html2tex 0.1.0

data/COPYING

@@ -0,0 +1,21 @@
+Licence (MIT)
+
+Copyright (c) 2010 Paul Battley
+
+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 +1,41 @@
+HTML2TeX
+========
+
+This is a simple library and command-line tool to convert HTML documents into
+LaTeX. The intended use is for preparing ebooks, but it might also be useful
+for other purposes.
+
+Library use
+-----------
+
+    require "html2tex"
+    
+    # Return output as a string
+    tex = HTML2TeX.new(html).to_tex
+    
+    # Write directly to a stream
+    File.open("output.tex", "w") do |f|
+      HTML2TeX.new(html).to_tex(f)
+    end
+
+Command-line use
+----------------
+
+    html2tex source.html destination.tex
+
+Dependencies
+------------
+
+* htmlentities, to decode character entities
+* rubypants, to convert `'` and `"` into something more appealing
+
+Limitations
+-----------
+
+The HTML recognised is currently limited to headings, paragraphs, and bold and
+italic mark-up. This covers the majority of novels, but it's far from
+comprehensive.
+
+StringScanner is used to process the HTML, but cannot read from a stream
+directly, so the entire input document must be read into memory as a string
+first.

data/bin/html2tex

@@ -0,0 +1,6 @@
+#!/usr/bin/env ruby
+require "html2tex"
+
+File.open(ARGV[1], "w") do |output|
+  HTML2TeX.new(File.read(ARGV[0])).to_tex(output)
+end

data/lib/html2tex/basic_processor.rb

@@ -0,0 +1,80 @@
+class HTML2TeX
+  class BasicProcessor
+    attr_reader :scanner
+
+    def initialize(scanner)
+      @decoder = HTMLEntities.new
+      @scanner = scanner
+    end
+
+    def to_tex(buffer="")
+      while n = next_element
+        buffer << n
+      end
+      buffer
+    end
+
+  private
+    def next_element
+      if scanner.eos?
+        nil
+      elsif s = scanner.scan(/<[^>]+>/)
+        tag(s[/<([^>\s]+)/, 1].downcase)
+      elsif scanner.scan(/\s+/)
+        whitespace
+      elsif scanner.scan(/\*(\s*\*){2,5}/)
+        dinkus
+      elsif s = scanner.scan(/[^\s<]+/)
+        text(s)
+      else
+        ""
+      end
+    end
+
+    def text(s)
+      tex_escape(@decoder.decode(RubyPants.new(s).to_html))
+    end
+
+    def tex_escape(s)
+      return nil if s.nil?
+      s.gsub(/[\\{}$&#%^_~]/, '\\\\\\0')
+    end
+
+    def whitespace
+      if @squash_next
+        @squash_next = false
+        ""
+      else
+        " "
+      end
+    end
+
+    def tag(t)
+      @squash_next = false
+      case t
+      when "/p"
+        @squash_next = true
+        "\n\n"
+      when "em", "i"
+        "\\textit{"
+      when "strong", "b"
+        "\\textbf{"
+      when "/em", "/i", "/strong", "/b"
+        "}"
+      when "br"
+        "\\\\"
+      when /^h\d/
+        @squash_next = true
+        HeadingProcessor.new(scanner, t).to_tex + "\n\n"
+      else
+        ""
+      end
+    end
+
+    def dinkus
+      "\\begin{center}\n***\n\\end{center}"
+    end
+  end
+end
+
+require "html2tex/heading_processor"

data/lib/html2tex/heading_processor.rb

@@ -0,0 +1,32 @@
+require "html2tex/basic_processor"
+
+class HTML2TeX
+  class HeadingProcessor < BasicProcessor
+    HEADINGS = %w[part chapter section subsection subsubsection]
+
+    def initialize(scanner, label)
+      @label = label
+      super(scanner)
+    end
+
+    def to_tex(*args)
+      wrap(super(*args))
+    end
+
+  private
+    def wrap(content)
+      return "" if content.strip.empty?
+      index = @label[/\d/].to_i - 1
+      "\\#{HEADINGS[index]}*{#{content}}"
+    end
+
+    def tag(t)
+      case t
+      when "/#{@label}"
+        nil
+      else
+        ""
+      end
+    end
+  end
+end

data/lib/html2tex/version.rb

@@ -0,0 +1,3 @@
+class HTML2TeX
+  VERSION = "0.1.0"
+end

data/lib/html2tex.rb

@@ -0,0 +1,14 @@
+require "htmlentities"
+require "rubypants"
+require "html2tex/version"
+require "html2tex/basic_processor"
+
+class HTML2TeX
+  def initialize(html)
+    @html = html
+  end
+
+  def to_tex(buffer="")
+    BasicProcessor.new(StringScanner.new(@html)).to_tex(buffer)
+  end
+end

metadata

@@ -0,0 +1,91 @@
+--- !ruby/object:Gem::Specification 
+name: html2tex
+version: !ruby/object:Gem::Version 
+  version: 0.1.0
+platform: ruby
+authors: 
+- Paul Battley
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-05-09 00:00:00 +01:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: htmlentities
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 4.2.0
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: rubypants
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.2.0
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: shoulda
+  type: :development
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+    version: 
+description: Converts an HTML document to a LaTeX version with reasonably sensible markup.
+email: 
+- pbattley@gmail.com
+executables: 
+- html2tex
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- bin/html2tex
+- lib/html2tex.rb
+- lib/html2tex/version.rb
+- lib/html2tex/basic_processor.rb
+- lib/html2tex/heading_processor.rb
+- README.md
+- COPYING
+has_rdoc: true
+homepage: http://github.com/threedaymonk/html2tex
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.5
+signing_key: 
+specification_version: 3
+summary: HTML to LaTeX converter
+test_files: []
+