lyber-utils 0.1.2

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2011 Stanford University Library
+
+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.rdoc

@@ -0,0 +1,31 @@
+= lyber_utils
+
+Require the following:
+  require 'lyber_utils'
+
+
+This will give you:
+  LyberUtils::BagitBag
+  LyberUtils::ChecksumValidate
+  LyberUtils::FileUtilities
+
+If you do not want all 3, you can require the individual classes.  I.E. if you only want the bagit utils, then require:
+  require 'lyber_utils/bagit_bag'
+
+The BagitBag class requires the bagit gem
+  http://github.com/flazz/bagit
+
+== Build and release procedure
+Modify the version number in lyber-utils.gemspec, then push your commits to AFS.  DO NOT TAG!
+Run: 'rake dlss_release' to tag, build, and publish the lyber-core gem
+See the Rakefile and the LyberCore::DlssRelease task in lyberteam-devel/lib/dlss/rake/dlss_release.rb
+for more details
+
+== Releases
+- <b>1.3</b> Started to use Dor::Config for workspace configuration
+- <b>0.1.1</b> Update dependent version of nokogiri for more flexibility
+- <b>0.1.2</b> Ensure bag begins with an empty directory.  Disallow nil values in bag-info.txt properties
+
+== Copyright
+
+Copyright (c) 2011 Stanford University Library. See LICENSE for details.

data/lib/lyber-utils.rb

@@ -0,0 +1,3 @@
+require 'lyber_utils/file_utilities'
+require 'lyber_utils/checksum_validate'
+require 'lyber_utils/bagit_bag'

data/lib/lyber_utils/bagit_bag.rb

@@ -0,0 +1,108 @@
+require 'find'
+require 'fileutils'
+require 'bagit' # http://github.com/flazz/bagit
+
+module LyberUtils
+
+  class BagitBag
+
+    attr_reader :bag_dir
+
+    def initialize(bag_dir)
+      @bag_dir = bag_dir
+      create_bag
+    end
+
+    def create_bag()
+      if (File.exist?(@bag_dir))
+        FileUtils.rm_r(@bag_dir)
+      end
+      @bag = BagIt::Bag.new @bag_dir
+    end
+
+    def add_content_files(source_dir, use_links)
+      data_content_dir = File.join(@bag_dir, 'data', 'content')
+      copy_dir(source_dir, data_content_dir, use_links)
+    end
+
+    def copy_dir(source_dir, target_dir, use_links)
+      FileUtils.mkdir_p(target_dir)
+      Dir.foreach(source_dir) do |file|
+        unless (file == '.' or file == '..')
+          source_file = File.join(source_dir, file)
+          target_file = File.join(target_dir, file)
+          if File.directory?(source_file)
+            copy_dir(source_file, target_file, use_links)
+          elsif (use_links)
+            FileUtils.ln(source_file, target_file, :force => true)
+          else
+            FileUtils.cp(source_file, target_file)
+          end
+        end
+      end
+    end
+
+    def add_metadata_file_from_string(metadata_string, file_name)
+      if (not metadata_string.nil?)
+        data_file_path = "metadata/#{file_name}"
+        @bag.add_file(data_file_path) do |io|
+          io.puts metadata_string
+        end
+      end
+    end
+
+    def write_metadata_info(md_hash)
+      # make sure none of the md_hash values are nil
+      md_hash.each  do |key, value|
+        raise "The bag-info.txt value for #{key} is not allowed to be nil" if value.nil?
+      end
+      payload = bag_payload()
+      bag_info_hash = {
+          'Bag-Size' => bag_size_human(payload[0]),
+          'Payload-Oxum' => "#{payload[0]}.#{payload[1]}",
+          'Bagging-Date' => DateTime.now.to_s[0..9]
+      }
+      @bag.write_bag_info(md_hash.merge(bag_info_hash))
+    end
+
+    def bag_payload()
+      bytes = 0
+      files = 0
+      Find.find(@bag.data_dir) do |filepath|
+        if (not File.directory?(filepath))
+          bytes += File.size(filepath)
+          files += 1
+        end
+      end
+      return [bytes, files]
+    end
+
+    def bag_size_human(bytes)
+      count = 0
+      size = bytes
+      while (size >= 1000 and count < 4)
+        size /= 1000.0
+        count += 1
+      end
+      if (count == 0)
+        return sprintf("%d B", size)
+      else
+        return sprintf("%.2f %s", size, %w[B KB MB GB TB][count])
+      end
+    end
+
+    def write_manifests()
+      @bag.manifest!
+      @bag.tagmanifest!
+    end
+
+    def validate()
+      if not @bag.valid?
+        raise "bag not valid: #{@bag_dir}"
+      end
+
+    end
+
+  end
+
+end

