dfm 0.0.3 → 0.0.4

checksums.yaml

@@ -1,15 +1,7 @@
 ---
-!binary "U0hBMQ==":
-  metadata.gz: !binary |-
-    ZjAyNGI2NDE4M2M4NzRmODUwNjQzYjkxZTFjNjQxZTJlNjg3NTAxMA==
-  data.tar.gz: !binary |-
-    MzBiY2RkYTcxNmI0ODlhMGE0ZTdhNmU3NjFhMTRkYTBhZGE4ODRiZg==
+SHA1:
+  metadata.gz: 7fece188fe6d67b2870fc093036f2f155be9dd6d
+  data.tar.gz: db1ada3f9d2d0739ab122238ecba24f5d3c96075
 SHA512:
-  metadata.gz: !binary |-
-    M2IxYzYyZGIyZDQzYmU2ZTIyOTM1NzIyYWE1ZDNkM2QwNGZjYTE4OGIxNTJk
-    ZmMwYWYzZDZiMTBjMWE0NjVmNmIwOTIyMzg0ODZkNmMyZjgwZTljOWZkZmU4
-    ZjYyODNlM2VkMDZkMjAwYWE4NTNkYjMxZjllODFjYThkYTY2NWE=
-  data.tar.gz: !binary |-
-    Yjc3OTc5MTlhYmVmOTM5OTgyY2MxZGQyYzg2OGZkZDcwMjE4YjM1ZWIzMDYy
-    NTljYjZlNmVmZDJlMjg3NDI1ODFjMmM1ZWJhYjEwM2RiNmE4MjMyZTJjZDYx
-    OGMxZWM1MDQ1OWQ2NjBlNzJhNmJlNWMxN2NkZmM1ZDc1MTU1OTE=
+  metadata.gz: 9d3cd8d0966d3c8ad45caf4dc7978b4aa52641ebc167ced0baf338a7efd80ec03af43c47416fe0dbe080f6ea3450e806ef9b5eefff1d2d6a6b41e123c7615c12
+  data.tar.gz: 222170ee269434ae6918b2ea6dfcf57ed27ec8711ff6522a19a95005b633021a72b384ccf4ab251dff9dc7b42c13a033527a9c4ebff2ef42f4ad963e866b4ce9

data/README.md

@@ -1,35 +1,44 @@
-dfm
-===
-
-Duplicate File Manager
-
-The purpose of dfm is to locate duplicate files through a recursive search.
-
-You can create an instance of the DFM object with optionally secifing the
+dfm 
+=== 
+ 
+Duplicate File Manager 
+
+    gem install dfm
+ 
+The purpose of dfm is to locate duplicate files through a recursive search. 
+ 
+You can create an instance of the DFM object with optionally specifying the 
 directory path and the file extensions.
-
-    instance = DFM.new( path: './', filters: ["jpg","png"] )
-
-If you are using a ruby version before 2 then this would be:
-
-    instance = DFM.new( { :path => './', :filters => ["jpg","png"] } )
-
-Then you may get a hash of the hex matches (indacating files with identical content) by
-
-    instance.hex
-
-And by duplicate faile name by
-
-    instance.name
-
-Either of these can be called with false if you want only single instances of files.
-
-    instance.hex( false )
-    instance.name( false )
-
----
-
-Also included is a command line version which outputs nicely formatted JSON in case
-you would like to use it with anything else.  Type `dfm -h` on the command line to get
-a list of available options.  Running `dfm` by itself will recursively search the current
-folder for all duplicates by both file name and hash indexes.
+ 
+    dfm = DFM.new( path: './', filters: ["jpg","png"] ) 
+ 
+If you are using a ruby version before 2 then this would be: 
+ 
+    dfm = DFM.new( { :path => './', :filters => ["jpg","png"] } ) 
+
+Or you can use the default behaviour which uses the current directory and searches
+all files.
+
+    dfm = DFM.new
+ 
+Then you may get a hash of the MD5 hexdigest matches (indicating files with
+identical content) by 
+ 
+    dfm.hex 
+ 
+And by duplicate file name by 
+ 
+    dfm.name 
+ 
+Either of these can be called with false if you want only single instances of files. 
+ 
+    dfm.hex( false ) 
+    dfm.name( false ) 
+ 
+--- 
+ 
+Also included is a command line version which outputs nicely formatted JSON in case 
+you would like to use it with anything else.  Type `dfm -h` on the command line to get 
+a list of available options.  Running `dfm` by itself will recursively search the current 
+folder for all duplicates by both file name and MD5 hexdigest indexes. 
+ 

data/lib/dfm/version.rb

@@ -1,7 +1,10 @@
 class DFM
-	VERSION = "0.0.3"
+	#:nodoc:
+	VERSION = "0.0.4"
 end
 
