Module: Hydra::FileCharacterization

Defined in:
lib/hydra/file_characterization.rb,
lib/hydra/file_characterization/version.rb,
lib/hydra/file_characterization/exceptions.rb,
lib/hydra/file_characterization/to_temp_file.rb,
lib/hydra/file_characterization/characterizer.rb,
lib/hydra/file_characterization/characterizers.rb

Defined Under Namespace

Modules: Characterizers Classes: Characterizer, Configuration, FileNotFoundError, ToTempFile, ToolNotFoundError

Constant Summary collapse

VERSION = 
"1.1.2"

Class Attribute Summary collapse

Class Method Summary collapse

Class Attribute Details

.configuration ⇒ Object

Returns the value of attribute configuration.



19
20
21
 
# File 'lib/hydra/file_characterization.rb', line 19

def configuration
  @configuration
end

Class Method Details

.characterize(*args) {|For| ... } ⇒ String+

Run all of the specified tools against the given content and filename.

Examples:

xml_string = Hydra::FileCharacterization.characterize(contents_of_a_file, 'file.rb', :fits)
xml_string = Hydra::FileCharacterization.characterize(contents_of_a_file, 'file.rb', :fits) do |config|
  config[:fits] = './really/custom/path/to/fits'
end
xml_string = Hydra::FileCharacterization.characterize(contents_of_a_file, 'file.rb', :fits) do |config|
  config[:fits] = lambda {|filename| … }
end
fits_xml, ffprobe_xml = Hydra::FileCharacterization.characterize(contents_of_a_file, 'file.rb', :fits, :ffprobe)

With an open file

fits_xml, ffprobe_xml = Hydra::FileCharacterization.characterize(File.open('foo.mkv'), :fits, :ffprobe)

With an open file and a filename

fits_xml, ffprobe_xml = Hydra::FileCharacterization.characterize(File.open('foo.mkv'), 'my_movie.mkv', :fits, :ffprobe)

Parameters:

  • content (String) —

    • The contents of the original file

  • filename (String) —

    • The original file’s filename; Some

    characterization tools take hints from the file names

  • tool_names (Hash/Array) —

    • A list of tool names available on the system

    if you provide a Hash

Yield Parameters:

  • For (Hash) —

    any of the specified tool_names, if you add a key to the yieldparam with a value, that value will be used as the path

Returns:

  • (String, Array<String>) —

    - String - When a single tool_name is given, returns the raw XML as a

    string

    Array<String> - When multiple tool_names are given, returns an equal

    length Array of XML strings

See Also:



63
64
65
66
67
68
69
70
71
 
# File 'lib/hydra/file_characterization.rb', line 63

def self.characterize(*args)
  content, filename, tool_names = extract_arguments(args)
  tool_names = Array(tool_names).flatten.compact
  custom_paths = {}
  yield(custom_paths) if block_given?

  tool_outputs = run_characterizers(content, filename, tool_names, custom_paths)
  tool_names.size == 1 ? tool_outputs.first : tool_outputs
end

.characterize_with(tool_name, path_to_file, path_to_tool) ⇒ Object 



21
22
23
24
25
26
27
28
 
# File 'lib/hydra/file_characterization/characterizers.rb', line 21

def characterize_with(tool_name, path_to_file, path_to_tool)
  if path_to_tool.respond_to?(:call)
    path_to_tool.call(path_to_file)
  else
    tool_obj = characterizer(tool_name).new(path_to_file, path_to_tool)
    tool_obj.call
  end
end

.characterizer(tool_name) ⇒ Object 



8
9
10
11
12
13
14
15
 
# File 'lib/hydra/file_characterization/characterizers.rb', line 8

def characterizer(tool_name)
  characterizer_name = characterizer_name_from(tool_name)
  if Characterizers.const_defined?(characterizer_name)
    Characterizers.const_get(characterizer_name)
  else
    raise ToolNotFoundError, tool_name
  end
end

.characterizer_name_from(tool_name) ⇒ Object 



17
18
19
 
# File 'lib/hydra/file_characterization/characterizers.rb', line 17

def characterizer_name_from(tool_name)
  tool_name.to_s.gsub(/(?:^|_)([a-z])/) { Regexp.last_match(1).upcase }
end

.configure {|configuration| ... } ⇒ Object

Yields:



73
74
75
76
 
# File 'lib/hydra/file_characterization.rb', line 73

def self.configure
  self.configuration ||= Configuration.new
  yield(configuration)
end

.extract_arguments(args) ⇒ String, File

Break up a list of arguments into two possible lists:

option1:  [String] content, [String] filename, [Array] tool_names
option2:  [File] content, [Array] tool_names

In the case of option2, derive the filename from the file’s path

Returns:

  • (String, File) —

    , [String], [Array]



83
84
85
86
87
88
89
90
91
92
 
# File 'lib/hydra/file_characterization.rb', line 83

def self.extract_arguments(args)
  content = args.shift
  filename = if content.is_a?(File) && !args[0].is_a?(String)
               File.basename(content.path)
             else
               args.shift
  end
  tool_names = args
  [content, filename, tool_names]
end

.run_characterizers(content, filename, tool_names, custom_paths) ⇒ Object

Parameters:

  • content (File, String) —

    Either an open file or a string. If a string is passed a temp file will be created

  • filename (String) —

    Used in creating a temp file name

  • tool_names (Array<Symbol>) —

    A list of symbols referencing the characerization tools to run

  • custom_paths (Hash) —

    The paths to the executables of the tool.



99
100
101
102
103
104
105
106
107
 
# File 'lib/hydra/file_characterization.rb', line 99

def self.run_characterizers(content, filename, tool_names, custom_paths)
  if content.is_a? File
    run_characterizers_on_file(content, tool_names, custom_paths)
  else
    FileCharacterization::ToTempFile.open(filename, content) do |f|
      run_characterizers_on_file(f, tool_names, custom_paths)
    end
  end
end

.run_characterizers_on_file(f, tool_names, custom_paths) ⇒ Object 



109
110
111
112
113
 
# File 'lib/hydra/file_characterization.rb', line 109

def self.run_characterizers_on_file(f, tool_names, custom_paths)
  tool_names.map do |tool_name|
    FileCharacterization.characterize_with(tool_name, f.path, custom_paths[tool_name])
  end
end