Merge pull request #22 from rajbot/master

Add Vagrantfile

.gitignore

@@ -37,3 +37,5 @@ nosetests.xml
 
 # Other
 globalwb.py
+
+.vagrant

README.md

@@ -58,17 +58,39 @@ To start a pywb with sample data
 2. Install with `python setup.py install`
 
 3. Run pywb by via script `run.sh` (script currently assumes a default python and uwsgi install, feel free to edit as needed)
- 
+
 4. Test pywb in your browser!  (pywb is set to run on port 8080 by default.)
 
 
 If everything worked, the following pages should be loading (served from *sample_archive* dir):
 
 | Original Url       | Latest Capture  | List of All Captures    |
-| -------------      | -------------   | ----------------------- |         
+| -------------      | -------------   | ----------------------- |
 | `http://example.com` | [http://localhost:8080/pywb/example.com](http://localhost:8080/pywb/example.com) | [http://localhost:8080/pywb/*/example.com](http://localhost:8080/pywb/*/example.com) |
 | `http://iana.org`    | [http://localhost:8080/pywb/iana.org](http://localhost:8080/pywb/iana.org) | [http://localhost:8080/pywb/*/iana.org](http://localhost:8080/pywb/*/iana.org) |
 
+
+### Vagrant
+
+pywb comes with a Vagrantfile to help you set up a VM quickly for testing.
+If you have [Vagrant](http://www.vagrantup.com/) and [VirtualBox](https://www.virtualbox.org/)
+installed, then you can start a test instance of pywb like so:
+
+```bash
+git clone https://github.com/ikreymer/pywb.git
+cd pywb
+vagrant up
+```
+
+After pywb and all its dependencies are installed, the uwsgi server will start up and you should see:
+
+```
+spawned uWSGI worker 1 (and the only) (pid: 123, cores: 1)
+```
+
+At this point, you can open a web browser and navigate to `http://localhost:8080` for testing.
+
+
 ### Automated Tests
 
 Currently pywb consists of numerous doctests against the sample archive.
@@ -129,8 +151,8 @@ the location of those files.
 
 #### SURT
 
-By default, pywb expects the cdx files to be Sort-Friendly-Url-Transform (SURT) ordering. 
-This is an ordering that transforms: `example.com` -> `com,example)/` to faciliate better search. 
+By default, pywb expects the cdx files to be Sort-Friendly-Url-Transform (SURT) ordering.
+This is an ordering that transforms: `example.com` -> `com,example)/` to faciliate better search.
 It is recommended for future indexing, but is not required.
 
 Non-SURT ordered cdx indexs will work as well, but be sure to specify:
@@ -164,7 +186,7 @@ The directions are for running in a shell:
 
 4. Ensure sort order set to byte-order `export LC_ALL=C` to ensure proper sorting.
 
-5. From the directory of the warc(s), run `<FULL PATH>/warctools/hanzo/cdx_writer mypath/warcs/mywarc.gz | sort > mypath/cdx/mywarc.cdx` 
+5. From the directory of the warc(s), run `<FULL PATH>/warctools/hanzo/cdx_writer mypath/warcs/mywarc.gz | sort > mypath/cdx/mywarc.cdx`
 
    This will create a sorted `mywarc.cdx` for `mywarc.gz`. Then point `pywb` to the `mypath/warcs` and `mypath/cdx` directories in the yaml config.
 

