extract_files 0.0.1

data/.gitignore

@@ -0,0 +1,4 @@
+*.gem
+.bundle
+Gemfile.lock
+pkg/*

data/.travis.yml

@@ -0,0 +1,9 @@
+language: ruby
+rvm:
+  - 1.8.7
+  - 1.9.2
+  - 1.9.3
+  - jruby-18mode # JRuby in 1.8 mode
+  - jruby-19mode # JRuby in 1.9 mode
+  - rbx-18mode
+script: rake test

data/Gemfile

@@ -0,0 +1,4 @@
+source "http://rubygems.org"
+
+# Specify your gem's dependencies in extract_files.gemspec
+gemspec

data/README.md

@@ -0,0 +1,114 @@
+# extract_files
+
+Extract files from files or stdin for a given extension.
+
+## Yes, but i can do that with sed.
+
+I know. Before this I use this snippet:
+
+    for css_file in `find css -name "*.css" ` ; do sed  -n 's/^.*url *( *"*\'"'"'*\([^"]*\)\'"'"'*"* *).*$/'`dirname $css_file`'\/\1/p' $css_file  ; done | ruby  -n -e "puts File.expand_path(\$_)[File.expand_path('.').size+1..-1]"
+
+Probably could be improve.
+
+
+## Usage
+
+Given a css file with absolute and relative images
+
+		$ cat style.css
+		body {
+			background: url(../images/bg.jpg), url ( ../images/bg2.jpg );
+			background: url("../images/bg3.jpg");
+			background: url('/images/bg4.jpg);
+			background: url('images/bg5.jpg');
+		}
+
+Extract the images only ``-e jpg -e png -e gif``
+
+		$ cat style.css | extract_files -e jpg
+		../images/bg.jpg
+		../images/bg2.jpg
+		../images/bg3.jpg
+		/images/bg4.jpg
+		images/bg5.jpg
+
+Now, relative to the css directory ``-b css``
+
+		$ cat style.css | extract_files  -e jpg -b css
+		css/../images/bg.jpg
+		css/../images/bg2.jpg
+		css/../images/bg3.jpg
+		css/images/bg4.jpg
+		css/images/bg5.jpg
+
+And do the path expansion ``-p``.
+
+		$ cat style.css | extract_files  -e jpg -b css -p
+		images/bg.jpg
+		images/bg2.jpg
+		images/bg3.jpg
+		css/images/bg4.jpg
+		css/images/bg5.jpg
+
+Or show the full path ``-f``.
+
+		$ cat style.css | extract_files  -e jpg -b css -p -f
+		/Users/guillermo/Documents/extract_files/images/bg.jpg
+		/Users/guillermo/Documents/extract_files/images/bg2.jpg
+		/Users/guillermo/Documents/extract_files/images/bg3.jpg
+		/Users/guillermo/Documents/extract_files/css/images/bg4.jpg
+		/Users/guillermo/Documents/extract_files/css/images/bg5.jpg
+
+
+
+You can pass the file/files directly: 
+
+		$ extract_files * -e png
+		image1.png
+		/images/img1.png
+
+
+## Install
+
+There are two ways of installing this small libbrary:
+
+### Rubygems
+
+    $ gem install extract_files
+
+You will have the code as a library and the binary
+
+### Script only
+
+		curl -O https://raw.github.com/guillermo/extract_files/master/bin/extract_files
+		chmod +x extract_files
+
+## Development
+
+The script is generated automatically with rake, so if you fork, ensure that you edit the correct files.
+
+## License
+
+<pre>
+ ____               __        __             
+| __ )  ___  ___ _ _\ \      / /_ _ _ __ ___ 
+|  _ \ / _ \/ _ \ '__\ \ /\ / / _` | '__/ _ \
+| |_) |  __/  __/ |   \ V  V / (_| | | |  __/
+|____/ \___|\___|_|    \_/\_/ \__,_|_|  \___|
+                                             
+ _     _                         
+| |   (_) ___ ___ _ __  ___  ___ 
+| |   | |/ __/ _ \ '_ \/ __|/ _ \
+| |___| | (_|  __/ | | \__ \  __/
+|_____|_|\___\___|_| |_|___/\___|
+                                 
+----------------------------------------------------------------------------
+"THE BEER-WARE LICENSE" (Revision 42):
+guillermo@cientifico.net wrote this file. As long as you retain this 
+notice you can do whatever you want with this stuff. If we meet some day,
+and you think this stuff is worth it, you can buy me a beer in return 
+Guillermo Alvarez Fernandez
+----------------------------------------------------------------------------
+
+</pre>
+

