ziplookup 1.0.0

data/.project

@@ -0,0 +1,17 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<projectDescription>
+	<name>ZipLookup</name>
+	<comment></comment>
+	<projects>
+	</projects>
+	<buildSpec>
+		<buildCommand>
+			<name>org.rubypeople.rdt.core.rubybuilder</name>
+			<arguments>
+			</arguments>
+		</buildCommand>
+	</buildSpec>
+	<natures>
+		<nature>org.rubypeople.rdt.core.rubynature</nature>
+	</natures>
+</projectDescription>

data/Manifest.txt

@@ -0,0 +1,9 @@
+.project
+bin/tryme.rb
+lib/USPS/address.rb
+lib/USPS/zip_lookup.rb
+Manifest.txt
+Rakefile
+test/tc_address.rb
+test/tc_standardize.rb
+test/ts_zip_lookup.rb

data/Rakefile

@@ -0,0 +1,28 @@
+require 'rake'
+require 'rake/gempackagetask'
+
+spec = Gem::Specification.new do |s|
+  s.name = 'ziplookup'
+  s.version = '1.0.0'
+  s.summary = 'Classes for standardizing addresses via the USPS web site.'
+  s.description = 'Classes for standardizing addresses via the USPS web site.'
+  s.author = 'Gregor N. Purdy'
+  s.email = 'gregor@focusresearch.com'
+
+  s.has_rdoc = true
+  s.files = File.read('Manifest.txt').split($/)
+  s.require_path = 'lib' # library files go here
+  s.executables = ['tryme.rb'] # must be in bin/
+end
+
+#desc 'Generate RDoc'
+#Rake::RDocTask.new :rdoc do |rd|
+#  rd.rdoc_dir = 'doc'
+#  rd.rdoc_files.add 'lib', 'README', 'LICENSE' # add those files to your RDoc output
+#  rd.main = 'README' # the main page for the RDoc
+#end
+
+desc 'Build Gem'
+Rake::GemPackageTask.new spec do |pkg|
+  pkg.need_tar = true
+end

data/bin/tryme.rb

@@ -0,0 +1,28 @@
+require "USPS/zip_lookup"
+require "USPS/address"
+
+delivery_address = "6216 Eddington Drive"
+city = "Middletown"
+state = "OH"
+
+address = USPS::Address.new
+address.delivery_address = delivery_address
+address.city = city
+address.state = state
+
+zlu = USPS::ZipLookup.new()
+#zlu.verbose = true
+
+matches = zlu.std_addr(address)
+
+if matches != nil && matches.size > 0
+  printf "\n%d matches:\n", matches.size
+  matches.each { |match|
+    print "-" * 39, "\n"
+    print match.to_dump
+    print "\n"
+  }
+  print "-" * 39, "\n"
+else
+  print "No matches!\n"
+end

