hydra-file_characterization 0.0.1 → 0.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: b48cc683c771d57e58d8e3ba222f55822d1b2aca
-  data.tar.gz: 384687f9e2a2dd88304addc3c34681a5c05d065e
+  metadata.gz: 3042462b8a14d3ec133d9ccc86fa20663fe4260d
+  data.tar.gz: 12e6b321515dfdcbf5621d107bf8b9a28ea0a597
 SHA512:
-  metadata.gz: c2febb48269319ea4d22a31d07da41a5d5fa3ccf8293f878d333339c90bf1ad2c69379587de1751db4d6a7953614f3e4f634e42b66aa1d2e7b04d792a009b871
-  data.tar.gz: 46ba44281c3773fb119c2ff3b196fcfce7e83e4a03b4711d4590d210ac04d786f455322df0ca6969b6a3d84408d590daafc1ee2b8654777eda7d334a656ac21f
+  metadata.gz: 53c9607e32ab504221c9f8752450af260ac109ebd497d85c546e5fd35dc22293169b16ddef8884351a34e4a1759636a45461a8172f8ac774d867a57d09080568
+  data.tar.gz: 4b1bdb304e398b2f78e5ce039d94e666373d6f247d11d7912fba2db35ac51f1daed7dcad21924df53be7fa875e9048aab9091f74c21cbc50816ad1277c826309

data/.gitignore

@@ -15,3 +15,4 @@ spec/reports
 test/tmp
 test/version_tmp
 tmp
+.idea/

data/.rspec

@@ -0,0 +1,2 @@
+--color
+--format progress

data/Guardfile

@@ -0,0 +1,8 @@
+# A sample Guardfile
+# More info at https://github.com/guard/guard#readme
+
+guard 'rspec' do
+  watch(%r{^spec/.+_spec\.rb$})
+  watch(%r{^lib/(.+)\.rb$})     { |m| "spec/lib/#{m[1]}_spec.rb" }
+  watch('spec/spec_helper.rb')  { "spec" }
+end

data/README.md

@@ -13,6 +13,13 @@ How others are using the extract_metadata method
 
 ## Todo Steps
 
-- Given a filename, characterize the file and return a raw XML stream
+- ~~Given a filename, characterize the file and return a raw XML stream~~
+- Provide method for converting a StringIO and original file name to a temp file with comparable, then running the characterizer against the tempfile
+- Provide a configuration option for the fits path; This would be the default for the characterizer
+- Update existing Sufia implementation
+  - Deprecrate Hydra::Derivatives direct method call
+  - Instead call the characterizer with the content
 - Allow characterization services to be chained together
+  - This would involve renaming the Characterizer to something else (i.e. Characterizers::Fits)
 - Provide an ActiveFedora Datastream that maps the raw XML stream to a datastructure
+

data/hydra-file_characterization.gemspec

@@ -8,11 +8,15 @@ Gem::Specification.new do |gem|
   gem.version       = Hydra::FileCharacterization::VERSION
   gem.authors       = [
     "James Treacy",
-    "Jeremy Friesen"
+    "Jeremy Friesen",
+    "Sue Richeson",
+    "Rajesh Balekai"
   ]
   gem.email         = [
     "jatr@kb.dk",
-    "jeremy.n.friesen@gmail.com"
+    "jeremy.n.friesen@gmail.com",
+    "spr7b@virginia.edu",
+    "rbalekai@gmail.com"
   ]
   gem.description   = %q{To provide a wrapper for file characterization}
   gem.summary       = %q{To provide a wrapper for file characterization}
@@ -23,4 +27,9 @@ Gem::Specification.new do |gem|
   gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
   gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
   gem.require_paths = ["lib"]
+
+  gem.add_dependency "activesupport", ">= 3.0.0"
+  gem.add_development_dependency "rspec"
+  gem.add_development_dependency "guard"
+  gem.add_development_dependency 'guard-rspec'
 end

data/lib/hydra-file_characterization.rb

@@ -1,7 +1,14 @@
 require "hydra-file_characterization/version"
+require "hydra-file_characterization/characterizer"
+require "active_support/configurable"
 
