hydra-file_characterization 0.3.1 → 0.3.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 998550a6f8a8090fa8e735b3d863f8b8da45fa26
-  data.tar.gz: aeedc6fcecc36f7ce17e07dcc4479709971ca30e
+  metadata.gz: 34fca572cbda0f223170f1a23ae8cd43dcd1b6f0
+  data.tar.gz: a13e96336fa3a2327d92f1e77938c1bf1e3510a4
 SHA512:
-  metadata.gz: 42f80b2cdde8ff05833dee837dadba37770fd27a91ddefcdd6c1b90563b05c9d737f7bd0274a4dfe7a3ef05b8c0ab057db626ea72cadc3a27d4d8036dabbc217
-  data.tar.gz: e9bc81ce59caf0702fb8d762d4881341635793dadc6ad46e4dae08464bc8f0ea89ec1bb0c6bd1cf3c5ea52aca6f820415a18ca8f97a741d98014733702d3e5fc
+  metadata.gz: d65d9d4e65cc7275859bcf6fe1798f9e854bd40c31a966be4846de5717cb1f0b19de1cbe2bfbdfb8d4e0cae134adf5e7f4a9d7c698f2f6e64b49175f355c359e
+  data.tar.gz: 5beff9b3009b44f25dd362137befa286673b92dfdc36fdb9f63cd69c482773ee8f3cb998772ac66a0f50a0873bc51decfc147aa7eff8f889354a3bc5e51a974b

data/lib/hydra/file_characterization/characterizer.rb

@@ -19,11 +19,7 @@ module Hydra::FileCharacterization
         raise Hydra::FileCharacterization::FileNotFoundError.new("File: #{filename} does not exist.")
       end
 
-      if tool_path.respond_to?(:call)
-        tool_path.call(filename)
-      else
-        internal_call
-      end
+      post_process(output)
     end
 
     def tool_path
@@ -32,27 +28,43 @@ module Hydra::FileCharacterization
 
     protected
 
-    def convention_based_tool_name
-      self.class.name.split("::").last.downcase
-    end
+      # Override this method if you want your processor to mutate the
+      # raw output
+      def post_process(raw_output)
+        raw_output
+      end
 
-    def internal_call
-      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
+      def convention_based_tool_name
+        self.class.name.split("::").last.downcase
       end
-    end
 
-    def command
-      raise NotImplementedError, "Method #command should be overriden in child classes"
-    end
+      def internal_call
+        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
+
+      def command
+        raise NotImplementedError, "Method #command should be overriden in child classes"
+      end
+
+    private
+
+      def output
+        if tool_path.respond_to?(:call)
+          tool_path.call(filename)
+        else
+          internal_call
+        end
+      end
   end
 end

data/lib/hydra/file_characterization/characterizers/fits.rb

@@ -4,9 +4,15 @@ module Hydra::FileCharacterization::Characterizers
   class Fits < Hydra::FileCharacterization::Characterizer
 
     protected
-    def command
-      "#{tool_path} -i \"#{filename}\""
-    end
 
+      def command
+        "#{tool_path} -i \"#{filename}\""
+      end
+
+      # Remove any residual non-XML from JHOVE
+      # See: https://github.com/harvard-lts/fits/issues/20
+      def post_process(raw_output)
+        raw_output.sub(/^READBOX seen=true\n/, '')
+      end
   end
 end

data/lib/hydra/file_characterization/version.rb

@@ -1,5 +1,5 @@
 module Hydra
   module FileCharacterization
-    VERSION = "0.3.1"
+    VERSION = "0.3.2"
   end
 end

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

@@ -6,7 +6,8 @@ module Hydra::FileCharacterization
     let(:instance_tool_path) { nil }
     let(:class_tool_path) { nil }
 