data/lib/USPS/address.rb

@@ -0,0 +1,356 @@
+=begin
+= address.rb
+Copyright (C) 2006 Gregor N. Purdy. All rights reserved.
+
+This program is free software. It is subject to the same license as Ruby.
+
+= Classes
+* ((<Address>))
+
+= Address
+
+== Synopsis
+    require "USPS/ZipLookup"
+    require "USPS/Address"
+    
+    address = USPS::Address.new(delivery_address, city, state)
+
+    zlu = USPS::ZipLookup.new()
+
+    matches = zlu.std_addr(address)
+
+    if matches.size > 0
+      printf "\n%d matches:\n", matches.size
+      matches.each { |match|
+   #     print "-" x 39, "\n"
+        print match.to_dump
+        print "\n";
+      }
+   #   print "-" x 39, "\n"
+    else
+      print "No matches!\n"
+    end
+
+== Description
+
+Results from USPS::ZipLookup calls are of this type. 
+
+Class to represent U.S. postal addresses for the purpose of
+standardizing via the U.S. Postal Service's web site:
+
+http://www.usps.com/zip4/
+
+BE SURE TO READ AND UNDERSTAND THE TERMS OF USE SECTION IN THE
+DOCUMENTATION, WHICH MAY BE FOUND AT THE END OF THIS SOURCE CODE.
+
+== Class Methods
+
+== Instance Methods
+--- Address#dump()
+--- Address#firm()
+--- Address#urbanization()
+--- Address#delivery_address()
+--- Address#city()
+--- Address#state()
+--- Address#zip_code()
+--- Address#carrier_route()
+Detailed information (see the U.S. Postal Service web site for definitions at
+L<http://zip4.usps.com/zip4/pu_mailing_industry_def.htm>):
+--- Address#county()
+Detailed information (see the U.S. Postal Service web site for definitions at
+L<http://zip4.usps.com/zip4/pu_mailing_industry_def.htm>):
+--- Address#delivery_point()
+Detailed information (see the U.S. Postal Service web site for definitions at
+L<http://zip4.usps.com/zip4/pu_mailing_industry_def.htm>):
+--- Address#check_digit()
+Detailed information (see the U.S. Postal Service web site for definitions at
+L<http://zip4.usps.com/zip4/pu_mailing_industry_def.htm>):
+--- Address#lac_indicator()
+Detailed information (see the U.S. Postal Service web site for definitions at
+L<http://zip4.usps.com/zip4/pu_mailing_industry_def.htm>):
+--- Address#elot_sequence()
+Detailed information (see the U.S. Postal Service web site for definitions at
+L<http://zip4.usps.com/zip4/pu_mailing_industry_def.htm>):
+--- Address#elot_indicator()
+Detailed information (see the U.S. Postal Service web site for definitions at
+L<http://zip4.usps.com/zip4/pu_mailing_industry_def.htm>):
+--- Address#record_type()
+Detailed information (see the U.S. Postal Service web site for definitions at
+L<http://zip4.usps.com/zip4/pu_mailing_industry_def.htm>):
+--- Address#pmb_designator()
+Detailed information (see the U.S. Postal Service web site for definitions at
+L<http://zip4.usps.com/zip4/pu_mailing_industry_def.htm>):
+--- Address#pmb_number()
+Detailed information (see the U.S. Postal Service web site for definitions at
+L<http://zip4.usps.com/zip4/pu_mailing_industry_def.htm>):
+--- Address#default_address()
+Detailed information (see the U.S. Postal Service web site for definitions at
+L<http://zip4.usps.com/zip4/pu_mailing_industry_def.htm>):
+--- Address#early_warning()
+Detailed information (see the U.S. Postal Service web site for definitions at
+L<http://zip4.usps.com/zip4/pu_mailing_industry_def.htm>):