 module Hydra
   module FileCharacterization
-    # Your code goes here...
+
+    class Configuration
+      include ActiveSupport::Configurable
+      config_accessor :fits_path
+    end
   end
 end
+

data/lib/hydra-file_characterization/characterizer.rb

@@ -0,0 +1,36 @@
+require 'open3'
+
+module Hydra::FileCharacterization
+
+  class Characterizer
+    include Open3
+
+    class FileNotFoundError < RuntimeError
+    end
+
+    attr_reader :filename, :fits_path
+    def initialize(filename, fits_path)
+      @filename = filename
+      @fits_path = fits_path
+    end
+
+    def call
+      unless File.exists?(filename)
+        raise FileNotFoundError.new("File: #{filename} does not exist.")
+      end
+      command = "#{fits_path} -i \"#{filename}\""
+      stdin, stdout, stderr, wait_thr = popen3(command)
+      begin
+        out = stdout.read
+        err = stderr.read
+        exit_status = wait_thr.value
+        raise "Unable to execute command \"#{command}\"\n#{err}" unless exit_status.success?
+        out
+      ensure
+        stdin.close
+        stdout.close
+        stderr.close
+      end
+    end
+  end
+end

data/lib/hydra-file_characterization/to_temp_file.rb

@@ -0,0 +1,25 @@
+require 'open3'
+
+module Hydra::FileCharacterization
+  class ToTempFile
+    include Open3
+
+    attr_accessor :data, :filename
+
+    def initialize(data, filename)
+      @data = data
+      @filename = filename
+    end
+
+    def call
+      return unless data.empty?
+      timestamp = DateTime.now.strftime("%Y%m%d%M%S")
+      Tempfile.open("#{timestamp}_#{File.basename(filename)}") do |f|
+        f.binmode
+        f.write(data)
+        f.rewind
+        yield(f)
+      end
+    end
+  end
+end

data/lib/hydra-file_characterization/version.rb

@@ -1,5 +1,5 @@
 module Hydra
   module FileCharacterization
-    VERSION = "0.0.1"
+    VERSION = "0.0.2"
   end
 end

data/spec/fixtures/archive.zip.fits.xml

@@ -0,0 +1,24 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<fits xmlns="http://hul.harvard.edu/ois/xml/ns/fits/fits_output" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://hul.harvard.edu/ois/xml/ns/fits/fits_output http://hul.harvard.edu/ois/xml/xsd/fits/fits_output.xsd" version="0.6.2" timestamp="9/17/13 3:46 PM">
+  <identification>
+    <identity format="ZIP Format" mimetype="application/zip" toolname="FITS" toolversion="0.6.2">
+      <tool toolname="file utility" toolversion="5.04" />
+      <tool toolname="Exiftool" toolversion="9.06" />
+      <tool toolname="Droid" toolversion="3.0" />
+      <tool toolname="ffident" toolversion="0.2" />
+      <version toolname="file utility" toolversion="5.04">2.0</version>
+      <externalIdentifier toolname="Droid" toolversion="3.0" type="puid">x-fmt/263</externalIdentifier>
+    </identity>
+  </identification>
+  <fileinfo>
+    <lastmodified toolname="Exiftool" toolversion="9.06" status="SINGLE_RESULT">2013:09:17 15:45:51-04:00</lastmodified>
+    <filepath toolname="OIS File Information" toolversion="0.1" status="SINGLE_RESULT">/Users/jfriesen/Repositories/hydra-file_characterization/spec/fixtures/archive.zip</filepath>
+    <filename toolname="OIS File Information" toolversion="0.1" status="SINGLE_RESULT">spec/fixtures/archive.zip</filename>
+    <size toolname="OIS File Information" toolversion="0.1" status="SINGLE_RESULT">302</size>
+    <md5checksum toolname="OIS File Information" toolversion="0.1" status="SINGLE_RESULT">7c5b22ea09ba0eb837f70e2e8094b26f</md5checksum>
+    <fslastmodified toolname="OIS File Information" toolversion="0.1" status="SINGLE_RESULT">1379447151000</fslastmodified>
+  </fileinfo>
+  <filestatus />
+  <metadata />
+</fits>
+

