notroff 0.2.1

data/bin/notroff

@@ -0,0 +1,47 @@
+#!/usr/bin/env ruby
+require 'pp'
+require "notroff"
+
+options={}
+formatter_class = HtmlFormatter
+
+while true
+  if ARGV.first == '-o'
+    formatter_class = OdtFormatter
+    ARGV.shift
+  elsif ARGV.first == '-d'
+    formatter_class = DocbookFormatter
+    ARGV.shift
+  elsif ARGV.first == '-v'
+    Logger.verbose = true
+    ARGV.shift
+  else
+    break
+  end
+end
+
+unless ARGV.size == 2
+  raise "Usage: notroff [-d] <nr file> <output file>"
+end
+
+
+f = formatter_class.new( ARGV[0], ARGV[1]  )
+f.process
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

data/lib/notroff/code_scrubber.rb

@@ -0,0 +1,9 @@
+class CodeScrubber
+  def process( paragraphs )
+    paragraphs.each do |p|
+      next unless p[:type] == :code
+      p.string.gsub!(/##.*$/, '')
+    end
+    paragraphs
+  end
+end

data/lib/notroff/code_typer.rb

@@ -0,0 +1,37 @@
+class CodeTypeRefiner
+  def process( paragraphs )
+    processed_paragraphs = []
+
+    previous_type = nil
+
+    paragraphs.each_with_index do |paragraph, i|
+      type = paragraph[:type]
+      previous_type = ( paragraphs.first == paragraph) ? nil : paragraphs[i-1][:type]
+      next_type = ( paragraphs.last == paragraph) ? nil : paragraphs[i+1][:type]
+      new_type = code_type_for( previous_type, type, next_type )
+      paragraph[:type] = new_type
+      processed_paragraphs << paragraph
+    end
+    processed_paragraphs
+  end
+
+  def code_type_for( previous_type, type, next_type )
+    if type != :code
+      new_type = type
+
+    elsif previous_type == :code and next_type == :code
+      new_type = :middle_code
+
+    elsif previous_type == :code
+      new_type = :end_code
+
+    elsif next_type == :code
+      new_type = :first_code
+
+    else
+      new_type = :single_code
+    end
+
+    new_type
+  end
+end

data/lib/notroff/command_processor.rb

@@ -0,0 +1,28 @@
+class CommandProcessor
+  def process( lines )
+    paragraphs = []
+    lines.each do |line|
+      cmd, text = parse_line( line )
+      if cmd.empty?
+        cmd = :text
+      else
+        cmd = cmd.sub(/^./, '').to_sym
+      end
+      para = Text.new(text, :type => cmd, :original_text => line.to_s)
+      paragraphs << para
+    end
+    paragraphs
+  end
+
+  def parse_line( line )
+    match_data = /^(\.\w+ ?)(.*)/.match(line)
+    if match_data
+      cmd = match_data[1].strip
+      text = match_data[2]
+    else
+      cmd = ''
+      text = line
+    end
+    [ cmd.strip, text ]
+  end
+end

data/lib/notroff/composite_processor.rb

@@ -0,0 +1,52 @@
+class CompositeProcessor
+  def initialize(*args)
+    @processors = args
+  end
+
+  def add_processor(p)
+    @processors << p
+  end
+
+  def prepend_processor(p)
+    @processors = [p] + @processors
+  end
+
+  def process(paras=[])
+    @processors.each do |processor|
+      Logger.log "Applying processor #{processor.class} to #{paras.size} paragraphs"
+      dump(paras)
+      Logger.log
+      paras = processor.process( paras )
+      Logger.log "After processor #{processor.class}"
+      Logger.log
+    end
+    paras
+  end
+
+  def dump(data)
+    return unless Verbose
+    Logger.log "======="
+    if data.nil?
+      Logger.log "data: nil"
+    elsif data.kind_of?(Array)
+      Logger.log "data with #{data.size} items:"
+      data.each_with_index {|item, i| Logger.log "[#{i}] - #{item.inspect}" }
+    else
+      Logger.log data
+    end
+    Logger.log "======="
+  end
+end
+
+
+
+
+
+
+
+
+
+
+
+
+