+--- Address#valid()
+Detailed information (see the U.S. Postal Service web site for definitions at
+L<http://zip4.usps.com/zip4/pu_mailing_industry_def.htm>):
+
+= History
+$Id: address.rb 2255 2006-08-07 05:39:57Z gregor $ 
+
+= TERMS OF USE
+
+BE SURE TO READ AND FOLLOW THE UNITED STATES POSTAL SERVICE TERMS OF USE
+PAGE AT C<http://www.usps.gov/disclaimer.html>. IN PARTICULAR, NOTE THAT THEY
+DO NOT PERMIT THE USE OF THEIR WEB SITE'S FUNCTIONALITY FOR COMMERCIAL
+PURPOSES. DO NOT USE THIS CODE IN A WAY THAT VIOLATES THE TERMS OF USE.
+
+The author believes that the example usage given above does not violate
+these terms, but sole responsibility for conforming to the terms of use
+belongs to the user of this code, not the author.
+
+= Author
+
+Gregor N. Purdy, C<gregor@focusresearch.com>.
+
+= Copyright
+
+Copyright (C) 2006 Gregor N. Purdy. All rights reserved.
+This program is free software; you can redistribute it and/or
+modify it under the same terms as Ruby itself.
+
+=end
+
+module USPS
+
+class Address
+
+  @firm = nil
+  @urbanization = nil
+  @delivery_address = nil
+  @city = nil
+  @state = nil
+  @zip_code = nil
+  
+  @carrier_route = nil
+  @county = nil
+  @delivery_point = nil
+  @check_digit = nil
+  @lac_indicator = nil
+  @elot_sequence = nil
+  @elot_indicator = nil
+  @record_type = nil
+  @pmb_designator = nil
+  @pmb_number = nil
+  @default_address = nil
+  @early_warning = nil
+  @valid = nil
+  
+  attr_reader :firm, :urbanization, :delivery_address, :city, :state, :zip_code,
+    :carrier_route, :county, :delivery_point, :check_digit, :lac_indicator, :elot_sequence,
+    :elot_indicator, :record_type, :pmb_designator, :pmb_number, :default_address, :early_warning,
+    :valid
+    
+  attr_writer :firm, :urbanization, :delivery_address, :city, :state, :zip_code,
+    :carrier_route, :county, :delivery_point, :check_digit, :lac_indicator, :elot_sequence,
+    :elot_indicator, :record_type, :pmb_designator, :pmb_number, :default_address, :early_warning,
+    :valid
+    
+  @@input_fields = {
+    'Firm'             => :firm,
+    'Urbanization'     => :urbanization,
+    'Delivery Address' => :delivery_address,
+    'City'             => :city,
+    'State'            => :state,
+    'Zip Code'         => :zip_code,
+  }
+
+  @@output_fields = {
+    'Carrier Route'   => :carrier_route,
+    'County'          => :county,
+    'Delivery Point'  => :delivery_point,
+    'Check Digit'     => :check_digit,
+    'LAC Indicator'   => :lac_indicator,
+    'eLOT Sequence'   => :elot_sequence,
+    'eLOT Indicator'  => :elot_indicator,
+    'Record Type'     => :record_type,
+    'PMB Designator'  => :pmb_designator,
+    'PMB Number'      => :pmb_number,
+    'Default Address' => :default_address,
+    'Early Warning'   => :early_warning,
+    'Valid'           => :valid,
+  }
+  
+  @@field_order = [
+    "Firm",
+    "Urbanization",
+    "Delivery Address",
+    "City",
+    "State",
+    "Zip Code",
+    "Carrier Route",
+    "County",
+    "Delivery Point",
+    "Check Digit",
+    "LAC Indicator",
+    "eLot Sequence",
+    "eLot Indicator",
+    "Record Type",
+    "PMB Designator",
+    "PMB Number",
+    "Default Address",
+    "Early Warning",
+    "Valid",