data/Rakefile

@@ -0,0 +1,18 @@
+require "bundler/gem_tasks"
+require 'rake/clean'
+
+
+task :test do
+	sh "ruby -I lib -rubygems test/extract_files_test.rb"
+end
+
+file 'bin/extract_files' => ['lib/extract_files.rb', 'lib/extract_files/optparse.rb'] do
+	sh "echo '#!/usr/bin/env ruby' > bin/extract_files"
+	sh "cat lib/extract_files.rb >> bin/extract_files"
+	sh "cat lib/extract_files/cli.rb >> bin/extract_files"
+	sh "chmod +x bin/extract_files"
+end
+
+CLEAN.add 'bin/extract_files'
+
+

data/bin/extract_files

@@ -0,0 +1,121 @@
+#!/usr/bin/env ruby
+
+module ExtractFiles
+  VERSION = "0.0.1"
+
+  extend self
+
+  DEFAULT_EXTENSIONS = %w(png jpeg jpg gif css js)
+
+  # Process the input io, or anything that respond to __read__ and return a string.
+  # options are:
+  #
+  #   * **extensions**: Array of extensions to look for. Default is DEFAULT_EXTENSIONS
+  #
+  #   * **base**: Base directory. Image a relative path for a image **bg.png** in a css file inside the **styles** folder. The default output
+  #       will say "../images/bg.png". If you say that the base directory is "styles" the output will be "styles/../images/bg.png". Is unset by default.
+  #
+  #   * **expand**: If the output is somehing like "sytles/../images/bg.png" expand will convert that in "images/bg.png". Is enabled by false.
+  #
+  #   * **full_path**: Show the full_path
+  #
+  # If no **block** is passed, it will output to the stdout throught puts. If a block is given, it will yield each founded entry.
+  #
+  def extract!(io, options = {})
+    raise "Incorrect format for IO" unless io.respond_to?(:read)
+
+    options = {:extensions => DEFAULT_EXTENSIONS}.merge(options)
+
+    ext = "(" + options[:extensions].join("|") + ")"
+    re = /([a-z0-9\-_\/\.]*[a-z0-9]*\.#{ext})/i
+
+    io.read.scan(re).each do |match|
+      path = match[0]
+      path = File.join(options[:base], path) if options[:base]
+      path = simplify_path(path)             if options[:expand]
+      path = File.expand_path(path)          if options[:full_path]
+      if block_given?
+        yield path
+      else
+        puts path
+      end
+    end
+
+  end
+
+  # get! is a wrapper for extract! that returns and array of the matches.
+  def get!(io,options)
+    matches = []
+    extract!(io,options){|match| matches<<match}
+    matches
+  end
+
+  protected
+
+  def simplify_path(string)
+    string.gsub(/[^\/]*\/\.\.\//,'').gsub(/^\.\//,'').gsub(/\.\//,'')
+  end
+
+
+end
+
+require 'optparse'
+
+
+options = {:extensions => []}
+OptionParser.new do |opts|
+  opts.banner = "Usage: #{File.basename $0} [options] file"
+
+
+  opts.on("-e", "--ext EXT", "Extract files with extension EXT. Can be used several times.") do |v|
+    options[:extensions] << v
+  end
+
+	opts.separator ""
+
+  opts.on("-b", "--base-directory DIR", "Use DIR as a base directory") do |base_dir|
+    options[:base] = base_dir
+  end
+
+  opts.on("-p", "--expand-path", "Remove .. from output directories") do |e|
+    options[:expand] = true
+  end
+
+	opts.on("-f", "--full-path", "Show full path") do
+		options[:full_path] = true
+	end
+
+	opts.separator ""
+
+	opts.on("-v", "--version", "Show the version") do
+		puts ExtractFiles::VERSION
+		exit 0
+	end
+
+  opts.on_tail("-h", "--help", "Show this help") do
+    puts opts
+    exit 0
+  end
+
+end.parse!
+
+if ARGV.empty? || !$stdin.tty?
+	ExtractFiles.extract!($stdin, options)
+	exit 0
+end
+
+ARGV.each do |file|
+  (raise "File #{file} not found" ; exit -1) unless File.exists?(file)
+
+  if options[:extensions].any?
+
+		begin
+			file = File.open(file)
+			ExtractFiles.extract!(file, options)
+		ensure
+			file.close
+		end
+  end
+
+
+end

