RubyGems - best_type - Versions diffs - 0.0.2 → 0.0.9 - Mend

best_type 0.0.2 → 0.0.9

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (9) hide show

checksums.yaml +5 -5
data/README.md +86 -12
data/config/internal_config_options.yml +6 -0
data/lib/best_type.rb +5 -0
data/lib/best_type/config.rb +9 -3
data/lib/best_type/dc_type_lookup.rb +36 -8
data/lib/best_type/pcdm_type_lookup.rb +113 -0
data/lib/best_type/version.rb +1 -1
metadata +3 -3

checksums.yaml CHANGED

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 8d0a354dd631cb8c8c051dcb86a5ce63b8921dec
-  data.tar.gz: 57fe2ddc45928bbd3d18f9d3350f414d4de30147
+SHA256:
+  metadata.gz: fbde6b38db251ef80d23a7b7711e31adef831a93fbff03bbfcee54609eeb1c9d
+  data.tar.gz: 95e9cfecc1d063eb21755650a1e77307b86e8ff5a98c161e92854cdf236f2e7d
 SHA512:
-  metadata.gz: 72876496600f945fbbf2f6faf8145592dfb4eefe856afc8587feb51f29b3aa920e9477489e25d6b78600edaaffb4fe9ff01e04f97b782013e187a88829239184
-  data.tar.gz: 93534fa26253ee1d95940af36f884e7f1856fd690812c41dfba399d2a62d54e3dc4812d4f35ad607527a72dbb7277534680de5833802626dbf012fe15c5f0782
+  metadata.gz: 75cb28f10e1e533a4928b03a825bf00ebb98a6a20d4e66b657c800e0e46006952c93bc91a5a044855abe23c7d451ae6cd1a4a22391f992e07dcb2bc4e713e15f
+  data.tar.gz: 5a12871eda5fdd29f44b277286716810a39ef95a142d5b5328c6976011b89ed679d39923980d34e996318df3dfa8224dda249a0049c13098af3f534a9b65b0bb

data/README.md CHANGED

@@ -1,6 +1,6 @@
 # best_type
-A pure-ruby library for selecting the best MIME type for a file name, or DC type for a file name / MIME type.
+A pure-ruby library for selecting the best MIME type for a file name or DC type (http://dublincore.org/2012/06/14/dctype) for a file name / MIME type.
 ### Installation
@@ -8,33 +8,107 @@ A pure-ruby library for selecting the best MIME type for a file name, or DC type
 gem install best_type
 ```
-### Standalone Usage
+### Usage
 ```ruby
+# require the gem
 require 'best_type'
-TODO: Provide usage examples
+# detect mime type for file names
+BestType.mime_type.for_file_name('myfile.jpg') # 'image/jpeg'
+# detect mime type for file names (including full file path)
+BestType.mime_type.for_file_name('/path/to/some/file.jpg') # 'image/jpeg'
+# detect dc type for file names
+BestType.dc_type.for_file_name('myfile.jpg') # 'StillImage'
+# detect dc type for file names (including full file path)
+BestType.dc_type.for_file_name('/path/to/some/file.jpg') # 'StillImage'
+# detect dc type for mime types
+BestType.dc_type.for_mime_type('image/jpeg') # 'StillImage'
+# detect dc type for file names (including full file path)
+BestType.pcdm_type.for_file_name('/path/to/some/file.jpg') # 'Image'
+# detect dc type for mime types
+BestType.pcdm_type.for_mime_type('image/jpeg') # 'Image'
+```
+### Add Custom Overrides
+```ruby
+BestType.configure({
+  extension_to_mime_type_overrides:
+    'custom': 'custom/type'
+  mime_type_to_dc_type_overrides:
+    'custom/type': 'CustomDC'
+  mime_type_to_pcdm_type_overrides:
+    'custom/type': 'CustomPCDM'
+})
+BestType.mime_type.for_file_name('myfile.custom') # 'custom/type'
+BestType.dc_type.for_file_name('myfile.custom') # 'CustomDC'
+BestType.pcdm_type.for_mime_type('custom/type') # 'CustomPCDM'
 ```
-### Rails Usage
+### Recommended Setup For Rails
-Gemfile:
+Add best_type to your Gemfile:
 ```ruby
 gem 'best_type'
 ```
-Adding Custom Overrides via initializer (config/initializers/best_type.rb):
+And then call it from anywhere!
+If you want to set custom overrides, the best place to do so is in a Rails initializer:
 ```ruby
-# via hash
+# config/initializers/best_type.rb
 BestType.configure({
   extension_to_mime_type_overrides:
-    'ext': 'mime/type'
+    'custom': 'custom/type'
   mime_type_to_dc_type_overrides:
-    'mime/type': 'GreatType'
+    'custom/type': 'Custom'
+  mime_type_to_pcdm_type_overrides:
+    'custom/type': 'Custom'
 })
+```
+You may also want to consider using a YAML file for configuration:
+```ruby
+# config/initializers/best_type.rb
-# via YAML file, based on Rails environment:
-BestType.configure(YAML.load_file('config/best_type.yml')[Rails.env])
+BestType.configure(YAML.load_file(File.join(Rails.root, 'config/best_type.yml'))[Rails.env])
+```
+```yaml
+# config/initializers/best_type.rb
+development:
+  extension_to_mime_type_overrides:
+    'good': 'good/type'
+  mime_type_to_dc_type_overrides:
+    'good/type': 'Good'
+  mime_type_to_pcdm_type_overrides:
+    'good/type': 'Goodly'
+test:
+  extension_to_mime_type_overrides:
+    'better': 'better/type'
+  mime_type_to_dc_type_overrides:
+    'better/type': 'Better'
+  mime_type_to_pcdm_type_overrides:
+    'best/type': 'Betterly'
+production:
+  extension_to_mime_type_overrides:
+    'best': 'best/type'
+  mime_type_to_dc_type_overrides:
+    'best/type': 'Best'
+  mime_type_to_pcdm_type_overrides:
+    'best/type': 'Bestly'
 ```
 ### Running Tests (for developers):
@@ -49,4 +123,4 @@ bundle exec rake best_type:ci
 ```sh
 bundle exec rake release
-```
+```