+  
+  ]
+
+#
+# initialize()
+#
+#
+#def initialize(firm, urbanization, delivery_address, city, state, zip_code)
+#  @firm = firm
+#  @urbanization = urbanization
+#  @delivery_address = delivery_address
+#  @city = city
+#  @state = state
+#  @zip_code = zip_code
+#end
+#
+#def initialize(firm, delivery_address, city, state, zip_code)
+#  @firm = firm
+#  @delivery_address = delivery_address
+#  @city = city
+#  @state = state
+#  @zip_code = zip_code
+#end
+#
+#def initialize(delivery_address, city, state, zip_code)
+#  @delivery_address = delivery_address
+#  @city = city
+#  @state = state
+#  @zip_code = zip_code
+#end
+#
+#def initialize(delivery_address, city, state)
+#  @delivery_address = delivery_address
+#  @city = city
+#  @state = state
+#end
+#
+#def initialize(delivery_address, zip_code)
+#  @delivery_address = delivery_address
+#  @zip_code = zip_code
+#end
+
+#
+# fields()
+#
+
+def fields
+  return {
+    "Firm" => @firm,
+    "Urbanization" => @urbanization,
+    "Delivery Address" => @delivery_address,
+    "City" => @city,
+    "State" => @state,
+    "Zip Code" => @zip_code,
+    "Carrier Route" => @carrier_route,
+    "County" => @county,
+    "Delivery Point" => @delivery_point,
+    "Check Digit" => @check_digit,
+    "LAC Indicator" => @lac_indicator,
+    "eLot Sequence" => @elot_sequence,
+    "eLot Indicator" => @elot_indicator,
+    "Record Type" => @record_type,
+    "PMB Designator" => @pmb_designator,
+    "PMB Number" => @pmb_number,
+    "Default Address" => @default_address,
+    "Early Warning" => @early_warning,
+    "Valid" => @valid,
+  }
+end
+
+  #
+  # to_s()
+  #
+
+  def to_s(message = nil)
+    output = ''
+    
+    if message != nil
+      output = sprintf "ADDRESS: %s\n", message
+    end
+  
+    temp = fields
+  
+    @@field_order.each { |key|
+      value = temp[key]
+      next if value == nil
+      line = sprintf "  %s => '%s'\n", key, value
+      output += line
+    }
+
+    output += "\n"
+  
+    return output
+  end
+
+  #
+  # dump()
+  #
+
+  def dump(message = nil)
+    print to_s(message)
+  end
+
+  #
+  # to_dump()
+  #
+
+  def to_dump
+    return to_s()
+  end
+
+  def query_string
+    require 'cgi'
+  
+    args = [
+      [ 'visited'      , '1' ], # NOTE: CGI.escape pukes if this doesn't have quotes. It isn't smart enough to convert to String on its own!
+      [ 'pagenumber'   , 'all' ],
+      [ 'firmname'      , '' ],
+      [ 'address1'     , @delivery_address.upcase ],
+#     [ 'address1'     , '' ],
+#     [ 'address2'     , addr.delivery_address.upcase ],
+      [ 'address2'     , '' ],
+      [ 'city'         , @city.upcase ],
+      [ 'state'        , @state.upcase ],
+      [ 'urbanization' , '' ],
+      [ 'zip5'         , @zip_code == nil ? '' : @zip_code.upcase ],
+    ]
+
+    result = ''
+    
+    args.each { |arg|
+      key = arg[0]
+      value = arg[1]
+      
+      if value == nil
+        raise "Value is nil for key '" + key + "'!!!"
+      end
+      
+      value = CGI.escape(arg[1])
+      
+      temp = sprintf("%s=%s", key, value)
+      
+      if result != ''
+        result += "&"
+      end
+      
+      result += temp
+    }
+    
+    return result
+  end
+  
+end # class Address
+
+end # module USPS

