geo_coder 0.1.0

data/doc/parsing.rst

@@ -0,0 +1,125 @@
+.. _parsing:
+
+====================================
+Geocoder.us Address Parsing Strategy
+====================================
+
+:Author: Schuyler Erle
+:Contact: schuyler at geocoder dot us
+:Created: 2009/03/18
+:Edited: 2009/03/18
+
+Structured address components
+-----------------------------
+
+Unless otherwise labeled as "required", all components of a structured address
+are optional.
+
+prenum
+    The alphanumeric prefix portion of a house or building number. (e.g. "32-"
+    in "32-20 Jackson St".
+
+number
+    The house or building number component. Required.
+
+sufnum
+    The alphanumeric suffix portion of a house or building number. (e.g. "23B
+    Baker St")
+
+fraction
+    The fractional portion of a house or building number. (e.g. "23 1/2 Baker
+    St")
+
+predir
+    The prefixed street directional component. (e.g. "N", "SW")
+
+prequal
+    The prefixed street qualifier component. (e.g. "Old", "Business")
+
+pretyp
+    The prefixed street type component. (e.g. "US Hwy")
+
+street
+    The main portion of the street name. Required.
+
+suftyp
+    The suffixed street type component. (e.g. "Rd", "Ave")
+
+sufqual
+    The suffixed street qualifier component.
+
+sufdir
+    The suffixed street directional component.
+
+unittyp
+    The unit type, if any. (e.g. "Fl", "Apt", "Ste")
+
+unit
+    The unit identifer, if any.
+
+city
+    The name of the city or locale.
+
+state
+    The two letter postal state code.
+
+zip
+    The zero padded, five digit ZIP postal code.
+
+plus4
+    The zero padded, four digit ZIP+4 postal extension.
+
+Parsing Strategy
+----------------
+
+Each component will have a regular expression, and a maximum
+count. Components are ordered from first to last.
+
+Those components drawn from finite lists - directionals, qualifiers,
+types, and states - will have regular expressions composed of the union of
+the corresponding list.
+
+A *parse* will consist of a component state, a penalty count, a list of
+component strings and a counter for each component.
+
+1. Initialize an input stack, consisting of a single blank parse.
+
+#. Split the address string on whitespace into tokens.
+
+#. For each token:
+
+   A. For each component:
+
+      i. Test the token against the regular expression.
+      #. If the regexp matches, add the component name to a list of matching
+         components.
+
+   #. Initialize an empty output stack.
+
+   #. For each parse in the input stack:
+
+      i. Copy the current parse, increment the penalty count on the new parse,
+         and add it to the output stack.
+      #. For each matching component for the current token:
+
+         a. If the component state for this parse is later than the
+            matching component, continue to the next matching component.
+         #. If the component count for this parse state is equal to the 
+            maximum count for the component, continue to the next matching
+            component.
+         #. Otherwise, copy the parse state, and append the token to the
+            component string, with a leading space, if necessary.
+         #. Increment the matching component counter for the current parse.
+         #. Set the component state of the current parse to the matching
+            component.
+         #. Push the new parse on to the output stack.
+
+   #. Replace the input stack with the output stack.
+
+#. Post-process number prefix/suffixes and ZIP+4 extensions.
+
+#. Score each parse by the number of components with non-empty strings,
+   minus the penalty count of the parse.
+
+#. Return the sorted list of parsed string lists.
+

