archive_io 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 85be778c44e05a1acce8d7da11e8b8d59e3959f7
+  data.tar.gz: eeda3b05ca916422564bed68c861f2c28c3f75d9
+SHA512:
+  metadata.gz: 93ebdc5b74f7aee6183b7645b71a2985cbc43e7946b7a1467032f420a20a1e708ed35b1bade51ca2459bbb80a9d395859eb568be2d2ff6065109004c97667b56
+  data.tar.gz: bf0cc25bc5054e8cbe70bd5d35c41b03e3a9c82202c5edf4d197e920187755120781492421ccec98ab035afae7e9f9ac63f7f18282bfee1af510b9fbd67014dc

data/.gitignore

@@ -0,0 +1,10 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+/spec/examples.txt

data/.rspec

@@ -0,0 +1,2 @@
+--color
+--require spec_helper

data/Gemfile

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

data/README.md

@@ -0,0 +1,57 @@
+# ArchiveIo
+
+Library which can traverse archived file (using [libarchive](http://www.libarchive.org/) under the hood) and yields IO like object on each file entry inside it for further streamline processing.
+
+**Note:** [libarchive](http://www.libarchive.org/) have to be pre-installed and available on the host system
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'archive_io'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install archive_io
+
+## Usage
+
+Simple usage:
+
+```ruby
+archive = ArchiveIO.open("archive.7z")
+archive.each do |cursor|
+  puts cursor.pathname # prints out pathname inside archive
+  puts cursor.read(10) # prints out beginning of each file
+end
+archive.close
+```
+
+This library can come in handy if you want to process huge xml files reading straight from the archive without uncompressing it and works nicely together with `Nokogiri::XML::Reader` and can be used as follows:
+
+```ruby
+archive = ArchiveIO.open("archive.7z")
+archive.select("*.xml") do |cursor|
+  Nokogiri::XML::Reader(cursor).each do |xml_node|
+    # your custom xml processing logic goes here
+  end
+end
+archive.close
+```
+
+## Development
+
+After checking out the repo, run `bundle install` to install dependencies. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/AMekss/archive_io.
+

data/Rakefile

@@ -0,0 +1,2 @@
+require "bundler/gem_tasks"
+task :default => :spec

data/archive_io.gemspec

@@ -0,0 +1,28 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'archive_io/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "archive_io"
+  spec.version       = ArchiveIO::VERSION
+  spec.authors       = ["Artūrs Mekšs"]
+  spec.email         = ["arturs.mekss@gmail.com"]
+
+  spec.summary       = %q{Library which can traverse archived file and yields io like object on each file in it.}
+  spec.description   = %q{Library which can traverse archived file (using `libarchive` under the hood) and yield io like object on each file entry inside it for further processing.}
+  spec.homepage      = "https://github.com/AMekss/archive_io"
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_dependency "ffi", "~> 1.9"
+
+  spec.add_development_dependency "bundler", "~> 1.11"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.5"
+  spec.add_development_dependency "pry"
+  spec.add_development_dependency "nokogiri"
+end

data/bin/console

@@ -0,0 +1,10 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "archive_io"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+require "pry"
+Pry.start

data/lib/archive_io.rb

@@ -0,0 +1,10 @@
+require "archive_io/version"
+require "archive_io/archive_reader"
+
+module ArchiveIO
+  def self.open(filename)
+    reader = ArchiveIO::ArchiveReader.new
+    reader.open(filename)
+    reader
+  end
+end

data/lib/archive_io/archive_reader.rb

@@ -0,0 +1,70 @@
+require "archive_io/lib_archive"
+require "archive_io/header"
+require "archive_io/file_reader"
+require "archive_io/wildcard_pattern"
+
+module ArchiveIO
+  class ArchiveReader
+    HEADER_HANDLING_STRATEGIES = {
+      LibArchive::OK => -> (pointer) { Header.new(pointer) },
+      LibArchive::EOF => -> (_) { nil },
+    }.freeze
+
+    def initialize
+      ObjectSpace.define_finalizer(self, &method(:close))
+    end
+
+    def open(filename)
+      close
+
+      @archive = LibArchive::archive_read_new
+      @filename = filename
+
+      assert_operation_valid(LibArchive::archive_read_support_compression_all(archive))
+      assert_operation_valid(LibArchive::archive_read_support_format_all(archive))
+      assert_operation_valid(LibArchive::archive_read_open_filename(archive, filename, 10240))
+    end
+
+    def each
+      raise LibArchive::NoArchiveError, "Archive is not open, call open with filename on archive before this operation" unless archive
+
+      while header = next_header
+        yield FileReader.new(header.pathname, archive) if header.file?
+      end
+
+      open(@filename) #reopen file for the next call
+    end
+
+    def select(pattern)
+      wildcard = WildcardPattern.new(pattern)
+
+      each do |file|
+        yield file if wildcard.match?(file.pathname)
+      end
+    end
+
+    def close
+      LibArchive::archive_read_finish(archive) if archive
+    ensure
+      @archive = nil
+      @filename = nil
+    end
+
+    private
+
+    attr_reader :archive
+
+    def header_handler(code)
+      HEADER_HANDLING_STRATEGIES.fetch(code) { raise LibArchive::Error, archive }
+    end
+
+    def next_header
+      header = LibArchive::archive_entry_new
+      header_handler(LibArchive::archive_read_next_header(archive, header)).call(header.read_pointer)
+    end
+
+    def assert_operation_valid(operation_result_code)
+      raise LibArchive::Error, archive if operation_result_code != LibArchive::OK
+    end
+  end
+end

