fixed_width_parser 1.0.0

data/.rspec

@@ -0,0 +1,4 @@
+--color
+--format documentation
+--backtrace
+--debug

data/.rvmrc

@@ -0,0 +1,2 @@
+rvm use ruby-1.8.7-p334@fixed-width-parser
+rvm info

data/Gemfile

@@ -0,0 +1,13 @@
+source :gemcutter
+
+group :development, :test do
+  gem 'ruby-debug'
+	gem 'guard'
+  gem 'rb-fsevent'
+  gem 'growl'
+	gem 'guard-rspec'
+	gem 'guard-shell'
+end
+
+# Specify your gem's dependencies in geonames_client.gemspec
+gemspec

data/Gemfile.lock

@@ -0,0 +1,52 @@
+PATH
+  remote: .
+  specs:
+    fixed_width_parser (1.0.0)
+
+GEM
+  remote: http://rubygems.org/
+  specs:
+    columnize (0.3.4)
+    diff-lcs (1.1.3)
+    gem-dandy (0.2.1)
+      trollop (= 1.16.2)
+    growl (1.0.3)
+    guard (0.6.3)
+      thor (~> 0.14.6)
+    guard-rspec (0.4.5)
+      guard (>= 0.4.0)
+    guard-shell (0.1.1)
+      guard (>= 0.2.0)
+    linecache (0.46)
+      rbx-require-relative (> 0.0.4)
+    rb-fsevent (0.4.3.1)
+    rbx-require-relative (0.0.5)
+    rspec (2.6.0)
+      rspec-core (~> 2.6.0)
+      rspec-expectations (~> 2.6.0)
+      rspec-mocks (~> 2.6.0)
+    rspec-core (2.6.4)
+    rspec-expectations (2.6.0)
+      diff-lcs (~> 1.1.2)
+    rspec-mocks (2.6.0)
+    ruby-debug (0.10.4)
+      columnize (>= 0.1)
+      ruby-debug-base (~> 0.10.4.0)
+    ruby-debug-base (0.10.4)
+      linecache (>= 0.3)
+    thor (0.14.6)
+    trollop (1.16.2)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  fixed_width_parser!
+  gem-dandy
+  growl
+  guard
+  guard-rspec
+  guard-shell
+  rb-fsevent
+  rspec
+  ruby-debug

data/Guardfile

@@ -0,0 +1,11 @@
+#!/usr/bin/env ruby
+
+# guard 'shell' do
+#   watch( 'fixed_width_parser.rb' ) { |m| `ruby fixed_width_parser.rb` }
+# end
+
+guard 'rspec', :version => 2, :all_on_start => true, :all_after_pass => false, :cli => '--color --format doc' do
+  watch( %r{^spec/.+_spec\.rb$} )
+  watch( %r{^lib/(.+)\.rb$} )     { |m| "spec/lib/#{m[1]}_spec.rb" }
+  watch( 'spec/spec_helper.rb' )  { "spec" }
+end

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/fixed_width_parser.gemspec

@@ -0,0 +1,30 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "fixed_width_parser/version"
+
+Gem::Specification.new do |s|
+  s.name        = "fixed_width_parser"
+  s.version     = FixedWidthParser::VERSION
+  s.authors     = ["C. Jason Harrelson"]
+  s.email       = ["jason@lookforwardenterprises.com"]
+  s.homepage    = ""
+  s.summary     = %q{}
+  s.description = %q{}
+
+  s.rubyforge_project = "fixed_width_parser"
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+
+  # specify any dependencies here; for example:
+  %w(
+    gem-dandy
+    rspec
+  ).each do |development_dependency|
+    s.add_development_dependency development_dependency
+  end
+
+  # s.add_runtime_dependency "rest-client"
+end