data/doc/voidspace.css

@@ -0,0 +1,147 @@
+/*
+:Authors: Ian Bicking, Michael Foord
+:Contact: fuzzyman@voidspace.org.uk
+:Date: 2005/08/26 
+:Version: 0.1.0
+:Copyright: This stylesheet has been placed in the public domain.
+:Modified By: Schuyler Erle, for geocoder.us, 2008-03-14
+
+Stylesheet for Docutils.
+Based on ``blue_box.css`` by Ian Bicking
+and ``html4css1.css`` revision 1.46.
+*/
+
+@import url(html4css1.css);
+
+/* changes made by SDE */
+body {
+  font-family: Arial, sans-serif;
+  margin-left: 10%;
+  margin-right: 10%;
+}
+
+p { text-align: justify; }
+dt { font-style: italic; }
+/* end changes */
+
+em, i {
+  /* Typically serif fonts have much nicer italics */
+  font-family: Times New Roman, Times, serif;
+}
+
+a.target {
+  color: blue;
+}
+
+a.target {
+  color: blue;
+}
+
+a.toc-backref {
+  text-decoration: none;
+  color: black;
+}
+
+a.toc-backref:hover {
+  background-color: inherit;
+}
+
+a:hover {
+  background-color: #cccccc;
+}
+
+div.attention, div.caution, div.danger, div.error, div.hint,
+div.important, div.note, div.tip, div.warning {
+  background-color: #cccccc;
+  padding: 3px;
+  width: 80%;
+}
+
+div.admonition p.admonition-title, div.hint p.admonition-title,
+div.important p.admonition-title, div.note p.admonition-title,
+div.tip p.admonition-title  {
+  text-align: center;
+  background-color: #999999;
+  display: block;
+  margin: 0;
+}
+
+div.attention p.admonition-title, div.caution p.admonition-title,
+div.danger p.admonition-title, div.error p.admonition-title,
+div.warning p.admonition-title {
+  color: #cc0000;
+  font-family: sans-serif;
+  text-align: center;
+  background-color: #999999;
+  display: block;
+  margin: 0;
+}
+
+h1, h2, h3, h4, h5, h6 {
+  font-family: Helvetica, Arial, sans-serif;
+  border: thin solid black;
+  /* This makes the borders rounded on Mozilla, which pleases me */
+  -moz-border-radius: 8px;
+  padding: 4px;
+}
+
+h1 {
+  background-color: #444499;
+  color: #ffffff;
+  border: medium solid black;
+}
+
+h1 a.toc-backref, h2 a.toc-backref { 
+  color: #ffffff;
+}
+
+h2 {
+  background-color: #666666;
+  color: #ffffff;
+  border: medium solid black;
+}
+
+h3, h4, h5, h6 {
+  background-color: #cccccc;
+  color: #000000;
+}
+
+h3 a.toc-backref, h4 a.toc-backref, h5 a.toc-backref, 
+h6 a.toc-backref { 
+  color: #000000;
+}
+
+h1.title {
+  text-align: center;
+  background-color: #444499;
+  color: #eeeeee;
+  border: thick solid black;
+  -moz-border-radius: 20px;
+}
+
+table.footnote {
+  padding-left: 0.5ex;
+}
+
+table.citation {
+  padding-left: 0.5ex
+}
+
+pre.literal-block, pre.doctest-block {
+  border: thin black solid;
+  padding: 5px;
+}
+
+.image img { border-style : solid;
+            border-width : 2px;
+}
+
+h1 tt, h2 tt, h3 tt, h4 tt, h5 tt, h6 tt {
+  font-size: 100%;
+}
+
+code, tt {
+  color: #000066;
+}
+
+