data/lib/notroff/content.xml.erb

@@ -0,0 +1,110 @@
+<?xml version="1.0" encoding="utf-8"?>
+<office:document-content xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office:1.0"
+xmlns:style="urn:oasis:names:tc:opendocument:xmlns:style:1.0"
+xmlns:text="urn:oasis:names:tc:opendocument:xmlns:text:1.0"
+xmlns:table="urn:oasis:names:tc:opendocument:xmlns:table:1.0"
+xmlns:draw="urn:oasis:names:tc:opendocument:xmlns:drawing:1.0"
+xmlns:fo="urn:oasis:names:tc:opendocument:xmlns:xsl-fo-compatible:1.0"
+xmlns:xlink="http://www.w3.org/1999/xlink"
+xmlns:dc="http://purl.org/dc/elements/1.1/"
+xmlns:meta="urn:oasis:names:tc:opendocument:xmlns:meta:1.0"
+xmlns:number="urn:oasis:names:tc:opendocument:xmlns:datastyle:1.0"
+xmlns:svg="urn:oasis:names:tc:opendocument:xmlns:svg-compatible:1.0"
+xmlns:chart="urn:oasis:names:tc:opendocument:xmlns:chart:1.0"
+xmlns:dr3d="urn:oasis:names:tc:opendocument:xmlns:dr3d:1.0"
+xmlns:math="http://www.w3.org/1998/Math/MathML"
+xmlns:form="urn:oasis:names:tc:opendocument:xmlns:form:1.0"
+xmlns:script="urn:oasis:names:tc:opendocument:xmlns:script:1.0"
+xmlns:ooo="http://openoffice.org/2004/office"
+xmlns:ooow="http://openoffice.org/2004/writer"
+xmlns:oooc="http://openoffice.org/2004/calc"
+xmlns:dom="http://www.w3.org/2001/xml-events"
+xmlns:xforms="http://www.w3.org/2002/xforms"
+xmlns:xsd="http://www.w3.org/2001/XMLSchema"
+xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+xmlns:field="urn:openoffice:names:experimental:ooxml-odf-interop:xmlns:field:1.0"
+office:version="1.1">
+  <office:scripts />
+  <office:font-face-decls>
+    <style:font-face style:name="Wingdings"
+    svg:font-family="Wingdings" style:font-pitch="variable"
+    style:font-charset="x-symbol" />
+    <style:font-face style:name="Symbol" svg:font-family="Symbol"
+    style:font-family-generic="roman" style:font-pitch="variable"
+    style:font-charset="x-symbol" />
+    <style:font-face style:name="Courier New"
+    svg:font-family="'Courier New'"
+    style:font-family-generic="modern" />
+    <style:font-face style:name="Courier"
+    svg:font-family="Courier, 'Courier New'"
+    style:font-family-generic="modern" />
+    <style:font-face style:name="Nimbus Mono L"
+    svg:font-family="'Nimbus Mono L', 'Courier New'"
+    style:font-family-generic="modern" />
+    <style:font-face style:name="Nimbus Roman No9 L"
+    svg:font-family="'Nimbus Roman No9 L'"
+    style:font-family-generic="roman"
+    style:font-pitch="variable" />
+    <style:font-face style:name="Times" svg:font-family="Times"
