hasherize_csv 0.0.2

data/.gitignore

@@ -0,0 +1,18 @@
+*.gem
+*.rbc
+*.swp
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in hasherize_csv.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2012 Brent Bradbury
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,29 @@
+# HasherizeCsv
+
+TODO: Write a gem description
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'hasherize_csv'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install hasherize_csv
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require 'rake/testtask'
+
+Rake::TestTask.new do |t|
+  t.libs << 'test'
+end

data/hasherize_csv.gemspec

@@ -0,0 +1,24 @@
+# -*- encoding: utf-8 -*-
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'hasherize_csv/version'
+
+Gem::Specification.new do |gem|
+  gem.name          = "hasherize_csv"
+  gem.version       = HasherizeCsv::VERSION
+  gem.authors       = ["Brent Bradbury"]
+  gem.email         = ["brent@brentium.com"]
+  gem.description   = %q{Turns csv files into hashes without reading the entire csv into memory}
+  gem.summary       = %q{Hasherizes a csv file line by line}
+  gem.homepage      = "https://github.com/bbradbury/hasherize_csv"
+
+  gem.files         = `git ls-files`.split($/)
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.require_paths = ["lib"]
+
+  # Dependencies
+  # specify any dependencies here; for example:
+  # gem.add_runtime_dependency "activesupport", ">=3.0.0"
+  # gem.add_runtime_dependency "testunit"
+end

data/lib/hasherize_csv.rb

@@ -0,0 +1,50 @@
+require "hasherize_csv/version"
+
+module HasherizeCsv
+   module DefaultOpts
+     SALESFORCE = { :separator => "\r", :value_pattern => /\"(.*?)\"/m }
+   end
+ 
+   class Csv 
+     attr_accessor :keys, :file, :separator
+     def initialize file, opts = {}
+	@file = file
+	@separator = opts[:separator] || "\n"
+        @value_pattern = opts[:value_pattern] || /([\s\w_-]+),?/
+	@keys = []
+	next_line { |l| @keys = values_from_line l if !l.nil? }
+     end
+
+     def next_item 
+	next_line { |l|
+          if l.nil?
+	   yield nil
+          else
+	   yield hashify_values( values_from_line l ) 
+          end
+	}
+     end
+ 
+     def each
+        while(1) 
+	   self.next_item { |hash|
+	     return if hash.nil?
+             yield hash
+	   }
+        end 
+     end
+
+    private 
+     def next_line
+	  yield(@file.gets(@separator)) 
+     end
+
+     def hashify_values values
+        Hash[keys.zip(values)] if !values.nil? and values.length != 0
+     end
+
+     def values_from_line line
+	line.scan(@value_pattern).flatten
+     end
+   end
+end

data/lib/hasherize_csv/version.rb

@@ -0,0 +1,3 @@
+module HasherizeCsv
+  VERSION = "0.0.2"
+end

data/test/sample_csv.csv

@@ -0,0 +1,8 @@
+"Heading1","Heading2","H_EA_3__c"
+"Item1","Item2","Item3"
+"Email","SUP MAN
+
+WE HAVE LOTS OF MULTILINE EMAILS IN CAPS
+
+THEY ALSO HAVE LINEBREAKS IN THEM","FinalField"
+"Blank1","",""

data/test/test_hasherize_csv.rb

@@ -0,0 +1,46 @@
+require 'test/unit'
+require 'hasherize_csv'
+
+class HasherizeCsvTest < Test::Unit::TestCase
+  def setup 
+    @f = File.new(File.join(File.expand_path(File.dirname(__FILE__)),"sample_csv.csv"))
+    @csv = HasherizeCsv::Csv.new(@f, HasherizeCsv::DefaultOpts::SALESFORCE)
+  end
+
+  def teardown
+    @f.close
+  end
+
+  def test_keys
+        assert_equal ["Heading1", "Heading2", "H_EA_3__c"], @csv.keys
+  end
+
+  def test_hash_file
+       @csv.next { |hash|
+         assert_equal({"Heading1"=>"Item1", "Heading2"=>"Item2", "H_EA_3__c"=>"Item3"}, hash) 
+       }
+   
+       @csv.next { |hash|
+         assert_equal({"Heading1"=>"Email",
+                       "Heading2"=> "SUP MAN\n\nWE HAVE LOTS OF MULTILINE EMAILS IN CAPS\n\nTHEY ALSO HAVE LINEBREAKS IN THEM",
+                       "H_EA_3__c"=>"FinalField"}, hash)
+       }
+
+       @csv.next { |hash| 
+	 assert_equal nil, hash 
+       }
+  end
+
+  def test_hash_file
+       result = []
+       @csv.each { |hash|
+	 result << hash
+       }
+       assert_equal [{"Heading1"=>"Item1", "Heading2"=>"Item2", "H_EA_3__c"=>"Item3"}, 
+                     {"Heading1"=>"Email", 
+                      "Heading2"=>"SUP MAN\n\nWE HAVE LOTS OF MULTILINE EMAILS IN CAPS\n\nTHEY ALSO HAVE LINEBREAKS IN THEM",
+                      "H_EA_3__c"=>"FinalField"},
+                     {"Heading1"=>"Blank1", "Heading2"=>"", "H_EA_3__c"=>""}], result
+  end
+
+end

metadata

@@ -0,0 +1,58 @@
+--- !ruby/object:Gem::Specification
+name: hasherize_csv
+version: !ruby/object:Gem::Version
+  prerelease:
+  version: 0.0.2
+platform: ruby
+authors:
+- Brent Bradbury
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2012-10-25 00:00:00.000000000 Z
+dependencies: []
+description: Turns csv files into hashes without reading the entire csv into memory
+email:
+- brent@brentium.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- hasherize_csv.gemspec
+- lib/hasherize_csv.rb
+- lib/hasherize_csv/version.rb
+- test/sample_csv.csv
+- test/test_hasherize_csv.rb
+homepage: https://github.com/bbradbury/hasherize_csv
+licenses: []
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+  none: false
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+  none: false
+requirements: []
+rubyforge_project:
+rubygems_version: 1.8.24
+signing_key:
+specification_version: 3
+summary: Hasherizes a csv file line by line
+test_files:
+- test/sample_csv.csv
+- test/test_hasherize_csv.rb
+...