data/extract_files.gemspec

@@ -0,0 +1,22 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "extract_files"
+
+Gem::Specification.new do |s|
+  s.name        = "extract_files"
+  s.version     = ExtractFiles::VERSION
+  s.authors     = ["Guillermo Álvarez"]
+  s.email       = ["guillermo@cientifico.net"]
+  s.homepage    = "https://github.com/guillermo/extract_files"
+  s.summary     = %q{Extract files from stdin or files given an extension/extensions}
+  s.description = File.read('README.md')
+
+  s.rubyforge_project = "extract_files"
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+
+  s.add_development_dependency "minitest"
+end

data/lib/extract_files.rb

@@ -0,0 +1,59 @@
+
+module ExtractFiles
+  VERSION = "0.0.1"
+
+  extend self
+
+  DEFAULT_EXTENSIONS = %w(png jpeg jpg gif css js)
+
+  # Process the input io, or anything that respond to __read__ and return a string.
+  # options are:
+  #
+  #   * **extensions**: Array of extensions to look for. Default is DEFAULT_EXTENSIONS
+  #
+  #   * **base**: Base directory. Image a relative path for a image **bg.png** in a css file inside the **styles** folder. The default output
+  #       will say "../images/bg.png". If you say that the base directory is "styles" the output will be "styles/../images/bg.png". Is unset by default.
+  #
+  #   * **expand**: If the output is somehing like "sytles/../images/bg.png" expand will convert that in "images/bg.png". Is enabled by false.
+  #
+  #   * **full_path**: Show the full_path
+  #
+  # If no **block** is passed, it will output to the stdout throught puts. If a block is given, it will yield each founded entry.
+  #
+  def extract!(io, options = {})
+    raise "Incorrect format for IO" unless io.respond_to?(:read)
+
+    options = {:extensions => DEFAULT_EXTENSIONS}.merge(options)
+
+    ext = "(" + options[:extensions].join("|") + ")"
+    re = /([a-z0-9\-_\/\.]*[a-z0-9]*\.#{ext})/i
+
+    io.read.scan(re).each do |match|
+      path = match[0]
+      path = File.join(options[:base], path) if options[:base]
+      path = simplify_path(path)             if options[:expand]
+      path = File.expand_path(path)          if options[:full_path]
+      if block_given?
+        yield path
+      else
+        puts path
+      end
+    end
+
+  end
+
+  # get! is a wrapper for extract! that returns and array of the matches.
+  def get!(io,options)
+    matches = []
+    extract!(io,options){|match| matches<<match}
+    matches
+  end
+
+  protected
+
+  def simplify_path(string)
+    string.gsub(/[^\/]*\/\.\.\//,'').gsub(/^\.\//,'').gsub(/\.\//,'')
+  end
+
+
+end

data/lib/extract_files/cli.rb

@@ -0,0 +1,61 @@
+
+require 'optparse'
+
+
+options = {:extensions => []}
+OptionParser.new do |opts|
+  opts.banner = "Usage: #{File.basename $0} [options] file"
+
+
+  opts.on("-e", "--ext EXT", "Extract files with extension EXT. Can be used several times.") do |v|
+    options[:extensions] << v
+  end
+
+	opts.separator ""
+
+  opts.on("-b", "--base-directory DIR", "Use DIR as a base directory") do |base_dir|
+    options[:base] = base_dir
+  end
+
+  opts.on("-p", "--expand-path", "Remove .. from output directories") do |e|
+    options[:expand] = true
+  end
+
+	opts.on("-f", "--full-path", "Show full path") do
+		options[:full_path] = true
+	end
+
+	opts.separator ""
+
+	opts.on("-v", "--version", "Show the version") do
+		puts ExtractFiles::VERSION
+		exit 0
+	end
+
+  opts.on_tail("-h", "--help", "Show this help") do
+    puts opts
+    exit 0
+  end
+
+end.parse!
+
+if ARGV.empty? || !$stdin.tty?
+	ExtractFiles.extract!($stdin, options)
+	exit 0
+end
+
+ARGV.each do |file|
+  (raise "File #{file} not found" ; exit -1) unless File.exists?(file)
+
+  if options[:extensions].any?
+
+		begin
+			file = File.open(file)
+			ExtractFiles.extract!(file, options)
+		ensure
+			file.close
+		end
+  end
+
+
+end