+    style:font-family-generic="roman"
+    style:font-pitch="variable" />
+    <style:font-face style:name="Times New Roman"
+    svg:font-family="'Times New Roman'"
+    style:font-family-generic="roman"
+    style:font-pitch="variable" />
+    <style:font-face style:name="Arial" svg:font-family="Arial"
+    style:font-family-generic="swiss"
+    style:font-pitch="variable" />
+    <style:font-face style:name="Arial Unicode MS"
+    svg:font-family="'Arial Unicode MS'"
+    style:font-family-generic="swiss"
+    style:font-pitch="variable" />
+    <style:font-face style:name="Helvetica"
+    svg:font-family="Helvetica" style:font-family-generic="swiss"
+    style:font-pitch="variable" />
+    <style:font-face style:name="Tahoma" svg:font-family="Tahoma"
+    style:font-family-generic="swiss"
+    style:font-pitch="variable" />
+    <style:font-face style:name="Verdana" svg:font-family="Verdana"
+    style:font-family-generic="swiss"
+    style:font-pitch="variable" />
+    <style:font-face style:name="DejaVu Sans"
+    svg:font-family="'DejaVu Sans'"
+    style:font-family-generic="system"
+    style:font-pitch="variable" />
+  </office:font-face-decls>
+  <office:automatic-styles>
+    <style:style style:name="P1" style:family="paragraph"
+    style:parent-style-name="Standard">
+      <style:paragraph-properties fo:text-align="end"
+      style:justify-single-word="false" />
+    </style:style>
+    <style:style style:name="P2" style:family="paragraph"
+    style:parent-style-name="HA" style:master-page-name="Standard">
+      <style:paragraph-properties style:page-number="1" />
+    </style:style>
+    <style:style style:name="P3" style:family="paragraph"
+    style:parent-style-name="FTN">
+      <style:paragraph-properties fo:margin-left="0.1598in"
+      fo:margin-right="0in" fo:margin-top="0.0417in"
+      fo:margin-bottom="0.0417in"
+      style:line-height-at-least="0.1807in"
+      fo:text-indent="-0.1598in" style:auto-text-indent="false" />
+    </style:style>
+    <style:style style:name="T1" style:family="text">
+      <style:text-properties fo:font-style="italic"
+      style:font-style-asian="italic"
+      style:font-style-complex="italic" />
+    </style:style>
+    <style:style style:name="T2" style:family="text">
+      <style:text-properties fo:font-weight="bold"
+      style:font-weight-asian="bold"
+      style:font-weight-complex="bold" />
+    </style:style>
+  </office:automatic-styles>
+  <office:body>
+    <office:text>
+<%=content%>
+    </office:text>
+  </office:body>
+</office:document-content>

