hydra-file_characterization 0.3.2 → 0.3.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 34fca572cbda0f223170f1a23ae8cd43dcd1b6f0
-  data.tar.gz: a13e96336fa3a2327d92f1e77938c1bf1e3510a4
+  metadata.gz: 8c3e177907738ef60151151394669f403baf76e9
+  data.tar.gz: 9c76f5edba884d3a0308f493c41748827b9dc531
 SHA512:
-  metadata.gz: d65d9d4e65cc7275859bcf6fe1798f9e854bd40c31a966be4846de5717cb1f0b19de1cbe2bfbdfb8d4e0cae134adf5e7f4a9d7c698f2f6e64b49175f355c359e
-  data.tar.gz: 5beff9b3009b44f25dd362137befa286673b92dfdc36fdb9f63cd69c482773ee8f3cb998772ac66a0f50a0873bc51decfc147aa7eff8f889354a3bc5e51a974b
+  metadata.gz: 84ee01ddc01e363e95d1eb253e836feb6c1666233f9d0f5cc40ed4d40c0be2e8cbc49a02a50441b5ca97ea938e848604b4729c724f889d5400031ef2e0b2edc4
+  data.tar.gz: 0c511f76ddb998a39f84971ccf180e5397d1ae042fc37370de061a97ccb231d1531978aa5593a5234958b5972ca9c06ac3af0424262321e06e8d29f59bff9c9b

data/.travis.yml

@@ -0,0 +1,9 @@
+language: ruby
+cache: bundler
+sudo: false
+bundler_args: --without debug
+env:
+  global:
+    - NOKOGIRI_USE_SYSTEM_LIBRARIES=true
+rvm:
+  - 2.2

data/Rakefile

@@ -1 +1,7 @@
 require "bundler/gem_tasks"
+require 'rspec/core'
+require 'rspec/core/rake_task'
+
+RSpec::Core::RakeTask.new(:spec)
+
+task default: :spec

data/hydra-file_characterization.gemspec

@@ -29,6 +29,7 @@ Gem::Specification.new do |gem|
   gem.require_paths = ["lib"]
 
   gem.add_dependency "activesupport", ">= 3.0.0"
+  gem.add_development_dependency "rake"
   gem.add_development_dependency "rspec"
   gem.add_development_dependency "guard"
   gem.add_development_dependency 'guard-rspec'

data/lib/hydra/file_characterization/characterizer.rb

@@ -26,6 +26,10 @@ module Hydra::FileCharacterization
       @tool_path || self.class.tool_path || convention_based_tool_name
     end
 
+    def logger
+      @logger ||= activefedora_logger || Logger.new(STDERR)
+    end
+
     protected
 
       # Override this method if you want your processor to mutate the
@@ -66,5 +70,9 @@ module Hydra::FileCharacterization
           internal_call
         end
       end
+
+      def activefedora_logger
+        ActiveFedora::Base.logger if defined? ActiveFedora
+      end
   end
 end

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

@@ -1,5 +1,6 @@
 require 'hydra/file_characterization/exceptions'
 require 'hydra/file_characterization/characterizer'
+require 'logger'
 module Hydra::FileCharacterization::Characterizers
   class Fits < Hydra::FileCharacterization::Characterizer
 
@@ -9,10 +10,14 @@ module Hydra::FileCharacterization::Characterizers
         "#{tool_path} -i \"#{filename}\""
       end
 
-      # Remove any residual non-XML from JHOVE
+      # Remove any non-XML output that precedes the <?xml> tag
       # See: https://github.com/harvard-lts/fits/issues/20
+      #      https://github.com/harvard-lts/fits/issues/40
+      #      https://github.com/harvard-lts/fits/issues/46
       def post_process(raw_output)
-        raw_output.sub(/^READBOX seen=true\n/, '')
+        md = /\A(.*)(<\?xml.*)\Z/m.match(raw_output)
+        logger.warn "FITS produced non-xml output: \"#{md[1].chomp}\"" unless md[1].empty?
+        md[2]
       end
   end
 end

data/lib/hydra/file_characterization/version.rb

@@ -1,5 +1,5 @@
 module Hydra
   module FileCharacterization
-    VERSION = "0.3.2"
+    VERSION = "0.3.3"
   end
 end

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

@@ -5,7 +5,7 @@ module Hydra::FileCharacterization::Characterizers
   describe Fits do
     let(:fits) { Fits.new(filename) }
 
-    describe "#call" do
+    describe "#call", unless: ENV['TRAVIS'] do
       subject { fits.call }
 
       context 'validfile' do
@@ -29,20 +29,40 @@ module Hydra::FileCharacterization::Characterizers
         let(:filename) { fixture_file('archive.zip') }
         it { is_expected.to include(%(<identity format="ZIP Format" mimetype="application/zip"))}
       end
+    end
+
+    context 'when JHOVE adds non-xml' do
+      # https://github.com/harvard-lts/fits/issues/20
+      subject { fits.call }
 
-      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
+      before do
+        expect(fits.logger).to receive(:warn)
+        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
+<identification/></fits>')
+      end
 
-        let(:filename) { fixture_file('brendan_behan.jpeg') }
-        it { is_expected.not_to include('READBOX') }
+      let(:filename) { fixture_file('brendan_behan.jpeg') }
+      it { is_expected.not_to include('READBOX') }
+    end
+
+    context "when FITS itself adds non-xml" do
+      # https://github.com/harvard-lts/fits/issues/46
+      subject { fits.call }
+
+      before do
+        expect(fits.logger).to receive(:warn)
+        allow(fits).to receive(:internal_call).and_return(
+          '2015-10-15 17:14:25,761 ERROR [main] ToolBelt:79 - Thread 1 error initializing edu.harvard.hul.ois.fits.tools.droid.Droid: edu.harvard.hul.ois.fits.exceptions.FitsToolException  Message: DROID cannot run under Java 8
+<?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('FitsToolException') }
     end
   end
 end

data/spec/lib/hydra/file_characterization_spec.rb

@@ -6,7 +6,7 @@ module Hydra
 
   describe FileCharacterization do
 
-    describe '.characterize' do
+    describe '.characterize', unless: ENV['TRAVIS'] do
       describe "for content in memory" do
         let(:content) { "class Test; end\n" }
         let(:filename) { 'test.rb' }
@@ -89,7 +89,7 @@ module Hydra
         Hydra::FileCharacterization::Characterizers::Fits.tool_path = old_tool_path
       end
 
-      it 'without configuration' do
+      it 'without configuration', unless: ENV['TRAVIS'] do
         Hydra::FileCharacterization.configure do |config|
           config.tool_path(:fits, nil)
         end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: hydra-file_characterization
 version: !ruby/object:Gem::Version
-  version: 0.3.2
+  version: 0.3.3
 platform: ruby
 authors:
 - James Treacy
@@ -11,7 +11,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-08-31 00:00:00.000000000 Z
+date: 2015-10-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -27,6 +27,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 3.0.0
+- !ruby/object:Gem::Dependency
+  name: rake
+  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: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -81,6 +95,7 @@ extra_rdoc_files: []
 files:
 - ".gitignore"
 - ".rspec"
+- ".travis.yml"
 - CONTRIBUTING.md
 - Gemfile
 - Guardfile
@@ -130,7 +145,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.5
+rubygems_version: 2.4.5.1
 signing_key: 
 specification_version: 4
 summary: To provide a wrapper for file characterization