From 1fe5de86c5a7f215b03bb44069700a65aae78dc1 Mon Sep 17 00:00:00 2001
From: Jack Reed <pjreed@stanford.edu>
Date: Sat, 31 Jan 2015 15:09:39 -0800
Subject: [PATCH] adds in basic tasks for harvesting opengeometadata

---
 README.md                  | 28 +++++++++++++++++++++++++---
 Rakefile                   |  3 ++-
 geo_combine.gemspec        | 10 ++++++----
 lib/geo_combine.rb         |  6 ++++--
 lib/geo_combine/version.rb |  2 +-
 lib/tasks/geo_combine.rake | 36 ++++++++++++++++++++++++++++++++++++
 6 files changed, 74 insertions(+), 11 deletions(-)
 create mode 100644 lib/tasks/geo_combine.rake

diff --git a/README.md b/README.md
index df3b753..f13fdbe 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,6 @@
 # GeoCombine
 
-TODO: Write a gem description
+A Ruby toolkit for managing geospatial metadata
 
 ## Installation
 
@@ -20,11 +20,33 @@ Or install it yourself as:
 
 ## Usage
 
-TODO: Write usage instructions here
+### Clone all OpenGeoMetadata repositories
+
+```sh
+$ rake geocombine:clone
+```
+
+Will clone all edu.* OpenGeoMetadata repositories into `./tmp`
+
+### Pull all OpenGeoMetadata repositories
+
+```sh
+$ rake geocombine:pull
+```
+
+Runs `git pull origin master` on all cloned repositories in `./tmp`
+
+### Index all of the GeoBlacklight documents
+
+```sh
+$ rake geocombine:index
+```
+
+Indexs all of the `geoblacklight.xml` files in cloned repositories to a Solr index running at http://127.0.0.1:8983/solr
 
 ## Contributing
 
-1. Fork it ( https://github.com/[my-github-username]/geo_combine/fork )
+1. Fork it ( https://github.com/[my-github-username]/GeoCombine/fork )
 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`)
diff --git a/Rakefile b/Rakefile
index 809eb56..3571bb3 100644
--- a/Rakefile
+++ b/Rakefile
@@ -1,2 +1,3 @@
-require "bundler/gem_tasks"
+require 'bundler/gem_tasks'
 
+Dir.glob('lib/tasks/*.rake').each { |r| load r}
diff --git a/geo_combine.gemspec b/geo_combine.gemspec
index 096e1b3..1b70516 100644
--- a/geo_combine.gemspec
+++ b/geo_combine.gemspec
@@ -6,18 +6,20 @@ require 'geo_combine/version'
 Gem::Specification.new do |spec|
   spec.name          = "geo_combine"
   spec.version       = GeoCombine::VERSION
-  spec.authors       = ["TODO: Write your name"]
+  spec.authors       = ["Jack Reed"]
   spec.email         = ["pjreed@stanford.edu"]
-  spec.summary       = %q{TODO: Write a short summary. Required.}
-  spec.description   = %q{TODO: Write a longer description. Optional.}
+  spec.summary       = %q{A Ruby toolkit for managing geospatial metadata}
+  spec.description   = %q{A Ruby toolkit for managing geospatial metadata}
   spec.homepage      = ""
-  spec.license       = "MIT"
+  spec.license       = "Apache"
 
   spec.files         = `git ls-files -z`.split("\x0")
   spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
   spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
   spec.require_paths = ["lib"]
 
+  spec.add_dependency 'rsolr'
+
   spec.add_development_dependency "bundler", "~> 1.7"
   spec.add_development_dependency "rake", "~> 10.0"
 end
diff --git a/lib/geo_combine.rb b/lib/geo_combine.rb
index 8d536ac..1f92037 100644
--- a/lib/geo_combine.rb
+++ b/lib/geo_combine.rb
@@ -1,5 +1,7 @@
-require "geo_combine/version"
+require 'geo_combine/version'
 
 module GeoCombine
-  # Your code goes here...
+
 end
+
+load File.expand_path('../tasks/geo_combine.rake', __FILE__)
diff --git a/lib/geo_combine/version.rb b/lib/geo_combine/version.rb
index c2b1690..c4bee73 100644
--- a/lib/geo_combine/version.rb
+++ b/lib/geo_combine/version.rb
@@ -1,3 +1,3 @@
 module GeoCombine
-  VERSION = "0.0.1"
+  VERSION = '0.0.1'
 end
diff --git a/lib/tasks/geo_combine.rake b/lib/tasks/geo_combine.rake
new file mode 100644
index 0000000..4ff4585
--- /dev/null
+++ b/lib/tasks/geo_combine.rake
@@ -0,0 +1,36 @@
+require 'find'
+require 'net/http'
+require 'json'
+require 'rsolr'
+
+namespace :geocombine do
+  desc 'Clone all OpenGeoMetadata repositories'
+  task :clone do
+    ogm_api_uri = URI('https://api.github.com/orgs/opengeometadata/repos')
+    ogm_repos = JSON.parse(Net::HTTP.get(ogm_api_uri)).map{ |repo| repo['git_url']}
+    ogm_repos.each do |repo|
+      if repo =~ /^git:\/\/github.com\/OpenGeoMetadata\/edu.*/
+        system "cd tmp && git clone #{repo}"
+      end
+    end
+  end
+  desc '"git pull" OpenGeoMetadata repositories'
+  task :pull do
+    Dir.glob('tmp/*').map{ |dir| system "cd #{dir} && git pull origin master" if dir =~ /.*edu.*./ }
+  end
+  desc 'Index all of the GeoBlacklight documents'
+  task :index do
+    solr = RSolr.connect :url => 'http://127.0.0.1:8983/solr'
+    Find.find('tmp') do |path|
+      if path =~ /.*geoblacklight.xml$/
+        doc = File.read(path)
+        begin
+          solr.update data: doc
+          solr.commit
+        rescue RSolr::Error::Http => error
+          puts error
+        end
+      end
+    end
+  end
+end