Vagrantfile

@@ -0,0 +1,137 @@
+# -*- mode: ruby -*-
+# vi: set ft=ruby :
+
+$script = <<SCRIPT
+apt-get update
+apt-get install -y python-dev
+apt-get install -y git
+apt-get install -y python-pip
+pip install virtualenv
+sudo -u vagrant virtualenv pywb_env
+echo Installing pywb and dependencies via pip... This may take a while.
+if [ ! -d pywb ]; then
+    git clone https://github.com/ikreymer/pywb.git;
+fi;
+cd pywb
+sudo -u vagrant ../pywb_env/bin/pip install .
+sudo -u vagrant -H sh -c ". ../pywb_env/bin/activate; ./run.sh"
+SCRIPT
+
+# Vagrantfile API/syntax version. Don't touch unless you know what you're doing!
+VAGRANTFILE_API_VERSION = "2"
+
+Vagrant.configure(VAGRANTFILE_API_VERSION) do |config|
+  # All Vagrant configuration is done here. The most common configuration
+  # options are documented and commented below. For a complete reference,
+  # please see the online documentation at vagrantup.com.
+
+  # Every Vagrant virtual environment requires a box to build off of.
+  config.vm.box = "precise32"
+
+  # The url from where the 'config.vm.box' box will be fetched if it
+  # doesn't already exist on the user's system.
+  config.vm.box_url = "http://files.vagrantup.com/precise32.box"
+
+  config.vm.provision "shell", inline: $script
+
+  # Create a forwarded port mapping which allows access to a specific port
+  # within the machine from a port on the host machine. In the example below,
+  # accessing "localhost:8080" will access port 80 on the guest machine.
+  # config.vm.network :forwarded_port, guest: 80, host: 8080
+  config.vm.network :forwarded_port, guest: 8080, host: 8080
+
+  # Create a private network, which allows host-only access to the machine
+  # using a specific IP.
+  # config.vm.network :private_network, ip: "192.168.33.10"
+
+  # Create a public network, which generally matched to bridged network.
+  # Bridged networks make the machine appear as another physical device on
+  # your network.
+  # config.vm.network :public_network
+
+  # If true, then any SSH connections made will enable agent forwarding.
+  # Default value: false
+  # config.ssh.forward_agent = true
+
+  # Share an additional folder to the guest VM. The first argument is
+  # the path on the host to the actual folder. The second argument is
+  # the path on the guest to mount the folder. And the optional third
+  # argument is a set of non-required options.
+  # config.vm.synced_folder "../data", "/vagrant_data"
+
+  # Provider-specific configuration so you can fine-tune various
+  # backing providers for Vagrant. These expose provider-specific options.
+  # Example for VirtualBox:
+  #
+  # config.vm.provider :virtualbox do |vb|
+  #   # Don't boot with headless mode
+  #   vb.gui = true
+  #
+  #   # Use VBoxManage to customize the VM. For example to change memory:
+  #   vb.customize ["modifyvm", :id, "--memory", "1024"]
+  # end
+  #
+  # View the documentation for the provider you're using for more
+  # information on available options.
+
+  # Enable provisioning with Puppet stand alone.  Puppet manifests
+  # are contained in a directory path relative to this Vagrantfile.
+  # You will need to create the manifests directory and a manifest in
+  # the file precise32.pp in the manifests_path directory.
+  #
+  # An example Puppet manifest to provision the message of the day:
+  #
+  # # group { "puppet":
+  # #   ensure => "present",
+  # # }
+  # #
+  # # File { owner => 0, group => 0, mode => 0644 }
+  # #
+  # # file { '/etc/motd':
+  # #   content => "Welcome to your Vagrant-built virtual machine!
+  # #               Managed by Puppet.\n"
+  # # }
+  #
+  # config.vm.provision :puppet do |puppet|
+  #   puppet.manifests_path = "manifests"
+  #   puppet.manifest_file  = "site.pp"
+  # end
+
+  # Enable provisioning with chef solo, specifying a cookbooks path, roles
+  # path, and data_bags path (all relative to this Vagrantfile), and adding
+  # some recipes and/or roles.
+  #
+  # config.vm.provision :chef_solo do |chef|
+  #   chef.cookbooks_path = "../my-recipes/cookbooks"
+  #   chef.roles_path = "../my-recipes/roles"
+  #   chef.data_bags_path = "../my-recipes/data_bags"
+  #   chef.add_recipe "mysql"
+  #   chef.add_role "web"
+  #
+  #   # You may also specify custom JSON attributes:
+  #   chef.json = { :mysql_password => "foo" }
+  # end
+
+  # Enable provisioning with chef server, specifying the chef server URL,
+  # and the path to the validation key (relative to this Vagrantfile).
+  #
+  # The Opscode Platform uses HTTPS. Substitute your organization for
+  # ORGNAME in the URL and validation key.
+  #
+  # If you have your own Chef Server, use the appropriate URL, which may be
+  # HTTP instead of HTTPS depending on your configuration. Also change the
+  # validation key to validation.pem.
+  #
+  # config.vm.provision :chef_client do |chef|
+  #   chef.chef_server_url = "https://api.opscode.com/organizations/ORGNAME"
+  #   chef.validation_key_path = "ORGNAME-validator.pem"
+  # end
+  #
+  # If you're using the Opscode platform, your validator client is
+  # ORGNAME-validator, replacing ORGNAME with your organization name.
+  #
+  # If you have your own Chef Server, the default validation client name is
+  # chef-validator, unless you changed the configuration.
+  #
+  #   chef.validation_client_name = "ORGNAME-validator"
+end