-    subject { Hydra::FileCharacterization::Characterizer.new(filename, instance_tool_path) }
+    let(:characterizer) { Hydra::FileCharacterization::Characterizer.new(filename, instance_tool_path) }
+    subject { characterizer }
     around(:each) do |example|
       Hydra::FileCharacterization::Characterizer.tool_path = class_tool_path
       example.run
@@ -30,23 +31,25 @@ module Hydra::FileCharacterization
     end
 
     context 'tool_path' do
+      subject { characterizer.tool_path }
+
       context 'with custom instance tool_path' do
         let(:instance_tool_path) { '/arbitrary/path' }
         let(:class_tool_path) { '/a_different/path' }
 
-        its(:tool_path) { should eq instance_tool_path}
+        it { is_expected.to eq instance_tool_path }
       end
 
       context 'with custom class tool_path' do
         let(:instance_tool_path) { nil }
         let(:class_tool_path) { '/a_different/path' }
 
-        its(:tool_path) { should eq class_tool_path}
+        it { is_expected.to eq class_tool_path }
       end
 
       context 'without a specified tool_path' do
-        its(:tool_path) { should eq 'characterizer' }
+        it { is_expected.to eq 'characterizer' }
       end
     end
   end
-end
+end

data/spec/lib/hydra/file_characterization/characterizers/fits_spec.rb

@@ -2,37 +2,47 @@ require 'spec_helper'
 require 'hydra/file_characterization/characterizers/fits'
 
 module Hydra::FileCharacterization::Characterizers
-
   describe Fits do
+    let(:fits) { Fits.new(filename) }
 
-    subject { Fits.new(filename) }
+    describe "#call" do
+      subject { fits.call }
 
-    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"))
+      context 'validfile' do
+        let(:filename) { fixture_file('brendan_behan.jpeg') }
+        it { is_expected.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::FileNotFoundError)
+      context 'invalidFile' do
+        let(:filename) { fixture_file('nofile.pdf') }
+        it "raises an error" do
+          expect { subject }.to raise_error(Hydra::FileCharacterization::FileNotFoundError)
+        end
       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"))
+      context 'corruptFile' do
+        let(:filename) { fixture_file('brendan_broken.dxxd') }
+        it { is_expected.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
+      context 'zip file should be characterized not its contents' do
+        let(:filename) { fixture_file('archive.zip') }
+        it { is_expected.to include(%(<identity format="ZIP Format" mimetype="application/zip"))}
+      end
 
+      context 'when JHOVE adds non-xml' do
+        # https://github.com/harvard-lts/fits/issues/20
+        before do
+          allow(fits).to receive(:internal_call).and_return(
+            'READBOX seen=true
+<?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="0.8.2" timestamp="15/09/14 10:00 AM">
+  <identification/></fits>')
+        end
+
+        let(:filename) { fixture_file('brendan_behan.jpeg') }
+        it { is_expected.not_to include('READBOX') }
+      end
+    end
   end
-
 end

data/spec/lib/hydra/file_characterization_spec.rb

@@ -14,7 +14,7 @@ module Hydra
 
         describe 'for fits' do
           let(:tool_names) { [:fits] }
-          it { should match(/#{'<identity format="Plain text" mimetype="text/plain"'}/) }
+          it { is_expected.to match(/#{'<identity format="Plain text" mimetype="text/plain"'}/) }
         end
 
         describe 'with configured path' do

data/spec/spec_helper.rb

@@ -18,7 +18,6 @@ end
 
 RSpec.configure do |config|
   config.include SpecSupport
-  config.treat_symbols_as_metadata_keys_with_true_values = true
   config.run_all_when_everything_filtered = true
   config.filter_run :focus
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: hydra-file_characterization
 version: !ruby/object:Gem::Version
-  version: 0.3.1
+  version: 0.3.2
 platform: ruby
 authors:
 - James Treacy
@@ -11,62 +11,62 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-10-25 00:00:00.000000000 Z
+date: 2015-08-31 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
@@ -79,8 +79,8 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- .gitignore
-- .rspec
+- ".gitignore"
+- ".rspec"
 - CONTRIBUTING.md
 - Gemfile
 - Guardfile
@@ -120,17 +120,17 @@ 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: 2.0.3
+rubygems_version: 2.4.5
 signing_key: 
 specification_version: 4
 summary: To provide a wrapper for file characterization