def tag(node) # :nodoc:
+        toc << {
+          :level     => node.name.gsub(/[^\d]/, "").to_i,
+          :text      => node.text,
+          :permalink => node["id"]
+        }
+      end
+
+      # Return a hash with all normalized attributes.
+      #
+      def to_hash
+        {
+          :content => content,
+          :html => to_html,
+          :toc => toc
+        }
+      end
+
+      # Return the table of contents in HTML format.
+      #
+      def to_html
+        String.new.tap do |html|
+          toc.each do |options|
+            html << %[<div class="level#{options[:level]} #{options[:permalink]}"><a href="##{options[:permalink]}"><span>#{CGI.escape_html(options[:text])}</span></a></div>]
+          end
+        end
+      end
+    end
+  end
+end

data/lib/bookshelf/version.rb

@@ -0,0 +1,8 @@
+module Bookshelf
+  module Version
+    MAJOR = 1
+    MINOR = 0
+    PATCH = 0
+    STRING = "#{MAJOR}.#{MINOR}.#{PATCH}"
+  end
+end

data/templates/Guardfile

@@ -0,0 +1,12 @@
+notification :off
+interactor :off
+
+guard :shell do
+  watch %r[^(?!output|templates/scss)] do |m|
+    `bookshelf export`
+  end
+
+  watch %r[^templates/scss] do |m|
+    `sass --unix-newlines templates/scss:templates`
+  end
+end

data/templates/config.erb

@@ -0,0 +1,44 @@
+# The book's title. Will be used everywhere!
+title: "[Your Book Title]"
+
+# The book's language.
+language: en
+
+# Your book copyright info.
+# Here's some examples:
+#
+#   Copyright <%= @year %> by <%= @name %>.
+#   Copyright <%= @year %> by <%= @name %>. This work is licensed under MIT License.
+#   This work is licensed under a Creative Commons Attribution-ShareAlike 3.0 Unported License.
+#   This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License.
+#   This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.
+#
+copyright: "Copyright (C) <%= @year %> <%= @name %>."
+
+# Who's publishing this book.
+publisher: "<%= @name %>"
+
+# When this book was published.
+published_at: "<%= Date.today %>"
+
+# Some book description.
+subject: "[Your book description]"
+
+# Some keywords that identify this book.
+keywords: "[Your book keywords (comma-separated)]"
+
+# Some unique identification. Works great with your domain
+# like `http://yourbook.example.com`.
+uid: "<%= @uid %>"
+
+# Your book identification like ISBN or ISSN.
+identifier:
+  id: "http://yourbook.example.com"
+  type: "URL" # can be ISBN, ISSN or URL
+
+# This book authors.
+authors:
+  - "<%= @name %>"
+
+# The base URL from your source code.
+base_url: http://example.com