data/lib/fixed_width_parser.rb

@@ -0,0 +1,84 @@
+module FixedWidthParser
+
+  def self.foreach( filepath, formats, options={} )
+    File.open( filepath, 'r' ) do |f|
+      f.each_line do |line|
+        line.chomp!
+        next if line.nil? || line.empty?
+
+        yield parse( line, formats, options )
+      end
+    end
+  end
+
+  def self.foreach_named( filepath, formats, options={} )
+    File.open( filepath, 'r' ) do |f|
+      f.each_line do |line|
+        line.chomp!
+        next if line.nil? || line.empty?
+
+        yield parse_named( line, formats, options )
+      end
+    end
+  end
+
+  def self.parse( line, formats, options={} )
+    raise 'Invalid format: expected an array of integers' unless formats.is_a?( Array )
+
+    regex = generate_regex( formats )
+
+     line.chomp!
+
+     parts = regex.match( line )[1..formats.size]
+
+     options[:rstrip] ? parts.map { |p| p.rstrip } : parts
+  end
+
+  def self.parse_named( line, formats, options={} )
+    unless formats.is_a?( Array )
+      unless formats.first.is_a?( Array ) #&& formats.first.size != 2
+        raise 'Invalid format: expected a hash-like array'
+      end
+    end
+
+    names   = formats.collect { |name,length| name.to_s }
+    lengths = formats.collect { |name,length| length }
+    regex   = generate_regex( lengths )
+
+    line.chomp!
+
+    parts = regex.match( line )[1..formats.size]
+    parts = options[:rstrip] ? parts.map { |p| p.rstrip } : parts
+
+    Hash[*(names.zip( parts ).flatten)]
+  end
+
+private
+
+  def self.calculate_ranges( formats )
+    ranges = []
+    start  = 0
+    _end   = 0
+
+    formats.each do |length|
+      start = _end
+      _end  = _end + length
+      ranges << (start.._end-1)
+    end
+
+    ranges
+  end
+
+  def self.generate_regex( formats )
+    regex = '^'
+
+    formats.each do |length|
+      regex << "(.{#{length}})"
+    end
+
+    regex << '$'
+
+    Regexp.new( regex  )
+  end
+
+end

data/lib/fixed_width_parser/version.rb

@@ -0,0 +1,3 @@
+module FixedWidthParser
+  VERSION = "1.0.0"
+end

data/spec/data/test.txt

@@ -0,0 +1,8 @@
+DOCUMENT  00014438P       PLAT          
+PARTIES   DYECK EW ADDN                 
+PARTIES   DHOMER STEPHEN M              
+PARTIES   DHOMER REBECCA R              
+DOCUMENT  00023133P       PLAT          
+PARTIES   DJUSTIN J/V                   
+PARTIES   DFRAZIER BRIAN TR             
+