data/geo_coder.gemspec

@@ -0,0 +1,172 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = "geo_coder"
+  s.version = "0.1.0"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Travis Dempsey"]
+  s.date = "2011-09-21"
+  s.description = "Geocode a text address."
+  s.email = "dempsey.travis@gmail.com"
+  s.executables = ["build_indexes", "rebuild_cluster", "rebuild_metaphones", "tiger_import"]
+  s.extra_rdoc_files = [
+    "README.rdoc"
+  ]
+  s.files = [
+    "Gemfile",
+    "Gemfile.lock",
+    "History.txt",
+    "Makefile",
+    "Manifest.txt",
+    "README.rdoc",
+    "Rakefile",
+    "TODO.txt",
+    "VERSION",
+    "bin/build_indexes",
+    "bin/rebuild_cluster",
+    "bin/rebuild_metaphones",
+    "bin/tiger_import",
+    "demos/demo/app/ext/geocodewrap.rb",
+    "demos/demo/app/views/index.builder",
+    "demos/demo/app/views/index.erb",
+    "demos/demo/config.ru",
+    "demos/demo/config/bootstraps.rb",
+    "demos/demo/config/geoenvironment.rb",
+    "demos/demo/geocoder_helper.rb",
+    "demos/demo/geocom_geocode.rb",
+    "demos/demo/main.rb",
+    "demos/demo/rakefile.rb",
+    "demos/demo/tmp/restart.txt",
+    "demos/simpledemo/views/index.builder",
+    "demos/simpledemo/views/index.erb",
+    "demos/simpledemo/ws.rb",
+    "doc/Makefile",
+    "doc/html4css1.css",
+    "doc/lookup.rst",
+    "doc/parsing.rst",
+    "doc/voidspace.css",
+    "geo_coder.gemspec",
+    "lib/geocoder/us.rb",
+    "lib/geocoder/us/address.rb",
+    "lib/geocoder/us/constants.rb",
+    "lib/geocoder/us/database.rb",
+    "lib/geocoder/us/import.rb",
+    "lib/geocoder/us/import/tiger.rb",
+    "lib/geocoder/us/numbers.rb",
+    "navteq/README",
+    "navteq/convert.sql",
+    "navteq/navteq_import",
+    "navteq/prepare.sql",
+    "sql/cluster.sql",
+    "sql/convert.sql",
+    "sql/create.sql",
+    "sql/index.sql",
+    "sql/place.csv",
+    "sql/place.sql",
+    "sql/setup.sql",
+    "src/Makefile",
+    "src/README",
+    "src/liblwgeom/Makefile",
+    "src/liblwgeom/box2d.c",
+    "src/liblwgeom/lex.yy.c",
+    "src/liblwgeom/liblwgeom.h",
+    "src/liblwgeom/lwalgorithm.c",
+    "src/liblwgeom/lwalgorithm.h",
+    "src/liblwgeom/lwcircstring.c",
+    "src/liblwgeom/lwcollection.c",
+    "src/liblwgeom/lwcompound.c",
+    "src/liblwgeom/lwcurvepoly.c",
+    "src/liblwgeom/lwgeom.c",
+    "src/liblwgeom/lwgeom_api.c",
+    "src/liblwgeom/lwgparse.c",
+    "src/liblwgeom/lwgunparse.c",
+    "src/liblwgeom/lwline.c",
+    "src/liblwgeom/lwmcurve.c",
+    "src/liblwgeom/lwmline.c",
+    "src/liblwgeom/lwmpoint.c",
+    "src/liblwgeom/lwmpoly.c",
+    "src/liblwgeom/lwmsurface.c",
+    "src/liblwgeom/lwpoint.c",
+    "src/liblwgeom/lwpoly.c",
+    "src/liblwgeom/lwsegmentize.c",
+    "src/liblwgeom/lwutil.c",
+    "src/liblwgeom/measures.c",
+    "src/liblwgeom/postgis_config.h",
+    "src/liblwgeom/ptarray.c",
+    "src/liblwgeom/vsprintf.c",
+    "src/liblwgeom/wktparse.h",
+    "src/liblwgeom/wktparse.lex",
+    "src/liblwgeom/wktparse.tab.c",
+    "src/liblwgeom/wktparse.tab.h",
+    "src/liblwgeom/wktparse.y",
+    "src/libsqlite3_geocoder/Makefile",
