man_parser 0.1.0

data/README.markdown

@@ -0,0 +1,42 @@
+Parse man source
+
+Install
+=======
+    sudo gem install grosser-man_parser -s http://gems.github.com/
+
+Usage
+=====
+    ManParser.parse('ls')
+    # all the sections
+    :sections=>{
+      "NAME"=>"printf \\- format and print data",
+      "SYNOPSIS"=>".B printf\n\\f...",
+      "AUTHOR"=>"Written by David MacKenzie.",
+      ...
+    },
+
+    # options parsed into :name, :alias, :argument, :description
+    :options=>[
+      {:name=>"help", :description=>"display this help and exit"},
+      {:name=>"version", :description=>"output version information and exit"},
+      {:alias=>"Z", :name => 'context', :description=>"print any SELinux security context of each file"}
+    ],
+
+    # description without options
+    :description=>".PPPrint ARGUMENT(s) according to FORMAT\n bla bla...."}
+
+### available_commands
+    ManParser.available_commands => array of commands that are available for parsing
+
+### source
+    ManParser.source('ls') => uncleaned source of man file
+
+TODO
+====
+ - add to_html("\fBxx\fR") == "<b>xx</b>"
+
+Author
+======
+[Michael Grosser](http://pragmatig.wordpress.com)  
+grosser.michael@gmail.com  
+Hereby placed under public domain, do what you want, just do not hold me accountable...

data/Rakefile

@@ -0,0 +1,21 @@
+desc "Run all specs in spec directory"
+task :default do
+  options = "--colour --format progress --loadby --reverse"
+  files = FileList['spec/**/*_spec.rb']
+  system("spec #{options} #{files}")
+end
+
+begin
+  require 'jeweler'
+  project_name = 'man_parser'
+  Jeweler::Tasks.new do |gem|
+    gem.name = project_name
+    gem.summary = "Parse unix man pages into ruby-readable format"
+    gem.email = "grosser.michael@gmail.com"
+    gem.homepage = "http://github.com/grosser/#{project_name}"
+    gem.authors = ["Michael Grosser"]
+  end
+  Jeweler::GemcutterTasks.new
+rescue LoadError
+  puts "Jeweler, or one of its dependencies, is not available. Install it with: sudo gem install technicalpickles-jeweler -s http://gems.github.com"
+end

data/VERSION

@@ -0,0 +1 @@
+0.1.0

data/lib/man_parser.rb

@@ -0,0 +1,95 @@
+class ManParser
+  def self.available_commands
+    `ls #{root}`.split("\n").map{|c| c.sub('.1.gz','')}
+  end
+
+  def self.source(cmd)
+    `gzip -dc #{root}/#{cmd}.1.gz`
+  end
+
+  def self.parse(cmd)
+    sections = sections(source(cmd))
+    description, options = parse_description(sections['DESCRIPTION'])
+    options = options.map{|option| parse_option(option*' ') }
+    {:description => description.map{|l|l.strip}.join(''), :options=>options, :sections=>sections}
+  end
+
+  private
+
+  def self.root
+    '/usr/share/man/man1'
+  end
+
+  def self.parse_option(option)
+    option = option.gsub(/\\f[IB](.*?)\\fR/,"\\1").gsub('\\','')
+
+    found =  if option =~ /^-(\w+), --([-\w]+)(=(\w+))?(.*)/
+      {:alias=>$1, :name=>$2, :argument=>$4, :description=>$5}
+    elsif option =~ /^--([-\w]+)(=(\w+))?(.*)/
+      {:name=>$1, :argument=>$3, :description=>$4}
+    elsif option =~ /^-([-\w]+)(.*)/
+      {:alias=>$1, :description=>$2}
+    end
+
+    if not found
+      puts "#{option} <-> nil !"
+      return
+    end
+
+    found[:description] = found[:description].to_s.strip.sub(/\s*\.TP$/,'')
+    found.delete(:argument) unless found[:argument]
+
+    found
+  end
+
+  # description can be split like "description, options, descriptions"
+  # so we remove the options part, and combind the 2 descriptions parts
+  def self.parse_description(text)
+    in_option = false
+    already_switched = false
+    options = []
+    description = []
+
+    text.split("\n")[1..-1].each do |line|
+
+      if start_of_option?(line) and not already_switched
+        in_option = true
+        options << [] #new option
+      elsif line =~ /^\.PP/ and in_option
+        already_switched = true
+        in_option = false
+      end
+
+      next if line.strip.empty?
+
+      if in_option
+        options.last << line
+      else
+        description << line
+      end
+    end
+
+    [description * "\n", options]
+  end
+
+  # split into sections according to "SectionHead" aka .SH
+  def self.sections(text)
+    name = 'OUT_OF_SECTION'
+    sections = Hash.new([])
+
+    text.split("\n").each do |line|
+      if line =~ /^\.SH (.*)$/
+        name = $1
+      else
+        sections[name] += [line]
+      end
+    end
+
+    sections.each{|k,v| sections[k] = v*"\n"}
+    sections
+  end
+
+  def self.start_of_option?(line)
+    !!( line =~ /^\\fB\\-/)
+  end
+end