data/lib/lyber_utils/checksum_validate.rb

@@ -0,0 +1,109 @@
+require 'nokogiri'
+
+
+module LyberUtils
+
+  class ChecksumValidate
+
+    # Test the equality of two hashes
+    # @return [Boolean]
+    def self.compare_hashes(hash1, hash2)
+      return (hash1 == hash2)
+    end
+
+    # create a new hash containing:
+    # entries from hash1 where:
+    # * key is in hash1 but missing from hash2
+    # * value is different in the two hashes
+    # entries from hash2 where:
+    # * key is in hash2 but missing from hash1
+    # @return [Hash]
+    def self.get_hash_differences(hash1, hash2)
+      hash1.reject { |k, v| hash2[k] == v }.merge!(hash2.reject { |k, v| hash1.has_key?(k) })
+    end
+
+    # Generate a filename => checksum hash
+    # from an output of the md5sum (or compatible) program
+    # @return [Hash]
+    def self.md5_hash_from_md5sum(md5sum)
+      checksum_hash = {}
+      md5sum.each do |line|
+        line.chomp!
+        digest, filename = line.split(/[ *]{2}/)
+        checksum_hash[filename] = digest.downcase
+      end
+      return checksum_hash
+    end
+
+    # Generate a filename => checksum hash
+    # from the contents of a METS file
+    # @return [Hash]
+    def self.md5_hash_from_mets(mets)
+      mets_checksum_hash = {}
+      doc = Nokogiri::XML(mets)
+      doc.xpath('/mets:mets/mets:fileSec//mets:file', {'mets' => 'http://www.loc.gov/METS/'}).each do |filenode|
+        digest = filenode.attribute('CHECKSUM')
+        if (digest)
+          flocat = filenode.xpath('mets:FLocat', {'mets' => 'http://www.loc.gov/METS/'}).first
+          if (flocat)
+            filename = flocat.attribute_with_ns('href', 'http://www.w3.org/1999/xlink')
+            if (filename)
+              mets_checksum_hash[filename.text] = digest.text.downcase
+            end
+          end
+        end
+      end
+      return mets_checksum_hash
+    end
+
+    # Generate a filename => checksum hash
+    # from contentMetadata XML
+    # @return [Hash]
+    def self.md5_hash_from_content_metadata(content_md)
+      content_md_checksum_hash = {}
+      doc = Nokogiri::XML(content_md)
+      doc.xpath('/contentMetadata/resource[@type="page"]/file').each do |filenode|
+        filename = filenode.attribute('id')
+        if (filename)
+          md5_element = filenode.xpath('checksum[@type="MD5"]').first
+          if (md5_element)
+            digest = md5_element.text
+            if (digest)
+              content_md_checksum_hash[filename.text] = digest.downcase
+            end
+          end
+        end
+      end
+      return content_md_checksum_hash
+    end
+
+      # Verifies MD5 checksums for the files in a directory
+      # against the checksum values in the supplied file
+      # (Uses md5sum command)
+      #
+      # = Inputs:
+      # * directory = dirname containing the file to be checked
+      # * checksum_file = the name of the file containing the expected checksums
+      #
+      # = Return value:
+      # * The method will return true if the verification is successful.
+      # * The method will raise an exception if either the md5sum command fails,
+      # or a test of the md5sum output indicates a checksum mismatch.
+      # The exception's message will contain the explaination of the failure.
+    def self.verify_md5sum_checksums(directory, checksum_file)
+#      LyberCore::Log.debug("verifying checksums in #{directory}")
+      dir_save = Dir.pwd
+      Dir.chdir(directory)
+      checksum_cmd = 'md5sum -c ' + checksum_file + ' | grep -v OK | wc -l'
+      badcount = FileUtilities.execute(checksum_cmd).to_i
+      if not (badcount==0)
+        raise "#{badcount} files had bad checksums"
+      end
+      return true
+    ensure
+      Dir.chdir(dir_save)
+    end
+
+  end
+
+end