+    "src/libsqlite3_geocoder/Makefile.nix",
+    "src/libsqlite3_geocoder/Makefile.redhat",
+    "src/libsqlite3_geocoder/extension.c",
+    "src/libsqlite3_geocoder/extension.h",
+    "src/libsqlite3_geocoder/levenshtein.c",
+    "src/libsqlite3_geocoder/metaphon.c",
+    "src/libsqlite3_geocoder/util.c",
+    "src/libsqlite3_geocoder/wkb_compress.c",
+    "src/metaphone/Makefile",
+    "src/metaphone/README",
+    "src/metaphone/extension.c",
+    "src/metaphone/metaphon.c",
+    "src/shp2sqlite/Makefile",
+    "src/shp2sqlite/Makefile.nix",
+    "src/shp2sqlite/Makefile.redhat",
+    "src/shp2sqlite/dbfopen.c",
+    "src/shp2sqlite/getopt.c",
+    "src/shp2sqlite/getopt.h",
+    "src/shp2sqlite/shapefil.h",
+    "src/shp2sqlite/shp2sqlite.c",
+    "src/shp2sqlite/shpopen.c",
+    "tests/address.rb",
+    "tests/benchmark.rb",
+    "tests/constants.rb",
+    "tests/data/address-sample.csv",
+    "tests/data/db-test.csv",
+    "tests/data/locations.csv",
+    "tests/database.rb",
+    "tests/generate.rb",
+    "tests/numbers.rb",
+    "tests/run.rb"
+  ]
+  s.homepage = "http://github.com/kornypoet/geo_coder"
+  s.licenses = ["MIT"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = "1.8.10"
+  s.summary = "Geocoder based upon the Geocommons Geocoder."
+
+  if s.respond_to? :specification_version then
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+      s.add_runtime_dependency(%q<sqlite3-ruby>, ["= 1.2.5"])
+      s.add_runtime_dependency(%q<text>, [">= 0"])
+      s.add_development_dependency(%q<bundler>, ["~> 1.0.0"])
+      s.add_development_dependency(%q<jeweler>, ["~> 1.6.4"])
+      s.add_development_dependency(%q<rcov>, [">= 0"])
+      s.add_development_dependency(%q<rspec>, [">= 0"])
+    else
+      s.add_dependency(%q<sqlite3-ruby>, ["= 1.2.5"])
+      s.add_dependency(%q<text>, [">= 0"])
+      s.add_dependency(%q<bundler>, ["~> 1.0.0"])
+      s.add_dependency(%q<jeweler>, ["~> 1.6.4"])
+      s.add_dependency(%q<rcov>, [">= 0"])
+      s.add_dependency(%q<rspec>, [">= 0"])
+    end
+  else
+    s.add_dependency(%q<sqlite3-ruby>, ["= 1.2.5"])
+    s.add_dependency(%q<text>, [">= 0"])
+    s.add_dependency(%q<bundler>, ["~> 1.0.0"])
+    s.add_dependency(%q<jeweler>, ["~> 1.6.4"])
+    s.add_dependency(%q<rcov>, [">= 0"])
+    s.add_dependency(%q<rspec>, [">= 0"])
+  end
+end
+

data/lib/geocoder/us.rb

@@ -0,0 +1,21 @@
+require "geocoder/us/database"
+require "geocoder/us/address"
+
+# Imports the Geocoder::US::Database and Geocoder::US::Address
+# modules.
+#
+# General usage is as follows:
+#
+#  >> require 'geocoder/us'
+#  >> db = Geocoder::US::Database.new("/opt/tiger/geocoder.db")
+#  >> p db.geocode("1600 Pennsylvania Av, Washington DC")
+#
+#  [{:pretyp=>"", :street=>"Pennsylvania", :sufdir=>"NW", :zip=>"20502",
+#    :lon=>-77.037528, :number=>"1600", :fips_county=>"11001", :predir=>"",
+#    :precision=>:range, :city=>"Washington", :lat=>38.898746, :suftyp=>"Ave",
+#    :state=>"DC", :prequal=>"", :sufqual=>"", :score=>0.906, :prenum=>""}]
+#
+# See Geocoder::US::Database and README.txt for more details.
+module Geocoder::US
+  VERSION = "2.0.0"
+end