data/lib/extract_files/optparse.rb

@@ -0,0 +1,4 @@
+
+
+
+

data/test/extract_files_test.rb

@@ -0,0 +1,47 @@
+
+require 'minitest/autorun'
+require 'extract_files'
+
+
+class ExtractFilesTest < MiniTest::Unit::TestCase
+
+  HTML = ["css/font.css", "css/font2.css", "../css/font3.css", "./css/font3.css", "js/script.js", "js/script2.JS", "/js/script3.JS", "./js/script4.JS", "/images/img1.png", "./images/img2.GIF", "../images/img3.GIF"]
+  JSON = ["image1.png", "image_3.jpeg", "images/img2.gif"]
+  CSS =  ["../images/bg.jpg", "../images/bg2.jpg", "../images/bg3.jpg", "/images/bg4.jpg", "images/bg5.jpg"]
+
+
+  def test_extract
+    assert_equal JSON, extract!('files.json'), 'should extract files from files.json'
+    assert_equal HTML, extract!('index.html'), 'should extract files from index.html'
+    assert_equal CSS, extract!('style.css'), 'should extract files from style.css'
+  end
+
+  CSS2 = ["fixtures/../images/bg.jpg", "fixtures/../images/bg2.jpg", "fixtures/../images/bg3.jpg", "fixtures/images/bg4.jpg", "fixtures/images/bg5.jpg"]
+
+  def test_base
+    assert_equal CSS2, extract!('style.css', :base => "fixtures"), 'should append fixtures path'
+  end
+
+  CSS3 = ["images/bg.jpg", "images/bg2.jpg", "images/bg3.jpg", "fixtures/images/bg4.jpg", "fixtures/images/bg5.jpg"]
+
+  def test_base_expand
+    assert_equal CSS3, extract!('style.css', :base => 'fixtures', :expand => true), "Should expand the path"
+  end
+
+  CSS4 = ["/images/bg.jpg", "/images/bg2.jpg", "/images/bg3.jpg", "/fixtures/images/bg4.jpg", "/fixtures/images/bg5.jpg"]
+  def test_base_expand_full
+    files = extract!('style.css', :base => 'fixtures', :expand => true, :full_path => true).map{|f| f[File.expand_path('.').size..-1]}
+    assert_equal CSS4, files, "Should show the full path"
+  end
+
+  def extract!(filename, options = {})
+    file = File.join(File.dirname($0), 'fixtures', filename)
+    raise "File #{file} not found" unless File.file?(file)
+
+    f = File.open(file,"r")
+    ExtractFiles.get!(f,options)
+  ensure
+    f.close
+  end
+
+end

data/test/fixtures/files.json

@@ -0,0 +1,2 @@
+{ url: "image1.png", url2: 'image_3.jpeg', url3: 'images/img2.gif' }
+

data/test/fixtures/index.html

@@ -0,0 +1,21 @@
+<html>
+  <head>
+    <link rel='stylesheet' href='css/font.css'/>
+    <link rel='stylesheet' href="css/font2.css"/>
+    <link rel="stylesheet" HREF="../css/font3.css"/>
+    <link rel="stylesheet" HREF="./css/font3.css"/>
+
+    <script src="js/script.js"></script>
+    <script src="js/script2.JS"></script>
+    <script src="/js/script3.JS"></script>
+    <script src="./js/script4.JS"></script>
+  </head>
+  <body>
+    <img src="/images/img1.png">
+    <img src="./images/img2.GIF">
+    <img src="../images/img3.GIF">
+  </body>
+</html>
+
+
+

data/test/fixtures/style.css

@@ -0,0 +1,6 @@
+body {
+  background: url(../images/bg.jpg), url ( ../images/bg2.jpg );
+  background: url("../images/bg3.jpg");
+  background: url('/images/bg4.jpg);
+  background: url('images/bg5.jpg');
+}