data/lib/lyber_utils/file_utilities.rb

@@ -0,0 +1,169 @@
+require 'fileutils'
+require 'systemu'
+
+# File Utilities for use in transferring filesystem objects,
+# decrypting a file, unpacking a targz archive, and validating checksums
+# @author rnanders@stanford.edu
+module LyberUtils
+
+  class FileUtilities
+
+
+    # Executes a system command in a subprocess.
+    # The method will return stdout from the command if execution was successful.
+    # The method will raise an exception if if execution fails.
+    # The exception's message will contain the explaination of the failure.
+    # @param [String] command the command to be executed
+    # @return [String] stdout from the command if execution was successful
+    def FileUtilities.execute(command)
+      status, stdout, stderr = systemu(command)
+      if (status.exitstatus != 0)
+        raise stderr
+      end
+      return stdout
+    rescue
+      msg = "Command failed to execute: [#{command}] caused by <STDERR = #{stderr.split($/).join('; ')}>"
+      msg << " STDOUT = #{stdout.split($/).join('; ')}" if (stdout && (stdout.length > 0))
+      raise msg
+
+    end
+
+      # Generates a dirname for storing or retrieving a file in
+      # "pair tree" hierachical structure, where the path is derived
+      # from segments of a barcode string
+      #
+      # = Input:
+      # * barcode = barcode string
+      #
+      # = Return value:
+      # * A string containing a slash-delimited dirname derived from the barcode
+    def FileUtilities.pair_tree_from_barcode(barcode)
+      if (barcode.class != String)
+        raise "Barcode must be a String"
+      end
+        # figure out if this is a SUL barcode or from coordinate library
+      library_prefix=barcode[0..4]
+      if (library_prefix == '36105')
+        pair_tree=barcode[5..10].gsub(/(..)/, '\1/')
+      else
+        library_prefix=barcode[0..2]
+        pair_tree=barcode[3..8].gsub(/(..)/, '\1/')
+      end
+      return "#{library_prefix}/#{pair_tree}"
+    end
+
+      # Transfers a filesystem object (file or directory)
+      # from a source to a target location. Uses rsync in "archive" mode
+      # over an ssh connection.
+      #
+      # = Inputs:
+      # * filename = basename of the filesystem object to be transferred
+      # * source_dir = dirname of the source location from which the object is read
+      # * dest_dir = dirname of the target location to which the object is written
+      # If one of the locations is on a remote server, then the dirname should be
+      # prefixed with  user@hosthame:
+      #
+      # = Return value:
+      # * The method will return true if the transfer is successful.
+      # * The method will raise an exception if either the rsync command fails,
+      # or a test for the existence of the transferred object fails.
+      # The exception's message will contain the explaination of the failure
+      #
+      # Network transfers will only succeed if the appropriate public key
+      # authentication has been previously set up.
+    def FileUtilities.transfer_object(filename, source_dir, dest_dir)
+      source_path=File.join(source_dir, filename)
+      rsync='rsync -a -e ssh '
+      rsync_cmd = rsync + "'" + source_path + "' " + dest_dir
+#      LyberCore::Log.debug("rsync command is: #{rsync_cmd}")
+      self.execute(rsync_cmd)
+      if not File.exists?(File.join(dest_dir, filename))
+        raise "#{filename} is not found in  #{dest_dir}"
+      end
+      return true
+    end
+