data/config/internal_config_options.yml CHANGED

@@ -1,6 +1,12 @@
 extension_to_mime_type_overrides:
   'test': 'test/type'
   'mp4': 'video/mp4'
+  'vtt': 'text/vtt'
+  'm4v': 'video/x-m4v'
 mime_type_to_dc_type_overrides:
   'test/type': 'Test'
   'application/mxf': 'MovingImage'
+  'application/vnd.openxmlformats-officedocument.wordprocessingml.document': 'Text'
+  'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet': 'Dataset'
+mime_type_to_pcdm_type_overrides:
+  'test/type': 'Test'

data/lib/best_type.rb CHANGED

@@ -2,6 +2,7 @@ require 'best_type/version'
 require 'best_type/config'
 require 'best_type/mime_type_lookup'
 require 'best_type/dc_type_lookup'
+require 'best_type/pcdm_type_lookup'
 require 'yaml'
 module BestType
@@ -15,6 +16,10 @@ module BestType
     @dc_type ||= BestType::DcTypeLookup.new(mime_type)
   end
+  def self.pcdm_type
+    @pcdm_type ||= BestType::PcdmTypeLookup.new(mime_type)
+  end
   def self.config(reload = false, user_config_options = {})
     if @config.nil? || reload
       @semaphore.synchronize do

data/lib/best_type/config.rb CHANGED

@@ -1,7 +1,7 @@
 module BestType
   class Config
-    attr_reader :extension_to_mime_type_overrides, :mime_type_to_dc_type_overrides
+    attr_reader :extension_to_mime_type_overrides, :mime_type_to_dc_type_overrides, :mime_type_to_pcdm_type_overrides
     def initialize(user_config_options = {})
       # Get defaults from internal_custom_mapping.yml in gem
@@ -9,12 +9,14 @@ module BestType
       internal_config_file_path = File.join(gem_dir, 'config/internal_config_options.yml')
       internal_config_options = YAML.load_file(internal_config_file_path)
-      @extension_to_mime_type_overrides = internal_config_options['extension_to_mime_type_overrides']
-      @mime_type_to_dc_type_overrides = internal_config_options['mime_type_to_dc_type_overrides']
+      @extension_to_mime_type_overrides = internal_config_options['extension_to_mime_type_overrides'] || {}
+      @mime_type_to_dc_type_overrides = internal_config_options['mime_type_to_dc_type_overrides'] || {}
+      @mime_type_to_pcdm_type_overrides = internal_config_options['mime_type_to_pcdm_type_overrides'] || {}
       stringify_user_config_options_keys!(user_config_options)
       add_extension_to_mime_type_overrides(user_config_options['extension_to_mime_type_overrides']) if user_config_options.key?('extension_to_mime_type_overrides')
       add_mime_type_to_dc_type_overrides(user_config_options['mime_type_to_dc_type_overrides']) if user_config_options.key?('mime_type_to_dc_type_overrides')
+      add_mime_type_to_pcdm_type_overrides(user_config_options['mime_type_to_pcdm_type_overrides']) if user_config_options.key?('mime_type_to_pcdm_type_overrides')
     end
     private
@@ -27,6 +29,10 @@ module BestType
       @mime_type_to_dc_type_overrides.merge!(overrides)
     end
+    def add_mime_type_to_pcdm_type_overrides(overrides)
+      @mime_type_to_pcdm_type_overrides.merge!(overrides)
+    end
     def stringify_user_config_options_keys!(user_config_options)
       user_config_options_keys = user_config_options.keys
       user_config_options_keys.each do |key|