metadata

@@ -0,0 +1,105 @@
+--- !ruby/object:Gem::Specification
+name: extract_files
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- Guillermo Álvarez
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-02-11 00:00:00.000000000Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: &70282753354860 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *70282753354860
+description: ! "# extract_files\n\nExtract files from files or stdin for a given extension.\n\n##
+  Yes, but i can do that with sed.\n\nI know. Before this I use this snippet:\n\n
+  \   for css_file in `find css -name \"*.css\" ` ; do sed  -n 's/^.*url *( *\"*\\'\"'\"'*\\([^\"]*\\)\\'\"'\"'*\"*
+  *).*$/'`dirname $css_file`'\\/\\1/p' $css_file  ; done | ruby  -n -e \"puts File.expand_path(\\$_)[File.expand_path('.').size+1..-1]\"\n\nProbably
+  could be improve.\n\n\n## Usage\n\nGiven a css file with absolute and relative images\n\n\t\t$
+  cat style.css\n\t\tbody {\n\t\t\tbackground: url(../images/bg.jpg), url ( ../images/bg2.jpg
+  );\n\t\t\tbackground: url(\"../images/bg3.jpg\");\n\t\t\tbackground: url('/images/bg4.jpg);\n\t\t\tbackground:
+  url('images/bg5.jpg');\n\t\t}\n\nExtract the images only ``-e jpg -e png -e gif``\n\n\t\t$
+  cat style.css | extract_files -e jpg\n\t\t../images/bg.jpg\n\t\t../images/bg2.jpg\n\t\t../images/bg3.jpg\n\t\t/images/bg4.jpg\n\t\timages/bg5.jpg\n\nNow,
+  relative to the css directory ``-b css``\n\n\t\t$ cat style.css | extract_files
+  \ -e jpg -b css\n\t\tcss/../images/bg.jpg\n\t\tcss/../images/bg2.jpg\n\t\tcss/../images/bg3.jpg\n\t\tcss/images/bg4.jpg\n\t\tcss/images/bg5.jpg\n\nAnd
+  do the path expansion ``-p``.\n\n\t\t$ cat style.css | extract_files  -e jpg -b
+  css -p\n\t\timages/bg.jpg\n\t\timages/bg2.jpg\n\t\timages/bg3.jpg\n\t\tcss/images/bg4.jpg\n\t\tcss/images/bg5.jpg\n\nOr
+  show the full path ``-f``.\n\n\t\t$ cat style.css | extract_files  -e jpg -b css
+  -p -f\n\t\t/Users/guillermo/Documents/extract_files/images/bg.jpg\n\t\t/Users/guillermo/Documents/extract_files/images/bg2.jpg\n\t\t/Users/guillermo/Documents/extract_files/images/bg3.jpg\n\t\t/Users/guillermo/Documents/extract_files/css/images/bg4.jpg\n\t\t/Users/guillermo/Documents/extract_files/css/images/bg5.jpg\n\n\n\nYou
+  can pass the file/files directly: \n\n\t\t$ extract_files * -e png\n\t\timage1.png\n\t\t/images/img1.png\n\n\n##
+  Install\n\nThere are two ways of installing this small libbrary:\n\n### Rubygems\n\n
+  \   $ gem install extract_files\n\nYou will have the code as a library and the binary\n\n###
+  Script only\n\n\t\tcurl -O https://raw.github.com/guillermo/extract_files/master/bin/extract_files\n\t\tchmod
+  +x extract_files\n\n## Development\n\nThe script is generated automatically with
+  rake, so if you fork, ensure that you edit the correct files.\n\n## License\n\n<pre>\n
+  ____               __        __             \n| __ )  ___  ___ _ _\\ \\      / /_
+  _ _ __ ___ \n|  _ \\ / _ \\/ _ \\ '__\\ \\ /\\ / / _` | '__/ _ \\\n| |_) |  __/
+  \ __/ |   \\ V  V / (_| | | |  __/\n|____/ \\___|\\___|_|    \\_/\\_/ \\__,_|_|
+  \ \\___|\n                                             \n _     _                         \n|
+  |   (_) ___ ___ _ __  ___  ___ \n| |   | |/ __/ _ \\ '_ \\/ __|/ _ \\\n| |___| |
+  (_|  __/ | | \\__ \\  __/\n|_____|_|\\___\\___|_| |_|___/\\___|\n                                 \n----------------------------------------------------------------------------\n\"THE
+  BEER-WARE LICENSE\" (Revision 42):\nguillermo@cientifico.net wrote this file. As
+  long as you retain this \nnotice you can do whatever you want with this stuff. If
+  we meet some day,\nand you think this stuff is worth it, you can buy me a beer in
+  return \nGuillermo Alvarez Fernandez\n----------------------------------------------------------------------------\n\n</pre>\n\n"
+email:
+- guillermo@cientifico.net
+executables:
+- extract_files
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- .travis.yml
+- Gemfile
+- README.md
+- Rakefile
+- bin/extract_files
+- extract_files.gemspec
+- lib/extract_files.rb
+- lib/extract_files/cli.rb
+- lib/extract_files/optparse.rb
+- test/extract_files_test.rb
+- test/fixtures/files.json
+- test/fixtures/index.html
+- test/fixtures/style.css
+homepage: https://github.com/guillermo/extract_files
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: extract_files
+rubygems_version: 1.8.10
+signing_key: 
+specification_version: 3
+summary: Extract files from stdin or files given an extension/extensions
+test_files:
+- test/extract_files_test.rb
+- test/fixtures/files.json
+- test/fixtures/index.html
+- test/fixtures/style.css