data/lib/notroff/docbook_renderer.rb

@@ -0,0 +1,155 @@
+require 'rexml/document'
+require 'pp'
+
+class DocbookRenderer < Processor
+  include Tokenize
+  include REXML
+
+  def process( paragraphs )
+    @author = 'John Smith'
+    @title = 'Wealth of Nations'
+    @chapters = []
+    @chapter = nil
+    @section = nil
+
+    paragraphs.each do |paragraph|
+      format( paragraph )
+    end
+    @book = Element.new('book')
+    @book.add_namespace('http://docbook.org/ns/docbook')
+    @book.add_attribute('version', '5.0')
+    @book.add_element element_for('title', @title)
+    @book.add_element element_for('author', @author)
+    @chapters.each {|ch| @book << ch}
+    doc = Document.new
+    decl = XMLDecl.new
+    decl.version = '1.0'
+    doc << decl
+    doc << @book
+    doc
+  end
+
+  def element_for(type, text)
+    result = Element.new(type)
+    result.add_text(text)
+    result
+  end
+
+  def format( p )
+    type = p[:type]
+    text = p.string
+
+    return nil if text.empty? and :type != :code
+
+    case type
+    when :title
+      @title = text
+    when :author
+      @author = text
+    when :chapter
+      Logger.log "adding chapter #{text}"
+      @chapter = Element.new('chapter')
+      @chapters << @chapter
+      @section = nil
+      title_element = Element.new('title')
+      add_body_text(title_element, text)
+      @chapter.add_element(title_element)
+    when :section
+      Logger.log "adding section #{text}"
+      @section = Element.new('section')
+      @chapter.add(@section)
+      title_element = Element.new('title')
+      add_body_text(title_element, text)
+      @section.add_element(title_element)
+    when :body
+      Logger.log "adding body #{text[0..5]}"
+      paragraph = Element.new('para')
+      add_body_text(paragraph, text)
+      add_content_element(paragraph)
+    when :code
+      add_content_element(code_element(type, text))
+    else
+      raise "#{type}???"
+    end
+  end
+
+  def add_content_element(el)
+    if @section
+      @section.add_element(el)
+    elsif @chapter
+      @chapter.add_element(el)
+    else
+      raise "No chapter to add #{el} to"
+    end
+  end
+
+  def text_element(type, text)
+    element = [ tag_for(type) ]
+    add_body_text(element, text)
+    element
+  end
+
+  def tag_for(type)
+    case type
+    when :body
+      'para'
+    when :text
+      'p'
+    when :author
+      'h3'
+    when :section
+      'h3'
+    when :chapter
+      'chapter'
+    when :sec
+      'h3'
+    when :title
+      'h2'
+    else
+        raise "Dont know what to do with #{type}"
+    end
+  end
+
+  def add_body_text( element, text )
+    tokens = tokenize_body_text( text )
+    tokens.each {|token| add_span( token, element ) }
+  end
+
+  def add_span( token, element )
+    Logger.log "Add span: token: #{token} element: #{element}"
+    case token[:type]
+    when :italic
+      element.add( span_for( token.string, "emphasis" ))
+    when :code
+      element.add( span_for( token.string, "code" ))
+    when :bold
+      element.add( span_for( token.string, "emphasis" ))
+    when :normal
+      element.add_text( token.string )
+    when :footnote
+      element.add(footnote_for(token.string))
+    else
+      raise "Dont know what to do with #{token}"
+    end
+  end
+
+  def footnote_for( text )
+    fn = Element.new('footnote')
+    fn.add_element(element_for('para', text))
+    fn
+  end
+
+  def code_element(type, text)
+    element = Element.new('informalexample')
+    prog_element = element_for('programlisting', text)
+    prog_element.add_attribute('xml:space', 'preserve')
+    element.add_element(prog_element)
+    element
+  end
+
+  def span_for( text, style )
+    span = Element.new(style)
+    span.text = remove_escapes(text)
+    span
+  end
+end

