orchard 0.1 → 0.2

data/README.rdoc

@@ -0,0 +1,38 @@
+Orchard is a Ruby library for working with Pairtrees, a filesystem hierarchy 
+mapping identifiers to object directories.
+
+More information can be found at:
+
+  Pairtrees for Object Storage
+  https://confluence.ucop.edu/display/Curation/PairTree
+
+==== Usage Examples
+
+===== Encoding/decoding strings according to the Pairtree specification
+
+  Orchard::Pairtree.encode('ark:/13030/xt12t3')
+  # => ark+=13030=xt12t3
+
+  Orchard::Pairtree.decode('ark+=13030=xt12t3')
+  # => ark:/13030/xt12t3
+
+===== Converting IDs to pairpaths and pairpaths to IDs
+
+  Orchard::Pairtree.id_to_ppath('ark:/13030/xt12t3')
+  # => ar/k+/=1/30/30/=x/t1/2t/3
+
+  Orchard::Pairtree.ppath_to_id('ar/k+/=1/30/30/=x/t1/2t/3')
+  # => ark:/13030/xt12t3
+  
+===== Iterating through a Pairtree for processing
+
+  Orchard::Pairtree.iterate('repo/pairtree_root/', {:raise_errors => true}) do |path|
+    puts path
+  end
+  # => /absolute_path/repo/pairtree_root/ab/cd/e/object
+  ...
+  # => /absolute_path/repo/pairtree_root/xy/z/object
+  
+==== Thanks
+  Erik Hetzner for contributions.
+  Ben O'Steen (this module is a semi-port of his Python Pairtree module, http://github.com/benosteen/pairtree)

data/lib/orchard.rb

@@ -1,5 +1,6 @@
 require 'orchard/pairtree'
 require 'orchard/version'
+require 'find'
 
 # Orchard is a Ruby library for working with Pairtrees, a filesystem hierarchy 
 # mapping identifiers to object directories.
@@ -11,19 +12,19 @@ require 'orchard/version'
 # 
 # ==== Usage Examples
 #
-#   Pairtree.encode('ark:/13030/xt12t3')
+#   Orchard::Pairtree.encode('ark:/13030/xt12t3')
 #   # => ark+=13030=xt12t3
 #
-#   Pairtree.decode('ark+=13030=xt12t3')
+#   Orchard::Pairtree.decode('ark+=13030=xt12t3')
 #   # => ark:/13030/xt12t3
 #
-#   Pairtree.id_to_ppath('ark:/13030/xt12t3')
+#   Orchard::Pairtree.id_to_ppath('ark:/13030/xt12t3')
 #   # => ar/k+/=1/30/30/=x/t1/2t/3
 #
-#   Pairtree.ppath_to_id('ar/k+/=1/30/30/=x/t1/2t/3')
+#   Orchard::Pairtree.ppath_to_id('ar/k+/=1/30/30/=x/t1/2t/3')
 #   # => ark:/13030/xt12t3
 
 module Orchard
-  class InvalidPPathError < StandardError
-  end
+  class InvalidPPathError < StandardError; end
+  class UnexpectedPairpathError < Exception; end
 end

data/lib/orchard/pairtree.rb

@@ -1,3 +1,4 @@
+require 'find'
 module Orchard
   # Provides a set of methods for working with Pairtree paths.
   class Pairtree
@@ -8,6 +9,53 @@ module Orchard
     CHAR_ENCODE_CONV = {'/'=>'=',':'=>'+','.'=>','}
     CHAR_DECODE_CONV = {'='=>'/','+'=>':',','=>'.'}
     
+    # ---------------------------
+    # Instance Methods
+    # ---------------------------    
+    def initialize(*args)
+      path = args[0]
+      options = args[1] || {}
+      
+    end
+    
+    def each
+      dirs = ["pairtree_root"]
+      excludes = []
+      for dir in dirs
+        Find.find(dir) do |path|
+          if FileTest.directory?(path)
+            if excludes.include?(File.basename(path))
+              Find.prune       # Don't look any further into this directory.
+            else
+              next
+            end
+          else
+            p path
+          end
+        end
+      end   
+    end
+    
+    def test(path)
+       begin
+         if File.lstat(path).directory?
+           begin
+             dir = Dir.open(path)
+             dir.each do |f|
+               unless f == "." or f == ".."
+                 test(f)
+               end             
+              end
+           ensure
+             dir.close
+           end
+         end
+       end
+    end
+    
+    # ---------------------------
+    # Class Methods
+    # ---------------------------
     # Encodes a given +id+ <em>(String)</em> according to the "identifier string 
     # cleaning" in the pairtree 0.1 specification. 
     #
@@ -89,7 +137,7 @@ module Orchard
     #
     # ==== Options
     # * <tt>:prefix => Pairtree prefix</tt> - This will remove the prefix from the id
-    #   before creating a pairpath.
+    #   before creating a pairpath. (String)
     #
     # ==== Examples
     #
@@ -143,7 +191,7 @@ module Orchard
     #
     # ==== Options
     # * <tt>:prefix => Pairtree prefix</tt> - This will remove the prefix from the id
-    #   before creating a pairpath.
+    #   before creating a pairpath. (String)
     #
     # ==== Examples
     #
@@ -166,6 +214,52 @@ module Orchard
       options[:prefix].nil? ? id : options[:prefix] + id
     end
     