data/spec/lib/fixed_width_parser_spec.rb

@@ -0,0 +1,242 @@
+require 'spec_helper'
+
+describe FixedWidthParser do
+
+  let :fixed_width_file do
+    File.join File.dirname( __FILE__ ), '..', 'data', 'test.txt'
+  end
+
+  let :lengths_format do
+    [10,8,8,14]
+  end
+
+  let :named_lengths_format do
+    [
+      ['a', 10],
+      [:b,  8 ],
+      [:c,  8 ],
+      [:d,  14]
+    ]
+  end
+
+  let :line do
+    "DOCUMENT  00014438P       PLAT          "
+  end
+
+  context 'yielding the correct lines' do
+
+    context '.foreach' do
+
+      context 'when given a valid format' do
+
+         before :each do
+           @yielded_lines = []
+         end
+
+        let :yielded_lines do
+          @yielded_lines
+        end
+
+        context 'when rstrip is false' do
+
+          before :each do
+            FixedWidthParser.foreach( fixed_width_file,
+                                      lengths_format ) do |line|
+              @yielded_lines << line
+            end
+          end
+
+          it "should yield the correct number of lines" do
+            yielded_lines.size.should == 7
+          end
+
+          it "should yield each line correctly parsed" do
+            yielded_lines[0].should == ['DOCUMENT  ', '00014438', 'P       ', 'PLAT          ']
+          end
+
+        end
+
+        context 'when rstrip is true' do
+
+          before :each do
+            FixedWidthParser.foreach( fixed_width_file,
+                                      lengths_format, :rstrip => true ) do |line|
+              @yielded_lines << line
+            end
+          end
+
+          it "should yield the correct number of lines" do
+            yielded_lines.size.should == 7
+          end
+
+          it "should yield each line correctly parsed" do
+            yielded_lines[0].should == ['DOCUMENT', '00014438', 'P', 'PLAT']
+          end
+
+        end
+
+      end
+
+      context 'when given an invalid format' do
+
+        it "should raise an exception when the format is not an array of integers" do
+          lambda { FixedWidthParser.foreach( fixed_width_file, {} ) { |l| } }.should(
+            raise_error( RuntimeError, 'Invalid format: expected an array of integers' )
+          )
+        end
+
+      end
+
+    end
+
+    context '.foreach_named' do
+
+      context 'when given a valid format' do
+
+        before :each do
+           @yielded_lines = []
+         end
+
+        let :yielded_lines do
+          @yielded_lines
+        end
+
+        context 'when rstrip is false' do
+
+          before :each do
+            FixedWidthParser.foreach_named( fixed_width_file,
+                                            named_lengths_format ) do |line|
+              @yielded_lines << line
+            end
+          end
+
+          it "should yield the correct number of lines" do
+            yielded_lines.size.should == 7
+          end
+
+          it "should yield each line correctly parsed" do
+            yielded_lines[0].should == {
+                'a', 'DOCUMENT  ',
+                'b', '00014438',
+                'c', 'P       ',
+                'd',  'PLAT          '
+              }
+          end
+
+        end
+
+        context 'when rstrip is true' do
+
+          before :each do
+            FixedWidthParser.foreach_named( fixed_width_file,
+                                            named_lengths_format, :rstrip => true ) do |line|
+              @yielded_lines << line
+            end
+          end
+
+          xit "should yield the correct number of lines" do
+            yielded_lines.size.should == 7
+          end
+
+          it "should yield each line correctly parsed" do
+            yielded_lines[0].should == {
+                'a', 'DOCUMENT',
+                'b', '00014438',
+                'c', 'P',
+                'd',  'PLAT'
+              }
+          end
+
+        end
+
+      end
+
+      context 'when given an invalid format' do
+
+        xit "should raise an exception when the format is an array of integers" do
+          lambda { FixedWidthParser.foreach_named( fixed_width_file, lengths_format ) { |l| } }.should(
+            raise_error( RuntimeError, 'Invalid format: expected a hash-like array' )
+          )
+        end
+
+        it "should raise an exception when the format is a hash" do
+          lambda { FixedWidthParser.foreach_named( fixed_width_file, {} ) { |l| } }.should(
+            raise_error( RuntimeError, 'Invalid format: expected a hash-like array' )
+          )
+        end
+
+      end
+
+    end
+
+  end
+
+  context '.parse' do
+
+    context 'when rstrip is false' do
+
+      subject { FixedWidthParser.parse( line, lengths_format ) }
+
+      it { should == ['DOCUMENT  ', '00014438', 'P       ', 'PLAT          '] }
+
+    end
+
+    context 'when rstrip is true' do
+
+      subject { FixedWidthParser.parse( line, lengths_format, :rstrip => true ) }
+
+      it { should == ['DOCUMENT', '00014438', 'P', 'PLAT'] }
+
+    end
+
+  end
+
+  context '.parse_named' do
+
+    context 'when rstrip is false' do
+
+      subject  { FixedWidthParser.parse_named( line, named_lengths_format ) }
+
+      it { should == {
+             'a', 'DOCUMENT  ',
+             'b', '00014438',
+             'c', 'P       ',
+             'd',  'PLAT          '
+           }
+      }
+
+    end
+
+    context 'when rstrip is true' do
+
+      subject  { FixedWidthParser.parse_named( line, named_lengths_format, :rstrip => true ) }
+
+      it { should == {
+             'a', 'DOCUMENT',
+             'b', '00014438',
+             'c', 'P',
+             'd',  'PLAT'
+           }
+      }
+
+    end
+
+  end
+
+  context 'calculating ranges from lengths' do
+
+    it "should return the correct ranges" do
+      FixedWidthParser.send( :calculate_ranges, lengths_format ).should == [(0..9), (10..17), (18..25), (26..39)]
+    end
+
+  end
+
+  context 'generating a regex from lengths' do
+
+    it "should return the correct regex" do
+      FixedWidthParser.send( :generate_regex, lengths_format ).should == /^(.{10})(.{8})(.{8})(.{14})$/
+    end
+
+  end
+
+end

data/spec/spec_helper.rb

@@ -0,0 +1,10 @@
+require 'rubygems'
+require 'bundler/setup'
+
+require 'fixed_width_parser'
+
+RSpec.configure do |config|
+
+  config.mock_with :rspec
+
+end

metadata

@@ -0,0 +1,109 @@
+--- !ruby/object:Gem::Specification 
+name: fixed_width_parser
+version: !ruby/object:Gem::Version 
+  hash: 23
+  prerelease: 
+  segments: 
+  - 1
+  - 0
+  - 0
+  version: 1.0.0
+platform: ruby
+authors: 
+- C. Jason Harrelson
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2011-11-08 00:00:00 -06:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: gem-dandy
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  type: :development
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: rspec
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  type: :development
+  version_requirements: *id002
+description: ""
+email: 
+- jason@lookforwardenterprises.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- .rspec
+- .rvmrc
+- Gemfile
+- Gemfile.lock
+- Guardfile
+- README.rdoc
+- Rakefile
+- fixed_width_parser.gemspec
+- lib/fixed_width_parser.rb
+- lib/fixed_width_parser/version.rb
+- spec/data/test.txt
+- spec/lib/fixed_width_parser_spec.rb
+- spec/spec_helper.rb
+has_rdoc: true
+homepage: ""
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: fixed_width_parser
+rubygems_version: 1.6.0
+signing_key: 
+specification_version: 3
+summary: ""
+test_files: 
+- spec/data/test.txt
+- spec/lib/fixed_width_parser_spec.rb
+- spec/spec_helper.rb