data/lib/notroff/embedded.rb

@@ -0,0 +1,132 @@
+class BetweenFilter
+  def initialize(re1, re2=re1)
+    @re1 = re1
+    @re2 = re2
+  end
+
+  def process(paras)
+    state = :before_first
+    paras.each do |para|
+      if state == :before_first and @re1 =~ para
+        para[:included] = true
+        state = :after_first
+        break if para =~ @re2
+      elsif state == :after_first
+        para[:included] = true
+        break if para =~ @re2
+      end
+    end
+    paras
+  end
+end
+
+class DefinitionFilter
+  def initialize(def_re, include_body=true)
+    @def_re = def_re
+    @include_body = include_body
+  end 
+
+  def process(paras)
+    state = :before_def
+    end_re = nil
+    paras.each do |para|
+      Logger.log para, (@def_re =~ para)
+      if state == :before_def and @def_re =~ para
+        para[:included] = true
+        end_re = Regexp.new( "^#{' ' * para.string.indent_depth}end" )
+        state = :after_def
+      elsif state == :after_def and end_re =~ para.string
+        para[:included] = true
+        break
+      elsif state == :after_def and @include_body
+        para[:included] = true
+      end
+    end
+    paras
+  end
+end
+
+class MethodFilter < DefinitionFilter
+  def initialize(method_name, include_body)
+    super /^ *def +#{method_name}(\(|$| )/, include_body
+  end
+end
+
+class ClassFilter < DefinitionFilter
+  def initialize(class_name, include_body)
+    super /^ *class +#{class_name}(\(|$| )/, include_body
+  end
+end
+
+class ModuleFilter < DefinitionFilter
+  def initialize(module_name, include_body)
+    super /^ *module +#{module_name}(\(|$| )/, include_body
+  end
+end
+
+class EmbeddedRubyProcessor
+  def process(paragraphs)
+    new_paragraphs = []
+    paragraphs.each do |p|
+      if p[:type] == :x
+        Logger.log p
+        results = process_command(p.string)
+        new_paragraphs << results if results
+      else
+        new_paragraphs << p
+      end
+    end
+    new_paragraphs.flatten
+  end
+
+  def process_command(ruby_expression)
+    Logger.log "Ruby expression: #{ruby_expression}"
+    lines = eval(ruby_expression, binding)
+  end
+
+  def embed(*filters, &block)
+    paras = block.call.map {|line| line.rstrip}
+    paras.map! {|p| Text.new(p, :type => :code)}
+    Logger.log "EMBED: #{paras}"
+    unless filters.empty?
+      filters.each {|f| paras = f.process(paras)}
+      paras = paras.find_all {|p| p[:included]}
+    end
+    paras
+  end
+
+  def inc(path, *filters)
+    embed(*filters) {File.readlines(path)}
+  end
+
+  def run(command, *filters)
+    embed(*filters) {File.popen(command).readlines}
+  end
+
+  def matches(re1, re2=re1)
+    BetweenFilter.new(re1, re2)
+  end
+
+  def method(name, include_body=true)
+    MethodFilter.new(name, include_body)
+  end
+
+  def clazz(name, include_body=true)
+    ClassFilter.new(name, include_body)
+  end
+
+  def mod(name, include_body=true)
+    ModuleFilter.new(name, include_body)
+  end
+
+  def indent(delta_indent, paragraphs)
+    paragraphs.map do |p| 
+      if delta_indent > 0
+        p.string = (" " * delta_indent) + p.string
+      elsif delta_indent < 0
+        p.string.sub!( ' ' * delta_indent.abs, '' )
+      end
+    end
+    paragraphs
+  end
+end

data/lib/notroff/filter.rb

@@ -0,0 +1,15 @@
+class Filter
+  def process(paragraphs)
+    paragraphs.find_all {|p| included?(p)}
+  end
+
+  def included?(paragraph)
+    true
+  end
+end
+
+class IncludedFilter < Filter
+  def included?(paragraph)
+    paragraph[:included]
+  end
+end

data/lib/notroff/formatter.rb

@@ -0,0 +1,54 @@
+class Formatter < CompositeProcessor
+  def initialize()
+    super
+    add_processor CommandProcessor.new
+    add_processor TypeAssigner.new
+    add_processor EmbeddedRubyProcessor.new
+    add_processor CodeScrubber.new
+    add_processor BodyParagraphJoiner.new
+  end
+end
+
+class HtmlFormatter < Formatter
+  def initialize(input, output)
+    super()
+    prepend_processor FileReader.new(input)
+    add_processor CodeParagraphJoiner.new
+    add_processor HtmlRenderer.new
+    add_processor FileWriter.new(output)
+  end
+end
+
+class DocbookFormatter < Formatter
+  def initialize(input, output)
+    super()
+    prepend_processor FileReader.new(input)
+    add_processor CodeParagraphJoiner.new
+    add_processor DocbookRenderer.new
+    add_processor FileWriter.new(output)
+  end
+end
+
+class OdtFormatter < Formatter
+  def initialize(input, output)
+    super()
+    prepend_processor FileReader.new(input)
+    add_processor CodeTypeRefiner.new
+    add_processor OdtRenderer.new
+    add_processor TemplateExpander.new
+    add_processor OdtReplacer.new(output)
+  end
+end
+
+
+
+
+
+
+
+
+
+
+
+
+