data/lib/USPS/zip_lookup.rb

@@ -0,0 +1,424 @@
+=begin
+= zip_lookup.rb
+Copyright (C) 2006 Gregor N. Purdy. All rights reserved.
+
+This program is free software. It is subject to the same license as Ruby.
+
+= Classes
+* ((<Address>))
+
+= ZipLookup
+
+== Synopsis
+
+Ruby class to standardize U.S. postal addresses by referencing
+the U.S. Postal Service's web site:
+
+http://www.usps.com/zip4/
+
+  #! ruby
+  require "USPS/zip_lookup"
+  require "USPS/address"
+
+  delivery_address = "6216 Eddington Drive"
+  city = "Middletown"
+  state = "OH"
+
+  address = USPS::Address.new
+  address.delivery_address = delivery_address
+  address.city = city
+  address.state = state
+
+  zlu = USPS::ZipLookup.new()
+
+  matches = zlu.std_addr(address)
+
+  if matches != nil && matches.size > 0
+    printf "\n%d matches:\n", matches.size
+    matches.each { |match|
+      print "-" * 39, "\n"
+      print match.to_dump
+      print "\n"
+    }
+    print "-" * 39, "\n"
+  else
+    print "No matches!\n"
+  end
+
+== Description
+
+The United States Postal Service (USPS) has on its web site an HTML form at
+C<http://www.usps.com/zip4/>
+for standardizing an address. Given a firm, urbanization, street address,
+city, state, and zip, it will put the address into standard form (provided
+the address is in their database) and display a page with the resulting
+address.
+
+This Ruby module provides a programmatic interface to this service, so you
+can write a program to process your entire personal address book without
+having to manually type them all in to the form.
+
+Because the USPS could change or remove this functionality at any time,
+be prepared for the possibility that this code may fail to function. In
+fact, as of this version, there is no error checking in place, so if they
+do change things, this code will most likely fail in a noisy way. If you
+discover that the service has changed, please email the author your findings.
+
+If an error occurs in trying to standardize the address, then no array
+will be returned. Otherwise, a four-element array will be returned.
+
+To see debugging output, set zlu.verbose = true
+
+
+== Fields
+
+This page at the U.S. Postal Service web site contains definitions of some
+of the fields: C<http://zip4.usps.com/zip4/pu_mailing_industry_def.htm>
+
+
+= TERMS OF USE
+
+BE SURE TO READ AND FOLLOW THE UNITED STATES POSTAL SERVICE TERMS OF USE PAGE
+(AT C<http://www.usps.com/homearea/docs/termsofuse.htm> AT THE TIME THIS TEXT
+WAS WRITTEN). IN PARTICULAR, NOTE THAT THEY DO NOT PERMIT THE USE OF THEIR WEB
+SITE'S FUNCTIONALITY FOR COMMERCIAL PURPOSES. DO NOT USE THIS CODE IN A WAY
+THAT VIOLATES THE TERMS OF USE.
+
+As the user of this code, you are responsible for complying with the most
+recent version of the Terms of Use, whether at the URL provided above or
+elsewhere if the U.S. Postal Service moves it or updates it. As a convenience,
+here is a copy of the most relevant paragraph of the Terms of Use as of
+2006-07-04:
+
+  Material on this site is the copyrighted property of the United States
+  Postal Service� (Postal Service�). All rights reserved. The information
+  and images presented here may not under any circumstances be reproduced
+  or used without prior written permission. Users may view and download
+  material from this site only for the following purposes: (a) for personal,
+  non-commercial home use; (b) where the materials clearly state that these
+  materials may be copied and reproduced according to the terms stated in
+  those particular pages; or (c) with the express written permission of the
+  Postal Service. In all other cases, you will need written permission from
+  the Postal Service to reproduce, republish, upload, post, transmit,
+  distribute or publicly display material from this Web site. Users agree not
+  to use the site for sale, trade or other commercial purposes. Users may not
+  use language that is threatening, abusive, vulgar, discourteous or criminal.
+  Users also may not post or transmit information or materials that would
+  violate rights of any third party or which contains a virus or other harmful
+  component. The Postal Service reserves the right to remove or edit any
+  messages or material submitted by users. 
+
+The author believes that the example usage given above does not violate
+these terms, but sole responsibility for conforming to the terms of use
+belongs to the user of this code, not the author.
+
+
+= BUG REPORTS
+
+When contacting the author with bug reports, please provide a test address that
+exhibits the problem, and make sure it is OK to add that address to the test
+suite.
+
+Be sure to let me know if you don't want me to mention your name or email