data/spec/fixtures/brendan_behan.jpeg.fits.xml

@@ -0,0 +1,43 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<fits xmlns="http://hul.harvard.edu/ois/xml/ns/fits/fits_output" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://hul.harvard.edu/ois/xml/ns/fits/fits_output http://hul.harvard.edu/ois/xml/xsd/fits/fits_output.xsd" version="0.6.2" timestamp="9/17/13 1:28 PM">
+  <identification>
+    <identity format="JPEG File Interchange Format" mimetype="image/jpeg" toolname="FITS" toolversion="0.6.2">
+      <tool toolname="Jhove" toolversion="1.5" />
+      <tool toolname="file utility" toolversion="5.04" />
+      <tool toolname="Exiftool" toolversion="9.06" />
+      <tool toolname="Droid" toolversion="3.0" />
+      <tool toolname="NLNZ Metadata Extractor" toolversion="3.4GA" />
+      <version toolname="Jhove" toolversion="1.5">1.01</version>
+      <externalIdentifier toolname="Droid" toolversion="3.0" type="puid">fmt/43</externalIdentifier>
+    </identity>
+  </identification>
+  <fileinfo>
+    <size toolname="Jhove" toolversion="1.5">8744</size>
+    <lastmodified toolname="Exiftool" toolversion="9.06" status="SINGLE_RESULT">2013:09:17 13:15:45-04:00</lastmodified>
+    <filepath toolname="OIS File Information" toolversion="0.1" status="SINGLE_RESULT">/Users/jfriesen/Repositories/hydra-file_characterization/spec/fixtures/brendan_behan.jpeg</filepath>
+    <filename toolname="OIS File Information" toolversion="0.1" status="SINGLE_RESULT">/Users/jfriesen/Repositories/hydra-file_characterization/spec/fixtures/brendan_behan.jpeg</filename>
+    <md5checksum toolname="OIS File Information" toolversion="0.1" status="SINGLE_RESULT">66a51b92863dd8e2c71c38979d84161c</md5checksum>
+    <fslastmodified toolname="OIS File Information" toolversion="0.1" status="SINGLE_RESULT">1379438145000</fslastmodified>
+  </fileinfo>
+  <filestatus>
+    <well-formed toolname="Jhove" toolversion="1.5" status="SINGLE_RESULT">true</well-formed>
+    <valid toolname="Jhove" toolversion="1.5" status="SINGLE_RESULT">true</valid>
+  </filestatus>
+  <metadata>
+    <image>
+      <byteOrder toolname="Jhove" toolversion="1.5" status="SINGLE_RESULT">big endian</byteOrder>
+      <compressionScheme toolname="Jhove" toolversion="1.5" status="SINGLE_RESULT">JPEG (old-style)</compressionScheme>
+      <imageWidth toolname="Jhove" toolversion="1.5">189</imageWidth>
+      <imageHeight toolname="Jhove" toolversion="1.5">267</imageHeight>
+      <colorSpace toolname="Jhove" toolversion="1.5" status="SINGLE_RESULT">YCbCr</colorSpace>
+      <YCbCrSubSampling toolname="Exiftool" toolversion="9.06" status="SINGLE_RESULT">2 2</YCbCrSubSampling>
+      <samplingFrequencyUnit toolname="Jhove" toolversion="1.5" status="CONFLICT">no absolute unit of measurement</samplingFrequencyUnit>
+      <samplingFrequencyUnit toolname="Exiftool" toolversion="9.06" status="CONFLICT">None</samplingFrequencyUnit>
+      <xSamplingFrequency toolname="Exiftool" toolversion="9.06">1</xSamplingFrequency>
+      <ySamplingFrequency toolname="Exiftool" toolversion="9.06">1</ySamplingFrequency>
+      <bitsPerSample toolname="Jhove" toolversion="1.5">8 8 8</bitsPerSample>
+      <samplesPerPixel toolname="Jhove" toolversion="1.5" status="SINGLE_RESULT">3</samplesPerPixel>
+      <lightSource toolname="NLNZ Metadata Extractor" toolversion="3.4GA" status="SINGLE_RESULT">unknown</lightSource>
+    </image>
+  </metadata>
+</fits>