+    # Iterates a given +pairpath+ with a +block+. 
+    #
+    #   iterate(pairtree_path,options,&block)
+    #     # pairtree_path is a String
+    #
+    # ==== Options
+    # * <tt>:raise_errors => Raise encountered errors/tt> - This will show (true) or surpress 
+    #   (false) ecountered errors. (Boolean)
+    # * <tt>:error_handling => Function to call on error</tt> - The Proc will execute if errors occur.
+    #   Error passed into Proc as parameter. (Proc or Nil)
+    #
+    # ==== Examples
+    #
+    #   Pairtree.iterate('repo/pairtree_root/', true) do |path|
+    #     puts path
+    #   end
+    #   # => /absolute_path/repo/pairtree_root/ab/cd/e/object
+    #   ...
+    #   # => /absolute_path/repo/pairtree_root/xy/z/object
+    #
+    def self.iterate(*args,&block)
+      #pairtree_path,raise_errors=false,error_handling=nil,&block
+      ppath = args[0]
+      options = args[1] || {}
+      Find.find(ppath) do |entry|
+        begin
+          if File.directory?(entry)
+            case entry
+            when /^.*\/[^\/:.]{1,2}$/ # in pairtree
+            when /^.*[^\/]{3,}$/ # found object
+              block.call(File.absolute_path(entry))
+              Find.prune
+            when ppath # ignore initial path
+            else
+              raise UnexpectedPairpathError, File.absolute_path(entry)
+            end
+          else
+            raise UnexpectedPairpathError, File.absolute_path(entry)
+          end
+        rescue Exception => e
+          options[:error_handling].call(e) unless options[:error_handling].nil?
+          raise e if options[:raise_errors] == true
+        end
+      end
+    end
+    
     private
     # Internal - split a string into a directory path by shorty length.
     def self.string_to_dirpath(s, dir_length_max)

data/lib/orchard/version.rb

@@ -1,3 +1,3 @@
 module Orchard
-  VERSION = '0.1'
+  VERSION = '0.2'
 end

metadata

@@ -4,8 +4,8 @@ version: !ruby/object:Gem::Version
   prerelease: false
   segments: 
   - 0
-  - 1
-  version: "0.1"
+  - 2
+  version: "0.2"
 platform: ruby
 authors: 
 - Stephanie Collett
@@ -13,7 +13,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-12-17 00:00:00 -08:00
+date: 2011-08-26 00:00:00 -07:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -43,9 +43,9 @@ files:
 - lib/orchard/version.rb
 - lib/orchard.rb
 - LICENSE
-- README.md
+- README.rdoc
 has_rdoc: true
-homepage: 
+homepage: http://github.com/cdlib/orchard
 licenses: []
 
 post_install_message: 
@@ -73,7 +73,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: 1.3.6
 requirements: []
 
-rubyforge_project: 
+rubyforge_project: orchard
 rubygems_version: 1.3.7
 signing_key: 
 specification_version: 3

data/README.md

@@ -1,21 +0,0 @@
-Orchard is a Ruby library for working with Pairtrees, a filesystem hierarchy 
-mapping identifiers to object directories.
-
-More information can be found at:
-
-  Pairtrees for Object Storage
-  https://confluence.ucop.edu/display/Curation/PairTree
-
-==== Usage Examples
-
-  Pairtree.encode('ark:/13030/xt12t3')
-  # => ark+=13030=xt12t3
-
-  Pairtree.decode('ark+=13030=xt12t3')
-  # => ark:/13030/xt12t3
-
-  Pairtree.id_to_ppath('ark:/13030/xt12t3')
-  # => ar/k+/=1/30/30/=x/t1/2t/3
-
-  Pairtree.ppath_to_id('ar/k+/=1/30/30/=x/t1/2t/3')
-  # => ark:/13030/xt12t3