data/man_parser.gemspec

@@ -0,0 +1,45 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE
+# Instead, edit Jeweler::Tasks in Rakefile, and run `rake gemspec`
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{man_parser}
+  s.version = "0.1.0"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Michael Grosser"]
+  s.date = %q{2009-10-03}
+  s.email = %q{grosser.michael@gmail.com}
+  s.extra_rdoc_files = [
+    "README.markdown"
+  ]
+  s.files = [
+    "README.markdown",
+     "Rakefile",
+     "VERSION",
+     "lib/man_parser.rb",
+     "man_parser.gemspec",
+     "spec/man_parser_spec.rb",
+     "spec/spec_helper.rb"
+  ]
+  s.homepage = %q{http://github.com/grosser/man_parser}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.3.5}
+  s.summary = %q{Parse unix man pages into ruby-readable format}
+  s.test_files = [
+    "spec/man_parser_spec.rb",
+     "spec/spec_helper.rb"
+  ]
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
+    else
+    end
+  else
+  end
+end

data/spec/man_parser_spec.rb

@@ -0,0 +1,105 @@
+require 'spec/spec_helper'
+
+describe ManParser do
+  describe :parse do
+    it "finds the description" do
+      d = ManParser.parse('ls')[:description]
+      d.should =~ /^\.PPList information about the FILEs \(the current/
+      d.should =~ /problems, 2 if serious trouble\.$/
+      d.should_not include('\\-\\-all')
+      d.should_not include('do not ignore entries starting with')
+      d.should_not include("      ")
+    end
+
+    describe 'options' do
+      def options
+        ManParser.parse('ls')[:options]
+      end
+
+      it "finds all options" do
+        options.size.should == 58
+      end
+
+      it "extracts the name" do
+        options.first[:name].should == 'all'
+      end
+
+      it "extracts the alias" do
+        options.first[:alias].should == 'a'
+      end
+
+      it "extracts the description" do
+        options.first[:description].should == 'do not ignore entries starting with .'
+      end
+
+      it "understands format with only name (--author)" do
+        options[2].should == {:name=>'author', :description=>'with -l, print the author of each file'}
+      end
+    end
+  end
+
+  describe :source do
+    it "reads the source" do
+      ManParser.source('printf').should =~ /^.\\\" DO NOT MODIFY THIS F(.*) access to the complete manual.\n$/m
+    end
+  end
+
+  describe :available_commands do
+    it "finds them" do
+      ManParser.available_commands.should include('printf')
+    end
+  end
+
+  describe :parse_option do
+    def parse(x)
+      ManParser.send(:parse_option, x)
+    end
+
+    it "parses single --" do
+      x = parse('\fB\-\-help\fR display this help and exit .TP')
+      x.should == {:name=>"help", :description=>"display this help and exit"}
+    end
+
+    it "parses single -- with =" do
+      x = parse('\fB\-\-block\-size\fR=\fISIZE\fR xyz')
+      x.should == {:name => 'block-size', :argument=>'SIZE', :description=>"xyz"}
+    end
+
+    it "parses single -" do
+      x = parse('\fB\-1\fR list one file per line .TP')
+      x.should == {:alias=>"1", :description=>"list one file per line"}
+    end
+
+    it "parses - and --" do
+      x = parse('\fB\-Z\fR, \fB\-\-context\fR print any SELinux security context of each file .TP')
+      x.should == {:alias=>"Z", :name => 'context', :description=>"print any SELinux security context of each file"}
+    end
+
+    it "parses - and -- with =" do
+      x = parse('\fB\-T\fR, \fB\-\-tabsize\fR=\fICOLS\fR assume tab stops at each COLS instead of 8 .TP')
+      x.should == {:alias=>"T", :name => 'tabsize', :argument=>'COLS', :description=>"assume tab stops at each COLS instead of 8"}
+    end
+
+    it "does not parse random stuff" do
+      ManParser.stub!(:puts)
+      x = parse('as we say: \fB\-T\fR, \fB\-\-tabsize\fR=\fICOLS\fR assume tab stops at each COLS instead of 8')
+      x.should == nil
+    end
+  end
+
+  describe :start_of_option? do
+    {
+      '\fB\-\-version\fR'=>true,
+      '\fB\-1\fR'=>true,
+      '\fB\-\-color\fR=\fIauto\fR'=>true,
+      '\fB\-T\fR, \fB\-\-tabsize\fR=\fICOLS\fR'=>true,
+      '\fB\-U\fR'=>true,
+      '\-\-\-\-\-'=>false,
+      '   asdadas'=>false
+    }.each do |line, success|
+      it "recognises #{line} -- #{success}" do
+        ManParser.send(:start_of_option?, line).should == success
+      end
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,4 @@
+# ---- requirements
+$LOAD_PATH << File.expand_path("../lib", File.dirname(__FILE__))
+
+require 'man_parser'

metadata

@@ -0,0 +1,62 @@
+--- !ruby/object:Gem::Specification 
+name: man_parser
+version: !ruby/object:Gem::Version 
+  version: 0.1.0
+platform: ruby
+authors: 
+- Michael Grosser
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-10-03 00:00:00 +02:00
+default_executable: 
+dependencies: []
+
+description: 
+email: grosser.michael@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- README.markdown
+files: 
+- README.markdown
+- Rakefile
+- VERSION
+- lib/man_parser.rb
+- man_parser.gemspec
+- spec/man_parser_spec.rb
+- spec/spec_helper.rb
+has_rdoc: true
+homepage: http://github.com/grosser/man_parser
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+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: Parse unix man pages into ruby-readable format
+test_files: 
+- spec/man_parser_spec.rb
+- spec/spec_helper.rb