data/spec/fixtures/brendan_broken.dxxd.fits.xml

@@ -0,0 +1,18 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<fits xmlns="http://hul.harvard.edu/ois/xml/ns/fits/fits_output" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://hul.harvard.edu/ois/xml/ns/fits/fits_output http://hul.harvard.edu/ois/xml/xsd/fits/fits_output.xsd" version="0.6.2" timestamp="9/17/13 3:44 PM">
+  <identification status="UNKNOWN">
+    <identity format="Unknown Binary" mimetype="application/octet-stream" toolname="FITS" toolversion="0.6.2">
+      <tool toolname="Jhove" toolversion="1.5" />
+    </identity>
+  </identification>
+  <fileinfo>
+    <filepath toolname="OIS File Information" toolversion="0.1" status="SINGLE_RESULT">/Users/jfriesen/Repositories/hydra-file_characterization/spec/fixtures/brendan_broken.dxxd</filepath>
+    <filename toolname="OIS File Information" toolversion="0.1" status="SINGLE_RESULT">/Users/jfriesen/Repositories/hydra-file_characterization/spec/fixtures/brendan_broken.dxxd</filename>
+    <size toolname="OIS File Information" toolversion="0.1" status="SINGLE_RESULT">9574</size>
+    <md5checksum toolname="OIS File Information" toolversion="0.1" status="SINGLE_RESULT">ca786ec0489e53c945d1fa7b584bac7f</md5checksum>
+    <fslastmodified toolname="OIS File Information" toolversion="0.1" status="SINGLE_RESULT">1379446883000</fslastmodified>
+  </fileinfo>
+  <filestatus />
+  <metadata />
+</fits>
+

data/spec/lib/hydra-file_characterization/characterizer_spec.rb

@@ -0,0 +1,40 @@
+require 'spec_helper'
+require 'hydra-file_characterization'
+
+describe Hydra::FileCharacterization do
+  describe 'Characterizer' do
+    def fixture_file(filename)
+      File.expand_path(File.join('../../../fixtures', filename), __FILE__)
+    end
+
+    let(:fits_path) { `which fits || which fits.sh`.strip }
+    subject { Hydra::FileCharacterization::Characterizer.new(filename, fits_path) }
+
+    describe 'validfile' do
+      let(:filename) { fixture_file('brendan_behan.jpeg') }
+      it '#call' do
+        expect(subject.call).to include(%(<identity format="JPEG File Interchange Format" mimetype="image/jpeg"))
+      end
+    end
+
+    describe 'invalidFile' do
+      let(:filename) { fixture_file('nofile.pdf') }
+      it "should raise an error if the path does not contain the file" do
+        expect {subject.call}.to raise_error(Hydra::FileCharacterization::Characterizer::FileNotFoundError)
+      end
+    end
+
+    describe 'corruptFile' do
+      let(:filename) { fixture_file('brendan_broken.dxxd') }
+      it "should return xml showing Unknown Binary and application/octet-stream mimetype" do
+        expect(subject.call).to include(%(<identity format="Unknown Binary" mimetype="application/octet-stream"))
+      end
+    end
+
+    describe 'zip file should be characterized not its contents' do
+      let(:filename) { fixture_file('archive.zip') }
+      its(:call) { should include(%(<identity format="ZIP Format" mimetype="application/zip"))}
+    end
+
+  end
+end

data/spec/lib/hydra-file_characterization/to_temp_file_spec.rb

@@ -0,0 +1,20 @@
+require 'spec_helper'
+require 'hydra-file_characterization/to_temp_file'
+
+describe Hydra::FileCharacterization do
+
+  describe 'ToTempFile' do
+    let(:string) { "This is the content of the file." }
+    subject { Hydra::FileCharacterization::ToTempFile.new(string, "hello.rb") }
+
+    it 'create a tempfile that exists' do
+      @temp_file = ''
+      subject.call do |temp_file|
+        @temp_file = temp_file
+        expect(File.exist?(@temp_file)).to eq true
+        expect(File.extname(@temp_file)).to eq '.rb'
+      end
+      expect(File.exist?(@temp_file)).to eq false
+    end
+  end
+end