+# Version 0.0.4
+# * RDOC
 # Version 0.0.3
 # * Updated commandline app to merge miltiple JSON searches as single JSON output
 # Version 0.0.2

data/lib/dfm.rb

@@ -1,11 +1,18 @@
-require 'digest'
-require 'json'
-require 'dfm/version'
-
+# Tilte::     Duplicate File Manager (dfm)
+# Author::    Daniel P. Clark  (mailto:6ftdan@gmail.com)
+# License::   MIT License
+['digest','json','dfm/version'].each {|r|require r;}
+# Class instance of DFM generates a list of files recursively
+# and indexes the by both MD5 hexdigest and file name
+# Optional parameters include file extension filters with
+# { :filters => ["jpg", "png"] } and path suh as { :path => "./" }
 class DFM
+	# File extension filters can be set on DFM.new( { :filters => ["jpg","gif"] } )
+	# or you should assign it to the class instance variable filters
+	# before calling recurse( path )
 	attr_accessor :filters
 
-	def initialize( params = {} )
+	def initialize( params = {} ) #:nodoc:
 		@files_by_hexdigest = {}
 		@files_by_name = {}
 		@filters = Array( params.fetch( :filters, nil ) )
@@ -14,22 +21,34 @@ class DFM
 		recurse_path( @path )
 	end
 
+	# Prints out JSON list of single copy files by MD5 hexdigest
+	# index or if the parameter is set to "name" then the list is
+	# indexed by file name.
 	def print_singles( opt = "hex" )
 		print_match( { :type => opt, :duplicates => false } )
 	end
 	
+	# Prints out JSON list of duplicate copy files by MD5 hexdigest
+	# index or if the parameter is set to "name" then the list is
+	# indexed by file name.
 	def print_duplicates( opt = "hex" )
 		print_match( { :type => opt } )
 	end
 
+	# Returns hash of duplicate files by MD5 hexdigest index.  If
+	# the parameter is set to false then the hash returns non-duplicates.
 	def hex( duplicates = true )
 		select_duplicates( { :hash => @files_by_hexdigest, :duplicates => duplicates } )
 	end
 
+	# Returns hash of duplicate files by file name index.  If the
+	# parameter is set to false then the hash returns non-duplicates.
 	def name( duplicates = true )
 		select_duplicates( { :hash => @files_by_name, :duplicates => duplicates } )
 	end
 
+	# Start a fresh recursive search with empty hash indexes.
+	# Accepts parameter for path.  (See filters for settings file extensions.)
 	def recurse( path )
 		@files_by_hexdigest = {}
 		@files_by_name = {}
@@ -38,15 +57,19 @@ class DFM
 
 	private
 
+	# Private method which creates indexed hash(es) of files searched.
 	def insert_file( file )
 		# hex
 		file_io = File.open( file, "rb" ) { |io| io.read }
 		hex_file = @hashFunc.hexdigest( file_io )
 		@files_by_hexdigest[ hex_file ] = Array( @files_by_hexdigest[ hex_file ] ) << file
+
 		# name
 		@files_by_name[ File.basename( file ) ] = Array( @files_by_name[ File.basename( file ) ] ) << file
 	end
 
+	# Private method recursive search of parameter path.
+	# Filters by file type if defined.
 	def recurse_path( path = @path )
 		@filters.empty? ? ( filters = "" ) : ( filters = @filters.join( "," ).prepend( ".{" ).<<( "}" ) )
 		Dir.glob( path + '**' + File::SEPARATOR + '*' + filters ).each { |file|
@@ -56,16 +79,19 @@ class DFM
 		}
 	end
 
+	# Private method selects duplicates from hash, or if set will return hash of single instances.
 	def select_duplicates( opt = { :hash => @files_by_hexdigest, :duplicates => true } )
 		opt[ :hash ].select { |k,v| opt[ :duplicates ] ? ( v.length >= 2 ) : ( v.length == 1 ) }
 	end
 
+	# Private method calls either hex, or name, method to print to JSON via private method print_json.
 	def print_match( opt = { :type => "hex", :duplicates => true } )
 		if !!opt[ :type ][ "hex" ] or !!opt[ :type ][ "name" ]
 			print_json send( opt[ :type ], *Array( opt[ :duplicates ] ) )
 		end
 	end
 
+	# Private method prints formatted JSON to STDOUT
 	def print_json( hash )
 		puts JSON.pretty_generate( hash )
 	end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: dfm
 version: !ruby/object:Gem::Version
-  version: 0.0.3
+  version: 0.0.4
 platform: ruby
 authors:
 - Daniel P. Clark / 6ftDan(TM)
@@ -32,17 +32,17 @@ 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: 2.2.2
+rubygems_version: 2.3.0
 signing_key: 
 specification_version: 4
 summary: Duplicate File Manager.