data/lib/best_type/dc_type_lookup.rb CHANGED

@@ -3,11 +3,39 @@ module BestType
     attr_reader :config
+    COLLECTION = 'Collection'.freeze
+    DATASET = 'Dataset'.freeze
+    EVENT = 'Event'.freeze
+    INTERACTIVE_RESOURCE = 'InteractiveResource'.freeze
+    MOVING_IMAGE = 'MovingImage'.freeze
+    PHYSICAL_OBJECT = 'PhysicalObject'.freeze
+    SERVICE = 'Service'.freeze
+    SOFTWARE = 'Software'.freeze
+    SOUND = 'Sound'.freeze
+    STILL_IMAGE = 'StillImage'.freeze
+    TEXT = 'Text'.freeze
+    # these include values that will not be derived from MIME/content types
+    VALID_TYPES = [
+      COLLECTION, EVENT, INTERACTIVE_RESOURCE, MOVING_IMAGE, PHYSICAL_OBJECT,
+      SERVICE, SOFTWARE, SOUND, STILL_IMAGE, TEXT
+    ].freeze
+    FALLBACK_DC_TYPE = SOFTWARE
     def initialize(mime_type_lookup_instance)
       @mime_type_lookup = mime_type_lookup_instance
       @config = @mime_type_lookup.config
     end
+    def fallback_type
+      FALLBACK_DC_TYPE
+    end
+    def valid_type?(value)
+      VALID_TYPES.include? value
+    end
     def for_file_name(file_name_or_path)
       for_mime_type(@mime_type_lookup.for_file_name(file_name_or_path))
     end
@@ -18,17 +46,17 @@ module BestType
       return dc_type unless dc_type.nil?
       mimes_to_dc = {
-        /^image/ => 'StillImage',
-        /^video/ => 'MovingImage',
-        /^audio/ => 'Sound',
-        /^text/ => 'Text',
-        /^application\/(pdf|msword)/ => 'Text',
-        /excel|spreadsheet|xls|application\/sql/ => 'Dataset',
-        /^application/ => 'Software'
+        /^image/ => STILL_IMAGE,
+        /^video/ => MOVING_IMAGE,
+        /^audio/ => SOUND,
+        /^text/ => TEXT,
+        /^application\/(pdf|msword)/ => TEXT,
+        /excel|spreadsheet|xls|application\/sql/ => DATASET,
+        /^application/ => SOFTWARE
       }
       dc_type = mimes_to_dc.find { |pattern, _type_val| mime_type =~ pattern }
-      dc_type.last
+      dc_type.nil? ? FALLBACK_DC_TYPE : dc_type.last
     end
   end