+address when I document the changes and contributions to the release. Typically
+I put this information in the CHANGES file.
+
+= History
+$Id: zip_lookup.rb 2255 2006-08-07 05:39:57Z gregor $ 
+
+= Author
+
+Gregor N. Purdy, C<gregor@focusresearch.com>.
+
+= Copyright
+
+Copyright (C) 2006 Gregor N. Purdy. All rights reserved.
+This program is free software; you can redistribute it and/or
+modify it under the same terms as Ruby itself.
+
+=end
+
+#require 'mechanize'
+
+module USPS
+
+class ZipLookup
+#  @@VERSION = '1.0'
+  @@usps_host = 'zip4.usps.com'
+  
+  @@start_path = '/zip4/welcome.jsp'
+  @@start_url = sprintf('http://%s%s', @@usps_host, @@start_path)
+
+  @@post_path = '/zip4/zcl_0_results.jsp'
+  @@post_url = sprintf('http://%s%s', @@usps_host, @@post_path)
+
+#  @@form_name = 'form1'
+  @@form_number = 0
+  
+  attr_reader :user_agent, :verbose
+  attr_writer :verbose
+  
+  def initialize
+#    @user_agent = WWW::Mechanize.new
+    @verbose = false
+  end
+  
+  def std_addr(address)
+    return std_inner(address)
+  end
+
+  def std_addrs(addresses)
+    result = [ ]
+
+    addresses.each { |address|
+      temp = std_inner(address)
+      
+      result.push(temp)
+    }
+    
+    return result
+  end
+    
+  def direct_get(addr)
+    query_string = addr.query_string
+    
+    require 'net/http'
+    
+    content = nil
+    
+#   headers = { 'Referer' => @@start_url, 'Content-Type' => 'application/x-www-form-urlencoded' }
+    headers = { }
+       
+    path = @@post_path + "?" + query_string
+    
+    session = Net::HTTP.new(@@usps_host)
+    (response, content) = session.get(path, headers)
+        
+    if @verbose
+      print "-" * 79, "\n"
+      printf "Direct HTTP GET (of http://%s%s) Body:\n", @@usps_host, path
+      print "HTTP Response:\n"
+      print content
+    end
+
+    return content
+  rescue WWW::Mechanize::ResponseCodeError => error
+    printf "Unhandled response: %s\n", error.response_code
+    raise
+  end
+  
+  #
+  # std_inner()
+  #
+  # The inner portion of the process, so it can be shared by
+  # std_addr() and std_addrs().
+  #
+  #
+  def std_inner(addr)
+    if @verbose
+      print ' ', '_' * 77, ' ',  "\n"
+      print '/', ' ' * 77, '\\', "\n"
+      addr.dump("Input")
+      print "\n"
+    end
+
+    content = direct_get(addr)
+
+    #
+    # Time to Parse:
+    #
+    # The results look like this:
+    #
+    #   <td width="312" background="images/light_blue_bg2.gif" class="mainText">6216 EDDINGTON ST <br>LIBERTY TOWNSHIP&nbsp;OH&nbsp;45044-9761 <br>
+    #
+    # 1. We find <td header ...> ... </td> to find the data fields.
+    # 2. We strip out <font> and <a>
+    # 3. We replace &nbsp; with space
+    # 4. We strip out leading "...: "
+    # 5. We find <!--< ... />--> to get the field id
+    # 6. We standardize the field id (upper case, alpha only)
+    # 7. We standardize the value (trimming and whitespace coalescing)
+    #
+    # We end up with something like this:
+    #
+    #   ADDRESSLINE:  6216 EDDINGTON ST
+    #   CITYSTATEZIP: LIBERTY TOWNSHIP OH  45044-9761
+    #   CARRIERROUTE: R007
+    #   COUNTY: BUTLER
+    #   DELIVERYPOINT: 16
+    #   CHECKDIGIT: 3
+    #
+
+    matches =[ ]
+
+    content.gsub!(Regexp.new('[\cI\cJ\cM]'), '')
+    content.squeeze!(" ")
+    content.strip!
+    
+    raw_matches = content.scan(%r{<td headers="\w+" height="34" valign="top" class="main" style="background:url\(images/table_gray\.gif\); padding:5px 10px;">(.*?)>Mailing Industry Information</a>}mi)
+  
+    raw_matches.each { |raw_match|
+      if @verbose
+        print "-" * 79, "\n"
+        print "Raw match:\n"
+        printf("%s\n", raw_match[0])
+      end
+      
+      match = parse_match(raw_match[0])
+      
+      matches.push(match)
+    }
+
+    print('\\', '_' * 77, '/', "\n") if @verbose
+
+    return matches;
+  end # method std_inner
+
+  def parse_match(raw_match)
+    carrier_route   = nil
+    county          = nil
+    delivery_point  = nil
+    check_digit     = nil
+    lac_indicator   = nil
+    elot_sequence   = nil
+    elot_indicator  = nil
+    record_type     = nil
+    pmb_designator  = nil
+    pmb_number      = nil
+    default_address = nil
+    early_warning   = nil
+    valid           = nil
+
+    #
+    # Looking for some text like this:
+    # 
+    # onClick="mailingIndustryPopup2('R007','BUTLER','16','3','','0179','A','S','','','','','Y');"
+    #
+    
+    regex = %r{mailingIndustryPopup2\((.*?)\);}i
+    result = regex.match(raw_match)
+    
+    if result != nil
+      args = result[1]
+      
+      # Reformat to pipe-delimited
+      args.sub!(/^'/, '')
+      args.gsub!(/\s*'?\s*,\s*'?\s*/, '|')
+      args.sub!(/'$/, '')