data/lib/archive_io/file_reader.rb

@@ -0,0 +1,23 @@
+require "archive_io/lib_archive"
+
+module ArchiveIO
+  class FileReader
+    attr_reader :pathname
+
+    def initialize(pathname, archive)
+      @pathname = pathname
+      @archive = archive
+    end
+
+    def read(size)
+      buffer = FFI::MemoryPointer.new(:char, size)
+      return nil if LibArchive::archive_read_data(@archive, buffer, size) < 0
+      buffer.get_string(0)
+    end
+
+    def close
+      # does nothing, purpose of having it is to support IO like interface
+    end
+  end
+  private_constant :FileReader
+end

data/lib/archive_io/header.rb

@@ -0,0 +1,21 @@
+require "archive_io/lib_archive"
+
+module ArchiveIO
+  class Header
+    S_IFMT   = 0170000
+    S_IFREG  = 0100000 #  regular file
+
+    def initialize(pointer)
+      @pointer = pointer
+    end
+
+    def file?
+      LibArchive::archive_entry_filetype(@pointer) & S_IFMT == S_IFREG
+    end
+
+    def pathname
+      LibArchive::archive_entry_pathname(@pointer)
+    end
+  end
+  private_constant :Header
+end

data/lib/archive_io/lib_archive.rb

@@ -0,0 +1,35 @@
+require "ffi"
+
+module ArchiveIO
+  module LibArchive
+    extend FFI::Library
+
+    OK = 0
+    EOF = 1
+
+    ffi_lib ["archive", "libarchive.so.2"]
+
+    attach_function :archive_version_string, [], :string
+    attach_function :archive_read_open_filename, [:pointer, :string, :size_t], :int
+    attach_function :archive_read_support_compression_all, [:pointer], :int
+    attach_function :archive_read_support_format_all, [:pointer], :int
+    attach_function :archive_error_string, [:pointer], :string
+    attach_function :archive_read_new, [], :pointer
+    attach_function :archive_read_finish, [:pointer], :int
+    attach_function :archive_read_header_position, [:pointer], :int
+    attach_function :archive_read_next_header, [:pointer, :pointer], :int
+    attach_function :archive_read_data, [:pointer, :pointer, :size_t], :size_t
+
+    # entry
+    attach_function :archive_entry_new, [], :pointer
+    attach_function :archive_entry_filetype, [:pointer], :mode_t
+    attach_function :archive_entry_pathname, [:pointer], :string
+
+    class NoArchiveError < StandardError; end
+    class Error < StandardError
+      def initialize(archive)
+        super "#{LibArchive::archive_error_string(archive)}"
+      end
+    end
+  end
+end

data/lib/archive_io/version.rb

@@ -0,0 +1,3 @@
+module ArchiveIO
+  VERSION = "0.1.0"
+end

data/lib/archive_io/wildcard_pattern.rb

@@ -0,0 +1,12 @@
+module ArchiveIO
+  class WildcardPattern
+    def initialize(expression)
+      escaped = Regexp.escape(expression).gsub('\*','.*?')
+      @regex = Regexp.new "^#{escaped}$", Regexp::IGNORECASE
+    end
+
+    def match?(str)
+      !!(str =~ @regex)
+    end
+  end
+end

metadata

@@ -0,0 +1,143 @@
+--- !ruby/object:Gem::Specification
+name: archive_io
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Artūrs Mekšs
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2016-08-29 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: ffi
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.9'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.9'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.11'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.11'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.5'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.5'
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Library which can traverse archived file (using `libarchive` under the
+  hood) and yield io like object on each file entry inside it for further processing.
+email:
+- arturs.mekss@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- Gemfile
+- README.md
+- Rakefile
+- archive_io.gemspec
+- bin/console
+- lib/archive_io.rb
+- lib/archive_io/archive_reader.rb
+- lib/archive_io/file_reader.rb
+- lib/archive_io/header.rb
+- lib/archive_io/lib_archive.rb
+- lib/archive_io/version.rb
+- lib/archive_io/wildcard_pattern.rb
+homepage: https://github.com/AMekss/archive_io
+licenses: []
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.5.1
+signing_key: 
+specification_version: 4
+summary: Library which can traverse archived file and yields io like object on each
+  file in it.
+test_files: []