+      # Decrypts a GPG encrypted file using the "gpg" command
+      #
+      # = Inputs:
+      # * workspace_dir = dirname containing the file
+      # * targzgpg = the filename of the GPG encrypted file
+      # * targz = the filename of the unencrypted file
+      # * passphrase = the string used to decrypt the file
+      #
+      # = Return value:
+      # * The method will return true if the decryption is successful.
+      # * The method will raise an exception if either the decryption command fails,
+      # or a test for the existence of the decrypted file fails.
+      # The exception's message will contain the explaination of the failure
+    def FileUtilities.gpgdecrypt(workspace_dir, targzgpg, targz, passphrase)
+#      LyberCore::Log.debug("decrypting #{targzgpg}")
+      gpg_cmd="/usr/bin/gpg --passphrase '#{passphrase}'  " +
+          "--batch --no-mdc-warning --no-secmem-warning " +
+          " --output " + File.join(workspace_dir, targz) +
+          " --decrypt " + File.join(workspace_dir, targzgpg)
+      self.execute(gpg_cmd)
+      if not File.exists?(File.join(workspace_dir, targz))
+        raise "#{targz} was not created in  #{workspace_dir}"
+      end
+      return true
+    end
+
+      # Unpacks a TAR-ed, GZipped archive using a "tar -xzf" command
+      #
+      # = Inputs:
+      # * original_dir = dirname containing the archive file
+      # * targz = the filename of the archive file
+      # * destination_dir = the target directory into which the contents are written
+      #
+      # = Return value:
+      # * The method will return true if the unpacking is successful.
+      # * The method will raise an exception if either the unpack command fails,
+      # or a test for the existence of files in the target directory fails.
+      # The exception's message will contain the explaination of the failure.
+    def FileUtilities.unpack(original_dir, targz, destination_dir)
+ #     LyberCore::Log.debug("unpacking #{targz}")
+      FileUtils.mkdir_p(destination_dir)
+      dir_save = Dir.pwd
+      Dir.chdir(destination_dir)
+      unpack_cmd="tar -xzf " + File.join(original_dir, targz)
+      self.execute(unpack_cmd)
+      if not (Dir.entries(destination_dir).length > 0)
+        raise "#{destination_dir} is empty"
+      end
+      return true
+    ensure
+      Dir.chdir(dir_save)
+    end
+
+      # Tars a directory hierarchy
+      #
+      # = Inputs:
+      # * source_path = the filesystem object to be tarred
+      # * dest_path = name of the tar file to be written
+      #     (if nil create sourcname.tar in the same dir as the source object)
+      #
+      # = Return value:
+      # * The method will return true if the transfer is successful.
+      # * The method will raise an exception if either the rsync command fails,
+      # or a test for the existence of the transferred object fails.
+      # The exception's message will contain the explaination of the failure
+      #
+      def FileUtilities.tar_object(source_path, dest_path=nil)
+        if (dest_path.nil?)
+            dest_path = source_path + ".tar"
+        end
+        parent_path = File.dirname(source_path)
+        object_name = File.basename(source_path)
+        tar="cd #{parent_path}; tar --force-local -chf "
+        tar_cmd = "#{tar} '#{dest_path}' '#{object_name}'"
+        self.execute(tar_cmd)
+        if not File.exists?(dest_path)
+          raise "#{dest_path} was not created"
+        end
+        return true
+      end
+
+  end
+
+end