+
+      args_array = args.split(/\|/)
+
+      carrier_route   = (args_array[0]  != nil && args_array[0]  != '') ? args_array[0]  : nil
+      county          = (args_array[1]  != nil && args_array[1]  != '') ? args_array[1]  : nil
+      delivery_point  = (args_array[2]  != nil && args_array[2]  != '') ? args_array[2]  : nil
+      check_digit     = (args_array[3]  != nil && args_array[3]  != '') ? args_array[3]  : nil
+      lac_indicator   = (args_array[4]  != nil && args_array[4]  != '') ? args_array[4]  : nil
+      elot_sequence   = (args_array[5]  != nil && args_array[5]  != '') ? args_array[5]  : nil
+      elot_indicator  = (args_array[6]  != nil && args_array[6]  != '') ? args_array[6]  : nil
+      record_type     = (args_array[7]  != nil && args_array[7]  != '') ? args_array[7]  : nil
+      pmb_designator  = (args_array[8]  != nil && args_array[8]  != '') ? args_array[8]  : nil
+      pmb_number      = (args_array[9]  != nil && args_array[9]  != '') ? args_array[9]  : nil
+      default_address = (args_array[10] != nil && args_array[10] != '') ? args_array[10] : nil
+      early_warning   = (args_array[11] != nil && args_array[11] != '') ? args_array[11] : nil
+      valid           = (args_array[12] != nil && args_array[12] != '') ? args_array[12] : nil
+    else
+      if @verbose
+        printf "WARNING: Could not find Mailing Industry info in '%s'!\n", raw_match
+      end
+    end
+
+    raw_match.gsub!(%r{</td>\s*<td.*?>}, ' ')
+    raw_match.gsub!(%r{</?font.*?>}, '')
+    raw_match.gsub!(%r{</?span.*?>}, '')
+    raw_match.gsub!(%r{</?a.*?>}, '')
+    raw_match.gsub!(%r{&nbsp;}, ' ')
+    raw_match.gsub!(%r{^.*?:\s*}, '')
+    raw_match.gsub!(%r{\s+}, ' ')
+    raw_match.gsub!(%r{<!--<(.*?)/>-->}, '')
+    raw_match.sub!(%r{<a.*$}, '')
+    raw_match.sub!(%r{<br\s*/?>\s*$}, '')
+
+    if @verbose
+      print "-" * 79, "\n"
+      print "Distilled match:\n"
+      printf "%s\n", raw_match
+    end
+
+    parts = raw_match.split( /\s*<br\s*\/?>\s*/)
+
+    firm            = nil
+    address        = nil
+    city_state_zip = nil
+
+    if parts.size == 2
+      (address, city_state_zip) = parts
+    elsif parts.size == 3
+      (firm, address, city_state_zip) = parts
+    else
+#      die "Parts = " . scalar(@parts) . "!";
+    end
+
+    next if city_state_zip == nil
+    next if !(city_state_zip =~ /^(.*)\s+(\w\w)\s+(\d{5}(-\d{4})?)/)
+
+    city = $1
+    state = $2
+    zip = $3
+
+    if @verbose
+      print("-" * 70, "\n");
+
+      printf "Firm:            %s\n", firm            if firm != nil
+
+      printf "Address:         %s\n", address
+      printf "City:            %s\n", city
+      printf "State:           %s\n", state
+      printf "Zip:             %s\n", zip
+
+      printf "Carrier Route:   %s\n", carrier_route   if carrier_route   != nil
+      printf "County:          %s\n", county          if county          != nil
+      printf "Delivery Point:  %s\n", delivery_point  if delivery_point  != nil
+      printf "Check Digit:     %s\n", check_digit     if check_digit     != nil
+      printf "LAC Indicator:   %s\n", lac_indicator   if lac_indicator   != nil
+      printf "eLOT Sequence:   %s\n", elot_sequence   if elot_sequence   != nil
+      printf "eLOT Indicator:  %s\n", elot_indicator  if elot_indicator  != nil
+      printf "Record Type:     %s\n", record_type     if record_type     != nil
+      printf "PMB Designator:  %s\n", pmb_designator  if pmb_designator  != nil
+      printf "PMB Number:      %s\n", pmb_number      if pmb_number      != nil
+      printf "Default Address: %s\n", default_address if default_address != nil
+      printf "Early Warning:   %s\n", early_warning   if early_warning   != nil
+      printf "Valid:           %s\n", valid           if valid           != nil
+
+      print "\n";
+    end
+
+    match = USPS::Address.new
+
+    match.delivery_address = address
+    match.city             = city
+    match.state            = state
+    match.zip_code         = zip
+    
+    match.firm              = firm
+
+    match.carrier_route    = carrier_route
+    match.county           = county
+    match.delivery_point   = delivery_point
+    match.check_digit      = check_digit
+
+    match.lac_indicator    = lac_indicator
+    match.elot_sequence    = elot_sequence
+    match.elot_indicator   =  elot_indicator
+    match.record_type      = record_type
+    match.pmb_designator   = pmb_designator
+    match.pmb_number       = pmb_number
+    match.default_address  = default_address
+    match.early_warning    = early_warning
+    match.valid            = valid
+    
+    return match
+  end # method parse_match
+
+end # class ZipLookup
+
+end # module USPS