data/lib/best_type/pcdm_type_lookup.rb ADDED

@@ -0,0 +1,113 @@
+module BestType
+  class PcdmTypeLookup
+    attr_reader :config
+    # https://github.com/duraspace/pcdm/blob/master/pcdm-ext/file-format-types.rdf
+    ARCHIVE = "Archive".freeze
+    AUDIO = "Audio".freeze
+    DATABASE = "Database".freeze
+    DATASET = "Dataset".freeze
+    EMAIL = "Email".freeze
+    FONT = "Font".freeze
+    HTML = "HTML".freeze
+    IMAGE = "Image".freeze
+    PAGE_DESCRIPTION = "PageDescription".freeze
+    PRESENTATION = "Presentation".freeze
+    SOFTWARE = "Software".freeze
+    SOURCE_CODE = "SourceCode".freeze
+    SPREADSHEET = "Spreadsheet".freeze
+    STRUCTURED_TEXT = "StructuredText".freeze
+    TEXT = "Text".freeze
+    UNKNOWN = "Unknown".freeze
+    UNSTRUCTURED_TEXT = "UnstructuredText".freeze
+    VIDEO = "Video".freeze
+    WEBSITE = "Website".freeze
+    # these include values that will not be derived from MIME/content types
+    VALID_TYPES = [
+      ARCHIVE, AUDIO, DATABASE, DATASET, EMAIL, FONT, HTML, IMAGE, PAGE_DESCRIPTION, PRESENTATION, SOFTWARE,
+      SOURCE_CODE, SPREADSHEET, STRUCTURED_TEXT, TEXT, UNKNOWN, UNSTRUCTURED_TEXT, VIDEO, WEBSITE
+    ].freeze
+    FALLBACK_TYPE = UNKNOWN
+    def initialize(mime_type_lookup_instance)
+      @mime_type_lookup = mime_type_lookup_instance
+      @config = @mime_type_lookup.config
+    end
+    def fallback_type
+      FALLBACK_TYPE
+    end
+    def valid_type?(value)
+      VALID_TYPES.include? value
+    end
+    def for_file_name(file_name_or_path)
+      for_mime_type(@mime_type_lookup.for_file_name(file_name_or_path))
+    end
+    def for_mime_type(mime_type)
+      # Check config overrides first
+      file_type = @config.mime_type_to_pcdm_type_overrides.fetch(mime_type, nil)
+      return file_type unless file_type.nil?
+      mimes_to_type = {
+        /^image/i => IMAGE,
+        /^video/i => VIDEO,
+        /^audio/i => AUDIO,
+        /^text/i => {
+          /\/css/i => SOURCE_CODE,
+          /\/html/i => HTML,
+          /.+/ => TEXT
+        },
+        /excel|spreadsheet|xls/i => SPREADSHEET,
+        /application\/sql/i => DATABASE,
+        /csv/i => DATASET,
+        /octet.stream/i => UNKNOWN,
+        /^application/i => {
+          /\/access/i => DATABASE,
+          /\/css/i => SOURCE_CODE,
+          /\/html/i => HTML,
+          /\/mbox/i => EMAIL,
+          /\/mp4/i => VIDEO,
+          /\/mp4a/i => AUDIO,
+          /\/msaccess/i => DATABASE,
+          /\/mxf/i => VIDEO,
+          /\/(pdf|msword)/i => PAGE_DESCRIPTION,
+          /\/postscript/i => PAGE_DESCRIPTION,
+          /\/powerpoint/i => PRESENTATION,
+          /\/rtf/i => PAGE_DESCRIPTION,
+          /\/sql/i => DATABASE,
+          /\/swf/ => VIDEO,
+          /\/vnd.ms-asf/i => VIDEO,
+          /\/vnd.ms-word/i => PAGE_DESCRIPTION,
+          /\/vnd.ms-wpl/i => PAGE_DESCRIPTION,
+          /\/vnd.oasis.opendocument.text/i => PAGE_DESCRIPTION,
+          /\/vnd.openxmlformats-officedocument.presentation/i => PRESENTATION,
+          /\/vnd.openxmlformats-officedocument.wordprocessingml/i => PAGE_DESCRIPTION,
+          /\/vnd.ms-powerpoint/i => PRESENTATION,
+          /\/vnd.sun.xml.calc/i => SPREADSHEET,
+          /\/vnd.sun.xml.impress/i => PRESENTATION,
+          /\/vnd.sun.xml.writer/i => PAGE_DESCRIPTION,
+          /\/xml/i => STRUCTURED_TEXT,
+          /\/x.mspublisher/i => PAGE_DESCRIPTION,
+          /\/x.shockwave-flash/ => VIDEO,
+          /\/x.spss/i => DATASET,
+          /\/zip/i => ARCHIVE,
+          /.+/ => UNKNOWN
+        }
+      }
+      file_type = mimes_to_type.detect { |pattern, _type_val| mime_type =~ pattern }
+      return fallback_type unless file_type
+      if file_type&.last.is_a? Hash
+        file_type = file_type.last.detect { |pattern, _type_val| mime_type =~ pattern }
+      end
+      file_type.nil? ? fallback_type : file_type.last
+    end
+  end
+end

data/lib/best_type/version.rb CHANGED

@@ -1,6 +1,6 @@
 module BestType
-  VERSION = '0.0.2'.freeze
+  VERSION = '0.0.9'.freeze
   def self.version
     VERSION

metadata CHANGED

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: best_type
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.9
 platform: ruby
 authors:
 - Eric O'Hanlon
@@ -106,6 +106,7 @@ files:
 - lib/best_type/config.rb
 - lib/best_type/dc_type_lookup.rb
 - lib/best_type/mime_type_lookup.rb
+- lib/best_type/pcdm_type_lookup.rb
 - lib/best_type/version.rb
 - lib/tasks/best_type.rake
 - lib/tasks/best_type/ci.rake
@@ -128,8 +129,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project:
-rubygems_version: 2.6.14
+rubygems_version: 3.1.4
 signing_key:
 specification_version: 4
 summary: A library for selecting the best mime type or dc type for a file.