data/lib/tasks/rdoc.rake

@@ -0,0 +1,32 @@
+desc "Generate RDoc"
+task :doc => ['doc:generate']
+
+namespace :doc do
+  project_root = File.expand_path(File.join(File.dirname(__FILE__), '..', '..'))
+  doc_destination = File.join(project_root, 'rdoc')
+
+  begin
+    require 'yard'
+    require 'yard/rake/yardoc_task'
+
+    YARD::Rake::YardocTask.new(:generate) do |yt|
+      yt.files   =  Dir.glob(File.join(project_root, 'lib', '*.rb')) + 
+                    Dir.glob(File.join(project_root, 'lib', '**', '*.rb')) +
+                   [ File.join(project_root, 'README.rdoc') ] +
+                   [ File.join(project_root, 'LICENSE') ]
+                   
+      yt.options = ['--output-dir', doc_destination, '--readme', 'README.rdoc']
+    end
+  rescue LoadError
+    desc "Generate YARD Documentation"
+    task :generate do
+      abort "Please install the YARD gem to generate rdoc."
+    end
+  end
+
+  desc "Remove generated documenation"
+  task :clean do
+    rm_r doc_destination if File.exists?(doc_destination)
+  end
+
+end

metadata

@@ -0,0 +1,241 @@
+--- !ruby/object:Gem::Specification 
+name: lyber-utils
+version: !ruby/object:Gem::Version 
+  hash: 31
+  prerelease: 
+  segments: 
+  - 0
+  - 1
+  - 2
+  version: 0.1.2
+platform: ruby
+authors: 
+- Richard Anderson
+- Willy Mene
+- Michael Klein
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2011-09-27 00:00:00 Z
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 27
+        segments: 
+        - 0
+        - 1
+        - 0
+        version: 0.1.0
+  version_requirements: *id001
+  name: bagit
+  prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency 
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 113
+        segments: 
+        - 1
+        - 4
+        - 3
+        - 1
+        version: 1.4.3.1
+  version_requirements: *id002
+  name: nokogiri
+  prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency 
+  requirement: &id003 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 31
+        segments: 
+        - 1
+        - 2
+        - 0
+        version: 1.2.0
+  version_requirements: *id003
+  name: systemu
+  prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency 
+  requirement: &id004 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  version_requirements: *id004
+  name: validatable
+  prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency 
+  requirement: &id005 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 13
+        segments: 
+        - 0
+        - 4
+        - 1
+        version: 0.4.1
+  version_requirements: *id005
+  name: lyberteam-devel
+  prerelease: false
+  type: :development
+- !ruby/object:Gem::Dependency 
+  requirement: &id006 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 49
+        segments: 
+        - 0
+        - 8
+        - 7
+        version: 0.8.7
+  version_requirements: *id006
+  name: rake
+  prerelease: false
+  type: :development
+- !ruby/object:Gem::Dependency 
+  requirement: &id007 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  version_requirements: *id007
+  name: rcov
+  prerelease: false
+  type: :development
+- !ruby/object:Gem::Dependency 
+  requirement: &id008 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  version_requirements: *id008
+  name: rdoc
+  prerelease: false
+  type: :development
+- !ruby/object:Gem::Dependency 
+  requirement: &id009 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - <
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 2
+        - 0
+        version: "2.0"
+  version_requirements: *id009
+  name: rspec
+  prerelease: false
+  type: :development
+- !ruby/object:Gem::Dependency 
+  requirement: &id010 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  version_requirements: *id010
+  name: ruby-debug
+  prerelease: false
+  type: :development
+- !ruby/object:Gem::Dependency 
+  requirement: &id011 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  version_requirements: *id011
+  name: yard
+  prerelease: false
+  type: :development
+description: Contains classes perform generic utilty functions
+email: 
+- rnanders@stanford.edu
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- lib/lyber-utils.rb
+- lib/lyber_utils/bagit_bag.rb
+- lib/lyber_utils/checksum_validate.rb
+- lib/lyber_utils/file_utilities.rb
+- lib/tasks/rdoc.rake
+- LICENSE
+- README.rdoc
+homepage: 
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 23
+      segments: 
+      - 1
+      - 3
+      - 6
+      version: 1.3.6
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.8.10
+signing_key: 
+specification_version: 3
+summary: Generic utilities used by the SULAIR Digital Library
+test_files: []
+