data/test/tc_address.rb

@@ -0,0 +1,26 @@
+$:.unshift File.join(File.dirname(__FILE__), "..", "lib")
+
+require 'test/unit'
+#require 'rubygems'
+require 'USPS/address'
+#require 'test_includes'
+
+class AddressTest < Test::Unit::TestCase
+#  include TestMethods
+
+  def setup
+  end
+
+  def test_address
+    address = USPS::Address.new
+
+    address.delivery_address = '6216 Eddington'
+    address.city = 'Middletown'
+    address.zip_code = '45044'
+
+    assert_equal('6216 Eddington', address.delivery_address)
+    assert_equal('Middletown', address.city)
+    assert_equal('45044', address.zip_code)
+  end
+end
+

data/test/tc_standardize.rb

@@ -0,0 +1,94 @@
+$:.unshift File.join(File.dirname(__FILE__), "..", "lib")
+#
+# Copyright (C) 2006 Gregor N. Purdy. All rights reserved.
+# This program is free software. It is subject to the same license as Ruby.
+#
+# [ $Id: tc_standardize.rb 2255 2006-08-07 05:39:57Z gregor $ ]
+#
+
+require 'test/unit'
+require 'USPS/address'
+require 'USPS/zip_lookup'
+
+class StandardizeTest < Test::Unit::TestCase
+  def setup
+    @zlu = USPS::ZipLookup.new
+    if (ARGV.size >= 1) && (ARGV[0] == '-v') # ARGV is a global var, but doesn't use prefix '$'; GO FIGURE!
+      @zlu.verbose = true
+    end
+  end
+
+  def test_error
+    address = USPS::Address.new
+
+    address.delivery_address = 'bar'
+    address.city = 'splee'
+    address.state = 'OH'
+
+    result = @zlu.std_addr(address)
+    assert_equal([], result)
+  end
+
+  def test_simple_1
+    address = USPS::Address.new
+
+    address.delivery_address = '6216 Eddington Drive'
+    address.city = 'Liberty Township'
+    address.state = 'oh'
+
+    result = @zlu.std_addr(address)
+    assert_equal(1, result.size)
+
+    assert_equal('6216 EDDINGTON ST', result[0].delivery_address)
+    assert_equal('LIBERTY TOWNSHIP', result[0].city)
+    assert_equal('OH', result[0].state)
+    assert_equal('45044-9761', result[0].zip_code)
+  end
+
+  def test_apartment
+    address = USPS::Address.new
+
+    address.delivery_address = '3303 Pine Meadow DR SE #202'
+    address.city = 'Kentwood'
+    address.state = 'MI'
+    address.zip_code = '49512'
+
+    result = @zlu.std_addr(address)
+    assert_equal(1, result.size)
+
+    assert_equal('3303 PINE MEADOW DR SE APT 202', result[0].delivery_address)
+    assert_equal('KENTWOOD', result[0].city)
+    assert_equal('MI', result[0].state)
+    assert_equal('49512-8325', result[0].zip_code)
+  end
+
+  def test_simple_2
+    address = USPS::Address.new
+
+    address.delivery_address = '2701 DOUGLAS AVE'
+    address.city = 'DES MOINES'
+    address.state = 'IA'
+    address.zip_code = '50310'
+
+    result = @zlu.std_addr(address)
+    assert_equal(1, result.size)
+
+    assert_equal('2701 DOUGLAS AVE', result[0].delivery_address)
+    assert_equal('DES MOINES', result[0].city)
+    assert_equal('IA', result[0].state)
+    assert_equal('50310-5840', result[0].zip_code)
+  end
+
+  def test_multiple
+    address = USPS::Address.new
+
+    address.delivery_address = '1670 Broadway'
+    address.city = 'Denver'
+    address.state = 'CO'
+    address.zip_code = '80202'
+
+    result = @zlu.std_addr(address)
+    assert(result.size > 1)
+  end
+
+end

data/test/ts_zip_lookup.rb

@@ -0,0 +1,8 @@
+$:.unshift File.join(File.dirname(__FILE__), "..", "lib")
+$:.unshift File.join(File.dirname(__FILE__), "..", "test")
+
+require 'test/unit'
+
+require 'tc_address'
+require 'tc_standardize'
+

metadata

@@ -0,0 +1,49 @@
+--- !ruby/object:Gem::Specification 
+rubygems_version: 0.9.0
+specification_version: 1
+name: ziplookup
+version: !ruby/object:Gem::Version 
+  version: 1.0.0
+date: 2006-08-06 00:00:00 -07:00
+summary: Classes for standardizing addresses via the USPS web site.
+require_paths: 
+  - lib
+email: gregor@focusresearch.com
+homepage: 
+rubyforge_project: 
+description: Classes for standardizing addresses via the USPS web site.
+autorequire: 
+default_executable: 
+bindir: bin
+has_rdoc: true
+required_ruby_version: !ruby/object:Gem::Version::Requirement 
+  requirements: 
+    - 
+      - ">"
+      - !ruby/object:Gem::Version 
+        version: 0.0.0
+  version: 
+platform: ruby
+signing_key: 
+cert_chain: 
+post_install_message: 
+authors: 
+  - Gregor N. Purdy
+files: 
+  - ".project"
+  - bin/tryme.rb
+  - lib/USPS/address.rb
+  - lib/USPS/zip_lookup.rb
+  - Manifest.txt
+  - Rakefile
+  - test/tc_address.rb
+  - test/tc_standardize.rb
+  - test/ts_zip_lookup.rb
+test_files: []
+rdoc_options: []
+extra_rdoc_files: []
+executables: 
+  - tryme.rb
+extensions: []
+requirements: []
+dependencies: []