data/spec/lib/hydra-file_characterization_spec.rb

@@ -0,0 +1,18 @@
+require 'spec_helper'
+require 'hydra-file_characterization'
+
+describe Hydra::FileCharacterization do
+
+
+
+  describe 'config' do
+    subject { Hydra::FileCharacterization::Configuration.new }
+    let (:expected_fits_path) {"string"}
+    before(:each) do
+      subject.fits_path = expected_fits_path
+    end
+    its(:config) {should have_key :fits_path}
+    its(:fits_path) {should == expected_fits_path}
+  end
+
+end

data/spec/spec_helper.rb

@@ -0,0 +1,17 @@
+# This file was generated by the `rspec --init` command. Conventionally, all
+# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
+# Require this file using `require "spec_helper"` to ensure that it is only
+# loaded once.
+#
+# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
+RSpec.configure do |config|
+  config.treat_symbols_as_metadata_keys_with_true_values = true
+  config.run_all_when_everything_filtered = true
+  config.filter_run :focus
+
+  # Run specs in random order to surface order dependencies. If you find an
+  # order dependency and want to debug it, you can fix the order by providing
+  # the seed, which is printed after each run.
+  #     --seed 1234
+  config.order = 'random'
+end

metadata

@@ -1,32 +1,106 @@
 --- !ruby/object:Gem::Specification
 name: hydra-file_characterization
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors:
 - James Treacy
 - Jeremy Friesen
+- Sue Richeson
+- Rajesh Balekai
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-09-17 00:00:00.000000000 Z
-dependencies: []
+date: 2013-09-18 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: activesupport
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: 3.0.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: 3.0.0
+- !ruby/object:Gem::Dependency
+  name: rspec
+  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: guard
+  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: guard-rspec
+  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: To provide a wrapper for file characterization
 email:
 - jatr@kb.dk
 - jeremy.n.friesen@gmail.com
+- spr7b@virginia.edu
+- rbalekai@gmail.com
 executables: []
 extensions: []
 extra_rdoc_files: []
 files:
 - .gitignore
+- .rspec
 - Gemfile
+- Guardfile
 - LICENSE
 - README.md
 - Rakefile
 - hydra-file_characterization.gemspec
 - lib/hydra-file_characterization.rb
+- lib/hydra-file_characterization/characterizer.rb
+- lib/hydra-file_characterization/to_temp_file.rb
 - lib/hydra-file_characterization/version.rb
+- spec/fixtures/archive.zip
+- spec/fixtures/archive.zip.fits.xml
+- spec/fixtures/brendan_behan.jpeg
+- spec/fixtures/brendan_behan.jpeg.fits.xml
+- spec/fixtures/brendan_broken.dxxd
+- spec/fixtures/brendan_broken.dxxd.fits.xml
+- spec/lib/hydra-file_characterization/characterizer_spec.rb
+- spec/lib/hydra-file_characterization/to_temp_file_spec.rb
+- spec/lib/hydra-file_characterization_spec.rb
+- spec/spec_helper.rb
 homepage: https://github.com/projecthydra/hydra-file_characterization
 licenses:
 - APACHE2
@@ -51,4 +125,14 @@ rubygems_version: 2.0.3
 signing_key: 
 specification_version: 4
 summary: To provide a wrapper for file characterization
-test_files: []
+test_files:
+- spec/fixtures/archive.zip
+- spec/fixtures/archive.zip.fits.xml
+- spec/fixtures/brendan_behan.jpeg
+- spec/fixtures/brendan_behan.jpeg.fits.xml
+- spec/fixtures/brendan_broken.dxxd
+- spec/fixtures/brendan_broken.dxxd.fits.xml
+- spec/lib/hydra-file_characterization/characterizer_spec.rb
+- spec/lib/hydra-file_characterization/to_temp_file_spec.rb
+- spec/lib/hydra-file_characterization_spec.rb
+- spec/spec_helper.rb