saxony 0.1.3 → 0.2.0

data/CHANGES.txt

@@ -1,5 +1,13 @@
 SAXONY, CHANGES
 
+#### 0.2.0 (2010-02-02) ####
+
+* ADDED: Saxony.fork
+
+#### 0.1.4 (2010-02-01) ####
+
+* ADDED: Saxony#total_count
+
 #### 0.1.3 (2010-02-01) ####
 
 * FIXED: Don't blank out path between batches

data/README.md

@@ -1,16 +1,16 @@
-## Saxony - 0.1 ##
+## Saxony - 0.2 ##
 
-**Parse gigantic XML files with pleasure and a without running out of memory.**
+**Parse gigantic XML files with pleasure and without running out of memory.**
 
 ## Example ##
     
     sax = Saxony.new :SomeObject, 1000
     sax.parse 'path/2/huge.xml' do
-      total_count     # => Total number of SomeObjects processed
+      xml             # => The XML containing 1000 SomeObjects
       doc             # => Nokogiri object for 1000 SomeObjects
+      total_count     # => Total number of SomeObjects processed
       elapsed_time    # => time processing current batch
       path            # => Current file being processed
-      xml             # => The XML containing 1000 SomeObjects
     end
       
 ## Credits

data/lib/saxony.rb

@@ -3,7 +3,7 @@ require 'stringio'
 
 
 class Saxony 
-  VERSION = "0.1.3".freeze unless defined?(Saxony::VERSION)
+  VERSION = "0.2.0".freeze unless defined?(Saxony::VERSION)
   
   class Document < Nokogiri::XML::SAX::Document
     attr_accessor :path
@@ -89,19 +89,42 @@ class Saxony
   # * sources can be a list of file paths, IO objects, or XML strings
   def parse *sources, &blk
     sources.flatten!
+    @saxdoc = Saxony::Document.new @element, @granularity, &blk
     sources.each do |src|
-      saxdoc = Saxony::Document.new @element, @granularity, &blk
-      parser = Nokogiri::XML::SAX::Parser.new(saxdoc)
+      parser = Nokogiri::XML::SAX::Parser.new(@saxdoc)
       if (String === src && File.exists?(src)) 
         xml = File.open(src) 
-        saxdoc.path = src
+        @saxdoc.path = src
       else
         xml = src
-        saxdoc.path = src.class.to_s
+        @saxdoc.path = src.class
       end
       parser.parse xml
     end
   end
+  
+  def total_count
+    @saxdoc.total_count
+  end
+  
+  
+  def Saxony.fork(procs,*paths,&logic)
+    puts
+    paths.flatten!
+    if procs > 1
+      path_chunks = paths.chunk(procs)
+      procs.times do |idx|
+        proc_paths = path_chunks[idx]
+        pid = Kernel.fork do
+          logic.call(proc_paths,idx)
+        end
+        puts "PID #{pid} (#{idx+1}/#{procs}): #{proc_paths.join(', ')}"
+      end
+    else
+      logic.call paths, 1
+    end
+    
+  end
 end
 
 class Array

data/saxony.gemspec

@@ -1,7 +1,7 @@
 @spec = Gem::Specification.new do |s|
   s.name = "saxony"
   s.rubyforge_project = 'bone'
-  s.version = "0.1.3"
+  s.version = "0.2.0"
   s.summary = "Parse gigantic XML files with pleasure and a without running out of memory."
   s.description = s.summary
   s.author = "Delano Mandelbaum"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: saxony
 version: !ruby/object:Gem::Version 
-  version: 0.1.3
+  version: 0.2.0
 platform: ruby
 authors: 
 - Delano Mandelbaum
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-02-01 00:00:00 -05:00
+date: 2010-02-02 00:00:00 -05:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency