shp2geocouch 0.0.8 → 0.0.9

data/README.textile

@@ -4,7 +4,9 @@ This is an executable rubygem that creates "GeoCouch":http://www.github.com/vmx/
 
 h2. Installation
 
-You will need access to a GeoCouch server. For instructions on setting up your own local GeoCouch, check out "my related blog post":http://maxogden.com/#/2010-08-14-loading-shapefiles-into-geocouch.html.
+This has been verified to work on Unix/MacOSX. Your mileage may vary if you are on Windows.
+
+You will need access to a GeoCouch server. For instructions on setting up your own local GeoCouch, check out "my related blog post":http://maxogden.com/#/blog/installing-geocouch. The easiest way to get GeoCouch is the "binary distribution from Couchbase":http://www.couchbase.com/downloads.
 
 Install dependencies:
 @unzip@, @sed@, @ogr2ogr@
@@ -26,10 +28,12 @@ h2. Usage
 @shp2geocouch <path_to_shapefile> [geocouch-url (optional, default: http://localhost:5984/zip_filename)]@
 
 example: @shp2geocouch /sweet_geo_data/Portland_Oregon_Public_Libraries.shp@
-another possible example: @shp2geocouch /zipped_shapfiles/US_Railroads.zip http://myusername.couchone.com/railroads@
+another possible example: @shp2geocouch /zipped_shapfiles/US_Railroads.zip http://admin:password@helloworld.couchone.com/railroads@
 
 Once completed, you can run bounding box queries against your data! Visit the following link to receive a dump of your entire dataset as GeoJSON (a bounding box that covers the entire planet):
-@http://localhost:5984/your_db_name/_design/geojson/_spatial/points?bbox=-180,-90,180,90@
+@http://localhost:5984/your_db_name/_design/geo/_spatial/ful?bbox=-180,-90,180,90@
+
+@shp2geocouch@ will try to install "geocouch-utils":http://github.com/maxogden/geocouch-utils into your database by replicating it from "my public couch":http://max.couchone.com/apps/_design/geo. @geocouch-utils@ includes a basic web based map browser that will allow you to view the data from your Shapefile.
 
 If you uploaded a large dataset, you may experience a delay on the first ever spatial query as GeoCouch builds it's spatial index. You can check the status of the indexer by visiting @http://localhost:5984/_utils/status.html@
 
@@ -39,6 +43,7 @@ h3. Arguments:
 * @-v@ for verbose
 * @--no-cleanup@ if you want @shp2geocouch@ to leave you a copy of unzipped Shapefile and converted JSON.
 * @--chunksize@ to customize the number of docs that it sends in each PUT to CouchDB's @_bulk_docs@ interface (default is 50)
+* @-i@ to set the CouchDB IDs (@_id@) based on the given column in the Shapefile. The column is assumed to be unique; no error checking is performed.
 
 h2. What?
 

data/bin/shp2geocouch

@@ -1,13 +1,16 @@
 #!/usr/bin/env ruby
+
+require 'rubygems'
 require 'httparty'
 require 'couchrest'
 require 'optparse'
 require 'iconv'
 require 'net/http'
 require 'uri'
+require 'json'
 
 class ShapefileToGeoCouch
-  attr_accessor :path, :extension, :name, :database_url, :cleanup, :verbose, :chunksize, :uri
+  attr_accessor :path, :extension, :name, :database_url, :cleanup, :verbose, :chunksize, :uri, :id
   
   def initialize(options)
     set_accessors(options)
@@ -78,19 +81,40 @@ class ShapefileToGeoCouch
     %x!ogr2ogr -t_srs EPSG:4326 -a_srs EPSG:4326 -f "GeoJSON" #{json} #{shapefile}!
     puts "Reformatting json for bulk import, saving as #{bulk}..." if @verbose
     %x!sed -e '/^\"type\": \"FeatureCollection\",$/d' -e '/^\"features\": \\[$/d' -e '/^{$/d' -e '/^,$/d' -e '/^}$/d' -e '/^]$/d' -e '/^$/d' -e 's/$/,/' #{json} > #{bulk}!
+
+    # the user wants to use a predefined ID field
+    if @id
+      puts "Inserting _id attributes based on col '#{id}'"
+    end
   end
-  
+
   def post(string)
     ic = Iconv.new('UTF-8//IGNORE', 'UTF-8') # disregard all UTF8 characters
     valid_string = ic.iconv(string[0..-3] + '  ')[0..-3] # http://po-ru.com/diary/fixing-invalid-utf-8-in-ruby-revisited/
-    HTTParty.post(@database_url + '/_bulk_docs', :body => '{"docs": [' + valid_string + "]}", :headers => {'content-type' => "application/json"})
+    body = '{"docs": [' + valid_string + ']}'
+    HTTParty.post(@database_url + '/_bulk_docs', :body => body, :headers => {'content-type' => "application/json"})
   end
-  
+
   def upload
     puts "Bulk loading data into GeoCouch... view progress at #{couch_url}/_utils" if @verbose
     group = []
     length = File.open(bulk).lines.count - 1
     File.open(bulk).each_with_index do |line, index|
+      # check that the line is non-blank and not invalid JSON (e.g. rogue
+      # punctuation characters)
+      stripped_line = line.strip
+      if stripped_line.empty? or stripped_line == ","
+        next
+      end
+      # create an _id attr if requested
+      if @id
+        # The slice is to get rid of ,\n at the end of the line
+        parsedLine = JSON.parse(line[0...-2])
+        # Cast it to a string, so that Couch will take an integer id
+        parsedLine['_id'] = parsedLine['properties'][@id].to_s
+        line = parsedLine.to_json + ",\n"
+      end
+
       if (index % @chunksize == 0)
         post(group.join(''))
         group = [line]
@@ -155,11 +179,16 @@ OptionParser.new do |opts|
   opts.on('-v') do |v|
     defaults[:verbose] = true
   end
+
+  opts.on('-i [ID]', 'ID column to use for the database load') do |id|
+    defaults[:id] = id
+  end
 end.parse!
 
 raise "You must specify a Shapefile to convert." if ARGV[0].nil?
 
-extension = ARGV[0].split('.')[1]
+# Use -1, not 1, in case user has specified ../
+extension = ARGV[0].split('.')[-1]
 raise "You must specify a .shp or a .zip" unless extension =~ /zip|shp/i
 
 name = ARGV[0].split('/')[-1].split('.')[0]
@@ -167,4 +196,4 @@ name = ARGV[0].split('/')[-1].split('.')[0]
 options = {:path => ARGV[0], :extension => extension}.merge(defaults)
 options[:database_url] = ARGV[1] || "http://localhost:5984/#{name.downcase}"
 
-ShapefileToGeoCouch.new(options)
+ShapefileToGeoCouch.new(options)

data/shp2geocouch.gemspec

@@ -5,7 +5,7 @@
 
 Gem::Specification.new do |s|
   s.name = %q{shp2geocouch}
-  s.version = "0.0.8"
+  s.version = "0.0.9"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Max Ogden"]

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: shp2geocouch
 version: !ruby/object:Gem::Version 
-  hash: 15
+  hash: 13
   prerelease: 
   segments: 
   - 0
   - 0
-  - 8
-  version: 0.0.8
+  - 9
+  version: 0.0.9
 platform: ruby
 authors: 
 - Max Ogden
@@ -15,8 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-04-23 00:00:00 -07:00
-default_executable: shp2geocouch
+date: 2011-04-23 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: httparty
@@ -63,7 +62,6 @@ files:
 - bin/shp2geocouch
 - pkg/shp2geocouch-0.0.8.gem
 - shp2geocouch.gemspec
-has_rdoc: true
 homepage: http://github.com/maxogden/shp2geocouch
 licenses: []
 
@@ -93,9 +91,10 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.4.2
+rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
 summary: rubygem that converts Shapefiles into GeoCouch databases
 test_files: []
 
+has_rdoc: